1333 files changed, 44236 insertions, 24272 deletions
diff --git a/.mailmap b/.mailmap
index fd6219293057..e7f0341a6dbf 100644
--- a/.mailmap
+++ b/.mailmap
@@ -32,6 +32,7 @@ Andy Adamson <andros@citi.umich.edu>
 Antoine Tenart <antoine.tenart@free-electrons.com>
 Antonio Ospite <ao2@ao2.it> <ao2@amarulasolutions.com>
 Archit Taneja <archit@ti.com>
+Ard Biesheuvel <ardb@kernel.org> <ard.biesheuvel@linaro.org>
 Arnaud Patard <arnaud.patard@rtp-net.org>
 Arnd Bergmann <arnd@arndb.de>
 Axel Dyks <xl@xlsigned.net>
diff --git a/Documentation/RCU/Design/Data-Structures/Data-Structures.html b/Documentation/RCU/Design/Data-Structures/Data-Structures.html
deleted file mode 100644
index c30c1957c7e6..000000000000
--- a/Documentation/RCU/Design/Data-Structures/Data-Structures.html
+++ /dev/null
@@ -1,1391 +0,0 @@
-<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN"
-        "http://www.w3.org/TR/html4/loose.dtd">
-        <html>
-        <head><title>A Tour Through TREE_RCU's Data Structures [LWN.net]</title>
-        <meta HTTP-EQUIV="Content-Type" CONTENT="text/html; charset=iso-8859-1">
-
-           <p>December 18, 2016</p>
-           <p>This article was contributed by Paul E.&nbsp;McKenney</p>
-
-<h3>Introduction</h3>
-
-This document describes RCU's major data structures and their relationship
-to each other.
-
-<ol>
-<li>	<a href="#Data-Structure Relationships">
-	Data-Structure Relationships</a>
-<li>	<a href="#The rcu_state Structure">
-	The <tt>rcu_state</tt> Structure</a>
-<li>	<a href="#The rcu_node Structure">
-	The <tt>rcu_node</tt> Structure</a>
-<li>	<a href="#The rcu_segcblist Structure">
-	The <tt>rcu_segcblist</tt> Structure</a>
-<li>	<a href="#The rcu_data Structure">
-	The <tt>rcu_data</tt> Structure</a>
-<li>	<a href="#The rcu_head Structure">
-	The <tt>rcu_head</tt> Structure</a>
-<li>	<a href="#RCU-Specific Fields in the task_struct Structure">
-	RCU-Specific Fields in the <tt>task_struct</tt> Structure</a>
-<li>	<a href="#Accessor Functions">
-	Accessor Functions</a>
-</ol>
-
-<h3><a name="Data-Structure Relationships">Data-Structure Relationships</a></h3>
-
-<p>RCU is for all intents and purposes a large state machine, and its
-data structures maintain the state in such a way as to allow RCU readers
-to execute extremely quickly, while also processing the RCU grace periods
-requested by updaters in an efficient and extremely scalable fashion.
-The efficiency and scalability of RCU updaters is provided primarily
-by a combining tree, as shown below:
-
-</p><p><img src="BigTreeClassicRCU.svg" alt="BigTreeClassicRCU.svg" width="30%">
-
-</p><p>This diagram shows an enclosing <tt>rcu_state</tt> structure
-containing a tree of <tt>rcu_node</tt> structures.
-Each leaf node of the <tt>rcu_node</tt> tree has up to 16
-<tt>rcu_data</tt> structures associated with it, so that there
-are <tt>NR_CPUS</tt> number of <tt>rcu_data</tt> structures,
-one for each possible CPU.
-This structure is adjusted at boot time, if needed, to handle the
-common case where <tt>nr_cpu_ids</tt> is much less than
-<tt>NR_CPUs</tt>.
-For example, a number of Linux distributions set <tt>NR_CPUs=4096</tt>,
-which results in a three-level <tt>rcu_node</tt> tree.
-If the actual hardware has only 16 CPUs, RCU will adjust itself
-at boot time, resulting in an <tt>rcu_node</tt> tree with only a single node.
-
-</p><p>The purpose of this combining tree is to allow per-CPU events
-such as quiescent states, dyntick-idle transitions,
-and CPU hotplug operations to be processed efficiently
-and scalably.
-Quiescent states are recorded by the per-CPU <tt>rcu_data</tt> structures,
-and other events are recorded by the leaf-level <tt>rcu_node</tt>
-structures.
-All of these events are combined at each level of the tree until finally
-grace periods are completed at the tree's root <tt>rcu_node</tt>
-structure.
-A grace period can be completed at the root once every CPU
-(or, in the case of <tt>CONFIG_PREEMPT_RCU</tt>, task)
-has passed through a quiescent state.
-Once a grace period has completed, record of that fact is propagated
-back down the tree.
-
-</p><p>As can be seen from the diagram, on a 64-bit system
-a two-level tree with 64 leaves can accommodate 1,024 CPUs, with a fanout
-of 64 at the root and a fanout of 16 at the leaves.
-
-<table>
-<tr><th>&nbsp;</th></tr>
-<tr><th align="left">Quick Quiz:</th></tr>
-<tr><td>
-	Why isn't the fanout at the leaves also 64?
-</td></tr>
-<tr><th align="left">Answer:</th></tr>
-<tr><td bgcolor="#ffffff"><font color="ffffff">
-	Because there are more types of events that affect the leaf-level
-	<tt>rcu_node</tt> structures than further up the tree.
-	Therefore, if the leaf <tt>rcu_node</tt> structures have fanout of
-	64, the contention on these structures' <tt>-&gt;structures</tt>
-	becomes excessive.
-	Experimentation on a wide variety of systems has shown that a fanout
-	of 16 works well for the leaves of the <tt>rcu_node</tt> tree.
-	</font>
-
-	<p><font color="ffffff">Of course, further experience with
-	systems having hundreds or thousands of CPUs may demonstrate
-	that the fanout for the non-leaf <tt>rcu_node</tt> structures
-	must also be reduced.
-	Such reduction can be easily carried out when and if it proves
-	necessary.
-	In the meantime, if you are using such a system and running into
-	contention problems on the non-leaf <tt>rcu_node</tt> structures,
-	you may use the <tt>CONFIG_RCU_FANOUT</tt> kernel configuration
-	parameter to reduce the non-leaf fanout as needed.
-	</font>
-
-	<p><font color="ffffff">Kernels built for systems with
-	strong NUMA characteristics might also need to adjust
-	<tt>CONFIG_RCU_FANOUT</tt> so that the domains of the
-	<tt>rcu_node</tt> structures align with hardware boundaries.
-	However, there has thus far been no need for this.
-</font></td></tr>
-<tr><td>&nbsp;</td></tr>
-</table>
-
-<p>If your system has more than 1,024 CPUs (or more than 512 CPUs on
-a 32-bit system), then RCU will automatically add more levels to the
-tree.
-For example, if you are crazy enough to build a 64-bit system with 65,536
-CPUs, RCU would configure the <tt>rcu_node</tt> tree as follows:
-
-</p><p><img src="HugeTreeClassicRCU.svg" alt="HugeTreeClassicRCU.svg" width="50%">
-
-</p><p>RCU currently permits up to a four-level tree, which on a 64-bit system
-accommodates up to 4,194,304 CPUs, though only a mere 524,288 CPUs for
-32-bit systems.
-On the other hand, you can set both <tt>CONFIG_RCU_FANOUT</tt> and
-<tt>CONFIG_RCU_FANOUT_LEAF</tt> to be as small as 2, which would result
-in a 16-CPU test using a 4-level tree.
-This can be useful for testing large-system capabilities on small test
-machines.
-
-</p><p>This multi-level combining tree allows us to get most of the
-performance and scalability
-benefits of partitioning, even though RCU grace-period detection is
-inherently a global operation.
-The trick here is that only the last CPU to report a quiescent state
-into a given <tt>rcu_node</tt> structure need advance to the <tt>rcu_node</tt>
-structure at the next level up the tree.
-This means that at the leaf-level <tt>rcu_node</tt> structure, only
-one access out of sixteen will progress up the tree.
-For the internal <tt>rcu_node</tt> structures, the situation is even
-more extreme:  Only one access out of sixty-four will progress up
-the tree.
-Because the vast majority of the CPUs do not progress up the tree,
-the lock contention remains roughly constant up the tree.
-No matter how many CPUs there are in the system, at most 64 quiescent-state
-reports per grace period will progress all the way to the root
-<tt>rcu_node</tt> structure, thus ensuring that the lock contention
-on that root <tt>rcu_node</tt> structure remains acceptably low.
-
-</p><p>In effect, the combining tree acts like a big shock absorber,
-keeping lock contention under control at all tree levels regardless
-of the level of loading on the system.
-
-</p><p>RCU updaters wait for normal grace periods by registering
-RCU callbacks, either directly via <tt>call_rcu()</tt>
-or indirectly via <tt>synchronize_rcu()</tt> and friends.
-RCU callbacks are represented by <tt>rcu_head</tt> structures,
-which are queued on <tt>rcu_data</tt> structures while they are
-waiting for a grace period to elapse, as shown in the following figure:
-
-</p><p><img src="BigTreePreemptRCUBHdyntickCB.svg" alt="BigTreePreemptRCUBHdyntickCB.svg" width="40%">
-
-</p><p>This figure shows how <tt>TREE_RCU</tt>'s and
-<tt>PREEMPT_RCU</tt>'s major data structures are related.
-Lesser data structures will be introduced with the algorithms that
-make use of them.
-
-</p><p>Note that each of the data structures in the above figure has
-its own synchronization:
-
-<p><ol>
-<li>	Each <tt>rcu_state</tt> structures has a lock and a mutex,
-	and some fields are protected by the corresponding root
-	<tt>rcu_node</tt> structure's lock.
-<li>	Each <tt>rcu_node</tt> structure has a spinlock.
-<li>	The fields in <tt>rcu_data</tt> are private to the corresponding
-	CPU, although a few can be read and written by other CPUs.
-</ol>
-
-<p>It is important to note that different data structures can have
-very different ideas about the state of RCU at any given time.
-For but one example, awareness of the start or end of a given RCU
-grace period propagates slowly through the data structures.
-This slow propagation is absolutely necessary for RCU to have good
-read-side performance.
-If this balkanized implementation seems foreign to you, one useful
-trick is to consider each instance of these data structures to be
-a different person, each having the usual slightly different
-view of reality.
-
-</p><p>The general role of each of these data structures is as
-follows:
-
-</p><ol>
-<li>	<tt>rcu_state</tt>:
-	This structure forms the interconnection between the
-	<tt>rcu_node</tt> and <tt>rcu_data</tt> structures,
-	tracks grace periods, serves as short-term repository
-	for callbacks orphaned by CPU-hotplug events,
-	maintains <tt>rcu_barrier()</tt> state,
-	tracks expedited grace-period state,
-	and maintains state used to force quiescent states when
-	grace periods extend too long,
-<li>	<tt>rcu_node</tt>: This structure forms the combining
-	tree that propagates quiescent-state
-	information from the leaves to the root, and also propagates
-	grace-period information from the root to the leaves.
-	It provides local copies of the grace-period state in order
-	to allow this information to be accessed in a synchronized
-	manner without suffering the scalability limitations that
-	would otherwise be imposed by global locking.
-	In <tt>CONFIG_PREEMPT_RCU</tt> kernels, it manages the lists
-	of tasks that have blocked while in their current
-	RCU read-side critical section.
-	In <tt>CONFIG_PREEMPT_RCU</tt> with
-	<tt>CONFIG_RCU_BOOST</tt>, it manages the
-	per-<tt>rcu_node</tt> priority-boosting
-	kernel threads (kthreads) and state.
-	Finally, it records CPU-hotplug state in order to determine
-	which CPUs should be ignored during a given grace period.
-<li>	<tt>rcu_data</tt>: This per-CPU structure is the
-	focus of quiescent-state detection and RCU callback queuing.
-	It also tracks its relationship to the corresponding leaf
-	<tt>rcu_node</tt> structure to allow more-efficient
-	propagation of quiescent states up the <tt>rcu_node</tt>
-	combining tree.
-	Like the <tt>rcu_node</tt> structure, it provides a local
-	copy of the grace-period information to allow for-free
-	synchronized
-	access to this information from the corresponding CPU.
-	Finally, this structure records past dyntick-idle state
-	for the corresponding CPU and also tracks statistics.
-<li>	<tt>rcu_head</tt>:
-	This structure represents RCU callbacks, and is the
-	only structure allocated and managed by RCU users.
-	The <tt>rcu_head</tt> structure is normally embedded
-	within the RCU-protected data structure.
-</ol>
-
-<p>If all you wanted from this article was a general notion of how
-RCU's data structures are related, you are done.
-Otherwise, each of the following sections give more details on
-the <tt>rcu_state</tt>, <tt>rcu_node</tt> and <tt>rcu_data</tt> data
-structures.
-
-<h3><a name="The rcu_state Structure">
-The <tt>rcu_state</tt> Structure</a></h3>
-
-<p>The <tt>rcu_state</tt> structure is the base structure that
-represents the state of RCU in the system.
-This structure forms the interconnection between the
-<tt>rcu_node</tt> and <tt>rcu_data</tt> structures,
-tracks grace periods, contains the lock used to
-synchronize with CPU-hotplug events,
-and maintains state used to force quiescent states when
-grace periods extend too long,
-
-</p><p>A few of the <tt>rcu_state</tt> structure's fields are discussed,
-singly and in groups, in the following sections.
-The more specialized fields are covered in the discussion of their
-use.
-
-<h5>Relationship to rcu_node and rcu_data Structures</h5>
-
-This portion of the <tt>rcu_state</tt> structure is declared
-as follows:
-
-<pre>
-  1   struct rcu_node node[NUM_RCU_NODES];
-  2   struct rcu_node *level[NUM_RCU_LVLS + 1];
-  3   struct rcu_data __percpu *rda;
-</pre>
-
-<table>
-<tr><th>&nbsp;</th></tr>
-<tr><th align="left">Quick Quiz:</th></tr>
-<tr><td>
-	Wait a minute!
-	You said that the <tt>rcu_node</tt> structures formed a tree,
-	but they are declared as a flat array!
-	What gives?
-</td></tr>
-<tr><th align="left">Answer:</th></tr>
-<tr><td bgcolor="#ffffff"><font color="ffffff">
-	The tree is laid out in the array.
-	The first node In the array is the head, the next set of nodes in the
-	array are children of the head node, and so on until the last set of
-	nodes in the array are the leaves.
-	</font>
-
-	<p><font color="ffffff">See the following diagrams to see how
-	this works.
-</font></td></tr>
-<tr><td>&nbsp;</td></tr>
-</table>
-
-<p>The <tt>rcu_node</tt> tree is embedded into the
-<tt>-&gt;node[]</tt> array as shown in the following figure:
-
-</p><p><img src="TreeMapping.svg" alt="TreeMapping.svg" width="40%">
-
-</p><p>One interesting consequence of this mapping is that a
-breadth-first traversal of the tree is implemented as a simple
-linear scan of the array, which is in fact what the
-<tt>rcu_for_each_node_breadth_first()</tt> macro does.
-This macro is used at the beginning and ends of grace periods.
-
-</p><p>Each entry of the <tt>-&gt;level</tt> array references
-the first <tt>rcu_node</tt> structure on the corresponding level
-of the tree, for example, as shown below:
-
-</p><p><img src="TreeMappingLevel.svg" alt="TreeMappingLevel.svg" width="40%">
-
-</p><p>The zero<sup>th</sup> element of the array references the root
-<tt>rcu_node</tt> structure, the first element references the
-first child of the root <tt>rcu_node</tt>, and finally the second
-element references the first leaf <tt>rcu_node</tt> structure.
-
-</p><p>For whatever it is worth, if you draw the tree to be tree-shaped
-rather than array-shaped, it is easy to draw a planar representation:
-
-</p><p><img src="TreeLevel.svg" alt="TreeLevel.svg" width="60%">
-
-</p><p>Finally, the <tt>-&gt;rda</tt> field references a per-CPU
-pointer to the corresponding CPU's <tt>rcu_data</tt> structure.
-
-</p><p>All of these fields are constant once initialization is complete,
-and therefore need no protection.
-
-<h5>Grace-Period Tracking</h5>
-
-<p>This portion of the <tt>rcu_state</tt> structure is declared
-as follows:
-
-<pre>
-  1   unsigned long gp_seq;
-</pre>
-
-<p>RCU grace periods are numbered, and
-the <tt>-&gt;gp_seq</tt> field contains the current grace-period
-sequence number.
-The bottom two bits are the state of the current grace period,
-which can be zero for not yet started or one for in progress.
-In other words, if the bottom two bits of <tt>-&gt;gp_seq</tt> are
-zero, then RCU is idle.
-Any other value in the bottom two bits indicates that something is broken.
-This field is protected by the root <tt>rcu_node</tt> structure's
-<tt>-&gt;lock</tt> field.
-
-</p><p>There are <tt>-&gt;gp_seq</tt> fields
-in the <tt>rcu_node</tt> and <tt>rcu_data</tt> structures
-as well.
-The fields in the <tt>rcu_state</tt> structure represent the
-most current value, and those of the other structures are compared
-in order to detect the beginnings and ends of grace periods in a distributed
-fashion.
-The values flow from <tt>rcu_state</tt> to <tt>rcu_node</tt>
-(down the tree from the root to the leaves) to <tt>rcu_data</tt>.
-
-<h5>Miscellaneous</h5>
-
-<p>This portion of the <tt>rcu_state</tt> structure is declared
-as follows:
-
-<pre>
-  1   unsigned long gp_max;
-  2   char abbr;
-  3   char *name;
-</pre>
-
-<p>The <tt>-&gt;gp_max</tt> field tracks the duration of the longest
-grace period in jiffies.
-It is protected by the root <tt>rcu_node</tt>'s <tt>-&gt;lock</tt>.
-
-<p>The <tt>-&gt;name</tt> and <tt>-&gt;abbr</tt> fields distinguish
-between preemptible RCU (&ldquo;rcu_preempt&rdquo; and &ldquo;p&rdquo;)
-and non-preemptible RCU (&ldquo;rcu_sched&rdquo; and &ldquo;s&rdquo;).
-These fields are used for diagnostic and tracing purposes.
-
-<h3><a name="The rcu_node Structure">
-The <tt>rcu_node</tt> Structure</a></h3>
-
-<p>The <tt>rcu_node</tt> structures form the combining
-tree that propagates quiescent-state
-information from the leaves to the root and also that propagates
-grace-period information from the root down to the leaves.
-They provides local copies of the grace-period state in order
-to allow this information to be accessed in a synchronized
-manner without suffering the scalability limitations that
-would otherwise be imposed by global locking.
-In <tt>CONFIG_PREEMPT_RCU</tt> kernels, they manage the lists
-of tasks that have blocked while in their current
-RCU read-side critical section.
-In <tt>CONFIG_PREEMPT_RCU</tt> with
-<tt>CONFIG_RCU_BOOST</tt>, they manage the
-per-<tt>rcu_node</tt> priority-boosting
-kernel threads (kthreads) and state.
-Finally, they record CPU-hotplug state in order to determine
-which CPUs should be ignored during a given grace period.
-
-</p><p>The <tt>rcu_node</tt> structure's fields are discussed,
-singly and in groups, in the following sections.
-
-<h5>Connection to Combining Tree</h5>
-
-<p>This portion of the <tt>rcu_node</tt> structure is declared
-as follows:
-
-<pre>
-  1   struct rcu_node *parent;
-  2   u8 level;
-  3   u8 grpnum;
-  4   unsigned long grpmask;
-  5   int grplo;
-  6   int grphi;
-</pre>
-
-<p>The <tt>-&gt;parent</tt> pointer references the <tt>rcu_node</tt>
-one level up in the tree, and is <tt>NULL</tt> for the root
-<tt>rcu_node</tt>.
-The RCU implementation makes heavy use of this field to push quiescent
-states up the tree.
-The <tt>-&gt;level</tt> field gives the level in the tree, with
-the root being at level zero, its children at level one, and so on.
-The <tt>-&gt;grpnum</tt> field gives this node's position within
-the children of its parent, so this number can range between 0 and 31
-on 32-bit systems and between 0 and 63 on 64-bit systems.
-The <tt>-&gt;level</tt> and <tt>-&gt;grpnum</tt> fields are
-used only during initialization and for tracing.
-The <tt>-&gt;grpmask</tt> field is the bitmask counterpart of
-<tt>-&gt;grpnum</tt>, and therefore always has exactly one bit set.
-This mask is used to clear the bit corresponding to this <tt>rcu_node</tt>
-structure in its parent's bitmasks, which are described later.
-Finally, the <tt>-&gt;grplo</tt> and <tt>-&gt;grphi</tt> fields
-contain the lowest and highest numbered CPU served by this
-<tt>rcu_node</tt> structure, respectively.
-
-</p><p>All of these fields are constant, and thus do not require any
-synchronization.
-
-<h5>Synchronization</h5>
-
-<p>This field of the <tt>rcu_node</tt> structure is declared
-as follows:
-
-<pre>
-  1   raw_spinlock_t lock;
-</pre>
-
-<p>This field is used to protect the remaining fields in this structure,
-unless otherwise stated.
-That said, all of the fields in this structure can be accessed without
-locking for tracing purposes.
-Yes, this can result in confusing traces, but better some tracing confusion
-than to be heisenbugged out of existence.
-
-<h5>Grace-Period Tracking</h5>
-
-<p>This portion of the <tt>rcu_node</tt> structure is declared
-as follows:
-
-<pre>
-  1   unsigned long gp_seq;
-  2   unsigned long gp_seq_needed;
-</pre>
-
-<p>The <tt>rcu_node</tt> structures' <tt>-&gt;gp_seq</tt> fields are
-the counterparts of the field of the same name in the <tt>rcu_state</tt>
-structure.
-They each may lag up to one step behind their <tt>rcu_state</tt>
-counterpart.
-If the bottom two bits of a given <tt>rcu_node</tt> structure's
-<tt>-&gt;gp_seq</tt> field is zero, then this <tt>rcu_node</tt>
-structure believes that RCU is idle.
-</p><p>The <tt>&gt;gp_seq</tt> field of each <tt>rcu_node</tt>
-structure is updated at the beginning and the end
-of each grace period.
-
-<p>The <tt>-&gt;gp_seq_needed</tt> fields record the
-furthest-in-the-future grace period request seen by the corresponding
-<tt>rcu_node</tt> structure.  The request is considered fulfilled when
-the value of the <tt>-&gt;gp_seq</tt> field equals or exceeds that of
-the <tt>-&gt;gp_seq_needed</tt> field.
-
-<table>
-<tr><th>&nbsp;</th></tr>
-<tr><th align="left">Quick Quiz:</th></tr>
-<tr><td>
-	Suppose that this <tt>rcu_node</tt> structure doesn't see
-	a request for a very long time.
-	Won't wrapping of the <tt>-&gt;gp_seq</tt> field cause
-	problems?
-</td></tr>
-<tr><th align="left">Answer:</th></tr>
-<tr><td bgcolor="#ffffff"><font color="ffffff">
-	No, because if the <tt>-&gt;gp_seq_needed</tt> field lags behind the
-	<tt>-&gt;gp_seq</tt> field, the <tt>-&gt;gp_seq_needed</tt> field
-	will be updated at the end of the grace period.
-	Modulo-arithmetic comparisons therefore will always get the
-	correct answer, even with wrapping.
-</font></td></tr>
-<tr><td>&nbsp;</td></tr>
-</table>
-
-<h5>Quiescent-State Tracking</h5>
-
-<p>These fields manage the propagation of quiescent states up the
-combining tree.
-
-</p><p>This portion of the <tt>rcu_node</tt> structure has fields
-as follows:
-
-<pre>
-  1   unsigned long qsmask;
-  2   unsigned long expmask;
-  3   unsigned long qsmaskinit;
-  4   unsigned long expmaskinit;
-</pre>
-
-<p>The <tt>-&gt;qsmask</tt> field tracks which of this
-<tt>rcu_node</tt> structure's children still need to report
-quiescent states for the current normal grace period.
-Such children will have a value of 1 in their corresponding bit.
-Note that the leaf <tt>rcu_node</tt> structures should be
-thought of as having <tt>rcu_data</tt> structures as their
-children.
-Similarly, the <tt>-&gt;expmask</tt> field tracks which
-of this <tt>rcu_node</tt> structure's children still need to report
-quiescent states for the current expedited grace period.
-An expedited grace period has
-the same conceptual properties as a normal grace period, but the
-expedited implementation accepts extreme CPU overhead to obtain
-much lower grace-period latency, for example, consuming a few
-tens of microseconds worth of CPU time to reduce grace-period
-duration from milliseconds to tens of microseconds.
-The <tt>-&gt;qsmaskinit</tt> field tracks which of this
-<tt>rcu_node</tt> structure's children cover for at least
-one online CPU.
-This mask is used to initialize <tt>-&gt;qsmask</tt>,
-and <tt>-&gt;expmaskinit</tt> is used to initialize
-<tt>-&gt;expmask</tt> and the beginning of the
-normal and expedited grace periods, respectively.
-
-<table>
-<tr><th>&nbsp;</th></tr>
-<tr><th align="left">Quick Quiz:</th></tr>
-<tr><td>
-	Why are these bitmasks protected by locking?
-	Come on, haven't you heard of atomic instructions???
-</td></tr>
-<tr><th align="left">Answer:</th></tr>
-<tr><td bgcolor="#ffffff"><font color="ffffff">
-	Lockless grace-period computation!  Such a tantalizing possibility!
-	</font>
-
-	<p><font color="ffffff">But consider the following sequence of events:
-	</font>
-
-	<ol>
-	<li>	<font color="ffffff">CPU&nbsp;0 has been in dyntick-idle
-		mode for quite some time.
-		When it wakes up, it notices that the current RCU
-		grace period needs it to report in, so it sets a
-		flag where the scheduling clock interrupt will find it.
-		</font><p>
-	<li>	<font color="ffffff">Meanwhile, CPU&nbsp;1 is running
-		<tt>force_quiescent_state()</tt>,
-		and notices that CPU&nbsp;0 has been in dyntick idle mode,
-		which qualifies as an extended quiescent state.
-		</font><p>
-	<li>	<font color="ffffff">CPU&nbsp;0's scheduling clock
-		interrupt fires in the
-		middle of an RCU read-side critical section, and notices
-		that the RCU core needs something, so commences RCU softirq
-		processing.
-		</font>
-		<p>
-	<li>	<font color="ffffff">CPU&nbsp;0's softirq handler
-		executes and is just about ready
-		to report its quiescent state up the <tt>rcu_node</tt>
-		tree.
-		</font><p>
-	<li>	<font color="ffffff">But CPU&nbsp;1 beats it to the punch,
-		completing the current
-		grace period and starting a new one.
-		</font><p>
-	<li>	<font color="ffffff">CPU&nbsp;0 now reports its quiescent
-		state for the wrong
-		grace period.
-		That grace period might now end before the RCU read-side
-		critical section.
-		If that happens, disaster will ensue.
-		</font>
-	</ol>
-
-	<p><font color="ffffff">So the locking is absolutely required in
-	order to coordinate clearing of the bits with updating of the
-	grace-period sequence number in <tt>-&gt;gp_seq</tt>.
-</font></td></tr>
-<tr><td>&nbsp;</td></tr>
-</table>
-
-<h5>Blocked-Task Management</h5>
-
-<p><tt>PREEMPT_RCU</tt> allows tasks to be preempted in the
-midst of their RCU read-side critical sections, and these tasks
-must be tracked explicitly.
-The details of exactly why and how they are tracked will be covered
-in a separate article on RCU read-side processing.
-For now, it is enough to know that the <tt>rcu_node</tt>
-structure tracks them.
-
-<pre>
-  1   struct list_head blkd_tasks;
-  2   struct list_head *gp_tasks;
-  3   struct list_head *exp_tasks;
-  4   bool wait_blkd_tasks;
-</pre>
-
-<p>The <tt>-&gt;blkd_tasks</tt> field is a list header for
-the list of blocked and preempted tasks.
-As tasks undergo context switches within RCU read-side critical
-sections, their <tt>task_struct</tt> structures are enqueued
-(via the <tt>task_struct</tt>'s <tt>-&gt;rcu_node_entry</tt>
-field) onto the head of the <tt>-&gt;blkd_tasks</tt> list for the
-leaf <tt>rcu_node</tt> structure corresponding to the CPU
-on which the outgoing context switch executed.
-As these tasks later exit their RCU read-side critical sections,
-they remove themselves from the list.
-This list is therefore in reverse time order, so that if one of the tasks
-is blocking the current grace period, all subsequent tasks must
-also be blocking that same grace period.
-Therefore, a single pointer into this list suffices to track
-all tasks blocking a given grace period.
-That pointer is stored in <tt>-&gt;gp_tasks</tt> for normal
-grace periods and in <tt>-&gt;exp_tasks</tt> for expedited
-grace periods.
-These last two fields are <tt>NULL</tt> if either there is
-no grace period in flight or if there are no blocked tasks
-preventing that grace period from completing.
-If either of these two pointers is referencing a task that
-removes itself from the <tt>-&gt;blkd_tasks</tt> list,
-then that task must advance the pointer to the next task on
-the list, or set the pointer to <tt>NULL</tt> if there
-are no subsequent tasks on the list.
-
-</p><p>For example, suppose that tasks&nbsp;T1, T2, and&nbsp;T3 are
-all hard-affinitied to the largest-numbered CPU in the system.
-Then if task&nbsp;T1 blocked in an RCU read-side
-critical section, then an expedited grace period started,
-then task&nbsp;T2 blocked in an RCU read-side critical section,
-then a normal grace period started, and finally task&nbsp;3 blocked
-in an RCU read-side critical section, then the state of the
-last leaf <tt>rcu_node</tt> structure's blocked-task list
-would be as shown below:
-
-</p><p><img src="blkd_task.svg" alt="blkd_task.svg" width="60%">
-
-</p><p>Task&nbsp;T1 is blocking both grace periods, task&nbsp;T2 is
-blocking only the normal grace period, and task&nbsp;T3 is blocking
-neither grace period.
-Note that these tasks will not remove themselves from this list
-immediately upon resuming execution.
-They will instead remain on the list until they execute the outermost
-<tt>rcu_read_unlock()</tt> that ends their RCU read-side critical
-section.
-
-<p>
-The <tt>-&gt;wait_blkd_tasks</tt> field indicates whether or not
-the current grace period is waiting on a blocked task.
-
-<h5>Sizing the <tt>rcu_node</tt> Array</h5>
-
-<p>The <tt>rcu_node</tt> array is sized via a series of
-C-preprocessor expressions as follows:
-
-<pre>
- 1 #ifdef CONFIG_RCU_FANOUT
- 2 #define RCU_FANOUT CONFIG_RCU_FANOUT
- 3 #else
- 4 # ifdef CONFIG_64BIT
- 5 # define RCU_FANOUT 64
- 6 # else
- 7 # define RCU_FANOUT 32
- 8 # endif
- 9 #endif
-10
-11 #ifdef CONFIG_RCU_FANOUT_LEAF
-12 #define RCU_FANOUT_LEAF CONFIG_RCU_FANOUT_LEAF
-13 #else
-14 # ifdef CONFIG_64BIT
-15 # define RCU_FANOUT_LEAF 64
-16 # else
-17 # define RCU_FANOUT_LEAF 32
-18 # endif
-19 #endif
-20
-21 #define RCU_FANOUT_1        (RCU_FANOUT_LEAF)
-22 #define RCU_FANOUT_2        (RCU_FANOUT_1 * RCU_FANOUT)
-23 #define RCU_FANOUT_3        (RCU_FANOUT_2 * RCU_FANOUT)
-24 #define RCU_FANOUT_4        (RCU_FANOUT_3 * RCU_FANOUT)
-25
-26 #if NR_CPUS &lt;= RCU_FANOUT_1
-27 #  define RCU_NUM_LVLS        1
-28 #  define NUM_RCU_LVL_0        1
-29 #  define NUM_RCU_NODES        NUM_RCU_LVL_0
-30 #  define NUM_RCU_LVL_INIT    { NUM_RCU_LVL_0 }
-31 #  define RCU_NODE_NAME_INIT  { "rcu_node_0" }
-32 #  define RCU_FQS_NAME_INIT   { "rcu_node_fqs_0" }
-33 #  define RCU_EXP_NAME_INIT   { "rcu_node_exp_0" }
-34 #elif NR_CPUS &lt;= RCU_FANOUT_2
-35 #  define RCU_NUM_LVLS        2
-36 #  define NUM_RCU_LVL_0        1
-37 #  define NUM_RCU_LVL_1        DIV_ROUND_UP(NR_CPUS, RCU_FANOUT_1)
-38 #  define NUM_RCU_NODES        (NUM_RCU_LVL_0 + NUM_RCU_LVL_1)
-39 #  define NUM_RCU_LVL_INIT    { NUM_RCU_LVL_0, NUM_RCU_LVL_1 }
-40 #  define RCU_NODE_NAME_INIT  { "rcu_node_0", "rcu_node_1" }
-41 #  define RCU_FQS_NAME_INIT   { "rcu_node_fqs_0", "rcu_node_fqs_1" }
-42 #  define RCU_EXP_NAME_INIT   { "rcu_node_exp_0", "rcu_node_exp_1" }
-43 #elif NR_CPUS &lt;= RCU_FANOUT_3
-44 #  define RCU_NUM_LVLS        3
-45 #  define NUM_RCU_LVL_0        1
-46 #  define NUM_RCU_LVL_1        DIV_ROUND_UP(NR_CPUS, RCU_FANOUT_2)
-47 #  define NUM_RCU_LVL_2        DIV_ROUND_UP(NR_CPUS, RCU_FANOUT_1)
-48 #  define NUM_RCU_NODES        (NUM_RCU_LVL_0 + NUM_RCU_LVL_1 + NUM_RCU_LVL_2)
-49 #  define NUM_RCU_LVL_INIT    { NUM_RCU_LVL_0, NUM_RCU_LVL_1, NUM_RCU_LVL_2 }
-50 #  define RCU_NODE_NAME_INIT  { "rcu_node_0", "rcu_node_1", "rcu_node_2" }
-51 #  define RCU_FQS_NAME_INIT   { "rcu_node_fqs_0", "rcu_node_fqs_1", "rcu_node_fqs_2" }
-52 #  define RCU_EXP_NAME_INIT   { "rcu_node_exp_0", "rcu_node_exp_1", "rcu_node_exp_2" }
-53 #elif NR_CPUS &lt;= RCU_FANOUT_4
-54 #  define RCU_NUM_LVLS        4
-55 #  define NUM_RCU_LVL_0        1
-56 #  define NUM_RCU_LVL_1        DIV_ROUND_UP(NR_CPUS, RCU_FANOUT_3)
-57 #  define NUM_RCU_LVL_2        DIV_ROUND_UP(NR_CPUS, RCU_FANOUT_2)
-58 #  define NUM_RCU_LVL_3        DIV_ROUND_UP(NR_CPUS, RCU_FANOUT_1)
-59 #  define NUM_RCU_NODES        (NUM_RCU_LVL_0 + NUM_RCU_LVL_1 + NUM_RCU_LVL_2 + NUM_RCU_LVL_3)
-60 #  define NUM_RCU_LVL_INIT    { NUM_RCU_LVL_0, NUM_RCU_LVL_1, NUM_RCU_LVL_2, NUM_RCU_LVL_3 }
-61 #  define RCU_NODE_NAME_INIT  { "rcu_node_0", "rcu_node_1", "rcu_node_2", "rcu_node_3" }
-62 #  define RCU_FQS_NAME_INIT   { "rcu_node_fqs_0", "rcu_node_fqs_1", "rcu_node_fqs_2", "rcu_node_fqs_3" }
-63 #  define RCU_EXP_NAME_INIT   { "rcu_node_exp_0", "rcu_node_exp_1", "rcu_node_exp_2", "rcu_node_exp_3" }
-64 #else
-65 # error "CONFIG_RCU_FANOUT insufficient for NR_CPUS"
-66 #endif
-</pre>
-
-<p>The maximum number of levels in the <tt>rcu_node</tt> structure
-is currently limited to four, as specified by lines&nbsp;21-24
-and the structure of the subsequent &ldquo;if&rdquo; statement.
-For 32-bit systems, this allows 16*32*32*32=524,288 CPUs, which
-should be sufficient for the next few years at least.
-For 64-bit systems, 16*64*64*64=4,194,304 CPUs is allowed, which
-should see us through the next decade or so.
-This four-level tree also allows kernels built with
-<tt>CONFIG_RCU_FANOUT=8</tt> to support up to 4096 CPUs,
-which might be useful in very large systems having eight CPUs per
-socket (but please note that no one has yet shown any measurable
-performance degradation due to misaligned socket and <tt>rcu_node</tt>
-boundaries).
-In addition, building kernels with a full four levels of <tt>rcu_node</tt>
-tree permits better testing of RCU's combining-tree code.
-
-</p><p>The <tt>RCU_FANOUT</tt> symbol controls how many children
-are permitted at each non-leaf level of the <tt>rcu_node</tt> tree.
-If the <tt>CONFIG_RCU_FANOUT</tt> Kconfig option is not specified,
-it is set based on the word size of the system, which is also
-the Kconfig default.
-
-</p><p>The <tt>RCU_FANOUT_LEAF</tt> symbol controls how many CPUs are
-handled by each leaf <tt>rcu_node</tt> structure.
-Experience has shown that allowing a given leaf <tt>rcu_node</tt>
-structure to handle 64 CPUs, as permitted by the number of bits in
-the <tt>-&gt;qsmask</tt> field on a 64-bit system, results in
-excessive contention for the leaf <tt>rcu_node</tt> structures'
-<tt>-&gt;lock</tt> fields.
-The number of CPUs per leaf <tt>rcu_node</tt> structure is therefore
-limited to 16 given the default value of <tt>CONFIG_RCU_FANOUT_LEAF</tt>.
-If <tt>CONFIG_RCU_FANOUT_LEAF</tt> is unspecified, the value
-selected is based on the word size of the system, just as for
-<tt>CONFIG_RCU_FANOUT</tt>.
-Lines&nbsp;11-19 perform this computation.
-
-</p><p>Lines&nbsp;21-24 compute the maximum number of CPUs supported by
-a single-level (which contains a single <tt>rcu_node</tt> structure),
-two-level, three-level, and four-level <tt>rcu_node</tt> tree,
-respectively, given the fanout specified by <tt>RCU_FANOUT</tt>
-and <tt>RCU_FANOUT_LEAF</tt>.
-These numbers of CPUs are retained in the
-<tt>RCU_FANOUT_1</tt>,
-<tt>RCU_FANOUT_2</tt>,
-<tt>RCU_FANOUT_3</tt>, and
-<tt>RCU_FANOUT_4</tt>
-C-preprocessor variables, respectively.
-
-</p><p>These variables are used to control the C-preprocessor <tt>#if</tt>
-statement spanning lines&nbsp;26-66 that computes the number of
-<tt>rcu_node</tt> structures required for each level of the tree,
-as well as the number of levels required.
-The number of levels is placed in the <tt>NUM_RCU_LVLS</tt>
-C-preprocessor variable by lines&nbsp;27, 35, 44, and&nbsp;54.
-The number of <tt>rcu_node</tt> structures for the topmost level
-of the tree is always exactly one, and this value is unconditionally
-placed into <tt>NUM_RCU_LVL_0</tt> by lines&nbsp;28, 36, 45, and&nbsp;55.
-The rest of the levels (if any) of the <tt>rcu_node</tt> tree
-are computed by dividing the maximum number of CPUs by the
-fanout supported by the number of levels from the current level down,
-rounding up.  This computation is performed by lines&nbsp;37,
-46-47, and&nbsp;56-58.
-Lines&nbsp;31-33, 40-42, 50-52, and&nbsp;62-63 create initializers
-for lockdep lock-class names.
-Finally, lines&nbsp;64-66 produce an error if the maximum number of
-CPUs is too large for the specified fanout.
-
-<h3><a name="The rcu_segcblist Structure">
-The <tt>rcu_segcblist</tt> Structure</a></h3>
-
-The <tt>rcu_segcblist</tt> structure maintains a segmented list of
-callbacks as follows:
-
-<pre>
- 1 #define RCU_DONE_TAIL        0
- 2 #define RCU_WAIT_TAIL        1
- 3 #define RCU_NEXT_READY_TAIL  2
- 4 #define RCU_NEXT_TAIL        3
- 5 #define RCU_CBLIST_NSEGS     4
- 6
- 7 struct rcu_segcblist {
- 8   struct rcu_head *head;
- 9   struct rcu_head **tails[RCU_CBLIST_NSEGS];
-10   unsigned long gp_seq[RCU_CBLIST_NSEGS];
-11   long len;
-12   long len_lazy;
-13 };
-</pre>
-
-<p>
-The segments are as follows:
-
-<ol>
-<li>	<tt>RCU_DONE_TAIL</tt>: Callbacks whose grace periods have elapsed.
-	These callbacks are ready to be invoked.
-<li>	<tt>RCU_WAIT_TAIL</tt>: Callbacks that are waiting for the
-	current grace period.
-	Note that different CPUs can have different ideas about which
-	grace period is current, hence the <tt>-&gt;gp_seq</tt> field.
-<li>	<tt>RCU_NEXT_READY_TAIL</tt>: Callbacks waiting for the next
-	grace period to start.
-<li>	<tt>RCU_NEXT_TAIL</tt>: Callbacks that have not yet been
-	associated with a grace period.
-</ol>
-
-<p>
-The <tt>-&gt;head</tt> pointer references the first callback or
-is <tt>NULL</tt> if the list contains no callbacks (which is
-<i>not</i> the same as being empty).
-Each element of the <tt>-&gt;tails[]</tt> array references the
-<tt>-&gt;next</tt> pointer of the last callback in the corresponding
-segment of the list, or the list's <tt>-&gt;head</tt> pointer if
-that segment and all previous segments are empty.
-If the corresponding segment is empty but some previous segment is
-not empty, then the array element is identical to its predecessor.
-Older callbacks are closer to the head of the list, and new callbacks
-are added at the tail.
-This relationship between the <tt>-&gt;head</tt> pointer, the
-<tt>-&gt;tails[]</tt> array, and the callbacks is shown in this
-diagram:
-
-</p><p><img src="nxtlist.svg" alt="nxtlist.svg" width="40%">
-
-</p><p>In this figure, the <tt>-&gt;head</tt> pointer references the
-first
-RCU callback in the list.
-The <tt>-&gt;tails[RCU_DONE_TAIL]</tt> array element references
-the <tt>-&gt;head</tt> pointer itself, indicating that none
-of the callbacks is ready to invoke.
-The <tt>-&gt;tails[RCU_WAIT_TAIL]</tt> array element references callback
-CB&nbsp;2's <tt>-&gt;next</tt> pointer, which indicates that
-CB&nbsp;1 and CB&nbsp;2 are both waiting on the current grace period,
-give or take possible disagreements about exactly which grace period
-is the current one.
-The <tt>-&gt;tails[RCU_NEXT_READY_TAIL]</tt> array element
-references the same RCU callback that <tt>-&gt;tails[RCU_WAIT_TAIL]</tt>
-does, which indicates that there are no callbacks waiting on the next
-RCU grace period.
-The <tt>-&gt;tails[RCU_NEXT_TAIL]</tt> array element references
-CB&nbsp;4's <tt>-&gt;next</tt> pointer, indicating that all the
-remaining RCU callbacks have not yet been assigned to an RCU grace
-period.
-Note that the <tt>-&gt;tails[RCU_NEXT_TAIL]</tt> array element
-always references the last RCU callback's <tt>-&gt;next</tt> pointer
-unless the callback list is empty, in which case it references
-the <tt>-&gt;head</tt> pointer.
-
-<p>
-There is one additional important special case for the
-<tt>-&gt;tails[RCU_NEXT_TAIL]</tt> array element: It can be <tt>NULL</tt>
-when this list is <i>disabled</i>.
-Lists are disabled when the corresponding CPU is offline or when
-the corresponding CPU's callbacks are offloaded to a kthread,
-both of which are described elsewhere.
-
-</p><p>CPUs advance their callbacks from the
-<tt>RCU_NEXT_TAIL</tt> to the <tt>RCU_NEXT_READY_TAIL</tt> to the
-<tt>RCU_WAIT_TAIL</tt> to the <tt>RCU_DONE_TAIL</tt> list segments
-as grace periods advance.
-
-</p><p>The <tt>-&gt;gp_seq[]</tt> array records grace-period
-numbers corresponding to the list segments.
-This is what allows different CPUs to have different ideas as to
-which is the current grace period while still avoiding premature
-invocation of their callbacks.
-In particular, this allows CPUs that go idle for extended periods
-to determine which of their callbacks are ready to be invoked after
-reawakening.
-
-</p><p>The <tt>-&gt;len</tt> counter contains the number of
-callbacks in <tt>-&gt;head</tt>, and the
-<tt>-&gt;len_lazy</tt> contains the number of those callbacks that
-are known to only free memory, and whose invocation can therefore
-be safely deferred.
-
-<p><b>Important note</b>: It is the <tt>-&gt;len</tt> field that
-determines whether or not there are callbacks associated with
-this <tt>rcu_segcblist</tt> structure, <i>not</i> the <tt>-&gt;head</tt>
-pointer.
-The reason for this is that all the ready-to-invoke callbacks
-(that is, those in the <tt>RCU_DONE_TAIL</tt> segment) are extracted
-all at once at callback-invocation time (<tt>rcu_do_batch</tt>), due
-to which <tt>-&gt;head</tt> may be set to NULL if there are no not-done
-callbacks remaining in the <tt>rcu_segcblist</tt>.
-If callback invocation must be postponed, for example, because a
-high-priority process just woke up on this CPU, then the remaining
-callbacks are placed back on the <tt>RCU_DONE_TAIL</tt> segment and
-<tt>-&gt;head</tt> once again points to the start of the segment.
-In short, the head field can briefly be <tt>NULL</tt> even though the
-CPU has callbacks present the entire time.
-Therefore, it is not appropriate to test the <tt>-&gt;head</tt> pointer
-for <tt>NULL</tt>.
-
-<p>In contrast, the <tt>-&gt;len</tt> and <tt>-&gt;len_lazy</tt> counts
-are adjusted only after the corresponding callbacks have been invoked.
-This means that the <tt>-&gt;len</tt> count is zero only if
-the <tt>rcu_segcblist</tt> structure really is devoid of callbacks.
-Of course, off-CPU sampling of the <tt>-&gt;len</tt> count requires
-careful use of appropriate synchronization, for example, memory barriers.
-This synchronization can be a bit subtle, particularly in the case
-of <tt>rcu_barrier()</tt>.
-
-<h3><a name="The rcu_data Structure">
-The <tt>rcu_data</tt> Structure</a></h3>
-
-<p>The <tt>rcu_data</tt> maintains the per-CPU state for the RCU subsystem.
-The fields in this structure may be accessed only from the corresponding
-CPU (and from tracing) unless otherwise stated.
-This structure is the
-focus of quiescent-state detection and RCU callback queuing.
-It also tracks its relationship to the corresponding leaf
-<tt>rcu_node</tt> structure to allow more-efficient
-propagation of quiescent states up the <tt>rcu_node</tt>
-combining tree.
-Like the <tt>rcu_node</tt> structure, it provides a local
-copy of the grace-period information to allow for-free
-synchronized
-access to this information from the corresponding CPU.
-Finally, this structure records past dyntick-idle state
-for the corresponding CPU and also tracks statistics.
-
-</p><p>The <tt>rcu_data</tt> structure's fields are discussed,
-singly and in groups, in the following sections.
-
-<h5>Connection to Other Data Structures</h5>
-
-<p>This portion of the <tt>rcu_data</tt> structure is declared
-as follows:
-
-<pre>
-  1   int cpu;
-  2   struct rcu_node *mynode;
-  3   unsigned long grpmask;
-  4   bool beenonline;
-</pre>
-
-<p>The <tt>-&gt;cpu</tt> field contains the number of the
-corresponding CPU and the <tt>-&gt;mynode</tt> field references the
-corresponding <tt>rcu_node</tt> structure.
-The <tt>-&gt;mynode</tt> is used to propagate quiescent states
-up the combining tree.
-These two fields are constant and therefore do not require synchronization.
-
-<p>The <tt>-&gt;grpmask</tt> field indicates the bit in
-the <tt>-&gt;mynode-&gt;qsmask</tt> corresponding to this
-<tt>rcu_data</tt> structure, and is also used when propagating
-quiescent states.
-The <tt>-&gt;beenonline</tt> flag is set whenever the corresponding
-CPU comes online, which means that the debugfs tracing need not dump
-out any <tt>rcu_data</tt> structure for which this flag is not set.
-
-<h5>Quiescent-State and Grace-Period Tracking</h5>
-
-<p>This portion of the <tt>rcu_data</tt> structure is declared
-as follows:
-
-<pre>
-  1   unsigned long gp_seq;
-  2   unsigned long gp_seq_needed;
-  3   bool cpu_no_qs;
-  4   bool core_needs_qs;
-  5   bool gpwrap;
-</pre>
-
-<p>The <tt>-&gt;gp_seq</tt> field is the counterpart of the field of the same
-name in the <tt>rcu_state</tt> and <tt>rcu_node</tt> structures.  The
-<tt>-&gt;gp_seq_needed</tt> field is the counterpart of the field of the same
-name in the rcu_node</tt> structure.
-They may each lag up to one behind their <tt>rcu_node</tt>
-counterparts, but in <tt>CONFIG_NO_HZ_IDLE</tt> and
-<tt>CONFIG_NO_HZ_FULL</tt> kernels can lag
-arbitrarily far behind for CPUs in dyntick-idle mode (but these counters
-will catch up upon exit from dyntick-idle mode).
-If the lower two bits of a given <tt>rcu_data</tt> structure's
-<tt>-&gt;gp_seq</tt> are zero, then this <tt>rcu_data</tt>
-structure believes that RCU is idle.
-
-<table>
-<tr><th>&nbsp;</th></tr>
-<tr><th align="left">Quick Quiz:</th></tr>
-<tr><td>
-	All this replication of the grace period numbers can only cause
-	massive confusion.
-	Why not just keep a global sequence number and be done with it???
-</td></tr>
-<tr><th align="left">Answer:</th></tr>
-<tr><td bgcolor="#ffffff"><font color="ffffff">
-	Because if there was only a single global sequence
-	numbers, there would need to be a single global lock to allow
-	safely accessing and updating it.
-	And if we are not going to have a single global lock, we need
-	to carefully manage the numbers on a per-node basis.
-	Recall from the answer to a previous Quick Quiz that the consequences
-	of applying a previously sampled quiescent state to the wrong
-	grace period are quite severe.
-</font></td></tr>
-<tr><td>&nbsp;</td></tr>
-</table>
-
-<p>The <tt>-&gt;cpu_no_qs</tt> flag indicates that the
-CPU has not yet passed through a quiescent state,
-while the <tt>-&gt;core_needs_qs</tt> flag indicates that the
-RCU core needs a quiescent state from the corresponding CPU.
-The <tt>-&gt;gpwrap</tt> field indicates that the corresponding
-CPU has remained idle for so long that the
-<tt>gp_seq</tt> counter is in danger of overflow, which
-will cause the CPU to disregard the values of its counters on
-its next exit from idle.
-
-<h5>RCU Callback Handling</h5>
-
-<p>In the absence of CPU-hotplug events, RCU callbacks are invoked by
-the same CPU that registered them.
-This is strictly a cache-locality optimization: callbacks can and
-do get invoked on CPUs other than the one that registered them.
-After all, if the CPU that registered a given callback has gone
-offline before the callback can be invoked, there really is no other
-choice.
-
-</p><p>This portion of the <tt>rcu_data</tt> structure is declared
-as follows:
-
-<pre>
- 1 struct rcu_segcblist cblist;
- 2 long qlen_last_fqs_check;
- 3 unsigned long n_cbs_invoked;
- 4 unsigned long n_nocbs_invoked;
- 5 unsigned long n_cbs_orphaned;
- 6 unsigned long n_cbs_adopted;
- 7 unsigned long n_force_qs_snap;
- 8 long blimit;
-</pre>
-
-<p>The <tt>-&gt;cblist</tt> structure is the segmented callback list
-described earlier.
-The CPU advances the callbacks in its <tt>rcu_data</tt> structure
-whenever it notices that another RCU grace period has completed.
-The CPU detects the completion of an RCU grace period by noticing
-that the value of its <tt>rcu_data</tt> structure's
-<tt>-&gt;gp_seq</tt> field differs from that of its leaf
-<tt>rcu_node</tt> structure.
-Recall that each <tt>rcu_node</tt> structure's
-<tt>-&gt;gp_seq</tt> field is updated at the beginnings and ends of each
-grace period.
-
-<p>
-The <tt>-&gt;qlen_last_fqs_check</tt> and
-<tt>-&gt;n_force_qs_snap</tt> coordinate the forcing of quiescent
-states from <tt>call_rcu()</tt> and friends when callback
-lists grow excessively long.
-
-</p><p>The <tt>-&gt;n_cbs_invoked</tt>,
-<tt>-&gt;n_cbs_orphaned</tt>, and <tt>-&gt;n_cbs_adopted</tt>
-fields count the number of callbacks invoked,
-sent to other CPUs when this CPU goes offline,
-and received from other CPUs when those other CPUs go offline.
-The <tt>-&gt;n_nocbs_invoked</tt> is used when the CPU's callbacks
-are offloaded to a kthread.
-
-<p>
-Finally, the <tt>-&gt;blimit</tt> counter is the maximum number of
-RCU callbacks that may be invoked at a given time.
-
-<h5>Dyntick-Idle Handling</h5>
-
-<p>This portion of the <tt>rcu_data</tt> structure is declared
-as follows:
-
-<pre>
-  1   int dynticks_snap;
-  2   unsigned long dynticks_fqs;
-</pre>
-
-The <tt>-&gt;dynticks_snap</tt> field is used to take a snapshot
-of the corresponding CPU's dyntick-idle state when forcing
-quiescent states, and is therefore accessed from other CPUs.
-Finally, the <tt>-&gt;dynticks_fqs</tt> field is used to
-count the number of times this CPU is determined to be in
-dyntick-idle state, and is used for tracing and debugging purposes.
-
-<p>
-This portion of the rcu_data structure is declared as follows:
-
-<pre>
-  1   long dynticks_nesting;
-  2   long dynticks_nmi_nesting;
-  3   atomic_t dynticks;
-  4   bool rcu_need_heavy_qs;
-  5   bool rcu_urgent_qs;
-</pre>
-
-<p>These fields in the rcu_data structure maintain the per-CPU dyntick-idle
-state for the corresponding CPU.
-The fields may be accessed only from the corresponding CPU (and from tracing)
-unless otherwise stated.
-
-<p>The <tt>-&gt;dynticks_nesting</tt> field counts the
-nesting depth of process execution, so that in normal circumstances
-this counter has value zero or one.
-NMIs, irqs, and tracers are counted by the <tt>-&gt;dynticks_nmi_nesting</tt>
-field.
-Because NMIs cannot be masked, changes to this variable have to be
-undertaken carefully using an algorithm provided by Andy Lutomirski.
-The initial transition from idle adds one, and nested transitions
-add two, so that a nesting level of five is represented by a
-<tt>-&gt;dynticks_nmi_nesting</tt> value of nine.
-This counter can therefore be thought of as counting the number
-of reasons why this CPU cannot be permitted to enter dyntick-idle
-mode, aside from process-level transitions.
-
-<p>However, it turns out that when running in non-idle kernel context,
-the Linux kernel is fully capable of entering interrupt handlers that
-never exit and perhaps also vice versa.
-Therefore, whenever the <tt>-&gt;dynticks_nesting</tt> field is
-incremented up from zero, the <tt>-&gt;dynticks_nmi_nesting</tt> field
-is set to a large positive number, and whenever the
-<tt>-&gt;dynticks_nesting</tt> field is decremented down to zero,
-the the <tt>-&gt;dynticks_nmi_nesting</tt> field is set to zero.
-Assuming that the number of misnested interrupts is not sufficient
-to overflow the counter, this approach corrects the
-<tt>-&gt;dynticks_nmi_nesting</tt> field every time the corresponding
-CPU enters the idle loop from process context.
-
-</p><p>The <tt>-&gt;dynticks</tt> field counts the corresponding
-CPU's transitions to and from either dyntick-idle or user mode, so
-that this counter has an even value when the CPU is in dyntick-idle
-mode or user mode and an odd value otherwise. The transitions to/from
-user mode need to be counted for user mode adaptive-ticks support
-(see timers/NO_HZ.txt).
-
-</p><p>The <tt>-&gt;rcu_need_heavy_qs</tt> field is used
-to record the fact that the RCU core code would really like to
-see a quiescent state from the corresponding CPU, so much so that
-it is willing to call for heavy-weight dyntick-counter operations.
-This flag is checked by RCU's context-switch and <tt>cond_resched()</tt>
-code, which provide a momentary idle sojourn in response.
-
-</p><p>Finally, the <tt>-&gt;rcu_urgent_qs</tt> field is used to record
-the fact that the RCU core code would really like to see a quiescent state from
-the corresponding CPU, with the various other fields indicating just how badly
-RCU wants this quiescent state.
-This flag is checked by RCU's context-switch path
-(<tt>rcu_note_context_switch</tt>) and the cond_resched code.
-
-<table>
-<tr><th>&nbsp;</th></tr>
-<tr><th align="left">Quick Quiz:</th></tr>
-<tr><td>
-	Why not simply combine the <tt>-&gt;dynticks_nesting</tt>
-	and <tt>-&gt;dynticks_nmi_nesting</tt> counters into a
-	single counter that just counts the number of reasons that
-	the corresponding CPU is non-idle?
-</td></tr>
-<tr><th align="left">Answer:</th></tr>
-<tr><td bgcolor="#ffffff"><font color="ffffff">
-	Because this would fail in the presence of interrupts whose
-	handlers never return and of handlers that manage to return
-	from a made-up interrupt.
-</font></td></tr>
-<tr><td>&nbsp;</td></tr>
-</table>
-
-<p>Additional fields are present for some special-purpose
-builds, and are discussed separately.
-
-<h3><a name="The rcu_head Structure">
-The <tt>rcu_head</tt> Structure</a></h3>
-
-<p>Each <tt>rcu_head</tt> structure represents an RCU callback.
-These structures are normally embedded within RCU-protected data
-structures whose algorithms use asynchronous grace periods.
-In contrast, when using algorithms that block waiting for RCU grace periods,
-RCU users need not provide <tt>rcu_head</tt> structures.
-
-</p><p>The <tt>rcu_head</tt> structure has fields as follows:
-
-<pre>
-  1   struct rcu_head *next;
-  2   void (*func)(struct rcu_head *head);
-</pre>
-
-<p>The <tt>-&gt;next</tt> field is used
-to link the <tt>rcu_head</tt> structures together in the
-lists within the <tt>rcu_data</tt> structures.
-The <tt>-&gt;func</tt> field is a pointer to the function
-to be called when the callback is ready to be invoked, and
-this function is passed a pointer to the <tt>rcu_head</tt>
-structure.
-However, <tt>kfree_rcu()</tt> uses the <tt>-&gt;func</tt>
-field to record the offset of the <tt>rcu_head</tt>
-structure within the enclosing RCU-protected data structure.
-
-</p><p>Both of these fields are used internally by RCU.
-From the viewpoint of RCU users, this structure is an
-opaque &ldquo;cookie&rdquo;.
-
-<table>
-<tr><th>&nbsp;</th></tr>
-<tr><th align="left">Quick Quiz:</th></tr>
-<tr><td>
-	Given that the callback function <tt>-&gt;func</tt>
-	is passed a pointer to the <tt>rcu_head</tt> structure,
-	how is that function supposed to find the beginning of the
-	enclosing RCU-protected data structure?
-</td></tr>
-<tr><th align="left">Answer:</th></tr>
-<tr><td bgcolor="#ffffff"><font color="ffffff">
-	In actual practice, there is a separate callback function per
-	type of RCU-protected data structure.
-	The callback function can therefore use the <tt>container_of()</tt>
-	macro in the Linux kernel (or other pointer-manipulation facilities
-	in other software environments) to find the beginning of the
-	enclosing structure.
-</font></td></tr>
-<tr><td>&nbsp;</td></tr>
-</table>
-
-<h3><a name="RCU-Specific Fields in the task_struct Structure">
-RCU-Specific Fields in the <tt>task_struct</tt> Structure</a></h3>
-
-<p>The <tt>CONFIG_PREEMPT_RCU</tt> implementation uses some
-additional fields in the <tt>task_struct</tt> structure:
-
-<pre>
- 1 #ifdef CONFIG_PREEMPT_RCU
- 2   int rcu_read_lock_nesting;
- 3   union rcu_special rcu_read_unlock_special;
- 4   struct list_head rcu_node_entry;
- 5   struct rcu_node *rcu_blocked_node;
- 6 #endif /* #ifdef CONFIG_PREEMPT_RCU */
- 7 #ifdef CONFIG_TASKS_RCU
- 8   unsigned long rcu_tasks_nvcsw;
- 9   bool rcu_tasks_holdout;
-10   struct list_head rcu_tasks_holdout_list;
-11   int rcu_tasks_idle_cpu;
-12 #endif /* #ifdef CONFIG_TASKS_RCU */
-</pre>
-
-<p>The <tt>-&gt;rcu_read_lock_nesting</tt> field records the
-nesting level for RCU read-side critical sections, and
-the <tt>-&gt;rcu_read_unlock_special</tt> field is a bitmask
-that records special conditions that require <tt>rcu_read_unlock()</tt>
-to do additional work.
-The <tt>-&gt;rcu_node_entry</tt> field is used to form lists of
-tasks that have blocked within preemptible-RCU read-side critical
-sections and the <tt>-&gt;rcu_blocked_node</tt> field references
-the <tt>rcu_node</tt> structure whose list this task is a member of,
-or <tt>NULL</tt> if it is not blocked within a preemptible-RCU
-read-side critical section.
-
-<p>The <tt>-&gt;rcu_tasks_nvcsw</tt> field tracks the number of
-voluntary context switches that this task had undergone at the
-beginning of the current tasks-RCU grace period,
-<tt>-&gt;rcu_tasks_holdout</tt> is set if the current tasks-RCU
-grace period is waiting on this task, <tt>-&gt;rcu_tasks_holdout_list</tt>
-is a list element enqueuing this task on the holdout list,
-and <tt>-&gt;rcu_tasks_idle_cpu</tt> tracks which CPU this
-idle task is running, but only if the task is currently running,
-that is, if the CPU is currently idle.
-
-<h3><a name="Accessor Functions">
-Accessor Functions</a></h3>
-
-<p>The following listing shows the
-<tt>rcu_get_root()</tt>, <tt>rcu_for_each_node_breadth_first</tt> and
-<tt>rcu_for_each_leaf_node()</tt> function and macros:
-
-<pre>
-  1 static struct rcu_node *rcu_get_root(struct rcu_state *rsp)
-  2 {
-  3   return &amp;rsp-&gt;node[0];
-  4 }
-  5
-  6 #define rcu_for_each_node_breadth_first(rsp, rnp) \
-  7   for ((rnp) = &amp;(rsp)-&gt;node[0]; \
-  8        (rnp) &lt; &amp;(rsp)-&gt;node[NUM_RCU_NODES]; (rnp)++)
-  9
- 10 #define rcu_for_each_leaf_node(rsp, rnp) \
- 11   for ((rnp) = (rsp)-&gt;level[NUM_RCU_LVLS - 1]; \
- 12        (rnp) &lt; &amp;(rsp)-&gt;node[NUM_RCU_NODES]; (rnp)++)
-</pre>
-
-<p>The <tt>rcu_get_root()</tt> simply returns a pointer to the
-first element of the specified <tt>rcu_state</tt> structure's
-<tt>-&gt;node[]</tt> array, which is the root <tt>rcu_node</tt>
-structure.
-
-</p><p>As noted earlier, the <tt>rcu_for_each_node_breadth_first()</tt>
-macro takes advantage of the layout of the <tt>rcu_node</tt>
-structures in the <tt>rcu_state</tt> structure's
-<tt>-&gt;node[]</tt> array, performing a breadth-first traversal by
-simply traversing the array in order.
-Similarly, the <tt>rcu_for_each_leaf_node()</tt> macro traverses only
-the last part of the array, thus traversing only the leaf
-<tt>rcu_node</tt> structures.
-
-<table>
-<tr><th>&nbsp;</th></tr>
-<tr><th align="left">Quick Quiz:</th></tr>
-<tr><td>
-	What does
-	<tt>rcu_for_each_leaf_node()</tt> do if the <tt>rcu_node</tt> tree
-	contains only a single node?
-</td></tr>
-<tr><th align="left">Answer:</th></tr>
-<tr><td bgcolor="#ffffff"><font color="ffffff">
-	In the single-node case,
-	<tt>rcu_for_each_leaf_node()</tt> traverses the single node.
-</font></td></tr>
-<tr><td>&nbsp;</td></tr>
-</table>
-
-<h3><a name="Summary">
-Summary</a></h3>
-
-So the state of RCU is represented by an <tt>rcu_state</tt> structure,
-which contains a combining tree of <tt>rcu_node</tt> and
-<tt>rcu_data</tt> structures.
-Finally, in <tt>CONFIG_NO_HZ_IDLE</tt> kernels, each CPU's dyntick-idle
-state is tracked by dynticks-related fields in the <tt>rcu_data</tt> structure.
-
-If you made it this far, you are well prepared to read the code
-walkthroughs in the other articles in this series.
-
-<h3><a name="Acknowledgments">
-Acknowledgments</a></h3>
-
-I owe thanks to Cyrill Gorcunov, Mathieu Desnoyers, Dhaval Giani, Paul
-Turner, Abhishek Srivastava, Matt Kowalczyk, and Serge Hallyn
-for helping me get this document into a more human-readable state.
-
-<h3><a name="Legal Statement">
-Legal Statement</a></h3>
-
-<p>This work represents the view of the author and does not necessarily
-represent the view of IBM.
-
-</p><p>Linux is a registered trademark of Linus Torvalds.
-
-</p><p>Other company, product, and service names may be trademarks or
-service marks of others.
-
-</body></html>
diff --git a/Documentation/RCU/Design/Data-Structures/Data-Structures.rst b/Documentation/RCU/Design/Data-Structures/Data-Structures.rst
new file mode 100644
index 000000000000..4a48e20a46f2
--- /dev/null
+++ b/Documentation/RCU/Design/Data-Structures/Data-Structures.rst
@@ -0,0 +1,1163 @@
+===================================================
+A Tour Through TREE_RCU's Data Structures [LWN.net]
+===================================================
+
+December 18, 2016
+
+This article was contributed by Paul E. McKenney
+
+Introduction
+============
+
+This document describes RCU's major data structures and their relationship
+to each other.
+
+Data-Structure Relationships
+============================
+
+RCU is for all intents and purposes a large state machine, and its
+data structures maintain the state in such a way as to allow RCU readers
+to execute extremely quickly, while also processing the RCU grace periods
+requested by updaters in an efficient and extremely scalable fashion.
+The efficiency and scalability of RCU updaters is provided primarily
+by a combining tree, as shown below:
+
+.. kernel-figure:: BigTreeClassicRCU.svg
+
+This diagram shows an enclosing ``rcu_state`` structure containing a tree
+of ``rcu_node`` structures. Each leaf node of the ``rcu_node`` tree has up
+to 16 ``rcu_data`` structures associated with it, so that there are
+``NR_CPUS`` number of ``rcu_data`` structures, one for each possible CPU.
+This structure is adjusted at boot time, if needed, to handle the common
+case where ``nr_cpu_ids`` is much less than ``NR_CPUs``.
+For example, a number of Linux distributions set ``NR_CPUs=4096``,
+which results in a three-level ``rcu_node`` tree.
+If the actual hardware has only 16 CPUs, RCU will adjust itself
+at boot time, resulting in an ``rcu_node`` tree with only a single node.
+
+The purpose of this combining tree is to allow per-CPU events
+such as quiescent states, dyntick-idle transitions,
+and CPU hotplug operations to be processed efficiently
+and scalably.
+Quiescent states are recorded by the per-CPU ``rcu_data`` structures,
+and other events are recorded by the leaf-level ``rcu_node``
+structures.
+All of these events are combined at each level of the tree until finally
+grace periods are completed at the tree's root ``rcu_node``
+structure.
+A grace period can be completed at the root once every CPU
+(or, in the case of ``CONFIG_PREEMPT_RCU``, task)
+has passed through a quiescent state.
+Once a grace period has completed, record of that fact is propagated
+back down the tree.
+
+As can be seen from the diagram, on a 64-bit system
+a two-level tree with 64 leaves can accommodate 1,024 CPUs, with a fanout
+of 64 at the root and a fanout of 16 at the leaves.
+
++-----------------------------------------------------------------------+
+| **Quick Quiz**:                                                       |
++-----------------------------------------------------------------------+
+| Why isn't the fanout at the leaves also 64?                           |
++-----------------------------------------------------------------------+
+| **Answer**:                                                           |
++-----------------------------------------------------------------------+
+| Because there are more types of events that affect the leaf-level     |
+| ``rcu_node`` structures than further up the tree. Therefore, if the   |
+| leaf ``rcu_node`` structures have fanout of 64, the contention on     |
+| these structures' ``->structures`` becomes excessive. Experimentation |
+| on a wide variety of systems has shown that a fanout of 16 works well |
+| for the leaves of the ``rcu_node`` tree.                              |
+|                                                                       |
+| Of course, further experience with systems having hundreds or         |
+| thousands of CPUs may demonstrate that the fanout for the non-leaf    |
+| ``rcu_node`` structures must also be reduced. Such reduction can be   |
+| easily carried out when and if it proves necessary. In the meantime,  |
+| if you are using such a system and running into contention problems   |
+| on the non-leaf ``rcu_node`` structures, you may use the              |
+| ``CONFIG_RCU_FANOUT`` kernel configuration parameter to reduce the    |
+| non-leaf fanout as needed.                                            |
+|                                                                       |
+| Kernels built for systems with strong NUMA characteristics might      |
+| also need to adjust ``CONFIG_RCU_FANOUT`` so that the domains of      |
+| the ``rcu_node`` structures align with hardware boundaries.           |
+| However, there has thus far been no need for this.                    |
++-----------------------------------------------------------------------+
+
+If your system has more than 1,024 CPUs (or more than 512 CPUs on a
+32-bit system), then RCU will automatically add more levels to the tree.
+For example, if you are crazy enough to build a 64-bit system with
+65,536 CPUs, RCU would configure the ``rcu_node`` tree as follows:
+
+.. kernel-figure:: HugeTreeClassicRCU.svg
+
+RCU currently permits up to a four-level tree, which on a 64-bit system
+accommodates up to 4,194,304 CPUs, though only a mere 524,288 CPUs for
+32-bit systems. On the other hand, you can set both
+``CONFIG_RCU_FANOUT`` and ``CONFIG_RCU_FANOUT_LEAF`` to be as small as
+2, which would result in a 16-CPU test using a 4-level tree. This can be
+useful for testing large-system capabilities on small test machines.
+
+This multi-level combining tree allows us to get most of the performance
+and scalability benefits of partitioning, even though RCU grace-period
+detection is inherently a global operation. The trick here is that only
+the last CPU to report a quiescent state into a given ``rcu_node``
+structure need advance to the ``rcu_node`` structure at the next level
+up the tree. This means that at the leaf-level ``rcu_node`` structure,
+only one access out of sixteen will progress up the tree. For the
+internal ``rcu_node`` structures, the situation is even more extreme:
+Only one access out of sixty-four will progress up the tree. Because the
+vast majority of the CPUs do not progress up the tree, the lock
+contention remains roughly constant up the tree. No matter how many CPUs
+there are in the system, at most 64 quiescent-state reports per grace
+period will progress all the way to the root ``rcu_node`` structure,
+thus ensuring that the lock contention on that root ``rcu_node``
+structure remains acceptably low.
+
+In effect, the combining tree acts like a big shock absorber, keeping
+lock contention under control at all tree levels regardless of the level
+of loading on the system.
+
+RCU updaters wait for normal grace periods by registering RCU callbacks,
+either directly via ``call_rcu()`` or indirectly via
+``synchronize_rcu()`` and friends. RCU callbacks are represented by
+``rcu_head`` structures, which are queued on ``rcu_data`` structures
+while they are waiting for a grace period to elapse, as shown in the
+following figure:
+
+.. kernel-figure:: BigTreePreemptRCUBHdyntickCB.svg
+
+This figure shows how ``TREE_RCU``'s and ``PREEMPT_RCU``'s major data
+structures are related. Lesser data structures will be introduced with
+the algorithms that make use of them.
+
+Note that each of the data structures in the above figure has its own
+synchronization:
+
+#. Each ``rcu_state`` structures has a lock and a mutex, and some fields
+   are protected by the corresponding root ``rcu_node`` structure's lock.
+#. Each ``rcu_node`` structure has a spinlock.
+#. The fields in ``rcu_data`` are private to the corresponding CPU,
+   although a few can be read and written by other CPUs.
+
+It is important to note that different data structures can have very
+different ideas about the state of RCU at any given time. For but one
+example, awareness of the start or end of a given RCU grace period
+propagates slowly through the data structures. This slow propagation is
+absolutely necessary for RCU to have good read-side performance. If this
+balkanized implementation seems foreign to you, one useful trick is to
+consider each instance of these data structures to be a different
+person, each having the usual slightly different view of reality.
+
+The general role of each of these data structures is as follows:
+
+#. ``rcu_state``: This structure forms the interconnection between the
+   ``rcu_node`` and ``rcu_data`` structures, tracks grace periods,
+   serves as short-term repository for callbacks orphaned by CPU-hotplug
+   events, maintains ``rcu_barrier()`` state, tracks expedited
+   grace-period state, and maintains state used to force quiescent
+   states when grace periods extend too long,
+#. ``rcu_node``: This structure forms the combining tree that propagates
+   quiescent-state information from the leaves to the root, and also
+   propagates grace-period information from the root to the leaves. It
+   provides local copies of the grace-period state in order to allow
+   this information to be accessed in a synchronized manner without
+   suffering the scalability limitations that would otherwise be imposed
+   by global locking. In ``CONFIG_PREEMPT_RCU`` kernels, it manages the
+   lists of tasks that have blocked while in their current RCU read-side
+   critical section. In ``CONFIG_PREEMPT_RCU`` with
+   ``CONFIG_RCU_BOOST``, it manages the per-\ ``rcu_node``
+   priority-boosting kernel threads (kthreads) and state. Finally, it
+   records CPU-hotplug state in order to determine which CPUs should be
+   ignored during a given grace period.
+#. ``rcu_data``: This per-CPU structure is the focus of quiescent-state
+   detection and RCU callback queuing. It also tracks its relationship
+   to the corresponding leaf ``rcu_node`` structure to allow
+   more-efficient propagation of quiescent states up the ``rcu_node``
+   combining tree. Like the ``rcu_node`` structure, it provides a local
+   copy of the grace-period information to allow for-free synchronized
+   access to this information from the corresponding CPU. Finally, this
+   structure records past dyntick-idle state for the corresponding CPU
+   and also tracks statistics.
+#. ``rcu_head``: This structure represents RCU callbacks, and is the
+   only structure allocated and managed by RCU users. The ``rcu_head``
+   structure is normally embedded within the RCU-protected data
+   structure.
+
+If all you wanted from this article was a general notion of how RCU's
+data structures are related, you are done. Otherwise, each of the
+following sections give more details on the ``rcu_state``, ``rcu_node``
+and ``rcu_data`` data structures.
+
+The ``rcu_state`` Structure
+~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+The ``rcu_state`` structure is the base structure that represents the
+state of RCU in the system. This structure forms the interconnection
+between the ``rcu_node`` and ``rcu_data`` structures, tracks grace
+periods, contains the lock used to synchronize with CPU-hotplug events,
+and maintains state used to force quiescent states when grace periods
+extend too long,
+
+A few of the ``rcu_state`` structure's fields are discussed, singly and
+in groups, in the following sections. The more specialized fields are
+covered in the discussion of their use.
+
+Relationship to rcu_node and rcu_data Structures
+''''''''''''''''''''''''''''''''''''''''''''''''
+
+This portion of the ``rcu_state`` structure is declared as follows:
+
+::
+
+     1   struct rcu_node node[NUM_RCU_NODES];
+     2   struct rcu_node *level[NUM_RCU_LVLS + 1];
+     3   struct rcu_data __percpu *rda;
+
++-----------------------------------------------------------------------+
+| **Quick Quiz**:                                                       |
++-----------------------------------------------------------------------+
+| Wait a minute! You said that the ``rcu_node`` structures formed a     |
+| tree, but they are declared as a flat array! What gives?              |
++-----------------------------------------------------------------------+
+| **Answer**:                                                           |
++-----------------------------------------------------------------------+
+| The tree is laid out in the array. The first node In the array is the |
+| head, the next set of nodes in the array are children of the head     |
+| node, and so on until the last set of nodes in the array are the      |
+| leaves.                                                               |
+| See the following diagrams to see how this works.                     |
++-----------------------------------------------------------------------+
+
+The ``rcu_node`` tree is embedded into the ``->node[]`` array as shown
+in the following figure:
+
+.. kernel-figure:: TreeMapping.svg
+
+One interesting consequence of this mapping is that a breadth-first
+traversal of the tree is implemented as a simple linear scan of the
+array, which is in fact what the ``rcu_for_each_node_breadth_first()``
+macro does. This macro is used at the beginning and ends of grace
+periods.
+
+Each entry of the ``->level`` array references the first ``rcu_node``
+structure on the corresponding level of the tree, for example, as shown
+below:
+
+.. kernel-figure:: TreeMappingLevel.svg
+
+The zero\ :sup:`th` element of the array references the root
+``rcu_node`` structure, the first element references the first child of
+the root ``rcu_node``, and finally the second element references the
+first leaf ``rcu_node`` structure.
+
+For whatever it is worth, if you draw the tree to be tree-shaped rather
+than array-shaped, it is easy to draw a planar representation:
+
+.. kernel-figure:: TreeLevel.svg
+
+Finally, the ``->rda`` field references a per-CPU pointer to the
+corresponding CPU's ``rcu_data`` structure.
+
+All of these fields are constant once initialization is complete, and
+therefore need no protection.
+
+Grace-Period Tracking
+'''''''''''''''''''''
+
+This portion of the ``rcu_state`` structure is declared as follows:
+
+::
+
+     1   unsigned long gp_seq;
+
+RCU grace periods are numbered, and the ``->gp_seq`` field contains the
+current grace-period sequence number. The bottom two bits are the state
+of the current grace period, which can be zero for not yet started or
+one for in progress. In other words, if the bottom two bits of
+``->gp_seq`` are zero, then RCU is idle. Any other value in the bottom
+two bits indicates that something is broken. This field is protected by
+the root ``rcu_node`` structure's ``->lock`` field.
+
+There are ``->gp_seq`` fields in the ``rcu_node`` and ``rcu_data``
+structures as well. The fields in the ``rcu_state`` structure represent
+the most current value, and those of the other structures are compared
+in order to detect the beginnings and ends of grace periods in a
+distributed fashion. The values flow from ``rcu_state`` to ``rcu_node``
+(down the tree from the root to the leaves) to ``rcu_data``.
+
+Miscellaneous
+'''''''''''''
+
+This portion of the ``rcu_state`` structure is declared as follows:
+
+::
+
+     1   unsigned long gp_max;
+     2   char abbr;
+     3   char *name;
+
+The ``->gp_max`` field tracks the duration of the longest grace period
+in jiffies. It is protected by the root ``rcu_node``'s ``->lock``.
+
+The ``->name`` and ``->abbr`` fields distinguish between preemptible RCU
+(“rcu_preempt” and “p”) and non-preemptible RCU (“rcu_sched” and “s”).
+These fields are used for diagnostic and tracing purposes.
+
+The ``rcu_node`` Structure
+~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+The ``rcu_node`` structures form the combining tree that propagates
+quiescent-state information from the leaves to the root and also that
+propagates grace-period information from the root down to the leaves.
+They provides local copies of the grace-period state in order to allow
+this information to be accessed in a synchronized manner without
+suffering the scalability limitations that would otherwise be imposed by
+global locking. In ``CONFIG_PREEMPT_RCU`` kernels, they manage the lists
+of tasks that have blocked while in their current RCU read-side critical
+section. In ``CONFIG_PREEMPT_RCU`` with ``CONFIG_RCU_BOOST``, they
+manage the per-\ ``rcu_node`` priority-boosting kernel threads
+(kthreads) and state. Finally, they record CPU-hotplug state in order to
+determine which CPUs should be ignored during a given grace period.
+
+The ``rcu_node`` structure's fields are discussed, singly and in groups,
+in the following sections.
+
+Connection to Combining Tree
+''''''''''''''''''''''''''''
+
+This portion of the ``rcu_node`` structure is declared as follows:
+
+::
+
+     1   struct rcu_node *parent;
+     2   u8 level;
+     3   u8 grpnum;
+     4   unsigned long grpmask;
+     5   int grplo;
+     6   int grphi;
+
+The ``->parent`` pointer references the ``rcu_node`` one level up in the
+tree, and is ``NULL`` for the root ``rcu_node``. The RCU implementation
+makes heavy use of this field to push quiescent states up the tree. The
+``->level`` field gives the level in the tree, with the root being at
+level zero, its children at level one, and so on. The ``->grpnum`` field
+gives this node's position within the children of its parent, so this
+number can range between 0 and 31 on 32-bit systems and between 0 and 63
+on 64-bit systems. The ``->level`` and ``->grpnum`` fields are used only
+during initialization and for tracing. The ``->grpmask`` field is the
+bitmask counterpart of ``->grpnum``, and therefore always has exactly
+one bit set. This mask is used to clear the bit corresponding to this
+``rcu_node`` structure in its parent's bitmasks, which are described
+later. Finally, the ``->grplo`` and ``->grphi`` fields contain the
+lowest and highest numbered CPU served by this ``rcu_node`` structure,
+respectively.
+
+All of these fields are constant, and thus do not require any
+synchronization.
+
+Synchronization
+'''''''''''''''
+
+This field of the ``rcu_node`` structure is declared as follows:
+
+::
+
+     1   raw_spinlock_t lock;
+
+This field is used to protect the remaining fields in this structure,
+unless otherwise stated. That said, all of the fields in this structure
+can be accessed without locking for tracing purposes. Yes, this can
+result in confusing traces, but better some tracing confusion than to be
+heisenbugged out of existence.
+
+.. _grace-period-tracking-1:
+
+Grace-Period Tracking
+'''''''''''''''''''''
+
+This portion of the ``rcu_node`` structure is declared as follows:
+
+::
+
+     1   unsigned long gp_seq;
+     2   unsigned long gp_seq_needed;
+
+The ``rcu_node`` structures' ``->gp_seq`` fields are the counterparts of
+the field of the same name in the ``rcu_state`` structure. They each may
+lag up to one step behind their ``rcu_state`` counterpart. If the bottom
+two bits of a given ``rcu_node`` structure's ``->gp_seq`` field is zero,
+then this ``rcu_node`` structure believes that RCU is idle.
+
+The ``>gp_seq`` field of each ``rcu_node`` structure is updated at the
+beginning and the end of each grace period.
+
+The ``->gp_seq_needed`` fields record the furthest-in-the-future grace
+period request seen by the corresponding ``rcu_node`` structure. The
+request is considered fulfilled when the value of the ``->gp_seq`` field
+equals or exceeds that of the ``->gp_seq_needed`` field.
+
++-----------------------------------------------------------------------+
+| **Quick Quiz**:                                                       |
++-----------------------------------------------------------------------+
+| Suppose that this ``rcu_node`` structure doesn't see a request for a  |
+| very long time. Won't wrapping of the ``->gp_seq`` field cause        |
+| problems?                                                             |
++-----------------------------------------------------------------------+
+| **Answer**:                                                           |
++-----------------------------------------------------------------------+
+| No, because if the ``->gp_seq_needed`` field lags behind the          |
+| ``->gp_seq`` field, the ``->gp_seq_needed`` field will be updated at  |
+| the end of the grace period. Modulo-arithmetic comparisons therefore  |
+| will always get the correct answer, even with wrapping.               |
++-----------------------------------------------------------------------+
+
+Quiescent-State Tracking
+''''''''''''''''''''''''
+
+These fields manage the propagation of quiescent states up the combining
+tree.
+
+This portion of the ``rcu_node`` structure has fields as follows:
+
+::
+
+     1   unsigned long qsmask;
+     2   unsigned long expmask;
+     3   unsigned long qsmaskinit;
+     4   unsigned long expmaskinit;
+
+The ``->qsmask`` field tracks which of this ``rcu_node`` structure's
+children still need to report quiescent states for the current normal
+grace period. Such children will have a value of 1 in their
+corresponding bit. Note that the leaf ``rcu_node`` structures should be
+thought of as having ``rcu_data`` structures as their children.
+Similarly, the ``->expmask`` field tracks which of this ``rcu_node``
+structure's children still need to report quiescent states for the
+current expedited grace period. An expedited grace period has the same
+conceptual properties as a normal grace period, but the expedited
+implementation accepts extreme CPU overhead to obtain much lower
+grace-period latency, for example, consuming a few tens of microseconds
+worth of CPU time to reduce grace-period duration from milliseconds to
+tens of microseconds. The ``->qsmaskinit`` field tracks which of this
+``rcu_node`` structure's children cover for at least one online CPU.
+This mask is used to initialize ``->qsmask``, and ``->expmaskinit`` is
+used to initialize ``->expmask`` and the beginning of the normal and
+expedited grace periods, respectively.
+
++-----------------------------------------------------------------------+
+| **Quick Quiz**:                                                       |
++-----------------------------------------------------------------------+
+| Why are these bitmasks protected by locking? Come on, haven't you     |
+| heard of atomic instructions???                                       |
++-----------------------------------------------------------------------+
+| **Answer**:                                                           |
++-----------------------------------------------------------------------+
+| Lockless grace-period computation! Such a tantalizing possibility!    |
+| But consider the following sequence of events:                        |
+|                                                                       |
+| #. CPU 0 has been in dyntick-idle mode for quite some time. When it   |
+|    wakes up, it notices that the current RCU grace period needs it to |
+|    report in, so it sets a flag where the scheduling clock interrupt  |
+|    will find it.                                                      |
+| #. Meanwhile, CPU 1 is running ``force_quiescent_state()``, and       |
+|    notices that CPU 0 has been in dyntick idle mode, which qualifies  |
+|    as an extended quiescent state.                                    |
+| #. CPU 0's scheduling clock interrupt fires in the middle of an RCU   |
+|    read-side critical section, and notices that the RCU core needs    |
+|    something, so commences RCU softirq processing.                    |
+| #. CPU 0's softirq handler executes and is just about ready to report |
+|    its quiescent state up the ``rcu_node`` tree.                      |
+| #. But CPU 1 beats it to the punch, completing the current grace      |
+|    period and starting a new one.                                     |
+| #. CPU 0 now reports its quiescent state for the wrong grace period.  |
+|    That grace period might now end before the RCU read-side critical  |
+|    section. If that happens, disaster will ensue.                     |
+|                                                                       |
+| So the locking is absolutely required in order to coordinate clearing |
+| of the bits with updating of the grace-period sequence number in      |
+| ``->gp_seq``.                                                         |
++-----------------------------------------------------------------------+
+
+Blocked-Task Management
+'''''''''''''''''''''''
+
+``PREEMPT_RCU`` allows tasks to be preempted in the midst of their RCU
+read-side critical sections, and these tasks must be tracked explicitly.
+The details of exactly why and how they are tracked will be covered in a
+separate article on RCU read-side processing. For now, it is enough to
+know that the ``rcu_node`` structure tracks them.
+
+::
+
+     1   struct list_head blkd_tasks;
+     2   struct list_head *gp_tasks;
+     3   struct list_head *exp_tasks;
+     4   bool wait_blkd_tasks;
+
+The ``->blkd_tasks`` field is a list header for the list of blocked and
+preempted tasks. As tasks undergo context switches within RCU read-side
+critical sections, their ``task_struct`` structures are enqueued (via
+the ``task_struct``'s ``->rcu_node_entry`` field) onto the head of the
+``->blkd_tasks`` list for the leaf ``rcu_node`` structure corresponding
+to the CPU on which the outgoing context switch executed. As these tasks
+later exit their RCU read-side critical sections, they remove themselves
+from the list. This list is therefore in reverse time order, so that if
+one of the tasks is blocking the current grace period, all subsequent
+tasks must also be blocking that same grace period. Therefore, a single
+pointer into this list suffices to track all tasks blocking a given
+grace period. That pointer is stored in ``->gp_tasks`` for normal grace
+periods and in ``->exp_tasks`` for expedited grace periods. These last
+two fields are ``NULL`` if either there is no grace period in flight or
+if there are no blocked tasks preventing that grace period from
+completing. If either of these two pointers is referencing a task that
+removes itself from the ``->blkd_tasks`` list, then that task must
+advance the pointer to the next task on the list, or set the pointer to
+``NULL`` if there are no subsequent tasks on the list.
+
+For example, suppose that tasks T1, T2, and T3 are all hard-affinitied
+to the largest-numbered CPU in the system. Then if task T1 blocked in an
+RCU read-side critical section, then an expedited grace period started,
+then task T2 blocked in an RCU read-side critical section, then a normal
+grace period started, and finally task 3 blocked in an RCU read-side
+critical section, then the state of the last leaf ``rcu_node``
+structure's blocked-task list would be as shown below:
+
+.. kernel-figure:: blkd_task.svg
+
+Task T1 is blocking both grace periods, task T2 is blocking only the
+normal grace period, and task T3 is blocking neither grace period. Note
+that these tasks will not remove themselves from this list immediately
+upon resuming execution. They will instead remain on the list until they
+execute the outermost ``rcu_read_unlock()`` that ends their RCU
+read-side critical section.
+
+The ``->wait_blkd_tasks`` field indicates whether or not the current
+grace period is waiting on a blocked task.
+
+Sizing the ``rcu_node`` Array
+'''''''''''''''''''''''''''''
+
+The ``rcu_node`` array is sized via a series of C-preprocessor
+expressions as follows:
+
+::
+
+    1 #ifdef CONFIG_RCU_FANOUT
+    2 #define RCU_FANOUT CONFIG_RCU_FANOUT
+    3 #else
+    4 # ifdef CONFIG_64BIT
+    5 # define RCU_FANOUT 64
+    6 # else
+    7 # define RCU_FANOUT 32
+    8 # endif
+    9 #endif
+   10
+   11 #ifdef CONFIG_RCU_FANOUT_LEAF
+   12 #define RCU_FANOUT_LEAF CONFIG_RCU_FANOUT_LEAF
+   13 #else
+   14 # ifdef CONFIG_64BIT
+   15 # define RCU_FANOUT_LEAF 64
+   16 # else
+   17 # define RCU_FANOUT_LEAF 32
+   18 # endif
+   19 #endif
+   20
+   21 #define RCU_FANOUT_1        (RCU_FANOUT_LEAF)
+   22 #define RCU_FANOUT_2        (RCU_FANOUT_1 * RCU_FANOUT)
+   23 #define RCU_FANOUT_3        (RCU_FANOUT_2 * RCU_FANOUT)
+   24 #define RCU_FANOUT_4        (RCU_FANOUT_3 * RCU_FANOUT)
+   25
+   26 #if NR_CPUS <= RCU_FANOUT_1
+   27 #  define RCU_NUM_LVLS        1
+   28 #  define NUM_RCU_LVL_0        1
+   29 #  define NUM_RCU_NODES        NUM_RCU_LVL_0
+   30 #  define NUM_RCU_LVL_INIT    { NUM_RCU_LVL_0 }
+   31 #  define RCU_NODE_NAME_INIT  { "rcu_node_0" }
+   32 #  define RCU_FQS_NAME_INIT   { "rcu_node_fqs_0" }
+   33 #  define RCU_EXP_NAME_INIT   { "rcu_node_exp_0" }
+   34 #elif NR_CPUS <= RCU_FANOUT_2
+   35 #  define RCU_NUM_LVLS        2
+   36 #  define NUM_RCU_LVL_0        1
+   37 #  define NUM_RCU_LVL_1        DIV_ROUND_UP(NR_CPUS, RCU_FANOUT_1)
+   38 #  define NUM_RCU_NODES        (NUM_RCU_LVL_0 + NUM_RCU_LVL_1)
+   39 #  define NUM_RCU_LVL_INIT    { NUM_RCU_LVL_0, NUM_RCU_LVL_1 }
+   40 #  define RCU_NODE_NAME_INIT  { "rcu_node_0", "rcu_node_1" }
+   41 #  define RCU_FQS_NAME_INIT   { "rcu_node_fqs_0", "rcu_node_fqs_1" }
+   42 #  define RCU_EXP_NAME_INIT   { "rcu_node_exp_0", "rcu_node_exp_1" }
+   43 #elif NR_CPUS <= RCU_FANOUT_3
+   44 #  define RCU_NUM_LVLS        3
+   45 #  define NUM_RCU_LVL_0        1
+   46 #  define NUM_RCU_LVL_1        DIV_ROUND_UP(NR_CPUS, RCU_FANOUT_2)
+   47 #  define NUM_RCU_LVL_2        DIV_ROUND_UP(NR_CPUS, RCU_FANOUT_1)
+   48 #  define NUM_RCU_NODES        (NUM_RCU_LVL_0 + NUM_RCU_LVL_1 + NUM_RCU_LVL_2)
+   49 #  define NUM_RCU_LVL_INIT    { NUM_RCU_LVL_0, NUM_RCU_LVL_1, NUM_RCU_LVL_2 }
+   50 #  define RCU_NODE_NAME_INIT  { "rcu_node_0", "rcu_node_1", "rcu_node_2" }
+   51 #  define RCU_FQS_NAME_INIT   { "rcu_node_fqs_0", "rcu_node_fqs_1", "rcu_node_fqs_2" }
+   52 #  define RCU_EXP_NAME_INIT   { "rcu_node_exp_0", "rcu_node_exp_1", "rcu_node_exp_2" }
+   53 #elif NR_CPUS <= RCU_FANOUT_4
+   54 #  define RCU_NUM_LVLS        4
+   55 #  define NUM_RCU_LVL_0        1
+   56 #  define NUM_RCU_LVL_1        DIV_ROUND_UP(NR_CPUS, RCU_FANOUT_3)
+   57 #  define NUM_RCU_LVL_2        DIV_ROUND_UP(NR_CPUS, RCU_FANOUT_2)
+   58 #  define NUM_RCU_LVL_3        DIV_ROUND_UP(NR_CPUS, RCU_FANOUT_1)
+   59 #  define NUM_RCU_NODES        (NUM_RCU_LVL_0 + NUM_RCU_LVL_1 + NUM_RCU_LVL_2 + NUM_RCU_LVL_3)
+   60 #  define NUM_RCU_LVL_INIT    { NUM_RCU_LVL_0, NUM_RCU_LVL_1, NUM_RCU_LVL_2, NUM_RCU_LVL_3 }
+   61 #  define RCU_NODE_NAME_INIT  { "rcu_node_0", "rcu_node_1", "rcu_node_2", "rcu_node_3" }
+   62 #  define RCU_FQS_NAME_INIT   { "rcu_node_fqs_0", "rcu_node_fqs_1", "rcu_node_fqs_2", "rcu_node_fqs_3" }
+   63 #  define RCU_EXP_NAME_INIT   { "rcu_node_exp_0", "rcu_node_exp_1", "rcu_node_exp_2", "rcu_node_exp_3" }
+   64 #else
+   65 # error "CONFIG_RCU_FANOUT insufficient for NR_CPUS"
+   66 #endif
+
+The maximum number of levels in the ``rcu_node`` structure is currently
+limited to four, as specified by lines 21-24 and the structure of the
+subsequent “if” statement. For 32-bit systems, this allows
+16*32*32*32=524,288 CPUs, which should be sufficient for the next few
+years at least. For 64-bit systems, 16*64*64*64=4,194,304 CPUs is
+allowed, which should see us through the next decade or so. This
+four-level tree also allows kernels built with ``CONFIG_RCU_FANOUT=8``
+to support up to 4096 CPUs, which might be useful in very large systems
+having eight CPUs per socket (but please note that no one has yet shown
+any measurable performance degradation due to misaligned socket and
+``rcu_node`` boundaries). In addition, building kernels with a full four
+levels of ``rcu_node`` tree permits better testing of RCU's
+combining-tree code.
+
+The ``RCU_FANOUT`` symbol controls how many children are permitted at
+each non-leaf level of the ``rcu_node`` tree. If the
+``CONFIG_RCU_FANOUT`` Kconfig option is not specified, it is set based
+on the word size of the system, which is also the Kconfig default.
+
+The ``RCU_FANOUT_LEAF`` symbol controls how many CPUs are handled by
+each leaf ``rcu_node`` structure. Experience has shown that allowing a
+given leaf ``rcu_node`` structure to handle 64 CPUs, as permitted by the
+number of bits in the ``->qsmask`` field on a 64-bit system, results in
+excessive contention for the leaf ``rcu_node`` structures' ``->lock``
+fields. The number of CPUs per leaf ``rcu_node`` structure is therefore
+limited to 16 given the default value of ``CONFIG_RCU_FANOUT_LEAF``. If
+``CONFIG_RCU_FANOUT_LEAF`` is unspecified, the value selected is based
+on the word size of the system, just as for ``CONFIG_RCU_FANOUT``.
+Lines 11-19 perform this computation.
+
+Lines 21-24 compute the maximum number of CPUs supported by a
+single-level (which contains a single ``rcu_node`` structure),
+two-level, three-level, and four-level ``rcu_node`` tree, respectively,
+given the fanout specified by ``RCU_FANOUT`` and ``RCU_FANOUT_LEAF``.
+These numbers of CPUs are retained in the ``RCU_FANOUT_1``,
+``RCU_FANOUT_2``, ``RCU_FANOUT_3``, and ``RCU_FANOUT_4`` C-preprocessor
+variables, respectively.
+
+These variables are used to control the C-preprocessor ``#if`` statement
+spanning lines 26-66 that computes the number of ``rcu_node`` structures
+required for each level of the tree, as well as the number of levels
+required. The number of levels is placed in the ``NUM_RCU_LVLS``
+C-preprocessor variable by lines 27, 35, 44, and 54. The number of
+``rcu_node`` structures for the topmost level of the tree is always
+exactly one, and this value is unconditionally placed into
+``NUM_RCU_LVL_0`` by lines 28, 36, 45, and 55. The rest of the levels
+(if any) of the ``rcu_node`` tree are computed by dividing the maximum
+number of CPUs by the fanout supported by the number of levels from the
+current level down, rounding up. This computation is performed by
+lines 37, 46-47, and 56-58. Lines 31-33, 40-42, 50-52, and 62-63 create
+initializers for lockdep lock-class names. Finally, lines 64-66 produce
+an error if the maximum number of CPUs is too large for the specified
+fanout.
+
+The ``rcu_segcblist`` Structure
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+The ``rcu_segcblist`` structure maintains a segmented list of callbacks
+as follows:
+
+::
+
+    1 #define RCU_DONE_TAIL        0
+    2 #define RCU_WAIT_TAIL        1
+    3 #define RCU_NEXT_READY_TAIL  2
+    4 #define RCU_NEXT_TAIL        3
+    5 #define RCU_CBLIST_NSEGS     4
+    6
+    7 struct rcu_segcblist {
+    8   struct rcu_head *head;
+    9   struct rcu_head **tails[RCU_CBLIST_NSEGS];
+   10   unsigned long gp_seq[RCU_CBLIST_NSEGS];
+   11   long len;
+   12   long len_lazy;
+   13 };
+
+The segments are as follows:
+
+#. ``RCU_DONE_TAIL``: Callbacks whose grace periods have elapsed. These
+   callbacks are ready to be invoked.
+#. ``RCU_WAIT_TAIL``: Callbacks that are waiting for the current grace
+   period. Note that different CPUs can have different ideas about which
+   grace period is current, hence the ``->gp_seq`` field.
+#. ``RCU_NEXT_READY_TAIL``: Callbacks waiting for the next grace period
+   to start.
+#. ``RCU_NEXT_TAIL``: Callbacks that have not yet been associated with a
+   grace period.
+
+The ``->head`` pointer references the first callback or is ``NULL`` if
+the list contains no callbacks (which is *not* the same as being empty).
+Each element of the ``->tails[]`` array references the ``->next``
+pointer of the last callback in the corresponding segment of the list,
+or the list's ``->head`` pointer if that segment and all previous
+segments are empty. If the corresponding segment is empty but some
+previous segment is not empty, then the array element is identical to
+its predecessor. Older callbacks are closer to the head of the list, and
+new callbacks are added at the tail. This relationship between the
+``->head`` pointer, the ``->tails[]`` array, and the callbacks is shown
+in this diagram:
+
+.. kernel-figure:: nxtlist.svg
+
+In this figure, the ``->head`` pointer references the first RCU callback
+in the list. The ``->tails[RCU_DONE_TAIL]`` array element references the
+``->head`` pointer itself, indicating that none of the callbacks is
+ready to invoke. The ``->tails[RCU_WAIT_TAIL]`` array element references
+callback CB 2's ``->next`` pointer, which indicates that CB 1 and CB 2
+are both waiting on the current grace period, give or take possible
+disagreements about exactly which grace period is the current one. The
+``->tails[RCU_NEXT_READY_TAIL]`` array element references the same RCU
+callback that ``->tails[RCU_WAIT_TAIL]`` does, which indicates that
+there are no callbacks waiting on the next RCU grace period. The
+``->tails[RCU_NEXT_TAIL]`` array element references CB 4's ``->next``
+pointer, indicating that all the remaining RCU callbacks have not yet
+been assigned to an RCU grace period. Note that the
+``->tails[RCU_NEXT_TAIL]`` array element always references the last RCU
+callback's ``->next`` pointer unless the callback list is empty, in
+which case it references the ``->head`` pointer.
+
+There is one additional important special case for the
+``->tails[RCU_NEXT_TAIL]`` array element: It can be ``NULL`` when this
+list is *disabled*. Lists are disabled when the corresponding CPU is
+offline or when the corresponding CPU's callbacks are offloaded to a
+kthread, both of which are described elsewhere.
+
+CPUs advance their callbacks from the ``RCU_NEXT_TAIL`` to the
+``RCU_NEXT_READY_TAIL`` to the ``RCU_WAIT_TAIL`` to the
+``RCU_DONE_TAIL`` list segments as grace periods advance.
+
+The ``->gp_seq[]`` array records grace-period numbers corresponding to
+the list segments. This is what allows different CPUs to have different
+ideas as to which is the current grace period while still avoiding
+premature invocation of their callbacks. In particular, this allows CPUs
+that go idle for extended periods to determine which of their callbacks
+are ready to be invoked after reawakening.
+
+The ``->len`` counter contains the number of callbacks in ``->head``,
+and the ``->len_lazy`` contains the number of those callbacks that are
+known to only free memory, and whose invocation can therefore be safely
+deferred.
+
+.. important::
+
+   It is the ``->len`` field that determines whether or
+   not there are callbacks associated with this ``rcu_segcblist``
+   structure, *not* the ``->head`` pointer. The reason for this is that all
+   the ready-to-invoke callbacks (that is, those in the ``RCU_DONE_TAIL``
+   segment) are extracted all at once at callback-invocation time
+   (``rcu_do_batch``), due to which ``->head`` may be set to NULL if there
+   are no not-done callbacks remaining in the ``rcu_segcblist``. If
+   callback invocation must be postponed, for example, because a
+   high-priority process just woke up on this CPU, then the remaining
+   callbacks are placed back on the ``RCU_DONE_TAIL`` segment and
+   ``->head`` once again points to the start of the segment. In short, the
+   head field can briefly be ``NULL`` even though the CPU has callbacks
+   present the entire time. Therefore, it is not appropriate to test the
+   ``->head`` pointer for ``NULL``.
+
+In contrast, the ``->len`` and ``->len_lazy`` counts are adjusted only
+after the corresponding callbacks have been invoked. This means that the
+``->len`` count is zero only if the ``rcu_segcblist`` structure really
+is devoid of callbacks. Of course, off-CPU sampling of the ``->len``
+count requires careful use of appropriate synchronization, for example,
+memory barriers. This synchronization can be a bit subtle, particularly
+in the case of ``rcu_barrier()``.
+
+The ``rcu_data`` Structure
+~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+The ``rcu_data`` maintains the per-CPU state for the RCU subsystem. The
+fields in this structure may be accessed only from the corresponding CPU
+(and from tracing) unless otherwise stated. This structure is the focus
+of quiescent-state detection and RCU callback queuing. It also tracks
+its relationship to the corresponding leaf ``rcu_node`` structure to
+allow more-efficient propagation of quiescent states up the ``rcu_node``
+combining tree. Like the ``rcu_node`` structure, it provides a local
+copy of the grace-period information to allow for-free synchronized
+access to this information from the corresponding CPU. Finally, this
+structure records past dyntick-idle state for the corresponding CPU and
+also tracks statistics.
+
+The ``rcu_data`` structure's fields are discussed, singly and in groups,
+in the following sections.
+
+Connection to Other Data Structures
+'''''''''''''''''''''''''''''''''''
+
+This portion of the ``rcu_data`` structure is declared as follows:
+
+::
+
+     1   int cpu;
+     2   struct rcu_node *mynode;
+     3   unsigned long grpmask;
+     4   bool beenonline;
+
+The ``->cpu`` field contains the number of the corresponding CPU and the
+``->mynode`` field references the corresponding ``rcu_node`` structure.
+The ``->mynode`` is used to propagate quiescent states up the combining
+tree. These two fields are constant and therefore do not require
+synchronization.
+
+The ``->grpmask`` field indicates the bit in the ``->mynode->qsmask``
+corresponding to this ``rcu_data`` structure, and is also used when
+propagating quiescent states. The ``->beenonline`` flag is set whenever
+the corresponding CPU comes online, which means that the debugfs tracing
+need not dump out any ``rcu_data`` structure for which this flag is not
+set.
+
+Quiescent-State and Grace-Period Tracking
+'''''''''''''''''''''''''''''''''''''''''
+
+This portion of the ``rcu_data`` structure is declared as follows:
+
+::
+
+     1   unsigned long gp_seq;
+     2   unsigned long gp_seq_needed;
+     3   bool cpu_no_qs;
+     4   bool core_needs_qs;
+     5   bool gpwrap;
+
+The ``->gp_seq`` field is the counterpart of the field of the same name
+in the ``rcu_state`` and ``rcu_node`` structures. The
+``->gp_seq_needed`` field is the counterpart of the field of the same
+name in the rcu_node structure. They may each lag up to one behind their
+``rcu_node`` counterparts, but in ``CONFIG_NO_HZ_IDLE`` and
+``CONFIG_NO_HZ_FULL`` kernels can lag arbitrarily far behind for CPUs in
+dyntick-idle mode (but these counters will catch up upon exit from
+dyntick-idle mode). If the lower two bits of a given ``rcu_data``
+structure's ``->gp_seq`` are zero, then this ``rcu_data`` structure
+believes that RCU is idle.
+
++-----------------------------------------------------------------------+
+| **Quick Quiz**:                                                       |
++-----------------------------------------------------------------------+
+| All this replication of the grace period numbers can only cause       |
+| massive confusion. Why not just keep a global sequence number and be  |
+| done with it???                                                       |
++-----------------------------------------------------------------------+
+| **Answer**:                                                           |
++-----------------------------------------------------------------------+
+| Because if there was only a single global sequence numbers, there     |
+| would need to be a single global lock to allow safely accessing and   |
+| updating it. And if we are not going to have a single global lock, we |
+| need to carefully manage the numbers on a per-node basis. Recall from |
+| the answer to a previous Quick Quiz that the consequences of applying |
+| a previously sampled quiescent state to the wrong grace period are    |
+| quite severe.                                                         |
++-----------------------------------------------------------------------+
+
+The ``->cpu_no_qs`` flag indicates that the CPU has not yet passed
+through a quiescent state, while the ``->core_needs_qs`` flag indicates
+that the RCU core needs a quiescent state from the corresponding CPU.
+The ``->gpwrap`` field indicates that the corresponding CPU has remained
+idle for so long that the ``gp_seq`` counter is in danger of overflow,
+which will cause the CPU to disregard the values of its counters on its
+next exit from idle.
+
+RCU Callback Handling
+'''''''''''''''''''''
+
+In the absence of CPU-hotplug events, RCU callbacks are invoked by the
+same CPU that registered them. This is strictly a cache-locality
+optimization: callbacks can and do get invoked on CPUs other than the
+one that registered them. After all, if the CPU that registered a given
+callback has gone offline before the callback can be invoked, there
+really is no other choice.
+
+This portion of the ``rcu_data`` structure is declared as follows:
+
+::
+
+    1 struct rcu_segcblist cblist;
+    2 long qlen_last_fqs_check;
+    3 unsigned long n_cbs_invoked;
+    4 unsigned long n_nocbs_invoked;
+    5 unsigned long n_cbs_orphaned;
+    6 unsigned long n_cbs_adopted;
+    7 unsigned long n_force_qs_snap;
+    8 long blimit;
+
+The ``->cblist`` structure is the segmented callback list described
+earlier. The CPU advances the callbacks in its ``rcu_data`` structure
+whenever it notices that another RCU grace period has completed. The CPU
+detects the completion of an RCU grace period by noticing that the value
+of its ``rcu_data`` structure's ``->gp_seq`` field differs from that of
+its leaf ``rcu_node`` structure. Recall that each ``rcu_node``
+structure's ``->gp_seq`` field is updated at the beginnings and ends of
+each grace period.
+
+The ``->qlen_last_fqs_check`` and ``->n_force_qs_snap`` coordinate the
+forcing of quiescent states from ``call_rcu()`` and friends when
+callback lists grow excessively long.
+
+The ``->n_cbs_invoked``, ``->n_cbs_orphaned``, and ``->n_cbs_adopted``
+fields count the number of callbacks invoked, sent to other CPUs when
+this CPU goes offline, and received from other CPUs when those other
+CPUs go offline. The ``->n_nocbs_invoked`` is used when the CPU's
+callbacks are offloaded to a kthread.
+
+Finally, the ``->blimit`` counter is the maximum number of RCU callbacks
+that may be invoked at a given time.
+
+Dyntick-Idle Handling
+'''''''''''''''''''''
+
+This portion of the ``rcu_data`` structure is declared as follows:
+
+::
+
+     1   int dynticks_snap;
+     2   unsigned long dynticks_fqs;
+
+The ``->dynticks_snap`` field is used to take a snapshot of the
+corresponding CPU's dyntick-idle state when forcing quiescent states,
+and is therefore accessed from other CPUs. Finally, the
+``->dynticks_fqs`` field is used to count the number of times this CPU
+is determined to be in dyntick-idle state, and is used for tracing and
+debugging purposes.
+
+This portion of the rcu_data structure is declared as follows:
+
+::
+
+     1   long dynticks_nesting;
+     2   long dynticks_nmi_nesting;
+     3   atomic_t dynticks;
+     4   bool rcu_need_heavy_qs;
+     5   bool rcu_urgent_qs;
+
+These fields in the rcu_data structure maintain the per-CPU dyntick-idle
+state for the corresponding CPU. The fields may be accessed only from
+the corresponding CPU (and from tracing) unless otherwise stated.
+
+The ``->dynticks_nesting`` field counts the nesting depth of process
+execution, so that in normal circumstances this counter has value zero
+or one. NMIs, irqs, and tracers are counted by the
+``->dynticks_nmi_nesting`` field. Because NMIs cannot be masked, changes
+to this variable have to be undertaken carefully using an algorithm
+provided by Andy Lutomirski. The initial transition from idle adds one,
+and nested transitions add two, so that a nesting level of five is
+represented by a ``->dynticks_nmi_nesting`` value of nine. This counter
+can therefore be thought of as counting the number of reasons why this
+CPU cannot be permitted to enter dyntick-idle mode, aside from
+process-level transitions.
+
+However, it turns out that when running in non-idle kernel context, the
+Linux kernel is fully capable of entering interrupt handlers that never
+exit and perhaps also vice versa. Therefore, whenever the
+``->dynticks_nesting`` field is incremented up from zero, the
+``->dynticks_nmi_nesting`` field is set to a large positive number, and
+whenever the ``->dynticks_nesting`` field is decremented down to zero,
+the the ``->dynticks_nmi_nesting`` field is set to zero. Assuming that
+the number of misnested interrupts is not sufficient to overflow the
+counter, this approach corrects the ``->dynticks_nmi_nesting`` field
+every time the corresponding CPU enters the idle loop from process
+context.
+
+The ``->dynticks`` field counts the corresponding CPU's transitions to
+and from either dyntick-idle or user mode, so that this counter has an
+even value when the CPU is in dyntick-idle mode or user mode and an odd
+value otherwise. The transitions to/from user mode need to be counted
+for user mode adaptive-ticks support (see timers/NO_HZ.txt).
+
+The ``->rcu_need_heavy_qs`` field is used to record the fact that the
+RCU core code would really like to see a quiescent state from the
+corresponding CPU, so much so that it is willing to call for
+heavy-weight dyntick-counter operations. This flag is checked by RCU's
+context-switch and ``cond_resched()`` code, which provide a momentary
+idle sojourn in response.
+
+Finally, the ``->rcu_urgent_qs`` field is used to record the fact that
+the RCU core code would really like to see a quiescent state from the
+corresponding CPU, with the various other fields indicating just how
+badly RCU wants this quiescent state. This flag is checked by RCU's
+context-switch path (``rcu_note_context_switch``) and the cond_resched
+code.
+
++-----------------------------------------------------------------------+
+| **Quick Quiz**:                                                       |
++-----------------------------------------------------------------------+
+| Why not simply combine the ``->dynticks_nesting`` and                 |
+| ``->dynticks_nmi_nesting`` counters into a single counter that just   |
+| counts the number of reasons that the corresponding CPU is non-idle?  |
++-----------------------------------------------------------------------+
+| **Answer**:                                                           |
++-----------------------------------------------------------------------+
+| Because this would fail in the presence of interrupts whose handlers  |
+| never return and of handlers that manage to return from a made-up     |
+| interrupt.                                                            |
++-----------------------------------------------------------------------+
+
+Additional fields are present for some special-purpose builds, and are
+discussed separately.
+
+The ``rcu_head`` Structure
+~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+Each ``rcu_head`` structure represents an RCU callback. These structures
+are normally embedded within RCU-protected data structures whose
+algorithms use asynchronous grace periods. In contrast, when using
+algorithms that block waiting for RCU grace periods, RCU users need not
+provide ``rcu_head`` structures.
+
+The ``rcu_head`` structure has fields as follows:
+
+::
+
+     1   struct rcu_head *next;
+     2   void (*func)(struct rcu_head *head);
+
+The ``->next`` field is used to link the ``rcu_head`` structures
+together in the lists within the ``rcu_data`` structures. The ``->func``
+field is a pointer to the function to be called when the callback is
+ready to be invoked, and this function is passed a pointer to the
+``rcu_head`` structure. However, ``kfree_rcu()`` uses the ``->func``
+field to record the offset of the ``rcu_head`` structure within the
+enclosing RCU-protected data structure.
+
+Both of these fields are used internally by RCU. From the viewpoint of
+RCU users, this structure is an opaque “cookie”.
+
++-----------------------------------------------------------------------+
+| **Quick Quiz**:                                                       |
++-----------------------------------------------------------------------+
+| Given that the callback function ``->func`` is passed a pointer to    |
+| the ``rcu_head`` structure, how is that function supposed to find the |
+| beginning of the enclosing RCU-protected data structure?              |
++-----------------------------------------------------------------------+
+| **Answer**:                                                           |
++-----------------------------------------------------------------------+
+| In actual practice, there is a separate callback function per type of |
+| RCU-protected data structure. The callback function can therefore use |
+| the ``container_of()`` macro in the Linux kernel (or other            |
+| pointer-manipulation facilities in other software environments) to    |
+| find the beginning of the enclosing structure.                        |
++-----------------------------------------------------------------------+
+
+RCU-Specific Fields in the ``task_struct`` Structure
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+The ``CONFIG_PREEMPT_RCU`` implementation uses some additional fields in
+the ``task_struct`` structure:
+
+::
+
+    1 #ifdef CONFIG_PREEMPT_RCU
+    2   int rcu_read_lock_nesting;
+    3   union rcu_special rcu_read_unlock_special;
+    4   struct list_head rcu_node_entry;
+    5   struct rcu_node *rcu_blocked_node;
+    6 #endif /* #ifdef CONFIG_PREEMPT_RCU */
+    7 #ifdef CONFIG_TASKS_RCU
+    8   unsigned long rcu_tasks_nvcsw;
+    9   bool rcu_tasks_holdout;
+   10   struct list_head rcu_tasks_holdout_list;
+   11   int rcu_tasks_idle_cpu;
+   12 #endif /* #ifdef CONFIG_TASKS_RCU */
+
+The ``->rcu_read_lock_nesting`` field records the nesting level for RCU
+read-side critical sections, and the ``->rcu_read_unlock_special`` field
+is a bitmask that records special conditions that require
+``rcu_read_unlock()`` to do additional work. The ``->rcu_node_entry``
+field is used to form lists of tasks that have blocked within
+preemptible-RCU read-side critical sections and the
+``->rcu_blocked_node`` field references the ``rcu_node`` structure whose
+list this task is a member of, or ``NULL`` if it is not blocked within a
+preemptible-RCU read-side critical section.
+
+The ``->rcu_tasks_nvcsw`` field tracks the number of voluntary context
+switches that this task had undergone at the beginning of the current
+tasks-RCU grace period, ``->rcu_tasks_holdout`` is set if the current
+tasks-RCU grace period is waiting on this task,
+``->rcu_tasks_holdout_list`` is a list element enqueuing this task on
+the holdout list, and ``->rcu_tasks_idle_cpu`` tracks which CPU this
+idle task is running, but only if the task is currently running, that
+is, if the CPU is currently idle.
+
+Accessor Functions
+~~~~~~~~~~~~~~~~~~
+
+The following listing shows the ``rcu_get_root()``,
+``rcu_for_each_node_breadth_first`` and ``rcu_for_each_leaf_node()``
+function and macros:
+
+::
+
+     1 static struct rcu_node *rcu_get_root(struct rcu_state *rsp)
+     2 {
+     3   return &rsp->node[0];
+     4 }
+     5
+     6 #define rcu_for_each_node_breadth_first(rsp, rnp) \
+     7   for ((rnp) = &(rsp)->node[0]; \
+     8        (rnp) < &(rsp)->node[NUM_RCU_NODES]; (rnp)++)
+     9
+    10 #define rcu_for_each_leaf_node(rsp, rnp) \
+    11   for ((rnp) = (rsp)->level[NUM_RCU_LVLS - 1]; \
+    12        (rnp) < &(rsp)->node[NUM_RCU_NODES]; (rnp)++)
+
+The ``rcu_get_root()`` simply returns a pointer to the first element of
+the specified ``rcu_state`` structure's ``->node[]`` array, which is the
+root ``rcu_node`` structure.
+
+As noted earlier, the ``rcu_for_each_node_breadth_first()`` macro takes
+advantage of the layout of the ``rcu_node`` structures in the
+``rcu_state`` structure's ``->node[]`` array, performing a breadth-first
+traversal by simply traversing the array in order. Similarly, the
+``rcu_for_each_leaf_node()`` macro traverses only the last part of the
+array, thus traversing only the leaf ``rcu_node`` structures.
+
++-----------------------------------------------------------------------+
+| **Quick Quiz**:                                                       |
++-----------------------------------------------------------------------+
+| What does ``rcu_for_each_leaf_node()`` do if the ``rcu_node`` tree    |
+| contains only a single node?                                          |
++-----------------------------------------------------------------------+
+| **Answer**:                                                           |
++-----------------------------------------------------------------------+
+| In the single-node case, ``rcu_for_each_leaf_node()`` traverses the   |
+| single node.                                                          |
++-----------------------------------------------------------------------+
+
+Summary
+~~~~~~~
+
+So the state of RCU is represented by an ``rcu_state`` structure, which
+contains a combining tree of ``rcu_node`` and ``rcu_data`` structures.
+Finally, in ``CONFIG_NO_HZ_IDLE`` kernels, each CPU's dyntick-idle state
+is tracked by dynticks-related fields in the ``rcu_data`` structure. If
+you made it this far, you are well prepared to read the code
+walkthroughs in the other articles in this series.
+
+Acknowledgments
+~~~~~~~~~~~~~~~
+
+I owe thanks to Cyrill Gorcunov, Mathieu Desnoyers, Dhaval Giani, Paul
+Turner, Abhishek Srivastava, Matt Kowalczyk, and Serge Hallyn for
+helping me get this document into a more human-readable state.
+
+Legal Statement
+~~~~~~~~~~~~~~~
+
+This work represents the view of the author and does not necessarily
+represent the view of IBM.
+
+Linux is a registered trademark of Linus Torvalds.
+
+Other company, product, and service names may be trademarks or service
+marks of others.
diff --git a/Documentation/RCU/Design/Expedited-Grace-Periods/Expedited-Grace-Periods.html b/Documentation/RCU/Design/Expedited-Grace-Periods/Expedited-Grace-Periods.html
deleted file mode 100644
index 57300db4b5ff..000000000000
--- a/Documentation/RCU/Design/Expedited-Grace-Periods/Expedited-Grace-Periods.html
+++ /dev/null
@@ -1,668 +0,0 @@
-<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN"
-        "http://www.w3.org/TR/html4/loose.dtd">
-        <html>
-        <head><title>A Tour Through TREE_RCU's Expedited Grace Periods</title>
-        <meta HTTP-EQUIV="Content-Type" CONTENT="text/html; charset=iso-8859-1">
-
-<h2>Introduction</h2>
-
-This document describes RCU's expedited grace periods.
-Unlike RCU's normal grace periods, which accept long latencies to attain
-high efficiency and minimal disturbance, expedited grace periods accept
-lower efficiency and significant disturbance to attain shorter latencies.
-
-<p>
-There are two flavors of RCU (RCU-preempt and RCU-sched), with an earlier
-third RCU-bh flavor having been implemented in terms of the other two.
-Each of the two implementations is covered in its own section.
-
-<ol>
-<li>	<a href="#Expedited Grace Period Design">
-	Expedited Grace Period Design</a>
-<li>	<a href="#RCU-preempt Expedited Grace Periods">
-	RCU-preempt Expedited Grace Periods</a>
-<li>	<a href="#RCU-sched Expedited Grace Periods">
-	RCU-sched Expedited Grace Periods</a>
-<li>	<a href="#Expedited Grace Period and CPU Hotplug">
-	Expedited Grace Period and CPU Hotplug</a>
-<li>	<a href="#Expedited Grace Period Refinements">
-	Expedited Grace Period Refinements</a>
-</ol>
-
-<h2><a name="Expedited Grace Period Design">
-Expedited Grace Period Design</a></h2>
-
-<p>
-The expedited RCU grace periods cannot be accused of being subtle,
-given that they for all intents and purposes hammer every CPU that
-has not yet provided a quiescent state for the current expedited
-grace period.
-The one saving grace is that the hammer has grown a bit smaller
-over time:  The old call to <tt>try_stop_cpus()</tt> has been
-replaced with a set of calls to <tt>smp_call_function_single()</tt>,
-each of which results in an IPI to the target CPU.
-The corresponding handler function checks the CPU's state, motivating
-a faster quiescent state where possible, and triggering a report
-of that quiescent state.
-As always for RCU, once everything has spent some time in a quiescent
-state, the expedited grace period has completed.
-
-<p>
-The details of the <tt>smp_call_function_single()</tt> handler's
-operation depend on the RCU flavor, as described in the following
-sections.
-
-<h2><a name="RCU-preempt Expedited Grace Periods">
-RCU-preempt Expedited Grace Periods</a></h2>
-
-<p>
-<tt>CONFIG_PREEMPT=y</tt> kernels implement RCU-preempt.
-The overall flow of the handling of a given CPU by an RCU-preempt
-expedited grace period is shown in the following diagram:
-
-<p><img src="ExpRCUFlow.svg" alt="ExpRCUFlow.svg" width="55%">
-
-<p>
-The solid arrows denote direct action, for example, a function call.
-The dotted arrows denote indirect action, for example, an IPI
-or a state that is reached after some time.
-
-<p>
-If a given CPU is offline or idle, <tt>synchronize_rcu_expedited()</tt>
-will ignore it because idle and offline CPUs are already residing
-in quiescent states.
-Otherwise, the expedited grace period will use
-<tt>smp_call_function_single()</tt> to send the CPU an IPI, which
-is handled by <tt>rcu_exp_handler()</tt>.
-
-<p>
-However, because this is preemptible RCU, <tt>rcu_exp_handler()</tt>
-can check to see if the CPU is currently running in an RCU read-side
-critical section.
-If not, the handler can immediately report a quiescent state.
-Otherwise, it sets flags so that the outermost <tt>rcu_read_unlock()</tt>
-invocation will provide the needed quiescent-state report.
-This flag-setting avoids the previous forced preemption of all
-CPUs that might have RCU read-side critical sections.
-In addition, this flag-setting is done so as to avoid increasing
-the overhead of the common-case fastpath through the scheduler.
-
-<p>
-Again because this is preemptible RCU, an RCU read-side critical section
-can be preempted.
-When that happens, RCU will enqueue the task, which will the continue to
-block the current expedited grace period until it resumes and finds its
-outermost <tt>rcu_read_unlock()</tt>.
-The CPU will report a quiescent state just after enqueuing the task because
-the CPU is no longer blocking the grace period.
-It is instead the preempted task doing the blocking.
-The list of blocked tasks is managed by <tt>rcu_preempt_ctxt_queue()</tt>,
-which is called from <tt>rcu_preempt_note_context_switch()</tt>, which
-in turn is called from <tt>rcu_note_context_switch()</tt>, which in
-turn is called from the scheduler.
-
-<table>
-<tr><th>&nbsp;</th></tr>
-<tr><th align="left">Quick Quiz:</th></tr>
-<tr><td>
-	Why not just have the expedited grace period check the
-	state of all the CPUs?
-	After all, that would avoid all those real-time-unfriendly IPIs.
-</td></tr>
-<tr><th align="left">Answer:</th></tr>
-<tr><td bgcolor="#ffffff"><font color="ffffff">
-	Because we want the RCU read-side critical sections to run fast,
-	which means no memory barriers.
-	Therefore, it is not possible to safely check the state from some
-	other CPU.
-	And even if it was possible to safely check the state, it would
-	still be necessary to IPI the CPU to safely interact with the
-	upcoming <tt>rcu_read_unlock()</tt> invocation, which means that
-	the remote state testing would not help the worst-case
-	latency that real-time applications care about.
-
-	<p><font color="ffffff">One way to prevent your real-time
-	application from getting hit with these IPIs is to
-	build your kernel with <tt>CONFIG_NO_HZ_FULL=y</tt>.
-	RCU would then perceive the CPU running your application
-	as being idle, and it would be able to safely detect that
-	state without needing to IPI the CPU.
-</font></td></tr>
-<tr><td>&nbsp;</td></tr>
-</table>
-
-<p>
-Please note that this is just the overall flow:
-Additional complications can arise due to races with CPUs going idle
-or offline, among other things.
-
-<h2><a name="RCU-sched Expedited Grace Periods">
-RCU-sched Expedited Grace Periods</a></h2>
-
-<p>
-<tt>CONFIG_PREEMPT=n</tt> kernels implement RCU-sched.
-The overall flow of the handling of a given CPU by an RCU-sched
-expedited grace period is shown in the following diagram:
-
-<p><img src="ExpSchedFlow.svg" alt="ExpSchedFlow.svg" width="55%">
-
-<p>
-As with RCU-preempt, RCU-sched's
-<tt>synchronize_rcu_expedited()</tt> ignores offline and
-idle CPUs, again because they are in remotely detectable
-quiescent states.
-However, because the
-<tt>rcu_read_lock_sched()</tt> and <tt>rcu_read_unlock_sched()</tt>
-leave no trace of their invocation, in general it is not possible to tell
-whether or not the current CPU is in an RCU read-side critical section.
-The best that RCU-sched's <tt>rcu_exp_handler()</tt> can do is to check
-for idle, on the off-chance that the CPU went idle while the IPI
-was in flight.
-If the CPU is idle, then <tt>rcu_exp_handler()</tt> reports
-the quiescent state.
-
-<p> Otherwise, the handler forces a future context switch by setting the
-NEED_RESCHED flag of the current task's thread flag and the CPU preempt
-counter.
-At the time of the context switch, the CPU reports the quiescent state.
-Should the CPU go offline first, it will report the quiescent state
-at that time.
-
-<h2><a name="Expedited Grace Period and CPU Hotplug">
-Expedited Grace Period and CPU Hotplug</a></h2>
-
-<p>
-The expedited nature of expedited grace periods require a much tighter
-interaction with CPU hotplug operations than is required for normal
-grace periods.
-In addition, attempting to IPI offline CPUs will result in splats, but
-failing to IPI online CPUs can result in too-short grace periods.
-Neither option is acceptable in production kernels.
-
-<p>
-The interaction between expedited grace periods and CPU hotplug operations
-is carried out at several levels:
-
-<ol>
-<li>	The number of CPUs that have ever been online is tracked
-	by the <tt>rcu_state</tt> structure's <tt>-&gt;ncpus</tt>
-	field.
-	The <tt>rcu_state</tt> structure's <tt>-&gt;ncpus_snap</tt>
-	field tracks the number of CPUs that have ever been online
-	at the beginning of an RCU expedited grace period.
-	Note that this number never decreases, at least in the absence
-	of a time machine.
-<li>	The identities of the CPUs that have ever been online is
-	tracked by the <tt>rcu_node</tt> structure's
-	<tt>-&gt;expmaskinitnext</tt> field.
-	The <tt>rcu_node</tt> structure's <tt>-&gt;expmaskinit</tt>
-	field tracks the identities of the CPUs that were online
-	at least once at the beginning of the most recent RCU
-	expedited grace period.
-	The <tt>rcu_state</tt> structure's <tt>-&gt;ncpus</tt> and
-	<tt>-&gt;ncpus_snap</tt> fields are used to detect when
-	new CPUs have come online for the first time, that is,
-	when the <tt>rcu_node</tt> structure's <tt>-&gt;expmaskinitnext</tt>
-	field has changed since the beginning of the last RCU
-	expedited grace period, which triggers an update of each
-	<tt>rcu_node</tt> structure's <tt>-&gt;expmaskinit</tt>
-	field from its <tt>-&gt;expmaskinitnext</tt> field.
-<li>	Each <tt>rcu_node</tt> structure's <tt>-&gt;expmaskinit</tt>
-	field is used to initialize that structure's
-	<tt>-&gt;expmask</tt> at the beginning of each RCU
-	expedited grace period.
-	This means that only those CPUs that have been online at least
-	once will be considered for a given grace period.
-<li>	Any CPU that goes offline will clear its bit in its leaf
-	<tt>rcu_node</tt> structure's <tt>-&gt;qsmaskinitnext</tt>
-	field, so any CPU with that bit clear can safely be ignored.
-	However, it is possible for a CPU coming online or going offline
-	to have this bit set for some time while <tt>cpu_online</tt>
-	returns <tt>false</tt>.
-<li>	For each non-idle CPU that RCU believes is currently online, the grace
-	period invokes <tt>smp_call_function_single()</tt>.
-	If this succeeds, the CPU was fully online.
-	Failure indicates that the CPU is in the process of coming online
-	or going offline, in which case it is necessary to wait for a
-	short time period and try again.
-	The purpose of this wait (or series of waits, as the case may be)
-	is to permit a concurrent CPU-hotplug operation to complete.
-<li>	In the case of RCU-sched, one of the last acts of an outgoing CPU
-	is to invoke <tt>rcu_report_dead()</tt>, which
-	reports a quiescent state for that CPU.
-	However, this is likely paranoia-induced redundancy. <!-- @@@ -->
-</ol>
-
-<table>
-<tr><th>&nbsp;</th></tr>
-<tr><th align="left">Quick Quiz:</th></tr>
-<tr><td>
-	Why all the dancing around with multiple counters and masks
-	tracking CPUs that were once online?
-	Why not just have a single set of masks tracking the currently
-	online CPUs and be done with it?
-</td></tr>
-<tr><th align="left">Answer:</th></tr>
-<tr><td bgcolor="#ffffff"><font color="ffffff">
-	Maintaining single set of masks tracking the online CPUs <i>sounds</i>
-	easier, at least until you try working out all the race conditions
-	between grace-period initialization and CPU-hotplug operations.
-	For example, suppose initialization is progressing down the
-	tree while a CPU-offline operation is progressing up the tree.
-	This situation can result in bits set at the top of the tree
-	that have no counterparts at the bottom of the tree.
-	Those bits will never be cleared, which will result in
-	grace-period hangs.
-	In short, that way lies madness, to say nothing of a great many
-	bugs, hangs, and deadlocks.
-
-	<p><font color="ffffff">
-	In contrast, the current multi-mask multi-counter scheme ensures
-	that grace-period initialization will always see consistent masks
-	up and down the tree, which brings significant simplifications
-	over the single-mask method.
-
-	<p><font color="ffffff">
-	This is an instance of
-	<a href="http://www.cs.columbia.edu/~library/TR-repository/reports/reports-1992/cucs-039-92.ps.gz"><font color="ffffff">
-	deferring work in order to avoid synchronization</a>.
-	Lazily recording CPU-hotplug events at the beginning of the next
-	grace period greatly simplifies maintenance of the CPU-tracking
-	bitmasks in the <tt>rcu_node</tt> tree.
-</font></td></tr>
-<tr><td>&nbsp;</td></tr>
-</table>
-
-<h2><a name="Expedited Grace Period Refinements">
-Expedited Grace Period Refinements</a></h2>
-
-<ol>
-<li>	<a href="#Idle-CPU Checks">Idle-CPU checks</a>.
-<li>	<a href="#Batching via Sequence Counter">
-	Batching via sequence counter</a>.
-<li>	<a href="#Funnel Locking and Wait/Wakeup">
-	Funnel locking and wait/wakeup</a>.
-<li>	<a href="#Use of Workqueues">Use of Workqueues</a>.
-<li>	<a href="#Stall Warnings">Stall warnings</a>.
-<li>	<a href="#Mid-Boot Operation">Mid-boot operation</a>.
-</ol>
-
-<h3><a name="Idle-CPU Checks">Idle-CPU Checks</a></h3>
-
-<p>
-Each expedited grace period checks for idle CPUs when initially forming
-the mask of CPUs to be IPIed and again just before IPIing a CPU
-(both checks are carried out by <tt>sync_rcu_exp_select_cpus()</tt>).
-If the CPU is idle at any time between those two times, the CPU will
-not be IPIed.
-Instead, the task pushing the grace period forward will include the
-idle CPUs in the mask passed to <tt>rcu_report_exp_cpu_mult()</tt>.
-
-<p>
-For RCU-sched, there is an additional check:
-If the IPI has interrupted the idle loop, then
-<tt>rcu_exp_handler()</tt> invokes <tt>rcu_report_exp_rdp()</tt>
-to report the corresponding quiescent state.
-
-<p>
-For RCU-preempt, there is no specific check for idle in the
-IPI handler (<tt>rcu_exp_handler()</tt>), but because
-RCU read-side critical sections are not permitted within the
-idle loop, if <tt>rcu_exp_handler()</tt> sees that the CPU is within
-RCU read-side critical section, the CPU cannot possibly be idle.
-Otherwise, <tt>rcu_exp_handler()</tt> invokes
-<tt>rcu_report_exp_rdp()</tt> to report the corresponding quiescent
-state, regardless of whether or not that quiescent state was due to
-the CPU being idle.
-
-<p>
-In summary, RCU expedited grace periods check for idle when building
-the bitmask of CPUs that must be IPIed, just before sending each IPI,
-and (either explicitly or implicitly) within the IPI handler.
-
-<h3><a name="Batching via Sequence Counter">
-Batching via Sequence Counter</a></h3>
-
-<p>
-If each grace-period request was carried out separately, expedited
-grace periods would have abysmal scalability and
-problematic high-load characteristics.
-Because each grace-period operation can serve an unlimited number of
-updates, it is important to <i>batch</i> requests, so that a single
-expedited grace-period operation will cover all requests in the
-corresponding batch.
-
-<p>
-This batching is controlled by a sequence counter named
-<tt>-&gt;expedited_sequence</tt> in the <tt>rcu_state</tt> structure.
-This counter has an odd value when there is an expedited grace period
-in progress and an even value otherwise, so that dividing the counter
-value by two gives the number of completed grace periods.
-During any given update request, the counter must transition from
-even to odd and then back to even, thus indicating that a grace
-period has elapsed.
-Therefore, if the initial value of the counter is <tt>s</tt>,
-the updater must wait until the counter reaches at least the
-value <tt>(s+3)&amp;~0x1</tt>.
-This counter is managed by the following access functions:
-
-<ol>
-<li>	<tt>rcu_exp_gp_seq_start()</tt>, which marks the start of
-	an expedited grace period.
-<li>	<tt>rcu_exp_gp_seq_end()</tt>, which marks the end of an
-	expedited grace period.
-<li>	<tt>rcu_exp_gp_seq_snap()</tt>, which obtains a snapshot of
-	the counter.
-<li>	<tt>rcu_exp_gp_seq_done()</tt>, which returns <tt>true</tt>
-	if a full expedited grace period has elapsed since the
-	corresponding call to <tt>rcu_exp_gp_seq_snap()</tt>.
-</ol>
-
-<p>
-Again, only one request in a given batch need actually carry out
-a grace-period operation, which means there must be an efficient
-way to identify which of many concurrent reqeusts will initiate
-the grace period, and that there be an efficient way for the
-remaining requests to wait for that grace period to complete.
-However, that is the topic of the next section.
-
-<h3><a name="Funnel Locking and Wait/Wakeup">
-Funnel Locking and Wait/Wakeup</a></h3>
-
-<p>
-The natural way to sort out which of a batch of updaters will initiate
-the expedited grace period is to use the <tt>rcu_node</tt> combining
-tree, as implemented by the <tt>exp_funnel_lock()</tt> function.
-The first updater corresponding to a given grace period arriving
-at a given <tt>rcu_node</tt> structure records its desired grace-period
-sequence number in the <tt>-&gt;exp_seq_rq</tt> field and moves up
-to the next level in the tree.
-Otherwise, if the <tt>-&gt;exp_seq_rq</tt> field already contains
-the sequence number for the desired grace period or some later one,
-the updater blocks on one of four wait queues in the
-<tt>-&gt;exp_wq[]</tt> array, using the second-from-bottom
-and third-from bottom bits as an index.
-An <tt>-&gt;exp_lock</tt> field in the <tt>rcu_node</tt> structure
-synchronizes access to these fields.
-
-<p>
-An empty <tt>rcu_node</tt> tree is shown in the following diagram,
-with the white cells representing the <tt>-&gt;exp_seq_rq</tt> field
-and the red cells representing the elements of the
-<tt>-&gt;exp_wq[]</tt> array.
-
-<p><img src="Funnel0.svg" alt="Funnel0.svg" width="75%">
-
-<p>
-The next diagram shows the situation after the arrival of Task&nbsp;A
-and Task&nbsp;B at the leftmost and rightmost leaf <tt>rcu_node</tt>
-structures, respectively.
-The current value of the <tt>rcu_state</tt> structure's
-<tt>-&gt;expedited_sequence</tt> field is zero, so adding three and
-clearing the bottom bit results in the value two, which both tasks
-record in the <tt>-&gt;exp_seq_rq</tt> field of their respective
-<tt>rcu_node</tt> structures:
-
-<p><img src="Funnel1.svg" alt="Funnel1.svg" width="75%">
-
-<p>
-Each of Tasks&nbsp;A and&nbsp;B will move up to the root
-<tt>rcu_node</tt> structure.
-Suppose that Task&nbsp;A wins, recording its desired grace-period sequence
-number and resulting in the state shown below:
-
-<p><img src="Funnel2.svg" alt="Funnel2.svg" width="75%">
-
-<p>
-Task&nbsp;A now advances to initiate a new grace period, while Task&nbsp;B
-moves up to the root <tt>rcu_node</tt> structure, and, seeing that
-its desired sequence number is already recorded, blocks on
-<tt>-&gt;exp_wq[1]</tt>.
-
-<table>
-<tr><th>&nbsp;</th></tr>
-<tr><th align="left">Quick Quiz:</th></tr>
-<tr><td>
-	Why <tt>-&gt;exp_wq[1]</tt>?
-	Given that the value of these tasks' desired sequence number is
-	two, so shouldn't they instead block on <tt>-&gt;exp_wq[2]</tt>?
-</td></tr>
-<tr><th align="left">Answer:</th></tr>
-<tr><td bgcolor="#ffffff"><font color="ffffff">
-	No.
-
-	<p><font color="ffffff">
-	Recall that the bottom bit of the desired sequence number indicates
-	whether or not a grace period is currently in progress.
-	It is therefore necessary to shift the sequence number right one
-	bit position to obtain the number of the grace period.
-	This results in <tt>-&gt;exp_wq[1]</tt>.
-</font></td></tr>
-<tr><td>&nbsp;</td></tr>
-</table>
-
-<p>
-If Tasks&nbsp;C and&nbsp;D also arrive at this point, they will compute the
-same desired grace-period sequence number, and see that both leaf
-<tt>rcu_node</tt> structures already have that value recorded.
-They will therefore block on their respective <tt>rcu_node</tt>
-structures' <tt>-&gt;exp_wq[1]</tt> fields, as shown below:
-
-<p><img src="Funnel3.svg" alt="Funnel3.svg" width="75%">
-
-<p>
-Task&nbsp;A now acquires the <tt>rcu_state</tt> structure's
-<tt>-&gt;exp_mutex</tt> and initiates the grace period, which
-increments <tt>-&gt;expedited_sequence</tt>.
-Therefore, if Tasks&nbsp;E and&nbsp;F arrive, they will compute
-a desired sequence number of 4 and will record this value as
-shown below:
-
-<p><img src="Funnel4.svg" alt="Funnel4.svg" width="75%">
-
-<p>
-Tasks&nbsp;E and&nbsp;F will propagate up the <tt>rcu_node</tt>
-combining tree, with Task&nbsp;F blocking on the root <tt>rcu_node</tt>
-structure and Task&nbsp;E wait for Task&nbsp;A to finish so that
-it can start the next grace period.
-The resulting state is as shown below:
-
-<p><img src="Funnel5.svg" alt="Funnel5.svg" width="75%">
-
-<p>
-Once the grace period completes, Task&nbsp;A
-starts waking up the tasks waiting for this grace period to complete,
-increments the <tt>-&gt;expedited_sequence</tt>,
-acquires the <tt>-&gt;exp_wake_mutex</tt> and then releases the
-<tt>-&gt;exp_mutex</tt>.
-This results in the following state:
-
-<p><img src="Funnel6.svg" alt="Funnel6.svg" width="75%">
-
-<p>
-Task&nbsp;E can then acquire <tt>-&gt;exp_mutex</tt> and increment
-<tt>-&gt;expedited_sequence</tt> to the value three.
-If new tasks&nbsp;G and&nbsp;H arrive and moves up the combining tree at the
-same time, the state will be as follows:
-
-<p><img src="Funnel7.svg" alt="Funnel7.svg" width="75%">
-
-<p>
-Note that three of the root <tt>rcu_node</tt> structure's
-waitqueues are now occupied.
-However, at some point, Task&nbsp;A will wake up the
-tasks blocked on the <tt>-&gt;exp_wq</tt> waitqueues, resulting
-in the following state:
-
-<p><img src="Funnel8.svg" alt="Funnel8.svg" width="75%">
-
-<p>
-Execution will continue with Tasks&nbsp;E and&nbsp;H completing
-their grace periods and carrying out their wakeups.
-
-<table>
-<tr><th>&nbsp;</th></tr>
-<tr><th align="left">Quick Quiz:</th></tr>
-<tr><td>
-	What happens if Task&nbsp;A takes so long to do its wakeups
-	that Task&nbsp;E's grace period completes?
-</td></tr>
-<tr><th align="left">Answer:</th></tr>
-<tr><td bgcolor="#ffffff"><font color="ffffff">
-	Then Task&nbsp;E will block on the <tt>-&gt;exp_wake_mutex</tt>,
-	which will also prevent it from releasing <tt>-&gt;exp_mutex</tt>,
-	which in turn will prevent the next grace period from starting.
-	This last is important in preventing overflow of the
-	<tt>-&gt;exp_wq[]</tt> array.
-</font></td></tr>
-<tr><td>&nbsp;</td></tr>
-</table>
-
-<h3><a name="Use of Workqueues">Use of Workqueues</a></h3>
-
-<p>
-In earlier implementations, the task requesting the expedited
-grace period also drove it to completion.
-This straightforward approach had the disadvantage of needing to
-account for POSIX signals sent to user tasks,
-so more recent implemementations use the Linux kernel's
-<a href="https://www.kernel.org/doc/Documentation/core-api/workqueue.rst">workqueues</a>.
-
-<p>
-The requesting task still does counter snapshotting and funnel-lock
-processing, but the task reaching the top of the funnel lock
-does a <tt>schedule_work()</tt> (from <tt>_synchronize_rcu_expedited()</tt>
-so that a workqueue kthread does the actual grace-period processing.
-Because workqueue kthreads do not accept POSIX signals, grace-period-wait
-processing need not allow for POSIX signals.
-
-In addition, this approach allows wakeups for the previous expedited
-grace period to be overlapped with processing for the next expedited
-grace period.
-Because there are only four sets of waitqueues, it is necessary to
-ensure that the previous grace period's wakeups complete before the
-next grace period's wakeups start.
-This is handled by having the <tt>-&gt;exp_mutex</tt>
-guard expedited grace-period processing and the
-<tt>-&gt;exp_wake_mutex</tt> guard wakeups.
-The key point is that the <tt>-&gt;exp_mutex</tt> is not released
-until the first wakeup is complete, which means that the
-<tt>-&gt;exp_wake_mutex</tt> has already been acquired at that point.
-This approach ensures that the previous grace period's wakeups can
-be carried out while the current grace period is in process, but
-that these wakeups will complete before the next grace period starts.
-This means that only three waitqueues are required, guaranteeing that
-the four that are provided are sufficient.
-
-<h3><a name="Stall Warnings">Stall Warnings</a></h3>
-
-<p>
-Expediting grace periods does nothing to speed things up when RCU
-readers take too long, and therefore expedited grace periods check
-for stalls just as normal grace periods do.
-
-<table>
-<tr><th>&nbsp;</th></tr>
-<tr><th align="left">Quick Quiz:</th></tr>
-<tr><td>
-	But why not just let the normal grace-period machinery
-	detect the stalls, given that a given reader must block
-	both normal and expedited grace periods?
-</td></tr>
-<tr><th align="left">Answer:</th></tr>
-<tr><td bgcolor="#ffffff"><font color="ffffff">
-	Because it is quite possible that at a given time there
-	is no normal grace period in progress, in which case the
-	normal grace period cannot emit a stall warning.
-</font></td></tr>
-<tr><td>&nbsp;</td></tr>
-</table>
-
-The <tt>synchronize_sched_expedited_wait()</tt> function loops waiting
-for the expedited grace period to end, but with a timeout set to the
-current RCU CPU stall-warning time.
-If this time is exceeded, any CPUs or <tt>rcu_node</tt> structures
-blocking the current grace period are printed.
-Each stall warning results in another pass through the loop, but the
-second and subsequent passes use longer stall times.
-
-<h3><a name="Mid-Boot Operation">Mid-boot operation</a></h3>
-
-<p>
-The use of workqueues has the advantage that the expedited
-grace-period code need not worry about POSIX signals.
-Unfortunately, it has the
-corresponding disadvantage that workqueues cannot be used until
-they are initialized, which does not happen until some time after
-the scheduler spawns the first task.
-Given that there are parts of the kernel that really do want to
-execute grace periods during this mid-boot &ldquo;dead zone&rdquo;,
-expedited grace periods must do something else during thie time.
-
-<p>
-What they do is to fall back to the old practice of requiring that the
-requesting task drive the expedited grace period, as was the case
-before the use of workqueues.
-However, the requesting task is only required to drive the grace period
-during the mid-boot dead zone.
-Before mid-boot, a synchronous grace period is a no-op.
-Some time after mid-boot, workqueues are used.
-
-<p>
-Non-expedited non-SRCU synchronous grace periods must also operate
-normally during mid-boot.
-This is handled by causing non-expedited grace periods to take the
-expedited code path during mid-boot.
-
-<p>
-The current code assumes that there are no POSIX signals during
-the mid-boot dead zone.
-However, if an overwhelming need for POSIX signals somehow arises,
-appropriate adjustments can be made to the expedited stall-warning code.
-One such adjustment would reinstate the pre-workqueue stall-warning
-checks, but only during the mid-boot dead zone.
-
-<p>
-With this refinement, synchronous grace periods can now be used from
-task context pretty much any time during the life of the kernel.
-That is, aside from some points in the suspend, hibernate, or shutdown
-code path.
-
-<h3><a name="Summary">
-Summary</a></h3>
-
-<p>
-Expedited grace periods use a sequence-number approach to promote
-batching, so that a single grace-period operation can serve numerous
-requests.
-A funnel lock is used to efficiently identify the one task out of
-a concurrent group that will request the grace period.
-All members of the group will block on waitqueues provided in
-the <tt>rcu_node</tt> structure.
-The actual grace-period processing is carried out by a workqueue.
-
-<p>
-CPU-hotplug operations are noted lazily in order to prevent the need
-for tight synchronization between expedited grace periods and
-CPU-hotplug operations.
-The dyntick-idle counters are used to avoid sending IPIs to idle CPUs,
-at least in the common case.
-RCU-preempt and RCU-sched use different IPI handlers and different
-code to respond to the state changes carried out by those handlers,
-but otherwise use common code.
-
-<p>
-Quiescent states are tracked using the <tt>rcu_node</tt> tree,
-and once all necessary quiescent states have been reported,
-all tasks waiting on this expedited grace period are awakened.
-A pair of mutexes are used to allow one grace period's wakeups
-to proceed concurrently with the next grace period's processing.
-
-<p>
-This combination of mechanisms allows expedited grace periods to
-run reasonably efficiently.
-However, for non-time-critical tasks, normal grace periods should be
-used instead because their longer duration permits much higher
-degrees of batching, and thus much lower per-request overheads.
-
-</body></html>
diff --git a/Documentation/RCU/Design/Expedited-Grace-Periods/Expedited-Grace-Periods.rst b/Documentation/RCU/Design/Expedited-Grace-Periods/Expedited-Grace-Periods.rst
new file mode 100644
index 000000000000..72f0f6fbd53c
--- /dev/null
+++ b/Documentation/RCU/Design/Expedited-Grace-Periods/Expedited-Grace-Periods.rst
@@ -0,0 +1,521 @@
+=================================================
+A Tour Through TREE_RCU's Expedited Grace Periods
+=================================================
+
+Introduction
+============
+
+This document describes RCU's expedited grace periods.
+Unlike RCU's normal grace periods, which accept long latencies to attain
+high efficiency and minimal disturbance, expedited grace periods accept
+lower efficiency and significant disturbance to attain shorter latencies.
+
+There are two flavors of RCU (RCU-preempt and RCU-sched), with an earlier
+third RCU-bh flavor having been implemented in terms of the other two.
+Each of the two implementations is covered in its own section.
+
+Expedited Grace Period Design
+=============================
+
+The expedited RCU grace periods cannot be accused of being subtle,
+given that they for all intents and purposes hammer every CPU that
+has not yet provided a quiescent state for the current expedited
+grace period.
+The one saving grace is that the hammer has grown a bit smaller
+over time:  The old call to ``try_stop_cpus()`` has been
+replaced with a set of calls to ``smp_call_function_single()``,
+each of which results in an IPI to the target CPU.
+The corresponding handler function checks the CPU's state, motivating
+a faster quiescent state where possible, and triggering a report
+of that quiescent state.
+As always for RCU, once everything has spent some time in a quiescent
+state, the expedited grace period has completed.
+
+The details of the ``smp_call_function_single()`` handler's
+operation depend on the RCU flavor, as described in the following
+sections.
+
+RCU-preempt Expedited Grace Periods
+===================================
+
+``CONFIG_PREEMPT=y`` kernels implement RCU-preempt.
+The overall flow of the handling of a given CPU by an RCU-preempt
+expedited grace period is shown in the following diagram:
+
+.. kernel-figure:: ExpRCUFlow.svg
+
+The solid arrows denote direct action, for example, a function call.
+The dotted arrows denote indirect action, for example, an IPI
+or a state that is reached after some time.
+
+If a given CPU is offline or idle, ``synchronize_rcu_expedited()``
+will ignore it because idle and offline CPUs are already residing
+in quiescent states.
+Otherwise, the expedited grace period will use
+``smp_call_function_single()`` to send the CPU an IPI, which
+is handled by ``rcu_exp_handler()``.
+
+However, because this is preemptible RCU, ``rcu_exp_handler()``
+can check to see if the CPU is currently running in an RCU read-side
+critical section.
+If not, the handler can immediately report a quiescent state.
+Otherwise, it sets flags so that the outermost ``rcu_read_unlock()``
+invocation will provide the needed quiescent-state report.
+This flag-setting avoids the previous forced preemption of all
+CPUs that might have RCU read-side critical sections.
+In addition, this flag-setting is done so as to avoid increasing
+the overhead of the common-case fastpath through the scheduler.
+
+Again because this is preemptible RCU, an RCU read-side critical section
+can be preempted.
+When that happens, RCU will enqueue the task, which will the continue to
+block the current expedited grace period until it resumes and finds its
+outermost ``rcu_read_unlock()``.
+The CPU will report a quiescent state just after enqueuing the task because
+the CPU is no longer blocking the grace period.
+It is instead the preempted task doing the blocking.
+The list of blocked tasks is managed by ``rcu_preempt_ctxt_queue()``,
+which is called from ``rcu_preempt_note_context_switch()``, which
+in turn is called from ``rcu_note_context_switch()``, which in
+turn is called from the scheduler.
+
+
++-----------------------------------------------------------------------+
+| **Quick Quiz**:                                                       |
++-----------------------------------------------------------------------+
+| Why not just have the expedited grace period check the state of all   |
+| the CPUs? After all, that would avoid all those real-time-unfriendly  |
+| IPIs.                                                                 |
++-----------------------------------------------------------------------+
+| **Answer**:                                                           |
++-----------------------------------------------------------------------+
+| Because we want the RCU read-side critical sections to run fast,      |
+| which means no memory barriers. Therefore, it is not possible to      |
+| safely check the state from some other CPU. And even if it was        |
+| possible to safely check the state, it would still be necessary to    |
+| IPI the CPU to safely interact with the upcoming                      |
+| ``rcu_read_unlock()`` invocation, which means that the remote state   |
+| testing would not help the worst-case latency that real-time          |
+| applications care about.                                              |
+|                                                                       |
+| One way to prevent your real-time application from getting hit with   |
+| these IPIs is to build your kernel with ``CONFIG_NO_HZ_FULL=y``. RCU  |
+| would then perceive the CPU running your application as being idle,   |
+| and it would be able to safely detect that state without needing to   |
+| IPI the CPU.                                                          |
++-----------------------------------------------------------------------+
+
+Please note that this is just the overall flow: Additional complications
+can arise due to races with CPUs going idle or offline, among other
+things.
+
+RCU-sched Expedited Grace Periods
+---------------------------------
+
+``CONFIG_PREEMPT=n`` kernels implement RCU-sched. The overall flow of
+the handling of a given CPU by an RCU-sched expedited grace period is
+shown in the following diagram:
+
+.. kernel-figure:: ExpSchedFlow.svg
+
+As with RCU-preempt, RCU-sched's ``synchronize_rcu_expedited()`` ignores
+offline and idle CPUs, again because they are in remotely detectable
+quiescent states. However, because the ``rcu_read_lock_sched()`` and
+``rcu_read_unlock_sched()`` leave no trace of their invocation, in
+general it is not possible to tell whether or not the current CPU is in
+an RCU read-side critical section. The best that RCU-sched's
+``rcu_exp_handler()`` can do is to check for idle, on the off-chance
+that the CPU went idle while the IPI was in flight. If the CPU is idle,
+then ``rcu_exp_handler()`` reports the quiescent state.
+
+Otherwise, the handler forces a future context switch by setting the
+NEED_RESCHED flag of the current task's thread flag and the CPU preempt
+counter. At the time of the context switch, the CPU reports the
+quiescent state. Should the CPU go offline first, it will report the
+quiescent state at that time.
+
+Expedited Grace Period and CPU Hotplug
+--------------------------------------
+
+The expedited nature of expedited grace periods require a much tighter
+interaction with CPU hotplug operations than is required for normal
+grace periods. In addition, attempting to IPI offline CPUs will result
+in splats, but failing to IPI online CPUs can result in too-short grace
+periods. Neither option is acceptable in production kernels.
+
+The interaction between expedited grace periods and CPU hotplug
+operations is carried out at several levels:
+
+#. The number of CPUs that have ever been online is tracked by the
+   ``rcu_state`` structure's ``->ncpus`` field. The ``rcu_state``
+   structure's ``->ncpus_snap`` field tracks the number of CPUs that
+   have ever been online at the beginning of an RCU expedited grace
+   period. Note that this number never decreases, at least in the
+   absence of a time machine.
+#. The identities of the CPUs that have ever been online is tracked by
+   the ``rcu_node`` structure's ``->expmaskinitnext`` field. The
+   ``rcu_node`` structure's ``->expmaskinit`` field tracks the
+   identities of the CPUs that were online at least once at the
+   beginning of the most recent RCU expedited grace period. The
+   ``rcu_state`` structure's ``->ncpus`` and ``->ncpus_snap`` fields are
+   used to detect when new CPUs have come online for the first time,
+   that is, when the ``rcu_node`` structure's ``->expmaskinitnext``
+   field has changed since the beginning of the last RCU expedited grace
+   period, which triggers an update of each ``rcu_node`` structure's
+   ``->expmaskinit`` field from its ``->expmaskinitnext`` field.
+#. Each ``rcu_node`` structure's ``->expmaskinit`` field is used to
+   initialize that structure's ``->expmask`` at the beginning of each
+   RCU expedited grace period. This means that only those CPUs that have
+   been online at least once will be considered for a given grace
+   period.
+#. Any CPU that goes offline will clear its bit in its leaf ``rcu_node``
+   structure's ``->qsmaskinitnext`` field, so any CPU with that bit
+   clear can safely be ignored. However, it is possible for a CPU coming
+   online or going offline to have this bit set for some time while
+   ``cpu_online`` returns ``false``.
+#. For each non-idle CPU that RCU believes is currently online, the
+   grace period invokes ``smp_call_function_single()``. If this
+   succeeds, the CPU was fully online. Failure indicates that the CPU is
+   in the process of coming online or going offline, in which case it is
+   necessary to wait for a short time period and try again. The purpose
+   of this wait (or series of waits, as the case may be) is to permit a
+   concurrent CPU-hotplug operation to complete.
+#. In the case of RCU-sched, one of the last acts of an outgoing CPU is
+   to invoke ``rcu_report_dead()``, which reports a quiescent state for
+   that CPU. However, this is likely paranoia-induced redundancy.
+
++-----------------------------------------------------------------------+
+| **Quick Quiz**:                                                       |
++-----------------------------------------------------------------------+
+| Why all the dancing around with multiple counters and masks tracking  |
+| CPUs that were once online? Why not just have a single set of masks   |
+| tracking the currently online CPUs and be done with it?               |
++-----------------------------------------------------------------------+
+| **Answer**:                                                           |
++-----------------------------------------------------------------------+
+| Maintaining single set of masks tracking the online CPUs *sounds*     |
+| easier, at least until you try working out all the race conditions    |
+| between grace-period initialization and CPU-hotplug operations. For   |
+| example, suppose initialization is progressing down the tree while a  |
+| CPU-offline operation is progressing up the tree. This situation can  |
+| result in bits set at the top of the tree that have no counterparts   |
+| at the bottom of the tree. Those bits will never be cleared, which    |
+| will result in grace-period hangs. In short, that way lies madness,   |
+| to say nothing of a great many bugs, hangs, and deadlocks.            |
+| In contrast, the current multi-mask multi-counter scheme ensures that |
+| grace-period initialization will always see consistent masks up and   |
+| down the tree, which brings significant simplifications over the      |
+| single-mask method.                                                   |
+|                                                                       |
+| This is an instance of `deferring work in order to avoid              |
+| synchronization <http://www.cs.columbia.edu/~library/TR-repository/re |
+| ports/reports-1992/cucs-039-92.ps.gz>`__.                             |
+| Lazily recording CPU-hotplug events at the beginning of the next      |
+| grace period greatly simplifies maintenance of the CPU-tracking       |
+| bitmasks in the ``rcu_node`` tree.                                    |
++-----------------------------------------------------------------------+
+
+Expedited Grace Period Refinements
+----------------------------------
+
+Idle-CPU Checks
+~~~~~~~~~~~~~~~
+
+Each expedited grace period checks for idle CPUs when initially forming
+the mask of CPUs to be IPIed and again just before IPIing a CPU (both
+checks are carried out by ``sync_rcu_exp_select_cpus()``). If the CPU is
+idle at any time between those two times, the CPU will not be IPIed.
+Instead, the task pushing the grace period forward will include the idle
+CPUs in the mask passed to ``rcu_report_exp_cpu_mult()``.
+
+For RCU-sched, there is an additional check: If the IPI has interrupted
+the idle loop, then ``rcu_exp_handler()`` invokes
+``rcu_report_exp_rdp()`` to report the corresponding quiescent state.
+
+For RCU-preempt, there is no specific check for idle in the IPI handler
+(``rcu_exp_handler()``), but because RCU read-side critical sections are
+not permitted within the idle loop, if ``rcu_exp_handler()`` sees that
+the CPU is within RCU read-side critical section, the CPU cannot
+possibly be idle. Otherwise, ``rcu_exp_handler()`` invokes
+``rcu_report_exp_rdp()`` to report the corresponding quiescent state,
+regardless of whether or not that quiescent state was due to the CPU
+being idle.
+
+In summary, RCU expedited grace periods check for idle when building the
+bitmask of CPUs that must be IPIed, just before sending each IPI, and
+(either explicitly or implicitly) within the IPI handler.
+
+Batching via Sequence Counter
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+If each grace-period request was carried out separately, expedited grace
+periods would have abysmal scalability and problematic high-load
+characteristics. Because each grace-period operation can serve an
+unlimited number of updates, it is important to *batch* requests, so
+that a single expedited grace-period operation will cover all requests
+in the corresponding batch.
+
+This batching is controlled by a sequence counter named
+``->expedited_sequence`` in the ``rcu_state`` structure. This counter
+has an odd value when there is an expedited grace period in progress and
+an even value otherwise, so that dividing the counter value by two gives
+the number of completed grace periods. During any given update request,
+the counter must transition from even to odd and then back to even, thus
+indicating that a grace period has elapsed. Therefore, if the initial
+value of the counter is ``s``, the updater must wait until the counter
+reaches at least the value ``(s+3)&~0x1``. This counter is managed by
+the following access functions:
+
+#. ``rcu_exp_gp_seq_start()``, which marks the start of an expedited
+   grace period.
+#. ``rcu_exp_gp_seq_end()``, which marks the end of an expedited grace
+   period.
+#. ``rcu_exp_gp_seq_snap()``, which obtains a snapshot of the counter.
+#. ``rcu_exp_gp_seq_done()``, which returns ``true`` if a full expedited
+   grace period has elapsed since the corresponding call to
+   ``rcu_exp_gp_seq_snap()``.
+
+Again, only one request in a given batch need actually carry out a
+grace-period operation, which means there must be an efficient way to
+identify which of many concurrent reqeusts will initiate the grace
+period, and that there be an efficient way for the remaining requests to
+wait for that grace period to complete. However, that is the topic of
+the next section.
+
+Funnel Locking and Wait/Wakeup
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+The natural way to sort out which of a batch of updaters will initiate
+the expedited grace period is to use the ``rcu_node`` combining tree, as
+implemented by the ``exp_funnel_lock()`` function. The first updater
+corresponding to a given grace period arriving at a given ``rcu_node``
+structure records its desired grace-period sequence number in the
+``->exp_seq_rq`` field and moves up to the next level in the tree.
+Otherwise, if the ``->exp_seq_rq`` field already contains the sequence
+number for the desired grace period or some later one, the updater
+blocks on one of four wait queues in the ``->exp_wq[]`` array, using the
+second-from-bottom and third-from bottom bits as an index. An
+``->exp_lock`` field in the ``rcu_node`` structure synchronizes access
+to these fields.
+
+An empty ``rcu_node`` tree is shown in the following diagram, with the
+white cells representing the ``->exp_seq_rq`` field and the red cells
+representing the elements of the ``->exp_wq[]`` array.
+
+.. kernel-figure:: Funnel0.svg
+
+The next diagram shows the situation after the arrival of Task A and
+Task B at the leftmost and rightmost leaf ``rcu_node`` structures,
+respectively. The current value of the ``rcu_state`` structure's
+``->expedited_sequence`` field is zero, so adding three and clearing the
+bottom bit results in the value two, which both tasks record in the
+``->exp_seq_rq`` field of their respective ``rcu_node`` structures:
+
+.. kernel-figure:: Funnel1.svg
+
+Each of Tasks A and B will move up to the root ``rcu_node`` structure.
+Suppose that Task A wins, recording its desired grace-period sequence
+number and resulting in the state shown below:
+
+.. kernel-figure:: Funnel2.svg
+
+Task A now advances to initiate a new grace period, while Task B moves
+up to the root ``rcu_node`` structure, and, seeing that its desired
+sequence number is already recorded, blocks on ``->exp_wq[1]``.
+
++-----------------------------------------------------------------------+
+| **Quick Quiz**:                                                       |
++-----------------------------------------------------------------------+
+| Why ``->exp_wq[1]``? Given that the value of these tasks' desired     |
+| sequence number is two, so shouldn't they instead block on            |
+| ``->exp_wq[2]``?                                                      |
++-----------------------------------------------------------------------+
+| **Answer**:                                                           |
++-----------------------------------------------------------------------+
+| No.                                                                   |
+| Recall that the bottom bit of the desired sequence number indicates   |
+| whether or not a grace period is currently in progress. It is         |
+| therefore necessary to shift the sequence number right one bit        |
+| position to obtain the number of the grace period. This results in    |
+| ``->exp_wq[1]``.                                                      |
++-----------------------------------------------------------------------+
+
+If Tasks C and D also arrive at this point, they will compute the same
+desired grace-period sequence number, and see that both leaf
+``rcu_node`` structures already have that value recorded. They will
+therefore block on their respective ``rcu_node`` structures'
+``->exp_wq[1]`` fields, as shown below:
+
+.. kernel-figure:: Funnel3.svg
+
+Task A now acquires the ``rcu_state`` structure's ``->exp_mutex`` and
+initiates the grace period, which increments ``->expedited_sequence``.
+Therefore, if Tasks E and F arrive, they will compute a desired sequence
+number of 4 and will record this value as shown below:
+
+.. kernel-figure:: Funnel4.svg
+
+Tasks E and F will propagate up the ``rcu_node`` combining tree, with
+Task F blocking on the root ``rcu_node`` structure and Task E wait for
+Task A to finish so that it can start the next grace period. The
+resulting state is as shown below:
+
+.. kernel-figure:: Funnel5.svg
+
+Once the grace period completes, Task A starts waking up the tasks
+waiting for this grace period to complete, increments the
+``->expedited_sequence``, acquires the ``->exp_wake_mutex`` and then
+releases the ``->exp_mutex``. This results in the following state:
+
+.. kernel-figure:: Funnel6.svg
+
+Task E can then acquire ``->exp_mutex`` and increment
+``->expedited_sequence`` to the value three. If new tasks G and H arrive
+and moves up the combining tree at the same time, the state will be as
+follows:
+
+.. kernel-figure:: Funnel7.svg
+
+Note that three of the root ``rcu_node`` structure's waitqueues are now
+occupied. However, at some point, Task A will wake up the tasks blocked
+on the ``->exp_wq`` waitqueues, resulting in the following state:
+
+.. kernel-figure:: Funnel8.svg
+
+Execution will continue with Tasks E and H completing their grace
+periods and carrying out their wakeups.
+
++-----------------------------------------------------------------------+
+| **Quick Quiz**:                                                       |
++-----------------------------------------------------------------------+
+| What happens if Task A takes so long to do its wakeups that Task E's  |
+| grace period completes?                                               |
++-----------------------------------------------------------------------+
+| **Answer**:                                                           |
++-----------------------------------------------------------------------+
+| Then Task E will block on the ``->exp_wake_mutex``, which will also   |
+| prevent it from releasing ``->exp_mutex``, which in turn will prevent |
+| the next grace period from starting. This last is important in        |
+| preventing overflow of the ``->exp_wq[]`` array.                      |
++-----------------------------------------------------------------------+
+
+Use of Workqueues
+~~~~~~~~~~~~~~~~~
+
+In earlier implementations, the task requesting the expedited grace
+period also drove it to completion. This straightforward approach had
+the disadvantage of needing to account for POSIX signals sent to user
+tasks, so more recent implemementations use the Linux kernel's
+`workqueues <https://www.kernel.org/doc/Documentation/core-api/workqueue.rst>`__.
+
+The requesting task still does counter snapshotting and funnel-lock
+processing, but the task reaching the top of the funnel lock does a
+``schedule_work()`` (from ``_synchronize_rcu_expedited()`` so that a
+workqueue kthread does the actual grace-period processing. Because
+workqueue kthreads do not accept POSIX signals, grace-period-wait
+processing need not allow for POSIX signals. In addition, this approach
+allows wakeups for the previous expedited grace period to be overlapped
+with processing for the next expedited grace period. Because there are
+only four sets of waitqueues, it is necessary to ensure that the
+previous grace period's wakeups complete before the next grace period's
+wakeups start. This is handled by having the ``->exp_mutex`` guard
+expedited grace-period processing and the ``->exp_wake_mutex`` guard
+wakeups. The key point is that the ``->exp_mutex`` is not released until
+the first wakeup is complete, which means that the ``->exp_wake_mutex``
+has already been acquired at that point. This approach ensures that the
+previous grace period's wakeups can be carried out while the current
+grace period is in process, but that these wakeups will complete before
+the next grace period starts. This means that only three waitqueues are
+required, guaranteeing that the four that are provided are sufficient.
+
+Stall Warnings
+~~~~~~~~~~~~~~
+
+Expediting grace periods does nothing to speed things up when RCU
+readers take too long, and therefore expedited grace periods check for
+stalls just as normal grace periods do.
+
++-----------------------------------------------------------------------+
+| **Quick Quiz**:                                                       |
++-----------------------------------------------------------------------+
+| But why not just let the normal grace-period machinery detect the     |
+| stalls, given that a given reader must block both normal and          |
+| expedited grace periods?                                              |
++-----------------------------------------------------------------------+
+| **Answer**:                                                           |
++-----------------------------------------------------------------------+
+| Because it is quite possible that at a given time there is no normal  |
+| grace period in progress, in which case the normal grace period       |
+| cannot emit a stall warning.                                          |
++-----------------------------------------------------------------------+
+
+The ``synchronize_sched_expedited_wait()`` function loops waiting for
+the expedited grace period to end, but with a timeout set to the current
+RCU CPU stall-warning time. If this time is exceeded, any CPUs or
+``rcu_node`` structures blocking the current grace period are printed.
+Each stall warning results in another pass through the loop, but the
+second and subsequent passes use longer stall times.
+
+Mid-boot operation
+~~~~~~~~~~~~~~~~~~
+
+The use of workqueues has the advantage that the expedited grace-period
+code need not worry about POSIX signals. Unfortunately, it has the
+corresponding disadvantage that workqueues cannot be used until they are
+initialized, which does not happen until some time after the scheduler
+spawns the first task. Given that there are parts of the kernel that
+really do want to execute grace periods during this mid-boot “dead
+zone”, expedited grace periods must do something else during thie time.
+
+What they do is to fall back to the old practice of requiring that the
+requesting task drive the expedited grace period, as was the case before
+the use of workqueues. However, the requesting task is only required to
+drive the grace period during the mid-boot dead zone. Before mid-boot, a
+synchronous grace period is a no-op. Some time after mid-boot,
+workqueues are used.
+
+Non-expedited non-SRCU synchronous grace periods must also operate
+normally during mid-boot. This is handled by causing non-expedited grace
+periods to take the expedited code path during mid-boot.
+
+The current code assumes that there are no POSIX signals during the
+mid-boot dead zone. However, if an overwhelming need for POSIX signals
+somehow arises, appropriate adjustments can be made to the expedited
+stall-warning code. One such adjustment would reinstate the
+pre-workqueue stall-warning checks, but only during the mid-boot dead
+zone.
+
+With this refinement, synchronous grace periods can now be used from
+task context pretty much any time during the life of the kernel. That
+is, aside from some points in the suspend, hibernate, or shutdown code
+path.
+
+Summary
+~~~~~~~
+
+Expedited grace periods use a sequence-number approach to promote
+batching, so that a single grace-period operation can serve numerous
+requests. A funnel lock is used to efficiently identify the one task out
+of a concurrent group that will request the grace period. All members of
+the group will block on waitqueues provided in the ``rcu_node``
+structure. The actual grace-period processing is carried out by a
+workqueue.
+
+CPU-hotplug operations are noted lazily in order to prevent the need for
+tight synchronization between expedited grace periods and CPU-hotplug
+operations. The dyntick-idle counters are used to avoid sending IPIs to
+idle CPUs, at least in the common case. RCU-preempt and RCU-sched use
+different IPI handlers and different code to respond to the state
+changes carried out by those handlers, but otherwise use common code.
+
+Quiescent states are tracked using the ``rcu_node`` tree, and once all
+necessary quiescent states have been reported, all tasks waiting on this
+expedited grace period are awakened. A pair of mutexes are used to allow
+one grace period's wakeups to proceed concurrently with the next grace
+period's processing.
+
+This combination of mechanisms allows expedited grace periods to run
+reasonably efficiently. However, for non-time-critical tasks, normal
+grace periods should be used instead because their longer duration
+permits much higher degrees of batching, and thus much lower per-request
+overheads.
diff --git a/Documentation/RCU/Design/Memory-Ordering/Tree-RCU-Diagram.html b/Documentation/RCU/Design/Memory-Ordering/Tree-RCU-Diagram.html
deleted file mode 100644
index e5b42a798ff3..000000000000
--- a/Documentation/RCU/Design/Memory-Ordering/Tree-RCU-Diagram.html
+++ /dev/null
@@ -1,9 +0,0 @@
-<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN"
-        "http://www.w3.org/TR/html4/loose.dtd">
-        <html>
-        <head><title>A Diagram of TREE_RCU's Grace-Period Memory Ordering</title>
-        <meta HTTP-EQUIV="Content-Type" CONTENT="text/html; charset=iso-8859-1">
-
-<p><img src="TreeRCU-gp.svg" alt="TreeRCU-gp.svg">
-
-</body></html>
diff --git a/Documentation/RCU/Design/Memory-Ordering/Tree-RCU-Memory-Ordering.html b/Documentation/RCU/Design/Memory-Ordering/Tree-RCU-Memory-Ordering.html
deleted file mode 100644
index c64f8d26609f..000000000000
--- a/Documentation/RCU/Design/Memory-Ordering/Tree-RCU-Memory-Ordering.html
+++ /dev/null
@@ -1,704 +0,0 @@
-<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN"
-        "http://www.w3.org/TR/html4/loose.dtd">
-        <html>
-        <head><title>A Tour Through TREE_RCU's Grace-Period Memory Ordering</title>
-        <meta HTTP-EQUIV="Content-Type" CONTENT="text/html; charset=iso-8859-1">
-
-           <p>August 8, 2017</p>
-           <p>This article was contributed by Paul E.&nbsp;McKenney</p>
-
-<h3>Introduction</h3>
-
-<p>This document gives a rough visual overview of how Tree RCU's
-grace-period memory ordering guarantee is provided.
-
-<ol>
-<li>	<a href="#What Is Tree RCU's Grace Period Memory Ordering Guarantee?">
-	What Is Tree RCU's Grace Period Memory Ordering Guarantee?</a>
-<li>	<a href="#Tree RCU Grace Period Memory Ordering Building Blocks">
-	Tree RCU Grace Period Memory Ordering Building Blocks</a>
-<li>	<a href="#Tree RCU Grace Period Memory Ordering Components">
-	Tree RCU Grace Period Memory Ordering Components</a>
-<li>	<a href="#Putting It All Together">Putting It All Together</a>
-</ol>
-
-<h3><a name="What Is Tree RCU's Grace Period Memory Ordering Guarantee?">
-What Is Tree RCU's Grace Period Memory Ordering Guarantee?</a></h3>
-
-<p>RCU grace periods provide extremely strong memory-ordering guarantees
-for non-idle non-offline code.
-Any code that happens after the end of a given RCU grace period is guaranteed
-to see the effects of all accesses prior to the beginning of that grace
-period that are within RCU read-side critical sections.
-Similarly, any code that happens before the beginning of a given RCU grace
-period is guaranteed to see the effects of all accesses following the end
-of that grace period that are within RCU read-side critical sections.
-
-<p>Note well that RCU-sched read-side critical sections include any region
-of code for which preemption is disabled.
-Given that each individual machine instruction can be thought of as
-an extremely small region of preemption-disabled code, one can think of
-<tt>synchronize_rcu()</tt> as <tt>smp_mb()</tt> on steroids.
-
-<p>RCU updaters use this guarantee by splitting their updates into
-two phases, one of which is executed before the grace period and
-the other of which is executed after the grace period.
-In the most common use case, phase one removes an element from
-a linked RCU-protected data structure, and phase two frees that element.
-For this to work, any readers that have witnessed state prior to the
-phase-one update (in the common case, removal) must not witness state
-following the phase-two update (in the common case, freeing).
-
-<p>The RCU implementation provides this guarantee using a network
-of lock-based critical sections, memory barriers, and per-CPU
-processing, as is described in the following sections.
-
-<h3><a name="Tree RCU Grace Period Memory Ordering Building Blocks">
-Tree RCU Grace Period Memory Ordering Building Blocks</a></h3>
-
-<p>The workhorse for RCU's grace-period memory ordering is the
-critical section for the <tt>rcu_node</tt> structure's
-<tt>-&gt;lock</tt>.
-These critical sections use helper functions for lock acquisition, including
-<tt>raw_spin_lock_rcu_node()</tt>,
-<tt>raw_spin_lock_irq_rcu_node()</tt>, and
-<tt>raw_spin_lock_irqsave_rcu_node()</tt>.
-Their lock-release counterparts are
-<tt>raw_spin_unlock_rcu_node()</tt>,
-<tt>raw_spin_unlock_irq_rcu_node()</tt>, and
-<tt>raw_spin_unlock_irqrestore_rcu_node()</tt>,
-respectively.
-For completeness, a
-<tt>raw_spin_trylock_rcu_node()</tt>
-is also provided.
-The key point is that the lock-acquisition functions, including
-<tt>raw_spin_trylock_rcu_node()</tt>, all invoke
-<tt>smp_mb__after_unlock_lock()</tt> immediately after successful
-acquisition of the lock.
-
-<p>Therefore, for any given <tt>rcu_node</tt> structure, any access
-happening before one of the above lock-release functions will be seen
-by all CPUs as happening before any access happening after a later
-one of the above lock-acquisition functions.
-Furthermore, any access happening before one of the
-above lock-release function on any given CPU will be seen by all
-CPUs as happening before any access happening after a later one
-of the above lock-acquisition functions executing on that same CPU,
-even if the lock-release and lock-acquisition functions are operating
-on different <tt>rcu_node</tt> structures.
-Tree RCU uses these two ordering guarantees to form an ordering
-network among all CPUs that were in any way involved in the grace
-period, including any CPUs that came online or went offline during
-the grace period in question.
-
-<p>The following litmus test exhibits the ordering effects of these
-lock-acquisition and lock-release functions:
-
-<pre>
- 1 int x, y, z;
- 2
- 3 void task0(void)
- 4 {
- 5   raw_spin_lock_rcu_node(rnp);
- 6   WRITE_ONCE(x, 1);
- 7   r1 = READ_ONCE(y);
- 8   raw_spin_unlock_rcu_node(rnp);
- 9 }
-10
-11 void task1(void)
-12 {
-13   raw_spin_lock_rcu_node(rnp);
-14   WRITE_ONCE(y, 1);
-15   r2 = READ_ONCE(z);
-16   raw_spin_unlock_rcu_node(rnp);
-17 }
-18
-19 void task2(void)
-20 {
-21   WRITE_ONCE(z, 1);
-22   smp_mb();
-23   r3 = READ_ONCE(x);
-24 }
-25
-26 WARN_ON(r1 == 0 &amp;&amp; r2 == 0 &amp;&amp; r3 == 0);
-</pre>
-
-<p>The <tt>WARN_ON()</tt> is evaluated at &ldquo;the end of time&rdquo;,
-after all changes have propagated throughout the system.
-Without the <tt>smp_mb__after_unlock_lock()</tt> provided by the
-acquisition functions, this <tt>WARN_ON()</tt> could trigger, for example
-on PowerPC.
-The <tt>smp_mb__after_unlock_lock()</tt> invocations prevent this
-<tt>WARN_ON()</tt> from triggering.
-
-<p>This approach must be extended to include idle CPUs, which need
-RCU's grace-period memory ordering guarantee to extend to any
-RCU read-side critical sections preceding and following the current
-idle sojourn.
-This case is handled by calls to the strongly ordered
-<tt>atomic_add_return()</tt> read-modify-write atomic operation that
-is invoked within <tt>rcu_dynticks_eqs_enter()</tt> at idle-entry
-time and within <tt>rcu_dynticks_eqs_exit()</tt> at idle-exit time.
-The grace-period kthread invokes <tt>rcu_dynticks_snap()</tt> and
-<tt>rcu_dynticks_in_eqs_since()</tt> (both of which invoke
-an <tt>atomic_add_return()</tt> of zero) to detect idle CPUs.
-
-<table>
-<tr><th>&nbsp;</th></tr>
-<tr><th align="left">Quick Quiz:</th></tr>
-<tr><td>
-	But what about CPUs that remain offline for the entire
-	grace period?
-</td></tr>
-<tr><th align="left">Answer:</th></tr>
-<tr><td bgcolor="#ffffff"><font color="ffffff">
-	Such CPUs will be offline at the beginning of the grace period,
-	so the grace period won't expect quiescent states from them.
-	Races between grace-period start and CPU-hotplug operations
-	are mediated by the CPU's leaf <tt>rcu_node</tt> structure's
-	<tt>-&gt;lock</tt> as described above.
-</font></td></tr>
-<tr><td>&nbsp;</td></tr>
-</table>
-
-<p>The approach must be extended to handle one final case, that
-of waking a task blocked in <tt>synchronize_rcu()</tt>.
-This task might be affinitied to a CPU that is not yet aware that
-the grace period has ended, and thus might not yet be subject to
-the grace period's memory ordering.
-Therefore, there is an <tt>smp_mb()</tt> after the return from
-<tt>wait_for_completion()</tt> in the <tt>synchronize_rcu()</tt>
-code path.
-
-<table>
-<tr><th>&nbsp;</th></tr>
-<tr><th align="left">Quick Quiz:</th></tr>
-<tr><td>
-	What?  Where???
-	I don't see any <tt>smp_mb()</tt> after the return from
-	<tt>wait_for_completion()</tt>!!!
-</td></tr>
-<tr><th align="left">Answer:</th></tr>
-<tr><td bgcolor="#ffffff"><font color="ffffff">
-	That would be because I spotted the need for that
-	<tt>smp_mb()</tt> during the creation of this documentation,
-	and it is therefore unlikely to hit mainline before v4.14.
-	Kudos to Lance Roy, Will Deacon, Peter Zijlstra, and
-	Jonathan Cameron for asking questions that sensitized me
-	to the rather elaborate sequence of events that demonstrate
-	the need for this memory barrier.
-</font></td></tr>
-<tr><td>&nbsp;</td></tr>
-</table>
-
-<p>Tree RCU's grace--period memory-ordering guarantees rely most
-heavily on the <tt>rcu_node</tt> structure's <tt>-&gt;lock</tt>
-field, so much so that it is necessary to abbreviate this pattern
-in the diagrams in the next section.
-For example, consider the <tt>rcu_prepare_for_idle()</tt> function
-shown below, which is one of several functions that enforce ordering
-of newly arrived RCU callbacks against future grace periods:
-
-<pre>
- 1 static void rcu_prepare_for_idle(void)
- 2 {
- 3   bool needwake;
- 4   struct rcu_data *rdp;
- 5   struct rcu_dynticks *rdtp = this_cpu_ptr(&amp;rcu_dynticks);
- 6   struct rcu_node *rnp;
- 7   struct rcu_state *rsp;
- 8   int tne;
- 9
-10   if (IS_ENABLED(CONFIG_RCU_NOCB_CPU_ALL) ||
-11       rcu_is_nocb_cpu(smp_processor_id()))
-12     return;
-13   tne = READ_ONCE(tick_nohz_active);
-14   if (tne != rdtp-&gt;tick_nohz_enabled_snap) {
-15     if (rcu_cpu_has_callbacks(NULL))
-16       invoke_rcu_core();
-17     rdtp-&gt;tick_nohz_enabled_snap = tne;
-18     return;
-19   }
-20   if (!tne)
-21     return;
-22   if (rdtp-&gt;all_lazy &amp;&amp;
-23       rdtp-&gt;nonlazy_posted != rdtp-&gt;nonlazy_posted_snap) {
-24     rdtp-&gt;all_lazy = false;
-25     rdtp-&gt;nonlazy_posted_snap = rdtp-&gt;nonlazy_posted;
-26     invoke_rcu_core();
-27     return;
-28   }
-29   if (rdtp-&gt;last_accelerate == jiffies)
-30     return;
-31   rdtp-&gt;last_accelerate = jiffies;
-32   for_each_rcu_flavor(rsp) {
-33     rdp = this_cpu_ptr(rsp-&gt;rda);
-34     if (rcu_segcblist_pend_cbs(&amp;rdp-&gt;cblist))
-35       continue;
-36     rnp = rdp-&gt;mynode;
-37     raw_spin_lock_rcu_node(rnp);
-38     needwake = rcu_accelerate_cbs(rsp, rnp, rdp);
-39     raw_spin_unlock_rcu_node(rnp);
-40     if (needwake)
-41       rcu_gp_kthread_wake(rsp);
-42   }
-43 }
-</pre>
-
-<p>But the only part of <tt>rcu_prepare_for_idle()</tt> that really
-matters for this discussion are lines&nbsp;37&ndash;39.
-We will therefore abbreviate this function as follows:
-
-</p><p><img src="rcu_node-lock.svg" alt="rcu_node-lock.svg">
-
-<p>The box represents the <tt>rcu_node</tt> structure's <tt>-&gt;lock</tt>
-critical section, with the double line on top representing the additional
-<tt>smp_mb__after_unlock_lock()</tt>.
-
-<h3><a name="Tree RCU Grace Period Memory Ordering Components">
-Tree RCU Grace Period Memory Ordering Components</a></h3>
-
-<p>Tree RCU's grace-period memory-ordering guarantee is provided by
-a number of RCU components:
-
-<ol>
-<li>	<a href="#Callback Registry">Callback Registry</a>
-<li>	<a href="#Grace-Period Initialization">Grace-Period Initialization</a>
-<li>	<a href="#Self-Reported Quiescent States">
-	Self-Reported Quiescent States</a>
-<li>	<a href="#Dynamic Tick Interface">Dynamic Tick Interface</a>
-<li>	<a href="#CPU-Hotplug Interface">CPU-Hotplug Interface</a>
-<li>	<a href="Forcing Quiescent States">Forcing Quiescent States</a>
-<li>	<a href="Grace-Period Cleanup">Grace-Period Cleanup</a>
-<li>	<a href="Callback Invocation">Callback Invocation</a>
-</ol>
-
-<p>Each of the following section looks at the corresponding component
-in detail.
-
-<h4><a name="Callback Registry">Callback Registry</a></h4>
-
-<p>If RCU's grace-period guarantee is to mean anything at all, any
-access that happens before a given invocation of <tt>call_rcu()</tt>
-must also happen before the corresponding grace period.
-The implementation of this portion of RCU's grace period guarantee
-is shown in the following figure:
-
-</p><p><img src="TreeRCU-callback-registry.svg" alt="TreeRCU-callback-registry.svg">
-
-<p>Because <tt>call_rcu()</tt> normally acts only on CPU-local state,
-it provides no ordering guarantees, either for itself or for
-phase one of the update (which again will usually be removal of
-an element from an RCU-protected data structure).
-It simply enqueues the <tt>rcu_head</tt> structure on a per-CPU list,
-which cannot become associated with a grace period until a later
-call to <tt>rcu_accelerate_cbs()</tt>, as shown in the diagram above.
-
-<p>One set of code paths shown on the left invokes
-<tt>rcu_accelerate_cbs()</tt> via
-<tt>note_gp_changes()</tt>, either directly from <tt>call_rcu()</tt> (if
-the current CPU is inundated with queued <tt>rcu_head</tt> structures)
-or more likely from an <tt>RCU_SOFTIRQ</tt> handler.
-Another code path in the middle is taken only in kernels built with
-<tt>CONFIG_RCU_FAST_NO_HZ=y</tt>, which invokes
-<tt>rcu_accelerate_cbs()</tt> via <tt>rcu_prepare_for_idle()</tt>.
-The final code path on the right is taken only in kernels built with
-<tt>CONFIG_HOTPLUG_CPU=y</tt>, which invokes
-<tt>rcu_accelerate_cbs()</tt> via
-<tt>rcu_advance_cbs()</tt>, <tt>rcu_migrate_callbacks</tt>,
-<tt>rcutree_migrate_callbacks()</tt>, and <tt>takedown_cpu()</tt>,
-which in turn is invoked on a surviving CPU after the outgoing
-CPU has been completely offlined.
-
-<p>There are a few other code paths within grace-period processing
-that opportunistically invoke <tt>rcu_accelerate_cbs()</tt>.
-However, either way, all of the CPU's recently queued <tt>rcu_head</tt>
-structures are associated with a future grace-period number under
-the protection of the CPU's lead <tt>rcu_node</tt> structure's
-<tt>-&gt;lock</tt>.
-In all cases, there is full ordering against any prior critical section
-for that same <tt>rcu_node</tt> structure's <tt>-&gt;lock</tt>, and
-also full ordering against any of the current task's or CPU's prior critical
-sections for any <tt>rcu_node</tt> structure's <tt>-&gt;lock</tt>.
-
-<p>The next section will show how this ordering ensures that any
-accesses prior to the <tt>call_rcu()</tt> (particularly including phase
-one of the update)
-happen before the start of the corresponding grace period.
-
-<table>
-<tr><th>&nbsp;</th></tr>
-<tr><th align="left">Quick Quiz:</th></tr>
-<tr><td>
-	But what about <tt>synchronize_rcu()</tt>?
-</td></tr>
-<tr><th align="left">Answer:</th></tr>
-<tr><td bgcolor="#ffffff"><font color="ffffff">
-	The <tt>synchronize_rcu()</tt> passes <tt>call_rcu()</tt>
-	to <tt>wait_rcu_gp()</tt>, which invokes it.
-	So either way, it eventually comes down to <tt>call_rcu()</tt>.
-</font></td></tr>
-<tr><td>&nbsp;</td></tr>
-</table>
-
-<h4><a name="Grace-Period Initialization">Grace-Period Initialization</a></h4>
-
-<p>Grace-period initialization is carried out by
-the grace-period kernel thread, which makes several passes over the
-<tt>rcu_node</tt> tree within the <tt>rcu_gp_init()</tt> function.
-This means that showing the full flow of ordering through the
-grace-period computation will require duplicating this tree.
-If you find this confusing, please note that the state of the
-<tt>rcu_node</tt> changes over time, just like Heraclitus's river.
-However, to keep the <tt>rcu_node</tt> river tractable, the
-grace-period kernel thread's traversals are presented in multiple
-parts, starting in this section with the various phases of
-grace-period initialization.
-
-<p>The first ordering-related grace-period initialization action is to
-advance the <tt>rcu_state</tt> structure's <tt>-&gt;gp_seq</tt>
-grace-period-number counter, as shown below:
-
-</p><p><img src="TreeRCU-gp-init-1.svg" alt="TreeRCU-gp-init-1.svg" width="75%">
-
-<p>The actual increment is carried out using <tt>smp_store_release()</tt>,
-which helps reject false-positive RCU CPU stall detection.
-Note that only the root <tt>rcu_node</tt> structure is touched.
-
-<p>The first pass through the <tt>rcu_node</tt> tree updates bitmasks
-based on CPUs having come online or gone offline since the start of
-the previous grace period.
-In the common case where the number of online CPUs for this <tt>rcu_node</tt>
-structure has not transitioned to or from zero,
-this pass will scan only the leaf <tt>rcu_node</tt> structures.
-However, if the number of online CPUs for a given leaf <tt>rcu_node</tt>
-structure has transitioned from zero,
-<tt>rcu_init_new_rnp()</tt> will be invoked for the first incoming CPU.
-Similarly, if the number of online CPUs for a given leaf <tt>rcu_node</tt>
-structure has transitioned to zero,
-<tt>rcu_cleanup_dead_rnp()</tt> will be invoked for the last outgoing CPU.
-The diagram below shows the path of ordering if the leftmost
-<tt>rcu_node</tt> structure onlines its first CPU and if the next
-<tt>rcu_node</tt> structure has no online CPUs
-(or, alternatively if the leftmost <tt>rcu_node</tt> structure offlines
-its last CPU and if the next <tt>rcu_node</tt> structure has no online CPUs).
-
-</p><p><img src="TreeRCU-gp-init-2.svg" alt="TreeRCU-gp-init-1.svg" width="75%">
-
-<p>The final <tt>rcu_gp_init()</tt> pass through the <tt>rcu_node</tt>
-tree traverses breadth-first, setting each <tt>rcu_node</tt> structure's
-<tt>-&gt;gp_seq</tt> field to the newly advanced value from the
-<tt>rcu_state</tt> structure, as shown in the following diagram.
-
-</p><p><img src="TreeRCU-gp-init-3.svg" alt="TreeRCU-gp-init-1.svg" width="75%">
-
-<p>This change will also cause each CPU's next call to
-<tt>__note_gp_changes()</tt>
-to notice that a new grace period has started, as described in the next
-section.
-But because the grace-period kthread started the grace period at the
-root (with the advancing of the <tt>rcu_state</tt> structure's
-<tt>-&gt;gp_seq</tt> field) before setting each leaf <tt>rcu_node</tt>
-structure's <tt>-&gt;gp_seq</tt> field, each CPU's observation of
-the start of the grace period will happen after the actual start
-of the grace period.
-
-<table>
-<tr><th>&nbsp;</th></tr>
-<tr><th align="left">Quick Quiz:</th></tr>
-<tr><td>
-	But what about the CPU that started the grace period?
-	Why wouldn't it see the start of the grace period right when
-	it started that grace period?
-</td></tr>
-<tr><th align="left">Answer:</th></tr>
-<tr><td bgcolor="#ffffff"><font color="ffffff">
-	In some deep philosophical and overly anthromorphized
-	sense, yes, the CPU starting the grace period is immediately
-	aware of having done so.
-	However, if we instead assume that RCU is not self-aware,
-	then even the CPU starting the grace period does not really
-	become aware of the start of this grace period until its
-	first call to <tt>__note_gp_changes()</tt>.
-	On the other hand, this CPU potentially gets early notification
-	because it invokes <tt>__note_gp_changes()</tt> during its
-	last <tt>rcu_gp_init()</tt> pass through its leaf
-	<tt>rcu_node</tt> structure.
-</font></td></tr>
-<tr><td>&nbsp;</td></tr>
-</table>
-
-<h4><a name="Self-Reported Quiescent States">
-Self-Reported Quiescent States</a></h4>
-
-<p>When all entities that might block the grace period have reported
-quiescent states (or as described in a later section, had quiescent
-states reported on their behalf), the grace period can end.
-Online non-idle CPUs report their own quiescent states, as shown
-in the following diagram:
-
-</p><p><img src="TreeRCU-qs.svg" alt="TreeRCU-qs.svg" width="75%">
-
-<p>This is for the last CPU to report a quiescent state, which signals
-the end of the grace period.
-Earlier quiescent states would push up the <tt>rcu_node</tt> tree
-only until they encountered an <tt>rcu_node</tt> structure that
-is waiting for additional quiescent states.
-However, ordering is nevertheless preserved because some later quiescent
-state will acquire that <tt>rcu_node</tt> structure's <tt>-&gt;lock</tt>.
-
-<p>Any number of events can lead up to a CPU invoking
-<tt>note_gp_changes</tt> (or alternatively, directly invoking
-<tt>__note_gp_changes()</tt>), at which point that CPU will notice
-the start of a new grace period while holding its leaf
-<tt>rcu_node</tt> lock.
-Therefore, all execution shown in this diagram happens after the
-start of the grace period.
-In addition, this CPU will consider any RCU read-side critical
-section that started before the invocation of <tt>__note_gp_changes()</tt>
-to have started before the grace period, and thus a critical
-section that the grace period must wait on.
-
-<table>
-<tr><th>&nbsp;</th></tr>
-<tr><th align="left">Quick Quiz:</th></tr>
-<tr><td>
-	But a RCU read-side critical section might have started
-	after the beginning of the grace period
-	(the advancing of <tt>-&gt;gp_seq</tt> from earlier), so why should
-	the grace period wait on such a critical section?
-</td></tr>
-<tr><th align="left">Answer:</th></tr>
-<tr><td bgcolor="#ffffff"><font color="ffffff">
-	It is indeed not necessary for the grace period to wait on such
-	a critical section.
-	However, it is permissible to wait on it.
-	And it is furthermore important to wait on it, as this
-	lazy approach is far more scalable than a &ldquo;big bang&rdquo;
-	all-at-once grace-period start could possibly be.
-</font></td></tr>
-<tr><td>&nbsp;</td></tr>
-</table>
-
-<p>If the CPU does a context switch, a quiescent state will be
-noted by <tt>rcu_node_context_switch()</tt> on the left.
-On the other hand, if the CPU takes a scheduler-clock interrupt
-while executing in usermode, a quiescent state will be noted by
-<tt>rcu_sched_clock_irq()</tt> on the right.
-Either way, the passage through a quiescent state will be noted
-in a per-CPU variable.
-
-<p>The next time an <tt>RCU_SOFTIRQ</tt> handler executes on
-this CPU (for example, after the next scheduler-clock
-interrupt), <tt>rcu_core()</tt> will invoke
-<tt>rcu_check_quiescent_state()</tt>, which will notice the
-recorded quiescent state, and invoke
-<tt>rcu_report_qs_rdp()</tt>.
-If <tt>rcu_report_qs_rdp()</tt> verifies that the quiescent state
-really does apply to the current grace period, it invokes
-<tt>rcu_report_rnp()</tt> which traverses up the <tt>rcu_node</tt>
-tree as shown at the bottom of the diagram, clearing bits from
-each <tt>rcu_node</tt> structure's <tt>-&gt;qsmask</tt> field,
-and propagating up the tree when the result is zero.
-
-<p>Note that traversal passes upwards out of a given <tt>rcu_node</tt>
-structure only if the current CPU is reporting the last quiescent
-state for the subtree headed by that <tt>rcu_node</tt> structure.
-A key point is that if a CPU's traversal stops at a given <tt>rcu_node</tt>
-structure, then there will be a later traversal by another CPU
-(or perhaps the same one) that proceeds upwards
-from that point, and the <tt>rcu_node</tt> <tt>-&gt;lock</tt>
-guarantees that the first CPU's quiescent state happens before the
-remainder of the second CPU's traversal.
-Applying this line of thought repeatedly shows that all CPUs'
-quiescent states happen before the last CPU traverses through
-the root <tt>rcu_node</tt> structure, the &ldquo;last CPU&rdquo;
-being the one that clears the last bit in the root <tt>rcu_node</tt>
-structure's <tt>-&gt;qsmask</tt> field.
-
-<h4><a name="Dynamic Tick Interface">Dynamic Tick Interface</a></h4>
-
-<p>Due to energy-efficiency considerations, RCU is forbidden from
-disturbing idle CPUs.
-CPUs are therefore required to notify RCU when entering or leaving idle
-state, which they do via fully ordered value-returning atomic operations
-on a per-CPU variable.
-The ordering effects are as shown below:
-
-</p><p><img src="TreeRCU-dyntick.svg" alt="TreeRCU-dyntick.svg" width="50%">
-
-<p>The RCU grace-period kernel thread samples the per-CPU idleness
-variable while holding the corresponding CPU's leaf <tt>rcu_node</tt>
-structure's <tt>-&gt;lock</tt>.
-This means that any RCU read-side critical sections that precede the
-idle period (the oval near the top of the diagram above) will happen
-before the end of the current grace period.
-Similarly, the beginning of the current grace period will happen before
-any RCU read-side critical sections that follow the
-idle period (the oval near the bottom of the diagram above).
-
-<p>Plumbing this into the full grace-period execution is described
-<a href="#Forcing Quiescent States">below</a>.
-
-<h4><a name="CPU-Hotplug Interface">CPU-Hotplug Interface</a></h4>
-
-<p>RCU is also forbidden from disturbing offline CPUs, which might well
-be powered off and removed from the system completely.
-CPUs are therefore required to notify RCU of their comings and goings
-as part of the corresponding CPU hotplug operations.
-The ordering effects are shown below:
-
-</p><p><img src="TreeRCU-hotplug.svg" alt="TreeRCU-hotplug.svg" width="50%">
-
-<p>Because CPU hotplug operations are much less frequent than idle transitions,
-they are heavier weight, and thus acquire the CPU's leaf <tt>rcu_node</tt>
-structure's <tt>-&gt;lock</tt> and update this structure's
-<tt>-&gt;qsmaskinitnext</tt>.
-The RCU grace-period kernel thread samples this mask to detect CPUs
-having gone offline since the beginning of this grace period.
-
-<p>Plumbing this into the full grace-period execution is described
-<a href="#Forcing Quiescent States">below</a>.
-
-<h4><a name="Forcing Quiescent States">Forcing Quiescent States</a></h4>
-
-<p>As noted above, idle and offline CPUs cannot report their own
-quiescent states, and therefore the grace-period kernel thread
-must do the reporting on their behalf.
-This process is called &ldquo;forcing quiescent states&rdquo;, it is
-repeated every few jiffies, and its ordering effects are shown below:
-
-</p><p><img src="TreeRCU-gp-fqs.svg" alt="TreeRCU-gp-fqs.svg" width="100%">
-
-<p>Each pass of quiescent state forcing is guaranteed to traverse the
-leaf <tt>rcu_node</tt> structures, and if there are no new quiescent
-states due to recently idled and/or offlined CPUs, then only the
-leaves are traversed.
-However, if there is a newly offlined CPU as illustrated on the left
-or a newly idled CPU as illustrated on the right, the corresponding
-quiescent state will be driven up towards the root.
-As with self-reported quiescent states, the upwards driving stops
-once it reaches an <tt>rcu_node</tt> structure that has quiescent
-states outstanding from other CPUs.
-
-<table>
-<tr><th>&nbsp;</th></tr>
-<tr><th align="left">Quick Quiz:</th></tr>
-<tr><td>
-	The leftmost drive to root stopped before it reached
-	the root <tt>rcu_node</tt> structure, which means that
-	there are still CPUs subordinate to that structure on
-	which the current grace period is waiting.
-	Given that, how is it possible that the rightmost drive
-	to root ended the grace period?
-</td></tr>
-<tr><th align="left">Answer:</th></tr>
-<tr><td bgcolor="#ffffff"><font color="ffffff">
-	Good analysis!
-	It is in fact impossible in the absence of bugs in RCU.
-	But this diagram is complex enough as it is, so simplicity
-	overrode accuracy.
-	You can think of it as poetic license, or you can think of
-	it as misdirection that is resolved in the
-	<a href="#Putting It All Together">stitched-together diagram</a>.
-</font></td></tr>
-<tr><td>&nbsp;</td></tr>
-</table>
-
-<h4><a name="Grace-Period Cleanup">Grace-Period Cleanup</a></h4>
-
-<p>Grace-period cleanup first scans the <tt>rcu_node</tt> tree
-breadth-first advancing all the <tt>-&gt;gp_seq</tt> fields, then it
-advances the <tt>rcu_state</tt> structure's <tt>-&gt;gp_seq</tt> field.
-The ordering effects are shown below:
-
-</p><p><img src="TreeRCU-gp-cleanup.svg" alt="TreeRCU-gp-cleanup.svg" width="75%">
-
-<p>As indicated by the oval at the bottom of the diagram, once
-grace-period cleanup is complete, the next grace period can begin.
-
-<table>
-<tr><th>&nbsp;</th></tr>
-<tr><th align="left">Quick Quiz:</th></tr>
-<tr><td>
-	But when precisely does the grace period end?
-</td></tr>
-<tr><th align="left">Answer:</th></tr>
-<tr><td bgcolor="#ffffff"><font color="ffffff">
-	There is no useful single point at which the grace period
-	can be said to end.
-	The earliest reasonable candidate is as soon as the last
-	CPU has reported its quiescent state, but it may be some
-	milliseconds before RCU becomes aware of this.
-	The latest reasonable candidate is once the <tt>rcu_state</tt>
-	structure's <tt>-&gt;gp_seq</tt> field has been updated,
-	but it is quite possible that some CPUs have already completed
-	phase two of their updates by that time.
-	In short, if you are going to work with RCU, you need to
-	learn to embrace uncertainty.
-</font></td></tr>
-<tr><td>&nbsp;</td></tr>
-</table>
-
-
-<h4><a name="Callback Invocation">Callback Invocation</a></h4>
-
-<p>Once a given CPU's leaf <tt>rcu_node</tt> structure's
-<tt>-&gt;gp_seq</tt> field has been updated, that CPU can begin
-invoking its RCU callbacks that were waiting for this grace period
-to end.
-These callbacks are identified by <tt>rcu_advance_cbs()</tt>,
-which is usually invoked by <tt>__note_gp_changes()</tt>.
-As shown in the diagram below, this invocation can be triggered by
-the scheduling-clock interrupt (<tt>rcu_sched_clock_irq()</tt> on
-the left) or by idle entry (<tt>rcu_cleanup_after_idle()</tt> on
-the right, but only for kernels build with
-<tt>CONFIG_RCU_FAST_NO_HZ=y</tt>).
-Either way, <tt>RCU_SOFTIRQ</tt> is raised, which results in
-<tt>rcu_do_batch()</tt> invoking the callbacks, which in turn
-allows those callbacks to carry out (either directly or indirectly
-via wakeup) the needed phase-two processing for each update.
-
-</p><p><img src="TreeRCU-callback-invocation.svg" alt="TreeRCU-callback-invocation.svg" width="60%">
-
-<p>Please note that callback invocation can also be prompted by any
-number of corner-case code paths, for example, when a CPU notes that
-it has excessive numbers of callbacks queued.
-In all cases, the CPU acquires its leaf <tt>rcu_node</tt> structure's
-<tt>-&gt;lock</tt> before invoking callbacks, which preserves the
-required ordering against the newly completed grace period.
-
-<p>However, if the callback function communicates to other CPUs,
-for example, doing a wakeup, then it is that function's responsibility
-to maintain ordering.
-For example, if the callback function wakes up a task that runs on
-some other CPU, proper ordering must in place in both the callback
-function and the task being awakened.
-To see why this is important, consider the top half of the
-<a href="#Grace-Period Cleanup">grace-period cleanup</a> diagram.
-The callback might be running on a CPU corresponding to the leftmost
-leaf <tt>rcu_node</tt> structure, and awaken a task that is to run on
-a CPU corresponding to the rightmost leaf <tt>rcu_node</tt> structure,
-and the grace-period kernel thread might not yet have reached the
-rightmost leaf.
-In this case, the grace period's memory ordering might not yet have
-reached that CPU, so again the callback function and the awakened
-task must supply proper ordering.
-
-<h3><a name="Putting It All Together">Putting It All Together</a></h3>
-
-<p>A stitched-together diagram is
-<a href="Tree-RCU-Diagram.html">here</a>.
-
-<h3><a name="Legal Statement">
-Legal Statement</a></h3>
-
-<p>This work represents the view of the author and does not necessarily
-represent the view of IBM.
-
-</p><p>Linux is a registered trademark of Linus Torvalds.
-
-</p><p>Other company, product, and service names may be trademarks or
-service marks of others.
-
-</body></html>
diff --git a/Documentation/RCU/Design/Memory-Ordering/Tree-RCU-Memory-Ordering.rst b/Documentation/RCU/Design/Memory-Ordering/Tree-RCU-Memory-Ordering.rst
new file mode 100644
index 000000000000..1a8b129cfc04
--- /dev/null
+++ b/Documentation/RCU/Design/Memory-Ordering/Tree-RCU-Memory-Ordering.rst
@@ -0,0 +1,624 @@
+======================================================
+A Tour Through TREE_RCU's Grace-Period Memory Ordering
+======================================================
+
+August 8, 2017
+
+This article was contributed by Paul E.&nbsp;McKenney
+
+Introduction
+============
+
+This document gives a rough visual overview of how Tree RCU's
+grace-period memory ordering guarantee is provided.
+
+What Is Tree RCU's Grace Period Memory Ordering Guarantee?
+==========================================================
+
+RCU grace periods provide extremely strong memory-ordering guarantees
+for non-idle non-offline code.
+Any code that happens after the end of a given RCU grace period is guaranteed
+to see the effects of all accesses prior to the beginning of that grace
+period that are within RCU read-side critical sections.
+Similarly, any code that happens before the beginning of a given RCU grace
+period is guaranteed to see the effects of all accesses following the end
+of that grace period that are within RCU read-side critical sections.
+
+Note well that RCU-sched read-side critical sections include any region
+of code for which preemption is disabled.
+Given that each individual machine instruction can be thought of as
+an extremely small region of preemption-disabled code, one can think of
+``synchronize_rcu()`` as ``smp_mb()`` on steroids.
+
+RCU updaters use this guarantee by splitting their updates into
+two phases, one of which is executed before the grace period and
+the other of which is executed after the grace period.
+In the most common use case, phase one removes an element from
+a linked RCU-protected data structure, and phase two frees that element.
+For this to work, any readers that have witnessed state prior to the
+phase-one update (in the common case, removal) must not witness state
+following the phase-two update (in the common case, freeing).
+
+The RCU implementation provides this guarantee using a network
+of lock-based critical sections, memory barriers, and per-CPU
+processing, as is described in the following sections.
+
+Tree RCU Grace Period Memory Ordering Building Blocks
+=====================================================
+
+The workhorse for RCU's grace-period memory ordering is the
+critical section for the ``rcu_node`` structure's
+``-&gt;lock``. These critical sections use helper functions for lock
+acquisition, including ``raw_spin_lock_rcu_node()``,
+``raw_spin_lock_irq_rcu_node()``, and ``raw_spin_lock_irqsave_rcu_node()``.
+Their lock-release counterparts are ``raw_spin_unlock_rcu_node()``,
+``raw_spin_unlock_irq_rcu_node()``, and
+``raw_spin_unlock_irqrestore_rcu_node()``, respectively.
+For completeness, a ``raw_spin_trylock_rcu_node()`` is also provided.
+The key point is that the lock-acquisition functions, including
+``raw_spin_trylock_rcu_node()``, all invoke ``smp_mb__after_unlock_lock()``
+immediately after successful acquisition of the lock.
+
+Therefore, for any given ``rcu_node`` structure, any access
+happening before one of the above lock-release functions will be seen
+by all CPUs as happening before any access happening after a later
+one of the above lock-acquisition functions.
+Furthermore, any access happening before one of the
+above lock-release function on any given CPU will be seen by all
+CPUs as happening before any access happening after a later one
+of the above lock-acquisition functions executing on that same CPU,
+even if the lock-release and lock-acquisition functions are operating
+on different ``rcu_node`` structures.
+Tree RCU uses these two ordering guarantees to form an ordering
+network among all CPUs that were in any way involved in the grace
+period, including any CPUs that came online or went offline during
+the grace period in question.
+
+The following litmus test exhibits the ordering effects of these
+lock-acquisition and lock-release functions::
+
+    1 int x, y, z;
+    2
+    3 void task0(void)
+    4 {
+    5   raw_spin_lock_rcu_node(rnp);
+    6   WRITE_ONCE(x, 1);
+    7   r1 = READ_ONCE(y);
+    8   raw_spin_unlock_rcu_node(rnp);
+    9 }
+   10
+   11 void task1(void)
+   12 {
+   13   raw_spin_lock_rcu_node(rnp);
+   14   WRITE_ONCE(y, 1);
+   15   r2 = READ_ONCE(z);
+   16   raw_spin_unlock_rcu_node(rnp);
+   17 }
+   18
+   19 void task2(void)
+   20 {
+   21   WRITE_ONCE(z, 1);
+   22   smp_mb();
+   23   r3 = READ_ONCE(x);
+   24 }
+   25
+   26 WARN_ON(r1 == 0 &amp;&amp; r2 == 0 &amp;&amp; r3 == 0);
+
+The ``WARN_ON()`` is evaluated at &ldquo;the end of time&rdquo;,
+after all changes have propagated throughout the system.
+Without the ``smp_mb__after_unlock_lock()`` provided by the
+acquisition functions, this ``WARN_ON()`` could trigger, for example
+on PowerPC.
+The ``smp_mb__after_unlock_lock()`` invocations prevent this
+``WARN_ON()`` from triggering.
+
+This approach must be extended to include idle CPUs, which need
+RCU's grace-period memory ordering guarantee to extend to any
+RCU read-side critical sections preceding and following the current
+idle sojourn.
+This case is handled by calls to the strongly ordered
+``atomic_add_return()`` read-modify-write atomic operation that
+is invoked within ``rcu_dynticks_eqs_enter()`` at idle-entry
+time and within ``rcu_dynticks_eqs_exit()`` at idle-exit time.
+The grace-period kthread invokes ``rcu_dynticks_snap()`` and
+``rcu_dynticks_in_eqs_since()`` (both of which invoke
+an ``atomic_add_return()`` of zero) to detect idle CPUs.
+
++-----------------------------------------------------------------------+
+| **Quick Quiz**:                                                       |
++-----------------------------------------------------------------------+
+| But what about CPUs that remain offline for the entire grace period?  |
++-----------------------------------------------------------------------+
+| **Answer**:                                                           |
++-----------------------------------------------------------------------+
+| Such CPUs will be offline at the beginning of the grace period, so    |
+| the grace period won't expect quiescent states from them. Races       |
+| between grace-period start and CPU-hotplug operations are mediated    |
+| by the CPU's leaf ``rcu_node`` structure's ``->lock`` as described    |
+| above.                                                                |
++-----------------------------------------------------------------------+
+
+The approach must be extended to handle one final case, that of waking a
+task blocked in ``synchronize_rcu()``. This task might be affinitied to
+a CPU that is not yet aware that the grace period has ended, and thus
+might not yet be subject to the grace period's memory ordering.
+Therefore, there is an ``smp_mb()`` after the return from
+``wait_for_completion()`` in the ``synchronize_rcu()`` code path.
+
++-----------------------------------------------------------------------+
+| **Quick Quiz**:                                                       |
++-----------------------------------------------------------------------+
+| What? Where??? I don't see any ``smp_mb()`` after the return from     |
+| ``wait_for_completion()``!!!                                          |
++-----------------------------------------------------------------------+
+| **Answer**:                                                           |
++-----------------------------------------------------------------------+
+| That would be because I spotted the need for that ``smp_mb()`` during |
+| the creation of this documentation, and it is therefore unlikely to   |
+| hit mainline before v4.14. Kudos to Lance Roy, Will Deacon, Peter     |
+| Zijlstra, and Jonathan Cameron for asking questions that sensitized   |
+| me to the rather elaborate sequence of events that demonstrate the    |
+| need for this memory barrier.                                         |
++-----------------------------------------------------------------------+
+
+Tree RCU's grace--period memory-ordering guarantees rely most heavily on
+the ``rcu_node`` structure's ``->lock`` field, so much so that it is
+necessary to abbreviate this pattern in the diagrams in the next
+section. For example, consider the ``rcu_prepare_for_idle()`` function
+shown below, which is one of several functions that enforce ordering of
+newly arrived RCU callbacks against future grace periods:
+
+::
+
+    1 static void rcu_prepare_for_idle(void)
+    2 {
+    3   bool needwake;
+    4   struct rcu_data *rdp;
+    5   struct rcu_dynticks *rdtp = this_cpu_ptr(&rcu_dynticks);
+    6   struct rcu_node *rnp;
+    7   struct rcu_state *rsp;
+    8   int tne;
+    9
+   10   if (IS_ENABLED(CONFIG_RCU_NOCB_CPU_ALL) ||
+   11       rcu_is_nocb_cpu(smp_processor_id()))
+   12     return;
+   13   tne = READ_ONCE(tick_nohz_active);
+   14   if (tne != rdtp->tick_nohz_enabled_snap) {
+   15     if (rcu_cpu_has_callbacks(NULL))
+   16       invoke_rcu_core();
+   17     rdtp->tick_nohz_enabled_snap = tne;
+   18     return;
+   19   }
+   20   if (!tne)
+   21     return;
+   22   if (rdtp->all_lazy &&
+   23       rdtp->nonlazy_posted != rdtp->nonlazy_posted_snap) {
+   24     rdtp->all_lazy = false;
+   25     rdtp->nonlazy_posted_snap = rdtp->nonlazy_posted;
+   26     invoke_rcu_core();
+   27     return;
+   28   }
+   29   if (rdtp->last_accelerate == jiffies)
+   30     return;
+   31   rdtp->last_accelerate = jiffies;
+   32   for_each_rcu_flavor(rsp) {
+   33     rdp = this_cpu_ptr(rsp->rda);
+   34     if (rcu_segcblist_pend_cbs(&rdp->cblist))
+   35       continue;
+   36     rnp = rdp->mynode;
+   37     raw_spin_lock_rcu_node(rnp);
+   38     needwake = rcu_accelerate_cbs(rsp, rnp, rdp);
+   39     raw_spin_unlock_rcu_node(rnp);
+   40     if (needwake)
+   41       rcu_gp_kthread_wake(rsp);
+   42   }
+   43 }
+
+But the only part of ``rcu_prepare_for_idle()`` that really matters for
+this discussion are lines 37–39. We will therefore abbreviate this
+function as follows:
+
+.. kernel-figure:: rcu_node-lock.svg
+
+The box represents the ``rcu_node`` structure's ``->lock`` critical
+section, with the double line on top representing the additional
+``smp_mb__after_unlock_lock()``.
+
+Tree RCU Grace Period Memory Ordering Components
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+Tree RCU's grace-period memory-ordering guarantee is provided by a
+number of RCU components:
+
+#. `Callback Registry`_
+#. `Grace-Period Initialization`_
+#. `Self-Reported Quiescent States`_
+#. `Dynamic Tick Interface`_
+#. `CPU-Hotplug Interface`_
+#. `Forcing Quiescent States`_
+#. `Grace-Period Cleanup`_
+#. `Callback Invocation`_
+
+Each of the following section looks at the corresponding component in
+detail.
+
+Callback Registry
+^^^^^^^^^^^^^^^^^
+
+If RCU's grace-period guarantee is to mean anything at all, any access
+that happens before a given invocation of ``call_rcu()`` must also
+happen before the corresponding grace period. The implementation of this
+portion of RCU's grace period guarantee is shown in the following
+figure:
+
+.. kernel-figure:: TreeRCU-callback-registry.svg
+
+Because ``call_rcu()`` normally acts only on CPU-local state, it
+provides no ordering guarantees, either for itself or for phase one of
+the update (which again will usually be removal of an element from an
+RCU-protected data structure). It simply enqueues the ``rcu_head``
+structure on a per-CPU list, which cannot become associated with a grace
+period until a later call to ``rcu_accelerate_cbs()``, as shown in the
+diagram above.
+
+One set of code paths shown on the left invokes ``rcu_accelerate_cbs()``
+via ``note_gp_changes()``, either directly from ``call_rcu()`` (if the
+current CPU is inundated with queued ``rcu_head`` structures) or more
+likely from an ``RCU_SOFTIRQ`` handler. Another code path in the middle
+is taken only in kernels built with ``CONFIG_RCU_FAST_NO_HZ=y``, which
+invokes ``rcu_accelerate_cbs()`` via ``rcu_prepare_for_idle()``. The
+final code path on the right is taken only in kernels built with
+``CONFIG_HOTPLUG_CPU=y``, which invokes ``rcu_accelerate_cbs()`` via
+``rcu_advance_cbs()``, ``rcu_migrate_callbacks``,
+``rcutree_migrate_callbacks()``, and ``takedown_cpu()``, which in turn
+is invoked on a surviving CPU after the outgoing CPU has been completely
+offlined.
+
+There are a few other code paths within grace-period processing that
+opportunistically invoke ``rcu_accelerate_cbs()``. However, either way,
+all of the CPU's recently queued ``rcu_head`` structures are associated
+with a future grace-period number under the protection of the CPU's lead
+``rcu_node`` structure's ``->lock``. In all cases, there is full
+ordering against any prior critical section for that same ``rcu_node``
+structure's ``->lock``, and also full ordering against any of the
+current task's or CPU's prior critical sections for any ``rcu_node``
+structure's ``->lock``.
+
+The next section will show how this ordering ensures that any accesses
+prior to the ``call_rcu()`` (particularly including phase one of the
+update) happen before the start of the corresponding grace period.
+
++-----------------------------------------------------------------------+
+| **Quick Quiz**:                                                       |
++-----------------------------------------------------------------------+
+| But what about ``synchronize_rcu()``?                                 |
++-----------------------------------------------------------------------+
+| **Answer**:                                                           |
++-----------------------------------------------------------------------+
+| The ``synchronize_rcu()`` passes ``call_rcu()`` to ``wait_rcu_gp()``, |
+| which invokes it. So either way, it eventually comes down to          |
+| ``call_rcu()``.                                                       |
++-----------------------------------------------------------------------+
+
+Grace-Period Initialization
+^^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+Grace-period initialization is carried out by the grace-period kernel
+thread, which makes several passes over the ``rcu_node`` tree within the
+``rcu_gp_init()`` function. This means that showing the full flow of
+ordering through the grace-period computation will require duplicating
+this tree. If you find this confusing, please note that the state of the
+``rcu_node`` changes over time, just like Heraclitus's river. However,
+to keep the ``rcu_node`` river tractable, the grace-period kernel
+thread's traversals are presented in multiple parts, starting in this
+section with the various phases of grace-period initialization.
+
+The first ordering-related grace-period initialization action is to
+advance the ``rcu_state`` structure's ``->gp_seq`` grace-period-number
+counter, as shown below:
+
+.. kernel-figure:: TreeRCU-gp-init-1.svg
+
+The actual increment is carried out using ``smp_store_release()``, which
+helps reject false-positive RCU CPU stall detection. Note that only the
+root ``rcu_node`` structure is touched.
+
+The first pass through the ``rcu_node`` tree updates bitmasks based on
+CPUs having come online or gone offline since the start of the previous
+grace period. In the common case where the number of online CPUs for
+this ``rcu_node`` structure has not transitioned to or from zero, this
+pass will scan only the leaf ``rcu_node`` structures. However, if the
+number of online CPUs for a given leaf ``rcu_node`` structure has
+transitioned from zero, ``rcu_init_new_rnp()`` will be invoked for the
+first incoming CPU. Similarly, if the number of online CPUs for a given
+leaf ``rcu_node`` structure has transitioned to zero,
+``rcu_cleanup_dead_rnp()`` will be invoked for the last outgoing CPU.
+The diagram below shows the path of ordering if the leftmost
+``rcu_node`` structure onlines its first CPU and if the next
+``rcu_node`` structure has no online CPUs (or, alternatively if the
+leftmost ``rcu_node`` structure offlines its last CPU and if the next
+``rcu_node`` structure has no online CPUs).
+
+.. kernel-figure:: TreeRCU-gp-init-1.svg
+
+The final ``rcu_gp_init()`` pass through the ``rcu_node`` tree traverses
+breadth-first, setting each ``rcu_node`` structure's ``->gp_seq`` field
+to the newly advanced value from the ``rcu_state`` structure, as shown
+in the following diagram.
+
+.. kernel-figure:: TreeRCU-gp-init-1.svg
+
+This change will also cause each CPU's next call to
+``__note_gp_changes()`` to notice that a new grace period has started,
+as described in the next section. But because the grace-period kthread
+started the grace period at the root (with the advancing of the
+``rcu_state`` structure's ``->gp_seq`` field) before setting each leaf
+``rcu_node`` structure's ``->gp_seq`` field, each CPU's observation of
+the start of the grace period will happen after the actual start of the
+grace period.
+
++-----------------------------------------------------------------------+
+| **Quick Quiz**:                                                       |
++-----------------------------------------------------------------------+
+| But what about the CPU that started the grace period? Why wouldn't it |
+| see the start of the grace period right when it started that grace    |
+| period?                                                               |
++-----------------------------------------------------------------------+
+| **Answer**:                                                           |
++-----------------------------------------------------------------------+
+| In some deep philosophical and overly anthromorphized sense, yes, the |
+| CPU starting the grace period is immediately aware of having done so. |
+| However, if we instead assume that RCU is not self-aware, then even   |
+| the CPU starting the grace period does not really become aware of the |
+| start of this grace period until its first call to                    |
+| ``__note_gp_changes()``. On the other hand, this CPU potentially gets |
+| early notification because it invokes ``__note_gp_changes()`` during  |
+| its last ``rcu_gp_init()`` pass through its leaf ``rcu_node``         |
+| structure.                                                            |
++-----------------------------------------------------------------------+
+
+Self-Reported Quiescent States
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+When all entities that might block the grace period have reported
+quiescent states (or as described in a later section, had quiescent
+states reported on their behalf), the grace period can end. Online
+non-idle CPUs report their own quiescent states, as shown in the
+following diagram:
+
+.. kernel-figure:: TreeRCU-qs.svg
+
+This is for the last CPU to report a quiescent state, which signals the
+end of the grace period. Earlier quiescent states would push up the
+``rcu_node`` tree only until they encountered an ``rcu_node`` structure
+that is waiting for additional quiescent states. However, ordering is
+nevertheless preserved because some later quiescent state will acquire
+that ``rcu_node`` structure's ``->lock``.
+
+Any number of events can lead up to a CPU invoking ``note_gp_changes``
+(or alternatively, directly invoking ``__note_gp_changes()``), at which
+point that CPU will notice the start of a new grace period while holding
+its leaf ``rcu_node`` lock. Therefore, all execution shown in this
+diagram happens after the start of the grace period. In addition, this
+CPU will consider any RCU read-side critical section that started before
+the invocation of ``__note_gp_changes()`` to have started before the
+grace period, and thus a critical section that the grace period must
+wait on.
+
++-----------------------------------------------------------------------+
+| **Quick Quiz**:                                                       |
++-----------------------------------------------------------------------+
+| But a RCU read-side critical section might have started after the     |
+| beginning of the grace period (the advancing of ``->gp_seq`` from     |
+| earlier), so why should the grace period wait on such a critical      |
+| section?                                                              |
++-----------------------------------------------------------------------+
+| **Answer**:                                                           |
++-----------------------------------------------------------------------+
+| It is indeed not necessary for the grace period to wait on such a     |
+| critical section. However, it is permissible to wait on it. And it is |
+| furthermore important to wait on it, as this lazy approach is far     |
+| more scalable than a “big bang” all-at-once grace-period start could  |
+| possibly be.                                                          |
++-----------------------------------------------------------------------+
+
+If the CPU does a context switch, a quiescent state will be noted by
+``rcu_note_context_switch()`` on the left. On the other hand, if the CPU
+takes a scheduler-clock interrupt while executing in usermode, a
+quiescent state will be noted by ``rcu_sched_clock_irq()`` on the right.
+Either way, the passage through a quiescent state will be noted in a
+per-CPU variable.
+
+The next time an ``RCU_SOFTIRQ`` handler executes on this CPU (for
+example, after the next scheduler-clock interrupt), ``rcu_core()`` will
+invoke ``rcu_check_quiescent_state()``, which will notice the recorded
+quiescent state, and invoke ``rcu_report_qs_rdp()``. If
+``rcu_report_qs_rdp()`` verifies that the quiescent state really does
+apply to the current grace period, it invokes ``rcu_report_rnp()`` which
+traverses up the ``rcu_node`` tree as shown at the bottom of the
+diagram, clearing bits from each ``rcu_node`` structure's ``->qsmask``
+field, and propagating up the tree when the result is zero.
+
+Note that traversal passes upwards out of a given ``rcu_node`` structure
+only if the current CPU is reporting the last quiescent state for the
+subtree headed by that ``rcu_node`` structure. A key point is that if a
+CPU's traversal stops at a given ``rcu_node`` structure, then there will
+be a later traversal by another CPU (or perhaps the same one) that
+proceeds upwards from that point, and the ``rcu_node`` ``->lock``
+guarantees that the first CPU's quiescent state happens before the
+remainder of the second CPU's traversal. Applying this line of thought
+repeatedly shows that all CPUs' quiescent states happen before the last
+CPU traverses through the root ``rcu_node`` structure, the “last CPU”
+being the one that clears the last bit in the root ``rcu_node``
+structure's ``->qsmask`` field.
+
+Dynamic Tick Interface
+^^^^^^^^^^^^^^^^^^^^^^
+
+Due to energy-efficiency considerations, RCU is forbidden from
+disturbing idle CPUs. CPUs are therefore required to notify RCU when
+entering or leaving idle state, which they do via fully ordered
+value-returning atomic operations on a per-CPU variable. The ordering
+effects are as shown below:
+
+.. kernel-figure:: TreeRCU-dyntick.svg
+
+The RCU grace-period kernel thread samples the per-CPU idleness variable
+while holding the corresponding CPU's leaf ``rcu_node`` structure's
+``->lock``. This means that any RCU read-side critical sections that
+precede the idle period (the oval near the top of the diagram above)
+will happen before the end of the current grace period. Similarly, the
+beginning of the current grace period will happen before any RCU
+read-side critical sections that follow the idle period (the oval near
+the bottom of the diagram above).
+
+Plumbing this into the full grace-period execution is described
+`below <#Forcing%20Quiescent%20States>`__.
+
+CPU-Hotplug Interface
+^^^^^^^^^^^^^^^^^^^^^
+
+RCU is also forbidden from disturbing offline CPUs, which might well be
+powered off and removed from the system completely. CPUs are therefore
+required to notify RCU of their comings and goings as part of the
+corresponding CPU hotplug operations. The ordering effects are shown
+below:
+
+.. kernel-figure:: TreeRCU-hotplug.svg
+
+Because CPU hotplug operations are much less frequent than idle
+transitions, they are heavier weight, and thus acquire the CPU's leaf
+``rcu_node`` structure's ``->lock`` and update this structure's
+``->qsmaskinitnext``. The RCU grace-period kernel thread samples this
+mask to detect CPUs having gone offline since the beginning of this
+grace period.
+
+Plumbing this into the full grace-period execution is described
+`below <#Forcing%20Quiescent%20States>`__.
+
+Forcing Quiescent States
+^^^^^^^^^^^^^^^^^^^^^^^^
+
+As noted above, idle and offline CPUs cannot report their own quiescent
+states, and therefore the grace-period kernel thread must do the
+reporting on their behalf. This process is called “forcing quiescent
+states”, it is repeated every few jiffies, and its ordering effects are
+shown below:
+
+.. kernel-figure:: TreeRCU-gp-fqs.svg
+
+Each pass of quiescent state forcing is guaranteed to traverse the leaf
+``rcu_node`` structures, and if there are no new quiescent states due to
+recently idled and/or offlined CPUs, then only the leaves are traversed.
+However, if there is a newly offlined CPU as illustrated on the left or
+a newly idled CPU as illustrated on the right, the corresponding
+quiescent state will be driven up towards the root. As with
+self-reported quiescent states, the upwards driving stops once it
+reaches an ``rcu_node`` structure that has quiescent states outstanding
+from other CPUs.
+
++-----------------------------------------------------------------------+
+| **Quick Quiz**:                                                       |
++-----------------------------------------------------------------------+
+| The leftmost drive to root stopped before it reached the root         |
+| ``rcu_node`` structure, which means that there are still CPUs         |
+| subordinate to that structure on which the current grace period is    |
+| waiting. Given that, how is it possible that the rightmost drive to   |
+| root ended the grace period?                                          |
++-----------------------------------------------------------------------+
+| **Answer**:                                                           |
++-----------------------------------------------------------------------+
+| Good analysis! It is in fact impossible in the absence of bugs in     |
+| RCU. But this diagram is complex enough as it is, so simplicity       |
+| overrode accuracy. You can think of it as poetic license, or you can  |
+| think of it as misdirection that is resolved in the                   |
+| `stitched-together diagram <#Putting%20It%20All%20Together>`__.       |
++-----------------------------------------------------------------------+
+
+Grace-Period Cleanup
+^^^^^^^^^^^^^^^^^^^^
+
+Grace-period cleanup first scans the ``rcu_node`` tree breadth-first
+advancing all the ``->gp_seq`` fields, then it advances the
+``rcu_state`` structure's ``->gp_seq`` field. The ordering effects are
+shown below:
+
+.. kernel-figure:: TreeRCU-gp-cleanup.svg
+
+As indicated by the oval at the bottom of the diagram, once grace-period
+cleanup is complete, the next grace period can begin.
+
++-----------------------------------------------------------------------+
+| **Quick Quiz**:                                                       |
++-----------------------------------------------------------------------+
+| But when precisely does the grace period end?                         |
++-----------------------------------------------------------------------+
+| **Answer**:                                                           |
++-----------------------------------------------------------------------+
+| There is no useful single point at which the grace period can be said |
+| to end. The earliest reasonable candidate is as soon as the last CPU  |
+| has reported its quiescent state, but it may be some milliseconds     |
+| before RCU becomes aware of this. The latest reasonable candidate is  |
+| once the ``rcu_state`` structure's ``->gp_seq`` field has been        |
+| updated, but it is quite possible that some CPUs have already         |
+| completed phase two of their updates by that time. In short, if you   |
+| are going to work with RCU, you need to learn to embrace uncertainty. |
++-----------------------------------------------------------------------+
+
+Callback Invocation
+^^^^^^^^^^^^^^^^^^^
+
+Once a given CPU's leaf ``rcu_node`` structure's ``->gp_seq`` field has
+been updated, that CPU can begin invoking its RCU callbacks that were
+waiting for this grace period to end. These callbacks are identified by
+``rcu_advance_cbs()``, which is usually invoked by
+``__note_gp_changes()``. As shown in the diagram below, this invocation
+can be triggered by the scheduling-clock interrupt
+(``rcu_sched_clock_irq()`` on the left) or by idle entry
+(``rcu_cleanup_after_idle()`` on the right, but only for kernels build
+with ``CONFIG_RCU_FAST_NO_HZ=y``). Either way, ``RCU_SOFTIRQ`` is
+raised, which results in ``rcu_do_batch()`` invoking the callbacks,
+which in turn allows those callbacks to carry out (either directly or
+indirectly via wakeup) the needed phase-two processing for each update.
+
+.. kernel-figure:: TreeRCU-callback-invocation.svg
+
+Please note that callback invocation can also be prompted by any number
+of corner-case code paths, for example, when a CPU notes that it has
+excessive numbers of callbacks queued. In all cases, the CPU acquires
+its leaf ``rcu_node`` structure's ``->lock`` before invoking callbacks,
+which preserves the required ordering against the newly completed grace
+period.
+
+However, if the callback function communicates to other CPUs, for
+example, doing a wakeup, then it is that function's responsibility to
+maintain ordering. For example, if the callback function wakes up a task
+that runs on some other CPU, proper ordering must in place in both the
+callback function and the task being awakened. To see why this is
+important, consider the top half of the `grace-period
+cleanup <#Grace-Period%20Cleanup>`__ diagram. The callback might be
+running on a CPU corresponding to the leftmost leaf ``rcu_node``
+structure, and awaken a task that is to run on a CPU corresponding to
+the rightmost leaf ``rcu_node`` structure, and the grace-period kernel
+thread might not yet have reached the rightmost leaf. In this case, the
+grace period's memory ordering might not yet have reached that CPU, so
+again the callback function and the awakened task must supply proper
+ordering.
+
+Putting It All Together
+~~~~~~~~~~~~~~~~~~~~~~~
+
+A stitched-together diagram is here:
+
+.. kernel-figure:: TreeRCU-gp.svg
+
+Legal Statement
+~~~~~~~~~~~~~~~
+
+This work represents the view of the author and does not necessarily
+represent the view of IBM.
+
+Linux is a registered trademark of Linus Torvalds.
+
+Other company, product, and service names may be trademarks or service
+marks of others.
diff --git a/Documentation/RCU/Design/Memory-Ordering/TreeRCU-gp.svg b/Documentation/RCU/Design/Memory-Ordering/TreeRCU-gp.svg
index 2bcd742d6e49..069f6f8371c2 100644
--- a/Documentation/RCU/Design/Memory-Ordering/TreeRCU-gp.svg
+++ b/Documentation/RCU/Design/Memory-Ordering/TreeRCU-gp.svg
@@ -3880,7 +3880,7 @@
          font-style="normal"
          y="-4418.6582"
          x="3745.7725"
-         xml:space="preserve">rcu_node_context_switch()</text>
+         xml:space="preserve">rcu_note_context_switch()</text>
     </g>
     <g
        transform="translate(1881.1886,54048.57)"
diff --git a/Documentation/RCU/Design/Memory-Ordering/TreeRCU-qs.svg b/Documentation/RCU/Design/Memory-Ordering/TreeRCU-qs.svg
index 779c9ac31a52..7d6c5f7e505c 100644
--- a/Documentation/RCU/Design/Memory-Ordering/TreeRCU-qs.svg
+++ b/Documentation/RCU/Design/Memory-Ordering/TreeRCU-qs.svg
@@ -753,7 +753,7 @@
          font-style="normal"
          y="-4418.6582"
          x="3745.7725"
-         xml:space="preserve">rcu_node_context_switch()</text>
+         xml:space="preserve">rcu_note_context_switch()</text>
     </g>
     <g
        transform="translate(3131.2648,-585.6713)"
diff --git a/Documentation/RCU/Design/Requirements/Requirements.html b/Documentation/RCU/Design/Requirements/Requirements.html
deleted file mode 100644
index 467251f7fef6..000000000000
--- a/Documentation/RCU/Design/Requirements/Requirements.html
+++ /dev/null
@@ -1,3401 +0,0 @@
-<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN"
-        "http://www.w3.org/TR/html4/loose.dtd">
-        <html>
-        <head><title>A Tour Through RCU's Requirements [LWN.net]</title>
-        <meta HTTP-EQUIV="Content-Type" CONTENT="text/html; charset=utf-8">
-
-<h1>A Tour Through RCU's Requirements</h1>
-
-<p>Copyright IBM Corporation, 2015</p>
-<p>Author: Paul E.&nbsp;McKenney</p>
-<p><i>The initial version of this document appeared in the
-<a href="https://lwn.net/">LWN</a> articles
-<a href="https://lwn.net/Articles/652156/">here</a>,
-<a href="https://lwn.net/Articles/652677/">here</a>, and
-<a href="https://lwn.net/Articles/653326/">here</a>.</i></p>
-
-<h2>Introduction</h2>
-
-<p>
-Read-copy update (RCU) is a synchronization mechanism that is often
-used as a replacement for reader-writer locking.
-RCU is unusual in that updaters do not block readers,
-which means that RCU's read-side primitives can be exceedingly fast
-and scalable.
-In addition, updaters can make useful forward progress concurrently
-with readers.
-However, all this concurrency between RCU readers and updaters does raise
-the question of exactly what RCU readers are doing, which in turn
-raises the question of exactly what RCU's requirements are.
-
-<p>
-This document therefore summarizes RCU's requirements, and can be thought
-of as an informal, high-level specification for RCU.
-It is important to understand that RCU's specification is primarily
-empirical in nature;
-in fact, I learned about many of these requirements the hard way.
-This situation might cause some consternation, however, not only
-has this learning process been a lot of fun, but it has also been
-a great privilege to work with so many people willing to apply
-technologies in interesting new ways.
-
-<p>
-All that aside, here are the categories of currently known RCU requirements:
-</p>
-
-<ol>
-<li>	<a href="#Fundamental Requirements">
-	Fundamental Requirements</a>
-<li>	<a href="#Fundamental Non-Requirements">Fundamental Non-Requirements</a>
-<li>	<a href="#Parallelism Facts of Life">
-	Parallelism Facts of Life</a>
-<li>	<a href="#Quality-of-Implementation Requirements">
-	Quality-of-Implementation Requirements</a>
-<li>	<a href="#Linux Kernel Complications">
-	Linux Kernel Complications</a>
-<li>	<a href="#Software-Engineering Requirements">
-	Software-Engineering Requirements</a>
-<li>	<a href="#Other RCU Flavors">
-	Other RCU Flavors</a>
-<li>	<a href="#Possible Future Changes">
-	Possible Future Changes</a>
-</ol>
-
-<p>
-This is followed by a <a href="#Summary">summary</a>,
-however, the answers to each quick quiz immediately follows the quiz.
-Select the big white space with your mouse to see the answer.
-
-<h2><a name="Fundamental Requirements">Fundamental Requirements</a></h2>
-
-<p>
-RCU's fundamental requirements are the closest thing RCU has to hard
-mathematical requirements.
-These are:
-
-<ol>
-<li>	<a href="#Grace-Period Guarantee">
-	Grace-Period Guarantee</a>
-<li>	<a href="#Publish-Subscribe Guarantee">
-	Publish-Subscribe Guarantee</a>
-<li>	<a href="#Memory-Barrier Guarantees">
-	Memory-Barrier Guarantees</a>
-<li>	<a href="#RCU Primitives Guaranteed to Execute Unconditionally">
-	RCU Primitives Guaranteed to Execute Unconditionally</a>
-<li>	<a href="#Guaranteed Read-to-Write Upgrade">
-	Guaranteed Read-to-Write Upgrade</a>
-</ol>
-
-<h3><a name="Grace-Period Guarantee">Grace-Period Guarantee</a></h3>
-
-<p>
-RCU's grace-period guarantee is unusual in being premeditated:
-Jack Slingwine and I had this guarantee firmly in mind when we started
-work on RCU (then called &ldquo;rclock&rdquo;) in the early 1990s.
-That said, the past two decades of experience with RCU have produced
-a much more detailed understanding of this guarantee.
-
-<p>
-RCU's grace-period guarantee allows updaters to wait for the completion
-of all pre-existing RCU read-side critical sections.
-An RCU read-side critical section
-begins with the marker <tt>rcu_read_lock()</tt> and ends with
-the marker <tt>rcu_read_unlock()</tt>.
-These markers may be nested, and RCU treats a nested set as one
-big RCU read-side critical section.
-Production-quality implementations of <tt>rcu_read_lock()</tt> and
-<tt>rcu_read_unlock()</tt> are extremely lightweight, and in
-fact have exactly zero overhead in Linux kernels built for production
-use with <tt>CONFIG_PREEMPT=n</tt>.
-
-<p>
-This guarantee allows ordering to be enforced with extremely low
-overhead to readers, for example:
-
-<blockquote>
-<pre>
- 1 int x, y;
- 2
- 3 void thread0(void)
- 4 {
- 5   rcu_read_lock();
- 6   r1 = READ_ONCE(x);
- 7   r2 = READ_ONCE(y);
- 8   rcu_read_unlock();
- 9 }
-10
-11 void thread1(void)
-12 {
-13   WRITE_ONCE(x, 1);
-14   synchronize_rcu();
-15   WRITE_ONCE(y, 1);
-16 }
-</pre>
-</blockquote>
-
-<p>
-Because the <tt>synchronize_rcu()</tt> on line&nbsp;14 waits for
-all pre-existing readers, any instance of <tt>thread0()</tt> that
-loads a value of zero from <tt>x</tt> must complete before
-<tt>thread1()</tt> stores to <tt>y</tt>, so that instance must
-also load a value of zero from <tt>y</tt>.
-Similarly, any instance of <tt>thread0()</tt> that loads a value of
-one from <tt>y</tt> must have started after the
-<tt>synchronize_rcu()</tt> started, and must therefore also load
-a value of one from <tt>x</tt>.
-Therefore, the outcome:
-<blockquote>
-<pre>
-(r1 == 0 &amp;&amp; r2 == 1)
-</pre>
-</blockquote>
-cannot happen.
-
-<table>
-<tr><th>&nbsp;</th></tr>
-<tr><th align="left">Quick Quiz:</th></tr>
-<tr><td>
-	Wait a minute!
-	You said that updaters can make useful forward progress concurrently
-	with readers, but pre-existing readers will block
-	<tt>synchronize_rcu()</tt>!!!
-	Just who are you trying to fool???
-</td></tr>
-<tr><th align="left">Answer:</th></tr>
-<tr><td bgcolor="#ffffff"><font color="ffffff">
-	First, if updaters do not wish to be blocked by readers, they can use
-	<tt>call_rcu()</tt> or <tt>kfree_rcu()</tt>, which will
-	be discussed later.
-	Second, even when using <tt>synchronize_rcu()</tt>, the other
-	update-side code does run concurrently with readers, whether
-	pre-existing or not.
-</font></td></tr>
-<tr><td>&nbsp;</td></tr>
-</table>
-
-<p>
-This scenario resembles one of the first uses of RCU in
-<a href="https://en.wikipedia.org/wiki/DYNIX">DYNIX/ptx</a>,
-which managed a distributed lock manager's transition into
-a state suitable for handling recovery from node failure,
-more or less as follows:
-
-<blockquote>
-<pre>
- 1 #define STATE_NORMAL        0
- 2 #define STATE_WANT_RECOVERY 1
- 3 #define STATE_RECOVERING    2
- 4 #define STATE_WANT_NORMAL   3
- 5
- 6 int state = STATE_NORMAL;
- 7
- 8 void do_something_dlm(void)
- 9 {
-10   int state_snap;
-11
-12   rcu_read_lock();
-13   state_snap = READ_ONCE(state);
-14   if (state_snap == STATE_NORMAL)
-15     do_something();
-16   else
-17     do_something_carefully();
-18   rcu_read_unlock();
-19 }
-20
-21 void start_recovery(void)
-22 {
-23   WRITE_ONCE(state, STATE_WANT_RECOVERY);
-24   synchronize_rcu();
-25   WRITE_ONCE(state, STATE_RECOVERING);
-26   recovery();
-27   WRITE_ONCE(state, STATE_WANT_NORMAL);
-28   synchronize_rcu();
-29   WRITE_ONCE(state, STATE_NORMAL);
-30 }
-</pre>
-</blockquote>
-
-<p>
-The RCU read-side critical section in <tt>do_something_dlm()</tt>
-works with the <tt>synchronize_rcu()</tt> in <tt>start_recovery()</tt>
-to guarantee that <tt>do_something()</tt> never runs concurrently
-with <tt>recovery()</tt>, but with little or no synchronization
-overhead in <tt>do_something_dlm()</tt>.
-
-<table>
-<tr><th>&nbsp;</th></tr>
-<tr><th align="left">Quick Quiz:</th></tr>
-<tr><td>
-	Why is the <tt>synchronize_rcu()</tt> on line&nbsp;28 needed?
-</td></tr>
-<tr><th align="left">Answer:</th></tr>
-<tr><td bgcolor="#ffffff"><font color="ffffff">
-	Without that extra grace period, memory reordering could result in
-	<tt>do_something_dlm()</tt> executing <tt>do_something()</tt>
-	concurrently with the last bits of <tt>recovery()</tt>.
-</font></td></tr>
-<tr><td>&nbsp;</td></tr>
-</table>
-
-<p>
-In order to avoid fatal problems such as deadlocks,
-an RCU read-side critical section must not contain calls to
-<tt>synchronize_rcu()</tt>.
-Similarly, an RCU read-side critical section must not
-contain anything that waits, directly or indirectly, on completion of
-an invocation of <tt>synchronize_rcu()</tt>.
-
-<p>
-Although RCU's grace-period guarantee is useful in and of itself, with
-<a href="https://lwn.net/Articles/573497/">quite a few use cases</a>,
-it would be good to be able to use RCU to coordinate read-side
-access to linked data structures.
-For this, the grace-period guarantee is not sufficient, as can
-be seen in function <tt>add_gp_buggy()</tt> below.
-We will look at the reader's code later, but in the meantime, just think of
-the reader as locklessly picking up the <tt>gp</tt> pointer,
-and, if the value loaded is non-<tt>NULL</tt>, locklessly accessing the
-<tt>-&gt;a</tt> and <tt>-&gt;b</tt> fields.
-
-<blockquote>
-<pre>
- 1 bool add_gp_buggy(int a, int b)
- 2 {
- 3   p = kmalloc(sizeof(*p), GFP_KERNEL);
- 4   if (!p)
- 5     return -ENOMEM;
- 6   spin_lock(&amp;gp_lock);
- 7   if (rcu_access_pointer(gp)) {
- 8     spin_unlock(&amp;gp_lock);
- 9     return false;
-10   }
-11   p-&gt;a = a;
-12   p-&gt;b = a;
-13   gp = p; /* ORDERING BUG */
-14   spin_unlock(&amp;gp_lock);
-15   return true;
-16 }
-</pre>
-</blockquote>
-
-<p>
-The problem is that both the compiler and weakly ordered CPUs are within
-their rights to reorder this code as follows:
-
-<blockquote>
-<pre>
- 1 bool add_gp_buggy_optimized(int a, int b)
- 2 {
- 3   p = kmalloc(sizeof(*p), GFP_KERNEL);
- 4   if (!p)
- 5     return -ENOMEM;
- 6   spin_lock(&amp;gp_lock);
- 7   if (rcu_access_pointer(gp)) {
- 8     spin_unlock(&amp;gp_lock);
- 9     return false;
-10   }
-<b>11   gp = p; /* ORDERING BUG */
-12   p-&gt;a = a;
-13   p-&gt;b = a;</b>
-14   spin_unlock(&amp;gp_lock);
-15   return true;
-16 }
-</pre>
-</blockquote>
-
-<p>
-If an RCU reader fetches <tt>gp</tt> just after
-<tt>add_gp_buggy_optimized</tt> executes line&nbsp;11,
-it will see garbage in the <tt>-&gt;a</tt> and <tt>-&gt;b</tt>
-fields.
-And this is but one of many ways in which compiler and hardware optimizations
-could cause trouble.
-Therefore, we clearly need some way to prevent the compiler and the CPU from
-reordering in this manner, which brings us to the publish-subscribe
-guarantee discussed in the next section.
-
-<h3><a name="Publish-Subscribe Guarantee">Publish/Subscribe Guarantee</a></h3>
-
-<p>
-RCU's publish-subscribe guarantee allows data to be inserted
-into a linked data structure without disrupting RCU readers.
-The updater uses <tt>rcu_assign_pointer()</tt> to insert the
-new data, and readers use <tt>rcu_dereference()</tt> to
-access data, whether new or old.
-The following shows an example of insertion:
-
-<blockquote>
-<pre>
- 1 bool add_gp(int a, int b)
- 2 {
- 3   p = kmalloc(sizeof(*p), GFP_KERNEL);
- 4   if (!p)
- 5     return -ENOMEM;
- 6   spin_lock(&amp;gp_lock);
- 7   if (rcu_access_pointer(gp)) {
- 8     spin_unlock(&amp;gp_lock);
- 9     return false;
-10   }
-11   p-&gt;a = a;
-12   p-&gt;b = a;
-13   rcu_assign_pointer(gp, p);
-14   spin_unlock(&amp;gp_lock);
-15   return true;
-16 }
-</pre>
-</blockquote>
-
-<p>
-The <tt>rcu_assign_pointer()</tt> on line&nbsp;13 is conceptually
-equivalent to a simple assignment statement, but also guarantees
-that its assignment will
-happen after the two assignments in lines&nbsp;11 and&nbsp;12,
-similar to the C11 <tt>memory_order_release</tt> store operation.
-It also prevents any number of &ldquo;interesting&rdquo; compiler
-optimizations, for example, the use of <tt>gp</tt> as a scratch
-location immediately preceding the assignment.
-
-<table>
-<tr><th>&nbsp;</th></tr>
-<tr><th align="left">Quick Quiz:</th></tr>
-<tr><td>
-	But <tt>rcu_assign_pointer()</tt> does nothing to prevent the
-	two assignments to <tt>p-&gt;a</tt> and <tt>p-&gt;b</tt>
-	from being reordered.
-	Can't that also cause problems?
-</td></tr>
-<tr><th align="left">Answer:</th></tr>
-<tr><td bgcolor="#ffffff"><font color="ffffff">
-	No, it cannot.
-	The readers cannot see either of these two fields until
-	the assignment to <tt>gp</tt>, by which time both fields are
-	fully initialized.
-	So reordering the assignments
-	to <tt>p-&gt;a</tt> and <tt>p-&gt;b</tt> cannot possibly
-	cause any problems.
-</font></td></tr>
-<tr><td>&nbsp;</td></tr>
-</table>
-
-<p>
-It is tempting to assume that the reader need not do anything special
-to control its accesses to the RCU-protected data,
-as shown in <tt>do_something_gp_buggy()</tt> below:
-
-<blockquote>
-<pre>
- 1 bool do_something_gp_buggy(void)
- 2 {
- 3   rcu_read_lock();
- 4   p = gp;  /* OPTIMIZATIONS GALORE!!! */
- 5   if (p) {
- 6     do_something(p-&gt;a, p-&gt;b);
- 7     rcu_read_unlock();
- 8     return true;
- 9   }
-10   rcu_read_unlock();
-11   return false;
-12 }
-</pre>
-</blockquote>
-
-<p>
-However, this temptation must be resisted because there are a
-surprisingly large number of ways that the compiler
-(to say nothing of
-<a href="https://h71000.www7.hp.com/wizard/wiz_2637.html">DEC Alpha CPUs</a>)
-can trip this code up.
-For but one example, if the compiler were short of registers, it
-might choose to refetch from <tt>gp</tt> rather than keeping
-a separate copy in <tt>p</tt> as follows:
-
-<blockquote>
-<pre>
- 1 bool do_something_gp_buggy_optimized(void)
- 2 {
- 3   rcu_read_lock();
- 4   if (gp) { /* OPTIMIZATIONS GALORE!!! */
-<b> 5     do_something(gp-&gt;a, gp-&gt;b);</b>
- 6     rcu_read_unlock();
- 7     return true;
- 8   }
- 9   rcu_read_unlock();
-10   return false;
-11 }
-</pre>
-</blockquote>
-
-<p>
-If this function ran concurrently with a series of updates that
-replaced the current structure with a new one,
-the fetches of <tt>gp-&gt;a</tt>
-and <tt>gp-&gt;b</tt> might well come from two different structures,
-which could cause serious confusion.
-To prevent this (and much else besides), <tt>do_something_gp()</tt> uses
-<tt>rcu_dereference()</tt> to fetch from <tt>gp</tt>:
-
-<blockquote>
-<pre>
- 1 bool do_something_gp(void)
- 2 {
- 3   rcu_read_lock();
- 4   p = rcu_dereference(gp);
- 5   if (p) {
- 6     do_something(p-&gt;a, p-&gt;b);
- 7     rcu_read_unlock();
- 8     return true;
- 9   }
-10   rcu_read_unlock();
-11   return false;
-12 }
-</pre>
-</blockquote>
-
-<p>
-The <tt>rcu_dereference()</tt> uses volatile casts and (for DEC Alpha)
-memory barriers in the Linux kernel.
-Should a
-<a href="http://www.rdrop.com/users/paulmck/RCU/consume.2015.07.13a.pdf">high-quality implementation of C11 <tt>memory_order_consume</tt> [PDF]</a>
-ever appear, then <tt>rcu_dereference()</tt> could be implemented
-as a <tt>memory_order_consume</tt> load.
-Regardless of the exact implementation, a pointer fetched by
-<tt>rcu_dereference()</tt> may not be used outside of the
-outermost RCU read-side critical section containing that
-<tt>rcu_dereference()</tt>, unless protection of
-the corresponding data element has been passed from RCU to some
-other synchronization mechanism, most commonly locking or
-<a href="https://www.kernel.org/doc/Documentation/RCU/rcuref.txt">reference counting</a>.
-
-<p>
-In short, updaters use <tt>rcu_assign_pointer()</tt> and readers
-use <tt>rcu_dereference()</tt>, and these two RCU API elements
-work together to ensure that readers have a consistent view of
-newly added data elements.
-
-<p>
-Of course, it is also necessary to remove elements from RCU-protected
-data structures, for example, using the following process:
-
-<ol>
-<li>	Remove the data element from the enclosing structure.
-<li>	Wait for all pre-existing RCU read-side critical sections
-	to complete (because only pre-existing readers can possibly have
-	a reference to the newly removed data element).
-<li>	At this point, only the updater has a reference to the
-	newly removed data element, so it can safely reclaim
-	the data element, for example, by passing it to <tt>kfree()</tt>.
-</ol>
-
-This process is implemented by <tt>remove_gp_synchronous()</tt>:
-
-<blockquote>
-<pre>
- 1 bool remove_gp_synchronous(void)
- 2 {
- 3   struct foo *p;
- 4
- 5   spin_lock(&amp;gp_lock);
- 6   p = rcu_access_pointer(gp);
- 7   if (!p) {
- 8     spin_unlock(&amp;gp_lock);
- 9     return false;
-10   }
-11   rcu_assign_pointer(gp, NULL);
-12   spin_unlock(&amp;gp_lock);
-13   synchronize_rcu();
-14   kfree(p);
-15   return true;
-16 }
-</pre>
-</blockquote>
-
-<p>
-This function is straightforward, with line&nbsp;13 waiting for a grace
-period before line&nbsp;14 frees the old data element.
-This waiting ensures that readers will reach line&nbsp;7 of
-<tt>do_something_gp()</tt> before the data element referenced by
-<tt>p</tt> is freed.
-The <tt>rcu_access_pointer()</tt> on line&nbsp;6 is similar to
-<tt>rcu_dereference()</tt>, except that:
-
-<ol>
-<li>	The value returned by <tt>rcu_access_pointer()</tt>
-	cannot be dereferenced.
-	If you want to access the value pointed to as well as
-	the pointer itself, use <tt>rcu_dereference()</tt>
-	instead of <tt>rcu_access_pointer()</tt>.
-<li>	The call to <tt>rcu_access_pointer()</tt> need not be
-	protected.
-	In contrast, <tt>rcu_dereference()</tt> must either be
-	within an RCU read-side critical section or in a code
-	segment where the pointer cannot change, for example, in
-	code protected by the corresponding update-side lock.
-</ol>
-
-<table>
-<tr><th>&nbsp;</th></tr>
-<tr><th align="left">Quick Quiz:</th></tr>
-<tr><td>
-	Without the <tt>rcu_dereference()</tt> or the
-	<tt>rcu_access_pointer()</tt>, what destructive optimizations
-	might the compiler make use of?
-</td></tr>
-<tr><th align="left">Answer:</th></tr>
-<tr><td bgcolor="#ffffff"><font color="ffffff">
-	Let's start with what happens to <tt>do_something_gp()</tt>
-	if it fails to use <tt>rcu_dereference()</tt>.
-	It could reuse a value formerly fetched from this same pointer.
-	It could also fetch the pointer from <tt>gp</tt> in a byte-at-a-time
-	manner, resulting in <i>load tearing</i>, in turn resulting a bytewise
-	mash-up of two distinct pointer values.
-	It might even use value-speculation optimizations, where it makes
-	a wrong guess, but by the time it gets around to checking the
-	value, an update has changed the pointer to match the wrong guess.
-	Too bad about any dereferences that returned pre-initialization garbage
-	in the meantime!
-	</font>
-
-	<p><font color="ffffff">
-	For <tt>remove_gp_synchronous()</tt>, as long as all modifications
-	to <tt>gp</tt> are carried out while holding <tt>gp_lock</tt>,
-	the above optimizations are harmless.
-	However, <tt>sparse</tt> will complain if you
-	define <tt>gp</tt> with <tt>__rcu</tt> and then
-	access it without using
-	either <tt>rcu_access_pointer()</tt> or <tt>rcu_dereference()</tt>.
-</font></td></tr>
-<tr><td>&nbsp;</td></tr>
-</table>
-
-<p>
-In short, RCU's publish-subscribe guarantee is provided by the combination
-of <tt>rcu_assign_pointer()</tt> and <tt>rcu_dereference()</tt>.
-This guarantee allows data elements to be safely added to RCU-protected
-linked data structures without disrupting RCU readers.
-This guarantee can be used in combination with the grace-period
-guarantee to also allow data elements to be removed from RCU-protected
-linked data structures, again without disrupting RCU readers.
-
-<p>
-This guarantee was only partially premeditated.
-DYNIX/ptx used an explicit memory barrier for publication, but had nothing
-resembling <tt>rcu_dereference()</tt> for subscription, nor did it
-have anything resembling the <tt>smp_read_barrier_depends()</tt>
-that was later subsumed into <tt>rcu_dereference()</tt> and later
-still into <tt>READ_ONCE()</tt>.
-The need for these operations made itself known quite suddenly at a
-late-1990s meeting with the DEC Alpha architects, back in the days when
-DEC was still a free-standing company.
-It took the Alpha architects a good hour to convince me that any sort
-of barrier would ever be needed, and it then took me a good <i>two</i> hours
-to convince them that their documentation did not make this point clear.
-More recent work with the C and C++ standards committees have provided
-much education on tricks and traps from the compiler.
-In short, compilers were much less tricky in the early 1990s, but in
-2015, don't even think about omitting <tt>rcu_dereference()</tt>!
-
-<h3><a name="Memory-Barrier Guarantees">Memory-Barrier Guarantees</a></h3>
-
-<p>
-The previous section's simple linked-data-structure scenario clearly
-demonstrates the need for RCU's stringent memory-ordering guarantees on
-systems with more than one CPU:
-
-<ol>
-<li>	Each CPU that has an RCU read-side critical section that
-	begins before <tt>synchronize_rcu()</tt> starts is
-	guaranteed to execute a full memory barrier between the time
-	that the RCU read-side critical section ends and the time that
-	<tt>synchronize_rcu()</tt> returns.
-	Without this guarantee, a pre-existing RCU read-side critical section
-	might hold a reference to the newly removed <tt>struct foo</tt>
-	after the <tt>kfree()</tt> on line&nbsp;14 of
-	<tt>remove_gp_synchronous()</tt>.
-<li>	Each CPU that has an RCU read-side critical section that ends
-	after <tt>synchronize_rcu()</tt> returns is guaranteed
-	to execute a full memory barrier between the time that
-	<tt>synchronize_rcu()</tt> begins and the time that the RCU
-	read-side critical section begins.
-	Without this guarantee, a later RCU read-side critical section
-	running after the <tt>kfree()</tt> on line&nbsp;14 of
-	<tt>remove_gp_synchronous()</tt> might
-	later run <tt>do_something_gp()</tt> and find the
-	newly deleted <tt>struct foo</tt>.
-<li>	If the task invoking <tt>synchronize_rcu()</tt> remains
-	on a given CPU, then that CPU is guaranteed to execute a full
-	memory barrier sometime during the execution of
-	<tt>synchronize_rcu()</tt>.
-	This guarantee ensures that the <tt>kfree()</tt> on
-	line&nbsp;14 of <tt>remove_gp_synchronous()</tt> really does
-	execute after the removal on line&nbsp;11.
-<li>	If the task invoking <tt>synchronize_rcu()</tt> migrates
-	among a group of CPUs during that invocation, then each of the
-	CPUs in that group is guaranteed to execute a full memory barrier
-	sometime during the execution of <tt>synchronize_rcu()</tt>.
-	This guarantee also ensures that the <tt>kfree()</tt> on
-	line&nbsp;14 of <tt>remove_gp_synchronous()</tt> really does
-	execute after the removal on
-	line&nbsp;11, but also in the case where the thread executing the
-	<tt>synchronize_rcu()</tt> migrates in the meantime.
-</ol>
-
-<table>
-<tr><th>&nbsp;</th></tr>
-<tr><th align="left">Quick Quiz:</th></tr>
-<tr><td>
-	Given that multiple CPUs can start RCU read-side critical sections
-	at any time without any ordering whatsoever, how can RCU possibly
-	tell whether or not a given RCU read-side critical section starts
-	before a given instance of <tt>synchronize_rcu()</tt>?
-</td></tr>
-<tr><th align="left">Answer:</th></tr>
-<tr><td bgcolor="#ffffff"><font color="ffffff">
-	If RCU cannot tell whether or not a given
-	RCU read-side critical section starts before a
-	given instance of <tt>synchronize_rcu()</tt>,
-	then it must assume that the RCU read-side critical section
-	started first.
-	In other words, a given instance of <tt>synchronize_rcu()</tt>
-	can avoid waiting on a given RCU read-side critical section only
-	if it can prove that <tt>synchronize_rcu()</tt> started first.
-	</font>
-
-	<p><font color="ffffff">
-	A related question is &ldquo;When <tt>rcu_read_lock()</tt>
-	doesn't generate any code, why does it matter how it relates
-	to a grace period?&rdquo;
-	The answer is that it is not the relationship of
-	<tt>rcu_read_lock()</tt> itself that is important, but rather
-	the relationship of the code within the enclosed RCU read-side
-	critical section to the code preceding and following the
-	grace period.
-	If we take this viewpoint, then a given RCU read-side critical
-	section begins before a given grace period when some access
-	preceding the grace period observes the effect of some access
-	within the critical section, in which case none of the accesses
-	within the critical section may observe the effects of any
-	access following the grace period.
-	</font>
-
-	<p><font color="ffffff">
-	As of late 2016, mathematical models of RCU take this
-	viewpoint, for example, see slides&nbsp;62 and&nbsp;63
-	of the
-	<a href="http://www2.rdrop.com/users/paulmck/scalability/paper/LinuxMM.2016.10.04c.LCE.pdf">2016 LinuxCon EU</a>
-	presentation.
-</font></td></tr>
-<tr><td>&nbsp;</td></tr>
-</table>
-
-<table>
-<tr><th>&nbsp;</th></tr>
-<tr><th align="left">Quick Quiz:</th></tr>
-<tr><td>
-	The first and second guarantees require unbelievably strict ordering!
-	Are all these memory barriers <i> really</i> required?
-</td></tr>
-<tr><th align="left">Answer:</th></tr>
-<tr><td bgcolor="#ffffff"><font color="ffffff">
-	Yes, they really are required.
-	To see why the first guarantee is required, consider the following
-	sequence of events:
-	</font>
-
-	<ol>
-	<li>	<font color="ffffff">
-		CPU 1: <tt>rcu_read_lock()</tt>
-		</font>
-	<li>	<font color="ffffff">
-		CPU 1: <tt>q = rcu_dereference(gp);
-		/* Very likely to return p. */</tt>
-		</font>
-	<li>	<font color="ffffff">
-		CPU 0: <tt>list_del_rcu(p);</tt>
-		</font>
-	<li>	<font color="ffffff">
-		CPU 0: <tt>synchronize_rcu()</tt> starts.
-		</font>
-	<li>	<font color="ffffff">
-		CPU 1: <tt>do_something_with(q-&gt;a);
-		/* No smp_mb(), so might happen after kfree(). */</tt>
-		</font>
-	<li>	<font color="ffffff">
-		CPU 1: <tt>rcu_read_unlock()</tt>
-		</font>
-	<li>	<font color="ffffff">
-		CPU 0: <tt>synchronize_rcu()</tt> returns.
-		</font>
-	<li>	<font color="ffffff">
-		CPU 0: <tt>kfree(p);</tt>
-		</font>
-	</ol>
-
-	<p><font color="ffffff">
-	Therefore, there absolutely must be a full memory barrier between the
-	end of the RCU read-side critical section and the end of the
-	grace period.
-	</font>
-
-	<p><font color="ffffff">
-	The sequence of events demonstrating the necessity of the second rule
-	is roughly similar:
-	</font>
-
-	<ol>
-	<li>	<font color="ffffff">CPU 0: <tt>list_del_rcu(p);</tt>
-		</font>
-	<li>	<font color="ffffff">CPU 0: <tt>synchronize_rcu()</tt> starts.
-		</font>
-	<li>	<font color="ffffff">CPU 1: <tt>rcu_read_lock()</tt>
-		</font>
-	<li>	<font color="ffffff">CPU 1: <tt>q = rcu_dereference(gp);
-		/* Might return p if no memory barrier. */</tt>
-		</font>
-	<li>	<font color="ffffff">CPU 0: <tt>synchronize_rcu()</tt> returns.
-		</font>
-	<li>	<font color="ffffff">CPU 0: <tt>kfree(p);</tt>
-		</font>
-	<li>	<font color="ffffff">
-		CPU 1: <tt>do_something_with(q-&gt;a); /* Boom!!! */</tt>
-		</font>
-	<li>	<font color="ffffff">CPU 1: <tt>rcu_read_unlock()</tt>
-		</font>
-	</ol>
-
-	<p><font color="ffffff">
-	And similarly, without a memory barrier between the beginning of the
-	grace period and the beginning of the RCU read-side critical section,
-	CPU&nbsp;1 might end up accessing the freelist.
-	</font>
-
-	<p><font color="ffffff">
-	The &ldquo;as if&rdquo; rule of course applies, so that any
-	implementation that acts as if the appropriate memory barriers
-	were in place is a correct implementation.
-	That said, it is much easier to fool yourself into believing
-	that you have adhered to the as-if rule than it is to actually
-	adhere to it!
-</font></td></tr>
-<tr><td>&nbsp;</td></tr>
-</table>
-
-<table>
-<tr><th>&nbsp;</th></tr>
-<tr><th align="left">Quick Quiz:</th></tr>
-<tr><td>
-	You claim that <tt>rcu_read_lock()</tt> and <tt>rcu_read_unlock()</tt>
-	generate absolutely no code in some kernel builds.
-	This means that the compiler might arbitrarily rearrange consecutive
-	RCU read-side critical sections.
-	Given such rearrangement, if a given RCU read-side critical section
-	is done, how can you be sure that all prior RCU read-side critical
-	sections are done?
-	Won't the compiler rearrangements make that impossible to determine?
-</td></tr>
-<tr><th align="left">Answer:</th></tr>
-<tr><td bgcolor="#ffffff"><font color="ffffff">
-	In cases where <tt>rcu_read_lock()</tt> and <tt>rcu_read_unlock()</tt>
-	generate absolutely no code, RCU infers quiescent states only at
-	special locations, for example, within the scheduler.
-	Because calls to <tt>schedule()</tt> had better prevent calling-code
-	accesses to shared variables from being rearranged across the call to
-	<tt>schedule()</tt>, if RCU detects the end of a given RCU read-side
-	critical section, it will necessarily detect the end of all prior
-	RCU read-side critical sections, no matter how aggressively the
-	compiler scrambles the code.
-	</font>
-
-	<p><font color="ffffff">
-	Again, this all assumes that the compiler cannot scramble code across
-	calls to the scheduler, out of interrupt handlers, into the idle loop,
-	into user-mode code, and so on.
-	But if your kernel build allows that sort of scrambling, you have broken
-	far more than just RCU!
-</font></td></tr>
-<tr><td>&nbsp;</td></tr>
-</table>
-
-<p>
-Note that these memory-barrier requirements do not replace the fundamental
-RCU requirement that a grace period wait for all pre-existing readers.
-On the contrary, the memory barriers called out in this section must operate in
-such a way as to <i>enforce</i> this fundamental requirement.
-Of course, different implementations enforce this requirement in different
-ways, but enforce it they must.
-
-<h3><a name="RCU Primitives Guaranteed to Execute Unconditionally">RCU Primitives Guaranteed to Execute Unconditionally</a></h3>
-
-<p>
-The common-case RCU primitives are unconditional.
-They are invoked, they do their job, and they return, with no possibility
-of error, and no need to retry.
-This is a key RCU design philosophy.
-
-<p>
-However, this philosophy is pragmatic rather than pigheaded.
-If someone comes up with a good justification for a particular conditional
-RCU primitive, it might well be implemented and added.
-After all, this guarantee was reverse-engineered, not premeditated.
-The unconditional nature of the RCU primitives was initially an
-accident of implementation, and later experience with synchronization
-primitives with conditional primitives caused me to elevate this
-accident to a guarantee.
-Therefore, the justification for adding a conditional primitive to
-RCU would need to be based on detailed and compelling use cases.
-
-<h3><a name="Guaranteed Read-to-Write Upgrade">Guaranteed Read-to-Write Upgrade</a></h3>
-
-<p>
-As far as RCU is concerned, it is always possible to carry out an
-update within an RCU read-side critical section.
-For example, that RCU read-side critical section might search for
-a given data element, and then might acquire the update-side
-spinlock in order to update that element, all while remaining
-in that RCU read-side critical section.
-Of course, it is necessary to exit the RCU read-side critical section
-before invoking <tt>synchronize_rcu()</tt>, however, this
-inconvenience can be avoided through use of the
-<tt>call_rcu()</tt> and <tt>kfree_rcu()</tt> API members
-described later in this document.
-
-<table>
-<tr><th>&nbsp;</th></tr>
-<tr><th align="left">Quick Quiz:</th></tr>
-<tr><td>
-	But how does the upgrade-to-write operation exclude other readers?
-</td></tr>
-<tr><th align="left">Answer:</th></tr>
-<tr><td bgcolor="#ffffff"><font color="ffffff">
-	It doesn't, just like normal RCU updates, which also do not exclude
-	RCU readers.
-</font></td></tr>
-<tr><td>&nbsp;</td></tr>
-</table>
-
-<p>
-This guarantee allows lookup code to be shared between read-side
-and update-side code, and was premeditated, appearing in the earliest
-DYNIX/ptx RCU documentation.
-
-<h2><a name="Fundamental Non-Requirements">Fundamental Non-Requirements</a></h2>
-
-<p>
-RCU provides extremely lightweight readers, and its read-side guarantees,
-though quite useful, are correspondingly lightweight.
-It is therefore all too easy to assume that RCU is guaranteeing more
-than it really is.
-Of course, the list of things that RCU does not guarantee is infinitely
-long, however, the following sections list a few non-guarantees that
-have caused confusion.
-Except where otherwise noted, these non-guarantees were premeditated.
-
-<ol>
-<li>	<a href="#Readers Impose Minimal Ordering">
-	Readers Impose Minimal Ordering</a>
-<li>	<a href="#Readers Do Not Exclude Updaters">
-	Readers Do Not Exclude Updaters</a>
-<li>	<a href="#Updaters Only Wait For Old Readers">
-	Updaters Only Wait For Old Readers</a>
-<li>	<a href="#Grace Periods Don't Partition Read-Side Critical Sections">
-	Grace Periods Don't Partition Read-Side Critical Sections</a>
-<li>	<a href="#Read-Side Critical Sections Don't Partition Grace Periods">
-	Read-Side Critical Sections Don't Partition Grace Periods</a>
-</ol>
-
-<h3><a name="Readers Impose Minimal Ordering">Readers Impose Minimal Ordering</a></h3>
-
-<p>
-Reader-side markers such as <tt>rcu_read_lock()</tt> and
-<tt>rcu_read_unlock()</tt> provide absolutely no ordering guarantees
-except through their interaction with the grace-period APIs such as
-<tt>synchronize_rcu()</tt>.
-To see this, consider the following pair of threads:
-
-<blockquote>
-<pre>
- 1 void thread0(void)
- 2 {
- 3   rcu_read_lock();
- 4   WRITE_ONCE(x, 1);
- 5   rcu_read_unlock();
- 6   rcu_read_lock();
- 7   WRITE_ONCE(y, 1);
- 8   rcu_read_unlock();
- 9 }
-10
-11 void thread1(void)
-12 {
-13   rcu_read_lock();
-14   r1 = READ_ONCE(y);
-15   rcu_read_unlock();
-16   rcu_read_lock();
-17   r2 = READ_ONCE(x);
-18   rcu_read_unlock();
-19 }
-</pre>
-</blockquote>
-
-<p>
-After <tt>thread0()</tt> and <tt>thread1()</tt> execute
-concurrently, it is quite possible to have
-
-<blockquote>
-<pre>
-(r1 == 1 &amp;&amp; r2 == 0)
-</pre>
-</blockquote>
-
-(that is, <tt>y</tt> appears to have been assigned before <tt>x</tt>),
-which would not be possible if <tt>rcu_read_lock()</tt> and
-<tt>rcu_read_unlock()</tt> had much in the way of ordering
-properties.
-But they do not, so the CPU is within its rights
-to do significant reordering.
-This is by design:  Any significant ordering constraints would slow down
-these fast-path APIs.
-
-<table>
-<tr><th>&nbsp;</th></tr>
-<tr><th align="left">Quick Quiz:</th></tr>
-<tr><td>
-	Can't the compiler also reorder this code?
-</td></tr>
-<tr><th align="left">Answer:</th></tr>
-<tr><td bgcolor="#ffffff"><font color="ffffff">
-	No, the volatile casts in <tt>READ_ONCE()</tt> and
-	<tt>WRITE_ONCE()</tt> prevent the compiler from reordering in
-	this particular case.
-</font></td></tr>
-<tr><td>&nbsp;</td></tr>
-</table>
-
-<h3><a name="Readers Do Not Exclude Updaters">Readers Do Not Exclude Updaters</a></h3>
-
-<p>
-Neither <tt>rcu_read_lock()</tt> nor <tt>rcu_read_unlock()</tt>
-exclude updates.
-All they do is to prevent grace periods from ending.
-The following example illustrates this:
-
-<blockquote>
-<pre>
- 1 void thread0(void)
- 2 {
- 3   rcu_read_lock();
- 4   r1 = READ_ONCE(y);
- 5   if (r1) {
- 6     do_something_with_nonzero_x();
- 7     r2 = READ_ONCE(x);
- 8     WARN_ON(!r2); /* BUG!!! */
- 9   }
-10   rcu_read_unlock();
-11 }
-12
-13 void thread1(void)
-14 {
-15   spin_lock(&amp;my_lock);
-16   WRITE_ONCE(x, 1);
-17   WRITE_ONCE(y, 1);
-18   spin_unlock(&amp;my_lock);
-19 }
-</pre>
-</blockquote>
-
-<p>
-If the <tt>thread0()</tt> function's <tt>rcu_read_lock()</tt>
-excluded the <tt>thread1()</tt> function's update,
-the <tt>WARN_ON()</tt> could never fire.
-But the fact is that <tt>rcu_read_lock()</tt> does not exclude
-much of anything aside from subsequent grace periods, of which
-<tt>thread1()</tt> has none, so the
-<tt>WARN_ON()</tt> can and does fire.
-
-<h3><a name="Updaters Only Wait For Old Readers">Updaters Only Wait For Old Readers</a></h3>
-
-<p>
-It might be tempting to assume that after <tt>synchronize_rcu()</tt>
-completes, there are no readers executing.
-This temptation must be avoided because
-new readers can start immediately after <tt>synchronize_rcu()</tt>
-starts, and <tt>synchronize_rcu()</tt> is under no
-obligation to wait for these new readers.
-
-<table>
-<tr><th>&nbsp;</th></tr>
-<tr><th align="left">Quick Quiz:</th></tr>
-<tr><td>
-	Suppose that synchronize_rcu() did wait until <i>all</i>
-	readers had completed instead of waiting only on
-	pre-existing readers.
-	For how long would the updater be able to rely on there
-	being no readers?
-</td></tr>
-<tr><th align="left">Answer:</th></tr>
-<tr><td bgcolor="#ffffff"><font color="ffffff">
-	For no time at all.
-	Even if <tt>synchronize_rcu()</tt> were to wait until
-	all readers had completed, a new reader might start immediately after
-	<tt>synchronize_rcu()</tt> completed.
-	Therefore, the code following
-	<tt>synchronize_rcu()</tt> can <i>never</i> rely on there being
-	no readers.
-</font></td></tr>
-<tr><td>&nbsp;</td></tr>
-</table>
-
-<h3><a name="Grace Periods Don't Partition Read-Side Critical Sections">
-Grace Periods Don't Partition Read-Side Critical Sections</a></h3>
-
-<p>
-It is tempting to assume that if any part of one RCU read-side critical
-section precedes a given grace period, and if any part of another RCU
-read-side critical section follows that same grace period, then all of
-the first RCU read-side critical section must precede all of the second.
-However, this just isn't the case: A single grace period does not
-partition the set of RCU read-side critical sections.
-An example of this situation can be illustrated as follows, where
-<tt>x</tt>, <tt>y</tt>, and <tt>z</tt> are initially all zero:
-
-<blockquote>
-<pre>
- 1 void thread0(void)
- 2 {
- 3   rcu_read_lock();
- 4   WRITE_ONCE(a, 1);
- 5   WRITE_ONCE(b, 1);
- 6   rcu_read_unlock();
- 7 }
- 8
- 9 void thread1(void)
-10 {
-11   r1 = READ_ONCE(a);
-12   synchronize_rcu();
-13   WRITE_ONCE(c, 1);
-14 }
-15
-16 void thread2(void)
-17 {
-18   rcu_read_lock();
-19   r2 = READ_ONCE(b);
-20   r3 = READ_ONCE(c);
-21   rcu_read_unlock();
-22 }
-</pre>
-</blockquote>
-
-<p>
-It turns out that the outcome:
-
-<blockquote>
-<pre>
-(r1 == 1 &amp;&amp; r2 == 0 &amp;&amp; r3 == 1)
-</pre>
-</blockquote>
-
-is entirely possible.
-The following figure show how this can happen, with each circled
-<tt>QS</tt> indicating the point at which RCU recorded a
-<i>quiescent state</i> for each thread, that is, a state in which
-RCU knows that the thread cannot be in the midst of an RCU read-side
-critical section that started before the current grace period:
-
-<p><img src="GPpartitionReaders1.svg" alt="GPpartitionReaders1.svg" width="60%"></p>
-
-<p>
-If it is necessary to partition RCU read-side critical sections in this
-manner, it is necessary to use two grace periods, where the first
-grace period is known to end before the second grace period starts:
-
-<blockquote>
-<pre>
- 1 void thread0(void)
- 2 {
- 3   rcu_read_lock();
- 4   WRITE_ONCE(a, 1);
- 5   WRITE_ONCE(b, 1);
- 6   rcu_read_unlock();
- 7 }
- 8
- 9 void thread1(void)
-10 {
-11   r1 = READ_ONCE(a);
-12   synchronize_rcu();
-13   WRITE_ONCE(c, 1);
-14 }
-15
-16 void thread2(void)
-17 {
-18   r2 = READ_ONCE(c);
-19   synchronize_rcu();
-20   WRITE_ONCE(d, 1);
-21 }
-22
-23 void thread3(void)
-24 {
-25   rcu_read_lock();
-26   r3 = READ_ONCE(b);
-27   r4 = READ_ONCE(d);
-28   rcu_read_unlock();
-29 }
-</pre>
-</blockquote>
-
-<p>
-Here, if <tt>(r1 == 1)</tt>, then
-<tt>thread0()</tt>'s write to <tt>b</tt> must happen
-before the end of <tt>thread1()</tt>'s grace period.
-If in addition <tt>(r4 == 1)</tt>, then
-<tt>thread3()</tt>'s read from <tt>b</tt> must happen
-after the beginning of <tt>thread2()</tt>'s grace period.
-If it is also the case that <tt>(r2 == 1)</tt>, then the
-end of <tt>thread1()</tt>'s grace period must precede the
-beginning of <tt>thread2()</tt>'s grace period.
-This mean that the two RCU read-side critical sections cannot overlap,
-guaranteeing that <tt>(r3 == 1)</tt>.
-As a result, the outcome:
-
-<blockquote>
-<pre>
-(r1 == 1 &amp;&amp; r2 == 1 &amp;&amp; r3 == 0 &amp;&amp; r4 == 1)
-</pre>
-</blockquote>
-
-cannot happen.
-
-<p>
-This non-requirement was also non-premeditated, but became apparent
-when studying RCU's interaction with memory ordering.
-
-<h3><a name="Read-Side Critical Sections Don't Partition Grace Periods">
-Read-Side Critical Sections Don't Partition Grace Periods</a></h3>
-
-<p>
-It is also tempting to assume that if an RCU read-side critical section
-happens between a pair of grace periods, then those grace periods cannot
-overlap.
-However, this temptation leads nowhere good, as can be illustrated by
-the following, with all variables initially zero:
-
-<blockquote>
-<pre>
- 1 void thread0(void)
- 2 {
- 3   rcu_read_lock();
- 4   WRITE_ONCE(a, 1);
- 5   WRITE_ONCE(b, 1);
- 6   rcu_read_unlock();
- 7 }
- 8
- 9 void thread1(void)
-10 {
-11   r1 = READ_ONCE(a);
-12   synchronize_rcu();
-13   WRITE_ONCE(c, 1);
-14 }
-15
-16 void thread2(void)
-17 {
-18   rcu_read_lock();
-19   WRITE_ONCE(d, 1);
-20   r2 = READ_ONCE(c);
-21   rcu_read_unlock();
-22 }
-23
-24 void thread3(void)
-25 {
-26   r3 = READ_ONCE(d);
-27   synchronize_rcu();
-28   WRITE_ONCE(e, 1);
-29 }
-30
-31 void thread4(void)
-32 {
-33   rcu_read_lock();
-34   r4 = READ_ONCE(b);
-35   r5 = READ_ONCE(e);
-36   rcu_read_unlock();
-37 }
-</pre>
-</blockquote>
-
-<p>
-In this case, the outcome:
-
-<blockquote>
-<pre>
-(r1 == 1 &amp;&amp; r2 == 1 &amp;&amp; r3 == 1 &amp;&amp; r4 == 0 &amp&amp; r5 == 1)
-</pre>
-</blockquote>
-
-is entirely possible, as illustrated below:
-
-<p><img src="ReadersPartitionGP1.svg" alt="ReadersPartitionGP1.svg" width="100%"></p>
-
-<p>
-Again, an RCU read-side critical section can overlap almost all of a
-given grace period, just so long as it does not overlap the entire
-grace period.
-As a result, an RCU read-side critical section cannot partition a pair
-of RCU grace periods.
-
-<table>
-<tr><th>&nbsp;</th></tr>
-<tr><th align="left">Quick Quiz:</th></tr>
-<tr><td>
-	How long a sequence of grace periods, each separated by an RCU
-	read-side critical section, would be required to partition the RCU
-	read-side critical sections at the beginning and end of the chain?
-</td></tr>
-<tr><th align="left">Answer:</th></tr>
-<tr><td bgcolor="#ffffff"><font color="ffffff">
-	In theory, an infinite number.
-	In practice, an unknown number that is sensitive to both implementation
-	details and timing considerations.
-	Therefore, even in practice, RCU users must abide by the
-	theoretical rather than the practical answer.
-</font></td></tr>
-<tr><td>&nbsp;</td></tr>
-</table>
-
-<h2><a name="Parallelism Facts of Life">Parallelism Facts of Life</a></h2>
-
-<p>
-These parallelism facts of life are by no means specific to RCU, but
-the RCU implementation must abide by them.
-They therefore bear repeating:
-
-<ol>
-<li>	Any CPU or task may be delayed at any time,
-	and any attempts to avoid these delays by disabling
-	preemption, interrupts, or whatever are completely futile.
-	This is most obvious in preemptible user-level
-	environments and in virtualized environments (where
-	a given guest OS's VCPUs can be preempted at any time by
-	the underlying hypervisor), but can also happen in bare-metal
-	environments due to ECC errors, NMIs, and other hardware
-	events.
-	Although a delay of more than about 20 seconds can result
-	in splats, the RCU implementation is obligated to use
-	algorithms that can tolerate extremely long delays, but where
-	&ldquo;extremely long&rdquo; is not long enough to allow
-	wrap-around when incrementing a 64-bit counter.
-<li>	Both the compiler and the CPU can reorder memory accesses.
-	Where it matters, RCU must use compiler directives and
-	memory-barrier instructions to preserve ordering.
-<li>	Conflicting writes to memory locations in any given cache line
-	will result in expensive cache misses.
-	Greater numbers of concurrent writes and more-frequent
-	concurrent writes will result in more dramatic slowdowns.
-	RCU is therefore obligated to use algorithms that have
-	sufficient locality to avoid significant performance and
-	scalability problems.
-<li>	As a rough rule of thumb, only one CPU's worth of processing
-	may be carried out under the protection of any given exclusive
-	lock.
-	RCU must therefore use scalable locking designs.
-<li>	Counters are finite, especially on 32-bit systems.
-	RCU's use of counters must therefore tolerate counter wrap,
-	or be designed such that counter wrap would take way more
-	time than a single system is likely to run.
-	An uptime of ten years is quite possible, a runtime
-	of a century much less so.
-	As an example of the latter, RCU's dyntick-idle nesting counter
-	allows 54 bits for interrupt nesting level (this counter
-	is 64 bits even on a 32-bit system).
-	Overflowing this counter requires 2<sup>54</sup>
-	half-interrupts on a given CPU without that CPU ever going idle.
-	If a half-interrupt happened every microsecond, it would take
-	570 years of runtime to overflow this counter, which is currently
-	believed to be an acceptably long time.
-<li>	Linux systems can have thousands of CPUs running a single
-	Linux kernel in a single shared-memory environment.
-	RCU must therefore pay close attention to high-end scalability.
-</ol>
-
-<p>
-This last parallelism fact of life means that RCU must pay special
-attention to the preceding facts of life.
-The idea that Linux might scale to systems with thousands of CPUs would
-have been met with some skepticism in the 1990s, but these requirements
-would have otherwise have been unsurprising, even in the early 1990s.
-
-<h2><a name="Quality-of-Implementation Requirements">Quality-of-Implementation Requirements</a></h2>
-
-<p>
-These sections list quality-of-implementation requirements.
-Although an RCU implementation that ignores these requirements could
-still be used, it would likely be subject to limitations that would
-make it inappropriate for industrial-strength production use.
-Classes of quality-of-implementation requirements are as follows:
-
-<ol>
-<li>	<a href="#Specialization">Specialization</a>
-<li>	<a href="#Performance and Scalability">Performance and Scalability</a>
-<li>	<a href="#Forward Progress">Forward Progress</a>
-<li>	<a href="#Composability">Composability</a>
-<li>	<a href="#Corner Cases">Corner Cases</a>
-</ol>
-
-<p>
-These classes is covered in the following sections.
-
-<h3><a name="Specialization">Specialization</a></h3>
-
-<p>
-RCU is and always has been intended primarily for read-mostly situations,
-which means that RCU's read-side primitives are optimized, often at the
-expense of its update-side primitives.
-Experience thus far is captured by the following list of situations:
-
-<ol>
-<li>	Read-mostly data, where stale and inconsistent data is not
-	a problem:   RCU works great!
-<li>	Read-mostly data, where data must be consistent:
-	RCU works well.
-<li>	Read-write data, where data must be consistent:
-	RCU <i>might</i> work OK.
-	Or not.
-<li>	Write-mostly data, where data must be consistent:
-	RCU is very unlikely to be the right tool for the job,
-	with the following exceptions, where RCU can provide:
-	<ol type=a>
-	<li>	Existence guarantees for update-friendly mechanisms.
-	<li>	Wait-free read-side primitives for real-time use.
-	</ol>
-</ol>
-
-<p>
-This focus on read-mostly situations means that RCU must interoperate
-with other synchronization primitives.
-For example, the <tt>add_gp()</tt> and <tt>remove_gp_synchronous()</tt>
-examples discussed earlier use RCU to protect readers and locking to
-coordinate updaters.
-However, the need extends much farther, requiring that a variety of
-synchronization primitives be legal within RCU read-side critical sections,
-including spinlocks, sequence locks, atomic operations, reference
-counters, and memory barriers.
-
-<table>
-<tr><th>&nbsp;</th></tr>
-<tr><th align="left">Quick Quiz:</th></tr>
-<tr><td>
-	What about sleeping locks?
-</td></tr>
-<tr><th align="left">Answer:</th></tr>
-<tr><td bgcolor="#ffffff"><font color="ffffff">
-	These are forbidden within Linux-kernel RCU read-side critical
-	sections because it is not legal to place a quiescent state
-	(in this case, voluntary context switch) within an RCU read-side
-	critical section.
-	However, sleeping locks may be used within userspace RCU read-side
-	critical sections, and also within Linux-kernel sleepable RCU
-	<a href="#Sleepable RCU"><font color="ffffff">(SRCU)</font></a>
-	read-side critical sections.
-	In addition, the -rt patchset turns spinlocks into a
-	sleeping locks so that the corresponding critical sections
-	can be preempted, which also means that these sleeplockified
-	spinlocks (but not other sleeping locks!)  may be acquire within
-	-rt-Linux-kernel RCU read-side critical sections.
-	</font>
-
-	<p><font color="ffffff">
-	Note that it <i>is</i> legal for a normal RCU read-side
-	critical section to conditionally acquire a sleeping locks
-	(as in <tt>mutex_trylock()</tt>), but only as long as it does
-	not loop indefinitely attempting to conditionally acquire that
-	sleeping locks.
-	The key point is that things like <tt>mutex_trylock()</tt>
-	either return with the mutex held, or return an error indication if
-	the mutex was not immediately available.
-	Either way, <tt>mutex_trylock()</tt> returns immediately without
-	sleeping.
-</font></td></tr>
-<tr><td>&nbsp;</td></tr>
-</table>
-
-<p>
-It often comes as a surprise that many algorithms do not require a
-consistent view of data, but many can function in that mode,
-with network routing being the poster child.
-Internet routing algorithms take significant time to propagate
-updates, so that by the time an update arrives at a given system,
-that system has been sending network traffic the wrong way for
-a considerable length of time.
-Having a few threads continue to send traffic the wrong way for a
-few more milliseconds is clearly not a problem:  In the worst case,
-TCP retransmissions will eventually get the data where it needs to go.
-In general, when tracking the state of the universe outside of the
-computer, some level of inconsistency must be tolerated due to
-speed-of-light delays if nothing else.
-
-<p>
-Furthermore, uncertainty about external state is inherent in many cases.
-For example, a pair of veterinarians might use heartbeat to determine
-whether or not a given cat was alive.
-But how long should they wait after the last heartbeat to decide that
-the cat is in fact dead?
-Waiting less than 400 milliseconds makes no sense because this would
-mean that a relaxed cat would be considered to cycle between death
-and life more than 100 times per minute.
-Moreover, just as with human beings, a cat's heart might stop for
-some period of time, so the exact wait period is a judgment call.
-One of our pair of veterinarians might wait 30 seconds before pronouncing
-the cat dead, while the other might insist on waiting a full minute.
-The two veterinarians would then disagree on the state of the cat during
-the final 30 seconds of the minute following the last heartbeat.
-
-<p>
-Interestingly enough, this same situation applies to hardware.
-When push comes to shove, how do we tell whether or not some
-external server has failed?
-We send messages to it periodically, and declare it failed if we
-don't receive a response within a given period of time.
-Policy decisions can usually tolerate short
-periods of inconsistency.
-The policy was decided some time ago, and is only now being put into
-effect, so a few milliseconds of delay is normally inconsequential.
-
-<p>
-However, there are algorithms that absolutely must see consistent data.
-For example, the translation between a user-level SystemV semaphore
-ID to the corresponding in-kernel data structure is protected by RCU,
-but it is absolutely forbidden to update a semaphore that has just been
-removed.
-In the Linux kernel, this need for consistency is accommodated by acquiring
-spinlocks located in the in-kernel data structure from within
-the RCU read-side critical section, and this is indicated by the
-green box in the figure above.
-Many other techniques may be used, and are in fact used within the
-Linux kernel.
-
-<p>
-In short, RCU is not required to maintain consistency, and other
-mechanisms may be used in concert with RCU when consistency is required.
-RCU's specialization allows it to do its job extremely well, and its
-ability to interoperate with other synchronization mechanisms allows
-the right mix of synchronization tools to be used for a given job.
-
-<h3><a name="Performance and Scalability">Performance and Scalability</a></h3>
-
-<p>
-Energy efficiency is a critical component of performance today,
-and Linux-kernel RCU implementations must therefore avoid unnecessarily
-awakening idle CPUs.
-I cannot claim that this requirement was premeditated.
-In fact, I learned of it during a telephone conversation in which I
-was given &ldquo;frank and open&rdquo; feedback on the importance
-of energy efficiency in battery-powered systems and on specific
-energy-efficiency shortcomings of the Linux-kernel RCU implementation.
-In my experience, the battery-powered embedded community will consider
-any unnecessary wakeups to be extremely unfriendly acts.
-So much so that mere Linux-kernel-mailing-list posts are
-insufficient to vent their ire.
-
-<p>
-Memory consumption is not particularly important for in most
-situations, and has become decreasingly
-so as memory sizes have expanded and memory
-costs have plummeted.
-However, as I learned from Matt Mackall's
-<a href="http://elinux.org/Linux_Tiny-FAQ">bloatwatch</a>
-efforts, memory footprint is critically important on single-CPU systems with
-non-preemptible (<tt>CONFIG_PREEMPT=n</tt>) kernels, and thus
-<a href="https://lkml.kernel.org/g/20090113221724.GA15307@linux.vnet.ibm.com">tiny RCU</a>
-was born.
-Josh Triplett has since taken over the small-memory banner with his
-<a href="https://tiny.wiki.kernel.org/">Linux kernel tinification</a>
-project, which resulted in
-<a href="#Sleepable RCU">SRCU</a>
-becoming optional for those kernels not needing it.
-
-<p>
-The remaining performance requirements are, for the most part,
-unsurprising.
-For example, in keeping with RCU's read-side specialization,
-<tt>rcu_dereference()</tt> should have negligible overhead (for
-example, suppression of a few minor compiler optimizations).
-Similarly, in non-preemptible environments, <tt>rcu_read_lock()</tt> and
-<tt>rcu_read_unlock()</tt> should have exactly zero overhead.
-
-<p>
-In preemptible environments, in the case where the RCU read-side
-critical section was not preempted (as will be the case for the
-highest-priority real-time process), <tt>rcu_read_lock()</tt> and
-<tt>rcu_read_unlock()</tt> should have minimal overhead.
-In particular, they should not contain atomic read-modify-write
-operations, memory-barrier instructions, preemption disabling,
-interrupt disabling, or backwards branches.
-However, in the case where the RCU read-side critical section was preempted,
-<tt>rcu_read_unlock()</tt> may acquire spinlocks and disable interrupts.
-This is why it is better to nest an RCU read-side critical section
-within a preempt-disable region than vice versa, at least in cases
-where that critical section is short enough to avoid unduly degrading
-real-time latencies.
-
-<p>
-The <tt>synchronize_rcu()</tt> grace-period-wait primitive is
-optimized for throughput.
-It may therefore incur several milliseconds of latency in addition to
-the duration of the longest RCU read-side critical section.
-On the other hand, multiple concurrent invocations of
-<tt>synchronize_rcu()</tt> are required to use batching optimizations
-so that they can be satisfied by a single underlying grace-period-wait
-operation.
-For example, in the Linux kernel, it is not unusual for a single
-grace-period-wait operation to serve more than
-<a href="https://www.usenix.org/conference/2004-usenix-annual-technical-conference/making-rcu-safe-deep-sub-millisecond-response">1,000 separate invocations</a>
-of <tt>synchronize_rcu()</tt>, thus amortizing the per-invocation
-overhead down to nearly zero.
-However, the grace-period optimization is also required to avoid
-measurable degradation of real-time scheduling and interrupt latencies.
-
-<p>
-In some cases, the multi-millisecond <tt>synchronize_rcu()</tt>
-latencies are unacceptable.
-In these cases, <tt>synchronize_rcu_expedited()</tt> may be used
-instead, reducing the grace-period latency down to a few tens of
-microseconds on small systems, at least in cases where the RCU read-side
-critical sections are short.
-There are currently no special latency requirements for
-<tt>synchronize_rcu_expedited()</tt> on large systems, but,
-consistent with the empirical nature of the RCU specification,
-that is subject to change.
-However, there most definitely are scalability requirements:
-A storm of <tt>synchronize_rcu_expedited()</tt> invocations on 4096
-CPUs should at least make reasonable forward progress.
-In return for its shorter latencies, <tt>synchronize_rcu_expedited()</tt>
-is permitted to impose modest degradation of real-time latency
-on non-idle online CPUs.
-Here, &ldquo;modest&rdquo; means roughly the same latency
-degradation as a scheduling-clock interrupt.
-
-<p>
-There are a number of situations where even
-<tt>synchronize_rcu_expedited()</tt>'s reduced grace-period
-latency is unacceptable.
-In these situations, the asynchronous <tt>call_rcu()</tt> can be
-used in place of <tt>synchronize_rcu()</tt> as follows:
-
-<blockquote>
-<pre>
- 1 struct foo {
- 2   int a;
- 3   int b;
- 4   struct rcu_head rh;
- 5 };
- 6
- 7 static void remove_gp_cb(struct rcu_head *rhp)
- 8 {
- 9   struct foo *p = container_of(rhp, struct foo, rh);
-10
-11   kfree(p);
-12 }
-13
-14 bool remove_gp_asynchronous(void)
-15 {
-16   struct foo *p;
-17
-18   spin_lock(&amp;gp_lock);
-19   p = rcu_access_pointer(gp);
-20   if (!p) {
-21     spin_unlock(&amp;gp_lock);
-22     return false;
-23   }
-24   rcu_assign_pointer(gp, NULL);
-25   call_rcu(&amp;p-&gt;rh, remove_gp_cb);
-26   spin_unlock(&amp;gp_lock);
-27   return true;
-28 }
-</pre>
-</blockquote>
-
-<p>
-A definition of <tt>struct foo</tt> is finally needed, and appears
-on lines&nbsp;1-5.
-The function <tt>remove_gp_cb()</tt> is passed to <tt>call_rcu()</tt>
-on line&nbsp;25, and will be invoked after the end of a subsequent
-grace period.
-This gets the same effect as <tt>remove_gp_synchronous()</tt>,
-but without forcing the updater to wait for a grace period to elapse.
-The <tt>call_rcu()</tt> function may be used in a number of
-situations where neither <tt>synchronize_rcu()</tt> nor
-<tt>synchronize_rcu_expedited()</tt> would be legal,
-including within preempt-disable code, <tt>local_bh_disable()</tt> code,
-interrupt-disable code, and interrupt handlers.
-However, even <tt>call_rcu()</tt> is illegal within NMI handlers
-and from idle and offline CPUs.
-The callback function (<tt>remove_gp_cb()</tt> in this case) will be
-executed within softirq (software interrupt) environment within the
-Linux kernel,
-either within a real softirq handler or under the protection
-of <tt>local_bh_disable()</tt>.
-In both the Linux kernel and in userspace, it is bad practice to
-write an RCU callback function that takes too long.
-Long-running operations should be relegated to separate threads or
-(in the Linux kernel) workqueues.
-
-<table>
-<tr><th>&nbsp;</th></tr>
-<tr><th align="left">Quick Quiz:</th></tr>
-<tr><td>
-	Why does line&nbsp;19 use <tt>rcu_access_pointer()</tt>?
-	After all, <tt>call_rcu()</tt> on line&nbsp;25 stores into the
-	structure, which would interact badly with concurrent insertions.
-	Doesn't this mean that <tt>rcu_dereference()</tt> is required?
-</td></tr>
-<tr><th align="left">Answer:</th></tr>
-<tr><td bgcolor="#ffffff"><font color="ffffff">
-	Presumably the <tt>-&gt;gp_lock</tt> acquired on line&nbsp;18 excludes
-	any changes, including any insertions that <tt>rcu_dereference()</tt>
-	would protect against.
-	Therefore, any insertions will be delayed until after
-	<tt>-&gt;gp_lock</tt>
-	is released on line&nbsp;25, which in turn means that
-	<tt>rcu_access_pointer()</tt> suffices.
-</font></td></tr>
-<tr><td>&nbsp;</td></tr>
-</table>
-
-<p>
-However, all that <tt>remove_gp_cb()</tt> is doing is
-invoking <tt>kfree()</tt> on the data element.
-This is a common idiom, and is supported by <tt>kfree_rcu()</tt>,
-which allows &ldquo;fire and forget&rdquo; operation as shown below:
-
-<blockquote>
-<pre>
- 1 struct foo {
- 2   int a;
- 3   int b;
- 4   struct rcu_head rh;
- 5 };
- 6
- 7 bool remove_gp_faf(void)
- 8 {
- 9   struct foo *p;
-10
-11   spin_lock(&amp;gp_lock);
-12   p = rcu_dereference(gp);
-13   if (!p) {
-14     spin_unlock(&amp;gp_lock);
-15     return false;
-16   }
-17   rcu_assign_pointer(gp, NULL);
-18   kfree_rcu(p, rh);
-19   spin_unlock(&amp;gp_lock);
-20   return true;
-21 }
-</pre>
-</blockquote>
-
-<p>
-Note that <tt>remove_gp_faf()</tt> simply invokes
-<tt>kfree_rcu()</tt> and proceeds, without any need to pay any
-further attention to the subsequent grace period and <tt>kfree()</tt>.
-It is permissible to invoke <tt>kfree_rcu()</tt> from the same
-environments as for <tt>call_rcu()</tt>.
-Interestingly enough, DYNIX/ptx had the equivalents of
-<tt>call_rcu()</tt> and <tt>kfree_rcu()</tt>, but not
-<tt>synchronize_rcu()</tt>.
-This was due to the fact that RCU was not heavily used within DYNIX/ptx,
-so the very few places that needed something like
-<tt>synchronize_rcu()</tt> simply open-coded it.
-
-<table>
-<tr><th>&nbsp;</th></tr>
-<tr><th align="left">Quick Quiz:</th></tr>
-<tr><td>
-	Earlier it was claimed that <tt>call_rcu()</tt> and
-	<tt>kfree_rcu()</tt> allowed updaters to avoid being blocked
-	by readers.
-	But how can that be correct, given that the invocation of the callback
-	and the freeing of the memory (respectively) must still wait for
-	a grace period to elapse?
-</td></tr>
-<tr><th align="left">Answer:</th></tr>
-<tr><td bgcolor="#ffffff"><font color="ffffff">
-	We could define things this way, but keep in mind that this sort of
-	definition would say that updates in garbage-collected languages
-	cannot complete until the next time the garbage collector runs,
-	which does not seem at all reasonable.
-	The key point is that in most cases, an updater using either
-	<tt>call_rcu()</tt> or <tt>kfree_rcu()</tt> can proceed to the
-	next update as soon as it has invoked <tt>call_rcu()</tt> or
-	<tt>kfree_rcu()</tt>, without having to wait for a subsequent
-	grace period.
-</font></td></tr>
-<tr><td>&nbsp;</td></tr>
-</table>
-
-<p>
-But what if the updater must wait for the completion of code to be
-executed after the end of the grace period, but has other tasks
-that can be carried out in the meantime?
-The polling-style <tt>get_state_synchronize_rcu()</tt> and
-<tt>cond_synchronize_rcu()</tt> functions may be used for this
-purpose, as shown below:
-
-<blockquote>
-<pre>
- 1 bool remove_gp_poll(void)
- 2 {
- 3   struct foo *p;
- 4   unsigned long s;
- 5
- 6   spin_lock(&amp;gp_lock);
- 7   p = rcu_access_pointer(gp);
- 8   if (!p) {
- 9     spin_unlock(&amp;gp_lock);
-10     return false;
-11   }
-12   rcu_assign_pointer(gp, NULL);
-13   spin_unlock(&amp;gp_lock);
-14   s = get_state_synchronize_rcu();
-15   do_something_while_waiting();
-16   cond_synchronize_rcu(s);
-17   kfree(p);
-18   return true;
-19 }
-</pre>
-</blockquote>
-
-<p>
-On line&nbsp;14, <tt>get_state_synchronize_rcu()</tt> obtains a
-&ldquo;cookie&rdquo; from RCU,
-then line&nbsp;15 carries out other tasks,
-and finally, line&nbsp;16 returns immediately if a grace period has
-elapsed in the meantime, but otherwise waits as required.
-The need for <tt>get_state_synchronize_rcu</tt> and
-<tt>cond_synchronize_rcu()</tt> has appeared quite recently,
-so it is too early to tell whether they will stand the test of time.
-
-<p>
-RCU thus provides a range of tools to allow updaters to strike the
-required tradeoff between latency, flexibility and CPU overhead.
-
-<h3><a name="Forward Progress">Forward Progress</a></h3>
-
-<p>
-In theory, delaying grace-period completion and callback invocation
-is harmless.
-In practice, not only are memory sizes finite but also callbacks sometimes
-do wakeups, and sufficiently deferred wakeups can be difficult
-to distinguish from system hangs.
-Therefore, RCU must provide a number of mechanisms to promote forward
-progress.
-
-<p>
-These mechanisms are not foolproof, nor can they be.
-For one simple example, an infinite loop in an RCU read-side critical
-section must by definition prevent later grace periods from ever completing.
-For a more involved example, consider a 64-CPU system built with
-<tt>CONFIG_RCU_NOCB_CPU=y</tt> and booted with <tt>rcu_nocbs=1-63</tt>,
-where CPUs&nbsp;1 through&nbsp;63 spin in tight loops that invoke
-<tt>call_rcu()</tt>.
-Even if these tight loops also contain calls to <tt>cond_resched()</tt>
-(thus allowing grace periods to complete), CPU&nbsp;0 simply will
-not be able to invoke callbacks as fast as the other 63 CPUs can
-register them, at least not until the system runs out of memory.
-In both of these examples, the Spiderman principle applies:  With great
-power comes great responsibility.
-However, short of this level of abuse, RCU is required to
-ensure timely completion of grace periods and timely invocation of
-callbacks.
-
-<p>
-RCU takes the following steps to encourage timely completion of
-grace periods:
-
-<ol>
-<li>	If a grace period fails to complete within 100&nbsp;milliseconds,
-	RCU causes future invocations of <tt>cond_resched()</tt> on
-	the holdout CPUs to provide an RCU quiescent state.
-	RCU also causes those CPUs' <tt>need_resched()</tt> invocations
-	to return <tt>true</tt>, but only after the corresponding CPU's
-	next scheduling-clock.
-<li>	CPUs mentioned in the <tt>nohz_full</tt> kernel boot parameter
-	can run indefinitely in the kernel without scheduling-clock
-	interrupts, which defeats the above <tt>need_resched()</tt>
-	strategem.
-	RCU will therefore invoke <tt>resched_cpu()</tt> on any
-	<tt>nohz_full</tt> CPUs still holding out after
-	109&nbsp;milliseconds.
-<li>	In kernels built with <tt>CONFIG_RCU_BOOST=y</tt>, if a given
-	task that has been preempted within an RCU read-side critical
-	section is holding out for more than 500&nbsp;milliseconds,
-	RCU will resort to priority boosting.
-<li>	If a CPU is still holding out 10&nbsp;seconds into the grace
-	period, RCU will invoke <tt>resched_cpu()</tt> on it regardless
-	of its <tt>nohz_full</tt> state.
-</ol>
-
-<p>
-The above values are defaults for systems running with <tt>HZ=1000</tt>.
-They will vary as the value of <tt>HZ</tt> varies, and can also be
-changed using the relevant Kconfig options and kernel boot parameters.
-RCU currently does not do much sanity checking of these
-parameters, so please use caution when changing them.
-Note that these forward-progress measures are provided only for RCU,
-not for
-<a href="#Sleepable RCU">SRCU</a> or
-<a href="#Tasks RCU">Tasks RCU</a>.
-
-<p>
-RCU takes the following steps in <tt>call_rcu()</tt> to encourage timely
-invocation of callbacks when any given non-<tt>rcu_nocbs</tt> CPU has
-10,000 callbacks, or has 10,000 more callbacks than it had the last time
-encouragement was provided:
-
-<ol>
-<li>	Starts a grace period, if one is not already in progress.
-<li>	Forces immediate checking for quiescent states, rather than
-	waiting for three milliseconds to have elapsed since the
-	beginning of the grace period.
-<li>	Immediately tags the CPU's callbacks with their grace period
-	completion numbers, rather than waiting for the <tt>RCU_SOFTIRQ</tt>
-	handler to get around to it.
-<li>	Lifts callback-execution batch limits, which speeds up callback
-	invocation at the expense of degrading realtime response.
-</ol>
-
-<p>
-Again, these are default values when running at <tt>HZ=1000</tt>,
-and can be overridden.
-Again, these forward-progress measures are provided only for RCU,
-not for
-<a href="#Sleepable RCU">SRCU</a> or
-<a href="#Tasks RCU">Tasks RCU</a>.
-Even for RCU, callback-invocation forward progress for <tt>rcu_nocbs</tt>
-CPUs is much less well-developed, in part because workloads benefiting
-from <tt>rcu_nocbs</tt> CPUs tend to invoke <tt>call_rcu()</tt>
-relatively infrequently.
-If workloads emerge that need both <tt>rcu_nocbs</tt> CPUs and high
-<tt>call_rcu()</tt> invocation rates, then additional forward-progress
-work will be required.
-
-<h3><a name="Composability">Composability</a></h3>
-
-<p>
-Composability has received much attention in recent years, perhaps in part
-due to the collision of multicore hardware with object-oriented techniques
-designed in single-threaded environments for single-threaded use.
-And in theory, RCU read-side critical sections may be composed, and in
-fact may be nested arbitrarily deeply.
-In practice, as with all real-world implementations of composable
-constructs, there are limitations.
-
-<p>
-Implementations of RCU for which <tt>rcu_read_lock()</tt>
-and <tt>rcu_read_unlock()</tt> generate no code, such as
-Linux-kernel RCU when <tt>CONFIG_PREEMPT=n</tt>, can be
-nested arbitrarily deeply.
-After all, there is no overhead.
-Except that if all these instances of <tt>rcu_read_lock()</tt>
-and <tt>rcu_read_unlock()</tt> are visible to the compiler,
-compilation will eventually fail due to exhausting memory,
-mass storage, or user patience, whichever comes first.
-If the nesting is not visible to the compiler, as is the case with
-mutually recursive functions each in its own translation unit,
-stack overflow will result.
-If the nesting takes the form of loops, perhaps in the guise of tail
-recursion, either the control variable
-will overflow or (in the Linux kernel) you will get an RCU CPU stall warning.
-Nevertheless, this class of RCU implementations is one
-of the most composable constructs in existence.
-
-<p>
-RCU implementations that explicitly track nesting depth
-are limited by the nesting-depth counter.
-For example, the Linux kernel's preemptible RCU limits nesting to
-<tt>INT_MAX</tt>.
-This should suffice for almost all practical purposes.
-That said, a consecutive pair of RCU read-side critical sections
-between which there is an operation that waits for a grace period
-cannot be enclosed in another RCU read-side critical section.
-This is because it is not legal to wait for a grace period within
-an RCU read-side critical section:  To do so would result either
-in deadlock or
-in RCU implicitly splitting the enclosing RCU read-side critical
-section, neither of which is conducive to a long-lived and prosperous
-kernel.
-
-<p>
-It is worth noting that RCU is not alone in limiting composability.
-For example, many transactional-memory implementations prohibit
-composing a pair of transactions separated by an irrevocable
-operation (for example, a network receive operation).
-For another example, lock-based critical sections can be composed
-surprisingly freely, but only if deadlock is avoided.
-
-<p>
-In short, although RCU read-side critical sections are highly composable,
-care is required in some situations, just as is the case for any other
-composable synchronization mechanism.
-
-<h3><a name="Corner Cases">Corner Cases</a></h3>
-
-<p>
-A given RCU workload might have an endless and intense stream of
-RCU read-side critical sections, perhaps even so intense that there
-was never a point in time during which there was not at least one
-RCU read-side critical section in flight.
-RCU cannot allow this situation to block grace periods:  As long as
-all the RCU read-side critical sections are finite, grace periods
-must also be finite.
-
-<p>
-That said, preemptible RCU implementations could potentially result
-in RCU read-side critical sections being preempted for long durations,
-which has the effect of creating a long-duration RCU read-side
-critical section.
-This situation can arise only in heavily loaded systems, but systems using
-real-time priorities are of course more vulnerable.
-Therefore, RCU priority boosting is provided to help deal with this
-case.
-That said, the exact requirements on RCU priority boosting will likely
-evolve as more experience accumulates.
-
-<p>
-Other workloads might have very high update rates.
-Although one can argue that such workloads should instead use
-something other than RCU, the fact remains that RCU must
-handle such workloads gracefully.
-This requirement is another factor driving batching of grace periods,
-but it is also the driving force behind the checks for large numbers
-of queued RCU callbacks in the <tt>call_rcu()</tt> code path.
-Finally, high update rates should not delay RCU read-side critical
-sections, although some small read-side delays can occur when using
-<tt>synchronize_rcu_expedited()</tt>, courtesy of this function's use
-of <tt>smp_call_function_single()</tt>.
-
-<p>
-Although all three of these corner cases were understood in the early
-1990s, a simple user-level test consisting of <tt>close(open(path))</tt>
-in a tight loop
-in the early 2000s suddenly provided a much deeper appreciation of the
-high-update-rate corner case.
-This test also motivated addition of some RCU code to react to high update
-rates, for example, if a given CPU finds itself with more than 10,000
-RCU callbacks queued, it will cause RCU to take evasive action by
-more aggressively starting grace periods and more aggressively forcing
-completion of grace-period processing.
-This evasive action causes the grace period to complete more quickly,
-but at the cost of restricting RCU's batching optimizations, thus
-increasing the CPU overhead incurred by that grace period.
-
-<h2><a name="Software-Engineering Requirements">
-Software-Engineering Requirements</a></h2>
-
-<p>
-Between Murphy's Law and &ldquo;To err is human&rdquo;, it is necessary to
-guard against mishaps and misuse:
-
-<ol>
-<li>	It is all too easy to forget to use <tt>rcu_read_lock()</tt>
-	everywhere that it is needed, so kernels built with
-	<tt>CONFIG_PROVE_RCU=y</tt> will splat if
-	<tt>rcu_dereference()</tt> is used outside of an
-	RCU read-side critical section.
-	Update-side code can use <tt>rcu_dereference_protected()</tt>,
-	which takes a
-	<a href="https://lwn.net/Articles/371986/">lockdep expression</a>
-	to indicate what is providing the protection.
-	If the indicated protection is not provided, a lockdep splat
-	is emitted.
-
-	<p>
-	Code shared between readers and updaters can use
-	<tt>rcu_dereference_check()</tt>, which also takes a
-	lockdep expression, and emits a lockdep splat if neither
-	<tt>rcu_read_lock()</tt> nor the indicated protection
-	is in place.
-	In addition, <tt>rcu_dereference_raw()</tt> is used in those
-	(hopefully rare) cases where the required protection cannot
-	be easily described.
-	Finally, <tt>rcu_read_lock_held()</tt> is provided to
-	allow a function to verify that it has been invoked within
-	an RCU read-side critical section.
-	I was made aware of this set of requirements shortly after Thomas
-	Gleixner audited a number of RCU uses.
-<li>	A given function might wish to check for RCU-related preconditions
-	upon entry, before using any other RCU API.
-	The <tt>rcu_lockdep_assert()</tt> does this job,
-	asserting the expression in kernels having lockdep enabled
-	and doing nothing otherwise.
-<li>	It is also easy to forget to use <tt>rcu_assign_pointer()</tt>
-	and <tt>rcu_dereference()</tt>, perhaps (incorrectly)
-	substituting a simple assignment.
-	To catch this sort of error, a given RCU-protected pointer may be
-	tagged with <tt>__rcu</tt>, after which sparse
-	will complain about simple-assignment accesses to that pointer.
-	Arnd Bergmann made me aware of this requirement, and also
-	supplied the needed
-	<a href="https://lwn.net/Articles/376011/">patch series</a>.
-<li>	Kernels built with <tt>CONFIG_DEBUG_OBJECTS_RCU_HEAD=y</tt>
-	will splat if a data element is passed to <tt>call_rcu()</tt>
-	twice in a row, without a grace period in between.
-	(This error is similar to a double free.)
-	The corresponding <tt>rcu_head</tt> structures that are
-	dynamically allocated are automatically tracked, but
-	<tt>rcu_head</tt> structures allocated on the stack
-	must be initialized with <tt>init_rcu_head_on_stack()</tt>
-	and cleaned up with <tt>destroy_rcu_head_on_stack()</tt>.
-	Similarly, statically allocated non-stack <tt>rcu_head</tt>
-	structures must be initialized with <tt>init_rcu_head()</tt>
-	and cleaned up with <tt>destroy_rcu_head()</tt>.
-	Mathieu Desnoyers made me aware of this requirement, and also
-	supplied the needed
-	<a href="https://lkml.kernel.org/g/20100319013024.GA28456@Krystal">patch</a>.
-<li>	An infinite loop in an RCU read-side critical section will
-	eventually trigger an RCU CPU stall warning splat, with
-	the duration of &ldquo;eventually&rdquo; being controlled by the
-	<tt>RCU_CPU_STALL_TIMEOUT</tt> <tt>Kconfig</tt> option, or,
-	alternatively, by the
-	<tt>rcupdate.rcu_cpu_stall_timeout</tt> boot/sysfs
-	parameter.
-	However, RCU is not obligated to produce this splat
-	unless there is a grace period waiting on that particular
-	RCU read-side critical section.
-	<p>
-	Some extreme workloads might intentionally delay
-	RCU grace periods, and systems running those workloads can
-	be booted with <tt>rcupdate.rcu_cpu_stall_suppress</tt>
-	to suppress the splats.
-	This kernel parameter may also be set via <tt>sysfs</tt>.
-	Furthermore, RCU CPU stall warnings are counter-productive
-	during sysrq dumps and during panics.
-	RCU therefore supplies the <tt>rcu_sysrq_start()</tt> and
-	<tt>rcu_sysrq_end()</tt> API members to be called before
-	and after long sysrq dumps.
-	RCU also supplies the <tt>rcu_panic()</tt> notifier that is
-	automatically invoked at the beginning of a panic to suppress
-	further RCU CPU stall warnings.
-
-	<p>
-	This requirement made itself known in the early 1990s, pretty
-	much the first time that it was necessary to debug a CPU stall.
-	That said, the initial implementation in DYNIX/ptx was quite
-	generic in comparison with that of Linux.
-<li>	Although it would be very good to detect pointers leaking out
-	of RCU read-side critical sections, there is currently no
-	good way of doing this.
-	One complication is the need to distinguish between pointers
-	leaking and pointers that have been handed off from RCU to
-	some other synchronization mechanism, for example, reference
-	counting.
-<li>	In kernels built with <tt>CONFIG_RCU_TRACE=y</tt>, RCU-related
-	information is provided via event tracing.
-<li>	Open-coded use of <tt>rcu_assign_pointer()</tt> and
-	<tt>rcu_dereference()</tt> to create typical linked
-	data structures can be surprisingly error-prone.
-	Therefore, RCU-protected
-	<a href="https://lwn.net/Articles/609973/#RCU List APIs">linked lists</a>
-	and, more recently, RCU-protected
-	<a href="https://lwn.net/Articles/612100/">hash tables</a>
-	are available.
-	Many other special-purpose RCU-protected data structures are
-	available in the Linux kernel and the userspace RCU library.
-<li>	Some linked structures are created at compile time, but still
-	require <tt>__rcu</tt> checking.
-	The <tt>RCU_POINTER_INITIALIZER()</tt> macro serves this
-	purpose.
-<li>	It is not necessary to use <tt>rcu_assign_pointer()</tt>
-	when creating linked structures that are to be published via
-	a single external pointer.
-	The <tt>RCU_INIT_POINTER()</tt> macro is provided for
-	this task and also for assigning <tt>NULL</tt> pointers
-	at runtime.
-</ol>
-
-<p>
-This not a hard-and-fast list:  RCU's diagnostic capabilities will
-continue to be guided by the number and type of usage bugs found
-in real-world RCU usage.
-
-<h2><a name="Linux Kernel Complications">Linux Kernel Complications</a></h2>
-
-<p>
-The Linux kernel provides an interesting environment for all kinds of
-software, including RCU.
-Some of the relevant points of interest are as follows:
-
-<ol>
-<li>	<a href="#Configuration">Configuration</a>.
-<li>	<a href="#Firmware Interface">Firmware Interface</a>.
-<li>	<a href="#Early Boot">Early Boot</a>.
-<li>	<a href="#Interrupts and NMIs">
-	Interrupts and non-maskable interrupts (NMIs)</a>.
-<li>	<a href="#Loadable Modules">Loadable Modules</a>.
-<li>	<a href="#Hotplug CPU">Hotplug CPU</a>.
-<li>	<a href="#Scheduler and RCU">Scheduler and RCU</a>.
-<li>	<a href="#Tracing and RCU">Tracing and RCU</a>.
-<li>	<a href="#Accesses to User Memory and RCU">
-Accesses to User Memory and RCU</a>.
-<li>	<a href="#Energy Efficiency">Energy Efficiency</a>.
-<li>	<a href="#Scheduling-Clock Interrupts and RCU">
-	Scheduling-Clock Interrupts and RCU</a>.
-<li>	<a href="#Memory Efficiency">Memory Efficiency</a>.
-<li>	<a href="#Performance, Scalability, Response Time, and Reliability">
-	Performance, Scalability, Response Time, and Reliability</a>.
-</ol>
-
-<p>
-This list is probably incomplete, but it does give a feel for the
-most notable Linux-kernel complications.
-Each of the following sections covers one of the above topics.
-
-<h3><a name="Configuration">Configuration</a></h3>
-
-<p>
-RCU's goal is automatic configuration, so that almost nobody
-needs to worry about RCU's <tt>Kconfig</tt> options.
-And for almost all users, RCU does in fact work well
-&ldquo;out of the box.&rdquo;
-
-<p>
-However, there are specialized use cases that are handled by
-kernel boot parameters and <tt>Kconfig</tt> options.
-Unfortunately, the <tt>Kconfig</tt> system will explicitly ask users
-about new <tt>Kconfig</tt> options, which requires almost all of them
-be hidden behind a <tt>CONFIG_RCU_EXPERT</tt> <tt>Kconfig</tt> option.
-
-<p>
-This all should be quite obvious, but the fact remains that
-Linus Torvalds recently had to
-<a href="https://lkml.kernel.org/g/CA+55aFy4wcCwaL4okTs8wXhGZ5h-ibecy_Meg9C4MNQrUnwMcg@mail.gmail.com">remind</a>
-me of this requirement.
-
-<h3><a name="Firmware Interface">Firmware Interface</a></h3>
-
-<p>
-In many cases, kernel obtains information about the system from the
-firmware, and sometimes things are lost in translation.
-Or the translation is accurate, but the original message is bogus.
-
-<p>
-For example, some systems' firmware overreports the number of CPUs,
-sometimes by a large factor.
-If RCU naively believed the firmware, as it used to do,
-it would create too many per-CPU kthreads.
-Although the resulting system will still run correctly, the extra
-kthreads needlessly consume memory and can cause confusion
-when they show up in <tt>ps</tt> listings.
-
-<p>
-RCU must therefore wait for a given CPU to actually come online before
-it can allow itself to believe that the CPU actually exists.
-The resulting &ldquo;ghost CPUs&rdquo; (which are never going to
-come online) cause a number of
-<a href="https://paulmck.livejournal.com/37494.html">interesting complications</a>.
-
-<h3><a name="Early Boot">Early Boot</a></h3>
-
-<p>
-The Linux kernel's boot sequence is an interesting process,
-and RCU is used early, even before <tt>rcu_init()</tt>
-is invoked.
-In fact, a number of RCU's primitives can be used as soon as the
-initial task's <tt>task_struct</tt> is available and the
-boot CPU's per-CPU variables are set up.
-The read-side primitives (<tt>rcu_read_lock()</tt>,
-<tt>rcu_read_unlock()</tt>, <tt>rcu_dereference()</tt>,
-and <tt>rcu_access_pointer()</tt>) will operate normally very early on,
-as will <tt>rcu_assign_pointer()</tt>.
-
-<p>
-Although <tt>call_rcu()</tt> may be invoked at any
-time during boot, callbacks are not guaranteed to be invoked until after
-all of RCU's kthreads have been spawned, which occurs at
-<tt>early_initcall()</tt> time.
-This delay in callback invocation is due to the fact that RCU does not
-invoke callbacks until it is fully initialized, and this full initialization
-cannot occur until after the scheduler has initialized itself to the
-point where RCU can spawn and run its kthreads.
-In theory, it would be possible to invoke callbacks earlier,
-however, this is not a panacea because there would be severe restrictions
-on what operations those callbacks could invoke.
-
-<p>
-Perhaps surprisingly, <tt>synchronize_rcu()</tt> and
-<tt>synchronize_rcu_expedited()</tt>,
-will operate normally
-during very early boot, the reason being that there is only one CPU
-and preemption is disabled.
-This means that the call <tt>synchronize_rcu()</tt> (or friends)
-itself is a quiescent
-state and thus a grace period, so the early-boot implementation can
-be a no-op.
-
-<p>
-However, once the scheduler has spawned its first kthread, this early
-boot trick fails for <tt>synchronize_rcu()</tt> (as well as for
-<tt>synchronize_rcu_expedited()</tt>) in <tt>CONFIG_PREEMPT=y</tt>
-kernels.
-The reason is that an RCU read-side critical section might be preempted,
-which means that a subsequent <tt>synchronize_rcu()</tt> really does have
-to wait for something, as opposed to simply returning immediately.
-Unfortunately, <tt>synchronize_rcu()</tt> can't do this until all of
-its kthreads are spawned, which doesn't happen until some time during
-<tt>early_initcalls()</tt> time.
-But this is no excuse:  RCU is nevertheless required to correctly handle
-synchronous grace periods during this time period.
-Once all of its kthreads are up and running, RCU starts running
-normally.
-
-<table>
-<tr><th>&nbsp;</th></tr>
-<tr><th align="left">Quick Quiz:</th></tr>
-<tr><td>
-	How can RCU possibly handle grace periods before all of its
-	kthreads have been spawned???
-</td></tr>
-<tr><th align="left">Answer:</th></tr>
-<tr><td bgcolor="#ffffff"><font color="ffffff">
-	Very carefully!
-	</font>
-
-	<p><font color="ffffff">
-	During the &ldquo;dead zone&rdquo; between the time that the
-	scheduler spawns the first task and the time that all of RCU's
-	kthreads have been spawned, all synchronous grace periods are
-	handled by the expedited grace-period mechanism.
-	At runtime, this expedited mechanism relies on workqueues, but
-	during the dead zone the requesting task itself drives the
-	desired expedited grace period.
-	Because dead-zone execution takes place within task context,
-	everything works.
-	Once the dead zone ends, expedited grace periods go back to
-	using workqueues, as is required to avoid problems that would
-	otherwise occur when a user task received a POSIX signal while
-	driving an expedited grace period.
-	</font>
-
-	<p><font color="ffffff">
-	And yes, this does mean that it is unhelpful to send POSIX
-	signals to random tasks between the time that the scheduler
-	spawns its first kthread and the time that RCU's kthreads
-	have all been spawned.
-	If there ever turns out to be a good reason for sending POSIX
-	signals during that time, appropriate adjustments will be made.
-	(If it turns out that POSIX signals are sent during this time for
-	no good reason, other adjustments will be made, appropriate
-	or otherwise.)
-</font></td></tr>
-<tr><td>&nbsp;</td></tr>
-</table>
-
-<p>
-I learned of these boot-time requirements as a result of a series of
-system hangs.
-
-<h3><a name="Interrupts and NMIs">Interrupts and NMIs</a></h3>
-
-<p>
-The Linux kernel has interrupts, and RCU read-side critical sections are
-legal within interrupt handlers and within interrupt-disabled regions
-of code, as are invocations of <tt>call_rcu()</tt>.
-
-<p>
-Some Linux-kernel architectures can enter an interrupt handler from
-non-idle process context, and then just never leave it, instead stealthily
-transitioning back to process context.
-This trick is sometimes used to invoke system calls from inside the kernel.
-These &ldquo;half-interrupts&rdquo; mean that RCU has to be very careful
-about how it counts interrupt nesting levels.
-I learned of this requirement the hard way during a rewrite
-of RCU's dyntick-idle code.
-
-<p>
-The Linux kernel has non-maskable interrupts (NMIs), and
-RCU read-side critical sections are legal within NMI handlers.
-Thankfully, RCU update-side primitives, including
-<tt>call_rcu()</tt>, are prohibited within NMI handlers.
-
-<p>
-The name notwithstanding, some Linux-kernel architectures
-can have nested NMIs, which RCU must handle correctly.
-Andy Lutomirski
-<a href="https://lkml.kernel.org/r/CALCETrXLq1y7e_dKFPgou-FKHB6Pu-r8+t-6Ds+8=va7anBWDA@mail.gmail.com">surprised me</a>
-with this requirement;
-he also kindly surprised me with
-<a href="https://lkml.kernel.org/r/CALCETrXSY9JpW3uE6H8WYk81sg56qasA2aqmjMPsq5dOtzso=g@mail.gmail.com">an algorithm</a>
-that meets this requirement.
-
-<p>
-Furthermore, NMI handlers can be interrupted by what appear to RCU
-to be normal interrupts.
-One way that this can happen is for code that directly invokes
-<tt>rcu_irq_enter()</tt> and <tt>rcu_irq_exit()</tt> to be called
-from an NMI handler.
-This astonishing fact of life prompted the current code structure,
-which has <tt>rcu_irq_enter()</tt> invoking <tt>rcu_nmi_enter()</tt>
-and <tt>rcu_irq_exit()</tt> invoking <tt>rcu_nmi_exit()</tt>.
-And yes, I also learned of this requirement the hard way.
-
-<h3><a name="Loadable Modules">Loadable Modules</a></h3>
-
-<p>
-The Linux kernel has loadable modules, and these modules can
-also be unloaded.
-After a given module has been unloaded, any attempt to call
-one of its functions results in a segmentation fault.
-The module-unload functions must therefore cancel any
-delayed calls to loadable-module functions, for example,
-any outstanding <tt>mod_timer()</tt> must be dealt with
-via <tt>del_timer_sync()</tt> or similar.
-
-<p>
-Unfortunately, there is no way to cancel an RCU callback;
-once you invoke <tt>call_rcu()</tt>, the callback function is
-eventually going to be invoked, unless the system goes down first.
-Because it is normally considered socially irresponsible to crash the system
-in response to a module unload request, we need some other way
-to deal with in-flight RCU callbacks.
-
-<p>
-RCU therefore provides
-<tt><a href="https://lwn.net/Articles/217484/">rcu_barrier()</a></tt>,
-which waits until all in-flight RCU callbacks have been invoked.
-If a module uses <tt>call_rcu()</tt>, its exit function should therefore
-prevent any future invocation of <tt>call_rcu()</tt>, then invoke
-<tt>rcu_barrier()</tt>.
-In theory, the underlying module-unload code could invoke
-<tt>rcu_barrier()</tt> unconditionally, but in practice this would
-incur unacceptable latencies.
-
-<p>
-Nikita Danilov noted this requirement for an analogous filesystem-unmount
-situation, and Dipankar Sarma incorporated <tt>rcu_barrier()</tt> into RCU.
-The need for <tt>rcu_barrier()</tt> for module unloading became
-apparent later.
-
-<p>
-<b>Important note</b>: The <tt>rcu_barrier()</tt> function is not,
-repeat, <i>not</i>, obligated to wait for a grace period.
-It is instead only required to wait for RCU callbacks that have
-already been posted.
-Therefore, if there are no RCU callbacks posted anywhere in the system,
-<tt>rcu_barrier()</tt> is within its rights to return immediately.
-Even if there are callbacks posted, <tt>rcu_barrier()</tt> does not
-necessarily need to wait for a grace period.
-
-<table>
-<tr><th>&nbsp;</th></tr>
-<tr><th align="left">Quick Quiz:</th></tr>
-<tr><td>
-	Wait a minute!
-	Each RCU callbacks must wait for a grace period to complete,
-	and <tt>rcu_barrier()</tt> must wait for each pre-existing
-	callback to be invoked.
-	Doesn't <tt>rcu_barrier()</tt> therefore need to wait for
-	a full grace period if there is even one callback posted anywhere
-	in the system?
-</td></tr>
-<tr><th align="left">Answer:</th></tr>
-<tr><td bgcolor="#ffffff"><font color="ffffff">
-	Absolutely not!!!
-	</font>
-
-	<p><font color="ffffff">
-	Yes, each RCU callbacks must wait for a grace period to complete,
-	but it might well be partly (or even completely) finished waiting
-	by the time <tt>rcu_barrier()</tt> is invoked.
-	In that case, <tt>rcu_barrier()</tt> need only wait for the
-	remaining portion of the grace period to elapse.
-	So even if there are quite a few callbacks posted,
-	<tt>rcu_barrier()</tt> might well return quite quickly.
-	</font>
-
-	<p><font color="ffffff">
-	So if you need to wait for a grace period as well as for all
-	pre-existing callbacks, you will need to invoke both
-	<tt>synchronize_rcu()</tt> and <tt>rcu_barrier()</tt>.
-	If latency is a concern, you can always use workqueues
-	to invoke them concurrently.
-</font></td></tr>
-<tr><td>&nbsp;</td></tr>
-</table>
-
-<h3><a name="Hotplug CPU">Hotplug CPU</a></h3>
-
-<p>
-The Linux kernel supports CPU hotplug, which means that CPUs
-can come and go.
-It is of course illegal to use any RCU API member from an offline CPU,
-with the exception of <a href="#Sleepable RCU">SRCU</a> read-side
-critical sections.
-This requirement was present from day one in DYNIX/ptx, but
-on the other hand, the Linux kernel's CPU-hotplug implementation
-is &ldquo;interesting.&rdquo;
-
-<p>
-The Linux-kernel CPU-hotplug implementation has notifiers that
-are used to allow the various kernel subsystems (including RCU)
-to respond appropriately to a given CPU-hotplug operation.
-Most RCU operations may be invoked from CPU-hotplug notifiers,
-including even synchronous grace-period operations such as
-<tt>synchronize_rcu()</tt> and <tt>synchronize_rcu_expedited()</tt>.
-
-<p>
-However, all-callback-wait operations such as
-<tt>rcu_barrier()</tt> are also not supported, due to the
-fact that there are phases of CPU-hotplug operations where
-the outgoing CPU's callbacks will not be invoked until after
-the CPU-hotplug operation ends, which could also result in deadlock.
-Furthermore, <tt>rcu_barrier()</tt> blocks CPU-hotplug operations
-during its execution, which results in another type of deadlock
-when invoked from a CPU-hotplug notifier.
-
-<h3><a name="Scheduler and RCU">Scheduler and RCU</a></h3>
-
-<p>
-RCU depends on the scheduler, and the scheduler uses RCU to
-protect some of its data structures.
-The preemptible-RCU <tt>rcu_read_unlock()</tt>
-implementation must therefore be written carefully to avoid deadlocks
-involving the scheduler's runqueue and priority-inheritance locks.
-In particular, <tt>rcu_read_unlock()</tt> must tolerate an
-interrupt where the interrupt handler invokes both
-<tt>rcu_read_lock()</tt> and <tt>rcu_read_unlock()</tt>.
-This possibility requires <tt>rcu_read_unlock()</tt> to use
-negative nesting levels to avoid destructive recursion via
-interrupt handler's use of RCU.
-
-<p>
-This scheduler-RCU requirement came as a
-<a href="https://lwn.net/Articles/453002/">complete surprise</a>.
-
-<p>
-As noted above, RCU makes use of kthreads, and it is necessary to
-avoid excessive CPU-time accumulation by these kthreads.
-This requirement was no surprise, but RCU's violation of it
-when running context-switch-heavy workloads when built with
-<tt>CONFIG_NO_HZ_FULL=y</tt>
-<a href="http://www.rdrop.com/users/paulmck/scalability/paper/BareMetal.2015.01.15b.pdf">did come as a surprise [PDF]</a>.
-RCU has made good progress towards meeting this requirement, even
-for context-switch-heavy <tt>CONFIG_NO_HZ_FULL=y</tt> workloads,
-but there is room for further improvement.
-
-<p>
-It is forbidden to hold any of scheduler's runqueue or priority-inheritance
-spinlocks across an <tt>rcu_read_unlock()</tt> unless interrupts have been
-disabled across the entire RCU read-side critical section, that is,
-up to and including the matching <tt>rcu_read_lock()</tt>.
-Violating this restriction can result in deadlocks involving these
-scheduler spinlocks.
-There was hope that this restriction might be lifted when interrupt-disabled
-calls to <tt>rcu_read_unlock()</tt> started deferring the reporting of
-the resulting RCU-preempt quiescent state until the end of the corresponding
-interrupts-disabled region.
-Unfortunately, timely reporting of the corresponding quiescent state
-to expedited grace periods requires a call to <tt>raise_softirq()</tt>,
-which can acquire these scheduler spinlocks.
-In addition, real-time systems using RCU priority boosting
-need this restriction to remain in effect because deferred
-quiescent-state reporting would also defer deboosting, which in turn
-would degrade real-time latencies.
-
-<p>
-In theory, if a given RCU read-side critical section could be
-guaranteed to be less than one second in duration, holding a scheduler
-spinlock across that critical section's <tt>rcu_read_unlock()</tt>
-would require only that preemption be disabled across the entire
-RCU read-side critical section, not interrupts.
-Unfortunately, given the possibility of vCPU preemption, long-running
-interrupts, and so on, it is not possible in practice to guarantee
-that a given RCU read-side critical section will complete in less than
-one second.
-Therefore, as noted above, if scheduler spinlocks are held across
-a given call to <tt>rcu_read_unlock()</tt>, interrupts must be
-disabled across the entire RCU read-side critical section.
-
-<h3><a name="Tracing and RCU">Tracing and RCU</a></h3>
-
-<p>
-It is possible to use tracing on RCU code, but tracing itself
-uses RCU.
-For this reason, <tt>rcu_dereference_raw_check()</tt>
-is provided for use by tracing, which avoids the destructive
-recursion that could otherwise ensue.
-This API is also used by virtualization in some architectures,
-where RCU readers execute in environments in which tracing
-cannot be used.
-The tracing folks both located the requirement and provided the
-needed fix, so this surprise requirement was relatively painless.
-
-<h3><a name="Accesses to User Memory and RCU">
-Accesses to User Memory and RCU</a></h3>
-
-<p>
-The kernel needs to access user-space memory, for example, to access
-data referenced by system-call parameters.
-The <tt>get_user()</tt> macro does this job.
-
-<p>
-However, user-space memory might well be paged out, which means
-that <tt>get_user()</tt> might well page-fault and thus block while
-waiting for the resulting I/O to complete.
-It would be a very bad thing for the compiler to reorder
-a <tt>get_user()</tt> invocation into an RCU read-side critical
-section.
-For example, suppose that the source code looked like this:
-
-<blockquote>
-<pre>
- 1 rcu_read_lock();
- 2 p = rcu_dereference(gp);
- 3 v = p-&gt;value;
- 4 rcu_read_unlock();
- 5 get_user(user_v, user_p);
- 6 do_something_with(v, user_v);
-</pre>
-</blockquote>
-
-<p>
-The compiler must not be permitted to transform this source code into
-the following:
-
-<blockquote>
-<pre>
- 1 rcu_read_lock();
- 2 p = rcu_dereference(gp);
- 3 get_user(user_v, user_p); // BUG: POSSIBLE PAGE FAULT!!!
- 4 v = p-&gt;value;
- 5 rcu_read_unlock();
- 6 do_something_with(v, user_v);
-</pre>
-</blockquote>
-
-<p>
-If the compiler did make this transformation in a
-<tt>CONFIG_PREEMPT=n</tt> kernel build, and if <tt>get_user()</tt> did
-page fault, the result would be a quiescent state in the middle
-of an RCU read-side critical section.
-This misplaced quiescent state could result in line&nbsp;4 being
-a use-after-free access, which could be bad for your kernel's
-actuarial statistics.
-Similar examples can be constructed with the call to <tt>get_user()</tt>
-preceding the <tt>rcu_read_lock()</tt>.
-
-<p>
-Unfortunately, <tt>get_user()</tt> doesn't have any particular
-ordering properties, and in some architectures the underlying <tt>asm</tt>
-isn't even marked <tt>volatile</tt>.
-And even if it was marked <tt>volatile</tt>, the above access to
-<tt>p-&gt;value</tt> is not volatile, so the compiler would not have any
-reason to keep those two accesses in order.
-
-<p>
-Therefore, the Linux-kernel definitions of <tt>rcu_read_lock()</tt>
-and <tt>rcu_read_unlock()</tt> must act as compiler barriers,
-at least for outermost instances of <tt>rcu_read_lock()</tt> and
-<tt>rcu_read_unlock()</tt> within a nested set of RCU read-side critical
-sections.
-
-<h3><a name="Energy Efficiency">Energy Efficiency</a></h3>
-
-<p>
-Interrupting idle CPUs is considered socially unacceptable,
-especially by people with battery-powered embedded systems.
-RCU therefore conserves energy by detecting which CPUs are
-idle, including tracking CPUs that have been interrupted from idle.
-This is a large part of the energy-efficiency requirement,
-so I learned of this via an irate phone call.
-
-<p>
-Because RCU avoids interrupting idle CPUs, it is illegal to
-execute an RCU read-side critical section on an idle CPU.
-(Kernels built with <tt>CONFIG_PROVE_RCU=y</tt> will splat
-if you try it.)
-The <tt>RCU_NONIDLE()</tt> macro and <tt>_rcuidle</tt>
-event tracing is provided to work around this restriction.
-In addition, <tt>rcu_is_watching()</tt> may be used to
-test whether or not it is currently legal to run RCU read-side
-critical sections on this CPU.
-I learned of the need for diagnostics on the one hand
-and <tt>RCU_NONIDLE()</tt> on the other while inspecting
-idle-loop code.
-Steven Rostedt supplied <tt>_rcuidle</tt> event tracing,
-which is used quite heavily in the idle loop.
-However, there are some restrictions on the code placed within
-<tt>RCU_NONIDLE()</tt>:
-
-<ol>
-<li>	Blocking is prohibited.
-	In practice, this is not a serious restriction given that idle
-	tasks are prohibited from blocking to begin with.
-<li>	Although nesting <tt>RCU_NONIDLE()</tt> is permitted, they cannot
-	nest indefinitely deeply.
-	However, given that they can be nested on the order of a million
-	deep, even on 32-bit systems, this should not be a serious
-	restriction.
-	This nesting limit would probably be reached long after the
-	compiler OOMed or the stack overflowed.
-<li>	Any code path that enters <tt>RCU_NONIDLE()</tt> must sequence
-	out of that same <tt>RCU_NONIDLE()</tt>.
-	For example, the following is grossly illegal:
-
-	<blockquote>
-	<pre>
- 1     RCU_NONIDLE({
- 2       do_something();
- 3       goto bad_idea;  /* BUG!!! */
- 4       do_something_else();});
- 5   bad_idea:
-	</pre>
-	</blockquote>
-
-	<p>
-	It is just as illegal to transfer control into the middle of
-	<tt>RCU_NONIDLE()</tt>'s argument.
-	Yes, in theory, you could transfer in as long as you also
-	transferred out, but in practice you could also expect to get sharply
-	worded review comments.
-</ol>
-
-<p>
-It is similarly socially unacceptable to interrupt an
-<tt>nohz_full</tt> CPU running in userspace.
-RCU must therefore track <tt>nohz_full</tt> userspace
-execution.
-RCU must therefore be able to sample state at two points in
-time, and be able to determine whether or not some other CPU spent
-any time idle and/or executing in userspace.
-
-<p>
-These energy-efficiency requirements have proven quite difficult to
-understand and to meet, for example, there have been more than five
-clean-sheet rewrites of RCU's energy-efficiency code, the last of
-which was finally able to demonstrate
-<a href="http://www.rdrop.com/users/paulmck/realtime/paper/AMPenergy.2013.04.19a.pdf">real energy savings running on real hardware [PDF]</a>.
-As noted earlier,
-I learned of many of these requirements via angry phone calls:
-Flaming me on the Linux-kernel mailing list was apparently not
-sufficient to fully vent their ire at RCU's energy-efficiency bugs!
-
-<h3><a name="Scheduling-Clock Interrupts and RCU">
-Scheduling-Clock Interrupts and RCU</a></h3>
-
-<p>
-The kernel transitions between in-kernel non-idle execution, userspace
-execution, and the idle loop.
-Depending on kernel configuration, RCU handles these states differently:
-
-<table border=3>
-<tr><th><tt>HZ</tt> Kconfig</th>
-	<th>In-Kernel</th>
-		<th>Usermode</th>
-			<th>Idle</th></tr>
-<tr><th align="left"><tt>HZ_PERIODIC</tt></th>
-	<td>Can rely on scheduling-clock interrupt.</td>
-		<td>Can rely on scheduling-clock interrupt and its
-		    detection of interrupt from usermode.</td>
-			<td>Can rely on RCU's dyntick-idle detection.</td></tr>
-<tr><th align="left"><tt>NO_HZ_IDLE</tt></th>
-	<td>Can rely on scheduling-clock interrupt.</td>
-		<td>Can rely on scheduling-clock interrupt and its
-		    detection of interrupt from usermode.</td>
-			<td>Can rely on RCU's dyntick-idle detection.</td></tr>
-<tr><th align="left"><tt>NO_HZ_FULL</tt></th>
-	<td>Can only sometimes rely on scheduling-clock interrupt.
-	    In other cases, it is necessary to bound kernel execution
-	    times and/or use IPIs.</td>
-		<td>Can rely on RCU's dyntick-idle detection.</td>
-			<td>Can rely on RCU's dyntick-idle detection.</td></tr>
-</table>
-
-<table>
-<tr><th>&nbsp;</th></tr>
-<tr><th align="left">Quick Quiz:</th></tr>
-<tr><td>
-	Why can't <tt>NO_HZ_FULL</tt> in-kernel execution rely on the
-	scheduling-clock interrupt, just like <tt>HZ_PERIODIC</tt>
-	and <tt>NO_HZ_IDLE</tt> do?
-</td></tr>
-<tr><th align="left">Answer:</th></tr>
-<tr><td bgcolor="#ffffff"><font color="ffffff">
-	Because, as a performance optimization, <tt>NO_HZ_FULL</tt>
-	does not necessarily re-enable the scheduling-clock interrupt
-	on entry to each and every system call.
-</font></td></tr>
-<tr><td>&nbsp;</td></tr>
-</table>
-
-<p>
-However, RCU must be reliably informed as to whether any given
-CPU is currently in the idle loop, and, for <tt>NO_HZ_FULL</tt>,
-also whether that CPU is executing in usermode, as discussed
-<a href="#Energy Efficiency">earlier</a>.
-It also requires that the scheduling-clock interrupt be enabled when
-RCU needs it to be:
-
-<ol>
-<li>	If a CPU is either idle or executing in usermode, and RCU believes
-	it is non-idle, the scheduling-clock tick had better be running.
-	Otherwise, you will get RCU CPU stall warnings.  Or at best,
-	very long (11-second) grace periods, with a pointless IPI waking
-	the CPU from time to time.
-<li>	If a CPU is in a portion of the kernel that executes RCU read-side
-	critical sections, and RCU believes this CPU to be idle, you will get
-	random memory corruption.  <b>DON'T DO THIS!!!</b>
-
-	<br>This is one reason to test with lockdep, which will complain
-	about this sort of thing.
-<li>	If a CPU is in a portion of the kernel that is absolutely
-	positively no-joking guaranteed to never execute any RCU read-side
-	critical sections, and RCU believes this CPU to to be idle,
-	no problem.  This sort of thing is used by some architectures
-	for light-weight exception handlers, which can then avoid the
-	overhead of <tt>rcu_irq_enter()</tt> and <tt>rcu_irq_exit()</tt>
-	at exception entry and exit, respectively.
-	Some go further and avoid the entireties of <tt>irq_enter()</tt>
-	and <tt>irq_exit()</tt>.
-
-	<br>Just make very sure you are running some of your tests with
-	<tt>CONFIG_PROVE_RCU=y</tt>, just in case one of your code paths
-	was in fact joking about not doing RCU read-side critical sections.
-<li>	If a CPU is executing in the kernel with the scheduling-clock
-	interrupt disabled and RCU believes this CPU to be non-idle,
-	and if the CPU goes idle (from an RCU perspective) every few
-	jiffies, no problem.  It is usually OK for there to be the
-	occasional gap between idle periods of up to a second or so.
-
-	<br>If the gap grows too long, you get RCU CPU stall warnings.
-<li>	If a CPU is either idle or executing in usermode, and RCU believes
-	it to be idle, of course no problem.
-<li>	If a CPU is executing in the kernel, the kernel code
-	path is passing through quiescent states at a reasonable
-	frequency (preferably about once per few jiffies, but the
-	occasional excursion to a second or so is usually OK) and the
-	scheduling-clock interrupt is enabled, of course no problem.
-
-	<br>If the gap between a successive pair of quiescent states grows
-	too long, you get RCU CPU stall warnings.
-</ol>
-
-<table>
-<tr><th>&nbsp;</th></tr>
-<tr><th align="left">Quick Quiz:</th></tr>
-<tr><td>
-	But what if my driver has a hardware interrupt handler
-	that can run for many seconds?
-	I cannot invoke <tt>schedule()</tt> from an hardware
-	interrupt handler, after all!
-</td></tr>
-<tr><th align="left">Answer:</th></tr>
-<tr><td bgcolor="#ffffff"><font color="ffffff">
-	One approach is to do <tt>rcu_irq_exit();rcu_irq_enter();</tt>
-	every so often.
-	But given that long-running interrupt handlers can cause
-	other problems, not least for response time, shouldn't you
-	work to keep your interrupt handler's runtime within reasonable
-	bounds?
-</font></td></tr>
-<tr><td>&nbsp;</td></tr>
-</table>
-
-<p>
-But as long as RCU is properly informed of kernel state transitions between
-in-kernel execution, usermode execution, and idle, and as long as the
-scheduling-clock interrupt is enabled when RCU needs it to be, you
-can rest assured that the bugs you encounter will be in some other
-part of RCU or some other part of the kernel!
-
-<h3><a name="Memory Efficiency">Memory Efficiency</a></h3>
-
-<p>
-Although small-memory non-realtime systems can simply use Tiny RCU,
-code size is only one aspect of memory efficiency.
-Another aspect is the size of the <tt>rcu_head</tt> structure
-used by <tt>call_rcu()</tt> and <tt>kfree_rcu()</tt>.
-Although this structure contains nothing more than a pair of pointers,
-it does appear in many RCU-protected data structures, including
-some that are size critical.
-The <tt>page</tt> structure is a case in point, as evidenced by
-the many occurrences of the <tt>union</tt> keyword within that structure.
-
-<p>
-This need for memory efficiency is one reason that RCU uses hand-crafted
-singly linked lists to track the <tt>rcu_head</tt> structures that
-are waiting for a grace period to elapse.
-It is also the reason why <tt>rcu_head</tt> structures do not contain
-debug information, such as fields tracking the file and line of the
-<tt>call_rcu()</tt> or <tt>kfree_rcu()</tt> that posted them.
-Although this information might appear in debug-only kernel builds at some
-point, in the meantime, the <tt>-&gt;func</tt> field will often provide
-the needed debug information.
-
-<p>
-However, in some cases, the need for memory efficiency leads to even
-more extreme measures.
-Returning to the <tt>page</tt> structure, the <tt>rcu_head</tt> field
-shares storage with a great many other structures that are used at
-various points in the corresponding page's lifetime.
-In order to correctly resolve certain
-<a href="https://lkml.kernel.org/g/1439976106-137226-1-git-send-email-kirill.shutemov@linux.intel.com">race conditions</a>,
-the Linux kernel's memory-management subsystem needs a particular bit
-to remain zero during all phases of grace-period processing,
-and that bit happens to map to the bottom bit of the
-<tt>rcu_head</tt> structure's <tt>-&gt;next</tt> field.
-RCU makes this guarantee as long as <tt>call_rcu()</tt>
-is used to post the callback, as opposed to <tt>kfree_rcu()</tt>
-or some future &ldquo;lazy&rdquo;
-variant of <tt>call_rcu()</tt> that might one day be created for
-energy-efficiency purposes.
-
-<p>
-That said, there are limits.
-RCU requires that the <tt>rcu_head</tt> structure be aligned to a
-two-byte boundary, and passing a misaligned <tt>rcu_head</tt>
-structure to one of the <tt>call_rcu()</tt> family of functions
-will result in a splat.
-It is therefore necessary to exercise caution when packing
-structures containing fields of type <tt>rcu_head</tt>.
-Why not a four-byte or even eight-byte alignment requirement?
-Because the m68k architecture provides only two-byte alignment,
-and thus acts as alignment's least common denominator.
-
-<p>
-The reason for reserving the bottom bit of pointers to
-<tt>rcu_head</tt> structures is to leave the door open to
-&ldquo;lazy&rdquo; callbacks whose invocations can safely be deferred.
-Deferring invocation could potentially have energy-efficiency
-benefits, but only if the rate of non-lazy callbacks decreases
-significantly for some important workload.
-In the meantime, reserving the bottom bit keeps this option open
-in case it one day becomes useful.
-
-<h3><a name="Performance, Scalability, Response Time, and Reliability">
-Performance, Scalability, Response Time, and Reliability</a></h3>
-
-<p>
-Expanding on the
-<a href="#Performance and Scalability">earlier discussion</a>,
-RCU is used heavily by hot code paths in performance-critical
-portions of the Linux kernel's networking, security, virtualization,
-and scheduling code paths.
-RCU must therefore use efficient implementations, especially in its
-read-side primitives.
-To that end, it would be good if preemptible RCU's implementation
-of <tt>rcu_read_lock()</tt> could be inlined, however, doing
-this requires resolving <tt>#include</tt> issues with the
-<tt>task_struct</tt> structure.
-
-<p>
-The Linux kernel supports hardware configurations with up to
-4096 CPUs, which means that RCU must be extremely scalable.
-Algorithms that involve frequent acquisitions of global locks or
-frequent atomic operations on global variables simply cannot be
-tolerated within the RCU implementation.
-RCU therefore makes heavy use of a combining tree based on the
-<tt>rcu_node</tt> structure.
-RCU is required to tolerate all CPUs continuously invoking any
-combination of RCU's runtime primitives with minimal per-operation
-overhead.
-In fact, in many cases, increasing load must <i>decrease</i> the
-per-operation overhead, witness the batching optimizations for
-<tt>synchronize_rcu()</tt>, <tt>call_rcu()</tt>,
-<tt>synchronize_rcu_expedited()</tt>, and <tt>rcu_barrier()</tt>.
-As a general rule, RCU must cheerfully accept whatever the
-rest of the Linux kernel decides to throw at it.
-
-<p>
-The Linux kernel is used for real-time workloads, especially
-in conjunction with the
-<a href="https://rt.wiki.kernel.org/index.php/Main_Page">-rt patchset</a>.
-The real-time-latency response requirements are such that the
-traditional approach of disabling preemption across RCU
-read-side critical sections is inappropriate.
-Kernels built with <tt>CONFIG_PREEMPT=y</tt> therefore
-use an RCU implementation that allows RCU read-side critical
-sections to be preempted.
-This requirement made its presence known after users made it
-clear that an earlier
-<a href="https://lwn.net/Articles/107930/">real-time patch</a>
-did not meet their needs, in conjunction with some
-<a href="https://lkml.kernel.org/g/20050318002026.GA2693@us.ibm.com">RCU issues</a>
-encountered by a very early version of the -rt patchset.
-
-<p>
-In addition, RCU must make do with a sub-100-microsecond real-time latency
-budget.
-In fact, on smaller systems with the -rt patchset, the Linux kernel
-provides sub-20-microsecond real-time latencies for the whole kernel,
-including RCU.
-RCU's scalability and latency must therefore be sufficient for
-these sorts of configurations.
-To my surprise, the sub-100-microsecond real-time latency budget
-<a href="http://www.rdrop.com/users/paulmck/realtime/paper/bigrt.2013.01.31a.LCA.pdf">
-applies to even the largest systems [PDF]</a>,
-up to and including systems with 4096 CPUs.
-This real-time requirement motivated the grace-period kthread, which
-also simplified handling of a number of race conditions.
-
-<p>
-RCU must avoid degrading real-time response for CPU-bound threads, whether
-executing in usermode (which is one use case for
-<tt>CONFIG_NO_HZ_FULL=y</tt>) or in the kernel.
-That said, CPU-bound loops in the kernel must execute
-<tt>cond_resched()</tt> at least once per few tens of milliseconds
-in order to avoid receiving an IPI from RCU.
-
-<p>
-Finally, RCU's status as a synchronization primitive means that
-any RCU failure can result in arbitrary memory corruption that can be
-extremely difficult to debug.
-This means that RCU must be extremely reliable, which in
-practice also means that RCU must have an aggressive stress-test
-suite.
-This stress-test suite is called <tt>rcutorture</tt>.
-
-<p>
-Although the need for <tt>rcutorture</tt> was no surprise,
-the current immense popularity of the Linux kernel is posing
-interesting&mdash;and perhaps unprecedented&mdash;validation
-challenges.
-To see this, keep in mind that there are well over one billion
-instances of the Linux kernel running today, given Android
-smartphones, Linux-powered televisions, and servers.
-This number can be expected to increase sharply with the advent of
-the celebrated Internet of Things.
-
-<p>
-Suppose that RCU contains a race condition that manifests on average
-once per million years of runtime.
-This bug will be occurring about three times per <i>day</i> across
-the installed base.
-RCU could simply hide behind hardware error rates, given that no one
-should really expect their smartphone to last for a million years.
-However, anyone taking too much comfort from this thought should
-consider the fact that in most jurisdictions, a successful multi-year
-test of a given mechanism, which might include a Linux kernel,
-suffices for a number of types of safety-critical certifications.
-In fact, rumor has it that the Linux kernel is already being used
-in production for safety-critical applications.
-I don't know about you, but I would feel quite bad if a bug in RCU
-killed someone.
-Which might explain my recent focus on validation and verification.
-
-<h2><a name="Other RCU Flavors">Other RCU Flavors</a></h2>
-
-<p>
-One of the more surprising things about RCU is that there are now
-no fewer than five <i>flavors</i>, or API families.
-In addition, the primary flavor that has been the sole focus up to
-this point has two different implementations, non-preemptible and
-preemptible.
-The other four flavors are listed below, with requirements for each
-described in a separate section.
-
-<ol>
-<li>	<a href="#Bottom-Half Flavor">Bottom-Half Flavor (Historical)</a>
-<li>	<a href="#Sched Flavor">Sched Flavor (Historical)</a>
-<li>	<a href="#Sleepable RCU">Sleepable RCU</a>
-<li>	<a href="#Tasks RCU">Tasks RCU</a>
-</ol>
-
-<h3><a name="Bottom-Half Flavor">Bottom-Half Flavor (Historical)</a></h3>
-
-<p>
-The RCU-bh flavor of RCU has since been expressed in terms of
-the other RCU flavors as part of a consolidation of the three
-flavors into a single flavor.
-The read-side API remains, and continues to disable softirq and to
-be accounted for by lockdep.
-Much of the material in this section is therefore strictly historical
-in nature.
-
-<p>
-The softirq-disable (AKA &ldquo;bottom-half&rdquo;,
-hence the &ldquo;_bh&rdquo; abbreviations)
-flavor of RCU, or <i>RCU-bh</i>, was developed by
-Dipankar Sarma to provide a flavor of RCU that could withstand the
-network-based denial-of-service attacks researched by Robert
-Olsson.
-These attacks placed so much networking load on the system
-that some of the CPUs never exited softirq execution,
-which in turn prevented those CPUs from ever executing a context switch,
-which, in the RCU implementation of that time, prevented grace periods
-from ever ending.
-The result was an out-of-memory condition and a system hang.
-
-<p>
-The solution was the creation of RCU-bh, which does
-<tt>local_bh_disable()</tt>
-across its read-side critical sections, and which uses the transition
-from one type of softirq processing to another as a quiescent state
-in addition to context switch, idle, user mode, and offline.
-This means that RCU-bh grace periods can complete even when some of
-the CPUs execute in softirq indefinitely, thus allowing algorithms
-based on RCU-bh to withstand network-based denial-of-service attacks.
-
-<p>
-Because
-<tt>rcu_read_lock_bh()</tt> and <tt>rcu_read_unlock_bh()</tt>
-disable and re-enable softirq handlers, any attempt to start a softirq
-handlers during the
-RCU-bh read-side critical section will be deferred.
-In this case, <tt>rcu_read_unlock_bh()</tt>
-will invoke softirq processing, which can take considerable time.
-One can of course argue that this softirq overhead should be associated
-with the code following the RCU-bh read-side critical section rather
-than <tt>rcu_read_unlock_bh()</tt>, but the fact
-is that most profiling tools cannot be expected to make this sort
-of fine distinction.
-For example, suppose that a three-millisecond-long RCU-bh read-side
-critical section executes during a time of heavy networking load.
-There will very likely be an attempt to invoke at least one softirq
-handler during that three milliseconds, but any such invocation will
-be delayed until the time of the <tt>rcu_read_unlock_bh()</tt>.
-This can of course make it appear at first glance as if
-<tt>rcu_read_unlock_bh()</tt> was executing very slowly.
-
-<p>
-The
-<a href="https://lwn.net/Articles/609973/#RCU Per-Flavor API Table">RCU-bh API</a>
-includes
-<tt>rcu_read_lock_bh()</tt>,
-<tt>rcu_read_unlock_bh()</tt>,
-<tt>rcu_dereference_bh()</tt>,
-<tt>rcu_dereference_bh_check()</tt>,
-<tt>synchronize_rcu_bh()</tt>,
-<tt>synchronize_rcu_bh_expedited()</tt>,
-<tt>call_rcu_bh()</tt>,
-<tt>rcu_barrier_bh()</tt>, and
-<tt>rcu_read_lock_bh_held()</tt>.
-However, the update-side APIs are now simple wrappers for other RCU
-flavors, namely RCU-sched in CONFIG_PREEMPT=n kernels and RCU-preempt
-otherwise.
-
-<h3><a name="Sched Flavor">Sched Flavor (Historical)</a></h3>
-
-<p>
-The RCU-sched flavor of RCU has since been expressed in terms of
-the other RCU flavors as part of a consolidation of the three
-flavors into a single flavor.
-The read-side API remains, and continues to disable preemption and to
-be accounted for by lockdep.
-Much of the material in this section is therefore strictly historical
-in nature.
-
-<p>
-Before preemptible RCU, waiting for an RCU grace period had the
-side effect of also waiting for all pre-existing interrupt
-and NMI handlers.
-However, there are legitimate preemptible-RCU implementations that
-do not have this property, given that any point in the code outside
-of an RCU read-side critical section can be a quiescent state.
-Therefore, <i>RCU-sched</i> was created, which follows &ldquo;classic&rdquo;
-RCU in that an RCU-sched grace period waits for for pre-existing
-interrupt and NMI handlers.
-In kernels built with <tt>CONFIG_PREEMPT=n</tt>, the RCU and RCU-sched
-APIs have identical implementations, while kernels built with
-<tt>CONFIG_PREEMPT=y</tt> provide a separate implementation for each.
-
-<p>
-Note well that in <tt>CONFIG_PREEMPT=y</tt> kernels,
-<tt>rcu_read_lock_sched()</tt> and <tt>rcu_read_unlock_sched()</tt>
-disable and re-enable preemption, respectively.
-This means that if there was a preemption attempt during the
-RCU-sched read-side critical section, <tt>rcu_read_unlock_sched()</tt>
-will enter the scheduler, with all the latency and overhead entailed.
-Just as with <tt>rcu_read_unlock_bh()</tt>, this can make it look
-as if <tt>rcu_read_unlock_sched()</tt> was executing very slowly.
-However, the highest-priority task won't be preempted, so that task
-will enjoy low-overhead <tt>rcu_read_unlock_sched()</tt> invocations.
-
-<p>
-The
-<a href="https://lwn.net/Articles/609973/#RCU Per-Flavor API Table">RCU-sched API</a>
-includes
-<tt>rcu_read_lock_sched()</tt>,
-<tt>rcu_read_unlock_sched()</tt>,
-<tt>rcu_read_lock_sched_notrace()</tt>,
-<tt>rcu_read_unlock_sched_notrace()</tt>,
-<tt>rcu_dereference_sched()</tt>,
-<tt>rcu_dereference_sched_check()</tt>,
-<tt>synchronize_sched()</tt>,
-<tt>synchronize_rcu_sched_expedited()</tt>,
-<tt>call_rcu_sched()</tt>,
-<tt>rcu_barrier_sched()</tt>, and
-<tt>rcu_read_lock_sched_held()</tt>.
-However, anything that disables preemption also marks an RCU-sched
-read-side critical section, including
-<tt>preempt_disable()</tt> and <tt>preempt_enable()</tt>,
-<tt>local_irq_save()</tt> and <tt>local_irq_restore()</tt>,
-and so on.
-
-<h3><a name="Sleepable RCU">Sleepable RCU</a></h3>
-
-<p>
-For well over a decade, someone saying &ldquo;I need to block within
-an RCU read-side critical section&rdquo; was a reliable indication
-that this someone did not understand RCU.
-After all, if you are always blocking in an RCU read-side critical
-section, you can probably afford to use a higher-overhead synchronization
-mechanism.
-However, that changed with the advent of the Linux kernel's notifiers,
-whose RCU read-side critical
-sections almost never sleep, but sometimes need to.
-This resulted in the introduction of
-<a href="https://lwn.net/Articles/202847/">sleepable RCU</a>,
-or <i>SRCU</i>.
-
-<p>
-SRCU allows different domains to be defined, with each such domain
-defined by an instance of an <tt>srcu_struct</tt> structure.
-A pointer to this structure must be passed in to each SRCU function,
-for example, <tt>synchronize_srcu(&amp;ss)</tt>, where
-<tt>ss</tt> is the <tt>srcu_struct</tt> structure.
-The key benefit of these domains is that a slow SRCU reader in one
-domain does not delay an SRCU grace period in some other domain.
-That said, one consequence of these domains is that read-side code
-must pass a &ldquo;cookie&rdquo; from <tt>srcu_read_lock()</tt>
-to <tt>srcu_read_unlock()</tt>, for example, as follows:
-
-<blockquote>
-<pre>
- 1 int idx;
- 2
- 3 idx = srcu_read_lock(&amp;ss);
- 4 do_something();
- 5 srcu_read_unlock(&amp;ss, idx);
-</pre>
-</blockquote>
-
-<p>
-As noted above, it is legal to block within SRCU read-side critical sections,
-however, with great power comes great responsibility.
-If you block forever in one of a given domain's SRCU read-side critical
-sections, then that domain's grace periods will also be blocked forever.
-Of course, one good way to block forever is to deadlock, which can
-happen if any operation in a given domain's SRCU read-side critical
-section can wait, either directly or indirectly, for that domain's
-grace period to elapse.
-For example, this results in a self-deadlock:
-
-<blockquote>
-<pre>
- 1 int idx;
- 2
- 3 idx = srcu_read_lock(&amp;ss);
- 4 do_something();
- 5 synchronize_srcu(&amp;ss);
- 6 srcu_read_unlock(&amp;ss, idx);
-</pre>
-</blockquote>
-
-<p>
-However, if line&nbsp;5 acquired a mutex that was held across
-a <tt>synchronize_srcu()</tt> for domain <tt>ss</tt>,
-deadlock would still be possible.
-Furthermore, if line&nbsp;5 acquired a mutex that was held across
-a <tt>synchronize_srcu()</tt> for some other domain <tt>ss1</tt>,
-and if an <tt>ss1</tt>-domain SRCU read-side critical section
-acquired another mutex that was held across as <tt>ss</tt>-domain
-<tt>synchronize_srcu()</tt>,
-deadlock would again be possible.
-Such a deadlock cycle could extend across an arbitrarily large number
-of different SRCU domains.
-Again, with great power comes great responsibility.
-
-<p>
-Unlike the other RCU flavors, SRCU read-side critical sections can
-run on idle and even offline CPUs.
-This ability requires that <tt>srcu_read_lock()</tt> and
-<tt>srcu_read_unlock()</tt> contain memory barriers, which means
-that SRCU readers will run a bit slower than would RCU readers.
-It also motivates the <tt>smp_mb__after_srcu_read_unlock()</tt>
-API, which, in combination with <tt>srcu_read_unlock()</tt>,
-guarantees a full memory barrier.
-
-<p>
-Also unlike other RCU flavors, <tt>synchronize_srcu()</tt> may <b>not</b>
-be invoked from CPU-hotplug notifiers, due to the fact that SRCU grace
-periods make use of timers and the possibility of timers being temporarily
-&ldquo;stranded&rdquo; on the outgoing CPU.
-This stranding of timers means that timers posted to the outgoing CPU
-will not fire until late in the CPU-hotplug process.
-The problem is that if a notifier is waiting on an SRCU grace period,
-that grace period is waiting on a timer, and that timer is stranded on the
-outgoing CPU, then the notifier will never be awakened, in other words,
-deadlock has occurred.
-This same situation of course also prohibits <tt>srcu_barrier()</tt>
-from being invoked from CPU-hotplug notifiers.
-
-<p>
-SRCU also differs from other RCU flavors in that SRCU's expedited and
-non-expedited grace periods are implemented by the same mechanism.
-This means that in the current SRCU implementation, expediting a
-future grace period has the side effect of expediting all prior
-grace periods that have not yet completed.
-(But please note that this is a property of the current implementation,
-not necessarily of future implementations.)
-In addition, if SRCU has been idle for longer than the interval
-specified by the <tt>srcutree.exp_holdoff</tt> kernel boot parameter
-(25&nbsp;microseconds by default),
-and if a <tt>synchronize_srcu()</tt> invocation ends this idle period,
-that invocation will be automatically expedited.
-
-<p>
-As of v4.12, SRCU's callbacks are maintained per-CPU, eliminating
-a locking bottleneck present in prior kernel versions.
-Although this will allow users to put much heavier stress on
-<tt>call_srcu()</tt>, it is important to note that SRCU does not
-yet take any special steps to deal with callback flooding.
-So if you are posting (say) 10,000 SRCU callbacks per second per CPU,
-you are probably totally OK, but if you intend to post (say) 1,000,000
-SRCU callbacks per second per CPU, please run some tests first.
-SRCU just might need a few adjustment to deal with that sort of load.
-Of course, your mileage may vary based on the speed of your CPUs and
-the size of your memory.
-
-<p>
-The
-<a href="https://lwn.net/Articles/609973/#RCU Per-Flavor API Table">SRCU API</a>
-includes
-<tt>srcu_read_lock()</tt>,
-<tt>srcu_read_unlock()</tt>,
-<tt>srcu_dereference()</tt>,
-<tt>srcu_dereference_check()</tt>,
-<tt>synchronize_srcu()</tt>,
-<tt>synchronize_srcu_expedited()</tt>,
-<tt>call_srcu()</tt>,
-<tt>srcu_barrier()</tt>, and
-<tt>srcu_read_lock_held()</tt>.
-It also includes
-<tt>DEFINE_SRCU()</tt>,
-<tt>DEFINE_STATIC_SRCU()</tt>, and
-<tt>init_srcu_struct()</tt>
-APIs for defining and initializing <tt>srcu_struct</tt> structures.
-
-<h3><a name="Tasks RCU">Tasks RCU</a></h3>
-
-<p>
-Some forms of tracing use &ldquo;trampolines&rdquo; to handle the
-binary rewriting required to install different types of probes.
-It would be good to be able to free old trampolines, which sounds
-like a job for some form of RCU.
-However, because it is necessary to be able to install a trace
-anywhere in the code, it is not possible to use read-side markers
-such as <tt>rcu_read_lock()</tt> and <tt>rcu_read_unlock()</tt>.
-In addition, it does not work to have these markers in the trampoline
-itself, because there would need to be instructions following
-<tt>rcu_read_unlock()</tt>.
-Although <tt>synchronize_rcu()</tt> would guarantee that execution
-reached the <tt>rcu_read_unlock()</tt>, it would not be able to
-guarantee that execution had completely left the trampoline.
-
-<p>
-The solution, in the form of
-<a href="https://lwn.net/Articles/607117/"><i>Tasks RCU</i></a>,
-is to have implicit
-read-side critical sections that are delimited by voluntary context
-switches, that is, calls to <tt>schedule()</tt>,
-<tt>cond_resched()</tt>, and
-<tt>synchronize_rcu_tasks()</tt>.
-In addition, transitions to and from userspace execution also delimit
-tasks-RCU read-side critical sections.
-
-<p>
-The tasks-RCU API is quite compact, consisting only of
-<tt>call_rcu_tasks()</tt>,
-<tt>synchronize_rcu_tasks()</tt>, and
-<tt>rcu_barrier_tasks()</tt>.
-In <tt>CONFIG_PREEMPT=n</tt> kernels, trampolines cannot be preempted,
-so these APIs map to
-<tt>call_rcu()</tt>,
-<tt>synchronize_rcu()</tt>, and
-<tt>rcu_barrier()</tt>, respectively.
-In <tt>CONFIG_PREEMPT=y</tt> kernels, trampolines can be preempted,
-and these three APIs are therefore implemented by separate functions
-that check for voluntary context switches.
-
-<h2><a name="Possible Future Changes">Possible Future Changes</a></h2>
-
-<p>
-One of the tricks that RCU uses to attain update-side scalability is
-to increase grace-period latency with increasing numbers of CPUs.
-If this becomes a serious problem, it will be necessary to rework the
-grace-period state machine so as to avoid the need for the additional
-latency.
-
-<p>
-RCU disables CPU hotplug in a few places, perhaps most notably in the
-<tt>rcu_barrier()</tt> operations.
-If there is a strong reason to use <tt>rcu_barrier()</tt> in CPU-hotplug
-notifiers, it will be necessary to avoid disabling CPU hotplug.
-This would introduce some complexity, so there had better be a <i>very</i>
-good reason.
-
-<p>
-The tradeoff between grace-period latency on the one hand and interruptions
-of other CPUs on the other hand may need to be re-examined.
-The desire is of course for zero grace-period latency as well as zero
-interprocessor interrupts undertaken during an expedited grace period
-operation.
-While this ideal is unlikely to be achievable, it is quite possible that
-further improvements can be made.
-
-<p>
-The multiprocessor implementations of RCU use a combining tree that
-groups CPUs so as to reduce lock contention and increase cache locality.
-However, this combining tree does not spread its memory across NUMA
-nodes nor does it align the CPU groups with hardware features such
-as sockets or cores.
-Such spreading and alignment is currently believed to be unnecessary
-because the hotpath read-side primitives do not access the combining
-tree, nor does <tt>call_rcu()</tt> in the common case.
-If you believe that your architecture needs such spreading and alignment,
-then your architecture should also benefit from the
-<tt>rcutree.rcu_fanout_leaf</tt> boot parameter, which can be set
-to the number of CPUs in a socket, NUMA node, or whatever.
-If the number of CPUs is too large, use a fraction of the number of
-CPUs.
-If the number of CPUs is a large prime number, well, that certainly
-is an &ldquo;interesting&rdquo; architectural choice!
-More flexible arrangements might be considered, but only if
-<tt>rcutree.rcu_fanout_leaf</tt> has proven inadequate, and only
-if the inadequacy has been demonstrated by a carefully run and
-realistic system-level workload.
-
-<p>
-Please note that arrangements that require RCU to remap CPU numbers will
-require extremely good demonstration of need and full exploration of
-alternatives.
-
-<p>
-RCU's various kthreads are reasonably recent additions.
-It is quite likely that adjustments will be required to more gracefully
-handle extreme loads.
-It might also be necessary to be able to relate CPU utilization by
-RCU's kthreads and softirq handlers to the code that instigated this
-CPU utilization.
-For example, RCU callback overhead might be charged back to the
-originating <tt>call_rcu()</tt> instance, though probably not
-in production kernels.
-
-<p>
-Additional work may be required to provide reasonable forward-progress
-guarantees under heavy load for grace periods and for callback
-invocation.
-
-<h2><a name="Summary">Summary</a></h2>
-
-<p>
-This document has presented more than two decade's worth of RCU
-requirements.
-Given that the requirements keep changing, this will not be the last
-word on this subject, but at least it serves to get an important
-subset of the requirements set forth.
-
-<h2><a name="Acknowledgments">Acknowledgments</a></h2>
-
-I am grateful to Steven Rostedt, Lai Jiangshan, Ingo Molnar,
-Oleg Nesterov, Borislav Petkov, Peter Zijlstra, Boqun Feng, and
-Andy Lutomirski for their help in rendering
-this article human readable, and to Michelle Rankin for her support
-of this effort.
-Other contributions are acknowledged in the Linux kernel's git archive.
-
-</body></html>
diff --git a/Documentation/RCU/Design/Requirements/Requirements.rst b/Documentation/RCU/Design/Requirements/Requirements.rst
new file mode 100644
index 000000000000..fd5e2cbc4935
--- /dev/null
+++ b/Documentation/RCU/Design/Requirements/Requirements.rst
@@ -0,0 +1,2704 @@
+=================================
+A Tour Through RCU's Requirements
+=================================
+
+Copyright IBM Corporation, 2015
+
+Author: Paul E. McKenney
+
+The initial version of this document appeared in the
+`LWN <https://lwn.net/>`_ on those articles:
+`part 1 <https://lwn.net/Articles/652156/>`_,
+`part 2 <https://lwn.net/Articles/652677/>`_, and
+`part 3 <https://lwn.net/Articles/653326/>`_.
+
+Introduction
+------------
+
+Read-copy update (RCU) is a synchronization mechanism that is often used
+as a replacement for reader-writer locking. RCU is unusual in that
+updaters do not block readers, which means that RCU's read-side
+primitives can be exceedingly fast and scalable. In addition, updaters
+can make useful forward progress concurrently with readers. However, all
+this concurrency between RCU readers and updaters does raise the
+question of exactly what RCU readers are doing, which in turn raises the
+question of exactly what RCU's requirements are.
+
+This document therefore summarizes RCU's requirements, and can be
+thought of as an informal, high-level specification for RCU. It is
+important to understand that RCU's specification is primarily empirical
+in nature; in fact, I learned about many of these requirements the hard
+way. This situation might cause some consternation, however, not only
+has this learning process been a lot of fun, but it has also been a
+great privilege to work with so many people willing to apply
+technologies in interesting new ways.
+
+All that aside, here are the categories of currently known RCU
+requirements:
+
+#. `Fundamental Requirements`_
+#. `Fundamental Non-Requirements`_
+#. `Parallelism Facts of Life`_
+#. `Quality-of-Implementation Requirements`_
+#. `Linux Kernel Complications`_
+#. `Software-Engineering Requirements`_
+#. `Other RCU Flavors`_
+#. `Possible Future Changes`_
+
+This is followed by a `summary <#Summary>`__, however, the answers to
+each quick quiz immediately follows the quiz. Select the big white space
+with your mouse to see the answer.
+
+Fundamental Requirements
+------------------------
+
+RCU's fundamental requirements are the closest thing RCU has to hard
+mathematical requirements. These are:
+
+#. `Grace-Period Guarantee`_
+#. `Publish/Subscribe Guarantee`_
+#. `Memory-Barrier Guarantees`_
+#. `RCU Primitives Guaranteed to Execute Unconditionally`_
+#. `Guaranteed Read-to-Write Upgrade`_
+
+Grace-Period Guarantee
+~~~~~~~~~~~~~~~~~~~~~~
+
+RCU's grace-period guarantee is unusual in being premeditated: Jack
+Slingwine and I had this guarantee firmly in mind when we started work
+on RCU (then called “rclock”) in the early 1990s. That said, the past
+two decades of experience with RCU have produced a much more detailed
+understanding of this guarantee.
+
+RCU's grace-period guarantee allows updaters to wait for the completion
+of all pre-existing RCU read-side critical sections. An RCU read-side
+critical section begins with the marker ``rcu_read_lock()`` and ends
+with the marker ``rcu_read_unlock()``. These markers may be nested, and
+RCU treats a nested set as one big RCU read-side critical section.
+Production-quality implementations of ``rcu_read_lock()`` and
+``rcu_read_unlock()`` are extremely lightweight, and in fact have
+exactly zero overhead in Linux kernels built for production use with
+``CONFIG_PREEMPT=n``.
+
+This guarantee allows ordering to be enforced with extremely low
+overhead to readers, for example:
+
+   ::
+
+       1 int x, y;
+       2
+       3 void thread0(void)
+       4 {
+       5   rcu_read_lock();
+       6   r1 = READ_ONCE(x);
+       7   r2 = READ_ONCE(y);
+       8   rcu_read_unlock();
+       9 }
+      10
+      11 void thread1(void)
+      12 {
+      13   WRITE_ONCE(x, 1);
+      14   synchronize_rcu();
+      15   WRITE_ONCE(y, 1);
+      16 }
+
+Because the ``synchronize_rcu()`` on line 14 waits for all pre-existing
+readers, any instance of ``thread0()`` that loads a value of zero from
+``x`` must complete before ``thread1()`` stores to ``y``, so that
+instance must also load a value of zero from ``y``. Similarly, any
+instance of ``thread0()`` that loads a value of one from ``y`` must have
+started after the ``synchronize_rcu()`` started, and must therefore also
+load a value of one from ``x``. Therefore, the outcome:
+
+   ::
+
+      (r1 == 0 && r2 == 1)
+
+cannot happen.
+
++-----------------------------------------------------------------------+
+| **Quick Quiz**:                                                       |
++-----------------------------------------------------------------------+
+| Wait a minute! You said that updaters can make useful forward         |
+| progress concurrently with readers, but pre-existing readers will     |
+| block ``synchronize_rcu()``!!!                                        |
+| Just who are you trying to fool???                                    |
++-----------------------------------------------------------------------+
+| **Answer**:                                                           |
++-----------------------------------------------------------------------+
+| First, if updaters do not wish to be blocked by readers, they can use |
+| ``call_rcu()`` or ``kfree_rcu()``, which will be discussed later.     |
+| Second, even when using ``synchronize_rcu()``, the other update-side  |
+| code does run concurrently with readers, whether pre-existing or not. |
++-----------------------------------------------------------------------+
+
+This scenario resembles one of the first uses of RCU in
+`DYNIX/ptx <https://en.wikipedia.org/wiki/DYNIX>`__, which managed a
+distributed lock manager's transition into a state suitable for handling
+recovery from node failure, more or less as follows:
+
+   ::
+
+       1 #define STATE_NORMAL        0
+       2 #define STATE_WANT_RECOVERY 1
+       3 #define STATE_RECOVERING    2
+       4 #define STATE_WANT_NORMAL   3
+       5
+       6 int state = STATE_NORMAL;
+       7
+       8 void do_something_dlm(void)
+       9 {
+      10   int state_snap;
+      11
+      12   rcu_read_lock();
+      13   state_snap = READ_ONCE(state);
+      14   if (state_snap == STATE_NORMAL)
+      15     do_something();
+      16   else
+      17     do_something_carefully();
+      18   rcu_read_unlock();
+      19 }
+      20
+      21 void start_recovery(void)
+      22 {
+      23   WRITE_ONCE(state, STATE_WANT_RECOVERY);
+      24   synchronize_rcu();
+      25   WRITE_ONCE(state, STATE_RECOVERING);
+      26   recovery();
+      27   WRITE_ONCE(state, STATE_WANT_NORMAL);
+      28   synchronize_rcu();
+      29   WRITE_ONCE(state, STATE_NORMAL);
+      30 }
+
+The RCU read-side critical section in ``do_something_dlm()`` works with
+the ``synchronize_rcu()`` in ``start_recovery()`` to guarantee that
+``do_something()`` never runs concurrently with ``recovery()``, but with
+little or no synchronization overhead in ``do_something_dlm()``.
+
++-----------------------------------------------------------------------+
+| **Quick Quiz**:                                                       |
++-----------------------------------------------------------------------+
+| Why is the ``synchronize_rcu()`` on line 28 needed?                   |
++-----------------------------------------------------------------------+
+| **Answer**:                                                           |
++-----------------------------------------------------------------------+
+| Without that extra grace period, memory reordering could result in    |
+| ``do_something_dlm()`` executing ``do_something()`` concurrently with |
+| the last bits of ``recovery()``.                                      |
++-----------------------------------------------------------------------+
+
+In order to avoid fatal problems such as deadlocks, an RCU read-side
+critical section must not contain calls to ``synchronize_rcu()``.
+Similarly, an RCU read-side critical section must not contain anything
+that waits, directly or indirectly, on completion of an invocation of
+``synchronize_rcu()``.
+
+Although RCU's grace-period guarantee is useful in and of itself, with
+`quite a few use cases <https://lwn.net/Articles/573497/>`__, it would
+be good to be able to use RCU to coordinate read-side access to linked
+data structures. For this, the grace-period guarantee is not sufficient,
+as can be seen in function ``add_gp_buggy()`` below. We will look at the
+reader's code later, but in the meantime, just think of the reader as
+locklessly picking up the ``gp`` pointer, and, if the value loaded is
+non-\ ``NULL``, locklessly accessing the ``->a`` and ``->b`` fields.
+
+   ::
+
+       1 bool add_gp_buggy(int a, int b)
+       2 {
+       3   p = kmalloc(sizeof(*p), GFP_KERNEL);
+       4   if (!p)
+       5     return -ENOMEM;
+       6   spin_lock(&gp_lock);
+       7   if (rcu_access_pointer(gp)) {
+       8     spin_unlock(&gp_lock);
+       9     return false;
+      10   }
+      11   p->a = a;
+      12   p->b = a;
+      13   gp = p; /* ORDERING BUG */
+      14   spin_unlock(&gp_lock);
+      15   return true;
+      16 }
+
+The problem is that both the compiler and weakly ordered CPUs are within
+their rights to reorder this code as follows:
+
+   ::
+
+       1 bool add_gp_buggy_optimized(int a, int b)
+       2 {
+       3   p = kmalloc(sizeof(*p), GFP_KERNEL);
+       4   if (!p)
+       5     return -ENOMEM;
+       6   spin_lock(&gp_lock);
+       7   if (rcu_access_pointer(gp)) {
+       8     spin_unlock(&gp_lock);
+       9     return false;
+      10   }
+      11   gp = p; /* ORDERING BUG */
+      12   p->a = a;
+      13   p->b = a;
+      14   spin_unlock(&gp_lock);
+      15   return true;
+      16 }
+
+If an RCU reader fetches ``gp`` just after ``add_gp_buggy_optimized``
+executes line 11, it will see garbage in the ``->a`` and ``->b`` fields.
+And this is but one of many ways in which compiler and hardware
+optimizations could cause trouble. Therefore, we clearly need some way
+to prevent the compiler and the CPU from reordering in this manner,
+which brings us to the publish-subscribe guarantee discussed in the next
+section.
+
+Publish/Subscribe Guarantee
+~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+RCU's publish-subscribe guarantee allows data to be inserted into a
+linked data structure without disrupting RCU readers. The updater uses
+``rcu_assign_pointer()`` to insert the new data, and readers use
+``rcu_dereference()`` to access data, whether new or old. The following
+shows an example of insertion:
+
+   ::
+
+       1 bool add_gp(int a, int b)
+       2 {
+       3   p = kmalloc(sizeof(*p), GFP_KERNEL);
+       4   if (!p)
+       5     return -ENOMEM;
+       6   spin_lock(&gp_lock);
+       7   if (rcu_access_pointer(gp)) {
+       8     spin_unlock(&gp_lock);
+       9     return false;
+      10   }
+      11   p->a = a;
+      12   p->b = a;
+      13   rcu_assign_pointer(gp, p);
+      14   spin_unlock(&gp_lock);
+      15   return true;
+      16 }
+
+The ``rcu_assign_pointer()`` on line 13 is conceptually equivalent to a
+simple assignment statement, but also guarantees that its assignment
+will happen after the two assignments in lines 11 and 12, similar to the
+C11 ``memory_order_release`` store operation. It also prevents any
+number of “interesting” compiler optimizations, for example, the use of
+``gp`` as a scratch location immediately preceding the assignment.
+
++-----------------------------------------------------------------------+
+| **Quick Quiz**:                                                       |
++-----------------------------------------------------------------------+
+| But ``rcu_assign_pointer()`` does nothing to prevent the two          |
+| assignments to ``p->a`` and ``p->b`` from being reordered. Can't that |
+| also cause problems?                                                  |
++-----------------------------------------------------------------------+
+| **Answer**:                                                           |
++-----------------------------------------------------------------------+
+| No, it cannot. The readers cannot see either of these two fields      |
+| until the assignment to ``gp``, by which time both fields are fully   |
+| initialized. So reordering the assignments to ``p->a`` and ``p->b``   |
+| cannot possibly cause any problems.                                   |
++-----------------------------------------------------------------------+
+
+It is tempting to assume that the reader need not do anything special to
+control its accesses to the RCU-protected data, as shown in
+``do_something_gp_buggy()`` below:
+
+   ::
+
+       1 bool do_something_gp_buggy(void)
+       2 {
+       3   rcu_read_lock();
+       4   p = gp;  /* OPTIMIZATIONS GALORE!!! */
+       5   if (p) {
+       6     do_something(p->a, p->b);
+       7     rcu_read_unlock();
+       8     return true;
+       9   }
+      10   rcu_read_unlock();
+      11   return false;
+      12 }
+
+However, this temptation must be resisted because there are a
+surprisingly large number of ways that the compiler (to say nothing of
+`DEC Alpha CPUs <https://h71000.www7.hp.com/wizard/wiz_2637.html>`__)
+can trip this code up. For but one example, if the compiler were short
+of registers, it might choose to refetch from ``gp`` rather than keeping
+a separate copy in ``p`` as follows:
+
+   ::
+
+       1 bool do_something_gp_buggy_optimized(void)
+       2 {
+       3   rcu_read_lock();
+       4   if (gp) { /* OPTIMIZATIONS GALORE!!! */
+       5     do_something(gp->a, gp->b);
+       6     rcu_read_unlock();
+       7     return true;
+       8   }
+       9   rcu_read_unlock();
+      10   return false;
+      11 }
+
+If this function ran concurrently with a series of updates that replaced
+the current structure with a new one, the fetches of ``gp->a`` and
+``gp->b`` might well come from two different structures, which could
+cause serious confusion. To prevent this (and much else besides),
+``do_something_gp()`` uses ``rcu_dereference()`` to fetch from ``gp``:
+
+   ::
+
+       1 bool do_something_gp(void)
+       2 {
+       3   rcu_read_lock();
+       4   p = rcu_dereference(gp);
+       5   if (p) {
+       6     do_something(p->a, p->b);
+       7     rcu_read_unlock();
+       8     return true;
+       9   }
+      10   rcu_read_unlock();
+      11   return false;
+      12 }
+
+The ``rcu_dereference()`` uses volatile casts and (for DEC Alpha) memory
+barriers in the Linux kernel. Should a `high-quality implementation of
+C11 ``memory_order_consume``
+[PDF] <http://www.rdrop.com/users/paulmck/RCU/consume.2015.07.13a.pdf>`__
+ever appear, then ``rcu_dereference()`` could be implemented as a
+``memory_order_consume`` load. Regardless of the exact implementation, a
+pointer fetched by ``rcu_dereference()`` may not be used outside of the
+outermost RCU read-side critical section containing that
+``rcu_dereference()``, unless protection of the corresponding data
+element has been passed from RCU to some other synchronization
+mechanism, most commonly locking or `reference
+counting <https://www.kernel.org/doc/Documentation/RCU/rcuref.txt>`__.
+
+In short, updaters use ``rcu_assign_pointer()`` and readers use
+``rcu_dereference()``, and these two RCU API elements work together to
+ensure that readers have a consistent view of newly added data elements.
+
+Of course, it is also necessary to remove elements from RCU-protected
+data structures, for example, using the following process:
+
+#. Remove the data element from the enclosing structure.
+#. Wait for all pre-existing RCU read-side critical sections to complete
+   (because only pre-existing readers can possibly have a reference to
+   the newly removed data element).
+#. At this point, only the updater has a reference to the newly removed
+   data element, so it can safely reclaim the data element, for example,
+   by passing it to ``kfree()``.
+
+This process is implemented by ``remove_gp_synchronous()``:
+
+   ::
+
+       1 bool remove_gp_synchronous(void)
+       2 {
+       3   struct foo *p;
+       4
+       5   spin_lock(&gp_lock);
+       6   p = rcu_access_pointer(gp);
+       7   if (!p) {
+       8     spin_unlock(&gp_lock);
+       9     return false;
+      10   }
+      11   rcu_assign_pointer(gp, NULL);
+      12   spin_unlock(&gp_lock);
+      13   synchronize_rcu();
+      14   kfree(p);
+      15   return true;
+      16 }
+
+This function is straightforward, with line 13 waiting for a grace
+period before line 14 frees the old data element. This waiting ensures
+that readers will reach line 7 of ``do_something_gp()`` before the data
+element referenced by ``p`` is freed. The ``rcu_access_pointer()`` on
+line 6 is similar to ``rcu_dereference()``, except that:
+
+#. The value returned by ``rcu_access_pointer()`` cannot be
+   dereferenced. If you want to access the value pointed to as well as
+   the pointer itself, use ``rcu_dereference()`` instead of
+   ``rcu_access_pointer()``.
+#. The call to ``rcu_access_pointer()`` need not be protected. In
+   contrast, ``rcu_dereference()`` must either be within an RCU
+   read-side critical section or in a code segment where the pointer
+   cannot change, for example, in code protected by the corresponding
+   update-side lock.
+
++-----------------------------------------------------------------------+
+| **Quick Quiz**:                                                       |
++-----------------------------------------------------------------------+
+| Without the ``rcu_dereference()`` or the ``rcu_access_pointer()``,    |
+| what destructive optimizations might the compiler make use of?        |
++-----------------------------------------------------------------------+
+| **Answer**:                                                           |
++-----------------------------------------------------------------------+
+| Let's start with what happens to ``do_something_gp()`` if it fails to |
+| use ``rcu_dereference()``. It could reuse a value formerly fetched    |
+| from this same pointer. It could also fetch the pointer from ``gp``   |
+| in a byte-at-a-time manner, resulting in *load tearing*, in turn      |
+| resulting a bytewise mash-up of two distinct pointer values. It might |
+| even use value-speculation optimizations, where it makes a wrong      |
+| guess, but by the time it gets around to checking the value, an       |
+| update has changed the pointer to match the wrong guess. Too bad      |
+| about any dereferences that returned pre-initialization garbage in    |
+| the meantime!                                                         |
+| For ``remove_gp_synchronous()``, as long as all modifications to      |
+| ``gp`` are carried out while holding ``gp_lock``, the above           |
+| optimizations are harmless. However, ``sparse`` will complain if you  |
+| define ``gp`` with ``__rcu`` and then access it without using either  |
+| ``rcu_access_pointer()`` or ``rcu_dereference()``.                    |
++-----------------------------------------------------------------------+
+
+In short, RCU's publish-subscribe guarantee is provided by the
+combination of ``rcu_assign_pointer()`` and ``rcu_dereference()``. This
+guarantee allows data elements to be safely added to RCU-protected
+linked data structures without disrupting RCU readers. This guarantee
+can be used in combination with the grace-period guarantee to also allow
+data elements to be removed from RCU-protected linked data structures,
+again without disrupting RCU readers.
+
+This guarantee was only partially premeditated. DYNIX/ptx used an
+explicit memory barrier for publication, but had nothing resembling
+``rcu_dereference()`` for subscription, nor did it have anything
+resembling the ``smp_read_barrier_depends()`` that was later subsumed
+into ``rcu_dereference()`` and later still into ``READ_ONCE()``. The
+need for these operations made itself known quite suddenly at a
+late-1990s meeting with the DEC Alpha architects, back in the days when
+DEC was still a free-standing company. It took the Alpha architects a
+good hour to convince me that any sort of barrier would ever be needed,
+and it then took me a good *two* hours to convince them that their
+documentation did not make this point clear. More recent work with the C
+and C++ standards committees have provided much education on tricks and
+traps from the compiler. In short, compilers were much less tricky in
+the early 1990s, but in 2015, don't even think about omitting
+``rcu_dereference()``!
+
+Memory-Barrier Guarantees
+~~~~~~~~~~~~~~~~~~~~~~~~~
+
+The previous section's simple linked-data-structure scenario clearly
+demonstrates the need for RCU's stringent memory-ordering guarantees on
+systems with more than one CPU:
+
+#. Each CPU that has an RCU read-side critical section that begins
+   before ``synchronize_rcu()`` starts is guaranteed to execute a full
+   memory barrier between the time that the RCU read-side critical
+   section ends and the time that ``synchronize_rcu()`` returns. Without
+   this guarantee, a pre-existing RCU read-side critical section might
+   hold a reference to the newly removed ``struct foo`` after the
+   ``kfree()`` on line 14 of ``remove_gp_synchronous()``.
+#. Each CPU that has an RCU read-side critical section that ends after
+   ``synchronize_rcu()`` returns is guaranteed to execute a full memory
+   barrier between the time that ``synchronize_rcu()`` begins and the
+   time that the RCU read-side critical section begins. Without this
+   guarantee, a later RCU read-side critical section running after the
+   ``kfree()`` on line 14 of ``remove_gp_synchronous()`` might later run
+   ``do_something_gp()`` and find the newly deleted ``struct foo``.
+#. If the task invoking ``synchronize_rcu()`` remains on a given CPU,
+   then that CPU is guaranteed to execute a full memory barrier sometime
+   during the execution of ``synchronize_rcu()``. This guarantee ensures
+   that the ``kfree()`` on line 14 of ``remove_gp_synchronous()`` really
+   does execute after the removal on line 11.
+#. If the task invoking ``synchronize_rcu()`` migrates among a group of
+   CPUs during that invocation, then each of the CPUs in that group is
+   guaranteed to execute a full memory barrier sometime during the
+   execution of ``synchronize_rcu()``. This guarantee also ensures that
+   the ``kfree()`` on line 14 of ``remove_gp_synchronous()`` really does
+   execute after the removal on line 11, but also in the case where the
+   thread executing the ``synchronize_rcu()`` migrates in the meantime.
+
++-----------------------------------------------------------------------+
+| **Quick Quiz**:                                                       |
++-----------------------------------------------------------------------+
+| Given that multiple CPUs can start RCU read-side critical sections at |
+| any time without any ordering whatsoever, how can RCU possibly tell   |
+| whether or not a given RCU read-side critical section starts before a |
+| given instance of ``synchronize_rcu()``?                              |
++-----------------------------------------------------------------------+
+| **Answer**:                                                           |
++-----------------------------------------------------------------------+
+| If RCU cannot tell whether or not a given RCU read-side critical      |
+| section starts before a given instance of ``synchronize_rcu()``, then |
+| it must assume that the RCU read-side critical section started first. |
+| In other words, a given instance of ``synchronize_rcu()`` can avoid   |
+| waiting on a given RCU read-side critical section only if it can      |
+| prove that ``synchronize_rcu()`` started first.                       |
+| A related question is “When ``rcu_read_lock()`` doesn't generate any  |
+| code, why does it matter how it relates to a grace period?” The       |
+| answer is that it is not the relationship of ``rcu_read_lock()``      |
+| itself that is important, but rather the relationship of the code     |
+| within the enclosed RCU read-side critical section to the code        |
+| preceding and following the grace period. If we take this viewpoint,  |
+| then a given RCU read-side critical section begins before a given     |
+| grace period when some access preceding the grace period observes the |
+| effect of some access within the critical section, in which case none |
+| of the accesses within the critical section may observe the effects   |
+| of any access following the grace period.                             |
+|                                                                       |
+| As of late 2016, mathematical models of RCU take this viewpoint, for  |
+| example, see slides 62 and 63 of the `2016 LinuxCon                   |
+| EU <http://www2.rdrop.com/users/paulmck/scalability/paper/LinuxMM.201 |
+| 6.10.04c.LCE.pdf>`__                                                  |
+| presentation.                                                         |
++-----------------------------------------------------------------------+
+
++-----------------------------------------------------------------------+
+| **Quick Quiz**:                                                       |
++-----------------------------------------------------------------------+
+| The first and second guarantees require unbelievably strict ordering! |
+| Are all these memory barriers *really* required?                      |
++-----------------------------------------------------------------------+
+| **Answer**:                                                           |
++-----------------------------------------------------------------------+
+| Yes, they really are required. To see why the first guarantee is      |
+| required, consider the following sequence of events:                  |
+|                                                                       |
+| #. CPU 1: ``rcu_read_lock()``                                         |
+| #. CPU 1: ``q = rcu_dereference(gp); /* Very likely to return p. */`` |
+| #. CPU 0: ``list_del_rcu(p);``                                        |
+| #. CPU 0: ``synchronize_rcu()`` starts.                               |
+| #. CPU 1: ``do_something_with(q->a);``                                |
+|    ``/* No smp_mb(), so might happen after kfree(). */``              |
+| #. CPU 1: ``rcu_read_unlock()``                                       |
+| #. CPU 0: ``synchronize_rcu()`` returns.                              |
+| #. CPU 0: ``kfree(p);``                                               |
+|                                                                       |
+| Therefore, there absolutely must be a full memory barrier between the |
+| end of the RCU read-side critical section and the end of the grace    |
+| period.                                                               |
+|                                                                       |
+| The sequence of events demonstrating the necessity of the second rule |
+| is roughly similar:                                                   |
+|                                                                       |
+| #. CPU 0: ``list_del_rcu(p);``                                        |
+| #. CPU 0: ``synchronize_rcu()`` starts.                               |
+| #. CPU 1: ``rcu_read_lock()``                                         |
+| #. CPU 1: ``q = rcu_dereference(gp);``                                |
+|    ``/* Might return p if no memory barrier. */``                     |
+| #. CPU 0: ``synchronize_rcu()`` returns.                              |
+| #. CPU 0: ``kfree(p);``                                               |
+| #. CPU 1: ``do_something_with(q->a); /* Boom!!! */``                  |
+| #. CPU 1: ``rcu_read_unlock()``                                       |
+|                                                                       |
+| And similarly, without a memory barrier between the beginning of the  |
+| grace period and the beginning of the RCU read-side critical section, |
+| CPU 1 might end up accessing the freelist.                            |
+|                                                                       |
+| The “as if” rule of course applies, so that any implementation that   |
+| acts as if the appropriate memory barriers were in place is a correct |
+| implementation. That said, it is much easier to fool yourself into    |
+| believing that you have adhered to the as-if rule than it is to       |
+| actually adhere to it!                                                |
++-----------------------------------------------------------------------+
+
++-----------------------------------------------------------------------+
+| **Quick Quiz**:                                                       |
++-----------------------------------------------------------------------+
+| You claim that ``rcu_read_lock()`` and ``rcu_read_unlock()`` generate |
+| absolutely no code in some kernel builds. This means that the         |
+| compiler might arbitrarily rearrange consecutive RCU read-side        |
+| critical sections. Given such rearrangement, if a given RCU read-side |
+| critical section is done, how can you be sure that all prior RCU      |
+| read-side critical sections are done? Won't the compiler              |
+| rearrangements make that impossible to determine?                     |
++-----------------------------------------------------------------------+
+| **Answer**:                                                           |
++-----------------------------------------------------------------------+
+| In cases where ``rcu_read_lock()`` and ``rcu_read_unlock()`` generate |
+| absolutely no code, RCU infers quiescent states only at special       |
+| locations, for example, within the scheduler. Because calls to        |
+| ``schedule()`` had better prevent calling-code accesses to shared     |
+| variables from being rearranged across the call to ``schedule()``, if |
+| RCU detects the end of a given RCU read-side critical section, it     |
+| will necessarily detect the end of all prior RCU read-side critical   |
+| sections, no matter how aggressively the compiler scrambles the code. |
+| Again, this all assumes that the compiler cannot scramble code across |
+| calls to the scheduler, out of interrupt handlers, into the idle      |
+| loop, into user-mode code, and so on. But if your kernel build allows |
+| that sort of scrambling, you have broken far more than just RCU!      |
++-----------------------------------------------------------------------+
+
+Note that these memory-barrier requirements do not replace the
+fundamental RCU requirement that a grace period wait for all
+pre-existing readers. On the contrary, the memory barriers called out in
+this section must operate in such a way as to *enforce* this fundamental
+requirement. Of course, different implementations enforce this
+requirement in different ways, but enforce it they must.
+
+RCU Primitives Guaranteed to Execute Unconditionally
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+The common-case RCU primitives are unconditional. They are invoked, they
+do their job, and they return, with no possibility of error, and no need
+to retry. This is a key RCU design philosophy.
+
+However, this philosophy is pragmatic rather than pigheaded. If someone
+comes up with a good justification for a particular conditional RCU
+primitive, it might well be implemented and added. After all, this
+guarantee was reverse-engineered, not premeditated. The unconditional
+nature of the RCU primitives was initially an accident of
+implementation, and later experience with synchronization primitives
+with conditional primitives caused me to elevate this accident to a
+guarantee. Therefore, the justification for adding a conditional
+primitive to RCU would need to be based on detailed and compelling use
+cases.
+
+Guaranteed Read-to-Write Upgrade
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+As far as RCU is concerned, it is always possible to carry out an update
+within an RCU read-side critical section. For example, that RCU
+read-side critical section might search for a given data element, and
+then might acquire the update-side spinlock in order to update that
+element, all while remaining in that RCU read-side critical section. Of
+course, it is necessary to exit the RCU read-side critical section
+before invoking ``synchronize_rcu()``, however, this inconvenience can
+be avoided through use of the ``call_rcu()`` and ``kfree_rcu()`` API
+members described later in this document.
+
++-----------------------------------------------------------------------+
+| **Quick Quiz**:                                                       |
++-----------------------------------------------------------------------+
+| But how does the upgrade-to-write operation exclude other readers?    |
++-----------------------------------------------------------------------+
+| **Answer**:                                                           |
++-----------------------------------------------------------------------+
+| It doesn't, just like normal RCU updates, which also do not exclude   |
+| RCU readers.                                                          |
++-----------------------------------------------------------------------+
+
+This guarantee allows lookup code to be shared between read-side and
+update-side code, and was premeditated, appearing in the earliest
+DYNIX/ptx RCU documentation.
+
+Fundamental Non-Requirements
+----------------------------
+
+RCU provides extremely lightweight readers, and its read-side
+guarantees, though quite useful, are correspondingly lightweight. It is
+therefore all too easy to assume that RCU is guaranteeing more than it
+really is. Of course, the list of things that RCU does not guarantee is
+infinitely long, however, the following sections list a few
+non-guarantees that have caused confusion. Except where otherwise noted,
+these non-guarantees were premeditated.
+
+#. `Readers Impose Minimal Ordering`_
+#. `Readers Do Not Exclude Updaters`_
+#. `Updaters Only Wait For Old Readers`_
+#. `Grace Periods Don't Partition Read-Side Critical Sections`_
+#. `Read-Side Critical Sections Don't Partition Grace Periods`_
+
+Readers Impose Minimal Ordering
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+Reader-side markers such as ``rcu_read_lock()`` and
+``rcu_read_unlock()`` provide absolutely no ordering guarantees except
+through their interaction with the grace-period APIs such as
+``synchronize_rcu()``. To see this, consider the following pair of
+threads:
+
+   ::
+
+       1 void thread0(void)
+       2 {
+       3   rcu_read_lock();
+       4   WRITE_ONCE(x, 1);
+       5   rcu_read_unlock();
+       6   rcu_read_lock();
+       7   WRITE_ONCE(y, 1);
+       8   rcu_read_unlock();
+       9 }
+      10
+      11 void thread1(void)
+      12 {
+      13   rcu_read_lock();
+      14   r1 = READ_ONCE(y);
+      15   rcu_read_unlock();
+      16   rcu_read_lock();
+      17   r2 = READ_ONCE(x);
+      18   rcu_read_unlock();
+      19 }
+
+After ``thread0()`` and ``thread1()`` execute concurrently, it is quite
+possible to have
+
+   ::
+
+      (r1 == 1 && r2 == 0)
+
+(that is, ``y`` appears to have been assigned before ``x``), which would
+not be possible if ``rcu_read_lock()`` and ``rcu_read_unlock()`` had
+much in the way of ordering properties. But they do not, so the CPU is
+within its rights to do significant reordering. This is by design: Any
+significant ordering constraints would slow down these fast-path APIs.
+
++-----------------------------------------------------------------------+
+| **Quick Quiz**:                                                       |
++-----------------------------------------------------------------------+
+| Can't the compiler also reorder this code?                            |
++-----------------------------------------------------------------------+
+| **Answer**:                                                           |
++-----------------------------------------------------------------------+
+| No, the volatile casts in ``READ_ONCE()`` and ``WRITE_ONCE()``        |
+| prevent the compiler from reordering in this particular case.         |
++-----------------------------------------------------------------------+
+
+Readers Do Not Exclude Updaters
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+Neither ``rcu_read_lock()`` nor ``rcu_read_unlock()`` exclude updates.
+All they do is to prevent grace periods from ending. The following
+example illustrates this:
+
+   ::
+
+       1 void thread0(void)
+       2 {
+       3   rcu_read_lock();
+       4   r1 = READ_ONCE(y);
+       5   if (r1) {
+       6     do_something_with_nonzero_x();
+       7     r2 = READ_ONCE(x);
+       8     WARN_ON(!r2); /* BUG!!! */
+       9   }
+      10   rcu_read_unlock();
+      11 }
+      12
+      13 void thread1(void)
+      14 {
+      15   spin_lock(&my_lock);
+      16   WRITE_ONCE(x, 1);
+      17   WRITE_ONCE(y, 1);
+      18   spin_unlock(&my_lock);
+      19 }
+
+If the ``thread0()`` function's ``rcu_read_lock()`` excluded the
+``thread1()`` function's update, the ``WARN_ON()`` could never fire. But
+the fact is that ``rcu_read_lock()`` does not exclude much of anything
+aside from subsequent grace periods, of which ``thread1()`` has none, so
+the ``WARN_ON()`` can and does fire.
+
+Updaters Only Wait For Old Readers
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+It might be tempting to assume that after ``synchronize_rcu()``
+completes, there are no readers executing. This temptation must be
+avoided because new readers can start immediately after
+``synchronize_rcu()`` starts, and ``synchronize_rcu()`` is under no
+obligation to wait for these new readers.
+
++-----------------------------------------------------------------------+
+| **Quick Quiz**:                                                       |
++-----------------------------------------------------------------------+
+| Suppose that synchronize_rcu() did wait until *all* readers had       |
+| completed instead of waiting only on pre-existing readers. For how    |
+| long would the updater be able to rely on there being no readers?     |
++-----------------------------------------------------------------------+
+| **Answer**:                                                           |
++-----------------------------------------------------------------------+
+| For no time at all. Even if ``synchronize_rcu()`` were to wait until  |
+| all readers had completed, a new reader might start immediately after |
+| ``synchronize_rcu()`` completed. Therefore, the code following        |
+| ``synchronize_rcu()`` can *never* rely on there being no readers.     |
++-----------------------------------------------------------------------+
+
+Grace Periods Don't Partition Read-Side Critical Sections
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+It is tempting to assume that if any part of one RCU read-side critical
+section precedes a given grace period, and if any part of another RCU
+read-side critical section follows that same grace period, then all of
+the first RCU read-side critical section must precede all of the second.
+However, this just isn't the case: A single grace period does not
+partition the set of RCU read-side critical sections. An example of this
+situation can be illustrated as follows, where ``x``, ``y``, and ``z``
+are initially all zero:
+
+   ::
+
+       1 void thread0(void)
+       2 {
+       3   rcu_read_lock();
+       4   WRITE_ONCE(a, 1);
+       5   WRITE_ONCE(b, 1);
+       6   rcu_read_unlock();
+       7 }
+       8
+       9 void thread1(void)
+      10 {
+      11   r1 = READ_ONCE(a);
+      12   synchronize_rcu();
+      13   WRITE_ONCE(c, 1);
+      14 }
+      15
+      16 void thread2(void)
+      17 {
+      18   rcu_read_lock();
+      19   r2 = READ_ONCE(b);
+      20   r3 = READ_ONCE(c);
+      21   rcu_read_unlock();
+      22 }
+
+It turns out that the outcome:
+
+   ::
+
+      (r1 == 1 && r2 == 0 && r3 == 1)
+
+is entirely possible. The following figure show how this can happen,
+with each circled ``QS`` indicating the point at which RCU recorded a
+*quiescent state* for each thread, that is, a state in which RCU knows
+that the thread cannot be in the midst of an RCU read-side critical
+section that started before the current grace period:
+
+.. kernel-figure:: GPpartitionReaders1.svg
+
+If it is necessary to partition RCU read-side critical sections in this
+manner, it is necessary to use two grace periods, where the first grace
+period is known to end before the second grace period starts:
+
+   ::
+
+       1 void thread0(void)
+       2 {
+       3   rcu_read_lock();
+       4   WRITE_ONCE(a, 1);
+       5   WRITE_ONCE(b, 1);
+       6   rcu_read_unlock();
+       7 }
+       8
+       9 void thread1(void)
+      10 {
+      11   r1 = READ_ONCE(a);
+      12   synchronize_rcu();
+      13   WRITE_ONCE(c, 1);
+      14 }
+      15
+      16 void thread2(void)
+      17 {
+      18   r2 = READ_ONCE(c);
+      19   synchronize_rcu();
+      20   WRITE_ONCE(d, 1);
+      21 }
+      22
+      23 void thread3(void)
+      24 {
+      25   rcu_read_lock();
+      26   r3 = READ_ONCE(b);
+      27   r4 = READ_ONCE(d);
+      28   rcu_read_unlock();
+      29 }
+
+Here, if ``(r1 == 1)``, then ``thread0()``'s write to ``b`` must happen
+before the end of ``thread1()``'s grace period. If in addition
+``(r4 == 1)``, then ``thread3()``'s read from ``b`` must happen after
+the beginning of ``thread2()``'s grace period. If it is also the case
+that ``(r2 == 1)``, then the end of ``thread1()``'s grace period must
+precede the beginning of ``thread2()``'s grace period. This mean that
+the two RCU read-side critical sections cannot overlap, guaranteeing
+that ``(r3 == 1)``. As a result, the outcome:
+
+   ::
+
+      (r1 == 1 && r2 == 1 && r3 == 0 && r4 == 1)
+
+cannot happen.
+
+This non-requirement was also non-premeditated, but became apparent when
+studying RCU's interaction with memory ordering.
+
+Read-Side Critical Sections Don't Partition Grace Periods
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+It is also tempting to assume that if an RCU read-side critical section
+happens between a pair of grace periods, then those grace periods cannot
+overlap. However, this temptation leads nowhere good, as can be
+illustrated by the following, with all variables initially zero:
+
+   ::
+
+       1 void thread0(void)
+       2 {
+       3   rcu_read_lock();
+       4   WRITE_ONCE(a, 1);
+       5   WRITE_ONCE(b, 1);
+       6   rcu_read_unlock();
+       7 }
+       8
+       9 void thread1(void)
+      10 {
+      11   r1 = READ_ONCE(a);
+      12   synchronize_rcu();
+      13   WRITE_ONCE(c, 1);
+      14 }
+      15
+      16 void thread2(void)
+      17 {
+      18   rcu_read_lock();
+      19   WRITE_ONCE(d, 1);
+      20   r2 = READ_ONCE(c);
+      21   rcu_read_unlock();
+      22 }
+      23
+      24 void thread3(void)
+      25 {
+      26   r3 = READ_ONCE(d);
+      27   synchronize_rcu();
+      28   WRITE_ONCE(e, 1);
+      29 }
+      30
+      31 void thread4(void)
+      32 {
+      33   rcu_read_lock();
+      34   r4 = READ_ONCE(b);
+      35   r5 = READ_ONCE(e);
+      36   rcu_read_unlock();
+      37 }
+
+In this case, the outcome:
+
+   ::
+
+      (r1 == 1 && r2 == 1 && r3 == 1 && r4 == 0 && r5 == 1)
+
+is entirely possible, as illustrated below:
+
+.. kernel-figure:: ReadersPartitionGP1.svg
+
+Again, an RCU read-side critical section can overlap almost all of a
+given grace period, just so long as it does not overlap the entire grace
+period. As a result, an RCU read-side critical section cannot partition
+a pair of RCU grace periods.
+
++-----------------------------------------------------------------------+
+| **Quick Quiz**:                                                       |
++-----------------------------------------------------------------------+
+| How long a sequence of grace periods, each separated by an RCU        |
+| read-side critical section, would be required to partition the RCU    |
+| read-side critical sections at the beginning and end of the chain?    |
++-----------------------------------------------------------------------+
+| **Answer**:                                                           |
++-----------------------------------------------------------------------+
+| In theory, an infinite number. In practice, an unknown number that is |
+| sensitive to both implementation details and timing considerations.   |
+| Therefore, even in practice, RCU users must abide by the theoretical  |
+| rather than the practical answer.                                     |
++-----------------------------------------------------------------------+
+
+Parallelism Facts of Life
+-------------------------
+
+These parallelism facts of life are by no means specific to RCU, but the
+RCU implementation must abide by them. They therefore bear repeating:
+
+#. Any CPU or task may be delayed at any time, and any attempts to avoid
+   these delays by disabling preemption, interrupts, or whatever are
+   completely futile. This is most obvious in preemptible user-level
+   environments and in virtualized environments (where a given guest
+   OS's VCPUs can be preempted at any time by the underlying
+   hypervisor), but can also happen in bare-metal environments due to
+   ECC errors, NMIs, and other hardware events. Although a delay of more
+   than about 20 seconds can result in splats, the RCU implementation is
+   obligated to use algorithms that can tolerate extremely long delays,
+   but where “extremely long” is not long enough to allow wrap-around
+   when incrementing a 64-bit counter.
+#. Both the compiler and the CPU can reorder memory accesses. Where it
+   matters, RCU must use compiler directives and memory-barrier
+   instructions to preserve ordering.
+#. Conflicting writes to memory locations in any given cache line will
+   result in expensive cache misses. Greater numbers of concurrent
+   writes and more-frequent concurrent writes will result in more
+   dramatic slowdowns. RCU is therefore obligated to use algorithms that
+   have sufficient locality to avoid significant performance and
+   scalability problems.
+#. As a rough rule of thumb, only one CPU's worth of processing may be
+   carried out under the protection of any given exclusive lock. RCU
+   must therefore use scalable locking designs.
+#. Counters are finite, especially on 32-bit systems. RCU's use of
+   counters must therefore tolerate counter wrap, or be designed such
+   that counter wrap would take way more time than a single system is
+   likely to run. An uptime of ten years is quite possible, a runtime of
+   a century much less so. As an example of the latter, RCU's
+   dyntick-idle nesting counter allows 54 bits for interrupt nesting
+   level (this counter is 64 bits even on a 32-bit system). Overflowing
+   this counter requires 2\ :sup:`54` half-interrupts on a given CPU
+   without that CPU ever going idle. If a half-interrupt happened every
+   microsecond, it would take 570 years of runtime to overflow this
+   counter, which is currently believed to be an acceptably long time.
+#. Linux systems can have thousands of CPUs running a single Linux
+   kernel in a single shared-memory environment. RCU must therefore pay
+   close attention to high-end scalability.
+
+This last parallelism fact of life means that RCU must pay special
+attention to the preceding facts of life. The idea that Linux might
+scale to systems with thousands of CPUs would have been met with some
+skepticism in the 1990s, but these requirements would have otherwise
+have been unsurprising, even in the early 1990s.
+
+Quality-of-Implementation Requirements
+--------------------------------------
+
+These sections list quality-of-implementation requirements. Although an
+RCU implementation that ignores these requirements could still be used,
+it would likely be subject to limitations that would make it
+inappropriate for industrial-strength production use. Classes of
+quality-of-implementation requirements are as follows:
+
+#. `Specialization`_
+#. `Performance and Scalability`_
+#. `Forward Progress`_
+#. `Composability`_
+#. `Corner Cases`_
+
+These classes is covered in the following sections.
+
+Specialization
+~~~~~~~~~~~~~~
+
+RCU is and always has been intended primarily for read-mostly
+situations, which means that RCU's read-side primitives are optimized,
+often at the expense of its update-side primitives. Experience thus far
+is captured by the following list of situations:
+
+#. Read-mostly data, where stale and inconsistent data is not a problem:
+   RCU works great!
+#. Read-mostly data, where data must be consistent: RCU works well.
+#. Read-write data, where data must be consistent: RCU *might* work OK.
+   Or not.
+#. Write-mostly data, where data must be consistent: RCU is very
+   unlikely to be the right tool for the job, with the following
+   exceptions, where RCU can provide:
+
+   a. Existence guarantees for update-friendly mechanisms.
+   b. Wait-free read-side primitives for real-time use.
+
+This focus on read-mostly situations means that RCU must interoperate
+with other synchronization primitives. For example, the ``add_gp()`` and
+``remove_gp_synchronous()`` examples discussed earlier use RCU to
+protect readers and locking to coordinate updaters. However, the need
+extends much farther, requiring that a variety of synchronization
+primitives be legal within RCU read-side critical sections, including
+spinlocks, sequence locks, atomic operations, reference counters, and
+memory barriers.
+
++-----------------------------------------------------------------------+
+| **Quick Quiz**:                                                       |
++-----------------------------------------------------------------------+
+| What about sleeping locks?                                            |
++-----------------------------------------------------------------------+
+| **Answer**:                                                           |
++-----------------------------------------------------------------------+
+| These are forbidden within Linux-kernel RCU read-side critical        |
+| sections because it is not legal to place a quiescent state (in this  |
+| case, voluntary context switch) within an RCU read-side critical      |
+| section. However, sleeping locks may be used within userspace RCU     |
+| read-side critical sections, and also within Linux-kernel sleepable   |
+| RCU `(SRCU) <#Sleepable%20RCU>`__ read-side critical sections. In     |
+| addition, the -rt patchset turns spinlocks into a sleeping locks so   |
+| that the corresponding critical sections can be preempted, which also |
+| means that these sleeplockified spinlocks (but not other sleeping     |
+| locks!) may be acquire within -rt-Linux-kernel RCU read-side critical |
+| sections.                                                             |
+| Note that it *is* legal for a normal RCU read-side critical section   |
+| to conditionally acquire a sleeping locks (as in                      |
+| ``mutex_trylock()``), but only as long as it does not loop            |
+| indefinitely attempting to conditionally acquire that sleeping locks. |
+| The key point is that things like ``mutex_trylock()`` either return   |
+| with the mutex held, or return an error indication if the mutex was   |
+| not immediately available. Either way, ``mutex_trylock()`` returns    |
+| immediately without sleeping.                                         |
++-----------------------------------------------------------------------+
+
+It often comes as a surprise that many algorithms do not require a
+consistent view of data, but many can function in that mode, with
+network routing being the poster child. Internet routing algorithms take
+significant time to propagate updates, so that by the time an update
+arrives at a given system, that system has been sending network traffic
+the wrong way for a considerable length of time. Having a few threads
+continue to send traffic the wrong way for a few more milliseconds is
+clearly not a problem: In the worst case, TCP retransmissions will
+eventually get the data where it needs to go. In general, when tracking
+the state of the universe outside of the computer, some level of
+inconsistency must be tolerated due to speed-of-light delays if nothing
+else.
+
+Furthermore, uncertainty about external state is inherent in many cases.
+For example, a pair of veterinarians might use heartbeat to determine
+whether or not a given cat was alive. But how long should they wait
+after the last heartbeat to decide that the cat is in fact dead? Waiting
+less than 400 milliseconds makes no sense because this would mean that a
+relaxed cat would be considered to cycle between death and life more
+than 100 times per minute. Moreover, just as with human beings, a cat's
+heart might stop for some period of time, so the exact wait period is a
+judgment call. One of our pair of veterinarians might wait 30 seconds
+before pronouncing the cat dead, while the other might insist on waiting
+a full minute. The two veterinarians would then disagree on the state of
+the cat during the final 30 seconds of the minute following the last
+heartbeat.
+
+Interestingly enough, this same situation applies to hardware. When push
+comes to shove, how do we tell whether or not some external server has
+failed? We send messages to it periodically, and declare it failed if we
+don't receive a response within a given period of time. Policy decisions
+can usually tolerate short periods of inconsistency. The policy was
+decided some time ago, and is only now being put into effect, so a few
+milliseconds of delay is normally inconsequential.
+
+However, there are algorithms that absolutely must see consistent data.
+For example, the translation between a user-level SystemV semaphore ID
+to the corresponding in-kernel data structure is protected by RCU, but
+it is absolutely forbidden to update a semaphore that has just been
+removed. In the Linux kernel, this need for consistency is accommodated
+by acquiring spinlocks located in the in-kernel data structure from
+within the RCU read-side critical section, and this is indicated by the
+green box in the figure above. Many other techniques may be used, and
+are in fact used within the Linux kernel.
+
+In short, RCU is not required to maintain consistency, and other
+mechanisms may be used in concert with RCU when consistency is required.
+RCU's specialization allows it to do its job extremely well, and its
+ability to interoperate with other synchronization mechanisms allows the
+right mix of synchronization tools to be used for a given job.
+
+Performance and Scalability
+~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+Energy efficiency is a critical component of performance today, and
+Linux-kernel RCU implementations must therefore avoid unnecessarily
+awakening idle CPUs. I cannot claim that this requirement was
+premeditated. In fact, I learned of it during a telephone conversation
+in which I was given “frank and open” feedback on the importance of
+energy efficiency in battery-powered systems and on specific
+energy-efficiency shortcomings of the Linux-kernel RCU implementation.
+In my experience, the battery-powered embedded community will consider
+any unnecessary wakeups to be extremely unfriendly acts. So much so that
+mere Linux-kernel-mailing-list posts are insufficient to vent their ire.
+
+Memory consumption is not particularly important for in most situations,
+and has become decreasingly so as memory sizes have expanded and memory
+costs have plummeted. However, as I learned from Matt Mackall's
+`bloatwatch <http://elinux.org/Linux_Tiny-FAQ>`__ efforts, memory
+footprint is critically important on single-CPU systems with
+non-preemptible (``CONFIG_PREEMPT=n``) kernels, and thus `tiny
+RCU <https://lkml.kernel.org/g/20090113221724.GA15307@linux.vnet.ibm.com>`__
+was born. Josh Triplett has since taken over the small-memory banner
+with his `Linux kernel tinification <https://tiny.wiki.kernel.org/>`__
+project, which resulted in `SRCU <#Sleepable%20RCU>`__ becoming optional
+for those kernels not needing it.
+
+The remaining performance requirements are, for the most part,
+unsurprising. For example, in keeping with RCU's read-side
+specialization, ``rcu_dereference()`` should have negligible overhead
+(for example, suppression of a few minor compiler optimizations).
+Similarly, in non-preemptible environments, ``rcu_read_lock()`` and
+``rcu_read_unlock()`` should have exactly zero overhead.
+
+In preemptible environments, in the case where the RCU read-side
+critical section was not preempted (as will be the case for the
+highest-priority real-time process), ``rcu_read_lock()`` and
+``rcu_read_unlock()`` should have minimal overhead. In particular, they
+should not contain atomic read-modify-write operations, memory-barrier
+instructions, preemption disabling, interrupt disabling, or backwards
+branches. However, in the case where the RCU read-side critical section
+was preempted, ``rcu_read_unlock()`` may acquire spinlocks and disable
+interrupts. This is why it is better to nest an RCU read-side critical
+section within a preempt-disable region than vice versa, at least in
+cases where that critical section is short enough to avoid unduly
+degrading real-time latencies.
+
+The ``synchronize_rcu()`` grace-period-wait primitive is optimized for
+throughput. It may therefore incur several milliseconds of latency in
+addition to the duration of the longest RCU read-side critical section.
+On the other hand, multiple concurrent invocations of
+``synchronize_rcu()`` are required to use batching optimizations so that
+they can be satisfied by a single underlying grace-period-wait
+operation. For example, in the Linux kernel, it is not unusual for a
+single grace-period-wait operation to serve more than `1,000 separate
+invocations <https://www.usenix.org/conference/2004-usenix-annual-technical-conference/making-rcu-safe-deep-sub-millisecond-response>`__
+of ``synchronize_rcu()``, thus amortizing the per-invocation overhead
+down to nearly zero. However, the grace-period optimization is also
+required to avoid measurable degradation of real-time scheduling and
+interrupt latencies.
+
+In some cases, the multi-millisecond ``synchronize_rcu()`` latencies are
+unacceptable. In these cases, ``synchronize_rcu_expedited()`` may be
+used instead, reducing the grace-period latency down to a few tens of
+microseconds on small systems, at least in cases where the RCU read-side
+critical sections are short. There are currently no special latency
+requirements for ``synchronize_rcu_expedited()`` on large systems, but,
+consistent with the empirical nature of the RCU specification, that is
+subject to change. However, there most definitely are scalability
+requirements: A storm of ``synchronize_rcu_expedited()`` invocations on
+4096 CPUs should at least make reasonable forward progress. In return
+for its shorter latencies, ``synchronize_rcu_expedited()`` is permitted
+to impose modest degradation of real-time latency on non-idle online
+CPUs. Here, “modest” means roughly the same latency degradation as a
+scheduling-clock interrupt.
+
+There are a number of situations where even
+``synchronize_rcu_expedited()``'s reduced grace-period latency is
+unacceptable. In these situations, the asynchronous ``call_rcu()`` can
+be used in place of ``synchronize_rcu()`` as follows:
+
+   ::
+
+       1 struct foo {
+       2   int a;
+       3   int b;
+       4   struct rcu_head rh;
+       5 };
+       6
+       7 static void remove_gp_cb(struct rcu_head *rhp)
+       8 {
+       9   struct foo *p = container_of(rhp, struct foo, rh);
+      10
+      11   kfree(p);
+      12 }
+      13
+      14 bool remove_gp_asynchronous(void)
+      15 {
+      16   struct foo *p;
+      17
+      18   spin_lock(&gp_lock);
+      19   p = rcu_access_pointer(gp);
+      20   if (!p) {
+      21     spin_unlock(&gp_lock);
+      22     return false;
+      23   }
+      24   rcu_assign_pointer(gp, NULL);
+      25   call_rcu(&p->rh, remove_gp_cb);
+      26   spin_unlock(&gp_lock);
+      27   return true;
+      28 }
+
+A definition of ``struct foo`` is finally needed, and appears on
+lines 1-5. The function ``remove_gp_cb()`` is passed to ``call_rcu()``
+on line 25, and will be invoked after the end of a subsequent grace
+period. This gets the same effect as ``remove_gp_synchronous()``, but
+without forcing the updater to wait for a grace period to elapse. The
+``call_rcu()`` function may be used in a number of situations where
+neither ``synchronize_rcu()`` nor ``synchronize_rcu_expedited()`` would
+be legal, including within preempt-disable code, ``local_bh_disable()``
+code, interrupt-disable code, and interrupt handlers. However, even
+``call_rcu()`` is illegal within NMI handlers and from idle and offline
+CPUs. The callback function (``remove_gp_cb()`` in this case) will be
+executed within softirq (software interrupt) environment within the
+Linux kernel, either within a real softirq handler or under the
+protection of ``local_bh_disable()``. In both the Linux kernel and in
+userspace, it is bad practice to write an RCU callback function that
+takes too long. Long-running operations should be relegated to separate
+threads or (in the Linux kernel) workqueues.
+
++-----------------------------------------------------------------------+
+| **Quick Quiz**:                                                       |
++-----------------------------------------------------------------------+
+| Why does line 19 use ``rcu_access_pointer()``? After all,             |
+| ``call_rcu()`` on line 25 stores into the structure, which would      |
+| interact badly with concurrent insertions. Doesn't this mean that     |
+| ``rcu_dereference()`` is required?                                    |
++-----------------------------------------------------------------------+
+| **Answer**:                                                           |
++-----------------------------------------------------------------------+
+| Presumably the ``->gp_lock`` acquired on line 18 excludes any         |
+| changes, including any insertions that ``rcu_dereference()`` would    |
+| protect against. Therefore, any insertions will be delayed until      |
+| after ``->gp_lock`` is released on line 25, which in turn means that  |
+| ``rcu_access_pointer()`` suffices.                                    |
++-----------------------------------------------------------------------+
+
+However, all that ``remove_gp_cb()`` is doing is invoking ``kfree()`` on
+the data element. This is a common idiom, and is supported by
+``kfree_rcu()``, which allows “fire and forget” operation as shown
+below:
+
+   ::
+
+       1 struct foo {
+       2   int a;
+       3   int b;
+       4   struct rcu_head rh;
+       5 };
+       6
+       7 bool remove_gp_faf(void)
+       8 {
+       9   struct foo *p;
+      10
+      11   spin_lock(&gp_lock);
+      12   p = rcu_dereference(gp);
+      13   if (!p) {
+      14     spin_unlock(&gp_lock);
+      15     return false;
+      16   }
+      17   rcu_assign_pointer(gp, NULL);
+      18   kfree_rcu(p, rh);
+      19   spin_unlock(&gp_lock);
+      20   return true;
+      21 }
+
+Note that ``remove_gp_faf()`` simply invokes ``kfree_rcu()`` and
+proceeds, without any need to pay any further attention to the
+subsequent grace period and ``kfree()``. It is permissible to invoke
+``kfree_rcu()`` from the same environments as for ``call_rcu()``.
+Interestingly enough, DYNIX/ptx had the equivalents of ``call_rcu()``
+and ``kfree_rcu()``, but not ``synchronize_rcu()``. This was due to the
+fact that RCU was not heavily used within DYNIX/ptx, so the very few
+places that needed something like ``synchronize_rcu()`` simply
+open-coded it.
+
++-----------------------------------------------------------------------+
+| **Quick Quiz**:                                                       |
++-----------------------------------------------------------------------+
+| Earlier it was claimed that ``call_rcu()`` and ``kfree_rcu()``        |
+| allowed updaters to avoid being blocked by readers. But how can that  |
+| be correct, given that the invocation of the callback and the freeing |
+| of the memory (respectively) must still wait for a grace period to    |
+| elapse?                                                               |
++-----------------------------------------------------------------------+
+| **Answer**:                                                           |
++-----------------------------------------------------------------------+
+| We could define things this way, but keep in mind that this sort of   |
+| definition would say that updates in garbage-collected languages      |
+| cannot complete until the next time the garbage collector runs, which |
+| does not seem at all reasonable. The key point is that in most cases, |
+| an updater using either ``call_rcu()`` or ``kfree_rcu()`` can proceed |
+| to the next update as soon as it has invoked ``call_rcu()`` or        |
+| ``kfree_rcu()``, without having to wait for a subsequent grace        |
+| period.                                                               |
++-----------------------------------------------------------------------+
+
+But what if the updater must wait for the completion of code to be
+executed after the end of the grace period, but has other tasks that can
+be carried out in the meantime? The polling-style
+``get_state_synchronize_rcu()`` and ``cond_synchronize_rcu()`` functions
+may be used for this purpose, as shown below:
+
+   ::
+
+       1 bool remove_gp_poll(void)
+       2 {
+       3   struct foo *p;
+       4   unsigned long s;
+       5
+       6   spin_lock(&gp_lock);
+       7   p = rcu_access_pointer(gp);
+       8   if (!p) {
+       9     spin_unlock(&gp_lock);
+      10     return false;
+      11   }
+      12   rcu_assign_pointer(gp, NULL);
+      13   spin_unlock(&gp_lock);
+      14   s = get_state_synchronize_rcu();
+      15   do_something_while_waiting();
+      16   cond_synchronize_rcu(s);
+      17   kfree(p);
+      18   return true;
+      19 }
+
+On line 14, ``get_state_synchronize_rcu()`` obtains a “cookie” from RCU,
+then line 15 carries out other tasks, and finally, line 16 returns
+immediately if a grace period has elapsed in the meantime, but otherwise
+waits as required. The need for ``get_state_synchronize_rcu`` and
+``cond_synchronize_rcu()`` has appeared quite recently, so it is too
+early to tell whether they will stand the test of time.
+
+RCU thus provides a range of tools to allow updaters to strike the
+required tradeoff between latency, flexibility and CPU overhead.
+
+Forward Progress
+~~~~~~~~~~~~~~~~
+
+In theory, delaying grace-period completion and callback invocation is
+harmless. In practice, not only are memory sizes finite but also
+callbacks sometimes do wakeups, and sufficiently deferred wakeups can be
+difficult to distinguish from system hangs. Therefore, RCU must provide
+a number of mechanisms to promote forward progress.
+
+These mechanisms are not foolproof, nor can they be. For one simple
+example, an infinite loop in an RCU read-side critical section must by
+definition prevent later grace periods from ever completing. For a more
+involved example, consider a 64-CPU system built with
+``CONFIG_RCU_NOCB_CPU=y`` and booted with ``rcu_nocbs=1-63``, where
+CPUs 1 through 63 spin in tight loops that invoke ``call_rcu()``. Even
+if these tight loops also contain calls to ``cond_resched()`` (thus
+allowing grace periods to complete), CPU 0 simply will not be able to
+invoke callbacks as fast as the other 63 CPUs can register them, at
+least not until the system runs out of memory. In both of these
+examples, the Spiderman principle applies: With great power comes great
+responsibility. However, short of this level of abuse, RCU is required
+to ensure timely completion of grace periods and timely invocation of
+callbacks.
+
+RCU takes the following steps to encourage timely completion of grace
+periods:
+
+#. If a grace period fails to complete within 100 milliseconds, RCU
+   causes future invocations of ``cond_resched()`` on the holdout CPUs
+   to provide an RCU quiescent state. RCU also causes those CPUs'
+   ``need_resched()`` invocations to return ``true``, but only after the
+   corresponding CPU's next scheduling-clock.
+#. CPUs mentioned in the ``nohz_full`` kernel boot parameter can run
+   indefinitely in the kernel without scheduling-clock interrupts, which
+   defeats the above ``need_resched()`` strategem. RCU will therefore
+   invoke ``resched_cpu()`` on any ``nohz_full`` CPUs still holding out
+   after 109 milliseconds.
+#. In kernels built with ``CONFIG_RCU_BOOST=y``, if a given task that
+   has been preempted within an RCU read-side critical section is
+   holding out for more than 500 milliseconds, RCU will resort to
+   priority boosting.
+#. If a CPU is still holding out 10 seconds into the grace period, RCU
+   will invoke ``resched_cpu()`` on it regardless of its ``nohz_full``
+   state.
+
+The above values are defaults for systems running with ``HZ=1000``. They
+will vary as the value of ``HZ`` varies, and can also be changed using
+the relevant Kconfig options and kernel boot parameters. RCU currently
+does not do much sanity checking of these parameters, so please use
+caution when changing them. Note that these forward-progress measures
+are provided only for RCU, not for `SRCU <#Sleepable%20RCU>`__ or `Tasks
+RCU <#Tasks%20RCU>`__.
+
+RCU takes the following steps in ``call_rcu()`` to encourage timely
+invocation of callbacks when any given non-\ ``rcu_nocbs`` CPU has
+10,000 callbacks, or has 10,000 more callbacks than it had the last time
+encouragement was provided:
+
+#. Starts a grace period, if one is not already in progress.
+#. Forces immediate checking for quiescent states, rather than waiting
+   for three milliseconds to have elapsed since the beginning of the
+   grace period.
+#. Immediately tags the CPU's callbacks with their grace period
+   completion numbers, rather than waiting for the ``RCU_SOFTIRQ``
+   handler to get around to it.
+#. Lifts callback-execution batch limits, which speeds up callback
+   invocation at the expense of degrading realtime response.
+
+Again, these are default values when running at ``HZ=1000``, and can be
+overridden. Again, these forward-progress measures are provided only for
+RCU, not for `SRCU <#Sleepable%20RCU>`__ or `Tasks
+RCU <#Tasks%20RCU>`__. Even for RCU, callback-invocation forward
+progress for ``rcu_nocbs`` CPUs is much less well-developed, in part
+because workloads benefiting from ``rcu_nocbs`` CPUs tend to invoke
+``call_rcu()`` relatively infrequently. If workloads emerge that need
+both ``rcu_nocbs`` CPUs and high ``call_rcu()`` invocation rates, then
+additional forward-progress work will be required.
+
+Composability
+~~~~~~~~~~~~~
+
+Composability has received much attention in recent years, perhaps in
+part due to the collision of multicore hardware with object-oriented
+techniques designed in single-threaded environments for single-threaded
+use. And in theory, RCU read-side critical sections may be composed, and
+in fact may be nested arbitrarily deeply. In practice, as with all
+real-world implementations of composable constructs, there are
+limitations.
+
+Implementations of RCU for which ``rcu_read_lock()`` and
+``rcu_read_unlock()`` generate no code, such as Linux-kernel RCU when
+``CONFIG_PREEMPT=n``, can be nested arbitrarily deeply. After all, there
+is no overhead. Except that if all these instances of
+``rcu_read_lock()`` and ``rcu_read_unlock()`` are visible to the
+compiler, compilation will eventually fail due to exhausting memory,
+mass storage, or user patience, whichever comes first. If the nesting is
+not visible to the compiler, as is the case with mutually recursive
+functions each in its own translation unit, stack overflow will result.
+If the nesting takes the form of loops, perhaps in the guise of tail
+recursion, either the control variable will overflow or (in the Linux
+kernel) you will get an RCU CPU stall warning. Nevertheless, this class
+of RCU implementations is one of the most composable constructs in
+existence.
+
+RCU implementations that explicitly track nesting depth are limited by
+the nesting-depth counter. For example, the Linux kernel's preemptible
+RCU limits nesting to ``INT_MAX``. This should suffice for almost all
+practical purposes. That said, a consecutive pair of RCU read-side
+critical sections between which there is an operation that waits for a
+grace period cannot be enclosed in another RCU read-side critical
+section. This is because it is not legal to wait for a grace period
+within an RCU read-side critical section: To do so would result either
+in deadlock or in RCU implicitly splitting the enclosing RCU read-side
+critical section, neither of which is conducive to a long-lived and
+prosperous kernel.
+
+It is worth noting that RCU is not alone in limiting composability. For
+example, many transactional-memory implementations prohibit composing a
+pair of transactions separated by an irrevocable operation (for example,
+a network receive operation). For another example, lock-based critical
+sections can be composed surprisingly freely, but only if deadlock is
+avoided.
+
+In short, although RCU read-side critical sections are highly
+composable, care is required in some situations, just as is the case for
+any other composable synchronization mechanism.
+
+Corner Cases
+~~~~~~~~~~~~
+
+A given RCU workload might have an endless and intense stream of RCU
+read-side critical sections, perhaps even so intense that there was
+never a point in time during which there was not at least one RCU
+read-side critical section in flight. RCU cannot allow this situation to
+block grace periods: As long as all the RCU read-side critical sections
+are finite, grace periods must also be finite.
+
+That said, preemptible RCU implementations could potentially result in
+RCU read-side critical sections being preempted for long durations,
+which has the effect of creating a long-duration RCU read-side critical
+section. This situation can arise only in heavily loaded systems, but
+systems using real-time priorities are of course more vulnerable.
+Therefore, RCU priority boosting is provided to help deal with this
+case. That said, the exact requirements on RCU priority boosting will
+likely evolve as more experience accumulates.
+
+Other workloads might have very high update rates. Although one can
+argue that such workloads should instead use something other than RCU,
+the fact remains that RCU must handle such workloads gracefully. This
+requirement is another factor driving batching of grace periods, but it
+is also the driving force behind the checks for large numbers of queued
+RCU callbacks in the ``call_rcu()`` code path. Finally, high update
+rates should not delay RCU read-side critical sections, although some
+small read-side delays can occur when using
+``synchronize_rcu_expedited()``, courtesy of this function's use of
+``smp_call_function_single()``.
+
+Although all three of these corner cases were understood in the early
+1990s, a simple user-level test consisting of ``close(open(path))`` in a
+tight loop in the early 2000s suddenly provided a much deeper
+appreciation of the high-update-rate corner case. This test also
+motivated addition of some RCU code to react to high update rates, for
+example, if a given CPU finds itself with more than 10,000 RCU callbacks
+queued, it will cause RCU to take evasive action by more aggressively
+starting grace periods and more aggressively forcing completion of
+grace-period processing. This evasive action causes the grace period to
+complete more quickly, but at the cost of restricting RCU's batching
+optimizations, thus increasing the CPU overhead incurred by that grace
+period.
+
+Software-Engineering Requirements
+---------------------------------
+
+Between Murphy's Law and “To err is human”, it is necessary to guard
+against mishaps and misuse:
+
+#. It is all too easy to forget to use ``rcu_read_lock()`` everywhere
+   that it is needed, so kernels built with ``CONFIG_PROVE_RCU=y`` will
+   splat if ``rcu_dereference()`` is used outside of an RCU read-side
+   critical section. Update-side code can use
+   ``rcu_dereference_protected()``, which takes a `lockdep
+   expression <https://lwn.net/Articles/371986/>`__ to indicate what is
+   providing the protection. If the indicated protection is not
+   provided, a lockdep splat is emitted.
+   Code shared between readers and updaters can use
+   ``rcu_dereference_check()``, which also takes a lockdep expression,
+   and emits a lockdep splat if neither ``rcu_read_lock()`` nor the
+   indicated protection is in place. In addition,
+   ``rcu_dereference_raw()`` is used in those (hopefully rare) cases
+   where the required protection cannot be easily described. Finally,
+   ``rcu_read_lock_held()`` is provided to allow a function to verify
+   that it has been invoked within an RCU read-side critical section. I
+   was made aware of this set of requirements shortly after Thomas
+   Gleixner audited a number of RCU uses.
+#. A given function might wish to check for RCU-related preconditions
+   upon entry, before using any other RCU API. The
+   ``rcu_lockdep_assert()`` does this job, asserting the expression in
+   kernels having lockdep enabled and doing nothing otherwise.
+#. It is also easy to forget to use ``rcu_assign_pointer()`` and
+   ``rcu_dereference()``, perhaps (incorrectly) substituting a simple
+   assignment. To catch this sort of error, a given RCU-protected
+   pointer may be tagged with ``__rcu``, after which sparse will
+   complain about simple-assignment accesses to that pointer. Arnd
+   Bergmann made me aware of this requirement, and also supplied the
+   needed `patch series <https://lwn.net/Articles/376011/>`__.
+#. Kernels built with ``CONFIG_DEBUG_OBJECTS_RCU_HEAD=y`` will splat if
+   a data element is passed to ``call_rcu()`` twice in a row, without a
+   grace period in between. (This error is similar to a double free.)
+   The corresponding ``rcu_head`` structures that are dynamically
+   allocated are automatically tracked, but ``rcu_head`` structures
+   allocated on the stack must be initialized with
+   ``init_rcu_head_on_stack()`` and cleaned up with
+   ``destroy_rcu_head_on_stack()``. Similarly, statically allocated
+   non-stack ``rcu_head`` structures must be initialized with
+   ``init_rcu_head()`` and cleaned up with ``destroy_rcu_head()``.
+   Mathieu Desnoyers made me aware of this requirement, and also
+   supplied the needed
+   `patch <https://lkml.kernel.org/g/20100319013024.GA28456@Krystal>`__.
+#. An infinite loop in an RCU read-side critical section will eventually
+   trigger an RCU CPU stall warning splat, with the duration of
+   “eventually” being controlled by the ``RCU_CPU_STALL_TIMEOUT``
+   ``Kconfig`` option, or, alternatively, by the
+   ``rcupdate.rcu_cpu_stall_timeout`` boot/sysfs parameter. However, RCU
+   is not obligated to produce this splat unless there is a grace period
+   waiting on that particular RCU read-side critical section.
+
+   Some extreme workloads might intentionally delay RCU grace periods,
+   and systems running those workloads can be booted with
+   ``rcupdate.rcu_cpu_stall_suppress`` to suppress the splats. This
+   kernel parameter may also be set via ``sysfs``. Furthermore, RCU CPU
+   stall warnings are counter-productive during sysrq dumps and during
+   panics. RCU therefore supplies the ``rcu_sysrq_start()`` and
+   ``rcu_sysrq_end()`` API members to be called before and after long
+   sysrq dumps. RCU also supplies the ``rcu_panic()`` notifier that is
+   automatically invoked at the beginning of a panic to suppress further
+   RCU CPU stall warnings.
+
+   This requirement made itself known in the early 1990s, pretty much
+   the first time that it was necessary to debug a CPU stall. That said,
+   the initial implementation in DYNIX/ptx was quite generic in
+   comparison with that of Linux.
+
+#. Although it would be very good to detect pointers leaking out of RCU
+   read-side critical sections, there is currently no good way of doing
+   this. One complication is the need to distinguish between pointers
+   leaking and pointers that have been handed off from RCU to some other
+   synchronization mechanism, for example, reference counting.
+#. In kernels built with ``CONFIG_RCU_TRACE=y``, RCU-related information
+   is provided via event tracing.
+#. Open-coded use of ``rcu_assign_pointer()`` and ``rcu_dereference()``
+   to create typical linked data structures can be surprisingly
+   error-prone. Therefore, RCU-protected `linked
+   lists <https://lwn.net/Articles/609973/#RCU%20List%20APIs>`__ and,
+   more recently, RCU-protected `hash
+   tables <https://lwn.net/Articles/612100/>`__ are available. Many
+   other special-purpose RCU-protected data structures are available in
+   the Linux kernel and the userspace RCU library.
+#. Some linked structures are created at compile time, but still require
+   ``__rcu`` checking. The ``RCU_POINTER_INITIALIZER()`` macro serves
+   this purpose.
+#. It is not necessary to use ``rcu_assign_pointer()`` when creating
+   linked structures that are to be published via a single external
+   pointer. The ``RCU_INIT_POINTER()`` macro is provided for this task
+   and also for assigning ``NULL`` pointers at runtime.
+
+This not a hard-and-fast list: RCU's diagnostic capabilities will
+continue to be guided by the number and type of usage bugs found in
+real-world RCU usage.
+
+Linux Kernel Complications
+--------------------------
+
+The Linux kernel provides an interesting environment for all kinds of
+software, including RCU. Some of the relevant points of interest are as
+follows:
+
+#. `Configuration`_
+#. `Firmware Interface`_
+#. `Early Boot`_
+#. `Interrupts and NMIs`_
+#. `Loadable Modules`_
+#. `Hotplug CPU`_
+#. `Scheduler and RCU`_
+#. `Tracing and RCU`_
+#. `Accesses to User Memory and RCU`_
+#. `Energy Efficiency`_
+#. `Scheduling-Clock Interrupts and RCU`_
+#. `Memory Efficiency`_
+#. `Performance, Scalability, Response Time, and Reliability`_
+
+This list is probably incomplete, but it does give a feel for the most
+notable Linux-kernel complications. Each of the following sections
+covers one of the above topics.
+
+Configuration
+~~~~~~~~~~~~~
+
+RCU's goal is automatic configuration, so that almost nobody needs to
+worry about RCU's ``Kconfig`` options. And for almost all users, RCU
+does in fact work well “out of the box.”
+
+However, there are specialized use cases that are handled by kernel boot
+parameters and ``Kconfig`` options. Unfortunately, the ``Kconfig``
+system will explicitly ask users about new ``Kconfig`` options, which
+requires almost all of them be hidden behind a ``CONFIG_RCU_EXPERT``
+``Kconfig`` option.
+
+This all should be quite obvious, but the fact remains that Linus
+Torvalds recently had to
+`remind <https://lkml.kernel.org/g/CA+55aFy4wcCwaL4okTs8wXhGZ5h-ibecy_Meg9C4MNQrUnwMcg@mail.gmail.com>`__
+me of this requirement.
+
+Firmware Interface
+~~~~~~~~~~~~~~~~~~
+
+In many cases, kernel obtains information about the system from the
+firmware, and sometimes things are lost in translation. Or the
+translation is accurate, but the original message is bogus.
+
+For example, some systems' firmware overreports the number of CPUs,
+sometimes by a large factor. If RCU naively believed the firmware, as it
+used to do, it would create too many per-CPU kthreads. Although the
+resulting system will still run correctly, the extra kthreads needlessly
+consume memory and can cause confusion when they show up in ``ps``
+listings.
+
+RCU must therefore wait for a given CPU to actually come online before
+it can allow itself to believe that the CPU actually exists. The
+resulting “ghost CPUs” (which are never going to come online) cause a
+number of `interesting
+complications <https://paulmck.livejournal.com/37494.html>`__.
+
+Early Boot
+~~~~~~~~~~
+
+The Linux kernel's boot sequence is an interesting process, and RCU is
+used early, even before ``rcu_init()`` is invoked. In fact, a number of
+RCU's primitives can be used as soon as the initial task's
+``task_struct`` is available and the boot CPU's per-CPU variables are
+set up. The read-side primitives (``rcu_read_lock()``,
+``rcu_read_unlock()``, ``rcu_dereference()``, and
+``rcu_access_pointer()``) will operate normally very early on, as will
+``rcu_assign_pointer()``.
+
+Although ``call_rcu()`` may be invoked at any time during boot,
+callbacks are not guaranteed to be invoked until after all of RCU's
+kthreads have been spawned, which occurs at ``early_initcall()`` time.
+This delay in callback invocation is due to the fact that RCU does not
+invoke callbacks until it is fully initialized, and this full
+initialization cannot occur until after the scheduler has initialized
+itself to the point where RCU can spawn and run its kthreads. In theory,
+it would be possible to invoke callbacks earlier, however, this is not a
+panacea because there would be severe restrictions on what operations
+those callbacks could invoke.
+
+Perhaps surprisingly, ``synchronize_rcu()`` and
+``synchronize_rcu_expedited()``, will operate normally during very early
+boot, the reason being that there is only one CPU and preemption is
+disabled. This means that the call ``synchronize_rcu()`` (or friends)
+itself is a quiescent state and thus a grace period, so the early-boot
+implementation can be a no-op.
+
+However, once the scheduler has spawned its first kthread, this early
+boot trick fails for ``synchronize_rcu()`` (as well as for
+``synchronize_rcu_expedited()``) in ``CONFIG_PREEMPT=y`` kernels. The
+reason is that an RCU read-side critical section might be preempted,
+which means that a subsequent ``synchronize_rcu()`` really does have to
+wait for something, as opposed to simply returning immediately.
+Unfortunately, ``synchronize_rcu()`` can't do this until all of its
+kthreads are spawned, which doesn't happen until some time during
+``early_initcalls()`` time. But this is no excuse: RCU is nevertheless
+required to correctly handle synchronous grace periods during this time
+period. Once all of its kthreads are up and running, RCU starts running
+normally.
+
++-----------------------------------------------------------------------+
+| **Quick Quiz**:                                                       |
++-----------------------------------------------------------------------+
+| How can RCU possibly handle grace periods before all of its kthreads  |
+| have been spawned???                                                  |
++-----------------------------------------------------------------------+
+| **Answer**:                                                           |
++-----------------------------------------------------------------------+
+| Very carefully!                                                       |
+| During the “dead zone” between the time that the scheduler spawns the |
+| first task and the time that all of RCU's kthreads have been spawned, |
+| all synchronous grace periods are handled by the expedited            |
+| grace-period mechanism. At runtime, this expedited mechanism relies   |
+| on workqueues, but during the dead zone the requesting task itself    |
+| drives the desired expedited grace period. Because dead-zone          |
+| execution takes place within task context, everything works. Once the |
+| dead zone ends, expedited grace periods go back to using workqueues,  |
+| as is required to avoid problems that would otherwise occur when a    |
+| user task received a POSIX signal while driving an expedited grace    |
+| period.                                                               |
+|                                                                       |
+| And yes, this does mean that it is unhelpful to send POSIX signals to |
+| random tasks between the time that the scheduler spawns its first     |
+| kthread and the time that RCU's kthreads have all been spawned. If    |
+| there ever turns out to be a good reason for sending POSIX signals    |
+| during that time, appropriate adjustments will be made. (If it turns  |
+| out that POSIX signals are sent during this time for no good reason,  |
+| other adjustments will be made, appropriate or otherwise.)            |
++-----------------------------------------------------------------------+
+
+I learned of these boot-time requirements as a result of a series of
+system hangs.
+
+Interrupts and NMIs
+~~~~~~~~~~~~~~~~~~~
+
+The Linux kernel has interrupts, and RCU read-side critical sections are
+legal within interrupt handlers and within interrupt-disabled regions of
+code, as are invocations of ``call_rcu()``.
+
+Some Linux-kernel architectures can enter an interrupt handler from
+non-idle process context, and then just never leave it, instead
+stealthily transitioning back to process context. This trick is
+sometimes used to invoke system calls from inside the kernel. These
+“half-interrupts” mean that RCU has to be very careful about how it
+counts interrupt nesting levels. I learned of this requirement the hard
+way during a rewrite of RCU's dyntick-idle code.
+
+The Linux kernel has non-maskable interrupts (NMIs), and RCU read-side
+critical sections are legal within NMI handlers. Thankfully, RCU
+update-side primitives, including ``call_rcu()``, are prohibited within
+NMI handlers.
+
+The name notwithstanding, some Linux-kernel architectures can have
+nested NMIs, which RCU must handle correctly. Andy Lutomirski `surprised
+me <https://lkml.kernel.org/r/CALCETrXLq1y7e_dKFPgou-FKHB6Pu-r8+t-6Ds+8=va7anBWDA@mail.gmail.com>`__
+with this requirement; he also kindly surprised me with `an
+algorithm <https://lkml.kernel.org/r/CALCETrXSY9JpW3uE6H8WYk81sg56qasA2aqmjMPsq5dOtzso=g@mail.gmail.com>`__
+that meets this requirement.
+
+Furthermore, NMI handlers can be interrupted by what appear to RCU to be
+normal interrupts. One way that this can happen is for code that
+directly invokes ``rcu_irq_enter()`` and ``rcu_irq_exit()`` to be called
+from an NMI handler. This astonishing fact of life prompted the current
+code structure, which has ``rcu_irq_enter()`` invoking
+``rcu_nmi_enter()`` and ``rcu_irq_exit()`` invoking ``rcu_nmi_exit()``.
+And yes, I also learned of this requirement the hard way.
+
+Loadable Modules
+~~~~~~~~~~~~~~~~
+
+The Linux kernel has loadable modules, and these modules can also be
+unloaded. After a given module has been unloaded, any attempt to call
+one of its functions results in a segmentation fault. The module-unload
+functions must therefore cancel any delayed calls to loadable-module
+functions, for example, any outstanding ``mod_timer()`` must be dealt
+with via ``del_timer_sync()`` or similar.
+
+Unfortunately, there is no way to cancel an RCU callback; once you
+invoke ``call_rcu()``, the callback function is eventually going to be
+invoked, unless the system goes down first. Because it is normally
+considered socially irresponsible to crash the system in response to a
+module unload request, we need some other way to deal with in-flight RCU
+callbacks.
+
+RCU therefore provides ``rcu_barrier()``, which waits until all
+in-flight RCU callbacks have been invoked. If a module uses
+``call_rcu()``, its exit function should therefore prevent any future
+invocation of ``call_rcu()``, then invoke ``rcu_barrier()``. In theory,
+the underlying module-unload code could invoke ``rcu_barrier()``
+unconditionally, but in practice this would incur unacceptable
+latencies.
+
+Nikita Danilov noted this requirement for an analogous
+filesystem-unmount situation, and Dipankar Sarma incorporated
+``rcu_barrier()`` into RCU. The need for ``rcu_barrier()`` for module
+unloading became apparent later.
+
+.. important::
+
+   The ``rcu_barrier()`` function is not, repeat,
+   *not*, obligated to wait for a grace period. It is instead only required
+   to wait for RCU callbacks that have already been posted. Therefore, if
+   there are no RCU callbacks posted anywhere in the system,
+   ``rcu_barrier()`` is within its rights to return immediately. Even if
+   there are callbacks posted, ``rcu_barrier()`` does not necessarily need
+   to wait for a grace period.
+
++-----------------------------------------------------------------------+
+| **Quick Quiz**:                                                       |
++-----------------------------------------------------------------------+
+| Wait a minute! Each RCU callbacks must wait for a grace period to     |
+| complete, and ``rcu_barrier()`` must wait for each pre-existing       |
+| callback to be invoked. Doesn't ``rcu_barrier()`` therefore need to   |
+| wait for a full grace period if there is even one callback posted     |
+| anywhere in the system?                                               |
++-----------------------------------------------------------------------+
+| **Answer**:                                                           |
++-----------------------------------------------------------------------+
+| Absolutely not!!!                                                     |
+| Yes, each RCU callbacks must wait for a grace period to complete, but |
+| it might well be partly (or even completely) finished waiting by the  |
+| time ``rcu_barrier()`` is invoked. In that case, ``rcu_barrier()``    |
+| need only wait for the remaining portion of the grace period to       |
+| elapse. So even if there are quite a few callbacks posted,            |
+| ``rcu_barrier()`` might well return quite quickly.                    |
+|                                                                       |
+| So if you need to wait for a grace period as well as for all          |
+| pre-existing callbacks, you will need to invoke both                  |
+| ``synchronize_rcu()`` and ``rcu_barrier()``. If latency is a concern, |
+| you can always use workqueues to invoke them concurrently.            |
++-----------------------------------------------------------------------+
+
+Hotplug CPU
+~~~~~~~~~~~
+
+The Linux kernel supports CPU hotplug, which means that CPUs can come
+and go. It is of course illegal to use any RCU API member from an
+offline CPU, with the exception of `SRCU <#Sleepable%20RCU>`__ read-side
+critical sections. This requirement was present from day one in
+DYNIX/ptx, but on the other hand, the Linux kernel's CPU-hotplug
+implementation is “interesting.”
+
+The Linux-kernel CPU-hotplug implementation has notifiers that are used
+to allow the various kernel subsystems (including RCU) to respond
+appropriately to a given CPU-hotplug operation. Most RCU operations may
+be invoked from CPU-hotplug notifiers, including even synchronous
+grace-period operations such as ``synchronize_rcu()`` and
+``synchronize_rcu_expedited()``.
+
+However, all-callback-wait operations such as ``rcu_barrier()`` are also
+not supported, due to the fact that there are phases of CPU-hotplug
+operations where the outgoing CPU's callbacks will not be invoked until
+after the CPU-hotplug operation ends, which could also result in
+deadlock. Furthermore, ``rcu_barrier()`` blocks CPU-hotplug operations
+during its execution, which results in another type of deadlock when
+invoked from a CPU-hotplug notifier.
+
+Scheduler and RCU
+~~~~~~~~~~~~~~~~~
+
+RCU depends on the scheduler, and the scheduler uses RCU to protect some
+of its data structures. The preemptible-RCU ``rcu_read_unlock()``
+implementation must therefore be written carefully to avoid deadlocks
+involving the scheduler's runqueue and priority-inheritance locks. In
+particular, ``rcu_read_unlock()`` must tolerate an interrupt where the
+interrupt handler invokes both ``rcu_read_lock()`` and
+``rcu_read_unlock()``. This possibility requires ``rcu_read_unlock()``
+to use negative nesting levels to avoid destructive recursion via
+interrupt handler's use of RCU.
+
+This scheduler-RCU requirement came as a `complete
+surprise <https://lwn.net/Articles/453002/>`__.
+
+As noted above, RCU makes use of kthreads, and it is necessary to avoid
+excessive CPU-time accumulation by these kthreads. This requirement was
+no surprise, but RCU's violation of it when running context-switch-heavy
+workloads when built with ``CONFIG_NO_HZ_FULL=y`` `did come as a
+surprise
+[PDF] <http://www.rdrop.com/users/paulmck/scalability/paper/BareMetal.2015.01.15b.pdf>`__.
+RCU has made good progress towards meeting this requirement, even for
+context-switch-heavy ``CONFIG_NO_HZ_FULL=y`` workloads, but there is
+room for further improvement.
+
+It is forbidden to hold any of scheduler's runqueue or
+priority-inheritance spinlocks across an ``rcu_read_unlock()`` unless
+interrupts have been disabled across the entire RCU read-side critical
+section, that is, up to and including the matching ``rcu_read_lock()``.
+Violating this restriction can result in deadlocks involving these
+scheduler spinlocks. There was hope that this restriction might be
+lifted when interrupt-disabled calls to ``rcu_read_unlock()`` started
+deferring the reporting of the resulting RCU-preempt quiescent state
+until the end of the corresponding interrupts-disabled region.
+Unfortunately, timely reporting of the corresponding quiescent state to
+expedited grace periods requires a call to ``raise_softirq()``, which
+can acquire these scheduler spinlocks. In addition, real-time systems
+using RCU priority boosting need this restriction to remain in effect
+because deferred quiescent-state reporting would also defer deboosting,
+which in turn would degrade real-time latencies.
+
+In theory, if a given RCU read-side critical section could be guaranteed
+to be less than one second in duration, holding a scheduler spinlock
+across that critical section's ``rcu_read_unlock()`` would require only
+that preemption be disabled across the entire RCU read-side critical
+section, not interrupts. Unfortunately, given the possibility of vCPU
+preemption, long-running interrupts, and so on, it is not possible in
+practice to guarantee that a given RCU read-side critical section will
+complete in less than one second. Therefore, as noted above, if
+scheduler spinlocks are held across a given call to
+``rcu_read_unlock()``, interrupts must be disabled across the entire RCU
+read-side critical section.
+
+Tracing and RCU
+~~~~~~~~~~~~~~~
+
+It is possible to use tracing on RCU code, but tracing itself uses RCU.
+For this reason, ``rcu_dereference_raw_check()`` is provided for use
+by tracing, which avoids the destructive recursion that could otherwise
+ensue. This API is also used by virtualization in some architectures,
+where RCU readers execute in environments in which tracing cannot be
+used. The tracing folks both located the requirement and provided the
+needed fix, so this surprise requirement was relatively painless.
+
+Accesses to User Memory and RCU
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+The kernel needs to access user-space memory, for example, to access data
+referenced by system-call parameters.  The ``get_user()`` macro does this job.
+
+However, user-space memory might well be paged out, which means that
+``get_user()`` might well page-fault and thus block while waiting for the
+resulting I/O to complete.  It would be a very bad thing for the compiler to
+reorder a ``get_user()`` invocation into an RCU read-side critical section.
+
+For example, suppose that the source code looked like this:
+
+  ::
+
+       1 rcu_read_lock();
+       2 p = rcu_dereference(gp);
+       3 v = p->value;
+       4 rcu_read_unlock();
+       5 get_user(user_v, user_p);
+       6 do_something_with(v, user_v);
+
+The compiler must not be permitted to transform this source code into
+the following:
+
+  ::
+
+       1 rcu_read_lock();
+       2 p = rcu_dereference(gp);
+       3 get_user(user_v, user_p); // BUG: POSSIBLE PAGE FAULT!!!
+       4 v = p->value;
+       5 rcu_read_unlock();
+       6 do_something_with(v, user_v);
+
+If the compiler did make this transformation in a ``CONFIG_PREEMPT=n`` kernel
+build, and if ``get_user()`` did page fault, the result would be a quiescent
+state in the middle of an RCU read-side critical section.  This misplaced
+quiescent state could result in line 4 being a use-after-free access,
+which could be bad for your kernel's actuarial statistics.  Similar examples
+can be constructed with the call to ``get_user()`` preceding the
+``rcu_read_lock()``.
+
+Unfortunately, ``get_user()`` doesn't have any particular ordering properties,
+and in some architectures the underlying ``asm`` isn't even marked
+``volatile``.  And even if it was marked ``volatile``, the above access to
+``p->value`` is not volatile, so the compiler would not have any reason to keep
+those two accesses in order.
+
+Therefore, the Linux-kernel definitions of ``rcu_read_lock()`` and
+``rcu_read_unlock()`` must act as compiler barriers, at least for outermost
+instances of ``rcu_read_lock()`` and ``rcu_read_unlock()`` within a nested set
+of RCU read-side critical sections.
+
+Energy Efficiency
+~~~~~~~~~~~~~~~~~
+
+Interrupting idle CPUs is considered socially unacceptable, especially
+by people with battery-powered embedded systems. RCU therefore conserves
+energy by detecting which CPUs are idle, including tracking CPUs that
+have been interrupted from idle. This is a large part of the
+energy-efficiency requirement, so I learned of this via an irate phone
+call.
+
+Because RCU avoids interrupting idle CPUs, it is illegal to execute an
+RCU read-side critical section on an idle CPU. (Kernels built with
+``CONFIG_PROVE_RCU=y`` will splat if you try it.) The ``RCU_NONIDLE()``
+macro and ``_rcuidle`` event tracing is provided to work around this
+restriction. In addition, ``rcu_is_watching()`` may be used to test
+whether or not it is currently legal to run RCU read-side critical
+sections on this CPU. I learned of the need for diagnostics on the one
+hand and ``RCU_NONIDLE()`` on the other while inspecting idle-loop code.
+Steven Rostedt supplied ``_rcuidle`` event tracing, which is used quite
+heavily in the idle loop. However, there are some restrictions on the
+code placed within ``RCU_NONIDLE()``:
+
+#. Blocking is prohibited. In practice, this is not a serious
+   restriction given that idle tasks are prohibited from blocking to
+   begin with.
+#. Although nesting ``RCU_NONIDLE()`` is permitted, they cannot nest
+   indefinitely deeply. However, given that they can be nested on the
+   order of a million deep, even on 32-bit systems, this should not be a
+   serious restriction. This nesting limit would probably be reached
+   long after the compiler OOMed or the stack overflowed.
+#. Any code path that enters ``RCU_NONIDLE()`` must sequence out of that
+   same ``RCU_NONIDLE()``. For example, the following is grossly
+   illegal:
+
+      ::
+
+	  1     RCU_NONIDLE({
+	  2       do_something();
+	  3       goto bad_idea;  /* BUG!!! */
+	  4       do_something_else();});
+	  5   bad_idea:
+
+
+   It is just as illegal to transfer control into the middle of
+   ``RCU_NONIDLE()``'s argument. Yes, in theory, you could transfer in
+   as long as you also transferred out, but in practice you could also
+   expect to get sharply worded review comments.
+
+It is similarly socially unacceptable to interrupt an ``nohz_full`` CPU
+running in userspace. RCU must therefore track ``nohz_full`` userspace
+execution. RCU must therefore be able to sample state at two points in
+time, and be able to determine whether or not some other CPU spent any
+time idle and/or executing in userspace.
+
+These energy-efficiency requirements have proven quite difficult to
+understand and to meet, for example, there have been more than five
+clean-sheet rewrites of RCU's energy-efficiency code, the last of which
+was finally able to demonstrate `real energy savings running on real
+hardware
+[PDF] <http://www.rdrop.com/users/paulmck/realtime/paper/AMPenergy.2013.04.19a.pdf>`__.
+As noted earlier, I learned of many of these requirements via angry
+phone calls: Flaming me on the Linux-kernel mailing list was apparently
+not sufficient to fully vent their ire at RCU's energy-efficiency bugs!
+
+Scheduling-Clock Interrupts and RCU
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+The kernel transitions between in-kernel non-idle execution, userspace
+execution, and the idle loop. Depending on kernel configuration, RCU
+handles these states differently:
+
++-----------------+------------------+------------------+-----------------+
+| ``HZ`` Kconfig  | In-Kernel        | Usermode         | Idle            |
++=================+==================+==================+=================+
+| ``HZ_PERIODIC`` | Can rely on      | Can rely on      | Can rely on     |
+|                 | scheduling-clock | scheduling-clock | RCU's           |
+|                 | interrupt.       | interrupt and    | dyntick-idle    |
+|                 |                  | its detection    | detection.      |
+|                 |                  | of interrupt     |                 |
+|                 |                  | from usermode.   |                 |
++-----------------+------------------+------------------+-----------------+
+| ``NO_HZ_IDLE``  | Can rely on      | Can rely on      | Can rely on     |
+|                 | scheduling-clock | scheduling-clock | RCU's           |
+|                 | interrupt.       | interrupt and    | dyntick-idle    |
+|                 |                  | its detection    | detection.      |
+|                 |                  | of interrupt     |                 |
+|                 |                  | from usermode.   |                 |
++-----------------+------------------+------------------+-----------------+
+| ``NO_HZ_FULL``  | Can only         | Can rely on      | Can rely on     |
+|                 | sometimes rely   | RCU's            | RCU's           |
+|                 | on               | dyntick-idle     | dyntick-idle    |
+|                 | scheduling-clock | detection.       | detection.      |
+|                 | interrupt. In    |                  |                 |
+|                 | other cases, it  |                  |                 |
+|                 | is necessary to  |                  |                 |
+|                 | bound kernel     |                  |                 |
+|                 | execution times  |                  |                 |
+|                 | and/or use       |                  |                 |
+|                 | IPIs.            |                  |                 |
++-----------------+------------------+------------------+-----------------+
+
++-----------------------------------------------------------------------+
+| **Quick Quiz**:                                                       |
++-----------------------------------------------------------------------+
+| Why can't ``NO_HZ_FULL`` in-kernel execution rely on the              |
+| scheduling-clock interrupt, just like ``HZ_PERIODIC`` and             |
+| ``NO_HZ_IDLE`` do?                                                    |
++-----------------------------------------------------------------------+
+| **Answer**:                                                           |
++-----------------------------------------------------------------------+
+| Because, as a performance optimization, ``NO_HZ_FULL`` does not       |
+| necessarily re-enable the scheduling-clock interrupt on entry to each |
+| and every system call.                                                |
++-----------------------------------------------------------------------+
+
+However, RCU must be reliably informed as to whether any given CPU is
+currently in the idle loop, and, for ``NO_HZ_FULL``, also whether that
+CPU is executing in usermode, as discussed
+`earlier <#Energy%20Efficiency>`__. It also requires that the
+scheduling-clock interrupt be enabled when RCU needs it to be:
+
+#. If a CPU is either idle or executing in usermode, and RCU believes it
+   is non-idle, the scheduling-clock tick had better be running.
+   Otherwise, you will get RCU CPU stall warnings. Or at best, very long
+   (11-second) grace periods, with a pointless IPI waking the CPU from
+   time to time.
+#. If a CPU is in a portion of the kernel that executes RCU read-side
+   critical sections, and RCU believes this CPU to be idle, you will get
+   random memory corruption. **DON'T DO THIS!!!**
+   This is one reason to test with lockdep, which will complain about
+   this sort of thing.
+#. If a CPU is in a portion of the kernel that is absolutely positively
+   no-joking guaranteed to never execute any RCU read-side critical
+   sections, and RCU believes this CPU to to be idle, no problem. This
+   sort of thing is used by some architectures for light-weight
+   exception handlers, which can then avoid the overhead of
+   ``rcu_irq_enter()`` and ``rcu_irq_exit()`` at exception entry and
+   exit, respectively. Some go further and avoid the entireties of
+   ``irq_enter()`` and ``irq_exit()``.
+   Just make very sure you are running some of your tests with
+   ``CONFIG_PROVE_RCU=y``, just in case one of your code paths was in
+   fact joking about not doing RCU read-side critical sections.
+#. If a CPU is executing in the kernel with the scheduling-clock
+   interrupt disabled and RCU believes this CPU to be non-idle, and if
+   the CPU goes idle (from an RCU perspective) every few jiffies, no
+   problem. It is usually OK for there to be the occasional gap between
+   idle periods of up to a second or so.
+   If the gap grows too long, you get RCU CPU stall warnings.
+#. If a CPU is either idle or executing in usermode, and RCU believes it
+   to be idle, of course no problem.
+#. If a CPU is executing in the kernel, the kernel code path is passing
+   through quiescent states at a reasonable frequency (preferably about
+   once per few jiffies, but the occasional excursion to a second or so
+   is usually OK) and the scheduling-clock interrupt is enabled, of
+   course no problem.
+   If the gap between a successive pair of quiescent states grows too
+   long, you get RCU CPU stall warnings.
+
++-----------------------------------------------------------------------+
+| **Quick Quiz**:                                                       |
++-----------------------------------------------------------------------+
+| But what if my driver has a hardware interrupt handler that can run   |
+| for many seconds? I cannot invoke ``schedule()`` from an hardware     |
+| interrupt handler, after all!                                         |
++-----------------------------------------------------------------------+
+| **Answer**:                                                           |
++-----------------------------------------------------------------------+
+| One approach is to do ``rcu_irq_exit();rcu_irq_enter();`` every so    |
+| often. But given that long-running interrupt handlers can cause other |
+| problems, not least for response time, shouldn't you work to keep     |
+| your interrupt handler's runtime within reasonable bounds?            |
++-----------------------------------------------------------------------+
+
+But as long as RCU is properly informed of kernel state transitions
+between in-kernel execution, usermode execution, and idle, and as long
+as the scheduling-clock interrupt is enabled when RCU needs it to be,
+you can rest assured that the bugs you encounter will be in some other
+part of RCU or some other part of the kernel!
+
+Memory Efficiency
+~~~~~~~~~~~~~~~~~
+
+Although small-memory non-realtime systems can simply use Tiny RCU, code
+size is only one aspect of memory efficiency. Another aspect is the size
+of the ``rcu_head`` structure used by ``call_rcu()`` and
+``kfree_rcu()``. Although this structure contains nothing more than a
+pair of pointers, it does appear in many RCU-protected data structures,
+including some that are size critical. The ``page`` structure is a case
+in point, as evidenced by the many occurrences of the ``union`` keyword
+within that structure.
+
+This need for memory efficiency is one reason that RCU uses hand-crafted
+singly linked lists to track the ``rcu_head`` structures that are
+waiting for a grace period to elapse. It is also the reason why
+``rcu_head`` structures do not contain debug information, such as fields
+tracking the file and line of the ``call_rcu()`` or ``kfree_rcu()`` that
+posted them. Although this information might appear in debug-only kernel
+builds at some point, in the meantime, the ``->func`` field will often
+provide the needed debug information.
+
+However, in some cases, the need for memory efficiency leads to even
+more extreme measures. Returning to the ``page`` structure, the
+``rcu_head`` field shares storage with a great many other structures
+that are used at various points in the corresponding page's lifetime. In
+order to correctly resolve certain `race
+conditions <https://lkml.kernel.org/g/1439976106-137226-1-git-send-email-kirill.shutemov@linux.intel.com>`__,
+the Linux kernel's memory-management subsystem needs a particular bit to
+remain zero during all phases of grace-period processing, and that bit
+happens to map to the bottom bit of the ``rcu_head`` structure's
+``->next`` field. RCU makes this guarantee as long as ``call_rcu()`` is
+used to post the callback, as opposed to ``kfree_rcu()`` or some future
+“lazy” variant of ``call_rcu()`` that might one day be created for
+energy-efficiency purposes.
+
+That said, there are limits. RCU requires that the ``rcu_head``
+structure be aligned to a two-byte boundary, and passing a misaligned
+``rcu_head`` structure to one of the ``call_rcu()`` family of functions
+will result in a splat. It is therefore necessary to exercise caution
+when packing structures containing fields of type ``rcu_head``. Why not
+a four-byte or even eight-byte alignment requirement? Because the m68k
+architecture provides only two-byte alignment, and thus acts as
+alignment's least common denominator.
+
+The reason for reserving the bottom bit of pointers to ``rcu_head``
+structures is to leave the door open to “lazy” callbacks whose
+invocations can safely be deferred. Deferring invocation could
+potentially have energy-efficiency benefits, but only if the rate of
+non-lazy callbacks decreases significantly for some important workload.
+In the meantime, reserving the bottom bit keeps this option open in case
+it one day becomes useful.
+
+Performance, Scalability, Response Time, and Reliability
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+Expanding on the `earlier
+discussion <#Performance%20and%20Scalability>`__, RCU is used heavily by
+hot code paths in performance-critical portions of the Linux kernel's
+networking, security, virtualization, and scheduling code paths. RCU
+must therefore use efficient implementations, especially in its
+read-side primitives. To that end, it would be good if preemptible RCU's
+implementation of ``rcu_read_lock()`` could be inlined, however, doing
+this requires resolving ``#include`` issues with the ``task_struct``
+structure.
+
+The Linux kernel supports hardware configurations with up to 4096 CPUs,
+which means that RCU must be extremely scalable. Algorithms that involve
+frequent acquisitions of global locks or frequent atomic operations on
+global variables simply cannot be tolerated within the RCU
+implementation. RCU therefore makes heavy use of a combining tree based
+on the ``rcu_node`` structure. RCU is required to tolerate all CPUs
+continuously invoking any combination of RCU's runtime primitives with
+minimal per-operation overhead. In fact, in many cases, increasing load
+must *decrease* the per-operation overhead, witness the batching
+optimizations for ``synchronize_rcu()``, ``call_rcu()``,
+``synchronize_rcu_expedited()``, and ``rcu_barrier()``. As a general
+rule, RCU must cheerfully accept whatever the rest of the Linux kernel
+decides to throw at it.
+
+The Linux kernel is used for real-time workloads, especially in
+conjunction with the `-rt
+patchset <https://rt.wiki.kernel.org/index.php/Main_Page>`__. The
+real-time-latency response requirements are such that the traditional
+approach of disabling preemption across RCU read-side critical sections
+is inappropriate. Kernels built with ``CONFIG_PREEMPT=y`` therefore use
+an RCU implementation that allows RCU read-side critical sections to be
+preempted. This requirement made its presence known after users made it
+clear that an earlier `real-time
+patch <https://lwn.net/Articles/107930/>`__ did not meet their needs, in
+conjunction with some `RCU
+issues <https://lkml.kernel.org/g/20050318002026.GA2693@us.ibm.com>`__
+encountered by a very early version of the -rt patchset.
+
+In addition, RCU must make do with a sub-100-microsecond real-time
+latency budget. In fact, on smaller systems with the -rt patchset, the
+Linux kernel provides sub-20-microsecond real-time latencies for the
+whole kernel, including RCU. RCU's scalability and latency must
+therefore be sufficient for these sorts of configurations. To my
+surprise, the sub-100-microsecond real-time latency budget `applies to
+even the largest systems
+[PDF] <http://www.rdrop.com/users/paulmck/realtime/paper/bigrt.2013.01.31a.LCA.pdf>`__,
+up to and including systems with 4096 CPUs. This real-time requirement
+motivated the grace-period kthread, which also simplified handling of a
+number of race conditions.
+
+RCU must avoid degrading real-time response for CPU-bound threads,
+whether executing in usermode (which is one use case for
+``CONFIG_NO_HZ_FULL=y``) or in the kernel. That said, CPU-bound loops in
+the kernel must execute ``cond_resched()`` at least once per few tens of
+milliseconds in order to avoid receiving an IPI from RCU.
+
+Finally, RCU's status as a synchronization primitive means that any RCU
+failure can result in arbitrary memory corruption that can be extremely
+difficult to debug. This means that RCU must be extremely reliable,
+which in practice also means that RCU must have an aggressive
+stress-test suite. This stress-test suite is called ``rcutorture``.
+
+Although the need for ``rcutorture`` was no surprise, the current
+immense popularity of the Linux kernel is posing interesting—and perhaps
+unprecedented—validation challenges. To see this, keep in mind that
+there are well over one billion instances of the Linux kernel running
+today, given Android smartphones, Linux-powered televisions, and
+servers. This number can be expected to increase sharply with the advent
+of the celebrated Internet of Things.
+
+Suppose that RCU contains a race condition that manifests on average
+once per million years of runtime. This bug will be occurring about
+three times per *day* across the installed base. RCU could simply hide
+behind hardware error rates, given that no one should really expect
+their smartphone to last for a million years. However, anyone taking too
+much comfort from this thought should consider the fact that in most
+jurisdictions, a successful multi-year test of a given mechanism, which
+might include a Linux kernel, suffices for a number of types of
+safety-critical certifications. In fact, rumor has it that the Linux
+kernel is already being used in production for safety-critical
+applications. I don't know about you, but I would feel quite bad if a
+bug in RCU killed someone. Which might explain my recent focus on
+validation and verification.
+
+Other RCU Flavors
+-----------------
+
+One of the more surprising things about RCU is that there are now no
+fewer than five *flavors*, or API families. In addition, the primary
+flavor that has been the sole focus up to this point has two different
+implementations, non-preemptible and preemptible. The other four flavors
+are listed below, with requirements for each described in a separate
+section.
+
+#. `Bottom-Half Flavor (Historical)`_
+#. `Sched Flavor (Historical)`_
+#. `Sleepable RCU`_
+#. `Tasks RCU`_
+
+Bottom-Half Flavor (Historical)
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+The RCU-bh flavor of RCU has since been expressed in terms of the other
+RCU flavors as part of a consolidation of the three flavors into a
+single flavor. The read-side API remains, and continues to disable
+softirq and to be accounted for by lockdep. Much of the material in this
+section is therefore strictly historical in nature.
+
+The softirq-disable (AKA “bottom-half”, hence the “_bh” abbreviations)
+flavor of RCU, or *RCU-bh*, was developed by Dipankar Sarma to provide a
+flavor of RCU that could withstand the network-based denial-of-service
+attacks researched by Robert Olsson. These attacks placed so much
+networking load on the system that some of the CPUs never exited softirq
+execution, which in turn prevented those CPUs from ever executing a
+context switch, which, in the RCU implementation of that time, prevented
+grace periods from ever ending. The result was an out-of-memory
+condition and a system hang.
+
+The solution was the creation of RCU-bh, which does
+``local_bh_disable()`` across its read-side critical sections, and which
+uses the transition from one type of softirq processing to another as a
+quiescent state in addition to context switch, idle, user mode, and
+offline. This means that RCU-bh grace periods can complete even when
+some of the CPUs execute in softirq indefinitely, thus allowing
+algorithms based on RCU-bh to withstand network-based denial-of-service
+attacks.
+
+Because ``rcu_read_lock_bh()`` and ``rcu_read_unlock_bh()`` disable and
+re-enable softirq handlers, any attempt to start a softirq handlers
+during the RCU-bh read-side critical section will be deferred. In this
+case, ``rcu_read_unlock_bh()`` will invoke softirq processing, which can
+take considerable time. One can of course argue that this softirq
+overhead should be associated with the code following the RCU-bh
+read-side critical section rather than ``rcu_read_unlock_bh()``, but the
+fact is that most profiling tools cannot be expected to make this sort
+of fine distinction. For example, suppose that a three-millisecond-long
+RCU-bh read-side critical section executes during a time of heavy
+networking load. There will very likely be an attempt to invoke at least
+one softirq handler during that three milliseconds, but any such
+invocation will be delayed until the time of the
+``rcu_read_unlock_bh()``. This can of course make it appear at first
+glance as if ``rcu_read_unlock_bh()`` was executing very slowly.
+
+The `RCU-bh
+API <https://lwn.net/Articles/609973/#RCU%20Per-Flavor%20API%20Table>`__
+includes ``rcu_read_lock_bh()``, ``rcu_read_unlock_bh()``,
+``rcu_dereference_bh()``, ``rcu_dereference_bh_check()``,
+``synchronize_rcu_bh()``, ``synchronize_rcu_bh_expedited()``,
+``call_rcu_bh()``, ``rcu_barrier_bh()``, and
+``rcu_read_lock_bh_held()``. However, the update-side APIs are now
+simple wrappers for other RCU flavors, namely RCU-sched in
+CONFIG_PREEMPT=n kernels and RCU-preempt otherwise.
+
+Sched Flavor (Historical)
+~~~~~~~~~~~~~~~~~~~~~~~~~
+
+The RCU-sched flavor of RCU has since been expressed in terms of the
+other RCU flavors as part of a consolidation of the three flavors into a
+single flavor. The read-side API remains, and continues to disable
+preemption and to be accounted for by lockdep. Much of the material in
+this section is therefore strictly historical in nature.
+
+Before preemptible RCU, waiting for an RCU grace period had the side
+effect of also waiting for all pre-existing interrupt and NMI handlers.
+However, there are legitimate preemptible-RCU implementations that do
+not have this property, given that any point in the code outside of an
+RCU read-side critical section can be a quiescent state. Therefore,
+*RCU-sched* was created, which follows “classic” RCU in that an
+RCU-sched grace period waits for for pre-existing interrupt and NMI
+handlers. In kernels built with ``CONFIG_PREEMPT=n``, the RCU and
+RCU-sched APIs have identical implementations, while kernels built with
+``CONFIG_PREEMPT=y`` provide a separate implementation for each.
+
+Note well that in ``CONFIG_PREEMPT=y`` kernels,
+``rcu_read_lock_sched()`` and ``rcu_read_unlock_sched()`` disable and
+re-enable preemption, respectively. This means that if there was a
+preemption attempt during the RCU-sched read-side critical section,
+``rcu_read_unlock_sched()`` will enter the scheduler, with all the
+latency and overhead entailed. Just as with ``rcu_read_unlock_bh()``,
+this can make it look as if ``rcu_read_unlock_sched()`` was executing
+very slowly. However, the highest-priority task won't be preempted, so
+that task will enjoy low-overhead ``rcu_read_unlock_sched()``
+invocations.
+
+The `RCU-sched
+API <https://lwn.net/Articles/609973/#RCU%20Per-Flavor%20API%20Table>`__
+includes ``rcu_read_lock_sched()``, ``rcu_read_unlock_sched()``,
+``rcu_read_lock_sched_notrace()``, ``rcu_read_unlock_sched_notrace()``,
+``rcu_dereference_sched()``, ``rcu_dereference_sched_check()``,
+``synchronize_sched()``, ``synchronize_rcu_sched_expedited()``,
+``call_rcu_sched()``, ``rcu_barrier_sched()``, and
+``rcu_read_lock_sched_held()``. However, anything that disables
+preemption also marks an RCU-sched read-side critical section, including
+``preempt_disable()`` and ``preempt_enable()``, ``local_irq_save()`` and
+``local_irq_restore()``, and so on.
+
+Sleepable RCU
+~~~~~~~~~~~~~
+
+For well over a decade, someone saying “I need to block within an RCU
+read-side critical section” was a reliable indication that this someone
+did not understand RCU. After all, if you are always blocking in an RCU
+read-side critical section, you can probably afford to use a
+higher-overhead synchronization mechanism. However, that changed with
+the advent of the Linux kernel's notifiers, whose RCU read-side critical
+sections almost never sleep, but sometimes need to. This resulted in the
+introduction of `sleepable RCU <https://lwn.net/Articles/202847/>`__, or
+*SRCU*.
+
+SRCU allows different domains to be defined, with each such domain
+defined by an instance of an ``srcu_struct`` structure. A pointer to
+this structure must be passed in to each SRCU function, for example,
+``synchronize_srcu(&ss)``, where ``ss`` is the ``srcu_struct``
+structure. The key benefit of these domains is that a slow SRCU reader
+in one domain does not delay an SRCU grace period in some other domain.
+That said, one consequence of these domains is that read-side code must
+pass a “cookie” from ``srcu_read_lock()`` to ``srcu_read_unlock()``, for
+example, as follows:
+
+   ::
+
+       1 int idx;
+       2
+       3 idx = srcu_read_lock(&ss);
+       4 do_something();
+       5 srcu_read_unlock(&ss, idx);
+
+As noted above, it is legal to block within SRCU read-side critical
+sections, however, with great power comes great responsibility. If you
+block forever in one of a given domain's SRCU read-side critical
+sections, then that domain's grace periods will also be blocked forever.
+Of course, one good way to block forever is to deadlock, which can
+happen if any operation in a given domain's SRCU read-side critical
+section can wait, either directly or indirectly, for that domain's grace
+period to elapse. For example, this results in a self-deadlock:
+
+   ::
+
+       1 int idx;
+       2
+       3 idx = srcu_read_lock(&ss);
+       4 do_something();
+       5 synchronize_srcu(&ss);
+       6 srcu_read_unlock(&ss, idx);
+
+However, if line 5 acquired a mutex that was held across a
+``synchronize_srcu()`` for domain ``ss``, deadlock would still be
+possible. Furthermore, if line 5 acquired a mutex that was held across a
+``synchronize_srcu()`` for some other domain ``ss1``, and if an
+``ss1``-domain SRCU read-side critical section acquired another mutex
+that was held across as ``ss``-domain ``synchronize_srcu()``, deadlock
+would again be possible. Such a deadlock cycle could extend across an
+arbitrarily large number of different SRCU domains. Again, with great
+power comes great responsibility.
+
+Unlike the other RCU flavors, SRCU read-side critical sections can run
+on idle and even offline CPUs. This ability requires that
+``srcu_read_lock()`` and ``srcu_read_unlock()`` contain memory barriers,
+which means that SRCU readers will run a bit slower than would RCU
+readers. It also motivates the ``smp_mb__after_srcu_read_unlock()`` API,
+which, in combination with ``srcu_read_unlock()``, guarantees a full
+memory barrier.
+
+Also unlike other RCU flavors, ``synchronize_srcu()`` may **not** be
+invoked from CPU-hotplug notifiers, due to the fact that SRCU grace
+periods make use of timers and the possibility of timers being
+temporarily “stranded” on the outgoing CPU. This stranding of timers
+means that timers posted to the outgoing CPU will not fire until late in
+the CPU-hotplug process. The problem is that if a notifier is waiting on
+an SRCU grace period, that grace period is waiting on a timer, and that
+timer is stranded on the outgoing CPU, then the notifier will never be
+awakened, in other words, deadlock has occurred. This same situation of
+course also prohibits ``srcu_barrier()`` from being invoked from
+CPU-hotplug notifiers.
+
+SRCU also differs from other RCU flavors in that SRCU's expedited and
+non-expedited grace periods are implemented by the same mechanism. This
+means that in the current SRCU implementation, expediting a future grace
+period has the side effect of expediting all prior grace periods that
+have not yet completed. (But please note that this is a property of the
+current implementation, not necessarily of future implementations.) In
+addition, if SRCU has been idle for longer than the interval specified
+by the ``srcutree.exp_holdoff`` kernel boot parameter (25 microseconds
+by default), and if a ``synchronize_srcu()`` invocation ends this idle
+period, that invocation will be automatically expedited.
+
+As of v4.12, SRCU's callbacks are maintained per-CPU, eliminating a
+locking bottleneck present in prior kernel versions. Although this will
+allow users to put much heavier stress on ``call_srcu()``, it is
+important to note that SRCU does not yet take any special steps to deal
+with callback flooding. So if you are posting (say) 10,000 SRCU
+callbacks per second per CPU, you are probably totally OK, but if you
+intend to post (say) 1,000,000 SRCU callbacks per second per CPU, please
+run some tests first. SRCU just might need a few adjustment to deal with
+that sort of load. Of course, your mileage may vary based on the speed
+of your CPUs and the size of your memory.
+
+The `SRCU
+API <https://lwn.net/Articles/609973/#RCU%20Per-Flavor%20API%20Table>`__
+includes ``srcu_read_lock()``, ``srcu_read_unlock()``,
+``srcu_dereference()``, ``srcu_dereference_check()``,
+``synchronize_srcu()``, ``synchronize_srcu_expedited()``,
+``call_srcu()``, ``srcu_barrier()``, and ``srcu_read_lock_held()``. It
+also includes ``DEFINE_SRCU()``, ``DEFINE_STATIC_SRCU()``, and
+``init_srcu_struct()`` APIs for defining and initializing
+``srcu_struct`` structures.
+
+Tasks RCU
+~~~~~~~~~
+
+Some forms of tracing use “trampolines” to handle the binary rewriting
+required to install different types of probes. It would be good to be
+able to free old trampolines, which sounds like a job for some form of
+RCU. However, because it is necessary to be able to install a trace
+anywhere in the code, it is not possible to use read-side markers such
+as ``rcu_read_lock()`` and ``rcu_read_unlock()``. In addition, it does
+not work to have these markers in the trampoline itself, because there
+would need to be instructions following ``rcu_read_unlock()``. Although
+``synchronize_rcu()`` would guarantee that execution reached the
+``rcu_read_unlock()``, it would not be able to guarantee that execution
+had completely left the trampoline.
+
+The solution, in the form of `Tasks
+RCU <https://lwn.net/Articles/607117/>`__, is to have implicit read-side
+critical sections that are delimited by voluntary context switches, that
+is, calls to ``schedule()``, ``cond_resched()``, and
+``synchronize_rcu_tasks()``. In addition, transitions to and from
+userspace execution also delimit tasks-RCU read-side critical sections.
+
+The tasks-RCU API is quite compact, consisting only of
+``call_rcu_tasks()``, ``synchronize_rcu_tasks()``, and
+``rcu_barrier_tasks()``. In ``CONFIG_PREEMPT=n`` kernels, trampolines
+cannot be preempted, so these APIs map to ``call_rcu()``,
+``synchronize_rcu()``, and ``rcu_barrier()``, respectively. In
+``CONFIG_PREEMPT=y`` kernels, trampolines can be preempted, and these
+three APIs are therefore implemented by separate functions that check
+for voluntary context switches.
+
+Possible Future Changes
+-----------------------
+
+One of the tricks that RCU uses to attain update-side scalability is to
+increase grace-period latency with increasing numbers of CPUs. If this
+becomes a serious problem, it will be necessary to rework the
+grace-period state machine so as to avoid the need for the additional
+latency.
+
+RCU disables CPU hotplug in a few places, perhaps most notably in the
+``rcu_barrier()`` operations. If there is a strong reason to use
+``rcu_barrier()`` in CPU-hotplug notifiers, it will be necessary to
+avoid disabling CPU hotplug. This would introduce some complexity, so
+there had better be a *very* good reason.
+
+The tradeoff between grace-period latency on the one hand and
+interruptions of other CPUs on the other hand may need to be
+re-examined. The desire is of course for zero grace-period latency as
+well as zero interprocessor interrupts undertaken during an expedited
+grace period operation. While this ideal is unlikely to be achievable,
+it is quite possible that further improvements can be made.
+
+The multiprocessor implementations of RCU use a combining tree that
+groups CPUs so as to reduce lock contention and increase cache locality.
+However, this combining tree does not spread its memory across NUMA
+nodes nor does it align the CPU groups with hardware features such as
+sockets or cores. Such spreading and alignment is currently believed to
+be unnecessary because the hotpath read-side primitives do not access
+the combining tree, nor does ``call_rcu()`` in the common case. If you
+believe that your architecture needs such spreading and alignment, then
+your architecture should also benefit from the
+``rcutree.rcu_fanout_leaf`` boot parameter, which can be set to the
+number of CPUs in a socket, NUMA node, or whatever. If the number of
+CPUs is too large, use a fraction of the number of CPUs. If the number
+of CPUs is a large prime number, well, that certainly is an
+“interesting” architectural choice! More flexible arrangements might be
+considered, but only if ``rcutree.rcu_fanout_leaf`` has proven
+inadequate, and only if the inadequacy has been demonstrated by a
+carefully run and realistic system-level workload.
+
+Please note that arrangements that require RCU to remap CPU numbers will
+require extremely good demonstration of need and full exploration of
+alternatives.
+
+RCU's various kthreads are reasonably recent additions. It is quite
+likely that adjustments will be required to more gracefully handle
+extreme loads. It might also be necessary to be able to relate CPU
+utilization by RCU's kthreads and softirq handlers to the code that
+instigated this CPU utilization. For example, RCU callback overhead
+might be charged back to the originating ``call_rcu()`` instance, though
+probably not in production kernels.
+
+Additional work may be required to provide reasonable forward-progress
+guarantees under heavy load for grace periods and for callback
+invocation.
+
+Summary
+-------
+
+This document has presented more than two decade's worth of RCU
+requirements. Given that the requirements keep changing, this will not
+be the last word on this subject, but at least it serves to get an
+important subset of the requirements set forth.
+
+Acknowledgments
+---------------
+
+I am grateful to Steven Rostedt, Lai Jiangshan, Ingo Molnar, Oleg
+Nesterov, Borislav Petkov, Peter Zijlstra, Boqun Feng, and Andy
+Lutomirski for their help in rendering this article human readable, and
+to Michelle Rankin for her support of this effort. Other contributions
+are acknowledged in the Linux kernel's git archive.
diff --git a/Documentation/RCU/index.rst b/Documentation/RCU/index.rst
index 340a9725676c..5c99185710fa 100644
--- a/Documentation/RCU/index.rst
+++ b/Documentation/RCU/index.rst
@@ -5,12 +5,17 @@ RCU concepts
 ============
 
 .. toctree::
-   :maxdepth: 1
+   :maxdepth: 3
 
    rcu
    listRCU
    UP
 
+   Design/Memory-Ordering/Tree-RCU-Memory-Ordering
+   Design/Expedited-Grace-Periods/Expedited-Grace-Periods
+   Design/Requirements/Requirements
+   Design/Data-Structures/Data-Structures
+
 .. only:: subproject and html
 
    Indices
diff --git a/Documentation/RCU/lockdep.txt b/Documentation/RCU/lockdep.txt
index da51d3068850..89db949eeca0 100644
--- a/Documentation/RCU/lockdep.txt
+++ b/Documentation/RCU/lockdep.txt
@@ -96,7 +96,17 @@ other flavors of rcu_dereference().  On the other hand, it is illegal
 to use rcu_dereference_protected() if either the RCU-protected pointer
 or the RCU-protected data that it points to can change concurrently.
 
-There are currently only "universal" versions of the rcu_assign_pointer()
-and RCU list-/tree-traversal primitives, which do not (yet) check for
-being in an RCU read-side critical section.  In the future, separate
-versions of these primitives might be created.
+Like rcu_dereference(), when lockdep is enabled, RCU list and hlist
+traversal primitives check for being called from within an RCU read-side
+critical section.  However, a lockdep expression can be passed to them
+as a additional optional argument.  With this lockdep expression, these
+traversal primitives will complain only if the lockdep expression is
+false and they are called from outside any RCU read-side critical section.
+
+For example, the workqueue for_each_pwq() macro is intended to be used
+either within an RCU read-side critical section or with wq->mutex held.
+It is thus implemented as follows:
+
+	#define for_each_pwq(pwq, wq)
+		list_for_each_entry_rcu((pwq), &(wq)->pwqs, pwqs_node,
+					lock_is_held(&(wq->mutex).dep_map))
diff --git a/Documentation/RCU/whatisRCU.txt b/Documentation/RCU/whatisRCU.txt
index 7e1a8721637a..58ba05c4d97f 100644
--- a/Documentation/RCU/whatisRCU.txt
+++ b/Documentation/RCU/whatisRCU.txt
@@ -290,7 +290,7 @@ rcu_dereference()
 	at any time, including immediately after the rcu_dereference().
 	And, again like rcu_assign_pointer(), rcu_dereference() is
 	typically used indirectly, via the _rcu list-manipulation
-	primitives, such as list_for_each_entry_rcu().
+	primitives, such as list_for_each_entry_rcu() [2].
 
 	[1] The variant rcu_dereference_protected() can be used outside
 	of an RCU read-side critical section as long as the usage is
@@ -302,9 +302,17 @@ rcu_dereference()
 	must prohibit.	The rcu_dereference_protected() variant takes
 	a lockdep expression to indicate which locks must be acquired
 	by the caller. If the indicated protection is not provided,
-	a lockdep splat is emitted.  See RCU/Design/Requirements/Requirements.html
+	a lockdep splat is emitted.  See Documentation/RCU/Design/Requirements/Requirements.rst
 	and the API's code comments for more details and example usage.
 
+	[2] If the list_for_each_entry_rcu() instance might be used by
+	update-side code as well as by RCU readers, then an additional
+	lockdep expression can be added to its list of arguments.
+	For example, given an additional "lock_is_held(&mylock)" argument,
+	the RCU lockdep code would complain only if this instance was
+	invoked outside of an RCU read-side critical section and without
+	the protection of mylock.
+
 The following diagram shows how each API communicates among the
 reader, updater, and reclaimer.
 
@@ -630,7 +638,7 @@ been able to write-acquire the lock otherwise.  The smp_mb__after_spinlock()
 promotes synchronize_rcu() to a full memory barrier in compliance with
 the "Memory-Barrier Guarantees" listed in:
 
-	Documentation/RCU/Design/Requirements/Requirements.html.
+	Documentation/RCU/Design/Requirements/Requirements.rst
 
 It is possible to nest rcu_read_lock(), since reader-writer locks may
 be recursively acquired.  Note also that rcu_read_lock() is immune
diff --git a/Documentation/admin-guide/hw-vuln/mds.rst b/Documentation/admin-guide/hw-vuln/mds.rst
index e3a796c0d3a2..2d19c9f4c1fe 100644
--- a/Documentation/admin-guide/hw-vuln/mds.rst
+++ b/Documentation/admin-guide/hw-vuln/mds.rst
@@ -265,8 +265,11 @@ time with the option "mds=". The valid arguments for this option are:
 
   ============  =============================================================
 
-Not specifying this option is equivalent to "mds=full".
-
+Not specifying this option is equivalent to "mds=full". For processors
+that are affected by both TAA (TSX Asynchronous Abort) and MDS,
+specifying just "mds=off" without an accompanying "tsx_async_abort=off"
+will have no effect as the same mitigation is used for both
+vulnerabilities.
 
 Mitigation selection guide
 --------------------------
diff --git a/Documentation/admin-guide/hw-vuln/tsx_async_abort.rst b/Documentation/admin-guide/hw-vuln/tsx_async_abort.rst
index fddbd7579c53..af6865b822d2 100644
--- a/Documentation/admin-guide/hw-vuln/tsx_async_abort.rst
+++ b/Documentation/admin-guide/hw-vuln/tsx_async_abort.rst
@@ -174,7 +174,10 @@ the option "tsx_async_abort=". The valid arguments for this option are:
                 CPU is not vulnerable to cross-thread TAA attacks.
   ============  =============================================================
 
-Not specifying this option is equivalent to "tsx_async_abort=full".
+Not specifying this option is equivalent to "tsx_async_abort=full". For
+processors that are affected by both TAA and MDS, specifying just
+"tsx_async_abort=off" without an accompanying "mds=off" will have no
+effect as the same mitigation is used for both vulnerabilities.
 
 The kernel command line also allows to control the TSX feature using the
 parameter "tsx=" on CPUs which support TSX control. MSR_IA32_TSX_CTRL is used
diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index 9b847f06cb19..122f2d2f3e96 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -1168,7 +1168,8 @@
 			Format: {"off" | "on" | "skip[mbr]"}
 
 	efi=		[EFI]
-			Format: { "old_map", "nochunk", "noruntime", "debug" }
+			Format: { "old_map", "nochunk", "noruntime", "debug",
+				  "nosoftreserve" }
 			old_map [X86-64]: switch to the old ioremap-based EFI
 			runtime services mapping. 32-bit still uses this one by
 			default.
@@ -1177,6 +1178,12 @@
 			firmware implementations.
 			noruntime : disable EFI runtime services support
 			debug: enable misc debug output
+			nosoftreserve: The EFI_MEMORY_SP (Specific Purpose)
+			attribute may cause the kernel to reserve the
+			memory range for a memory mapping driver to
+			claim. Specify efi=nosoftreserve to disable this
+			reservation and treat the memory by its base type
+			(i.e. EFI_CONVENTIONAL_MEMORY / "System RAM").
 
 	efi_no_storage_paranoia [EFI; X86]
 			Using this parameter you can use more than 50% of
@@ -1189,15 +1196,21 @@
 			updating original EFI memory map.
 			Region of memory which aa attribute is added to is
 			from ss to ss+nn.
+
 			If efi_fake_mem=2G@4G:0x10000,2G@0x10a0000000:0x10000
 			is specified, EFI_MEMORY_MORE_RELIABLE(0x10000)
 			attribute is added to range 0x100000000-0x180000000 and
 			0x10a0000000-0x1120000000.
 
+			If efi_fake_mem=8G@9G:0x40000 is specified, the
+			EFI_MEMORY_SP(0x40000) attribute is added to
+			range 0x240000000-0x43fffffff.
+
 			Using this parameter you can do debugging of EFI memmap
-			related feature. For example, you can do debugging of
+			related features. For example, you can do debugging of
 			Address Range Mirroring feature even if your box
-			doesn't support it.
+			doesn't support it, or mark specific memory as
+			"soft reserved".
 
 	efivar_ssdt=	[EFI; X86] Name of an EFI variable that contains an SSDT
 			that is to be dynamically loaded by Linux. If there are
@@ -2473,6 +2486,12 @@
 				     SMT on vulnerable CPUs
 			off        - Unconditionally disable MDS mitigation
 
+			On TAA-affected machines, mds=off can be prevented by
+			an active TAA mitigation as both vulnerabilities are
+			mitigated with the same mechanism so in order to disable
+			this mitigation, you need to specify tsx_async_abort=off
+			too.
+
 			Not specifying this option is equivalent to
 			mds=full.
 
@@ -4931,6 +4950,11 @@
 				     vulnerable to cross-thread TAA attacks.
 			off        - Unconditionally disable TAA mitigation
 
+			On MDS-affected machines, tsx_async_abort=off can be
+			prevented by an active MDS mitigation as both vulnerabilities
+			are mitigated with the same mechanism so in order to disable
+			this mitigation, you need to specify mds=off too.
+
 			Not specifying this option is equivalent to
 			tsx_async_abort=full.  On CPUs which are MDS affected
 			and deploy MDS mitigation, TAA mitigation is not
diff --git a/Documentation/asm-annotations.rst b/Documentation/asm-annotations.rst
new file mode 100644
index 000000000000..f55c2bb74d00
--- /dev/null
+++ b/Documentation/asm-annotations.rst
@@ -0,0 +1,216 @@
+Assembler Annotations
+=====================
+
+Copyright (c) 2017-2019 Jiri Slaby
+
+This document describes the new macros for annotation of data and code in
+assembly. In particular, it contains information about ``SYM_FUNC_START``,
+``SYM_FUNC_END``, ``SYM_CODE_START``, and similar.
+
+Rationale
+---------
+Some code like entries, trampolines, or boot code needs to be written in
+assembly. The same as in C, such code is grouped into functions and
+accompanied with data. Standard assemblers do not force users into precisely
+marking these pieces as code, data, or even specifying their length.
+Nevertheless, assemblers provide developers with such annotations to aid
+debuggers throughout assembly. On top of that, developers also want to mark
+some functions as *global* in order to be visible outside of their translation
+units.
+
+Over time, the Linux kernel has adopted macros from various projects (like
+``binutils``) to facilitate such annotations. So for historic reasons,
+developers have been using ``ENTRY``, ``END``, ``ENDPROC``, and other
+annotations in assembly.  Due to the lack of their documentation, the macros
+are used in rather wrong contexts at some locations. Clearly, ``ENTRY`` was
+intended to denote the beginning of global symbols (be it data or code).
+``END`` used to mark the end of data or end of special functions with
+*non-standard* calling convention. In contrast, ``ENDPROC`` should annotate
+only ends of *standard* functions.
+
+When these macros are used correctly, they help assemblers generate a nice
+object with both sizes and types set correctly. For example, the result of
+``arch/x86/lib/putuser.S``::
+
+   Num:    Value          Size Type    Bind   Vis      Ndx Name
+    25: 0000000000000000    33 FUNC    GLOBAL DEFAULT    1 __put_user_1
+    29: 0000000000000030    37 FUNC    GLOBAL DEFAULT    1 __put_user_2
+    32: 0000000000000060    36 FUNC    GLOBAL DEFAULT    1 __put_user_4
+    35: 0000000000000090    37 FUNC    GLOBAL DEFAULT    1 __put_user_8
+
+This is not only important for debugging purposes. When there are properly
+annotated objects like this, tools can be run on them to generate more useful
+information. In particular, on properly annotated objects, ``objtool`` can be
+run to check and fix the object if needed. Currently, ``objtool`` can report
+missing frame pointer setup/destruction in functions. It can also
+automatically generate annotations for :doc:`ORC unwinder <x86/orc-unwinder>`
+for most code. Both of these are especially important to support reliable
+stack traces which are in turn necessary for :doc:`Kernel live patching
+<livepatch/livepatch>`.
+
+Caveat and Discussion
+---------------------
+As one might realize, there were only three macros previously. That is indeed
+insufficient to cover all the combinations of cases:
+
+* standard/non-standard function
+* code/data
+* global/local symbol
+
+There was a discussion_ and instead of extending the current ``ENTRY/END*``
+macros, it was decided that brand new macros should be introduced instead::
+
+    So how about using macro names that actually show the purpose, instead
+    of importing all the crappy, historic, essentially randomly chosen
+    debug symbol macro names from the binutils and older kernels?
+
+.. _discussion: https://lkml.kernel.org/r/20170217104757.28588-1-jslaby@suse.cz
+
+Macros Description
+------------------
+
+The new macros are prefixed with the ``SYM_`` prefix and can be divided into
+three main groups:
+
+1. ``SYM_FUNC_*`` -- to annotate C-like functions. This means functions with
+   standard C calling conventions, i.e. the stack contains a return address at
+   the predefined place and a return from the function can happen in a
+   standard way. When frame pointers are enabled, save/restore of frame
+   pointer shall happen at the start/end of a function, respectively, too.
+
+   Checking tools like ``objtool`` should ensure such marked functions conform
+   to these rules. The tools can also easily annotate these functions with
+   debugging information (like *ORC data*) automatically.
+
+2. ``SYM_CODE_*`` -- special functions called with special stack. Be it
+   interrupt handlers with special stack content, trampolines, or startup
+   functions.
+
+   Checking tools mostly ignore checking of these functions. But some debug
+   information still can be generated automatically. For correct debug data,
+   this code needs hints like ``UNWIND_HINT_REGS`` provided by developers.
+
+3. ``SYM_DATA*`` -- obviously data belonging to ``.data`` sections and not to
+   ``.text``. Data do not contain instructions, so they have to be treated
+   specially by the tools: they should not treat the bytes as instructions,
+   nor assign any debug information to them.
+
+Instruction Macros
+~~~~~~~~~~~~~~~~~~
+This section covers ``SYM_FUNC_*`` and ``SYM_CODE_*`` enumerated above.
+
+* ``SYM_FUNC_START`` and ``SYM_FUNC_START_LOCAL`` are supposed to be **the
+  most frequent markings**. They are used for functions with standard calling
+  conventions -- global and local. Like in C, they both align the functions to
+  architecture specific ``__ALIGN`` bytes. There are also ``_NOALIGN`` variants
+  for special cases where developers do not want this implicit alignment.
+
+  ``SYM_FUNC_START_WEAK`` and ``SYM_FUNC_START_WEAK_NOALIGN`` markings are
+  also offered as an assembler counterpart to the *weak* attribute known from
+  C.
+
+  All of these **shall** be coupled with ``SYM_FUNC_END``. First, it marks
+  the sequence of instructions as a function and computes its size to the
+  generated object file. Second, it also eases checking and processing such
+  object files as the tools can trivially find exact function boundaries.
+
+  So in most cases, developers should write something like in the following
+  example, having some asm instructions in between the macros, of course::
+
+    SYM_FUNC_START(memset)
+        ... asm insns ...
+    SYM_FUNC_END(memset)
+
+  In fact, this kind of annotation corresponds to the now deprecated ``ENTRY``
+  and ``ENDPROC`` macros.
+
+* ``SYM_FUNC_START_ALIAS`` and ``SYM_FUNC_START_LOCAL_ALIAS`` serve for those
+  who decided to have two or more names for one function. The typical use is::
+
+    SYM_FUNC_START_ALIAS(__memset)
+    SYM_FUNC_START(memset)
+        ... asm insns ...
+    SYM_FUNC_END(memset)
+    SYM_FUNC_END_ALIAS(__memset)
+
+  In this example, one can call ``__memset`` or ``memset`` with the same
+  result, except the debug information for the instructions is generated to
+  the object file only once -- for the non-``ALIAS`` case.
+
+* ``SYM_CODE_START`` and ``SYM_CODE_START_LOCAL`` should be used only in
+  special cases -- if you know what you are doing. This is used exclusively
+  for interrupt handlers and similar where the calling convention is not the C
+  one. ``_NOALIGN`` variants exist too. The use is the same as for the ``FUNC``
+  category above::
+
+    SYM_CODE_START_LOCAL(bad_put_user)
+        ... asm insns ...
+    SYM_CODE_END(bad_put_user)
+
+  Again, every ``SYM_CODE_START*`` **shall** be coupled by ``SYM_CODE_END``.
+
+  To some extent, this category corresponds to deprecated ``ENTRY`` and
+  ``END``. Except ``END`` had several other meanings too.
+
+* ``SYM_INNER_LABEL*`` is used to denote a label inside some
+  ``SYM_{CODE,FUNC}_START`` and ``SYM_{CODE,FUNC}_END``.  They are very similar
+  to C labels, except they can be made global. An example of use::
+
+    SYM_CODE_START(ftrace_caller)
+        /* save_mcount_regs fills in first two parameters */
+        ...
+
+    SYM_INNER_LABEL(ftrace_caller_op_ptr, SYM_L_GLOBAL)
+        /* Load the ftrace_ops into the 3rd parameter */
+        ...
+
+    SYM_INNER_LABEL(ftrace_call, SYM_L_GLOBAL)
+        call ftrace_stub
+        ...
+        retq
+    SYM_CODE_END(ftrace_caller)
+
+Data Macros
+~~~~~~~~~~~
+Similar to instructions, there is a couple of macros to describe data in the
+assembly.
+
+* ``SYM_DATA_START`` and ``SYM_DATA_START_LOCAL`` mark the start of some data
+  and shall be used in conjunction with either ``SYM_DATA_END``, or
+  ``SYM_DATA_END_LABEL``. The latter adds also a label to the end, so that
+  people can use ``lstack`` and (local) ``lstack_end`` in the following
+  example::
+
+    SYM_DATA_START_LOCAL(lstack)
+        .skip 4096
+    SYM_DATA_END_LABEL(lstack, SYM_L_LOCAL, lstack_end)
+
+* ``SYM_DATA`` and ``SYM_DATA_LOCAL`` are variants for simple, mostly one-line
+  data::
+
+    SYM_DATA(HEAP,     .long rm_heap)
+    SYM_DATA(heap_end, .long rm_stack)
+
+  In the end, they expand to ``SYM_DATA_START`` with ``SYM_DATA_END``
+  internally.
+
+Support Macros
+~~~~~~~~~~~~~~
+All the above reduce themselves to some invocation of ``SYM_START``,
+``SYM_END``, or ``SYM_ENTRY`` at last. Normally, developers should avoid using
+these.
+
+Further, in the above examples, one could see ``SYM_L_LOCAL``. There are also
+``SYM_L_GLOBAL`` and ``SYM_L_WEAK``. All are intended to denote linkage of a
+symbol marked by them. They are used either in ``_LABEL`` variants of the
+earlier macros, or in ``SYM_START``.
+
+
+Overriding Macros
+~~~~~~~~~~~~~~~~~
+Architecture can also override any of the macros in their own
+``asm/linkage.h``, including macros specifying the type of a symbol
+(``SYM_T_FUNC``, ``SYM_T_OBJECT``, and ``SYM_T_NONE``).  As every macro
+described in this file is surrounded by ``#ifdef`` + ``#endif``, it is enough
+to define the macros differently in the aforementioned architecture-dependent
+header.
diff --git a/Documentation/core-api/printk-formats.rst b/Documentation/core-api/printk-formats.rst
index 050f34f3a70f..ea21dd4b9bad 100644
--- a/Documentation/core-api/printk-formats.rst
+++ b/Documentation/core-api/printk-formats.rst
@@ -98,8 +98,6 @@ Symbols/Function Pointers
 
 	%pS	versatile_init+0x0/0x110
 	%ps	versatile_init
-	%pF	versatile_init+0x0/0x110
-	%pf	versatile_init
 	%pSR	versatile_init+0x9/0x110
 		(with __builtin_extract_return_addr() translation)
 	%pB	prev_fn_of_versatile_init+0x88/0x88
@@ -109,14 +107,6 @@ The ``S`` and ``s`` specifiers are used for printing a pointer in symbolic
 format. They result in the symbol name with (S) or without (s)
 offsets. If KALLSYMS are disabled then the symbol address is printed instead.
 
-Note, that the ``F`` and ``f`` specifiers are identical to ``S`` (``s``)
-and thus deprecated. We have ``F`` and ``f`` because on ia64, ppc64 and
-parisc64 function pointers are indirect and, in fact, are function
-descriptors, which require additional dereferencing before we can lookup
-the symbol. As of now, ``S`` and ``s`` perform dereferencing on those
-platforms (when needed), so ``F`` and ``f`` exist for compatibility
-reasons only.
-
 The ``B`` specifier results in the symbol name with offsets and should be
 used when printing stack backtraces. The specifier takes into
 consideration the effect of compiler optimisations which may occur
@@ -440,6 +430,30 @@ Examples::
 
 Passed by reference.
 
+Fwnode handles
+--------------
+
+::
+
+	%pfw[fP]
+
+For printing information on fwnode handles. The default is to print the full
+node name, including the path. The modifiers are functionally equivalent to
+%pOF above.
+
+	- f - full name of the node, including the path
+	- P - the name of the node including an address (if there is one)
+
+Examples (ACPI)::
+
+	%pfwf	\_SB.PCI0.CIO2.port@1.endpoint@0	- Full node name
+	%pfwP	endpoint@0				- Node name
+
+Examples (OF)::
+
+	%pfwf	/ocp@68000000/i2c@48072000/camera@10/port/endpoint - Full name
+	%pfwP	endpoint				- Node name
+
 Time and date (struct rtc_time)
 -------------------------------
 
diff --git a/Documentation/devicetree/bindings/arm/omap/omap.txt b/Documentation/devicetree/bindings/arm/omap/omap.txt
index b301f753ed2c..e77635c5422c 100644
--- a/Documentation/devicetree/bindings/arm/omap/omap.txt
+++ b/Documentation/devicetree/bindings/arm/omap/omap.txt
@@ -43,7 +43,7 @@ SoC Families:
 
 - OMAP2 generic - defaults to OMAP2420
   compatible = "ti,omap2"
-- OMAP3 generic - defaults to OMAP3430
+- OMAP3 generic
   compatible = "ti,omap3"
 - OMAP4 generic - defaults to OMAP4430
   compatible = "ti,omap4"
@@ -51,6 +51,8 @@ SoC Families:
   compatible = "ti,omap5"
 - DRA7 generic - defaults to DRA742
   compatible = "ti,dra7"
+- AM33x generic
+  compatible = "ti,am33xx"
 - AM43x generic - defaults to AM4372
   compatible = "ti,am43"
 
@@ -63,12 +65,14 @@ SoCs:
 
 - OMAP3430
   compatible = "ti,omap3430", "ti,omap3"
+  legacy: "ti,omap34xx" - please do not use any more
 - AM3517
   compatible = "ti,am3517", "ti,omap3"
 - OMAP3630
-  compatible = "ti,omap36xx", "ti,omap3"
-- AM33xx
-  compatible = "ti,am33xx", "ti,omap3"
+  compatible = "ti,omap3630", "ti,omap3"
+  legacy: "ti,omap36xx" - please do not use any more
+- AM335x
+  compatible = "ti,am33xx"
 
 - OMAP4430
   compatible = "ti,omap4430", "ti,omap4"
@@ -110,19 +114,19 @@ SoCs:
 - AM4372
   compatible = "ti,am4372", "ti,am43"
 
-Boards:
+Boards (incomplete list of examples):
 
 - OMAP3 BeagleBoard : Low cost community board
-  compatible = "ti,omap3-beagle", "ti,omap3"
+  compatible = "ti,omap3-beagle", "ti,omap3430", "ti,omap3"
 
 - OMAP3 Tobi with Overo : Commercial expansion board with daughter board
-  compatible = "gumstix,omap3-overo-tobi", "gumstix,omap3-overo", "ti,omap3"
+  compatible = "gumstix,omap3-overo-tobi", "gumstix,omap3-overo", "ti,omap3430", "ti,omap3"
 
 - OMAP4 SDP : Software Development Board
-  compatible = "ti,omap4-sdp", "ti,omap4430"
+  compatible = "ti,omap4-sdp", "ti,omap4430", "ti,omap4"
 
 - OMAP4 PandaBoard : Low cost community board
-  compatible = "ti,omap4-panda", "ti,omap4430"
+  compatible = "ti,omap4-panda", "ti,omap4430", "ti,omap4"
 
 - OMAP4 DuoVero with Parlor : Commercial expansion board with daughter board
   compatible = "gumstix,omap4-duovero-parlor", "gumstix,omap4-duovero", "ti,omap4430", "ti,omap4";
@@ -134,16 +138,16 @@ Boards:
   compatible = "variscite,var-dvk-om44", "variscite,var-som-om44", "ti,omap4460", "ti,omap4";
 
 - OMAP3 EVM : Software Development Board for OMAP35x, AM/DM37x
-  compatible = "ti,omap3-evm", "ti,omap3"
+  compatible = "ti,omap3-evm", "ti,omap3630", "ti,omap3"
 
 - AM335X EVM : Software Development Board for AM335x
-  compatible = "ti,am335x-evm", "ti,am33xx", "ti,omap3"
+  compatible = "ti,am335x-evm", "ti,am33xx"
 
 - AM335X Bone : Low cost community board
-  compatible = "ti,am335x-bone", "ti,am33xx", "ti,omap3"
+  compatible = "ti,am335x-bone", "ti,am33xx"
 
 - AM3359 ICEv2 : Low cost Industrial Communication Engine EVM.
-  compatible = "ti,am3359-icev2", "ti,am33xx", "ti,omap3"
+  compatible = "ti,am3359-icev2", "ti,am33xx"
 
 - AM335X OrionLXm : Substation Automation Platform
   compatible = "novatech,am335x-lxm", "ti,am33xx"
diff --git a/Documentation/devicetree/bindings/cpufreq/ti-cpufreq.txt b/Documentation/devicetree/bindings/cpufreq/ti-cpufreq.txt
index 0c38e4b8fc51..1758051798fe 100644
--- a/Documentation/devicetree/bindings/cpufreq/ti-cpufreq.txt
+++ b/Documentation/devicetree/bindings/cpufreq/ti-cpufreq.txt
@@ -15,12 +15,16 @@ In 'cpus' nodes:
 
 In 'operating-points-v2' table:
 - compatible: Should be
-	- 'operating-points-v2-ti-cpu' for am335x, am43xx, and dra7xx/am57xx SoCs
+	- 'operating-points-v2-ti-cpu' for am335x, am43xx, and dra7xx/am57xx,
+	  omap34xx, omap36xx and am3517 SoCs
 - syscon: A phandle pointing to a syscon node representing the control module
 	  register space of the SoC.
 
 Optional properties:
 --------------------
+- "vdd-supply", "vbb-supply": to define two regulators for dra7xx
+- "cpu0-supply", "vbb-supply": to define two regulators for omap36xx
+
 For each opp entry in 'operating-points-v2' table:
 - opp-supported-hw: Two bitfields indicating:
 	1. Which revision of the SoC the OPP is supported by
diff --git a/Documentation/devicetree/bindings/devfreq/event/exynos-ppmu.txt b/Documentation/devicetree/bindings/devfreq/event/exynos-ppmu.txt
index 3e36c1d11386..fb46b491791c 100644
--- a/Documentation/devicetree/bindings/devfreq/event/exynos-ppmu.txt
+++ b/Documentation/devicetree/bindings/devfreq/event/exynos-ppmu.txt
@@ -10,14 +10,23 @@ The Exynos PPMU driver uses the devfreq-event class to provide event data
 to various devfreq devices. The devfreq devices would use the event data when
 derterming the current state of each IP.
 
-Required properties:
+Required properties for PPMU device:
 - compatible: Should be "samsung,exynos-ppmu" or "samsung,exynos-ppmu-v2.
 - reg: physical base address of each PPMU and length of memory mapped region.
 
-Optional properties:
+Optional properties for PPMU device:
 - clock-names : the name of clock used by the PPMU, "ppmu"
 - clocks : phandles for clock specified in "clock-names" property
 
+Required properties for 'events' child node of PPMU device:
+- event-name : the unique event name among PPMU device
+Optional properties for 'events' child node of PPMU device:
+- event-data-type : Define the type of data which shell be counted
+by the counter. You can check include/dt-bindings/pmu/exynos_ppmu.h for
+all possible type, i.e. count read requests, count write data in bytes,
+etc. This field is optional and when it is missing, the driver code
+will use default data type.
+
 Example1 : PPMUv1 nodes in exynos3250.dtsi are listed below.
 
 		ppmu_dmc0: ppmu_dmc0@106a0000 {
@@ -145,3 +154,16 @@ Example3 : PPMUv2 nodes in exynos5433.dtsi are listed below.
 			reg = <0x104d0000 0x2000>;
 			status = "disabled";
 		};
+
+Example4 : 'event-data-type' in exynos4412-ppmu-common.dtsi are listed below.
+
+	&ppmu_dmc0 {
+		status = "okay";
+		events {
+			ppmu_dmc0_3: ppmu-event3-dmc0 {
+			event-name = "ppmu-event3-dmc0";
+			event-data-type = <(PPMU_RO_DATA_CNT |
+					PPMU_WO_DATA_CNT)>;
+			};
+		};
+	};
diff --git a/Documentation/devicetree/bindings/devfreq/exynos-bus.txt b/Documentation/devicetree/bindings/devfreq/exynos-bus.txt
index f8e946471a58..e71f752cc18f 100644
--- a/Documentation/devicetree/bindings/devfreq/exynos-bus.txt
+++ b/Documentation/devicetree/bindings/devfreq/exynos-bus.txt
@@ -50,8 +50,6 @@ Required properties only for passive bus device:
 Optional properties only for parent bus device:
 - exynos,saturation-ratio: the percentage value which is used to calibrate
 			the performance count against total cycle count.
-- exynos,voltage-tolerance: the percentage value for bus voltage tolerance
-			which is used to calculate the max voltage.
 
 Detailed correlation between sub-blocks and power line according to Exynos SoC:
 - In case of Exynos3250, there are two power line as following:
diff --git a/Documentation/devicetree/bindings/media/allwinner,sun8i-h3-deinterlace.yaml b/Documentation/devicetree/bindings/media/allwinner,sun8i-h3-deinterlace.yaml
new file mode 100644
index 000000000000..2e40f700e84f
--- /dev/null
+++ b/Documentation/devicetree/bindings/media/allwinner,sun8i-h3-deinterlace.yaml
@@ -0,0 +1,76 @@
+# SPDX-License-Identifier: (GPL-2.0 OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/media/allwinner,sun8i-h3-deinterlace.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Allwinner H3 Deinterlace Device Tree Bindings
+
+maintainers:
+  - Jernej Skrabec <jernej.skrabec@siol.net>
+  - Chen-Yu Tsai <wens@csie.org>
+  - Maxime Ripard <mripard@kernel.org>
+
+description: |-
+  The Allwinner H3 and later has a deinterlace core used for
+  deinterlacing interlaced video content.
+
+properties:
+  compatible:
+    const: allwinner,sun8i-h3-deinterlace
+
+  reg:
+    maxItems: 1
+
+  interrupts:
+    maxItems: 1
+
+  clocks:
+    items:
+      - description: Deinterlace interface clock
+      - description: Deinterlace module clock
+      - description: Deinterlace DRAM clock
+
+  clock-names:
+    items:
+      - const: bus
+      - const: mod
+      - const: ram
+
+  resets:
+    maxItems: 1
+
+  interconnects:
+    maxItems: 1
+
+  interconnect-names:
+    const: dma-mem
+
+required:
+  - compatible
+  - reg
+  - interrupts
+  - clocks
+
+additionalProperties: false
+
+examples:
+  - |
+    #include <dt-bindings/interrupt-controller/arm-gic.h>
+    #include <dt-bindings/clock/sun8i-h3-ccu.h>
+    #include <dt-bindings/reset/sun8i-h3-ccu.h>
+
+    deinterlace: deinterlace@1400000 {
+        compatible = "allwinner,sun8i-h3-deinterlace";
+        reg = <0x01400000 0x20000>;
+        clocks = <&ccu CLK_BUS_DEINTERLACE>,
+                 <&ccu CLK_DEINTERLACE>,
+                 <&ccu CLK_DRAM_DEINTERLACE>;
+        clock-names = "bus", "mod", "ram";
+        resets = <&ccu RST_BUS_DEINTERLACE>;
+        interrupts = <GIC_SPI 93 IRQ_TYPE_LEVEL_HIGH>;
+        interconnects = <&mbus 9>;
+        interconnect-names = "dma-mem";
+    };
+
+...
diff --git a/Documentation/devicetree/bindings/media/i2c/ad5820.txt b/Documentation/devicetree/bindings/media/i2c/ad5820.txt
index 5940ca11c021..5764cbedf9b7 100644
--- a/Documentation/devicetree/bindings/media/i2c/ad5820.txt
+++ b/Documentation/devicetree/bindings/media/i2c/ad5820.txt
@@ -2,12 +2,20 @@
 
 Required Properties:
 
-  - compatible: Must contain "adi,ad5820"
+  - compatible: Must contain one of:
+		- "adi,ad5820"
+		- "adi,ad5821"
+		- "adi,ad5823"
 
   - reg: I2C slave address
 
   - VANA-supply: supply of voltage for VANA pin
 
+Optional properties:
+
+   - enable-gpios : GPIO spec for the XSHUTDOWN pin. The XSHUTDOWN signal is
+active low, a high level on the pin enables the device.
+
 Example:
 
        ad5820: coil@c {
@@ -15,5 +23,6 @@ Example:
                reg = <0x0c>;
 
                VANA-supply = <&vaux4>;
+               enable-gpios = <&msmgpio 26 GPIO_ACTIVE_HIGH>;
        };
 
diff --git a/Documentation/devicetree/bindings/media/i2c/imx290.txt b/Documentation/devicetree/bindings/media/i2c/imx290.txt
new file mode 100644
index 000000000000..a3cc21410f7c
--- /dev/null
+++ b/Documentation/devicetree/bindings/media/i2c/imx290.txt
@@ -0,0 +1,57 @@
+* Sony IMX290 1/2.8-Inch CMOS Image Sensor
+
+The Sony IMX290 is a 1/2.8-Inch CMOS Solid-state image sensor with
+Square Pixel for Color Cameras. It is programmable through I2C and 4-wire
+interfaces. The sensor output is available via CMOS logic parallel SDR output,
+Low voltage LVDS DDR output and CSI-2 serial data output. The CSI-2 bus is the
+default. No bindings have been defined for the other busses.
+
+Required Properties:
+- compatible: Should be "sony,imx290"
+- reg: I2C bus address of the device
+- clocks: Reference to the xclk clock.
+- clock-names: Should be "xclk".
+- clock-frequency: Frequency of the xclk clock in Hz.
+- vdddo-supply: Sensor digital IO regulator.
+- vdda-supply: Sensor analog regulator.
+- vddd-supply: Sensor digital core regulator.
+
+Optional Properties:
+- reset-gpios: Sensor reset GPIO
+
+The imx290 device node should contain one 'port' child node with
+an 'endpoint' subnode. For further reading on port node refer to
+Documentation/devicetree/bindings/media/video-interfaces.txt.
+
+Required Properties on endpoint:
+- data-lanes: check ../video-interfaces.txt
+- link-frequencies: check ../video-interfaces.txt
+- remote-endpoint: check ../video-interfaces.txt
+
+Example:
+	&i2c1 {
+		...
+		imx290: camera-sensor@1a {
+			compatible = "sony,imx290";
+			reg = <0x1a>;
+
+			reset-gpios = <&msmgpio 35 GPIO_ACTIVE_LOW>;
+			pinctrl-names = "default";
+			pinctrl-0 = <&camera_rear_default>;
+
+			clocks = <&gcc GCC_CAMSS_MCLK0_CLK>;
+			clock-names = "xclk";
+			clock-frequency = <37125000>;
+
+			vdddo-supply = <&camera_vdddo_1v8>;
+			vdda-supply = <&camera_vdda_2v8>;
+			vddd-supply = <&camera_vddd_1v5>;
+
+			port {
+				imx290_ep: endpoint {
+					data-lanes = <1 2 3 4>;
+					link-frequencies = /bits/ 64 <445500000>;
+					remote-endpoint = <&csiphy0_ep>;
+				};
+			};
+		};
diff --git a/Documentation/devicetree/bindings/media/i2c/nokia,smia.txt b/Documentation/devicetree/bindings/media/i2c/nokia,smia.txt
index c3c3479233c4..10ece8108081 100644
--- a/Documentation/devicetree/bindings/media/i2c/nokia,smia.txt
+++ b/Documentation/devicetree/bindings/media/i2c/nokia,smia.txt
@@ -27,8 +27,6 @@ Mandatory properties
 Optional properties
 -------------------
 
-- nokia,nvm-size: The size of the NVM, in bytes. If the size is not given,
-  the NVM contents will not be read.
 - reset-gpios: XSHUTDOWN GPIO
 - flash-leds: See ../video-interfaces.txt
 - lens-focus: See ../video-interfaces.txt
diff --git a/Documentation/devicetree/bindings/media/i2c/ov2659.txt b/Documentation/devicetree/bindings/media/i2c/ov2659.txt
index cabc7d827dfb..92989a619f29 100644
--- a/Documentation/devicetree/bindings/media/i2c/ov2659.txt
+++ b/Documentation/devicetree/bindings/media/i2c/ov2659.txt
@@ -12,6 +12,12 @@ Required Properties:
 - clock-names: should be "xvclk".
 - link-frequencies: target pixel clock frequency.
 
+Optional Properties:
+- powerdown-gpios: reference to the GPIO connected to the pwdn pin, if any.
+  Active high with internal pull down resistor.
+- reset-gpios: reference to the GPIO connected to the resetb pin, if any.
+  Active low with internal pull up resistor.
+
 For further reading on port node refer to
 Documentation/devicetree/bindings/media/video-interfaces.txt.
 
@@ -27,6 +33,9 @@ Example:
 			clocks = <&clk_ov2659 0>;
 			clock-names = "xvclk";
 
+			powerdown-gpios = <&gpio6 14 GPIO_ACTIVE_HIGH>;
+			reset-gpios = <&gpio6 15 GPIO_ACTIVE_LOW>;
+
 			port {
 				ov2659_0: endpoint {
 					remote-endpoint = <&vpfe_ep>;
diff --git a/Documentation/devicetree/bindings/media/rc.yaml b/Documentation/devicetree/bindings/media/rc.yaml
index 9054555e6608..cdfc8ee023ac 100644
--- a/Documentation/devicetree/bindings/media/rc.yaml
+++ b/Documentation/devicetree/bindings/media/rc.yaml
@@ -39,6 +39,7 @@ properties:
           - rc-avermedia-rm-ks
           - rc-avertv-303
           - rc-azurewave-ad-tu700
+          - rc-beelink-gs1
           - rc-behold
           - rc-behold-columbus
           - rc-budget-ci-old
diff --git a/Documentation/devicetree/bindings/media/renesas,csi2.txt b/Documentation/devicetree/bindings/media/renesas,csi2.txt
index 331409259752..2da6f60b2b56 100644
--- a/Documentation/devicetree/bindings/media/renesas,csi2.txt
+++ b/Documentation/devicetree/bindings/media/renesas,csi2.txt
@@ -9,6 +9,7 @@ Mandatory properties
 --------------------
  - compatible: Must be one or more of the following
    - "renesas,r8a774a1-csi2" for the R8A774A1 device.
+   - "renesas,r8a774b1-csi2" for the R8A774B1 device.
    - "renesas,r8a774c0-csi2" for the R8A774C0 device.
    - "renesas,r8a7795-csi2" for the R8A7795 device.
    - "renesas,r8a7796-csi2" for the R8A7796 device.
diff --git a/Documentation/devicetree/bindings/media/renesas,vin.txt b/Documentation/devicetree/bindings/media/renesas,vin.txt
index aa217b096279..e30b0d4eefdd 100644
--- a/Documentation/devicetree/bindings/media/renesas,vin.txt
+++ b/Documentation/devicetree/bindings/media/renesas,vin.txt
@@ -14,6 +14,7 @@ on Gen3 and RZ/G2 platforms to a CSI-2 receiver.
    - "renesas,vin-r8a7744" for the R8A7744 device
    - "renesas,vin-r8a7745" for the R8A7745 device
    - "renesas,vin-r8a774a1" for the R8A774A1 device
+   - "renesas,vin-r8a774b1" for the R8A774B1 device
    - "renesas,vin-r8a774c0" for the R8A774C0 device
    - "renesas,vin-r8a7778" for the R8A7778 device
    - "renesas,vin-r8a7779" for the R8A7779 device
@@ -43,7 +44,7 @@ on Gen3 and RZ/G2 platforms to a CSI-2 receiver.
 Additionally, an alias named vinX will need to be created to specify
 which video input device this is.
 
-The per-board settings Gen2 platforms:
+The per-board settings for Gen2 and RZ/G1 platforms:
 
 - port - sub-node describing a single endpoint connected to the VIN
   from external SoC pins as described in video-interfaces.txt[1].
@@ -63,7 +64,7 @@ The per-board settings Gen2 platforms:
     - data-enable-active: polarity of CLKENB signal, see [1] for
       description. Default is active high.
 
-The per-board settings Gen3 and RZ/G2 platforms:
+The per-board settings for Gen3 and RZ/G2 platforms:
 
 Gen3 and RZ/G2 platforms can support both a single connected parallel input
 source from external SoC pins (port@0) and/or multiple parallel input sources
diff --git a/Documentation/devicetree/bindings/media/sh_mobile_ceu.txt b/Documentation/devicetree/bindings/media/sh_mobile_ceu.txt
deleted file mode 100644
index cfa4ffada8ae..000000000000
--- a/Documentation/devicetree/bindings/media/sh_mobile_ceu.txt
+++ /dev/null
@@ -1,17 +0,0 @@
-Bindings, specific for the sh_mobile_ceu_camera.c driver:
- - compatible: Should be "renesas,sh-mobile-ceu"
- - reg: register base and size
- - interrupts: the interrupt number
- - renesas,max-width: maximum image width, supported on this SoC
- - renesas,max-height: maximum image height, supported on this SoC
-
-Example:
-
-ceu0: ceu@fe910000 {
-	compatible = "renesas,sh-mobile-ceu";
-	reg = <0xfe910000 0xa0>;
-	interrupt-parent = <&intcs>;
-	interrupts = <0x880>;
-	renesas,max-width = <8188>;
-	renesas,max-height = <8188>;
-};
diff --git a/Documentation/devicetree/bindings/media/ti,vpe.yaml b/Documentation/devicetree/bindings/media/ti,vpe.yaml
new file mode 100644
index 000000000000..f3a8a350e85f
--- /dev/null
+++ b/Documentation/devicetree/bindings/media/ti,vpe.yaml
@@ -0,0 +1,64 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/media/ti,vpe.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Texas Instruments DRA7x Video Processing Engine (VPE) Device Tree Bindings
+
+maintainers:
+  - Benoit Parrot <bparrot@ti.com>
+
+description: |-
+  The Video Processing Engine (VPE) is a key component for image post
+  processing applications. VPE consist of a single memory to memory
+  path which can perform chroma up/down sampling, deinterlacing,
+  scaling and color space conversion.
+
+properties:
+  compatible:
+      const: ti,dra7-vpe
+
+  reg:
+    items:
+      - description: The VPE main register region
+      - description: Scaler (SC) register region
+      - description: Color Space Conversion (CSC) register region
+      - description: Video Port Direct Memory Access (VPDMA) register region
+
+  reg-names:
+    items:
+      - const: vpe_top
+      - const: sc
+      - const: csc
+      - const: vpdma
+
+  interrupts:
+    maxItems: 1
+
+required:
+  - compatible
+  - reg
+  - reg-names
+  - interrupts
+
+additionalProperties: false
+
+examples:
+  - |
+    #include <dt-bindings/interrupt-controller/arm-gic.h>
+
+    vpe: vpe@489d0000 {
+        compatible = "ti,dra7-vpe";
+        reg = <0x489d0000 0x120>,
+              <0x489d0700 0x80>,
+              <0x489d5700 0x18>,
+              <0x489dd000 0x400>;
+        reg-names = "vpe_top",
+                    "sc",
+                    "csc",
+                    "vpdma";
+        interrupts = <GIC_SPI 354 IRQ_TYPE_LEVEL_HIGH>;
+    };
+
+...
diff --git a/Documentation/devicetree/bindings/sound/adi,adau7118.yaml b/Documentation/devicetree/bindings/sound/adi,adau7118.yaml
new file mode 100644
index 000000000000..75e0cbe6be70
--- /dev/null
+++ b/Documentation/devicetree/bindings/sound/adi,adau7118.yaml
@@ -0,0 +1,85 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/sound/adi,adau7118.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+
+title: Analog Devices ADAU7118 8 Channel PDM to I2S/TDM Converter
+
+maintainers:
+  - Nuno Sá <nuno.sa@analog.com>
+
+description: |
+  Analog Devices ADAU7118 8 Channel PDM to I2S/TDM Converter over I2C or HW
+  standalone mode.
+  https://www.analog.com/media/en/technical-documentation/data-sheets/ADAU7118.pdf
+
+properties:
+  compatible:
+    enum:
+      - adi,adau7118
+
+  reg:
+    maxItems: 1
+
+  "#sound-dai-cells":
+    const: 0
+
+  iovdd-supply:
+    description: Digital Input/Output Power Supply.
+
+  dvdd-supply:
+    description: Internal Core Digital Power Supply.
+
+  adi,decimation-ratio:
+    description: |
+      This property set's the decimation ratio of PDM to PCM audio data.
+    allOf:
+      - $ref: /schemas/types.yaml#/definitions/uint32
+      - enum: [64, 32, 16]
+        default: 64
+
+  adi,pdm-clk-map:
+    description: |
+      The ADAU7118 has two PDM clocks for the four Inputs. Each input must be
+      assigned to one of these two clocks. This property set's the mapping
+      between the clocks and the inputs.
+    allOf:
+      - $ref: /schemas/types.yaml#/definitions/uint32-array
+      - minItems: 4
+        maxItems: 4
+        items:
+          maximum: 1
+        default: [0, 0, 1, 1]
+
+required:
+  - "#sound-dai-cells"
+  - compatible
+  - iovdd-supply
+  - dvdd-supply
+
+examples:
+  - |
+    i2c {
+        /* example with i2c support */
+        #address-cells = <1>;
+        #size-cells = <0>;
+        adau7118_codec: audio-codec@14 {
+                compatible = "adi,adau7118";
+                reg = <0x14>;
+                #sound-dai-cells = <0>;
+                iovdd-supply = <&supply>;
+                dvdd-supply = <&supply>;
+                adi,pdm-clk-map = <1 1 0 0>;
+                adi,decimation-ratio = <16>;
+        };
+    };
+
+    /* example with hw standalone mode */
+    adau7118_codec_hw: adau7118-codec-hw {
+            compatible = "adi,adau7118";
+            #sound-dai-cells = <0>;
+            iovdd-supply = <&supply>;
+            dvdd-supply = <&supply>;
+    };
diff --git a/Documentation/devicetree/bindings/sound/allwinner,sun4i-a10-codec.yaml b/Documentation/devicetree/bindings/sound/allwinner,sun4i-a10-codec.yaml
new file mode 100644
index 000000000000..b8f89c7258eb
--- /dev/null
+++ b/Documentation/devicetree/bindings/sound/allwinner,sun4i-a10-codec.yaml
@@ -0,0 +1,267 @@
+# SPDX-License-Identifier: GPL-2.0
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/sound/allwinner,sun4i-a10-codec.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Allwinner A10 Codec Device Tree Bindings
+
+maintainers:
+  - Chen-Yu Tsai <wens@csie.org>
+  - Maxime Ripard <maxime.ripard@bootlin.com>
+
+properties:
+  "#sound-dai-cells":
+    const: 0
+
+  compatible:
+    enum:
+      - allwinner,sun4i-a10-codec
+      - allwinner,sun6i-a31-codec
+      - allwinner,sun7i-a20-codec
+      - allwinner,sun8i-a23-codec
+      - allwinner,sun8i-h3-codec
+      - allwinner,sun8i-v3s-codec
+
+  reg:
+    maxItems: 1
+
+  interrupts:
+    maxItems: 1
+
+  clocks:
+    items:
+      - description: Bus Clock
+      - description: Module Clock
+
+  clock-names:
+    items:
+      - const: apb
+      - const: codec
+
+  dmas:
+    items:
+      - description: RX DMA Channel
+      - description: TX DMA Channel
+
+  dma-names:
+    items:
+      - const: rx
+      - const: tx
+
+  resets:
+    maxItems: 1
+
+  allwinner,audio-routing:
+    description: |-
+      A list of the connections between audio components.  Each entry
+      is a pair of strings, the first being the connection's sink, the
+      second being the connection's source.
+    allOf:
+      - $ref: /schemas/types.yaml#definitions/non-unique-string-array
+      - minItems: 2
+        maxItems: 18
+        items:
+          enum:
+            # Audio Pins on the SoC
+            - HP
+            - HPCOM
+            - LINEIN
+            - LINEOUT
+            - MIC1
+            - MIC2
+            - MIC3
+
+            # Microphone Biases from the SoC
+            - HBIAS
+            - MBIAS
+
+            # Board Connectors
+            - Headphone
+            - Headset Mic
+            - Line In
+            - Line Out
+            - Mic
+            - Speaker
+
+  allwinner,codec-analog-controls:
+    $ref: /schemas/types.yaml#/definitions/phandle
+    description: Phandle to the codec analog controls in the PRCM
+
+  allwinner,pa-gpios:
+    description: GPIO to enable the external amplifier
+
+required:
+  - "#sound-dai-cells"
+  - compatible
+  - reg
+  - interrupts
+  - clocks
+  - clock-names
+  - dmas
+  - dma-names
+
+allOf:
+  - if:
+      properties:
+        compatible:
+          enum:
+            - allwinner,sun6i-a31-codec
+            - allwinner,sun8i-a23-codec
+            - allwinner,sun8i-h3-codec
+            - allwinner,sun8i-v3s-codec
+
+    then:
+      if:
+        properties:
+          compatible:
+            const: allwinner,sun6i-a31-codec
+
+      then:
+        required:
+          - resets
+          - allwinner,audio-routing
+
+      else:
+        required:
+          - resets
+          - allwinner,audio-routing
+          - allwinner,codec-analog-controls
+
+  - if:
+      properties:
+        compatible:
+          enum:
+            - allwinner,sun6i-a31-codec
+
+    then:
+      properties:
+        allwinner,audio-routing:
+          items:
+            enum:
+              - HP
+              - HPCOM
+              - LINEIN
+              - LINEOUT
+              - MIC1
+              - MIC2
+              - MIC3
+              - HBIAS
+              - MBIAS
+              - Headphone
+              - Headset Mic
+              - Line In
+              - Line Out
+              - Mic
+              - Speaker
+
+  - if:
+      properties:
+        compatible:
+          enum:
+            - allwinner,sun8i-a23-codec
+
+    then:
+      properties:
+        allwinner,audio-routing:
+          items:
+            enum:
+              - HP
+              - HPCOM
+              - LINEIN
+              - MIC1
+              - MIC2
+              - HBIAS
+              - MBIAS
+              - Headphone
+              - Headset Mic
+              - Line In
+              - Line Out
+              - Mic
+              - Speaker
+
+  - if:
+      properties:
+        compatible:
+          enum:
+            - allwinner,sun8i-h3-codec
+
+    then:
+      properties:
+        allwinner,audio-routing:
+          items:
+            enum:
+              - HP
+              - HPCOM
+              - LINEIN
+              - LINEOUT
+              - MIC1
+              - MIC2
+              - HBIAS
+              - MBIAS
+              - Headphone
+              - Headset Mic
+              - Line In
+              - Line Out
+              - Mic
+              - Speaker
+
+  - if:
+      properties:
+        compatible:
+          enum:
+            - allwinner,sun8i-v3s-codec
+
+    then:
+      properties:
+        allwinner,audio-routing:
+          items:
+            enum:
+              - HP
+              - HPCOM
+              - MIC1
+              - HBIAS
+              - Headphone
+              - Headset Mic
+              - Line In
+              - Line Out
+              - Mic
+              - Speaker
+
+additionalProperties: false
+
+examples:
+  - |
+    codec@1c22c00 {
+        #sound-dai-cells = <0>;
+        compatible = "allwinner,sun7i-a20-codec";
+        reg = <0x01c22c00 0x40>;
+        interrupts = <0 30 4>;
+        clocks = <&apb0_gates 0>, <&codec_clk>;
+        clock-names = "apb", "codec";
+        dmas = <&dma 0 19>, <&dma 0 19>;
+        dma-names = "rx", "tx";
+    };
+
+  - |
+    codec@1c22c00 {
+        #sound-dai-cells = <0>;
+        compatible = "allwinner,sun6i-a31-codec";
+        reg = <0x01c22c00 0x98>;
+        interrupts = <0 29 4>;
+        clocks = <&ccu 61>, <&ccu 135>;
+        clock-names = "apb", "codec";
+        resets = <&ccu 42>;
+        dmas = <&dma 15>, <&dma 15>;
+        dma-names = "rx", "tx";
+        allwinner,audio-routing =
+            "Headphone", "HP",
+            "Speaker", "LINEOUT",
+            "LINEIN", "Line In",
+            "MIC1", "MBIAS",
+            "MIC1", "Mic",
+            "MIC2", "HBIAS",
+            "MIC2", "Headset Mic";
+    };
+
+...
diff --git a/Documentation/devicetree/bindings/sound/allwinner,sun8i-a23-codec-analog.yaml b/Documentation/devicetree/bindings/sound/allwinner,sun8i-a23-codec-analog.yaml
new file mode 100644
index 000000000000..85305b4c2729
--- /dev/null
+++ b/Documentation/devicetree/bindings/sound/allwinner,sun8i-a23-codec-analog.yaml
@@ -0,0 +1,38 @@
+# SPDX-License-Identifier: GPL-2.0
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/sound/allwinner,sun8i-a23-codec-analog.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Allwinner A23 Analog Codec Device Tree Bindings
+
+maintainers:
+  - Chen-Yu Tsai <wens@csie.org>
+  - Maxime Ripard <maxime.ripard@bootlin.com>
+
+properties:
+  compatible:
+    enum:
+      # FIXME: This is documented in the PRCM binding, but needs to be
+      # migrated here at some point
+      # - allwinner,sun8i-a23-codec-analog
+      - allwinner,sun8i-h3-codec-analog
+      - allwinner,sun8i-v3s-codec-analog
+
+  reg:
+    maxItems: 1
+
+required:
+  - compatible
+  - reg
+
+additionalProperties: false
+
+examples:
+  - |
+    codec_analog: codec-analog@1f015c0 {
+      compatible = "allwinner,sun8i-h3-codec-analog";
+      reg = <0x01f015c0 0x4>;
+    };
+
+...
diff --git a/Documentation/devicetree/bindings/sound/arndale.txt b/Documentation/devicetree/bindings/sound/arndale.txt
index 0e76946385ae..17530120ccfc 100644
--- a/Documentation/devicetree/bindings/sound/arndale.txt
+++ b/Documentation/devicetree/bindings/sound/arndale.txt
@@ -1,8 +1,9 @@
 Audio Binding for Arndale boards
 
 Required properties:
-- compatible : Can be the following,
-			"samsung,arndale-rt5631"
+- compatible : Can be one of the following:
+		"samsung,arndale-rt5631",
+		"samsung,arndale-wm1811"
 
 - samsung,audio-cpu: The phandle of the Samsung I2S controller
 - samsung,audio-codec: The phandle of the audio codec
diff --git a/Documentation/devicetree/bindings/sound/fsl,mqs.txt b/Documentation/devicetree/bindings/sound/fsl,mqs.txt
new file mode 100644
index 000000000000..40353fc30255
--- /dev/null
+++ b/Documentation/devicetree/bindings/sound/fsl,mqs.txt
@@ -0,0 +1,36 @@
+fsl,mqs audio CODEC
+
+Required properties:
+  - compatible : Must contain one of "fsl,imx6sx-mqs", "fsl,codec-mqs"
+		"fsl,imx8qm-mqs", "fsl,imx8qxp-mqs".
+  - clocks : A list of phandles + clock-specifiers, one for each entry in
+	     clock-names
+  - clock-names : "mclk" - must required.
+		  "core" - required if compatible is "fsl,imx8qm-mqs", it
+		           is for register access.
+  - gpr : A phandle of General Purpose Registers in IOMUX Controller.
+	  Required if compatible is "fsl,imx6sx-mqs".
+
+Required if compatible is "fsl,imx8qm-mqs":
+  - power-domains: A phandle of PM domain provider node.
+  - reg: Offset and length of the register set for the device.
+
+Example:
+
+mqs: mqs {
+	compatible = "fsl,imx6sx-mqs";
+	gpr = <&gpr>;
+	clocks = <&clks IMX6SX_CLK_SAI1>;
+	clock-names = "mclk";
+	status = "disabled";
+};
+
+mqs: mqs@59850000 {
+	compatible = "fsl,imx8qm-mqs";
+	reg = <0x59850000 0x10000>;
+	clocks = <&clk IMX8QM_AUD_MQS_IPG>,
+		 <&clk IMX8QM_AUD_MQS_HMCLK>;
+	clock-names = "core", "mclk";
+	power-domains = <&pd_mqs0>;
+	status = "disabled";
+};
diff --git a/Documentation/devicetree/bindings/sound/google,cros-ec-codec.txt b/Documentation/devicetree/bindings/sound/google,cros-ec-codec.txt
index 1084f7f22eea..8ca52dcc5572 100644
--- a/Documentation/devicetree/bindings/sound/google,cros-ec-codec.txt
+++ b/Documentation/devicetree/bindings/sound/google,cros-ec-codec.txt
@@ -1,4 +1,4 @@
-* Audio codec controlled by ChromeOS EC
+Audio codec controlled by ChromeOS EC
 
 Google's ChromeOS EC codec is a digital mic codec provided by the
 Embedded Controller (EC) and is controlled via a host-command interface.
@@ -9,10 +9,27 @@ Documentation/devicetree/bindings/mfd/cros-ec.txt).
 Required properties:
 - compatible: Must contain "google,cros-ec-codec"
 - #sound-dai-cells: Should be 1. The cell specifies number of DAIs.
-- max-dmic-gain: A number for maximum gain in dB on digital microphone.
+
+Optional properties:
+- reg: Pysical base address and length of shared memory region from EC.
+       It contains 3 unsigned 32-bit integer.  The first 2 integers
+       combine to become an unsigned 64-bit physical address.  The last
+       one integer is length of the shared memory.
+- memory-region: Shared memory region to EC.  A "shared-dma-pool".  See
+                 ../reserved-memory/reserved-memory.txt for details.
 
 Example:
 
+{
+	...
+
+	reserved_mem: reserved_mem {
+		compatible = "shared-dma-pool";
+		reg = <0 0x52800000 0 0x100000>;
+		no-map;
+	};
+}
+
 cros-ec@0 {
 	compatible = "google,cros-ec-spi";
 
@@ -21,6 +38,7 @@ cros-ec@0 {
 	cros_ec_codec: ec-codec {
 		compatible = "google,cros-ec-codec";
 		#sound-dai-cells = <1>;
-		max-dmic-gain = <43>;
+		reg = <0x0 0x10500000 0x80000>;
+		memory-region = <&reserved_mem>;
 	};
 };
diff --git a/Documentation/devicetree/bindings/sound/mt8183-afe-pcm.txt b/Documentation/devicetree/bindings/sound/mt8183-afe-pcm.txt
index 396ba38619f6..1f1cba4152ce 100644
--- a/Documentation/devicetree/bindings/sound/mt8183-afe-pcm.txt
+++ b/Documentation/devicetree/bindings/sound/mt8183-afe-pcm.txt
@@ -4,6 +4,10 @@ Required properties:
 - compatible = "mediatek,mt68183-audio";
 - reg: register location and size
 - interrupts: should contain AFE interrupt
+- resets: Must contain an entry for each entry in reset-names
+  See ../reset/reset.txt for details.
+- reset-names: should have these reset names:
+		"audiosys";
 - power-domains: should define the power domain
 - clocks: Must contain an entry for each entry in clock-names
 - clock-names: should have these clock names:
@@ -20,6 +24,8 @@ Example:
 		compatible = "mediatek,mt8183-audio";
 		reg = <0 0x11220000 0 0x1000>;
 		interrupts = <GIC_SPI 161 IRQ_TYPE_LEVEL_LOW>;
+		resets = <&watchdog MT8183_TOPRGU_AUDIO_SW_RST>;
+		reset-names = "audiosys";
 		power-domains = <&scpsys MT8183_POWER_DOMAIN_AUDIO>;
 		clocks = <&infrasys CLK_INFRA_AUDIO>,
 			 <&infrasys CLK_INFRA_AUDIO_26M_BCLK>,
diff --git a/Documentation/devicetree/bindings/sound/mt8183-mt6358-ts3a227-max98357.txt b/Documentation/devicetree/bindings/sound/mt8183-mt6358-ts3a227-max98357.txt
index d6d5207fa996..decaa013a07e 100644
--- a/Documentation/devicetree/bindings/sound/mt8183-mt6358-ts3a227-max98357.txt
+++ b/Documentation/devicetree/bindings/sound/mt8183-mt6358-ts3a227-max98357.txt
@@ -2,14 +2,19 @@ MT8183 with MT6358, TS3A227 and MAX98357 CODECS
 
 Required properties:
 - compatible : "mediatek,mt8183_mt6358_ts3a227_max98357"
-- mediatek,headset-codec: the phandles of ts3a227 codecs
 - mediatek,platform: the phandle of MT8183 ASoC platform
 
+Optional properties:
+- mediatek,headset-codec: the phandles of ts3a227 codecs
+- mediatek,ec-codec: the phandle of EC codecs.
+                     See google,cros-ec-codec.txt for more details.
+
 Example:
 
 	sound {
 		compatible = "mediatek,mt8183_mt6358_ts3a227_max98357";
 		mediatek,headset-codec = <&ts3a227>;
+		mediatek,ec-codec = <&ec_codec>;
 		mediatek,platform = <&afe>;
 	};
 
diff --git a/Documentation/devicetree/bindings/sound/renesas,fsi.txt b/Documentation/devicetree/bindings/sound/renesas,fsi.txt
deleted file mode 100644
index 0cf0f819b823..000000000000
--- a/Documentation/devicetree/bindings/sound/renesas,fsi.txt
+++ /dev/null
@@ -1,31 +0,0 @@
-Renesas FSI
-
-Required properties:
-- compatible			: "renesas,fsi2-<soctype>",
-				  "renesas,sh_fsi2" or "renesas,sh_fsi" as
-				  fallback.
-				  Examples with soctypes are:
-				    - "renesas,fsi2-r8a7740" (R-Mobile A1)
-				    - "renesas,fsi2-sh73a0" (SH-Mobile AG5)
-- reg				: Should contain the register physical address and length
-- interrupts			: Should contain FSI interrupt
-
-- fsia,spdif-connection		: FSI is connected by S/PDIF
-- fsia,stream-mode-support	: FSI supports 16bit stream mode.
-- fsia,use-internal-clock	: FSI uses internal clock when master mode.
-
-- fsib,spdif-connection		: same as fsia
-- fsib,stream-mode-support	: same as fsia
-- fsib,use-internal-clock	: same as fsia
-
-Example:
-
-sh_fsi2: sh_fsi2@ec230000 {
-	compatible = "renesas,sh_fsi2";
-	reg = <0xec230000 0x400>;
-	interrupts = <0 146 0x4>;
-
-	fsia,spdif-connection;
-	fsia,stream-mode-support;
-	fsia,use-internal-clock;
-};
diff --git a/Documentation/devicetree/bindings/sound/renesas,fsi.yaml b/Documentation/devicetree/bindings/sound/renesas,fsi.yaml
new file mode 100644
index 000000000000..140a37fc3c0b
--- /dev/null
+++ b/Documentation/devicetree/bindings/sound/renesas,fsi.yaml
@@ -0,0 +1,76 @@
+# SPDX-License-Identifier: GPL-2.0
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/sound/renesas,fsi.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Renesas FSI Sound Driver Device Tree Bindings
+
+maintainers:
+  - Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
+
+properties:
+  $nodename:
+    pattern: "^sound@.*"
+
+  compatible:
+    oneOf:
+      # for FSI2 SoC
+      - items:
+        - enum:
+          - renesas,fsi2-sh73a0
+          - renesas,fsi2-r8a7740
+        - enum:
+          - renesas,sh_fsi2
+      # for Generic
+      - items:
+        - enum:
+          - renesas,sh_fsi
+          - renesas,sh_fsi2
+
+  reg:
+    maxItems: 1
+
+  interrupts:
+    maxItems: 1
+
+  fsia,spdif-connection:
+    $ref: /schemas/types.yaml#/definitions/flag
+    description: FSI is connected by S/PDIF
+
+  fsia,stream-mode-support:
+    $ref: /schemas/types.yaml#/definitions/flag
+    description: FSI supports 16bit stream mode
+
+  fsia,use-internal-clock:
+    $ref: /schemas/types.yaml#/definitions/flag
+    description: FSI uses internal clock when master mode
+
+  fsib,spdif-connection:
+    $ref: /schemas/types.yaml#/definitions/flag
+    description: same as fsia
+
+  fsib,stream-mode-support:
+    $ref: /schemas/types.yaml#/definitions/flag
+    description: same as fsia
+
+  fsib,use-internal-clock:
+    $ref: /schemas/types.yaml#/definitions/flag
+    description: same as fsia
+
+required:
+  - compatible
+  - reg
+  - interrupts
+
+examples:
+  - |
+    sh_fsi2: sound@ec230000 {
+            compatible = "renesas,fsi2-r8a7740", "renesas,sh_fsi2";
+            reg = <0xec230000 0x400>;
+            interrupts = <0 146 0x4>;
+
+            fsia,spdif-connection;
+            fsia,stream-mode-support;
+            fsia,use-internal-clock;
+    };
diff --git a/Documentation/devicetree/bindings/sound/renesas,rsnd.txt b/Documentation/devicetree/bindings/sound/renesas,rsnd.txt
index 5c52182f7dcf..797fd035434c 100644
--- a/Documentation/devicetree/bindings/sound/renesas,rsnd.txt
+++ b/Documentation/devicetree/bindings/sound/renesas,rsnd.txt
@@ -268,6 +268,7 @@ Required properties:
 				    - "renesas,rcar_sound-r8a7745" (RZ/G1E)
 				    - "renesas,rcar_sound-r8a77470" (RZ/G1C)
 				    - "renesas,rcar_sound-r8a774a1" (RZ/G2M)
+				    - "renesas,rcar_sound-r8a774b1" (RZ/G2N)
 				    - "renesas,rcar_sound-r8a774c0" (RZ/G2E)
 				    - "renesas,rcar_sound-r8a7778" (R-Car M1A)
 				    - "renesas,rcar_sound-r8a7779" (R-Car H1)
diff --git a/Documentation/devicetree/bindings/sound/rockchip-max98090.txt b/Documentation/devicetree/bindings/sound/rockchip-max98090.txt
index a805aa99ad75..e9c58b204399 100644
--- a/Documentation/devicetree/bindings/sound/rockchip-max98090.txt
+++ b/Documentation/devicetree/bindings/sound/rockchip-max98090.txt
@@ -5,15 +5,38 @@ Required properties:
 - rockchip,model: The user-visible name of this sound complex
 - rockchip,i2s-controller: The phandle of the Rockchip I2S controller that's
   connected to the CODEC
-- rockchip,audio-codec: The phandle of the MAX98090 audio codec
-- rockchip,headset-codec: The phandle of Ext chip for jack detection
+
+Optional properties:
+- rockchip,audio-codec: The phandle of the MAX98090 audio codec.
+- rockchip,headset-codec: The phandle of Ext chip for jack detection. This is
+                          required if there is rockchip,audio-codec.
+- rockchip,hdmi-codec: The phandle of HDMI device for HDMI codec.
 
 Example:
 
+/* For max98090-only board. */
+sound {
+	compatible = "rockchip,rockchip-audio-max98090";
+	rockchip,model = "ROCKCHIP-I2S";
+	rockchip,i2s-controller = <&i2s>;
+	rockchip,audio-codec = <&max98090>;
+	rockchip,headset-codec = <&headsetcodec>;
+};
+
+/* For HDMI-only board. */
+sound {
+	compatible = "rockchip,rockchip-audio-max98090";
+	rockchip,model = "ROCKCHIP-I2S";
+	rockchip,i2s-controller = <&i2s>;
+	rockchip,hdmi-codec = <&hdmi>;
+};
+
+/* For max98090 plus HDMI board. */
 sound {
 	compatible = "rockchip,rockchip-audio-max98090";
 	rockchip,model = "ROCKCHIP-I2S";
 	rockchip,i2s-controller = <&i2s>;
 	rockchip,audio-codec = <&max98090>;
 	rockchip,headset-codec = <&headsetcodec>;
+	rockchip,hdmi-codec = <&hdmi>;
 };
diff --git a/Documentation/devicetree/bindings/sound/rt1011.txt b/Documentation/devicetree/bindings/sound/rt1011.txt
index 35a23e60d679..02d53b9aa247 100644
--- a/Documentation/devicetree/bindings/sound/rt1011.txt
+++ b/Documentation/devicetree/bindings/sound/rt1011.txt
@@ -20,6 +20,14 @@ Required properties:
         |     1     |    1     |   0x3b     |
         -------------------------------------
 
+Optional properties:
+
+- realtek,temperature_calib
+  u32. The temperature was measured while doing the calibration. Units: Celsius degree
+
+- realtek,r0_calib
+  u32. This is r0 calibration data which was measured in factory mode.
+
 Pins on the device (for linking into audio routes) for RT1011:
 
   * SPO
@@ -29,4 +37,6 @@ Example:
 rt1011: codec@38 {
 	compatible = "realtek,rt1011";
 	reg = <0x38>;
+	realtek,temperature_calib = <25>;
+	realtek,r0_calib = <0x224050>;
 };
diff --git a/Documentation/devicetree/bindings/sound/rt5682.txt b/Documentation/devicetree/bindings/sound/rt5682.txt
index 312e9a129530..30e927a28369 100644
--- a/Documentation/devicetree/bindings/sound/rt5682.txt
+++ b/Documentation/devicetree/bindings/sound/rt5682.txt
@@ -27,6 +27,11 @@ Optional properties:
 
 - realtek,ldo1-en-gpios : The GPIO that controls the CODEC's LDO1_EN pin.
 
+- realtek,btndet-delay
+  The debounce delay for push button.
+  The delay time is realtek,btndet-delay value multiple of 8.192 ms.
+  If absent, the default is 16.
+
 Pins on the device (for linking into audio routes) for RT5682:
 
   * DMIC L1
@@ -47,4 +52,5 @@ rt5682 {
 	realtek,dmic1-data-pin = <1>;
 	realtek,dmic1-clk-pin = <1>;
 	realtek,jd-src = <1>;
+	realtek,btndet-delay = <16>;
 };
diff --git a/Documentation/devicetree/bindings/sound/samsung,odroid.txt b/Documentation/devicetree/bindings/sound/samsung,odroid.txt
deleted file mode 100644
index e9da2200e173..000000000000
--- a/Documentation/devicetree/bindings/sound/samsung,odroid.txt
+++ /dev/null
@@ -1,54 +0,0 @@
-Samsung Exynos Odroid XU3/XU4 audio complex with MAX98090 codec
-
-Required properties:
-
- - compatible - "hardkernel,odroid-xu3-audio" - for Odroid XU3 board,
-		"hardkernel,odroid-xu4-audio" - for Odroid XU4 board (deprecated),
-		"samsung,odroid-xu3-audio" - for Odroid XU3 board (deprecated),
-		"samsung,odroid-xu4-audio" - for Odroid XU4 board (deprecated)
- - model - the user-visible name of this sound complex
- - clocks - should contain entries matching clock names in the clock-names
-    property
- - samsung,audio-widgets - this property specifies off-codec audio elements
-   like headphones or speakers, for details see widgets.txt
- - samsung,audio-routing - a list of the connections between audio
-   components;  each entry is a pair of strings, the first being the
-   connection's sink, the second being the connection's source;
-   valid names for sources and sinks are the MAX98090's pins (as
-   documented in its binding), and the jacks on the board
-
-   For Odroid X2:
-     "Headphone Jack", "Mic Jack", "DMIC"
-
-   For Odroid U3, XU3:
-     "Headphone Jack", "Speakers"
-
-   For Odroid XU4:
-     no entries
-
-Required sub-nodes:
-
- - 'cpu' subnode with a 'sound-dai' property containing the phandle of the I2S
-    controller
- - 'codec' subnode with a 'sound-dai' property containing list of phandles
-    to the CODEC nodes, first entry must be corresponding to the MAX98090
-    CODEC and the second entry must be the phandle of the HDMI IP block node
-
-Example:
-
-sound {
-	compatible = "hardkernel,odroid-xu3-audio";
-	model = "Odroid-XU3";
-	samsung,audio-routing =
-		"Headphone Jack", "HPL",
-		"Headphone Jack", "HPR",
-		"IN1", "Mic Jack",
-		"Mic Jack", "MICBIAS";
-
-	cpu {
-		sound-dai = <&i2s0 0>;
-	};
-	codec {
-		sound-dai = <&hdmi>, <&max98090>;
-	};
-};
diff --git a/Documentation/devicetree/bindings/sound/samsung,odroid.yaml b/Documentation/devicetree/bindings/sound/samsung,odroid.yaml
new file mode 100644
index 000000000000..c6b244352d05
--- /dev/null
+++ b/Documentation/devicetree/bindings/sound/samsung,odroid.yaml
@@ -0,0 +1,91 @@
+# SPDX-License-Identifier: GPL-2.0
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/sound/samsung,odroid.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Samsung Exynos Odroid XU3/XU4 audio complex with MAX98090 codec
+
+maintainers:
+  - Krzysztof Kozlowski <krzk@kernel.org>
+  - Sylwester Nawrocki <s.nawrocki@samsung.com>
+
+properties:
+  compatible:
+    oneOf:
+      - const: hardkernel,odroid-xu3-audio
+
+      - const: hardkernel,odroid-xu4-audio
+        deprecated: true
+
+      - const: samsung,odroid-xu3-audio
+        deprecated: true
+
+      - const: samsung,odroid-xu4-audio
+        deprecated: true
+
+  model:
+    $ref: /schemas/types.yaml#/definitions/string
+    description: The user-visible name of this sound complex.
+
+  cpu:
+    type: object
+    properties:
+      sound-dai:
+        $ref: /schemas/types.yaml#/definitions/phandle-array
+        description: phandles to the I2S controllers
+
+  codec:
+    type: object
+    properties:
+      sound-dai:
+        $ref: /schemas/types.yaml#/definitions/phandle-array
+        description: |
+          List of phandles to the CODEC nodes,
+          first entry must be corresponding to the MAX98090 CODEC and
+          the second entry must be the phandle of the HDMI IP block node.
+
+  samsung,audio-routing:
+    $ref: /schemas/types.yaml#/definitions/non-unique-string-array
+    description: |
+      List of the connections between audio
+      components;  each entry is a pair of strings, the first being the
+      connection's sink, the second being the connection's source;
+      valid names for sources and sinks are the MAX98090's pins (as
+      documented in its binding), and the jacks on the board.
+      For Odroid X2: "Headphone Jack", "Mic Jack", "DMIC"
+      For Odroid U3, XU3: "Headphone Jack", "Speakers"
+      For Odroid XU4: no entries
+
+  samsung,audio-widgets:
+    $ref: /schemas/types.yaml#/definitions/non-unique-string-array
+    description: |
+      This property specifies off-codec audio elements
+      like headphones or speakers, for details see widgets.txt
+
+required:
+  - compatible
+  - model
+  - cpu
+  - codec
+
+examples:
+  - |
+    sound {
+        compatible = "hardkernel,odroid-xu3-audio";
+        model = "Odroid-XU3";
+        samsung,audio-routing =
+                "Headphone Jack", "HPL",
+                "Headphone Jack", "HPR",
+                "IN1", "Mic Jack",
+                "Mic Jack", "MICBIAS";
+
+        cpu {
+            sound-dai = <&i2s0 0>;
+        };
+
+        codec {
+            sound-dai = <&hdmi>, <&max98090>;
+        };
+    };
+
diff --git a/Documentation/devicetree/bindings/sound/samsung-i2s.txt b/Documentation/devicetree/bindings/sound/samsung-i2s.txt
deleted file mode 100644
index a88cb00fa096..000000000000
--- a/Documentation/devicetree/bindings/sound/samsung-i2s.txt
+++ /dev/null
@@ -1,84 +0,0 @@
-* Samsung I2S controller
-
-Required SoC Specific Properties:
-
-- compatible : should be one of the following.
-   - samsung,s3c6410-i2s: for 8/16/24bit stereo I2S.
-   - samsung,s5pv210-i2s: for 8/16/24bit multichannel(5.1) I2S with
-     secondary fifo, s/w reset control and internal mux for root clk src.
-   - samsung,exynos5420-i2s: for 8/16/24bit multichannel(5.1) I2S for
-     playback, stereo channel capture, secondary fifo using internal
-     or external dma, s/w reset control, internal mux for root clk src
-     and 7.1 channel TDM support for playback. TDM (Time division multiplexing)
-     is to allow transfer of multiple channel audio data on single data line.
-   - samsung,exynos7-i2s: with all the available features of exynos5 i2s,
-     exynos7 I2S has 7.1 channel TDM support for capture, secondary fifo
-     with only external dma and more no.of root clk sampling frequencies.
-   - samsung,exynos7-i2s1: I2S1 on previous samsung platforms supports
-     stereo channels. exynos7 i2s1 upgraded to 5.1 multichannel with
-     slightly modified bit offsets.
-
-- reg: physical base address of the controller and length of memory mapped
-  region.
-- dmas: list of DMA controller phandle and DMA request line ordered pairs.
-- dma-names: identifier string for each DMA request line in the dmas property.
-  These strings correspond 1:1 with the ordered pairs in dmas.
-- clocks: Handle to iis clock and RCLK source clk.
-- clock-names:
-  i2s0 uses some base clocks from CMU and some are from audio subsystem internal
-  clock controller. The clock names for i2s0 should be "iis", "i2s_opclk0" and
-  "i2s_opclk1" as shown in the example below.
-  i2s1 and i2s2 uses clocks from CMU. The clock names for i2s1 and i2s2 should
-  be "iis" and "i2s_opclk0".
-  "iis" is the i2s bus clock and i2s_opclk0, i2s_opclk1 are sources of the root
-  clk. i2s0 has internal mux to select the source of root clk and i2s1 and i2s2
-  doesn't have any such mux.
-- #clock-cells: should be 1, this property must be present if the I2S device
-  is a clock provider in terms of the common clock bindings, described in
-  ../clock/clock-bindings.txt.
-- clock-output-names (deprecated): from the common clock bindings, names of
-  the CDCLK I2S output clocks, suggested values are "i2s_cdclk0", "i2s_cdclk1",
-  "i2s_cdclk3" for the I2S0, I2S1, I2S2 devices respectively.
-
-There are following clocks available at the I2S device nodes:
- CLK_I2S_CDCLK    - the CDCLK (CODECLKO) gate clock,
- CLK_I2S_RCLK_PSR - the RCLK prescaler divider clock (corresponding to the
-		    IISPSR register),
- CLK_I2S_RCLK_SRC - the RCLKSRC mux clock (corresponding to RCLKSRC bit in
-		    IISMOD register).
-
-Refer to the SoC datasheet for availability of the above clocks.
-The CLK_I2S_RCLK_PSR and CLK_I2S_RCLK_SRC clocks are usually only available
-in the IIS Multi Audio Interface.
-
-Note: Old DTs may not have the #clock-cells property and then not use the I2S
-node as a clock supplier.
-
-Optional SoC Specific Properties:
-
-- samsung,idma-addr: Internal DMA register base address of the audio
-  sub system(used in secondary sound source).
-- pinctrl-0: Should specify pin control groups used for this controller.
-- pinctrl-names: Should contain only one value - "default".
-- #sound-dai-cells: should be 1.
-
-
-Example:
-
-i2s0: i2s@3830000 {
-	compatible = "samsung,s5pv210-i2s";
-	reg = <0x03830000 0x100>;
-	dmas = <&pdma0 10
-		&pdma0 9
-		&pdma0 8>;
-	dma-names = "tx", "rx", "tx-sec";
-	clocks = <&clock_audss EXYNOS_I2S_BUS>,
-		<&clock_audss EXYNOS_I2S_BUS>,
-		<&clock_audss EXYNOS_SCLK_I2S>;
-	clock-names = "iis", "i2s_opclk0", "i2s_opclk1";
-	#clock-cells = <1>;
-	samsung,idma-addr = <0x03000000>;
-	pinctrl-names = "default";
-	pinctrl-0 = <&i2s0_bus>;
-	#sound-dai-cells = <1>;
-};
diff --git a/Documentation/devicetree/bindings/sound/samsung-i2s.yaml b/Documentation/devicetree/bindings/sound/samsung-i2s.yaml
new file mode 100644
index 000000000000..53e3bad4178c
--- /dev/null
+++ b/Documentation/devicetree/bindings/sound/samsung-i2s.yaml
@@ -0,0 +1,138 @@
+# SPDX-License-Identifier: GPL-2.0
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/sound/samsung-i2s.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Samsung SoC I2S controller
+
+maintainers:
+  - Krzysztof Kozlowski <krzk@kernel.org>
+  - Sylwester Nawrocki <s.nawrocki@samsung.com>
+
+properties:
+  compatible:
+    description: |
+      samsung,s3c6410-i2s: for 8/16/24bit stereo I2S.
+
+      samsung,s5pv210-i2s: for 8/16/24bit multichannel (5.1) I2S with
+      secondary FIFO, s/w reset control and internal mux for root clock
+      source.
+
+      samsung,exynos5420-i2s: for 8/16/24bit multichannel (5.1) I2S for
+      playback, stereo channel capture, secondary FIFO using internal
+      or external DMA, s/w reset control, internal mux for root clock
+      source and 7.1 channel TDM support for playback; TDM (Time division
+      multiplexing) is to allow transfer of multiple channel audio data on
+      single data line.
+
+      samsung,exynos7-i2s: with all the available features of Exynos5 I2S.
+      Exynos7 I2S has 7.1 channel TDM support for capture, secondary FIFO
+      with only external DMA and more number of root clock sampling
+      frequencies.
+
+      samsung,exynos7-i2s1: I2S1 on previous samsung platforms supports
+      stereo channels. Exynos7 I2S1 upgraded to 5.1 multichannel with
+      slightly modified bit offsets.
+    enum:
+      - samsung,s3c6410-i2s
+      - samsung,s5pv210-i2s
+      - samsung,exynos5420-i2s
+      - samsung,exynos7-i2s
+      - samsung,exynos7-i2s1
+
+  reg:
+    maxItems: 1
+
+  dmas:
+    minItems: 2
+    maxItems: 3
+
+  dma-names:
+    oneOf:
+      - items:
+          - const: tx
+          - const: rx
+      - items:
+          - const: tx
+          - const: rx
+          - const: tx-sec
+
+  clocks:
+    minItems: 1
+    maxItems: 3
+
+  clock-names:
+    oneOf:
+      - items:
+          - const: iis
+      - items: # for I2S0
+          - const: iis
+          - const: i2s_opclk0
+          - const: i2s_opclk1
+      - items: # for I2S1 and I2S2
+          - const: iis
+          - const: i2s_opclk0
+    description: |
+      "iis" is the I2S bus clock and i2s_opclk0, i2s_opclk1 are sources
+      of the root clock. I2S0 has internal mux to select the source
+      of root clock and I2S1 and I2S2 doesn't have any such mux.
+
+  "#clock-cells":
+    const: 1
+
+  clock-output-names:
+    deprecated: true
+    oneOf:
+      - items: # for I2S0
+          - const: i2s_cdclk0
+      - items: # for I2S1
+          - const: i2s_cdclk1
+      - items: # for I2S2
+          - const: i2s_cdclk2
+    description: Names of the CDCLK I2S output clocks.
+
+  samsung,idma-addr:
+    $ref: /schemas/types.yaml#/definitions/uint32
+    description: |
+      Internal DMA register base address of the audio
+      subsystem (used in secondary sound source).
+
+  pinctrl-0:
+    description: Should specify pin control groups used for this controller.
+
+  pinctrl-names:
+    const: default
+
+  "#sound-dai-cells":
+    const: 1
+
+required:
+  - compatible
+  - reg
+  - dmas
+  - dma-names
+  - clocks
+  - clock-names
+
+examples:
+  - |
+    #include <dt-bindings/clock/exynos-audss-clk.h>
+
+    i2s0: i2s@3830000 {
+        compatible = "samsung,s5pv210-i2s";
+        reg = <0x03830000 0x100>;
+        dmas = <&pdma0 10>,
+                <&pdma0 9>,
+                <&pdma0 8>;
+        dma-names = "tx", "rx", "tx-sec";
+        clocks = <&clock_audss EXYNOS_I2S_BUS>,
+                <&clock_audss EXYNOS_I2S_BUS>,
+                <&clock_audss EXYNOS_SCLK_I2S>;
+        clock-names = "iis", "i2s_opclk0", "i2s_opclk1";
+        #clock-cells = <1>;
+        samsung,idma-addr = <0x03000000>;
+        pinctrl-names = "default";
+        pinctrl-0 = <&i2s0_bus>;
+        #sound-dai-cells = <1>;
+    };
diff --git a/Documentation/devicetree/bindings/sound/sun4i-codec.txt b/Documentation/devicetree/bindings/sound/sun4i-codec.txt
deleted file mode 100644
index 66579bbd3294..000000000000
--- a/Documentation/devicetree/bindings/sound/sun4i-codec.txt
+++ /dev/null
@@ -1,94 +0,0 @@
-* Allwinner A10 Codec
-
-Required properties:
-- compatible: must be one of the following compatibles:
-		- "allwinner,sun4i-a10-codec"
-		- "allwinner,sun6i-a31-codec"
-		- "allwinner,sun7i-a20-codec"
-		- "allwinner,sun8i-a23-codec"
-		- "allwinner,sun8i-h3-codec"
-		- "allwinner,sun8i-v3s-codec"
-- reg: must contain the registers location and length
-- interrupts: must contain the codec interrupt
-- dmas: DMA channels for tx and rx dma. See the DMA client binding,
-	Documentation/devicetree/bindings/dma/dma.txt
-- dma-names: should include "tx" and "rx".
-- clocks: a list of phandle + clock-specifer pairs, one for each entry
-  in clock-names.
-- clock-names: should contain the following:
-   - "apb": the parent APB clock for this controller
-   - "codec": the parent module clock
-
-Optional properties:
-- allwinner,pa-gpios: gpio to enable external amplifier
-
-Required properties for the following compatibles:
-		- "allwinner,sun6i-a31-codec"
-		- "allwinner,sun8i-a23-codec"
-		- "allwinner,sun8i-h3-codec"
-		- "allwinner,sun8i-v3s-codec"
-- resets: phandle to the reset control for this device
-- allwinner,audio-routing: A list of the connections between audio components.
-			   Each entry is a pair of strings, the first being the
-			   connection's sink, the second being the connection's
-			   source. Valid names include:
-
-			   Audio pins on the SoC:
-			   "HP"
-			   "HPCOM"
-			   "LINEIN"	(not on sun8i-v3s)
-			   "LINEOUT"	(not on sun8i-a23 or sun8i-v3s)
-			   "MIC1"
-			   "MIC2"	(not on sun8i-v3s)
-			   "MIC3"	(sun6i-a31 only)
-
-			   Microphone biases from the SoC:
-			   "HBIAS"
-			   "MBIAS"	(not on sun8i-v3s)
-
-			   Board connectors:
-			   "Headphone"
-			   "Headset Mic"
-			   "Line In"
-			   "Line Out"
-			   "Mic"
-			   "Speaker"
-
-Required properties for the following compatibles:
-		- "allwinner,sun8i-a23-codec"
-		- "allwinner,sun8i-h3-codec"
-		- "allwinner,sun8i-v3s-codec"
-- allwinner,codec-analog-controls: A phandle to the codec analog controls
-				   block in the PRCM.
-
-Example:
-codec: codec@1c22c00 {
-	#sound-dai-cells = <0>;
-	compatible = "allwinner,sun7i-a20-codec";
-	reg = <0x01c22c00 0x40>;
-	interrupts = <0 30 4>;
-	clocks = <&apb0_gates 0>, <&codec_clk>;
-	clock-names = "apb", "codec";
-	dmas = <&dma 0 19>, <&dma 0 19>;
-	dma-names = "rx", "tx";
-};
-
-codec: codec@1c22c00 {
-	#sound-dai-cells = <0>;
-	compatible = "allwinner,sun6i-a31-codec";
-	reg = <0x01c22c00 0x98>;
-	interrupts = <GIC_SPI 29 IRQ_TYPE_LEVEL_HIGH>;
-	clocks = <&ccu CLK_APB1_CODEC>, <&ccu CLK_CODEC>;
-	clock-names = "apb", "codec";
-	resets = <&ccu RST_APB1_CODEC>;
-	dmas = <&dma 15>, <&dma 15>;
-	dma-names = "rx", "tx";
-	allwinner,audio-routing =
-		"Headphone", "HP",
-		"Speaker", "LINEOUT",
-		"LINEIN", "Line In",
-		"MIC1",	"MBIAS",
-		"MIC1", "Mic",
-		"MIC2", "HBIAS",
-		"MIC2", "Headset Mic";
-};
diff --git a/Documentation/devicetree/bindings/sound/sun8i-codec-analog.txt b/Documentation/devicetree/bindings/sound/sun8i-codec-analog.txt
deleted file mode 100644
index 07356758bd91..000000000000
--- a/Documentation/devicetree/bindings/sound/sun8i-codec-analog.txt
+++ /dev/null
@@ -1,17 +0,0 @@
-* Allwinner Codec Analog Controls
-
-Required properties:
-- compatible: must be one of the following compatibles:
-		- "allwinner,sun8i-a23-codec-analog"
-		- "allwinner,sun8i-h3-codec-analog"
-		- "allwinner,sun8i-v3s-codec-analog"
-
-Required properties if not a sub-node of the PRCM node:
-- reg: must contain the registers location and length
-
-Example:
-prcm: prcm@1f01400 {
-	codec_analog: codec-analog {
-		compatible = "allwinner,sun8i-a23-codec-analog";
-	};
-};
diff --git a/Documentation/devicetree/bindings/sound/tas2562.txt b/Documentation/devicetree/bindings/sound/tas2562.txt
new file mode 100644
index 000000000000..658e1fb18a99
--- /dev/null
+++ b/Documentation/devicetree/bindings/sound/tas2562.txt
@@ -0,0 +1,34 @@
+Texas Instruments TAS2562 Smart PA
+
+The TAS2562 is a mono, digital input Class-D audio amplifier optimized for
+efficiently driving high peak power into small loudspeakers.
+Integrated speaker voltage and current sense provides for
+real time monitoring of loudspeaker behavior.
+
+Required properties:
+ - #address-cells  - Should be <1>.
+ - #size-cells     - Should be <0>.
+ - compatible:	   - Should contain "ti,tas2562".
+ - reg:		   - The i2c address. Should be 0x4c, 0x4d, 0x4e or 0x4f.
+ - ti,imon-slot-no:- TDM TX current sense time slot.
+
+Optional properties:
+- interrupt-parent: phandle to the interrupt controller which provides
+                    the interrupt.
+- interrupts: (GPIO) interrupt to which the chip is connected.
+- shut-down: GPIO used to control the state of the device.
+
+Examples:
+tas2562@4c {
+        #address-cells = <1>;
+        #size-cells = <0>;
+        compatible = "ti,tas2562";
+        reg = <0x4c>;
+
+        interrupt-parent = <&gpio1>;
+        interrupts = <14>;
+
+	shut-down = <&gpio1 15 0>;
+        ti,imon-slot-no = <0>;
+};
+
diff --git a/Documentation/devicetree/bindings/sound/tas2770.txt b/Documentation/devicetree/bindings/sound/tas2770.txt
new file mode 100644
index 000000000000..ede6bb3d9637
--- /dev/null
+++ b/Documentation/devicetree/bindings/sound/tas2770.txt
@@ -0,0 +1,37 @@
+Texas Instruments TAS2770 Smart PA
+
+The TAS2770 is a mono, digital input Class-D audio amplifier optimized for
+efficiently driving high peak power into small loudspeakers.
+Integrated speaker voltage and current sense provides for
+real time monitoring of loudspeaker behavior.
+
+Required properties:
+
+ - compatible:	   - Should contain "ti,tas2770".
+ - reg:		       - The i2c address. Should contain <0x4c>, <0x4d>,<0x4e>, or <0x4f>.
+ - #address-cells  - Should be <1>.
+ - #size-cells     - Should be <0>.
+ - ti,asi-format:  - Sets TDM RX capture edge. 0->Rising; 1->Falling.
+ - ti,imon-slot-no:- TDM TX current sense time slot.
+ - ti,vmon-slot-no:- TDM TX voltage sense time slot.
+
+Optional properties:
+
+- interrupt-parent: the phandle to the interrupt controller which provides
+                     the interrupt.
+- interrupts: interrupt specification for data-ready.
+
+Examples:
+
+    tas2770@4c {
+                compatible = "ti,tas2770";
+                reg = <0x4c>;
+                #address-cells = <1>;
+                #size-cells = <0>;
+                interrupt-parent = <&msm_gpio>;
+                interrupts = <97 0>;
+                ti,asi-format = <0>;
+                ti,imon-slot-no = <0>;
+                ti,vmon-slot-no = <2>;
+        };
+
diff --git a/Documentation/devicetree/bindings/sound/ti,pcm3168a.txt b/Documentation/devicetree/bindings/sound/ti,pcm3168a.txt
index 5d9cb84c661d..a02ecaab5183 100644
--- a/Documentation/devicetree/bindings/sound/ti,pcm3168a.txt
+++ b/Documentation/devicetree/bindings/sound/ti,pcm3168a.txt
@@ -25,6 +25,13 @@ Required properties:
 
 For required properties on SPI/I2C, consult SPI/I2C device tree documentation
 
+Optional properties:
+
+  - reset-gpios : Optional reset gpio line connected to RST pin of the codec.
+		  The RST line is low active:
+		  RST = low: device power-down
+		  RST = high: device is enabled
+
 Examples:
 
 i2c0: i2c0@0 {
@@ -34,6 +41,7 @@ i2c0: i2c0@0 {
 	pcm3168a: audio-codec@44 {
 		compatible = "ti,pcm3168a";
 		reg = <0x44>;
+		reset-gpios = <&gpio0 4 GPIO_ACTIVE_LOW>;
 		clocks = <&clk_core CLK_AUDIO>;
 		clock-names = "scki";
 		VDD1-supply = <&supply3v3>;
diff --git a/Documentation/devicetree/bindings/sound/tlv320aic31xx.txt b/Documentation/devicetree/bindings/sound/tlv320aic31xx.txt
index 5b3c33bb99e5..e372303697dc 100644
--- a/Documentation/devicetree/bindings/sound/tlv320aic31xx.txt
+++ b/Documentation/devicetree/bindings/sound/tlv320aic31xx.txt
@@ -29,6 +29,11 @@ Optional properties:
         3 or MICBIAS_AVDD - MICBIAS output is connected to AVDD
 	If this node is not mentioned or if the value is unknown, then
 	micbias	is set to 2.0V.
+- ai31xx-ocmv - output common-mode voltage setting
+        0 - 1.35V,
+        1 - 1.5V,
+        2 - 1.65V,
+        3 - 1.8V
 
 Deprecated properties:
 
diff --git a/Documentation/devicetree/bindings/vendor-prefixes.yaml b/Documentation/devicetree/bindings/vendor-prefixes.yaml
index 05b3904a995b..fd6fa07c45b8 100644
--- a/Documentation/devicetree/bindings/vendor-prefixes.yaml
+++ b/Documentation/devicetree/bindings/vendor-prefixes.yaml
@@ -16,7 +16,7 @@ properties: {}
 patternProperties:
   # Prefixes which are not vendors, but followed the pattern
   # DO NOT ADD NEW PROPERTIES TO THIS LIST
-  "^(at25|devbus|dmacap|dsa|exynos|gpio-fan|gpio|gpmc|hdmi|i2c-gpio),.*": true
+  "^(at25|devbus|dmacap|dsa|exynos|fsi[ab]|gpio-fan|gpio|gpmc|hdmi|i2c-gpio),.*": true
   "^(keypad|m25p|max8952|max8997|max8998|mpmc),.*": true
   "^(pinctrl-single|#pinctrl-single|PowerPC),.*": true
   "^(pl022|pxa-mmc|rcar_sound|rotary-encoder|s5m8767|sdhci),.*": true
diff --git a/Documentation/firmware-guide/acpi/namespace.rst b/Documentation/firmware-guide/acpi/namespace.rst
index 835521baeb89..3eb763d6656d 100644
--- a/Documentation/firmware-guide/acpi/namespace.rst
+++ b/Documentation/firmware-guide/acpi/namespace.rst
@@ -261,7 +261,7 @@ Description Tables contain information used for the creation of the
 struct acpi_device objects represented by the given row (xSDT means DSDT
 or SSDT).
 
-The forth column of the above table indicates the 'bus_id' generation
+The fourth column of the above table indicates the 'bus_id' generation
 rule of the struct acpi_device object:
 
    _HID:
diff --git a/Documentation/index.rst b/Documentation/index.rst
index b843e313d2f2..2ceab197246f 100644
--- a/Documentation/index.rst
+++ b/Documentation/index.rst
@@ -135,6 +135,14 @@ needed).
    mic/index
    scheduler/index
 
+Architecture-agnostic documentation
+-----------------------------------
+
+.. toctree::
+   :maxdepth: 2
+
+   asm-annotations
+
 Architecture-specific documentation
 -----------------------------------
 
diff --git a/Documentation/media/cec.h.rst.exceptions b/Documentation/media/cec.h.rst.exceptions
index 014816d04b9e..d83790ccac8e 100644
--- a/Documentation/media/cec.h.rst.exceptions
+++ b/Documentation/media/cec.h.rst.exceptions
@@ -335,6 +335,95 @@ ignore define CEC_OP_MENU_STATE_DEACTIVATED
 
 ignore define CEC_MSG_USER_CONTROL_PRESSED
 
+ignore define CEC_OP_UI_CMD_SELECT
+ignore define CEC_OP_UI_CMD_UP
+ignore define CEC_OP_UI_CMD_DOWN
+ignore define CEC_OP_UI_CMD_LEFT
+ignore define CEC_OP_UI_CMD_RIGHT
+ignore define CEC_OP_UI_CMD_RIGHT_UP
+ignore define CEC_OP_UI_CMD_RIGHT_DOWN
+ignore define CEC_OP_UI_CMD_LEFT_UP
+ignore define CEC_OP_UI_CMD_LEFT_DOWN
+ignore define CEC_OP_UI_CMD_DEVICE_ROOT_MENU
+ignore define CEC_OP_UI_CMD_DEVICE_SETUP_MENU
+ignore define CEC_OP_UI_CMD_CONTENTS_MENU
+ignore define CEC_OP_UI_CMD_FAVORITE_MENU
+ignore define CEC_OP_UI_CMD_BACK
+ignore define CEC_OP_UI_CMD_MEDIA_TOP_MENU
+ignore define CEC_OP_UI_CMD_MEDIA_CONTEXT_SENSITIVE_MENU
+ignore define CEC_OP_UI_CMD_NUMBER_ENTRY_MODE
+ignore define CEC_OP_UI_CMD_NUMBER_11
+ignore define CEC_OP_UI_CMD_NUMBER_12
+ignore define CEC_OP_UI_CMD_NUMBER_0_OR_NUMBER_10
+ignore define CEC_OP_UI_CMD_NUMBER_1
+ignore define CEC_OP_UI_CMD_NUMBER_2
+ignore define CEC_OP_UI_CMD_NUMBER_3
+ignore define CEC_OP_UI_CMD_NUMBER_4
+ignore define CEC_OP_UI_CMD_NUMBER_5
+ignore define CEC_OP_UI_CMD_NUMBER_6
+ignore define CEC_OP_UI_CMD_NUMBER_7
+ignore define CEC_OP_UI_CMD_NUMBER_8
+ignore define CEC_OP_UI_CMD_NUMBER_9
+ignore define CEC_OP_UI_CMD_DOT
+ignore define CEC_OP_UI_CMD_ENTER
+ignore define CEC_OP_UI_CMD_CLEAR
+ignore define CEC_OP_UI_CMD_NEXT_FAVORITE
+ignore define CEC_OP_UI_CMD_CHANNEL_UP
+ignore define CEC_OP_UI_CMD_CHANNEL_DOWN
+ignore define CEC_OP_UI_CMD_PREVIOUS_CHANNEL
+ignore define CEC_OP_UI_CMD_SOUND_SELECT
+ignore define CEC_OP_UI_CMD_INPUT_SELECT
+ignore define CEC_OP_UI_CMD_DISPLAY_INFORMATION
+ignore define CEC_OP_UI_CMD_HELP
+ignore define CEC_OP_UI_CMD_PAGE_UP
+ignore define CEC_OP_UI_CMD_PAGE_DOWN
+ignore define CEC_OP_UI_CMD_POWER
+ignore define CEC_OP_UI_CMD_VOLUME_UP
+ignore define CEC_OP_UI_CMD_VOLUME_DOWN
+ignore define CEC_OP_UI_CMD_MUTE
+ignore define CEC_OP_UI_CMD_PLAY
+ignore define CEC_OP_UI_CMD_STOP
+ignore define CEC_OP_UI_CMD_PAUSE
+ignore define CEC_OP_UI_CMD_RECORD
+ignore define CEC_OP_UI_CMD_REWIND
+ignore define CEC_OP_UI_CMD_FAST_FORWARD
+ignore define CEC_OP_UI_CMD_EJECT
+ignore define CEC_OP_UI_CMD_SKIP_FORWARD
+ignore define CEC_OP_UI_CMD_SKIP_BACKWARD
+ignore define CEC_OP_UI_CMD_STOP_RECORD
+ignore define CEC_OP_UI_CMD_PAUSE_RECORD
+ignore define CEC_OP_UI_CMD_ANGLE
+ignore define CEC_OP_UI_CMD_SUB_PICTURE
+ignore define CEC_OP_UI_CMD_VIDEO_ON_DEMAND
+ignore define CEC_OP_UI_CMD_ELECTRONIC_PROGRAM_GUIDE
+ignore define CEC_OP_UI_CMD_TIMER_PROGRAMMING
+ignore define CEC_OP_UI_CMD_INITIAL_CONFIGURATION
+ignore define CEC_OP_UI_CMD_SELECT_BROADCAST_TYPE
+ignore define CEC_OP_UI_CMD_SELECT_SOUND_PRESENTATION
+ignore define CEC_OP_UI_CMD_AUDIO_DESCRIPTION
+ignore define CEC_OP_UI_CMD_INTERNET
+ignore define CEC_OP_UI_CMD_3D_MODE
+ignore define CEC_OP_UI_CMD_PLAY_FUNCTION
+ignore define CEC_OP_UI_CMD_PAUSE_PLAY_FUNCTION
+ignore define CEC_OP_UI_CMD_RECORD_FUNCTION
+ignore define CEC_OP_UI_CMD_PAUSE_RECORD_FUNCTION
+ignore define CEC_OP_UI_CMD_STOP_FUNCTION
+ignore define CEC_OP_UI_CMD_MUTE_FUNCTION
+ignore define CEC_OP_UI_CMD_RESTORE_VOLUME_FUNCTION
+ignore define CEC_OP_UI_CMD_TUNE_FUNCTION
+ignore define CEC_OP_UI_CMD_SELECT_MEDIA_FUNCTION
+ignore define CEC_OP_UI_CMD_SELECT_AV_INPUT_FUNCTION
+ignore define CEC_OP_UI_CMD_SELECT_AUDIO_INPUT_FUNCTION
+ignore define CEC_OP_UI_CMD_POWER_TOGGLE_FUNCTION
+ignore define CEC_OP_UI_CMD_POWER_OFF_FUNCTION
+ignore define CEC_OP_UI_CMD_POWER_ON_FUNCTION
+ignore define CEC_OP_UI_CMD_F1_BLUE
+ignore define CEC_OP_UI_CMD_F2_RED
+ignore define CEC_OP_UI_CMD_F3_GREEN
+ignore define CEC_OP_UI_CMD_F4_YELLOW
+ignore define CEC_OP_UI_CMD_F5
+ignore define CEC_OP_UI_CMD_DATA
+
 ignore define CEC_OP_UI_BCAST_TYPE_TOGGLE_ALL
 ignore define CEC_OP_UI_BCAST_TYPE_TOGGLE_DIG_ANA
 ignore define CEC_OP_UI_BCAST_TYPE_ANALOGUE
diff --git a/Documentation/media/kapi/v4l2-controls.rst b/Documentation/media/kapi/v4l2-controls.rst
index ebe2a55908be..b20800cae3f2 100644
--- a/Documentation/media/kapi/v4l2-controls.rst
+++ b/Documentation/media/kapi/v4l2-controls.rst
@@ -140,6 +140,15 @@ Menu controls with a driver specific menu are added by calling
                        const struct v4l2_ctrl_ops *ops, u32 id, s32 max,
                        s32 skip_mask, s32 def, const char * const *qmenu);
 
+Standard compound controls can be added by calling
+:c:func:`v4l2_ctrl_new_std_compound`:
+
+.. code-block:: c
+
+       struct v4l2_ctrl *v4l2_ctrl_new_std_compound(struct v4l2_ctrl_handler *hdl,
+                       const struct v4l2_ctrl_ops *ops, u32 id,
+                       const union v4l2_ctrl_ptr p_def);
+
 Integer menu controls with a driver specific menu can be added by calling
 :c:func:`v4l2_ctrl_new_int_menu`:
 
diff --git a/Documentation/media/uapi/cec/cec-funcs.rst b/Documentation/media/uapi/cec/cec-funcs.rst
index 620590b168c9..dc6da9c639a8 100644
--- a/Documentation/media/uapi/cec/cec-funcs.rst
+++ b/Documentation/media/uapi/cec/cec-funcs.rst
@@ -24,6 +24,7 @@ Function Reference
     cec-ioc-adap-g-caps
     cec-ioc-adap-g-log-addrs
     cec-ioc-adap-g-phys-addr
+    cec-ioc-adap-g-conn-info
     cec-ioc-dqevent
     cec-ioc-g-mode
     cec-ioc-receive
diff --git a/Documentation/media/uapi/cec/cec-ioc-adap-g-caps.rst b/Documentation/media/uapi/cec/cec-ioc-adap-g-caps.rst
index 0c44f31a9b59..76761a98c312 100644
--- a/Documentation/media/uapi/cec/cec-ioc-adap-g-caps.rst
+++ b/Documentation/media/uapi/cec/cec-ioc-adap-g-caps.rst
@@ -135,8 +135,12 @@ returns the information to the application. The ioctl never fails.
       - The CEC hardware can monitor CEC pin changes from low to high voltage
         and vice versa. When in pin monitoring mode the application will
 	receive ``CEC_EVENT_PIN_CEC_LOW`` and ``CEC_EVENT_PIN_CEC_HIGH`` events.
+    * .. _`CEC-CAP-CONNECTOR-INFO`:
 
-
+      - ``CEC_CAP_CONNECTOR_INFO``
+      - 0x00000100
+      - If this capability is set, then :ref:`CEC_ADAP_G_CONNECTOR_INFO` can
+        be used.
 
 Return Value
 ============
diff --git a/Documentation/media/uapi/cec/cec-ioc-adap-g-conn-info.rst b/Documentation/media/uapi/cec/cec-ioc-adap-g-conn-info.rst
new file mode 100644
index 000000000000..a21659d55c6b
--- /dev/null
+++ b/Documentation/media/uapi/cec/cec-ioc-adap-g-conn-info.rst
@@ -0,0 +1,105 @@
+.. SPDX-License-Identifier: GPL-2.0
+..
+.. Copyright 2019 Google LLC
+..
+.. _CEC_ADAP_G_CONNECTOR_INFO:
+
+*******************************
+ioctl CEC_ADAP_G_CONNECTOR_INFO
+*******************************
+
+Name
+====
+
+CEC_ADAP_G_CONNECTOR_INFO - Query HDMI connector information
+
+Synopsis
+========
+
+.. c:function:: int ioctl( int fd, CEC_ADAP_G_CONNECTOR_INFO, struct cec_connector_info *argp )
+    :name: CEC_ADAP_G_CONNECTOR_INFO
+
+Arguments
+=========
+
+``fd``
+    File descriptor returned by :c:func:`open() <cec-open>`.
+
+``argp``
+
+
+Description
+===========
+
+Using this ioctl an application can learn which HDMI connector this CEC
+device corresponds to. While calling this ioctl the application should
+provide a pointer to a cec_connector_info struct which will be populated
+by the kernel with the info provided by the adapter's driver. This ioctl
+is only available if the ``CEC_CAP_CONNECTOR_INFO`` capability is set.
+
+.. tabularcolumns:: |p{1.0cm}|p{4.4cm}|p{2.5cm}|p{9.6cm}|
+
+.. c:type:: cec_connector_info
+
+.. flat-table:: struct cec_connector_info
+    :header-rows:  0
+    :stub-columns: 0
+    :widths:       1 1 1 8
+
+    * - __u32
+      - ``type``
+      - The type of connector this adapter is associated with.
+    * - union
+      - ``(anonymous)``
+      -
+    * -
+      - ``struct cec_drm_connector_info``
+      - drm
+      - :ref:`cec-drm-connector-info`
+
+
+.. tabularcolumns:: |p{4.4cm}|p{2.5cm}|p{10.6cm}|
+
+.. _connector-type:
+
+.. flat-table:: Connector types
+    :header-rows:  0
+    :stub-columns: 0
+    :widths:       3 1 8
+
+    * .. _`CEC-CONNECTOR-TYPE-NO-CONNECTOR`:
+
+      - ``CEC_CONNECTOR_TYPE_NO_CONNECTOR``
+      - 0
+      - No connector is associated with the adapter/the information is not
+        provided by the driver.
+    * .. _`CEC-CONNECTOR-TYPE-DRM`:
+
+      - ``CEC_CONNECTOR_TYPE_DRM``
+      - 1
+      - Indicates that a DRM connector is associated with this adapter.
+        Information about the connector can be found in
+	:ref:`cec-drm-connector-info`.
+
+.. tabularcolumns:: |p{4.4cm}|p{2.5cm}|p{10.6cm}|
+
+.. c:type:: cec_drm_connector_info
+
+.. _cec-drm-connector-info:
+
+.. flat-table:: struct cec_drm_connector_info
+    :header-rows:  0
+    :stub-columns: 0
+    :widths:       3 1 8
+
+    * .. _`CEC-DRM-CONNECTOR-TYPE-CARD-NO`:
+
+      - __u32
+      - ``card_no``
+      - DRM card number: the number from a card's path, e.g. 0 in case of
+        /dev/card0.
+    * .. _`CEC-DRM-CONNECTOR-TYPE-CONNECTOR_ID`:
+
+      - __u32
+      - ``connector_id``
+      - DRM connector ID.
diff --git a/Documentation/media/uapi/cec/cec-ioc-dqevent.rst b/Documentation/media/uapi/cec/cec-ioc-dqevent.rst
index 46a1c99a595e..5e21b1fbfc01 100644
--- a/Documentation/media/uapi/cec/cec-ioc-dqevent.rst
+++ b/Documentation/media/uapi/cec/cec-ioc-dqevent.rst
@@ -70,6 +70,14 @@ it is guaranteed that the state did change in between the two events.
         addresses are claimed or if ``phys_addr`` is ``CEC_PHYS_ADDR_INVALID``.
 	If bit 15 is set (``1 << CEC_LOG_ADDR_UNREGISTERED``) then this device
 	has the unregistered logical address. In that case all other bits are 0.
+    * - __u16
+      - ``have_conn_info``
+      - If non-zero, then HDMI connector information is available.
+        This field is only valid if ``CEC_CAP_CONNECTOR_INFO`` is set. If that
+        capability is set and ``have_conn_info`` is zero, then that indicates
+        that the HDMI connector device is not instantiated, either because
+        the HDMI driver is still configuring the device or because the HDMI
+        device was unbound.
 
 
 .. c:type:: cec_event_lost_msgs
diff --git a/Documentation/media/uapi/mediactl/request-api.rst b/Documentation/media/uapi/mediactl/request-api.rst
index a74c82d95609..01abe8103bdd 100644
--- a/Documentation/media/uapi/mediactl/request-api.rst
+++ b/Documentation/media/uapi/mediactl/request-api.rst
@@ -53,8 +53,8 @@ with different configurations in advance, knowing that the configuration will be
 applied when needed to get the expected result. Configuration values at the time
 of request completion are also available for reading.
 
-Usage
-=====
+General Usage
+-------------
 
 The Request API extends the Media Controller API and cooperates with
 subsystem-specific APIs to support request usage. At the Media Controller
diff --git a/Documentation/media/uapi/v4l/biblio.rst b/Documentation/media/uapi/v4l/biblio.rst
index ad2ff258afa8..8095f57d3d75 100644
--- a/Documentation/media/uapi/v4l/biblio.rst
+++ b/Documentation/media/uapi/v4l/biblio.rst
@@ -131,6 +131,15 @@ ITU-T Rec. H.264 Specification (04/2017 Edition)
 
 :author:    International Telecommunication Union (http://www.itu.ch)
 
+.. _hevc:
+
+ITU H.265/HEVC
+==============
+
+:title:     ITU-T Rec. H.265 | ISO/IEC 23008-2 "High Efficiency Video Coding"
+
+:author:    International Telecommunication Union (http://www.itu.ch), International Organisation for Standardisation (http://www.iso.ch)
+
 .. _jfif:
 
 JFIF
diff --git a/Documentation/media/uapi/v4l/buffer.rst b/Documentation/media/uapi/v4l/buffer.rst
index 1cbd9cde57f3..9149b57728e5 100644
--- a/Documentation/media/uapi/v4l/buffer.rst
+++ b/Documentation/media/uapi/v4l/buffer.rst
@@ -607,6 +607,19 @@ Buffer Flags
 	applications shall use this flag for output buffers if the data in
 	this buffer has not been created by the CPU but by some
 	DMA-capable unit, in which case caches have not been used.
+    * .. _`V4L2-BUF-FLAG-M2M-HOLD-CAPTURE-BUF`:
+
+      - ``V4L2_BUF_FLAG_M2M_HOLD_CAPTURE_BUF``
+      - 0x00000200
+      - Only valid if ``V4L2_BUF_CAP_SUPPORTS_M2M_HOLD_CAPTURE_BUF`` is
+	set. It is typically used with stateless decoders where multiple
+	output buffers each decode to a slice of the decoded frame.
+	Applications can set this flag when queueing the output buffer
+	to prevent the driver from dequeueing the capture buffer after
+	the output buffer has been decoded (i.e. the capture buffer is
+	'held'). If the timestamp of this output buffer differs from that
+	of the previous output buffer, then that indicates the start of a
+	new frame and the previously held capture buffer is dequeued.
     * .. _`V4L2-BUF-FLAG-LAST`:
 
       - ``V4L2_BUF_FLAG_LAST``
diff --git a/Documentation/media/uapi/v4l/dev-mem2mem.rst b/Documentation/media/uapi/v4l/dev-mem2mem.rst
index caa05f5f6380..70953958cee6 100644
--- a/Documentation/media/uapi/v4l/dev-mem2mem.rst
+++ b/Documentation/media/uapi/v4l/dev-mem2mem.rst
@@ -46,3 +46,4 @@ devices are given in the following sections.
     :maxdepth: 1
 
     dev-decoder
+    dev-stateless-decoder
diff --git a/Documentation/media/uapi/v4l/dev-stateless-decoder.rst b/Documentation/media/uapi/v4l/dev-stateless-decoder.rst
new file mode 100644
index 000000000000..4a26646eeec5
--- /dev/null
+++ b/Documentation/media/uapi/v4l/dev-stateless-decoder.rst
@@ -0,0 +1,424 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+.. _stateless_decoder:
+
+**************************************************
+Memory-to-memory Stateless Video Decoder Interface
+**************************************************
+
+A stateless decoder is a decoder that works without retaining any kind of state
+between processed frames. This means that each frame is decoded independently
+of any previous and future frames, and that the client is responsible for
+maintaining the decoding state and providing it to the decoder with each
+decoding request. This is in contrast to the stateful video decoder interface,
+where the hardware and driver maintain the decoding state and all the client
+has to do is to provide the raw encoded stream and dequeue decoded frames in
+display order.
+
+This section describes how user-space ("the client") is expected to communicate
+with stateless decoders in order to successfully decode an encoded stream.
+Compared to stateful codecs, the decoder/client sequence is simpler, but the
+cost of this simplicity is extra complexity in the client which is responsible
+for maintaining a consistent decoding state.
+
+Stateless decoders make use of the :ref:`media-request-api`. A stateless
+decoder must expose the ``V4L2_BUF_CAP_SUPPORTS_REQUESTS`` capability on its
+``OUTPUT`` queue when :c:func:`VIDIOC_REQBUFS` or :c:func:`VIDIOC_CREATE_BUFS`
+are invoked.
+
+Depending on the encoded formats supported by the decoder, a single decoded
+frame may be the result of several decode requests (for instance, H.264 streams
+with multiple slices per frame). Decoders that support such formats must also
+expose the ``V4L2_BUF_CAP_SUPPORTS_M2M_HOLD_CAPTURE_BUF`` capability on their
+``OUTPUT`` queue.
+
+Querying capabilities
+=====================
+
+1. To enumerate the set of coded formats supported by the decoder, the client
+   calls :c:func:`VIDIOC_ENUM_FMT` on the ``OUTPUT`` queue.
+
+   * The driver must always return the full set of supported ``OUTPUT`` formats,
+     irrespective of the format currently set on the ``CAPTURE`` queue.
+
+   * Simultaneously, the driver must restrain the set of values returned by
+     codec-specific capability controls (such as H.264 profiles) to the set
+     actually supported by the hardware.
+
+2. To enumerate the set of supported raw formats, the client calls
+   :c:func:`VIDIOC_ENUM_FMT` on the ``CAPTURE`` queue.
+
+   * The driver must return only the formats supported for the format currently
+     active on the ``OUTPUT`` queue.
+
+   * Depending on the currently set ``OUTPUT`` format, the set of supported raw
+     formats may depend on the value of some codec-dependent controls.
+     The client is responsible for making sure that these controls are set
+     before querying the ``CAPTURE`` queue. Failure to do so will result in the
+     default values for these controls being used, and a returned set of formats
+     that may not be usable for the media the client is trying to decode.
+
+3. The client may use :c:func:`VIDIOC_ENUM_FRAMESIZES` to detect supported
+   resolutions for a given format, passing desired pixel format in
+   :c:type:`v4l2_frmsizeenum`'s ``pixel_format``.
+
+4. Supported profiles and levels for the current ``OUTPUT`` format, if
+   applicable, may be queried using their respective controls via
+   :c:func:`VIDIOC_QUERYCTRL`.
+
+Initialization
+==============
+
+1. Set the coded format on the ``OUTPUT`` queue via :c:func:`VIDIOC_S_FMT`.
+
+   * **Required fields:**
+
+     ``type``
+         a ``V4L2_BUF_TYPE_*`` enum appropriate for ``OUTPUT``.
+
+     ``pixelformat``
+         a coded pixel format.
+
+     ``width``, ``height``
+         coded width and height parsed from the stream.
+
+     other fields
+         follow standard semantics.
+
+   .. note::
+
+      Changing the ``OUTPUT`` format may change the currently set ``CAPTURE``
+      format. The driver will derive a new ``CAPTURE`` format from the
+      ``OUTPUT`` format being set, including resolution, colorimetry
+      parameters, etc. If the client needs a specific ``CAPTURE`` format,
+      it must adjust it afterwards.
+
+2. Call :c:func:`VIDIOC_S_EXT_CTRLS` to set all the controls (parsed headers,
+   etc.) required by the ``OUTPUT`` format to enumerate the ``CAPTURE`` formats.
+
+3. Call :c:func:`VIDIOC_G_FMT` for ``CAPTURE`` queue to get the format for the
+   destination buffers parsed/decoded from the bytestream.
+
+   * **Required fields:**
+
+     ``type``
+         a ``V4L2_BUF_TYPE_*`` enum appropriate for ``CAPTURE``.
+
+   * **Returned fields:**
+
+     ``width``, ``height``
+         frame buffer resolution for the decoded frames.
+
+     ``pixelformat``
+         pixel format for decoded frames.
+
+     ``num_planes`` (for _MPLANE ``type`` only)
+         number of planes for pixelformat.
+
+     ``sizeimage``, ``bytesperline``
+         as per standard semantics; matching frame buffer format.
+
+   .. note::
+
+      The value of ``pixelformat`` may be any pixel format supported for the
+      ``OUTPUT`` format, based on the hardware capabilities. It is suggested
+      that the driver chooses the preferred/optimal format for the current
+      configuration. For example, a YUV format may be preferred over an RGB
+      format, if an additional conversion step would be required for RGB.
+
+4. *[optional]* Enumerate ``CAPTURE`` formats via :c:func:`VIDIOC_ENUM_FMT` on
+   the ``CAPTURE`` queue. The client may use this ioctl to discover which
+   alternative raw formats are supported for the current ``OUTPUT`` format and
+   select one of them via :c:func:`VIDIOC_S_FMT`.
+
+   .. note::
+
+      The driver will return only formats supported for the currently selected
+      ``OUTPUT`` format and currently set controls, even if more formats may be
+      supported by the decoder in general.
+
+      For example, a decoder may support YUV and RGB formats for
+      resolutions 1920x1088 and lower, but only YUV for higher resolutions (due
+      to hardware limitations). After setting a resolution of 1920x1088 or lower
+      as the ``OUTPUT`` format, :c:func:`VIDIOC_ENUM_FMT` may return a set of
+      YUV and RGB pixel formats, but after setting a resolution higher than
+      1920x1088, the driver will not return RGB pixel formats, since they are
+      unsupported for this resolution.
+
+5. *[optional]* Choose a different ``CAPTURE`` format than suggested via
+   :c:func:`VIDIOC_S_FMT` on ``CAPTURE`` queue. It is possible for the client to
+   choose a different format than selected/suggested by the driver in
+   :c:func:`VIDIOC_G_FMT`.
+
+    * **Required fields:**
+
+      ``type``
+          a ``V4L2_BUF_TYPE_*`` enum appropriate for ``CAPTURE``.
+
+      ``pixelformat``
+          a raw pixel format.
+
+      ``width``, ``height``
+         frame buffer resolution of the decoded stream; typically unchanged from
+         what was returned with :c:func:`VIDIOC_G_FMT`, but it may be different
+         if the hardware supports composition and/or scaling.
+
+   After performing this step, the client must perform step 3 again in order
+   to obtain up-to-date information about the buffers size and layout.
+
+6. Allocate source (bytestream) buffers via :c:func:`VIDIOC_REQBUFS` on
+   ``OUTPUT`` queue.
+
+    * **Required fields:**
+
+      ``count``
+          requested number of buffers to allocate; greater than zero.
+
+      ``type``
+          a ``V4L2_BUF_TYPE_*`` enum appropriate for ``OUTPUT``.
+
+      ``memory``
+          follows standard semantics.
+
+    * **Return fields:**
+
+      ``count``
+          actual number of buffers allocated.
+
+    * If required, the driver will adjust ``count`` to be equal or bigger to the
+      minimum of required number of ``OUTPUT`` buffers for the given format and
+      requested count. The client must check this value after the ioctl returns
+      to get the actual number of buffers allocated.
+
+7. Allocate destination (raw format) buffers via :c:func:`VIDIOC_REQBUFS` on the
+   ``CAPTURE`` queue.
+
+    * **Required fields:**
+
+      ``count``
+          requested number of buffers to allocate; greater than zero. The client
+          is responsible for deducing the minimum number of buffers required
+          for the stream to be properly decoded (taking e.g. reference frames
+          into account) and pass an equal or bigger number.
+
+      ``type``
+          a ``V4L2_BUF_TYPE_*`` enum appropriate for ``CAPTURE``.
+
+      ``memory``
+          follows standard semantics. ``V4L2_MEMORY_USERPTR`` is not supported
+          for ``CAPTURE`` buffers.
+
+    * **Return fields:**
+
+      ``count``
+          adjusted to allocated number of buffers, in case the codec requires
+          more buffers than requested.
+
+    * The driver must adjust count to the minimum of required number of
+      ``CAPTURE`` buffers for the current format, stream configuration and
+      requested count. The client must check this value after the ioctl
+      returns to get the number of buffers allocated.
+
+8. Allocate requests (likely one per ``OUTPUT`` buffer) via
+    :c:func:`MEDIA_IOC_REQUEST_ALLOC` on the media device.
+
+9. Start streaming on both ``OUTPUT`` and ``CAPTURE`` queues via
+    :c:func:`VIDIOC_STREAMON`.
+
+Decoding
+========
+
+For each frame, the client is responsible for submitting at least one request to
+which the following is attached:
+
+* The amount of encoded data expected by the codec for its current
+  configuration, as a buffer submitted to the ``OUTPUT`` queue. Typically, this
+  corresponds to one frame worth of encoded data, but some formats may allow (or
+  require) different amounts per unit.
+* All the metadata needed to decode the submitted encoded data, in the form of
+  controls relevant to the format being decoded.
+
+The amount of data and contents of the source ``OUTPUT`` buffer, as well as the
+controls that must be set on the request, depend on the active coded pixel
+format and might be affected by codec-specific extended controls, as stated in
+documentation of each format.
+
+If there is a possibility that the decoded frame will require one or more
+decode requests after the current one in order to be produced, then the client
+must set the ``V4L2_BUF_FLAG_M2M_HOLD_CAPTURE_BUF`` flag on the ``OUTPUT``
+buffer. This will result in the (potentially partially) decoded ``CAPTURE``
+buffer not being made available for dequeueing, and reused for the next decode
+request if the timestamp of the next ``OUTPUT`` buffer has not changed.
+
+A typical frame would thus be decoded using the following sequence:
+
+1. Queue an ``OUTPUT`` buffer containing one unit of encoded bytestream data for
+   the decoding request, using :c:func:`VIDIOC_QBUF`.
+
+    * **Required fields:**
+
+      ``index``
+          index of the buffer being queued.
+
+      ``type``
+          type of the buffer.
+
+      ``bytesused``
+          number of bytes taken by the encoded data frame in the buffer.
+
+      ``flags``
+          the ``V4L2_BUF_FLAG_REQUEST_FD`` flag must be set. Additionally, if
+          we are not sure that the current decode request is the last one needed
+          to produce a fully decoded frame, then
+          ``V4L2_BUF_FLAG_M2M_HOLD_CAPTURE_BUF`` must also be set.
+
+      ``request_fd``
+          must be set to the file descriptor of the decoding request.
+
+      ``timestamp``
+          must be set to a unique value per frame. This value will be propagated
+          into the decoded frame's buffer and can also be used to use this frame
+          as the reference of another. If using multiple decode requests per
+          frame, then the timestamps of all the ``OUTPUT`` buffers for a given
+          frame must be identical. If the timestamp changes, then the currently
+          held ``CAPTURE`` buffer will be made available for dequeuing and the
+          current request will work on a new ``CAPTURE`` buffer.
+
+2. Set the codec-specific controls for the decoding request, using
+   :c:func:`VIDIOC_S_EXT_CTRLS`.
+
+    * **Required fields:**
+
+      ``which``
+          must be ``V4L2_CTRL_WHICH_REQUEST_VAL``.
+
+      ``request_fd``
+          must be set to the file descriptor of the decoding request.
+
+      other fields
+          other fields are set as usual when setting controls. The ``controls``
+          array must contain all the codec-specific controls required to decode
+          a frame.
+
+   .. note::
+
+      It is possible to specify the controls in different invocations of
+      :c:func:`VIDIOC_S_EXT_CTRLS`, or to overwrite a previously set control, as
+      long as ``request_fd`` and ``which`` are properly set. The controls state
+      at the moment of request submission is the one that will be considered.
+
+   .. note::
+
+      The order in which steps 1 and 2 take place is interchangeable.
+
+3. Submit the request by invoking :c:func:`MEDIA_REQUEST_IOC_QUEUE` on the
+   request FD.
+
+    If the request is submitted without an ``OUTPUT`` buffer, or if some of the
+    required controls are missing from the request, then
+    :c:func:`MEDIA_REQUEST_IOC_QUEUE` will return ``-ENOENT``. If more than one
+    ``OUTPUT`` buffer is queued, then it will return ``-EINVAL``.
+    :c:func:`MEDIA_REQUEST_IOC_QUEUE` returning non-zero means that no
+    ``CAPTURE`` buffer will be produced for this request.
+
+``CAPTURE`` buffers must not be part of the request, and are queued
+independently. They are returned in decode order (i.e. the same order as coded
+frames were submitted to the ``OUTPUT`` queue).
+
+Runtime decoding errors are signaled by the dequeued ``CAPTURE`` buffers
+carrying the ``V4L2_BUF_FLAG_ERROR`` flag. If a decoded reference frame has an
+error, then all following decoded frames that refer to it also have the
+``V4L2_BUF_FLAG_ERROR`` flag set, although the decoder will still try to
+produce (likely corrupted) frames.
+
+Buffer management while decoding
+================================
+Contrary to stateful decoders, a stateless decoder does not perform any kind of
+buffer management: it only guarantees that dequeued ``CAPTURE`` buffers can be
+used by the client for as long as they are not queued again. "Used" here
+encompasses using the buffer for compositing or display.
+
+A dequeued capture buffer can also be used as the reference frame of another
+buffer.
+
+A frame is specified as reference by converting its timestamp into nanoseconds,
+and storing it into the relevant member of a codec-dependent control structure.
+The :c:func:`v4l2_timeval_to_ns` function must be used to perform that
+conversion. The timestamp of a frame can be used to reference it as soon as all
+its units of encoded data are successfully submitted to the ``OUTPUT`` queue.
+
+A decoded buffer containing a reference frame must not be reused as a decoding
+target until all the frames referencing it have been decoded. The safest way to
+achieve this is to refrain from queueing a reference buffer until all the
+decoded frames referencing it have been dequeued. However, if the driver can
+guarantee that buffers queued to the ``CAPTURE`` queue are processed in queued
+order, then user-space can take advantage of this guarantee and queue a
+reference buffer when the following conditions are met:
+
+1. All the requests for frames affected by the reference frame have been
+   queued, and
+
+2. A sufficient number of ``CAPTURE`` buffers to cover all the decoded
+   referencing frames have been queued.
+
+When queuing a decoding request, the driver will increase the reference count of
+all the resources associated with reference frames. This means that the client
+can e.g. close the DMABUF file descriptors of reference frame buffers if it
+won't need them afterwards.
+
+Seeking
+=======
+In order to seek, the client just needs to submit requests using input buffers
+corresponding to the new stream position. It must however be aware that
+resolution may have changed and follow the dynamic resolution change sequence in
+that case. Also depending on the codec used, picture parameters (e.g. SPS/PPS
+for H.264) may have changed and the client is responsible for making sure that a
+valid state is sent to the decoder.
+
+The client is then free to ignore any returned ``CAPTURE`` buffer that comes
+from the pre-seek position.
+
+Pausing
+=======
+
+In order to pause, the client can just cease queuing buffers onto the ``OUTPUT``
+queue. Without source bytestream data, there is no data to process and the codec
+will remain idle.
+
+Dynamic resolution change
+=========================
+
+If the client detects a resolution change in the stream, it will need to perform
+the initialization sequence again with the new resolution:
+
+1. If the last submitted request resulted in a ``CAPTURE`` buffer being
+   held by the use of the ``V4L2_BUF_FLAG_M2M_HOLD_CAPTURE_BUF`` flag, then the
+   last frame is not available on the ``CAPTURE`` queue. In this case, a
+   ``V4L2_DEC_CMD_FLUSH`` command shall be sent. This will make the driver
+   dequeue the held ``CAPTURE`` buffer.
+
+2. Wait until all submitted requests have completed and dequeue the
+   corresponding output buffers.
+
+3. Call :c:func:`VIDIOC_STREAMOFF` on both the ``OUTPUT`` and ``CAPTURE``
+   queues.
+
+4. Free all ``CAPTURE`` buffers by calling :c:func:`VIDIOC_REQBUFS` on the
+   ``CAPTURE`` queue with a buffer count of zero.
+
+5. Perform the initialization sequence again (minus the allocation of
+   ``OUTPUT`` buffers), with the new resolution set on the ``OUTPUT`` queue.
+   Note that due to resolution constraints, a different format may need to be
+   picked on the ``CAPTURE`` queue.
+
+Drain
+=====
+
+If the last submitted request resulted in a ``CAPTURE`` buffer being
+held by the use of the ``V4L2_BUF_FLAG_M2M_HOLD_CAPTURE_BUF`` flag, then the
+last frame is not available on the ``CAPTURE`` queue. In this case, a
+``V4L2_DEC_CMD_FLUSH`` command shall be sent. This will make the driver
+dequeue the held ``CAPTURE`` buffer.
+
+After that, in order to drain the stream on a stateless decoder, the client
+just needs to wait until all the submitted requests are completed.
diff --git a/Documentation/media/uapi/v4l/ext-ctrls-codec.rst b/Documentation/media/uapi/v4l/ext-ctrls-codec.rst
index bc5dd8e76567..28313c0f4e7c 100644
--- a/Documentation/media/uapi/v4l/ext-ctrls-codec.rst
+++ b/Documentation/media/uapi/v4l/ext-ctrls-codec.rst
@@ -1713,10 +1713,14 @@ enum v4l2_mpeg_video_h264_hierarchical_coding_type -
 
     * - __u8
       - ``scaling_list_4x4[6][16]``
-      -
+      - Scaling matrix after applying the inverse scanning process.
+        Expected list order is Intra Y, Intra Cb, Intra Cr, Inter Y,
+        Inter Cb, Inter Cr.
     * - __u8
       - ``scaling_list_8x8[6][64]``
-      -
+      - Scaling matrix after applying the inverse scanning process.
+        Expected list order is Intra Y, Inter Y, Intra Cb, Inter Cb,
+        Intra Cr, Inter Cr.
 
 ``V4L2_CID_MPEG_VIDEO_H264_SLICE_PARAMS (struct)``
     Specifies the slice parameters (as extracted from the bitstream)
@@ -1796,7 +1800,7 @@ enum v4l2_mpeg_video_h264_hierarchical_coding_type -
       -
     * - __u32
       - ``dec_ref_pic_marking_bit_size``
-      -
+      - Size in bits of the dec_ref_pic_marking() syntax element.
     * - __u32
       - ``pic_order_cnt_bit_size``
       -
@@ -1820,10 +1824,12 @@ enum v4l2_mpeg_video_h264_hierarchical_coding_type -
       -
     * - __u8
       - ``num_ref_idx_l0_active_minus1``
-      -
+      - If num_ref_idx_active_override_flag is not set, this field must be
+        set to the value of num_ref_idx_l0_default_active_minus1.
     * - __u8
       - ``num_ref_idx_l1_active_minus1``
-      -
+      - If num_ref_idx_active_override_flag is not set, this field must be
+        set to the value of num_ref_idx_l1_default_active_minus1.
     * - __u32
       - ``slice_group_change_cycle``
       -
@@ -1983,9 +1989,9 @@ enum v4l2_mpeg_video_h264_hierarchical_coding_type -
       - ``reference_ts``
       - Timestamp of the V4L2 capture buffer to use as reference, used
         with B-coded and P-coded frames. The timestamp refers to the
-	``timestamp`` field in struct :c:type:`v4l2_buffer`. Use the
-	:c:func:`v4l2_timeval_to_ns()` function to convert the struct
-	:c:type:`timeval` in struct :c:type:`v4l2_buffer` to a __u64.
+        ``timestamp`` field in struct :c:type:`v4l2_buffer`. Use the
+        :c:func:`v4l2_timeval_to_ns()` function to convert the struct
+        :c:type:`timeval` in struct :c:type:`v4l2_buffer` to a __u64.
     * - __u16
       - ``frame_num``
       -
@@ -3693,3 +3699,550 @@ enum v4l2_mpeg_video_hevc_size_of_length_field -
     Indicates whether to generate SPS and PPS at every IDR. Setting it to 0
     disables generating SPS and PPS at every IDR. Setting it to one enables
     generating SPS and PPS at every IDR.
+
+.. _v4l2-mpeg-hevc:
+
+``V4L2_CID_MPEG_VIDEO_HEVC_SPS (struct)``
+    Specifies the Sequence Parameter Set fields (as extracted from the
+    bitstream) for the associated HEVC slice data.
+    These bitstream parameters are defined according to :ref:`hevc`.
+    They are described in section 7.4.3.2 "Sequence parameter set RBSP
+    semantics" of the specification.
+
+.. c:type:: v4l2_ctrl_hevc_sps
+
+.. cssclass:: longtable
+
+.. flat-table:: struct v4l2_ctrl_hevc_sps
+    :header-rows:  0
+    :stub-columns: 0
+    :widths:       1 1 2
+
+    * - __u16
+      - ``pic_width_in_luma_samples``
+      -
+    * - __u16
+      - ``pic_height_in_luma_samples``
+      -
+    * - __u8
+      - ``bit_depth_luma_minus8``
+      -
+    * - __u8
+      - ``bit_depth_chroma_minus8``
+      -
+    * - __u8
+      - ``log2_max_pic_order_cnt_lsb_minus4``
+      -
+    * - __u8
+      - ``sps_max_dec_pic_buffering_minus1``
+      -
+    * - __u8
+      - ``sps_max_num_reorder_pics``
+      -
+    * - __u8
+      - ``sps_max_latency_increase_plus1``
+      -
+    * - __u8
+      - ``log2_min_luma_coding_block_size_minus3``
+      -
+    * - __u8
+      - ``log2_diff_max_min_luma_coding_block_size``
+      -
+    * - __u8
+      - ``log2_min_luma_transform_block_size_minus2``
+      -
+    * - __u8
+      - ``log2_diff_max_min_luma_transform_block_size``
+      -
+    * - __u8
+      - ``max_transform_hierarchy_depth_inter``
+      -
+    * - __u8
+      - ``max_transform_hierarchy_depth_intra``
+      -
+    * - __u8
+      - ``pcm_sample_bit_depth_luma_minus1``
+      -
+    * - __u8
+      - ``pcm_sample_bit_depth_chroma_minus1``
+      -
+    * - __u8
+      - ``log2_min_pcm_luma_coding_block_size_minus3``
+      -
+    * - __u8
+      - ``log2_diff_max_min_pcm_luma_coding_block_size``
+      -
+    * - __u8
+      - ``num_short_term_ref_pic_sets``
+      -
+    * - __u8
+      - ``num_long_term_ref_pics_sps``
+      -
+    * - __u8
+      - ``chroma_format_idc``
+      -
+    * - __u64
+      - ``flags``
+      - See :ref:`Sequence Parameter Set Flags <hevc_sps_flags>`
+
+.. _hevc_sps_flags:
+
+``Sequence Parameter Set Flags``
+
+.. cssclass:: longtable
+
+.. flat-table::
+    :header-rows:  0
+    :stub-columns: 0
+    :widths:       1 1 2
+
+    * - ``V4L2_HEVC_SPS_FLAG_SEPARATE_COLOUR_PLANE``
+      - 0x00000001
+      -
+    * - ``V4L2_HEVC_SPS_FLAG_SCALING_LIST_ENABLED``
+      - 0x00000002
+      -
+    * - ``V4L2_HEVC_SPS_FLAG_AMP_ENABLED``
+      - 0x00000004
+      -
+    * - ``V4L2_HEVC_SPS_FLAG_SAMPLE_ADAPTIVE_OFFSET``
+      - 0x00000008
+      -
+    * - ``V4L2_HEVC_SPS_FLAG_PCM_ENABLED``
+      - 0x00000010
+      -
+    * - ``V4L2_HEVC_SPS_FLAG_PCM_LOOP_FILTER_DISABLED``
+      - 0x00000020
+      -
+    * - ``V4L2_HEVC_SPS_FLAG_LONG_TERM_REF_PICS_PRESENT``
+      - 0x00000040
+      -
+    * - ``V4L2_HEVC_SPS_FLAG_SPS_TEMPORAL_MVP_ENABLED``
+      - 0x00000080
+      -
+    * - ``V4L2_HEVC_SPS_FLAG_STRONG_INTRA_SMOOTHING_ENABLED``
+      - 0x00000100
+      -
+
+``V4L2_CID_MPEG_VIDEO_HEVC_PPS (struct)``
+    Specifies the Picture Parameter Set fields (as extracted from the
+    bitstream) for the associated HEVC slice data.
+    These bitstream parameters are defined according to :ref:`hevc`.
+    They are described in section 7.4.3.3 "Picture parameter set RBSP
+    semantics" of the specification.
+
+.. c:type:: v4l2_ctrl_hevc_pps
+
+.. cssclass:: longtable
+
+.. flat-table:: struct v4l2_ctrl_hevc_pps
+    :header-rows:  0
+    :stub-columns: 0
+    :widths:       1 1 2
+
+    * - __u8
+      - ``num_extra_slice_header_bits``
+      -
+    * - __s8
+      - ``init_qp_minus26``
+      -
+    * - __u8
+      - ``diff_cu_qp_delta_depth``
+      -
+    * - __s8
+      - ``pps_cb_qp_offset``
+      -
+    * - __s8
+      - ``pps_cr_qp_offset``
+      -
+    * - __u8
+      - ``num_tile_columns_minus1``
+      -
+    * - __u8
+      - ``num_tile_rows_minus1``
+      -
+    * - __u8
+      - ``column_width_minus1[20]``
+      -
+    * - __u8
+      - ``row_height_minus1[22]``
+      -
+    * - __s8
+      - ``pps_beta_offset_div2``
+      -
+    * - __s8
+      - ``pps_tc_offset_div2``
+      -
+    * - __u8
+      - ``log2_parallel_merge_level_minus2``
+      -
+    * - __u8
+      - ``padding[4]``
+      - Applications and drivers must set this to zero.
+    * - __u64
+      - ``flags``
+      - See :ref:`Picture Parameter Set Flags <hevc_pps_flags>`
+
+.. _hevc_pps_flags:
+
+``Picture Parameter Set Flags``
+
+.. cssclass:: longtable
+
+.. flat-table::
+    :header-rows:  0
+    :stub-columns: 0
+    :widths:       1 1 2
+
+    * - ``V4L2_HEVC_PPS_FLAG_DEPENDENT_SLICE_SEGMENT``
+      - 0x00000001
+      -
+    * - ``V4L2_HEVC_PPS_FLAG_OUTPUT_FLAG_PRESENT``
+      - 0x00000002
+      -
+    * - ``V4L2_HEVC_PPS_FLAG_SIGN_DATA_HIDING_ENABLED``
+      - 0x00000004
+      -
+    * - ``V4L2_HEVC_PPS_FLAG_CABAC_INIT_PRESENT``
+      - 0x00000008
+      -
+    * - ``V4L2_HEVC_PPS_FLAG_CONSTRAINED_INTRA_PRED``
+      - 0x00000010
+      -
+    * - ``V4L2_HEVC_PPS_FLAG_TRANSFORM_SKIP_ENABLED``
+      - 0x00000020
+      -
+    * - ``V4L2_HEVC_PPS_FLAG_CU_QP_DELTA_ENABLED``
+      - 0x00000040
+      -
+    * - ``V4L2_HEVC_PPS_FLAG_PPS_SLICE_CHROMA_QP_OFFSETS_PRESENT``
+      - 0x00000080
+      -
+    * - ``V4L2_HEVC_PPS_FLAG_WEIGHTED_PRED``
+      - 0x00000100
+      -
+    * - ``V4L2_HEVC_PPS_FLAG_WEIGHTED_BIPRED``
+      - 0x00000200
+      -
+    * - ``V4L2_HEVC_PPS_FLAG_TRANSQUANT_BYPASS_ENABLED``
+      - 0x00000400
+      -
+    * - ``V4L2_HEVC_PPS_FLAG_TILES_ENABLED``
+      - 0x00000800
+      -
+    * - ``V4L2_HEVC_PPS_FLAG_ENTROPY_CODING_SYNC_ENABLED``
+      - 0x00001000
+      -
+    * - ``V4L2_HEVC_PPS_FLAG_LOOP_FILTER_ACROSS_TILES_ENABLED``
+      - 0x00002000
+      -
+    * - ``V4L2_HEVC_PPS_FLAG_PPS_LOOP_FILTER_ACROSS_SLICES_ENABLED``
+      - 0x00004000
+      -
+    * - ``V4L2_HEVC_PPS_FLAG_DEBLOCKING_FILTER_OVERRIDE_ENABLED``
+      - 0x00008000
+      -
+    * - ``V4L2_HEVC_PPS_FLAG_PPS_DISABLE_DEBLOCKING_FILTER``
+      - 0x00010000
+      -
+    * - ``V4L2_HEVC_PPS_FLAG_LISTS_MODIFICATION_PRESENT``
+      - 0x00020000
+      -
+    * - ``V4L2_HEVC_PPS_FLAG_SLICE_SEGMENT_HEADER_EXTENSION_PRESENT``
+      - 0x00040000
+      -
+
+``V4L2_CID_MPEG_VIDEO_HEVC_SLICE_PARAMS (struct)``
+    Specifies various slice-specific parameters, especially from the NAL unit
+    header, general slice segment header and weighted prediction parameter
+    parts of the bitstream.
+    These bitstream parameters are defined according to :ref:`hevc`.
+    They are described in section 7.4.7 "General slice segment header
+    semantics" of the specification.
+
+.. c:type:: v4l2_ctrl_hevc_slice_params
+
+.. cssclass:: longtable
+
+.. flat-table:: struct v4l2_ctrl_hevc_slice_params
+    :header-rows:  0
+    :stub-columns: 0
+    :widths:       1 1 2
+
+    * - __u32
+      - ``bit_size``
+      - Size (in bits) of the current slice data.
+    * - __u32
+      - ``data_bit_offset``
+      - Offset (in bits) to the video data in the current slice data.
+    * - __u8
+      - ``nal_unit_type``
+      -
+    * - __u8
+      - ``nuh_temporal_id_plus1``
+      -
+    * - __u8
+      - ``slice_type``
+      -
+	(V4L2_HEVC_SLICE_TYPE_I, V4L2_HEVC_SLICE_TYPE_P or
+	V4L2_HEVC_SLICE_TYPE_B).
+    * - __u8
+      - ``colour_plane_id``
+      -
+    * - __u16
+      - ``slice_pic_order_cnt``
+      -
+    * - __u8
+      - ``num_ref_idx_l0_active_minus1``
+      -
+    * - __u8
+      - ``num_ref_idx_l1_active_minus1``
+      -
+    * - __u8
+      - ``collocated_ref_idx``
+      -
+    * - __u8
+      - ``five_minus_max_num_merge_cand``
+      -
+    * - __s8
+      - ``slice_qp_delta``
+      -
+    * - __s8
+      - ``slice_cb_qp_offset``
+      -
+    * - __s8
+      - ``slice_cr_qp_offset``
+      -
+    * - __s8
+      - ``slice_act_y_qp_offset``
+      -
+    * - __s8
+      - ``slice_act_cb_qp_offset``
+      -
+    * - __s8
+      - ``slice_act_cr_qp_offset``
+      -
+    * - __s8
+      - ``slice_beta_offset_div2``
+      -
+    * - __s8
+      - ``slice_tc_offset_div2``
+      -
+    * - __u8
+      - ``pic_struct``
+      -
+    * - __u8
+      - ``num_active_dpb_entries``
+      - The number of entries in ``dpb``.
+    * - __u8
+      - ``ref_idx_l0[V4L2_HEVC_DPB_ENTRIES_NUM_MAX]``
+      - The list of L0 reference elements as indices in the DPB.
+    * - __u8
+      - ``ref_idx_l1[V4L2_HEVC_DPB_ENTRIES_NUM_MAX]``
+      - The list of L1 reference elements as indices in the DPB.
+    * - __u8
+      - ``num_rps_poc_st_curr_before``
+      - The number of reference pictures in the short-term set that come before
+        the current frame.
+    * - __u8
+      - ``num_rps_poc_st_curr_after``
+      - The number of reference pictures in the short-term set that come after
+        the current frame.
+    * - __u8
+      - ``num_rps_poc_lt_curr``
+      - The number of reference pictures in the long-term set.
+    * - __u8
+      - ``padding[7]``
+      - Applications and drivers must set this to zero.
+    * - struct :c:type:`v4l2_hevc_dpb_entry`
+      - ``dpb[V4L2_HEVC_DPB_ENTRIES_NUM_MAX]``
+      - The decoded picture buffer, for meta-data about reference frames.
+    * - struct :c:type:`v4l2_hevc_pred_weight_table`
+      - ``pred_weight_table``
+      - The prediction weight coefficients for inter-picture prediction.
+    * - __u64
+      - ``flags``
+      - See :ref:`Slice Parameters Flags <hevc_slice_params_flags>`
+
+.. _hevc_slice_params_flags:
+
+``Slice Parameters Flags``
+
+.. cssclass:: longtable
+
+.. flat-table::
+    :header-rows:  0
+    :stub-columns: 0
+    :widths:       1 1 2
+
+    * - ``V4L2_HEVC_SLICE_PARAMS_FLAG_SLICE_SAO_LUMA``
+      - 0x00000001
+      -
+    * - ``V4L2_HEVC_SLICE_PARAMS_FLAG_SLICE_SAO_CHROMA``
+      - 0x00000002
+      -
+    * - ``V4L2_HEVC_SLICE_PARAMS_FLAG_SLICE_TEMPORAL_MVP_ENABLED``
+      - 0x00000004
+      -
+    * - ``V4L2_HEVC_SLICE_PARAMS_FLAG_MVD_L1_ZERO``
+      - 0x00000008
+      -
+    * - ``V4L2_HEVC_SLICE_PARAMS_FLAG_CABAC_INIT``
+      - 0x00000010
+      -
+    * - ``V4L2_HEVC_SLICE_PARAMS_FLAG_COLLOCATED_FROM_L0``
+      - 0x00000020
+      -
+    * - ``V4L2_HEVC_SLICE_PARAMS_FLAG_USE_INTEGER_MV``
+      - 0x00000040
+      -
+    * - ``V4L2_HEVC_SLICE_PARAMS_FLAG_SLICE_DEBLOCKING_FILTER_DISABLED``
+      - 0x00000080
+      -
+    * - ``V4L2_HEVC_SLICE_PARAMS_FLAG_SLICE_LOOP_FILTER_ACROSS_SLICES_ENABLED``
+      - 0x00000100
+      -
+
+.. c:type:: v4l2_hevc_dpb_entry
+
+.. cssclass:: longtable
+
+.. flat-table:: struct v4l2_hevc_dpb_entry
+    :header-rows:  0
+    :stub-columns: 0
+    :widths:       1 1 2
+
+    * - __u64
+      - ``timestamp``
+      - Timestamp of the V4L2 capture buffer to use as reference, used
+        with B-coded and P-coded frames. The timestamp refers to the
+	``timestamp`` field in struct :c:type:`v4l2_buffer`. Use the
+	:c:func:`v4l2_timeval_to_ns()` function to convert the struct
+	:c:type:`timeval` in struct :c:type:`v4l2_buffer` to a __u64.
+    * - __u8
+      - ``rps``
+      - The reference set for the reference frame
+        (V4L2_HEVC_DPB_ENTRY_RPS_ST_CURR_BEFORE,
+        V4L2_HEVC_DPB_ENTRY_RPS_ST_CURR_AFTER or
+        V4L2_HEVC_DPB_ENTRY_RPS_LT_CURR)
+    * - __u8
+      - ``field_pic``
+      - Whether the reference is a field picture or a frame.
+    * - __u16
+      - ``pic_order_cnt[2]``
+      - The picture order count of the reference. Only the first element of the
+        array is used for frame pictures, while the first element identifies the
+        top field and the second the bottom field in field-coded pictures.
+    * - __u8
+      - ``padding[2]``
+      - Applications and drivers must set this to zero.
+
+.. c:type:: v4l2_hevc_pred_weight_table
+
+.. cssclass:: longtable
+
+.. flat-table:: struct v4l2_hevc_pred_weight_table
+    :header-rows:  0
+    :stub-columns: 0
+    :widths:       1 1 2
+
+    * - __u8
+      - ``luma_log2_weight_denom``
+      -
+    * - __s8
+      - ``delta_chroma_log2_weight_denom``
+      -
+    * - __s8
+      - ``delta_luma_weight_l0[V4L2_HEVC_DPB_ENTRIES_NUM_MAX]``
+      -
+    * - __s8
+      - ``luma_offset_l0[V4L2_HEVC_DPB_ENTRIES_NUM_MAX]``
+      -
+    * - __s8
+      - ``delta_chroma_weight_l0[V4L2_HEVC_DPB_ENTRIES_NUM_MAX][2]``
+      -
+    * - __s8
+      - ``chroma_offset_l0[V4L2_HEVC_DPB_ENTRIES_NUM_MAX][2]``
+      -
+    * - __s8
+      - ``delta_luma_weight_l1[V4L2_HEVC_DPB_ENTRIES_NUM_MAX]``
+      -
+    * - __s8
+      - ``luma_offset_l1[V4L2_HEVC_DPB_ENTRIES_NUM_MAX]``
+      -
+    * - __s8
+      - ``delta_chroma_weight_l1[V4L2_HEVC_DPB_ENTRIES_NUM_MAX][2]``
+      -
+    * - __s8
+      - ``chroma_offset_l1[V4L2_HEVC_DPB_ENTRIES_NUM_MAX][2]``
+      -
+    * - __u8
+      - ``padding[6]``
+      - Applications and drivers must set this to zero.
+
+``V4L2_CID_MPEG_VIDEO_HEVC_DECODE_MODE (enum)``
+    Specifies the decoding mode to use. Currently exposes slice-based and
+    frame-based decoding but new modes might be added later on.
+    This control is used as a modifier for V4L2_PIX_FMT_HEVC_SLICE
+    pixel format. Applications that support V4L2_PIX_FMT_HEVC_SLICE
+    are required to set this control in order to specify the decoding mode
+    that is expected for the buffer.
+    Drivers may expose a single or multiple decoding modes, depending
+    on what they can support.
+
+    .. note::
+
+       This menu control is not yet part of the public kernel API and
+       it is expected to change.
+
+.. c:type:: v4l2_mpeg_video_hevc_decode_mode
+
+.. cssclass:: longtable
+
+.. flat-table::
+    :header-rows:  0
+    :stub-columns: 0
+    :widths:       1 1 2
+
+    * - ``V4L2_MPEG_VIDEO_HEVC_DECODE_MODE_SLICE_BASED``
+      - 0
+      - Decoding is done at the slice granularity.
+        The OUTPUT buffer must contain a single slice.
+    * - ``V4L2_MPEG_VIDEO_HEVC_DECODE_MODE_FRAME_BASED``
+      - 1
+      - Decoding is done at the frame granularity.
+        The OUTPUT buffer must contain all slices needed to decode the
+        frame. The OUTPUT buffer must also contain both fields.
+
+``V4L2_CID_MPEG_VIDEO_HEVC_START_CODE (enum)``
+    Specifies the HEVC slice start code expected for each slice.
+    This control is used as a modifier for V4L2_PIX_FMT_HEVC_SLICE
+    pixel format. Applications that support V4L2_PIX_FMT_HEVC_SLICE
+    are required to set this control in order to specify the start code
+    that is expected for the buffer.
+    Drivers may expose a single or multiple start codes, depending
+    on what they can support.
+
+    .. note::
+
+       This menu control is not yet part of the public kernel API and
+       it is expected to change.
+
+.. c:type:: v4l2_mpeg_video_hevc_start_code
+
+.. cssclass:: longtable
+
+.. flat-table::
+    :header-rows:  0
+    :stub-columns: 0
+    :widths:       1 1 2
+
+    * - ``V4L2_MPEG_VIDEO_HEVC_START_CODE_NONE``
+      - 0
+      - Selecting this value specifies that HEVC slices are passed
+        to the driver without any start code.
+    * - ``V4L2_MPEG_VIDEO_HEVC_START_CODE_ANNEX_B``
+      - 1
+      - Selecting this value specifies that HEVC slices are expected
+        to be prefixed by Annex B start codes. According to :ref:`hevc`
+        valid start codes can be 3-bytes 0x000001 or 4-bytes 0x00000001.
diff --git a/Documentation/media/uapi/v4l/ext-ctrls-flash.rst b/Documentation/media/uapi/v4l/ext-ctrls-flash.rst
index eff056b17167..b9a6b08fbf32 100644
--- a/Documentation/media/uapi/v4l/ext-ctrls-flash.rst
+++ b/Documentation/media/uapi/v4l/ext-ctrls-flash.rst
@@ -98,7 +98,7 @@ Flash Control IDs
 	V4L2_CID_FLASH_STROBE control.
     * - ``V4L2_FLASH_STROBE_SOURCE_EXTERNAL``
       - The flash strobe is triggered by an external source. Typically
-	this is a sensor, which makes it possible to synchronises the
+	this is a sensor, which makes it possible to synchronise the
 	flash strobe start to exposure start.
 
 
diff --git a/Documentation/media/uapi/v4l/ext-ctrls-image-source.rst b/Documentation/media/uapi/v4l/ext-ctrls-image-source.rst
index 2c3ab5796d76..2d3e2b83d6dd 100644
--- a/Documentation/media/uapi/v4l/ext-ctrls-image-source.rst
+++ b/Documentation/media/uapi/v4l/ext-ctrls-image-source.rst
@@ -55,3 +55,13 @@ Image Source Control IDs
 
 ``V4L2_CID_TEST_PATTERN_GREENB (integer)``
     Test pattern green (next to blue) colour component.
+
+``V4L2_CID_UNIT_CELL_SIZE (struct)``
+    This control returns the unit cell size in nanometers. The struct
+    :c:type:`v4l2_area` provides the width and the height in separate
+    fields to take into consideration asymmetric pixels.
+    This control does not take into consideration any possible hardware
+    binning.
+    The unit cell consists of the whole area of the pixel, sensitive and
+    non-sensitive.
+    This control is required for automatic calibration of sensors/cameras.
diff --git a/Documentation/media/uapi/v4l/meta-formats.rst b/Documentation/media/uapi/v4l/meta-formats.rst
index b10ca9ee3968..74c8659ee9d6 100644
--- a/Documentation/media/uapi/v4l/meta-formats.rst
+++ b/Documentation/media/uapi/v4l/meta-formats.rst
@@ -24,3 +24,4 @@ These formats are used for the :ref:`metadata` interface only.
     pixfmt-meta-uvc
     pixfmt-meta-vsp1-hgo
     pixfmt-meta-vsp1-hgt
+    pixfmt-meta-vivid
diff --git a/Documentation/media/uapi/v4l/pixfmt-compressed.rst b/Documentation/media/uapi/v4l/pixfmt-compressed.rst
index 292fdc116c77..561bda112809 100644
--- a/Documentation/media/uapi/v4l/pixfmt-compressed.rst
+++ b/Documentation/media/uapi/v4l/pixfmt-compressed.rst
@@ -61,10 +61,10 @@ Compressed Formats
 
       - ``V4L2_PIX_FMT_H264_SLICE``
       - 'S264'
-      - H264 parsed slice data, without the start code and as
-	extracted from the H264 bitstream.  This format is adapted for
-	stateless video decoders that implement an H264 pipeline
-	(using the :ref:`mem2mem` and :ref:`media-request-api`).
+      - H264 parsed slice data, including slice headers, either with or
+	without the start code, as extracted from the H264 bitstream.
+	This format is adapted for stateless video decoders that implement an
+	H264 pipeline (using the :ref:`mem2mem` and :ref:`media-request-api`).
 	This pixelformat has two modifiers that must be set at least once
 	through the ``V4L2_CID_MPEG_VIDEO_H264_DECODE_MODE``
         and ``V4L2_CID_MPEG_VIDEO_H264_START_CODE`` controls.
@@ -80,6 +80,10 @@ Compressed Formats
 	appropriate number of macroblocks to decode a full
 	corresponding frame to the matching capture buffer.
 
+	The syntax for this format is documented in :ref:`h264`, section
+	7.3.2.8 "Slice layer without partitioning RBSP syntax" and the following
+	sections.
+
 	.. note::
 
 	   This format is not yet part of the public kernel API and it
@@ -188,6 +192,29 @@ Compressed Formats
 	If :ref:`VIDIOC_ENUM_FMT` reports ``V4L2_FMT_FLAG_CONTINUOUS_BYTESTREAM``
 	then the decoder has no	requirements since it can parse all the
 	information from the raw bytestream.
+    * .. _V4L2-PIX-FMT-HEVC-SLICE:
+
+      - ``V4L2_PIX_FMT_HEVC_SLICE``
+      - 'S265'
+      - HEVC parsed slice data, as extracted from the HEVC bitstream.
+	This format is adapted for stateless video decoders that implement a
+	HEVC pipeline (using the :ref:`mem2mem` and :ref:`media-request-api`).
+	This pixelformat has two modifiers that must be set at least once
+	through the ``V4L2_CID_MPEG_VIDEO_HEVC_DECODE_MODE``
+        and ``V4L2_CID_MPEG_VIDEO_HEVC_START_CODE`` controls.
+	Metadata associated with the frame to decode is required to be passed
+	through the following controls :
+        * ``V4L2_CID_MPEG_VIDEO_HEVC_SPS``
+        * ``V4L2_CID_MPEG_VIDEO_HEVC_PPS``
+        * ``V4L2_CID_MPEG_VIDEO_HEVC_SLICE_PARAMS``
+	See the :ref:`associated Codec Control IDs <v4l2-mpeg-hevc>`.
+	Buffers associated with this pixel format must contain the appropriate
+	number of macroblocks to decode a full corresponding frame.
+
+	.. note::
+
+	   This format is not yet part of the public kernel API and it
+	   is expected to change.
     * .. _V4L2-PIX-FMT-FWHT:
 
       - ``V4L2_PIX_FMT_FWHT``
diff --git a/Documentation/media/uapi/v4l/pixfmt-meta-vivid.rst b/Documentation/media/uapi/v4l/pixfmt-meta-vivid.rst
new file mode 100644
index 000000000000..eed20eaefe24
--- /dev/null
+++ b/Documentation/media/uapi/v4l/pixfmt-meta-vivid.rst
@@ -0,0 +1,60 @@
+.. This file is dual-licensed: you can use it either under the terms
+.. of the GPL 2.0 or the GFDL 1.1+ license, at your option. Note that this
+.. dual licensing only applies to this file, and not this project as a
+.. whole.
+..
+.. a) This file is free software; you can redistribute it and/or
+..    modify it under the terms of the GNU General Public License as
+..    published by the Free Software Foundation version 2 of
+..    the License.
+..
+..    This file is distributed in the hope that it will be useful,
+..    but WITHOUT ANY WARRANTY; without even the implied warranty of
+..    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+..    GNU General Public License for more details.
+..
+.. Or, alternatively,
+..
+.. b) Permission is granted to copy, distribute and/or modify this
+..    document under the terms of the GNU Free Documentation License,
+..    Version 1.1 or any later version published by the Free Software
+..    Foundation, with no Invariant Sections, no Front-Cover Texts
+..    and no Back-Cover Texts. A copy of the license is included at
+..    Documentation/media/uapi/fdl-appendix.rst.
+..
+.. TODO: replace it to GPL-2.0 OR GFDL-1.1-or-later WITH no-invariant-sections
+
+.. _v4l2-meta-fmt-vivid:
+
+*******************************
+V4L2_META_FMT_VIVID ('VIVD')
+*******************************
+
+VIVID Metadata Format
+
+
+Description
+===========
+
+This describes metadata format used by the vivid driver.
+
+It sets Brightness, Saturation, Contrast and Hue, each of which maps to
+corresponding controls of the vivid driver with respect to the range and default values.
+
+It contains the following fields:
+
+.. flat-table:: VIVID Metadata
+    :widths: 1 4
+    :header-rows:  1
+    :stub-columns: 0
+
+    * - Field
+      - Description
+    * - u16 brightness;
+      - Image brightness, the value is in the range 0 to 255, with the default value as 128.
+    * - u16 contrast;
+      - Image contrast, the value is in the range 0 to 255, with the default value as 128.
+    * - u16 saturation;
+      - Image color saturation, the value is in the range 0 to 255, with the default value as 128.
+    * - s16 hue;
+      - Image color balance, the value is in the range -128 to 128, with the default value as 0.
diff --git a/Documentation/media/uapi/v4l/v4l2-selection-targets.rst b/Documentation/media/uapi/v4l/v4l2-selection-targets.rst
index f74f239b0510..aae0c0013eb1 100644
--- a/Documentation/media/uapi/v4l/v4l2-selection-targets.rst
+++ b/Documentation/media/uapi/v4l/v4l2-selection-targets.rst
@@ -38,8 +38,10 @@ of the two interfaces they are used.
     * - ``V4L2_SEL_TGT_CROP_DEFAULT``
       - 0x0001
       - Suggested cropping rectangle that covers the "whole picture".
+        This includes only active pixels and excludes other non-active
+        pixels such as black pixels.
+      - Yes
       - Yes
-      - No
     * - ``V4L2_SEL_TGT_CROP_BOUNDS``
       - 0x0002
       - Bounds of the crop rectangle. All valid crop rectangles fit inside
diff --git a/Documentation/media/uapi/v4l/vidioc-decoder-cmd.rst b/Documentation/media/uapi/v4l/vidioc-decoder-cmd.rst
index 57f0066f4cff..f1a504836f31 100644
--- a/Documentation/media/uapi/v4l/vidioc-decoder-cmd.rst
+++ b/Documentation/media/uapi/v4l/vidioc-decoder-cmd.rst
@@ -208,7 +208,15 @@ introduced in Linux 3.3. They are, however, mandatory for stateful mem2mem decod
 	been started yet, the driver will return an ``EPERM`` error code. When
 	the decoder is already running, this command does nothing. No
 	flags are defined for this command.
-
+    * - ``V4L2_DEC_CMD_FLUSH``
+      - 4
+      - Flush any held capture buffers. Only valid for stateless decoders.
+	This command is typically used when the application reached the
+	end of the stream and the last output buffer had the
+	``V4L2_BUF_FLAG_M2M_HOLD_CAPTURE_BUF`` flag set. This would prevent
+	dequeueing the capture buffer containing the last decoded frame.
+	So this command can be used to explicitly flush that final decoded
+	frame. This command does nothing if there are no held capture buffers.
 
 Return Value
 ============
diff --git a/Documentation/media/uapi/v4l/vidioc-g-ext-ctrls.rst b/Documentation/media/uapi/v4l/vidioc-g-ext-ctrls.rst
index 13dc1a986249..271cac18afbb 100644
--- a/Documentation/media/uapi/v4l/vidioc-g-ext-ctrls.rst
+++ b/Documentation/media/uapi/v4l/vidioc-g-ext-ctrls.rst
@@ -199,6 +199,11 @@ still cause this situation.
       - A pointer to a matrix control of unsigned 32-bit values. Valid if
 	this control is of type ``V4L2_CTRL_TYPE_U32``.
     * -
+      - :c:type:`v4l2_area` *
+      - ``p_area``
+      - A pointer to a struct :c:type:`v4l2_area`. Valid if this control is
+        of type ``V4L2_CTRL_TYPE_AREA``.
+    * -
       - void *
       - ``ptr``
       - A pointer to a compound type which can be an N-dimensional array
diff --git a/Documentation/media/uapi/v4l/vidioc-g-fbuf.rst b/Documentation/media/uapi/v4l/vidioc-g-fbuf.rst
index 7b6179627803..2d197e6bba8f 100644
--- a/Documentation/media/uapi/v4l/vidioc-g-fbuf.rst
+++ b/Documentation/media/uapi/v4l/vidioc-g-fbuf.rst
@@ -63,7 +63,7 @@ EINVAL error code when overlays are not supported.
 
 To set the parameters for a *Video Output Overlay*, applications must
 initialize the ``flags`` field of a struct
-struct :c:type:`v4l2_framebuffer`. Since the framebuffer is
+:c:type:`v4l2_framebuffer`. Since the framebuffer is
 implemented on the TV card all other parameters are determined by the
 driver. When an application calls :ref:`VIDIOC_S_FBUF <VIDIOC_G_FBUF>` with a pointer to
 this structure, the driver prepares for the overlay and returns the
diff --git a/Documentation/media/uapi/v4l/vidioc-queryctrl.rst b/Documentation/media/uapi/v4l/vidioc-queryctrl.rst
index a3d56ffbf4cc..6690928e657b 100644
--- a/Documentation/media/uapi/v4l/vidioc-queryctrl.rst
+++ b/Documentation/media/uapi/v4l/vidioc-queryctrl.rst
@@ -443,6 +443,12 @@ See also the examples in :ref:`control`.
       - n/a
       - A struct :c:type:`v4l2_ctrl_mpeg2_quantization`, containing MPEG-2
 	quantization matrices for stateless video decoders.
+    * - ``V4L2_CTRL_TYPE_AREA``
+      - n/a
+      - n/a
+      - n/a
+      - A struct :c:type:`v4l2_area`, containing the width and the height
+        of a rectangular area. Units depend on the use case.
     * - ``V4L2_CTRL_TYPE_H264_SPS``
       - n/a
       - n/a
@@ -473,6 +479,24 @@ See also the examples in :ref:`control`.
       - n/a
       - A struct :c:type:`v4l2_ctrl_h264_decode_params`, containing H264
 	decode parameters for stateless video decoders.
+    * - ``V4L2_CTRL_TYPE_HEVC_SPS``
+      - n/a
+      - n/a
+      - n/a
+      - A struct :c:type:`v4l2_ctrl_hevc_sps`, containing HEVC Sequence
+	Parameter Set for stateless video decoders.
+    * - ``V4L2_CTRL_TYPE_HEVC_PPS``
+      - n/a
+      - n/a
+      - n/a
+      - A struct :c:type:`v4l2_ctrl_hevc_pps`, containing HEVC Picture
+	Parameter Set for stateless video decoders.
+    * - ``V4L2_CTRL_TYPE_HEVC_SLICE_PARAMS``
+      - n/a
+      - n/a
+      - n/a
+      - A struct :c:type:`v4l2_ctrl_hevc_slice_params`, containing HEVC
+	slice parameters for stateless video decoders.
 
 .. tabularcolumns:: |p{6.6cm}|p{2.2cm}|p{8.7cm}|
 
diff --git a/Documentation/media/uapi/v4l/vidioc-reqbufs.rst b/Documentation/media/uapi/v4l/vidioc-reqbufs.rst
index d7faef10e39b..d0c643db477a 100644
--- a/Documentation/media/uapi/v4l/vidioc-reqbufs.rst
+++ b/Documentation/media/uapi/v4l/vidioc-reqbufs.rst
@@ -125,6 +125,7 @@ aborting or finishing any DMA in progress, an implicit
 .. _V4L2-BUF-CAP-SUPPORTS-DMABUF:
 .. _V4L2-BUF-CAP-SUPPORTS-REQUESTS:
 .. _V4L2-BUF-CAP-SUPPORTS-ORPHANED-BUFS:
+.. _V4L2-BUF-CAP-SUPPORTS-M2M-HOLD-CAPTURE-BUF:
 
 .. cssclass:: longtable
 
@@ -150,6 +151,11 @@ aborting or finishing any DMA in progress, an implicit
       - The kernel allows calling :ref:`VIDIOC_REQBUFS` while buffers are still
         mapped or exported via DMABUF. These orphaned buffers will be freed
         when they are unmapped or when the exported DMABUF fds are closed.
+    * - ``V4L2_BUF_CAP_SUPPORTS_M2M_HOLD_CAPTURE_BUF``
+      - 0x00000020
+      - Only valid for stateless decoders. If set, then userspace can set the
+        ``V4L2_BUF_FLAG_M2M_HOLD_CAPTURE_BUF`` flag to hold off on returning the
+	capture buffer until the OUTPUT timestamp changes.
 
 Return Value
 ============
diff --git a/Documentation/media/v4l-drivers/imx.rst b/Documentation/media/v4l-drivers/imx.rst
index 1d7eb8c7bd5c..1246573c1019 100644
--- a/Documentation/media/v4l-drivers/imx.rst
+++ b/Documentation/media/v4l-drivers/imx.rst
@@ -515,10 +515,10 @@ Streaming can then begin independently on the capture device nodes
 be used to select any supported YUV pixelformat on the capture device
 nodes, including planar.
 
-SabreAuto with ADV7180 decoder
-------------------------------
+i.MX6Q SabreAuto with ADV7180 decoder
+-------------------------------------
 
-On the SabreAuto, an on-board ADV7180 SD decoder is connected to the
+On the i.MX6Q SabreAuto, an on-board ADV7180 SD decoder is connected to the
 parallel bus input on the internal video mux to IPU1 CSI0.
 
 The following example configures a pipeline to capture from the ADV7180
@@ -547,8 +547,6 @@ This example configures a pipeline to capture from the ADV7180
 video decoder, assuming PAL 720x576 input signals, with Motion
 Compensated de-interlacing. The adv7180 must output sequential or
 alternating fields (field type 'seq-tb' for PAL, or 'alternate').
-$outputfmt can be any format supported by the ipu1_ic_prpvf entity
-at its output pad:
 
 .. code-block:: none
 
@@ -565,11 +563,70 @@ at its output pad:
    media-ctl -V "'ipu1_csi0':1 [fmt:AYUV32/720x576]"
    media-ctl -V "'ipu1_vdic':2 [fmt:AYUV32/720x576 field:none]"
    media-ctl -V "'ipu1_ic_prp':2 [fmt:AYUV32/720x576 field:none]"
-   media-ctl -V "'ipu1_ic_prpvf':1 [fmt:$outputfmt field:none]"
+   media-ctl -V "'ipu1_ic_prpvf':1 [fmt:AYUV32/720x576 field:none]"
+   # Configure "ipu1_ic_prpvf capture" interface (assumed at /dev/video2)
+   v4l2-ctl -d2 --set-fmt-video=field=none
+
+Streaming can then begin on /dev/video2. The v4l2-ctl tool can also be
+used to select any supported YUV pixelformat on /dev/video2.
+
+This platform accepts Composite Video analog inputs to the ADV7180 on
+Ain1 (connector J42).
+
+i.MX6DL SabreAuto with ADV7180 decoder
+--------------------------------------
+
+On the i.MX6DL SabreAuto, an on-board ADV7180 SD decoder is connected to the
+parallel bus input on the internal video mux to IPU1 CSI0.
+
+The following example configures a pipeline to capture from the ADV7180
+video decoder, assuming NTSC 720x480 input signals, using simple
+interweave (unconverted and without motion compensation). The adv7180
+must output sequential or alternating fields (field type 'seq-bt' for
+NTSC, or 'alternate'):
+
+.. code-block:: none
+
+   # Setup links
+   media-ctl -l "'adv7180 4-0021':0 -> 'ipu1_csi0_mux':4[1]"
+   media-ctl -l "'ipu1_csi0_mux':5 -> 'ipu1_csi0':0[1]"
+   media-ctl -l "'ipu1_csi0':2 -> 'ipu1_csi0 capture':0[1]"
+   # Configure pads
+   media-ctl -V "'adv7180 4-0021':0 [fmt:UYVY2X8/720x480 field:seq-bt]"
+   media-ctl -V "'ipu1_csi0_mux':5 [fmt:UYVY2X8/720x480]"
+   media-ctl -V "'ipu1_csi0':2 [fmt:AYUV32/720x480]"
+   # Configure "ipu1_csi0 capture" interface (assumed at /dev/video0)
+   v4l2-ctl -d0 --set-fmt-video=field=interlaced_bt
+
+Streaming can then begin on /dev/video0. The v4l2-ctl tool can also be
+used to select any supported YUV pixelformat on /dev/video0.
+
+This example configures a pipeline to capture from the ADV7180
+video decoder, assuming PAL 720x576 input signals, with Motion
+Compensated de-interlacing. The adv7180 must output sequential or
+alternating fields (field type 'seq-tb' for PAL, or 'alternate').
+
+.. code-block:: none
+
+   # Setup links
+   media-ctl -l "'adv7180 4-0021':0 -> 'ipu1_csi0_mux':4[1]"
+   media-ctl -l "'ipu1_csi0_mux':5 -> 'ipu1_csi0':0[1]"
+   media-ctl -l "'ipu1_csi0':1 -> 'ipu1_vdic':0[1]"
+   media-ctl -l "'ipu1_vdic':2 -> 'ipu1_ic_prp':0[1]"
+   media-ctl -l "'ipu1_ic_prp':2 -> 'ipu1_ic_prpvf':0[1]"
+   media-ctl -l "'ipu1_ic_prpvf':1 -> 'ipu1_ic_prpvf capture':0[1]"
+   # Configure pads
+   media-ctl -V "'adv7180 4-0021':0 [fmt:UYVY2X8/720x576 field:seq-tb]"
+   media-ctl -V "'ipu1_csi0_mux':5 [fmt:UYVY2X8/720x576]"
+   media-ctl -V "'ipu1_csi0':1 [fmt:AYUV32/720x576]"
+   media-ctl -V "'ipu1_vdic':2 [fmt:AYUV32/720x576 field:none]"
+   media-ctl -V "'ipu1_ic_prp':2 [fmt:AYUV32/720x576 field:none]"
+   media-ctl -V "'ipu1_ic_prpvf':1 [fmt:AYUV32/720x576 field:none]"
+   # Configure "ipu1_ic_prpvf capture" interface (assumed at /dev/video2)
+   v4l2-ctl -d2 --set-fmt-video=field=none
 
-Streaming can then begin on the capture device node at
-"ipu1_ic_prpvf capture". The v4l2-ctl tool can be used to select any
-supported YUV or RGB pixelformat on the capture device node.
+Streaming can then begin on /dev/video2. The v4l2-ctl tool can also be
+used to select any supported YUV pixelformat on /dev/video2.
 
 This platform accepts Composite Video analog inputs to the ADV7180 on
 Ain1 (connector J42).
diff --git a/Documentation/media/v4l-drivers/ipu3.rst b/Documentation/media/v4l-drivers/ipu3.rst
index c9f780404eee..e4904ab44e60 100644
--- a/Documentation/media/v4l-drivers/ipu3.rst
+++ b/Documentation/media/v4l-drivers/ipu3.rst
@@ -265,19 +265,56 @@ below.
 
 yavta -w "0x009819A1 1" /dev/v4l-subdev7
 
-RAW Bayer frames go through the following ImgU pipeline HW blocks to have the
+Certain hardware blocks in ImgU pipeline can change the frame resolution by
+cropping or scaling, these hardware blocks include Input Feeder(IF), Bayer Down
+Scaler (BDS) and Geometric Distortion Correction (GDC).
+There is also a block which can change the frame resolution - YUV Scaler, it is
+only applicable to the secondary output.
+
+RAW Bayer frames go through these ImgU pipeline hardware blocks and the final
 processed image output to the DDR memory.
 
-RAW Bayer frame -> Input Feeder -> Bayer Down Scaling (BDS) -> Geometric
-Distortion Correction (GDC) -> DDR
+.. kernel-figure::  ipu3_rcb.svg
+   :alt: ipu3 resolution blocks image
 
-The ImgU V4L2 subdev has to be configured with the supported resolutions in all
-the above HW blocks, for a given input resolution.
+   IPU3 resolution change hardware blocks
+
+**Input Feeder**
+
+Input Feeder gets the Bayer frame data from the sensor, it can enable cropping
+of lines and columns from the frame and then store pixels into device's internal
+pixel buffer which are ready to readout by following blocks.
+
+**Bayer Down Scaler**
+
+Bayer Down Scaler is capable of performing image scaling in Bayer domain, the
+downscale factor can be configured from 1X to 1/4X in each axis with
+configuration steps of 0.03125 (1/32).
 
+**Geometric Distortion Correction**
+
+Geometric Distortion Correction is used to performe correction of distortions
+and image filtering. It needs some extra filter and envelop padding pixels to
+work, so the input resolution of GDC should be larger than the output
+resolution.
+
+**YUV Scaler**
+
+YUV Scaler which similar with BDS, but it is mainly do image down scaling in
+YUV domain, it can support up to 1/12X down scaling, but it can not be applied
+to the main output.
+
+The ImgU V4L2 subdev has to be configured with the supported resolutions in all
+the above hardware blocks, for a given input resolution.
 For a given supported resolution for an input frame, the Input Feeder, Bayer
-Down Scaling and GDC blocks should be configured with the supported resolutions.
-This information can be obtained by looking at the following IPU3 ImgU
-configuration table.
+Down Scaler and GDC blocks should be configured with the supported resolutions
+as each hardware block has its own alignment requirement.
+
+You must configure the output resolution of the hardware blocks smartly to meet
+the hardware requirement along with keeping the maximum field of view.
+The intermediate resolutions can be generated by specific tool and this
+information can be obtained by looking at the following IPU3 ImgU configuration
+table.
 
 https://chromium.googlesource.com/chromiumos/overlays/board-overlays/+/master
 
diff --git a/Documentation/media/v4l-drivers/ipu3_rcb.svg b/Documentation/media/v4l-drivers/ipu3_rcb.svg
new file mode 100644
index 000000000000..d878421b42a0
--- /dev/null
+++ b/Documentation/media/v4l-drivers/ipu3_rcb.svg
@@ -0,0 +1,331 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<svg xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" width="774pt" height="152pt" viewBox="0 0 774 152" version="1.1">
+<defs>
+<g>
+<symbol overflow="visible" id="glyph0-0">
+<path style="stroke:none;" d="M 1 0 L 1 -15 L 9 -15 L 9 0 Z M 8 -1 L 8 -14 L 2 -14 L 2 -1 Z M 8 -1 "/>
+</symbol>
+<symbol overflow="visible" id="glyph0-1">
+<path style="stroke:none;" d="M 4.6875 -1.15625 C 5.519531 -1.15625 6.15625 -1.316406 6.59375 -1.640625 C 7.039062 -1.960938 7.265625 -2.441406 7.265625 -3.078125 C 7.265625 -3.460938 7.179688 -3.789062 7.015625 -4.0625 C 6.859375 -4.34375 6.644531 -4.582031 6.375 -4.78125 C 6.113281 -4.988281 5.816406 -5.171875 5.484375 -5.328125 C 5.148438 -5.484375 4.804688 -5.628906 4.453125 -5.765625 C 4.054688 -5.921875 3.675781 -6.097656 3.3125 -6.296875 C 2.945312 -6.492188 2.617188 -6.726562 2.328125 -7 C 2.046875 -7.269531 1.820312 -7.582031 1.65625 -7.9375 C 1.488281 -8.300781 1.40625 -8.726562 1.40625 -9.21875 C 1.40625 -10.300781 1.742188 -11.144531 2.421875 -11.75 C 3.097656 -12.351562 4.046875 -12.65625 5.265625 -12.65625 C 5.597656 -12.65625 5.925781 -12.628906 6.25 -12.578125 C 6.570312 -12.535156 6.875 -12.476562 7.15625 -12.40625 C 7.4375 -12.34375 7.6875 -12.265625 7.90625 -12.171875 C 8.125 -12.085938 8.300781 -12 8.4375 -11.90625 L 7.921875 -10.515625 C 7.648438 -10.679688 7.28125 -10.84375 6.8125 -11 C 6.351562 -11.15625 5.835938 -11.234375 5.265625 -11.234375 C 4.660156 -11.234375 4.140625 -11.082031 3.703125 -10.78125 C 3.265625 -10.488281 3.046875 -10.039062 3.046875 -9.4375 C 3.046875 -9.09375 3.109375 -8.800781 3.234375 -8.5625 C 3.359375 -8.320312 3.53125 -8.109375 3.75 -7.921875 C 3.96875 -7.742188 4.222656 -7.582031 4.515625 -7.4375 C 4.804688 -7.289062 5.128906 -7.144531 5.484375 -7 C 5.984375 -6.789062 6.441406 -6.578125 6.859375 -6.359375 C 7.285156 -6.148438 7.648438 -5.894531 7.953125 -5.59375 C 8.253906 -5.300781 8.488281 -4.953125 8.65625 -4.546875 C 8.820312 -4.148438 8.90625 -3.664062 8.90625 -3.09375 C 8.90625 -2.019531 8.539062 -1.191406 7.8125 -0.609375 C 7.082031 -0.0234375 6.039062 0.265625 4.6875 0.265625 C 4.238281 0.265625 3.820312 0.234375 3.4375 0.171875 C 3.050781 0.109375 2.707031 0.03125 2.40625 -0.0625 C 2.101562 -0.15625 1.835938 -0.25 1.609375 -0.34375 C 1.390625 -0.4375 1.21875 -0.519531 1.09375 -0.59375 L 1.59375 -1.953125 C 1.863281 -1.804688 2.257812 -1.632812 2.78125 -1.4375 C 3.300781 -1.25 3.9375 -1.15625 4.6875 -1.15625 Z M 4.6875 -1.15625 "/>
+</symbol>
+<symbol overflow="visible" id="glyph0-2">
+<path style="stroke:none;" d="M 5.1875 -9.5 C 6.4375 -9.5 7.398438 -9.109375 8.078125 -8.328125 C 8.753906 -7.546875 9.09375 -6.363281 9.09375 -4.78125 L 9.09375 -4.203125 L 2.453125 -4.203125 C 2.523438 -3.242188 2.84375 -2.515625 3.40625 -2.015625 C 3.976562 -1.515625 4.773438 -1.265625 5.796875 -1.265625 C 6.390625 -1.265625 6.890625 -1.3125 7.296875 -1.40625 C 7.710938 -1.5 8.023438 -1.597656 8.234375 -1.703125 L 8.453125 -0.296875 C 8.253906 -0.191406 7.894531 -0.0820312 7.375 0.03125 C 6.851562 0.15625 6.269531 0.21875 5.625 0.21875 C 4.820312 0.21875 4.113281 0.0976562 3.5 -0.140625 C 2.894531 -0.390625 2.394531 -0.726562 2 -1.15625 C 1.601562 -1.582031 1.300781 -2.09375 1.09375 -2.6875 C 0.894531 -3.28125 0.796875 -3.925781 0.796875 -4.625 C 0.796875 -5.445312 0.921875 -6.164062 1.171875 -6.78125 C 1.429688 -7.394531 1.765625 -7.898438 2.171875 -8.296875 C 2.585938 -8.703125 3.054688 -9.003906 3.578125 -9.203125 C 4.097656 -9.398438 4.632812 -9.5 5.1875 -9.5 Z M 7.421875 -5.546875 C 7.421875 -6.328125 7.210938 -6.945312 6.796875 -7.40625 C 6.390625 -7.863281 5.84375 -8.09375 5.15625 -8.09375 C 4.769531 -8.09375 4.421875 -8.019531 4.109375 -7.875 C 3.796875 -7.726562 3.523438 -7.535156 3.296875 -7.296875 C 3.066406 -7.054688 2.882812 -6.78125 2.75 -6.46875 C 2.625 -6.164062 2.539062 -5.859375 2.5 -5.546875 Z M 7.421875 -5.546875 "/>
+</symbol>
+<symbol overflow="visible" id="glyph0-3">
+<path style="stroke:none;" d="M 1.421875 -9.015625 C 2.015625 -9.160156 2.609375 -9.273438 3.203125 -9.359375 C 3.796875 -9.441406 4.351562 -9.484375 4.875 -9.484375 C 6.113281 -9.484375 7.050781 -9.160156 7.6875 -8.515625 C 8.320312 -7.878906 8.640625 -6.851562 8.640625 -5.4375 L 8.640625 0 L 7 0 L 7 -5.140625 C 7 -5.742188 6.945312 -6.226562 6.84375 -6.59375 C 6.738281 -6.96875 6.585938 -7.257812 6.390625 -7.46875 C 6.191406 -7.675781 5.957031 -7.816406 5.6875 -7.890625 C 5.414062 -7.972656 5.117188 -8.015625 4.796875 -8.015625 C 4.535156 -8.015625 4.253906 -8 3.953125 -7.96875 C 3.648438 -7.9375 3.359375 -7.894531 3.078125 -7.84375 L 3.078125 0 L 1.421875 0 Z M 1.421875 -9.015625 "/>
+</symbol>
+<symbol overflow="visible" id="glyph0-4">
+<path style="stroke:none;" d="M 7.015625 -2.3125 C 7.015625 -2.644531 6.878906 -2.914062 6.609375 -3.125 C 6.335938 -3.34375 6 -3.53125 5.59375 -3.6875 C 5.1875 -3.851562 4.742188 -4.015625 4.265625 -4.171875 C 3.785156 -4.328125 3.335938 -4.515625 2.921875 -4.734375 C 2.515625 -4.960938 2.175781 -5.242188 1.90625 -5.578125 C 1.632812 -5.910156 1.5 -6.34375 1.5 -6.875 C 1.5 -7.625 1.800781 -8.25 2.40625 -8.75 C 3.007812 -9.25 3.960938 -9.5 5.265625 -9.5 C 5.765625 -9.5 6.285156 -9.460938 6.828125 -9.390625 C 7.367188 -9.316406 7.832031 -9.21875 8.21875 -9.09375 L 7.921875 -7.625 C 7.816406 -7.675781 7.671875 -7.726562 7.484375 -7.78125 C 7.296875 -7.84375 7.082031 -7.894531 6.84375 -7.9375 C 6.601562 -7.988281 6.34375 -8.023438 6.0625 -8.046875 C 5.789062 -8.078125 5.53125 -8.09375 5.28125 -8.09375 C 3.84375 -8.09375 3.125 -7.703125 3.125 -6.921875 C 3.125 -6.640625 3.257812 -6.398438 3.53125 -6.203125 C 3.800781 -6.015625 4.144531 -5.835938 4.5625 -5.671875 C 4.976562 -5.515625 5.425781 -5.351562 5.90625 -5.1875 C 6.382812 -5.019531 6.828125 -4.816406 7.234375 -4.578125 C 7.648438 -4.335938 7.992188 -4.046875 8.265625 -3.703125 C 8.546875 -3.367188 8.6875 -2.941406 8.6875 -2.421875 C 8.6875 -1.578125 8.359375 -0.925781 7.703125 -0.46875 C 7.046875 -0.0078125 6.007812 0.21875 4.59375 0.21875 C 3.957031 0.21875 3.375 0.164062 2.84375 0.0625 C 2.3125 -0.0390625 1.800781 -0.203125 1.3125 -0.421875 L 1.640625 -1.921875 C 2.109375 -1.703125 2.597656 -1.523438 3.109375 -1.390625 C 3.617188 -1.253906 4.171875 -1.1875 4.765625 -1.1875 C 6.265625 -1.1875 7.015625 -1.5625 7.015625 -2.3125 Z M 7.015625 -2.3125 "/>
+</symbol>
+<symbol overflow="visible" id="glyph0-5">
+<path style="stroke:none;" d="M 9.203125 -4.640625 C 9.203125 -3.910156 9.097656 -3.25 8.890625 -2.65625 C 8.679688 -2.0625 8.390625 -1.550781 8.015625 -1.125 C 7.640625 -0.695312 7.191406 -0.363281 6.671875 -0.125 C 6.160156 0.101562 5.597656 0.21875 4.984375 0.21875 C 4.378906 0.21875 3.820312 0.101562 3.3125 -0.125 C 2.800781 -0.363281 2.359375 -0.695312 1.984375 -1.125 C 1.609375 -1.550781 1.316406 -2.0625 1.109375 -2.65625 C 0.898438 -3.25 0.796875 -3.910156 0.796875 -4.640625 C 0.796875 -5.367188 0.898438 -6.035156 1.109375 -6.640625 C 1.316406 -7.242188 1.609375 -7.753906 1.984375 -8.171875 C 2.359375 -8.585938 2.800781 -8.910156 3.3125 -9.140625 C 3.820312 -9.378906 4.378906 -9.5 4.984375 -9.5 C 5.597656 -9.5 6.160156 -9.378906 6.671875 -9.140625 C 7.191406 -8.910156 7.640625 -8.585938 8.015625 -8.171875 C 8.390625 -7.753906 8.679688 -7.242188 8.890625 -6.640625 C 9.097656 -6.035156 9.203125 -5.367188 9.203125 -4.640625 Z M 7.5 -4.640625 C 7.5 -5.691406 7.269531 -6.519531 6.8125 -7.125 C 6.363281 -7.738281 5.753906 -8.046875 4.984375 -8.046875 C 4.222656 -8.046875 3.617188 -7.738281 3.171875 -7.125 C 2.722656 -6.519531 2.5 -5.691406 2.5 -4.640625 C 2.5 -3.597656 2.722656 -2.773438 3.171875 -2.171875 C 3.617188 -1.566406 4.222656 -1.265625 4.984375 -1.265625 C 5.753906 -1.265625 6.363281 -1.566406 6.8125 -2.171875 C 7.269531 -2.773438 7.5 -3.597656 7.5 -4.640625 Z M 7.5 -4.640625 "/>
+</symbol>
+<symbol overflow="visible" id="glyph0-6">
+<path style="stroke:none;" d="M 2.140625 0 L 2.140625 -8.78125 C 3.503906 -9.25 4.878906 -9.484375 6.265625 -9.484375 C 6.691406 -9.484375 7.097656 -9.460938 7.484375 -9.421875 C 7.867188 -9.390625 8.296875 -9.320312 8.765625 -9.21875 L 8.453125 -7.765625 C 8.023438 -7.878906 7.648438 -7.953125 7.328125 -7.984375 C 7.003906 -8.023438 6.648438 -8.046875 6.265625 -8.046875 C 5.453125 -8.046875 4.625 -7.929688 3.78125 -7.703125 L 3.78125 0 Z M 2.140625 0 "/>
+</symbol>
+<symbol overflow="visible" id="glyph0-7">
+<path style="stroke:none;" d="M 5.8125 -10.984375 L 5.8125 -1.40625 L 8.21875 -1.40625 L 8.21875 0 L 1.78125 0 L 1.78125 -1.40625 L 4.1875 -1.40625 L 4.1875 -10.984375 L 1.78125 -10.984375 L 1.78125 -12.375 L 8.21875 -12.375 L 8.21875 -10.984375 Z M 5.8125 -10.984375 "/>
+</symbol>
+<symbol overflow="visible" id="glyph0-8">
+<path style="stroke:none;" d="M 1.8125 0 L 1.8125 -12.375 L 8.84375 -12.375 L 8.84375 -10.984375 L 3.453125 -10.984375 L 3.453125 -7.125 L 8.203125 -7.125 L 8.203125 -5.734375 L 3.453125 -5.734375 L 3.453125 0 Z M 1.8125 0 "/>
+</symbol>
+<symbol overflow="visible" id="glyph0-9">
+<path style="stroke:none;" d="M 4.078125 0.09375 C 3.878906 0.09375 3.644531 0.0859375 3.375 0.078125 C 3.113281 0.0664062 2.847656 0.0507812 2.578125 0.03125 C 2.316406 0.0078125 2.050781 -0.0195312 1.78125 -0.0625 C 1.507812 -0.101562 1.273438 -0.148438 1.078125 -0.203125 L 1.078125 -12.203125 C 1.273438 -12.253906 1.503906 -12.300781 1.765625 -12.34375 C 2.023438 -12.382812 2.289062 -12.410156 2.5625 -12.421875 C 2.84375 -12.441406 3.113281 -12.457031 3.375 -12.46875 C 3.632812 -12.488281 3.867188 -12.5 4.078125 -12.5 C 4.691406 -12.5 5.265625 -12.445312 5.796875 -12.34375 C 6.328125 -12.238281 6.789062 -12.054688 7.1875 -11.796875 C 7.582031 -11.546875 7.890625 -11.210938 8.109375 -10.796875 C 8.328125 -10.390625 8.4375 -9.878906 8.4375 -9.265625 C 8.4375 -8.960938 8.390625 -8.675781 8.296875 -8.40625 C 8.203125 -8.132812 8.070312 -7.878906 7.90625 -7.640625 C 7.738281 -7.398438 7.546875 -7.1875 7.328125 -7 C 7.109375 -6.820312 6.875 -6.6875 6.625 -6.59375 C 7.300781 -6.40625 7.867188 -6.0625 8.328125 -5.5625 C 8.785156 -5.0625 9.015625 -4.414062 9.015625 -3.625 C 9.015625 -2.394531 8.617188 -1.46875 7.828125 -0.84375 C 7.046875 -0.21875 5.796875 0.09375 4.078125 0.09375 Z M 2.71875 -5.78125 L 2.71875 -1.359375 C 2.75 -1.347656 2.898438 -1.332031 3.171875 -1.3125 C 3.441406 -1.289062 3.785156 -1.28125 4.203125 -1.28125 C 4.609375 -1.28125 5 -1.3125 5.375 -1.375 C 5.757812 -1.445312 6.097656 -1.570312 6.390625 -1.75 C 6.691406 -1.925781 6.929688 -2.160156 7.109375 -2.453125 C 7.285156 -2.753906 7.375 -3.132812 7.375 -3.59375 C 7.375 -4.007812 7.289062 -4.359375 7.125 -4.640625 C 6.957031 -4.921875 6.738281 -5.144531 6.46875 -5.3125 C 6.195312 -5.476562 5.878906 -5.597656 5.515625 -5.671875 C 5.160156 -5.742188 4.789062 -5.78125 4.40625 -5.78125 Z M 2.71875 -7.140625 L 4.015625 -7.140625 C 4.347656 -7.140625 4.679688 -7.171875 5.015625 -7.234375 C 5.347656 -7.304688 5.644531 -7.414062 5.90625 -7.5625 C 6.175781 -7.707031 6.390625 -7.90625 6.546875 -8.15625 C 6.710938 -8.414062 6.796875 -8.738281 6.796875 -9.125 C 6.796875 -9.476562 6.722656 -9.78125 6.578125 -10.03125 C 6.429688 -10.289062 6.238281 -10.5 6 -10.65625 C 5.757812 -10.820312 5.484375 -10.9375 5.171875 -11 C 4.859375 -11.0625 4.53125 -11.09375 4.1875 -11.09375 C 3.832031 -11.09375 3.523438 -11.085938 3.265625 -11.078125 C 3.003906 -11.078125 2.820312 -11.066406 2.71875 -11.046875 Z M 2.71875 -7.140625 "/>
+</symbol>
+<symbol overflow="visible" id="glyph0-10">
+<path style="stroke:none;" d="M 9.203125 -6.203125 C 9.203125 -5.054688 9.054688 -4.082031 8.765625 -3.28125 C 8.484375 -2.476562 8.09375 -1.828125 7.59375 -1.328125 C 7.09375 -0.828125 6.5 -0.460938 5.8125 -0.234375 C 5.125 -0.015625 4.378906 0.09375 3.578125 0.09375 C 2.753906 0.09375 1.921875 -0.00390625 1.078125 -0.203125 L 1.078125 -12.203125 C 1.921875 -12.398438 2.753906 -12.5 3.578125 -12.5 C 4.378906 -12.5 5.125 -12.382812 5.8125 -12.15625 C 6.5 -11.925781 7.09375 -11.554688 7.59375 -11.046875 C 8.09375 -10.546875 8.484375 -9.894531 8.765625 -9.09375 C 9.054688 -8.300781 9.203125 -7.335938 9.203125 -6.203125 Z M 2.71875 -1.375 C 3.050781 -1.332031 3.390625 -1.3125 3.734375 -1.3125 C 4.335938 -1.3125 4.875 -1.398438 5.34375 -1.578125 C 5.8125 -1.765625 6.203125 -2.054688 6.515625 -2.453125 C 6.835938 -2.847656 7.082031 -3.351562 7.25 -3.96875 C 7.425781 -4.59375 7.515625 -5.335938 7.515625 -6.203125 C 7.515625 -7.878906 7.191406 -9.109375 6.546875 -9.890625 C 5.898438 -10.679688 4.945312 -11.078125 3.6875 -11.078125 C 3.507812 -11.078125 3.335938 -11.070312 3.171875 -11.0625 C 3.003906 -11.0625 2.851562 -11.046875 2.71875 -11.015625 Z M 2.71875 -1.375 "/>
+</symbol>
+<symbol overflow="visible" id="glyph0-11">
+<path style="stroke:none;" d="M 7.453125 -6.09375 L 9.09375 -6.09375 L 9.09375 -0.296875 C 8.84375 -0.203125 8.4375 -0.0859375 7.875 0.046875 C 7.320312 0.191406 6.664062 0.265625 5.90625 0.265625 C 5.15625 0.265625 4.472656 0.125 3.859375 -0.15625 C 3.242188 -0.445312 2.71875 -0.863281 2.28125 -1.40625 C 1.851562 -1.957031 1.519531 -2.632812 1.28125 -3.4375 C 1.039062 -4.25 0.921875 -5.171875 0.921875 -6.203125 C 0.921875 -7.242188 1.050781 -8.160156 1.3125 -8.953125 C 1.582031 -9.753906 1.945312 -10.425781 2.40625 -10.96875 C 2.863281 -11.519531 3.398438 -11.9375 4.015625 -12.21875 C 4.628906 -12.507812 5.289062 -12.65625 6 -12.65625 C 6.457031 -12.65625 6.859375 -12.617188 7.203125 -12.546875 C 7.546875 -12.484375 7.835938 -12.40625 8.078125 -12.3125 C 8.328125 -12.226562 8.53125 -12.132812 8.6875 -12.03125 C 8.851562 -11.925781 8.976562 -11.847656 9.0625 -11.796875 L 8.515625 -10.421875 C 8.210938 -10.660156 7.847656 -10.851562 7.421875 -11 C 7.003906 -11.15625 6.5625 -11.234375 6.09375 -11.234375 C 5.59375 -11.234375 5.125 -11.113281 4.6875 -10.875 C 4.257812 -10.632812 3.890625 -10.296875 3.578125 -9.859375 C 3.273438 -9.421875 3.035156 -8.890625 2.859375 -8.265625 C 2.679688 -7.648438 2.59375 -6.960938 2.59375 -6.203125 C 2.59375 -5.453125 2.671875 -4.769531 2.828125 -4.15625 C 2.984375 -3.539062 3.207031 -3.015625 3.5 -2.578125 C 3.789062 -2.140625 4.148438 -1.796875 4.578125 -1.546875 C 5.015625 -1.304688 5.515625 -1.1875 6.078125 -1.1875 C 6.460938 -1.1875 6.757812 -1.210938 6.96875 -1.265625 C 7.1875 -1.316406 7.347656 -1.367188 7.453125 -1.421875 Z M 7.453125 -6.09375 "/>
+</symbol>
+<symbol overflow="visible" id="glyph0-12">
+<path style="stroke:none;" d="M 9.203125 -0.515625 C 8.734375 -0.253906 8.234375 -0.0625 7.703125 0.0625 C 7.179688 0.195312 6.617188 0.265625 6.015625 0.265625 C 5.285156 0.265625 4.609375 0.132812 3.984375 -0.125 C 3.367188 -0.382812 2.832031 -0.773438 2.375 -1.296875 C 1.925781 -1.828125 1.570312 -2.5 1.3125 -3.3125 C 1.050781 -4.132812 0.921875 -5.097656 0.921875 -6.203125 C 0.921875 -7.253906 1.054688 -8.179688 1.328125 -8.984375 C 1.597656 -9.785156 1.96875 -10.457031 2.4375 -11 C 2.90625 -11.539062 3.453125 -11.953125 4.078125 -12.234375 C 4.703125 -12.515625 5.367188 -12.65625 6.078125 -12.65625 C 6.566406 -12.65625 7.066406 -12.585938 7.578125 -12.453125 C 8.097656 -12.328125 8.601562 -12.109375 9.09375 -11.796875 L 8.625 -10.4375 C 7.738281 -10.945312 6.910156 -11.203125 6.140625 -11.203125 C 5.585938 -11.203125 5.09375 -11.082031 4.65625 -10.84375 C 4.226562 -10.613281 3.859375 -10.28125 3.546875 -9.84375 C 3.242188 -9.40625 3.007812 -8.878906 2.84375 -8.265625 C 2.675781 -7.648438 2.59375 -6.960938 2.59375 -6.203125 C 2.59375 -5.347656 2.679688 -4.609375 2.859375 -3.984375 C 3.046875 -3.359375 3.296875 -2.835938 3.609375 -2.421875 C 3.929688 -2.003906 4.316406 -1.695312 4.765625 -1.5 C 5.210938 -1.300781 5.695312 -1.203125 6.21875 -1.203125 C 6.601562 -1.203125 7.007812 -1.25 7.4375 -1.34375 C 7.863281 -1.445312 8.304688 -1.625 8.765625 -1.875 Z M 9.203125 -0.515625 "/>
+</symbol>
+<symbol overflow="visible" id="glyph1-0">
+<path style="stroke:none;" d="M 0.59375 0 L 0.59375 -9 L 5.40625 -9 L 5.40625 0 Z M 4.796875 -0.59375 L 4.796875 -8.40625 L 1.203125 -8.40625 L 1.203125 -0.59375 Z M 4.796875 -0.59375 "/>
+</symbol>
+<symbol overflow="visible" id="glyph1-1">
+<path style="stroke:none;" d="M 2.515625 0 L 2.515625 -2.765625 C 2.023438 -3.554688 1.582031 -4.332031 1.1875 -5.09375 C 0.789062 -5.851562 0.445312 -6.628906 0.15625 -7.421875 L 1.265625 -7.421875 C 1.492188 -6.753906 1.757812 -6.113281 2.0625 -5.5 C 2.363281 -4.882812 2.6875 -4.253906 3.03125 -3.609375 C 3.394531 -4.285156 3.71875 -4.929688 4 -5.546875 C 4.28125 -6.160156 4.539062 -6.785156 4.78125 -7.421875 L 5.859375 -7.421875 C 5.554688 -6.640625 5.207031 -5.875 4.8125 -5.125 C 4.414062 -4.382812 3.976562 -3.601562 3.5 -2.78125 L 3.5 0 Z M 2.515625 0 "/>
+</symbol>
+<symbol overflow="visible" id="glyph1-2">
+<path style="stroke:none;" d="M 3 0.15625 C 2.5625 0.15625 2.1875 0.09375 1.875 -0.03125 C 1.570312 -0.164062 1.320312 -0.347656 1.125 -0.578125 C 0.9375 -0.804688 0.796875 -1.085938 0.703125 -1.421875 C 0.617188 -1.765625 0.578125 -2.144531 0.578125 -2.5625 L 0.578125 -7.421875 L 1.5625 -7.421875 L 1.5625 -2.65625 C 1.5625 -2.28125 1.59375 -1.96875 1.65625 -1.71875 C 1.726562 -1.46875 1.828125 -1.265625 1.953125 -1.109375 C 2.078125 -0.960938 2.222656 -0.859375 2.390625 -0.796875 C 2.566406 -0.734375 2.769531 -0.703125 3 -0.703125 C 3.226562 -0.703125 3.425781 -0.734375 3.59375 -0.796875 C 3.769531 -0.859375 3.921875 -0.960938 4.046875 -1.109375 C 4.171875 -1.265625 4.265625 -1.46875 4.328125 -1.71875 C 4.398438 -1.96875 4.4375 -2.28125 4.4375 -2.65625 L 4.4375 -7.421875 L 5.421875 -7.421875 L 5.421875 -2.5625 C 5.421875 -2.144531 5.375 -1.765625 5.28125 -1.421875 C 5.195312 -1.085938 5.054688 -0.804688 4.859375 -0.578125 C 4.671875 -0.347656 4.421875 -0.164062 4.109375 -0.03125 C 3.804688 0.09375 3.4375 0.15625 3 0.15625 Z M 3 0.15625 "/>
+</symbol>
+<symbol overflow="visible" id="glyph1-3">
+<path style="stroke:none;" d="M 1.21875 -7.421875 C 1.320312 -6.921875 1.445312 -6.375 1.59375 -5.78125 C 1.738281 -5.1875 1.890625 -4.585938 2.046875 -3.984375 C 2.210938 -3.390625 2.378906 -2.820312 2.546875 -2.28125 C 2.722656 -1.738281 2.882812 -1.265625 3.03125 -0.859375 C 3.15625 -1.265625 3.300781 -1.742188 3.46875 -2.296875 C 3.644531 -2.847656 3.816406 -3.421875 3.984375 -4.015625 C 4.148438 -4.609375 4.304688 -5.203125 4.453125 -5.796875 C 4.609375 -6.390625 4.734375 -6.929688 4.828125 -7.421875 L 5.859375 -7.421875 C 5.796875 -7.109375 5.691406 -6.679688 5.546875 -6.140625 C 5.398438 -5.597656 5.226562 -4.992188 5.03125 -4.328125 C 4.832031 -3.660156 4.609375 -2.953125 4.359375 -2.203125 C 4.117188 -1.453125 3.863281 -0.71875 3.59375 0 L 2.375 0 C 2.125 -0.71875 1.878906 -1.445312 1.640625 -2.1875 C 1.410156 -2.9375 1.195312 -3.644531 1 -4.3125 C 0.800781 -4.976562 0.628906 -5.582031 0.484375 -6.125 C 0.335938 -6.675781 0.226562 -7.109375 0.15625 -7.421875 Z M 1.21875 -7.421875 "/>
+</symbol>
+<symbol overflow="visible" id="glyph1-4">
+<path style="stroke:none;" d=""/>
+</symbol>
+<symbol overflow="visible" id="glyph1-5">
+<path style="stroke:none;" d="M 5.515625 -3.71875 C 5.515625 -3.03125 5.425781 -2.445312 5.25 -1.96875 C 5.082031 -1.488281 4.847656 -1.097656 4.546875 -0.796875 C 4.253906 -0.492188 3.898438 -0.273438 3.484375 -0.140625 C 3.078125 -0.00390625 2.628906 0.0625 2.140625 0.0625 C 1.648438 0.0625 1.148438 0 0.640625 -0.125 L 0.640625 -7.3125 C 1.148438 -7.4375 1.648438 -7.5 2.140625 -7.5 C 2.628906 -7.5 3.078125 -7.429688 3.484375 -7.296875 C 3.898438 -7.160156 4.253906 -6.941406 4.546875 -6.640625 C 4.847656 -6.335938 5.082031 -5.941406 5.25 -5.453125 C 5.425781 -4.972656 5.515625 -4.394531 5.515625 -3.71875 Z M 1.625 -0.828125 C 1.832031 -0.804688 2.039062 -0.796875 2.25 -0.796875 C 2.601562 -0.796875 2.921875 -0.847656 3.203125 -0.953125 C 3.484375 -1.054688 3.71875 -1.226562 3.90625 -1.46875 C 4.101562 -1.707031 4.253906 -2.007812 4.359375 -2.375 C 4.460938 -2.75 4.515625 -3.195312 4.515625 -3.71875 C 4.515625 -4.726562 4.316406 -5.46875 3.921875 -5.9375 C 3.535156 -6.40625 2.960938 -6.640625 2.203125 -6.640625 C 2.097656 -6.640625 1.992188 -6.640625 1.890625 -6.640625 C 1.796875 -6.640625 1.707031 -6.628906 1.625 -6.609375 Z M 1.625 -0.828125 "/>
+</symbol>
+<symbol overflow="visible" id="glyph1-6">
+<path style="stroke:none;" d="M 5.515625 -2.78125 C 5.515625 -2.34375 5.453125 -1.945312 5.328125 -1.59375 C 5.203125 -1.238281 5.023438 -0.929688 4.796875 -0.671875 C 4.578125 -0.410156 4.3125 -0.210938 4 -0.078125 C 3.695312 0.0546875 3.359375 0.125 2.984375 0.125 C 2.628906 0.125 2.296875 0.0546875 1.984375 -0.078125 C 1.679688 -0.210938 1.414062 -0.410156 1.1875 -0.671875 C 0.96875 -0.929688 0.796875 -1.238281 0.671875 -1.59375 C 0.546875 -1.945312 0.484375 -2.34375 0.484375 -2.78125 C 0.484375 -3.21875 0.546875 -3.617188 0.671875 -3.984375 C 0.796875 -4.347656 0.96875 -4.65625 1.1875 -4.90625 C 1.414062 -5.15625 1.679688 -5.347656 1.984375 -5.484375 C 2.296875 -5.628906 2.628906 -5.703125 2.984375 -5.703125 C 3.359375 -5.703125 3.695312 -5.628906 4 -5.484375 C 4.3125 -5.347656 4.578125 -5.15625 4.796875 -4.90625 C 5.023438 -4.65625 5.203125 -4.347656 5.328125 -3.984375 C 5.453125 -3.617188 5.515625 -3.21875 5.515625 -2.78125 Z M 4.5 -2.78125 C 4.5 -3.414062 4.363281 -3.914062 4.09375 -4.28125 C 3.820312 -4.644531 3.453125 -4.828125 2.984375 -4.828125 C 2.523438 -4.828125 2.160156 -4.644531 1.890625 -4.28125 C 1.628906 -3.914062 1.5 -3.414062 1.5 -2.78125 C 1.5 -2.15625 1.628906 -1.660156 1.890625 -1.296875 C 2.160156 -0.929688 2.523438 -0.75 2.984375 -0.75 C 3.453125 -0.75 3.820312 -0.929688 4.09375 -1.296875 C 4.363281 -1.660156 4.5 -2.15625 4.5 -2.78125 Z M 4.5 -2.78125 "/>
+</symbol>
+<symbol overflow="visible" id="glyph1-7">
+<path style="stroke:none;" d="M 4.109375 0 C 3.992188 -0.269531 3.890625 -0.515625 3.796875 -0.734375 C 3.710938 -0.960938 3.628906 -1.1875 3.546875 -1.40625 C 3.460938 -1.632812 3.378906 -1.867188 3.296875 -2.109375 C 3.210938 -2.359375 3.113281 -2.640625 3 -2.953125 C 2.882812 -2.640625 2.78125 -2.359375 2.6875 -2.109375 C 2.601562 -1.867188 2.519531 -1.632812 2.4375 -1.40625 C 2.351562 -1.1875 2.265625 -0.960938 2.171875 -0.734375 C 2.085938 -0.515625 1.984375 -0.269531 1.859375 0 L 1.109375 0 C 0.890625 -0.976562 0.707031 -1.953125 0.5625 -2.921875 C 0.414062 -3.890625 0.304688 -4.769531 0.234375 -5.5625 L 1.15625 -5.5625 C 1.1875 -5.25 1.210938 -4.941406 1.234375 -4.640625 C 1.265625 -4.347656 1.300781 -4.035156 1.34375 -3.703125 C 1.382812 -3.378906 1.429688 -3.023438 1.484375 -2.640625 C 1.535156 -2.253906 1.59375 -1.820312 1.65625 -1.34375 C 1.78125 -1.664062 1.882812 -1.945312 1.96875 -2.1875 C 2.0625 -2.425781 2.144531 -2.648438 2.21875 -2.859375 C 2.289062 -3.078125 2.359375 -3.296875 2.421875 -3.515625 C 2.492188 -3.742188 2.570312 -4 2.65625 -4.28125 L 3.390625 -4.28125 C 3.472656 -4 3.546875 -3.742188 3.609375 -3.515625 C 3.671875 -3.296875 3.738281 -3.078125 3.8125 -2.859375 C 3.882812 -2.648438 3.957031 -2.425781 4.03125 -2.1875 C 4.113281 -1.945312 4.21875 -1.671875 4.34375 -1.359375 C 4.414062 -1.796875 4.476562 -2.203125 4.53125 -2.578125 C 4.59375 -2.953125 4.640625 -3.304688 4.671875 -3.640625 C 4.710938 -3.972656 4.75 -4.296875 4.78125 -4.609375 C 4.820312 -4.921875 4.851562 -5.238281 4.875 -5.5625 L 5.765625 -5.5625 C 5.734375 -5.164062 5.6875 -4.738281 5.625 -4.28125 C 5.570312 -3.820312 5.503906 -3.351562 5.421875 -2.875 C 5.335938 -2.394531 5.25 -1.910156 5.15625 -1.421875 C 5.0625 -0.929688 4.960938 -0.457031 4.859375 0 Z M 4.109375 0 "/>
+</symbol>
+<symbol overflow="visible" id="glyph1-8">
+<path style="stroke:none;" d="M 0.859375 -5.40625 C 1.210938 -5.5 1.566406 -5.566406 1.921875 -5.609375 C 2.273438 -5.660156 2.609375 -5.6875 2.921875 -5.6875 C 3.671875 -5.6875 4.234375 -5.492188 4.609375 -5.109375 C 4.992188 -4.722656 5.1875 -4.109375 5.1875 -3.265625 L 5.1875 0 L 4.203125 0 L 4.203125 -3.078125 C 4.203125 -3.441406 4.171875 -3.734375 4.109375 -3.953125 C 4.046875 -4.179688 3.953125 -4.359375 3.828125 -4.484375 C 3.710938 -4.609375 3.570312 -4.691406 3.40625 -4.734375 C 3.25 -4.785156 3.070312 -4.8125 2.875 -4.8125 C 2.71875 -4.8125 2.546875 -4.800781 2.359375 -4.78125 C 2.179688 -4.757812 2.007812 -4.734375 1.84375 -4.703125 L 1.84375 0 L 0.859375 0 Z M 0.859375 -5.40625 "/>
+</symbol>
+<symbol overflow="visible" id="glyph1-9">
+<path style="stroke:none;" d="M 4.21875 -1.390625 C 4.21875 -1.585938 4.132812 -1.75 3.96875 -1.875 C 3.800781 -2.007812 3.59375 -2.125 3.34375 -2.21875 C 3.101562 -2.3125 2.835938 -2.40625 2.546875 -2.5 C 2.265625 -2.59375 2 -2.707031 1.75 -2.84375 C 1.507812 -2.976562 1.304688 -3.144531 1.140625 -3.34375 C 0.984375 -3.539062 0.90625 -3.800781 0.90625 -4.125 C 0.90625 -4.570312 1.082031 -4.945312 1.4375 -5.25 C 1.800781 -5.550781 2.375 -5.703125 3.15625 -5.703125 C 3.457031 -5.703125 3.769531 -5.675781 4.09375 -5.625 C 4.414062 -5.582031 4.695312 -5.523438 4.9375 -5.453125 L 4.75 -4.578125 C 4.6875 -4.609375 4.597656 -4.640625 4.484375 -4.671875 C 4.367188 -4.710938 4.238281 -4.742188 4.09375 -4.765625 C 3.957031 -4.796875 3.804688 -4.816406 3.640625 -4.828125 C 3.472656 -4.847656 3.316406 -4.859375 3.171875 -4.859375 C 2.304688 -4.859375 1.875 -4.625 1.875 -4.15625 C 1.875 -3.988281 1.953125 -3.84375 2.109375 -3.71875 C 2.273438 -3.601562 2.484375 -3.5 2.734375 -3.40625 C 2.984375 -3.3125 3.25 -3.210938 3.53125 -3.109375 C 3.820312 -3.015625 4.09375 -2.894531 4.34375 -2.75 C 4.59375 -2.601562 4.796875 -2.425781 4.953125 -2.21875 C 5.117188 -2.019531 5.203125 -1.765625 5.203125 -1.453125 C 5.203125 -0.953125 5.003906 -0.5625 4.609375 -0.28125 C 4.222656 -0.0078125 3.609375 0.125 2.765625 0.125 C 2.378906 0.125 2.023438 0.09375 1.703125 0.03125 C 1.378906 -0.03125 1.078125 -0.125 0.796875 -0.25 L 0.984375 -1.15625 C 1.265625 -1.019531 1.554688 -0.910156 1.859375 -0.828125 C 2.171875 -0.742188 2.503906 -0.703125 2.859375 -0.703125 C 3.765625 -0.703125 4.21875 -0.929688 4.21875 -1.390625 Z M 4.21875 -1.390625 "/>
+</symbol>
+<symbol overflow="visible" id="glyph1-10">
+<path style="stroke:none;" d="M 0.59375 -2.765625 C 0.59375 -3.273438 0.671875 -3.710938 0.828125 -4.078125 C 0.984375 -4.441406 1.203125 -4.742188 1.484375 -4.984375 C 1.765625 -5.234375 2.09375 -5.414062 2.46875 -5.53125 C 2.84375 -5.644531 3.238281 -5.703125 3.65625 -5.703125 C 3.925781 -5.703125 4.195312 -5.679688 4.46875 -5.640625 C 4.738281 -5.609375 5.023438 -5.546875 5.328125 -5.453125 L 5.09375 -4.59375 C 4.832031 -4.6875 4.59375 -4.75 4.375 -4.78125 C 4.15625 -4.8125 3.929688 -4.828125 3.703125 -4.828125 C 3.421875 -4.828125 3.148438 -4.785156 2.890625 -4.703125 C 2.640625 -4.628906 2.414062 -4.507812 2.21875 -4.34375 C 2.03125 -4.1875 1.878906 -3.976562 1.765625 -3.71875 C 1.660156 -3.457031 1.609375 -3.140625 1.609375 -2.765625 C 1.609375 -2.421875 1.660156 -2.117188 1.765625 -1.859375 C 1.867188 -1.609375 2.015625 -1.398438 2.203125 -1.234375 C 2.390625 -1.078125 2.613281 -0.957031 2.875 -0.875 C 3.144531 -0.789062 3.4375 -0.75 3.75 -0.75 C 4.007812 -0.75 4.253906 -0.765625 4.484375 -0.796875 C 4.722656 -0.828125 4.984375 -0.890625 5.265625 -0.984375 L 5.40625 -0.15625 C 5.125 -0.0507812 4.835938 0.0195312 4.546875 0.0625 C 4.265625 0.101562 3.957031 0.125 3.625 0.125 C 3.175781 0.125 2.765625 0.0664062 2.390625 -0.046875 C 2.023438 -0.171875 1.707031 -0.351562 1.4375 -0.59375 C 1.164062 -0.832031 0.957031 -1.132812 0.8125 -1.5 C 0.664062 -1.863281 0.59375 -2.285156 0.59375 -2.765625 Z M 0.59375 -2.765625 "/>
+</symbol>
+<symbol overflow="visible" id="glyph1-11">
+<path style="stroke:none;" d="M 3.0625 -0.703125 C 3.3125 -0.703125 3.53125 -0.707031 3.71875 -0.71875 C 3.914062 -0.738281 4.082031 -0.765625 4.21875 -0.796875 L 4.21875 -2.453125 C 4.082031 -2.492188 3.925781 -2.523438 3.75 -2.546875 C 3.570312 -2.566406 3.382812 -2.578125 3.1875 -2.578125 C 3 -2.578125 2.816406 -2.5625 2.640625 -2.53125 C 2.460938 -2.507812 2.304688 -2.460938 2.171875 -2.390625 C 2.035156 -2.316406 1.921875 -2.222656 1.828125 -2.109375 C 1.742188 -1.992188 1.703125 -1.847656 1.703125 -1.671875 C 1.703125 -1.304688 1.820312 -1.050781 2.0625 -0.90625 C 2.3125 -0.769531 2.644531 -0.703125 3.0625 -0.703125 Z M 2.96875 -5.703125 C 3.382812 -5.703125 3.734375 -5.648438 4.015625 -5.546875 C 4.296875 -5.441406 4.523438 -5.296875 4.703125 -5.109375 C 4.878906 -4.929688 5.003906 -4.707031 5.078125 -4.4375 C 5.148438 -4.175781 5.1875 -3.890625 5.1875 -3.578125 L 5.1875 -0.09375 C 4.957031 -0.0507812 4.648438 -0.00390625 4.265625 0.046875 C 3.890625 0.0976562 3.5 0.125 3.09375 0.125 C 2.789062 0.125 2.492188 0.0976562 2.203125 0.046875 C 1.921875 -0.00390625 1.664062 -0.09375 1.4375 -0.21875 C 1.21875 -0.351562 1.039062 -0.535156 0.90625 -0.765625 C 0.769531 -0.992188 0.703125 -1.289062 0.703125 -1.65625 C 0.703125 -1.976562 0.769531 -2.25 0.90625 -2.46875 C 1.039062 -2.6875 1.21875 -2.863281 1.4375 -3 C 1.664062 -3.132812 1.921875 -3.234375 2.203125 -3.296875 C 2.484375 -3.359375 2.769531 -3.390625 3.0625 -3.390625 C 3.445312 -3.390625 3.832031 -3.34375 4.21875 -3.25 L 4.21875 -3.53125 C 4.21875 -3.695312 4.195312 -3.859375 4.15625 -4.015625 C 4.125 -4.171875 4.054688 -4.3125 3.953125 -4.4375 C 3.847656 -4.5625 3.707031 -4.660156 3.53125 -4.734375 C 3.363281 -4.816406 3.144531 -4.859375 2.875 -4.859375 C 2.53125 -4.859375 2.226562 -4.832031 1.96875 -4.78125 C 1.71875 -4.738281 1.523438 -4.691406 1.390625 -4.640625 L 1.265625 -5.453125 C 1.398438 -5.523438 1.625 -5.582031 1.9375 -5.625 C 2.257812 -5.675781 2.601562 -5.703125 2.96875 -5.703125 Z M 2.96875 -5.703125 "/>
+</symbol>
+<symbol overflow="visible" id="glyph1-12">
+<path style="stroke:none;" d="M 4.0625 0.125 C 3.707031 0.125 3.410156 0.078125 3.171875 -0.015625 C 2.941406 -0.109375 2.757812 -0.25 2.625 -0.4375 C 2.488281 -0.632812 2.390625 -0.875 2.328125 -1.15625 C 2.273438 -1.4375 2.25 -1.765625 2.25 -2.140625 L 2.25 -7.421875 L 0.640625 -7.421875 L 0.640625 -8.25 L 3.234375 -8.25 L 3.234375 -2.140625 C 3.234375 -1.867188 3.25 -1.644531 3.28125 -1.46875 C 3.320312 -1.289062 3.378906 -1.144531 3.453125 -1.03125 C 3.535156 -0.925781 3.628906 -0.851562 3.734375 -0.8125 C 3.847656 -0.769531 3.984375 -0.75 4.140625 -0.75 C 4.367188 -0.75 4.582031 -0.773438 4.78125 -0.828125 C 4.988281 -0.890625 5.144531 -0.953125 5.25 -1.015625 L 5.40625 -0.1875 C 5.351562 -0.15625 5.28125 -0.117188 5.1875 -0.078125 C 5.101562 -0.046875 5 -0.015625 4.875 0.015625 C 4.757812 0.046875 4.628906 0.0703125 4.484375 0.09375 C 4.347656 0.113281 4.207031 0.125 4.0625 0.125 Z M 4.0625 0.125 "/>
+</symbol>
+<symbol overflow="visible" id="glyph1-13">
+<path style="stroke:none;" d="M 2.515625 -6.4375 C 2.304688 -6.4375 2.125 -6.503906 1.96875 -6.640625 C 1.8125 -6.785156 1.734375 -6.984375 1.734375 -7.234375 C 1.734375 -7.484375 1.8125 -7.679688 1.96875 -7.828125 C 2.125 -7.972656 2.304688 -8.046875 2.515625 -8.046875 C 2.722656 -8.046875 2.898438 -7.972656 3.046875 -7.828125 C 3.203125 -7.679688 3.28125 -7.484375 3.28125 -7.234375 C 3.28125 -6.984375 3.203125 -6.785156 3.046875 -6.640625 C 2.898438 -6.503906 2.722656 -6.4375 2.515625 -6.4375 Z M 2.25 -4.734375 L 0.640625 -4.734375 L 0.640625 -5.5625 L 3.234375 -5.5625 L 3.234375 -2.140625 C 3.234375 -1.585938 3.3125 -1.21875 3.46875 -1.03125 C 3.625 -0.84375 3.851562 -0.75 4.15625 -0.75 C 4.382812 -0.75 4.597656 -0.773438 4.796875 -0.828125 C 4.992188 -0.890625 5.144531 -0.953125 5.25 -1.015625 L 5.40625 -0.1875 C 5.351562 -0.15625 5.28125 -0.117188 5.1875 -0.078125 C 5.101562 -0.046875 5.003906 -0.015625 4.890625 0.015625 C 4.773438 0.046875 4.644531 0.0703125 4.5 0.09375 C 4.363281 0.113281 4.21875 0.125 4.0625 0.125 C 3.71875 0.125 3.425781 0.078125 3.1875 -0.015625 C 2.957031 -0.109375 2.769531 -0.25 2.625 -0.4375 C 2.488281 -0.632812 2.390625 -0.875 2.328125 -1.15625 C 2.273438 -1.4375 2.25 -1.765625 2.25 -2.140625 Z M 2.25 -4.734375 "/>
+</symbol>
+<symbol overflow="visible" id="glyph1-14">
+<path style="stroke:none;" d="M 4.15625 -0.515625 C 4.039062 -0.453125 3.863281 -0.382812 3.625 -0.3125 C 3.394531 -0.238281 3.128906 -0.203125 2.828125 -0.203125 C 2.503906 -0.203125 2.195312 -0.253906 1.90625 -0.359375 C 1.625 -0.472656 1.378906 -0.640625 1.171875 -0.859375 C 0.960938 -1.078125 0.796875 -1.351562 0.671875 -1.6875 C 0.546875 -2.03125 0.484375 -2.4375 0.484375 -2.90625 C 0.484375 -3.3125 0.539062 -3.679688 0.65625 -4.015625 C 0.769531 -4.359375 0.9375 -4.65625 1.15625 -4.90625 C 1.375 -5.15625 1.644531 -5.347656 1.96875 -5.484375 C 2.289062 -5.628906 2.65625 -5.703125 3.0625 -5.703125 C 3.539062 -5.703125 3.945312 -5.664062 4.28125 -5.59375 C 4.625 -5.53125 4.910156 -5.46875 5.140625 -5.40625 L 5.140625 -0.4375 C 5.140625 0.425781 4.921875 1.050781 4.484375 1.4375 C 4.054688 1.820312 3.398438 2.015625 2.515625 2.015625 C 2.160156 2.015625 1.835938 1.984375 1.546875 1.921875 C 1.253906 1.867188 0.992188 1.804688 0.765625 1.734375 L 0.953125 0.859375 C 1.160156 0.941406 1.394531 1.007812 1.65625 1.0625 C 1.925781 1.125 2.222656 1.15625 2.546875 1.15625 C 3.117188 1.15625 3.53125 1.035156 3.78125 0.796875 C 4.03125 0.566406 4.15625 0.191406 4.15625 -0.328125 Z M 4.15625 -4.6875 C 4.0625 -4.71875 3.925781 -4.75 3.75 -4.78125 C 3.582031 -4.8125 3.359375 -4.828125 3.078125 -4.828125 C 2.554688 -4.828125 2.160156 -4.648438 1.890625 -4.296875 C 1.628906 -3.941406 1.5 -3.472656 1.5 -2.890625 C 1.5 -2.566406 1.535156 -2.289062 1.609375 -2.0625 C 1.691406 -1.84375 1.796875 -1.65625 1.921875 -1.5 C 2.054688 -1.351562 2.207031 -1.242188 2.375 -1.171875 C 2.539062 -1.109375 2.722656 -1.078125 2.921875 -1.078125 C 3.160156 -1.078125 3.390625 -1.113281 3.609375 -1.1875 C 3.835938 -1.257812 4.019531 -1.34375 4.15625 -1.4375 Z M 4.15625 -4.6875 "/>
+</symbol>
+<symbol overflow="visible" id="glyph1-15">
+<path style="stroke:none;" d="M 2.8125 -0.703125 C 3.3125 -0.703125 3.691406 -0.796875 3.953125 -0.984375 C 4.222656 -1.171875 4.359375 -1.457031 4.359375 -1.84375 C 4.359375 -2.082031 4.304688 -2.28125 4.203125 -2.4375 C 4.109375 -2.601562 3.984375 -2.75 3.828125 -2.875 C 3.671875 -3 3.488281 -3.109375 3.28125 -3.203125 C 3.082031 -3.296875 2.878906 -3.378906 2.671875 -3.453125 C 2.429688 -3.546875 2.203125 -3.648438 1.984375 -3.765625 C 1.765625 -3.890625 1.566406 -4.03125 1.390625 -4.1875 C 1.222656 -4.351562 1.085938 -4.546875 0.984375 -4.765625 C 0.890625 -4.984375 0.84375 -5.238281 0.84375 -5.53125 C 0.84375 -6.175781 1.046875 -6.679688 1.453125 -7.046875 C 1.859375 -7.410156 2.425781 -7.59375 3.15625 -7.59375 C 3.351562 -7.59375 3.550781 -7.578125 3.75 -7.546875 C 3.945312 -7.523438 4.128906 -7.492188 4.296875 -7.453125 C 4.460938 -7.410156 4.609375 -7.359375 4.734375 -7.296875 C 4.867188 -7.242188 4.976562 -7.191406 5.0625 -7.140625 L 4.75 -6.3125 C 4.59375 -6.40625 4.375 -6.5 4.09375 -6.59375 C 3.8125 -6.695312 3.5 -6.75 3.15625 -6.75 C 2.789062 -6.75 2.476562 -6.65625 2.21875 -6.46875 C 1.957031 -6.289062 1.828125 -6.019531 1.828125 -5.65625 C 1.828125 -5.457031 1.863281 -5.285156 1.9375 -5.140625 C 2.007812 -4.992188 2.113281 -4.863281 2.25 -4.75 C 2.382812 -4.644531 2.535156 -4.546875 2.703125 -4.453125 C 2.878906 -4.367188 3.070312 -4.285156 3.28125 -4.203125 C 3.59375 -4.078125 3.875 -3.945312 4.125 -3.8125 C 4.375 -3.6875 4.585938 -3.535156 4.765625 -3.359375 C 4.953125 -3.179688 5.09375 -2.972656 5.1875 -2.734375 C 5.289062 -2.492188 5.34375 -2.203125 5.34375 -1.859375 C 5.34375 -1.210938 5.125 -0.710938 4.6875 -0.359375 C 4.25 -0.015625 3.625 0.15625 2.8125 0.15625 C 2.539062 0.15625 2.289062 0.132812 2.0625 0.09375 C 1.832031 0.0625 1.625 0.0195312 1.4375 -0.03125 C 1.257812 -0.09375 1.101562 -0.148438 0.96875 -0.203125 C 0.832031 -0.253906 0.726562 -0.304688 0.65625 -0.359375 L 0.953125 -1.171875 C 1.117188 -1.085938 1.359375 -0.988281 1.671875 -0.875 C 1.984375 -0.757812 2.363281 -0.703125 2.8125 -0.703125 Z M 2.8125 -0.703125 "/>
+</symbol>
+<symbol overflow="visible" id="glyph1-16">
+<path style="stroke:none;" d="M 3.109375 -5.703125 C 3.859375 -5.703125 4.4375 -5.46875 4.84375 -5 C 5.25 -4.53125 5.453125 -3.820312 5.453125 -2.875 L 5.453125 -2.515625 L 1.46875 -2.515625 C 1.507812 -1.941406 1.703125 -1.503906 2.046875 -1.203125 C 2.390625 -0.898438 2.867188 -0.75 3.484375 -0.75 C 3.835938 -0.75 4.132812 -0.773438 4.375 -0.828125 C 4.625 -0.890625 4.8125 -0.953125 4.9375 -1.015625 L 5.078125 -0.1875 C 4.953125 -0.113281 4.734375 -0.046875 4.421875 0.015625 C 4.109375 0.0859375 3.757812 0.125 3.375 0.125 C 2.894531 0.125 2.472656 0.0507812 2.109375 -0.09375 C 1.742188 -0.238281 1.441406 -0.4375 1.203125 -0.6875 C 0.960938 -0.945312 0.78125 -1.253906 0.65625 -1.609375 C 0.539062 -1.960938 0.484375 -2.347656 0.484375 -2.765625 C 0.484375 -3.265625 0.554688 -3.695312 0.703125 -4.0625 C 0.859375 -4.4375 1.0625 -4.742188 1.3125 -4.984375 C 1.5625 -5.222656 1.835938 -5.398438 2.140625 -5.515625 C 2.453125 -5.640625 2.773438 -5.703125 3.109375 -5.703125 Z M 4.453125 -3.328125 C 4.453125 -3.796875 4.328125 -4.164062 4.078125 -4.4375 C 3.828125 -4.71875 3.5 -4.859375 3.09375 -4.859375 C 2.863281 -4.859375 2.65625 -4.8125 2.46875 -4.71875 C 2.28125 -4.632812 2.117188 -4.519531 1.984375 -4.375 C 1.847656 -4.226562 1.738281 -4.0625 1.65625 -3.875 C 1.570312 -3.695312 1.519531 -3.515625 1.5 -3.328125 Z M 4.453125 -3.328125 "/>
+</symbol>
+<symbol overflow="visible" id="glyph1-17">
+<path style="stroke:none;" d="M 4.15625 -4.390625 C 4.039062 -4.492188 3.875 -4.59375 3.65625 -4.6875 C 3.445312 -4.78125 3.222656 -4.828125 2.984375 -4.828125 C 2.722656 -4.828125 2.5 -4.773438 2.3125 -4.671875 C 2.125 -4.566406 1.96875 -4.421875 1.84375 -4.234375 C 1.726562 -4.054688 1.640625 -3.84375 1.578125 -3.59375 C 1.523438 -3.34375 1.5 -3.070312 1.5 -2.78125 C 1.5 -2.132812 1.648438 -1.632812 1.953125 -1.28125 C 2.253906 -0.925781 2.648438 -0.75 3.140625 -0.75 C 3.390625 -0.75 3.597656 -0.757812 3.765625 -0.78125 C 3.941406 -0.8125 4.070312 -0.835938 4.15625 -0.859375 Z M 4.15625 -8.140625 L 5.140625 -8.3125 L 5.140625 -0.15625 C 4.929688 -0.09375 4.65625 -0.03125 4.3125 0.03125 C 3.976562 0.09375 3.585938 0.125 3.140625 0.125 C 2.742188 0.125 2.378906 0.0546875 2.046875 -0.078125 C 1.722656 -0.210938 1.441406 -0.40625 1.203125 -0.65625 C 0.972656 -0.90625 0.796875 -1.207031 0.671875 -1.5625 C 0.546875 -1.925781 0.484375 -2.332031 0.484375 -2.78125 C 0.484375 -3.21875 0.535156 -3.613281 0.640625 -3.96875 C 0.742188 -4.320312 0.898438 -4.625 1.109375 -4.875 C 1.316406 -5.132812 1.566406 -5.335938 1.859375 -5.484375 C 2.148438 -5.628906 2.488281 -5.703125 2.875 -5.703125 C 3.164062 -5.703125 3.421875 -5.664062 3.640625 -5.59375 C 3.867188 -5.519531 4.039062 -5.441406 4.15625 -5.359375 Z M 4.15625 -8.140625 "/>
+</symbol>
+<symbol overflow="visible" id="glyph1-18">
+<path style="stroke:none;" d="M 1.28125 0 L 1.28125 -5.265625 C 2.101562 -5.546875 2.925781 -5.6875 3.75 -5.6875 C 4.007812 -5.6875 4.253906 -5.675781 4.484375 -5.65625 C 4.722656 -5.632812 4.976562 -5.59375 5.25 -5.53125 L 5.078125 -4.65625 C 4.816406 -4.726562 4.585938 -4.773438 4.390625 -4.796875 C 4.203125 -4.816406 3.988281 -4.828125 3.75 -4.828125 C 3.269531 -4.828125 2.773438 -4.757812 2.265625 -4.625 L 2.265625 0 Z M 1.28125 0 "/>
+</symbol>
+<symbol overflow="visible" id="glyph1-19">
+<path style="stroke:none;" d="M 0.609375 1.046875 C 0.679688 1.085938 0.78125 1.117188 0.90625 1.140625 C 1.039062 1.160156 1.164062 1.171875 1.28125 1.171875 C 1.675781 1.171875 1.984375 1.082031 2.203125 0.90625 C 2.421875 0.738281 2.625 0.460938 2.8125 0.078125 C 2.363281 -0.773438 1.941406 -1.6875 1.546875 -2.65625 C 1.148438 -3.625 0.828125 -4.59375 0.578125 -5.5625 L 1.65625 -5.5625 C 1.738281 -5.25 1.832031 -4.90625 1.9375 -4.53125 C 2.039062 -4.15625 2.160156 -3.769531 2.296875 -3.375 C 2.441406 -2.988281 2.585938 -2.597656 2.734375 -2.203125 C 2.890625 -1.804688 3.054688 -1.425781 3.234375 -1.0625 C 3.367188 -1.4375 3.488281 -1.800781 3.59375 -2.15625 C 3.707031 -2.519531 3.8125 -2.882812 3.90625 -3.25 C 4.007812 -3.613281 4.109375 -3.984375 4.203125 -4.359375 C 4.296875 -4.742188 4.394531 -5.144531 4.5 -5.5625 L 5.53125 -5.5625 C 5.269531 -4.53125 4.984375 -3.523438 4.671875 -2.546875 C 4.359375 -1.566406 4.019531 -0.660156 3.65625 0.171875 C 3.519531 0.484375 3.375 0.753906 3.21875 0.984375 C 3.0625 1.222656 2.890625 1.414062 2.703125 1.5625 C 2.523438 1.71875 2.316406 1.832031 2.078125 1.90625 C 1.847656 1.976562 1.585938 2.015625 1.296875 2.015625 C 1.140625 2.015625 0.972656 1.992188 0.796875 1.953125 C 0.617188 1.910156 0.5 1.875 0.4375 1.84375 Z M 0.609375 1.046875 "/>
+</symbol>
+<symbol overflow="visible" id="glyph1-20">
+<path style="stroke:none;" d="M 0.34375 -3.71875 C 0.34375 -4.382812 0.40625 -4.960938 0.53125 -5.453125 C 0.664062 -5.941406 0.847656 -6.34375 1.078125 -6.65625 C 1.304688 -6.96875 1.582031 -7.203125 1.90625 -7.359375 C 2.238281 -7.515625 2.601562 -7.59375 3 -7.59375 C 3.394531 -7.59375 3.753906 -7.515625 4.078125 -7.359375 C 4.410156 -7.203125 4.691406 -6.96875 4.921875 -6.65625 C 5.148438 -6.34375 5.328125 -5.941406 5.453125 -5.453125 C 5.585938 -4.960938 5.65625 -4.382812 5.65625 -3.71875 C 5.65625 -3.050781 5.585938 -2.472656 5.453125 -1.984375 C 5.328125 -1.503906 5.148438 -1.101562 4.921875 -0.78125 C 4.691406 -0.457031 4.410156 -0.21875 4.078125 -0.0625 C 3.753906 0.0820312 3.394531 0.15625 3 0.15625 C 2.601562 0.15625 2.238281 0.0820312 1.90625 -0.0625 C 1.582031 -0.21875 1.304688 -0.457031 1.078125 -0.78125 C 0.847656 -1.101562 0.664062 -1.503906 0.53125 -1.984375 C 0.40625 -2.472656 0.34375 -3.050781 0.34375 -3.71875 Z M 1.359375 -3.71875 C 1.359375 -2.738281 1.488281 -1.988281 1.75 -1.46875 C 2.007812 -0.957031 2.414062 -0.703125 2.96875 -0.703125 C 3.53125 -0.703125 3.953125 -0.957031 4.234375 -1.46875 C 4.515625 -1.988281 4.65625 -2.738281 4.65625 -3.71875 C 4.65625 -4.695312 4.515625 -5.445312 4.234375 -5.96875 C 3.953125 -6.488281 3.53125 -6.75 2.96875 -6.75 C 2.414062 -6.75 2.007812 -6.488281 1.75 -5.96875 C 1.488281 -5.445312 1.359375 -4.695312 1.359375 -3.71875 Z M 1.359375 -3.71875 "/>
+</symbol>
+<symbol overflow="visible" id="glyph1-21">
+<path style="stroke:none;" d="M 5.140625 -0.15625 C 4.929688 -0.101562 4.644531 -0.046875 4.28125 0.015625 C 3.925781 0.0859375 3.507812 0.125 3.03125 0.125 C 2.613281 0.125 2.265625 0.0625 1.984375 -0.0625 C 1.703125 -0.1875 1.472656 -0.363281 1.296875 -0.59375 C 1.117188 -0.820312 0.992188 -1.09375 0.921875 -1.40625 C 0.847656 -1.71875 0.8125 -2.0625 0.8125 -2.4375 L 0.8125 -5.5625 L 1.796875 -5.5625 L 1.796875 -2.65625 C 1.796875 -1.96875 1.894531 -1.476562 2.09375 -1.1875 C 2.300781 -0.894531 2.644531 -0.75 3.125 -0.75 C 3.226562 -0.75 3.332031 -0.753906 3.4375 -0.765625 C 3.550781 -0.773438 3.65625 -0.785156 3.75 -0.796875 C 3.851562 -0.804688 3.9375 -0.816406 4 -0.828125 C 4.070312 -0.847656 4.125 -0.859375 4.15625 -0.859375 L 4.15625 -5.5625 L 5.140625 -5.5625 Z M 5.140625 -0.15625 "/>
+</symbol>
+<symbol overflow="visible" id="glyph1-22">
+<path style="stroke:none;" d="M 2.921875 -5.5625 L 5.265625 -5.5625 L 5.265625 -4.734375 L 2.921875 -4.734375 L 2.921875 -2.140625 C 2.921875 -1.867188 2.9375 -1.644531 2.96875 -1.46875 C 3.007812 -1.289062 3.078125 -1.144531 3.171875 -1.03125 C 3.265625 -0.925781 3.382812 -0.851562 3.53125 -0.8125 C 3.675781 -0.769531 3.851562 -0.75 4.0625 -0.75 C 4.34375 -0.75 4.570312 -0.773438 4.75 -0.828125 C 4.925781 -0.878906 5.09375 -0.941406 5.25 -1.015625 L 5.40625 -0.1875 C 5.289062 -0.132812 5.109375 -0.0703125 4.859375 0 C 4.617188 0.0820312 4.316406 0.125 3.953125 0.125 C 3.546875 0.125 3.207031 0.078125 2.9375 -0.015625 C 2.675781 -0.109375 2.46875 -0.25 2.3125 -0.4375 C 2.164062 -0.632812 2.066406 -0.875 2.015625 -1.15625 C 1.960938 -1.4375 1.9375 -1.765625 1.9375 -2.140625 L 1.9375 -4.734375 L 0.75 -4.734375 L 0.75 -5.5625 L 1.9375 -5.5625 L 1.9375 -7.125 L 2.921875 -7.296875 Z M 2.921875 -5.5625 "/>
+</symbol>
+<symbol overflow="visible" id="glyph1-23">
+<path style="stroke:none;" d="M 4.5 -2.765625 C 4.5 -3.421875 4.347656 -3.925781 4.046875 -4.28125 C 3.742188 -4.632812 3.347656 -4.8125 2.859375 -4.8125 C 2.585938 -4.8125 2.375 -4.796875 2.21875 -4.765625 C 2.0625 -4.742188 1.9375 -4.71875 1.84375 -4.6875 L 1.84375 -1.171875 C 1.957031 -1.066406 2.117188 -0.96875 2.328125 -0.875 C 2.546875 -0.789062 2.773438 -0.75 3.015625 -0.75 C 3.273438 -0.75 3.5 -0.800781 3.6875 -0.90625 C 3.875 -1.007812 4.023438 -1.148438 4.140625 -1.328125 C 4.265625 -1.515625 4.351562 -1.726562 4.40625 -1.96875 C 4.46875 -2.21875 4.5 -2.484375 4.5 -2.765625 Z M 5.515625 -2.765625 C 5.515625 -2.347656 5.460938 -1.957031 5.359375 -1.59375 C 5.253906 -1.238281 5.097656 -0.929688 4.890625 -0.671875 C 4.679688 -0.421875 4.429688 -0.222656 4.140625 -0.078125 C 3.847656 0.0546875 3.507812 0.125 3.125 0.125 C 2.832031 0.125 2.570312 0.0859375 2.34375 0.015625 C 2.125 -0.046875 1.957031 -0.125 1.84375 -0.21875 L 1.84375 1.984375 L 0.859375 1.984375 L 0.859375 -5.40625 C 1.066406 -5.46875 1.34375 -5.53125 1.6875 -5.59375 C 2.03125 -5.65625 2.421875 -5.6875 2.859375 -5.6875 C 3.253906 -5.6875 3.613281 -5.617188 3.9375 -5.484375 C 4.269531 -5.347656 4.550781 -5.15625 4.78125 -4.90625 C 5.019531 -4.65625 5.203125 -4.347656 5.328125 -3.984375 C 5.453125 -3.617188 5.515625 -3.210938 5.515625 -2.765625 Z M 5.515625 -2.765625 "/>
+</symbol>
+<symbol overflow="visible" id="glyph1-24">
+<path style="stroke:none;" d="M 3.015625 -3.734375 L 4.15625 -7.421875 L 5.09375 -7.421875 C 5.25 -6.253906 5.359375 -5.054688 5.421875 -3.828125 C 5.492188 -2.609375 5.554688 -1.332031 5.609375 0 L 4.65625 0 C 4.644531 -0.425781 4.632812 -0.890625 4.625 -1.390625 C 4.625 -1.898438 4.613281 -2.421875 4.59375 -2.953125 C 4.582031 -3.492188 4.570312 -4.039062 4.5625 -4.59375 C 4.550781 -5.144531 4.539062 -5.679688 4.53125 -6.203125 L 3.4375 -2.8125 L 2.578125 -2.8125 L 1.46875 -6.203125 C 1.46875 -5.679688 1.457031 -5.144531 1.4375 -4.59375 C 1.425781 -4.050781 1.414062 -3.507812 1.40625 -2.96875 C 1.394531 -2.425781 1.382812 -1.898438 1.375 -1.390625 C 1.363281 -0.890625 1.351562 -0.425781 1.34375 0 L 0.390625 0 C 0.410156 -0.601562 0.4375 -1.222656 0.46875 -1.859375 C 0.5 -2.503906 0.535156 -3.144531 0.578125 -3.78125 C 0.617188 -4.414062 0.671875 -5.039062 0.734375 -5.65625 C 0.796875 -6.269531 0.863281 -6.859375 0.9375 -7.421875 L 1.84375 -7.421875 Z M 3.015625 -3.734375 "/>
+</symbol>
+<symbol overflow="visible" id="glyph2-0">
+<path style="stroke:none;" d="M 0.640625 2.296875 L 0.640625 -9.171875 L 7.140625 -9.171875 L 7.140625 2.296875 Z M 1.375 1.578125 L 6.421875 1.578125 L 6.421875 -8.4375 L 1.375 -8.4375 Z M 1.375 1.578125 "/>
+</symbol>
+<symbol overflow="visible" id="glyph2-1">
+<path style="stroke:none;" d="M 6.34375 -6.84375 L 6.34375 -5.75 C 6.007812 -5.925781 5.675781 -6.0625 5.34375 -6.15625 C 5.007812 -6.25 4.675781 -6.296875 4.34375 -6.296875 C 3.582031 -6.296875 2.992188 -6.050781 2.578125 -5.5625 C 2.160156 -5.082031 1.953125 -4.410156 1.953125 -3.546875 C 1.953125 -2.679688 2.160156 -2.007812 2.578125 -1.53125 C 2.992188 -1.050781 3.582031 -0.8125 4.34375 -0.8125 C 4.675781 -0.8125 5.007812 -0.851562 5.34375 -0.9375 C 5.675781 -1.03125 6.007812 -1.171875 6.34375 -1.359375 L 6.34375 -0.265625 C 6.019531 -0.117188 5.679688 -0.0078125 5.328125 0.0625 C 4.984375 0.144531 4.613281 0.1875 4.21875 0.1875 C 3.144531 0.1875 2.289062 -0.144531 1.65625 -0.8125 C 1.03125 -1.488281 0.71875 -2.398438 0.71875 -3.546875 C 0.71875 -4.703125 1.035156 -5.613281 1.671875 -6.28125 C 2.304688 -6.945312 3.179688 -7.28125 4.296875 -7.28125 C 4.648438 -7.28125 5 -7.242188 5.34375 -7.171875 C 5.6875 -7.097656 6.019531 -6.988281 6.34375 -6.84375 Z M 6.34375 -6.84375 "/>
+</symbol>
+<symbol overflow="visible" id="glyph2-2">
+<path style="stroke:none;" d="M 5.34375 -6.015625 C 5.207031 -6.085938 5.0625 -6.140625 4.90625 -6.171875 C 4.757812 -6.210938 4.59375 -6.234375 4.40625 -6.234375 C 3.75 -6.234375 3.242188 -6.019531 2.890625 -5.59375 C 2.535156 -5.164062 2.359375 -4.550781 2.359375 -3.75 L 2.359375 0 L 1.1875 0 L 1.1875 -7.109375 L 2.359375 -7.109375 L 2.359375 -6 C 2.597656 -6.4375 2.914062 -6.757812 3.3125 -6.96875 C 3.707031 -7.175781 4.1875 -7.28125 4.75 -7.28125 C 4.832031 -7.28125 4.921875 -7.273438 5.015625 -7.265625 C 5.109375 -7.253906 5.21875 -7.238281 5.34375 -7.21875 Z M 5.34375 -6.015625 "/>
+</symbol>
+<symbol overflow="visible" id="glyph2-3">
+<path style="stroke:none;" d="M 3.984375 -6.296875 C 3.359375 -6.296875 2.863281 -6.050781 2.5 -5.5625 C 2.132812 -5.070312 1.953125 -4.398438 1.953125 -3.546875 C 1.953125 -2.691406 2.128906 -2.019531 2.484375 -1.53125 C 2.847656 -1.050781 3.347656 -0.8125 3.984375 -0.8125 C 4.597656 -0.8125 5.085938 -1.054688 5.453125 -1.546875 C 5.816406 -2.035156 6 -2.703125 6 -3.546875 C 6 -4.390625 5.816406 -5.054688 5.453125 -5.546875 C 5.085938 -6.046875 4.597656 -6.296875 3.984375 -6.296875 Z M 3.984375 -7.28125 C 4.992188 -7.28125 5.789062 -6.945312 6.375 -6.28125 C 6.957031 -5.625 7.25 -4.710938 7.25 -3.546875 C 7.25 -2.378906 6.957031 -1.460938 6.375 -0.796875 C 5.789062 -0.140625 4.992188 0.1875 3.984375 0.1875 C 2.960938 0.1875 2.160156 -0.140625 1.578125 -0.796875 C 1.003906 -1.460938 0.71875 -2.378906 0.71875 -3.546875 C 0.71875 -4.710938 1.003906 -5.625 1.578125 -6.28125 C 2.160156 -6.945312 2.960938 -7.28125 3.984375 -7.28125 Z M 3.984375 -7.28125 "/>
+</symbol>
+<symbol overflow="visible" id="glyph2-4">
+<path style="stroke:none;" d="M 2.359375 -1.0625 L 2.359375 2.703125 L 1.1875 2.703125 L 1.1875 -7.109375 L 2.359375 -7.109375 L 2.359375 -6.03125 C 2.597656 -6.457031 2.90625 -6.769531 3.28125 -6.96875 C 3.65625 -7.175781 4.101562 -7.28125 4.625 -7.28125 C 5.488281 -7.28125 6.191406 -6.9375 6.734375 -6.25 C 7.273438 -5.5625 7.546875 -4.660156 7.546875 -3.546875 C 7.546875 -2.429688 7.273438 -1.53125 6.734375 -0.84375 C 6.191406 -0.15625 5.488281 0.1875 4.625 0.1875 C 4.101562 0.1875 3.65625 0.0820312 3.28125 -0.125 C 2.90625 -0.332031 2.597656 -0.644531 2.359375 -1.0625 Z M 6.328125 -3.546875 C 6.328125 -4.410156 6.148438 -5.082031 5.796875 -5.5625 C 5.441406 -6.050781 4.957031 -6.296875 4.34375 -6.296875 C 3.726562 -6.296875 3.242188 -6.050781 2.890625 -5.5625 C 2.535156 -5.082031 2.359375 -4.410156 2.359375 -3.546875 C 2.359375 -2.691406 2.535156 -2.019531 2.890625 -1.53125 C 3.242188 -1.039062 3.726562 -0.796875 4.34375 -0.796875 C 4.957031 -0.796875 5.441406 -1.039062 5.796875 -1.53125 C 6.148438 -2.019531 6.328125 -2.691406 6.328125 -3.546875 Z M 6.328125 -3.546875 "/>
+</symbol>
+<symbol overflow="visible" id="glyph2-5">
+<path style="stroke:none;" d="M 5.75 -6.90625 L 5.75 -5.796875 C 5.425781 -5.960938 5.085938 -6.085938 4.734375 -6.171875 C 4.378906 -6.253906 4.007812 -6.296875 3.625 -6.296875 C 3.039062 -6.296875 2.601562 -6.207031 2.3125 -6.03125 C 2.03125 -5.851562 1.890625 -5.585938 1.890625 -5.234375 C 1.890625 -4.960938 1.988281 -4.75 2.1875 -4.59375 C 2.394531 -4.445312 2.816406 -4.300781 3.453125 -4.15625 L 3.84375 -4.0625 C 4.675781 -3.882812 5.265625 -3.632812 5.609375 -3.3125 C 5.960938 -2.988281 6.140625 -2.539062 6.140625 -1.96875 C 6.140625 -1.300781 5.878906 -0.773438 5.359375 -0.390625 C 4.835938 -0.00390625 4.117188 0.1875 3.203125 0.1875 C 2.816406 0.1875 2.414062 0.148438 2 0.078125 C 1.59375 0.00390625 1.160156 -0.109375 0.703125 -0.265625 L 0.703125 -1.46875 C 1.140625 -1.238281 1.566406 -1.066406 1.984375 -0.953125 C 2.398438 -0.847656 2.8125 -0.796875 3.21875 -0.796875 C 3.769531 -0.796875 4.191406 -0.890625 4.484375 -1.078125 C 4.785156 -1.265625 4.9375 -1.53125 4.9375 -1.875 C 4.9375 -2.1875 4.828125 -2.425781 4.609375 -2.59375 C 4.398438 -2.769531 3.9375 -2.9375 3.21875 -3.09375 L 2.8125 -3.1875 C 2.082031 -3.34375 1.554688 -3.578125 1.234375 -3.890625 C 0.910156 -4.203125 0.75 -4.632812 0.75 -5.1875 C 0.75 -5.851562 0.984375 -6.367188 1.453125 -6.734375 C 1.929688 -7.097656 2.609375 -7.28125 3.484375 -7.28125 C 3.910156 -7.28125 4.316406 -7.25 4.703125 -7.1875 C 5.085938 -7.125 5.4375 -7.03125 5.75 -6.90625 Z M 5.75 -6.90625 "/>
+</symbol>
+<symbol overflow="visible" id="glyph2-6">
+<path style="stroke:none;" d="M 4.453125 -3.578125 C 3.515625 -3.578125 2.863281 -3.46875 2.5 -3.25 C 2.132812 -3.03125 1.953125 -2.660156 1.953125 -2.140625 C 1.953125 -1.734375 2.085938 -1.40625 2.359375 -1.15625 C 2.628906 -0.914062 3 -0.796875 3.46875 -0.796875 C 4.113281 -0.796875 4.632812 -1.023438 5.03125 -1.484375 C 5.425781 -1.941406 5.625 -2.550781 5.625 -3.3125 L 5.625 -3.578125 Z M 6.78125 -4.0625 L 6.78125 0 L 5.625 0 L 5.625 -1.078125 C 5.351562 -0.648438 5.019531 -0.332031 4.625 -0.125 C 4.226562 0.0820312 3.738281 0.1875 3.15625 0.1875 C 2.425781 0.1875 1.847656 -0.015625 1.421875 -0.421875 C 0.992188 -0.835938 0.78125 -1.382812 0.78125 -2.0625 C 0.78125 -2.863281 1.046875 -3.46875 1.578125 -3.875 C 2.117188 -4.28125 2.921875 -4.484375 3.984375 -4.484375 L 5.625 -4.484375 L 5.625 -4.609375 C 5.625 -5.140625 5.445312 -5.550781 5.09375 -5.84375 C 4.738281 -6.144531 4.238281 -6.296875 3.59375 -6.296875 C 3.1875 -6.296875 2.789062 -6.242188 2.40625 -6.140625 C 2.019531 -6.046875 1.648438 -5.898438 1.296875 -5.703125 L 1.296875 -6.78125 C 1.722656 -6.945312 2.140625 -7.070312 2.546875 -7.15625 C 2.953125 -7.238281 3.34375 -7.28125 3.71875 -7.28125 C 4.75 -7.28125 5.515625 -7.015625 6.015625 -6.484375 C 6.523438 -5.953125 6.78125 -5.144531 6.78125 -4.0625 Z M 6.78125 -4.0625 "/>
+</symbol>
+<symbol overflow="visible" id="glyph2-7">
+<path style="stroke:none;" d="M 1.21875 -9.875 L 2.390625 -9.875 L 2.390625 0 L 1.21875 0 Z M 1.21875 -9.875 "/>
+</symbol>
+<symbol overflow="visible" id="glyph2-8">
+<path style="stroke:none;" d="M 7.3125 -3.84375 L 7.3125 -3.28125 L 1.9375 -3.28125 C 1.988281 -2.46875 2.226562 -1.851562 2.65625 -1.4375 C 3.09375 -1.019531 3.695312 -0.8125 4.46875 -0.8125 C 4.914062 -0.8125 5.347656 -0.863281 5.765625 -0.96875 C 6.191406 -1.082031 6.613281 -1.25 7.03125 -1.46875 L 7.03125 -0.359375 C 6.613281 -0.179688 6.179688 -0.046875 5.734375 0.046875 C 5.296875 0.140625 4.851562 0.1875 4.40625 0.1875 C 3.269531 0.1875 2.367188 -0.140625 1.703125 -0.796875 C 1.046875 -1.460938 0.71875 -2.359375 0.71875 -3.484375 C 0.71875 -4.648438 1.03125 -5.570312 1.65625 -6.25 C 2.289062 -6.9375 3.140625 -7.28125 4.203125 -7.28125 C 5.160156 -7.28125 5.914062 -6.972656 6.46875 -6.359375 C 7.03125 -5.742188 7.3125 -4.90625 7.3125 -3.84375 Z M 6.140625 -4.1875 C 6.128906 -4.820312 5.945312 -5.332031 5.59375 -5.71875 C 5.25 -6.101562 4.789062 -6.296875 4.21875 -6.296875 C 3.5625 -6.296875 3.035156 -6.109375 2.640625 -5.734375 C 2.253906 -5.367188 2.03125 -4.851562 1.96875 -4.1875 Z M 6.140625 -4.1875 "/>
+</symbol>
+<symbol overflow="visible" id="glyph2-9">
+<path style="stroke:none;" d="M 6.328125 -3.546875 C 6.328125 -4.410156 6.148438 -5.082031 5.796875 -5.5625 C 5.441406 -6.050781 4.957031 -6.296875 4.34375 -6.296875 C 3.726562 -6.296875 3.242188 -6.050781 2.890625 -5.5625 C 2.535156 -5.082031 2.359375 -4.410156 2.359375 -3.546875 C 2.359375 -2.691406 2.535156 -2.019531 2.890625 -1.53125 C 3.242188 -1.039062 3.726562 -0.796875 4.34375 -0.796875 C 4.957031 -0.796875 5.441406 -1.039062 5.796875 -1.53125 C 6.148438 -2.019531 6.328125 -2.691406 6.328125 -3.546875 Z M 2.359375 -6.03125 C 2.597656 -6.457031 2.90625 -6.769531 3.28125 -6.96875 C 3.65625 -7.175781 4.101562 -7.28125 4.625 -7.28125 C 5.488281 -7.28125 6.191406 -6.9375 6.734375 -6.25 C 7.273438 -5.5625 7.546875 -4.660156 7.546875 -3.546875 C 7.546875 -2.429688 7.273438 -1.53125 6.734375 -0.84375 C 6.191406 -0.15625 5.488281 0.1875 4.625 0.1875 C 4.101562 0.1875 3.65625 0.0820312 3.28125 -0.125 C 2.90625 -0.332031 2.597656 -0.644531 2.359375 -1.0625 L 2.359375 0 L 1.1875 0 L 1.1875 -9.875 L 2.359375 -9.875 Z M 2.359375 -6.03125 "/>
+</symbol>
+<symbol overflow="visible" id="glyph2-10">
+<path style="stroke:none;" d="M 1.21875 -7.109375 L 2.390625 -7.109375 L 2.390625 0 L 1.21875 0 Z M 1.21875 -9.875 L 2.390625 -9.875 L 2.390625 -8.390625 L 1.21875 -8.390625 Z M 1.21875 -9.875 "/>
+</symbol>
+<symbol overflow="visible" id="glyph2-11">
+<path style="stroke:none;" d="M 7.140625 -4.296875 L 7.140625 0 L 5.96875 0 L 5.96875 -4.25 C 5.96875 -4.925781 5.835938 -5.429688 5.578125 -5.765625 C 5.316406 -6.097656 4.921875 -6.265625 4.390625 -6.265625 C 3.765625 -6.265625 3.269531 -6.0625 2.90625 -5.65625 C 2.539062 -5.257812 2.359375 -4.710938 2.359375 -4.015625 L 2.359375 0 L 1.1875 0 L 1.1875 -7.109375 L 2.359375 -7.109375 L 2.359375 -6 C 2.640625 -6.425781 2.96875 -6.742188 3.34375 -6.953125 C 3.71875 -7.171875 4.15625 -7.28125 4.65625 -7.28125 C 5.46875 -7.28125 6.082031 -7.023438 6.5 -6.515625 C 6.925781 -6.015625 7.140625 -5.273438 7.140625 -4.296875 Z M 7.140625 -4.296875 "/>
+</symbol>
+<symbol overflow="visible" id="glyph2-12">
+<path style="stroke:none;" d="M 5.90625 -3.640625 C 5.90625 -4.484375 5.726562 -5.132812 5.375 -5.59375 C 5.03125 -6.0625 4.539062 -6.296875 3.90625 -6.296875 C 3.28125 -6.296875 2.789062 -6.0625 2.4375 -5.59375 C 2.09375 -5.132812 1.921875 -4.484375 1.921875 -3.640625 C 1.921875 -2.796875 2.09375 -2.140625 2.4375 -1.671875 C 2.789062 -1.210938 3.28125 -0.984375 3.90625 -0.984375 C 4.539062 -0.984375 5.03125 -1.210938 5.375 -1.671875 C 5.726562 -2.140625 5.90625 -2.796875 5.90625 -3.640625 Z M 7.078125 -0.875 C 7.078125 0.332031 6.804688 1.226562 6.265625 1.8125 C 5.722656 2.40625 4.898438 2.703125 3.796875 2.703125 C 3.390625 2.703125 3.003906 2.671875 2.640625 2.609375 C 2.273438 2.546875 1.921875 2.453125 1.578125 2.328125 L 1.578125 1.1875 C 1.921875 1.375 2.257812 1.507812 2.59375 1.59375 C 2.925781 1.6875 3.265625 1.734375 3.609375 1.734375 C 4.378906 1.734375 4.953125 1.535156 5.328125 1.140625 C 5.710938 0.742188 5.90625 0.140625 5.90625 -0.671875 L 5.90625 -1.25 C 5.664062 -0.832031 5.351562 -0.519531 4.96875 -0.3125 C 4.59375 -0.101562 4.144531 0 3.625 0 C 2.75 0 2.046875 -0.332031 1.515625 -1 C 0.984375 -1.664062 0.71875 -2.546875 0.71875 -3.640625 C 0.71875 -4.734375 0.984375 -5.613281 1.515625 -6.28125 C 2.046875 -6.945312 2.75 -7.28125 3.625 -7.28125 C 4.144531 -7.28125 4.59375 -7.175781 4.96875 -6.96875 C 5.351562 -6.757812 5.664062 -6.445312 5.90625 -6.03125 L 5.90625 -7.109375 L 7.078125 -7.109375 Z M 7.078125 -0.875 "/>
+</symbol>
+<symbol overflow="visible" id="glyph2-13">
+<path style="stroke:none;" d="M 5.125 -8.609375 C 4.1875 -8.609375 3.441406 -8.257812 2.890625 -7.5625 C 2.347656 -6.875 2.078125 -5.929688 2.078125 -4.734375 C 2.078125 -3.535156 2.347656 -2.585938 2.890625 -1.890625 C 3.441406 -1.203125 4.1875 -0.859375 5.125 -0.859375 C 6.050781 -0.859375 6.785156 -1.203125 7.328125 -1.890625 C 7.878906 -2.585938 8.15625 -3.535156 8.15625 -4.734375 C 8.15625 -5.929688 7.878906 -6.875 7.328125 -7.5625 C 6.785156 -8.257812 6.050781 -8.609375 5.125 -8.609375 Z M 5.125 -9.65625 C 6.445312 -9.65625 7.503906 -9.207031 8.296875 -8.3125 C 9.097656 -7.414062 9.5 -6.222656 9.5 -4.734375 C 9.5 -3.234375 9.097656 -2.035156 8.296875 -1.140625 C 7.503906 -0.253906 6.445312 0.1875 5.125 0.1875 C 3.789062 0.1875 2.722656 -0.253906 1.921875 -1.140625 C 1.128906 -2.035156 0.734375 -3.234375 0.734375 -4.734375 C 0.734375 -6.222656 1.128906 -7.414062 1.921875 -8.3125 C 2.722656 -9.207031 3.789062 -9.65625 5.125 -9.65625 Z M 5.125 -9.65625 "/>
+</symbol>
+<symbol overflow="visible" id="glyph2-14">
+<path style="stroke:none;" d="M 1.109375 -2.8125 L 1.109375 -7.109375 L 2.265625 -7.109375 L 2.265625 -2.84375 C 2.265625 -2.175781 2.394531 -1.671875 2.65625 -1.328125 C 2.925781 -0.992188 3.320312 -0.828125 3.84375 -0.828125 C 4.476562 -0.828125 4.976562 -1.023438 5.34375 -1.421875 C 5.707031 -1.828125 5.890625 -2.378906 5.890625 -3.078125 L 5.890625 -7.109375 L 7.0625 -7.109375 L 7.0625 0 L 5.890625 0 L 5.890625 -1.09375 C 5.609375 -0.65625 5.28125 -0.332031 4.90625 -0.125 C 4.53125 0.0820312 4.09375 0.1875 3.59375 0.1875 C 2.78125 0.1875 2.160156 -0.0664062 1.734375 -0.578125 C 1.316406 -1.085938 1.109375 -1.832031 1.109375 -2.8125 Z M 4.046875 -7.28125 Z M 4.046875 -7.28125 "/>
+</symbol>
+<symbol overflow="visible" id="glyph2-15">
+<path style="stroke:none;" d="M 2.375 -9.125 L 2.375 -7.109375 L 4.78125 -7.109375 L 4.78125 -6.203125 L 2.375 -6.203125 L 2.375 -2.34375 C 2.375 -1.757812 2.453125 -1.382812 2.609375 -1.21875 C 2.773438 -1.0625 3.101562 -0.984375 3.59375 -0.984375 L 4.78125 -0.984375 L 4.78125 0 L 3.59375 0 C 2.6875 0 2.0625 -0.164062 1.71875 -0.5 C 1.375 -0.84375 1.203125 -1.457031 1.203125 -2.34375 L 1.203125 -6.203125 L 0.34375 -6.203125 L 0.34375 -7.109375 L 1.203125 -7.109375 L 1.203125 -9.125 Z M 2.375 -9.125 "/>
+</symbol>
+<symbol overflow="visible" id="glyph2-16">
+<path style="stroke:none;" d=""/>
+</symbol>
+<symbol overflow="visible" id="glyph2-17">
+<path style="stroke:none;" d="M 1.28125 -9.484375 L 6.71875 -9.484375 L 6.71875 -8.390625 L 2.5625 -8.390625 L 2.5625 -5.609375 L 6.3125 -5.609375 L 6.3125 -4.53125 L 2.5625 -4.53125 L 2.5625 0 L 1.28125 0 Z M 1.28125 -9.484375 "/>
+</symbol>
+<symbol overflow="visible" id="glyph2-18">
+<path style="stroke:none;" d="M 6.765625 -5.75 C 7.054688 -6.269531 7.40625 -6.65625 7.8125 -6.90625 C 8.21875 -7.15625 8.695312 -7.28125 9.25 -7.28125 C 9.988281 -7.28125 10.554688 -7.019531 10.953125 -6.5 C 11.359375 -5.976562 11.5625 -5.242188 11.5625 -4.296875 L 11.5625 0 L 10.390625 0 L 10.390625 -4.25 C 10.390625 -4.9375 10.265625 -5.441406 10.015625 -5.765625 C 9.773438 -6.097656 9.410156 -6.265625 8.921875 -6.265625 C 8.316406 -6.265625 7.835938 -6.0625 7.484375 -5.65625 C 7.128906 -5.257812 6.953125 -4.710938 6.953125 -4.015625 L 6.953125 0 L 5.78125 0 L 5.78125 -4.25 C 5.78125 -4.9375 5.660156 -5.441406 5.421875 -5.765625 C 5.179688 -6.097656 4.804688 -6.265625 4.296875 -6.265625 C 3.703125 -6.265625 3.226562 -6.0625 2.875 -5.65625 C 2.53125 -5.25 2.359375 -4.703125 2.359375 -4.015625 L 2.359375 0 L 1.1875 0 L 1.1875 -7.109375 L 2.359375 -7.109375 L 2.359375 -6 C 2.617188 -6.4375 2.9375 -6.757812 3.3125 -6.96875 C 3.6875 -7.175781 4.128906 -7.28125 4.640625 -7.28125 C 5.160156 -7.28125 5.597656 -7.148438 5.953125 -6.890625 C 6.316406 -6.628906 6.585938 -6.25 6.765625 -5.75 Z M 6.765625 -5.75 "/>
+</symbol>
+<symbol overflow="visible" id="glyph2-19">
+<path style="stroke:none;" d="M 6.953125 -9.171875 L 6.953125 -7.921875 C 6.472656 -8.148438 6.015625 -8.320312 5.578125 -8.4375 C 5.148438 -8.550781 4.734375 -8.609375 4.328125 -8.609375 C 3.628906 -8.609375 3.085938 -8.472656 2.703125 -8.203125 C 2.328125 -7.929688 2.140625 -7.546875 2.140625 -7.046875 C 2.140625 -6.628906 2.265625 -6.3125 2.515625 -6.09375 C 2.773438 -5.882812 3.253906 -5.710938 3.953125 -5.578125 L 4.734375 -5.421875 C 5.679688 -5.234375 6.382812 -4.910156 6.84375 -4.453125 C 7.300781 -3.992188 7.53125 -3.378906 7.53125 -2.609375 C 7.53125 -1.691406 7.222656 -0.992188 6.609375 -0.515625 C 5.992188 -0.046875 5.085938 0.1875 3.890625 0.1875 C 3.441406 0.1875 2.960938 0.132812 2.453125 0.03125 C 1.953125 -0.0703125 1.429688 -0.222656 0.890625 -0.421875 L 0.890625 -1.734375 C 1.410156 -1.441406 1.921875 -1.222656 2.421875 -1.078125 C 2.921875 -0.929688 3.410156 -0.859375 3.890625 -0.859375 C 4.628906 -0.859375 5.195312 -1 5.59375 -1.28125 C 5.988281 -1.570312 6.1875 -1.984375 6.1875 -2.515625 C 6.1875 -2.984375 6.039062 -3.347656 5.75 -3.609375 C 5.46875 -3.867188 5.003906 -4.066406 4.359375 -4.203125 L 3.578125 -4.359375 C 2.617188 -4.546875 1.925781 -4.84375 1.5 -5.25 C 1.070312 -5.65625 0.859375 -6.21875 0.859375 -6.9375 C 0.859375 -7.78125 1.148438 -8.441406 1.734375 -8.921875 C 2.328125 -9.410156 3.144531 -9.65625 4.1875 -9.65625 C 4.625 -9.65625 5.070312 -9.613281 5.53125 -9.53125 C 6 -9.445312 6.472656 -9.328125 6.953125 -9.171875 Z M 6.953125 -9.171875 "/>
+</symbol>
+<symbol overflow="visible" id="glyph2-20">
+<path style="stroke:none;" d="M 4.1875 0.65625 C 3.851562 1.507812 3.53125 2.0625 3.21875 2.3125 C 2.90625 2.570312 2.488281 2.703125 1.96875 2.703125 L 1.03125 2.703125 L 1.03125 1.734375 L 1.71875 1.734375 C 2.039062 1.734375 2.289062 1.65625 2.46875 1.5 C 2.644531 1.34375 2.835938 0.984375 3.046875 0.421875 L 3.265625 -0.109375 L 0.390625 -7.109375 L 1.625 -7.109375 L 3.84375 -1.546875 L 6.0625 -7.109375 L 7.3125 -7.109375 Z M 4.1875 0.65625 "/>
+</symbol>
+</g>
+</defs>
+<g id="surface268880">
+<rect x="0" y="0" width="774" height="152" style="fill:rgb(100%,100%,100%);fill-opacity:1;stroke:none;"/>
+<path style="fill-rule:evenodd;fill:rgb(100%,100%,100%);fill-opacity:1;stroke-width:0.1;stroke-linecap:butt;stroke-linejoin:miter;stroke:rgb(0%,0%,0%);stroke-opacity:1;stroke-miterlimit:10;" d="M 21.75297 10.408118 L 26.433829 10.408118 L 26.433829 12.281165 L 21.75297 12.281165 Z M 21.75297 10.408118 " transform="matrix(20,0,0,20,-434.059401,-172.47877)"/>
+<path style="fill-rule:evenodd;fill:rgb(100%,100%,100%);fill-opacity:1;stroke-width:0.1;stroke-linecap:butt;stroke-linejoin:miter;stroke:rgb(0%,0%,0%);stroke-opacity:1;stroke-miterlimit:10;" d="M 29.079728 10.51222 L 32.829728 10.51222 L 32.829728 12.149915 L 29.079728 12.149915 Z M 29.079728 10.51222 " transform="matrix(20,0,0,20,-434.059401,-172.47877)"/>
+<g style="fill:rgb(0%,0%,0%);fill-opacity:1;">
+  <use xlink:href="#glyph0-1" x="20.171875" y="57.705621"/>
+  <use xlink:href="#glyph0-2" x="30.171875" y="57.705621"/>
+  <use xlink:href="#glyph0-3" x="40.171875" y="57.705621"/>
+  <use xlink:href="#glyph0-4" x="50.171875" y="57.705621"/>
+  <use xlink:href="#glyph0-5" x="60.171875" y="57.705621"/>
+  <use xlink:href="#glyph0-6" x="70.171875" y="57.705621"/>
+</g>
+<g style="fill:rgb(0%,0%,0%);fill-opacity:1;">
+  <use xlink:href="#glyph0-7" x="174.203125" y="60.053277"/>
+  <use xlink:href="#glyph0-8" x="184.203125" y="60.053277"/>
+</g>
+<path style="fill-rule:evenodd;fill:rgb(100%,100%,100%);fill-opacity:1;stroke-width:0.1;stroke-linecap:butt;stroke-linejoin:miter;stroke:rgb(0%,0%,0%);stroke-opacity:1;stroke-miterlimit:10;" d="M 40.925236 10.544446 L 44.675236 10.544446 L 44.675236 12.090345 L 40.925236 12.090345 Z M 40.925236 10.544446 " transform="matrix(20,0,0,20,-434.059401,-172.47877)"/>
+<path style="fill-rule:evenodd;fill:rgb(100%,100%,100%);fill-opacity:1;stroke-width:0.1;stroke-linecap:butt;stroke-linejoin:miter;stroke:rgb(0%,0%,0%);stroke-opacity:1;stroke-miterlimit:10;" d="M 34.883439 10.536634 L 38.633439 10.536634 L 38.633439 12.120032 L 34.883439 12.120032 Z M 34.883439 10.536634 " transform="matrix(20,0,0,20,-434.059401,-172.47877)"/>
+<path style="fill-rule:evenodd;fill:rgb(100%,100%,100%);fill-opacity:1;stroke-width:0.1;stroke-linecap:butt;stroke-linejoin:miter;stroke:rgb(0%,0%,0%);stroke-opacity:1;stroke-miterlimit:10;" d="M 47.084806 10.484876 L 52.045743 10.484876 L 52.045743 12.130774 L 47.084806 12.130774 Z M 47.084806 10.484876 " transform="matrix(20,0,0,20,-434.059401,-172.47877)"/>
+<path style="fill-rule:evenodd;fill:rgb(100%,100%,100%);fill-opacity:1;stroke-width:0.1;stroke-linecap:butt;stroke-linejoin:miter;stroke:rgb(0%,0%,0%);stroke-opacity:1;stroke-miterlimit:10;" d="M 53.980118 10.376868 L 59.866642 10.376868 L 59.866642 12.279603 L 53.980118 12.279603 Z M 53.980118 10.376868 " transform="matrix(20,0,0,20,-434.059401,-172.47877)"/>
+<path style="fill-rule:evenodd;fill:rgb(100%,100%,100%);fill-opacity:1;stroke-width:0.1;stroke-linecap:butt;stroke-linejoin:miter;stroke:rgb(0%,0%,0%);stroke-opacity:1;stroke-miterlimit:10;" d="M 54.048478 13.825501 L 59.868009 13.825501 L 59.868009 15.490345 L 54.048478 15.490345 Z M 54.048478 13.825501 " transform="matrix(20,0,0,20,-434.059401,-172.47877)"/>
+<path style="fill:none;stroke-width:0.1;stroke-linecap:butt;stroke-linejoin:miter;stroke:rgb(0%,0%,0%);stroke-opacity:1;stroke-miterlimit:10;" d="M 26.481876 11.338001 L 28.593009 11.332337 " transform="matrix(20,0,0,20,-434.059401,-172.47877)"/>
+<path style="fill-rule:evenodd;fill:rgb(0%,0%,0%);fill-opacity:1;stroke-width:0.1;stroke-linecap:butt;stroke-linejoin:miter;stroke:rgb(0%,0%,0%);stroke-opacity:1;stroke-miterlimit:10;" d="M 28.968009 11.33136 L 28.468595 11.582728 L 28.593009 11.332337 L 28.467228 11.082728 Z M 28.968009 11.33136 " transform="matrix(20,0,0,20,-434.059401,-172.47877)"/>
+<path style="fill:none;stroke-width:0.1;stroke-linecap:butt;stroke-linejoin:miter;stroke:rgb(0%,0%,0%);stroke-opacity:1;stroke-miterlimit:10;" d="M 32.876798 11.329798 L 34.396525 11.328626 " transform="matrix(20,0,0,20,-434.059401,-172.47877)"/>
+<path style="fill-rule:evenodd;fill:rgb(0%,0%,0%);fill-opacity:1;stroke-width:0.1;stroke-linecap:butt;stroke-linejoin:miter;stroke:rgb(0%,0%,0%);stroke-opacity:1;stroke-miterlimit:10;" d="M 34.771525 11.328431 L 34.27172 11.578821 L 34.396525 11.328626 L 34.271329 11.078821 Z M 34.771525 11.328431 " transform="matrix(20,0,0,20,-434.059401,-172.47877)"/>
+<path style="fill:none;stroke-width:0.1;stroke-linecap:butt;stroke-linejoin:miter;stroke:rgb(0%,0%,0%);stroke-opacity:1;stroke-miterlimit:10;" d="M 38.633439 11.328431 L 40.438517 11.319642 " transform="matrix(20,0,0,20,-434.059401,-172.47877)"/>
+<path style="fill-rule:evenodd;fill:rgb(0%,0%,0%);fill-opacity:1;stroke-width:0.1;stroke-linecap:butt;stroke-linejoin:miter;stroke:rgb(0%,0%,0%);stroke-opacity:1;stroke-miterlimit:10;" d="M 40.813517 11.317884 L 40.314689 11.570228 L 40.438517 11.319642 L 40.312345 11.070423 Z M 40.813517 11.317884 " transform="matrix(20,0,0,20,-434.059401,-172.47877)"/>
+<path style="fill:none;stroke-width:0.1;stroke-linecap:butt;stroke-linejoin:miter;stroke:rgb(0%,0%,0%);stroke-opacity:1;stroke-miterlimit:10;" d="M 44.675236 11.317298 L 46.597892 11.309876 " transform="matrix(20,0,0,20,-434.059401,-172.47877)"/>
+<path style="fill-rule:evenodd;fill:rgb(0%,0%,0%);fill-opacity:1;stroke-width:0.1;stroke-linecap:butt;stroke-linejoin:miter;stroke:rgb(0%,0%,0%);stroke-opacity:1;stroke-miterlimit:10;" d="M 46.972892 11.308313 L 46.473868 11.560267 L 46.597892 11.309876 L 46.471915 11.060267 Z M 46.972892 11.308313 " transform="matrix(20,0,0,20,-434.059401,-172.47877)"/>
+<path style="fill:none;stroke-width:0.1;stroke-linecap:butt;stroke-linejoin:miter;stroke:rgb(0%,0%,0%);stroke-opacity:1;stroke-miterlimit:10;" d="M 52.045743 11.307923 L 53.4934 11.323157 " transform="matrix(20,0,0,20,-434.059401,-172.47877)"/>
+<path style="fill-rule:evenodd;fill:rgb(0%,0%,0%);fill-opacity:1;stroke-width:0.1;stroke-linecap:butt;stroke-linejoin:miter;stroke:rgb(0%,0%,0%);stroke-opacity:1;stroke-miterlimit:10;" d="M 53.8684 11.327063 L 53.365861 11.57179 L 53.4934 11.323157 L 53.370939 11.07179 Z M 53.8684 11.327063 " transform="matrix(20,0,0,20,-434.059401,-172.47877)"/>
+<g style="fill:rgb(0%,0%,0%);fill-opacity:1;">
+  <use xlink:href="#glyph0-9" x="286.757813" y="60.611871"/>
+  <use xlink:href="#glyph0-10" x="296.757813" y="60.611871"/>
+  <use xlink:href="#glyph0-1" x="306.757813" y="60.611871"/>
+</g>
+<g style="fill:rgb(0%,0%,0%);fill-opacity:1;">
+  <use xlink:href="#glyph0-11" x="405.660156" y="59.904839"/>
+  <use xlink:href="#glyph0-10" x="415.660156" y="59.904839"/>
+  <use xlink:href="#glyph0-12" x="425.660156" y="59.904839"/>
+</g>
+<g style="fill:rgb(0%,0%,0%);fill-opacity:1;">
+  <use xlink:href="#glyph1-1" x="511.308594" y="58.064616"/>
+  <use xlink:href="#glyph1-2" x="517.308757" y="58.064616"/>
+  <use xlink:href="#glyph1-3" x="523.308919" y="58.064616"/>
+  <use xlink:href="#glyph1-4" x="529.309082" y="58.064616"/>
+  <use xlink:href="#glyph1-5" x="535.309245" y="58.064616"/>
+  <use xlink:href="#glyph1-6" x="541.309408" y="58.064616"/>
+  <use xlink:href="#glyph1-7" x="547.30957" y="58.064616"/>
+  <use xlink:href="#glyph1-8" x="553.309733" y="58.064616"/>
+  <use xlink:href="#glyph1-9" x="559.309896" y="58.064616"/>
+  <use xlink:href="#glyph1-10" x="565.310059" y="58.064616"/>
+  <use xlink:href="#glyph1-11" x="571.310221" y="58.064616"/>
+  <use xlink:href="#glyph1-12" x="577.310384" y="58.064616"/>
+  <use xlink:href="#glyph1-13" x="583.310547" y="58.064616"/>
+  <use xlink:href="#glyph1-8" x="589.31071" y="58.064616"/>
+  <use xlink:href="#glyph1-14" x="595.310872" y="58.064616"/>
+</g>
+<path style="fill:none;stroke-width:0.1;stroke-linecap:butt;stroke-linejoin:miter;stroke:rgb(0%,0%,0%);stroke-opacity:1;stroke-miterlimit:10;" d="M 45.671915 11.342298 L 45.655704 11.342298 L 45.655704 14.657923 L 53.561759 14.657923 " transform="matrix(20,0,0,20,-434.059401,-172.47877)"/>
+<path style="fill-rule:evenodd;fill:rgb(0%,0%,0%);fill-opacity:1;stroke-width:0.1;stroke-linecap:butt;stroke-linejoin:miter;stroke:rgb(0%,0%,0%);stroke-opacity:1;stroke-miterlimit:10;" d="M 53.936759 14.657923 L 53.436759 14.907923 L 53.561759 14.657923 L 53.436759 14.407923 Z M 53.936759 14.657923 " transform="matrix(20,0,0,20,-434.059401,-172.47877)"/>
+<g style="fill:rgb(0%,0%,0%);fill-opacity:1;">
+  <use xlink:href="#glyph1-15" x="657.078125" y="57.724772"/>
+  <use xlink:href="#glyph1-16" x="663.078288" y="57.724772"/>
+  <use xlink:href="#glyph1-10" x="669.078451" y="57.724772"/>
+  <use xlink:href="#glyph1-6" x="675.078613" y="57.724772"/>
+  <use xlink:href="#glyph1-8" x="681.078776" y="57.724772"/>
+  <use xlink:href="#glyph1-17" x="687.078939" y="57.724772"/>
+  <use xlink:href="#glyph1-11" x="693.079102" y="57.724772"/>
+  <use xlink:href="#glyph1-18" x="699.079264" y="57.724772"/>
+  <use xlink:href="#glyph1-19" x="705.079427" y="57.724772"/>
+  <use xlink:href="#glyph1-4" x="711.07959" y="57.724772"/>
+  <use xlink:href="#glyph1-20" x="717.079753" y="57.724772"/>
+  <use xlink:href="#glyph1-21" x="723.079915" y="57.724772"/>
+  <use xlink:href="#glyph1-22" x="729.080078" y="57.724772"/>
+  <use xlink:href="#glyph1-23" x="735.080241" y="57.724772"/>
+  <use xlink:href="#glyph1-21" x="741.080404" y="57.724772"/>
+  <use xlink:href="#glyph1-22" x="747.080566" y="57.724772"/>
+</g>
+<g style="fill:rgb(0%,0%,0%);fill-opacity:1;">
+  <use xlink:href="#glyph1-24" x="673.335938" y="124.170085"/>
+  <use xlink:href="#glyph1-11" x="679.3361" y="124.170085"/>
+  <use xlink:href="#glyph1-13" x="685.336263" y="124.170085"/>
+  <use xlink:href="#glyph1-8" x="691.336426" y="124.170085"/>
+  <use xlink:href="#glyph1-4" x="697.336589" y="124.170085"/>
+  <use xlink:href="#glyph1-20" x="703.336751" y="124.170085"/>
+  <use xlink:href="#glyph1-21" x="709.336914" y="124.170085"/>
+  <use xlink:href="#glyph1-22" x="715.337077" y="124.170085"/>
+  <use xlink:href="#glyph1-23" x="721.33724" y="124.170085"/>
+  <use xlink:href="#glyph1-21" x="727.337402" y="124.170085"/>
+  <use xlink:href="#glyph1-22" x="733.337565" y="124.170085"/>
+</g>
+<g style="fill:rgb(0%,0%,0%);fill-opacity:1;">
+  <use xlink:href="#glyph2-1" x="168.71875" y="31.959093"/>
+  <use xlink:href="#glyph2-2" x="175.866102" y="31.959093"/>
+  <use xlink:href="#glyph2-3" x="180.92551" y="31.959093"/>
+  <use xlink:href="#glyph2-4" x="188.879069" y="31.959093"/>
+</g>
+<g style="fill:rgb(0%,0%,0%);fill-opacity:1;">
+  <use xlink:href="#glyph2-5" x="288.109375" y="31.681749"/>
+  <use xlink:href="#glyph2-1" x="294.882378" y="31.681749"/>
+  <use xlink:href="#glyph2-6" x="302.029731" y="31.681749"/>
+  <use xlink:href="#glyph2-7" x="309.996039" y="31.681749"/>
+  <use xlink:href="#glyph2-8" x="313.607964" y="31.681749"/>
+</g>
+<g style="fill:rgb(0%,0%,0%);fill-opacity:1;">
+  <use xlink:href="#glyph2-5" x="535.988281" y="33.365343"/>
+  <use xlink:href="#glyph2-1" x="542.761285" y="33.365343"/>
+  <use xlink:href="#glyph2-6" x="549.908637" y="33.365343"/>
+  <use xlink:href="#glyph2-7" x="557.874946" y="33.365343"/>
+  <use xlink:href="#glyph2-8" x="561.486871" y="33.365343"/>
+</g>
+<g style="fill:rgb(0%,0%,0%);fill-opacity:1;">
+  <use xlink:href="#glyph2-9" x="26.695313" y="32.365343"/>
+  <use xlink:href="#glyph2-10" x="34.947266" y="32.365343"/>
+  <use xlink:href="#glyph2-11" x="38.559191" y="32.365343"/>
+  <use xlink:href="#glyph2-11" x="46.798394" y="32.365343"/>
+  <use xlink:href="#glyph2-10" x="55.037598" y="32.365343"/>
+  <use xlink:href="#glyph2-11" x="58.649523" y="32.365343"/>
+  <use xlink:href="#glyph2-12" x="66.888726" y="32.365343"/>
+</g>
+<path style="fill:none;stroke-width:0.1;stroke-linecap:butt;stroke-linejoin:miter;stroke:rgb(0%,0%,0%);stroke-opacity:1;stroke-dasharray:0.14,0.14;stroke-miterlimit:10;" d="M 45.300431 9.486438 L 60.373478 9.486438 L 60.373478 16.175696 L 45.300431 16.175696 Z M 45.300431 9.486438 " transform="matrix(20,0,0,20,-434.059401,-172.47877)"/>
+<g style="fill:rgb(0%,0%,0%);fill-opacity:1;">
+  <use xlink:href="#glyph2-13" x="532.003906" y="11.904405"/>
+  <use xlink:href="#glyph2-14" x="542.236382" y="11.904405"/>
+  <use xlink:href="#glyph2-15" x="550.475586" y="11.904405"/>
+  <use xlink:href="#glyph2-4" x="555.5727" y="11.904405"/>
+  <use xlink:href="#glyph2-14" x="563.824653" y="11.904405"/>
+  <use xlink:href="#glyph2-15" x="572.063856" y="11.904405"/>
+  <use xlink:href="#glyph2-16" x="577.16097" y="11.904405"/>
+  <use xlink:href="#glyph2-17" x="581.293186" y="11.904405"/>
+  <use xlink:href="#glyph2-3" x="588.307346" y="11.904405"/>
+  <use xlink:href="#glyph2-2" x="596.260905" y="11.904405"/>
+  <use xlink:href="#glyph2-18" x="601.377279" y="11.904405"/>
+  <use xlink:href="#glyph2-6" x="614.040853" y="11.904405"/>
+  <use xlink:href="#glyph2-15" x="622.007161" y="11.904405"/>
+  <use xlink:href="#glyph2-15" x="627.104275" y="11.904405"/>
+  <use xlink:href="#glyph2-8" x="632.201389" y="11.904405"/>
+  <use xlink:href="#glyph2-2" x="640.199436" y="11.904405"/>
+  <use xlink:href="#glyph2-16" x="645.544217" y="11.904405"/>
+  <use xlink:href="#glyph2-19" x="649.676432" y="11.904405"/>
+  <use xlink:href="#glyph2-20" x="657.928385" y="11.904405"/>
+  <use xlink:href="#glyph2-5" x="665.621799" y="11.904405"/>
+  <use xlink:href="#glyph2-15" x="672.394803" y="11.904405"/>
+  <use xlink:href="#glyph2-8" x="677.491916" y="11.904405"/>
+  <use xlink:href="#glyph2-18" x="685.489963" y="11.904405"/>
+</g>
+</g>
+</svg>
diff --git a/Documentation/media/v4l-drivers/vimc.rst b/Documentation/media/v4l-drivers/vimc.rst
index 406417680db5..8f5d7f8d83bb 100644
--- a/Documentation/media/v4l-drivers/vimc.rst
+++ b/Documentation/media/v4l-drivers/vimc.rst
@@ -76,27 +76,19 @@ vimc-capture:
 	* 1 Pad sink
 	* 1 Pad source
 
-Module options
----------------
 
-Vimc has a few module parameters to configure the driver. You should pass
-those arguments to each subdevice, not to the vimc module. For example::
+Module options
+--------------
 
-        vimc_subdevice.param=value
+Vimc has a module parameter to configure the driver.
 
-* ``vimc_scaler.sca_mult=<unsigned int>``
+* ``sca_mult=<unsigned int>``
 
         Image size multiplier factor to be used to multiply both width and
         height, so the image size will be ``sca_mult^2`` bigger than the
         original one. Currently, only supports scaling up (the default value
         is 3).
 
-* ``vimc_debayer.deb_mean_win_size=<unsigned int>``
-
-        Window size to calculate the mean. Note: the window size needs to be an
-        odd number, as the main pixel stays in the center of the window,
-        otherwise the next odd number is considered (the default value is 3).
-
 Source code documentation
 -------------------------
 
diff --git a/Documentation/media/videodev2.h.rst.exceptions b/Documentation/media/videodev2.h.rst.exceptions
index adeb6b7a15cb..cb6ccf91776e 100644
--- a/Documentation/media/videodev2.h.rst.exceptions
+++ b/Documentation/media/videodev2.h.rst.exceptions
@@ -141,6 +141,10 @@ replace symbol V4L2_CTRL_TYPE_H264_PPS :c:type:`v4l2_ctrl_type`
 replace symbol V4L2_CTRL_TYPE_H264_SCALING_MATRIX :c:type:`v4l2_ctrl_type`
 replace symbol V4L2_CTRL_TYPE_H264_SLICE_PARAMS :c:type:`v4l2_ctrl_type`
 replace symbol V4L2_CTRL_TYPE_H264_DECODE_PARAMS :c:type:`v4l2_ctrl_type`
+replace symbol V4L2_CTRL_TYPE_HEVC_SPS :c:type:`v4l2_ctrl_type`
+replace symbol V4L2_CTRL_TYPE_HEVC_PPS :c:type:`v4l2_ctrl_type`
+replace symbol V4L2_CTRL_TYPE_HEVC_SLICE_PARAMS :c:type:`v4l2_ctrl_type`
+replace symbol V4L2_CTRL_TYPE_AREA :c:type:`v4l2_ctrl_type`
 
 # V4L2 capability defines
 replace define V4L2_CAP_VIDEO_CAPTURE device-capabilities
@@ -434,6 +438,7 @@ replace define V4L2_DEC_CMD_START decoder-cmds
 replace define V4L2_DEC_CMD_STOP decoder-cmds
 replace define V4L2_DEC_CMD_PAUSE decoder-cmds
 replace define V4L2_DEC_CMD_RESUME decoder-cmds
+replace define V4L2_DEC_CMD_FLUSH decoder-cmds
 
 replace define V4L2_DEC_CMD_START_MUTE_AUDIO decoder-cmds
 replace define V4L2_DEC_CMD_PAUSE_TO_BLACK decoder-cmds
diff --git a/Documentation/power/drivers-testing.rst b/Documentation/power/drivers-testing.rst
index e53f1999fc39..d77d2894f9fe 100644
--- a/Documentation/power/drivers-testing.rst
+++ b/Documentation/power/drivers-testing.rst
@@ -39,9 +39,10 @@ c) Compile the driver directly into the kernel and try the test modes of
 d) Attempt to hibernate with the driver compiled directly into the kernel
    in the "reboot", "shutdown" and "platform" modes.
 
-e) Try the test modes of suspend (see: Documentation/power/basic-pm-debugging.rst,
-   2).  [As far as the STR tests are concerned, it should not matter whether or
-   not the driver is built as a module.]
+e) Try the test modes of suspend (see:
+   Documentation/power/basic-pm-debugging.rst, 2).  [As far as the STR tests are
+   concerned, it should not matter whether or not the driver is built as a
+   module.]
 
 f) Attempt to suspend to RAM using the s2ram tool with the driver loaded
    (see: Documentation/power/basic-pm-debugging.rst, 2).
diff --git a/Documentation/power/freezing-of-tasks.rst b/Documentation/power/freezing-of-tasks.rst
index ef110fe55e82..8bd693399834 100644
--- a/Documentation/power/freezing-of-tasks.rst
+++ b/Documentation/power/freezing-of-tasks.rst
@@ -215,30 +215,31 @@ VI. Are there any precautions to be taken to prevent freezing failures?
 
 Yes, there are.
 
-First of all, grabbing the 'system_transition_mutex' lock to mutually exclude a piece of code
-from system-wide sleep such as suspend/hibernation is not encouraged.
-If possible, that piece of code must instead hook onto the suspend/hibernation
-notifiers to achieve mutual exclusion. Look at the CPU-Hotplug code
-(kernel/cpu.c) for an example.
-
-However, if that is not feasible, and grabbing 'system_transition_mutex' is deemed necessary,
-it is strongly discouraged to directly call mutex_[un]lock(&system_transition_mutex) since
-that could lead to freezing failures, because if the suspend/hibernate code
-successfully acquired the 'system_transition_mutex' lock, and hence that other entity failed
-to acquire the lock, then that task would get blocked in TASK_UNINTERRUPTIBLE
-state. As a consequence, the freezer would not be able to freeze that task,
-leading to freezing failure.
+First of all, grabbing the 'system_transition_mutex' lock to mutually exclude a
+piece of code from system-wide sleep such as suspend/hibernation is not
+encouraged.  If possible, that piece of code must instead hook onto the
+suspend/hibernation notifiers to achieve mutual exclusion. Look at the
+CPU-Hotplug code (kernel/cpu.c) for an example.
+
+However, if that is not feasible, and grabbing 'system_transition_mutex' is
+deemed necessary, it is strongly discouraged to directly call
+mutex_[un]lock(&system_transition_mutex) since that could lead to freezing
+failures, because if the suspend/hibernate code successfully acquired the
+'system_transition_mutex' lock, and hence that other entity failed to acquire
+the lock, then that task would get blocked in TASK_UNINTERRUPTIBLE state. As a
+consequence, the freezer would not be able to freeze that task, leading to
+freezing failure.
 
 However, the [un]lock_system_sleep() APIs are safe to use in this scenario,
 since they ask the freezer to skip freezing this task, since it is anyway
-"frozen enough" as it is blocked on 'system_transition_mutex', which will be released
-only after the entire suspend/hibernation sequence is complete.
-So, to summarize, use [un]lock_system_sleep() instead of directly using
+"frozen enough" as it is blocked on 'system_transition_mutex', which will be
+released only after the entire suspend/hibernation sequence is complete.  So, to
+summarize, use [un]lock_system_sleep() instead of directly using
 mutex_[un]lock(&system_transition_mutex). That would prevent freezing failures.
 
 V. Miscellaneous
 ================
 
 /sys/power/pm_freeze_timeout controls how long it will cost at most to freeze
-all user space processes or all freezable kernel threads, in unit of millisecond.
-The default value is 20000, with range of unsigned integer.
+all user space processes or all freezable kernel threads, in unit of
+millisecond.  The default value is 20000, with range of unsigned integer.
diff --git a/Documentation/power/opp.rst b/Documentation/power/opp.rst
index 209c7613f5a4..e3cc4f349ea8 100644
--- a/Documentation/power/opp.rst
+++ b/Documentation/power/opp.rst
@@ -73,19 +73,21 @@ factors. Example usage: Thermal management or other exceptional situations where
 SoC framework might choose to disable a higher frequency OPP to safely continue
 operations until that OPP could be re-enabled if possible.
 
-OPP library facilitates this concept in it's implementation. The following
+OPP library facilitates this concept in its implementation. The following
 operational functions operate only on available opps:
-opp_find_freq_{ceil, floor}, dev_pm_opp_get_voltage, dev_pm_opp_get_freq, dev_pm_opp_get_opp_count
+opp_find_freq_{ceil, floor}, dev_pm_opp_get_voltage, dev_pm_opp_get_freq,
+dev_pm_opp_get_opp_count
 
-dev_pm_opp_find_freq_exact is meant to be used to find the opp pointer which can then
-be used for dev_pm_opp_enable/disable functions to make an opp available as required.
+dev_pm_opp_find_freq_exact is meant to be used to find the opp pointer
+which can then be used for dev_pm_opp_enable/disable functions to make an
+opp available as required.
 
 WARNING: Users of OPP library should refresh their availability count using
-get_opp_count if dev_pm_opp_enable/disable functions are invoked for a device, the
-exact mechanism to trigger these or the notification mechanism to other
-dependent subsystems such as cpufreq are left to the discretion of the SoC
-specific framework which uses the OPP library. Similar care needs to be taken
-care to refresh the cpufreq table in cases of these operations.
+get_opp_count if dev_pm_opp_enable/disable functions are invoked for a
+device, the exact mechanism to trigger these or the notification mechanism
+to other dependent subsystems such as cpufreq are left to the discretion of
+the SoC specific framework which uses the OPP library. Similar care needs
+to be taken care to refresh the cpufreq table in cases of these operations.
 
 2. Initial OPP List Registration
 ================================
@@ -99,11 +101,11 @@ OPPs dynamically using the dev_pm_opp_enable / disable functions.
 dev_pm_opp_add
 	Add a new OPP for a specific domain represented by the device pointer.
 	The OPP is defined using the frequency and voltage. Once added, the OPP
-	is assumed to be available and control of it's availability can be done
-	with the dev_pm_opp_enable/disable functions. OPP library internally stores
-	and manages this information in the opp struct. This function may be
-	used by SoC framework to define a optimal list as per the demands of
-	SoC usage environment.
+	is assumed to be available and control of its availability can be done
+	with the dev_pm_opp_enable/disable functions. OPP library
+	internally stores and manages this information in the opp struct.
+	This function may be used by SoC framework to define a optimal list
+	as per the demands of SoC usage environment.
 
 	WARNING:
 		Do not use this function in interrupt context.
@@ -354,7 +356,7 @@ struct dev_pm_opp
 
 struct device
 	This is used to identify a domain to the OPP layer. The
-	nature of the device and it's implementation is left to the user of
+	nature of the device and its implementation is left to the user of
 	OPP library such as the SoC framework.
 
 Overall, in a simplistic view, the data structure operations is represented as
diff --git a/Documentation/power/pci.rst b/Documentation/power/pci.rst
index 0e2ef7429304..51e0a493d284 100644
--- a/Documentation/power/pci.rst
+++ b/Documentation/power/pci.rst
@@ -426,12 +426,12 @@ pm->runtime_idle() callback.
 2.4. System-Wide Power Transitions
 ----------------------------------
 There are a few different types of system-wide power transitions, described in
-Documentation/driver-api/pm/devices.rst.  Each of them requires devices to be handled
-in a specific way and the PM core executes subsystem-level power management
-callbacks for this purpose.  They are executed in phases such that each phase
-involves executing the same subsystem-level callback for every device belonging
-to the given subsystem before the next phase begins.  These phases always run
-after tasks have been frozen.
+Documentation/driver-api/pm/devices.rst.  Each of them requires devices to be
+handled in a specific way and the PM core executes subsystem-level power
+management callbacks for this purpose.  They are executed in phases such that
+each phase involves executing the same subsystem-level callback for every device
+belonging to the given subsystem before the next phase begins.  These phases
+always run after tasks have been frozen.
 
 2.4.1. System Suspend
 ^^^^^^^^^^^^^^^^^^^^^
@@ -636,12 +636,12 @@ System restore requires a hibernation image to be loaded into memory and the
 pre-hibernation memory contents to be restored before the pre-hibernation system
 activity can be resumed.
 
-As described in Documentation/driver-api/pm/devices.rst, the hibernation image is loaded
-into memory by a fresh instance of the kernel, called the boot kernel, which in
-turn is loaded and run by a boot loader in the usual way.  After the boot kernel
-has loaded the image, it needs to replace its own code and data with the code
-and data of the "hibernated" kernel stored within the image, called the image
-kernel.  For this purpose all devices are frozen just like before creating
+As described in Documentation/driver-api/pm/devices.rst, the hibernation image
+is loaded into memory by a fresh instance of the kernel, called the boot kernel,
+which in turn is loaded and run by a boot loader in the usual way.  After the
+boot kernel has loaded the image, it needs to replace its own code and data with
+the code and data of the "hibernated" kernel stored within the image, called the
+image kernel.  For this purpose all devices are frozen just like before creating
 the image during hibernation, in the
 
 	prepare, freeze, freeze_noirq
@@ -691,8 +691,8 @@ controlling the runtime power management of their devices.
 
 At the time of this writing there are two ways to define power management
 callbacks for a PCI device driver, the recommended one, based on using a
-dev_pm_ops structure described in Documentation/driver-api/pm/devices.rst, and the
-"legacy" one, in which the .suspend(), .suspend_late(), .resume_early(), and
+dev_pm_ops structure described in Documentation/driver-api/pm/devices.rst, and
+the "legacy" one, in which the .suspend(), .suspend_late(), .resume_early(), and
 .resume() callbacks from struct pci_driver are used.  The legacy approach,
 however, doesn't allow one to define runtime power management callbacks and is
 not really suitable for any new drivers.  Therefore it is not covered by this
diff --git a/Documentation/power/pm_qos_interface.rst b/Documentation/power/pm_qos_interface.rst
index 3097694fba69..0d62d506caf0 100644
--- a/Documentation/power/pm_qos_interface.rst
+++ b/Documentation/power/pm_qos_interface.rst
@@ -8,8 +8,8 @@ one of the parameters.
 
 Two different PM QoS frameworks are available:
 1. PM QoS classes for cpu_dma_latency
-2. the per-device PM QoS framework provides the API to manage the per-device latency
-constraints and PM QoS flags.
+2. The per-device PM QoS framework provides the API to manage the
+   per-device latency constraints and PM QoS flags.
 
 Each parameters have defined units:
 
@@ -47,14 +47,14 @@ void pm_qos_add_request(handle, param_class, target_value):
   pm_qos API functions.
 
 void pm_qos_update_request(handle, new_target_value):
-  Will update the list element pointed to by the handle with the new target value
-  and recompute the new aggregated target, calling the notification tree if the
-  target is changed.
+  Will update the list element pointed to by the handle with the new target
+  value and recompute the new aggregated target, calling the notification tree
+  if the target is changed.
 
 void pm_qos_remove_request(handle):
-  Will remove the element.  After removal it will update the aggregate target and
-  call the notification tree if the target was changed as a result of removing
-  the request.
+  Will remove the element.  After removal it will update the aggregate target
+  and call the notification tree if the target was changed as a result of
+  removing the request.
 
 int pm_qos_request(param_class):
   Returns the aggregated value for a given PM QoS class.
@@ -167,9 +167,9 @@ int dev_pm_qos_expose_flags(device, value)
   change the value of the PM_QOS_FLAG_NO_POWER_OFF flag.
 
 void dev_pm_qos_hide_flags(device)
-  Drop the request added by dev_pm_qos_expose_flags() from the device's PM QoS list
-  of flags and remove sysfs attribute pm_qos_no_power_off from the device's power
-  directory.
+  Drop the request added by dev_pm_qos_expose_flags() from the device's PM QoS
+  list of flags and remove sysfs attribute pm_qos_no_power_off from the device's
+  power directory.
 
 Notification mechanisms:
 
@@ -179,8 +179,8 @@ int dev_pm_qos_add_notifier(device, notifier, type):
   Adds a notification callback function for the device for a particular request
   type.
 
-  The callback is called when the aggregated value of the device constraints list
-  is changed.
+  The callback is called when the aggregated value of the device constraints
+  list is changed.
 
 int dev_pm_qos_remove_notifier(device, notifier, type):
   Removes the notification callback function for the device.
diff --git a/Documentation/power/runtime_pm.rst b/Documentation/power/runtime_pm.rst
index 2c2ec99b5088..ab8406c84254 100644
--- a/Documentation/power/runtime_pm.rst
+++ b/Documentation/power/runtime_pm.rst
@@ -268,8 +268,8 @@ defined in include/linux/pm.h:
   `unsigned int runtime_auto;`
     - if set, indicates that the user space has allowed the device driver to
       power manage the device at run time via the /sys/devices/.../power/control
-      `interface;` it may only be modified with the help of the pm_runtime_allow()
-      and pm_runtime_forbid() helper functions
+      `interface;` it may only be modified with the help of the
+      pm_runtime_allow() and pm_runtime_forbid() helper functions
 
   `unsigned int no_callbacks;`
     - indicates that the device does not use the runtime PM callbacks (see
diff --git a/Documentation/power/suspend-and-cpuhotplug.rst b/Documentation/power/suspend-and-cpuhotplug.rst
index 7ac8e1f549f4..572d968c5375 100644
--- a/Documentation/power/suspend-and-cpuhotplug.rst
+++ b/Documentation/power/suspend-and-cpuhotplug.rst
@@ -106,8 +106,8 @@ execution during resume):
 * Release system_transition_mutex lock.
 
 
-It is to be noted here that the system_transition_mutex lock is acquired at the very
-beginning, when we are just starting out to suspend, and then released only
+It is to be noted here that the system_transition_mutex lock is acquired at the
+very beginning, when we are just starting out to suspend, and then released only
 after the entire cycle is complete (i.e., suspend + resume).
 
 ::
@@ -165,7 +165,8 @@ Important files and functions/entry points:
 
 - kernel/power/process.c : freeze_processes(), thaw_processes()
 - kernel/power/suspend.c : suspend_prepare(), suspend_enter(), suspend_finish()
-- kernel/cpu.c: cpu_[up|down](), _cpu_[up|down](), [disable|enable]_nonboot_cpus()
+- kernel/cpu.c: cpu_[up|down](), _cpu_[up|down](),
+  [disable|enable]_nonboot_cpus()
 
 
 
diff --git a/Documentation/power/swsusp.rst b/Documentation/power/swsusp.rst
index d000312f6965..8524f079e05c 100644
--- a/Documentation/power/swsusp.rst
+++ b/Documentation/power/swsusp.rst
@@ -118,7 +118,8 @@ In a really perfect world::
 
   echo 1 > /proc/acpi/sleep       # for standby
   echo 2 > /proc/acpi/sleep       # for suspend to ram
-  echo 3 > /proc/acpi/sleep       # for suspend to ram, but with more power conservative
+  echo 3 > /proc/acpi/sleep       # for suspend to ram, but with more power
+                                  # conservative
   echo 4 > /proc/acpi/sleep       # for suspend to disk
   echo 5 > /proc/acpi/sleep       # for shutdown unfriendly the system
 
@@ -192,8 +193,8 @@ Q:
 
 A:
   The freezing of tasks is a mechanism by which user space processes and some
-  kernel threads are controlled during hibernation or system-wide suspend (on some
-  architectures).  See freezing-of-tasks.txt for details.
+  kernel threads are controlled during hibernation or system-wide suspend (on
+  some architectures).  See freezing-of-tasks.txt for details.
 
 Q:
   What is the difference between "platform" and "shutdown"?
@@ -282,7 +283,8 @@ A:
       suspend(PMSG_FREEZE): devices are frozen so that they don't interfere
       with state snapshot
 
-      state snapshot: copy of whole used memory is taken with interrupts disabled
+      state snapshot: copy of whole used memory is taken with interrupts
+      disabled
 
       resume(): devices are woken up so that we can write image to swap
 
@@ -353,8 +355,8 @@ Q:
 
 A:
   Generally, yes, you can.  However, it requires you to use the "resume=" and
-  "resume_offset=" kernel command line parameters, so the resume from a swap file
-  cannot be initiated from an initrd or initramfs image.  See
+  "resume_offset=" kernel command line parameters, so the resume from a swap
+  file cannot be initiated from an initrd or initramfs image.  See
   swsusp-and-swap-files.txt for details.
 
 Q:
diff --git a/Documentation/sound/kernel-api/writing-an-alsa-driver.rst b/Documentation/sound/kernel-api/writing-an-alsa-driver.rst
index 132f5eb9b530..f169d58ca019 100644
--- a/Documentation/sound/kernel-api/writing-an-alsa-driver.rst
+++ b/Documentation/sound/kernel-api/writing-an-alsa-driver.rst
@@ -805,6 +805,7 @@ destructor and PCI entries. Example code is shown first, below.
                       return -EBUSY;
               }
               chip->irq = pci->irq;
+              card->sync_irq = chip->irq;
 
               /* (2) initialization of the chip hardware */
               .... /*   (not implemented in this document) */
@@ -965,6 +966,15 @@ usually like the following:
           return IRQ_HANDLED;
   }
 
+After requesting the IRQ, you can passed it to ``card->sync_irq``
+field:
+::
+
+          card->irq = chip->irq;
+
+This allows PCM core automatically performing
+:c:func:`synchronize_irq()` at the necessary timing like ``hw_free``.
+See the later section `sync_stop callback`_ for details.
 
 Now let's write the corresponding destructor for the resources above.
 The role of destructor is simple: disable the hardware (if already
@@ -1270,21 +1280,23 @@ shows only the skeleton, how to build up the PCM interfaces.
               /* the hardware-specific codes will be here */
               ....
               return 0;
-
       }
 
       /* hw_params callback */
       static int snd_mychip_pcm_hw_params(struct snd_pcm_substream *substream,
                                    struct snd_pcm_hw_params *hw_params)
       {
-              return snd_pcm_lib_malloc_pages(substream,
-                                         params_buffer_bytes(hw_params));
+              /* the hardware-specific codes will be here */
+              ....
+              return 0;
       }
 
       /* hw_free callback */
       static int snd_mychip_pcm_hw_free(struct snd_pcm_substream *substream)
       {
-              return snd_pcm_lib_free_pages(substream);
+              /* the hardware-specific codes will be here */
+              ....
+              return 0;
       }
 
       /* prepare callback */
@@ -1339,7 +1351,6 @@ shows only the skeleton, how to build up the PCM interfaces.
       static struct snd_pcm_ops snd_mychip_playback_ops = {
               .open =        snd_mychip_playback_open,
               .close =       snd_mychip_playback_close,
-              .ioctl =       snd_pcm_lib_ioctl,
               .hw_params =   snd_mychip_pcm_hw_params,
               .hw_free =     snd_mychip_pcm_hw_free,
               .prepare =     snd_mychip_pcm_prepare,
@@ -1351,7 +1362,6 @@ shows only the skeleton, how to build up the PCM interfaces.
       static struct snd_pcm_ops snd_mychip_capture_ops = {
               .open =        snd_mychip_capture_open,
               .close =       snd_mychip_capture_close,
-              .ioctl =       snd_pcm_lib_ioctl,
               .hw_params =   snd_mychip_pcm_hw_params,
               .hw_free =     snd_mychip_pcm_hw_free,
               .prepare =     snd_mychip_pcm_prepare,
@@ -1382,9 +1392,9 @@ shows only the skeleton, how to build up the PCM interfaces.
                               &snd_mychip_capture_ops);
               /* pre-allocation of buffers */
               /* NOTE: this may fail */
-              snd_pcm_lib_preallocate_pages_for_all(pcm, SNDRV_DMA_TYPE_DEV,
-                                                    snd_dma_pci_data(chip->pci),
-                                                    64*1024, 64*1024);
+              snd_pcm_set_managed_buffer_all(pcm, SNDRV_DMA_TYPE_DEV,
+                                             &chip->pci->dev,
+                                             64*1024, 64*1024);
               return 0;
       }
 
@@ -1454,7 +1464,6 @@ The operators are defined typically like this:
   static struct snd_pcm_ops snd_mychip_playback_ops = {
           .open =        snd_mychip_pcm_open,
           .close =       snd_mychip_pcm_close,
-          .ioctl =       snd_pcm_lib_ioctl,
           .hw_params =   snd_mychip_pcm_hw_params,
           .hw_free =     snd_mychip_pcm_hw_free,
           .prepare =     snd_mychip_pcm_prepare,
@@ -1465,13 +1474,14 @@ The operators are defined typically like this:
 All the callbacks are described in the Operators_ subsection.
 
 After setting the operators, you probably will want to pre-allocate the
-buffer. For the pre-allocation, simply call the following:
+buffer and set up the managed allocation mode.
+For that, simply call the following:
 
 ::
 
-  snd_pcm_lib_preallocate_pages_for_all(pcm, SNDRV_DMA_TYPE_DEV,
-                                        snd_dma_pci_data(chip->pci),
-                                        64*1024, 64*1024);
+  snd_pcm_set_managed_buffer_all(pcm, SNDRV_DMA_TYPE_DEV,
+                                 &chip->pci->dev,
+                                 64*1024, 64*1024);
 
 It will allocate a buffer up to 64kB as default. Buffer management
 details will be described in the later section `Buffer and Memory
@@ -1621,8 +1631,7 @@ For the operators (callbacks) of each sound driver, most of these
 records are supposed to be read-only. Only the PCM middle-layer changes
 / updates them. The exceptions are the hardware description (hw) DMA
 buffer information and the private data. Besides, if you use the
-standard buffer allocation method via
-:c:func:`snd_pcm_lib_malloc_pages()`, you don't need to set the
+standard managed buffer allocation mode, you don't need to set the
 DMA buffer information by yourself.
 
 In the sections below, important records are explained.
@@ -1776,8 +1785,8 @@ the physical address of the buffer. This field is specified only when
 the buffer is a linear buffer. ``dma_bytes`` holds the size of buffer
 in bytes. ``dma_private`` is used for the ALSA DMA allocator.
 
-If you use a standard ALSA function,
-:c:func:`snd_pcm_lib_malloc_pages()`, for allocating the buffer,
+If you use either the managed buffer allocation mode or the standard
+API function :c:func:`snd_pcm_lib_malloc_pages()` for allocating the buffer,
 these fields are set by the ALSA middle layer, and you should *not*
 change them by yourself. You can read them but not write them. On the
 other hand, if you want to allocate the buffer by yourself, you'll
@@ -1911,7 +1920,10 @@ ioctl callback
 ~~~~~~~~~~~~~~
 
 This is used for any special call to pcm ioctls. But usually you can
-pass a generic ioctl callback, :c:func:`snd_pcm_lib_ioctl()`.
+leave it as NULL, then PCM core calls the generic ioctl callback
+function :c:func:`snd_pcm_lib_ioctl()`.  If you need to deal with the
+unique setup of channel info or reset procedure, you can pass your own
+callback function here.
 
 hw_params callback
 ~~~~~~~~~~~~~~~~~~~
@@ -1929,8 +1941,12 @@ Many hardware setups should be done in this callback, including the
 allocation of buffers.
 
 Parameters to be initialized are retrieved by
-:c:func:`params_xxx()` macros. To allocate buffer, you can call a
-helper function,
+:c:func:`params_xxx()` macros.
+
+When you set up the managed buffer allocation mode for the substream,
+a buffer is already allocated before this callback gets
+called. Alternatively, you can call a helper function below for
+allocating the buffer, too.
 
 ::
 
@@ -1964,18 +1980,23 @@ hw_free callback
   static int snd_xxx_hw_free(struct snd_pcm_substream *substream);
 
 This is called to release the resources allocated via
-``hw_params``. For example, releasing the buffer via
-:c:func:`snd_pcm_lib_malloc_pages()` is done by calling the
-following:
-
-::
-
-  snd_pcm_lib_free_pages(substream);
+``hw_params``.
 
 This function is always called before the close callback is called.
 Also, the callback may be called multiple times, too. Keep track
 whether the resource was already released.
 
+When you have set up the managed buffer allocation mode for the PCM
+substream, the allocated PCM buffer will be automatically released
+after this callback gets called.  Otherwise you'll have to release the
+buffer manually.  Typically, when the buffer was allocated from the
+pre-allocated pool, you can use the standard API function
+:c:func:`snd_pcm_lib_malloc_pages()` like:
+
+::
+
+  snd_pcm_lib_free_pages(substream);
+
 prepare callback
 ~~~~~~~~~~~~~~~~
 
@@ -2048,6 +2069,37 @@ flag set, and you cannot call functions which may sleep. The
 triggering the DMA. The other stuff should be initialized
 ``hw_params`` and ``prepare`` callbacks properly beforehand.
 
+sync_stop callback
+~~~~~~~~~~~~~~~~~~
+
+::
+
+  static int snd_xxx_sync_stop(struct snd_pcm_substream *substream);
+
+This callback is optional, and NULL can be passed.  It's called after
+the PCM core stops the stream and changes the stream state
+``prepare``, ``hw_params`` or ``hw_free``.
+Since the IRQ handler might be still pending, we need to wait until
+the pending task finishes before moving to the next step; otherwise it
+might lead to a crash due to resource conflicts or access to the freed
+resources.  A typical behavior is to call a synchronization function
+like :c:func:`synchronize_irq()` here.
+
+For majority of drivers that need only a call of
+:c:func:`synchronize_irq()`, there is a simpler setup, too.
+While keeping NULL to ``sync_stop`` PCM callback, the driver can set
+``card->sync_irq`` field to store the valid interrupt number after
+requesting an IRQ, instead.   Then PCM core will look call
+:c:func:`synchronize_irq()` with the given IRQ appropriately.
+
+If the IRQ handler is released at the card destructor, you don't need
+to clear ``card->sync_irq``, as the card itself is being released.
+So, usually you'll need to add just a single line for assigning
+``card->sync_irq`` in the driver code unless the driver re-acquires
+the IRQ.  When the driver frees and re-acquires the IRQ dynamically
+(e.g. for suspend/resume), it needs to clear and re-set
+``card->sync_irq`` again appropriately.
+
 pointer callback
 ~~~~~~~~~~~~~~~~
 
@@ -2095,10 +2147,12 @@ This callback is atomic as default.
 page callback
 ~~~~~~~~~~~~~
 
-This callback is optional too. This callback is used mainly for
-non-contiguous buffers. The mmap calls this callback to get the page
-address. Some examples will be explained in the later section `Buffer
-and Memory Management`_, too.
+This callback is optional too. The mmap calls this callback to get the
+page fault address.
+
+Since the recent changes, you need no special callback any longer for
+the standard SG-buffer or vmalloc-buffer. Hence this callback should
+be rarely used.
 
 mmap calllback
 ~~~~~~~~~~~~~~
@@ -3512,7 +3566,7 @@ bus).
 ::
 
   snd_pcm_lib_preallocate_pages_for_all(pcm, SNDRV_DMA_TYPE_DEV,
-                                        snd_dma_pci_data(pci), size, max);
+                                        &pci->dev, size, max);
 
 where ``size`` is the byte size to be pre-allocated and the ``max`` is
 the maximum size to be changed via the ``prealloc`` proc file. The
@@ -3523,12 +3577,14 @@ The second argument (type) and the third argument (device pointer) are
 dependent on the bus. For normal devices, pass the device pointer
 (typically identical as ``card->dev``) to the third argument with
 ``SNDRV_DMA_TYPE_DEV`` type. For the continuous buffer unrelated to the
-bus can be pre-allocated with ``SNDRV_DMA_TYPE_CONTINUOUS`` type and the
-``snd_dma_continuous_data(GFP_KERNEL)`` device pointer, where
-``GFP_KERNEL`` is the kernel allocation flag to use. For the
-scatter-gather buffers, use ``SNDRV_DMA_TYPE_DEV_SG`` with the device
-pointer (see the `Non-Contiguous Buffers`_
-section).
+bus can be pre-allocated with ``SNDRV_DMA_TYPE_CONTINUOUS`` type.
+You can pass NULL to the device pointer in that case, which is the
+default mode implying to allocate with ``GFP_KRENEL`` flag.
+If you need a different GFP flag, you can pass it by encoding the flag
+into the device pointer via a special macro
+:c:func:`snd_dma_continuous_data()`.
+For the scatter-gather buffers, use ``SNDRV_DMA_TYPE_DEV_SG`` with the
+device pointer (see the `Non-Contiguous Buffers`_ section).
 
 Once the buffer is pre-allocated, you can use the allocator in the
 ``hw_params`` callback:
@@ -3539,6 +3595,25 @@ Once the buffer is pre-allocated, you can use the allocator in the
 
 Note that you have to pre-allocate to use this function.
 
+Most of drivers use, though, rather the newly introduced "managed
+buffer allocation mode" instead of the manual allocation or release.
+This is done by calling :c:func:`snd_pcm_set_managed_buffer_all()`
+instead of :c:func:`snd_pcm_lib_preallocate_pages_for_all()`.
+
+::
+
+  snd_pcm_set_managed_buffer_all(pcm, SNDRV_DMA_TYPE_DEV,
+                                 &pci->dev, size, max);
+
+where passed arguments are identical in both functions.
+The difference in the managed mode is that PCM core will call
+:c:func:`snd_pcm_lib_malloc_pages()` internally already before calling
+the PCM ``hw_params`` callback, and call :c:func:`snd_pcm_lib_free_pages()`
+after the PCM ``hw_free`` callback automatically.  So the driver
+doesn't have to call these functions explicitly in its callback any
+longer.  This made many driver code having NULL ``hw_params`` and
+``hw_free`` entries.
+
 External Hardware Buffers
 -------------------------
 
@@ -3693,20 +3768,26 @@ provides an interface for handling SG-buffers. The API is provided in
 ``<sound/pcm.h>``.
 
 For creating the SG-buffer handler, call
-:c:func:`snd_pcm_lib_preallocate_pages()` or
-:c:func:`snd_pcm_lib_preallocate_pages_for_all()` with
+:c:func:`snd_pcm_set_managed_buffer()` or
+:c:func:`snd_pcm_set_managed_buffer_all()` with
 ``SNDRV_DMA_TYPE_DEV_SG`` in the PCM constructor like other PCI
-pre-allocator. You need to pass ``snd_dma_pci_data(pci)``, where pci is
+pre-allocator. You need to pass ``&pci->dev``, where pci is
 the :c:type:`struct pci_dev <pci_dev>` pointer of the chip as
-well. The ``struct snd_sg_buf`` instance is created as
-``substream->dma_private``. You can cast the pointer like:
+well.
+
+::
+
+  snd_pcm_set_managed_buffer_all(pcm, SNDRV_DMA_TYPE_DEV_SG,
+                                 &pci->dev, size, max);
+
+The ``struct snd_sg_buf`` instance is created as
+``substream->dma_private`` in turn. You can cast the pointer like:
 
 ::
 
   struct snd_sg_buf *sgbuf = (struct snd_sg_buf *)substream->dma_private;
 
-Then call :c:func:`snd_pcm_lib_malloc_pages()` in the ``hw_params``
-callback as well as in the case of normal PCI buffer. The SG-buffer
+Then in :c:func:`snd_pcm_lib_malloc_pages()` call, the common SG-buffer
 handler will allocate the non-contiguous kernel pages of the given size
 and map them onto the virtually contiguous memory. The virtual pointer
 is addressed in runtime->dma_area. The physical address
@@ -3715,41 +3796,40 @@ physically non-contiguous. The physical address table is set up in
 ``sgbuf->table``. You can get the physical address at a certain offset
 via :c:func:`snd_pcm_sgbuf_get_addr()`.
 
-When a SG-handler is used, you need to set
-:c:func:`snd_pcm_sgbuf_ops_page()` as the ``page`` callback. (See
-`page callback`_ section.)
-
-To release the data, call :c:func:`snd_pcm_lib_free_pages()` in
-the ``hw_free`` callback as usual.
+If you need to release the SG-buffer data explicitly, call the
+standard API function :c:func:`snd_pcm_lib_free_pages()` as usual.
 
 Vmalloc'ed Buffers
 ------------------
 
 It's possible to use a buffer allocated via :c:func:`vmalloc()`, for
-example, for an intermediate buffer. Since the allocated pages are not
-contiguous, you need to set the ``page`` callback to obtain the physical
-address at every offset.
+example, for an intermediate buffer. In the recent version of kernel,
+you can simply allocate it via standard
+:c:func:`snd_pcm_lib_malloc_pages()` and co after setting up the
+buffer preallocation with ``SNDRV_DMA_TYPE_VMALLOC`` type.
 
-The easiest way to achieve it would be to use
-:c:func:`snd_pcm_lib_alloc_vmalloc_buffer()` for allocating the buffer
-via :c:func:`vmalloc()`, and set :c:func:`snd_pcm_sgbuf_ops_page()` to
-the ``page`` callback.  At release, you need to call
-:c:func:`snd_pcm_lib_free_vmalloc_buffer()`.
+::
 
-If you want to implementation the ``page`` manually, it would be like
-this:
+  snd_pcm_set_managed_buffer_all(pcm, SNDRV_DMA_TYPE_VMALLOC,
+                                 NULL, 0, 0);
 
-::
+The NULL is passed to the device pointer argument, which indicates
+that the default pages (GFP_KERNEL and GFP_HIGHMEM) will be
+allocated.
 
-  #include <linux/vmalloc.h>
+Also, note that zero is passed to both the size and the max size
+arguments here.  Since each vmalloc call should succeed at any time,
+we don't need to pre-allocate the buffers like other continuous
+pages.
 
-  /* get the physical page pointer on the given offset */
-  static struct page *mychip_page(struct snd_pcm_substream *substream,
-                                  unsigned long offset)
-  {
-          void *pageptr = substream->runtime->dma_area + offset;
-          return vmalloc_to_page(pageptr);
-  }
+If you need the 32bit DMA allocation, pass the device pointer encoded
+by :c:func:`snd_dma_continuous_data()` with ``GFP_KERNEL|__GFP_DMA32``
+argument.
+
+::
+
+  snd_pcm_set_managed_buffer_all(pcm, SNDRV_DMA_TYPE_VMALLOC,
+          snd_dma_continuous_data(GFP_KERNEL | __GFP_DMA32), 0, 0);
 
 Proc Interface
 ==============
diff --git a/Documentation/x86/boot.rst b/Documentation/x86/boot.rst
index 08a2f100c0e6..90bb8f5ab384 100644
--- a/Documentation/x86/boot.rst
+++ b/Documentation/x86/boot.rst
@@ -68,8 +68,25 @@ Protocol 2.12	(Kernel 3.8) Added the xloadflags field and extension fields
 Protocol 2.13	(Kernel 3.14) Support 32- and 64-bit flags being set in
 		xloadflags to support booting a 64-bit kernel from 32-bit
 		EFI
+
+Protocol 2.14:	BURNT BY INCORRECT COMMIT ae7e1238e68f2a472a125673ab506d49158c1889
+		(x86/boot: Add ACPI RSDP address to setup_header)
+		DO NOT USE!!! ASSUME SAME AS 2.13.
+
+Protocol 2.15:	(Kernel 5.5) Added the kernel_info and kernel_info.setup_type_max.
 =============	============================================================
 
+.. note::
+     The protocol version number should be changed only if the setup header
+     is changed. There is no need to update the version number if boot_params
+     or kernel_info are changed. Additionally, it is recommended to use
+     xloadflags (in this case the protocol version number should not be
+     updated either) or kernel_info to communicate supported Linux kernel
+     features to the boot loader. Due to very limited space available in
+     the original setup header every update to it should be considered
+     with great care. Starting from the protocol 2.15 the primary way to
+     communicate things to the boot loader is the kernel_info.
+
 
 Memory Layout
 =============
@@ -207,6 +224,7 @@ Offset/Size	Proto		Name			Meaning
 0258/8		2.10+		pref_address		Preferred loading address
 0260/4		2.10+		init_size		Linear memory required during initialization
 0264/4		2.11+		handover_offset		Offset of handover entry point
+0268/4		2.15+		kernel_info_offset	Offset of the kernel_info
 ===========	========	=====================	============================================
 
 .. note::
@@ -809,6 +827,47 @@ Protocol:	2.09+
   sure to consider the case where the linked list already contains
   entries.
 
+  The setup_data is a bit awkward to use for extremely large data objects,
+  both because the setup_data header has to be adjacent to the data object
+  and because it has a 32-bit length field. However, it is important that
+  intermediate stages of the boot process have a way to identify which
+  chunks of memory are occupied by kernel data.
+
+  Thus setup_indirect struct and SETUP_INDIRECT type were introduced in
+  protocol 2.15.
+
+  struct setup_indirect {
+    __u32 type;
+    __u32 reserved;  /* Reserved, must be set to zero. */
+    __u64 len;
+    __u64 addr;
+  };
+
+  The type member is a SETUP_INDIRECT | SETUP_* type. However, it cannot be
+  SETUP_INDIRECT itself since making the setup_indirect a tree structure
+  could require a lot of stack space in something that needs to parse it
+  and stack space can be limited in boot contexts.
+
+  Let's give an example how to point to SETUP_E820_EXT data using setup_indirect.
+  In this case setup_data and setup_indirect will look like this:
+
+  struct setup_data {
+    __u64 next = 0 or <addr_of_next_setup_data_struct>;
+    __u32 type = SETUP_INDIRECT;
+    __u32 len = sizeof(setup_data);
+    __u8 data[sizeof(setup_indirect)] = struct setup_indirect {
+      __u32 type = SETUP_INDIRECT | SETUP_E820_EXT;
+      __u32 reserved = 0;
+      __u64 len = <len_of_SETUP_E820_EXT_data>;
+      __u64 addr = <addr_of_SETUP_E820_EXT_data>;
+    }
+  }
+
+.. note::
+     SETUP_INDIRECT | SETUP_NONE objects cannot be properly distinguished
+     from SETUP_INDIRECT itself. So, this kind of objects cannot be provided
+     by the bootloaders.
+
 ============	============
 Field name:	pref_address
 Type:		read (reloc)
@@ -855,6 +914,121 @@ Offset/size:	0x264/4
 
   See EFI HANDOVER PROTOCOL below for more details.
 
+============	==================
+Field name:	kernel_info_offset
+Type:		read
+Offset/size:	0x268/4
+Protocol:	2.15+
+============	==================
+
+  This field is the offset from the beginning of the kernel image to the
+  kernel_info. The kernel_info structure is embedded in the Linux image
+  in the uncompressed protected mode region.
+
+
+The kernel_info
+===============
+
+The relationships between the headers are analogous to the various data
+sections:
+
+  setup_header = .data
+  boot_params/setup_data = .bss
+
+What is missing from the above list? That's right:
+
+  kernel_info = .rodata
+
+We have been (ab)using .data for things that could go into .rodata or .bss for
+a long time, for lack of alternatives and -- especially early on -- inertia.
+Also, the BIOS stub is responsible for creating boot_params, so it isn't
+available to a BIOS-based loader (setup_data is, though).
+
+setup_header is permanently limited to 144 bytes due to the reach of the
+2-byte jump field, which doubles as a length field for the structure, combined
+with the size of the "hole" in struct boot_params that a protected-mode loader
+or the BIOS stub has to copy it into. It is currently 119 bytes long, which
+leaves us with 25 very precious bytes. This isn't something that can be fixed
+without revising the boot protocol entirely, breaking backwards compatibility.
+
+boot_params proper is limited to 4096 bytes, but can be arbitrarily extended
+by adding setup_data entries. It cannot be used to communicate properties of
+the kernel image, because it is .bss and has no image-provided content.
+
+kernel_info solves this by providing an extensible place for information about
+the kernel image. It is readonly, because the kernel cannot rely on a
+bootloader copying its contents anywhere, but that is OK; if it becomes
+necessary it can still contain data items that an enabled bootloader would be
+expected to copy into a setup_data chunk.
+
+All kernel_info data should be part of this structure. Fixed size data have to
+be put before kernel_info_var_len_data label. Variable size data have to be put
+after kernel_info_var_len_data label. Each chunk of variable size data has to
+be prefixed with header/magic and its size, e.g.:
+
+  kernel_info:
+          .ascii  "LToP"          /* Header, Linux top (structure). */
+          .long   kernel_info_var_len_data - kernel_info
+          .long   kernel_info_end - kernel_info
+          .long   0x01234567      /* Some fixed size data for the bootloaders. */
+  kernel_info_var_len_data:
+  example_struct:                 /* Some variable size data for the bootloaders. */
+          .ascii  "0123"          /* Header/Magic. */
+          .long   example_struct_end - example_struct
+          .ascii  "Struct"
+          .long   0x89012345
+  example_struct_end:
+  example_strings:                /* Some variable size data for the bootloaders. */
+          .ascii  "ABCD"          /* Header/Magic. */
+          .long   example_strings_end - example_strings
+          .asciz  "String_0"
+          .asciz  "String_1"
+  example_strings_end:
+  kernel_info_end:
+
+This way the kernel_info is self-contained blob.
+
+.. note::
+     Each variable size data header/magic can be any 4-character string,
+     without \0 at the end of the string, which does not collide with
+     existing variable length data headers/magics.
+
+
+Details of the kernel_info Fields
+=================================
+
+============	========
+Field name:	header
+Offset/size:	0x0000/4
+============	========
+
+  Contains the magic number "LToP" (0x506f544c).
+
+============	========
+Field name:	size
+Offset/size:	0x0004/4
+============	========
+
+  This field contains the size of the kernel_info including kernel_info.header.
+  It does not count kernel_info.kernel_info_var_len_data size. This field should be
+  used by the bootloaders to detect supported fixed size fields in the kernel_info
+  and beginning of kernel_info.kernel_info_var_len_data.
+
+============	========
+Field name:	size_total
+Offset/size:	0x0008/4
+============	========
+
+  This field contains the size of the kernel_info including kernel_info.header
+  and kernel_info.kernel_info_var_len_data.
+
+============	==============
+Field name:	setup_type_max
+Offset/size:	0x000c/4
+============	==============
+
+  This field contains maximal allowed type for setup_data and setup_indirect structs.
+
 
 The Image Checksum
 ==================
diff --git a/MAINTAINERS b/MAINTAINERS
index 2c7aa547d8b8..08bbf9649a1b 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -1002,6 +1002,7 @@ F:	drivers/media/i2c/adv7842*
 
 ANALOG DEVICES INC ASOC CODEC DRIVERS
 M:	Lars-Peter Clausen <lars@metafoo.de>
+M:	Nuno Sá <nuno.sa@analog.com>
 L:	alsa-devel@alsa-project.org (moderated for non-subscribers)
 W:	http://wiki.analog.com/
 W:	http://ez.analog.com/community/linux-device-drivers
@@ -3548,7 +3549,7 @@ BUS FREQUENCY DRIVER FOR SAMSUNG EXYNOS
 M:	Chanwoo Choi <cw00.choi@samsung.com>
 L:	linux-pm@vger.kernel.org
 L:	linux-samsung-soc@vger.kernel.org
-T:	git git://git.kernel.org/pub/scm/linux/kernel/git/mzx/devfreq.git
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/chanwoo/linux.git
 S:	Maintained
 F:	drivers/devfreq/exynos-bus.c
 F:	Documentation/devicetree/bindings/devfreq/exynos-bus.txt
@@ -3649,16 +3650,6 @@ L:	cake@lists.bufferbloat.net (moderated for non-subscribers)
 S:	Maintained
 F:	net/sched/sch_cake.c
 
-CALGARY x86-64 IOMMU
-M:	Muli Ben-Yehuda <mulix@mulix.org>
-M:	Jon Mason <jdmason@kudzu.us>
-L:	iommu@lists.linux-foundation.org
-S:	Maintained
-F:	arch/x86/kernel/pci-calgary_64.c
-F:	arch/x86/kernel/tce_64.c
-F:	arch/x86/include/asm/calgary.h
-F:	arch/x86/include/asm/tce.h
-
 CAN NETWORK DRIVERS
 M:	Wolfgang Grandegger <wg@grandegger.com>
 M:	Marc Kleine-Budde <mkl@pengutronix.de>
@@ -4292,14 +4283,13 @@ F:	include/linux/cpufreq.h
 F:	include/linux/sched/cpufreq.h
 F:	tools/testing/selftests/cpufreq/
 
-CPU FREQUENCY DRIVERS - ARM BIG LITTLE
+CPU FREQUENCY DRIVERS - VEXPRESS SPC ARM BIG LITTLE
 M:	Viresh Kumar <viresh.kumar@linaro.org>
 M:	Sudeep Holla <sudeep.holla@arm.com>
 L:	linux-pm@vger.kernel.org
 W:	http://www.arm.com/products/processors/technologies/biglittleprocessing.php
 S:	Maintained
-F:	drivers/cpufreq/arm_big_little.h
-F:	drivers/cpufreq/arm_big_little.c
+F:	drivers/cpufreq/vexpress-spc-cpufreq.c
 
 CPU POWER MONITORING SUBSYSTEM
 M:	Thomas Renninger <trenn@suse.com>
@@ -4660,6 +4650,14 @@ M:	"Maciej W. Rozycki" <macro@linux-mips.org>
 S:	Maintained
 F:	drivers/net/fddi/defxx.*
 
+DEINTERLACE DRIVERS FOR ALLWINNER H3
+M:	Jernej Skrabec <jernej.skrabec@siol.net>
+L:	linux-media@vger.kernel.org
+T:	git git://linuxtv.org/media_tree.git
+S:	Maintained
+F:	drivers/media/platform/sunxi/sun8i-di/
+F:	Documentation/devicetree/bindings/media/allwinner,sun8i-h3-deinterlace.yaml
+
 DELL SMBIOS DRIVER
 M:	Pali Rohár <pali.rohar@gmail.com>
 M:	Mario Limonciello <mario.limonciello@dell.com>
@@ -4784,9 +4782,9 @@ F:	include/linux/devcoredump.h
 DEVICE FREQUENCY (DEVFREQ)
 M:	MyungJoo Ham <myungjoo.ham@samsung.com>
 M:	Kyungmin Park <kyungmin.park@samsung.com>
-R:	Chanwoo Choi <cw00.choi@samsung.com>
+M:	Chanwoo Choi <cw00.choi@samsung.com>
 L:	linux-pm@vger.kernel.org
-T:	git git://git.kernel.org/pub/scm/linux/kernel/git/mzx/devfreq.git
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/chanwoo/linux.git
 S:	Maintained
 F:	drivers/devfreq/
 F:	include/linux/devfreq.h
@@ -4796,10 +4794,11 @@ F:	include/trace/events/devfreq.h
 DEVICE FREQUENCY EVENT (DEVFREQ-EVENT)
 M:	Chanwoo Choi <cw00.choi@samsung.com>
 L:	linux-pm@vger.kernel.org
-T:	git git://git.kernel.org/pub/scm/linux/kernel/git/mzx/devfreq.git
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/chanwoo/linux.git
 S:	Supported
 F:	drivers/devfreq/event/
 F:	drivers/devfreq/devfreq-event.c
+F:	include/dt-bindings/pmu/exynos_ppmu.h
 F:	include/linux/devfreq-event.h
 F:	Documentation/devicetree/bindings/devfreq/event/
 
@@ -6029,14 +6028,14 @@ F:	sound/usb/misc/ua101.c
 EFI TEST DRIVER
 L:	linux-efi@vger.kernel.org
 M:	Ivan Hu <ivan.hu@canonical.com>
-M:	Ard Biesheuvel <ard.biesheuvel@linaro.org>
+M:	Ard Biesheuvel <ardb@kernel.org>
 S:	Maintained
 F:	drivers/firmware/efi/test/
 
 EFI VARIABLE FILESYSTEM
 M:	Matthew Garrett <matthew.garrett@nebula.com>
 M:	Jeremy Kerr <jk@ozlabs.org>
-M:	Ard Biesheuvel <ard.biesheuvel@linaro.org>
+M:	Ard Biesheuvel <ardb@kernel.org>
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/efi/efi.git
 L:	linux-efi@vger.kernel.org
 S:	Maintained
@@ -6217,7 +6216,7 @@ S:	Supported
 F:	security/integrity/evm/
 
 EXTENSIBLE FIRMWARE INTERFACE (EFI)
-M:	Ard Biesheuvel <ard.biesheuvel@linaro.org>
+M:	Ard Biesheuvel <ardb@kernel.org>
 L:	linux-efi@vger.kernel.org
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/efi/efi.git
 S:	Maintained
@@ -7597,6 +7596,13 @@ L:	linux-kernel@vger.kernel.org
 S:	Maintained
 F:	arch/x86/kernel/cpu/hygon.c
 
+HYNIX HI556 SENSOR DRIVER
+M:	Shawn Tu <shawnx.tu@intel.com>
+L:	linux-media@vger.kernel.org
+T:	git git://linuxtv.org/media_tree.git
+S:	Maintained
+F:	drivers/media/i2c/hi556.c
+
 Hyper-V CORE AND DRIVERS
 M:	"K. Y. Srinivasan" <kys@microsoft.com>
 M:	Haiyang Zhang <haiyangz@microsoft.com>
@@ -8387,6 +8393,7 @@ S:	Maintained
 F:	drivers/staging/media/ipu3/
 F:	Documentation/media/uapi/v4l/pixfmt-meta-intel-ipu3.rst
 F:	Documentation/media/v4l-drivers/ipu3.rst
+F:	Documentation/media/v4l-drivers/ipu3_rcb.svg
 
 INTEL IXP4XX QMGR, NPE, ETHERNET and HSS SUPPORT
 M:	Krzysztof Halasa <khalasa@piap.pl>
@@ -9942,7 +9949,7 @@ F:	Documentation/hwmon/max16065.rst
 F:	drivers/hwmon/max16065.c
 
 MAX2175 SDR TUNER DRIVER
-M:	Ramesh Shanmugasundaram <ramesh.shanmugasundaram@bp.renesas.com>
+M:	Ramesh Shanmugasundaram <rashanmu@gmail.com>
 L:	linux-media@vger.kernel.org
 T:	git git://linuxtv.org/media_tree.git
 S:	Maintained
@@ -10204,7 +10211,7 @@ F:	drivers/media/platform/renesas-ceu.c
 F:	include/media/drv-intf/renesas-ceu.h
 
 MEDIA DRIVERS FOR RENESAS - DRIF
-M:	Ramesh Shanmugasundaram <ramesh.shanmugasundaram@bp.renesas.com>
+M:	Ramesh Shanmugasundaram <rashanmu@gmail.com>
 L:	linux-media@vger.kernel.org
 L:	linux-renesas-soc@vger.kernel.org
 T:	git git://linuxtv.org/media_tree.git
@@ -10665,7 +10672,7 @@ W:	http://linux-meson.com/
 S:	Supported
 F:	drivers/media/platform/meson/ao-cec.c
 F:	drivers/media/platform/meson/ao-cec-g12a.c
-F:	Documentation/devicetree/bindings/media/meson-ao-cec.txt
+F:	Documentation/devicetree/bindings/media/amlogic,meson-gx-ao-cec.yaml
 T:	git git://linuxtv.org/media_tree.git
 
 MESON NAND CONTROLLER DRIVER FOR AMLOGIC SOCS
@@ -13086,6 +13093,15 @@ L:	linux-scsi@vger.kernel.org
 S:	Supported
 F:	drivers/scsi/pm8001/
 
+PM-GRAPH UTILITY
+M:	"Todd E Brandt" <todd.e.brandt@linux.intel.com>
+L:	linux-pm@vger.kernel.org
+W:	https://01.org/pm-graph
+B:	https://bugzilla.kernel.org/buglist.cgi?component=pm-graph&product=Tools
+T:	git git://github.com/intel/pm-graph
+S:	Supported
+F:	tools/power/pm-graph
+
 PNP SUPPORT
 M:	"Rafael J. Wysocki" <rafael.j.wysocki@intel.com>
 S:	Maintained
@@ -15100,7 +15116,7 @@ F:	include/media/soc_camera.h
 F:	drivers/staging/media/soc_camera/
 
 SOCIONEXT SYNQUACER I2C DRIVER
-M:	Ard Biesheuvel <ard.biesheuvel@linaro.org>
+M:	Ard Biesheuvel <ardb@kernel.org>
 L:	linux-i2c@vger.kernel.org
 S:	Maintained
 F:	drivers/i2c/busses/i2c-synquacer.c
@@ -15235,6 +15251,14 @@ S:	Maintained
 F:	drivers/media/i2c/imx274.c
 F:	Documentation/devicetree/bindings/media/i2c/imx274.txt
 
+SONY IMX290 SENSOR DRIVER
+M:	Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
+L:	linux-media@vger.kernel.org
+T:	git git://linuxtv.org/media_tree.git
+S:	Maintained
+F:	drivers/media/i2c/imx290.c
+F:	Documentation/devicetree/bindings/media/i2c/imx290.txt
+
 SONY IMX319 SENSOR DRIVER
 M:	Bingbu Cao <bingbu.cao@intel.com>
 L:	linux-media@vger.kernel.org
@@ -16397,6 +16421,7 @@ W:	http://linuxtv.org/
 Q:	http://patchwork.linuxtv.org/project/linux-media/list/
 S:	Maintained
 F:	drivers/media/platform/ti-vpe/
+F:	Documentation/devicetree/bindings/media/ti,vpe.yaml
 
 TI WILINK WIRELESS DRIVERS
 L:	linux-wireless@vger.kernel.org
@@ -17286,6 +17311,7 @@ F:	include/media/videobuf2-*
 
 VIMC VIRTUAL MEDIA CONTROLLER DRIVER
 M:	Helen Koike <helen.koike@collabora.com>
+R:	Shuah Khan <skhan@linuxfoundation.org>
 L:	linux-media@vger.kernel.org
 T:	git git://linuxtv.org/media_tree.git
 W:	https://linuxtv.org
diff --git a/arch/Kconfig b/arch/Kconfig
index 5f8a5d84dbbe..8bcc1c746142 100644
--- a/arch/Kconfig
+++ b/arch/Kconfig
@@ -892,27 +892,6 @@ config STRICT_MODULE_RWX
 config ARCH_HAS_PHYS_TO_DMA
 	bool
 
-config ARCH_HAS_REFCOUNT
-	bool
-	help
-	  An architecture selects this when it has implemented refcount_t
-	  using open coded assembly primitives that provide an optimized
-	  refcount_t implementation, possibly at the expense of some full
-	  refcount state checks of CONFIG_REFCOUNT_FULL=y.
-
-	  The refcount overflow check behavior, however, must be retained.
-	  Catching overflows is the primary security concern for protecting
-	  against bugs in reference counts.
-
-config REFCOUNT_FULL
-	bool "Perform full reference count validation at the expense of speed"
-	help
-	  Enabling this switches the refcounting infrastructure from a fast
-	  unchecked atomic_t implementation to a fully state checked
-	  implementation, which can be (slightly) slower but provides protections
-	  against various use-after-free conditions that can be used in
-	  security flaw exploits.
-
 config HAVE_ARCH_COMPILER_H
 	bool
 	help
diff --git a/arch/alpha/kernel/vmlinux.lds.S b/arch/alpha/kernel/vmlinux.lds.S
index c4b5ceceab52..bc6f727278fd 100644
--- a/arch/alpha/kernel/vmlinux.lds.S
+++ b/arch/alpha/kernel/vmlinux.lds.S
@@ -1,4 +1,8 @@
 /* SPDX-License-Identifier: GPL-2.0 */
+
+#define EMITS_PT_NOTE
+#define RO_EXCEPTION_TABLE_ALIGN	16
+
 #include <asm-generic/vmlinux.lds.h>
 #include <asm/thread_info.h>
 #include <asm/cache.h>
@@ -8,7 +12,7 @@
 OUTPUT_FORMAT("elf64-alpha")
 OUTPUT_ARCH(alpha)
 ENTRY(__start)
-PHDRS { kernel PT_LOAD; note PT_NOTE; }
+PHDRS { text PT_LOAD; note PT_NOTE; }
 jiffies = jiffies_64;
 SECTIONS
 {
@@ -27,17 +31,11 @@ SECTIONS
 		LOCK_TEXT
 		*(.fixup)
 		*(.gnu.warning)
-	} :kernel
+	} :text
 	swapper_pg_dir = SWAPPER_PGD;
 	_etext = .;	/* End of text section */
 
-	NOTES :kernel :note
-	.dummy : {
-		*(.dummy)
-	} :kernel
-
-	RODATA
-	EXCEPTION_TABLE(16)
+	RO_DATA(4096)
 
 	/* Will be freed after init */
 	__init_begin = ALIGN(PAGE_SIZE);
@@ -52,7 +50,7 @@ SECTIONS
 
 	_sdata = .;	/* Start of rw data section */
 	_data = .;
-	RW_DATA_SECTION(L1_CACHE_BYTES, PAGE_SIZE, THREAD_SIZE)
+	RW_DATA(L1_CACHE_BYTES, PAGE_SIZE, THREAD_SIZE)
 
 	.got : {
 		*(.got)
diff --git a/arch/arc/kernel/vmlinux.lds.S b/arch/arc/kernel/vmlinux.lds.S
index 6c693a9d29b6..54139a6f469b 100644
--- a/arch/arc/kernel/vmlinux.lds.S
+++ b/arch/arc/kernel/vmlinux.lds.S
@@ -95,13 +95,13 @@ SECTIONS
 	_etext = .;
 
 	_sdata = .;
-	RO_DATA_SECTION(PAGE_SIZE)
+	RO_DATA(PAGE_SIZE)
 
 	/*
 	 * 1. this is .data essentially
 	 * 2. THREAD_SIZE for init.task, must be kernel-stk sz aligned
 	 */
-	RW_DATA_SECTION(L1_CACHE_BYTES, PAGE_SIZE, THREAD_SIZE)
+	RW_DATA(L1_CACHE_BYTES, PAGE_SIZE, THREAD_SIZE)
 
 	_edata = .;
 
@@ -118,8 +118,6 @@ SECTIONS
 	/DISCARD/ : {	*(.eh_frame) }
 #endif
 
-	NOTES
-
 	. = ALIGN(PAGE_SIZE);
 	_end = . ;
 
diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index 8a50efb559f3..0d3c5d7cceb7 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -117,7 +117,6 @@ config ARM
 	select OLD_SIGSUSPEND3
 	select PCI_SYSCALL if PCI
 	select PERF_USE_VMALLOC
-	select REFCOUNT_FULL
 	select RTC_LIB
 	select SYS_SUPPORTS_APM_EMULATION
 	# Above selects are sorted alphabetically; please add new ones
diff --git a/arch/arm/boot/dts/am3517.dtsi b/arch/arm/boot/dts/am3517.dtsi
index bf3002009b00..76f819f4ba48 100644
--- a/arch/arm/boot/dts/am3517.dtsi
+++ b/arch/arm/boot/dts/am3517.dtsi
@@ -16,6 +16,37 @@
 		can = &hecc;
 	};
 
+	cpus {
+		cpu: cpu@0 {
+			/* Based on OMAP3630 variants OPP50 and OPP100 */
+			operating-points-v2 = <&cpu0_opp_table>;
+
+			clock-latency = <300000>; /* From legacy driver */
+		};
+	};
+
+	cpu0_opp_table: opp-table {
+		compatible = "operating-points-v2-ti-cpu";
+		syscon = <&scm_conf>;
+		/*
+		 * AM3517 TRM only lists 600MHz @ 1.2V, but omap36xx
+		 * appear to operate at 300MHz as well. Since AM3517 only
+		 * lists one operating voltage, it will remain fixed at 1.2V
+		 */
+		opp50-300000000 {
+			opp-hz = /bits/ 64 <300000000>;
+			opp-microvolt = <1200000>;
+			opp-supported-hw = <0xffffffff 0xffffffff>;
+			opp-suspend;
+		};
+
+		opp100-600000000 {
+			opp-hz = /bits/ 64 <600000000>;
+			opp-microvolt = <1200000>;
+			opp-supported-hw = <0xffffffff 0xffffffff>;
+		};
+	};
+
 	ocp@68000000 {
 		am35x_otg_hs: am35x_otg_hs@5c040000 {
 			compatible = "ti,omap3-musb";
diff --git a/arch/arm/boot/dts/am3517_mt_ventoux.dts b/arch/arm/boot/dts/am3517_mt_ventoux.dts
index e507e4ae0d88..e7d7124a34ba 100644
--- a/arch/arm/boot/dts/am3517_mt_ventoux.dts
+++ b/arch/arm/boot/dts/am3517_mt_ventoux.dts
@@ -8,7 +8,7 @@
 
 / {
 	model = "TeeJet Mt.Ventoux";
-	compatible = "teejet,mt_ventoux", "ti,omap3";
+	compatible = "teejet,mt_ventoux", "ti,am3517", "ti,omap3";
 
 	memory@80000000 {
 		device_type = "memory";
diff --git a/arch/arm/boot/dts/logicpd-som-lv-35xx-devkit.dts b/arch/arm/boot/dts/logicpd-som-lv-35xx-devkit.dts
index f7a841a28865..2a0a98fe67f0 100644
--- a/arch/arm/boot/dts/logicpd-som-lv-35xx-devkit.dts
+++ b/arch/arm/boot/dts/logicpd-som-lv-35xx-devkit.dts
@@ -9,5 +9,5 @@
 
 / {
 	model = "LogicPD Zoom OMAP35xx SOM-LV Development Kit";
-	compatible = "logicpd,dm3730-som-lv-devkit", "ti,omap3";
+	compatible = "logicpd,dm3730-som-lv-devkit", "ti,omap3430", "ti,omap3";
 };
diff --git a/arch/arm/boot/dts/logicpd-torpedo-35xx-devkit.dts b/arch/arm/boot/dts/logicpd-torpedo-35xx-devkit.dts
index 7675bc3fa868..57bae2aa910e 100644
--- a/arch/arm/boot/dts/logicpd-torpedo-35xx-devkit.dts
+++ b/arch/arm/boot/dts/logicpd-torpedo-35xx-devkit.dts
@@ -9,5 +9,5 @@
 
 / {
 	model = "LogicPD Zoom OMAP35xx Torpedo Development Kit";
-	compatible = "logicpd,dm3730-torpedo-devkit", "ti,omap3";
+	compatible = "logicpd,dm3730-torpedo-devkit", "ti,omap3430", "ti,omap3";
 };
diff --git a/arch/arm/boot/dts/omap3-beagle-xm.dts b/arch/arm/boot/dts/omap3-beagle-xm.dts
index 1aa99fc1487a..125ed933ca75 100644
--- a/arch/arm/boot/dts/omap3-beagle-xm.dts
+++ b/arch/arm/boot/dts/omap3-beagle-xm.dts
@@ -8,7 +8,7 @@
 
 / {
 	model = "TI OMAP3 BeagleBoard xM";
-	compatible = "ti,omap3-beagle-xm", "ti,omap36xx", "ti,omap3";
+	compatible = "ti,omap3-beagle-xm", "ti,omap3630", "ti,omap36xx", "ti,omap3";
 
 	cpus {
 		cpu@0 {
diff --git a/arch/arm/boot/dts/omap3-beagle.dts b/arch/arm/boot/dts/omap3-beagle.dts
index e3df3c166902..4ed3f93f5841 100644
--- a/arch/arm/boot/dts/omap3-beagle.dts
+++ b/arch/arm/boot/dts/omap3-beagle.dts
@@ -8,7 +8,7 @@
 
 / {
 	model = "TI OMAP3 BeagleBoard";
-	compatible = "ti,omap3-beagle", "ti,omap3";
+	compatible = "ti,omap3-beagle", "ti,omap3430", "ti,omap3";
 
 	cpus {
 		cpu@0 {
diff --git a/arch/arm/boot/dts/omap3-cm-t3530.dts b/arch/arm/boot/dts/omap3-cm-t3530.dts
index 76e52c78cbb4..32dbaeaed147 100644
--- a/arch/arm/boot/dts/omap3-cm-t3530.dts
+++ b/arch/arm/boot/dts/omap3-cm-t3530.dts
@@ -9,7 +9,7 @@
 
 / {
 	model = "CompuLab CM-T3530";
-	compatible = "compulab,omap3-cm-t3530", "ti,omap34xx", "ti,omap3";
+	compatible = "compulab,omap3-cm-t3530", "ti,omap3430", "ti,omap34xx", "ti,omap3";
 
 	/* Regulator to trigger the reset signal of the Wifi module */
 	mmc2_sdio_reset: regulator-mmc2-sdio-reset {
diff --git a/arch/arm/boot/dts/omap3-cm-t3730.dts b/arch/arm/boot/dts/omap3-cm-t3730.dts
index 6e944dfa0f3d..683819bf0915 100644
--- a/arch/arm/boot/dts/omap3-cm-t3730.dts
+++ b/arch/arm/boot/dts/omap3-cm-t3730.dts
@@ -9,7 +9,7 @@
 
 / {
 	model = "CompuLab CM-T3730";
-	compatible = "compulab,omap3-cm-t3730", "ti,omap36xx", "ti,omap3";
+	compatible = "compulab,omap3-cm-t3730", "ti,omap3630", "ti,omap36xx", "ti,omap3";
 
 	wl12xx_vmmc2: wl12xx_vmmc2 {
 		compatible = "regulator-fixed";
diff --git a/arch/arm/boot/dts/omap3-devkit8000-lcd43.dts b/arch/arm/boot/dts/omap3-devkit8000-lcd43.dts
index a80fc60bc773..afed85078ad8 100644
--- a/arch/arm/boot/dts/omap3-devkit8000-lcd43.dts
+++ b/arch/arm/boot/dts/omap3-devkit8000-lcd43.dts
@@ -11,7 +11,7 @@
 #include "omap3-devkit8000-lcd-common.dtsi"
 / {
 	model = "TimLL OMAP3 Devkit8000 with 4.3'' LCD panel";
-	compatible = "timll,omap3-devkit8000", "ti,omap3";
+	compatible = "timll,omap3-devkit8000", "ti,omap3430", "ti,omap3";
 
 	lcd0: display {
 		panel-timing {
diff --git a/arch/arm/boot/dts/omap3-devkit8000-lcd70.dts b/arch/arm/boot/dts/omap3-devkit8000-lcd70.dts
index 0753776071f8..07c51a105c0d 100644
--- a/arch/arm/boot/dts/omap3-devkit8000-lcd70.dts
+++ b/arch/arm/boot/dts/omap3-devkit8000-lcd70.dts
@@ -11,7 +11,7 @@
 #include "omap3-devkit8000-lcd-common.dtsi"
 / {
 	model = "TimLL OMAP3 Devkit8000 with 7.0'' LCD panel";
-	compatible = "timll,omap3-devkit8000", "ti,omap3";
+	compatible = "timll,omap3-devkit8000", "ti,omap3430", "ti,omap3";
 
 	lcd0: display {
 		panel-timing {
diff --git a/arch/arm/boot/dts/omap3-devkit8000.dts b/arch/arm/boot/dts/omap3-devkit8000.dts
index faafc48d8f61..162d0726b008 100644
--- a/arch/arm/boot/dts/omap3-devkit8000.dts
+++ b/arch/arm/boot/dts/omap3-devkit8000.dts
@@ -7,7 +7,7 @@
 #include "omap3-devkit8000-common.dtsi"
 / {
 	model = "TimLL OMAP3 Devkit8000";
-	compatible = "timll,omap3-devkit8000", "ti,omap3";
+	compatible = "timll,omap3-devkit8000", "ti,omap3430", "ti,omap3";
 
 	aliases {
 		display1 = &dvi0;
diff --git a/arch/arm/boot/dts/omap3-gta04.dtsi b/arch/arm/boot/dts/omap3-gta04.dtsi
index b6ef1a7ac8a4..409a758c99f1 100644
--- a/arch/arm/boot/dts/omap3-gta04.dtsi
+++ b/arch/arm/boot/dts/omap3-gta04.dtsi
@@ -11,7 +11,7 @@
 
 / {
 	model = "OMAP3 GTA04";
-	compatible = "ti,omap3-gta04", "ti,omap36xx", "ti,omap3";
+	compatible = "ti,omap3-gta04", "ti,omap3630", "ti,omap36xx", "ti,omap3";
 
 	cpus {
 		cpu@0 {
diff --git a/arch/arm/boot/dts/omap3-ha-lcd.dts b/arch/arm/boot/dts/omap3-ha-lcd.dts
index badb9b3c8897..c9ecbc45c8e2 100644
--- a/arch/arm/boot/dts/omap3-ha-lcd.dts
+++ b/arch/arm/boot/dts/omap3-ha-lcd.dts
@@ -8,7 +8,7 @@
 
 / {
 	model = "TI OMAP3 HEAD acoustics LCD-baseboard with TAO3530 SOM";
-	compatible = "headacoustics,omap3-ha-lcd", "technexion,omap3-tao3530", "ti,omap34xx", "ti,omap3";
+	compatible = "headacoustics,omap3-ha-lcd", "technexion,omap3-tao3530", "ti,omap3430", "ti,omap34xx", "ti,omap3";
 };
 
 &omap3_pmx_core {
diff --git a/arch/arm/boot/dts/omap3-ha.dts b/arch/arm/boot/dts/omap3-ha.dts
index a5365252bfbe..35c4e15abeb7 100644
--- a/arch/arm/boot/dts/omap3-ha.dts
+++ b/arch/arm/boot/dts/omap3-ha.dts
@@ -8,7 +8,7 @@
 
 / {
 	model = "TI OMAP3 HEAD acoustics baseboard with TAO3530 SOM";
-	compatible = "headacoustics,omap3-ha", "technexion,omap3-tao3530", "ti,omap34xx", "ti,omap3";
+	compatible = "headacoustics,omap3-ha", "technexion,omap3-tao3530", "ti,omap3430", "ti,omap34xx", "ti,omap3";
 };
 
 &omap3_pmx_core {
diff --git a/arch/arm/boot/dts/omap3-igep0020-rev-f.dts b/arch/arm/boot/dts/omap3-igep0020-rev-f.dts
index 03dcd05fb8a0..d134ce1cffc0 100644
--- a/arch/arm/boot/dts/omap3-igep0020-rev-f.dts
+++ b/arch/arm/boot/dts/omap3-igep0020-rev-f.dts
@@ -10,7 +10,7 @@
 
 / {
 	model = "IGEPv2 Rev. F (TI OMAP AM/DM37x)";
-	compatible = "isee,omap3-igep0020-rev-f", "ti,omap36xx", "ti,omap3";
+	compatible = "isee,omap3-igep0020-rev-f", "ti,omap3630", "ti,omap36xx", "ti,omap3";
 
 	/* Regulator to trigger the WL_EN signal of the Wifi module */
 	lbep5clwmc_wlen: regulator-lbep5clwmc-wlen {
diff --git a/arch/arm/boot/dts/omap3-igep0020.dts b/arch/arm/boot/dts/omap3-igep0020.dts
index 6d0519e3dfd0..e341535a7162 100644
--- a/arch/arm/boot/dts/omap3-igep0020.dts
+++ b/arch/arm/boot/dts/omap3-igep0020.dts
@@ -10,7 +10,7 @@
 
 / {
 	model = "IGEPv2 Rev. C (TI OMAP AM/DM37x)";
-	compatible = "isee,omap3-igep0020", "ti,omap36xx", "ti,omap3";
+	compatible = "isee,omap3-igep0020", "ti,omap3630", "ti,omap36xx", "ti,omap3";
 
 	vmmcsdio_fixed: fixedregulator-mmcsdio {
 		compatible = "regulator-fixed";
diff --git a/arch/arm/boot/dts/omap3-igep0030-rev-g.dts b/arch/arm/boot/dts/omap3-igep0030-rev-g.dts
index 060acd1e803a..9ca1d0f61964 100644
--- a/arch/arm/boot/dts/omap3-igep0030-rev-g.dts
+++ b/arch/arm/boot/dts/omap3-igep0030-rev-g.dts
@@ -10,7 +10,7 @@
 
 / {
 	model = "IGEP COM MODULE Rev. G (TI OMAP AM/DM37x)";
-	compatible = "isee,omap3-igep0030-rev-g", "ti,omap36xx", "ti,omap3";
+	compatible = "isee,omap3-igep0030-rev-g", "ti,omap3630", "ti,omap36xx", "ti,omap3";
 
 	/* Regulator to trigger the WL_EN signal of the Wifi module */
 	lbep5clwmc_wlen: regulator-lbep5clwmc-wlen {
diff --git a/arch/arm/boot/dts/omap3-igep0030.dts b/arch/arm/boot/dts/omap3-igep0030.dts
index 25170bd3c573..32f31035daa2 100644
--- a/arch/arm/boot/dts/omap3-igep0030.dts
+++ b/arch/arm/boot/dts/omap3-igep0030.dts
@@ -10,7 +10,7 @@
 
 / {
 	model = "IGEP COM MODULE Rev. E (TI OMAP AM/DM37x)";
-	compatible = "isee,omap3-igep0030", "ti,omap36xx", "ti,omap3";
+	compatible = "isee,omap3-igep0030", "ti,omap3630", "ti,omap36xx", "ti,omap3";
 
 	vmmcsdio_fixed: fixedregulator-mmcsdio {
 		compatible = "regulator-fixed";
diff --git a/arch/arm/boot/dts/omap3-ldp.dts b/arch/arm/boot/dts/omap3-ldp.dts
index 9a5fde2d9bce..ec9ba04ef43b 100644
--- a/arch/arm/boot/dts/omap3-ldp.dts
+++ b/arch/arm/boot/dts/omap3-ldp.dts
@@ -10,7 +10,7 @@
 
 / {
 	model = "TI OMAP3430 LDP (Zoom1 Labrador)";
-	compatible = "ti,omap3-ldp", "ti,omap3";
+	compatible = "ti,omap3-ldp", "ti,omap3430", "ti,omap3";
 
 	memory@80000000 {
 		device_type = "memory";
diff --git a/arch/arm/boot/dts/omap3-lilly-a83x.dtsi b/arch/arm/boot/dts/omap3-lilly-a83x.dtsi
index c22833d4e568..73d477898ec2 100644
--- a/arch/arm/boot/dts/omap3-lilly-a83x.dtsi
+++ b/arch/arm/boot/dts/omap3-lilly-a83x.dtsi
@@ -7,7 +7,7 @@
 
 / {
 	model = "INCOstartec LILLY-A83X module (DM3730)";
-	compatible = "incostartec,omap3-lilly-a83x", "ti,omap36xx", "ti,omap3";
+	compatible = "incostartec,omap3-lilly-a83x", "ti,omap3630", "ti,omap36xx", "ti,omap3";
 
 	chosen {
 			bootargs = "console=ttyO0,115200n8 vt.global_cursor_default=0 consoleblank=0";
diff --git a/arch/arm/boot/dts/omap3-lilly-dbb056.dts b/arch/arm/boot/dts/omap3-lilly-dbb056.dts
index fec335400074..ecb4ef738e07 100644
--- a/arch/arm/boot/dts/omap3-lilly-dbb056.dts
+++ b/arch/arm/boot/dts/omap3-lilly-dbb056.dts
@@ -8,7 +8,7 @@
 
 / {
 	model = "INCOstartec LILLY-DBB056 (DM3730)";
-	compatible = "incostartec,omap3-lilly-dbb056", "incostartec,omap3-lilly-a83x", "ti,omap36xx", "ti,omap3";
+	compatible = "incostartec,omap3-lilly-dbb056", "incostartec,omap3-lilly-a83x", "ti,omap3630", "ti,omap36xx", "ti,omap3";
 };
 
 &twl {
diff --git a/arch/arm/boot/dts/omap3-n9.dts b/arch/arm/boot/dts/omap3-n9.dts
index 74c0ff2350d3..2495a696cec6 100644
--- a/arch/arm/boot/dts/omap3-n9.dts
+++ b/arch/arm/boot/dts/omap3-n9.dts
@@ -12,7 +12,7 @@
 
 / {
 	model = "Nokia N9";
-	compatible = "nokia,omap3-n9", "ti,omap36xx", "ti,omap3";
+	compatible = "nokia,omap3-n9", "ti,omap3630", "ti,omap36xx", "ti,omap3";
 };
 
 &i2c2 {
diff --git a/arch/arm/boot/dts/omap3-n950-n9.dtsi b/arch/arm/boot/dts/omap3-n950-n9.dtsi
index 6681d4519e97..a075b63f3087 100644
--- a/arch/arm/boot/dts/omap3-n950-n9.dtsi
+++ b/arch/arm/boot/dts/omap3-n950-n9.dtsi
@@ -11,13 +11,6 @@
 	cpus {
 		cpu@0 {
 			cpu0-supply = <&vcc>;
-			operating-points = <
-				/* kHz    uV */
-				300000  1012500
-				600000  1200000
-				800000  1325000
-				1000000	1375000
-			>;
 		};
 	};
 
diff --git a/arch/arm/boot/dts/omap3-n950.dts b/arch/arm/boot/dts/omap3-n950.dts
index 9886bf8b90ab..31d47a1fad84 100644
--- a/arch/arm/boot/dts/omap3-n950.dts
+++ b/arch/arm/boot/dts/omap3-n950.dts
@@ -12,7 +12,7 @@
 
 / {
 	model = "Nokia N950";
-	compatible = "nokia,omap3-n950", "ti,omap36xx", "ti,omap3";
+	compatible = "nokia,omap3-n950", "ti,omap3630", "ti,omap36xx", "ti,omap3";
 
 	keys {
 		compatible = "gpio-keys";
diff --git a/arch/arm/boot/dts/omap3-overo-storm-alto35.dts b/arch/arm/boot/dts/omap3-overo-storm-alto35.dts
index 18338576c41d..7f04dfad8203 100644
--- a/arch/arm/boot/dts/omap3-overo-storm-alto35.dts
+++ b/arch/arm/boot/dts/omap3-overo-storm-alto35.dts
@@ -14,5 +14,5 @@
 
 / {
 	model = "OMAP36xx/AM37xx/DM37xx Gumstix Overo on Alto35";
-	compatible = "gumstix,omap3-overo-alto35", "gumstix,omap3-overo", "ti,omap36xx", "ti,omap3";
+	compatible = "gumstix,omap3-overo-alto35", "gumstix,omap3-overo", "ti,omap3630", "ti,omap36xx", "ti,omap3";
 };
diff --git a/arch/arm/boot/dts/omap3-overo-storm-chestnut43.dts b/arch/arm/boot/dts/omap3-overo-storm-chestnut43.dts
index f204c8af8281..bc5a04e03336 100644
--- a/arch/arm/boot/dts/omap3-overo-storm-chestnut43.dts
+++ b/arch/arm/boot/dts/omap3-overo-storm-chestnut43.dts
@@ -14,7 +14,7 @@
 
 / {
 	model = "OMAP36xx/AM37xx/DM37xx Gumstix Overo on Chestnut43";
-	compatible = "gumstix,omap3-overo-chestnut43", "gumstix,omap3-overo", "ti,omap36xx", "ti,omap3";
+	compatible = "gumstix,omap3-overo-chestnut43", "gumstix,omap3-overo", "ti,omap3630", "ti,omap36xx", "ti,omap3";
 };
 
 &omap3_pmx_core2 {
diff --git a/arch/arm/boot/dts/omap3-overo-storm-gallop43.dts b/arch/arm/boot/dts/omap3-overo-storm-gallop43.dts
index c633f7cee68e..065c31cbf0e2 100644
--- a/arch/arm/boot/dts/omap3-overo-storm-gallop43.dts
+++ b/arch/arm/boot/dts/omap3-overo-storm-gallop43.dts
@@ -14,7 +14,7 @@
 
 / {
 	model = "OMAP36xx/AM37xx/DM37xx Gumstix Overo on Gallop43";
-	compatible = "gumstix,omap3-overo-gallop43", "gumstix,omap3-overo", "ti,omap36xx", "ti,omap3";
+	compatible = "gumstix,omap3-overo-gallop43", "gumstix,omap3-overo", "ti,omap3630", "ti,omap36xx", "ti,omap3";
 };
 
 &omap3_pmx_core2 {
diff --git a/arch/arm/boot/dts/omap3-overo-storm-palo35.dts b/arch/arm/boot/dts/omap3-overo-storm-palo35.dts
index fb88ebc9858c..e38c1c51392c 100644
--- a/arch/arm/boot/dts/omap3-overo-storm-palo35.dts
+++ b/arch/arm/boot/dts/omap3-overo-storm-palo35.dts
@@ -14,7 +14,7 @@
 
 / {
 	model = "OMAP36xx/AM37xx/DM37xx Gumstix Overo on Palo35";
-	compatible = "gumstix,omap3-overo-palo35", "gumstix,omap3-overo", "ti,omap36xx", "ti,omap3";
+	compatible = "gumstix,omap3-overo-palo35", "gumstix,omap3-overo", "ti,omap3630", "ti,omap36xx", "ti,omap3";
 };
 
 &omap3_pmx_core2 {
diff --git a/arch/arm/boot/dts/omap3-overo-storm-palo43.dts b/arch/arm/boot/dts/omap3-overo-storm-palo43.dts
index 76cca00d97b6..e6dc23159c4d 100644
--- a/arch/arm/boot/dts/omap3-overo-storm-palo43.dts
+++ b/arch/arm/boot/dts/omap3-overo-storm-palo43.dts
@@ -14,7 +14,7 @@
 
 / {
 	model = "OMAP36xx/AM37xx/DM37xx Gumstix Overo on Palo43";
-	compatible = "gumstix,omap3-overo-palo43", "gumstix,omap3-overo", "ti,omap36xx", "ti,omap3";
+	compatible = "gumstix,omap3-overo-palo43", "gumstix,omap3-overo", "ti,omap3630", "ti,omap36xx", "ti,omap3";
 };
 
 &omap3_pmx_core2 {
diff --git a/arch/arm/boot/dts/omap3-overo-storm-summit.dts b/arch/arm/boot/dts/omap3-overo-storm-summit.dts
index cc081a9e4c1e..587c08ce282d 100644
--- a/arch/arm/boot/dts/omap3-overo-storm-summit.dts
+++ b/arch/arm/boot/dts/omap3-overo-storm-summit.dts
@@ -14,7 +14,7 @@
 
 / {
 	model = "OMAP36xx/AM37xx/DM37xx Gumstix Overo on Summit";
-	compatible = "gumstix,omap3-overo-summit", "gumstix,omap3-overo", "ti,omap36xx", "ti,omap3";
+	compatible = "gumstix,omap3-overo-summit", "gumstix,omap3-overo", "ti,omap3630", "ti,omap36xx", "ti,omap3";
 };
 
 &omap3_pmx_core2 {
diff --git a/arch/arm/boot/dts/omap3-overo-storm-tobi.dts b/arch/arm/boot/dts/omap3-overo-storm-tobi.dts
index 1de41c0826e0..f57de6010994 100644
--- a/arch/arm/boot/dts/omap3-overo-storm-tobi.dts
+++ b/arch/arm/boot/dts/omap3-overo-storm-tobi.dts
@@ -14,6 +14,6 @@
 
 / {
 	model = "OMAP36xx/AM37xx/DM37xx Gumstix Overo on Tobi";
-	compatible = "gumstix,omap3-overo-tobi", "gumstix,omap3-overo", "ti,omap36xx", "ti,omap3";
+	compatible = "gumstix,omap3-overo-tobi", "gumstix,omap3-overo", "ti,omap3630", "ti,omap36xx", "ti,omap3";
 };
 
diff --git a/arch/arm/boot/dts/omap3-overo-storm-tobiduo.dts b/arch/arm/boot/dts/omap3-overo-storm-tobiduo.dts
index 9ed13118ed8e..281af6c113be 100644
--- a/arch/arm/boot/dts/omap3-overo-storm-tobiduo.dts
+++ b/arch/arm/boot/dts/omap3-overo-storm-tobiduo.dts
@@ -14,5 +14,5 @@
 
 / {
 	model = "OMAP36xx/AM37xx/DM37xx Gumstix Overo on TobiDuo";
-	compatible = "gumstix,omap3-overo-tobiduo", "gumstix,omap3-overo", "ti,omap36xx", "ti,omap3";
+	compatible = "gumstix,omap3-overo-tobiduo", "gumstix,omap3-overo", "ti,omap3630", "ti,omap36xx", "ti,omap3";
 };
diff --git a/arch/arm/boot/dts/omap3-pandora-1ghz.dts b/arch/arm/boot/dts/omap3-pandora-1ghz.dts
index 81b957f33c9f..ea509956d7ac 100644
--- a/arch/arm/boot/dts/omap3-pandora-1ghz.dts
+++ b/arch/arm/boot/dts/omap3-pandora-1ghz.dts
@@ -16,7 +16,7 @@
 / {
 	model = "Pandora Handheld Console 1GHz";
 
-	compatible = "openpandora,omap3-pandora-1ghz", "ti,omap36xx", "ti,omap3";
+	compatible = "openpandora,omap3-pandora-1ghz", "ti,omap3630", "ti,omap36xx", "ti,omap3";
 };
 
 &omap3_pmx_core2 {
diff --git a/arch/arm/boot/dts/omap3-sbc-t3530.dts b/arch/arm/boot/dts/omap3-sbc-t3530.dts
index ae96002abb3b..24bf3fd86641 100644
--- a/arch/arm/boot/dts/omap3-sbc-t3530.dts
+++ b/arch/arm/boot/dts/omap3-sbc-t3530.dts
@@ -8,7 +8,7 @@
 
 / {
 	model = "CompuLab SBC-T3530 with CM-T3530";
-	compatible = "compulab,omap3-sbc-t3530", "compulab,omap3-cm-t3530", "ti,omap34xx", "ti,omap3";
+	compatible = "compulab,omap3-sbc-t3530", "compulab,omap3-cm-t3530", "ti,omap3430", "ti,omap34xx", "ti,omap3";
 
 	aliases {
 		display0 = &dvi0;
diff --git a/arch/arm/boot/dts/omap3-sbc-t3730.dts b/arch/arm/boot/dts/omap3-sbc-t3730.dts
index 7de6df16fc17..eb3893b9535e 100644
--- a/arch/arm/boot/dts/omap3-sbc-t3730.dts
+++ b/arch/arm/boot/dts/omap3-sbc-t3730.dts
@@ -8,7 +8,7 @@
 
 / {
 	model = "CompuLab SBC-T3730 with CM-T3730";
-	compatible = "compulab,omap3-sbc-t3730", "compulab,omap3-cm-t3730", "ti,omap36xx", "ti,omap3";
+	compatible = "compulab,omap3-sbc-t3730", "compulab,omap3-cm-t3730", "ti,omap3630", "ti,omap36xx", "ti,omap3";
 
 	aliases {
 		display0 = &dvi0;
diff --git a/arch/arm/boot/dts/omap3-sniper.dts b/arch/arm/boot/dts/omap3-sniper.dts
index 40a87330e8c3..b6879cdc5c13 100644
--- a/arch/arm/boot/dts/omap3-sniper.dts
+++ b/arch/arm/boot/dts/omap3-sniper.dts
@@ -9,7 +9,7 @@
 
 / {
 	model = "LG Optimus Black";
-	compatible = "lg,omap3-sniper", "ti,omap36xx", "ti,omap3";
+	compatible = "lg,omap3-sniper", "ti,omap3630", "ti,omap36xx", "ti,omap3";
 
 	cpus {
 		cpu@0 {
diff --git a/arch/arm/boot/dts/omap3-thunder.dts b/arch/arm/boot/dts/omap3-thunder.dts
index 6276e7079b36..64221e3b3477 100644
--- a/arch/arm/boot/dts/omap3-thunder.dts
+++ b/arch/arm/boot/dts/omap3-thunder.dts
@@ -8,7 +8,7 @@
 
 / {
 	model = "TI OMAP3 Thunder baseboard with TAO3530 SOM";
-	compatible = "technexion,omap3-thunder", "technexion,omap3-tao3530", "ti,omap34xx", "ti,omap3";
+	compatible = "technexion,omap3-thunder", "technexion,omap3-tao3530", "ti,omap3430", "ti,omap34xx", "ti,omap3";
 };
 
 &omap3_pmx_core {
diff --git a/arch/arm/boot/dts/omap3-zoom3.dts b/arch/arm/boot/dts/omap3-zoom3.dts
index db3a2fe84e99..d240e39f2151 100644
--- a/arch/arm/boot/dts/omap3-zoom3.dts
+++ b/arch/arm/boot/dts/omap3-zoom3.dts
@@ -9,7 +9,7 @@
 
 / {
 	model = "TI Zoom3";
-	compatible = "ti,omap3-zoom3", "ti,omap36xx", "ti,omap3";
+	compatible = "ti,omap3-zoom3", "ti,omap3630", "ti,omap36xx", "ti,omap3";
 
 	cpus {
 		cpu@0 {
diff --git a/arch/arm/boot/dts/omap3430-sdp.dts b/arch/arm/boot/dts/omap3430-sdp.dts
index 0abd61108a53..7bfde8aac7ae 100644
--- a/arch/arm/boot/dts/omap3430-sdp.dts
+++ b/arch/arm/boot/dts/omap3430-sdp.dts
@@ -8,7 +8,7 @@
 
 / {
 	model = "TI OMAP3430 SDP";
-	compatible = "ti,omap3430-sdp", "ti,omap3";
+	compatible = "ti,omap3430-sdp", "ti,omap3430", "ti,omap3";
 
 	memory@80000000 {
 		device_type = "memory";
diff --git a/arch/arm/boot/dts/omap34xx.dtsi b/arch/arm/boot/dts/omap34xx.dtsi
index 7b09cbee8bb8..c4dd9801840d 100644
--- a/arch/arm/boot/dts/omap34xx.dtsi
+++ b/arch/arm/boot/dts/omap34xx.dtsi
@@ -16,19 +16,67 @@
 / {
 	cpus {
 		cpu: cpu@0 {
-			/* OMAP343x/OMAP35xx variants OPP1-5 */
-			operating-points = <
-				/* kHz    uV */
-				125000   975000
-				250000  1075000
-				500000  1200000
-				550000  1270000
-				600000  1350000
-			>;
+			/* OMAP343x/OMAP35xx variants OPP1-6 */
+			operating-points-v2 = <&cpu0_opp_table>;
+
 			clock-latency = <300000>; /* From legacy driver */
 		};
 	};
 
+	/* see Documentation/devicetree/bindings/opp/opp.txt */
+	cpu0_opp_table: opp-table {
+		compatible = "operating-points-v2-ti-cpu";
+		syscon = <&scm_conf>;
+
+		opp1-125000000 {
+			opp-hz = /bits/ 64 <125000000>;
+			/*
+			 * we currently only select the max voltage from table
+			 * Table 3-3 of the omap3530 Data sheet (SPRS507F).
+			 * Format is: <target min max>
+			 */
+			opp-microvolt = <975000 975000 975000>;
+			/*
+			 * first value is silicon revision bit mask
+			 * second one 720MHz Device Identification bit mask
+			 */
+			opp-supported-hw = <0xffffffff 3>;
+		};
+
+		opp2-250000000 {
+			opp-hz = /bits/ 64 <250000000>;
+			opp-microvolt = <1075000 1075000 1075000>;
+			opp-supported-hw = <0xffffffff 3>;
+			opp-suspend;
+		};
+
+		opp3-500000000 {
+			opp-hz = /bits/ 64 <500000000>;
+			opp-microvolt = <1200000 1200000 1200000>;
+			opp-supported-hw = <0xffffffff 3>;
+		};
+
+		opp4-550000000 {
+			opp-hz = /bits/ 64 <550000000>;
+			opp-microvolt = <1275000 1275000 1275000>;
+			opp-supported-hw = <0xffffffff 3>;
+		};
+
+		opp5-600000000 {
+			opp-hz = /bits/ 64 <600000000>;
+			opp-microvolt = <1350000 1350000 1350000>;
+			opp-supported-hw = <0xffffffff 3>;
+		};
+
+		opp6-720000000 {
+			opp-hz = /bits/ 64 <720000000>;
+			opp-microvolt = <1350000 1350000 1350000>;
+			/* only high-speed grade omap3530 devices */
+			opp-supported-hw = <0xffffffff 2>;
+			turbo-mode;
+		};
+	};
+
 	ocp@68000000 {
 		omap3_pmx_core2: pinmux@480025d8 {
 			compatible = "ti,omap3-padconf", "pinctrl-single";
diff --git a/arch/arm/boot/dts/omap36xx.dtsi b/arch/arm/boot/dts/omap36xx.dtsi
index 1e552f08f120..c618cb257d00 100644
--- a/arch/arm/boot/dts/omap36xx.dtsi
+++ b/arch/arm/boot/dts/omap36xx.dtsi
@@ -19,16 +19,65 @@
 	};
 
 	cpus {
-		/* OMAP3630/OMAP37xx 'standard device' variants OPP50 to OPP130 */
+		/* OMAP3630/OMAP37xx variants OPP50 to OPP130 and OPP1G */
 		cpu: cpu@0 {
-			operating-points = <
-				/* kHz    uV */
-				300000  1012500
-				600000  1200000
-				800000  1325000
-			>;
-			clock-latency = <300000>; /* From legacy driver */
+			operating-points-v2 = <&cpu0_opp_table>;
+
+			vbb-supply = <&abb_mpu_iva>;
+			clock-latency = <300000>; /* From omap-cpufreq driver */
+		};
+	};
+
+	/* see Documentation/devicetree/bindings/opp/opp.txt */
+	cpu0_opp_table: opp-table {
+		compatible = "operating-points-v2-ti-cpu";
+		syscon = <&scm_conf>;
+
+		opp50-300000000 {
+			opp-hz = /bits/ 64 <300000000>;
+			/*
+			 * we currently only select the max voltage from table
+			 * Table 4-19 of the DM3730 Data sheet (SPRS685B)
+			 * Format is:	cpu0-supply:	<target min max>
+			 *		vbb-supply:	<target min max>
+			 */
+			opp-microvolt = <1012500 1012500 1012500>,
+					 <1012500 1012500 1012500>;
+			/*
+			 * first value is silicon revision bit mask
+			 * second one is "speed binned" bit mask
+			 */
+			opp-supported-hw = <0xffffffff 3>;
+			opp-suspend;
+		};
+
+		opp100-600000000 {
+			opp-hz = /bits/ 64 <600000000>;
+			opp-microvolt = <1200000 1200000 1200000>,
+					 <1200000 1200000 1200000>;
+			opp-supported-hw = <0xffffffff 3>;
+		};
+
+		opp130-800000000 {
+			opp-hz = /bits/ 64 <800000000>;
+			opp-microvolt = <1325000 1325000 1325000>,
+					 <1325000 1325000 1325000>;
+			opp-supported-hw = <0xffffffff 3>;
 		};
+
+		opp1g-1000000000 {
+			opp-hz = /bits/ 64 <1000000000>;
+			opp-microvolt = <1375000 1375000 1375000>,
+					 <1375000 1375000 1375000>;
+			/* only on am/dm37x with speed-binned bit set */
+			opp-supported-hw = <0xffffffff 2>;
+			turbo-mode;
+		};
+	};
+
+	opp_supply_mpu_iva: opp_supply {
+		compatible = "ti,omap-opp-supply";
+		ti,absolute-max-voltage-uv = <1375000>;
 	};
 
 	ocp@68000000 {
diff --git a/arch/arm/kernel/vmlinux-xip.lds.S b/arch/arm/kernel/vmlinux-xip.lds.S
index 8c74037ade22..21b8b271c80d 100644
--- a/arch/arm/kernel/vmlinux-xip.lds.S
+++ b/arch/arm/kernel/vmlinux-xip.lds.S
@@ -70,8 +70,6 @@ SECTIONS
 	ARM_UNWIND_SECTIONS
 #endif
 
-	NOTES
-
 	_etext = .;			/* End of text and rodata section */
 
 	ARM_VECTORS
@@ -114,7 +112,7 @@ SECTIONS
 
 	. = ALIGN(THREAD_SIZE);
 	_sdata = .;
-	RW_DATA_SECTION(L1_CACHE_BYTES, PAGE_SIZE, THREAD_SIZE)
+	RW_DATA(L1_CACHE_BYTES, PAGE_SIZE, THREAD_SIZE)
 	.data.ro_after_init : AT(ADDR(.data.ro_after_init) - LOAD_OFFSET) {
 		*(.data..ro_after_init)
 	}
diff --git a/arch/arm/kernel/vmlinux.lds.S b/arch/arm/kernel/vmlinux.lds.S
index 23150c0f0f4d..319ccb10846a 100644
--- a/arch/arm/kernel/vmlinux.lds.S
+++ b/arch/arm/kernel/vmlinux.lds.S
@@ -81,8 +81,6 @@ SECTIONS
 	ARM_UNWIND_SECTIONS
 #endif
 
-	NOTES
-
 #ifdef CONFIG_STRICT_KERNEL_RWX
 	. = ALIGN(1<<SECTION_SHIFT);
 #else
@@ -143,7 +141,7 @@ SECTIONS
 	__init_end = .;
 
 	_sdata = .;
-	RW_DATA_SECTION(L1_CACHE_BYTES, PAGE_SIZE, THREAD_SIZE)
+	RW_DATA(L1_CACHE_BYTES, PAGE_SIZE, THREAD_SIZE)
 	_edata = .;
 
 	BSS_SECTION(0, 0, 0)
diff --git a/arch/arm/mach-imx/cpuidle-imx6q.c b/arch/arm/mach-imx/cpuidle-imx6q.c
index 39a7d9393641..24dd5bbe60e4 100644
--- a/arch/arm/mach-imx/cpuidle-imx6q.c
+++ b/arch/arm/mach-imx/cpuidle-imx6q.c
@@ -62,13 +62,13 @@ static struct cpuidle_driver imx6q_cpuidle_driver = {
  */
 void imx6q_cpuidle_fec_irqs_used(void)
 {
-	imx6q_cpuidle_driver.states[1].disabled = true;
+	cpuidle_driver_state_disabled(&imx6q_cpuidle_driver, 1, true);
 }
 EXPORT_SYMBOL_GPL(imx6q_cpuidle_fec_irqs_used);
 
 void imx6q_cpuidle_fec_irqs_unused(void)
 {
-	imx6q_cpuidle_driver.states[1].disabled = false;
+	cpuidle_driver_state_disabled(&imx6q_cpuidle_driver, 1, false);
 }
 EXPORT_SYMBOL_GPL(imx6q_cpuidle_fec_irqs_unused);
 
diff --git a/arch/arm/mach-tegra/cpuidle-tegra20.c b/arch/arm/mach-tegra/cpuidle-tegra20.c
index 2447427cb4a8..69f3fa270fbe 100644
--- a/arch/arm/mach-tegra/cpuidle-tegra20.c
+++ b/arch/arm/mach-tegra/cpuidle-tegra20.c
@@ -203,7 +203,7 @@ void tegra20_cpuidle_pcie_irqs_in_use(void)
 {
 	pr_info_once(
 		"Disabling cpuidle LP2 state, since PCIe IRQs are in use\n");
-	tegra_idle_driver.states[1].disabled = true;
+	cpuidle_driver_state_disabled(&tegra_idle_driver, 1, true);
 }
 
 int __init tegra20_cpuidle_init(void)
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index fcc6635666b4..afe6412fe769 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -182,7 +182,6 @@ config ARM64
 	select PCI_SYSCALL if PCI
 	select POWER_RESET
 	select POWER_SUPPLY
-	select REFCOUNT_FULL
 	select SPARSE_IRQ
 	select SWIOTLB
 	select SYSCTL_EXCEPTION_TRACE
diff --git a/arch/arm64/boot/dts/allwinner/sun50i-h6-beelink-gs1.dts b/arch/arm64/boot/dts/allwinner/sun50i-h6-beelink-gs1.dts
index 1d05d570142f..ce4b0679839d 100644
--- a/arch/arm64/boot/dts/allwinner/sun50i-h6-beelink-gs1.dts
+++ b/arch/arm64/boot/dts/allwinner/sun50i-h6-beelink-gs1.dts
@@ -252,6 +252,7 @@
 };
 
 &r_ir {
+	linux,rc-map-name = "rc-beelink-gs1";
 	status = "okay";
 };
 
diff --git a/arch/arm64/kernel/vmlinux.lds.S b/arch/arm64/kernel/vmlinux.lds.S
index 009057517bdd..841a8b4ce114 100644
--- a/arch/arm64/kernel/vmlinux.lds.S
+++ b/arch/arm64/kernel/vmlinux.lds.S
@@ -5,6 +5,8 @@
  * Written by Martin Mares <mj@atrey.karlin.mff.cuni.cz>
  */
 
+#define RO_EXCEPTION_TABLE_ALIGN	8
+
 #include <asm-generic/vmlinux.lds.h>
 #include <asm/cache.h>
 #include <asm/kernel-pgtable.h>
@@ -132,11 +134,9 @@ SECTIONS
 	. = ALIGN(SEGMENT_ALIGN);
 	_etext = .;			/* End of text section */
 
-	RO_DATA(PAGE_SIZE)		/* everything from this point to     */
-	EXCEPTION_TABLE(8)		/* __init_begin will be marked RO NX */
-	NOTES
+	/* everything from this point to __init_begin will be marked RO NX */
+	RO_DATA(PAGE_SIZE)
 
-	. = ALIGN(PAGE_SIZE);
 	idmap_pg_dir = .;
 	. += IDMAP_DIR_SIZE;
 
@@ -212,7 +212,7 @@ SECTIONS
 
 	_data = .;
 	_sdata = .;
-	RW_DATA_SECTION(L1_CACHE_BYTES, PAGE_SIZE, THREAD_ALIGN)
+	RW_DATA(L1_CACHE_BYTES, PAGE_SIZE, THREAD_ALIGN)
 
 	/*
 	 * Data written with the MMU off but read with the MMU on requires
diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c
index a9f541912289..5a3b15a14a7f 100644
--- a/arch/arm64/mm/mmu.c
+++ b/arch/arm64/mm/mmu.c
@@ -1060,6 +1060,8 @@ int arch_add_memory(int nid, u64 start, u64 size,
 	__create_pgd_mapping(swapper_pg_dir, start, __phys_to_virt(start),
 			     size, PAGE_KERNEL, __pgd_pgtable_alloc, flags);
 
+	memblock_clear_nomap(start, size);
+
 	return __add_pages(nid, start >> PAGE_SHIFT, size >> PAGE_SHIFT,
 			   restrictions);
 }
diff --git a/arch/c6x/kernel/vmlinux.lds.S b/arch/c6x/kernel/vmlinux.lds.S
index 584bab2bace6..ac99ba0864bf 100644
--- a/arch/c6x/kernel/vmlinux.lds.S
+++ b/arch/c6x/kernel/vmlinux.lds.S
@@ -5,6 +5,9 @@
  *  Copyright (C) 2010, 2011 Texas Instruments Incorporated
  *  Mark Salter <msalter@redhat.com>
  */
+
+#define RO_EXCEPTION_TABLE_ALIGN	16
+
 #include <asm-generic/vmlinux.lds.h>
 #include <asm/thread_info.h>
 #include <asm/page.h>
@@ -80,10 +83,7 @@ SECTIONS
 		*(.gnu.warning)
 	}
 
-	EXCEPTION_TABLE(16)
-	NOTES
-
-	RO_DATA_SECTION(PAGE_SIZE)
+	RO_DATA(PAGE_SIZE)
 	.const :
 	{
 		*(.const .const.* .gnu.linkonce.r.*)
diff --git a/arch/csky/kernel/vmlinux.lds.S b/arch/csky/kernel/vmlinux.lds.S
index ae7961b973f2..2ff37beaf2bf 100644
--- a/arch/csky/kernel/vmlinux.lds.S
+++ b/arch/csky/kernel/vmlinux.lds.S
@@ -49,11 +49,10 @@ SECTIONS
 
 
 	_sdata = .;
-	RO_DATA_SECTION(PAGE_SIZE)
-	RW_DATA_SECTION(L1_CACHE_BYTES, PAGE_SIZE, THREAD_SIZE)
+	RO_DATA(PAGE_SIZE)
+	RW_DATA(L1_CACHE_BYTES, PAGE_SIZE, THREAD_SIZE)
 	_edata = .;
 
-	NOTES
 	EXCEPTION_TABLE(L1_CACHE_BYTES)
 	BSS_SECTION(L1_CACHE_BYTES, PAGE_SIZE, L1_CACHE_BYTES)
 	VBR_BASE
diff --git a/arch/h8300/kernel/vmlinux.lds.S b/arch/h8300/kernel/vmlinux.lds.S
index 49f716c0a1df..6b1afc2f9b68 100644
--- a/arch/h8300/kernel/vmlinux.lds.S
+++ b/arch/h8300/kernel/vmlinux.lds.S
@@ -1,4 +1,7 @@
 /* SPDX-License-Identifier: GPL-2.0 */
+
+#define RO_EXCEPTION_TABLE_ALIGN	16
+
 #include <asm-generic/vmlinux.lds.h>
 #include <asm/page.h>
 #include <asm/thread_info.h>
@@ -37,9 +40,7 @@ SECTIONS
 #endif
 	_etext = . ;
 	}
-	EXCEPTION_TABLE(16)
-	NOTES
-	RO_DATA_SECTION(4)
+	RO_DATA(4)
 	ROMEND = .;
 #if defined(CONFIG_ROMKERNEL)
 	. = RAMTOP;
@@ -48,7 +49,7 @@ SECTIONS
 #endif
 	_sdata = . ;
 	__data_start = . ;
-	RW_DATA_SECTION(0, PAGE_SIZE, THREAD_SIZE)
+	RW_DATA(0, PAGE_SIZE, THREAD_SIZE)
 #if defined(CONFIG_ROMKERNEL)
 #undef ADDR
 #endif
diff --git a/arch/hexagon/kernel/vmlinux.lds.S b/arch/hexagon/kernel/vmlinux.lds.S
index 78f2418e97c8..0ca2471ddb9f 100644
--- a/arch/hexagon/kernel/vmlinux.lds.S
+++ b/arch/hexagon/kernel/vmlinux.lds.S
@@ -49,12 +49,11 @@ SECTIONS
 	INIT_DATA_SECTION(PAGE_SIZE)
 
 	_sdata = .;
-		RW_DATA_SECTION(32,PAGE_SIZE,_THREAD_SIZE)
-		RO_DATA_SECTION(PAGE_SIZE)
+		RW_DATA(32,PAGE_SIZE,_THREAD_SIZE)
+		RO_DATA(PAGE_SIZE)
 	_edata = .;
 
 	EXCEPTION_TABLE(16)
-	NOTES
 
 	BSS_SECTION(_PAGE_SIZE, _PAGE_SIZE, _PAGE_SIZE)
 
diff --git a/arch/ia64/kernel/time.c b/arch/ia64/kernel/time.c
index 1e95d32c8877..91b4024c9351 100644
--- a/arch/ia64/kernel/time.c
+++ b/arch/ia64/kernel/time.c
@@ -132,7 +132,7 @@ static __u64 vtime_delta(struct task_struct *tsk)
 	return delta_stime;
 }
 
-void vtime_account_system(struct task_struct *tsk)
+void vtime_account_kernel(struct task_struct *tsk)
 {
 	struct thread_info *ti = task_thread_info(tsk);
 	__u64 stime = vtime_delta(tsk);
@@ -146,7 +146,7 @@ void vtime_account_system(struct task_struct *tsk)
 	else
 		ti->stime += stime;
 }
-EXPORT_SYMBOL_GPL(vtime_account_system);
+EXPORT_SYMBOL_GPL(vtime_account_kernel);
 
 void vtime_account_idle(struct task_struct *tsk)
 {
diff --git a/arch/ia64/kernel/vmlinux.lds.S b/arch/ia64/kernel/vmlinux.lds.S
index d9d4e21107cd..1ec6b703c5b4 100644
--- a/arch/ia64/kernel/vmlinux.lds.S
+++ b/arch/ia64/kernel/vmlinux.lds.S
@@ -5,6 +5,9 @@
 #include <asm/pgtable.h>
 #include <asm/thread_info.h>
 
+#define EMITS_PT_NOTE
+#define RO_EXCEPTION_TABLE_ALIGN	16
+
 #include <asm-generic/vmlinux.lds.h>
 
 OUTPUT_FORMAT("elf64-ia64-little")
@@ -13,7 +16,7 @@ ENTRY(phys_start)
 jiffies = jiffies_64;
 
 PHDRS {
-	code   PT_LOAD;
+	text   PT_LOAD;
 	percpu PT_LOAD;
 	data   PT_LOAD;
 	note   PT_NOTE;
@@ -36,7 +39,7 @@ SECTIONS {
 	phys_start = _start - LOAD_OFFSET;
 
 	code : {
-	} :code
+	} :text
 	. = KERNEL_START;
 
 	_text = .;
@@ -68,11 +71,6 @@ SECTIONS {
 	/*
 	 * Read-only data
 	 */
-	NOTES :code :note       /* put .notes in text and mark in PT_NOTE  */
-	code_continues : {
-	} : code               /* switch back to regular program...  */
-
-	EXCEPTION_TABLE(16)
 
 	/* MCA table */
 	. = ALIGN(16);
@@ -102,11 +100,11 @@ SECTIONS {
 		__start_unwind = .;
 		*(.IA_64.unwind*)
 		__end_unwind = .;
-	} :code :unwind
+	} :text :unwind
 	code_continues2 : {
-	} : code
+	} :text
 
-	RODATA
+	RO_DATA(4096)
 
 	.opd : AT(ADDR(.opd) - LOAD_OFFSET) {
 		__start_opd = .;
@@ -214,7 +212,7 @@ SECTIONS {
 	_end = .;
 
 	code : {
-	} :code
+	} :text
 
 	STABS_DEBUG
 	DWARF_DEBUG
diff --git a/arch/m68k/kernel/vmlinux-nommu.lds b/arch/m68k/kernel/vmlinux-nommu.lds
index cf6edda38971..7b975420c3d9 100644
--- a/arch/m68k/kernel/vmlinux-nommu.lds
+++ b/arch/m68k/kernel/vmlinux-nommu.lds
@@ -60,8 +60,8 @@ SECTIONS {
 #endif
 
 	_sdata = .;
-	RO_DATA_SECTION(PAGE_SIZE)
-	RW_DATA_SECTION(16, PAGE_SIZE, THREAD_SIZE)
+	RO_DATA(PAGE_SIZE)
+	RW_DATA(16, PAGE_SIZE, THREAD_SIZE)
 	_edata = .;
 
 	EXCEPTION_TABLE(16)
diff --git a/arch/m68k/kernel/vmlinux-std.lds b/arch/m68k/kernel/vmlinux-std.lds
index 625a5785804f..4d33da4e7106 100644
--- a/arch/m68k/kernel/vmlinux-std.lds
+++ b/arch/m68k/kernel/vmlinux-std.lds
@@ -31,9 +31,9 @@ SECTIONS
 
   _sdata = .;			/* Start of data section */
 
-  RODATA
+  RO_DATA(4096)
 
-  RW_DATA_SECTION(16, PAGE_SIZE, THREAD_SIZE)
+  RW_DATA(16, PAGE_SIZE, THREAD_SIZE)
 
   BSS_SECTION(0, 0, 0)
 
diff --git a/arch/m68k/kernel/vmlinux-sun3.lds b/arch/m68k/kernel/vmlinux-sun3.lds
index 9868270b0984..87d9f4d08f65 100644
--- a/arch/m68k/kernel/vmlinux-sun3.lds
+++ b/arch/m68k/kernel/vmlinux-sun3.lds
@@ -24,13 +24,13 @@ SECTIONS
 	*(.fixup)
 	*(.gnu.warning)
 	} :text = 0x4e75
-	RODATA
+	RO_DATA(4096)
 
   _etext = .;			/* End of text section */
 
   EXCEPTION_TABLE(16) :data
   _sdata = .;			/* Start of rw data section */
-  RW_DATA_SECTION(16, PAGE_SIZE, THREAD_SIZE) :data
+  RW_DATA(16, PAGE_SIZE, THREAD_SIZE) :data
   /* End of data goes *here* so that freeing init code works properly. */
   _edata = .;
   NOTES
diff --git a/arch/microblaze/kernel/vmlinux.lds.S b/arch/microblaze/kernel/vmlinux.lds.S
index e1f3e8741292..760cac41cbfe 100644
--- a/arch/microblaze/kernel/vmlinux.lds.S
+++ b/arch/microblaze/kernel/vmlinux.lds.S
@@ -11,6 +11,8 @@
 OUTPUT_ARCH(microblaze)
 ENTRY(microblaze_start)
 
+#define RO_EXCEPTION_TABLE_ALIGN	16
+
 #include <asm/page.h>
 #include <asm-generic/vmlinux.lds.h>
 #include <asm/thread_info.h>
@@ -51,9 +53,7 @@ SECTIONS {
 	}
 
 	. = ALIGN(16);
-	RODATA
-	EXCEPTION_TABLE(16)
-	NOTES
+	RO_DATA(4096)
 
 	/*
 	 * sdata2 section can go anywhere, but must be word aligned
@@ -70,7 +70,7 @@ SECTIONS {
 	}
 
 	_sdata = . ;
-	RW_DATA_SECTION(32, PAGE_SIZE, THREAD_SIZE)
+	RW_DATA(32, PAGE_SIZE, THREAD_SIZE)
 	_edata = . ;
 
 	/* Under the microblaze ABI, .sdata and .sbss must be contiguous */
diff --git a/arch/mips/kernel/vmlinux.lds.S b/arch/mips/kernel/vmlinux.lds.S
index 33ee0d18fb0a..a5f00ec73ea6 100644
--- a/arch/mips/kernel/vmlinux.lds.S
+++ b/arch/mips/kernel/vmlinux.lds.S
@@ -10,6 +10,11 @@
  */
 #define BSS_FIRST_SECTIONS *(.bss..swapper_pg_dir)
 
+/* Cavium Octeon should not have a separate PT_NOTE Program Header. */
+#ifndef CONFIG_CAVIUM_OCTEON_SOC
+#define EMITS_PT_NOTE
+#endif
+
 #include <asm-generic/vmlinux.lds.h>
 
 #undef mips
@@ -76,16 +81,8 @@ SECTIONS
 		__stop___dbe_table = .;
 	}
 
-#ifdef CONFIG_CAVIUM_OCTEON_SOC
-#define NOTES_HEADER
-#else /* CONFIG_CAVIUM_OCTEON_SOC */
-#define NOTES_HEADER :note
-#endif /* CONFIG_CAVIUM_OCTEON_SOC */
-	NOTES :text NOTES_HEADER
-	.dummy : { *(.dummy) } :text
-
 	_sdata = .;			/* Start of data section */
-	RODATA
+	RO_DATA(4096)
 
 	/* writeable */
 	.data : {	/* Data */
diff --git a/arch/nds32/kernel/vmlinux.lds.S b/arch/nds32/kernel/vmlinux.lds.S
index 9e90f30a181d..f679d3397436 100644
--- a/arch/nds32/kernel/vmlinux.lds.S
+++ b/arch/nds32/kernel/vmlinux.lds.S
@@ -53,12 +53,11 @@ SECTIONS
 	_etext = .;			/* End of text and rodata section */
 
 	_sdata = .;
-	RO_DATA_SECTION(PAGE_SIZE)
-	RW_DATA_SECTION(L1_CACHE_BYTES, PAGE_SIZE, THREAD_SIZE)
+	RO_DATA(PAGE_SIZE)
+	RW_DATA(L1_CACHE_BYTES, PAGE_SIZE, THREAD_SIZE)
 	_edata  =  .;
 
 	EXCEPTION_TABLE(16)
-	NOTES
 	BSS_SECTION(4, 4, 4)
 	_end = .;
 
diff --git a/arch/nios2/kernel/vmlinux.lds.S b/arch/nios2/kernel/vmlinux.lds.S
index 6ad64f14617d..c55a7cfa1075 100644
--- a/arch/nios2/kernel/vmlinux.lds.S
+++ b/arch/nios2/kernel/vmlinux.lds.S
@@ -49,8 +49,8 @@ SECTIONS
 	__init_end = .;
 
 	_sdata = .;
-	RO_DATA_SECTION(PAGE_SIZE)
-	RW_DATA_SECTION(L1_CACHE_BYTES, PAGE_SIZE, THREAD_SIZE)
+	RO_DATA(PAGE_SIZE)
+	RW_DATA(L1_CACHE_BYTES, PAGE_SIZE, THREAD_SIZE)
 	_edata = .;
 
 	BSS_SECTION(0, 0, 0)
@@ -58,7 +58,6 @@ SECTIONS
 
 	STABS_DEBUG
 	DWARF_DEBUG
-	NOTES
 
 	DISCARDS
 }
diff --git a/arch/openrisc/kernel/vmlinux.lds.S b/arch/openrisc/kernel/vmlinux.lds.S
index 2e2c72c157f3..60449fd7f16f 100644
--- a/arch/openrisc/kernel/vmlinux.lds.S
+++ b/arch/openrisc/kernel/vmlinux.lds.S
@@ -67,19 +67,18 @@ SECTIONS
 
 	_sdata = .;
 
-	/* Page alignment required for RO_DATA_SECTION */
-	RO_DATA_SECTION(PAGE_SIZE)
+	/* Page alignment required for RO_DATA */
+	RO_DATA(PAGE_SIZE)
 	_e_kernel_ro = .;
 
 	/* Whatever comes after _e_kernel_ro had better be page-aligend, too */
 
 	/* 32 here is cacheline size... recheck this */
-	RW_DATA_SECTION(32, PAGE_SIZE, PAGE_SIZE)
+	RW_DATA(32, PAGE_SIZE, PAGE_SIZE)
 
         _edata  =  .;
 
 	EXCEPTION_TABLE(4)
-	NOTES
 
 	/* Init code and data */
 	. = ALIGN(PAGE_SIZE);
diff --git a/arch/parisc/kernel/vmlinux.lds.S b/arch/parisc/kernel/vmlinux.lds.S
index 99cd24f2ea01..53e29d88f99c 100644
--- a/arch/parisc/kernel/vmlinux.lds.S
+++ b/arch/parisc/kernel/vmlinux.lds.S
@@ -19,6 +19,7 @@
 				*(.data..vm0.pte)
 
 #define CC_USING_PATCHABLE_FUNCTION_ENTRY
+#define RO_EXCEPTION_TABLE_ALIGN	8
 
 #include <asm-generic/vmlinux.lds.h>
 
@@ -109,7 +110,7 @@ SECTIONS
 	_sdata = .;
 
 	/* Architecturally we need to keep __gp below 0x1000000 and thus
-	 * in front of RO_DATA_SECTION() which stores lots of tracepoint
+	 * in front of RO_DATA() which stores lots of tracepoint
 	 * and ftrace symbols. */
 #ifdef CONFIG_64BIT
 	. = ALIGN(16);
@@ -127,11 +128,7 @@ SECTIONS
 	}
 #endif
 
-	RO_DATA_SECTION(8)
-
-	/* RO because of BUILDTIME_EXTABLE_SORT */
-	EXCEPTION_TABLE(8)
-	NOTES
+	RO_DATA(8)
 
 	/* unwind info */
 	.PARISC.unwind : {
@@ -149,7 +146,7 @@ SECTIONS
 	data_start = .;
 
 	/* Data */
-	RW_DATA_SECTION(L1_CACHE_BYTES, PAGE_SIZE, PAGE_SIZE)
+	RW_DATA(L1_CACHE_BYTES, PAGE_SIZE, PAGE_SIZE)
 
 	/* PA-RISC locks requires 16-byte alignment */
 	. = ALIGN(16);
diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c
index 694522308cd5..84827da01d45 100644
--- a/arch/powerpc/kernel/time.c
+++ b/arch/powerpc/kernel/time.c
@@ -338,7 +338,7 @@ static unsigned long vtime_delta(struct task_struct *tsk,
 	return stime;
 }
 
-void vtime_account_system(struct task_struct *tsk)
+void vtime_account_kernel(struct task_struct *tsk)
 {
 	unsigned long stime, stime_scaled, steal_time;
 	struct cpu_accounting_data *acct = get_accounting(tsk);
@@ -366,7 +366,7 @@ void vtime_account_system(struct task_struct *tsk)
 #endif
 	}
 }
-EXPORT_SYMBOL_GPL(vtime_account_system);
+EXPORT_SYMBOL_GPL(vtime_account_kernel);
 
 void vtime_account_idle(struct task_struct *tsk)
 {
@@ -395,7 +395,7 @@ static void vtime_flush_scaled(struct task_struct *tsk,
 /*
  * Account the whole cputime accumulated in the paca
  * Must be called with interrupts disabled.
- * Assumes that vtime_account_system/idle() has been called
+ * Assumes that vtime_account_kernel/idle() has been called
  * recently (i.e. since the last entry from usermode) so that
  * get_paca()->user_time_scaled is up to date.
  */
diff --git a/arch/powerpc/kernel/vmlinux.lds.S b/arch/powerpc/kernel/vmlinux.lds.S
index 060a1acd7c6d..8834220036a5 100644
--- a/arch/powerpc/kernel/vmlinux.lds.S
+++ b/arch/powerpc/kernel/vmlinux.lds.S
@@ -6,6 +6,8 @@
 #endif
 
 #define BSS_FIRST_SECTIONS *(.bss.prominit)
+#define EMITS_PT_NOTE
+#define RO_EXCEPTION_TABLE_ALIGN	0
 
 #include <asm/page.h>
 #include <asm-generic/vmlinux.lds.h>
@@ -18,22 +20,8 @@
 ENTRY(_stext)
 
 PHDRS {
-	kernel PT_LOAD FLAGS(7); /* RWX */
-	notes PT_NOTE FLAGS(0);
-	dummy PT_NOTE FLAGS(0);
-
-	/* binutils < 2.18 has a bug that makes it misbehave when taking an
-	   ELF file with all segments at load address 0 as input.  This
-	   happens when running "strip" on vmlinux, because of the AT() magic
-	   in this linker script.  People using GCC >= 4.2 won't run into
-	   this problem, because the "build-id" support will put some data
-	   into the "notes" segment (at a non-zero load address).
-
-	   To work around this, we force some data into both the "dummy"
-	   segment and the kernel segment, so the dummy segment will get a
-	   non-zero load address.  It's not enough to always create the
-	   "notes" segment, since if nothing gets assigned to it, its load
-	   address will be zero.  */
+	text PT_LOAD FLAGS(7); /* RWX */
+	note PT_NOTE FLAGS(0);
 }
 
 #ifdef CONFIG_PPC64
@@ -77,7 +65,7 @@ SECTIONS
 #else /* !CONFIG_PPC64 */
 		HEAD_TEXT
 #endif
-	} :kernel
+	} :text
 
 	__head_end = .;
 
@@ -126,7 +114,7 @@ SECTIONS
 		__got2_end = .;
 #endif /* CONFIG_PPC32 */
 
-	} :kernel
+	} :text
 
 	. = ALIGN(ETEXT_ALIGN_SIZE);
 	_etext = .;
@@ -175,17 +163,6 @@ SECTIONS
 		__stop__btb_flush_fixup = .;
 	}
 #endif
-	EXCEPTION_TABLE(0)
-
-	NOTES :kernel :notes
-
-	/* The dummy segment contents for the bug workaround mentioned above
-	   near PHDRS.  */
-	.dummy : AT(ADDR(.dummy) - LOAD_OFFSET) {
-		LONG(0)
-		LONG(0)
-		LONG(0)
-	} :kernel :dummy
 
 /*
  * Init sections discarded at runtime
@@ -200,7 +177,7 @@ SECTIONS
 #ifdef CONFIG_PPC64
 		*(.tramp.ftrace.init);
 #endif
-	} :kernel
+	} :text
 
 	/* .exit.text is discarded at runtime, not link time,
 	 * to deal with references from __bug_table
diff --git a/arch/riscv/kernel/vmlinux.lds.S b/arch/riscv/kernel/vmlinux.lds.S
index 23cd1a9e52a1..12f42f96d46e 100644
--- a/arch/riscv/kernel/vmlinux.lds.S
+++ b/arch/riscv/kernel/vmlinux.lds.S
@@ -52,12 +52,12 @@ SECTIONS
 
 	/* Start of data section */
 	_sdata = .;
-	RO_DATA_SECTION(L1_CACHE_BYTES)
+	RO_DATA(L1_CACHE_BYTES)
 	.srodata : {
 		*(.srodata*)
 	}
 
-	RW_DATA_SECTION(L1_CACHE_BYTES, PAGE_SIZE, THREAD_SIZE)
+	RW_DATA(L1_CACHE_BYTES, PAGE_SIZE, THREAD_SIZE)
 	.sdata : {
 		__global_pointer$ = . + 0x800;
 		*(.sdata*)
@@ -69,7 +69,6 @@ SECTIONS
 	BSS_SECTION(PAGE_SIZE, PAGE_SIZE, 0)
 
 	EXCEPTION_TABLE(0x10)
-	NOTES
 
 	.rel.dyn : {
 		*(.rel.dyn*)
diff --git a/arch/s390/configs/debug_defconfig b/arch/s390/configs/debug_defconfig
index 38d64030aacf..2e60c80395ab 100644
--- a/arch/s390/configs/debug_defconfig
+++ b/arch/s390/configs/debug_defconfig
@@ -62,7 +62,6 @@ CONFIG_OPROFILE=m
 CONFIG_KPROBES=y
 CONFIG_JUMP_LABEL=y
 CONFIG_STATIC_KEYS_SELFTEST=y
-CONFIG_REFCOUNT_FULL=y
 CONFIG_LOCK_EVENT_COUNTS=y
 CONFIG_MODULES=y
 CONFIG_MODULE_FORCE_LOAD=y
diff --git a/arch/s390/kernel/vmlinux.lds.S b/arch/s390/kernel/vmlinux.lds.S
index 7e0eb4020917..37695499717d 100644
--- a/arch/s390/kernel/vmlinux.lds.S
+++ b/arch/s390/kernel/vmlinux.lds.S
@@ -15,6 +15,8 @@
 /* Handle ro_after_init data on our own. */
 #define RO_AFTER_INIT_DATA
 
+#define EMITS_PT_NOTE
+
 #include <asm-generic/vmlinux.lds.h>
 #include <asm/vmlinux.lds.h>
 
@@ -50,11 +52,7 @@ SECTIONS
 		_etext = .;		/* End of text section */
 	} :text = 0x0700
 
-	NOTES :text :note
-
-	.dummy : { *(.dummy) } :data
-
-	RO_DATA_SECTION(PAGE_SIZE)
+	RO_DATA(PAGE_SIZE)
 
 	. = ALIGN(PAGE_SIZE);
 	_sdata = .;		/* Start of data section */
@@ -64,12 +62,12 @@ SECTIONS
 	.data..ro_after_init : {
 		 *(.data..ro_after_init)
 		JUMP_TABLE_DATA
-	}
+	} :data
 	EXCEPTION_TABLE(16)
 	. = ALIGN(PAGE_SIZE);
 	__end_ro_after_init = .;
 
-	RW_DATA_SECTION(0x100, PAGE_SIZE, THREAD_SIZE)
+	RW_DATA(0x100, PAGE_SIZE, THREAD_SIZE)
 	BOOT_DATA_PRESERVED
 
 	_edata = .;		/* End of data section */
diff --git a/arch/s390/kernel/vtime.c b/arch/s390/kernel/vtime.c
index c475ca49cfc6..8df10d3c8f6c 100644
--- a/arch/s390/kernel/vtime.c
+++ b/arch/s390/kernel/vtime.c
@@ -247,9 +247,9 @@ void vtime_account_irq_enter(struct task_struct *tsk)
 }
 EXPORT_SYMBOL_GPL(vtime_account_irq_enter);
 
-void vtime_account_system(struct task_struct *tsk)
+void vtime_account_kernel(struct task_struct *tsk)
 __attribute__((alias("vtime_account_irq_enter")));
-EXPORT_SYMBOL_GPL(vtime_account_system);
+EXPORT_SYMBOL_GPL(vtime_account_kernel);
 
 /*
  * Sorted add to a list. List is linear searched until first bigger
diff --git a/arch/sh/kernel/vmlinux.lds.S b/arch/sh/kernel/vmlinux.lds.S
index 77a59d8c6b4d..c60b19958c35 100644
--- a/arch/sh/kernel/vmlinux.lds.S
+++ b/arch/sh/kernel/vmlinux.lds.S
@@ -48,11 +48,10 @@ SECTIONS
 	} = 0x0009
 
 	EXCEPTION_TABLE(16)
-	NOTES
 
 	_sdata = .;
 	RO_DATA(PAGE_SIZE)
-	RW_DATA_SECTION(L1_CACHE_BYTES, PAGE_SIZE, THREAD_SIZE)
+	RW_DATA(L1_CACHE_BYTES, PAGE_SIZE, THREAD_SIZE)
 	_edata = .;
 
 	DWARF_EH_FRAME
diff --git a/arch/sparc/kernel/vmlinux.lds.S b/arch/sparc/kernel/vmlinux.lds.S
index 61afd787bd0c..7ec79918b566 100644
--- a/arch/sparc/kernel/vmlinux.lds.S
+++ b/arch/sparc/kernel/vmlinux.lds.S
@@ -67,7 +67,7 @@ SECTIONS
 	.data1 : {
 		*(.data1)
 	}
-	RW_DATA_SECTION(SMP_CACHE_BYTES, 0, THREAD_SIZE)
+	RW_DATA(SMP_CACHE_BYTES, 0, THREAD_SIZE)
 
 	/* End of data section */
 	_edata = .;
@@ -78,7 +78,6 @@ SECTIONS
 		__stop___fixup = .;
 	}
 	EXCEPTION_TABLE(16)
-	NOTES
 
 	. = ALIGN(PAGE_SIZE);
 	__init_begin = ALIGN(PAGE_SIZE);
diff --git a/arch/um/include/asm/common.lds.S b/arch/um/include/asm/common.lds.S
index d7086b985f27..7145ce699982 100644
--- a/arch/um/include/asm/common.lds.S
+++ b/arch/um/include/asm/common.lds.S
@@ -9,14 +9,13 @@
   _sdata = .;
   PROVIDE (sdata = .);
 
-  RODATA
+  RO_DATA(4096)
 
   .unprotected : { *(.unprotected) }
   . = ALIGN(4096);
   PROVIDE (_unprotected_end = .);
 
   . = ALIGN(4096);
-  NOTES
   EXCEPTION_TABLE(0)
 
   BUG_TABLE
diff --git a/arch/unicore32/kernel/vmlinux.lds.S b/arch/unicore32/kernel/vmlinux.lds.S
index 7abf90537cd5..6fb320b337ef 100644
--- a/arch/unicore32/kernel/vmlinux.lds.S
+++ b/arch/unicore32/kernel/vmlinux.lds.S
@@ -43,12 +43,11 @@ SECTIONS
 	_etext = .;
 
 	_sdata = .;
-	RO_DATA_SECTION(PAGE_SIZE)
-	RW_DATA_SECTION(L1_CACHE_BYTES, PAGE_SIZE, THREAD_SIZE)
+	RO_DATA(PAGE_SIZE)
+	RW_DATA(L1_CACHE_BYTES, PAGE_SIZE, THREAD_SIZE)
 	_edata = .;
 
 	EXCEPTION_TABLE(L1_CACHE_BYTES)
-	NOTES
 
 	BSS_SECTION(0, 0, 0)
 	_end = .;
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index f2aed8012e9c..9c9bc348c412 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -73,7 +73,6 @@ config X86
 	select ARCH_HAS_PMEM_API		if X86_64
 	select ARCH_HAS_PTE_DEVMAP		if X86_64
 	select ARCH_HAS_PTE_SPECIAL
-	select ARCH_HAS_REFCOUNT
 	select ARCH_HAS_UACCESS_FLUSHCACHE	if X86_64
 	select ARCH_HAS_UACCESS_MCSAFE		if X86_64 && X86_MCE
 	select ARCH_HAS_SET_MEMORY
@@ -932,36 +931,6 @@ config GART_IOMMU
 
 	  If unsure, say Y.
 
-config CALGARY_IOMMU
-	bool "IBM Calgary IOMMU support"
-	select IOMMU_HELPER
-	select SWIOTLB
-	depends on X86_64 && PCI
-	---help---
-	  Support for hardware IOMMUs in IBM's xSeries x366 and x460
-	  systems. Needed to run systems with more than 3GB of memory
-	  properly with 32-bit PCI devices that do not support DAC
-	  (Double Address Cycle). Calgary also supports bus level
-	  isolation, where all DMAs pass through the IOMMU.  This
-	  prevents them from going anywhere except their intended
-	  destination. This catches hard-to-find kernel bugs and
-	  mis-behaving drivers and devices that do not use the DMA-API
-	  properly to set up their DMA buffers.  The IOMMU can be
-	  turned off at boot time with the iommu=off parameter.
-	  Normally the kernel will make the right choice by itself.
-	  If unsure, say Y.
-
-config CALGARY_IOMMU_ENABLED_BY_DEFAULT
-	def_bool y
-	prompt "Should Calgary be enabled by default?"
-	depends on CALGARY_IOMMU
-	---help---
-	  Should Calgary be enabled by default? if you choose 'y', Calgary
-	  will be used (if it exists). If you choose 'n', Calgary will not be
-	  used even if it exists. If you choose 'n' and would like to use
-	  Calgary anyway, pass 'iommu=calgary' on the kernel command line.
-	  If unsure, say Y.
-
 config MAXSMP
 	bool "Enable Maximum number of SMP Processors and NUMA Nodes"
 	depends on X86_64 && SMP && DEBUG_KERNEL
@@ -1000,8 +969,8 @@ config NR_CPUS_RANGE_END
 config NR_CPUS_RANGE_END
 	int
 	depends on X86_64
-	default 8192 if  SMP && ( MAXSMP ||  CPUMASK_OFFSTACK)
-	default  512 if  SMP && (!MAXSMP && !CPUMASK_OFFSTACK)
+	default 8192 if  SMP && CPUMASK_OFFSTACK
+	default  512 if  SMP && !CPUMASK_OFFSTACK
 	default    1 if !SMP
 
 config NR_CPUS_DEFAULT
@@ -1254,6 +1223,24 @@ config X86_VSYSCALL_EMULATION
 	 Disabling this option saves about 7K of kernel size and
 	 possibly 4K of additional runtime pagetable memory.
 
+config X86_IOPL_IOPERM
+	bool "IOPERM and IOPL Emulation"
+	default y
+	---help---
+	  This enables the ioperm() and iopl() syscalls which are necessary
+	  for legacy applications.
+
+	  Legacy IOPL support is an overbroad mechanism which allows user
+	  space aside of accessing all 65536 I/O ports also to disable
+	  interrupts. To gain this access the caller needs CAP_SYS_RAWIO
+	  capabilities and permission from potentially active security
+	  modules.
+
+	  The emulation restricts the functionality of the syscall to
+	  only allowing the full range I/O port access, but prevents the
+	  ability to disable interrupts from user space which would be
+	  granted if the hardware IOPL mechanism would be used.
+
 config TOSHIBA
 	tristate "Toshiba Laptop support"
 	depends on X86_32
@@ -1492,6 +1479,7 @@ config X86_PAE
 
 config X86_5LEVEL
 	bool "Enable 5-level page tables support"
+	default y
 	select DYNAMIC_MEMORY_LAYOUT
 	select SPARSEMEM_VMEMMAP
 	depends on X86_64
@@ -1751,7 +1739,7 @@ config X86_RESERVE_LOW
 config MATH_EMULATION
 	bool
 	depends on MODIFY_LDT_SYSCALL
-	prompt "Math emulation" if X86_32
+	prompt "Math emulation" if X86_32 && (M486SX || MELAN)
 	---help---
 	  Linux can emulate a math coprocessor (used for floating point
 	  operations) if you don't have one. 486DX and Pentium processors have
@@ -1880,16 +1868,16 @@ config X86_SMAP
 
 	  If unsure, say Y.
 
-config X86_INTEL_UMIP
+config X86_UMIP
 	def_bool y
-	depends on CPU_SUP_INTEL
-	prompt "Intel User Mode Instruction Prevention" if EXPERT
+	depends on CPU_SUP_INTEL || CPU_SUP_AMD
+	prompt "User Mode Instruction Prevention" if EXPERT
 	---help---
-	  The User Mode Instruction Prevention (UMIP) is a security
-	  feature in newer Intel processors. If enabled, a general
-	  protection fault is issued if the SGDT, SLDT, SIDT, SMSW
-	  or STR instructions are executed in user mode. These instructions
-	  unnecessarily expose information about the hardware state.
+	  User Mode Instruction Prevention (UMIP) is a security feature in
+	  some x86 processors. If enabled, a general protection fault is
+	  issued if the SGDT, SLDT, SIDT, SMSW or STR instructions are
+	  executed in user mode. These instructions unnecessarily expose
+	  information about the hardware state.
 
 	  The vast majority of applications do not use these instructions.
 	  For the very few that do, software emulation is provided in
diff --git a/arch/x86/Kconfig.cpu b/arch/x86/Kconfig.cpu
index 8e29c991ba3e..af9c967782f6 100644
--- a/arch/x86/Kconfig.cpu
+++ b/arch/x86/Kconfig.cpu
@@ -50,12 +50,19 @@ choice
 	  See each option's help text for additional details. If you don't know
 	  what to do, choose "486".
 
+config M486SX
+	bool "486SX"
+	depends on X86_32
+	---help---
+	  Select this for an 486-class CPU without an FPU such as
+	  AMD/Cyrix/IBM/Intel SL/SLC/SLC2/SLC3/SX/SX2 and UMC U5S.
+
 config M486
-	bool "486"
+	bool "486DX"
 	depends on X86_32
 	---help---
 	  Select this for an 486-class CPU such as AMD/Cyrix/IBM/Intel
-	  486DX/DX2/DX4 or SL/SLC/SLC2/SLC3/SX/SX2 and UMC U5D or U5S.
+	  486DX/DX2/DX4 and UMC U5D.
 
 config M586
 	bool "586/K5/5x86/6x86/6x86MX"
@@ -312,20 +319,20 @@ config X86_L1_CACHE_SHIFT
 	int
 	default "7" if MPENTIUM4 || MPSC
 	default "6" if MK7 || MK8 || MPENTIUMM || MCORE2 || MATOM || MVIAC7 || X86_GENERIC || GENERIC_CPU
-	default "4" if MELAN || M486 || MGEODEGX1
+	default "4" if MELAN || M486SX || M486 || MGEODEGX1
 	default "5" if MWINCHIP3D || MWINCHIPC6 || MCRUSOE || MEFFICEON || MCYRIXIII || MK6 || MPENTIUMIII || MPENTIUMII || M686 || M586MMX || M586TSC || M586 || MVIAC3_2 || MGEODE_LX
 
 config X86_F00F_BUG
 	def_bool y
-	depends on M586MMX || M586TSC || M586 || M486
+	depends on M586MMX || M586TSC || M586 || M486SX || M486
 
 config X86_INVD_BUG
 	def_bool y
-	depends on M486
+	depends on M486SX || M486
 
 config X86_ALIGNMENT_16
 	def_bool y
-	depends on MWINCHIP3D || MWINCHIPC6 || MCYRIXIII || MELAN || MK6 || M586MMX || M586TSC || M586 || M486 || MVIAC3_2 || MGEODEGX1
+	depends on MWINCHIP3D || MWINCHIPC6 || MCYRIXIII || MELAN || MK6 || M586MMX || M586TSC || M586 || M486SX || M486 || MVIAC3_2 || MGEODEGX1
 
 config X86_INTEL_USERCOPY
 	def_bool y
@@ -378,7 +385,7 @@ config X86_MINIMUM_CPU_FAMILY
 
 config X86_DEBUGCTLMSR
 	def_bool y
-	depends on !(MK6 || MWINCHIPC6 || MWINCHIP3D || MCYRIXIII || M586MMX || M586TSC || M586 || M486) && !UML
+	depends on !(MK6 || MWINCHIPC6 || MWINCHIP3D || MCYRIXIII || M586MMX || M586TSC || M586 || M486SX || M486) && !UML
 
 menuconfig PROCESSOR_SELECT
 	bool "Supported processor vendors" if EXPERT
@@ -402,7 +409,7 @@ config CPU_SUP_INTEL
 config CPU_SUP_CYRIX_32
 	default y
 	bool "Support Cyrix processors" if PROCESSOR_SELECT
-	depends on M486 || M586 || M586TSC || M586MMX || (EXPERT && !64BIT)
+	depends on M486SX || M486 || M586 || M586TSC || M586MMX || (EXPERT && !64BIT)
 	---help---
 	  This enables detection, tunings and quirks for Cyrix processors
 
@@ -470,7 +477,7 @@ config CPU_SUP_TRANSMETA_32
 config CPU_SUP_UMC_32
 	default y
 	bool "Support UMC processors" if PROCESSOR_SELECT
-	depends on M486 || (EXPERT && !64BIT)
+	depends on M486SX || M486 || (EXPERT && !64BIT)
 	---help---
 	  This enables detection, tunings and quirks for UMC processors
 
diff --git a/arch/x86/Makefile_32.cpu b/arch/x86/Makefile_32.cpu
index 1f5faf8606b4..cd3056759880 100644
--- a/arch/x86/Makefile_32.cpu
+++ b/arch/x86/Makefile_32.cpu
@@ -10,6 +10,7 @@ else
 tune		= $(call cc-option,-mcpu=$(1),$(2))
 endif
 
+cflags-$(CONFIG_M486SX)		+= -march=i486
 cflags-$(CONFIG_M486)		+= -march=i486
 cflags-$(CONFIG_M586)		+= -march=i586
 cflags-$(CONFIG_M586TSC)	+= -march=i586
diff --git a/arch/x86/boot/Makefile b/arch/x86/boot/Makefile
index e2839b5c246c..95410d6ee2ff 100644
--- a/arch/x86/boot/Makefile
+++ b/arch/x86/boot/Makefile
@@ -67,6 +67,7 @@ clean-files += cpustr.h
 
 KBUILD_CFLAGS	:= $(REALMODE_CFLAGS) -D_SETUP
 KBUILD_AFLAGS	:= $(KBUILD_CFLAGS) -D__ASSEMBLY__
+KBUILD_CFLAGS	+= $(call cc-option,-fmacro-prefix-map=$(srctree)/=)
 GCOV_PROFILE := n
 UBSAN_SANITIZE := n
 
@@ -87,7 +88,7 @@ $(obj)/vmlinux.bin: $(obj)/compressed/vmlinux FORCE
 
 SETUP_OBJS = $(addprefix $(obj)/,$(setup-y))
 
-sed-zoffset := -e 's/^\([0-9a-fA-F]*\) [ABCDGRSTVW] \(startup_32\|startup_64\|efi32_stub_entry\|efi64_stub_entry\|efi_pe_entry\|input_data\|_end\|_ehead\|_text\|z_.*\)$$/\#define ZO_\2 0x\1/p'
+sed-zoffset := -e 's/^\([0-9a-fA-F]*\) [ABCDGRSTVW] \(startup_32\|startup_64\|efi32_stub_entry\|efi64_stub_entry\|efi_pe_entry\|input_data\|kernel_info\|_end\|_ehead\|_text\|z_.*\)$$/\#define ZO_\2 0x\1/p'
 
 quiet_cmd_zoffset = ZOFFSET $@
       cmd_zoffset = $(NM) $< | sed -n $(sed-zoffset) > $@
diff --git a/arch/x86/boot/compressed/Makefile b/arch/x86/boot/compressed/Makefile
index 6b84afdd7538..aa976adb7094 100644
--- a/arch/x86/boot/compressed/Makefile
+++ b/arch/x86/boot/compressed/Makefile
@@ -38,6 +38,7 @@ KBUILD_CFLAGS += $(call cc-option,-fno-stack-protector)
 KBUILD_CFLAGS += $(call cc-disable-warning, address-of-packed-member)
 KBUILD_CFLAGS += $(call cc-disable-warning, gnu)
 KBUILD_CFLAGS += -Wno-pointer-sign
+KBUILD_CFLAGS += $(call cc-option,-fmacro-prefix-map=$(srctree)/=)
 
 KBUILD_AFLAGS  := $(KBUILD_CFLAGS) -D__ASSEMBLY__
 GCOV_PROFILE := n
@@ -72,8 +73,8 @@ $(obj)/../voffset.h: vmlinux FORCE
 
 $(obj)/misc.o: $(obj)/../voffset.h
 
-vmlinux-objs-y := $(obj)/vmlinux.lds $(obj)/head_$(BITS).o $(obj)/misc.o \
-	$(obj)/string.o $(obj)/cmdline.o $(obj)/error.o \
+vmlinux-objs-y := $(obj)/vmlinux.lds $(obj)/kernel_info.o $(obj)/head_$(BITS).o \
+	$(obj)/misc.o $(obj)/string.o $(obj)/cmdline.o $(obj)/error.o \
 	$(obj)/piggy.o $(obj)/cpuflags.o
 
 vmlinux-objs-$(CONFIG_EARLY_PRINTK) += $(obj)/early_serial_console.o
diff --git a/arch/x86/boot/compressed/eboot.c b/arch/x86/boot/compressed/eboot.c
index 82bc60c8acb2..72b08fde6de6 100644
--- a/arch/x86/boot/compressed/eboot.c
+++ b/arch/x86/boot/compressed/eboot.c
@@ -554,7 +554,11 @@ setup_e820(struct boot_params *params, struct setup_data *e820ext, u32 e820ext_s
 		case EFI_BOOT_SERVICES_CODE:
 		case EFI_BOOT_SERVICES_DATA:
 		case EFI_CONVENTIONAL_MEMORY:
-			e820_type = E820_TYPE_RAM;
+			if (efi_soft_reserve_enabled() &&
+			    (d->attribute & EFI_MEMORY_SP))
+				e820_type = E820_TYPE_SOFT_RESERVED;
+			else
+				e820_type = E820_TYPE_RAM;
 			break;
 
 		case EFI_ACPI_MEMORY_NVS:
@@ -782,6 +786,9 @@ efi_main(struct efi_config *c, struct boot_params *boot_params)
 
 	/* Ask the firmware to clear memory on unclean shutdown */
 	efi_enable_reset_attack_mitigation(sys_table);
+
+	efi_random_get_seed(sys_table);
+
 	efi_retrieve_tpm2_eventlog(sys_table);
 
 	setup_graphics(boot_params);
diff --git a/arch/x86/boot/compressed/efi_stub_32.S b/arch/x86/boot/compressed/efi_stub_32.S
index 257e341fd2c8..ed6c351d34ed 100644
--- a/arch/x86/boot/compressed/efi_stub_32.S
+++ b/arch/x86/boot/compressed/efi_stub_32.S
@@ -24,7 +24,7 @@
  */
 
 .text
-ENTRY(efi_call_phys)
+SYM_FUNC_START(efi_call_phys)
 	/*
 	 * 0. The function can only be called in Linux kernel. So CS has been
 	 * set to 0x0010, DS and SS have been set to 0x0018. In EFI, I found
@@ -77,7 +77,7 @@ ENTRY(efi_call_phys)
 	movl	saved_return_addr(%edx), %ecx
 	pushl	%ecx
 	ret
-ENDPROC(efi_call_phys)
+SYM_FUNC_END(efi_call_phys)
 .previous
 
 .data
diff --git a/arch/x86/boot/compressed/efi_thunk_64.S b/arch/x86/boot/compressed/efi_thunk_64.S
index bff9ab7c6317..593913692d16 100644
--- a/arch/x86/boot/compressed/efi_thunk_64.S
+++ b/arch/x86/boot/compressed/efi_thunk_64.S
@@ -23,7 +23,7 @@
 
 	.code64
 	.text
-ENTRY(efi64_thunk)
+SYM_FUNC_START(efi64_thunk)
 	push	%rbp
 	push	%rbx
 
@@ -97,14 +97,14 @@ ENTRY(efi64_thunk)
 	pop	%rbx
 	pop	%rbp
 	ret
-ENDPROC(efi64_thunk)
+SYM_FUNC_END(efi64_thunk)
 
-ENTRY(efi_exit32)
+SYM_FUNC_START_LOCAL(efi_exit32)
 	movq	func_rt_ptr(%rip), %rax
 	push	%rax
 	mov	%rdi, %rax
 	ret
-ENDPROC(efi_exit32)
+SYM_FUNC_END(efi_exit32)
 
 	.code32
 /*
@@ -112,7 +112,7 @@ ENDPROC(efi_exit32)
  *
  * The stack should represent the 32-bit calling convention.
  */
-ENTRY(efi_enter32)
+SYM_FUNC_START_LOCAL(efi_enter32)
 	movl	$__KERNEL_DS, %eax
 	movl	%eax, %ds
 	movl	%eax, %es
@@ -172,20 +172,23 @@ ENTRY(efi_enter32)
 	btsl	$X86_CR0_PG_BIT, %eax
 	movl	%eax, %cr0
 	lret
-ENDPROC(efi_enter32)
+SYM_FUNC_END(efi_enter32)
 
 	.data
 	.balign	8
-	.global	efi32_boot_gdt
-efi32_boot_gdt:	.word	0
-		.quad	0
+SYM_DATA_START(efi32_boot_gdt)
+	.word	0
+	.quad	0
+SYM_DATA_END(efi32_boot_gdt)
+
+SYM_DATA_START_LOCAL(save_gdt)
+	.word	0
+	.quad	0
+SYM_DATA_END(save_gdt)
 
-save_gdt:	.word	0
-		.quad	0
-func_rt_ptr:	.quad	0
+SYM_DATA_LOCAL(func_rt_ptr, .quad 0)
 
-	.global efi_gdt64
-efi_gdt64:
+SYM_DATA_START(efi_gdt64)
 	.word	efi_gdt64_end - efi_gdt64
 	.long	0			/* Filled out by user */
 	.word	0
@@ -194,4 +197,4 @@ efi_gdt64:
 	.quad	0x00cf92000000ffff	/* __KERNEL_DS */
 	.quad	0x0080890000000000	/* TS descriptor */
 	.quad   0x0000000000000000	/* TS continued */
-efi_gdt64_end:
+SYM_DATA_END_LABEL(efi_gdt64, SYM_L_LOCAL, efi_gdt64_end)
diff --git a/arch/x86/boot/compressed/head_32.S b/arch/x86/boot/compressed/head_32.S
index 5e30eaaf8576..f2dfd6d083ef 100644
--- a/arch/x86/boot/compressed/head_32.S
+++ b/arch/x86/boot/compressed/head_32.S
@@ -61,7 +61,7 @@
 	.hidden _egot
 
 	__HEAD
-ENTRY(startup_32)
+SYM_FUNC_START(startup_32)
 	cld
 	/*
 	 * Test KEEP_SEGMENTS flag to see if the bootloader is asking
@@ -142,14 +142,14 @@ ENTRY(startup_32)
  */
 	leal	.Lrelocated(%ebx), %eax
 	jmp	*%eax
-ENDPROC(startup_32)
+SYM_FUNC_END(startup_32)
 
 #ifdef CONFIG_EFI_STUB
 /*
  * We don't need the return address, so set up the stack so efi_main() can find
  * its arguments.
  */
-ENTRY(efi_pe_entry)
+SYM_FUNC_START(efi_pe_entry)
 	add	$0x4, %esp
 
 	call	1f
@@ -174,9 +174,9 @@ ENTRY(efi_pe_entry)
 	pushl	%eax
 	pushl	%ecx
 	jmp	2f		/* Skip efi_config initialization */
-ENDPROC(efi_pe_entry)
+SYM_FUNC_END(efi_pe_entry)
 
-ENTRY(efi32_stub_entry)
+SYM_FUNC_START(efi32_stub_entry)
 	add	$0x4, %esp
 	popl	%ecx
 	popl	%edx
@@ -205,11 +205,11 @@ fail:
 	movl	BP_code32_start(%esi), %eax
 	leal	startup_32(%eax), %eax
 	jmp	*%eax
-ENDPROC(efi32_stub_entry)
+SYM_FUNC_END(efi32_stub_entry)
 #endif
 
 	.text
-.Lrelocated:
+SYM_FUNC_START_LOCAL_NOALIGN(.Lrelocated)
 
 /*
  * Clear BSS (stack is currently empty)
@@ -260,6 +260,7 @@ ENDPROC(efi32_stub_entry)
  */
 	xorl	%ebx, %ebx
 	jmp	*%eax
+SYM_FUNC_END(.Lrelocated)
 
 #ifdef CONFIG_EFI_STUB
 	.data
diff --git a/arch/x86/boot/compressed/head_64.S b/arch/x86/boot/compressed/head_64.S
index d98cd483377e..58a512e33d8d 100644
--- a/arch/x86/boot/compressed/head_64.S
+++ b/arch/x86/boot/compressed/head_64.S
@@ -45,7 +45,7 @@
 
 	__HEAD
 	.code32
-ENTRY(startup_32)
+SYM_FUNC_START(startup_32)
 	/*
 	 * 32bit entry is 0 and it is ABI so immutable!
 	 * If we come here directly from a bootloader,
@@ -222,11 +222,11 @@ ENTRY(startup_32)
 
 	/* Jump from 32bit compatibility mode into 64bit mode. */
 	lret
-ENDPROC(startup_32)
+SYM_FUNC_END(startup_32)
 
 #ifdef CONFIG_EFI_MIXED
 	.org 0x190
-ENTRY(efi32_stub_entry)
+SYM_FUNC_START(efi32_stub_entry)
 	add	$0x4, %esp		/* Discard return address */
 	popl	%ecx
 	popl	%edx
@@ -245,12 +245,12 @@ ENTRY(efi32_stub_entry)
 	movl	%eax, efi_config(%ebp)
 
 	jmp	startup_32
-ENDPROC(efi32_stub_entry)
+SYM_FUNC_END(efi32_stub_entry)
 #endif
 
 	.code64
 	.org 0x200
-ENTRY(startup_64)
+SYM_CODE_START(startup_64)
 	/*
 	 * 64bit entry is 0x200 and it is ABI so immutable!
 	 * We come here either from startup_32 or directly from a
@@ -442,11 +442,12 @@ trampoline_return:
  */
 	leaq	.Lrelocated(%rbx), %rax
 	jmp	*%rax
+SYM_CODE_END(startup_64)
 
 #ifdef CONFIG_EFI_STUB
 
 /* The entry point for the PE/COFF executable is efi_pe_entry. */
-ENTRY(efi_pe_entry)
+SYM_FUNC_START(efi_pe_entry)
 	movq	%rcx, efi64_config(%rip)	/* Handle */
 	movq	%rdx, efi64_config+8(%rip) /* EFI System table pointer */
 
@@ -495,10 +496,10 @@ fail:
 	movl	BP_code32_start(%esi), %eax
 	leaq	startup_64(%rax), %rax
 	jmp	*%rax
-ENDPROC(efi_pe_entry)
+SYM_FUNC_END(efi_pe_entry)
 
 	.org 0x390
-ENTRY(efi64_stub_entry)
+SYM_FUNC_START(efi64_stub_entry)
 	movq	%rdi, efi64_config(%rip)	/* Handle */
 	movq	%rsi, efi64_config+8(%rip) /* EFI System table pointer */
 
@@ -507,11 +508,11 @@ ENTRY(efi64_stub_entry)
 
 	movq	%rdx, %rsi
 	jmp	handover_entry
-ENDPROC(efi64_stub_entry)
+SYM_FUNC_END(efi64_stub_entry)
 #endif
 
 	.text
-.Lrelocated:
+SYM_FUNC_START_LOCAL_NOALIGN(.Lrelocated)
 
 /*
  * Clear BSS (stack is currently empty)
@@ -540,6 +541,7 @@ ENDPROC(efi64_stub_entry)
  * Jump to the decompressed kernel.
  */
 	jmp	*%rax
+SYM_FUNC_END(.Lrelocated)
 
 /*
  * Adjust the global offset table
@@ -570,7 +572,7 @@ ENDPROC(efi64_stub_entry)
  * ECX contains the base address of the trampoline memory.
  * Non zero RDX means trampoline needs to enable 5-level paging.
  */
-ENTRY(trampoline_32bit_src)
+SYM_CODE_START(trampoline_32bit_src)
 	/* Set up data and stack segments */
 	movl	$__KERNEL_DS, %eax
 	movl	%eax, %ds
@@ -633,11 +635,13 @@ ENTRY(trampoline_32bit_src)
 	movl	%eax, %cr0
 
 	lret
+SYM_CODE_END(trampoline_32bit_src)
 
 	.code64
-.Lpaging_enabled:
+SYM_FUNC_START_LOCAL_NOALIGN(.Lpaging_enabled)
 	/* Return from the trampoline */
 	jmp	*%rdi
+SYM_FUNC_END(.Lpaging_enabled)
 
 	/*
          * The trampoline code has a size limit.
@@ -647,20 +651,22 @@ ENTRY(trampoline_32bit_src)
 	.org	trampoline_32bit_src + TRAMPOLINE_32BIT_CODE_SIZE
 
 	.code32
-.Lno_longmode:
+SYM_FUNC_START_LOCAL_NOALIGN(.Lno_longmode)
 	/* This isn't an x86-64 CPU, so hang intentionally, we cannot continue */
 1:
 	hlt
 	jmp     1b
+SYM_FUNC_END(.Lno_longmode)
 
 #include "../../kernel/verify_cpu.S"
 
 	.data
-gdt64:
+SYM_DATA_START_LOCAL(gdt64)
 	.word	gdt_end - gdt
 	.quad   0
+SYM_DATA_END(gdt64)
 	.balign	8
-gdt:
+SYM_DATA_START_LOCAL(gdt)
 	.word	gdt_end - gdt
 	.long	gdt
 	.word	0
@@ -669,25 +675,24 @@ gdt:
 	.quad	0x00cf92000000ffff	/* __KERNEL_DS */
 	.quad	0x0080890000000000	/* TS descriptor */
 	.quad   0x0000000000000000	/* TS continued */
-gdt_end:
+SYM_DATA_END_LABEL(gdt, SYM_L_LOCAL, gdt_end)
 
 #ifdef CONFIG_EFI_STUB
-efi_config:
-	.quad	0
+SYM_DATA_LOCAL(efi_config, .quad 0)
 
 #ifdef CONFIG_EFI_MIXED
-	.global efi32_config
-efi32_config:
+SYM_DATA_START(efi32_config)
 	.fill	5,8,0
 	.quad	efi64_thunk
 	.byte	0
+SYM_DATA_END(efi32_config)
 #endif
 
-	.global efi64_config
-efi64_config:
+SYM_DATA_START(efi64_config)
 	.fill	5,8,0
 	.quad	efi_call
 	.byte	1
+SYM_DATA_END(efi64_config)
 #endif /* CONFIG_EFI_STUB */
 
 /*
@@ -695,23 +700,21 @@ efi64_config:
  */
 	.bss
 	.balign 4
-boot_heap:
-	.fill BOOT_HEAP_SIZE, 1, 0
-boot_stack:
+SYM_DATA_LOCAL(boot_heap,	.fill BOOT_HEAP_SIZE, 1, 0)
+
+SYM_DATA_START_LOCAL(boot_stack)
 	.fill BOOT_STACK_SIZE, 1, 0
-boot_stack_end:
+SYM_DATA_END_LABEL(boot_stack, SYM_L_LOCAL, boot_stack_end)
 
 /*
  * Space for page tables (not in .bss so not zeroed)
  */
 	.section ".pgtable","a",@nobits
 	.balign 4096
-pgtable:
-	.fill BOOT_PGT_SIZE, 1, 0
+SYM_DATA_LOCAL(pgtable,		.fill BOOT_PGT_SIZE, 1, 0)
 
 /*
  * The page table is going to be used instead of page table in the trampoline
  * memory.
  */
-top_pgtable:
-	.fill PAGE_SIZE, 1, 0
+SYM_DATA_LOCAL(top_pgtable,	.fill PAGE_SIZE, 1, 0)
diff --git a/arch/x86/boot/compressed/kaslr.c b/arch/x86/boot/compressed/kaslr.c
index 2e53c056ba20..d7408af55738 100644
--- a/arch/x86/boot/compressed/kaslr.c
+++ b/arch/x86/boot/compressed/kaslr.c
@@ -132,8 +132,14 @@ char *skip_spaces(const char *str)
 #include "../../../../lib/ctype.c"
 #include "../../../../lib/cmdline.c"
 
+enum parse_mode {
+	PARSE_MEMMAP,
+	PARSE_EFI,
+};
+
 static int
-parse_memmap(char *p, unsigned long long *start, unsigned long long *size)
+parse_memmap(char *p, unsigned long long *start, unsigned long long *size,
+		enum parse_mode mode)
 {
 	char *oldp;
 
@@ -156,8 +162,29 @@ parse_memmap(char *p, unsigned long long *start, unsigned long long *size)
 		*start = memparse(p + 1, &p);
 		return 0;
 	case '@':
-		/* memmap=nn@ss specifies usable region, should be skipped */
-		*size = 0;
+		if (mode == PARSE_MEMMAP) {
+			/*
+			 * memmap=nn@ss specifies usable region, should
+			 * be skipped
+			 */
+			*size = 0;
+		} else {
+			unsigned long long flags;
+
+			/*
+			 * efi_fake_mem=nn@ss:attr the attr specifies
+			 * flags that might imply a soft-reservation.
+			 */
+			*start = memparse(p + 1, &p);
+			if (p && *p == ':') {
+				p++;
+				if (kstrtoull(p, 0, &flags) < 0)
+					*size = 0;
+				else if (flags & EFI_MEMORY_SP)
+					return 0;
+			}
+			*size = 0;
+		}
 		/* Fall through */
 	default:
 		/*
@@ -172,7 +199,7 @@ parse_memmap(char *p, unsigned long long *start, unsigned long long *size)
 	return -EINVAL;
 }
 
-static void mem_avoid_memmap(char *str)
+static void mem_avoid_memmap(enum parse_mode mode, char *str)
 {
 	static int i;
 
@@ -187,7 +214,7 @@ static void mem_avoid_memmap(char *str)
 		if (k)
 			*k++ = 0;
 
-		rc = parse_memmap(str, &start, &size);
+		rc = parse_memmap(str, &start, &size, mode);
 		if (rc < 0)
 			break;
 		str = k;
@@ -238,7 +265,6 @@ static void parse_gb_huge_pages(char *param, char *val)
 	}
 }
 
-
 static void handle_mem_options(void)
 {
 	char *args = (char *)get_cmd_line_ptr();
@@ -271,7 +297,7 @@ static void handle_mem_options(void)
 		}
 
 		if (!strcmp(param, "memmap")) {
-			mem_avoid_memmap(val);
+			mem_avoid_memmap(PARSE_MEMMAP, val);
 		} else if (strstr(param, "hugepages")) {
 			parse_gb_huge_pages(param, val);
 		} else if (!strcmp(param, "mem")) {
@@ -284,6 +310,8 @@ static void handle_mem_options(void)
 				goto out;
 
 			mem_limit = mem_size;
+		} else if (!strcmp(param, "efi_fake_mem")) {
+			mem_avoid_memmap(PARSE_EFI, val);
 		}
 	}
 
@@ -459,6 +487,18 @@ static bool mem_avoid_overlap(struct mem_vector *img,
 			is_overlapping = true;
 		}
 
+		if (ptr->type == SETUP_INDIRECT &&
+		    ((struct setup_indirect *)ptr->data)->type != SETUP_INDIRECT) {
+			avoid.start = ((struct setup_indirect *)ptr->data)->addr;
+			avoid.size = ((struct setup_indirect *)ptr->data)->len;
+
+			if (mem_overlaps(img, &avoid) && (avoid.start < earliest)) {
+				*overlap = avoid;
+				earliest = overlap->start;
+				is_overlapping = true;
+			}
+		}
+
 		ptr = (struct setup_data *)(unsigned long)ptr->next;
 	}
 
@@ -760,6 +800,10 @@ process_efi_entries(unsigned long minimum, unsigned long image_size)
 		if (md->type != EFI_CONVENTIONAL_MEMORY)
 			continue;
 
+		if (efi_soft_reserve_enabled() &&
+		    (md->attribute & EFI_MEMORY_SP))
+			continue;
+
 		if (efi_mirror_found &&
 		    !(md->attribute & EFI_MEMORY_MORE_RELIABLE))
 			continue;
diff --git a/arch/x86/boot/compressed/kernel_info.S b/arch/x86/boot/compressed/kernel_info.S
new file mode 100644
index 000000000000..f818ee8fba38
--- /dev/null
+++ b/arch/x86/boot/compressed/kernel_info.S
@@ -0,0 +1,22 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#include <asm/bootparam.h>
+
+	.section ".rodata.kernel_info", "a"
+
+	.global kernel_info
+
+kernel_info:
+	/* Header, Linux top (structure). */
+	.ascii	"LToP"
+	/* Size. */
+	.long	kernel_info_var_len_data - kernel_info
+	/* Size total. */
+	.long	kernel_info_end - kernel_info
+
+	/* Maximal allowed type for setup_data and setup_indirect structs. */
+	.long	SETUP_TYPE_MAX
+
+kernel_info_var_len_data:
+	/* Empty for time being... */
+kernel_info_end:
diff --git a/arch/x86/boot/compressed/mem_encrypt.S b/arch/x86/boot/compressed/mem_encrypt.S
index 6afb7130a387..dd07e7b41b11 100644
--- a/arch/x86/boot/compressed/mem_encrypt.S
+++ b/arch/x86/boot/compressed/mem_encrypt.S
@@ -15,7 +15,7 @@
 
 	.text
 	.code32
-ENTRY(get_sev_encryption_bit)
+SYM_FUNC_START(get_sev_encryption_bit)
 	xor	%eax, %eax
 
 #ifdef CONFIG_AMD_MEM_ENCRYPT
@@ -65,10 +65,10 @@ ENTRY(get_sev_encryption_bit)
 #endif	/* CONFIG_AMD_MEM_ENCRYPT */
 
 	ret
-ENDPROC(get_sev_encryption_bit)
+SYM_FUNC_END(get_sev_encryption_bit)
 
 	.code64
-ENTRY(set_sev_encryption_mask)
+SYM_FUNC_START(set_sev_encryption_mask)
 #ifdef CONFIG_AMD_MEM_ENCRYPT
 	push	%rbp
 	push	%rdx
@@ -90,12 +90,11 @@ ENTRY(set_sev_encryption_mask)
 
 	xor	%rax, %rax
 	ret
-ENDPROC(set_sev_encryption_mask)
+SYM_FUNC_END(set_sev_encryption_mask)
 
 	.data
 
 #ifdef CONFIG_AMD_MEM_ENCRYPT
 	.balign	8
-GLOBAL(sme_me_mask)
-	.quad	0
+SYM_DATA(sme_me_mask, .quad 0)
 #endif
diff --git a/arch/x86/boot/copy.S b/arch/x86/boot/copy.S
index 4c5f4f4ad035..6afd05e819d2 100644
--- a/arch/x86/boot/copy.S
+++ b/arch/x86/boot/copy.S
@@ -15,7 +15,7 @@
 	.code16
 	.text
 
-GLOBAL(memcpy)
+SYM_FUNC_START_NOALIGN(memcpy)
 	pushw	%si
 	pushw	%di
 	movw	%ax, %di
@@ -29,9 +29,9 @@ GLOBAL(memcpy)
 	popw	%di
 	popw	%si
 	retl
-ENDPROC(memcpy)
+SYM_FUNC_END(memcpy)
 
-GLOBAL(memset)
+SYM_FUNC_START_NOALIGN(memset)
 	pushw	%di
 	movw	%ax, %di
 	movzbl	%dl, %eax
@@ -44,22 +44,22 @@ GLOBAL(memset)
 	rep; stosb
 	popw	%di
 	retl
-ENDPROC(memset)
+SYM_FUNC_END(memset)
 
-GLOBAL(copy_from_fs)
+SYM_FUNC_START_NOALIGN(copy_from_fs)
 	pushw	%ds
 	pushw	%fs
 	popw	%ds
 	calll	memcpy
 	popw	%ds
 	retl
-ENDPROC(copy_from_fs)
+SYM_FUNC_END(copy_from_fs)
 
-GLOBAL(copy_to_fs)
+SYM_FUNC_START_NOALIGN(copy_to_fs)
 	pushw	%es
 	pushw	%fs
 	popw	%es
 	calll	memcpy
 	popw	%es
 	retl
-ENDPROC(copy_to_fs)
+SYM_FUNC_END(copy_to_fs)
diff --git a/arch/x86/boot/header.S b/arch/x86/boot/header.S
index 2c11c0f45d49..97d9b6d6c1af 100644
--- a/arch/x86/boot/header.S
+++ b/arch/x86/boot/header.S
@@ -300,7 +300,7 @@ _start:
 	# Part 2 of the header, from the old setup.S
 
 		.ascii	"HdrS"		# header signature
-		.word	0x020d		# header version number (>= 0x0105)
+		.word	0x020f		# header version number (>= 0x0105)
 					# or else old loadlin-1.5 will fail)
 		.globl realmode_swtch
 realmode_swtch:	.word	0, 0		# default_switch, SETUPSEG
@@ -567,6 +567,7 @@ pref_address:		.quad LOAD_PHYSICAL_ADDR	# preferred load addr
 
 init_size:		.long INIT_SIZE		# kernel initialization size
 handover_offset:	.long 0			# Filled in by build.c
+kernel_info_offset:	.long 0			# Filled in by build.c
 
 # End of setup header #####################################################
 
diff --git a/arch/x86/boot/pmjump.S b/arch/x86/boot/pmjump.S
index c22f9a7d1aeb..cbec8bd0841f 100644
--- a/arch/x86/boot/pmjump.S
+++ b/arch/x86/boot/pmjump.S
@@ -21,7 +21,7 @@
 /*
  * void protected_mode_jump(u32 entrypoint, u32 bootparams);
  */
-GLOBAL(protected_mode_jump)
+SYM_FUNC_START_NOALIGN(protected_mode_jump)
 	movl	%edx, %esi		# Pointer to boot_params table
 
 	xorl	%ebx, %ebx
@@ -40,13 +40,13 @@ GLOBAL(protected_mode_jump)
 
 	# Transition to 32-bit mode
 	.byte	0x66, 0xea		# ljmpl opcode
-2:	.long	in_pm32			# offset
+2:	.long	.Lin_pm32		# offset
 	.word	__BOOT_CS		# segment
-ENDPROC(protected_mode_jump)
+SYM_FUNC_END(protected_mode_jump)
 
 	.code32
 	.section ".text32","ax"
-GLOBAL(in_pm32)
+SYM_FUNC_START_LOCAL_NOALIGN(.Lin_pm32)
 	# Set up data segments for flat 32-bit mode
 	movl	%ecx, %ds
 	movl	%ecx, %es
@@ -72,4 +72,4 @@ GLOBAL(in_pm32)
 	lldt	%cx
 
 	jmpl	*%eax			# Jump to the 32-bit entrypoint
-ENDPROC(in_pm32)
+SYM_FUNC_END(.Lin_pm32)
diff --git a/arch/x86/boot/tools/build.c b/arch/x86/boot/tools/build.c
index a93d44e58f9c..55e669d29e54 100644
--- a/arch/x86/boot/tools/build.c
+++ b/arch/x86/boot/tools/build.c
@@ -56,6 +56,7 @@ u8 buf[SETUP_SECT_MAX*512];
 unsigned long efi32_stub_entry;
 unsigned long efi64_stub_entry;
 unsigned long efi_pe_entry;
+unsigned long kernel_info;
 unsigned long startup_64;
 
 /*----------------------------------------------------------------------*/
@@ -321,6 +322,7 @@ static void parse_zoffset(char *fname)
 		PARSE_ZOFS(p, efi32_stub_entry);
 		PARSE_ZOFS(p, efi64_stub_entry);
 		PARSE_ZOFS(p, efi_pe_entry);
+		PARSE_ZOFS(p, kernel_info);
 		PARSE_ZOFS(p, startup_64);
 
 		p = strchr(p, '\n');
@@ -410,6 +412,9 @@ int main(int argc, char ** argv)
 
 	efi_stub_entry_update();
 
+	/* Update kernel_info offset. */
+	put_unaligned_le32(kernel_info, &buf[0x268]);
+
 	crc = partial_crc32(buf, i, crc);
 	if (fwrite(buf, 1, i, dest) != i)
 		die("Writing setup failed");
diff --git a/arch/x86/configs/x86_64_defconfig b/arch/x86/configs/x86_64_defconfig
index d0a5ffeae8df..0b9654c7a05c 100644
--- a/arch/x86/configs/x86_64_defconfig
+++ b/arch/x86/configs/x86_64_defconfig
@@ -25,7 +25,6 @@ CONFIG_MODULES=y
 CONFIG_MODULE_UNLOAD=y
 CONFIG_MODULE_FORCE_UNLOAD=y
 CONFIG_SMP=y
-CONFIG_CALGARY_IOMMU=y
 CONFIG_NR_CPUS=64
 CONFIG_SCHED_SMT=y
 CONFIG_PREEMPT_VOLUNTARY=y
diff --git a/arch/x86/crypto/aegis128-aesni-asm.S b/arch/x86/crypto/aegis128-aesni-asm.S
index 4434607e366d..51d46d93efbc 100644
--- a/arch/x86/crypto/aegis128-aesni-asm.S
+++ b/arch/x86/crypto/aegis128-aesni-asm.S
@@ -71,7 +71,7 @@
  *   %r8
  *   %r9
  */
-__load_partial:
+SYM_FUNC_START_LOCAL(__load_partial)
 	xor %r9d, %r9d
 	pxor MSG, MSG
 
@@ -123,7 +123,7 @@ __load_partial:
 
 .Lld_partial_8:
 	ret
-ENDPROC(__load_partial)
+SYM_FUNC_END(__load_partial)
 
 /*
  * __store_partial: internal ABI
@@ -137,7 +137,7 @@ ENDPROC(__load_partial)
  *   %r9
  *   %r10
  */
-__store_partial:
+SYM_FUNC_START_LOCAL(__store_partial)
 	mov LEN, %r8
 	mov DST, %r9
 
@@ -181,12 +181,12 @@ __store_partial:
 
 .Lst_partial_1:
 	ret
-ENDPROC(__store_partial)
+SYM_FUNC_END(__store_partial)
 
 /*
  * void crypto_aegis128_aesni_init(void *state, const void *key, const void *iv);
  */
-ENTRY(crypto_aegis128_aesni_init)
+SYM_FUNC_START(crypto_aegis128_aesni_init)
 	FRAME_BEGIN
 
 	/* load IV: */
@@ -226,13 +226,13 @@ ENTRY(crypto_aegis128_aesni_init)
 
 	FRAME_END
 	ret
-ENDPROC(crypto_aegis128_aesni_init)
+SYM_FUNC_END(crypto_aegis128_aesni_init)
 
 /*
  * void crypto_aegis128_aesni_ad(void *state, unsigned int length,
  *                               const void *data);
  */
-ENTRY(crypto_aegis128_aesni_ad)
+SYM_FUNC_START(crypto_aegis128_aesni_ad)
 	FRAME_BEGIN
 
 	cmp $0x10, LEN
@@ -378,7 +378,7 @@ ENTRY(crypto_aegis128_aesni_ad)
 .Lad_out:
 	FRAME_END
 	ret
-ENDPROC(crypto_aegis128_aesni_ad)
+SYM_FUNC_END(crypto_aegis128_aesni_ad)
 
 .macro encrypt_block a s0 s1 s2 s3 s4 i
 	movdq\a (\i * 0x10)(SRC), MSG
@@ -402,7 +402,7 @@ ENDPROC(crypto_aegis128_aesni_ad)
  * void crypto_aegis128_aesni_enc(void *state, unsigned int length,
  *                                const void *src, void *dst);
  */
-ENTRY(crypto_aegis128_aesni_enc)
+SYM_FUNC_START(crypto_aegis128_aesni_enc)
 	FRAME_BEGIN
 
 	cmp $0x10, LEN
@@ -493,13 +493,13 @@ ENTRY(crypto_aegis128_aesni_enc)
 .Lenc_out:
 	FRAME_END
 	ret
-ENDPROC(crypto_aegis128_aesni_enc)
+SYM_FUNC_END(crypto_aegis128_aesni_enc)
 
 /*
  * void crypto_aegis128_aesni_enc_tail(void *state, unsigned int length,
  *                                     const void *src, void *dst);
  */
-ENTRY(crypto_aegis128_aesni_enc_tail)
+SYM_FUNC_START(crypto_aegis128_aesni_enc_tail)
 	FRAME_BEGIN
 
 	/* load the state: */
@@ -533,7 +533,7 @@ ENTRY(crypto_aegis128_aesni_enc_tail)
 
 	FRAME_END
 	ret
-ENDPROC(crypto_aegis128_aesni_enc_tail)
+SYM_FUNC_END(crypto_aegis128_aesni_enc_tail)
 
 .macro decrypt_block a s0 s1 s2 s3 s4 i
 	movdq\a (\i * 0x10)(SRC), MSG
@@ -556,7 +556,7 @@ ENDPROC(crypto_aegis128_aesni_enc_tail)
  * void crypto_aegis128_aesni_dec(void *state, unsigned int length,
  *                                const void *src, void *dst);
  */
-ENTRY(crypto_aegis128_aesni_dec)
+SYM_FUNC_START(crypto_aegis128_aesni_dec)
 	FRAME_BEGIN
 
 	cmp $0x10, LEN
@@ -647,13 +647,13 @@ ENTRY(crypto_aegis128_aesni_dec)
 .Ldec_out:
 	FRAME_END
 	ret
-ENDPROC(crypto_aegis128_aesni_dec)
+SYM_FUNC_END(crypto_aegis128_aesni_dec)
 
 /*
  * void crypto_aegis128_aesni_dec_tail(void *state, unsigned int length,
  *                                     const void *src, void *dst);
  */
-ENTRY(crypto_aegis128_aesni_dec_tail)
+SYM_FUNC_START(crypto_aegis128_aesni_dec_tail)
 	FRAME_BEGIN
 
 	/* load the state: */
@@ -697,13 +697,13 @@ ENTRY(crypto_aegis128_aesni_dec_tail)
 
 	FRAME_END
 	ret
-ENDPROC(crypto_aegis128_aesni_dec_tail)
+SYM_FUNC_END(crypto_aegis128_aesni_dec_tail)
 
 /*
  * void crypto_aegis128_aesni_final(void *state, void *tag_xor,
  *                                  u64 assoclen, u64 cryptlen);
  */
-ENTRY(crypto_aegis128_aesni_final)
+SYM_FUNC_START(crypto_aegis128_aesni_final)
 	FRAME_BEGIN
 
 	/* load the state: */
@@ -744,4 +744,4 @@ ENTRY(crypto_aegis128_aesni_final)
 
 	FRAME_END
 	ret
-ENDPROC(crypto_aegis128_aesni_final)
+SYM_FUNC_END(crypto_aegis128_aesni_final)
diff --git a/arch/x86/crypto/aes_ctrby8_avx-x86_64.S b/arch/x86/crypto/aes_ctrby8_avx-x86_64.S
index 5f6a5af9c489..ec437db1fa54 100644
--- a/arch/x86/crypto/aes_ctrby8_avx-x86_64.S
+++ b/arch/x86/crypto/aes_ctrby8_avx-x86_64.S
@@ -544,11 +544,11 @@ ddq_add_8:
  * aes_ctr_enc_128_avx_by8(void *in, void *iv, void *keys, void *out,
  *			unsigned int num_bytes)
  */
-ENTRY(aes_ctr_enc_128_avx_by8)
+SYM_FUNC_START(aes_ctr_enc_128_avx_by8)
 	/* call the aes main loop */
 	do_aes_ctrmain KEY_128
 
-ENDPROC(aes_ctr_enc_128_avx_by8)
+SYM_FUNC_END(aes_ctr_enc_128_avx_by8)
 
 /*
  * routine to do AES192 CTR enc/decrypt "by8"
@@ -557,11 +557,11 @@ ENDPROC(aes_ctr_enc_128_avx_by8)
  * aes_ctr_enc_192_avx_by8(void *in, void *iv, void *keys, void *out,
  *			unsigned int num_bytes)
  */
-ENTRY(aes_ctr_enc_192_avx_by8)
+SYM_FUNC_START(aes_ctr_enc_192_avx_by8)
 	/* call the aes main loop */
 	do_aes_ctrmain KEY_192
 
-ENDPROC(aes_ctr_enc_192_avx_by8)
+SYM_FUNC_END(aes_ctr_enc_192_avx_by8)
 
 /*
  * routine to do AES256 CTR enc/decrypt "by8"
@@ -570,8 +570,8 @@ ENDPROC(aes_ctr_enc_192_avx_by8)
  * aes_ctr_enc_256_avx_by8(void *in, void *iv, void *keys, void *out,
  *			unsigned int num_bytes)
  */
-ENTRY(aes_ctr_enc_256_avx_by8)
+SYM_FUNC_START(aes_ctr_enc_256_avx_by8)
 	/* call the aes main loop */
 	do_aes_ctrmain KEY_256
 
-ENDPROC(aes_ctr_enc_256_avx_by8)
+SYM_FUNC_END(aes_ctr_enc_256_avx_by8)
diff --git a/arch/x86/crypto/aesni-intel_asm.S b/arch/x86/crypto/aesni-intel_asm.S
index e40bdf024ba7..d28503f99f58 100644
--- a/arch/x86/crypto/aesni-intel_asm.S
+++ b/arch/x86/crypto/aesni-intel_asm.S
@@ -1592,7 +1592,7 @@ _esb_loop_\@:
 * poly = x^128 + x^127 + x^126 + x^121 + 1
 *
 *****************************************************************************/
-ENTRY(aesni_gcm_dec)
+SYM_FUNC_START(aesni_gcm_dec)
 	FUNC_SAVE
 
 	GCM_INIT %arg6, arg7, arg8, arg9
@@ -1600,7 +1600,7 @@ ENTRY(aesni_gcm_dec)
 	GCM_COMPLETE arg10, arg11
 	FUNC_RESTORE
 	ret
-ENDPROC(aesni_gcm_dec)
+SYM_FUNC_END(aesni_gcm_dec)
 
 
 /*****************************************************************************
@@ -1680,7 +1680,7 @@ ENDPROC(aesni_gcm_dec)
 *
 * poly = x^128 + x^127 + x^126 + x^121 + 1
 ***************************************************************************/
-ENTRY(aesni_gcm_enc)
+SYM_FUNC_START(aesni_gcm_enc)
 	FUNC_SAVE
 
 	GCM_INIT %arg6, arg7, arg8, arg9
@@ -1689,7 +1689,7 @@ ENTRY(aesni_gcm_enc)
 	GCM_COMPLETE arg10, arg11
 	FUNC_RESTORE
 	ret
-ENDPROC(aesni_gcm_enc)
+SYM_FUNC_END(aesni_gcm_enc)
 
 /*****************************************************************************
 * void aesni_gcm_init(void *aes_ctx,      // AES Key schedule. Starts on a 16 byte boundary.
@@ -1702,12 +1702,12 @@ ENDPROC(aesni_gcm_enc)
 *                     const u8 *aad,      // Additional Authentication Data (AAD)
 *                     u64 aad_len)        // Length of AAD in bytes.
 */
-ENTRY(aesni_gcm_init)
+SYM_FUNC_START(aesni_gcm_init)
 	FUNC_SAVE
 	GCM_INIT %arg3, %arg4,%arg5, %arg6
 	FUNC_RESTORE
 	ret
-ENDPROC(aesni_gcm_init)
+SYM_FUNC_END(aesni_gcm_init)
 
 /*****************************************************************************
 * void aesni_gcm_enc_update(void *aes_ctx,      // AES Key schedule. Starts on a 16 byte boundary.
@@ -1717,12 +1717,12 @@ ENDPROC(aesni_gcm_init)
 *                    const u8 *in,       // Plaintext input
 *                    u64 plaintext_len,  // Length of data in bytes for encryption.
 */
-ENTRY(aesni_gcm_enc_update)
+SYM_FUNC_START(aesni_gcm_enc_update)
 	FUNC_SAVE
 	GCM_ENC_DEC enc
 	FUNC_RESTORE
 	ret
-ENDPROC(aesni_gcm_enc_update)
+SYM_FUNC_END(aesni_gcm_enc_update)
 
 /*****************************************************************************
 * void aesni_gcm_dec_update(void *aes_ctx,      // AES Key schedule. Starts on a 16 byte boundary.
@@ -1732,12 +1732,12 @@ ENDPROC(aesni_gcm_enc_update)
 *                    const u8 *in,       // Plaintext input
 *                    u64 plaintext_len,  // Length of data in bytes for encryption.
 */
-ENTRY(aesni_gcm_dec_update)
+SYM_FUNC_START(aesni_gcm_dec_update)
 	FUNC_SAVE
 	GCM_ENC_DEC dec
 	FUNC_RESTORE
 	ret
-ENDPROC(aesni_gcm_dec_update)
+SYM_FUNC_END(aesni_gcm_dec_update)
 
 /*****************************************************************************
 * void aesni_gcm_finalize(void *aes_ctx,      // AES Key schedule. Starts on a 16 byte boundary.
@@ -1747,19 +1747,18 @@ ENDPROC(aesni_gcm_dec_update)
 *                    u64 auth_tag_len);  // Authenticated Tag Length in bytes. Valid values are 16 (most likely),
 *                                        // 12 or 8.
 */
-ENTRY(aesni_gcm_finalize)
+SYM_FUNC_START(aesni_gcm_finalize)
 	FUNC_SAVE
 	GCM_COMPLETE %arg3 %arg4
 	FUNC_RESTORE
 	ret
-ENDPROC(aesni_gcm_finalize)
+SYM_FUNC_END(aesni_gcm_finalize)
 
 #endif
 
 
-.align 4
-_key_expansion_128:
-_key_expansion_256a:
+SYM_FUNC_START_LOCAL_ALIAS(_key_expansion_128)
+SYM_FUNC_START_LOCAL(_key_expansion_256a)
 	pshufd $0b11111111, %xmm1, %xmm1
 	shufps $0b00010000, %xmm0, %xmm4
 	pxor %xmm4, %xmm0
@@ -1769,11 +1768,10 @@ _key_expansion_256a:
 	movaps %xmm0, (TKEYP)
 	add $0x10, TKEYP
 	ret
-ENDPROC(_key_expansion_128)
-ENDPROC(_key_expansion_256a)
+SYM_FUNC_END(_key_expansion_256a)
+SYM_FUNC_END_ALIAS(_key_expansion_128)
 
-.align 4
-_key_expansion_192a:
+SYM_FUNC_START_LOCAL(_key_expansion_192a)
 	pshufd $0b01010101, %xmm1, %xmm1
 	shufps $0b00010000, %xmm0, %xmm4
 	pxor %xmm4, %xmm0
@@ -1795,10 +1793,9 @@ _key_expansion_192a:
 	movaps %xmm1, 0x10(TKEYP)
 	add $0x20, TKEYP
 	ret
-ENDPROC(_key_expansion_192a)
+SYM_FUNC_END(_key_expansion_192a)
 
-.align 4
-_key_expansion_192b:
+SYM_FUNC_START_LOCAL(_key_expansion_192b)
 	pshufd $0b01010101, %xmm1, %xmm1
 	shufps $0b00010000, %xmm0, %xmm4
 	pxor %xmm4, %xmm0
@@ -1815,10 +1812,9 @@ _key_expansion_192b:
 	movaps %xmm0, (TKEYP)
 	add $0x10, TKEYP
 	ret
-ENDPROC(_key_expansion_192b)
+SYM_FUNC_END(_key_expansion_192b)
 
-.align 4
-_key_expansion_256b:
+SYM_FUNC_START_LOCAL(_key_expansion_256b)
 	pshufd $0b10101010, %xmm1, %xmm1
 	shufps $0b00010000, %xmm2, %xmm4
 	pxor %xmm4, %xmm2
@@ -1828,13 +1824,13 @@ _key_expansion_256b:
 	movaps %xmm2, (TKEYP)
 	add $0x10, TKEYP
 	ret
-ENDPROC(_key_expansion_256b)
+SYM_FUNC_END(_key_expansion_256b)
 
 /*
  * int aesni_set_key(struct crypto_aes_ctx *ctx, const u8 *in_key,
  *                   unsigned int key_len)
  */
-ENTRY(aesni_set_key)
+SYM_FUNC_START(aesni_set_key)
 	FRAME_BEGIN
 #ifndef __x86_64__
 	pushl KEYP
@@ -1943,12 +1939,12 @@ ENTRY(aesni_set_key)
 #endif
 	FRAME_END
 	ret
-ENDPROC(aesni_set_key)
+SYM_FUNC_END(aesni_set_key)
 
 /*
  * void aesni_enc(struct crypto_aes_ctx *ctx, u8 *dst, const u8 *src)
  */
-ENTRY(aesni_enc)
+SYM_FUNC_START(aesni_enc)
 	FRAME_BEGIN
 #ifndef __x86_64__
 	pushl KEYP
@@ -1967,7 +1963,7 @@ ENTRY(aesni_enc)
 #endif
 	FRAME_END
 	ret
-ENDPROC(aesni_enc)
+SYM_FUNC_END(aesni_enc)
 
 /*
  * _aesni_enc1:		internal ABI
@@ -1981,8 +1977,7 @@ ENDPROC(aesni_enc)
  *	KEY
  *	TKEYP (T1)
  */
-.align 4
-_aesni_enc1:
+SYM_FUNC_START_LOCAL(_aesni_enc1)
 	movaps (KEYP), KEY		# key
 	mov KEYP, TKEYP
 	pxor KEY, STATE		# round 0
@@ -2025,7 +2020,7 @@ _aesni_enc1:
 	movaps 0x70(TKEYP), KEY
 	AESENCLAST KEY STATE
 	ret
-ENDPROC(_aesni_enc1)
+SYM_FUNC_END(_aesni_enc1)
 
 /*
  * _aesni_enc4:	internal ABI
@@ -2045,8 +2040,7 @@ ENDPROC(_aesni_enc1)
  *	KEY
  *	TKEYP (T1)
  */
-.align 4
-_aesni_enc4:
+SYM_FUNC_START_LOCAL(_aesni_enc4)
 	movaps (KEYP), KEY		# key
 	mov KEYP, TKEYP
 	pxor KEY, STATE1		# round 0
@@ -2134,12 +2128,12 @@ _aesni_enc4:
 	AESENCLAST KEY STATE3
 	AESENCLAST KEY STATE4
 	ret
-ENDPROC(_aesni_enc4)
+SYM_FUNC_END(_aesni_enc4)
 
 /*
  * void aesni_dec (struct crypto_aes_ctx *ctx, u8 *dst, const u8 *src)
  */
-ENTRY(aesni_dec)
+SYM_FUNC_START(aesni_dec)
 	FRAME_BEGIN
 #ifndef __x86_64__
 	pushl KEYP
@@ -2159,7 +2153,7 @@ ENTRY(aesni_dec)
 #endif
 	FRAME_END
 	ret
-ENDPROC(aesni_dec)
+SYM_FUNC_END(aesni_dec)
 
 /*
  * _aesni_dec1:		internal ABI
@@ -2173,8 +2167,7 @@ ENDPROC(aesni_dec)
  *	KEY
  *	TKEYP (T1)
  */
-.align 4
-_aesni_dec1:
+SYM_FUNC_START_LOCAL(_aesni_dec1)
 	movaps (KEYP), KEY		# key
 	mov KEYP, TKEYP
 	pxor KEY, STATE		# round 0
@@ -2217,7 +2210,7 @@ _aesni_dec1:
 	movaps 0x70(TKEYP), KEY
 	AESDECLAST KEY STATE
 	ret
-ENDPROC(_aesni_dec1)
+SYM_FUNC_END(_aesni_dec1)
 
 /*
  * _aesni_dec4:	internal ABI
@@ -2237,8 +2230,7 @@ ENDPROC(_aesni_dec1)
  *	KEY
  *	TKEYP (T1)
  */
-.align 4
-_aesni_dec4:
+SYM_FUNC_START_LOCAL(_aesni_dec4)
 	movaps (KEYP), KEY		# key
 	mov KEYP, TKEYP
 	pxor KEY, STATE1		# round 0
@@ -2326,13 +2318,13 @@ _aesni_dec4:
 	AESDECLAST KEY STATE3
 	AESDECLAST KEY STATE4
 	ret
-ENDPROC(_aesni_dec4)
+SYM_FUNC_END(_aesni_dec4)
 
 /*
  * void aesni_ecb_enc(struct crypto_aes_ctx *ctx, const u8 *dst, u8 *src,
  *		      size_t len)
  */
-ENTRY(aesni_ecb_enc)
+SYM_FUNC_START(aesni_ecb_enc)
 	FRAME_BEGIN
 #ifndef __x86_64__
 	pushl LEN
@@ -2386,13 +2378,13 @@ ENTRY(aesni_ecb_enc)
 #endif
 	FRAME_END
 	ret
-ENDPROC(aesni_ecb_enc)
+SYM_FUNC_END(aesni_ecb_enc)
 
 /*
  * void aesni_ecb_dec(struct crypto_aes_ctx *ctx, const u8 *dst, u8 *src,
  *		      size_t len);
  */
-ENTRY(aesni_ecb_dec)
+SYM_FUNC_START(aesni_ecb_dec)
 	FRAME_BEGIN
 #ifndef __x86_64__
 	pushl LEN
@@ -2447,13 +2439,13 @@ ENTRY(aesni_ecb_dec)
 #endif
 	FRAME_END
 	ret
-ENDPROC(aesni_ecb_dec)
+SYM_FUNC_END(aesni_ecb_dec)
 
 /*
  * void aesni_cbc_enc(struct crypto_aes_ctx *ctx, const u8 *dst, u8 *src,
  *		      size_t len, u8 *iv)
  */
-ENTRY(aesni_cbc_enc)
+SYM_FUNC_START(aesni_cbc_enc)
 	FRAME_BEGIN
 #ifndef __x86_64__
 	pushl IVP
@@ -2491,13 +2483,13 @@ ENTRY(aesni_cbc_enc)
 #endif
 	FRAME_END
 	ret
-ENDPROC(aesni_cbc_enc)
+SYM_FUNC_END(aesni_cbc_enc)
 
 /*
  * void aesni_cbc_dec(struct crypto_aes_ctx *ctx, const u8 *dst, u8 *src,
  *		      size_t len, u8 *iv)
  */
-ENTRY(aesni_cbc_dec)
+SYM_FUNC_START(aesni_cbc_dec)
 	FRAME_BEGIN
 #ifndef __x86_64__
 	pushl IVP
@@ -2584,7 +2576,7 @@ ENTRY(aesni_cbc_dec)
 #endif
 	FRAME_END
 	ret
-ENDPROC(aesni_cbc_dec)
+SYM_FUNC_END(aesni_cbc_dec)
 
 #ifdef __x86_64__
 .pushsection .rodata
@@ -2604,8 +2596,7 @@ ENDPROC(aesni_cbc_dec)
  *	INC:	== 1, in little endian
  *	BSWAP_MASK == endian swapping mask
  */
-.align 4
-_aesni_inc_init:
+SYM_FUNC_START_LOCAL(_aesni_inc_init)
 	movaps .Lbswap_mask, BSWAP_MASK
 	movaps IV, CTR
 	PSHUFB_XMM BSWAP_MASK CTR
@@ -2613,7 +2604,7 @@ _aesni_inc_init:
 	MOVQ_R64_XMM TCTR_LOW INC
 	MOVQ_R64_XMM CTR TCTR_LOW
 	ret
-ENDPROC(_aesni_inc_init)
+SYM_FUNC_END(_aesni_inc_init)
 
 /*
  * _aesni_inc:		internal ABI
@@ -2630,8 +2621,7 @@ ENDPROC(_aesni_inc_init)
  *	CTR:	== output IV, in little endian
  *	TCTR_LOW: == lower qword of CTR
  */
-.align 4
-_aesni_inc:
+SYM_FUNC_START_LOCAL(_aesni_inc)
 	paddq INC, CTR
 	add $1, TCTR_LOW
 	jnc .Linc_low
@@ -2642,13 +2632,13 @@ _aesni_inc:
 	movaps CTR, IV
 	PSHUFB_XMM BSWAP_MASK IV
 	ret
-ENDPROC(_aesni_inc)
+SYM_FUNC_END(_aesni_inc)
 
 /*
  * void aesni_ctr_enc(struct crypto_aes_ctx *ctx, const u8 *dst, u8 *src,
  *		      size_t len, u8 *iv)
  */
-ENTRY(aesni_ctr_enc)
+SYM_FUNC_START(aesni_ctr_enc)
 	FRAME_BEGIN
 	cmp $16, LEN
 	jb .Lctr_enc_just_ret
@@ -2705,7 +2695,7 @@ ENTRY(aesni_ctr_enc)
 .Lctr_enc_just_ret:
 	FRAME_END
 	ret
-ENDPROC(aesni_ctr_enc)
+SYM_FUNC_END(aesni_ctr_enc)
 
 /*
  * _aesni_gf128mul_x_ble:		internal ABI
@@ -2729,7 +2719,7 @@ ENDPROC(aesni_ctr_enc)
  * void aesni_xts_crypt8(struct crypto_aes_ctx *ctx, const u8 *dst, u8 *src,
  *			 bool enc, u8 *iv)
  */
-ENTRY(aesni_xts_crypt8)
+SYM_FUNC_START(aesni_xts_crypt8)
 	FRAME_BEGIN
 	cmpb $0, %cl
 	movl $0, %ecx
@@ -2833,6 +2823,6 @@ ENTRY(aesni_xts_crypt8)
 
 	FRAME_END
 	ret
-ENDPROC(aesni_xts_crypt8)
+SYM_FUNC_END(aesni_xts_crypt8)
 
 #endif
diff --git a/arch/x86/crypto/aesni-intel_avx-x86_64.S b/arch/x86/crypto/aesni-intel_avx-x86_64.S
index 91c039ab5699..bfa1c0b3e5b4 100644
--- a/arch/x86/crypto/aesni-intel_avx-x86_64.S
+++ b/arch/x86/crypto/aesni-intel_avx-x86_64.S
@@ -1775,12 +1775,12 @@ _initial_blocks_done\@:
 #        const   u8 *aad, /* Additional Authentication Data (AAD)*/
 #        u64     aad_len) /* Length of AAD in bytes. With RFC4106 this is going to be 8 or 12 Bytes */
 #############################################################
-ENTRY(aesni_gcm_init_avx_gen2)
+SYM_FUNC_START(aesni_gcm_init_avx_gen2)
         FUNC_SAVE
         INIT GHASH_MUL_AVX, PRECOMPUTE_AVX
         FUNC_RESTORE
         ret
-ENDPROC(aesni_gcm_init_avx_gen2)
+SYM_FUNC_END(aesni_gcm_init_avx_gen2)
 
 ###############################################################################
 #void   aesni_gcm_enc_update_avx_gen2(
@@ -1790,7 +1790,7 @@ ENDPROC(aesni_gcm_init_avx_gen2)
 #        const   u8 *in, /* Plaintext input */
 #        u64     plaintext_len) /* Length of data in Bytes for encryption. */
 ###############################################################################
-ENTRY(aesni_gcm_enc_update_avx_gen2)
+SYM_FUNC_START(aesni_gcm_enc_update_avx_gen2)
         FUNC_SAVE
         mov     keysize, %eax
         cmp     $32, %eax
@@ -1809,7 +1809,7 @@ key_256_enc_update:
         GCM_ENC_DEC INITIAL_BLOCKS_AVX, GHASH_8_ENCRYPT_8_PARALLEL_AVX, GHASH_LAST_8_AVX, GHASH_MUL_AVX, ENC, 13
         FUNC_RESTORE
         ret
-ENDPROC(aesni_gcm_enc_update_avx_gen2)
+SYM_FUNC_END(aesni_gcm_enc_update_avx_gen2)
 
 ###############################################################################
 #void   aesni_gcm_dec_update_avx_gen2(
@@ -1819,7 +1819,7 @@ ENDPROC(aesni_gcm_enc_update_avx_gen2)
 #        const   u8 *in, /* Ciphertext input */
 #        u64     plaintext_len) /* Length of data in Bytes for encryption. */
 ###############################################################################
-ENTRY(aesni_gcm_dec_update_avx_gen2)
+SYM_FUNC_START(aesni_gcm_dec_update_avx_gen2)
         FUNC_SAVE
         mov     keysize,%eax
         cmp     $32, %eax
@@ -1838,7 +1838,7 @@ key_256_dec_update:
         GCM_ENC_DEC INITIAL_BLOCKS_AVX, GHASH_8_ENCRYPT_8_PARALLEL_AVX, GHASH_LAST_8_AVX, GHASH_MUL_AVX, DEC, 13
         FUNC_RESTORE
         ret
-ENDPROC(aesni_gcm_dec_update_avx_gen2)
+SYM_FUNC_END(aesni_gcm_dec_update_avx_gen2)
 
 ###############################################################################
 #void   aesni_gcm_finalize_avx_gen2(
@@ -1848,7 +1848,7 @@ ENDPROC(aesni_gcm_dec_update_avx_gen2)
 #        u64     auth_tag_len)# /* Authenticated Tag Length in bytes.
 #				Valid values are 16 (most likely), 12 or 8. */
 ###############################################################################
-ENTRY(aesni_gcm_finalize_avx_gen2)
+SYM_FUNC_START(aesni_gcm_finalize_avx_gen2)
         FUNC_SAVE
         mov	keysize,%eax
         cmp     $32, %eax
@@ -1867,7 +1867,7 @@ key_256_finalize:
         GCM_COMPLETE GHASH_MUL_AVX, 13, arg3, arg4
         FUNC_RESTORE
         ret
-ENDPROC(aesni_gcm_finalize_avx_gen2)
+SYM_FUNC_END(aesni_gcm_finalize_avx_gen2)
 
 #endif /* CONFIG_AS_AVX */
 
@@ -2746,12 +2746,12 @@ _initial_blocks_done\@:
 #        const   u8 *aad, /* Additional Authentication Data (AAD)*/
 #        u64     aad_len) /* Length of AAD in bytes. With RFC4106 this is going to be 8 or 12 Bytes */
 #############################################################
-ENTRY(aesni_gcm_init_avx_gen4)
+SYM_FUNC_START(aesni_gcm_init_avx_gen4)
         FUNC_SAVE
         INIT GHASH_MUL_AVX2, PRECOMPUTE_AVX2
         FUNC_RESTORE
         ret
-ENDPROC(aesni_gcm_init_avx_gen4)
+SYM_FUNC_END(aesni_gcm_init_avx_gen4)
 
 ###############################################################################
 #void   aesni_gcm_enc_avx_gen4(
@@ -2761,7 +2761,7 @@ ENDPROC(aesni_gcm_init_avx_gen4)
 #        const   u8 *in, /* Plaintext input */
 #        u64     plaintext_len) /* Length of data in Bytes for encryption. */
 ###############################################################################
-ENTRY(aesni_gcm_enc_update_avx_gen4)
+SYM_FUNC_START(aesni_gcm_enc_update_avx_gen4)
         FUNC_SAVE
         mov     keysize,%eax
         cmp     $32, %eax
@@ -2780,7 +2780,7 @@ key_256_enc_update4:
         GCM_ENC_DEC INITIAL_BLOCKS_AVX2, GHASH_8_ENCRYPT_8_PARALLEL_AVX2, GHASH_LAST_8_AVX2, GHASH_MUL_AVX2, ENC, 13
         FUNC_RESTORE
 	ret
-ENDPROC(aesni_gcm_enc_update_avx_gen4)
+SYM_FUNC_END(aesni_gcm_enc_update_avx_gen4)
 
 ###############################################################################
 #void   aesni_gcm_dec_update_avx_gen4(
@@ -2790,7 +2790,7 @@ ENDPROC(aesni_gcm_enc_update_avx_gen4)
 #        const   u8 *in, /* Ciphertext input */
 #        u64     plaintext_len) /* Length of data in Bytes for encryption. */
 ###############################################################################
-ENTRY(aesni_gcm_dec_update_avx_gen4)
+SYM_FUNC_START(aesni_gcm_dec_update_avx_gen4)
         FUNC_SAVE
         mov     keysize,%eax
         cmp     $32, %eax
@@ -2809,7 +2809,7 @@ key_256_dec_update4:
         GCM_ENC_DEC INITIAL_BLOCKS_AVX2, GHASH_8_ENCRYPT_8_PARALLEL_AVX2, GHASH_LAST_8_AVX2, GHASH_MUL_AVX2, DEC, 13
         FUNC_RESTORE
         ret
-ENDPROC(aesni_gcm_dec_update_avx_gen4)
+SYM_FUNC_END(aesni_gcm_dec_update_avx_gen4)
 
 ###############################################################################
 #void   aesni_gcm_finalize_avx_gen4(
@@ -2819,7 +2819,7 @@ ENDPROC(aesni_gcm_dec_update_avx_gen4)
 #        u64     auth_tag_len)# /* Authenticated Tag Length in bytes.
 #                              Valid values are 16 (most likely), 12 or 8. */
 ###############################################################################
-ENTRY(aesni_gcm_finalize_avx_gen4)
+SYM_FUNC_START(aesni_gcm_finalize_avx_gen4)
         FUNC_SAVE
         mov	keysize,%eax
         cmp     $32, %eax
@@ -2838,6 +2838,6 @@ key_256_finalize4:
         GCM_COMPLETE GHASH_MUL_AVX2, 13, arg3, arg4
         FUNC_RESTORE
         ret
-ENDPROC(aesni_gcm_finalize_avx_gen4)
+SYM_FUNC_END(aesni_gcm_finalize_avx_gen4)
 
 #endif /* CONFIG_AS_AVX2 */
diff --git a/arch/x86/crypto/blake2s-core.S b/arch/x86/crypto/blake2s-core.S
index 8591938eee26..24910b766bdd 100644
--- a/arch/x86/crypto/blake2s-core.S
+++ b/arch/x86/crypto/blake2s-core.S
@@ -47,7 +47,7 @@ SIGMA2:
 
 .text
 #ifdef CONFIG_AS_SSSE3
-ENTRY(blake2s_compress_ssse3)
+SYM_FUNC_START(blake2s_compress_ssse3)
 	testq		%rdx,%rdx
 	je		.Lendofloop
 	movdqu		(%rdi),%xmm0
@@ -173,11 +173,11 @@ ENTRY(blake2s_compress_ssse3)
 	movdqu		%xmm14,0x20(%rdi)
 .Lendofloop:
 	ret
-ENDPROC(blake2s_compress_ssse3)
+SYM_FUNC_END(blake2s_compress_ssse3)
 #endif /* CONFIG_AS_SSSE3 */
 
 #ifdef CONFIG_AS_AVX512
-ENTRY(blake2s_compress_avx512)
+SYM_FUNC_START(blake2s_compress_avx512)
 	vmovdqu		(%rdi),%xmm0
 	vmovdqu		0x10(%rdi),%xmm1
 	vmovdqu		0x20(%rdi),%xmm4
@@ -254,5 +254,5 @@ ENTRY(blake2s_compress_avx512)
 	vmovdqu		%xmm4,0x20(%rdi)
 	vzeroupper
 	retq
-ENDPROC(blake2s_compress_avx512)
+SYM_FUNC_END(blake2s_compress_avx512)
 #endif /* CONFIG_AS_AVX512 */
diff --git a/arch/x86/crypto/blowfish-x86_64-asm_64.S b/arch/x86/crypto/blowfish-x86_64-asm_64.S
index 330db7a48af8..4222ac6d6584 100644
--- a/arch/x86/crypto/blowfish-x86_64-asm_64.S
+++ b/arch/x86/crypto/blowfish-x86_64-asm_64.S
@@ -103,7 +103,7 @@
 	bswapq 			RX0; \
 	xorq RX0, 		(RIO);
 
-ENTRY(__blowfish_enc_blk)
+SYM_FUNC_START(__blowfish_enc_blk)
 	/* input:
 	 *	%rdi: ctx
 	 *	%rsi: dst
@@ -139,9 +139,9 @@ ENTRY(__blowfish_enc_blk)
 .L__enc_xor:
 	xor_block();
 	ret;
-ENDPROC(__blowfish_enc_blk)
+SYM_FUNC_END(__blowfish_enc_blk)
 
-ENTRY(blowfish_dec_blk)
+SYM_FUNC_START(blowfish_dec_blk)
 	/* input:
 	 *	%rdi: ctx
 	 *	%rsi: dst
@@ -171,7 +171,7 @@ ENTRY(blowfish_dec_blk)
 	movq %r11, %r12;
 
 	ret;
-ENDPROC(blowfish_dec_blk)
+SYM_FUNC_END(blowfish_dec_blk)
 
 /**********************************************************************
   4-way blowfish, four blocks parallel
@@ -283,7 +283,7 @@ ENDPROC(blowfish_dec_blk)
 	bswapq 			RX3; \
 	xorq RX3,		24(RIO);
 
-ENTRY(__blowfish_enc_blk_4way)
+SYM_FUNC_START(__blowfish_enc_blk_4way)
 	/* input:
 	 *	%rdi: ctx
 	 *	%rsi: dst
@@ -330,9 +330,9 @@ ENTRY(__blowfish_enc_blk_4way)
 	popq %rbx;
 	popq %r12;
 	ret;
-ENDPROC(__blowfish_enc_blk_4way)
+SYM_FUNC_END(__blowfish_enc_blk_4way)
 
-ENTRY(blowfish_dec_blk_4way)
+SYM_FUNC_START(blowfish_dec_blk_4way)
 	/* input:
 	 *	%rdi: ctx
 	 *	%rsi: dst
@@ -365,4 +365,4 @@ ENTRY(blowfish_dec_blk_4way)
 	popq %r12;
 
 	ret;
-ENDPROC(blowfish_dec_blk_4way)
+SYM_FUNC_END(blowfish_dec_blk_4way)
diff --git a/arch/x86/crypto/camellia-aesni-avx-asm_64.S b/arch/x86/crypto/camellia-aesni-avx-asm_64.S
index a14af6eb09cb..d01ddd73de65 100644
--- a/arch/x86/crypto/camellia-aesni-avx-asm_64.S
+++ b/arch/x86/crypto/camellia-aesni-avx-asm_64.S
@@ -189,20 +189,20 @@
  * larger and would only be 0.5% faster (on sandy-bridge).
  */
 .align 8
-roundsm16_x0_x1_x2_x3_x4_x5_x6_x7_y0_y1_y2_y3_y4_y5_y6_y7_cd:
+SYM_FUNC_START_LOCAL(roundsm16_x0_x1_x2_x3_x4_x5_x6_x7_y0_y1_y2_y3_y4_y5_y6_y7_cd)
 	roundsm16(%xmm0, %xmm1, %xmm2, %xmm3, %xmm4, %xmm5, %xmm6, %xmm7,
 		  %xmm8, %xmm9, %xmm10, %xmm11, %xmm12, %xmm13, %xmm14, %xmm15,
 		  %rcx, (%r9));
 	ret;
-ENDPROC(roundsm16_x0_x1_x2_x3_x4_x5_x6_x7_y0_y1_y2_y3_y4_y5_y6_y7_cd)
+SYM_FUNC_END(roundsm16_x0_x1_x2_x3_x4_x5_x6_x7_y0_y1_y2_y3_y4_y5_y6_y7_cd)
 
 .align 8
-roundsm16_x4_x5_x6_x7_x0_x1_x2_x3_y4_y5_y6_y7_y0_y1_y2_y3_ab:
+SYM_FUNC_START_LOCAL(roundsm16_x4_x5_x6_x7_x0_x1_x2_x3_y4_y5_y6_y7_y0_y1_y2_y3_ab)
 	roundsm16(%xmm4, %xmm5, %xmm6, %xmm7, %xmm0, %xmm1, %xmm2, %xmm3,
 		  %xmm12, %xmm13, %xmm14, %xmm15, %xmm8, %xmm9, %xmm10, %xmm11,
 		  %rax, (%r9));
 	ret;
-ENDPROC(roundsm16_x4_x5_x6_x7_x0_x1_x2_x3_y4_y5_y6_y7_y0_y1_y2_y3_ab)
+SYM_FUNC_END(roundsm16_x4_x5_x6_x7_x0_x1_x2_x3_y4_y5_y6_y7_y0_y1_y2_y3_ab)
 
 /*
  * IN/OUT:
@@ -722,7 +722,7 @@ ENDPROC(roundsm16_x4_x5_x6_x7_x0_x1_x2_x3_y4_y5_y6_y7_y0_y1_y2_y3_ab)
 .text
 
 .align 8
-__camellia_enc_blk16:
+SYM_FUNC_START_LOCAL(__camellia_enc_blk16)
 	/* input:
 	 *	%rdi: ctx, CTX
 	 *	%rax: temporary storage, 256 bytes
@@ -806,10 +806,10 @@ __camellia_enc_blk16:
 		     %xmm15, %rax, %rcx, 24);
 
 	jmp .Lenc_done;
-ENDPROC(__camellia_enc_blk16)
+SYM_FUNC_END(__camellia_enc_blk16)
 
 .align 8
-__camellia_dec_blk16:
+SYM_FUNC_START_LOCAL(__camellia_dec_blk16)
 	/* input:
 	 *	%rdi: ctx, CTX
 	 *	%rax: temporary storage, 256 bytes
@@ -891,9 +891,9 @@ __camellia_dec_blk16:
 	      ((key_table + (24) * 8) + 4)(CTX));
 
 	jmp .Ldec_max24;
-ENDPROC(__camellia_dec_blk16)
+SYM_FUNC_END(__camellia_dec_blk16)
 
-ENTRY(camellia_ecb_enc_16way)
+SYM_FUNC_START(camellia_ecb_enc_16way)
 	/* input:
 	 *	%rdi: ctx, CTX
 	 *	%rsi: dst (16 blocks)
@@ -916,9 +916,9 @@ ENTRY(camellia_ecb_enc_16way)
 
 	FRAME_END
 	ret;
-ENDPROC(camellia_ecb_enc_16way)
+SYM_FUNC_END(camellia_ecb_enc_16way)
 
-ENTRY(camellia_ecb_dec_16way)
+SYM_FUNC_START(camellia_ecb_dec_16way)
 	/* input:
 	 *	%rdi: ctx, CTX
 	 *	%rsi: dst (16 blocks)
@@ -946,9 +946,9 @@ ENTRY(camellia_ecb_dec_16way)
 
 	FRAME_END
 	ret;
-ENDPROC(camellia_ecb_dec_16way)
+SYM_FUNC_END(camellia_ecb_dec_16way)
 
-ENTRY(camellia_cbc_dec_16way)
+SYM_FUNC_START(camellia_cbc_dec_16way)
 	/* input:
 	 *	%rdi: ctx, CTX
 	 *	%rsi: dst (16 blocks)
@@ -997,7 +997,7 @@ ENTRY(camellia_cbc_dec_16way)
 
 	FRAME_END
 	ret;
-ENDPROC(camellia_cbc_dec_16way)
+SYM_FUNC_END(camellia_cbc_dec_16way)
 
 #define inc_le128(x, minus_one, tmp) \
 	vpcmpeqq minus_one, x, tmp; \
@@ -1005,7 +1005,7 @@ ENDPROC(camellia_cbc_dec_16way)
 	vpslldq $8, tmp, tmp; \
 	vpsubq tmp, x, x;
 
-ENTRY(camellia_ctr_16way)
+SYM_FUNC_START(camellia_ctr_16way)
 	/* input:
 	 *	%rdi: ctx, CTX
 	 *	%rsi: dst (16 blocks)
@@ -1110,7 +1110,7 @@ ENTRY(camellia_ctr_16way)
 
 	FRAME_END
 	ret;
-ENDPROC(camellia_ctr_16way)
+SYM_FUNC_END(camellia_ctr_16way)
 
 #define gf128mul_x_ble(iv, mask, tmp) \
 	vpsrad $31, iv, tmp; \
@@ -1120,7 +1120,7 @@ ENDPROC(camellia_ctr_16way)
 	vpxor tmp, iv, iv;
 
 .align 8
-camellia_xts_crypt_16way:
+SYM_FUNC_START_LOCAL(camellia_xts_crypt_16way)
 	/* input:
 	 *	%rdi: ctx, CTX
 	 *	%rsi: dst (16 blocks)
@@ -1254,9 +1254,9 @@ camellia_xts_crypt_16way:
 
 	FRAME_END
 	ret;
-ENDPROC(camellia_xts_crypt_16way)
+SYM_FUNC_END(camellia_xts_crypt_16way)
 
-ENTRY(camellia_xts_enc_16way)
+SYM_FUNC_START(camellia_xts_enc_16way)
 	/* input:
 	 *	%rdi: ctx, CTX
 	 *	%rsi: dst (16 blocks)
@@ -1268,9 +1268,9 @@ ENTRY(camellia_xts_enc_16way)
 	leaq __camellia_enc_blk16, %r9;
 
 	jmp camellia_xts_crypt_16way;
-ENDPROC(camellia_xts_enc_16way)
+SYM_FUNC_END(camellia_xts_enc_16way)
 
-ENTRY(camellia_xts_dec_16way)
+SYM_FUNC_START(camellia_xts_dec_16way)
 	/* input:
 	 *	%rdi: ctx, CTX
 	 *	%rsi: dst (16 blocks)
@@ -1286,4 +1286,4 @@ ENTRY(camellia_xts_dec_16way)
 	leaq __camellia_dec_blk16, %r9;
 
 	jmp camellia_xts_crypt_16way;
-ENDPROC(camellia_xts_dec_16way)
+SYM_FUNC_END(camellia_xts_dec_16way)
diff --git a/arch/x86/crypto/camellia-aesni-avx2-asm_64.S b/arch/x86/crypto/camellia-aesni-avx2-asm_64.S
index 4be4c7c3ba27..563ef6e83cdd 100644
--- a/arch/x86/crypto/camellia-aesni-avx2-asm_64.S
+++ b/arch/x86/crypto/camellia-aesni-avx2-asm_64.S
@@ -223,20 +223,20 @@
  * larger and would only marginally faster.
  */
 .align 8
-roundsm32_x0_x1_x2_x3_x4_x5_x6_x7_y0_y1_y2_y3_y4_y5_y6_y7_cd:
+SYM_FUNC_START_LOCAL(roundsm32_x0_x1_x2_x3_x4_x5_x6_x7_y0_y1_y2_y3_y4_y5_y6_y7_cd)
 	roundsm32(%ymm0, %ymm1, %ymm2, %ymm3, %ymm4, %ymm5, %ymm6, %ymm7,
 		  %ymm8, %ymm9, %ymm10, %ymm11, %ymm12, %ymm13, %ymm14, %ymm15,
 		  %rcx, (%r9));
 	ret;
-ENDPROC(roundsm32_x0_x1_x2_x3_x4_x5_x6_x7_y0_y1_y2_y3_y4_y5_y6_y7_cd)
+SYM_FUNC_END(roundsm32_x0_x1_x2_x3_x4_x5_x6_x7_y0_y1_y2_y3_y4_y5_y6_y7_cd)
 
 .align 8
-roundsm32_x4_x5_x6_x7_x0_x1_x2_x3_y4_y5_y6_y7_y0_y1_y2_y3_ab:
+SYM_FUNC_START_LOCAL(roundsm32_x4_x5_x6_x7_x0_x1_x2_x3_y4_y5_y6_y7_y0_y1_y2_y3_ab)
 	roundsm32(%ymm4, %ymm5, %ymm6, %ymm7, %ymm0, %ymm1, %ymm2, %ymm3,
 		  %ymm12, %ymm13, %ymm14, %ymm15, %ymm8, %ymm9, %ymm10, %ymm11,
 		  %rax, (%r9));
 	ret;
-ENDPROC(roundsm32_x4_x5_x6_x7_x0_x1_x2_x3_y4_y5_y6_y7_y0_y1_y2_y3_ab)
+SYM_FUNC_END(roundsm32_x4_x5_x6_x7_x0_x1_x2_x3_y4_y5_y6_y7_y0_y1_y2_y3_ab)
 
 /*
  * IN/OUT:
@@ -760,7 +760,7 @@ ENDPROC(roundsm32_x4_x5_x6_x7_x0_x1_x2_x3_y4_y5_y6_y7_y0_y1_y2_y3_ab)
 .text
 
 .align 8
-__camellia_enc_blk32:
+SYM_FUNC_START_LOCAL(__camellia_enc_blk32)
 	/* input:
 	 *	%rdi: ctx, CTX
 	 *	%rax: temporary storage, 512 bytes
@@ -844,10 +844,10 @@ __camellia_enc_blk32:
 		     %ymm15, %rax, %rcx, 24);
 
 	jmp .Lenc_done;
-ENDPROC(__camellia_enc_blk32)
+SYM_FUNC_END(__camellia_enc_blk32)
 
 .align 8
-__camellia_dec_blk32:
+SYM_FUNC_START_LOCAL(__camellia_dec_blk32)
 	/* input:
 	 *	%rdi: ctx, CTX
 	 *	%rax: temporary storage, 512 bytes
@@ -929,9 +929,9 @@ __camellia_dec_blk32:
 	      ((key_table + (24) * 8) + 4)(CTX));
 
 	jmp .Ldec_max24;
-ENDPROC(__camellia_dec_blk32)
+SYM_FUNC_END(__camellia_dec_blk32)
 
-ENTRY(camellia_ecb_enc_32way)
+SYM_FUNC_START(camellia_ecb_enc_32way)
 	/* input:
 	 *	%rdi: ctx, CTX
 	 *	%rsi: dst (32 blocks)
@@ -958,9 +958,9 @@ ENTRY(camellia_ecb_enc_32way)
 
 	FRAME_END
 	ret;
-ENDPROC(camellia_ecb_enc_32way)
+SYM_FUNC_END(camellia_ecb_enc_32way)
 
-ENTRY(camellia_ecb_dec_32way)
+SYM_FUNC_START(camellia_ecb_dec_32way)
 	/* input:
 	 *	%rdi: ctx, CTX
 	 *	%rsi: dst (32 blocks)
@@ -992,9 +992,9 @@ ENTRY(camellia_ecb_dec_32way)
 
 	FRAME_END
 	ret;
-ENDPROC(camellia_ecb_dec_32way)
+SYM_FUNC_END(camellia_ecb_dec_32way)
 
-ENTRY(camellia_cbc_dec_32way)
+SYM_FUNC_START(camellia_cbc_dec_32way)
 	/* input:
 	 *	%rdi: ctx, CTX
 	 *	%rsi: dst (32 blocks)
@@ -1060,7 +1060,7 @@ ENTRY(camellia_cbc_dec_32way)
 
 	FRAME_END
 	ret;
-ENDPROC(camellia_cbc_dec_32way)
+SYM_FUNC_END(camellia_cbc_dec_32way)
 
 #define inc_le128(x, minus_one, tmp) \
 	vpcmpeqq minus_one, x, tmp; \
@@ -1076,7 +1076,7 @@ ENDPROC(camellia_cbc_dec_32way)
 	vpslldq $8, tmp1, tmp1; \
 	vpsubq tmp1, x, x;
 
-ENTRY(camellia_ctr_32way)
+SYM_FUNC_START(camellia_ctr_32way)
 	/* input:
 	 *	%rdi: ctx, CTX
 	 *	%rsi: dst (32 blocks)
@@ -1200,7 +1200,7 @@ ENTRY(camellia_ctr_32way)
 
 	FRAME_END
 	ret;
-ENDPROC(camellia_ctr_32way)
+SYM_FUNC_END(camellia_ctr_32way)
 
 #define gf128mul_x_ble(iv, mask, tmp) \
 	vpsrad $31, iv, tmp; \
@@ -1222,7 +1222,7 @@ ENDPROC(camellia_ctr_32way)
 	vpxor tmp1, iv, iv;
 
 .align 8
-camellia_xts_crypt_32way:
+SYM_FUNC_START_LOCAL(camellia_xts_crypt_32way)
 	/* input:
 	 *	%rdi: ctx, CTX
 	 *	%rsi: dst (32 blocks)
@@ -1367,9 +1367,9 @@ camellia_xts_crypt_32way:
 
 	FRAME_END
 	ret;
-ENDPROC(camellia_xts_crypt_32way)
+SYM_FUNC_END(camellia_xts_crypt_32way)
 
-ENTRY(camellia_xts_enc_32way)
+SYM_FUNC_START(camellia_xts_enc_32way)
 	/* input:
 	 *	%rdi: ctx, CTX
 	 *	%rsi: dst (32 blocks)
@@ -1382,9 +1382,9 @@ ENTRY(camellia_xts_enc_32way)
 	leaq __camellia_enc_blk32, %r9;
 
 	jmp camellia_xts_crypt_32way;
-ENDPROC(camellia_xts_enc_32way)
+SYM_FUNC_END(camellia_xts_enc_32way)
 
-ENTRY(camellia_xts_dec_32way)
+SYM_FUNC_START(camellia_xts_dec_32way)
 	/* input:
 	 *	%rdi: ctx, CTX
 	 *	%rsi: dst (32 blocks)
@@ -1400,4 +1400,4 @@ ENTRY(camellia_xts_dec_32way)
 	leaq __camellia_dec_blk32, %r9;
 
 	jmp camellia_xts_crypt_32way;
-ENDPROC(camellia_xts_dec_32way)
+SYM_FUNC_END(camellia_xts_dec_32way)
diff --git a/arch/x86/crypto/camellia-x86_64-asm_64.S b/arch/x86/crypto/camellia-x86_64-asm_64.S
index 23528bc18fc6..1372e6408850 100644
--- a/arch/x86/crypto/camellia-x86_64-asm_64.S
+++ b/arch/x86/crypto/camellia-x86_64-asm_64.S
@@ -175,7 +175,7 @@
 	bswapq				RAB0; \
 	movq RAB0,			4*2(RIO);
 
-ENTRY(__camellia_enc_blk)
+SYM_FUNC_START(__camellia_enc_blk)
 	/* input:
 	 *	%rdi: ctx, CTX
 	 *	%rsi: dst
@@ -220,9 +220,9 @@ ENTRY(__camellia_enc_blk)
 
 	movq RR12, %r12;
 	ret;
-ENDPROC(__camellia_enc_blk)
+SYM_FUNC_END(__camellia_enc_blk)
 
-ENTRY(camellia_dec_blk)
+SYM_FUNC_START(camellia_dec_blk)
 	/* input:
 	 *	%rdi: ctx, CTX
 	 *	%rsi: dst
@@ -258,7 +258,7 @@ ENTRY(camellia_dec_blk)
 
 	movq RR12, %r12;
 	ret;
-ENDPROC(camellia_dec_blk)
+SYM_FUNC_END(camellia_dec_blk)
 
 /**********************************************************************
   2-way camellia
@@ -409,7 +409,7 @@ ENDPROC(camellia_dec_blk)
 		bswapq				RAB1; \
 		movq RAB1,			12*2(RIO);
 
-ENTRY(__camellia_enc_blk_2way)
+SYM_FUNC_START(__camellia_enc_blk_2way)
 	/* input:
 	 *	%rdi: ctx, CTX
 	 *	%rsi: dst
@@ -456,9 +456,9 @@ ENTRY(__camellia_enc_blk_2way)
 	movq RR12, %r12;
 	popq %rbx;
 	ret;
-ENDPROC(__camellia_enc_blk_2way)
+SYM_FUNC_END(__camellia_enc_blk_2way)
 
-ENTRY(camellia_dec_blk_2way)
+SYM_FUNC_START(camellia_dec_blk_2way)
 	/* input:
 	 *	%rdi: ctx, CTX
 	 *	%rsi: dst
@@ -496,4 +496,4 @@ ENTRY(camellia_dec_blk_2way)
 	movq RR12, %r12;
 	movq RXOR, %rbx;
 	ret;
-ENDPROC(camellia_dec_blk_2way)
+SYM_FUNC_END(camellia_dec_blk_2way)
diff --git a/arch/x86/crypto/cast5-avx-x86_64-asm_64.S b/arch/x86/crypto/cast5-avx-x86_64-asm_64.S
index dc55c3332fcc..8a6181b08b59 100644
--- a/arch/x86/crypto/cast5-avx-x86_64-asm_64.S
+++ b/arch/x86/crypto/cast5-avx-x86_64-asm_64.S
@@ -209,7 +209,7 @@
 .text
 
 .align 16
-__cast5_enc_blk16:
+SYM_FUNC_START_LOCAL(__cast5_enc_blk16)
 	/* input:
 	 *	%rdi: ctx
 	 *	RL1: blocks 1 and 2
@@ -280,10 +280,10 @@ __cast5_enc_blk16:
 	outunpack_blocks(RR4, RL4, RTMP, RX, RKM);
 
 	ret;
-ENDPROC(__cast5_enc_blk16)
+SYM_FUNC_END(__cast5_enc_blk16)
 
 .align 16
-__cast5_dec_blk16:
+SYM_FUNC_START_LOCAL(__cast5_dec_blk16)
 	/* input:
 	 *	%rdi: ctx
 	 *	RL1: encrypted blocks 1 and 2
@@ -357,9 +357,9 @@ __cast5_dec_blk16:
 .L__skip_dec:
 	vpsrldq $4, RKR, RKR;
 	jmp .L__dec_tail;
-ENDPROC(__cast5_dec_blk16)
+SYM_FUNC_END(__cast5_dec_blk16)
 
-ENTRY(cast5_ecb_enc_16way)
+SYM_FUNC_START(cast5_ecb_enc_16way)
 	/* input:
 	 *	%rdi: ctx
 	 *	%rsi: dst
@@ -394,9 +394,9 @@ ENTRY(cast5_ecb_enc_16way)
 	popq %r15;
 	FRAME_END
 	ret;
-ENDPROC(cast5_ecb_enc_16way)
+SYM_FUNC_END(cast5_ecb_enc_16way)
 
-ENTRY(cast5_ecb_dec_16way)
+SYM_FUNC_START(cast5_ecb_dec_16way)
 	/* input:
 	 *	%rdi: ctx
 	 *	%rsi: dst
@@ -432,9 +432,9 @@ ENTRY(cast5_ecb_dec_16way)
 	popq %r15;
 	FRAME_END
 	ret;
-ENDPROC(cast5_ecb_dec_16way)
+SYM_FUNC_END(cast5_ecb_dec_16way)
 
-ENTRY(cast5_cbc_dec_16way)
+SYM_FUNC_START(cast5_cbc_dec_16way)
 	/* input:
 	 *	%rdi: ctx
 	 *	%rsi: dst
@@ -484,9 +484,9 @@ ENTRY(cast5_cbc_dec_16way)
 	popq %r12;
 	FRAME_END
 	ret;
-ENDPROC(cast5_cbc_dec_16way)
+SYM_FUNC_END(cast5_cbc_dec_16way)
 
-ENTRY(cast5_ctr_16way)
+SYM_FUNC_START(cast5_ctr_16way)
 	/* input:
 	 *	%rdi: ctx
 	 *	%rsi: dst
@@ -560,4 +560,4 @@ ENTRY(cast5_ctr_16way)
 	popq %r12;
 	FRAME_END
 	ret;
-ENDPROC(cast5_ctr_16way)
+SYM_FUNC_END(cast5_ctr_16way)
diff --git a/arch/x86/crypto/cast6-avx-x86_64-asm_64.S b/arch/x86/crypto/cast6-avx-x86_64-asm_64.S
index 4f0a7cdb94d9..932a3ce32a88 100644
--- a/arch/x86/crypto/cast6-avx-x86_64-asm_64.S
+++ b/arch/x86/crypto/cast6-avx-x86_64-asm_64.S
@@ -247,7 +247,7 @@
 .text
 
 .align 8
-__cast6_enc_blk8:
+SYM_FUNC_START_LOCAL(__cast6_enc_blk8)
 	/* input:
 	 *	%rdi: ctx
 	 *	RA1, RB1, RC1, RD1, RA2, RB2, RC2, RD2: blocks
@@ -292,10 +292,10 @@ __cast6_enc_blk8:
 	outunpack_blocks(RA2, RB2, RC2, RD2, RTMP, RX, RKRF, RKM);
 
 	ret;
-ENDPROC(__cast6_enc_blk8)
+SYM_FUNC_END(__cast6_enc_blk8)
 
 .align 8
-__cast6_dec_blk8:
+SYM_FUNC_START_LOCAL(__cast6_dec_blk8)
 	/* input:
 	 *	%rdi: ctx
 	 *	RA1, RB1, RC1, RD1, RA2, RB2, RC2, RD2: encrypted blocks
@@ -339,9 +339,9 @@ __cast6_dec_blk8:
 	outunpack_blocks(RA2, RB2, RC2, RD2, RTMP, RX, RKRF, RKM);
 
 	ret;
-ENDPROC(__cast6_dec_blk8)
+SYM_FUNC_END(__cast6_dec_blk8)
 
-ENTRY(cast6_ecb_enc_8way)
+SYM_FUNC_START(cast6_ecb_enc_8way)
 	/* input:
 	 *	%rdi: ctx
 	 *	%rsi: dst
@@ -362,9 +362,9 @@ ENTRY(cast6_ecb_enc_8way)
 	popq %r15;
 	FRAME_END
 	ret;
-ENDPROC(cast6_ecb_enc_8way)
+SYM_FUNC_END(cast6_ecb_enc_8way)
 
-ENTRY(cast6_ecb_dec_8way)
+SYM_FUNC_START(cast6_ecb_dec_8way)
 	/* input:
 	 *	%rdi: ctx
 	 *	%rsi: dst
@@ -385,9 +385,9 @@ ENTRY(cast6_ecb_dec_8way)
 	popq %r15;
 	FRAME_END
 	ret;
-ENDPROC(cast6_ecb_dec_8way)
+SYM_FUNC_END(cast6_ecb_dec_8way)
 
-ENTRY(cast6_cbc_dec_8way)
+SYM_FUNC_START(cast6_cbc_dec_8way)
 	/* input:
 	 *	%rdi: ctx
 	 *	%rsi: dst
@@ -411,9 +411,9 @@ ENTRY(cast6_cbc_dec_8way)
 	popq %r12;
 	FRAME_END
 	ret;
-ENDPROC(cast6_cbc_dec_8way)
+SYM_FUNC_END(cast6_cbc_dec_8way)
 
-ENTRY(cast6_ctr_8way)
+SYM_FUNC_START(cast6_ctr_8way)
 	/* input:
 	 *	%rdi: ctx, CTX
 	 *	%rsi: dst
@@ -439,9 +439,9 @@ ENTRY(cast6_ctr_8way)
 	popq %r12;
 	FRAME_END
 	ret;
-ENDPROC(cast6_ctr_8way)
+SYM_FUNC_END(cast6_ctr_8way)
 
-ENTRY(cast6_xts_enc_8way)
+SYM_FUNC_START(cast6_xts_enc_8way)
 	/* input:
 	 *	%rdi: ctx, CTX
 	 *	%rsi: dst
@@ -466,9 +466,9 @@ ENTRY(cast6_xts_enc_8way)
 	popq %r15;
 	FRAME_END
 	ret;
-ENDPROC(cast6_xts_enc_8way)
+SYM_FUNC_END(cast6_xts_enc_8way)
 
-ENTRY(cast6_xts_dec_8way)
+SYM_FUNC_START(cast6_xts_dec_8way)
 	/* input:
 	 *	%rdi: ctx, CTX
 	 *	%rsi: dst
@@ -493,4 +493,4 @@ ENTRY(cast6_xts_dec_8way)
 	popq %r15;
 	FRAME_END
 	ret;
-ENDPROC(cast6_xts_dec_8way)
+SYM_FUNC_END(cast6_xts_dec_8way)
diff --git a/arch/x86/crypto/chacha-avx2-x86_64.S b/arch/x86/crypto/chacha-avx2-x86_64.S
index 831e4434fc20..ee9a40ab4109 100644
--- a/arch/x86/crypto/chacha-avx2-x86_64.S
+++ b/arch/x86/crypto/chacha-avx2-x86_64.S
@@ -34,7 +34,7 @@ CTR4BL:	.octa 0x00000000000000000000000000000002
 
 .text
 
-ENTRY(chacha_2block_xor_avx2)
+SYM_FUNC_START(chacha_2block_xor_avx2)
 	# %rdi: Input state matrix, s
 	# %rsi: up to 2 data blocks output, o
 	# %rdx: up to 2 data blocks input, i
@@ -224,9 +224,9 @@ ENTRY(chacha_2block_xor_avx2)
 	lea		-8(%r10),%rsp
 	jmp		.Ldone2
 
-ENDPROC(chacha_2block_xor_avx2)
+SYM_FUNC_END(chacha_2block_xor_avx2)
 
-ENTRY(chacha_4block_xor_avx2)
+SYM_FUNC_START(chacha_4block_xor_avx2)
 	# %rdi: Input state matrix, s
 	# %rsi: up to 4 data blocks output, o
 	# %rdx: up to 4 data blocks input, i
@@ -529,9 +529,9 @@ ENTRY(chacha_4block_xor_avx2)
 	lea		-8(%r10),%rsp
 	jmp		.Ldone4
 
-ENDPROC(chacha_4block_xor_avx2)
+SYM_FUNC_END(chacha_4block_xor_avx2)
 
-ENTRY(chacha_8block_xor_avx2)
+SYM_FUNC_START(chacha_8block_xor_avx2)
 	# %rdi: Input state matrix, s
 	# %rsi: up to 8 data blocks output, o
 	# %rdx: up to 8 data blocks input, i
@@ -1018,4 +1018,4 @@ ENTRY(chacha_8block_xor_avx2)
 
 	jmp		.Ldone8
 
-ENDPROC(chacha_8block_xor_avx2)
+SYM_FUNC_END(chacha_8block_xor_avx2)
diff --git a/arch/x86/crypto/chacha-avx512vl-x86_64.S b/arch/x86/crypto/chacha-avx512vl-x86_64.S
index 848f9c75fd4f..bb193fde123a 100644
--- a/arch/x86/crypto/chacha-avx512vl-x86_64.S
+++ b/arch/x86/crypto/chacha-avx512vl-x86_64.S
@@ -24,7 +24,7 @@ CTR8BL:	.octa 0x00000003000000020000000100000000
 
 .text
 
-ENTRY(chacha_2block_xor_avx512vl)
+SYM_FUNC_START(chacha_2block_xor_avx512vl)
 	# %rdi: Input state matrix, s
 	# %rsi: up to 2 data blocks output, o
 	# %rdx: up to 2 data blocks input, i
@@ -187,9 +187,9 @@ ENTRY(chacha_2block_xor_avx512vl)
 
 	jmp		.Ldone2
 
-ENDPROC(chacha_2block_xor_avx512vl)
+SYM_FUNC_END(chacha_2block_xor_avx512vl)
 
-ENTRY(chacha_4block_xor_avx512vl)
+SYM_FUNC_START(chacha_4block_xor_avx512vl)
 	# %rdi: Input state matrix, s
 	# %rsi: up to 4 data blocks output, o
 	# %rdx: up to 4 data blocks input, i
@@ -453,9 +453,9 @@ ENTRY(chacha_4block_xor_avx512vl)
 
 	jmp		.Ldone4
 
-ENDPROC(chacha_4block_xor_avx512vl)
+SYM_FUNC_END(chacha_4block_xor_avx512vl)
 
-ENTRY(chacha_8block_xor_avx512vl)
+SYM_FUNC_START(chacha_8block_xor_avx512vl)
 	# %rdi: Input state matrix, s
 	# %rsi: up to 8 data blocks output, o
 	# %rdx: up to 8 data blocks input, i
@@ -833,4 +833,4 @@ ENTRY(chacha_8block_xor_avx512vl)
 
 	jmp		.Ldone8
 
-ENDPROC(chacha_8block_xor_avx512vl)
+SYM_FUNC_END(chacha_8block_xor_avx512vl)
diff --git a/arch/x86/crypto/chacha-ssse3-x86_64.S b/arch/x86/crypto/chacha-ssse3-x86_64.S
index 2d86c7d6dc88..a38ab2512a6f 100644
--- a/arch/x86/crypto/chacha-ssse3-x86_64.S
+++ b/arch/x86/crypto/chacha-ssse3-x86_64.S
@@ -33,7 +33,7 @@ CTRINC:	.octa 0x00000003000000020000000100000000
  *
  * Clobbers: %r8d, %xmm4-%xmm7
  */
-chacha_permute:
+SYM_FUNC_START_LOCAL(chacha_permute)
 
 	movdqa		ROT8(%rip),%xmm4
 	movdqa		ROT16(%rip),%xmm5
@@ -109,9 +109,9 @@ chacha_permute:
 	jnz		.Ldoubleround
 
 	ret
-ENDPROC(chacha_permute)
+SYM_FUNC_END(chacha_permute)
 
-ENTRY(chacha_block_xor_ssse3)
+SYM_FUNC_START(chacha_block_xor_ssse3)
 	# %rdi: Input state matrix, s
 	# %rsi: up to 1 data block output, o
 	# %rdx: up to 1 data block input, i
@@ -197,9 +197,9 @@ ENTRY(chacha_block_xor_ssse3)
 	lea		-8(%r10),%rsp
 	jmp		.Ldone
 
-ENDPROC(chacha_block_xor_ssse3)
+SYM_FUNC_END(chacha_block_xor_ssse3)
 
-ENTRY(hchacha_block_ssse3)
+SYM_FUNC_START(hchacha_block_ssse3)
 	# %rdi: Input state matrix, s
 	# %rsi: output (8 32-bit words)
 	# %edx: nrounds
@@ -218,9 +218,9 @@ ENTRY(hchacha_block_ssse3)
 
 	FRAME_END
 	ret
-ENDPROC(hchacha_block_ssse3)
+SYM_FUNC_END(hchacha_block_ssse3)
 
-ENTRY(chacha_4block_xor_ssse3)
+SYM_FUNC_START(chacha_4block_xor_ssse3)
 	# %rdi: Input state matrix, s
 	# %rsi: up to 4 data blocks output, o
 	# %rdx: up to 4 data blocks input, i
@@ -788,4 +788,4 @@ ENTRY(chacha_4block_xor_ssse3)
 
 	jmp		.Ldone4
 
-ENDPROC(chacha_4block_xor_ssse3)
+SYM_FUNC_END(chacha_4block_xor_ssse3)
diff --git a/arch/x86/crypto/crc32-pclmul_asm.S b/arch/x86/crypto/crc32-pclmul_asm.S
index 1c099dc08cc3..9fd28ff65bc2 100644
--- a/arch/x86/crypto/crc32-pclmul_asm.S
+++ b/arch/x86/crypto/crc32-pclmul_asm.S
@@ -103,7 +103,7 @@
  *	                     size_t len, uint crc32)
  */
 
-ENTRY(crc32_pclmul_le_16) /* buffer and buffer size are 16 bytes aligned */
+SYM_FUNC_START(crc32_pclmul_le_16) /* buffer and buffer size are 16 bytes aligned */
 	movdqa  (BUF), %xmm1
 	movdqa  0x10(BUF), %xmm2
 	movdqa  0x20(BUF), %xmm3
@@ -238,4 +238,4 @@ fold_64:
 	PEXTRD  0x01, %xmm1, %eax
 
 	ret
-ENDPROC(crc32_pclmul_le_16)
+SYM_FUNC_END(crc32_pclmul_le_16)
diff --git a/arch/x86/crypto/crc32c-pcl-intel-asm_64.S b/arch/x86/crypto/crc32c-pcl-intel-asm_64.S
index d9b734d0c8cc..0e6690e3618c 100644
--- a/arch/x86/crypto/crc32c-pcl-intel-asm_64.S
+++ b/arch/x86/crypto/crc32c-pcl-intel-asm_64.S
@@ -74,7 +74,7 @@
 # unsigned int crc_pcl(u8 *buffer, int len, unsigned int crc_init);
 
 .text
-ENTRY(crc_pcl)
+SYM_FUNC_START(crc_pcl)
 #define    bufp		%rdi
 #define    bufp_dw	%edi
 #define    bufp_w	%di
@@ -311,7 +311,7 @@ do_return:
 	popq    %rdi
 	popq    %rbx
         ret
-ENDPROC(crc_pcl)
+SYM_FUNC_END(crc_pcl)
 
 .section	.rodata, "a", @progbits
         ################################################################
diff --git a/arch/x86/crypto/crct10dif-pcl-asm_64.S b/arch/x86/crypto/crct10dif-pcl-asm_64.S
index 3d873e67749d..b2533d63030e 100644
--- a/arch/x86/crypto/crct10dif-pcl-asm_64.S
+++ b/arch/x86/crypto/crct10dif-pcl-asm_64.S
@@ -95,7 +95,7 @@
 # Assumes len >= 16.
 #
 .align 16
-ENTRY(crc_t10dif_pcl)
+SYM_FUNC_START(crc_t10dif_pcl)
 
 	movdqa	.Lbswap_mask(%rip), BSWAP_MASK
 
@@ -280,7 +280,7 @@ ENTRY(crc_t10dif_pcl)
 	jge	.Lfold_16_bytes_loop		# 32 <= len <= 255
 	add	$16, len
 	jmp	.Lhandle_partial_segment	# 17 <= len <= 31
-ENDPROC(crc_t10dif_pcl)
+SYM_FUNC_END(crc_t10dif_pcl)
 
 .section	.rodata, "a", @progbits
 .align 16
diff --git a/arch/x86/crypto/des3_ede-asm_64.S b/arch/x86/crypto/des3_ede-asm_64.S
index 7fca43099a5f..fac0fdc3f25d 100644
--- a/arch/x86/crypto/des3_ede-asm_64.S
+++ b/arch/x86/crypto/des3_ede-asm_64.S
@@ -162,7 +162,7 @@
 	movl   left##d,   (io); \
 	movl   right##d, 4(io);
 
-ENTRY(des3_ede_x86_64_crypt_blk)
+SYM_FUNC_START(des3_ede_x86_64_crypt_blk)
 	/* input:
 	 *	%rdi: round keys, CTX
 	 *	%rsi: dst
@@ -244,7 +244,7 @@ ENTRY(des3_ede_x86_64_crypt_blk)
 	popq %rbx;
 
 	ret;
-ENDPROC(des3_ede_x86_64_crypt_blk)
+SYM_FUNC_END(des3_ede_x86_64_crypt_blk)
 
 /***********************************************************************
  * 3-way 3DES
@@ -418,7 +418,7 @@ ENDPROC(des3_ede_x86_64_crypt_blk)
 #define __movq(src, dst) \
 	movq src, dst;
 
-ENTRY(des3_ede_x86_64_crypt_blk_3way)
+SYM_FUNC_START(des3_ede_x86_64_crypt_blk_3way)
 	/* input:
 	 *	%rdi: ctx, round keys
 	 *	%rsi: dst (3 blocks)
@@ -529,7 +529,7 @@ ENTRY(des3_ede_x86_64_crypt_blk_3way)
 	popq %rbx;
 
 	ret;
-ENDPROC(des3_ede_x86_64_crypt_blk_3way)
+SYM_FUNC_END(des3_ede_x86_64_crypt_blk_3way)
 
 .section	.rodata, "a", @progbits
 .align 16
diff --git a/arch/x86/crypto/ghash-clmulni-intel_asm.S b/arch/x86/crypto/ghash-clmulni-intel_asm.S
index 5d53effe8abe..bb9735fbb865 100644
--- a/arch/x86/crypto/ghash-clmulni-intel_asm.S
+++ b/arch/x86/crypto/ghash-clmulni-intel_asm.S
@@ -44,7 +44,7 @@
  *	T2
  *	T3
  */
-__clmul_gf128mul_ble:
+SYM_FUNC_START_LOCAL(__clmul_gf128mul_ble)
 	movaps DATA, T1
 	pshufd $0b01001110, DATA, T2
 	pshufd $0b01001110, SHASH, T3
@@ -87,10 +87,10 @@ __clmul_gf128mul_ble:
 	pxor T2, T1
 	pxor T1, DATA
 	ret
-ENDPROC(__clmul_gf128mul_ble)
+SYM_FUNC_END(__clmul_gf128mul_ble)
 
 /* void clmul_ghash_mul(char *dst, const u128 *shash) */
-ENTRY(clmul_ghash_mul)
+SYM_FUNC_START(clmul_ghash_mul)
 	FRAME_BEGIN
 	movups (%rdi), DATA
 	movups (%rsi), SHASH
@@ -101,13 +101,13 @@ ENTRY(clmul_ghash_mul)
 	movups DATA, (%rdi)
 	FRAME_END
 	ret
-ENDPROC(clmul_ghash_mul)
+SYM_FUNC_END(clmul_ghash_mul)
 
 /*
  * void clmul_ghash_update(char *dst, const char *src, unsigned int srclen,
  *			   const u128 *shash);
  */
-ENTRY(clmul_ghash_update)
+SYM_FUNC_START(clmul_ghash_update)
 	FRAME_BEGIN
 	cmp $16, %rdx
 	jb .Lupdate_just_ret	# check length
@@ -130,4 +130,4 @@ ENTRY(clmul_ghash_update)
 .Lupdate_just_ret:
 	FRAME_END
 	ret
-ENDPROC(clmul_ghash_update)
+SYM_FUNC_END(clmul_ghash_update)
diff --git a/arch/x86/crypto/nh-avx2-x86_64.S b/arch/x86/crypto/nh-avx2-x86_64.S
index f7946ea1b704..b22c7b936272 100644
--- a/arch/x86/crypto/nh-avx2-x86_64.S
+++ b/arch/x86/crypto/nh-avx2-x86_64.S
@@ -69,7 +69,7 @@
  *
  * It's guaranteed that message_len % 16 == 0.
  */
-ENTRY(nh_avx2)
+SYM_FUNC_START(nh_avx2)
 
 	vmovdqu		0x00(KEY), K0
 	vmovdqu		0x10(KEY), K1
@@ -154,4 +154,4 @@ ENTRY(nh_avx2)
 	vpaddq		T4, T0, T0
 	vmovdqu		T0, (HASH)
 	ret
-ENDPROC(nh_avx2)
+SYM_FUNC_END(nh_avx2)
diff --git a/arch/x86/crypto/nh-sse2-x86_64.S b/arch/x86/crypto/nh-sse2-x86_64.S
index 51f52d4ab4bb..d7ae22dd6683 100644
--- a/arch/x86/crypto/nh-sse2-x86_64.S
+++ b/arch/x86/crypto/nh-sse2-x86_64.S
@@ -71,7 +71,7 @@
  *
  * It's guaranteed that message_len % 16 == 0.
  */
-ENTRY(nh_sse2)
+SYM_FUNC_START(nh_sse2)
 
 	movdqu		0x00(KEY), K0
 	movdqu		0x10(KEY), K1
@@ -120,4 +120,4 @@ ENTRY(nh_sse2)
 	movdqu		T0, 0x00(HASH)
 	movdqu		T1, 0x10(HASH)
 	ret
-ENDPROC(nh_sse2)
+SYM_FUNC_END(nh_sse2)
diff --git a/arch/x86/crypto/poly1305-avx2-x86_64.S b/arch/x86/crypto/poly1305-avx2-x86_64.S
index 8b341bc29d41..d6063feda9da 100644
--- a/arch/x86/crypto/poly1305-avx2-x86_64.S
+++ b/arch/x86/crypto/poly1305-avx2-x86_64.S
@@ -79,7 +79,7 @@ ORMASK:	.octa 0x00000000010000000000000001000000
 #define d3 %r12
 #define d4 %r13
 
-ENTRY(poly1305_4block_avx2)
+SYM_FUNC_START(poly1305_4block_avx2)
 	# %rdi: Accumulator h[5]
 	# %rsi: 64 byte input block m
 	# %rdx: Poly1305 key r[5]
@@ -387,4 +387,4 @@ ENTRY(poly1305_4block_avx2)
 	pop		%r12
 	pop		%rbx
 	ret
-ENDPROC(poly1305_4block_avx2)
+SYM_FUNC_END(poly1305_4block_avx2)
diff --git a/arch/x86/crypto/poly1305-sse2-x86_64.S b/arch/x86/crypto/poly1305-sse2-x86_64.S
index 5578f846e622..d8ea29b96640 100644
--- a/arch/x86/crypto/poly1305-sse2-x86_64.S
+++ b/arch/x86/crypto/poly1305-sse2-x86_64.S
@@ -46,7 +46,7 @@ ORMASK:	.octa 0x00000000010000000000000001000000
 #define d3 %r11
 #define d4 %r12
 
-ENTRY(poly1305_block_sse2)
+SYM_FUNC_START(poly1305_block_sse2)
 	# %rdi: Accumulator h[5]
 	# %rsi: 16 byte input block m
 	# %rdx: Poly1305 key r[5]
@@ -276,7 +276,7 @@ ENTRY(poly1305_block_sse2)
 	pop		%r12
 	pop		%rbx
 	ret
-ENDPROC(poly1305_block_sse2)
+SYM_FUNC_END(poly1305_block_sse2)
 
 
 #define u0 0x00(%r8)
@@ -301,7 +301,7 @@ ENDPROC(poly1305_block_sse2)
 #undef d0
 #define d0 %r13
 
-ENTRY(poly1305_2block_sse2)
+SYM_FUNC_START(poly1305_2block_sse2)
 	# %rdi: Accumulator h[5]
 	# %rsi: 16 byte input block m
 	# %rdx: Poly1305 key r[5]
@@ -587,4 +587,4 @@ ENTRY(poly1305_2block_sse2)
 	pop		%r12
 	pop		%rbx
 	ret
-ENDPROC(poly1305_2block_sse2)
+SYM_FUNC_END(poly1305_2block_sse2)
diff --git a/arch/x86/crypto/serpent-avx-x86_64-asm_64.S b/arch/x86/crypto/serpent-avx-x86_64-asm_64.S
index ddc51dbba3af..ba9e4c1e7f5c 100644
--- a/arch/x86/crypto/serpent-avx-x86_64-asm_64.S
+++ b/arch/x86/crypto/serpent-avx-x86_64-asm_64.S
@@ -555,7 +555,7 @@
 	transpose_4x4(x0, x1, x2, x3, t0, t1, t2)
 
 .align 8
-__serpent_enc_blk8_avx:
+SYM_FUNC_START_LOCAL(__serpent_enc_blk8_avx)
 	/* input:
 	 *	%rdi: ctx, CTX
 	 *	RA1, RB1, RC1, RD1, RA2, RB2, RC2, RD2: blocks
@@ -606,10 +606,10 @@ __serpent_enc_blk8_avx:
 	write_blocks(RA2, RB2, RC2, RD2, RK0, RK1, RK2);
 
 	ret;
-ENDPROC(__serpent_enc_blk8_avx)
+SYM_FUNC_END(__serpent_enc_blk8_avx)
 
 .align 8
-__serpent_dec_blk8_avx:
+SYM_FUNC_START_LOCAL(__serpent_dec_blk8_avx)
 	/* input:
 	 *	%rdi: ctx, CTX
 	 *	RA1, RB1, RC1, RD1, RA2, RB2, RC2, RD2: encrypted blocks
@@ -660,9 +660,9 @@ __serpent_dec_blk8_avx:
 	write_blocks(RC2, RD2, RB2, RE2, RK0, RK1, RK2);
 
 	ret;
-ENDPROC(__serpent_dec_blk8_avx)
+SYM_FUNC_END(__serpent_dec_blk8_avx)
 
-ENTRY(serpent_ecb_enc_8way_avx)
+SYM_FUNC_START(serpent_ecb_enc_8way_avx)
 	/* input:
 	 *	%rdi: ctx, CTX
 	 *	%rsi: dst
@@ -678,9 +678,9 @@ ENTRY(serpent_ecb_enc_8way_avx)
 
 	FRAME_END
 	ret;
-ENDPROC(serpent_ecb_enc_8way_avx)
+SYM_FUNC_END(serpent_ecb_enc_8way_avx)
 
-ENTRY(serpent_ecb_dec_8way_avx)
+SYM_FUNC_START(serpent_ecb_dec_8way_avx)
 	/* input:
 	 *	%rdi: ctx, CTX
 	 *	%rsi: dst
@@ -696,9 +696,9 @@ ENTRY(serpent_ecb_dec_8way_avx)
 
 	FRAME_END
 	ret;
-ENDPROC(serpent_ecb_dec_8way_avx)
+SYM_FUNC_END(serpent_ecb_dec_8way_avx)
 
-ENTRY(serpent_cbc_dec_8way_avx)
+SYM_FUNC_START(serpent_cbc_dec_8way_avx)
 	/* input:
 	 *	%rdi: ctx, CTX
 	 *	%rsi: dst
@@ -714,9 +714,9 @@ ENTRY(serpent_cbc_dec_8way_avx)
 
 	FRAME_END
 	ret;
-ENDPROC(serpent_cbc_dec_8way_avx)
+SYM_FUNC_END(serpent_cbc_dec_8way_avx)
 
-ENTRY(serpent_ctr_8way_avx)
+SYM_FUNC_START(serpent_ctr_8way_avx)
 	/* input:
 	 *	%rdi: ctx, CTX
 	 *	%rsi: dst
@@ -734,9 +734,9 @@ ENTRY(serpent_ctr_8way_avx)
 
 	FRAME_END
 	ret;
-ENDPROC(serpent_ctr_8way_avx)
+SYM_FUNC_END(serpent_ctr_8way_avx)
 
-ENTRY(serpent_xts_enc_8way_avx)
+SYM_FUNC_START(serpent_xts_enc_8way_avx)
 	/* input:
 	 *	%rdi: ctx, CTX
 	 *	%rsi: dst
@@ -756,9 +756,9 @@ ENTRY(serpent_xts_enc_8way_avx)
 
 	FRAME_END
 	ret;
-ENDPROC(serpent_xts_enc_8way_avx)
+SYM_FUNC_END(serpent_xts_enc_8way_avx)
 
-ENTRY(serpent_xts_dec_8way_avx)
+SYM_FUNC_START(serpent_xts_dec_8way_avx)
 	/* input:
 	 *	%rdi: ctx, CTX
 	 *	%rsi: dst
@@ -778,4 +778,4 @@ ENTRY(serpent_xts_dec_8way_avx)
 
 	FRAME_END
 	ret;
-ENDPROC(serpent_xts_dec_8way_avx)
+SYM_FUNC_END(serpent_xts_dec_8way_avx)
diff --git a/arch/x86/crypto/serpent-avx2-asm_64.S b/arch/x86/crypto/serpent-avx2-asm_64.S
index 37bc1d48106c..c9648aeae705 100644
--- a/arch/x86/crypto/serpent-avx2-asm_64.S
+++ b/arch/x86/crypto/serpent-avx2-asm_64.S
@@ -561,7 +561,7 @@
 	transpose_4x4(x0, x1, x2, x3, t0, t1, t2)
 
 .align 8
-__serpent_enc_blk16:
+SYM_FUNC_START_LOCAL(__serpent_enc_blk16)
 	/* input:
 	 *	%rdi: ctx, CTX
 	 *	RA1, RB1, RC1, RD1, RA2, RB2, RC2, RD2: plaintext
@@ -612,10 +612,10 @@ __serpent_enc_blk16:
 	write_blocks(RA2, RB2, RC2, RD2, RK0, RK1, RK2);
 
 	ret;
-ENDPROC(__serpent_enc_blk16)
+SYM_FUNC_END(__serpent_enc_blk16)
 
 .align 8
-__serpent_dec_blk16:
+SYM_FUNC_START_LOCAL(__serpent_dec_blk16)
 	/* input:
 	 *	%rdi: ctx, CTX
 	 *	RA1, RB1, RC1, RD1, RA2, RB2, RC2, RD2: ciphertext
@@ -666,9 +666,9 @@ __serpent_dec_blk16:
 	write_blocks(RC2, RD2, RB2, RE2, RK0, RK1, RK2);
 
 	ret;
-ENDPROC(__serpent_dec_blk16)
+SYM_FUNC_END(__serpent_dec_blk16)
 
-ENTRY(serpent_ecb_enc_16way)
+SYM_FUNC_START(serpent_ecb_enc_16way)
 	/* input:
 	 *	%rdi: ctx, CTX
 	 *	%rsi: dst
@@ -688,9 +688,9 @@ ENTRY(serpent_ecb_enc_16way)
 
 	FRAME_END
 	ret;
-ENDPROC(serpent_ecb_enc_16way)
+SYM_FUNC_END(serpent_ecb_enc_16way)
 
-ENTRY(serpent_ecb_dec_16way)
+SYM_FUNC_START(serpent_ecb_dec_16way)
 	/* input:
 	 *	%rdi: ctx, CTX
 	 *	%rsi: dst
@@ -710,9 +710,9 @@ ENTRY(serpent_ecb_dec_16way)
 
 	FRAME_END
 	ret;
-ENDPROC(serpent_ecb_dec_16way)
+SYM_FUNC_END(serpent_ecb_dec_16way)
 
-ENTRY(serpent_cbc_dec_16way)
+SYM_FUNC_START(serpent_cbc_dec_16way)
 	/* input:
 	 *	%rdi: ctx, CTX
 	 *	%rsi: dst
@@ -733,9 +733,9 @@ ENTRY(serpent_cbc_dec_16way)
 
 	FRAME_END
 	ret;
-ENDPROC(serpent_cbc_dec_16way)
+SYM_FUNC_END(serpent_cbc_dec_16way)
 
-ENTRY(serpent_ctr_16way)
+SYM_FUNC_START(serpent_ctr_16way)
 	/* input:
 	 *	%rdi: ctx, CTX
 	 *	%rsi: dst (16 blocks)
@@ -758,9 +758,9 @@ ENTRY(serpent_ctr_16way)
 
 	FRAME_END
 	ret;
-ENDPROC(serpent_ctr_16way)
+SYM_FUNC_END(serpent_ctr_16way)
 
-ENTRY(serpent_xts_enc_16way)
+SYM_FUNC_START(serpent_xts_enc_16way)
 	/* input:
 	 *	%rdi: ctx, CTX
 	 *	%rsi: dst (16 blocks)
@@ -784,9 +784,9 @@ ENTRY(serpent_xts_enc_16way)
 
 	FRAME_END
 	ret;
-ENDPROC(serpent_xts_enc_16way)
+SYM_FUNC_END(serpent_xts_enc_16way)
 
-ENTRY(serpent_xts_dec_16way)
+SYM_FUNC_START(serpent_xts_dec_16way)
 	/* input:
 	 *	%rdi: ctx, CTX
 	 *	%rsi: dst (16 blocks)
@@ -810,4 +810,4 @@ ENTRY(serpent_xts_dec_16way)
 
 	FRAME_END
 	ret;
-ENDPROC(serpent_xts_dec_16way)
+SYM_FUNC_END(serpent_xts_dec_16way)
diff --git a/arch/x86/crypto/serpent-sse2-i586-asm_32.S b/arch/x86/crypto/serpent-sse2-i586-asm_32.S
index e5c4a4690ca9..6379b99cb722 100644
--- a/arch/x86/crypto/serpent-sse2-i586-asm_32.S
+++ b/arch/x86/crypto/serpent-sse2-i586-asm_32.S
@@ -497,7 +497,7 @@
 	pxor t0,		x3; \
 	movdqu x3,		(3*4*4)(out);
 
-ENTRY(__serpent_enc_blk_4way)
+SYM_FUNC_START(__serpent_enc_blk_4way)
 	/* input:
 	 *	arg_ctx(%esp): ctx, CTX
 	 *	arg_dst(%esp): dst
@@ -559,9 +559,9 @@ ENTRY(__serpent_enc_blk_4way)
 	xor_blocks(%eax, RA, RB, RC, RD, RT0, RT1, RE);
 
 	ret;
-ENDPROC(__serpent_enc_blk_4way)
+SYM_FUNC_END(__serpent_enc_blk_4way)
 
-ENTRY(serpent_dec_blk_4way)
+SYM_FUNC_START(serpent_dec_blk_4way)
 	/* input:
 	 *	arg_ctx(%esp): ctx, CTX
 	 *	arg_dst(%esp): dst
@@ -613,4 +613,4 @@ ENTRY(serpent_dec_blk_4way)
 	write_blocks(%eax, RC, RD, RB, RE, RT0, RT1, RA);
 
 	ret;
-ENDPROC(serpent_dec_blk_4way)
+SYM_FUNC_END(serpent_dec_blk_4way)
diff --git a/arch/x86/crypto/serpent-sse2-x86_64-asm_64.S b/arch/x86/crypto/serpent-sse2-x86_64-asm_64.S
index 5e0b3a3e97af..efb6dc17dc90 100644
--- a/arch/x86/crypto/serpent-sse2-x86_64-asm_64.S
+++ b/arch/x86/crypto/serpent-sse2-x86_64-asm_64.S
@@ -619,7 +619,7 @@
 	pxor t0,		x3; \
 	movdqu x3,		(3*4*4)(out);
 
-ENTRY(__serpent_enc_blk_8way)
+SYM_FUNC_START(__serpent_enc_blk_8way)
 	/* input:
 	 *	%rdi: ctx, CTX
 	 *	%rsi: dst
@@ -682,9 +682,9 @@ ENTRY(__serpent_enc_blk_8way)
 	xor_blocks(%rax, RA2, RB2, RC2, RD2, RK0, RK1, RK2);
 
 	ret;
-ENDPROC(__serpent_enc_blk_8way)
+SYM_FUNC_END(__serpent_enc_blk_8way)
 
-ENTRY(serpent_dec_blk_8way)
+SYM_FUNC_START(serpent_dec_blk_8way)
 	/* input:
 	 *	%rdi: ctx, CTX
 	 *	%rsi: dst
@@ -736,4 +736,4 @@ ENTRY(serpent_dec_blk_8way)
 	write_blocks(%rax, RC2, RD2, RB2, RE2, RK0, RK1, RK2);
 
 	ret;
-ENDPROC(serpent_dec_blk_8way)
+SYM_FUNC_END(serpent_dec_blk_8way)
diff --git a/arch/x86/crypto/sha1_avx2_x86_64_asm.S b/arch/x86/crypto/sha1_avx2_x86_64_asm.S
index 9f712a7dfd79..6decc85ef7b7 100644
--- a/arch/x86/crypto/sha1_avx2_x86_64_asm.S
+++ b/arch/x86/crypto/sha1_avx2_x86_64_asm.S
@@ -634,7 +634,7 @@ _loop3:
  * param: function's name
  */
 .macro SHA1_VECTOR_ASM  name
-	ENTRY(\name)
+	SYM_FUNC_START(\name)
 
 	push	%rbx
 	push	%r12
@@ -676,7 +676,7 @@ _loop3:
 
 	ret
 
-	ENDPROC(\name)
+	SYM_FUNC_END(\name)
 .endm
 
 .section .rodata
diff --git a/arch/x86/crypto/sha1_ni_asm.S b/arch/x86/crypto/sha1_ni_asm.S
index ebbdba72ae07..11efe3a45a1f 100644
--- a/arch/x86/crypto/sha1_ni_asm.S
+++ b/arch/x86/crypto/sha1_ni_asm.S
@@ -95,7 +95,7 @@
  */
 .text
 .align 32
-ENTRY(sha1_ni_transform)
+SYM_FUNC_START(sha1_ni_transform)
 	mov		%rsp, RSPSAVE
 	sub		$FRAME_SIZE, %rsp
 	and		$~0xF, %rsp
@@ -291,7 +291,7 @@ ENTRY(sha1_ni_transform)
 	mov		RSPSAVE, %rsp
 
 	ret
-ENDPROC(sha1_ni_transform)
+SYM_FUNC_END(sha1_ni_transform)
 
 .section	.rodata.cst16.PSHUFFLE_BYTE_FLIP_MASK, "aM", @progbits, 16
 .align 16
diff --git a/arch/x86/crypto/sha1_ssse3_asm.S b/arch/x86/crypto/sha1_ssse3_asm.S
index 99c5b8c4dc38..5d03c1173690 100644
--- a/arch/x86/crypto/sha1_ssse3_asm.S
+++ b/arch/x86/crypto/sha1_ssse3_asm.S
@@ -67,7 +67,7 @@
  * param: function's name
  */
 .macro SHA1_VECTOR_ASM  name
-	ENTRY(\name)
+	SYM_FUNC_START(\name)
 
 	push	%rbx
 	push	%r12
@@ -101,7 +101,7 @@
 	pop	%rbx
 	ret
 
-	ENDPROC(\name)
+	SYM_FUNC_END(\name)
 .endm
 
 /*
diff --git a/arch/x86/crypto/sha256-avx-asm.S b/arch/x86/crypto/sha256-avx-asm.S
index 001bbcf93c79..22e14c8dd2e4 100644
--- a/arch/x86/crypto/sha256-avx-asm.S
+++ b/arch/x86/crypto/sha256-avx-asm.S
@@ -347,7 +347,7 @@ a = TMP_
 ## arg 3 : Num blocks
 ########################################################################
 .text
-ENTRY(sha256_transform_avx)
+SYM_FUNC_START(sha256_transform_avx)
 .align 32
 	pushq   %rbx
 	pushq   %r12
@@ -460,7 +460,7 @@ done_hash:
 	popq	%r12
 	popq    %rbx
 	ret
-ENDPROC(sha256_transform_avx)
+SYM_FUNC_END(sha256_transform_avx)
 
 .section	.rodata.cst256.K256, "aM", @progbits, 256
 .align 64
diff --git a/arch/x86/crypto/sha256-avx2-asm.S b/arch/x86/crypto/sha256-avx2-asm.S
index 1420db15dcdd..519b551ad576 100644
--- a/arch/x86/crypto/sha256-avx2-asm.S
+++ b/arch/x86/crypto/sha256-avx2-asm.S
@@ -526,7 +526,7 @@ STACK_SIZE	= _RSP      + _RSP_SIZE
 ## arg 3 : Num blocks
 ########################################################################
 .text
-ENTRY(sha256_transform_rorx)
+SYM_FUNC_START(sha256_transform_rorx)
 .align 32
 	pushq	%rbx
 	pushq	%r12
@@ -713,7 +713,7 @@ done_hash:
 	popq	%r12
 	popq	%rbx
 	ret
-ENDPROC(sha256_transform_rorx)
+SYM_FUNC_END(sha256_transform_rorx)
 
 .section	.rodata.cst512.K256, "aM", @progbits, 512
 .align 64
diff --git a/arch/x86/crypto/sha256-ssse3-asm.S b/arch/x86/crypto/sha256-ssse3-asm.S
index c6c05ed2c16a..69cc2f91dc4c 100644
--- a/arch/x86/crypto/sha256-ssse3-asm.S
+++ b/arch/x86/crypto/sha256-ssse3-asm.S
@@ -353,7 +353,7 @@ a = TMP_
 ## arg 3 : Num blocks
 ########################################################################
 .text
-ENTRY(sha256_transform_ssse3)
+SYM_FUNC_START(sha256_transform_ssse3)
 .align 32
 	pushq   %rbx
 	pushq   %r12
@@ -471,7 +471,7 @@ done_hash:
 	popq    %rbx
 
 	ret
-ENDPROC(sha256_transform_ssse3)
+SYM_FUNC_END(sha256_transform_ssse3)
 
 .section	.rodata.cst256.K256, "aM", @progbits, 256
 .align 64
diff --git a/arch/x86/crypto/sha256_ni_asm.S b/arch/x86/crypto/sha256_ni_asm.S
index fb58f58ecfbc..7abade04a3a3 100644
--- a/arch/x86/crypto/sha256_ni_asm.S
+++ b/arch/x86/crypto/sha256_ni_asm.S
@@ -97,7 +97,7 @@
 
 .text
 .align 32
-ENTRY(sha256_ni_transform)
+SYM_FUNC_START(sha256_ni_transform)
 
 	shl		$6, NUM_BLKS		/*  convert to bytes */
 	jz		.Ldone_hash
@@ -327,7 +327,7 @@ ENTRY(sha256_ni_transform)
 .Ldone_hash:
 
 	ret
-ENDPROC(sha256_ni_transform)
+SYM_FUNC_END(sha256_ni_transform)
 
 .section	.rodata.cst256.K256, "aM", @progbits, 256
 .align 64
diff --git a/arch/x86/crypto/sha512-avx-asm.S b/arch/x86/crypto/sha512-avx-asm.S
index 39235fefe6f7..3704ddd7e5d5 100644
--- a/arch/x86/crypto/sha512-avx-asm.S
+++ b/arch/x86/crypto/sha512-avx-asm.S
@@ -277,7 +277,7 @@ frame_size = frame_GPRSAVE + GPRSAVE_SIZE
 # message blocks.
 # L is the message length in SHA512 blocks
 ########################################################################
-ENTRY(sha512_transform_avx)
+SYM_FUNC_START(sha512_transform_avx)
 	cmp $0, msglen
 	je nowork
 
@@ -365,7 +365,7 @@ updateblock:
 
 nowork:
 	ret
-ENDPROC(sha512_transform_avx)
+SYM_FUNC_END(sha512_transform_avx)
 
 ########################################################################
 ### Binary Data
diff --git a/arch/x86/crypto/sha512-avx2-asm.S b/arch/x86/crypto/sha512-avx2-asm.S
index b16d56005162..80d830e7ee09 100644
--- a/arch/x86/crypto/sha512-avx2-asm.S
+++ b/arch/x86/crypto/sha512-avx2-asm.S
@@ -569,7 +569,7 @@ frame_size = frame_GPRSAVE + GPRSAVE_SIZE
 #   message blocks.
 # L is the message length in SHA512 blocks
 ########################################################################
-ENTRY(sha512_transform_rorx)
+SYM_FUNC_START(sha512_transform_rorx)
 	# Allocate Stack Space
 	mov	%rsp, %rax
 	sub	$frame_size, %rsp
@@ -682,7 +682,7 @@ done_hash:
 	# Restore Stack Pointer
 	mov	frame_RSPSAVE(%rsp), %rsp
 	ret
-ENDPROC(sha512_transform_rorx)
+SYM_FUNC_END(sha512_transform_rorx)
 
 ########################################################################
 ### Binary Data
diff --git a/arch/x86/crypto/sha512-ssse3-asm.S b/arch/x86/crypto/sha512-ssse3-asm.S
index 66bbd9058a90..838f984e95d9 100644
--- a/arch/x86/crypto/sha512-ssse3-asm.S
+++ b/arch/x86/crypto/sha512-ssse3-asm.S
@@ -275,7 +275,7 @@ frame_size = frame_GPRSAVE + GPRSAVE_SIZE
 #   message blocks.
 # L is the message length in SHA512 blocks.
 ########################################################################
-ENTRY(sha512_transform_ssse3)
+SYM_FUNC_START(sha512_transform_ssse3)
 
 	cmp $0, msglen
 	je nowork
@@ -364,7 +364,7 @@ updateblock:
 
 nowork:
 	ret
-ENDPROC(sha512_transform_ssse3)
+SYM_FUNC_END(sha512_transform_ssse3)
 
 ########################################################################
 ### Binary Data
diff --git a/arch/x86/crypto/twofish-avx-x86_64-asm_64.S b/arch/x86/crypto/twofish-avx-x86_64-asm_64.S
index 698b8f2a56e2..a5151393bb2f 100644
--- a/arch/x86/crypto/twofish-avx-x86_64-asm_64.S
+++ b/arch/x86/crypto/twofish-avx-x86_64-asm_64.S
@@ -234,7 +234,7 @@
 	vpxor		x3, wkey, x3;
 
 .align 8
-__twofish_enc_blk8:
+SYM_FUNC_START_LOCAL(__twofish_enc_blk8)
 	/* input:
 	 *	%rdi: ctx, CTX
 	 *	RA1, RB1, RC1, RD1, RA2, RB2, RC2, RD2: blocks
@@ -273,10 +273,10 @@ __twofish_enc_blk8:
 	outunpack_blocks(RC2, RD2, RA2, RB2, RK1, RX0, RY0, RK2);
 
 	ret;
-ENDPROC(__twofish_enc_blk8)
+SYM_FUNC_END(__twofish_enc_blk8)
 
 .align 8
-__twofish_dec_blk8:
+SYM_FUNC_START_LOCAL(__twofish_dec_blk8)
 	/* input:
 	 *	%rdi: ctx, CTX
 	 *	RC1, RD1, RA1, RB1, RC2, RD2, RA2, RB2: encrypted blocks
@@ -313,9 +313,9 @@ __twofish_dec_blk8:
 	outunpack_blocks(RA2, RB2, RC2, RD2, RK1, RX0, RY0, RK2);
 
 	ret;
-ENDPROC(__twofish_dec_blk8)
+SYM_FUNC_END(__twofish_dec_blk8)
 
-ENTRY(twofish_ecb_enc_8way)
+SYM_FUNC_START(twofish_ecb_enc_8way)
 	/* input:
 	 *	%rdi: ctx, CTX
 	 *	%rsi: dst
@@ -333,9 +333,9 @@ ENTRY(twofish_ecb_enc_8way)
 
 	FRAME_END
 	ret;
-ENDPROC(twofish_ecb_enc_8way)
+SYM_FUNC_END(twofish_ecb_enc_8way)
 
-ENTRY(twofish_ecb_dec_8way)
+SYM_FUNC_START(twofish_ecb_dec_8way)
 	/* input:
 	 *	%rdi: ctx, CTX
 	 *	%rsi: dst
@@ -353,9 +353,9 @@ ENTRY(twofish_ecb_dec_8way)
 
 	FRAME_END
 	ret;
-ENDPROC(twofish_ecb_dec_8way)
+SYM_FUNC_END(twofish_ecb_dec_8way)
 
-ENTRY(twofish_cbc_dec_8way)
+SYM_FUNC_START(twofish_cbc_dec_8way)
 	/* input:
 	 *	%rdi: ctx, CTX
 	 *	%rsi: dst
@@ -378,9 +378,9 @@ ENTRY(twofish_cbc_dec_8way)
 
 	FRAME_END
 	ret;
-ENDPROC(twofish_cbc_dec_8way)
+SYM_FUNC_END(twofish_cbc_dec_8way)
 
-ENTRY(twofish_ctr_8way)
+SYM_FUNC_START(twofish_ctr_8way)
 	/* input:
 	 *	%rdi: ctx, CTX
 	 *	%rsi: dst
@@ -405,9 +405,9 @@ ENTRY(twofish_ctr_8way)
 
 	FRAME_END
 	ret;
-ENDPROC(twofish_ctr_8way)
+SYM_FUNC_END(twofish_ctr_8way)
 
-ENTRY(twofish_xts_enc_8way)
+SYM_FUNC_START(twofish_xts_enc_8way)
 	/* input:
 	 *	%rdi: ctx, CTX
 	 *	%rsi: dst
@@ -429,9 +429,9 @@ ENTRY(twofish_xts_enc_8way)
 
 	FRAME_END
 	ret;
-ENDPROC(twofish_xts_enc_8way)
+SYM_FUNC_END(twofish_xts_enc_8way)
 
-ENTRY(twofish_xts_dec_8way)
+SYM_FUNC_START(twofish_xts_dec_8way)
 	/* input:
 	 *	%rdi: ctx, CTX
 	 *	%rsi: dst
@@ -453,4 +453,4 @@ ENTRY(twofish_xts_dec_8way)
 
 	FRAME_END
 	ret;
-ENDPROC(twofish_xts_dec_8way)
+SYM_FUNC_END(twofish_xts_dec_8way)
diff --git a/arch/x86/crypto/twofish-i586-asm_32.S b/arch/x86/crypto/twofish-i586-asm_32.S
index 290cc4e9a6fe..a6f09e4f2e46 100644
--- a/arch/x86/crypto/twofish-i586-asm_32.S
+++ b/arch/x86/crypto/twofish-i586-asm_32.S
@@ -207,7 +207,7 @@
 	xor	%esi,		d ## D;\
 	ror	$1,		d ## D;
 
-ENTRY(twofish_enc_blk)
+SYM_FUNC_START(twofish_enc_blk)
 	push	%ebp			/* save registers according to calling convention*/
 	push    %ebx
 	push    %esi
@@ -261,9 +261,9 @@ ENTRY(twofish_enc_blk)
 	pop	%ebp
 	mov	$1,	%eax
 	ret
-ENDPROC(twofish_enc_blk)
+SYM_FUNC_END(twofish_enc_blk)
 
-ENTRY(twofish_dec_blk)
+SYM_FUNC_START(twofish_dec_blk)
 	push	%ebp			/* save registers according to calling convention*/
 	push    %ebx
 	push    %esi
@@ -318,4 +318,4 @@ ENTRY(twofish_dec_blk)
 	pop	%ebp
 	mov	$1,	%eax
 	ret
-ENDPROC(twofish_dec_blk)
+SYM_FUNC_END(twofish_dec_blk)
diff --git a/arch/x86/crypto/twofish-x86_64-asm_64-3way.S b/arch/x86/crypto/twofish-x86_64-asm_64-3way.S
index e495e07c7f1b..fc23552afe37 100644
--- a/arch/x86/crypto/twofish-x86_64-asm_64-3way.S
+++ b/arch/x86/crypto/twofish-x86_64-asm_64-3way.S
@@ -220,7 +220,7 @@
 	rorq $32,			RAB2; \
 	outunpack3(mov, RIO, 2, RAB, 2);
 
-ENTRY(__twofish_enc_blk_3way)
+SYM_FUNC_START(__twofish_enc_blk_3way)
 	/* input:
 	 *	%rdi: ctx, CTX
 	 *	%rsi: dst
@@ -267,9 +267,9 @@ ENTRY(__twofish_enc_blk_3way)
 	popq %r12;
 	popq %r13;
 	ret;
-ENDPROC(__twofish_enc_blk_3way)
+SYM_FUNC_END(__twofish_enc_blk_3way)
 
-ENTRY(twofish_dec_blk_3way)
+SYM_FUNC_START(twofish_dec_blk_3way)
 	/* input:
 	 *	%rdi: ctx, CTX
 	 *	%rsi: dst
@@ -302,4 +302,4 @@ ENTRY(twofish_dec_blk_3way)
 	popq %r12;
 	popq %r13;
 	ret;
-ENDPROC(twofish_dec_blk_3way)
+SYM_FUNC_END(twofish_dec_blk_3way)
diff --git a/arch/x86/crypto/twofish-x86_64-asm_64.S b/arch/x86/crypto/twofish-x86_64-asm_64.S
index ecef2cb9f43f..d2e56232494a 100644
--- a/arch/x86/crypto/twofish-x86_64-asm_64.S
+++ b/arch/x86/crypto/twofish-x86_64-asm_64.S
@@ -202,7 +202,7 @@
 	xor	%r8d,		d ## D;\
 	ror	$1,		d ## D;
 
-ENTRY(twofish_enc_blk)
+SYM_FUNC_START(twofish_enc_blk)
 	pushq    R1
 
 	/* %rdi contains the ctx address */
@@ -253,9 +253,9 @@ ENTRY(twofish_enc_blk)
 	popq	R1
 	movl	$1,%eax
 	ret
-ENDPROC(twofish_enc_blk)
+SYM_FUNC_END(twofish_enc_blk)
 
-ENTRY(twofish_dec_blk)
+SYM_FUNC_START(twofish_dec_blk)
 	pushq    R1
 
 	/* %rdi contains the ctx address */
@@ -305,4 +305,4 @@ ENTRY(twofish_dec_blk)
 	popq	R1
 	movl	$1,%eax
 	ret
-ENDPROC(twofish_dec_blk)
+SYM_FUNC_END(twofish_dec_blk)
diff --git a/arch/x86/entry/calling.h b/arch/x86/entry/calling.h
index 515c0ceeb4a3..0789e13ece90 100644
--- a/arch/x86/entry/calling.h
+++ b/arch/x86/entry/calling.h
@@ -354,7 +354,7 @@ For 32-bit we have the following conventions - kernel is built with
 .macro CALL_enter_from_user_mode
 #ifdef CONFIG_CONTEXT_TRACKING
 #ifdef CONFIG_JUMP_LABEL
-	STATIC_JUMP_IF_FALSE .Lafter_call_\@, context_tracking_enabled, def=0
+	STATIC_JUMP_IF_FALSE .Lafter_call_\@, context_tracking_key, def=0
 #endif
 	call enter_from_user_mode
 .Lafter_call_\@:
diff --git a/arch/x86/entry/common.c b/arch/x86/entry/common.c
index 3f8e22615812..9747876980b5 100644
--- a/arch/x86/entry/common.c
+++ b/arch/x86/entry/common.c
@@ -33,6 +33,7 @@
 #include <asm/cpufeature.h>
 #include <asm/fpu/api.h>
 #include <asm/nospec-branch.h>
+#include <asm/io_bitmap.h>
 
 #define CREATE_TRACE_POINTS
 #include <trace/events/syscalls.h>
@@ -196,6 +197,9 @@ __visible inline void prepare_exit_to_usermode(struct pt_regs *regs)
 	/* Reload ti->flags; we may have rescheduled above. */
 	cached_flags = READ_ONCE(ti->flags);
 
+	if (unlikely(cached_flags & _TIF_IO_BITMAP))
+		tss_update_io_bitmap();
+
 	fpregs_assert_state_consistent();
 	if (unlikely(cached_flags & _TIF_NEED_FPU_LOAD))
 		switch_fpu_return();
diff --git a/arch/x86/entry/entry_32.S b/arch/x86/entry/entry_32.S
index f83ca5aa8b77..5832b11f01bb 100644
--- a/arch/x86/entry/entry_32.S
+++ b/arch/x86/entry/entry_32.S
@@ -172,7 +172,7 @@
 	ALTERNATIVE "jmp .Lend_\@", "", X86_FEATURE_PTI
 	.if \no_user_check == 0
 	/* coming from usermode? */
-	testl	$SEGMENT_RPL_MASK, PT_CS(%esp)
+	testl	$USER_SEGMENT_RPL_MASK, PT_CS(%esp)
 	jz	.Lend_\@
 	.endif
 	/* On user-cr3? */
@@ -205,64 +205,76 @@
 #define CS_FROM_ENTRY_STACK	(1 << 31)
 #define CS_FROM_USER_CR3	(1 << 30)
 #define CS_FROM_KERNEL		(1 << 29)
+#define CS_FROM_ESPFIX		(1 << 28)
 
 .macro FIXUP_FRAME
 	/*
 	 * The high bits of the CS dword (__csh) are used for CS_FROM_*.
 	 * Clear them in case hardware didn't do this for us.
 	 */
-	andl	$0x0000ffff, 3*4(%esp)
+	andl	$0x0000ffff, 4*4(%esp)
 
 #ifdef CONFIG_VM86
-	testl	$X86_EFLAGS_VM, 4*4(%esp)
+	testl	$X86_EFLAGS_VM, 5*4(%esp)
 	jnz	.Lfrom_usermode_no_fixup_\@
 #endif
-	testl	$SEGMENT_RPL_MASK, 3*4(%esp)
+	testl	$USER_SEGMENT_RPL_MASK, 4*4(%esp)
 	jnz	.Lfrom_usermode_no_fixup_\@
 
-	orl	$CS_FROM_KERNEL, 3*4(%esp)
+	orl	$CS_FROM_KERNEL, 4*4(%esp)
 
 	/*
 	 * When we're here from kernel mode; the (exception) stack looks like:
 	 *
-	 *  5*4(%esp) - <previous context>
-	 *  4*4(%esp) - flags
-	 *  3*4(%esp) - cs
-	 *  2*4(%esp) - ip
-	 *  1*4(%esp) - orig_eax
-	 *  0*4(%esp) - gs / function
+	 *  6*4(%esp) - <previous context>
+	 *  5*4(%esp) - flags
+	 *  4*4(%esp) - cs
+	 *  3*4(%esp) - ip
+	 *  2*4(%esp) - orig_eax
+	 *  1*4(%esp) - gs / function
+	 *  0*4(%esp) - fs
 	 *
 	 * Lets build a 5 entry IRET frame after that, such that struct pt_regs
 	 * is complete and in particular regs->sp is correct. This gives us
-	 * the original 5 enties as gap:
+	 * the original 6 enties as gap:
 	 *
-	 * 12*4(%esp) - <previous context>
-	 * 11*4(%esp) - gap / flags
-	 * 10*4(%esp) - gap / cs
-	 *  9*4(%esp) - gap / ip
-	 *  8*4(%esp) - gap / orig_eax
-	 *  7*4(%esp) - gap / gs / function
-	 *  6*4(%esp) - ss
-	 *  5*4(%esp) - sp
-	 *  4*4(%esp) - flags
-	 *  3*4(%esp) - cs
-	 *  2*4(%esp) - ip
-	 *  1*4(%esp) - orig_eax
-	 *  0*4(%esp) - gs / function
+	 * 14*4(%esp) - <previous context>
+	 * 13*4(%esp) - gap / flags
+	 * 12*4(%esp) - gap / cs
+	 * 11*4(%esp) - gap / ip
+	 * 10*4(%esp) - gap / orig_eax
+	 *  9*4(%esp) - gap / gs / function
+	 *  8*4(%esp) - gap / fs
+	 *  7*4(%esp) - ss
+	 *  6*4(%esp) - sp
+	 *  5*4(%esp) - flags
+	 *  4*4(%esp) - cs
+	 *  3*4(%esp) - ip
+	 *  2*4(%esp) - orig_eax
+	 *  1*4(%esp) - gs / function
+	 *  0*4(%esp) - fs
 	 */
 
 	pushl	%ss		# ss
 	pushl	%esp		# sp (points at ss)
-	addl	$6*4, (%esp)	# point sp back at the previous context
-	pushl	6*4(%esp)	# flags
-	pushl	6*4(%esp)	# cs
-	pushl	6*4(%esp)	# ip
-	pushl	6*4(%esp)	# orig_eax
-	pushl	6*4(%esp)	# gs / function
+	addl	$7*4, (%esp)	# point sp back at the previous context
+	pushl	7*4(%esp)	# flags
+	pushl	7*4(%esp)	# cs
+	pushl	7*4(%esp)	# ip
+	pushl	7*4(%esp)	# orig_eax
+	pushl	7*4(%esp)	# gs / function
+	pushl	7*4(%esp)	# fs
 .Lfrom_usermode_no_fixup_\@:
 .endm
 
 .macro IRET_FRAME
+	/*
+	 * We're called with %ds, %es, %fs, and %gs from the interrupted
+	 * frame, so we shouldn't use them.  Also, we may be in ESPFIX
+	 * mode and therefore have a nonzero SS base and an offset ESP,
+	 * so any attempt to access the stack needs to use SS.  (except for
+	 * accesses through %esp, which automatically use SS.)
+	 */
 	testl $CS_FROM_KERNEL, 1*4(%esp)
 	jz .Lfinished_frame_\@
 
@@ -276,31 +288,40 @@
 	movl	5*4(%esp), %eax		# (modified) regs->sp
 
 	movl	4*4(%esp), %ecx		# flags
-	movl	%ecx, -4(%eax)
+	movl	%ecx, %ss:-1*4(%eax)
 
 	movl	3*4(%esp), %ecx		# cs
 	andl	$0x0000ffff, %ecx
-	movl	%ecx, -8(%eax)
+	movl	%ecx, %ss:-2*4(%eax)
 
 	movl	2*4(%esp), %ecx		# ip
-	movl	%ecx, -12(%eax)
+	movl	%ecx, %ss:-3*4(%eax)
 
 	movl	1*4(%esp), %ecx		# eax
-	movl	%ecx, -16(%eax)
+	movl	%ecx, %ss:-4*4(%eax)
 
 	popl	%ecx
-	lea	-16(%eax), %esp
+	lea	-4*4(%eax), %esp
 	popl	%eax
 .Lfinished_frame_\@:
 .endm
 
-.macro SAVE_ALL pt_regs_ax=%eax switch_stacks=0 skip_gs=0
+.macro SAVE_ALL pt_regs_ax=%eax switch_stacks=0 skip_gs=0 unwind_espfix=0
 	cld
 .if \skip_gs == 0
 	PUSH_GS
 .endif
-	FIXUP_FRAME
 	pushl	%fs
+
+	pushl	%eax
+	movl	$(__KERNEL_PERCPU), %eax
+	movl	%eax, %fs
+.if \unwind_espfix > 0
+	UNWIND_ESPFIX_STACK
+.endif
+	popl	%eax
+
+	FIXUP_FRAME
 	pushl	%es
 	pushl	%ds
 	pushl	\pt_regs_ax
@@ -313,8 +334,6 @@
 	movl	$(__USER_DS), %edx
 	movl	%edx, %ds
 	movl	%edx, %es
-	movl	$(__KERNEL_PERCPU), %edx
-	movl	%edx, %fs
 .if \skip_gs == 0
 	SET_KERNEL_GS %edx
 .endif
@@ -324,8 +343,8 @@
 .endif
 .endm
 
-.macro SAVE_ALL_NMI cr3_reg:req
-	SAVE_ALL
+.macro SAVE_ALL_NMI cr3_reg:req unwind_espfix=0
+	SAVE_ALL unwind_espfix=\unwind_espfix
 
 	BUG_IF_WRONG_CR3
 
@@ -357,6 +376,7 @@
 2:	popl	%es
 3:	popl	%fs
 	POP_GS \pop
+	IRET_FRAME
 .pushsection .fixup, "ax"
 4:	movl	$0, (%esp)
 	jmp	1b
@@ -395,7 +415,8 @@
 
 .macro CHECK_AND_APPLY_ESPFIX
 #ifdef CONFIG_X86_ESPFIX32
-#define GDT_ESPFIX_SS PER_CPU_VAR(gdt_page) + (GDT_ENTRY_ESPFIX_SS * 8)
+#define GDT_ESPFIX_OFFSET (GDT_ENTRY_ESPFIX_SS * 8)
+#define GDT_ESPFIX_SS PER_CPU_VAR(gdt_page) + GDT_ESPFIX_OFFSET
 
 	ALTERNATIVE	"jmp .Lend_\@", "", X86_BUG_ESPFIX
 
@@ -709,7 +730,7 @@
  * %eax: prev task
  * %edx: next task
  */
-ENTRY(__switch_to_asm)
+SYM_CODE_START(__switch_to_asm)
 	/*
 	 * Save callee-saved registers
 	 * This must match the order in struct inactive_task_frame
@@ -718,6 +739,11 @@ ENTRY(__switch_to_asm)
 	pushl	%ebx
 	pushl	%edi
 	pushl	%esi
+	/*
+	 * Flags are saved to prevent AC leakage. This could go
+	 * away if objtool would have 32bit support to verify
+	 * the STAC/CLAC correctness.
+	 */
 	pushfl
 
 	/* switch stack */
@@ -740,15 +766,16 @@ ENTRY(__switch_to_asm)
 	FILL_RETURN_BUFFER %ebx, RSB_CLEAR_LOOPS, X86_FEATURE_RSB_CTXSW
 #endif
 
-	/* restore callee-saved registers */
+	/* Restore flags or the incoming task to restore AC state. */
 	popfl
+	/* restore callee-saved registers */
 	popl	%esi
 	popl	%edi
 	popl	%ebx
 	popl	%ebp
 
 	jmp	__switch_to
-END(__switch_to_asm)
+SYM_CODE_END(__switch_to_asm)
 
 /*
  * The unwinder expects the last frame on the stack to always be at the same
@@ -757,7 +784,7 @@ END(__switch_to_asm)
  * asmlinkage function so its argument has to be pushed on the stack.  This
  * wrapper creates a proper "end of stack" frame header before the call.
  */
-ENTRY(schedule_tail_wrapper)
+SYM_FUNC_START(schedule_tail_wrapper)
 	FRAME_BEGIN
 
 	pushl	%eax
@@ -766,7 +793,7 @@ ENTRY(schedule_tail_wrapper)
 
 	FRAME_END
 	ret
-ENDPROC(schedule_tail_wrapper)
+SYM_FUNC_END(schedule_tail_wrapper)
 /*
  * A newly forked process directly context switches into this address.
  *
@@ -774,7 +801,7 @@ ENDPROC(schedule_tail_wrapper)
  * ebx: kernel thread func (NULL for user thread)
  * edi: kernel thread arg
  */
-ENTRY(ret_from_fork)
+SYM_CODE_START(ret_from_fork)
 	call	schedule_tail_wrapper
 
 	testl	%ebx, %ebx
@@ -797,7 +824,7 @@ ENTRY(ret_from_fork)
 	 */
 	movl	$0, PT_EAX(%esp)
 	jmp	2b
-END(ret_from_fork)
+SYM_CODE_END(ret_from_fork)
 
 /*
  * Return to user mode is not as complex as all this looks,
@@ -807,8 +834,7 @@ END(ret_from_fork)
  */
 
 	# userspace resumption stub bypassing syscall exit tracing
-	ALIGN
-ret_from_exception:
+SYM_CODE_START_LOCAL(ret_from_exception)
 	preempt_stop(CLBR_ANY)
 ret_from_intr:
 #ifdef CONFIG_VM86
@@ -825,15 +851,14 @@ ret_from_intr:
 	cmpl	$USER_RPL, %eax
 	jb	restore_all_kernel		# not returning to v8086 or userspace
 
-ENTRY(resume_userspace)
 	DISABLE_INTERRUPTS(CLBR_ANY)
 	TRACE_IRQS_OFF
 	movl	%esp, %eax
 	call	prepare_exit_to_usermode
 	jmp	restore_all
-END(ret_from_exception)
+SYM_CODE_END(ret_from_exception)
 
-GLOBAL(__begin_SYSENTER_singlestep_region)
+SYM_ENTRY(__begin_SYSENTER_singlestep_region, SYM_L_GLOBAL, SYM_A_NONE)
 /*
  * All code from here through __end_SYSENTER_singlestep_region is subject
  * to being single-stepped if a user program sets TF and executes SYSENTER.
@@ -848,9 +873,10 @@ GLOBAL(__begin_SYSENTER_singlestep_region)
  * Xen doesn't set %esp to be precisely what the normal SYSENTER
  * entry point expects, so fix it up before using the normal path.
  */
-ENTRY(xen_sysenter_target)
+SYM_CODE_START(xen_sysenter_target)
 	addl	$5*4, %esp			/* remove xen-provided frame */
 	jmp	.Lsysenter_past_esp
+SYM_CODE_END(xen_sysenter_target)
 #endif
 
 /*
@@ -885,7 +911,7 @@ ENTRY(xen_sysenter_target)
  * ebp  user stack
  * 0(%ebp) arg6
  */
-ENTRY(entry_SYSENTER_32)
+SYM_FUNC_START(entry_SYSENTER_32)
 	/*
 	 * On entry-stack with all userspace-regs live - save and
 	 * restore eflags and %eax to use it as scratch-reg for the cr3
@@ -1012,8 +1038,8 @@ ENTRY(entry_SYSENTER_32)
 	pushl	$X86_EFLAGS_FIXED
 	popfl
 	jmp	.Lsysenter_flags_fixed
-GLOBAL(__end_SYSENTER_singlestep_region)
-ENDPROC(entry_SYSENTER_32)
+SYM_ENTRY(__end_SYSENTER_singlestep_region, SYM_L_GLOBAL, SYM_A_NONE)
+SYM_FUNC_END(entry_SYSENTER_32)
 
 /*
  * 32-bit legacy system call entry.
@@ -1043,7 +1069,7 @@ ENDPROC(entry_SYSENTER_32)
  * edi  arg5
  * ebp  arg6
  */
-ENTRY(entry_INT80_32)
+SYM_FUNC_START(entry_INT80_32)
 	ASM_CLAC
 	pushl	%eax			/* pt_regs->orig_ax */
 
@@ -1075,7 +1101,6 @@ restore_all:
 	/* Restore user state */
 	RESTORE_REGS pop=4			# skip orig_eax/error_code
 .Lirq_return:
-	IRET_FRAME
 	/*
 	 * ARCH_HAS_MEMBARRIER_SYNC_CORE rely on IRET core serialization
 	 * when returning from IPI handler and when returning from
@@ -1100,7 +1125,7 @@ restore_all_kernel:
 	jmp	.Lirq_return
 
 .section .fixup, "ax"
-ENTRY(iret_exc	)
+SYM_CODE_START(iret_exc)
 	pushl	$0				# no error code
 	pushl	$do_iret_error
 
@@ -1117,9 +1142,10 @@ ENTRY(iret_exc	)
 #endif
 
 	jmp	common_exception
+SYM_CODE_END(iret_exc)
 .previous
 	_ASM_EXTABLE(.Lirq_return, iret_exc)
-ENDPROC(entry_INT80_32)
+SYM_FUNC_END(entry_INT80_32)
 
 .macro FIXUP_ESPFIX_STACK
 /*
@@ -1128,30 +1154,43 @@ ENDPROC(entry_INT80_32)
  * We can't call C functions using the ESPFIX stack. This code reads
  * the high word of the segment base from the GDT and swiches to the
  * normal stack and adjusts ESP with the matching offset.
+ *
+ * We might be on user CR3 here, so percpu data is not mapped and we can't
+ * access the GDT through the percpu segment.  Instead, use SGDT to find
+ * the cpu_entry_area alias of the GDT.
  */
 #ifdef CONFIG_X86_ESPFIX32
 	/* fixup the stack */
-	mov	GDT_ESPFIX_SS + 4, %al /* bits 16..23 */
-	mov	GDT_ESPFIX_SS + 7, %ah /* bits 24..31 */
+	pushl	%ecx
+	subl	$2*4, %esp
+	sgdt	(%esp)
+	movl	2(%esp), %ecx				/* GDT address */
+	/*
+	 * Careful: ECX is a linear pointer, so we need to force base
+	 * zero.  %cs is the only known-linear segment we have right now.
+	 */
+	mov	%cs:GDT_ESPFIX_OFFSET + 4(%ecx), %al	/* bits 16..23 */
+	mov	%cs:GDT_ESPFIX_OFFSET + 7(%ecx), %ah	/* bits 24..31 */
 	shl	$16, %eax
+	addl	$2*4, %esp
+	popl	%ecx
 	addl	%esp, %eax			/* the adjusted stack pointer */
 	pushl	$__KERNEL_DS
 	pushl	%eax
 	lss	(%esp), %esp			/* switch to the normal stack segment */
 #endif
 .endm
+
 .macro UNWIND_ESPFIX_STACK
+	/* It's safe to clobber %eax, all other regs need to be preserved */
 #ifdef CONFIG_X86_ESPFIX32
 	movl	%ss, %eax
 	/* see if on espfix stack */
 	cmpw	$__ESPFIX_SS, %ax
-	jne	27f
-	movl	$__KERNEL_DS, %eax
-	movl	%eax, %ds
-	movl	%eax, %es
+	jne	.Lno_fixup_\@
 	/* switch to normal stack */
 	FIXUP_ESPFIX_STACK
-27:
+.Lno_fixup_\@:
 #endif
 .endm
 
@@ -1160,7 +1199,7 @@ ENDPROC(entry_INT80_32)
  * We pack 1 stub into every 8-byte block.
  */
 	.align 8
-ENTRY(irq_entries_start)
+SYM_CODE_START(irq_entries_start)
     vector=FIRST_EXTERNAL_VECTOR
     .rept (FIRST_SYSTEM_VECTOR - FIRST_EXTERNAL_VECTOR)
 	pushl	$(~vector+0x80)			/* Note: always in signed byte range */
@@ -1168,11 +1207,11 @@ ENTRY(irq_entries_start)
 	jmp	common_interrupt
 	.align	8
     .endr
-END(irq_entries_start)
+SYM_CODE_END(irq_entries_start)
 
 #ifdef CONFIG_X86_LOCAL_APIC
 	.align 8
-ENTRY(spurious_entries_start)
+SYM_CODE_START(spurious_entries_start)
     vector=FIRST_SYSTEM_VECTOR
     .rept (NR_VECTORS - FIRST_SYSTEM_VECTOR)
 	pushl	$(~vector+0x80)			/* Note: always in signed byte range */
@@ -1180,9 +1219,9 @@ ENTRY(spurious_entries_start)
 	jmp	common_spurious
 	.align	8
     .endr
-END(spurious_entries_start)
+SYM_CODE_END(spurious_entries_start)
 
-common_spurious:
+SYM_CODE_START_LOCAL(common_spurious)
 	ASM_CLAC
 	addl	$-0x80, (%esp)			/* Adjust vector into the [-256, -1] range */
 	SAVE_ALL switch_stacks=1
@@ -1191,7 +1230,7 @@ common_spurious:
 	movl	%esp, %eax
 	call	smp_spurious_interrupt
 	jmp	ret_from_intr
-ENDPROC(common_spurious)
+SYM_CODE_END(common_spurious)
 #endif
 
 /*
@@ -1199,7 +1238,7 @@ ENDPROC(common_spurious)
  * so IRQ-flags tracing has to follow that:
  */
 	.p2align CONFIG_X86_L1_CACHE_SHIFT
-common_interrupt:
+SYM_CODE_START_LOCAL(common_interrupt)
 	ASM_CLAC
 	addl	$-0x80, (%esp)			/* Adjust vector into the [-256, -1] range */
 
@@ -1209,10 +1248,10 @@ common_interrupt:
 	movl	%esp, %eax
 	call	do_IRQ
 	jmp	ret_from_intr
-ENDPROC(common_interrupt)
+SYM_CODE_END(common_interrupt)
 
 #define BUILD_INTERRUPT3(name, nr, fn)			\
-ENTRY(name)						\
+SYM_FUNC_START(name)					\
 	ASM_CLAC;					\
 	pushl	$~(nr);					\
 	SAVE_ALL switch_stacks=1;			\
@@ -1221,7 +1260,7 @@ ENTRY(name)						\
 	movl	%esp, %eax;				\
 	call	fn;					\
 	jmp	ret_from_intr;				\
-ENDPROC(name)
+SYM_FUNC_END(name)
 
 #define BUILD_INTERRUPT(name, nr)		\
 	BUILD_INTERRUPT3(name, nr, smp_##name);	\
@@ -1229,14 +1268,14 @@ ENDPROC(name)
 /* The include is where all of the SMP etc. interrupts come from */
 #include <asm/entry_arch.h>
 
-ENTRY(coprocessor_error)
+SYM_CODE_START(coprocessor_error)
 	ASM_CLAC
 	pushl	$0
 	pushl	$do_coprocessor_error
 	jmp	common_exception
-END(coprocessor_error)
+SYM_CODE_END(coprocessor_error)
 
-ENTRY(simd_coprocessor_error)
+SYM_CODE_START(simd_coprocessor_error)
 	ASM_CLAC
 	pushl	$0
 #ifdef CONFIG_X86_INVD_BUG
@@ -1248,104 +1287,99 @@ ENTRY(simd_coprocessor_error)
 	pushl	$do_simd_coprocessor_error
 #endif
 	jmp	common_exception
-END(simd_coprocessor_error)
+SYM_CODE_END(simd_coprocessor_error)
 
-ENTRY(device_not_available)
+SYM_CODE_START(device_not_available)
 	ASM_CLAC
 	pushl	$-1				# mark this as an int
 	pushl	$do_device_not_available
 	jmp	common_exception
-END(device_not_available)
+SYM_CODE_END(device_not_available)
 
 #ifdef CONFIG_PARAVIRT
-ENTRY(native_iret)
+SYM_CODE_START(native_iret)
 	iret
 	_ASM_EXTABLE(native_iret, iret_exc)
-END(native_iret)
+SYM_CODE_END(native_iret)
 #endif
 
-ENTRY(overflow)
+SYM_CODE_START(overflow)
 	ASM_CLAC
 	pushl	$0
 	pushl	$do_overflow
 	jmp	common_exception
-END(overflow)
+SYM_CODE_END(overflow)
 
-ENTRY(bounds)
+SYM_CODE_START(bounds)
 	ASM_CLAC
 	pushl	$0
 	pushl	$do_bounds
 	jmp	common_exception
-END(bounds)
+SYM_CODE_END(bounds)
 
-ENTRY(invalid_op)
+SYM_CODE_START(invalid_op)
 	ASM_CLAC
 	pushl	$0
 	pushl	$do_invalid_op
 	jmp	common_exception
-END(invalid_op)
+SYM_CODE_END(invalid_op)
 
-ENTRY(coprocessor_segment_overrun)
+SYM_CODE_START(coprocessor_segment_overrun)
 	ASM_CLAC
 	pushl	$0
 	pushl	$do_coprocessor_segment_overrun
 	jmp	common_exception
-END(coprocessor_segment_overrun)
+SYM_CODE_END(coprocessor_segment_overrun)
 
-ENTRY(invalid_TSS)
+SYM_CODE_START(invalid_TSS)
 	ASM_CLAC
 	pushl	$do_invalid_TSS
 	jmp	common_exception
-END(invalid_TSS)
+SYM_CODE_END(invalid_TSS)
 
-ENTRY(segment_not_present)
+SYM_CODE_START(segment_not_present)
 	ASM_CLAC
 	pushl	$do_segment_not_present
 	jmp	common_exception
-END(segment_not_present)
+SYM_CODE_END(segment_not_present)
 
-ENTRY(stack_segment)
+SYM_CODE_START(stack_segment)
 	ASM_CLAC
 	pushl	$do_stack_segment
 	jmp	common_exception
-END(stack_segment)
+SYM_CODE_END(stack_segment)
 
-ENTRY(alignment_check)
+SYM_CODE_START(alignment_check)
 	ASM_CLAC
 	pushl	$do_alignment_check
 	jmp	common_exception
-END(alignment_check)
+SYM_CODE_END(alignment_check)
 
-ENTRY(divide_error)
+SYM_CODE_START(divide_error)
 	ASM_CLAC
 	pushl	$0				# no error code
 	pushl	$do_divide_error
 	jmp	common_exception
-END(divide_error)
+SYM_CODE_END(divide_error)
 
 #ifdef CONFIG_X86_MCE
-ENTRY(machine_check)
+SYM_CODE_START(machine_check)
 	ASM_CLAC
 	pushl	$0
 	pushl	machine_check_vector
 	jmp	common_exception
-END(machine_check)
+SYM_CODE_END(machine_check)
 #endif
 
-ENTRY(spurious_interrupt_bug)
+SYM_CODE_START(spurious_interrupt_bug)
 	ASM_CLAC
 	pushl	$0
 	pushl	$do_spurious_interrupt_bug
 	jmp	common_exception
-END(spurious_interrupt_bug)
+SYM_CODE_END(spurious_interrupt_bug)
 
 #ifdef CONFIG_XEN_PV
-ENTRY(xen_hypervisor_callback)
-	pushl	$-1				/* orig_ax = -1 => not a system call */
-	SAVE_ALL
-	ENCODE_FRAME_POINTER
-	TRACE_IRQS_OFF
-
+SYM_FUNC_START(xen_hypervisor_callback)
 	/*
 	 * Check to see if we got the event in the critical
 	 * region in xen_iret_direct, after we've reenabled
@@ -1353,22 +1387,23 @@ ENTRY(xen_hypervisor_callback)
 	 * iret instruction's behaviour where it delivers a
 	 * pending interrupt when enabling interrupts:
 	 */
-	movl	PT_EIP(%esp), %eax
-	cmpl	$xen_iret_start_crit, %eax
+	cmpl	$xen_iret_start_crit, (%esp)
 	jb	1f
-	cmpl	$xen_iret_end_crit, %eax
+	cmpl	$xen_iret_end_crit, (%esp)
 	jae	1f
-
-	jmp	xen_iret_crit_fixup
-
-ENTRY(xen_do_upcall)
-1:	mov	%esp, %eax
+	call	xen_iret_crit_fixup
+1:
+	pushl	$-1				/* orig_ax = -1 => not a system call */
+	SAVE_ALL
+	ENCODE_FRAME_POINTER
+	TRACE_IRQS_OFF
+	mov	%esp, %eax
 	call	xen_evtchn_do_upcall
 #ifndef CONFIG_PREEMPTION
 	call	xen_maybe_preempt_hcall
 #endif
 	jmp	ret_from_intr
-ENDPROC(xen_hypervisor_callback)
+SYM_FUNC_END(xen_hypervisor_callback)
 
 /*
  * Hypervisor uses this for application faults while it executes.
@@ -1382,7 +1417,7 @@ ENDPROC(xen_hypervisor_callback)
  * to pop the stack frame we end up in an infinite loop of failsafe callbacks.
  * We distinguish between categories by maintaining a status value in EAX.
  */
-ENTRY(xen_failsafe_callback)
+SYM_FUNC_START(xen_failsafe_callback)
 	pushl	%eax
 	movl	$1, %eax
 1:	mov	4(%esp), %ds
@@ -1419,7 +1454,7 @@ ENTRY(xen_failsafe_callback)
 	_ASM_EXTABLE(2b, 7b)
 	_ASM_EXTABLE(3b, 8b)
 	_ASM_EXTABLE(4b, 9b)
-ENDPROC(xen_failsafe_callback)
+SYM_FUNC_END(xen_failsafe_callback)
 #endif /* CONFIG_XEN_PV */
 
 #ifdef CONFIG_XEN_PVHVM
@@ -1441,18 +1476,17 @@ BUILD_INTERRUPT3(hv_stimer0_callback_vector, HYPERV_STIMER0_VECTOR,
 
 #endif /* CONFIG_HYPERV */
 
-ENTRY(page_fault)
+SYM_CODE_START(page_fault)
 	ASM_CLAC
 	pushl	$do_page_fault
 	jmp	common_exception_read_cr2
-END(page_fault)
+SYM_CODE_END(page_fault)
 
-common_exception_read_cr2:
+SYM_CODE_START_LOCAL_NOALIGN(common_exception_read_cr2)
 	/* the function address is in %gs's slot on the stack */
-	SAVE_ALL switch_stacks=1 skip_gs=1
+	SAVE_ALL switch_stacks=1 skip_gs=1 unwind_espfix=1
 
 	ENCODE_FRAME_POINTER
-	UNWIND_ESPFIX_STACK
 
 	/* fixup %gs */
 	GS_TO_REG %ecx
@@ -1470,13 +1504,12 @@ common_exception_read_cr2:
 	movl	%esp, %eax			# pt_regs pointer
 	CALL_NOSPEC %edi
 	jmp	ret_from_exception
-END(common_exception_read_cr2)
+SYM_CODE_END(common_exception_read_cr2)
 
-common_exception:
+SYM_CODE_START_LOCAL_NOALIGN(common_exception)
 	/* the function address is in %gs's slot on the stack */
-	SAVE_ALL switch_stacks=1 skip_gs=1
+	SAVE_ALL switch_stacks=1 skip_gs=1 unwind_espfix=1
 	ENCODE_FRAME_POINTER
-	UNWIND_ESPFIX_STACK
 
 	/* fixup %gs */
 	GS_TO_REG %ecx
@@ -1492,9 +1525,9 @@ common_exception:
 	movl	%esp, %eax			# pt_regs pointer
 	CALL_NOSPEC %edi
 	jmp	ret_from_exception
-END(common_exception)
+SYM_CODE_END(common_exception)
 
-ENTRY(debug)
+SYM_CODE_START(debug)
 	/*
 	 * Entry from sysenter is now handled in common_exception
 	 */
@@ -1502,7 +1535,7 @@ ENTRY(debug)
 	pushl	$-1				# mark this as an int
 	pushl	$do_debug
 	jmp	common_exception
-END(debug)
+SYM_CODE_END(debug)
 
 /*
  * NMI is doubly nasty.  It can happen on the first instruction of
@@ -1511,10 +1544,14 @@ END(debug)
  * switched stacks.  We handle both conditions by simply checking whether we
  * interrupted kernel code running on the SYSENTER stack.
  */
-ENTRY(nmi)
+SYM_CODE_START(nmi)
 	ASM_CLAC
 
 #ifdef CONFIG_X86_ESPFIX32
+	/*
+	 * ESPFIX_SS is only ever set on the return to user path
+	 * after we've switched to the entry stack.
+	 */
 	pushl	%eax
 	movl	%ss, %eax
 	cmpw	$__ESPFIX_SS, %ax
@@ -1550,6 +1587,11 @@ ENTRY(nmi)
 	movl	%ebx, %esp
 
 .Lnmi_return:
+#ifdef CONFIG_X86_ESPFIX32
+	testl	$CS_FROM_ESPFIX, PT_CS(%esp)
+	jnz	.Lnmi_from_espfix
+#endif
+
 	CHECK_AND_APPLY_ESPFIX
 	RESTORE_ALL_NMI cr3_reg=%edi pop=4
 	jmp	.Lirq_return
@@ -1557,28 +1599,47 @@ ENTRY(nmi)
 #ifdef CONFIG_X86_ESPFIX32
 .Lnmi_espfix_stack:
 	/*
-	 * create the pointer to lss back
+	 * Create the pointer to LSS back
 	 */
 	pushl	%ss
 	pushl	%esp
 	addl	$4, (%esp)
-	/* copy the iret frame of 12 bytes */
-	.rept 3
-	pushl	16(%esp)
-	.endr
-	pushl	%eax
-	SAVE_ALL_NMI cr3_reg=%edi
+
+	/* Copy the (short) IRET frame */
+	pushl	4*4(%esp)	# flags
+	pushl	4*4(%esp)	# cs
+	pushl	4*4(%esp)	# ip
+
+	pushl	%eax		# orig_ax
+
+	SAVE_ALL_NMI cr3_reg=%edi unwind_espfix=1
 	ENCODE_FRAME_POINTER
-	FIXUP_ESPFIX_STACK			# %eax == %esp
+
+	/* clear CS_FROM_KERNEL, set CS_FROM_ESPFIX */
+	xorl	$(CS_FROM_ESPFIX | CS_FROM_KERNEL), PT_CS(%esp)
+
 	xorl	%edx, %edx			# zero error code
-	call	do_nmi
+	movl	%esp, %eax			# pt_regs pointer
+	jmp	.Lnmi_from_sysenter_stack
+
+.Lnmi_from_espfix:
 	RESTORE_ALL_NMI cr3_reg=%edi
-	lss	12+4(%esp), %esp		# back to espfix stack
+	/*
+	 * Because we cleared CS_FROM_KERNEL, IRET_FRAME 'forgot' to
+	 * fix up the gap and long frame:
+	 *
+	 *  3 - original frame	(exception)
+	 *  2 - ESPFIX block	(above)
+	 *  6 - gap		(FIXUP_FRAME)
+	 *  5 - long frame	(FIXUP_FRAME)
+	 *  1 - orig_ax
+	 */
+	lss	(1+5+6)*4(%esp), %esp			# back to espfix stack
 	jmp	.Lirq_return
 #endif
-END(nmi)
+SYM_CODE_END(nmi)
 
-ENTRY(int3)
+SYM_CODE_START(int3)
 	ASM_CLAC
 	pushl	$-1				# mark this as an int
 
@@ -1589,22 +1650,22 @@ ENTRY(int3)
 	movl	%esp, %eax			# pt_regs pointer
 	call	do_int3
 	jmp	ret_from_exception
-END(int3)
+SYM_CODE_END(int3)
 
-ENTRY(general_protection)
+SYM_CODE_START(general_protection)
 	pushl	$do_general_protection
 	jmp	common_exception
-END(general_protection)
+SYM_CODE_END(general_protection)
 
 #ifdef CONFIG_KVM_GUEST
-ENTRY(async_page_fault)
+SYM_CODE_START(async_page_fault)
 	ASM_CLAC
 	pushl	$do_async_page_fault
 	jmp	common_exception_read_cr2
-END(async_page_fault)
+SYM_CODE_END(async_page_fault)
 #endif
 
-ENTRY(rewind_stack_do_exit)
+SYM_CODE_START(rewind_stack_do_exit)
 	/* Prevent any naive code from trying to unwind to our caller. */
 	xorl	%ebp, %ebp
 
@@ -1613,4 +1674,4 @@ ENTRY(rewind_stack_do_exit)
 
 	call	do_exit
 1:	jmp 1b
-END(rewind_stack_do_exit)
+SYM_CODE_END(rewind_stack_do_exit)
diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S
index b7c3ea4cb19d..76942cbd95a1 100644
--- a/arch/x86/entry/entry_64.S
+++ b/arch/x86/entry/entry_64.S
@@ -15,7 +15,7 @@
  *			at the top of the kernel process stack.
  *
  * Some macro usage:
- * - ENTRY/END:		Define functions in the symbol table.
+ * - SYM_FUNC_START/END:Define functions in the symbol table.
  * - TRACE_IRQ_*:	Trace hardirq state for lock debugging.
  * - idtentry:		Define exception entry points.
  */
@@ -46,11 +46,11 @@
 .section .entry.text, "ax"
 
 #ifdef CONFIG_PARAVIRT
-ENTRY(native_usergs_sysret64)
+SYM_CODE_START(native_usergs_sysret64)
 	UNWIND_HINT_EMPTY
 	swapgs
 	sysretq
-END(native_usergs_sysret64)
+SYM_CODE_END(native_usergs_sysret64)
 #endif /* CONFIG_PARAVIRT */
 
 .macro TRACE_IRQS_FLAGS flags:req
@@ -142,7 +142,7 @@ END(native_usergs_sysret64)
  * with them due to bugs in both AMD and Intel CPUs.
  */
 
-ENTRY(entry_SYSCALL_64)
+SYM_CODE_START(entry_SYSCALL_64)
 	UNWIND_HINT_EMPTY
 	/*
 	 * Interrupts are off on entry.
@@ -162,7 +162,7 @@ ENTRY(entry_SYSCALL_64)
 	pushq	%r11					/* pt_regs->flags */
 	pushq	$__USER_CS				/* pt_regs->cs */
 	pushq	%rcx					/* pt_regs->ip */
-GLOBAL(entry_SYSCALL_64_after_hwframe)
+SYM_INNER_LABEL(entry_SYSCALL_64_after_hwframe, SYM_L_GLOBAL)
 	pushq	%rax					/* pt_regs->orig_ax */
 
 	PUSH_AND_CLEAR_REGS rax=$-ENOSYS
@@ -273,13 +273,13 @@ syscall_return_via_sysret:
 	popq	%rdi
 	popq	%rsp
 	USERGS_SYSRET64
-END(entry_SYSCALL_64)
+SYM_CODE_END(entry_SYSCALL_64)
 
 /*
  * %rdi: prev task
  * %rsi: next task
  */
-ENTRY(__switch_to_asm)
+SYM_CODE_START(__switch_to_asm)
 	UNWIND_HINT_FUNC
 	/*
 	 * Save callee-saved registers
@@ -321,7 +321,7 @@ ENTRY(__switch_to_asm)
 	popq	%rbp
 
 	jmp	__switch_to
-END(__switch_to_asm)
+SYM_CODE_END(__switch_to_asm)
 
 /*
  * A newly forked process directly context switches into this address.
@@ -330,7 +330,7 @@ END(__switch_to_asm)
  * rbx: kernel thread func (NULL for user thread)
  * r12: kernel thread arg
  */
-ENTRY(ret_from_fork)
+SYM_CODE_START(ret_from_fork)
 	UNWIND_HINT_EMPTY
 	movq	%rax, %rdi
 	call	schedule_tail			/* rdi: 'prev' task parameter */
@@ -357,14 +357,14 @@ ENTRY(ret_from_fork)
 	 */
 	movq	$0, RAX(%rsp)
 	jmp	2b
-END(ret_from_fork)
+SYM_CODE_END(ret_from_fork)
 
 /*
  * Build the entry stubs with some assembler magic.
  * We pack 1 stub into every 8-byte block.
  */
 	.align 8
-ENTRY(irq_entries_start)
+SYM_CODE_START(irq_entries_start)
     vector=FIRST_EXTERNAL_VECTOR
     .rept (FIRST_SYSTEM_VECTOR - FIRST_EXTERNAL_VECTOR)
 	UNWIND_HINT_IRET_REGS
@@ -373,10 +373,10 @@ ENTRY(irq_entries_start)
 	.align	8
 	vector=vector+1
     .endr
-END(irq_entries_start)
+SYM_CODE_END(irq_entries_start)
 
 	.align 8
-ENTRY(spurious_entries_start)
+SYM_CODE_START(spurious_entries_start)
     vector=FIRST_SYSTEM_VECTOR
     .rept (NR_VECTORS - FIRST_SYSTEM_VECTOR)
 	UNWIND_HINT_IRET_REGS
@@ -385,7 +385,7 @@ ENTRY(spurious_entries_start)
 	.align	8
 	vector=vector+1
     .endr
-END(spurious_entries_start)
+SYM_CODE_END(spurious_entries_start)
 
 .macro DEBUG_ENTRY_ASSERT_IRQS_OFF
 #ifdef CONFIG_DEBUG_ENTRY
@@ -511,7 +511,7 @@ END(spurious_entries_start)
  * | return address					|
  * +----------------------------------------------------+
  */
-ENTRY(interrupt_entry)
+SYM_CODE_START(interrupt_entry)
 	UNWIND_HINT_FUNC
 	ASM_CLAC
 	cld
@@ -579,7 +579,7 @@ ENTRY(interrupt_entry)
 	TRACE_IRQS_OFF
 
 	ret
-END(interrupt_entry)
+SYM_CODE_END(interrupt_entry)
 _ASM_NOKPROBE(interrupt_entry)
 
 
@@ -589,18 +589,18 @@ _ASM_NOKPROBE(interrupt_entry)
  * The interrupt stubs push (~vector+0x80) onto the stack and
  * then jump to common_spurious/interrupt.
  */
-common_spurious:
+SYM_CODE_START_LOCAL(common_spurious)
 	addq	$-0x80, (%rsp)			/* Adjust vector to [-256, -1] range */
 	call	interrupt_entry
 	UNWIND_HINT_REGS indirect=1
 	call	smp_spurious_interrupt		/* rdi points to pt_regs */
 	jmp	ret_from_intr
-END(common_spurious)
+SYM_CODE_END(common_spurious)
 _ASM_NOKPROBE(common_spurious)
 
 /* common_interrupt is a hotpath. Align it */
 	.p2align CONFIG_X86_L1_CACHE_SHIFT
-common_interrupt:
+SYM_CODE_START_LOCAL(common_interrupt)
 	addq	$-0x80, (%rsp)			/* Adjust vector to [-256, -1] range */
 	call	interrupt_entry
 	UNWIND_HINT_REGS indirect=1
@@ -616,12 +616,12 @@ ret_from_intr:
 	jz	retint_kernel
 
 	/* Interrupt came from user space */
-GLOBAL(retint_user)
+.Lretint_user:
 	mov	%rsp,%rdi
 	call	prepare_exit_to_usermode
 	TRACE_IRQS_IRETQ
 
-GLOBAL(swapgs_restore_regs_and_return_to_usermode)
+SYM_INNER_LABEL(swapgs_restore_regs_and_return_to_usermode, SYM_L_GLOBAL)
 #ifdef CONFIG_DEBUG_ENTRY
 	/* Assert that pt_regs indicates user mode. */
 	testb	$3, CS(%rsp)
@@ -679,7 +679,7 @@ retint_kernel:
 	 */
 	TRACE_IRQS_IRETQ
 
-GLOBAL(restore_regs_and_return_to_kernel)
+SYM_INNER_LABEL(restore_regs_and_return_to_kernel, SYM_L_GLOBAL)
 #ifdef CONFIG_DEBUG_ENTRY
 	/* Assert that pt_regs indicates kernel mode. */
 	testb	$3, CS(%rsp)
@@ -695,7 +695,7 @@ GLOBAL(restore_regs_and_return_to_kernel)
 	 */
 	INTERRUPT_RETURN
 
-ENTRY(native_iret)
+SYM_INNER_LABEL_ALIGN(native_iret, SYM_L_GLOBAL)
 	UNWIND_HINT_IRET_REGS
 	/*
 	 * Are we returning to a stack segment from the LDT?  Note: in
@@ -706,8 +706,7 @@ ENTRY(native_iret)
 	jnz	native_irq_return_ldt
 #endif
 
-.global native_irq_return_iret
-native_irq_return_iret:
+SYM_INNER_LABEL(native_irq_return_iret, SYM_L_GLOBAL)
 	/*
 	 * This may fault.  Non-paranoid faults on return to userspace are
 	 * handled by fixup_bad_iret.  These include #SS, #GP, and #NP.
@@ -789,14 +788,14 @@ native_irq_return_ldt:
 	 */
 	jmp	native_irq_return_iret
 #endif
-END(common_interrupt)
+SYM_CODE_END(common_interrupt)
 _ASM_NOKPROBE(common_interrupt)
 
 /*
  * APIC interrupts.
  */
 .macro apicinterrupt3 num sym do_sym
-ENTRY(\sym)
+SYM_CODE_START(\sym)
 	UNWIND_HINT_IRET_REGS
 	pushq	$~(\num)
 .Lcommon_\sym:
@@ -804,7 +803,7 @@ ENTRY(\sym)
 	UNWIND_HINT_REGS indirect=1
 	call	\do_sym	/* rdi points to pt_regs */
 	jmp	ret_from_intr
-END(\sym)
+SYM_CODE_END(\sym)
 _ASM_NOKPROBE(\sym)
 .endm
 
@@ -969,7 +968,7 @@ apicinterrupt IRQ_WORK_VECTOR			irq_work_interrupt		smp_irq_work_interrupt
  * #DF: if the thread stack is somehow unusable, we'll still get a useful OOPS.
  */
 .macro idtentry sym do_sym has_error_code:req paranoid=0 shift_ist=-1 ist_offset=0 create_gap=0 read_cr2=0
-ENTRY(\sym)
+SYM_CODE_START(\sym)
 	UNWIND_HINT_IRET_REGS offset=\has_error_code*8
 
 	/* Sanity check */
@@ -1019,7 +1018,7 @@ ENTRY(\sym)
 	.endif
 
 _ASM_NOKPROBE(\sym)
-END(\sym)
+SYM_CODE_END(\sym)
 .endm
 
 idtentry divide_error			do_divide_error			has_error_code=0
@@ -1041,7 +1040,7 @@ idtentry simd_coprocessor_error		do_simd_coprocessor_error	has_error_code=0
 	 * Reload gs selector with exception handling
 	 * edi:  new selector
 	 */
-ENTRY(native_load_gs_index)
+SYM_FUNC_START(native_load_gs_index)
 	FRAME_BEGIN
 	pushfq
 	DISABLE_INTERRUPTS(CLBR_ANY & ~CLBR_RDI)
@@ -1055,13 +1054,13 @@ ENTRY(native_load_gs_index)
 	popfq
 	FRAME_END
 	ret
-ENDPROC(native_load_gs_index)
+SYM_FUNC_END(native_load_gs_index)
 EXPORT_SYMBOL(native_load_gs_index)
 
 	_ASM_EXTABLE(.Lgs_change, .Lbad_gs)
 	.section .fixup, "ax"
 	/* running with kernelgs */
-.Lbad_gs:
+SYM_CODE_START_LOCAL_NOALIGN(.Lbad_gs)
 	SWAPGS					/* switch back to user gs */
 .macro ZAP_GS
 	/* This can't be a string because the preprocessor needs to see it. */
@@ -1072,10 +1071,11 @@ EXPORT_SYMBOL(native_load_gs_index)
 	xorl	%eax, %eax
 	movl	%eax, %gs
 	jmp	2b
+SYM_CODE_END(.Lbad_gs)
 	.previous
 
 /* Call softirq on interrupt stack. Interrupts are off. */
-ENTRY(do_softirq_own_stack)
+SYM_FUNC_START(do_softirq_own_stack)
 	pushq	%rbp
 	mov	%rsp, %rbp
 	ENTER_IRQ_STACK regs=0 old_rsp=%r11
@@ -1083,7 +1083,7 @@ ENTRY(do_softirq_own_stack)
 	LEAVE_IRQ_STACK regs=0
 	leaveq
 	ret
-ENDPROC(do_softirq_own_stack)
+SYM_FUNC_END(do_softirq_own_stack)
 
 #ifdef CONFIG_XEN_PV
 idtentry hypervisor_callback xen_do_hypervisor_callback has_error_code=0
@@ -1101,7 +1101,8 @@ idtentry hypervisor_callback xen_do_hypervisor_callback has_error_code=0
  * existing activation in its critical region -- if so, we pop the current
  * activation and restart the handler using the previous one.
  */
-ENTRY(xen_do_hypervisor_callback)		/* do_hypervisor_callback(struct *pt_regs) */
+/* do_hypervisor_callback(struct *pt_regs) */
+SYM_CODE_START_LOCAL(xen_do_hypervisor_callback)
 
 /*
  * Since we don't modify %rdi, evtchn_do_upall(struct *pt_regs) will
@@ -1119,7 +1120,7 @@ ENTRY(xen_do_hypervisor_callback)		/* do_hypervisor_callback(struct *pt_regs) */
 	call	xen_maybe_preempt_hcall
 #endif
 	jmp	error_exit
-END(xen_do_hypervisor_callback)
+SYM_CODE_END(xen_do_hypervisor_callback)
 
 /*
  * Hypervisor uses this for application faults while it executes.
@@ -1134,7 +1135,7 @@ END(xen_do_hypervisor_callback)
  * We distinguish between categories by comparing each saved segment register
  * with its current contents: any discrepancy means we in category 1.
  */
-ENTRY(xen_failsafe_callback)
+SYM_CODE_START(xen_failsafe_callback)
 	UNWIND_HINT_EMPTY
 	movl	%ds, %ecx
 	cmpw	%cx, 0x10(%rsp)
@@ -1164,7 +1165,7 @@ ENTRY(xen_failsafe_callback)
 	PUSH_AND_CLEAR_REGS
 	ENCODE_FRAME_POINTER
 	jmp	error_exit
-END(xen_failsafe_callback)
+SYM_CODE_END(xen_failsafe_callback)
 #endif /* CONFIG_XEN_PV */
 
 #ifdef CONFIG_XEN_PVHVM
@@ -1214,7 +1215,7 @@ idtentry machine_check		do_mce			has_error_code=0	paranoid=1
  * Use slow, but surefire "are we in kernel?" check.
  * Return: ebx=0: need swapgs on exit, ebx=1: otherwise
  */
-ENTRY(paranoid_entry)
+SYM_CODE_START_LOCAL(paranoid_entry)
 	UNWIND_HINT_FUNC
 	cld
 	PUSH_AND_CLEAR_REGS save_ret=1
@@ -1248,7 +1249,7 @@ ENTRY(paranoid_entry)
 	FENCE_SWAPGS_KERNEL_ENTRY
 
 	ret
-END(paranoid_entry)
+SYM_CODE_END(paranoid_entry)
 
 /*
  * "Paranoid" exit path from exception stack.  This is invoked
@@ -1262,7 +1263,7 @@ END(paranoid_entry)
  *
  * On entry, ebx is "no swapgs" flag (1: don't need swapgs, 0: need it)
  */
-ENTRY(paranoid_exit)
+SYM_CODE_START_LOCAL(paranoid_exit)
 	UNWIND_HINT_REGS
 	DISABLE_INTERRUPTS(CLBR_ANY)
 	TRACE_IRQS_OFF_DEBUG
@@ -1272,19 +1273,18 @@ ENTRY(paranoid_exit)
 	/* Always restore stashed CR3 value (see paranoid_entry) */
 	RESTORE_CR3	scratch_reg=%rbx save_reg=%r14
 	SWAPGS_UNSAFE_STACK
-	jmp	.Lparanoid_exit_restore
+	jmp	restore_regs_and_return_to_kernel
 .Lparanoid_exit_no_swapgs:
 	TRACE_IRQS_IRETQ_DEBUG
 	/* Always restore stashed CR3 value (see paranoid_entry) */
 	RESTORE_CR3	scratch_reg=%rbx save_reg=%r14
-.Lparanoid_exit_restore:
 	jmp restore_regs_and_return_to_kernel
-END(paranoid_exit)
+SYM_CODE_END(paranoid_exit)
 
 /*
  * Save all registers in pt_regs, and switch GS if needed.
  */
-ENTRY(error_entry)
+SYM_CODE_START_LOCAL(error_entry)
 	UNWIND_HINT_FUNC
 	cld
 	PUSH_AND_CLEAR_REGS save_ret=1
@@ -1364,16 +1364,16 @@ ENTRY(error_entry)
 	call	fixup_bad_iret
 	mov	%rax, %rsp
 	jmp	.Lerror_entry_from_usermode_after_swapgs
-END(error_entry)
+SYM_CODE_END(error_entry)
 
-ENTRY(error_exit)
+SYM_CODE_START_LOCAL(error_exit)
 	UNWIND_HINT_REGS
 	DISABLE_INTERRUPTS(CLBR_ANY)
 	TRACE_IRQS_OFF
 	testb	$3, CS(%rsp)
 	jz	retint_kernel
-	jmp	retint_user
-END(error_exit)
+	jmp	.Lretint_user
+SYM_CODE_END(error_exit)
 
 /*
  * Runs on exception stack.  Xen PV does not go through this path at all,
@@ -1383,7 +1383,7 @@ END(error_exit)
  *	%r14: Used to save/restore the CR3 of the interrupted context
  *	      when PAGE_TABLE_ISOLATION is in use.  Do not clobber.
  */
-ENTRY(nmi)
+SYM_CODE_START(nmi)
 	UNWIND_HINT_IRET_REGS
 
 	/*
@@ -1718,21 +1718,21 @@ nmi_restore:
 	 * about espfix64 on the way back to kernel mode.
 	 */
 	iretq
-END(nmi)
+SYM_CODE_END(nmi)
 
 #ifndef CONFIG_IA32_EMULATION
 /*
  * This handles SYSCALL from 32-bit code.  There is no way to program
  * MSRs to fully disable 32-bit SYSCALL.
  */
-ENTRY(ignore_sysret)
+SYM_CODE_START(ignore_sysret)
 	UNWIND_HINT_EMPTY
 	mov	$-ENOSYS, %eax
 	sysret
-END(ignore_sysret)
+SYM_CODE_END(ignore_sysret)
 #endif
 
-ENTRY(rewind_stack_do_exit)
+SYM_CODE_START(rewind_stack_do_exit)
 	UNWIND_HINT_FUNC
 	/* Prevent any naive code from trying to unwind to our caller. */
 	xorl	%ebp, %ebp
@@ -1742,4 +1742,4 @@ ENTRY(rewind_stack_do_exit)
 	UNWIND_HINT_FUNC sp_offset=PTREGS_SIZE
 
 	call	do_exit
-END(rewind_stack_do_exit)
+SYM_CODE_END(rewind_stack_do_exit)
diff --git a/arch/x86/entry/entry_64_compat.S b/arch/x86/entry/entry_64_compat.S
index 39913770a44d..f1d3ccae5dd5 100644
--- a/arch/x86/entry/entry_64_compat.S
+++ b/arch/x86/entry/entry_64_compat.S
@@ -46,7 +46,7 @@
  * ebp  user stack
  * 0(%ebp) arg6
  */
-ENTRY(entry_SYSENTER_compat)
+SYM_FUNC_START(entry_SYSENTER_compat)
 	/* Interrupts are off on entry. */
 	SWAPGS
 
@@ -146,8 +146,8 @@ ENTRY(entry_SYSENTER_compat)
 	pushq	$X86_EFLAGS_FIXED
 	popfq
 	jmp	.Lsysenter_flags_fixed
-GLOBAL(__end_entry_SYSENTER_compat)
-ENDPROC(entry_SYSENTER_compat)
+SYM_INNER_LABEL(__end_entry_SYSENTER_compat, SYM_L_GLOBAL)
+SYM_FUNC_END(entry_SYSENTER_compat)
 
 /*
  * 32-bit SYSCALL entry.
@@ -196,7 +196,7 @@ ENDPROC(entry_SYSENTER_compat)
  * esp  user stack
  * 0(%esp) arg6
  */
-ENTRY(entry_SYSCALL_compat)
+SYM_CODE_START(entry_SYSCALL_compat)
 	/* Interrupts are off on entry. */
 	swapgs
 
@@ -215,7 +215,7 @@ ENTRY(entry_SYSCALL_compat)
 	pushq	%r11			/* pt_regs->flags */
 	pushq	$__USER32_CS		/* pt_regs->cs */
 	pushq	%rcx			/* pt_regs->ip */
-GLOBAL(entry_SYSCALL_compat_after_hwframe)
+SYM_INNER_LABEL(entry_SYSCALL_compat_after_hwframe, SYM_L_GLOBAL)
 	movl	%eax, %eax		/* discard orig_ax high bits */
 	pushq	%rax			/* pt_regs->orig_ax */
 	pushq	%rdi			/* pt_regs->di */
@@ -311,7 +311,7 @@ sysret32_from_system_call:
 	xorl	%r10d, %r10d
 	swapgs
 	sysretl
-END(entry_SYSCALL_compat)
+SYM_CODE_END(entry_SYSCALL_compat)
 
 /*
  * 32-bit legacy system call entry.
@@ -339,7 +339,7 @@ END(entry_SYSCALL_compat)
  * edi  arg5
  * ebp  arg6
  */
-ENTRY(entry_INT80_compat)
+SYM_CODE_START(entry_INT80_compat)
 	/*
 	 * Interrupts are off on entry.
 	 */
@@ -416,4 +416,4 @@ ENTRY(entry_INT80_compat)
 	/* Go back to user mode. */
 	TRACE_IRQS_ON
 	jmp	swapgs_restore_regs_and_return_to_usermode
-END(entry_INT80_compat)
+SYM_CODE_END(entry_INT80_compat)
diff --git a/arch/x86/entry/syscall_32.c b/arch/x86/entry/syscall_32.c
index aa3336a7cb15..7d17b3addbbb 100644
--- a/arch/x86/entry/syscall_32.c
+++ b/arch/x86/entry/syscall_32.c
@@ -10,13 +10,11 @@
 #ifdef CONFIG_IA32_EMULATION
 /* On X86_64, we use struct pt_regs * to pass parameters to syscalls */
 #define __SYSCALL_I386(nr, sym, qual) extern asmlinkage long sym(const struct pt_regs *);
-
-/* this is a lie, but it does not hurt as sys_ni_syscall just returns -EINVAL */
-extern asmlinkage long sys_ni_syscall(const struct pt_regs *);
-
+#define __sys_ni_syscall __ia32_sys_ni_syscall
 #else /* CONFIG_IA32_EMULATION */
 #define __SYSCALL_I386(nr, sym, qual) extern asmlinkage long sym(unsigned long, unsigned long, unsigned long, unsigned long, unsigned long, unsigned long);
 extern asmlinkage long sys_ni_syscall(unsigned long, unsigned long, unsigned long, unsigned long, unsigned long, unsigned long);
+#define __sys_ni_syscall sys_ni_syscall
 #endif /* CONFIG_IA32_EMULATION */
 
 #include <asm/syscalls_32.h>
@@ -29,6 +27,6 @@ __visible const sys_call_ptr_t ia32_sys_call_table[__NR_syscall_compat_max+1] =
 	 * Smells like a compiler bug -- it doesn't work
 	 * when the & below is removed.
 	 */
-	[0 ... __NR_syscall_compat_max] = &sys_ni_syscall,
+	[0 ... __NR_syscall_compat_max] = &__sys_ni_syscall,
 #include <asm/syscalls_32.h>
 };
diff --git a/arch/x86/entry/syscall_64.c b/arch/x86/entry/syscall_64.c
index b1bf31713374..adf619a856e8 100644
--- a/arch/x86/entry/syscall_64.c
+++ b/arch/x86/entry/syscall_64.c
@@ -4,11 +4,17 @@
 #include <linux/linkage.h>
 #include <linux/sys.h>
 #include <linux/cache.h>
+#include <linux/syscalls.h>
 #include <asm/asm-offsets.h>
 #include <asm/syscall.h>
 
-/* this is a lie, but it does not hurt as sys_ni_syscall just returns -EINVAL */
-extern asmlinkage long sys_ni_syscall(const struct pt_regs *);
+extern asmlinkage long sys_ni_syscall(void);
+
+SYSCALL_DEFINE0(ni_syscall)
+{
+	return sys_ni_syscall();
+}
+
 #define __SYSCALL_64(nr, sym, qual) extern asmlinkage long sym(const struct pt_regs *);
 #define __SYSCALL_X32(nr, sym, qual) __SYSCALL_64(nr, sym, qual)
 #include <asm/syscalls_64.h>
@@ -23,7 +29,7 @@ asmlinkage const sys_call_ptr_t sys_call_table[__NR_syscall_max+1] = {
 	 * Smells like a compiler bug -- it doesn't work
 	 * when the & below is removed.
 	 */
-	[0 ... __NR_syscall_max] = &sys_ni_syscall,
+	[0 ... __NR_syscall_max] = &__x64_sys_ni_syscall,
 #include <asm/syscalls_64.h>
 };
 
@@ -40,7 +46,7 @@ asmlinkage const sys_call_ptr_t x32_sys_call_table[__NR_syscall_x32_max+1] = {
 	 * Smells like a compiler bug -- it doesn't work
 	 * when the & below is removed.
 	 */
-	[0 ... __NR_syscall_x32_max] = &sys_ni_syscall,
+	[0 ... __NR_syscall_x32_max] = &__x64_sys_ni_syscall,
 #include <asm/syscalls_64.h>
 };
 
diff --git a/arch/x86/entry/syscalls/syscall_32.tbl b/arch/x86/entry/syscalls/syscall_32.tbl
index 3fe02546aed3..15908eb9b17e 100644
--- a/arch/x86/entry/syscalls/syscall_32.tbl
+++ b/arch/x86/entry/syscalls/syscall_32.tbl
@@ -124,13 +124,13 @@
 110	i386	iopl			sys_iopl			__ia32_sys_iopl
 111	i386	vhangup			sys_vhangup			__ia32_sys_vhangup
 112	i386	idle
-113	i386	vm86old			sys_vm86old			sys_ni_syscall
+113	i386	vm86old			sys_vm86old			__ia32_sys_ni_syscall
 114	i386	wait4			sys_wait4			__ia32_compat_sys_wait4
 115	i386	swapoff			sys_swapoff			__ia32_sys_swapoff
 116	i386	sysinfo			sys_sysinfo			__ia32_compat_sys_sysinfo
 117	i386	ipc			sys_ipc				__ia32_compat_sys_ipc
 118	i386	fsync			sys_fsync			__ia32_sys_fsync
-119	i386	sigreturn		sys_sigreturn			sys32_sigreturn
+119	i386	sigreturn		sys_sigreturn			__ia32_compat_sys_sigreturn
 120	i386	clone			sys_clone			__ia32_compat_sys_x86_clone
 121	i386	setdomainname		sys_setdomainname		__ia32_sys_setdomainname
 122	i386	uname			sys_newuname			__ia32_sys_newuname
@@ -177,14 +177,14 @@
 163	i386	mremap			sys_mremap			__ia32_sys_mremap
 164	i386	setresuid		sys_setresuid16			__ia32_sys_setresuid16
 165	i386	getresuid		sys_getresuid16			__ia32_sys_getresuid16
-166	i386	vm86			sys_vm86			sys_ni_syscall
+166	i386	vm86			sys_vm86			__ia32_sys_ni_syscall
 167	i386	query_module
 168	i386	poll			sys_poll			__ia32_sys_poll
 169	i386	nfsservctl
 170	i386	setresgid		sys_setresgid16			__ia32_sys_setresgid16
 171	i386	getresgid		sys_getresgid16			__ia32_sys_getresgid16
 172	i386	prctl			sys_prctl			__ia32_sys_prctl
-173	i386	rt_sigreturn		sys_rt_sigreturn		sys32_rt_sigreturn
+173	i386	rt_sigreturn		sys_rt_sigreturn		__ia32_compat_sys_rt_sigreturn
 174	i386	rt_sigaction		sys_rt_sigaction		__ia32_compat_sys_rt_sigaction
 175	i386	rt_sigprocmask		sys_rt_sigprocmask		__ia32_compat_sys_rt_sigprocmask
 176	i386	rt_sigpending		sys_rt_sigpending		__ia32_compat_sys_rt_sigpending
diff --git a/arch/x86/entry/thunk_32.S b/arch/x86/entry/thunk_32.S
index 2713490611a3..e010d4ae11f1 100644
--- a/arch/x86/entry/thunk_32.S
+++ b/arch/x86/entry/thunk_32.S
@@ -10,8 +10,7 @@
 
 	/* put return address in eax (arg1) */
 	.macro THUNK name, func, put_ret_addr_in_eax=0
-	.globl \name
-\name:
+SYM_CODE_START_NOALIGN(\name)
 	pushl %eax
 	pushl %ecx
 	pushl %edx
@@ -27,6 +26,7 @@
 	popl %eax
 	ret
 	_ASM_NOKPROBE(\name)
+SYM_CODE_END(\name)
 	.endm
 
 #ifdef CONFIG_TRACE_IRQFLAGS
diff --git a/arch/x86/entry/thunk_64.S b/arch/x86/entry/thunk_64.S
index ea5c4167086c..c5c3b6e86e62 100644
--- a/arch/x86/entry/thunk_64.S
+++ b/arch/x86/entry/thunk_64.S
@@ -12,7 +12,7 @@
 
 	/* rdi:	arg1 ... normal C conventions. rax is saved/restored. */
 	.macro THUNK name, func, put_ret_addr_in_rdi=0
-	ENTRY(\name)
+SYM_FUNC_START_NOALIGN(\name)
 	pushq %rbp
 	movq %rsp, %rbp
 
@@ -33,7 +33,7 @@
 
 	call \func
 	jmp  .L_restore
-	ENDPROC(\name)
+SYM_FUNC_END(\name)
 	_ASM_NOKPROBE(\name)
 	.endm
 
@@ -56,7 +56,7 @@
 #if defined(CONFIG_TRACE_IRQFLAGS) \
  || defined(CONFIG_DEBUG_LOCK_ALLOC) \
  || defined(CONFIG_PREEMPTION)
-.L_restore:
+SYM_CODE_START_LOCAL_NOALIGN(.L_restore)
 	popq %r11
 	popq %r10
 	popq %r9
@@ -69,4 +69,5 @@
 	popq %rbp
 	ret
 	_ASM_NOKPROBE(.L_restore)
+SYM_CODE_END(.L_restore)
 #endif
diff --git a/arch/x86/entry/vdso/Makefile b/arch/x86/entry/vdso/Makefile
index 0f2154106d01..2b75e80f6b41 100644
--- a/arch/x86/entry/vdso/Makefile
+++ b/arch/x86/entry/vdso/Makefile
@@ -87,11 +87,9 @@ $(vobjs): KBUILD_CFLAGS := $(filter-out $(GCC_PLUGINS_CFLAGS) $(RETPOLINE_CFLAGS
 #
 # vDSO code runs in userspace and -pg doesn't help with profiling anyway.
 #
-CFLAGS_REMOVE_vdso-note.o = -pg
 CFLAGS_REMOVE_vclock_gettime.o = -pg
 CFLAGS_REMOVE_vdso32/vclock_gettime.o = -pg
 CFLAGS_REMOVE_vgetcpu.o = -pg
-CFLAGS_REMOVE_vvar.o = -pg
 
 #
 # X32 processes use x32 vDSO to access 64bit kernel data.
diff --git a/arch/x86/entry/vdso/vdso32/system_call.S b/arch/x86/entry/vdso/vdso32/system_call.S
index 263d7433dea8..de1fff7188aa 100644
--- a/arch/x86/entry/vdso/vdso32/system_call.S
+++ b/arch/x86/entry/vdso/vdso32/system_call.S
@@ -62,7 +62,7 @@ __kernel_vsyscall:
 
 	/* Enter using int $0x80 */
 	int	$0x80
-GLOBAL(int80_landing_pad)
+SYM_INNER_LABEL(int80_landing_pad, SYM_L_GLOBAL)
 
 	/*
 	 * Restore EDX and ECX in case they were clobbered.  EBP is not
diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c
index 6e3f0c18908e..9a89d98c55bd 100644
--- a/arch/x86/events/core.c
+++ b/arch/x86/events/core.c
@@ -49,6 +49,7 @@ DEFINE_PER_CPU(struct cpu_hw_events, cpu_hw_events) = {
 	.enabled = 1,
 };
 
+DEFINE_STATIC_KEY_FALSE(rdpmc_never_available_key);
 DEFINE_STATIC_KEY_FALSE(rdpmc_always_available_key);
 
 u64 __read_mostly hw_cache_event_ids
@@ -2181,21 +2182,26 @@ static ssize_t set_attr_rdpmc(struct device *cdev,
 	if (x86_pmu.attr_rdpmc_broken)
 		return -ENOTSUPP;
 
-	if ((val == 2) != (x86_pmu.attr_rdpmc == 2)) {
+	if (val != x86_pmu.attr_rdpmc) {
 		/*
-		 * Changing into or out of always available, aka
-		 * perf-event-bypassing mode.  This path is extremely slow,
+		 * Changing into or out of never available or always available,
+		 * aka perf-event-bypassing mode. This path is extremely slow,
 		 * but only root can trigger it, so it's okay.
 		 */
+		if (val == 0)
+			static_branch_inc(&rdpmc_never_available_key);
+		else if (x86_pmu.attr_rdpmc == 0)
+			static_branch_dec(&rdpmc_never_available_key);
+
 		if (val == 2)
 			static_branch_inc(&rdpmc_always_available_key);
-		else
+		else if (x86_pmu.attr_rdpmc == 2)
 			static_branch_dec(&rdpmc_always_available_key);
+
 		on_each_cpu(refresh_pce, NULL, 1);
+		x86_pmu.attr_rdpmc = val;
 	}
 
-	x86_pmu.attr_rdpmc = val;
-
 	return count;
 }
 
diff --git a/arch/x86/hyperv/hv_apic.c b/arch/x86/hyperv/hv_apic.c
index e01078e93dd3..40e0e322161d 100644
--- a/arch/x86/hyperv/hv_apic.c
+++ b/arch/x86/hyperv/hv_apic.c
@@ -194,10 +194,20 @@ do_ex_hypercall:
 
 static bool __send_ipi_one(int cpu, int vector)
 {
-	struct cpumask mask = CPU_MASK_NONE;
+	int vp = hv_cpu_number_to_vp_number(cpu);
 
-	cpumask_set_cpu(cpu, &mask);
-	return __send_ipi_mask(&mask, vector);
+	trace_hyperv_send_ipi_one(cpu, vector);
+
+	if (!hv_hypercall_pg || (vp == VP_INVAL))
+		return false;
+
+	if ((vector < HV_IPI_LOW_VECTOR) || (vector > HV_IPI_HIGH_VECTOR))
+		return false;
+
+	if (vp >= 64)
+		return __send_ipi_mask_ex(cpumask_of(cpu), vector);
+
+	return !hv_do_fast_hypercall16(HVCALL_SEND_IPI, vector, BIT_ULL(vp));
 }
 
 static void hv_send_ipi(int cpu, int vector)
diff --git a/arch/x86/hyperv/hv_init.c b/arch/x86/hyperv/hv_init.c
index 2db3972c0e0f..50ff030d9224 100644
--- a/arch/x86/hyperv/hv_init.c
+++ b/arch/x86/hyperv/hv_init.c
@@ -311,6 +311,12 @@ void __init hyperv_init(void)
 	hypercall_msr.guest_physical_address = vmalloc_to_pfn(hv_hypercall_pg);
 	wrmsrl(HV_X64_MSR_HYPERCALL, hypercall_msr.as_uint64);
 
+	/*
+	 * Ignore any errors in setting up stimer clockevents
+	 * as we can run with the LAPIC timer as a fallback.
+	 */
+	(void)hv_stimer_alloc();
+
 	hv_apic_init();
 
 	x86_init.pci.arch_init = hv_pci_init;
diff --git a/arch/x86/ia32/ia32_signal.c b/arch/x86/ia32/ia32_signal.c
index 1cee10091b9f..30416d7f19d4 100644
--- a/arch/x86/ia32/ia32_signal.c
+++ b/arch/x86/ia32/ia32_signal.c
@@ -21,6 +21,7 @@
 #include <linux/personality.h>
 #include <linux/compat.h>
 #include <linux/binfmts.h>
+#include <linux/syscalls.h>
 #include <asm/ucontext.h>
 #include <linux/uaccess.h>
 #include <asm/fpu/internal.h>
@@ -118,7 +119,7 @@ static int ia32_restore_sigcontext(struct pt_regs *regs,
 	return err;
 }
 
-asmlinkage long sys32_sigreturn(void)
+COMPAT_SYSCALL_DEFINE0(sigreturn)
 {
 	struct pt_regs *regs = current_pt_regs();
 	struct sigframe_ia32 __user *frame = (struct sigframe_ia32 __user *)(regs->sp-8);
@@ -144,7 +145,7 @@ badframe:
 	return 0;
 }
 
-asmlinkage long sys32_rt_sigreturn(void)
+COMPAT_SYSCALL_DEFINE0(rt_sigreturn)
 {
 	struct pt_regs *regs = current_pt_regs();
 	struct rt_sigframe_ia32 __user *frame;
diff --git a/arch/x86/include/asm/asm.h b/arch/x86/include/asm/asm.h
index 1b563f9167ea..cd339b88d5d4 100644
--- a/arch/x86/include/asm/asm.h
+++ b/arch/x86/include/asm/asm.h
@@ -141,9 +141,6 @@
 # define _ASM_EXTABLE_EX(from, to)				\
 	_ASM_EXTABLE_HANDLE(from, to, ex_handler_ext)
 
-# define _ASM_EXTABLE_REFCOUNT(from, to)			\
-	_ASM_EXTABLE_HANDLE(from, to, ex_handler_refcount)
-
 # define _ASM_NOKPROBE(entry)					\
 	.pushsection "_kprobe_blacklist","aw" ;			\
 	_ASM_ALIGN ;						\
@@ -172,9 +169,6 @@
 # define _ASM_EXTABLE_EX(from, to)				\
 	_ASM_EXTABLE_HANDLE(from, to, ex_handler_ext)
 
-# define _ASM_EXTABLE_REFCOUNT(from, to)			\
-	_ASM_EXTABLE_HANDLE(from, to, ex_handler_refcount)
-
 /* For C file, we already have NOKPROBE_SYMBOL macro */
 #endif
 
diff --git a/arch/x86/include/asm/calgary.h b/arch/x86/include/asm/calgary.h
deleted file mode 100644
index facd374a1bf7..000000000000
--- a/arch/x86/include/asm/calgary.h
+++ /dev/null
@@ -1,57 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-or-later */
-/*
- * Derived from include/asm-powerpc/iommu.h
- *
- * Copyright IBM Corporation, 2006-2007
- *
- * Author: Jon Mason <jdmason@us.ibm.com>
- * Author: Muli Ben-Yehuda <muli@il.ibm.com>
- */
-
-#ifndef _ASM_X86_CALGARY_H
-#define _ASM_X86_CALGARY_H
-
-#include <linux/spinlock.h>
-#include <linux/device.h>
-#include <linux/dma-mapping.h>
-#include <linux/timer.h>
-#include <asm/types.h>
-
-struct iommu_table {
-	const struct cal_chipset_ops *chip_ops; /* chipset specific funcs */
-	unsigned long  it_base;      /* mapped address of tce table */
-	unsigned long  it_hint;      /* Hint for next alloc */
-	unsigned long *it_map;       /* A simple allocation bitmap for now */
-	void __iomem  *bbar;         /* Bridge BAR */
-	u64	       tar_val;      /* Table Address Register */
-	struct timer_list watchdog_timer;
-	spinlock_t     it_lock;      /* Protects it_map */
-	unsigned int   it_size;      /* Size of iommu table in entries */
-	unsigned char  it_busno;     /* Bus number this table belongs to */
-};
-
-struct cal_chipset_ops {
-	void (*handle_quirks)(struct iommu_table *tbl, struct pci_dev *dev);
-	void (*tce_cache_blast)(struct iommu_table *tbl);
-	void (*dump_error_regs)(struct iommu_table *tbl);
-};
-
-#define TCE_TABLE_SIZE_UNSPECIFIED	~0
-#define TCE_TABLE_SIZE_64K		0
-#define TCE_TABLE_SIZE_128K		1
-#define TCE_TABLE_SIZE_256K		2
-#define TCE_TABLE_SIZE_512K		3
-#define TCE_TABLE_SIZE_1M		4
-#define TCE_TABLE_SIZE_2M		5
-#define TCE_TABLE_SIZE_4M		6
-#define TCE_TABLE_SIZE_8M		7
-
-extern int use_calgary;
-
-#ifdef CONFIG_CALGARY_IOMMU
-extern int detect_calgary(void);
-#else
-static inline int detect_calgary(void) { return -ENODEV; }
-#endif
-
-#endif /* _ASM_X86_CALGARY_H */
diff --git a/arch/x86/include/asm/cpu_entry_area.h b/arch/x86/include/asm/cpu_entry_area.h
index 8348f7d69fd5..ea866c7bf31d 100644
--- a/arch/x86/include/asm/cpu_entry_area.h
+++ b/arch/x86/include/asm/cpu_entry_area.h
@@ -78,8 +78,12 @@ struct cpu_entry_area {
 
 	/*
 	 * The GDT is just below entry_stack and thus serves (on x86_64) as
-	 * a a read-only guard page.
+	 * a read-only guard page. On 32-bit the GDT must be writeable, so
+	 * it needs an extra guard page.
 	 */
+#ifdef CONFIG_X86_32
+	char guard_entry_stack[PAGE_SIZE];
+#endif
 	struct entry_stack_page entry_stack_page;
 
 	/*
@@ -94,7 +98,6 @@ struct cpu_entry_area {
 	 */
 	struct cea_exception_stacks estacks;
 #endif
-#ifdef CONFIG_CPU_SUP_INTEL
 	/*
 	 * Per CPU debug store for Intel performance monitoring. Wastes a
 	 * full page at the moment.
@@ -105,11 +108,13 @@ struct cpu_entry_area {
 	 * Reserve enough fixmap PTEs.
 	 */
 	struct debug_store_buffers cpu_debug_buffers;
-#endif
 };
 
-#define CPU_ENTRY_AREA_SIZE	(sizeof(struct cpu_entry_area))
-#define CPU_ENTRY_AREA_TOT_SIZE	(CPU_ENTRY_AREA_SIZE * NR_CPUS)
+#define CPU_ENTRY_AREA_SIZE		(sizeof(struct cpu_entry_area))
+#define CPU_ENTRY_AREA_ARRAY_SIZE	(CPU_ENTRY_AREA_SIZE * NR_CPUS)
+
+/* Total size includes the readonly IDT mapping page as well: */
+#define CPU_ENTRY_AREA_TOTAL_SIZE	(CPU_ENTRY_AREA_ARRAY_SIZE + PAGE_SIZE)
 
 DECLARE_PER_CPU(struct cpu_entry_area *, cpu_entry_area);
 DECLARE_PER_CPU(struct cea_exception_stacks *, cea_exception_stacks);
@@ -117,13 +122,14 @@ DECLARE_PER_CPU(struct cea_exception_stacks *, cea_exception_stacks);
 extern void setup_cpu_entry_areas(void);
 extern void cea_set_pte(void *cea_vaddr, phys_addr_t pa, pgprot_t flags);
 
+/* Single page reserved for the readonly IDT mapping: */
 #define	CPU_ENTRY_AREA_RO_IDT		CPU_ENTRY_AREA_BASE
 #define CPU_ENTRY_AREA_PER_CPU		(CPU_ENTRY_AREA_RO_IDT + PAGE_SIZE)
 
 #define CPU_ENTRY_AREA_RO_IDT_VADDR	((void *)CPU_ENTRY_AREA_RO_IDT)
 
 #define CPU_ENTRY_AREA_MAP_SIZE			\
-	(CPU_ENTRY_AREA_PER_CPU + CPU_ENTRY_AREA_TOT_SIZE - CPU_ENTRY_AREA_BASE)
+	(CPU_ENTRY_AREA_PER_CPU + CPU_ENTRY_AREA_ARRAY_SIZE - CPU_ENTRY_AREA_BASE)
 
 extern struct cpu_entry_area *get_cpu_entry_area(int cpu);
 
diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h
index c4fbe379cc0b..e9b62498fe75 100644
--- a/arch/x86/include/asm/cpufeatures.h
+++ b/arch/x86/include/asm/cpufeatures.h
@@ -292,6 +292,7 @@
 #define X86_FEATURE_CLZERO		(13*32+ 0) /* CLZERO instruction */
 #define X86_FEATURE_IRPERF		(13*32+ 1) /* Instructions Retired Count */
 #define X86_FEATURE_XSAVEERPTR		(13*32+ 2) /* Always save/restore FP error pointers */
+#define X86_FEATURE_RDPRU		(13*32+ 4) /* Read processor register at user level */
 #define X86_FEATURE_WBNOINVD		(13*32+ 9) /* WBNOINVD instruction */
 #define X86_FEATURE_AMD_IBPB		(13*32+12) /* "" Indirect Branch Prediction Barrier */
 #define X86_FEATURE_AMD_IBRS		(13*32+14) /* "" Indirect Branch Restricted Speculation */
diff --git a/arch/x86/include/asm/crash.h b/arch/x86/include/asm/crash.h
index 0acf5ee45a21..f58de66091e5 100644
--- a/arch/x86/include/asm/crash.h
+++ b/arch/x86/include/asm/crash.h
@@ -2,10 +2,17 @@
 #ifndef _ASM_X86_CRASH_H
 #define _ASM_X86_CRASH_H
 
+struct kimage;
+
 int crash_load_segments(struct kimage *image);
-int crash_copy_backup_region(struct kimage *image);
 int crash_setup_memmap_entries(struct kimage *image,
 		struct boot_params *params);
 void crash_smp_send_stop(void);
 
+#ifdef CONFIG_KEXEC_CORE
+void __init crash_reserve_low_1M(void);
+#else
+static inline void __init crash_reserve_low_1M(void) { }
+#endif
+
 #endif /* _ASM_X86_CRASH_H */
diff --git a/arch/x86/include/asm/disabled-features.h b/arch/x86/include/asm/disabled-features.h
index a5ea841cc6d2..8e1d0bb46361 100644
--- a/arch/x86/include/asm/disabled-features.h
+++ b/arch/x86/include/asm/disabled-features.h
@@ -22,7 +22,7 @@
 # define DISABLE_SMAP	(1<<(X86_FEATURE_SMAP & 31))
 #endif
 
-#ifdef CONFIG_X86_INTEL_UMIP
+#ifdef CONFIG_X86_UMIP
 # define DISABLE_UMIP	0
 #else
 # define DISABLE_UMIP	(1<<(X86_FEATURE_UMIP & 31))
diff --git a/arch/x86/include/asm/e820/types.h b/arch/x86/include/asm/e820/types.h
index c3aa4b5e49e2..314f75d886d0 100644
--- a/arch/x86/include/asm/e820/types.h
+++ b/arch/x86/include/asm/e820/types.h
@@ -29,6 +29,14 @@ enum e820_type {
 	E820_TYPE_PRAM		= 12,
 
 	/*
+	 * Special-purpose memory is indicated to the system via the
+	 * EFI_MEMORY_SP attribute. Define an e820 translation of this
+	 * memory type for the purpose of reserving this range and
+	 * marking it with the IORES_DESC_SOFT_RESERVED designation.
+	 */
+	E820_TYPE_SOFT_RESERVED	= 0xefffffff,
+
+	/*
 	 * Reserved RAM used by the kernel itself if
 	 * CONFIG_INTEL_TXT=y is enabled, memory of this type
 	 * will be included in the S3 integrity calculation
diff --git a/arch/x86/include/asm/efi.h b/arch/x86/include/asm/efi.h
index 43a82e59c59d..d028e9acdf1c 100644
--- a/arch/x86/include/asm/efi.h
+++ b/arch/x86/include/asm/efi.h
@@ -140,7 +140,6 @@ extern void efi_delete_dummy_variable(void);
 extern void efi_switch_mm(struct mm_struct *mm);
 extern void efi_recover_from_page_fault(unsigned long phys_addr);
 extern void efi_free_boot_services(void);
-extern void efi_reserve_boot_services(void);
 
 struct efi_setup_data {
 	u64 fw_vendor;
@@ -244,6 +243,8 @@ static inline bool efi_is_64bit(void)
 extern bool efi_reboot_required(void);
 extern bool efi_is_table_address(unsigned long phys_addr);
 
+extern void efi_find_mirror(void);
+extern void efi_reserve_boot_services(void);
 #else
 static inline void parse_efi_setup(u64 phys_addr, u32 data_len) {}
 static inline bool efi_reboot_required(void)
@@ -254,6 +255,20 @@ static inline  bool efi_is_table_address(unsigned long phys_addr)
 {
 	return false;
 }
+static inline void efi_find_mirror(void)
+{
+}
+static inline void efi_reserve_boot_services(void)
+{
+}
 #endif /* CONFIG_EFI */
 
+#ifdef CONFIG_EFI_FAKE_MEMMAP
+extern void __init efi_fake_memmap_early(void);
+#else
+static inline void efi_fake_memmap_early(void)
+{
+}
+#endif
+
 #endif /* _ASM_X86_EFI_H */
diff --git a/arch/x86/include/asm/fixmap.h b/arch/x86/include/asm/fixmap.h
index 0c47aa82e2e2..28183ee3cc42 100644
--- a/arch/x86/include/asm/fixmap.h
+++ b/arch/x86/include/asm/fixmap.h
@@ -156,7 +156,7 @@ extern pte_t *kmap_pte;
 extern pte_t *pkmap_page_table;
 
 void __native_set_fixmap(enum fixed_addresses idx, pte_t pte);
-void native_set_fixmap(enum fixed_addresses idx,
+void native_set_fixmap(unsigned /* enum fixed_addresses */ idx,
 		       phys_addr_t phys, pgprot_t flags);
 
 #ifndef CONFIG_PARAVIRT_XXL
diff --git a/arch/x86/include/asm/hyperv-tlfs.h b/arch/x86/include/asm/hyperv-tlfs.h
index 7741e211f7f5..5f10f7f2098d 100644
--- a/arch/x86/include/asm/hyperv-tlfs.h
+++ b/arch/x86/include/asm/hyperv-tlfs.h
@@ -86,6 +86,8 @@
 #define HV_X64_ACCESS_FREQUENCY_MSRS		BIT(11)
 /* AccessReenlightenmentControls privilege */
 #define HV_X64_ACCESS_REENLIGHTENMENT		BIT(13)
+/* AccessTscInvariantControls privilege */
+#define HV_X64_ACCESS_TSC_INVARIANT		BIT(15)
 
 /*
  * Feature identification: indicates which flags were specified at partition
@@ -278,6 +280,9 @@
 #define HV_X64_MSR_TSC_EMULATION_CONTROL	0x40000107
 #define HV_X64_MSR_TSC_EMULATION_STATUS		0x40000108
 
+/* TSC invariant control */
+#define HV_X64_MSR_TSC_INVARIANT_CONTROL	0x40000118
+
 /*
  * Declare the MSR used to setup pages used to communicate with the hypervisor.
  */
diff --git a/arch/x86/include/asm/io_bitmap.h b/arch/x86/include/asm/io_bitmap.h
new file mode 100644
index 000000000000..02c6ef8f7667
--- /dev/null
+++ b/arch/x86/include/asm/io_bitmap.h
@@ -0,0 +1,29 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_X86_IOBITMAP_H
+#define _ASM_X86_IOBITMAP_H
+
+#include <linux/refcount.h>
+#include <asm/processor.h>
+
+struct io_bitmap {
+	u64		sequence;
+	refcount_t	refcnt;
+	/* The maximum number of bytes to copy so all zero bits are covered */
+	unsigned int	max;
+	unsigned long	bitmap[IO_BITMAP_LONGS];
+};
+
+struct task_struct;
+
+#ifdef CONFIG_X86_IOPL_IOPERM
+void io_bitmap_share(struct task_struct *tsk);
+void io_bitmap_exit(void);
+
+void tss_update_io_bitmap(void);
+#else
+static inline void io_bitmap_share(struct task_struct *tsk) { }
+static inline void io_bitmap_exit(void) { }
+static inline void tss_update_io_bitmap(void) { }
+#endif
+
+#endif
diff --git a/arch/x86/include/asm/kexec.h b/arch/x86/include/asm/kexec.h
index 5e7d6b46de97..6802c59e8252 100644
--- a/arch/x86/include/asm/kexec.h
+++ b/arch/x86/include/asm/kexec.h
@@ -66,10 +66,6 @@ struct kimage;
 # define KEXEC_ARCH KEXEC_ARCH_X86_64
 #endif
 
-/* Memory to backup during crash kdump */
-#define KEXEC_BACKUP_SRC_START	(0UL)
-#define KEXEC_BACKUP_SRC_END	(640 * 1024UL - 1)	/* 640K */
-
 /*
  * This function is responsible for capturing register states if coming
  * via panic otherwise just fix up the ss and sp if coming via kernel
@@ -154,12 +150,6 @@ struct kimage_arch {
 	pud_t *pud;
 	pmd_t *pmd;
 	pte_t *pte;
-	/* Details of backup region */
-	unsigned long backup_src_start;
-	unsigned long backup_src_sz;
-
-	/* Physical address of backup segment */
-	unsigned long backup_load_addr;
 
 	/* Core ELF header buffer */
 	void *elf_headers;
diff --git a/arch/x86/include/asm/linkage.h b/arch/x86/include/asm/linkage.h
index 14caa9d9fb7f..365111789cc6 100644
--- a/arch/x86/include/asm/linkage.h
+++ b/arch/x86/include/asm/linkage.h
@@ -13,10 +13,6 @@
 
 #ifdef __ASSEMBLY__
 
-#define GLOBAL(name)	\
-	.globl name;	\
-	name:
-
 #if defined(CONFIG_X86_64) || defined(CONFIG_X86_ALIGNMENT_16)
 #define __ALIGN		.p2align 4, 0x90
 #define __ALIGN_STR	__stringify(__ALIGN)
diff --git a/arch/x86/include/asm/mmu_context.h b/arch/x86/include/asm/mmu_context.h
index 16ae821483c8..5f33924e200f 100644
--- a/arch/x86/include/asm/mmu_context.h
+++ b/arch/x86/include/asm/mmu_context.h
@@ -26,12 +26,14 @@ static inline void paravirt_activate_mm(struct mm_struct *prev,
 
 #ifdef CONFIG_PERF_EVENTS
 
+DECLARE_STATIC_KEY_FALSE(rdpmc_never_available_key);
 DECLARE_STATIC_KEY_FALSE(rdpmc_always_available_key);
 
 static inline void load_mm_cr4_irqsoff(struct mm_struct *mm)
 {
 	if (static_branch_unlikely(&rdpmc_always_available_key) ||
-	    atomic_read(&mm->context.perf_rdpmc_allowed))
+	    (!static_branch_unlikely(&rdpmc_never_available_key) &&
+	     atomic_read(&mm->context.perf_rdpmc_allowed)))
 		cr4_set_bits_irqsoff(X86_CR4_PCE);
 	else
 		cr4_clear_bits_irqsoff(X86_CR4_PCE);
diff --git a/arch/x86/include/asm/module.h b/arch/x86/include/asm/module.h
index 7948a17febb4..c215d2762488 100644
--- a/arch/x86/include/asm/module.h
+++ b/arch/x86/include/asm/module.h
@@ -15,6 +15,8 @@ struct mod_arch_specific {
 
 #ifdef CONFIG_X86_64
 /* X86_64 does not define MODULE_PROC_FAMILY */
+#elif defined CONFIG_M486SX
+#define MODULE_PROC_FAMILY "486SX "
 #elif defined CONFIG_M486
 #define MODULE_PROC_FAMILY "486 "
 #elif defined CONFIG_M586
diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h
index 69089d46f128..86e7317eb31f 100644
--- a/arch/x86/include/asm/paravirt.h
+++ b/arch/x86/include/asm/paravirt.h
@@ -294,10 +294,6 @@ static inline void write_idt_entry(gate_desc *dt, int entry, const gate_desc *g)
 {
 	PVOP_VCALL3(cpu.write_idt_entry, dt, entry, g);
 }
-static inline void set_iopl_mask(unsigned mask)
-{
-	PVOP_VCALL1(cpu.set_iopl_mask, mask);
-}
 
 static inline void paravirt_activate_mm(struct mm_struct *prev,
 					struct mm_struct *next)
diff --git a/arch/x86/include/asm/paravirt_types.h b/arch/x86/include/asm/paravirt_types.h
index 70b654f3ffe5..84812964d3dd 100644
--- a/arch/x86/include/asm/paravirt_types.h
+++ b/arch/x86/include/asm/paravirt_types.h
@@ -140,8 +140,6 @@ struct pv_cpu_ops {
 
 	void (*load_sp0)(unsigned long sp0);
 
-	void (*set_iopl_mask)(unsigned mask);
-
 	void (*wbinvd)(void);
 
 	/* cpuid emulation, mostly so that caps bits can be disabled */
diff --git a/arch/x86/include/asm/pci.h b/arch/x86/include/asm/pci.h
index e662f987dfa2..90d0731fdcb6 100644
--- a/arch/x86/include/asm/pci.h
+++ b/arch/x86/include/asm/pci.h
@@ -12,8 +12,6 @@
 #include <asm/pat.h>
 #include <asm/x86_init.h>
 
-#ifdef __KERNEL__
-
 struct pci_sysdata {
 	int		domain;		/* PCI domain */
 	int		node;		/* NUMA node */
@@ -118,11 +116,6 @@ void native_restore_msi_irqs(struct pci_dev *dev);
 #define native_setup_msi_irqs		NULL
 #define native_teardown_msi_irq		NULL
 #endif
-#endif  /* __KERNEL__ */
-
-#ifdef CONFIG_X86_64
-#include <asm/pci_64.h>
-#endif
 
 /* generic pci stuff */
 #include <asm-generic/pci.h>
diff --git a/arch/x86/include/asm/pci_64.h b/arch/x86/include/asm/pci_64.h
deleted file mode 100644
index f5411de0ae11..000000000000
--- a/arch/x86/include/asm/pci_64.h
+++ /dev/null
@@ -1,28 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _ASM_X86_PCI_64_H
-#define _ASM_X86_PCI_64_H
-
-#ifdef __KERNEL__
-
-#ifdef CONFIG_CALGARY_IOMMU
-static inline void *pci_iommu(struct pci_bus *bus)
-{
-	struct pci_sysdata *sd = bus->sysdata;
-	return sd->iommu;
-}
-
-static inline void set_pci_iommu(struct pci_bus *bus, void *val)
-{
-	struct pci_sysdata *sd = bus->sysdata;
-	sd->iommu = val;
-}
-#endif /* CONFIG_CALGARY_IOMMU */
-
-extern int (*pci_config_read)(int seg, int bus, int dev, int fn,
-			      int reg, int len, u32 *value);
-extern int (*pci_config_write)(int seg, int bus, int dev, int fn,
-			       int reg, int len, u32 value);
-
-#endif /* __KERNEL__ */
-
-#endif /* _ASM_X86_PCI_64_H */
diff --git a/arch/x86/include/asm/pgtable-3level.h b/arch/x86/include/asm/pgtable-3level.h
index e3633795fb22..5afb5e0fe903 100644
--- a/arch/x86/include/asm/pgtable-3level.h
+++ b/arch/x86/include/asm/pgtable-3level.h
@@ -36,39 +36,41 @@ static inline void native_set_pte(pte_t *ptep, pte_t pte)
 
 #define pmd_read_atomic pmd_read_atomic
 /*
- * pte_offset_map_lock on 32bit PAE kernels was reading the pmd_t with
- * a "*pmdp" dereference done by gcc. Problem is, in certain places
- * where pte_offset_map_lock is called, concurrent page faults are
+ * pte_offset_map_lock() on 32-bit PAE kernels was reading the pmd_t with
+ * a "*pmdp" dereference done by GCC. Problem is, in certain places
+ * where pte_offset_map_lock() is called, concurrent page faults are
  * allowed, if the mmap_sem is hold for reading. An example is mincore
  * vs page faults vs MADV_DONTNEED. On the page fault side
- * pmd_populate rightfully does a set_64bit, but if we're reading the
+ * pmd_populate() rightfully does a set_64bit(), but if we're reading the
  * pmd_t with a "*pmdp" on the mincore side, a SMP race can happen
- * because gcc will not read the 64bit of the pmd atomically. To fix
- * this all places running pmd_offset_map_lock() while holding the
+ * because GCC will not read the 64-bit value of the pmd atomically.
+ *
+ * To fix this all places running pte_offset_map_lock() while holding the
  * mmap_sem in read mode, shall read the pmdp pointer using this
- * function to know if the pmd is null nor not, and in turn to know if
- * they can run pmd_offset_map_lock or pmd_trans_huge or other pmd
+ * function to know if the pmd is null or not, and in turn to know if
+ * they can run pte_offset_map_lock() or pmd_trans_huge() or other pmd
  * operations.
  *
- * Without THP if the mmap_sem is hold for reading, the pmd can only
- * transition from null to not null while pmd_read_atomic runs. So
+ * Without THP if the mmap_sem is held for reading, the pmd can only
+ * transition from null to not null while pmd_read_atomic() runs. So
  * we can always return atomic pmd values with this function.
  *
- * With THP if the mmap_sem is hold for reading, the pmd can become
+ * With THP if the mmap_sem is held for reading, the pmd can become
  * trans_huge or none or point to a pte (and in turn become "stable")
- * at any time under pmd_read_atomic. We could read it really
- * atomically here with a atomic64_read for the THP enabled case (and
+ * at any time under pmd_read_atomic(). We could read it truly
+ * atomically here with an atomic64_read() for the THP enabled case (and
  * it would be a whole lot simpler), but to avoid using cmpxchg8b we
  * only return an atomic pmdval if the low part of the pmdval is later
- * found stable (i.e. pointing to a pte). And we're returning a none
- * pmdval if the low part of the pmd is none. In some cases the high
- * and low part of the pmdval returned may not be consistent if THP is
- * enabled (the low part may point to previously mapped hugepage,
- * while the high part may point to a more recently mapped hugepage),
- * but pmd_none_or_trans_huge_or_clear_bad() only needs the low part
- * of the pmd to be read atomically to decide if the pmd is unstable
- * or not, with the only exception of when the low part of the pmd is
- * zero in which case we return a none pmd.
+ * found to be stable (i.e. pointing to a pte). We are also returning a
+ * 'none' (zero) pmdval if the low part of the pmd is zero.
+ *
+ * In some cases the high and low part of the pmdval returned may not be
+ * consistent if THP is enabled (the low part may point to previously
+ * mapped hugepage, while the high part may point to a more recently
+ * mapped hugepage), but pmd_none_or_trans_huge_or_clear_bad() only
+ * needs the low part of the pmd to be read atomically to decide if the
+ * pmd is unstable or not, with the only exception when the low part
+ * of the pmd is zero, in which case we return a 'none' pmd.
  */
 static inline pmd_t pmd_read_atomic(pmd_t *pmdp)
 {
diff --git a/arch/x86/include/asm/pgtable_32_types.h b/arch/x86/include/asm/pgtable_32_types.h
index b0bc0fff5f1f..19f5807260c3 100644
--- a/arch/x86/include/asm/pgtable_32_types.h
+++ b/arch/x86/include/asm/pgtable_32_types.h
@@ -44,11 +44,11 @@ extern bool __vmalloc_start_set; /* set once high_memory is set */
  * Define this here and validate with BUILD_BUG_ON() in pgtable_32.c
  * to avoid include recursion hell
  */
-#define CPU_ENTRY_AREA_PAGES	(NR_CPUS * 40)
+#define CPU_ENTRY_AREA_PAGES	(NR_CPUS * 41)
 
-#define CPU_ENTRY_AREA_BASE						\
-	((FIXADDR_TOT_START - PAGE_SIZE * (CPU_ENTRY_AREA_PAGES + 1))   \
-	 & PMD_MASK)
+/* The +1 is for the readonly IDT page: */
+#define CPU_ENTRY_AREA_BASE	\
+	((FIXADDR_TOT_START - PAGE_SIZE*(CPU_ENTRY_AREA_PAGES+1)) & PMD_MASK)
 
 #define LDT_BASE_ADDR		\
 	((CPU_ENTRY_AREA_BASE - PAGE_SIZE) & PMD_MASK)
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index 54f5d54280f6..e51afbb0cbfb 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -7,6 +7,7 @@
 /* Forward declaration, a strange C thing */
 struct task_struct;
 struct mm_struct;
+struct io_bitmap;
 struct vm86;
 
 #include <asm/math_emu.h>
@@ -93,7 +94,15 @@ struct cpuinfo_x86 {
 	__u32			extended_cpuid_level;
 	/* Maximum supported CPUID level, -1=no CPUID: */
 	int			cpuid_level;
-	__u32			x86_capability[NCAPINTS + NBUGINTS];
+	/*
+	 * Align to size of unsigned long because the x86_capability array
+	 * is passed to bitops which require the alignment. Use unnamed
+	 * union to enforce the array is aligned to size of unsigned long.
+	 */
+	union {
+		__u32		x86_capability[NCAPINTS + NBUGINTS];
+		unsigned long	x86_capability_alignment;
+	};
 	char			x86_vendor_id[16];
 	char			x86_model_id[64];
 	/* in KB - valid for CPUS which support this call: */
@@ -328,10 +337,32 @@ struct x86_hw_tss {
  * IO-bitmap sizes:
  */
 #define IO_BITMAP_BITS			65536
-#define IO_BITMAP_BYTES			(IO_BITMAP_BITS/8)
-#define IO_BITMAP_LONGS			(IO_BITMAP_BYTES/sizeof(long))
-#define IO_BITMAP_OFFSET		(offsetof(struct tss_struct, io_bitmap) - offsetof(struct tss_struct, x86_tss))
-#define INVALID_IO_BITMAP_OFFSET	0x8000
+#define IO_BITMAP_BYTES			(IO_BITMAP_BITS / BITS_PER_BYTE)
+#define IO_BITMAP_LONGS			(IO_BITMAP_BYTES / sizeof(long))
+
+#define IO_BITMAP_OFFSET_VALID_MAP				\
+	(offsetof(struct tss_struct, io_bitmap.bitmap) -	\
+	 offsetof(struct tss_struct, x86_tss))
+
+#define IO_BITMAP_OFFSET_VALID_ALL				\
+	(offsetof(struct tss_struct, io_bitmap.mapall) -	\
+	 offsetof(struct tss_struct, x86_tss))
+
+#ifdef CONFIG_X86_IOPL_IOPERM
+/*
+ * sizeof(unsigned long) coming from an extra "long" at the end of the
+ * iobitmap. The limit is inclusive, i.e. the last valid byte.
+ */
+# define __KERNEL_TSS_LIMIT	\
+	(IO_BITMAP_OFFSET_VALID_ALL + IO_BITMAP_BYTES + \
+	 sizeof(unsigned long) - 1)
+#else
+# define __KERNEL_TSS_LIMIT	\
+	(offsetof(struct tss_struct, x86_tss) + sizeof(struct x86_hw_tss) - 1)
+#endif
+
+/* Base offset outside of TSS_LIMIT so unpriviledged IO causes #GP */
+#define IO_BITMAP_OFFSET_INVALID	(__KERNEL_TSS_LIMIT + 1)
 
 struct entry_stack {
 	unsigned long		words[64];
@@ -341,13 +372,21 @@ struct entry_stack_page {
 	struct entry_stack stack;
 } __aligned(PAGE_SIZE);
 
-struct tss_struct {
+/*
+ * All IO bitmap related data stored in the TSS:
+ */
+struct x86_io_bitmap {
+	/* The sequence number of the last active bitmap. */
+	u64			prev_sequence;
+
 	/*
-	 * The fixed hardware portion.  This must not cross a page boundary
-	 * at risk of violating the SDM's advice and potentially triggering
-	 * errata.
+	 * Store the dirty size of the last io bitmap offender. The next
+	 * one will have to do the cleanup as the switch out to a non io
+	 * bitmap user will just set x86_tss.io_bitmap_base to a value
+	 * outside of the TSS limit. So for sane tasks there is no need to
+	 * actually touch the io_bitmap at all.
 	 */
-	struct x86_hw_tss	x86_tss;
+	unsigned int		prev_max;
 
 	/*
 	 * The extra 1 is there because the CPU will access an
@@ -355,21 +394,28 @@ struct tss_struct {
 	 * bitmap. The extra byte must be all 1 bits, and must
 	 * be within the limit.
 	 */
-	unsigned long		io_bitmap[IO_BITMAP_LONGS + 1];
+	unsigned long		bitmap[IO_BITMAP_LONGS + 1];
+
+	/*
+	 * Special I/O bitmap to emulate IOPL(3). All bytes zero,
+	 * except the additional byte at the end.
+	 */
+	unsigned long		mapall[IO_BITMAP_LONGS + 1];
+};
+
+struct tss_struct {
+	/*
+	 * The fixed hardware portion.  This must not cross a page boundary
+	 * at risk of violating the SDM's advice and potentially triggering
+	 * errata.
+	 */
+	struct x86_hw_tss	x86_tss;
+
+	struct x86_io_bitmap	io_bitmap;
 } __aligned(PAGE_SIZE);
 
 DECLARE_PER_CPU_PAGE_ALIGNED(struct tss_struct, cpu_tss_rw);
 
-/*
- * sizeof(unsigned long) coming from an extra "long" at the end
- * of the iobitmap.
- *
- * -1? seg base+limit should be pointing to the address of the
- * last valid byte
- */
-#define __KERNEL_TSS_LIMIT	\
-	(IO_BITMAP_OFFSET + IO_BITMAP_BYTES + sizeof(unsigned long) - 1)
-
 /* Per CPU interrupt stacks */
 struct irq_stack {
 	char		stack[IRQ_STACK_SIZE];
@@ -480,10 +526,14 @@ struct thread_struct {
 	struct vm86		*vm86;
 #endif
 	/* IO permissions: */
-	unsigned long		*io_bitmap_ptr;
-	unsigned long		iopl;
-	/* Max allowed port in the bitmap, in bytes: */
-	unsigned		io_bitmap_max;
+	struct io_bitmap	*io_bitmap;
+
+	/*
+	 * IOPL. Priviledge level dependent I/O permission which is
+	 * emulated via the I/O bitmap to prevent user space from disabling
+	 * interrupts.
+	 */
+	unsigned long		iopl_emul;
 
 	mm_segment_t		addr_limit;
 
@@ -515,25 +565,6 @@ static inline void arch_thread_struct_whitelist(unsigned long *offset,
  */
 #define TS_COMPAT		0x0002	/* 32bit syscall active (64BIT)*/
 
-/*
- * Set IOPL bits in EFLAGS from given mask
- */
-static inline void native_set_iopl_mask(unsigned mask)
-{
-#ifdef CONFIG_X86_32
-	unsigned int reg;
-
-	asm volatile ("pushfl;"
-		      "popl %0;"
-		      "andl %1, %0;"
-		      "orl %2, %0;"
-		      "pushl %0;"
-		      "popfl"
-		      : "=&r" (reg)
-		      : "i" (~X86_EFLAGS_IOPL), "r" (mask));
-#endif
-}
-
 static inline void
 native_load_sp0(unsigned long sp0)
 {
@@ -573,7 +604,6 @@ static inline void load_sp0(unsigned long sp0)
 	native_load_sp0(sp0);
 }
 
-#define set_iopl_mask native_set_iopl_mask
 #endif /* CONFIG_PARAVIRT_XXL */
 
 /* Free all resources held by a thread. */
@@ -841,7 +871,6 @@ static inline void spin_lock_prefetch(const void *x)
 #define INIT_THREAD  {							  \
 	.sp0			= TOP_OF_INIT_STACK,			  \
 	.sysenter_cs		= __KERNEL_CS,				  \
-	.io_bitmap_ptr		= NULL,					  \
 	.addr_limit		= KERNEL_DS,				  \
 }
 
@@ -958,7 +987,7 @@ static inline uint32_t hypervisor_cpuid_base(const char *sig, uint32_t leaves)
 
 extern unsigned long arch_align_stack(unsigned long sp);
 void free_init_pages(const char *what, unsigned long begin, unsigned long end);
-extern void free_kernel_image_pages(void *begin, void *end);
+extern void free_kernel_image_pages(const char *what, void *begin, void *end);
 
 void default_idle(void);
 #ifdef	CONFIG_XEN
diff --git a/arch/x86/include/asm/ptrace.h b/arch/x86/include/asm/ptrace.h
index 332eb3525867..5057a8ed100b 100644
--- a/arch/x86/include/asm/ptrace.h
+++ b/arch/x86/include/asm/ptrace.h
@@ -361,5 +361,11 @@ extern int do_get_thread_area(struct task_struct *p, int idx,
 extern int do_set_thread_area(struct task_struct *p, int idx,
 			      struct user_desc __user *info, int can_allocate);
 
+#ifdef CONFIG_X86_64
+# define do_set_thread_area_64(p, s, t)	do_arch_prctl_64(p, s, t)
+#else
+# define do_set_thread_area_64(p, s, t)	(0)
+#endif
+
 #endif /* !__ASSEMBLY__ */
 #endif /* _ASM_X86_PTRACE_H */
diff --git a/arch/x86/include/asm/purgatory.h b/arch/x86/include/asm/purgatory.h
index 92c34e517da1..5528e9325049 100644
--- a/arch/x86/include/asm/purgatory.h
+++ b/arch/x86/include/asm/purgatory.h
@@ -6,16 +6,6 @@
 #include <linux/purgatory.h>
 
 extern void purgatory(void);
-/*
- * These forward declarations serve two purposes:
- *
- * 1) Make sparse happy when checking arch/purgatory
- * 2) Document that these are required to be global so the symbol
- *    lookup in kexec works
- */
-extern unsigned long purgatory_backup_dest;
-extern unsigned long purgatory_backup_src;
-extern unsigned long purgatory_backup_sz;
 #endif	/* __ASSEMBLY__ */
 
 #endif /* _ASM_PURGATORY_H */
diff --git a/arch/x86/include/asm/refcount.h b/arch/x86/include/asm/refcount.h
deleted file mode 100644
index 232f856e0db0..000000000000
--- a/arch/x86/include/asm/refcount.h
+++ /dev/null
@@ -1,126 +0,0 @@
-#ifndef __ASM_X86_REFCOUNT_H
-#define __ASM_X86_REFCOUNT_H
-/*
- * x86-specific implementation of refcount_t. Based on PAX_REFCOUNT from
- * PaX/grsecurity.
- */
-#include <linux/refcount.h>
-#include <asm/bug.h>
-
-/*
- * This is the first portion of the refcount error handling, which lives in
- * .text.unlikely, and is jumped to from the CPU flag check (in the
- * following macros). This saves the refcount value location into CX for
- * the exception handler to use (in mm/extable.c), and then triggers the
- * central refcount exception. The fixup address for the exception points
- * back to the regular execution flow in .text.
- */
-#define _REFCOUNT_EXCEPTION				\
-	".pushsection .text..refcount\n"		\
-	"111:\tlea %[var], %%" _ASM_CX "\n"		\
-	"112:\t" ASM_UD2 "\n"				\
-	ASM_UNREACHABLE					\
-	".popsection\n"					\
-	"113:\n"					\
-	_ASM_EXTABLE_REFCOUNT(112b, 113b)
-
-/* Trigger refcount exception if refcount result is negative. */
-#define REFCOUNT_CHECK_LT_ZERO				\
-	"js 111f\n\t"					\
-	_REFCOUNT_EXCEPTION
-
-/* Trigger refcount exception if refcount result is zero or negative. */
-#define REFCOUNT_CHECK_LE_ZERO				\
-	"jz 111f\n\t"					\
-	REFCOUNT_CHECK_LT_ZERO
-
-/* Trigger refcount exception unconditionally. */
-#define REFCOUNT_ERROR					\
-	"jmp 111f\n\t"					\
-	_REFCOUNT_EXCEPTION
-
-static __always_inline void refcount_add(unsigned int i, refcount_t *r)
-{
-	asm volatile(LOCK_PREFIX "addl %1,%0\n\t"
-		REFCOUNT_CHECK_LT_ZERO
-		: [var] "+m" (r->refs.counter)
-		: "ir" (i)
-		: "cc", "cx");
-}
-
-static __always_inline void refcount_inc(refcount_t *r)
-{
-	asm volatile(LOCK_PREFIX "incl %0\n\t"
-		REFCOUNT_CHECK_LT_ZERO
-		: [var] "+m" (r->refs.counter)
-		: : "cc", "cx");
-}
-
-static __always_inline void refcount_dec(refcount_t *r)
-{
-	asm volatile(LOCK_PREFIX "decl %0\n\t"
-		REFCOUNT_CHECK_LE_ZERO
-		: [var] "+m" (r->refs.counter)
-		: : "cc", "cx");
-}
-
-static __always_inline __must_check
-bool refcount_sub_and_test(unsigned int i, refcount_t *r)
-{
-	bool ret = GEN_BINARY_SUFFIXED_RMWcc(LOCK_PREFIX "subl",
-					 REFCOUNT_CHECK_LT_ZERO,
-					 r->refs.counter, e, "er", i, "cx");
-
-	if (ret) {
-		smp_acquire__after_ctrl_dep();
-		return true;
-	}
-
-	return false;
-}
-
-static __always_inline __must_check bool refcount_dec_and_test(refcount_t *r)
-{
-	bool ret = GEN_UNARY_SUFFIXED_RMWcc(LOCK_PREFIX "decl",
-					 REFCOUNT_CHECK_LT_ZERO,
-					 r->refs.counter, e, "cx");
-
-	if (ret) {
-		smp_acquire__after_ctrl_dep();
-		return true;
-	}
-
-	return false;
-}
-
-static __always_inline __must_check
-bool refcount_add_not_zero(unsigned int i, refcount_t *r)
-{
-	int c, result;
-
-	c = atomic_read(&(r->refs));
-	do {
-		if (unlikely(c == 0))
-			return false;
-
-		result = c + i;
-
-		/* Did we try to increment from/to an undesirable state? */
-		if (unlikely(c < 0 || c == INT_MAX || result < c)) {
-			asm volatile(REFCOUNT_ERROR
-				     : : [var] "m" (r->refs.counter)
-				     : "cc", "cx");
-			break;
-		}
-
-	} while (!atomic_try_cmpxchg(&(r->refs), &c, result));
-
-	return c != 0;
-}
-
-static __always_inline __must_check bool refcount_inc_not_zero(refcount_t *r)
-{
-	return refcount_add_not_zero(1, r);
-}
-
-#endif
diff --git a/arch/x86/include/asm/rio.h b/arch/x86/include/asm/rio.h
deleted file mode 100644
index 0a21986d2238..000000000000
--- a/arch/x86/include/asm/rio.h
+++ /dev/null
@@ -1,64 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-/*
- * Derived from include/asm-x86/mach-summit/mach_mpparse.h
- *          and include/asm-x86/mach-default/bios_ebda.h
- *
- * Author: Laurent Vivier <Laurent.Vivier@bull.net>
- */
-
-#ifndef _ASM_X86_RIO_H
-#define _ASM_X86_RIO_H
-
-#define RIO_TABLE_VERSION	3
-
-struct rio_table_hdr {
-	u8 version;		/* Version number of this data structure  */
-	u8 num_scal_dev;	/* # of Scalability devices               */
-	u8 num_rio_dev;		/* # of RIO I/O devices                   */
-} __attribute__((packed));
-
-struct scal_detail {
-	u8 node_id;		/* Scalability Node ID                    */
-	u32 CBAR;		/* Address of 1MB register space          */
-	u8 port0node;		/* Node ID port connected to: 0xFF=None   */
-	u8 port0port;		/* Port num port connected to: 0,1,2, or  */
-				/* 0xFF=None                              */
-	u8 port1node;		/* Node ID port connected to: 0xFF = None */
-	u8 port1port;		/* Port num port connected to: 0,1,2, or  */
-				/* 0xFF=None                              */
-	u8 port2node;		/* Node ID port connected to: 0xFF = None */
-	u8 port2port;		/* Port num port connected to: 0,1,2, or  */
-				/* 0xFF=None                              */
-	u8 chassis_num;		/* 1 based Chassis number (1 = boot node) */
-} __attribute__((packed));
-
-struct rio_detail {
-	u8 node_id;		/* RIO Node ID                            */
-	u32 BBAR;		/* Address of 1MB register space          */
-	u8 type;		/* Type of device                         */
-	u8 owner_id;		/* Node ID of Hurricane that owns this    */
-				/* node                                   */
-	u8 port0node;		/* Node ID port connected to: 0xFF=None   */
-	u8 port0port;		/* Port num port connected to: 0,1,2, or  */
-				/* 0xFF=None                              */
-	u8 port1node;		/* Node ID port connected to: 0xFF=None   */
-	u8 port1port;		/* Port num port connected to: 0,1,2, or  */
-				/* 0xFF=None                              */
-	u8 first_slot;		/* Lowest slot number below this Calgary  */
-	u8 status;		/* Bit 0 = 1 : the XAPIC is used          */
-				/*       = 0 : the XAPIC is not used, ie: */
-				/*            ints fwded to another XAPIC */
-				/*           Bits1:7 Reserved             */
-	u8 WP_index;		/* instance index - lower ones have       */
-				/*     lower slot numbers/PCI bus numbers */
-	u8 chassis_num;		/* 1 based Chassis number                 */
-} __attribute__((packed));
-
-enum {
-	HURR_SCALABILTY	= 0,	/* Hurricane Scalability info */
-	HURR_RIOIB	= 2,	/* Hurricane RIOIB info       */
-	COMPAT_CALGARY	= 4,	/* Compatibility Calgary      */
-	ALT_CALGARY	= 5,	/* Second Planar Calgary      */
-};
-
-#endif /* _ASM_X86_RIO_H */
diff --git a/arch/x86/include/asm/sections.h b/arch/x86/include/asm/sections.h
index 71b32f2570ab..036c360910c5 100644
--- a/arch/x86/include/asm/sections.h
+++ b/arch/x86/include/asm/sections.h
@@ -6,7 +6,6 @@
 #include <asm/extable.h>
 
 extern char __brk_base[], __brk_limit[];
-extern struct exception_table_entry __stop___ex_table[];
 extern char __end_rodata_aligned[];
 
 #if defined(CONFIG_X86_64)
diff --git a/arch/x86/include/asm/segment.h b/arch/x86/include/asm/segment.h
index ac3892920419..6669164abadc 100644
--- a/arch/x86/include/asm/segment.h
+++ b/arch/x86/include/asm/segment.h
@@ -31,6 +31,18 @@
  */
 #define SEGMENT_RPL_MASK	0x3
 
+/*
+ * When running on Xen PV, the actual privilege level of the kernel is 1,
+ * not 0. Testing the Requested Privilege Level in a segment selector to
+ * determine whether the context is user mode or kernel mode with
+ * SEGMENT_RPL_MASK is wrong because the PV kernel's privilege level
+ * matches the 0x3 mask.
+ *
+ * Testing with USER_SEGMENT_RPL_MASK is valid for both native and Xen PV
+ * kernels because privilege level 2 is never used.
+ */
+#define USER_SEGMENT_RPL_MASK	0x2
+
 /* User mode is privilege level 3: */
 #define USER_RPL		0x3
 
diff --git a/arch/x86/include/asm/switch_to.h b/arch/x86/include/asm/switch_to.h
index 18a4b6890fa8..0e059b73437b 100644
--- a/arch/x86/include/asm/switch_to.h
+++ b/arch/x86/include/asm/switch_to.h
@@ -103,7 +103,17 @@ static inline void update_task_stack(struct task_struct *task)
 	if (static_cpu_has(X86_FEATURE_XENPV))
 		load_sp0(task_top_of_stack(task));
 #endif
+}
 
+static inline void kthread_frame_init(struct inactive_task_frame *frame,
+				      unsigned long fun, unsigned long arg)
+{
+	frame->bx = fun;
+#ifdef CONFIG_X86_32
+	frame->di = arg;
+#else
+	frame->r12 = arg;
+#endif
 }
 
 #endif /* _ASM_X86_SWITCH_TO_H */
diff --git a/arch/x86/include/asm/syscall_wrapper.h b/arch/x86/include/asm/syscall_wrapper.h
index e046a405743d..e2389ce9bf58 100644
--- a/arch/x86/include/asm/syscall_wrapper.h
+++ b/arch/x86/include/asm/syscall_wrapper.h
@@ -6,6 +6,8 @@
 #ifndef _ASM_X86_SYSCALL_WRAPPER_H
 #define _ASM_X86_SYSCALL_WRAPPER_H
 
+struct pt_regs;
+
 /* Mapping of registers to parameters for syscalls on x86-64 and x32 */
 #define SC_X86_64_REGS_TO_ARGS(x, ...)					\
 	__MAP(x,__SC_ARGS						\
@@ -28,13 +30,21 @@
  * kernel/sys_ni.c and SYS_NI in kernel/time/posix-stubs.c to cover this
  * case as well.
  */
+#define __IA32_COMPAT_SYS_STUB0(x, name)				\
+	asmlinkage long __ia32_compat_sys_##name(const struct pt_regs *regs);\
+	ALLOW_ERROR_INJECTION(__ia32_compat_sys_##name, ERRNO);		\
+	asmlinkage long __ia32_compat_sys_##name(const struct pt_regs *regs)\
+	{								\
+		return __se_compat_sys_##name();			\
+	}
+
 #define __IA32_COMPAT_SYS_STUBx(x, name, ...)				\
 	asmlinkage long __ia32_compat_sys##name(const struct pt_regs *regs);\
 	ALLOW_ERROR_INJECTION(__ia32_compat_sys##name, ERRNO);		\
 	asmlinkage long __ia32_compat_sys##name(const struct pt_regs *regs)\
 	{								\
 		return __se_compat_sys##name(SC_IA32_REGS_TO_ARGS(x,__VA_ARGS__));\
-	}								\
+	}
 
 #define __IA32_SYS_STUBx(x, name, ...)					\
 	asmlinkage long __ia32_sys##name(const struct pt_regs *regs);	\
@@ -48,16 +58,23 @@
  * To keep the naming coherent, re-define SYSCALL_DEFINE0 to create an alias
  * named __ia32_sys_*()
  */
-#define SYSCALL_DEFINE0(sname)					\
-	SYSCALL_METADATA(_##sname, 0);				\
-	asmlinkage long __x64_sys_##sname(void);		\
-	ALLOW_ERROR_INJECTION(__x64_sys_##sname, ERRNO);	\
-	SYSCALL_ALIAS(__ia32_sys_##sname, __x64_sys_##sname);	\
-	asmlinkage long __x64_sys_##sname(void)
 
-#define COND_SYSCALL(name)						\
-	cond_syscall(__x64_sys_##name);					\
-	cond_syscall(__ia32_sys_##name)
+#define SYSCALL_DEFINE0(sname)						\
+	SYSCALL_METADATA(_##sname, 0);					\
+	asmlinkage long __x64_sys_##sname(const struct pt_regs *__unused);\
+	ALLOW_ERROR_INJECTION(__x64_sys_##sname, ERRNO);		\
+	SYSCALL_ALIAS(__ia32_sys_##sname, __x64_sys_##sname);		\
+	asmlinkage long __x64_sys_##sname(const struct pt_regs *__unused)
+
+#define COND_SYSCALL(name)							\
+	asmlinkage __weak long __x64_sys_##name(const struct pt_regs *__unused)	\
+	{									\
+		return sys_ni_syscall();					\
+	}									\
+	asmlinkage __weak long __ia32_sys_##name(const struct pt_regs *__unused)\
+	{									\
+		return sys_ni_syscall();					\
+	}
 
 #define SYS_NI(name)							\
 	SYSCALL_ALIAS(__x64_sys_##name, sys_ni_posix_timers);		\
@@ -75,15 +92,24 @@
  * of the x86-64-style parameter ordering of x32 syscalls. The syscalls common
  * with x86_64 obviously do not need such care.
  */
+#define __X32_COMPAT_SYS_STUB0(x, name, ...)				\
+	asmlinkage long __x32_compat_sys_##name(const struct pt_regs *regs);\
+	ALLOW_ERROR_INJECTION(__x32_compat_sys_##name, ERRNO);		\
+	asmlinkage long __x32_compat_sys_##name(const struct pt_regs *regs)\
+	{								\
+		return __se_compat_sys_##name();\
+	}
+
 #define __X32_COMPAT_SYS_STUBx(x, name, ...)				\
 	asmlinkage long __x32_compat_sys##name(const struct pt_regs *regs);\
 	ALLOW_ERROR_INJECTION(__x32_compat_sys##name, ERRNO);		\
 	asmlinkage long __x32_compat_sys##name(const struct pt_regs *regs)\
 	{								\
 		return __se_compat_sys##name(SC_X86_64_REGS_TO_ARGS(x,__VA_ARGS__));\
-	}								\
+	}
 
 #else /* CONFIG_X86_X32 */
+#define __X32_COMPAT_SYS_STUB0(x, name)
 #define __X32_COMPAT_SYS_STUBx(x, name, ...)
 #endif /* CONFIG_X86_X32 */
 
@@ -94,6 +120,17 @@
  * mapping of registers to parameters, we need to generate stubs for each
  * of them.
  */
+#define COMPAT_SYSCALL_DEFINE0(name)					\
+	static long __se_compat_sys_##name(void);			\
+	static inline long __do_compat_sys_##name(void);		\
+	__IA32_COMPAT_SYS_STUB0(x, name)				\
+	__X32_COMPAT_SYS_STUB0(x, name)					\
+	static long __se_compat_sys_##name(void)			\
+	{								\
+		return __do_compat_sys_##name();			\
+	}								\
+	static inline long __do_compat_sys_##name(void)
+
 #define COMPAT_SYSCALL_DEFINEx(x, name, ...)					\
 	static long __se_compat_sys##name(__MAP(x,__SC_LONG,__VA_ARGS__));	\
 	static inline long __do_compat_sys##name(__MAP(x,__SC_DECL,__VA_ARGS__));\
@@ -181,15 +218,19 @@
  * macros to work correctly.
  */
 #ifndef SYSCALL_DEFINE0
-#define SYSCALL_DEFINE0(sname)					\
-	SYSCALL_METADATA(_##sname, 0);				\
-	asmlinkage long __x64_sys_##sname(void);		\
-	ALLOW_ERROR_INJECTION(__x64_sys_##sname, ERRNO);	\
-	asmlinkage long __x64_sys_##sname(void)
+#define SYSCALL_DEFINE0(sname)						\
+	SYSCALL_METADATA(_##sname, 0);					\
+	asmlinkage long __x64_sys_##sname(const struct pt_regs *__unused);\
+	ALLOW_ERROR_INJECTION(__x64_sys_##sname, ERRNO);		\
+	asmlinkage long __x64_sys_##sname(const struct pt_regs *__unused)
 #endif
 
 #ifndef COND_SYSCALL
-#define COND_SYSCALL(name) cond_syscall(__x64_sys_##name)
+#define COND_SYSCALL(name) 							\
+	asmlinkage __weak long __x64_sys_##name(const struct pt_regs *__unused)	\
+	{									\
+		return sys_ni_syscall();					\
+	}
 #endif
 
 #ifndef SYS_NI
@@ -201,7 +242,6 @@
  * For VSYSCALLS, we need to declare these three syscalls with the new
  * pt_regs-based calling convention for in-kernel use.
  */
-struct pt_regs;
 asmlinkage long __x64_sys_getcpu(const struct pt_regs *regs);
 asmlinkage long __x64_sys_gettimeofday(const struct pt_regs *regs);
 asmlinkage long __x64_sys_time(const struct pt_regs *regs);
diff --git a/arch/x86/include/asm/tce.h b/arch/x86/include/asm/tce.h
deleted file mode 100644
index 6ed2deacf1d0..000000000000
--- a/arch/x86/include/asm/tce.h
+++ /dev/null
@@ -1,35 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-or-later */
-/*
- * This file is derived from asm-powerpc/tce.h.
- *
- * Copyright (C) IBM Corporation, 2006
- *
- * Author: Muli Ben-Yehuda <muli@il.ibm.com>
- * Author: Jon Mason <jdmason@us.ibm.com>
- */
-
-#ifndef _ASM_X86_TCE_H
-#define _ASM_X86_TCE_H
-
-extern unsigned int specified_table_size;
-struct iommu_table;
-
-#define TCE_ENTRY_SIZE   8   /* in bytes */
-
-#define TCE_READ_SHIFT   0
-#define TCE_WRITE_SHIFT  1
-#define TCE_HUBID_SHIFT  2   /* unused */
-#define TCE_RSVD_SHIFT   8   /* unused */
-#define TCE_RPN_SHIFT    12
-#define TCE_UNUSED_SHIFT 48  /* unused */
-
-#define TCE_RPN_MASK     0x0000fffffffff000ULL
-
-extern void tce_build(struct iommu_table *tbl, unsigned long index,
-		      unsigned int npages, unsigned long uaddr, int direction);
-extern void tce_free(struct iommu_table *tbl, long index, unsigned int npages);
-extern void * __init alloc_tce_table(void);
-extern void __init free_tce_table(void *tbl);
-extern int __init build_tce_table(struct pci_dev *dev, void __iomem *bbar);
-
-#endif /* _ASM_X86_TCE_H */
diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h
index f9453536f9bb..d779366ce3f8 100644
--- a/arch/x86/include/asm/thread_info.h
+++ b/arch/x86/include/asm/thread_info.h
@@ -143,8 +143,8 @@ struct thread_info {
 	 _TIF_NOHZ)
 
 /* flags to check in __switch_to() */
-#define _TIF_WORK_CTXSW_BASE						\
-	(_TIF_IO_BITMAP|_TIF_NOCPUID|_TIF_NOTSC|_TIF_BLOCKSTEP|		\
+#define _TIF_WORK_CTXSW_BASE					\
+	(_TIF_NOCPUID | _TIF_NOTSC | _TIF_BLOCKSTEP |		\
 	 _TIF_SSBD | _TIF_SPEC_FORCE_UPDATE)
 
 /*
@@ -156,8 +156,14 @@ struct thread_info {
 # define _TIF_WORK_CTXSW	(_TIF_WORK_CTXSW_BASE)
 #endif
 
-#define _TIF_WORK_CTXSW_PREV (_TIF_WORK_CTXSW|_TIF_USER_RETURN_NOTIFY)
-#define _TIF_WORK_CTXSW_NEXT (_TIF_WORK_CTXSW)
+#ifdef CONFIG_X86_IOPL_IOPERM
+# define _TIF_WORK_CTXSW_PREV	(_TIF_WORK_CTXSW| _TIF_USER_RETURN_NOTIFY | \
+				 _TIF_IO_BITMAP)
+#else
+# define _TIF_WORK_CTXSW_PREV	(_TIF_WORK_CTXSW| _TIF_USER_RETURN_NOTIFY)
+#endif
+
+#define _TIF_WORK_CTXSW_NEXT	(_TIF_WORK_CTXSW)
 
 #define STACK_WARN		(THREAD_SIZE/8)
 
diff --git a/arch/x86/include/asm/trace/hyperv.h b/arch/x86/include/asm/trace/hyperv.h
index ace464f09681..4d705cb4d63b 100644
--- a/arch/x86/include/asm/trace/hyperv.h
+++ b/arch/x86/include/asm/trace/hyperv.h
@@ -71,6 +71,21 @@ TRACE_EVENT(hyperv_send_ipi_mask,
 		      __entry->ncpus, __entry->vector)
 	);
 
+TRACE_EVENT(hyperv_send_ipi_one,
+	    TP_PROTO(int cpu,
+		     int vector),
+	    TP_ARGS(cpu, vector),
+	    TP_STRUCT__entry(
+		    __field(int, cpu)
+		    __field(int, vector)
+		    ),
+	    TP_fast_assign(__entry->cpu = cpu;
+			   __entry->vector = vector;
+		    ),
+	    TP_printk("cpu %d vector %x",
+		      __entry->cpu, __entry->vector)
+	);
+
 #endif /* CONFIG_HYPERV */
 
 #undef TRACE_INCLUDE_PATH
diff --git a/arch/x86/include/asm/umip.h b/arch/x86/include/asm/umip.h
index db43f2a0d92c..aeed98c3c9e1 100644
--- a/arch/x86/include/asm/umip.h
+++ b/arch/x86/include/asm/umip.h
@@ -4,9 +4,9 @@
 #include <linux/types.h>
 #include <asm/ptrace.h>
 
-#ifdef CONFIG_X86_INTEL_UMIP
+#ifdef CONFIG_X86_UMIP
 bool fixup_umip_exception(struct pt_regs *regs);
 #else
 static inline bool fixup_umip_exception(struct pt_regs *regs) { return false; }
-#endif  /* CONFIG_X86_INTEL_UMIP */
+#endif  /* CONFIG_X86_UMIP */
 #endif  /* _ASM_X86_UMIP_H */
diff --git a/arch/x86/include/asm/uv/bios.h b/arch/x86/include/asm/uv/bios.h
index 6e7caf65fa40..389174eaec79 100644
--- a/arch/x86/include/asm/uv/bios.h
+++ b/arch/x86/include/asm/uv/bios.h
@@ -138,7 +138,7 @@ extern s64 uv_bios_change_memprotect(u64, u64, enum uv_memprotect);
 extern s64 uv_bios_reserved_page_pa(u64, u64 *, u64 *, u64 *);
 extern int uv_bios_set_legacy_vga_target(bool decode, int domain, int bus);
 
-extern void uv_bios_init(void);
+extern int uv_bios_init(void);
 
 extern unsigned long sn_rtc_cycles_per_second;
 extern int uv_type;
diff --git a/arch/x86/include/asm/uv/uv.h b/arch/x86/include/asm/uv/uv.h
index 6bc6d89d8e2a..45ea95ce79b4 100644
--- a/arch/x86/include/asm/uv/uv.h
+++ b/arch/x86/include/asm/uv/uv.h
@@ -12,6 +12,16 @@ struct mm_struct;
 #ifdef CONFIG_X86_UV
 #include <linux/efi.h>
 
+#define	UV_PROC_NODE	"sgi_uv"
+
+static inline int uv(int uvtype)
+{
+	/* uv(0) is "any" */
+	if (uvtype >= 0 && uvtype <= 30)
+		return 1 << uvtype;
+	return 1;
+}
+
 extern unsigned long uv_systab_phys;
 
 extern enum uv_system_type get_uv_system_type(void);
@@ -20,7 +30,8 @@ static inline bool is_early_uv_system(void)
 	return uv_systab_phys && uv_systab_phys != EFI_INVALID_TABLE_ADDR;
 }
 extern int is_uv_system(void);
-extern int is_uv_hubless(void);
+extern int is_uv_hubbed(int uvtype);
+extern int is_uv_hubless(int uvtype);
 extern void uv_cpu_init(void);
 extern void uv_nmi_init(void);
 extern void uv_system_init(void);
@@ -32,7 +43,8 @@ extern const struct cpumask *uv_flush_tlb_others(const struct cpumask *cpumask,
 static inline enum uv_system_type get_uv_system_type(void) { return UV_NONE; }
 static inline bool is_early_uv_system(void)	{ return 0; }
 static inline int is_uv_system(void)	{ return 0; }
-static inline int is_uv_hubless(void)	{ return 0; }
+static inline int is_uv_hubbed(int uv)	{ return 0; }
+static inline int is_uv_hubless(int uv) { return 0; }
 static inline void uv_cpu_init(void)	{ }
 static inline void uv_system_init(void)	{ }
 static inline const struct cpumask *
diff --git a/arch/x86/include/asm/uv/uv_hub.h b/arch/x86/include/asm/uv/uv_hub.h
index 44cf6d6deb7a..950cd1395d5d 100644
--- a/arch/x86/include/asm/uv/uv_hub.h
+++ b/arch/x86/include/asm/uv/uv_hub.h
@@ -19,6 +19,7 @@
 #include <linux/topology.h>
 #include <asm/types.h>
 #include <asm/percpu.h>
+#include <asm/uv/uv.h>
 #include <asm/uv/uv_mmrs.h>
 #include <asm/uv/bios.h>
 #include <asm/irq_vectors.h>
@@ -243,83 +244,61 @@ static inline int uv_hub_info_check(int version)
 #define UV4_HUB_REVISION_BASE		7
 #define UV4A_HUB_REVISION_BASE		8	/* UV4 (fixed) rev 2 */
 
-#ifdef	UV1_HUB_IS_SUPPORTED
+/* WARNING: UVx_HUB_IS_SUPPORTED defines are deprecated and will be removed */
 static inline int is_uv1_hub(void)
 {
-	return uv_hub_info->hub_revision < UV2_HUB_REVISION_BASE;
-}
+#ifdef	UV1_HUB_IS_SUPPORTED
+	return is_uv_hubbed(uv(1));
 #else
-static inline int is_uv1_hub(void)
-{
 	return 0;
-}
 #endif
+}
 
-#ifdef	UV2_HUB_IS_SUPPORTED
 static inline int is_uv2_hub(void)
 {
-	return ((uv_hub_info->hub_revision >= UV2_HUB_REVISION_BASE) &&
-		(uv_hub_info->hub_revision < UV3_HUB_REVISION_BASE));
-}
+#ifdef	UV2_HUB_IS_SUPPORTED
+	return is_uv_hubbed(uv(2));
 #else
-static inline int is_uv2_hub(void)
-{
 	return 0;
-}
 #endif
+}
 
-#ifdef	UV3_HUB_IS_SUPPORTED
 static inline int is_uv3_hub(void)
 {
-	return ((uv_hub_info->hub_revision >= UV3_HUB_REVISION_BASE) &&
-		(uv_hub_info->hub_revision < UV4_HUB_REVISION_BASE));
-}
+#ifdef	UV3_HUB_IS_SUPPORTED
+	return is_uv_hubbed(uv(3));
 #else
-static inline int is_uv3_hub(void)
-{
 	return 0;
-}
 #endif
+}
 
 /* First test "is UV4A", then "is UV4" */
-#ifdef	UV4A_HUB_IS_SUPPORTED
-static inline int is_uv4a_hub(void)
-{
-	return (uv_hub_info->hub_revision >= UV4A_HUB_REVISION_BASE);
-}
-#else
 static inline int is_uv4a_hub(void)
 {
+#ifdef	UV4A_HUB_IS_SUPPORTED
+	if (is_uv_hubbed(uv(4)))
+		return (uv_hub_info->hub_revision == UV4A_HUB_REVISION_BASE);
+#endif
 	return 0;
 }
-#endif
 
-#ifdef	UV4_HUB_IS_SUPPORTED
 static inline int is_uv4_hub(void)
 {
-	return uv_hub_info->hub_revision >= UV4_HUB_REVISION_BASE;
-}
+#ifdef	UV4_HUB_IS_SUPPORTED
+	return is_uv_hubbed(uv(4));
 #else
-static inline int is_uv4_hub(void)
-{
 	return 0;
-}
 #endif
+}
 
 static inline int is_uvx_hub(void)
 {
-	if (uv_hub_info->hub_revision >= UV2_HUB_REVISION_BASE)
-		return uv_hub_info->hub_revision;
-
-	return 0;
+	return (is_uv_hubbed(-2) >= uv(2));
 }
 
 static inline int is_uv_hub(void)
 {
-#ifdef	UV1_HUB_IS_SUPPORTED
-	return uv_hub_info->hub_revision;
-#endif
-	return is_uvx_hub();
+	return is_uv1_hub() || is_uvx_hub();
 }
 
 union uvh_apicid {
diff --git a/arch/x86/include/asm/xen/hypervisor.h b/arch/x86/include/asm/xen/hypervisor.h
index 42e1245af0d8..ff4b52e37e60 100644
--- a/arch/x86/include/asm/xen/hypervisor.h
+++ b/arch/x86/include/asm/xen/hypervisor.h
@@ -62,6 +62,4 @@ void xen_arch_register_cpu(int num);
 void xen_arch_unregister_cpu(int num);
 #endif
 
-extern void xen_set_iopl_mask(unsigned mask);
-
 #endif /* _ASM_X86_XEN_HYPERVISOR_H */
diff --git a/arch/x86/include/uapi/asm/bootparam.h b/arch/x86/include/uapi/asm/bootparam.h
index c895df5482c5..8669c6bdbb84 100644
--- a/arch/x86/include/uapi/asm/bootparam.h
+++ b/arch/x86/include/uapi/asm/bootparam.h
@@ -2,7 +2,7 @@
 #ifndef _ASM_X86_BOOTPARAM_H
 #define _ASM_X86_BOOTPARAM_H
 
-/* setup_data types */
+/* setup_data/setup_indirect types */
 #define SETUP_NONE			0
 #define SETUP_E820_EXT			1
 #define SETUP_DTB			2
@@ -11,6 +11,11 @@
 #define SETUP_APPLE_PROPERTIES		5
 #define SETUP_JAILHOUSE			6
 
+#define SETUP_INDIRECT			(1<<31)
+
+/* SETUP_INDIRECT | max(SETUP_*) */
+#define SETUP_TYPE_MAX			(SETUP_INDIRECT | SETUP_JAILHOUSE)
+
 /* ram_size flags */
 #define RAMDISK_IMAGE_START_MASK	0x07FF
 #define RAMDISK_PROMPT_FLAG		0x8000
@@ -49,6 +54,14 @@ struct setup_data {
 	__u8 data[0];
 };
 
+/* extensible setup indirect data node */
+struct setup_indirect {
+	__u32 type;
+	__u32 reserved;  /* Reserved, must be set to zero. */
+	__u64 len;
+	__u64 addr;
+};
+
 struct setup_header {
 	__u8	setup_sects;
 	__u16	root_flags;
@@ -88,6 +101,7 @@ struct setup_header {
 	__u64	pref_address;
 	__u32	init_size;
 	__u32	handover_offset;
+	__u32	kernel_info_offset;
 } __attribute__((packed));
 
 struct sys_desc_table {
@@ -139,15 +153,22 @@ struct boot_e820_entry {
  * setup data structure.
  */
 struct jailhouse_setup_data {
-	__u16	version;
-	__u16	compatible_version;
-	__u16	pm_timer_address;
-	__u16	num_cpus;
-	__u64	pci_mmconfig_base;
-	__u32	tsc_khz;
-	__u32	apic_khz;
-	__u8	standard_ioapic;
-	__u8	cpu_ids[255];
+	struct {
+		__u16	version;
+		__u16	compatible_version;
+	} __attribute__((packed)) hdr;
+	struct {
+		__u16	pm_timer_address;
+		__u16	num_cpus;
+		__u64	pci_mmconfig_base;
+		__u32	tsc_khz;
+		__u32	apic_khz;
+		__u8	standard_ioapic;
+		__u8	cpu_ids[255];
+	} __attribute__((packed)) v1;
+	struct {
+		__u32	flags;
+	} __attribute__((packed)) v2;
 } __attribute__((packed));
 
 /* The so-called "zeropage" */
diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile
index 3578ad248bc9..32acb970f416 100644
--- a/arch/x86/kernel/Makefile
+++ b/arch/x86/kernel/Makefile
@@ -134,7 +134,7 @@ obj-$(CONFIG_EFI)			+= sysfb_efi.o
 obj-$(CONFIG_PERF_EVENTS)		+= perf_regs.o
 obj-$(CONFIG_TRACING)			+= tracepoint.o
 obj-$(CONFIG_SCHED_MC_PRIO)		+= itmt.o
-obj-$(CONFIG_X86_INTEL_UMIP)		+= umip.o
+obj-$(CONFIG_X86_UMIP)			+= umip.o
 
 obj-$(CONFIG_UNWINDER_ORC)		+= unwind_orc.o
 obj-$(CONFIG_UNWINDER_FRAME_POINTER)	+= unwind_frame.o
@@ -146,7 +146,6 @@ ifeq ($(CONFIG_X86_64),y)
 	obj-$(CONFIG_AUDIT)		+= audit_64.o
 
 	obj-$(CONFIG_GART_IOMMU)	+= amd_gart_64.o aperture_64.o
-	obj-$(CONFIG_CALGARY_IOMMU)	+= pci-calgary_64.o tce_64.o
 
 	obj-$(CONFIG_MMCONF_FAM10H)	+= mmconf-fam10h_64.o
 	obj-y				+= vsmp_64.o
diff --git a/arch/x86/kernel/acpi/wakeup_32.S b/arch/x86/kernel/acpi/wakeup_32.S
index e95e95960156..daf88f8143c5 100644
--- a/arch/x86/kernel/acpi/wakeup_32.S
+++ b/arch/x86/kernel/acpi/wakeup_32.S
@@ -9,8 +9,7 @@
 	.code32
 	ALIGN
 
-ENTRY(wakeup_pmode_return)
-wakeup_pmode_return:
+SYM_CODE_START(wakeup_pmode_return)
 	movw	$__KERNEL_DS, %ax
 	movw	%ax, %ss
 	movw	%ax, %fs
@@ -39,6 +38,7 @@ wakeup_pmode_return:
 	# jump to place where we left off
 	movl	saved_eip, %eax
 	jmp	*%eax
+SYM_CODE_END(wakeup_pmode_return)
 
 bogus_magic:
 	jmp	bogus_magic
@@ -72,7 +72,7 @@ restore_registers:
 	popfl
 	ret
 
-ENTRY(do_suspend_lowlevel)
+SYM_CODE_START(do_suspend_lowlevel)
 	call	save_processor_state
 	call	save_registers
 	pushl	$3
@@ -87,10 +87,11 @@ ret_point:
 	call	restore_registers
 	call	restore_processor_state
 	ret
+SYM_CODE_END(do_suspend_lowlevel)
 
 .data
 ALIGN
-ENTRY(saved_magic)	.long	0
+SYM_DATA(saved_magic,	.long 0)
 saved_eip:		.long 0
 
 # saved registers
diff --git a/arch/x86/kernel/acpi/wakeup_64.S b/arch/x86/kernel/acpi/wakeup_64.S
index 7f9ade13bbcf..c8daa92f38dc 100644
--- a/arch/x86/kernel/acpi/wakeup_64.S
+++ b/arch/x86/kernel/acpi/wakeup_64.S
@@ -14,7 +14,7 @@
 	/*
 	 * Hooray, we are in Long 64-bit mode (but still running in low memory)
 	 */
-ENTRY(wakeup_long64)
+SYM_FUNC_START(wakeup_long64)
 	movq	saved_magic, %rax
 	movq	$0x123456789abcdef0, %rdx
 	cmpq	%rdx, %rax
@@ -40,9 +40,9 @@ ENTRY(wakeup_long64)
 
 	movq	saved_rip, %rax
 	jmp	*%rax
-ENDPROC(wakeup_long64)
+SYM_FUNC_END(wakeup_long64)
 
-ENTRY(do_suspend_lowlevel)
+SYM_FUNC_START(do_suspend_lowlevel)
 	FRAME_BEGIN
 	subq	$8, %rsp
 	xorl	%eax, %eax
@@ -125,7 +125,7 @@ ENTRY(do_suspend_lowlevel)
 	addq	$8, %rsp
 	FRAME_END
 	jmp	restore_processor_state
-ENDPROC(do_suspend_lowlevel)
+SYM_FUNC_END(do_suspend_lowlevel)
 
 .data
 saved_rbp:		.quad	0
@@ -136,4 +136,4 @@ saved_rbx:		.quad	0
 saved_rip:		.quad	0
 saved_rsp:		.quad	0
 
-ENTRY(saved_magic)	.quad	0
+SYM_DATA(saved_magic,	.quad	0)
diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c
index 05feaec5d3d7..28446fa6bf18 100644
--- a/arch/x86/kernel/apic/apic.c
+++ b/arch/x86/kernel/apic/apic.c
@@ -2337,7 +2337,7 @@ static int cpuid_to_apicid[] = {
 #ifdef CONFIG_SMP
 /**
  * apic_id_is_primary_thread - Check whether APIC ID belongs to a primary thread
- * @id:	APIC ID to check
+ * @apicid: APIC ID to check
  */
 bool apic_id_is_primary_thread(unsigned int apicid)
 {
diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c
index d6af97fd170a..913c88617848 100644
--- a/arch/x86/kernel/apic/io_apic.c
+++ b/arch/x86/kernel/apic/io_apic.c
@@ -1725,19 +1725,20 @@ static bool io_apic_level_ack_pending(struct mp_chip_data *data)
 	return false;
 }
 
-static inline bool ioapic_irqd_mask(struct irq_data *data)
+static inline bool ioapic_prepare_move(struct irq_data *data)
 {
-	/* If we are moving the irq we need to mask it */
+	/* If we are moving the IRQ we need to mask it */
 	if (unlikely(irqd_is_setaffinity_pending(data))) {
-		mask_ioapic_irq(data);
+		if (!irqd_irq_masked(data))
+			mask_ioapic_irq(data);
 		return true;
 	}
 	return false;
 }
 
-static inline void ioapic_irqd_unmask(struct irq_data *data, bool masked)
+static inline void ioapic_finish_move(struct irq_data *data, bool moveit)
 {
-	if (unlikely(masked)) {
+	if (unlikely(moveit)) {
 		/* Only migrate the irq if the ack has been received.
 		 *
 		 * On rare occasions the broadcast level triggered ack gets
@@ -1766,15 +1767,17 @@ static inline void ioapic_irqd_unmask(struct irq_data *data, bool masked)
 		 */
 		if (!io_apic_level_ack_pending(data->chip_data))
 			irq_move_masked_irq(data);
-		unmask_ioapic_irq(data);
+		/* If the IRQ is masked in the core, leave it: */
+		if (!irqd_irq_masked(data))
+			unmask_ioapic_irq(data);
 	}
 }
 #else
-static inline bool ioapic_irqd_mask(struct irq_data *data)
+static inline bool ioapic_prepare_move(struct irq_data *data)
 {
 	return false;
 }
-static inline void ioapic_irqd_unmask(struct irq_data *data, bool masked)
+static inline void ioapic_finish_move(struct irq_data *data, bool moveit)
 {
 }
 #endif
@@ -1783,11 +1786,11 @@ static void ioapic_ack_level(struct irq_data *irq_data)
 {
 	struct irq_cfg *cfg = irqd_cfg(irq_data);
 	unsigned long v;
-	bool masked;
+	bool moveit;
 	int i;
 
 	irq_complete_move(cfg);
-	masked = ioapic_irqd_mask(irq_data);
+	moveit = ioapic_prepare_move(irq_data);
 
 	/*
 	 * It appears there is an erratum which affects at least version 0x11
@@ -1842,7 +1845,7 @@ static void ioapic_ack_level(struct irq_data *irq_data)
 		eoi_ioapic_pin(cfg->vector, irq_data->chip_data);
 	}
 
-	ioapic_irqd_unmask(irq_data, masked);
+	ioapic_finish_move(irq_data, moveit);
 }
 
 static void ioapic_ir_ack_level(struct irq_data *irq_data)
diff --git a/arch/x86/kernel/apic/x2apic_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c
index e6230af19864..d5b51a740524 100644
--- a/arch/x86/kernel/apic/x2apic_uv_x.c
+++ b/arch/x86/kernel/apic/x2apic_uv_x.c
@@ -14,6 +14,8 @@
 #include <linux/memory.h>
 #include <linux/export.h>
 #include <linux/pci.h>
+#include <linux/acpi.h>
+#include <linux/efi.h>
 
 #include <asm/e820/api.h>
 #include <asm/uv/uv_mmrs.h>
@@ -25,12 +27,17 @@
 static DEFINE_PER_CPU(int, x2apic_extra_bits);
 
 static enum uv_system_type	uv_system_type;
-static bool			uv_hubless_system;
+static int			uv_hubbed_system;
+static int			uv_hubless_system;
 static u64			gru_start_paddr, gru_end_paddr;
 static u64			gru_dist_base, gru_first_node_paddr = -1LL, gru_last_node_paddr;
 static u64			gru_dist_lmask, gru_dist_umask;
 static union uvh_apicid		uvh_apicid;
 
+/* Unpack OEM/TABLE ID's to be NULL terminated strings */
+static u8 oem_id[ACPI_OEM_ID_SIZE + 1];
+static u8 oem_table_id[ACPI_OEM_TABLE_ID_SIZE + 1];
+
 /* Information derived from CPUID: */
 static struct {
 	unsigned int apicid_shift;
@@ -248,17 +255,35 @@ static void __init uv_set_apicid_hibit(void)
 	}
 }
 
-static int __init uv_acpi_madt_oem_check(char *oem_id, char *oem_table_id)
+static void __init uv_stringify(int len, char *to, char *from)
+{
+	/* Relies on 'to' being NULL chars so result will be NULL terminated */
+	strncpy(to, from, len-1);
+}
+
+static int __init uv_acpi_madt_oem_check(char *_oem_id, char *_oem_table_id)
 {
 	int pnodeid;
 	int uv_apic;
 
+	uv_stringify(sizeof(oem_id), oem_id, _oem_id);
+	uv_stringify(sizeof(oem_table_id), oem_table_id, _oem_table_id);
+
 	if (strncmp(oem_id, "SGI", 3) != 0) {
-		if (strncmp(oem_id, "NSGI", 4) == 0) {
-			uv_hubless_system = true;
-			pr_info("UV: OEM IDs %s/%s, HUBLESS\n",
-				oem_id, oem_table_id);
-		}
+		if (strncmp(oem_id, "NSGI", 4) != 0)
+			return 0;
+
+		/* UV4 Hubless, CH, (0x11:UV4+Any) */
+		if (strncmp(oem_id, "NSGI4", 5) == 0)
+			uv_hubless_system = 0x11;
+
+		/* UV3 Hubless, UV300/MC990X w/o hub (0x9:UV3+Any) */
+		else
+			uv_hubless_system = 0x9;
+
+		pr_info("UV: OEM IDs %s/%s, HUBLESS(0x%x)\n",
+			oem_id, oem_table_id, uv_hubless_system);
+
 		return 0;
 	}
 
@@ -286,6 +311,24 @@ static int __init uv_acpi_madt_oem_check(char *oem_id, char *oem_table_id)
 	if (uv_hub_info->hub_revision == 0)
 		goto badbios;
 
+	switch (uv_hub_info->hub_revision) {
+	case UV4_HUB_REVISION_BASE:
+		uv_hubbed_system = 0x11;
+		break;
+
+	case UV3_HUB_REVISION_BASE:
+		uv_hubbed_system = 0x9;
+		break;
+
+	case UV2_HUB_REVISION_BASE:
+		uv_hubbed_system = 0x5;
+		break;
+
+	case UV1_HUB_REVISION_BASE:
+		uv_hubbed_system = 0x3;
+		break;
+	}
+
 	pnodeid = early_get_pnodeid();
 	early_get_apic_socketid_shift();
 
@@ -336,9 +379,15 @@ int is_uv_system(void)
 }
 EXPORT_SYMBOL_GPL(is_uv_system);
 
-int is_uv_hubless(void)
+int is_uv_hubbed(int uvtype)
+{
+	return (uv_hubbed_system & uvtype);
+}
+EXPORT_SYMBOL_GPL(is_uv_hubbed);
+
+int is_uv_hubless(int uvtype)
 {
-	return uv_hubless_system;
+	return (uv_hubless_system & uvtype);
 }
 EXPORT_SYMBOL_GPL(is_uv_hubless);
 
@@ -1255,7 +1304,8 @@ static int __init decode_uv_systab(void)
 	struct uv_systab *st;
 	int i;
 
-	if (uv_hub_info->hub_revision < UV4_HUB_REVISION_BASE)
+	/* If system is uv3 or lower, there is no extended UVsystab */
+	if (is_uv_hubbed(0xfffffe) < uv(4) && is_uv_hubless(0xfffffe) < uv(4))
 		return 0;	/* No extended UVsystab required */
 
 	st = uv_systab;
@@ -1434,6 +1484,103 @@ static void __init build_socket_tables(void)
 	}
 }
 
+/* Check which reboot to use */
+static void check_efi_reboot(void)
+{
+	/* If EFI reboot not available, use ACPI reboot */
+	if (!efi_enabled(EFI_BOOT))
+		reboot_type = BOOT_ACPI;
+}
+
+/* Setup user proc fs files */
+static int proc_hubbed_show(struct seq_file *file, void *data)
+{
+	seq_printf(file, "0x%x\n", uv_hubbed_system);
+	return 0;
+}
+
+static int proc_hubless_show(struct seq_file *file, void *data)
+{
+	seq_printf(file, "0x%x\n", uv_hubless_system);
+	return 0;
+}
+
+static int proc_oemid_show(struct seq_file *file, void *data)
+{
+	seq_printf(file, "%s/%s\n", oem_id, oem_table_id);
+	return 0;
+}
+
+static int proc_hubbed_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, proc_hubbed_show, (void *)NULL);
+}
+
+static int proc_hubless_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, proc_hubless_show, (void *)NULL);
+}
+
+static int proc_oemid_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, proc_oemid_show, (void *)NULL);
+}
+
+/* (struct is "non-const" as open function is set at runtime) */
+static struct file_operations proc_version_fops = {
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= single_release,
+};
+
+static const struct file_operations proc_oemid_fops = {
+	.open		= proc_oemid_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= single_release,
+};
+
+static __init void uv_setup_proc_files(int hubless)
+{
+	struct proc_dir_entry *pde;
+	char *name = hubless ? "hubless" : "hubbed";
+
+	pde = proc_mkdir(UV_PROC_NODE, NULL);
+	proc_create("oemid", 0, pde, &proc_oemid_fops);
+	proc_create(name, 0, pde, &proc_version_fops);
+	if (hubless)
+		proc_version_fops.open = proc_hubless_open;
+	else
+		proc_version_fops.open = proc_hubbed_open;
+}
+
+/* Initialize UV hubless systems */
+static __init int uv_system_init_hubless(void)
+{
+	int rc;
+
+	/* Setup PCH NMI handler */
+	uv_nmi_setup_hubless();
+
+	/* Init kernel/BIOS interface */
+	rc = uv_bios_init();
+	if (rc < 0)
+		return rc;
+
+	/* Process UVsystab */
+	rc = decode_uv_systab();
+	if (rc < 0)
+		return rc;
+
+	/* Create user access node */
+	if (rc >= 0)
+		uv_setup_proc_files(1);
+
+	check_efi_reboot();
+
+	return rc;
+}
+
 static void __init uv_system_init_hub(void)
 {
 	struct uv_hub_info_s hub_info = {0};
@@ -1559,32 +1706,27 @@ static void __init uv_system_init_hub(void)
 	uv_nmi_setup();
 	uv_cpu_init();
 	uv_scir_register_cpu_notifier();
-	proc_mkdir("sgi_uv", NULL);
+	uv_setup_proc_files(0);
 
 	/* Register Legacy VGA I/O redirection handler: */
 	pci_register_set_vga_state(uv_set_vga_state);
 
-	/*
-	 * For a kdump kernel the reset must be BOOT_ACPI, not BOOT_EFI, as
-	 * EFI is not enabled in the kdump kernel:
-	 */
-	if (is_kdump_kernel())
-		reboot_type = BOOT_ACPI;
+	check_efi_reboot();
 }
 
 /*
- * There is a small amount of UV specific code needed to initialize a
- * UV system that does not have a "UV HUB" (referred to as "hubless").
+ * There is a different code path needed to initialize a UV system that does
+ * not have a "UV HUB" (referred to as "hubless").
  */
 void __init uv_system_init(void)
 {
-	if (likely(!is_uv_system() && !is_uv_hubless()))
+	if (likely(!is_uv_system() && !is_uv_hubless(1)))
 		return;
 
 	if (is_uv_system())
 		uv_system_init_hub();
 	else
-		uv_nmi_setup_hubless();
+		uv_system_init_hubless();
 }
 
 apic_driver(apic_x2apic_uv_x);
diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c
index 4c7b0fa15a19..8bf64899f56a 100644
--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@@ -39,6 +39,7 @@ static void __init spectre_v2_select_mitigation(void);
 static void __init ssb_select_mitigation(void);
 static void __init l1tf_select_mitigation(void);
 static void __init mds_select_mitigation(void);
+static void __init mds_print_mitigation(void);
 static void __init taa_select_mitigation(void);
 
 /* The base value of the SPEC_CTRL MSR that always has to be preserved. */
@@ -108,6 +109,12 @@ void __init check_bugs(void)
 	mds_select_mitigation();
 	taa_select_mitigation();
 
+	/*
+	 * As MDS and TAA mitigations are inter-related, print MDS
+	 * mitigation until after TAA mitigation selection is done.
+	 */
+	mds_print_mitigation();
+
 	arch_smt_update();
 
 #ifdef CONFIG_X86_32
@@ -245,6 +252,12 @@ static void __init mds_select_mitigation(void)
 		    (mds_nosmt || cpu_mitigations_auto_nosmt()))
 			cpu_smt_disable(false);
 	}
+}
+
+static void __init mds_print_mitigation(void)
+{
+	if (!boot_cpu_has_bug(X86_BUG_MDS) || cpu_mitigations_off())
+		return;
 
 	pr_info("%s\n", mds_strings[mds_mitigation]);
 }
@@ -304,8 +317,12 @@ static void __init taa_select_mitigation(void)
 		return;
 	}
 
-	/* TAA mitigation is turned off on the cmdline (tsx_async_abort=off) */
-	if (taa_mitigation == TAA_MITIGATION_OFF)
+	/*
+	 * TAA mitigation via VERW is turned off if both
+	 * tsx_async_abort=off and mds=off are specified.
+	 */
+	if (taa_mitigation == TAA_MITIGATION_OFF &&
+	    mds_mitigation == MDS_MITIGATION_OFF)
 		goto out;
 
 	if (boot_cpu_has(X86_FEATURE_MD_CLEAR))
@@ -339,6 +356,15 @@ static void __init taa_select_mitigation(void)
 	if (taa_nosmt || cpu_mitigations_auto_nosmt())
 		cpu_smt_disable(false);
 
+	/*
+	 * Update MDS mitigation, if necessary, as the mds_user_clear is
+	 * now enabled for TAA mitigation.
+	 */
+	if (mds_mitigation == MDS_MITIGATION_OFF &&
+	    boot_cpu_has_bug(X86_BUG_MDS)) {
+		mds_mitigation = MDS_MITIGATION_FULL;
+		mds_select_mitigation();
+	}
 out:
 	pr_info("%s\n", taa_strings[taa_mitigation]);
 }
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index fffe21945374..baa2fed8deb6 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -53,10 +53,7 @@
 #include <asm/microcode_intel.h>
 #include <asm/intel-family.h>
 #include <asm/cpu_device_id.h>
-
-#ifdef CONFIG_X86_LOCAL_APIC
 #include <asm/uv/uv.h>
-#endif
 
 #include "cpu.h"
 
@@ -565,8 +562,9 @@ static const char *table_lookup_model(struct cpuinfo_x86 *c)
 	return NULL;		/* Not found */
 }
 
-__u32 cpu_caps_cleared[NCAPINTS + NBUGINTS];
-__u32 cpu_caps_set[NCAPINTS + NBUGINTS];
+/* Aligned to unsigned long to avoid split lock in atomic bitmap ops */
+__u32 cpu_caps_cleared[NCAPINTS + NBUGINTS] __aligned(sizeof(unsigned long));
+__u32 cpu_caps_set[NCAPINTS + NBUGINTS] __aligned(sizeof(unsigned long));
 
 void load_percpu_segment(int cpu)
 {
@@ -1780,7 +1778,7 @@ static void wait_for_master_cpu(int cpu)
 }
 
 #ifdef CONFIG_X86_64
-static void setup_getcpu(int cpu)
+static inline void setup_getcpu(int cpu)
 {
 	unsigned long cpudata = vdso_encode_cpunode(cpu, early_cpu_to_node(cpu));
 	struct desc_struct d = { };
@@ -1800,7 +1798,59 @@ static void setup_getcpu(int cpu)
 
 	write_gdt_entry(get_cpu_gdt_rw(cpu), GDT_ENTRY_CPUNODE, &d, DESCTYPE_S);
 }
+
+static inline void ucode_cpu_init(int cpu)
+{
+	if (cpu)
+		load_ucode_ap();
+}
+
+static inline void tss_setup_ist(struct tss_struct *tss)
+{
+	/* Set up the per-CPU TSS IST stacks */
+	tss->x86_tss.ist[IST_INDEX_DF] = __this_cpu_ist_top_va(DF);
+	tss->x86_tss.ist[IST_INDEX_NMI] = __this_cpu_ist_top_va(NMI);
+	tss->x86_tss.ist[IST_INDEX_DB] = __this_cpu_ist_top_va(DB);
+	tss->x86_tss.ist[IST_INDEX_MCE] = __this_cpu_ist_top_va(MCE);
+}
+
+static inline void gdt_setup_doublefault_tss(int cpu) { }
+
+#else /* CONFIG_X86_64 */
+
+static inline void setup_getcpu(int cpu) { }
+
+static inline void ucode_cpu_init(int cpu)
+{
+	show_ucode_info_early();
+}
+
+static inline void tss_setup_ist(struct tss_struct *tss) { }
+
+static inline void gdt_setup_doublefault_tss(int cpu)
+{
+#ifdef CONFIG_DOUBLEFAULT
+	/* Set up the doublefault TSS pointer in the GDT */
+	__set_tss_desc(cpu, GDT_ENTRY_DOUBLEFAULT_TSS, &doublefault_tss);
+#endif
+}
+#endif /* !CONFIG_X86_64 */
+
+static inline void tss_setup_io_bitmap(struct tss_struct *tss)
+{
+	tss->x86_tss.io_bitmap_base = IO_BITMAP_OFFSET_INVALID;
+
+#ifdef CONFIG_X86_IOPL_IOPERM
+	tss->io_bitmap.prev_max = 0;
+	tss->io_bitmap.prev_sequence = 0;
+	memset(tss->io_bitmap.bitmap, 0xff, sizeof(tss->io_bitmap.bitmap));
+	/*
+	 * Invalidate the extra array entry past the end of the all
+	 * permission bitmap as required by the hardware.
+	 */
+	tss->io_bitmap.mapall[IO_BITMAP_LONGS] = ~0UL;
 #endif
+}
 
 /*
  * cpu_init() initializes state that is per-CPU. Some data is already
@@ -1808,21 +1858,15 @@ static void setup_getcpu(int cpu)
  * and IDT. We reload them nevertheless, this function acts as a
  * 'CPU state barrier', nothing should get across.
  */
-#ifdef CONFIG_X86_64
-
 void cpu_init(void)
 {
+	struct tss_struct *tss = this_cpu_ptr(&cpu_tss_rw);
+	struct task_struct *cur = current;
 	int cpu = raw_smp_processor_id();
-	struct task_struct *me;
-	struct tss_struct *t;
-	int i;
 
 	wait_for_master_cpu(cpu);
 
-	if (cpu)
-		load_ucode_ap();
-
-	t = &per_cpu(cpu_tss_rw, cpu);
+	ucode_cpu_init(cpu);
 
 #ifdef CONFIG_NUMA
 	if (this_cpu_read(numa_node) == 0 &&
@@ -1831,63 +1875,47 @@ void cpu_init(void)
 #endif
 	setup_getcpu(cpu);
 
-	me = current;
-
 	pr_debug("Initializing CPU#%d\n", cpu);
 
-	cr4_clear_bits(X86_CR4_VME|X86_CR4_PVI|X86_CR4_TSD|X86_CR4_DE);
+	if (IS_ENABLED(CONFIG_X86_64) || cpu_feature_enabled(X86_FEATURE_VME) ||
+	    boot_cpu_has(X86_FEATURE_TSC) || boot_cpu_has(X86_FEATURE_DE))
+		cr4_clear_bits(X86_CR4_VME|X86_CR4_PVI|X86_CR4_TSD|X86_CR4_DE);
 
 	/*
 	 * Initialize the per-CPU GDT with the boot GDT,
 	 * and set up the GDT descriptor:
 	 */
-
 	switch_to_new_gdt(cpu);
-	loadsegment(fs, 0);
-
 	load_current_idt();
 
-	memset(me->thread.tls_array, 0, GDT_ENTRY_TLS_ENTRIES * 8);
-	syscall_init();
-
-	wrmsrl(MSR_FS_BASE, 0);
-	wrmsrl(MSR_KERNEL_GS_BASE, 0);
-	barrier();
+	if (IS_ENABLED(CONFIG_X86_64)) {
+		loadsegment(fs, 0);
+		memset(cur->thread.tls_array, 0, GDT_ENTRY_TLS_ENTRIES * 8);
+		syscall_init();
 
-	x86_configure_nx();
-	x2apic_setup();
+		wrmsrl(MSR_FS_BASE, 0);
+		wrmsrl(MSR_KERNEL_GS_BASE, 0);
+		barrier();
 
-	/*
-	 * set up and load the per-CPU TSS
-	 */
-	if (!t->x86_tss.ist[0]) {
-		t->x86_tss.ist[IST_INDEX_DF] = __this_cpu_ist_top_va(DF);
-		t->x86_tss.ist[IST_INDEX_NMI] = __this_cpu_ist_top_va(NMI);
-		t->x86_tss.ist[IST_INDEX_DB] = __this_cpu_ist_top_va(DB);
-		t->x86_tss.ist[IST_INDEX_MCE] = __this_cpu_ist_top_va(MCE);
+		x2apic_setup();
 	}
 
-	t->x86_tss.io_bitmap_base = IO_BITMAP_OFFSET;
-
-	/*
-	 * <= is required because the CPU will access up to
-	 * 8 bits beyond the end of the IO permission bitmap.
-	 */
-	for (i = 0; i <= IO_BITMAP_LONGS; i++)
-		t->io_bitmap[i] = ~0UL;
-
 	mmgrab(&init_mm);
-	me->active_mm = &init_mm;
-	BUG_ON(me->mm);
+	cur->active_mm = &init_mm;
+	BUG_ON(cur->mm);
 	initialize_tlbstate_and_flush();
-	enter_lazy_tlb(&init_mm, me);
+	enter_lazy_tlb(&init_mm, cur);
 
-	/*
-	 * Initialize the TSS.  sp0 points to the entry trampoline stack
-	 * regardless of what task is running.
-	 */
+	/* Initialize the TSS. */
+	tss_setup_ist(tss);
+	tss_setup_io_bitmap(tss);
 	set_tss_desc(cpu, &get_cpu_entry_area(cpu)->tss.x86_tss);
+
 	load_TR_desc();
+	/*
+	 * sp0 points to the entry trampoline stack regardless of what task
+	 * is running.
+	 */
 	load_sp0((unsigned long)(cpu_entry_stack(cpu) + 1));
 
 	load_mm_ldt(&init_mm);
@@ -1895,6 +1923,8 @@ void cpu_init(void)
 	clear_all_debug_regs();
 	dbg_restore_debug_regs();
 
+	gdt_setup_doublefault_tss(cpu);
+
 	fpu__init_cpu();
 
 	if (is_uv_system())
@@ -1903,63 +1933,6 @@ void cpu_init(void)
 	load_fixmap_gdt(cpu);
 }
 
-#else
-
-void cpu_init(void)
-{
-	int cpu = smp_processor_id();
-	struct task_struct *curr = current;
-	struct tss_struct *t = &per_cpu(cpu_tss_rw, cpu);
-
-	wait_for_master_cpu(cpu);
-
-	show_ucode_info_early();
-
-	pr_info("Initializing CPU#%d\n", cpu);
-
-	if (cpu_feature_enabled(X86_FEATURE_VME) ||
-	    boot_cpu_has(X86_FEATURE_TSC) ||
-	    boot_cpu_has(X86_FEATURE_DE))
-		cr4_clear_bits(X86_CR4_VME|X86_CR4_PVI|X86_CR4_TSD|X86_CR4_DE);
-
-	load_current_idt();
-	switch_to_new_gdt(cpu);
-
-	/*
-	 * Set up and load the per-CPU TSS and LDT
-	 */
-	mmgrab(&init_mm);
-	curr->active_mm = &init_mm;
-	BUG_ON(curr->mm);
-	initialize_tlbstate_and_flush();
-	enter_lazy_tlb(&init_mm, curr);
-
-	/*
-	 * Initialize the TSS.  sp0 points to the entry trampoline stack
-	 * regardless of what task is running.
-	 */
-	set_tss_desc(cpu, &get_cpu_entry_area(cpu)->tss.x86_tss);
-	load_TR_desc();
-	load_sp0((unsigned long)(cpu_entry_stack(cpu) + 1));
-
-	load_mm_ldt(&init_mm);
-
-	t->x86_tss.io_bitmap_base = IO_BITMAP_OFFSET;
-
-#ifdef CONFIG_DOUBLEFAULT
-	/* Set up doublefault TSS pointer in the GDT */
-	__set_tss_desc(cpu, GDT_ENTRY_DOUBLEFAULT_TSS, &doublefault_tss);
-#endif
-
-	clear_all_debug_regs();
-	dbg_restore_debug_regs();
-
-	fpu__init_cpu();
-
-	load_fixmap_gdt(cpu);
-}
-#endif
-
 /*
  * The microcode loader calls this upon late microcode load to recheck features,
  * only when microcode has been updated. Caller holds microcode_mutex and CPU
diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c
index 11d5c5950e2d..4a900804a023 100644
--- a/arch/x86/kernel/cpu/intel.c
+++ b/arch/x86/kernel/cpu/intel.c
@@ -819,7 +819,7 @@ static const struct _tlb_table intel_tlb_table[] = {
 	{ 0x04, TLB_DATA_4M,		8,	" TLB_DATA 4 MByte pages, 4-way set associative" },
 	{ 0x05, TLB_DATA_4M,		32,	" TLB_DATA 4 MByte pages, 4-way set associative" },
 	{ 0x0b, TLB_INST_4M,		4,	" TLB_INST 4 MByte pages, 4-way set associative" },
-	{ 0x4f, TLB_INST_4K,		32,	" TLB_INST 4 KByte pages */" },
+	{ 0x4f, TLB_INST_4K,		32,	" TLB_INST 4 KByte pages" },
 	{ 0x50, TLB_INST_ALL,		64,	" TLB_INST 4 KByte and 2-MByte or 4-MByte pages" },
 	{ 0x51, TLB_INST_ALL,		128,	" TLB_INST 4 KByte and 2-MByte or 4-MByte pages" },
 	{ 0x52, TLB_INST_ALL,		256,	" TLB_INST 4 KByte and 2-MByte or 4-MByte pages" },
@@ -847,7 +847,7 @@ static const struct _tlb_table intel_tlb_table[] = {
 	{ 0xba, TLB_DATA_4K,		64,	" TLB_DATA 4 KByte pages, 4-way associative" },
 	{ 0xc0, TLB_DATA_4K_4M,		8,	" TLB_DATA 4 KByte and 4 MByte pages, 4-way associative" },
 	{ 0xc1, STLB_4K_2M,		1024,	" STLB 4 KByte and 2 MByte pages, 8-way associative" },
-	{ 0xc2, TLB_DATA_2M_4M,		16,	" DTLB 2 MByte/4MByte pages, 4-way associative" },
+	{ 0xc2, TLB_DATA_2M_4M,		16,	" TLB_DATA 2 MByte/4MByte pages, 4-way associative" },
 	{ 0xca, STLB_4K,		512,	" STLB 4 KByte pages, 4-way associative" },
 	{ 0x00, 0, 0 }
 };
@@ -859,8 +859,8 @@ static void intel_tlb_lookup(const unsigned char desc)
 		return;
 
 	/* look up this descriptor in the table */
-	for (k = 0; intel_tlb_table[k].descriptor != desc && \
-			intel_tlb_table[k].descriptor != 0; k++)
+	for (k = 0; intel_tlb_table[k].descriptor != desc &&
+	     intel_tlb_table[k].descriptor != 0; k++)
 		;
 
 	if (intel_tlb_table[k].tlb_type == 0)
diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c
index c656d92cd708..caa032ce3fe3 100644
--- a/arch/x86/kernel/cpu/mshyperv.c
+++ b/arch/x86/kernel/cpu/mshyperv.c
@@ -290,7 +290,12 @@ static void __init ms_hyperv_init_platform(void)
 	machine_ops.shutdown = hv_machine_shutdown;
 	machine_ops.crash_shutdown = hv_machine_crash_shutdown;
 #endif
-	mark_tsc_unstable("running on Hyper-V");
+	if (ms_hyperv.features & HV_X64_ACCESS_TSC_INVARIANT) {
+		wrmsrl(HV_X64_MSR_TSC_INVARIANT_CONTROL, 0x1);
+		setup_force_cpu_cap(X86_FEATURE_TSC_RELIABLE);
+	} else {
+		mark_tsc_unstable("running on Hyper-V");
+	}
 
 	/*
 	 * Generation 2 instances don't support reading the NMI status from
diff --git a/arch/x86/kernel/cpu/rdrand.c b/arch/x86/kernel/cpu/rdrand.c
index 5c900f9527ff..c4be62058dd9 100644
--- a/arch/x86/kernel/cpu/rdrand.c
+++ b/arch/x86/kernel/cpu/rdrand.c
@@ -29,7 +29,8 @@ __setup("nordrand", x86_rdrand_setup);
 #ifdef CONFIG_ARCH_RANDOM
 void x86_init_rdrand(struct cpuinfo_x86 *c)
 {
-	unsigned long tmp;
+	unsigned int changed = 0;
+	unsigned long tmp, prev;
 	int i;
 
 	if (!cpu_has(c, X86_FEATURE_RDRAND))
@@ -42,5 +43,24 @@ void x86_init_rdrand(struct cpuinfo_x86 *c)
 			return;
 		}
 	}
+
+	/*
+	 * Stupid sanity-check whether RDRAND does *actually* generate
+	 * some at least random-looking data.
+	 */
+	prev = tmp;
+	for (i = 0; i < SANITY_CHECK_LOOPS; i++) {
+		if (rdrand_long(&tmp)) {
+			if (prev != tmp)
+				changed++;
+
+			prev = tmp;
+		}
+	}
+
+	if (WARN_ON_ONCE(!changed))
+		pr_emerg(
+"RDRAND gives funky smelling output, might consider not using it by booting with \"nordrand\"");
+
 }
 #endif
diff --git a/arch/x86/kernel/crash.c b/arch/x86/kernel/crash.c
index eb651fbde92a..00fc55ac7ffa 100644
--- a/arch/x86/kernel/crash.c
+++ b/arch/x86/kernel/crash.c
@@ -24,6 +24,7 @@
 #include <linux/export.h>
 #include <linux/slab.h>
 #include <linux/vmalloc.h>
+#include <linux/memblock.h>
 
 #include <asm/processor.h>
 #include <asm/hardirq.h>
@@ -39,6 +40,7 @@
 #include <asm/virtext.h>
 #include <asm/intel_pt.h>
 #include <asm/crash.h>
+#include <asm/cmdline.h>
 
 /* Used while preparing memory map entries for second kernel */
 struct crash_memmap_data {
@@ -68,6 +70,19 @@ static inline void cpu_crash_vmclear_loaded_vmcss(void)
 	rcu_read_unlock();
 }
 
+/*
+ * When the crashkernel option is specified, only use the low
+ * 1M for the real mode trampoline.
+ */
+void __init crash_reserve_low_1M(void)
+{
+	if (cmdline_find_option(boot_command_line, "crashkernel", NULL, 0) < 0)
+		return;
+
+	memblock_reserve(0, 1<<20);
+	pr_info("Reserving the low 1M of memory for crashkernel\n");
+}
+
 #if defined(CONFIG_SMP) && defined(CONFIG_X86_LOCAL_APIC)
 
 static void kdump_nmi_callback(int cpu, struct pt_regs *regs)
@@ -173,8 +188,6 @@ void native_machine_crash_shutdown(struct pt_regs *regs)
 
 #ifdef CONFIG_KEXEC_FILE
 
-static unsigned long crash_zero_bytes;
-
 static int get_nr_ram_ranges_callback(struct resource *res, void *arg)
 {
 	unsigned int *nr_ranges = arg;
@@ -189,8 +202,7 @@ static struct crash_mem *fill_up_crash_elf_data(void)
 	unsigned int nr_ranges = 0;
 	struct crash_mem *cmem;
 
-	walk_system_ram_res(0, -1, &nr_ranges,
-				get_nr_ram_ranges_callback);
+	walk_system_ram_res(0, -1, &nr_ranges, get_nr_ram_ranges_callback);
 	if (!nr_ranges)
 		return NULL;
 
@@ -217,15 +229,19 @@ static int elf_header_exclude_ranges(struct crash_mem *cmem)
 {
 	int ret = 0;
 
+	/* Exclude the low 1M because it is always reserved */
+	ret = crash_exclude_mem_range(cmem, 0, 1<<20);
+	if (ret)
+		return ret;
+
 	/* Exclude crashkernel region */
 	ret = crash_exclude_mem_range(cmem, crashk_res.start, crashk_res.end);
 	if (ret)
 		return ret;
 
-	if (crashk_low_res.end) {
+	if (crashk_low_res.end)
 		ret = crash_exclude_mem_range(cmem, crashk_low_res.start,
-							crashk_low_res.end);
-	}
+					      crashk_low_res.end);
 
 	return ret;
 }
@@ -246,16 +262,13 @@ static int prepare_elf_headers(struct kimage *image, void **addr,
 					unsigned long *sz)
 {
 	struct crash_mem *cmem;
-	Elf64_Ehdr *ehdr;
-	Elf64_Phdr *phdr;
-	int ret, i;
+	int ret;
 
 	cmem = fill_up_crash_elf_data();
 	if (!cmem)
 		return -ENOMEM;
 
-	ret = walk_system_ram_res(0, -1, cmem,
-				prepare_elf64_ram_headers_callback);
+	ret = walk_system_ram_res(0, -1, cmem, prepare_elf64_ram_headers_callback);
 	if (ret)
 		goto out;
 
@@ -265,24 +278,8 @@ static int prepare_elf_headers(struct kimage *image, void **addr,
 		goto out;
 
 	/* By default prepare 64bit headers */
-	ret =  crash_prepare_elf64_headers(cmem,
-				IS_ENABLED(CONFIG_X86_64), addr, sz);
-	if (ret)
-		goto out;
+	ret =  crash_prepare_elf64_headers(cmem, IS_ENABLED(CONFIG_X86_64), addr, sz);
 
-	/*
-	 * If a range matches backup region, adjust offset to backup
-	 * segment.
-	 */
-	ehdr = (Elf64_Ehdr *)*addr;
-	phdr = (Elf64_Phdr *)(ehdr + 1);
-	for (i = 0; i < ehdr->e_phnum; phdr++, i++)
-		if (phdr->p_type == PT_LOAD &&
-				phdr->p_paddr == image->arch.backup_src_start &&
-				phdr->p_memsz == image->arch.backup_src_sz) {
-			phdr->p_offset = image->arch.backup_load_addr;
-			break;
-		}
 out:
 	vfree(cmem);
 	return ret;
@@ -296,8 +293,7 @@ static int add_e820_entry(struct boot_params *params, struct e820_entry *entry)
 	if (nr_e820_entries >= E820_MAX_ENTRIES_ZEROPAGE)
 		return 1;
 
-	memcpy(&params->e820_table[nr_e820_entries], entry,
-			sizeof(struct e820_entry));
+	memcpy(&params->e820_table[nr_e820_entries], entry, sizeof(struct e820_entry));
 	params->e820_entries++;
 	return 0;
 }
@@ -321,19 +317,11 @@ static int memmap_exclude_ranges(struct kimage *image, struct crash_mem *cmem,
 				 unsigned long long mend)
 {
 	unsigned long start, end;
-	int ret = 0;
 
 	cmem->ranges[0].start = mstart;
 	cmem->ranges[0].end = mend;
 	cmem->nr_ranges = 1;
 
-	/* Exclude Backup region */
-	start = image->arch.backup_load_addr;
-	end = start + image->arch.backup_src_sz - 1;
-	ret = crash_exclude_mem_range(cmem, start, end);
-	if (ret)
-		return ret;
-
 	/* Exclude elf header region */
 	start = image->arch.elf_load_addr;
 	end = start + image->arch.elf_headers_sz - 1;
@@ -356,28 +344,28 @@ int crash_setup_memmap_entries(struct kimage *image, struct boot_params *params)
 	memset(&cmd, 0, sizeof(struct crash_memmap_data));
 	cmd.params = params;
 
-	/* Add first 640K segment */
-	ei.addr = image->arch.backup_src_start;
-	ei.size = image->arch.backup_src_sz;
-	ei.type = E820_TYPE_RAM;
-	add_e820_entry(params, &ei);
+	/* Add the low 1M */
+	cmd.type = E820_TYPE_RAM;
+	flags = IORESOURCE_SYSTEM_RAM | IORESOURCE_BUSY;
+	walk_iomem_res_desc(IORES_DESC_NONE, flags, 0, (1<<20)-1, &cmd,
+			    memmap_entry_callback);
 
 	/* Add ACPI tables */
 	cmd.type = E820_TYPE_ACPI;
 	flags = IORESOURCE_MEM | IORESOURCE_BUSY;
 	walk_iomem_res_desc(IORES_DESC_ACPI_TABLES, flags, 0, -1, &cmd,
-		       memmap_entry_callback);
+			    memmap_entry_callback);
 
 	/* Add ACPI Non-volatile Storage */
 	cmd.type = E820_TYPE_NVS;
 	walk_iomem_res_desc(IORES_DESC_ACPI_NV_STORAGE, flags, 0, -1, &cmd,
-			memmap_entry_callback);
+			    memmap_entry_callback);
 
 	/* Add e820 reserved ranges */
 	cmd.type = E820_TYPE_RESERVED;
 	flags = IORESOURCE_MEM;
 	walk_iomem_res_desc(IORES_DESC_RESERVED, flags, 0, -1, &cmd,
-			   memmap_entry_callback);
+			    memmap_entry_callback);
 
 	/* Add crashk_low_res region */
 	if (crashk_low_res.end) {
@@ -388,8 +376,7 @@ int crash_setup_memmap_entries(struct kimage *image, struct boot_params *params)
 	}
 
 	/* Exclude some ranges from crashk_res and add rest to memmap */
-	ret = memmap_exclude_ranges(image, cmem, crashk_res.start,
-						crashk_res.end);
+	ret = memmap_exclude_ranges(image, cmem, crashk_res.start, crashk_res.end);
 	if (ret)
 		goto out;
 
@@ -409,55 +396,12 @@ out:
 	return ret;
 }
 
-static int determine_backup_region(struct resource *res, void *arg)
-{
-	struct kimage *image = arg;
-
-	image->arch.backup_src_start = res->start;
-	image->arch.backup_src_sz = resource_size(res);
-
-	/* Expecting only one range for backup region */
-	return 1;
-}
-
 int crash_load_segments(struct kimage *image)
 {
 	int ret;
 	struct kexec_buf kbuf = { .image = image, .buf_min = 0,
 				  .buf_max = ULONG_MAX, .top_down = false };
 
-	/*
-	 * Determine and load a segment for backup area. First 640K RAM
-	 * region is backup source
-	 */
-
-	ret = walk_system_ram_res(KEXEC_BACKUP_SRC_START, KEXEC_BACKUP_SRC_END,
-				image, determine_backup_region);
-
-	/* Zero or postive return values are ok */
-	if (ret < 0)
-		return ret;
-
-	/* Add backup segment. */
-	if (image->arch.backup_src_sz) {
-		kbuf.buffer = &crash_zero_bytes;
-		kbuf.bufsz = sizeof(crash_zero_bytes);
-		kbuf.memsz = image->arch.backup_src_sz;
-		kbuf.buf_align = PAGE_SIZE;
-		/*
-		 * Ideally there is no source for backup segment. This is
-		 * copied in purgatory after crash. Just add a zero filled
-		 * segment for now to make sure checksum logic works fine.
-		 */
-		ret = kexec_add_buffer(&kbuf);
-		if (ret)
-			return ret;
-		image->arch.backup_load_addr = kbuf.mem;
-		pr_debug("Loaded backup region at 0x%lx backup_start=0x%lx memsz=0x%lx\n",
-			 image->arch.backup_load_addr,
-			 image->arch.backup_src_start, kbuf.memsz);
-	}
-
 	/* Prepare elf headers and add a segment */
 	ret = prepare_elf_headers(image, &kbuf.buffer, &kbuf.bufsz);
 	if (ret)
diff --git a/arch/x86/kernel/doublefault.c b/arch/x86/kernel/doublefault.c
index 0b8cedb20d6d..0d6c657593f8 100644
--- a/arch/x86/kernel/doublefault.c
+++ b/arch/x86/kernel/doublefault.c
@@ -54,7 +54,7 @@ struct x86_hw_tss doublefault_tss __cacheline_aligned = {
 	.sp0		= STACK_START,
 	.ss0		= __KERNEL_DS,
 	.ldt		= 0,
-	.io_bitmap_base	= INVALID_IO_BITMAP_OFFSET,
+	.io_bitmap_base	= IO_BITMAP_OFFSET_INVALID,
 
 	.ip		= (unsigned long) doublefault_fn,
 	/* 0x2 bit is always set */
@@ -65,6 +65,9 @@ struct x86_hw_tss doublefault_tss __cacheline_aligned = {
 	.ss		= __KERNEL_DS,
 	.ds		= __USER_DS,
 	.fs		= __KERNEL_PERCPU,
+#ifndef CONFIG_X86_32_LAZY_GS
+	.gs		= __KERNEL_STACK_CANARY,
+#endif
 
 	.__cr3		= __pa_nodebug(swapper_pg_dir),
 };
diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c
index 7da2bcd2b8eb..c5399e80c59c 100644
--- a/arch/x86/kernel/e820.c
+++ b/arch/x86/kernel/e820.c
@@ -190,6 +190,7 @@ static void __init e820_print_type(enum e820_type type)
 	case E820_TYPE_RAM:		/* Fall through: */
 	case E820_TYPE_RESERVED_KERN:	pr_cont("usable");			break;
 	case E820_TYPE_RESERVED:	pr_cont("reserved");			break;
+	case E820_TYPE_SOFT_RESERVED:	pr_cont("soft reserved");		break;
 	case E820_TYPE_ACPI:		pr_cont("ACPI data");			break;
 	case E820_TYPE_NVS:		pr_cont("ACPI NVS");			break;
 	case E820_TYPE_UNUSABLE:	pr_cont("unusable");			break;
@@ -999,6 +1000,17 @@ void __init e820__reserve_setup_data(void)
 		data = early_memremap(pa_data, sizeof(*data));
 		e820__range_update(pa_data, sizeof(*data)+data->len, E820_TYPE_RAM, E820_TYPE_RESERVED_KERN);
 		e820__range_update_kexec(pa_data, sizeof(*data)+data->len, E820_TYPE_RAM, E820_TYPE_RESERVED_KERN);
+
+		if (data->type == SETUP_INDIRECT &&
+		    ((struct setup_indirect *)data->data)->type != SETUP_INDIRECT) {
+			e820__range_update(((struct setup_indirect *)data->data)->addr,
+					   ((struct setup_indirect *)data->data)->len,
+					   E820_TYPE_RAM, E820_TYPE_RESERVED_KERN);
+			e820__range_update_kexec(((struct setup_indirect *)data->data)->addr,
+						 ((struct setup_indirect *)data->data)->len,
+						 E820_TYPE_RAM, E820_TYPE_RESERVED_KERN);
+		}
+
 		pa_data = data->next;
 		early_memunmap(data, sizeof(*data));
 	}
@@ -1037,6 +1049,7 @@ static const char *__init e820_type_to_string(struct e820_entry *entry)
 	case E820_TYPE_PRAM:		return "Persistent Memory (legacy)";
 	case E820_TYPE_PMEM:		return "Persistent Memory";
 	case E820_TYPE_RESERVED:	return "Reserved";
+	case E820_TYPE_SOFT_RESERVED:	return "Soft Reserved";
 	default:			return "Unknown E820 type";
 	}
 }
@@ -1052,6 +1065,7 @@ static unsigned long __init e820_type_to_iomem_type(struct e820_entry *entry)
 	case E820_TYPE_PRAM:		/* Fall-through: */
 	case E820_TYPE_PMEM:		/* Fall-through: */
 	case E820_TYPE_RESERVED:	/* Fall-through: */
+	case E820_TYPE_SOFT_RESERVED:	/* Fall-through: */
 	default:			return IORESOURCE_MEM;
 	}
 }
@@ -1064,6 +1078,7 @@ static unsigned long __init e820_type_to_iores_desc(struct e820_entry *entry)
 	case E820_TYPE_PMEM:		return IORES_DESC_PERSISTENT_MEMORY;
 	case E820_TYPE_PRAM:		return IORES_DESC_PERSISTENT_MEMORY_LEGACY;
 	case E820_TYPE_RESERVED:	return IORES_DESC_RESERVED;
+	case E820_TYPE_SOFT_RESERVED:	return IORES_DESC_SOFT_RESERVED;
 	case E820_TYPE_RESERVED_KERN:	/* Fall-through: */
 	case E820_TYPE_RAM:		/* Fall-through: */
 	case E820_TYPE_UNUSABLE:	/* Fall-through: */
@@ -1078,11 +1093,12 @@ static bool __init do_mark_busy(enum e820_type type, struct resource *res)
 		return true;
 
 	/*
-	 * Treat persistent memory like device memory, i.e. reserve it
-	 * for exclusive use of a driver
+	 * Treat persistent memory and other special memory ranges like
+	 * device memory, i.e. reserve it for exclusive use of a driver
 	 */
 	switch (type) {
 	case E820_TYPE_RESERVED:
+	case E820_TYPE_SOFT_RESERVED:
 	case E820_TYPE_PRAM:
 	case E820_TYPE_PMEM:
 		return false;
@@ -1285,6 +1301,9 @@ void __init e820__memblock_setup(void)
 		if (end != (resource_size_t)end)
 			continue;
 
+		if (entry->type == E820_TYPE_SOFT_RESERVED)
+			memblock_reserve(entry->addr, entry->size);
+
 		if (entry->type != E820_TYPE_RAM && entry->type != E820_TYPE_RESERVED_KERN)
 			continue;
 
diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c
index e5cb67d67c03..319be936c348 100644
--- a/arch/x86/kernel/fpu/xstate.c
+++ b/arch/x86/kernel/fpu/xstate.c
@@ -60,7 +60,7 @@ u64 xfeatures_mask __read_mostly;
 
 static unsigned int xstate_offsets[XFEATURE_MAX] = { [ 0 ... XFEATURE_MAX - 1] = -1};
 static unsigned int xstate_sizes[XFEATURE_MAX]   = { [ 0 ... XFEATURE_MAX - 1] = -1};
-static unsigned int xstate_comp_offsets[sizeof(xfeatures_mask)*8];
+static unsigned int xstate_comp_offsets[XFEATURE_MAX] = { [ 0 ... XFEATURE_MAX - 1] = -1};
 
 /*
  * The XSAVE area of kernel can be in standard or compacted format;
@@ -254,10 +254,13 @@ static void __init setup_xstate_features(void)
 	 * in the fixed offsets in the xsave area in either compacted form
 	 * or standard form.
 	 */
-	xstate_offsets[0] = 0;
-	xstate_sizes[0] = offsetof(struct fxregs_state, xmm_space);
-	xstate_offsets[1] = xstate_sizes[0];
-	xstate_sizes[1] = FIELD_SIZEOF(struct fxregs_state, xmm_space);
+	xstate_offsets[XFEATURE_FP]	= 0;
+	xstate_sizes[XFEATURE_FP]	= offsetof(struct fxregs_state,
+						   xmm_space);
+
+	xstate_offsets[XFEATURE_SSE]	= xstate_sizes[XFEATURE_FP];
+	xstate_sizes[XFEATURE_SSE]	= FIELD_SIZEOF(struct fxregs_state,
+						       xmm_space);
 
 	for (i = FIRST_EXTENDED_XFEATURE; i < XFEATURE_MAX; i++) {
 		if (!xfeature_enabled(i))
@@ -342,7 +345,7 @@ static int xfeature_is_aligned(int xfeature_nr)
  */
 static void __init setup_xstate_comp(void)
 {
-	unsigned int xstate_comp_sizes[sizeof(xfeatures_mask)*8];
+	unsigned int xstate_comp_sizes[XFEATURE_MAX];
 	int i;
 
 	/*
@@ -350,8 +353,9 @@ static void __init setup_xstate_comp(void)
 	 * in the fixed offsets in the xsave area in either compacted form
 	 * or standard form.
 	 */
-	xstate_comp_offsets[0] = 0;
-	xstate_comp_offsets[1] = offsetof(struct fxregs_state, xmm_space);
+	xstate_comp_offsets[XFEATURE_FP] = 0;
+	xstate_comp_offsets[XFEATURE_SSE] = offsetof(struct fxregs_state,
+						     xmm_space);
 
 	if (!boot_cpu_has(X86_FEATURE_XSAVES)) {
 		for (i = FIRST_EXTENDED_XFEATURE; i < XFEATURE_MAX; i++) {
@@ -840,7 +844,7 @@ void *get_xsave_addr(struct xregs_state *xsave, int xfeature_nr)
 
 	/*
 	 * We should not ever be requesting features that we
-	 * have not enabled.  Remember that pcntxt_mask is
+	 * have not enabled.  Remember that xfeatures_mask is
 	 * what we write to the XCR0 register.
 	 */
 	WARN_ONCE(!(xfeatures_mask & BIT_ULL(xfeature_nr)),
diff --git a/arch/x86/kernel/ftrace_32.S b/arch/x86/kernel/ftrace_32.S
index 073aab525d80..e8a9f8370112 100644
--- a/arch/x86/kernel/ftrace_32.S
+++ b/arch/x86/kernel/ftrace_32.S
@@ -12,20 +12,18 @@
 #include <asm/frame.h>
 #include <asm/asm-offsets.h>
 
-# define function_hook	__fentry__
-EXPORT_SYMBOL(__fentry__)
-
 #ifdef CONFIG_FRAME_POINTER
 # define MCOUNT_FRAME			1	/* using frame = true  */
 #else
 # define MCOUNT_FRAME			0	/* using frame = false */
 #endif
 
-ENTRY(function_hook)
+SYM_FUNC_START(__fentry__)
 	ret
-END(function_hook)
+SYM_FUNC_END(__fentry__)
+EXPORT_SYMBOL(__fentry__)
 
-ENTRY(ftrace_caller)
+SYM_CODE_START(ftrace_caller)
 
 #ifdef CONFIG_FRAME_POINTER
 	/*
@@ -85,11 +83,11 @@ ftrace_graph_call:
 #endif
 
 /* This is weak to keep gas from relaxing the jumps */
-WEAK(ftrace_stub)
+SYM_INNER_LABEL_ALIGN(ftrace_stub, SYM_L_WEAK)
 	ret
-END(ftrace_caller)
+SYM_CODE_END(ftrace_caller)
 
-ENTRY(ftrace_regs_caller)
+SYM_CODE_START(ftrace_regs_caller)
 	/*
 	 * We're here from an mcount/fentry CALL, and the stack frame looks like:
 	 *
@@ -138,7 +136,7 @@ ENTRY(ftrace_regs_caller)
 	movl	function_trace_op, %ecx	# 3rd argument: ftrace_pos
 	pushl	%esp			# 4th argument: pt_regs
 
-GLOBAL(ftrace_regs_call)
+SYM_INNER_LABEL(ftrace_regs_call, SYM_L_GLOBAL)
 	call	ftrace_stub
 
 	addl	$4, %esp		# skip 4th argument
@@ -163,9 +161,10 @@ GLOBAL(ftrace_regs_call)
 	popl	%eax
 
 	jmp	.Lftrace_ret
+SYM_CODE_END(ftrace_regs_caller)
 
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
-ENTRY(ftrace_graph_caller)
+SYM_CODE_START(ftrace_graph_caller)
 	pushl	%eax
 	pushl	%ecx
 	pushl	%edx
@@ -179,7 +178,7 @@ ENTRY(ftrace_graph_caller)
 	popl	%ecx
 	popl	%eax
 	ret
-END(ftrace_graph_caller)
+SYM_CODE_END(ftrace_graph_caller)
 
 .globl return_to_handler
 return_to_handler:
diff --git a/arch/x86/kernel/ftrace_64.S b/arch/x86/kernel/ftrace_64.S
index 809d54397dba..6e8961ca3605 100644
--- a/arch/x86/kernel/ftrace_64.S
+++ b/arch/x86/kernel/ftrace_64.S
@@ -14,9 +14,6 @@
 	.code64
 	.section .entry.text, "ax"
 
-# define function_hook	__fentry__
-EXPORT_SYMBOL(__fentry__)
-
 #ifdef CONFIG_FRAME_POINTER
 /* Save parent and function stack frames (rip and rbp) */
 #  define MCOUNT_FRAME_SIZE	(8+16*2)
@@ -132,22 +129,23 @@ EXPORT_SYMBOL(__fentry__)
 
 #ifdef CONFIG_DYNAMIC_FTRACE
 
-ENTRY(function_hook)
+SYM_FUNC_START(__fentry__)
 	retq
-ENDPROC(function_hook)
+SYM_FUNC_END(__fentry__)
+EXPORT_SYMBOL(__fentry__)
 
-ENTRY(ftrace_caller)
+SYM_FUNC_START(ftrace_caller)
 	/* save_mcount_regs fills in first two parameters */
 	save_mcount_regs
 
-GLOBAL(ftrace_caller_op_ptr)
+SYM_INNER_LABEL(ftrace_caller_op_ptr, SYM_L_GLOBAL)
 	/* Load the ftrace_ops into the 3rd parameter */
 	movq function_trace_op(%rip), %rdx
 
 	/* regs go into 4th parameter (but make it NULL) */
 	movq $0, %rcx
 
-GLOBAL(ftrace_call)
+SYM_INNER_LABEL(ftrace_call, SYM_L_GLOBAL)
 	call ftrace_stub
 
 	restore_mcount_regs
@@ -157,10 +155,10 @@ GLOBAL(ftrace_call)
 	 * think twice before adding any new code or changing the
 	 * layout here.
 	 */
-GLOBAL(ftrace_epilogue)
+SYM_INNER_LABEL(ftrace_epilogue, SYM_L_GLOBAL)
 
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
-GLOBAL(ftrace_graph_call)
+SYM_INNER_LABEL(ftrace_graph_call, SYM_L_GLOBAL)
 	jmp ftrace_stub
 #endif
 
@@ -168,11 +166,11 @@ GLOBAL(ftrace_graph_call)
  * This is weak to keep gas from relaxing the jumps.
  * It is also used to copy the retq for trampolines.
  */
-WEAK(ftrace_stub)
+SYM_INNER_LABEL_ALIGN(ftrace_stub, SYM_L_WEAK)
 	retq
-ENDPROC(ftrace_caller)
+SYM_FUNC_END(ftrace_caller)
 
-ENTRY(ftrace_regs_caller)
+SYM_FUNC_START(ftrace_regs_caller)
 	/* Save the current flags before any operations that can change them */
 	pushfq
 
@@ -180,7 +178,7 @@ ENTRY(ftrace_regs_caller)
 	save_mcount_regs 8
 	/* save_mcount_regs fills in first two parameters */
 
-GLOBAL(ftrace_regs_caller_op_ptr)
+SYM_INNER_LABEL(ftrace_regs_caller_op_ptr, SYM_L_GLOBAL)
 	/* Load the ftrace_ops into the 3rd parameter */
 	movq function_trace_op(%rip), %rdx
 
@@ -209,7 +207,7 @@ GLOBAL(ftrace_regs_caller_op_ptr)
 	/* regs go into 4th parameter */
 	leaq (%rsp), %rcx
 
-GLOBAL(ftrace_regs_call)
+SYM_INNER_LABEL(ftrace_regs_call, SYM_L_GLOBAL)
 	call ftrace_stub
 
 	/* Copy flags back to SS, to restore them */
@@ -239,16 +237,16 @@ GLOBAL(ftrace_regs_call)
 	 * The trampoline will add the code to jump
 	 * to the return.
 	 */
-GLOBAL(ftrace_regs_caller_end)
+SYM_INNER_LABEL(ftrace_regs_caller_end, SYM_L_GLOBAL)
 
 	jmp ftrace_epilogue
 
-ENDPROC(ftrace_regs_caller)
+SYM_FUNC_END(ftrace_regs_caller)
 
 
 #else /* ! CONFIG_DYNAMIC_FTRACE */
 
-ENTRY(function_hook)
+SYM_FUNC_START(__fentry__)
 	cmpq $ftrace_stub, ftrace_trace_function
 	jnz trace
 
@@ -261,7 +259,7 @@ fgraph_trace:
 	jnz ftrace_graph_caller
 #endif
 
-GLOBAL(ftrace_stub)
+SYM_INNER_LABEL(ftrace_stub, SYM_L_GLOBAL)
 	retq
 
 trace:
@@ -279,11 +277,12 @@ trace:
 	restore_mcount_regs
 
 	jmp fgraph_trace
-ENDPROC(function_hook)
+SYM_FUNC_END(__fentry__)
+EXPORT_SYMBOL(__fentry__)
 #endif /* CONFIG_DYNAMIC_FTRACE */
 
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
-ENTRY(ftrace_graph_caller)
+SYM_FUNC_START(ftrace_graph_caller)
 	/* Saves rbp into %rdx and fills first parameter  */
 	save_mcount_regs
 
@@ -294,9 +293,9 @@ ENTRY(ftrace_graph_caller)
 	restore_mcount_regs
 
 	retq
-ENDPROC(ftrace_graph_caller)
+SYM_FUNC_END(ftrace_graph_caller)
 
-ENTRY(return_to_handler)
+SYM_CODE_START(return_to_handler)
 	UNWIND_HINT_EMPTY
 	subq  $24, %rsp
 
@@ -312,5 +311,5 @@ ENTRY(return_to_handler)
 	movq (%rsp), %rax
 	addq $24, %rsp
 	JMP_NOSPEC %rdi
-END(return_to_handler)
+SYM_CODE_END(return_to_handler)
 #endif
diff --git a/arch/x86/kernel/head_32.S b/arch/x86/kernel/head_32.S
index 30f9cb2c0b55..3923ab4630d7 100644
--- a/arch/x86/kernel/head_32.S
+++ b/arch/x86/kernel/head_32.S
@@ -64,7 +64,7 @@ RESERVE_BRK(pagetables, INIT_MAP_SIZE)
  * can.
  */
 __HEAD
-ENTRY(startup_32)
+SYM_CODE_START(startup_32)
 	movl pa(initial_stack),%ecx
 	
 	/* test KEEP_SEGMENTS flag to see if the bootloader is asking
@@ -156,7 +156,7 @@ ENTRY(startup_32)
 	jmp *%eax
 
 .Lbad_subarch:
-WEAK(xen_entry)
+SYM_INNER_LABEL_ALIGN(xen_entry, SYM_L_WEAK)
 	/* Unknown implementation; there's really
 	   nothing we can do at this point. */
 	ud2a
@@ -172,6 +172,7 @@ num_subarch_entries = (. - subarch_entries) / 4
 #else
 	jmp .Ldefault_entry
 #endif /* CONFIG_PARAVIRT */
+SYM_CODE_END(startup_32)
 
 #ifdef CONFIG_HOTPLUG_CPU
 /*
@@ -179,12 +180,12 @@ num_subarch_entries = (. - subarch_entries) / 4
  * up already except stack. We just set up stack here. Then call
  * start_secondary().
  */
-ENTRY(start_cpu0)
+SYM_FUNC_START(start_cpu0)
 	movl initial_stack, %ecx
 	movl %ecx, %esp
 	call *(initial_code)
 1:	jmp 1b
-ENDPROC(start_cpu0)
+SYM_FUNC_END(start_cpu0)
 #endif
 
 /*
@@ -195,7 +196,7 @@ ENDPROC(start_cpu0)
  * If cpu hotplug is not supported then this code can go in init section
  * which will be freed later
  */
-ENTRY(startup_32_smp)
+SYM_FUNC_START(startup_32_smp)
 	cld
 	movl $(__BOOT_DS),%eax
 	movl %eax,%ds
@@ -362,7 +363,7 @@ ENTRY(startup_32_smp)
 
 	call *(initial_code)
 1:	jmp 1b
-ENDPROC(startup_32_smp)
+SYM_FUNC_END(startup_32_smp)
 
 #include "verify_cpu.S"
 
@@ -392,7 +393,7 @@ setup_once:
 	andl $0,setup_once_ref	/* Once is enough, thanks */
 	ret
 
-ENTRY(early_idt_handler_array)
+SYM_FUNC_START(early_idt_handler_array)
 	# 36(%esp) %eflags
 	# 32(%esp) %cs
 	# 28(%esp) %eip
@@ -407,9 +408,9 @@ ENTRY(early_idt_handler_array)
 	i = i + 1
 	.fill early_idt_handler_array + i*EARLY_IDT_HANDLER_SIZE - ., 1, 0xcc
 	.endr
-ENDPROC(early_idt_handler_array)
+SYM_FUNC_END(early_idt_handler_array)
 	
-early_idt_handler_common:
+SYM_CODE_START_LOCAL(early_idt_handler_common)
 	/*
 	 * The stack is the hardware frame, an error code or zero, and the
 	 * vector number.
@@ -460,10 +461,10 @@ early_idt_handler_common:
 	decl	%ss:early_recursion_flag
 	addl	$4, %esp	/* pop pt_regs->orig_ax */
 	iret
-ENDPROC(early_idt_handler_common)
+SYM_CODE_END(early_idt_handler_common)
 
 /* This is the default interrupt "handler" :-) */
-ENTRY(early_ignore_irq)
+SYM_FUNC_START(early_ignore_irq)
 	cld
 #ifdef CONFIG_PRINTK
 	pushl %eax
@@ -498,19 +499,16 @@ ENTRY(early_ignore_irq)
 hlt_loop:
 	hlt
 	jmp hlt_loop
-ENDPROC(early_ignore_irq)
+SYM_FUNC_END(early_ignore_irq)
 
 __INITDATA
 	.align 4
-GLOBAL(early_recursion_flag)
-	.long 0
+SYM_DATA(early_recursion_flag, .long 0)
 
 __REFDATA
 	.align 4
-ENTRY(initial_code)
-	.long i386_start_kernel
-ENTRY(setup_once_ref)
-	.long setup_once
+SYM_DATA(initial_code,		.long i386_start_kernel)
+SYM_DATA(setup_once_ref,	.long setup_once)
 
 #ifdef CONFIG_PAGE_TABLE_ISOLATION
 #define	PGD_ALIGN	(2 * PAGE_SIZE)
@@ -553,7 +551,7 @@ EXPORT_SYMBOL(empty_zero_page)
 __PAGE_ALIGNED_DATA
 	/* Page-aligned for the benefit of paravirt? */
 	.align PGD_ALIGN
-ENTRY(initial_page_table)
+SYM_DATA_START(initial_page_table)
 	.long	pa(initial_pg_pmd+PGD_IDENT_ATTR),0	/* low identity map */
 # if KPMDS == 3
 	.long	pa(initial_pg_pmd+PGD_IDENT_ATTR),0
@@ -571,17 +569,28 @@ ENTRY(initial_page_table)
 #  error "Kernel PMDs should be 1, 2 or 3"
 # endif
 	.align PAGE_SIZE		/* needs to be page-sized too */
+
+#ifdef CONFIG_PAGE_TABLE_ISOLATION
+	/*
+	 * PTI needs another page so sync_initial_pagetable() works correctly
+	 * and does not scribble over the data which is placed behind the
+	 * actual initial_page_table. See clone_pgd_range().
+	 */
+	.fill 1024, 4, 0
+#endif
+
+SYM_DATA_END(initial_page_table)
 #endif
 
 .data
 .balign 4
-ENTRY(initial_stack)
-	/*
-	 * The SIZEOF_PTREGS gap is a convention which helps the in-kernel
-	 * unwinder reliably detect the end of the stack.
-	 */
-	.long init_thread_union + THREAD_SIZE - SIZEOF_PTREGS - \
-	      TOP_OF_KERNEL_STACK_PADDING;
+/*
+ * The SIZEOF_PTREGS gap is a convention which helps the in-kernel unwinder
+ * reliably detect the end of the stack.
+ */
+SYM_DATA(initial_stack,
+		.long init_thread_union + THREAD_SIZE -
+		SIZEOF_PTREGS - TOP_OF_KERNEL_STACK_PADDING)
 
 __INITRODATA
 int_msg:
@@ -597,27 +606,28 @@ int_msg:
  */
 
 	.data
-.globl boot_gdt_descr
-
 	ALIGN
 # early boot GDT descriptor (must use 1:1 address mapping)
 	.word 0				# 32 bit align gdt_desc.address
-boot_gdt_descr:
+SYM_DATA_START_LOCAL(boot_gdt_descr)
 	.word __BOOT_DS+7
 	.long boot_gdt - __PAGE_OFFSET
+SYM_DATA_END(boot_gdt_descr)
 
 # boot GDT descriptor (later on used by CPU#0):
 	.word 0				# 32 bit align gdt_desc.address
-ENTRY(early_gdt_descr)
+SYM_DATA_START(early_gdt_descr)
 	.word GDT_ENTRIES*8-1
 	.long gdt_page			/* Overwritten for secondary CPUs */
+SYM_DATA_END(early_gdt_descr)
 
 /*
  * The boot_gdt must mirror the equivalent in setup.S and is
  * used only for booting.
  */
 	.align L1_CACHE_BYTES
-ENTRY(boot_gdt)
+SYM_DATA_START(boot_gdt)
 	.fill GDT_ENTRY_BOOT_CS,8,0
 	.quad 0x00cf9a000000ffff	/* kernel 4GB code at 0x00000000 */
 	.quad 0x00cf92000000ffff	/* kernel 4GB data at 0x00000000 */
+SYM_DATA_END(boot_gdt)
diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S
index f3d3e9646a99..4bbc770af632 100644
--- a/arch/x86/kernel/head_64.S
+++ b/arch/x86/kernel/head_64.S
@@ -49,8 +49,7 @@ L3_START_KERNEL = pud_index(__START_KERNEL_map)
 	.text
 	__HEAD
 	.code64
-	.globl startup_64
-startup_64:
+SYM_CODE_START_NOALIGN(startup_64)
 	UNWIND_HINT_EMPTY
 	/*
 	 * At this point the CPU runs in 64bit mode CS.L = 1 CS.D = 0,
@@ -90,7 +89,9 @@ startup_64:
 	/* Form the CR3 value being sure to include the CR3 modifier */
 	addq	$(early_top_pgt - __START_KERNEL_map), %rax
 	jmp 1f
-ENTRY(secondary_startup_64)
+SYM_CODE_END(startup_64)
+
+SYM_CODE_START(secondary_startup_64)
 	UNWIND_HINT_EMPTY
 	/*
 	 * At this point the CPU runs in 64bit mode CS.L = 1 CS.D = 0,
@@ -240,7 +241,7 @@ ENTRY(secondary_startup_64)
 	pushq	%rax		# target address in negative space
 	lretq
 .Lafter_lret:
-END(secondary_startup_64)
+SYM_CODE_END(secondary_startup_64)
 
 #include "verify_cpu.S"
 
@@ -250,30 +251,28 @@ END(secondary_startup_64)
  * up already except stack. We just set up stack here. Then call
  * start_secondary() via .Ljump_to_C_code.
  */
-ENTRY(start_cpu0)
+SYM_CODE_START(start_cpu0)
 	UNWIND_HINT_EMPTY
 	movq	initial_stack(%rip), %rsp
 	jmp	.Ljump_to_C_code
-END(start_cpu0)
+SYM_CODE_END(start_cpu0)
 #endif
 
 	/* Both SMP bootup and ACPI suspend change these variables */
 	__REFDATA
 	.balign	8
-	GLOBAL(initial_code)
-	.quad	x86_64_start_kernel
-	GLOBAL(initial_gs)
-	.quad	INIT_PER_CPU_VAR(fixed_percpu_data)
-	GLOBAL(initial_stack)
-	/*
-	 * The SIZEOF_PTREGS gap is a convention which helps the in-kernel
-	 * unwinder reliably detect the end of the stack.
-	 */
-	.quad  init_thread_union + THREAD_SIZE - SIZEOF_PTREGS
+SYM_DATA(initial_code,	.quad x86_64_start_kernel)
+SYM_DATA(initial_gs,	.quad INIT_PER_CPU_VAR(fixed_percpu_data))
+
+/*
+ * The SIZEOF_PTREGS gap is a convention which helps the in-kernel unwinder
+ * reliably detect the end of the stack.
+ */
+SYM_DATA(initial_stack, .quad init_thread_union + THREAD_SIZE - SIZEOF_PTREGS)
 	__FINITDATA
 
 	__INIT
-ENTRY(early_idt_handler_array)
+SYM_CODE_START(early_idt_handler_array)
 	i = 0
 	.rept NUM_EXCEPTION_VECTORS
 	.if ((EXCEPTION_ERRCODE_MASK >> i) & 1) == 0
@@ -289,9 +288,9 @@ ENTRY(early_idt_handler_array)
 	.fill early_idt_handler_array + i*EARLY_IDT_HANDLER_SIZE - ., 1, 0xcc
 	.endr
 	UNWIND_HINT_IRET_REGS offset=16
-END(early_idt_handler_array)
+SYM_CODE_END(early_idt_handler_array)
 
-early_idt_handler_common:
+SYM_CODE_START_LOCAL(early_idt_handler_common)
 	/*
 	 * The stack is the hardware frame, an error code or zero, and the
 	 * vector number.
@@ -333,17 +332,11 @@ early_idt_handler_common:
 20:
 	decl early_recursion_flag(%rip)
 	jmp restore_regs_and_return_to_kernel
-END(early_idt_handler_common)
+SYM_CODE_END(early_idt_handler_common)
 
-	__INITDATA
 
-	.balign 4
-GLOBAL(early_recursion_flag)
-	.long 0
-
-#define NEXT_PAGE(name) \
-	.balign	PAGE_SIZE; \
-GLOBAL(name)
+#define SYM_DATA_START_PAGE_ALIGNED(name)			\
+	SYM_START(name, SYM_L_GLOBAL, .balign PAGE_SIZE)
 
 #ifdef CONFIG_PAGE_TABLE_ISOLATION
 /*
@@ -358,11 +351,11 @@ GLOBAL(name)
  */
 #define PTI_USER_PGD_FILL	512
 /* This ensures they are 8k-aligned: */
-#define NEXT_PGD_PAGE(name) \
-	.balign 2 * PAGE_SIZE; \
-GLOBAL(name)
+#define SYM_DATA_START_PTI_ALIGNED(name) \
+	SYM_START(name, SYM_L_GLOBAL, .balign 2 * PAGE_SIZE)
 #else
-#define NEXT_PGD_PAGE(name) NEXT_PAGE(name)
+#define SYM_DATA_START_PTI_ALIGNED(name) \
+	SYM_DATA_START_PAGE_ALIGNED(name)
 #define PTI_USER_PGD_FILL	0
 #endif
 
@@ -375,17 +368,23 @@ GLOBAL(name)
 	.endr
 
 	__INITDATA
-NEXT_PGD_PAGE(early_top_pgt)
+	.balign 4
+
+SYM_DATA_START_PTI_ALIGNED(early_top_pgt)
 	.fill	512,8,0
 	.fill	PTI_USER_PGD_FILL,8,0
+SYM_DATA_END(early_top_pgt)
 
-NEXT_PAGE(early_dynamic_pgts)
+SYM_DATA_START_PAGE_ALIGNED(early_dynamic_pgts)
 	.fill	512*EARLY_DYNAMIC_PAGE_TABLES,8,0
+SYM_DATA_END(early_dynamic_pgts)
+
+SYM_DATA(early_recursion_flag, .long 0)
 
 	.data
 
 #if defined(CONFIG_XEN_PV) || defined(CONFIG_PVH)
-NEXT_PGD_PAGE(init_top_pgt)
+SYM_DATA_START_PTI_ALIGNED(init_top_pgt)
 	.quad   level3_ident_pgt - __START_KERNEL_map + _KERNPG_TABLE_NOENC
 	.org    init_top_pgt + L4_PAGE_OFFSET*8, 0
 	.quad   level3_ident_pgt - __START_KERNEL_map + _KERNPG_TABLE_NOENC
@@ -393,11 +392,13 @@ NEXT_PGD_PAGE(init_top_pgt)
 	/* (2^48-(2*1024*1024*1024))/(2^39) = 511 */
 	.quad   level3_kernel_pgt - __START_KERNEL_map + _PAGE_TABLE_NOENC
 	.fill	PTI_USER_PGD_FILL,8,0
+SYM_DATA_END(init_top_pgt)
 
-NEXT_PAGE(level3_ident_pgt)
+SYM_DATA_START_PAGE_ALIGNED(level3_ident_pgt)
 	.quad	level2_ident_pgt - __START_KERNEL_map + _KERNPG_TABLE_NOENC
 	.fill	511, 8, 0
-NEXT_PAGE(level2_ident_pgt)
+SYM_DATA_END(level3_ident_pgt)
+SYM_DATA_START_PAGE_ALIGNED(level2_ident_pgt)
 	/*
 	 * Since I easily can, map the first 1G.
 	 * Don't set NX because code runs from these pages.
@@ -407,25 +408,29 @@ NEXT_PAGE(level2_ident_pgt)
 	 * the CPU should ignore the bit.
 	 */
 	PMDS(0, __PAGE_KERNEL_IDENT_LARGE_EXEC, PTRS_PER_PMD)
+SYM_DATA_END(level2_ident_pgt)
 #else
-NEXT_PGD_PAGE(init_top_pgt)
+SYM_DATA_START_PTI_ALIGNED(init_top_pgt)
 	.fill	512,8,0
 	.fill	PTI_USER_PGD_FILL,8,0
+SYM_DATA_END(init_top_pgt)
 #endif
 
 #ifdef CONFIG_X86_5LEVEL
-NEXT_PAGE(level4_kernel_pgt)
+SYM_DATA_START_PAGE_ALIGNED(level4_kernel_pgt)
 	.fill	511,8,0
 	.quad	level3_kernel_pgt - __START_KERNEL_map + _PAGE_TABLE_NOENC
+SYM_DATA_END(level4_kernel_pgt)
 #endif
 
-NEXT_PAGE(level3_kernel_pgt)
+SYM_DATA_START_PAGE_ALIGNED(level3_kernel_pgt)
 	.fill	L3_START_KERNEL,8,0
 	/* (2^48-(2*1024*1024*1024)-((2^39)*511))/(2^30) = 510 */
 	.quad	level2_kernel_pgt - __START_KERNEL_map + _KERNPG_TABLE_NOENC
 	.quad	level2_fixmap_pgt - __START_KERNEL_map + _PAGE_TABLE_NOENC
+SYM_DATA_END(level3_kernel_pgt)
 
-NEXT_PAGE(level2_kernel_pgt)
+SYM_DATA_START_PAGE_ALIGNED(level2_kernel_pgt)
 	/*
 	 * 512 MB kernel mapping. We spend a full page on this pagetable
 	 * anyway.
@@ -442,8 +447,9 @@ NEXT_PAGE(level2_kernel_pgt)
 	 */
 	PMDS(0, __PAGE_KERNEL_LARGE_EXEC,
 		KERNEL_IMAGE_SIZE/PMD_SIZE)
+SYM_DATA_END(level2_kernel_pgt)
 
-NEXT_PAGE(level2_fixmap_pgt)
+SYM_DATA_START_PAGE_ALIGNED(level2_fixmap_pgt)
 	.fill	(512 - 4 - FIXMAP_PMD_NUM),8,0
 	pgtno = 0
 	.rept (FIXMAP_PMD_NUM)
@@ -453,31 +459,32 @@ NEXT_PAGE(level2_fixmap_pgt)
 	.endr
 	/* 6 MB reserved space + a 2MB hole */
 	.fill	4,8,0
+SYM_DATA_END(level2_fixmap_pgt)
 
-NEXT_PAGE(level1_fixmap_pgt)
+SYM_DATA_START_PAGE_ALIGNED(level1_fixmap_pgt)
 	.rept (FIXMAP_PMD_NUM)
 	.fill	512,8,0
 	.endr
+SYM_DATA_END(level1_fixmap_pgt)
 
 #undef PMDS
 
 	.data
 	.align 16
-	.globl early_gdt_descr
-early_gdt_descr:
-	.word	GDT_ENTRIES*8-1
-early_gdt_descr_base:
-	.quad	INIT_PER_CPU_VAR(gdt_page)
-
-ENTRY(phys_base)
-	/* This must match the first entry in level2_kernel_pgt */
-	.quad   0x0000000000000000
+
+SYM_DATA(early_gdt_descr,		.word GDT_ENTRIES*8-1)
+SYM_DATA_LOCAL(early_gdt_descr_base,	.quad INIT_PER_CPU_VAR(gdt_page))
+
+	.align 16
+/* This must match the first entry in level2_kernel_pgt */
+SYM_DATA(phys_base, .quad 0x0)
 EXPORT_SYMBOL(phys_base)
 
 #include "../../x86/xen/xen-head.S"
 
 	__PAGE_ALIGNED_BSS
-NEXT_PAGE(empty_zero_page)
+SYM_DATA_START_PAGE_ALIGNED(empty_zero_page)
 	.skip PAGE_SIZE
+SYM_DATA_END(empty_zero_page)
 EXPORT_SYMBOL(empty_zero_page)
 
diff --git a/arch/x86/kernel/ioport.c b/arch/x86/kernel/ioport.c
index 61a89d3c0382..8abeee0dd7bf 100644
--- a/arch/x86/kernel/ioport.c
+++ b/arch/x86/kernel/ioport.c
@@ -3,32 +3,69 @@
  * This contains the io-permission bitmap code - written by obz, with changes
  * by Linus. 32/64 bits code unification by Miguel Botón.
  */
-
-#include <linux/sched.h>
-#include <linux/sched/task_stack.h>
-#include <linux/kernel.h>
 #include <linux/capability.h>
-#include <linux/errno.h>
-#include <linux/types.h>
-#include <linux/ioport.h>
 #include <linux/security.h>
-#include <linux/smp.h>
-#include <linux/stddef.h>
-#include <linux/slab.h>
-#include <linux/thread_info.h>
 #include <linux/syscalls.h>
 #include <linux/bitmap.h>
-#include <asm/syscalls.h>
+#include <linux/ioport.h>
+#include <linux/sched.h>
+#include <linux/slab.h>
+
+#include <asm/io_bitmap.h>
 #include <asm/desc.h>
 
+#ifdef CONFIG_X86_IOPL_IOPERM
+
+static atomic64_t io_bitmap_sequence;
+
+void io_bitmap_share(struct task_struct *tsk)
+{
+	/* Can be NULL when current->thread.iopl_emul == 3 */
+	if (current->thread.io_bitmap) {
+		/*
+		 * Take a refcount on current's bitmap. It can be used by
+		 * both tasks as long as none of them changes the bitmap.
+		 */
+		refcount_inc(&current->thread.io_bitmap->refcnt);
+		tsk->thread.io_bitmap = current->thread.io_bitmap;
+	}
+	set_tsk_thread_flag(tsk, TIF_IO_BITMAP);
+}
+
+static void task_update_io_bitmap(void)
+{
+	struct thread_struct *t = &current->thread;
+
+	if (t->iopl_emul == 3 || t->io_bitmap) {
+		/* TSS update is handled on exit to user space */
+		set_thread_flag(TIF_IO_BITMAP);
+	} else {
+		clear_thread_flag(TIF_IO_BITMAP);
+		/* Invalidate TSS */
+		preempt_disable();
+		tss_update_io_bitmap();
+		preempt_enable();
+	}
+}
+
+void io_bitmap_exit(void)
+{
+	struct io_bitmap *iobm = current->thread.io_bitmap;
+
+	current->thread.io_bitmap = NULL;
+	task_update_io_bitmap();
+	if (iobm && refcount_dec_and_test(&iobm->refcnt))
+		kfree(iobm);
+}
+
 /*
- * this changes the io permissions bitmap in the current task.
+ * This changes the io permissions bitmap in the current task.
  */
 long ksys_ioperm(unsigned long from, unsigned long num, int turn_on)
 {
 	struct thread_struct *t = &current->thread;
-	struct tss_struct *tss;
-	unsigned int i, max_long, bytes, bytes_updated;
+	unsigned int i, max_long;
+	struct io_bitmap *iobm;
 
 	if ((from + num <= from) || (from + num > IO_BITMAP_BITS))
 		return -EINVAL;
@@ -41,59 +78,72 @@ long ksys_ioperm(unsigned long from, unsigned long num, int turn_on)
 	 * IO bitmap up. ioperm() is much less timing critical than clone(),
 	 * this is why we delay this operation until now:
 	 */
-	if (!t->io_bitmap_ptr) {
-		unsigned long *bitmap = kmalloc(IO_BITMAP_BYTES, GFP_KERNEL);
-
-		if (!bitmap)
+	iobm = t->io_bitmap;
+	if (!iobm) {
+		/* No point to allocate a bitmap just to clear permissions */
+		if (!turn_on)
+			return 0;
+		iobm = kmalloc(sizeof(*iobm), GFP_KERNEL);
+		if (!iobm)
 			return -ENOMEM;
 
-		memset(bitmap, 0xff, IO_BITMAP_BYTES);
-		t->io_bitmap_ptr = bitmap;
-		set_thread_flag(TIF_IO_BITMAP);
+		memset(iobm->bitmap, 0xff, sizeof(iobm->bitmap));
+		refcount_set(&iobm->refcnt, 1);
+	}
 
-		/*
-		 * Now that we have an IO bitmap, we need our TSS limit to be
-		 * correct.  It's fine if we are preempted after doing this:
-		 * with TIF_IO_BITMAP set, context switches will keep our TSS
-		 * limit correct.
-		 */
-		preempt_disable();
-		refresh_tss_limit();
-		preempt_enable();
+	/*
+	 * If the bitmap is not shared, then nothing can take a refcount as
+	 * current can obviously not fork at the same time. If it's shared
+	 * duplicate it and drop the refcount on the original one.
+	 */
+	if (refcount_read(&iobm->refcnt) > 1) {
+		iobm = kmemdup(iobm, sizeof(*iobm), GFP_KERNEL);
+		if (!iobm)
+			return -ENOMEM;
+		refcount_set(&iobm->refcnt, 1);
+		io_bitmap_exit();
 	}
 
 	/*
-	 * do it in the per-thread copy and in the TSS ...
-	 *
-	 * Disable preemption via get_cpu() - we must not switch away
-	 * because the ->io_bitmap_max value must match the bitmap
-	 * contents:
+	 * Store the bitmap pointer (might be the same if the task already
+	 * head one). Must be done here so freeing the bitmap when all
+	 * permissions are dropped has the pointer set up.
 	 */
-	tss = &per_cpu(cpu_tss_rw, get_cpu());
+	t->io_bitmap = iobm;
+	/* Mark it active for context switching and exit to user mode */
+	set_thread_flag(TIF_IO_BITMAP);
 
+	/*
+	 * Update the tasks bitmap. The update of the TSS bitmap happens on
+	 * exit to user mode. So this needs no protection.
+	 */
 	if (turn_on)
-		bitmap_clear(t->io_bitmap_ptr, from, num);
+		bitmap_clear(iobm->bitmap, from, num);
 	else
-		bitmap_set(t->io_bitmap_ptr, from, num);
+		bitmap_set(iobm->bitmap, from, num);
 
 	/*
 	 * Search for a (possibly new) maximum. This is simple and stupid,
 	 * to keep it obviously correct:
 	 */
-	max_long = 0;
-	for (i = 0; i < IO_BITMAP_LONGS; i++)
-		if (t->io_bitmap_ptr[i] != ~0UL)
+	max_long = UINT_MAX;
+	for (i = 0; i < IO_BITMAP_LONGS; i++) {
+		if (iobm->bitmap[i] != ~0UL)
 			max_long = i;
+	}
+	/* All permissions dropped? */
+	if (max_long == UINT_MAX) {
+		io_bitmap_exit();
+		return 0;
+	}
 
-	bytes = (max_long + 1) * sizeof(unsigned long);
-	bytes_updated = max(bytes, t->io_bitmap_max);
-
-	t->io_bitmap_max = bytes;
-
-	/* Update the TSS: */
-	memcpy(tss->io_bitmap, t->io_bitmap_ptr, bytes_updated);
+	iobm->max = (max_long + 1) * sizeof(unsigned long);
 
-	put_cpu();
+	/*
+	 * Update the sequence number to force a TSS update on return to
+	 * user mode.
+	 */
+	iobm->sequence = atomic64_add_return(1, &io_bitmap_sequence);
 
 	return 0;
 }
@@ -104,38 +154,61 @@ SYSCALL_DEFINE3(ioperm, unsigned long, from, unsigned long, num, int, turn_on)
 }
 
 /*
- * sys_iopl has to be used when you want to access the IO ports
- * beyond the 0x3ff range: to get the full 65536 ports bitmapped
- * you'd need 8kB of bitmaps/process, which is a bit excessive.
+ * The sys_iopl functionality depends on the level argument, which if
+ * granted for the task is used to enable access to all 65536 I/O ports.
+ *
+ * This does not use the IOPL mechanism provided by the CPU as that would
+ * also allow the user space task to use the CLI/STI instructions.
  *
- * Here we just change the flags value on the stack: we allow
- * only the super-user to do it. This depends on the stack-layout
- * on system-call entry - see also fork() and the signal handling
- * code.
+ * Disabling interrupts in a user space task is dangerous as it might lock
+ * up the machine and the semantics vs. syscalls and exceptions is
+ * undefined.
+ *
+ * Setting IOPL to level 0-2 is disabling I/O permissions. Level 3
+ * 3 enables them.
+ *
+ * IOPL is strictly per thread and inherited on fork.
  */
 SYSCALL_DEFINE1(iopl, unsigned int, level)
 {
-	struct pt_regs *regs = current_pt_regs();
 	struct thread_struct *t = &current->thread;
-
-	/*
-	 * Careful: the IOPL bits in regs->flags are undefined under Xen PV
-	 * and changing them has no effect.
-	 */
-	unsigned int old = t->iopl >> X86_EFLAGS_IOPL_BIT;
+	unsigned int old;
 
 	if (level > 3)
 		return -EINVAL;
+
+	old = t->iopl_emul;
+
+	/* No point in going further if nothing changes */
+	if (level == old)
+		return 0;
+
 	/* Trying to gain more privileges? */
 	if (level > old) {
 		if (!capable(CAP_SYS_RAWIO) ||
 		    security_locked_down(LOCKDOWN_IOPORT))
 			return -EPERM;
 	}
-	regs->flags = (regs->flags & ~X86_EFLAGS_IOPL) |
-		(level << X86_EFLAGS_IOPL_BIT);
-	t->iopl = level << X86_EFLAGS_IOPL_BIT;
-	set_iopl_mask(t->iopl);
+
+	t->iopl_emul = level;
+	task_update_io_bitmap();
 
 	return 0;
 }
+
+#else /* CONFIG_X86_IOPL_IOPERM */
+
+long ksys_ioperm(unsigned long from, unsigned long num, int turn_on)
+{
+	return -ENOSYS;
+}
+SYSCALL_DEFINE3(ioperm, unsigned long, from, unsigned long, num, int, turn_on)
+{
+	return -ENOSYS;
+}
+
+SYSCALL_DEFINE1(iopl, unsigned int, level)
+{
+	return -ENOSYS;
+}
+#endif
diff --git a/arch/x86/kernel/irqflags.S b/arch/x86/kernel/irqflags.S
index ddeeaac8adda..0db0375235b4 100644
--- a/arch/x86/kernel/irqflags.S
+++ b/arch/x86/kernel/irqflags.S
@@ -7,20 +7,20 @@
 /*
  * unsigned long native_save_fl(void)
  */
-ENTRY(native_save_fl)
+SYM_FUNC_START(native_save_fl)
 	pushf
 	pop %_ASM_AX
 	ret
-ENDPROC(native_save_fl)
+SYM_FUNC_END(native_save_fl)
 EXPORT_SYMBOL(native_save_fl)
 
 /*
  * void native_restore_fl(unsigned long flags)
  * %eax/%rdi: flags
  */
-ENTRY(native_restore_fl)
+SYM_FUNC_START(native_restore_fl)
 	push %_ASM_ARG1
 	popf
 	ret
-ENDPROC(native_restore_fl)
+SYM_FUNC_END(native_restore_fl)
 EXPORT_SYMBOL(native_restore_fl)
diff --git a/arch/x86/kernel/jailhouse.c b/arch/x86/kernel/jailhouse.c
index 3ad34f01de2a..6eb8b50ea07e 100644
--- a/arch/x86/kernel/jailhouse.c
+++ b/arch/x86/kernel/jailhouse.c
@@ -11,6 +11,7 @@
 #include <linux/acpi_pmtmr.h>
 #include <linux/kernel.h>
 #include <linux/reboot.h>
+#include <linux/serial_8250.h>
 #include <asm/apic.h>
 #include <asm/cpu.h>
 #include <asm/hypervisor.h>
@@ -21,9 +22,24 @@
 #include <asm/setup.h>
 #include <asm/jailhouse_para.h>
 
-static __initdata struct jailhouse_setup_data setup_data;
+static struct jailhouse_setup_data setup_data;
+#define SETUP_DATA_V1_LEN	(sizeof(setup_data.hdr) + sizeof(setup_data.v1))
+#define SETUP_DATA_V2_LEN	(SETUP_DATA_V1_LEN + sizeof(setup_data.v2))
+
 static unsigned int precalibrated_tsc_khz;
 
+static void jailhouse_setup_irq(unsigned int irq)
+{
+	struct mpc_intsrc mp_irq = {
+		.type		= MP_INTSRC,
+		.irqtype	= mp_INT,
+		.irqflag	= MP_IRQPOL_ACTIVE_HIGH | MP_IRQTRIG_EDGE,
+		.srcbusirq	= irq,
+		.dstirq		= irq,
+	};
+	mp_save_irq(&mp_irq);
+}
+
 static uint32_t jailhouse_cpuid_base(void)
 {
 	if (boot_cpu_data.cpuid_level < 0 ||
@@ -45,7 +61,7 @@ static void jailhouse_get_wallclock(struct timespec64 *now)
 
 static void __init jailhouse_timer_init(void)
 {
-	lapic_timer_period = setup_data.apic_khz * (1000 / HZ);
+	lapic_timer_period = setup_data.v1.apic_khz * (1000 / HZ);
 }
 
 static unsigned long jailhouse_get_tsc(void)
@@ -77,33 +93,28 @@ static void __init jailhouse_get_smp_config(unsigned int early)
 		.type = IOAPIC_DOMAIN_STRICT,
 		.ops = &mp_ioapic_irqdomain_ops,
 	};
-	struct mpc_intsrc mp_irq = {
-		.type = MP_INTSRC,
-		.irqtype = mp_INT,
-		.irqflag = MP_IRQPOL_ACTIVE_HIGH | MP_IRQTRIG_EDGE,
-	};
 	unsigned int cpu;
 
 	jailhouse_x2apic_init();
 
 	register_lapic_address(0xfee00000);
 
-	for (cpu = 0; cpu < setup_data.num_cpus; cpu++) {
-		generic_processor_info(setup_data.cpu_ids[cpu],
+	for (cpu = 0; cpu < setup_data.v1.num_cpus; cpu++) {
+		generic_processor_info(setup_data.v1.cpu_ids[cpu],
 				       boot_cpu_apic_version);
 	}
 
 	smp_found_config = 1;
 
-	if (setup_data.standard_ioapic) {
+	if (setup_data.v1.standard_ioapic) {
 		mp_register_ioapic(0, 0xfec00000, gsi_top, &ioapic_cfg);
 
-		/* Register 1:1 mapping for legacy UART IRQs 3 and 4 */
-		mp_irq.srcbusirq = mp_irq.dstirq = 3;
-		mp_save_irq(&mp_irq);
-
-		mp_irq.srcbusirq = mp_irq.dstirq = 4;
-		mp_save_irq(&mp_irq);
+		if (IS_ENABLED(CONFIG_SERIAL_8250) &&
+		    setup_data.hdr.version < 2) {
+			/* Register 1:1 mapping for legacy UART IRQs 3 and 4 */
+			jailhouse_setup_irq(3);
+			jailhouse_setup_irq(4);
+		}
 	}
 }
 
@@ -126,9 +137,9 @@ static int __init jailhouse_pci_arch_init(void)
 		pcibios_last_bus = 0xff;
 
 #ifdef CONFIG_PCI_MMCONFIG
-	if (setup_data.pci_mmconfig_base) {
+	if (setup_data.v1.pci_mmconfig_base) {
 		pci_mmconfig_add(0, 0, pcibios_last_bus,
-				 setup_data.pci_mmconfig_base);
+				 setup_data.v1.pci_mmconfig_base);
 		pci_mmcfg_arch_init();
 	}
 #endif
@@ -136,9 +147,57 @@ static int __init jailhouse_pci_arch_init(void)
 	return 0;
 }
 
+#ifdef CONFIG_SERIAL_8250
+static inline bool jailhouse_uart_enabled(unsigned int uart_nr)
+{
+	return setup_data.v2.flags & BIT(uart_nr);
+}
+
+static void jailhouse_serial_fixup(int port, struct uart_port *up,
+				   u32 *capabilities)
+{
+	static const u16 pcuart_base[] = {0x3f8, 0x2f8, 0x3e8, 0x2e8};
+	unsigned int n;
+
+	for (n = 0; n < ARRAY_SIZE(pcuart_base); n++) {
+		if (pcuart_base[n] != up->iobase)
+			continue;
+
+		if (jailhouse_uart_enabled(n)) {
+			pr_info("Enabling UART%u (port 0x%lx)\n", n,
+				up->iobase);
+			jailhouse_setup_irq(up->irq);
+		} else {
+			/* Deactivate UART if access isn't allowed */
+			up->iobase = 0;
+		}
+		break;
+	}
+}
+
+static void __init jailhouse_serial_workaround(void)
+{
+	/*
+	 * There are flags inside setup_data that indicate availability of
+	 * platform UARTs since setup data version 2.
+	 *
+	 * In case of version 1, we don't know which UARTs belong Linux. In
+	 * this case, unconditionally register 1:1 mapping for legacy UART IRQs
+	 * 3 and 4.
+	 */
+	if (setup_data.hdr.version > 1)
+		serial8250_set_isa_configurator(jailhouse_serial_fixup);
+}
+#else /* !CONFIG_SERIAL_8250 */
+static inline void jailhouse_serial_workaround(void)
+{
+}
+#endif /* CONFIG_SERIAL_8250 */
+
 static void __init jailhouse_init_platform(void)
 {
 	u64 pa_data = boot_params.hdr.setup_data;
+	unsigned long setup_data_len;
 	struct setup_data header;
 	void *mapping;
 
@@ -163,16 +222,8 @@ static void __init jailhouse_init_platform(void)
 		memcpy(&header, mapping, sizeof(header));
 		early_memunmap(mapping, sizeof(header));
 
-		if (header.type == SETUP_JAILHOUSE &&
-		    header.len >= sizeof(setup_data)) {
-			pa_data += offsetof(struct setup_data, data);
-
-			mapping = early_memremap(pa_data, sizeof(setup_data));
-			memcpy(&setup_data, mapping, sizeof(setup_data));
-			early_memunmap(mapping, sizeof(setup_data));
-
+		if (header.type == SETUP_JAILHOUSE)
 			break;
-		}
 
 		pa_data = header.next;
 	}
@@ -180,13 +231,28 @@ static void __init jailhouse_init_platform(void)
 	if (!pa_data)
 		panic("Jailhouse: No valid setup data found");
 
-	if (setup_data.compatible_version > JAILHOUSE_SETUP_REQUIRED_VERSION)
-		panic("Jailhouse: Unsupported setup data structure");
-
-	pmtmr_ioport = setup_data.pm_timer_address;
+	/* setup data must at least contain the header */
+	if (header.len < sizeof(setup_data.hdr))
+		goto unsupported;
+
+	pa_data += offsetof(struct setup_data, data);
+	setup_data_len = min_t(unsigned long, sizeof(setup_data),
+			       (unsigned long)header.len);
+	mapping = early_memremap(pa_data, setup_data_len);
+	memcpy(&setup_data, mapping, setup_data_len);
+	early_memunmap(mapping, setup_data_len);
+
+	if (setup_data.hdr.version == 0 ||
+	    setup_data.hdr.compatible_version !=
+		JAILHOUSE_SETUP_REQUIRED_VERSION ||
+	    (setup_data.hdr.version == 1 && header.len < SETUP_DATA_V1_LEN) ||
+	    (setup_data.hdr.version >= 2 && header.len < SETUP_DATA_V2_LEN))
+		goto unsupported;
+
+	pmtmr_ioport = setup_data.v1.pm_timer_address;
 	pr_debug("Jailhouse: PM-Timer IO Port: %#x\n", pmtmr_ioport);
 
-	precalibrated_tsc_khz = setup_data.tsc_khz;
+	precalibrated_tsc_khz = setup_data.v1.tsc_khz;
 	setup_force_cpu_cap(X86_FEATURE_TSC_KNOWN_FREQ);
 
 	pci_probe = 0;
@@ -196,6 +262,12 @@ static void __init jailhouse_init_platform(void)
 	 * are none in a non-root cell.
 	 */
 	disable_acpi();
+
+	jailhouse_serial_workaround();
+	return;
+
+unsupported:
+	panic("Jailhouse: Unsupported setup data structure");
 }
 
 bool jailhouse_paravirt(void)
diff --git a/arch/x86/kernel/kdebugfs.c b/arch/x86/kernel/kdebugfs.c
index edaa30b20841..64b6da95af98 100644
--- a/arch/x86/kernel/kdebugfs.c
+++ b/arch/x86/kernel/kdebugfs.c
@@ -44,7 +44,12 @@ static ssize_t setup_data_read(struct file *file, char __user *user_buf,
 	if (count > node->len - pos)
 		count = node->len - pos;
 
-	pa = node->paddr + sizeof(struct setup_data) + pos;
+	pa = node->paddr + pos;
+
+	/* Is it direct data or invalid indirect one? */
+	if (!(node->type & SETUP_INDIRECT) || node->type == SETUP_INDIRECT)
+		pa += sizeof(struct setup_data);
+
 	p = memremap(pa, count, MEMREMAP_WB);
 	if (!p)
 		return -ENOMEM;
@@ -108,9 +113,17 @@ static int __init create_setup_data_nodes(struct dentry *parent)
 			goto err_dir;
 		}
 
-		node->paddr = pa_data;
-		node->type = data->type;
-		node->len = data->len;
+		if (data->type == SETUP_INDIRECT &&
+		    ((struct setup_indirect *)data->data)->type != SETUP_INDIRECT) {
+			node->paddr = ((struct setup_indirect *)data->data)->addr;
+			node->type  = ((struct setup_indirect *)data->data)->type;
+			node->len   = ((struct setup_indirect *)data->data)->len;
+		} else {
+			node->paddr = pa_data;
+			node->type  = data->type;
+			node->len   = data->len;
+		}
+
 		create_setup_data_node(d, no, node);
 		pa_data = data->next;
 
diff --git a/arch/x86/kernel/ksysfs.c b/arch/x86/kernel/ksysfs.c
index 7969da939213..d0a19121c6a4 100644
--- a/arch/x86/kernel/ksysfs.c
+++ b/arch/x86/kernel/ksysfs.c
@@ -100,7 +100,12 @@ static int __init get_setup_data_size(int nr, size_t *size)
 		if (!data)
 			return -ENOMEM;
 		if (nr == i) {
-			*size = data->len;
+			if (data->type == SETUP_INDIRECT &&
+			    ((struct setup_indirect *)data->data)->type != SETUP_INDIRECT)
+				*size = ((struct setup_indirect *)data->data)->len;
+			else
+				*size = data->len;
+
 			memunmap(data);
 			return 0;
 		}
@@ -130,7 +135,10 @@ static ssize_t type_show(struct kobject *kobj,
 	if (!data)
 		return -ENOMEM;
 
-	ret = sprintf(buf, "0x%x\n", data->type);
+	if (data->type == SETUP_INDIRECT)
+		ret = sprintf(buf, "0x%x\n", ((struct setup_indirect *)data->data)->type);
+	else
+		ret = sprintf(buf, "0x%x\n", data->type);
 	memunmap(data);
 	return ret;
 }
@@ -142,7 +150,7 @@ static ssize_t setup_data_data_read(struct file *fp,
 				    loff_t off, size_t count)
 {
 	int nr, ret = 0;
-	u64 paddr;
+	u64 paddr, len;
 	struct setup_data *data;
 	void *p;
 
@@ -157,19 +165,28 @@ static ssize_t setup_data_data_read(struct file *fp,
 	if (!data)
 		return -ENOMEM;
 
-	if (off > data->len) {
+	if (data->type == SETUP_INDIRECT &&
+	    ((struct setup_indirect *)data->data)->type != SETUP_INDIRECT) {
+		paddr = ((struct setup_indirect *)data->data)->addr;
+		len = ((struct setup_indirect *)data->data)->len;
+	} else {
+		paddr += sizeof(*data);
+		len = data->len;
+	}
+
+	if (off > len) {
 		ret = -EINVAL;
 		goto out;
 	}
 
-	if (count > data->len - off)
-		count = data->len - off;
+	if (count > len - off)
+		count = len - off;
 
 	if (!count)
 		goto out;
 
 	ret = count;
-	p = memremap(paddr + sizeof(*data), data->len, MEMREMAP_WB);
+	p = memremap(paddr, len, MEMREMAP_WB);
 	if (!p) {
 		ret = -ENOMEM;
 		goto out;
diff --git a/arch/x86/kernel/machine_kexec_64.c b/arch/x86/kernel/machine_kexec_64.c
index 5dcd438ad8f2..16e125a50b33 100644
--- a/arch/x86/kernel/machine_kexec_64.c
+++ b/arch/x86/kernel/machine_kexec_64.c
@@ -298,48 +298,6 @@ static void load_segments(void)
 		);
 }
 
-#ifdef CONFIG_KEXEC_FILE
-/* Update purgatory as needed after various image segments have been prepared */
-static int arch_update_purgatory(struct kimage *image)
-{
-	int ret = 0;
-
-	if (!image->file_mode)
-		return 0;
-
-	/* Setup copying of backup region */
-	if (image->type == KEXEC_TYPE_CRASH) {
-		ret = kexec_purgatory_get_set_symbol(image,
-				"purgatory_backup_dest",
-				&image->arch.backup_load_addr,
-				sizeof(image->arch.backup_load_addr), 0);
-		if (ret)
-			return ret;
-
-		ret = kexec_purgatory_get_set_symbol(image,
-				"purgatory_backup_src",
-				&image->arch.backup_src_start,
-				sizeof(image->arch.backup_src_start), 0);
-		if (ret)
-			return ret;
-
-		ret = kexec_purgatory_get_set_symbol(image,
-				"purgatory_backup_sz",
-				&image->arch.backup_src_sz,
-				sizeof(image->arch.backup_src_sz), 0);
-		if (ret)
-			return ret;
-	}
-
-	return ret;
-}
-#else /* !CONFIG_KEXEC_FILE */
-static inline int arch_update_purgatory(struct kimage *image)
-{
-	return 0;
-}
-#endif /* CONFIG_KEXEC_FILE */
-
 int machine_kexec_prepare(struct kimage *image)
 {
 	unsigned long start_pgtable;
@@ -353,11 +311,6 @@ int machine_kexec_prepare(struct kimage *image)
 	if (result)
 		return result;
 
-	/* update purgatory as needed */
-	result = arch_update_purgatory(image);
-	if (result)
-		return result;
-
 	return 0;
 }
 
diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c
index 59d3d2763a9e..789f5e4f89de 100644
--- a/arch/x86/kernel/paravirt.c
+++ b/arch/x86/kernel/paravirt.c
@@ -341,8 +341,6 @@ struct paravirt_patch_template pv_ops = {
 	.cpu.iret		= native_iret,
 	.cpu.swapgs		= native_swapgs,
 
-	.cpu.set_iopl_mask	= native_set_iopl_mask,
-
 	.cpu.start_context_switch	= paravirt_nop,
 	.cpu.end_context_switch		= paravirt_nop,
 
diff --git a/arch/x86/kernel/pci-calgary_64.c b/arch/x86/kernel/pci-calgary_64.c
deleted file mode 100644
index 23fdec030c37..000000000000
--- a/arch/x86/kernel/pci-calgary_64.c
+++ /dev/null
@@ -1,1586 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-or-later
-/*
- * Derived from arch/powerpc/kernel/iommu.c
- *
- * Copyright IBM Corporation, 2006-2007
- * Copyright (C) 2006  Jon Mason <jdmason@kudzu.us>
- *
- * Author: Jon Mason <jdmason@kudzu.us>
- * Author: Muli Ben-Yehuda <muli@il.ibm.com>
-
- */
-
-#define pr_fmt(fmt) "Calgary: " fmt
-
-#include <linux/kernel.h>
-#include <linux/init.h>
-#include <linux/types.h>
-#include <linux/slab.h>
-#include <linux/mm.h>
-#include <linux/spinlock.h>
-#include <linux/string.h>
-#include <linux/crash_dump.h>
-#include <linux/dma-mapping.h>
-#include <linux/dma-direct.h>
-#include <linux/bitmap.h>
-#include <linux/pci_ids.h>
-#include <linux/pci.h>
-#include <linux/delay.h>
-#include <linux/scatterlist.h>
-#include <linux/iommu-helper.h>
-
-#include <asm/iommu.h>
-#include <asm/calgary.h>
-#include <asm/tce.h>
-#include <asm/pci-direct.h>
-#include <asm/dma.h>
-#include <asm/rio.h>
-#include <asm/bios_ebda.h>
-#include <asm/x86_init.h>
-#include <asm/iommu_table.h>
-
-#ifdef CONFIG_CALGARY_IOMMU_ENABLED_BY_DEFAULT
-int use_calgary __read_mostly = 1;
-#else
-int use_calgary __read_mostly = 0;
-#endif /* CONFIG_CALGARY_DEFAULT_ENABLED */
-
-#define PCI_DEVICE_ID_IBM_CALGARY 0x02a1
-#define PCI_DEVICE_ID_IBM_CALIOC2 0x0308
-
-/* register offsets inside the host bridge space */
-#define CALGARY_CONFIG_REG	0x0108
-#define PHB_CSR_OFFSET		0x0110 /* Channel Status */
-#define PHB_PLSSR_OFFSET	0x0120
-#define PHB_CONFIG_RW_OFFSET	0x0160
-#define PHB_IOBASE_BAR_LOW	0x0170
-#define PHB_IOBASE_BAR_HIGH	0x0180
-#define PHB_MEM_1_LOW		0x0190
-#define PHB_MEM_1_HIGH		0x01A0
-#define PHB_IO_ADDR_SIZE	0x01B0
-#define PHB_MEM_1_SIZE		0x01C0
-#define PHB_MEM_ST_OFFSET	0x01D0
-#define PHB_AER_OFFSET		0x0200
-#define PHB_CONFIG_0_HIGH	0x0220
-#define PHB_CONFIG_0_LOW	0x0230
-#define PHB_CONFIG_0_END	0x0240
-#define PHB_MEM_2_LOW		0x02B0
-#define PHB_MEM_2_HIGH		0x02C0
-#define PHB_MEM_2_SIZE_HIGH	0x02D0
-#define PHB_MEM_2_SIZE_LOW	0x02E0
-#define PHB_DOSHOLE_OFFSET	0x08E0
-
-/* CalIOC2 specific */
-#define PHB_SAVIOR_L2		0x0DB0
-#define PHB_PAGE_MIG_CTRL	0x0DA8
-#define PHB_PAGE_MIG_DEBUG	0x0DA0
-#define PHB_ROOT_COMPLEX_STATUS 0x0CB0
-
-/* PHB_CONFIG_RW */
-#define PHB_TCE_ENABLE		0x20000000
-#define PHB_SLOT_DISABLE	0x1C000000
-#define PHB_DAC_DISABLE		0x01000000
-#define PHB_MEM2_ENABLE		0x00400000
-#define PHB_MCSR_ENABLE		0x00100000
-/* TAR (Table Address Register) */
-#define TAR_SW_BITS		0x0000ffffffff800fUL
-#define TAR_VALID		0x0000000000000008UL
-/* CSR (Channel/DMA Status Register) */
-#define CSR_AGENT_MASK		0xffe0ffff
-/* CCR (Calgary Configuration Register) */
-#define CCR_2SEC_TIMEOUT	0x000000000000000EUL
-/* PMCR/PMDR (Page Migration Control/Debug Registers */
-#define PMR_SOFTSTOP		0x80000000
-#define PMR_SOFTSTOPFAULT	0x40000000
-#define PMR_HARDSTOP		0x20000000
-
-/*
- * The maximum PHB bus number.
- * x3950M2 (rare): 8 chassis, 48 PHBs per chassis = 384
- * x3950M2: 4 chassis, 48 PHBs per chassis        = 192
- * x3950 (PCIE): 8 chassis, 32 PHBs per chassis   = 256
- * x3950 (PCIX): 8 chassis, 16 PHBs per chassis   = 128
- */
-#define MAX_PHB_BUS_NUM		256
-
-#define PHBS_PER_CALGARY	  4
-
-/* register offsets in Calgary's internal register space */
-static const unsigned long tar_offsets[] = {
-	0x0580 /* TAR0 */,
-	0x0588 /* TAR1 */,
-	0x0590 /* TAR2 */,
-	0x0598 /* TAR3 */
-};
-
-static const unsigned long split_queue_offsets[] = {
-	0x4870 /* SPLIT QUEUE 0 */,
-	0x5870 /* SPLIT QUEUE 1 */,
-	0x6870 /* SPLIT QUEUE 2 */,
-	0x7870 /* SPLIT QUEUE 3 */
-};
-
-static const unsigned long phb_offsets[] = {
-	0x8000 /* PHB0 */,
-	0x9000 /* PHB1 */,
-	0xA000 /* PHB2 */,
-	0xB000 /* PHB3 */
-};
-
-/* PHB debug registers */
-
-static const unsigned long phb_debug_offsets[] = {
-	0x4000	/* PHB 0 DEBUG */,
-	0x5000	/* PHB 1 DEBUG */,
-	0x6000	/* PHB 2 DEBUG */,
-	0x7000	/* PHB 3 DEBUG */
-};
-
-/*
- * STUFF register for each debug PHB,
- * byte 1 = start bus number, byte 2 = end bus number
- */
-
-#define PHB_DEBUG_STUFF_OFFSET	0x0020
-
-unsigned int specified_table_size = TCE_TABLE_SIZE_UNSPECIFIED;
-static int translate_empty_slots __read_mostly = 0;
-static int calgary_detected __read_mostly = 0;
-
-static struct rio_table_hdr	*rio_table_hdr __initdata;
-static struct scal_detail	*scal_devs[MAX_NUMNODES] __initdata;
-static struct rio_detail	*rio_devs[MAX_NUMNODES * 4] __initdata;
-
-struct calgary_bus_info {
-	void *tce_space;
-	unsigned char translation_disabled;
-	signed char phbid;
-	void __iomem *bbar;
-};
-
-static void calgary_handle_quirks(struct iommu_table *tbl, struct pci_dev *dev);
-static void calgary_tce_cache_blast(struct iommu_table *tbl);
-static void calgary_dump_error_regs(struct iommu_table *tbl);
-static void calioc2_handle_quirks(struct iommu_table *tbl, struct pci_dev *dev);
-static void calioc2_tce_cache_blast(struct iommu_table *tbl);
-static void calioc2_dump_error_regs(struct iommu_table *tbl);
-static void calgary_init_bitmap_from_tce_table(struct iommu_table *tbl);
-static void get_tce_space_from_tar(void);
-
-static const struct cal_chipset_ops calgary_chip_ops = {
-	.handle_quirks = calgary_handle_quirks,
-	.tce_cache_blast = calgary_tce_cache_blast,
-	.dump_error_regs = calgary_dump_error_regs
-};
-
-static const struct cal_chipset_ops calioc2_chip_ops = {
-	.handle_quirks = calioc2_handle_quirks,
-	.tce_cache_blast = calioc2_tce_cache_blast,
-	.dump_error_regs = calioc2_dump_error_regs
-};
-
-static struct calgary_bus_info bus_info[MAX_PHB_BUS_NUM] = { { NULL, 0, 0 }, };
-
-static inline int translation_enabled(struct iommu_table *tbl)
-{
-	/* only PHBs with translation enabled have an IOMMU table */
-	return (tbl != NULL);
-}
-
-static void iommu_range_reserve(struct iommu_table *tbl,
-	unsigned long start_addr, unsigned int npages)
-{
-	unsigned long index;
-	unsigned long end;
-	unsigned long flags;
-
-	index = start_addr >> PAGE_SHIFT;
-
-	/* bail out if we're asked to reserve a region we don't cover */
-	if (index >= tbl->it_size)
-		return;
-
-	end = index + npages;
-	if (end > tbl->it_size) /* don't go off the table */
-		end = tbl->it_size;
-
-	spin_lock_irqsave(&tbl->it_lock, flags);
-
-	bitmap_set(tbl->it_map, index, npages);
-
-	spin_unlock_irqrestore(&tbl->it_lock, flags);
-}
-
-static unsigned long iommu_range_alloc(struct device *dev,
-				       struct iommu_table *tbl,
-				       unsigned int npages)
-{
-	unsigned long flags;
-	unsigned long offset;
-	unsigned long boundary_size;
-
-	boundary_size = ALIGN(dma_get_seg_boundary(dev) + 1,
-			      PAGE_SIZE) >> PAGE_SHIFT;
-
-	BUG_ON(npages == 0);
-
-	spin_lock_irqsave(&tbl->it_lock, flags);
-
-	offset = iommu_area_alloc(tbl->it_map, tbl->it_size, tbl->it_hint,
-				  npages, 0, boundary_size, 0);
-	if (offset == ~0UL) {
-		tbl->chip_ops->tce_cache_blast(tbl);
-
-		offset = iommu_area_alloc(tbl->it_map, tbl->it_size, 0,
-					  npages, 0, boundary_size, 0);
-		if (offset == ~0UL) {
-			pr_warn("IOMMU full\n");
-			spin_unlock_irqrestore(&tbl->it_lock, flags);
-			if (panic_on_overflow)
-				panic("Calgary: fix the allocator.\n");
-			else
-				return DMA_MAPPING_ERROR;
-		}
-	}
-
-	tbl->it_hint = offset + npages;
-	BUG_ON(tbl->it_hint > tbl->it_size);
-
-	spin_unlock_irqrestore(&tbl->it_lock, flags);
-
-	return offset;
-}
-
-static dma_addr_t iommu_alloc(struct device *dev, struct iommu_table *tbl,
-			      void *vaddr, unsigned int npages, int direction)
-{
-	unsigned long entry;
-	dma_addr_t ret;
-
-	entry = iommu_range_alloc(dev, tbl, npages);
-	if (unlikely(entry == DMA_MAPPING_ERROR)) {
-		pr_warn("failed to allocate %u pages in iommu %p\n",
-			npages, tbl);
-		return DMA_MAPPING_ERROR;
-	}
-
-	/* set the return dma address */
-	ret = (entry << PAGE_SHIFT) | ((unsigned long)vaddr & ~PAGE_MASK);
-
-	/* put the TCEs in the HW table */
-	tce_build(tbl, entry, npages, (unsigned long)vaddr & PAGE_MASK,
-		  direction);
-	return ret;
-}
-
-static void iommu_free(struct iommu_table *tbl, dma_addr_t dma_addr,
-	unsigned int npages)
-{
-	unsigned long entry;
-	unsigned long flags;
-
-	/* were we called with bad_dma_address? */
-	if (unlikely(dma_addr == DMA_MAPPING_ERROR)) {
-		WARN(1, KERN_ERR "Calgary: driver tried unmapping bad DMA "
-		       "address 0x%Lx\n", dma_addr);
-		return;
-	}
-
-	entry = dma_addr >> PAGE_SHIFT;
-
-	BUG_ON(entry + npages > tbl->it_size);
-
-	tce_free(tbl, entry, npages);
-
-	spin_lock_irqsave(&tbl->it_lock, flags);
-
-	bitmap_clear(tbl->it_map, entry, npages);
-
-	spin_unlock_irqrestore(&tbl->it_lock, flags);
-}
-
-static inline struct iommu_table *find_iommu_table(struct device *dev)
-{
-	struct pci_dev *pdev;
-	struct pci_bus *pbus;
-	struct iommu_table *tbl;
-
-	pdev = to_pci_dev(dev);
-
-	/* search up the device tree for an iommu */
-	pbus = pdev->bus;
-	do {
-		tbl = pci_iommu(pbus);
-		if (tbl && tbl->it_busno == pbus->number)
-			break;
-		tbl = NULL;
-		pbus = pbus->parent;
-	} while (pbus);
-
-	BUG_ON(tbl && (tbl->it_busno != pbus->number));
-
-	return tbl;
-}
-
-static void calgary_unmap_sg(struct device *dev, struct scatterlist *sglist,
-			     int nelems,enum dma_data_direction dir,
-			     unsigned long attrs)
-{
-	struct iommu_table *tbl = find_iommu_table(dev);
-	struct scatterlist *s;
-	int i;
-
-	if (!translation_enabled(tbl))
-		return;
-
-	for_each_sg(sglist, s, nelems, i) {
-		unsigned int npages;
-		dma_addr_t dma = s->dma_address;
-		unsigned int dmalen = s->dma_length;
-
-		if (dmalen == 0)
-			break;
-
-		npages = iommu_num_pages(dma, dmalen, PAGE_SIZE);
-		iommu_free(tbl, dma, npages);
-	}
-}
-
-static int calgary_map_sg(struct device *dev, struct scatterlist *sg,
-			  int nelems, enum dma_data_direction dir,
-			  unsigned long attrs)
-{
-	struct iommu_table *tbl = find_iommu_table(dev);
-	struct scatterlist *s;
-	unsigned long vaddr;
-	unsigned int npages;
-	unsigned long entry;
-	int i;
-
-	for_each_sg(sg, s, nelems, i) {
-		BUG_ON(!sg_page(s));
-
-		vaddr = (unsigned long) sg_virt(s);
-		npages = iommu_num_pages(vaddr, s->length, PAGE_SIZE);
-
-		entry = iommu_range_alloc(dev, tbl, npages);
-		if (entry == DMA_MAPPING_ERROR) {
-			/* makes sure unmap knows to stop */
-			s->dma_length = 0;
-			goto error;
-		}
-
-		s->dma_address = (entry << PAGE_SHIFT) | s->offset;
-
-		/* insert into HW table */
-		tce_build(tbl, entry, npages, vaddr & PAGE_MASK, dir);
-
-		s->dma_length = s->length;
-	}
-
-	return nelems;
-error:
-	calgary_unmap_sg(dev, sg, nelems, dir, 0);
-	for_each_sg(sg, s, nelems, i) {
-		sg->dma_address = DMA_MAPPING_ERROR;
-		sg->dma_length = 0;
-	}
-	return 0;
-}
-
-static dma_addr_t calgary_map_page(struct device *dev, struct page *page,
-				   unsigned long offset, size_t size,
-				   enum dma_data_direction dir,
-				   unsigned long attrs)
-{
-	void *vaddr = page_address(page) + offset;
-	unsigned long uaddr;
-	unsigned int npages;
-	struct iommu_table *tbl = find_iommu_table(dev);
-
-	uaddr = (unsigned long)vaddr;
-	npages = iommu_num_pages(uaddr, size, PAGE_SIZE);
-
-	return iommu_alloc(dev, tbl, vaddr, npages, dir);
-}
-
-static void calgary_unmap_page(struct device *dev, dma_addr_t dma_addr,
-			       size_t size, enum dma_data_direction dir,
-			       unsigned long attrs)
-{
-	struct iommu_table *tbl = find_iommu_table(dev);
-	unsigned int npages;
-
-	npages = iommu_num_pages(dma_addr, size, PAGE_SIZE);
-	iommu_free(tbl, dma_addr, npages);
-}
-
-static void* calgary_alloc_coherent(struct device *dev, size_t size,
-	dma_addr_t *dma_handle, gfp_t flag, unsigned long attrs)
-{
-	void *ret = NULL;
-	dma_addr_t mapping;
-	unsigned int npages, order;
-	struct iommu_table *tbl = find_iommu_table(dev);
-
-	size = PAGE_ALIGN(size); /* size rounded up to full pages */
-	npages = size >> PAGE_SHIFT;
-	order = get_order(size);
-
-	/* alloc enough pages (and possibly more) */
-	ret = (void *)__get_free_pages(flag, order);
-	if (!ret)
-		goto error;
-	memset(ret, 0, size);
-
-	/* set up tces to cover the allocated range */
-	mapping = iommu_alloc(dev, tbl, ret, npages, DMA_BIDIRECTIONAL);
-	if (mapping == DMA_MAPPING_ERROR)
-		goto free;
-	*dma_handle = mapping;
-	return ret;
-free:
-	free_pages((unsigned long)ret, get_order(size));
-	ret = NULL;
-error:
-	return ret;
-}
-
-static void calgary_free_coherent(struct device *dev, size_t size,
-				  void *vaddr, dma_addr_t dma_handle,
-				  unsigned long attrs)
-{
-	unsigned int npages;
-	struct iommu_table *tbl = find_iommu_table(dev);
-
-	size = PAGE_ALIGN(size);
-	npages = size >> PAGE_SHIFT;
-
-	iommu_free(tbl, dma_handle, npages);
-	free_pages((unsigned long)vaddr, get_order(size));
-}
-
-static const struct dma_map_ops calgary_dma_ops = {
-	.alloc = calgary_alloc_coherent,
-	.free = calgary_free_coherent,
-	.map_sg = calgary_map_sg,
-	.unmap_sg = calgary_unmap_sg,
-	.map_page = calgary_map_page,
-	.unmap_page = calgary_unmap_page,
-	.dma_supported = dma_direct_supported,
-	.mmap = dma_common_mmap,
-	.get_sgtable = dma_common_get_sgtable,
-};
-
-static inline void __iomem * busno_to_bbar(unsigned char num)
-{
-	return bus_info[num].bbar;
-}
-
-static inline int busno_to_phbid(unsigned char num)
-{
-	return bus_info[num].phbid;
-}
-
-static inline unsigned long split_queue_offset(unsigned char num)
-{
-	size_t idx = busno_to_phbid(num);
-
-	return split_queue_offsets[idx];
-}
-
-static inline unsigned long tar_offset(unsigned char num)
-{
-	size_t idx = busno_to_phbid(num);
-
-	return tar_offsets[idx];
-}
-
-static inline unsigned long phb_offset(unsigned char num)
-{
-	size_t idx = busno_to_phbid(num);
-
-	return phb_offsets[idx];
-}
-
-static inline void __iomem* calgary_reg(void __iomem *bar, unsigned long offset)
-{
-	unsigned long target = ((unsigned long)bar) | offset;
-	return (void __iomem*)target;
-}
-
-static inline int is_calioc2(unsigned short device)
-{
-	return (device == PCI_DEVICE_ID_IBM_CALIOC2);
-}
-
-static inline int is_calgary(unsigned short device)
-{
-	return (device == PCI_DEVICE_ID_IBM_CALGARY);
-}
-
-static inline int is_cal_pci_dev(unsigned short device)
-{
-	return (is_calgary(device) || is_calioc2(device));
-}
-
-static void calgary_tce_cache_blast(struct iommu_table *tbl)
-{
-	u64 val;
-	u32 aer;
-	int i = 0;
-	void __iomem *bbar = tbl->bbar;
-	void __iomem *target;
-
-	/* disable arbitration on the bus */
-	target = calgary_reg(bbar, phb_offset(tbl->it_busno) | PHB_AER_OFFSET);
-	aer = readl(target);
-	writel(0, target);
-
-	/* read plssr to ensure it got there */
-	target = calgary_reg(bbar, phb_offset(tbl->it_busno) | PHB_PLSSR_OFFSET);
-	val = readl(target);
-
-	/* poll split queues until all DMA activity is done */
-	target = calgary_reg(bbar, split_queue_offset(tbl->it_busno));
-	do {
-		val = readq(target);
-		i++;
-	} while ((val & 0xff) != 0xff && i < 100);
-	if (i == 100)
-		pr_warn("PCI bus not quiesced, continuing anyway\n");
-
-	/* invalidate TCE cache */
-	target = calgary_reg(bbar, tar_offset(tbl->it_busno));
-	writeq(tbl->tar_val, target);
-
-	/* enable arbitration */
-	target = calgary_reg(bbar, phb_offset(tbl->it_busno) | PHB_AER_OFFSET);
-	writel(aer, target);
-	(void)readl(target); /* flush */
-}
-
-static void calioc2_tce_cache_blast(struct iommu_table *tbl)
-{
-	void __iomem *bbar = tbl->bbar;
-	void __iomem *target;
-	u64 val64;
-	u32 val;
-	int i = 0;
-	int count = 1;
-	unsigned char bus = tbl->it_busno;
-
-begin:
-	printk(KERN_DEBUG "Calgary: CalIOC2 bus 0x%x entering tce cache blast "
-	       "sequence - count %d\n", bus, count);
-
-	/* 1. using the Page Migration Control reg set SoftStop */
-	target = calgary_reg(bbar, phb_offset(bus) | PHB_PAGE_MIG_CTRL);
-	val = be32_to_cpu(readl(target));
-	printk(KERN_DEBUG "1a. read 0x%x [LE] from %p\n", val, target);
-	val |= PMR_SOFTSTOP;
-	printk(KERN_DEBUG "1b. writing 0x%x [LE] to %p\n", val, target);
-	writel(cpu_to_be32(val), target);
-
-	/* 2. poll split queues until all DMA activity is done */
-	printk(KERN_DEBUG "2a. starting to poll split queues\n");
-	target = calgary_reg(bbar, split_queue_offset(bus));
-	do {
-		val64 = readq(target);
-		i++;
-	} while ((val64 & 0xff) != 0xff && i < 100);
-	if (i == 100)
-		pr_warn("CalIOC2: PCI bus not quiesced, continuing anyway\n");
-
-	/* 3. poll Page Migration DEBUG for SoftStopFault */
-	target = calgary_reg(bbar, phb_offset(bus) | PHB_PAGE_MIG_DEBUG);
-	val = be32_to_cpu(readl(target));
-	printk(KERN_DEBUG "3. read 0x%x [LE] from %p\n", val, target);
-
-	/* 4. if SoftStopFault - goto (1) */
-	if (val & PMR_SOFTSTOPFAULT) {
-		if (++count < 100)
-			goto begin;
-		else {
-			pr_warn("CalIOC2: too many SoftStopFaults, aborting TCE cache flush sequence!\n");
-			return; /* pray for the best */
-		}
-	}
-
-	/* 5. Slam into HardStop by reading PHB_PAGE_MIG_CTRL */
-	target = calgary_reg(bbar, phb_offset(bus) | PHB_PAGE_MIG_CTRL);
-	printk(KERN_DEBUG "5a. slamming into HardStop by reading %p\n", target);
-	val = be32_to_cpu(readl(target));
-	printk(KERN_DEBUG "5b. read 0x%x [LE] from %p\n", val, target);
-	target = calgary_reg(bbar, phb_offset(bus) | PHB_PAGE_MIG_DEBUG);
-	val = be32_to_cpu(readl(target));
-	printk(KERN_DEBUG "5c. read 0x%x [LE] from %p (debug)\n", val, target);
-
-	/* 6. invalidate TCE cache */
-	printk(KERN_DEBUG "6. invalidating TCE cache\n");
-	target = calgary_reg(bbar, tar_offset(bus));
-	writeq(tbl->tar_val, target);
-
-	/* 7. Re-read PMCR */
-	printk(KERN_DEBUG "7a. Re-reading PMCR\n");
-	target = calgary_reg(bbar, phb_offset(bus) | PHB_PAGE_MIG_CTRL);
-	val = be32_to_cpu(readl(target));
-	printk(KERN_DEBUG "7b. read 0x%x [LE] from %p\n", val, target);
-
-	/* 8. Remove HardStop */
-	printk(KERN_DEBUG "8a. removing HardStop from PMCR\n");
-	target = calgary_reg(bbar, phb_offset(bus) | PHB_PAGE_MIG_CTRL);
-	val = 0;
-	printk(KERN_DEBUG "8b. writing 0x%x [LE] to %p\n", val, target);
-	writel(cpu_to_be32(val), target);
-	val = be32_to_cpu(readl(target));
-	printk(KERN_DEBUG "8c. read 0x%x [LE] from %p\n", val, target);
-}
-
-static void __init calgary_reserve_mem_region(struct pci_dev *dev, u64 start,
-	u64 limit)
-{
-	unsigned int numpages;
-
-	limit = limit | 0xfffff;
-	limit++;
-
-	numpages = ((limit - start) >> PAGE_SHIFT);
-	iommu_range_reserve(pci_iommu(dev->bus), start, numpages);
-}
-
-static void __init calgary_reserve_peripheral_mem_1(struct pci_dev *dev)
-{
-	void __iomem *target;
-	u64 low, high, sizelow;
-	u64 start, limit;
-	struct iommu_table *tbl = pci_iommu(dev->bus);
-	unsigned char busnum = dev->bus->number;
-	void __iomem *bbar = tbl->bbar;
-
-	/* peripheral MEM_1 region */
-	target = calgary_reg(bbar, phb_offset(busnum) | PHB_MEM_1_LOW);
-	low = be32_to_cpu(readl(target));
-	target = calgary_reg(bbar, phb_offset(busnum) | PHB_MEM_1_HIGH);
-	high = be32_to_cpu(readl(target));
-	target = calgary_reg(bbar, phb_offset(busnum) | PHB_MEM_1_SIZE);
-	sizelow = be32_to_cpu(readl(target));
-
-	start = (high << 32) | low;
-	limit = sizelow;
-
-	calgary_reserve_mem_region(dev, start, limit);
-}
-
-static void __init calgary_reserve_peripheral_mem_2(struct pci_dev *dev)
-{
-	void __iomem *target;
-	u32 val32;
-	u64 low, high, sizelow, sizehigh;
-	u64 start, limit;
-	struct iommu_table *tbl = pci_iommu(dev->bus);
-	unsigned char busnum = dev->bus->number;
-	void __iomem *bbar = tbl->bbar;
-
-	/* is it enabled? */
-	target = calgary_reg(bbar, phb_offset(busnum) | PHB_CONFIG_RW_OFFSET);
-	val32 = be32_to_cpu(readl(target));
-	if (!(val32 & PHB_MEM2_ENABLE))
-		return;
-
-	target = calgary_reg(bbar, phb_offset(busnum) | PHB_MEM_2_LOW);
-	low = be32_to_cpu(readl(target));
-	target = calgary_reg(bbar, phb_offset(busnum) | PHB_MEM_2_HIGH);
-	high = be32_to_cpu(readl(target));
-	target = calgary_reg(bbar, phb_offset(busnum) | PHB_MEM_2_SIZE_LOW);
-	sizelow = be32_to_cpu(readl(target));
-	target = calgary_reg(bbar, phb_offset(busnum) | PHB_MEM_2_SIZE_HIGH);
-	sizehigh = be32_to_cpu(readl(target));
-
-	start = (high << 32) | low;
-	limit = (sizehigh << 32) | sizelow;
-
-	calgary_reserve_mem_region(dev, start, limit);
-}
-
-/*
- * some regions of the IO address space do not get translated, so we
- * must not give devices IO addresses in those regions. The regions
- * are the 640KB-1MB region and the two PCI peripheral memory holes.
- * Reserve all of them in the IOMMU bitmap to avoid giving them out
- * later.
- */
-static void __init calgary_reserve_regions(struct pci_dev *dev)
-{
-	unsigned int npages;
-	u64 start;
-	struct iommu_table *tbl = pci_iommu(dev->bus);
-
-	/* avoid the BIOS/VGA first 640KB-1MB region */
-	/* for CalIOC2 - avoid the entire first MB */
-	if (is_calgary(dev->device)) {
-		start = (640 * 1024);
-		npages = ((1024 - 640) * 1024) >> PAGE_SHIFT;
-	} else { /* calioc2 */
-		start = 0;
-		npages = (1 * 1024 * 1024) >> PAGE_SHIFT;
-	}
-	iommu_range_reserve(tbl, start, npages);
-
-	/* reserve the two PCI peripheral memory regions in IO space */
-	calgary_reserve_peripheral_mem_1(dev);
-	calgary_reserve_peripheral_mem_2(dev);
-}
-
-static int __init calgary_setup_tar(struct pci_dev *dev, void __iomem *bbar)
-{
-	u64 val64;
-	u64 table_phys;
-	void __iomem *target;
-	int ret;
-	struct iommu_table *tbl;
-
-	/* build TCE tables for each PHB */
-	ret = build_tce_table(dev, bbar);
-	if (ret)
-		return ret;
-
-	tbl = pci_iommu(dev->bus);
-	tbl->it_base = (unsigned long)bus_info[dev->bus->number].tce_space;
-
-	if (is_kdump_kernel())
-		calgary_init_bitmap_from_tce_table(tbl);
-	else
-		tce_free(tbl, 0, tbl->it_size);
-
-	if (is_calgary(dev->device))
-		tbl->chip_ops = &calgary_chip_ops;
-	else if (is_calioc2(dev->device))
-		tbl->chip_ops = &calioc2_chip_ops;
-	else
-		BUG();
-
-	calgary_reserve_regions(dev);
-
-	/* set TARs for each PHB */
-	target = calgary_reg(bbar, tar_offset(dev->bus->number));
-	val64 = be64_to_cpu(readq(target));
-
-	/* zero out all TAR bits under sw control */
-	val64 &= ~TAR_SW_BITS;
-	table_phys = (u64)__pa(tbl->it_base);
-
-	val64 |= table_phys;
-
-	BUG_ON(specified_table_size > TCE_TABLE_SIZE_8M);
-	val64 |= (u64) specified_table_size;
-
-	tbl->tar_val = cpu_to_be64(val64);
-
-	writeq(tbl->tar_val, target);
-	readq(target); /* flush */
-
-	return 0;
-}
-
-static void __init calgary_free_bus(struct pci_dev *dev)
-{
-	u64 val64;
-	struct iommu_table *tbl = pci_iommu(dev->bus);
-	void __iomem *target;
-	unsigned int bitmapsz;
-
-	target = calgary_reg(tbl->bbar, tar_offset(dev->bus->number));
-	val64 = be64_to_cpu(readq(target));
-	val64 &= ~TAR_SW_BITS;
-	writeq(cpu_to_be64(val64), target);
-	readq(target); /* flush */
-
-	bitmapsz = tbl->it_size / BITS_PER_BYTE;
-	free_pages((unsigned long)tbl->it_map, get_order(bitmapsz));
-	tbl->it_map = NULL;
-
-	kfree(tbl);
-	
-	set_pci_iommu(dev->bus, NULL);
-
-	/* Can't free bootmem allocated memory after system is up :-( */
-	bus_info[dev->bus->number].tce_space = NULL;
-}
-
-static void calgary_dump_error_regs(struct iommu_table *tbl)
-{
-	void __iomem *bbar = tbl->bbar;
-	void __iomem *target;
-	u32 csr, plssr;
-
-	target = calgary_reg(bbar, phb_offset(tbl->it_busno) | PHB_CSR_OFFSET);
-	csr = be32_to_cpu(readl(target));
-
-	target = calgary_reg(bbar, phb_offset(tbl->it_busno) | PHB_PLSSR_OFFSET);
-	plssr = be32_to_cpu(readl(target));
-
-	/* If no error, the agent ID in the CSR is not valid */
-	pr_emerg("DMA error on Calgary PHB 0x%x, 0x%08x@CSR 0x%08x@PLSSR\n",
-		 tbl->it_busno, csr, plssr);
-}
-
-static void calioc2_dump_error_regs(struct iommu_table *tbl)
-{
-	void __iomem *bbar = tbl->bbar;
-	u32 csr, csmr, plssr, mck, rcstat;
-	void __iomem *target;
-	unsigned long phboff = phb_offset(tbl->it_busno);
-	unsigned long erroff;
-	u32 errregs[7];
-	int i;
-
-	/* dump CSR */
-	target = calgary_reg(bbar, phboff | PHB_CSR_OFFSET);
-	csr = be32_to_cpu(readl(target));
-	/* dump PLSSR */
-	target = calgary_reg(bbar, phboff | PHB_PLSSR_OFFSET);
-	plssr = be32_to_cpu(readl(target));
-	/* dump CSMR */
-	target = calgary_reg(bbar, phboff | 0x290);
-	csmr = be32_to_cpu(readl(target));
-	/* dump mck */
-	target = calgary_reg(bbar, phboff | 0x800);
-	mck = be32_to_cpu(readl(target));
-
-	pr_emerg("DMA error on CalIOC2 PHB 0x%x\n", tbl->it_busno);
-
-	pr_emerg("0x%08x@CSR 0x%08x@PLSSR 0x%08x@CSMR 0x%08x@MCK\n",
-		 csr, plssr, csmr, mck);
-
-	/* dump rest of error regs */
-	pr_emerg("");
-	for (i = 0; i < ARRAY_SIZE(errregs); i++) {
-		/* err regs are at 0x810 - 0x870 */
-		erroff = (0x810 + (i * 0x10));
-		target = calgary_reg(bbar, phboff | erroff);
-		errregs[i] = be32_to_cpu(readl(target));
-		pr_cont("0x%08x@0x%lx ", errregs[i], erroff);
-	}
-	pr_cont("\n");
-
-	/* root complex status */
-	target = calgary_reg(bbar, phboff | PHB_ROOT_COMPLEX_STATUS);
-	rcstat = be32_to_cpu(readl(target));
-	printk(KERN_EMERG "Calgary: 0x%08x@0x%x\n", rcstat,
-	       PHB_ROOT_COMPLEX_STATUS);
-}
-
-static void calgary_watchdog(struct timer_list *t)
-{
-	struct iommu_table *tbl = from_timer(tbl, t, watchdog_timer);
-	void __iomem *bbar = tbl->bbar;
-	u32 val32;
-	void __iomem *target;
-
-	target = calgary_reg(bbar, phb_offset(tbl->it_busno) | PHB_CSR_OFFSET);
-	val32 = be32_to_cpu(readl(target));
-
-	/* If no error, the agent ID in the CSR is not valid */
-	if (val32 & CSR_AGENT_MASK) {
-		tbl->chip_ops->dump_error_regs(tbl);
-
-		/* reset error */
-		writel(0, target);
-
-		/* Disable bus that caused the error */
-		target = calgary_reg(bbar, phb_offset(tbl->it_busno) |
-				     PHB_CONFIG_RW_OFFSET);
-		val32 = be32_to_cpu(readl(target));
-		val32 |= PHB_SLOT_DISABLE;
-		writel(cpu_to_be32(val32), target);
-		readl(target); /* flush */
-	} else {
-		/* Reset the timer */
-		mod_timer(&tbl->watchdog_timer, jiffies + 2 * HZ);
-	}
-}
-
-static void __init calgary_set_split_completion_timeout(void __iomem *bbar,
-	unsigned char busnum, unsigned long timeout)
-{
-	u64 val64;
-	void __iomem *target;
-	unsigned int phb_shift = ~0; /* silence gcc */
-	u64 mask;
-
-	switch (busno_to_phbid(busnum)) {
-	case 0: phb_shift = (63 - 19);
-		break;
-	case 1: phb_shift = (63 - 23);
-		break;
-	case 2: phb_shift = (63 - 27);
-		break;
-	case 3: phb_shift = (63 - 35);
-		break;
-	default:
-		BUG_ON(busno_to_phbid(busnum));
-	}
-
-	target = calgary_reg(bbar, CALGARY_CONFIG_REG);
-	val64 = be64_to_cpu(readq(target));
-
-	/* zero out this PHB's timer bits */
-	mask = ~(0xFUL << phb_shift);
-	val64 &= mask;
-	val64 |= (timeout << phb_shift);
-	writeq(cpu_to_be64(val64), target);
-	readq(target); /* flush */
-}
-
-static void __init calioc2_handle_quirks(struct iommu_table *tbl, struct pci_dev *dev)
-{
-	unsigned char busnum = dev->bus->number;
-	void __iomem *bbar = tbl->bbar;
-	void __iomem *target;
-	u32 val;
-
-	/*
-	 * CalIOC2 designers recommend setting bit 8 in 0xnDB0 to 1
-	 */
-	target = calgary_reg(bbar, phb_offset(busnum) | PHB_SAVIOR_L2);
-	val = cpu_to_be32(readl(target));
-	val |= 0x00800000;
-	writel(cpu_to_be32(val), target);
-}
-
-static void __init calgary_handle_quirks(struct iommu_table *tbl, struct pci_dev *dev)
-{
-	unsigned char busnum = dev->bus->number;
-
-	/*
-	 * Give split completion a longer timeout on bus 1 for aic94xx
-	 * http://bugzilla.kernel.org/show_bug.cgi?id=7180
-	 */
-	if (is_calgary(dev->device) && (busnum == 1))
-		calgary_set_split_completion_timeout(tbl->bbar, busnum,
-						     CCR_2SEC_TIMEOUT);
-}
-
-static void __init calgary_enable_translation(struct pci_dev *dev)
-{
-	u32 val32;
-	unsigned char busnum;
-	void __iomem *target;
-	void __iomem *bbar;
-	struct iommu_table *tbl;
-
-	busnum = dev->bus->number;
-	tbl = pci_iommu(dev->bus);
-	bbar = tbl->bbar;
-
-	/* enable TCE in PHB Config Register */
-	target = calgary_reg(bbar, phb_offset(busnum) | PHB_CONFIG_RW_OFFSET);
-	val32 = be32_to_cpu(readl(target));
-	val32 |= PHB_TCE_ENABLE | PHB_DAC_DISABLE | PHB_MCSR_ENABLE;
-
-	printk(KERN_INFO "Calgary: enabling translation on %s PHB %#x\n",
-	       (dev->device == PCI_DEVICE_ID_IBM_CALGARY) ?
-	       "Calgary" : "CalIOC2", busnum);
-	printk(KERN_INFO "Calgary: errant DMAs will now be prevented on this "
-	       "bus.\n");
-
-	writel(cpu_to_be32(val32), target);
-	readl(target); /* flush */
-
-	timer_setup(&tbl->watchdog_timer, calgary_watchdog, 0);
-	mod_timer(&tbl->watchdog_timer, jiffies);
-}
-
-static void __init calgary_disable_translation(struct pci_dev *dev)
-{
-	u32 val32;
-	unsigned char busnum;
-	void __iomem *target;
-	void __iomem *bbar;
-	struct iommu_table *tbl;
-
-	busnum = dev->bus->number;
-	tbl = pci_iommu(dev->bus);
-	bbar = tbl->bbar;
-
-	/* disable TCE in PHB Config Register */
-	target = calgary_reg(bbar, phb_offset(busnum) | PHB_CONFIG_RW_OFFSET);
-	val32 = be32_to_cpu(readl(target));
-	val32 &= ~(PHB_TCE_ENABLE | PHB_DAC_DISABLE | PHB_MCSR_ENABLE);
-
-	printk(KERN_INFO "Calgary: disabling translation on PHB %#x!\n", busnum);
-	writel(cpu_to_be32(val32), target);
-	readl(target); /* flush */
-
-	del_timer_sync(&tbl->watchdog_timer);
-}
-
-static void __init calgary_init_one_nontraslated(struct pci_dev *dev)
-{
-	pci_dev_get(dev);
-	set_pci_iommu(dev->bus, NULL);
-
-	/* is the device behind a bridge? */
-	if (dev->bus->parent)
-		dev->bus->parent->self = dev;
-	else
-		dev->bus->self = dev;
-}
-
-static int __init calgary_init_one(struct pci_dev *dev)
-{
-	void __iomem *bbar;
-	struct iommu_table *tbl;
-	int ret;
-
-	bbar = busno_to_bbar(dev->bus->number);
-	ret = calgary_setup_tar(dev, bbar);
-	if (ret)
-		goto done;
-
-	pci_dev_get(dev);
-
-	if (dev->bus->parent) {
-		if (dev->bus->parent->self)
-			printk(KERN_WARNING "Calgary: IEEEE, dev %p has "
-			       "bus->parent->self!\n", dev);
-		dev->bus->parent->self = dev;
-	} else
-		dev->bus->self = dev;
-
-	tbl = pci_iommu(dev->bus);
-	tbl->chip_ops->handle_quirks(tbl, dev);
-
-	calgary_enable_translation(dev);
-
-	return 0;
-
-done:
-	return ret;
-}
-
-static int __init calgary_locate_bbars(void)
-{
-	int ret;
-	int rioidx, phb, bus;
-	void __iomem *bbar;
-	void __iomem *target;
-	unsigned long offset;
-	u8 start_bus, end_bus;
-	u32 val;
-
-	ret = -ENODATA;
-	for (rioidx = 0; rioidx < rio_table_hdr->num_rio_dev; rioidx++) {
-		struct rio_detail *rio = rio_devs[rioidx];
-
-		if ((rio->type != COMPAT_CALGARY) && (rio->type != ALT_CALGARY))
-			continue;
-
-		/* map entire 1MB of Calgary config space */
-		bbar = ioremap_nocache(rio->BBAR, 1024 * 1024);
-		if (!bbar)
-			goto error;
-
-		for (phb = 0; phb < PHBS_PER_CALGARY; phb++) {
-			offset = phb_debug_offsets[phb] | PHB_DEBUG_STUFF_OFFSET;
-			target = calgary_reg(bbar, offset);
-
-			val = be32_to_cpu(readl(target));
-
-			start_bus = (u8)((val & 0x00FF0000) >> 16);
-			end_bus = (u8)((val & 0x0000FF00) >> 8);
-
-			if (end_bus) {
-				for (bus = start_bus; bus <= end_bus; bus++) {
-					bus_info[bus].bbar = bbar;
-					bus_info[bus].phbid = phb;
-				}
-			} else {
-				bus_info[start_bus].bbar = bbar;
-				bus_info[start_bus].phbid = phb;
-			}
-		}
-	}
-
-	return 0;
-
-error:
-	/* scan bus_info and iounmap any bbars we previously ioremap'd */
-	for (bus = 0; bus < ARRAY_SIZE(bus_info); bus++)
-		if (bus_info[bus].bbar)
-			iounmap(bus_info[bus].bbar);
-
-	return ret;
-}
-
-static int __init calgary_init(void)
-{
-	int ret;
-	struct pci_dev *dev = NULL;
-	struct calgary_bus_info *info;
-
-	ret = calgary_locate_bbars();
-	if (ret)
-		return ret;
-
-	/* Purely for kdump kernel case */
-	if (is_kdump_kernel())
-		get_tce_space_from_tar();
-
-	do {
-		dev = pci_get_device(PCI_VENDOR_ID_IBM, PCI_ANY_ID, dev);
-		if (!dev)
-			break;
-		if (!is_cal_pci_dev(dev->device))
-			continue;
-
-		info = &bus_info[dev->bus->number];
-		if (info->translation_disabled) {
-			calgary_init_one_nontraslated(dev);
-			continue;
-		}
-
-		if (!info->tce_space && !translate_empty_slots)
-			continue;
-
-		ret = calgary_init_one(dev);
-		if (ret)
-			goto error;
-	} while (1);
-
-	dev = NULL;
-	for_each_pci_dev(dev) {
-		struct iommu_table *tbl;
-
-		tbl = find_iommu_table(&dev->dev);
-
-		if (translation_enabled(tbl))
-			dev->dev.dma_ops = &calgary_dma_ops;
-	}
-
-	return ret;
-
-error:
-	do {
-		dev = pci_get_device(PCI_VENDOR_ID_IBM, PCI_ANY_ID, dev);
-		if (!dev)
-			break;
-		if (!is_cal_pci_dev(dev->device))
-			continue;
-
-		info = &bus_info[dev->bus->number];
-		if (info->translation_disabled) {
-			pci_dev_put(dev);
-			continue;
-		}
-		if (!info->tce_space && !translate_empty_slots)
-			continue;
-
-		calgary_disable_translation(dev);
-		calgary_free_bus(dev);
-		pci_dev_put(dev); /* Undo calgary_init_one()'s pci_dev_get() */
-		dev->dev.dma_ops = NULL;
-	} while (1);
-
-	return ret;
-}
-
-static inline int __init determine_tce_table_size(void)
-{
-	int ret;
-
-	if (specified_table_size != TCE_TABLE_SIZE_UNSPECIFIED)
-		return specified_table_size;
-
-	if (is_kdump_kernel() && saved_max_pfn) {
-		/*
-		 * Table sizes are from 0 to 7 (TCE_TABLE_SIZE_64K to
-		 * TCE_TABLE_SIZE_8M). Table size 0 has 8K entries and each
-		 * larger table size has twice as many entries, so shift the
-		 * max ram address by 13 to divide by 8K and then look at the
-		 * order of the result to choose between 0-7.
-		 */
-		ret = get_order((saved_max_pfn * PAGE_SIZE) >> 13);
-		if (ret > TCE_TABLE_SIZE_8M)
-			ret = TCE_TABLE_SIZE_8M;
-	} else {
-		/*
-		 * Use 8M by default (suggested by Muli) if it's not
-		 * kdump kernel and saved_max_pfn isn't set.
-		 */
-		ret = TCE_TABLE_SIZE_8M;
-	}
-
-	return ret;
-}
-
-static int __init build_detail_arrays(void)
-{
-	unsigned long ptr;
-	unsigned numnodes, i;
-	int scal_detail_size, rio_detail_size;
-
-	numnodes = rio_table_hdr->num_scal_dev;
-	if (numnodes > MAX_NUMNODES){
-		printk(KERN_WARNING
-			"Calgary: MAX_NUMNODES too low! Defined as %d, "
-			"but system has %d nodes.\n",
-			MAX_NUMNODES, numnodes);
-		return -ENODEV;
-	}
-
-	switch (rio_table_hdr->version){
-	case 2:
-		scal_detail_size = 11;
-		rio_detail_size = 13;
-		break;
-	case 3:
-		scal_detail_size = 12;
-		rio_detail_size = 15;
-		break;
-	default:
-		printk(KERN_WARNING
-		       "Calgary: Invalid Rio Grande Table Version: %d\n",
-		       rio_table_hdr->version);
-		return -EPROTO;
-	}
-
-	ptr = ((unsigned long)rio_table_hdr) + 3;
-	for (i = 0; i < numnodes; i++, ptr += scal_detail_size)
-		scal_devs[i] = (struct scal_detail *)ptr;
-
-	for (i = 0; i < rio_table_hdr->num_rio_dev;
-		    i++, ptr += rio_detail_size)
-		rio_devs[i] = (struct rio_detail *)ptr;
-
-	return 0;
-}
-
-static int __init calgary_bus_has_devices(int bus, unsigned short pci_dev)
-{
-	int dev;
-	u32 val;
-
-	if (pci_dev == PCI_DEVICE_ID_IBM_CALIOC2) {
-		/*
-		 * FIXME: properly scan for devices across the
-		 * PCI-to-PCI bridge on every CalIOC2 port.
-		 */
-		return 1;
-	}
-
-	for (dev = 1; dev < 8; dev++) {
-		val = read_pci_config(bus, dev, 0, 0);
-		if (val != 0xffffffff)
-			break;
-	}
-	return (val != 0xffffffff);
-}
-
-/*
- * calgary_init_bitmap_from_tce_table():
- * Function for kdump case. In the second/kdump kernel initialize
- * the bitmap based on the tce table entries obtained from first kernel
- */
-static void calgary_init_bitmap_from_tce_table(struct iommu_table *tbl)
-{
-	u64 *tp;
-	unsigned int index;
-	tp = ((u64 *)tbl->it_base);
-	for (index = 0 ; index < tbl->it_size; index++) {
-		if (*tp != 0x0)
-			set_bit(index, tbl->it_map);
-		tp++;
-	}
-}
-
-/*
- * get_tce_space_from_tar():
- * Function for kdump case. Get the tce tables from first kernel
- * by reading the contents of the base address register of calgary iommu
- */
-static void __init get_tce_space_from_tar(void)
-{
-	int bus;
-	void __iomem *target;
-	unsigned long tce_space;
-
-	for (bus = 0; bus < MAX_PHB_BUS_NUM; bus++) {
-		struct calgary_bus_info *info = &bus_info[bus];
-		unsigned short pci_device;
-		u32 val;
-
-		val = read_pci_config(bus, 0, 0, 0);
-		pci_device = (val & 0xFFFF0000) >> 16;
-
-		if (!is_cal_pci_dev(pci_device))
-			continue;
-		if (info->translation_disabled)
-			continue;
-
-		if (calgary_bus_has_devices(bus, pci_device) ||
-						translate_empty_slots) {
-			target = calgary_reg(bus_info[bus].bbar,
-						tar_offset(bus));
-			tce_space = be64_to_cpu(readq(target));
-			tce_space = tce_space & TAR_SW_BITS;
-
-			tce_space = tce_space & (~specified_table_size);
-			info->tce_space = (u64 *)__va(tce_space);
-		}
-	}
-	return;
-}
-
-static int __init calgary_iommu_init(void)
-{
-	int ret;
-
-	/* ok, we're trying to use Calgary - let's roll */
-	printk(KERN_INFO "PCI-DMA: Using Calgary IOMMU\n");
-
-	ret = calgary_init();
-	if (ret) {
-		printk(KERN_ERR "PCI-DMA: Calgary init failed %d, "
-		       "falling back to no_iommu\n", ret);
-		return ret;
-	}
-
-	return 0;
-}
-
-int __init detect_calgary(void)
-{
-	int bus;
-	void *tbl;
-	int calgary_found = 0;
-	unsigned long ptr;
-	unsigned int offset, prev_offset;
-	int ret;
-
-	/*
-	 * if the user specified iommu=off or iommu=soft or we found
-	 * another HW IOMMU already, bail out.
-	 */
-	if (no_iommu || iommu_detected)
-		return -ENODEV;
-
-	if (!use_calgary)
-		return -ENODEV;
-
-	if (!early_pci_allowed())
-		return -ENODEV;
-
-	printk(KERN_DEBUG "Calgary: detecting Calgary via BIOS EBDA area\n");
-
-	ptr = (unsigned long)phys_to_virt(get_bios_ebda());
-
-	rio_table_hdr = NULL;
-	prev_offset = 0;
-	offset = 0x180;
-	/*
-	 * The next offset is stored in the 1st word.
-	 * Only parse up until the offset increases:
-	 */
-	while (offset > prev_offset) {
-		/* The block id is stored in the 2nd word */
-		if (*((unsigned short *)(ptr + offset + 2)) == 0x4752){
-			/* set the pointer past the offset & block id */
-			rio_table_hdr = (struct rio_table_hdr *)(ptr + offset + 4);
-			break;
-		}
-		prev_offset = offset;
-		offset = *((unsigned short *)(ptr + offset));
-	}
-	if (!rio_table_hdr) {
-		printk(KERN_DEBUG "Calgary: Unable to locate Rio Grande table "
-		       "in EBDA - bailing!\n");
-		return -ENODEV;
-	}
-
-	ret = build_detail_arrays();
-	if (ret) {
-		printk(KERN_DEBUG "Calgary: build_detail_arrays ret %d\n", ret);
-		return -ENOMEM;
-	}
-
-	specified_table_size = determine_tce_table_size();
-
-	for (bus = 0; bus < MAX_PHB_BUS_NUM; bus++) {
-		struct calgary_bus_info *info = &bus_info[bus];
-		unsigned short pci_device;
-		u32 val;
-
-		val = read_pci_config(bus, 0, 0, 0);
-		pci_device = (val & 0xFFFF0000) >> 16;
-
-		if (!is_cal_pci_dev(pci_device))
-			continue;
-
-		if (info->translation_disabled)
-			continue;
-
-		if (calgary_bus_has_devices(bus, pci_device) ||
-		    translate_empty_slots) {
-			/*
-			 * If it is kdump kernel, find and use tce tables
-			 * from first kernel, else allocate tce tables here
-			 */
-			if (!is_kdump_kernel()) {
-				tbl = alloc_tce_table();
-				if (!tbl)
-					goto cleanup;
-				info->tce_space = tbl;
-			}
-			calgary_found = 1;
-		}
-	}
-
-	printk(KERN_DEBUG "Calgary: finished detection, Calgary %s\n",
-	       calgary_found ? "found" : "not found");
-
-	if (calgary_found) {
-		iommu_detected = 1;
-		calgary_detected = 1;
-		printk(KERN_INFO "PCI-DMA: Calgary IOMMU detected.\n");
-		printk(KERN_INFO "PCI-DMA: Calgary TCE table spec is %d\n",
-		       specified_table_size);
-
-		x86_init.iommu.iommu_init = calgary_iommu_init;
-	}
-	return calgary_found;
-
-cleanup:
-	for (--bus; bus >= 0; --bus) {
-		struct calgary_bus_info *info = &bus_info[bus];
-
-		if (info->tce_space)
-			free_tce_table(info->tce_space);
-	}
-	return -ENOMEM;
-}
-
-static int __init calgary_parse_options(char *p)
-{
-	unsigned int bridge;
-	unsigned long val;
-	size_t len;
-	ssize_t ret;
-
-	while (*p) {
-		if (!strncmp(p, "64k", 3))
-			specified_table_size = TCE_TABLE_SIZE_64K;
-		else if (!strncmp(p, "128k", 4))
-			specified_table_size = TCE_TABLE_SIZE_128K;
-		else if (!strncmp(p, "256k", 4))
-			specified_table_size = TCE_TABLE_SIZE_256K;
-		else if (!strncmp(p, "512k", 4))
-			specified_table_size = TCE_TABLE_SIZE_512K;
-		else if (!strncmp(p, "1M", 2))
-			specified_table_size = TCE_TABLE_SIZE_1M;
-		else if (!strncmp(p, "2M", 2))
-			specified_table_size = TCE_TABLE_SIZE_2M;
-		else if (!strncmp(p, "4M", 2))
-			specified_table_size = TCE_TABLE_SIZE_4M;
-		else if (!strncmp(p, "8M", 2))
-			specified_table_size = TCE_TABLE_SIZE_8M;
-
-		len = strlen("translate_empty_slots");
-		if (!strncmp(p, "translate_empty_slots", len))
-			translate_empty_slots = 1;
-
-		len = strlen("disable");
-		if (!strncmp(p, "disable", len)) {
-			p += len;
-			if (*p == '=')
-				++p;
-			if (*p == '\0')
-				break;
-			ret = kstrtoul(p, 0, &val);
-			if (ret)
-				break;
-
-			bridge = val;
-			if (bridge < MAX_PHB_BUS_NUM) {
-				printk(KERN_INFO "Calgary: disabling "
-				       "translation for PHB %#x\n", bridge);
-				bus_info[bridge].translation_disabled = 1;
-			}
-		}
-
-		p = strpbrk(p, ",");
-		if (!p)
-			break;
-
-		p++; /* skip ',' */
-	}
-	return 1;
-}
-__setup("calgary=", calgary_parse_options);
-
-static void __init calgary_fixup_one_tce_space(struct pci_dev *dev)
-{
-	struct iommu_table *tbl;
-	unsigned int npages;
-	int i;
-
-	tbl = pci_iommu(dev->bus);
-
-	for (i = 0; i < 4; i++) {
-		struct resource *r = &dev->resource[PCI_BRIDGE_RESOURCES + i];
-
-		/* Don't give out TCEs that map MEM resources */
-		if (!(r->flags & IORESOURCE_MEM))
-			continue;
-
-		/* 0-based? we reserve the whole 1st MB anyway */
-		if (!r->start)
-			continue;
-
-		/* cover the whole region */
-		npages = resource_size(r) >> PAGE_SHIFT;
-		npages++;
-
-		iommu_range_reserve(tbl, r->start, npages);
-	}
-}
-
-static int __init calgary_fixup_tce_spaces(void)
-{
-	struct pci_dev *dev = NULL;
-	struct calgary_bus_info *info;
-
-	if (no_iommu || swiotlb || !calgary_detected)
-		return -ENODEV;
-
-	printk(KERN_DEBUG "Calgary: fixing up tce spaces\n");
-
-	do {
-		dev = pci_get_device(PCI_VENDOR_ID_IBM, PCI_ANY_ID, dev);
-		if (!dev)
-			break;
-		if (!is_cal_pci_dev(dev->device))
-			continue;
-
-		info = &bus_info[dev->bus->number];
-		if (info->translation_disabled)
-			continue;
-
-		if (!info->tce_space)
-			continue;
-
-		calgary_fixup_one_tce_space(dev);
-
-	} while (1);
-
-	return 0;
-}
-
-/*
- * We need to be call after pcibios_assign_resources (fs_initcall level)
- * and before device_initcall.
- */
-rootfs_initcall(calgary_fixup_tce_spaces);
-
-IOMMU_INIT_POST(detect_calgary);
diff --git a/arch/x86/kernel/pci-dma.c b/arch/x86/kernel/pci-dma.c
index fa4352dce491..57de2ebff7e2 100644
--- a/arch/x86/kernel/pci-dma.c
+++ b/arch/x86/kernel/pci-dma.c
@@ -12,7 +12,6 @@
 #include <asm/dma.h>
 #include <asm/iommu.h>
 #include <asm/gart.h>
-#include <asm/calgary.h>
 #include <asm/x86_init.h>
 #include <asm/iommu_table.h>
 
@@ -112,11 +111,6 @@ static __init int iommu_setup(char *p)
 
 		gart_parse_options(p);
 
-#ifdef CONFIG_CALGARY_IOMMU
-		if (!strncmp(p, "calgary", 7))
-			use_calgary = 1;
-#endif /* CONFIG_CALGARY_IOMMU */
-
 		p += strcspn(p, ",");
 		if (*p == ',')
 			++p;
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index 5e94c4354d4e..bd2a11ca5dd6 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -41,6 +41,7 @@
 #include <asm/desc.h>
 #include <asm/prctl.h>
 #include <asm/spec-ctrl.h>
+#include <asm/io_bitmap.h>
 #include <asm/proto.h>
 
 #include "process.h"
@@ -72,18 +73,9 @@ __visible DEFINE_PER_CPU_PAGE_ALIGNED(struct tss_struct, cpu_tss_rw) = {
 #ifdef CONFIG_X86_32
 		.ss0 = __KERNEL_DS,
 		.ss1 = __KERNEL_CS,
-		.io_bitmap_base	= INVALID_IO_BITMAP_OFFSET,
 #endif
+		.io_bitmap_base	= IO_BITMAP_OFFSET_INVALID,
 	 },
-#ifdef CONFIG_X86_32
-	 /*
-	  * Note that the .io_bitmap member must be extra-big. This is because
-	  * the CPU will access an additional byte beyond the end of the IO
-	  * permission bitmap. The extra byte must be all 1 bits, and must
-	  * be within the limit.
-	  */
-	.io_bitmap		= { [0 ... IO_BITMAP_LONGS] = ~0 },
-#endif
 };
 EXPORT_PER_CPU_SYMBOL(cpu_tss_rw);
 
@@ -110,28 +102,89 @@ int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src)
 void exit_thread(struct task_struct *tsk)
 {
 	struct thread_struct *t = &tsk->thread;
-	unsigned long *bp = t->io_bitmap_ptr;
 	struct fpu *fpu = &t->fpu;
 
-	if (bp) {
-		struct tss_struct *tss = &per_cpu(cpu_tss_rw, get_cpu());
-
-		t->io_bitmap_ptr = NULL;
-		clear_thread_flag(TIF_IO_BITMAP);
-		/*
-		 * Careful, clear this in the TSS too:
-		 */
-		memset(tss->io_bitmap, 0xff, t->io_bitmap_max);
-		t->io_bitmap_max = 0;
-		put_cpu();
-		kfree(bp);
-	}
+	if (test_thread_flag(TIF_IO_BITMAP))
+		io_bitmap_exit();
 
 	free_vm86(t);
 
 	fpu__drop(fpu);
 }
 
+static int set_new_tls(struct task_struct *p, unsigned long tls)
+{
+	struct user_desc __user *utls = (struct user_desc __user *)tls;
+
+	if (in_ia32_syscall())
+		return do_set_thread_area(p, -1, utls, 0);
+	else
+		return do_set_thread_area_64(p, ARCH_SET_FS, tls);
+}
+
+int copy_thread_tls(unsigned long clone_flags, unsigned long sp,
+		    unsigned long arg, struct task_struct *p, unsigned long tls)
+{
+	struct inactive_task_frame *frame;
+	struct fork_frame *fork_frame;
+	struct pt_regs *childregs;
+	int ret = 0;
+
+	childregs = task_pt_regs(p);
+	fork_frame = container_of(childregs, struct fork_frame, regs);
+	frame = &fork_frame->frame;
+
+	frame->bp = 0;
+	frame->ret_addr = (unsigned long) ret_from_fork;
+	p->thread.sp = (unsigned long) fork_frame;
+	p->thread.io_bitmap = NULL;
+	memset(p->thread.ptrace_bps, 0, sizeof(p->thread.ptrace_bps));
+
+#ifdef CONFIG_X86_64
+	savesegment(gs, p->thread.gsindex);
+	p->thread.gsbase = p->thread.gsindex ? 0 : current->thread.gsbase;
+	savesegment(fs, p->thread.fsindex);
+	p->thread.fsbase = p->thread.fsindex ? 0 : current->thread.fsbase;
+	savesegment(es, p->thread.es);
+	savesegment(ds, p->thread.ds);
+#else
+	p->thread.sp0 = (unsigned long) (childregs + 1);
+	/*
+	 * Clear all status flags including IF and set fixed bit. 64bit
+	 * does not have this initialization as the frame does not contain
+	 * flags. The flags consistency (especially vs. AC) is there
+	 * ensured via objtool, which lacks 32bit support.
+	 */
+	frame->flags = X86_EFLAGS_FIXED;
+#endif
+
+	/* Kernel thread ? */
+	if (unlikely(p->flags & PF_KTHREAD)) {
+		memset(childregs, 0, sizeof(struct pt_regs));
+		kthread_frame_init(frame, sp, arg);
+		return 0;
+	}
+
+	frame->bx = 0;
+	*childregs = *current_pt_regs();
+	childregs->ax = 0;
+	if (sp)
+		childregs->sp = sp;
+
+#ifdef CONFIG_X86_32
+	task_user_gs(p) = get_user_gs(current_pt_regs());
+#endif
+
+	/* Set a new TLS for the child thread? */
+	if (clone_flags & CLONE_SETTLS)
+		ret = set_new_tls(p, tls);
+
+	if (!ret && unlikely(test_tsk_thread_flag(current, TIF_IO_BITMAP)))
+		io_bitmap_share(p);
+
+	return ret;
+}
+
 void flush_thread(void)
 {
 	struct task_struct *tsk = current;
@@ -269,31 +322,96 @@ void arch_setup_new_exec(void)
 	}
 }
 
-static inline void switch_to_bitmap(struct thread_struct *prev,
-				    struct thread_struct *next,
-				    unsigned long tifp, unsigned long tifn)
+#ifdef CONFIG_X86_IOPL_IOPERM
+static inline void tss_invalidate_io_bitmap(struct tss_struct *tss)
 {
-	struct tss_struct *tss = this_cpu_ptr(&cpu_tss_rw);
+	/*
+	 * Invalidate the I/O bitmap by moving io_bitmap_base outside the
+	 * TSS limit so any subsequent I/O access from user space will
+	 * trigger a #GP.
+	 *
+	 * This is correct even when VMEXIT rewrites the TSS limit
+	 * to 0x67 as the only requirement is that the base points
+	 * outside the limit.
+	 */
+	tss->x86_tss.io_bitmap_base = IO_BITMAP_OFFSET_INVALID;
+}
 
-	if (tifn & _TIF_IO_BITMAP) {
-		/*
-		 * Copy the relevant range of the IO bitmap.
-		 * Normally this is 128 bytes or less:
-		 */
-		memcpy(tss->io_bitmap, next->io_bitmap_ptr,
-		       max(prev->io_bitmap_max, next->io_bitmap_max));
+static inline void switch_to_bitmap(unsigned long tifp)
+{
+	/*
+	 * Invalidate I/O bitmap if the previous task used it. This prevents
+	 * any possible leakage of an active I/O bitmap.
+	 *
+	 * If the next task has an I/O bitmap it will handle it on exit to
+	 * user mode.
+	 */
+	if (tifp & _TIF_IO_BITMAP)
+		tss_invalidate_io_bitmap(this_cpu_ptr(&cpu_tss_rw));
+}
+
+static void tss_copy_io_bitmap(struct tss_struct *tss, struct io_bitmap *iobm)
+{
+	/*
+	 * Copy at least the byte range of the incoming tasks bitmap which
+	 * covers the permitted I/O ports.
+	 *
+	 * If the previous task which used an I/O bitmap had more bits
+	 * permitted, then the copy needs to cover those as well so they
+	 * get turned off.
+	 */
+	memcpy(tss->io_bitmap.bitmap, iobm->bitmap,
+	       max(tss->io_bitmap.prev_max, iobm->max));
+
+	/*
+	 * Store the new max and the sequence number of this bitmap
+	 * and a pointer to the bitmap itself.
+	 */
+	tss->io_bitmap.prev_max = iobm->max;
+	tss->io_bitmap.prev_sequence = iobm->sequence;
+}
+
+/**
+ * tss_update_io_bitmap - Update I/O bitmap before exiting to usermode
+ */
+void tss_update_io_bitmap(void)
+{
+	struct tss_struct *tss = this_cpu_ptr(&cpu_tss_rw);
+	u16 *base = &tss->x86_tss.io_bitmap_base;
+
+	if (test_thread_flag(TIF_IO_BITMAP)) {
+		struct thread_struct *t = &current->thread;
+
+		if (IS_ENABLED(CONFIG_X86_IOPL_IOPERM) && t->iopl_emul == 3) {
+			*base = IO_BITMAP_OFFSET_VALID_ALL;
+		} else {
+			struct io_bitmap *iobm = t->io_bitmap;
+			/*
+			 * Only copy bitmap data when the sequence number
+			 * differs. The update time is accounted to the
+			 * incoming task.
+			 */
+			if (tss->io_bitmap.prev_sequence != iobm->sequence)
+				tss_copy_io_bitmap(tss, iobm);
+
+			/* Enable the bitmap */
+			*base = IO_BITMAP_OFFSET_VALID_MAP;
+		}
 		/*
-		 * Make sure that the TSS limit is correct for the CPU
-		 * to notice the IO bitmap.
+		 * Make sure that the TSS limit is covering the io bitmap.
+		 * It might have been cut down by a VMEXIT to 0x67 which
+		 * would cause a subsequent I/O access from user space to
+		 * trigger a #GP because tbe bitmap is outside the TSS
+		 * limit.
 		 */
 		refresh_tss_limit();
-	} else if (tifp & _TIF_IO_BITMAP) {
-		/*
-		 * Clear any possible leftover bits:
-		 */
-		memset(tss->io_bitmap, 0xff, prev->io_bitmap_max);
+	} else {
+		tss_invalidate_io_bitmap(tss);
 	}
 }
+#else /* CONFIG_X86_IOPL_IOPERM */
+static inline void switch_to_bitmap(unsigned long tifp) { }
+#endif
 
 #ifdef CONFIG_SMP
 
@@ -505,7 +623,8 @@ void __switch_to_xtra(struct task_struct *prev_p, struct task_struct *next_p)
 
 	tifn = READ_ONCE(task_thread_info(next_p)->flags);
 	tifp = READ_ONCE(task_thread_info(prev_p)->flags);
-	switch_to_bitmap(prev, next, tifp, tifn);
+
+	switch_to_bitmap(tifp);
 
 	propagate_user_return_notify(prev_p, next_p);
 
diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c
index b8ceec4974fe..323499f48858 100644
--- a/arch/x86/kernel/process_32.c
+++ b/arch/x86/kernel/process_32.c
@@ -112,74 +112,6 @@ void release_thread(struct task_struct *dead_task)
 	release_vm86_irqs(dead_task);
 }
 
-int copy_thread_tls(unsigned long clone_flags, unsigned long sp,
-	unsigned long arg, struct task_struct *p, unsigned long tls)
-{
-	struct pt_regs *childregs = task_pt_regs(p);
-	struct fork_frame *fork_frame = container_of(childregs, struct fork_frame, regs);
-	struct inactive_task_frame *frame = &fork_frame->frame;
-	struct task_struct *tsk;
-	int err;
-
-	/*
-	 * For a new task use the RESET flags value since there is no before.
-	 * All the status flags are zero; DF and all the system flags must also
-	 * be 0, specifically IF must be 0 because we context switch to the new
-	 * task with interrupts disabled.
-	 */
-	frame->flags = X86_EFLAGS_FIXED;
-	frame->bp = 0;
-	frame->ret_addr = (unsigned long) ret_from_fork;
-	p->thread.sp = (unsigned long) fork_frame;
-	p->thread.sp0 = (unsigned long) (childregs+1);
-	memset(p->thread.ptrace_bps, 0, sizeof(p->thread.ptrace_bps));
-
-	if (unlikely(p->flags & PF_KTHREAD)) {
-		/* kernel thread */
-		memset(childregs, 0, sizeof(struct pt_regs));
-		frame->bx = sp;		/* function */
-		frame->di = arg;
-		p->thread.io_bitmap_ptr = NULL;
-		return 0;
-	}
-	frame->bx = 0;
-	*childregs = *current_pt_regs();
-	childregs->ax = 0;
-	if (sp)
-		childregs->sp = sp;
-
-	task_user_gs(p) = get_user_gs(current_pt_regs());
-
-	p->thread.io_bitmap_ptr = NULL;
-	tsk = current;
-	err = -ENOMEM;
-
-	if (unlikely(test_tsk_thread_flag(tsk, TIF_IO_BITMAP))) {
-		p->thread.io_bitmap_ptr = kmemdup(tsk->thread.io_bitmap_ptr,
-						IO_BITMAP_BYTES, GFP_KERNEL);
-		if (!p->thread.io_bitmap_ptr) {
-			p->thread.io_bitmap_max = 0;
-			return -ENOMEM;
-		}
-		set_tsk_thread_flag(p, TIF_IO_BITMAP);
-	}
-
-	err = 0;
-
-	/*
-	 * Set a new TLS for the child thread?
-	 */
-	if (clone_flags & CLONE_SETTLS)
-		err = do_set_thread_area(p, -1,
-			(struct user_desc __user *)tls, 0);
-
-	if (err && p->thread.io_bitmap_ptr) {
-		kfree(p->thread.io_bitmap_ptr);
-		p->thread.io_bitmap_max = 0;
-	}
-	return err;
-}
-
 void
 start_thread(struct pt_regs *regs, unsigned long new_ip, unsigned long new_sp)
 {
@@ -255,15 +187,6 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
 	 */
 	load_TLS(next, cpu);
 
-	/*
-	 * Restore IOPL if needed.  In normal use, the flags restore
-	 * in the switch assembly will handle this.  But if the kernel
-	 * is running virtualized at a non-zero CPL, the popf will
-	 * not restore flags, so it must be done in a separate step.
-	 */
-	if (get_kernel_rpl() && unlikely(prev->iopl != next->iopl))
-		set_iopl_mask(next->iopl);
-
 	switch_to_extra(prev_p, next_p);
 
 	/*
diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c
index af64519b2695..506d66830d4d 100644
--- a/arch/x86/kernel/process_64.c
+++ b/arch/x86/kernel/process_64.c
@@ -371,81 +371,6 @@ void x86_gsbase_write_task(struct task_struct *task, unsigned long gsbase)
 	task->thread.gsbase = gsbase;
 }
 
-int copy_thread_tls(unsigned long clone_flags, unsigned long sp,
-		unsigned long arg, struct task_struct *p, unsigned long tls)
-{
-	int err;
-	struct pt_regs *childregs;
-	struct fork_frame *fork_frame;
-	struct inactive_task_frame *frame;
-	struct task_struct *me = current;
-
-	childregs = task_pt_regs(p);
-	fork_frame = container_of(childregs, struct fork_frame, regs);
-	frame = &fork_frame->frame;
-
-	frame->bp = 0;
-	frame->ret_addr = (unsigned long) ret_from_fork;
-	p->thread.sp = (unsigned long) fork_frame;
-	p->thread.io_bitmap_ptr = NULL;
-
-	savesegment(gs, p->thread.gsindex);
-	p->thread.gsbase = p->thread.gsindex ? 0 : me->thread.gsbase;
-	savesegment(fs, p->thread.fsindex);
-	p->thread.fsbase = p->thread.fsindex ? 0 : me->thread.fsbase;
-	savesegment(es, p->thread.es);
-	savesegment(ds, p->thread.ds);
-	memset(p->thread.ptrace_bps, 0, sizeof(p->thread.ptrace_bps));
-
-	if (unlikely(p->flags & PF_KTHREAD)) {
-		/* kernel thread */
-		memset(childregs, 0, sizeof(struct pt_regs));
-		frame->bx = sp;		/* function */
-		frame->r12 = arg;
-		return 0;
-	}
-	frame->bx = 0;
-	*childregs = *current_pt_regs();
-
-	childregs->ax = 0;
-	if (sp)
-		childregs->sp = sp;
-
-	err = -ENOMEM;
-	if (unlikely(test_tsk_thread_flag(me, TIF_IO_BITMAP))) {
-		p->thread.io_bitmap_ptr = kmemdup(me->thread.io_bitmap_ptr,
-						  IO_BITMAP_BYTES, GFP_KERNEL);
-		if (!p->thread.io_bitmap_ptr) {
-			p->thread.io_bitmap_max = 0;
-			return -ENOMEM;
-		}
-		set_tsk_thread_flag(p, TIF_IO_BITMAP);
-	}
-
-	/*
-	 * Set a new TLS for the child thread?
-	 */
-	if (clone_flags & CLONE_SETTLS) {
-#ifdef CONFIG_IA32_EMULATION
-		if (in_ia32_syscall())
-			err = do_set_thread_area(p, -1,
-				(struct user_desc __user *)tls, 0);
-		else
-#endif
-			err = do_arch_prctl_64(p, ARCH_SET_FS, tls);
-		if (err)
-			goto out;
-	}
-	err = 0;
-out:
-	if (err && p->thread.io_bitmap_ptr) {
-		kfree(p->thread.io_bitmap_ptr);
-		p->thread.io_bitmap_max = 0;
-	}
-
-	return err;
-}
-
 static void
 start_thread_common(struct pt_regs *regs, unsigned long new_ip,
 		    unsigned long new_sp,
@@ -572,17 +497,6 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
 
 	switch_to_extra(prev_p, next_p);
 
-#ifdef CONFIG_XEN_PV
-	/*
-	 * On Xen PV, IOPL bits in pt_regs->flags have no effect, and
-	 * current_pt_regs()->flags may not match the current task's
-	 * intended IOPL.  We need to switch it manually.
-	 */
-	if (unlikely(static_cpu_has(X86_FEATURE_XENPV) &&
-		     prev->iopl != next->iopl))
-		xen_set_iopl_mask(next->iopl);
-#endif
-
 	if (static_cpu_has_bug(X86_BUG_SYSRET_SS_ATTRS)) {
 		/*
 		 * AMD CPUs have a misfeature: SYSRET sets the SS selector but
diff --git a/arch/x86/kernel/ptrace.c b/arch/x86/kernel/ptrace.c
index 3c5bbe8e4120..066e5b01a7e0 100644
--- a/arch/x86/kernel/ptrace.c
+++ b/arch/x86/kernel/ptrace.c
@@ -42,6 +42,7 @@
 #include <asm/traps.h>
 #include <asm/syscall.h>
 #include <asm/fsgsbase.h>
+#include <asm/io_bitmap.h>
 
 #include "tls.h"
 
@@ -697,7 +698,9 @@ static int ptrace_set_debugreg(struct task_struct *tsk, int n,
 static int ioperm_active(struct task_struct *target,
 			 const struct user_regset *regset)
 {
-	return target->thread.io_bitmap_max / regset->size;
+	struct io_bitmap *iobm = target->thread.io_bitmap;
+
+	return iobm ? DIV_ROUND_UP(iobm->max, regset->size) : 0;
 }
 
 static int ioperm_get(struct task_struct *target,
@@ -705,12 +708,13 @@ static int ioperm_get(struct task_struct *target,
 		      unsigned int pos, unsigned int count,
 		      void *kbuf, void __user *ubuf)
 {
-	if (!target->thread.io_bitmap_ptr)
+	struct io_bitmap *iobm = target->thread.io_bitmap;
+
+	if (!iobm)
 		return -ENXIO;
 
 	return user_regset_copyout(&pos, &count, &kbuf, &ubuf,
-				   target->thread.io_bitmap_ptr,
-				   0, IO_BITMAP_BYTES);
+				   iobm->bitmap, 0, IO_BITMAP_BYTES);
 }
 
 /*
diff --git a/arch/x86/kernel/relocate_kernel_32.S b/arch/x86/kernel/relocate_kernel_32.S
index ee26df08002e..94b33885f8d2 100644
--- a/arch/x86/kernel/relocate_kernel_32.S
+++ b/arch/x86/kernel/relocate_kernel_32.S
@@ -35,8 +35,7 @@
 #define CP_PA_BACKUP_PAGES_MAP	DATA(0x1c)
 
 	.text
-	.globl relocate_kernel
-relocate_kernel:
+SYM_CODE_START_NOALIGN(relocate_kernel)
 	/* Save the CPU context, used for jumping back */
 
 	pushl	%ebx
@@ -93,8 +92,9 @@ relocate_kernel:
 	addl    $(identity_mapped - relocate_kernel), %eax
 	pushl   %eax
 	ret
+SYM_CODE_END(relocate_kernel)
 
-identity_mapped:
+SYM_CODE_START_LOCAL_NOALIGN(identity_mapped)
 	/* set return address to 0 if not preserving context */
 	pushl	$0
 	/* store the start address on the stack */
@@ -191,8 +191,9 @@ identity_mapped:
 	addl	$(virtual_mapped - relocate_kernel), %eax
 	pushl	%eax
 	ret
+SYM_CODE_END(identity_mapped)
 
-virtual_mapped:
+SYM_CODE_START_LOCAL_NOALIGN(virtual_mapped)
 	movl	CR4(%edi), %eax
 	movl	%eax, %cr4
 	movl	CR3(%edi), %eax
@@ -208,9 +209,10 @@ virtual_mapped:
 	popl	%esi
 	popl	%ebx
 	ret
+SYM_CODE_END(virtual_mapped)
 
 	/* Do the copies */
-swap_pages:
+SYM_CODE_START_LOCAL_NOALIGN(swap_pages)
 	movl	8(%esp), %edx
 	movl	4(%esp), %ecx
 	pushl	%ebp
@@ -270,6 +272,7 @@ swap_pages:
 	popl	%ebx
 	popl	%ebp
 	ret
+SYM_CODE_END(swap_pages)
 
 	.globl kexec_control_code_size
 .set kexec_control_code_size, . - relocate_kernel
diff --git a/arch/x86/kernel/relocate_kernel_64.S b/arch/x86/kernel/relocate_kernel_64.S
index c51ccff5cd01..ef3ba99068d3 100644
--- a/arch/x86/kernel/relocate_kernel_64.S
+++ b/arch/x86/kernel/relocate_kernel_64.S
@@ -38,8 +38,7 @@
 	.text
 	.align PAGE_SIZE
 	.code64
-	.globl relocate_kernel
-relocate_kernel:
+SYM_CODE_START_NOALIGN(relocate_kernel)
 	/*
 	 * %rdi indirection_page
 	 * %rsi page_list
@@ -103,8 +102,9 @@ relocate_kernel:
 	addq	$(identity_mapped - relocate_kernel), %r8
 	pushq	%r8
 	ret
+SYM_CODE_END(relocate_kernel)
 
-identity_mapped:
+SYM_CODE_START_LOCAL_NOALIGN(identity_mapped)
 	/* set return address to 0 if not preserving context */
 	pushq	$0
 	/* store the start address on the stack */
@@ -209,8 +209,9 @@ identity_mapped:
 	movq	$virtual_mapped, %rax
 	pushq	%rax
 	ret
+SYM_CODE_END(identity_mapped)
 
-virtual_mapped:
+SYM_CODE_START_LOCAL_NOALIGN(virtual_mapped)
 	movq	RSP(%r8), %rsp
 	movq	CR4(%r8), %rax
 	movq	%rax, %cr4
@@ -228,9 +229,10 @@ virtual_mapped:
 	popq	%rbp
 	popq	%rbx
 	ret
+SYM_CODE_END(virtual_mapped)
 
 	/* Do the copies */
-swap_pages:
+SYM_CODE_START_LOCAL_NOALIGN(swap_pages)
 	movq	%rdi, %rcx 	/* Put the page_list in %rcx */
 	xorl	%edi, %edi
 	xorl	%esi, %esi
@@ -283,6 +285,7 @@ swap_pages:
 	jmp	0b
 3:
 	ret
+SYM_CODE_END(swap_pages)
 
 	.globl kexec_control_code_size
 .set kexec_control_code_size, . - relocate_kernel
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index 77ea96b794bd..cedfe2077a69 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -143,6 +143,13 @@ struct boot_params boot_params;
 /*
  * Machine setup..
  */
+static struct resource rodata_resource = {
+	.name	= "Kernel rodata",
+	.start	= 0,
+	.end	= 0,
+	.flags	= IORESOURCE_BUSY | IORESOURCE_SYSTEM_RAM
+};
+
 static struct resource data_resource = {
 	.name	= "Kernel data",
 	.start	= 0,
@@ -438,6 +445,12 @@ static void __init memblock_x86_reserve_range_setup_data(void)
 	while (pa_data) {
 		data = early_memremap(pa_data, sizeof(*data));
 		memblock_reserve(pa_data, sizeof(*data) + data->len);
+
+		if (data->type == SETUP_INDIRECT &&
+		    ((struct setup_indirect *)data->data)->type != SETUP_INDIRECT)
+			memblock_reserve(((struct setup_indirect *)data->data)->addr,
+					 ((struct setup_indirect *)data->data)->len);
+
 		pa_data = data->next;
 		early_memunmap(data, sizeof(*data));
 	}
@@ -459,7 +472,7 @@ static void __init memblock_x86_reserve_range_setup_data(void)
  * due to mapping restrictions.
  *
  * On 64bit, kdump kernel need be restricted to be under 64TB, which is
- * the upper limit of system RAM in 4-level paing mode. Since the kdump
+ * the upper limit of system RAM in 4-level paging mode. Since the kdump
  * jumping could be from 5-level to 4-level, the jumping will fail if
  * kernel is put above 64TB, and there's no way to detect the paging mode
  * of the kernel which will be loaded for dumping during the 1st kernel
@@ -743,8 +756,8 @@ static void __init trim_bios_range(void)
 	e820__range_update(0, PAGE_SIZE, E820_TYPE_RAM, E820_TYPE_RESERVED);
 
 	/*
-	 * special case: Some BIOSen report the PC BIOS
-	 * area (640->1Mb) as ram even though it is not.
+	 * special case: Some BIOSes report the PC BIOS
+	 * area (640Kb -> 1Mb) as RAM even though it is not.
 	 * take them out.
 	 */
 	e820__range_remove(BIOS_BEGIN, BIOS_END - BIOS_BEGIN, E820_TYPE_RAM, 1);
@@ -951,7 +964,9 @@ void __init setup_arch(char **cmdline_p)
 
 	code_resource.start = __pa_symbol(_text);
 	code_resource.end = __pa_symbol(_etext)-1;
-	data_resource.start = __pa_symbol(_etext);
+	rodata_resource.start = __pa_symbol(__start_rodata);
+	rodata_resource.end = __pa_symbol(__end_rodata)-1;
+	data_resource.start = __pa_symbol(_sdata);
 	data_resource.end = __pa_symbol(_edata)-1;
 	bss_resource.start = __pa_symbol(__bss_start);
 	bss_resource.end = __pa_symbol(__bss_stop)-1;
@@ -1040,6 +1055,7 @@ void __init setup_arch(char **cmdline_p)
 
 	/* after parse_early_param, so could debug it */
 	insert_resource(&iomem_resource, &code_resource);
+	insert_resource(&iomem_resource, &rodata_resource);
 	insert_resource(&iomem_resource, &data_resource);
 	insert_resource(&iomem_resource, &bss_resource);
 
@@ -1122,17 +1138,15 @@ void __init setup_arch(char **cmdline_p)
 
 	reserve_bios_regions();
 
-	if (efi_enabled(EFI_MEMMAP)) {
-		efi_fake_memmap();
-		efi_find_mirror();
-		efi_esrt_init();
+	efi_fake_memmap();
+	efi_find_mirror();
+	efi_esrt_init();
 
-		/*
-		 * The EFI specification says that boot service code won't be
-		 * called after ExitBootServices(). This is, in fact, a lie.
-		 */
-		efi_reserve_boot_services();
-	}
+	/*
+	 * The EFI specification says that boot service code won't be
+	 * called after ExitBootServices(). This is, in fact, a lie.
+	 */
+	efi_reserve_boot_services();
 
 	/* preallocate 4k for mptable mpc */
 	e820__memblock_alloc_reserved_mpc_new();
diff --git a/arch/x86/kernel/tce_64.c b/arch/x86/kernel/tce_64.c
deleted file mode 100644
index 6384be751eff..000000000000
--- a/arch/x86/kernel/tce_64.c
+++ /dev/null
@@ -1,177 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-or-later
-/*
- * This file manages the translation entries for the IBM Calgary IOMMU.
- *
- * Derived from arch/powerpc/platforms/pseries/iommu.c
- *
- * Copyright (C) IBM Corporation, 2006
- *
- * Author: Jon Mason <jdmason@us.ibm.com>
- * Author: Muli Ben-Yehuda <muli@il.ibm.com>
- */
-
-#include <linux/types.h>
-#include <linux/slab.h>
-#include <linux/mm.h>
-#include <linux/spinlock.h>
-#include <linux/string.h>
-#include <linux/pci.h>
-#include <linux/dma-mapping.h>
-#include <linux/memblock.h>
-#include <asm/tce.h>
-#include <asm/calgary.h>
-#include <asm/proto.h>
-#include <asm/cacheflush.h>
-
-/* flush a tce at 'tceaddr' to main memory */
-static inline void flush_tce(void* tceaddr)
-{
-	/* a single tce can't cross a cache line */
-	if (boot_cpu_has(X86_FEATURE_CLFLUSH))
-		clflush(tceaddr);
-	else
-		wbinvd();
-}
-
-void tce_build(struct iommu_table *tbl, unsigned long index,
-	unsigned int npages, unsigned long uaddr, int direction)
-{
-	u64* tp;
-	u64 t;
-	u64 rpn;
-
-	t = (1 << TCE_READ_SHIFT);
-	if (direction != DMA_TO_DEVICE)
-		t |= (1 << TCE_WRITE_SHIFT);
-
-	tp = ((u64*)tbl->it_base) + index;
-
-	while (npages--) {
-		rpn = (virt_to_bus((void*)uaddr)) >> PAGE_SHIFT;
-		t &= ~TCE_RPN_MASK;
-		t |= (rpn << TCE_RPN_SHIFT);
-
-		*tp = cpu_to_be64(t);
-		flush_tce(tp);
-
-		uaddr += PAGE_SIZE;
-		tp++;
-	}
-}
-
-void tce_free(struct iommu_table *tbl, long index, unsigned int npages)
-{
-	u64* tp;
-
-	tp  = ((u64*)tbl->it_base) + index;
-
-	while (npages--) {
-		*tp = cpu_to_be64(0);
-		flush_tce(tp);
-		tp++;
-	}
-}
-
-static inline unsigned int table_size_to_number_of_entries(unsigned char size)
-{
-	/*
-	 * size is the order of the table, 0-7
-	 * smallest table is 8K entries, so shift result by 13 to
-	 * multiply by 8K
-	 */
-	return (1 << size) << 13;
-}
-
-static int tce_table_setparms(struct pci_dev *dev, struct iommu_table *tbl)
-{
-	unsigned int bitmapsz;
-	unsigned long bmppages;
-	int ret;
-
-	tbl->it_busno = dev->bus->number;
-
-	/* set the tce table size - measured in entries */
-	tbl->it_size = table_size_to_number_of_entries(specified_table_size);
-
-	/*
-	 * number of bytes needed for the bitmap size in number of
-	 * entries; we need one bit per entry
-	 */
-	bitmapsz = tbl->it_size / BITS_PER_BYTE;
-	bmppages = __get_free_pages(GFP_KERNEL, get_order(bitmapsz));
-	if (!bmppages) {
-		printk(KERN_ERR "Calgary: cannot allocate bitmap\n");
-		ret = -ENOMEM;
-		goto done;
-	}
-
-	tbl->it_map = (unsigned long*)bmppages;
-
-	memset(tbl->it_map, 0, bitmapsz);
-
-	tbl->it_hint = 0;
-
-	spin_lock_init(&tbl->it_lock);
-
-	return 0;
-
-done:
-	return ret;
-}
-
-int __init build_tce_table(struct pci_dev *dev, void __iomem *bbar)
-{
-	struct iommu_table *tbl;
-	int ret;
-
-	if (pci_iommu(dev->bus)) {
-		printk(KERN_ERR "Calgary: dev %p has sysdata->iommu %p\n",
-		       dev, pci_iommu(dev->bus));
-		BUG();
-	}
-
-	tbl = kzalloc(sizeof(struct iommu_table), GFP_KERNEL);
-	if (!tbl) {
-		printk(KERN_ERR "Calgary: error allocating iommu_table\n");
-		ret = -ENOMEM;
-		goto done;
-	}
-
-	ret = tce_table_setparms(dev, tbl);
-	if (ret)
-		goto free_tbl;
-
-	tbl->bbar = bbar;
-
-	set_pci_iommu(dev->bus, tbl);
-
-	return 0;
-
-free_tbl:
-	kfree(tbl);
-done:
-	return ret;
-}
-
-void * __init alloc_tce_table(void)
-{
-	unsigned int size;
-
-	size = table_size_to_number_of_entries(specified_table_size);
-	size *= TCE_ENTRY_SIZE;
-
-	return memblock_alloc_low(size, size);
-}
-
-void __init free_tce_table(void *tbl)
-{
-	unsigned int size;
-
-	if (!tbl)
-		return;
-
-	size = table_size_to_number_of_entries(specified_table_size);
-	size *= TCE_ENTRY_SIZE;
-
-	memblock_free(__pa(tbl), size);
-}
diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index 4bb0f8447112..c90312146da0 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -37,11 +37,6 @@
 #include <linux/mm.h>
 #include <linux/smp.h>
 #include <linux/io.h>
-
-#if defined(CONFIG_EDAC)
-#include <linux/edac.h>
-#endif
-
 #include <asm/stacktrace.h>
 #include <asm/processor.h>
 #include <asm/debugreg.h>
diff --git a/arch/x86/kernel/umip.c b/arch/x86/kernel/umip.c
index b4a304893189..4d732a444711 100644
--- a/arch/x86/kernel/umip.c
+++ b/arch/x86/kernel/umip.c
@@ -1,6 +1,6 @@
 /*
- * umip.c Emulation for instruction protected by the Intel User-Mode
- * Instruction Prevention feature
+ * umip.c Emulation for instruction protected by the User-Mode Instruction
+ * Prevention feature
  *
  * Copyright (c) 2017, Intel Corporation.
  * Ricardo Neri <ricardo.neri-calderon@linux.intel.com>
@@ -18,10 +18,10 @@
 
 /** DOC: Emulation for User-Mode Instruction Prevention (UMIP)
  *
- * The feature User-Mode Instruction Prevention present in recent Intel
- * processor prevents a group of instructions (SGDT, SIDT, SLDT, SMSW and STR)
- * from being executed with CPL > 0. Otherwise, a general protection fault is
- * issued.
+ * User-Mode Instruction Prevention is a security feature present in recent
+ * x86 processors that, when enabled, prevents a group of instructions (SGDT,
+ * SIDT, SLDT, SMSW and STR) from being run in user mode by issuing a general
+ * protection fault if the instruction is executed with CPL > 0.
  *
  * Rather than relaying to the user space the general protection fault caused by
  * the UMIP-protected instructions (in the form of a SIGSEGV signal), it can be
diff --git a/arch/x86/kernel/uprobes.c b/arch/x86/kernel/uprobes.c
index 8cd745ef8c7b..15e5aad8ac2c 100644
--- a/arch/x86/kernel/uprobes.c
+++ b/arch/x86/kernel/uprobes.c
@@ -842,8 +842,8 @@ static int push_setup_xol_ops(struct arch_uprobe *auprobe, struct insn *insn)
 
 /**
  * arch_uprobe_analyze_insn - instruction analysis including validity and fixups.
+ * @auprobe: the probepoint information.
  * @mm: the probed address space.
- * @arch_uprobe: the probepoint information.
  * @addr: virtual address at which to install the probepoint
  * Return 0 on success or a -ve number on error.
  */
diff --git a/arch/x86/kernel/verify_cpu.S b/arch/x86/kernel/verify_cpu.S
index a024c4f7ba56..641f0fe1e5b4 100644
--- a/arch/x86/kernel/verify_cpu.S
+++ b/arch/x86/kernel/verify_cpu.S
@@ -31,7 +31,7 @@
 #include <asm/cpufeatures.h>
 #include <asm/msr-index.h>
 
-ENTRY(verify_cpu)
+SYM_FUNC_START_LOCAL(verify_cpu)
 	pushf				# Save caller passed flags
 	push	$0			# Kill any dangerous flags
 	popf
@@ -137,4 +137,4 @@ ENTRY(verify_cpu)
 	popf				# Restore caller passed flags
 	xorl %eax, %eax
 	ret
-ENDPROC(verify_cpu)
+SYM_FUNC_END(verify_cpu)
diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S
index e2feacf921a0..3a1a819da137 100644
--- a/arch/x86/kernel/vmlinux.lds.S
+++ b/arch/x86/kernel/vmlinux.lds.S
@@ -21,6 +21,9 @@
 #define LOAD_OFFSET __START_KERNEL_map
 #endif
 
+#define EMITS_PT_NOTE
+#define RO_EXCEPTION_TABLE_ALIGN	16
+
 #include <asm-generic/vmlinux.lds.h>
 #include <asm/asm-offsets.h>
 #include <asm/thread_info.h>
@@ -141,17 +144,12 @@ SECTIONS
 		*(.text.__x86.indirect_thunk)
 		__indirect_thunk_end = .;
 #endif
+	} :text =0xcccc
 
-		/* End of text section */
-		_etext = .;
-	} :text = 0x9090
-
-	NOTES :text :note
-
-	EXCEPTION_TABLE(16) :text = 0x9090
-
-	/* .text should occupy whole number of pages */
+	/* End of text section, which should occupy whole number of pages */
+	_etext = .;
 	. = ALIGN(PAGE_SIZE);
+
 	X86_ALIGN_RODATA_BEGIN
 	RO_DATA(PAGE_SIZE)
 	X86_ALIGN_RODATA_END
diff --git a/arch/x86/kernel/x86_init.c b/arch/x86/kernel/x86_init.c
index 18a799c8fa28..ce89430a7f80 100644
--- a/arch/x86/kernel/x86_init.c
+++ b/arch/x86/kernel/x86_init.c
@@ -31,6 +31,28 @@ static int __init iommu_init_noop(void) { return 0; }
 static void iommu_shutdown_noop(void) { }
 bool __init bool_x86_init_noop(void) { return false; }
 void x86_op_int_noop(int cpu) { }
+static __init int set_rtc_noop(const struct timespec64 *now) { return -EINVAL; }
+static __init void get_rtc_noop(struct timespec64 *now) { }
+
+static __initconst const struct of_device_id of_cmos_match[] = {
+	{ .compatible = "motorola,mc146818" },
+	{}
+};
+
+/*
+ * Allow devicetree configured systems to disable the RTC by setting the
+ * corresponding DT node's status property to disabled. Code is optimized
+ * out for CONFIG_OF=n builds.
+ */
+static __init void x86_wallclock_init(void)
+{
+	struct device_node *node = of_find_matching_node(NULL, of_cmos_match);
+
+	if (node && !of_device_is_available(node)) {
+		x86_platform.get_wallclock = get_rtc_noop;
+		x86_platform.set_wallclock = set_rtc_noop;
+	}
+}
 
 /*
  * The platform setup functions are preset with the default functions
@@ -73,7 +95,7 @@ struct x86_init_ops x86_init __initdata = {
 	.timers = {
 		.setup_percpu_clockev	= setup_boot_APIC_clock,
 		.timer_init		= hpet_time_init,
-		.wallclock_init		= x86_init_noop,
+		.wallclock_init		= x86_wallclock_init,
 	},
 
 	.iommu = {
diff --git a/arch/x86/kvm/pmu.c b/arch/x86/kvm/pmu.c
index d5e6d5b3f06f..bcc6a73d6628 100644
--- a/arch/x86/kvm/pmu.c
+++ b/arch/x86/kvm/pmu.c
@@ -508,8 +508,8 @@ int kvm_vm_ioctl_set_pmu_event_filter(struct kvm *kvm, void __user *argp)
 	*filter = tmp;
 
 	mutex_lock(&kvm->lock);
-	rcu_swap_protected(kvm->arch.pmu_event_filter, filter,
-			   mutex_is_locked(&kvm->lock));
+	filter = rcu_replace_pointer(kvm->arch.pmu_event_filter, filter,
+				     mutex_is_locked(&kvm->lock));
 	mutex_unlock(&kvm->lock);
 
 	synchronize_srcu_expedited(&kvm->srcu);
diff --git a/arch/x86/kvm/vmx/vmenter.S b/arch/x86/kvm/vmx/vmenter.S
index 751a384c2eb0..81ada2ce99e7 100644
--- a/arch/x86/kvm/vmx/vmenter.S
+++ b/arch/x86/kvm/vmx/vmenter.S
@@ -43,7 +43,7 @@
  * they VM-Fail, whereas a successful VM-Enter + VM-Exit will jump
  * to vmx_vmexit.
  */
-ENTRY(vmx_vmenter)
+SYM_FUNC_START(vmx_vmenter)
 	/* EFLAGS.ZF is set if VMCS.LAUNCHED == 0 */
 	je 2f
 
@@ -65,7 +65,7 @@ ENTRY(vmx_vmenter)
 	_ASM_EXTABLE(1b, 5b)
 	_ASM_EXTABLE(2b, 5b)
 
-ENDPROC(vmx_vmenter)
+SYM_FUNC_END(vmx_vmenter)
 
 /**
  * vmx_vmexit - Handle a VMX VM-Exit
@@ -77,7 +77,7 @@ ENDPROC(vmx_vmenter)
  * here after hardware loads the host's state, i.e. this is the destination
  * referred to by VMCS.HOST_RIP.
  */
-ENTRY(vmx_vmexit)
+SYM_FUNC_START(vmx_vmexit)
 #ifdef CONFIG_RETPOLINE
 	ALTERNATIVE "jmp .Lvmexit_skip_rsb", "", X86_FEATURE_RETPOLINE
 	/* Preserve guest's RAX, it's used to stuff the RSB. */
@@ -90,7 +90,7 @@ ENTRY(vmx_vmexit)
 .Lvmexit_skip_rsb:
 #endif
 	ret
-ENDPROC(vmx_vmexit)
+SYM_FUNC_END(vmx_vmexit)
 
 /**
  * __vmx_vcpu_run - Run a vCPU via a transition to VMX guest mode
@@ -101,7 +101,7 @@ ENDPROC(vmx_vmexit)
  * Returns:
  *	0 on VM-Exit, 1 on VM-Fail
  */
-ENTRY(__vmx_vcpu_run)
+SYM_FUNC_START(__vmx_vcpu_run)
 	push %_ASM_BP
 	mov  %_ASM_SP, %_ASM_BP
 #ifdef CONFIG_X86_64
@@ -233,4 +233,4 @@ ENTRY(__vmx_vcpu_run)
 	/* VM-Fail.  Out-of-line to avoid a taken Jcc after VM-Exit. */
 2:	mov $1, %eax
 	jmp 1b
-ENDPROC(__vmx_vcpu_run)
+SYM_FUNC_END(__vmx_vcpu_run)
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index d175429c91b0..1b9ab4166397 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -1368,14 +1368,6 @@ void vmx_vcpu_load_vmcs(struct kvm_vcpu *vcpu, int cpu)
 			    (unsigned long)&get_cpu_entry_area(cpu)->tss.x86_tss);
 		vmcs_writel(HOST_GDTR_BASE, (unsigned long)gdt);   /* 22.2.4 */
 
-		/*
-		 * VM exits change the host TR limit to 0x67 after a VM
-		 * exit.  This is okay, since 0x67 covers everything except
-		 * the IO bitmap and have have code to handle the IO bitmap
-		 * being lost after a VM exit.
-		 */
-		BUILD_BUG_ON(IO_BITMAP_OFFSET - 1 != 0x67);
-
 		rdmsrl(MSR_IA32_SYSENTER_ESP, sysenter_esp);
 		vmcs_writel(HOST_IA32_SYSENTER_ESP, sysenter_esp); /* 22.2.3 */
 
diff --git a/arch/x86/lib/atomic64_386_32.S b/arch/x86/lib/atomic64_386_32.S
index e0788bade5ab..3b6544111ac9 100644
--- a/arch/x86/lib/atomic64_386_32.S
+++ b/arch/x86/lib/atomic64_386_32.S
@@ -20,10 +20,10 @@
 
 #define BEGIN(op) \
 .macro endp; \
-ENDPROC(atomic64_##op##_386); \
+SYM_FUNC_END(atomic64_##op##_386); \
 .purgem endp; \
 .endm; \
-ENTRY(atomic64_##op##_386); \
+SYM_FUNC_START(atomic64_##op##_386); \
 	LOCK v;
 
 #define ENDP endp
diff --git a/arch/x86/lib/atomic64_cx8_32.S b/arch/x86/lib/atomic64_cx8_32.S
index 843d978ee341..1c5c81c16b06 100644
--- a/arch/x86/lib/atomic64_cx8_32.S
+++ b/arch/x86/lib/atomic64_cx8_32.S
@@ -16,12 +16,12 @@
 	cmpxchg8b (\reg)
 .endm
 
-ENTRY(atomic64_read_cx8)
+SYM_FUNC_START(atomic64_read_cx8)
 	read64 %ecx
 	ret
-ENDPROC(atomic64_read_cx8)
+SYM_FUNC_END(atomic64_read_cx8)
 
-ENTRY(atomic64_set_cx8)
+SYM_FUNC_START(atomic64_set_cx8)
 1:
 /* we don't need LOCK_PREFIX since aligned 64-bit writes
  * are atomic on 586 and newer */
@@ -29,19 +29,19 @@ ENTRY(atomic64_set_cx8)
 	jne 1b
 
 	ret
-ENDPROC(atomic64_set_cx8)
+SYM_FUNC_END(atomic64_set_cx8)
 
-ENTRY(atomic64_xchg_cx8)
+SYM_FUNC_START(atomic64_xchg_cx8)
 1:
 	LOCK_PREFIX
 	cmpxchg8b (%esi)
 	jne 1b
 
 	ret
-ENDPROC(atomic64_xchg_cx8)
+SYM_FUNC_END(atomic64_xchg_cx8)
 
 .macro addsub_return func ins insc
-ENTRY(atomic64_\func\()_return_cx8)
+SYM_FUNC_START(atomic64_\func\()_return_cx8)
 	pushl %ebp
 	pushl %ebx
 	pushl %esi
@@ -69,14 +69,14 @@ ENTRY(atomic64_\func\()_return_cx8)
 	popl %ebx
 	popl %ebp
 	ret
-ENDPROC(atomic64_\func\()_return_cx8)
+SYM_FUNC_END(atomic64_\func\()_return_cx8)
 .endm
 
 addsub_return add add adc
 addsub_return sub sub sbb
 
 .macro incdec_return func ins insc
-ENTRY(atomic64_\func\()_return_cx8)
+SYM_FUNC_START(atomic64_\func\()_return_cx8)
 	pushl %ebx
 
 	read64 %esi
@@ -94,13 +94,13 @@ ENTRY(atomic64_\func\()_return_cx8)
 	movl %ecx, %edx
 	popl %ebx
 	ret
-ENDPROC(atomic64_\func\()_return_cx8)
+SYM_FUNC_END(atomic64_\func\()_return_cx8)
 .endm
 
 incdec_return inc add adc
 incdec_return dec sub sbb
 
-ENTRY(atomic64_dec_if_positive_cx8)
+SYM_FUNC_START(atomic64_dec_if_positive_cx8)
 	pushl %ebx
 
 	read64 %esi
@@ -119,9 +119,9 @@ ENTRY(atomic64_dec_if_positive_cx8)
 	movl %ecx, %edx
 	popl %ebx
 	ret
-ENDPROC(atomic64_dec_if_positive_cx8)
+SYM_FUNC_END(atomic64_dec_if_positive_cx8)
 
-ENTRY(atomic64_add_unless_cx8)
+SYM_FUNC_START(atomic64_add_unless_cx8)
 	pushl %ebp
 	pushl %ebx
 /* these just push these two parameters on the stack */
@@ -155,9 +155,9 @@ ENTRY(atomic64_add_unless_cx8)
 	jne 2b
 	xorl %eax, %eax
 	jmp 3b
-ENDPROC(atomic64_add_unless_cx8)
+SYM_FUNC_END(atomic64_add_unless_cx8)
 
-ENTRY(atomic64_inc_not_zero_cx8)
+SYM_FUNC_START(atomic64_inc_not_zero_cx8)
 	pushl %ebx
 
 	read64 %esi
@@ -177,4 +177,4 @@ ENTRY(atomic64_inc_not_zero_cx8)
 3:
 	popl %ebx
 	ret
-ENDPROC(atomic64_inc_not_zero_cx8)
+SYM_FUNC_END(atomic64_inc_not_zero_cx8)
diff --git a/arch/x86/lib/checksum_32.S b/arch/x86/lib/checksum_32.S
index 4df90c9ea383..4742e8fa7ee7 100644
--- a/arch/x86/lib/checksum_32.S
+++ b/arch/x86/lib/checksum_32.S
@@ -46,7 +46,7 @@ unsigned int csum_partial(const unsigned char * buff, int len, unsigned int sum)
 	   * Fortunately, it is easy to convert 2-byte alignment to 4-byte
 	   * alignment for the unrolled loop.
 	   */		
-ENTRY(csum_partial)
+SYM_FUNC_START(csum_partial)
 	pushl %esi
 	pushl %ebx
 	movl 20(%esp),%eax	# Function arg: unsigned int sum
@@ -128,13 +128,13 @@ ENTRY(csum_partial)
 	popl %ebx
 	popl %esi
 	ret
-ENDPROC(csum_partial)
+SYM_FUNC_END(csum_partial)
 
 #else
 
 /* Version for PentiumII/PPro */
 
-ENTRY(csum_partial)
+SYM_FUNC_START(csum_partial)
 	pushl %esi
 	pushl %ebx
 	movl 20(%esp),%eax	# Function arg: unsigned int sum
@@ -246,7 +246,7 @@ ENTRY(csum_partial)
 	popl %ebx
 	popl %esi
 	ret
-ENDPROC(csum_partial)
+SYM_FUNC_END(csum_partial)
 				
 #endif
 EXPORT_SYMBOL(csum_partial)
@@ -280,7 +280,7 @@ unsigned int csum_partial_copy_generic (const char *src, char *dst,
 #define ARGBASE 16		
 #define FP		12
 		
-ENTRY(csum_partial_copy_generic)
+SYM_FUNC_START(csum_partial_copy_generic)
 	subl  $4,%esp	
 	pushl %edi
 	pushl %esi
@@ -398,7 +398,7 @@ DST(	movb %cl, (%edi)	)
 	popl %edi
 	popl %ecx			# equivalent to addl $4,%esp
 	ret	
-ENDPROC(csum_partial_copy_generic)
+SYM_FUNC_END(csum_partial_copy_generic)
 
 #else
 
@@ -416,7 +416,7 @@ ENDPROC(csum_partial_copy_generic)
 
 #define ARGBASE 12
 		
-ENTRY(csum_partial_copy_generic)
+SYM_FUNC_START(csum_partial_copy_generic)
 	pushl %ebx
 	pushl %edi
 	pushl %esi
@@ -483,7 +483,7 @@ DST(	movb %dl, (%edi)         )
 	popl %edi
 	popl %ebx
 	ret
-ENDPROC(csum_partial_copy_generic)
+SYM_FUNC_END(csum_partial_copy_generic)
 				
 #undef ROUND
 #undef ROUND1		
diff --git a/arch/x86/lib/clear_page_64.S b/arch/x86/lib/clear_page_64.S
index 75a5a4515fa7..c4c7dd115953 100644
--- a/arch/x86/lib/clear_page_64.S
+++ b/arch/x86/lib/clear_page_64.S
@@ -13,15 +13,15 @@
  * Zero a page.
  * %rdi	- page
  */
-ENTRY(clear_page_rep)
+SYM_FUNC_START(clear_page_rep)
 	movl $4096/8,%ecx
 	xorl %eax,%eax
 	rep stosq
 	ret
-ENDPROC(clear_page_rep)
+SYM_FUNC_END(clear_page_rep)
 EXPORT_SYMBOL_GPL(clear_page_rep)
 
-ENTRY(clear_page_orig)
+SYM_FUNC_START(clear_page_orig)
 	xorl   %eax,%eax
 	movl   $4096/64,%ecx
 	.p2align 4
@@ -40,13 +40,13 @@ ENTRY(clear_page_orig)
 	jnz	.Lloop
 	nop
 	ret
-ENDPROC(clear_page_orig)
+SYM_FUNC_END(clear_page_orig)
 EXPORT_SYMBOL_GPL(clear_page_orig)
 
-ENTRY(clear_page_erms)
+SYM_FUNC_START(clear_page_erms)
 	movl $4096,%ecx
 	xorl %eax,%eax
 	rep stosb
 	ret
-ENDPROC(clear_page_erms)
+SYM_FUNC_END(clear_page_erms)
 EXPORT_SYMBOL_GPL(clear_page_erms)
diff --git a/arch/x86/lib/cmpxchg16b_emu.S b/arch/x86/lib/cmpxchg16b_emu.S
index d63185698a23..3542502faa3b 100644
--- a/arch/x86/lib/cmpxchg16b_emu.S
+++ b/arch/x86/lib/cmpxchg16b_emu.S
@@ -13,7 +13,7 @@
  * %rcx : high 64 bits of new value
  * %al  : Operation successful
  */
-ENTRY(this_cpu_cmpxchg16b_emu)
+SYM_FUNC_START(this_cpu_cmpxchg16b_emu)
 
 #
 # Emulate 'cmpxchg16b %gs:(%rsi)' except we return the result in %al not
@@ -44,4 +44,4 @@ ENTRY(this_cpu_cmpxchg16b_emu)
 	xor %al,%al
 	ret
 
-ENDPROC(this_cpu_cmpxchg16b_emu)
+SYM_FUNC_END(this_cpu_cmpxchg16b_emu)
diff --git a/arch/x86/lib/cmpxchg8b_emu.S b/arch/x86/lib/cmpxchg8b_emu.S
index 691d80e97488..ca01ed6029f4 100644
--- a/arch/x86/lib/cmpxchg8b_emu.S
+++ b/arch/x86/lib/cmpxchg8b_emu.S
@@ -13,7 +13,7 @@
  * %ebx : low 32 bits of new value
  * %ecx : high 32 bits of new value
  */
-ENTRY(cmpxchg8b_emu)
+SYM_FUNC_START(cmpxchg8b_emu)
 
 #
 # Emulate 'cmpxchg8b (%esi)' on UP except we don't
@@ -42,5 +42,5 @@ ENTRY(cmpxchg8b_emu)
 	popfl
 	ret
 
-ENDPROC(cmpxchg8b_emu)
+SYM_FUNC_END(cmpxchg8b_emu)
 EXPORT_SYMBOL(cmpxchg8b_emu)
diff --git a/arch/x86/lib/copy_page_64.S b/arch/x86/lib/copy_page_64.S
index fd2d09afa097..2402d4c489d2 100644
--- a/arch/x86/lib/copy_page_64.S
+++ b/arch/x86/lib/copy_page_64.S
@@ -13,15 +13,15 @@
  * prefetch distance based on SMP/UP.
  */
 	ALIGN
-ENTRY(copy_page)
+SYM_FUNC_START(copy_page)
 	ALTERNATIVE "jmp copy_page_regs", "", X86_FEATURE_REP_GOOD
 	movl	$4096/8, %ecx
 	rep	movsq
 	ret
-ENDPROC(copy_page)
+SYM_FUNC_END(copy_page)
 EXPORT_SYMBOL(copy_page)
 
-ENTRY(copy_page_regs)
+SYM_FUNC_START_LOCAL(copy_page_regs)
 	subq	$2*8,	%rsp
 	movq	%rbx,	(%rsp)
 	movq	%r12,	1*8(%rsp)
@@ -86,4 +86,4 @@ ENTRY(copy_page_regs)
 	movq	1*8(%rsp), %r12
 	addq	$2*8, %rsp
 	ret
-ENDPROC(copy_page_regs)
+SYM_FUNC_END(copy_page_regs)
diff --git a/arch/x86/lib/copy_user_64.S b/arch/x86/lib/copy_user_64.S
index 86976b55ae74..816f128a6d52 100644
--- a/arch/x86/lib/copy_user_64.S
+++ b/arch/x86/lib/copy_user_64.S
@@ -53,7 +53,7 @@
  * Output:
  * eax uncopied bytes or 0 if successful.
  */
-ENTRY(copy_user_generic_unrolled)
+SYM_FUNC_START(copy_user_generic_unrolled)
 	ASM_STAC
 	cmpl $8,%edx
 	jb 20f		/* less then 8 bytes, go to byte copy loop */
@@ -136,7 +136,7 @@ ENTRY(copy_user_generic_unrolled)
 	_ASM_EXTABLE_UA(19b, 40b)
 	_ASM_EXTABLE_UA(21b, 50b)
 	_ASM_EXTABLE_UA(22b, 50b)
-ENDPROC(copy_user_generic_unrolled)
+SYM_FUNC_END(copy_user_generic_unrolled)
 EXPORT_SYMBOL(copy_user_generic_unrolled)
 
 /* Some CPUs run faster using the string copy instructions.
@@ -157,7 +157,7 @@ EXPORT_SYMBOL(copy_user_generic_unrolled)
  * Output:
  * eax uncopied bytes or 0 if successful.
  */
-ENTRY(copy_user_generic_string)
+SYM_FUNC_START(copy_user_generic_string)
 	ASM_STAC
 	cmpl $8,%edx
 	jb 2f		/* less than 8 bytes, go to byte copy loop */
@@ -182,7 +182,7 @@ ENTRY(copy_user_generic_string)
 
 	_ASM_EXTABLE_UA(1b, 11b)
 	_ASM_EXTABLE_UA(3b, 12b)
-ENDPROC(copy_user_generic_string)
+SYM_FUNC_END(copy_user_generic_string)
 EXPORT_SYMBOL(copy_user_generic_string)
 
 /*
@@ -197,7 +197,7 @@ EXPORT_SYMBOL(copy_user_generic_string)
  * Output:
  * eax uncopied bytes or 0 if successful.
  */
-ENTRY(copy_user_enhanced_fast_string)
+SYM_FUNC_START(copy_user_enhanced_fast_string)
 	ASM_STAC
 	cmpl $64,%edx
 	jb .L_copy_short_string	/* less then 64 bytes, avoid the costly 'rep' */
@@ -214,7 +214,7 @@ ENTRY(copy_user_enhanced_fast_string)
 	.previous
 
 	_ASM_EXTABLE_UA(1b, 12b)
-ENDPROC(copy_user_enhanced_fast_string)
+SYM_FUNC_END(copy_user_enhanced_fast_string)
 EXPORT_SYMBOL(copy_user_enhanced_fast_string)
 
 /*
@@ -230,8 +230,7 @@ EXPORT_SYMBOL(copy_user_enhanced_fast_string)
  * Output:
  * eax uncopied bytes or 0 if successful.
  */
-ALIGN;
-.Lcopy_user_handle_tail:
+SYM_CODE_START_LOCAL(.Lcopy_user_handle_tail)
 	movl %edx,%ecx
 1:	rep movsb
 2:	mov %ecx,%eax
@@ -239,7 +238,7 @@ ALIGN;
 	ret
 
 	_ASM_EXTABLE_UA(1b, 2b)
-END(.Lcopy_user_handle_tail)
+SYM_CODE_END(.Lcopy_user_handle_tail)
 
 /*
  * copy_user_nocache - Uncached memory copy with exception handling
@@ -250,7 +249,7 @@ END(.Lcopy_user_handle_tail)
  *  - Require 8-byte alignment when size is 8 bytes or larger.
  *  - Require 4-byte alignment when size is 4 bytes.
  */
-ENTRY(__copy_user_nocache)
+SYM_FUNC_START(__copy_user_nocache)
 	ASM_STAC
 
 	/* If size is less than 8 bytes, go to 4-byte copy */
@@ -389,5 +388,5 @@ ENTRY(__copy_user_nocache)
 	_ASM_EXTABLE_UA(31b, .L_fixup_4b_copy)
 	_ASM_EXTABLE_UA(40b, .L_fixup_1b_copy)
 	_ASM_EXTABLE_UA(41b, .L_fixup_1b_copy)
-ENDPROC(__copy_user_nocache)
+SYM_FUNC_END(__copy_user_nocache)
 EXPORT_SYMBOL(__copy_user_nocache)
diff --git a/arch/x86/lib/csum-copy_64.S b/arch/x86/lib/csum-copy_64.S
index a4a379e79259..3394a8ff7fd0 100644
--- a/arch/x86/lib/csum-copy_64.S
+++ b/arch/x86/lib/csum-copy_64.S
@@ -49,7 +49,7 @@
 	.endm
 
 
-ENTRY(csum_partial_copy_generic)
+SYM_FUNC_START(csum_partial_copy_generic)
 	cmpl	$3*64, %edx
 	jle	.Lignore
 
@@ -225,4 +225,4 @@ ENTRY(csum_partial_copy_generic)
 	jz   .Lende
 	movl $-EFAULT, (%rax)
 	jmp .Lende
-ENDPROC(csum_partial_copy_generic)
+SYM_FUNC_END(csum_partial_copy_generic)
diff --git a/arch/x86/lib/getuser.S b/arch/x86/lib/getuser.S
index 9578eb88fc87..c8a85b512796 100644
--- a/arch/x86/lib/getuser.S
+++ b/arch/x86/lib/getuser.S
@@ -36,7 +36,7 @@
 #include <asm/export.h>
 
 	.text
-ENTRY(__get_user_1)
+SYM_FUNC_START(__get_user_1)
 	mov PER_CPU_VAR(current_task), %_ASM_DX
 	cmp TASK_addr_limit(%_ASM_DX),%_ASM_AX
 	jae bad_get_user
@@ -47,10 +47,10 @@ ENTRY(__get_user_1)
 	xor %eax,%eax
 	ASM_CLAC
 	ret
-ENDPROC(__get_user_1)
+SYM_FUNC_END(__get_user_1)
 EXPORT_SYMBOL(__get_user_1)
 
-ENTRY(__get_user_2)
+SYM_FUNC_START(__get_user_2)
 	add $1,%_ASM_AX
 	jc bad_get_user
 	mov PER_CPU_VAR(current_task), %_ASM_DX
@@ -63,10 +63,10 @@ ENTRY(__get_user_2)
 	xor %eax,%eax
 	ASM_CLAC
 	ret
-ENDPROC(__get_user_2)
+SYM_FUNC_END(__get_user_2)
 EXPORT_SYMBOL(__get_user_2)
 
-ENTRY(__get_user_4)
+SYM_FUNC_START(__get_user_4)
 	add $3,%_ASM_AX
 	jc bad_get_user
 	mov PER_CPU_VAR(current_task), %_ASM_DX
@@ -79,10 +79,10 @@ ENTRY(__get_user_4)
 	xor %eax,%eax
 	ASM_CLAC
 	ret
-ENDPROC(__get_user_4)
+SYM_FUNC_END(__get_user_4)
 EXPORT_SYMBOL(__get_user_4)
 
-ENTRY(__get_user_8)
+SYM_FUNC_START(__get_user_8)
 #ifdef CONFIG_X86_64
 	add $7,%_ASM_AX
 	jc bad_get_user
@@ -111,25 +111,27 @@ ENTRY(__get_user_8)
 	ASM_CLAC
 	ret
 #endif
-ENDPROC(__get_user_8)
+SYM_FUNC_END(__get_user_8)
 EXPORT_SYMBOL(__get_user_8)
 
 
-.Lbad_get_user_clac:
+SYM_CODE_START_LOCAL(.Lbad_get_user_clac)
 	ASM_CLAC
 bad_get_user:
 	xor %edx,%edx
 	mov $(-EFAULT),%_ASM_AX
 	ret
+SYM_CODE_END(.Lbad_get_user_clac)
 
 #ifdef CONFIG_X86_32
-.Lbad_get_user_8_clac:
+SYM_CODE_START_LOCAL(.Lbad_get_user_8_clac)
 	ASM_CLAC
 bad_get_user_8:
 	xor %edx,%edx
 	xor %ecx,%ecx
 	mov $(-EFAULT),%_ASM_AX
 	ret
+SYM_CODE_END(.Lbad_get_user_8_clac)
 #endif
 
 	_ASM_EXTABLE_UA(1b, .Lbad_get_user_clac)
diff --git a/arch/x86/lib/hweight.S b/arch/x86/lib/hweight.S
index a14f9939c365..dbf8cc97b7f5 100644
--- a/arch/x86/lib/hweight.S
+++ b/arch/x86/lib/hweight.S
@@ -8,7 +8,7 @@
  * unsigned int __sw_hweight32(unsigned int w)
  * %rdi: w
  */
-ENTRY(__sw_hweight32)
+SYM_FUNC_START(__sw_hweight32)
 
 #ifdef CONFIG_X86_64
 	movl %edi, %eax				# w
@@ -33,10 +33,10 @@ ENTRY(__sw_hweight32)
 	shrl $24, %eax				# w = w_tmp >> 24
 	__ASM_SIZE(pop,) %__ASM_REG(dx)
 	ret
-ENDPROC(__sw_hweight32)
+SYM_FUNC_END(__sw_hweight32)
 EXPORT_SYMBOL(__sw_hweight32)
 
-ENTRY(__sw_hweight64)
+SYM_FUNC_START(__sw_hweight64)
 #ifdef CONFIG_X86_64
 	pushq   %rdi
 	pushq   %rdx
@@ -79,5 +79,5 @@ ENTRY(__sw_hweight64)
 	popl    %ecx
 	ret
 #endif
-ENDPROC(__sw_hweight64)
+SYM_FUNC_END(__sw_hweight64)
 EXPORT_SYMBOL(__sw_hweight64)
diff --git a/arch/x86/lib/iomap_copy_64.S b/arch/x86/lib/iomap_copy_64.S
index a9bdf0805be0..cb5a1964506b 100644
--- a/arch/x86/lib/iomap_copy_64.S
+++ b/arch/x86/lib/iomap_copy_64.S
@@ -8,8 +8,8 @@
 /*
  * override generic version in lib/iomap_copy.c
  */
-ENTRY(__iowrite32_copy)
+SYM_FUNC_START(__iowrite32_copy)
 	movl %edx,%ecx
 	rep movsd
 	ret
-ENDPROC(__iowrite32_copy)
+SYM_FUNC_END(__iowrite32_copy)
diff --git a/arch/x86/lib/memcpy_64.S b/arch/x86/lib/memcpy_64.S
index 92748660ba51..56b243b14c3a 100644
--- a/arch/x86/lib/memcpy_64.S
+++ b/arch/x86/lib/memcpy_64.S
@@ -28,8 +28,8 @@
  * Output:
  * rax original destination
  */
-ENTRY(__memcpy)
-ENTRY(memcpy)
+SYM_FUNC_START_ALIAS(__memcpy)
+SYM_FUNC_START_LOCAL(memcpy)
 	ALTERNATIVE_2 "jmp memcpy_orig", "", X86_FEATURE_REP_GOOD, \
 		      "jmp memcpy_erms", X86_FEATURE_ERMS
 
@@ -41,8 +41,8 @@ ENTRY(memcpy)
 	movl %edx, %ecx
 	rep movsb
 	ret
-ENDPROC(memcpy)
-ENDPROC(__memcpy)
+SYM_FUNC_END(memcpy)
+SYM_FUNC_END_ALIAS(__memcpy)
 EXPORT_SYMBOL(memcpy)
 EXPORT_SYMBOL(__memcpy)
 
@@ -50,14 +50,14 @@ EXPORT_SYMBOL(__memcpy)
  * memcpy_erms() - enhanced fast string memcpy. This is faster and
  * simpler than memcpy. Use memcpy_erms when possible.
  */
-ENTRY(memcpy_erms)
+SYM_FUNC_START_LOCAL(memcpy_erms)
 	movq %rdi, %rax
 	movq %rdx, %rcx
 	rep movsb
 	ret
-ENDPROC(memcpy_erms)
+SYM_FUNC_END(memcpy_erms)
 
-ENTRY(memcpy_orig)
+SYM_FUNC_START_LOCAL(memcpy_orig)
 	movq %rdi, %rax
 
 	cmpq $0x20, %rdx
@@ -182,7 +182,7 @@ ENTRY(memcpy_orig)
 
 .Lend:
 	retq
-ENDPROC(memcpy_orig)
+SYM_FUNC_END(memcpy_orig)
 
 #ifndef CONFIG_UML
 
@@ -193,7 +193,7 @@ MCSAFE_TEST_CTL
  * Note that we only catch machine checks when reading the source addresses.
  * Writes to target are posted and don't generate machine checks.
  */
-ENTRY(__memcpy_mcsafe)
+SYM_FUNC_START(__memcpy_mcsafe)
 	cmpl $8, %edx
 	/* Less than 8 bytes? Go to byte copy loop */
 	jb .L_no_whole_words
@@ -260,7 +260,7 @@ ENTRY(__memcpy_mcsafe)
 	xorl %eax, %eax
 .L_done:
 	ret
-ENDPROC(__memcpy_mcsafe)
+SYM_FUNC_END(__memcpy_mcsafe)
 EXPORT_SYMBOL_GPL(__memcpy_mcsafe)
 
 	.section .fixup, "ax"
diff --git a/arch/x86/lib/memmove_64.S b/arch/x86/lib/memmove_64.S
index bbec69d8223b..337830d7a59c 100644
--- a/arch/x86/lib/memmove_64.S
+++ b/arch/x86/lib/memmove_64.S
@@ -26,8 +26,8 @@
  */
 .weak memmove
 
-ENTRY(memmove)
-ENTRY(__memmove)
+SYM_FUNC_START_ALIAS(memmove)
+SYM_FUNC_START(__memmove)
 
 	/* Handle more 32 bytes in loop */
 	mov %rdi, %rax
@@ -207,7 +207,7 @@ ENTRY(__memmove)
 	movb %r11b, (%rdi)
 13:
 	retq
-ENDPROC(__memmove)
-ENDPROC(memmove)
+SYM_FUNC_END(__memmove)
+SYM_FUNC_END_ALIAS(memmove)
 EXPORT_SYMBOL(__memmove)
 EXPORT_SYMBOL(memmove)
diff --git a/arch/x86/lib/memset_64.S b/arch/x86/lib/memset_64.S
index 9bc861c71e75..9ff15ee404a4 100644
--- a/arch/x86/lib/memset_64.S
+++ b/arch/x86/lib/memset_64.S
@@ -19,8 +19,8 @@
  *
  * rax   original destination
  */
-ENTRY(memset)
-ENTRY(__memset)
+SYM_FUNC_START_ALIAS(memset)
+SYM_FUNC_START(__memset)
 	/*
 	 * Some CPUs support enhanced REP MOVSB/STOSB feature. It is recommended
 	 * to use it when possible. If not available, use fast string instructions.
@@ -43,8 +43,8 @@ ENTRY(__memset)
 	rep stosb
 	movq %r9,%rax
 	ret
-ENDPROC(memset)
-ENDPROC(__memset)
+SYM_FUNC_END(__memset)
+SYM_FUNC_END_ALIAS(memset)
 EXPORT_SYMBOL(memset)
 EXPORT_SYMBOL(__memset)
 
@@ -59,16 +59,16 @@ EXPORT_SYMBOL(__memset)
  *
  * rax   original destination
  */
-ENTRY(memset_erms)
+SYM_FUNC_START_LOCAL(memset_erms)
 	movq %rdi,%r9
 	movb %sil,%al
 	movq %rdx,%rcx
 	rep stosb
 	movq %r9,%rax
 	ret
-ENDPROC(memset_erms)
+SYM_FUNC_END(memset_erms)
 
-ENTRY(memset_orig)
+SYM_FUNC_START_LOCAL(memset_orig)
 	movq %rdi,%r10
 
 	/* expand byte value  */
@@ -139,4 +139,4 @@ ENTRY(memset_orig)
 	subq %r8,%rdx
 	jmp .Lafter_bad_alignment
 .Lfinal:
-ENDPROC(memset_orig)
+SYM_FUNC_END(memset_orig)
diff --git a/arch/x86/lib/msr-reg.S b/arch/x86/lib/msr-reg.S
index ed33cbab3958..a2b9caa5274c 100644
--- a/arch/x86/lib/msr-reg.S
+++ b/arch/x86/lib/msr-reg.S
@@ -12,7 +12,7 @@
  *
  */
 .macro op_safe_regs op
-ENTRY(\op\()_safe_regs)
+SYM_FUNC_START(\op\()_safe_regs)
 	pushq %rbx
 	pushq %r12
 	movq	%rdi, %r10	/* Save pointer */
@@ -41,13 +41,13 @@ ENTRY(\op\()_safe_regs)
 	jmp     2b
 
 	_ASM_EXTABLE(1b, 3b)
-ENDPROC(\op\()_safe_regs)
+SYM_FUNC_END(\op\()_safe_regs)
 .endm
 
 #else /* X86_32 */
 
 .macro op_safe_regs op
-ENTRY(\op\()_safe_regs)
+SYM_FUNC_START(\op\()_safe_regs)
 	pushl %ebx
 	pushl %ebp
 	pushl %esi
@@ -83,7 +83,7 @@ ENTRY(\op\()_safe_regs)
 	jmp     2b
 
 	_ASM_EXTABLE(1b, 3b)
-ENDPROC(\op\()_safe_regs)
+SYM_FUNC_END(\op\()_safe_regs)
 .endm
 
 #endif
diff --git a/arch/x86/lib/putuser.S b/arch/x86/lib/putuser.S
index 126dd6a9ec9b..7c7c92db8497 100644
--- a/arch/x86/lib/putuser.S
+++ b/arch/x86/lib/putuser.S
@@ -34,7 +34,7 @@
 #define ENTER	mov PER_CPU_VAR(current_task), %_ASM_BX
 
 .text
-ENTRY(__put_user_1)
+SYM_FUNC_START(__put_user_1)
 	ENTER
 	cmp TASK_addr_limit(%_ASM_BX),%_ASM_CX
 	jae .Lbad_put_user
@@ -43,10 +43,10 @@ ENTRY(__put_user_1)
 	xor %eax,%eax
 	ASM_CLAC
 	ret
-ENDPROC(__put_user_1)
+SYM_FUNC_END(__put_user_1)
 EXPORT_SYMBOL(__put_user_1)
 
-ENTRY(__put_user_2)
+SYM_FUNC_START(__put_user_2)
 	ENTER
 	mov TASK_addr_limit(%_ASM_BX),%_ASM_BX
 	sub $1,%_ASM_BX
@@ -57,10 +57,10 @@ ENTRY(__put_user_2)
 	xor %eax,%eax
 	ASM_CLAC
 	ret
-ENDPROC(__put_user_2)
+SYM_FUNC_END(__put_user_2)
 EXPORT_SYMBOL(__put_user_2)
 
-ENTRY(__put_user_4)
+SYM_FUNC_START(__put_user_4)
 	ENTER
 	mov TASK_addr_limit(%_ASM_BX),%_ASM_BX
 	sub $3,%_ASM_BX
@@ -71,10 +71,10 @@ ENTRY(__put_user_4)
 	xor %eax,%eax
 	ASM_CLAC
 	ret
-ENDPROC(__put_user_4)
+SYM_FUNC_END(__put_user_4)
 EXPORT_SYMBOL(__put_user_4)
 
-ENTRY(__put_user_8)
+SYM_FUNC_START(__put_user_8)
 	ENTER
 	mov TASK_addr_limit(%_ASM_BX),%_ASM_BX
 	sub $7,%_ASM_BX
@@ -88,14 +88,15 @@ ENTRY(__put_user_8)
 	xor %eax,%eax
 	ASM_CLAC
 	RET
-ENDPROC(__put_user_8)
+SYM_FUNC_END(__put_user_8)
 EXPORT_SYMBOL(__put_user_8)
 
-.Lbad_put_user_clac:
+SYM_CODE_START_LOCAL(.Lbad_put_user_clac)
 	ASM_CLAC
 .Lbad_put_user:
 	movl $-EFAULT,%eax
 	RET
+SYM_CODE_END(.Lbad_put_user_clac)
 
 	_ASM_EXTABLE_UA(1b, .Lbad_put_user_clac)
 	_ASM_EXTABLE_UA(2b, .Lbad_put_user_clac)
diff --git a/arch/x86/lib/retpoline.S b/arch/x86/lib/retpoline.S
index c909961e678a..363ec132df7e 100644
--- a/arch/x86/lib/retpoline.S
+++ b/arch/x86/lib/retpoline.S
@@ -11,11 +11,11 @@
 .macro THUNK reg
 	.section .text.__x86.indirect_thunk
 
-ENTRY(__x86_indirect_thunk_\reg)
+SYM_FUNC_START(__x86_indirect_thunk_\reg)
 	CFI_STARTPROC
 	JMP_NOSPEC %\reg
 	CFI_ENDPROC
-ENDPROC(__x86_indirect_thunk_\reg)
+SYM_FUNC_END(__x86_indirect_thunk_\reg)
 .endm
 
 /*
diff --git a/arch/x86/math-emu/div_Xsig.S b/arch/x86/math-emu/div_Xsig.S
index ee08449d20fd..951da2ad54bb 100644
--- a/arch/x86/math-emu/div_Xsig.S
+++ b/arch/x86/math-emu/div_Xsig.S
@@ -75,7 +75,7 @@ FPU_result_1:
 
 
 .text
-ENTRY(div_Xsig)
+SYM_FUNC_START(div_Xsig)
 	pushl	%ebp
 	movl	%esp,%ebp
 #ifndef NON_REENTRANT_FPU
@@ -364,4 +364,4 @@ L_bugged_2:
 	pop	%ebx
 	jmp	L_exit
 #endif /* PARANOID */ 
-ENDPROC(div_Xsig)
+SYM_FUNC_END(div_Xsig)
diff --git a/arch/x86/math-emu/div_small.S b/arch/x86/math-emu/div_small.S
index 8f5025c80ee0..d047d1816abe 100644
--- a/arch/x86/math-emu/div_small.S
+++ b/arch/x86/math-emu/div_small.S
@@ -19,7 +19,7 @@
 #include "fpu_emu.h"
 
 .text
-ENTRY(FPU_div_small)
+SYM_FUNC_START(FPU_div_small)
 	pushl	%ebp
 	movl	%esp,%ebp
 
@@ -45,4 +45,4 @@ ENTRY(FPU_div_small)
 
 	leave
 	ret
-ENDPROC(FPU_div_small)
+SYM_FUNC_END(FPU_div_small)
diff --git a/arch/x86/math-emu/fpu_system.h b/arch/x86/math-emu/fpu_system.h
index f98a0c956764..9b41391867dc 100644
--- a/arch/x86/math-emu/fpu_system.h
+++ b/arch/x86/math-emu/fpu_system.h
@@ -107,6 +107,8 @@ static inline bool seg_writable(struct desc_struct *d)
 #define FPU_access_ok(y,z)	if ( !access_ok(y,z) ) \
 				math_abort(FPU_info,SIGSEGV)
 #define FPU_abort		math_abort(FPU_info, SIGSEGV)
+#define FPU_copy_from_user(to, from, n)	\
+		do { if (copy_from_user(to, from, n)) FPU_abort; } while (0)
 
 #undef FPU_IGNORE_CODE_SEGV
 #ifdef FPU_IGNORE_CODE_SEGV
@@ -122,7 +124,7 @@ static inline bool seg_writable(struct desc_struct *d)
 #define	FPU_code_access_ok(z) FPU_access_ok((void __user *)FPU_EIP,z)
 #endif
 
-#define FPU_get_user(x,y)       get_user((x),(y))
-#define FPU_put_user(x,y)       put_user((x),(y))
+#define FPU_get_user(x,y) do { if (get_user((x),(y))) FPU_abort; } while (0)
+#define FPU_put_user(x,y) do { if (put_user((x),(y))) FPU_abort; } while (0)
 
 #endif
diff --git a/arch/x86/math-emu/mul_Xsig.S b/arch/x86/math-emu/mul_Xsig.S
index 3e489122a2b0..4afc7b1fa6e9 100644
--- a/arch/x86/math-emu/mul_Xsig.S
+++ b/arch/x86/math-emu/mul_Xsig.S
@@ -25,7 +25,7 @@
 #include "fpu_emu.h"
 
 .text
-ENTRY(mul32_Xsig)
+SYM_FUNC_START(mul32_Xsig)
 	pushl %ebp
 	movl %esp,%ebp
 	subl $16,%esp
@@ -63,10 +63,10 @@ ENTRY(mul32_Xsig)
 	popl %esi
 	leave
 	ret
-ENDPROC(mul32_Xsig)
+SYM_FUNC_END(mul32_Xsig)
 
 
-ENTRY(mul64_Xsig)
+SYM_FUNC_START(mul64_Xsig)
 	pushl %ebp
 	movl %esp,%ebp
 	subl $16,%esp
@@ -116,11 +116,11 @@ ENTRY(mul64_Xsig)
 	popl %esi
 	leave
 	ret
-ENDPROC(mul64_Xsig)
+SYM_FUNC_END(mul64_Xsig)
 
 
 
-ENTRY(mul_Xsig_Xsig)
+SYM_FUNC_START(mul_Xsig_Xsig)
 	pushl %ebp
 	movl %esp,%ebp
 	subl $16,%esp
@@ -176,4 +176,4 @@ ENTRY(mul_Xsig_Xsig)
 	popl %esi
 	leave
 	ret
-ENDPROC(mul_Xsig_Xsig)
+SYM_FUNC_END(mul_Xsig_Xsig)
diff --git a/arch/x86/math-emu/polynom_Xsig.S b/arch/x86/math-emu/polynom_Xsig.S
index 604f0b2d17e8..702315eecb86 100644
--- a/arch/x86/math-emu/polynom_Xsig.S
+++ b/arch/x86/math-emu/polynom_Xsig.S
@@ -37,7 +37,7 @@
 #define OVERFLOWED      -16(%ebp)	/* addition overflow flag */
 
 .text
-ENTRY(polynomial_Xsig)
+SYM_FUNC_START(polynomial_Xsig)
 	pushl	%ebp
 	movl	%esp,%ebp
 	subl	$32,%esp
@@ -134,4 +134,4 @@ L_accum_done:
 	popl	%esi
 	leave
 	ret
-ENDPROC(polynomial_Xsig)
+SYM_FUNC_END(polynomial_Xsig)
diff --git a/arch/x86/math-emu/reg_ld_str.c b/arch/x86/math-emu/reg_ld_str.c
index f3779743d15e..fe6246ff9887 100644
--- a/arch/x86/math-emu/reg_ld_str.c
+++ b/arch/x86/math-emu/reg_ld_str.c
@@ -85,7 +85,7 @@ int FPU_load_extended(long double __user *s, int stnr)
 
 	RE_ENTRANT_CHECK_OFF;
 	FPU_access_ok(s, 10);
-	__copy_from_user(sti_ptr, s, 10);
+	FPU_copy_from_user(sti_ptr, s, 10);
 	RE_ENTRANT_CHECK_ON;
 
 	return FPU_tagof(sti_ptr);
@@ -1126,9 +1126,9 @@ void frstor(fpu_addr_modes addr_modes, u_char __user *data_address)
 	/* Copy all registers in stack order. */
 	RE_ENTRANT_CHECK_OFF;
 	FPU_access_ok(s, 80);
-	__copy_from_user(register_base + offset, s, other);
+	FPU_copy_from_user(register_base + offset, s, other);
 	if (offset)
-		__copy_from_user(register_base, s + other, offset);
+		FPU_copy_from_user(register_base, s + other, offset);
 	RE_ENTRANT_CHECK_ON;
 
 	for (i = 0; i < 8; i++) {
diff --git a/arch/x86/math-emu/reg_norm.S b/arch/x86/math-emu/reg_norm.S
index 7f6b4392a15d..cad1d60b1e84 100644
--- a/arch/x86/math-emu/reg_norm.S
+++ b/arch/x86/math-emu/reg_norm.S
@@ -22,7 +22,7 @@
 
 
 .text
-ENTRY(FPU_normalize)
+SYM_FUNC_START(FPU_normalize)
 	pushl	%ebp
 	movl	%esp,%ebp
 	pushl	%ebx
@@ -95,12 +95,12 @@ L_overflow:
 	call	arith_overflow
 	pop	%ebx
 	jmp	L_exit
-ENDPROC(FPU_normalize)
+SYM_FUNC_END(FPU_normalize)
 
 
 
 /* Normalise without reporting underflow or overflow */
-ENTRY(FPU_normalize_nuo)
+SYM_FUNC_START(FPU_normalize_nuo)
 	pushl	%ebp
 	movl	%esp,%ebp
 	pushl	%ebx
@@ -147,4 +147,4 @@ L_exit_nuo_zero:
 	popl	%ebx
 	leave
 	ret
-ENDPROC(FPU_normalize_nuo)
+SYM_FUNC_END(FPU_normalize_nuo)
diff --git a/arch/x86/math-emu/reg_round.S b/arch/x86/math-emu/reg_round.S
index 04563421ee7d..11a1f798451b 100644
--- a/arch/x86/math-emu/reg_round.S
+++ b/arch/x86/math-emu/reg_round.S
@@ -109,7 +109,7 @@ FPU_denormal:
 .globl fpu_Arith_exit
 
 /* Entry point when called from C */
-ENTRY(FPU_round)
+SYM_FUNC_START(FPU_round)
 	pushl	%ebp
 	movl	%esp,%ebp
 	pushl	%esi
@@ -708,4 +708,4 @@ L_exception_exit:
 	jmp	fpu_reg_round_special_exit
 #endif /* PARANOID */ 
 
-ENDPROC(FPU_round)
+SYM_FUNC_END(FPU_round)
diff --git a/arch/x86/math-emu/reg_u_add.S b/arch/x86/math-emu/reg_u_add.S
index 50fe9f8c893c..9c9e2c810afe 100644
--- a/arch/x86/math-emu/reg_u_add.S
+++ b/arch/x86/math-emu/reg_u_add.S
@@ -32,7 +32,7 @@
 #include "control_w.h"
 
 .text
-ENTRY(FPU_u_add)
+SYM_FUNC_START(FPU_u_add)
 	pushl	%ebp
 	movl	%esp,%ebp
 	pushl	%esi
@@ -166,4 +166,4 @@ L_exit:
 	leave
 	ret
 #endif /* PARANOID */
-ENDPROC(FPU_u_add)
+SYM_FUNC_END(FPU_u_add)
diff --git a/arch/x86/math-emu/reg_u_div.S b/arch/x86/math-emu/reg_u_div.S
index 94d545e118e4..e2fb5c2644c5 100644
--- a/arch/x86/math-emu/reg_u_div.S
+++ b/arch/x86/math-emu/reg_u_div.S
@@ -75,7 +75,7 @@ FPU_ovfl_flag:
 #define DEST	PARAM3
 
 .text
-ENTRY(FPU_u_div)
+SYM_FUNC_START(FPU_u_div)
 	pushl	%ebp
 	movl	%esp,%ebp
 #ifndef NON_REENTRANT_FPU
@@ -471,4 +471,4 @@ L_exit:
 	ret
 #endif /* PARANOID */ 
 
-ENDPROC(FPU_u_div)
+SYM_FUNC_END(FPU_u_div)
diff --git a/arch/x86/math-emu/reg_u_mul.S b/arch/x86/math-emu/reg_u_mul.S
index 21cde47fb3e5..0c779c87ac5b 100644
--- a/arch/x86/math-emu/reg_u_mul.S
+++ b/arch/x86/math-emu/reg_u_mul.S
@@ -45,7 +45,7 @@ FPU_accum_1:
 
 
 .text
-ENTRY(FPU_u_mul)
+SYM_FUNC_START(FPU_u_mul)
 	pushl	%ebp
 	movl	%esp,%ebp
 #ifndef NON_REENTRANT_FPU
@@ -147,4 +147,4 @@ L_exit:
 	ret
 #endif /* PARANOID */ 
 
-ENDPROC(FPU_u_mul)
+SYM_FUNC_END(FPU_u_mul)
diff --git a/arch/x86/math-emu/reg_u_sub.S b/arch/x86/math-emu/reg_u_sub.S
index f05dea7dec38..e9bb7c248649 100644
--- a/arch/x86/math-emu/reg_u_sub.S
+++ b/arch/x86/math-emu/reg_u_sub.S
@@ -33,7 +33,7 @@
 #include "control_w.h"
 
 .text
-ENTRY(FPU_u_sub)
+SYM_FUNC_START(FPU_u_sub)
 	pushl	%ebp
 	movl	%esp,%ebp
 	pushl	%esi
@@ -271,4 +271,4 @@ L_exit:
 	popl	%esi
 	leave
 	ret
-ENDPROC(FPU_u_sub)
+SYM_FUNC_END(FPU_u_sub)
diff --git a/arch/x86/math-emu/round_Xsig.S b/arch/x86/math-emu/round_Xsig.S
index 226a51e991f1..d9d7de8dbd7b 100644
--- a/arch/x86/math-emu/round_Xsig.S
+++ b/arch/x86/math-emu/round_Xsig.S
@@ -23,7 +23,7 @@
 
 
 .text
-ENTRY(round_Xsig)
+SYM_FUNC_START(round_Xsig)
 	pushl	%ebp
 	movl	%esp,%ebp
 	pushl	%ebx		/* Reserve some space */
@@ -79,11 +79,11 @@ L_exit:
 	popl	%ebx
 	leave
 	ret
-ENDPROC(round_Xsig)
+SYM_FUNC_END(round_Xsig)
 
 
 
-ENTRY(norm_Xsig)
+SYM_FUNC_START(norm_Xsig)
 	pushl	%ebp
 	movl	%esp,%ebp
 	pushl	%ebx		/* Reserve some space */
@@ -139,4 +139,4 @@ L_n_exit:
 	popl	%ebx
 	leave
 	ret
-ENDPROC(norm_Xsig)
+SYM_FUNC_END(norm_Xsig)
diff --git a/arch/x86/math-emu/shr_Xsig.S b/arch/x86/math-emu/shr_Xsig.S
index 96f4779aa9c1..726af985f758 100644
--- a/arch/x86/math-emu/shr_Xsig.S
+++ b/arch/x86/math-emu/shr_Xsig.S
@@ -22,7 +22,7 @@
 #include "fpu_emu.h"
 
 .text
-ENTRY(shr_Xsig)
+SYM_FUNC_START(shr_Xsig)
 	push	%ebp
 	movl	%esp,%ebp
 	pushl	%esi
@@ -86,4 +86,4 @@ L_more_than_95:
 	popl	%esi
 	leave
 	ret
-ENDPROC(shr_Xsig)
+SYM_FUNC_END(shr_Xsig)
diff --git a/arch/x86/math-emu/wm_shrx.S b/arch/x86/math-emu/wm_shrx.S
index d588874eb6fb..4fc89174caf0 100644
--- a/arch/x86/math-emu/wm_shrx.S
+++ b/arch/x86/math-emu/wm_shrx.S
@@ -33,7 +33,7 @@
  |   Results returned in the 64 bit arg and eax.                             |
  +---------------------------------------------------------------------------*/
 
-ENTRY(FPU_shrx)
+SYM_FUNC_START(FPU_shrx)
 	push	%ebp
 	movl	%esp,%ebp
 	pushl	%esi
@@ -93,7 +93,7 @@ L_more_than_95:
 	popl	%esi
 	leave
 	ret
-ENDPROC(FPU_shrx)
+SYM_FUNC_END(FPU_shrx)
 
 
 /*---------------------------------------------------------------------------+
@@ -112,7 +112,7 @@ ENDPROC(FPU_shrx)
  |   part which has been shifted out of the arg.                             |
  |   Results returned in the 64 bit arg and eax.                             |
  +---------------------------------------------------------------------------*/
-ENTRY(FPU_shrxs)
+SYM_FUNC_START(FPU_shrxs)
 	push	%ebp
 	movl	%esp,%ebp
 	pushl	%esi
@@ -204,4 +204,4 @@ Ls_more_than_95:
 	popl	%esi
 	leave
 	ret
-ENDPROC(FPU_shrxs)
+SYM_FUNC_END(FPU_shrxs)
diff --git a/arch/x86/math-emu/wm_sqrt.S b/arch/x86/math-emu/wm_sqrt.S
index f031c0e19356..3b2b58164ec1 100644
--- a/arch/x86/math-emu/wm_sqrt.S
+++ b/arch/x86/math-emu/wm_sqrt.S
@@ -75,7 +75,7 @@ FPU_fsqrt_arg_0:
 
 
 .text
-ENTRY(wm_sqrt)
+SYM_FUNC_START(wm_sqrt)
 	pushl	%ebp
 	movl	%esp,%ebp
 #ifndef NON_REENTRANT_FPU
@@ -469,4 +469,4 @@ sqrt_more_prec_large:
 /* Our estimate is too large */
 	movl	$0x7fffff00,%eax
 	jmp	sqrt_round_result
-ENDPROC(wm_sqrt)
+SYM_FUNC_END(wm_sqrt)
diff --git a/arch/x86/mm/Makefile b/arch/x86/mm/Makefile
index bbc68a54795e..3b89c201ac26 100644
--- a/arch/x86/mm/Makefile
+++ b/arch/x86/mm/Makefile
@@ -23,7 +23,7 @@ CFLAGS_mem_encrypt_identity.o	:= $(nostackp)
 
 CFLAGS_fault.o := -I $(srctree)/$(src)/../include/asm/trace
 
-obj-$(CONFIG_X86_PAT)		+= pat_rbtree.o
+obj-$(CONFIG_X86_PAT)		+= pat_interval.o
 
 obj-$(CONFIG_X86_32)		+= pgtable_32.o iomap_32.o
 
diff --git a/arch/x86/mm/cpu_entry_area.c b/arch/x86/mm/cpu_entry_area.c
index 752ad11d6868..82ead8e27888 100644
--- a/arch/x86/mm/cpu_entry_area.c
+++ b/arch/x86/mm/cpu_entry_area.c
@@ -161,6 +161,14 @@ static void __init setup_cpu_entry_area(unsigned int cpu)
 	BUILD_BUG_ON((offsetof(struct tss_struct, x86_tss) ^
 		      offsetofend(struct tss_struct, x86_tss)) & PAGE_MASK);
 	BUILD_BUG_ON(sizeof(struct tss_struct) % PAGE_SIZE != 0);
+	/*
+	 * VMX changes the host TR limit to 0x67 after a VM exit. This is
+	 * okay, since 0x67 covers the size of struct x86_hw_tss. Make sure
+	 * that this is correct.
+	 */
+	BUILD_BUG_ON(offsetof(struct tss_struct, x86_tss) != 0);
+	BUILD_BUG_ON(sizeof(struct x86_hw_tss) != 0x68);
+
 	cea_map_percpu_pages(&cea->tss, &per_cpu(cpu_tss_rw, cpu),
 			     sizeof(struct tss_struct) / PAGE_SIZE, tss_prot);
 
@@ -178,7 +186,9 @@ static __init void setup_cpu_entry_area_ptes(void)
 #ifdef CONFIG_X86_32
 	unsigned long start, end;
 
-	BUILD_BUG_ON(CPU_ENTRY_AREA_PAGES * PAGE_SIZE < CPU_ENTRY_AREA_MAP_SIZE);
+	/* The +1 is for the readonly IDT: */
+	BUILD_BUG_ON((CPU_ENTRY_AREA_PAGES+1)*PAGE_SIZE != CPU_ENTRY_AREA_MAP_SIZE);
+	BUILD_BUG_ON(CPU_ENTRY_AREA_TOTAL_SIZE != CPU_ENTRY_AREA_MAP_SIZE);
 	BUG_ON(CPU_ENTRY_AREA_BASE & ~PMD_MASK);
 
 	start = CPU_ENTRY_AREA_BASE;
diff --git a/arch/x86/mm/extable.c b/arch/x86/mm/extable.c
index 4d75bc656f97..30bb0bd3b1b8 100644
--- a/arch/x86/mm/extable.c
+++ b/arch/x86/mm/extable.c
@@ -45,55 +45,6 @@ __visible bool ex_handler_fault(const struct exception_table_entry *fixup,
 EXPORT_SYMBOL_GPL(ex_handler_fault);
 
 /*
- * Handler for UD0 exception following a failed test against the
- * result of a refcount inc/dec/add/sub.
- */
-__visible bool ex_handler_refcount(const struct exception_table_entry *fixup,
-				   struct pt_regs *regs, int trapnr,
-				   unsigned long error_code,
-				   unsigned long fault_addr)
-{
-	/* First unconditionally saturate the refcount. */
-	*(int *)regs->cx = INT_MIN / 2;
-
-	/*
-	 * Strictly speaking, this reports the fixup destination, not
-	 * the fault location, and not the actually overflowing
-	 * instruction, which is the instruction before the "js", but
-	 * since that instruction could be a variety of lengths, just
-	 * report the location after the overflow, which should be close
-	 * enough for finding the overflow, as it's at least back in
-	 * the function, having returned from .text.unlikely.
-	 */
-	regs->ip = ex_fixup_addr(fixup);
-
-	/*
-	 * This function has been called because either a negative refcount
-	 * value was seen by any of the refcount functions, or a zero
-	 * refcount value was seen by refcount_dec().
-	 *
-	 * If we crossed from INT_MAX to INT_MIN, OF (Overflow Flag: result
-	 * wrapped around) will be set. Additionally, seeing the refcount
-	 * reach 0 will set ZF (Zero Flag: result was zero). In each of
-	 * these cases we want a report, since it's a boundary condition.
-	 * The SF case is not reported since it indicates post-boundary
-	 * manipulations below zero or above INT_MAX. And if none of the
-	 * flags are set, something has gone very wrong, so report it.
-	 */
-	if (regs->flags & (X86_EFLAGS_OF | X86_EFLAGS_ZF)) {
-		bool zero = regs->flags & X86_EFLAGS_ZF;
-
-		refcount_error_report(regs, zero ? "hit zero" : "overflow");
-	} else if ((regs->flags & X86_EFLAGS_SF) == 0) {
-		/* Report if none of OF, ZF, nor SF are set. */
-		refcount_error_report(regs, "unexpected saturation");
-	}
-
-	return true;
-}
-EXPORT_SYMBOL(ex_handler_refcount);
-
-/*
  * Handler for when we fail to restore a task's FPU state.  We should never get
  * here because the FPU state of a task using the FPU (task->thread.fpu.state)
  * should always be valid.  However, past bugs have allowed userspace to set
diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c
index fd10d91a6115..e7bb483557c9 100644
--- a/arch/x86/mm/init.c
+++ b/arch/x86/mm/init.c
@@ -829,14 +829,13 @@ void free_init_pages(const char *what, unsigned long begin, unsigned long end)
  * used for the kernel image only.  free_init_pages() will do the
  * right thing for either kind of address.
  */
-void free_kernel_image_pages(void *begin, void *end)
+void free_kernel_image_pages(const char *what, void *begin, void *end)
 {
 	unsigned long begin_ul = (unsigned long)begin;
 	unsigned long end_ul = (unsigned long)end;
 	unsigned long len_pages = (end_ul - begin_ul) >> PAGE_SHIFT;
 
-
-	free_init_pages("unused kernel image", begin_ul, end_ul);
+	free_init_pages(what, begin_ul, end_ul);
 
 	/*
 	 * PTI maps some of the kernel into userspace.  For performance,
@@ -865,7 +864,8 @@ void __ref free_initmem(void)
 
 	mem_encrypt_free_decrypted_mem();
 
-	free_kernel_image_pages(&__init_begin, &__init_end);
+	free_kernel_image_pages("unused kernel image (initmem)",
+				&__init_begin, &__init_end);
 }
 
 #ifdef CONFIG_BLK_DEV_INITRD
diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index a6b5c653727b..dcb9bc961b39 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -1263,7 +1263,7 @@ int kernel_set_to_readonly;
 void set_kernel_text_rw(void)
 {
 	unsigned long start = PFN_ALIGN(_text);
-	unsigned long end = PFN_ALIGN(__stop___ex_table);
+	unsigned long end = PFN_ALIGN(_etext);
 
 	if (!kernel_set_to_readonly)
 		return;
@@ -1282,7 +1282,7 @@ void set_kernel_text_rw(void)
 void set_kernel_text_ro(void)
 {
 	unsigned long start = PFN_ALIGN(_text);
-	unsigned long end = PFN_ALIGN(__stop___ex_table);
+	unsigned long end = PFN_ALIGN(_etext);
 
 	if (!kernel_set_to_readonly)
 		return;
@@ -1300,9 +1300,9 @@ void mark_rodata_ro(void)
 {
 	unsigned long start = PFN_ALIGN(_text);
 	unsigned long rodata_start = PFN_ALIGN(__start_rodata);
-	unsigned long end = (unsigned long) &__end_rodata_hpage_align;
-	unsigned long text_end = PFN_ALIGN(&__stop___ex_table);
-	unsigned long rodata_end = PFN_ALIGN(&__end_rodata);
+	unsigned long end = (unsigned long)__end_rodata_hpage_align;
+	unsigned long text_end = PFN_ALIGN(_etext);
+	unsigned long rodata_end = PFN_ALIGN(__end_rodata);
 	unsigned long all_end;
 
 	printk(KERN_INFO "Write protecting the kernel read-only data: %luk\n",
@@ -1334,8 +1334,10 @@ void mark_rodata_ro(void)
 	set_memory_ro(start, (end-start) >> PAGE_SHIFT);
 #endif
 
-	free_kernel_image_pages((void *)text_end, (void *)rodata_start);
-	free_kernel_image_pages((void *)rodata_end, (void *)_sdata);
+	free_kernel_image_pages("unused kernel image (text/rodata gap)",
+				(void *)text_end, (void *)rodata_start);
+	free_kernel_image_pages("unused kernel image (rodata/data gap)",
+				(void *)rodata_end, (void *)_sdata);
 
 	debug_checkwx();
 }
diff --git a/arch/x86/mm/ioremap.c b/arch/x86/mm/ioremap.c
index a39dcdb5ae34..1ff9c2030b4f 100644
--- a/arch/x86/mm/ioremap.c
+++ b/arch/x86/mm/ioremap.c
@@ -626,6 +626,17 @@ static bool memremap_is_setup_data(resource_size_t phys_addr,
 		paddr_next = data->next;
 		len = data->len;
 
+		if ((phys_addr > paddr) && (phys_addr < (paddr + len))) {
+			memunmap(data);
+			return true;
+		}
+
+		if (data->type == SETUP_INDIRECT &&
+		    ((struct setup_indirect *)data->data)->type != SETUP_INDIRECT) {
+			paddr = ((struct setup_indirect *)data->data)->addr;
+			len = ((struct setup_indirect *)data->data)->len;
+		}
+
 		memunmap(data);
 
 		if ((phys_addr > paddr) && (phys_addr < (paddr + len)))
diff --git a/arch/x86/mm/mem_encrypt_boot.S b/arch/x86/mm/mem_encrypt_boot.S
index 6d71481a1e70..106ead05bbe3 100644
--- a/arch/x86/mm/mem_encrypt_boot.S
+++ b/arch/x86/mm/mem_encrypt_boot.S
@@ -16,7 +16,7 @@
 
 	.text
 	.code64
-ENTRY(sme_encrypt_execute)
+SYM_FUNC_START(sme_encrypt_execute)
 
 	/*
 	 * Entry parameters:
@@ -66,9 +66,9 @@ ENTRY(sme_encrypt_execute)
 	pop	%rbp
 
 	ret
-ENDPROC(sme_encrypt_execute)
+SYM_FUNC_END(sme_encrypt_execute)
 
-ENTRY(__enc_copy)
+SYM_FUNC_START(__enc_copy)
 /*
  * Routine used to encrypt memory in place.
  *   This routine must be run outside of the kernel proper since
@@ -153,4 +153,4 @@ ENTRY(__enc_copy)
 
 	ret
 .L__enc_copy_end:
-ENDPROC(__enc_copy)
+SYM_FUNC_END(__enc_copy)
diff --git a/arch/x86/mm/numa.c b/arch/x86/mm/numa.c
index 4123100e0eaf..99f7a68738f0 100644
--- a/arch/x86/mm/numa.c
+++ b/arch/x86/mm/numa.c
@@ -699,7 +699,7 @@ static int __init dummy_numa_init(void)
  * x86_numa_init - Initialize NUMA
  *
  * Try each configured NUMA initialization method until one succeeds.  The
- * last fallback is dummy single node config encomapssing whole memory and
+ * last fallback is dummy single node config encompassing whole memory and
  * never fails.
  */
 void __init x86_numa_init(void)
diff --git a/arch/x86/mm/pat.c b/arch/x86/mm/pat.c
index d9fbd4f69920..2d758e19ef22 100644
--- a/arch/x86/mm/pat.c
+++ b/arch/x86/mm/pat.c
@@ -603,7 +603,7 @@ int reserve_memtype(u64 start, u64 end, enum page_cache_mode req_type,
 
 	spin_lock(&memtype_lock);
 
-	err = rbt_memtype_check_insert(new, new_type);
+	err = memtype_check_insert(new, new_type);
 	if (err) {
 		pr_info("x86/PAT: reserve_memtype failed [mem %#010Lx-%#010Lx], track %s, req %s\n",
 			start, end - 1,
@@ -650,7 +650,7 @@ int free_memtype(u64 start, u64 end)
 	}
 
 	spin_lock(&memtype_lock);
-	entry = rbt_memtype_erase(start, end);
+	entry = memtype_erase(start, end);
 	spin_unlock(&memtype_lock);
 
 	if (IS_ERR(entry)) {
@@ -693,7 +693,7 @@ static enum page_cache_mode lookup_memtype(u64 paddr)
 
 	spin_lock(&memtype_lock);
 
-	entry = rbt_memtype_lookup(paddr);
+	entry = memtype_lookup(paddr);
 	if (entry != NULL)
 		rettype = entry->type;
 	else
@@ -1109,7 +1109,7 @@ static struct memtype *memtype_get_idx(loff_t pos)
 		return NULL;
 
 	spin_lock(&memtype_lock);
-	ret = rbt_memtype_copy_nth_element(print_entry, pos);
+	ret = memtype_copy_nth_element(print_entry, pos);
 	spin_unlock(&memtype_lock);
 
 	if (!ret) {
diff --git a/arch/x86/mm/pat_internal.h b/arch/x86/mm/pat_internal.h
index eeb5caeb089b..79a06684349e 100644
--- a/arch/x86/mm/pat_internal.h
+++ b/arch/x86/mm/pat_internal.h
@@ -29,20 +29,20 @@ static inline char *cattr_name(enum page_cache_mode pcm)
 }
 
 #ifdef CONFIG_X86_PAT
-extern int rbt_memtype_check_insert(struct memtype *new,
-					enum page_cache_mode *new_type);
-extern struct memtype *rbt_memtype_erase(u64 start, u64 end);
-extern struct memtype *rbt_memtype_lookup(u64 addr);
-extern int rbt_memtype_copy_nth_element(struct memtype *out, loff_t pos);
+extern int memtype_check_insert(struct memtype *new,
+				enum page_cache_mode *new_type);
+extern struct memtype *memtype_erase(u64 start, u64 end);
+extern struct memtype *memtype_lookup(u64 addr);
+extern int memtype_copy_nth_element(struct memtype *out, loff_t pos);
 #else
-static inline int rbt_memtype_check_insert(struct memtype *new,
-					enum page_cache_mode *new_type)
+static inline int memtype_check_insert(struct memtype *new,
+				       enum page_cache_mode *new_type)
 { return 0; }
-static inline struct memtype *rbt_memtype_erase(u64 start, u64 end)
+static inline struct memtype *memtype_erase(u64 start, u64 end)
 { return NULL; }
-static inline struct memtype *rbt_memtype_lookup(u64 addr)
+static inline struct memtype *memtype_lookup(u64 addr)
 { return NULL; }
-static inline int rbt_memtype_copy_nth_element(struct memtype *out, loff_t pos)
+static inline int memtype_copy_nth_element(struct memtype *out, loff_t pos)
 { return 0; }
 #endif
 
diff --git a/arch/x86/mm/pat_interval.c b/arch/x86/mm/pat_interval.c
new file mode 100644
index 000000000000..47a1bf30748f
--- /dev/null
+++ b/arch/x86/mm/pat_interval.c
@@ -0,0 +1,185 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Handle caching attributes in page tables (PAT)
+ *
+ * Authors: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com>
+ *          Suresh B Siddha <suresh.b.siddha@intel.com>
+ *
+ * Interval tree used to store the PAT memory type reservations.
+ */
+
+#include <linux/seq_file.h>
+#include <linux/debugfs.h>
+#include <linux/kernel.h>
+#include <linux/interval_tree_generic.h>
+#include <linux/sched.h>
+#include <linux/gfp.h>
+
+#include <asm/pgtable.h>
+#include <asm/pat.h>
+
+#include "pat_internal.h"
+
+/*
+ * The memtype tree keeps track of memory type for specific
+ * physical memory areas. Without proper tracking, conflicting memory
+ * types in different mappings can cause CPU cache corruption.
+ *
+ * The tree is an interval tree (augmented rbtree) with tree ordered
+ * on starting address. Tree can contain multiple entries for
+ * different regions which overlap. All the aliases have the same
+ * cache attributes of course.
+ *
+ * memtype_lock protects the rbtree.
+ */
+static inline u64 memtype_interval_start(struct memtype *memtype)
+{
+	return memtype->start;
+}
+
+static inline u64 memtype_interval_end(struct memtype *memtype)
+{
+	return memtype->end - 1;
+}
+INTERVAL_TREE_DEFINE(struct memtype, rb, u64, subtree_max_end,
+		     memtype_interval_start, memtype_interval_end,
+		     static, memtype_interval)
+
+static struct rb_root_cached memtype_rbroot = RB_ROOT_CACHED;
+
+enum {
+	MEMTYPE_EXACT_MATCH	= 0,
+	MEMTYPE_END_MATCH	= 1
+};
+
+static struct memtype *memtype_match(u64 start, u64 end, int match_type)
+{
+	struct memtype *match;
+
+	match = memtype_interval_iter_first(&memtype_rbroot, start, end);
+	while (match != NULL && match->start < end) {
+		if ((match_type == MEMTYPE_EXACT_MATCH) &&
+		    (match->start == start) && (match->end == end))
+			return match;
+
+		if ((match_type == MEMTYPE_END_MATCH) &&
+		    (match->start < start) && (match->end == end))
+			return match;
+
+		match = memtype_interval_iter_next(match, start, end);
+	}
+
+	return NULL; /* Returns NULL if there is no match */
+}
+
+static int memtype_check_conflict(u64 start, u64 end,
+				  enum page_cache_mode reqtype,
+				  enum page_cache_mode *newtype)
+{
+	struct memtype *match;
+	enum page_cache_mode found_type = reqtype;
+
+	match = memtype_interval_iter_first(&memtype_rbroot, start, end);
+	if (match == NULL)
+		goto success;
+
+	if (match->type != found_type && newtype == NULL)
+		goto failure;
+
+	dprintk("Overlap at 0x%Lx-0x%Lx\n", match->start, match->end);
+	found_type = match->type;
+
+	match = memtype_interval_iter_next(match, start, end);
+	while (match) {
+		if (match->type != found_type)
+			goto failure;
+
+		match = memtype_interval_iter_next(match, start, end);
+	}
+success:
+	if (newtype)
+		*newtype = found_type;
+
+	return 0;
+
+failure:
+	pr_info("x86/PAT: %s:%d conflicting memory types %Lx-%Lx %s<->%s\n",
+		current->comm, current->pid, start, end,
+		cattr_name(found_type), cattr_name(match->type));
+	return -EBUSY;
+}
+
+int memtype_check_insert(struct memtype *new,
+			 enum page_cache_mode *ret_type)
+{
+	int err = 0;
+
+	err = memtype_check_conflict(new->start, new->end, new->type, ret_type);
+	if (err)
+		return err;
+
+	if (ret_type)
+		new->type = *ret_type;
+
+	memtype_interval_insert(new, &memtype_rbroot);
+	return 0;
+}
+
+struct memtype *memtype_erase(u64 start, u64 end)
+{
+	struct memtype *data;
+
+	/*
+	 * Since the memtype_rbroot tree allows overlapping ranges,
+	 * memtype_erase() checks with EXACT_MATCH first, i.e. free
+	 * a whole node for the munmap case.  If no such entry is found,
+	 * it then checks with END_MATCH, i.e. shrink the size of a node
+	 * from the end for the mremap case.
+	 */
+	data = memtype_match(start, end, MEMTYPE_EXACT_MATCH);
+	if (!data) {
+		data = memtype_match(start, end, MEMTYPE_END_MATCH);
+		if (!data)
+			return ERR_PTR(-EINVAL);
+	}
+
+	if (data->start == start) {
+		/* munmap: erase this node */
+		memtype_interval_remove(data, &memtype_rbroot);
+	} else {
+		/* mremap: update the end value of this node */
+		memtype_interval_remove(data, &memtype_rbroot);
+		data->end = start;
+		memtype_interval_insert(data, &memtype_rbroot);
+		return NULL;
+	}
+
+	return data;
+}
+
+struct memtype *memtype_lookup(u64 addr)
+{
+	return memtype_interval_iter_first(&memtype_rbroot, addr,
+					   addr + PAGE_SIZE);
+}
+
+#if defined(CONFIG_DEBUG_FS)
+int memtype_copy_nth_element(struct memtype *out, loff_t pos)
+{
+	struct memtype *match;
+	int i = 1;
+
+	match = memtype_interval_iter_first(&memtype_rbroot, 0, ULONG_MAX);
+	while (match && pos != i) {
+		match = memtype_interval_iter_next(match, 0, ULONG_MAX);
+		i++;
+	}
+
+	if (match) { /* pos == i */
+		*out = *match;
+		return 0;
+	} else {
+		return 1;
+	}
+}
+#endif
diff --git a/arch/x86/mm/pat_rbtree.c b/arch/x86/mm/pat_rbtree.c
deleted file mode 100644
index 65ebe4b88f7c..000000000000
--- a/arch/x86/mm/pat_rbtree.c
+++ /dev/null
@@ -1,268 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/*
- * Handle caching attributes in page tables (PAT)
- *
- * Authors: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com>
- *          Suresh B Siddha <suresh.b.siddha@intel.com>
- *
- * Interval tree (augmented rbtree) used to store the PAT memory type
- * reservations.
- */
-
-#include <linux/seq_file.h>
-#include <linux/debugfs.h>
-#include <linux/kernel.h>
-#include <linux/rbtree_augmented.h>
-#include <linux/sched.h>
-#include <linux/gfp.h>
-
-#include <asm/pgtable.h>
-#include <asm/pat.h>
-
-#include "pat_internal.h"
-
-/*
- * The memtype tree keeps track of memory type for specific
- * physical memory areas. Without proper tracking, conflicting memory
- * types in different mappings can cause CPU cache corruption.
- *
- * The tree is an interval tree (augmented rbtree) with tree ordered
- * on starting address. Tree can contain multiple entries for
- * different regions which overlap. All the aliases have the same
- * cache attributes of course.
- *
- * memtype_lock protects the rbtree.
- */
-
-static struct rb_root memtype_rbroot = RB_ROOT;
-
-static int is_node_overlap(struct memtype *node, u64 start, u64 end)
-{
-	if (node->start >= end || node->end <= start)
-		return 0;
-
-	return 1;
-}
-
-static u64 get_subtree_max_end(struct rb_node *node)
-{
-	u64 ret = 0;
-	if (node) {
-		struct memtype *data = rb_entry(node, struct memtype, rb);
-		ret = data->subtree_max_end;
-	}
-	return ret;
-}
-
-#define NODE_END(node) ((node)->end)
-
-RB_DECLARE_CALLBACKS_MAX(static, memtype_rb_augment_cb,
-			 struct memtype, rb, u64, subtree_max_end, NODE_END)
-
-/* Find the first (lowest start addr) overlapping range from rb tree */
-static struct memtype *memtype_rb_lowest_match(struct rb_root *root,
-				u64 start, u64 end)
-{
-	struct rb_node *node = root->rb_node;
-	struct memtype *last_lower = NULL;
-
-	while (node) {
-		struct memtype *data = rb_entry(node, struct memtype, rb);
-
-		if (get_subtree_max_end(node->rb_left) > start) {
-			/* Lowest overlap if any must be on left side */
-			node = node->rb_left;
-		} else if (is_node_overlap(data, start, end)) {
-			last_lower = data;
-			break;
-		} else if (start >= data->start) {
-			/* Lowest overlap if any must be on right side */
-			node = node->rb_right;
-		} else {
-			break;
-		}
-	}
-	return last_lower; /* Returns NULL if there is no overlap */
-}
-
-enum {
-	MEMTYPE_EXACT_MATCH	= 0,
-	MEMTYPE_END_MATCH	= 1
-};
-
-static struct memtype *memtype_rb_match(struct rb_root *root,
-				u64 start, u64 end, int match_type)
-{
-	struct memtype *match;
-
-	match = memtype_rb_lowest_match(root, start, end);
-	while (match != NULL && match->start < end) {
-		struct rb_node *node;
-
-		if ((match_type == MEMTYPE_EXACT_MATCH) &&
-		    (match->start == start) && (match->end == end))
-			return match;
-
-		if ((match_type == MEMTYPE_END_MATCH) &&
-		    (match->start < start) && (match->end == end))
-			return match;
-
-		node = rb_next(&match->rb);
-		if (node)
-			match = rb_entry(node, struct memtype, rb);
-		else
-			match = NULL;
-	}
-
-	return NULL; /* Returns NULL if there is no match */
-}
-
-static int memtype_rb_check_conflict(struct rb_root *root,
-				u64 start, u64 end,
-				enum page_cache_mode reqtype,
-				enum page_cache_mode *newtype)
-{
-	struct rb_node *node;
-	struct memtype *match;
-	enum page_cache_mode found_type = reqtype;
-
-	match = memtype_rb_lowest_match(&memtype_rbroot, start, end);
-	if (match == NULL)
-		goto success;
-
-	if (match->type != found_type && newtype == NULL)
-		goto failure;
-
-	dprintk("Overlap at 0x%Lx-0x%Lx\n", match->start, match->end);
-	found_type = match->type;
-
-	node = rb_next(&match->rb);
-	while (node) {
-		match = rb_entry(node, struct memtype, rb);
-
-		if (match->start >= end) /* Checked all possible matches */
-			goto success;
-
-		if (is_node_overlap(match, start, end) &&
-		    match->type != found_type) {
-			goto failure;
-		}
-
-		node = rb_next(&match->rb);
-	}
-success:
-	if (newtype)
-		*newtype = found_type;
-
-	return 0;
-
-failure:
-	pr_info("x86/PAT: %s:%d conflicting memory types %Lx-%Lx %s<->%s\n",
-		current->comm, current->pid, start, end,
-		cattr_name(found_type), cattr_name(match->type));
-	return -EBUSY;
-}
-
-static void memtype_rb_insert(struct rb_root *root, struct memtype *newdata)
-{
-	struct rb_node **node = &(root->rb_node);
-	struct rb_node *parent = NULL;
-
-	while (*node) {
-		struct memtype *data = rb_entry(*node, struct memtype, rb);
-
-		parent = *node;
-		if (data->subtree_max_end < newdata->end)
-			data->subtree_max_end = newdata->end;
-		if (newdata->start <= data->start)
-			node = &((*node)->rb_left);
-		else if (newdata->start > data->start)
-			node = &((*node)->rb_right);
-	}
-
-	newdata->subtree_max_end = newdata->end;
-	rb_link_node(&newdata->rb, parent, node);
-	rb_insert_augmented(&newdata->rb, root, &memtype_rb_augment_cb);
-}
-
-int rbt_memtype_check_insert(struct memtype *new,
-			     enum page_cache_mode *ret_type)
-{
-	int err = 0;
-
-	err = memtype_rb_check_conflict(&memtype_rbroot, new->start, new->end,
-						new->type, ret_type);
-
-	if (!err) {
-		if (ret_type)
-			new->type = *ret_type;
-
-		new->subtree_max_end = new->end;
-		memtype_rb_insert(&memtype_rbroot, new);
-	}
-	return err;
-}
-
-struct memtype *rbt_memtype_erase(u64 start, u64 end)
-{
-	struct memtype *data;
-
-	/*
-	 * Since the memtype_rbroot tree allows overlapping ranges,
-	 * rbt_memtype_erase() checks with EXACT_MATCH first, i.e. free
-	 * a whole node for the munmap case.  If no such entry is found,
-	 * it then checks with END_MATCH, i.e. shrink the size of a node
-	 * from the end for the mremap case.
-	 */
-	data = memtype_rb_match(&memtype_rbroot, start, end,
-				MEMTYPE_EXACT_MATCH);
-	if (!data) {
-		data = memtype_rb_match(&memtype_rbroot, start, end,
-					MEMTYPE_END_MATCH);
-		if (!data)
-			return ERR_PTR(-EINVAL);
-	}
-
-	if (data->start == start) {
-		/* munmap: erase this node */
-		rb_erase_augmented(&data->rb, &memtype_rbroot,
-					&memtype_rb_augment_cb);
-	} else {
-		/* mremap: update the end value of this node */
-		rb_erase_augmented(&data->rb, &memtype_rbroot,
-					&memtype_rb_augment_cb);
-		data->end = start;
-		data->subtree_max_end = data->end;
-		memtype_rb_insert(&memtype_rbroot, data);
-		return NULL;
-	}
-
-	return data;
-}
-
-struct memtype *rbt_memtype_lookup(u64 addr)
-{
-	return memtype_rb_lowest_match(&memtype_rbroot, addr, addr + PAGE_SIZE);
-}
-
-#if defined(CONFIG_DEBUG_FS)
-int rbt_memtype_copy_nth_element(struct memtype *out, loff_t pos)
-{
-	struct rb_node *node;
-	int i = 1;
-
-	node = rb_first(&memtype_rbroot);
-	while (node && pos != i) {
-		node = rb_next(node);
-		i++;
-	}
-
-	if (node) { /* pos == i */
-		struct memtype *this = rb_entry(node, struct memtype, rb);
-		*out = *this;
-		return 0;
-	} else {
-		return 1;
-	}
-}
-#endif
diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c
index 3e4b9035bb9a..7bd2c3a52297 100644
--- a/arch/x86/mm/pgtable.c
+++ b/arch/x86/mm/pgtable.c
@@ -643,8 +643,8 @@ void __native_set_fixmap(enum fixed_addresses idx, pte_t pte)
 	fixmaps_set++;
 }
 
-void native_set_fixmap(enum fixed_addresses idx, phys_addr_t phys,
-		       pgprot_t flags)
+void native_set_fixmap(unsigned /* enum fixed_addresses */ idx,
+		       phys_addr_t phys, pgprot_t flags)
 {
 	/* Sanitize 'prot' against any unsupported bits: */
 	pgprot_val(flags) &= __default_kernel_pte_mask;
diff --git a/arch/x86/mm/pti.c b/arch/x86/mm/pti.c
index 7f2140414440..44a9f068eee0 100644
--- a/arch/x86/mm/pti.c
+++ b/arch/x86/mm/pti.c
@@ -574,7 +574,7 @@ static void pti_clone_kernel_text(void)
 	 */
 	unsigned long start = PFN_ALIGN(_text);
 	unsigned long end_clone  = (unsigned long)__end_rodata_aligned;
-	unsigned long end_global = PFN_ALIGN((unsigned long)__stop___ex_table);
+	unsigned long end_global = PFN_ALIGN((unsigned long)_etext);
 
 	if (!pti_kernel_image_global_ok())
 		return;
diff --git a/arch/x86/platform/efi/efi.c b/arch/x86/platform/efi/efi.c
index 425e025341db..38d44f36d5ed 100644
--- a/arch/x86/platform/efi/efi.c
+++ b/arch/x86/platform/efi/efi.c
@@ -128,6 +128,9 @@ void __init efi_find_mirror(void)
 	efi_memory_desc_t *md;
 	u64 mirror_size = 0, total_size = 0;
 
+	if (!efi_enabled(EFI_MEMMAP))
+		return;
+
 	for_each_efi_memory_desc(md) {
 		unsigned long long start = md->phys_addr;
 		unsigned long long size = md->num_pages << EFI_PAGE_SHIFT;
@@ -145,14 +148,18 @@ void __init efi_find_mirror(void)
 
 /*
  * Tell the kernel about the EFI memory map.  This might include
- * more than the max 128 entries that can fit in the e820 legacy
- * (zeropage) memory map.
+ * more than the max 128 entries that can fit in the passed in e820
+ * legacy (zeropage) memory map, but the kernel's e820 table can hold
+ * E820_MAX_ENTRIES.
  */
 
 static void __init do_add_efi_memmap(void)
 {
 	efi_memory_desc_t *md;
 
+	if (!efi_enabled(EFI_MEMMAP))
+		return;
+
 	for_each_efi_memory_desc(md) {
 		unsigned long long start = md->phys_addr;
 		unsigned long long size = md->num_pages << EFI_PAGE_SHIFT;
@@ -164,7 +171,10 @@ static void __init do_add_efi_memmap(void)
 		case EFI_BOOT_SERVICES_CODE:
 		case EFI_BOOT_SERVICES_DATA:
 		case EFI_CONVENTIONAL_MEMORY:
-			if (md->attribute & EFI_MEMORY_WB)
+			if (efi_soft_reserve_enabled()
+			    && (md->attribute & EFI_MEMORY_SP))
+				e820_type = E820_TYPE_SOFT_RESERVED;
+			else if (md->attribute & EFI_MEMORY_WB)
 				e820_type = E820_TYPE_RAM;
 			else
 				e820_type = E820_TYPE_RESERVED;
@@ -190,11 +200,36 @@ static void __init do_add_efi_memmap(void)
 			e820_type = E820_TYPE_RESERVED;
 			break;
 		}
+
 		e820__range_add(start, size, e820_type);
 	}
 	e820__update_table(e820_table);
 }
 
+/*
+ * Given add_efi_memmap defaults to 0 and there there is no alternative
+ * e820 mechanism for soft-reserved memory, import the full EFI memory
+ * map if soft reservations are present and enabled. Otherwise, the
+ * mechanism to disable the kernel's consideration of EFI_MEMORY_SP is
+ * the efi=nosoftreserve option.
+ */
+static bool do_efi_soft_reserve(void)
+{
+	efi_memory_desc_t *md;
+
+	if (!efi_enabled(EFI_MEMMAP))
+		return false;
+
+	if (!efi_soft_reserve_enabled())
+		return false;
+
+	for_each_efi_memory_desc(md)
+		if (md->type == EFI_CONVENTIONAL_MEMORY &&
+		    (md->attribute & EFI_MEMORY_SP))
+			return true;
+	return false;
+}
+
 int __init efi_memblock_x86_reserve_range(void)
 {
 	struct efi_info *e = &boot_params.efi_info;
@@ -224,9 +259,11 @@ int __init efi_memblock_x86_reserve_range(void)
 	if (rv)
 		return rv;
 
-	if (add_efi_memmap)
+	if (add_efi_memmap || do_efi_soft_reserve())
 		do_add_efi_memmap();
 
+	efi_fake_memmap_early();
+
 	WARN(efi.memmap.desc_version != 1,
 	     "Unexpected EFI_MEMORY_DESCRIPTOR version %ld",
 	     efi.memmap.desc_version);
@@ -779,6 +816,15 @@ static bool should_map_region(efi_memory_desc_t *md)
 		return false;
 
 	/*
+	 * EFI specific purpose memory may be reserved by default
+	 * depending on kernel config and boot options.
+	 */
+	if (md->type == EFI_CONVENTIONAL_MEMORY &&
+	    efi_soft_reserve_enabled() &&
+	    (md->attribute & EFI_MEMORY_SP))
+		return false;
+
+	/*
 	 * Map all of RAM so that we can access arguments in the 1:1
 	 * mapping when making EFI runtime calls.
 	 */
diff --git a/arch/x86/platform/efi/efi_stub_32.S b/arch/x86/platform/efi/efi_stub_32.S
index ab2e91e76894..eed8b5b441f8 100644
--- a/arch/x86/platform/efi/efi_stub_32.S
+++ b/arch/x86/platform/efi/efi_stub_32.S
@@ -22,7 +22,7 @@
  */
 
 .text
-ENTRY(efi_call_phys)
+SYM_FUNC_START(efi_call_phys)
 	/*
 	 * 0. The function can only be called in Linux kernel. So CS has been
 	 * set to 0x0010, DS and SS have been set to 0x0018. In EFI, I found
@@ -114,7 +114,7 @@ ENTRY(efi_call_phys)
 	movl	(%edx), %ecx
 	pushl	%ecx
 	ret
-ENDPROC(efi_call_phys)
+SYM_FUNC_END(efi_call_phys)
 .previous
 
 .data
diff --git a/arch/x86/platform/efi/efi_stub_64.S b/arch/x86/platform/efi/efi_stub_64.S
index 74628ec78f29..b1d2313fe3bf 100644
--- a/arch/x86/platform/efi/efi_stub_64.S
+++ b/arch/x86/platform/efi/efi_stub_64.S
@@ -39,7 +39,7 @@
 	mov %rsi, %cr0;			\
 	mov (%rsp), %rsp
 
-ENTRY(efi_call)
+SYM_FUNC_START(efi_call)
 	pushq %rbp
 	movq %rsp, %rbp
 	SAVE_XMM
@@ -55,4 +55,4 @@ ENTRY(efi_call)
 	RESTORE_XMM
 	popq %rbp
 	ret
-ENDPROC(efi_call)
+SYM_FUNC_END(efi_call)
diff --git a/arch/x86/platform/efi/efi_thunk_64.S b/arch/x86/platform/efi/efi_thunk_64.S
index 46c58b08739c..3189f1394701 100644
--- a/arch/x86/platform/efi/efi_thunk_64.S
+++ b/arch/x86/platform/efi/efi_thunk_64.S
@@ -25,7 +25,7 @@
 
 	.text
 	.code64
-ENTRY(efi64_thunk)
+SYM_FUNC_START(efi64_thunk)
 	push	%rbp
 	push	%rbx
 
@@ -60,14 +60,14 @@ ENTRY(efi64_thunk)
 	pop	%rbx
 	pop	%rbp
 	retq
-ENDPROC(efi64_thunk)
+SYM_FUNC_END(efi64_thunk)
 
 /*
  * We run this function from the 1:1 mapping.
  *
  * This function must be invoked with a 1:1 mapped stack.
  */
-ENTRY(__efi64_thunk)
+SYM_FUNC_START_LOCAL(__efi64_thunk)
 	movl	%ds, %eax
 	push	%rax
 	movl	%es, %eax
@@ -114,14 +114,14 @@ ENTRY(__efi64_thunk)
 	or	%rcx, %rax
 1:
 	ret
-ENDPROC(__efi64_thunk)
+SYM_FUNC_END(__efi64_thunk)
 
-ENTRY(efi_exit32)
+SYM_FUNC_START_LOCAL(efi_exit32)
 	movq	func_rt_ptr(%rip), %rax
 	push	%rax
 	mov	%rdi, %rax
 	ret
-ENDPROC(efi_exit32)
+SYM_FUNC_END(efi_exit32)
 
 	.code32
 /*
@@ -129,7 +129,7 @@ ENDPROC(efi_exit32)
  *
  * The stack should represent the 32-bit calling convention.
  */
-ENTRY(efi_enter32)
+SYM_FUNC_START_LOCAL(efi_enter32)
 	movl	$__KERNEL_DS, %eax
 	movl	%eax, %ds
 	movl	%eax, %es
@@ -145,7 +145,7 @@ ENTRY(efi_enter32)
 	pushl	%eax
 
 	lret
-ENDPROC(efi_enter32)
+SYM_FUNC_END(efi_enter32)
 
 	.data
 	.balign	8
diff --git a/arch/x86/platform/efi/quirks.c b/arch/x86/platform/efi/quirks.c
index 3b9fd679cea9..7675cf754d90 100644
--- a/arch/x86/platform/efi/quirks.c
+++ b/arch/x86/platform/efi/quirks.c
@@ -320,6 +320,9 @@ void __init efi_reserve_boot_services(void)
 {
 	efi_memory_desc_t *md;
 
+	if (!efi_enabled(EFI_MEMMAP))
+		return;
+
 	for_each_efi_memory_desc(md) {
 		u64 start = md->phys_addr;
 		u64 size = md->num_pages << EFI_PAGE_SHIFT;
diff --git a/arch/x86/platform/olpc/xo1-wakeup.S b/arch/x86/platform/olpc/xo1-wakeup.S
index 5fee3a2c2fd4..75f4faff8468 100644
--- a/arch/x86/platform/olpc/xo1-wakeup.S
+++ b/arch/x86/platform/olpc/xo1-wakeup.S
@@ -90,7 +90,7 @@ restore_registers:
 
 	ret
 
-ENTRY(do_olpc_suspend_lowlevel)
+SYM_CODE_START(do_olpc_suspend_lowlevel)
 	call	save_processor_state
 	call	save_registers
 
@@ -110,6 +110,7 @@ ret_point:
 	call	restore_registers
 	call	restore_processor_state
 	ret
+SYM_CODE_END(do_olpc_suspend_lowlevel)
 
 .data
 saved_gdt:             .long   0,0
diff --git a/arch/x86/platform/pvh/head.S b/arch/x86/platform/pvh/head.S
index 1f8825bbaffb..43b4d864817e 100644
--- a/arch/x86/platform/pvh/head.S
+++ b/arch/x86/platform/pvh/head.S
@@ -50,7 +50,7 @@
 #define PVH_DS_SEL		(PVH_GDT_ENTRY_DS * 8)
 #define PVH_CANARY_SEL		(PVH_GDT_ENTRY_CANARY * 8)
 
-ENTRY(pvh_start_xen)
+SYM_CODE_START_LOCAL(pvh_start_xen)
 	cld
 
 	lgdt (_pa(gdt))
@@ -146,15 +146,16 @@ ENTRY(pvh_start_xen)
 
 	ljmp $PVH_CS_SEL, $_pa(startup_32)
 #endif
-END(pvh_start_xen)
+SYM_CODE_END(pvh_start_xen)
 
 	.section ".init.data","aw"
 	.balign 8
-gdt:
+SYM_DATA_START_LOCAL(gdt)
 	.word gdt_end - gdt_start
 	.long _pa(gdt_start)
 	.word 0
-gdt_start:
+SYM_DATA_END(gdt)
+SYM_DATA_START_LOCAL(gdt_start)
 	.quad 0x0000000000000000            /* NULL descriptor */
 #ifdef CONFIG_X86_64
 	.quad GDT_ENTRY(0xa09a, 0, 0xfffff) /* PVH_CS_SEL */
@@ -163,15 +164,14 @@ gdt_start:
 #endif
 	.quad GDT_ENTRY(0xc092, 0, 0xfffff) /* PVH_DS_SEL */
 	.quad GDT_ENTRY(0x4090, 0, 0x18)    /* PVH_CANARY_SEL */
-gdt_end:
+SYM_DATA_END_LABEL(gdt_start, SYM_L_LOCAL, gdt_end)
 
 	.balign 16
-canary:
-	.fill 48, 1, 0
+SYM_DATA_LOCAL(canary, .fill 48, 1, 0)
 
-early_stack:
+SYM_DATA_START_LOCAL(early_stack)
 	.fill BOOT_STACK_SIZE, 1, 0
-early_stack_end:
+SYM_DATA_END_LABEL(early_stack, SYM_L_LOCAL, early_stack_end)
 
 	ELFNOTE(Xen, XEN_ELFNOTE_PHYS32_ENTRY,
 	             _ASM_PTR (pvh_start_xen - __START_KERNEL_map))
diff --git a/arch/x86/platform/uv/bios_uv.c b/arch/x86/platform/uv/bios_uv.c
index c2ee31953372..ece9cb9c1189 100644
--- a/arch/x86/platform/uv/bios_uv.c
+++ b/arch/x86/platform/uv/bios_uv.c
@@ -184,20 +184,20 @@ int uv_bios_set_legacy_vga_target(bool decode, int domain, int bus)
 }
 EXPORT_SYMBOL_GPL(uv_bios_set_legacy_vga_target);
 
-void uv_bios_init(void)
+int uv_bios_init(void)
 {
 	uv_systab = NULL;
 	if ((uv_systab_phys == EFI_INVALID_TABLE_ADDR) ||
 	    !uv_systab_phys || efi_runtime_disabled()) {
 		pr_crit("UV: UVsystab: missing\n");
-		return;
+		return -EEXIST;
 	}
 
 	uv_systab = ioremap(uv_systab_phys, sizeof(struct uv_systab));
 	if (!uv_systab || strncmp(uv_systab->signature, UV_SYSTAB_SIG, 4)) {
 		pr_err("UV: UVsystab: bad signature!\n");
 		iounmap(uv_systab);
-		return;
+		return -EINVAL;
 	}
 
 	/* Starting with UV4 the UV systab size is variable */
@@ -208,8 +208,9 @@ void uv_bios_init(void)
 		uv_systab = ioremap(uv_systab_phys, size);
 		if (!uv_systab) {
 			pr_err("UV: UVsystab: ioremap(%d) failed!\n", size);
-			return;
+			return -EFAULT;
 		}
 	}
 	pr_info("UV: UVsystab: Revision:%x\n", uv_systab->revision);
+	return 0;
 }
diff --git a/arch/x86/power/hibernate_asm_32.S b/arch/x86/power/hibernate_asm_32.S
index 6fe383002125..8786653ad3c0 100644
--- a/arch/x86/power/hibernate_asm_32.S
+++ b/arch/x86/power/hibernate_asm_32.S
@@ -16,7 +16,7 @@
 
 .text
 
-ENTRY(swsusp_arch_suspend)
+SYM_FUNC_START(swsusp_arch_suspend)
 	movl %esp, saved_context_esp
 	movl %ebx, saved_context_ebx
 	movl %ebp, saved_context_ebp
@@ -33,9 +33,9 @@ ENTRY(swsusp_arch_suspend)
 	call swsusp_save
 	FRAME_END
 	ret
-ENDPROC(swsusp_arch_suspend)
+SYM_FUNC_END(swsusp_arch_suspend)
 
-ENTRY(restore_image)
+SYM_CODE_START(restore_image)
 	/* prepare to jump to the image kernel */
 	movl	restore_jump_address, %ebx
 	movl	restore_cr3, %ebp
@@ -45,9 +45,10 @@ ENTRY(restore_image)
 	/* jump to relocated restore code */
 	movl	relocated_restore_code, %eax
 	jmpl	*%eax
+SYM_CODE_END(restore_image)
 
 /* code below has been relocated to a safe page */
-ENTRY(core_restore_code)
+SYM_CODE_START(core_restore_code)
 	movl	temp_pgt, %eax
 	movl	%eax, %cr3
 
@@ -77,10 +78,11 @@ copy_loop:
 
 done:
 	jmpl	*%ebx
+SYM_CODE_END(core_restore_code)
 
 	/* code below belongs to the image kernel */
 	.align PAGE_SIZE
-ENTRY(restore_registers)
+SYM_FUNC_START(restore_registers)
 	/* go back to the original page tables */
 	movl	%ebp, %cr3
 	movl	mmu_cr4_features, %ecx
@@ -107,4 +109,4 @@ ENTRY(restore_registers)
 	movl	%eax, in_suspend
 
 	ret
-ENDPROC(restore_registers)
+SYM_FUNC_END(restore_registers)
diff --git a/arch/x86/power/hibernate_asm_64.S b/arch/x86/power/hibernate_asm_64.S
index a4d5eb0a7ece..7918b8415f13 100644
--- a/arch/x86/power/hibernate_asm_64.S
+++ b/arch/x86/power/hibernate_asm_64.S
@@ -22,7 +22,7 @@
 #include <asm/processor-flags.h>
 #include <asm/frame.h>
 
-ENTRY(swsusp_arch_suspend)
+SYM_FUNC_START(swsusp_arch_suspend)
 	movq	$saved_context, %rax
 	movq	%rsp, pt_regs_sp(%rax)
 	movq	%rbp, pt_regs_bp(%rax)
@@ -50,9 +50,9 @@ ENTRY(swsusp_arch_suspend)
 	call swsusp_save
 	FRAME_END
 	ret
-ENDPROC(swsusp_arch_suspend)
+SYM_FUNC_END(swsusp_arch_suspend)
 
-ENTRY(restore_image)
+SYM_CODE_START(restore_image)
 	/* prepare to jump to the image kernel */
 	movq	restore_jump_address(%rip), %r8
 	movq	restore_cr3(%rip), %r9
@@ -67,9 +67,10 @@ ENTRY(restore_image)
 	/* jump to relocated restore code */
 	movq	relocated_restore_code(%rip), %rcx
 	jmpq	*%rcx
+SYM_CODE_END(restore_image)
 
 	/* code below has been relocated to a safe page */
-ENTRY(core_restore_code)
+SYM_CODE_START(core_restore_code)
 	/* switch to temporary page tables */
 	movq	%rax, %cr3
 	/* flush TLB */
@@ -97,10 +98,11 @@ ENTRY(core_restore_code)
 .Ldone:
 	/* jump to the restore_registers address from the image header */
 	jmpq	*%r8
+SYM_CODE_END(core_restore_code)
 
 	 /* code below belongs to the image kernel */
 	.align PAGE_SIZE
-ENTRY(restore_registers)
+SYM_FUNC_START(restore_registers)
 	/* go back to the original page tables */
 	movq    %r9, %cr3
 
@@ -142,4 +144,4 @@ ENTRY(restore_registers)
 	movq	%rax, in_suspend(%rip)
 
 	ret
-ENDPROC(restore_registers)
+SYM_FUNC_END(restore_registers)
diff --git a/arch/x86/purgatory/entry64.S b/arch/x86/purgatory/entry64.S
index 275a646d1048..0b4390ce586b 100644
--- a/arch/x86/purgatory/entry64.S
+++ b/arch/x86/purgatory/entry64.S
@@ -8,13 +8,13 @@
  * This code has been taken from kexec-tools.
  */
 
+#include <linux/linkage.h>
+
 	.text
 	.balign 16
 	.code64
-	.globl entry64, entry64_regs
-
 
-entry64:
+SYM_CODE_START(entry64)
 	/* Setup a gdt that should be preserved */
 	lgdt gdt(%rip)
 
@@ -54,10 +54,11 @@ new_cs_exit:
 
 	/* Jump to the new code... */
 	jmpq	*rip(%rip)
+SYM_CODE_END(entry64)
 
 	.section ".rodata"
 	.balign 4
-entry64_regs:
+SYM_DATA_START(entry64_regs)
 rax:	.quad 0x0
 rcx:	.quad 0x0
 rdx:	.quad 0x0
@@ -75,13 +76,14 @@ r13:	.quad 0x0
 r14:	.quad 0x0
 r15:	.quad 0x0
 rip:	.quad 0x0
-	.size entry64_regs, . - entry64_regs
+SYM_DATA_END(entry64_regs)
 
 	/* GDT */
 	.section ".rodata"
 	.balign 16
-gdt:
-	/* 0x00 unusable segment
+SYM_DATA_START_LOCAL(gdt)
+	/*
+	 * 0x00 unusable segment
 	 * 0x08 unused
 	 * so use them as gdt ptr
 	 */
@@ -94,6 +96,8 @@ gdt:
 
 	/* 0x18 4GB flat data segment */
 	.word 0xFFFF, 0x0000, 0x9200, 0x00CF
-gdt_end:
-stack:	.quad   0, 0
-stack_init:
+SYM_DATA_END_LABEL(gdt, SYM_L_LOCAL, gdt_end)
+
+SYM_DATA_START_LOCAL(stack)
+	.quad   0, 0
+SYM_DATA_END_LABEL(stack, SYM_L_LOCAL, stack_init)
diff --git a/arch/x86/purgatory/purgatory.c b/arch/x86/purgatory/purgatory.c
index 3b95410ff0f8..2961234d0795 100644
--- a/arch/x86/purgatory/purgatory.c
+++ b/arch/x86/purgatory/purgatory.c
@@ -14,28 +14,10 @@
 
 #include "../boot/string.h"
 
-unsigned long purgatory_backup_dest __section(.kexec-purgatory);
-unsigned long purgatory_backup_src __section(.kexec-purgatory);
-unsigned long purgatory_backup_sz __section(.kexec-purgatory);
-
 u8 purgatory_sha256_digest[SHA256_DIGEST_SIZE] __section(.kexec-purgatory);
 
 struct kexec_sha_region purgatory_sha_regions[KEXEC_SEGMENT_MAX] __section(.kexec-purgatory);
 
-/*
- * On x86, second kernel requries first 640K of memory to boot. Copy
- * first 640K to a backup region in reserved memory range so that second
- * kernel can use first 640K.
- */
-static int copy_backup_region(void)
-{
-	if (purgatory_backup_dest) {
-		memcpy((void *)purgatory_backup_dest,
-		       (void *)purgatory_backup_src, purgatory_backup_sz);
-	}
-	return 0;
-}
-
 static int verify_sha256_digest(void)
 {
 	struct kexec_sha_region *ptr, *end;
@@ -66,7 +48,6 @@ void purgatory(void)
 		for (;;)
 			;
 	}
-	copy_backup_region();
 }
 
 /*
diff --git a/arch/x86/purgatory/setup-x86_64.S b/arch/x86/purgatory/setup-x86_64.S
index 321146be741d..89d9e9e53fcd 100644
--- a/arch/x86/purgatory/setup-x86_64.S
+++ b/arch/x86/purgatory/setup-x86_64.S
@@ -7,14 +7,14 @@
  *
  * This code has been taken from kexec-tools.
  */
+#include <linux/linkage.h>
 #include <asm/purgatory.h>
 
 	.text
-	.globl purgatory_start
 	.balign 16
-purgatory_start:
 	.code64
 
+SYM_CODE_START(purgatory_start)
 	/* Load a gdt so I know what the segment registers are */
 	lgdt	gdt(%rip)
 
@@ -32,10 +32,12 @@ purgatory_start:
 	/* Call the C code */
 	call purgatory
 	jmp	entry64
+SYM_CODE_END(purgatory_start)
 
 	.section ".rodata"
 	.balign 16
-gdt:	/* 0x00 unusable segment
+SYM_DATA_START_LOCAL(gdt)
+	/* 0x00 unusable segment
 	 * 0x08 unused
 	 * so use them as the gdt ptr
 	 */
@@ -48,10 +50,10 @@ gdt:	/* 0x00 unusable segment
 
 	/* 0x18 4GB flat data segment */
 	.word	0xFFFF, 0x0000, 0x9200, 0x00CF
-gdt_end:
+SYM_DATA_END_LABEL(gdt, SYM_L_LOCAL, gdt_end)
 
 	.bss
 	.balign 4096
-lstack:
+SYM_DATA_START_LOCAL(lstack)
 	.skip 4096
-lstack_end:
+SYM_DATA_END_LABEL(lstack, SYM_L_LOCAL, lstack_end)
diff --git a/arch/x86/purgatory/stack.S b/arch/x86/purgatory/stack.S
index 8b1427422dfc..1ef507ca50a5 100644
--- a/arch/x86/purgatory/stack.S
+++ b/arch/x86/purgatory/stack.S
@@ -5,13 +5,14 @@
  * Copyright (C) 2014 Red Hat Inc.
  */
 
+#include <linux/linkage.h>
+
 	/* A stack for the loaded kernel.
 	 * Separate and in the data section so it can be prepopulated.
 	 */
 	.data
 	.balign 4096
-	.globl stack, stack_end
 
-stack:
+SYM_DATA_START(stack)
 	.skip 4096
-stack_end:
+SYM_DATA_END_LABEL(stack, SYM_L_GLOBAL, stack_end)
diff --git a/arch/x86/realmode/init.c b/arch/x86/realmode/init.c
index 7dce39c8c034..262f83cad355 100644
--- a/arch/x86/realmode/init.c
+++ b/arch/x86/realmode/init.c
@@ -8,6 +8,7 @@
 #include <asm/pgtable.h>
 #include <asm/realmode.h>
 #include <asm/tlbflush.h>
+#include <asm/crash.h>
 
 struct real_mode_header *real_mode_header;
 u32 *trampoline_cr4_features;
@@ -34,6 +35,7 @@ void __init reserve_real_mode(void)
 
 	memblock_reserve(mem, size);
 	set_real_mode_mem(mem);
+	crash_reserve_low_1M();
 }
 
 static void __init setup_real_mode(void)
diff --git a/arch/x86/realmode/rm/header.S b/arch/x86/realmode/rm/header.S
index 6363761cc74c..af04512c02d9 100644
--- a/arch/x86/realmode/rm/header.S
+++ b/arch/x86/realmode/rm/header.S
@@ -14,7 +14,7 @@
 	.section ".header", "a"
 
 	.balign	16
-GLOBAL(real_mode_header)
+SYM_DATA_START(real_mode_header)
 	.long	pa_text_start
 	.long	pa_ro_end
 	/* SMP trampoline */
@@ -33,11 +33,9 @@ GLOBAL(real_mode_header)
 #ifdef CONFIG_X86_64
 	.long	__KERNEL32_CS
 #endif
-END(real_mode_header)
+SYM_DATA_END(real_mode_header)
 
 	/* End signature, used to verify integrity */
 	.section ".signature","a"
 	.balign 4
-GLOBAL(end_signature)
-	.long	REALMODE_END_SIGNATURE
-END(end_signature)
+SYM_DATA(end_signature, .long REALMODE_END_SIGNATURE)
diff --git a/arch/x86/realmode/rm/realmode.lds.S b/arch/x86/realmode/rm/realmode.lds.S
index 3bb980800c58..64d135d1ee63 100644
--- a/arch/x86/realmode/rm/realmode.lds.S
+++ b/arch/x86/realmode/rm/realmode.lds.S
@@ -11,6 +11,7 @@
 
 OUTPUT_FORMAT("elf32-i386")
 OUTPUT_ARCH(i386)
+ENTRY(pa_text_start)
 
 SECTIONS
 {
diff --git a/arch/x86/realmode/rm/reboot.S b/arch/x86/realmode/rm/reboot.S
index cd2f97b9623b..f10515b10e0a 100644
--- a/arch/x86/realmode/rm/reboot.S
+++ b/arch/x86/realmode/rm/reboot.S
@@ -19,7 +19,7 @@
  */
 	.section ".text32", "ax"
 	.code32
-ENTRY(machine_real_restart_asm)
+SYM_CODE_START(machine_real_restart_asm)
 
 #ifdef CONFIG_X86_64
 	/* Switch to trampoline GDT as it is guaranteed < 4 GiB */
@@ -33,7 +33,7 @@ ENTRY(machine_real_restart_asm)
 	movl	%eax, %cr0
 	ljmpl	$__KERNEL32_CS, $pa_machine_real_restart_paging_off
 
-GLOBAL(machine_real_restart_paging_off)
+SYM_INNER_LABEL(machine_real_restart_paging_off, SYM_L_GLOBAL)
 	xorl	%eax, %eax
 	xorl	%edx, %edx
 	movl	$MSR_EFER, %ecx
@@ -63,6 +63,7 @@ GLOBAL(machine_real_restart_paging_off)
 	movl	%ecx, %gs
 	movl	%ecx, %ss
 	ljmpw	$8, $1f
+SYM_CODE_END(machine_real_restart_asm)
 
 /*
  * This is 16-bit protected mode code to disable paging and the cache,
@@ -127,13 +128,13 @@ bios:
 	.section ".rodata", "a"
 
 	.balign	16
-GLOBAL(machine_real_restart_idt)
+SYM_DATA_START(machine_real_restart_idt)
 	.word	0xffff		/* Length - real mode default value */
 	.long	0		/* Base - real mode default value */
-END(machine_real_restart_idt)
+SYM_DATA_END(machine_real_restart_idt)
 
 	.balign	16
-GLOBAL(machine_real_restart_gdt)
+SYM_DATA_START(machine_real_restart_gdt)
 	/* Self-pointer */
 	.word	0xffff		/* Length - real mode default value */
 	.long	pa_machine_real_restart_gdt
@@ -153,4 +154,4 @@ GLOBAL(machine_real_restart_gdt)
 	 * semantics we don't have to reload the segments once CR0.PE = 0.
 	 */
 	.quad	GDT_ENTRY(0x0093, 0x100, 0xffff)
-END(machine_real_restart_gdt)
+SYM_DATA_END(machine_real_restart_gdt)
diff --git a/arch/x86/realmode/rm/stack.S b/arch/x86/realmode/rm/stack.S
index 8d4cb64799ea..0fca64061ad2 100644
--- a/arch/x86/realmode/rm/stack.S
+++ b/arch/x86/realmode/rm/stack.S
@@ -6,15 +6,13 @@
 #include <linux/linkage.h>
 
 	.data
-GLOBAL(HEAP)
-	.long	rm_heap
-GLOBAL(heap_end)
-	.long	rm_stack
+SYM_DATA(HEAP,		.long rm_heap)
+SYM_DATA(heap_end,	.long rm_stack)
 
 	.bss
 	.balign	16
-GLOBAL(rm_heap)
-	.space	2048
-GLOBAL(rm_stack)
+SYM_DATA(rm_heap,	.space 2048)
+
+SYM_DATA_START(rm_stack)
 	.space	2048
-GLOBAL(rm_stack_end)
+SYM_DATA_END_LABEL(rm_stack, SYM_L_GLOBAL, rm_stack_end)
diff --git a/arch/x86/realmode/rm/trampoline_32.S b/arch/x86/realmode/rm/trampoline_32.S
index 1868b158480d..3fad907a179f 100644
--- a/arch/x86/realmode/rm/trampoline_32.S
+++ b/arch/x86/realmode/rm/trampoline_32.S
@@ -29,7 +29,7 @@
 	.code16
 
 	.balign	PAGE_SIZE
-ENTRY(trampoline_start)
+SYM_CODE_START(trampoline_start)
 	wbinvd			# Needed for NUMA-Q should be harmless for others
 
 	LJMPW_RM(1f)
@@ -54,18 +54,20 @@ ENTRY(trampoline_start)
 	lmsw	%dx			# into protected mode
 
 	ljmpl	$__BOOT_CS, $pa_startup_32
+SYM_CODE_END(trampoline_start)
 
 	.section ".text32","ax"
 	.code32
-ENTRY(startup_32)			# note: also used from wakeup_asm.S
+SYM_CODE_START(startup_32)			# note: also used from wakeup_asm.S
 	jmp	*%eax
+SYM_CODE_END(startup_32)
 
 	.bss
 	.balign 8
-GLOBAL(trampoline_header)
-	tr_start:		.space	4
-	tr_gdt_pad:		.space	2
-	tr_gdt:			.space	6
-END(trampoline_header)
+SYM_DATA_START(trampoline_header)
+	SYM_DATA_LOCAL(tr_start,	.space 4)
+	SYM_DATA_LOCAL(tr_gdt_pad,	.space 2)
+	SYM_DATA_LOCAL(tr_gdt,		.space 6)
+SYM_DATA_END(trampoline_header)
 	
 #include "trampoline_common.S"
diff --git a/arch/x86/realmode/rm/trampoline_64.S b/arch/x86/realmode/rm/trampoline_64.S
index aee2b45d83b8..251758ed7443 100644
--- a/arch/x86/realmode/rm/trampoline_64.S
+++ b/arch/x86/realmode/rm/trampoline_64.S
@@ -38,7 +38,7 @@
 	.code16
 
 	.balign	PAGE_SIZE
-ENTRY(trampoline_start)
+SYM_CODE_START(trampoline_start)
 	cli			# We should be safe anyway
 	wbinvd
 
@@ -78,12 +78,14 @@ ENTRY(trampoline_start)
 no_longmode:
 	hlt
 	jmp no_longmode
+SYM_CODE_END(trampoline_start)
+
 #include "../kernel/verify_cpu.S"
 
 	.section ".text32","ax"
 	.code32
 	.balign 4
-ENTRY(startup_32)
+SYM_CODE_START(startup_32)
 	movl	%edx, %ss
 	addl	$pa_real_mode_base, %esp
 	movl	%edx, %ds
@@ -137,38 +139,39 @@ ENTRY(startup_32)
 	 * the new gdt/idt that has __KERNEL_CS with CS.L = 1.
 	 */
 	ljmpl	$__KERNEL_CS, $pa_startup_64
+SYM_CODE_END(startup_32)
 
 	.section ".text64","ax"
 	.code64
 	.balign 4
-ENTRY(startup_64)
+SYM_CODE_START(startup_64)
 	# Now jump into the kernel using virtual addresses
 	jmpq	*tr_start(%rip)
+SYM_CODE_END(startup_64)
 
 	.section ".rodata","a"
 	# Duplicate the global descriptor table
 	# so the kernel can live anywhere
 	.balign	16
-	.globl tr_gdt
-tr_gdt:
+SYM_DATA_START(tr_gdt)
 	.short	tr_gdt_end - tr_gdt - 1	# gdt limit
 	.long	pa_tr_gdt
 	.short	0
 	.quad	0x00cf9b000000ffff	# __KERNEL32_CS
 	.quad	0x00af9b000000ffff	# __KERNEL_CS
 	.quad	0x00cf93000000ffff	# __KERNEL_DS
-tr_gdt_end:
+SYM_DATA_END_LABEL(tr_gdt, SYM_L_LOCAL, tr_gdt_end)
 
 	.bss
 	.balign	PAGE_SIZE
-GLOBAL(trampoline_pgd)		.space	PAGE_SIZE
+SYM_DATA(trampoline_pgd, .space PAGE_SIZE)
 
 	.balign	8
-GLOBAL(trampoline_header)
-	tr_start:		.space	8
-	GLOBAL(tr_efer)		.space	8
-	GLOBAL(tr_cr4)		.space	4
-	GLOBAL(tr_flags)	.space	4
-END(trampoline_header)
+SYM_DATA_START(trampoline_header)
+	SYM_DATA_LOCAL(tr_start,	.space 8)
+	SYM_DATA(tr_efer,		.space 8)
+	SYM_DATA(tr_cr4,		.space 4)
+	SYM_DATA(tr_flags,		.space 4)
+SYM_DATA_END(trampoline_header)
 
 #include "trampoline_common.S"
diff --git a/arch/x86/realmode/rm/trampoline_common.S b/arch/x86/realmode/rm/trampoline_common.S
index 8d8208dcca24..5033e640f957 100644
--- a/arch/x86/realmode/rm/trampoline_common.S
+++ b/arch/x86/realmode/rm/trampoline_common.S
@@ -1,4 +1,4 @@
 /* SPDX-License-Identifier: GPL-2.0 */
 	.section ".rodata","a"
 	.balign	16
-tr_idt: .fill 1, 6, 0
+SYM_DATA_LOCAL(tr_idt, .fill 1, 6, 0)
diff --git a/arch/x86/realmode/rm/wakeup_asm.S b/arch/x86/realmode/rm/wakeup_asm.S
index 05ac9c17c811..02d0ba16ae33 100644
--- a/arch/x86/realmode/rm/wakeup_asm.S
+++ b/arch/x86/realmode/rm/wakeup_asm.S
@@ -17,7 +17,7 @@
 	.section ".data", "aw"
 
 	.balign	16
-GLOBAL(wakeup_header)
+SYM_DATA_START(wakeup_header)
 	video_mode:	.short	0	/* Video mode number */
 	pmode_entry:	.long	0
 	pmode_cs:	.short	__KERNEL_CS
@@ -31,13 +31,13 @@ GLOBAL(wakeup_header)
 	realmode_flags:	.long	0
 	real_magic:	.long	0
 	signature:	.long	WAKEUP_HEADER_SIGNATURE
-END(wakeup_header)
+SYM_DATA_END(wakeup_header)
 
 	.text
 	.code16
 
 	.balign	16
-ENTRY(wakeup_start)
+SYM_CODE_START(wakeup_start)
 	cli
 	cld
 
@@ -73,7 +73,7 @@ ENTRY(wakeup_start)
 	movw	%ax, %fs
 	movw	%ax, %gs
 
-	lidtl	wakeup_idt
+	lidtl	.Lwakeup_idt
 
 	/* Clear the EFLAGS */
 	pushl $0
@@ -135,6 +135,7 @@ ENTRY(wakeup_start)
 #else
 	jmp	trampoline_start
 #endif
+SYM_CODE_END(wakeup_start)
 
 bogus_real_magic:
 1:
@@ -152,7 +153,7 @@ bogus_real_magic:
 	 */
 
 	.balign	16
-GLOBAL(wakeup_gdt)
+SYM_DATA_START(wakeup_gdt)
 	.word	3*8-1		/* Self-descriptor */
 	.long	pa_wakeup_gdt
 	.word	0
@@ -164,15 +165,15 @@ GLOBAL(wakeup_gdt)
 	.word	0xffff		/* 16-bit data segment @ real_mode_base */
 	.long	0x93000000 + pa_real_mode_base
 	.word	0x008f		/* big real mode */
-END(wakeup_gdt)
+SYM_DATA_END(wakeup_gdt)
 
 	.section ".rodata","a"
 	.balign	8
 
 	/* This is the standard real-mode IDT */
 	.balign	16
-GLOBAL(wakeup_idt)
+SYM_DATA_START_LOCAL(.Lwakeup_idt)
 	.word	0xffff		/* limit */
 	.long	0		/* address */
 	.word	0
-END(wakeup_idt)
+SYM_DATA_END(.Lwakeup_idt)
diff --git a/arch/x86/realmode/rmpiggy.S b/arch/x86/realmode/rmpiggy.S
index c078dba40cef..c8fef76743f6 100644
--- a/arch/x86/realmode/rmpiggy.S
+++ b/arch/x86/realmode/rmpiggy.S
@@ -10,12 +10,10 @@
 
 	.balign PAGE_SIZE
 
-GLOBAL(real_mode_blob)
+SYM_DATA_START(real_mode_blob)
 	.incbin	"arch/x86/realmode/rm/realmode.bin"
-END(real_mode_blob)
+SYM_DATA_END_LABEL(real_mode_blob, SYM_L_GLOBAL, real_mode_blob_end)
 
-GLOBAL(real_mode_blob_end);
-
-GLOBAL(real_mode_relocs)
+SYM_DATA_START(real_mode_relocs)
 	.incbin	"arch/x86/realmode/rm/realmode.relocs"
-END(real_mode_relocs)
+SYM_DATA_END(real_mode_relocs)
diff --git a/arch/x86/tools/gen-insn-attr-x86.awk b/arch/x86/tools/gen-insn-attr-x86.awk
index b02a36b2c14f..a42015b305f4 100644
--- a/arch/x86/tools/gen-insn-attr-x86.awk
+++ b/arch/x86/tools/gen-insn-attr-x86.awk
@@ -69,7 +69,7 @@ BEGIN {
 
 	lprefix1_expr = "\\((66|!F3)\\)"
 	lprefix2_expr = "\\(F3\\)"
-	lprefix3_expr = "\\((F2|!F3|66\\&F2)\\)"
+	lprefix3_expr = "\\((F2|!F3|66&F2)\\)"
 	lprefix_expr = "\\((66|F2|F3)\\)"
 	max_lprefix = 4
 
@@ -257,7 +257,7 @@ function convert_operands(count,opnd,       i,j,imm,mod)
 	return add_flags(imm, mod)
 }
 
-/^[0-9a-f]+\:/ {
+/^[0-9a-f]+:/ {
 	if (NR == 1)
 		next
 	# get index
diff --git a/arch/x86/um/vdso/vdso.S b/arch/x86/um/vdso/vdso.S
index a4a3870dc059..a6eaf293a73b 100644
--- a/arch/x86/um/vdso/vdso.S
+++ b/arch/x86/um/vdso/vdso.S
@@ -1,11 +1,11 @@
 /* SPDX-License-Identifier: GPL-2.0 */
 #include <linux/init.h>
+#include <linux/linkage.h>
 
 __INITDATA
 
-	.globl vdso_start, vdso_end
-vdso_start:
+SYM_DATA_START(vdso_start)
 	.incbin "arch/x86/um/vdso/vdso.so"
-vdso_end:
+SYM_DATA_END_LABEL(vdso_start, SYM_L_GLOBAL, vdso_end)
 
 __FINIT
diff --git a/arch/x86/xen/enlighten_pv.c b/arch/x86/xen/enlighten_pv.c
index 5bfea374a160..ae4a41ca19f6 100644
--- a/arch/x86/xen/enlighten_pv.c
+++ b/arch/x86/xen/enlighten_pv.c
@@ -837,15 +837,6 @@ static void xen_load_sp0(unsigned long sp0)
 	this_cpu_write(cpu_tss_rw.x86_tss.sp0, sp0);
 }
 
-void xen_set_iopl_mask(unsigned mask)
-{
-	struct physdev_set_iopl set_iopl;
-
-	/* Force the change at ring 0. */
-	set_iopl.iopl = (mask == 0) ? 1 : (mask >> 12) & 3;
-	HYPERVISOR_physdev_op(PHYSDEVOP_set_iopl, &set_iopl);
-}
-
 static void xen_io_delay(void)
 {
 }
@@ -1055,7 +1046,6 @@ static const struct pv_cpu_ops xen_cpu_ops __initconst = {
 	.write_idt_entry = xen_write_idt_entry,
 	.load_sp0 = xen_load_sp0,
 
-	.set_iopl_mask = xen_set_iopl_mask,
 	.io_delay = xen_io_delay,
 
 	/* Xen takes care of %gs when switching to usermode for us */
diff --git a/arch/x86/xen/xen-asm.S b/arch/x86/xen/xen-asm.S
index be104eef80be..508fe204520b 100644
--- a/arch/x86/xen/xen-asm.S
+++ b/arch/x86/xen/xen-asm.S
@@ -19,7 +19,7 @@
  * event status with one and operation.  If there are pending events,
  * then enter the hypervisor to get them handled.
  */
-ENTRY(xen_irq_enable_direct)
+SYM_FUNC_START(xen_irq_enable_direct)
 	FRAME_BEGIN
 	/* Unmask events */
 	movb $0, PER_CPU_VAR(xen_vcpu_info) + XEN_vcpu_info_mask
@@ -38,17 +38,17 @@ ENTRY(xen_irq_enable_direct)
 1:
 	FRAME_END
 	ret
-	ENDPROC(xen_irq_enable_direct)
+SYM_FUNC_END(xen_irq_enable_direct)
 
 
 /*
  * Disabling events is simply a matter of making the event mask
  * non-zero.
  */
-ENTRY(xen_irq_disable_direct)
+SYM_FUNC_START(xen_irq_disable_direct)
 	movb $1, PER_CPU_VAR(xen_vcpu_info) + XEN_vcpu_info_mask
 	ret
-ENDPROC(xen_irq_disable_direct)
+SYM_FUNC_END(xen_irq_disable_direct)
 
 /*
  * (xen_)save_fl is used to get the current interrupt enable status.
@@ -59,12 +59,12 @@ ENDPROC(xen_irq_disable_direct)
  * undefined.  We need to toggle the state of the bit, because Xen and
  * x86 use opposite senses (mask vs enable).
  */
-ENTRY(xen_save_fl_direct)
+SYM_FUNC_START(xen_save_fl_direct)
 	testb $0xff, PER_CPU_VAR(xen_vcpu_info) + XEN_vcpu_info_mask
 	setz %ah
 	addb %ah, %ah
 	ret
-	ENDPROC(xen_save_fl_direct)
+SYM_FUNC_END(xen_save_fl_direct)
 
 
 /*
@@ -74,7 +74,7 @@ ENTRY(xen_save_fl_direct)
  * interrupt mask state, it checks for unmasked pending events and
  * enters the hypervisor to get them delivered if so.
  */
-ENTRY(xen_restore_fl_direct)
+SYM_FUNC_START(xen_restore_fl_direct)
 	FRAME_BEGIN
 #ifdef CONFIG_X86_64
 	testw $X86_EFLAGS_IF, %di
@@ -95,14 +95,14 @@ ENTRY(xen_restore_fl_direct)
 1:
 	FRAME_END
 	ret
-	ENDPROC(xen_restore_fl_direct)
+SYM_FUNC_END(xen_restore_fl_direct)
 
 
 /*
  * Force an event check by making a hypercall, but preserve regs
  * before making the call.
  */
-ENTRY(check_events)
+SYM_FUNC_START(check_events)
 	FRAME_BEGIN
 #ifdef CONFIG_X86_32
 	push %eax
@@ -135,19 +135,19 @@ ENTRY(check_events)
 #endif
 	FRAME_END
 	ret
-ENDPROC(check_events)
+SYM_FUNC_END(check_events)
 
-ENTRY(xen_read_cr2)
+SYM_FUNC_START(xen_read_cr2)
 	FRAME_BEGIN
 	_ASM_MOV PER_CPU_VAR(xen_vcpu), %_ASM_AX
 	_ASM_MOV XEN_vcpu_info_arch_cr2(%_ASM_AX), %_ASM_AX
 	FRAME_END
 	ret
-	ENDPROC(xen_read_cr2);
+SYM_FUNC_END(xen_read_cr2);
 
-ENTRY(xen_read_cr2_direct)
+SYM_FUNC_START(xen_read_cr2_direct)
 	FRAME_BEGIN
 	_ASM_MOV PER_CPU_VAR(xen_vcpu_info) + XEN_vcpu_info_arch_cr2, %_ASM_AX
 	FRAME_END
 	ret
-	ENDPROC(xen_read_cr2_direct);
+SYM_FUNC_END(xen_read_cr2_direct);
diff --git a/arch/x86/xen/xen-asm_32.S b/arch/x86/xen/xen-asm_32.S
index c15db060a242..2712e9155306 100644
--- a/arch/x86/xen/xen-asm_32.S
+++ b/arch/x86/xen/xen-asm_32.S
@@ -56,7 +56,7 @@
 	_ASM_EXTABLE(1b,2b)
 .endm
 
-ENTRY(xen_iret)
+SYM_CODE_START(xen_iret)
 	/* test eflags for special cases */
 	testl $(X86_EFLAGS_VM | XEN_EFLAGS_NMI), 8(%esp)
 	jnz hyper_iret
@@ -122,14 +122,14 @@ xen_iret_end_crit:
 hyper_iret:
 	/* put this out of line since its very rarely used */
 	jmp hypercall_page + __HYPERVISOR_iret * 32
+SYM_CODE_END(xen_iret)
 
 	.globl xen_iret_start_crit, xen_iret_end_crit
 
 /*
- * This is called by xen_hypervisor_callback in entry.S when it sees
+ * This is called by xen_hypervisor_callback in entry_32.S when it sees
  * that the EIP at the time of interrupt was between
- * xen_iret_start_crit and xen_iret_end_crit.  We're passed the EIP in
- * %eax so we can do a more refined determination of what to do.
+ * xen_iret_start_crit and xen_iret_end_crit.
  *
  * The stack format at this point is:
  *	----------------
@@ -138,70 +138,46 @@ hyper_iret:
  *	 eflags		}  outer exception info
  *	 cs		}
  *	 eip		}
- *	---------------- <- edi (copy dest)
- *	 eax		:  outer eax if it hasn't been restored
  *	----------------
- *	 eflags		}  nested exception info
- *	 cs		}   (no ss/esp because we're nested
- *	 eip		}    from the same ring)
- *	 orig_eax	}<- esi (copy src)
- *	 - - - - - - - -
- *	 fs		}
- *	 es		}
- *	 ds		}  SAVE_ALL state
- *	 eax		}
- *	  :		:
- *	 ebx		}<- esp
+ *	 eax		:  outer eax if it hasn't been restored
  *	----------------
+ *	 eflags		}
+ *	 cs		}  nested exception info
+ *	 eip		}
+ *	 return address	: (into xen_hypervisor_callback)
  *
- * In order to deliver the nested exception properly, we need to shift
- * everything from the return addr up to the error code so it sits
- * just under the outer exception info.  This means that when we
- * handle the exception, we do it in the context of the outer
- * exception rather than starting a new one.
+ * In order to deliver the nested exception properly, we need to discard the
+ * nested exception frame such that when we handle the exception, we do it
+ * in the context of the outer exception rather than starting a new one.
  *
- * The only caveat is that if the outer eax hasn't been restored yet
- * (ie, it's still on stack), we need to insert its value into the
- * SAVE_ALL state before going on, since it's usermode state which we
- * eventually need to restore.
+ * The only caveat is that if the outer eax hasn't been restored yet (i.e.
+ * it's still on stack), we need to restore its value here.
  */
-ENTRY(xen_iret_crit_fixup)
+SYM_CODE_START(xen_iret_crit_fixup)
 	/*
 	 * Paranoia: Make sure we're really coming from kernel space.
 	 * One could imagine a case where userspace jumps into the
 	 * critical range address, but just before the CPU delivers a
-	 * GP, it decides to deliver an interrupt instead.  Unlikely?
-	 * Definitely.  Easy to avoid?  Yes.  The Intel documents
-	 * explicitly say that the reported EIP for a bad jump is the
-	 * jump instruction itself, not the destination, but some
-	 * virtual environments get this wrong.
+	 * PF, it decides to deliver an interrupt instead.  Unlikely?
+	 * Definitely.  Easy to avoid?  Yes.
 	 */
-	movl PT_CS(%esp), %ecx
-	andl $SEGMENT_RPL_MASK, %ecx
-	cmpl $USER_RPL, %ecx
-	je 2f
-
-	lea PT_ORIG_EAX(%esp), %esi
-	lea PT_EFLAGS(%esp), %edi
+	testb $2, 2*4(%esp)		/* nested CS */
+	jnz 2f
 
 	/*
 	 * If eip is before iret_restore_end then stack
 	 * hasn't been restored yet.
 	 */
-	cmp $iret_restore_end, %eax
+	cmpl $iret_restore_end, 1*4(%esp)
 	jae 1f
 
-	movl 0+4(%edi), %eax		/* copy EAX (just above top of frame) */
-	movl %eax, PT_EAX(%esp)
+	movl 4*4(%esp), %eax		/* load outer EAX */
+	ret $4*4			/* discard nested EIP, CS, and EFLAGS as
+					 * well as the just restored EAX */
 
-	lea ESP_OFFSET(%edi), %edi	/* move dest up over saved regs */
-
-	/* set up the copy */
-1:	std
-	mov $PT_EIP / 4, %ecx		/* saved regs up to orig_eax */
-	rep movsl
-	cld
-
-	lea 4(%edi), %esp		/* point esp to new frame */
-2:	jmp xen_do_upcall
+1:
+	ret $3*4			/* discard nested EIP, CS, and EFLAGS */
 
+2:
+	ret
+SYM_CODE_END(xen_iret_crit_fixup)
diff --git a/arch/x86/xen/xen-asm_64.S b/arch/x86/xen/xen-asm_64.S
index ebf610b49c06..0a0fd168683a 100644
--- a/arch/x86/xen/xen-asm_64.S
+++ b/arch/x86/xen/xen-asm_64.S
@@ -20,11 +20,11 @@
 #include <linux/linkage.h>
 
 .macro xen_pv_trap name
-ENTRY(xen_\name)
+SYM_CODE_START(xen_\name)
 	pop %rcx
 	pop %r11
 	jmp  \name
-END(xen_\name)
+SYM_CODE_END(xen_\name)
 _ASM_NOKPROBE(xen_\name)
 .endm
 
@@ -57,7 +57,7 @@ xen_pv_trap entry_INT80_compat
 xen_pv_trap hypervisor_callback
 
 	__INIT
-ENTRY(xen_early_idt_handler_array)
+SYM_CODE_START(xen_early_idt_handler_array)
 	i = 0
 	.rept NUM_EXCEPTION_VECTORS
 	pop %rcx
@@ -66,7 +66,7 @@ ENTRY(xen_early_idt_handler_array)
 	i = i + 1
 	.fill xen_early_idt_handler_array + i*XEN_EARLY_IDT_HANDLER_SIZE - ., 1, 0xcc
 	.endr
-END(xen_early_idt_handler_array)
+SYM_CODE_END(xen_early_idt_handler_array)
 	__FINIT
 
 hypercall_iret = hypercall_page + __HYPERVISOR_iret * 32
@@ -85,11 +85,12 @@ hypercall_iret = hypercall_page + __HYPERVISOR_iret * 32
  *	r11		}<-- pushed by hypercall page
  * rsp->rax		}
  */
-ENTRY(xen_iret)
+SYM_CODE_START(xen_iret)
 	pushq $0
 	jmp hypercall_iret
+SYM_CODE_END(xen_iret)
 
-ENTRY(xen_sysret64)
+SYM_CODE_START(xen_sysret64)
 	/*
 	 * We're already on the usermode stack at this point, but
 	 * still with the kernel gs, so we can easily switch back.
@@ -107,6 +108,7 @@ ENTRY(xen_sysret64)
 
 	pushq $VGCF_in_syscall
 	jmp hypercall_iret
+SYM_CODE_END(xen_sysret64)
 
 /*
  * Xen handles syscall callbacks much like ordinary exceptions, which
@@ -124,7 +126,7 @@ ENTRY(xen_sysret64)
  */
 
 /* Normal 64-bit system call target */
-ENTRY(xen_syscall_target)
+SYM_FUNC_START(xen_syscall_target)
 	popq %rcx
 	popq %r11
 
@@ -137,12 +139,12 @@ ENTRY(xen_syscall_target)
 	movq $__USER_CS, 1*8(%rsp)
 
 	jmp entry_SYSCALL_64_after_hwframe
-ENDPROC(xen_syscall_target)
+SYM_FUNC_END(xen_syscall_target)
 
 #ifdef CONFIG_IA32_EMULATION
 
 /* 32-bit compat syscall target */
-ENTRY(xen_syscall32_target)
+SYM_FUNC_START(xen_syscall32_target)
 	popq %rcx
 	popq %r11
 
@@ -155,25 +157,25 @@ ENTRY(xen_syscall32_target)
 	movq $__USER32_CS, 1*8(%rsp)
 
 	jmp entry_SYSCALL_compat_after_hwframe
-ENDPROC(xen_syscall32_target)
+SYM_FUNC_END(xen_syscall32_target)
 
 /* 32-bit compat sysenter target */
-ENTRY(xen_sysenter_target)
+SYM_FUNC_START(xen_sysenter_target)
 	mov 0*8(%rsp), %rcx
 	mov 1*8(%rsp), %r11
 	mov 5*8(%rsp), %rsp
 	jmp entry_SYSENTER_compat
-ENDPROC(xen_sysenter_target)
+SYM_FUNC_END(xen_sysenter_target)
 
 #else /* !CONFIG_IA32_EMULATION */
 
-ENTRY(xen_syscall32_target)
-ENTRY(xen_sysenter_target)
+SYM_FUNC_START_ALIAS(xen_syscall32_target)
+SYM_FUNC_START(xen_sysenter_target)
 	lea 16(%rsp), %rsp	/* strip %rcx, %r11 */
 	mov $-ENOSYS, %rax
 	pushq $0
 	jmp hypercall_iret
-ENDPROC(xen_syscall32_target)
-ENDPROC(xen_sysenter_target)
+SYM_FUNC_END(xen_sysenter_target)
+SYM_FUNC_END_ALIAS(xen_syscall32_target)
 
 #endif	/* CONFIG_IA32_EMULATION */
diff --git a/arch/x86/xen/xen-head.S b/arch/x86/xen/xen-head.S
index c1d8b90aa4e2..1d0cee3163e4 100644
--- a/arch/x86/xen/xen-head.S
+++ b/arch/x86/xen/xen-head.S
@@ -22,7 +22,7 @@
 
 #ifdef CONFIG_XEN_PV
 	__INIT
-ENTRY(startup_xen)
+SYM_CODE_START(startup_xen)
 	UNWIND_HINT_EMPTY
 	cld
 
@@ -52,13 +52,13 @@ ENTRY(startup_xen)
 #endif
 
 	jmp xen_start_kernel
-END(startup_xen)
+SYM_CODE_END(startup_xen)
 	__FINIT
 #endif
 
 .pushsection .text
 	.balign PAGE_SIZE
-ENTRY(hypercall_page)
+SYM_CODE_START(hypercall_page)
 	.rept (PAGE_SIZE / 32)
 		UNWIND_HINT_EMPTY
 		.skip 32
@@ -69,7 +69,7 @@ ENTRY(hypercall_page)
 	.type xen_hypercall_##n, @function; .size xen_hypercall_##n, 32
 #include <asm/xen-hypercalls.h>
 #undef HYPERCALL
-END(hypercall_page)
+SYM_CODE_END(hypercall_page)
 .popsection
 
 	ELFNOTE(Xen, XEN_ELFNOTE_GUEST_OS,       .asciz "linux")
diff --git a/arch/xtensa/kernel/vmlinux.lds.S b/arch/xtensa/kernel/vmlinux.lds.S
index 943f10639a93..0043d5858f14 100644
--- a/arch/xtensa/kernel/vmlinux.lds.S
+++ b/arch/xtensa/kernel/vmlinux.lds.S
@@ -14,6 +14,8 @@
  * Joe Taylor <joe@tensilica.com, joetylr@yahoo.com>
  */
 
+#define RO_EXCEPTION_TABLE_ALIGN	16
+
 #include <asm-generic/vmlinux.lds.h>
 #include <asm/page.h>
 #include <asm/thread_info.h>
@@ -124,18 +126,16 @@ SECTIONS
 
   . = ALIGN(16);
 
-  RODATA
+  RO_DATA(4096)
 
   /*  Relocation table */
 
   .fixup   : { *(.fixup) }
 
-  EXCEPTION_TABLE(16)
-  NOTES
   /* Data section */
 
   _sdata = .;
-  RW_DATA_SECTION(XCHAL_ICACHE_LINESIZE, PAGE_SIZE, THREAD_SIZE)
+  RW_DATA(XCHAL_ICACHE_LINESIZE, PAGE_SIZE, THREAD_SIZE)
   _edata = .;
 
   /* Initialization code and data: */
diff --git a/drivers/acpi/Kconfig b/drivers/acpi/Kconfig
index ebe1e9e5fd81..4fb97511a16f 100644
--- a/drivers/acpi/Kconfig
+++ b/drivers/acpi/Kconfig
@@ -319,12 +319,6 @@ config ACPI_THERMAL
 	  To compile this driver as a module, choose M here:
 	  the module will be called thermal.
 
-config ACPI_NUMA
-	bool "NUMA support"
-	depends on NUMA
-	depends on (X86 || IA64 || ARM64)
-	default y if IA64 || ARM64
-
 config ACPI_CUSTOM_DSDT_FILE
 	string "Custom DSDT Table file to include"
 	default ""
@@ -473,8 +467,7 @@ config ACPI_REDUCED_HARDWARE_ONLY
 	  If you are unsure what to do, do not enable this option.
 
 source "drivers/acpi/nfit/Kconfig"
-source "drivers/acpi/hmat/Kconfig"
-
+source "drivers/acpi/numa/Kconfig"
 source "drivers/acpi/apei/Kconfig"
 source "drivers/acpi/dptf/Kconfig"
 
@@ -513,11 +506,19 @@ menuconfig PMIC_OPREGION
 	  PMIC chip.
 
 if PMIC_OPREGION
-config CRC_PMIC_OPREGION
-	bool "ACPI operation region support for CrystalCove PMIC"
+config BYTCRC_PMIC_OPREGION
+	bool "ACPI operation region support for Bay Trail Crystal Cove PMIC"
+	depends on INTEL_SOC_PMIC
+	help
+	  This config adds ACPI operation region support for the Bay Trail
+	  version of the Crystal Cove PMIC.
+
+config CHTCRC_PMIC_OPREGION
+	bool "ACPI operation region support for Cherry Trail Crystal Cove PMIC"
 	depends on INTEL_SOC_PMIC
 	help
-	  This config adds ACPI operation region support for CrystalCove PMIC.
+	  This config adds ACPI operation region support for the Cherry Trail
+	  version of the Crystal Cove PMIC.
 
 config XPOWER_PMIC_OPREGION
 	bool "ACPI operation region support for XPower AXP288 PMIC"
diff --git a/drivers/acpi/Makefile b/drivers/acpi/Makefile
index 5d361e4e3405..33fdaf67454e 100644
--- a/drivers/acpi/Makefile
+++ b/drivers/acpi/Makefile
@@ -48,14 +48,13 @@ acpi-y				+= acpi_pnp.o
 acpi-$(CONFIG_ARM_AMBA)	+= acpi_amba.o
 acpi-y				+= power.o
 acpi-y				+= event.o
-acpi-$(CONFIG_ACPI_REDUCED_HARDWARE_ONLY) += evged.o
+acpi-y				+= evged.o
 acpi-y				+= sysfs.o
 acpi-y				+= property.o
 acpi-$(CONFIG_X86)		+= acpi_cmos_rtc.o
 acpi-$(CONFIG_X86)		+= x86/apple.o
 acpi-$(CONFIG_X86)		+= x86/utils.o
 acpi-$(CONFIG_DEBUG_FS)		+= debugfs.o
-acpi-$(CONFIG_ACPI_NUMA)	+= numa.o
 acpi-$(CONFIG_ACPI_PROCFS_POWER) += cm_sbs.o
 acpi-y				+= acpi_lpat.o
 acpi-$(CONFIG_ACPI_LPIT)	+= acpi_lpit.o
@@ -80,7 +79,7 @@ obj-$(CONFIG_ACPI_PROCESSOR)	+= processor.o
 obj-$(CONFIG_ACPI)		+= container.o
 obj-$(CONFIG_ACPI_THERMAL)	+= thermal.o
 obj-$(CONFIG_ACPI_NFIT)		+= nfit/
-obj-$(CONFIG_ACPI_HMAT)		+= hmat/
+obj-$(CONFIG_ACPI_NUMA)		+= numa/
 obj-$(CONFIG_ACPI)		+= acpi_memhotplug.o
 obj-$(CONFIG_ACPI_HOTPLUG_IOAPIC) += ioapic.o
 obj-$(CONFIG_ACPI_BATTERY)	+= battery.o
@@ -109,7 +108,8 @@ obj-$(CONFIG_ACPI_APEI)		+= apei/
 obj-$(CONFIG_ACPI_EXTLOG)	+= acpi_extlog.o
 
 obj-$(CONFIG_PMIC_OPREGION)	+= pmic/intel_pmic.o
-obj-$(CONFIG_CRC_PMIC_OPREGION) += pmic/intel_pmic_crc.o
+obj-$(CONFIG_BYTCRC_PMIC_OPREGION) += pmic/intel_pmic_bytcrc.o
+obj-$(CONFIG_CHTCRC_PMIC_OPREGION) += pmic/intel_pmic_chtcrc.o
 obj-$(CONFIG_XPOWER_PMIC_OPREGION) += pmic/intel_pmic_xpower.o
 obj-$(CONFIG_BXT_WC_PMIC_OPREGION) += pmic/intel_pmic_bxtwc.o
 obj-$(CONFIG_CHT_WC_PMIC_OPREGION) += pmic/intel_pmic_chtwc.o
diff --git a/drivers/acpi/acpi_configfs.c b/drivers/acpi/acpi_configfs.c
index 57d9d574d4dd..ece8c1a921cc 100644
--- a/drivers/acpi/acpi_configfs.c
+++ b/drivers/acpi/acpi_configfs.c
@@ -53,7 +53,7 @@ static ssize_t acpi_table_aml_write(struct config_item *cfg,
 	if (!table->header)
 		return -ENOMEM;
 
-	ret = acpi_load_table(table->header);
+	ret = acpi_load_table(table->header, &table->index);
 	if (ret) {
 		kfree(table->header);
 		table->header = NULL;
@@ -223,7 +223,7 @@ static void acpi_table_drop_item(struct config_group *group,
 	struct acpi_table *table = container_of(cfg, struct acpi_table, cfg);
 
 	ACPI_INFO(("Host-directed Dynamic ACPI Table Unload"));
-	acpi_tb_unload_table(table->index);
+	acpi_unload_table(table->index);
 }
 
 static struct configfs_group_operations acpi_table_group_ops = {
diff --git a/drivers/acpi/acpi_lpss.c b/drivers/acpi/acpi_lpss.c
index 60bbc5090abe..70f740b09684 100644
--- a/drivers/acpi/acpi_lpss.c
+++ b/drivers/acpi/acpi_lpss.c
@@ -10,6 +10,7 @@
 #include <linux/acpi.h>
 #include <linux/clkdev.h>
 #include <linux/clk-provider.h>
+#include <linux/dmi.h>
 #include <linux/err.h>
 #include <linux/io.h>
 #include <linux/mutex.h>
@@ -463,6 +464,18 @@ struct lpss_device_links {
 	const char *consumer_hid;
 	const char *consumer_uid;
 	u32 flags;
+	const struct dmi_system_id *dep_missing_ids;
+};
+
+/* Please keep this list sorted alphabetically by vendor and model */
+static const struct dmi_system_id i2c1_dep_missing_dmi_ids[] = {
+	{
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
+			DMI_MATCH(DMI_PRODUCT_NAME, "T200TA"),
+		},
+	},
+	{}
 };
 
 /*
@@ -473,36 +486,29 @@ struct lpss_device_links {
  * the supplier is not enumerated until after the consumer is probed.
  */
 static const struct lpss_device_links lpss_device_links[] = {
+	/* CHT External sdcard slot controller depends on PMIC I2C ctrl */
 	{"808622C1", "7", "80860F14", "3", DL_FLAG_PM_RUNTIME},
+	/* CHT iGPU depends on PMIC I2C controller */
 	{"808622C1", "7", "LNXVIDEO", NULL, DL_FLAG_PM_RUNTIME},
+	/* BYT iGPU depends on the Embedded Controller I2C controller (UID 1) */
+	{"80860F41", "1", "LNXVIDEO", NULL, DL_FLAG_PM_RUNTIME,
+	 i2c1_dep_missing_dmi_ids},
+	/* BYT CR iGPU depends on PMIC I2C controller (UID 5 on CR) */
 	{"80860F41", "5", "LNXVIDEO", NULL, DL_FLAG_PM_RUNTIME},
+	/* BYT iGPU depends on PMIC I2C controller (UID 7 on non CR) */
+	{"80860F41", "7", "LNXVIDEO", NULL, DL_FLAG_PM_RUNTIME},
 };
 
-static bool hid_uid_match(struct acpi_device *adev,
-			  const char *hid2, const char *uid2)
-{
-	const char *hid1 = acpi_device_hid(adev);
-	const char *uid1 = acpi_device_uid(adev);
-
-	if (strcmp(hid1, hid2))
-		return false;
-
-	if (!uid2)
-		return true;
-
-	return uid1 && !strcmp(uid1, uid2);
-}
-
 static bool acpi_lpss_is_supplier(struct acpi_device *adev,
 				  const struct lpss_device_links *link)
 {
-	return hid_uid_match(adev, link->supplier_hid, link->supplier_uid);
+	return acpi_dev_hid_uid_match(adev, link->supplier_hid, link->supplier_uid);
 }
 
 static bool acpi_lpss_is_consumer(struct acpi_device *adev,
 				  const struct lpss_device_links *link)
 {
-	return hid_uid_match(adev, link->consumer_hid, link->consumer_uid);
+	return acpi_dev_hid_uid_match(adev, link->consumer_hid, link->consumer_uid);
 }
 
 struct hid_uid {
@@ -518,7 +524,7 @@ static int match_hid_uid(struct device *dev, const void *data)
 	if (!adev)
 		return 0;
 
-	return hid_uid_match(adev, id->hid, id->uid);
+	return acpi_dev_hid_uid_match(adev, id->hid, id->uid);
 }
 
 static struct device *acpi_lpss_find_device(const char *hid, const char *uid)
@@ -570,7 +576,8 @@ static void acpi_lpss_link_consumer(struct device *dev1,
 	if (!dev2)
 		return;
 
-	if (acpi_lpss_dep(ACPI_COMPANION(dev2), ACPI_HANDLE(dev1)))
+	if ((link->dep_missing_ids && dmi_check_system(link->dep_missing_ids))
+	    || acpi_lpss_dep(ACPI_COMPANION(dev2), ACPI_HANDLE(dev1)))
 		device_link_add(dev2, dev1, link->flags);
 
 	put_device(dev2);
@@ -585,7 +592,8 @@ static void acpi_lpss_link_supplier(struct device *dev1,
 	if (!dev2)
 		return;
 
-	if (acpi_lpss_dep(ACPI_COMPANION(dev1), ACPI_HANDLE(dev2)))
+	if ((link->dep_missing_ids && dmi_check_system(link->dep_missing_ids))
+	    || acpi_lpss_dep(ACPI_COMPANION(dev1), ACPI_HANDLE(dev2)))
 		device_link_add(dev1, dev2, link->flags);
 
 	put_device(dev2);
diff --git a/drivers/acpi/acpi_platform.c b/drivers/acpi/acpi_platform.c
index 00ec4f2bf015..c05050f474cd 100644
--- a/drivers/acpi/acpi_platform.c
+++ b/drivers/acpi/acpi_platform.c
@@ -31,6 +31,44 @@ static const struct acpi_device_id forbidden_id_list[] = {
 	{"", 0},
 };
 
+static struct platform_device *acpi_platform_device_find_by_companion(struct acpi_device *adev)
+{
+	struct device *dev;
+
+	dev = bus_find_device_by_acpi_dev(&platform_bus_type, adev);
+	return dev ? to_platform_device(dev) : NULL;
+}
+
+static int acpi_platform_device_remove_notify(struct notifier_block *nb,
+					      unsigned long value, void *arg)
+{
+	struct acpi_device *adev = arg;
+	struct platform_device *pdev;
+
+	switch (value) {
+	case ACPI_RECONFIG_DEVICE_ADD:
+		/* Nothing to do here */
+		break;
+	case ACPI_RECONFIG_DEVICE_REMOVE:
+		if (!acpi_device_enumerated(adev))
+			break;
+
+		pdev = acpi_platform_device_find_by_companion(adev);
+		if (!pdev)
+			break;
+
+		platform_device_unregister(pdev);
+		put_device(&pdev->dev);
+		break;
+	}
+
+	return NOTIFY_OK;
+}
+
+static struct notifier_block acpi_platform_notifier = {
+	.notifier_call = acpi_platform_device_remove_notify,
+};
+
 static void acpi_platform_fill_resource(struct acpi_device *adev,
 	const struct resource *src, struct resource *dest)
 {
@@ -130,3 +168,8 @@ struct platform_device *acpi_create_platform_device(struct acpi_device *adev,
 	return pdev;
 }
 EXPORT_SYMBOL_GPL(acpi_create_platform_device);
+
+void __init acpi_platform_init(void)
+{
+	acpi_reconfig_notifier_register(&acpi_platform_notifier);
+}
diff --git a/drivers/acpi/acpi_video.c b/drivers/acpi/acpi_video.c
index 4f325e47519f..2f380e7381d6 100644
--- a/drivers/acpi/acpi_video.c
+++ b/drivers/acpi/acpi_video.c
@@ -699,9 +699,13 @@ acpi_video_device_EDID(struct acpi_video_device *device,
  *			event notify code.
  *	lcd_flag	:
  *		0.	The system BIOS should automatically control the brightness level
- *			of the LCD when the power changes from AC to DC
+ *			of the LCD when:
+ *			- the power changes from AC to DC (ACPI appendix B)
+ *			- a brightness hotkey gets pressed (implied by Win7/8 backlight docs)
  *		1.	The system BIOS should NOT automatically control the brightness
- *			level of the LCD when the power changes from AC to DC.
+ *			level of the LCD when:
+ *			- the power changes from AC to DC (ACPI appendix B)
+ *			- a brightness hotkey gets pressed (implied by Win7/8 backlight docs)
  *  Return Value:
  *		-EINVAL	wrong arg.
  */
diff --git a/drivers/acpi/acpica/acdebug.h b/drivers/acpi/acpica/acdebug.h
index 32f2e38c7570..694cf206fa9a 100644
--- a/drivers/acpi/acpica/acdebug.h
+++ b/drivers/acpi/acpica/acdebug.h
@@ -148,6 +148,8 @@ void acpi_db_find_references(char *object_arg);
 
 void acpi_db_get_bus_info(void);
 
+acpi_status acpi_db_display_fields(u32 address_space_id);
+
 /*
  * dbdisply - debug display commands
  */
diff --git a/drivers/acpi/acpica/acstruct.h b/drivers/acpi/acpica/acstruct.h
index 218ff4c8b817..2043dff370b1 100644
--- a/drivers/acpi/acpica/acstruct.h
+++ b/drivers/acpi/acpica/acstruct.h
@@ -192,6 +192,16 @@ struct acpi_device_walk_info {
 	u32 num_INI;
 };
 
+/* Info used by Acpi  acpi_db_display_fields */
+
+struct acpi_region_walk_info {
+	u32 debug_level;
+	u32 count;
+	acpi_owner_id owner_id;
+	u8 display_type;
+	u32 address_space_id;
+};
+
 /* TBD: [Restructure] Merge with struct above */
 
 struct acpi_walk_info {
diff --git a/drivers/acpi/acpica/acutils.h b/drivers/acpi/acpica/acutils.h
index 601808be86d1..5fb50634e08e 100644
--- a/drivers/acpi/acpica/acutils.h
+++ b/drivers/acpi/acpica/acutils.h
@@ -142,10 +142,11 @@ struct acpi_pkg_info {
 
 /* acpi_ut_dump_buffer */
 
-#define DB_BYTE_DISPLAY     1
-#define DB_WORD_DISPLAY     2
-#define DB_DWORD_DISPLAY    4
-#define DB_QWORD_DISPLAY    8
+#define DB_BYTE_DISPLAY      0x01
+#define DB_WORD_DISPLAY      0x02
+#define DB_DWORD_DISPLAY     0x04
+#define DB_QWORD_DISPLAY     0x08
+#define DB_DISPLAY_DATA_ONLY 0x10
 
 /*
  * utascii - ASCII utilities
diff --git a/drivers/acpi/acpica/dbconvert.c b/drivers/acpi/acpica/dbconvert.c
index 9fd9a98a9cbe..2b84ac093698 100644
--- a/drivers/acpi/acpica/dbconvert.c
+++ b/drivers/acpi/acpica/dbconvert.c
@@ -106,6 +106,10 @@ acpi_db_convert_to_buffer(char *string, union acpi_object *object)
 	u8 *buffer;
 	acpi_status status;
 
+	/* Skip all preceding white space */
+
+	acpi_ut_remove_whitespace(&string);
+
 	/* Generate the final buffer length */
 
 	for (i = 0, length = 0; string[i];) {
diff --git a/drivers/acpi/acpica/dbdisply.c b/drivers/acpi/acpica/dbdisply.c
index 30ab62b0fec8..f2df416d0d2d 100644
--- a/drivers/acpi/acpica/dbdisply.c
+++ b/drivers/acpi/acpica/dbdisply.c
@@ -513,7 +513,6 @@ void acpi_db_display_results(void)
 		return;
 	}
 
-	obj_desc = walk_state->method_desc;
 	node = walk_state->method_node;
 
 	if (walk_state->results) {
@@ -565,7 +564,6 @@ void acpi_db_display_calling_tree(void)
 		return;
 	}
 
-	node = walk_state->method_node;
 	acpi_os_printf("Current Control Method Call Tree\n");
 
 	while (walk_state) {
diff --git a/drivers/acpi/acpica/dbfileio.c b/drivers/acpi/acpica/dbfileio.c
index c6e25734dc5c..e1b6e54a96ac 100644
--- a/drivers/acpi/acpica/dbfileio.c
+++ b/drivers/acpi/acpica/dbfileio.c
@@ -93,7 +93,7 @@ acpi_status acpi_db_load_tables(struct acpi_new_table_desc *list_head)
 	while (table_list_head) {
 		table = table_list_head->table;
 
-		status = acpi_load_table(table);
+		status = acpi_load_table(table, NULL);
 		if (ACPI_FAILURE(status)) {
 			if (status == AE_ALREADY_EXISTS) {
 				acpi_os_printf
diff --git a/drivers/acpi/acpica/dbinput.c b/drivers/acpi/acpica/dbinput.c
index 55a7e10998d8..e1632b340182 100644
--- a/drivers/acpi/acpica/dbinput.c
+++ b/drivers/acpi/acpica/dbinput.c
@@ -50,6 +50,7 @@ enum acpi_ex_debugger_commands {
 	CMD_EVALUATE,
 	CMD_EXECUTE,
 	CMD_EXIT,
+	CMD_FIELDS,
 	CMD_FIND,
 	CMD_GO,
 	CMD_HANDLERS,
@@ -127,6 +128,7 @@ static const struct acpi_db_command_info acpi_gbl_db_commands[] = {
 	{"EVALUATE", 1},
 	{"EXECUTE", 1},
 	{"EXIT", 0},
+	{"FIELDS", 1},
 	{"FIND", 1},
 	{"GO", 0},
 	{"HANDLERS", 0},
@@ -200,6 +202,8 @@ static const struct acpi_db_command_help acpi_gbl_db_command_help[] = {
 	 "Find ACPI name(s) with wildcards\n"},
 	{1, "  Integrity", "Validate namespace integrity\n"},
 	{1, "  Methods", "Display list of loaded control methods\n"},
+	{1, "  Fields <AddressSpaceId>",
+	 "Display list of loaded field units by space ID\n"},
 	{1, "  Namespace [Object] [Depth]",
 	 "Display loaded namespace tree/subtree\n"},
 	{1, "  Notify <Object> <Value>", "Send a notification on Object\n"},
@@ -507,6 +511,21 @@ char *acpi_db_get_next_token(char *string,
 		}
 		break;
 
+	case '{':
+
+		/* This is the start of a field unit, scan until closing brace */
+
+		string++;
+		start = string;
+		type = ACPI_TYPE_FIELD_UNIT;
+
+		/* Find end of buffer */
+
+		while (*string && (*string != '}')) {
+			string++;
+		}
+		break;
+
 	case '[':
 
 		/* This is the start of a package, scan until closing bracket */
@@ -674,6 +693,7 @@ acpi_db_command_dispatch(char *input_buffer,
 			 union acpi_parse_object *op)
 {
 	u32 temp;
+	u64 temp64;
 	u32 command_index;
 	u32 param_count;
 	char *command_line;
@@ -689,7 +709,6 @@ acpi_db_command_dispatch(char *input_buffer,
 
 	param_count = acpi_db_get_line(input_buffer);
 	command_index = acpi_db_match_command(acpi_gbl_db_args[0]);
-	temp = 0;
 
 	/*
 	 * We don't want to add the !! command to the history buffer. It
@@ -790,6 +809,21 @@ acpi_db_command_dispatch(char *input_buffer,
 		status = acpi_db_find_name_in_namespace(acpi_gbl_db_args[1]);
 		break;
 
+	case CMD_FIELDS:
+
+		status = acpi_ut_strtoul64(acpi_gbl_db_args[1], &temp64);
+
+		if (ACPI_FAILURE(status)
+		    || temp64 >= ACPI_NUM_PREDEFINED_REGIONS) {
+			acpi_os_printf
+			    ("Invalid adress space ID: must be between 0 and %u inclusive\n",
+			     ACPI_NUM_PREDEFINED_REGIONS - 1);
+			return (AE_OK);
+		}
+
+		status = acpi_db_display_fields((u32)temp64);
+		break;
+
 	case CMD_GO:
 
 		acpi_gbl_cm_single_step = FALSE;
diff --git a/drivers/acpi/acpica/dbmethod.c b/drivers/acpi/acpica/dbmethod.c
index 76a15b6ffc5d..4e48a7de7413 100644
--- a/drivers/acpi/acpica/dbmethod.c
+++ b/drivers/acpi/acpica/dbmethod.c
@@ -321,6 +321,10 @@ acpi_status acpi_db_disassemble_method(char *name)
 	walk_state->parse_flags |= ACPI_PARSE_DISASSEMBLE;
 
 	status = acpi_ps_parse_aml(walk_state);
+	if (ACPI_FAILURE(status)) {
+		return (status);
+	}
+
 	(void)acpi_dm_parse_deferred_ops(op);
 
 	/* Now we can disassemble the method */
diff --git a/drivers/acpi/acpica/dbnames.c b/drivers/acpi/acpica/dbnames.c
index 63fe30e86807..3615e1a6efd8 100644
--- a/drivers/acpi/acpica/dbnames.c
+++ b/drivers/acpi/acpica/dbnames.c
@@ -10,6 +10,7 @@
 #include "acnamesp.h"
 #include "acdebug.h"
 #include "acpredef.h"
+#include "acinterp.h"
 
 #define _COMPONENT          ACPI_CA_DEBUGGER
 ACPI_MODULE_NAME("dbnames")
@@ -504,6 +505,86 @@ acpi_db_walk_for_object_counts(acpi_handle obj_handle,
 
 /*******************************************************************************
  *
+ * FUNCTION:    acpi_db_walk_for_fields
+ *
+ * PARAMETERS:  Callback from walk_namespace
+ *
+ * RETURN:      Status
+ *
+ * DESCRIPTION: Display short info about objects in the namespace
+ *
+ ******************************************************************************/
+
+static acpi_status
+acpi_db_walk_for_fields(acpi_handle obj_handle,
+			u32 nesting_level, void *context, void **return_value)
+{
+	union acpi_object *ret_value;
+	struct acpi_region_walk_info *info =
+	    (struct acpi_region_walk_info *)context;
+	struct acpi_buffer buffer;
+	acpi_status status;
+	struct acpi_namespace_node *node = acpi_ns_validate_handle(obj_handle);
+
+	if (!node) {
+		return (AE_OK);
+	}
+	if (node->object->field.region_obj->region.space_id !=
+	    info->address_space_id) {
+		return (AE_OK);
+	}
+
+	info->count++;
+
+	/* Get and display the full pathname to this object */
+
+	buffer.length = ACPI_ALLOCATE_LOCAL_BUFFER;
+	status = acpi_ns_handle_to_pathname(obj_handle, &buffer, TRUE);
+	if (ACPI_FAILURE(status)) {
+		acpi_os_printf("Could Not get pathname for object %p\n",
+			       obj_handle);
+		return (AE_OK);
+	}
+
+	acpi_os_printf("%s ", (char *)buffer.pointer);
+	ACPI_FREE(buffer.pointer);
+
+	buffer.length = ACPI_ALLOCATE_LOCAL_BUFFER;
+	acpi_evaluate_object(obj_handle, NULL, NULL, &buffer);
+
+	/*
+	 * Since this is a field unit, surround the output in braces
+	 */
+	acpi_os_printf("{");
+
+	ret_value = (union acpi_object *)buffer.pointer;
+	switch (ret_value->type) {
+	case ACPI_TYPE_INTEGER:
+
+		acpi_os_printf("%8.8X%8.8X",
+			       ACPI_FORMAT_UINT64(ret_value->integer.value));
+		break;
+
+	case ACPI_TYPE_BUFFER:
+
+		acpi_ut_dump_buffer(ret_value->buffer.pointer,
+				    ret_value->buffer.length,
+				    DB_DISPLAY_DATA_ONLY | DB_BYTE_DISPLAY, 0);
+		break;
+
+	default:
+
+		break;
+	}
+	acpi_os_printf("}\n");
+
+	ACPI_FREE(buffer.pointer);
+
+	return (AE_OK);
+}
+
+/*******************************************************************************
+ *
  * FUNCTION:    acpi_db_walk_for_specific_objects
  *
  * PARAMETERS:  Callback from walk_namespace
@@ -630,6 +711,39 @@ acpi_status acpi_db_display_objects(char *obj_type_arg, char *display_count_arg)
 
 /*******************************************************************************
  *
+ * FUNCTION:    acpi_db_display_fields
+ *
+ * PARAMETERS:  obj_type_arg        - Type of object to display
+ *              display_count_arg   - Max depth to display
+ *
+ * RETURN:      None
+ *
+ * DESCRIPTION: Display objects in the namespace of the requested type
+ *
+ ******************************************************************************/
+
+acpi_status acpi_db_display_fields(u32 address_space_id)
+{
+	struct acpi_region_walk_info info;
+
+	info.count = 0;
+	info.owner_id = ACPI_OWNER_ID_MAX;
+	info.debug_level = ACPI_UINT32_MAX;
+	info.display_type = ACPI_DISPLAY_SUMMARY | ACPI_DISPLAY_SHORT;
+	info.address_space_id = address_space_id;
+
+	/* Walk the namespace from the root */
+
+	(void)acpi_walk_namespace(ACPI_TYPE_LOCAL_REGION_FIELD,
+				  ACPI_ROOT_OBJECT, ACPI_UINT32_MAX,
+				  acpi_db_walk_for_fields, NULL, (void *)&info,
+				  NULL);
+
+	return (AE_OK);
+}
+
+/*******************************************************************************
+ *
  * FUNCTION:    acpi_db_integrity_walk
  *
  * PARAMETERS:  Callback from walk_namespace
diff --git a/drivers/acpi/acpica/dbobject.c b/drivers/acpi/acpica/dbobject.c
index f9fc84bc3e84..4b4c530a0654 100644
--- a/drivers/acpi/acpica/dbobject.c
+++ b/drivers/acpi/acpica/dbobject.c
@@ -464,7 +464,6 @@ void acpi_db_decode_arguments(struct acpi_walk_state *walk_state)
 	u8 display_args = FALSE;
 
 	node = walk_state->method_node;
-	obj_desc = walk_state->method_desc;
 
 	/* There are no arguments for the module-level code case */
 
diff --git a/drivers/acpi/acpica/dscontrol.c b/drivers/acpi/acpica/dscontrol.c
index 4847f89c678c..5034fab9cf69 100644
--- a/drivers/acpi/acpica/dscontrol.c
+++ b/drivers/acpi/acpica/dscontrol.c
@@ -85,7 +85,7 @@ acpi_ds_exec_begin_control_op(struct acpi_walk_state *walk_state,
 		    walk_state->parser_state.pkg_end;
 		control_state->control.opcode = op->common.aml_opcode;
 		control_state->control.loop_timeout = acpi_os_get_timer() +
-		    (u64)(acpi_gbl_max_loop_iterations * ACPI_100NSEC_PER_SEC);
+		    ((u64)acpi_gbl_max_loop_iterations * ACPI_100NSEC_PER_SEC);
 
 		/* Push the control state on this walk's control stack */
 
diff --git a/drivers/acpi/acpica/dsfield.c b/drivers/acpi/acpica/dsfield.c
index cf4e061bb0f0..faa38a22263a 100644
--- a/drivers/acpi/acpica/dsfield.c
+++ b/drivers/acpi/acpica/dsfield.c
@@ -149,7 +149,6 @@ acpi_ds_create_buffer_field(union acpi_parse_object *op,
 
 	if (walk_state->deferred_node) {
 		node = walk_state->deferred_node;
-		status = AE_OK;
 	} else {
 		/* Execute flag should always be set when this function is entered */
 
@@ -264,7 +263,6 @@ acpi_ds_get_field_names(struct acpi_create_field_info *info,
 	union acpi_parse_object *child;
 
 #ifdef ACPI_EXEC_APP
-	u64 value = 0;
 	union acpi_operand_object *result_desc;
 	union acpi_operand_object *obj_desc;
 	char *name_path;
@@ -406,19 +404,17 @@ acpi_ds_get_field_names(struct acpi_create_field_info *info,
 					name_path =
 					    acpi_ns_get_external_pathname(info->
 									  field_node);
-					obj_desc =
-					    acpi_ut_create_integer_object
-					    (value);
 					if (ACPI_SUCCESS
 					    (ae_lookup_init_file_entry
-					     (name_path, &value))) {
+					     (name_path, &obj_desc))) {
 						acpi_ex_write_data_to_field
 						    (obj_desc,
 						     acpi_ns_get_attached_object
 						     (info->field_node),
 						     &result_desc);
+						acpi_ut_remove_reference
+						    (obj_desc);
 					}
-					acpi_ut_remove_reference(obj_desc);
 					ACPI_FREE(name_path);
 #endif
 				}
@@ -636,8 +632,6 @@ acpi_ds_init_field_objects(union acpi_parse_object *op,
 				}
 
 				/* Name already exists, just ignore this error */
-
-				status = AE_OK;
 			}
 
 			arg->common.node = node;
diff --git a/drivers/acpi/acpica/evgpeblk.c b/drivers/acpi/acpica/evgpeblk.c
index fb15e9e2373b..9c7adaa7b582 100644
--- a/drivers/acpi/acpica/evgpeblk.c
+++ b/drivers/acpi/acpica/evgpeblk.c
@@ -110,6 +110,9 @@ acpi_status acpi_ev_delete_gpe_block(struct acpi_gpe_block_info *gpe_block)
 
 	status =
 	    acpi_hw_disable_gpe_block(gpe_block->xrupt_block, gpe_block, NULL);
+	if (ACPI_FAILURE(status)) {
+		return_ACPI_STATUS(status);
+	}
 
 	if (!gpe_block->previous && !gpe_block->next) {
 
@@ -359,10 +362,10 @@ acpi_ev_create_gpe_block(struct acpi_namespace_node *gpe_device,
 	walk_info.gpe_device = gpe_device;
 	walk_info.execute_by_owner_id = FALSE;
 
-	status = acpi_ns_walk_namespace(ACPI_TYPE_METHOD, gpe_device,
-					ACPI_UINT32_MAX, ACPI_NS_WALK_NO_UNLOCK,
-					acpi_ev_match_gpe_method, NULL,
-					&walk_info, NULL);
+	(void)acpi_ns_walk_namespace(ACPI_TYPE_METHOD, gpe_device,
+				     ACPI_UINT32_MAX, ACPI_NS_WALK_NO_UNLOCK,
+				     acpi_ev_match_gpe_method, NULL, &walk_info,
+				     NULL);
 
 	/* Return the new block */
 
diff --git a/drivers/acpi/acpica/evgpeinit.c b/drivers/acpi/acpica/evgpeinit.c
index b04f982e59fa..70d21d5ec5f3 100644
--- a/drivers/acpi/acpica/evgpeinit.c
+++ b/drivers/acpi/acpica/evgpeinit.c
@@ -156,8 +156,6 @@ acpi_status acpi_ev_gpe_initialize(void)
 			 * GPE0 and GPE1 do not have to be contiguous in the GPE number
 			 * space. However, GPE0 always starts at GPE number zero.
 			 */
-			gpe_number_max = acpi_gbl_FADT.gpe1_base +
-			    ((register_count1 * ACPI_GPE_REGISTER_WIDTH) - 1);
 		}
 	}
 
@@ -169,7 +167,6 @@ acpi_status acpi_ev_gpe_initialize(void)
 
 		ACPI_DEBUG_PRINT((ACPI_DB_INIT,
 				  "There are no GPE blocks defined in the FADT\n"));
-		status = AE_OK;
 		goto cleanup;
 	}
 
diff --git a/drivers/acpi/acpica/evmisc.c b/drivers/acpi/acpica/evmisc.c
index d45f7639f7ee..aa98fe07cd1b 100644
--- a/drivers/acpi/acpica/evmisc.c
+++ b/drivers/acpi/acpica/evmisc.c
@@ -230,11 +230,15 @@ void acpi_ev_terminate(void)
 		/* Disable all GPEs in all GPE blocks */
 
 		status = acpi_ev_walk_gpe_list(acpi_hw_disable_gpe_block, NULL);
+		if (ACPI_FAILURE(status)) {
+			ACPI_EXCEPTION((AE_INFO, status,
+					"Could not disable GPEs in GPE block"));
+		}
 
 		status = acpi_ev_remove_global_lock_handler();
 		if (ACPI_FAILURE(status)) {
-			ACPI_ERROR((AE_INFO,
-				    "Could not remove Global Lock handler"));
+			ACPI_EXCEPTION((AE_INFO, status,
+					"Could not remove Global Lock handler"));
 		}
 
 		acpi_gbl_events_initialized = FALSE;
@@ -250,6 +254,10 @@ void acpi_ev_terminate(void)
 	/* Deallocate all handler objects installed within GPE info structs */
 
 	status = acpi_ev_walk_gpe_list(acpi_ev_delete_gpe_handlers, NULL);
+	if (ACPI_FAILURE(status)) {
+		ACPI_EXCEPTION((AE_INFO, status,
+				"Could not delete GPE handlers"));
+	}
 
 	/* Return to original mode if necessary */
 
diff --git a/drivers/acpi/acpica/evregion.c b/drivers/acpi/acpica/evregion.c
index 45dc797df05d..1ff126460007 100644
--- a/drivers/acpi/acpica/evregion.c
+++ b/drivers/acpi/acpica/evregion.c
@@ -836,11 +836,11 @@ acpi_ev_orphan_ec_reg_method(struct acpi_namespace_node *ec_device_node)
 	objects[1].type = ACPI_TYPE_INTEGER;
 	objects[1].integer.value = ACPI_REG_CONNECT;
 
-	status = acpi_evaluate_object(reg_method, NULL, &args, NULL);
+	(void)acpi_evaluate_object(reg_method, NULL, &args, NULL);
 
 exit:
 	/* We ignore all errors from above, don't care */
 
-	status = acpi_ut_acquire_mutex(ACPI_MTX_NAMESPACE);
+	(void)acpi_ut_acquire_mutex(ACPI_MTX_NAMESPACE);
 	return_VOID;
 }
diff --git a/drivers/acpi/acpica/evrgnini.c b/drivers/acpi/acpica/evrgnini.c
index 0b47bbcd2a23..aee09640d710 100644
--- a/drivers/acpi/acpica/evrgnini.c
+++ b/drivers/acpi/acpica/evrgnini.c
@@ -198,7 +198,6 @@ acpi_ev_pci_config_region_setup(acpi_handle handle,
 						 * root bridge. Still need to return a context object
 						 * for the new PCI_Config operation region, however.
 						 */
-						status = AE_OK;
 					} else {
 						ACPI_EXCEPTION((AE_INFO, status,
 								"Could not install PciConfig handler "
diff --git a/drivers/acpi/acpica/hwxfsleep.c b/drivers/acpi/acpica/hwxfsleep.c
index abbf9702aa7f..2919746c9041 100644
--- a/drivers/acpi/acpica/hwxfsleep.c
+++ b/drivers/acpi/acpica/hwxfsleep.c
@@ -166,6 +166,9 @@ acpi_status acpi_enter_sleep_state_s4bios(void)
 
 	status = acpi_hw_write_port(acpi_gbl_FADT.smi_command,
 				    (u32)acpi_gbl_FADT.s4_bios_request, 8);
+	if (ACPI_FAILURE(status)) {
+		return_ACPI_STATUS(status);
+	}
 
 	do {
 		acpi_os_stall(ACPI_USEC_PER_MSEC);
diff --git a/drivers/acpi/acpica/nsconvert.c b/drivers/acpi/acpica/nsconvert.c
index 14cbf63f1991..c86d0770ed6e 100644
--- a/drivers/acpi/acpica/nsconvert.c
+++ b/drivers/acpi/acpica/nsconvert.c
@@ -486,5 +486,5 @@ acpi_ns_convert_to_reference(struct acpi_namespace_node *scope,
 error_exit:
 	ACPI_FREE(name);
 	*return_object = new_object;
-	return (AE_OK);
+	return (status);
 }
diff --git a/drivers/acpi/acpica/nsdump.c b/drivers/acpi/acpica/nsdump.c
index 9731d7cf1b83..9ad340f644a1 100644
--- a/drivers/acpi/acpica/nsdump.c
+++ b/drivers/acpi/acpica/nsdump.c
@@ -291,7 +291,7 @@ acpi_ns_dump_one_object(acpi_handle obj_handle,
 					for (i = 0;
 					     (i < obj_desc->buffer.length
 					      && i < 12); i++) {
-						acpi_os_printf(" %.2hX",
+						acpi_os_printf(" %2.2X",
 							       obj_desc->buffer.
 							       pointer[i]);
 					}
@@ -404,7 +404,7 @@ acpi_ns_dump_one_object(acpi_handle obj_handle,
 		case ACPI_TYPE_LOCAL_BANK_FIELD:
 		case ACPI_TYPE_LOCAL_INDEX_FIELD:
 
-			acpi_os_printf(" Off %.3X Len %.2X Acc %.2hd\n",
+			acpi_os_printf(" Off %.3X Len %.2X Acc %.2X\n",
 				       (obj_desc->common_field.
 					base_byte_offset * 8)
 				       +
@@ -589,8 +589,6 @@ acpi_ns_dump_one_object(acpi_handle obj_handle,
 
 			goto cleanup;
 		}
-
-		obj_type = ACPI_TYPE_INVALID;	/* Terminate loop after next pass */
 	}
 
 cleanup:
diff --git a/drivers/acpi/acpica/nsxfname.c b/drivers/acpi/acpica/nsxfname.c
index 55b4a5b3331f..161e60ddfb69 100644
--- a/drivers/acpi/acpica/nsxfname.c
+++ b/drivers/acpi/acpica/nsxfname.c
@@ -425,8 +425,8 @@ acpi_get_object_info(acpi_handle handle,
 	}
 
 	if (cls) {
-		next_id_string = acpi_ns_copy_device_id(&info->class_code,
-							cls, next_id_string);
+		(void)acpi_ns_copy_device_id(&info->class_code,
+					     cls, next_id_string);
 	}
 
 	/* Copy the fixed-length data */
diff --git a/drivers/acpi/acpica/psobject.c b/drivers/acpi/acpica/psobject.c
index 98e5c7400e54..ded2779fc8ea 100644
--- a/drivers/acpi/acpica/psobject.c
+++ b/drivers/acpi/acpica/psobject.c
@@ -481,8 +481,7 @@ acpi_ps_complete_op(struct acpi_walk_state *walk_state,
 			walk_state->opcode = (*op)->common.aml_opcode;
 
 			status = walk_state->ascending_callback(walk_state);
-			status =
-			    acpi_ps_next_parse_state(walk_state, *op, status);
+			(void)acpi_ps_next_parse_state(walk_state, *op, status);
 
 			status2 = acpi_ps_complete_this_op(walk_state, *op);
 			if (ACPI_FAILURE(status2)) {
@@ -490,7 +489,6 @@ acpi_ps_complete_op(struct acpi_walk_state *walk_state,
 			}
 		}
 
-		status = AE_OK;
 		break;
 
 	case AE_CTRL_BREAK:
@@ -512,14 +510,13 @@ acpi_ps_complete_op(struct acpi_walk_state *walk_state,
 		walk_state->opcode = (*op)->common.aml_opcode;
 
 		status = walk_state->ascending_callback(walk_state);
-		status = acpi_ps_next_parse_state(walk_state, *op, status);
+		(void)acpi_ps_next_parse_state(walk_state, *op, status);
 
 		status2 = acpi_ps_complete_this_op(walk_state, *op);
 		if (ACPI_FAILURE(status2)) {
 			return_ACPI_STATUS(status2);
 		}
 
-		status = AE_OK;
 		break;
 
 	case AE_CTRL_TERMINATE:
diff --git a/drivers/acpi/acpica/rscreate.c b/drivers/acpi/acpica/rscreate.c
index 570ea0df8a1b..c659b54985a5 100644
--- a/drivers/acpi/acpica/rscreate.c
+++ b/drivers/acpi/acpica/rscreate.c
@@ -312,6 +312,9 @@ acpi_rs_create_pci_routing_table(union acpi_operand_object *package_object,
 				path_buffer.pointer = user_prt->source;
 
 				status = acpi_ns_handle_to_pathname((acpi_handle)node, &path_buffer, FALSE);
+				if (ACPI_FAILURE(status)) {
+					return_ACPI_STATUS(status);
+				}
 
 				/* +1 to include null terminator */
 
diff --git a/drivers/acpi/acpica/tbdata.c b/drivers/acpi/acpica/tbdata.c
index 309440010ab2..2cf36451e46f 100644
--- a/drivers/acpi/acpica/tbdata.c
+++ b/drivers/acpi/acpica/tbdata.c
@@ -933,6 +933,9 @@ acpi_tb_load_table(u32 table_index, struct acpi_namespace_node *parent_node)
 	}
 
 	status = acpi_ns_load_table(table_index, parent_node);
+	if (ACPI_FAILURE(status)) {
+		return_ACPI_STATUS(status);
+	}
 
 	/*
 	 * Update GPEs for any new _Lxx/_Exx methods. Ignore errors. The host is
diff --git a/drivers/acpi/acpica/tbxfload.c b/drivers/acpi/acpica/tbxfload.c
index 86f1693f6d29..0782acf85722 100644
--- a/drivers/acpi/acpica/tbxfload.c
+++ b/drivers/acpi/acpica/tbxfload.c
@@ -268,6 +268,8 @@ ACPI_EXPORT_SYMBOL_INIT(acpi_install_table)
  *
  * PARAMETERS:  table               - Pointer to a buffer containing the ACPI
  *                                    table to be loaded.
+ *              table_idx           - Pointer to a u32 for storing the table
+ *                                    index, might be NULL
  *
  * RETURN:      Status
  *
@@ -278,7 +280,7 @@ ACPI_EXPORT_SYMBOL_INIT(acpi_install_table)
  *              to ensure that the table is not deleted or unmapped.
  *
  ******************************************************************************/
-acpi_status acpi_load_table(struct acpi_table_header *table)
+acpi_status acpi_load_table(struct acpi_table_header *table, u32 *table_idx)
 {
 	acpi_status status;
 	u32 table_index;
@@ -297,6 +299,10 @@ acpi_status acpi_load_table(struct acpi_table_header *table)
 	status = acpi_tb_install_and_load_table(ACPI_PTR_TO_PHYSADDR(table),
 						ACPI_TABLE_ORIGIN_EXTERNAL_VIRTUAL,
 						FALSE, &table_index);
+	if (table_idx) {
+		*table_idx = table_index;
+	}
+
 	if (ACPI_SUCCESS(status)) {
 
 		/* Complete the initialization/resolution of new objects */
@@ -390,3 +396,35 @@ acpi_status acpi_unload_parent_table(acpi_handle object)
 }
 
 ACPI_EXPORT_SYMBOL(acpi_unload_parent_table)
+/*******************************************************************************
+ *
+ * FUNCTION:    acpi_unload_table
+ *
+ * PARAMETERS:  table_index         - Index as returned by acpi_load_table
+ *
+ * RETURN:      Status
+ *
+ * DESCRIPTION: Via the table_index representing an SSDT or OEMx table, unloads
+ *              the table and deletes all namespace objects associated with
+ *              that table. Unloading of the DSDT is not allowed.
+ *              Note: Mainly intended to support hotplug removal of SSDTs.
+ *
+ ******************************************************************************/
+acpi_status acpi_unload_table(u32 table_index)
+{
+	acpi_status status;
+
+	ACPI_FUNCTION_TRACE(acpi_unload_table);
+
+	if (table_index == 1) {
+
+		/* table_index==1 means DSDT is the owner. DSDT cannot be unloaded */
+
+		return_ACPI_STATUS(AE_TYPE);
+	}
+
+	status = acpi_tb_unload_table(table_index);
+	return_ACPI_STATUS(status);
+}
+
+ACPI_EXPORT_SYMBOL(acpi_unload_table)
diff --git a/drivers/acpi/acpica/utbuffer.c b/drivers/acpi/acpica/utbuffer.c
index 61db9967ebe4..db897af1de05 100644
--- a/drivers/acpi/acpica/utbuffer.c
+++ b/drivers/acpi/acpica/utbuffer.c
@@ -37,7 +37,9 @@ void acpi_ut_dump_buffer(u8 *buffer, u32 count, u32 display, u32 base_offset)
 	u32 j;
 	u32 temp32;
 	u8 buf_char;
+	u32 display_data_only = display & DB_DISPLAY_DATA_ONLY;
 
+	display &= ~DB_DISPLAY_DATA_ONLY;
 	if (!buffer) {
 		acpi_os_printf("Null Buffer Pointer in DumpBuffer!\n");
 		return;
@@ -53,7 +55,9 @@ void acpi_ut_dump_buffer(u8 *buffer, u32 count, u32 display, u32 base_offset)
 
 		/* Print current offset */
 
-		acpi_os_printf("%8.4X: ", (base_offset + i));
+		if (!display_data_only) {
+			acpi_os_printf("%8.4X: ", (base_offset + i));
+		}
 
 		/* Print 16 hex chars */
 
@@ -109,32 +113,34 @@ void acpi_ut_dump_buffer(u8 *buffer, u32 count, u32 display, u32 base_offset)
 		 * Print the ASCII equivalent characters but watch out for the bad
 		 * unprintable ones (printable chars are 0x20 through 0x7E)
 		 */
-		acpi_os_printf(" ");
-		for (j = 0; j < 16; j++) {
-			if (i + j >= count) {
-				acpi_os_printf("\n");
-				return;
+		if (!display_data_only) {
+			acpi_os_printf(" ");
+			for (j = 0; j < 16; j++) {
+				if (i + j >= count) {
+					acpi_os_printf("\n");
+					return;
+				}
+
+				/*
+				 * Add comment characters so rest of line is ignored when
+				 * compiled
+				 */
+				if (j == 0) {
+					acpi_os_printf("// ");
+				}
+
+				buf_char = buffer[(acpi_size)i + j];
+				if (isprint(buf_char)) {
+					acpi_os_printf("%c", buf_char);
+				} else {
+					acpi_os_printf(".");
+				}
 			}
 
-			/*
-			 * Add comment characters so rest of line is ignored when
-			 * compiled
-			 */
-			if (j == 0) {
-				acpi_os_printf("// ");
-			}
+			/* Done with that line. */
 
-			buf_char = buffer[(acpi_size)i + j];
-			if (isprint(buf_char)) {
-				acpi_os_printf("%c", buf_char);
-			} else {
-				acpi_os_printf(".");
-			}
+			acpi_os_printf("\n");
 		}
-
-		/* Done with that line. */
-
-		acpi_os_printf("\n");
 		i += 16;
 	}
 
diff --git a/drivers/acpi/acpica/utids.c b/drivers/acpi/acpica/utids.c
index e805abdd95b8..30198c828ab6 100644
--- a/drivers/acpi/acpica/utids.c
+++ b/drivers/acpi/acpica/utids.c
@@ -289,9 +289,7 @@ acpi_ut_execute_CID(struct acpi_namespace_node *device_node,
 						  value);
 			length = ACPI_EISAID_STRING_SIZE;
 		} else {	/* ACPI_TYPE_STRING */
-
 			/* Copy the String CID from the returned object */
-
 			strcpy(next_id_string, cid_objects[i]->string.pointer);
 			length = cid_objects[i]->string.length + 1;
 		}
diff --git a/drivers/acpi/acpica/uttrack.c b/drivers/acpi/acpica/uttrack.c
index 8052f7ef5025..14de4d15e618 100644
--- a/drivers/acpi/acpica/uttrack.c
+++ b/drivers/acpi/acpica/uttrack.c
@@ -660,7 +660,7 @@ void acpi_ut_dump_allocations(u32 component, const char *module)
 					case ACPI_DESC_TYPE_PARSER:
 
 						acpi_os_printf
-						    ("AmlOpcode 0x%04hX\n",
+						    ("AmlOpcode 0x%04X\n",
 						     descriptor->op.asl.
 						     aml_opcode);
 						break;
diff --git a/drivers/acpi/button.c b/drivers/acpi/button.c
index 4a2cde2c536a..d27b01c0323d 100644
--- a/drivers/acpi/button.c
+++ b/drivers/acpi/button.c
@@ -44,9 +44,19 @@
 #define ACPI_BUTTON_DEVICE_NAME_LID	"Lid Switch"
 #define ACPI_BUTTON_TYPE_LID		0x05
 
-#define ACPI_BUTTON_LID_INIT_IGNORE	0x00
-#define ACPI_BUTTON_LID_INIT_OPEN	0x01
-#define ACPI_BUTTON_LID_INIT_METHOD	0x02
+enum {
+	ACPI_BUTTON_LID_INIT_IGNORE,
+	ACPI_BUTTON_LID_INIT_OPEN,
+	ACPI_BUTTON_LID_INIT_METHOD,
+	ACPI_BUTTON_LID_INIT_DISABLED,
+};
+
+static const char * const lid_init_state_str[] = {
+	[ACPI_BUTTON_LID_INIT_IGNORE]		= "ignore",
+	[ACPI_BUTTON_LID_INIT_OPEN]		= "open",
+	[ACPI_BUTTON_LID_INIT_METHOD]		= "method",
+	[ACPI_BUTTON_LID_INIT_DISABLED]		= "disabled",
+};
 
 #define _COMPONENT		ACPI_BUTTON_COMPONENT
 ACPI_MODULE_NAME("button");
@@ -65,18 +75,39 @@ static const struct acpi_device_id button_device_ids[] = {
 };
 MODULE_DEVICE_TABLE(acpi, button_device_ids);
 
-/*
- * Some devices which don't even have a lid in anyway have a broken _LID
- * method (e.g. pointing to a floating gpio pin) causing spurious LID events.
- */
-static const struct dmi_system_id lid_blacklst[] = {
+/* Please keep this list sorted alphabetically by vendor and model */
+static const struct dmi_system_id dmi_lid_quirks[] = {
+	{
+		/*
+		 * Asus T200TA, _LID keeps reporting closed after every second
+		 * openening of the lid. Causing immediate re-suspend after
+		 * opening every other open. Using LID_INIT_OPEN fixes this.
+		 */
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
+			DMI_MATCH(DMI_PRODUCT_NAME, "T200TA"),
+		},
+		.driver_data = (void *)(long)ACPI_BUTTON_LID_INIT_OPEN,
+	},
 	{
-		/* GP-electronic T701 */
+		/* GP-electronic T701, _LID method points to a floating GPIO */
 		.matches = {
 			DMI_MATCH(DMI_SYS_VENDOR, "Insyde"),
 			DMI_MATCH(DMI_PRODUCT_NAME, "T701"),
 			DMI_MATCH(DMI_BIOS_VERSION, "BYT70A.YNCHENG.WIN.007"),
 		},
+		.driver_data = (void *)(long)ACPI_BUTTON_LID_INIT_DISABLED,
+	},
+	{
+		/*
+		 * Medion Akoya E2215T, notification of the LID device only
+		 * happens on close, not on open and _LID always returns closed.
+		 */
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "MEDION"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "E2215T MD60198"),
+		},
+		.driver_data = (void *)(long)ACPI_BUTTON_LID_INIT_OPEN,
 	},
 	{}
 };
@@ -116,9 +147,8 @@ struct acpi_button {
 	bool suspended;
 };
 
-static BLOCKING_NOTIFIER_HEAD(acpi_lid_notifier);
 static struct acpi_device *lid_device;
-static u8 lid_init_state = ACPI_BUTTON_LID_INIT_METHOD;
+static long lid_init_state = -1;
 
 static unsigned long lid_report_interval __read_mostly = 500;
 module_param(lid_report_interval, ulong, 0644);
@@ -146,7 +176,6 @@ static int acpi_lid_evaluate_state(struct acpi_device *device)
 static int acpi_lid_notify_state(struct acpi_device *device, int state)
 {
 	struct acpi_button *button = acpi_driver_data(device);
-	int ret;
 	ktime_t next_report;
 	bool do_update;
 
@@ -223,18 +252,7 @@ static int acpi_lid_notify_state(struct acpi_device *device, int state)
 		button->last_time = ktime_get();
 	}
 
-	ret = blocking_notifier_call_chain(&acpi_lid_notifier, state, device);
-	if (ret == NOTIFY_DONE)
-		ret = blocking_notifier_call_chain(&acpi_lid_notifier, state,
-						   device);
-	if (ret == NOTIFY_DONE || ret == NOTIFY_OK) {
-		/*
-		 * It is also regarded as success if the notifier_chain
-		 * returns NOTIFY_OK or NOTIFY_DONE.
-		 */
-		ret = 0;
-	}
-	return ret;
+	return 0;
 }
 
 static int __maybe_unused acpi_button_state_seq_show(struct seq_file *seq,
@@ -331,18 +349,6 @@ static int acpi_button_remove_fs(struct acpi_device *device)
 /* --------------------------------------------------------------------------
                                 Driver Interface
    -------------------------------------------------------------------------- */
-int acpi_lid_notifier_register(struct notifier_block *nb)
-{
-	return blocking_notifier_chain_register(&acpi_lid_notifier, nb);
-}
-EXPORT_SYMBOL(acpi_lid_notifier_register);
-
-int acpi_lid_notifier_unregister(struct notifier_block *nb)
-{
-	return blocking_notifier_chain_unregister(&acpi_lid_notifier, nb);
-}
-EXPORT_SYMBOL(acpi_lid_notifier_unregister);
-
 int acpi_lid_open(void)
 {
 	if (!lid_device)
@@ -472,7 +478,8 @@ static int acpi_button_add(struct acpi_device *device)
 	char *name, *class;
 	int error;
 
-	if (!strcmp(hid, ACPI_BUTTON_HID_LID) && dmi_check_system(lid_blacklst))
+	if (!strcmp(hid, ACPI_BUTTON_HID_LID) &&
+	     lid_init_state == ACPI_BUTTON_LID_INIT_DISABLED)
 		return -ENODEV;
 
 	button = kzalloc(sizeof(struct acpi_button), GFP_KERNEL);
@@ -578,36 +585,30 @@ static int acpi_button_remove(struct acpi_device *device)
 static int param_set_lid_init_state(const char *val,
 				    const struct kernel_param *kp)
 {
-	int result = 0;
-
-	if (!strncmp(val, "open", sizeof("open") - 1)) {
-		lid_init_state = ACPI_BUTTON_LID_INIT_OPEN;
-		pr_info("Notify initial lid state as open\n");
-	} else if (!strncmp(val, "method", sizeof("method") - 1)) {
-		lid_init_state = ACPI_BUTTON_LID_INIT_METHOD;
-		pr_info("Notify initial lid state with _LID return value\n");
-	} else if (!strncmp(val, "ignore", sizeof("ignore") - 1)) {
-		lid_init_state = ACPI_BUTTON_LID_INIT_IGNORE;
-		pr_info("Do not notify initial lid state\n");
-	} else
-		result = -EINVAL;
-	return result;
+	int i;
+
+	i = sysfs_match_string(lid_init_state_str, val);
+	if (i < 0)
+		return i;
+
+	lid_init_state = i;
+	pr_info("Initial lid state set to '%s'\n", lid_init_state_str[i]);
+	return 0;
 }
 
-static int param_get_lid_init_state(char *buffer,
-				    const struct kernel_param *kp)
+static int param_get_lid_init_state(char *buf, const struct kernel_param *kp)
 {
-	switch (lid_init_state) {
-	case ACPI_BUTTON_LID_INIT_OPEN:
-		return sprintf(buffer, "open");
-	case ACPI_BUTTON_LID_INIT_METHOD:
-		return sprintf(buffer, "method");
-	case ACPI_BUTTON_LID_INIT_IGNORE:
-		return sprintf(buffer, "ignore");
-	default:
-		return sprintf(buffer, "invalid");
-	}
-	return 0;
+	int i, c = 0;
+
+	for (i = 0; i < ARRAY_SIZE(lid_init_state_str); i++)
+		if (i == lid_init_state)
+			c += sprintf(buf + c, "[%s] ", lid_init_state_str[i]);
+		else
+			c += sprintf(buf + c, "%s ", lid_init_state_str[i]);
+
+	buf[c - 1] = '\n'; /* Replace the final space with a newline */
+
+	return c;
 }
 
 module_param_call(lid_init_state,
@@ -617,6 +618,16 @@ MODULE_PARM_DESC(lid_init_state, "Behavior for reporting LID initial state");
 
 static int acpi_button_register_driver(struct acpi_driver *driver)
 {
+	const struct dmi_system_id *dmi_id;
+
+	if (lid_init_state == -1) {
+		dmi_id = dmi_first_match(dmi_lid_quirks);
+		if (dmi_id)
+			lid_init_state = (long)dmi_id->driver_data;
+		else
+			lid_init_state = ACPI_BUTTON_LID_INIT_METHOD;
+	}
+
 	/*
 	 * Modules such as nouveau.ko and i915.ko have a link time dependency
 	 * on acpi_lid_open(), and would therefore not be loadable on ACPI
diff --git a/drivers/acpi/ec.c b/drivers/acpi/ec.c
index da1e5c5ce150..4fd84fbdac29 100644
--- a/drivers/acpi/ec.c
+++ b/drivers/acpi/ec.c
@@ -95,12 +95,12 @@ enum {
 	EC_FLAGS_QUERY_ENABLED,		/* Query is enabled */
 	EC_FLAGS_QUERY_PENDING,		/* Query is pending */
 	EC_FLAGS_QUERY_GUARDING,	/* Guard for SCI_EVT check */
-	EC_FLAGS_GPE_HANDLER_INSTALLED,	/* GPE handler installed */
+	EC_FLAGS_EVENT_HANDLER_INSTALLED,	/* Event handler installed */
 	EC_FLAGS_EC_HANDLER_INSTALLED,	/* OpReg handler installed */
-	EC_FLAGS_EVT_HANDLER_INSTALLED, /* _Qxx handlers installed */
+	EC_FLAGS_QUERY_METHODS_INSTALLED, /* _Qxx handlers installed */
 	EC_FLAGS_STARTED,		/* Driver is started */
 	EC_FLAGS_STOPPED,		/* Driver is stopped */
-	EC_FLAGS_GPE_MASKED,		/* GPE masked */
+	EC_FLAGS_EVENTS_MASKED,		/* Events masked */
 };
 
 #define ACPI_EC_COMMAND_POLL		0x01 /* Available for command byte */
@@ -397,8 +397,8 @@ static inline void acpi_ec_clear_gpe(struct acpi_ec *ec)
 static void acpi_ec_submit_request(struct acpi_ec *ec)
 {
 	ec->reference_count++;
-	if (test_bit(EC_FLAGS_GPE_HANDLER_INSTALLED, &ec->flags) &&
-	    ec->reference_count == 1)
+	if (test_bit(EC_FLAGS_EVENT_HANDLER_INSTALLED, &ec->flags) &&
+	    ec->gpe >= 0 && ec->reference_count == 1)
 		acpi_ec_enable_gpe(ec, true);
 }
 
@@ -407,28 +407,36 @@ static void acpi_ec_complete_request(struct acpi_ec *ec)
 	bool flushed = false;
 
 	ec->reference_count--;
-	if (test_bit(EC_FLAGS_GPE_HANDLER_INSTALLED, &ec->flags) &&
-	    ec->reference_count == 0)
+	if (test_bit(EC_FLAGS_EVENT_HANDLER_INSTALLED, &ec->flags) &&
+	    ec->gpe >= 0 && ec->reference_count == 0)
 		acpi_ec_disable_gpe(ec, true);
 	flushed = acpi_ec_flushed(ec);
 	if (flushed)
 		wake_up(&ec->wait);
 }
 
-static void acpi_ec_mask_gpe(struct acpi_ec *ec)
+static void acpi_ec_mask_events(struct acpi_ec *ec)
 {
-	if (!test_bit(EC_FLAGS_GPE_MASKED, &ec->flags)) {
-		acpi_ec_disable_gpe(ec, false);
+	if (!test_bit(EC_FLAGS_EVENTS_MASKED, &ec->flags)) {
+		if (ec->gpe >= 0)
+			acpi_ec_disable_gpe(ec, false);
+		else
+			disable_irq_nosync(ec->irq);
+
 		ec_dbg_drv("Polling enabled");
-		set_bit(EC_FLAGS_GPE_MASKED, &ec->flags);
+		set_bit(EC_FLAGS_EVENTS_MASKED, &ec->flags);
 	}
 }
 
-static void acpi_ec_unmask_gpe(struct acpi_ec *ec)
+static void acpi_ec_unmask_events(struct acpi_ec *ec)
 {
-	if (test_bit(EC_FLAGS_GPE_MASKED, &ec->flags)) {
-		clear_bit(EC_FLAGS_GPE_MASKED, &ec->flags);
-		acpi_ec_enable_gpe(ec, false);
+	if (test_bit(EC_FLAGS_EVENTS_MASKED, &ec->flags)) {
+		clear_bit(EC_FLAGS_EVENTS_MASKED, &ec->flags);
+		if (ec->gpe >= 0)
+			acpi_ec_enable_gpe(ec, false);
+		else
+			enable_irq(ec->irq);
+
 		ec_dbg_drv("Polling disabled");
 	}
 }
@@ -454,7 +462,7 @@ static bool acpi_ec_submit_flushable_request(struct acpi_ec *ec)
 
 static void acpi_ec_submit_query(struct acpi_ec *ec)
 {
-	acpi_ec_mask_gpe(ec);
+	acpi_ec_mask_events(ec);
 	if (!acpi_ec_event_enabled(ec))
 		return;
 	if (!test_and_set_bit(EC_FLAGS_QUERY_PENDING, &ec->flags)) {
@@ -470,7 +478,7 @@ static void acpi_ec_complete_query(struct acpi_ec *ec)
 	if (test_and_clear_bit(EC_FLAGS_QUERY_PENDING, &ec->flags))
 		ec_dbg_evt("Command(%s) unblocked",
 			   acpi_ec_cmd_string(ACPI_EC_COMMAND_QUERY));
-	acpi_ec_unmask_gpe(ec);
+	acpi_ec_unmask_events(ec);
 }
 
 static inline void __acpi_ec_enable_event(struct acpi_ec *ec)
@@ -648,7 +656,9 @@ static void advance_transaction(struct acpi_ec *ec)
 	 * ensure a hardware STS 0->1 change after this clearing can always
 	 * trigger a GPE interrupt.
 	 */
-	acpi_ec_clear_gpe(ec);
+	if (ec->gpe >= 0)
+		acpi_ec_clear_gpe(ec);
+
 	status = acpi_ec_read_status(ec);
 	t = ec->curr;
 	/*
@@ -717,7 +727,7 @@ err:
 				++t->irq_count;
 			/* Allow triggering on 0 threshold */
 			if (t->irq_count == ec_storm_threshold)
-				acpi_ec_mask_gpe(ec);
+				acpi_ec_mask_events(ec);
 		}
 	}
 out:
@@ -815,7 +825,7 @@ static int acpi_ec_transaction_unlocked(struct acpi_ec *ec,
 
 	spin_lock_irqsave(&ec->lock, tmp);
 	if (t->irq_count == ec_storm_threshold)
-		acpi_ec_unmask_gpe(ec);
+		acpi_ec_unmask_events(ec);
 	ec_dbg_req("Command(%s) stopped", acpi_ec_cmd_string(t->command));
 	ec->curr = NULL;
 	/* Disable GPE for command processing (IBF=0/OBF=1) */
@@ -1275,18 +1285,28 @@ static void acpi_ec_event_handler(struct work_struct *work)
 	acpi_ec_check_event(ec);
 }
 
-static u32 acpi_ec_gpe_handler(acpi_handle gpe_device,
-	u32 gpe_number, void *data)
+static void acpi_ec_handle_interrupt(struct acpi_ec *ec)
 {
 	unsigned long flags;
-	struct acpi_ec *ec = data;
 
 	spin_lock_irqsave(&ec->lock, flags);
 	advance_transaction(ec);
 	spin_unlock_irqrestore(&ec->lock, flags);
+}
+
+static u32 acpi_ec_gpe_handler(acpi_handle gpe_device,
+			       u32 gpe_number, void *data)
+{
+	acpi_ec_handle_interrupt(data);
 	return ACPI_INTERRUPT_HANDLED;
 }
 
+static irqreturn_t acpi_ec_irq_handler(int irq, void *data)
+{
+	acpi_ec_handle_interrupt(data);
+	return IRQ_HANDLED;
+}
+
 /* --------------------------------------------------------------------------
  *                           Address Space Management
  * -------------------------------------------------------------------------- */
@@ -1359,6 +1379,8 @@ static struct acpi_ec *acpi_ec_alloc(void)
 	ec->timestamp = jiffies;
 	ec->busy_polling = true;
 	ec->polling_guard = 0;
+	ec->gpe = -1;
+	ec->irq = -1;
 	return ec;
 }
 
@@ -1406,9 +1428,13 @@ ec_parse_device(acpi_handle handle, u32 Level, void *context, void **retval)
 		/* Get GPE bit assignment (EC events). */
 		/* TODO: Add support for _GPE returning a package */
 		status = acpi_evaluate_integer(handle, "_GPE", NULL, &tmp);
-		if (ACPI_FAILURE(status))
-			return status;
-		ec->gpe = tmp;
+		if (ACPI_SUCCESS(status))
+			ec->gpe = tmp;
+
+		/*
+		 * Errors are non-fatal, allowing for ACPI Reduced Hardware
+		 * platforms which use GpioInt instead of GPE.
+		 */
 	}
 	/* Use the global lock for all EC transactions? */
 	tmp = 0;
@@ -1418,12 +1444,57 @@ ec_parse_device(acpi_handle handle, u32 Level, void *context, void **retval)
 	return AE_CTRL_TERMINATE;
 }
 
+static void install_gpe_event_handler(struct acpi_ec *ec)
+{
+	acpi_status status =
+		acpi_install_gpe_raw_handler(NULL, ec->gpe,
+					     ACPI_GPE_EDGE_TRIGGERED,
+					     &acpi_ec_gpe_handler,
+					     ec);
+	if (ACPI_SUCCESS(status)) {
+		/* This is not fatal as we can poll EC events */
+		set_bit(EC_FLAGS_EVENT_HANDLER_INSTALLED, &ec->flags);
+		acpi_ec_leave_noirq(ec);
+		if (test_bit(EC_FLAGS_STARTED, &ec->flags) &&
+		    ec->reference_count >= 1)
+			acpi_ec_enable_gpe(ec, true);
+	}
+}
+
+/* ACPI reduced hardware platforms use a GpioInt specified in _CRS. */
+static int install_gpio_irq_event_handler(struct acpi_ec *ec,
+					  struct acpi_device *device)
+{
+	int irq = acpi_dev_gpio_irq_get(device, 0);
+	int ret;
+
+	if (irq < 0)
+		return irq;
+
+	ret = request_irq(irq, acpi_ec_irq_handler, IRQF_SHARED,
+			  "ACPI EC", ec);
+
+	/*
+	 * Unlike the GPE case, we treat errors here as fatal, we'll only
+	 * implement GPIO polling if we find a case that needs it.
+	 */
+	if (ret < 0)
+		return ret;
+
+	ec->irq = irq;
+	set_bit(EC_FLAGS_EVENT_HANDLER_INSTALLED, &ec->flags);
+	acpi_ec_leave_noirq(ec);
+
+	return 0;
+}
+
 /*
  * Note: This function returns an error code only when the address space
  *       handler is not installed, which means "not able to handle
  *       transactions".
  */
-static int ec_install_handlers(struct acpi_ec *ec, bool handle_events)
+static int ec_install_handlers(struct acpi_ec *ec, struct acpi_device *device,
+			       bool handle_events)
 {
 	acpi_status status;
 
@@ -1456,24 +1527,23 @@ static int ec_install_handlers(struct acpi_ec *ec, bool handle_events)
 	if (!handle_events)
 		return 0;
 
-	if (!test_bit(EC_FLAGS_EVT_HANDLER_INSTALLED, &ec->flags)) {
+	if (!test_bit(EC_FLAGS_QUERY_METHODS_INSTALLED, &ec->flags)) {
 		/* Find and register all query methods */
 		acpi_walk_namespace(ACPI_TYPE_METHOD, ec->handle, 1,
 				    acpi_ec_register_query_methods,
 				    NULL, ec, NULL);
-		set_bit(EC_FLAGS_EVT_HANDLER_INSTALLED, &ec->flags);
+		set_bit(EC_FLAGS_QUERY_METHODS_INSTALLED, &ec->flags);
 	}
-	if (!test_bit(EC_FLAGS_GPE_HANDLER_INSTALLED, &ec->flags)) {
-		status = acpi_install_gpe_raw_handler(NULL, ec->gpe,
-					  ACPI_GPE_EDGE_TRIGGERED,
-					  &acpi_ec_gpe_handler, ec);
-		/* This is not fatal as we can poll EC events */
-		if (ACPI_SUCCESS(status)) {
-			set_bit(EC_FLAGS_GPE_HANDLER_INSTALLED, &ec->flags);
-			acpi_ec_leave_noirq(ec);
-			if (test_bit(EC_FLAGS_STARTED, &ec->flags) &&
-			    ec->reference_count >= 1)
-				acpi_ec_enable_gpe(ec, true);
+	if (!test_bit(EC_FLAGS_EVENT_HANDLER_INSTALLED, &ec->flags)) {
+		if (ec->gpe >= 0) {
+			install_gpe_event_handler(ec);
+		} else if (device) {
+			int ret = install_gpio_irq_event_handler(ec, device);
+
+			if (ret)
+				return ret;
+		} else { /* No GPE and no GpioInt? */
+			return -ENODEV;
 		}
 	}
 	/* EC is fully operational, allow queries */
@@ -1504,23 +1574,29 @@ static void ec_remove_handlers(struct acpi_ec *ec)
 	 */
 	acpi_ec_stop(ec, false);
 
-	if (test_bit(EC_FLAGS_GPE_HANDLER_INSTALLED, &ec->flags)) {
-		if (ACPI_FAILURE(acpi_remove_gpe_handler(NULL, ec->gpe,
-					&acpi_ec_gpe_handler)))
+	if (test_bit(EC_FLAGS_EVENT_HANDLER_INSTALLED, &ec->flags)) {
+		if (ec->gpe >= 0 &&
+		    ACPI_FAILURE(acpi_remove_gpe_handler(NULL, ec->gpe,
+				 &acpi_ec_gpe_handler)))
 			pr_err("failed to remove gpe handler\n");
-		clear_bit(EC_FLAGS_GPE_HANDLER_INSTALLED, &ec->flags);
+
+		if (ec->irq >= 0)
+			free_irq(ec->irq, ec);
+
+		clear_bit(EC_FLAGS_EVENT_HANDLER_INSTALLED, &ec->flags);
 	}
-	if (test_bit(EC_FLAGS_EVT_HANDLER_INSTALLED, &ec->flags)) {
+	if (test_bit(EC_FLAGS_QUERY_METHODS_INSTALLED, &ec->flags)) {
 		acpi_ec_remove_query_handlers(ec, true, 0);
-		clear_bit(EC_FLAGS_EVT_HANDLER_INSTALLED, &ec->flags);
+		clear_bit(EC_FLAGS_QUERY_METHODS_INSTALLED, &ec->flags);
 	}
 }
 
-static int acpi_ec_setup(struct acpi_ec *ec, bool handle_events)
+static int acpi_ec_setup(struct acpi_ec *ec, struct acpi_device *device,
+			 bool handle_events)
 {
 	int ret;
 
-	ret = ec_install_handlers(ec, handle_events);
+	ret = ec_install_handlers(ec, device, handle_events);
 	if (ret)
 		return ret;
 
@@ -1531,8 +1607,8 @@ static int acpi_ec_setup(struct acpi_ec *ec, bool handle_events)
 	}
 
 	acpi_handle_info(ec->handle,
-			 "GPE=0x%x, EC_CMD/EC_SC=0x%lx, EC_DATA=0x%lx\n",
-			 ec->gpe, ec->command_addr, ec->data_addr);
+			 "GPE=0x%x, IRQ=%d, EC_CMD/EC_SC=0x%lx, EC_DATA=0x%lx\n",
+			 ec->gpe, ec->irq, ec->command_addr, ec->data_addr);
 	return ret;
 }
 
@@ -1596,7 +1672,7 @@ static int acpi_ec_add(struct acpi_device *device)
 		}
 	}
 
-	ret = acpi_ec_setup(ec, true);
+	ret = acpi_ec_setup(ec, device, true);
 	if (ret)
 		goto err_query;
 
@@ -1716,7 +1792,7 @@ void __init acpi_ec_dsdt_probe(void)
 	 * At this point, the GPE is not fully initialized, so do not to
 	 * handle the events.
 	 */
-	ret = acpi_ec_setup(ec, false);
+	ret = acpi_ec_setup(ec, NULL, false);
 	if (ret) {
 		acpi_ec_free(ec);
 		return;
@@ -1889,14 +1965,21 @@ void __init acpi_ec_ecdt_probe(void)
 		ec->command_addr = ecdt_ptr->control.address;
 		ec->data_addr = ecdt_ptr->data.address;
 	}
-	ec->gpe = ecdt_ptr->gpe;
+
+	/*
+	 * Ignore the GPE value on Reduced Hardware platforms.
+	 * Some products have this set to an erroneous value.
+	 */
+	if (!acpi_gbl_reduced_hardware)
+		ec->gpe = ecdt_ptr->gpe;
+
 	ec->handle = ACPI_ROOT_OBJECT;
 
 	/*
 	 * At this point, the namespace is not initialized, so do not find
 	 * the namespace objects, or handle the events.
 	 */
-	ret = acpi_ec_setup(ec, false);
+	ret = acpi_ec_setup(ec, NULL, false);
 	if (ret) {
 		acpi_ec_free(ec);
 		return;
@@ -1928,7 +2011,7 @@ static int acpi_ec_suspend_noirq(struct device *dev)
 	 * masked at the low level without side effects.
 	 */
 	if (ec_no_wakeup && test_bit(EC_FLAGS_STARTED, &ec->flags) &&
-	    ec->reference_count >= 1)
+	    ec->gpe >= 0 && ec->reference_count >= 1)
 		acpi_set_gpe(NULL, ec->gpe, ACPI_GPE_DISABLE);
 
 	acpi_ec_enter_noirq(ec);
@@ -1943,7 +2026,7 @@ static int acpi_ec_resume_noirq(struct device *dev)
 	acpi_ec_leave_noirq(ec);
 
 	if (ec_no_wakeup && test_bit(EC_FLAGS_STARTED, &ec->flags) &&
-	    ec->reference_count >= 1)
+	    ec->gpe >= 0 && ec->reference_count >= 1)
 		acpi_set_gpe(NULL, ec->gpe, ACPI_GPE_ENABLE);
 
 	return 0;
diff --git a/drivers/acpi/hmat/Makefile b/drivers/acpi/hmat/Makefile
deleted file mode 100644
index 1c20ef36a385..000000000000
--- a/drivers/acpi/hmat/Makefile
+++ /dev/null
@@ -1,2 +0,0 @@
-# SPDX-License-Identifier: GPL-2.0-only
-obj-$(CONFIG_ACPI_HMAT) := hmat.o
diff --git a/drivers/acpi/internal.h b/drivers/acpi/internal.h
index afe6636f9ad3..3616daec650b 100644
--- a/drivers/acpi/internal.h
+++ b/drivers/acpi/internal.h
@@ -165,7 +165,8 @@ static inline void acpi_early_processor_osc(void) {}
    -------------------------------------------------------------------------- */
 struct acpi_ec {
 	acpi_handle handle;
-	u32 gpe;
+	int gpe;
+	int irq;
 	unsigned long command_addr;
 	unsigned long data_addr;
 	bool global_lock;
diff --git a/drivers/acpi/hmat/Kconfig b/drivers/acpi/numa/Kconfig
index 95a29964dbea..fcf2e556d69d 100644
--- a/drivers/acpi/hmat/Kconfig
+++ b/drivers/acpi/numa/Kconfig
@@ -1,8 +1,15 @@
 # SPDX-License-Identifier: GPL-2.0
+config ACPI_NUMA
+	bool "NUMA support"
+	depends on NUMA
+	depends on (X86 || IA64 || ARM64)
+	default y if IA64 || ARM64
+
 config ACPI_HMAT
 	bool "ACPI Heterogeneous Memory Attribute Table Support"
 	depends on ACPI_NUMA
 	select HMEM_REPORTING
+	select MEMREGION
 	help
 	 If set, this option has the kernel parse and report the
 	 platform's ACPI HMAT (Heterogeneous Memory Attributes Table),
diff --git a/drivers/acpi/numa/Makefile b/drivers/acpi/numa/Makefile
new file mode 100644
index 000000000000..517a6c689a94
--- /dev/null
+++ b/drivers/acpi/numa/Makefile
@@ -0,0 +1,3 @@
+# SPDX-License-Identifier: GPL-2.0-only
+obj-$(CONFIG_ACPI_NUMA) += srat.o
+obj-$(CONFIG_ACPI_HMAT) += hmat.o
diff --git a/drivers/acpi/hmat/hmat.c b/drivers/acpi/numa/hmat.c
index 8b0de8a3c647..2c32cfb72370 100644
--- a/drivers/acpi/hmat/hmat.c
+++ b/drivers/acpi/numa/hmat.c
@@ -8,12 +8,18 @@
  * the applicable attributes with the node's interfaces.
  */
 
+#define pr_fmt(fmt) "acpi/hmat: " fmt
+#define dev_fmt(fmt) "acpi/hmat: " fmt
+
 #include <linux/acpi.h>
 #include <linux/bitops.h>
 #include <linux/device.h>
 #include <linux/init.h>
 #include <linux/list.h>
+#include <linux/mm.h>
+#include <linux/platform_device.h>
 #include <linux/list_sort.h>
+#include <linux/memregion.h>
 #include <linux/memory.h>
 #include <linux/mutex.h>
 #include <linux/node.h>
@@ -49,6 +55,7 @@ struct memory_target {
 	struct list_head node;
 	unsigned int memory_pxm;
 	unsigned int processor_pxm;
+	struct resource memregions;
 	struct node_hmem_attrs hmem_attrs;
 	struct list_head caches;
 	struct node_cache_attrs cache_attrs;
@@ -104,22 +111,36 @@ static __init void alloc_memory_initiator(unsigned int cpu_pxm)
 	list_add_tail(&initiator->node, &initiators);
 }
 
-static __init void alloc_memory_target(unsigned int mem_pxm)
+static __init void alloc_memory_target(unsigned int mem_pxm,
+		resource_size_t start, resource_size_t len)
 {
 	struct memory_target *target;
 
 	target = find_mem_target(mem_pxm);
-	if (target)
-		return;
-
-	target = kzalloc(sizeof(*target), GFP_KERNEL);
-	if (!target)
-		return;
+	if (!target) {
+		target = kzalloc(sizeof(*target), GFP_KERNEL);
+		if (!target)
+			return;
+		target->memory_pxm = mem_pxm;
+		target->processor_pxm = PXM_INVAL;
+		target->memregions = (struct resource) {
+			.name	= "ACPI mem",
+			.start	= 0,
+			.end	= -1,
+			.flags	= IORESOURCE_MEM,
+		};
+		list_add_tail(&target->node, &targets);
+		INIT_LIST_HEAD(&target->caches);
+	}
 
-	target->memory_pxm = mem_pxm;
-	target->processor_pxm = PXM_INVAL;
-	list_add_tail(&target->node, &targets);
-	INIT_LIST_HEAD(&target->caches);
+	/*
+	 * There are potentially multiple ranges per PXM, so record each
+	 * in the per-target memregions resource tree.
+	 */
+	if (!__request_region(&target->memregions, start, len, "memory target",
+				IORESOURCE_MEM))
+		pr_warn("failed to reserve %#llx - %#llx in pxm: %d\n",
+				start, start + len, mem_pxm);
 }
 
 static __init const char *hmat_data_type(u8 type)
@@ -272,7 +293,7 @@ static __init int hmat_parse_locality(union acpi_subtable_headers *header,
 	u8 type, mem_hier;
 
 	if (hmat_loc->header.length < sizeof(*hmat_loc)) {
-		pr_notice("HMAT: Unexpected locality header length: %d\n",
+		pr_notice("HMAT: Unexpected locality header length: %u\n",
 			 hmat_loc->header.length);
 		return -EINVAL;
 	}
@@ -284,12 +305,12 @@ static __init int hmat_parse_locality(union acpi_subtable_headers *header,
 	total_size = sizeof(*hmat_loc) + sizeof(*entries) * ipds * tpds +
 		     sizeof(*inits) * ipds + sizeof(*targs) * tpds;
 	if (hmat_loc->header.length < total_size) {
-		pr_notice("HMAT: Unexpected locality header length:%d, minimum required:%d\n",
+		pr_notice("HMAT: Unexpected locality header length:%u, minimum required:%u\n",
 			 hmat_loc->header.length, total_size);
 		return -EINVAL;
 	}
 
-	pr_info("HMAT: Locality: Flags:%02x Type:%s Initiator Domains:%d Target Domains:%d Base:%lld\n",
+	pr_info("HMAT: Locality: Flags:%02x Type:%s Initiator Domains:%u Target Domains:%u Base:%lld\n",
 		hmat_loc->flags, hmat_data_type(type), ipds, tpds,
 		hmat_loc->entry_base_unit);
 
@@ -302,7 +323,7 @@ static __init int hmat_parse_locality(union acpi_subtable_headers *header,
 			value = hmat_normalize(entries[init * tpds + targ],
 					       hmat_loc->entry_base_unit,
 					       type);
-			pr_info("  Initiator-Target[%d-%d]:%d%s\n",
+			pr_info("  Initiator-Target[%u-%u]:%u%s\n",
 				inits[init], targs[targ], value,
 				hmat_data_type_suffix(type));
 
@@ -329,13 +350,13 @@ static __init int hmat_parse_cache(union acpi_subtable_headers *header,
 	u32 attrs;
 
 	if (cache->header.length < sizeof(*cache)) {
-		pr_notice("HMAT: Unexpected cache header length: %d\n",
+		pr_notice("HMAT: Unexpected cache header length: %u\n",
 			 cache->header.length);
 		return -EINVAL;
 	}
 
 	attrs = cache->cache_attributes;
-	pr_info("HMAT: Cache: Domain:%d Size:%llu Attrs:%08x SMBIOS Handles:%d\n",
+	pr_info("HMAT: Cache: Domain:%u Size:%llu Attrs:%08x SMBIOS Handles:%d\n",
 		cache->memory_PD, cache->cache_size, attrs,
 		cache->number_of_SMBIOShandles);
 
@@ -390,17 +411,17 @@ static int __init hmat_parse_proximity_domain(union acpi_subtable_headers *heade
 	struct memory_target *target = NULL;
 
 	if (p->header.length != sizeof(*p)) {
-		pr_notice("HMAT: Unexpected address range header length: %d\n",
+		pr_notice("HMAT: Unexpected address range header length: %u\n",
 			 p->header.length);
 		return -EINVAL;
 	}
 
 	if (hmat_revision == 1)
-		pr_info("HMAT: Memory (%#llx length %#llx) Flags:%04x Processor Domain:%d Memory Domain:%d\n",
+		pr_info("HMAT: Memory (%#llx length %#llx) Flags:%04x Processor Domain:%u Memory Domain:%u\n",
 			p->reserved3, p->reserved4, p->flags, p->processor_PD,
 			p->memory_PD);
 	else
-		pr_info("HMAT: Memory Flags:%04x Processor Domain:%d Memory Domain:%d\n",
+		pr_info("HMAT: Memory Flags:%04x Processor Domain:%u Memory Domain:%u\n",
 			p->flags, p->processor_PD, p->memory_PD);
 
 	if (p->flags & ACPI_HMAT_MEMORY_PD_VALID && hmat_revision == 1) {
@@ -417,7 +438,7 @@ static int __init hmat_parse_proximity_domain(union acpi_subtable_headers *heade
 			pr_debug("HMAT: Invalid Processor Domain\n");
 			return -EINVAL;
 		}
-		target->processor_pxm = p_node;
+		target->processor_pxm = p->processor_PD;
 	}
 
 	return 0;
@@ -452,7 +473,7 @@ static __init int srat_parse_mem_affinity(union acpi_subtable_headers *header,
 		return -EINVAL;
 	if (!(ma->flags & ACPI_SRAT_MEM_ENABLED))
 		return 0;
-	alloc_memory_target(ma->proximity_domain);
+	alloc_memory_target(ma->proximity_domain, ma->base_address, ma->length);
 	return 0;
 }
 
@@ -613,11 +634,92 @@ static void hmat_register_target_perf(struct memory_target *target)
 	node_set_perf_attrs(mem_nid, &target->hmem_attrs, 0);
 }
 
+static void hmat_register_target_device(struct memory_target *target,
+		struct resource *r)
+{
+	/* define a clean / non-busy resource for the platform device */
+	struct resource res = {
+		.start = r->start,
+		.end = r->end,
+		.flags = IORESOURCE_MEM,
+	};
+	struct platform_device *pdev;
+	struct memregion_info info;
+	int rc, id;
+
+	rc = region_intersects(res.start, resource_size(&res), IORESOURCE_MEM,
+			IORES_DESC_SOFT_RESERVED);
+	if (rc != REGION_INTERSECTS)
+		return;
+
+	id = memregion_alloc(GFP_KERNEL);
+	if (id < 0) {
+		pr_err("memregion allocation failure for %pr\n", &res);
+		return;
+	}
+
+	pdev = platform_device_alloc("hmem", id);
+	if (!pdev) {
+		pr_err("hmem device allocation failure for %pr\n", &res);
+		goto out_pdev;
+	}
+
+	pdev->dev.numa_node = acpi_map_pxm_to_online_node(target->memory_pxm);
+	info = (struct memregion_info) {
+		.target_node = acpi_map_pxm_to_node(target->memory_pxm),
+	};
+	rc = platform_device_add_data(pdev, &info, sizeof(info));
+	if (rc < 0) {
+		pr_err("hmem memregion_info allocation failure for %pr\n", &res);
+		goto out_pdev;
+	}
+
+	rc = platform_device_add_resources(pdev, &res, 1);
+	if (rc < 0) {
+		pr_err("hmem resource allocation failure for %pr\n", &res);
+		goto out_resource;
+	}
+
+	rc = platform_device_add(pdev);
+	if (rc < 0) {
+		dev_err(&pdev->dev, "device add failed for %pr\n", &res);
+		goto out_resource;
+	}
+
+	return;
+
+out_resource:
+	put_device(&pdev->dev);
+out_pdev:
+	memregion_free(id);
+}
+
+static void hmat_register_target_devices(struct memory_target *target)
+{
+	struct resource *res;
+
+	/*
+	 * Do not bother creating devices if no driver is available to
+	 * consume them.
+	 */
+	if (!IS_ENABLED(CONFIG_DEV_DAX_HMEM))
+		return;
+
+	for (res = target->memregions.child; res; res = res->sibling)
+		hmat_register_target_device(target, res);
+}
+
 static void hmat_register_target(struct memory_target *target)
 {
 	int nid = pxm_to_node(target->memory_pxm);
 
 	/*
+	 * Devices may belong to either an offline or online
+	 * node, so unconditionally add them.
+	 */
+	hmat_register_target_devices(target);
+
+	/*
 	 * Skip offline nodes. This can happen when memory
 	 * marked EFI_MEMORY_SP, "specific purpose", is applied
 	 * to all the memory in a promixity domain leading to
@@ -677,11 +779,21 @@ static __init void hmat_free_structures(void)
 	struct target_cache *tcache, *cnext;
 
 	list_for_each_entry_safe(target, tnext, &targets, node) {
+		struct resource *res, *res_next;
+
 		list_for_each_entry_safe(tcache, cnext, &target->caches, node) {
 			list_del(&tcache->node);
 			kfree(tcache);
 		}
+
 		list_del(&target->node);
+		res = target->memregions.child;
+		while (res) {
+			res_next = res->sibling;
+			__release_region(&target->memregions, res->start,
+					resource_size(res));
+			res = res_next;
+		}
 		kfree(target);
 	}
 
@@ -748,4 +860,4 @@ out_put:
 	acpi_put_table(tbl);
 	return 0;
 }
-subsys_initcall(hmat_init);
+device_initcall(hmat_init);
diff --git a/drivers/acpi/numa.c b/drivers/acpi/numa/srat.c
index eadbf90e65d1..eadbf90e65d1 100644
--- a/drivers/acpi/numa.c
+++ b/drivers/acpi/numa/srat.c
diff --git a/drivers/acpi/osi.c b/drivers/acpi/osi.c
index bec0bebc7f52..9f6853809138 100644
--- a/drivers/acpi/osi.c
+++ b/drivers/acpi/osi.c
@@ -473,9 +473,9 @@ static const struct dmi_system_id acpi_osi_dmi_table[] __initconst = {
 	 */
 
 	/*
-	 * Without this this EEEpc exports a non working WMI interface, with
-	 * this it exports a working "good old" eeepc_laptop interface, fixing
-	 * both brightness control, and rfkill not working.
+	 * Without this EEEpc exports a non working WMI interface, with
+	 * this it exports a working "good old" eeepc_laptop interface,
+	 * fixing both brightness control, and rfkill not working.
 	 */
 	{
 	.callback = dmi_enable_osi_linux,
diff --git a/drivers/acpi/pmic/intel_pmic.c b/drivers/acpi/pmic/intel_pmic.c
index 452041398b34..a371f273f99d 100644
--- a/drivers/acpi/pmic/intel_pmic.c
+++ b/drivers/acpi/pmic/intel_pmic.c
@@ -252,7 +252,7 @@ int intel_pmic_install_opregion_handler(struct device *dev, acpi_handle handle,
 					struct regmap *regmap,
 					struct intel_pmic_opregion_data *d)
 {
-	acpi_status status;
+	acpi_status status = AE_OK;
 	struct intel_pmic_opregion *opregion;
 	int ret;
 
@@ -270,7 +270,8 @@ int intel_pmic_install_opregion_handler(struct device *dev, acpi_handle handle,
 	opregion->regmap = regmap;
 	opregion->lpat_table = acpi_lpat_get_conversion_table(handle);
 
-	status = acpi_install_address_space_handler(handle,
+	if (d->power_table_count)
+		status = acpi_install_address_space_handler(handle,
 						    PMIC_POWER_OPREGION_ID,
 						    intel_pmic_power_handler,
 						    NULL, opregion);
@@ -279,7 +280,8 @@ int intel_pmic_install_opregion_handler(struct device *dev, acpi_handle handle,
 		goto out_error;
 	}
 
-	status = acpi_install_address_space_handler(handle,
+	if (d->thermal_table_count)
+		status = acpi_install_address_space_handler(handle,
 						    PMIC_THERMAL_OPREGION_ID,
 						    intel_pmic_thermal_handler,
 						    NULL, opregion);
@@ -301,12 +303,16 @@ int intel_pmic_install_opregion_handler(struct device *dev, acpi_handle handle,
 	return 0;
 
 out_remove_thermal_handler:
-	acpi_remove_address_space_handler(handle, PMIC_THERMAL_OPREGION_ID,
-					  intel_pmic_thermal_handler);
+	if (d->thermal_table_count)
+		acpi_remove_address_space_handler(handle,
+						  PMIC_THERMAL_OPREGION_ID,
+						  intel_pmic_thermal_handler);
 
 out_remove_power_handler:
-	acpi_remove_address_space_handler(handle, PMIC_POWER_OPREGION_ID,
-					  intel_pmic_power_handler);
+	if (d->power_table_count)
+		acpi_remove_address_space_handler(handle,
+						  PMIC_POWER_OPREGION_ID,
+						  intel_pmic_power_handler);
 
 out_error:
 	acpi_lpat_free_conversion_table(opregion->lpat_table);
diff --git a/drivers/acpi/pmic/intel_pmic_crc.c b/drivers/acpi/pmic/intel_pmic_bytcrc.c
index a0f411a6e5ac..2a692cc4b7ae 100644
--- a/drivers/acpi/pmic/intel_pmic_crc.c
+++ b/drivers/acpi/pmic/intel_pmic_bytcrc.c
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
 /*
- * Intel CrystalCove PMIC operation region driver
+ * Intel Bay Trail Crystal Cove PMIC operation region driver
  *
  * Copyright (C) 2014 Intel Corporation. All rights reserved.
  */
@@ -295,7 +295,7 @@ static int intel_crc_pmic_opregion_probe(struct platform_device *pdev)
 static struct platform_driver intel_crc_pmic_opregion_driver = {
 	.probe = intel_crc_pmic_opregion_probe,
 	.driver = {
-		.name = "crystal_cove_pmic",
+		.name = "byt_crystal_cove_pmic",
 	},
 };
 builtin_platform_driver(intel_crc_pmic_opregion_driver);
diff --git a/drivers/acpi/pmic/intel_pmic_chtcrc.c b/drivers/acpi/pmic/intel_pmic_chtcrc.c
new file mode 100644
index 000000000000..ebf8d3187df1
--- /dev/null
+++ b/drivers/acpi/pmic/intel_pmic_chtcrc.c
@@ -0,0 +1,44 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Intel Cherry Trail Crystal Cove PMIC operation region driver
+ *
+ * Copyright (C) 2019 Hans de Goede <hdegoede@redhat.com>
+ */
+
+#include <linux/acpi.h>
+#include <linux/init.h>
+#include <linux/mfd/intel_soc_pmic.h>
+#include <linux/platform_device.h>
+#include <linux/regmap.h>
+#include "intel_pmic.h"
+
+/*
+ * We have no docs for the CHT Crystal Cove PMIC. The Asus Zenfone-2 kernel
+ * code has 2 Crystal Cove regulator drivers, one calls the PMIC a "Crystal
+ * Cove Plus" PMIC and talks about Cherry Trail, so presuambly that one
+ * could be used to get register info for the regulators if we need to
+ * implement regulator support in the future.
+ *
+ * For now the sole purpose of this driver is to make
+ * intel_soc_pmic_exec_mipi_pmic_seq_element work on devices with a
+ * CHT Crystal Cove PMIC.
+ */
+static struct intel_pmic_opregion_data intel_chtcrc_pmic_opregion_data = {
+	.pmic_i2c_address = 0x6e,
+};
+
+static int intel_chtcrc_pmic_opregion_probe(struct platform_device *pdev)
+{
+	struct intel_soc_pmic *pmic = dev_get_drvdata(pdev->dev.parent);
+	return intel_pmic_install_opregion_handler(&pdev->dev,
+			ACPI_HANDLE(pdev->dev.parent), pmic->regmap,
+			&intel_chtcrc_pmic_opregion_data);
+}
+
+static struct platform_driver intel_chtcrc_pmic_opregion_driver = {
+	.probe = intel_chtcrc_pmic_opregion_probe,
+	.driver = {
+		.name = "cht_crystal_cove_pmic",
+	},
+};
+builtin_platform_driver(intel_chtcrc_pmic_opregion_driver);
diff --git a/drivers/acpi/processor_idle.c b/drivers/acpi/processor_idle.c
index ed56c6d20b08..2ae95df2e74f 100644
--- a/drivers/acpi/processor_idle.c
+++ b/drivers/acpi/processor_idle.c
@@ -642,6 +642,19 @@ static int acpi_idle_bm_check(void)
 	return bm_status;
 }
 
+static void wait_for_freeze(void)
+{
+#ifdef	CONFIG_X86
+	/* No delay is needed if we are in guest */
+	if (boot_cpu_has(X86_FEATURE_HYPERVISOR))
+		return;
+#endif
+	/* Dummy wait op - must do something useless after P_LVL2 read
+	   because chipsets cannot guarantee that STPCLK# signal
+	   gets asserted in time to freeze execution properly. */
+	inl(acpi_gbl_FADT.xpm_timer_block.address);
+}
+
 /**
  * acpi_idle_do_entry - enter idle state using the appropriate method
  * @cx: cstate data
@@ -658,10 +671,7 @@ static void __cpuidle acpi_idle_do_entry(struct acpi_processor_cx *cx)
 	} else {
 		/* IO port based C-state */
 		inb(cx->address);
-		/* Dummy wait op - must do something useless after P_LVL2 read
-		   because chipsets cannot guarantee that STPCLK# signal
-		   gets asserted in time to freeze execution properly. */
-		inl(acpi_gbl_FADT.xpm_timer_block.address);
+		wait_for_freeze();
 	}
 }
 
@@ -682,8 +692,7 @@ static int acpi_idle_play_dead(struct cpuidle_device *dev, int index)
 			safe_halt();
 		else if (cx->entry_method == ACPI_CSTATE_SYSTEMIO) {
 			inb(cx->address);
-			/* See comment in acpi_idle_do_entry() */
-			inl(acpi_gbl_FADT.xpm_timer_block.address);
+			wait_for_freeze();
 		} else
 			return -ENODEV;
 	}
diff --git a/drivers/acpi/property.c b/drivers/acpi/property.c
index 3eacf474e1e3..e601c4511a8b 100644
--- a/drivers/acpi/property.c
+++ b/drivers/acpi/property.c
@@ -1317,6 +1317,52 @@ acpi_fwnode_get_reference_args(const struct fwnode_handle *fwnode,
 						  args_count, args);
 }
 
+static const char *acpi_fwnode_get_name(const struct fwnode_handle *fwnode)
+{
+	const struct acpi_device *adev;
+	struct fwnode_handle *parent;
+
+	/* Is this the root node? */
+	parent = fwnode_get_parent(fwnode);
+	if (!parent)
+		return "\\";
+
+	fwnode_handle_put(parent);
+
+	if (is_acpi_data_node(fwnode)) {
+		const struct acpi_data_node *dn = to_acpi_data_node(fwnode);
+
+		return dn->name;
+	}
+
+	adev = to_acpi_device_node(fwnode);
+	if (WARN_ON(!adev))
+		return NULL;
+
+	return acpi_device_bid(adev);
+}
+
+static const char *
+acpi_fwnode_get_name_prefix(const struct fwnode_handle *fwnode)
+{
+	struct fwnode_handle *parent;
+
+	/* Is this the root node? */
+	parent = fwnode_get_parent(fwnode);
+	if (!parent)
+		return "";
+
+	/* Is this 2nd node from the root? */
+	parent = fwnode_get_next_parent(parent);
+	if (!parent)
+		return "";
+
+	fwnode_handle_put(parent);
+
+	/* ACPI device or data node. */
+	return ".";
+}
+
 static struct fwnode_handle *
 acpi_fwnode_get_parent(struct fwnode_handle *fwnode)
 {
@@ -1357,6 +1403,8 @@ acpi_fwnode_device_get_match_data(const struct fwnode_handle *fwnode,
 		.get_parent = acpi_node_get_parent,			\
 		.get_next_child_node = acpi_get_next_subnode,		\
 		.get_named_child_node = acpi_fwnode_get_named_child_node, \
+		.get_name = acpi_fwnode_get_name,			\
+		.get_name_prefix = acpi_fwnode_get_name_prefix,		\
 		.get_reference_args = acpi_fwnode_get_reference_args,	\
 		.graph_get_next_endpoint =				\
 			acpi_graph_get_next_endpoint,			\
diff --git a/drivers/acpi/scan.c b/drivers/acpi/scan.c
index aad6be5c0af0..915650bf519f 100644
--- a/drivers/acpi/scan.c
+++ b/drivers/acpi/scan.c
@@ -2174,6 +2174,7 @@ int __init acpi_scan_init(void)
 	acpi_pci_root_init();
 	acpi_pci_link_init();
 	acpi_processor_init();
+	acpi_platform_init();
 	acpi_lpss_init();
 	acpi_apd_init();
 	acpi_cmos_rtc_init();
diff --git a/drivers/acpi/utils.c b/drivers/acpi/utils.c
index e3974a8f8fd4..804ac0df58ec 100644
--- a/drivers/acpi/utils.c
+++ b/drivers/acpi/utils.c
@@ -455,6 +455,7 @@ EXPORT_SYMBOL(acpi_evaluate_ost);
 
 /**
  * acpi_handle_path: Return the object path of handle
+ * @handle: ACPI device handle
  *
  * Caller must free the returned buffer
  */
@@ -473,6 +474,9 @@ static char *acpi_handle_path(acpi_handle handle)
 
 /**
  * acpi_handle_printk: Print message with ACPI prefix and object path
+ * @level: log level
+ * @handle: ACPI device handle
+ * @fmt: format string
  *
  * This function is called through acpi_handle_<level> macros and prints
  * a message with ACPI prefix and object path.  This function acquires
@@ -501,6 +505,9 @@ EXPORT_SYMBOL(acpi_handle_printk);
 #if defined(CONFIG_DYNAMIC_DEBUG)
 /**
  * __acpi_handle_debug: pr_debug with ACPI prefix and object path
+ * @descriptor: Dynamic Debug descriptor
+ * @handle: ACPI device handle
+ * @fmt: format string
  *
  * This function is called through acpi_handle_debug macro and debug
  * prints a message with ACPI prefix and object path. This function
@@ -695,6 +702,31 @@ bool acpi_check_dsm(acpi_handle handle, const guid_t *guid, u64 rev, u64 funcs)
 EXPORT_SYMBOL(acpi_check_dsm);
 
 /**
+ * acpi_dev_hid_uid_match - Match device by supplied HID and UID
+ * @adev: ACPI device to match.
+ * @hid2: Hardware ID of the device.
+ * @uid2: Unique ID of the device, pass NULL to not check _UID.
+ *
+ * Matches HID and UID in @adev with given @hid2 and @uid2.
+ * Returns true if matches.
+ */
+bool acpi_dev_hid_uid_match(struct acpi_device *adev,
+			    const char *hid2, const char *uid2)
+{
+	const char *hid1 = acpi_device_hid(adev);
+	const char *uid1 = acpi_device_uid(adev);
+
+	if (strcmp(hid1, hid2))
+		return false;
+
+	if (!uid2)
+		return true;
+
+	return uid1 && !strcmp(uid1, uid2);
+}
+EXPORT_SYMBOL(acpi_dev_hid_uid_match);
+
+/**
  * acpi_dev_found - Detect presence of a given ACPI device in the namespace.
  * @hid: Hardware ID of the device.
  *
diff --git a/drivers/base/power/common.c b/drivers/base/power/common.c
index 8db98a1f83dc..bbddb267c2e6 100644
--- a/drivers/base/power/common.c
+++ b/drivers/base/power/common.c
@@ -188,6 +188,26 @@ void dev_pm_domain_detach(struct device *dev, bool power_off)
 EXPORT_SYMBOL_GPL(dev_pm_domain_detach);
 
 /**
+ * dev_pm_domain_start - Start the device through its PM domain.
+ * @dev: Device to start.
+ *
+ * This function should typically be called during probe by a subsystem/driver,
+ * when it needs to start its device from the PM domain's perspective. Note
+ * that, it's assumed that the PM domain is already powered on when this
+ * function is called.
+ *
+ * Returns 0 on success and negative error values on failures.
+ */
+int dev_pm_domain_start(struct device *dev)
+{
+	if (dev->pm_domain && dev->pm_domain->start)
+		return dev->pm_domain->start(dev);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(dev_pm_domain_start);
+
+/**
  * dev_pm_domain_set - Set PM domain of a device.
  * @dev: Device whose PM domain is to be set.
  * @pd: PM domain to be set, or NULL.
diff --git a/drivers/base/power/domain.c b/drivers/base/power/domain.c
index cc85e87eaf05..8e5725b11ee8 100644
--- a/drivers/base/power/domain.c
+++ b/drivers/base/power/domain.c
@@ -634,6 +634,13 @@ static int genpd_power_on(struct generic_pm_domain *genpd, unsigned int depth)
 	return ret;
 }
 
+static int genpd_dev_pm_start(struct device *dev)
+{
+	struct generic_pm_domain *genpd = dev_to_genpd(dev);
+
+	return genpd_start_dev(genpd, dev);
+}
+
 static int genpd_dev_pm_qos_notifier(struct notifier_block *nb,
 				     unsigned long val, void *ptr)
 {
@@ -922,24 +929,6 @@ static int __init genpd_power_off_unused(void)
 }
 late_initcall(genpd_power_off_unused);
 
-#if defined(CONFIG_PM_SLEEP) || defined(CONFIG_PM_GENERIC_DOMAINS_OF)
-
-static bool genpd_present(const struct generic_pm_domain *genpd)
-{
-	const struct generic_pm_domain *gpd;
-
-	if (IS_ERR_OR_NULL(genpd))
-		return false;
-
-	list_for_each_entry(gpd, &gpd_list, gpd_list_node)
-		if (gpd == genpd)
-			return true;
-
-	return false;
-}
-
-#endif
-
 #ifdef CONFIG_PM_SLEEP
 
 /**
@@ -1354,8 +1343,8 @@ static void genpd_syscore_switch(struct device *dev, bool suspend)
 {
 	struct generic_pm_domain *genpd;
 
-	genpd = dev_to_genpd(dev);
-	if (!genpd_present(genpd))
+	genpd = dev_to_genpd_safe(dev);
+	if (!genpd)
 		return;
 
 	if (suspend) {
@@ -1805,6 +1794,7 @@ int pm_genpd_init(struct generic_pm_domain *genpd,
 	genpd->domain.ops.poweroff_noirq = genpd_poweroff_noirq;
 	genpd->domain.ops.restore_noirq = genpd_restore_noirq;
 	genpd->domain.ops.complete = genpd_complete;
+	genpd->domain.start = genpd_dev_pm_start;
 
 	if (genpd->flags & GENPD_FLAG_PM_CLK) {
 		genpd->dev_ops.stop = pm_clk_suspend;
@@ -2020,6 +2010,16 @@ static int genpd_add_provider(struct device_node *np, genpd_xlate_t xlate,
 	return 0;
 }
 
+static bool genpd_present(const struct generic_pm_domain *genpd)
+{
+	const struct generic_pm_domain *gpd;
+
+	list_for_each_entry(gpd, &gpd_list, gpd_list_node)
+		if (gpd == genpd)
+			return true;
+	return false;
+}
+
 /**
  * of_genpd_add_provider_simple() - Register a simple PM domain provider
  * @np: Device node pointer associated with the PM domain provider.
diff --git a/drivers/base/power/power.h b/drivers/base/power/power.h
index 39a06a0cfdaa..444f5c169a0b 100644
--- a/drivers/base/power/power.h
+++ b/drivers/base/power/power.h
@@ -117,6 +117,13 @@ static inline bool device_pm_initialized(struct device *dev)
 	return dev->power.in_dpm_list;
 }
 
+/* drivers/base/power/wakeup_stats.c */
+extern int wakeup_source_sysfs_add(struct device *parent,
+				   struct wakeup_source *ws);
+extern void wakeup_source_sysfs_remove(struct wakeup_source *ws);
+
+extern int pm_wakeup_source_sysfs_add(struct device *parent);
+
 #else /* !CONFIG_PM_SLEEP */
 
 static inline void device_pm_sleep_init(struct device *dev) {}
@@ -141,6 +148,11 @@ static inline bool device_pm_initialized(struct device *dev)
 	return device_is_registered(dev);
 }
 
+static inline int pm_wakeup_source_sysfs_add(struct device *parent)
+{
+	return 0;
+}
+
 #endif /* !CONFIG_PM_SLEEP */
 
 static inline void device_pm_init(struct device *dev)
@@ -149,21 +161,3 @@ static inline void device_pm_init(struct device *dev)
 	device_pm_sleep_init(dev);
 	pm_runtime_init(dev);
 }
-
-#ifdef CONFIG_PM_SLEEP
-
-/* drivers/base/power/wakeup_stats.c */
-extern int wakeup_source_sysfs_add(struct device *parent,
-				   struct wakeup_source *ws);
-extern void wakeup_source_sysfs_remove(struct wakeup_source *ws);
-
-extern int pm_wakeup_source_sysfs_add(struct device *parent);
-
-#else /* !CONFIG_PM_SLEEP */
-
-static inline int pm_wakeup_source_sysfs_add(struct device *parent)
-{
-	return 0;
-}
-
-#endif /* CONFIG_PM_SLEEP */
diff --git a/drivers/base/power/wakeirq.c b/drivers/base/power/wakeirq.c
index 5ce77d1ef9fc..8e021082dba8 100644
--- a/drivers/base/power/wakeirq.c
+++ b/drivers/base/power/wakeirq.c
@@ -272,7 +272,7 @@ void dev_pm_enable_wake_irq_check(struct device *dev,
 {
 	struct wake_irq *wirq = dev->power.wakeirq;
 
-	if (!wirq || !((wirq->status & WAKE_IRQ_DEDICATED_MASK)))
+	if (!wirq || !(wirq->status & WAKE_IRQ_DEDICATED_MASK))
 		return;
 
 	if (likely(wirq->status & WAKE_IRQ_DEDICATED_MANAGED)) {
@@ -299,7 +299,7 @@ void dev_pm_disable_wake_irq_check(struct device *dev)
 {
 	struct wake_irq *wirq = dev->power.wakeirq;
 
-	if (!wirq || !((wirq->status & WAKE_IRQ_DEDICATED_MASK)))
+	if (!wirq || !(wirq->status & WAKE_IRQ_DEDICATED_MASK))
 		return;
 
 	if (wirq->status & WAKE_IRQ_DEDICATED_MANAGED)
diff --git a/drivers/base/property.c b/drivers/base/property.c
index 81bd01ed4042..511f6d7acdfe 100644
--- a/drivers/base/property.c
+++ b/drivers/base/property.c
@@ -557,6 +557,42 @@ int device_add_properties(struct device *dev,
 EXPORT_SYMBOL_GPL(device_add_properties);
 
 /**
+ * fwnode_get_name - Return the name of a node
+ * @fwnode: The firmware node
+ *
+ * Returns a pointer to the node name.
+ */
+const char *fwnode_get_name(const struct fwnode_handle *fwnode)
+{
+	return fwnode_call_ptr_op(fwnode, get_name);
+}
+
+/**
+ * fwnode_get_name_prefix - Return the prefix of node for printing purposes
+ * @fwnode: The firmware node
+ *
+ * Returns the prefix of a node, intended to be printed right before the node.
+ * The prefix works also as a separator between the nodes.
+ */
+const char *fwnode_get_name_prefix(const struct fwnode_handle *fwnode)
+{
+	return fwnode_call_ptr_op(fwnode, get_name_prefix);
+}
+
+/**
+ * fwnode_get_parent - Return parent firwmare node
+ * @fwnode: Firmware whose parent is retrieved
+ *
+ * Return parent firmware node of the given node if possible or %NULL if no
+ * parent was available.
+ */
+struct fwnode_handle *fwnode_get_parent(const struct fwnode_handle *fwnode)
+{
+	return fwnode_call_ptr_op(fwnode, get_parent);
+}
+EXPORT_SYMBOL_GPL(fwnode_get_parent);
+
+/**
  * fwnode_get_next_parent - Iterate to the node's parent
  * @fwnode: Firmware whose parent is retrieved
  *
@@ -578,17 +614,50 @@ struct fwnode_handle *fwnode_get_next_parent(struct fwnode_handle *fwnode)
 EXPORT_SYMBOL_GPL(fwnode_get_next_parent);
 
 /**
- * fwnode_get_parent - Return parent firwmare node
- * @fwnode: Firmware whose parent is retrieved
+ * fwnode_count_parents - Return the number of parents a node has
+ * @fwnode: The node the parents of which are to be counted
  *
- * Return parent firmware node of the given node if possible or %NULL if no
- * parent was available.
+ * Returns the number of parents a node has.
  */
-struct fwnode_handle *fwnode_get_parent(const struct fwnode_handle *fwnode)
+unsigned int fwnode_count_parents(const struct fwnode_handle *fwnode)
 {
-	return fwnode_call_ptr_op(fwnode, get_parent);
+	struct fwnode_handle *__fwnode;
+	unsigned int count;
+
+	__fwnode = fwnode_get_parent(fwnode);
+
+	for (count = 0; __fwnode; count++)
+		__fwnode = fwnode_get_next_parent(__fwnode);
+
+	return count;
 }
-EXPORT_SYMBOL_GPL(fwnode_get_parent);
+EXPORT_SYMBOL_GPL(fwnode_count_parents);
+
+/**
+ * fwnode_get_nth_parent - Return an nth parent of a node
+ * @fwnode: The node the parent of which is requested
+ * @depth: Distance of the parent from the node
+ *
+ * Returns the nth parent of a node. If there is no parent at the requested
+ * @depth, %NULL is returned. If @depth is 0, the functionality is equivalent to
+ * fwnode_handle_get(). For @depth == 1, it is fwnode_get_parent() and so on.
+ *
+ * The caller is responsible for calling fwnode_handle_put() for the returned
+ * node.
+ */
+struct fwnode_handle *fwnode_get_nth_parent(struct fwnode_handle *fwnode,
+					    unsigned int depth)
+{
+	unsigned int i;
+
+	fwnode_handle_get(fwnode);
+
+	for (i = 0; i < depth && fwnode; i++)
+		fwnode = fwnode_get_next_parent(fwnode);
+
+	return fwnode;
+}
+EXPORT_SYMBOL_GPL(fwnode_get_nth_parent);
 
 /**
  * fwnode_get_next_child_node - Return the next child node handle for a node
diff --git a/drivers/base/swnode.c b/drivers/base/swnode.c
index a1f3f0994f9f..d8d0dc0ca5ac 100644
--- a/drivers/base/swnode.c
+++ b/drivers/base/swnode.c
@@ -71,9 +71,9 @@ software_node_to_swnode(const struct software_node *node)
 	return swnode;
 }
 
-const struct software_node *to_software_node(struct fwnode_handle *fwnode)
+const struct software_node *to_software_node(const struct fwnode_handle *fwnode)
 {
-	struct swnode *swnode = to_swnode(fwnode);
+	const struct swnode *swnode = to_swnode(fwnode);
 
 	return swnode ? swnode->node : NULL;
 }
@@ -103,71 +103,15 @@ property_entry_get(const struct property_entry *prop, const char *name)
 	return NULL;
 }
 
-static void
-property_set_pointer(struct property_entry *prop, const void *pointer)
-{
-	switch (prop->type) {
-	case DEV_PROP_U8:
-		if (prop->is_array)
-			prop->pointer.u8_data = pointer;
-		else
-			prop->value.u8_data = *((u8 *)pointer);
-		break;
-	case DEV_PROP_U16:
-		if (prop->is_array)
-			prop->pointer.u16_data = pointer;
-		else
-			prop->value.u16_data = *((u16 *)pointer);
-		break;
-	case DEV_PROP_U32:
-		if (prop->is_array)
-			prop->pointer.u32_data = pointer;
-		else
-			prop->value.u32_data = *((u32 *)pointer);
-		break;
-	case DEV_PROP_U64:
-		if (prop->is_array)
-			prop->pointer.u64_data = pointer;
-		else
-			prop->value.u64_data = *((u64 *)pointer);
-		break;
-	case DEV_PROP_STRING:
-		if (prop->is_array)
-			prop->pointer.str = pointer;
-		else
-			prop->value.str = pointer;
-		break;
-	default:
-		break;
-	}
-}
-
 static const void *property_get_pointer(const struct property_entry *prop)
 {
-	switch (prop->type) {
-	case DEV_PROP_U8:
-		if (prop->is_array)
-			return prop->pointer.u8_data;
-		return &prop->value.u8_data;
-	case DEV_PROP_U16:
-		if (prop->is_array)
-			return prop->pointer.u16_data;
-		return &prop->value.u16_data;
-	case DEV_PROP_U32:
-		if (prop->is_array)
-			return prop->pointer.u32_data;
-		return &prop->value.u32_data;
-	case DEV_PROP_U64:
-		if (prop->is_array)
-			return prop->pointer.u64_data;
-		return &prop->value.u64_data;
-	case DEV_PROP_STRING:
-		if (prop->is_array)
-			return prop->pointer.str;
-		return &prop->value.str;
-	default:
+	if (!prop->length)
 		return NULL;
-	}
+
+	if (prop->is_array)
+		return prop->pointer;
+
+	return &prop->value;
 }
 
 static const void *property_entry_find(const struct property_entry *props,
@@ -187,66 +131,6 @@ static const void *property_entry_find(const struct property_entry *props,
 	return pointer;
 }
 
-static int property_entry_read_u8_array(const struct property_entry *props,
-					const char *propname,
-					u8 *values, size_t nval)
-{
-	const void *pointer;
-	size_t length = nval * sizeof(*values);
-
-	pointer = property_entry_find(props, propname, length);
-	if (IS_ERR(pointer))
-		return PTR_ERR(pointer);
-
-	memcpy(values, pointer, length);
-	return 0;
-}
-
-static int property_entry_read_u16_array(const struct property_entry *props,
-					 const char *propname,
-					 u16 *values, size_t nval)
-{
-	const void *pointer;
-	size_t length = nval * sizeof(*values);
-
-	pointer = property_entry_find(props, propname, length);
-	if (IS_ERR(pointer))
-		return PTR_ERR(pointer);
-
-	memcpy(values, pointer, length);
-	return 0;
-}
-
-static int property_entry_read_u32_array(const struct property_entry *props,
-					 const char *propname,
-					 u32 *values, size_t nval)
-{
-	const void *pointer;
-	size_t length = nval * sizeof(*values);
-
-	pointer = property_entry_find(props, propname, length);
-	if (IS_ERR(pointer))
-		return PTR_ERR(pointer);
-
-	memcpy(values, pointer, length);
-	return 0;
-}
-
-static int property_entry_read_u64_array(const struct property_entry *props,
-					 const char *propname,
-					 u64 *values, size_t nval)
-{
-	const void *pointer;
-	size_t length = nval * sizeof(*values);
-
-	pointer = property_entry_find(props, propname, length);
-	if (IS_ERR(pointer))
-		return PTR_ERR(pointer);
-
-	memcpy(values, pointer, length);
-	return 0;
-}
-
 static int
 property_entry_count_elems_of_size(const struct property_entry *props,
 				   const char *propname, size_t length)
@@ -265,49 +149,45 @@ static int property_entry_read_int_array(const struct property_entry *props,
 					 unsigned int elem_size, void *val,
 					 size_t nval)
 {
+	const void *pointer;
+	size_t length;
+
 	if (!val)
 		return property_entry_count_elems_of_size(props, name,
 							  elem_size);
-	switch (elem_size) {
-	case sizeof(u8):
-		return property_entry_read_u8_array(props, name, val, nval);
-	case sizeof(u16):
-		return property_entry_read_u16_array(props, name, val, nval);
-	case sizeof(u32):
-		return property_entry_read_u32_array(props, name, val, nval);
-	case sizeof(u64):
-		return property_entry_read_u64_array(props, name, val, nval);
-	}
 
-	return -ENXIO;
+	if (!is_power_of_2(elem_size) || elem_size > sizeof(u64))
+		return -ENXIO;
+
+	length = nval * elem_size;
+
+	pointer = property_entry_find(props, name, length);
+	if (IS_ERR(pointer))
+		return PTR_ERR(pointer);
+
+	memcpy(val, pointer, length);
+	return 0;
 }
 
 static int property_entry_read_string_array(const struct property_entry *props,
 					    const char *propname,
 					    const char **strings, size_t nval)
 {
-	const struct property_entry *prop;
 	const void *pointer;
-	size_t array_len, length;
+	size_t length;
+	int array_len;
 
 	/* Find out the array length. */
-	prop = property_entry_get(props, propname);
-	if (!prop)
-		return -EINVAL;
-
-	if (prop->is_array)
-		/* Find the length of an array. */
-		array_len = property_entry_count_elems_of_size(props, propname,
-							  sizeof(const char *));
-	else
-		/* The array length for a non-array string property is 1. */
-		array_len = 1;
+	array_len = property_entry_count_elems_of_size(props, propname,
+						       sizeof(const char *));
+	if (array_len < 0)
+		return array_len;
 
 	/* Return how many there are if strings is NULL. */
 	if (!strings)
 		return array_len;
 
-	array_len = min(nval, array_len);
+	array_len = min_t(size_t, nval, array_len);
 	length = array_len * sizeof(*strings);
 
 	pointer = property_entry_find(props, propname, length);
@@ -322,13 +202,15 @@ static int property_entry_read_string_array(const struct property_entry *props,
 static void property_entry_free_data(const struct property_entry *p)
 {
 	const void *pointer = property_get_pointer(p);
+	const char * const *src_str;
 	size_t i, nval;
 
 	if (p->is_array) {
-		if (p->type == DEV_PROP_STRING && p->pointer.str) {
+		if (p->type == DEV_PROP_STRING && p->pointer) {
+			src_str = p->pointer;
 			nval = p->length / sizeof(const char *);
 			for (i = 0; i < nval; i++)
-				kfree(p->pointer.str[i]);
+				kfree(src_str[i]);
 		}
 		kfree(pointer);
 	} else if (p->type == DEV_PROP_STRING) {
@@ -337,29 +219,29 @@ static void property_entry_free_data(const struct property_entry *p)
 	kfree(p->name);
 }
 
-static int property_copy_string_array(struct property_entry *dst,
-				      const struct property_entry *src)
+static const char * const *
+property_copy_string_array(const struct property_entry *src)
 {
 	const char **d;
+	const char * const *src_str = src->pointer;
 	size_t nval = src->length / sizeof(*d);
 	int i;
 
 	d = kcalloc(nval, sizeof(*d), GFP_KERNEL);
 	if (!d)
-		return -ENOMEM;
+		return NULL;
 
 	for (i = 0; i < nval; i++) {
-		d[i] = kstrdup(src->pointer.str[i], GFP_KERNEL);
-		if (!d[i] && src->pointer.str[i]) {
+		d[i] = kstrdup(src_str[i], GFP_KERNEL);
+		if (!d[i] && src_str[i]) {
 			while (--i >= 0)
 				kfree(d[i]);
 			kfree(d);
-			return -ENOMEM;
+			return NULL;
 		}
 	}
 
-	dst->pointer.str = d;
-	return 0;
+	return d;
 }
 
 static int property_entry_copy_data(struct property_entry *dst,
@@ -367,36 +249,35 @@ static int property_entry_copy_data(struct property_entry *dst,
 {
 	const void *pointer = property_get_pointer(src);
 	const void *new;
-	int error;
 
 	if (src->is_array) {
 		if (!src->length)
 			return -ENODATA;
 
 		if (src->type == DEV_PROP_STRING) {
-			error = property_copy_string_array(dst, src);
-			if (error)
-				return error;
-			new = dst->pointer.str;
+			new = property_copy_string_array(src);
+			if (!new)
+				return -ENOMEM;
 		} else {
 			new = kmemdup(pointer, src->length, GFP_KERNEL);
 			if (!new)
 				return -ENOMEM;
 		}
+
+		dst->is_array = true;
+		dst->pointer = new;
 	} else if (src->type == DEV_PROP_STRING) {
 		new = kstrdup(src->value.str, GFP_KERNEL);
 		if (!new && src->value.str)
 			return -ENOMEM;
+
+		dst->value.str = new;
 	} else {
-		new = pointer;
+		dst->value = src->value;
 	}
 
 	dst->length = src->length;
-	dst->is_array = src->is_array;
 	dst->type = src->type;
-
-	property_set_pointer(dst, new);
-
 	dst->name = kstrdup(src->name, GFP_KERNEL);
 	if (!dst->name)
 		goto out_free_data;
@@ -515,12 +396,47 @@ static int software_node_read_string_array(const struct fwnode_handle *fwnode,
 						propname, val, nval);
 }
 
+static const char *
+software_node_get_name(const struct fwnode_handle *fwnode)
+{
+	const struct swnode *swnode = to_swnode(fwnode);
+
+	if (!swnode)
+		return "(null)";
+
+	return kobject_name(&swnode->kobj);
+}
+
+static const char *
+software_node_get_name_prefix(const struct fwnode_handle *fwnode)
+{
+	struct fwnode_handle *parent;
+	const char *prefix;
+
+	parent = fwnode_get_parent(fwnode);
+	if (!parent)
+		return "";
+
+	/* Figure out the prefix from the parents. */
+	while (is_software_node(parent))
+		parent = fwnode_get_next_parent(parent);
+
+	prefix = fwnode_get_name_prefix(parent);
+	fwnode_handle_put(parent);
+
+	/* Guess something if prefix was NULL. */
+	return prefix ?: "/";
+}
+
 static struct fwnode_handle *
 software_node_get_parent(const struct fwnode_handle *fwnode)
 {
 	struct swnode *swnode = to_swnode(fwnode);
 
-	return swnode ? (swnode->parent ? &swnode->parent->fwnode : NULL) : NULL;
+	if (!swnode || !swnode->parent)
+		return NULL;
+
+	return fwnode_handle_get(&swnode->parent->fwnode);
 }
 
 static struct fwnode_handle *
@@ -612,6 +528,8 @@ static const struct fwnode_operations software_node_ops = {
 	.property_present = software_node_property_present,
 	.property_read_int_array = software_node_read_int_array,
 	.property_read_string_array = software_node_read_string_array,
+	.get_name = software_node_get_name,
+	.get_name_prefix = software_node_get_name_prefix,
 	.get_parent = software_node_get_parent,
 	.get_next_child_node = software_node_get_next_child,
 	.get_named_child_node = software_node_get_named_child_node,
diff --git a/drivers/clocksource/hyperv_timer.c b/drivers/clocksource/hyperv_timer.c
index 2317d4e3daaf..287d8d58c21a 100644
--- a/drivers/clocksource/hyperv_timer.c
+++ b/drivers/clocksource/hyperv_timer.c
@@ -17,6 +17,7 @@
 #include <linux/clocksource.h>
 #include <linux/sched_clock.h>
 #include <linux/mm.h>
+#include <linux/cpuhotplug.h>
 #include <clocksource/hyperv_timer.h>
 #include <asm/hyperv-tlfs.h>
 #include <asm/mshyperv.h>
@@ -30,6 +31,15 @@ static u64 hv_sched_clock_offset __ro_after_init;
  * mechanism is used when running on older versions of Hyper-V
  * that don't support Direct Mode. While Hyper-V provides
  * four stimer's per CPU, Linux uses only stimer0.
+ *
+ * Because Direct Mode does not require processing a VMbus
+ * message, stimer interrupts can be enabled earlier in the
+ * process of booting a CPU, and consistent with when timer
+ * interrupts are enabled for other clocksource drivers.
+ * However, for legacy versions of Hyper-V when Direct Mode
+ * is not enabled, setting up stimer interrupts must be
+ * delayed until VMbus is initialized and can process the
+ * interrupt message.
  */
 static bool direct_mode_enabled;
 
@@ -102,17 +112,12 @@ static int hv_ce_set_oneshot(struct clock_event_device *evt)
 /*
  * hv_stimer_init - Per-cpu initialization of the clockevent
  */
-void hv_stimer_init(unsigned int cpu)
+static int hv_stimer_init(unsigned int cpu)
 {
 	struct clock_event_device *ce;
 
-	/*
-	 * Synthetic timers are always available except on old versions of
-	 * Hyper-V on x86.  In that case, just return as Linux will use a
-	 * clocksource based on emulated PIT or LAPIC timer hardware.
-	 */
-	if (!(ms_hyperv.features & HV_MSR_SYNTIMER_AVAILABLE))
-		return;
+	if (!hv_clock_event)
+		return 0;
 
 	ce = per_cpu_ptr(hv_clock_event, cpu);
 	ce->name = "Hyper-V clockevent";
@@ -127,28 +132,55 @@ void hv_stimer_init(unsigned int cpu)
 					HV_CLOCK_HZ,
 					HV_MIN_DELTA_TICKS,
 					HV_MAX_MAX_DELTA_TICKS);
+	return 0;
 }
-EXPORT_SYMBOL_GPL(hv_stimer_init);
 
 /*
  * hv_stimer_cleanup - Per-cpu cleanup of the clockevent
  */
-void hv_stimer_cleanup(unsigned int cpu)
+int hv_stimer_cleanup(unsigned int cpu)
 {
 	struct clock_event_device *ce;
 
-	/* Turn off clockevent device */
-	if (ms_hyperv.features & HV_MSR_SYNTIMER_AVAILABLE) {
-		ce = per_cpu_ptr(hv_clock_event, cpu);
+	if (!hv_clock_event)
+		return 0;
+
+	/*
+	 * In the legacy case where Direct Mode is not enabled
+	 * (which can only be on x86/64), stimer cleanup happens
+	 * relatively early in the CPU offlining process. We
+	 * must unbind the stimer-based clockevent device so
+	 * that the LAPIC timer can take over until clockevents
+	 * are no longer needed in the offlining process. Note
+	 * that clockevents_unbind_device() eventually calls
+	 * hv_ce_shutdown().
+	 *
+	 * The unbind should not be done when Direct Mode is
+	 * enabled because we may be on an architecture where
+	 * there are no other clockevent devices to fallback to.
+	 */
+	ce = per_cpu_ptr(hv_clock_event, cpu);
+	if (direct_mode_enabled)
 		hv_ce_shutdown(ce);
-	}
+	else
+		clockevents_unbind_device(ce, cpu);
+
+	return 0;
 }
 EXPORT_SYMBOL_GPL(hv_stimer_cleanup);
 
 /* hv_stimer_alloc - Global initialization of the clockevent and stimer0 */
-int hv_stimer_alloc(int sint)
+int hv_stimer_alloc(void)
 {
-	int ret;
+	int ret = 0;
+
+	/*
+	 * Synthetic timers are always available except on old versions of
+	 * Hyper-V on x86.  In that case, return as error as Linux will use a
+	 * clockevent based on emulated LAPIC timer hardware.
+	 */
+	if (!(ms_hyperv.features & HV_MSR_SYNTIMER_AVAILABLE))
+		return -EINVAL;
 
 	hv_clock_event = alloc_percpu(struct clock_event_device);
 	if (!hv_clock_event)
@@ -159,22 +191,78 @@ int hv_stimer_alloc(int sint)
 	if (direct_mode_enabled) {
 		ret = hv_setup_stimer0_irq(&stimer0_irq, &stimer0_vector,
 				hv_stimer0_isr);
-		if (ret) {
-			free_percpu(hv_clock_event);
-			hv_clock_event = NULL;
-			return ret;
-		}
+		if (ret)
+			goto free_percpu;
+
+		/*
+		 * Since we are in Direct Mode, stimer initialization
+		 * can be done now with a CPUHP value in the same range
+		 * as other clockevent devices.
+		 */
+		ret = cpuhp_setup_state(CPUHP_AP_HYPERV_TIMER_STARTING,
+				"clockevents/hyperv/stimer:starting",
+				hv_stimer_init, hv_stimer_cleanup);
+		if (ret < 0)
+			goto free_stimer0_irq;
 	}
+	return ret;
 
-	stimer0_message_sint = sint;
-	return 0;
+free_stimer0_irq:
+	hv_remove_stimer0_irq(stimer0_irq);
+	stimer0_irq = 0;
+free_percpu:
+	free_percpu(hv_clock_event);
+	hv_clock_event = NULL;
+	return ret;
 }
 EXPORT_SYMBOL_GPL(hv_stimer_alloc);
 
+/*
+ * hv_stimer_legacy_init -- Called from the VMbus driver to handle
+ * the case when Direct Mode is not enabled, and the stimer
+ * must be initialized late in the CPU onlining process.
+ *
+ */
+void hv_stimer_legacy_init(unsigned int cpu, int sint)
+{
+	if (direct_mode_enabled)
+		return;
+
+	/*
+	 * This function gets called by each vCPU, so setting the
+	 * global stimer_message_sint value each time is conceptually
+	 * not ideal, but the value passed in is always the same and
+	 * it avoids introducing yet another interface into this
+	 * clocksource driver just to set the sint in the legacy case.
+	 */
+	stimer0_message_sint = sint;
+	(void)hv_stimer_init(cpu);
+}
+EXPORT_SYMBOL_GPL(hv_stimer_legacy_init);
+
+/*
+ * hv_stimer_legacy_cleanup -- Called from the VMbus driver to
+ * handle the case when Direct Mode is not enabled, and the
+ * stimer must be cleaned up early in the CPU offlining
+ * process.
+ */
+void hv_stimer_legacy_cleanup(unsigned int cpu)
+{
+	if (direct_mode_enabled)
+		return;
+	(void)hv_stimer_cleanup(cpu);
+}
+EXPORT_SYMBOL_GPL(hv_stimer_legacy_cleanup);
+
+
 /* hv_stimer_free - Free global resources allocated by hv_stimer_alloc() */
 void hv_stimer_free(void)
 {
-	if (direct_mode_enabled && (stimer0_irq != 0)) {
+	if (!hv_clock_event)
+		return;
+
+	if (direct_mode_enabled) {
+		cpuhp_remove_state(CPUHP_AP_HYPERV_TIMER_STARTING);
 		hv_remove_stimer0_irq(stimer0_irq);
 		stimer0_irq = 0;
 	}
@@ -190,14 +278,20 @@ EXPORT_SYMBOL_GPL(hv_stimer_free);
 void hv_stimer_global_cleanup(void)
 {
 	int	cpu;
-	struct clock_event_device *ce;
 
-	if (ms_hyperv.features & HV_MSR_SYNTIMER_AVAILABLE) {
-		for_each_present_cpu(cpu) {
-			ce = per_cpu_ptr(hv_clock_event, cpu);
-			clockevents_unbind_device(ce, cpu);
-		}
+	/*
+	 * hv_stime_legacy_cleanup() will stop the stimer if Direct
+	 * Mode is not enabled, and fallback to the LAPIC timer.
+	 */
+	for_each_present_cpu(cpu) {
+		hv_stimer_legacy_cleanup(cpu);
 	}
+
+	/*
+	 * If Direct Mode is enabled, the cpuhp teardown callback
+	 * (hv_stimer_cleanup) will be run on all CPUs to stop the
+	 * stimers.
+	 */
 	hv_stimer_free();
 }
 EXPORT_SYMBOL_GPL(hv_stimer_global_cleanup);
diff --git a/drivers/cpufreq/Kconfig.arm b/drivers/cpufreq/Kconfig.arm
index a905796f7f85..3858d86cf409 100644
--- a/drivers/cpufreq/Kconfig.arm
+++ b/drivers/cpufreq/Kconfig.arm
@@ -49,14 +49,6 @@ config ARM_ARMADA_8K_CPUFREQ
 
 	  If in doubt, say N.
 
-# big LITTLE core layer and glue drivers
-config ARM_BIG_LITTLE_CPUFREQ
-	tristate "Generic ARM big LITTLE CPUfreq driver"
-	depends on ARM_CPU_TOPOLOGY && HAVE_CLK
-	select PM_OPP
-	help
-	  This enables the Generic CPUfreq driver for ARM big.LITTLE platforms.
-
 config ARM_SCPI_CPUFREQ
 	tristate "SCPI based CPUfreq driver"
 	depends on ARM_SCPI_PROTOCOL && COMMON_CLK_SCPI
@@ -69,7 +61,9 @@ config ARM_SCPI_CPUFREQ
 
 config ARM_VEXPRESS_SPC_CPUFREQ
 	tristate "Versatile Express SPC based CPUfreq driver"
-	depends on ARM_BIG_LITTLE_CPUFREQ && ARCH_VEXPRESS_SPC
+	depends on ARM_CPU_TOPOLOGY && HAVE_CLK
+	depends on ARCH_VEXPRESS_SPC
+	select PM_OPP
 	help
 	  This add the CPUfreq driver support for Versatile Express
 	  big.LITTLE platforms using SPC for power management.
diff --git a/drivers/cpufreq/Makefile b/drivers/cpufreq/Makefile
index 9a9f5ccd13d9..f6670c4abbb0 100644
--- a/drivers/cpufreq/Makefile
+++ b/drivers/cpufreq/Makefile
@@ -47,8 +47,6 @@ obj-$(CONFIG_X86_SFI_CPUFREQ)		+= sfi-cpufreq.o
 
 ##################################################################################
 # ARM SoC drivers
-obj-$(CONFIG_ARM_BIG_LITTLE_CPUFREQ)	+= arm_big_little.o
-
 obj-$(CONFIG_ARM_ARMADA_37XX_CPUFREQ)	+= armada-37xx-cpufreq.o
 obj-$(CONFIG_ARM_ARMADA_8K_CPUFREQ)	+= armada-8k-cpufreq.o
 obj-$(CONFIG_ARM_BRCMSTB_AVS_CPUFREQ)	+= brcmstb-avs-cpufreq.o
diff --git a/drivers/cpufreq/arm_big_little.c b/drivers/cpufreq/arm_big_little.c
deleted file mode 100644
index 7fe52fcddcf1..000000000000
--- a/drivers/cpufreq/arm_big_little.c
+++ /dev/null
@@ -1,658 +0,0 @@
-/*
- * ARM big.LITTLE Platforms CPUFreq support
- *
- * Copyright (C) 2013 ARM Ltd.
- * Sudeep KarkadaNagesha <sudeep.karkadanagesha@arm.com>
- *
- * Copyright (C) 2013 Linaro.
- * Viresh Kumar <viresh.kumar@linaro.org>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
- * This program is distributed "as is" WITHOUT ANY WARRANTY of any
- * kind, whether express or implied; without even the implied warranty
- * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- */
-
-#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
-
-#include <linux/clk.h>
-#include <linux/cpu.h>
-#include <linux/cpufreq.h>
-#include <linux/cpumask.h>
-#include <linux/cpu_cooling.h>
-#include <linux/export.h>
-#include <linux/module.h>
-#include <linux/mutex.h>
-#include <linux/of_platform.h>
-#include <linux/pm_opp.h>
-#include <linux/slab.h>
-#include <linux/topology.h>
-#include <linux/types.h>
-
-#include "arm_big_little.h"
-
-/* Currently we support only two clusters */
-#define A15_CLUSTER	0
-#define A7_CLUSTER	1
-#define MAX_CLUSTERS	2
-
-#ifdef CONFIG_BL_SWITCHER
-#include <asm/bL_switcher.h>
-static bool bL_switching_enabled;
-#define is_bL_switching_enabled()	bL_switching_enabled
-#define set_switching_enabled(x)	(bL_switching_enabled = (x))
-#else
-#define is_bL_switching_enabled()	false
-#define set_switching_enabled(x)	do { } while (0)
-#define bL_switch_request(...)		do { } while (0)
-#define bL_switcher_put_enabled()	do { } while (0)
-#define bL_switcher_get_enabled()	do { } while (0)
-#endif
-
-#define ACTUAL_FREQ(cluster, freq)  ((cluster == A7_CLUSTER) ? freq << 1 : freq)
-#define VIRT_FREQ(cluster, freq)    ((cluster == A7_CLUSTER) ? freq >> 1 : freq)
-
-static struct thermal_cooling_device *cdev[MAX_CLUSTERS];
-static const struct cpufreq_arm_bL_ops *arm_bL_ops;
-static struct clk *clk[MAX_CLUSTERS];
-static struct cpufreq_frequency_table *freq_table[MAX_CLUSTERS + 1];
-static atomic_t cluster_usage[MAX_CLUSTERS + 1];
-
-static unsigned int clk_big_min;	/* (Big) clock frequencies */
-static unsigned int clk_little_max;	/* Maximum clock frequency (Little) */
-
-static DEFINE_PER_CPU(unsigned int, physical_cluster);
-static DEFINE_PER_CPU(unsigned int, cpu_last_req_freq);
-
-static struct mutex cluster_lock[MAX_CLUSTERS];
-
-static inline int raw_cpu_to_cluster(int cpu)
-{
-	return topology_physical_package_id(cpu);
-}
-
-static inline int cpu_to_cluster(int cpu)
-{
-	return is_bL_switching_enabled() ?
-		MAX_CLUSTERS : raw_cpu_to_cluster(cpu);
-}
-
-static unsigned int find_cluster_maxfreq(int cluster)
-{
-	int j;
-	u32 max_freq = 0, cpu_freq;
-
-	for_each_online_cpu(j) {
-		cpu_freq = per_cpu(cpu_last_req_freq, j);
-
-		if ((cluster == per_cpu(physical_cluster, j)) &&
-				(max_freq < cpu_freq))
-			max_freq = cpu_freq;
-	}
-
-	pr_debug("%s: cluster: %d, max freq: %d\n", __func__, cluster,
-			max_freq);
-
-	return max_freq;
-}
-
-static unsigned int clk_get_cpu_rate(unsigned int cpu)
-{
-	u32 cur_cluster = per_cpu(physical_cluster, cpu);
-	u32 rate = clk_get_rate(clk[cur_cluster]) / 1000;
-
-	/* For switcher we use virtual A7 clock rates */
-	if (is_bL_switching_enabled())
-		rate = VIRT_FREQ(cur_cluster, rate);
-
-	pr_debug("%s: cpu: %d, cluster: %d, freq: %u\n", __func__, cpu,
-			cur_cluster, rate);
-
-	return rate;
-}
-
-static unsigned int bL_cpufreq_get_rate(unsigned int cpu)
-{
-	if (is_bL_switching_enabled()) {
-		pr_debug("%s: freq: %d\n", __func__, per_cpu(cpu_last_req_freq,
-					cpu));
-
-		return per_cpu(cpu_last_req_freq, cpu);
-	} else {
-		return clk_get_cpu_rate(cpu);
-	}
-}
-
-static unsigned int
-bL_cpufreq_set_rate(u32 cpu, u32 old_cluster, u32 new_cluster, u32 rate)
-{
-	u32 new_rate, prev_rate;
-	int ret;
-	bool bLs = is_bL_switching_enabled();
-
-	mutex_lock(&cluster_lock[new_cluster]);
-
-	if (bLs) {
-		prev_rate = per_cpu(cpu_last_req_freq, cpu);
-		per_cpu(cpu_last_req_freq, cpu) = rate;
-		per_cpu(physical_cluster, cpu) = new_cluster;
-
-		new_rate = find_cluster_maxfreq(new_cluster);
-		new_rate = ACTUAL_FREQ(new_cluster, new_rate);
-	} else {
-		new_rate = rate;
-	}
-
-	pr_debug("%s: cpu: %d, old cluster: %d, new cluster: %d, freq: %d\n",
-			__func__, cpu, old_cluster, new_cluster, new_rate);
-
-	ret = clk_set_rate(clk[new_cluster], new_rate * 1000);
-	if (!ret) {
-		/*
-		 * FIXME: clk_set_rate hasn't returned an error here however it
-		 * may be that clk_change_rate failed due to hardware or
-		 * firmware issues and wasn't able to report that due to the
-		 * current design of the clk core layer. To work around this
-		 * problem we will read back the clock rate and check it is
-		 * correct. This needs to be removed once clk core is fixed.
-		 */
-		if (clk_get_rate(clk[new_cluster]) != new_rate * 1000)
-			ret = -EIO;
-	}
-
-	if (WARN_ON(ret)) {
-		pr_err("clk_set_rate failed: %d, new cluster: %d\n", ret,
-				new_cluster);
-		if (bLs) {
-			per_cpu(cpu_last_req_freq, cpu) = prev_rate;
-			per_cpu(physical_cluster, cpu) = old_cluster;
-		}
-
-		mutex_unlock(&cluster_lock[new_cluster]);
-
-		return ret;
-	}
-
-	mutex_unlock(&cluster_lock[new_cluster]);
-
-	/* Recalc freq for old cluster when switching clusters */
-	if (old_cluster != new_cluster) {
-		pr_debug("%s: cpu: %d, old cluster: %d, new cluster: %d\n",
-				__func__, cpu, old_cluster, new_cluster);
-
-		/* Switch cluster */
-		bL_switch_request(cpu, new_cluster);
-
-		mutex_lock(&cluster_lock[old_cluster]);
-
-		/* Set freq of old cluster if there are cpus left on it */
-		new_rate = find_cluster_maxfreq(old_cluster);
-		new_rate = ACTUAL_FREQ(old_cluster, new_rate);
-
-		if (new_rate) {
-			pr_debug("%s: Updating rate of old cluster: %d, to freq: %d\n",
-					__func__, old_cluster, new_rate);
-
-			if (clk_set_rate(clk[old_cluster], new_rate * 1000))
-				pr_err("%s: clk_set_rate failed: %d, old cluster: %d\n",
-						__func__, ret, old_cluster);
-		}
-		mutex_unlock(&cluster_lock[old_cluster]);
-	}
-
-	return 0;
-}
-
-/* Set clock frequency */
-static int bL_cpufreq_set_target(struct cpufreq_policy *policy,
-		unsigned int index)
-{
-	u32 cpu = policy->cpu, cur_cluster, new_cluster, actual_cluster;
-	unsigned int freqs_new;
-	int ret;
-
-	cur_cluster = cpu_to_cluster(cpu);
-	new_cluster = actual_cluster = per_cpu(physical_cluster, cpu);
-
-	freqs_new = freq_table[cur_cluster][index].frequency;
-
-	if (is_bL_switching_enabled()) {
-		if ((actual_cluster == A15_CLUSTER) &&
-				(freqs_new < clk_big_min)) {
-			new_cluster = A7_CLUSTER;
-		} else if ((actual_cluster == A7_CLUSTER) &&
-				(freqs_new > clk_little_max)) {
-			new_cluster = A15_CLUSTER;
-		}
-	}
-
-	ret = bL_cpufreq_set_rate(cpu, actual_cluster, new_cluster, freqs_new);
-
-	if (!ret) {
-		arch_set_freq_scale(policy->related_cpus, freqs_new,
-				    policy->cpuinfo.max_freq);
-	}
-
-	return ret;
-}
-
-static inline u32 get_table_count(struct cpufreq_frequency_table *table)
-{
-	int count;
-
-	for (count = 0; table[count].frequency != CPUFREQ_TABLE_END; count++)
-		;
-
-	return count;
-}
-
-/* get the minimum frequency in the cpufreq_frequency_table */
-static inline u32 get_table_min(struct cpufreq_frequency_table *table)
-{
-	struct cpufreq_frequency_table *pos;
-	uint32_t min_freq = ~0;
-	cpufreq_for_each_entry(pos, table)
-		if (pos->frequency < min_freq)
-			min_freq = pos->frequency;
-	return min_freq;
-}
-
-/* get the maximum frequency in the cpufreq_frequency_table */
-static inline u32 get_table_max(struct cpufreq_frequency_table *table)
-{
-	struct cpufreq_frequency_table *pos;
-	uint32_t max_freq = 0;
-	cpufreq_for_each_entry(pos, table)
-		if (pos->frequency > max_freq)
-			max_freq = pos->frequency;
-	return max_freq;
-}
-
-static int merge_cluster_tables(void)
-{
-	int i, j, k = 0, count = 1;
-	struct cpufreq_frequency_table *table;
-
-	for (i = 0; i < MAX_CLUSTERS; i++)
-		count += get_table_count(freq_table[i]);
-
-	table = kcalloc(count, sizeof(*table), GFP_KERNEL);
-	if (!table)
-		return -ENOMEM;
-
-	freq_table[MAX_CLUSTERS] = table;
-
-	/* Add in reverse order to get freqs in increasing order */
-	for (i = MAX_CLUSTERS - 1; i >= 0; i--) {
-		for (j = 0; freq_table[i][j].frequency != CPUFREQ_TABLE_END;
-				j++) {
-			table[k].frequency = VIRT_FREQ(i,
-					freq_table[i][j].frequency);
-			pr_debug("%s: index: %d, freq: %d\n", __func__, k,
-					table[k].frequency);
-			k++;
-		}
-	}
-
-	table[k].driver_data = k;
-	table[k].frequency = CPUFREQ_TABLE_END;
-
-	pr_debug("%s: End, table: %p, count: %d\n", __func__, table, k);
-
-	return 0;
-}
-
-static void _put_cluster_clk_and_freq_table(struct device *cpu_dev,
-					    const struct cpumask *cpumask)
-{
-	u32 cluster = raw_cpu_to_cluster(cpu_dev->id);
-
-	if (!freq_table[cluster])
-		return;
-
-	clk_put(clk[cluster]);
-	dev_pm_opp_free_cpufreq_table(cpu_dev, &freq_table[cluster]);
-	if (arm_bL_ops->free_opp_table)
-		arm_bL_ops->free_opp_table(cpumask);
-	dev_dbg(cpu_dev, "%s: cluster: %d\n", __func__, cluster);
-}
-
-static void put_cluster_clk_and_freq_table(struct device *cpu_dev,
-					   const struct cpumask *cpumask)
-{
-	u32 cluster = cpu_to_cluster(cpu_dev->id);
-	int i;
-
-	if (atomic_dec_return(&cluster_usage[cluster]))
-		return;
-
-	if (cluster < MAX_CLUSTERS)
-		return _put_cluster_clk_and_freq_table(cpu_dev, cpumask);
-
-	for_each_present_cpu(i) {
-		struct device *cdev = get_cpu_device(i);
-		if (!cdev) {
-			pr_err("%s: failed to get cpu%d device\n", __func__, i);
-			return;
-		}
-
-		_put_cluster_clk_and_freq_table(cdev, cpumask);
-	}
-
-	/* free virtual table */
-	kfree(freq_table[cluster]);
-}
-
-static int _get_cluster_clk_and_freq_table(struct device *cpu_dev,
-					   const struct cpumask *cpumask)
-{
-	u32 cluster = raw_cpu_to_cluster(cpu_dev->id);
-	int ret;
-
-	if (freq_table[cluster])
-		return 0;
-
-	ret = arm_bL_ops->init_opp_table(cpumask);
-	if (ret) {
-		dev_err(cpu_dev, "%s: init_opp_table failed, cpu: %d, err: %d\n",
-				__func__, cpu_dev->id, ret);
-		goto out;
-	}
-
-	ret = dev_pm_opp_init_cpufreq_table(cpu_dev, &freq_table[cluster]);
-	if (ret) {
-		dev_err(cpu_dev, "%s: failed to init cpufreq table, cpu: %d, err: %d\n",
-				__func__, cpu_dev->id, ret);
-		goto free_opp_table;
-	}
-
-	clk[cluster] = clk_get(cpu_dev, NULL);
-	if (!IS_ERR(clk[cluster])) {
-		dev_dbg(cpu_dev, "%s: clk: %p & freq table: %p, cluster: %d\n",
-				__func__, clk[cluster], freq_table[cluster],
-				cluster);
-		return 0;
-	}
-
-	dev_err(cpu_dev, "%s: Failed to get clk for cpu: %d, cluster: %d\n",
-			__func__, cpu_dev->id, cluster);
-	ret = PTR_ERR(clk[cluster]);
-	dev_pm_opp_free_cpufreq_table(cpu_dev, &freq_table[cluster]);
-
-free_opp_table:
-	if (arm_bL_ops->free_opp_table)
-		arm_bL_ops->free_opp_table(cpumask);
-out:
-	dev_err(cpu_dev, "%s: Failed to get data for cluster: %d\n", __func__,
-			cluster);
-	return ret;
-}
-
-static int get_cluster_clk_and_freq_table(struct device *cpu_dev,
-					  const struct cpumask *cpumask)
-{
-	u32 cluster = cpu_to_cluster(cpu_dev->id);
-	int i, ret;
-
-	if (atomic_inc_return(&cluster_usage[cluster]) != 1)
-		return 0;
-
-	if (cluster < MAX_CLUSTERS) {
-		ret = _get_cluster_clk_and_freq_table(cpu_dev, cpumask);
-		if (ret)
-			atomic_dec(&cluster_usage[cluster]);
-		return ret;
-	}
-
-	/*
-	 * Get data for all clusters and fill virtual cluster with a merge of
-	 * both
-	 */
-	for_each_present_cpu(i) {
-		struct device *cdev = get_cpu_device(i);
-		if (!cdev) {
-			pr_err("%s: failed to get cpu%d device\n", __func__, i);
-			return -ENODEV;
-		}
-
-		ret = _get_cluster_clk_and_freq_table(cdev, cpumask);
-		if (ret)
-			goto put_clusters;
-	}
-
-	ret = merge_cluster_tables();
-	if (ret)
-		goto put_clusters;
-
-	/* Assuming 2 cluster, set clk_big_min and clk_little_max */
-	clk_big_min = get_table_min(freq_table[0]);
-	clk_little_max = VIRT_FREQ(1, get_table_max(freq_table[1]));
-
-	pr_debug("%s: cluster: %d, clk_big_min: %d, clk_little_max: %d\n",
-			__func__, cluster, clk_big_min, clk_little_max);
-
-	return 0;
-
-put_clusters:
-	for_each_present_cpu(i) {
-		struct device *cdev = get_cpu_device(i);
-		if (!cdev) {
-			pr_err("%s: failed to get cpu%d device\n", __func__, i);
-			return -ENODEV;
-		}
-
-		_put_cluster_clk_and_freq_table(cdev, cpumask);
-	}
-
-	atomic_dec(&cluster_usage[cluster]);
-
-	return ret;
-}
-
-/* Per-CPU initialization */
-static int bL_cpufreq_init(struct cpufreq_policy *policy)
-{
-	u32 cur_cluster = cpu_to_cluster(policy->cpu);
-	struct device *cpu_dev;
-	int ret;
-
-	cpu_dev = get_cpu_device(policy->cpu);
-	if (!cpu_dev) {
-		pr_err("%s: failed to get cpu%d device\n", __func__,
-				policy->cpu);
-		return -ENODEV;
-	}
-
-	if (cur_cluster < MAX_CLUSTERS) {
-		int cpu;
-
-		cpumask_copy(policy->cpus, topology_core_cpumask(policy->cpu));
-
-		for_each_cpu(cpu, policy->cpus)
-			per_cpu(physical_cluster, cpu) = cur_cluster;
-	} else {
-		/* Assumption: during init, we are always running on A15 */
-		per_cpu(physical_cluster, policy->cpu) = A15_CLUSTER;
-	}
-
-	ret = get_cluster_clk_and_freq_table(cpu_dev, policy->cpus);
-	if (ret)
-		return ret;
-
-	policy->freq_table = freq_table[cur_cluster];
-	policy->cpuinfo.transition_latency =
-				arm_bL_ops->get_transition_latency(cpu_dev);
-
-	dev_pm_opp_of_register_em(policy->cpus);
-
-	if (is_bL_switching_enabled())
-		per_cpu(cpu_last_req_freq, policy->cpu) = clk_get_cpu_rate(policy->cpu);
-
-	dev_info(cpu_dev, "%s: CPU %d initialized\n", __func__, policy->cpu);
-	return 0;
-}
-
-static int bL_cpufreq_exit(struct cpufreq_policy *policy)
-{
-	struct device *cpu_dev;
-	int cur_cluster = cpu_to_cluster(policy->cpu);
-
-	if (cur_cluster < MAX_CLUSTERS) {
-		cpufreq_cooling_unregister(cdev[cur_cluster]);
-		cdev[cur_cluster] = NULL;
-	}
-
-	cpu_dev = get_cpu_device(policy->cpu);
-	if (!cpu_dev) {
-		pr_err("%s: failed to get cpu%d device\n", __func__,
-				policy->cpu);
-		return -ENODEV;
-	}
-
-	put_cluster_clk_and_freq_table(cpu_dev, policy->related_cpus);
-	dev_dbg(cpu_dev, "%s: Exited, cpu: %d\n", __func__, policy->cpu);
-
-	return 0;
-}
-
-static void bL_cpufreq_ready(struct cpufreq_policy *policy)
-{
-	int cur_cluster = cpu_to_cluster(policy->cpu);
-
-	/* Do not register a cpu_cooling device if we are in IKS mode */
-	if (cur_cluster >= MAX_CLUSTERS)
-		return;
-
-	cdev[cur_cluster] = of_cpufreq_cooling_register(policy);
-}
-
-static struct cpufreq_driver bL_cpufreq_driver = {
-	.name			= "arm-big-little",
-	.flags			= CPUFREQ_STICKY |
-					CPUFREQ_HAVE_GOVERNOR_PER_POLICY |
-					CPUFREQ_NEED_INITIAL_FREQ_CHECK,
-	.verify			= cpufreq_generic_frequency_table_verify,
-	.target_index		= bL_cpufreq_set_target,
-	.get			= bL_cpufreq_get_rate,
-	.init			= bL_cpufreq_init,
-	.exit			= bL_cpufreq_exit,
-	.ready			= bL_cpufreq_ready,
-	.attr			= cpufreq_generic_attr,
-};
-
-#ifdef CONFIG_BL_SWITCHER
-static int bL_cpufreq_switcher_notifier(struct notifier_block *nfb,
-					unsigned long action, void *_arg)
-{
-	pr_debug("%s: action: %ld\n", __func__, action);
-
-	switch (action) {
-	case BL_NOTIFY_PRE_ENABLE:
-	case BL_NOTIFY_PRE_DISABLE:
-		cpufreq_unregister_driver(&bL_cpufreq_driver);
-		break;
-
-	case BL_NOTIFY_POST_ENABLE:
-		set_switching_enabled(true);
-		cpufreq_register_driver(&bL_cpufreq_driver);
-		break;
-
-	case BL_NOTIFY_POST_DISABLE:
-		set_switching_enabled(false);
-		cpufreq_register_driver(&bL_cpufreq_driver);
-		break;
-
-	default:
-		return NOTIFY_DONE;
-	}
-
-	return NOTIFY_OK;
-}
-
-static struct notifier_block bL_switcher_notifier = {
-	.notifier_call = bL_cpufreq_switcher_notifier,
-};
-
-static int __bLs_register_notifier(void)
-{
-	return bL_switcher_register_notifier(&bL_switcher_notifier);
-}
-
-static int __bLs_unregister_notifier(void)
-{
-	return bL_switcher_unregister_notifier(&bL_switcher_notifier);
-}
-#else
-static int __bLs_register_notifier(void) { return 0; }
-static int __bLs_unregister_notifier(void) { return 0; }
-#endif
-
-int bL_cpufreq_register(const struct cpufreq_arm_bL_ops *ops)
-{
-	int ret, i;
-
-	if (arm_bL_ops) {
-		pr_debug("%s: Already registered: %s, exiting\n", __func__,
-				arm_bL_ops->name);
-		return -EBUSY;
-	}
-
-	if (!ops || !strlen(ops->name) || !ops->init_opp_table ||
-	    !ops->get_transition_latency) {
-		pr_err("%s: Invalid arm_bL_ops, exiting\n", __func__);
-		return -ENODEV;
-	}
-
-	arm_bL_ops = ops;
-
-	set_switching_enabled(bL_switcher_get_enabled());
-
-	for (i = 0; i < MAX_CLUSTERS; i++)
-		mutex_init(&cluster_lock[i]);
-
-	ret = cpufreq_register_driver(&bL_cpufreq_driver);
-	if (ret) {
-		pr_info("%s: Failed registering platform driver: %s, err: %d\n",
-				__func__, ops->name, ret);
-		arm_bL_ops = NULL;
-	} else {
-		ret = __bLs_register_notifier();
-		if (ret) {
-			cpufreq_unregister_driver(&bL_cpufreq_driver);
-			arm_bL_ops = NULL;
-		} else {
-			pr_info("%s: Registered platform driver: %s\n",
-					__func__, ops->name);
-		}
-	}
-
-	bL_switcher_put_enabled();
-	return ret;
-}
-EXPORT_SYMBOL_GPL(bL_cpufreq_register);
-
-void bL_cpufreq_unregister(const struct cpufreq_arm_bL_ops *ops)
-{
-	if (arm_bL_ops != ops) {
-		pr_err("%s: Registered with: %s, can't unregister, exiting\n",
-				__func__, arm_bL_ops->name);
-		return;
-	}
-
-	bL_switcher_get_enabled();
-	__bLs_unregister_notifier();
-	cpufreq_unregister_driver(&bL_cpufreq_driver);
-	bL_switcher_put_enabled();
-	pr_info("%s: Un-registered platform driver: %s\n", __func__,
-			arm_bL_ops->name);
-	arm_bL_ops = NULL;
-}
-EXPORT_SYMBOL_GPL(bL_cpufreq_unregister);
-
-MODULE_AUTHOR("Viresh Kumar <viresh.kumar@linaro.org>");
-MODULE_DESCRIPTION("Generic ARM big LITTLE cpufreq driver");
-MODULE_LICENSE("GPL v2");
diff --git a/drivers/cpufreq/arm_big_little.h b/drivers/cpufreq/arm_big_little.h
deleted file mode 100644
index 88a176e466c8..000000000000
--- a/drivers/cpufreq/arm_big_little.h
+++ /dev/null
@@ -1,43 +0,0 @@
-/*
- * ARM big.LITTLE platform's CPUFreq header file
- *
- * Copyright (C) 2013 ARM Ltd.
- * Sudeep KarkadaNagesha <sudeep.karkadanagesha@arm.com>
- *
- * Copyright (C) 2013 Linaro.
- * Viresh Kumar <viresh.kumar@linaro.org>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
- * This program is distributed "as is" WITHOUT ANY WARRANTY of any
- * kind, whether express or implied; without even the implied warranty
- * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- */
-#ifndef CPUFREQ_ARM_BIG_LITTLE_H
-#define CPUFREQ_ARM_BIG_LITTLE_H
-
-#include <linux/cpufreq.h>
-#include <linux/device.h>
-#include <linux/types.h>
-
-struct cpufreq_arm_bL_ops {
-	char name[CPUFREQ_NAME_LEN];
-
-	/*
-	 * This must set opp table for cpu_dev in a similar way as done by
-	 * dev_pm_opp_of_add_table().
-	 */
-	int (*init_opp_table)(const struct cpumask *cpumask);
-
-	/* Optional */
-	int (*get_transition_latency)(struct device *cpu_dev);
-	void (*free_opp_table)(const struct cpumask *cpumask);
-};
-
-int bL_cpufreq_register(const struct cpufreq_arm_bL_ops *ops);
-void bL_cpufreq_unregister(const struct cpufreq_arm_bL_ops *ops);
-
-#endif /* CPUFREQ_ARM_BIG_LITTLE_H */
diff --git a/drivers/cpufreq/cpufreq-dt-platdev.c b/drivers/cpufreq/cpufreq-dt-platdev.c
index bca8d1f47fd2..54bc76743b1f 100644
--- a/drivers/cpufreq/cpufreq-dt-platdev.c
+++ b/drivers/cpufreq/cpufreq-dt-platdev.c
@@ -86,7 +86,6 @@ static const struct of_device_id whitelist[] __initconst = {
 	{ .compatible = "st-ericsson,u9540", },
 
 	{ .compatible = "ti,omap2", },
-	{ .compatible = "ti,omap3", },
 	{ .compatible = "ti,omap4", },
 	{ .compatible = "ti,omap5", },
 
@@ -137,6 +136,7 @@ static const struct of_device_id blacklist[] __initconst = {
 	{ .compatible = "ti,am33xx", },
 	{ .compatible = "ti,am43", },
 	{ .compatible = "ti,dra7", },
+	{ .compatible = "ti,omap3", },
 
 	{ }
 };
diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c
index 48a224a6b178..77114a3897fb 100644
--- a/drivers/cpufreq/cpufreq.c
+++ b/drivers/cpufreq/cpufreq.c
@@ -113,18 +113,21 @@ EXPORT_SYMBOL_GPL(get_governor_parent_kobj);
 
 static inline u64 get_cpu_idle_time_jiffy(unsigned int cpu, u64 *wall)
 {
-	u64 idle_time;
+	struct kernel_cpustat kcpustat;
 	u64 cur_wall_time;
+	u64 idle_time;
 	u64 busy_time;
 
 	cur_wall_time = jiffies64_to_nsecs(get_jiffies_64());
 
-	busy_time = kcpustat_cpu(cpu).cpustat[CPUTIME_USER];
-	busy_time += kcpustat_cpu(cpu).cpustat[CPUTIME_SYSTEM];
-	busy_time += kcpustat_cpu(cpu).cpustat[CPUTIME_IRQ];
-	busy_time += kcpustat_cpu(cpu).cpustat[CPUTIME_SOFTIRQ];
-	busy_time += kcpustat_cpu(cpu).cpustat[CPUTIME_STEAL];
-	busy_time += kcpustat_cpu(cpu).cpustat[CPUTIME_NICE];
+	kcpustat_cpu_fetch(&kcpustat, cpu);
+
+	busy_time = kcpustat.cpustat[CPUTIME_USER];
+	busy_time += kcpustat.cpustat[CPUTIME_SYSTEM];
+	busy_time += kcpustat.cpustat[CPUTIME_IRQ];
+	busy_time += kcpustat.cpustat[CPUTIME_SOFTIRQ];
+	busy_time += kcpustat.cpustat[CPUTIME_STEAL];
+	busy_time += kcpustat.cpustat[CPUTIME_NICE];
 
 	idle_time = cur_wall_time - busy_time;
 	if (wall)
@@ -933,6 +936,9 @@ static ssize_t show(struct kobject *kobj, struct attribute *attr, char *buf)
 	struct freq_attr *fattr = to_attr(attr);
 	ssize_t ret;
 
+	if (!fattr->show)
+		return -EIO;
+
 	down_read(&policy->rwsem);
 	ret = fattr->show(policy, buf);
 	up_read(&policy->rwsem);
@@ -947,6 +953,9 @@ static ssize_t store(struct kobject *kobj, struct attribute *attr,
 	struct freq_attr *fattr = to_attr(attr);
 	ssize_t ret = -EINVAL;
 
+	if (!fattr->store)
+		return -EIO;
+
 	/*
 	 * cpus_read_trylock() is used here to work around a circular lock
 	 * dependency problem with respect to the cpufreq_register_driver().
@@ -2385,7 +2394,10 @@ int cpufreq_set_policy(struct cpufreq_policy *policy,
 	new_policy->min = freq_qos_read_value(&policy->constraints, FREQ_QOS_MIN);
 	new_policy->max = freq_qos_read_value(&policy->constraints, FREQ_QOS_MAX);
 
-	/* verify the cpu speed can be set within this limit */
+	/*
+	 * Verify that the CPU speed can be set within these limits and make sure
+	 * that min <= max.
+	 */
 	ret = cpufreq_driver->verify(new_policy);
 	if (ret)
 		return ret;
@@ -2628,6 +2640,13 @@ int cpufreq_register_driver(struct cpufreq_driver *driver_data)
 	if (cpufreq_disabled())
 		return -ENODEV;
 
+	/*
+	 * The cpufreq core depends heavily on the availability of device
+	 * structure, make sure they are available before proceeding further.
+	 */
+	if (!get_cpu_device(0))
+		return -EPROBE_DEFER;
+
 	if (!driver_data || !driver_data->verify || !driver_data->init ||
 	    !(driver_data->setpolicy || driver_data->target_index ||
 		    driver_data->target) ||
diff --git a/drivers/cpufreq/cpufreq_governor.c b/drivers/cpufreq/cpufreq_governor.c
index 4bb054d0cb43..f99ae45efaea 100644
--- a/drivers/cpufreq/cpufreq_governor.c
+++ b/drivers/cpufreq/cpufreq_governor.c
@@ -105,7 +105,7 @@ void gov_update_cpu_data(struct dbs_data *dbs_data)
 			j_cdbs->prev_cpu_idle = get_cpu_idle_time(j, &j_cdbs->prev_update_time,
 								  dbs_data->io_is_busy);
 			if (dbs_data->ignore_nice_load)
-				j_cdbs->prev_cpu_nice = kcpustat_cpu(j).cpustat[CPUTIME_NICE];
+				j_cdbs->prev_cpu_nice = kcpustat_field(&kcpustat_cpu(j), CPUTIME_NICE, j);
 		}
 	}
 }
@@ -149,7 +149,7 @@ unsigned int dbs_update(struct cpufreq_policy *policy)
 		j_cdbs->prev_cpu_idle = cur_idle_time;
 
 		if (ignore_nice) {
-			u64 cur_nice = kcpustat_cpu(j).cpustat[CPUTIME_NICE];
+			u64 cur_nice = kcpustat_field(&kcpustat_cpu(j), CPUTIME_NICE, j);
 
 			idle_time += div_u64(cur_nice - j_cdbs->prev_cpu_nice, NSEC_PER_USEC);
 			j_cdbs->prev_cpu_nice = cur_nice;
@@ -530,7 +530,7 @@ int cpufreq_dbs_governor_start(struct cpufreq_policy *policy)
 		j_cdbs->prev_load = 0;
 
 		if (ignore_nice)
-			j_cdbs->prev_cpu_nice = kcpustat_cpu(j).cpustat[CPUTIME_NICE];
+			j_cdbs->prev_cpu_nice = kcpustat_field(&kcpustat_cpu(j), CPUTIME_NICE, j);
 	}
 
 	gov->start(policy);
diff --git a/drivers/cpufreq/imx-cpufreq-dt.c b/drivers/cpufreq/imx-cpufreq-dt.c
index 35db14cf3102..85a6efd6b68f 100644
--- a/drivers/cpufreq/imx-cpufreq-dt.c
+++ b/drivers/cpufreq/imx-cpufreq-dt.c
@@ -44,19 +44,19 @@ static int imx_cpufreq_dt_probe(struct platform_device *pdev)
 	mkt_segment = (cell_value & OCOTP_CFG3_MKT_SEGMENT_MASK) >> OCOTP_CFG3_MKT_SEGMENT_SHIFT;
 
 	/*
-	 * Early samples without fuses written report "0 0" which means
-	 * consumer segment and minimum speed grading.
-	 *
-	 * According to datasheet minimum speed grading is not supported for
-	 * consumer parts so clamp to 1 to avoid warning for "no OPPs"
+	 * Early samples without fuses written report "0 0" which may NOT
+	 * match any OPP defined in DT. So clamp to minimum OPP defined in
+	 * DT to avoid warning for "no OPPs".
 	 *
 	 * Applies to i.MX8M series SoCs.
 	 */
-	if (mkt_segment == 0 && speed_grade == 0 && (
-			of_machine_is_compatible("fsl,imx8mm") ||
-			of_machine_is_compatible("fsl,imx8mn") ||
-			of_machine_is_compatible("fsl,imx8mq")))
-		speed_grade = 1;
+	if (mkt_segment == 0 && speed_grade == 0) {
+		if (of_machine_is_compatible("fsl,imx8mm") ||
+		    of_machine_is_compatible("fsl,imx8mq"))
+			speed_grade = 1;
+		if (of_machine_is_compatible("fsl,imx8mn"))
+			speed_grade = 0xb;
+	}
 
 	supported_hw[0] = BIT(speed_grade);
 	supported_hw[1] = BIT(mkt_segment);
diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c
index 8ab31702cf6a..d2fa3e9ccd97 100644
--- a/drivers/cpufreq/intel_pstate.c
+++ b/drivers/cpufreq/intel_pstate.c
@@ -2662,21 +2662,21 @@ enum {
 
 /* Hardware vendor-specific info that has its own power management modes */
 static struct acpi_platform_list plat_info[] __initdata = {
-	{"HP    ", "ProLiant", 0, ACPI_SIG_FADT, all_versions, 0, PSS},
-	{"ORACLE", "X4-2    ", 0, ACPI_SIG_FADT, all_versions, 0, PPC},
-	{"ORACLE", "X4-2L   ", 0, ACPI_SIG_FADT, all_versions, 0, PPC},
-	{"ORACLE", "X4-2B   ", 0, ACPI_SIG_FADT, all_versions, 0, PPC},
-	{"ORACLE", "X3-2    ", 0, ACPI_SIG_FADT, all_versions, 0, PPC},
-	{"ORACLE", "X3-2L   ", 0, ACPI_SIG_FADT, all_versions, 0, PPC},
-	{"ORACLE", "X3-2B   ", 0, ACPI_SIG_FADT, all_versions, 0, PPC},
-	{"ORACLE", "X4470M2 ", 0, ACPI_SIG_FADT, all_versions, 0, PPC},
-	{"ORACLE", "X4270M3 ", 0, ACPI_SIG_FADT, all_versions, 0, PPC},
-	{"ORACLE", "X4270M2 ", 0, ACPI_SIG_FADT, all_versions, 0, PPC},
-	{"ORACLE", "X4170M2 ", 0, ACPI_SIG_FADT, all_versions, 0, PPC},
-	{"ORACLE", "X4170 M3", 0, ACPI_SIG_FADT, all_versions, 0, PPC},
-	{"ORACLE", "X4275 M3", 0, ACPI_SIG_FADT, all_versions, 0, PPC},
-	{"ORACLE", "X6-2    ", 0, ACPI_SIG_FADT, all_versions, 0, PPC},
-	{"ORACLE", "Sudbury ", 0, ACPI_SIG_FADT, all_versions, 0, PPC},
+	{"HP    ", "ProLiant", 0, ACPI_SIG_FADT, all_versions, NULL, PSS},
+	{"ORACLE", "X4-2    ", 0, ACPI_SIG_FADT, all_versions, NULL, PPC},
+	{"ORACLE", "X4-2L   ", 0, ACPI_SIG_FADT, all_versions, NULL, PPC},
+	{"ORACLE", "X4-2B   ", 0, ACPI_SIG_FADT, all_versions, NULL, PPC},
+	{"ORACLE", "X3-2    ", 0, ACPI_SIG_FADT, all_versions, NULL, PPC},
+	{"ORACLE", "X3-2L   ", 0, ACPI_SIG_FADT, all_versions, NULL, PPC},
+	{"ORACLE", "X3-2B   ", 0, ACPI_SIG_FADT, all_versions, NULL, PPC},
+	{"ORACLE", "X4470M2 ", 0, ACPI_SIG_FADT, all_versions, NULL, PPC},
+	{"ORACLE", "X4270M3 ", 0, ACPI_SIG_FADT, all_versions, NULL, PPC},
+	{"ORACLE", "X4270M2 ", 0, ACPI_SIG_FADT, all_versions, NULL, PPC},
+	{"ORACLE", "X4170M2 ", 0, ACPI_SIG_FADT, all_versions, NULL, PPC},
+	{"ORACLE", "X4170 M3", 0, ACPI_SIG_FADT, all_versions, NULL, PPC},
+	{"ORACLE", "X4275 M3", 0, ACPI_SIG_FADT, all_versions, NULL, PPC},
+	{"ORACLE", "X6-2    ", 0, ACPI_SIG_FADT, all_versions, NULL, PPC},
+	{"ORACLE", "Sudbury ", 0, ACPI_SIG_FADT, all_versions, NULL, PPC},
 	{ } /* End */
 };
 
diff --git a/drivers/cpufreq/powernv-cpufreq.c b/drivers/cpufreq/powernv-cpufreq.c
index 6061850e59c9..56f4bc0d209e 100644
--- a/drivers/cpufreq/powernv-cpufreq.c
+++ b/drivers/cpufreq/powernv-cpufreq.c
@@ -1041,9 +1041,14 @@ static struct cpufreq_driver powernv_cpufreq_driver = {
 
 static int init_chip_info(void)
 {
-	unsigned int chip[256];
+	unsigned int *chip;
 	unsigned int cpu, i;
 	unsigned int prev_chip_id = UINT_MAX;
+	int ret = 0;
+
+	chip = kcalloc(num_possible_cpus(), sizeof(*chip), GFP_KERNEL);
+	if (!chip)
+		return -ENOMEM;
 
 	for_each_possible_cpu(cpu) {
 		unsigned int id = cpu_to_chip_id(cpu);
@@ -1055,8 +1060,10 @@ static int init_chip_info(void)
 	}
 
 	chips = kcalloc(nr_chips, sizeof(struct chip), GFP_KERNEL);
-	if (!chips)
-		return -ENOMEM;
+	if (!chips) {
+		ret = -ENOMEM;
+		goto free_and_return;
+	}
 
 	for (i = 0; i < nr_chips; i++) {
 		chips[i].id = chip[i];
@@ -1066,7 +1073,9 @@ static int init_chip_info(void)
 			per_cpu(chip_info, cpu) =  &chips[i];
 	}
 
-	return 0;
+free_and_return:
+	kfree(chip);
+	return ret;
 }
 
 static inline void clean_chip_info(void)
diff --git a/drivers/cpufreq/s3c64xx-cpufreq.c b/drivers/cpufreq/s3c64xx-cpufreq.c
index af0c00dabb22..c6bdfc308e99 100644
--- a/drivers/cpufreq/s3c64xx-cpufreq.c
+++ b/drivers/cpufreq/s3c64xx-cpufreq.c
@@ -19,7 +19,6 @@
 static struct regulator *vddarm;
 static unsigned long regulator_latency;
 
-#ifdef CONFIG_CPU_S3C6410
 struct s3c64xx_dvfs {
 	unsigned int vddarm_min;
 	unsigned int vddarm_max;
@@ -48,7 +47,6 @@ static struct cpufreq_frequency_table s3c64xx_freq_table[] = {
 	{ 0, 4, 800000 },
 	{ 0, 0, CPUFREQ_TABLE_END },
 };
-#endif
 
 static int s3c64xx_cpufreq_set_target(struct cpufreq_policy *policy,
 				      unsigned int index)
@@ -149,11 +147,6 @@ static int s3c64xx_cpufreq_driver_init(struct cpufreq_policy *policy)
 	if (policy->cpu != 0)
 		return -EINVAL;
 
-	if (s3c64xx_freq_table == NULL) {
-		pr_err("No frequency information for this CPU\n");
-		return -ENODEV;
-	}
-
 	policy->clk = clk_get(NULL, "armclk");
 	if (IS_ERR(policy->clk)) {
 		pr_err("Unable to obtain ARMCLK: %ld\n",
diff --git a/drivers/cpufreq/scpi-cpufreq.c b/drivers/cpufreq/scpi-cpufreq.c
index 2b51e0718c9f..20d1f85d5f5a 100644
--- a/drivers/cpufreq/scpi-cpufreq.c
+++ b/drivers/cpufreq/scpi-cpufreq.c
@@ -1,8 +1,6 @@
 /*
  * System Control and Power Interface (SCPI) based CPUFreq Interface driver
  *
- * It provides necessary ops to arm_big_little cpufreq driver.
- *
  * Copyright (C) 2015 ARM Ltd.
  * Sudeep Holla <sudeep.holla@arm.com>
  *
diff --git a/drivers/cpufreq/sun50i-cpufreq-nvmem.c b/drivers/cpufreq/sun50i-cpufreq-nvmem.c
index eca32e443716..9907a165135b 100644
--- a/drivers/cpufreq/sun50i-cpufreq-nvmem.c
+++ b/drivers/cpufreq/sun50i-cpufreq-nvmem.c
@@ -25,7 +25,7 @@
 static struct platform_device *cpufreq_dt_pdev, *sun50i_cpufreq_pdev;
 
 /**
- * sun50i_cpufreq_get_efuse() - Parse and return efuse value present on SoC
+ * sun50i_cpufreq_get_efuse() - Determine speed grade from efuse value
  * @versions: Set to the value parsed from efuse
  *
  * Returns 0 if success.
@@ -69,21 +69,16 @@ static int sun50i_cpufreq_get_efuse(u32 *versions)
 		return PTR_ERR(speedbin);
 
 	efuse_value = (*speedbin >> NVMEM_SHIFT) & NVMEM_MASK;
-	switch (efuse_value) {
-	case 0b0001:
-		*versions = 1;
-		break;
-	case 0b0011:
-		*versions = 2;
-		break;
-	default:
-		/*
-		 * For other situations, we treat it as bin0.
-		 * This vf table can be run for any good cpu.
-		 */
+
+	/*
+	 * We treat unexpected efuse values as if the SoC was from
+	 * the slowest bin. Expected efuse values are 1-3, slowest
+	 * to fastest.
+	 */
+	if (efuse_value >= 1 && efuse_value <= 3)
+		*versions = efuse_value - 1;
+	else
 		*versions = 0;
-		break;
-	}
 
 	kfree(speedbin);
 	return 0;
diff --git a/drivers/cpufreq/ti-cpufreq.c b/drivers/cpufreq/ti-cpufreq.c
index aeaa883a8c9d..557cb513bf7f 100644
--- a/drivers/cpufreq/ti-cpufreq.c
+++ b/drivers/cpufreq/ti-cpufreq.c
@@ -31,11 +31,17 @@
 #define DRA7_EFUSE_OD_MPU_OPP			BIT(1)
 #define DRA7_EFUSE_HIGH_MPU_OPP			BIT(2)
 
+#define OMAP3_CONTROL_DEVICE_STATUS		0x4800244C
+#define OMAP3_CONTROL_IDCODE			0x4830A204
+#define OMAP34xx_ProdID_SKUID			0x4830A20C
+#define OMAP3_SYSCON_BASE	(0x48000000 + 0x2000 + 0x270)
+
 #define VERSION_COUNT				2
 
 struct ti_cpufreq_data;
 
 struct ti_cpufreq_soc_data {
+	const char * const *reg_names;
 	unsigned long (*efuse_xlate)(struct ti_cpufreq_data *opp_data,
 				     unsigned long efuse);
 	unsigned long efuse_fallback;
@@ -85,6 +91,13 @@ static unsigned long dra7_efuse_xlate(struct ti_cpufreq_data *opp_data,
 	return calculated_efuse;
 }
 
+static unsigned long omap3_efuse_xlate(struct ti_cpufreq_data *opp_data,
+				      unsigned long efuse)
+{
+	/* OPP enable bit ("Speed Binned") */
+	return BIT(efuse);
+}
+
 static struct ti_cpufreq_soc_data am3x_soc_data = {
 	.efuse_xlate = amx3_efuse_xlate,
 	.efuse_fallback = AM33XX_800M_ARM_MPU_MAX_FREQ,
@@ -112,6 +125,74 @@ static struct ti_cpufreq_soc_data dra7_soc_data = {
 	.multi_regulator = true,
 };
 
+/*
+ * OMAP35x TRM (SPRUF98K):
+ *  CONTROL_IDCODE (0x4830 A204) describes Silicon revisions.
+ *  Control OMAP Status Register 15:0 (Address 0x4800 244C)
+ *    to separate between omap3503, omap3515, omap3525, omap3530
+ *    and feature presence.
+ *    There are encodings for versions limited to 400/266MHz
+ *    but we ignore.
+ *    Not clear if this also holds for omap34xx.
+ *  some eFuse values e.g. CONTROL_FUSE_OPP1_VDD1
+ *    are stored in the SYSCON register range
+ *  Register 0x4830A20C [ProdID.SKUID] [0:3]
+ *    0x0 for normal 600/430MHz device.
+ *    0x8 for 720/520MHz device.
+ *    Not clear what omap34xx value is.
+ */
+
+static struct ti_cpufreq_soc_data omap34xx_soc_data = {
+	.efuse_xlate = omap3_efuse_xlate,
+	.efuse_offset = OMAP34xx_ProdID_SKUID - OMAP3_SYSCON_BASE,
+	.efuse_shift = 3,
+	.efuse_mask = BIT(3),
+	.rev_offset = OMAP3_CONTROL_IDCODE - OMAP3_SYSCON_BASE,
+	.multi_regulator = false,
+};
+
+/*
+ * AM/DM37x TRM (SPRUGN4M)
+ *  CONTROL_IDCODE (0x4830 A204) describes Silicon revisions.
+ *  Control Device Status Register 15:0 (Address 0x4800 244C)
+ *    to separate between am3703, am3715, dm3725, dm3730
+ *    and feature presence.
+ *   Speed Binned = Bit 9
+ *     0 800/600 MHz
+ *     1 1000/800 MHz
+ *  some eFuse values e.g. CONTROL_FUSE_OPP 1G_VDD1
+ *    are stored in the SYSCON register range.
+ *  There is no 0x4830A20C [ProdID.SKUID] register (exists but
+ *    seems to always read as 0).
+ */
+
+static const char * const omap3_reg_names[] = {"cpu0", "vbb"};
+
+static struct ti_cpufreq_soc_data omap36xx_soc_data = {
+	.reg_names = omap3_reg_names,
+	.efuse_xlate = omap3_efuse_xlate,
+	.efuse_offset = OMAP3_CONTROL_DEVICE_STATUS - OMAP3_SYSCON_BASE,
+	.efuse_shift = 9,
+	.efuse_mask = BIT(9),
+	.rev_offset = OMAP3_CONTROL_IDCODE - OMAP3_SYSCON_BASE,
+	.multi_regulator = true,
+};
+
+/*
+ * AM3517 is quite similar to AM/DM37x except that it has no
+ * high speed grade eFuse and no abb ldo
+ */
+
+static struct ti_cpufreq_soc_data am3517_soc_data = {
+	.efuse_xlate = omap3_efuse_xlate,
+	.efuse_offset = OMAP3_CONTROL_DEVICE_STATUS - OMAP3_SYSCON_BASE,
+	.efuse_shift = 0,
+	.efuse_mask = 0,
+	.rev_offset = OMAP3_CONTROL_IDCODE - OMAP3_SYSCON_BASE,
+	.multi_regulator = false,
+};
+
+
 /**
  * ti_cpufreq_get_efuse() - Parse and return efuse value present on SoC
  * @opp_data: pointer to ti_cpufreq_data context
@@ -128,7 +209,17 @@ static int ti_cpufreq_get_efuse(struct ti_cpufreq_data *opp_data,
 
 	ret = regmap_read(opp_data->syscon, opp_data->soc_data->efuse_offset,
 			  &efuse);
-	if (ret) {
+	if (ret == -EIO) {
+		/* not a syscon register! */
+		void __iomem *regs = ioremap(OMAP3_SYSCON_BASE +
+				opp_data->soc_data->efuse_offset, 4);
+
+		if (!regs)
+			return -ENOMEM;
+		efuse = readl(regs);
+		iounmap(regs);
+		}
+	else if (ret) {
 		dev_err(dev,
 			"Failed to read the efuse value from syscon: %d\n",
 			ret);
@@ -159,7 +250,17 @@ static int ti_cpufreq_get_rev(struct ti_cpufreq_data *opp_data,
 
 	ret = regmap_read(opp_data->syscon, opp_data->soc_data->rev_offset,
 			  &revision);
-	if (ret) {
+	if (ret == -EIO) {
+		/* not a syscon register! */
+		void __iomem *regs = ioremap(OMAP3_SYSCON_BASE +
+				opp_data->soc_data->rev_offset, 4);
+
+		if (!regs)
+			return -ENOMEM;
+		revision = readl(regs);
+		iounmap(regs);
+		}
+	else if (ret) {
 		dev_err(dev,
 			"Failed to read the revision number from syscon: %d\n",
 			ret);
@@ -189,8 +290,14 @@ static int ti_cpufreq_setup_syscon_register(struct ti_cpufreq_data *opp_data)
 
 static const struct of_device_id ti_cpufreq_of_match[] = {
 	{ .compatible = "ti,am33xx", .data = &am3x_soc_data, },
+	{ .compatible = "ti,am3517", .data = &am3517_soc_data, },
 	{ .compatible = "ti,am43", .data = &am4x_soc_data, },
 	{ .compatible = "ti,dra7", .data = &dra7_soc_data },
+	{ .compatible = "ti,omap34xx", .data = &omap34xx_soc_data, },
+	{ .compatible = "ti,omap36xx", .data = &omap36xx_soc_data, },
+	/* legacy */
+	{ .compatible = "ti,omap3430", .data = &omap34xx_soc_data, },
+	{ .compatible = "ti,omap3630", .data = &omap36xx_soc_data, },
 	{},
 };
 
@@ -212,7 +319,7 @@ static int ti_cpufreq_probe(struct platform_device *pdev)
 	const struct of_device_id *match;
 	struct opp_table *ti_opp_table;
 	struct ti_cpufreq_data *opp_data;
-	const char * const reg_names[] = {"vdd", "vbb"};
+	const char * const default_reg_names[] = {"vdd", "vbb"};
 	int ret;
 
 	match = dev_get_platdata(&pdev->dev);
@@ -268,9 +375,13 @@ static int ti_cpufreq_probe(struct platform_device *pdev)
 	opp_data->opp_table = ti_opp_table;
 
 	if (opp_data->soc_data->multi_regulator) {
+		const char * const *reg_names = default_reg_names;
+
+		if (opp_data->soc_data->reg_names)
+			reg_names = opp_data->soc_data->reg_names;
 		ti_opp_table = dev_pm_opp_set_regulators(opp_data->cpu_dev,
 							 reg_names,
-							 ARRAY_SIZE(reg_names));
+							 ARRAY_SIZE(default_reg_names));
 		if (IS_ERR(ti_opp_table)) {
 			dev_pm_opp_put_supported_hw(opp_data->opp_table);
 			ret =  PTR_ERR(ti_opp_table);
diff --git a/drivers/cpufreq/vexpress-spc-cpufreq.c b/drivers/cpufreq/vexpress-spc-cpufreq.c
index 53237289e606..506e3f2bf53a 100644
--- a/drivers/cpufreq/vexpress-spc-cpufreq.c
+++ b/drivers/cpufreq/vexpress-spc-cpufreq.c
@@ -1,61 +1,592 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Versatile Express SPC CPUFreq Interface driver
  *
- * It provides necessary ops to arm_big_little cpufreq driver.
+ * Copyright (C) 2013 - 2019 ARM Ltd.
+ * Sudeep Holla <sudeep.holla@arm.com>
  *
- * Copyright (C) 2013 ARM Ltd.
- * Sudeep KarkadaNagesha <sudeep.karkadanagesha@arm.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
- * This program is distributed "as is" WITHOUT ANY WARRANTY of any
- * kind, whether express or implied; without even the implied warranty
- * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
+ * Copyright (C) 2013 Linaro.
+ * Viresh Kumar <viresh.kumar@linaro.org>
  */
 
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
 
+#include <linux/clk.h>
 #include <linux/cpu.h>
 #include <linux/cpufreq.h>
+#include <linux/cpumask.h>
+#include <linux/cpu_cooling.h>
+#include <linux/device.h>
 #include <linux/module.h>
+#include <linux/mutex.h>
+#include <linux/of_platform.h>
 #include <linux/platform_device.h>
 #include <linux/pm_opp.h>
+#include <linux/slab.h>
+#include <linux/topology.h>
 #include <linux/types.h>
 
-#include "arm_big_little.h"
+/* Currently we support only two clusters */
+#define A15_CLUSTER	0
+#define A7_CLUSTER	1
+#define MAX_CLUSTERS	2
+
+#ifdef CONFIG_BL_SWITCHER
+#include <asm/bL_switcher.h>
+static bool bL_switching_enabled;
+#define is_bL_switching_enabled()	bL_switching_enabled
+#define set_switching_enabled(x)	(bL_switching_enabled = (x))
+#else
+#define is_bL_switching_enabled()	false
+#define set_switching_enabled(x)	do { } while (0)
+#define bL_switch_request(...)		do { } while (0)
+#define bL_switcher_put_enabled()	do { } while (0)
+#define bL_switcher_get_enabled()	do { } while (0)
+#endif
+
+#define ACTUAL_FREQ(cluster, freq)  ((cluster == A7_CLUSTER) ? freq << 1 : freq)
+#define VIRT_FREQ(cluster, freq)    ((cluster == A7_CLUSTER) ? freq >> 1 : freq)
+
+static struct thermal_cooling_device *cdev[MAX_CLUSTERS];
+static struct clk *clk[MAX_CLUSTERS];
+static struct cpufreq_frequency_table *freq_table[MAX_CLUSTERS + 1];
+static atomic_t cluster_usage[MAX_CLUSTERS + 1];
+
+static unsigned int clk_big_min;	/* (Big) clock frequencies */
+static unsigned int clk_little_max;	/* Maximum clock frequency (Little) */
+
+static DEFINE_PER_CPU(unsigned int, physical_cluster);
+static DEFINE_PER_CPU(unsigned int, cpu_last_req_freq);
+
+static struct mutex cluster_lock[MAX_CLUSTERS];
+
+static inline int raw_cpu_to_cluster(int cpu)
+{
+	return topology_physical_package_id(cpu);
+}
+
+static inline int cpu_to_cluster(int cpu)
+{
+	return is_bL_switching_enabled() ?
+		MAX_CLUSTERS : raw_cpu_to_cluster(cpu);
+}
+
+static unsigned int find_cluster_maxfreq(int cluster)
+{
+	int j;
+	u32 max_freq = 0, cpu_freq;
+
+	for_each_online_cpu(j) {
+		cpu_freq = per_cpu(cpu_last_req_freq, j);
+
+		if (cluster == per_cpu(physical_cluster, j) &&
+		    max_freq < cpu_freq)
+			max_freq = cpu_freq;
+	}
+
+	return max_freq;
+}
+
+static unsigned int clk_get_cpu_rate(unsigned int cpu)
+{
+	u32 cur_cluster = per_cpu(physical_cluster, cpu);
+	u32 rate = clk_get_rate(clk[cur_cluster]) / 1000;
+
+	/* For switcher we use virtual A7 clock rates */
+	if (is_bL_switching_enabled())
+		rate = VIRT_FREQ(cur_cluster, rate);
+
+	return rate;
+}
+
+static unsigned int ve_spc_cpufreq_get_rate(unsigned int cpu)
+{
+	if (is_bL_switching_enabled())
+		return per_cpu(cpu_last_req_freq, cpu);
+	else
+		return clk_get_cpu_rate(cpu);
+}
+
+static unsigned int
+ve_spc_cpufreq_set_rate(u32 cpu, u32 old_cluster, u32 new_cluster, u32 rate)
+{
+	u32 new_rate, prev_rate;
+	int ret;
+	bool bLs = is_bL_switching_enabled();
+
+	mutex_lock(&cluster_lock[new_cluster]);
+
+	if (bLs) {
+		prev_rate = per_cpu(cpu_last_req_freq, cpu);
+		per_cpu(cpu_last_req_freq, cpu) = rate;
+		per_cpu(physical_cluster, cpu) = new_cluster;
+
+		new_rate = find_cluster_maxfreq(new_cluster);
+		new_rate = ACTUAL_FREQ(new_cluster, new_rate);
+	} else {
+		new_rate = rate;
+	}
+
+	ret = clk_set_rate(clk[new_cluster], new_rate * 1000);
+	if (!ret) {
+		/*
+		 * FIXME: clk_set_rate hasn't returned an error here however it
+		 * may be that clk_change_rate failed due to hardware or
+		 * firmware issues and wasn't able to report that due to the
+		 * current design of the clk core layer. To work around this
+		 * problem we will read back the clock rate and check it is
+		 * correct. This needs to be removed once clk core is fixed.
+		 */
+		if (clk_get_rate(clk[new_cluster]) != new_rate * 1000)
+			ret = -EIO;
+	}
+
+	if (WARN_ON(ret)) {
+		if (bLs) {
+			per_cpu(cpu_last_req_freq, cpu) = prev_rate;
+			per_cpu(physical_cluster, cpu) = old_cluster;
+		}
+
+		mutex_unlock(&cluster_lock[new_cluster]);
+
+		return ret;
+	}
+
+	mutex_unlock(&cluster_lock[new_cluster]);
+
+	/* Recalc freq for old cluster when switching clusters */
+	if (old_cluster != new_cluster) {
+		/* Switch cluster */
+		bL_switch_request(cpu, new_cluster);
+
+		mutex_lock(&cluster_lock[old_cluster]);
+
+		/* Set freq of old cluster if there are cpus left on it */
+		new_rate = find_cluster_maxfreq(old_cluster);
+		new_rate = ACTUAL_FREQ(old_cluster, new_rate);
+
+		if (new_rate &&
+		    clk_set_rate(clk[old_cluster], new_rate * 1000)) {
+			pr_err("%s: clk_set_rate failed: %d, old cluster: %d\n",
+			       __func__, ret, old_cluster);
+		}
+		mutex_unlock(&cluster_lock[old_cluster]);
+	}
+
+	return 0;
+}
+
+/* Set clock frequency */
+static int ve_spc_cpufreq_set_target(struct cpufreq_policy *policy,
+				     unsigned int index)
+{
+	u32 cpu = policy->cpu, cur_cluster, new_cluster, actual_cluster;
+	unsigned int freqs_new;
+	int ret;
+
+	cur_cluster = cpu_to_cluster(cpu);
+	new_cluster = actual_cluster = per_cpu(physical_cluster, cpu);
+
+	freqs_new = freq_table[cur_cluster][index].frequency;
+
+	if (is_bL_switching_enabled()) {
+		if (actual_cluster == A15_CLUSTER && freqs_new < clk_big_min)
+			new_cluster = A7_CLUSTER;
+		else if (actual_cluster == A7_CLUSTER &&
+			 freqs_new > clk_little_max)
+			new_cluster = A15_CLUSTER;
+	}
+
+	ret = ve_spc_cpufreq_set_rate(cpu, actual_cluster, new_cluster,
+				      freqs_new);
+
+	if (!ret) {
+		arch_set_freq_scale(policy->related_cpus, freqs_new,
+				    policy->cpuinfo.max_freq);
+	}
+
+	return ret;
+}
+
+static inline u32 get_table_count(struct cpufreq_frequency_table *table)
+{
+	int count;
+
+	for (count = 0; table[count].frequency != CPUFREQ_TABLE_END; count++)
+		;
+
+	return count;
+}
+
+/* get the minimum frequency in the cpufreq_frequency_table */
+static inline u32 get_table_min(struct cpufreq_frequency_table *table)
+{
+	struct cpufreq_frequency_table *pos;
+	u32 min_freq = ~0;
+
+	cpufreq_for_each_entry(pos, table)
+		if (pos->frequency < min_freq)
+			min_freq = pos->frequency;
+	return min_freq;
+}
+
+/* get the maximum frequency in the cpufreq_frequency_table */
+static inline u32 get_table_max(struct cpufreq_frequency_table *table)
+{
+	struct cpufreq_frequency_table *pos;
+	u32 max_freq = 0;
+
+	cpufreq_for_each_entry(pos, table)
+		if (pos->frequency > max_freq)
+			max_freq = pos->frequency;
+	return max_freq;
+}
+
+static bool search_frequency(struct cpufreq_frequency_table *table, int size,
+			     unsigned int freq)
+{
+	int count;
+
+	for (count = 0; count < size; count++) {
+		if (table[count].frequency == freq)
+			return true;
+	}
+
+	return false;
+}
+
+static int merge_cluster_tables(void)
+{
+	int i, j, k = 0, count = 1;
+	struct cpufreq_frequency_table *table;
+
+	for (i = 0; i < MAX_CLUSTERS; i++)
+		count += get_table_count(freq_table[i]);
+
+	table = kcalloc(count, sizeof(*table), GFP_KERNEL);
+	if (!table)
+		return -ENOMEM;
+
+	freq_table[MAX_CLUSTERS] = table;
+
+	/* Add in reverse order to get freqs in increasing order */
+	for (i = MAX_CLUSTERS - 1; i >= 0; i--, count = k) {
+		for (j = 0; freq_table[i][j].frequency != CPUFREQ_TABLE_END;
+		     j++) {
+			if (i == A15_CLUSTER &&
+			    search_frequency(table, count, freq_table[i][j].frequency))
+				continue; /* skip duplicates */
+			table[k++].frequency =
+				VIRT_FREQ(i, freq_table[i][j].frequency);
+		}
+	}
+
+	table[k].driver_data = k;
+	table[k].frequency = CPUFREQ_TABLE_END;
+
+	return 0;
+}
 
-static int ve_spc_init_opp_table(const struct cpumask *cpumask)
+static void _put_cluster_clk_and_freq_table(struct device *cpu_dev,
+					    const struct cpumask *cpumask)
 {
-	struct device *cpu_dev = get_cpu_device(cpumask_first(cpumask));
+	u32 cluster = raw_cpu_to_cluster(cpu_dev->id);
+
+	if (!freq_table[cluster])
+		return;
+
+	clk_put(clk[cluster]);
+	dev_pm_opp_free_cpufreq_table(cpu_dev, &freq_table[cluster]);
+}
+
+static void put_cluster_clk_and_freq_table(struct device *cpu_dev,
+					   const struct cpumask *cpumask)
+{
+	u32 cluster = cpu_to_cluster(cpu_dev->id);
+	int i;
+
+	if (atomic_dec_return(&cluster_usage[cluster]))
+		return;
+
+	if (cluster < MAX_CLUSTERS)
+		return _put_cluster_clk_and_freq_table(cpu_dev, cpumask);
+
+	for_each_present_cpu(i) {
+		struct device *cdev = get_cpu_device(i);
+
+		if (!cdev)
+			return;
+
+		_put_cluster_clk_and_freq_table(cdev, cpumask);
+	}
+
+	/* free virtual table */
+	kfree(freq_table[cluster]);
+}
+
+static int _get_cluster_clk_and_freq_table(struct device *cpu_dev,
+					   const struct cpumask *cpumask)
+{
+	u32 cluster = raw_cpu_to_cluster(cpu_dev->id);
+	int ret;
+
+	if (freq_table[cluster])
+		return 0;
+
 	/*
 	 * platform specific SPC code must initialise the opp table
 	 * so just check if the OPP count is non-zero
 	 */
-	return dev_pm_opp_get_opp_count(cpu_dev) <= 0;
+	ret = dev_pm_opp_get_opp_count(cpu_dev) <= 0;
+	if (ret)
+		goto out;
+
+	ret = dev_pm_opp_init_cpufreq_table(cpu_dev, &freq_table[cluster]);
+	if (ret)
+		goto out;
+
+	clk[cluster] = clk_get(cpu_dev, NULL);
+	if (!IS_ERR(clk[cluster]))
+		return 0;
+
+	dev_err(cpu_dev, "%s: Failed to get clk for cpu: %d, cluster: %d\n",
+		__func__, cpu_dev->id, cluster);
+	ret = PTR_ERR(clk[cluster]);
+	dev_pm_opp_free_cpufreq_table(cpu_dev, &freq_table[cluster]);
+
+out:
+	dev_err(cpu_dev, "%s: Failed to get data for cluster: %d\n", __func__,
+		cluster);
+	return ret;
 }
 
-static int ve_spc_get_transition_latency(struct device *cpu_dev)
+static int get_cluster_clk_and_freq_table(struct device *cpu_dev,
+					  const struct cpumask *cpumask)
 {
-	return 1000000; /* 1 ms */
+	u32 cluster = cpu_to_cluster(cpu_dev->id);
+	int i, ret;
+
+	if (atomic_inc_return(&cluster_usage[cluster]) != 1)
+		return 0;
+
+	if (cluster < MAX_CLUSTERS) {
+		ret = _get_cluster_clk_and_freq_table(cpu_dev, cpumask);
+		if (ret)
+			atomic_dec(&cluster_usage[cluster]);
+		return ret;
+	}
+
+	/*
+	 * Get data for all clusters and fill virtual cluster with a merge of
+	 * both
+	 */
+	for_each_present_cpu(i) {
+		struct device *cdev = get_cpu_device(i);
+
+		if (!cdev)
+			return -ENODEV;
+
+		ret = _get_cluster_clk_and_freq_table(cdev, cpumask);
+		if (ret)
+			goto put_clusters;
+	}
+
+	ret = merge_cluster_tables();
+	if (ret)
+		goto put_clusters;
+
+	/* Assuming 2 cluster, set clk_big_min and clk_little_max */
+	clk_big_min = get_table_min(freq_table[A15_CLUSTER]);
+	clk_little_max = VIRT_FREQ(A7_CLUSTER,
+				   get_table_max(freq_table[A7_CLUSTER]));
+
+	return 0;
+
+put_clusters:
+	for_each_present_cpu(i) {
+		struct device *cdev = get_cpu_device(i);
+
+		if (!cdev)
+			return -ENODEV;
+
+		_put_cluster_clk_and_freq_table(cdev, cpumask);
+	}
+
+	atomic_dec(&cluster_usage[cluster]);
+
+	return ret;
 }
 
-static const struct cpufreq_arm_bL_ops ve_spc_cpufreq_ops = {
-	.name	= "vexpress-spc",
-	.get_transition_latency = ve_spc_get_transition_latency,
-	.init_opp_table = ve_spc_init_opp_table,
+/* Per-CPU initialization */
+static int ve_spc_cpufreq_init(struct cpufreq_policy *policy)
+{
+	u32 cur_cluster = cpu_to_cluster(policy->cpu);
+	struct device *cpu_dev;
+	int ret;
+
+	cpu_dev = get_cpu_device(policy->cpu);
+	if (!cpu_dev) {
+		pr_err("%s: failed to get cpu%d device\n", __func__,
+		       policy->cpu);
+		return -ENODEV;
+	}
+
+	if (cur_cluster < MAX_CLUSTERS) {
+		int cpu;
+
+		cpumask_copy(policy->cpus, topology_core_cpumask(policy->cpu));
+
+		for_each_cpu(cpu, policy->cpus)
+			per_cpu(physical_cluster, cpu) = cur_cluster;
+	} else {
+		/* Assumption: during init, we are always running on A15 */
+		per_cpu(physical_cluster, policy->cpu) = A15_CLUSTER;
+	}
+
+	ret = get_cluster_clk_and_freq_table(cpu_dev, policy->cpus);
+	if (ret)
+		return ret;
+
+	policy->freq_table = freq_table[cur_cluster];
+	policy->cpuinfo.transition_latency = 1000000; /* 1 ms */
+
+	dev_pm_opp_of_register_em(policy->cpus);
+
+	if (is_bL_switching_enabled())
+		per_cpu(cpu_last_req_freq, policy->cpu) =
+						clk_get_cpu_rate(policy->cpu);
+
+	dev_info(cpu_dev, "%s: CPU %d initialized\n", __func__, policy->cpu);
+	return 0;
+}
+
+static int ve_spc_cpufreq_exit(struct cpufreq_policy *policy)
+{
+	struct device *cpu_dev;
+	int cur_cluster = cpu_to_cluster(policy->cpu);
+
+	if (cur_cluster < MAX_CLUSTERS) {
+		cpufreq_cooling_unregister(cdev[cur_cluster]);
+		cdev[cur_cluster] = NULL;
+	}
+
+	cpu_dev = get_cpu_device(policy->cpu);
+	if (!cpu_dev) {
+		pr_err("%s: failed to get cpu%d device\n", __func__,
+		       policy->cpu);
+		return -ENODEV;
+	}
+
+	put_cluster_clk_and_freq_table(cpu_dev, policy->related_cpus);
+	return 0;
+}
+
+static void ve_spc_cpufreq_ready(struct cpufreq_policy *policy)
+{
+	int cur_cluster = cpu_to_cluster(policy->cpu);
+
+	/* Do not register a cpu_cooling device if we are in IKS mode */
+	if (cur_cluster >= MAX_CLUSTERS)
+		return;
+
+	cdev[cur_cluster] = of_cpufreq_cooling_register(policy);
+}
+
+static struct cpufreq_driver ve_spc_cpufreq_driver = {
+	.name			= "vexpress-spc",
+	.flags			= CPUFREQ_STICKY |
+					CPUFREQ_HAVE_GOVERNOR_PER_POLICY |
+					CPUFREQ_NEED_INITIAL_FREQ_CHECK,
+	.verify			= cpufreq_generic_frequency_table_verify,
+	.target_index		= ve_spc_cpufreq_set_target,
+	.get			= ve_spc_cpufreq_get_rate,
+	.init			= ve_spc_cpufreq_init,
+	.exit			= ve_spc_cpufreq_exit,
+	.ready			= ve_spc_cpufreq_ready,
+	.attr			= cpufreq_generic_attr,
 };
 
+#ifdef CONFIG_BL_SWITCHER
+static int bL_cpufreq_switcher_notifier(struct notifier_block *nfb,
+					unsigned long action, void *_arg)
+{
+	pr_debug("%s: action: %ld\n", __func__, action);
+
+	switch (action) {
+	case BL_NOTIFY_PRE_ENABLE:
+	case BL_NOTIFY_PRE_DISABLE:
+		cpufreq_unregister_driver(&ve_spc_cpufreq_driver);
+		break;
+
+	case BL_NOTIFY_POST_ENABLE:
+		set_switching_enabled(true);
+		cpufreq_register_driver(&ve_spc_cpufreq_driver);
+		break;
+
+	case BL_NOTIFY_POST_DISABLE:
+		set_switching_enabled(false);
+		cpufreq_register_driver(&ve_spc_cpufreq_driver);
+		break;
+
+	default:
+		return NOTIFY_DONE;
+	}
+
+	return NOTIFY_OK;
+}
+
+static struct notifier_block bL_switcher_notifier = {
+	.notifier_call = bL_cpufreq_switcher_notifier,
+};
+
+static int __bLs_register_notifier(void)
+{
+	return bL_switcher_register_notifier(&bL_switcher_notifier);
+}
+
+static int __bLs_unregister_notifier(void)
+{
+	return bL_switcher_unregister_notifier(&bL_switcher_notifier);
+}
+#else
+static int __bLs_register_notifier(void) { return 0; }
+static int __bLs_unregister_notifier(void) { return 0; }
+#endif
+
 static int ve_spc_cpufreq_probe(struct platform_device *pdev)
 {
-	return bL_cpufreq_register(&ve_spc_cpufreq_ops);
+	int ret, i;
+
+	set_switching_enabled(bL_switcher_get_enabled());
+
+	for (i = 0; i < MAX_CLUSTERS; i++)
+		mutex_init(&cluster_lock[i]);
+
+	ret = cpufreq_register_driver(&ve_spc_cpufreq_driver);
+	if (ret) {
+		pr_info("%s: Failed registering platform driver: %s, err: %d\n",
+			__func__, ve_spc_cpufreq_driver.name, ret);
+	} else {
+		ret = __bLs_register_notifier();
+		if (ret)
+			cpufreq_unregister_driver(&ve_spc_cpufreq_driver);
+		else
+			pr_info("%s: Registered platform driver: %s\n",
+				__func__, ve_spc_cpufreq_driver.name);
+	}
+
+	bL_switcher_put_enabled();
+	return ret;
 }
 
 static int ve_spc_cpufreq_remove(struct platform_device *pdev)
 {
-	bL_cpufreq_unregister(&ve_spc_cpufreq_ops);
+	bL_switcher_get_enabled();
+	__bLs_unregister_notifier();
+	cpufreq_unregister_driver(&ve_spc_cpufreq_driver);
+	bL_switcher_put_enabled();
+	pr_info("%s: Un-registered platform driver: %s\n", __func__,
+		ve_spc_cpufreq_driver.name);
 	return 0;
 }
 
@@ -68,4 +599,7 @@ static struct platform_driver ve_spc_cpufreq_platdrv = {
 };
 module_platform_driver(ve_spc_cpufreq_platdrv);
 
-MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Viresh Kumar <viresh.kumar@linaro.org>");
+MODULE_AUTHOR("Sudeep Holla <sudeep.holla@arm.com>");
+MODULE_DESCRIPTION("Vexpress SPC ARM big LITTLE cpufreq driver");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/cpuidle/cpuidle-powernv.c b/drivers/cpuidle/cpuidle-powernv.c
index 84b1ebe212b3..1b299e801f74 100644
--- a/drivers/cpuidle/cpuidle-powernv.c
+++ b/drivers/cpuidle/cpuidle-powernv.c
@@ -56,13 +56,10 @@ static u64 get_snooze_timeout(struct cpuidle_device *dev,
 		return default_snooze_timeout;
 
 	for (i = index + 1; i < drv->state_count; i++) {
-		struct cpuidle_state *s = &drv->states[i];
-		struct cpuidle_state_usage *su = &dev->states_usage[i];
-
-		if (s->disabled || su->disable)
+		if (dev->states_usage[i].disable)
 			continue;
 
-		return s->target_residency * tb_ticks_per_usec;
+		return drv->states[i].target_residency * tb_ticks_per_usec;
 	}
 
 	return default_snooze_timeout;
diff --git a/drivers/cpuidle/cpuidle.c b/drivers/cpuidle/cpuidle.c
index 0895b988fa92..569dbac443bd 100644
--- a/drivers/cpuidle/cpuidle.c
+++ b/drivers/cpuidle/cpuidle.c
@@ -75,44 +75,45 @@ int cpuidle_play_dead(void)
 
 static int find_deepest_state(struct cpuidle_driver *drv,
 			      struct cpuidle_device *dev,
-			      unsigned int max_latency,
+			      u64 max_latency_ns,
 			      unsigned int forbidden_flags,
 			      bool s2idle)
 {
-	unsigned int latency_req = 0;
+	u64 latency_req = 0;
 	int i, ret = 0;
 
 	for (i = 1; i < drv->state_count; i++) {
 		struct cpuidle_state *s = &drv->states[i];
-		struct cpuidle_state_usage *su = &dev->states_usage[i];
 
-		if (s->disabled || su->disable || s->exit_latency <= latency_req
-		    || s->exit_latency > max_latency
-		    || (s->flags & forbidden_flags)
-		    || (s2idle && !s->enter_s2idle))
+		if (dev->states_usage[i].disable ||
+		    s->exit_latency_ns <= latency_req ||
+		    s->exit_latency_ns > max_latency_ns ||
+		    (s->flags & forbidden_flags) ||
+		    (s2idle && !s->enter_s2idle))
 			continue;
 
-		latency_req = s->exit_latency;
+		latency_req = s->exit_latency_ns;
 		ret = i;
 	}
 	return ret;
 }
 
 /**
- * cpuidle_use_deepest_state - Set/clear governor override flag.
- * @enable: New value of the flag.
+ * cpuidle_use_deepest_state - Set/unset governor override mode.
+ * @latency_limit_ns: Idle state exit latency limit (or no override if 0).
  *
- * Set/unset the current CPU to use the deepest idle state (override governors
- * going forward if set).
+ * If @latency_limit_ns is nonzero, set the current CPU to use the deepest idle
+ * state with exit latency within @latency_limit_ns (override governors going
+ * forward), or do not override governors if it is zero.
  */
-void cpuidle_use_deepest_state(bool enable)
+void cpuidle_use_deepest_state(u64 latency_limit_ns)
 {
 	struct cpuidle_device *dev;
 
 	preempt_disable();
 	dev = cpuidle_get_device();
 	if (dev)
-		dev->use_deepest_state = enable;
+		dev->forced_idle_latency_limit_ns = latency_limit_ns;
 	preempt_enable();
 }
 
@@ -122,9 +123,10 @@ void cpuidle_use_deepest_state(bool enable)
  * @dev: cpuidle device for the given CPU.
  */
 int cpuidle_find_deepest_state(struct cpuidle_driver *drv,
-			       struct cpuidle_device *dev)
+			       struct cpuidle_device *dev,
+			       u64 latency_limit_ns)
 {
-	return find_deepest_state(drv, dev, UINT_MAX, 0, false);
+	return find_deepest_state(drv, dev, latency_limit_ns, 0, false);
 }
 
 #ifdef CONFIG_SUSPEND
@@ -180,7 +182,7 @@ int cpuidle_enter_s2idle(struct cpuidle_driver *drv, struct cpuidle_device *dev)
 	 * that interrupts won't be enabled when it exits and allows the tick to
 	 * be frozen safely.
 	 */
-	index = find_deepest_state(drv, dev, UINT_MAX, 0, true);
+	index = find_deepest_state(drv, dev, U64_MAX, 0, true);
 	if (index > 0)
 		enter_s2idle_proper(drv, dev, index);
 
@@ -209,7 +211,7 @@ int cpuidle_enter_state(struct cpuidle_device *dev, struct cpuidle_driver *drv,
 	 * CPU as a broadcast timer, this call may fail if it is not available.
 	 */
 	if (broadcast && tick_broadcast_enter()) {
-		index = find_deepest_state(drv, dev, target_state->exit_latency,
+		index = find_deepest_state(drv, dev, target_state->exit_latency_ns,
 					   CPUIDLE_FLAG_TIMER_STOP, false);
 		if (index < 0) {
 			default_idle_call();
@@ -247,7 +249,7 @@ int cpuidle_enter_state(struct cpuidle_device *dev, struct cpuidle_driver *drv,
 		local_irq_enable();
 
 	if (entered_state >= 0) {
-		s64 diff, delay = drv->states[entered_state].exit_latency;
+		s64 diff, delay = drv->states[entered_state].exit_latency_ns;
 		int i;
 
 		/*
@@ -255,18 +257,15 @@ int cpuidle_enter_state(struct cpuidle_device *dev, struct cpuidle_driver *drv,
 		 * This can be moved to within driver enter routine,
 		 * but that results in multiple copies of same code.
 		 */
-		diff = ktime_us_delta(time_end, time_start);
-		if (diff > INT_MAX)
-			diff = INT_MAX;
+		diff = ktime_sub(time_end, time_start);
 
-		dev->last_residency = (int)diff;
-		dev->states_usage[entered_state].time += dev->last_residency;
+		dev->last_residency_ns = diff;
+		dev->states_usage[entered_state].time_ns += diff;
 		dev->states_usage[entered_state].usage++;
 
-		if (diff < drv->states[entered_state].target_residency) {
+		if (diff < drv->states[entered_state].target_residency_ns) {
 			for (i = entered_state - 1; i >= 0; i--) {
-				if (drv->states[i].disabled ||
-				    dev->states_usage[i].disable)
+				if (dev->states_usage[i].disable)
 					continue;
 
 				/* Shallower states are enabled, so update. */
@@ -275,22 +274,21 @@ int cpuidle_enter_state(struct cpuidle_device *dev, struct cpuidle_driver *drv,
 			}
 		} else if (diff > delay) {
 			for (i = entered_state + 1; i < drv->state_count; i++) {
-				if (drv->states[i].disabled ||
-				    dev->states_usage[i].disable)
+				if (dev->states_usage[i].disable)
 					continue;
 
 				/*
 				 * Update if a deeper state would have been a
 				 * better match for the observed idle duration.
 				 */
-				if (diff - delay >= drv->states[i].target_residency)
+				if (diff - delay >= drv->states[i].target_residency_ns)
 					dev->states_usage[entered_state].below++;
 
 				break;
 			}
 		}
 	} else {
-		dev->last_residency = 0;
+		dev->last_residency_ns = 0;
 	}
 
 	return entered_state;
@@ -380,10 +378,10 @@ u64 cpuidle_poll_time(struct cpuidle_driver *drv,
 
 	limit_ns = TICK_NSEC;
 	for (i = 1; i < drv->state_count; i++) {
-		if (drv->states[i].disabled || dev->states_usage[i].disable)
+		if (dev->states_usage[i].disable)
 			continue;
 
-		limit_ns = (u64)drv->states[i].target_residency * NSEC_PER_USEC;
+		limit_ns = (u64)drv->states[i].target_residency_ns;
 	}
 
 	dev->poll_limit_ns = limit_ns;
@@ -554,7 +552,7 @@ static void __cpuidle_unregister_device(struct cpuidle_device *dev)
 static void __cpuidle_device_init(struct cpuidle_device *dev)
 {
 	memset(dev->states_usage, 0, sizeof(dev->states_usage));
-	dev->last_residency = 0;
+	dev->last_residency_ns = 0;
 	dev->next_hrtimer = 0;
 }
 
@@ -567,12 +565,16 @@ static void __cpuidle_device_init(struct cpuidle_device *dev)
  */
 static int __cpuidle_register_device(struct cpuidle_device *dev)
 {
-	int ret;
 	struct cpuidle_driver *drv = cpuidle_get_cpu_driver(dev);
+	int i, ret;
 
 	if (!try_module_get(drv->owner))
 		return -EINVAL;
 
+	for (i = 0; i < drv->state_count; i++)
+		if (drv->states[i].disabled)
+			dev->states_usage[i].disable |= CPUIDLE_STATE_DISABLED_BY_DRIVER;
+
 	per_cpu(cpuidle_devices, dev->cpu) = dev;
 	list_add(&dev->device_list, &cpuidle_detected_devices);
 
diff --git a/drivers/cpuidle/driver.c b/drivers/cpuidle/driver.c
index 80c1a830d991..c76423aaef4d 100644
--- a/drivers/cpuidle/driver.c
+++ b/drivers/cpuidle/driver.c
@@ -62,24 +62,23 @@ static inline void __cpuidle_unset_driver(struct cpuidle_driver *drv)
  * __cpuidle_set_driver - set per CPU driver variables for the given driver.
  * @drv: a valid pointer to a struct cpuidle_driver
  *
- * For each CPU in the driver's cpumask, unset the registered driver per CPU
- * to @drv.
- *
- * Returns 0 on success, -EBUSY if the CPUs have driver(s) already.
+ * Returns 0 on success, -EBUSY if any CPU in the cpumask have a driver
+ * different from drv already.
  */
 static inline int __cpuidle_set_driver(struct cpuidle_driver *drv)
 {
 	int cpu;
 
 	for_each_cpu(cpu, drv->cpumask) {
+		struct cpuidle_driver *old_drv;
 
-		if (__cpuidle_get_cpu_driver(cpu)) {
-			__cpuidle_unset_driver(drv);
+		old_drv = __cpuidle_get_cpu_driver(cpu);
+		if (old_drv && old_drv != drv)
 			return -EBUSY;
-		}
+	}
 
+	for_each_cpu(cpu, drv->cpumask)
 		per_cpu(cpuidle_drivers, cpu) = drv;
-	}
 
 	return 0;
 }
@@ -166,16 +165,27 @@ static void __cpuidle_driver_init(struct cpuidle_driver *drv)
 	if (!drv->cpumask)
 		drv->cpumask = (struct cpumask *)cpu_possible_mask;
 
-	/*
-	 * Look for the timer stop flag in the different states, so that we know
-	 * if the broadcast timer has to be set up.  The loop is in the reverse
-	 * order, because usually one of the deeper states have this flag set.
-	 */
-	for (i = drv->state_count - 1; i >= 0 ; i--) {
-		if (drv->states[i].flags & CPUIDLE_FLAG_TIMER_STOP) {
+	for (i = 0; i < drv->state_count; i++) {
+		struct cpuidle_state *s = &drv->states[i];
+
+		/*
+		 * Look for the timer stop flag in the different states and if
+		 * it is found, indicate that the broadcast timer has to be set
+		 * up.
+		 */
+		if (s->flags & CPUIDLE_FLAG_TIMER_STOP)
 			drv->bctimer = 1;
-			break;
-		}
+
+		/*
+		 * The core will use the target residency and exit latency
+		 * values in nanoseconds, but allow drivers to provide them in
+		 * microseconds too.
+		 */
+		if (s->target_residency > 0)
+			s->target_residency_ns = s->target_residency * NSEC_PER_USEC;
+
+		if (s->exit_latency > 0)
+			s->exit_latency_ns = s->exit_latency * NSEC_PER_USEC;
 	}
 }
 
@@ -379,3 +389,31 @@ void cpuidle_driver_unref(void)
 
 	spin_unlock(&cpuidle_driver_lock);
 }
+
+/**
+ * cpuidle_driver_state_disabled - Disable or enable an idle state
+ * @drv: cpuidle driver owning the state
+ * @idx: State index
+ * @disable: Whether or not to disable the state
+ */
+void cpuidle_driver_state_disabled(struct cpuidle_driver *drv, int idx,
+				 bool disable)
+{
+	unsigned int cpu;
+
+	mutex_lock(&cpuidle_lock);
+
+	for_each_cpu(cpu, drv->cpumask) {
+		struct cpuidle_device *dev = per_cpu(cpuidle_devices, cpu);
+
+		if (!dev)
+			continue;
+
+		if (disable)
+			dev->states_usage[idx].disable |= CPUIDLE_STATE_DISABLED_BY_DRIVER;
+		else
+			dev->states_usage[idx].disable &= ~CPUIDLE_STATE_DISABLED_BY_DRIVER;
+	}
+
+	mutex_unlock(&cpuidle_lock);
+}
diff --git a/drivers/cpuidle/governor.c b/drivers/cpuidle/governor.c
index e9801f26c732..e48271e117a3 100644
--- a/drivers/cpuidle/governor.c
+++ b/drivers/cpuidle/governor.c
@@ -107,11 +107,14 @@ int cpuidle_register_governor(struct cpuidle_governor *gov)
  * cpuidle_governor_latency_req - Compute a latency constraint for CPU
  * @cpu: Target CPU
  */
-int cpuidle_governor_latency_req(unsigned int cpu)
+s64 cpuidle_governor_latency_req(unsigned int cpu)
 {
 	int global_req = pm_qos_request(PM_QOS_CPU_DMA_LATENCY);
 	struct device *device = get_cpu_device(cpu);
 	int device_req = dev_pm_qos_raw_resume_latency(device);
 
-	return device_req < global_req ? device_req : global_req;
+	if (device_req > global_req)
+		device_req = global_req;
+
+	return (s64)device_req * NSEC_PER_USEC;
 }
diff --git a/drivers/cpuidle/governors/haltpoll.c b/drivers/cpuidle/governors/haltpoll.c
index 7a703d2e0064..cb2a96eafc02 100644
--- a/drivers/cpuidle/governors/haltpoll.c
+++ b/drivers/cpuidle/governors/haltpoll.c
@@ -49,7 +49,7 @@ static int haltpoll_select(struct cpuidle_driver *drv,
 			   struct cpuidle_device *dev,
 			   bool *stop_tick)
 {
-	int latency_req = cpuidle_governor_latency_req(dev->cpu);
+	s64 latency_req = cpuidle_governor_latency_req(dev->cpu);
 
 	if (!drv->state_count || latency_req == 0) {
 		*stop_tick = false;
@@ -75,10 +75,9 @@ static int haltpoll_select(struct cpuidle_driver *drv,
 	return 0;
 }
 
-static void adjust_poll_limit(struct cpuidle_device *dev, unsigned int block_us)
+static void adjust_poll_limit(struct cpuidle_device *dev, u64 block_ns)
 {
 	unsigned int val;
-	u64 block_ns = block_us*NSEC_PER_USEC;
 
 	/* Grow cpu_halt_poll_us if
 	 * cpu_halt_poll_us < block_ns < guest_halt_poll_us
@@ -115,7 +114,7 @@ static void haltpoll_reflect(struct cpuidle_device *dev, int index)
 	dev->last_state_idx = index;
 
 	if (index != 0)
-		adjust_poll_limit(dev, dev->last_residency);
+		adjust_poll_limit(dev, dev->last_residency_ns);
 }
 
 /**
diff --git a/drivers/cpuidle/governors/ladder.c b/drivers/cpuidle/governors/ladder.c
index 428eeb832fe7..8e9058c4ea63 100644
--- a/drivers/cpuidle/governors/ladder.c
+++ b/drivers/cpuidle/governors/ladder.c
@@ -27,8 +27,8 @@ struct ladder_device_state {
 	struct {
 		u32 promotion_count;
 		u32 demotion_count;
-		u32 promotion_time;
-		u32 demotion_time;
+		u64 promotion_time_ns;
+		u64 demotion_time_ns;
 	} threshold;
 	struct {
 		int promotion_count;
@@ -68,9 +68,10 @@ static int ladder_select_state(struct cpuidle_driver *drv,
 {
 	struct ladder_device *ldev = this_cpu_ptr(&ladder_devices);
 	struct ladder_device_state *last_state;
-	int last_residency, last_idx = dev->last_state_idx;
+	int last_idx = dev->last_state_idx;
 	int first_idx = drv->states[0].flags & CPUIDLE_FLAG_POLLING ? 1 : 0;
-	int latency_req = cpuidle_governor_latency_req(dev->cpu);
+	s64 latency_req = cpuidle_governor_latency_req(dev->cpu);
+	s64 last_residency;
 
 	/* Special case when user has set very strict latency requirement */
 	if (unlikely(latency_req == 0)) {
@@ -80,14 +81,13 @@ static int ladder_select_state(struct cpuidle_driver *drv,
 
 	last_state = &ldev->states[last_idx];
 
-	last_residency = dev->last_residency - drv->states[last_idx].exit_latency;
+	last_residency = dev->last_residency_ns - drv->states[last_idx].exit_latency_ns;
 
 	/* consider promotion */
 	if (last_idx < drv->state_count - 1 &&
-	    !drv->states[last_idx + 1].disabled &&
 	    !dev->states_usage[last_idx + 1].disable &&
-	    last_residency > last_state->threshold.promotion_time &&
-	    drv->states[last_idx + 1].exit_latency <= latency_req) {
+	    last_residency > last_state->threshold.promotion_time_ns &&
+	    drv->states[last_idx + 1].exit_latency_ns <= latency_req) {
 		last_state->stats.promotion_count++;
 		last_state->stats.demotion_count = 0;
 		if (last_state->stats.promotion_count >= last_state->threshold.promotion_count) {
@@ -98,13 +98,12 @@ static int ladder_select_state(struct cpuidle_driver *drv,
 
 	/* consider demotion */
 	if (last_idx > first_idx &&
-	    (drv->states[last_idx].disabled ||
-	    dev->states_usage[last_idx].disable ||
-	    drv->states[last_idx].exit_latency > latency_req)) {
+	    (dev->states_usage[last_idx].disable ||
+	    drv->states[last_idx].exit_latency_ns > latency_req)) {
 		int i;
 
 		for (i = last_idx - 1; i > first_idx; i--) {
-			if (drv->states[i].exit_latency <= latency_req)
+			if (drv->states[i].exit_latency_ns <= latency_req)
 				break;
 		}
 		ladder_do_selection(dev, ldev, last_idx, i);
@@ -112,7 +111,7 @@ static int ladder_select_state(struct cpuidle_driver *drv,
 	}
 
 	if (last_idx > first_idx &&
-	    last_residency < last_state->threshold.demotion_time) {
+	    last_residency < last_state->threshold.demotion_time_ns) {
 		last_state->stats.demotion_count++;
 		last_state->stats.promotion_count = 0;
 		if (last_state->stats.demotion_count >= last_state->threshold.demotion_count) {
@@ -152,9 +151,9 @@ static int ladder_enable_device(struct cpuidle_driver *drv,
 		lstate->threshold.demotion_count = DEMOTION_COUNT;
 
 		if (i < drv->state_count - 1)
-			lstate->threshold.promotion_time = state->exit_latency;
+			lstate->threshold.promotion_time_ns = state->exit_latency_ns;
 		if (i > first_idx)
-			lstate->threshold.demotion_time = state->exit_latency;
+			lstate->threshold.demotion_time_ns = state->exit_latency_ns;
 	}
 
 	return 0;
diff --git a/drivers/cpuidle/governors/menu.c b/drivers/cpuidle/governors/menu.c
index e5a5d0c8d66b..b0a7ad566081 100644
--- a/drivers/cpuidle/governors/menu.c
+++ b/drivers/cpuidle/governors/menu.c
@@ -19,22 +19,12 @@
 #include <linux/sched/stat.h>
 #include <linux/math64.h>
 
-/*
- * Please note when changing the tuning values:
- * If (MAX_INTERESTING-1) * RESOLUTION > UINT_MAX, the result of
- * a scaling operation multiplication may overflow on 32 bit platforms.
- * In that case, #define RESOLUTION as ULL to get 64 bit result:
- * #define RESOLUTION 1024ULL
- *
- * The default values do not overflow.
- */
 #define BUCKETS 12
 #define INTERVAL_SHIFT 3
 #define INTERVALS (1UL << INTERVAL_SHIFT)
 #define RESOLUTION 1024
 #define DECAY 8
-#define MAX_INTERESTING 50000
-
+#define MAX_INTERESTING (50000 * NSEC_PER_USEC)
 
 /*
  * Concepts and ideas behind the menu governor
@@ -120,14 +110,14 @@ struct menu_device {
 	int             needs_update;
 	int             tick_wakeup;
 
-	unsigned int	next_timer_us;
+	u64		next_timer_ns;
 	unsigned int	bucket;
 	unsigned int	correction_factor[BUCKETS];
 	unsigned int	intervals[INTERVALS];
 	int		interval_ptr;
 };
 
-static inline int which_bucket(unsigned int duration, unsigned long nr_iowaiters)
+static inline int which_bucket(u64 duration_ns, unsigned long nr_iowaiters)
 {
 	int bucket = 0;
 
@@ -140,15 +130,15 @@ static inline int which_bucket(unsigned int duration, unsigned long nr_iowaiters
 	if (nr_iowaiters)
 		bucket = BUCKETS/2;
 
-	if (duration < 10)
+	if (duration_ns < 10ULL * NSEC_PER_USEC)
 		return bucket;
-	if (duration < 100)
+	if (duration_ns < 100ULL * NSEC_PER_USEC)
 		return bucket + 1;
-	if (duration < 1000)
+	if (duration_ns < 1000ULL * NSEC_PER_USEC)
 		return bucket + 2;
-	if (duration < 10000)
+	if (duration_ns < 10000ULL * NSEC_PER_USEC)
 		return bucket + 3;
-	if (duration < 100000)
+	if (duration_ns < 100000ULL * NSEC_PER_USEC)
 		return bucket + 4;
 	return bucket + 5;
 }
@@ -276,13 +266,13 @@ static int menu_select(struct cpuidle_driver *drv, struct cpuidle_device *dev,
 		       bool *stop_tick)
 {
 	struct menu_device *data = this_cpu_ptr(&menu_devices);
-	int latency_req = cpuidle_governor_latency_req(dev->cpu);
-	int i;
-	int idx;
-	unsigned int interactivity_req;
+	s64 latency_req = cpuidle_governor_latency_req(dev->cpu);
 	unsigned int predicted_us;
+	u64 predicted_ns;
+	u64 interactivity_req;
 	unsigned long nr_iowaiters;
 	ktime_t delta_next;
+	int i, idx;
 
 	if (data->needs_update) {
 		menu_update(drv, dev);
@@ -290,15 +280,15 @@ static int menu_select(struct cpuidle_driver *drv, struct cpuidle_device *dev,
 	}
 
 	/* determine the expected residency time, round up */
-	data->next_timer_us = ktime_to_us(tick_nohz_get_sleep_length(&delta_next));
+	data->next_timer_ns = tick_nohz_get_sleep_length(&delta_next);
 
 	nr_iowaiters = nr_iowait_cpu(dev->cpu);
-	data->bucket = which_bucket(data->next_timer_us, nr_iowaiters);
+	data->bucket = which_bucket(data->next_timer_ns, nr_iowaiters);
 
 	if (unlikely(drv->state_count <= 1 || latency_req == 0) ||
-	    ((data->next_timer_us < drv->states[1].target_residency ||
-	      latency_req < drv->states[1].exit_latency) &&
-	     !drv->states[0].disabled && !dev->states_usage[0].disable)) {
+	    ((data->next_timer_ns < drv->states[1].target_residency_ns ||
+	      latency_req < drv->states[1].exit_latency_ns) &&
+	     !dev->states_usage[0].disable)) {
 		/*
 		 * In this case state[0] will be used no matter what, so return
 		 * it right away and keep the tick running if state[0] is a
@@ -308,18 +298,15 @@ static int menu_select(struct cpuidle_driver *drv, struct cpuidle_device *dev,
 		return 0;
 	}
 
-	/*
-	 * Force the result of multiplication to be 64 bits even if both
-	 * operands are 32 bits.
-	 * Make sure to round up for half microseconds.
-	 */
-	predicted_us = DIV_ROUND_CLOSEST_ULL((uint64_t)data->next_timer_us *
-					 data->correction_factor[data->bucket],
-					 RESOLUTION * DECAY);
-	/*
-	 * Use the lowest expected idle interval to pick the idle state.
-	 */
-	predicted_us = min(predicted_us, get_typical_interval(data, predicted_us));
+	/* Round up the result for half microseconds. */
+	predicted_us = div_u64(data->next_timer_ns *
+			       data->correction_factor[data->bucket] +
+			       (RESOLUTION * DECAY * NSEC_PER_USEC) / 2,
+			       RESOLUTION * DECAY * NSEC_PER_USEC);
+	/* Use the lowest expected idle interval to pick the idle state. */
+	predicted_ns = (u64)min(predicted_us,
+				get_typical_interval(data, predicted_us)) *
+				NSEC_PER_USEC;
 
 	if (tick_nohz_tick_stopped()) {
 		/*
@@ -330,14 +317,15 @@ static int menu_select(struct cpuidle_driver *drv, struct cpuidle_device *dev,
 		 * the known time till the closest timer event for the idle
 		 * state selection.
 		 */
-		if (predicted_us < TICK_USEC)
-			predicted_us = ktime_to_us(delta_next);
+		if (predicted_ns < TICK_NSEC)
+			predicted_ns = delta_next;
 	} else {
 		/*
 		 * Use the performance multiplier and the user-configurable
 		 * latency_req to determine the maximum exit latency.
 		 */
-		interactivity_req = predicted_us / performance_multiplier(nr_iowaiters);
+		interactivity_req = div64_u64(predicted_ns,
+					      performance_multiplier(nr_iowaiters));
 		if (latency_req > interactivity_req)
 			latency_req = interactivity_req;
 	}
@@ -349,27 +337,26 @@ static int menu_select(struct cpuidle_driver *drv, struct cpuidle_device *dev,
 	idx = -1;
 	for (i = 0; i < drv->state_count; i++) {
 		struct cpuidle_state *s = &drv->states[i];
-		struct cpuidle_state_usage *su = &dev->states_usage[i];
 
-		if (s->disabled || su->disable)
+		if (dev->states_usage[i].disable)
 			continue;
 
 		if (idx == -1)
 			idx = i; /* first enabled state */
 
-		if (s->target_residency > predicted_us) {
+		if (s->target_residency_ns > predicted_ns) {
 			/*
 			 * Use a physical idle state, not busy polling, unless
 			 * a timer is going to trigger soon enough.
 			 */
 			if ((drv->states[idx].flags & CPUIDLE_FLAG_POLLING) &&
-			    s->exit_latency <= latency_req &&
-			    s->target_residency <= data->next_timer_us) {
-				predicted_us = s->target_residency;
+			    s->exit_latency_ns <= latency_req &&
+			    s->target_residency_ns <= data->next_timer_ns) {
+				predicted_ns = s->target_residency_ns;
 				idx = i;
 				break;
 			}
-			if (predicted_us < TICK_USEC)
+			if (predicted_ns < TICK_NSEC)
 				break;
 
 			if (!tick_nohz_tick_stopped()) {
@@ -379,7 +366,7 @@ static int menu_select(struct cpuidle_driver *drv, struct cpuidle_device *dev,
 				 * tick in that case and let the governor run
 				 * again in the next iteration of the loop.
 				 */
-				predicted_us = drv->states[idx].target_residency;
+				predicted_ns = drv->states[idx].target_residency_ns;
 				break;
 			}
 
@@ -389,13 +376,13 @@ static int menu_select(struct cpuidle_driver *drv, struct cpuidle_device *dev,
 			 * closest timer event, select this one to avoid getting
 			 * stuck in the shallow one for too long.
 			 */
-			if (drv->states[idx].target_residency < TICK_USEC &&
-			    s->target_residency <= ktime_to_us(delta_next))
+			if (drv->states[idx].target_residency_ns < TICK_NSEC &&
+			    s->target_residency_ns <= delta_next)
 				idx = i;
 
 			return idx;
 		}
-		if (s->exit_latency > latency_req)
+		if (s->exit_latency_ns > latency_req)
 			break;
 
 		idx = i;
@@ -409,12 +396,10 @@ static int menu_select(struct cpuidle_driver *drv, struct cpuidle_device *dev,
 	 * expected idle duration is shorter than the tick period length.
 	 */
 	if (((drv->states[idx].flags & CPUIDLE_FLAG_POLLING) ||
-	     predicted_us < TICK_USEC) && !tick_nohz_tick_stopped()) {
-		unsigned int delta_next_us = ktime_to_us(delta_next);
-
+	     predicted_ns < TICK_NSEC) && !tick_nohz_tick_stopped()) {
 		*stop_tick = false;
 
-		if (idx > 0 && drv->states[idx].target_residency > delta_next_us) {
+		if (idx > 0 && drv->states[idx].target_residency_ns > delta_next) {
 			/*
 			 * The tick is not going to be stopped and the target
 			 * residency of the state to be returned is not within
@@ -422,12 +407,11 @@ static int menu_select(struct cpuidle_driver *drv, struct cpuidle_device *dev,
 			 * tick, so try to correct that.
 			 */
 			for (i = idx - 1; i >= 0; i--) {
-				if (drv->states[i].disabled ||
-				    dev->states_usage[i].disable)
+				if (dev->states_usage[i].disable)
 					continue;
 
 				idx = i;
-				if (drv->states[i].target_residency <= delta_next_us)
+				if (drv->states[i].target_residency_ns <= delta_next)
 					break;
 			}
 		}
@@ -463,7 +447,7 @@ static void menu_update(struct cpuidle_driver *drv, struct cpuidle_device *dev)
 	struct menu_device *data = this_cpu_ptr(&menu_devices);
 	int last_idx = dev->last_state_idx;
 	struct cpuidle_state *target = &drv->states[last_idx];
-	unsigned int measured_us;
+	u64 measured_ns;
 	unsigned int new_factor;
 
 	/*
@@ -481,7 +465,7 @@ static void menu_update(struct cpuidle_driver *drv, struct cpuidle_device *dev)
 	 * assume the state was never reached and the exit latency is 0.
 	 */
 
-	if (data->tick_wakeup && data->next_timer_us > TICK_USEC) {
+	if (data->tick_wakeup && data->next_timer_ns > TICK_NSEC) {
 		/*
 		 * The nohz code said that there wouldn't be any events within
 		 * the tick boundary (if the tick was stopped), but the idle
@@ -491,7 +475,7 @@ static void menu_update(struct cpuidle_driver *drv, struct cpuidle_device *dev)
 		 * have been idle long (but not forever) to help the idle
 		 * duration predictor do a better job next time.
 		 */
-		measured_us = 9 * MAX_INTERESTING / 10;
+		measured_ns = 9 * MAX_INTERESTING / 10;
 	} else if ((drv->states[last_idx].flags & CPUIDLE_FLAG_POLLING) &&
 		   dev->poll_time_limit) {
 		/*
@@ -501,28 +485,29 @@ static void menu_update(struct cpuidle_driver *drv, struct cpuidle_device *dev)
 		 * the CPU might have been woken up from idle by the next timer.
 		 * Assume that to be the case.
 		 */
-		measured_us = data->next_timer_us;
+		measured_ns = data->next_timer_ns;
 	} else {
 		/* measured value */
-		measured_us = dev->last_residency;
+		measured_ns = dev->last_residency_ns;
 
 		/* Deduct exit latency */
-		if (measured_us > 2 * target->exit_latency)
-			measured_us -= target->exit_latency;
+		if (measured_ns > 2 * target->exit_latency_ns)
+			measured_ns -= target->exit_latency_ns;
 		else
-			measured_us /= 2;
+			measured_ns /= 2;
 	}
 
 	/* Make sure our coefficients do not exceed unity */
-	if (measured_us > data->next_timer_us)
-		measured_us = data->next_timer_us;
+	if (measured_ns > data->next_timer_ns)
+		measured_ns = data->next_timer_ns;
 
 	/* Update our correction ratio */
 	new_factor = data->correction_factor[data->bucket];
 	new_factor -= new_factor / DECAY;
 
-	if (data->next_timer_us > 0 && measured_us < MAX_INTERESTING)
-		new_factor += RESOLUTION * measured_us / data->next_timer_us;
+	if (data->next_timer_ns > 0 && measured_ns < MAX_INTERESTING)
+		new_factor += div64_u64(RESOLUTION * measured_ns,
+					data->next_timer_ns);
 	else
 		/*
 		 * we were idle so long that we count it as a perfect
@@ -542,7 +527,7 @@ static void menu_update(struct cpuidle_driver *drv, struct cpuidle_device *dev)
 	data->correction_factor[data->bucket] = new_factor;
 
 	/* update the repeating-pattern data */
-	data->intervals[data->interval_ptr++] = measured_us;
+	data->intervals[data->interval_ptr++] = ktime_to_us(measured_ns);
 	if (data->interval_ptr >= INTERVALS)
 		data->interval_ptr = 0;
 }
diff --git a/drivers/cpuidle/governors/teo.c b/drivers/cpuidle/governors/teo.c
index b5a0e498f798..de7e706efd46 100644
--- a/drivers/cpuidle/governors/teo.c
+++ b/drivers/cpuidle/governors/teo.c
@@ -104,7 +104,7 @@ struct teo_cpu {
 	u64 sleep_length_ns;
 	struct teo_idle_state states[CPUIDLE_STATE_MAX];
 	int interval_idx;
-	unsigned int intervals[INTERVALS];
+	u64 intervals[INTERVALS];
 };
 
 static DEFINE_PER_CPU(struct teo_cpu, teo_cpus);
@@ -117,9 +117,8 @@ static DEFINE_PER_CPU(struct teo_cpu, teo_cpus);
 static void teo_update(struct cpuidle_driver *drv, struct cpuidle_device *dev)
 {
 	struct teo_cpu *cpu_data = per_cpu_ptr(&teo_cpus, dev->cpu);
-	unsigned int sleep_length_us = ktime_to_us(cpu_data->sleep_length_ns);
 	int i, idx_hit = -1, idx_timer = -1;
-	unsigned int measured_us;
+	u64 measured_ns;
 
 	if (cpu_data->time_span_ns >= cpu_data->sleep_length_ns) {
 		/*
@@ -127,23 +126,28 @@ static void teo_update(struct cpuidle_driver *drv, struct cpuidle_device *dev)
 		 * enough to the closest timer event expected at the idle state
 		 * selection time to be discarded.
 		 */
-		measured_us = UINT_MAX;
+		measured_ns = U64_MAX;
 	} else {
-		unsigned int lat;
+		u64 lat_ns = drv->states[dev->last_state_idx].exit_latency_ns;
 
-		lat = drv->states[dev->last_state_idx].exit_latency;
-
-		measured_us = ktime_to_us(cpu_data->time_span_ns);
+		/*
+		 * The computations below are to determine whether or not the
+		 * (saved) time till the next timer event and the measured idle
+		 * duration fall into the same "bin", so use last_residency_ns
+		 * for that instead of time_span_ns which includes the cpuidle
+		 * overhead.
+		 */
+		measured_ns = dev->last_residency_ns;
 		/*
 		 * The delay between the wakeup and the first instruction
 		 * executed by the CPU is not likely to be worst-case every
 		 * time, so take 1/2 of the exit latency as a very rough
 		 * approximation of the average of it.
 		 */
-		if (measured_us >= lat)
-			measured_us -= lat / 2;
+		if (measured_ns >= lat_ns)
+			measured_ns -= lat_ns / 2;
 		else
-			measured_us /= 2;
+			measured_ns /= 2;
 	}
 
 	/*
@@ -155,9 +159,9 @@ static void teo_update(struct cpuidle_driver *drv, struct cpuidle_device *dev)
 
 		cpu_data->states[i].early_hits -= early_hits >> DECAY_SHIFT;
 
-		if (drv->states[i].target_residency <= sleep_length_us) {
+		if (drv->states[i].target_residency_ns <= cpu_data->sleep_length_ns) {
 			idx_timer = i;
-			if (drv->states[i].target_residency <= measured_us)
+			if (drv->states[i].target_residency_ns <= measured_ns)
 				idx_hit = i;
 		}
 	}
@@ -193,30 +197,35 @@ static void teo_update(struct cpuidle_driver *drv, struct cpuidle_device *dev)
 	 * Save idle duration values corresponding to non-timer wakeups for
 	 * pattern detection.
 	 */
-	cpu_data->intervals[cpu_data->interval_idx++] = measured_us;
+	cpu_data->intervals[cpu_data->interval_idx++] = measured_ns;
 	if (cpu_data->interval_idx > INTERVALS)
 		cpu_data->interval_idx = 0;
 }
 
+static bool teo_time_ok(u64 interval_ns)
+{
+	return !tick_nohz_tick_stopped() || interval_ns >= TICK_NSEC;
+}
+
 /**
  * teo_find_shallower_state - Find shallower idle state matching given duration.
  * @drv: cpuidle driver containing state data.
  * @dev: Target CPU.
  * @state_idx: Index of the capping idle state.
- * @duration_us: Idle duration value to match.
+ * @duration_ns: Idle duration value to match.
  */
 static int teo_find_shallower_state(struct cpuidle_driver *drv,
 				    struct cpuidle_device *dev, int state_idx,
-				    unsigned int duration_us)
+				    u64 duration_ns)
 {
 	int i;
 
 	for (i = state_idx - 1; i >= 0; i--) {
-		if (drv->states[i].disabled || dev->states_usage[i].disable)
+		if (dev->states_usage[i].disable)
 			continue;
 
 		state_idx = i;
-		if (drv->states[i].target_residency <= duration_us)
+		if (drv->states[i].target_residency_ns <= duration_ns)
 			break;
 	}
 	return state_idx;
@@ -232,9 +241,10 @@ static int teo_select(struct cpuidle_driver *drv, struct cpuidle_device *dev,
 		      bool *stop_tick)
 {
 	struct teo_cpu *cpu_data = per_cpu_ptr(&teo_cpus, dev->cpu);
-	int latency_req = cpuidle_governor_latency_req(dev->cpu);
-	unsigned int duration_us, count;
-	int max_early_idx, constraint_idx, idx, i;
+	s64 latency_req = cpuidle_governor_latency_req(dev->cpu);
+	u64 duration_ns;
+	unsigned int hits, misses, early_hits;
+	int max_early_idx, prev_max_early_idx, constraint_idx, idx, i;
 	ktime_t delta_tick;
 
 	if (dev->last_state_idx >= 0) {
@@ -244,50 +254,92 @@ static int teo_select(struct cpuidle_driver *drv, struct cpuidle_device *dev,
 
 	cpu_data->time_span_ns = local_clock();
 
-	cpu_data->sleep_length_ns = tick_nohz_get_sleep_length(&delta_tick);
-	duration_us = ktime_to_us(cpu_data->sleep_length_ns);
+	duration_ns = tick_nohz_get_sleep_length(&delta_tick);
+	cpu_data->sleep_length_ns = duration_ns;
 
-	count = 0;
+	hits = 0;
+	misses = 0;
+	early_hits = 0;
 	max_early_idx = -1;
+	prev_max_early_idx = -1;
 	constraint_idx = drv->state_count;
 	idx = -1;
 
 	for (i = 0; i < drv->state_count; i++) {
 		struct cpuidle_state *s = &drv->states[i];
-		struct cpuidle_state_usage *su = &dev->states_usage[i];
 
-		if (s->disabled || su->disable) {
+		if (dev->states_usage[i].disable) {
+			/*
+			 * Ignore disabled states with target residencies beyond
+			 * the anticipated idle duration.
+			 */
+			if (s->target_residency_ns > duration_ns)
+				continue;
+
+			/*
+			 * This state is disabled, so the range of idle duration
+			 * values corresponding to it is covered by the current
+			 * candidate state, but still the "hits" and "misses"
+			 * metrics of the disabled state need to be used to
+			 * decide whether or not the state covering the range in
+			 * question is good enough.
+			 */
+			hits = cpu_data->states[i].hits;
+			misses = cpu_data->states[i].misses;
+
+			if (early_hits >= cpu_data->states[i].early_hits ||
+			    idx < 0)
+				continue;
+
 			/*
-			 * If the "early hits" metric of a disabled state is
-			 * greater than the current maximum, it should be taken
-			 * into account, because it would be a mistake to select
-			 * a deeper state with lower "early hits" metric.  The
-			 * index cannot be changed to point to it, however, so
-			 * just increase the max count alone and let the index
-			 * still point to a shallower idle state.
+			 * If the current candidate state has been the one with
+			 * the maximum "early hits" metric so far, the "early
+			 * hits" metric of the disabled state replaces the
+			 * current "early hits" count to avoid selecting a
+			 * deeper state with lower "early hits" metric.
 			 */
-			if (max_early_idx >= 0 &&
-			    count < cpu_data->states[i].early_hits)
-				count = cpu_data->states[i].early_hits;
+			if (max_early_idx == idx) {
+				early_hits = cpu_data->states[i].early_hits;
+				continue;
+			}
+
+			/*
+			 * The current candidate state is closer to the disabled
+			 * one than the current maximum "early hits" state, so
+			 * replace the latter with it, but in case the maximum
+			 * "early hits" state index has not been set so far,
+			 * check if the current candidate state is not too
+			 * shallow for that role.
+			 */
+			if (teo_time_ok(drv->states[idx].target_residency_ns)) {
+				prev_max_early_idx = max_early_idx;
+				early_hits = cpu_data->states[i].early_hits;
+				max_early_idx = idx;
+			}
 
 			continue;
 		}
 
-		if (idx < 0)
+		if (idx < 0) {
 			idx = i; /* first enabled state */
+			hits = cpu_data->states[i].hits;
+			misses = cpu_data->states[i].misses;
+		}
 
-		if (s->target_residency > duration_us)
+		if (s->target_residency_ns > duration_ns)
 			break;
 
-		if (s->exit_latency > latency_req && constraint_idx > i)
+		if (s->exit_latency_ns > latency_req && constraint_idx > i)
 			constraint_idx = i;
 
 		idx = i;
+		hits = cpu_data->states[i].hits;
+		misses = cpu_data->states[i].misses;
 
-		if (count < cpu_data->states[i].early_hits &&
-		    !(tick_nohz_tick_stopped() &&
-		      drv->states[i].target_residency < TICK_USEC)) {
-			count = cpu_data->states[i].early_hits;
+		if (early_hits < cpu_data->states[i].early_hits &&
+		    teo_time_ok(drv->states[i].target_residency_ns)) {
+			prev_max_early_idx = max_early_idx;
+			early_hits = cpu_data->states[i].early_hits;
 			max_early_idx = i;
 		}
 	}
@@ -300,10 +352,19 @@ static int teo_select(struct cpuidle_driver *drv, struct cpuidle_device *dev,
 	 * "early hits" metric, but if that cannot be determined, just use the
 	 * state selected so far.
 	 */
-	if (cpu_data->states[idx].hits <= cpu_data->states[idx].misses &&
-	    max_early_idx >= 0) {
-		idx = max_early_idx;
-		duration_us = drv->states[idx].target_residency;
+	if (hits <= misses) {
+		/*
+		 * The current candidate state is not suitable, so take the one
+		 * whose "early hits" metric is the maximum for the range of
+		 * shallower states.
+		 */
+		if (idx == max_early_idx)
+			max_early_idx = prev_max_early_idx;
+
+		if (max_early_idx >= 0) {
+			idx = max_early_idx;
+			duration_ns = drv->states[idx].target_residency_ns;
+		}
 	}
 
 	/*
@@ -316,18 +377,17 @@ static int teo_select(struct cpuidle_driver *drv, struct cpuidle_device *dev,
 	if (idx < 0) {
 		idx = 0; /* No states enabled. Must use 0. */
 	} else if (idx > 0) {
+		unsigned int count = 0;
 		u64 sum = 0;
 
-		count = 0;
-
 		/*
 		 * Count and sum the most recent idle duration values less than
 		 * the current expected idle duration value.
 		 */
 		for (i = 0; i < INTERVALS; i++) {
-			unsigned int val = cpu_data->intervals[i];
+			u64 val = cpu_data->intervals[i];
 
-			if (val >= duration_us)
+			if (val >= duration_ns)
 				continue;
 
 			count++;
@@ -339,17 +399,17 @@ static int teo_select(struct cpuidle_driver *drv, struct cpuidle_device *dev,
 		 * values are in the interesting range.
 		 */
 		if (count > INTERVALS / 2) {
-			unsigned int avg_us = div64_u64(sum, count);
+			u64 avg_ns = div64_u64(sum, count);
 
 			/*
 			 * Avoid spending too much time in an idle state that
 			 * would be too shallow.
 			 */
-			if (!(tick_nohz_tick_stopped() && avg_us < TICK_USEC)) {
-				duration_us = avg_us;
-				if (drv->states[idx].target_residency > avg_us)
+			if (teo_time_ok(avg_ns)) {
+				duration_ns = avg_ns;
+				if (drv->states[idx].target_residency_ns > avg_ns)
 					idx = teo_find_shallower_state(drv, dev,
-								       idx, avg_us);
+								       idx, avg_ns);
 			}
 		}
 	}
@@ -359,9 +419,7 @@ static int teo_select(struct cpuidle_driver *drv, struct cpuidle_device *dev,
 	 * expected idle duration is shorter than the tick period length.
 	 */
 	if (((drv->states[idx].flags & CPUIDLE_FLAG_POLLING) ||
-	    duration_us < TICK_USEC) && !tick_nohz_tick_stopped()) {
-		unsigned int delta_tick_us = ktime_to_us(delta_tick);
-
+	    duration_ns < TICK_NSEC) && !tick_nohz_tick_stopped()) {
 		*stop_tick = false;
 
 		/*
@@ -370,8 +428,8 @@ static int teo_select(struct cpuidle_driver *drv, struct cpuidle_device *dev,
 		 * till the closest timer including the tick, try to correct
 		 * that.
 		 */
-		if (idx > 0 && drv->states[idx].target_residency > delta_tick_us)
-			idx = teo_find_shallower_state(drv, dev, idx, delta_tick_us);
+		if (idx > 0 && drv->states[idx].target_residency_ns > delta_tick)
+			idx = teo_find_shallower_state(drv, dev, idx, delta_tick);
 	}
 
 	return idx;
@@ -415,7 +473,7 @@ static int teo_enable_device(struct cpuidle_driver *drv,
 	memset(cpu_data, 0, sizeof(*cpu_data));
 
 	for (i = 0; i < INTERVALS; i++)
-		cpu_data->intervals[i] = UINT_MAX;
+		cpu_data->intervals[i] = U64_MAX;
 
 	return 0;
 }
diff --git a/drivers/cpuidle/poll_state.c b/drivers/cpuidle/poll_state.c
index c8fa5f41dfc4..9f1ace9c53da 100644
--- a/drivers/cpuidle/poll_state.c
+++ b/drivers/cpuidle/poll_state.c
@@ -49,6 +49,8 @@ void cpuidle_poll_state_init(struct cpuidle_driver *drv)
 	snprintf(state->desc, CPUIDLE_DESC_LEN, "CPUIDLE CORE POLL IDLE");
 	state->exit_latency = 0;
 	state->target_residency = 0;
+	state->exit_latency_ns = 0;
+	state->target_residency_ns = 0;
 	state->power_usage = -1;
 	state->enter = poll_idle;
 	state->disabled = false;
diff --git a/drivers/cpuidle/sysfs.c b/drivers/cpuidle/sysfs.c
index 2bb2683b493c..38ef770be90d 100644
--- a/drivers/cpuidle/sysfs.c
+++ b/drivers/cpuidle/sysfs.c
@@ -255,25 +255,6 @@ static ssize_t show_state_##_name(struct cpuidle_state *state, \
 	return sprintf(buf, "%u\n", state->_name);\
 }
 
-#define define_store_state_ull_function(_name) \
-static ssize_t store_state_##_name(struct cpuidle_state *state, \
-				   struct cpuidle_state_usage *state_usage, \
-				   const char *buf, size_t size)	\
-{ \
-	unsigned long long value; \
-	int err; \
-	if (!capable(CAP_SYS_ADMIN)) \
-		return -EPERM; \
-	err = kstrtoull(buf, 0, &value); \
-	if (err) \
-		return err; \
-	if (value) \
-		state_usage->_name = 1; \
-	else \
-		state_usage->_name = 0; \
-	return size; \
-}
-
 #define define_show_state_ull_function(_name) \
 static ssize_t show_state_##_name(struct cpuidle_state *state, \
 				  struct cpuidle_state_usage *state_usage, \
@@ -292,18 +273,60 @@ static ssize_t show_state_##_name(struct cpuidle_state *state, \
 	return sprintf(buf, "%s\n", state->_name);\
 }
 
-define_show_state_function(exit_latency)
-define_show_state_function(target_residency)
+#define define_show_state_time_function(_name) \
+static ssize_t show_state_##_name(struct cpuidle_state *state, \
+				  struct cpuidle_state_usage *state_usage, \
+				  char *buf) \
+{ \
+	return sprintf(buf, "%llu\n", ktime_to_us(state->_name##_ns)); \
+}
+
+define_show_state_time_function(exit_latency)
+define_show_state_time_function(target_residency)
 define_show_state_function(power_usage)
 define_show_state_ull_function(usage)
-define_show_state_ull_function(time)
 define_show_state_str_function(name)
 define_show_state_str_function(desc)
-define_show_state_ull_function(disable)
-define_store_state_ull_function(disable)
 define_show_state_ull_function(above)
 define_show_state_ull_function(below)
 
+static ssize_t show_state_time(struct cpuidle_state *state,
+			       struct cpuidle_state_usage *state_usage,
+			       char *buf)
+{
+	return sprintf(buf, "%llu\n", ktime_to_us(state_usage->time_ns));
+}
+
+static ssize_t show_state_disable(struct cpuidle_state *state,
+				  struct cpuidle_state_usage *state_usage,
+				  char *buf)
+{
+	return sprintf(buf, "%llu\n",
+		       state_usage->disable & CPUIDLE_STATE_DISABLED_BY_USER);
+}
+
+static ssize_t store_state_disable(struct cpuidle_state *state,
+				   struct cpuidle_state_usage *state_usage,
+				   const char *buf, size_t size)
+{
+	unsigned int value;
+	int err;
+
+	if (!capable(CAP_SYS_ADMIN))
+		return -EPERM;
+
+	err = kstrtouint(buf, 0, &value);
+	if (err)
+		return err;
+
+	if (value)
+		state_usage->disable |= CPUIDLE_STATE_DISABLED_BY_USER;
+	else
+		state_usage->disable &= ~CPUIDLE_STATE_DISABLED_BY_USER;
+
+	return size;
+}
+
 define_one_state_ro(name, show_state_name);
 define_one_state_ro(desc, show_state_desc);
 define_one_state_ro(latency, show_state_exit_latency);
diff --git a/drivers/dax/Kconfig b/drivers/dax/Kconfig
index f33c73e4af41..3b6c06f07326 100644
--- a/drivers/dax/Kconfig
+++ b/drivers/dax/Kconfig
@@ -32,19 +32,36 @@ config DEV_DAX_PMEM
 
 	  Say M if unsure
 
+config DEV_DAX_HMEM
+	tristate "HMEM DAX: direct access to 'specific purpose' memory"
+	depends on EFI_SOFT_RESERVE
+	default DEV_DAX
+	help
+	  EFI 2.8 platforms, and others, may advertise 'specific purpose'
+	  memory. For example, a high bandwidth memory pool. The
+	  indication from platform firmware is meant to reserve the
+	  memory from typical usage by default. This driver creates
+	  device-dax instances for these memory ranges, and that also
+	  enables the possibility to assign them to the DEV_DAX_KMEM
+	  driver to override the reservation and add them to kernel
+	  "System RAM" pool.
+
+	  Say M if unsure.
+
 config DEV_DAX_KMEM
 	tristate "KMEM DAX: volatile-use of persistent memory"
 	default DEV_DAX
 	depends on DEV_DAX
 	depends on MEMORY_HOTPLUG # for add_memory() and friends
 	help
-	  Support access to persistent memory as if it were RAM.  This
-	  allows easier use of persistent memory by unmodified
-	  applications.
+	  Support access to persistent, or other performance
+	  differentiated memory as if it were System RAM. This allows
+	  easier use of persistent memory by unmodified applications, or
+	  adds core kernel memory services to heterogeneous memory types
+	  (HMEM) marked "reserved" by platform firmware.
 
 	  To use this feature, a DAX device must be unbound from the
-	  device_dax driver (PMEM DAX) and bound to this kmem driver
-	  on each boot.
+	  device_dax driver and bound to this kmem driver on each boot.
 
 	  Say N if unsure.
 
diff --git a/drivers/dax/Makefile b/drivers/dax/Makefile
index 81f7d54dadfb..80065b38b3c4 100644
--- a/drivers/dax/Makefile
+++ b/drivers/dax/Makefile
@@ -2,9 +2,11 @@
 obj-$(CONFIG_DAX) += dax.o
 obj-$(CONFIG_DEV_DAX) += device_dax.o
 obj-$(CONFIG_DEV_DAX_KMEM) += kmem.o
+obj-$(CONFIG_DEV_DAX_HMEM) += dax_hmem.o
 
 dax-y := super.o
 dax-y += bus.o
 device_dax-y := device.o
+dax_hmem-y := hmem.o
 
 obj-y += pmem/
diff --git a/drivers/dax/bus.c b/drivers/dax/bus.c
index 8fafbeab510a..eccdda1f7b71 100644
--- a/drivers/dax/bus.c
+++ b/drivers/dax/bus.c
@@ -227,7 +227,7 @@ static void dax_region_unregister(void *region)
 
 struct dax_region *alloc_dax_region(struct device *parent, int region_id,
 		struct resource *res, int target_node, unsigned int align,
-		unsigned long pfn_flags)
+		unsigned long long pfn_flags)
 {
 	struct dax_region *dax_region;
 
diff --git a/drivers/dax/bus.h b/drivers/dax/bus.h
index 8619e3299943..9e4eba67e8b9 100644
--- a/drivers/dax/bus.h
+++ b/drivers/dax/bus.h
@@ -11,7 +11,7 @@ struct dax_region;
 void dax_region_put(struct dax_region *dax_region);
 struct dax_region *alloc_dax_region(struct device *parent, int region_id,
 		struct resource *res, int target_node, unsigned int align,
-		unsigned long flags);
+		unsigned long long flags);
 
 enum dev_dax_subsys {
 	DEV_DAX_BUS,
diff --git a/drivers/dax/dax-private.h b/drivers/dax/dax-private.h
index 6ccca3b890d6..3107ce80e809 100644
--- a/drivers/dax/dax-private.h
+++ b/drivers/dax/dax-private.h
@@ -32,7 +32,7 @@ struct dax_region {
 	struct device *dev;
 	unsigned int align;
 	struct resource res;
-	unsigned long pfn_flags;
+	unsigned long long pfn_flags;
 };
 
 /**
diff --git a/drivers/dax/hmem.c b/drivers/dax/hmem.c
new file mode 100644
index 000000000000..fe7214daf62e
--- /dev/null
+++ b/drivers/dax/hmem.c
@@ -0,0 +1,56 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/platform_device.h>
+#include <linux/memregion.h>
+#include <linux/module.h>
+#include <linux/pfn_t.h>
+#include "bus.h"
+
+static int dax_hmem_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct dev_pagemap pgmap = { };
+	struct dax_region *dax_region;
+	struct memregion_info *mri;
+	struct dev_dax *dev_dax;
+	struct resource *res;
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	if (!res)
+		return -ENOMEM;
+
+	mri = dev->platform_data;
+	memcpy(&pgmap.res, res, sizeof(*res));
+
+	dax_region = alloc_dax_region(dev, pdev->id, res, mri->target_node,
+			PMD_SIZE, PFN_DEV|PFN_MAP);
+	if (!dax_region)
+		return -ENOMEM;
+
+	dev_dax = devm_create_dev_dax(dax_region, 0, &pgmap);
+	if (IS_ERR(dev_dax))
+		return PTR_ERR(dev_dax);
+
+	/* child dev_dax instances now own the lifetime of the dax_region */
+	dax_region_put(dax_region);
+	return 0;
+}
+
+static int dax_hmem_remove(struct platform_device *pdev)
+{
+	/* devm handles teardown */
+	return 0;
+}
+
+static struct platform_driver dax_hmem_driver = {
+	.probe = dax_hmem_probe,
+	.remove = dax_hmem_remove,
+	.driver = {
+		.name = "hmem",
+	},
+};
+
+module_platform_driver(dax_hmem_driver);
+
+MODULE_ALIAS("platform:hmem*");
+MODULE_LICENSE("GPL v2");
+MODULE_AUTHOR("Intel Corporation");
diff --git a/drivers/devfreq/devfreq.c b/drivers/devfreq/devfreq.c
index 446490c9d635..f840e61e5a27 100644
--- a/drivers/devfreq/devfreq.c
+++ b/drivers/devfreq/devfreq.c
@@ -160,6 +160,7 @@ int devfreq_update_status(struct devfreq *devfreq, unsigned long freq)
 	int lev, prev_lev, ret = 0;
 	unsigned long cur_time;
 
+	lockdep_assert_held(&devfreq->lock);
 	cur_time = jiffies;
 
 	/* Immediately exit if previous_freq is not initialized yet. */
@@ -409,6 +410,9 @@ static void devfreq_monitor(struct work_struct *work)
  */
 void devfreq_monitor_start(struct devfreq *devfreq)
 {
+	if (devfreq->governor->interrupt_driven)
+		return;
+
 	INIT_DEFERRABLE_WORK(&devfreq->work, devfreq_monitor);
 	if (devfreq->profile->polling_ms)
 		queue_delayed_work(devfreq_wq, &devfreq->work,
@@ -426,6 +430,9 @@ EXPORT_SYMBOL(devfreq_monitor_start);
  */
 void devfreq_monitor_stop(struct devfreq *devfreq)
 {
+	if (devfreq->governor->interrupt_driven)
+		return;
+
 	cancel_delayed_work_sync(&devfreq->work);
 }
 EXPORT_SYMBOL(devfreq_monitor_stop);
@@ -453,6 +460,10 @@ void devfreq_monitor_suspend(struct devfreq *devfreq)
 	devfreq_update_status(devfreq, devfreq->previous_freq);
 	devfreq->stop_polling = true;
 	mutex_unlock(&devfreq->lock);
+
+	if (devfreq->governor->interrupt_driven)
+		return;
+
 	cancel_delayed_work_sync(&devfreq->work);
 }
 EXPORT_SYMBOL(devfreq_monitor_suspend);
@@ -473,11 +484,15 @@ void devfreq_monitor_resume(struct devfreq *devfreq)
 	if (!devfreq->stop_polling)
 		goto out;
 
+	if (devfreq->governor->interrupt_driven)
+		goto out_update;
+
 	if (!delayed_work_pending(&devfreq->work) &&
 			devfreq->profile->polling_ms)
 		queue_delayed_work(devfreq_wq, &devfreq->work,
 			msecs_to_jiffies(devfreq->profile->polling_ms));
 
+out_update:
 	devfreq->last_stat_updated = jiffies;
 	devfreq->stop_polling = false;
 
@@ -509,6 +524,9 @@ void devfreq_interval_update(struct devfreq *devfreq, unsigned int *delay)
 	if (devfreq->stop_polling)
 		goto out;
 
+	if (devfreq->governor->interrupt_driven)
+		goto out;
+
 	/* if new delay is zero, stop polling */
 	if (!new_delay) {
 		mutex_unlock(&devfreq->lock);
@@ -625,7 +643,7 @@ struct devfreq *devfreq_add_device(struct device *dev,
 	devfreq = find_device_devfreq(dev);
 	mutex_unlock(&devfreq_list_lock);
 	if (!IS_ERR(devfreq)) {
-		dev_err(dev, "%s: Unable to create devfreq for the device.\n",
+		dev_err(dev, "%s: devfreq device already exists!\n",
 			__func__);
 		err = -EINVAL;
 		goto err_out;
@@ -1195,7 +1213,7 @@ static ssize_t available_governors_show(struct device *d,
 	 * The devfreq with immutable governor (e.g., passive) shows
 	 * only own governor.
 	 */
-	if (df->governor->immutable) {
+	if (df->governor && df->governor->immutable) {
 		count = scnprintf(&buf[count], DEVFREQ_NAME_LEN,
 				  "%s ", df->governor_name);
 	/*
@@ -1397,12 +1415,17 @@ static ssize_t trans_stat_show(struct device *dev,
 	int i, j;
 	unsigned int max_state = devfreq->profile->max_state;
 
-	if (!devfreq->stop_polling &&
-			devfreq_update_status(devfreq, devfreq->previous_freq))
-		return 0;
 	if (max_state == 0)
 		return sprintf(buf, "Not Supported.\n");
 
+	mutex_lock(&devfreq->lock);
+	if (!devfreq->stop_polling &&
+			devfreq_update_status(devfreq, devfreq->previous_freq)) {
+		mutex_unlock(&devfreq->lock);
+		return 0;
+	}
+	mutex_unlock(&devfreq->lock);
+
 	len = sprintf(buf, "     From  :   To\n");
 	len += sprintf(buf + len, "           :");
 	for (i = 0; i < max_state; i++)
diff --git a/drivers/devfreq/event/exynos-ppmu.c b/drivers/devfreq/event/exynos-ppmu.c
index 87b42055e6bc..85c7a77bf3f0 100644
--- a/drivers/devfreq/event/exynos-ppmu.c
+++ b/drivers/devfreq/event/exynos-ppmu.c
@@ -673,7 +673,6 @@ static int exynos_ppmu_probe(struct platform_device *pdev)
 	for (i = 0; i < info->num_events; i++) {
 		edev[i] = devm_devfreq_event_add_edev(&pdev->dev, &desc[i]);
 		if (IS_ERR(edev[i])) {
-			ret = PTR_ERR(edev[i]);
 			dev_err(&pdev->dev,
 				"failed to add devfreq-event device\n");
 			return PTR_ERR(edev[i]);
diff --git a/drivers/devfreq/governor.h b/drivers/devfreq/governor.h
index bbe5ff9fcecf..dc7533ccc3db 100644
--- a/drivers/devfreq/governor.h
+++ b/drivers/devfreq/governor.h
@@ -31,6 +31,8 @@
  * @name:		Governor's name
  * @immutable:		Immutable flag for governor. If the value is 1,
  *			this govenror is never changeable to other governor.
+ * @interrupt_driven:	Devfreq core won't schedule polling work for this
+ *			governor if value is set to 1.
  * @get_target_freq:	Returns desired operating frequency for the device.
  *			Basically, get_target_freq will run
  *			devfreq_dev_profile.get_dev_status() to get the
@@ -49,6 +51,7 @@ struct devfreq_governor {
 
 	const char name[DEVFREQ_NAME_LEN];
 	const unsigned int immutable;
+	const unsigned int interrupt_driven;
 	int (*get_target_freq)(struct devfreq *this, unsigned long *freq);
 	int (*event_handler)(struct devfreq *devfreq,
 				unsigned int event, void *data);
diff --git a/drivers/devfreq/tegra30-devfreq.c b/drivers/devfreq/tegra30-devfreq.c
index a6ba75f4106d..0b65f89d74d5 100644
--- a/drivers/devfreq/tegra30-devfreq.c
+++ b/drivers/devfreq/tegra30-devfreq.c
@@ -11,11 +11,13 @@
 #include <linux/devfreq.h>
 #include <linux/interrupt.h>
 #include <linux/io.h>
+#include <linux/irq.h>
 #include <linux/module.h>
-#include <linux/mod_devicetable.h>
+#include <linux/of_device.h>
 #include <linux/platform_device.h>
 #include <linux/pm_opp.h>
 #include <linux/reset.h>
+#include <linux/workqueue.h>
 
 #include "governor.h"
 
@@ -33,6 +35,8 @@
 #define ACTMON_DEV_CTRL_CONSECUTIVE_ABOVE_WMARK_EN		BIT(30)
 #define ACTMON_DEV_CTRL_ENB					BIT(31)
 
+#define ACTMON_DEV_CTRL_STOP					0x00000000
+
 #define ACTMON_DEV_UPPER_WMARK					0x4
 #define ACTMON_DEV_LOWER_WMARK					0x8
 #define ACTMON_DEV_INIT_AVG					0xc
@@ -68,6 +72,8 @@
 
 #define KHZ							1000
 
+#define KHZ_MAX						(ULONG_MAX / KHZ)
+
 /* Assume that the bus is saturated if the utilization is 25% */
 #define BUS_SATURATION_RATIO					25
 
@@ -90,9 +96,10 @@ struct tegra_devfreq_device_config {
 	unsigned int	boost_down_threshold;
 
 	/*
-	 * Threshold of activity (cycles) below which the CPU frequency isn't
-	 * to be taken into account. This is to avoid increasing the EMC
-	 * frequency when the CPU is very busy but not accessing the bus often.
+	 * Threshold of activity (cycles translated to kHz) below which the
+	 * CPU frequency isn't to be taken into account. This is to avoid
+	 * increasing the EMC frequency when the CPU is very busy but not
+	 * accessing the bus often.
 	 */
 	u32		avg_dependency_threshold;
 };
@@ -102,7 +109,7 @@ enum tegra_actmon_device {
 	MCCPU,
 };
 
-static struct tegra_devfreq_device_config actmon_device_configs[] = {
+static const struct tegra_devfreq_device_config actmon_device_configs[] = {
 	{
 		/* MCALL: All memory accesses (including from the CPUs) */
 		.offset = 0x1c0,
@@ -117,10 +124,10 @@ static struct tegra_devfreq_device_config actmon_device_configs[] = {
 		.offset = 0x200,
 		.irq_mask = 1 << 25,
 		.boost_up_coeff = 800,
-		.boost_down_coeff = 90,
+		.boost_down_coeff = 40,
 		.boost_up_threshold = 27,
 		.boost_down_threshold = 10,
-		.avg_dependency_threshold = 50000,
+		.avg_dependency_threshold = 16000, /* 16MHz in kHz units */
 	},
 };
 
@@ -156,11 +163,16 @@ struct tegra_devfreq {
 	struct clk		*emc_clock;
 	unsigned long		max_freq;
 	unsigned long		cur_freq;
-	struct notifier_block	rate_change_nb;
+	struct notifier_block	clk_rate_change_nb;
+
+	struct delayed_work	cpufreq_update_work;
+	struct notifier_block	cpu_rate_change_nb;
 
 	struct tegra_devfreq_device devices[ARRAY_SIZE(actmon_device_configs)];
 
-	int irq;
+	unsigned int		irq;
+
+	bool			started;
 };
 
 struct tegra_actmon_emc_ratio {
@@ -168,8 +180,8 @@ struct tegra_actmon_emc_ratio {
 	unsigned long emc_freq;
 };
 
-static struct tegra_actmon_emc_ratio actmon_emc_ratios[] = {
-	{ 1400000, ULONG_MAX },
+static const struct tegra_actmon_emc_ratio actmon_emc_ratios[] = {
+	{ 1400000,    KHZ_MAX },
 	{ 1200000,    750000 },
 	{ 1100000,    600000 },
 	{ 1000000,    500000 },
@@ -199,18 +211,26 @@ static void device_writel(struct tegra_devfreq_device *dev, u32 val,
 	writel_relaxed(val, dev->regs + offset);
 }
 
-static unsigned long do_percent(unsigned long val, unsigned int pct)
+static unsigned long do_percent(unsigned long long val, unsigned int pct)
 {
-	return val * pct / 100;
+	val = val * pct;
+	do_div(val, 100);
+
+	/*
+	 * High freq + high boosting percent + large polling interval are
+	 * resulting in integer overflow when watermarks are calculated.
+	 */
+	return min_t(u64, val, U32_MAX);
 }
 
 static void tegra_devfreq_update_avg_wmark(struct tegra_devfreq *tegra,
 					   struct tegra_devfreq_device *dev)
 {
-	u32 avg = dev->avg_count;
 	u32 avg_band_freq = tegra->max_freq * ACTMON_DEFAULT_AVG_BAND / KHZ;
-	u32 band = avg_band_freq * ACTMON_SAMPLING_PERIOD;
+	u32 band = avg_band_freq * tegra->devfreq->profile->polling_ms;
+	u32 avg;
 
+	avg = min(dev->avg_count, U32_MAX - band);
 	device_writel(dev, avg + band, ACTMON_DEV_AVG_UPPER_WMARK);
 
 	avg = max(dev->avg_count, band);
@@ -220,7 +240,7 @@ static void tegra_devfreq_update_avg_wmark(struct tegra_devfreq *tegra,
 static void tegra_devfreq_update_wmark(struct tegra_devfreq *tegra,
 				       struct tegra_devfreq_device *dev)
 {
-	u32 val = tegra->cur_freq * ACTMON_SAMPLING_PERIOD;
+	u32 val = tegra->cur_freq * tegra->devfreq->profile->polling_ms;
 
 	device_writel(dev, do_percent(val, dev->config->boost_up_threshold),
 		      ACTMON_DEV_UPPER_WMARK);
@@ -229,12 +249,6 @@ static void tegra_devfreq_update_wmark(struct tegra_devfreq *tegra,
 		      ACTMON_DEV_LOWER_WMARK);
 }
 
-static void actmon_write_barrier(struct tegra_devfreq *tegra)
-{
-	/* ensure the update has reached the ACTMON */
-	readl(tegra->regs + ACTMON_GLB_STATUS);
-}
-
 static void actmon_isr_device(struct tegra_devfreq *tegra,
 			      struct tegra_devfreq_device *dev)
 {
@@ -256,10 +270,10 @@ static void actmon_isr_device(struct tegra_devfreq *tegra,
 
 		dev_ctrl |= ACTMON_DEV_CTRL_CONSECUTIVE_BELOW_WMARK_EN;
 
-		if (dev->boost_freq >= tegra->max_freq)
+		if (dev->boost_freq >= tegra->max_freq) {
+			dev_ctrl &= ~ACTMON_DEV_CTRL_CONSECUTIVE_ABOVE_WMARK_EN;
 			dev->boost_freq = tegra->max_freq;
-		else
-			dev_ctrl |= ACTMON_DEV_CTRL_CONSECUTIVE_ABOVE_WMARK_EN;
+		}
 	} else if (intr_status & ACTMON_DEV_INTR_CONSECUTIVE_LOWER) {
 		/*
 		 * new_boost = old_boost * down_coef
@@ -270,31 +284,22 @@ static void actmon_isr_device(struct tegra_devfreq *tegra,
 
 		dev_ctrl |= ACTMON_DEV_CTRL_CONSECUTIVE_ABOVE_WMARK_EN;
 
-		if (dev->boost_freq < (ACTMON_BOOST_FREQ_STEP >> 1))
-			dev->boost_freq = 0;
-		else
-			dev_ctrl |= ACTMON_DEV_CTRL_CONSECUTIVE_BELOW_WMARK_EN;
-	}
-
-	if (dev->config->avg_dependency_threshold) {
-		if (dev->avg_count >= dev->config->avg_dependency_threshold)
-			dev_ctrl |= ACTMON_DEV_CTRL_CONSECUTIVE_BELOW_WMARK_EN;
-		else if (dev->boost_freq == 0)
+		if (dev->boost_freq < (ACTMON_BOOST_FREQ_STEP >> 1)) {
 			dev_ctrl &= ~ACTMON_DEV_CTRL_CONSECUTIVE_BELOW_WMARK_EN;
+			dev->boost_freq = 0;
+		}
 	}
 
 	device_writel(dev, dev_ctrl, ACTMON_DEV_CTRL);
 
 	device_writel(dev, ACTMON_INTR_STATUS_CLEAR, ACTMON_DEV_INTR_STATUS);
-
-	actmon_write_barrier(tegra);
 }
 
 static unsigned long actmon_cpu_to_emc_rate(struct tegra_devfreq *tegra,
 					    unsigned long cpu_freq)
 {
 	unsigned int i;
-	struct tegra_actmon_emc_ratio *ratio = actmon_emc_ratios;
+	const struct tegra_actmon_emc_ratio *ratio = actmon_emc_ratios;
 
 	for (i = 0; i < ARRAY_SIZE(actmon_emc_ratios); i++, ratio++) {
 		if (cpu_freq >= ratio->cpu_freq) {
@@ -308,25 +313,37 @@ static unsigned long actmon_cpu_to_emc_rate(struct tegra_devfreq *tegra,
 	return 0;
 }
 
+static unsigned long actmon_device_target_freq(struct tegra_devfreq *tegra,
+					       struct tegra_devfreq_device *dev)
+{
+	unsigned int avg_sustain_coef;
+	unsigned long target_freq;
+
+	target_freq = dev->avg_count / tegra->devfreq->profile->polling_ms;
+	avg_sustain_coef = 100 * 100 / dev->config->boost_up_threshold;
+	target_freq = do_percent(target_freq, avg_sustain_coef);
+
+	return target_freq;
+}
+
 static void actmon_update_target(struct tegra_devfreq *tegra,
 				 struct tegra_devfreq_device *dev)
 {
 	unsigned long cpu_freq = 0;
 	unsigned long static_cpu_emc_freq = 0;
-	unsigned int avg_sustain_coef;
 
-	if (dev->config->avg_dependency_threshold) {
-		cpu_freq = cpufreq_get(0);
-		static_cpu_emc_freq = actmon_cpu_to_emc_rate(tegra, cpu_freq);
-	}
+	dev->target_freq = actmon_device_target_freq(tegra, dev);
 
-	dev->target_freq = dev->avg_count / ACTMON_SAMPLING_PERIOD;
-	avg_sustain_coef = 100 * 100 / dev->config->boost_up_threshold;
-	dev->target_freq = do_percent(dev->target_freq, avg_sustain_coef);
-	dev->target_freq += dev->boost_freq;
+	if (dev->config->avg_dependency_threshold &&
+	    dev->config->avg_dependency_threshold <= dev->target_freq) {
+		cpu_freq = cpufreq_quick_get(0);
+		static_cpu_emc_freq = actmon_cpu_to_emc_rate(tegra, cpu_freq);
 
-	if (dev->avg_count >= dev->config->avg_dependency_threshold)
+		dev->target_freq += dev->boost_freq;
 		dev->target_freq = max(dev->target_freq, static_cpu_emc_freq);
+	} else {
+		dev->target_freq += dev->boost_freq;
+	}
 }
 
 static irqreturn_t actmon_thread_isr(int irq, void *data)
@@ -354,8 +371,8 @@ static irqreturn_t actmon_thread_isr(int irq, void *data)
 	return handled ? IRQ_HANDLED : IRQ_NONE;
 }
 
-static int tegra_actmon_rate_notify_cb(struct notifier_block *nb,
-				       unsigned long action, void *ptr)
+static int tegra_actmon_clk_notify_cb(struct notifier_block *nb,
+				      unsigned long action, void *ptr)
 {
 	struct clk_notifier_data *data = ptr;
 	struct tegra_devfreq *tegra;
@@ -365,7 +382,7 @@ static int tegra_actmon_rate_notify_cb(struct notifier_block *nb,
 	if (action != POST_RATE_CHANGE)
 		return NOTIFY_OK;
 
-	tegra = container_of(nb, struct tegra_devfreq, rate_change_nb);
+	tegra = container_of(nb, struct tegra_devfreq, clk_rate_change_nb);
 
 	tegra->cur_freq = data->new_rate / KHZ;
 
@@ -375,7 +392,79 @@ static int tegra_actmon_rate_notify_cb(struct notifier_block *nb,
 		tegra_devfreq_update_wmark(tegra, dev);
 	}
 
-	actmon_write_barrier(tegra);
+	return NOTIFY_OK;
+}
+
+static void tegra_actmon_delayed_update(struct work_struct *work)
+{
+	struct tegra_devfreq *tegra = container_of(work, struct tegra_devfreq,
+						   cpufreq_update_work.work);
+
+	mutex_lock(&tegra->devfreq->lock);
+	update_devfreq(tegra->devfreq);
+	mutex_unlock(&tegra->devfreq->lock);
+}
+
+static unsigned long
+tegra_actmon_cpufreq_contribution(struct tegra_devfreq *tegra,
+				  unsigned int cpu_freq)
+{
+	struct tegra_devfreq_device *actmon_dev = &tegra->devices[MCCPU];
+	unsigned long static_cpu_emc_freq, dev_freq;
+
+	dev_freq = actmon_device_target_freq(tegra, actmon_dev);
+
+	/* check whether CPU's freq is taken into account at all */
+	if (dev_freq < actmon_dev->config->avg_dependency_threshold)
+		return 0;
+
+	static_cpu_emc_freq = actmon_cpu_to_emc_rate(tegra, cpu_freq);
+
+	if (dev_freq >= static_cpu_emc_freq)
+		return 0;
+
+	return static_cpu_emc_freq;
+}
+
+static int tegra_actmon_cpu_notify_cb(struct notifier_block *nb,
+				      unsigned long action, void *ptr)
+{
+	struct cpufreq_freqs *freqs = ptr;
+	struct tegra_devfreq *tegra;
+	unsigned long old, new, delay;
+
+	if (action != CPUFREQ_POSTCHANGE)
+		return NOTIFY_OK;
+
+	tegra = container_of(nb, struct tegra_devfreq, cpu_rate_change_nb);
+
+	/*
+	 * Quickly check whether CPU frequency should be taken into account
+	 * at all, without blocking CPUFreq's core.
+	 */
+	if (mutex_trylock(&tegra->devfreq->lock)) {
+		old = tegra_actmon_cpufreq_contribution(tegra, freqs->old);
+		new = tegra_actmon_cpufreq_contribution(tegra, freqs->new);
+		mutex_unlock(&tegra->devfreq->lock);
+
+		/*
+		 * If CPU's frequency shouldn't be taken into account at
+		 * the moment, then there is no need to update the devfreq's
+		 * state because ISR will re-check CPU's frequency on the
+		 * next interrupt.
+		 */
+		if (old == new)
+			return NOTIFY_OK;
+	}
+
+	/*
+	 * CPUFreq driver should support CPUFREQ_ASYNC_NOTIFICATION in order
+	 * to allow asynchronous notifications. This means we can't block
+	 * here for too long, otherwise CPUFreq's core will complain with a
+	 * warning splat.
+	 */
+	delay = msecs_to_jiffies(ACTMON_SAMPLING_PERIOD);
+	schedule_delayed_work(&tegra->cpufreq_update_work, delay);
 
 	return NOTIFY_OK;
 }
@@ -385,9 +474,12 @@ static void tegra_actmon_configure_device(struct tegra_devfreq *tegra,
 {
 	u32 val = 0;
 
+	/* reset boosting on governor's restart */
+	dev->boost_freq = 0;
+
 	dev->target_freq = tegra->cur_freq;
 
-	dev->avg_count = tegra->cur_freq * ACTMON_SAMPLING_PERIOD;
+	dev->avg_count = tegra->cur_freq * tegra->devfreq->profile->polling_ms;
 	device_writel(dev, dev->avg_count, ACTMON_DEV_INIT_AVG);
 
 	tegra_devfreq_update_avg_wmark(tegra, dev);
@@ -405,45 +497,116 @@ static void tegra_actmon_configure_device(struct tegra_devfreq *tegra,
 		<< ACTMON_DEV_CTRL_CONSECUTIVE_ABOVE_WMARK_NUM_SHIFT;
 	val |= ACTMON_DEV_CTRL_AVG_ABOVE_WMARK_EN;
 	val |= ACTMON_DEV_CTRL_AVG_BELOW_WMARK_EN;
-	val |= ACTMON_DEV_CTRL_CONSECUTIVE_BELOW_WMARK_EN;
 	val |= ACTMON_DEV_CTRL_CONSECUTIVE_ABOVE_WMARK_EN;
 	val |= ACTMON_DEV_CTRL_ENB;
 
 	device_writel(dev, val, ACTMON_DEV_CTRL);
 }
 
-static void tegra_actmon_start(struct tegra_devfreq *tegra)
+static void tegra_actmon_stop_devices(struct tegra_devfreq *tegra)
 {
+	struct tegra_devfreq_device *dev = tegra->devices;
 	unsigned int i;
 
-	disable_irq(tegra->irq);
+	for (i = 0; i < ARRAY_SIZE(tegra->devices); i++, dev++) {
+		device_writel(dev, ACTMON_DEV_CTRL_STOP, ACTMON_DEV_CTRL);
+		device_writel(dev, ACTMON_INTR_STATUS_CLEAR,
+			      ACTMON_DEV_INTR_STATUS);
+	}
+}
 
-	actmon_writel(tegra, ACTMON_SAMPLING_PERIOD - 1,
+static int tegra_actmon_resume(struct tegra_devfreq *tegra)
+{
+	unsigned int i;
+	int err;
+
+	if (!tegra->devfreq->profile->polling_ms || !tegra->started)
+		return 0;
+
+	actmon_writel(tegra, tegra->devfreq->profile->polling_ms - 1,
 		      ACTMON_GLB_PERIOD_CTRL);
 
+	/*
+	 * CLK notifications are needed in order to reconfigure the upper
+	 * consecutive watermark in accordance to the actual clock rate
+	 * to avoid unnecessary upper interrupts.
+	 */
+	err = clk_notifier_register(tegra->emc_clock,
+				    &tegra->clk_rate_change_nb);
+	if (err) {
+		dev_err(tegra->devfreq->dev.parent,
+			"Failed to register rate change notifier\n");
+		return err;
+	}
+
+	tegra->cur_freq = clk_get_rate(tegra->emc_clock) / KHZ;
+
 	for (i = 0; i < ARRAY_SIZE(tegra->devices); i++)
 		tegra_actmon_configure_device(tegra, &tegra->devices[i]);
 
-	actmon_write_barrier(tegra);
+	/*
+	 * We are estimating CPU's memory bandwidth requirement based on
+	 * amount of memory accesses and system's load, judging by CPU's
+	 * frequency. We also don't want to receive events about CPU's
+	 * frequency transaction when governor is stopped, hence notifier
+	 * is registered dynamically.
+	 */
+	err = cpufreq_register_notifier(&tegra->cpu_rate_change_nb,
+					CPUFREQ_TRANSITION_NOTIFIER);
+	if (err) {
+		dev_err(tegra->devfreq->dev.parent,
+			"Failed to register rate change notifier: %d\n", err);
+		goto err_stop;
+	}
 
 	enable_irq(tegra->irq);
+
+	return 0;
+
+err_stop:
+	tegra_actmon_stop_devices(tegra);
+
+	clk_notifier_unregister(tegra->emc_clock, &tegra->clk_rate_change_nb);
+
+	return err;
 }
 
-static void tegra_actmon_stop(struct tegra_devfreq *tegra)
+static int tegra_actmon_start(struct tegra_devfreq *tegra)
 {
-	unsigned int i;
+	int ret = 0;
 
-	disable_irq(tegra->irq);
+	if (!tegra->started) {
+		tegra->started = true;
 
-	for (i = 0; i < ARRAY_SIZE(tegra->devices); i++) {
-		device_writel(&tegra->devices[i], 0x00000000, ACTMON_DEV_CTRL);
-		device_writel(&tegra->devices[i], ACTMON_INTR_STATUS_CLEAR,
-			      ACTMON_DEV_INTR_STATUS);
+		ret = tegra_actmon_resume(tegra);
+		if (ret)
+			tegra->started = false;
 	}
 
-	actmon_write_barrier(tegra);
+	return ret;
+}
 
-	enable_irq(tegra->irq);
+static void tegra_actmon_pause(struct tegra_devfreq *tegra)
+{
+	if (!tegra->devfreq->profile->polling_ms || !tegra->started)
+		return;
+
+	disable_irq(tegra->irq);
+
+	cpufreq_unregister_notifier(&tegra->cpu_rate_change_nb,
+				    CPUFREQ_TRANSITION_NOTIFIER);
+
+	cancel_delayed_work_sync(&tegra->cpufreq_update_work);
+
+	tegra_actmon_stop_devices(tegra);
+
+	clk_notifier_unregister(tegra->emc_clock, &tegra->clk_rate_change_nb);
+}
+
+static void tegra_actmon_stop(struct tegra_devfreq *tegra)
+{
+	tegra_actmon_pause(tegra);
+	tegra->started = false;
 }
 
 static int tegra_devfreq_target(struct device *dev, unsigned long *freq,
@@ -463,7 +626,7 @@ static int tegra_devfreq_target(struct device *dev, unsigned long *freq,
 	rate = dev_pm_opp_get_freq(opp);
 	dev_pm_opp_put(opp);
 
-	err = clk_set_min_rate(tegra->emc_clock, rate);
+	err = clk_set_min_rate(tegra->emc_clock, rate * KHZ);
 	if (err)
 		return err;
 
@@ -492,7 +655,7 @@ static int tegra_devfreq_get_dev_status(struct device *dev,
 	stat->private_data = tegra;
 
 	/* The below are to be used by the other governors */
-	stat->current_frequency = cur_freq * KHZ;
+	stat->current_frequency = cur_freq;
 
 	actmon_dev = &tegra->devices[MCALL];
 
@@ -503,7 +666,7 @@ static int tegra_devfreq_get_dev_status(struct device *dev,
 	stat->busy_time *= 100 / BUS_SATURATION_RATIO;
 
 	/* Number of cycles in a sampling period */
-	stat->total_time = ACTMON_SAMPLING_PERIOD * cur_freq;
+	stat->total_time = tegra->devfreq->profile->polling_ms * cur_freq;
 
 	stat->busy_time = min(stat->busy_time, stat->total_time);
 
@@ -511,7 +674,7 @@ static int tegra_devfreq_get_dev_status(struct device *dev,
 }
 
 static struct devfreq_dev_profile tegra_devfreq_profile = {
-	.polling_ms	= 0,
+	.polling_ms	= ACTMON_SAMPLING_PERIOD,
 	.target		= tegra_devfreq_target,
 	.get_dev_status	= tegra_devfreq_get_dev_status,
 };
@@ -542,7 +705,7 @@ static int tegra_governor_get_target(struct devfreq *devfreq,
 		target_freq = max(target_freq, dev->target_freq);
 	}
 
-	*freq = target_freq * KHZ;
+	*freq = target_freq;
 
 	return 0;
 }
@@ -551,11 +714,19 @@ static int tegra_governor_event_handler(struct devfreq *devfreq,
 					unsigned int event, void *data)
 {
 	struct tegra_devfreq *tegra = dev_get_drvdata(devfreq->dev.parent);
+	unsigned int *new_delay = data;
+	int ret = 0;
+
+	/*
+	 * Couple devfreq-device with the governor early because it is
+	 * needed at the moment of governor's start (used by ISR).
+	 */
+	tegra->devfreq = devfreq;
 
 	switch (event) {
 	case DEVFREQ_GOV_START:
 		devfreq_monitor_start(devfreq);
-		tegra_actmon_start(tegra);
+		ret = tegra_actmon_start(tegra);
 		break;
 
 	case DEVFREQ_GOV_STOP:
@@ -563,6 +734,21 @@ static int tegra_governor_event_handler(struct devfreq *devfreq,
 		devfreq_monitor_stop(devfreq);
 		break;
 
+	case DEVFREQ_GOV_INTERVAL:
+		/*
+		 * ACTMON hardware supports up to 256 milliseconds for the
+		 * sampling period.
+		 */
+		if (*new_delay > 256) {
+			ret = -EINVAL;
+			break;
+		}
+
+		tegra_actmon_pause(tegra);
+		devfreq_interval_update(devfreq, new_delay);
+		ret = tegra_actmon_resume(tegra);
+		break;
+
 	case DEVFREQ_GOV_SUSPEND:
 		tegra_actmon_stop(tegra);
 		devfreq_monitor_suspend(devfreq);
@@ -570,11 +756,11 @@ static int tegra_governor_event_handler(struct devfreq *devfreq,
 
 	case DEVFREQ_GOV_RESUME:
 		devfreq_monitor_resume(devfreq);
-		tegra_actmon_start(tegra);
+		ret = tegra_actmon_start(tegra);
 		break;
 	}
 
-	return 0;
+	return ret;
 }
 
 static struct devfreq_governor tegra_devfreq_governor = {
@@ -582,14 +768,16 @@ static struct devfreq_governor tegra_devfreq_governor = {
 	.get_target_freq = tegra_governor_get_target,
 	.event_handler = tegra_governor_event_handler,
 	.immutable = true,
+	.interrupt_driven = true,
 };
 
 static int tegra_devfreq_probe(struct platform_device *pdev)
 {
-	struct tegra_devfreq *tegra;
 	struct tegra_devfreq_device *dev;
+	struct tegra_devfreq *tegra;
+	struct devfreq *devfreq;
 	unsigned int i;
-	unsigned long rate;
+	long rate;
 	int err;
 
 	tegra = devm_kzalloc(&pdev->dev, sizeof(*tegra), GFP_KERNEL);
@@ -618,12 +806,22 @@ static int tegra_devfreq_probe(struct platform_device *pdev)
 		return PTR_ERR(tegra->emc_clock);
 	}
 
-	tegra->irq = platform_get_irq(pdev, 0);
-	if (tegra->irq < 0) {
-		err = tegra->irq;
+	err = platform_get_irq(pdev, 0);
+	if (err < 0) {
 		dev_err(&pdev->dev, "Failed to get IRQ: %d\n", err);
 		return err;
 	}
+	tegra->irq = err;
+
+	irq_set_status_flags(tegra->irq, IRQ_NOAUTOEN);
+
+	err = devm_request_threaded_irq(&pdev->dev, tegra->irq, NULL,
+					actmon_thread_isr, IRQF_ONESHOT,
+					"tegra-devfreq", tegra);
+	if (err) {
+		dev_err(&pdev->dev, "Interrupt request failed: %d\n", err);
+		return err;
+	}
 
 	reset_control_assert(tegra->reset);
 
@@ -636,8 +834,13 @@ static int tegra_devfreq_probe(struct platform_device *pdev)
 
 	reset_control_deassert(tegra->reset);
 
-	tegra->max_freq = clk_round_rate(tegra->emc_clock, ULONG_MAX) / KHZ;
-	tegra->cur_freq = clk_get_rate(tegra->emc_clock) / KHZ;
+	rate = clk_round_rate(tegra->emc_clock, ULONG_MAX);
+	if (rate < 0) {
+		dev_err(&pdev->dev, "Failed to round clock rate: %ld\n", rate);
+		return rate;
+	}
+
+	tegra->max_freq = rate / KHZ;
 
 	for (i = 0; i < ARRAY_SIZE(actmon_device_configs); i++) {
 		dev = tegra->devices + i;
@@ -648,7 +851,14 @@ static int tegra_devfreq_probe(struct platform_device *pdev)
 	for (rate = 0; rate <= tegra->max_freq * KHZ; rate++) {
 		rate = clk_round_rate(tegra->emc_clock, rate);
 
-		err = dev_pm_opp_add(&pdev->dev, rate, 0);
+		if (rate < 0) {
+			dev_err(&pdev->dev,
+				"Failed to round clock rate: %ld\n", rate);
+			err = rate;
+			goto remove_opps;
+		}
+
+		err = dev_pm_opp_add(&pdev->dev, rate / KHZ, 0);
 		if (err) {
 			dev_err(&pdev->dev, "Failed to add OPP: %d\n", err);
 			goto remove_opps;
@@ -657,49 +867,33 @@ static int tegra_devfreq_probe(struct platform_device *pdev)
 
 	platform_set_drvdata(pdev, tegra);
 
-	tegra->rate_change_nb.notifier_call = tegra_actmon_rate_notify_cb;
-	err = clk_notifier_register(tegra->emc_clock, &tegra->rate_change_nb);
-	if (err) {
-		dev_err(&pdev->dev,
-			"Failed to register rate change notifier\n");
-		goto remove_opps;
-	}
+	tegra->clk_rate_change_nb.notifier_call = tegra_actmon_clk_notify_cb;
+	tegra->cpu_rate_change_nb.notifier_call = tegra_actmon_cpu_notify_cb;
+
+	INIT_DELAYED_WORK(&tegra->cpufreq_update_work,
+			  tegra_actmon_delayed_update);
 
 	err = devfreq_add_governor(&tegra_devfreq_governor);
 	if (err) {
 		dev_err(&pdev->dev, "Failed to add governor: %d\n", err);
-		goto unreg_notifier;
+		goto remove_opps;
 	}
 
 	tegra_devfreq_profile.initial_freq = clk_get_rate(tegra->emc_clock);
-	tegra->devfreq = devfreq_add_device(&pdev->dev,
-					    &tegra_devfreq_profile,
-					    "tegra_actmon",
-					    NULL);
-	if (IS_ERR(tegra->devfreq)) {
-		err = PTR_ERR(tegra->devfreq);
-		goto remove_governor;
-	}
+	tegra_devfreq_profile.initial_freq /= KHZ;
 
-	err = devm_request_threaded_irq(&pdev->dev, tegra->irq, NULL,
-					actmon_thread_isr, IRQF_ONESHOT,
-					"tegra-devfreq", tegra);
-	if (err) {
-		dev_err(&pdev->dev, "Interrupt request failed: %d\n", err);
-		goto remove_devfreq;
+	devfreq = devfreq_add_device(&pdev->dev, &tegra_devfreq_profile,
+				     "tegra_actmon", NULL);
+	if (IS_ERR(devfreq)) {
+		err = PTR_ERR(devfreq);
+		goto remove_governor;
 	}
 
 	return 0;
 
-remove_devfreq:
-	devfreq_remove_device(tegra->devfreq);
-
 remove_governor:
 	devfreq_remove_governor(&tegra_devfreq_governor);
 
-unreg_notifier:
-	clk_notifier_unregister(tegra->emc_clock, &tegra->rate_change_nb);
-
 remove_opps:
 	dev_pm_opp_remove_all_dynamic(&pdev->dev);
 
@@ -716,7 +910,6 @@ static int tegra_devfreq_remove(struct platform_device *pdev)
 	devfreq_remove_device(tegra->devfreq);
 	devfreq_remove_governor(&tegra_devfreq_governor);
 
-	clk_notifier_unregister(tegra->emc_clock, &tegra->rate_change_nb);
 	dev_pm_opp_remove_all_dynamic(&pdev->dev);
 
 	reset_control_reset(tegra->reset);
diff --git a/drivers/firmware/efi/Kconfig b/drivers/firmware/efi/Kconfig
index b248870a9806..bcc378c19ebe 100644
--- a/drivers/firmware/efi/Kconfig
+++ b/drivers/firmware/efi/Kconfig
@@ -75,6 +75,27 @@ config EFI_MAX_FAKE_MEM
 	  Ranges can be set up to this value using comma-separated list.
 	  The default value is 8.
 
+config EFI_SOFT_RESERVE
+	bool "Reserve EFI Specific Purpose Memory"
+	depends on EFI && EFI_STUB && ACPI_HMAT
+	default ACPI_HMAT
+	help
+	  On systems that have mixed performance classes of memory EFI
+	  may indicate specific purpose memory with an attribute (See
+	  EFI_MEMORY_SP in UEFI 2.8). A memory range tagged with this
+	  attribute may have unique performance characteristics compared
+	  to the system's general purpose "System RAM" pool. On the
+	  expectation that such memory has application specific usage,
+	  and its base EFI memory type is "conventional" answer Y to
+	  arrange for the kernel to reserve it as a "Soft Reserved"
+	  resource, and set aside for direct-access (device-dax) by
+	  default. The memory range can later be optionally assigned to
+	  the page allocator by system administrator policy via the
+	  device-dax kmem facility. Say N to have the kernel treat this
+	  memory as "System RAM" by default.
+
+	  If unsure, say Y.
+
 config EFI_PARAMS_FROM_FDT
 	bool
 	help
diff --git a/drivers/firmware/efi/Makefile b/drivers/firmware/efi/Makefile
index 4ac2de4dfa72..554d795270d9 100644
--- a/drivers/firmware/efi/Makefile
+++ b/drivers/firmware/efi/Makefile
@@ -20,13 +20,16 @@ obj-$(CONFIG_UEFI_CPER)			+= cper.o
 obj-$(CONFIG_EFI_RUNTIME_MAP)		+= runtime-map.o
 obj-$(CONFIG_EFI_RUNTIME_WRAPPERS)	+= runtime-wrappers.o
 obj-$(CONFIG_EFI_STUB)			+= libstub/
-obj-$(CONFIG_EFI_FAKE_MEMMAP)		+= fake_mem.o
+obj-$(CONFIG_EFI_FAKE_MEMMAP)		+= fake_map.o
 obj-$(CONFIG_EFI_BOOTLOADER_CONTROL)	+= efibc.o
 obj-$(CONFIG_EFI_TEST)			+= test/
 obj-$(CONFIG_EFI_DEV_PATH_PARSER)	+= dev-path-parser.o
 obj-$(CONFIG_APPLE_PROPERTIES)		+= apple-properties.o
 obj-$(CONFIG_EFI_RCI2_TABLE)		+= rci2-table.o
 
+fake_map-y				+= fake_mem.o
+fake_map-$(CONFIG_X86)			+= x86_fake_mem.o
+
 arm-obj-$(CONFIG_EFI)			:= arm-init.o arm-runtime.o
 obj-$(CONFIG_ARM)			+= $(arm-obj-y)
 obj-$(CONFIG_ARM64)			+= $(arm-obj-y)
diff --git a/drivers/firmware/efi/apple-properties.c b/drivers/firmware/efi/apple-properties.c
index 0e206c9e0d7a..5ccf39986a14 100644
--- a/drivers/firmware/efi/apple-properties.c
+++ b/drivers/firmware/efi/apple-properties.c
@@ -53,7 +53,8 @@ static void __init unmarshal_key_value_pairs(struct dev_header *dev_header,
 
 	for (i = 0; i < dev_header->prop_count; i++) {
 		int remaining = dev_header->len - (ptr - (void *)dev_header);
-		u32 key_len, val_len;
+		u32 key_len, val_len, entry_len;
+		const u8 *entry_data;
 		char *key;
 
 		if (sizeof(key_len) > remaining)
@@ -85,17 +86,14 @@ static void __init unmarshal_key_value_pairs(struct dev_header *dev_header,
 		ucs2_as_utf8(key, ptr + sizeof(key_len),
 			     key_len - sizeof(key_len));
 
-		entry[i].name = key;
-		entry[i].length = val_len - sizeof(val_len);
-		entry[i].is_array = !!entry[i].length;
-		entry[i].type = DEV_PROP_U8;
-		entry[i].pointer.u8_data = ptr + key_len + sizeof(val_len);
-
+		entry_data = ptr + key_len + sizeof(val_len);
+		entry_len = val_len - sizeof(val_len);
+		entry[i] = PROPERTY_ENTRY_U8_ARRAY_LEN(key, entry_data,
+						       entry_len);
 		if (dump_properties) {
-			dev_info(dev, "property: %s\n", entry[i].name);
+			dev_info(dev, "property: %s\n", key);
 			print_hex_dump(KERN_INFO, pr_fmt(), DUMP_PREFIX_OFFSET,
-				16, 1, entry[i].pointer.u8_data,
-				entry[i].length, true);
+				16, 1, entry_data, entry_len, true);
 		}
 
 		ptr += key_len + val_len;
diff --git a/drivers/firmware/efi/arm-init.c b/drivers/firmware/efi/arm-init.c
index 311cd349a862..904fa09e6a6b 100644
--- a/drivers/firmware/efi/arm-init.c
+++ b/drivers/firmware/efi/arm-init.c
@@ -164,6 +164,15 @@ static __init int is_usable_memory(efi_memory_desc_t *md)
 	case EFI_CONVENTIONAL_MEMORY:
 	case EFI_PERSISTENT_MEMORY:
 		/*
+		 * Special purpose memory is 'soft reserved', which means it
+		 * is set aside initially, but can be hotplugged back in or
+		 * be assigned to the dax driver after boot.
+		 */
+		if (efi_soft_reserve_enabled() &&
+		    (md->attribute & EFI_MEMORY_SP))
+			return false;
+
+		/*
 		 * According to the spec, these regions are no longer reserved
 		 * after calling ExitBootServices(). However, we can only use
 		 * them as System RAM if they can be mapped writeback cacheable.
diff --git a/drivers/firmware/efi/arm-runtime.c b/drivers/firmware/efi/arm-runtime.c
index e2ac5fa5531b..899b803842bb 100644
--- a/drivers/firmware/efi/arm-runtime.c
+++ b/drivers/firmware/efi/arm-runtime.c
@@ -121,6 +121,30 @@ static int __init arm_enable_runtime_services(void)
 		return 0;
 	}
 
+	if (efi_soft_reserve_enabled()) {
+		efi_memory_desc_t *md;
+
+		for_each_efi_memory_desc(md) {
+			int md_size = md->num_pages << EFI_PAGE_SHIFT;
+			struct resource *res;
+
+			if (!(md->attribute & EFI_MEMORY_SP))
+				continue;
+
+			res = kzalloc(sizeof(*res), GFP_KERNEL);
+			if (WARN_ON(!res))
+				break;
+
+			res->start	= md->phys_addr;
+			res->end	= md->phys_addr + md_size - 1;
+			res->name	= "Soft Reserved";
+			res->flags	= IORESOURCE_MEM;
+			res->desc	= IORES_DESC_SOFT_RESERVED;
+
+			insert_resource(&iomem_resource, res);
+		}
+	}
+
 	if (efi_runtime_disabled()) {
 		pr_info("EFI runtime services will be disabled.\n");
 		return 0;
diff --git a/drivers/firmware/efi/efi.c b/drivers/firmware/efi/efi.c
index e98bbf8e56d9..d101f072c8f8 100644
--- a/drivers/firmware/efi/efi.c
+++ b/drivers/firmware/efi/efi.c
@@ -81,6 +81,11 @@ bool efi_runtime_disabled(void)
 	return disable_runtime;
 }
 
+bool __pure __efi_soft_reserve_enabled(void)
+{
+	return !efi_enabled(EFI_MEM_NO_SOFT_RESERVE);
+}
+
 static int __init parse_efi_cmdline(char *str)
 {
 	if (!str) {
@@ -94,6 +99,9 @@ static int __init parse_efi_cmdline(char *str)
 	if (parse_option_str(str, "noruntime"))
 		disable_runtime = true;
 
+	if (parse_option_str(str, "nosoftreserve"))
+		set_bit(EFI_MEM_NO_SOFT_RESERVE, &efi.flags);
+
 	return 0;
 }
 early_param("efi", parse_efi_cmdline);
@@ -296,7 +304,7 @@ static __init int efivar_ssdt_load(void)
 			goto free_data;
 		}
 
-		ret = acpi_load_table(data);
+		ret = acpi_load_table(data, NULL);
 		if (ret) {
 			pr_err("failed to load table: %d\n", ret);
 			goto free_data;
@@ -842,15 +850,16 @@ char * __init efi_md_typeattr_format(char *buf, size_t size,
 	if (attr & ~(EFI_MEMORY_UC | EFI_MEMORY_WC | EFI_MEMORY_WT |
 		     EFI_MEMORY_WB | EFI_MEMORY_UCE | EFI_MEMORY_RO |
 		     EFI_MEMORY_WP | EFI_MEMORY_RP | EFI_MEMORY_XP |
-		     EFI_MEMORY_NV |
+		     EFI_MEMORY_NV | EFI_MEMORY_SP |
 		     EFI_MEMORY_RUNTIME | EFI_MEMORY_MORE_RELIABLE))
 		snprintf(pos, size, "|attr=0x%016llx]",
 			 (unsigned long long)attr);
 	else
 		snprintf(pos, size,
-			 "|%3s|%2s|%2s|%2s|%2s|%2s|%2s|%3s|%2s|%2s|%2s|%2s]",
+			 "|%3s|%2s|%2s|%2s|%2s|%2s|%2s|%2s|%3s|%2s|%2s|%2s|%2s]",
 			 attr & EFI_MEMORY_RUNTIME ? "RUN" : "",
 			 attr & EFI_MEMORY_MORE_RELIABLE ? "MR" : "",
+			 attr & EFI_MEMORY_SP      ? "SP"  : "",
 			 attr & EFI_MEMORY_NV      ? "NV"  : "",
 			 attr & EFI_MEMORY_XP      ? "XP"  : "",
 			 attr & EFI_MEMORY_RP      ? "RP"  : "",
diff --git a/drivers/firmware/efi/esrt.c b/drivers/firmware/efi/esrt.c
index d6dd5f503fa2..2762e0662bf4 100644
--- a/drivers/firmware/efi/esrt.c
+++ b/drivers/firmware/efi/esrt.c
@@ -246,6 +246,9 @@ void __init efi_esrt_init(void)
 	int rc;
 	phys_addr_t end;
 
+	if (!efi_enabled(EFI_MEMMAP))
+		return;
+
 	pr_debug("esrt-init: loading.\n");
 	if (!esrt_table_exists())
 		return;
diff --git a/drivers/firmware/efi/fake_mem.c b/drivers/firmware/efi/fake_mem.c
index 9501edc0fcfb..bb9fc70d0cfa 100644
--- a/drivers/firmware/efi/fake_mem.c
+++ b/drivers/firmware/efi/fake_mem.c
@@ -17,12 +17,10 @@
 #include <linux/memblock.h>
 #include <linux/types.h>
 #include <linux/sort.h>
-#include <asm/efi.h>
+#include "fake_mem.h"
 
-#define EFI_MAX_FAKEMEM CONFIG_EFI_MAX_FAKE_MEM
-
-static struct efi_mem_range fake_mems[EFI_MAX_FAKEMEM];
-static int nr_fake_mem;
+struct efi_mem_range efi_fake_mems[EFI_MAX_FAKEMEM];
+int nr_fake_mem;
 
 static int __init cmp_fake_mem(const void *x1, const void *x2)
 {
@@ -44,13 +42,13 @@ void __init efi_fake_memmap(void)
 	void *new_memmap;
 	int i;
 
-	if (!nr_fake_mem)
+	if (!efi_enabled(EFI_MEMMAP) || !nr_fake_mem)
 		return;
 
 	/* count up the number of EFI memory descriptor */
 	for (i = 0; i < nr_fake_mem; i++) {
 		for_each_efi_memory_desc(md) {
-			struct range *r = &fake_mems[i].range;
+			struct range *r = &efi_fake_mems[i].range;
 
 			new_nr_map += efi_memmap_split_count(md, r);
 		}
@@ -70,7 +68,7 @@ void __init efi_fake_memmap(void)
 	}
 
 	for (i = 0; i < nr_fake_mem; i++)
-		efi_memmap_insert(&efi.memmap, new_memmap, &fake_mems[i]);
+		efi_memmap_insert(&efi.memmap, new_memmap, &efi_fake_mems[i]);
 
 	/* swap into new EFI memmap */
 	early_memunmap(new_memmap, efi.memmap.desc_size * new_nr_map);
@@ -104,22 +102,22 @@ static int __init setup_fake_mem(char *p)
 		if (nr_fake_mem >= EFI_MAX_FAKEMEM)
 			break;
 
-		fake_mems[nr_fake_mem].range.start = start;
-		fake_mems[nr_fake_mem].range.end = start + mem_size - 1;
-		fake_mems[nr_fake_mem].attribute = attribute;
+		efi_fake_mems[nr_fake_mem].range.start = start;
+		efi_fake_mems[nr_fake_mem].range.end = start + mem_size - 1;
+		efi_fake_mems[nr_fake_mem].attribute = attribute;
 		nr_fake_mem++;
 
 		if (*p == ',')
 			p++;
 	}
 
-	sort(fake_mems, nr_fake_mem, sizeof(struct efi_mem_range),
+	sort(efi_fake_mems, nr_fake_mem, sizeof(struct efi_mem_range),
 	     cmp_fake_mem, NULL);
 
 	for (i = 0; i < nr_fake_mem; i++)
 		pr_info("efi_fake_mem: add attr=0x%016llx to [mem 0x%016llx-0x%016llx]",
-			fake_mems[i].attribute, fake_mems[i].range.start,
-			fake_mems[i].range.end);
+			efi_fake_mems[i].attribute, efi_fake_mems[i].range.start,
+			efi_fake_mems[i].range.end);
 
 	return *p == '\0' ? 0 : -EINVAL;
 }
diff --git a/drivers/firmware/efi/fake_mem.h b/drivers/firmware/efi/fake_mem.h
new file mode 100644
index 000000000000..d52791af4b18
--- /dev/null
+++ b/drivers/firmware/efi/fake_mem.h
@@ -0,0 +1,10 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __EFI_FAKE_MEM_H__
+#define __EFI_FAKE_MEM_H__
+#include <asm/efi.h>
+
+#define EFI_MAX_FAKEMEM CONFIG_EFI_MAX_FAKE_MEM
+
+extern struct efi_mem_range efi_fake_mems[EFI_MAX_FAKEMEM];
+extern int nr_fake_mem;
+#endif /* __EFI_FAKE_MEM_H__ */
diff --git a/drivers/firmware/efi/libstub/Makefile b/drivers/firmware/efi/libstub/Makefile
index ee0661ddb25b..c35f893897e1 100644
--- a/drivers/firmware/efi/libstub/Makefile
+++ b/drivers/firmware/efi/libstub/Makefile
@@ -38,7 +38,8 @@ OBJECT_FILES_NON_STANDARD	:= y
 # Prevents link failures: __sanitizer_cov_trace_pc() is not linked in.
 KCOV_INSTRUMENT			:= n
 
-lib-y				:= efi-stub-helper.o gop.o secureboot.o tpm.o
+lib-y				:= efi-stub-helper.o gop.o secureboot.o tpm.o \
+				   random.o
 
 # include the stub's generic dependencies from lib/ when building for ARM/arm64
 arm-deps-y := fdt_rw.c fdt_ro.c fdt_wip.c fdt.c fdt_empty_tree.c fdt_sw.c
@@ -47,7 +48,7 @@ arm-deps-$(CONFIG_ARM64) += sort.c
 $(obj)/lib-%.o: $(srctree)/lib/%.c FORCE
 	$(call if_changed_rule,cc_o_c)
 
-lib-$(CONFIG_EFI_ARMSTUB)	+= arm-stub.o fdt.o string.o random.o \
+lib-$(CONFIG_EFI_ARMSTUB)	+= arm-stub.o fdt.o string.o \
 				   $(patsubst %.c,lib-%.o,$(arm-deps-y))
 
 lib-$(CONFIG_ARM)		+= arm32-stub.o
diff --git a/drivers/firmware/efi/libstub/arm-stub.c b/drivers/firmware/efi/libstub/arm-stub.c
index c382a48c6678..817237ce2420 100644
--- a/drivers/firmware/efi/libstub/arm-stub.c
+++ b/drivers/firmware/efi/libstub/arm-stub.c
@@ -189,6 +189,8 @@ unsigned long efi_entry(void *handle, efi_system_table_t *sys_table,
 		goto fail_free_cmdline;
 	}
 
+	efi_retrieve_tpm2_eventlog(sys_table);
+
 	/* Ask the firmware to clear memory on unclean shutdown */
 	efi_enable_reset_attack_mitigation(sys_table);
 
diff --git a/drivers/firmware/efi/libstub/arm32-stub.c b/drivers/firmware/efi/libstub/arm32-stub.c
index 41213bf5fcf5..4566640de650 100644
--- a/drivers/firmware/efi/libstub/arm32-stub.c
+++ b/drivers/firmware/efi/libstub/arm32-stub.c
@@ -146,6 +146,11 @@ static efi_status_t reserve_kernel_base(efi_system_table_t *sys_table_arg,
 			continue;
 
 		case EFI_CONVENTIONAL_MEMORY:
+			/* Skip soft reserved conventional memory */
+			if (efi_soft_reserve_enabled() &&
+			    (desc->attribute & EFI_MEMORY_SP))
+				continue;
+
 			/*
 			 * Reserve the intersection between this entry and the
 			 * region.
diff --git a/drivers/firmware/efi/libstub/efi-stub-helper.c b/drivers/firmware/efi/libstub/efi-stub-helper.c
index 35dbc2791c97..e02579907f2e 100644
--- a/drivers/firmware/efi/libstub/efi-stub-helper.c
+++ b/drivers/firmware/efi/libstub/efi-stub-helper.c
@@ -32,6 +32,7 @@ static unsigned long __chunk_size = EFI_READ_CHUNK_SIZE;
 static int __section(.data) __nokaslr;
 static int __section(.data) __quiet;
 static int __section(.data) __novamap;
+static bool __section(.data) efi_nosoftreserve;
 
 int __pure nokaslr(void)
 {
@@ -45,6 +46,10 @@ int __pure novamap(void)
 {
 	return __novamap;
 }
+bool __pure __efi_soft_reserve_enabled(void)
+{
+	return !efi_nosoftreserve;
+}
 
 #define EFI_MMAP_NR_SLACK_SLOTS	8
 
@@ -211,6 +216,10 @@ again:
 		if (desc->type != EFI_CONVENTIONAL_MEMORY)
 			continue;
 
+		if (efi_soft_reserve_enabled() &&
+		    (desc->attribute & EFI_MEMORY_SP))
+			continue;
+
 		if (desc->num_pages < nr_pages)
 			continue;
 
@@ -305,6 +314,10 @@ efi_status_t efi_low_alloc_above(efi_system_table_t *sys_table_arg,
 		if (desc->type != EFI_CONVENTIONAL_MEMORY)
 			continue;
 
+		if (efi_soft_reserve_enabled() &&
+		    (desc->attribute & EFI_MEMORY_SP))
+			continue;
+
 		if (desc->num_pages < nr_pages)
 			continue;
 
@@ -484,6 +497,12 @@ efi_status_t efi_parse_options(char const *cmdline)
 			__novamap = 1;
 		}
 
+		if (IS_ENABLED(CONFIG_EFI_SOFT_RESERVE) &&
+		    !strncmp(str, "nosoftreserve", 7)) {
+			str += strlen("nosoftreserve");
+			efi_nosoftreserve = 1;
+		}
+
 		/* Group words together, delimited by "," */
 		while (*str && *str != ' ' && *str != ',')
 			str++;
diff --git a/drivers/firmware/efi/libstub/efistub.h b/drivers/firmware/efi/libstub/efistub.h
index 7f1556fd867d..05739ae013c8 100644
--- a/drivers/firmware/efi/libstub/efistub.h
+++ b/drivers/firmware/efi/libstub/efistub.h
@@ -63,8 +63,6 @@ efi_status_t efi_random_alloc(efi_system_table_t *sys_table_arg,
 
 efi_status_t check_platform_features(efi_system_table_t *sys_table_arg);
 
-efi_status_t efi_random_get_seed(efi_system_table_t *sys_table_arg);
-
 void *get_efi_config_table(efi_system_table_t *sys_table, efi_guid_t guid);
 
 /* Helper macros for the usual case of using simple C variables: */
diff --git a/drivers/firmware/efi/libstub/random.c b/drivers/firmware/efi/libstub/random.c
index b4b1d1dcb5fd..35edd7cfb6a1 100644
--- a/drivers/firmware/efi/libstub/random.c
+++ b/drivers/firmware/efi/libstub/random.c
@@ -9,6 +9,18 @@
 
 #include "efistub.h"
 
+typedef struct efi_rng_protocol efi_rng_protocol_t;
+
+typedef struct {
+	u32 get_info;
+	u32 get_rng;
+} efi_rng_protocol_32_t;
+
+typedef struct {
+	u64 get_info;
+	u64 get_rng;
+} efi_rng_protocol_64_t;
+
 struct efi_rng_protocol {
 	efi_status_t (*get_info)(struct efi_rng_protocol *,
 				 unsigned long *, efi_guid_t *);
@@ -28,7 +40,7 @@ efi_status_t efi_get_random_bytes(efi_system_table_t *sys_table_arg,
 	if (status != EFI_SUCCESS)
 		return status;
 
-	return rng->get_rng(rng, NULL, size, out);
+	return efi_call_proto(efi_rng_protocol, get_rng, rng, NULL, size, out);
 }
 
 /*
@@ -46,6 +58,10 @@ static unsigned long get_entry_num_slots(efi_memory_desc_t *md,
 	if (md->type != EFI_CONVENTIONAL_MEMORY)
 		return 0;
 
+	if (efi_soft_reserve_enabled() &&
+	    (md->attribute & EFI_MEMORY_SP))
+		return 0;
+
 	region_end = min((u64)ULONG_MAX, md->phys_addr + md->num_pages*EFI_PAGE_SIZE - 1);
 
 	first_slot = round_up(md->phys_addr, align);
@@ -161,15 +177,16 @@ efi_status_t efi_random_get_seed(efi_system_table_t *sys_table_arg)
 	if (status != EFI_SUCCESS)
 		return status;
 
-	status = rng->get_rng(rng, &rng_algo_raw, EFI_RANDOM_SEED_SIZE,
-			      seed->bits);
+	status = efi_call_proto(efi_rng_protocol, get_rng, rng, &rng_algo_raw,
+				 EFI_RANDOM_SEED_SIZE, seed->bits);
+
 	if (status == EFI_UNSUPPORTED)
 		/*
 		 * Use whatever algorithm we have available if the raw algorithm
 		 * is not implemented.
 		 */
-		status = rng->get_rng(rng, NULL, EFI_RANDOM_SEED_SIZE,
-				      seed->bits);
+		status = efi_call_proto(efi_rng_protocol, get_rng, rng, NULL,
+					 EFI_RANDOM_SEED_SIZE, seed->bits);
 
 	if (status != EFI_SUCCESS)
 		goto err_freepool;
diff --git a/drivers/firmware/efi/x86_fake_mem.c b/drivers/firmware/efi/x86_fake_mem.c
new file mode 100644
index 000000000000..e5d6d5a1b240
--- /dev/null
+++ b/drivers/firmware/efi/x86_fake_mem.c
@@ -0,0 +1,69 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright(c) 2019 Intel Corporation. All rights reserved. */
+#include <linux/efi.h>
+#include <asm/e820/api.h>
+#include "fake_mem.h"
+
+void __init efi_fake_memmap_early(void)
+{
+	int i;
+
+	/*
+	 * The late efi_fake_mem() call can handle all requests if
+	 * EFI_MEMORY_SP support is disabled.
+	 */
+	if (!efi_soft_reserve_enabled())
+		return;
+
+	if (!efi_enabled(EFI_MEMMAP) || !nr_fake_mem)
+		return;
+
+	/*
+	 * Given that efi_fake_memmap() needs to perform memblock
+	 * allocations it needs to run after e820__memblock_setup().
+	 * However, if efi_fake_mem specifies EFI_MEMORY_SP for a given
+	 * address range that potentially needs to mark the memory as
+	 * reserved prior to e820__memblock_setup(). Update e820
+	 * directly if EFI_MEMORY_SP is specified for an
+	 * EFI_CONVENTIONAL_MEMORY descriptor.
+	 */
+	for (i = 0; i < nr_fake_mem; i++) {
+		struct efi_mem_range *mem = &efi_fake_mems[i];
+		efi_memory_desc_t *md;
+		u64 m_start, m_end;
+
+		if ((mem->attribute & EFI_MEMORY_SP) == 0)
+			continue;
+
+		m_start = mem->range.start;
+		m_end = mem->range.end;
+		for_each_efi_memory_desc(md) {
+			u64 start, end;
+
+			if (md->type != EFI_CONVENTIONAL_MEMORY)
+				continue;
+
+			start = md->phys_addr;
+			end = md->phys_addr + (md->num_pages << EFI_PAGE_SHIFT) - 1;
+
+			if (m_start <= end && m_end >= start)
+				/* fake range overlaps descriptor */;
+			else
+				continue;
+
+			/*
+			 * Trim the boundary of the e820 update to the
+			 * descriptor in case the fake range overlaps
+			 * !EFI_CONVENTIONAL_MEMORY
+			 */
+			start = max(start, m_start);
+			end = min(end, m_end);
+
+			if (end <= start)
+				continue;
+			e820__range_update(start, end - start + 1, E820_TYPE_RAM,
+					E820_TYPE_SOFT_RESERVED);
+			e820__update_table(e820_table);
+		}
+	}
+}
diff --git a/drivers/gpu/drm/bridge/synopsys/dw-hdmi-i2s-audio.c b/drivers/gpu/drm/bridge/synopsys/dw-hdmi-i2s-audio.c
index 1d15cf9b6821..6c2c44d0bdee 100644
--- a/drivers/gpu/drm/bridge/synopsys/dw-hdmi-i2s-audio.c
+++ b/drivers/gpu/drm/bridge/synopsys/dw-hdmi-i2s-audio.c
@@ -151,11 +151,22 @@ static int dw_hdmi_i2s_get_dai_id(struct snd_soc_component *component,
 	return -EINVAL;
 }
 
+static int dw_hdmi_i2s_hook_plugged_cb(struct device *dev, void *data,
+				       hdmi_codec_plugged_cb fn,
+				       struct device *codec_dev)
+{
+	struct dw_hdmi_i2s_audio_data *audio = data;
+	struct dw_hdmi *hdmi = audio->hdmi;
+
+	return dw_hdmi_set_plugged_cb(hdmi, fn, codec_dev);
+}
+
 static struct hdmi_codec_ops dw_hdmi_i2s_ops = {
 	.hw_params	= dw_hdmi_i2s_hw_params,
 	.audio_shutdown	= dw_hdmi_i2s_audio_shutdown,
 	.get_eld	= dw_hdmi_i2s_get_eld,
 	.get_dai_id	= dw_hdmi_i2s_get_dai_id,
+	.hook_plugged_cb = dw_hdmi_i2s_hook_plugged_cb,
 };
 
 static int snd_dw_hdmi_probe(struct platform_device *pdev)
diff --git a/drivers/gpu/drm/bridge/synopsys/dw-hdmi.c b/drivers/gpu/drm/bridge/synopsys/dw-hdmi.c
index 521d689413c8..2102872bf43c 100644
--- a/drivers/gpu/drm/bridge/synopsys/dw-hdmi.c
+++ b/drivers/gpu/drm/bridge/synopsys/dw-hdmi.c
@@ -191,6 +191,10 @@ struct dw_hdmi {
 
 	struct mutex cec_notifier_mutex;
 	struct cec_notifier *cec_notifier;
+
+	hdmi_codec_plugged_cb plugged_cb;
+	struct device *codec_dev;
+	enum drm_connector_status last_connector_result;
 };
 
 #define HDMI_IH_PHY_STAT0_RX_SENSE \
@@ -215,6 +219,28 @@ static inline u8 hdmi_readb(struct dw_hdmi *hdmi, int offset)
 	return val;
 }
 
+static void handle_plugged_change(struct dw_hdmi *hdmi, bool plugged)
+{
+	if (hdmi->plugged_cb && hdmi->codec_dev)
+		hdmi->plugged_cb(hdmi->codec_dev, plugged);
+}
+
+int dw_hdmi_set_plugged_cb(struct dw_hdmi *hdmi, hdmi_codec_plugged_cb fn,
+			   struct device *codec_dev)
+{
+	bool plugged;
+
+	mutex_lock(&hdmi->mutex);
+	hdmi->plugged_cb = fn;
+	hdmi->codec_dev = codec_dev;
+	plugged = hdmi->last_connector_result == connector_status_connected;
+	handle_plugged_change(hdmi, plugged);
+	mutex_unlock(&hdmi->mutex);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(dw_hdmi_set_plugged_cb);
+
 static void hdmi_modb(struct dw_hdmi *hdmi, u8 data, u8 mask, unsigned reg)
 {
 	regmap_update_bits(hdmi->regm, reg << hdmi->reg_shift, mask, data);
@@ -2161,6 +2187,7 @@ dw_hdmi_connector_detect(struct drm_connector *connector, bool force)
 {
 	struct dw_hdmi *hdmi = container_of(connector, struct dw_hdmi,
 					     connector);
+	enum drm_connector_status result;
 
 	mutex_lock(&hdmi->mutex);
 	hdmi->force = DRM_FORCE_UNSPECIFIED;
@@ -2168,7 +2195,18 @@ dw_hdmi_connector_detect(struct drm_connector *connector, bool force)
 	dw_hdmi_update_phy_mask(hdmi);
 	mutex_unlock(&hdmi->mutex);
 
-	return hdmi->phy.ops->read_hpd(hdmi, hdmi->phy.data);
+	result = hdmi->phy.ops->read_hpd(hdmi, hdmi->phy.data);
+
+	mutex_lock(&hdmi->mutex);
+	if (result != hdmi->last_connector_result) {
+		dev_dbg(hdmi->dev, "read_hpd result: %d", result);
+		handle_plugged_change(hdmi,
+				      result == connector_status_connected);
+		hdmi->last_connector_result = result;
+	}
+	mutex_unlock(&hdmi->mutex);
+
+	return result;
 }
 
 static int dw_hdmi_connector_get_modes(struct drm_connector *connector)
@@ -2619,6 +2657,7 @@ __dw_hdmi_probe(struct platform_device *pdev,
 	hdmi->rxsense = true;
 	hdmi->phy_mask = (u8)~(HDMI_PHY_HPD | HDMI_PHY_RX_SENSE);
 	hdmi->mc_clkdis = 0x7f;
+	hdmi->last_connector_result = connector_status_disconnected;
 
 	mutex_init(&hdmi->mutex);
 	mutex_init(&hdmi->audio_mutex);
diff --git a/drivers/gpu/drm/drm_connector.c b/drivers/gpu/drm/drm_connector.c
index 4c766624b20d..4a8b2e5c2af6 100644
--- a/drivers/gpu/drm/drm_connector.c
+++ b/drivers/gpu/drm/drm_connector.c
@@ -719,7 +719,7 @@ void drm_connector_list_iter_end(struct drm_connector_list_iter *iter)
 		__drm_connector_put_safe(iter->conn);
 		spin_unlock_irqrestore(&config->connector_list_lock, flags);
 	}
-	lock_release(&connector_list_iter_dep_map, 0, _RET_IP_);
+	lock_release(&connector_list_iter_dep_map, _RET_IP_);
 }
 EXPORT_SYMBOL(drm_connector_list_iter_end);
 
diff --git a/drivers/gpu/drm/i915/Kconfig.debug b/drivers/gpu/drm/i915/Kconfig.debug
index 00786a142ff0..1400fce39c58 100644
--- a/drivers/gpu/drm/i915/Kconfig.debug
+++ b/drivers/gpu/drm/i915/Kconfig.debug
@@ -22,7 +22,6 @@ config DRM_I915_DEBUG
         depends on DRM_I915
         select DEBUG_FS
         select PREEMPT_COUNT
-        select REFCOUNT_FULL
         select I2C_CHARDEV
         select STACKDEPOT
         select DRM_DP_AUX_CHARDEV
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_context.c b/drivers/gpu/drm/i915/gem/i915_gem_context.c
index e41fd94ae5a9..755c4542629f 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_context.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_context.c
@@ -1634,7 +1634,7 @@ replace:
 		i915_gem_context_set_user_engines(ctx);
 	else
 		i915_gem_context_clear_user_engines(ctx);
-	rcu_swap_protected(ctx->engines, set.engines, 1);
+	set.engines = rcu_replace_pointer(ctx->engines, set.engines, 1);
 	mutex_unlock(&ctx->engines_mutex);
 
 	call_rcu(&set.engines->rcu, free_engines_rcu);
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_shrinker.c b/drivers/gpu/drm/i915/gem/i915_gem_shrinker.c
index edd21d14e64f..1a51b3598d63 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_shrinker.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_shrinker.c
@@ -509,14 +509,14 @@ void i915_gem_shrinker_taints_mutex(struct drm_i915_private *i915,
 		      I915_MM_SHRINKER, 0, _RET_IP_);
 
 	mutex_acquire(&mutex->dep_map, 0, 0, _RET_IP_);
-	mutex_release(&mutex->dep_map, 0, _RET_IP_);
+	mutex_release(&mutex->dep_map, _RET_IP_);
 
-	mutex_release(&i915->drm.struct_mutex.dep_map, 0, _RET_IP_);
+	mutex_release(&i915->drm.struct_mutex.dep_map, _RET_IP_);
 
 	fs_reclaim_release(GFP_KERNEL);
 
 	if (unlock)
-		mutex_release(&i915->drm.struct_mutex.dep_map, 0, _RET_IP_);
+		mutex_release(&i915->drm.struct_mutex.dep_map, _RET_IP_);
 }
 
 #define obj_to_i915(obj__) to_i915((obj__)->base.dev)
diff --git a/drivers/gpu/drm/i915/gt/intel_engine_pm.c b/drivers/gpu/drm/i915/gt/intel_engine_pm.c
index 65b5ca74b394..7f647243b3b9 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine_pm.c
+++ b/drivers/gpu/drm/i915/gt/intel_engine_pm.c
@@ -52,7 +52,7 @@ static inline unsigned long __timeline_mark_lock(struct intel_context *ce)
 static inline void __timeline_mark_unlock(struct intel_context *ce,
 					  unsigned long flags)
 {
-	mutex_release(&ce->timeline->mutex.dep_map, 0, _THIS_IP_);
+	mutex_release(&ce->timeline->mutex.dep_map, _THIS_IP_);
 	local_irq_restore(flags);
 }
 
diff --git a/drivers/gpu/drm/i915/i915_request.c b/drivers/gpu/drm/i915/i915_request.c
index 1c5506822dc7..bc828a9ace84 100644
--- a/drivers/gpu/drm/i915/i915_request.c
+++ b/drivers/gpu/drm/i915/i915_request.c
@@ -1495,7 +1495,7 @@ long i915_request_wait(struct i915_request *rq,
 	dma_fence_remove_callback(&rq->fence, &wait.cb);
 
 out:
-	mutex_release(&rq->engine->gt->reset.mutex.dep_map, 0, _THIS_IP_);
+	mutex_release(&rq->engine->gt->reset.mutex.dep_map, _THIS_IP_);
 	trace_i915_request_wait_end(rq);
 	return timeout;
 }
diff --git a/drivers/hv/hv.c b/drivers/hv/hv.c
index fcc52797c169..6098e0cbdb4b 100644
--- a/drivers/hv/hv.c
+++ b/drivers/hv/hv.c
@@ -202,7 +202,7 @@ int hv_synic_init(unsigned int cpu)
 {
 	hv_synic_enable_regs(cpu);
 
-	hv_stimer_init(cpu);
+	hv_stimer_legacy_init(cpu, VMBUS_MESSAGE_SINT);
 
 	return 0;
 }
@@ -277,7 +277,7 @@ int hv_synic_cleanup(unsigned int cpu)
 	if (channel_found && vmbus_connection.conn_state == CONNECTED)
 		return -EBUSY;
 
-	hv_stimer_cleanup(cpu);
+	hv_stimer_legacy_cleanup(cpu);
 
 	hv_synic_disable_regs(cpu);
 
diff --git a/drivers/hv/vmbus_drv.c b/drivers/hv/vmbus_drv.c
index 53a60c81e220..8c06b3361c27 100644
--- a/drivers/hv/vmbus_drv.c
+++ b/drivers/hv/vmbus_drv.c
@@ -1340,10 +1340,6 @@ static int vmbus_bus_init(void)
 	if (ret)
 		goto err_alloc;
 
-	ret = hv_stimer_alloc(VMBUS_MESSAGE_SINT);
-	if (ret < 0)
-		goto err_alloc;
-
 	/*
 	 * Initialize the per-cpu interrupt state and stimer state.
 	 * Then connect to the host.
@@ -1400,9 +1396,8 @@ static int vmbus_bus_init(void)
 err_connect:
 	cpuhp_remove_state(hyperv_cpuhp_online);
 err_cpuhp:
-	hv_stimer_free();
-err_alloc:
 	hv_synic_free();
+err_alloc:
 	hv_remove_vmbus_irq();
 
 	bus_unregister(&hv_bus);
@@ -2315,20 +2310,23 @@ static void hv_crash_handler(struct pt_regs *regs)
 static int hv_synic_suspend(void)
 {
 	/*
-	 * When we reach here, all the non-boot CPUs have been offlined, and
-	 * the stimers on them have been unbound in hv_synic_cleanup() ->
+	 * When we reach here, all the non-boot CPUs have been offlined.
+	 * If we're in a legacy configuration where stimer Direct Mode is
+	 * not enabled, the stimers on the non-boot CPUs have been unbound
+	 * in hv_synic_cleanup() -> hv_stimer_legacy_cleanup() ->
 	 * hv_stimer_cleanup() -> clockevents_unbind_device().
 	 *
-	 * hv_synic_suspend() only runs on CPU0 with interrupts disabled. Here
-	 * we do not unbind the stimer on CPU0 because: 1) it's unnecessary
-	 * because the interrupts remain disabled between syscore_suspend()
-	 * and syscore_resume(): see create_image() and resume_target_kernel();
+	 * hv_synic_suspend() only runs on CPU0 with interrupts disabled.
+	 * Here we do not call hv_stimer_legacy_cleanup() on CPU0 because:
+	 * 1) it's unnecessary as interrupts remain disabled between
+	 * syscore_suspend() and syscore_resume(): see create_image() and
+	 * resume_target_kernel()
 	 * 2) the stimer on CPU0 is automatically disabled later by
 	 * syscore_suspend() -> timekeeping_suspend() -> tick_suspend() -> ...
-	 * -> clockevents_shutdown() -> ... -> hv_ce_shutdown(); 3) a warning
-	 * would be triggered if we call clockevents_unbind_device(), which
-	 * may sleep, in an interrupts-disabled context. So, we intentionally
-	 * don't call hv_stimer_cleanup(0) here.
+	 * -> clockevents_shutdown() -> ... -> hv_ce_shutdown()
+	 * 3) a warning would be triggered if we call
+	 * clockevents_unbind_device(), which may sleep, in an
+	 * interrupts-disabled context.
 	 */
 
 	hv_synic_disable_regs(0);
diff --git a/drivers/iommu/amd_iommu.c b/drivers/iommu/amd_iommu.c
index dd555078258c..12e5039a7a25 100644
--- a/drivers/iommu/amd_iommu.c
+++ b/drivers/iommu/amd_iommu.c
@@ -124,30 +124,6 @@ static struct lock_class_key reserved_rbtree_key;
  *
  ****************************************************************************/
 
-static inline int match_hid_uid(struct device *dev,
-				struct acpihid_map_entry *entry)
-{
-	struct acpi_device *adev = ACPI_COMPANION(dev);
-	const char *hid, *uid;
-
-	if (!adev)
-		return -ENODEV;
-
-	hid = acpi_device_hid(adev);
-	uid = acpi_device_uid(adev);
-
-	if (!hid || !(*hid))
-		return -ENODEV;
-
-	if (!uid || !(*uid))
-		return strcmp(hid, entry->hid);
-
-	if (!(*entry->uid))
-		return strcmp(hid, entry->hid);
-
-	return (strcmp(hid, entry->hid) || strcmp(uid, entry->uid));
-}
-
 static inline u16 get_pci_device_id(struct device *dev)
 {
 	struct pci_dev *pdev = to_pci_dev(dev);
@@ -158,10 +134,14 @@ static inline u16 get_pci_device_id(struct device *dev)
 static inline int get_acpihid_device_id(struct device *dev,
 					struct acpihid_map_entry **entry)
 {
+	struct acpi_device *adev = ACPI_COMPANION(dev);
 	struct acpihid_map_entry *p;
 
+	if (!adev)
+		return -ENODEV;
+
 	list_for_each_entry(p, &acpihid_map, list) {
-		if (!match_hid_uid(dev, p)) {
+		if (acpi_dev_hid_uid_match(adev, p->hid, p->uid)) {
 			if (entry)
 				*entry = p;
 			return p->devid;
diff --git a/drivers/leds/trigger/ledtrig-activity.c b/drivers/leds/trigger/ledtrig-activity.c
index 6a72b7e13719..14ba7faaed9e 100644
--- a/drivers/leds/trigger/ledtrig-activity.c
+++ b/drivers/leds/trigger/ledtrig-activity.c
@@ -57,11 +57,15 @@ static void led_activity_function(struct timer_list *t)
 	curr_used = 0;
 
 	for_each_possible_cpu(i) {
-		curr_used += kcpustat_cpu(i).cpustat[CPUTIME_USER]
-			  +  kcpustat_cpu(i).cpustat[CPUTIME_NICE]
-			  +  kcpustat_cpu(i).cpustat[CPUTIME_SYSTEM]
-			  +  kcpustat_cpu(i).cpustat[CPUTIME_SOFTIRQ]
-			  +  kcpustat_cpu(i).cpustat[CPUTIME_IRQ];
+		struct kernel_cpustat kcpustat;
+
+		kcpustat_cpu_fetch(&kcpustat, i);
+
+		curr_used += kcpustat.cpustat[CPUTIME_USER]
+			  +  kcpustat.cpustat[CPUTIME_NICE]
+			  +  kcpustat.cpustat[CPUTIME_SYSTEM]
+			  +  kcpustat.cpustat[CPUTIME_SOFTIRQ]
+			  +  kcpustat.cpustat[CPUTIME_IRQ];
 		cpus++;
 	}
 
diff --git a/drivers/macintosh/rack-meter.c b/drivers/macintosh/rack-meter.c
index 4134e580f786..60311e8d6240 100644
--- a/drivers/macintosh/rack-meter.c
+++ b/drivers/macintosh/rack-meter.c
@@ -81,13 +81,14 @@ static int rackmeter_ignore_nice;
  */
 static inline u64 get_cpu_idle_time(unsigned int cpu)
 {
+	struct kernel_cpustat *kcpustat = &kcpustat_cpu(cpu);
 	u64 retval;
 
-	retval = kcpustat_cpu(cpu).cpustat[CPUTIME_IDLE] +
-		 kcpustat_cpu(cpu).cpustat[CPUTIME_IOWAIT];
+	retval = kcpustat->cpustat[CPUTIME_IDLE] +
+		 kcpustat->cpustat[CPUTIME_IOWAIT];
 
 	if (rackmeter_ignore_nice)
-		retval += kcpustat_cpu(cpu).cpustat[CPUTIME_NICE];
+		retval += kcpustat_field(kcpustat, CPUTIME_NICE, cpu);
 
 	return retval;
 }
diff --git a/drivers/media/cec/cec-adap.c b/drivers/media/cec/cec-adap.c
index 5ef7daeb8cbd..9340435a94a0 100644
--- a/drivers/media/cec/cec-adap.c
+++ b/drivers/media/cec/cec-adap.c
@@ -319,6 +319,8 @@ static void cec_post_state_event(struct cec_adapter *adap)
 
 	ev.state_change.phys_addr = adap->phys_addr;
 	ev.state_change.log_addr_mask = adap->log_addrs.log_addr_mask;
+	ev.state_change.have_conn_info =
+		adap->conn_info.type != CEC_CONNECTOR_TYPE_NO_CONNECTOR;
 	cec_queue_event(adap, &ev);
 }
 
@@ -1976,7 +1978,7 @@ static int cec_receive_notify(struct cec_adapter *adap, struct cec_msg *msg,
 		 * Play function, this message can have variable length
 		 * depending on the specific play function that is used.
 		 */
-		case 0x60:
+		case CEC_OP_UI_CMD_PLAY_FUNCTION:
 			if (msg->len == 2)
 				rc_keydown(adap->rc, RC_PROTO_CEC,
 					   msg->msg[2], 0);
@@ -1993,8 +1995,12 @@ static int cec_receive_notify(struct cec_adapter *adap, struct cec_msg *msg,
 		 * For the time being these messages are not processed by the
 		 * framework and are simply forwarded to the user space.
 		 */
-		case 0x56: case 0x57:
-		case 0x67: case 0x68: case 0x69: case 0x6a:
+		case CEC_OP_UI_CMD_SELECT_BROADCAST_TYPE:
+		case CEC_OP_UI_CMD_SELECT_SOUND_PRESENTATION:
+		case CEC_OP_UI_CMD_TUNE_FUNCTION:
+		case CEC_OP_UI_CMD_SELECT_MEDIA_FUNCTION:
+		case CEC_OP_UI_CMD_SELECT_AV_INPUT_FUNCTION:
+		case CEC_OP_UI_CMD_SELECT_AUDIO_INPUT_FUNCTION:
 			break;
 		default:
 			rc_keydown(adap->rc, RC_PROTO_CEC, msg->msg[2], 0);
diff --git a/drivers/media/cec/cec-api.c b/drivers/media/cec/cec-api.c
index 12d676484472..17d1cb2e5f97 100644
--- a/drivers/media/cec/cec-api.c
+++ b/drivers/media/cec/cec-api.c
@@ -187,6 +187,21 @@ static long cec_adap_s_log_addrs(struct cec_adapter *adap, struct cec_fh *fh,
 	return 0;
 }
 
+static long cec_adap_g_connector_info(struct cec_adapter *adap,
+				      struct cec_log_addrs __user *parg)
+{
+	int ret = 0;
+
+	if (!(adap->capabilities & CEC_CAP_CONNECTOR_INFO))
+		return -ENOTTY;
+
+	mutex_lock(&adap->lock);
+	if (copy_to_user(parg, &adap->conn_info, sizeof(adap->conn_info)))
+		ret = -EFAULT;
+	mutex_unlock(&adap->lock);
+	return ret;
+}
+
 static long cec_transmit(struct cec_adapter *adap, struct cec_fh *fh,
 			 bool block, struct cec_msg __user *parg)
 {
@@ -506,6 +521,9 @@ static long cec_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
 	case CEC_ADAP_S_LOG_ADDRS:
 		return cec_adap_s_log_addrs(adap, fh, block, parg);
 
+	case CEC_ADAP_G_CONNECTOR_INFO:
+		return cec_adap_g_connector_info(adap, parg);
+
 	case CEC_TRANSMIT:
 		return cec_transmit(adap, fh, block, parg);
 
@@ -578,6 +596,8 @@ static int cec_open(struct inode *inode, struct file *filp)
 	/* Queue up initial state events */
 	ev.state_change.phys_addr = adap->phys_addr;
 	ev.state_change.log_addr_mask = adap->log_addrs.log_addr_mask;
+	ev.state_change.have_conn_info =
+		adap->conn_info.type != CEC_CONNECTOR_TYPE_NO_CONNECTOR;
 	cec_queue_event_fh(fh, &ev, 0);
 #ifdef CONFIG_CEC_PIN
 	if (adap->pin && adap->pin->ops->read_hpd) {
diff --git a/drivers/media/cec/cec-core.c b/drivers/media/cec/cec-core.c
index 9c610e1e99b8..db7adffcdc76 100644
--- a/drivers/media/cec/cec-core.c
+++ b/drivers/media/cec/cec-core.c
@@ -257,11 +257,6 @@ struct cec_adapter *cec_allocate_adapter(const struct cec_adap_ops *ops,
 	struct cec_adapter *adap;
 	int res;
 
-	/*
-	 * Disable this capability until the connector info public API
-	 * is ready.
-	 */
-	caps &= ~CEC_CAP_CONNECTOR_INFO;
 #ifndef CONFIG_MEDIA_CEC_RC
 	caps &= ~CEC_CAP_RC;
 #endif
diff --git a/drivers/media/cec/cec-pin.c b/drivers/media/cec/cec-pin.c
index 8f987bc0dd88..660fe111f540 100644
--- a/drivers/media/cec/cec-pin.c
+++ b/drivers/media/cec/cec-pin.c
@@ -1279,6 +1279,15 @@ static void cec_pin_adap_free(struct cec_adapter *adap)
 	kfree(pin);
 }
 
+static int cec_pin_received(struct cec_adapter *adap, struct cec_msg *msg)
+{
+	struct cec_pin *pin = adap->pin;
+
+	if (pin->ops->received)
+		return pin->ops->received(adap, msg);
+	return -ENOMSG;
+}
+
 void cec_pin_changed(struct cec_adapter *adap, bool value)
 {
 	struct cec_pin *pin = adap->pin;
@@ -1301,6 +1310,7 @@ static const struct cec_adap_ops cec_pin_adap_ops = {
 	.error_inj_parse_line = cec_pin_error_inj_parse_line,
 	.error_inj_show = cec_pin_error_inj_show,
 #endif
+	.received = cec_pin_received,
 };
 
 struct cec_adapter *cec_pin_allocate_adapter(const struct cec_pin_ops *pin_ops,
diff --git a/drivers/media/common/siano/smscoreapi.c b/drivers/media/common/siano/smscoreapi.c
index 0ba51dacc580..c1511094fdc7 100644
--- a/drivers/media/common/siano/smscoreapi.c
+++ b/drivers/media/common/siano/smscoreapi.c
@@ -230,8 +230,8 @@ static char *siano_msgs[] = {
 	[MSG_SMS_FLASH_DL_REQ                        - MSG_TYPE_BASE_VAL] = "MSG_SMS_FLASH_DL_REQ",
 	[MSG_SMS_EXEC_TEST_1_REQ                     - MSG_TYPE_BASE_VAL] = "MSG_SMS_EXEC_TEST_1_REQ",
 	[MSG_SMS_EXEC_TEST_1_RES                     - MSG_TYPE_BASE_VAL] = "MSG_SMS_EXEC_TEST_1_RES",
-	[MSG_SMS_ENBALE_TS_INTERFACE_REQ             - MSG_TYPE_BASE_VAL] = "MSG_SMS_ENBALE_TS_INTERFACE_REQ",
-	[MSG_SMS_ENBALE_TS_INTERFACE_RES             - MSG_TYPE_BASE_VAL] = "MSG_SMS_ENBALE_TS_INTERFACE_RES",
+	[MSG_SMS_ENABLE_TS_INTERFACE_REQ             - MSG_TYPE_BASE_VAL] = "MSG_SMS_ENABLE_TS_INTERFACE_REQ",
+	[MSG_SMS_ENABLE_TS_INTERFACE_RES             - MSG_TYPE_BASE_VAL] = "MSG_SMS_ENABLE_TS_INTERFACE_RES",
 	[MSG_SMS_SPI_SET_BUS_WIDTH_REQ               - MSG_TYPE_BASE_VAL] = "MSG_SMS_SPI_SET_BUS_WIDTH_REQ",
 	[MSG_SMS_SPI_SET_BUS_WIDTH_RES               - MSG_TYPE_BASE_VAL] = "MSG_SMS_SPI_SET_BUS_WIDTH_RES",
 	[MSG_SMS_SEND_EMM_REQ                        - MSG_TYPE_BASE_VAL] = "MSG_SMS_SEND_EMM_REQ",
diff --git a/drivers/media/common/siano/smscoreapi.h b/drivers/media/common/siano/smscoreapi.h
index a2f95f4899c2..b3b793b5caf3 100644
--- a/drivers/media/common/siano/smscoreapi.h
+++ b/drivers/media/common/siano/smscoreapi.h
@@ -434,8 +434,8 @@ enum msg_types {
 	MSG_SMS_FLASH_DL_REQ = 732,
 	MSG_SMS_EXEC_TEST_1_REQ = 734,
 	MSG_SMS_EXEC_TEST_1_RES = 735,
-	MSG_SMS_ENBALE_TS_INTERFACE_REQ = 736,
-	MSG_SMS_ENBALE_TS_INTERFACE_RES = 737,
+	MSG_SMS_ENABLE_TS_INTERFACE_REQ = 736,
+	MSG_SMS_ENABLE_TS_INTERFACE_RES = 737,
 	MSG_SMS_SPI_SET_BUS_WIDTH_REQ = 738,
 	MSG_SMS_SPI_SET_BUS_WIDTH_RES = 739,
 	MSG_SMS_SEND_EMM_REQ = 740,
diff --git a/drivers/media/common/siano/smsir.h b/drivers/media/common/siano/smsir.h
index b2c54c256e86..ada41d5c4e83 100644
--- a/drivers/media/common/siano/smsir.h
+++ b/drivers/media/common/siano/smsir.h
@@ -1,5 +1,5 @@
+/* SPDX-License-Identifier: GPL-2.0+ */
 /*
- * SPDX-License-Identifier: GPL-2.0+
  *
  * Siano Mobile Silicon, Inc.
  * MDTV receiver kernel modules.
diff --git a/drivers/media/common/videobuf2/videobuf2-v4l2.c b/drivers/media/common/videobuf2/videobuf2-v4l2.c
index 5a9ba3846f0a..e652f4318284 100644
--- a/drivers/media/common/videobuf2/videobuf2-v4l2.c
+++ b/drivers/media/common/videobuf2/videobuf2-v4l2.c
@@ -49,8 +49,11 @@ module_param(debug, int, 0644);
 				 V4L2_BUF_FLAG_REQUEST_FD | \
 				 V4L2_BUF_FLAG_TIMESTAMP_MASK)
 /* Output buffer flags that should be passed on to the driver */
-#define V4L2_BUFFER_OUT_FLAGS	(V4L2_BUF_FLAG_PFRAME | V4L2_BUF_FLAG_BFRAME | \
-				 V4L2_BUF_FLAG_KEYFRAME | V4L2_BUF_FLAG_TIMECODE)
+#define V4L2_BUFFER_OUT_FLAGS	(V4L2_BUF_FLAG_PFRAME | \
+				 V4L2_BUF_FLAG_BFRAME | \
+				 V4L2_BUF_FLAG_KEYFRAME | \
+				 V4L2_BUF_FLAG_TIMECODE | \
+				 V4L2_BUF_FLAG_M2M_HOLD_CAPTURE_BUF)
 
 /*
  * __verify_planes_array() - verify that the planes array passed in struct
@@ -194,6 +197,7 @@ static int vb2_fill_vb2_v4l2_buffer(struct vb2_buffer *vb, struct v4l2_buffer *b
 	}
 	vbuf->sequence = 0;
 	vbuf->request_fd = -1;
+	vbuf->is_held = false;
 
 	if (V4L2_TYPE_IS_MULTIPLANAR(b->type)) {
 		switch (b->memory) {
@@ -321,6 +325,8 @@ static int vb2_fill_vb2_v4l2_buffer(struct vb2_buffer *vb, struct v4l2_buffer *b
 		 */
 		vbuf->flags &= ~V4L2_BUF_FLAG_TIMECODE;
 		vbuf->field = b->field;
+		if (!(q->subsystem_flags & VB2_V4L2_FL_SUPPORTS_M2M_HOLD_CAPTURE_BUF))
+			vbuf->flags &= ~V4L2_BUF_FLAG_M2M_HOLD_CAPTURE_BUF;
 	} else {
 		/* Zero any output buffer flags as this is a capture buffer */
 		vbuf->flags &= ~V4L2_BUFFER_OUT_FLAGS;
@@ -654,6 +660,8 @@ static void fill_buf_caps(struct vb2_queue *q, u32 *caps)
 		*caps |= V4L2_BUF_CAP_SUPPORTS_USERPTR;
 	if (q->io_modes & VB2_DMABUF)
 		*caps |= V4L2_BUF_CAP_SUPPORTS_DMABUF;
+	if (q->subsystem_flags & VB2_V4L2_FL_SUPPORTS_M2M_HOLD_CAPTURE_BUF)
+		*caps |= V4L2_BUF_CAP_SUPPORTS_M2M_HOLD_CAPTURE_BUF;
 #ifdef CONFIG_MEDIA_CONTROLLER_REQUEST_API
 	if (q->supports_requests)
 		*caps |= V4L2_BUF_CAP_SUPPORTS_REQUESTS;
diff --git a/drivers/media/dvb-frontends/cxd2820r_c.c b/drivers/media/dvb-frontends/cxd2820r_c.c
index 6f7eedb4c00e..0ba382948c51 100644
--- a/drivers/media/dvb-frontends/cxd2820r_c.c
+++ b/drivers/media/dvb-frontends/cxd2820r_c.c
@@ -298,7 +298,7 @@ int cxd2820r_sleep_c(struct dvb_frontend *fe)
 	struct cxd2820r_priv *priv = fe->demodulator_priv;
 	struct i2c_client *client = priv->client[0];
 	int ret;
-	struct reg_val_mask tab[] = {
+	static const struct reg_val_mask tab[] = {
 		{ 0x000ff, 0x1f, 0xff },
 		{ 0x00085, 0x00, 0xff },
 		{ 0x00088, 0x01, 0xff },
diff --git a/drivers/media/dvb-frontends/cxd2820r_t.c b/drivers/media/dvb-frontends/cxd2820r_t.c
index d56c6f788196..fbdfa6bf38dc 100644
--- a/drivers/media/dvb-frontends/cxd2820r_t.c
+++ b/drivers/media/dvb-frontends/cxd2820r_t.c
@@ -392,7 +392,7 @@ int cxd2820r_sleep_t(struct dvb_frontend *fe)
 	struct cxd2820r_priv *priv = fe->demodulator_priv;
 	struct i2c_client *client = priv->client[0];
 	int ret;
-	struct reg_val_mask tab[] = {
+	static struct reg_val_mask tab[] = {
 		{ 0x000ff, 0x1f, 0xff },
 		{ 0x00085, 0x00, 0xff },
 		{ 0x00088, 0x01, 0xff },
diff --git a/drivers/media/dvb-frontends/cxd2820r_t2.c b/drivers/media/dvb-frontends/cxd2820r_t2.c
index f924a80b968a..34ef2bb2de34 100644
--- a/drivers/media/dvb-frontends/cxd2820r_t2.c
+++ b/drivers/media/dvb-frontends/cxd2820r_t2.c
@@ -386,7 +386,7 @@ int cxd2820r_sleep_t2(struct dvb_frontend *fe)
 	struct cxd2820r_priv *priv = fe->demodulator_priv;
 	struct i2c_client *client = priv->client[0];
 	int ret;
-	struct reg_val_mask tab[] = {
+	static const struct reg_val_mask tab[] = {
 		{ 0x000ff, 0x1f, 0xff },
 		{ 0x00085, 0x00, 0xff },
 		{ 0x00088, 0x01, 0xff },
diff --git a/drivers/media/dvb-frontends/cxd2841er.c b/drivers/media/dvb-frontends/cxd2841er.c
index 1b30cf570803..758c95bc3b11 100644
--- a/drivers/media/dvb-frontends/cxd2841er.c
+++ b/drivers/media/dvb-frontends/cxd2841er.c
@@ -60,6 +60,7 @@ struct cxd2841er_priv {
 	enum cxd2841er_xtal		xtal;
 	enum fe_caps caps;
 	u32				flags;
+	unsigned long			stats_time;
 };
 
 static const struct cxd2841er_cnr_data s_cn_data[] = {
@@ -3279,9 +3280,15 @@ static int cxd2841er_get_frontend(struct dvb_frontend *fe,
 		p->strength.stat[0].scale = FE_SCALE_NOT_AVAILABLE;
 
 	if (status & FE_HAS_LOCK) {
+		if (priv->stats_time &&
+		    (!time_after(jiffies, priv->stats_time)))
+			return 0;
+
+		/* Prevent retrieving stats faster than once per second */
+		priv->stats_time = jiffies + msecs_to_jiffies(1000);
+
 		cxd2841er_read_snr(fe);
 		cxd2841er_read_ucblocks(fe);
-
 		cxd2841er_read_ber(fe);
 	} else {
 		p->cnr.stat[0].scale = FE_SCALE_NOT_AVAILABLE;
@@ -3360,6 +3367,9 @@ done:
 	p->post_bit_error.stat[0].scale = FE_SCALE_NOT_AVAILABLE;
 	p->post_bit_count.stat[0].scale = FE_SCALE_NOT_AVAILABLE;
 
+	/* Reset the wait for jiffies logic */
+	priv->stats_time = 0;
+
 	return ret;
 }
 
diff --git a/drivers/media/dvb-frontends/drx39xyj/drxj.c b/drivers/media/dvb-frontends/drx39xyj/drxj.c
index 2f5af4813a74..ac7be872f460 100644
--- a/drivers/media/dvb-frontends/drx39xyj/drxj.c
+++ b/drivers/media/dvb-frontends/drx39xyj/drxj.c
@@ -4201,7 +4201,7 @@ int drxj_dap_scu_atomic_read_reg16(struct i2c_device_addr *dev_addr,
 					 u16 *data, u32 flags)
 {
 	u8 buf[2] = { 0 };
-	int rc = -EIO;
+	int rc;
 	u16 word = 0;
 
 	if (!data)
diff --git a/drivers/media/dvb-frontends/mb86a20s.c b/drivers/media/dvb-frontends/mb86a20s.c
index 4e50441c247a..a7faf0cf8788 100644
--- a/drivers/media/dvb-frontends/mb86a20s.c
+++ b/drivers/media/dvb-frontends/mb86a20s.c
@@ -517,7 +517,7 @@ static void mb86a20s_reset_frontend_cache(struct dvb_frontend *fe)
  * Estimates the bit rate using the per-segment bit rate given by
  * ABNT/NBR 15601 spec (table 4).
  */
-static u32 isdbt_rate[3][5][4] = {
+static const u32 isdbt_rate[3][5][4] = {
 	{	/* DQPSK/QPSK */
 		{  280850,  312060,  330420,  340430 },	/* 1/2 */
 		{  374470,  416080,  440560,  453910 },	/* 2/3 */
@@ -539,13 +539,9 @@ static u32 isdbt_rate[3][5][4] = {
 	}
 };
 
-static void mb86a20s_layer_bitrate(struct dvb_frontend *fe, u32 layer,
-				   u32 modulation, u32 forward_error_correction,
-				   u32 guard_interval,
-				   u32 segment)
+static u32 isdbt_layer_min_bitrate(struct dtv_frontend_properties *c,
+				   u32 layer)
 {
-	struct mb86a20s_state *state = fe->demodulator_priv;
-	u32 rate;
 	int mod, fec, guard;
 
 	/*
@@ -553,7 +549,7 @@ static void mb86a20s_layer_bitrate(struct dvb_frontend *fe, u32 layer,
 	 * to consider the lowest bit rate, to avoid taking too long time
 	 * to get BER.
 	 */
-	switch (modulation) {
+	switch (c->layer[layer].modulation) {
 	case DQPSK:
 	case QPSK:
 	default:
@@ -567,7 +563,7 @@ static void mb86a20s_layer_bitrate(struct dvb_frontend *fe, u32 layer,
 		break;
 	}
 
-	switch (forward_error_correction) {
+	switch (c->layer[layer].fec) {
 	default:
 	case FEC_1_2:
 	case FEC_AUTO:
@@ -587,7 +583,7 @@ static void mb86a20s_layer_bitrate(struct dvb_frontend *fe, u32 layer,
 		break;
 	}
 
-	switch (guard_interval) {
+	switch (c->guard_interval) {
 	default:
 	case GUARD_INTERVAL_1_4:
 		guard = 0;
@@ -603,29 +599,14 @@ static void mb86a20s_layer_bitrate(struct dvb_frontend *fe, u32 layer,
 		break;
 	}
 
-	/* Samples BER at BER_SAMPLING_RATE seconds */
-	rate = isdbt_rate[mod][fec][guard] * segment * BER_SAMPLING_RATE;
-
-	/* Avoids sampling too quickly or to overflow the register */
-	if (rate < 256)
-		rate = 256;
-	else if (rate > (1 << 24) - 1)
-		rate = (1 << 24) - 1;
-
-	dev_dbg(&state->i2c->dev,
-		"%s: layer %c bitrate: %d kbps; counter = %d (0x%06x)\n",
-		__func__, 'A' + layer,
-		segment * isdbt_rate[mod][fec][guard]/1000,
-		rate, rate);
-
-	state->estimated_rate[layer] = rate;
+	return isdbt_rate[mod][fec][guard] * c->layer[layer].segment_count;
 }
 
 static int mb86a20s_get_frontend(struct dvb_frontend *fe)
 {
 	struct mb86a20s_state *state = fe->demodulator_priv;
 	struct dtv_frontend_properties *c = &fe->dtv_property_cache;
-	int layer, rc;
+	int layer, rc, rate, counter;
 
 	dev_dbg(&state->i2c->dev, "%s called.\n", __func__);
 
@@ -676,10 +657,21 @@ static int mb86a20s_get_frontend(struct dvb_frontend *fe)
 		dev_dbg(&state->i2c->dev, "%s: interleaving %d.\n",
 			__func__, rc);
 		c->layer[layer].interleaving = rc;
-		mb86a20s_layer_bitrate(fe, layer, c->layer[layer].modulation,
-				       c->layer[layer].fec,
-				       c->guard_interval,
-				       c->layer[layer].segment_count);
+
+		rate = isdbt_layer_min_bitrate(c, layer);
+		counter = rate * BER_SAMPLING_RATE;
+
+		/* Avoids sampling too quickly or to overflow the register */
+		if (counter < 256)
+			counter = 256;
+		else if (counter > (1 << 24) - 1)
+			counter = (1 << 24) - 1;
+
+		dev_dbg(&state->i2c->dev,
+			"%s: layer %c bitrate: %d kbps; counter = %d (0x%06x)\n",
+			__func__, 'A' + layer, rate / 1000, counter, counter);
+
+		state->estimated_rate[layer] = counter;
 	}
 
 	rc = mb86a20s_writereg(state, 0x6d, 0x84);
diff --git a/drivers/media/dvb-frontends/mt312.c b/drivers/media/dvb-frontends/mt312.c
index 7cae7d632030..d43a67045dbe 100644
--- a/drivers/media/dvb-frontends/mt312.c
+++ b/drivers/media/dvb-frontends/mt312.c
@@ -135,11 +135,6 @@ static inline int mt312_writereg(struct mt312_state *state,
 	return mt312_write(state, reg, &tmp, 1);
 }
 
-static inline u32 mt312_div(u32 a, u32 b)
-{
-	return (a + (b / 2)) / b;
-}
-
 static int mt312_reset(struct mt312_state *state, const u8 full)
 {
 	return mt312_writereg(state, RESET, full ? 0x80 : 0x40);
@@ -187,7 +182,7 @@ static int mt312_get_symbol_rate(struct mt312_state *state, u32 *sr)
 		monitor = (buf[0] << 8) | buf[1];
 
 		dprintk("sr(auto) = %u\n",
-		       mt312_div(monitor * 15625, 4));
+			DIV_ROUND_CLOSEST(monitor * 15625, 4));
 	} else {
 		ret = mt312_writereg(state, MON_CTRL, 0x05);
 		if (ret < 0)
@@ -291,10 +286,10 @@ static int mt312_initfe(struct dvb_frontend *fe)
 	}
 
 	/* SYS_CLK */
-	buf[0] = mt312_div(state->xtal * state->freq_mult * 2, 1000000);
+	buf[0] = DIV_ROUND_CLOSEST(state->xtal * state->freq_mult * 2, 1000000);
 
 	/* DISEQC_RATIO */
-	buf[1] = mt312_div(state->xtal, 22000 * 4);
+	buf[1] = DIV_ROUND_CLOSEST(state->xtal, 22000 * 4);
 
 	ret = mt312_write(state, SYS_CLK, buf, sizeof(buf));
 	if (ret < 0)
@@ -610,7 +605,7 @@ static int mt312_set_frontend(struct dvb_frontend *fe)
 	}
 
 	/* sr = (u16)(sr * 256.0 / 1000000.0) */
-	sr = mt312_div(p->symbol_rate * 4, 15625);
+	sr = DIV_ROUND_CLOSEST(p->symbol_rate * 4, 15625);
 
 	/* SYM_RATE */
 	buf[0] = (sr >> 8) & 0x3f;
diff --git a/drivers/media/dvb-frontends/si2168.h b/drivers/media/dvb-frontends/si2168.h
index 50dccb394efa..ecd21adf8950 100644
--- a/drivers/media/dvb-frontends/si2168.h
+++ b/drivers/media/dvb-frontends/si2168.h
@@ -9,38 +9,43 @@
 #define SI2168_H
 
 #include <linux/dvb/frontend.h>
-/*
- * I2C address
- * 0x64
+/**
+ * struct si2168_config - configuration parameters for si2168
+ *
+ * @fe:
+ *	frontend returned by driver
+ * @i2c_adapter:
+ *	tuner I2C adapter returned by driver
+ * @ts_mode:
+ *	Transport Stream mode. Can be:
+ *	- %SI2168_TS_PARALLEL
+ *	- %SI2168_TS_SERIAL
+ *	- %SI2168_TS_TRISTATE
+ *	- %SI2168_TS_CLK_MANUAL
+ * @ts_clock_inv:
+ *	TS clock inverted
+ * @ts_clock_gapped:
+ *	TS clock gapped
+ * @spectral_inversion:
+ *	Inverted spectrum
+ *
+ * Note:
+ *	The I2C address of this demod is 0x64.
  */
 struct si2168_config {
-	/*
-	 * frontend
-	 * returned by driver
-	 */
 	struct dvb_frontend **fe;
-
-	/*
-	 * tuner I2C adapter
-	 * returned by driver
-	 */
 	struct i2c_adapter **i2c_adapter;
 
-	/* TS mode */
 #define SI2168_TS_PARALLEL	0x06
 #define SI2168_TS_SERIAL	0x03
 #define SI2168_TS_TRISTATE	0x00
 #define SI2168_TS_CLK_MANUAL	0x20
 	u8 ts_mode;
 
-	/* TS clock inverted */
-	bool ts_clock_inv;
-
-	/* TS clock gapped */
-	bool ts_clock_gapped;
-
-	/* Inverted spectrum */
-	bool spectral_inversion;
+	/* Flags */
+	unsigned int ts_clock_inv:1;
+	unsigned int ts_clock_gapped:1;
+	unsigned int spectral_inversion:1;
 };
 
 #endif
diff --git a/drivers/media/dvb-frontends/si2168_priv.h b/drivers/media/dvb-frontends/si2168_priv.h
index 804d5b30c697..18bea5222082 100644
--- a/drivers/media/dvb-frontends/si2168_priv.h
+++ b/drivers/media/dvb-frontends/si2168_priv.h
@@ -34,12 +34,12 @@ struct si2168_dev {
 	unsigned int chip_id;
 	unsigned int version;
 	const char *firmware_name;
-	bool active;
-	bool warm;
 	u8 ts_mode;
-	bool ts_clock_inv;
-	bool ts_clock_gapped;
-	bool spectral_inversion;
+	unsigned int active:1;
+	unsigned int warm:1;
+	unsigned int ts_clock_inv:1;
+	unsigned int ts_clock_gapped:1;
+	unsigned int spectral_inversion:1;
 };
 
 /* firmware command struct */
diff --git a/drivers/media/dvb-frontends/tc90522.c b/drivers/media/dvb-frontends/tc90522.c
index 849d63dbc279..e83836b29715 100644
--- a/drivers/media/dvb-frontends/tc90522.c
+++ b/drivers/media/dvb-frontends/tc90522.c
@@ -685,10 +685,33 @@ tc90522_master_xfer(struct i2c_adapter *adap, struct i2c_msg *msgs, int num)
 		p += new_msgs[j].len;
 	}
 
-	if (i < num)
+	if (i < num) {
 		ret = -ENOMEM;
-	else
+	} else if (!state->cfg.split_tuner_read_i2c || rd_num == 0) {
 		ret = i2c_transfer(state->i2c_client->adapter, new_msgs, j);
+	} else {
+		/*
+		 * Split transactions at each I2C_M_RD message.
+		 * Some of the parent device require this,
+		 * such as Friio (see. dvb-usb-gl861).
+		 */
+		int from, to;
+
+		ret = 0;
+		from = 0;
+		do {
+			int r;
+
+			to = from + 1;
+			while (to < j && !(new_msgs[to].flags & I2C_M_RD))
+				to++;
+			r = i2c_transfer(state->i2c_client->adapter,
+					 &new_msgs[from], to - from);
+			ret = (r <= 0) ? r : ret + r;
+			from = to;
+		} while (from < j && ret > 0);
+	}
+
 	if (ret >= 0 && ret < j)
 		ret = -EIO;
 	kfree(new_msgs);
diff --git a/drivers/media/dvb-frontends/tc90522.h b/drivers/media/dvb-frontends/tc90522.h
index ac0e2ab51924..07e3813bf590 100644
--- a/drivers/media/dvb-frontends/tc90522.h
+++ b/drivers/media/dvb-frontends/tc90522.h
@@ -28,6 +28,9 @@ struct tc90522_config {
 
 	/* [OUT] tuner I2C adapter returned by driver */
 	struct i2c_adapter *tuner_i2c;
+
+	/* [IN] use two separate I2C transactions for one tuner read */
+	bool split_tuner_read_i2c;
 };
 
 #endif /* TC90522_H */
diff --git a/drivers/media/i2c/Kconfig b/drivers/media/i2c/Kconfig
index 7eee1812bba3..c68e002d26ea 100644
--- a/drivers/media/i2c/Kconfig
+++ b/drivers/media/i2c/Kconfig
@@ -566,10 +566,23 @@ config VIDEO_APTINA_PLL
 config VIDEO_SMIAPP_PLL
 	tristate
 
+if MEDIA_CAMERA_SUPPORT
+
+config VIDEO_HI556
+	tristate "Hynix Hi-556 sensor support"
+	depends on I2C && VIDEO_V4L2 && VIDEO_V4L2_SUBDEV_API
+	depends on MEDIA_CONTROLLER
+	select V4L2_FWNODE
+	help
+	  This is a Video4Linux2 sensor driver for the Hynix
+	  Hi-556 camera.
+
+	  To compile this driver as a module, choose M here: the
+	  module will be called hi556.
+
 config VIDEO_IMX214
 	tristate "Sony IMX214 sensor support"
 	depends on GPIOLIB && I2C && VIDEO_V4L2 && VIDEO_V4L2_SUBDEV_API
-	depends on MEDIA_CAMERA_SUPPORT
 	depends on V4L2_FWNODE
 	help
 	  This is a Video4Linux2 sensor driver for the Sony
@@ -581,7 +594,6 @@ config VIDEO_IMX214
 config VIDEO_IMX258
 	tristate "Sony IMX258 sensor support"
 	depends on I2C && VIDEO_V4L2 && VIDEO_V4L2_SUBDEV_API
-	depends on MEDIA_CAMERA_SUPPORT
 	help
 	  This is a Video4Linux2 sensor driver for the Sony
 	  IMX258 camera.
@@ -592,16 +604,25 @@ config VIDEO_IMX258
 config VIDEO_IMX274
 	tristate "Sony IMX274 sensor support"
 	depends on I2C && VIDEO_V4L2 && VIDEO_V4L2_SUBDEV_API
-	depends on MEDIA_CAMERA_SUPPORT
 	select REGMAP_I2C
 	help
 	  This is a V4L2 sensor driver for the Sony IMX274
 	  CMOS image sensor.
 
+config VIDEO_IMX290
+	tristate "Sony IMX290 sensor support"
+	depends on I2C && VIDEO_V4L2 && VIDEO_V4L2_SUBDEV_API
+	select V4L2_FWNODE
+	help
+	  This is a Video4Linux2 sensor driver for the Sony
+	  IMX290 camera sensor.
+
+	  To compile this driver as a module, choose M here: the
+	  module will be called imx290.
+
 config VIDEO_IMX319
 	tristate "Sony IMX319 sensor support"
 	depends on I2C && VIDEO_V4L2 && VIDEO_V4L2_SUBDEV_API
-	depends on MEDIA_CAMERA_SUPPORT
 	help
 	  This is a Video4Linux2 sensor driver for the Sony
 	  IMX319 camera.
@@ -612,7 +633,6 @@ config VIDEO_IMX319
 config VIDEO_IMX355
 	tristate "Sony IMX355 sensor support"
 	depends on I2C && VIDEO_V4L2 && VIDEO_V4L2_SUBDEV_API
-	depends on MEDIA_CAMERA_SUPPORT
 	help
 	  This is a Video4Linux2 sensor driver for the Sony
 	  IMX355 camera.
@@ -623,7 +643,6 @@ config VIDEO_IMX355
 config VIDEO_OV2640
 	tristate "OmniVision OV2640 sensor support"
 	depends on VIDEO_V4L2 && I2C
-	depends on MEDIA_CAMERA_SUPPORT
 	help
 	  This is a Video4Linux2 sensor driver for the OmniVision
 	  OV2640 camera.
@@ -633,8 +652,7 @@ config VIDEO_OV2640
 
 config VIDEO_OV2659
 	tristate "OmniVision OV2659 sensor support"
-	depends on VIDEO_V4L2 && I2C
-	depends on MEDIA_CAMERA_SUPPORT
+	depends on VIDEO_V4L2 && I2C && GPIOLIB
 	select V4L2_FWNODE
 	help
 	  This is a Video4Linux2 sensor driver for the OmniVision
@@ -646,7 +664,6 @@ config VIDEO_OV2659
 config VIDEO_OV2680
 	tristate "OmniVision OV2680 sensor support"
 	depends on VIDEO_V4L2 && I2C && MEDIA_CONTROLLER
-	depends on MEDIA_CAMERA_SUPPORT
 	select V4L2_FWNODE
 	help
 	  This is a Video4Linux2 sensor driver for the OmniVision
@@ -658,7 +675,6 @@ config VIDEO_OV2680
 config VIDEO_OV2685
 	tristate "OmniVision OV2685 sensor support"
 	depends on VIDEO_V4L2 && I2C && MEDIA_CONTROLLER
-	depends on MEDIA_CAMERA_SUPPORT
 	select V4L2_FWNODE
 	help
 	  This is a Video4Linux2 sensor driver for the OmniVision
@@ -671,7 +687,6 @@ config VIDEO_OV5640
 	tristate "OmniVision OV5640 sensor support"
 	depends on OF
 	depends on GPIOLIB && VIDEO_V4L2 && I2C && VIDEO_V4L2_SUBDEV_API
-	depends on MEDIA_CAMERA_SUPPORT
 	select V4L2_FWNODE
 	help
 	  This is a Video4Linux2 sensor driver for the Omnivision
@@ -681,7 +696,6 @@ config VIDEO_OV5645
 	tristate "OmniVision OV5645 sensor support"
 	depends on OF
 	depends on I2C && VIDEO_V4L2 && VIDEO_V4L2_SUBDEV_API
-	depends on MEDIA_CAMERA_SUPPORT
 	select V4L2_FWNODE
 	help
 	  This is a Video4Linux2 sensor driver for the OmniVision
@@ -693,7 +707,6 @@ config VIDEO_OV5645
 config VIDEO_OV5647
 	tristate "OmniVision OV5647 sensor support"
 	depends on I2C && VIDEO_V4L2 && VIDEO_V4L2_SUBDEV_API
-	depends on MEDIA_CAMERA_SUPPORT
 	select V4L2_FWNODE
 	help
 	  This is a Video4Linux2 sensor driver for the OmniVision
@@ -705,7 +718,6 @@ config VIDEO_OV5647
 config VIDEO_OV6650
 	tristate "OmniVision OV6650 sensor support"
 	depends on I2C && VIDEO_V4L2
-	depends on MEDIA_CAMERA_SUPPORT
 	help
 	  This is a Video4Linux2 sensor driver for the OmniVision
 	  OV6650 camera.
@@ -716,7 +728,6 @@ config VIDEO_OV6650
 config VIDEO_OV5670
 	tristate "OmniVision OV5670 sensor support"
 	depends on I2C && VIDEO_V4L2 && VIDEO_V4L2_SUBDEV_API
-	depends on MEDIA_CAMERA_SUPPORT
 	depends on MEDIA_CONTROLLER
 	select V4L2_FWNODE
 	help
@@ -729,7 +740,6 @@ config VIDEO_OV5670
 config VIDEO_OV5675
 	tristate "OmniVision OV5675 sensor support"
 	depends on I2C && VIDEO_V4L2 && VIDEO_V4L2_SUBDEV_API
-	depends on MEDIA_CAMERA_SUPPORT
 	depends on MEDIA_CONTROLLER
 	select V4L2_FWNODE
 	help
@@ -742,7 +752,7 @@ config VIDEO_OV5675
 config VIDEO_OV5695
 	tristate "OmniVision OV5695 sensor support"
 	depends on I2C && VIDEO_V4L2
-	depends on MEDIA_CAMERA_SUPPORT
+	select V4L2_FWNODE
 	help
 	  This is a Video4Linux2 sensor driver for the OmniVision
 	  OV5695 camera.
@@ -753,7 +763,6 @@ config VIDEO_OV5695
 config VIDEO_OV7251
 	tristate "OmniVision OV7251 sensor support"
 	depends on I2C && VIDEO_V4L2 && VIDEO_V4L2_SUBDEV_API
-	depends on MEDIA_CAMERA_SUPPORT
 	select V4L2_FWNODE
 	help
 	  This is a Video4Linux2 sensor driver for the OmniVision
@@ -765,7 +774,6 @@ config VIDEO_OV7251
 config VIDEO_OV772X
 	tristate "OmniVision OV772x sensor support"
 	depends on I2C && VIDEO_V4L2
-	depends on MEDIA_CAMERA_SUPPORT
 	select REGMAP_SCCB
 	help
 	  This is a Video4Linux2 sensor driver for the OmniVision
@@ -777,7 +785,6 @@ config VIDEO_OV772X
 config VIDEO_OV7640
 	tristate "OmniVision OV7640 sensor support"
 	depends on I2C && VIDEO_V4L2
-	depends on MEDIA_CAMERA_SUPPORT
 	help
 	  This is a Video4Linux2 sensor driver for the OmniVision
 	  OV7640 camera.
@@ -788,7 +795,6 @@ config VIDEO_OV7640
 config VIDEO_OV7670
 	tristate "OmniVision OV7670 sensor support"
 	depends on I2C && VIDEO_V4L2
-	depends on MEDIA_CAMERA_SUPPORT
 	select V4L2_FWNODE
 	help
 	  This is a Video4Linux2 sensor driver for the OmniVision
@@ -798,7 +804,6 @@ config VIDEO_OV7670
 config VIDEO_OV7740
 	tristate "OmniVision OV7740 sensor support"
 	depends on I2C && VIDEO_V4L2
-	depends on MEDIA_CAMERA_SUPPORT
 	help
 	  This is a Video4Linux2 sensor driver for the OmniVision
 	  OV7740 VGA camera sensor.
@@ -806,7 +811,6 @@ config VIDEO_OV7740
 config VIDEO_OV8856
 	tristate "OmniVision OV8856 sensor support"
 	depends on I2C && VIDEO_V4L2 && VIDEO_V4L2_SUBDEV_API
-	depends on MEDIA_CAMERA_SUPPORT
 	select V4L2_FWNODE
 	help
 	  This is a Video4Linux2 sensor driver for the OmniVision
@@ -833,7 +837,6 @@ config VIDEO_OV9650
 config VIDEO_OV13858
 	tristate "OmniVision OV13858 sensor support"
 	depends on I2C && VIDEO_V4L2 && VIDEO_V4L2_SUBDEV_API
-	depends on MEDIA_CAMERA_SUPPORT
 	select V4L2_FWNODE
 	help
 	  This is a Video4Linux2 sensor driver for the OmniVision
@@ -842,7 +845,6 @@ config VIDEO_OV13858
 config VIDEO_VS6624
 	tristate "ST VS6624 sensor support"
 	depends on VIDEO_V4L2 && I2C
-	depends on MEDIA_CAMERA_SUPPORT
 	help
 	  This is a Video4Linux2 sensor driver for the ST VS6624
 	  camera.
@@ -853,7 +855,6 @@ config VIDEO_VS6624
 config VIDEO_MT9M001
 	tristate "mt9m001 support"
 	depends on I2C && VIDEO_V4L2 && VIDEO_V4L2_SUBDEV_API
-	depends on MEDIA_CAMERA_SUPPORT
 	help
 	  This driver supports MT9M001 cameras from Micron, monochrome
 	  and colour models.
@@ -861,7 +862,6 @@ config VIDEO_MT9M001
 config VIDEO_MT9M032
 	tristate "MT9M032 camera sensor support"
 	depends on I2C && VIDEO_V4L2 && VIDEO_V4L2_SUBDEV_API
-	depends on MEDIA_CAMERA_SUPPORT
 	select VIDEO_APTINA_PLL
 	help
 	  This driver supports MT9M032 camera sensors from Aptina, monochrome
@@ -878,7 +878,6 @@ config VIDEO_MT9M111
 config VIDEO_MT9P031
 	tristate "Aptina MT9P031 support"
 	depends on I2C && VIDEO_V4L2 && VIDEO_V4L2_SUBDEV_API
-	depends on MEDIA_CAMERA_SUPPORT
 	select VIDEO_APTINA_PLL
 	help
 	  This is a Video4Linux2 sensor driver for the Aptina
@@ -887,7 +886,6 @@ config VIDEO_MT9P031
 config VIDEO_MT9T001
 	tristate "Aptina MT9T001 support"
 	depends on I2C && VIDEO_V4L2 && VIDEO_V4L2_SUBDEV_API
-	depends on MEDIA_CAMERA_SUPPORT
 	help
 	  This is a Video4Linux2 sensor driver for the Aptina
 	  (Micron) mt0t001 3 Mpixel camera.
@@ -895,7 +893,6 @@ config VIDEO_MT9T001
 config VIDEO_MT9T112
 	tristate "Aptina MT9T111/MT9T112 support"
 	depends on I2C && VIDEO_V4L2
-	depends on MEDIA_CAMERA_SUPPORT
 	help
 	  This is a Video4Linux2 sensor driver for the Aptina
 	  (Micron) MT9T111 and MT9T112 3 Mpixel camera.
@@ -906,7 +903,6 @@ config VIDEO_MT9T112
 config VIDEO_MT9V011
 	tristate "Micron mt9v011 sensor support"
 	depends on I2C && VIDEO_V4L2
-	depends on MEDIA_CAMERA_SUPPORT
 	help
 	  This is a Video4Linux2 sensor driver for the Micron
 	  mt0v011 1.3 Mpixel camera.  It currently only works with the
@@ -915,7 +911,6 @@ config VIDEO_MT9V011
 config VIDEO_MT9V032
 	tristate "Micron MT9V032 sensor support"
 	depends on I2C && VIDEO_V4L2 && VIDEO_V4L2_SUBDEV_API
-	depends on MEDIA_CAMERA_SUPPORT
 	select REGMAP_I2C
 	select V4L2_FWNODE
 	help
@@ -925,7 +920,6 @@ config VIDEO_MT9V032
 config VIDEO_MT9V111
 	tristate "Aptina MT9V111 sensor support"
 	depends on I2C && VIDEO_V4L2
-	depends on MEDIA_CAMERA_SUPPORT
 	help
 	  This is a Video4Linux2 sensor driver for the Aptina/Micron
 	  MT9V111 sensor.
@@ -936,14 +930,12 @@ config VIDEO_MT9V111
 config VIDEO_SR030PC30
 	tristate "Siliconfile SR030PC30 sensor support"
 	depends on I2C && VIDEO_V4L2
-	depends on MEDIA_CAMERA_SUPPORT
 	help
 	  This driver supports SR030PC30 VGA camera from Siliconfile
 
 config VIDEO_NOON010PC30
 	tristate "Siliconfile NOON010PC30 sensor support"
 	depends on I2C && VIDEO_V4L2 && VIDEO_V4L2_SUBDEV_API
-	depends on MEDIA_CAMERA_SUPPORT
 	help
 	  This driver supports NOON010PC30 CIF camera from Siliconfile
 
@@ -952,7 +944,6 @@ source "drivers/media/i2c/m5mols/Kconfig"
 config VIDEO_RJ54N1
 	tristate "Sharp RJ54N1CB0C sensor support"
 	depends on I2C && VIDEO_V4L2
-	depends on MEDIA_CAMERA_SUPPORT
 	help
 	  This is a V4L2 sensor driver for Sharp RJ54N1CB0C CMOS image
 	  sensor.
@@ -962,7 +953,6 @@ config VIDEO_RJ54N1
 
 config VIDEO_S5K6AA
 	tristate "Samsung S5K6AAFX sensor support"
-	depends on MEDIA_CAMERA_SUPPORT
 	depends on I2C && VIDEO_V4L2 && VIDEO_V4L2_SUBDEV_API
 	help
 	  This is a V4L2 sensor driver for Samsung S5K6AA(FX) 1.3M
@@ -970,7 +960,6 @@ config VIDEO_S5K6AA
 
 config VIDEO_S5K6A3
 	tristate "Samsung S5K6A3 sensor support"
-	depends on MEDIA_CAMERA_SUPPORT
 	depends on I2C && VIDEO_V4L2 && VIDEO_V4L2_SUBDEV_API
 	help
 	  This is a V4L2 sensor driver for Samsung S5K6A3 raw
@@ -1002,12 +991,15 @@ config VIDEO_S5C73M3
 	help
 	  This is a V4L2 sensor driver for Samsung S5C73M3
 	  8 Mpixel camera.
+endif
 
 comment "Lens drivers"
 
+if MEDIA_CAMERA_SUPPORT
+
 config VIDEO_AD5820
 	tristate "AD5820 lens voice coil support"
-	depends on I2C && VIDEO_V4L2 && MEDIA_CONTROLLER
+	depends on GPIOLIB && I2C && VIDEO_V4L2 && MEDIA_CONTROLLER
 	help
 	  This is a driver for the AD5820 camera lens voice coil.
 	  It is used for example in Nokia N900 (RX-51).
@@ -1042,12 +1034,15 @@ config VIDEO_DW9807_VCM
 	  capability. This is designed for linear control of
 	  voice coil motors, controlled via I2C serial interface.
 
+endif
+
 comment "Flash devices"
 
+if MEDIA_CAMERA_SUPPORT
+
 config VIDEO_ADP1653
 	tristate "ADP1653 flash support"
 	depends on I2C && VIDEO_V4L2 && MEDIA_CONTROLLER
-	depends on MEDIA_CAMERA_SUPPORT
 	help
 	  This is a driver for the ADP1653 flash controller. It is used for
 	  example in Nokia N900.
@@ -1055,7 +1050,6 @@ config VIDEO_ADP1653
 config VIDEO_LM3560
 	tristate "LM3560 dual flash driver support"
 	depends on I2C && VIDEO_V4L2 && MEDIA_CONTROLLER
-	depends on MEDIA_CAMERA_SUPPORT
 	select REGMAP_I2C
 	help
 	  This is a driver for the lm3560 dual flash controllers. It controls
@@ -1064,12 +1058,13 @@ config VIDEO_LM3560
 config VIDEO_LM3646
 	tristate "LM3646 dual flash driver support"
 	depends on I2C && VIDEO_V4L2 && MEDIA_CONTROLLER
-	depends on MEDIA_CAMERA_SUPPORT
 	select REGMAP_I2C
 	help
 	  This is a driver for the lm3646 dual flash controllers. It controls
 	  flash, torch LEDs.
 
+endif
+
 comment "Video improvement chips"
 
 config VIDEO_UPD64031A
@@ -1113,6 +1108,7 @@ comment "SDR tuner chips"
 config SDR_MAX2175
 	tristate "Maxim 2175 RF to Bits tuner"
 	depends on VIDEO_V4L2 && MEDIA_SDR_SUPPORT && I2C
+	select REGMAP_I2C
 	help
 	  Support for Maxim 2175 tuner. It is an advanced analog/digital
 	  radio receiver with RF-to-Bits front-end designed for SDR solutions.
diff --git a/drivers/media/i2c/Makefile b/drivers/media/i2c/Makefile
index beb170b002dc..c147bb9d28db 100644
--- a/drivers/media/i2c/Makefile
+++ b/drivers/media/i2c/Makefile
@@ -109,9 +109,11 @@ obj-$(CONFIG_VIDEO_I2C)		+= video-i2c.o
 obj-$(CONFIG_VIDEO_ML86V7667)	+= ml86v7667.o
 obj-$(CONFIG_VIDEO_OV2659)	+= ov2659.o
 obj-$(CONFIG_VIDEO_TC358743)	+= tc358743.o
+obj-$(CONFIG_VIDEO_HI556)	+= hi556.o
 obj-$(CONFIG_VIDEO_IMX214)	+= imx214.o
 obj-$(CONFIG_VIDEO_IMX258)	+= imx258.o
 obj-$(CONFIG_VIDEO_IMX274)	+= imx274.o
+obj-$(CONFIG_VIDEO_IMX290)	+= imx290.o
 obj-$(CONFIG_VIDEO_IMX319)	+= imx319.o
 obj-$(CONFIG_VIDEO_IMX355)	+= imx355.o
 obj-$(CONFIG_VIDEO_ST_MIPID02) += st-mipid02.o
diff --git a/drivers/media/i2c/ad5820.c b/drivers/media/i2c/ad5820.c
index 925c171e7797..19c74db0649f 100644
--- a/drivers/media/i2c/ad5820.c
+++ b/drivers/media/i2c/ad5820.c
@@ -19,13 +19,12 @@
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/regulator/consumer.h>
+#include <linux/gpio/consumer.h>
 
 #include <media/v4l2-ctrls.h>
 #include <media/v4l2-device.h>
 #include <media/v4l2-subdev.h>
 
-#define AD5820_NAME		"ad5820"
-
 /* Register definitions */
 #define AD5820_POWER_DOWN		(1 << 15)
 #define AD5820_DAC_SHIFT		4
@@ -47,6 +46,8 @@ struct ad5820_device {
 	u32 focus_ramp_time;
 	u32 focus_ramp_mode;
 
+	struct gpio_desc *enable_gpio;
+
 	struct mutex power_lock;
 	int power_count;
 
@@ -114,6 +115,8 @@ static int ad5820_power_off(struct ad5820_device *coil, bool standby)
 		ret = ad5820_update_hw(coil);
 	}
 
+	gpiod_set_value_cansleep(coil->enable_gpio, 0);
+
 	ret2 = regulator_disable(coil->vana);
 	if (ret)
 		return ret;
@@ -128,6 +131,8 @@ static int ad5820_power_on(struct ad5820_device *coil, bool restore)
 	if (ret < 0)
 		return ret;
 
+	gpiod_set_value_cansleep(coil->enable_gpio, 1);
+
 	if (restore) {
 		/* Restore the hardware settings. */
 		coil->standby = false;
@@ -138,6 +143,7 @@ static int ad5820_power_on(struct ad5820_device *coil, bool restore)
 	return 0;
 
 fail:
+	gpiod_set_value_cansleep(coil->enable_gpio, 0);
 	coil->standby = true;
 	regulator_disable(coil->vana);
 
@@ -304,11 +310,21 @@ static int ad5820_probe(struct i2c_client *client,
 		return ret;
 	}
 
+	coil->enable_gpio = devm_gpiod_get_optional(&client->dev, "enable",
+						    GPIOD_OUT_LOW);
+	if (IS_ERR(coil->enable_gpio)) {
+		ret = PTR_ERR(coil->enable_gpio);
+		if (ret != -EPROBE_DEFER)
+			dev_err(&client->dev, "could not get enable gpio\n");
+		return ret;
+	}
+
 	mutex_init(&coil->power_lock);
 
 	v4l2_i2c_subdev_init(&coil->subdev, client, &ad5820_ops);
 	coil->subdev.flags |= V4L2_SUBDEV_FL_HAS_DEVNODE;
 	coil->subdev.internal_ops = &ad5820_internal_ops;
+	coil->subdev.entity.function = MEDIA_ENT_F_LENS;
 	strscpy(coil->subdev.name, "ad5820 focus", sizeof(coil->subdev.name));
 
 	ret = media_entity_pads_init(&coil->subdev.entity, 0, NULL);
@@ -341,17 +357,28 @@ static int ad5820_remove(struct i2c_client *client)
 }
 
 static const struct i2c_device_id ad5820_id_table[] = {
-	{ AD5820_NAME, 0 },
+	{ "ad5820", 0 },
+	{ "ad5821", 0 },
+	{ "ad5823", 0 },
 	{ }
 };
 MODULE_DEVICE_TABLE(i2c, ad5820_id_table);
 
+static const struct of_device_id ad5820_of_table[] = {
+	{ .compatible = "adi,ad5820" },
+	{ .compatible = "adi,ad5821" },
+	{ .compatible = "adi,ad5823" },
+	{ }
+};
+MODULE_DEVICE_TABLE(of, ad5820_of_table);
+
 static SIMPLE_DEV_PM_OPS(ad5820_pm, ad5820_suspend, ad5820_resume);
 
 static struct i2c_driver ad5820_i2c_driver = {
 	.driver		= {
-		.name	= AD5820_NAME,
+		.name	= "ad5820",
 		.pm	= &ad5820_pm,
+		.of_match_table = ad5820_of_table,
 	},
 	.probe		= ad5820_probe,
 	.remove		= ad5820_remove,
diff --git a/drivers/media/i2c/adv7180.c b/drivers/media/i2c/adv7180.c
index e780969cc2f2..6528e2343fc8 100644
--- a/drivers/media/i2c/adv7180.c
+++ b/drivers/media/i2c/adv7180.c
@@ -1309,9 +1309,6 @@ static int adv7180_probe(struct i2c_client *client,
 	if (!i2c_check_functionality(client->adapter, I2C_FUNC_SMBUS_BYTE_DATA))
 		return -EIO;
 
-	v4l_info(client, "chip found @ 0x%02x (%s)\n",
-		 client->addr, client->adapter->name);
-
 	state = devm_kzalloc(&client->dev, sizeof(*state), GFP_KERNEL);
 	if (state == NULL)
 		return -ENOMEM;
@@ -1382,6 +1379,9 @@ static int adv7180_probe(struct i2c_client *client,
 	if (ret)
 		goto err_free_irq;
 
+	v4l_info(client, "chip found @ 0x%02x (%s)\n",
+		 client->addr, client->adapter->name);
+
 	return 0;
 
 err_free_irq:
diff --git a/drivers/media/i2c/adv7842.c b/drivers/media/i2c/adv7842.c
index 885619841719..0855f648416d 100644
--- a/drivers/media/i2c/adv7842.c
+++ b/drivers/media/i2c/adv7842.c
@@ -2547,7 +2547,7 @@ struct adv7842_cfg_read_infoframe {
 	u8 payload_addr;
 };
 
-static void log_infoframe(struct v4l2_subdev *sd, struct adv7842_cfg_read_infoframe *cri)
+static void log_infoframe(struct v4l2_subdev *sd, const struct adv7842_cfg_read_infoframe *cri)
 {
 	int i;
 	u8 buffer[32];
@@ -2585,7 +2585,7 @@ static void log_infoframe(struct v4l2_subdev *sd, struct adv7842_cfg_read_infofr
 static void adv7842_log_infoframes(struct v4l2_subdev *sd)
 {
 	int i;
-	struct adv7842_cfg_read_infoframe cri[] = {
+	static const struct adv7842_cfg_read_infoframe cri[] = {
 		{ "AVI", 0x01, 0xe0, 0x00 },
 		{ "Audio", 0x02, 0xe3, 0x1c },
 		{ "SDP", 0x04, 0xe6, 0x2a },
diff --git a/drivers/media/i2c/bt819.c b/drivers/media/i2c/bt819.c
index 43336175c7d9..73bc50c919d7 100644
--- a/drivers/media/i2c/bt819.c
+++ b/drivers/media/i2c/bt819.c
@@ -157,7 +157,7 @@ static int bt819_init(struct v4l2_subdev *sd)
 		0x12, 0x04,	/* 0x12 Output Format */
 		0x13, 0x20,	/* 0x13 Vertical Scaling msb 0x00
 					   chroma comb OFF, line drop scaling, interlace scaling
-					   BUG? Why does turning the chroma comb on fuck up color?
+					   BUG? Why does turning the chroma comb on screw up color?
 					   Bug in the bt819 stepping on my board?
 					*/
 		0x14, 0x00,	/* 0x14 Vertical Scaling lsb */
diff --git a/drivers/media/i2c/hi556.c b/drivers/media/i2c/hi556.c
new file mode 100644
index 000000000000..c66cd1446c0f
--- /dev/null
+++ b/drivers/media/i2c/hi556.c
@@ -0,0 +1,1200 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) 2019 Intel Corporation.
+
+#include <asm/unaligned.h>
+#include <linux/acpi.h>
+#include <linux/delay.h>
+#include <linux/i2c.h>
+#include <linux/module.h>
+#include <linux/pm_runtime.h>
+#include <media/v4l2-ctrls.h>
+#include <media/v4l2-device.h>
+#include <media/v4l2-fwnode.h>
+
+#define HI556_REG_VALUE_08BIT		1
+#define HI556_REG_VALUE_16BIT		2
+#define HI556_REG_VALUE_24BIT		3
+
+#define HI556_LINK_FREQ_437MHZ		437000000ULL
+#define HI556_MCLK			19200000
+#define HI556_DATA_LANES		2
+#define HI556_RGB_DEPTH			10
+
+#define HI556_REG_CHIP_ID		0x0f16
+#define HI556_CHIP_ID			0x0556
+
+#define HI556_REG_MODE_SELECT		0x0a00
+#define HI556_MODE_STANDBY		0x0000
+#define HI556_MODE_STREAMING		0x0100
+
+/* vertical-timings from sensor */
+#define HI556_REG_FLL			0x0006
+#define HI556_FLL_30FPS			0x0814
+#define HI556_FLL_30FPS_MIN		0x0814
+#define HI556_FLL_MAX			0x7fff
+
+/* horizontal-timings from sensor */
+#define HI556_REG_LLP			0x0008
+
+/* Exposure controls from sensor */
+#define HI556_REG_EXPOSURE		0x0074
+#define HI556_EXPOSURE_MIN		6
+#define HI556_EXPOSURE_MAX_MARGIN	2
+#define HI556_EXPOSURE_STEP		1
+
+/* Analog gain controls from sensor */
+#define HI556_REG_ANALOG_GAIN		0x0077
+#define HI556_ANAL_GAIN_MIN		0
+#define HI556_ANAL_GAIN_MAX		240
+#define HI556_ANAL_GAIN_STEP		1
+
+/* Digital gain controls from sensor */
+#define HI556_REG_MWB_GR_GAIN		0x0078
+#define HI556_REG_MWB_GB_GAIN		0x007a
+#define HI556_REG_MWB_R_GAIN		0x007c
+#define HI556_REG_MWB_B_GAIN		0x007e
+#define HI556_DGTL_GAIN_MIN		0
+#define HI556_DGTL_GAIN_MAX		2048
+#define HI556_DGTL_GAIN_STEP		1
+#define HI556_DGTL_GAIN_DEFAULT		256
+
+/* Test Pattern Control */
+#define HI556_REG_ISP			0X0a05
+#define HI556_REG_ISP_TPG_EN		0x01
+#define HI556_REG_TEST_PATTERN		0x0201
+
+enum {
+	HI556_LINK_FREQ_437MHZ_INDEX,
+};
+
+struct hi556_reg {
+	u16 address;
+	u16 val;
+};
+
+struct hi556_reg_list {
+	u32 num_of_regs;
+	const struct hi556_reg *regs;
+};
+
+struct hi556_link_freq_config {
+	const struct hi556_reg_list reg_list;
+};
+
+struct hi556_mode {
+	/* Frame width in pixels */
+	u32 width;
+
+	/* Frame height in pixels */
+	u32 height;
+
+	/* Horizontal timining size */
+	u32 llp;
+
+	/* Default vertical timining size */
+	u32 fll_def;
+
+	/* Min vertical timining size */
+	u32 fll_min;
+
+	/* Link frequency needed for this resolution */
+	u32 link_freq_index;
+
+	/* Sensor register settings for this resolution */
+	const struct hi556_reg_list reg_list;
+};
+
+#define to_hi556(_sd) container_of(_sd, struct hi556, sd)
+
+//SENSOR_INITIALIZATION
+static const struct hi556_reg mipi_data_rate_874mbps[] = {
+	{0x0e00, 0x0102},
+	{0x0e02, 0x0102},
+	{0x0e0c, 0x0100},
+	{0x2000, 0x7400},
+	{0x2002, 0x001c},
+	{0x2004, 0x0242},
+	{0x2006, 0x0942},
+	{0x2008, 0x7007},
+	{0x200a, 0x0fd9},
+	{0x200c, 0x0259},
+	{0x200e, 0x7008},
+	{0x2010, 0x160e},
+	{0x2012, 0x0047},
+	{0x2014, 0x2118},
+	{0x2016, 0x0041},
+	{0x2018, 0x00d8},
+	{0x201a, 0x0145},
+	{0x201c, 0x0006},
+	{0x201e, 0x0181},
+	{0x2020, 0x13cc},
+	{0x2022, 0x2057},
+	{0x2024, 0x7001},
+	{0x2026, 0x0fca},
+	{0x2028, 0x00cb},
+	{0x202a, 0x009f},
+	{0x202c, 0x7002},
+	{0x202e, 0x13cc},
+	{0x2030, 0x019b},
+	{0x2032, 0x014d},
+	{0x2034, 0x2987},
+	{0x2036, 0x2766},
+	{0x2038, 0x0020},
+	{0x203a, 0x2060},
+	{0x203c, 0x0e5d},
+	{0x203e, 0x181d},
+	{0x2040, 0x2066},
+	{0x2042, 0x20c4},
+	{0x2044, 0x5000},
+	{0x2046, 0x0005},
+	{0x2048, 0x0000},
+	{0x204a, 0x01db},
+	{0x204c, 0x025a},
+	{0x204e, 0x00c0},
+	{0x2050, 0x0005},
+	{0x2052, 0x0006},
+	{0x2054, 0x0ad9},
+	{0x2056, 0x0259},
+	{0x2058, 0x0618},
+	{0x205a, 0x0258},
+	{0x205c, 0x2266},
+	{0x205e, 0x20c8},
+	{0x2060, 0x2060},
+	{0x2062, 0x707b},
+	{0x2064, 0x0fdd},
+	{0x2066, 0x81b8},
+	{0x2068, 0x5040},
+	{0x206a, 0x0020},
+	{0x206c, 0x5060},
+	{0x206e, 0x3143},
+	{0x2070, 0x5081},
+	{0x2072, 0x025c},
+	{0x2074, 0x7800},
+	{0x2076, 0x7400},
+	{0x2078, 0x001c},
+	{0x207a, 0x0242},
+	{0x207c, 0x0942},
+	{0x207e, 0x0bd9},
+	{0x2080, 0x0259},
+	{0x2082, 0x7008},
+	{0x2084, 0x160e},
+	{0x2086, 0x0047},
+	{0x2088, 0x2118},
+	{0x208a, 0x0041},
+	{0x208c, 0x00d8},
+	{0x208e, 0x0145},
+	{0x2090, 0x0006},
+	{0x2092, 0x0181},
+	{0x2094, 0x13cc},
+	{0x2096, 0x2057},
+	{0x2098, 0x7001},
+	{0x209a, 0x0fca},
+	{0x209c, 0x00cb},
+	{0x209e, 0x009f},
+	{0x20a0, 0x7002},
+	{0x20a2, 0x13cc},
+	{0x20a4, 0x019b},
+	{0x20a6, 0x014d},
+	{0x20a8, 0x2987},
+	{0x20aa, 0x2766},
+	{0x20ac, 0x0020},
+	{0x20ae, 0x2060},
+	{0x20b0, 0x0e5d},
+	{0x20b2, 0x181d},
+	{0x20b4, 0x2066},
+	{0x20b6, 0x20c4},
+	{0x20b8, 0x50a0},
+	{0x20ba, 0x0005},
+	{0x20bc, 0x0000},
+	{0x20be, 0x01db},
+	{0x20c0, 0x025a},
+	{0x20c2, 0x00c0},
+	{0x20c4, 0x0005},
+	{0x20c6, 0x0006},
+	{0x20c8, 0x0ad9},
+	{0x20ca, 0x0259},
+	{0x20cc, 0x0618},
+	{0x20ce, 0x0258},
+	{0x20d0, 0x2266},
+	{0x20d2, 0x20c8},
+	{0x20d4, 0x2060},
+	{0x20d6, 0x707b},
+	{0x20d8, 0x0fdd},
+	{0x20da, 0x86b8},
+	{0x20dc, 0x50e0},
+	{0x20de, 0x0020},
+	{0x20e0, 0x5100},
+	{0x20e2, 0x3143},
+	{0x20e4, 0x5121},
+	{0x20e6, 0x7800},
+	{0x20e8, 0x3140},
+	{0x20ea, 0x01c4},
+	{0x20ec, 0x01c1},
+	{0x20ee, 0x01c0},
+	{0x20f0, 0x01c4},
+	{0x20f2, 0x2700},
+	{0x20f4, 0x3d40},
+	{0x20f6, 0x7800},
+	{0x20f8, 0xffff},
+	{0x27fe, 0xe000},
+	{0x3000, 0x60f8},
+	{0x3002, 0x187f},
+	{0x3004, 0x7060},
+	{0x3006, 0x0114},
+	{0x3008, 0x60b0},
+	{0x300a, 0x1473},
+	{0x300c, 0x0013},
+	{0x300e, 0x140f},
+	{0x3010, 0x0040},
+	{0x3012, 0x100f},
+	{0x3014, 0x60f8},
+	{0x3016, 0x187f},
+	{0x3018, 0x7060},
+	{0x301a, 0x0114},
+	{0x301c, 0x60b0},
+	{0x301e, 0x1473},
+	{0x3020, 0x0013},
+	{0x3022, 0x140f},
+	{0x3024, 0x0040},
+	{0x3026, 0x000f},
+
+	{0x0b00, 0x0000},
+	{0x0b02, 0x0045},
+	{0x0b04, 0xb405},
+	{0x0b06, 0xc403},
+	{0x0b08, 0x0081},
+	{0x0b0a, 0x8252},
+	{0x0b0c, 0xf814},
+	{0x0b0e, 0xc618},
+	{0x0b10, 0xa828},
+	{0x0b12, 0x004c},
+	{0x0b14, 0x4068},
+	{0x0b16, 0x0000},
+	{0x0f30, 0x5b15},
+	{0x0f32, 0x7067},
+	{0x0954, 0x0009},
+	{0x0956, 0x0000},
+	{0x0958, 0xbb80},
+	{0x095a, 0x5140},
+	{0x0c00, 0x1110},
+	{0x0c02, 0x0011},
+	{0x0c04, 0x0000},
+	{0x0c06, 0x0200},
+	{0x0c10, 0x0040},
+	{0x0c12, 0x0040},
+	{0x0c14, 0x0040},
+	{0x0c16, 0x0040},
+	{0x0a10, 0x4000},
+	{0x3068, 0xf800},
+	{0x306a, 0xf876},
+	{0x006c, 0x0000},
+	{0x005e, 0x0200},
+	{0x000e, 0x0100},
+	{0x0e0a, 0x0001},
+	{0x004a, 0x0100},
+	{0x004c, 0x0000},
+	{0x004e, 0x0100},
+	{0x000c, 0x0022},
+	{0x0008, 0x0b00},
+	{0x005a, 0x0202},
+	{0x0012, 0x000e},
+	{0x0018, 0x0a33},
+	{0x0022, 0x0008},
+	{0x0028, 0x0017},
+	{0x0024, 0x0028},
+	{0x002a, 0x002d},
+	{0x0026, 0x0030},
+	{0x002c, 0x07c9},
+	{0x002e, 0x1111},
+	{0x0030, 0x1111},
+	{0x0032, 0x1111},
+	{0x0006, 0x07bc},
+	{0x0a22, 0x0000},
+	{0x0a12, 0x0a20},
+	{0x0a14, 0x0798},
+	{0x003e, 0x0000},
+	{0x0074, 0x080e},
+	{0x0070, 0x0407},
+	{0x0002, 0x0000},
+	{0x0a02, 0x0100},
+	{0x0a24, 0x0100},
+	{0x0046, 0x0000},
+	{0x0076, 0x0000},
+	{0x0060, 0x0000},
+	{0x0062, 0x0530},
+	{0x0064, 0x0500},
+	{0x0066, 0x0530},
+	{0x0068, 0x0500},
+	{0x0122, 0x0300},
+	{0x015a, 0xff08},
+	{0x0804, 0x0300},
+	{0x0806, 0x0100},
+	{0x005c, 0x0102},
+	{0x0a1a, 0x0800},
+};
+
+static const struct hi556_reg mode_2592x1944_regs[] = {
+	{0x0a00, 0x0000},
+	{0x0b0a, 0x8252},
+	{0x0f30, 0x5b15},
+	{0x0f32, 0x7067},
+	{0x004a, 0x0100},
+	{0x004c, 0x0000},
+	{0x004e, 0x0100},
+	{0x000c, 0x0022},
+	{0x0008, 0x0b00},
+	{0x005a, 0x0202},
+	{0x0012, 0x000e},
+	{0x0018, 0x0a33},
+	{0x0022, 0x0008},
+	{0x0028, 0x0017},
+	{0x0024, 0x0028},
+	{0x002a, 0x002d},
+	{0x0026, 0x0030},
+	{0x002c, 0x07c9},
+	{0x002e, 0x1111},
+	{0x0030, 0x1111},
+	{0x0032, 0x1111},
+	{0x0006, 0x0814},
+	{0x0a22, 0x0000},
+	{0x0a12, 0x0a20},
+	{0x0a14, 0x0798},
+	{0x003e, 0x0000},
+	{0x0074, 0x0812},
+	{0x0070, 0x0409},
+	{0x0804, 0x0300},
+	{0x0806, 0x0100},
+	{0x0a04, 0x014a},
+	{0x090c, 0x0fdc},
+	{0x090e, 0x002d},
+
+	{0x0902, 0x4319},
+	{0x0914, 0xc10a},
+	{0x0916, 0x071f},
+	{0x0918, 0x0408},
+	{0x091a, 0x0c0d},
+	{0x091c, 0x0f09},
+	{0x091e, 0x0a00},
+	{0x0958, 0xbb80},
+};
+
+static const struct hi556_reg mode_1296x972_regs[] = {
+	{0x0a00, 0x0000},
+	{0x0b0a, 0x8259},
+	{0x0f30, 0x5b15},
+	{0x0f32, 0x7167},
+	{0x004a, 0x0100},
+	{0x004c, 0x0000},
+	{0x004e, 0x0100},
+	{0x000c, 0x0122},
+	{0x0008, 0x0b00},
+	{0x005a, 0x0404},
+	{0x0012, 0x000c},
+	{0x0018, 0x0a33},
+	{0x0022, 0x0008},
+	{0x0028, 0x0017},
+	{0x0024, 0x0022},
+	{0x002a, 0x002b},
+	{0x0026, 0x0030},
+	{0x002c, 0x07c9},
+	{0x002e, 0x3311},
+	{0x0030, 0x3311},
+	{0x0032, 0x3311},
+	{0x0006, 0x0814},
+	{0x0a22, 0x0000},
+	{0x0a12, 0x0510},
+	{0x0a14, 0x03cc},
+	{0x003e, 0x0000},
+	{0x0074, 0x0812},
+	{0x0070, 0x0409},
+	{0x0804, 0x0308},
+	{0x0806, 0x0100},
+	{0x0a04, 0x016a},
+	{0x090e, 0x0010},
+	{0x090c, 0x09c0},
+
+	{0x0902, 0x4319},
+	{0x0914, 0xc106},
+	{0x0916, 0x040e},
+	{0x0918, 0x0304},
+	{0x091a, 0x0708},
+	{0x091c, 0x0e06},
+	{0x091e, 0x0300},
+	{0x0958, 0xbb80},
+};
+
+static const char * const hi556_test_pattern_menu[] = {
+	"Disabled",
+	"Solid Colour",
+	"100% Colour Bars",
+	"Fade To Grey Colour Bars",
+	"PN9",
+	"Gradient Horizontal",
+	"Gradient Vertical",
+	"Check Board",
+	"Slant Pattern",
+};
+
+static const s64 link_freq_menu_items[] = {
+	HI556_LINK_FREQ_437MHZ,
+};
+
+static const struct hi556_link_freq_config link_freq_configs[] = {
+	[HI556_LINK_FREQ_437MHZ_INDEX] = {
+		.reg_list = {
+			.num_of_regs = ARRAY_SIZE(mipi_data_rate_874mbps),
+			.regs = mipi_data_rate_874mbps,
+		}
+	}
+};
+
+static const struct hi556_mode supported_modes[] = {
+	{
+		.width = 2592,
+		.height = 1944,
+		.fll_def = HI556_FLL_30FPS,
+		.fll_min = HI556_FLL_30FPS_MIN,
+		.llp = 0x0b00,
+		.reg_list = {
+			.num_of_regs = ARRAY_SIZE(mode_2592x1944_regs),
+			.regs = mode_2592x1944_regs,
+		},
+		.link_freq_index = HI556_LINK_FREQ_437MHZ_INDEX,
+	},
+	{
+		.width = 1296,
+		.height = 972,
+		.fll_def = HI556_FLL_30FPS,
+		.fll_min = HI556_FLL_30FPS_MIN,
+		.llp = 0x0b00,
+		.reg_list = {
+			.num_of_regs = ARRAY_SIZE(mode_1296x972_regs),
+			.regs = mode_1296x972_regs,
+		},
+		.link_freq_index = HI556_LINK_FREQ_437MHZ_INDEX,
+	}
+};
+
+struct hi556 {
+	struct v4l2_subdev sd;
+	struct media_pad pad;
+	struct v4l2_ctrl_handler ctrl_handler;
+
+	/* V4L2 Controls */
+	struct v4l2_ctrl *link_freq;
+	struct v4l2_ctrl *pixel_rate;
+	struct v4l2_ctrl *vblank;
+	struct v4l2_ctrl *hblank;
+	struct v4l2_ctrl *exposure;
+
+	/* Current mode */
+	const struct hi556_mode *cur_mode;
+
+	/* To serialize asynchronus callbacks */
+	struct mutex mutex;
+
+	/* Streaming on/off */
+	bool streaming;
+};
+
+static u64 to_pixel_rate(u32 f_index)
+{
+	u64 pixel_rate = link_freq_menu_items[f_index] * 2 * HI556_DATA_LANES;
+
+	do_div(pixel_rate, HI556_RGB_DEPTH);
+
+	return pixel_rate;
+}
+
+static int hi556_read_reg(struct hi556 *hi556, u16 reg, u16 len, u32 *val)
+{
+	struct i2c_client *client = v4l2_get_subdevdata(&hi556->sd);
+	struct i2c_msg msgs[2];
+	u8 addr_buf[2];
+	u8 data_buf[4] = {0};
+	int ret;
+
+	if (len > 4)
+		return -EINVAL;
+
+	put_unaligned_be16(reg, addr_buf);
+	msgs[0].addr = client->addr;
+	msgs[0].flags = 0;
+	msgs[0].len = sizeof(addr_buf);
+	msgs[0].buf = addr_buf;
+	msgs[1].addr = client->addr;
+	msgs[1].flags = I2C_M_RD;
+	msgs[1].len = len;
+	msgs[1].buf = &data_buf[4 - len];
+
+	ret = i2c_transfer(client->adapter, msgs, ARRAY_SIZE(msgs));
+	if (ret != ARRAY_SIZE(msgs))
+		return -EIO;
+
+	*val = get_unaligned_be32(data_buf);
+
+	return 0;
+}
+
+static int hi556_write_reg(struct hi556 *hi556, u16 reg, u16 len, u32 val)
+{
+	struct i2c_client *client = v4l2_get_subdevdata(&hi556->sd);
+	u8 buf[6];
+
+	if (len > 4)
+		return -EINVAL;
+
+	put_unaligned_be16(reg, buf);
+	put_unaligned_be32(val << 8 * (4 - len), buf + 2);
+	if (i2c_master_send(client, buf, len + 2) != len + 2)
+		return -EIO;
+
+	return 0;
+}
+
+static int hi556_write_reg_list(struct hi556 *hi556,
+				const struct hi556_reg_list *r_list)
+{
+	struct i2c_client *client = v4l2_get_subdevdata(&hi556->sd);
+	unsigned int i;
+	int ret;
+
+	for (i = 0; i < r_list->num_of_regs; i++) {
+		ret = hi556_write_reg(hi556, r_list->regs[i].address,
+				      HI556_REG_VALUE_16BIT,
+				      r_list->regs[i].val);
+		if (ret) {
+			dev_err_ratelimited(&client->dev,
+					    "failed to write reg 0x%4.4x. error = %d",
+					    r_list->regs[i].address, ret);
+			return ret;
+		}
+	}
+
+	return 0;
+}
+
+static int hi556_update_digital_gain(struct hi556 *hi556, u32 d_gain)
+{
+	int ret;
+
+	ret = hi556_write_reg(hi556, HI556_REG_MWB_GR_GAIN,
+			      HI556_REG_VALUE_16BIT, d_gain);
+	if (ret)
+		return ret;
+
+	ret = hi556_write_reg(hi556, HI556_REG_MWB_GB_GAIN,
+			      HI556_REG_VALUE_16BIT, d_gain);
+	if (ret)
+		return ret;
+
+	ret = hi556_write_reg(hi556, HI556_REG_MWB_R_GAIN,
+			      HI556_REG_VALUE_16BIT, d_gain);
+	if (ret)
+		return ret;
+
+	return hi556_write_reg(hi556, HI556_REG_MWB_B_GAIN,
+			       HI556_REG_VALUE_16BIT, d_gain);
+}
+
+static int hi556_test_pattern(struct hi556 *hi556, u32 pattern)
+{
+	int ret;
+	u32 val;
+
+	if (pattern) {
+		ret = hi556_read_reg(hi556, HI556_REG_ISP,
+				     HI556_REG_VALUE_08BIT, &val);
+		if (ret)
+			return ret;
+
+		ret = hi556_write_reg(hi556, HI556_REG_ISP,
+				      HI556_REG_VALUE_08BIT,
+				      val | HI556_REG_ISP_TPG_EN);
+		if (ret)
+			return ret;
+	}
+
+	return hi556_write_reg(hi556, HI556_REG_TEST_PATTERN,
+			       HI556_REG_VALUE_08BIT, pattern);
+}
+
+static int hi556_set_ctrl(struct v4l2_ctrl *ctrl)
+{
+	struct hi556 *hi556 = container_of(ctrl->handler,
+					     struct hi556, ctrl_handler);
+	struct i2c_client *client = v4l2_get_subdevdata(&hi556->sd);
+	s64 exposure_max;
+	int ret = 0;
+
+	/* Propagate change of current control to all related controls */
+	if (ctrl->id == V4L2_CID_VBLANK) {
+		/* Update max exposure while meeting expected vblanking */
+		exposure_max = hi556->cur_mode->height + ctrl->val -
+			       HI556_EXPOSURE_MAX_MARGIN;
+		__v4l2_ctrl_modify_range(hi556->exposure,
+					 hi556->exposure->minimum,
+					 exposure_max, hi556->exposure->step,
+					 exposure_max);
+	}
+
+	/* V4L2 controls values will be applied only when power is already up */
+	if (!pm_runtime_get_if_in_use(&client->dev))
+		return 0;
+
+	switch (ctrl->id) {
+	case V4L2_CID_ANALOGUE_GAIN:
+		ret = hi556_write_reg(hi556, HI556_REG_ANALOG_GAIN,
+				      HI556_REG_VALUE_16BIT, ctrl->val);
+		break;
+
+	case V4L2_CID_DIGITAL_GAIN:
+		ret = hi556_update_digital_gain(hi556, ctrl->val);
+		break;
+
+	case V4L2_CID_EXPOSURE:
+		ret = hi556_write_reg(hi556, HI556_REG_EXPOSURE,
+				      HI556_REG_VALUE_16BIT, ctrl->val);
+		break;
+
+	case V4L2_CID_VBLANK:
+		/* Update FLL that meets expected vertical blanking */
+		ret = hi556_write_reg(hi556, HI556_REG_FLL,
+				      HI556_REG_VALUE_16BIT,
+				      hi556->cur_mode->height + ctrl->val);
+		break;
+
+	case V4L2_CID_TEST_PATTERN:
+		ret = hi556_test_pattern(hi556, ctrl->val);
+		break;
+
+	default:
+		ret = -EINVAL;
+		break;
+	}
+
+	pm_runtime_put(&client->dev);
+
+	return ret;
+}
+
+static const struct v4l2_ctrl_ops hi556_ctrl_ops = {
+	.s_ctrl = hi556_set_ctrl,
+};
+
+static int hi556_init_controls(struct hi556 *hi556)
+{
+	struct v4l2_ctrl_handler *ctrl_hdlr;
+	s64 exposure_max, h_blank;
+	int ret;
+
+	ctrl_hdlr = &hi556->ctrl_handler;
+	ret = v4l2_ctrl_handler_init(ctrl_hdlr, 8);
+	if (ret)
+		return ret;
+
+	ctrl_hdlr->lock = &hi556->mutex;
+	hi556->link_freq = v4l2_ctrl_new_int_menu(ctrl_hdlr, &hi556_ctrl_ops,
+						  V4L2_CID_LINK_FREQ,
+					ARRAY_SIZE(link_freq_menu_items) - 1,
+					0, link_freq_menu_items);
+	if (hi556->link_freq)
+		hi556->link_freq->flags |= V4L2_CTRL_FLAG_READ_ONLY;
+
+	hi556->pixel_rate = v4l2_ctrl_new_std
+			    (ctrl_hdlr, &hi556_ctrl_ops,
+			     V4L2_CID_PIXEL_RATE, 0,
+			     to_pixel_rate(HI556_LINK_FREQ_437MHZ_INDEX),
+			     1,
+			     to_pixel_rate(HI556_LINK_FREQ_437MHZ_INDEX));
+	hi556->vblank = v4l2_ctrl_new_std(ctrl_hdlr, &hi556_ctrl_ops,
+					  V4L2_CID_VBLANK,
+					  hi556->cur_mode->fll_min -
+					  hi556->cur_mode->height,
+					  HI556_FLL_MAX -
+					  hi556->cur_mode->height, 1,
+					  hi556->cur_mode->fll_def -
+					  hi556->cur_mode->height);
+
+	h_blank = hi556->cur_mode->llp - hi556->cur_mode->width;
+
+	hi556->hblank = v4l2_ctrl_new_std(ctrl_hdlr, &hi556_ctrl_ops,
+					  V4L2_CID_HBLANK, h_blank, h_blank, 1,
+					  h_blank);
+	if (hi556->hblank)
+		hi556->hblank->flags |= V4L2_CTRL_FLAG_READ_ONLY;
+
+	v4l2_ctrl_new_std(ctrl_hdlr, &hi556_ctrl_ops, V4L2_CID_ANALOGUE_GAIN,
+			  HI556_ANAL_GAIN_MIN, HI556_ANAL_GAIN_MAX,
+			  HI556_ANAL_GAIN_STEP, HI556_ANAL_GAIN_MIN);
+	v4l2_ctrl_new_std(ctrl_hdlr, &hi556_ctrl_ops, V4L2_CID_DIGITAL_GAIN,
+			  HI556_DGTL_GAIN_MIN, HI556_DGTL_GAIN_MAX,
+			  HI556_DGTL_GAIN_STEP, HI556_DGTL_GAIN_DEFAULT);
+	exposure_max = hi556->cur_mode->fll_def - HI556_EXPOSURE_MAX_MARGIN;
+	hi556->exposure = v4l2_ctrl_new_std(ctrl_hdlr, &hi556_ctrl_ops,
+					    V4L2_CID_EXPOSURE,
+					    HI556_EXPOSURE_MIN, exposure_max,
+					    HI556_EXPOSURE_STEP,
+					    exposure_max);
+	v4l2_ctrl_new_std_menu_items(ctrl_hdlr, &hi556_ctrl_ops,
+				     V4L2_CID_TEST_PATTERN,
+				     ARRAY_SIZE(hi556_test_pattern_menu) - 1,
+				     0, 0, hi556_test_pattern_menu);
+	if (ctrl_hdlr->error)
+		return ctrl_hdlr->error;
+
+	hi556->sd.ctrl_handler = ctrl_hdlr;
+
+	return 0;
+}
+
+static void hi556_assign_pad_format(const struct hi556_mode *mode,
+				    struct v4l2_mbus_framefmt *fmt)
+{
+	fmt->width = mode->width;
+	fmt->height = mode->height;
+	fmt->code = MEDIA_BUS_FMT_SGRBG10_1X10;
+	fmt->field = V4L2_FIELD_NONE;
+}
+
+static int hi556_start_streaming(struct hi556 *hi556)
+{
+	struct i2c_client *client = v4l2_get_subdevdata(&hi556->sd);
+	const struct hi556_reg_list *reg_list;
+	int link_freq_index, ret;
+
+	link_freq_index = hi556->cur_mode->link_freq_index;
+	reg_list = &link_freq_configs[link_freq_index].reg_list;
+	ret = hi556_write_reg_list(hi556, reg_list);
+	if (ret) {
+		dev_err(&client->dev, "failed to set plls");
+		return ret;
+	}
+
+	reg_list = &hi556->cur_mode->reg_list;
+	ret = hi556_write_reg_list(hi556, reg_list);
+	if (ret) {
+		dev_err(&client->dev, "failed to set mode");
+		return ret;
+	}
+
+	ret = __v4l2_ctrl_handler_setup(hi556->sd.ctrl_handler);
+	if (ret)
+		return ret;
+
+	ret = hi556_write_reg(hi556, HI556_REG_MODE_SELECT,
+			      HI556_REG_VALUE_16BIT, HI556_MODE_STREAMING);
+
+	if (ret) {
+		dev_err(&client->dev, "failed to set stream");
+		return ret;
+	}
+
+	return 0;
+}
+
+static void hi556_stop_streaming(struct hi556 *hi556)
+{
+	struct i2c_client *client = v4l2_get_subdevdata(&hi556->sd);
+
+	if (hi556_write_reg(hi556, HI556_REG_MODE_SELECT,
+			    HI556_REG_VALUE_16BIT, HI556_MODE_STANDBY))
+		dev_err(&client->dev, "failed to set stream");
+}
+
+static int hi556_set_stream(struct v4l2_subdev *sd, int enable)
+{
+	struct hi556 *hi556 = to_hi556(sd);
+	struct i2c_client *client = v4l2_get_subdevdata(sd);
+	int ret = 0;
+
+	if (hi556->streaming == enable)
+		return 0;
+
+	mutex_lock(&hi556->mutex);
+	if (enable) {
+		ret = pm_runtime_get_sync(&client->dev);
+		if (ret < 0) {
+			pm_runtime_put_noidle(&client->dev);
+			mutex_unlock(&hi556->mutex);
+			return ret;
+		}
+
+		ret = hi556_start_streaming(hi556);
+		if (ret) {
+			enable = 0;
+			hi556_stop_streaming(hi556);
+			pm_runtime_put(&client->dev);
+		}
+	} else {
+		hi556_stop_streaming(hi556);
+		pm_runtime_put(&client->dev);
+	}
+
+	hi556->streaming = enable;
+	mutex_unlock(&hi556->mutex);
+
+	return ret;
+}
+
+static int __maybe_unused hi556_suspend(struct device *dev)
+{
+	struct i2c_client *client = to_i2c_client(dev);
+	struct v4l2_subdev *sd = i2c_get_clientdata(client);
+	struct hi556 *hi556 = to_hi556(sd);
+
+	mutex_lock(&hi556->mutex);
+	if (hi556->streaming)
+		hi556_stop_streaming(hi556);
+
+	mutex_unlock(&hi556->mutex);
+
+	return 0;
+}
+
+static int __maybe_unused hi556_resume(struct device *dev)
+{
+	struct i2c_client *client = to_i2c_client(dev);
+	struct v4l2_subdev *sd = i2c_get_clientdata(client);
+	struct hi556 *hi556 = to_hi556(sd);
+	int ret;
+
+	mutex_lock(&hi556->mutex);
+	if (hi556->streaming) {
+		ret = hi556_start_streaming(hi556);
+		if (ret)
+			goto error;
+	}
+
+	mutex_unlock(&hi556->mutex);
+
+	return 0;
+
+error:
+	hi556_stop_streaming(hi556);
+	hi556->streaming = 0;
+	mutex_unlock(&hi556->mutex);
+	return ret;
+}
+
+static int hi556_set_format(struct v4l2_subdev *sd,
+			    struct v4l2_subdev_pad_config *cfg,
+			    struct v4l2_subdev_format *fmt)
+{
+	struct hi556 *hi556 = to_hi556(sd);
+	const struct hi556_mode *mode;
+	s32 vblank_def, h_blank;
+
+	mode = v4l2_find_nearest_size(supported_modes,
+				      ARRAY_SIZE(supported_modes), width,
+				      height, fmt->format.width,
+				      fmt->format.height);
+
+	mutex_lock(&hi556->mutex);
+	hi556_assign_pad_format(mode, &fmt->format);
+	if (fmt->which == V4L2_SUBDEV_FORMAT_TRY) {
+		*v4l2_subdev_get_try_format(sd, cfg, fmt->pad) = fmt->format;
+	} else {
+		hi556->cur_mode = mode;
+		__v4l2_ctrl_s_ctrl(hi556->link_freq, mode->link_freq_index);
+		__v4l2_ctrl_s_ctrl_int64(hi556->pixel_rate,
+					 to_pixel_rate(mode->link_freq_index));
+
+		/* Update limits and set FPS to default */
+		vblank_def = mode->fll_def - mode->height;
+		__v4l2_ctrl_modify_range(hi556->vblank,
+					 mode->fll_min - mode->height,
+					 HI556_FLL_MAX - mode->height, 1,
+					 vblank_def);
+		__v4l2_ctrl_s_ctrl(hi556->vblank, vblank_def);
+
+		h_blank = hi556->cur_mode->llp - hi556->cur_mode->width;
+
+		__v4l2_ctrl_modify_range(hi556->hblank, h_blank, h_blank, 1,
+					 h_blank);
+	}
+
+	mutex_unlock(&hi556->mutex);
+
+	return 0;
+}
+
+static int hi556_get_format(struct v4l2_subdev *sd,
+			    struct v4l2_subdev_pad_config *cfg,
+			    struct v4l2_subdev_format *fmt)
+{
+	struct hi556 *hi556 = to_hi556(sd);
+
+	mutex_lock(&hi556->mutex);
+	if (fmt->which == V4L2_SUBDEV_FORMAT_TRY)
+		fmt->format = *v4l2_subdev_get_try_format(&hi556->sd, cfg,
+							  fmt->pad);
+	else
+		hi556_assign_pad_format(hi556->cur_mode, &fmt->format);
+
+	mutex_unlock(&hi556->mutex);
+
+	return 0;
+}
+
+static int hi556_enum_mbus_code(struct v4l2_subdev *sd,
+				struct v4l2_subdev_pad_config *cfg,
+				struct v4l2_subdev_mbus_code_enum *code)
+{
+	if (code->index > 0)
+		return -EINVAL;
+
+	code->code = MEDIA_BUS_FMT_SGRBG10_1X10;
+
+	return 0;
+}
+
+static int hi556_enum_frame_size(struct v4l2_subdev *sd,
+				 struct v4l2_subdev_pad_config *cfg,
+				 struct v4l2_subdev_frame_size_enum *fse)
+{
+	if (fse->index >= ARRAY_SIZE(supported_modes))
+		return -EINVAL;
+
+	if (fse->code != MEDIA_BUS_FMT_SGRBG10_1X10)
+		return -EINVAL;
+
+	fse->min_width = supported_modes[fse->index].width;
+	fse->max_width = fse->min_width;
+	fse->min_height = supported_modes[fse->index].height;
+	fse->max_height = fse->min_height;
+
+	return 0;
+}
+
+static int hi556_open(struct v4l2_subdev *sd, struct v4l2_subdev_fh *fh)
+{
+	struct hi556 *hi556 = to_hi556(sd);
+
+	mutex_lock(&hi556->mutex);
+	hi556_assign_pad_format(&supported_modes[0],
+				v4l2_subdev_get_try_format(sd, fh->pad, 0));
+	mutex_unlock(&hi556->mutex);
+
+	return 0;
+}
+
+static const struct v4l2_subdev_video_ops hi556_video_ops = {
+	.s_stream = hi556_set_stream,
+};
+
+static const struct v4l2_subdev_pad_ops hi556_pad_ops = {
+	.set_fmt = hi556_set_format,
+	.get_fmt = hi556_get_format,
+	.enum_mbus_code = hi556_enum_mbus_code,
+	.enum_frame_size = hi556_enum_frame_size,
+};
+
+static const struct v4l2_subdev_ops hi556_subdev_ops = {
+	.video = &hi556_video_ops,
+	.pad = &hi556_pad_ops,
+};
+
+static const struct media_entity_operations hi556_subdev_entity_ops = {
+	.link_validate = v4l2_subdev_link_validate,
+};
+
+static const struct v4l2_subdev_internal_ops hi556_internal_ops = {
+	.open = hi556_open,
+};
+
+static int hi556_identify_module(struct hi556 *hi556)
+{
+	struct i2c_client *client = v4l2_get_subdevdata(&hi556->sd);
+	int ret;
+	u32 val;
+
+	ret = hi556_read_reg(hi556, HI556_REG_CHIP_ID,
+			     HI556_REG_VALUE_16BIT, &val);
+	if (ret)
+		return ret;
+
+	if (val != HI556_CHIP_ID) {
+		dev_err(&client->dev, "chip id mismatch: %x!=%x",
+			HI556_CHIP_ID, val);
+		return -ENXIO;
+	}
+
+	return 0;
+}
+
+static int hi556_check_hwcfg(struct device *dev)
+{
+	struct fwnode_handle *ep;
+	struct fwnode_handle *fwnode = dev_fwnode(dev);
+	struct v4l2_fwnode_endpoint bus_cfg = {
+		.bus_type = V4L2_MBUS_CSI2_DPHY
+	};
+	u32 mclk;
+	int ret = 0;
+	unsigned int i, j;
+
+	if (!fwnode)
+		return -ENXIO;
+
+	ret = fwnode_property_read_u32(fwnode, "clock-frequency", &mclk);
+	if (ret) {
+		dev_err(dev, "can't get clock frequency");
+		return ret;
+	}
+
+	if (mclk != HI556_MCLK) {
+		dev_err(dev, "external clock %d is not supported", mclk);
+		return -EINVAL;
+	}
+
+	ep = fwnode_graph_get_next_endpoint(fwnode, NULL);
+	if (!ep)
+		return -ENXIO;
+
+	ret = v4l2_fwnode_endpoint_alloc_parse(ep, &bus_cfg);
+	fwnode_handle_put(ep);
+	if (ret)
+		return ret;
+
+	if (bus_cfg.bus.mipi_csi2.num_data_lanes != 2) {
+		dev_err(dev, "number of CSI2 data lanes %d is not supported",
+			bus_cfg.bus.mipi_csi2.num_data_lanes);
+		ret = -EINVAL;
+		goto check_hwcfg_error;
+	}
+
+	if (!bus_cfg.nr_of_link_frequencies) {
+		dev_err(dev, "no link frequencies defined");
+		ret = -EINVAL;
+		goto check_hwcfg_error;
+	}
+
+	for (i = 0; i < ARRAY_SIZE(link_freq_menu_items); i++) {
+		for (j = 0; j < bus_cfg.nr_of_link_frequencies; j++) {
+			if (link_freq_menu_items[i] ==
+				bus_cfg.link_frequencies[j])
+				break;
+		}
+
+		if (j == bus_cfg.nr_of_link_frequencies) {
+			dev_err(dev, "no link frequency %lld supported",
+				link_freq_menu_items[i]);
+			ret = -EINVAL;
+			goto check_hwcfg_error;
+		}
+	}
+
+check_hwcfg_error:
+	v4l2_fwnode_endpoint_free(&bus_cfg);
+
+	return ret;
+}
+
+static int hi556_remove(struct i2c_client *client)
+{
+	struct v4l2_subdev *sd = i2c_get_clientdata(client);
+	struct hi556 *hi556 = to_hi556(sd);
+
+	v4l2_async_unregister_subdev(sd);
+	media_entity_cleanup(&sd->entity);
+	v4l2_ctrl_handler_free(sd->ctrl_handler);
+	pm_runtime_disable(&client->dev);
+	mutex_destroy(&hi556->mutex);
+
+	return 0;
+}
+
+static int hi556_probe(struct i2c_client *client)
+{
+	struct hi556 *hi556;
+	int ret;
+
+	ret = hi556_check_hwcfg(&client->dev);
+	if (ret) {
+		dev_err(&client->dev, "failed to check HW configuration: %d",
+			ret);
+		return ret;
+	}
+
+	hi556 = devm_kzalloc(&client->dev, sizeof(*hi556), GFP_KERNEL);
+	if (!hi556)
+		return -ENOMEM;
+
+	v4l2_i2c_subdev_init(&hi556->sd, client, &hi556_subdev_ops);
+	ret = hi556_identify_module(hi556);
+	if (ret) {
+		dev_err(&client->dev, "failed to find sensor: %d", ret);
+		return ret;
+	}
+
+	mutex_init(&hi556->mutex);
+	hi556->cur_mode = &supported_modes[0];
+	ret = hi556_init_controls(hi556);
+	if (ret) {
+		dev_err(&client->dev, "failed to init controls: %d", ret);
+		goto probe_error_v4l2_ctrl_handler_free;
+	}
+
+	hi556->sd.internal_ops = &hi556_internal_ops;
+	hi556->sd.flags |= V4L2_SUBDEV_FL_HAS_DEVNODE;
+	hi556->sd.entity.ops = &hi556_subdev_entity_ops;
+	hi556->sd.entity.function = MEDIA_ENT_F_CAM_SENSOR;
+	hi556->pad.flags = MEDIA_PAD_FL_SOURCE;
+	ret = media_entity_pads_init(&hi556->sd.entity, 1, &hi556->pad);
+	if (ret) {
+		dev_err(&client->dev, "failed to init entity pads: %d", ret);
+		goto probe_error_v4l2_ctrl_handler_free;
+	}
+
+	ret = v4l2_async_register_subdev_sensor_common(&hi556->sd);
+	if (ret < 0) {
+		dev_err(&client->dev, "failed to register V4L2 subdev: %d",
+			ret);
+		goto probe_error_media_entity_cleanup;
+	}
+
+	pm_runtime_set_active(&client->dev);
+	pm_runtime_enable(&client->dev);
+	pm_runtime_idle(&client->dev);
+
+	return 0;
+
+probe_error_media_entity_cleanup:
+	media_entity_cleanup(&hi556->sd.entity);
+
+probe_error_v4l2_ctrl_handler_free:
+	v4l2_ctrl_handler_free(hi556->sd.ctrl_handler);
+	mutex_destroy(&hi556->mutex);
+
+	return ret;
+}
+
+static const struct dev_pm_ops hi556_pm_ops = {
+	SET_SYSTEM_SLEEP_PM_OPS(hi556_suspend, hi556_resume)
+};
+
+#ifdef CONFIG_ACPI
+static const struct acpi_device_id hi556_acpi_ids[] = {
+	{"INT3537"},
+	{}
+};
+
+MODULE_DEVICE_TABLE(acpi, hi556_acpi_ids);
+#endif
+
+static struct i2c_driver hi556_i2c_driver = {
+	.driver = {
+		.name = "hi556",
+		.pm = &hi556_pm_ops,
+		.acpi_match_table = ACPI_PTR(hi556_acpi_ids),
+	},
+	.probe_new = hi556_probe,
+	.remove = hi556_remove,
+};
+
+module_i2c_driver(hi556_i2c_driver);
+
+MODULE_AUTHOR("Shawn Tu <shawnx.tu@intel.com>");
+MODULE_DESCRIPTION("Hynix HI556 sensor driver");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/media/i2c/imx214.c b/drivers/media/i2c/imx214.c
index 159a3a604f0e..adcaaa8c86d1 100644
--- a/drivers/media/i2c/imx214.c
+++ b/drivers/media/i2c/imx214.c
@@ -47,6 +47,7 @@ struct imx214 {
 	struct v4l2_ctrl *pixel_rate;
 	struct v4l2_ctrl *link_freq;
 	struct v4l2_ctrl *exposure;
+	struct v4l2_ctrl *unit_size;
 
 	struct regulator_bulk_data	supplies[IMX214_NUM_SUPPLIES];
 
@@ -948,6 +949,10 @@ static int imx214_probe(struct i2c_client *client)
 	static const s64 link_freq[] = {
 		IMX214_DEFAULT_LINK_FREQ,
 	};
+	static const struct v4l2_area unit_size = {
+		.width = 1120,
+		.height = 1120,
+	};
 	int ret;
 
 	ret = imx214_parse_fwnode(dev);
@@ -1029,6 +1034,10 @@ static int imx214_probe(struct i2c_client *client)
 					     V4L2_CID_EXPOSURE,
 					     0, 3184, 1, 0x0c70);
 
+	imx214->unit_size = v4l2_ctrl_new_std_compound(&imx214->ctrls,
+				NULL,
+				V4L2_CID_UNIT_CELL_SIZE,
+				v4l2_ctrl_ptr_create((void *)&unit_size));
 	ret = imx214->ctrls.error;
 	if (ret) {
 		dev_err(&client->dev, "%s control init failed (%d)\n",
diff --git a/drivers/media/i2c/imx290.c b/drivers/media/i2c/imx290.c
new file mode 100644
index 000000000000..f7678e5a5d87
--- /dev/null
+++ b/drivers/media/i2c/imx290.c
@@ -0,0 +1,884 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Sony IMX290 CMOS Image Sensor Driver
+ *
+ * Copyright (C) 2019 FRAMOS GmbH.
+ *
+ * Copyright (C) 2019 Linaro Ltd.
+ * Author: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
+ */
+
+#include <linux/clk.h>
+#include <linux/delay.h>
+#include <linux/gpio/consumer.h>
+#include <linux/i2c.h>
+#include <linux/module.h>
+#include <linux/pm_runtime.h>
+#include <linux/regmap.h>
+#include <linux/regulator/consumer.h>
+#include <media/media-entity.h>
+#include <media/v4l2-ctrls.h>
+#include <media/v4l2-device.h>
+#include <media/v4l2-fwnode.h>
+#include <media/v4l2-subdev.h>
+
+#define IMX290_STANDBY 0x3000
+#define IMX290_REGHOLD 0x3001
+#define IMX290_XMSTA 0x3002
+#define IMX290_GAIN 0x3014
+
+#define IMX290_DEFAULT_LINK_FREQ 445500000
+
+static const char * const imx290_supply_name[] = {
+	"vdda",
+	"vddd",
+	"vdddo",
+};
+
+#define IMX290_NUM_SUPPLIES ARRAY_SIZE(imx290_supply_name)
+
+struct imx290_regval {
+	u16 reg;
+	u8 val;
+};
+
+struct imx290_mode {
+	u32 width;
+	u32 height;
+	u32 pixel_rate;
+	u32 link_freq_index;
+
+	const struct imx290_regval *data;
+	u32 data_size;
+};
+
+struct imx290 {
+	struct device *dev;
+	struct clk *xclk;
+	struct regmap *regmap;
+
+	struct v4l2_subdev sd;
+	struct v4l2_fwnode_endpoint ep;
+	struct media_pad pad;
+	struct v4l2_mbus_framefmt current_format;
+	const struct imx290_mode *current_mode;
+
+	struct regulator_bulk_data supplies[IMX290_NUM_SUPPLIES];
+	struct gpio_desc *rst_gpio;
+
+	struct v4l2_ctrl_handler ctrls;
+	struct v4l2_ctrl *link_freq;
+	struct v4l2_ctrl *pixel_rate;
+
+	struct mutex lock;
+};
+
+struct imx290_pixfmt {
+	u32 code;
+};
+
+static const struct imx290_pixfmt imx290_formats[] = {
+	{ MEDIA_BUS_FMT_SRGGB10_1X10 },
+};
+
+static const struct regmap_config imx290_regmap_config = {
+	.reg_bits = 16,
+	.val_bits = 8,
+	.cache_type = REGCACHE_RBTREE,
+};
+
+static const struct imx290_regval imx290_global_init_settings[] = {
+	{ 0x3007, 0x00 },
+	{ 0x3009, 0x00 },
+	{ 0x3018, 0x65 },
+	{ 0x3019, 0x04 },
+	{ 0x301a, 0x00 },
+	{ 0x3443, 0x03 },
+	{ 0x3444, 0x20 },
+	{ 0x3445, 0x25 },
+	{ 0x3407, 0x03 },
+	{ 0x303a, 0x0c },
+	{ 0x3040, 0x00 },
+	{ 0x3041, 0x00 },
+	{ 0x303c, 0x00 },
+	{ 0x303d, 0x00 },
+	{ 0x3042, 0x9c },
+	{ 0x3043, 0x07 },
+	{ 0x303e, 0x49 },
+	{ 0x303f, 0x04 },
+	{ 0x304b, 0x0a },
+	{ 0x300f, 0x00 },
+	{ 0x3010, 0x21 },
+	{ 0x3012, 0x64 },
+	{ 0x3016, 0x09 },
+	{ 0x3070, 0x02 },
+	{ 0x3071, 0x11 },
+	{ 0x309b, 0x10 },
+	{ 0x309c, 0x22 },
+	{ 0x30a2, 0x02 },
+	{ 0x30a6, 0x20 },
+	{ 0x30a8, 0x20 },
+	{ 0x30aa, 0x20 },
+	{ 0x30ac, 0x20 },
+	{ 0x30b0, 0x43 },
+	{ 0x3119, 0x9e },
+	{ 0x311c, 0x1e },
+	{ 0x311e, 0x08 },
+	{ 0x3128, 0x05 },
+	{ 0x313d, 0x83 },
+	{ 0x3150, 0x03 },
+	{ 0x317e, 0x00 },
+	{ 0x32b8, 0x50 },
+	{ 0x32b9, 0x10 },
+	{ 0x32ba, 0x00 },
+	{ 0x32bb, 0x04 },
+	{ 0x32c8, 0x50 },
+	{ 0x32c9, 0x10 },
+	{ 0x32ca, 0x00 },
+	{ 0x32cb, 0x04 },
+	{ 0x332c, 0xd3 },
+	{ 0x332d, 0x10 },
+	{ 0x332e, 0x0d },
+	{ 0x3358, 0x06 },
+	{ 0x3359, 0xe1 },
+	{ 0x335a, 0x11 },
+	{ 0x3360, 0x1e },
+	{ 0x3361, 0x61 },
+	{ 0x3362, 0x10 },
+	{ 0x33b0, 0x50 },
+	{ 0x33b2, 0x1a },
+	{ 0x33b3, 0x04 },
+};
+
+static const struct imx290_regval imx290_1080p_settings[] = {
+	/* mode settings */
+	{ 0x3007, 0x00 },
+	{ 0x303a, 0x0c },
+	{ 0x3414, 0x0a },
+	{ 0x3472, 0x80 },
+	{ 0x3473, 0x07 },
+	{ 0x3418, 0x38 },
+	{ 0x3419, 0x04 },
+	{ 0x3012, 0x64 },
+	{ 0x3013, 0x00 },
+	{ 0x305c, 0x18 },
+	{ 0x305d, 0x03 },
+	{ 0x305e, 0x20 },
+	{ 0x305f, 0x01 },
+	{ 0x315e, 0x1a },
+	{ 0x3164, 0x1a },
+	{ 0x3480, 0x49 },
+	/* data rate settings */
+	{ 0x3009, 0x01 },
+	{ 0x3405, 0x10 },
+	{ 0x3446, 0x57 },
+	{ 0x3447, 0x00 },
+	{ 0x3448, 0x37 },
+	{ 0x3449, 0x00 },
+	{ 0x344a, 0x1f },
+	{ 0x344b, 0x00 },
+	{ 0x344c, 0x1f },
+	{ 0x344d, 0x00 },
+	{ 0x344e, 0x1f },
+	{ 0x344f, 0x00 },
+	{ 0x3450, 0x77 },
+	{ 0x3451, 0x00 },
+	{ 0x3452, 0x1f },
+	{ 0x3453, 0x00 },
+	{ 0x3454, 0x17 },
+	{ 0x3455, 0x00 },
+	{ 0x301c, 0x98 },
+	{ 0x301d, 0x08 },
+};
+
+static const struct imx290_regval imx290_720p_settings[] = {
+	/* mode settings */
+	{ 0x3007, 0x10 },
+	{ 0x303a, 0x06 },
+	{ 0x3414, 0x04 },
+	{ 0x3472, 0x00 },
+	{ 0x3473, 0x05 },
+	{ 0x3418, 0xd0 },
+	{ 0x3419, 0x02 },
+	{ 0x3012, 0x64 },
+	{ 0x3013, 0x00 },
+	{ 0x305c, 0x20 },
+	{ 0x305d, 0x00 },
+	{ 0x305e, 0x20 },
+	{ 0x305f, 0x01 },
+	{ 0x315e, 0x1a },
+	{ 0x3164, 0x1a },
+	{ 0x3480, 0x49 },
+	/* data rate settings */
+	{ 0x3009, 0x01 },
+	{ 0x3405, 0x10 },
+	{ 0x3446, 0x4f },
+	{ 0x3447, 0x00 },
+	{ 0x3448, 0x2f },
+	{ 0x3449, 0x00 },
+	{ 0x344a, 0x17 },
+	{ 0x344b, 0x00 },
+	{ 0x344c, 0x17 },
+	{ 0x344d, 0x00 },
+	{ 0x344e, 0x17 },
+	{ 0x344f, 0x00 },
+	{ 0x3450, 0x57 },
+	{ 0x3451, 0x00 },
+	{ 0x3452, 0x17 },
+	{ 0x3453, 0x00 },
+	{ 0x3454, 0x17 },
+	{ 0x3455, 0x00 },
+	{ 0x301c, 0xe4 },
+	{ 0x301d, 0x0c },
+};
+
+static const struct imx290_regval imx290_10bit_settings[] = {
+	{ 0x3005, 0x00},
+	{ 0x3046, 0x00},
+	{ 0x3129, 0x1d},
+	{ 0x317c, 0x12},
+	{ 0x31ec, 0x37},
+	{ 0x3441, 0x0a},
+	{ 0x3442, 0x0a},
+	{ 0x300a, 0x3c},
+	{ 0x300b, 0x00},
+};
+
+/* supported link frequencies */
+static const s64 imx290_link_freq[] = {
+	IMX290_DEFAULT_LINK_FREQ,
+};
+
+/* Mode configs */
+static const struct imx290_mode imx290_modes[] = {
+	{
+		.width = 1920,
+		.height = 1080,
+		.data = imx290_1080p_settings,
+		.data_size = ARRAY_SIZE(imx290_1080p_settings),
+		.pixel_rate = 178200000,
+		.link_freq_index = 0,
+	},
+	{
+		.width = 1280,
+		.height = 720,
+		.data = imx290_720p_settings,
+		.data_size = ARRAY_SIZE(imx290_720p_settings),
+		.pixel_rate = 178200000,
+		.link_freq_index = 0,
+	},
+};
+
+static inline struct imx290 *to_imx290(struct v4l2_subdev *_sd)
+{
+	return container_of(_sd, struct imx290, sd);
+}
+
+static inline int imx290_read_reg(struct imx290 *imx290, u16 addr, u8 *value)
+{
+	unsigned int regval;
+	int ret;
+
+	ret = regmap_read(imx290->regmap, addr, &regval);
+	if (ret) {
+		dev_err(imx290->dev, "I2C read failed for addr: %x\n", addr);
+		return ret;
+	}
+
+	*value = regval & 0xff;
+
+	return 0;
+}
+
+static int imx290_write_reg(struct imx290 *imx290, u16 addr, u8 value)
+{
+	int ret;
+
+	ret = regmap_write(imx290->regmap, addr, value);
+	if (ret) {
+		dev_err(imx290->dev, "I2C write failed for addr: %x\n", addr);
+		return ret;
+	}
+
+	return ret;
+}
+
+static int imx290_set_register_array(struct imx290 *imx290,
+				     const struct imx290_regval *settings,
+				     unsigned int num_settings)
+{
+	unsigned int i;
+	int ret;
+
+	for (i = 0; i < num_settings; ++i, ++settings) {
+		ret = imx290_write_reg(imx290, settings->reg, settings->val);
+		if (ret < 0)
+			return ret;
+
+		/* Settle time is 10ms for all registers */
+		msleep(10);
+	}
+
+	return 0;
+}
+
+static int imx290_write_buffered_reg(struct imx290 *imx290, u16 address_low,
+				     u8 nr_regs, u32 value)
+{
+	unsigned int i;
+	int ret;
+
+	ret = imx290_write_reg(imx290, IMX290_REGHOLD, 0x01);
+	if (ret) {
+		dev_err(imx290->dev, "Error setting hold register\n");
+		return ret;
+	}
+
+	for (i = 0; i < nr_regs; i++) {
+		ret = imx290_write_reg(imx290, address_low + i,
+				       (u8)(value >> (i * 8)));
+		if (ret) {
+			dev_err(imx290->dev, "Error writing buffered registers\n");
+			return ret;
+		}
+	}
+
+	ret = imx290_write_reg(imx290, IMX290_REGHOLD, 0x00);
+	if (ret) {
+		dev_err(imx290->dev, "Error setting hold register\n");
+		return ret;
+	}
+
+	return ret;
+}
+
+static int imx290_set_gain(struct imx290 *imx290, u32 value)
+{
+	int ret;
+
+	ret = imx290_write_buffered_reg(imx290, IMX290_GAIN, 1, value);
+	if (ret)
+		dev_err(imx290->dev, "Unable to write gain\n");
+
+	return ret;
+}
+
+/* Stop streaming */
+static int imx290_stop_streaming(struct imx290 *imx290)
+{
+	int ret;
+
+	ret = imx290_write_reg(imx290, IMX290_STANDBY, 0x01);
+	if (ret < 0)
+		return ret;
+
+	msleep(30);
+
+	return imx290_write_reg(imx290, IMX290_XMSTA, 0x01);
+}
+
+static int imx290_set_ctrl(struct v4l2_ctrl *ctrl)
+{
+	struct imx290 *imx290 = container_of(ctrl->handler,
+					     struct imx290, ctrls);
+	int ret = 0;
+
+	/* V4L2 controls values will be applied only when power is already up */
+	if (!pm_runtime_get_if_in_use(imx290->dev))
+		return 0;
+
+	switch (ctrl->id) {
+	case V4L2_CID_GAIN:
+		ret = imx290_set_gain(imx290, ctrl->val);
+		break;
+	default:
+		ret = -EINVAL;
+		break;
+	}
+
+	pm_runtime_put(imx290->dev);
+
+	return ret;
+}
+
+static const struct v4l2_ctrl_ops imx290_ctrl_ops = {
+	.s_ctrl = imx290_set_ctrl,
+};
+
+static int imx290_enum_mbus_code(struct v4l2_subdev *sd,
+				 struct v4l2_subdev_pad_config *cfg,
+				 struct v4l2_subdev_mbus_code_enum *code)
+{
+	if (code->index >= ARRAY_SIZE(imx290_formats))
+		return -EINVAL;
+
+	code->code = imx290_formats[code->index].code;
+
+	return 0;
+}
+
+static int imx290_get_fmt(struct v4l2_subdev *sd,
+			  struct v4l2_subdev_pad_config *cfg,
+			  struct v4l2_subdev_format *fmt)
+{
+	struct imx290 *imx290 = to_imx290(sd);
+	struct v4l2_mbus_framefmt *framefmt;
+
+	mutex_lock(&imx290->lock);
+
+	if (fmt->which == V4L2_SUBDEV_FORMAT_TRY)
+		framefmt = v4l2_subdev_get_try_format(&imx290->sd, cfg,
+						      fmt->pad);
+	else
+		framefmt = &imx290->current_format;
+
+	fmt->format = *framefmt;
+
+	mutex_unlock(&imx290->lock);
+
+	return 0;
+}
+
+static int imx290_set_fmt(struct v4l2_subdev *sd,
+			  struct v4l2_subdev_pad_config *cfg,
+		      struct v4l2_subdev_format *fmt)
+{
+	struct imx290 *imx290 = to_imx290(sd);
+	const struct imx290_mode *mode;
+	struct v4l2_mbus_framefmt *format;
+	unsigned int i;
+
+	mutex_lock(&imx290->lock);
+
+	mode = v4l2_find_nearest_size(imx290_modes,
+				      ARRAY_SIZE(imx290_modes),
+				      width, height,
+				      fmt->format.width, fmt->format.height);
+
+	fmt->format.width = mode->width;
+	fmt->format.height = mode->height;
+
+	for (i = 0; i < ARRAY_SIZE(imx290_formats); i++)
+		if (imx290_formats[i].code == fmt->format.code)
+			break;
+
+	if (i >= ARRAY_SIZE(imx290_formats))
+		i = 0;
+
+	fmt->format.code = imx290_formats[i].code;
+	fmt->format.field = V4L2_FIELD_NONE;
+
+	if (fmt->which == V4L2_SUBDEV_FORMAT_TRY) {
+		format = v4l2_subdev_get_try_format(sd, cfg, fmt->pad);
+	} else {
+		format = &imx290->current_format;
+		__v4l2_ctrl_s_ctrl(imx290->link_freq, mode->link_freq_index);
+		__v4l2_ctrl_s_ctrl_int64(imx290->pixel_rate, mode->pixel_rate);
+
+		imx290->current_mode = mode;
+	}
+
+	*format = fmt->format;
+
+	mutex_unlock(&imx290->lock);
+
+	return 0;
+}
+
+static int imx290_entity_init_cfg(struct v4l2_subdev *subdev,
+				  struct v4l2_subdev_pad_config *cfg)
+{
+	struct v4l2_subdev_format fmt = { 0 };
+
+	fmt.which = cfg ? V4L2_SUBDEV_FORMAT_TRY : V4L2_SUBDEV_FORMAT_ACTIVE;
+	fmt.format.width = 1920;
+	fmt.format.height = 1080;
+
+	imx290_set_fmt(subdev, cfg, &fmt);
+
+	return 0;
+}
+
+static int imx290_write_current_format(struct imx290 *imx290,
+				       struct v4l2_mbus_framefmt *format)
+{
+	int ret;
+
+	switch (format->code) {
+	case MEDIA_BUS_FMT_SRGGB10_1X10:
+		ret = imx290_set_register_array(imx290, imx290_10bit_settings,
+						ARRAY_SIZE(
+							imx290_10bit_settings));
+		if (ret < 0) {
+			dev_err(imx290->dev, "Could not set format registers\n");
+			return ret;
+		}
+		break;
+	default:
+		dev_err(imx290->dev, "Unknown pixel format\n");
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+/* Start streaming */
+static int imx290_start_streaming(struct imx290 *imx290)
+{
+	int ret;
+
+	/* Set init register settings */
+	ret = imx290_set_register_array(imx290, imx290_global_init_settings,
+					ARRAY_SIZE(
+						imx290_global_init_settings));
+	if (ret < 0) {
+		dev_err(imx290->dev, "Could not set init registers\n");
+		return ret;
+	}
+
+	/* Set current frame format */
+	ret = imx290_write_current_format(imx290, &imx290->current_format);
+	if (ret < 0) {
+		dev_err(imx290->dev, "Could not set frame format\n");
+		return ret;
+	}
+
+	/* Apply default values of current mode */
+	ret = imx290_set_register_array(imx290, imx290->current_mode->data,
+					imx290->current_mode->data_size);
+	if (ret < 0) {
+		dev_err(imx290->dev, "Could not set current mode\n");
+		return ret;
+	}
+
+	/* Apply customized values from user */
+	ret = v4l2_ctrl_handler_setup(imx290->sd.ctrl_handler);
+	if (ret) {
+		dev_err(imx290->dev, "Could not sync v4l2 controls\n");
+		return ret;
+	}
+
+	ret = imx290_write_reg(imx290, IMX290_STANDBY, 0x00);
+	if (ret < 0)
+		return ret;
+
+	msleep(30);
+
+	/* Start streaming */
+	return imx290_write_reg(imx290, IMX290_XMSTA, 0x00);
+}
+
+static int imx290_set_stream(struct v4l2_subdev *sd, int enable)
+{
+	struct imx290 *imx290 = to_imx290(sd);
+	int ret = 0;
+
+	if (enable) {
+		ret = pm_runtime_get_sync(imx290->dev);
+		if (ret < 0) {
+			pm_runtime_put_noidle(imx290->dev);
+			goto unlock_and_return;
+		}
+
+		ret = imx290_start_streaming(imx290);
+		if (ret) {
+			dev_err(imx290->dev, "Start stream failed\n");
+			pm_runtime_put(imx290->dev);
+			goto unlock_and_return;
+		}
+	} else {
+		imx290_stop_streaming(imx290);
+		pm_runtime_put(imx290->dev);
+	}
+
+unlock_and_return:
+
+	return ret;
+}
+
+static int imx290_get_regulators(struct device *dev, struct imx290 *imx290)
+{
+	unsigned int i;
+
+	for (i = 0; i < IMX290_NUM_SUPPLIES; i++)
+		imx290->supplies[i].supply = imx290_supply_name[i];
+
+	return devm_regulator_bulk_get(dev, IMX290_NUM_SUPPLIES,
+				       imx290->supplies);
+}
+
+static int imx290_power_on(struct device *dev)
+{
+	struct i2c_client *client = to_i2c_client(dev);
+	struct v4l2_subdev *sd = i2c_get_clientdata(client);
+	struct imx290 *imx290 = to_imx290(sd);
+	int ret;
+
+	ret = clk_prepare_enable(imx290->xclk);
+	if (ret) {
+		dev_err(imx290->dev, "Failed to enable clock\n");
+		return ret;
+	}
+
+	ret = regulator_bulk_enable(IMX290_NUM_SUPPLIES, imx290->supplies);
+	if (ret) {
+		dev_err(imx290->dev, "Failed to enable regulators\n");
+		clk_disable_unprepare(imx290->xclk);
+		return ret;
+	}
+
+	usleep_range(1, 2);
+	gpiod_set_value_cansleep(imx290->rst_gpio, 1);
+	usleep_range(30000, 31000);
+
+	return 0;
+}
+
+static int imx290_power_off(struct device *dev)
+{
+	struct i2c_client *client = to_i2c_client(dev);
+	struct v4l2_subdev *sd = i2c_get_clientdata(client);
+	struct imx290 *imx290 = to_imx290(sd);
+
+	clk_disable_unprepare(imx290->xclk);
+	gpiod_set_value_cansleep(imx290->rst_gpio, 0);
+	regulator_bulk_disable(IMX290_NUM_SUPPLIES, imx290->supplies);
+
+	return 0;
+}
+
+static const struct dev_pm_ops imx290_pm_ops = {
+	SET_RUNTIME_PM_OPS(imx290_power_on, imx290_power_off, NULL)
+};
+
+static const struct v4l2_subdev_video_ops imx290_video_ops = {
+	.s_stream = imx290_set_stream,
+};
+
+static const struct v4l2_subdev_pad_ops imx290_pad_ops = {
+	.init_cfg = imx290_entity_init_cfg,
+	.enum_mbus_code = imx290_enum_mbus_code,
+	.get_fmt = imx290_get_fmt,
+	.set_fmt = imx290_set_fmt,
+};
+
+static const struct v4l2_subdev_ops imx290_subdev_ops = {
+	.video = &imx290_video_ops,
+	.pad = &imx290_pad_ops,
+};
+
+static const struct media_entity_operations imx290_subdev_entity_ops = {
+	.link_validate = v4l2_subdev_link_validate,
+};
+
+static int imx290_probe(struct i2c_client *client)
+{
+	struct device *dev = &client->dev;
+	struct fwnode_handle *endpoint;
+	struct imx290 *imx290;
+	u32 xclk_freq;
+	int ret;
+
+	imx290 = devm_kzalloc(dev, sizeof(*imx290), GFP_KERNEL);
+	if (!imx290)
+		return -ENOMEM;
+
+	imx290->dev = dev;
+	imx290->regmap = devm_regmap_init_i2c(client, &imx290_regmap_config);
+	if (IS_ERR(imx290->regmap)) {
+		dev_err(dev, "Unable to initialize I2C\n");
+		return -ENODEV;
+	}
+
+	endpoint = fwnode_graph_get_next_endpoint(dev_fwnode(dev), NULL);
+	if (!endpoint) {
+		dev_err(dev, "Endpoint node not found\n");
+		return -EINVAL;
+	}
+
+	ret = v4l2_fwnode_endpoint_alloc_parse(endpoint, &imx290->ep);
+	fwnode_handle_put(endpoint);
+	if (ret) {
+		dev_err(dev, "Parsing endpoint node failed\n");
+		goto free_err;
+	}
+
+	if (!imx290->ep.nr_of_link_frequencies) {
+		dev_err(dev, "link-frequency property not found in DT\n");
+		ret = -EINVAL;
+		goto free_err;
+	}
+
+	if (imx290->ep.link_frequencies[0] != IMX290_DEFAULT_LINK_FREQ) {
+		dev_err(dev, "Unsupported link frequency\n");
+		ret = -EINVAL;
+		goto free_err;
+	}
+
+	/* Only CSI2 is supported for now */
+	if (imx290->ep.bus_type != V4L2_MBUS_CSI2_DPHY) {
+		dev_err(dev, "Unsupported bus type, should be CSI2\n");
+		ret = -EINVAL;
+		goto free_err;
+	}
+
+	/* Set default mode to max resolution */
+	imx290->current_mode = &imx290_modes[0];
+
+	/* get system clock (xclk) */
+	imx290->xclk = devm_clk_get(dev, "xclk");
+	if (IS_ERR(imx290->xclk)) {
+		dev_err(dev, "Could not get xclk");
+		ret = PTR_ERR(imx290->xclk);
+		goto free_err;
+	}
+
+	ret = fwnode_property_read_u32(dev_fwnode(dev), "clock-frequency",
+				       &xclk_freq);
+	if (ret) {
+		dev_err(dev, "Could not get xclk frequency\n");
+		goto free_err;
+	}
+
+	/* external clock must be 37.125 MHz */
+	if (xclk_freq != 37125000) {
+		dev_err(dev, "External clock frequency %u is not supported\n",
+			xclk_freq);
+		ret = -EINVAL;
+		goto free_err;
+	}
+
+	ret = clk_set_rate(imx290->xclk, xclk_freq);
+	if (ret) {
+		dev_err(dev, "Could not set xclk frequency\n");
+		goto free_err;
+	}
+
+	ret = imx290_get_regulators(dev, imx290);
+	if (ret < 0) {
+		dev_err(dev, "Cannot get regulators\n");
+		goto free_err;
+	}
+
+	imx290->rst_gpio = devm_gpiod_get_optional(dev, "reset", GPIOD_ASIS);
+	if (IS_ERR(imx290->rst_gpio)) {
+		dev_err(dev, "Cannot get reset gpio\n");
+		ret = PTR_ERR(imx290->rst_gpio);
+		goto free_err;
+	}
+
+	mutex_init(&imx290->lock);
+
+	v4l2_ctrl_handler_init(&imx290->ctrls, 3);
+
+	v4l2_ctrl_new_std(&imx290->ctrls, &imx290_ctrl_ops,
+			  V4L2_CID_GAIN, 0, 72, 1, 0);
+	imx290->link_freq =
+		v4l2_ctrl_new_int_menu(&imx290->ctrls,
+				       &imx290_ctrl_ops,
+				       V4L2_CID_LINK_FREQ,
+				       ARRAY_SIZE(imx290_link_freq) - 1,
+				       0, imx290_link_freq);
+	if (imx290->link_freq)
+		imx290->link_freq->flags |= V4L2_CTRL_FLAG_READ_ONLY;
+
+	imx290->pixel_rate = v4l2_ctrl_new_std(&imx290->ctrls, &imx290_ctrl_ops,
+					       V4L2_CID_PIXEL_RATE, 1,
+					       INT_MAX, 1,
+					       imx290_modes[0].pixel_rate);
+
+	imx290->sd.ctrl_handler = &imx290->ctrls;
+
+	if (imx290->ctrls.error) {
+		dev_err(dev, "Control initialization error %d\n",
+			imx290->ctrls.error);
+		ret = imx290->ctrls.error;
+		goto free_ctrl;
+	}
+
+	v4l2_i2c_subdev_init(&imx290->sd, client, &imx290_subdev_ops);
+	imx290->sd.flags |= V4L2_SUBDEV_FL_HAS_DEVNODE;
+	imx290->sd.dev = &client->dev;
+	imx290->sd.entity.ops = &imx290_subdev_entity_ops;
+	imx290->sd.entity.function = MEDIA_ENT_F_CAM_SENSOR;
+
+	imx290->pad.flags = MEDIA_PAD_FL_SOURCE;
+	ret = media_entity_pads_init(&imx290->sd.entity, 1, &imx290->pad);
+	if (ret < 0) {
+		dev_err(dev, "Could not register media entity\n");
+		goto free_ctrl;
+	}
+
+	ret = v4l2_async_register_subdev(&imx290->sd);
+	if (ret < 0) {
+		dev_err(dev, "Could not register v4l2 device\n");
+		goto free_entity;
+	}
+
+	/* Power on the device to match runtime PM state below */
+	ret = imx290_power_on(dev);
+	if (ret < 0) {
+		dev_err(dev, "Could not power on the device\n");
+		goto free_entity;
+	}
+
+	pm_runtime_set_active(dev);
+	pm_runtime_enable(dev);
+	pm_runtime_idle(dev);
+
+	v4l2_fwnode_endpoint_free(&imx290->ep);
+
+	return 0;
+
+free_entity:
+	media_entity_cleanup(&imx290->sd.entity);
+free_ctrl:
+	v4l2_ctrl_handler_free(&imx290->ctrls);
+	mutex_destroy(&imx290->lock);
+free_err:
+	v4l2_fwnode_endpoint_free(&imx290->ep);
+
+	return ret;
+}
+
+static int imx290_remove(struct i2c_client *client)
+{
+	struct v4l2_subdev *sd = i2c_get_clientdata(client);
+	struct imx290 *imx290 = to_imx290(sd);
+
+	v4l2_async_unregister_subdev(sd);
+	media_entity_cleanup(&sd->entity);
+	v4l2_ctrl_handler_free(sd->ctrl_handler);
+
+	mutex_destroy(&imx290->lock);
+
+	pm_runtime_disable(imx290->dev);
+	if (!pm_runtime_status_suspended(imx290->dev))
+		imx290_power_off(imx290->dev);
+	pm_runtime_set_suspended(imx290->dev);
+
+	return 0;
+}
+
+static const struct of_device_id imx290_of_match[] = {
+	{ .compatible = "sony,imx290" },
+	{ /* sentinel */ }
+};
+MODULE_DEVICE_TABLE(of, imx290_of_match);
+
+static struct i2c_driver imx290_i2c_driver = {
+	.probe_new  = imx290_probe,
+	.remove = imx290_remove,
+	.driver = {
+		.name  = "imx290",
+		.pm = &imx290_pm_ops,
+		.of_match_table = of_match_ptr(imx290_of_match),
+	},
+};
+
+module_i2c_driver(imx290_i2c_driver);
+
+MODULE_DESCRIPTION("Sony IMX290 CMOS Image Sensor Driver");
+MODULE_AUTHOR("FRAMOS GmbH");
+MODULE_AUTHOR("Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/media/i2c/lm3646.c b/drivers/media/i2c/lm3646.c
index d8a8853f9a2b..c76ccf67a909 100644
--- a/drivers/media/i2c/lm3646.c
+++ b/drivers/media/i2c/lm3646.c
@@ -134,7 +134,7 @@ static int lm3646_set_ctrl(struct v4l2_ctrl *ctrl)
 {
 	struct lm3646_flash *flash = to_lm3646_flash(ctrl);
 	unsigned int reg_val;
-	int rval = -EINVAL;
+	int rval;
 
 	switch (ctrl->id) {
 	case V4L2_CID_FLASH_LED_MODE:
diff --git a/drivers/media/i2c/max2175.c b/drivers/media/i2c/max2175.c
index 19a3ceea3bc2..506a30e69ced 100644
--- a/drivers/media/i2c/max2175.c
+++ b/drivers/media/i2c/max2175.c
@@ -591,8 +591,8 @@ static int max2175_set_lo_freq(struct max2175 *ctx, u32 lo_freq)
 		lo_freq *= lo_mult;
 
 	int_desired = lo_freq / ctx->xtal_freq;
-	frac_desired = div_u64((u64)(lo_freq % ctx->xtal_freq) << 20,
-			       ctx->xtal_freq);
+	frac_desired = div64_ul((u64)(lo_freq % ctx->xtal_freq) << 20,
+				ctx->xtal_freq);
 
 	/* Check CSM is not busy */
 	ret = max2175_poll_csm_ready(ctx);
diff --git a/drivers/media/i2c/max2175.h b/drivers/media/i2c/max2175.h
index 1ece587c153d..4c722ea3e5f1 100644
--- a/drivers/media/i2c/max2175.h
+++ b/drivers/media/i2c/max2175.h
@@ -1,5 +1,5 @@
-/* SPDX-License-Identifier: GPL-2.0
- *
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
  * Maxim Integrated MAX2175 RF to Bits tuner driver
  *
  * This driver & most of the hard coded values are based on the reference
diff --git a/drivers/media/i2c/mt9m001.c b/drivers/media/i2c/mt9m001.c
index 5613072908ac..210ea76adb53 100644
--- a/drivers/media/i2c/mt9m001.c
+++ b/drivers/media/i2c/mt9m001.c
@@ -167,7 +167,7 @@ static int multi_reg_write(struct i2c_client *client,
 
 static int mt9m001_init(struct i2c_client *client)
 {
-	const struct mt9m001_reg init_regs[] = {
+	static const struct mt9m001_reg init_regs[] = {
 		/*
 		 * Issue a soft reset. This returns all registers to their
 		 * default values.
diff --git a/drivers/media/i2c/ov2659.c b/drivers/media/i2c/ov2659.c
index f4ded0669ff9..42f64175a6df 100644
--- a/drivers/media/i2c/ov2659.c
+++ b/drivers/media/i2c/ov2659.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * Omnivision OV2659 CMOS Image Sensor driver
  *
@@ -5,46 +6,21 @@
  *
  * Benoit Parrot <bparrot@ti.com>
  * Lad, Prabhakar <prabhakar.csengg@gmail.com>
- *
- * This program is free software; you may redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; version 2 of the License.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
- * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
- * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
- * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
- * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
- * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
- * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
- * SOFTWARE.
  */
 
 #include <linux/clk.h>
 #include <linux/delay.h>
-#include <linux/err.h>
-#include <linux/init.h>
-#include <linux/interrupt.h>
-#include <linux/io.h>
+#include <linux/gpio/consumer.h>
 #include <linux/i2c.h>
-#include <linux/kernel.h>
-#include <linux/media.h>
 #include <linux/module.h>
-#include <linux/of.h>
 #include <linux/of_graph.h>
-#include <linux/slab.h>
-#include <linux/uaccess.h>
-#include <linux/videodev2.h>
+#include <linux/pm_runtime.h>
 
-#include <media/media-entity.h>
 #include <media/i2c/ov2659.h>
-#include <media/v4l2-common.h>
 #include <media/v4l2-ctrls.h>
-#include <media/v4l2-device.h>
 #include <media/v4l2-event.h>
 #include <media/v4l2-fwnode.h>
 #include <media/v4l2-image-sizes.h>
-#include <media/v4l2-mediabus.h>
 #include <media/v4l2-subdev.h>
 
 #define DRIVER_NAME "ov2659"
@@ -232,6 +208,10 @@ struct ov2659 {
 	struct sensor_register *format_ctrl_regs;
 	struct ov2659_pll_ctrl pll;
 	int streaming;
+	/* used to control the sensor PWDN pin */
+	struct gpio_desc *pwdn_gpio;
+	/* used to control the sensor RESETB pin */
+	struct gpio_desc *resetb_gpio;
 };
 
 static const struct sensor_register ov2659_init_regs[] = {
@@ -419,10 +399,14 @@ static struct sensor_register ov2659_720p[] = {
 	{ REG_TIMING_YINC, 0x11 },
 	{ REG_TIMING_VERT_FORMAT, 0x80 },
 	{ REG_TIMING_HORIZ_FORMAT, 0x00 },
+	{ 0x370a, 0x12 },
 	{ 0x3a03, 0xe8 },
 	{ 0x3a09, 0x6f },
 	{ 0x3a0b, 0x5d },
 	{ 0x3a15, 0x9a },
+	{ REG_VFIFO_READ_START_H, 0x00 },
+	{ REG_VFIFO_READ_START_L, 0x80 },
+	{ REG_ISP_CTRL02, 0x00 },
 	{ REG_NULL, 0x00 },
 };
 
@@ -661,7 +645,7 @@ static struct sensor_register ov2659_vga[] = {
 	{ REG_TIMING_HORIZ_FORMAT, 0x01 },
 	{ 0x370a, 0x52 },
 	{ REG_VFIFO_READ_START_H, 0x00 },
-	{ REG_VFIFO_READ_START_L, 0x80 },
+	{ REG_VFIFO_READ_START_L, 0xa0 },
 	{ REG_ISP_CTRL02, 0x10 },
 	{ REG_NULL, 0x00 },
 };
@@ -709,7 +693,7 @@ static  struct sensor_register ov2659_qvga[] = {
 	{ REG_TIMING_HORIZ_FORMAT, 0x01 },
 	{ 0x370a, 0x52 },
 	{ REG_VFIFO_READ_START_H, 0x00 },
-	{ REG_VFIFO_READ_START_L, 0x80 },
+	{ REG_VFIFO_READ_START_L, 0xa0 },
 	{ REG_ISP_CTRL02, 0x10 },
 	{ REG_NULL, 0x00 },
 };
@@ -1198,14 +1182,27 @@ static int ov2659_s_stream(struct v4l2_subdev *sd, int on)
 		/* Stop Streaming Sequence */
 		ov2659_set_streaming(ov2659, 0);
 		ov2659->streaming = on;
+		pm_runtime_put(&client->dev);
 		goto unlock;
 	}
 
-	ov2659_set_pixel_clock(ov2659);
-	ov2659_set_frame_size(ov2659);
-	ov2659_set_format(ov2659);
-	ov2659_set_streaming(ov2659, 1);
-	ov2659->streaming = on;
+	ret = pm_runtime_get_sync(&client->dev);
+	if (ret < 0) {
+		pm_runtime_put_noidle(&client->dev);
+		goto unlock;
+	}
+
+	ret = ov2659_init(sd, 0);
+	if (!ret)
+		ret = ov2659_set_pixel_clock(ov2659);
+	if (!ret)
+		ret = ov2659_set_frame_size(ov2659);
+	if (!ret)
+		ret = ov2659_set_format(ov2659);
+	if (!ret) {
+		ov2659_set_streaming(ov2659, 1);
+		ov2659->streaming = on;
+	}
 
 unlock:
 	mutex_unlock(&ov2659->lock);
@@ -1239,12 +1236,18 @@ static int ov2659_s_ctrl(struct v4l2_ctrl *ctrl)
 {
 	struct ov2659 *ov2659 =
 			container_of(ctrl->handler, struct ov2659, ctrls);
+	struct i2c_client *client = ov2659->client;
+
+	/* V4L2 controls values will be applied only when power is already up */
+	if (!pm_runtime_get_if_in_use(&client->dev))
+		return 0;
 
 	switch (ctrl->id) {
 	case V4L2_CID_TEST_PATTERN:
 		return ov2659_set_test_pattern(ov2659, ctrl->val);
 	}
 
+	pm_runtime_put(&client->dev);
 	return 0;
 }
 
@@ -1257,6 +1260,39 @@ static const char * const ov2659_test_pattern_menu[] = {
 	"Vertical Color Bars",
 };
 
+static int ov2659_power_off(struct device *dev)
+{
+	struct i2c_client *client = to_i2c_client(dev);
+	struct v4l2_subdev *sd = i2c_get_clientdata(client);
+	struct ov2659 *ov2659 = to_ov2659(sd);
+
+	dev_dbg(&client->dev, "%s:\n", __func__);
+
+	gpiod_set_value(ov2659->pwdn_gpio, 1);
+
+	return 0;
+}
+
+static int ov2659_power_on(struct device *dev)
+{
+	struct i2c_client *client = to_i2c_client(dev);
+	struct v4l2_subdev *sd = i2c_get_clientdata(client);
+	struct ov2659 *ov2659 = to_ov2659(sd);
+
+	dev_dbg(&client->dev, "%s:\n", __func__);
+
+	gpiod_set_value(ov2659->pwdn_gpio, 0);
+
+	if (ov2659->resetb_gpio) {
+		gpiod_set_value(ov2659->resetb_gpio, 1);
+		usleep_range(500, 1000);
+		gpiod_set_value(ov2659->resetb_gpio, 0);
+		usleep_range(3000, 5000);
+	}
+
+	return 0;
+}
+
 /* -----------------------------------------------------------------------------
  * V4L2 subdev internal operations
  */
@@ -1330,13 +1366,13 @@ static int ov2659_detect(struct v4l2_subdev *sd)
 		unsigned short id;
 
 		id = OV265X_ID(pid, ver);
-		if (id != OV2659_ID)
+		if (id != OV2659_ID) {
 			dev_err(&client->dev,
 				"Sensor detection failed (%04X, %d)\n",
 				id, ret);
-		else {
+			ret = -ENODEV;
+		} else {
 			dev_info(&client->dev, "Found OV%04X sensor\n", id);
-			ret = ov2659_init(sd, 0);
 		}
 	}
 
@@ -1413,6 +1449,18 @@ static int ov2659_probe(struct i2c_client *client)
 	    ov2659->xvclk_frequency > 27000000)
 		return -EINVAL;
 
+	/* Optional gpio don't fail if not present */
+	ov2659->pwdn_gpio = devm_gpiod_get_optional(&client->dev, "powerdown",
+						    GPIOD_OUT_LOW);
+	if (IS_ERR(ov2659->pwdn_gpio))
+		return PTR_ERR(ov2659->pwdn_gpio);
+
+	/* Optional gpio don't fail if not present */
+	ov2659->resetb_gpio = devm_gpiod_get_optional(&client->dev, "reset",
+						      GPIOD_OUT_HIGH);
+	if (IS_ERR(ov2659->resetb_gpio))
+		return PTR_ERR(ov2659->resetb_gpio);
+
 	v4l2_ctrl_handler_init(&ov2659->ctrls, 2);
 	ov2659->link_frequency =
 			v4l2_ctrl_new_std(&ov2659->ctrls, &ov2659_ctrl_ops,
@@ -1458,6 +1506,8 @@ static int ov2659_probe(struct i2c_client *client)
 	ov2659->frame_size = &ov2659_framesizes[2];
 	ov2659->format_ctrl_regs = ov2659_formats[0].format_ctrl_regs;
 
+	ov2659_power_on(&client->dev);
+
 	ret = ov2659_detect(sd);
 	if (ret < 0)
 		goto error;
@@ -1471,10 +1521,15 @@ static int ov2659_probe(struct i2c_client *client)
 
 	dev_info(&client->dev, "%s sensor driver registered !!\n", sd->name);
 
+	pm_runtime_set_active(&client->dev);
+	pm_runtime_enable(&client->dev);
+	pm_runtime_idle(&client->dev);
+
 	return 0;
 
 error:
 	v4l2_ctrl_handler_free(&ov2659->ctrls);
+	ov2659_power_off(&client->dev);
 	media_entity_cleanup(&sd->entity);
 	mutex_destroy(&ov2659->lock);
 	return ret;
@@ -1490,9 +1545,18 @@ static int ov2659_remove(struct i2c_client *client)
 	media_entity_cleanup(&sd->entity);
 	mutex_destroy(&ov2659->lock);
 
+	pm_runtime_disable(&client->dev);
+	if (!pm_runtime_status_suspended(&client->dev))
+		ov2659_power_off(&client->dev);
+	pm_runtime_set_suspended(&client->dev);
+
 	return 0;
 }
 
+static const struct dev_pm_ops ov2659_pm_ops = {
+	SET_RUNTIME_PM_OPS(ov2659_power_off, ov2659_power_on, NULL)
+};
+
 static const struct i2c_device_id ov2659_id[] = {
 	{ "ov2659", 0 },
 	{ /* sentinel */ },
@@ -1510,6 +1574,7 @@ MODULE_DEVICE_TABLE(of, ov2659_of_match);
 static struct i2c_driver ov2659_i2c_driver = {
 	.driver = {
 		.name	= DRIVER_NAME,
+		.pm	= &ov2659_pm_ops,
 		.of_match_table = of_match_ptr(ov2659_of_match),
 	},
 	.probe_new	= ov2659_probe,
diff --git a/drivers/media/i2c/ov5640.c b/drivers/media/i2c/ov5640.c
index 500d9bbff10b..5e495c833d32 100644
--- a/drivers/media/i2c/ov5640.c
+++ b/drivers/media/i2c/ov5640.c
@@ -193,6 +193,7 @@ struct ov5640_mode_info {
 
 struct ov5640_ctrls {
 	struct v4l2_ctrl_handler handler;
+	struct v4l2_ctrl *pixel_rate;
 	struct {
 		struct v4l2_ctrl *auto_exp;
 		struct v4l2_ctrl *exposure;
@@ -489,7 +490,6 @@ static const struct reg_value ov5640_setting_720P_1280_720[] = {
 };
 
 static const struct reg_value ov5640_setting_1080P_1920_1080[] = {
-	{0x3008, 0x42, 0, 0},
 	{0x3c07, 0x08, 0, 0},
 	{0x3c09, 0x1c, 0, 0}, {0x3c0a, 0x9c, 0, 0}, {0x3c0b, 0x40, 0, 0},
 	{0x3814, 0x11, 0, 0},
@@ -517,7 +517,7 @@ static const struct reg_value ov5640_setting_1080P_1920_1080[] = {
 	{0x3a0e, 0x03, 0, 0}, {0x3a0d, 0x04, 0, 0}, {0x3a14, 0x04, 0, 0},
 	{0x3a15, 0x60, 0, 0}, {0x4407, 0x04, 0, 0},
 	{0x460b, 0x37, 0, 0}, {0x460c, 0x20, 0, 0}, {0x3824, 0x04, 0, 0},
-	{0x4005, 0x1a, 0, 0}, {0x3008, 0x02, 0, 0},
+	{0x4005, 0x1a, 0, 0},
 };
 
 static const struct reg_value ov5640_setting_QSXGA_2592_1944[] = {
@@ -1611,9 +1611,24 @@ ov5640_find_mode(struct ov5640_dev *sensor, enum ov5640_frame_rate fr,
 	    !(mode->hact == 640 && mode->vact == 480))
 		return NULL;
 
+	/* 2592x1944 only works at 15fps max */
+	if ((mode->hact == 2592 && mode->vact == 1944) &&
+	    fr > OV5640_15_FPS)
+		return NULL;
+
 	return mode;
 }
 
+static u64 ov5640_calc_pixel_rate(struct ov5640_dev *sensor)
+{
+	u64 rate;
+
+	rate = sensor->current_mode->vtot * sensor->current_mode->htot;
+	rate *= ov5640_framerates[sensor->current_fr];
+
+	return rate;
+}
+
 /*
  * sensor changes between scaling and subsampling, go through
  * exposure calculation
@@ -1818,8 +1833,7 @@ static int ov5640_set_mode(struct ov5640_dev *sensor)
 	 * All the formats we support have 16 bits per pixel, seems to require
 	 * the same rate than YUV, so we can just use 16 bpp all the time.
 	 */
-	rate = mode->vtot * mode->htot * 16;
-	rate *= ov5640_framerates[sensor->current_fr];
+	rate = ov5640_calc_pixel_rate(sensor) * 16;
 	if (sensor->ep.bus_type == V4L2_MBUS_CSI2_DPHY) {
 		rate = rate / sensor->ep.bus.mipi_csi2.num_data_lanes;
 		ret = ov5640_set_mipi_pclk(sensor, rate);
@@ -2233,6 +2247,8 @@ static int ov5640_set_fmt(struct v4l2_subdev *sd,
 	if (mbus_fmt->code != sensor->fmt.code)
 		sensor->pending_fmt_change = true;
 
+	__v4l2_ctrl_s_ctrl_int64(sensor->ctrls.pixel_rate,
+				 ov5640_calc_pixel_rate(sensor));
 out:
 	mutex_unlock(&sensor->lock);
 	return ret;
@@ -2657,6 +2673,11 @@ static int ov5640_init_controls(struct ov5640_dev *sensor)
 	/* we can use our own mutex for the ctrl lock */
 	hdl->lock = &sensor->lock;
 
+	/* Clock related controls */
+	ctrls->pixel_rate = v4l2_ctrl_new_std(hdl, ops, V4L2_CID_PIXEL_RATE,
+					      0, INT_MAX, 1,
+					      ov5640_calc_pixel_rate(sensor));
+
 	/* Auto/manual white balance */
 	ctrls->auto_wb = v4l2_ctrl_new_std(hdl, ops,
 					   V4L2_CID_AUTO_WHITE_BALANCE,
@@ -2704,6 +2725,7 @@ static int ov5640_init_controls(struct ov5640_dev *sensor)
 		goto free_ctrls;
 	}
 
+	ctrls->pixel_rate->flags |= V4L2_CTRL_FLAG_READ_ONLY;
 	ctrls->gain->flags |= V4L2_CTRL_FLAG_VOLATILE;
 	ctrls->exposure->flags |= V4L2_CTRL_FLAG_VOLATILE;
 
@@ -2816,6 +2838,9 @@ static int ov5640_s_frame_interval(struct v4l2_subdev *sd,
 		sensor->frame_interval = fi->interval;
 		sensor->current_mode = mode;
 		sensor->pending_mode_change = true;
+
+		__v4l2_ctrl_s_ctrl_int64(sensor->ctrls.pixel_rate,
+					 ov5640_calc_pixel_rate(sensor));
 	}
 out:
 	mutex_unlock(&sensor->lock);
diff --git a/drivers/media/i2c/ov5695.c b/drivers/media/i2c/ov5695.c
index 34b7046d9702..d6cd15bb699a 100644
--- a/drivers/media/i2c/ov5695.c
+++ b/drivers/media/i2c/ov5695.c
@@ -1325,7 +1325,7 @@ static int ov5695_probe(struct i2c_client *client,
 		goto err_power_off;
 #endif
 
-	ret = v4l2_async_register_subdev(sd);
+	ret = v4l2_async_register_subdev_sensor_common(sd);
 	if (ret) {
 		dev_err(dev, "v4l2 async register subdev failed\n");
 		goto err_clean_entity;
diff --git a/drivers/media/i2c/ov6650.c b/drivers/media/i2c/ov6650.c
index 5b9af5e5b7f1..91906b94f978 100644
--- a/drivers/media/i2c/ov6650.c
+++ b/drivers/media/i2c/ov6650.c
@@ -124,12 +124,13 @@
 
 #define DEF_AECH		0x4D
 
-#define CLKRC_6MHz		0x00
+#define CLKRC_8MHz		0x00
 #define CLKRC_12MHz		0x40
 #define CLKRC_16MHz		0x80
 #define CLKRC_24MHz		0xc0
 #define CLKRC_DIV_MASK		0x3f
 #define GET_CLKRC_DIV(x)	(((x) & CLKRC_DIV_MASK) + 1)
+#define DEF_CLKRC		0x00
 
 #define COMA_RESET		BIT(7)
 #define COMA_QCIF		BIT(5)
@@ -196,13 +197,33 @@ struct ov6650 {
 	struct v4l2_clk		*clk;
 	bool			half_scale;	/* scale down output by 2 */
 	struct v4l2_rect	rect;		/* sensor cropping window */
-	unsigned long		pclk_limit;	/* from host */
-	unsigned long		pclk_max;	/* from resolution and format */
 	struct v4l2_fract	tpf;		/* as requested with s_frame_interval */
 	u32 code;
-	enum v4l2_colorspace	colorspace;
 };
 
+struct ov6650_xclk {
+	unsigned long	rate;
+	u8		clkrc;
+};
+
+static const struct ov6650_xclk ov6650_xclk[] = {
+{
+	.rate	= 8000000,
+	.clkrc	= CLKRC_8MHz,
+},
+{
+	.rate	= 12000000,
+	.clkrc	= CLKRC_12MHz,
+},
+{
+	.rate	= 16000000,
+	.clkrc	= CLKRC_16MHz,
+},
+{
+	.rate	= 24000000,
+	.clkrc	= CLKRC_24MHz,
+},
+};
 
 static u32 ov6650_codes[] = {
 	MEDIA_BUS_FMT_YUYV8_2X8,
@@ -213,6 +234,17 @@ static u32 ov6650_codes[] = {
 	MEDIA_BUS_FMT_Y8_1X8,
 };
 
+static const struct v4l2_mbus_framefmt ov6650_def_fmt = {
+	.width		= W_CIF,
+	.height		= H_CIF,
+	.code		= MEDIA_BUS_FMT_SBGGR8_1X8,
+	.colorspace	= V4L2_COLORSPACE_SRGB,
+	.field		= V4L2_FIELD_NONE,
+	.ycbcr_enc	= V4L2_YCBCR_ENC_DEFAULT,
+	.quantization	= V4L2_QUANTIZATION_DEFAULT,
+	.xfer_func	= V4L2_XFER_FUNC_DEFAULT,
+};
+
 /* read a register */
 static int ov6650_reg_read(struct i2c_client *client, u8 reg, u8 *val)
 {
@@ -465,38 +497,39 @@ static int ov6650_set_selection(struct v4l2_subdev *sd,
 {
 	struct i2c_client *client = v4l2_get_subdevdata(sd);
 	struct ov6650 *priv = to_ov6650(client);
-	struct v4l2_rect rect = sel->r;
 	int ret;
 
 	if (sel->which != V4L2_SUBDEV_FORMAT_ACTIVE ||
 	    sel->target != V4L2_SEL_TGT_CROP)
 		return -EINVAL;
 
-	v4l_bound_align_image(&rect.width, 2, W_CIF, 1,
-			      &rect.height, 2, H_CIF, 1, 0);
-	v4l_bound_align_image(&rect.left, DEF_HSTRT << 1,
-			      (DEF_HSTRT << 1) + W_CIF - (__s32)rect.width, 1,
-			      &rect.top, DEF_VSTRT << 1,
-			      (DEF_VSTRT << 1) + H_CIF - (__s32)rect.height, 1,
-			      0);
+	v4l_bound_align_image(&sel->r.width, 2, W_CIF, 1,
+			      &sel->r.height, 2, H_CIF, 1, 0);
+	v4l_bound_align_image(&sel->r.left, DEF_HSTRT << 1,
+			      (DEF_HSTRT << 1) + W_CIF - (__s32)sel->r.width, 1,
+			      &sel->r.top, DEF_VSTRT << 1,
+			      (DEF_VSTRT << 1) + H_CIF - (__s32)sel->r.height,
+			      1, 0);
 
-	ret = ov6650_reg_write(client, REG_HSTRT, rect.left >> 1);
+	ret = ov6650_reg_write(client, REG_HSTRT, sel->r.left >> 1);
 	if (!ret) {
-		priv->rect.left = rect.left;
+		priv->rect.width += priv->rect.left - sel->r.left;
+		priv->rect.left = sel->r.left;
 		ret = ov6650_reg_write(client, REG_HSTOP,
-				(rect.left + rect.width) >> 1);
+				       (sel->r.left + sel->r.width) >> 1);
 	}
 	if (!ret) {
-		priv->rect.width = rect.width;
-		ret = ov6650_reg_write(client, REG_VSTRT, rect.top >> 1);
+		priv->rect.width = sel->r.width;
+		ret = ov6650_reg_write(client, REG_VSTRT, sel->r.top >> 1);
 	}
 	if (!ret) {
-		priv->rect.top = rect.top;
+		priv->rect.height += priv->rect.top - sel->r.top;
+		priv->rect.top = sel->r.top;
 		ret = ov6650_reg_write(client, REG_VSTOP,
-				(rect.top + rect.height) >> 1);
+				       (sel->r.top + sel->r.height) >> 1);
 	}
 	if (!ret)
-		priv->rect.height = rect.height;
+		priv->rect.height = sel->r.height;
 
 	return ret;
 }
@@ -512,12 +545,20 @@ static int ov6650_get_fmt(struct v4l2_subdev *sd,
 	if (format->pad)
 		return -EINVAL;
 
-	mf->width	= priv->rect.width >> priv->half_scale;
-	mf->height	= priv->rect.height >> priv->half_scale;
-	mf->code	= priv->code;
-	mf->colorspace	= priv->colorspace;
-	mf->field	= V4L2_FIELD_NONE;
+	/* initialize response with default media bus frame format */
+	*mf = ov6650_def_fmt;
+
+	/* update media bus format code and frame size */
+	if (format->which == V4L2_SUBDEV_FORMAT_TRY) {
+		mf->width = cfg->try_fmt.width;
+		mf->height = cfg->try_fmt.height;
+		mf->code = cfg->try_fmt.code;
 
+	} else {
+		mf->width = priv->rect.width >> priv->half_scale;
+		mf->height = priv->rect.height >> priv->half_scale;
+		mf->code = priv->code;
+	}
 	return 0;
 }
 
@@ -526,22 +567,7 @@ static bool is_unscaled_ok(int width, int height, struct v4l2_rect *rect)
 	return width > rect->width >> 1 || height > rect->height >> 1;
 }
 
-static u8 to_clkrc(struct v4l2_fract *timeperframe,
-		unsigned long pclk_limit, unsigned long pclk_max)
-{
-	unsigned long pclk;
-
-	if (timeperframe->numerator && timeperframe->denominator)
-		pclk = pclk_max * timeperframe->denominator /
-				(FRAME_RATE_MAX * timeperframe->numerator);
-	else
-		pclk = pclk_max;
-
-	if (pclk_limit && pclk_limit < pclk)
-		pclk = pclk_limit;
-
-	return (pclk_max - 1) / pclk;
-}
+#define to_clkrc(div)	((div) - 1)
 
 /* set the format we will capture in */
 static int ov6650_s_fmt(struct v4l2_subdev *sd, struct v4l2_mbus_framefmt *mf)
@@ -560,8 +586,7 @@ static int ov6650_s_fmt(struct v4l2_subdev *sd, struct v4l2_mbus_framefmt *mf)
 		.r.height = mf->height << half_scale,
 	};
 	u32 code = mf->code;
-	unsigned long mclk, pclk;
-	u8 coma_set = 0, coma_mask = 0, coml_set, coml_mask, clkrc;
+	u8 coma_set = 0, coma_mask = 0, coml_set, coml_mask;
 	int ret;
 
 	/* select color matrix configuration for given color encoding */
@@ -610,58 +635,35 @@ static int ov6650_s_fmt(struct v4l2_subdev *sd, struct v4l2_mbus_framefmt *mf)
 		dev_err(&client->dev, "Pixel format not handled: 0x%x\n", code);
 		return -EINVAL;
 	}
-	priv->code = code;
 
 	if (code == MEDIA_BUS_FMT_Y8_1X8 ||
 			code == MEDIA_BUS_FMT_SBGGR8_1X8) {
 		coml_mask = COML_ONE_CHANNEL;
 		coml_set = 0;
-		priv->pclk_max = 4000000;
 	} else {
 		coml_mask = 0;
 		coml_set = COML_ONE_CHANNEL;
-		priv->pclk_max = 8000000;
 	}
 
-	if (code == MEDIA_BUS_FMT_SBGGR8_1X8)
-		priv->colorspace = V4L2_COLORSPACE_SRGB;
-	else if (code != 0)
-		priv->colorspace = V4L2_COLORSPACE_JPEG;
-
 	if (half_scale) {
 		dev_dbg(&client->dev, "max resolution: QCIF\n");
 		coma_set |= COMA_QCIF;
-		priv->pclk_max /= 2;
 	} else {
 		dev_dbg(&client->dev, "max resolution: CIF\n");
 		coma_mask |= COMA_QCIF;
 	}
-	priv->half_scale = half_scale;
-
-	clkrc = CLKRC_12MHz;
-	mclk = 12000000;
-	priv->pclk_limit = 1334000;
-	dev_dbg(&client->dev, "using 12MHz input clock\n");
-
-	clkrc |= to_clkrc(&priv->tpf, priv->pclk_limit, priv->pclk_max);
-
-	pclk = priv->pclk_max / GET_CLKRC_DIV(clkrc);
-	dev_dbg(&client->dev, "pixel clock divider: %ld.%ld\n",
-			mclk / pclk, 10 * mclk % pclk / pclk);
 
 	ret = ov6650_set_selection(sd, NULL, &sel);
 	if (!ret)
 		ret = ov6650_reg_rmw(client, REG_COMA, coma_set, coma_mask);
-	if (!ret)
-		ret = ov6650_reg_write(client, REG_CLKRC, clkrc);
-	if (!ret)
-		ret = ov6650_reg_rmw(client, REG_COML, coml_set, coml_mask);
-
 	if (!ret) {
-		mf->colorspace	= priv->colorspace;
-		mf->width = priv->rect.width >> half_scale;
-		mf->height = priv->rect.height >> half_scale;
+		priv->half_scale = half_scale;
+
+		ret = ov6650_reg_rmw(client, REG_COML, coml_set, coml_mask);
 	}
+	if (!ret)
+		priv->code = code;
+
 	return ret;
 }
 
@@ -680,8 +682,6 @@ static int ov6650_set_fmt(struct v4l2_subdev *sd,
 		v4l_bound_align_image(&mf->width, 2, W_CIF, 1,
 				&mf->height, 2, H_CIF, 1, 0);
 
-	mf->field = V4L2_FIELD_NONE;
-
 	switch (mf->code) {
 	case MEDIA_BUS_FMT_Y10_1X10:
 		mf->code = MEDIA_BUS_FMT_Y8_1X8;
@@ -691,20 +691,39 @@ static int ov6650_set_fmt(struct v4l2_subdev *sd,
 	case MEDIA_BUS_FMT_YUYV8_2X8:
 	case MEDIA_BUS_FMT_VYUY8_2X8:
 	case MEDIA_BUS_FMT_UYVY8_2X8:
-		mf->colorspace = V4L2_COLORSPACE_JPEG;
 		break;
 	default:
 		mf->code = MEDIA_BUS_FMT_SBGGR8_1X8;
 		/* fall through */
 	case MEDIA_BUS_FMT_SBGGR8_1X8:
-		mf->colorspace = V4L2_COLORSPACE_SRGB;
 		break;
 	}
 
-	if (format->which == V4L2_SUBDEV_FORMAT_ACTIVE)
-		return ov6650_s_fmt(sd, mf);
-	cfg->try_fmt = *mf;
+	if (format->which == V4L2_SUBDEV_FORMAT_TRY) {
+		/* store media bus format code and frame size in pad config */
+		cfg->try_fmt.width = mf->width;
+		cfg->try_fmt.height = mf->height;
+		cfg->try_fmt.code = mf->code;
 
+		/* return default mbus frame format updated with pad config */
+		*mf = ov6650_def_fmt;
+		mf->width = cfg->try_fmt.width;
+		mf->height = cfg->try_fmt.height;
+		mf->code = cfg->try_fmt.code;
+
+	} else {
+		/* apply new media bus format code and frame size */
+		int ret = ov6650_s_fmt(sd, mf);
+
+		if (ret)
+			return ret;
+
+		/* return default format updated with active size and code */
+		*mf = ov6650_def_fmt;
+		mf->width = priv->rect.width >> priv->half_scale;
+		mf->height = priv->rect.height >> priv->half_scale;
+		mf->code = priv->code;
+	}
 	return 0;
 }
 
@@ -725,9 +744,7 @@ static int ov6650_g_frame_interval(struct v4l2_subdev *sd,
 	struct i2c_client *client = v4l2_get_subdevdata(sd);
 	struct ov6650 *priv = to_ov6650(client);
 
-	ival->interval.numerator = GET_CLKRC_DIV(to_clkrc(&priv->tpf,
-			priv->pclk_limit, priv->pclk_max));
-	ival->interval.denominator = FRAME_RATE_MAX;
+	ival->interval = priv->tpf;
 
 	dev_dbg(&client->dev, "Frame interval: %u/%u s\n",
 		ival->interval.numerator, ival->interval.denominator);
@@ -742,7 +759,6 @@ static int ov6650_s_frame_interval(struct v4l2_subdev *sd,
 	struct ov6650 *priv = to_ov6650(client);
 	struct v4l2_fract *tpf = &ival->interval;
 	int div, ret;
-	u8 clkrc;
 
 	if (tpf->numerator == 0 || tpf->denominator == 0)
 		div = 1;  /* Reset to full rate */
@@ -754,19 +770,12 @@ static int ov6650_s_frame_interval(struct v4l2_subdev *sd,
 	else if (div > GET_CLKRC_DIV(CLKRC_DIV_MASK))
 		div = GET_CLKRC_DIV(CLKRC_DIV_MASK);
 
-	/*
-	 * Keep result to be used as tpf limit
-	 * for subsequent clock divider calculations
-	 */
-	priv->tpf.numerator = div;
-	priv->tpf.denominator = FRAME_RATE_MAX;
-
-	clkrc = to_clkrc(&priv->tpf, priv->pclk_limit, priv->pclk_max);
-
-	ret = ov6650_reg_rmw(client, REG_CLKRC, clkrc, CLKRC_DIV_MASK);
+	ret = ov6650_reg_rmw(client, REG_CLKRC, to_clkrc(div), CLKRC_DIV_MASK);
 	if (!ret) {
-		tpf->numerator = GET_CLKRC_DIV(clkrc);
-		tpf->denominator = FRAME_RATE_MAX;
+		priv->tpf.numerator = div;
+		priv->tpf.denominator = FRAME_RATE_MAX;
+
+		*tpf = priv->tpf;
 	}
 
 	return ret;
@@ -788,7 +797,7 @@ static int ov6650_reset(struct i2c_client *client)
 }
 
 /* program default register values */
-static int ov6650_prog_dflt(struct i2c_client *client)
+static int ov6650_prog_dflt(struct i2c_client *client, u8 clkrc)
 {
 	int ret;
 
@@ -796,6 +805,8 @@ static int ov6650_prog_dflt(struct i2c_client *client)
 
 	ret = ov6650_reg_write(client, REG_COMA, 0);	/* ~COMA_RESET */
 	if (!ret)
+		ret = ov6650_reg_write(client, REG_CLKRC, clkrc);
+	if (!ret)
 		ret = ov6650_reg_rmw(client, REG_COMB, 0, COMB_BAND_FILTER);
 
 	return ret;
@@ -805,8 +816,10 @@ static int ov6650_video_probe(struct v4l2_subdev *sd)
 {
 	struct i2c_client *client = v4l2_get_subdevdata(sd);
 	struct ov6650 *priv = to_ov6650(client);
-	u8		pidh, pidl, midh, midl;
-	int		ret;
+	const struct ov6650_xclk *xclk = NULL;
+	unsigned long rate;
+	u8 pidh, pidl, midh, midl;
+	int i, ret = 0;
 
 	priv->clk = v4l2_clk_get(&client->dev, NULL);
 	if (IS_ERR(priv->clk)) {
@@ -815,6 +828,33 @@ static int ov6650_video_probe(struct v4l2_subdev *sd)
 		return ret;
 	}
 
+	rate = v4l2_clk_get_rate(priv->clk);
+	for (i = 0; rate && i < ARRAY_SIZE(ov6650_xclk); i++) {
+		if (rate != ov6650_xclk[i].rate)
+			continue;
+
+		xclk = &ov6650_xclk[i];
+		dev_info(&client->dev, "using host default clock rate %lukHz\n",
+			 rate / 1000);
+		break;
+	}
+	for (i = 0; !xclk && i < ARRAY_SIZE(ov6650_xclk); i++) {
+		ret = v4l2_clk_set_rate(priv->clk, ov6650_xclk[i].rate);
+		if (ret || v4l2_clk_get_rate(priv->clk) != ov6650_xclk[i].rate)
+			continue;
+
+		xclk = &ov6650_xclk[i];
+		dev_info(&client->dev, "using negotiated clock rate %lukHz\n",
+			 xclk->rate / 1000);
+		break;
+	}
+	if (!xclk) {
+		dev_err(&client->dev, "unable to get supported clock rate\n");
+		if (!ret)
+			ret = -EINVAL;
+		goto eclkput;
+	}
+
 	ret = ov6650_s_power(sd, 1);
 	if (ret < 0)
 		goto eclkput;
@@ -848,7 +888,12 @@ static int ov6650_video_probe(struct v4l2_subdev *sd)
 
 	ret = ov6650_reset(client);
 	if (!ret)
-		ret = ov6650_prog_dflt(client);
+		ret = ov6650_prog_dflt(client, xclk->clkrc);
+	if (!ret) {
+		struct v4l2_mbus_framefmt mf = ov6650_def_fmt;
+
+		ret = ov6650_s_fmt(sd, &mf);
+	}
 	if (!ret)
 		ret = v4l2_ctrl_handler_setup(&priv->hdl);
 
@@ -989,8 +1034,10 @@ static int ov6650_probe(struct i2c_client *client,
 			V4L2_CID_GAMMA, 0, 0xff, 1, 0x12);
 
 	priv->subdev.ctrl_handler = &priv->hdl;
-	if (priv->hdl.error)
-		return priv->hdl.error;
+	if (priv->hdl.error) {
+		ret = priv->hdl.error;
+		goto ectlhdlfree;
+	}
 
 	v4l2_ctrl_auto_cluster(2, &priv->autogain, 0, true);
 	v4l2_ctrl_auto_cluster(3, &priv->autowb, 0, true);
@@ -1001,15 +1048,18 @@ static int ov6650_probe(struct i2c_client *client,
 	priv->rect.top	  = DEF_VSTRT << 1;
 	priv->rect.width  = W_CIF;
 	priv->rect.height = H_CIF;
-	priv->half_scale  = false;
-	priv->code	  = MEDIA_BUS_FMT_YUYV8_2X8;
-	priv->colorspace  = V4L2_COLORSPACE_JPEG;
+
+	/* Hardware default frame interval */
+	priv->tpf.numerator   = GET_CLKRC_DIV(DEF_CLKRC);
+	priv->tpf.denominator = FRAME_RATE_MAX;
 
 	priv->subdev.internal_ops = &ov6650_internal_ops;
 
 	ret = v4l2_async_register_subdev(&priv->subdev);
-	if (ret)
-		v4l2_ctrl_handler_free(&priv->hdl);
+	if (!ret)
+		return 0;
+ectlhdlfree:
+	v4l2_ctrl_handler_free(&priv->hdl);
 
 	return ret;
 }
@@ -1041,6 +1091,6 @@ static struct i2c_driver ov6650_i2c_driver = {
 
 module_i2c_driver(ov6650_i2c_driver);
 
-MODULE_DESCRIPTION("SoC Camera driver for OmniVision OV6650");
-MODULE_AUTHOR("Janusz Krzysztofik <jkrzyszt@tis.icnet.pl>");
+MODULE_DESCRIPTION("V4L2 subdevice driver for OmniVision OV6650 camera sensor");
+MODULE_AUTHOR("Janusz Krzysztofik <jmkrzyszt@gmail.com");
 MODULE_LICENSE("GPL v2");
diff --git a/drivers/media/i2c/saa711x_regs.h b/drivers/media/i2c/saa711x_regs.h
index 44fabe08234d..4b5f6985710b 100644
--- a/drivers/media/i2c/saa711x_regs.h
+++ b/drivers/media/i2c/saa711x_regs.h
@@ -1,5 +1,5 @@
+/* SPDX-License-Identifier: GPL-2.0+ */
 /*
- * SPDX-License-Identifier: GPL-2.0+
  * saa711x - Philips SAA711x video decoder register specifications
  *
  * Copyright (c) 2006 Mauro Carvalho Chehab <mchehab@kernel.org>
diff --git a/drivers/media/i2c/smiapp/smiapp-core.c b/drivers/media/i2c/smiapp/smiapp-core.c
index 9adf8e034e7d..84f9771b5fed 100644
--- a/drivers/media/i2c/smiapp/smiapp-core.c
+++ b/drivers/media/i2c/smiapp/smiapp-core.c
@@ -682,66 +682,6 @@ static int smiapp_get_all_limits(struct smiapp_sensor *sensor)
 	return 0;
 }
 
-static int smiapp_get_limits_binning(struct smiapp_sensor *sensor)
-{
-	struct i2c_client *client = v4l2_get_subdevdata(&sensor->src->sd);
-	static u32 const limits[] = {
-		SMIAPP_LIMIT_MIN_FRAME_LENGTH_LINES_BIN,
-		SMIAPP_LIMIT_MAX_FRAME_LENGTH_LINES_BIN,
-		SMIAPP_LIMIT_MIN_LINE_LENGTH_PCK_BIN,
-		SMIAPP_LIMIT_MAX_LINE_LENGTH_PCK_BIN,
-		SMIAPP_LIMIT_MIN_LINE_BLANKING_PCK_BIN,
-		SMIAPP_LIMIT_FINE_INTEGRATION_TIME_MIN_BIN,
-		SMIAPP_LIMIT_FINE_INTEGRATION_TIME_MAX_MARGIN_BIN,
-	};
-	static u32 const limits_replace[] = {
-		SMIAPP_LIMIT_MIN_FRAME_LENGTH_LINES,
-		SMIAPP_LIMIT_MAX_FRAME_LENGTH_LINES,
-		SMIAPP_LIMIT_MIN_LINE_LENGTH_PCK,
-		SMIAPP_LIMIT_MAX_LINE_LENGTH_PCK,
-		SMIAPP_LIMIT_MIN_LINE_BLANKING_PCK,
-		SMIAPP_LIMIT_FINE_INTEGRATION_TIME_MIN,
-		SMIAPP_LIMIT_FINE_INTEGRATION_TIME_MAX_MARGIN,
-	};
-	unsigned int i;
-	int rval;
-
-	if (sensor->limits[SMIAPP_LIMIT_BINNING_CAPABILITY] ==
-	    SMIAPP_BINNING_CAPABILITY_NO) {
-		for (i = 0; i < ARRAY_SIZE(limits); i++)
-			sensor->limits[limits[i]] =
-				sensor->limits[limits_replace[i]];
-
-		return 0;
-	}
-
-	rval = smiapp_get_limits(sensor, limits, ARRAY_SIZE(limits));
-	if (rval < 0)
-		return rval;
-
-	/*
-	 * Sanity check whether the binning limits are valid. If not,
-	 * use the non-binning ones.
-	 */
-	if (sensor->limits[SMIAPP_LIMIT_MIN_FRAME_LENGTH_LINES_BIN]
-	    && sensor->limits[SMIAPP_LIMIT_MIN_LINE_LENGTH_PCK_BIN]
-	    && sensor->limits[SMIAPP_LIMIT_MIN_LINE_BLANKING_PCK_BIN])
-		return 0;
-
-	for (i = 0; i < ARRAY_SIZE(limits); i++) {
-		dev_dbg(&client->dev,
-			"replace limit 0x%8.8x \"%s\" = %d, 0x%x\n",
-			smiapp_reg_limits[limits[i]].addr,
-			smiapp_reg_limits[limits[i]].what,
-			sensor->limits[limits_replace[i]],
-			sensor->limits[limits_replace[i]]);
-		sensor->limits[limits[i]] =
-			sensor->limits[limits_replace[i]];
-	}
-
-	return 0;
-}
-
 static int smiapp_get_mbus_formats(struct smiapp_sensor *sensor)
 {
 	struct i2c_client *client = v4l2_get_subdevdata(&sensor->src->sd);
@@ -891,60 +831,47 @@ static void smiapp_update_blanking(struct smiapp_sensor *sensor)
 {
 	struct v4l2_ctrl *vblank = sensor->vblank;
 	struct v4l2_ctrl *hblank = sensor->hblank;
+	uint16_t min_fll, max_fll, min_llp, max_llp, min_lbp;
 	int min, max;
 
+	if (sensor->binning_vertical > 1 || sensor->binning_horizontal > 1) {
+		min_fll = sensor->limits[SMIAPP_LIMIT_MIN_FRAME_LENGTH_LINES_BIN];
+		max_fll = sensor->limits[SMIAPP_LIMIT_MAX_FRAME_LENGTH_LINES_BIN];
+		min_llp = sensor->limits[SMIAPP_LIMIT_MIN_LINE_LENGTH_PCK_BIN];
+		max_llp = sensor->limits[SMIAPP_LIMIT_MAX_LINE_LENGTH_PCK_BIN];
+		min_lbp = sensor->limits[SMIAPP_LIMIT_MIN_LINE_BLANKING_PCK_BIN];
+	} else {
+		min_fll = sensor->limits[SMIAPP_LIMIT_MIN_FRAME_LENGTH_LINES];
+		max_fll = sensor->limits[SMIAPP_LIMIT_MAX_FRAME_LENGTH_LINES];
+		min_llp = sensor->limits[SMIAPP_LIMIT_MIN_LINE_LENGTH_PCK];
+		max_llp = sensor->limits[SMIAPP_LIMIT_MAX_LINE_LENGTH_PCK];
+		min_lbp = sensor->limits[SMIAPP_LIMIT_MIN_LINE_BLANKING_PCK];
+	}
+
 	min = max_t(int,
 		    sensor->limits[SMIAPP_LIMIT_MIN_FRAME_BLANKING_LINES],
-		    sensor->limits[SMIAPP_LIMIT_MIN_FRAME_LENGTH_LINES_BIN] -
+		    min_fll -
 		    sensor->pixel_array->crop[SMIAPP_PA_PAD_SRC].height);
-	max = sensor->limits[SMIAPP_LIMIT_MAX_FRAME_LENGTH_LINES_BIN] -
-		sensor->pixel_array->crop[SMIAPP_PA_PAD_SRC].height;
+	max = max_fll -	sensor->pixel_array->crop[SMIAPP_PA_PAD_SRC].height;
 
 	__v4l2_ctrl_modify_range(vblank, min, max, vblank->step, min);
 
 	min = max_t(int,
-		    sensor->limits[SMIAPP_LIMIT_MIN_LINE_LENGTH_PCK_BIN] -
+		    min_llp -
 		    sensor->pixel_array->crop[SMIAPP_PA_PAD_SRC].width,
-		    sensor->limits[SMIAPP_LIMIT_MIN_LINE_BLANKING_PCK_BIN]);
-	max = sensor->limits[SMIAPP_LIMIT_MAX_LINE_LENGTH_PCK_BIN] -
-		sensor->pixel_array->crop[SMIAPP_PA_PAD_SRC].width;
+		    min_lbp);
+	max = max_llp - sensor->pixel_array->crop[SMIAPP_PA_PAD_SRC].width;
 
 	__v4l2_ctrl_modify_range(hblank, min, max, hblank->step, min);
 
 	__smiapp_update_exposure_limits(sensor);
 }
 
-static int smiapp_update_mode(struct smiapp_sensor *sensor)
+static int smiapp_pll_blanking_update(struct smiapp_sensor *sensor)
 {
 	struct i2c_client *client = v4l2_get_subdevdata(&sensor->src->sd);
-	unsigned int binning_mode;
 	int rval;
 
-	/* Binning has to be set up here; it affects limits */
-	if (sensor->binning_horizontal == 1 &&
-	    sensor->binning_vertical == 1) {
-		binning_mode = 0;
-	} else {
-		u8 binning_type =
-			(sensor->binning_horizontal << 4)
-			| sensor->binning_vertical;
-
-		rval = smiapp_write(
-			sensor, SMIAPP_REG_U8_BINNING_TYPE, binning_type);
-		if (rval < 0)
-			return rval;
-
-		binning_mode = 1;
-	}
-	rval = smiapp_write(sensor, SMIAPP_REG_U8_BINNING_MODE, binning_mode);
-	if (rval < 0)
-		return rval;
-
-	/* Get updated limits due to binning */
-	rval = smiapp_get_limits_binning(sensor);
-	if (rval < 0)
-		return rval;
-
 	rval = smiapp_pll_update(sensor);
 	if (rval < 0)
 		return rval;
@@ -970,62 +897,91 @@ static int smiapp_update_mode(struct smiapp_sensor *sensor)
  * SMIA++ NVM handling
  *
  */
-static int smiapp_read_nvm(struct smiapp_sensor *sensor,
-			   unsigned char *nvm)
+
+static int smiapp_read_nvm_page(struct smiapp_sensor *sensor, u32 p, u8 *nvm,
+				u8 *status)
 {
-	u32 i, s, p, np, v;
-	int rval = 0, rval2;
+	unsigned int i;
+	int rval;
+	u32 s;
 
-	np = sensor->nvm_size / SMIAPP_NVM_PAGE_SIZE;
-	for (p = 0; p < np; p++) {
-		rval = smiapp_write(
-			sensor,
-			SMIAPP_REG_U8_DATA_TRANSFER_IF_1_PAGE_SELECT, p);
-		if (rval)
-			goto out;
+	*status = 0;
 
-		rval = smiapp_write(sensor,
-				    SMIAPP_REG_U8_DATA_TRANSFER_IF_1_CTRL,
-				    SMIAPP_DATA_TRANSFER_IF_1_CTRL_EN |
-				    SMIAPP_DATA_TRANSFER_IF_1_CTRL_RD_EN);
-		if (rval)
-			goto out;
+	rval = smiapp_write(sensor,
+			    SMIAPP_REG_U8_DATA_TRANSFER_IF_1_PAGE_SELECT, p);
+	if (rval)
+		return rval;
 
-		for (i = 1000; i > 0; i--) {
-			rval = smiapp_read(
-				sensor,
-				SMIAPP_REG_U8_DATA_TRANSFER_IF_1_STATUS, &s);
+	rval = smiapp_write(sensor, SMIAPP_REG_U8_DATA_TRANSFER_IF_1_CTRL,
+			    SMIAPP_DATA_TRANSFER_IF_1_CTRL_EN);
+	if (rval)
+		return rval;
 
-			if (rval)
-				goto out;
+	rval = smiapp_read(sensor, SMIAPP_REG_U8_DATA_TRANSFER_IF_1_STATUS,
+			   &s);
+	if (rval)
+		return rval;
+
+	if (s & SMIAPP_DATA_TRANSFER_IF_1_STATUS_EUSAGE) {
+		*status = s;
+		return -ENODATA;
+	}
 
+	if (sensor->limits[SMIAPP_LIMIT_DATA_TRANSFER_IF_CAPABILITY] &
+	    SMIAPP_DATA_TRANSFER_IF_CAPABILITY_POLL) {
+		for (i = 1000; i > 0; i--) {
 			if (s & SMIAPP_DATA_TRANSFER_IF_1_STATUS_RD_READY)
 				break;
 
-		}
-		if (!i) {
-			rval = -ETIMEDOUT;
-			goto out;
-		}
-
-		for (i = 0; i < SMIAPP_NVM_PAGE_SIZE; i++) {
 			rval = smiapp_read(
 				sensor,
-				SMIAPP_REG_U8_DATA_TRANSFER_IF_1_DATA_0 + i,
-				&v);
-			if (rval)
-				goto out;
+				SMIAPP_REG_U8_DATA_TRANSFER_IF_1_STATUS,
+				&s);
 
-			*nvm++ = v;
+			if (rval)
+				return rval;
 		}
+
+		if (!i)
+			return -ETIMEDOUT;
 	}
 
-out:
+	for (i = 0; i < SMIAPP_NVM_PAGE_SIZE; i++) {
+		u32 v;
+
+		rval = smiapp_read(sensor,
+				   SMIAPP_REG_U8_DATA_TRANSFER_IF_1_DATA_0 + i,
+				   &v);
+		if (rval)
+			return rval;
+
+		*nvm++ = v;
+	}
+
+	return 0;
+}
+
+static int smiapp_read_nvm(struct smiapp_sensor *sensor, unsigned char *nvm,
+			   size_t nvm_size)
+{
+	u8 status = 0;
+	u32 p;
+	int rval = 0, rval2;
+
+	for (p = 0; p < nvm_size / SMIAPP_NVM_PAGE_SIZE && !rval; p++) {
+		rval = smiapp_read_nvm_page(sensor, p, nvm, &status);
+		nvm += SMIAPP_NVM_PAGE_SIZE;
+	}
+
+	if (rval == -ENODATA &&
+	    status & SMIAPP_DATA_TRANSFER_IF_1_STATUS_EUSAGE)
+		rval = 0;
+
 	rval2 = smiapp_write(sensor, SMIAPP_REG_U8_DATA_TRANSFER_IF_1_CTRL, 0);
 	if (rval < 0)
 		return rval;
 	else
-		return rval2;
+		return rval2 ?: p * SMIAPP_NVM_PAGE_SIZE;
 }
 
 /*
@@ -1324,10 +1280,6 @@ static int smiapp_power_on(struct device *dev)
 		rval = __v4l2_ctrl_handler_setup(&sensor->src->ctrl_handler);
 		if (rval)
 			goto out_cci_addr_fail;
-
-		rval = smiapp_update_mode(sensor);
-		if (rval < 0)
-			goto out_cci_addr_fail;
 	}
 
 	mutex_unlock(&sensor->mutex);
@@ -1387,6 +1339,7 @@ static int smiapp_power_off(struct device *dev)
 static int smiapp_start_streaming(struct smiapp_sensor *sensor)
 {
 	struct i2c_client *client = v4l2_get_subdevdata(&sensor->src->sd);
+	unsigned int binning_mode;
 	int rval;
 
 	mutex_lock(&sensor->mutex);
@@ -1397,6 +1350,27 @@ static int smiapp_start_streaming(struct smiapp_sensor *sensor)
 	if (rval)
 		goto out;
 
+	/* Binning configuration */
+	if (sensor->binning_horizontal == 1 &&
+	    sensor->binning_vertical == 1) {
+		binning_mode = 0;
+	} else {
+		u8 binning_type =
+			(sensor->binning_horizontal << 4)
+			| sensor->binning_vertical;
+
+		rval = smiapp_write(
+			sensor, SMIAPP_REG_U8_BINNING_TYPE, binning_type);
+		if (rval < 0)
+			goto out;
+
+		binning_mode = 1;
+	}
+	rval = smiapp_write(sensor, SMIAPP_REG_U8_BINNING_MODE, binning_mode);
+	if (rval < 0)
+		goto out;
+
+	/* Set up PLL */
 	rval = smiapp_pll_configure(sensor);
 	if (rval)
 		goto out;
@@ -2073,7 +2047,7 @@ static int smiapp_set_compose(struct v4l2_subdev *subdev,
 	smiapp_propagate(subdev, cfg, sel->which, V4L2_SEL_TGT_COMPOSE);
 
 	if (sel->which == V4L2_SUBDEV_FORMAT_ACTIVE)
-		return smiapp_update_mode(sensor);
+		return smiapp_pll_blanking_update(sensor);
 
 	return 0;
 }
@@ -2312,41 +2286,34 @@ smiapp_sysfs_nvm_read(struct device *dev, struct device_attribute *attr,
 	struct v4l2_subdev *subdev = i2c_get_clientdata(to_i2c_client(dev));
 	struct i2c_client *client = v4l2_get_subdevdata(subdev);
 	struct smiapp_sensor *sensor = to_smiapp_sensor(subdev);
-	unsigned int nbytes;
+	int rval;
 
 	if (!sensor->dev_init_done)
 		return -EBUSY;
 
-	if (!sensor->nvm_size) {
-		int rval;
-
-		/* NVM not read yet - read it now */
-		sensor->nvm_size = sensor->hwcfg->nvm_size;
+	rval = pm_runtime_get_sync(&client->dev);
+	if (rval < 0) {
+		if (rval != -EBUSY && rval != -EAGAIN)
+			pm_runtime_set_active(&client->dev);
+		pm_runtime_put_noidle(&client->dev);
+		return -ENODEV;
+	}
 
-		rval = pm_runtime_get_sync(&client->dev);
-		if (rval < 0) {
-			if (rval != -EBUSY && rval != -EAGAIN)
-				pm_runtime_set_active(&client->dev);
-			pm_runtime_put(&client->dev);
-			return -ENODEV;
-		}
+	rval = smiapp_read_nvm(sensor, buf, PAGE_SIZE);
+	if (rval < 0) {
+		pm_runtime_put(&client->dev);
+		dev_err(&client->dev, "nvm read failed\n");
+		return -ENODEV;
+	}
 
-		if (smiapp_read_nvm(sensor, sensor->nvm)) {
-			dev_err(&client->dev, "nvm read failed\n");
-			return -ENODEV;
-		}
+	pm_runtime_mark_last_busy(&client->dev);
+	pm_runtime_put_autosuspend(&client->dev);
 
-		pm_runtime_mark_last_busy(&client->dev);
-		pm_runtime_put_autosuspend(&client->dev);
-	}
 	/*
 	 * NVM is still way below a PAGE_SIZE, so we can safely
 	 * assume this for now.
 	 */
-	nbytes = min_t(unsigned int, sensor->nvm_size, PAGE_SIZE);
-	memcpy(buf, sensor->nvm, nbytes);
-
-	return nbytes;
+	return rval;
 }
 static DEVICE_ATTR(nvm, S_IRUGO, smiapp_sysfs_nvm_read, NULL);
 
@@ -2810,16 +2777,13 @@ static struct smiapp_hwconfig *smiapp_get_hwconfig(struct device *dev)
 		}
 	}
 
-	/* NVM size is not mandatory */
-	fwnode_property_read_u32(fwnode, "nokia,nvm-size", &hwcfg->nvm_size);
-
 	rval = fwnode_property_read_u32(dev_fwnode(dev), "clock-frequency",
 					&hwcfg->ext_clk);
 	if (rval)
 		dev_info(dev, "can't get clock-frequency\n");
 
-	dev_dbg(dev, "nvm %d, clk %d, mode %d\n",
-		hwcfg->nvm_size, hwcfg->ext_clk, hwcfg->csi_signalling_mode);
+	dev_dbg(dev, "clk %d, mode %d\n", hwcfg->ext_clk,
+		hwcfg->csi_signalling_mode);
 
 	if (!bus_cfg.nr_of_link_frequencies) {
 		dev_warn(dev, "no link frequencies defined\n");
@@ -2862,7 +2826,6 @@ static int smiapp_probe(struct i2c_client *client)
 		return -ENOMEM;
 
 	sensor->hwcfg = hwcfg;
-	mutex_init(&sensor->mutex);
 	sensor->src = &sensor->ssds[sensor->ssds_used];
 
 	v4l2_i2c_subdev_init(&sensor->src->sd, client, &smiapp_ops);
@@ -2926,6 +2889,8 @@ static int smiapp_probe(struct i2c_client *client)
 	if (rval < 0)
 		return rval;
 
+	mutex_init(&sensor->mutex);
+
 	rval = smiapp_identify_module(sensor);
 	if (rval) {
 		rval = -ENODEV;
@@ -3003,17 +2968,10 @@ static int smiapp_probe(struct i2c_client *client)
 		rval = -ENOENT;
 		goto out_power_off;
 	}
-	/* SMIA++ NVM initialization - it will be read from the sensor
-	 * when it is first requested by userspace.
-	 */
-	if (sensor->minfo.smiapp_version && sensor->hwcfg->nvm_size) {
-		sensor->nvm = devm_kzalloc(&client->dev,
-				sensor->hwcfg->nvm_size, GFP_KERNEL);
-		if (sensor->nvm == NULL) {
-			rval = -ENOMEM;
-			goto out_cleanup;
-		}
 
+	if (sensor->minfo.smiapp_version &&
+	    sensor->limits[SMIAPP_LIMIT_DATA_TRANSFER_IF_CAPABILITY] &
+	    SMIAPP_DATA_TRANSFER_IF_CAPABILITY_SUPPORTED) {
 		if (device_create_file(&client->dev, &dev_attr_nvm) != 0) {
 			dev_err(&client->dev, "sysfs nvm entry failed\n");
 			rval = -EBUSY;
@@ -3086,7 +3044,7 @@ static int smiapp_probe(struct i2c_client *client)
 	}
 
 	mutex_lock(&sensor->mutex);
-	rval = smiapp_update_mode(sensor);
+	rval = smiapp_pll_blanking_update(sensor);
 	mutex_unlock(&sensor->mutex);
 	if (rval) {
 		dev_err(&client->dev, "update mode failed\n");
@@ -3101,19 +3059,23 @@ static int smiapp_probe(struct i2c_client *client)
 	if (rval < 0)
 		goto out_media_entity_cleanup;
 
-	rval = v4l2_async_register_subdev_sensor_common(&sensor->src->sd);
-	if (rval < 0)
-		goto out_media_entity_cleanup;
-
 	pm_runtime_set_active(&client->dev);
 	pm_runtime_get_noresume(&client->dev);
 	pm_runtime_enable(&client->dev);
+
+	rval = v4l2_async_register_subdev_sensor_common(&sensor->src->sd);
+	if (rval < 0)
+		goto out_disable_runtime_pm;
+
 	pm_runtime_set_autosuspend_delay(&client->dev, 1000);
 	pm_runtime_use_autosuspend(&client->dev);
 	pm_runtime_put_autosuspend(&client->dev);
 
 	return 0;
 
+out_disable_runtime_pm:
+	pm_runtime_disable(&client->dev);
+
 out_media_entity_cleanup:
 	media_entity_cleanup(&sensor->src->sd.entity);
 
@@ -3122,6 +3084,7 @@ out_cleanup:
 
 out_power_off:
 	smiapp_power_off(&client->dev);
+	mutex_destroy(&sensor->mutex);
 
 	return rval;
 }
@@ -3144,6 +3107,7 @@ static int smiapp_remove(struct i2c_client *client)
 		media_entity_cleanup(&sensor->ssds[i].sd.entity);
 	}
 	smiapp_cleanup(sensor);
+	mutex_destroy(&sensor->mutex);
 
 	return 0;
 }
diff --git a/drivers/media/i2c/smiapp/smiapp-reg.h b/drivers/media/i2c/smiapp/smiapp-reg.h
index 2804a4d9a4e1..43505cd0616e 100644
--- a/drivers/media/i2c/smiapp/smiapp-reg.h
+++ b/drivers/media/i2c/smiapp/smiapp-reg.h
@@ -11,25 +11,29 @@
 #ifndef __SMIAPP_REG_H_
 #define __SMIAPP_REG_H_
 
+#include <linux/bits.h>
+
 #include "smiapp-reg-defs.h"
 
 /* Bits for above register */
-#define SMIAPP_IMAGE_ORIENTATION_HFLIP		(1 << 0)
-#define SMIAPP_IMAGE_ORIENTATION_VFLIP		(1 << 1)
-
-#define SMIAPP_DATA_TRANSFER_IF_1_CTRL_EN		(1 << 0)
-#define SMIAPP_DATA_TRANSFER_IF_1_CTRL_RD_EN		(0 << 1)
-#define SMIAPP_DATA_TRANSFER_IF_1_CTRL_WR_EN		(1 << 1)
-#define SMIAPP_DATA_TRANSFER_IF_1_CTRL_ERR_CLEAR	(1 << 2)
-#define SMIAPP_DATA_TRANSFER_IF_1_STATUS_RD_READY	(1 << 0)
-#define SMIAPP_DATA_TRANSFER_IF_1_STATUS_WR_READY	(1 << 1)
-#define SMIAPP_DATA_TRANSFER_IF_1_STATUS_EDATA		(1 << 2)
-#define SMIAPP_DATA_TRANSFER_IF_1_STATUS_EUSAGE		(1 << 3)
-
-#define SMIAPP_SOFTWARE_RESET				(1 << 0)
-
-#define SMIAPP_FLASH_MODE_CAPABILITY_SINGLE_STROBE	(1 << 0)
-#define SMIAPP_FLASH_MODE_CAPABILITY_MULTIPLE_STROBE	(1 << 1)
+#define SMIAPP_IMAGE_ORIENTATION_HFLIP			BIT(0)
+#define SMIAPP_IMAGE_ORIENTATION_VFLIP			BIT(1)
+
+#define SMIAPP_DATA_TRANSFER_IF_1_CTRL_EN		BIT(0)
+#define SMIAPP_DATA_TRANSFER_IF_1_CTRL_WR_EN		BIT(1)
+#define SMIAPP_DATA_TRANSFER_IF_1_CTRL_ERR_CLEAR	BIT(2)
+#define SMIAPP_DATA_TRANSFER_IF_1_STATUS_RD_READY	BIT(0)
+#define SMIAPP_DATA_TRANSFER_IF_1_STATUS_WR_READY	BIT(1)
+#define SMIAPP_DATA_TRANSFER_IF_1_STATUS_EDATA		BIT(2)
+#define SMIAPP_DATA_TRANSFER_IF_1_STATUS_EUSAGE		BIT(3)
+
+#define SMIAPP_DATA_TRANSFER_IF_CAPABILITY_SUPPORTED	BIT(0)
+#define SMIAPP_DATA_TRANSFER_IF_CAPABILITY_POLL		BIT(2)
+
+#define SMIAPP_SOFTWARE_RESET				BIT(0)
+
+#define SMIAPP_FLASH_MODE_CAPABILITY_SINGLE_STROBE	BIT(0)
+#define SMIAPP_FLASH_MODE_CAPABILITY_MULTIPLE_STROBE	BIT(1)
 
 #define SMIAPP_DPHY_CTRL_AUTOMATIC			0
 /* DPHY control based on REQUESTED_LINK_BIT_RATE_MBPS */
diff --git a/drivers/media/i2c/smiapp/smiapp.h b/drivers/media/i2c/smiapp/smiapp.h
index ecf8a17dbe37..3ab874a5deba 100644
--- a/drivers/media/i2c/smiapp/smiapp.h
+++ b/drivers/media/i2c/smiapp/smiapp.h
@@ -208,9 +208,6 @@ struct smiapp_sensor {
 	bool dev_init_done;
 	u8 compressed_min_bpp;
 
-	u8 *nvm;		/* nvm memory buffer */
-	unsigned int nvm_size;	/* bytes */
-
 	struct smiapp_module_info minfo;
 
 	struct smiapp_pll pll;
diff --git a/drivers/media/i2c/st-mipid02.c b/drivers/media/i2c/st-mipid02.c
index 81285b8d5cfb..003ba22334cd 100644
--- a/drivers/media/i2c/st-mipid02.c
+++ b/drivers/media/i2c/st-mipid02.c
@@ -971,6 +971,11 @@ static int mipid02_probe(struct i2c_client *client)
 	bridge->reset_gpio = devm_gpiod_get_optional(dev, "reset",
 						     GPIOD_OUT_HIGH);
 
+	if (IS_ERR(bridge->reset_gpio)) {
+		dev_err(dev, "failed to get reset GPIO\n");
+		return PTR_ERR(bridge->reset_gpio);
+	}
+
 	ret = mipid02_get_regulators(bridge);
 	if (ret) {
 		dev_err(dev, "failed to get regulators %d", ret);
diff --git a/drivers/media/i2c/tda1997x_regs.h b/drivers/media/i2c/tda1997x_regs.h
index ecf87534613b..d9b3daada07d 100644
--- a/drivers/media/i2c/tda1997x_regs.h
+++ b/drivers/media/i2c/tda1997x_regs.h
@@ -1,4 +1,4 @@
-// SPDX-License-Identifier: GPL-2.0
+/* SPDX-License-Identifier: GPL-2.0 */
 /*
  * Copyright (C) 2018 Gateworks Corporation
  */
diff --git a/drivers/media/i2c/tvp5150_reg.h b/drivers/media/i2c/tvp5150_reg.h
index 9088186c24d1..f716129adf09 100644
--- a/drivers/media/i2c/tvp5150_reg.h
+++ b/drivers/media/i2c/tvp5150_reg.h
@@ -1,5 +1,5 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 /*
- * SPDX-License-Identifier: GPL-2.0
  *
  * tvp5150 - Texas Instruments TVP5150A/AM1 video decoder registers
  *
diff --git a/drivers/media/i2c/vpx3220.c b/drivers/media/i2c/vpx3220.c
index 39f66e7a0e42..8be03fe5928c 100644
--- a/drivers/media/i2c/vpx3220.c
+++ b/drivers/media/i2c/vpx3220.c
@@ -375,7 +375,7 @@ static int vpx3220_s_routing(struct v4l2_subdev *sd,
 		 input = 1: COMPOSITE  input
 		 input = 2: SVHS       input  */
 
-	const int input_vals[3][2] = {
+	static const int input_vals[3][2] = {
 		{0x0c, 0},
 		{0x0d, 0},
 		{0x0e, 1}
diff --git a/drivers/media/mc/mc-device.c b/drivers/media/mc/mc-device.c
index e19df5165e78..da8088351135 100644
--- a/drivers/media/mc/mc-device.c
+++ b/drivers/media/mc/mc-device.c
@@ -575,6 +575,38 @@ static void media_device_release(struct media_devnode *devnode)
 	dev_dbg(devnode->parent, "Media device released\n");
 }
 
+static void __media_device_unregister_entity(struct media_entity *entity)
+{
+	struct media_device *mdev = entity->graph_obj.mdev;
+	struct media_link *link, *tmp;
+	struct media_interface *intf;
+	unsigned int i;
+
+	ida_free(&mdev->entity_internal_idx, entity->internal_idx);
+
+	/* Remove all interface links pointing to this entity */
+	list_for_each_entry(intf, &mdev->interfaces, graph_obj.list) {
+		list_for_each_entry_safe(link, tmp, &intf->links, list) {
+			if (link->entity == entity)
+				__media_remove_intf_link(link);
+		}
+	}
+
+	/* Remove all data links that belong to this entity */
+	__media_entity_remove_links(entity);
+
+	/* Remove all pads that belong to this entity */
+	for (i = 0; i < entity->num_pads; i++)
+		media_gobj_destroy(&entity->pads[i].graph_obj);
+
+	/* Remove the entity */
+	media_gobj_destroy(&entity->graph_obj);
+
+	/* invoke entity_notify callbacks to handle entity removal?? */
+
+	entity->graph_obj.mdev = NULL;
+}
+
 /**
  * media_device_register_entity - Register an entity with a media device
  * @mdev:	The media device
@@ -632,6 +664,7 @@ int __must_check media_device_register_entity(struct media_device *mdev,
 		 */
 		ret = media_graph_walk_init(&new, mdev);
 		if (ret) {
+			__media_device_unregister_entity(entity);
 			mutex_unlock(&mdev->graph_mutex);
 			return ret;
 		}
@@ -644,38 +677,6 @@ int __must_check media_device_register_entity(struct media_device *mdev,
 }
 EXPORT_SYMBOL_GPL(media_device_register_entity);
 
-static void __media_device_unregister_entity(struct media_entity *entity)
-{
-	struct media_device *mdev = entity->graph_obj.mdev;
-	struct media_link *link, *tmp;
-	struct media_interface *intf;
-	unsigned int i;
-
-	ida_free(&mdev->entity_internal_idx, entity->internal_idx);
-
-	/* Remove all interface links pointing to this entity */
-	list_for_each_entry(intf, &mdev->interfaces, graph_obj.list) {
-		list_for_each_entry_safe(link, tmp, &intf->links, list) {
-			if (link->entity == entity)
-				__media_remove_intf_link(link);
-		}
-	}
-
-	/* Remove all data links that belong to this entity */
-	__media_entity_remove_links(entity);
-
-	/* Remove all pads that belong to this entity */
-	for (i = 0; i < entity->num_pads; i++)
-		media_gobj_destroy(&entity->pads[i].graph_obj);
-
-	/* Remove the entity */
-	media_gobj_destroy(&entity->graph_obj);
-
-	/* invoke entity_notify callbacks to handle entity removal?? */
-
-	entity->graph_obj.mdev = NULL;
-}
-
 void media_device_unregister_entity(struct media_entity *entity)
 {
 	struct media_device *mdev = entity->graph_obj.mdev;
diff --git a/drivers/media/pci/cx18/cx18-ioctl.c b/drivers/media/pci/cx18/cx18-ioctl.c
index 85f3e7307538..fa57e12f2ac8 100644
--- a/drivers/media/pci/cx18/cx18-ioctl.c
+++ b/drivers/media/pci/cx18/cx18-ioctl.c
@@ -664,7 +664,7 @@ static int _cx18_process_idx_data(struct cx18_buffer *buf,
 	struct cx18_enc_idx_entry *e_buf;
 
 	/* Frame type lookup: 1=I, 2=P, 4=B */
-	const int mapping[8] = {
+	static const int mapping[8] = {
 		-1, V4L2_ENC_IDX_FRAME_I, V4L2_ENC_IDX_FRAME_P,
 		-1, V4L2_ENC_IDX_FRAME_B, -1, -1, -1
 	};
diff --git a/drivers/media/pci/cx23885/cx23888-ir.c b/drivers/media/pci/cx23885/cx23888-ir.c
index e880afe37f15..d59ca3601785 100644
--- a/drivers/media/pci/cx23885/cx23888-ir.c
+++ b/drivers/media/pci/cx23885/cx23888-ir.c
@@ -1167,8 +1167,11 @@ int cx23888_ir_probe(struct cx23885_dev *dev)
 		return -ENOMEM;
 
 	spin_lock_init(&state->rx_kfifo_lock);
-	if (kfifo_alloc(&state->rx_kfifo, CX23888_IR_RX_KFIFO_SIZE, GFP_KERNEL))
+	if (kfifo_alloc(&state->rx_kfifo, CX23888_IR_RX_KFIFO_SIZE,
+			GFP_KERNEL)) {
+		kfree(state);
 		return -ENOMEM;
+	}
 
 	state->dev = dev;
 	sd = &state->sd;
diff --git a/drivers/media/pci/cx88/cx88-cards.c b/drivers/media/pci/cx88/cx88-cards.c
index 3cd87626cd79..9fa388626bae 100644
--- a/drivers/media/pci/cx88/cx88-cards.c
+++ b/drivers/media/pci/cx88/cx88-cards.c
@@ -1781,6 +1781,41 @@ static const struct cx88_board cx88_boards[] = {
 		},
 		.mpeg           = CX88_MPEG_DVB,
 	},
+	[CX88_BOARD_NOTONLYTV_LV3H] = {
+		.name           = "NotOnlyTV LV3H",
+		.tuner_type     = TUNER_XC2028,
+		.radio_type     = UNSET,
+		.tuner_addr     = 0x61,
+		.radio_addr     = ADDR_UNSET,
+		/* if gpio1:bit9 is enabled, DVB-T won't work */
+
+		.input          = { {
+			.type   = CX88_VMUX_TELEVISION,
+			.vmux   = 0,
+			.gpio0  = 0x0000,
+			.gpio1  = 0xa141,
+			.gpio2  = 0x0000,
+		}, {
+			.type   = CX88_VMUX_COMPOSITE1,
+			.vmux   = 1,
+			.gpio0  = 0x0000,
+			.gpio1  = 0xa161,
+			.gpio2  = 0x0000,
+		}, {
+			.type   = CX88_VMUX_SVIDEO,
+			.vmux   = 2,
+			.gpio0  = 0x0000,
+			.gpio1  = 0xa161,
+			.gpio2  = 0x0000,
+		} },
+		.radio = {
+			.type   = CX88_RADIO,
+			.gpio0  = 0x0000,
+			.gpio1  = 0xa141,
+			.gpio2  = 0x0000,
+		},
+		.mpeg           = CX88_MPEG_DVB,
+	},
 	[CX88_BOARD_DVICO_FUSIONHDTV_DVB_T_PRO] = {
 		.name           = "DViCO FusionHDTV DVB-T PRO",
 		.tuner_type     = TUNER_XC2028,
@@ -2654,6 +2689,7 @@ static const struct cx88_subid cx88_subids[] = {
 		.subdevice = 0x6f18,
 		.card      = CX88_BOARD_WINFAST_TV2000_XP_GLOBAL,
 	}, {
+		/* Also NotOnlyTV LV3H (version 1.11 is silkscreened on the board) */
 		.subvendor = 0x14f1,
 		.subdevice = 0x8852,
 		.card      = CX88_BOARD_GENIATECH_X8000_MT,
@@ -3121,6 +3157,7 @@ static int cx88_xc2028_tuner_callback(struct cx88_core *core,
 	case CX88_BOARD_DVICO_FUSIONHDTV_DVB_T_PRO:
 	case CX88_BOARD_DVICO_FUSIONHDTV_5_PCI_NANO:
 		return cx88_dvico_xc2028_callback(core, command, arg);
+	case CX88_BOARD_NOTONLYTV_LV3H:
 	case CX88_BOARD_WINFAST_TV2000_XP_GLOBAL:
 	case CX88_BOARD_WINFAST_DTV1800H:
 		return cx88_xc3028_winfast1800h_callback(core, command, arg);
@@ -3322,6 +3359,7 @@ static void cx88_card_setup_pre_i2c(struct cx88_core *core)
 		udelay(1000);
 		break;
 
+	case CX88_BOARD_NOTONLYTV_LV3H:
 	case CX88_BOARD_WINFAST_TV2000_XP_GLOBAL:
 	case CX88_BOARD_WINFAST_DTV1800H:
 		cx88_xc3028_winfast1800h_callback(core, XC2028_TUNER_RESET, 0);
@@ -3378,6 +3416,11 @@ void cx88_setup_xc3028(struct cx88_core *core, struct xc2028_ctrl *ctl)
 		 */
 		ctl->disable_power_mgmt = 1;
 		break;
+	case CX88_BOARD_NOTONLYTV_LV3H:
+		ctl->demod			= XC3028_FE_ZARLINK456;
+		ctl->fname			= XC3028L_DEFAULT_FIRMWARE;
+		ctl->read_not_reliable	= 1;
+		break;
 	case CX88_BOARD_WINFAST_TV2000_XP_GLOBAL:
 	case CX88_BOARD_PROLINK_PV_GLOBAL_XTREME:
 	case CX88_BOARD_PROLINK_PV_8000GT:
diff --git a/drivers/media/pci/cx88/cx88-dvb.c b/drivers/media/pci/cx88/cx88-dvb.c
index 0292d0947cc7..202ff9e8c257 100644
--- a/drivers/media/pci/cx88/cx88-dvb.c
+++ b/drivers/media/pci/cx88/cx88-dvb.c
@@ -1378,6 +1378,7 @@ static int dvb_register(struct cx8802_dev *dev)
 				fe->ops.tuner_ops.set_config(fe, &ctl);
 		}
 		break;
+	case CX88_BOARD_NOTONLYTV_LV3H:
 	case CX88_BOARD_PINNACLE_HYBRID_PCTV:
 	case CX88_BOARD_WINFAST_DTV1800H:
 		fe0->dvb.frontend = dvb_attach(zl10353_attach,
diff --git a/drivers/media/pci/cx88/cx88-video.c b/drivers/media/pci/cx88/cx88-video.c
index dcc0f02aeb70..b8abcd550604 100644
--- a/drivers/media/pci/cx88/cx88-video.c
+++ b/drivers/media/pci/cx88/cx88-video.c
@@ -1277,7 +1277,7 @@ static int cx8800_initdev(struct pci_dev *pci_dev,
 	core = cx88_core_get(dev->pci);
 	if (!core) {
 		err = -EINVAL;
-		goto fail_free;
+		goto fail_disable;
 	}
 	dev->core = core;
 
@@ -1323,7 +1323,7 @@ static int cx8800_initdev(struct pci_dev *pci_dev,
 				       cc->step, cc->default_value);
 		if (!vc) {
 			err = core->audio_hdl.error;
-			goto fail_core;
+			goto fail_irq;
 		}
 		vc->priv = (void *)cc;
 	}
@@ -1337,7 +1337,7 @@ static int cx8800_initdev(struct pci_dev *pci_dev,
 				       cc->step, cc->default_value);
 		if (!vc) {
 			err = core->video_hdl.error;
-			goto fail_core;
+			goto fail_irq;
 		}
 		vc->priv = (void *)cc;
 		if (vc->id == V4L2_CID_CHROMA_AGC)
@@ -1509,11 +1509,14 @@ static int cx8800_initdev(struct pci_dev *pci_dev,
 
 fail_unreg:
 	cx8800_unregister_video(dev);
-	free_irq(pci_dev->irq, dev);
 	mutex_unlock(&core->lock);
+fail_irq:
+	free_irq(pci_dev->irq, dev);
 fail_core:
 	core->v4ldev = NULL;
 	cx88_core_put(core, dev->pci);
+fail_disable:
+	pci_disable_device(pci_dev);
 fail_free:
 	kfree(dev);
 	return err;
diff --git a/drivers/media/pci/cx88/cx88.h b/drivers/media/pci/cx88/cx88.h
index 744a22328ebc..ce4acf6de6aa 100644
--- a/drivers/media/pci/cx88/cx88.h
+++ b/drivers/media/pci/cx88/cx88.h
@@ -228,6 +228,7 @@ extern const struct sram_channel cx88_sram_channels[];
 #define CX88_BOARD_WINFAST_DTV1800H_XC4000 88
 #define CX88_BOARD_WINFAST_TV2000_XP_GLOBAL_6F36 89
 #define CX88_BOARD_WINFAST_TV2000_XP_GLOBAL_6F43 90
+#define CX88_BOARD_NOTONLYTV_LV3H          91
 
 enum cx88_itype {
 	CX88_VMUX_COMPOSITE1 = 1,
diff --git a/drivers/media/pci/dm1105/dm1105.c b/drivers/media/pci/dm1105/dm1105.c
index bb3a8cc9de0c..9dce31d2b525 100644
--- a/drivers/media/pci/dm1105/dm1105.c
+++ b/drivers/media/pci/dm1105/dm1105.c
@@ -11,7 +11,6 @@
 #include <linux/interrupt.h>
 #include <linux/kernel.h>
 #include <linux/module.h>
-#include <linux/proc_fs.h>
 #include <linux/pci.h>
 #include <linux/dma-mapping.h>
 #include <linux/slab.h>
diff --git a/drivers/media/pci/ivtv/ivtv-vbi.c b/drivers/media/pci/ivtv/ivtv-vbi.c
index 6d22c0107d33..80478b026d75 100644
--- a/drivers/media/pci/ivtv/ivtv-vbi.c
+++ b/drivers/media/pci/ivtv/ivtv-vbi.c
@@ -325,7 +325,7 @@ static u32 compress_raw_buf(struct ivtv *itv, u8 *buf, u32 size)
 static u32 compress_sliced_buf(struct ivtv *itv, u32 line, u8 *buf, u32 size, u8 sav)
 {
 	u32 line_size = itv->vbi.sliced_decoder_line_size;
-	struct v4l2_decode_vbi_line vbi;
+	struct v4l2_decode_vbi_line vbi = {};
 	int i;
 	unsigned lines = 0;
 
diff --git a/drivers/media/pci/mantis/hopper_cards.c b/drivers/media/pci/mantis/hopper_cards.c
index 67aebe759232..c0bd5d7e148b 100644
--- a/drivers/media/pci/mantis/hopper_cards.c
+++ b/drivers/media/pci/mantis/hopper_cards.c
@@ -60,10 +60,8 @@ static irqreturn_t hopper_irq_handler(int irq, void *dev_id)
 	struct mantis_ca *ca;
 
 	mantis = (struct mantis_pci *) dev_id;
-	if (unlikely(!mantis)) {
-		dprintk(MANTIS_ERROR, 1, "Mantis == NULL");
+	if (unlikely(!mantis))
 		return IRQ_NONE;
-	}
 	ca = mantis->mantis_ca;
 
 	stat = mmread(MANTIS_INT_STAT);
diff --git a/drivers/media/pci/mantis/mantis_cards.c b/drivers/media/pci/mantis/mantis_cards.c
index deadd0b92233..906e4500d87d 100644
--- a/drivers/media/pci/mantis/mantis_cards.c
+++ b/drivers/media/pci/mantis/mantis_cards.c
@@ -69,10 +69,8 @@ static irqreturn_t mantis_irq_handler(int irq, void *dev_id)
 	struct mantis_ca *ca;
 
 	mantis = (struct mantis_pci *) dev_id;
-	if (unlikely(mantis == NULL)) {
-		dprintk(MANTIS_ERROR, 1, "Mantis == NULL");
+	if (unlikely(!mantis))
 		return IRQ_NONE;
-	}
 	ca = mantis->mantis_ca;
 
 	stat = mmread(MANTIS_INT_STAT);
diff --git a/drivers/media/pci/saa7164/saa7164-core.c b/drivers/media/pci/saa7164/saa7164-core.c
index 9ae04e18e6c6..126d085be9a7 100644
--- a/drivers/media/pci/saa7164/saa7164-core.c
+++ b/drivers/media/pci/saa7164/saa7164-core.c
@@ -13,12 +13,10 @@
 #include <linux/kernel.h>
 #include <linux/slab.h>
 #include <linux/interrupt.h>
+#include <linux/debugfs.h>
 #include <linux/delay.h>
 #include <asm/div64.h>
 
-#ifdef CONFIG_PROC_FS
-#include <linux/proc_fs.h>
-#endif
 #include "saa7164.h"
 
 MODULE_DESCRIPTION("Driver for NXP SAA7164 based TV cards");
@@ -1045,92 +1043,138 @@ static void saa7164_dev_unregister(struct saa7164_dev *dev)
 	return;
 }
 
-#ifdef CONFIG_PROC_FS
-static int saa7164_proc_show(struct seq_file *m, void *v)
+#ifdef CONFIG_DEBUG_FS
+static void *saa7164_seq_start(struct seq_file *s, loff_t *pos)
 {
 	struct saa7164_dev *dev;
-	struct tmComResBusInfo *b;
-	struct list_head *list;
-	int i, c;
+	loff_t index = *pos;
 
-	if (saa7164_devcount == 0)
-		return 0;
+	mutex_lock(&devlist);
+	list_for_each_entry(dev, &saa7164_devlist, devlist) {
+		if (index-- == 0) {
+			mutex_unlock(&devlist);
+			return dev;
+		}
+	}
+	mutex_unlock(&devlist);
 
-	list_for_each(list, &saa7164_devlist) {
-		dev = list_entry(list, struct saa7164_dev, devlist);
-		seq_printf(m, "%s = %p\n", dev->name, dev);
+	return NULL;
+}
 
-		/* Lock the bus from any other access */
-		b = &dev->bus;
-		mutex_lock(&b->lock);
+static void *saa7164_seq_next(struct seq_file *s, void *v, loff_t *pos)
+{
+	struct saa7164_dev *dev = v;
+	void *ret;
 
-		seq_printf(m, " .m_pdwSetWritePos = 0x%x (0x%08x)\n",
-			b->m_dwSetReadPos, saa7164_readl(b->m_dwSetReadPos));
+	mutex_lock(&devlist);
+	if (list_is_last(&dev->devlist, &saa7164_devlist))
+		ret = NULL;
+	else
+		ret = list_next_entry(dev, devlist);
+	mutex_unlock(&devlist);
 
-		seq_printf(m, " .m_pdwSetReadPos  = 0x%x (0x%08x)\n",
-			b->m_dwSetWritePos, saa7164_readl(b->m_dwSetWritePos));
+	++*pos;
 
-		seq_printf(m, " .m_pdwGetWritePos = 0x%x (0x%08x)\n",
-			b->m_dwGetReadPos, saa7164_readl(b->m_dwGetReadPos));
+	return ret;
+}
 
-		seq_printf(m, " .m_pdwGetReadPos  = 0x%x (0x%08x)\n",
-			b->m_dwGetWritePos, saa7164_readl(b->m_dwGetWritePos));
-		c = 0;
-		seq_printf(m, "\n  Set Ring:\n");
-		seq_printf(m, "\n addr  00 01 02 03 04 05 06 07 08 09 0a 0b 0c 0d 0e 0f\n");
-		for (i = 0; i < b->m_dwSizeSetRing; i++) {
-			if (c == 0)
-				seq_printf(m, " %04x:", i);
+static void saa7164_seq_stop(struct seq_file *s, void *v)
+{
+}
 
-			seq_printf(m, " %02x", readb(b->m_pdwSetRing + i));
+static int saa7164_seq_show(struct seq_file *m, void *v)
+{
+	struct saa7164_dev *dev = v;
+	struct tmComResBusInfo *b;
+	int i, c;
 
-			if (++c == 16) {
-				seq_printf(m, "\n");
-				c = 0;
-			}
-		}
+	seq_printf(m, "%s = %p\n", dev->name, dev);
 
-		c = 0;
-		seq_printf(m, "\n  Get Ring:\n");
-		seq_printf(m, "\n addr  00 01 02 03 04 05 06 07 08 09 0a 0b 0c 0d 0e 0f\n");
-		for (i = 0; i < b->m_dwSizeGetRing; i++) {
-			if (c == 0)
-				seq_printf(m, " %04x:", i);
+	/* Lock the bus from any other access */
+	b = &dev->bus;
+	mutex_lock(&b->lock);
 
-			seq_printf(m, " %02x", readb(b->m_pdwGetRing + i));
+	seq_printf(m, " .m_pdwSetWritePos = 0x%x (0x%08x)\n",
+		   b->m_dwSetReadPos, saa7164_readl(b->m_dwSetReadPos));
 
-			if (++c == 16) {
-				seq_printf(m, "\n");
-				c = 0;
-			}
+	seq_printf(m, " .m_pdwSetReadPos  = 0x%x (0x%08x)\n",
+		   b->m_dwSetWritePos, saa7164_readl(b->m_dwSetWritePos));
+
+	seq_printf(m, " .m_pdwGetWritePos = 0x%x (0x%08x)\n",
+		   b->m_dwGetReadPos, saa7164_readl(b->m_dwGetReadPos));
+
+	seq_printf(m, " .m_pdwGetReadPos  = 0x%x (0x%08x)\n",
+		   b->m_dwGetWritePos, saa7164_readl(b->m_dwGetWritePos));
+	c = 0;
+	seq_puts(m, "\n  Set Ring:\n");
+	seq_puts(m, "\n addr  00 01 02 03 04 05 06 07 08 09 0a 0b 0c 0d 0e 0f\n");
+	for (i = 0; i < b->m_dwSizeSetRing; i++) {
+		if (c == 0)
+			seq_printf(m, " %04x:", i);
+
+		seq_printf(m, " %02x", readb(b->m_pdwSetRing + i));
+
+		if (++c == 16) {
+			seq_puts(m, "\n");
+			c = 0;
 		}
+	}
 
-		mutex_unlock(&b->lock);
+	c = 0;
+	seq_puts(m, "\n  Get Ring:\n");
+	seq_puts(m, "\n addr  00 01 02 03 04 05 06 07 08 09 0a 0b 0c 0d 0e 0f\n");
+	for (i = 0; i < b->m_dwSizeGetRing; i++) {
+		if (c == 0)
+			seq_printf(m, " %04x:", i);
 
+		seq_printf(m, " %02x", readb(b->m_pdwGetRing + i));
+
+		if (++c == 16) {
+			seq_puts(m, "\n");
+			c = 0;
+		}
 	}
 
+	mutex_unlock(&b->lock);
+
 	return 0;
 }
 
-static struct proc_dir_entry *saa7164_pe;
+static const struct seq_operations saa7164_seq_ops = {
+	.start = saa7164_seq_start,
+	.next = saa7164_seq_next,
+	.stop = saa7164_seq_stop,
+	.show = saa7164_seq_show,
+};
 
-static int saa7164_proc_create(void)
+static int saa7164_open(struct inode *inode, struct file *file)
 {
-	saa7164_pe = proc_create_single("saa7164", 0444, NULL, saa7164_proc_show);
-	if (!saa7164_pe)
-		return -ENOMEM;
+	return seq_open(file, &saa7164_seq_ops);
+}
 
-	return 0;
+static const struct file_operations saa7164_operations = {
+	.owner          = THIS_MODULE,
+	.open           = saa7164_open,
+	.read           = seq_read,
+	.llseek         = seq_lseek,
+	.release        = seq_release,
+};
+
+static struct dentry *saa7614_dentry;
+
+static void __init saa7164_debugfs_create(void)
+{
+	saa7614_dentry = debugfs_create_file("saa7164", 0444, NULL, NULL,
+					     &saa7164_operations);
 }
 
-static void saa7164_proc_destroy(void)
+static void __exit saa7164_debugfs_remove(void)
 {
-	if (saa7164_pe)
-		remove_proc_entry("saa7164", NULL);
+	debugfs_remove(saa7614_dentry);
 }
 #else
-static int saa7164_proc_create(void) { return 0; }
-static void saa7164_proc_destroy(void) {}
+static void saa7164_debugfs_create(void) { }
+static void saa7164_debugfs_remove(void) { }
 #endif
 
 static int saa7164_thread_function(void *data)
@@ -1507,7 +1551,7 @@ static int __init saa7164_init(void)
 	if (ret)
 		return ret;
 
-	saa7164_proc_create();
+	saa7164_debugfs_create();
 
 	pr_info("saa7164 driver loaded\n");
 
@@ -1516,7 +1560,7 @@ static int __init saa7164_init(void)
 
 static void __exit saa7164_fini(void)
 {
-	saa7164_proc_destroy();
+	saa7164_debugfs_remove();
 	pci_unregister_driver(&saa7164_pci_driver);
 }
 
diff --git a/drivers/media/pci/smipcie/smipcie.h b/drivers/media/pci/smipcie/smipcie.h
index 65bc7e29450b..2b5e0154814c 100644
--- a/drivers/media/pci/smipcie/smipcie.h
+++ b/drivers/media/pci/smipcie/smipcie.h
@@ -14,7 +14,6 @@
 #include <linux/interrupt.h>
 #include <linux/kernel.h>
 #include <linux/module.h>
-#include <linux/proc_fs.h>
 #include <linux/pci.h>
 #include <linux/dma-mapping.h>
 #include <linux/slab.h>
diff --git a/drivers/media/pci/solo6x10/solo6x10-g723.c b/drivers/media/pci/solo6x10/solo6x10-g723.c
index 30c8f2ec9c3c..eaa57d835ea8 100644
--- a/drivers/media/pci/solo6x10/solo6x10-g723.c
+++ b/drivers/media/pci/solo6x10/solo6x10-g723.c
@@ -353,7 +353,7 @@ static int solo_snd_pcm_init(struct solo_dev *solo_dev)
 
 	snd_pcm_lib_preallocate_pages_for_all(pcm,
 					SNDRV_DMA_TYPE_CONTINUOUS,
-					snd_dma_continuous_data(GFP_KERNEL),
+					NULL,
 					G723_PERIOD_BYTES * PERIODS,
 					G723_PERIOD_BYTES * PERIODS);
 
diff --git a/drivers/media/pci/tw686x/tw686x-audio.c b/drivers/media/pci/tw686x/tw686x-audio.c
index 40373bd23381..7786e51d19ae 100644
--- a/drivers/media/pci/tw686x/tw686x-audio.c
+++ b/drivers/media/pci/tw686x/tw686x-audio.c
@@ -300,7 +300,7 @@ static int tw686x_snd_pcm_init(struct tw686x_dev *dev)
 
 	snd_pcm_lib_preallocate_pages_for_all(pcm,
 				SNDRV_DMA_TYPE_DEV,
-				snd_dma_pci_data(dev->pci_dev),
+				&dev->pci_dev->dev,
 				TW686X_AUDIO_PAGE_MAX * AUDIO_DMA_SIZE_MAX,
 				TW686X_AUDIO_PAGE_MAX * AUDIO_DMA_SIZE_MAX);
 	return 0;
diff --git a/drivers/media/platform/Kconfig b/drivers/media/platform/Kconfig
index f1f61419fd29..e84f35d3a68e 100644
--- a/drivers/media/platform/Kconfig
+++ b/drivers/media/platform/Kconfig
@@ -483,6 +483,7 @@ config VIDEO_QCOM_VENUS
 	tristate "Qualcomm Venus V4L2 encoder/decoder driver"
 	depends on VIDEO_DEV && VIDEO_V4L2
 	depends on (ARCH_QCOM && IOMMU_DMA) || COMPILE_TEST
+	depends on INTERCONNECT || !INTERCONNECT
 	select QCOM_MDT_LOADER if ARCH_QCOM
 	select QCOM_SCM if ARCH_QCOM
 	select VIDEOBUF2_DMA_SG
@@ -493,6 +494,19 @@ config VIDEO_QCOM_VENUS
 	  on various Qualcomm SoCs.
 	  To compile this driver as a module choose m here.
 
+config VIDEO_SUN8I_DEINTERLACE
+	tristate "Allwinner Deinterlace driver"
+	depends on VIDEO_DEV && VIDEO_V4L2
+	depends on ARCH_SUNXI || COMPILE_TEST
+	depends on COMMON_CLK && OF
+	depends on PM
+	select VIDEOBUF2_DMA_CONTIG
+	select V4L2_MEM2MEM_DEV
+	help
+	   Support for the Allwinner deinterlace unit with scaling
+	   capability found on some SoCs, like H3.
+	   To compile this driver as a module choose m here.
+
 endif # V4L_MEM2MEM_DRIVERS
 
 # TI VIDEO PORT Helper Modules
@@ -585,9 +599,10 @@ config VIDEO_MESON_G12A_AO_CEC
 
 config CEC_GPIO
 	tristate "Generic GPIO-based CEC driver"
-	depends on PREEMPT || COMPILE_TEST
+	depends on PREEMPTION || COMPILE_TEST
 	select CEC_CORE
 	select CEC_PIN
+	select CEC_NOTIFIER
 	select GPIOLIB
 	help
 	  This is a generic GPIO-based CEC driver.
diff --git a/drivers/media/platform/Makefile b/drivers/media/platform/Makefile
index 6ee7eb0d36f4..d13db96e3015 100644
--- a/drivers/media/platform/Makefile
+++ b/drivers/media/platform/Makefile
@@ -19,9 +19,7 @@ obj-$(CONFIG_VIDEO_VIVID)		+= vivid/
 obj-$(CONFIG_VIDEO_VIM2M)		+= vim2m.o
 obj-$(CONFIG_VIDEO_VICODEC)		+= vicodec/
 
-obj-$(CONFIG_VIDEO_TI_VPE)		+= ti-vpe/
-
-obj-$(CONFIG_VIDEO_TI_CAL)		+= ti-vpe/
+obj-y	+= ti-vpe/
 
 obj-$(CONFIG_VIDEO_MX2_EMMAPRP)		+= mx2_emmaprp.o
 obj-$(CONFIG_VIDEO_CODA)		+= coda/
diff --git a/drivers/media/platform/am437x/am437x-vpfe.c b/drivers/media/platform/am437x/am437x-vpfe.c
index 2b42ba1f5949..09104304bd06 100644
--- a/drivers/media/platform/am437x/am437x-vpfe.c
+++ b/drivers/media/platform/am437x/am437x-vpfe.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * TI VPFE capture Driver
  *
@@ -5,19 +6,6 @@
  *
  * Benoit Parrot <bparrot@ti.com>
  * Lad, Prabhakar <prabhakar.csengg@gmail.com>
- *
- * This program is free software; you may redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; version 2 of the License.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
- * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
- * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
- * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
- * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
- * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
- * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
- * SOFTWARE.
  */
 
 #include <linux/delay.h>
@@ -69,125 +57,64 @@ static const struct vpfe_standard vpfe_standards[] = {
 	{V4L2_STD_625_50, 720, 576, {54, 59}, 1},
 };
 
-struct bus_format {
-	unsigned int width;
-	unsigned int bpp;
-};
-
-/*
- * struct vpfe_fmt - VPFE media bus format information
- * @code: V4L2 media bus format code
- * @shifted: V4L2 media bus format code for the same pixel layout but
- *	shifted to be 8 bits per pixel. =0 if format is not shiftable.
- * @pixelformat: V4L2 pixel format FCC identifier
- * @width: Bits per pixel (when transferred over a bus)
- * @bpp: Bytes per pixel (when stored in memory)
- * @supported: Indicates format supported by subdev
- */
-struct vpfe_fmt {
-	u32 fourcc;
-	u32 code;
-	struct bus_format l;
-	struct bus_format s;
-	bool supported;
-	u32 index;
-};
-
-static struct vpfe_fmt formats[] = {
+static struct vpfe_fmt formats[VPFE_NUM_FORMATS] = {
 	{
 		.fourcc		= V4L2_PIX_FMT_YUYV,
 		.code		= MEDIA_BUS_FMT_YUYV8_2X8,
-		.l.width	= 10,
-		.l.bpp		= 4,
-		.s.width	= 8,
-		.s.bpp		= 2,
-		.supported	= false,
+		.bitsperpixel	= 16,
 	}, {
 		.fourcc		= V4L2_PIX_FMT_UYVY,
 		.code		= MEDIA_BUS_FMT_UYVY8_2X8,
-		.l.width	= 10,
-		.l.bpp		= 4,
-		.s.width	= 8,
-		.s.bpp		= 2,
-		.supported	= false,
+		.bitsperpixel	= 16,
 	}, {
 		.fourcc		= V4L2_PIX_FMT_YVYU,
 		.code		= MEDIA_BUS_FMT_YVYU8_2X8,
-		.l.width	= 10,
-		.l.bpp		= 4,
-		.s.width	= 8,
-		.s.bpp		= 2,
-		.supported	= false,
+		.bitsperpixel	= 16,
 	}, {
 		.fourcc		= V4L2_PIX_FMT_VYUY,
 		.code		= MEDIA_BUS_FMT_VYUY8_2X8,
-		.l.width	= 10,
-		.l.bpp		= 4,
-		.s.width	= 8,
-		.s.bpp		= 2,
-		.supported	= false,
+		.bitsperpixel	= 16,
 	}, {
 		.fourcc		= V4L2_PIX_FMT_SBGGR8,
 		.code		= MEDIA_BUS_FMT_SBGGR8_1X8,
-		.l.width	= 10,
-		.l.bpp		= 2,
-		.s.width	= 8,
-		.s.bpp		= 1,
-		.supported	= false,
+		.bitsperpixel	= 8,
 	}, {
 		.fourcc		= V4L2_PIX_FMT_SGBRG8,
 		.code		= MEDIA_BUS_FMT_SGBRG8_1X8,
-		.l.width	= 10,
-		.l.bpp		= 2,
-		.s.width	= 8,
-		.s.bpp		= 1,
-		.supported	= false,
+		.bitsperpixel	= 8,
 	}, {
 		.fourcc		= V4L2_PIX_FMT_SGRBG8,
 		.code		= MEDIA_BUS_FMT_SGRBG8_1X8,
-		.l.width	= 10,
-		.l.bpp		= 2,
-		.s.width	= 8,
-		.s.bpp		= 1,
-		.supported	= false,
+		.bitsperpixel	= 8,
 	}, {
 		.fourcc		= V4L2_PIX_FMT_SRGGB8,
 		.code		= MEDIA_BUS_FMT_SRGGB8_1X8,
-		.l.width	= 10,
-		.l.bpp		= 2,
-		.s.width	= 8,
-		.s.bpp		= 1,
-		.supported	= false,
+		.bitsperpixel	= 8,
 	}, {
 		.fourcc		= V4L2_PIX_FMT_RGB565,
 		.code		= MEDIA_BUS_FMT_RGB565_2X8_LE,
-		.l.width	= 10,
-		.l.bpp		= 4,
-		.s.width	= 8,
-		.s.bpp		= 2,
-		.supported	= false,
+		.bitsperpixel	= 16,
 	}, {
 		.fourcc		= V4L2_PIX_FMT_RGB565X,
 		.code		= MEDIA_BUS_FMT_RGB565_2X8_BE,
-		.l.width	= 10,
-		.l.bpp		= 4,
-		.s.width	= 8,
-		.s.bpp		= 2,
-		.supported	= false,
+		.bitsperpixel	= 16,
 	},
 };
 
-static int
-__vpfe_get_format(struct vpfe_device *vpfe,
-		  struct v4l2_format *format, unsigned int *bpp);
+static int __subdev_get_format(struct vpfe_device *vpfe,
+			       struct v4l2_mbus_framefmt *fmt);
+static int vpfe_calc_format_size(struct vpfe_device *vpfe,
+				 const struct vpfe_fmt *fmt,
+				 struct v4l2_format *f);
 
-static struct vpfe_fmt *find_format_by_code(unsigned int code)
+static struct vpfe_fmt *find_format_by_code(struct vpfe_device *vpfe,
+					    unsigned int code)
 {
 	struct vpfe_fmt *fmt;
 	unsigned int k;
 
-	for (k = 0; k < ARRAY_SIZE(formats); k++) {
-		fmt = &formats[k];
+	for (k = 0; k < vpfe->num_active_fmt; k++) {
+		fmt = vpfe->active_fmt[k];
 		if (fmt->code == code)
 			return fmt;
 	}
@@ -195,13 +122,14 @@ static struct vpfe_fmt *find_format_by_code(unsigned int code)
 	return NULL;
 }
 
-static struct vpfe_fmt *find_format_by_pix(unsigned int pixelformat)
+static struct vpfe_fmt *find_format_by_pix(struct vpfe_device *vpfe,
+					   unsigned int pixelformat)
 {
 	struct vpfe_fmt *fmt;
 	unsigned int k;
 
-	for (k = 0; k < ARRAY_SIZE(formats); k++) {
-		fmt = &formats[k];
+	for (k = 0; k < vpfe->num_active_fmt; k++) {
+		fmt = vpfe->active_fmt[k];
 		if (fmt->fourcc == pixelformat)
 			return fmt;
 	}
@@ -209,48 +137,18 @@ static struct vpfe_fmt *find_format_by_pix(unsigned int pixelformat)
 	return NULL;
 }
 
-static void
-mbus_to_pix(struct vpfe_device *vpfe,
-	    const struct v4l2_mbus_framefmt *mbus,
-	    struct v4l2_pix_format *pix, unsigned int *bpp)
+static unsigned int __get_bytesperpixel(struct vpfe_device *vpfe,
+					const struct vpfe_fmt *fmt)
 {
 	struct vpfe_subdev_info *sdinfo = vpfe->current_subdev;
 	unsigned int bus_width = sdinfo->vpfe_param.bus_width;
-	struct vpfe_fmt *fmt;
-
-	fmt = find_format_by_code(mbus->code);
-	if (WARN_ON(fmt == NULL)) {
-		pr_err("Invalid mbus code set\n");
-		*bpp = 1;
-		return;
-	}
-
-	memset(pix, 0, sizeof(*pix));
-	v4l2_fill_pix_format(pix, mbus);
-	pix->pixelformat = fmt->fourcc;
-	*bpp = (bus_width == 10) ?  fmt->l.bpp : fmt->s.bpp;
+	u32 bpp, bus_width_bytes, clocksperpixel;
 
-	/* pitch should be 32 bytes aligned */
-	pix->bytesperline = ALIGN(pix->width * *bpp, 32);
-	pix->sizeimage = pix->bytesperline * pix->height;
-}
-
-static void pix_to_mbus(struct vpfe_device *vpfe,
-			struct v4l2_pix_format *pix_fmt,
-			struct v4l2_mbus_framefmt *mbus_fmt)
-{
-	struct vpfe_fmt *fmt;
-
-	fmt = find_format_by_pix(pix_fmt->pixelformat);
-	if (!fmt) {
-		/* default to first entry */
-		vpfe_dbg(3, vpfe, "Invalid pixel code: %x, default used instead\n",
-			pix_fmt->pixelformat);
-		fmt = &formats[0];
-	}
+	bus_width_bytes = ALIGN(bus_width, 8) >> 3;
+	clocksperpixel = DIV_ROUND_UP(fmt->bitsperpixel, bus_width);
+	bpp = clocksperpixel * bus_width_bytes;
 
-	memset(mbus_fmt, 0, sizeof(*mbus_fmt));
-	v4l2_fill_mbus_format(mbus_fmt, pix_fmt, fmt->code);
+	return bpp;
 }
 
 /*  Print Four-character-code (FOURCC) */
@@ -267,20 +165,6 @@ static char *print_fourcc(u32 fmt)
 	return code;
 }
 
-static int
-cmp_v4l2_format(const struct v4l2_format *lhs, const struct v4l2_format *rhs)
-{
-	return lhs->type == rhs->type &&
-		lhs->fmt.pix.width == rhs->fmt.pix.width &&
-		lhs->fmt.pix.height == rhs->fmt.pix.height &&
-		lhs->fmt.pix.pixelformat == rhs->fmt.pix.pixelformat &&
-		lhs->fmt.pix.field == rhs->fmt.pix.field &&
-		lhs->fmt.pix.colorspace == rhs->fmt.pix.colorspace &&
-		lhs->fmt.pix.ycbcr_enc == rhs->fmt.pix.ycbcr_enc &&
-		lhs->fmt.pix.quantization == rhs->fmt.pix.quantization &&
-		lhs->fmt.pix.xfer_func == rhs->fmt.pix.xfer_func;
-}
-
 static inline u32 vpfe_reg_read(struct vpfe_ccdc *ccdc, u32 offset)
 {
 	return ioread32(ccdc->ccdc_cfg.base_addr + offset);
@@ -345,13 +229,9 @@ static void vpfe_ccdc_setwin(struct vpfe_ccdc *ccdc,
 	if (frm_fmt == CCDC_FRMFMT_INTERLACED) {
 		vert_nr_lines = (image_win->height >> 1) - 1;
 		vert_start >>= 1;
-		/* Since first line doesn't have any data */
-		vert_start += 1;
 		/* configure VDINT0 */
 		val = (vert_start << VPFE_VDINT_VDINT0_SHIFT);
 	} else {
-		/* Since first line doesn't have any data */
-		vert_start += 1;
 		vert_nr_lines = image_win->height - 1;
 		/*
 		 * configure VDINT0 and VDINT1. VDINT1 will be at half
@@ -405,7 +285,6 @@ vpfe_ccdc_validate_param(struct vpfe_ccdc *ccdc,
 	max_data = ccdc_data_size_max_bit(ccdcparam->data_sz);
 
 	if (ccdcparam->alaw.gamma_wd > VPFE_CCDC_GAMMA_BITS_09_0 ||
-	    ccdcparam->alaw.gamma_wd < VPFE_CCDC_GAMMA_BITS_15_6 ||
 	    max_gamma > max_data) {
 		vpfe_dbg(1, vpfe, "Invalid data line select\n");
 		return -EINVAL;
@@ -445,40 +324,25 @@ static void vpfe_ccdc_restore_defaults(struct vpfe_ccdc *ccdc)
 
 static int vpfe_ccdc_close(struct vpfe_ccdc *ccdc, struct device *dev)
 {
-	int dma_cntl, i, pcr;
+	struct vpfe_device *vpfe = container_of(ccdc, struct vpfe_device, ccdc);
+	u32 dma_cntl, pcr;
 
-	/* If the CCDC module is still busy wait for it to be done */
-	for (i = 0; i < 10; i++) {
-		usleep_range(5000, 6000);
-		pcr = vpfe_reg_read(ccdc, VPFE_PCR);
-		if (!pcr)
-			break;
+	pcr = vpfe_reg_read(ccdc, VPFE_PCR);
+	if (pcr)
+		vpfe_dbg(1, vpfe, "VPFE_PCR is still set (%x)", pcr);
 
-		/* make sure it it is disabled */
-		vpfe_pcr_enable(ccdc, 0);
-	}
+	dma_cntl = vpfe_reg_read(ccdc, VPFE_DMA_CNTL);
+	if ((dma_cntl & VPFE_DMA_CNTL_OVERFLOW))
+		vpfe_dbg(1, vpfe, "VPFE_DMA_CNTL_OVERFLOW is still set (%x)",
+			 dma_cntl);
 
 	/* Disable CCDC by resetting all register to default POR values */
 	vpfe_ccdc_restore_defaults(ccdc);
 
-	/* if DMA_CNTL overflow bit is set. Clear it
-	 *  It appears to take a while for this to become quiescent ~20ms
-	 */
-	for (i = 0; i < 10; i++) {
-		dma_cntl = vpfe_reg_read(ccdc, VPFE_DMA_CNTL);
-		if (!(dma_cntl & VPFE_DMA_CNTL_OVERFLOW))
-			break;
-
-		/* Clear the overflow bit */
-		vpfe_reg_write(ccdc, dma_cntl, VPFE_DMA_CNTL);
-		usleep_range(5000, 6000);
-	}
-
 	/* Disabled the module at the CONFIG level */
 	vpfe_config_enable(ccdc, 0);
 
 	pm_runtime_put_sync(dev);
-
 	return 0;
 }
 
@@ -494,8 +358,8 @@ static int vpfe_ccdc_set_params(struct vpfe_ccdc *ccdc, void __user *params)
 	x = copy_from_user(&raw_params, params, sizeof(raw_params));
 	if (x) {
 		vpfe_dbg(1, vpfe,
-			"vpfe_ccdc_set_params: error in copying ccdc params, %d\n",
-			x);
+			 "%s: error in copying ccdc params, %d\n",
+			 __func__, x);
 		return -EFAULT;
 	}
 
@@ -513,11 +377,9 @@ static int vpfe_ccdc_set_params(struct vpfe_ccdc *ccdc, void __user *params)
  */
 static void vpfe_ccdc_config_ycbcr(struct vpfe_ccdc *ccdc)
 {
-	struct vpfe_device *vpfe = container_of(ccdc, struct vpfe_device, ccdc);
 	struct ccdc_params_ycbcr *params = &ccdc->ccdc_cfg.ycbcr;
 	u32 syn_mode;
 
-	vpfe_dbg(3, vpfe, "vpfe_ccdc_config_ycbcr:\n");
 	/*
 	 * first restore the CCDC registers to default values
 	 * This is important since we assume default values to be set in
@@ -649,8 +511,6 @@ static void vpfe_ccdc_config_raw(struct vpfe_ccdc *ccdc)
 	unsigned int syn_mode;
 	unsigned int val;
 
-	vpfe_dbg(3, vpfe, "vpfe_ccdc_config_raw:\n");
-
 	/* Reset CCDC */
 	vpfe_ccdc_restore_defaults(ccdc);
 
@@ -751,8 +611,8 @@ static int vpfe_ccdc_set_pixel_format(struct vpfe_ccdc *ccdc, u32 pixfmt)
 {
 	struct vpfe_device *vpfe = container_of(ccdc, struct vpfe_device, ccdc);
 
-	vpfe_dbg(1, vpfe, "vpfe_ccdc_set_pixel_format: if_type: %d, pixfmt:%s\n",
-		 ccdc->ccdc_cfg.if_type, print_fourcc(pixfmt));
+	vpfe_dbg(1, vpfe, "%s: if_type: %d, pixfmt:%s\n",
+		 __func__, ccdc->ccdc_cfg.if_type, print_fourcc(pixfmt));
 
 	if (ccdc->ccdc_cfg.if_type == VPFE_RAW_BAYER) {
 		ccdc->ccdc_cfg.bayer.pix_fmt = CCDC_PIXFMT_RAW;
@@ -1036,10 +896,9 @@ static int vpfe_get_ccdc_image_format(struct vpfe_device *vpfe,
 static int vpfe_config_ccdc_image_format(struct vpfe_device *vpfe)
 {
 	enum ccdc_frmfmt frm_fmt = CCDC_FRMFMT_INTERLACED;
+	u32 bpp;
 	int ret = 0;
 
-	vpfe_dbg(2, vpfe, "vpfe_config_ccdc_image_format\n");
-
 	vpfe_dbg(1, vpfe, "pixelformat: %s\n",
 		print_fourcc(vpfe->fmt.fmt.pix.pixelformat));
 
@@ -1050,7 +909,8 @@ static int vpfe_config_ccdc_image_format(struct vpfe_device *vpfe)
 	}
 
 	/* configure the image window */
-	vpfe_ccdc_set_image_window(&vpfe->ccdc, &vpfe->crop, vpfe->bpp);
+	bpp = __get_bytesperpixel(vpfe, vpfe->current_vpfe_fmt);
+	vpfe_ccdc_set_image_window(&vpfe->ccdc, &vpfe->crop, bpp);
 
 	switch (vpfe->fmt.fmt.pix.field) {
 	case V4L2_FIELD_INTERLACED:
@@ -1094,7 +954,8 @@ static int vpfe_config_ccdc_image_format(struct vpfe_device *vpfe)
 static int vpfe_config_image_format(struct vpfe_device *vpfe,
 				    v4l2_std_id std_id)
 {
-	struct v4l2_pix_format *pix = &vpfe->fmt.fmt.pix;
+	struct vpfe_fmt *fmt;
+	struct v4l2_mbus_framefmt mbus_fmt;
 	int i, ret;
 
 	for (i = 0; i < ARRAY_SIZE(vpfe_standards); i++) {
@@ -1116,26 +977,29 @@ static int vpfe_config_image_format(struct vpfe_device *vpfe,
 		return -EINVAL;
 	}
 
-	vpfe->crop.top = vpfe->crop.left = 0;
-	vpfe->crop.width = vpfe->std_info.active_pixels;
-	vpfe->crop.height = vpfe->std_info.active_lines;
-	pix->width = vpfe->crop.width;
-	pix->height = vpfe->crop.height;
-	pix->pixelformat = V4L2_PIX_FMT_YUYV;
-
-	/* first field and frame format based on standard frame format */
-	if (vpfe->std_info.frame_format)
-		pix->field = V4L2_FIELD_INTERLACED;
-	else
-		pix->field = V4L2_FIELD_NONE;
-
-	ret = __vpfe_get_format(vpfe, &vpfe->fmt, &vpfe->bpp);
+	ret = __subdev_get_format(vpfe, &mbus_fmt);
 	if (ret)
 		return ret;
 
+	fmt = find_format_by_code(vpfe, mbus_fmt.code);
+	if (!fmt) {
+		vpfe_dbg(3, vpfe, "mbus code format (0x%08x) not found.\n",
+			 mbus_fmt.code);
+		return -EINVAL;
+	}
+
+	/* Save current subdev format */
+	v4l2_fill_pix_format(&vpfe->fmt.fmt.pix, &mbus_fmt);
+	vpfe->fmt.type = V4L2_BUF_TYPE_VIDEO_CAPTURE;
+	vpfe->fmt.fmt.pix.pixelformat = fmt->fourcc;
+	vpfe_calc_format_size(vpfe, fmt, &vpfe->fmt);
+	vpfe->current_vpfe_fmt = fmt;
+
 	/* Update the crop window based on found values */
-	vpfe->crop.width = pix->width;
-	vpfe->crop.height = pix->height;
+	vpfe->crop.top = 0;
+	vpfe->crop.left = 0;
+	vpfe->crop.width = mbus_fmt.width;
+	vpfe->crop.height = mbus_fmt.height;
 
 	return vpfe_config_ccdc_image_format(vpfe);
 }
@@ -1237,22 +1101,29 @@ unlock:
  * This function will get next buffer from the dma queue and
  * set the buffer address in the vpfe register for capture.
  * the buffer is marked active
- *
- * Assumes caller is holding vpfe->dma_queue_lock already
  */
-static inline void vpfe_schedule_next_buffer(struct vpfe_device *vpfe)
+static void vpfe_schedule_next_buffer(struct vpfe_device *vpfe)
 {
+	dma_addr_t addr;
+
+	spin_lock(&vpfe->dma_queue_lock);
+	if (list_empty(&vpfe->dma_queue)) {
+		spin_unlock(&vpfe->dma_queue_lock);
+		return;
+	}
+
 	vpfe->next_frm = list_entry(vpfe->dma_queue.next,
 				    struct vpfe_cap_buffer, list);
 	list_del(&vpfe->next_frm->list);
+	spin_unlock(&vpfe->dma_queue_lock);
 
-	vpfe_set_sdr_addr(&vpfe->ccdc,
-	       vb2_dma_contig_plane_dma_addr(&vpfe->next_frm->vb.vb2_buf, 0));
+	addr = vb2_dma_contig_plane_dma_addr(&vpfe->next_frm->vb.vb2_buf, 0);
+	vpfe_set_sdr_addr(&vpfe->ccdc, addr);
 }
 
 static inline void vpfe_schedule_bottom_field(struct vpfe_device *vpfe)
 {
-	unsigned long addr;
+	dma_addr_t addr;
 
 	addr = vb2_dma_contig_plane_dma_addr(&vpfe->next_frm->vb.vb2_buf, 0) +
 					vpfe->field_off;
@@ -1277,6 +1148,58 @@ static inline void vpfe_process_buffer_complete(struct vpfe_device *vpfe)
 	vpfe->cur_frm = vpfe->next_frm;
 }
 
+static void vpfe_handle_interlaced_irq(struct vpfe_device *vpfe,
+				       enum v4l2_field field)
+{
+	int fid;
+
+	/* interlaced or TB capture check which field
+	 * we are in hardware
+	 */
+	fid = vpfe_ccdc_getfid(&vpfe->ccdc);
+
+	/* switch the software maintained field id */
+	vpfe->field ^= 1;
+	if (fid == vpfe->field) {
+		/* we are in-sync here,continue */
+		if (fid == 0) {
+			/*
+			 * One frame is just being captured. If the
+			 * next frame is available, release the
+			 * current frame and move on
+			 */
+			if (vpfe->cur_frm != vpfe->next_frm)
+				vpfe_process_buffer_complete(vpfe);
+
+			if (vpfe->stopping)
+				return;
+
+			/*
+			 * based on whether the two fields are stored
+			 * interleave or separately in memory,
+			 * reconfigure the CCDC memory address
+			 */
+			if (field == V4L2_FIELD_SEQ_TB)
+				vpfe_schedule_bottom_field(vpfe);
+		} else {
+			/*
+			 * if one field is just being captured configure
+			 * the next frame get the next frame from the empty
+			 * queue if no frame is available hold on to the
+			 * current buffer
+			 */
+			if (vpfe->cur_frm == vpfe->next_frm)
+				vpfe_schedule_next_buffer(vpfe);
+		}
+	} else if (fid == 0) {
+		/*
+		 * out of sync. Recover from any hardware out-of-sync.
+		 * May loose one frame
+		 */
+		vpfe->field = fid;
+	}
+}
+
 /*
  * vpfe_isr : ISR handler for vpfe capture (VINT0)
  * @irq: irq number
@@ -1288,76 +1211,28 @@ static inline void vpfe_process_buffer_complete(struct vpfe_device *vpfe)
 static irqreturn_t vpfe_isr(int irq, void *dev)
 {
 	struct vpfe_device *vpfe = (struct vpfe_device *)dev;
-	enum v4l2_field field;
-	int intr_status;
-	int fid;
+	enum v4l2_field field = vpfe->fmt.fmt.pix.field;
+	int intr_status, stopping = vpfe->stopping;
 
 	intr_status = vpfe_reg_read(&vpfe->ccdc, VPFE_IRQ_STS);
 
 	if (intr_status & VPFE_VDINT0) {
-		field = vpfe->fmt.fmt.pix.field;
-
 		if (field == V4L2_FIELD_NONE) {
-			/* handle progressive frame capture */
 			if (vpfe->cur_frm != vpfe->next_frm)
 				vpfe_process_buffer_complete(vpfe);
-			goto next_intr;
+		} else {
+			vpfe_handle_interlaced_irq(vpfe, field);
 		}
-
-		/* interlaced or TB capture check which field
-		   we are in hardware */
-		fid = vpfe_ccdc_getfid(&vpfe->ccdc);
-
-		/* switch the software maintained field id */
-		vpfe->field ^= 1;
-		if (fid == vpfe->field) {
-			/* we are in-sync here,continue */
-			if (fid == 0) {
-				/*
-				 * One frame is just being captured. If the
-				 * next frame is available, release the
-				 * current frame and move on
-				 */
-				if (vpfe->cur_frm != vpfe->next_frm)
-					vpfe_process_buffer_complete(vpfe);
-				/*
-				 * based on whether the two fields are stored
-				 * interleave or separately in memory,
-				 * reconfigure the CCDC memory address
-				 */
-				if (field == V4L2_FIELD_SEQ_TB)
-					vpfe_schedule_bottom_field(vpfe);
-
-				goto next_intr;
-			}
-			/*
-			 * if one field is just being captured configure
-			 * the next frame get the next frame from the empty
-			 * queue if no frame is available hold on to the
-			 * current buffer
-			 */
-			spin_lock(&vpfe->dma_queue_lock);
-			if (!list_empty(&vpfe->dma_queue) &&
-			    vpfe->cur_frm == vpfe->next_frm)
-				vpfe_schedule_next_buffer(vpfe);
-			spin_unlock(&vpfe->dma_queue_lock);
-		} else if (fid == 0) {
-			/*
-			 * out of sync. Recover from any hardware out-of-sync.
-			 * May loose one frame
-			 */
-			vpfe->field = fid;
+		if (stopping) {
+			vpfe->stopping = false;
+			complete(&vpfe->capture_stop);
 		}
 	}
 
-next_intr:
-	if (intr_status & VPFE_VDINT1) {
-		spin_lock(&vpfe->dma_queue_lock);
-		if (vpfe->fmt.fmt.pix.field == V4L2_FIELD_NONE &&
-		    !list_empty(&vpfe->dma_queue) &&
+	if (intr_status & VPFE_VDINT1 && !stopping) {
+		if (field == V4L2_FIELD_NONE &&
 		    vpfe->cur_frm == vpfe->next_frm)
 			vpfe_schedule_next_buffer(vpfe);
-		spin_unlock(&vpfe->dma_queue_lock);
 	}
 
 	vpfe_clear_intr(&vpfe->ccdc, intr_status);
@@ -1394,8 +1269,6 @@ static int vpfe_querycap(struct file *file, void  *priv,
 {
 	struct vpfe_device *vpfe = video_drvdata(file);
 
-	vpfe_dbg(2, vpfe, "vpfe_querycap\n");
-
 	strscpy(cap->driver, VPFE_MODULE_NAME, sizeof(cap->driver));
 	strscpy(cap->card, "TI AM437x VPFE", sizeof(cap->card));
 	snprintf(cap->bus_info, sizeof(cap->bus_info),
@@ -1404,83 +1277,74 @@ static int vpfe_querycap(struct file *file, void  *priv,
 }
 
 /* get the format set at output pad of the adjacent subdev */
-static int __vpfe_get_format(struct vpfe_device *vpfe,
-			     struct v4l2_format *format, unsigned int *bpp)
+static int __subdev_get_format(struct vpfe_device *vpfe,
+			       struct v4l2_mbus_framefmt *fmt)
 {
-	struct v4l2_mbus_framefmt mbus_fmt;
-	struct vpfe_subdev_info *sdinfo;
-	struct v4l2_subdev_format fmt;
+	struct v4l2_subdev *sd = vpfe->current_subdev->sd;
+	struct v4l2_subdev_format sd_fmt;
+	struct v4l2_mbus_framefmt *mbus_fmt = &sd_fmt.format;
 	int ret;
 
-	sdinfo = vpfe->current_subdev;
-	if (!sdinfo->sd)
-		return -EINVAL;
-
-	fmt.which = V4L2_SUBDEV_FORMAT_ACTIVE;
-	fmt.pad = 0;
+	sd_fmt.which = V4L2_SUBDEV_FORMAT_ACTIVE;
+	sd_fmt.pad = 0;
 
-	ret = v4l2_subdev_call(sdinfo->sd, pad, get_fmt, NULL, &fmt);
-	if (ret && ret != -ENOIOCTLCMD && ret != -ENODEV)
+	ret = v4l2_subdev_call(sd, pad, get_fmt, NULL, &sd_fmt);
+	if (ret)
 		return ret;
 
-	if (!ret) {
-		v4l2_fill_pix_format(&format->fmt.pix, &fmt.format);
-		mbus_to_pix(vpfe, &fmt.format, &format->fmt.pix, bpp);
-	} else {
-		ret = v4l2_device_call_until_err(&vpfe->v4l2_dev,
-						 sdinfo->grp_id,
-						 pad, get_fmt,
-						 NULL, &fmt);
-		if (ret && ret != -ENOIOCTLCMD && ret != -ENODEV)
-			return ret;
-		v4l2_fill_pix_format(&format->fmt.pix, &mbus_fmt);
-		mbus_to_pix(vpfe, &mbus_fmt, &format->fmt.pix, bpp);
-	}
-
-	format->type = vpfe->fmt.type;
+	*fmt = *mbus_fmt;
 
-	vpfe_dbg(1, vpfe,
-		 "%s size %dx%d (%s) bytesperline = %d, size = %d, bpp = %d\n",
-		 __func__, format->fmt.pix.width, format->fmt.pix.height,
-		 print_fourcc(format->fmt.pix.pixelformat),
-		 format->fmt.pix.bytesperline, format->fmt.pix.sizeimage, *bpp);
+	vpfe_dbg(1, vpfe, "%s: %dx%d code:%04X\n", __func__,
+		 fmt->width, fmt->height, fmt->code);
 
 	return 0;
 }
 
 /* set the format at output pad of the adjacent subdev */
-static int __vpfe_set_format(struct vpfe_device *vpfe,
-			     struct v4l2_format *format, unsigned int *bpp)
+static int __subdev_set_format(struct vpfe_device *vpfe,
+			       struct v4l2_mbus_framefmt *fmt)
 {
-	struct vpfe_subdev_info *sdinfo;
-	struct v4l2_subdev_format fmt;
+	struct v4l2_subdev *sd = vpfe->current_subdev->sd;
+	struct v4l2_subdev_format sd_fmt;
+	struct v4l2_mbus_framefmt *mbus_fmt = &sd_fmt.format;
 	int ret;
 
-	vpfe_dbg(2, vpfe, "__vpfe_set_format\n");
+	sd_fmt.which = V4L2_SUBDEV_FORMAT_ACTIVE;
+	sd_fmt.pad = 0;
+	*mbus_fmt = *fmt;
 
-	sdinfo = vpfe->current_subdev;
-	if (!sdinfo->sd)
-		return -EINVAL;
+	ret = v4l2_subdev_call(sd, pad, set_fmt, NULL, &sd_fmt);
+	if (ret)
+		return ret;
 
-	fmt.which = V4L2_SUBDEV_FORMAT_ACTIVE;
-	fmt.pad = 0;
+	vpfe_dbg(1, vpfe, "%s %dx%d code:%04X\n", __func__,
+		 fmt->width, fmt->height, fmt->code);
 
-	pix_to_mbus(vpfe, &format->fmt.pix, &fmt.format);
+	return 0;
+}
 
-	ret = v4l2_subdev_call(sdinfo->sd, pad, set_fmt, NULL, &fmt);
-	if (ret)
-		return ret;
+static int vpfe_calc_format_size(struct vpfe_device *vpfe,
+				 const struct vpfe_fmt *fmt,
+				 struct v4l2_format *f)
+{
+	u32 bpp;
+
+	if (!fmt) {
+		vpfe_dbg(3, vpfe, "No vpfe_fmt provided!\n");
+		return -EINVAL;
+	}
 
-	v4l2_fill_pix_format(&format->fmt.pix, &fmt.format);
-	mbus_to_pix(vpfe, &fmt.format, &format->fmt.pix, bpp);
+	bpp = __get_bytesperpixel(vpfe, fmt);
 
-	format->type = vpfe->fmt.type;
+	/* pitch should be 32 bytes aligned */
+	f->fmt.pix.bytesperline = ALIGN(f->fmt.pix.width * bpp, 32);
+	f->fmt.pix.sizeimage = f->fmt.pix.bytesperline *
+			       f->fmt.pix.height;
 
-	vpfe_dbg(1, vpfe,
-		 "%s size %dx%d (%s) bytesperline = %d, size = %d, bpp = %d\n",
-		 __func__,  format->fmt.pix.width, format->fmt.pix.height,
-		 print_fourcc(format->fmt.pix.pixelformat),
-		 format->fmt.pix.bytesperline, format->fmt.pix.sizeimage, *bpp);
+	vpfe_dbg(3, vpfe, "%s: fourcc: %s size: %dx%d bpl:%d img_size:%d\n",
+		 __func__, print_fourcc(f->fmt.pix.pixelformat),
+		 f->fmt.pix.width, f->fmt.pix.height,
+		 f->fmt.pix.bytesperline, f->fmt.pix.sizeimage);
 
 	return 0;
 }
@@ -1490,8 +1354,6 @@ static int vpfe_g_fmt(struct file *file, void *priv,
 {
 	struct vpfe_device *vpfe = video_drvdata(file);
 
-	vpfe_dbg(2, vpfe, "vpfe_g_fmt\n");
-
 	*fmt = vpfe->fmt;
 
 	return 0;
@@ -1502,82 +1364,124 @@ static int vpfe_enum_fmt(struct file *file, void  *priv,
 {
 	struct vpfe_device *vpfe = video_drvdata(file);
 	struct vpfe_subdev_info *sdinfo;
-	struct vpfe_fmt *fmt = NULL;
-	unsigned int k;
-
-	vpfe_dbg(2, vpfe, "vpfe_enum_format index:%d\n",
-		f->index);
+	struct vpfe_fmt *fmt;
 
 	sdinfo = vpfe->current_subdev;
 	if (!sdinfo->sd)
 		return -EINVAL;
 
-	if (f->index > ARRAY_SIZE(formats))
+	if (f->index >= vpfe->num_active_fmt)
 		return -EINVAL;
 
-	for (k = 0; k < ARRAY_SIZE(formats); k++) {
-		if (formats[k].index == f->index) {
-			fmt = &formats[k];
-			break;
-		}
-	}
-	if (!fmt)
-		return -EINVAL;
+	fmt = vpfe->active_fmt[f->index];
 
 	f->pixelformat = fmt->fourcc;
 
-	vpfe_dbg(1, vpfe, "vpfe_enum_format: mbus index: %d code: %x pixelformat: %s\n",
-		 f->index, fmt->code, print_fourcc(fmt->fourcc));
+	vpfe_dbg(1, vpfe, "%s: mbus index: %d code: %x pixelformat: %s\n",
+		 __func__, f->index, fmt->code, print_fourcc(fmt->fourcc));
 
 	return 0;
 }
 
 static int vpfe_try_fmt(struct file *file, void *priv,
-			struct v4l2_format *fmt)
+			struct v4l2_format *f)
 {
 	struct vpfe_device *vpfe = video_drvdata(file);
-	unsigned int bpp;
+	struct v4l2_subdev *sd = vpfe->current_subdev->sd;
+	const struct vpfe_fmt *fmt;
+	struct v4l2_subdev_frame_size_enum fse;
+	int ret, found;
+
+	fmt = find_format_by_pix(vpfe, f->fmt.pix.pixelformat);
+	if (!fmt) {
+		/* default to first entry */
+		vpfe_dbg(3, vpfe, "Invalid pixel code: %x, default used instead\n",
+			 f->fmt.pix.pixelformat);
+		fmt = vpfe->active_fmt[0];
+		f->fmt.pix.pixelformat = fmt->fourcc;
+	}
+
+	f->fmt.pix.field = vpfe->fmt.fmt.pix.field;
+
+	/* check for/find a valid width/height */
+	ret = 0;
+	found = false;
+	fse.pad = 0;
+	fse.code = fmt->code;
+	fse.which = V4L2_SUBDEV_FORMAT_ACTIVE;
+	for (fse.index = 0; ; fse.index++) {
+		ret = v4l2_subdev_call(sd, pad, enum_frame_size,
+				       NULL, &fse);
+		if (ret)
+			break;
+
+		if (f->fmt.pix.width == fse.max_width &&
+		    f->fmt.pix.height == fse.max_height) {
+			found = true;
+			break;
+		} else if (f->fmt.pix.width >= fse.min_width &&
+			   f->fmt.pix.width <= fse.max_width &&
+			   f->fmt.pix.height >= fse.min_height &&
+			   f->fmt.pix.height <= fse.max_height) {
+			found = true;
+			break;
+		}
+	}
 
-	vpfe_dbg(2, vpfe, "vpfe_try_fmt\n");
+	if (!found) {
+		/* use existing values as default */
+		f->fmt.pix.width = vpfe->fmt.fmt.pix.width;
+		f->fmt.pix.height =  vpfe->fmt.fmt.pix.height;
+	}
 
-	return __vpfe_get_format(vpfe, fmt, &bpp);
+	/*
+	 * Use current colorspace for now, it will get
+	 * updated properly during s_fmt
+	 */
+	f->fmt.pix.colorspace = vpfe->fmt.fmt.pix.colorspace;
+	return vpfe_calc_format_size(vpfe, fmt, f);
 }
 
 static int vpfe_s_fmt(struct file *file, void *priv,
 		      struct v4l2_format *fmt)
 {
 	struct vpfe_device *vpfe = video_drvdata(file);
-	struct v4l2_format format;
-	unsigned int bpp;
+	struct vpfe_fmt *f;
+	struct v4l2_mbus_framefmt mbus_fmt;
 	int ret;
 
-	vpfe_dbg(2, vpfe, "vpfe_s_fmt\n");
-
 	/* If streaming is started, return error */
 	if (vb2_is_busy(&vpfe->buffer_queue)) {
 		vpfe_err(vpfe, "%s device busy\n", __func__);
 		return -EBUSY;
 	}
 
-	ret = __vpfe_get_format(vpfe, &format, &bpp);
-	if (ret)
+	ret = vpfe_try_fmt(file, priv, fmt);
+	if (ret < 0)
 		return ret;
 
+	f = find_format_by_pix(vpfe, fmt->fmt.pix.pixelformat);
 
-	if (!cmp_v4l2_format(fmt, &format)) {
-		/* Sensor format is different from the requested format
-		 * so we need to change it
-		 */
-		ret = __vpfe_set_format(vpfe, fmt, &bpp);
-		if (ret)
-			return ret;
-	} else /* Just make sure all of the fields are consistent */
-		*fmt = format;
+	v4l2_fill_mbus_format(&mbus_fmt, &fmt->fmt.pix, f->code);
 
-	/* First detach any IRQ if currently attached */
-	vpfe_detach_irq(vpfe);
-	vpfe->fmt = *fmt;
-	vpfe->bpp = bpp;
+	ret = __subdev_set_format(vpfe, &mbus_fmt);
+	if (ret)
+		return ret;
+
+	/* Just double check nothing has gone wrong */
+	if (mbus_fmt.code != f->code) {
+		vpfe_dbg(3, vpfe,
+			 "%s subdev changed format on us, this should not happen\n",
+			 __func__);
+		return -EINVAL;
+	}
+
+	v4l2_fill_pix_format(&vpfe->fmt.fmt.pix, &mbus_fmt);
+	vpfe->fmt.type = V4L2_BUF_TYPE_VIDEO_CAPTURE;
+	vpfe->fmt.fmt.pix.pixelformat  = f->fourcc;
+	vpfe_calc_format_size(vpfe, f, &vpfe->fmt);
+	*fmt = vpfe->fmt;
+	vpfe->current_vpfe_fmt = f;
 
 	/* Update the crop window based on found values */
 	vpfe->crop.width = fmt->fmt.pix.width;
@@ -1592,57 +1496,40 @@ static int vpfe_enum_size(struct file *file, void  *priv,
 {
 	struct vpfe_device *vpfe = video_drvdata(file);
 	struct v4l2_subdev_frame_size_enum fse;
-	struct vpfe_subdev_info *sdinfo;
-	struct v4l2_mbus_framefmt mbus;
-	struct v4l2_pix_format pix;
+	struct v4l2_subdev *sd = vpfe->current_subdev->sd;
 	struct vpfe_fmt *fmt;
 	int ret;
 
-	vpfe_dbg(2, vpfe, "vpfe_enum_size\n");
-
 	/* check for valid format */
-	fmt = find_format_by_pix(fsize->pixel_format);
+	fmt = find_format_by_pix(vpfe, fsize->pixel_format);
 	if (!fmt) {
-		vpfe_dbg(3, vpfe, "Invalid pixel code: %x, default used instead\n",
-			fsize->pixel_format);
+		vpfe_dbg(3, vpfe, "Invalid pixel code: %x\n",
+			 fsize->pixel_format);
 		return -EINVAL;
 	}
 
 	memset(fsize->reserved, 0x0, sizeof(fsize->reserved));
 
-	sdinfo = vpfe->current_subdev;
-	if (!sdinfo->sd)
-		return -EINVAL;
-
-	memset(&pix, 0x0, sizeof(pix));
-	/* Construct pix from parameter and use default for the rest */
-	pix.pixelformat = fsize->pixel_format;
-	pix.width = 640;
-	pix.height = 480;
-	pix.colorspace = V4L2_COLORSPACE_SRGB;
-	pix.field = V4L2_FIELD_NONE;
-	pix_to_mbus(vpfe, &pix, &mbus);
-
 	memset(&fse, 0x0, sizeof(fse));
 	fse.index = fsize->index;
 	fse.pad = 0;
-	fse.code = mbus.code;
+	fse.code = fmt->code;
 	fse.which = V4L2_SUBDEV_FORMAT_ACTIVE;
-	ret = v4l2_subdev_call(sdinfo->sd, pad, enum_frame_size, NULL, &fse);
+	ret = v4l2_subdev_call(sd, pad, enum_frame_size, NULL, &fse);
 	if (ret)
-		return -EINVAL;
+		return ret;
 
-	vpfe_dbg(1, vpfe, "vpfe_enum_size: index: %d code: %x W:[%d,%d] H:[%d,%d]\n",
-		fse.index, fse.code, fse.min_width, fse.max_width,
-		fse.min_height, fse.max_height);
+	vpfe_dbg(1, vpfe, "%s: index: %d code: %x W:[%d,%d] H:[%d,%d]\n",
+		 __func__, fse.index, fse.code, fse.min_width, fse.max_width,
+		 fse.min_height, fse.max_height);
 
 	fsize->type = V4L2_FRMSIZE_TYPE_DISCRETE;
 	fsize->discrete.width = fse.max_width;
 	fsize->discrete.height = fse.max_height;
 
-	vpfe_dbg(1, vpfe, "vpfe_enum_size: index: %d pixformat: %s size: %dx%d\n",
-		fsize->index, print_fourcc(fsize->pixel_format),
-		fsize->discrete.width, fsize->discrete.height);
+	vpfe_dbg(1, vpfe, "%s: index: %d pixformat: %s size: %dx%d\n",
+		 __func__, fsize->index, print_fourcc(fsize->pixel_format),
+		 fsize->discrete.width, fsize->discrete.height);
 
 	return 0;
 }
@@ -1707,8 +1594,6 @@ static int vpfe_enum_input(struct file *file, void *priv,
 	struct vpfe_subdev_info *sdinfo;
 	int subdev, index;
 
-	vpfe_dbg(2, vpfe, "vpfe_enum_input\n");
-
 	if (vpfe_get_subdev_input_index(vpfe, &subdev, &index,
 					inp->index) < 0) {
 		vpfe_dbg(1, vpfe,
@@ -1725,8 +1610,6 @@ static int vpfe_g_input(struct file *file, void *priv, unsigned int *index)
 {
 	struct vpfe_device *vpfe = video_drvdata(file);
 
-	vpfe_dbg(2, vpfe, "vpfe_g_input\n");
-
 	return vpfe_get_app_input_index(vpfe, index);
 }
 
@@ -1739,8 +1622,6 @@ static int vpfe_set_input(struct vpfe_device *vpfe, unsigned int index)
 	u32 input, output;
 	int ret;
 
-	vpfe_dbg(2, vpfe, "vpfe_set_input: index: %d\n", index);
-
 	/* If streaming is started, return error */
 	if (vb2_is_busy(&vpfe->buffer_queue)) {
 		vpfe_err(vpfe, "%s device busy\n", __func__);
@@ -1796,9 +1677,6 @@ static int vpfe_s_input(struct file *file, void *priv, unsigned int index)
 {
 	struct vpfe_device *vpfe = video_drvdata(file);
 
-	vpfe_dbg(2, vpfe,
-		"vpfe_s_input: index: %d\n", index);
-
 	return vpfe_set_input(vpfe, index);
 }
 
@@ -1807,8 +1685,6 @@ static int vpfe_querystd(struct file *file, void *priv, v4l2_std_id *std_id)
 	struct vpfe_device *vpfe = video_drvdata(file);
 	struct vpfe_subdev_info *sdinfo;
 
-	vpfe_dbg(2, vpfe, "vpfe_querystd\n");
-
 	sdinfo = vpfe->current_subdev;
 	if (!(sdinfo->inputs[0].capabilities & V4L2_IN_CAP_STD))
 		return -ENODATA;
@@ -1824,12 +1700,14 @@ static int vpfe_s_std(struct file *file, void *priv, v4l2_std_id std_id)
 	struct vpfe_subdev_info *sdinfo;
 	int ret;
 
-	vpfe_dbg(2, vpfe, "vpfe_s_std\n");
-
 	sdinfo = vpfe->current_subdev;
 	if (!(sdinfo->inputs[0].capabilities & V4L2_IN_CAP_STD))
 		return -ENODATA;
 
+	/* if trying to set the same std then nothing to do */
+	if (vpfe_standards[vpfe->std_index].std_id == std_id)
+		return 0;
+
 	/* If streaming is started, return error */
 	if (vb2_is_busy(&vpfe->buffer_queue)) {
 		vpfe_err(vpfe, "%s device busy\n", __func__);
@@ -1853,8 +1731,6 @@ static int vpfe_g_std(struct file *file, void *priv, v4l2_std_id *std_id)
 	struct vpfe_device *vpfe = video_drvdata(file);
 	struct vpfe_subdev_info *sdinfo;
 
-	vpfe_dbg(2, vpfe, "vpfe_g_std\n");
-
 	sdinfo = vpfe->current_subdev;
 	if (sdinfo->inputs[0].capabilities != V4L2_IN_CAP_STD)
 		return -ENODATA;
@@ -1872,8 +1748,6 @@ static void vpfe_calculate_offsets(struct vpfe_device *vpfe)
 {
 	struct v4l2_rect image_win;
 
-	vpfe_dbg(2, vpfe, "vpfe_calculate_offsets\n");
-
 	vpfe_ccdc_get_image_window(&vpfe->ccdc, &image_win);
 	vpfe->field_off = image_win.height * image_win.width;
 }
@@ -1957,6 +1831,29 @@ static void vpfe_buffer_queue(struct vb2_buffer *vb)
 	spin_unlock_irqrestore(&vpfe->dma_queue_lock, flags);
 }
 
+static void vpfe_return_all_buffers(struct vpfe_device *vpfe,
+				    enum vb2_buffer_state state)
+{
+	struct vpfe_cap_buffer *buf, *node;
+	unsigned long flags;
+
+	spin_lock_irqsave(&vpfe->dma_queue_lock, flags);
+	list_for_each_entry_safe(buf, node, &vpfe->dma_queue, list) {
+		vb2_buffer_done(&buf->vb.vb2_buf, state);
+		list_del(&buf->list);
+	}
+
+	if (vpfe->cur_frm)
+		vb2_buffer_done(&vpfe->cur_frm->vb.vb2_buf, state);
+
+	if (vpfe->next_frm && vpfe->next_frm != vpfe->cur_frm)
+		vb2_buffer_done(&vpfe->next_frm->vb.vb2_buf, state);
+
+	vpfe->cur_frm = NULL;
+	vpfe->next_frm = NULL;
+	spin_unlock_irqrestore(&vpfe->dma_queue_lock, flags);
+}
+
 /*
  * vpfe_start_streaming : Starts the DMA engine for streaming
  * @vb: ptr to vb2_buffer
@@ -1965,7 +1862,6 @@ static void vpfe_buffer_queue(struct vb2_buffer *vb)
 static int vpfe_start_streaming(struct vb2_queue *vq, unsigned int count)
 {
 	struct vpfe_device *vpfe = vb2_get_drv_priv(vq);
-	struct vpfe_cap_buffer *buf, *tmp;
 	struct vpfe_subdev_info *sdinfo;
 	unsigned long flags;
 	unsigned long addr;
@@ -1980,6 +1876,9 @@ static int vpfe_start_streaming(struct vb2_queue *vq, unsigned int count)
 
 	vpfe_attach_irq(vpfe);
 
+	vpfe->stopping = false;
+	init_completion(&vpfe->capture_stop);
+
 	if (vpfe->ccdc.ccdc_cfg.if_type == VPFE_RAW_BAYER)
 		vpfe_ccdc_config_raw(&vpfe->ccdc);
 	else
@@ -2008,11 +1907,8 @@ static int vpfe_start_streaming(struct vb2_queue *vq, unsigned int count)
 	return 0;
 
 err:
-	list_for_each_entry_safe(buf, tmp, &vpfe->dma_queue, list) {
-		list_del(&buf->list);
-		vb2_buffer_done(&buf->vb.vb2_buf, VB2_BUF_STATE_QUEUED);
-	}
-
+	vpfe_return_all_buffers(vpfe, VB2_BUF_STATE_QUEUED);
+	vpfe_pcr_enable(&vpfe->ccdc, 0);
 	return ret;
 }
 
@@ -2027,11 +1923,15 @@ static void vpfe_stop_streaming(struct vb2_queue *vq)
 {
 	struct vpfe_device *vpfe = vb2_get_drv_priv(vq);
 	struct vpfe_subdev_info *sdinfo;
-	unsigned long flags;
 	int ret;
 
 	vpfe_pcr_enable(&vpfe->ccdc, 0);
 
+	/* Wait for the last frame to be captured */
+	vpfe->stopping = true;
+	wait_for_completion_timeout(&vpfe->capture_stop,
+				    msecs_to_jiffies(250));
+
 	vpfe_detach_irq(vpfe);
 
 	sdinfo = vpfe->current_subdev;
@@ -2040,27 +1940,7 @@ static void vpfe_stop_streaming(struct vb2_queue *vq)
 		vpfe_dbg(1, vpfe, "stream off failed in subdev\n");
 
 	/* release all active buffers */
-	spin_lock_irqsave(&vpfe->dma_queue_lock, flags);
-	if (vpfe->cur_frm == vpfe->next_frm) {
-		vb2_buffer_done(&vpfe->cur_frm->vb.vb2_buf,
-				VB2_BUF_STATE_ERROR);
-	} else {
-		if (vpfe->cur_frm != NULL)
-			vb2_buffer_done(&vpfe->cur_frm->vb.vb2_buf,
-					VB2_BUF_STATE_ERROR);
-		if (vpfe->next_frm != NULL)
-			vb2_buffer_done(&vpfe->next_frm->vb.vb2_buf,
-					VB2_BUF_STATE_ERROR);
-	}
-
-	while (!list_empty(&vpfe->dma_queue)) {
-		vpfe->next_frm = list_entry(vpfe->dma_queue.next,
-						struct vpfe_cap_buffer, list);
-		list_del(&vpfe->next_frm->list);
-		vb2_buffer_done(&vpfe->next_frm->vb.vb2_buf,
-				VB2_BUF_STATE_ERROR);
-	}
-	spin_unlock_irqrestore(&vpfe->dma_queue_lock, flags);
+	vpfe_return_all_buffers(vpfe, VB2_BUF_STATE_ERROR);
 }
 
 static int vpfe_g_pixelaspect(struct file *file, void *priv,
@@ -2068,8 +1948,6 @@ static int vpfe_g_pixelaspect(struct file *file, void *priv,
 {
 	struct vpfe_device *vpfe = video_drvdata(file);
 
-	vpfe_dbg(2, vpfe, "vpfe_g_pixelaspect\n");
-
 	if (type != V4L2_BUF_TYPE_VIDEO_CAPTURE ||
 	    vpfe->std_index >= ARRAY_SIZE(vpfe_standards))
 		return -EINVAL;
@@ -2128,6 +2006,7 @@ vpfe_s_selection(struct file *file, void *fh, struct v4l2_selection *s)
 	struct vpfe_device *vpfe = video_drvdata(file);
 	struct v4l2_rect cr = vpfe->crop;
 	struct v4l2_rect r = s->r;
+	u32 bpp;
 
 	/* If streaming is started, return error */
 	if (vb2_is_busy(&vpfe->buffer_queue)) {
@@ -2153,10 +2032,12 @@ vpfe_s_selection(struct file *file, void *fh, struct v4l2_selection *s)
 
 	s->r = vpfe->crop = r;
 
-	vpfe_ccdc_set_image_window(&vpfe->ccdc, &r, vpfe->bpp);
+	bpp = __get_bytesperpixel(vpfe, vpfe->current_vpfe_fmt);
+	vpfe_ccdc_set_image_window(&vpfe->ccdc, &r, bpp);
 	vpfe->fmt.fmt.pix.width = r.width;
 	vpfe->fmt.fmt.pix.height = r.height;
-	vpfe->fmt.fmt.pix.bytesperline = vpfe_ccdc_get_line_length(&vpfe->ccdc);
+	vpfe->fmt.fmt.pix.bytesperline =
+		vpfe_ccdc_get_line_length(&vpfe->ccdc);
 	vpfe->fmt.fmt.pix.sizeimage = vpfe->fmt.fmt.pix.bytesperline *
 						vpfe->fmt.fmt.pix.height;
 
@@ -2172,8 +2053,6 @@ static long vpfe_ioctl_default(struct file *file, void *priv,
 	struct vpfe_device *vpfe = video_drvdata(file);
 	int ret;
 
-	vpfe_dbg(2, vpfe, "vpfe_ioctl_default\n");
-
 	if (!valid_prio) {
 		vpfe_err(vpfe, "%s device busy\n", __func__);
 		return -EBUSY;
@@ -2279,10 +2158,10 @@ vpfe_async_bound(struct v4l2_async_notifier *notifier,
 					       struct vpfe_device, v4l2_dev);
 	struct v4l2_subdev_mbus_code_enum mbus_code;
 	struct vpfe_subdev_info *sdinfo;
+	struct vpfe_fmt *fmt;
+	int ret = 0;
 	bool found = false;
-	int i, j;
-
-	vpfe_dbg(1, vpfe, "vpfe_async_bound\n");
+	int i, j, k;
 
 	for (i = 0; i < ARRAY_SIZE(vpfe->cfg->asd); i++) {
 		if (vpfe->cfg->asd[i]->match.fwnode ==
@@ -2302,27 +2181,37 @@ vpfe_async_bound(struct v4l2_async_notifier *notifier,
 
 	vpfe->video_dev.tvnorms |= sdinfo->inputs[0].std;
 
-	/* setup the supported formats & indexes */
-	for (j = 0, i = 0; ; ++j) {
-		struct vpfe_fmt *fmt;
-		int ret;
-
+	vpfe->num_active_fmt = 0;
+	for (j = 0, i = 0; (ret != -EINVAL); ++j) {
 		memset(&mbus_code, 0, sizeof(mbus_code));
 		mbus_code.index = j;
 		mbus_code.which = V4L2_SUBDEV_FORMAT_ACTIVE;
 		ret = v4l2_subdev_call(subdev, pad, enum_mbus_code,
-			       NULL, &mbus_code);
+				       NULL, &mbus_code);
 		if (ret)
-			break;
-
-		fmt = find_format_by_code(mbus_code.code);
-		if (!fmt)
 			continue;
 
-		fmt->supported = true;
-		fmt->index = i++;
+		vpfe_dbg(3, vpfe,
+			 "subdev %s: code: %04x idx: %d\n",
+			 subdev->name, mbus_code.code, j);
+
+		for (k = 0; k < ARRAY_SIZE(formats); k++) {
+			fmt = &formats[k];
+			if (mbus_code.code != fmt->code)
+				continue;
+			vpfe->active_fmt[i] = fmt;
+			vpfe_dbg(3, vpfe,
+				 "matched fourcc: %s code: %04x idx: %d\n",
+				 print_fourcc(fmt->fourcc), mbus_code.code, i);
+			vpfe->num_active_fmt = ++i;
+		}
 	}
 
+	if (!i) {
+		vpfe_err(vpfe, "No suitable format reported by subdev %s\n",
+			 subdev->name);
+		return -EINVAL;
+	}
 	return 0;
 }
 
@@ -2605,8 +2494,6 @@ static int vpfe_remove(struct platform_device *pdev)
 {
 	struct vpfe_device *vpfe = platform_get_drvdata(pdev);
 
-	vpfe_dbg(2, vpfe, "vpfe_remove\n");
-
 	pm_runtime_disable(&pdev->dev);
 
 	v4l2_async_notifier_unregister(&vpfe->notifier);
@@ -2653,22 +2540,21 @@ static int vpfe_suspend(struct device *dev)
 	struct vpfe_device *vpfe = dev_get_drvdata(dev);
 	struct vpfe_ccdc *ccdc = &vpfe->ccdc;
 
-	/* if streaming has not started we don't care */
-	if (!vb2_start_streaming_called(&vpfe->buffer_queue))
-		return 0;
-
-	pm_runtime_get_sync(dev);
-	vpfe_config_enable(ccdc, 1);
+	/* only do full suspend if streaming has started */
+	if (vb2_start_streaming_called(&vpfe->buffer_queue)) {
+		pm_runtime_get_sync(dev);
+		vpfe_config_enable(ccdc, 1);
 
-	/* Save VPFE context */
-	vpfe_save_context(ccdc);
+		/* Save VPFE context */
+		vpfe_save_context(ccdc);
 
-	/* Disable CCDC */
-	vpfe_pcr_enable(ccdc, 0);
-	vpfe_config_enable(ccdc, 0);
+		/* Disable CCDC */
+		vpfe_pcr_enable(ccdc, 0);
+		vpfe_config_enable(ccdc, 0);
 
-	/* Disable both master and slave clock */
-	pm_runtime_put_sync(dev);
+		/* Disable both master and slave clock */
+		pm_runtime_put_sync(dev);
+	}
 
 	/* Select sleep pin state */
 	pinctrl_pm_select_sleep_state(dev);
@@ -2710,19 +2596,18 @@ static int vpfe_resume(struct device *dev)
 	struct vpfe_device *vpfe = dev_get_drvdata(dev);
 	struct vpfe_ccdc *ccdc = &vpfe->ccdc;
 
-	/* if streaming has not started we don't care */
-	if (!vb2_start_streaming_called(&vpfe->buffer_queue))
-		return 0;
-
-	/* Enable both master and slave clock */
-	pm_runtime_get_sync(dev);
-	vpfe_config_enable(ccdc, 1);
+	/* only do full resume if streaming has started */
+	if (vb2_start_streaming_called(&vpfe->buffer_queue)) {
+		/* Enable both master and slave clock */
+		pm_runtime_get_sync(dev);
+		vpfe_config_enable(ccdc, 1);
 
-	/* Restore VPFE context */
-	vpfe_restore_context(ccdc);
+		/* Restore VPFE context */
+		vpfe_restore_context(ccdc);
 
-	vpfe_config_enable(ccdc, 0);
-	pm_runtime_put_sync(dev);
+		vpfe_config_enable(ccdc, 0);
+		pm_runtime_put_sync(dev);
+	}
 
 	/* Select default pin state */
 	pinctrl_pm_select_default_state(dev);
diff --git a/drivers/media/platform/am437x/am437x-vpfe.h b/drivers/media/platform/am437x/am437x-vpfe.h
index 4678285f34c6..05ee37db0273 100644
--- a/drivers/media/platform/am437x/am437x-vpfe.h
+++ b/drivers/media/platform/am437x/am437x-vpfe.h
@@ -1,21 +1,9 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /*
  * Copyright (C) 2013 - 2014 Texas Instruments, Inc.
  *
  * Benoit Parrot <bparrot@ti.com>
  * Lad, Prabhakar <prabhakar.csengg@gmail.com>
- *
- * This program is free software; you may redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; version 2 of the License.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
- * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
- * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
- * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
- * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
- * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
- * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
- * SOFTWARE.
  */
 
 #ifndef AM437X_VPFE_H
@@ -23,6 +11,7 @@
 
 #include <linux/am437x-vpfe.h>
 #include <linux/clk.h>
+#include <linux/completion.h>
 #include <linux/device.h>
 #include <linux/io.h>
 #include <linux/i2c.h>
@@ -214,6 +203,25 @@ struct vpfe_ccdc {
 	u32 ccdc_ctx[VPFE_REG_END / sizeof(u32)];
 };
 
+/*
+ * struct vpfe_fmt - VPFE media bus format information
+ * fourcc: V4L2 pixel format code
+ * code: V4L2 media bus format code
+ * bitsperpixel: Bits per pixel over the bus
+ */
+struct vpfe_fmt {
+	u32 fourcc;
+	u32 code;
+	u32 bitsperpixel;
+};
+
+/*
+ * When formats[] is modified make sure to adjust this value also.
+ * Expect compile time warnings if VPFE_NUM_FORMATS is smaller then
+ * the number of elements in formats[].
+ */
+#define VPFE_NUM_FORMATS	10
+
 struct vpfe_device {
 	/* V4l2 specific parameters */
 	/* Identifies video device for this channel */
@@ -249,8 +257,11 @@ struct vpfe_device {
 	struct vpfe_cap_buffer *next_frm;
 	/* Used to store pixel format */
 	struct v4l2_format fmt;
-	/* Used to store current bytes per pixel based on current format */
-	unsigned int bpp;
+	/* Used to keep a reference to the current vpfe_fmt */
+	struct vpfe_fmt *current_vpfe_fmt;
+	struct vpfe_fmt	*active_fmt[VPFE_NUM_FORMATS];
+	unsigned int num_active_fmt;
+
 	/*
 	 * used when IMP is chained to store the crop window which
 	 * is different from the image window
@@ -270,6 +281,8 @@ struct vpfe_device {
 	 */
 	u32 field_off;
 	struct vpfe_ccdc ccdc;
+	int stopping;
+	struct completion capture_stop;
 };
 
 #endif	/* AM437X_VPFE_H */
diff --git a/drivers/media/platform/am437x/am437x-vpfe_regs.h b/drivers/media/platform/am437x/am437x-vpfe_regs.h
index 0746c48ec23f..63ecdca3b908 100644
--- a/drivers/media/platform/am437x/am437x-vpfe_regs.h
+++ b/drivers/media/platform/am437x/am437x-vpfe_regs.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /*
  * TI AM437x Image Sensor Interface Registers
  *
@@ -5,15 +6,6 @@
  *
  * Benoit Parrot <bparrot@ti.com>
  * Lad, Prabhakar <prabhakar.csengg@gmail.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
- * This program is distributed "as is" WITHOUT ANY WARRANTY of any
- * kind, whether express or implied; without even the implied warranty
- * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
  */
 
 #ifndef AM437X_VPFE_REGS_H
diff --git a/drivers/media/platform/aspeed-video.c b/drivers/media/platform/aspeed-video.c
index eb12f3793062..d8593cb2ae84 100644
--- a/drivers/media/platform/aspeed-video.c
+++ b/drivers/media/platform/aspeed-video.c
@@ -606,6 +606,16 @@ static irqreturn_t aspeed_video_irq(int irq, void *arg)
 			aspeed_video_start_frame(video);
 	}
 
+	/*
+	 * CAPTURE_COMPLETE and FRAME_COMPLETE interrupts come even when these
+	 * are disabled in the VE_INTERRUPT_CTRL register so clear them to
+	 * prevent unnecessary interrupt calls.
+	 */
+	if (sts & VE_INTERRUPT_CAPTURE_COMPLETE)
+		sts &= ~VE_INTERRUPT_CAPTURE_COMPLETE;
+	if (sts & VE_INTERRUPT_FRAME_COMPLETE)
+		sts &= ~VE_INTERRUPT_FRAME_COMPLETE;
+
 	return sts ? IRQ_NONE : IRQ_HANDLED;
 }
 
@@ -614,7 +624,7 @@ static void aspeed_video_check_and_set_polarity(struct aspeed_video *video)
 	int i;
 	int hsync_counter = 0;
 	int vsync_counter = 0;
-	u32 sts;
+	u32 sts, ctrl;
 
 	for (i = 0; i < NUM_POLARITY_CHECKS; ++i) {
 		sts = aspeed_video_read(video, VE_MODE_DETECT_STATUS);
@@ -629,30 +639,29 @@ static void aspeed_video_check_and_set_polarity(struct aspeed_video *video)
 			hsync_counter++;
 	}
 
-	if (hsync_counter < 0 || vsync_counter < 0) {
-		u32 ctrl = 0;
+	ctrl = aspeed_video_read(video, VE_CTRL);
 
-		if (hsync_counter < 0) {
-			ctrl = VE_CTRL_HSYNC_POL;
-			video->detected_timings.polarities &=
-				~V4L2_DV_HSYNC_POS_POL;
-		} else {
-			video->detected_timings.polarities |=
-				V4L2_DV_HSYNC_POS_POL;
-		}
-
-		if (vsync_counter < 0) {
-			ctrl = VE_CTRL_VSYNC_POL;
-			video->detected_timings.polarities &=
-				~V4L2_DV_VSYNC_POS_POL;
-		} else {
-			video->detected_timings.polarities |=
-				V4L2_DV_VSYNC_POS_POL;
-		}
+	if (hsync_counter < 0) {
+		ctrl |= VE_CTRL_HSYNC_POL;
+		video->detected_timings.polarities &=
+			~V4L2_DV_HSYNC_POS_POL;
+	} else {
+		ctrl &= ~VE_CTRL_HSYNC_POL;
+		video->detected_timings.polarities |=
+			V4L2_DV_HSYNC_POS_POL;
+	}
 
-		if (ctrl)
-			aspeed_video_update(video, VE_CTRL, 0, ctrl);
+	if (vsync_counter < 0) {
+		ctrl |= VE_CTRL_VSYNC_POL;
+		video->detected_timings.polarities &=
+			~V4L2_DV_VSYNC_POS_POL;
+	} else {
+		ctrl &= ~VE_CTRL_VSYNC_POL;
+		video->detected_timings.polarities |=
+			V4L2_DV_VSYNC_POS_POL;
 	}
+
+	aspeed_video_write(video, VE_CTRL, ctrl);
 }
 
 static bool aspeed_video_alloc_buf(struct aspeed_video *video,
@@ -741,6 +750,8 @@ static void aspeed_video_get_resolution(struct aspeed_video *video)
 		}
 
 		set_bit(VIDEO_RES_DETECT, &video->flags);
+		aspeed_video_update(video, VE_CTRL,
+				    VE_CTRL_VSYNC_POL | VE_CTRL_HSYNC_POL, 0);
 		aspeed_video_enable_mode_detect(video);
 
 		rc = wait_event_interruptible_timeout(video->wait,
@@ -1646,7 +1657,8 @@ static int aspeed_video_probe(struct platform_device *pdev)
 {
 	int rc;
 	struct resource *res;
-	struct aspeed_video *video = kzalloc(sizeof(*video), GFP_KERNEL);
+	struct aspeed_video *video =
+		devm_kzalloc(&pdev->dev, sizeof(*video), GFP_KERNEL);
 
 	if (!video)
 		return -ENOMEM;
diff --git a/drivers/media/platform/cadence/cdns-csi2rx.c b/drivers/media/platform/cadence/cdns-csi2rx.c
index 31ace114eda1..be9ec59774d6 100644
--- a/drivers/media/platform/cadence/cdns-csi2rx.c
+++ b/drivers/media/platform/cadence/cdns-csi2rx.c
@@ -129,7 +129,7 @@ static int csi2rx_start(struct csi2rx_priv *csi2rx)
 	 */
 	for (i = csi2rx->num_lanes; i < csi2rx->max_lanes; i++) {
 		unsigned int idx = find_first_zero_bit(&lanes_used,
-						       sizeof(lanes_used));
+						       csi2rx->max_lanes);
 		set_bit(idx, &lanes_used);
 		reg |= CSI2RX_STATIC_CFG_DLANE_MAP(i, i + 1);
 	}
diff --git a/drivers/media/platform/cec-gpio/cec-gpio.c b/drivers/media/platform/cec-gpio/cec-gpio.c
index 5b17d3a31896..7be91e712c4a 100644
--- a/drivers/media/platform/cec-gpio/cec-gpio.c
+++ b/drivers/media/platform/cec-gpio/cec-gpio.c
@@ -8,10 +8,12 @@
 #include <linux/delay.h>
 #include <linux/platform_device.h>
 #include <linux/gpio/consumer.h>
+#include <media/cec-notifier.h>
 #include <media/cec-pin.h>
 
 struct cec_gpio {
 	struct cec_adapter	*adap;
+	struct cec_notifier	*notifier;
 	struct device		*dev;
 
 	struct gpio_desc	*cec_gpio;
@@ -173,9 +175,17 @@ static const struct cec_pin_ops cec_gpio_pin_ops = {
 static int cec_gpio_probe(struct platform_device *pdev)
 {
 	struct device *dev = &pdev->dev;
+	struct device *hdmi_dev;
 	struct cec_gpio *cec;
+	u32 caps = CEC_CAP_DEFAULTS | CEC_CAP_MONITOR_ALL | CEC_CAP_MONITOR_PIN;
 	int ret;
 
+	hdmi_dev = cec_notifier_parse_hdmi_phandle(dev);
+	if (PTR_ERR(hdmi_dev) == -EPROBE_DEFER)
+		return PTR_ERR(hdmi_dev);
+	if (IS_ERR(hdmi_dev))
+		caps |= CEC_CAP_PHYS_ADDR;
+
 	cec = devm_kzalloc(dev, sizeof(*cec), GFP_KERNEL);
 	if (!cec)
 		return -ENOMEM;
@@ -196,8 +206,7 @@ static int cec_gpio_probe(struct platform_device *pdev)
 		return PTR_ERR(cec->v5_gpio);
 
 	cec->adap = cec_pin_allocate_adapter(&cec_gpio_pin_ops,
-		cec, pdev->name, CEC_CAP_DEFAULTS | CEC_CAP_PHYS_ADDR |
-				 CEC_CAP_MONITOR_ALL | CEC_CAP_MONITOR_PIN);
+					     cec, pdev->name, caps);
 	if (IS_ERR(cec->adap))
 		return PTR_ERR(cec->adap);
 
@@ -205,7 +214,7 @@ static int cec_gpio_probe(struct platform_device *pdev)
 			       IRQF_TRIGGER_RISING | IRQF_TRIGGER_FALLING,
 			       cec->adap->name, cec);
 	if (ret)
-		return ret;
+		goto del_adap;
 
 	cec_gpio_disable_irq(cec->adap);
 
@@ -218,7 +227,7 @@ static int cec_gpio_probe(struct platform_device *pdev)
 			IRQF_TRIGGER_FALLING | IRQF_TRIGGER_RISING,
 			"hpd-gpio", cec);
 		if (ret)
-			return ret;
+			goto del_adap;
 	}
 
 	if (cec->v5_gpio) {
@@ -230,23 +239,37 @@ static int cec_gpio_probe(struct platform_device *pdev)
 			IRQF_TRIGGER_FALLING | IRQF_TRIGGER_RISING,
 			"v5-gpio", cec);
 		if (ret)
-			return ret;
+			goto del_adap;
 	}
 
-	ret = cec_register_adapter(cec->adap, &pdev->dev);
-	if (ret) {
-		cec_delete_adapter(cec->adap);
-		return ret;
+	if (!IS_ERR(hdmi_dev)) {
+		cec->notifier = cec_notifier_cec_adap_register(hdmi_dev, NULL,
+							       cec->adap);
+		if (!cec->notifier) {
+			ret = -ENOMEM;
+			goto del_adap;
+		}
 	}
 
+	ret = cec_register_adapter(cec->adap, &pdev->dev);
+	if (ret)
+		goto unreg_notifier;
+
 	platform_set_drvdata(pdev, cec);
 	return 0;
+
+unreg_notifier:
+	cec_notifier_cec_adap_unregister(cec->notifier);
+del_adap:
+	cec_delete_adapter(cec->adap);
+	return ret;
 }
 
 static int cec_gpio_remove(struct platform_device *pdev)
 {
 	struct cec_gpio *cec = platform_get_drvdata(pdev);
 
+	cec_notifier_cec_adap_unregister(cec->notifier);
 	cec_unregister_adapter(cec->adap);
 	return 0;
 }
diff --git a/drivers/media/platform/coda/coda-common.c b/drivers/media/platform/coda/coda-common.c
index 73222c0615c0..94fb4d2ecc43 100644
--- a/drivers/media/platform/coda/coda-common.c
+++ b/drivers/media/platform/coda/coda-common.c
@@ -933,7 +933,8 @@ static int coda_g_selection(struct file *file, void *fh,
 		rsel = &r;
 		/* fallthrough */
 	case V4L2_SEL_TGT_CROP:
-		if (s->type != V4L2_BUF_TYPE_VIDEO_OUTPUT)
+		if (s->type != V4L2_BUF_TYPE_VIDEO_OUTPUT ||
+		    ctx->inst_type == CODA_INST_DECODER)
 			return -EINVAL;
 		break;
 	case V4L2_SEL_TGT_COMPOSE_BOUNDS:
@@ -942,7 +943,8 @@ static int coda_g_selection(struct file *file, void *fh,
 		/* fallthrough */
 	case V4L2_SEL_TGT_COMPOSE:
 	case V4L2_SEL_TGT_COMPOSE_DEFAULT:
-		if (s->type != V4L2_BUF_TYPE_VIDEO_CAPTURE)
+		if (s->type != V4L2_BUF_TYPE_VIDEO_CAPTURE ||
+		    ctx->inst_type == CODA_INST_ENCODER)
 			return -EINVAL;
 		break;
 	default:
@@ -1084,16 +1086,16 @@ static int coda_decoder_cmd(struct file *file, void *fh,
 
 	switch (dc->cmd) {
 	case V4L2_DEC_CMD_START:
-		mutex_lock(&ctx->bitstream_mutex);
 		mutex_lock(&dev->coda_mutex);
+		mutex_lock(&ctx->bitstream_mutex);
 		coda_bitstream_flush(ctx);
-		mutex_unlock(&dev->coda_mutex);
 		dst_vq = v4l2_m2m_get_vq(ctx->fh.m2m_ctx,
 					 V4L2_BUF_TYPE_VIDEO_CAPTURE);
 		vb2_clear_last_buffer_dequeued(dst_vq);
 		ctx->bit_stream_param &= ~CODA_BIT_STREAM_END_FLAG;
 		coda_fill_bitstream(ctx, NULL);
 		mutex_unlock(&ctx->bitstream_mutex);
+		mutex_unlock(&dev->coda_mutex);
 		break;
 	case V4L2_DEC_CMD_STOP:
 		stream_end = false;
@@ -2387,6 +2389,7 @@ int coda_decoder_queue_init(void *priv, struct vb2_queue *src_vq,
 
 	dst_vq->type = V4L2_BUF_TYPE_VIDEO_CAPTURE;
 	dst_vq->io_modes = VB2_DMABUF | VB2_MMAP;
+	dst_vq->dma_attrs = DMA_ATTR_NO_KERNEL_MAPPING;
 	dst_vq->mem_ops = &vb2_dma_contig_memops;
 
 	return coda_queue_init(priv, dst_vq);
@@ -2959,8 +2962,6 @@ static int coda_probe(struct platform_device *pdev)
 	else
 		return -EINVAL;
 
-	spin_lock_init(&dev->irqlock);
-
 	dev->dev = &pdev->dev;
 	dev->clk_per = devm_clk_get(&pdev->dev, "per");
 	if (IS_ERR(dev->clk_per)) {
diff --git a/drivers/media/platform/coda/coda.h b/drivers/media/platform/coda/coda.h
index 848bf1da401e..9f226140b486 100644
--- a/drivers/media/platform/coda/coda.h
+++ b/drivers/media/platform/coda/coda.h
@@ -86,7 +86,6 @@ struct coda_dev {
 	struct gen_pool		*iram_pool;
 	struct coda_aux_buf	iram;
 
-	spinlock_t		irqlock;
 	struct mutex		dev_mutex;
 	struct mutex		coda_mutex;
 	struct workqueue_struct	*workqueue;
diff --git a/drivers/media/platform/exynos4-is/fimc-isp-video.c b/drivers/media/platform/exynos4-is/fimc-isp-video.c
index 378cc302e1f8..d2cbcdca0463 100644
--- a/drivers/media/platform/exynos4-is/fimc-isp-video.c
+++ b/drivers/media/platform/exynos4-is/fimc-isp-video.c
@@ -313,7 +313,7 @@ static int isp_video_release(struct file *file)
 		ivc->streaming = 0;
 	}
 
-	vb2_fop_release(file);
+	_vb2_fop_release(file, NULL);
 
 	if (v4l2_fh_is_singular_file(file)) {
 		fimc_pipeline_call(&ivc->ve, close);
diff --git a/drivers/media/platform/exynos4-is/media-dev.c b/drivers/media/platform/exynos4-is/media-dev.c
index a838189d4490..9aaf3b8060d5 100644
--- a/drivers/media/platform/exynos4-is/media-dev.c
+++ b/drivers/media/platform/exynos4-is/media-dev.c
@@ -1457,12 +1457,12 @@ static int fimc_md_probe(struct platform_device *pdev)
 	ret = v4l2_device_register(dev, &fmd->v4l2_dev);
 	if (ret < 0) {
 		v4l2_err(v4l2_dev, "Failed to register v4l2_device: %d\n", ret);
-		return ret;
+		goto err_md;
 	}
 
 	ret = fimc_md_get_clocks(fmd);
 	if (ret)
-		goto err_md;
+		goto err_v4l2dev;
 
 	ret = fimc_md_get_pinctrl(fmd);
 	if (ret < 0) {
@@ -1519,9 +1519,10 @@ err_m_ent:
 	fimc_md_unregister_entities(fmd);
 err_clk:
 	fimc_md_put_clocks(fmd);
+err_v4l2dev:
+	v4l2_device_unregister(&fmd->v4l2_dev);
 err_md:
 	media_device_cleanup(&fmd->media_dev);
-	v4l2_device_unregister(&fmd->v4l2_dev);
 	return ret;
 }
 
diff --git a/drivers/media/platform/meson/ao-cec-g12a.c b/drivers/media/platform/meson/ao-cec-g12a.c
index 3b39e875292e..3d8fe854feb0 100644
--- a/drivers/media/platform/meson/ao-cec-g12a.c
+++ b/drivers/media/platform/meson/ao-cec-g12a.c
@@ -662,34 +662,27 @@ static int meson_ao_cec_g12a_probe(struct platform_device *pdev)
 	if (IS_ERR(ao_cec->adap))
 		return PTR_ERR(ao_cec->adap);
 
-	ao_cec->notify = cec_notifier_cec_adap_register(hdmi_dev, NULL,
-							ao_cec->adap);
-	if (!ao_cec->notify) {
-		ret = -ENOMEM;
-		goto out_probe_adapter;
-	}
-
 	ao_cec->adap->owner = THIS_MODULE;
 
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	base = devm_ioremap_resource(&pdev->dev, res);
 	if (IS_ERR(base)) {
 		ret = PTR_ERR(base);
-		goto out_probe_notify;
+		goto out_probe_adapter;
 	}
 
 	ao_cec->regmap = devm_regmap_init_mmio(&pdev->dev, base,
 					       &meson_ao_cec_g12a_regmap_conf);
 	if (IS_ERR(ao_cec->regmap)) {
 		ret = PTR_ERR(ao_cec->regmap);
-		goto out_probe_notify;
+		goto out_probe_adapter;
 	}
 
 	ao_cec->regmap_cec = devm_regmap_init(&pdev->dev, NULL, ao_cec,
 					   &meson_ao_cec_g12a_cec_regmap_conf);
 	if (IS_ERR(ao_cec->regmap_cec)) {
 		ret = PTR_ERR(ao_cec->regmap_cec);
-		goto out_probe_notify;
+		goto out_probe_adapter;
 	}
 
 	irq = platform_get_irq(pdev, 0);
@@ -699,45 +692,52 @@ static int meson_ao_cec_g12a_probe(struct platform_device *pdev)
 					0, NULL, ao_cec);
 	if (ret) {
 		dev_err(&pdev->dev, "irq request failed\n");
-		goto out_probe_notify;
+		goto out_probe_adapter;
 	}
 
 	ao_cec->oscin = devm_clk_get(&pdev->dev, "oscin");
 	if (IS_ERR(ao_cec->oscin)) {
 		dev_err(&pdev->dev, "oscin clock request failed\n");
 		ret = PTR_ERR(ao_cec->oscin);
-		goto out_probe_notify;
+		goto out_probe_adapter;
 	}
 
 	ret = meson_ao_cec_g12a_setup_clk(ao_cec);
 	if (ret)
-		goto out_probe_notify;
+		goto out_probe_adapter;
 
 	ret = clk_prepare_enable(ao_cec->core);
 	if (ret) {
 		dev_err(&pdev->dev, "core clock enable failed\n");
-		goto out_probe_notify;
+		goto out_probe_adapter;
 	}
 
 	device_reset_optional(&pdev->dev);
 
 	platform_set_drvdata(pdev, ao_cec);
 
+	ao_cec->notify = cec_notifier_cec_adap_register(hdmi_dev, NULL,
+							ao_cec->adap);
+	if (!ao_cec->notify) {
+		ret = -ENOMEM;
+		goto out_probe_core_clk;
+	}
+
 	ret = cec_register_adapter(ao_cec->adap, &pdev->dev);
 	if (ret < 0)
-		goto out_probe_core_clk;
+		goto out_probe_notify;
 
 	/* Setup Hardware */
 	regmap_write(ao_cec->regmap, CECB_GEN_CNTL_REG, CECB_GEN_CNTL_RESET);
 
 	return 0;
 
-out_probe_core_clk:
-	clk_disable_unprepare(ao_cec->core);
-
 out_probe_notify:
 	cec_notifier_cec_adap_unregister(ao_cec->notify);
 
+out_probe_core_clk:
+	clk_disable_unprepare(ao_cec->core);
+
 out_probe_adapter:
 	cec_delete_adapter(ao_cec->adap);
 
diff --git a/drivers/media/platform/meson/ao-cec.c b/drivers/media/platform/meson/ao-cec.c
index 64ed549bf012..03600e8b3ef0 100644
--- a/drivers/media/platform/meson/ao-cec.c
+++ b/drivers/media/platform/meson/ao-cec.c
@@ -624,20 +624,13 @@ static int meson_ao_cec_probe(struct platform_device *pdev)
 	if (IS_ERR(ao_cec->adap))
 		return PTR_ERR(ao_cec->adap);
 
-	ao_cec->notify = cec_notifier_cec_adap_register(hdmi_dev, NULL,
-							ao_cec->adap);
-	if (!ao_cec->notify) {
-		ret = -ENOMEM;
-		goto out_probe_adapter;
-	}
-
 	ao_cec->adap->owner = THIS_MODULE;
 
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	ao_cec->base = devm_ioremap_resource(&pdev->dev, res);
 	if (IS_ERR(ao_cec->base)) {
 		ret = PTR_ERR(ao_cec->base);
-		goto out_probe_notify;
+		goto out_probe_adapter;
 	}
 
 	irq = platform_get_irq(pdev, 0);
@@ -647,20 +640,20 @@ static int meson_ao_cec_probe(struct platform_device *pdev)
 					0, NULL, ao_cec);
 	if (ret) {
 		dev_err(&pdev->dev, "irq request failed\n");
-		goto out_probe_notify;
+		goto out_probe_adapter;
 	}
 
 	ao_cec->core = devm_clk_get(&pdev->dev, "core");
 	if (IS_ERR(ao_cec->core)) {
 		dev_err(&pdev->dev, "core clock request failed\n");
 		ret = PTR_ERR(ao_cec->core);
-		goto out_probe_notify;
+		goto out_probe_adapter;
 	}
 
 	ret = clk_prepare_enable(ao_cec->core);
 	if (ret) {
 		dev_err(&pdev->dev, "core clock enable failed\n");
-		goto out_probe_notify;
+		goto out_probe_adapter;
 	}
 
 	ret = clk_set_rate(ao_cec->core, CEC_CLK_RATE);
@@ -674,9 +667,16 @@ static int meson_ao_cec_probe(struct platform_device *pdev)
 	ao_cec->pdev = pdev;
 	platform_set_drvdata(pdev, ao_cec);
 
+	ao_cec->notify = cec_notifier_cec_adap_register(hdmi_dev, NULL,
+							ao_cec->adap);
+	if (!ao_cec->notify) {
+		ret = -ENOMEM;
+		goto out_probe_clk;
+	}
+
 	ret = cec_register_adapter(ao_cec->adap, &pdev->dev);
 	if (ret < 0)
-		goto out_probe_clk;
+		goto out_probe_notify;
 
 	/* Setup Hardware */
 	writel_relaxed(CEC_GEN_CNTL_RESET,
@@ -684,12 +684,12 @@ static int meson_ao_cec_probe(struct platform_device *pdev)
 
 	return 0;
 
-out_probe_clk:
-	clk_disable_unprepare(ao_cec->core);
-
 out_probe_notify:
 	cec_notifier_cec_adap_unregister(ao_cec->notify);
 
+out_probe_clk:
+	clk_disable_unprepare(ao_cec->core);
+
 out_probe_adapter:
 	cec_delete_adapter(ao_cec->adap);
 
diff --git a/drivers/media/platform/mtk-vcodec/mtk_vcodec_dec.c b/drivers/media/platform/mtk-vcodec/mtk_vcodec_dec.c
index 26a55c3e807e..858727824889 100644
--- a/drivers/media/platform/mtk-vcodec/mtk_vcodec_dec.c
+++ b/drivers/media/platform/mtk-vcodec/mtk_vcodec_dec.c
@@ -284,7 +284,7 @@ static void mtk_vdec_update_fmt(struct mtk_vcodec_ctx *ctx,
 		fmt = &mtk_video_formats[k];
 		if (fmt->fourcc == pixelformat) {
 			mtk_v4l2_debug(1, "Update cap fourcc(%d -> %d)",
-				dst_q_data->fmt.fourcc, pixelformat);
+				dst_q_data->fmt->fourcc, pixelformat);
 			dst_q_data->fmt = fmt;
 			return;
 		}
@@ -841,12 +841,20 @@ static int vidioc_vdec_s_fmt(struct file *file, void *priv,
 		return -EINVAL;
 
 	pix_mp = &f->fmt.pix_mp;
+	/*
+	 * Setting OUTPUT format after OUTPUT buffers are allocated is invalid
+	 * if using the stateful API.
+	 */
 	if ((f->type == V4L2_BUF_TYPE_VIDEO_OUTPUT_MPLANE) &&
 	    vb2_is_busy(&ctx->m2m_ctx->out_q_ctx.q)) {
 		mtk_v4l2_err("out_q_ctx buffers already requested");
 		ret = -EBUSY;
 	}
 
+	/*
+	 * Setting CAPTURE format after CAPTURE buffers are allocated is
+	 * invalid.
+	 */
 	if ((f->type == V4L2_BUF_TYPE_VIDEO_CAPTURE_MPLANE) &&
 	    vb2_is_busy(&ctx->m2m_ctx->cap_q_ctx.q)) {
 		mtk_v4l2_err("cap_q_ctx buffers already requested");
@@ -865,6 +873,8 @@ static int vidioc_vdec_s_fmt(struct file *file, void *priv,
 			fmt = mtk_vdec_find_format(f);
 		}
 	}
+	if (fmt == NULL)
+		return -EINVAL;
 
 	q_data->fmt = fmt;
 	vidioc_try_fmt(f, q_data->fmt);
@@ -873,10 +883,10 @@ static int vidioc_vdec_s_fmt(struct file *file, void *priv,
 		q_data->coded_width = pix_mp->width;
 		q_data->coded_height = pix_mp->height;
 
-		ctx->colorspace = f->fmt.pix_mp.colorspace;
-		ctx->ycbcr_enc = f->fmt.pix_mp.ycbcr_enc;
-		ctx->quantization = f->fmt.pix_mp.quantization;
-		ctx->xfer_func = f->fmt.pix_mp.xfer_func;
+		ctx->colorspace = pix_mp->colorspace;
+		ctx->ycbcr_enc = pix_mp->ycbcr_enc;
+		ctx->quantization = pix_mp->quantization;
+		ctx->xfer_func = pix_mp->xfer_func;
 
 		if (ctx->state == MTK_STATE_FREE) {
 			ret = vdec_if_init(ctx, q_data->fmt->fourcc);
diff --git a/drivers/media/platform/mtk-vcodec/mtk_vcodec_dec_drv.c b/drivers/media/platform/mtk-vcodec/mtk_vcodec_dec_drv.c
index 00d090df11bb..944771ee5f5c 100644
--- a/drivers/media/platform/mtk-vcodec/mtk_vcodec_dec_drv.c
+++ b/drivers/media/platform/mtk-vcodec/mtk_vcodec_dec_drv.c
@@ -253,13 +253,7 @@ static int mtk_vcodec_probe(struct platform_device *pdev)
 	}
 
 	for (i = 0; i < NUM_MAX_VDEC_REG_BASE; i++) {
-		res = platform_get_resource(pdev, IORESOURCE_MEM, i);
-		if (res == NULL) {
-			dev_err(&pdev->dev, "get memory resource failed.");
-			ret = -ENXIO;
-			goto err_res;
-		}
-		dev->reg_base[i] = devm_ioremap_resource(&pdev->dev, res);
+		dev->reg_base[i] = devm_platform_ioremap_resource(pdev, i);
 		if (IS_ERR((__force void *)dev->reg_base[i])) {
 			ret = PTR_ERR((__force void *)dev->reg_base[i]);
 			goto err_res;
diff --git a/drivers/media/platform/mtk-vcodec/vdec/vdec_h264_if.c b/drivers/media/platform/mtk-vcodec/vdec/vdec_h264_if.c
index 49aa85a9bb5a..50048c170b99 100644
--- a/drivers/media/platform/mtk-vcodec/vdec/vdec_h264_if.c
+++ b/drivers/media/platform/mtk-vcodec/vdec/vdec_h264_if.c
@@ -283,7 +283,6 @@ static int vdec_h264_init(struct mtk_vcodec_ctx *ctx)
 	inst->vpu.id = IPI_VDEC_H264;
 	inst->vpu.dev = ctx->dev->vpu_plat_dev;
 	inst->vpu.ctx = ctx;
-	inst->vpu.handler = vpu_dec_ipi_handler;
 
 	err = vpu_dec_init(&inst->vpu);
 	if (err) {
diff --git a/drivers/media/platform/mtk-vcodec/vdec/vdec_vp8_if.c b/drivers/media/platform/mtk-vcodec/vdec/vdec_vp8_if.c
index 63a8708ce682..6011fdd60a22 100644
--- a/drivers/media/platform/mtk-vcodec/vdec/vdec_vp8_if.c
+++ b/drivers/media/platform/mtk-vcodec/vdec/vdec_vp8_if.c
@@ -402,7 +402,6 @@ static int vdec_vp8_init(struct mtk_vcodec_ctx *ctx)
 	inst->vpu.id = IPI_VDEC_VP8;
 	inst->vpu.dev = ctx->dev->vpu_plat_dev;
 	inst->vpu.ctx = ctx;
-	inst->vpu.handler = vpu_dec_ipi_handler;
 
 	err = vpu_dec_init(&inst->vpu);
 	if (err) {
diff --git a/drivers/media/platform/mtk-vcodec/vdec/vdec_vp9_if.c b/drivers/media/platform/mtk-vcodec/vdec/vdec_vp9_if.c
index 5066c283d86d..24c1f0bf2147 100644
--- a/drivers/media/platform/mtk-vcodec/vdec/vdec_vp9_if.c
+++ b/drivers/media/platform/mtk-vcodec/vdec/vdec_vp9_if.c
@@ -793,7 +793,6 @@ static int vdec_vp9_init(struct mtk_vcodec_ctx *ctx)
 	inst->vpu.id = IPI_VDEC_VP9;
 	inst->vpu.dev = ctx->dev->vpu_plat_dev;
 	inst->vpu.ctx = ctx;
-	inst->vpu.handler = vpu_dec_ipi_handler;
 
 	if (vpu_dec_init(&inst->vpu)) {
 		mtk_vcodec_err(inst, "vp9_dec_vpu_init failed");
diff --git a/drivers/media/platform/mtk-vcodec/vdec_vpu_if.c b/drivers/media/platform/mtk-vcodec/vdec_vpu_if.c
index 3f38cc4509ef..70abfd4cd4b9 100644
--- a/drivers/media/platform/mtk-vcodec/vdec_vpu_if.c
+++ b/drivers/media/platform/mtk-vcodec/vdec_vpu_if.c
@@ -25,10 +25,16 @@ static void handle_init_ack_msg(struct vdec_vpu_ipi_init_ack *msg)
 }
 
 /*
+ * vpu_dec_ipi_handler - Handler for VPU ipi message.
+ *
+ * @data: ipi message
+ * @len : length of ipi message
+ * @priv: callback private data which is passed by decoder when register.
+ *
  * This function runs in interrupt context and it means there's an IPI MSG
  * from VPU.
  */
-void vpu_dec_ipi_handler(void *data, unsigned int len, void *priv)
+static void vpu_dec_ipi_handler(void *data, unsigned int len, void *priv)
 {
 	struct vdec_vpu_ipi_ack *msg = data;
 	struct vdec_vpu_inst *vpu = (struct vdec_vpu_inst *)
@@ -102,6 +108,7 @@ int vpu_dec_init(struct vdec_vpu_inst *vpu)
 	mtk_vcodec_debug_enter(vpu);
 
 	init_waitqueue_head(&vpu->wq);
+	vpu->handler = vpu_dec_ipi_handler;
 
 	err = vpu_ipi_register(vpu->dev, vpu->id, vpu->handler, "vdec", NULL);
 	if (err != 0) {
diff --git a/drivers/media/platform/mtk-vcodec/vdec_vpu_if.h b/drivers/media/platform/mtk-vcodec/vdec_vpu_if.h
index b76f717e4fd7..f779b0676fbd 100644
--- a/drivers/media/platform/mtk-vcodec/vdec_vpu_if.h
+++ b/drivers/media/platform/mtk-vcodec/vdec_vpu_if.h
@@ -76,13 +76,4 @@ int vpu_dec_deinit(struct vdec_vpu_inst *vpu);
  */
 int vpu_dec_reset(struct vdec_vpu_inst *vpu);
 
-/**
- * vpu_dec_ipi_handler - Handler for VPU ipi message.
- *
- * @data: ipi message
- * @len : length of ipi message
- * @priv: callback private data which is passed by decoder when register.
- */
-void vpu_dec_ipi_handler(void *data, unsigned int len, void *priv);
-
 #endif
diff --git a/drivers/media/platform/mtk-vpu/mtk_vpu.c b/drivers/media/platform/mtk-vpu/mtk_vpu.c
index cc2ff40d060d..a768707abb94 100644
--- a/drivers/media/platform/mtk-vpu/mtk_vpu.c
+++ b/drivers/media/platform/mtk-vpu/mtk_vpu.c
@@ -273,7 +273,7 @@ int vpu_ipi_register(struct platform_device *pdev,
 		return -EPROBE_DEFER;
 	}
 
-	if (id >= 0 && id < IPI_MAX && handler) {
+	if (id < IPI_MAX && handler) {
 		ipi_desc = vpu->ipi_desc;
 		ipi_desc[id].name = name;
 		ipi_desc[id].handler = handler;
@@ -398,7 +398,7 @@ int vpu_wdt_reg_handler(struct platform_device *pdev,
 
 	handler = vpu->wdt.handler;
 
-	if (id >= 0 && id < VPU_RST_MAX && wdt_reset) {
+	if (id < VPU_RST_MAX && wdt_reset) {
 		dev_dbg(vpu->dev, "wdt register id %d\n", id);
 		mutex_lock(&vpu->vpu_mutex);
 		handler[id].reset_func = wdt_reset;
diff --git a/drivers/media/platform/qcom/venus/core.c b/drivers/media/platform/qcom/venus/core.c
index e6eff512a8a1..07312a2fab24 100644
--- a/drivers/media/platform/qcom/venus/core.c
+++ b/drivers/media/platform/qcom/venus/core.c
@@ -5,6 +5,7 @@
  */
 #include <linux/clk.h>
 #include <linux/init.h>
+#include <linux/interconnect.h>
 #include <linux/ioctl.h>
 #include <linux/list.h>
 #include <linux/module.h>
@@ -239,6 +240,14 @@ static int venus_probe(struct platform_device *pdev)
 	if (IS_ERR(core->base))
 		return PTR_ERR(core->base);
 
+	core->video_path = of_icc_get(dev, "video-mem");
+	if (IS_ERR(core->video_path))
+		return PTR_ERR(core->video_path);
+
+	core->cpucfg_path = of_icc_get(dev, "cpu-cfg");
+	if (IS_ERR(core->cpucfg_path))
+		return PTR_ERR(core->cpucfg_path);
+
 	core->irq = platform_get_irq(pdev, 0);
 	if (core->irq < 0)
 		return core->irq;
@@ -273,6 +282,10 @@ static int venus_probe(struct platform_device *pdev)
 	if (ret)
 		return ret;
 
+	ret = icc_set_bw(core->cpucfg_path, 0, kbps_to_icc(1000));
+	if (ret)
+		return ret;
+
 	ret = hfi_create(core, &venus_core_ops);
 	if (ret)
 		return ret;
@@ -355,6 +368,9 @@ static int venus_remove(struct platform_device *pdev)
 	pm_runtime_put_sync(dev);
 	pm_runtime_disable(dev);
 
+	icc_put(core->video_path);
+	icc_put(core->cpucfg_path);
+
 	v4l2_device_unregister(&core->v4l2_dev);
 
 	return ret;
@@ -427,10 +443,11 @@ static const struct venus_resources msm8916_res = {
 };
 
 static const struct freq_tbl msm8996_freq_table[] = {
-	{ 1944000, 490000000 },	/* 4k UHD @ 60 */
-	{  972000, 320000000 },	/* 4k UHD @ 30 */
-	{  489600, 150000000 },	/* 1080p @ 60 */
-	{  244800,  75000000 },	/* 1080p @ 30 */
+	{ 1944000, 520000000 },	/* 4k UHD @ 60 (decode only) */
+	{  972000, 520000000 },	/* 4k UHD @ 30 */
+	{  489600, 346666667 },	/* 1080p @ 60 */
+	{  244800, 150000000 },	/* 1080p @ 30 */
+	{  108000,  75000000 },	/* 720p @ 30 */
 };
 
 static const struct reg_val msm8996_reg_preset[] = {
@@ -464,9 +481,40 @@ static const struct freq_tbl sdm845_freq_table[] = {
 	{  244800, 100000000 },	/* 1920x1080@30 */
 };
 
+static struct codec_freq_data sdm845_codec_freq_data[] =  {
+	{ V4L2_PIX_FMT_H264, VIDC_SESSION_TYPE_ENC, 675, 10 },
+	{ V4L2_PIX_FMT_HEVC, VIDC_SESSION_TYPE_ENC, 675, 10 },
+	{ V4L2_PIX_FMT_VP8, VIDC_SESSION_TYPE_ENC, 675, 10 },
+	{ V4L2_PIX_FMT_MPEG2, VIDC_SESSION_TYPE_DEC, 200, 10 },
+	{ V4L2_PIX_FMT_H264, VIDC_SESSION_TYPE_DEC, 200, 10 },
+	{ V4L2_PIX_FMT_HEVC, VIDC_SESSION_TYPE_DEC, 200, 10 },
+	{ V4L2_PIX_FMT_VP8, VIDC_SESSION_TYPE_DEC, 200, 10 },
+	{ V4L2_PIX_FMT_VP9, VIDC_SESSION_TYPE_DEC, 200, 10 },
+};
+
+static const struct bw_tbl sdm845_bw_table_enc[] = {
+	{ 1944000, 1612000, 0, 2416000, 0 },	/* 3840x2160@60 */
+	{  972000,  951000, 0, 1434000, 0 },	/* 3840x2160@30 */
+	{  489600,  723000, 0,  973000, 0 },	/* 1920x1080@60 */
+	{  244800,  370000, 0,	495000, 0 },	/* 1920x1080@30 */
+};
+
+static const struct bw_tbl sdm845_bw_table_dec[] = {
+	{ 2073600, 3929000, 0, 5551000, 0 },	/* 4096x2160@60 */
+	{ 1036800, 1987000, 0, 2797000, 0 },	/* 4096x2160@30 */
+	{  489600, 1040000, 0, 1298000, 0 },	/* 1920x1080@60 */
+	{  244800,  530000, 0,  659000, 0 },	/* 1920x1080@30 */
+};
+
 static const struct venus_resources sdm845_res = {
 	.freq_tbl = sdm845_freq_table,
 	.freq_tbl_size = ARRAY_SIZE(sdm845_freq_table),
+	.bw_tbl_enc = sdm845_bw_table_enc,
+	.bw_tbl_enc_size = ARRAY_SIZE(sdm845_bw_table_enc),
+	.bw_tbl_dec = sdm845_bw_table_dec,
+	.bw_tbl_dec_size = ARRAY_SIZE(sdm845_bw_table_dec),
+	.codec_freq_data = sdm845_codec_freq_data,
+	.codec_freq_data_size = ARRAY_SIZE(sdm845_codec_freq_data),
 	.clks = {"core", "iface", "bus" },
 	.clks_num = 3,
 	.max_load = 3110400,	/* 4096x2160@90 */
diff --git a/drivers/media/platform/qcom/venus/core.h b/drivers/media/platform/qcom/venus/core.h
index 922cb7e64bfa..11585fb3cae3 100644
--- a/drivers/media/platform/qcom/venus/core.h
+++ b/drivers/media/platform/qcom/venus/core.h
@@ -26,12 +26,33 @@ struct reg_val {
 	u32 value;
 };
 
+struct codec_freq_data {
+	u32 pixfmt;
+	u32 session_type;
+	unsigned long vpp_freq;
+	unsigned long vsp_freq;
+};
+
+struct bw_tbl {
+	u32 mbs_per_sec;
+	u32 avg;
+	u32 peak;
+	u32 avg_10bit;
+	u32 peak_10bit;
+};
+
 struct venus_resources {
 	u64 dma_mask;
 	const struct freq_tbl *freq_tbl;
 	unsigned int freq_tbl_size;
+	const struct bw_tbl *bw_tbl_enc;
+	unsigned int bw_tbl_enc_size;
+	const struct bw_tbl *bw_tbl_dec;
+	unsigned int bw_tbl_dec_size;
 	const struct reg_val *reg_tbl;
 	unsigned int reg_tbl_size;
+	const struct codec_freq_data *codec_freq_data;
+	unsigned int codec_freq_data_size;
 	const char * const clks[VIDC_CLKS_NUM_MAX];
 	unsigned int clks_num;
 	enum hfi_version hfi_version;
@@ -115,6 +136,8 @@ struct venus_core {
 	struct clk *core1_clk;
 	struct clk *core0_bus_clk;
 	struct clk *core1_bus_clk;
+	struct icc_path *video_path;
+	struct icc_path *cpucfg_path;
 	struct video_device *vdev_dec;
 	struct video_device *vdev_enc;
 	struct v4l2_device v4l2_dev;
@@ -208,6 +231,12 @@ struct venus_buffer {
 	struct list_head ref_list;
 };
 
+struct clock_data {
+	u32 core_id;
+	unsigned long freq;
+	const struct codec_freq_data *codec_freq_data;
+};
+
 #define to_venus_buffer(ptr)	container_of(ptr, struct venus_buffer, vb)
 
 enum venus_dec_state {
@@ -288,6 +317,7 @@ struct venus_inst {
 	struct list_head list;
 	struct mutex lock;
 	struct venus_core *core;
+	struct clock_data clk_data;
 	struct list_head dpbbufs;
 	struct list_head internalbufs;
 	struct list_head registeredbufs;
diff --git a/drivers/media/platform/qcom/venus/helpers.c b/drivers/media/platform/qcom/venus/helpers.c
index 1ad96c25ab09..a172f1ac0b35 100644
--- a/drivers/media/platform/qcom/venus/helpers.c
+++ b/drivers/media/platform/qcom/venus/helpers.c
@@ -5,6 +5,7 @@
  */
 #include <linux/clk.h>
 #include <linux/iopoll.h>
+#include <linux/interconnect.h>
 #include <linux/list.h>
 #include <linux/mutex.h>
 #include <linux/pm_runtime.h>
@@ -388,12 +389,91 @@ static u32 load_per_type(struct venus_core *core, u32 session_type)
 	return mbs_per_sec;
 }
 
-int venus_helper_load_scale_clocks(struct venus_core *core)
+static void mbs_to_bw(struct venus_inst *inst, u32 mbs, u32 *avg, u32 *peak)
 {
+	const struct venus_resources *res = inst->core->res;
+	const struct bw_tbl *bw_tbl;
+	unsigned int num_rows, i;
+
+	*avg = 0;
+	*peak = 0;
+
+	if (mbs == 0)
+		return;
+
+	if (inst->session_type == VIDC_SESSION_TYPE_ENC) {
+		num_rows = res->bw_tbl_enc_size;
+		bw_tbl = res->bw_tbl_enc;
+	} else if (inst->session_type == VIDC_SESSION_TYPE_DEC) {
+		num_rows = res->bw_tbl_dec_size;
+		bw_tbl = res->bw_tbl_dec;
+	} else {
+		return;
+	}
+
+	if (!bw_tbl || num_rows == 0)
+		return;
+
+	for (i = 0; i < num_rows; i++) {
+		if (mbs > bw_tbl[i].mbs_per_sec)
+			break;
+
+		if (inst->dpb_fmt & HFI_COLOR_FORMAT_10_BIT_BASE) {
+			*avg = bw_tbl[i].avg_10bit;
+			*peak = bw_tbl[i].peak_10bit;
+		} else {
+			*avg = bw_tbl[i].avg;
+			*peak = bw_tbl[i].peak;
+		}
+	}
+}
+
+static int load_scale_bw(struct venus_core *core)
+{
+	struct venus_inst *inst = NULL;
+	u32 mbs_per_sec, avg, peak, total_avg = 0, total_peak = 0;
+
+	mutex_lock(&core->lock);
+	list_for_each_entry(inst, &core->instances, list) {
+		mbs_per_sec = load_per_instance(inst);
+		mbs_to_bw(inst, mbs_per_sec, &avg, &peak);
+		total_avg += avg;
+		total_peak += peak;
+	}
+	mutex_unlock(&core->lock);
+
+	dev_dbg(core->dev, "total: avg_bw: %u, peak_bw: %u\n",
+		total_avg, total_peak);
+
+	return icc_set_bw(core->video_path, total_avg, total_peak);
+}
+
+static int set_clk_freq(struct venus_core *core, unsigned long freq)
+{
+	struct clk *clk = core->clks[0];
+	int ret;
+
+	ret = clk_set_rate(clk, freq);
+	if (ret)
+		return ret;
+
+	ret = clk_set_rate(core->core0_clk, freq);
+	if (ret)
+		return ret;
+
+	ret = clk_set_rate(core->core1_clk, freq);
+	if (ret)
+		return ret;
+
+	return 0;
+}
+
+static int scale_clocks(struct venus_inst *inst)
+{
+	struct venus_core *core = inst->core;
 	const struct freq_tbl *table = core->res->freq_tbl;
 	unsigned int num_rows = core->res->freq_tbl_size;
 	unsigned long freq = table[0].freq;
-	struct clk *clk = core->clks[0];
 	struct device *dev = core->dev;
 	u32 mbs_per_sec;
 	unsigned int i;
@@ -419,23 +499,124 @@ int venus_helper_load_scale_clocks(struct venus_core *core)
 
 set_freq:
 
-	ret = clk_set_rate(clk, freq);
-	if (ret)
-		goto err;
+	ret = set_clk_freq(core, freq);
+	if (ret) {
+		dev_err(dev, "failed to set clock rate %lu (%d)\n",
+			freq, ret);
+		return ret;
+	}
 
-	ret = clk_set_rate(core->core0_clk, freq);
-	if (ret)
-		goto err;
+	ret = load_scale_bw(core);
+	if (ret) {
+		dev_err(dev, "failed to set bandwidth (%d)\n",
+			ret);
+		return ret;
+	}
 
-	ret = clk_set_rate(core->core1_clk, freq);
-	if (ret)
-		goto err;
+	return 0;
+}
+
+static unsigned long calculate_inst_freq(struct venus_inst *inst,
+					 unsigned long filled_len)
+{
+	unsigned long vpp_freq = 0, vsp_freq = 0;
+	u32 fps = (u32)inst->fps;
+	u32 mbs_per_sec;
+
+	mbs_per_sec = load_per_instance(inst) / fps;
+
+	vpp_freq = mbs_per_sec * inst->clk_data.codec_freq_data->vpp_freq;
+	/* 21 / 20 is overhead factor */
+	vpp_freq += vpp_freq / 20;
+	vsp_freq = mbs_per_sec * inst->clk_data.codec_freq_data->vsp_freq;
+
+	/* 10 / 7 is overhead factor */
+	if (inst->session_type == VIDC_SESSION_TYPE_ENC)
+		vsp_freq += (inst->controls.enc.bitrate * 10) / 7;
+	else
+		vsp_freq += ((fps * filled_len * 8) * 10) / 7;
+
+	return max(vpp_freq, vsp_freq);
+}
+
+static int scale_clocks_v4(struct venus_inst *inst)
+{
+	struct venus_core *core = inst->core;
+	const struct freq_tbl *table = core->res->freq_tbl;
+	unsigned int num_rows = core->res->freq_tbl_size;
+	struct v4l2_m2m_ctx *m2m_ctx = inst->m2m_ctx;
+	struct device *dev = core->dev;
+	unsigned long freq = 0, freq_core1 = 0, freq_core2 = 0;
+	unsigned long filled_len = 0;
+	struct venus_buffer *buf, *n;
+	struct vb2_buffer *vb;
+	int i, ret;
+
+	v4l2_m2m_for_each_src_buf_safe(m2m_ctx, buf, n) {
+		vb = &buf->vb.vb2_buf;
+		filled_len = max(filled_len, vb2_get_plane_payload(vb, 0));
+	}
+
+	if (inst->session_type == VIDC_SESSION_TYPE_DEC && !filled_len)
+		return 0;
+
+	freq = calculate_inst_freq(inst, filled_len);
+	inst->clk_data.freq = freq;
+
+	mutex_lock(&core->lock);
+	list_for_each_entry(inst, &core->instances, list) {
+		if (inst->clk_data.core_id == VIDC_CORE_ID_1) {
+			freq_core1 += inst->clk_data.freq;
+		} else if (inst->clk_data.core_id == VIDC_CORE_ID_2) {
+			freq_core2 += inst->clk_data.freq;
+		} else if (inst->clk_data.core_id == VIDC_CORE_ID_3) {
+			freq_core1 += inst->clk_data.freq;
+			freq_core2 += inst->clk_data.freq;
+		}
+	}
+	mutex_unlock(&core->lock);
+
+	freq = max(freq_core1, freq_core2);
+
+	if (freq >= table[0].freq) {
+		freq = table[0].freq;
+		dev_warn(dev, "HW is overloaded, needed: %lu max: %lu\n",
+			 freq, table[0].freq);
+		goto set_freq;
+	}
+
+	for (i = num_rows - 1 ; i >= 0; i--) {
+		if (freq <= table[i].freq) {
+			freq = table[i].freq;
+			break;
+		}
+	}
+
+set_freq:
+
+	ret = set_clk_freq(core, freq);
+	if (ret) {
+		dev_err(dev, "failed to set clock rate %lu (%d)\n",
+			freq, ret);
+		return ret;
+	}
+
+	ret = load_scale_bw(core);
+	if (ret) {
+		dev_err(dev, "failed to set bandwidth (%d)\n",
+			ret);
+		return ret;
+	}
 
 	return 0;
+}
 
-err:
-	dev_err(dev, "failed to set clock rate %lu (%d)\n", freq, ret);
-	return ret;
+int venus_helper_load_scale_clocks(struct venus_inst *inst)
+{
+	if (IS_V4(inst->core))
+		return scale_clocks_v4(inst);
+
+	return scale_clocks(inst);
 }
 EXPORT_SYMBOL_GPL(venus_helper_load_scale_clocks);
 
@@ -541,6 +722,8 @@ session_process_buf(struct venus_inst *inst, struct vb2_v4l2_buffer *vbuf)
 
 		if (inst->session_type == VIDC_SESSION_TYPE_DEC)
 			put_ts_metadata(inst, vbuf);
+
+		venus_helper_load_scale_clocks(inst);
 	} else if (type == V4L2_BUF_TYPE_VIDEO_CAPTURE_MPLANE) {
 		if (inst->session_type == VIDC_SESSION_TYPE_ENC)
 			fdata.buffer_type = HFI_BUFFER_OUTPUT;
@@ -809,6 +992,7 @@ int venus_helper_set_core_usage(struct venus_inst *inst, u32 usage)
 	const u32 ptype = HFI_PROPERTY_CONFIG_VIDEOCORES_USAGE;
 	struct hfi_videocores_usage_type cu;
 
+	inst->clk_data.core_id = usage;
 	if (!IS_V4(inst->core))
 		return 0;
 
@@ -818,6 +1002,36 @@ int venus_helper_set_core_usage(struct venus_inst *inst, u32 usage)
 }
 EXPORT_SYMBOL_GPL(venus_helper_set_core_usage);
 
+int venus_helper_init_codec_freq_data(struct venus_inst *inst)
+{
+	const struct codec_freq_data *data;
+	unsigned int i, data_size;
+	u32 pixfmt;
+	int ret = 0;
+
+	if (!IS_V4(inst->core))
+		return 0;
+
+	data = inst->core->res->codec_freq_data;
+	data_size = inst->core->res->codec_freq_data_size;
+	pixfmt = inst->session_type == VIDC_SESSION_TYPE_DEC ?
+			inst->fmt_out->pixfmt : inst->fmt_cap->pixfmt;
+
+	for (i = 0; i < data_size; i++) {
+		if (data[i].pixfmt == pixfmt &&
+		    data[i].session_type == inst->session_type) {
+			inst->clk_data.codec_freq_data = &data[i];
+			break;
+		}
+	}
+
+	if (!inst->clk_data.codec_freq_data)
+		ret = -EINVAL;
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(venus_helper_init_codec_freq_data);
+
 int venus_helper_set_num_bufs(struct venus_inst *inst, unsigned int input_bufs,
 			      unsigned int output_bufs,
 			      unsigned int output2_bufs)
@@ -1140,7 +1354,7 @@ void venus_helper_vb2_stop_streaming(struct vb2_queue *q)
 
 		venus_helper_free_dpb_bufs(inst);
 
-		venus_helper_load_scale_clocks(core);
+		venus_helper_load_scale_clocks(inst);
 		INIT_LIST_HEAD(&inst->registeredbufs);
 	}
 
@@ -1193,7 +1407,6 @@ EXPORT_SYMBOL_GPL(venus_helper_process_initial_out_bufs);
 
 int venus_helper_vb2_start_streaming(struct venus_inst *inst)
 {
-	struct venus_core *core = inst->core;
 	int ret;
 
 	ret = venus_helper_intbufs_alloc(inst);
@@ -1204,7 +1417,7 @@ int venus_helper_vb2_start_streaming(struct venus_inst *inst)
 	if (ret)
 		goto err_bufs_free;
 
-	venus_helper_load_scale_clocks(core);
+	venus_helper_load_scale_clocks(inst);
 
 	ret = hfi_session_load_res(inst);
 	if (ret)
diff --git a/drivers/media/platform/qcom/venus/helpers.h b/drivers/media/platform/qcom/venus/helpers.h
index 01f411b12f81..34dcd0c13f06 100644
--- a/drivers/media/platform/qcom/venus/helpers.h
+++ b/drivers/media/platform/qcom/venus/helpers.h
@@ -33,6 +33,7 @@ int venus_helper_set_output_resolution(struct venus_inst *inst,
 				       unsigned int width, unsigned int height,
 				       u32 buftype);
 int venus_helper_set_work_mode(struct venus_inst *inst, u32 mode);
+int venus_helper_init_codec_freq_data(struct venus_inst *inst);
 int venus_helper_set_core_usage(struct venus_inst *inst, u32 usage);
 int venus_helper_set_num_bufs(struct venus_inst *inst, unsigned int input_bufs,
 			      unsigned int output_bufs,
@@ -59,7 +60,7 @@ int venus_helper_intbufs_free(struct venus_inst *inst);
 int venus_helper_intbufs_realloc(struct venus_inst *inst);
 int venus_helper_queue_dpb_bufs(struct venus_inst *inst);
 int venus_helper_unregister_bufs(struct venus_inst *inst);
-int venus_helper_load_scale_clocks(struct venus_core *core);
+int venus_helper_load_scale_clocks(struct venus_inst *inst);
 int venus_helper_process_initial_cap_bufs(struct venus_inst *inst);
 int venus_helper_process_initial_out_bufs(struct venus_inst *inst);
 void venus_helper_get_ts_metadata(struct venus_inst *inst, u64 timestamp_us,
diff --git a/drivers/media/platform/qcom/venus/hfi_venus.c b/drivers/media/platform/qcom/venus/hfi_venus.c
index 7129a2aea09a..0d8855014ab3 100644
--- a/drivers/media/platform/qcom/venus/hfi_venus.c
+++ b/drivers/media/platform/qcom/venus/hfi_venus.c
@@ -1472,6 +1472,7 @@ static int venus_suspend_3xx(struct venus_core *core)
 {
 	struct venus_hfi_device *hdev = to_hfi_priv(core);
 	struct device *dev = core->dev;
+	u32 ctrl_status;
 	bool val;
 	int ret;
 
@@ -1487,6 +1488,10 @@ static int venus_suspend_3xx(struct venus_core *core)
 		return -EINVAL;
 	}
 
+	ctrl_status = venus_readl(hdev, CPU_CS_SCIACMDARG0);
+	if (ctrl_status & CPU_CS_SCIACMDARG0_PC_READY)
+		goto power_off;
+
 	/*
 	 * Power collapse sequence for Venus 3xx and 4xx versions:
 	 * 1. Check for ARM9 and video core to be idle by checking WFI bit
@@ -1511,6 +1516,7 @@ static int venus_suspend_3xx(struct venus_core *core)
 	if (ret)
 		return ret;
 
+power_off:
 	mutex_lock(&hdev->lock);
 
 	ret = venus_power_off(hdev);
diff --git a/drivers/media/platform/qcom/venus/vdec.c b/drivers/media/platform/qcom/venus/vdec.c
index 7f4660555ddb..8feaf5daece9 100644
--- a/drivers/media/platform/qcom/venus/vdec.c
+++ b/drivers/media/platform/qcom/venus/vdec.c
@@ -685,6 +685,10 @@ static int vdec_session_init(struct venus_inst *inst)
 	if (ret)
 		goto deinit;
 
+	ret = venus_helper_init_codec_freq_data(inst);
+	if (ret)
+		goto deinit;
+
 	return 0;
 deinit:
 	hfi_session_deinit(inst);
@@ -864,7 +868,7 @@ reconfigure:
 	if (ret)
 		goto free_dpb_bufs;
 
-	venus_helper_load_scale_clocks(inst->core);
+	venus_helper_load_scale_clocks(inst);
 
 	ret = hfi_session_continue(inst);
 	if (ret)
@@ -1072,7 +1076,7 @@ static void vdec_session_release(struct venus_inst *inst)
 		hfi_session_abort(inst);
 
 	venus_helper_free_dpb_bufs(inst);
-	venus_helper_load_scale_clocks(core);
+	venus_helper_load_scale_clocks(inst);
 	INIT_LIST_HEAD(&inst->registeredbufs);
 
 	mutex_unlock(&inst->lock);
@@ -1412,9 +1416,6 @@ static const struct v4l2_file_operations vdec_fops = {
 	.unlocked_ioctl = video_ioctl2,
 	.poll = v4l2_m2m_fop_poll,
 	.mmap = v4l2_m2m_fop_mmap,
-#ifdef CONFIG_COMPAT
-	.compat_ioctl32 = v4l2_compat_ioctl32,
-#endif
 };
 
 static int vdec_probe(struct platform_device *pdev)
diff --git a/drivers/media/platform/qcom/venus/venc.c b/drivers/media/platform/qcom/venus/venc.c
index 1b7fb2d5887c..453edf966d4f 100644
--- a/drivers/media/platform/qcom/venus/venc.c
+++ b/drivers/media/platform/qcom/venus/venc.c
@@ -842,6 +842,10 @@ static int venc_init_session(struct venus_inst *inst)
 	if (ret)
 		goto deinit;
 
+	ret = venus_helper_init_codec_freq_data(inst);
+	if (ret)
+		goto deinit;
+
 	ret = venc_set_properties(inst);
 	if (ret)
 		goto deinit;
@@ -1235,9 +1239,6 @@ static const struct v4l2_file_operations venc_fops = {
 	.unlocked_ioctl = video_ioctl2,
 	.poll = v4l2_m2m_fop_poll,
 	.mmap = v4l2_m2m_fop_mmap,
-#ifdef CONFIG_COMPAT
-	.compat_ioctl32 = v4l2_compat_ioctl32,
-#endif
 };
 
 static int venc_probe(struct platform_device *pdev)
diff --git a/drivers/media/platform/rcar-vin/rcar-core.c b/drivers/media/platform/rcar-vin/rcar-core.c
index 6993484ff0f3..7440c8965d27 100644
--- a/drivers/media/platform/rcar-vin/rcar-core.c
+++ b/drivers/media/platform/rcar-vin/rcar-core.c
@@ -983,6 +983,7 @@ static const struct rvin_group_route rcar_info_r8a7795_routes[] = {
 static const struct rvin_info rcar_info_r8a7795 = {
 	.model = RCAR_GEN3,
 	.use_mc = true,
+	.nv12 = true,
 	.max_width = 4096,
 	.max_height = 4096,
 	.routes = rcar_info_r8a7795_routes,
@@ -1077,6 +1078,7 @@ static const struct rvin_group_route rcar_info_r8a7796_routes[] = {
 static const struct rvin_info rcar_info_r8a7796 = {
 	.model = RCAR_GEN3,
 	.use_mc = true,
+	.nv12 = true,
 	.max_width = 4096,
 	.max_height = 4096,
 	.routes = rcar_info_r8a7796_routes,
@@ -1121,6 +1123,7 @@ static const struct rvin_group_route rcar_info_r8a77965_routes[] = {
 static const struct rvin_info rcar_info_r8a77965 = {
 	.model = RCAR_GEN3,
 	.use_mc = true,
+	.nv12 = true,
 	.max_width = 4096,
 	.max_height = 4096,
 	.routes = rcar_info_r8a77965_routes,
@@ -1168,6 +1171,7 @@ static const struct rvin_group_route rcar_info_r8a77980_routes[] = {
 static const struct rvin_info rcar_info_r8a77980 = {
 	.model = RCAR_GEN3,
 	.use_mc = true,
+	.nv12 = true,
 	.max_width = 4096,
 	.max_height = 4096,
 	.routes = rcar_info_r8a77980_routes,
@@ -1184,6 +1188,7 @@ static const struct rvin_group_route rcar_info_r8a77990_routes[] = {
 static const struct rvin_info rcar_info_r8a77990 = {
 	.model = RCAR_GEN3,
 	.use_mc = true,
+	.nv12 = true,
 	.max_width = 4096,
 	.max_height = 4096,
 	.routes = rcar_info_r8a77990_routes,
@@ -1196,6 +1201,7 @@ static const struct rvin_group_route rcar_info_r8a77995_routes[] = {
 static const struct rvin_info rcar_info_r8a77995 = {
 	.model = RCAR_GEN3,
 	.use_mc = true,
+	.nv12 = true,
 	.max_width = 4096,
 	.max_height = 4096,
 	.routes = rcar_info_r8a77995_routes,
@@ -1207,6 +1213,10 @@ static const struct of_device_id rvin_of_id_table[] = {
 		.data = &rcar_info_r8a7796,
 	},
 	{
+		.compatible = "renesas,vin-r8a774b1",
+		.data = &rcar_info_r8a77965,
+	},
+	{
 		.compatible = "renesas,vin-r8a774c0",
 		.data = &rcar_info_r8a77990,
 	},
@@ -1282,7 +1292,6 @@ static int rcar_vin_probe(struct platform_device *pdev)
 {
 	const struct soc_device_attribute *attr;
 	struct rvin_dev *vin;
-	struct resource *mem;
 	int irq, ret;
 
 	vin = devm_kzalloc(&pdev->dev, sizeof(*vin), GFP_KERNEL);
@@ -1301,11 +1310,7 @@ static int rcar_vin_probe(struct platform_device *pdev)
 	if (attr)
 		vin->info = attr->data;
 
-	mem = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	if (mem == NULL)
-		return -EINVAL;
-
-	vin->base = devm_ioremap_resource(vin->dev, mem);
+	vin->base = devm_platform_ioremap_resource(pdev, 0);
 	if (IS_ERR(vin->base))
 		return PTR_ERR(vin->base);
 
diff --git a/drivers/media/platform/rcar-vin/rcar-csi2.c b/drivers/media/platform/rcar-vin/rcar-csi2.c
index c14af1b929df..faa9fb23a2e9 100644
--- a/drivers/media/platform/rcar-vin/rcar-csi2.c
+++ b/drivers/media/platform/rcar-vin/rcar-csi2.c
@@ -1082,6 +1082,10 @@ static const struct of_device_id rcar_csi2_of_table[] = {
 		.data = &rcar_csi2_info_r8a7796,
 	},
 	{
+		.compatible = "renesas,r8a774b1-csi2",
+		.data = &rcar_csi2_info_r8a77965,
+	},
+	{
 		.compatible = "renesas,r8a774c0-csi2",
 		.data = &rcar_csi2_info_r8a77990,
 	},
diff --git a/drivers/media/platform/rcar-vin/rcar-dma.c b/drivers/media/platform/rcar-vin/rcar-dma.c
index 3cb29b2e0b2b..cf9029efeb04 100644
--- a/drivers/media/platform/rcar-vin/rcar-dma.c
+++ b/drivers/media/platform/rcar-vin/rcar-dma.c
@@ -118,6 +118,7 @@
 #define VNDMR_ABIT		(1 << 2)
 #define VNDMR_DTMD_YCSEP	(1 << 1)
 #define VNDMR_DTMD_ARGB		(1 << 0)
+#define VNDMR_DTMD_YCSEP_420	(3 << 0)
 
 /* Video n Data Mode Register 2 bits */
 #define VNDMR2_VPS		(1 << 30)
@@ -529,12 +530,17 @@ static void rvin_set_coeff(struct rvin_dev *vin, unsigned short xs)
 
 static void rvin_crop_scale_comp_gen2(struct rvin_dev *vin)
 {
+	unsigned int crop_height;
 	u32 xs, ys;
 
 	/* Set scaling coefficient */
+	crop_height = vin->crop.height;
+	if (V4L2_FIELD_IS_INTERLACED(vin->format.field))
+		crop_height *= 2;
+
 	ys = 0;
-	if (vin->crop.height != vin->compose.height)
-		ys = (4096 * vin->crop.height) / vin->compose.height;
+	if (crop_height != vin->compose.height)
+		ys = (4096 * crop_height) / vin->compose.height;
 	rvin_write(vin, ys, VNYS_REG);
 
 	xs = 0;
@@ -557,16 +563,11 @@ static void rvin_crop_scale_comp_gen2(struct rvin_dev *vin)
 	rvin_write(vin, 0, VNSPPOC_REG);
 	rvin_write(vin, 0, VNSLPOC_REG);
 	rvin_write(vin, vin->format.width - 1, VNEPPOC_REG);
-	switch (vin->format.field) {
-	case V4L2_FIELD_INTERLACED:
-	case V4L2_FIELD_INTERLACED_TB:
-	case V4L2_FIELD_INTERLACED_BT:
+
+	if (V4L2_FIELD_IS_INTERLACED(vin->format.field))
 		rvin_write(vin, vin->format.height / 2 - 1, VNELPOC_REG);
-		break;
-	default:
+	else
 		rvin_write(vin, vin->format.height - 1, VNELPOC_REG);
-		break;
-	}
 
 	vin_dbg(vin,
 		"Pre-Clip: %ux%u@%u:%u YS: %d XS: %d Post-Clip: %ux%u@%u:%u\n",
@@ -583,21 +584,9 @@ void rvin_crop_scale_comp(struct rvin_dev *vin)
 	/* Set Start/End Pixel/Line Pre-Clip */
 	rvin_write(vin, vin->crop.left, VNSPPRC_REG);
 	rvin_write(vin, vin->crop.left + vin->crop.width - 1, VNEPPRC_REG);
+	rvin_write(vin, vin->crop.top, VNSLPRC_REG);
+	rvin_write(vin, vin->crop.top + vin->crop.height - 1, VNELPRC_REG);
 
-	switch (vin->format.field) {
-	case V4L2_FIELD_INTERLACED:
-	case V4L2_FIELD_INTERLACED_TB:
-	case V4L2_FIELD_INTERLACED_BT:
-		rvin_write(vin, vin->crop.top / 2, VNSLPRC_REG);
-		rvin_write(vin, (vin->crop.top + vin->crop.height) / 2 - 1,
-			   VNELPRC_REG);
-		break;
-	default:
-		rvin_write(vin, vin->crop.top, VNSLPRC_REG);
-		rvin_write(vin, vin->crop.top + vin->crop.height - 1,
-			   VNELPRC_REG);
-		break;
-	}
 
 	/* TODO: Add support for the UDS scaler. */
 	if (vin->info->model != RCAR_GEN3)
@@ -641,6 +630,9 @@ static int rvin_setup(struct rvin_dev *vin)
 		vnmc = VNMC_IM_ODD_EVEN;
 		progressive = true;
 		break;
+	case V4L2_FIELD_ALTERNATE:
+		vnmc = VNMC_IM_ODD_EVEN;
+		break;
 	default:
 		vnmc = VNMC_IM_ODD;
 		break;
@@ -710,11 +702,13 @@ static int rvin_setup(struct rvin_dev *vin)
 	 * Output format
 	 */
 	switch (vin->format.pixelformat) {
+	case V4L2_PIX_FMT_NV12:
 	case V4L2_PIX_FMT_NV16:
 		rvin_write(vin,
-			   ALIGN(vin->format.width * vin->format.height, 0x80),
-			   VNUVAOF_REG);
-		dmr = VNDMR_DTMD_YCSEP;
+			   ALIGN(vin->format.bytesperline * vin->format.height,
+				 0x80), VNUVAOF_REG);
+		dmr = vin->format.pixelformat == V4L2_PIX_FMT_NV12 ?
+			VNDMR_DTMD_YCSEP_420 : VNDMR_DTMD_YCSEP;
 		output_is_yuv = true;
 		break;
 	case V4L2_PIX_FMT_YUYV:
@@ -799,6 +793,18 @@ static bool rvin_capture_active(struct rvin_dev *vin)
 	return rvin_read(vin, VNMS_REG) & VNMS_CA;
 }
 
+static enum v4l2_field rvin_get_active_field(struct rvin_dev *vin, u32 vnms)
+{
+	if (vin->format.field == V4L2_FIELD_ALTERNATE) {
+		/* If FS is set it is an Even field. */
+		if (vnms & VNMS_FS)
+			return V4L2_FIELD_BOTTOM;
+		return V4L2_FIELD_TOP;
+	}
+
+	return vin->format.field;
+}
+
 static void rvin_set_slot_addr(struct rvin_dev *vin, int slot, dma_addr_t addr)
 {
 	const struct rvin_video_format *fmt;
@@ -948,7 +954,7 @@ static irqreturn_t rvin_irq(int irq, void *data)
 
 	/* Capture frame */
 	if (vin->queue_buf[slot]) {
-		vin->queue_buf[slot]->field = vin->format.field;
+		vin->queue_buf[slot]->field = rvin_get_active_field(vin, vnms);
 		vin->queue_buf[slot]->sequence = vin->sequence;
 		vin->queue_buf[slot]->vb2_buf.timestamp = ktime_get_ns();
 		vb2_buffer_done(&vin->queue_buf[slot]->vb2_buf,
@@ -1075,6 +1081,7 @@ static int rvin_mc_validate_format(struct rvin_dev *vin, struct v4l2_subdev *sd,
 		case V4L2_FIELD_TOP:
 		case V4L2_FIELD_BOTTOM:
 		case V4L2_FIELD_NONE:
+		case V4L2_FIELD_ALTERNATE:
 			break;
 		case V4L2_FIELD_INTERLACED_TB:
 		case V4L2_FIELD_INTERLACED_BT:
diff --git a/drivers/media/platform/rcar-vin/rcar-v4l2.c b/drivers/media/platform/rcar-vin/rcar-v4l2.c
index cbc1c07f0a96..9e2e63ffcc47 100644
--- a/drivers/media/platform/rcar-vin/rcar-v4l2.c
+++ b/drivers/media/platform/rcar-vin/rcar-v4l2.c
@@ -31,6 +31,10 @@
 
 static const struct rvin_video_format rvin_formats[] = {
 	{
+		.fourcc			= V4L2_PIX_FMT_NV12,
+		.bpp			= 1,
+	},
+	{
 		.fourcc			= V4L2_PIX_FMT_NV16,
 		.bpp			= 1,
 	},
@@ -72,6 +76,9 @@ const struct rvin_video_format *rvin_format_from_pixel(struct rvin_dev *vin,
 	if (vin->info->model == RCAR_M1 && pixelformat == V4L2_PIX_FMT_XBGR32)
 		return NULL;
 
+	if (pixelformat == V4L2_PIX_FMT_NV12 && !vin->info->nv12)
+		return NULL;
+
 	for (i = 0; i < ARRAY_SIZE(rvin_formats); i++)
 		if (rvin_formats[i].fourcc == pixelformat)
 			return rvin_formats + i;
@@ -90,17 +97,29 @@ static u32 rvin_format_bytesperline(struct rvin_dev *vin,
 	if (WARN_ON(!fmt))
 		return -EINVAL;
 
-	align = pix->pixelformat == V4L2_PIX_FMT_NV16 ? 0x20 : 0x10;
+	switch (pix->pixelformat) {
+	case V4L2_PIX_FMT_NV12:
+	case V4L2_PIX_FMT_NV16:
+		align = 0x20;
+		break;
+	default:
+		align = 0x10;
+		break;
+	}
 
 	return ALIGN(pix->width, align) * fmt->bpp;
 }
 
 static u32 rvin_format_sizeimage(struct v4l2_pix_format *pix)
 {
-	if (pix->pixelformat == V4L2_PIX_FMT_NV16)
+	switch (pix->pixelformat) {
+	case V4L2_PIX_FMT_NV12:
+		return pix->bytesperline * pix->height * 3 / 2;
+	case V4L2_PIX_FMT_NV16:
 		return pix->bytesperline * pix->height * 2;
-
-	return pix->bytesperline * pix->height;
+	default:
+		return pix->bytesperline * pix->height;
+	}
 }
 
 static void rvin_format_align(struct rvin_dev *vin, struct v4l2_pix_format *pix)
@@ -117,23 +136,23 @@ static void rvin_format_align(struct rvin_dev *vin, struct v4l2_pix_format *pix)
 	case V4L2_FIELD_INTERLACED_TB:
 	case V4L2_FIELD_INTERLACED_BT:
 	case V4L2_FIELD_INTERLACED:
-		break;
 	case V4L2_FIELD_ALTERNATE:
-		/*
-		 * Driver does not (yet) support outputting ALTERNATE to a
-		 * userspace. It does support outputting INTERLACED so use
-		 * the VIN hardware to combine the two fields.
-		 */
-		pix->field = V4L2_FIELD_INTERLACED;
-		pix->height *= 2;
 		break;
 	default:
 		pix->field = RVIN_DEFAULT_FIELD;
 		break;
 	}
 
-	/* HW limit width to a multiple of 32 (2^5) for NV16 else 2 (2^1) */
-	walign = vin->format.pixelformat == V4L2_PIX_FMT_NV16 ? 5 : 1;
+	/* HW limit width to a multiple of 32 (2^5) for NV12/16 else 2 (2^1) */
+	switch (vin->format.pixelformat) {
+	case V4L2_PIX_FMT_NV12:
+	case V4L2_PIX_FMT_NV16:
+		walign = 5;
+		break;
+	default:
+		walign = 1;
+		break;
+	}
 
 	/* Limit to VIN capabilities */
 	v4l_bound_align_image(&pix->width, 2, vin->info->max_width, walign,
@@ -164,22 +183,32 @@ static int rvin_reset_format(struct rvin_dev *vin)
 
 	v4l2_fill_pix_format(&vin->format, &fmt.format);
 
+	vin->src_rect.top = 0;
+	vin->src_rect.left = 0;
+	vin->src_rect.width = vin->format.width;
+	vin->src_rect.height = vin->format.height;
+
+	/*  Make use of the hardware interlacer by default. */
+	if (vin->format.field == V4L2_FIELD_ALTERNATE) {
+		vin->format.field = V4L2_FIELD_INTERLACED;
+		vin->format.height *= 2;
+	}
+
 	rvin_format_align(vin, &vin->format);
 
-	vin->source.top = 0;
-	vin->source.left = 0;
-	vin->source.width = vin->format.width;
-	vin->source.height = vin->format.height;
+	vin->crop = vin->src_rect;
 
-	vin->crop = vin->source;
-	vin->compose = vin->source;
+	vin->compose.top = 0;
+	vin->compose.left = 0;
+	vin->compose.width = vin->format.width;
+	vin->compose.height = vin->format.height;
 
 	return 0;
 }
 
 static int rvin_try_format(struct rvin_dev *vin, u32 which,
 			   struct v4l2_pix_format *pix,
-			   struct v4l2_rect *crop, struct v4l2_rect *compose)
+			   struct v4l2_rect *src_rect)
 {
 	struct v4l2_subdev *sd = vin_to_source(vin);
 	struct v4l2_subdev_pad_config *pad_cfg;
@@ -208,21 +237,15 @@ static int rvin_try_format(struct rvin_dev *vin, u32 which,
 	ret = v4l2_subdev_call(sd, pad, set_fmt, pad_cfg, &format);
 	if (ret < 0 && ret != -ENOIOCTLCMD)
 		goto done;
+	ret = 0;
 
 	v4l2_fill_pix_format(pix, &format.format);
 
-	if (crop) {
-		crop->top = 0;
-		crop->left = 0;
-		crop->width = pix->width;
-		crop->height = pix->height;
-
-		/*
-		 * If source is ALTERNATE the driver will use the VIN hardware
-		 * to INTERLACE it. The crop height then needs to be doubled.
-		 */
-		if (pix->field == V4L2_FIELD_ALTERNATE)
-			crop->height *= 2;
+	if (src_rect) {
+		src_rect->top = 0;
+		src_rect->left = 0;
+		src_rect->width = pix->width;
+		src_rect->height = pix->height;
 	}
 
 	if (field != V4L2_FIELD_ANY)
@@ -232,17 +255,10 @@ static int rvin_try_format(struct rvin_dev *vin, u32 which,
 	pix->height = height;
 
 	rvin_format_align(vin, pix);
-
-	if (compose) {
-		compose->top = 0;
-		compose->left = 0;
-		compose->width = pix->width;
-		compose->height = pix->height;
-	}
 done:
 	v4l2_subdev_free_pad_config(pad_cfg);
 
-	return 0;
+	return ret;
 }
 
 static int rvin_querycap(struct file *file, void *priv,
@@ -262,29 +278,34 @@ static int rvin_try_fmt_vid_cap(struct file *file, void *priv,
 {
 	struct rvin_dev *vin = video_drvdata(file);
 
-	return rvin_try_format(vin, V4L2_SUBDEV_FORMAT_TRY, &f->fmt.pix, NULL,
-			       NULL);
+	return rvin_try_format(vin, V4L2_SUBDEV_FORMAT_TRY, &f->fmt.pix, NULL);
 }
 
 static int rvin_s_fmt_vid_cap(struct file *file, void *priv,
 			      struct v4l2_format *f)
 {
 	struct rvin_dev *vin = video_drvdata(file);
-	struct v4l2_rect crop, compose;
+	struct v4l2_rect fmt_rect, src_rect;
 	int ret;
 
 	if (vb2_is_busy(&vin->queue))
 		return -EBUSY;
 
 	ret = rvin_try_format(vin, V4L2_SUBDEV_FORMAT_ACTIVE, &f->fmt.pix,
-			      &crop, &compose);
+			      &src_rect);
 	if (ret)
 		return ret;
 
 	vin->format = f->fmt.pix;
-	vin->crop = crop;
-	vin->compose = compose;
-	vin->source = crop;
+
+	fmt_rect.top = 0;
+	fmt_rect.left = 0;
+	fmt_rect.width = vin->format.width;
+	fmt_rect.height = vin->format.height;
+
+	v4l2_rect_map_inside(&vin->crop, &src_rect);
+	v4l2_rect_map_inside(&vin->compose, &fmt_rect);
+	vin->src_rect = src_rect;
 
 	return 0;
 }
@@ -302,12 +323,22 @@ static int rvin_g_fmt_vid_cap(struct file *file, void *priv,
 static int rvin_enum_fmt_vid_cap(struct file *file, void *priv,
 				 struct v4l2_fmtdesc *f)
 {
-	if (f->index >= ARRAY_SIZE(rvin_formats))
-		return -EINVAL;
-
-	f->pixelformat = rvin_formats[f->index].fourcc;
+	struct rvin_dev *vin = video_drvdata(file);
+	unsigned int i;
+	int matched;
+
+	matched = -1;
+	for (i = 0; i < ARRAY_SIZE(rvin_formats); i++) {
+		if (rvin_format_from_pixel(vin, rvin_formats[i].fourcc))
+			matched++;
+
+		if (matched == f->index) {
+			f->pixelformat = rvin_formats[i].fourcc;
+			return 0;
+		}
+	}
 
-	return 0;
+	return -EINVAL;
 }
 
 static int rvin_g_selection(struct file *file, void *fh,
@@ -322,8 +353,8 @@ static int rvin_g_selection(struct file *file, void *fh,
 	case V4L2_SEL_TGT_CROP_BOUNDS:
 	case V4L2_SEL_TGT_CROP_DEFAULT:
 		s->r.left = s->r.top = 0;
-		s->r.width = vin->source.width;
-		s->r.height = vin->source.height;
+		s->r.width = vin->src_rect.width;
+		s->r.height = vin->src_rect.height;
 		break;
 	case V4L2_SEL_TGT_CROP:
 		s->r = vin->crop;
@@ -365,21 +396,22 @@ static int rvin_s_selection(struct file *file, void *fh,
 	case V4L2_SEL_TGT_CROP:
 		/* Can't crop outside of source input */
 		max_rect.top = max_rect.left = 0;
-		max_rect.width = vin->source.width;
-		max_rect.height = vin->source.height;
+		max_rect.width = vin->src_rect.width;
+		max_rect.height = vin->src_rect.height;
 		v4l2_rect_map_inside(&r, &max_rect);
 
-		v4l_bound_align_image(&r.width, 6, vin->source.width, 0,
-				      &r.height, 2, vin->source.height, 0, 0);
+		v4l_bound_align_image(&r.width, 6, vin->src_rect.width, 0,
+				      &r.height, 2, vin->src_rect.height, 0, 0);
 
-		r.top  = clamp_t(s32, r.top, 0, vin->source.height - r.height);
-		r.left = clamp_t(s32, r.left, 0, vin->source.width - r.width);
+		r.top  = clamp_t(s32, r.top, 0,
+				 vin->src_rect.height - r.height);
+		r.left = clamp_t(s32, r.left, 0, vin->src_rect.width - r.width);
 
 		vin->crop = s->r = r;
 
 		vin_dbg(vin, "Cropped %dx%d@%d:%d of %dx%d\n",
 			r.width, r.height, r.left, r.top,
-			vin->source.width, vin->source.height);
+			vin->src_rect.width, vin->src_rect.height);
 		break;
 	case V4L2_SEL_TGT_COMPOSE:
 		/* Make sure compose rect fits inside output format */
diff --git a/drivers/media/platform/rcar-vin/rcar-vin.h b/drivers/media/platform/rcar-vin/rcar-vin.h
index e562c2ff21ec..a36b0824f81d 100644
--- a/drivers/media/platform/rcar-vin/rcar-vin.h
+++ b/drivers/media/platform/rcar-vin/rcar-vin.h
@@ -126,6 +126,7 @@ struct rvin_group_route {
  * struct rvin_info - Information about the particular VIN implementation
  * @model:		VIN model
  * @use_mc:		use media controller instead of controlling subdevice
+ * @nv12:		support outputing NV12 pixel format
  * @max_width:		max input width the VIN supports
  * @max_height:		max input height the VIN supports
  * @routes:		list of possible routes from the CSI-2 recivers to
@@ -134,6 +135,7 @@ struct rvin_group_route {
 struct rvin_info {
 	enum model_id model;
 	bool use_mc;
+	bool nv12;
 
 	unsigned int max_width;
 	unsigned int max_height;
@@ -176,7 +178,7 @@ struct rvin_info {
  *
  * @crop:		active cropping
  * @compose:		active composing
- * @source:		active size of the video source
+ * @src_rect:		active size of the video source
  * @std:		active video standard of the video source
  *
  * @alpha:		Alpha component to fill in for supported pixel formats
@@ -215,7 +217,7 @@ struct rvin_dev {
 
 	struct v4l2_rect crop;
 	struct v4l2_rect compose;
-	struct v4l2_rect source;
+	struct v4l2_rect src_rect;
 	v4l2_std_id std;
 
 	unsigned int alpha;
diff --git a/drivers/media/platform/rcar_drif.c b/drivers/media/platform/rcar_drif.c
index 608e5217ccd5..0f267a237b42 100644
--- a/drivers/media/platform/rcar_drif.c
+++ b/drivers/media/platform/rcar_drif.c
@@ -912,6 +912,7 @@ static int rcar_drif_g_fmt_sdr_cap(struct file *file, void *priv,
 {
 	struct rcar_drif_sdr *sdr = video_drvdata(file);
 
+	memset(f->fmt.sdr.reserved, 0, sizeof(f->fmt.sdr.reserved));
 	f->fmt.sdr.pixelformat = sdr->fmt->pixelformat;
 	f->fmt.sdr.buffersize = sdr->fmt->buffersize;
 
diff --git a/drivers/media/platform/rcar_fdp1.c b/drivers/media/platform/rcar_fdp1.c
index cb93a13e1777..97bed45360f0 100644
--- a/drivers/media/platform/rcar_fdp1.c
+++ b/drivers/media/platform/rcar_fdp1.c
@@ -2369,7 +2369,7 @@ static int fdp1_probe(struct platform_device *pdev)
 		dprintk(fdp1, "FDP1 Version R-Car H3\n");
 		break;
 	case FD1_IP_M3N:
-		dprintk(fdp1, "FDP1 Version R-Car M3N\n");
+		dprintk(fdp1, "FDP1 Version R-Car M3-N\n");
 		break;
 	case FD1_IP_E3:
 		dprintk(fdp1, "FDP1 Version R-Car E3\n");
diff --git a/drivers/media/platform/s3c-camif/camif-regs.c b/drivers/media/platform/s3c-camif/camif-regs.c
index 1a65532dc36d..e80204f5720c 100644
--- a/drivers/media/platform/s3c-camif/camif-regs.c
+++ b/drivers/media/platform/s3c-camif/camif-regs.c
@@ -553,7 +553,7 @@ void camif_hw_disable_capture(struct camif_vp *vp)
 
 void camif_hw_dump_regs(struct camif_dev *camif, const char *label)
 {
-	struct {
+	static const struct {
 		u32 offset;
 		const char * const name;
 	} registers[] = {
diff --git a/drivers/media/platform/s5p-jpeg/jpeg-core.c b/drivers/media/platform/s5p-jpeg/jpeg-core.c
index 8dbbd5f2a40a..ac2162235cef 100644
--- a/drivers/media/platform/s5p-jpeg/jpeg-core.c
+++ b/drivers/media/platform/s5p-jpeg/jpeg-core.c
@@ -1236,7 +1236,6 @@ static bool s5p_jpeg_parse_hdr(struct s5p_jpeg_q_data *result,
 	}
 	result->sof = sof;
 	result->sof_len = sof_len;
-	result->components = components;
 
 	return true;
 }
diff --git a/drivers/media/platform/s5p-jpeg/jpeg-core.h b/drivers/media/platform/s5p-jpeg/jpeg-core.h
index 3bc52f83f5bc..4407fe775afa 100644
--- a/drivers/media/platform/s5p-jpeg/jpeg-core.h
+++ b/drivers/media/platform/s5p-jpeg/jpeg-core.h
@@ -190,7 +190,6 @@ struct s5p_jpeg_marker {
  * @dqt:	DQT markers' positions relative to the buffer beginning
  * @sof:	SOF0 marker's position relative to the buffer beginning
  * @sof_len:	SOF0 marker's payload length (without length field itself)
- * @components:	number of image components
  * @size:	image buffer size in bytes
  */
 struct s5p_jpeg_q_data {
@@ -202,7 +201,6 @@ struct s5p_jpeg_q_data {
 	struct s5p_jpeg_marker	dqt;
 	u32			sof;
 	u32			sof_len;
-	u32			components;
 	u32			size;
 };
 
diff --git a/drivers/media/platform/seco-cec/seco-cec.c b/drivers/media/platform/seco-cec/seco-cec.c
index 9cd60fe1867c..a86b6e8f9196 100644
--- a/drivers/media/platform/seco-cec/seco-cec.c
+++ b/drivers/media/platform/seco-cec/seco-cec.c
@@ -675,6 +675,7 @@ err_notifier:
 err_delete_adapter:
 	cec_delete_adapter(secocec->cec_adap);
 err:
+	release_region(BRA_SMB_BASE_ADDR, 7);
 	dev_err(dev, "%s device probe failed\n", dev_name(dev));
 
 	return ret;
diff --git a/drivers/media/platform/sti/bdisp/bdisp-v4l2.c b/drivers/media/platform/sti/bdisp/bdisp-v4l2.c
index e90f1ba30574..675b5f2b4c2e 100644
--- a/drivers/media/platform/sti/bdisp/bdisp-v4l2.c
+++ b/drivers/media/platform/sti/bdisp/bdisp-v4l2.c
@@ -651,8 +651,7 @@ static int bdisp_release(struct file *file)
 
 	dev_dbg(bdisp->dev, "%s\n", __func__);
 
-	if (mutex_lock_interruptible(&bdisp->lock))
-		return -ERESTARTSYS;
+	mutex_lock(&bdisp->lock);
 
 	v4l2_m2m_ctx_release(ctx->fh.m2m_ctx);
 
diff --git a/drivers/media/platform/sunxi/Makefile b/drivers/media/platform/sunxi/Makefile
index a05127529006..3878cb4efdc2 100644
--- a/drivers/media/platform/sunxi/Makefile
+++ b/drivers/media/platform/sunxi/Makefile
@@ -1,2 +1,3 @@
 obj-y		+= sun4i-csi/
 obj-y		+= sun6i-csi/
+obj-y		+= sun8i-di/
diff --git a/drivers/media/platform/sunxi/sun8i-di/Makefile b/drivers/media/platform/sunxi/sun8i-di/Makefile
new file mode 100644
index 000000000000..109f7e5442b7
--- /dev/null
+++ b/drivers/media/platform/sunxi/sun8i-di/Makefile
@@ -0,0 +1,2 @@
+# SPDX-License-Identifier: GPL-2.0
+obj-$(CONFIG_VIDEO_SUN8I_DEINTERLACE) += sun8i-di.o
diff --git a/drivers/media/platform/sunxi/sun8i-di/sun8i-di.c b/drivers/media/platform/sunxi/sun8i-di/sun8i-di.c
new file mode 100644
index 000000000000..aaa1dc159ac2
--- /dev/null
+++ b/drivers/media/platform/sunxi/sun8i-di/sun8i-di.c
@@ -0,0 +1,1028 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Allwinner sun8i deinterlacer with scaler driver
+ *
+ * Copyright (C) 2019 Jernej Skrabec <jernej.skrabec@siol.net>
+ *
+ * Based on vim2m driver.
+ */
+
+#include <linux/clk.h>
+#include <linux/interrupt.h>
+#include <linux/io.h>
+#include <linux/iopoll.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/of_device.h>
+#include <linux/pm_runtime.h>
+#include <linux/reset.h>
+
+#include <media/v4l2-device.h>
+#include <media/v4l2-ioctl.h>
+#include <media/v4l2-mem2mem.h>
+
+#include "sun8i-di.h"
+
+#define FLAG_SIZE (DEINTERLACE_MAX_WIDTH * DEINTERLACE_MAX_HEIGHT / 4)
+
+static u32 deinterlace_formats[] = {
+	V4L2_PIX_FMT_NV12,
+	V4L2_PIX_FMT_NV21,
+};
+
+static inline u32 deinterlace_read(struct deinterlace_dev *dev, u32 reg)
+{
+	return readl(dev->base + reg);
+}
+
+static inline void deinterlace_write(struct deinterlace_dev *dev,
+				     u32 reg, u32 value)
+{
+	writel(value, dev->base + reg);
+}
+
+static inline void deinterlace_set_bits(struct deinterlace_dev *dev,
+					u32 reg, u32 bits)
+{
+	writel(readl(dev->base + reg) | bits, dev->base + reg);
+}
+
+static inline void deinterlace_clr_set_bits(struct deinterlace_dev *dev,
+					    u32 reg, u32 clr, u32 set)
+{
+	u32 val = readl(dev->base + reg);
+
+	val &= ~clr;
+	val |= set;
+
+	writel(val, dev->base + reg);
+}
+
+static void deinterlace_device_run(void *priv)
+{
+	struct deinterlace_ctx *ctx = priv;
+	struct deinterlace_dev *dev = ctx->dev;
+	u32 size, stride, width, height, val;
+	struct vb2_v4l2_buffer *src, *dst;
+	unsigned int hstep, vstep;
+	dma_addr_t addr;
+
+	src = v4l2_m2m_next_src_buf(ctx->fh.m2m_ctx);
+	dst = v4l2_m2m_next_dst_buf(ctx->fh.m2m_ctx);
+
+	v4l2_m2m_buf_copy_metadata(src, dst, true);
+
+	deinterlace_write(dev, DEINTERLACE_MOD_ENABLE,
+			  DEINTERLACE_MOD_ENABLE_EN);
+
+	if (ctx->field) {
+		deinterlace_write(dev, DEINTERLACE_TILE_FLAG0,
+				  ctx->flag1_buf_dma);
+		deinterlace_write(dev, DEINTERLACE_TILE_FLAG1,
+				  ctx->flag2_buf_dma);
+	} else {
+		deinterlace_write(dev, DEINTERLACE_TILE_FLAG0,
+				  ctx->flag2_buf_dma);
+		deinterlace_write(dev, DEINTERLACE_TILE_FLAG1,
+				  ctx->flag1_buf_dma);
+	}
+	deinterlace_write(dev, DEINTERLACE_FLAG_LINE_STRIDE, 0x200);
+
+	width = ctx->src_fmt.width;
+	height = ctx->src_fmt.height;
+	stride = ctx->src_fmt.bytesperline;
+	size = stride * height;
+
+	addr = vb2_dma_contig_plane_dma_addr(&src->vb2_buf, 0);
+	deinterlace_write(dev, DEINTERLACE_BUF_ADDR0, addr);
+	deinterlace_write(dev, DEINTERLACE_BUF_ADDR1, addr + size);
+	deinterlace_write(dev, DEINTERLACE_BUF_ADDR2, 0);
+
+	deinterlace_write(dev, DEINTERLACE_LINE_STRIDE0, stride);
+	deinterlace_write(dev, DEINTERLACE_LINE_STRIDE1, stride);
+
+	deinterlace_write(dev, DEINTERLACE_CH0_IN_SIZE,
+			  DEINTERLACE_SIZE(width, height));
+	deinterlace_write(dev, DEINTERLACE_CH1_IN_SIZE,
+			  DEINTERLACE_SIZE(width / 2, height / 2));
+
+	val = DEINTERLACE_IN_FMT_FMT(DEINTERLACE_IN_FMT_YUV420) |
+	      DEINTERLACE_IN_FMT_MOD(DEINTERLACE_MODE_UV_COMBINED);
+	switch (ctx->src_fmt.pixelformat) {
+	case V4L2_PIX_FMT_NV12:
+		val |= DEINTERLACE_IN_FMT_PS(DEINTERLACE_PS_UVUV);
+		break;
+	case V4L2_PIX_FMT_NV21:
+		val |= DEINTERLACE_IN_FMT_PS(DEINTERLACE_PS_VUVU);
+		break;
+	}
+	deinterlace_write(dev, DEINTERLACE_IN_FMT, val);
+
+	if (ctx->prev)
+		addr = vb2_dma_contig_plane_dma_addr(&ctx->prev->vb2_buf, 0);
+
+	deinterlace_write(dev, DEINTERLACE_PRELUMA, addr);
+	deinterlace_write(dev, DEINTERLACE_PRECHROMA, addr + size);
+
+	val = DEINTERLACE_OUT_FMT_FMT(DEINTERLACE_OUT_FMT_YUV420SP);
+	switch (ctx->src_fmt.pixelformat) {
+	case V4L2_PIX_FMT_NV12:
+		val |= DEINTERLACE_OUT_FMT_PS(DEINTERLACE_PS_UVUV);
+		break;
+	case V4L2_PIX_FMT_NV21:
+		val |= DEINTERLACE_OUT_FMT_PS(DEINTERLACE_PS_VUVU);
+		break;
+	}
+	deinterlace_write(dev, DEINTERLACE_OUT_FMT, val);
+
+	width = ctx->dst_fmt.width;
+	height = ctx->dst_fmt.height;
+	stride = ctx->dst_fmt.bytesperline;
+	size = stride * height;
+
+	deinterlace_write(dev, DEINTERLACE_CH0_OUT_SIZE,
+			  DEINTERLACE_SIZE(width, height));
+	deinterlace_write(dev, DEINTERLACE_CH1_OUT_SIZE,
+			  DEINTERLACE_SIZE(width / 2, height / 2));
+
+	deinterlace_write(dev, DEINTERLACE_WB_LINE_STRIDE0, stride);
+	deinterlace_write(dev, DEINTERLACE_WB_LINE_STRIDE1, stride);
+
+	addr = vb2_dma_contig_plane_dma_addr(&dst->vb2_buf, 0);
+	deinterlace_write(dev, DEINTERLACE_WB_ADDR0, addr);
+	deinterlace_write(dev, DEINTERLACE_WB_ADDR1, addr + size);
+	deinterlace_write(dev, DEINTERLACE_WB_ADDR2, 0);
+
+	hstep = (ctx->src_fmt.width << 16) / ctx->dst_fmt.width;
+	vstep = (ctx->src_fmt.height << 16) / ctx->dst_fmt.height;
+	deinterlace_write(dev, DEINTERLACE_CH0_HORZ_FACT, hstep);
+	deinterlace_write(dev, DEINTERLACE_CH0_VERT_FACT, vstep);
+	deinterlace_write(dev, DEINTERLACE_CH1_HORZ_FACT, hstep);
+	deinterlace_write(dev, DEINTERLACE_CH1_VERT_FACT, vstep);
+
+	deinterlace_clr_set_bits(dev, DEINTERLACE_FIELD_CTRL,
+				 DEINTERLACE_FIELD_CTRL_FIELD_CNT_MSK,
+				 DEINTERLACE_FIELD_CTRL_FIELD_CNT(ctx->field));
+
+	deinterlace_set_bits(dev, DEINTERLACE_FRM_CTRL,
+			     DEINTERLACE_FRM_CTRL_START);
+
+	deinterlace_set_bits(dev, DEINTERLACE_FRM_CTRL,
+			     DEINTERLACE_FRM_CTRL_REG_READY);
+
+	deinterlace_set_bits(dev, DEINTERLACE_INT_ENABLE,
+			     DEINTERLACE_INT_ENABLE_WB_EN);
+
+	deinterlace_set_bits(dev, DEINTERLACE_FRM_CTRL,
+			     DEINTERLACE_FRM_CTRL_WB_EN);
+}
+
+static int deinterlace_job_ready(void *priv)
+{
+	struct deinterlace_ctx *ctx = priv;
+
+	return v4l2_m2m_num_src_bufs_ready(ctx->fh.m2m_ctx) >= 1 &&
+	       v4l2_m2m_num_dst_bufs_ready(ctx->fh.m2m_ctx) >= 2;
+}
+
+static void deinterlace_job_abort(void *priv)
+{
+	struct deinterlace_ctx *ctx = priv;
+
+	/* Will cancel the transaction in the next interrupt handler */
+	ctx->aborting = 1;
+}
+
+static irqreturn_t deinterlace_irq(int irq, void *data)
+{
+	struct deinterlace_dev *dev = data;
+	struct vb2_v4l2_buffer *src, *dst;
+	enum vb2_buffer_state state;
+	struct deinterlace_ctx *ctx;
+	unsigned int val;
+
+	ctx = v4l2_m2m_get_curr_priv(dev->m2m_dev);
+	if (!ctx) {
+		v4l2_err(&dev->v4l2_dev,
+			 "Instance released before the end of transaction\n");
+		return IRQ_NONE;
+	}
+
+	val = deinterlace_read(dev, DEINTERLACE_INT_STATUS);
+	if (!(val & DEINTERLACE_INT_STATUS_WRITEBACK))
+		return IRQ_NONE;
+
+	deinterlace_write(dev, DEINTERLACE_INT_ENABLE, 0);
+	deinterlace_set_bits(dev, DEINTERLACE_INT_STATUS,
+			     DEINTERLACE_INT_STATUS_WRITEBACK);
+	deinterlace_write(dev, DEINTERLACE_MOD_ENABLE, 0);
+	deinterlace_clr_set_bits(dev, DEINTERLACE_FRM_CTRL,
+				 DEINTERLACE_FRM_CTRL_START, 0);
+
+	val = deinterlace_read(dev, DEINTERLACE_STATUS);
+	if (val & DEINTERLACE_STATUS_WB_ERROR)
+		state = VB2_BUF_STATE_ERROR;
+	else
+		state = VB2_BUF_STATE_DONE;
+
+	dst = v4l2_m2m_dst_buf_remove(ctx->fh.m2m_ctx);
+	v4l2_m2m_buf_done(dst, state);
+
+	if (ctx->field != ctx->first_field || ctx->aborting) {
+		ctx->field = ctx->first_field;
+
+		src = v4l2_m2m_src_buf_remove(ctx->fh.m2m_ctx);
+		if (ctx->prev)
+			v4l2_m2m_buf_done(ctx->prev, state);
+		ctx->prev = src;
+
+		v4l2_m2m_job_finish(ctx->dev->m2m_dev, ctx->fh.m2m_ctx);
+	} else {
+		ctx->field = !ctx->first_field;
+		deinterlace_device_run(ctx);
+	}
+
+	return IRQ_HANDLED;
+}
+
+static void deinterlace_init(struct deinterlace_dev *dev)
+{
+	u32 val;
+	int i;
+
+	deinterlace_write(dev, DEINTERLACE_BYPASS,
+			  DEINTERLACE_BYPASS_CSC);
+	deinterlace_write(dev, DEINTERLACE_WB_LINE_STRIDE_CTRL,
+			  DEINTERLACE_WB_LINE_STRIDE_CTRL_EN);
+	deinterlace_set_bits(dev, DEINTERLACE_FRM_CTRL,
+			     DEINTERLACE_FRM_CTRL_OUT_CTRL);
+	deinterlace_write(dev, DEINTERLACE_AGTH_SEL,
+			  DEINTERLACE_AGTH_SEL_LINEBUF);
+
+	val = DEINTERLACE_CTRL_EN |
+	      DEINTERLACE_CTRL_MODE_MIXED |
+	      DEINTERLACE_CTRL_DIAG_INTP_EN |
+	      DEINTERLACE_CTRL_TEMP_DIFF_EN;
+	deinterlace_write(dev, DEINTERLACE_CTRL, val);
+
+	deinterlace_clr_set_bits(dev, DEINTERLACE_LUMA_TH,
+				 DEINTERLACE_LUMA_TH_MIN_LUMA_MSK,
+				 DEINTERLACE_LUMA_TH_MIN_LUMA(4));
+
+	deinterlace_clr_set_bits(dev, DEINTERLACE_SPAT_COMP,
+				 DEINTERLACE_SPAT_COMP_TH2_MSK,
+				 DEINTERLACE_SPAT_COMP_TH2(5));
+
+	deinterlace_clr_set_bits(dev, DEINTERLACE_TEMP_DIFF,
+				 DEINTERLACE_TEMP_DIFF_AMBIGUITY_TH_MSK,
+				 DEINTERLACE_TEMP_DIFF_AMBIGUITY_TH(5));
+
+	val = DEINTERLACE_DIAG_INTP_TH0(60) |
+	      DEINTERLACE_DIAG_INTP_TH1(0) |
+	      DEINTERLACE_DIAG_INTP_TH3(30);
+	deinterlace_write(dev, DEINTERLACE_DIAG_INTP, val);
+
+	deinterlace_clr_set_bits(dev, DEINTERLACE_CHROMA_DIFF,
+				 DEINTERLACE_CHROMA_DIFF_TH_MSK,
+				 DEINTERLACE_CHROMA_DIFF_TH(5));
+
+	/* neutral filter coefficients */
+	deinterlace_set_bits(dev, DEINTERLACE_FRM_CTRL,
+			     DEINTERLACE_FRM_CTRL_COEF_ACCESS);
+	readl_poll_timeout(dev->base + DEINTERLACE_STATUS, val,
+			   val & DEINTERLACE_STATUS_COEF_STATUS, 2, 40);
+
+	for (i = 0; i < 32; i++) {
+		deinterlace_write(dev, DEINTERLACE_CH0_HORZ_COEF0 + i * 4,
+				  DEINTERLACE_IDENTITY_COEF);
+		deinterlace_write(dev, DEINTERLACE_CH0_VERT_COEF + i * 4,
+				  DEINTERLACE_IDENTITY_COEF);
+		deinterlace_write(dev, DEINTERLACE_CH1_HORZ_COEF0 + i * 4,
+				  DEINTERLACE_IDENTITY_COEF);
+		deinterlace_write(dev, DEINTERLACE_CH1_VERT_COEF + i * 4,
+				  DEINTERLACE_IDENTITY_COEF);
+	}
+
+	deinterlace_clr_set_bits(dev, DEINTERLACE_FRM_CTRL,
+				 DEINTERLACE_FRM_CTRL_COEF_ACCESS, 0);
+}
+
+static inline struct deinterlace_ctx *deinterlace_file2ctx(struct file *file)
+{
+	return container_of(file->private_data, struct deinterlace_ctx, fh);
+}
+
+static bool deinterlace_check_format(u32 pixelformat)
+{
+	unsigned int i;
+
+	for (i = 0; i < ARRAY_SIZE(deinterlace_formats); i++)
+		if (deinterlace_formats[i] == pixelformat)
+			return true;
+
+	return false;
+}
+
+static void deinterlace_prepare_format(struct v4l2_pix_format *pix_fmt)
+{
+	unsigned int height = pix_fmt->height;
+	unsigned int width = pix_fmt->width;
+	unsigned int bytesperline;
+	unsigned int sizeimage;
+
+	width = clamp(width, DEINTERLACE_MIN_WIDTH,
+		      DEINTERLACE_MAX_WIDTH);
+	height = clamp(height, DEINTERLACE_MIN_HEIGHT,
+		       DEINTERLACE_MAX_HEIGHT);
+
+	bytesperline = ALIGN(width, 2);
+	/* luma */
+	sizeimage = bytesperline * height;
+	/* chroma */
+	sizeimage += bytesperline * height / 2;
+
+	pix_fmt->width = width;
+	pix_fmt->height = height;
+	pix_fmt->bytesperline = bytesperline;
+	pix_fmt->sizeimage = sizeimage;
+}
+
+static int deinterlace_querycap(struct file *file, void *priv,
+				struct v4l2_capability *cap)
+{
+	strscpy(cap->driver, DEINTERLACE_NAME, sizeof(cap->driver));
+	strscpy(cap->card, DEINTERLACE_NAME, sizeof(cap->card));
+	snprintf(cap->bus_info, sizeof(cap->bus_info),
+		 "platform:%s", DEINTERLACE_NAME);
+
+	return 0;
+}
+
+static int deinterlace_enum_fmt(struct file *file, void *priv,
+				struct v4l2_fmtdesc *f)
+{
+	if (f->index < ARRAY_SIZE(deinterlace_formats)) {
+		f->pixelformat = deinterlace_formats[f->index];
+
+		return 0;
+	}
+
+	return -EINVAL;
+}
+
+static int deinterlace_enum_framesizes(struct file *file, void *priv,
+				       struct v4l2_frmsizeenum *fsize)
+{
+	if (fsize->index != 0)
+		return -EINVAL;
+
+	if (!deinterlace_check_format(fsize->pixel_format))
+		return -EINVAL;
+
+	fsize->type = V4L2_FRMSIZE_TYPE_STEPWISE;
+	fsize->stepwise.min_width = DEINTERLACE_MIN_WIDTH;
+	fsize->stepwise.min_height = DEINTERLACE_MIN_HEIGHT;
+	fsize->stepwise.max_width = DEINTERLACE_MAX_WIDTH;
+	fsize->stepwise.max_height = DEINTERLACE_MAX_HEIGHT;
+	fsize->stepwise.step_width = 2;
+	fsize->stepwise.step_height = 1;
+
+	return 0;
+}
+
+static int deinterlace_g_fmt_vid_cap(struct file *file, void *priv,
+				     struct v4l2_format *f)
+{
+	struct deinterlace_ctx *ctx = deinterlace_file2ctx(file);
+
+	f->fmt.pix = ctx->dst_fmt;
+
+	return 0;
+}
+
+static int deinterlace_g_fmt_vid_out(struct file *file, void *priv,
+				     struct v4l2_format *f)
+{
+	struct deinterlace_ctx *ctx = deinterlace_file2ctx(file);
+
+	f->fmt.pix = ctx->src_fmt;
+
+	return 0;
+}
+
+static int deinterlace_try_fmt_vid_cap(struct file *file, void *priv,
+				       struct v4l2_format *f)
+{
+	if (!deinterlace_check_format(f->fmt.pix.pixelformat))
+		f->fmt.pix.pixelformat = deinterlace_formats[0];
+
+	if (f->fmt.pix.field != V4L2_FIELD_NONE)
+		f->fmt.pix.field = V4L2_FIELD_NONE;
+
+	deinterlace_prepare_format(&f->fmt.pix);
+
+	return 0;
+}
+
+static int deinterlace_try_fmt_vid_out(struct file *file, void *priv,
+				       struct v4l2_format *f)
+{
+	if (!deinterlace_check_format(f->fmt.pix.pixelformat))
+		f->fmt.pix.pixelformat = deinterlace_formats[0];
+
+	if (f->fmt.pix.field != V4L2_FIELD_INTERLACED_TB &&
+	    f->fmt.pix.field != V4L2_FIELD_INTERLACED_BT &&
+	    f->fmt.pix.field != V4L2_FIELD_INTERLACED)
+		f->fmt.pix.field = V4L2_FIELD_INTERLACED;
+
+	deinterlace_prepare_format(&f->fmt.pix);
+
+	return 0;
+}
+
+static int deinterlace_s_fmt_vid_cap(struct file *file, void *priv,
+				     struct v4l2_format *f)
+{
+	struct deinterlace_ctx *ctx = deinterlace_file2ctx(file);
+	struct vb2_queue *vq;
+	int ret;
+
+	ret = deinterlace_try_fmt_vid_cap(file, priv, f);
+	if (ret)
+		return ret;
+
+	vq = v4l2_m2m_get_vq(ctx->fh.m2m_ctx, f->type);
+	if (vb2_is_busy(vq))
+		return -EBUSY;
+
+	ctx->dst_fmt = f->fmt.pix;
+
+	return 0;
+}
+
+static int deinterlace_s_fmt_vid_out(struct file *file, void *priv,
+				     struct v4l2_format *f)
+{
+	struct deinterlace_ctx *ctx = deinterlace_file2ctx(file);
+	struct vb2_queue *vq;
+	int ret;
+
+	ret = deinterlace_try_fmt_vid_out(file, priv, f);
+	if (ret)
+		return ret;
+
+	vq = v4l2_m2m_get_vq(ctx->fh.m2m_ctx, f->type);
+	if (vb2_is_busy(vq))
+		return -EBUSY;
+
+	ctx->src_fmt = f->fmt.pix;
+
+	/* Propagate colorspace information to capture. */
+	ctx->dst_fmt.colorspace = f->fmt.pix.colorspace;
+	ctx->dst_fmt.xfer_func = f->fmt.pix.xfer_func;
+	ctx->dst_fmt.ycbcr_enc = f->fmt.pix.ycbcr_enc;
+	ctx->dst_fmt.quantization = f->fmt.pix.quantization;
+
+	return 0;
+}
+
+static const struct v4l2_ioctl_ops deinterlace_ioctl_ops = {
+	.vidioc_querycap		= deinterlace_querycap,
+
+	.vidioc_enum_framesizes		= deinterlace_enum_framesizes,
+
+	.vidioc_enum_fmt_vid_cap	= deinterlace_enum_fmt,
+	.vidioc_g_fmt_vid_cap		= deinterlace_g_fmt_vid_cap,
+	.vidioc_try_fmt_vid_cap		= deinterlace_try_fmt_vid_cap,
+	.vidioc_s_fmt_vid_cap		= deinterlace_s_fmt_vid_cap,
+
+	.vidioc_enum_fmt_vid_out	= deinterlace_enum_fmt,
+	.vidioc_g_fmt_vid_out		= deinterlace_g_fmt_vid_out,
+	.vidioc_try_fmt_vid_out		= deinterlace_try_fmt_vid_out,
+	.vidioc_s_fmt_vid_out		= deinterlace_s_fmt_vid_out,
+
+	.vidioc_reqbufs			= v4l2_m2m_ioctl_reqbufs,
+	.vidioc_querybuf		= v4l2_m2m_ioctl_querybuf,
+	.vidioc_qbuf			= v4l2_m2m_ioctl_qbuf,
+	.vidioc_dqbuf			= v4l2_m2m_ioctl_dqbuf,
+	.vidioc_prepare_buf		= v4l2_m2m_ioctl_prepare_buf,
+	.vidioc_create_bufs		= v4l2_m2m_ioctl_create_bufs,
+	.vidioc_expbuf			= v4l2_m2m_ioctl_expbuf,
+
+	.vidioc_streamon		= v4l2_m2m_ioctl_streamon,
+	.vidioc_streamoff		= v4l2_m2m_ioctl_streamoff,
+};
+
+static int deinterlace_queue_setup(struct vb2_queue *vq, unsigned int *nbuffers,
+				   unsigned int *nplanes, unsigned int sizes[],
+				   struct device *alloc_devs[])
+{
+	struct deinterlace_ctx *ctx = vb2_get_drv_priv(vq);
+	struct v4l2_pix_format *pix_fmt;
+
+	if (V4L2_TYPE_IS_OUTPUT(vq->type))
+		pix_fmt = &ctx->src_fmt;
+	else
+		pix_fmt = &ctx->dst_fmt;
+
+	if (*nplanes) {
+		if (sizes[0] < pix_fmt->sizeimage)
+			return -EINVAL;
+	} else {
+		sizes[0] = pix_fmt->sizeimage;
+		*nplanes = 1;
+	}
+
+	return 0;
+}
+
+static int deinterlace_buf_prepare(struct vb2_buffer *vb)
+{
+	struct vb2_queue *vq = vb->vb2_queue;
+	struct deinterlace_ctx *ctx = vb2_get_drv_priv(vq);
+	struct v4l2_pix_format *pix_fmt;
+
+	if (V4L2_TYPE_IS_OUTPUT(vq->type))
+		pix_fmt = &ctx->src_fmt;
+	else
+		pix_fmt = &ctx->dst_fmt;
+
+	if (vb2_plane_size(vb, 0) < pix_fmt->sizeimage)
+		return -EINVAL;
+
+	vb2_set_plane_payload(vb, 0, pix_fmt->sizeimage);
+
+	return 0;
+}
+
+static void deinterlace_buf_queue(struct vb2_buffer *vb)
+{
+	struct vb2_v4l2_buffer *vbuf = to_vb2_v4l2_buffer(vb);
+	struct deinterlace_ctx *ctx = vb2_get_drv_priv(vb->vb2_queue);
+
+	v4l2_m2m_buf_queue(ctx->fh.m2m_ctx, vbuf);
+}
+
+static void deinterlace_queue_cleanup(struct vb2_queue *vq, u32 state)
+{
+	struct deinterlace_ctx *ctx = vb2_get_drv_priv(vq);
+	struct vb2_v4l2_buffer *vbuf;
+
+	do {
+		if (V4L2_TYPE_IS_OUTPUT(vq->type))
+			vbuf = v4l2_m2m_src_buf_remove(ctx->fh.m2m_ctx);
+		else
+			vbuf = v4l2_m2m_dst_buf_remove(ctx->fh.m2m_ctx);
+
+		if (vbuf)
+			v4l2_m2m_buf_done(vbuf, state);
+	} while (vbuf);
+
+	if (V4L2_TYPE_IS_OUTPUT(vq->type) && ctx->prev)
+		v4l2_m2m_buf_done(ctx->prev, state);
+}
+
+static int deinterlace_start_streaming(struct vb2_queue *vq, unsigned int count)
+{
+	struct deinterlace_ctx *ctx = vb2_get_drv_priv(vq);
+	struct device *dev = ctx->dev->dev;
+	int ret;
+
+	if (V4L2_TYPE_IS_OUTPUT(vq->type)) {
+		ret = pm_runtime_get_sync(dev);
+		if (ret < 0) {
+			dev_err(dev, "Failed to enable module\n");
+
+			goto err_runtime_get;
+		}
+
+		ctx->first_field =
+			ctx->src_fmt.field == V4L2_FIELD_INTERLACED_BT;
+		ctx->field = ctx->first_field;
+
+		ctx->prev = NULL;
+		ctx->aborting = 0;
+
+		ctx->flag1_buf = dma_alloc_coherent(dev, FLAG_SIZE,
+						    &ctx->flag1_buf_dma,
+						    GFP_KERNEL);
+		if (!ctx->flag1_buf) {
+			ret = -ENOMEM;
+
+			goto err_no_mem1;
+		}
+
+		ctx->flag2_buf = dma_alloc_coherent(dev, FLAG_SIZE,
+						    &ctx->flag2_buf_dma,
+						    GFP_KERNEL);
+		if (!ctx->flag2_buf) {
+			ret = -ENOMEM;
+
+			goto err_no_mem2;
+		}
+	}
+
+	return 0;
+
+err_no_mem2:
+	dma_free_coherent(dev, FLAG_SIZE, ctx->flag1_buf,
+			  ctx->flag1_buf_dma);
+err_no_mem1:
+	pm_runtime_put(dev);
+err_runtime_get:
+	deinterlace_queue_cleanup(vq, VB2_BUF_STATE_QUEUED);
+
+	return ret;
+}
+
+static void deinterlace_stop_streaming(struct vb2_queue *vq)
+{
+	struct deinterlace_ctx *ctx = vb2_get_drv_priv(vq);
+
+	if (V4L2_TYPE_IS_OUTPUT(vq->type)) {
+		struct device *dev = ctx->dev->dev;
+
+		dma_free_coherent(dev, FLAG_SIZE, ctx->flag1_buf,
+				  ctx->flag1_buf_dma);
+		dma_free_coherent(dev, FLAG_SIZE, ctx->flag2_buf,
+				  ctx->flag2_buf_dma);
+
+		pm_runtime_put(dev);
+	}
+
+	deinterlace_queue_cleanup(vq, VB2_BUF_STATE_ERROR);
+}
+
+static const struct vb2_ops deinterlace_qops = {
+	.queue_setup		= deinterlace_queue_setup,
+	.buf_prepare		= deinterlace_buf_prepare,
+	.buf_queue		= deinterlace_buf_queue,
+	.start_streaming	= deinterlace_start_streaming,
+	.stop_streaming		= deinterlace_stop_streaming,
+	.wait_prepare		= vb2_ops_wait_prepare,
+	.wait_finish		= vb2_ops_wait_finish,
+};
+
+static int deinterlace_queue_init(void *priv, struct vb2_queue *src_vq,
+				  struct vb2_queue *dst_vq)
+{
+	struct deinterlace_ctx *ctx = priv;
+	int ret;
+
+	src_vq->type = V4L2_BUF_TYPE_VIDEO_OUTPUT;
+	src_vq->io_modes = VB2_MMAP | VB2_DMABUF;
+	src_vq->drv_priv = ctx;
+	src_vq->buf_struct_size = sizeof(struct v4l2_m2m_buffer);
+	src_vq->min_buffers_needed = 1;
+	src_vq->ops = &deinterlace_qops;
+	src_vq->mem_ops = &vb2_dma_contig_memops;
+	src_vq->timestamp_flags = V4L2_BUF_FLAG_TIMESTAMP_COPY;
+	src_vq->lock = &ctx->dev->dev_mutex;
+	src_vq->dev = ctx->dev->dev;
+
+	ret = vb2_queue_init(src_vq);
+	if (ret)
+		return ret;
+
+	dst_vq->type = V4L2_BUF_TYPE_VIDEO_CAPTURE;
+	dst_vq->io_modes = VB2_MMAP | VB2_DMABUF;
+	dst_vq->drv_priv = ctx;
+	dst_vq->buf_struct_size = sizeof(struct v4l2_m2m_buffer);
+	dst_vq->min_buffers_needed = 2;
+	dst_vq->ops = &deinterlace_qops;
+	dst_vq->mem_ops = &vb2_dma_contig_memops;
+	dst_vq->timestamp_flags = V4L2_BUF_FLAG_TIMESTAMP_COPY;
+	dst_vq->lock = &ctx->dev->dev_mutex;
+	dst_vq->dev = ctx->dev->dev;
+
+	ret = vb2_queue_init(dst_vq);
+	if (ret)
+		return ret;
+
+	return 0;
+}
+
+static int deinterlace_open(struct file *file)
+{
+	struct deinterlace_dev *dev = video_drvdata(file);
+	struct deinterlace_ctx *ctx = NULL;
+	int ret;
+
+	if (mutex_lock_interruptible(&dev->dev_mutex))
+		return -ERESTARTSYS;
+
+	ctx = kzalloc(sizeof(*ctx), GFP_KERNEL);
+	if (!ctx) {
+		mutex_unlock(&dev->dev_mutex);
+		return -ENOMEM;
+	}
+
+	/* default output format */
+	ctx->src_fmt.pixelformat = deinterlace_formats[0];
+	ctx->src_fmt.field = V4L2_FIELD_INTERLACED;
+	ctx->src_fmt.width = 640;
+	ctx->src_fmt.height = 480;
+	deinterlace_prepare_format(&ctx->src_fmt);
+
+	/* default capture format */
+	ctx->dst_fmt.pixelformat = deinterlace_formats[0];
+	ctx->dst_fmt.field = V4L2_FIELD_NONE;
+	ctx->dst_fmt.width = 640;
+	ctx->dst_fmt.height = 480;
+	deinterlace_prepare_format(&ctx->dst_fmt);
+
+	v4l2_fh_init(&ctx->fh, video_devdata(file));
+	file->private_data = &ctx->fh;
+	ctx->dev = dev;
+
+	ctx->fh.m2m_ctx = v4l2_m2m_ctx_init(dev->m2m_dev, ctx,
+					    &deinterlace_queue_init);
+	if (IS_ERR(ctx->fh.m2m_ctx)) {
+		ret = PTR_ERR(ctx->fh.m2m_ctx);
+		goto err_free;
+	}
+
+	v4l2_fh_add(&ctx->fh);
+
+	mutex_unlock(&dev->dev_mutex);
+
+	return 0;
+
+err_free:
+	kfree(ctx);
+	mutex_unlock(&dev->dev_mutex);
+
+	return ret;
+}
+
+static int deinterlace_release(struct file *file)
+{
+	struct deinterlace_dev *dev = video_drvdata(file);
+	struct deinterlace_ctx *ctx = container_of(file->private_data,
+						   struct deinterlace_ctx, fh);
+
+	mutex_lock(&dev->dev_mutex);
+
+	v4l2_fh_del(&ctx->fh);
+	v4l2_fh_exit(&ctx->fh);
+	v4l2_m2m_ctx_release(ctx->fh.m2m_ctx);
+
+	kfree(ctx);
+
+	mutex_unlock(&dev->dev_mutex);
+
+	return 0;
+}
+
+static const struct v4l2_file_operations deinterlace_fops = {
+	.owner		= THIS_MODULE,
+	.open		= deinterlace_open,
+	.release	= deinterlace_release,
+	.poll		= v4l2_m2m_fop_poll,
+	.unlocked_ioctl	= video_ioctl2,
+	.mmap		= v4l2_m2m_fop_mmap,
+};
+
+static const struct video_device deinterlace_video_device = {
+	.name		= DEINTERLACE_NAME,
+	.vfl_dir	= VFL_DIR_M2M,
+	.fops		= &deinterlace_fops,
+	.ioctl_ops	= &deinterlace_ioctl_ops,
+	.minor		= -1,
+	.release	= video_device_release_empty,
+	.device_caps	= V4L2_CAP_VIDEO_M2M | V4L2_CAP_STREAMING,
+};
+
+static const struct v4l2_m2m_ops deinterlace_m2m_ops = {
+	.device_run	= deinterlace_device_run,
+	.job_ready	= deinterlace_job_ready,
+	.job_abort	= deinterlace_job_abort,
+};
+
+static int deinterlace_probe(struct platform_device *pdev)
+{
+	struct deinterlace_dev *dev;
+	struct video_device *vfd;
+	struct resource *res;
+	int irq, ret;
+
+	dev = devm_kzalloc(&pdev->dev, sizeof(*dev), GFP_KERNEL);
+	if (!dev)
+		return -ENOMEM;
+
+	dev->vfd = deinterlace_video_device;
+	dev->dev = &pdev->dev;
+
+	irq = platform_get_irq(pdev, 0);
+	if (irq <= 0) {
+		dev_err(dev->dev, "Failed to get IRQ\n");
+
+		return irq;
+	}
+
+	ret = devm_request_irq(dev->dev, irq, deinterlace_irq,
+			       0, dev_name(dev->dev), dev);
+	if (ret) {
+		dev_err(dev->dev, "Failed to request IRQ\n");
+
+		return ret;
+	}
+
+	ret = of_dma_configure(dev->dev, dev->dev->of_node, true);
+	if (ret)
+		return ret;
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	dev->base = devm_ioremap_resource(&pdev->dev, res);
+	if (IS_ERR(dev->base)) {
+		dev_err(dev->dev, "Failed to map registers\n");
+
+		return PTR_ERR(dev->base);
+	}
+
+	dev->bus_clk = devm_clk_get(dev->dev, "bus");
+	if (IS_ERR(dev->bus_clk)) {
+		dev_err(dev->dev, "Failed to get bus clock\n");
+
+		return PTR_ERR(dev->bus_clk);
+	}
+
+	dev->mod_clk = devm_clk_get(dev->dev, "mod");
+	if (IS_ERR(dev->mod_clk)) {
+		dev_err(dev->dev, "Failed to get mod clock\n");
+
+		return PTR_ERR(dev->mod_clk);
+	}
+
+	dev->ram_clk = devm_clk_get(dev->dev, "ram");
+	if (IS_ERR(dev->ram_clk)) {
+		dev_err(dev->dev, "Failed to get ram clock\n");
+
+		return PTR_ERR(dev->ram_clk);
+	}
+
+	dev->rstc = devm_reset_control_get(dev->dev, NULL);
+	if (IS_ERR(dev->rstc)) {
+		dev_err(dev->dev, "Failed to get reset control\n");
+
+		return PTR_ERR(dev->rstc);
+	}
+
+	mutex_init(&dev->dev_mutex);
+
+	ret = v4l2_device_register(&pdev->dev, &dev->v4l2_dev);
+	if (ret) {
+		dev_err(dev->dev, "Failed to register V4L2 device\n");
+
+		return ret;
+	}
+
+	vfd = &dev->vfd;
+	vfd->lock = &dev->dev_mutex;
+	vfd->v4l2_dev = &dev->v4l2_dev;
+
+	snprintf(vfd->name, sizeof(vfd->name), "%s",
+		 deinterlace_video_device.name);
+	video_set_drvdata(vfd, dev);
+
+	ret = video_register_device(vfd, VFL_TYPE_GRABBER, 0);
+	if (ret) {
+		v4l2_err(&dev->v4l2_dev, "Failed to register video device\n");
+
+		goto err_v4l2;
+	}
+
+	v4l2_info(&dev->v4l2_dev,
+		  "Device registered as /dev/video%d\n", vfd->num);
+
+	dev->m2m_dev = v4l2_m2m_init(&deinterlace_m2m_ops);
+	if (IS_ERR(dev->m2m_dev)) {
+		v4l2_err(&dev->v4l2_dev,
+			 "Failed to initialize V4L2 M2M device\n");
+		ret = PTR_ERR(dev->m2m_dev);
+
+		goto err_video;
+	}
+
+	platform_set_drvdata(pdev, dev);
+
+	pm_runtime_enable(dev->dev);
+
+	return 0;
+
+err_video:
+	video_unregister_device(&dev->vfd);
+err_v4l2:
+	v4l2_device_unregister(&dev->v4l2_dev);
+
+	return ret;
+}
+
+static int deinterlace_remove(struct platform_device *pdev)
+{
+	struct deinterlace_dev *dev = platform_get_drvdata(pdev);
+
+	v4l2_m2m_release(dev->m2m_dev);
+	video_unregister_device(&dev->vfd);
+	v4l2_device_unregister(&dev->v4l2_dev);
+
+	pm_runtime_force_suspend(&pdev->dev);
+
+	return 0;
+}
+
+static int deinterlace_runtime_resume(struct device *device)
+{
+	struct deinterlace_dev *dev = dev_get_drvdata(device);
+	int ret;
+
+	ret = clk_set_rate_exclusive(dev->mod_clk, 300000000);
+	if (ret) {
+		dev_err(dev->dev, "Failed to set exclusive mod clock rate\n");
+
+		return ret;
+	}
+
+	ret = clk_prepare_enable(dev->bus_clk);
+	if (ret) {
+		dev_err(dev->dev, "Failed to enable bus clock\n");
+
+		goto err_exlusive_rate;
+	}
+
+	ret = clk_prepare_enable(dev->mod_clk);
+	if (ret) {
+		dev_err(dev->dev, "Failed to enable mod clock\n");
+
+		goto err_bus_clk;
+	}
+
+	ret = clk_prepare_enable(dev->ram_clk);
+	if (ret) {
+		dev_err(dev->dev, "Failed to enable ram clock\n");
+
+		goto err_mod_clk;
+	}
+
+	ret = reset_control_deassert(dev->rstc);
+	if (ret) {
+		dev_err(dev->dev, "Failed to apply reset\n");
+
+		goto err_ram_clk;
+	}
+
+	deinterlace_init(dev);
+
+	return 0;
+
+err_exlusive_rate:
+	clk_rate_exclusive_put(dev->mod_clk);
+err_ram_clk:
+	clk_disable_unprepare(dev->ram_clk);
+err_mod_clk:
+	clk_disable_unprepare(dev->mod_clk);
+err_bus_clk:
+	clk_disable_unprepare(dev->bus_clk);
+
+	return ret;
+}
+
+static int deinterlace_runtime_suspend(struct device *device)
+{
+	struct deinterlace_dev *dev = dev_get_drvdata(device);
+
+	reset_control_assert(dev->rstc);
+
+	clk_disable_unprepare(dev->ram_clk);
+	clk_disable_unprepare(dev->mod_clk);
+	clk_disable_unprepare(dev->bus_clk);
+	clk_rate_exclusive_put(dev->mod_clk);
+
+	return 0;
+}
+
+static const struct of_device_id deinterlace_dt_match[] = {
+	{ .compatible = "allwinner,sun8i-h3-deinterlace" },
+	{ /* sentinel */ }
+};
+MODULE_DEVICE_TABLE(of, deinterlace_dt_match);
+
+static const struct dev_pm_ops deinterlace_pm_ops = {
+	.runtime_resume		= deinterlace_runtime_resume,
+	.runtime_suspend	= deinterlace_runtime_suspend,
+};
+
+static struct platform_driver deinterlace_driver = {
+	.probe		= deinterlace_probe,
+	.remove		= deinterlace_remove,
+	.driver		= {
+		.name		= DEINTERLACE_NAME,
+		.of_match_table	= deinterlace_dt_match,
+		.pm		= &deinterlace_pm_ops,
+	},
+};
+module_platform_driver(deinterlace_driver);
+
+MODULE_LICENSE("GPL v2");
+MODULE_AUTHOR("Jernej Skrabec <jernej.skrabec@siol.net>");
+MODULE_DESCRIPTION("Allwinner Deinterlace driver");
diff --git a/drivers/media/platform/sunxi/sun8i-di/sun8i-di.h b/drivers/media/platform/sunxi/sun8i-di/sun8i-di.h
new file mode 100644
index 000000000000..0254251d8687
--- /dev/null
+++ b/drivers/media/platform/sunxi/sun8i-di/sun8i-di.h
@@ -0,0 +1,237 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Allwinner Deinterlace driver
+ *
+ * Copyright (C) 2019 Jernej Skrabec <jernej.skrabec@siol.net>
+ */
+
+#ifndef _SUN8I_DEINTERLACE_H_
+#define _SUN8I_DEINTERLACE_H_
+
+#include <media/v4l2-device.h>
+#include <media/v4l2-mem2mem.h>
+#include <media/videobuf2-v4l2.h>
+#include <media/videobuf2-dma-contig.h>
+
+#include <linux/platform_device.h>
+
+#define DEINTERLACE_NAME		"sun8i-di"
+
+#define DEINTERLACE_MOD_ENABLE			0x00
+#define DEINTERLACE_MOD_ENABLE_EN			BIT(0)
+
+#define DEINTERLACE_FRM_CTRL			0x04
+#define DEINTERLACE_FRM_CTRL_REG_READY			BIT(0)
+#define DEINTERLACE_FRM_CTRL_WB_EN			BIT(2)
+#define DEINTERLACE_FRM_CTRL_OUT_CTRL			BIT(11)
+#define DEINTERLACE_FRM_CTRL_START			BIT(16)
+#define DEINTERLACE_FRM_CTRL_COEF_ACCESS		BIT(23)
+
+#define DEINTERLACE_BYPASS			0x08
+#define DEINTERLACE_BYPASS_CSC				BIT(1)
+
+#define DEINTERLACE_AGTH_SEL			0x0c
+#define DEINTERLACE_AGTH_SEL_LINEBUF			BIT(8)
+
+#define DEINTERLACE_LINT_CTRL			0x10
+#define DEINTERLACE_TRD_PRELUMA			0x1c
+#define DEINTERLACE_BUF_ADDR0			0x20
+#define DEINTERLACE_BUF_ADDR1			0x24
+#define DEINTERLACE_BUF_ADDR2			0x28
+
+#define DEINTERLACE_FIELD_CTRL			0x2c
+#define DEINTERLACE_FIELD_CTRL_FIELD_CNT(v)		((v) & 0xff)
+#define DEINTERLACE_FIELD_CTRL_FIELD_CNT_MSK		(0xff)
+
+#define DEINTERLACE_TB_OFFSET0			0x30
+#define DEINTERLACE_TB_OFFSET1			0x34
+#define DEINTERLACE_TB_OFFSET2			0x38
+#define DEINTERLACE_TRD_PRECHROMA		0x3c
+#define DEINTERLACE_LINE_STRIDE0		0x40
+#define DEINTERLACE_LINE_STRIDE1		0x44
+#define DEINTERLACE_LINE_STRIDE2		0x48
+
+#define DEINTERLACE_IN_FMT			0x4c
+#define DEINTERLACE_IN_FMT_PS(v)			((v) & 3)
+#define DEINTERLACE_IN_FMT_FMT(v)			(((v) & 7) << 4)
+#define DEINTERLACE_IN_FMT_MOD(v)			(((v) & 7) << 8)
+
+#define DEINTERLACE_WB_ADDR0			0x50
+#define DEINTERLACE_WB_ADDR1			0x54
+#define DEINTERLACE_WB_ADDR2			0x58
+
+#define DEINTERLACE_OUT_FMT			0x5c
+#define DEINTERLACE_OUT_FMT_FMT(v)			((v) & 0xf)
+#define DEINTERLACE_OUT_FMT_PS(v)			(((v) & 3) << 5)
+
+#define DEINTERLACE_INT_ENABLE			0x60
+#define DEINTERLACE_INT_ENABLE_WB_EN			BIT(7)
+
+#define DEINTERLACE_INT_STATUS			0x64
+#define DEINTERLACE_INT_STATUS_WRITEBACK		BIT(7)
+
+#define DEINTERLACE_STATUS			0x68
+#define DEINTERLACE_STATUS_COEF_STATUS			BIT(11)
+#define DEINTERLACE_STATUS_WB_ERROR			BIT(12)
+
+#define DEINTERLACE_CSC_COEF			0x70 /* 12 registers */
+
+#define DEINTERLACE_CTRL			0xa0
+#define DEINTERLACE_CTRL_EN				BIT(0)
+#define DEINTERLACE_CTRL_FLAG_OUT_EN			BIT(8)
+#define DEINTERLACE_CTRL_MODE_PASSTROUGH		(0 << 16)
+#define DEINTERLACE_CTRL_MODE_WEAVE			(1 << 16)
+#define DEINTERLACE_CTRL_MODE_BOB			(2 << 16)
+#define DEINTERLACE_CTRL_MODE_MIXED			(3 << 16)
+#define DEINTERLACE_CTRL_DIAG_INTP_EN			BIT(24)
+#define DEINTERLACE_CTRL_TEMP_DIFF_EN			BIT(25)
+
+#define DEINTERLACE_DIAG_INTP			0xa4
+#define DEINTERLACE_DIAG_INTP_TH0(v)			((v) & 0x7f)
+#define DEINTERLACE_DIAG_INTP_TH0_MSK			(0x7f)
+#define DEINTERLACE_DIAG_INTP_TH1(v)			(((v) & 0x7f) << 8)
+#define DEINTERLACE_DIAG_INTP_TH1_MSK			(0x7f << 8)
+#define DEINTERLACE_DIAG_INTP_TH3(v)			(((v) & 0xff) << 24)
+#define DEINTERLACE_DIAG_INTP_TH3_MSK			(0xff << 24)
+
+#define DEINTERLACE_TEMP_DIFF			0xa8
+#define DEINTERLACE_TEMP_DIFF_SAD_CENTRAL_TH(v)		((v) & 0x7f)
+#define DEINTERLACE_TEMP_DIFF_SAD_CENTRAL_TH_MSK	(0x7f)
+#define DEINTERLACE_TEMP_DIFF_AMBIGUITY_TH(v)		(((v) & 0x7f) << 8)
+#define DEINTERLACE_TEMP_DIFF_AMBIGUITY_TH_MSK		(0x7f << 8)
+#define DEINTERLACE_TEMP_DIFF_DIRECT_DITHER_TH(v)	(((v) & 0x7ff) << 16)
+#define DEINTERLACE_TEMP_DIFF_DIRECT_DITHER_TH_MSK	(0x7ff << 16)
+
+#define DEINTERLACE_LUMA_TH			0xac
+#define DEINTERLACE_LUMA_TH_MIN_LUMA(v)			((v) & 0xff)
+#define DEINTERLACE_LUMA_TH_MIN_LUMA_MSK		(0xff)
+#define DEINTERLACE_LUMA_TH_MAX_LUMA(v)			(((v) & 0xff) << 8)
+#define DEINTERLACE_LUMA_TH_MAX_LUMA_MSK		(0xff << 8)
+#define DEINTERLACE_LUMA_TH_AVG_LUMA_SHIFT(v)		(((v) & 0xff) << 16)
+#define DEINTERLACE_LUMA_TH_AVG_LUMA_SHIFT_MSK		(0xff << 16)
+#define DEINTERLACE_LUMA_TH_PIXEL_STATIC(v)		(((v) & 3) << 24)
+#define DEINTERLACE_LUMA_TH_PIXEL_STATIC_MSK		(3 << 24)
+
+#define DEINTERLACE_SPAT_COMP			0xb0
+#define DEINTERLACE_SPAT_COMP_TH2(v)			((v) & 0xff)
+#define DEINTERLACE_SPAT_COMP_TH2_MSK			(0xff)
+#define DEINTERLACE_SPAT_COMP_TH3(v)			(((v) & 0xff) << 16)
+#define DEINTERLACE_SPAT_COMP_TH3_MSK			(0xff << 16)
+
+#define DEINTERLACE_CHROMA_DIFF			0xb4
+#define DEINTERLACE_CHROMA_DIFF_TH(v)			((v) & 0xff)
+#define DEINTERLACE_CHROMA_DIFF_TH_MSK			(0xff)
+#define DEINTERLACE_CHROMA_DIFF_LUMA(v)			(((v) & 0x3f) << 16)
+#define DEINTERLACE_CHROMA_DIFF_LUMA_MSK		(0x3f << 16)
+#define DEINTERLACE_CHROMA_DIFF_CHROMA(v)		(((v) & 0x3f) << 24)
+#define DEINTERLACE_CHROMA_DIFF_CHROMA_MSK		(0x3f << 24)
+
+#define DEINTERLACE_PRELUMA			0xb8
+#define DEINTERLACE_PRECHROMA			0xbc
+#define DEINTERLACE_TILE_FLAG0			0xc0
+#define DEINTERLACE_TILE_FLAG1			0xc4
+#define DEINTERLACE_FLAG_LINE_STRIDE		0xc8
+#define DEINTERLACE_FLAG_SEQ			0xcc
+
+#define DEINTERLACE_WB_LINE_STRIDE_CTRL		0xd0
+#define DEINTERLACE_WB_LINE_STRIDE_CTRL_EN		BIT(0)
+
+#define DEINTERLACE_WB_LINE_STRIDE0		0xd4
+#define DEINTERLACE_WB_LINE_STRIDE1		0xd8
+#define DEINTERLACE_WB_LINE_STRIDE2		0xdc
+#define DEINTERLACE_TRD_CTRL			0xe0
+#define DEINTERLACE_TRD_BUF_ADDR0		0xe4
+#define DEINTERLACE_TRD_BUF_ADDR1		0xe8
+#define DEINTERLACE_TRD_BUF_ADDR2		0xec
+#define DEINTERLACE_TRD_TB_OFF0			0xf0
+#define DEINTERLACE_TRD_TB_OFF1			0xf4
+#define DEINTERLACE_TRD_TB_OFF2			0xf8
+#define DEINTERLACE_TRD_WB_STRIDE		0xfc
+#define DEINTERLACE_CH0_IN_SIZE			0x100
+#define DEINTERLACE_CH0_OUT_SIZE		0x104
+#define DEINTERLACE_CH0_HORZ_FACT		0x108
+#define DEINTERLACE_CH0_VERT_FACT		0x10c
+#define DEINTERLACE_CH0_HORZ_PHASE		0x110
+#define DEINTERLACE_CH0_VERT_PHASE0		0x114
+#define DEINTERLACE_CH0_VERT_PHASE1		0x118
+#define DEINTERLACE_CH0_HORZ_TAP0		0x120
+#define DEINTERLACE_CH0_HORZ_TAP1		0x124
+#define DEINTERLACE_CH0_VERT_TAP		0x128
+#define DEINTERLACE_CH1_IN_SIZE			0x200
+#define DEINTERLACE_CH1_OUT_SIZE		0x204
+#define DEINTERLACE_CH1_HORZ_FACT		0x208
+#define DEINTERLACE_CH1_VERT_FACT		0x20c
+#define DEINTERLACE_CH1_HORZ_PHASE		0x210
+#define DEINTERLACE_CH1_VERT_PHASE0		0x214
+#define DEINTERLACE_CH1_VERT_PHASE1		0x218
+#define DEINTERLACE_CH1_HORZ_TAP0		0x220
+#define DEINTERLACE_CH1_HORZ_TAP1		0x224
+#define DEINTERLACE_CH1_VERT_TAP		0x228
+#define DEINTERLACE_CH0_HORZ_COEF0		0x400 /* 32 registers */
+#define DEINTERLACE_CH0_HORZ_COEF1		0x480 /* 32 registers */
+#define DEINTERLACE_CH0_VERT_COEF		0x500 /* 32 registers */
+#define DEINTERLACE_CH1_HORZ_COEF0		0x600 /* 32 registers */
+#define DEINTERLACE_CH1_HORZ_COEF1		0x680 /* 32 registers */
+#define DEINTERLACE_CH1_VERT_COEF		0x700 /* 32 registers */
+#define DEINTERLACE_CH3_HORZ_COEF0		0x800 /* 32 registers */
+#define DEINTERLACE_CH3_HORZ_COEF1		0x880 /* 32 registers */
+#define DEINTERLACE_CH3_VERT_COEF		0x900 /* 32 registers */
+
+#define DEINTERLACE_MIN_WIDTH	2U
+#define DEINTERLACE_MIN_HEIGHT	2U
+#define DEINTERLACE_MAX_WIDTH	2048U
+#define DEINTERLACE_MAX_HEIGHT	1100U
+
+#define DEINTERLACE_MODE_UV_COMBINED	2
+
+#define DEINTERLACE_IN_FMT_YUV420	2
+
+#define DEINTERLACE_OUT_FMT_YUV420SP	13
+
+#define DEINTERLACE_PS_UVUV		0
+#define DEINTERLACE_PS_VUVU		1
+
+#define DEINTERLACE_IDENTITY_COEF	0x4000
+
+#define DEINTERLACE_SIZE(w, h)	(((h) - 1) << 16 | ((w) - 1))
+
+struct deinterlace_ctx {
+	struct v4l2_fh		fh;
+	struct deinterlace_dev	*dev;
+
+	struct v4l2_pix_format	src_fmt;
+	struct v4l2_pix_format	dst_fmt;
+
+	void			*flag1_buf;
+	dma_addr_t		flag1_buf_dma;
+
+	void			*flag2_buf;
+	dma_addr_t		flag2_buf_dma;
+
+	struct vb2_v4l2_buffer	*prev;
+
+	unsigned int		first_field;
+	unsigned int		field;
+
+	int			aborting;
+};
+
+struct deinterlace_dev {
+	struct v4l2_device	v4l2_dev;
+	struct video_device	vfd;
+	struct device		*dev;
+	struct v4l2_m2m_dev	*m2m_dev;
+
+	/* Device file mutex */
+	struct mutex		dev_mutex;
+
+	void __iomem		*base;
+
+	struct clk		*bus_clk;
+	struct clk		*mod_clk;
+	struct clk		*ram_clk;
+
+	struct reset_control	*rstc;
+};
+
+#endif
diff --git a/drivers/media/platform/ti-vpe/csc.c b/drivers/media/platform/ti-vpe/csc.c
index eda2a5985da7..834114a4eebe 100644
--- a/drivers/media/platform/ti-vpe/csc.c
+++ b/drivers/media/platform/ti-vpe/csc.c
@@ -15,76 +15,96 @@
 #include <linux/platform_device.h>
 #include <linux/slab.h>
 #include <linux/videodev2.h>
+#include <media/v4l2-common.h>
 
 #include "csc.h"
 
 /*
- * 16 coefficients in the order:
+ * 12 coefficients in the order:
  * a0, b0, c0, a1, b1, c1, a2, b2, c2, d0, d1, d2
- * (we may need to pass non-default values from user space later on, we might
- * need to make the coefficient struct more easy to populate)
  */
-struct colorspace_coeffs {
-	u16	sd[12];
-	u16	hd[12];
+struct quantization {
+	u16	coeff[12];
 };
 
-/* VIDEO_RANGE: limited range, GRAPHICS_RANGE: full range */
-#define	CSC_COEFFS_VIDEO_RANGE_Y2R	0
-#define	CSC_COEFFS_GRAPHICS_RANGE_Y2R	1
-#define	CSC_COEFFS_VIDEO_RANGE_R2Y	2
-#define	CSC_COEFFS_GRAPHICS_RANGE_R2Y	3
+struct colorspace {
+	struct quantization limited;
+	struct quantization full;
+};
+
+struct encoding_direction {
+	struct colorspace r601;
+	struct colorspace r709;
+};
+
+struct csc_coeffs {
+	struct encoding_direction y2r;
+	struct encoding_direction r2y;
+};
 
 /* default colorspace coefficients */
-static struct colorspace_coeffs colorspace_coeffs[4] = {
-	[CSC_COEFFS_VIDEO_RANGE_Y2R] = {
-		{
-			/* SDTV */
-			0x0400, 0x0000, 0x057D, 0x0400, 0x1EA7, 0x1D35,
-			0x0400, 0x06EF, 0x1FFE, 0x0D40, 0x0210, 0x0C88,
+static struct csc_coeffs csc_coeffs = {
+	.y2r = {
+		.r601 = {
+			.limited = {
+				{	/* SDTV */
+				0x0400, 0x0000, 0x057D, 0x0400, 0x1EA7, 0x1D35,
+				0x0400, 0x06EF, 0x1FFE, 0x0D40, 0x0210, 0x0C88,
+				}
+			},
+			.full = {
+				{	/* SDTV */
+				0x04A8, 0x1FFE, 0x0662, 0x04A8, 0x1E6F, 0x1CBF,
+				0x04A8, 0x0812, 0x1FFF, 0x0C84, 0x0220, 0x0BAC,
+				}
+			},
 		},
-		{
-			/* HDTV */
-			0x0400, 0x0000, 0x0629, 0x0400, 0x1F45, 0x1E2B,
-			0x0400, 0x0742, 0x0000, 0x0CEC, 0x0148, 0x0C60,
+		.r709 = {
+			.limited = {
+				{	/* HDTV */
+				0x0400, 0x0000, 0x0629, 0x0400, 0x1F45, 0x1E2B,
+				0x0400, 0x0742, 0x0000, 0x0CEC, 0x0148, 0x0C60,
+				}
+			},
+			.full = {
+				{	/* HDTV */
+				0x04A8, 0x0000, 0x072C, 0x04A8, 0x1F26, 0x1DDE,
+				0x04A8, 0x0873, 0x0000, 0x0C20, 0x0134, 0x0B7C,
+				}
+			},
 		},
 	},
-	[CSC_COEFFS_GRAPHICS_RANGE_Y2R] = {
-		{
-			/* SDTV */
-			0x04A8, 0x1FFE, 0x0662, 0x04A8, 0x1E6F, 0x1CBF,
-			0x04A8, 0x0812, 0x1FFF, 0x0C84, 0x0220, 0x0BAC,
+	.r2y = {
+		.r601 = {
+			.limited = {
+				{	/* SDTV */
+				0x0132, 0x0259, 0x0075, 0x1F50, 0x1EA5, 0x020B,
+				0x020B, 0x1E4A, 0x1FAB, 0x0000, 0x0200, 0x0200,
+				}
+			},
+			.full = {
+				{	/* SDTV */
+				0x0107, 0x0204, 0x0064, 0x1F68, 0x1ED6, 0x01C2,
+				0x01C2, 0x1E87, 0x1FB7, 0x0040, 0x0200, 0x0200,
+				}
+			},
 		},
-		{
-			/* HDTV */
-			0x04A8, 0x0000, 0x072C, 0x04A8, 0x1F26, 0x1DDE,
-			0x04A8, 0x0873, 0x0000, 0x0C20, 0x0134, 0x0B7C,
-		},
-	},
-	[CSC_COEFFS_VIDEO_RANGE_R2Y] = {
-		{
-			/* SDTV */
-			0x0132, 0x0259, 0x0075, 0x1F50, 0x1EA5, 0x020B,
-			0x020B, 0x1E4A, 0x1FAB, 0x0000, 0x0200, 0x0200,
-		},
-		{
-			/* HDTV */
-			0x00DA, 0x02DC, 0x004A, 0x1F88, 0x1E6C, 0x020C,
-			0x020C, 0x1E24, 0x1FD0, 0x0000, 0x0200, 0x0200,
-		},
-	},
-	[CSC_COEFFS_GRAPHICS_RANGE_R2Y] = {
-		{
-			/* SDTV */
-			0x0107, 0x0204, 0x0064, 0x1F68, 0x1ED6, 0x01C2,
-			0x01C2, 0x1E87, 0x1FB7, 0x0040, 0x0200, 0x0200,
-		},
-		{
-			/* HDTV */
-			0x04A8, 0x0000, 0x072C, 0x04A8, 0x1F26, 0x1DDE,
-			0x04A8, 0x0873, 0x0000, 0x0C20, 0x0134, 0x0B7C,
+		.r709 = {
+			.limited = {
+				{	/* HDTV */
+				0x00DA, 0x02DC, 0x004A, 0x1F88, 0x1E6C, 0x020C,
+				0x020C, 0x1E24, 0x1FD0, 0x0000, 0x0200, 0x0200,
+				}
+			},
+			.full = {
+				{	/* HDTV */
+				0x00bb, 0x0275, 0x003f, 0x1f99, 0x1ea5, 0x01c2,
+				0x01c2, 0x1e67, 0x1fd7, 0x0040, 0x0200, 0x0200,
+				}
+			},
 		},
 	},
+
 };
 
 void csc_dump_regs(struct csc_data *csc)
@@ -117,46 +137,114 @@ EXPORT_SYMBOL(csc_set_coeff_bypass);
  * set the color space converter coefficient shadow register values
  */
 void csc_set_coeff(struct csc_data *csc, u32 *csc_reg0,
-		enum v4l2_colorspace src_colorspace,
-		enum v4l2_colorspace dst_colorspace)
+		   struct v4l2_format *src_fmt, struct v4l2_format *dst_fmt)
 {
 	u32 *csc_reg5 = csc_reg0 + 5;
 	u32 *shadow_csc = csc_reg0;
-	struct colorspace_coeffs *sd_hd_coeffs;
 	u16 *coeff, *end_coeff;
-	enum v4l2_colorspace yuv_colorspace;
-	int sel = 0;
-
-	/*
-	 * support only graphics data range(full range) for now, a control ioctl
-	 * would be nice here
-	 */
-	/* Y2R */
-	if (dst_colorspace == V4L2_COLORSPACE_SRGB &&
-			(src_colorspace == V4L2_COLORSPACE_SMPTE170M ||
-			src_colorspace == V4L2_COLORSPACE_REC709)) {
+	const struct v4l2_pix_format *pix;
+	const struct v4l2_pix_format_mplane *mp;
+	const struct v4l2_format_info *src_finfo, *dst_finfo;
+	enum v4l2_ycbcr_encoding src_ycbcr_enc, dst_ycbcr_enc;
+	enum v4l2_quantization src_quantization, dst_quantization;
+	u32 src_pixelformat, dst_pixelformat;
+
+	switch (src_fmt->type) {
+	case V4L2_BUF_TYPE_VIDEO_OUTPUT:
+		pix = &src_fmt->fmt.pix;
+		src_pixelformat = pix->pixelformat;
+		src_ycbcr_enc = pix->ycbcr_enc;
+		src_quantization = pix->quantization;
+		break;
+	case V4L2_BUF_TYPE_VIDEO_OUTPUT_MPLANE:
+	default:
+		mp = &src_fmt->fmt.pix_mp;
+		src_pixelformat = mp->pixelformat;
+		src_ycbcr_enc = mp->ycbcr_enc;
+		src_quantization = mp->quantization;
+		break;
+	}
+
+	switch (dst_fmt->type) {
+	case V4L2_BUF_TYPE_VIDEO_OUTPUT:
+		pix = &dst_fmt->fmt.pix;
+		dst_pixelformat = pix->pixelformat;
+		dst_ycbcr_enc = pix->ycbcr_enc;
+		dst_quantization = pix->quantization;
+		break;
+	case V4L2_BUF_TYPE_VIDEO_OUTPUT_MPLANE:
+	default:
+		mp = &dst_fmt->fmt.pix_mp;
+		dst_pixelformat = mp->pixelformat;
+		dst_ycbcr_enc = mp->ycbcr_enc;
+		dst_quantization = mp->quantization;
+		break;
+	}
+
+	src_finfo = v4l2_format_info(src_pixelformat);
+	dst_finfo = v4l2_format_info(dst_pixelformat);
+
+	if (v4l2_is_format_yuv(src_finfo) &&
+	    v4l2_is_format_rgb(dst_finfo)) {
 		/* Y2R */
-		sel = 1;
-		yuv_colorspace = src_colorspace;
-	} else if ((dst_colorspace == V4L2_COLORSPACE_SMPTE170M ||
-			dst_colorspace == V4L2_COLORSPACE_REC709) &&
-			src_colorspace == V4L2_COLORSPACE_SRGB) {
+
+		/*
+		 * These are not the standard default values but are
+		 * set this way for historical compatibility
+		 */
+		if (src_ycbcr_enc == V4L2_YCBCR_ENC_DEFAULT)
+			src_ycbcr_enc = V4L2_YCBCR_ENC_601;
+
+		if (src_quantization == V4L2_QUANTIZATION_DEFAULT)
+			src_quantization = V4L2_QUANTIZATION_FULL_RANGE;
+
+		if (src_ycbcr_enc == V4L2_YCBCR_ENC_601) {
+			if (src_quantization == V4L2_QUANTIZATION_FULL_RANGE)
+				coeff = csc_coeffs.y2r.r601.full.coeff;
+			else
+				coeff = csc_coeffs.y2r.r601.limited.coeff;
+		} else if (src_ycbcr_enc == V4L2_YCBCR_ENC_709) {
+			if (src_quantization == V4L2_QUANTIZATION_FULL_RANGE)
+				coeff = csc_coeffs.y2r.r709.full.coeff;
+			else
+				coeff = csc_coeffs.y2r.r709.limited.coeff;
+		} else {
+			/* Should never reach this, but it keeps gcc happy */
+			coeff = csc_coeffs.y2r.r601.full.coeff;
+		}
+	} else if (v4l2_is_format_rgb(src_finfo) &&
+		   v4l2_is_format_yuv(dst_finfo)) {
 		/* R2Y */
-		sel = 3;
-		yuv_colorspace = dst_colorspace;
+
+		/*
+		 * These are not the standard default values but are
+		 * set this way for historical compatibility
+		 */
+		if (dst_ycbcr_enc == V4L2_YCBCR_ENC_DEFAULT)
+			dst_ycbcr_enc = V4L2_YCBCR_ENC_601;
+
+		if (dst_quantization == V4L2_QUANTIZATION_DEFAULT)
+			dst_quantization = V4L2_QUANTIZATION_FULL_RANGE;
+
+		if (dst_ycbcr_enc == V4L2_YCBCR_ENC_601) {
+			if (dst_quantization == V4L2_QUANTIZATION_FULL_RANGE)
+				coeff = csc_coeffs.r2y.r601.full.coeff;
+			else
+				coeff = csc_coeffs.r2y.r601.limited.coeff;
+		} else if (dst_ycbcr_enc == V4L2_YCBCR_ENC_709) {
+			if (dst_quantization == V4L2_QUANTIZATION_FULL_RANGE)
+				coeff = csc_coeffs.r2y.r709.full.coeff;
+			else
+				coeff = csc_coeffs.r2y.r709.limited.coeff;
+		} else {
+			/* Should never reach this, but it keeps gcc happy */
+			coeff = csc_coeffs.r2y.r601.full.coeff;
+		}
 	} else {
 		*csc_reg5 |= CSC_BYPASS;
 		return;
 	}
 
-	sd_hd_coeffs = &colorspace_coeffs[sel];
-
-	/* select between SD or HD coefficients */
-	if (yuv_colorspace == V4L2_COLORSPACE_SMPTE170M)
-		coeff = sd_hd_coeffs->sd;
-	else
-		coeff = sd_hd_coeffs->hd;
-
 	end_coeff = coeff + 12;
 
 	for (; coeff < end_coeff; coeff += 2)
diff --git a/drivers/media/platform/ti-vpe/csc.h b/drivers/media/platform/ti-vpe/csc.h
index de9a58af2ca8..af2e86bccf57 100644
--- a/drivers/media/platform/ti-vpe/csc.h
+++ b/drivers/media/platform/ti-vpe/csc.h
@@ -58,8 +58,8 @@ struct csc_data {
 void csc_dump_regs(struct csc_data *csc);
 void csc_set_coeff_bypass(struct csc_data *csc, u32 *csc_reg5);
 void csc_set_coeff(struct csc_data *csc, u32 *csc_reg0,
-		enum v4l2_colorspace src_colorspace,
-		enum v4l2_colorspace dst_colorspace);
+		   struct v4l2_format *src_fmt, struct v4l2_format *dst_fmt);
+
 struct csc_data *csc_create(struct platform_device *pdev, const char *res_name);
 
 #endif
diff --git a/drivers/media/platform/ti-vpe/vpdma.c b/drivers/media/platform/ti-vpe/vpdma.c
index 53d27cd6e10a..2e5148ae7a0f 100644
--- a/drivers/media/platform/ti-vpe/vpdma.c
+++ b/drivers/media/platform/ti-vpe/vpdma.c
@@ -56,6 +56,11 @@ const struct vpdma_data_format vpdma_yuv_fmts[] = {
 		.data_type	= DATA_TYPE_C420,
 		.depth		= 4,
 	},
+	[VPDMA_DATA_FMT_CB420] = {
+		.type		= VPDMA_DATA_FMT_TYPE_YUV,
+		.data_type	= DATA_TYPE_CB420,
+		.depth		= 4,
+	},
 	[VPDMA_DATA_FMT_YCR422] = {
 		.type		= VPDMA_DATA_FMT_TYPE_YUV,
 		.data_type	= DATA_TYPE_YCR422,
@@ -759,7 +764,7 @@ static void dump_dtd(struct vpdma_dtd *dtd)
 		pr_debug("word1: line_length = %d, xfer_height = %d\n",
 			dtd_get_line_length(dtd), dtd_get_xfer_height(dtd));
 
-	pr_debug("word2: start_addr = %pad\n", &dtd->start_addr);
+	pr_debug("word2: start_addr = %x\n", dtd->start_addr);
 
 	pr_debug("word3: pkt_type = %d, mode = %d, dir = %d, chan = %d, pri = %d, next_chan = %d\n",
 		 dtd_get_pkt_type(dtd),
@@ -825,7 +830,8 @@ void vpdma_rawchan_add_out_dtd(struct vpdma_desc_list *list, int width,
 	channel = next_chan = raw_vpdma_chan;
 
 	if (fmt->type == VPDMA_DATA_FMT_TYPE_YUV &&
-			fmt->data_type == DATA_TYPE_C420) {
+	    (fmt->data_type == DATA_TYPE_C420 ||
+	     fmt->data_type == DATA_TYPE_CB420)) {
 		rect.height >>= 1;
 		rect.top >>= 1;
 		depth = 8;
@@ -893,7 +899,8 @@ void vpdma_add_in_dtd(struct vpdma_desc_list *list, int width,
 	channel = next_chan = chan_info[chan].num;
 
 	if (fmt->type == VPDMA_DATA_FMT_TYPE_YUV &&
-			fmt->data_type == DATA_TYPE_C420) {
+	    (fmt->data_type == DATA_TYPE_C420 ||
+	     fmt->data_type == DATA_TYPE_CB420)) {
 		rect.height >>= 1;
 		rect.top >>= 1;
 		depth = 8;
diff --git a/drivers/media/platform/ti-vpe/vpdma.h b/drivers/media/platform/ti-vpe/vpdma.h
index 28bc94129348..393fcbb3cb40 100644
--- a/drivers/media/platform/ti-vpe/vpdma.h
+++ b/drivers/media/platform/ti-vpe/vpdma.h
@@ -57,6 +57,7 @@ struct vpdma_data_format {
 						 * line stride of source and dest
 						 * buffers should be 16 byte aligned
 						 */
+#define VPDMA_MAX_STRIDE		65520	/* Max line stride 16 byte aligned */
 #define VPDMA_DTD_DESC_SIZE		32	/* 8 words */
 #define VPDMA_CFD_CTD_DESC_SIZE		16	/* 4 words */
 
@@ -71,6 +72,7 @@ enum vpdma_yuv_formats {
 	VPDMA_DATA_FMT_C444,
 	VPDMA_DATA_FMT_C422,
 	VPDMA_DATA_FMT_C420,
+	VPDMA_DATA_FMT_CB420,
 	VPDMA_DATA_FMT_YCR422,
 	VPDMA_DATA_FMT_YC444,
 	VPDMA_DATA_FMT_CRY422,
diff --git a/drivers/media/platform/ti-vpe/vpdma_priv.h b/drivers/media/platform/ti-vpe/vpdma_priv.h
index c488609bc162..0bbee45338bd 100644
--- a/drivers/media/platform/ti-vpe/vpdma_priv.h
+++ b/drivers/media/platform/ti-vpe/vpdma_priv.h
@@ -92,6 +92,7 @@
 #define DATA_TYPE_C444				0x4
 #define DATA_TYPE_C422				0x5
 #define DATA_TYPE_C420				0x6
+#define DATA_TYPE_CB420				0x16
 #define DATA_TYPE_YC444				0x8
 #define DATA_TYPE_YCB422			0x7
 #define DATA_TYPE_YCR422			0x17
@@ -165,11 +166,11 @@ struct vpdma_dtd {
 		u32		xfer_length_height;
 		u32		w1;
 	};
-	dma_addr_t		start_addr;
+	u32			start_addr;
 	u32			pkt_ctl;
 	union {
 		u32		frame_width_height;	/* inbound */
-		dma_addr_t	desc_write_addr;	/* outbound */
+		u32		desc_write_addr;	/* outbound */
 	};
 	union {
 		u32		start_h_v;		/* inbound */
diff --git a/drivers/media/platform/ti-vpe/vpe.c b/drivers/media/platform/ti-vpe/vpe.c
index 60b575bb44c4..65c2c048b018 100644
--- a/drivers/media/platform/ti-vpe/vpe.c
+++ b/drivers/media/platform/ti-vpe/vpe.c
@@ -52,7 +52,7 @@
 #define MIN_W		32
 #define MIN_H		32
 #define MAX_W		2048
-#define MAX_H		1184
+#define MAX_H		2048
 
 /* required alignments */
 #define S_ALIGN		0	/* multiple of 1 */
@@ -249,6 +249,14 @@ static struct vpe_fmt vpe_formats[] = {
 				  },
 	},
 	{
+		.fourcc		= V4L2_PIX_FMT_NV21,
+		.types		= VPE_FMT_TYPE_CAPTURE | VPE_FMT_TYPE_OUTPUT,
+		.coplanar	= 1,
+		.vpdma_fmt	= { &vpdma_yuv_fmts[VPDMA_DATA_FMT_Y420],
+				    &vpdma_yuv_fmts[VPDMA_DATA_FMT_CB420],
+				  },
+	},
+	{
 		.fourcc		= V4L2_PIX_FMT_YUYV,
 		.types		= VPE_FMT_TYPE_CAPTURE | VPE_FMT_TYPE_OUTPUT,
 		.coplanar	= 0,
@@ -311,14 +319,9 @@ static struct vpe_fmt vpe_formats[] = {
  * there is one source queue and one destination queue for each m2m context.
  */
 struct vpe_q_data {
-	unsigned int		width;				/* frame width */
-	unsigned int		height;				/* frame height */
-	unsigned int		nplanes;			/* Current number of planes */
-	unsigned int		bytesperline[VPE_MAX_PLANES];	/* bytes per line in memory */
-	enum v4l2_colorspace	colorspace;
-	enum v4l2_field		field;				/* supported field value */
+	/* current v4l2 format info */
+	struct v4l2_format	format;
 	unsigned int		flags;
-	unsigned int		sizeimage[VPE_MAX_PLANES];	/* image size in memory */
 	struct v4l2_rect	c_rect;				/* crop/compose rectangle */
 	struct vpe_fmt		*fmt;				/* format info */
 };
@@ -328,9 +331,14 @@ struct vpe_q_data {
 #define	Q_DATA_MODE_TILED		BIT(1)
 #define	Q_DATA_INTERLACED_ALTERNATE	BIT(2)
 #define	Q_DATA_INTERLACED_SEQ_TB	BIT(3)
+#define	Q_DATA_INTERLACED_SEQ_BT	BIT(4)
+
+#define Q_IS_SEQ_XX		(Q_DATA_INTERLACED_SEQ_TB | \
+				Q_DATA_INTERLACED_SEQ_BT)
 
 #define Q_IS_INTERLACED		(Q_DATA_INTERLACED_ALTERNATE | \
-				Q_DATA_INTERLACED_SEQ_TB)
+				Q_DATA_INTERLACED_SEQ_TB | \
+				Q_DATA_INTERLACED_SEQ_BT)
 
 enum {
 	Q_DATA_SRC = 0,
@@ -338,20 +346,25 @@ enum {
 };
 
 /* find our format description corresponding to the passed v4l2_format */
-static struct vpe_fmt *find_format(struct v4l2_format *f)
+static struct vpe_fmt *__find_format(u32 fourcc)
 {
 	struct vpe_fmt *fmt;
 	unsigned int k;
 
 	for (k = 0; k < ARRAY_SIZE(vpe_formats); k++) {
 		fmt = &vpe_formats[k];
-		if (fmt->fourcc == f->fmt.pix.pixelformat)
+		if (fmt->fourcc == fourcc)
 			return fmt;
 	}
 
 	return NULL;
 }
 
+static struct vpe_fmt *find_format(struct v4l2_format *f)
+{
+	return __find_format(f->fmt.pix.pixelformat);
+}
+
 /*
  * there is one vpe_dev structure in the driver, it is shared by
  * all instances.
@@ -681,7 +694,8 @@ static void set_cfg_modes(struct vpe_ctx *ctx)
 	 * Cfg Mode 1: YUV422 source, disable upsampler, DEI is de-interlacing.
 	 */
 
-	if (fmt->fourcc == V4L2_PIX_FMT_NV12)
+	if (fmt->fourcc == V4L2_PIX_FMT_NV12 ||
+	    fmt->fourcc == V4L2_PIX_FMT_NV21)
 		cfg_mode = 0;
 
 	write_field(us1_reg0, cfg_mode, VPE_US_MODE_MASK, VPE_US_MODE_SHIFT);
@@ -696,7 +710,8 @@ static void set_line_modes(struct vpe_ctx *ctx)
 	struct vpe_fmt *fmt = ctx->q_data[Q_DATA_SRC].fmt;
 	int line_mode = 1;
 
-	if (fmt->fourcc == V4L2_PIX_FMT_NV12)
+	if (fmt->fourcc == V4L2_PIX_FMT_NV12 ||
+	    fmt->fourcc == V4L2_PIX_FMT_NV21)
 		line_mode = 0;		/* double lines to line buffer */
 
 	/* regs for now */
@@ -741,11 +756,12 @@ static void set_src_registers(struct vpe_ctx *ctx)
 static void set_dst_registers(struct vpe_ctx *ctx)
 {
 	struct vpe_mmr_adb *mmr_adb = ctx->mmr_adb.addr;
-	enum v4l2_colorspace clrspc = ctx->q_data[Q_DATA_DST].colorspace;
 	struct vpe_fmt *fmt = ctx->q_data[Q_DATA_DST].fmt;
+	const struct v4l2_format_info *finfo;
 	u32 val = 0;
 
-	if (clrspc == V4L2_COLORSPACE_SRGB) {
+	finfo = v4l2_format_info(fmt->fourcc);
+	if (v4l2_is_format_rgb(finfo)) {
 		val |= VPE_RGB_OUT_SELECT;
 		vpdma_set_bg_color(ctx->dev->vpdma,
 			(struct vpdma_data_format *)fmt->vpdma_fmt[0], 0xff);
@@ -758,7 +774,8 @@ static void set_dst_registers(struct vpe_ctx *ctx)
 	 */
 	val |= VPE_DS_SRC_DEI_SCALER | VPE_CSC_SRC_DEI_SCALER;
 
-	if (fmt->fourcc != V4L2_PIX_FMT_NV12)
+	if (fmt->fourcc != V4L2_PIX_FMT_NV12 &&
+	    fmt->fourcc != V4L2_PIX_FMT_NV21)
 		val |= VPE_DS_BYPASS;
 
 	mmr_adb->out_fmt_reg[0] = val;
@@ -847,11 +864,13 @@ static int set_srcdst_params(struct vpe_ctx *ctx)
 	unsigned int src_h = s_q_data->c_rect.height;
 	unsigned int dst_w = d_q_data->c_rect.width;
 	unsigned int dst_h = d_q_data->c_rect.height;
+	struct v4l2_pix_format_mplane *spix;
 	size_t mv_buf_size;
 	int ret;
 
 	ctx->sequence = 0;
 	ctx->field = V4L2_FIELD_TOP;
+	spix = &s_q_data->format.fmt.pix_mp;
 
 	if ((s_q_data->flags & Q_IS_INTERLACED) &&
 			!(d_q_data->flags & Q_IS_INTERLACED)) {
@@ -866,9 +885,9 @@ static int set_srcdst_params(struct vpe_ctx *ctx)
 		 * extra space will not be used by the de-interlacer, but will
 		 * ensure that vpdma operates correctly
 		 */
-		bytes_per_line = ALIGN((s_q_data->width * mv->depth) >> 3,
-					VPDMA_STRIDE_ALIGN);
-		mv_buf_size = bytes_per_line * s_q_data->height;
+		bytes_per_line = ALIGN((spix->width * mv->depth) >> 3,
+				       VPDMA_STRIDE_ALIGN);
+		mv_buf_size = bytes_per_line * spix->height;
 
 		ctx->deinterlacing = true;
 		src_h <<= 1;
@@ -888,7 +907,7 @@ static int set_srcdst_params(struct vpe_ctx *ctx)
 	set_dei_regs(ctx);
 
 	csc_set_coeff(ctx->dev->csc, &mmr_adb->csc_regs[0],
-		s_q_data->colorspace, d_q_data->colorspace);
+		      &s_q_data->format, &d_q_data->format);
 
 	sc_set_hs_coeffs(ctx->dev->sc, ctx->sc_coeff_h.addr, src_w, dst_w);
 	sc_set_vs_coeffs(ctx->dev->sc, ctx->sc_coeff_v.addr, src_h, dst_h);
@@ -901,14 +920,6 @@ static int set_srcdst_params(struct vpe_ctx *ctx)
 }
 
 /*
- * Return the vpe_ctx structure for a given struct file
- */
-static struct vpe_ctx *file2ctx(struct file *file)
-{
-	return container_of(file->private_data, struct vpe_ctx, fh);
-}
-
-/*
  * mem2mem callbacks
  */
 
@@ -1010,27 +1021,33 @@ static void add_out_dtd(struct vpe_ctx *ctx, int port)
 	struct vpe_fmt *fmt = q_data->fmt;
 	const struct vpdma_data_format *vpdma_fmt;
 	int mv_buf_selector = !ctx->src_mv_buf_selector;
+	struct v4l2_pix_format_mplane *pix;
 	dma_addr_t dma_addr;
 	u32 flags = 0;
 	u32 offset = 0;
+	u32 stride;
 
 	if (port == VPE_PORT_MV_OUT) {
 		vpdma_fmt = &vpdma_misc_fmts[VPDMA_DATA_FMT_MV];
 		dma_addr = ctx->mv_buf_dma[mv_buf_selector];
 		q_data = &ctx->q_data[Q_DATA_SRC];
+		pix = &q_data->format.fmt.pix_mp;
+		stride = ALIGN((pix->width * vpdma_fmt->depth) >> 3,
+			       VPDMA_STRIDE_ALIGN);
 	} else {
 		/* to incorporate interleaved formats */
 		int plane = fmt->coplanar ? p_data->vb_part : 0;
 
+		pix = &q_data->format.fmt.pix_mp;
 		vpdma_fmt = fmt->vpdma_fmt[plane];
 		/*
 		 * If we are using a single plane buffer and
 		 * we need to set a separate vpdma chroma channel.
 		 */
-		if (q_data->nplanes == 1 && plane) {
+		if (pix->num_planes == 1 && plane) {
 			dma_addr = vb2_dma_contig_plane_dma_addr(vb, 0);
 			/* Compute required offset */
-			offset = q_data->bytesperline[0] * q_data->height;
+			offset = pix->plane_fmt[0].bytesperline * pix->height;
 		} else {
 			dma_addr = vb2_dma_contig_plane_dma_addr(vb, plane);
 			/* Use address as is, no offset */
@@ -1044,6 +1061,7 @@ static void add_out_dtd(struct vpe_ctx *ctx, int port)
 		}
 		/* Apply the offset */
 		dma_addr += offset;
+		stride = pix->plane_fmt[VPE_LUMA].bytesperline;
 	}
 
 	if (q_data->flags & Q_DATA_FRAME_1D)
@@ -1054,8 +1072,8 @@ static void add_out_dtd(struct vpe_ctx *ctx, int port)
 	vpdma_set_max_size(ctx->dev->vpdma, VPDMA_MAX_SIZE1,
 			   MAX_W, MAX_H);
 
-	vpdma_add_out_dtd(&ctx->desc_list, q_data->width,
-			  q_data->bytesperline[VPE_LUMA], &q_data->c_rect,
+	vpdma_add_out_dtd(&ctx->desc_list, pix->width,
+			  stride, &q_data->c_rect,
 			  vpdma_fmt, dma_addr, MAX_OUT_WIDTH_REG1,
 			  MAX_OUT_HEIGHT_REG1, p_data->channel, flags);
 }
@@ -1067,6 +1085,7 @@ static void add_in_dtd(struct vpe_ctx *ctx, int port)
 	struct vb2_buffer *vb = &ctx->src_vbs[p_data->vb_index]->vb2_buf;
 	struct vb2_v4l2_buffer *vbuf = to_vb2_v4l2_buffer(vb);
 	struct vpe_fmt *fmt = q_data->fmt;
+	struct v4l2_pix_format_mplane *pix;
 	const struct vpdma_data_format *vpdma_fmt;
 	int mv_buf_selector = ctx->src_mv_buf_selector;
 	int field = vbuf->field == V4L2_FIELD_BOTTOM;
@@ -1074,10 +1093,14 @@ static void add_in_dtd(struct vpe_ctx *ctx, int port)
 	dma_addr_t dma_addr;
 	u32 flags = 0;
 	u32 offset = 0;
+	u32 stride;
 
+	pix = &q_data->format.fmt.pix_mp;
 	if (port == VPE_PORT_MV_IN) {
 		vpdma_fmt = &vpdma_misc_fmts[VPDMA_DATA_FMT_MV];
 		dma_addr = ctx->mv_buf_dma[mv_buf_selector];
+		stride = ALIGN((pix->width * vpdma_fmt->depth) >> 3,
+			       VPDMA_STRIDE_ALIGN);
 	} else {
 		/* to incorporate interleaved formats */
 		int plane = fmt->coplanar ? p_data->vb_part : 0;
@@ -1087,10 +1110,10 @@ static void add_in_dtd(struct vpe_ctx *ctx, int port)
 		 * If we are using a single plane buffer and
 		 * we need to set a separate vpdma chroma channel.
 		 */
-		if (q_data->nplanes == 1 && plane) {
+		if (pix->num_planes == 1 && plane) {
 			dma_addr = vb2_dma_contig_plane_dma_addr(vb, 0);
 			/* Compute required offset */
-			offset = q_data->bytesperline[0] * q_data->height;
+			offset = pix->plane_fmt[0].bytesperline * pix->height;
 		} else {
 			dma_addr = vb2_dma_contig_plane_dma_addr(vb, plane);
 			/* Use address as is, no offset */
@@ -1104,26 +1127,39 @@ static void add_in_dtd(struct vpe_ctx *ctx, int port)
 		}
 		/* Apply the offset */
 		dma_addr += offset;
+		stride = pix->plane_fmt[VPE_LUMA].bytesperline;
 
-		if (q_data->flags & Q_DATA_INTERLACED_SEQ_TB) {
-			/*
-			 * Use top or bottom field from same vb alternately
-			 * f,f-1,f-2 = TBT when seq is even
-			 * f,f-1,f-2 = BTB when seq is odd
-			 */
-			field = (p_data->vb_index + (ctx->sequence % 2)) % 2;
+		/*
+		 * field used in VPDMA desc  = 0 (top) / 1 (bottom)
+		 * Use top or bottom field from same vb alternately
+		 * For each de-interlacing operation, f,f-1,f-2 should be one
+		 * of TBT or BTB
+		 */
+		if (q_data->flags & Q_DATA_INTERLACED_SEQ_TB ||
+		    q_data->flags & Q_DATA_INTERLACED_SEQ_BT) {
+			/* Select initial value based on format */
+			if (q_data->flags & Q_DATA_INTERLACED_SEQ_BT)
+				field = 1;
+			else
+				field = 0;
+
+			/* Toggle for each vb_index and each operation */
+			field = (field + p_data->vb_index + ctx->sequence) % 2;
 
 			if (field) {
-				/*
-				 * bottom field of a SEQ_TB buffer
-				 * Skip the top field data by
-				 */
-				int height = q_data->height / 2;
-				int bpp = fmt->fourcc == V4L2_PIX_FMT_NV12 ?
-						1 : (vpdma_fmt->depth >> 3);
+				int height = pix->height / 2;
+				int bpp;
+
+				if (fmt->fourcc == V4L2_PIX_FMT_NV12 ||
+				    fmt->fourcc == V4L2_PIX_FMT_NV21)
+					bpp = 1;
+				else
+					bpp = vpdma_fmt->depth >> 3;
+
 				if (plane)
 					height /= 2;
-				dma_addr += q_data->width * height * bpp;
+
+				dma_addr += pix->width * height * bpp;
 			}
 		}
 	}
@@ -1136,13 +1172,14 @@ static void add_in_dtd(struct vpe_ctx *ctx, int port)
 	frame_width = q_data->c_rect.width;
 	frame_height = q_data->c_rect.height;
 
-	if (p_data->vb_part && fmt->fourcc == V4L2_PIX_FMT_NV12)
+	if (p_data->vb_part && (fmt->fourcc == V4L2_PIX_FMT_NV12 ||
+				fmt->fourcc == V4L2_PIX_FMT_NV21))
 		frame_height /= 2;
 
-	vpdma_add_in_dtd(&ctx->desc_list, q_data->width,
-			 q_data->bytesperline[VPE_LUMA], &q_data->c_rect,
-		vpdma_fmt, dma_addr, p_data->channel, field, flags, frame_width,
-		frame_height, 0, 0);
+	vpdma_add_in_dtd(&ctx->desc_list, pix->width, stride,
+			 &q_data->c_rect, vpdma_fmt, dma_addr,
+			 p_data->channel, field, flags, frame_width,
+			 frame_height, 0, 0);
 }
 
 /*
@@ -1176,13 +1213,18 @@ static void device_run(void *priv)
 	struct sc_data *sc = ctx->dev->sc;
 	struct vpe_q_data *d_q_data = &ctx->q_data[Q_DATA_DST];
 	struct vpe_q_data *s_q_data = &ctx->q_data[Q_DATA_SRC];
-
-	if (ctx->deinterlacing && s_q_data->flags & Q_DATA_INTERLACED_SEQ_TB &&
-		ctx->sequence % 2 == 0) {
-		/* When using SEQ_TB buffers, When using it first time,
-		 * No need to remove the buffer as the next field is present
-		 * in the same buffer. (so that job_ready won't fail)
-		 * It will be removed when using bottom field
+	const struct v4l2_format_info *d_finfo;
+
+	d_finfo = v4l2_format_info(d_q_data->fmt->fourcc);
+
+	if (ctx->deinterlacing && s_q_data->flags & Q_IS_SEQ_XX &&
+	    ctx->sequence % 2 == 0) {
+		/* When using SEQ_XX type buffers, each buffer has two fields
+		 * each buffer has two fields (top & bottom)
+		 * Removing one buffer is actually getting two fields
+		 * Alternate between two operations:-
+		 * Even : consume one field but DO NOT REMOVE from queue
+		 * Odd : consume other field and REMOVE from queue
 		 */
 		ctx->src_vbs[0] = v4l2_m2m_next_src_buf(ctx->fh.m2m_ctx);
 		WARN_ON(ctx->src_vbs[0] == NULL);
@@ -1246,7 +1288,7 @@ static void device_run(void *priv)
 	if (ctx->deinterlacing)
 		add_out_dtd(ctx, VPE_PORT_MV_OUT);
 
-	if (d_q_data->colorspace == V4L2_COLORSPACE_SRGB) {
+	if (v4l2_is_format_rgb(d_finfo)) {
 		add_out_dtd(ctx, VPE_PORT_RGB_OUT);
 	} else {
 		add_out_dtd(ctx, VPE_PORT_LUMA_OUT);
@@ -1288,7 +1330,7 @@ static void device_run(void *priv)
 	}
 
 	/* sync on channel control descriptors for output ports */
-	if (d_q_data->colorspace == V4L2_COLORSPACE_SRGB) {
+	if (v4l2_is_format_rgb(d_finfo)) {
 		vpdma_add_sync_on_channel_ctd(&ctx->desc_list,
 			VPE_CHAN_RGB_OUT);
 	} else {
@@ -1391,9 +1433,6 @@ static irqreturn_t vpe_irq(int irq_vpe, void *data)
 	 /* the previous dst mv buffer becomes the next src mv buffer */
 	ctx->src_mv_buf_selector = !ctx->src_mv_buf_selector;
 
-	if (ctx->aborting)
-		goto finished;
-
 	s_vb = ctx->src_vbs[0];
 	d_vb = ctx->dst_vb;
 
@@ -1404,6 +1443,7 @@ static irqreturn_t vpe_irq(int irq_vpe, void *data)
 		d_vb->timecode = s_vb->timecode;
 
 	d_vb->sequence = ctx->sequence;
+	s_vb->sequence = ctx->sequence;
 
 	d_q_data = &ctx->q_data[Q_DATA_DST];
 	if (d_q_data->flags & Q_IS_INTERLACED) {
@@ -1457,6 +1497,9 @@ static irqreturn_t vpe_irq(int irq_vpe, void *data)
 	ctx->src_vbs[0] = NULL;
 	ctx->dst_vb = NULL;
 
+	if (ctx->aborting)
+		goto finished;
+
 	ctx->bufs_completed++;
 	if (ctx->bufs_completed < ctx->bufs_per_job && job_ready(ctx)) {
 		device_run(ctx);
@@ -1519,38 +1562,32 @@ static int vpe_enum_fmt(struct file *file, void *priv,
 static int vpe_g_fmt(struct file *file, void *priv, struct v4l2_format *f)
 {
 	struct v4l2_pix_format_mplane *pix = &f->fmt.pix_mp;
-	struct vpe_ctx *ctx = file2ctx(file);
+	struct vpe_ctx *ctx = file->private_data;
 	struct vb2_queue *vq;
 	struct vpe_q_data *q_data;
-	int i;
 
 	vq = v4l2_m2m_get_vq(ctx->fh.m2m_ctx, f->type);
 	if (!vq)
 		return -EINVAL;
 
 	q_data = get_q_data(ctx, f->type);
+	if (!q_data)
+		return -EINVAL;
 
-	pix->width = q_data->width;
-	pix->height = q_data->height;
-	pix->pixelformat = q_data->fmt->fourcc;
-	pix->field = q_data->field;
+	*f = q_data->format;
 
-	if (V4L2_TYPE_IS_OUTPUT(f->type)) {
-		pix->colorspace = q_data->colorspace;
-	} else {
+	if (!V4L2_TYPE_IS_OUTPUT(f->type)) {
 		struct vpe_q_data *s_q_data;
+		struct v4l2_pix_format_mplane *spix;
 
-		/* get colorspace from the source queue */
+		/* get colorimetry from the source queue */
 		s_q_data = get_q_data(ctx, V4L2_BUF_TYPE_VIDEO_OUTPUT_MPLANE);
+		spix = &s_q_data->format.fmt.pix_mp;
 
-		pix->colorspace = s_q_data->colorspace;
-	}
-
-	pix->num_planes = q_data->nplanes;
-
-	for (i = 0; i < pix->num_planes; i++) {
-		pix->plane_fmt[i].bytesperline = q_data->bytesperline[i];
-		pix->plane_fmt[i].sizeimage = q_data->sizeimage[i];
+		pix->colorspace = spix->colorspace;
+		pix->xfer_func = spix->xfer_func;
+		pix->ycbcr_enc = spix->ycbcr_enc;
+		pix->quantization = spix->quantization;
 	}
 
 	return 0;
@@ -1564,15 +1601,18 @@ static int __vpe_try_fmt(struct vpe_ctx *ctx, struct v4l2_format *f,
 	unsigned int w_align;
 	int i, depth, depth_bytes, height;
 	unsigned int stride = 0;
+	const struct v4l2_format_info *finfo;
 
 	if (!fmt || !(fmt->types & type)) {
-		vpe_err(ctx->dev, "Fourcc format (0x%08x) invalid.\n",
+		vpe_dbg(ctx->dev, "Fourcc format (0x%08x) invalid.\n",
 			pix->pixelformat);
-		return -EINVAL;
+		fmt = __find_format(V4L2_PIX_FMT_YUYV);
 	}
 
-	if (pix->field != V4L2_FIELD_NONE && pix->field != V4L2_FIELD_ALTERNATE
-			&& pix->field != V4L2_FIELD_SEQ_TB)
+	if (pix->field != V4L2_FIELD_NONE &&
+	    pix->field != V4L2_FIELD_ALTERNATE &&
+	    pix->field != V4L2_FIELD_SEQ_TB &&
+	    pix->field != V4L2_FIELD_SEQ_BT)
 		pix->field = V4L2_FIELD_NONE;
 
 	depth = fmt->vpdma_fmt[VPE_LUMA]->depth;
@@ -1615,27 +1655,25 @@ static int __vpe_try_fmt(struct vpe_ctx *ctx, struct v4l2_format *f,
 			      &pix->height, MIN_H, MAX_H, H_ALIGN,
 			      S_ALIGN);
 
-	if (!pix->num_planes)
+	if (!pix->num_planes || pix->num_planes > 2)
 		pix->num_planes = fmt->coplanar ? 2 : 1;
 	else if (pix->num_planes > 1 && !fmt->coplanar)
 		pix->num_planes = 1;
 
 	pix->pixelformat = fmt->fourcc;
+	finfo = v4l2_format_info(fmt->fourcc);
 
 	/*
 	 * For the actual image parameters, we need to consider the field
-	 * height of the image for SEQ_TB buffers.
+	 * height of the image for SEQ_XX buffers.
 	 */
-	if (pix->field == V4L2_FIELD_SEQ_TB)
+	if (pix->field == V4L2_FIELD_SEQ_TB || pix->field == V4L2_FIELD_SEQ_BT)
 		height = pix->height / 2;
 	else
 		height = pix->height;
 
 	if (!pix->colorspace) {
-		if (fmt->fourcc == V4L2_PIX_FMT_RGB24 ||
-				fmt->fourcc == V4L2_PIX_FMT_BGR24 ||
-				fmt->fourcc == V4L2_PIX_FMT_RGB32 ||
-				fmt->fourcc == V4L2_PIX_FMT_BGR32) {
+		if (v4l2_is_format_rgb(finfo)) {
 			pix->colorspace = V4L2_COLORSPACE_SRGB;
 		} else {
 			if (height > 1280)	/* HD */
@@ -1654,6 +1692,10 @@ static int __vpe_try_fmt(struct vpe_ctx *ctx, struct v4l2_format *f,
 		if (stride > plane_fmt->bytesperline)
 			plane_fmt->bytesperline = stride;
 
+		plane_fmt->bytesperline = clamp_t(u32, plane_fmt->bytesperline,
+						  stride,
+						  VPDMA_MAX_STRIDE);
+
 		plane_fmt->bytesperline = ALIGN(plane_fmt->bytesperline,
 						VPDMA_STRIDE_ALIGN);
 
@@ -1679,7 +1721,7 @@ static int __vpe_try_fmt(struct vpe_ctx *ctx, struct v4l2_format *f,
 
 static int vpe_try_fmt(struct file *file, void *priv, struct v4l2_format *f)
 {
-	struct vpe_ctx *ctx = file2ctx(file);
+	struct vpe_ctx *ctx = file->private_data;
 	struct vpe_fmt *fmt = find_format(f);
 
 	if (V4L2_TYPE_IS_OUTPUT(f->type))
@@ -1691,10 +1733,9 @@ static int vpe_try_fmt(struct file *file, void *priv, struct v4l2_format *f)
 static int __vpe_s_fmt(struct vpe_ctx *ctx, struct v4l2_format *f)
 {
 	struct v4l2_pix_format_mplane *pix = &f->fmt.pix_mp;
-	struct v4l2_plane_pix_format *plane_fmt;
+	struct v4l2_pix_format_mplane *qpix;
 	struct vpe_q_data *q_data;
 	struct vb2_queue *vq;
-	int i;
 
 	vq = v4l2_m2m_get_vq(ctx->fh.m2m_ctx, f->type);
 	if (!vq)
@@ -1709,42 +1750,34 @@ static int __vpe_s_fmt(struct vpe_ctx *ctx, struct v4l2_format *f)
 	if (!q_data)
 		return -EINVAL;
 
+	qpix = &q_data->format.fmt.pix_mp;
 	q_data->fmt		= find_format(f);
-	q_data->width		= pix->width;
-	q_data->height		= pix->height;
-	q_data->colorspace	= pix->colorspace;
-	q_data->field		= pix->field;
-	q_data->nplanes		= pix->num_planes;
-
-	for (i = 0; i < pix->num_planes; i++) {
-		plane_fmt = &pix->plane_fmt[i];
-
-		q_data->bytesperline[i]	= plane_fmt->bytesperline;
-		q_data->sizeimage[i]	= plane_fmt->sizeimage;
-	}
+	q_data->format = *f;
 
 	q_data->c_rect.left	= 0;
 	q_data->c_rect.top	= 0;
-	q_data->c_rect.width	= q_data->width;
-	q_data->c_rect.height	= q_data->height;
+	q_data->c_rect.width	= pix->width;
+	q_data->c_rect.height	= pix->height;
 
-	if (q_data->field == V4L2_FIELD_ALTERNATE)
+	if (qpix->field == V4L2_FIELD_ALTERNATE)
 		q_data->flags |= Q_DATA_INTERLACED_ALTERNATE;
-	else if (q_data->field == V4L2_FIELD_SEQ_TB)
+	else if (qpix->field == V4L2_FIELD_SEQ_TB)
 		q_data->flags |= Q_DATA_INTERLACED_SEQ_TB;
+	else if (qpix->field == V4L2_FIELD_SEQ_BT)
+		q_data->flags |= Q_DATA_INTERLACED_SEQ_BT;
 	else
 		q_data->flags &= ~Q_IS_INTERLACED;
 
-	/* the crop height is halved for the case of SEQ_TB buffers */
-	if (q_data->flags & Q_DATA_INTERLACED_SEQ_TB)
+	/* the crop height is halved for the case of SEQ_XX buffers */
+	if (q_data->flags & Q_IS_SEQ_XX)
 		q_data->c_rect.height /= 2;
 
 	vpe_dbg(ctx->dev, "Setting format for type %d, wxh: %dx%d, fmt: %d bpl_y %d",
-		f->type, q_data->width, q_data->height, q_data->fmt->fourcc,
-		q_data->bytesperline[VPE_LUMA]);
-	if (q_data->nplanes == 2)
+		f->type, pix->width, pix->height, pix->pixelformat,
+		pix->plane_fmt[0].bytesperline);
+	if (pix->num_planes == 2)
 		vpe_dbg(ctx->dev, " bpl_uv %d\n",
-			q_data->bytesperline[VPE_CHROMA]);
+			pix->plane_fmt[1].bytesperline);
 
 	return 0;
 }
@@ -1752,7 +1785,7 @@ static int __vpe_s_fmt(struct vpe_ctx *ctx, struct v4l2_format *f)
 static int vpe_s_fmt(struct file *file, void *priv, struct v4l2_format *f)
 {
 	int ret;
-	struct vpe_ctx *ctx = file2ctx(file);
+	struct vpe_ctx *ctx = file->private_data;
 
 	ret = vpe_try_fmt(file, priv, f);
 	if (ret)
@@ -1773,6 +1806,7 @@ static int vpe_s_fmt(struct file *file, void *priv, struct v4l2_format *f)
 static int __vpe_try_selection(struct vpe_ctx *ctx, struct v4l2_selection *s)
 {
 	struct vpe_q_data *q_data;
+	struct v4l2_pix_format_mplane *pix;
 	int height;
 
 	if ((s->type != V4L2_BUF_TYPE_VIDEO_CAPTURE) &&
@@ -1783,6 +1817,8 @@ static int __vpe_try_selection(struct vpe_ctx *ctx, struct v4l2_selection *s)
 	if (!q_data)
 		return -EINVAL;
 
+	pix = &q_data->format.fmt.pix_mp;
+
 	switch (s->target) {
 	case V4L2_SEL_TGT_COMPOSE:
 		/*
@@ -1809,27 +1845,27 @@ static int __vpe_try_selection(struct vpe_ctx *ctx, struct v4l2_selection *s)
 	}
 
 	/*
-	 * For SEQ_TB buffers, crop height should be less than the height of
+	 * For SEQ_XX buffers, crop height should be less than the height of
 	 * the field height, not the buffer height
 	 */
-	if (q_data->flags & Q_DATA_INTERLACED_SEQ_TB)
-		height = q_data->height / 2;
+	if (q_data->flags & Q_IS_SEQ_XX)
+		height = pix->height / 2;
 	else
-		height = q_data->height;
+		height = pix->height;
 
 	if (s->r.top < 0 || s->r.left < 0) {
 		vpe_err(ctx->dev, "negative values for top and left\n");
 		s->r.top = s->r.left = 0;
 	}
 
-	v4l_bound_align_image(&s->r.width, MIN_W, q_data->width, 1,
+	v4l_bound_align_image(&s->r.width, MIN_W, pix->width, 1,
 		&s->r.height, MIN_H, height, H_ALIGN, S_ALIGN);
 
 	/* adjust left/top if cropping rectangle is out of bounds */
-	if (s->r.left + s->r.width > q_data->width)
-		s->r.left = q_data->width - s->r.width;
-	if (s->r.top + s->r.height > q_data->height)
-		s->r.top = q_data->height - s->r.height;
+	if (s->r.left + s->r.width > pix->width)
+		s->r.left = pix->width - s->r.width;
+	if (s->r.top + s->r.height > pix->height)
+		s->r.top = pix->height - s->r.height;
 
 	return 0;
 }
@@ -1837,8 +1873,9 @@ static int __vpe_try_selection(struct vpe_ctx *ctx, struct v4l2_selection *s)
 static int vpe_g_selection(struct file *file, void *fh,
 		struct v4l2_selection *s)
 {
-	struct vpe_ctx *ctx = file2ctx(file);
+	struct vpe_ctx *ctx = file->private_data;
 	struct vpe_q_data *q_data;
+	struct v4l2_pix_format_mplane *pix;
 	bool use_c_rect = false;
 
 	if ((s->type != V4L2_BUF_TYPE_VIDEO_CAPTURE) &&
@@ -1849,6 +1886,8 @@ static int vpe_g_selection(struct file *file, void *fh,
 	if (!q_data)
 		return -EINVAL;
 
+	pix = &q_data->format.fmt.pix_mp;
+
 	switch (s->target) {
 	case V4L2_SEL_TGT_COMPOSE_DEFAULT:
 	case V4L2_SEL_TGT_COMPOSE_BOUNDS:
@@ -1887,8 +1926,8 @@ static int vpe_g_selection(struct file *file, void *fh,
 		 */
 		s->r.left = 0;
 		s->r.top = 0;
-		s->r.width = q_data->width;
-		s->r.height = q_data->height;
+		s->r.width = pix->width;
+		s->r.height = pix->height;
 	}
 
 	return 0;
@@ -1898,7 +1937,7 @@ static int vpe_g_selection(struct file *file, void *fh,
 static int vpe_s_selection(struct file *file, void *fh,
 		struct v4l2_selection *s)
 {
-	struct vpe_ctx *ctx = file2ctx(file);
+	struct vpe_ctx *ctx = file->private_data;
 	struct vpe_q_data *q_data;
 	struct v4l2_selection sel = *s;
 	int ret;
@@ -1991,17 +2030,21 @@ static int vpe_queue_setup(struct vb2_queue *vq,
 	int i;
 	struct vpe_ctx *ctx = vb2_get_drv_priv(vq);
 	struct vpe_q_data *q_data;
+	struct v4l2_pix_format_mplane *pix;
 
 	q_data = get_q_data(ctx, vq->type);
+	if (!q_data)
+		return -EINVAL;
 
-	*nplanes = q_data->nplanes;
+	pix = &q_data->format.fmt.pix_mp;
+	*nplanes = pix->num_planes;
 
 	for (i = 0; i < *nplanes; i++)
-		sizes[i] = q_data->sizeimage[i];
+		sizes[i] = pix->plane_fmt[i].sizeimage;
 
 	vpe_dbg(ctx->dev, "get %d buffer(s) of size %d", *nbuffers,
 		sizes[VPE_LUMA]);
-	if (q_data->nplanes == 2)
+	if (*nplanes == 2)
 		vpe_dbg(ctx->dev, " and %d\n", sizes[VPE_CHROMA]);
 
 	return 0;
@@ -2012,12 +2055,16 @@ static int vpe_buf_prepare(struct vb2_buffer *vb)
 	struct vb2_v4l2_buffer *vbuf = to_vb2_v4l2_buffer(vb);
 	struct vpe_ctx *ctx = vb2_get_drv_priv(vb->vb2_queue);
 	struct vpe_q_data *q_data;
-	int i, num_planes;
+	struct v4l2_pix_format_mplane *pix;
+	int i;
 
 	vpe_dbg(ctx->dev, "type: %d\n", vb->vb2_queue->type);
 
 	q_data = get_q_data(ctx, vb->vb2_queue->type);
-	num_planes = q_data->nplanes;
+	if (!q_data)
+		return -EINVAL;
+
+	pix = &q_data->format.fmt.pix_mp;
 
 	if (vb->vb2_queue->type == V4L2_BUF_TYPE_VIDEO_OUTPUT_MPLANE) {
 		if (!(q_data->flags & Q_IS_INTERLACED)) {
@@ -2025,23 +2072,24 @@ static int vpe_buf_prepare(struct vb2_buffer *vb)
 		} else {
 			if (vbuf->field != V4L2_FIELD_TOP &&
 			    vbuf->field != V4L2_FIELD_BOTTOM &&
-			    vbuf->field != V4L2_FIELD_SEQ_TB)
+			    vbuf->field != V4L2_FIELD_SEQ_TB &&
+			    vbuf->field != V4L2_FIELD_SEQ_BT)
 				return -EINVAL;
 		}
 	}
 
-	for (i = 0; i < num_planes; i++) {
-		if (vb2_plane_size(vb, i) < q_data->sizeimage[i]) {
+	for (i = 0; i < pix->num_planes; i++) {
+		if (vb2_plane_size(vb, i) < pix->plane_fmt[i].sizeimage) {
 			vpe_err(ctx->dev,
 				"data will not fit into plane (%lu < %lu)\n",
 				vb2_plane_size(vb, i),
-				(long) q_data->sizeimage[i]);
+				(long)pix->plane_fmt[i].sizeimage);
 			return -EINVAL;
 		}
 	}
 
-	for (i = 0; i < num_planes; i++)
-		vb2_set_plane_payload(vb, i, q_data->sizeimage[i]);
+	for (i = 0; i < pix->num_planes; i++)
+		vb2_set_plane_payload(vb, i, pix->plane_fmt[i].sizeimage);
 
 	return 0;
 }
@@ -2226,6 +2274,7 @@ static int vpe_open(struct file *file)
 	struct vpe_q_data *s_q_data;
 	struct v4l2_ctrl_handler *hdl;
 	struct vpe_ctx *ctx;
+	struct v4l2_pix_format_mplane *pix;
 	int ret;
 
 	vpe_dbg(dev, "vpe_open\n");
@@ -2261,7 +2310,7 @@ static int vpe_open(struct file *file)
 	init_adb_hdrs(ctx);
 
 	v4l2_fh_init(&ctx->fh, video_devdata(file));
-	file->private_data = &ctx->fh;
+	file->private_data = ctx;
 
 	hdl = &ctx->hdl;
 	v4l2_ctrl_handler_init(hdl, 1);
@@ -2274,23 +2323,32 @@ static int vpe_open(struct file *file)
 	v4l2_ctrl_handler_setup(hdl);
 
 	s_q_data = &ctx->q_data[Q_DATA_SRC];
-	s_q_data->fmt = &vpe_formats[2];
-	s_q_data->width = 1920;
-	s_q_data->height = 1080;
-	s_q_data->nplanes = 1;
-	s_q_data->bytesperline[VPE_LUMA] = (s_q_data->width *
+	pix = &s_q_data->format.fmt.pix_mp;
+	s_q_data->fmt = __find_format(V4L2_PIX_FMT_YUYV);
+	pix->pixelformat = s_q_data->fmt->fourcc;
+	s_q_data->format.type = V4L2_BUF_TYPE_VIDEO_OUTPUT_MPLANE;
+	pix->width = 1920;
+	pix->height = 1080;
+	pix->num_planes = 1;
+	pix->plane_fmt[VPE_LUMA].bytesperline = (pix->width *
 			s_q_data->fmt->vpdma_fmt[VPE_LUMA]->depth) >> 3;
-	s_q_data->sizeimage[VPE_LUMA] = (s_q_data->bytesperline[VPE_LUMA] *
-			s_q_data->height);
-	s_q_data->colorspace = V4L2_COLORSPACE_REC709;
-	s_q_data->field = V4L2_FIELD_NONE;
+	pix->plane_fmt[VPE_LUMA].sizeimage =
+			pix->plane_fmt[VPE_LUMA].bytesperline *
+			pix->height;
+	pix->colorspace = V4L2_COLORSPACE_REC709;
+	pix->xfer_func = V4L2_XFER_FUNC_DEFAULT;
+	pix->ycbcr_enc = V4L2_YCBCR_ENC_DEFAULT;
+	pix->quantization = V4L2_QUANTIZATION_DEFAULT;
+	pix->field = V4L2_FIELD_NONE;
 	s_q_data->c_rect.left = 0;
 	s_q_data->c_rect.top = 0;
-	s_q_data->c_rect.width = s_q_data->width;
-	s_q_data->c_rect.height = s_q_data->height;
+	s_q_data->c_rect.width = pix->width;
+	s_q_data->c_rect.height = pix->height;
 	s_q_data->flags = 0;
 
 	ctx->q_data[Q_DATA_DST] = *s_q_data;
+	ctx->q_data[Q_DATA_DST].format.type =
+			V4L2_BUF_TYPE_VIDEO_CAPTURE_MPLANE;
 
 	set_dei_shadow_registers(ctx);
 	set_src_registers(ctx);
@@ -2346,12 +2404,18 @@ free_ctx:
 static int vpe_release(struct file *file)
 {
 	struct vpe_dev *dev = video_drvdata(file);
-	struct vpe_ctx *ctx = file2ctx(file);
+	struct vpe_ctx *ctx = file->private_data;
 
 	vpe_dbg(dev, "releasing instance %p\n", ctx);
 
 	mutex_lock(&dev->dev_mutex);
 	free_mv_buffers(ctx);
+
+	vpdma_unmap_desc_buf(dev->vpdma, &ctx->desc_list.buf);
+	vpdma_unmap_desc_buf(dev->vpdma, &ctx->mmr_adb);
+	vpdma_unmap_desc_buf(dev->vpdma, &ctx->sc_coeff_h);
+	vpdma_unmap_desc_buf(dev->vpdma, &ctx->sc_coeff_v);
+
 	vpdma_free_desc_list(&ctx->desc_list);
 	vpdma_free_desc_buf(&ctx->mmr_adb);
 
@@ -2459,6 +2523,13 @@ static int vpe_probe(struct platform_device *pdev)
 	struct vpe_dev *dev;
 	int ret, irq, func;
 
+	ret = dma_coerce_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(32));
+	if (ret) {
+		dev_err(&pdev->dev,
+			"32-bit consistent DMA enable failed\n");
+		return ret;
+	}
+
 	dev = devm_kzalloc(&pdev->dev, sizeof(*dev), GFP_KERNEL);
 	if (!dev)
 		return -ENOMEM;
@@ -2473,7 +2544,12 @@ static int vpe_probe(struct platform_device *pdev)
 	mutex_init(&dev->dev_mutex);
 
 	dev->res = platform_get_resource_byname(pdev, IORESOURCE_MEM,
-			"vpe_top");
+						"vpe_top");
+	if (!dev->res) {
+		dev_err(&pdev->dev, "missing 'vpe_top' resources data\n");
+		return -ENODEV;
+	}
+
 	/*
 	 * HACK: we get resource info from device tree in the form of a list of
 	 * VPE sub blocks, the driver currently uses only the base of vpe_top
@@ -2568,7 +2644,7 @@ static int vpe_remove(struct platform_device *pdev)
 #if defined(CONFIG_OF)
 static const struct of_device_id vpe_of_match[] = {
 	{
-		.compatible = "ti,vpe",
+		.compatible = "ti,dra7-vpe",
 	},
 	{},
 };
diff --git a/drivers/media/platform/vicodec/vicodec-core.c b/drivers/media/platform/vicodec/vicodec-core.c
index 0ee143ae0f6b..82350097503e 100644
--- a/drivers/media/platform/vicodec/vicodec-core.c
+++ b/drivers/media/platform/vicodec/vicodec-core.c
@@ -2139,6 +2139,9 @@ static void vicodec_v4l2_dev_release(struct v4l2_device *v4l2_dev)
 	v4l2_m2m_release(dev->stateful_enc.m2m_dev);
 	v4l2_m2m_release(dev->stateful_dec.m2m_dev);
 	v4l2_m2m_release(dev->stateless_dec.m2m_dev);
+#ifdef CONFIG_MEDIA_CONTROLLER
+	media_device_cleanup(&dev->mdev);
+#endif
 	kfree(dev);
 }
 
@@ -2250,7 +2253,6 @@ static int vicodec_remove(struct platform_device *pdev)
 	v4l2_m2m_unregister_media_controller(dev->stateful_enc.m2m_dev);
 	v4l2_m2m_unregister_media_controller(dev->stateful_dec.m2m_dev);
 	v4l2_m2m_unregister_media_controller(dev->stateless_dec.m2m_dev);
-	media_device_cleanup(&dev->mdev);
 #endif
 
 	video_unregister_device(&dev->stateful_enc.vfd);
diff --git a/drivers/media/platform/vim2m.c b/drivers/media/platform/vim2m.c
index acd3bd48c7e2..8d6b09623d88 100644
--- a/drivers/media/platform/vim2m.c
+++ b/drivers/media/platform/vim2m.c
@@ -1073,6 +1073,9 @@ static int vim2m_start_streaming(struct vb2_queue *q, unsigned int count)
 	if (!q_data)
 		return -EINVAL;
 
+	if (V4L2_TYPE_IS_OUTPUT(q->type))
+		ctx->aborting = 0;
+
 	q_data->sequence = 0;
 	return 0;
 }
@@ -1272,6 +1275,9 @@ static void vim2m_device_release(struct video_device *vdev)
 
 	v4l2_device_unregister(&dev->v4l2_dev);
 	v4l2_m2m_release(dev->m2m_dev);
+#ifdef CONFIG_MEDIA_CONTROLLER
+	media_device_cleanup(&dev->mdev);
+#endif
 	kfree(dev);
 }
 
@@ -1343,6 +1349,7 @@ static int vim2m_probe(struct platform_device *pdev)
 	if (IS_ERR(dev->m2m_dev)) {
 		v4l2_err(&dev->v4l2_dev, "Failed to init mem2mem device\n");
 		ret = PTR_ERR(dev->m2m_dev);
+		dev->m2m_dev = NULL;
 		goto error_dev;
 	}
 
@@ -1395,7 +1402,6 @@ static int vim2m_remove(struct platform_device *pdev)
 #ifdef CONFIG_MEDIA_CONTROLLER
 	media_device_unregister(&dev->mdev);
 	v4l2_m2m_unregister_media_controller(dev->m2m_dev);
-	media_device_cleanup(&dev->mdev);
 #endif
 	video_unregister_device(&dev->vfd);
 
diff --git a/drivers/media/platform/vimc/Makefile b/drivers/media/platform/vimc/Makefile
index 96d06f030c31..a53b2b532e9f 100644
--- a/drivers/media/platform/vimc/Makefile
+++ b/drivers/media/platform/vimc/Makefile
@@ -1,5 +1,6 @@
 # SPDX-License-Identifier: GPL-2.0
-vimc-y := vimc-core.o vimc-common.o vimc-streamer.o
+vimc-y := vimc-core.o vimc-common.o vimc-streamer.o vimc-capture.o \
+		vimc-debayer.o vimc-scaler.o vimc-sensor.o
+
+obj-$(CONFIG_VIDEO_VIMC) += vimc.o
 
-obj-$(CONFIG_VIDEO_VIMC) += vimc.o vimc-capture.o vimc-debayer.o \
-                vimc-scaler.o vimc-sensor.o
diff --git a/drivers/media/platform/vimc/vimc-capture.c b/drivers/media/platform/vimc/vimc-capture.c
index 1d56b91830ba..76c015898cfd 100644
--- a/drivers/media/platform/vimc/vimc-capture.c
+++ b/drivers/media/platform/vimc/vimc-capture.c
@@ -5,10 +5,6 @@
  * Copyright (C) 2015-2017 Helen Koike <helen.fornazier@gmail.com>
  */
 
-#include <linux/component.h>
-#include <linux/module.h>
-#include <linux/mod_devicetable.h>
-#include <linux/platform_device.h>
 #include <media/v4l2-ioctl.h>
 #include <media/videobuf2-core.h>
 #include <media/videobuf2-vmalloc.h>
@@ -16,12 +12,9 @@
 #include "vimc-common.h"
 #include "vimc-streamer.h"
 
-#define VIMC_CAP_DRV_NAME "vimc-capture"
-
 struct vimc_cap_device {
 	struct vimc_ent_device ved;
 	struct video_device vdev;
-	struct device *dev;
 	struct v4l2_pix_format format;
 	struct vb2_queue queue;
 	struct list_head buf_list;
@@ -36,6 +29,7 @@ struct vimc_cap_device {
 	struct mutex lock;
 	u32 sequence;
 	struct vimc_stream stream;
+	struct media_pad pad;
 };
 
 static const struct v4l2_pix_format fmt_default = {
@@ -130,7 +124,7 @@ static int vimc_cap_s_fmt_vid_cap(struct file *file, void *priv,
 	if (ret)
 		return ret;
 
-	dev_dbg(vcap->dev, "%s: format update: "
+	dev_dbg(vcap->ved.dev, "%s: format update: "
 		"old:%dx%d (0x%x, %d, %d, %d, %d) "
 		"new:%dx%d (0x%x, %d, %d, %d, %d)\n", vcap->vdev.name,
 		/* old */
@@ -306,7 +300,7 @@ static int vimc_cap_buffer_prepare(struct vb2_buffer *vb)
 	unsigned long size = vcap->format.sizeimage;
 
 	if (vb2_plane_size(vb, 0) < size) {
-		dev_err(vcap->dev, "%s: buffer too small (%lu < %lu)\n",
+		dev_err(vcap->ved.dev, "%s: buffer too small (%lu < %lu)\n",
 			vcap->vdev.name, vb2_plane_size(vb, 0), size);
 		return -EINVAL;
 	}
@@ -328,7 +322,7 @@ static const struct vb2_ops vimc_cap_qops = {
 };
 
 static const struct media_entity_operations vimc_cap_mops = {
-	.link_validate		= vimc_link_validate,
+	.link_validate		= vimc_vdev_link_validate,
 };
 
 static void vimc_cap_release(struct video_device *vdev)
@@ -336,19 +330,16 @@ static void vimc_cap_release(struct video_device *vdev)
 	struct vimc_cap_device *vcap =
 		container_of(vdev, struct vimc_cap_device, vdev);
 
-	vimc_pads_cleanup(vcap->ved.pads);
+	media_entity_cleanup(vcap->ved.ent);
 	kfree(vcap);
 }
 
-static void vimc_cap_comp_unbind(struct device *comp, struct device *master,
-				 void *master_data)
+void vimc_cap_rm(struct vimc_device *vimc, struct vimc_ent_device *ved)
 {
-	struct vimc_ent_device *ved = dev_get_drvdata(comp);
-	struct vimc_cap_device *vcap = container_of(ved, struct vimc_cap_device,
-						    ved);
+	struct vimc_cap_device *vcap;
 
+	vcap = container_of(ved, struct vimc_cap_device, ved);
 	vb2_queue_release(&vcap->queue);
-	media_entity_cleanup(ved->ent);
 	video_unregister_device(&vcap->vdev);
 }
 
@@ -391,11 +382,10 @@ static void *vimc_cap_process_frame(struct vimc_ent_device *ved,
 	return NULL;
 }
 
-static int vimc_cap_comp_bind(struct device *comp, struct device *master,
-			      void *master_data)
+struct vimc_ent_device *vimc_cap_add(struct vimc_device *vimc,
+				     const char *vcfg_name)
 {
-	struct v4l2_device *v4l2_dev = master_data;
-	struct vimc_platform_data *pdata = comp->platform_data;
+	struct v4l2_device *v4l2_dev = &vimc->v4l2_dev;
 	const struct vimc_pix_map *vpix;
 	struct vimc_cap_device *vcap;
 	struct video_device *vdev;
@@ -405,23 +395,16 @@ static int vimc_cap_comp_bind(struct device *comp, struct device *master,
 	/* Allocate the vimc_cap_device struct */
 	vcap = kzalloc(sizeof(*vcap), GFP_KERNEL);
 	if (!vcap)
-		return -ENOMEM;
-
-	/* Allocate the pads */
-	vcap->ved.pads =
-		vimc_pads_init(1, (const unsigned long[1]) {MEDIA_PAD_FL_SINK});
-	if (IS_ERR(vcap->ved.pads)) {
-		ret = PTR_ERR(vcap->ved.pads);
-		goto err_free_vcap;
-	}
+		return NULL;
 
 	/* Initialize the media entity */
-	vcap->vdev.entity.name = pdata->entity_name;
+	vcap->vdev.entity.name = vcfg_name;
 	vcap->vdev.entity.function = MEDIA_ENT_F_IO_V4L;
+	vcap->pad.flags = MEDIA_PAD_FL_SINK;
 	ret = media_entity_pads_init(&vcap->vdev.entity,
-				     1, vcap->ved.pads);
+				     1, &vcap->pad);
 	if (ret)
-		goto err_clean_pads;
+		goto err_free_vcap;
 
 	/* Initialize the lock */
 	mutex_init(&vcap->lock);
@@ -440,8 +423,8 @@ static int vimc_cap_comp_bind(struct device *comp, struct device *master,
 
 	ret = vb2_queue_init(q);
 	if (ret) {
-		dev_err(comp, "%s: vb2 queue init failed (err=%d)\n",
-			pdata->entity_name, ret);
+		dev_err(&vimc->pdev.dev, "%s: vb2 queue init failed (err=%d)\n",
+			vcfg_name, ret);
 		goto err_clean_m_ent;
 	}
 
@@ -460,8 +443,7 @@ static int vimc_cap_comp_bind(struct device *comp, struct device *master,
 	vcap->ved.ent = &vcap->vdev.entity;
 	vcap->ved.process_frame = vimc_cap_process_frame;
 	vcap->ved.vdev_get_format = vimc_cap_get_format;
-	dev_set_drvdata(comp, &vcap->ved);
-	vcap->dev = comp;
+	vcap->ved.dev = &vimc->pdev.dev;
 
 	/* Initialize the video_device struct */
 	vdev = &vcap->vdev;
@@ -474,68 +456,25 @@ static int vimc_cap_comp_bind(struct device *comp, struct device *master,
 	vdev->queue = q;
 	vdev->v4l2_dev = v4l2_dev;
 	vdev->vfl_dir = VFL_DIR_RX;
-	strscpy(vdev->name, pdata->entity_name, sizeof(vdev->name));
+	strscpy(vdev->name, vcfg_name, sizeof(vdev->name));
 	video_set_drvdata(vdev, &vcap->ved);
 
 	/* Register the video_device with the v4l2 and the media framework */
 	ret = video_register_device(vdev, VFL_TYPE_GRABBER, -1);
 	if (ret) {
-		dev_err(comp, "%s: video register failed (err=%d)\n",
+		dev_err(&vimc->pdev.dev, "%s: video register failed (err=%d)\n",
 			vcap->vdev.name, ret);
 		goto err_release_queue;
 	}
 
-	return 0;
+	return &vcap->ved;
 
 err_release_queue:
 	vb2_queue_release(q);
 err_clean_m_ent:
 	media_entity_cleanup(&vcap->vdev.entity);
-err_clean_pads:
-	vimc_pads_cleanup(vcap->ved.pads);
 err_free_vcap:
 	kfree(vcap);
 
-	return ret;
-}
-
-static const struct component_ops vimc_cap_comp_ops = {
-	.bind = vimc_cap_comp_bind,
-	.unbind = vimc_cap_comp_unbind,
-};
-
-static int vimc_cap_probe(struct platform_device *pdev)
-{
-	return component_add(&pdev->dev, &vimc_cap_comp_ops);
-}
-
-static int vimc_cap_remove(struct platform_device *pdev)
-{
-	component_del(&pdev->dev, &vimc_cap_comp_ops);
-
-	return 0;
+	return NULL;
 }
-
-static const struct platform_device_id vimc_cap_driver_ids[] = {
-	{
-		.name           = VIMC_CAP_DRV_NAME,
-	},
-	{ }
-};
-
-static struct platform_driver vimc_cap_pdrv = {
-	.probe		= vimc_cap_probe,
-	.remove		= vimc_cap_remove,
-	.id_table	= vimc_cap_driver_ids,
-	.driver		= {
-		.name	= VIMC_CAP_DRV_NAME,
-	},
-};
-
-module_platform_driver(vimc_cap_pdrv);
-
-MODULE_DEVICE_TABLE(platform, vimc_cap_driver_ids);
-
-MODULE_DESCRIPTION("Virtual Media Controller Driver (VIMC) Capture");
-MODULE_AUTHOR("Helen Mae Koike Fornazier <helen.fornazier@gmail.com>");
-MODULE_LICENSE("GPL");
diff --git a/drivers/media/platform/vimc/vimc-common.c b/drivers/media/platform/vimc/vimc-common.c
index 7e1ae0b12f1e..16ce9f3b7c75 100644
--- a/drivers/media/platform/vimc/vimc-common.c
+++ b/drivers/media/platform/vimc/vimc-common.c
@@ -164,6 +164,16 @@ static const struct vimc_pix_map vimc_pix_map_list[] = {
 	},
 };
 
+bool vimc_is_source(struct media_entity *ent)
+{
+	unsigned int i;
+
+	for (i = 0; i < ent->num_pads; i++)
+		if (ent->pads[i].flags & MEDIA_PAD_FL_SINK)
+			return false;
+	return true;
+}
+
 const struct vimc_pix_map *vimc_pix_map_by_index(unsigned int i)
 {
 	if (i >= ARRAY_SIZE(vimc_pix_map_list))
@@ -171,7 +181,6 @@ const struct vimc_pix_map *vimc_pix_map_by_index(unsigned int i)
 
 	return &vimc_pix_map_list[i];
 }
-EXPORT_SYMBOL_GPL(vimc_pix_map_by_index);
 
 const struct vimc_pix_map *vimc_pix_map_by_code(u32 code)
 {
@@ -183,7 +192,6 @@ const struct vimc_pix_map *vimc_pix_map_by_code(u32 code)
 	}
 	return NULL;
 }
-EXPORT_SYMBOL_GPL(vimc_pix_map_by_code);
 
 const struct vimc_pix_map *vimc_pix_map_by_pixelformat(u32 pixelformat)
 {
@@ -195,87 +203,37 @@ const struct vimc_pix_map *vimc_pix_map_by_pixelformat(u32 pixelformat)
 	}
 	return NULL;
 }
-EXPORT_SYMBOL_GPL(vimc_pix_map_by_pixelformat);
-
-/* Helper function to allocate and initialize pads */
-struct media_pad *vimc_pads_init(u16 num_pads, const unsigned long *pads_flag)
-{
-	struct media_pad *pads;
-	unsigned int i;
-
-	/* Allocate memory for the pads */
-	pads = kcalloc(num_pads, sizeof(*pads), GFP_KERNEL);
-	if (!pads)
-		return ERR_PTR(-ENOMEM);
-
-	/* Initialize the pads */
-	for (i = 0; i < num_pads; i++) {
-		pads[i].index = i;
-		pads[i].flags = pads_flag[i];
-	}
-
-	return pads;
-}
-EXPORT_SYMBOL_GPL(vimc_pads_init);
 
-int vimc_pipeline_s_stream(struct media_entity *ent, int enable)
-{
-	struct v4l2_subdev *sd;
-	struct media_pad *pad;
-	unsigned int i;
-	int ret;
-
-	for (i = 0; i < ent->num_pads; i++) {
-		if (ent->pads[i].flags & MEDIA_PAD_FL_SOURCE)
-			continue;
-
-		/* Start the stream in the subdevice direct connected */
-		pad = media_entity_remote_pad(&ent->pads[i]);
-		if (!pad)
-			continue;
-
-		if (!is_media_entity_v4l2_subdev(pad->entity))
-			return -EINVAL;
-
-		sd = media_entity_to_v4l2_subdev(pad->entity);
-		ret = v4l2_subdev_call(sd, video, s_stream, enable);
-		if (ret && ret != -ENOIOCTLCMD)
-			return ret;
-	}
-
-	return 0;
-}
-EXPORT_SYMBOL_GPL(vimc_pipeline_s_stream);
-
-static int vimc_get_mbus_format(struct media_pad *pad,
-				struct v4l2_subdev_format *fmt)
+static int vimc_get_pix_format(struct media_pad *pad,
+			       struct v4l2_pix_format *fmt)
 {
 	if (is_media_entity_v4l2_subdev(pad->entity)) {
 		struct v4l2_subdev *sd =
 			media_entity_to_v4l2_subdev(pad->entity);
+		struct v4l2_subdev_format sd_fmt;
+		const struct vimc_pix_map *pix_map;
 		int ret;
 
-		fmt->which = V4L2_SUBDEV_FORMAT_ACTIVE;
-		fmt->pad = pad->index;
+		sd_fmt.which = V4L2_SUBDEV_FORMAT_ACTIVE;
+		sd_fmt.pad = pad->index;
 
-		ret = v4l2_subdev_call(sd, pad, get_fmt, NULL, fmt);
+		ret = v4l2_subdev_call(sd, pad, get_fmt, NULL, &sd_fmt);
 		if (ret)
 			return ret;
 
+		v4l2_fill_pix_format(fmt, &sd_fmt.format);
+		pix_map = vimc_pix_map_by_code(sd_fmt.format.code);
+		fmt->pixelformat = pix_map->pixelformat;
 	} else if (is_media_entity_v4l2_video_device(pad->entity)) {
 		struct video_device *vdev = container_of(pad->entity,
 							 struct video_device,
 							 entity);
 		struct vimc_ent_device *ved = video_get_drvdata(vdev);
-		const struct vimc_pix_map *vpix;
-		struct v4l2_pix_format vdev_fmt;
 
 		if (!ved->vdev_get_format)
 			return -ENOIOCTLCMD;
 
-		ved->vdev_get_format(ved, &vdev_fmt);
-		vpix = vimc_pix_map_by_pixelformat(vdev_fmt.pixelformat);
-		v4l2_fill_mbus_format(&fmt->format, &vdev_fmt, vpix->code);
+		ved->vdev_get_format(ved, fmt);
 	} else {
 		return -EINVAL;
 	}
@@ -283,16 +241,16 @@ static int vimc_get_mbus_format(struct media_pad *pad,
 	return 0;
 }
 
-int vimc_link_validate(struct media_link *link)
+int vimc_vdev_link_validate(struct media_link *link)
 {
-	struct v4l2_subdev_format source_fmt, sink_fmt;
+	struct v4l2_pix_format source_fmt, sink_fmt;
 	int ret;
 
-	ret = vimc_get_mbus_format(link->source, &source_fmt);
+	ret = vimc_get_pix_format(link->source, &source_fmt);
 	if (ret)
 		return ret;
 
-	ret = vimc_get_mbus_format(link->sink, &sink_fmt);
+	ret = vimc_get_pix_format(link->sink, &sink_fmt);
 	if (ret)
 		return ret;
 
@@ -301,21 +259,21 @@ int vimc_link_validate(struct media_link *link)
 		"%s:snk:%dx%d (0x%x, %d, %d, %d, %d)\n",
 		/* src */
 		link->source->entity->name,
-		source_fmt.format.width, source_fmt.format.height,
-		source_fmt.format.code, source_fmt.format.colorspace,
-		source_fmt.format.quantization, source_fmt.format.xfer_func,
-		source_fmt.format.ycbcr_enc,
+		source_fmt.width, source_fmt.height,
+		source_fmt.pixelformat, source_fmt.colorspace,
+		source_fmt.quantization, source_fmt.xfer_func,
+		source_fmt.ycbcr_enc,
 		/* sink */
 		link->sink->entity->name,
-		sink_fmt.format.width, sink_fmt.format.height,
-		sink_fmt.format.code, sink_fmt.format.colorspace,
-		sink_fmt.format.quantization, sink_fmt.format.xfer_func,
-		sink_fmt.format.ycbcr_enc);
-
-	/* The width, height and code must match. */
-	if (source_fmt.format.width != sink_fmt.format.width
-	    || source_fmt.format.height != sink_fmt.format.height
-	    || source_fmt.format.code != sink_fmt.format.code)
+		sink_fmt.width, sink_fmt.height,
+		sink_fmt.pixelformat, sink_fmt.colorspace,
+		sink_fmt.quantization, sink_fmt.xfer_func,
+		sink_fmt.ycbcr_enc);
+
+	/* The width, height and pixelformat must match. */
+	if (source_fmt.width != sink_fmt.width ||
+	    source_fmt.height != sink_fmt.height ||
+	    source_fmt.pixelformat != sink_fmt.pixelformat)
 		return -EPIPE;
 
 	/*
@@ -323,44 +281,43 @@ int vimc_link_validate(struct media_link *link)
 	 * to support interlaced hardware connected to bridges that support
 	 * progressive formats only.
 	 */
-	if (source_fmt.format.field != sink_fmt.format.field &&
-	    sink_fmt.format.field != V4L2_FIELD_NONE)
+	if (source_fmt.field != sink_fmt.field &&
+	    sink_fmt.field != V4L2_FIELD_NONE)
 		return -EPIPE;
 
 	/*
 	 * If colorspace is DEFAULT, then assume all the colorimetry is also
 	 * DEFAULT, return 0 to skip comparing the other colorimetry parameters
 	 */
-	if (source_fmt.format.colorspace == V4L2_COLORSPACE_DEFAULT
-	    || sink_fmt.format.colorspace == V4L2_COLORSPACE_DEFAULT)
+	if (source_fmt.colorspace == V4L2_COLORSPACE_DEFAULT ||
+	    sink_fmt.colorspace == V4L2_COLORSPACE_DEFAULT)
 		return 0;
 
 	/* Colorspace must match. */
-	if (source_fmt.format.colorspace != sink_fmt.format.colorspace)
+	if (source_fmt.colorspace != sink_fmt.colorspace)
 		return -EPIPE;
 
 	/* Colorimetry must match if they are not set to DEFAULT */
-	if (source_fmt.format.ycbcr_enc != V4L2_YCBCR_ENC_DEFAULT
-	    && sink_fmt.format.ycbcr_enc != V4L2_YCBCR_ENC_DEFAULT
-	    && source_fmt.format.ycbcr_enc != sink_fmt.format.ycbcr_enc)
+	if (source_fmt.ycbcr_enc != V4L2_YCBCR_ENC_DEFAULT &&
+	    sink_fmt.ycbcr_enc != V4L2_YCBCR_ENC_DEFAULT &&
+	    source_fmt.ycbcr_enc != sink_fmt.ycbcr_enc)
 		return -EPIPE;
 
-	if (source_fmt.format.quantization != V4L2_QUANTIZATION_DEFAULT
-	    && sink_fmt.format.quantization != V4L2_QUANTIZATION_DEFAULT
-	    && source_fmt.format.quantization != sink_fmt.format.quantization)
+	if (source_fmt.quantization != V4L2_QUANTIZATION_DEFAULT &&
+	    sink_fmt.quantization != V4L2_QUANTIZATION_DEFAULT &&
+	    source_fmt.quantization != sink_fmt.quantization)
 		return -EPIPE;
 
-	if (source_fmt.format.xfer_func != V4L2_XFER_FUNC_DEFAULT
-	    && sink_fmt.format.xfer_func != V4L2_XFER_FUNC_DEFAULT
-	    && source_fmt.format.xfer_func != sink_fmt.format.xfer_func)
+	if (source_fmt.xfer_func != V4L2_XFER_FUNC_DEFAULT &&
+	    sink_fmt.xfer_func != V4L2_XFER_FUNC_DEFAULT &&
+	    source_fmt.xfer_func != sink_fmt.xfer_func)
 		return -EPIPE;
 
 	return 0;
 }
-EXPORT_SYMBOL_GPL(vimc_link_validate);
 
 static const struct media_entity_operations vimc_ent_sd_mops = {
-	.link_validate = vimc_link_validate,
+	.link_validate = v4l2_subdev_link_validate,
 };
 
 int vimc_ent_sd_register(struct vimc_ent_device *ved,
@@ -369,17 +326,12 @@ int vimc_ent_sd_register(struct vimc_ent_device *ved,
 			 const char *const name,
 			 u32 function,
 			 u16 num_pads,
-			 const unsigned long *pads_flag,
+			 struct media_pad *pads,
 			 const struct v4l2_subdev_internal_ops *sd_int_ops,
 			 const struct v4l2_subdev_ops *sd_ops)
 {
 	int ret;
 
-	/* Allocate the pads */
-	ved->pads = vimc_pads_init(num_pads, pads_flag);
-	if (IS_ERR(ved->pads))
-		return PTR_ERR(ved->pads);
-
 	/* Fill the vimc_ent_device struct */
 	ved->ent = &sd->entity;
 
@@ -398,9 +350,9 @@ int vimc_ent_sd_register(struct vimc_ent_device *ved,
 		sd->flags |= V4L2_SUBDEV_FL_HAS_EVENTS;
 
 	/* Initialize the media entity */
-	ret = media_entity_pads_init(&sd->entity, num_pads, ved->pads);
+	ret = media_entity_pads_init(&sd->entity, num_pads, pads);
 	if (ret)
-		goto err_clean_pads;
+		return ret;
 
 	/* Register the subdev with the v4l2 and the media framework */
 	ret = v4l2_device_register_subdev(v4l2_dev, sd);
@@ -415,16 +367,5 @@ int vimc_ent_sd_register(struct vimc_ent_device *ved,
 
 err_clean_m_ent:
 	media_entity_cleanup(&sd->entity);
-err_clean_pads:
-	vimc_pads_cleanup(ved->pads);
 	return ret;
 }
-EXPORT_SYMBOL_GPL(vimc_ent_sd_register);
-
-void vimc_ent_sd_unregister(struct vimc_ent_device *ved, struct v4l2_subdev *sd)
-{
-	media_entity_cleanup(ved->ent);
-	vimc_pads_cleanup(ved->pads);
-	v4l2_device_unregister_subdev(sd);
-}
-EXPORT_SYMBOL_GPL(vimc_ent_sd_unregister);
diff --git a/drivers/media/platform/vimc/vimc-common.h b/drivers/media/platform/vimc/vimc-common.h
index 9c2e0e216c6b..87eb8259c2a8 100644
--- a/drivers/media/platform/vimc/vimc-common.h
+++ b/drivers/media/platform/vimc/vimc-common.h
@@ -8,6 +8,7 @@
 #ifndef _VIMC_COMMON_H_
 #define _VIMC_COMMON_H_
 
+#include <linux/platform_device.h>
 #include <linux/slab.h>
 #include <media/media-device.h>
 #include <media/v4l2-device.h>
@@ -18,6 +19,7 @@
 #define VIMC_CID_VIMC_BASE		(0x00f00000 | 0xf000)
 #define VIMC_CID_VIMC_CLASS		(0x00f00000 | 1)
 #define VIMC_CID_TEST_PATTERN		(VIMC_CID_VIMC_BASE + 0)
+#define VIMC_CID_MEAN_WIN_SIZE		(VIMC_CID_VIMC_BASE + 1)
 
 #define VIMC_FRAME_MAX_WIDTH 4096
 #define VIMC_FRAME_MAX_HEIGHT 2160
@@ -26,6 +28,10 @@
 
 #define VIMC_FRAME_INDEX(lin, col, width, bpp) ((lin * width + col) * bpp)
 
+/* Source and sink pad checks */
+#define VIMC_IS_SRC(pad)	(pad)
+#define VIMC_IS_SINK(pad)	(!(pad))
+
 /**
  * struct vimc_colorimetry_clamp - Adjust colorimetry parameters
  *
@@ -53,21 +59,6 @@ do {									\
 } while (0)
 
 /**
- * struct vimc_platform_data - platform data to components
- *
- * @entity_name:	The name of the entity to be created
- *
- * Board setup code will often provide additional information using the device's
- * platform_data field to hold additional information.
- * When injecting a new platform_device in the component system the core needs
- * to provide to the corresponding submodules the name of the entity that should
- * be used when registering the subdevice in the Media Controller system.
- */
-struct vimc_platform_data {
-	char entity_name[32];
-};
-
-/**
  * struct vimc_pix_map - maps media bus code with v4l2 pixel format
  *
  * @code:		media bus format code defined by MEDIA_BUS_FMT_* macros
@@ -85,10 +76,11 @@ struct vimc_pix_map {
 };
 
 /**
- * struct vimc_ent_device - core struct that represents a node in the topology
+ * struct vimc_ent_device - core struct that represents an entity in the
+ * topology
  *
+ * @dev:		a pointer of the device struct of the driver
  * @ent:		the pointer to struct media_entity for the node
- * @pads:		the list of pads of the node
  * @process_frame:	callback send a frame to that node
  * @vdev_get_format:	callback that returns the current format a pad, used
  *			only when is_media_entity_v4l2_video_device(ent) returns
@@ -103,8 +95,8 @@ struct vimc_pix_map {
  * media_entity
  */
 struct vimc_ent_device {
+	struct device *dev;
 	struct media_entity *ent;
-	struct media_pad *pads;
 	void * (*process_frame)(struct vimc_ent_device *ved,
 				const void *frame);
 	void (*vdev_get_format)(struct vimc_ent_device *ved,
@@ -112,38 +104,65 @@ struct vimc_ent_device {
 };
 
 /**
- * vimc_pads_init - initialize pads
- *
- * @num_pads:	number of pads to initialize
- * @pads_flags:	flags to use in each pad
+ * struct vimc_device - main device for vimc driver
  *
- * Helper functions to allocate/initialize pads
+ * @pdev	pointer to the platform device
+ * @pipe_cfg	pointer to the vimc pipeline configuration structure
+ * @ent_devs	array of vimc_ent_device pointers
+ * @mdev	the associated media_device parent
+ * @v4l2_dev	Internal v4l2 parent device
  */
-struct media_pad *vimc_pads_init(u16 num_pads,
-				 const unsigned long *pads_flag);
+struct vimc_device {
+	struct platform_device pdev;
+	const struct vimc_pipeline_config *pipe_cfg;
+	struct vimc_ent_device **ent_devs;
+	struct media_device mdev;
+	struct v4l2_device v4l2_dev;
+};
 
 /**
- * vimc_pads_cleanup - free pads
- *
- * @pads: pointer to the pads
- *
- * Helper function to free the pads initialized with vimc_pads_init
+ * struct vimc_ent_config	Structure which describes individual
+ *				configuration for each entity
+ *
+ * @name			entity name
+ * @ved				pointer to vimc_ent_device (a node in the
+ *					topology)
+ * @add				subdev add hook - initializes and registers
+ *					subdev called from vimc-core
+ * @rm				subdev rm hook - unregisters and frees
+ *					subdev called from vimc-core
  */
-static inline void vimc_pads_cleanup(struct media_pad *pads)
-{
-	kfree(pads);
-}
+struct vimc_ent_config {
+	const char *name;
+	struct vimc_ent_device *(*add)(struct vimc_device *vimc,
+				       const char *vcfg_name);
+	void (*rm)(struct vimc_device *vimc, struct vimc_ent_device *ved);
+};
 
 /**
- * vimc_pipeline_s_stream - start stream through the pipeline
+ * vimc_is_source - returns true if the entity has only source pads
  *
- * @ent:		the pointer to struct media_entity for the node
- * @enable:		1 to start the stream and 0 to stop
+ * @ent: pointer to &struct media_entity
  *
- * Helper function to call the s_stream of the subdevices connected
- * in all the sink pads of the entity
  */
-int vimc_pipeline_s_stream(struct media_entity *ent, int enable);
+bool vimc_is_source(struct media_entity *ent);
+
+/* prototypes for vimc_ent_config add and rm hooks */
+struct vimc_ent_device *vimc_cap_add(struct vimc_device *vimc,
+				     const char *vcfg_name);
+void vimc_cap_rm(struct vimc_device *vimc, struct vimc_ent_device *ved);
+
+struct vimc_ent_device *vimc_deb_add(struct vimc_device *vimc,
+				     const char *vcfg_name);
+void vimc_deb_rm(struct vimc_device *vimc, struct vimc_ent_device *ved);
+
+struct vimc_ent_device *vimc_sca_add(struct vimc_device *vimc,
+				     const char *vcfg_name);
+void vimc_sca_rm(struct vimc_device *vimc, struct vimc_ent_device *ved);
+
+struct vimc_ent_device *vimc_sen_add(struct vimc_device *vimc,
+				     const char *vcfg_name);
+void vimc_sen_rm(struct vimc_device *vimc, struct vimc_ent_device *ved);
 
 /**
  * vimc_pix_map_by_index - get vimc_pix_map struct by its index
@@ -176,7 +195,8 @@ const struct vimc_pix_map *vimc_pix_map_by_pixelformat(u32 pixelformat);
  *		unique.
  * @function:	media entity function defined by MEDIA_ENT_F_* macros
  * @num_pads:	number of pads to initialize
- * @pads_flag:	flags to use in each pad
+ * @pads:	the array of pads of the entity, the caller should set the
+		flags of the pads
  * @sd_int_ops:	pointer to &struct v4l2_subdev_internal_ops
  * @sd_ops:	pointer to &struct v4l2_subdev_ops.
  *
@@ -189,29 +209,17 @@ int vimc_ent_sd_register(struct vimc_ent_device *ved,
 			 const char *const name,
 			 u32 function,
 			 u16 num_pads,
-			 const unsigned long *pads_flag,
+			 struct media_pad *pads,
 			 const struct v4l2_subdev_internal_ops *sd_int_ops,
 			 const struct v4l2_subdev_ops *sd_ops);
 
 /**
- * vimc_ent_sd_unregister - cleanup and unregister a subdev node
- *
- * @ved:	the vimc_ent_device struct to be cleaned up
- * @sd:		the v4l2_subdev struct to be unregistered
- *
- * Helper function cleanup and unregister the struct vimc_ent_device and struct
- * v4l2_subdev which represents a subdev node in the topology
- */
-void vimc_ent_sd_unregister(struct vimc_ent_device *ved,
-			    struct v4l2_subdev *sd);
-
-/**
- * vimc_link_validate - validates a media link
+ * vimc_vdev_link_validate - validates a media link
  *
  * @link: pointer to &struct media_link
  *
  * This function calls validates if a media link is valid for streaming.
  */
-int vimc_link_validate(struct media_link *link);
+int vimc_vdev_link_validate(struct media_link *link);
 
 #endif
diff --git a/drivers/media/platform/vimc/vimc-core.c b/drivers/media/platform/vimc/vimc-core.c
index 571c55aa0e16..97a272f3350a 100644
--- a/drivers/media/platform/vimc/vimc-core.c
+++ b/drivers/media/platform/vimc/vimc-core.c
@@ -5,7 +5,6 @@
  * Copyright (C) 2015-2017 Helen Koike <helen.fornazier@gmail.com>
  */
 
-#include <linux/component.h>
 #include <linux/init.h>
 #include <linux/module.h>
 #include <linux/platform_device.h>
@@ -24,29 +23,6 @@
 	.flags = link_flags,					\
 }
 
-struct vimc_device {
-	/* The platform device */
-	struct platform_device pdev;
-
-	/* The pipeline configuration */
-	const struct vimc_pipeline_config *pipe_cfg;
-
-	/* The Associated media_device parent */
-	struct media_device mdev;
-
-	/* Internal v4l2 parent device*/
-	struct v4l2_device v4l2_dev;
-
-	/* Subdevices */
-	struct platform_device **subdevs;
-};
-
-/* Structure which describes individual configuration for each entity */
-struct vimc_ent_config {
-	const char *name;
-	const char *drv;
-};
-
 /* Structure which describes links between entities */
 struct vimc_ent_link {
 	unsigned int src_ent;
@@ -68,43 +44,52 @@ struct vimc_pipeline_config {
  * Topology Configuration
  */
 
-static const struct vimc_ent_config ent_config[] = {
+static struct vimc_ent_config ent_config[] = {
 	{
 		.name = "Sensor A",
-		.drv = "vimc-sensor",
+		.add = vimc_sen_add,
+		.rm = vimc_sen_rm,
 	},
 	{
 		.name = "Sensor B",
-		.drv = "vimc-sensor",
+		.add = vimc_sen_add,
+		.rm = vimc_sen_rm,
 	},
 	{
 		.name = "Debayer A",
-		.drv = "vimc-debayer",
+		.add = vimc_deb_add,
+		.rm = vimc_deb_rm,
 	},
 	{
 		.name = "Debayer B",
-		.drv = "vimc-debayer",
+		.add = vimc_deb_add,
+		.rm = vimc_deb_rm,
 	},
 	{
 		.name = "Raw Capture 0",
-		.drv = "vimc-capture",
+		.add = vimc_cap_add,
+		.rm = vimc_cap_rm,
 	},
 	{
 		.name = "Raw Capture 1",
-		.drv = "vimc-capture",
+		.add = vimc_cap_add,
+		.rm = vimc_cap_rm,
 	},
 	{
-		.name = "RGB/YUV Input",
 		/* TODO: change this to vimc-input when it is implemented */
-		.drv = "vimc-sensor",
+		.name = "RGB/YUV Input",
+		.add = vimc_sen_add,
+		.rm = vimc_sen_rm,
 	},
 	{
 		.name = "Scaler",
-		.drv = "vimc-scaler",
+		.add = vimc_sca_add,
+		.rm = vimc_sca_rm,
 	},
 	{
 		.name = "RGB/YUV Capture",
-		.drv = "vimc-capture",
+		.add = vimc_cap_add,
+		.rm = vimc_cap_rm,
 	},
 };
 
@@ -127,7 +112,7 @@ static const struct vimc_ent_link ent_links[] = {
 	VIMC_ENT_LINK(7, 1, 8, 0, MEDIA_LNK_FL_ENABLED | MEDIA_LNK_FL_IMMUTABLE),
 };
 
-static const struct vimc_pipeline_config pipe_cfg = {
+static struct vimc_pipeline_config pipe_cfg = {
 	.ents		= ent_config,
 	.num_ents	= ARRAY_SIZE(ent_config),
 	.links		= ent_links,
@@ -136,6 +121,14 @@ static const struct vimc_pipeline_config pipe_cfg = {
 
 /* -------------------------------------------------------------------------- */
 
+static void vimc_rm_links(struct vimc_device *vimc)
+{
+	unsigned int i;
+
+	for (i = 0; i < vimc->pipe_cfg->num_ents; i++)
+		media_entity_remove_links(vimc->ent_devs[i]->ent);
+}
+
 static int vimc_create_links(struct vimc_device *vimc)
 {
 	unsigned int i;
@@ -144,32 +137,56 @@ static int vimc_create_links(struct vimc_device *vimc)
 	/* Initialize the links between entities */
 	for (i = 0; i < vimc->pipe_cfg->num_links; i++) {
 		const struct vimc_ent_link *link = &vimc->pipe_cfg->links[i];
-		/*
-		 * TODO: Check another way of retrieving ved struct without
-		 * relying on platform_get_drvdata
-		 */
+
 		struct vimc_ent_device *ved_src =
-			platform_get_drvdata(vimc->subdevs[link->src_ent]);
+			vimc->ent_devs[link->src_ent];
 		struct vimc_ent_device *ved_sink =
-			platform_get_drvdata(vimc->subdevs[link->sink_ent]);
+			vimc->ent_devs[link->sink_ent];
 
 		ret = media_create_pad_link(ved_src->ent, link->src_pad,
 					    ved_sink->ent, link->sink_pad,
 					    link->flags);
 		if (ret)
-			return ret;
+			goto err_rm_links;
 	}
 
 	return 0;
+
+err_rm_links:
+	vimc_rm_links(vimc);
+	return ret;
 }
 
-static int vimc_comp_bind(struct device *master)
+static int vimc_add_subdevs(struct vimc_device *vimc)
 {
-	struct vimc_device *vimc = container_of(to_platform_device(master),
-						struct vimc_device, pdev);
-	int ret;
+	unsigned int i;
+
+	for (i = 0; i < vimc->pipe_cfg->num_ents; i++) {
+		dev_dbg(&vimc->pdev.dev, "new entity for %s\n",
+			vimc->pipe_cfg->ents[i].name);
+		vimc->ent_devs[i] = vimc->pipe_cfg->ents[i].add(vimc,
+					vimc->pipe_cfg->ents[i].name);
+		if (!vimc->ent_devs[i]) {
+			dev_err(&vimc->pdev.dev, "add new entity for %s\n",
+				vimc->pipe_cfg->ents[i].name);
+			return -EINVAL;
+		}
+	}
+	return 0;
+}
+
+static void vimc_rm_subdevs(struct vimc_device *vimc)
+{
+	unsigned int i;
+
+	for (i = 0; i < vimc->pipe_cfg->num_ents; i++)
+		if (vimc->ent_devs[i])
+			vimc->pipe_cfg->ents[i].rm(vimc, vimc->ent_devs[i]);
+}
 
-	dev_dbg(master, "bind");
+static int vimc_register_devices(struct vimc_device *vimc)
+{
+	int ret;
 
 	/* Register the v4l2 struct */
 	ret = v4l2_device_register(vimc->mdev.dev, &vimc->v4l2_dev);
@@ -179,22 +196,31 @@ static int vimc_comp_bind(struct device *master)
 		return ret;
 	}
 
-	/* Bind subdevices */
-	ret = component_bind_all(master, &vimc->v4l2_dev);
-	if (ret)
+	/* allocate ent_devs */
+	vimc->ent_devs = kcalloc(vimc->pipe_cfg->num_ents,
+				 sizeof(*vimc->ent_devs), GFP_KERNEL);
+	if (!vimc->ent_devs) {
+		ret = -ENOMEM;
 		goto err_v4l2_unregister;
+	}
+
+	/* Invoke entity config hooks to initialize and register subdevs */
+	ret = vimc_add_subdevs(vimc);
+	if (ret)
+		/* remove sundevs that got added */
+		goto err_rm_subdevs;
 
 	/* Initialize links */
 	ret = vimc_create_links(vimc);
 	if (ret)
-		goto err_comp_unbind_all;
+		goto err_rm_subdevs;
 
 	/* Register the media device */
 	ret = media_device_register(&vimc->mdev);
 	if (ret) {
 		dev_err(vimc->mdev.dev,
 			"media device register failed (err=%d)\n", ret);
-		goto err_comp_unbind_all;
+		goto err_rm_subdevs;
 	}
 
 	/* Expose all subdev's nodes*/
@@ -211,98 +237,32 @@ static int vimc_comp_bind(struct device *master)
 err_mdev_unregister:
 	media_device_unregister(&vimc->mdev);
 	media_device_cleanup(&vimc->mdev);
-err_comp_unbind_all:
-	component_unbind_all(master, NULL);
+err_rm_subdevs:
+	vimc_rm_subdevs(vimc);
+	kfree(vimc->ent_devs);
 err_v4l2_unregister:
 	v4l2_device_unregister(&vimc->v4l2_dev);
 
 	return ret;
 }
 
-static void vimc_comp_unbind(struct device *master)
+static void vimc_unregister(struct vimc_device *vimc)
 {
-	struct vimc_device *vimc = container_of(to_platform_device(master),
-						struct vimc_device, pdev);
-
-	dev_dbg(master, "unbind");
-
 	media_device_unregister(&vimc->mdev);
 	media_device_cleanup(&vimc->mdev);
-	component_unbind_all(master, NULL);
 	v4l2_device_unregister(&vimc->v4l2_dev);
+	kfree(vimc->ent_devs);
 }
 
-static int vimc_comp_compare(struct device *comp, void *data)
-{
-	return comp == data;
-}
-
-static struct component_match *vimc_add_subdevs(struct vimc_device *vimc)
-{
-	struct component_match *match = NULL;
-	struct vimc_platform_data pdata;
-	int i;
-
-	for (i = 0; i < vimc->pipe_cfg->num_ents; i++) {
-		dev_dbg(&vimc->pdev.dev, "new pdev for %s\n",
-			vimc->pipe_cfg->ents[i].drv);
-
-		strscpy(pdata.entity_name, vimc->pipe_cfg->ents[i].name,
-			sizeof(pdata.entity_name));
-
-		vimc->subdevs[i] = platform_device_register_data(&vimc->pdev.dev,
-						vimc->pipe_cfg->ents[i].drv,
-						PLATFORM_DEVID_AUTO,
-						&pdata,
-						sizeof(pdata));
-		if (IS_ERR(vimc->subdevs[i])) {
-			match = ERR_CAST(vimc->subdevs[i]);
-			while (--i >= 0)
-				platform_device_unregister(vimc->subdevs[i]);
-
-			return match;
-		}
-
-		component_match_add(&vimc->pdev.dev, &match, vimc_comp_compare,
-				    &vimc->subdevs[i]->dev);
-	}
-
-	return match;
-}
-
-static void vimc_rm_subdevs(struct vimc_device *vimc)
-{
-	unsigned int i;
-
-	for (i = 0; i < vimc->pipe_cfg->num_ents; i++)
-		platform_device_unregister(vimc->subdevs[i]);
-}
-
-static const struct component_master_ops vimc_comp_ops = {
-	.bind = vimc_comp_bind,
-	.unbind = vimc_comp_unbind,
-};
-
 static int vimc_probe(struct platform_device *pdev)
 {
 	struct vimc_device *vimc = container_of(pdev, struct vimc_device, pdev);
-	struct component_match *match = NULL;
 	int ret;
 
 	dev_dbg(&pdev->dev, "probe");
 
 	memset(&vimc->mdev, 0, sizeof(vimc->mdev));
 
-	/* Create platform_device for each entity in the topology*/
-	vimc->subdevs = devm_kcalloc(&vimc->pdev.dev, vimc->pipe_cfg->num_ents,
-				     sizeof(*vimc->subdevs), GFP_KERNEL);
-	if (!vimc->subdevs)
-		return -ENOMEM;
-
-	match = vimc_add_subdevs(vimc);
-	if (IS_ERR(match))
-		return PTR_ERR(match);
-
 	/* Link the media device within the v4l2_device */
 	vimc->v4l2_dev.mdev = &vimc->mdev;
 
@@ -314,12 +274,9 @@ static int vimc_probe(struct platform_device *pdev)
 	vimc->mdev.dev = &pdev->dev;
 	media_device_init(&vimc->mdev);
 
-	/* Add self to the component system */
-	ret = component_master_add_with_match(&pdev->dev, &vimc_comp_ops,
-					      match);
+	ret = vimc_register_devices(vimc);
 	if (ret) {
 		media_device_cleanup(&vimc->mdev);
-		vimc_rm_subdevs(vimc);
 		return ret;
 	}
 
@@ -332,8 +289,8 @@ static int vimc_remove(struct platform_device *pdev)
 
 	dev_dbg(&pdev->dev, "remove");
 
-	component_master_del(&pdev->dev, &vimc_comp_ops);
 	vimc_rm_subdevs(vimc);
+	vimc_unregister(vimc);
 
 	return 0;
 }
diff --git a/drivers/media/platform/vimc/vimc-debayer.c b/drivers/media/platform/vimc/vimc-debayer.c
index b72b8385067b..5d1b67d684bb 100644
--- a/drivers/media/platform/vimc/vimc-debayer.c
+++ b/drivers/media/platform/vimc/vimc-debayer.c
@@ -5,28 +5,16 @@
  * Copyright (C) 2015-2017 Helen Koike <helen.fornazier@gmail.com>
  */
 
-#include <linux/component.h>
-#include <linux/module.h>
-#include <linux/mod_devicetable.h>
+#include <linux/moduleparam.h>
 #include <linux/platform_device.h>
 #include <linux/vmalloc.h>
 #include <linux/v4l2-mediabus.h>
+#include <media/v4l2-ctrls.h>
+#include <media/v4l2-event.h>
 #include <media/v4l2-subdev.h>
 
 #include "vimc-common.h"
 
-#define VIMC_DEB_DRV_NAME "vimc-debayer"
-
-static unsigned int deb_mean_win_size = 3;
-module_param(deb_mean_win_size, uint, 0000);
-MODULE_PARM_DESC(deb_mean_win_size, " the window size to calculate the mean.\n"
-	"NOTE: the window size needs to be an odd number, as the main pixel "
-	"stays in the center of the window, otherwise the next odd number "
-	"is considered");
-
-#define IS_SINK(pad) (!pad)
-#define IS_SRC(pad)  (pad)
-
 enum vimc_deb_rgb_colors {
 	VIMC_DEB_RED = 0,
 	VIMC_DEB_GREEN = 1,
@@ -41,7 +29,6 @@ struct vimc_deb_pix_map {
 struct vimc_deb_device {
 	struct vimc_ent_device ved;
 	struct v4l2_subdev sd;
-	struct device *dev;
 	/* The active format */
 	struct v4l2_mbus_framefmt sink_fmt;
 	u32 src_code;
@@ -51,6 +38,9 @@ struct vimc_deb_device {
 	u8 *src_frame;
 	const struct vimc_deb_pix_map *sink_pix_map;
 	unsigned int sink_bpp;
+	unsigned int mean_win_size;
+	struct v4l2_ctrl_handler hdl;
+	struct media_pad pads[2];
 };
 
 static const struct v4l2_mbus_framefmt sink_fmt_default = {
@@ -159,7 +149,7 @@ static int vimc_deb_enum_mbus_code(struct v4l2_subdev *sd,
 				   struct v4l2_subdev_mbus_code_enum *code)
 {
 	/* We only support one format for source pads */
-	if (IS_SRC(code->pad)) {
+	if (VIMC_IS_SRC(code->pad)) {
 		struct vimc_deb_device *vdeb = v4l2_get_subdevdata(sd);
 
 		if (code->index)
@@ -185,7 +175,7 @@ static int vimc_deb_enum_frame_size(struct v4l2_subdev *sd,
 	if (fse->index)
 		return -EINVAL;
 
-	if (IS_SINK(fse->pad)) {
+	if (VIMC_IS_SINK(fse->pad)) {
 		const struct vimc_deb_pix_map *vpix =
 			vimc_deb_pix_map_by_code(fse->code);
 
@@ -215,7 +205,7 @@ static int vimc_deb_get_fmt(struct v4l2_subdev *sd,
 		      vdeb->sink_fmt;
 
 	/* Set the right code for the source pad */
-	if (IS_SRC(fmt->pad))
+	if (VIMC_IS_SRC(fmt->pad))
 		fmt->format.code = vdeb->src_code;
 
 	return 0;
@@ -262,7 +252,7 @@ static int vimc_deb_set_fmt(struct v4l2_subdev *sd,
 	 * Do not change the format of the source pad,
 	 * it is propagated from the sink
 	 */
-	if (IS_SRC(fmt->pad)) {
+	if (VIMC_IS_SRC(fmt->pad)) {
 		fmt->format = *sink_fmt;
 		/* TODO: Add support for other formats */
 		fmt->format.code = vdeb->src_code;
@@ -270,7 +260,7 @@ static int vimc_deb_set_fmt(struct v4l2_subdev *sd,
 		/* Set the new format in the sink pad */
 		vimc_deb_adjust_sink_fmt(&fmt->format);
 
-		dev_dbg(vdeb->dev, "%s: sink format update: "
+		dev_dbg(vdeb->ved.dev, "%s: sink format update: "
 			"old:%dx%d (0x%x, %d, %d, %d, %d) "
 			"new:%dx%d (0x%x, %d, %d, %d, %d)\n", vdeb->sd.name,
 			/* old */
@@ -351,11 +341,18 @@ static int vimc_deb_s_stream(struct v4l2_subdev *sd, int enable)
 	return 0;
 }
 
+static const struct v4l2_subdev_core_ops vimc_deb_core_ops = {
+	.log_status = v4l2_ctrl_subdev_log_status,
+	.subscribe_event = v4l2_ctrl_subdev_subscribe_event,
+	.unsubscribe_event = v4l2_event_subdev_unsubscribe,
+};
+
 static const struct v4l2_subdev_video_ops vimc_deb_video_ops = {
 	.s_stream = vimc_deb_s_stream,
 };
 
 static const struct v4l2_subdev_ops vimc_deb_ops = {
+	.core = &vimc_deb_core_ops,
 	.pad = &vimc_deb_pad_ops,
 	.video = &vimc_deb_video_ops,
 };
@@ -389,11 +386,11 @@ static void vimc_deb_calc_rgb_sink(struct vimc_deb_device *vdeb,
 	 * the top left corner of the mean window (considering the current
 	 * pixel as the center)
 	 */
-	seek = deb_mean_win_size / 2;
+	seek = vdeb->mean_win_size / 2;
 
 	/* Sum the values of the colors in the mean window */
 
-	dev_dbg(vdeb->dev,
+	dev_dbg(vdeb->ved.dev,
 		"deb: %s: --- Calc pixel %dx%d, window mean %d, seek %d ---\n",
 		vdeb->sd.name, lin, col, vdeb->sink_fmt.height, seek);
 
@@ -426,7 +423,7 @@ static void vimc_deb_calc_rgb_sink(struct vimc_deb_device *vdeb,
 						 vdeb->sink_fmt.width,
 						 vdeb->sink_bpp);
 
-			dev_dbg(vdeb->dev,
+			dev_dbg(vdeb->ved.dev,
 				"deb: %s: RGB CALC: frame index %d, win pos %dx%d, color %d\n",
 				vdeb->sd.name, index, wlin, wcol, color);
 
@@ -437,21 +434,21 @@ static void vimc_deb_calc_rgb_sink(struct vimc_deb_device *vdeb,
 			/* Save how many values we already added */
 			n_rgb[color]++;
 
-			dev_dbg(vdeb->dev, "deb: %s: RGB CALC: val %d, n %d\n",
+			dev_dbg(vdeb->ved.dev, "deb: %s: RGB CALC: val %d, n %d\n",
 				vdeb->sd.name, rgb[color], n_rgb[color]);
 		}
 	}
 
 	/* Calculate the mean */
 	for (i = 0; i < 3; i++) {
-		dev_dbg(vdeb->dev,
+		dev_dbg(vdeb->ved.dev,
 			"deb: %s: PRE CALC: %dx%d Color %d, val %d, n %d\n",
 			vdeb->sd.name, lin, col, i, rgb[i], n_rgb[i]);
 
 		if (n_rgb[i])
 			rgb[i] = rgb[i] / n_rgb[i];
 
-		dev_dbg(vdeb->dev,
+		dev_dbg(vdeb->ved.dev,
 			"deb: %s: FINAL CALC: %dx%d Color %d, val %d\n",
 			vdeb->sd.name, lin, col, i, rgb[i]);
 	}
@@ -476,14 +473,34 @@ static void *vimc_deb_process_frame(struct vimc_ent_device *ved,
 		}
 
 	return vdeb->src_frame;
+}
 
+static int vimc_deb_s_ctrl(struct v4l2_ctrl *ctrl)
+{
+	struct vimc_deb_device *vdeb =
+		container_of(ctrl->handler, struct vimc_deb_device, hdl);
+
+	switch (ctrl->id) {
+	case VIMC_CID_MEAN_WIN_SIZE:
+		vdeb->mean_win_size = ctrl->val;
+		break;
+	default:
+		return -EINVAL;
+	}
+	return 0;
 }
 
+static const struct v4l2_ctrl_ops vimc_deb_ctrl_ops = {
+	.s_ctrl = vimc_deb_s_ctrl,
+};
+
 static void vimc_deb_release(struct v4l2_subdev *sd)
 {
 	struct vimc_deb_device *vdeb =
 				container_of(sd, struct vimc_deb_device, sd);
 
+	v4l2_ctrl_handler_free(&vdeb->hdl);
+	media_entity_cleanup(vdeb->ved.ent);
 	kfree(vdeb);
 }
 
@@ -491,44 +508,69 @@ static const struct v4l2_subdev_internal_ops vimc_deb_int_ops = {
 	.release = vimc_deb_release,
 };
 
-static void vimc_deb_comp_unbind(struct device *comp, struct device *master,
-				 void *master_data)
+void vimc_deb_rm(struct vimc_device *vimc, struct vimc_ent_device *ved)
 {
-	struct vimc_ent_device *ved = dev_get_drvdata(comp);
-	struct vimc_deb_device *vdeb = container_of(ved, struct vimc_deb_device,
-						    ved);
+	struct vimc_deb_device *vdeb;
 
-	vimc_ent_sd_unregister(ved, &vdeb->sd);
+	vdeb = container_of(ved, struct vimc_deb_device, ved);
+	v4l2_device_unregister_subdev(&vdeb->sd);
 }
 
-static int vimc_deb_comp_bind(struct device *comp, struct device *master,
-			      void *master_data)
+static const struct v4l2_ctrl_config vimc_deb_ctrl_class = {
+	.flags = V4L2_CTRL_FLAG_READ_ONLY | V4L2_CTRL_FLAG_WRITE_ONLY,
+	.id = VIMC_CID_VIMC_CLASS,
+	.name = "VIMC Controls",
+	.type = V4L2_CTRL_TYPE_CTRL_CLASS,
+};
+
+static const struct v4l2_ctrl_config vimc_deb_ctrl_mean_win_size = {
+	.ops = &vimc_deb_ctrl_ops,
+	.id = VIMC_CID_MEAN_WIN_SIZE,
+	.name = "Debayer Mean Window Size",
+	.type = V4L2_CTRL_TYPE_INTEGER,
+	.min = 1,
+	.max = 25,
+	.step = 2,
+	.def = 3,
+};
+
+struct vimc_ent_device *vimc_deb_add(struct vimc_device *vimc,
+				     const char *vcfg_name)
 {
-	struct v4l2_device *v4l2_dev = master_data;
-	struct vimc_platform_data *pdata = comp->platform_data;
+	struct v4l2_device *v4l2_dev = &vimc->v4l2_dev;
 	struct vimc_deb_device *vdeb;
 	int ret;
 
 	/* Allocate the vdeb struct */
 	vdeb = kzalloc(sizeof(*vdeb), GFP_KERNEL);
 	if (!vdeb)
-		return -ENOMEM;
+		return NULL;
+
+	/* Create controls: */
+	v4l2_ctrl_handler_init(&vdeb->hdl, 2);
+	v4l2_ctrl_new_custom(&vdeb->hdl, &vimc_deb_ctrl_class, NULL);
+	v4l2_ctrl_new_custom(&vdeb->hdl, &vimc_deb_ctrl_mean_win_size, NULL);
+	vdeb->sd.ctrl_handler = &vdeb->hdl;
+	if (vdeb->hdl.error) {
+		ret = vdeb->hdl.error;
+		goto err_free_vdeb;
+	}
 
 	/* Initialize ved and sd */
+	vdeb->pads[0].flags = MEDIA_PAD_FL_SINK;
+	vdeb->pads[1].flags = MEDIA_PAD_FL_SOURCE;
+
 	ret = vimc_ent_sd_register(&vdeb->ved, &vdeb->sd, v4l2_dev,
-				   pdata->entity_name,
+				   vcfg_name,
 				   MEDIA_ENT_F_PROC_VIDEO_PIXEL_ENC_CONV, 2,
-				   (const unsigned long[2]) {MEDIA_PAD_FL_SINK,
-				   MEDIA_PAD_FL_SOURCE},
+				   vdeb->pads,
 				   &vimc_deb_int_ops, &vimc_deb_ops);
-	if (ret) {
-		kfree(vdeb);
-		return ret;
-	}
+	if (ret)
+		goto err_free_hdl;
 
 	vdeb->ved.process_frame = vimc_deb_process_frame;
-	dev_set_drvdata(comp, &vdeb->ved);
-	vdeb->dev = comp;
+	vdeb->ved.dev = &vimc->pdev.dev;
+	vdeb->mean_win_size = vimc_deb_ctrl_mean_win_size.def;
 
 	/* Initialize the frame format */
 	vdeb->sink_fmt = sink_fmt_default;
@@ -541,46 +583,12 @@ static int vimc_deb_comp_bind(struct device *comp, struct device *master,
 	vdeb->src_code = MEDIA_BUS_FMT_RGB888_1X24;
 	vdeb->set_rgb_src = vimc_deb_set_rgb_mbus_fmt_rgb888_1x24;
 
-	return 0;
-}
-
-static const struct component_ops vimc_deb_comp_ops = {
-	.bind = vimc_deb_comp_bind,
-	.unbind = vimc_deb_comp_unbind,
-};
+	return &vdeb->ved;
 
-static int vimc_deb_probe(struct platform_device *pdev)
-{
-	return component_add(&pdev->dev, &vimc_deb_comp_ops);
-}
-
-static int vimc_deb_remove(struct platform_device *pdev)
-{
-	component_del(&pdev->dev, &vimc_deb_comp_ops);
+err_free_hdl:
+	v4l2_ctrl_handler_free(&vdeb->hdl);
+err_free_vdeb:
+	kfree(vdeb);
 
-	return 0;
+	return NULL;
 }
-
-static const struct platform_device_id vimc_deb_driver_ids[] = {
-	{
-		.name           = VIMC_DEB_DRV_NAME,
-	},
-	{ }
-};
-
-static struct platform_driver vimc_deb_pdrv = {
-	.probe		= vimc_deb_probe,
-	.remove		= vimc_deb_remove,
-	.id_table	= vimc_deb_driver_ids,
-	.driver		= {
-		.name	= VIMC_DEB_DRV_NAME,
-	},
-};
-
-module_platform_driver(vimc_deb_pdrv);
-
-MODULE_DEVICE_TABLE(platform, vimc_deb_driver_ids);
-
-MODULE_DESCRIPTION("Virtual Media Controller Driver (VIMC) Debayer");
-MODULE_AUTHOR("Helen Mae Koike Fornazier <helen.fornazier@gmail.com>");
-MODULE_LICENSE("GPL");
diff --git a/drivers/media/platform/vimc/vimc-scaler.c b/drivers/media/platform/vimc/vimc-scaler.c
index 49ab8d9dd9c9..2f88a7d9d67b 100644
--- a/drivers/media/platform/vimc/vimc-scaler.c
+++ b/drivers/media/platform/vimc/vimc-scaler.c
@@ -5,30 +5,22 @@
  * Copyright (C) 2015-2017 Helen Koike <helen.fornazier@gmail.com>
  */
 
-#include <linux/component.h>
-#include <linux/module.h>
-#include <linux/mod_devicetable.h>
-#include <linux/platform_device.h>
+#include <linux/moduleparam.h>
 #include <linux/vmalloc.h>
 #include <linux/v4l2-mediabus.h>
 #include <media/v4l2-subdev.h>
 
 #include "vimc-common.h"
 
-#define VIMC_SCA_DRV_NAME "vimc-scaler"
-
 static unsigned int sca_mult = 3;
 module_param(sca_mult, uint, 0000);
 MODULE_PARM_DESC(sca_mult, " the image size multiplier");
 
-#define IS_SINK(pad)	(!pad)
-#define IS_SRC(pad)	(pad)
 #define MAX_ZOOM	8
 
 struct vimc_sca_device {
 	struct vimc_ent_device ved;
 	struct v4l2_subdev sd;
-	struct device *dev;
 	/* NOTE: the source fmt is the same as the sink
 	 * with the width and hight multiplied by mult
 	 */
@@ -37,6 +29,7 @@ struct vimc_sca_device {
 	u8 *src_frame;
 	unsigned int src_line_size;
 	unsigned int bpp;
+	struct media_pad pads[2];
 };
 
 static const struct v4l2_mbus_framefmt sink_fmt_default = {
@@ -98,7 +91,7 @@ static int vimc_sca_enum_frame_size(struct v4l2_subdev *sd,
 	fse->min_width = VIMC_FRAME_MIN_WIDTH;
 	fse->min_height = VIMC_FRAME_MIN_HEIGHT;
 
-	if (IS_SINK(fse->pad)) {
+	if (VIMC_IS_SINK(fse->pad)) {
 		fse->max_width = VIMC_FRAME_MAX_WIDTH;
 		fse->max_height = VIMC_FRAME_MAX_HEIGHT;
 	} else {
@@ -121,7 +114,7 @@ static int vimc_sca_get_fmt(struct v4l2_subdev *sd,
 			 vsca->sink_fmt;
 
 	/* Scale the frame size for the source pad */
-	if (IS_SRC(format->pad)) {
+	if (VIMC_IS_SRC(format->pad)) {
 		format->format.width = vsca->sink_fmt.width * sca_mult;
 		format->format.height = vsca->sink_fmt.height * sca_mult;
 	}
@@ -170,7 +163,7 @@ static int vimc_sca_set_fmt(struct v4l2_subdev *sd,
 	 * Do not change the format of the source pad,
 	 * it is propagated from the sink
 	 */
-	if (IS_SRC(fmt->pad)) {
+	if (VIMC_IS_SRC(fmt->pad)) {
 		fmt->format = *sink_fmt;
 		fmt->format.width = sink_fmt->width * sca_mult;
 		fmt->format.height = sink_fmt->height * sca_mult;
@@ -178,7 +171,7 @@ static int vimc_sca_set_fmt(struct v4l2_subdev *sd,
 		/* Set the new format in the sink pad */
 		vimc_sca_adjust_sink_fmt(&fmt->format);
 
-		dev_dbg(vsca->dev, "%s: sink format update: "
+		dev_dbg(vsca->ved.dev, "%s: sink format update: "
 			"old:%dx%d (0x%x, %d, %d, %d, %d) "
 			"new:%dx%d (0x%x, %d, %d, %d, %d)\n", vsca->sd.name,
 			/* old */
@@ -278,7 +271,7 @@ static void vimc_sca_scale_pix(const struct vimc_sca_device *const vsca,
 				 vsca->bpp);
 	pixel = &sink_frame[index];
 
-	dev_dbg(vsca->dev,
+	dev_dbg(vsca->ved.dev,
 		"sca: %s: --- scale_pix sink pos %dx%d, index %d ---\n",
 		vsca->sd.name, lin, col, index);
 
@@ -288,7 +281,7 @@ static void vimc_sca_scale_pix(const struct vimc_sca_device *const vsca,
 	index = VIMC_FRAME_INDEX(lin * sca_mult, col * sca_mult,
 				 vsca->sink_fmt.width * sca_mult, vsca->bpp);
 
-	dev_dbg(vsca->dev, "sca: %s: scale_pix src pos %dx%d, index %d\n",
+	dev_dbg(vsca->ved.dev, "sca: %s: scale_pix src pos %dx%d, index %d\n",
 		vsca->sd.name, lin * sca_mult, col * sca_mult, index);
 
 	/* Repeat this pixel mult times */
@@ -297,7 +290,7 @@ static void vimc_sca_scale_pix(const struct vimc_sca_device *const vsca,
 		 * pixel repetition in a line
 		 */
 		for (j = 0; j < sca_mult * vsca->bpp; j += vsca->bpp) {
-			dev_dbg(vsca->dev,
+			dev_dbg(vsca->ved.dev,
 				"sca: %s: sca: scale_pix src pos %d\n",
 				vsca->sd.name, index + j);
 
@@ -343,6 +336,7 @@ static void vimc_sca_release(struct v4l2_subdev *sd)
 	struct vimc_sca_device *vsca =
 				container_of(sd, struct vimc_sca_device, sd);
 
+	media_entity_cleanup(vsca->ved.ent);
 	kfree(vsca);
 }
 
@@ -350,89 +344,45 @@ static const struct v4l2_subdev_internal_ops vimc_sca_int_ops = {
 	.release = vimc_sca_release,
 };
 
-static void vimc_sca_comp_unbind(struct device *comp, struct device *master,
-				 void *master_data)
+void vimc_sca_rm(struct vimc_device *vimc, struct vimc_ent_device *ved)
 {
-	struct vimc_ent_device *ved = dev_get_drvdata(comp);
-	struct vimc_sca_device *vsca = container_of(ved, struct vimc_sca_device,
-						    ved);
+	struct vimc_sca_device *vsca;
 
-	vimc_ent_sd_unregister(ved, &vsca->sd);
+	vsca = container_of(ved, struct vimc_sca_device, ved);
+	v4l2_device_unregister_subdev(&vsca->sd);
 }
 
-
-static int vimc_sca_comp_bind(struct device *comp, struct device *master,
-			      void *master_data)
+struct vimc_ent_device *vimc_sca_add(struct vimc_device *vimc,
+				     const char *vcfg_name)
 {
-	struct v4l2_device *v4l2_dev = master_data;
-	struct vimc_platform_data *pdata = comp->platform_data;
+	struct v4l2_device *v4l2_dev = &vimc->v4l2_dev;
 	struct vimc_sca_device *vsca;
 	int ret;
 
 	/* Allocate the vsca struct */
 	vsca = kzalloc(sizeof(*vsca), GFP_KERNEL);
 	if (!vsca)
-		return -ENOMEM;
+		return NULL;
 
 	/* Initialize ved and sd */
+	vsca->pads[0].flags = MEDIA_PAD_FL_SINK;
+	vsca->pads[1].flags = MEDIA_PAD_FL_SOURCE;
+
 	ret = vimc_ent_sd_register(&vsca->ved, &vsca->sd, v4l2_dev,
-				   pdata->entity_name,
+				   vcfg_name,
 				   MEDIA_ENT_F_PROC_VIDEO_SCALER, 2,
-				   (const unsigned long[2]) {MEDIA_PAD_FL_SINK,
-				   MEDIA_PAD_FL_SOURCE},
+				   vsca->pads,
 				   &vimc_sca_int_ops, &vimc_sca_ops);
 	if (ret) {
 		kfree(vsca);
-		return ret;
+		return NULL;
 	}
 
 	vsca->ved.process_frame = vimc_sca_process_frame;
-	dev_set_drvdata(comp, &vsca->ved);
-	vsca->dev = comp;
+	vsca->ved.dev = &vimc->pdev.dev;
 
 	/* Initialize the frame format */
 	vsca->sink_fmt = sink_fmt_default;
 
-	return 0;
-}
-
-static const struct component_ops vimc_sca_comp_ops = {
-	.bind = vimc_sca_comp_bind,
-	.unbind = vimc_sca_comp_unbind,
-};
-
-static int vimc_sca_probe(struct platform_device *pdev)
-{
-	return component_add(&pdev->dev, &vimc_sca_comp_ops);
-}
-
-static int vimc_sca_remove(struct platform_device *pdev)
-{
-	component_del(&pdev->dev, &vimc_sca_comp_ops);
-
-	return 0;
+	return &vsca->ved;
 }
-
-static const struct platform_device_id vimc_sca_driver_ids[] = {
-	{
-		.name           = VIMC_SCA_DRV_NAME,
-	},
-	{ }
-};
-
-static struct platform_driver vimc_sca_pdrv = {
-	.probe		= vimc_sca_probe,
-	.remove		= vimc_sca_remove,
-	.id_table	= vimc_sca_driver_ids,
-	.driver		= {
-		.name	= VIMC_SCA_DRV_NAME,
-	},
-};
-
-module_platform_driver(vimc_sca_pdrv);
-
-MODULE_DEVICE_TABLE(platform, vimc_sca_driver_ids);
-
-MODULE_DESCRIPTION("Virtual Media Controller Driver (VIMC) Scaler");
-MODULE_AUTHOR("Helen Mae Koike Fornazier <helen.fornazier@gmail.com>");
-MODULE_LICENSE("GPL");
diff --git a/drivers/media/platform/vimc/vimc-sensor.c b/drivers/media/platform/vimc/vimc-sensor.c
index 6c53b9fc1617..32380f504591 100644
--- a/drivers/media/platform/vimc/vimc-sensor.c
+++ b/drivers/media/platform/vimc/vimc-sensor.c
@@ -5,10 +5,6 @@
  * Copyright (C) 2015-2017 Helen Koike <helen.fornazier@gmail.com>
  */
 
-#include <linux/component.h>
-#include <linux/module.h>
-#include <linux/mod_devicetable.h>
-#include <linux/platform_device.h>
 #include <linux/v4l2-mediabus.h>
 #include <linux/vmalloc.h>
 #include <media/v4l2-ctrls.h>
@@ -18,18 +14,15 @@
 
 #include "vimc-common.h"
 
-#define VIMC_SEN_DRV_NAME "vimc-sensor"
-
 struct vimc_sen_device {
 	struct vimc_ent_device ved;
 	struct v4l2_subdev sd;
-	struct device *dev;
 	struct tpg_data tpg;
-	struct task_struct *kthread_sen;
 	u8 *frame;
 	/* The active format */
 	struct v4l2_mbus_framefmt mbus_format;
 	struct v4l2_ctrl_handler hdl;
+	struct media_pad pad;
 };
 
 static const struct v4l2_mbus_framefmt fmt_default = {
@@ -164,7 +157,7 @@ static int vimc_sen_set_fmt(struct v4l2_subdev *sd,
 	/* Set the new format */
 	vimc_sen_adjust_fmt(&fmt->format);
 
-	dev_dbg(vsen->dev, "%s: format update: "
+	dev_dbg(vsen->ved.dev, "%s: format update: "
 		"old:%dx%d (0x%x, %d, %d, %d, %d) "
 		"new:%dx%d (0x%x, %d, %d, %d, %d)\n", vsen->sd.name,
 		/* old */
@@ -208,10 +201,6 @@ static int vimc_sen_s_stream(struct v4l2_subdev *sd, int enable)
 		const struct vimc_pix_map *vpix;
 		unsigned int frame_size;
 
-		if (vsen->kthread_sen)
-			/* tpg is already executing */
-			return 0;
-
 		/* Calculate the frame size */
 		vpix = vimc_pix_map_by_code(vsen->mbus_format.code);
 		frame_size = vsen->mbus_format.width * vpix->bpp *
@@ -297,6 +286,7 @@ static void vimc_sen_release(struct v4l2_subdev *sd)
 
 	v4l2_ctrl_handler_free(&vsen->hdl);
 	tpg_free(&vsen->tpg);
+	media_entity_cleanup(vsen->ved.ent);
 	kfree(vsen);
 }
 
@@ -304,14 +294,12 @@ static const struct v4l2_subdev_internal_ops vimc_sen_int_ops = {
 	.release = vimc_sen_release,
 };
 
-static void vimc_sen_comp_unbind(struct device *comp, struct device *master,
-				 void *master_data)
+void vimc_sen_rm(struct vimc_device *vimc, struct vimc_ent_device *ved)
 {
-	struct vimc_ent_device *ved = dev_get_drvdata(comp);
-	struct vimc_sen_device *vsen =
-				container_of(ved, struct vimc_sen_device, ved);
+	struct vimc_sen_device *vsen;
 
-	vimc_ent_sd_unregister(ved, &vsen->sd);
+	vsen = container_of(ved, struct vimc_sen_device, ved);
+	v4l2_device_unregister_subdev(&vsen->sd);
 }
 
 /* Image Processing Controls */
@@ -331,18 +319,17 @@ static const struct v4l2_ctrl_config vimc_sen_ctrl_test_pattern = {
 	.qmenu = tpg_pattern_strings,
 };
 
-static int vimc_sen_comp_bind(struct device *comp, struct device *master,
-			      void *master_data)
+struct vimc_ent_device *vimc_sen_add(struct vimc_device *vimc,
+				     const char *vcfg_name)
 {
-	struct v4l2_device *v4l2_dev = master_data;
-	struct vimc_platform_data *pdata = comp->platform_data;
+	struct v4l2_device *v4l2_dev = &vimc->v4l2_dev;
 	struct vimc_sen_device *vsen;
 	int ret;
 
 	/* Allocate the vsen struct */
 	vsen = kzalloc(sizeof(*vsen), GFP_KERNEL);
 	if (!vsen)
-		return -ENOMEM;
+		return NULL;
 
 	v4l2_ctrl_handler_init(&vsen->hdl, 4);
 
@@ -366,78 +353,36 @@ static int vimc_sen_comp_bind(struct device *comp, struct device *master,
 		goto err_free_vsen;
 	}
 
+	/* Initialize the test pattern generator */
+	tpg_init(&vsen->tpg, vsen->mbus_format.width,
+		 vsen->mbus_format.height);
+	ret = tpg_alloc(&vsen->tpg, VIMC_FRAME_MAX_WIDTH);
+	if (ret)
+		goto err_free_hdl;
+
 	/* Initialize ved and sd */
+	vsen->pad.flags = MEDIA_PAD_FL_SOURCE;
 	ret = vimc_ent_sd_register(&vsen->ved, &vsen->sd, v4l2_dev,
-				   pdata->entity_name,
-				   MEDIA_ENT_F_CAM_SENSOR, 1,
-				   (const unsigned long[1]) {MEDIA_PAD_FL_SOURCE},
+				   vcfg_name,
+				   MEDIA_ENT_F_CAM_SENSOR, 1, &vsen->pad,
 				   &vimc_sen_int_ops, &vimc_sen_ops);
 	if (ret)
-		goto err_free_hdl;
+		goto err_free_tpg;
 
 	vsen->ved.process_frame = vimc_sen_process_frame;
-	dev_set_drvdata(comp, &vsen->ved);
-	vsen->dev = comp;
+	vsen->ved.dev = &vimc->pdev.dev;
 
 	/* Initialize the frame format */
 	vsen->mbus_format = fmt_default;
 
-	/* Initialize the test pattern generator */
-	tpg_init(&vsen->tpg, vsen->mbus_format.width,
-		 vsen->mbus_format.height);
-	ret = tpg_alloc(&vsen->tpg, VIMC_FRAME_MAX_WIDTH);
-	if (ret)
-		goto err_unregister_ent_sd;
-
-	return 0;
+	return &vsen->ved;
 
-err_unregister_ent_sd:
-	vimc_ent_sd_unregister(&vsen->ved,  &vsen->sd);
+err_free_tpg:
+	tpg_free(&vsen->tpg);
 err_free_hdl:
 	v4l2_ctrl_handler_free(&vsen->hdl);
 err_free_vsen:
 	kfree(vsen);
 
-	return ret;
-}
-
-static const struct component_ops vimc_sen_comp_ops = {
-	.bind = vimc_sen_comp_bind,
-	.unbind = vimc_sen_comp_unbind,
-};
-
-static int vimc_sen_probe(struct platform_device *pdev)
-{
-	return component_add(&pdev->dev, &vimc_sen_comp_ops);
-}
-
-static int vimc_sen_remove(struct platform_device *pdev)
-{
-	component_del(&pdev->dev, &vimc_sen_comp_ops);
-
-	return 0;
+	return NULL;
 }
-
-static const struct platform_device_id vimc_sen_driver_ids[] = {
-	{
-		.name           = VIMC_SEN_DRV_NAME,
-	},
-	{ }
-};
-
-static struct platform_driver vimc_sen_pdrv = {
-	.probe		= vimc_sen_probe,
-	.remove		= vimc_sen_remove,
-	.id_table	= vimc_sen_driver_ids,
-	.driver		= {
-		.name	= VIMC_SEN_DRV_NAME,
-	},
-};
-
-module_platform_driver(vimc_sen_pdrv);
-
-MODULE_DEVICE_TABLE(platform, vimc_sen_driver_ids);
-
-MODULE_DESCRIPTION("Virtual Media Controller Driver (VIMC) Sensor");
-MODULE_AUTHOR("Helen Mae Koike Fornazier <helen.fornazier@gmail.com>");
-MODULE_LICENSE("GPL");
diff --git a/drivers/media/platform/vimc/vimc-streamer.c b/drivers/media/platform/vimc/vimc-streamer.c
index 048d770e498b..cd6b55433c9e 100644
--- a/drivers/media/platform/vimc/vimc-streamer.c
+++ b/drivers/media/platform/vimc/vimc-streamer.c
@@ -7,7 +7,6 @@
  */
 
 #include <linux/init.h>
-#include <linux/module.h>
 #include <linux/freezer.h>
 #include <linux/kthread.h>
 
@@ -97,17 +96,26 @@ static int vimc_streamer_pipeline_init(struct vimc_stream *stream,
 			sd = media_entity_to_v4l2_subdev(ved->ent);
 			ret = v4l2_subdev_call(sd, video, s_stream, 1);
 			if (ret && ret != -ENOIOCTLCMD) {
-				pr_err("subdev_call error %s\n",
-				       ved->ent->name);
+				dev_err(ved->dev, "subdev_call error %s\n",
+					ved->ent->name);
 				vimc_streamer_pipeline_terminate(stream);
 				return ret;
 			}
 		}
 
 		entity = vimc_get_source_entity(ved->ent);
-		/* Check if the end of the pipeline was reached*/
-		if (!entity)
+		/* Check if the end of the pipeline was reached */
+		if (!entity) {
+			/* the first entity of the pipe should be source only */
+			if (!vimc_is_source(ved->ent)) {
+				dev_err(ved->dev,
+					"first entity in the pipe '%s' is not a source\n",
+					ved->ent->name);
+				vimc_streamer_pipeline_terminate(stream);
+				return -EPIPE;
+			}
 			return 0;
+		}
 
 		/* Get the next device in the pipeline */
 		if (is_media_entity_v4l2_subdev(entity)) {
@@ -217,4 +225,3 @@ int vimc_streamer_s_stream(struct vimc_stream *stream,
 
 	return 0;
 }
-EXPORT_SYMBOL_GPL(vimc_streamer_s_stream);
diff --git a/drivers/media/platform/vivid/Makefile b/drivers/media/platform/vivid/Makefile
index 2f5762e3309a..e8a50c506dc9 100644
--- a/drivers/media/platform/vivid/Makefile
+++ b/drivers/media/platform/vivid/Makefile
@@ -3,7 +3,7 @@ vivid-objs := vivid-core.o vivid-ctrls.o vivid-vid-common.o vivid-vbi-gen.o \
 		vivid-vid-cap.o vivid-vid-out.o vivid-kthread-cap.o vivid-kthread-out.o \
 		vivid-radio-rx.o vivid-radio-tx.o vivid-radio-common.o \
 		vivid-rds-gen.o vivid-sdr-cap.o vivid-vbi-cap.o vivid-vbi-out.o \
-		vivid-osd.o
+		vivid-osd.o vivid-meta-cap.o vivid-meta-out.o
 ifeq ($(CONFIG_VIDEO_VIVID_CEC),y)
   vivid-objs += vivid-cec.o
 endif
diff --git a/drivers/media/platform/vivid/vivid-cec.c b/drivers/media/platform/vivid/vivid-cec.c
index 4d822dbed972..4d2413e87730 100644
--- a/drivers/media/platform/vivid/vivid-cec.c
+++ b/drivers/media/platform/vivid/vivid-cec.c
@@ -276,12 +276,11 @@ struct cec_adapter *vivid_cec_alloc_adap(struct vivid_dev *dev,
 					 unsigned int idx,
 					 bool is_source)
 {
-	char name[sizeof(dev->vid_out_dev.name) + 2];
 	u32 caps = CEC_CAP_DEFAULTS | CEC_CAP_MONITOR_ALL | CEC_CAP_MONITOR_PIN;
+	char name[32];
 
-	snprintf(name, sizeof(name), "%s%d",
-		 is_source ? dev->vid_out_dev.name : dev->vid_cap_dev.name,
-		 idx);
+	snprintf(name, sizeof(name), "vivid-%03d-vid-%s%d",
+		 dev->inst, is_source ? "out" : "cap", idx);
 	return cec_allocate_adapter(&vivid_cec_adap_ops, dev,
 		name, caps, 1);
 }
diff --git a/drivers/media/platform/vivid/vivid-core.c b/drivers/media/platform/vivid/vivid-core.c
index 53315c8dd2bb..c184f9b0be69 100644
--- a/drivers/media/platform/vivid/vivid-core.c
+++ b/drivers/media/platform/vivid/vivid-core.c
@@ -37,6 +37,8 @@
 #include "vivid-osd.h"
 #include "vivid-cec.h"
 #include "vivid-ctrls.h"
+#include "vivid-meta-cap.h"
+#include "vivid-meta-out.h"
 
 #define VIVID_MODULE_NAME "vivid"
 
@@ -79,6 +81,14 @@ static int radio_tx_nr[VIVID_MAX_DEVS] = { [0 ... (VIVID_MAX_DEVS - 1)] = -1 };
 module_param_array(radio_tx_nr, int, NULL, 0444);
 MODULE_PARM_DESC(radio_tx_nr, " radioX start number, -1 is autodetect");
 
+static int meta_cap_nr[VIVID_MAX_DEVS] = { [0 ... (VIVID_MAX_DEVS - 1)] = -1 };
+module_param_array(meta_cap_nr, int, NULL, 0444);
+MODULE_PARM_DESC(meta_cap_nr, " videoX start number, -1 is autodetect");
+
+static int meta_out_nr[VIVID_MAX_DEVS] = { [0 ... (VIVID_MAX_DEVS - 1)] = -1 };
+module_param_array(meta_out_nr, int, NULL, 0444);
+MODULE_PARM_DESC(meta_out_nr, " videoX start number, -1 is autodetect");
+
 static int ccs_cap_mode[VIVID_MAX_DEVS] = { [0 ... (VIVID_MAX_DEVS - 1)] = -1 };
 module_param_array(ccs_cap_mode, int, NULL, 0444);
 MODULE_PARM_DESC(ccs_cap_mode, " capture crop/compose/scale mode:\n"
@@ -95,10 +105,15 @@ static unsigned multiplanar[VIVID_MAX_DEVS] = { [0 ... (VIVID_MAX_DEVS - 1)] = 1
 module_param_array(multiplanar, uint, NULL, 0444);
 MODULE_PARM_DESC(multiplanar, " 1 (default) creates a single planar device, 2 creates a multiplanar device.");
 
-/* Default: video + vbi-cap (raw and sliced) + radio rx + radio tx + sdr + vbi-out + vid-out */
-static unsigned node_types[VIVID_MAX_DEVS] = { [0 ... (VIVID_MAX_DEVS - 1)] = 0x1d3d };
+/*
+ * Default: video + vbi-cap (raw and sliced) + radio rx + radio tx + sdr +
+ * vbi-out + vid-out + meta-cap
+ */
+static unsigned int node_types[VIVID_MAX_DEVS] = {
+	[0 ... (VIVID_MAX_DEVS - 1)] = 0x61d3d
+};
 module_param_array(node_types, uint, NULL, 0444);
-MODULE_PARM_DESC(node_types, " node types, default is 0x1d3d. Bitmask with the following meaning:\n"
+MODULE_PARM_DESC(node_types, " node types, default is 0x61d3d. Bitmask with the following meaning:\n"
 			     "\t\t    bit 0: Video Capture node\n"
 			     "\t\t    bit 2-3: VBI Capture node: 0 = none, 1 = raw vbi, 2 = sliced vbi, 3 = both\n"
 			     "\t\t    bit 4: Radio Receiver node\n"
@@ -106,7 +121,9 @@ MODULE_PARM_DESC(node_types, " node types, default is 0x1d3d. Bitmask with the f
 			     "\t\t    bit 8: Video Output node\n"
 			     "\t\t    bit 10-11: VBI Output node: 0 = none, 1 = raw vbi, 2 = sliced vbi, 3 = both\n"
 			     "\t\t    bit 12: Radio Transmitter node\n"
-			     "\t\t    bit 16: Framebuffer for testing overlays");
+			     "\t\t    bit 16: Framebuffer for testing overlays\n"
+			     "\t\t    bit 17: Metadata Capture node\n"
+			     "\t\t    bit 18: Metadata Output node\n");
 
 /* Default: 4 inputs */
 static unsigned num_inputs[VIVID_MAX_DEVS] = { [0 ... (VIVID_MAX_DEVS - 1)] = 4 };
@@ -205,7 +222,8 @@ static int vidioc_querycap(struct file *file, void  *priv,
 	cap->capabilities = dev->vid_cap_caps | dev->vid_out_caps |
 		dev->vbi_cap_caps | dev->vbi_out_caps |
 		dev->radio_rx_caps | dev->radio_tx_caps |
-		dev->sdr_cap_caps | V4L2_CAP_DEVICE_CAPS;
+		dev->sdr_cap_caps | dev->meta_cap_caps |
+		dev->meta_out_caps | V4L2_CAP_DEVICE_CAPS;
 	return 0;
 }
 
@@ -433,7 +451,9 @@ static bool vivid_is_last_user(struct vivid_dev *dev)
 			vivid_is_in_use(&dev->vbi_out_dev) +
 			vivid_is_in_use(&dev->sdr_cap_dev) +
 			vivid_is_in_use(&dev->radio_rx_dev) +
-			vivid_is_in_use(&dev->radio_tx_dev);
+			vivid_is_in_use(&dev->radio_tx_dev) +
+			vivid_is_in_use(&dev->meta_cap_dev) +
+			vivid_is_in_use(&dev->meta_out_dev);
 
 	return uses == 1;
 }
@@ -459,6 +479,8 @@ static int vivid_fop_release(struct file *file)
 		set_bit(V4L2_FL_REGISTERED, &dev->sdr_cap_dev.flags);
 		set_bit(V4L2_FL_REGISTERED, &dev->radio_rx_dev.flags);
 		set_bit(V4L2_FL_REGISTERED, &dev->radio_tx_dev.flags);
+		set_bit(V4L2_FL_REGISTERED, &dev->meta_cap_dev.flags);
+		set_bit(V4L2_FL_REGISTERED, &dev->meta_out_dev.flags);
 	}
 	mutex_unlock(&dev->mutex);
 	if (file->private_data == dev->overlay_cap_owner)
@@ -604,6 +626,16 @@ static const struct v4l2_ioctl_ops vivid_ioctl_ops = {
 	.vidioc_log_status		= vidioc_log_status,
 	.vidioc_subscribe_event		= vidioc_subscribe_event,
 	.vidioc_unsubscribe_event	= v4l2_event_unsubscribe,
+
+	.vidioc_enum_fmt_meta_cap	= vidioc_enum_fmt_meta_cap,
+	.vidioc_g_fmt_meta_cap		= vidioc_g_fmt_meta_cap,
+	.vidioc_s_fmt_meta_cap		= vidioc_g_fmt_meta_cap,
+	.vidioc_try_fmt_meta_cap	= vidioc_g_fmt_meta_cap,
+
+	.vidioc_enum_fmt_meta_out       = vidioc_enum_fmt_meta_out,
+	.vidioc_g_fmt_meta_out          = vidioc_g_fmt_meta_out,
+	.vidioc_s_fmt_meta_out          = vidioc_g_fmt_meta_out,
+	.vidioc_try_fmt_meta_out        = vidioc_g_fmt_meta_out,
 };
 
 /* -----------------------------------------------------------------
@@ -616,6 +648,9 @@ static void vivid_dev_release(struct v4l2_device *v4l2_dev)
 
 	vivid_free_controls(dev);
 	v4l2_device_unregister(&dev->v4l2_dev);
+#ifdef CONFIG_MEDIA_CONTROLLER
+	media_device_cleanup(&dev->mdev);
+#endif
 	vfree(dev->scaled_line);
 	vfree(dev->blended_line);
 	vfree(dev->edid);
@@ -645,14 +680,44 @@ static const struct media_device_ops vivid_media_ops = {
 };
 #endif
 
+static int vivid_create_queue(struct vivid_dev *dev,
+			      struct vb2_queue *q,
+			      u32 buf_type,
+			      unsigned int min_buffers_needed,
+			      const struct vb2_ops *ops)
+{
+	if (buf_type == V4L2_BUF_TYPE_VIDEO_CAPTURE && dev->multiplanar)
+		buf_type = V4L2_BUF_TYPE_VIDEO_CAPTURE_MPLANE;
+	else if (buf_type == V4L2_BUF_TYPE_VIDEO_OUTPUT && dev->multiplanar)
+		buf_type = V4L2_BUF_TYPE_VIDEO_OUTPUT_MPLANE;
+	else if (buf_type == V4L2_BUF_TYPE_VBI_CAPTURE && !dev->has_raw_vbi_cap)
+		buf_type = V4L2_BUF_TYPE_SLICED_VBI_CAPTURE;
+	else if (buf_type == V4L2_BUF_TYPE_VBI_OUTPUT && !dev->has_raw_vbi_out)
+		buf_type = V4L2_BUF_TYPE_SLICED_VBI_OUTPUT;
+
+	q->type = buf_type;
+	q->io_modes = VB2_MMAP | VB2_DMABUF;
+	q->io_modes |= V4L2_TYPE_IS_OUTPUT(buf_type) ?  VB2_WRITE : VB2_READ;
+	if (allocators[dev->inst] != 1)
+		q->io_modes |= VB2_USERPTR;
+	q->drv_priv = dev;
+	q->buf_struct_size = sizeof(struct vivid_buffer);
+	q->ops = ops;
+	q->mem_ops = allocators[dev->inst] == 1 ? &vb2_dma_contig_memops :
+						  &vb2_vmalloc_memops;
+	q->timestamp_flags = V4L2_BUF_FLAG_TIMESTAMP_MONOTONIC;
+	q->min_buffers_needed = min_buffers_needed;
+	q->lock = &dev->mutex;
+	q->dev = dev->v4l2_dev.dev;
+	q->supports_requests = true;
+
+	return vb2_queue_init(q);
+}
+
 static int vivid_create_instance(struct platform_device *pdev, int inst)
 {
 	static const struct v4l2_dv_timings def_dv_timings =
 					V4L2_DV_BT_CEA_1280X720P60;
-	static const struct vb2_mem_ops * const vivid_mem_ops[2] = {
-		&vb2_vmalloc_memops,
-		&vb2_dma_contig_memops,
-	};
 	unsigned in_type_counter[4] = { 0, 0, 0, 0 };
 	unsigned out_type_counter[4] = { 0, 0, 0, 0 };
 	int ccs_cap = ccs_cap_mode[inst];
@@ -661,9 +726,7 @@ static int vivid_create_instance(struct platform_device *pdev, int inst)
 	bool has_modulator;
 	struct vivid_dev *dev;
 	struct video_device *vfd;
-	struct vb2_queue *q;
 	unsigned node_type = node_types[inst];
-	unsigned int allocator = allocators[inst];
 	v4l2_std_id tvnorms_cap = 0, tvnorms_out = 0;
 	int ret;
 	int i;
@@ -758,6 +821,25 @@ static int vivid_create_instance(struct platform_device *pdev, int inst)
 		dev->has_vbi_cap = dev->has_raw_vbi_cap | dev->has_sliced_vbi_cap;
 	}
 
+	/* do we create a meta capture device */
+	dev->has_meta_cap = node_type & 0x20000;
+
+	/* sanity checks */
+	if ((in_type_counter[WEBCAM] || in_type_counter[HDMI]) &&
+	    !dev->has_vid_cap && !dev->has_meta_cap) {
+		v4l2_warn(&dev->v4l2_dev,
+			  "Webcam or HDMI input without video or metadata nodes\n");
+		kfree(dev);
+		return -EINVAL;
+	}
+	if ((in_type_counter[TV] || in_type_counter[SVID]) &&
+	    !dev->has_vid_cap && !dev->has_vbi_cap && !dev->has_meta_cap) {
+		v4l2_warn(&dev->v4l2_dev,
+			  "TV or S-Video input without video, VBI or metadata nodes\n");
+		kfree(dev);
+		return -EINVAL;
+	}
+
 	/* do we create a video output device? */
 	dev->has_vid_out = node_type & 0x0100;
 
@@ -768,6 +850,24 @@ static int vivid_create_instance(struct platform_device *pdev, int inst)
 		dev->has_vbi_out = dev->has_raw_vbi_out | dev->has_sliced_vbi_out;
 	}
 
+	/* do we create a metadata output device */
+	dev->has_meta_out = node_type & 0x40000;
+
+	/* sanity checks */
+	if (out_type_counter[SVID] &&
+	    !dev->has_vid_out && !dev->has_vbi_out && !dev->has_meta_out) {
+		v4l2_warn(&dev->v4l2_dev,
+			  "S-Video output without video, VBI or metadata nodes\n");
+		kfree(dev);
+		return -EINVAL;
+	}
+	if (out_type_counter[HDMI] && !dev->has_vid_out && !dev->has_meta_out) {
+		v4l2_warn(&dev->v4l2_dev,
+			  "HDMI output without video or metadata nodes\n");
+		kfree(dev);
+		return -EINVAL;
+	}
+
 	/* do we create a radio receiver device? */
 	dev->has_radio_rx = node_type & 0x0010;
 
@@ -777,6 +877,9 @@ static int vivid_create_instance(struct platform_device *pdev, int inst)
 	/* do we create a software defined radio capture device? */
 	dev->has_sdr_cap = node_type & 0x0020;
 
+	/* do we have a TV tuner? */
+	dev->has_tv_tuner = in_type_counter[TV];
+
 	/* do we have a tuner? */
 	has_tuner = ((dev->has_vid_cap || dev->has_vbi_cap) && in_type_counter[TV]) ||
 		    dev->has_radio_rx || dev->has_sdr_cap;
@@ -828,7 +931,7 @@ static int vivid_create_instance(struct platform_device *pdev, int inst)
 		dev->vid_cap_caps |= V4L2_CAP_STREAMING | V4L2_CAP_READWRITE;
 		if (dev->has_audio_inputs)
 			dev->vid_cap_caps |= V4L2_CAP_AUDIO;
-		if (in_type_counter[TV])
+		if (dev->has_tv_tuner)
 			dev->vid_cap_caps |= V4L2_CAP_TUNER;
 	}
 	if (dev->has_vid_out) {
@@ -849,7 +952,7 @@ static int vivid_create_instance(struct platform_device *pdev, int inst)
 		dev->vbi_cap_caps |= V4L2_CAP_STREAMING | V4L2_CAP_READWRITE;
 		if (dev->has_audio_inputs)
 			dev->vbi_cap_caps |= V4L2_CAP_AUDIO;
-		if (in_type_counter[TV])
+		if (dev->has_tv_tuner)
 			dev->vbi_cap_caps |= V4L2_CAP_TUNER;
 	}
 	if (dev->has_vbi_out) {
@@ -875,6 +978,23 @@ static int vivid_create_instance(struct platform_device *pdev, int inst)
 		dev->radio_tx_caps = V4L2_CAP_RDS_OUTPUT | V4L2_CAP_MODULATOR |
 				     V4L2_CAP_READWRITE;
 
+	/* set up the capabilities of meta capture device */
+	if (dev->has_meta_cap) {
+		dev->meta_cap_caps = V4L2_CAP_META_CAPTURE |
+				     V4L2_CAP_STREAMING | V4L2_CAP_READWRITE;
+		if (dev->has_audio_inputs)
+			dev->meta_cap_caps |= V4L2_CAP_AUDIO;
+		if (dev->has_tv_tuner)
+			dev->meta_cap_caps |= V4L2_CAP_TUNER;
+	}
+	/* set up the capabilities of meta output device */
+	if (dev->has_meta_out) {
+		dev->meta_out_caps = V4L2_CAP_META_OUTPUT |
+				     V4L2_CAP_STREAMING | V4L2_CAP_READWRITE;
+		if (dev->has_audio_outputs)
+			dev->meta_out_caps |= V4L2_CAP_AUDIO;
+	}
+
 	ret = -ENOMEM;
 	/* initialize the test pattern generator */
 	tpg_init(&dev->tpg, 640, 360);
@@ -934,6 +1054,9 @@ static int vivid_create_instance(struct platform_device *pdev, int inst)
 		v4l2_disable_ioctl(&dev->vbi_cap_dev, VIDIOC_S_AUDIO);
 		v4l2_disable_ioctl(&dev->vbi_cap_dev, VIDIOC_G_AUDIO);
 		v4l2_disable_ioctl(&dev->vbi_cap_dev, VIDIOC_ENUMAUDIO);
+		v4l2_disable_ioctl(&dev->meta_cap_dev, VIDIOC_S_AUDIO);
+		v4l2_disable_ioctl(&dev->meta_cap_dev, VIDIOC_G_AUDIO);
+		v4l2_disable_ioctl(&dev->meta_cap_dev, VIDIOC_ENUMAUDIO);
 	}
 	if (!dev->has_audio_outputs) {
 		v4l2_disable_ioctl(&dev->vid_out_dev, VIDIOC_S_AUDOUT);
@@ -942,6 +1065,9 @@ static int vivid_create_instance(struct platform_device *pdev, int inst)
 		v4l2_disable_ioctl(&dev->vbi_out_dev, VIDIOC_S_AUDOUT);
 		v4l2_disable_ioctl(&dev->vbi_out_dev, VIDIOC_G_AUDOUT);
 		v4l2_disable_ioctl(&dev->vbi_out_dev, VIDIOC_ENUMAUDOUT);
+		v4l2_disable_ioctl(&dev->meta_out_dev, VIDIOC_S_AUDOUT);
+		v4l2_disable_ioctl(&dev->meta_out_dev, VIDIOC_G_AUDOUT);
+		v4l2_disable_ioctl(&dev->meta_out_dev, VIDIOC_ENUMAUDOUT);
 	}
 	if (!in_type_counter[TV] && !in_type_counter[SVID]) {
 		v4l2_disable_ioctl(&dev->vid_cap_dev, VIDIOC_S_STD);
@@ -959,12 +1085,16 @@ static int vivid_create_instance(struct platform_device *pdev, int inst)
 		v4l2_disable_ioctl(&dev->vid_cap_dev, VIDIOC_G_FREQUENCY);
 		v4l2_disable_ioctl(&dev->vbi_cap_dev, VIDIOC_S_FREQUENCY);
 		v4l2_disable_ioctl(&dev->vbi_cap_dev, VIDIOC_G_FREQUENCY);
+		v4l2_disable_ioctl(&dev->meta_cap_dev, VIDIOC_S_FREQUENCY);
+		v4l2_disable_ioctl(&dev->meta_cap_dev, VIDIOC_G_FREQUENCY);
 	}
 	if (!has_tuner) {
 		v4l2_disable_ioctl(&dev->vid_cap_dev, VIDIOC_S_TUNER);
 		v4l2_disable_ioctl(&dev->vid_cap_dev, VIDIOC_G_TUNER);
 		v4l2_disable_ioctl(&dev->vbi_cap_dev, VIDIOC_S_TUNER);
 		v4l2_disable_ioctl(&dev->vbi_cap_dev, VIDIOC_G_TUNER);
+		v4l2_disable_ioctl(&dev->meta_cap_dev, VIDIOC_S_TUNER);
+		v4l2_disable_ioctl(&dev->meta_cap_dev, VIDIOC_G_TUNER);
 	}
 	if (in_type_counter[HDMI] == 0) {
 		v4l2_disable_ioctl(&dev->vid_cap_dev, VIDIOC_S_EDID);
@@ -990,12 +1120,15 @@ static int vivid_create_instance(struct platform_device *pdev, int inst)
 	v4l2_disable_ioctl(&dev->vid_cap_dev, VIDIOC_S_HW_FREQ_SEEK);
 	v4l2_disable_ioctl(&dev->vbi_cap_dev, VIDIOC_S_HW_FREQ_SEEK);
 	v4l2_disable_ioctl(&dev->sdr_cap_dev, VIDIOC_S_HW_FREQ_SEEK);
+	v4l2_disable_ioctl(&dev->meta_cap_dev, VIDIOC_S_HW_FREQ_SEEK);
 	v4l2_disable_ioctl(&dev->vid_out_dev, VIDIOC_S_FREQUENCY);
 	v4l2_disable_ioctl(&dev->vid_out_dev, VIDIOC_G_FREQUENCY);
 	v4l2_disable_ioctl(&dev->vid_out_dev, VIDIOC_ENUM_FRAMESIZES);
 	v4l2_disable_ioctl(&dev->vid_out_dev, VIDIOC_ENUM_FRAMEINTERVALS);
 	v4l2_disable_ioctl(&dev->vbi_out_dev, VIDIOC_S_FREQUENCY);
 	v4l2_disable_ioctl(&dev->vbi_out_dev, VIDIOC_G_FREQUENCY);
+	v4l2_disable_ioctl(&dev->meta_out_dev, VIDIOC_S_FREQUENCY);
+	v4l2_disable_ioctl(&dev->meta_out_dev, VIDIOC_G_FREQUENCY);
 
 	/* configure internal data */
 	dev->fmt_cap = &vivid_formats[0];
@@ -1078,6 +1211,8 @@ static int vivid_create_instance(struct platform_device *pdev, int inst)
 	INIT_LIST_HEAD(&dev->vbi_cap_active);
 	INIT_LIST_HEAD(&dev->vbi_out_active);
 	INIT_LIST_HEAD(&dev->sdr_cap_active);
+	INIT_LIST_HEAD(&dev->meta_cap_active);
+	INIT_LIST_HEAD(&dev->meta_out_active);
 
 	INIT_LIST_HEAD(&dev->cec_work_list);
 	spin_lock_init(&dev->cec_slock);
@@ -1092,126 +1227,69 @@ static int vivid_create_instance(struct platform_device *pdev, int inst)
 		goto unreg_dev;
 	}
 
-	if (allocator == 1)
+	if (allocators[inst] == 1)
 		dma_coerce_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(32));
-	else if (allocator >= ARRAY_SIZE(vivid_mem_ops))
-		allocator = 0;
 
 	/* start creating the vb2 queues */
 	if (dev->has_vid_cap) {
-		snprintf(dev->vid_cap_dev.name, sizeof(dev->vid_cap_dev.name),
-			 "vivid-%03d-vid-cap", inst);
 		/* initialize vid_cap queue */
-		q = &dev->vb_vid_cap_q;
-		q->type = dev->multiplanar ? V4L2_BUF_TYPE_VIDEO_CAPTURE_MPLANE :
-			V4L2_BUF_TYPE_VIDEO_CAPTURE;
-		q->io_modes = VB2_MMAP | VB2_DMABUF | VB2_READ;
-		if (!allocator)
-			q->io_modes |= VB2_USERPTR;
-		q->drv_priv = dev;
-		q->buf_struct_size = sizeof(struct vivid_buffer);
-		q->ops = &vivid_vid_cap_qops;
-		q->mem_ops = vivid_mem_ops[allocator];
-		q->timestamp_flags = V4L2_BUF_FLAG_TIMESTAMP_MONOTONIC;
-		q->min_buffers_needed = 2;
-		q->lock = &dev->mutex;
-		q->dev = dev->v4l2_dev.dev;
-		q->supports_requests = true;
-
-		ret = vb2_queue_init(q);
+		ret = vivid_create_queue(dev, &dev->vb_vid_cap_q,
+					 V4L2_BUF_TYPE_VIDEO_CAPTURE, 2,
+					 &vivid_vid_cap_qops);
 		if (ret)
 			goto unreg_dev;
 	}
 
 	if (dev->has_vid_out) {
-		snprintf(dev->vid_out_dev.name, sizeof(dev->vid_out_dev.name),
-			 "vivid-%03d-vid-out", inst);
 		/* initialize vid_out queue */
-		q = &dev->vb_vid_out_q;
-		q->type = dev->multiplanar ? V4L2_BUF_TYPE_VIDEO_OUTPUT_MPLANE :
-			V4L2_BUF_TYPE_VIDEO_OUTPUT;
-		q->io_modes = VB2_MMAP | VB2_DMABUF | VB2_WRITE;
-		if (!allocator)
-			q->io_modes |= VB2_USERPTR;
-		q->drv_priv = dev;
-		q->buf_struct_size = sizeof(struct vivid_buffer);
-		q->ops = &vivid_vid_out_qops;
-		q->mem_ops = vivid_mem_ops[allocator];
-		q->timestamp_flags = V4L2_BUF_FLAG_TIMESTAMP_MONOTONIC;
-		q->min_buffers_needed = 2;
-		q->lock = &dev->mutex;
-		q->dev = dev->v4l2_dev.dev;
-		q->supports_requests = true;
-
-		ret = vb2_queue_init(q);
+		ret = vivid_create_queue(dev, &dev->vb_vid_out_q,
+					 V4L2_BUF_TYPE_VIDEO_OUTPUT, 2,
+					 &vivid_vid_out_qops);
 		if (ret)
 			goto unreg_dev;
 	}
 
 	if (dev->has_vbi_cap) {
 		/* initialize vbi_cap queue */
-		q = &dev->vb_vbi_cap_q;
-		q->type = dev->has_raw_vbi_cap ? V4L2_BUF_TYPE_VBI_CAPTURE :
-					      V4L2_BUF_TYPE_SLICED_VBI_CAPTURE;
-		q->io_modes = VB2_MMAP | VB2_DMABUF | VB2_READ;
-		if (!allocator)
-			q->io_modes |= VB2_USERPTR;
-		q->drv_priv = dev;
-		q->buf_struct_size = sizeof(struct vivid_buffer);
-		q->ops = &vivid_vbi_cap_qops;
-		q->mem_ops = vivid_mem_ops[allocator];
-		q->timestamp_flags = V4L2_BUF_FLAG_TIMESTAMP_MONOTONIC;
-		q->min_buffers_needed = 2;
-		q->lock = &dev->mutex;
-		q->dev = dev->v4l2_dev.dev;
-		q->supports_requests = true;
-
-		ret = vb2_queue_init(q);
+		ret = vivid_create_queue(dev, &dev->vb_vbi_cap_q,
+					 V4L2_BUF_TYPE_VBI_CAPTURE, 2,
+					 &vivid_vbi_cap_qops);
 		if (ret)
 			goto unreg_dev;
 	}
 
 	if (dev->has_vbi_out) {
 		/* initialize vbi_out queue */
-		q = &dev->vb_vbi_out_q;
-		q->type = dev->has_raw_vbi_out ? V4L2_BUF_TYPE_VBI_OUTPUT :
-					      V4L2_BUF_TYPE_SLICED_VBI_OUTPUT;
-		q->io_modes = VB2_MMAP | VB2_DMABUF | VB2_WRITE;
-		if (!allocator)
-			q->io_modes |= VB2_USERPTR;
-		q->drv_priv = dev;
-		q->buf_struct_size = sizeof(struct vivid_buffer);
-		q->ops = &vivid_vbi_out_qops;
-		q->mem_ops = vivid_mem_ops[allocator];
-		q->timestamp_flags = V4L2_BUF_FLAG_TIMESTAMP_MONOTONIC;
-		q->min_buffers_needed = 2;
-		q->lock = &dev->mutex;
-		q->dev = dev->v4l2_dev.dev;
-		q->supports_requests = true;
-
-		ret = vb2_queue_init(q);
+		ret = vivid_create_queue(dev, &dev->vb_vbi_out_q,
+					 V4L2_BUF_TYPE_VBI_OUTPUT, 2,
+					 &vivid_vbi_out_qops);
 		if (ret)
 			goto unreg_dev;
 	}
 
 	if (dev->has_sdr_cap) {
 		/* initialize sdr_cap queue */
-		q = &dev->vb_sdr_cap_q;
-		q->type = V4L2_BUF_TYPE_SDR_CAPTURE;
-		q->io_modes = VB2_MMAP | VB2_DMABUF | VB2_READ;
-		if (!allocator)
-			q->io_modes |= VB2_USERPTR;
-		q->drv_priv = dev;
-		q->buf_struct_size = sizeof(struct vivid_buffer);
-		q->ops = &vivid_sdr_cap_qops;
-		q->mem_ops = vivid_mem_ops[allocator];
-		q->timestamp_flags = V4L2_BUF_FLAG_TIMESTAMP_MONOTONIC;
-		q->min_buffers_needed = 8;
-		q->lock = &dev->mutex;
-		q->dev = dev->v4l2_dev.dev;
-		q->supports_requests = true;
-
-		ret = vb2_queue_init(q);
+		ret = vivid_create_queue(dev, &dev->vb_sdr_cap_q,
+					 V4L2_BUF_TYPE_SDR_CAPTURE, 8,
+					 &vivid_sdr_cap_qops);
+		if (ret)
+			goto unreg_dev;
+	}
+
+	if (dev->has_meta_cap) {
+		/* initialize meta_cap queue */
+		ret = vivid_create_queue(dev, &dev->vb_meta_cap_q,
+					 V4L2_BUF_TYPE_META_CAPTURE, 2,
+					 &vivid_meta_cap_qops);
+		if (ret)
+			goto unreg_dev;
+	}
+
+	if (dev->has_meta_out) {
+		/* initialize meta_out queue */
+		ret = vivid_create_queue(dev, &dev->vb_meta_out_q,
+					 V4L2_BUF_TYPE_META_OUTPUT, 1,
+					 &vivid_meta_out_qops);
 		if (ret)
 			goto unreg_dev;
 	}
@@ -1222,7 +1300,7 @@ static int vivid_create_instance(struct platform_device *pdev, int inst)
 		if (ret)
 			goto unreg_dev;
 		v4l2_info(&dev->v4l2_dev, "Framebuffer device registered as fb%d\n",
-				dev->fb_info.node);
+			  dev->fb_info.node);
 	}
 
 #ifdef CONFIG_VIDEO_VIVID_CEC
@@ -1265,10 +1343,14 @@ static int vivid_create_instance(struct platform_device *pdev, int inst)
 	v4l2_ctrl_handler_setup(&dev->ctrl_hdl_radio_rx);
 	v4l2_ctrl_handler_setup(&dev->ctrl_hdl_radio_tx);
 	v4l2_ctrl_handler_setup(&dev->ctrl_hdl_sdr_cap);
+	v4l2_ctrl_handler_setup(&dev->ctrl_hdl_meta_cap);
+	v4l2_ctrl_handler_setup(&dev->ctrl_hdl_meta_out);
 
 	/* finally start creating the device nodes */
 	if (dev->has_vid_cap) {
 		vfd = &dev->vid_cap_dev;
+		snprintf(vfd->name, sizeof(vfd->name),
+			 "vivid-%03d-vid-cap", inst);
 		vfd->fops = &vivid_fops;
 		vfd->ioctl_ops = &vivid_ioctl_ops;
 		vfd->device_caps = dev->vid_cap_caps;
@@ -1314,6 +1396,8 @@ static int vivid_create_instance(struct platform_device *pdev, int inst)
 
 	if (dev->has_vid_out) {
 		vfd = &dev->vid_out_dev;
+		snprintf(vfd->name, sizeof(vfd->name),
+			 "vivid-%03d-vid-out", inst);
 		vfd->vfl_dir = VFL_DIR_TX;
 		vfd->fops = &vivid_fops;
 		vfd->ioctl_ops = &vivid_ioctl_ops;
@@ -1492,6 +1576,65 @@ static int vivid_create_instance(struct platform_device *pdev, int inst)
 					  video_device_node_name(vfd));
 	}
 
+	if (dev->has_meta_cap) {
+		vfd = &dev->meta_cap_dev;
+		snprintf(vfd->name, sizeof(vfd->name),
+			 "vivid-%03d-meta-cap", inst);
+		vfd->fops = &vivid_fops;
+		vfd->ioctl_ops = &vivid_ioctl_ops;
+		vfd->device_caps = dev->meta_cap_caps;
+		vfd->release = video_device_release_empty;
+		vfd->v4l2_dev = &dev->v4l2_dev;
+		vfd->queue = &dev->vb_meta_cap_q;
+		vfd->lock = &dev->mutex;
+		vfd->tvnorms = tvnorms_cap;
+		video_set_drvdata(vfd, dev);
+#ifdef CONFIG_MEDIA_CONTROLLER
+		dev->meta_cap_pad.flags = MEDIA_PAD_FL_SINK;
+		ret = media_entity_pads_init(&vfd->entity, 1,
+					     &dev->meta_cap_pad);
+		if (ret)
+			goto unreg_dev;
+#endif
+		ret = video_register_device(vfd, VFL_TYPE_GRABBER,
+					    meta_cap_nr[inst]);
+		if (ret < 0)
+			goto unreg_dev;
+		v4l2_info(&dev->v4l2_dev,
+			  "V4L2 metadata capture device registered as %s\n",
+			  video_device_node_name(vfd));
+	}
+
+	if (dev->has_meta_out) {
+		vfd = &dev->meta_out_dev;
+		snprintf(vfd->name, sizeof(vfd->name),
+			 "vivid-%03d-meta-out", inst);
+		vfd->vfl_dir = VFL_DIR_TX;
+		vfd->fops = &vivid_fops;
+		vfd->ioctl_ops = &vivid_ioctl_ops;
+		vfd->device_caps = dev->meta_out_caps;
+		vfd->release = video_device_release_empty;
+		vfd->v4l2_dev = &dev->v4l2_dev;
+		vfd->queue = &dev->vb_meta_out_q;
+		vfd->lock = &dev->mutex;
+		vfd->tvnorms = tvnorms_out;
+		video_set_drvdata(vfd, dev);
+#ifdef CONFIG_MEDIA_CONTROLLER
+		dev->meta_out_pad.flags = MEDIA_PAD_FL_SOURCE;
+		ret = media_entity_pads_init(&vfd->entity, 1,
+					     &dev->meta_out_pad);
+		if (ret)
+			goto unreg_dev;
+#endif
+		ret = video_register_device(vfd, VFL_TYPE_GRABBER,
+					    meta_out_nr[inst]);
+		if (ret < 0)
+			goto unreg_dev;
+		v4l2_info(&dev->v4l2_dev,
+			  "V4L2 metadata output device registered as %s\n",
+			  video_device_node_name(vfd));
+	}
+
 #ifdef CONFIG_MEDIA_CONTROLLER
 	/* Register the media device */
 	ret = media_device_register(&dev->mdev);
@@ -1508,6 +1651,8 @@ static int vivid_create_instance(struct platform_device *pdev, int inst)
 	return 0;
 
 unreg_dev:
+	video_unregister_device(&dev->meta_out_dev);
+	video_unregister_device(&dev->meta_cap_dev);
 	video_unregister_device(&dev->radio_tx_dev);
 	video_unregister_device(&dev->radio_rx_dev);
 	video_unregister_device(&dev->sdr_cap_dev);
@@ -1580,7 +1725,6 @@ static int vivid_remove(struct platform_device *pdev)
 
 #ifdef CONFIG_MEDIA_CONTROLLER
 		media_device_unregister(&dev->mdev);
-		media_device_cleanup(&dev->mdev);
 #endif
 
 		if (dev->has_vid_cap) {
@@ -1624,6 +1768,16 @@ static int vivid_remove(struct platform_device *pdev)
 			unregister_framebuffer(&dev->fb_info);
 			vivid_fb_release_buffers(dev);
 		}
+		if (dev->has_meta_cap) {
+			v4l2_info(&dev->v4l2_dev, "unregistering %s\n",
+				  video_device_node_name(&dev->meta_cap_dev));
+			video_unregister_device(&dev->meta_cap_dev);
+		}
+		if (dev->has_meta_out) {
+			v4l2_info(&dev->v4l2_dev, "unregistering %s\n",
+				  video_device_node_name(&dev->meta_out_dev));
+			video_unregister_device(&dev->meta_out_dev);
+		}
 		cec_unregister_adapter(dev->cec_rx_adap);
 		for (j = 0; j < MAX_OUTPUTS; j++)
 			cec_unregister_adapter(dev->cec_tx_adap[j]);
diff --git a/drivers/media/platform/vivid/vivid-core.h b/drivers/media/platform/vivid/vivid-core.h
index 7ebb14673c75..59192b67231c 100644
--- a/drivers/media/platform/vivid/vivid-core.h
+++ b/drivers/media/platform/vivid/vivid-core.h
@@ -131,6 +131,8 @@ struct vivid_dev {
 	struct media_pad		vbi_cap_pad;
 	struct media_pad		vbi_out_pad;
 	struct media_pad		sdr_cap_pad;
+	struct media_pad		meta_cap_pad;
+	struct media_pad		meta_out_pad;
 #endif
 	struct v4l2_ctrl_handler	ctrl_hdl_user_gen;
 	struct v4l2_ctrl_handler	ctrl_hdl_user_vid;
@@ -153,6 +155,11 @@ struct vivid_dev {
 	struct v4l2_ctrl_handler	ctrl_hdl_radio_tx;
 	struct video_device		sdr_cap_dev;
 	struct v4l2_ctrl_handler	ctrl_hdl_sdr_cap;
+	struct video_device		meta_cap_dev;
+	struct v4l2_ctrl_handler	ctrl_hdl_meta_cap;
+	struct video_device		meta_out_dev;
+	struct v4l2_ctrl_handler	ctrl_hdl_meta_out;
+
 	spinlock_t			slock;
 	struct mutex			mutex;
 
@@ -164,6 +171,8 @@ struct vivid_dev {
 	u32				sdr_cap_caps;
 	u32				radio_rx_caps;
 	u32				radio_tx_caps;
+	u32				meta_cap_caps;
+	u32				meta_out_caps;
 
 	/* supported features */
 	bool				multiplanar;
@@ -189,6 +198,9 @@ struct vivid_dev {
 	bool				has_radio_tx;
 	bool				has_sdr_cap;
 	bool				has_fb;
+	bool				has_meta_cap;
+	bool				has_meta_out;
+	bool				has_tv_tuner;
 
 	bool				can_loop_video;
 
@@ -390,6 +402,8 @@ struct vivid_dev {
 	struct list_head		vid_cap_active;
 	struct vb2_queue		vb_vbi_cap_q;
 	struct list_head		vbi_cap_active;
+	struct vb2_queue		vb_meta_cap_q;
+	struct list_head		meta_cap_active;
 
 	/* thread for generating video capture stream */
 	struct task_struct		*kthread_vid_cap;
@@ -407,6 +421,9 @@ struct vivid_dev {
 	u32				vbi_cap_seq_count;
 	bool				vbi_cap_streaming;
 	bool				stream_sliced_vbi_cap;
+	u32				meta_cap_seq_start;
+	u32				meta_cap_seq_count;
+	bool				meta_cap_streaming;
 
 	/* video output */
 	const struct vivid_fmt		*fmt_out;
@@ -421,6 +438,8 @@ struct vivid_dev {
 	struct list_head		vid_out_active;
 	struct vb2_queue		vb_vbi_out_q;
 	struct list_head		vbi_out_active;
+	struct vb2_queue		vb_meta_out_q;
+	struct list_head		meta_out_active;
 
 	/* video loop precalculated rectangles */
 
@@ -461,6 +480,9 @@ struct vivid_dev {
 	u32				vbi_out_seq_count;
 	bool				vbi_out_streaming;
 	bool				stream_sliced_vbi_out;
+	u32				meta_out_seq_start;
+	u32				meta_out_seq_count;
+	bool				meta_out_streaming;
 
 	/* SDR capture */
 	struct vb2_queue		vb_sdr_cap_q;
@@ -527,6 +549,9 @@ struct vivid_dev {
 	/* CEC OSD String */
 	char				osd[14];
 	unsigned long			osd_jiffies;
+
+	bool				meta_pts;
+	bool				meta_scr;
 };
 
 static inline bool vivid_is_webcam(const struct vivid_dev *dev)
diff --git a/drivers/media/platform/vivid/vivid-ctrls.c b/drivers/media/platform/vivid/vivid-ctrls.c
index cb19a9a73092..68e8124c7973 100644
--- a/drivers/media/platform/vivid/vivid-ctrls.c
+++ b/drivers/media/platform/vivid/vivid-ctrls.c
@@ -32,6 +32,7 @@
 #define VIVID_CID_U32_ARRAY		(VIVID_CID_CUSTOM_BASE + 8)
 #define VIVID_CID_U16_MATRIX		(VIVID_CID_CUSTOM_BASE + 9)
 #define VIVID_CID_U8_4D_ARRAY		(VIVID_CID_CUSTOM_BASE + 10)
+#define VIVID_CID_AREA			(VIVID_CID_CUSTOM_BASE + 11)
 
 #define VIVID_CID_VIVID_BASE		(0x00f00000 | 0xf000)
 #define VIVID_CID_VIVID_CLASS		(0x00f00000 | 1)
@@ -94,6 +95,9 @@
 
 #define VIVID_CID_SDR_CAP_FM_DEVIATION	(VIVID_CID_VIVID_BASE + 110)
 
+#define VIVID_CID_META_CAP_GENERATE_PTS	(VIVID_CID_VIVID_BASE + 111)
+#define VIVID_CID_META_CAP_GENERATE_SCR	(VIVID_CID_VIVID_BASE + 112)
+
 /* General User Controls */
 
 static int vivid_user_gen_s_ctrl(struct v4l2_ctrl *ctrl)
@@ -110,6 +114,7 @@ static int vivid_user_gen_s_ctrl(struct v4l2_ctrl *ctrl)
 		clear_bit(V4L2_FL_REGISTERED, &dev->sdr_cap_dev.flags);
 		clear_bit(V4L2_FL_REGISTERED, &dev->radio_rx_dev.flags);
 		clear_bit(V4L2_FL_REGISTERED, &dev->radio_tx_dev.flags);
+		clear_bit(V4L2_FL_REGISTERED, &dev->meta_cap_dev.flags);
 		break;
 	case VIVID_CID_BUTTON:
 		dev->button_pressed = 30;
@@ -262,6 +267,18 @@ static const struct v4l2_ctrl_config vivid_ctrl_disconnect = {
 	.type = V4L2_CTRL_TYPE_BUTTON,
 };
 
+static const struct v4l2_area area = {
+	.width = 1000,
+	.height = 2000,
+};
+
+static const struct v4l2_ctrl_config vivid_ctrl_area = {
+	.ops = &vivid_user_gen_ctrl_ops,
+	.id = VIVID_CID_AREA,
+	.name = "Area",
+	.type = V4L2_CTRL_TYPE_AREA,
+	.p_def.p_const = &area,
+};
 
 /* Framebuffer Controls */
 
@@ -1421,6 +1438,47 @@ static const struct v4l2_ctrl_config vivid_ctrl_sdr_cap_fm_deviation = {
 	.step =     1,
 };
 
+/* Metadata Capture Control */
+
+static int vivid_meta_cap_s_ctrl(struct v4l2_ctrl *ctrl)
+{
+	struct vivid_dev *dev = container_of(ctrl->handler, struct vivid_dev,
+					     ctrl_hdl_meta_cap);
+
+	switch (ctrl->id) {
+	case VIVID_CID_META_CAP_GENERATE_PTS:
+		dev->meta_pts = ctrl->val;
+		break;
+	case VIVID_CID_META_CAP_GENERATE_SCR:
+		dev->meta_scr = ctrl->val;
+		break;
+	}
+	return 0;
+}
+
+static const struct v4l2_ctrl_ops vivid_meta_cap_ctrl_ops = {
+	.s_ctrl = vivid_meta_cap_s_ctrl,
+};
+
+static const struct v4l2_ctrl_config vivid_ctrl_meta_has_pts = {
+	.ops = &vivid_meta_cap_ctrl_ops,
+	.id = VIVID_CID_META_CAP_GENERATE_PTS,
+	.name = "Generate PTS",
+	.type = V4L2_CTRL_TYPE_BOOLEAN,
+	.max = 1,
+	.def = 1,
+	.step = 1,
+};
+
+static const struct v4l2_ctrl_config vivid_ctrl_meta_has_src_clk = {
+	.ops = &vivid_meta_cap_ctrl_ops,
+	.id = VIVID_CID_META_CAP_GENERATE_SCR,
+	.name = "Generate SCR",
+	.type = V4L2_CTRL_TYPE_BOOLEAN,
+	.max = 1,
+	.def = 1,
+	.step = 1,
+};
 
 static const struct v4l2_ctrl_config vivid_ctrl_class = {
 	.ops = &vivid_user_gen_ctrl_ops,
@@ -1448,6 +1506,9 @@ int vivid_create_controls(struct vivid_dev *dev, bool show_ccs_cap,
 	struct v4l2_ctrl_handler *hdl_radio_rx = &dev->ctrl_hdl_radio_rx;
 	struct v4l2_ctrl_handler *hdl_radio_tx = &dev->ctrl_hdl_radio_tx;
 	struct v4l2_ctrl_handler *hdl_sdr_cap = &dev->ctrl_hdl_sdr_cap;
+	struct v4l2_ctrl_handler *hdl_meta_cap = &dev->ctrl_hdl_meta_cap;
+	struct v4l2_ctrl_handler *hdl_meta_out = &dev->ctrl_hdl_meta_out;
+
 	struct v4l2_ctrl_config vivid_ctrl_dv_timings = {
 		.ops = &vivid_vid_cap_ctrl_ops,
 		.id = VIVID_CID_DV_TIMINGS,
@@ -1486,6 +1547,10 @@ int vivid_create_controls(struct vivid_dev *dev, bool show_ccs_cap,
 	v4l2_ctrl_new_custom(hdl_radio_tx, &vivid_ctrl_class, NULL);
 	v4l2_ctrl_handler_init(hdl_sdr_cap, 19);
 	v4l2_ctrl_new_custom(hdl_sdr_cap, &vivid_ctrl_class, NULL);
+	v4l2_ctrl_handler_init(hdl_meta_cap, 2);
+	v4l2_ctrl_new_custom(hdl_meta_cap, &vivid_ctrl_class, NULL);
+	v4l2_ctrl_handler_init(hdl_meta_out, 2);
+	v4l2_ctrl_new_custom(hdl_meta_out, &vivid_ctrl_class, NULL);
 
 	/* User Controls */
 	dev->volume = v4l2_ctrl_new_std(hdl_user_aud, NULL,
@@ -1522,6 +1587,7 @@ int vivid_create_controls(struct vivid_dev *dev, bool show_ccs_cap,
 	dev->string = v4l2_ctrl_new_custom(hdl_user_gen, &vivid_ctrl_string, NULL);
 	dev->bitmask = v4l2_ctrl_new_custom(hdl_user_gen, &vivid_ctrl_bitmask, NULL);
 	dev->int_menu = v4l2_ctrl_new_custom(hdl_user_gen, &vivid_ctrl_int_menu, NULL);
+	v4l2_ctrl_new_custom(hdl_user_gen, &vivid_ctrl_area, NULL);
 	v4l2_ctrl_new_custom(hdl_user_gen, &vivid_ctrl_u32_array, NULL);
 	v4l2_ctrl_new_custom(hdl_user_gen, &vivid_ctrl_u16_matrix, NULL);
 	v4l2_ctrl_new_custom(hdl_user_gen, &vivid_ctrl_u8_4d_array, NULL);
@@ -1743,6 +1809,13 @@ int vivid_create_controls(struct vivid_dev *dev, bool show_ccs_cap,
 		v4l2_ctrl_new_custom(hdl_sdr_cap,
 			&vivid_ctrl_sdr_cap_fm_deviation, NULL);
 	}
+	if (dev->has_meta_cap) {
+		v4l2_ctrl_new_custom(hdl_meta_cap,
+				     &vivid_ctrl_meta_has_pts, NULL);
+		v4l2_ctrl_new_custom(hdl_meta_cap,
+				     &vivid_ctrl_meta_has_src_clk, NULL);
+	}
+
 	if (hdl_user_gen->error)
 		return hdl_user_gen->error;
 	if (hdl_user_vid->error)
@@ -1817,6 +1890,20 @@ int vivid_create_controls(struct vivid_dev *dev, bool show_ccs_cap,
 			return hdl_sdr_cap->error;
 		dev->sdr_cap_dev.ctrl_handler = hdl_sdr_cap;
 	}
+	if (dev->has_meta_cap) {
+		v4l2_ctrl_add_handler(hdl_meta_cap, hdl_user_gen, NULL, false);
+		v4l2_ctrl_add_handler(hdl_meta_cap, hdl_streaming, NULL, false);
+		if (hdl_meta_cap->error)
+			return hdl_meta_cap->error;
+		dev->meta_cap_dev.ctrl_handler = hdl_meta_cap;
+	}
+	if (dev->has_meta_out) {
+		v4l2_ctrl_add_handler(hdl_meta_out, hdl_user_gen, NULL, false);
+		v4l2_ctrl_add_handler(hdl_meta_out, hdl_streaming, NULL, false);
+		if (hdl_meta_out->error)
+			return hdl_meta_out->error;
+		dev->meta_out_dev.ctrl_handler = hdl_meta_out;
+	}
 	return 0;
 }
 
@@ -1836,4 +1923,6 @@ void vivid_free_controls(struct vivid_dev *dev)
 	v4l2_ctrl_handler_free(&dev->ctrl_hdl_sdtv_cap);
 	v4l2_ctrl_handler_free(&dev->ctrl_hdl_loop_cap);
 	v4l2_ctrl_handler_free(&dev->ctrl_hdl_fb);
+	v4l2_ctrl_handler_free(&dev->ctrl_hdl_meta_cap);
+	v4l2_ctrl_handler_free(&dev->ctrl_hdl_meta_out);
 }
diff --git a/drivers/media/platform/vivid/vivid-kthread-cap.c b/drivers/media/platform/vivid/vivid-kthread-cap.c
index 003319d7816d..01a9d671b947 100644
--- a/drivers/media/platform/vivid/vivid-kthread-cap.c
+++ b/drivers/media/platform/vivid/vivid-kthread-cap.c
@@ -39,6 +39,7 @@
 #include "vivid-osd.h"
 #include "vivid-ctrls.h"
 #include "vivid-kthread-cap.h"
+#include "vivid-meta-cap.h"
 
 static inline v4l2_std_id vivid_get_std_cap(const struct vivid_dev *dev)
 {
@@ -677,6 +678,7 @@ static noinline_for_stack void vivid_thread_vid_cap_tick(struct vivid_dev *dev,
 {
 	struct vivid_buffer *vid_cap_buf = NULL;
 	struct vivid_buffer *vbi_cap_buf = NULL;
+	struct vivid_buffer *meta_cap_buf = NULL;
 	u64 f_time = 0;
 
 	dprintk(dev, 1, "Video Capture Thread Tick\n");
@@ -704,15 +706,19 @@ static noinline_for_stack void vivid_thread_vid_cap_tick(struct vivid_dev *dev,
 			list_del(&vbi_cap_buf->list);
 		}
 	}
+	if (!list_empty(&dev->meta_cap_active)) {
+		meta_cap_buf = list_entry(dev->meta_cap_active.next,
+					  struct vivid_buffer, list);
+		list_del(&meta_cap_buf->list);
+	}
+
 	spin_unlock(&dev->slock);
 
-	if (!vid_cap_buf && !vbi_cap_buf)
+	if (!vid_cap_buf && !vbi_cap_buf && !meta_cap_buf)
 		goto update_mv;
 
 	f_time = dev->cap_frame_period * dev->vid_cap_seq_count +
 		 dev->cap_stream_start + dev->time_wrap_offset;
-	if (!dev->tstamp_src_is_soe)
-		f_time += dev->cap_frame_eof_offset;
 
 	if (vid_cap_buf) {
 		v4l2_ctrl_request_setup(vid_cap_buf->vb.vb2_buf.req_obj.req,
@@ -735,6 +741,8 @@ static noinline_for_stack void vivid_thread_vid_cap_tick(struct vivid_dev *dev,
 				vid_cap_buf->vb.vb2_buf.index);
 
 		vid_cap_buf->vb.vb2_buf.timestamp = f_time;
+		if (!dev->tstamp_src_is_soe)
+			vid_cap_buf->vb.vb2_buf.timestamp += dev->cap_frame_eof_offset;
 	}
 
 	if (vbi_cap_buf) {
@@ -756,8 +764,22 @@ static noinline_for_stack void vivid_thread_vid_cap_tick(struct vivid_dev *dev,
 		/* If capturing a VBI, offset by 0.05 */
 		vbi_period = dev->cap_frame_period * 5;
 		do_div(vbi_period, 100);
-		vbi_cap_buf->vb.vb2_buf.timestamp = f_time + vbi_period;
+		vbi_cap_buf->vb.vb2_buf.timestamp = f_time + dev->cap_frame_eof_offset + vbi_period;
+	}
+
+	if (meta_cap_buf) {
+		v4l2_ctrl_request_setup(meta_cap_buf->vb.vb2_buf.req_obj.req,
+					&dev->ctrl_hdl_meta_cap);
+		vivid_meta_cap_fillbuff(dev, meta_cap_buf, f_time);
+		v4l2_ctrl_request_complete(meta_cap_buf->vb.vb2_buf.req_obj.req,
+					   &dev->ctrl_hdl_meta_cap);
+		vb2_buffer_done(&meta_cap_buf->vb.vb2_buf, dev->dqbuf_error ?
+				VB2_BUF_STATE_ERROR : VB2_BUF_STATE_DONE);
+		dprintk(dev, 2, "meta_cap %d done\n",
+			meta_cap_buf->vb.vb2_buf.index);
+		meta_cap_buf->vb.vb2_buf.timestamp = f_time + dev->cap_frame_eof_offset;
 	}
+
 	dev->dqbuf_error = false;
 
 update_mv:
@@ -796,7 +818,11 @@ static int vivid_thread_vid_cap(void *data)
 		if (kthread_should_stop())
 			break;
 
-		mutex_lock(&dev->mutex);
+		if (!mutex_trylock(&dev->mutex)) {
+			schedule_timeout_uninterruptible(1);
+			continue;
+		}
+
 		cur_jiffies = jiffies;
 		if (dev->cap_seq_resync) {
 			dev->jiffies_vid_cap = cur_jiffies;
@@ -835,6 +861,7 @@ static int vivid_thread_vid_cap(void *data)
 		dev->cap_seq_count = buffers_since_start + dev->cap_seq_offset;
 		dev->vid_cap_seq_count = dev->cap_seq_count - dev->vid_cap_seq_start;
 		dev->vbi_cap_seq_count = dev->cap_seq_count - dev->vbi_cap_seq_start;
+		dev->meta_cap_seq_count = dev->cap_seq_count - dev->meta_cap_seq_start;
 
 		vivid_thread_vid_cap_tick(dev, dropped_bufs);
 
@@ -883,8 +910,10 @@ int vivid_start_generating_vid_cap(struct vivid_dev *dev, bool *pstreaming)
 
 		if (pstreaming == &dev->vid_cap_streaming)
 			dev->vid_cap_seq_start = seq_count;
-		else
+		else if (pstreaming == &dev->vbi_cap_streaming)
 			dev->vbi_cap_seq_start = seq_count;
+		else
+			dev->meta_cap_seq_start = seq_count;
 		*pstreaming = true;
 		return 0;
 	}
@@ -894,6 +923,7 @@ int vivid_start_generating_vid_cap(struct vivid_dev *dev, bool *pstreaming)
 
 	dev->vid_cap_seq_start = dev->seq_wrap * 128;
 	dev->vbi_cap_seq_start = dev->seq_wrap * 128;
+	dev->meta_cap_seq_start = dev->seq_wrap * 128;
 
 	dev->kthread_vid_cap = kthread_run(vivid_thread_vid_cap, dev,
 			"%s-vid-cap", dev->v4l2_dev.name);
@@ -951,13 +981,27 @@ void vivid_stop_generating_vid_cap(struct vivid_dev *dev, bool *pstreaming)
 		}
 	}
 
-	if (dev->vid_cap_streaming || dev->vbi_cap_streaming)
+	if (pstreaming == &dev->meta_cap_streaming) {
+		while (!list_empty(&dev->meta_cap_active)) {
+			struct vivid_buffer *buf;
+
+			buf = list_entry(dev->meta_cap_active.next,
+					 struct vivid_buffer, list);
+			list_del(&buf->list);
+			v4l2_ctrl_request_complete(buf->vb.vb2_buf.req_obj.req,
+						   &dev->ctrl_hdl_meta_cap);
+			vb2_buffer_done(&buf->vb.vb2_buf, VB2_BUF_STATE_ERROR);
+			dprintk(dev, 2, "meta_cap buffer %d done\n",
+				buf->vb.vb2_buf.index);
+		}
+	}
+
+	if (dev->vid_cap_streaming || dev->vbi_cap_streaming ||
+	    dev->meta_cap_streaming)
 		return;
 
 	/* shutdown control thread */
 	vivid_grab_controls(dev, false);
-	mutex_unlock(&dev->mutex);
 	kthread_stop(dev->kthread_vid_cap);
 	dev->kthread_vid_cap = NULL;
-	mutex_lock(&dev->mutex);
 }
diff --git a/drivers/media/platform/vivid/vivid-kthread-out.c b/drivers/media/platform/vivid/vivid-kthread-out.c
index ce5bcda2348c..6780687978f9 100644
--- a/drivers/media/platform/vivid/vivid-kthread-out.c
+++ b/drivers/media/platform/vivid/vivid-kthread-out.c
@@ -38,11 +38,13 @@
 #include "vivid-osd.h"
 #include "vivid-ctrls.h"
 #include "vivid-kthread-out.h"
+#include "vivid-meta-out.h"
 
 static void vivid_thread_vid_out_tick(struct vivid_dev *dev)
 {
 	struct vivid_buffer *vid_out_buf = NULL;
 	struct vivid_buffer *vbi_out_buf = NULL;
+	struct vivid_buffer *meta_out_buf = NULL;
 
 	dprintk(dev, 1, "Video Output Thread Tick\n");
 
@@ -69,9 +71,14 @@ static void vivid_thread_vid_out_tick(struct vivid_dev *dev)
 					 struct vivid_buffer, list);
 		list_del(&vbi_out_buf->list);
 	}
+	if (!list_empty(&dev->meta_out_active)) {
+		meta_out_buf = list_entry(dev->meta_out_active.next,
+					  struct vivid_buffer, list);
+		list_del(&meta_out_buf->list);
+	}
 	spin_unlock(&dev->slock);
 
-	if (!vid_out_buf && !vbi_out_buf)
+	if (!vid_out_buf && !vbi_out_buf && !meta_out_buf)
 		return;
 
 	if (vid_out_buf) {
@@ -111,6 +118,21 @@ static void vivid_thread_vid_out_tick(struct vivid_dev *dev)
 		dprintk(dev, 2, "vbi_out buffer %d done\n",
 			vbi_out_buf->vb.vb2_buf.index);
 	}
+	if (meta_out_buf) {
+		v4l2_ctrl_request_setup(meta_out_buf->vb.vb2_buf.req_obj.req,
+					&dev->ctrl_hdl_meta_out);
+		v4l2_ctrl_request_complete(meta_out_buf->vb.vb2_buf.req_obj.req,
+					   &dev->ctrl_hdl_meta_out);
+		vivid_meta_out_process(dev, meta_out_buf);
+		meta_out_buf->vb.sequence = dev->meta_out_seq_count;
+		meta_out_buf->vb.vb2_buf.timestamp =
+			ktime_get_ns() + dev->time_wrap_offset;
+		vb2_buffer_done(&meta_out_buf->vb.vb2_buf, dev->dqbuf_error ?
+				VB2_BUF_STATE_ERROR : VB2_BUF_STATE_DONE);
+		dprintk(dev, 2, "meta_out buffer %d done\n",
+			meta_out_buf->vb.vb2_buf.index);
+	}
+
 	dev->dqbuf_error = false;
 }
 
@@ -136,6 +158,7 @@ static int vivid_thread_vid_out(void *data)
 		dev->out_seq_count = 0xffffff80U;
 	dev->jiffies_vid_out = jiffies;
 	dev->vid_out_seq_start = dev->vbi_out_seq_start = 0;
+	dev->meta_out_seq_start = 0;
 	dev->out_seq_resync = false;
 
 	for (;;) {
@@ -143,7 +166,11 @@ static int vivid_thread_vid_out(void *data)
 		if (kthread_should_stop())
 			break;
 
-		mutex_lock(&dev->mutex);
+		if (!mutex_trylock(&dev->mutex)) {
+			schedule_timeout_uninterruptible(1);
+			continue;
+		}
+
 		cur_jiffies = jiffies;
 		if (dev->out_seq_resync) {
 			dev->jiffies_vid_out = cur_jiffies;
@@ -178,6 +205,7 @@ static int vivid_thread_vid_out(void *data)
 		dev->out_seq_count = buffers_since_start + dev->out_seq_offset;
 		dev->vid_out_seq_count = dev->out_seq_count - dev->vid_out_seq_start;
 		dev->vbi_out_seq_count = dev->out_seq_count - dev->vbi_out_seq_start;
+		dev->meta_out_seq_count = dev->out_seq_count - dev->meta_out_seq_start;
 
 		vivid_thread_vid_out_tick(dev);
 		mutex_unlock(&dev->mutex);
@@ -229,8 +257,10 @@ int vivid_start_generating_vid_out(struct vivid_dev *dev, bool *pstreaming)
 
 		if (pstreaming == &dev->vid_out_streaming)
 			dev->vid_out_seq_start = seq_count;
-		else
+		else if (pstreaming == &dev->vbi_out_streaming)
 			dev->vbi_out_seq_start = seq_count;
+		else
+			dev->meta_out_seq_start = seq_count;
 		*pstreaming = true;
 		return 0;
 	}
@@ -239,6 +269,7 @@ int vivid_start_generating_vid_out(struct vivid_dev *dev, bool *pstreaming)
 	dev->jiffies_vid_out = jiffies;
 	dev->vid_out_seq_start = dev->seq_wrap * 128;
 	dev->vbi_out_seq_start = dev->seq_wrap * 128;
+	dev->meta_out_seq_start = dev->seq_wrap * 128;
 
 	dev->kthread_vid_out = kthread_run(vivid_thread_vid_out, dev,
 			"%s-vid-out", dev->v4l2_dev.name);
@@ -296,13 +327,27 @@ void vivid_stop_generating_vid_out(struct vivid_dev *dev, bool *pstreaming)
 		}
 	}
 
-	if (dev->vid_out_streaming || dev->vbi_out_streaming)
+	if (pstreaming == &dev->meta_out_streaming) {
+		while (!list_empty(&dev->meta_out_active)) {
+			struct vivid_buffer *buf;
+
+			buf = list_entry(dev->meta_out_active.next,
+					 struct vivid_buffer, list);
+			list_del(&buf->list);
+			v4l2_ctrl_request_complete(buf->vb.vb2_buf.req_obj.req,
+						   &dev->ctrl_hdl_meta_out);
+			vb2_buffer_done(&buf->vb.vb2_buf, VB2_BUF_STATE_ERROR);
+			dprintk(dev, 2, "meta_out buffer %d done\n",
+				buf->vb.vb2_buf.index);
+		}
+	}
+
+	if (dev->vid_out_streaming || dev->vbi_out_streaming ||
+	    dev->meta_out_streaming)
 		return;
 
 	/* shutdown control thread */
 	vivid_grab_controls(dev, false);
-	mutex_unlock(&dev->mutex);
 	kthread_stop(dev->kthread_vid_out);
 	dev->kthread_vid_out = NULL;
-	mutex_lock(&dev->mutex);
 }
diff --git a/drivers/media/platform/vivid/vivid-meta-cap.c b/drivers/media/platform/vivid/vivid-meta-cap.c
new file mode 100644
index 000000000000..780f96860a6d
--- /dev/null
+++ b/drivers/media/platform/vivid/vivid-meta-cap.c
@@ -0,0 +1,201 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * vivid-meta-cap.c - meta capture support functions.
+ */
+
+#include <linux/errno.h>
+#include <linux/kernel.h>
+#include <linux/videodev2.h>
+#include <media/v4l2-common.h>
+#include <linux/usb/video.h>
+
+#include "vivid-core.h"
+#include "vivid-kthread-cap.h"
+#include "vivid-meta-cap.h"
+
+static int meta_cap_queue_setup(struct vb2_queue *vq, unsigned int *nbuffers,
+				unsigned int *nplanes, unsigned int sizes[],
+				struct device *alloc_devs[])
+{
+	struct vivid_dev *dev = vb2_get_drv_priv(vq);
+	unsigned int size =  sizeof(struct vivid_uvc_meta_buf);
+
+	if (!vivid_is_webcam(dev))
+		return -EINVAL;
+
+	if (*nplanes) {
+		if (sizes[0] < size)
+			return -EINVAL;
+	} else {
+		sizes[0] = size;
+	}
+
+	if (vq->num_buffers + *nbuffers < 2)
+		*nbuffers = 2 - vq->num_buffers;
+
+	*nplanes = 1;
+	return 0;
+}
+
+static int meta_cap_buf_prepare(struct vb2_buffer *vb)
+{
+	struct vivid_dev *dev = vb2_get_drv_priv(vb->vb2_queue);
+	unsigned int size = sizeof(struct vivid_uvc_meta_buf);
+
+	dprintk(dev, 1, "%s\n", __func__);
+
+	if (dev->buf_prepare_error) {
+		/*
+		 * Error injection: test what happens if buf_prepare() returns
+		 * an error.
+		 */
+		dev->buf_prepare_error = false;
+		return -EINVAL;
+	}
+	if (vb2_plane_size(vb, 0) < size) {
+		dprintk(dev, 1, "%s data will not fit into plane (%lu < %u)\n",
+			__func__, vb2_plane_size(vb, 0), size);
+		return -EINVAL;
+	}
+	vb2_set_plane_payload(vb, 0, size);
+
+	return 0;
+}
+
+static void meta_cap_buf_queue(struct vb2_buffer *vb)
+{
+	struct vb2_v4l2_buffer *vbuf = to_vb2_v4l2_buffer(vb);
+	struct vivid_dev *dev = vb2_get_drv_priv(vb->vb2_queue);
+	struct vivid_buffer *buf = container_of(vbuf, struct vivid_buffer, vb);
+
+	dprintk(dev, 1, "%s\n", __func__);
+
+	spin_lock(&dev->slock);
+	list_add_tail(&buf->list, &dev->meta_cap_active);
+	spin_unlock(&dev->slock);
+}
+
+static int meta_cap_start_streaming(struct vb2_queue *vq, unsigned int count)
+{
+	struct vivid_dev *dev = vb2_get_drv_priv(vq);
+	int err;
+
+	dprintk(dev, 1, "%s\n", __func__);
+	dev->meta_cap_seq_count = 0;
+	if (dev->start_streaming_error) {
+		dev->start_streaming_error = false;
+		err = -EINVAL;
+	} else {
+		err = vivid_start_generating_vid_cap(dev,
+						     &dev->meta_cap_streaming);
+	}
+	if (err) {
+		struct vivid_buffer *buf, *tmp;
+
+		list_for_each_entry_safe(buf, tmp,
+					 &dev->meta_cap_active, list) {
+			list_del(&buf->list);
+			vb2_buffer_done(&buf->vb.vb2_buf,
+					VB2_BUF_STATE_QUEUED);
+		}
+	}
+	return err;
+}
+
+/* abort streaming and wait for last buffer */
+static void meta_cap_stop_streaming(struct vb2_queue *vq)
+{
+	struct vivid_dev *dev = vb2_get_drv_priv(vq);
+
+	dprintk(dev, 1, "%s\n", __func__);
+	vivid_stop_generating_vid_cap(dev, &dev->meta_cap_streaming);
+}
+
+static void meta_cap_buf_request_complete(struct vb2_buffer *vb)
+{
+	struct vivid_dev *dev = vb2_get_drv_priv(vb->vb2_queue);
+
+	v4l2_ctrl_request_complete(vb->req_obj.req, &dev->ctrl_hdl_meta_cap);
+}
+
+const struct vb2_ops vivid_meta_cap_qops = {
+	.queue_setup		= meta_cap_queue_setup,
+	.buf_prepare		= meta_cap_buf_prepare,
+	.buf_queue		= meta_cap_buf_queue,
+	.start_streaming	= meta_cap_start_streaming,
+	.stop_streaming		= meta_cap_stop_streaming,
+	.buf_request_complete	= meta_cap_buf_request_complete,
+	.wait_prepare		= vb2_ops_wait_prepare,
+	.wait_finish		= vb2_ops_wait_finish,
+};
+
+int vidioc_enum_fmt_meta_cap(struct file *file, void  *priv,
+			     struct v4l2_fmtdesc *f)
+{
+	struct vivid_dev *dev = video_drvdata(file);
+
+	if (!vivid_is_webcam(dev))
+		return -EINVAL;
+
+	if (f->index > 0)
+		return -EINVAL;
+
+	f->type = V4L2_BUF_TYPE_META_CAPTURE;
+	f->pixelformat = V4L2_META_FMT_UVC;
+	return 0;
+}
+
+int vidioc_g_fmt_meta_cap(struct file *file, void *priv,
+			  struct v4l2_format *f)
+{
+	struct vivid_dev *dev = video_drvdata(file);
+	struct v4l2_meta_format *meta = &f->fmt.meta;
+
+	if (!vivid_is_webcam(dev) || !dev->has_meta_cap)
+		return -EINVAL;
+
+	meta->dataformat = V4L2_META_FMT_UVC;
+	meta->buffersize = sizeof(struct vivid_uvc_meta_buf);
+	return 0;
+}
+
+void vivid_meta_cap_fillbuff(struct vivid_dev *dev,
+			     struct vivid_buffer *buf, u64 soe)
+{
+	struct vivid_uvc_meta_buf *meta = vb2_plane_vaddr(&buf->vb.vb2_buf, 0);
+	int buf_off = 0;
+
+	buf->vb.sequence = dev->meta_cap_seq_count;
+	if (dev->field_cap == V4L2_FIELD_ALTERNATE)
+		buf->vb.sequence /= 2;
+	memset(meta, 1, vb2_plane_size(&buf->vb.vb2_buf, 0));
+
+	meta->ns = ktime_get_ns();
+	meta->sof = buf->vb.sequence * 30;
+	meta->length = sizeof(*meta) - offsetof(struct vivid_uvc_meta_buf, length);
+	meta->flags = UVC_STREAM_EOH | UVC_STREAM_EOF;
+
+	if ((buf->vb.sequence % 2) == 0)
+		meta->flags |= UVC_STREAM_FID;
+
+	dprintk(dev, 2, "%s ns:%llu sof:%4d len:%u flags: 0x%02x",
+		__func__, meta->ns, meta->sof, meta->length, meta->flags);
+	if (dev->meta_pts) {
+		meta->flags |= UVC_STREAM_PTS;
+		meta->buf[0] = div_u64(soe, VIVID_META_CLOCK_UNIT);
+		buf_off = 4;
+		dprintk(dev, 2, " pts: %u\n", *(__u32 *)(meta->buf));
+	}
+
+	if (dev->meta_scr) {
+		meta->flags |= UVC_STREAM_SCR;
+		meta->buf[buf_off] = div_u64((soe + dev->cap_frame_eof_offset),
+					     VIVID_META_CLOCK_UNIT);
+
+		meta->buf[buf_off + 4] = (buf->vb.sequence * 30) % 1000;
+		dprintk(dev, 2, " stc: %u, sof counter: %u\n",
+			*(__u32 *)(meta->buf + buf_off),
+			*(__u16 *)(meta->buf + buf_off + 4));
+	}
+	dprintk(dev, 2, "\n");
+}
diff --git a/drivers/media/platform/vivid/vivid-meta-cap.h b/drivers/media/platform/vivid/vivid-meta-cap.h
new file mode 100644
index 000000000000..4670d00d1576
--- /dev/null
+++ b/drivers/media/platform/vivid/vivid-meta-cap.h
@@ -0,0 +1,29 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * vivid-meta-cap.h - meta capture support functions.
+ */
+#ifndef _VIVID_META_CAP_H_
+#define _VIVID_META_CAP_H_
+
+#define VIVID_META_CLOCK_UNIT	10 /* 100 MHz */
+
+struct vivid_uvc_meta_buf {
+	__u64 ns;
+	__u16 sof;
+	__u8 length;
+	__u8 flags;
+	__u8 buf[10]; /* PTS(4)+STC(4)+SOF(2) */
+} __packed;
+
+void vivid_meta_cap_fillbuff(struct vivid_dev *dev,
+			     struct vivid_buffer *buf, u64 soe);
+
+int vidioc_enum_fmt_meta_cap(struct file *file, void  *priv,
+			     struct v4l2_fmtdesc *f);
+
+int vidioc_g_fmt_meta_cap(struct file *file, void *priv,
+			  struct v4l2_format *f);
+
+extern const struct vb2_ops vivid_meta_cap_qops;
+
+#endif
diff --git a/drivers/media/platform/vivid/vivid-meta-out.c b/drivers/media/platform/vivid/vivid-meta-out.c
new file mode 100644
index 000000000000..ff8a039aba72
--- /dev/null
+++ b/drivers/media/platform/vivid/vivid-meta-out.c
@@ -0,0 +1,174 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * vivid-meta-out.c - meta output support functions.
+ */
+
+#include <linux/errno.h>
+#include <linux/kernel.h>
+#include <linux/videodev2.h>
+#include <media/v4l2-common.h>
+#include <linux/usb/video.h>
+
+#include "vivid-core.h"
+#include "vivid-kthread-out.h"
+#include "vivid-meta-out.h"
+
+static int meta_out_queue_setup(struct vb2_queue *vq, unsigned int *nbuffers,
+				unsigned int *nplanes, unsigned int sizes[],
+				struct device *alloc_devs[])
+{
+	struct vivid_dev *dev = vb2_get_drv_priv(vq);
+	unsigned int size =  sizeof(struct vivid_meta_out_buf);
+
+	if (!vivid_is_webcam(dev))
+		return -EINVAL;
+
+	if (*nplanes) {
+		if (sizes[0] < size)
+			return -EINVAL;
+	} else {
+		sizes[0] = size;
+	}
+
+	if (vq->num_buffers + *nbuffers < 2)
+		*nbuffers = 2 - vq->num_buffers;
+
+	*nplanes = 1;
+	return 0;
+}
+
+static int meta_out_buf_prepare(struct vb2_buffer *vb)
+{
+	struct vivid_dev *dev = vb2_get_drv_priv(vb->vb2_queue);
+	unsigned int size = sizeof(struct vivid_meta_out_buf);
+
+	dprintk(dev, 1, "%s\n", __func__);
+
+	if (dev->buf_prepare_error) {
+		/*
+		 * Error injection: test what happens if buf_prepare() returns
+		 * an error.
+		 */
+		dev->buf_prepare_error = false;
+		return -EINVAL;
+	}
+	if (vb2_plane_size(vb, 0) < size) {
+		dprintk(dev, 1, "%s data will not fit into plane (%lu < %u)\n",
+			__func__, vb2_plane_size(vb, 0), size);
+		return -EINVAL;
+	}
+	vb2_set_plane_payload(vb, 0, size);
+
+	return 0;
+}
+
+static void meta_out_buf_queue(struct vb2_buffer *vb)
+{
+	struct vb2_v4l2_buffer *vbuf = to_vb2_v4l2_buffer(vb);
+	struct vivid_dev *dev = vb2_get_drv_priv(vb->vb2_queue);
+	struct vivid_buffer *buf = container_of(vbuf, struct vivid_buffer, vb);
+
+	dprintk(dev, 1, "%s\n", __func__);
+
+	spin_lock(&dev->slock);
+	list_add_tail(&buf->list, &dev->meta_out_active);
+	spin_unlock(&dev->slock);
+}
+
+static int meta_out_start_streaming(struct vb2_queue *vq, unsigned int count)
+{
+	struct vivid_dev *dev = vb2_get_drv_priv(vq);
+	int err;
+
+	dprintk(dev, 1, "%s\n", __func__);
+	dev->meta_out_seq_count = 0;
+	if (dev->start_streaming_error) {
+		dev->start_streaming_error = false;
+		err = -EINVAL;
+	} else {
+		err = vivid_start_generating_vid_out(dev,
+						     &dev->meta_out_streaming);
+	}
+	if (err) {
+		struct vivid_buffer *buf, *tmp;
+
+		list_for_each_entry_safe(buf, tmp,
+					 &dev->meta_out_active, list) {
+			list_del(&buf->list);
+			vb2_buffer_done(&buf->vb.vb2_buf,
+					VB2_BUF_STATE_QUEUED);
+		}
+	}
+	return err;
+}
+
+/* abort streaming and wait for last buffer */
+static void meta_out_stop_streaming(struct vb2_queue *vq)
+{
+	struct vivid_dev *dev = vb2_get_drv_priv(vq);
+
+	dprintk(dev, 1, "%s\n", __func__);
+	vivid_stop_generating_vid_out(dev, &dev->meta_out_streaming);
+}
+
+static void meta_out_buf_request_complete(struct vb2_buffer *vb)
+{
+	struct vivid_dev *dev = vb2_get_drv_priv(vb->vb2_queue);
+
+	v4l2_ctrl_request_complete(vb->req_obj.req, &dev->ctrl_hdl_meta_out);
+}
+
+const struct vb2_ops vivid_meta_out_qops = {
+	.queue_setup            = meta_out_queue_setup,
+	.buf_prepare            = meta_out_buf_prepare,
+	.buf_queue              = meta_out_buf_queue,
+	.start_streaming        = meta_out_start_streaming,
+	.stop_streaming         = meta_out_stop_streaming,
+	.buf_request_complete   = meta_out_buf_request_complete,
+	.wait_prepare           = vb2_ops_wait_prepare,
+	.wait_finish            = vb2_ops_wait_finish,
+};
+
+int vidioc_enum_fmt_meta_out(struct file *file, void  *priv,
+			     struct v4l2_fmtdesc *f)
+{
+	struct vivid_dev *dev = video_drvdata(file);
+
+	if (!vivid_is_webcam(dev))
+		return -EINVAL;
+
+	if (f->index > 0)
+		return -EINVAL;
+
+	f->type = V4L2_BUF_TYPE_META_OUTPUT;
+	f->pixelformat = V4L2_META_FMT_VIVID;
+	return 0;
+}
+
+int vidioc_g_fmt_meta_out(struct file *file, void *priv,
+			  struct v4l2_format *f)
+{
+	struct vivid_dev *dev = video_drvdata(file);
+	struct v4l2_meta_format *meta = &f->fmt.meta;
+
+	if (!vivid_is_webcam(dev) || !dev->has_meta_out)
+		return -EINVAL;
+
+	meta->dataformat = V4L2_META_FMT_VIVID;
+	meta->buffersize = sizeof(struct vivid_meta_out_buf);
+	return 0;
+}
+
+void vivid_meta_out_process(struct vivid_dev *dev,
+			    struct vivid_buffer *buf)
+{
+	struct vivid_meta_out_buf *meta = vb2_plane_vaddr(&buf->vb.vb2_buf, 0);
+
+	tpg_s_brightness(&dev->tpg, meta->brightness);
+	tpg_s_contrast(&dev->tpg, meta->contrast);
+	tpg_s_saturation(&dev->tpg, meta->saturation);
+	tpg_s_hue(&dev->tpg, meta->hue);
+	dprintk(dev, 2, " %s brightness %u contrast %u saturation %u hue %d\n",
+		__func__, meta->brightness, meta->contrast,
+		meta->saturation, meta->hue);
+}
diff --git a/drivers/media/platform/vivid/vivid-meta-out.h b/drivers/media/platform/vivid/vivid-meta-out.h
new file mode 100644
index 000000000000..0c639b7c2842
--- /dev/null
+++ b/drivers/media/platform/vivid/vivid-meta-out.h
@@ -0,0 +1,25 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * vivid-meta-out.h - meta output support functions.
+ */
+#ifndef _VIVID_META_OUT_H_
+#define _VIVID_META_OUT_H_
+
+struct vivid_meta_out_buf {
+	u16	brightness;
+	u16	contrast;
+	u16	saturation;
+	s16	hue;
+};
+
+void vivid_meta_out_process(struct vivid_dev *dev, struct vivid_buffer *buf);
+int vidioc_enum_fmt_meta_out(struct file *file, void  *priv,
+			     struct v4l2_fmtdesc *f);
+int vidioc_g_fmt_meta_out(struct file *file, void *priv,
+			  struct v4l2_format *f);
+int vidioc_s_fmt_meta_out(struct file *file, void *priv,
+			  struct v4l2_format *f);
+
+extern const struct vb2_ops vivid_meta_out_qops;
+
+#endif
diff --git a/drivers/media/platform/vivid/vivid-sdr-cap.c b/drivers/media/platform/vivid/vivid-sdr-cap.c
index 9acc709b0740..2b7522e16efc 100644
--- a/drivers/media/platform/vivid/vivid-sdr-cap.c
+++ b/drivers/media/platform/vivid/vivid-sdr-cap.c
@@ -141,7 +141,11 @@ static int vivid_thread_sdr_cap(void *data)
 		if (kthread_should_stop())
 			break;
 
-		mutex_lock(&dev->mutex);
+		if (!mutex_trylock(&dev->mutex)) {
+			schedule_timeout_uninterruptible(1);
+			continue;
+		}
+
 		cur_jiffies = jiffies;
 		if (dev->sdr_cap_seq_resync) {
 			dev->jiffies_sdr_cap = cur_jiffies;
@@ -303,10 +307,8 @@ static void sdr_cap_stop_streaming(struct vb2_queue *vq)
 	}
 
 	/* shutdown control thread */
-	mutex_unlock(&dev->mutex);
 	kthread_stop(dev->kthread_sdr_cap);
 	dev->kthread_sdr_cap = NULL;
-	mutex_lock(&dev->mutex);
 }
 
 static void sdr_cap_buf_request_complete(struct vb2_buffer *vb)
diff --git a/drivers/media/platform/vivid/vivid-vid-cap.c b/drivers/media/platform/vivid/vivid-vid-cap.c
index 8cbaa0c998ed..e94beef008c8 100644
--- a/drivers/media/platform/vivid/vivid-vid-cap.c
+++ b/drivers/media/platform/vivid/vivid-vid-cap.c
@@ -223,9 +223,6 @@ static int vid_cap_start_streaming(struct vb2_queue *vq, unsigned count)
 	if (vb2_is_streaming(&dev->vb_vid_out_q))
 		dev->can_loop_video = vivid_vid_can_loop(dev);
 
-	if (dev->kthread_vid_cap)
-		return 0;
-
 	dev->vid_cap_seq_count = 0;
 	dprintk(dev, 1, "%s\n", __func__);
 	for (i = 0; i < VIDEO_MAX_FRAME; i++)
@@ -1359,7 +1356,9 @@ int vidioc_s_input(struct file *file, void *priv, unsigned i)
 	if (i == dev->input)
 		return 0;
 
-	if (vb2_is_busy(&dev->vb_vid_cap_q) || vb2_is_busy(&dev->vb_vbi_cap_q))
+	if (vb2_is_busy(&dev->vb_vid_cap_q) ||
+	    vb2_is_busy(&dev->vb_vbi_cap_q) ||
+	    vb2_is_busy(&dev->vb_meta_cap_q))
 		return -EBUSY;
 
 	dev->input = i;
@@ -1369,6 +1368,7 @@ int vidioc_s_input(struct file *file, void *priv, unsigned i)
 		dev->vid_cap_dev.tvnorms = V4L2_STD_ALL;
 	}
 	dev->vbi_cap_dev.tvnorms = dev->vid_cap_dev.tvnorms;
+	dev->meta_cap_dev.tvnorms = dev->vid_cap_dev.tvnorms;
 	vivid_update_format_cap(dev, false);
 
 	if (dev->colorspace) {
diff --git a/drivers/media/platform/vivid/vivid-vid-out.c b/drivers/media/platform/vivid/vivid-vid-out.c
index 148b663a6075..ee3446e3217c 100644
--- a/drivers/media/platform/vivid/vivid-vid-out.c
+++ b/drivers/media/platform/vivid/vivid-vid-out.c
@@ -161,9 +161,6 @@ static int vid_out_start_streaming(struct vb2_queue *vq, unsigned count)
 	if (vb2_is_streaming(&dev->vb_vid_cap_q))
 		dev->can_loop_video = vivid_vid_can_loop(dev);
 
-	if (dev->kthread_vid_out)
-		return 0;
-
 	dev->vid_out_seq_count = 0;
 	dprintk(dev, 1, "%s\n", __func__);
 	if (dev->start_streaming_error) {
@@ -1082,7 +1079,9 @@ int vidioc_s_output(struct file *file, void *priv, unsigned o)
 	if (o == dev->output)
 		return 0;
 
-	if (vb2_is_busy(&dev->vb_vid_out_q) || vb2_is_busy(&dev->vb_vbi_out_q))
+	if (vb2_is_busy(&dev->vb_vid_out_q) ||
+	    vb2_is_busy(&dev->vb_vbi_out_q) ||
+	    vb2_is_busy(&dev->vb_meta_out_q))
 		return -EBUSY;
 
 	dev->output = o;
@@ -1093,6 +1092,7 @@ int vidioc_s_output(struct file *file, void *priv, unsigned o)
 		dev->vid_out_dev.tvnorms = 0;
 
 	dev->vbi_out_dev.tvnorms = dev->vid_out_dev.tvnorms;
+	dev->meta_out_dev.tvnorms = dev->vid_out_dev.tvnorms;
 	vivid_update_format_out(dev);
 
 	v4l2_ctrl_activate(dev->ctrl_display_present, vivid_is_hdmi_out(dev));
diff --git a/drivers/media/platform/xilinx/xilinx-dma.h b/drivers/media/platform/xilinx/xilinx-dma.h
index 5aec4d17eb21..2378bdae57ae 100644
--- a/drivers/media/platform/xilinx/xilinx-dma.h
+++ b/drivers/media/platform/xilinx/xilinx-dma.h
@@ -1,4 +1,4 @@
-// SPDX-License-Identifier: GPL-2.0
+/* SPDX-License-Identifier: GPL-2.0 */
 /*
  * Xilinx Video DMA
  *
diff --git a/drivers/media/platform/xilinx/xilinx-vip.h b/drivers/media/platform/xilinx/xilinx-vip.h
index f71e2b650453..a528a32ea1dc 100644
--- a/drivers/media/platform/xilinx/xilinx-vip.h
+++ b/drivers/media/platform/xilinx/xilinx-vip.h
@@ -1,4 +1,4 @@
-// SPDX-License-Identifier: GPL-2.0
+/* SPDX-License-Identifier: GPL-2.0 */
 /*
  * Xilinx Video IP Core
  *
diff --git a/drivers/media/platform/xilinx/xilinx-vipp.h b/drivers/media/platform/xilinx/xilinx-vipp.h
index e65fce9538f9..cc52c1854dbd 100644
--- a/drivers/media/platform/xilinx/xilinx-vipp.h
+++ b/drivers/media/platform/xilinx/xilinx-vipp.h
@@ -1,4 +1,4 @@
-// SPDX-License-Identifier: GPL-2.0
+/* SPDX-License-Identifier: GPL-2.0 */
 /*
  * Xilinx Video IP Composite Device
  *
diff --git a/drivers/media/platform/xilinx/xilinx-vtc.h b/drivers/media/platform/xilinx/xilinx-vtc.h
index 90cf44245283..855845911ffc 100644
--- a/drivers/media/platform/xilinx/xilinx-vtc.h
+++ b/drivers/media/platform/xilinx/xilinx-vtc.h
@@ -1,4 +1,4 @@
-// SPDX-License-Identifier: GPL-2.0
+/* SPDX-License-Identifier: GPL-2.0 */
 /*
  * Xilinx Video Timing Controller
  *
diff --git a/drivers/media/radio/radio-wl1273.c b/drivers/media/radio/radio-wl1273.c
index 104ac41c6f96..112376873167 100644
--- a/drivers/media/radio/radio-wl1273.c
+++ b/drivers/media/radio/radio-wl1273.c
@@ -1148,8 +1148,7 @@ static int wl1273_fm_fops_release(struct file *file)
 	if (radio->rds_users > 0) {
 		radio->rds_users--;
 		if (radio->rds_users == 0) {
-			if (mutex_lock_interruptible(&core->lock))
-				return -EINTR;
+			mutex_lock(&core->lock);
 
 			radio->irq_flags &= ~WL1273_RDS_EVENT;
 
diff --git a/drivers/media/radio/si470x/radio-si470x-i2c.c b/drivers/media/radio/si470x/radio-si470x-i2c.c
index 7541698a0be1..f491420d7b53 100644
--- a/drivers/media/radio/si470x/radio-si470x-i2c.c
+++ b/drivers/media/radio/si470x/radio-si470x-i2c.c
@@ -482,6 +482,8 @@ static int si470x_i2c_remove(struct i2c_client *client)
 	if (radio->gpio_reset)
 		gpiod_set_value(radio->gpio_reset, 0);
 
+	v4l2_ctrl_handler_free(&radio->hdl);
+	v4l2_device_unregister(&radio->v4l2_dev);
 	return 0;
 }
 
diff --git a/drivers/media/rc/imon.c b/drivers/media/rc/imon.c
index 37a850421fbb..ed95244da894 100644
--- a/drivers/media/rc/imon.c
+++ b/drivers/media/rc/imon.c
@@ -83,6 +83,7 @@ struct imon_usb_dev_descr {
 	__u16 flags;
 #define IMON_NO_FLAGS 0
 #define IMON_NEED_20MS_PKT_DELAY 1
+#define IMON_SUPPRESS_REPEATED_KEYS 2
 	struct imon_panel_key_table key_table[];
 };
 
@@ -149,8 +150,9 @@ struct imon_context {
 	struct timer_list ttimer;	/* touch screen timer */
 	int touch_x;			/* x coordinate on touchscreen */
 	int touch_y;			/* y coordinate on touchscreen */
-	struct imon_usb_dev_descr *dev_descr; /* device description with key
-						 table for front panels */
+	const struct imon_usb_dev_descr *dev_descr;
+					/* device description with key */
+					/* table for front panels */
 };
 
 #define TOUCH_TIMEOUT	(HZ/30)
@@ -315,6 +317,32 @@ static const struct imon_usb_dev_descr imon_DH102 = {
 	}
 };
 
+/* imon ultrabay front panel key table */
+static const struct imon_usb_dev_descr ultrabay_table = {
+	.flags = IMON_SUPPRESS_REPEATED_KEYS,
+	.key_table = {
+		{ 0x0000000f0000ffeell, KEY_MEDIA },      /* Go */
+		{ 0x000000000100ffeell, KEY_UP },
+		{ 0x000000000001ffeell, KEY_DOWN },
+		{ 0x000000160000ffeell, KEY_ENTER },
+		{ 0x0000001f0000ffeell, KEY_AUDIO },      /* Music */
+		{ 0x000000200000ffeell, KEY_VIDEO },      /* Movie */
+		{ 0x000000210000ffeell, KEY_CAMERA },     /* Photo */
+		{ 0x000000270000ffeell, KEY_DVD },        /* DVD */
+		{ 0x000000230000ffeell, KEY_TV },         /* TV */
+		{ 0x000000050000ffeell, KEY_PREVIOUS },   /* Previous */
+		{ 0x000000070000ffeell, KEY_REWIND },
+		{ 0x000000040000ffeell, KEY_STOP },
+		{ 0x000000020000ffeell, KEY_PLAYPAUSE },
+		{ 0x000000080000ffeell, KEY_FASTFORWARD },
+		{ 0x000000060000ffeell, KEY_NEXT },       /* Next */
+		{ 0x000100000000ffeell, KEY_VOLUMEUP },
+		{ 0x010000000000ffeell, KEY_VOLUMEDOWN },
+		{ 0x000000010000ffeell, KEY_MUTE },
+		{ 0, KEY_RESERVED },
+	}
+};
+
 /*
  * USB Device ID for iMON USB Control Boards
  *
@@ -1264,9 +1292,11 @@ static u32 imon_mce_key_lookup(struct imon_context *ictx, u32 scancode)
 
 static u32 imon_panel_key_lookup(struct imon_context *ictx, u64 code)
 {
-	int i;
+	const struct imon_panel_key_table *key_table;
 	u32 keycode = KEY_RESERVED;
-	struct imon_panel_key_table *key_table = ictx->dev_descr->key_table;
+	int i;
+
+	key_table = ictx->dev_descr->key_table;
 
 	for (i = 0; key_table[i].hw_code != 0; i++) {
 		if (key_table[i].hw_code == (code | 0xffee)) {
@@ -1550,7 +1580,6 @@ static void imon_incoming_packet(struct imon_context *ictx,
 	u32 kc;
 	u64 scancode;
 	int press_type = 0;
-	long msec;
 	ktime_t t;
 	static ktime_t prev_time;
 	u8 ktype;
@@ -1598,8 +1627,7 @@ static void imon_incoming_packet(struct imon_context *ictx,
 	spin_unlock_irqrestore(&ictx->kc_lock, flags);
 
 	/* send touchscreen events through input subsystem if touchpad data */
-	if (ictx->display_type == IMON_DISPLAY_TYPE_VGA && len == 8 &&
-	    buf[7] == 0x86) {
+	if (ictx->touch && len == 8 && buf[7] == 0x86) {
 		imon_touch_event(ictx, buf);
 		return;
 
@@ -1653,14 +1681,16 @@ static void imon_incoming_packet(struct imon_context *ictx,
 	spin_lock_irqsave(&ictx->kc_lock, flags);
 
 	t = ktime_get();
-	/* KEY_MUTE repeats from knob need to be suppressed */
-	if (ictx->kc == KEY_MUTE && ictx->kc == ictx->last_keycode) {
-		msec = ktime_ms_delta(t, prev_time);
-		if (msec < ictx->idev->rep[REP_DELAY]) {
+	/* KEY repeats from knob and panel that need to be suppressed */
+	if (ictx->kc == KEY_MUTE ||
+	    ictx->dev_descr->flags & IMON_SUPPRESS_REPEATED_KEYS) {
+		if (ictx->kc == ictx->last_keycode &&
+		    ktime_ms_delta(t, prev_time) < ictx->idev->rep[REP_DELAY]) {
 			spin_unlock_irqrestore(&ictx->kc_lock, flags);
 			return;
 		}
 	}
+
 	prev_time = t;
 	kc = ictx->kc;
 
@@ -1848,6 +1878,14 @@ static void imon_get_ffdc_type(struct imon_context *ictx)
 		dev_info(ictx->dev, "0xffdc iMON Inside, iMON IR");
 		ictx->display_supported = false;
 		break;
+	/* Soundgraph iMON UltraBay */
+	case 0x98:
+		dev_info(ictx->dev, "0xffdc iMON UltraBay, LCD + IR");
+		detected_display_type = IMON_DISPLAY_TYPE_LCD;
+		allowed_protos = RC_PROTO_BIT_IMON | RC_PROTO_BIT_RC6_MCE;
+		ictx->dev_descr = &ultrabay_table;
+		break;
+
 	default:
 		dev_info(ictx->dev, "Unknown 0xffdc device, defaulting to VFD and iMON IR");
 		detected_display_type = IMON_DISPLAY_TYPE_VFD;
@@ -1979,10 +2017,12 @@ out:
 
 static struct input_dev *imon_init_idev(struct imon_context *ictx)
 {
-	struct imon_panel_key_table *key_table = ictx->dev_descr->key_table;
+	const struct imon_panel_key_table *key_table;
 	struct input_dev *idev;
 	int ret, i;
 
+	key_table = ictx->dev_descr->key_table;
+
 	idev = input_allocate_device();
 	if (!idev)
 		goto out;
diff --git a/drivers/media/rc/imon_raw.c b/drivers/media/rc/imon_raw.c
index d4aedcf76418..aae0a3cc9479 100644
--- a/drivers/media/rc/imon_raw.c
+++ b/drivers/media/rc/imon_raw.c
@@ -57,32 +57,18 @@ static void imon_ir_data(struct imon *imon)
 		 * fls will tell us the highest bit set plus 1 (or 0 if no
 		 * bits are set).
 		 */
+		rawir.pulse = !rawir.pulse;
 		bit = fls64(data & (BIT_ULL(offset) - 1));
 		if (bit < offset) {
-			dev_dbg(imon->dev, "pulse: %d bits", offset - bit);
-			rawir.pulse = true;
+			dev_dbg(imon->dev, "%s: %d bits",
+				rawir.pulse ? "pulse" : "space", offset - bit);
 			rawir.duration = (offset - bit) * BIT_DURATION;
 			ir_raw_event_store_with_filter(imon->rcdev, &rawir);
 
-			if (bit == 0)
-				break;
-
 			offset = bit;
 		}
 
-		/*
-		 * Find highest clear bit which is less than offset.
-		 *
-		 * Just invert the data and use same trick as above.
-		 */
-		bit = fls64(~data & (BIT_ULL(offset) - 1));
-		dev_dbg(imon->dev, "space: %d bits", offset - bit);
-
-		rawir.pulse = false;
-		rawir.duration = (offset - bit) * BIT_DURATION;
-		ir_raw_event_store_with_filter(imon->rcdev, &rawir);
-
-		offset = bit;
+		data = ~data;
 	} while (offset > 0);
 
 	if (packet_no == 0x0a && !imon->rcdev->idle) {
diff --git a/drivers/media/rc/ir-rcmm-decoder.c b/drivers/media/rc/ir-rcmm-decoder.c
index 64fb65a9a19f..028df5cb1828 100644
--- a/drivers/media/rc/ir-rcmm-decoder.c
+++ b/drivers/media/rc/ir-rcmm-decoder.c
@@ -79,7 +79,7 @@ static int ir_rcmm_decode(struct rc_dev *dev, struct ir_raw_event ev)
 		if (!ev.pulse)
 			break;
 
-		if (!eq_margin(ev.duration, RCMM_PREFIX_PULSE, RCMM_UNIT / 2))
+		if (!eq_margin(ev.duration, RCMM_PREFIX_PULSE, RCMM_UNIT))
 			break;
 
 		data->state = STATE_LOW;
@@ -91,7 +91,7 @@ static int ir_rcmm_decode(struct rc_dev *dev, struct ir_raw_event ev)
 		if (ev.pulse)
 			break;
 
-		if (!eq_margin(ev.duration, RCMM_PULSE_0, RCMM_UNIT / 2))
+		if (!eq_margin(ev.duration, RCMM_PULSE_0, RCMM_UNIT))
 			break;
 
 		data->state = STATE_BUMP;
@@ -164,6 +164,8 @@ static int ir_rcmm_decode(struct rc_dev *dev, struct ir_raw_event ev)
 		break;
 	}
 
+	dev_dbg(&dev->dev, "RC-MM decode failed at count %d state %d (%uus %s)\n",
+		data->count, data->state, TO_US(ev.duration), TO_STR(ev.pulse));
 	data->state = STATE_INACTIVE;
 	return -EINVAL;
 }
diff --git a/drivers/media/rc/ite-cir.c b/drivers/media/rc/ite-cir.c
index 3ab6cec0dc3b..07667c04c1d2 100644
--- a/drivers/media/rc/ite-cir.c
+++ b/drivers/media/rc/ite-cir.c
@@ -382,7 +382,7 @@ static int ite_tx_ir(struct rc_dev *rcdev, unsigned *txbuf, unsigned n)
 	ite_dbg("%s called", __func__);
 
 	/* clear the array just in case */
-	memset(last_sent, 0, ARRAY_SIZE(last_sent));
+	memset(last_sent, 0, sizeof(last_sent));
 
 	spin_lock_irqsave(&dev->lock, flags);
 
diff --git a/drivers/media/rc/keymaps/Makefile b/drivers/media/rc/keymaps/Makefile
index a56fc634d2d6..63261ef6380a 100644
--- a/drivers/media/rc/keymaps/Makefile
+++ b/drivers/media/rc/keymaps/Makefile
@@ -17,6 +17,7 @@ obj-$(CONFIG_RC_MAP) += rc-adstech-dvb-t-pci.o \
 			rc-avermedia-rm-ks.o \
 			rc-avertv-303.o \
 			rc-azurewave-ad-tu700.o \
+			rc-beelink-gs1.o \
 			rc-behold.o \
 			rc-behold-columbus.o \
 			rc-budget-ci-old.o \
@@ -114,6 +115,7 @@ obj-$(CONFIG_RC_MAP) += rc-adstech-dvb-t-pci.o \
 			rc-tt-1500.o \
 			rc-twinhan-dtv-cab-ci.o \
 			rc-twinhan1027.o \
+			rc-vega-s9x.o \
 			rc-videomate-m1f.o \
 			rc-videomate-s350.o \
 			rc-videomate-tv-pvr.o \
diff --git a/drivers/media/rc/keymaps/rc-beelink-gs1.c b/drivers/media/rc/keymaps/rc-beelink-gs1.c
new file mode 100644
index 000000000000..cedbd5d20bc7
--- /dev/null
+++ b/drivers/media/rc/keymaps/rc-beelink-gs1.c
@@ -0,0 +1,84 @@
+// SPDX-License-Identifier: GPL-2.0+
+// Copyright (c) 2019 Clément Péron
+
+#include <media/rc-map.h>
+#include <linux/module.h>
+
+/*
+ * Keymap for the Beelink GS1 remote control
+ */
+
+static struct rc_map_table beelink_gs1_table[] = {
+	/*
+	 * TV Keys (Power, Learn and Volume)
+	 * { 0x40400d, KEY_TV },
+	 * { 0x80f1, KEY_TV },
+	 * { 0x80f3, KEY_TV },
+	 * { 0x80f4, KEY_TV },
+	 */
+
+	{ 0x8051, KEY_POWER },
+	{ 0x804d, KEY_MUTE },
+	{ 0x8040, KEY_CONFIG },
+
+	{ 0x8026, KEY_UP },
+	{ 0x8028, KEY_DOWN },
+	{ 0x8025, KEY_LEFT },
+	{ 0x8027, KEY_RIGHT },
+	{ 0x800d, KEY_OK },
+
+	{ 0x8053, KEY_HOME },
+	{ 0x80bc, KEY_MEDIA },
+	{ 0x801b, KEY_BACK },
+	{ 0x8049, KEY_MENU },
+
+	{ 0x804e, KEY_VOLUMEUP },
+	{ 0x8056, KEY_VOLUMEDOWN },
+
+	{ 0x8054, KEY_SUBTITLE }, /* Web */
+	{ 0x8052, KEY_EPG }, /* Media */
+
+	{ 0x8041, KEY_CHANNELUP },
+	{ 0x8042, KEY_CHANNELDOWN },
+
+	{ 0x8031, KEY_1 },
+	{ 0x8032, KEY_2 },
+	{ 0x8033, KEY_3 },
+
+	{ 0x8034, KEY_4 },
+	{ 0x8035, KEY_5 },
+	{ 0x8036, KEY_6 },
+
+	{ 0x8037, KEY_7 },
+	{ 0x8038, KEY_8 },
+	{ 0x8039, KEY_9 },
+
+	{ 0x8044, KEY_DELETE },
+	{ 0x8030, KEY_0 },
+	{ 0x8058, KEY_MODE }, /* # Input Method */
+};
+
+static struct rc_map_list beelink_gs1_map = {
+	.map = {
+		.scan     = beelink_gs1_table,
+		.size     = ARRAY_SIZE(beelink_gs1_table),
+		.rc_proto = RC_PROTO_NEC,
+		.name     = RC_MAP_BEELINK_GS1,
+	}
+};
+
+static int __init init_rc_map_beelink_gs1(void)
+{
+	return rc_map_register(&beelink_gs1_map);
+}
+
+static void __exit exit_rc_map_beelink_gs1(void)
+{
+	rc_map_unregister(&beelink_gs1_map);
+}
+
+module_init(init_rc_map_beelink_gs1)
+module_exit(exit_rc_map_beelink_gs1)
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Clément Péron <peron.clem@gmail.com>");
diff --git a/drivers/media/rc/keymaps/rc-vega-s9x.c b/drivers/media/rc/keymaps/rc-vega-s9x.c
new file mode 100644
index 000000000000..bf210c4dc535
--- /dev/null
+++ b/drivers/media/rc/keymaps/rc-vega-s9x.c
@@ -0,0 +1,54 @@
+// SPDX-License-Identifier: GPL-2.0+
+//
+// Copyright (C) 2019 Christian Hewitt <christianshewitt@gmail.com>
+
+#include <media/rc-map.h>
+#include <linux/module.h>
+
+//
+// Keytable for the Tronsmart Vega S9x remote control
+//
+
+static struct rc_map_table vega_s9x[] = {
+	{ 0x18, KEY_POWER },
+	{ 0x17, KEY_MUTE }, // mouse
+
+	{ 0x46, KEY_UP },
+	{ 0x47, KEY_LEFT },
+	{ 0x55, KEY_OK },
+	{ 0x15, KEY_RIGHT },
+	{ 0x16, KEY_DOWN },
+
+	{ 0x06, KEY_HOME },
+	{ 0x42, KEY_PLAYPAUSE},
+	{ 0x40, KEY_BACK },
+
+	{ 0x14, KEY_VOLUMEDOWN },
+	{ 0x04, KEY_MENU },
+	{ 0x10, KEY_VOLUMEUP },
+};
+
+static struct rc_map_list vega_s9x_map = {
+	.map = {
+		.scan     = vega_s9x,
+		.size     = ARRAY_SIZE(vega_s9x),
+		.rc_proto = RC_PROTO_NEC,
+		.name     = RC_MAP_VEGA_S9X,
+	}
+};
+
+static int __init init_rc_map_vega_s9x(void)
+{
+	return rc_map_register(&vega_s9x_map);
+}
+
+static void __exit exit_rc_map_vega_s9x(void)
+{
+	rc_map_unregister(&vega_s9x_map);
+}
+
+module_init(init_rc_map_vega_s9x)
+module_exit(exit_rc_map_vega_s9x)
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Christian Hewitt <christianshewitt@gmail.com");
diff --git a/drivers/media/rc/mceusb.c b/drivers/media/rc/mceusb.c
index 3fc9829a9233..f9616158bcf4 100644
--- a/drivers/media/rc/mceusb.c
+++ b/drivers/media/rc/mceusb.c
@@ -564,7 +564,7 @@ static int mceusb_cmd_datasize(u8 cmd, u8 subcmd)
 			datasize = 4;
 			break;
 		case MCE_CMD_G_REVISION:
-			datasize = 2;
+			datasize = 4;
 			break;
 		case MCE_RSP_EQWAKESUPPORT:
 		case MCE_RSP_GETWAKESOURCE:
@@ -600,14 +600,9 @@ static void mceusb_dev_printdata(struct mceusb_dev *ir, u8 *buf, int buf_len,
 	char *inout;
 	u8 cmd, subcmd, *data;
 	struct device *dev = ir->dev;
-	int start, skip = 0;
 	u32 carrier, period;
 
-	/* skip meaningless 0xb1 0x60 header bytes on orig receiver */
-	if (ir->flags.microsoft_gen1 && !out && !offset)
-		skip = 2;
-
-	if (len <= skip)
+	if (offset < 0 || offset >= buf_len)
 		return;
 
 	dev_dbg(dev, "%cx data[%d]: %*ph (len=%d sz=%d)",
@@ -616,11 +611,32 @@ static void mceusb_dev_printdata(struct mceusb_dev *ir, u8 *buf, int buf_len,
 
 	inout = out ? "Request" : "Got";
 
-	start  = offset + skip;
-	cmd    = buf[start] & 0xff;
-	subcmd = buf[start + 1] & 0xff;
-	data = buf + start + 2;
+	cmd    = buf[offset];
+	subcmd = (offset + 1 < buf_len) ? buf[offset + 1] : 0;
+	data   = &buf[offset] + 2;
+
+	/* Trace meaningless 0xb1 0x60 header bytes on original receiver */
+	if (ir->flags.microsoft_gen1 && !out && !offset) {
+		dev_dbg(dev, "MCE gen 1 header");
+		return;
+	}
+
+	/* Trace IR data header or trailer */
+	if (cmd != MCE_CMD_PORT_IR &&
+	    (cmd & MCE_PORT_MASK) == MCE_COMMAND_IRDATA) {
+		if (cmd == MCE_IRDATA_TRAILER)
+			dev_dbg(dev, "End of raw IR data");
+		else
+			dev_dbg(dev, "Raw IR data, %d pulse/space samples",
+				cmd & MCE_PACKET_LENGTH_MASK);
+		return;
+	}
+
+	/* Unexpected end of buffer? */
+	if (offset + len > buf_len)
+		return;
 
+	/* Decode MCE command/response */
 	switch (cmd) {
 	case MCE_CMD_NULL:
 		if (subcmd == MCE_CMD_NULL)
@@ -644,7 +660,7 @@ static void mceusb_dev_printdata(struct mceusb_dev *ir, u8 *buf, int buf_len,
 				dev_dbg(dev, "Get hw/sw rev?");
 			else
 				dev_dbg(dev, "hw/sw rev %*ph",
-					4, &buf[start + 2]);
+					4, &buf[offset + 2]);
 			break;
 		case MCE_CMD_RESUME:
 			dev_dbg(dev, "Device resume requested");
@@ -746,13 +762,6 @@ static void mceusb_dev_printdata(struct mceusb_dev *ir, u8 *buf, int buf_len,
 	default:
 		break;
 	}
-
-	if (cmd == MCE_IRDATA_TRAILER)
-		dev_dbg(dev, "End of raw IR data");
-	else if ((cmd != MCE_CMD_PORT_IR) &&
-		 ((cmd & MCE_PORT_MASK) == MCE_COMMAND_IRDATA))
-		dev_dbg(dev, "Raw IR data, %d pulse/space samples",
-			cmd & MCE_PACKET_LENGTH_MASK);
 #endif
 }
 
@@ -1136,32 +1145,62 @@ static int mceusb_set_rx_carrier_report(struct rc_dev *dev, int enable)
 }
 
 /*
+ * Handle PORT_SYS/IR command response received from the MCE device.
+ *
+ * Assumes single response with all its data (not truncated)
+ * in buf_in[]. The response itself determines its total length
+ * (mceusb_cmd_datasize() + 2) and hence the minimum size of buf_in[].
+ *
  * We don't do anything but print debug spew for many of the command bits
  * we receive from the hardware, but some of them are useful information
  * we want to store so that we can use them.
  */
-static void mceusb_handle_command(struct mceusb_dev *ir, int index)
+static void mceusb_handle_command(struct mceusb_dev *ir, u8 *buf_in)
 {
+	u8 cmd = buf_in[0];
+	u8 subcmd = buf_in[1];
+	u8 *hi = &buf_in[2];		/* read only when required */
+	u8 *lo = &buf_in[3];		/* read only when required */
 	struct ir_raw_event rawir = {};
-	u8 hi = ir->buf_in[index + 1] & 0xff;
-	u8 lo = ir->buf_in[index + 2] & 0xff;
 	u32 carrier_cycles;
 	u32 cycles_fix;
 
-	switch (ir->buf_in[index]) {
-	/* the one and only 5-byte return value command */
-	case MCE_RSP_GETPORTSTATUS:
-		if ((ir->buf_in[index + 4] & 0xff) == 0x00)
-			ir->txports_cabled |= 1 << hi;
-		break;
+	if (cmd == MCE_CMD_PORT_SYS) {
+		switch (subcmd) {
+		/* the one and only 5-byte return value command */
+		case MCE_RSP_GETPORTSTATUS:
+			if (buf_in[5] == 0)
+				ir->txports_cabled |= 1 << *hi;
+			break;
+
+		/* 1-byte return value commands */
+		case MCE_RSP_EQEMVER:
+			ir->emver = *hi;
+			break;
+
+		/* No return value commands */
+		case MCE_RSP_CMD_ILLEGAL:
+			ir->need_reset = true;
+			break;
+
+		default:
+			break;
+		}
+
+		return;
+	}
 
+	if (cmd != MCE_CMD_PORT_IR)
+		return;
+
+	switch (subcmd) {
 	/* 2-byte return value commands */
 	case MCE_RSP_EQIRTIMEOUT:
-		ir->rc->timeout = US_TO_NS((hi << 8 | lo) * MCE_TIME_UNIT);
+		ir->rc->timeout = US_TO_NS((*hi << 8 | *lo) * MCE_TIME_UNIT);
 		break;
 	case MCE_RSP_EQIRNUMPORTS:
-		ir->num_txports = hi;
-		ir->num_rxports = lo;
+		ir->num_txports = *hi;
+		ir->num_rxports = *lo;
 		break;
 	case MCE_RSP_EQIRRXCFCNT:
 		/*
@@ -1174,7 +1213,7 @@ static void mceusb_handle_command(struct mceusb_dev *ir, int index)
 		 */
 		if (ir->carrier_report_enabled && ir->learning_active &&
 		    ir->pulse_tunit > 0) {
-			carrier_cycles = (hi << 8 | lo);
+			carrier_cycles = (*hi << 8 | *lo);
 			/*
 			 * Adjust carrier cycle count by adding
 			 * 1 missed count per pulse "on"
@@ -1192,24 +1231,24 @@ static void mceusb_handle_command(struct mceusb_dev *ir, int index)
 		break;
 
 	/* 1-byte return value commands */
-	case MCE_RSP_EQEMVER:
-		ir->emver = hi;
-		break;
 	case MCE_RSP_EQIRTXPORTS:
-		ir->tx_mask = hi;
+		ir->tx_mask = *hi;
 		break;
 	case MCE_RSP_EQIRRXPORTEN:
-		ir->learning_active = ((hi & 0x02) == 0x02);
-		if (ir->rxports_active != hi) {
+		ir->learning_active = ((*hi & 0x02) == 0x02);
+		if (ir->rxports_active != *hi) {
 			dev_info(ir->dev, "%s-range (0x%x) receiver active",
-				 ir->learning_active ? "short" : "long", hi);
-			ir->rxports_active = hi;
+				 ir->learning_active ? "short" : "long", *hi);
+			ir->rxports_active = *hi;
 		}
 		break;
+
+	/* No return value commands */
 	case MCE_RSP_CMD_ILLEGAL:
 	case MCE_RSP_TX_TIMEOUT:
 		ir->need_reset = true;
 		break;
+
 	default:
 		break;
 	}
@@ -1235,7 +1274,8 @@ static void mceusb_process_ir_data(struct mceusb_dev *ir, int buf_len)
 			ir->rem = mceusb_cmd_datasize(ir->cmd, ir->buf_in[i]);
 			mceusb_dev_printdata(ir, ir->buf_in, buf_len, i - 1,
 					     ir->rem + 2, false);
-			mceusb_handle_command(ir, i);
+			if (i + ir->rem < buf_len)
+				mceusb_handle_command(ir, &ir->buf_in[i - 1]);
 			ir->parser_state = CMD_DATA;
 			break;
 		case PARSE_IRDATA:
@@ -1264,15 +1304,22 @@ static void mceusb_process_ir_data(struct mceusb_dev *ir, int buf_len)
 			ir->rem--;
 			break;
 		case CMD_HEADER:
-			/* decode mce packets of the form (84),AA,BB,CC,DD */
-			/* IR data packets can span USB messages - rem */
 			ir->cmd = ir->buf_in[i];
 			if ((ir->cmd == MCE_CMD_PORT_IR) ||
 			    ((ir->cmd & MCE_PORT_MASK) !=
 			     MCE_COMMAND_IRDATA)) {
+				/*
+				 * got PORT_SYS, PORT_IR, or unknown
+				 * command response prefix
+				 */
 				ir->parser_state = SUBCMD;
 				continue;
 			}
+			/*
+			 * got IR data prefix (0x80 + num_bytes)
+			 * decode MCE packets of the form {0x83, AA, BB, CC}
+			 * IR data packets can span USB messages
+			 */
 			ir->rem = (ir->cmd & MCE_PACKET_LENGTH_MASK);
 			mceusb_dev_printdata(ir, ir->buf_in, buf_len,
 					     i, ir->rem + 1, false);
@@ -1296,6 +1343,14 @@ static void mceusb_process_ir_data(struct mceusb_dev *ir, int buf_len)
 		if (ir->parser_state != CMD_HEADER && !ir->rem)
 			ir->parser_state = CMD_HEADER;
 	}
+
+	/*
+	 * Accept IR data spanning multiple rx buffers.
+	 * Reject MCE command response spanning multiple rx buffers.
+	 */
+	if (ir->parser_state != PARSE_IRDATA || !ir->rem)
+		ir->parser_state = CMD_HEADER;
+
 	if (event) {
 		dev_dbg(ir->dev, "processed IR data");
 		ir_raw_event_handle(ir->rc);
diff --git a/drivers/media/rc/rc-core-priv.h b/drivers/media/rc/rc-core-priv.h
index 9f21b3e8b377..5f36244cc34f 100644
--- a/drivers/media/rc/rc-core-priv.h
+++ b/drivers/media/rc/rc-core-priv.h
@@ -1,5 +1,5 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 /*
- * SPDX-License-Identifier: GPL-2.0
  * Remote Controller core raw events header
  *
  * Copyright (C) 2010 by Mauro Carvalho Chehab
diff --git a/drivers/media/rc/rc-main.c b/drivers/media/rc/rc-main.c
index 13da4c5c7d17..7741151606ef 100644
--- a/drivers/media/rc/rc-main.c
+++ b/drivers/media/rc/rc-main.c
@@ -1773,6 +1773,7 @@ static int rc_prepare_rx_device(struct rc_dev *dev)
 	set_bit(MSC_SCAN, dev->input_dev->mscbit);
 
 	/* Pointer/mouse events */
+	set_bit(INPUT_PROP_POINTING_STICK, dev->input_dev->propbit);
 	set_bit(EV_REL, dev->input_dev->evbit);
 	set_bit(REL_X, dev->input_dev->relbit);
 	set_bit(REL_Y, dev->input_dev->relbit);
diff --git a/drivers/media/rc/tango-ir.c b/drivers/media/rc/tango-ir.c
index 451ec4e9dcfa..b8eb5bc4d9be 100644
--- a/drivers/media/rc/tango-ir.c
+++ b/drivers/media/rc/tango-ir.c
@@ -157,20 +157,10 @@ static int tango_ir_probe(struct platform_device *pdev)
 	struct device *dev = &pdev->dev;
 	struct rc_dev *rc;
 	struct tango_ir *ir;
-	struct resource *rc5_res;
-	struct resource *rc6_res;
 	u64 clkrate, clkdiv;
 	int irq, err;
 	u32 val;
 
-	rc5_res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	if (!rc5_res)
-		return -EINVAL;
-
-	rc6_res = platform_get_resource(pdev, IORESOURCE_MEM, 1);
-	if (!rc6_res)
-		return -EINVAL;
-
 	irq = platform_get_irq(pdev, 0);
 	if (irq <= 0)
 		return -EINVAL;
@@ -179,11 +169,11 @@ static int tango_ir_probe(struct platform_device *pdev)
 	if (!ir)
 		return -ENOMEM;
 
-	ir->rc5_base = devm_ioremap_resource(dev, rc5_res);
+	ir->rc5_base = devm_platform_ioremap_resource(pdev, 0);
 	if (IS_ERR(ir->rc5_base))
 		return PTR_ERR(ir->rc5_base);
 
-	ir->rc6_base = devm_ioremap_resource(dev, rc6_res);
+	ir->rc6_base = devm_platform_ioremap_resource(pdev, 1);
 	if (IS_ERR(ir->rc6_base))
 		return PTR_ERR(ir->rc6_base);
 
diff --git a/drivers/media/tuners/qm1d1c0042.c b/drivers/media/tuners/qm1d1c0042.c
index 83ca5dc047ea..0e26d22f0b26 100644
--- a/drivers/media/tuners/qm1d1c0042.c
+++ b/drivers/media/tuners/qm1d1c0042.c
@@ -206,7 +206,7 @@ static int qm1d1c0042_set_params(struct dvb_frontend *fe)
 	if (ret < 0)
 		return ret;
 
-	a = (freq + state->cfg.xtal_freq / 2) / state->cfg.xtal_freq;
+	a = DIV_ROUND_CLOSEST(freq, state->cfg.xtal_freq);
 
 	state->regs[0x06] &= 0x40;
 	state->regs[0x06] |= (a - 12) / 4;
diff --git a/drivers/media/tuners/si2157.c b/drivers/media/tuners/si2157.c
index e87040d6eca7..898e0f9f8b70 100644
--- a/drivers/media/tuners/si2157.c
+++ b/drivers/media/tuners/si2157.c
@@ -118,6 +118,11 @@ static int si2157_init(struct dvb_frontend *fe)
 			goto err;
 	}
 
+	if (dev->dont_load_firmware) {
+		dev_info(&client->dev, "device is buggy, skipping firmware download\n");
+		goto skip_fw_download;
+	}
+
 	/* query chip revision */
 	memcpy(cmd.args, "\x02", 1);
 	cmd.wlen = 1;
@@ -440,6 +445,7 @@ static int si2157_probe(struct i2c_client *client,
 	i2c_set_clientdata(client, dev);
 	dev->fe = cfg->fe;
 	dev->inversion = cfg->inversion;
+	dev->dont_load_firmware = cfg->dont_load_firmware;
 	dev->if_port = cfg->if_port;
 	dev->chiptype = (u8)id->driver_data;
 	dev->if_frequency = 5000000; /* default value of property 0x0706 */
diff --git a/drivers/media/tuners/si2157.h b/drivers/media/tuners/si2157.h
index c22ca784f43f..ffdece3c2eaa 100644
--- a/drivers/media/tuners/si2157.h
+++ b/drivers/media/tuners/si2157.h
@@ -11,29 +11,34 @@
 #include <media/media-device.h>
 #include <media/dvb_frontend.h>
 
-/*
- * I2C address
- * 0x60
+/**
+ * struct si2157_config - configuration parameters for si2157
+ *
+ * @fe:
+ *	frontend returned by driver
+ * @mdev:
+ *	media device returned by driver
+ * @inversion:
+ *	spectral inversion
+ * @dont_load_firmware:
+ *	Instead of uploading a new firmware, use the existing one
+ * @if_port:
+ *	Port selection
+ *	Select the RF interface to use (pins 9+11 or 12+13)
+ *
+ * Note:
+ *	The I2C address of this demod is 0x60.
  */
 struct si2157_config {
-	/*
-	 * frontend
-	 */
 	struct dvb_frontend *fe;
 
 #if defined(CONFIG_MEDIA_CONTROLLER)
 	struct media_device *mdev;
 #endif
 
-	/*
-	 * Spectral Inversion
-	 */
-	bool inversion;
+	unsigned int inversion:1;
+	unsigned int dont_load_firmware:1;
 
-	/*
-	 * Port selection
-	 * Select the RF interface to use (pins 9+11 or 12+13)
-	 */
 	u8 if_port;
 };
 
diff --git a/drivers/media/tuners/si2157_priv.h b/drivers/media/tuners/si2157_priv.h
index 2bda903358da..778f81b39996 100644
--- a/drivers/media/tuners/si2157_priv.h
+++ b/drivers/media/tuners/si2157_priv.h
@@ -23,8 +23,9 @@ enum si2157_pads {
 struct si2157_dev {
 	struct mutex i2c_mutex;
 	struct dvb_frontend *fe;
-	bool active;
-	bool inversion;
+	unsigned int active:1;
+	unsigned int inversion:1;
+	unsigned int dont_load_firmware:1;
 	u8 chiptype;
 	u8 if_port;
 	u32 if_frequency;
diff --git a/drivers/media/tuners/tuner-xc2028-types.h b/drivers/media/tuners/tuner-xc2028-types.h
index 50d017a4822a..fcca39d3e006 100644
--- a/drivers/media/tuners/tuner-xc2028-types.h
+++ b/drivers/media/tuners/tuner-xc2028-types.h
@@ -1,5 +1,5 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 /*
- * SPDX-License-Identifier: GPL-2.0
  * tuner-xc2028_types
  *
  * This file includes internal tipes to be used inside tuner-xc2028.
diff --git a/drivers/media/tuners/tuner-xc2028.h b/drivers/media/tuners/tuner-xc2028.h
index 7b58bc06e35c..2dd45d0765d7 100644
--- a/drivers/media/tuners/tuner-xc2028.h
+++ b/drivers/media/tuners/tuner-xc2028.h
@@ -1,5 +1,5 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 /*
- * SPDX-License-Identifier: GPL-2.0
  * tuner-xc2028
  *
  * Copyright (c) 2007-2008 Mauro Carvalho Chehab <mchehab@kernel.org>
diff --git a/drivers/media/usb/b2c2/flexcop-usb.c b/drivers/media/usb/b2c2/flexcop-usb.c
index 1826ff825c2e..039963a7765b 100644
--- a/drivers/media/usb/b2c2/flexcop-usb.c
+++ b/drivers/media/usb/b2c2/flexcop-usb.c
@@ -295,7 +295,7 @@ static int flexcop_usb_i2c_req(struct flexcop_i2c_adapter *i2c,
 
 	mutex_unlock(&fc_usb->data_mutex);
 
-	return 0;
+	return ret;
 }
 
 /* actual bus specific access functions,
@@ -504,7 +504,13 @@ urb_error:
 static int flexcop_usb_init(struct flexcop_usb *fc_usb)
 {
 	/* use the alternate setting with the larges buffer */
-	usb_set_interface(fc_usb->udev,0,1);
+	int ret = usb_set_interface(fc_usb->udev, 0, 1);
+
+	if (ret) {
+		err("set interface failed.");
+		return ret;
+	}
+
 	switch (fc_usb->udev->speed) {
 	case USB_SPEED_LOW:
 		err("cannot handle USB speed because it is too slow.");
@@ -538,6 +544,9 @@ static int flexcop_usb_probe(struct usb_interface *intf,
 	struct flexcop_device *fc = NULL;
 	int ret;
 
+	if (intf->cur_altsetting->desc.bNumEndpoints < 1)
+		return -ENODEV;
+
 	if ((fc = flexcop_device_kmalloc(sizeof(struct flexcop_usb))) == NULL) {
 		err("out of memory\n");
 		return -ENOMEM;
diff --git a/drivers/media/usb/cx231xx/Kconfig b/drivers/media/usb/cx231xx/Kconfig
index 74f3b29d9c60..2fe2b2d335ba 100644
--- a/drivers/media/usb/cx231xx/Kconfig
+++ b/drivers/media/usb/cx231xx/Kconfig
@@ -4,7 +4,7 @@ config VIDEO_CX231XX
 	depends on VIDEO_DEV && I2C && I2C_MUX
 	select VIDEO_TUNER
 	select VIDEO_TVEEPROM
-	select VIDEOBUF_VMALLOC
+	select VIDEOBUF2_VMALLOC
 	select VIDEO_CX25840
 	select VIDEO_CX2341X
 
diff --git a/drivers/media/usb/cx231xx/cx231xx-417.c b/drivers/media/usb/cx231xx/cx231xx-417.c
index 6d218a036966..1aec4459f50a 100644
--- a/drivers/media/usb/cx231xx/cx231xx-417.c
+++ b/drivers/media/usb/cx231xx/cx231xx-417.c
@@ -60,10 +60,6 @@
 #define  MCI_MODE_MEMORY_READ           0x000
 #define  MCI_MODE_MEMORY_WRITE          0x4000
 
-static unsigned int mpegbufs = 8;
-module_param(mpegbufs, int, 0644);
-MODULE_PARM_DESC(mpegbufs, "number of mpeg buffers, range 2-32");
-
 static unsigned int mpeglines = 128;
 module_param(mpeglines, int, 0644);
 MODULE_PARM_DESC(mpeglines, "number of lines in an MPEG buffer, range 2-32");
@@ -1080,16 +1076,6 @@ static int cx231xx_load_firmware(struct cx231xx *dev)
 	return 0;
 }
 
-static void cx231xx_417_check_encoder(struct cx231xx *dev)
-{
-	u32 status, seq;
-
-	status = 0;
-	seq = 0;
-	cx231xx_api_cmd(dev, CX2341X_ENC_GET_SEQ_END, 0, 2, &status, &seq);
-	dprintk(1, "%s() status = %d, seq = %d\n", __func__, status, seq);
-}
-
 static void cx231xx_codec_settings(struct cx231xx *dev)
 {
 	dprintk(1, "%s()\n", __func__);
@@ -1227,40 +1213,25 @@ static int cx231xx_initialize_codec(struct cx231xx *dev)
 
 /* ------------------------------------------------------------------ */
 
-static int bb_buf_setup(struct videobuf_queue *q,
-	unsigned int *count, unsigned int *size)
+static int queue_setup(struct vb2_queue *vq,
+		       unsigned int *nbuffers, unsigned int *nplanes,
+		       unsigned int sizes[], struct device *alloc_devs[])
 {
-	struct cx231xx_fh *fh = q->priv_data;
+	struct cx231xx *dev = vb2_get_drv_priv(vq);
+	unsigned int size = mpeglinesize * mpeglines;
 
-	fh->dev->ts1.ts_packet_size  = mpeglinesize;
-	fh->dev->ts1.ts_packet_count = mpeglines;
+	dev->ts1.ts_packet_size  = mpeglinesize;
+	dev->ts1.ts_packet_count = mpeglines;
 
-	*size = fh->dev->ts1.ts_packet_size * fh->dev->ts1.ts_packet_count;
-	*count = mpegbufs;
+	if (vq->num_buffers + *nbuffers < CX231XX_MIN_BUF)
+		*nbuffers = CX231XX_MIN_BUF - vq->num_buffers;
 
-	return 0;
-}
-
-static void free_buffer(struct videobuf_queue *vq, struct cx231xx_buffer *buf)
-{
-	struct cx231xx_fh *fh = vq->priv_data;
-	struct cx231xx *dev = fh->dev;
-	unsigned long flags = 0;
+	if (*nplanes)
+		return sizes[0] < size ? -EINVAL : 0;
+	*nplanes = 1;
+	sizes[0] = mpeglinesize * mpeglines;
 
-	BUG_ON(in_interrupt());
-
-	spin_lock_irqsave(&dev->video_mode.slock, flags);
-	if (dev->USE_ISO) {
-		if (dev->video_mode.isoc_ctl.buf == buf)
-			dev->video_mode.isoc_ctl.buf = NULL;
-	} else {
-		if (dev->video_mode.bulk_ctl.buf == buf)
-			dev->video_mode.bulk_ctl.buf = NULL;
-	}
-	spin_unlock_irqrestore(&dev->video_mode.slock, flags);
-	videobuf_waiton(vq, &buf->vb, 0, 0);
-	videobuf_vmalloc_free(&buf->vb);
-	buf->vb.state = VIDEOBUF_NEEDS_INIT;
+	return 0;
 }
 
 static void buffer_copy(struct cx231xx *dev, char *data, int len, struct urb *urb,
@@ -1276,13 +1247,13 @@ static void buffer_copy(struct cx231xx *dev, char *data, int len, struct urb *ur
 			return;
 
 		buf = list_entry(dma_q->active.next,
-				struct cx231xx_buffer, vb.queue);
+				struct cx231xx_buffer, list);
 		dev->video_mode.isoc_ctl.buf = buf;
 		dma_q->mpeg_buffer_done = 1;
 	}
 	/* Fill buffer */
 	buf = dev->video_mode.isoc_ctl.buf;
-	vbuf = videobuf_to_vmalloc(&buf->vb);
+	vbuf = vb2_plane_vaddr(&buf->vb.vb2_buf, 0);
 
 	if ((dma_q->mpeg_buffer_completed+len) <
 			mpeglines*mpeglinesize) {
@@ -1306,11 +1277,10 @@ static void buffer_copy(struct cx231xx *dev, char *data, int len, struct urb *ur
 		memcpy(vbuf+dma_q->mpeg_buffer_completed,
 				data, tail_data);
 
-		buf->vb.state = VIDEOBUF_DONE;
-		buf->vb.field_count++;
-		buf->vb.ts = ktime_get_ns();
-		list_del(&buf->vb.queue);
-		wake_up(&buf->vb.done);
+		buf->vb.vb2_buf.timestamp = ktime_get_ns();
+		buf->vb.sequence = dma_q->sequence++;
+		list_del(&buf->list);
+		vb2_buffer_done(&buf->vb.vb2_buf, VB2_BUF_STATE_DONE);
 		dma_q->mpeg_buffer_completed = 0;
 
 		if (len - tail_data > 0) {
@@ -1331,17 +1301,15 @@ static void buffer_filled(char *data, int len, struct urb *urb,
 	if (list_empty(&dma_q->active))
 		return;
 
-	buf = list_entry(dma_q->active.next,
-			struct cx231xx_buffer, vb.queue);
+	buf = list_entry(dma_q->active.next, struct cx231xx_buffer, list);
 
 	/* Fill buffer */
-	vbuf = videobuf_to_vmalloc(&buf->vb);
+	vbuf = vb2_plane_vaddr(&buf->vb.vb2_buf, 0);
 	memcpy(vbuf, data, len);
-	buf->vb.state = VIDEOBUF_DONE;
-	buf->vb.field_count++;
-	buf->vb.ts = ktime_get_ns();
-	list_del(&buf->vb.queue);
-	wake_up(&buf->vb.done);
+	buf->vb.sequence = dma_q->sequence++;
+	buf->vb.vb2_buf.timestamp = ktime_get_ns();
+	list_del(&buf->list);
+	vb2_buffer_done(&buf->vb.vb2_buf, VB2_BUF_STATE_DONE);
 }
 
 static int cx231xx_isoc_copy(struct cx231xx *dev, struct urb *urb)
@@ -1394,100 +1362,104 @@ static int cx231xx_bulk_copy(struct cx231xx *dev, struct urb *urb)
 	return 0;
 }
 
-static int bb_buf_prepare(struct videobuf_queue *q,
-	struct videobuf_buffer *vb, enum v4l2_field field)
+static void buffer_queue(struct vb2_buffer *vb)
 {
-	struct cx231xx_fh *fh = q->priv_data;
 	struct cx231xx_buffer *buf =
-	    container_of(vb, struct cx231xx_buffer, vb);
-	struct cx231xx *dev = fh->dev;
-	int rc = 0, urb_init = 0;
-	int size = fh->dev->ts1.ts_packet_size * fh->dev->ts1.ts_packet_count;
+	    container_of(vb, struct cx231xx_buffer, vb.vb2_buf);
+	struct cx231xx *dev = vb2_get_drv_priv(vb->vb2_queue);
+	struct cx231xx_dmaqueue *vidq = &dev->video_mode.vidq;
+	unsigned long flags;
 
-	if (0 != buf->vb.baddr  &&  buf->vb.bsize < size)
-		return -EINVAL;
-	buf->vb.width = fh->dev->ts1.ts_packet_size;
-	buf->vb.height = fh->dev->ts1.ts_packet_count;
-	buf->vb.size = size;
-	buf->vb.field = field;
-
-	if (VIDEOBUF_NEEDS_INIT == buf->vb.state) {
-		rc = videobuf_iolock(q, &buf->vb, NULL);
-		if (rc < 0)
-			goto fail;
-	}
+	spin_lock_irqsave(&dev->video_mode.slock, flags);
+	list_add_tail(&buf->list, &vidq->active);
+	spin_unlock_irqrestore(&dev->video_mode.slock, flags);
+}
 
-	if (dev->USE_ISO) {
-		if (!dev->video_mode.isoc_ctl.num_bufs)
-			urb_init = 1;
-	} else {
-		if (!dev->video_mode.bulk_ctl.num_bufs)
-			urb_init = 1;
+static void return_all_buffers(struct cx231xx *dev,
+			       enum vb2_buffer_state state)
+{
+	struct cx231xx_dmaqueue *vidq = &dev->video_mode.vidq;
+	struct cx231xx_buffer *buf, *node;
+	unsigned long flags;
+
+	spin_lock_irqsave(&dev->video_mode.slock, flags);
+	list_for_each_entry_safe(buf, node, &vidq->active, list) {
+		vb2_buffer_done(&buf->vb.vb2_buf, state);
+		list_del(&buf->list);
 	}
-	dev_dbg(dev->dev,
-		"urb_init=%d dev->video_mode.max_pkt_size=%d\n",
-		urb_init, dev->video_mode.max_pkt_size);
+	spin_unlock_irqrestore(&dev->video_mode.slock, flags);
+}
+
+static int start_streaming(struct vb2_queue *vq, unsigned int count)
+{
+	struct cx231xx *dev = vb2_get_drv_priv(vq);
+	struct cx231xx_dmaqueue *vidq = &dev->video_mode.vidq;
+	int ret = 0;
+
+	vidq->sequence = 0;
 	dev->mode_tv = 1;
 
-	if (urb_init) {
-		rc = cx231xx_set_mode(dev, CX231XX_DIGITAL_MODE);
-		rc = cx231xx_unmute_audio(dev);
-		if (dev->USE_ISO) {
-			cx231xx_set_alt_setting(dev, INDEX_TS1, 4);
-			rc = cx231xx_init_isoc(dev, mpeglines,
-				       mpegbufs,
-				       dev->ts1_mode.max_pkt_size,
-				       cx231xx_isoc_copy);
-		} else {
-			cx231xx_set_alt_setting(dev, INDEX_TS1, 0);
-			rc = cx231xx_init_bulk(dev, mpeglines,
-				       mpegbufs,
-				       dev->ts1_mode.max_pkt_size,
-				       cx231xx_bulk_copy);
-		}
-		if (rc < 0)
-			goto fail;
-	}
+	cx231xx_set_alt_setting(dev, INDEX_VANC, 1);
+	cx231xx_set_gpio_value(dev, 2, 0);
 
-	buf->vb.state = VIDEOBUF_PREPARED;
-	return 0;
+	cx231xx_initialize_codec(dev);
+
+	cx231xx_start_TS1(dev);
+
+	cx231xx_set_alt_setting(dev, INDEX_TS1, 0);
+	cx231xx_set_mode(dev, CX231XX_DIGITAL_MODE);
+	if (dev->USE_ISO)
+		ret = cx231xx_init_isoc(dev, CX231XX_NUM_PACKETS,
+					CX231XX_NUM_BUFS,
+					dev->ts1_mode.max_pkt_size,
+					cx231xx_isoc_copy);
+	else
+		ret = cx231xx_init_bulk(dev, 320, 5,
+					dev->ts1_mode.max_pkt_size,
+					cx231xx_bulk_copy);
+	if (ret)
+		return_all_buffers(dev, VB2_BUF_STATE_QUEUED);
 
-fail:
-	free_buffer(q, buf);
-	return rc;
+	call_all(dev, video, s_stream, 1);
+	return ret;
 }
 
-static void bb_buf_queue(struct videobuf_queue *q,
-	struct videobuf_buffer *vb)
+static void stop_streaming(struct vb2_queue *vq)
 {
-	struct cx231xx_fh *fh = q->priv_data;
+	struct cx231xx *dev = vb2_get_drv_priv(vq);
+	unsigned long flags;
 
-	struct cx231xx_buffer *buf =
-	    container_of(vb, struct cx231xx_buffer, vb);
-	struct cx231xx *dev = fh->dev;
-	struct cx231xx_dmaqueue *vidq = &dev->video_mode.vidq;
+	call_all(dev, video, s_stream, 0);
 
-	buf->vb.state = VIDEOBUF_QUEUED;
-	list_add_tail(&buf->vb.queue, &vidq->active);
+	cx231xx_stop_TS1(dev);
 
-}
+	/* do this before setting alternate! */
+	if (dev->USE_ISO)
+		cx231xx_uninit_isoc(dev);
+	else
+		cx231xx_uninit_bulk(dev);
+	cx231xx_set_mode(dev, CX231XX_SUSPEND);
 
-static void bb_buf_release(struct videobuf_queue *q,
-	struct videobuf_buffer *vb)
-{
-	struct cx231xx_buffer *buf =
-	    container_of(vb, struct cx231xx_buffer, vb);
-	/*struct cx231xx_fh *fh = q->priv_data;*/
-	/*struct cx231xx *dev = (struct cx231xx *)fh->dev;*/
+	cx231xx_api_cmd(dev, CX2341X_ENC_STOP_CAPTURE, 3, 0,
+			CX231xx_END_NOW, CX231xx_MPEG_CAPTURE,
+			CX231xx_RAW_BITS_NONE);
 
-	free_buffer(q, buf);
+	spin_lock_irqsave(&dev->video_mode.slock, flags);
+	if (dev->USE_ISO)
+		dev->video_mode.isoc_ctl.buf = NULL;
+	else
+		dev->video_mode.bulk_ctl.buf = NULL;
+	spin_unlock_irqrestore(&dev->video_mode.slock, flags);
+	return_all_buffers(dev, VB2_BUF_STATE_ERROR);
 }
 
-static const struct videobuf_queue_ops cx231xx_qops = {
-	.buf_setup    = bb_buf_setup,
-	.buf_prepare  = bb_buf_prepare,
-	.buf_queue    = bb_buf_queue,
-	.buf_release  = bb_buf_release,
+static struct vb2_ops cx231xx_video_qops = {
+	.queue_setup		= queue_setup,
+	.buf_queue		= buffer_queue,
+	.start_streaming	= start_streaming,
+	.stop_streaming		= stop_streaming,
+	.wait_prepare		= vb2_ops_wait_prepare,
+	.wait_finish		= vb2_ops_wait_finish,
 };
 
 /* ------------------------------------------------------------------ */
@@ -1495,8 +1467,7 @@ static const struct videobuf_queue_ops cx231xx_qops = {
 static int vidioc_g_pixelaspect(struct file *file, void *priv,
 				int type, struct v4l2_fract *f)
 {
-	struct cx231xx_fh *fh = priv;
-	struct cx231xx *dev = fh->dev;
+	struct cx231xx *dev = video_drvdata(file);
 	bool is_50hz = dev->encodernorm.id & V4L2_STD_625_50;
 
 	if (type != V4L2_BUF_TYPE_VIDEO_CAPTURE)
@@ -1511,8 +1482,7 @@ static int vidioc_g_pixelaspect(struct file *file, void *priv,
 static int vidioc_g_selection(struct file *file, void *priv,
 			      struct v4l2_selection *s)
 {
-	struct cx231xx_fh *fh = priv;
-	struct cx231xx *dev = fh->dev;
+	struct cx231xx *dev = video_drvdata(file);
 
 	if (s->type != V4L2_BUF_TYPE_VIDEO_CAPTURE)
 		return -EINVAL;
@@ -1533,8 +1503,7 @@ static int vidioc_g_selection(struct file *file, void *priv,
 
 static int vidioc_g_std(struct file *file, void *fh0, v4l2_std_id *norm)
 {
-	struct cx231xx_fh  *fh  = file->private_data;
-	struct cx231xx *dev = fh->dev;
+	struct cx231xx *dev = video_drvdata(file);
 
 	*norm = dev->encodernorm.id;
 	return 0;
@@ -1542,8 +1511,7 @@ static int vidioc_g_std(struct file *file, void *fh0, v4l2_std_id *norm)
 
 static int vidioc_s_std(struct file *file, void *priv, v4l2_std_id id)
 {
-	struct cx231xx_fh  *fh  = file->private_data;
-	struct cx231xx *dev = fh->dev;
+	struct cx231xx *dev = video_drvdata(file);
 	unsigned int i;
 
 	for (i = 0; i < ARRAY_SIZE(cx231xx_tvnorms); i++)
@@ -1575,8 +1543,7 @@ static int vidioc_s_std(struct file *file, void *priv, v4l2_std_id id)
 static int vidioc_s_ctrl(struct file *file, void *priv,
 				struct v4l2_control *ctl)
 {
-	struct cx231xx_fh  *fh  = file->private_data;
-	struct cx231xx *dev = fh->dev;
+	struct cx231xx *dev = video_drvdata(file);
 	struct v4l2_subdev *sd;
 
 	dprintk(3, "enter vidioc_s_ctrl()\n");
@@ -1601,8 +1568,7 @@ static int vidioc_enum_fmt_vid_cap(struct file *file, void  *priv,
 static int vidioc_g_fmt_vid_cap(struct file *file, void *priv,
 				struct v4l2_format *f)
 {
-	struct cx231xx_fh  *fh  = file->private_data;
-	struct cx231xx *dev = fh->dev;
+	struct cx231xx *dev = video_drvdata(file);
 
 	dprintk(3, "enter vidioc_g_fmt_vid_cap()\n");
 	f->fmt.pix.pixelformat = V4L2_PIX_FMT_MPEG;
@@ -1621,8 +1587,7 @@ static int vidioc_g_fmt_vid_cap(struct file *file, void *priv,
 static int vidioc_try_fmt_vid_cap(struct file *file, void *priv,
 				struct v4l2_format *f)
 {
-	struct cx231xx_fh  *fh  = file->private_data;
-	struct cx231xx *dev = fh->dev;
+	struct cx231xx *dev = video_drvdata(file);
 
 	dprintk(3, "enter vidioc_try_fmt_vid_cap()\n");
 	f->fmt.pix.pixelformat = V4L2_PIX_FMT_MPEG;
@@ -1636,230 +1601,21 @@ static int vidioc_try_fmt_vid_cap(struct file *file, void *priv,
 	return 0;
 }
 
-static int vidioc_reqbufs(struct file *file, void *priv,
-				struct v4l2_requestbuffers *p)
-{
-	struct cx231xx_fh  *fh  = file->private_data;
-
-	return videobuf_reqbufs(&fh->vidq, p);
-}
-
-static int vidioc_querybuf(struct file *file, void *priv,
-				struct v4l2_buffer *p)
-{
-	struct cx231xx_fh  *fh  = file->private_data;
-
-	return videobuf_querybuf(&fh->vidq, p);
-}
-
-static int vidioc_qbuf(struct file *file, void *priv,
-				struct v4l2_buffer *p)
-{
-	struct cx231xx_fh  *fh  = file->private_data;
-
-	return videobuf_qbuf(&fh->vidq, p);
-}
-
-static int vidioc_dqbuf(struct file *file, void *priv, struct v4l2_buffer *b)
-{
-	struct cx231xx_fh  *fh  = priv;
-
-	return videobuf_dqbuf(&fh->vidq, b, file->f_flags & O_NONBLOCK);
-}
-
-
-static int vidioc_streamon(struct file *file, void *priv,
-				enum v4l2_buf_type i)
-{
-	struct cx231xx_fh  *fh  = file->private_data;
-	struct cx231xx *dev = fh->dev;
-
-	dprintk(3, "enter vidioc_streamon()\n");
-	cx231xx_set_alt_setting(dev, INDEX_TS1, 0);
-	cx231xx_set_mode(dev, CX231XX_DIGITAL_MODE);
-	if (dev->USE_ISO)
-		cx231xx_init_isoc(dev, CX231XX_NUM_PACKETS,
-				CX231XX_NUM_BUFS,
-				dev->video_mode.max_pkt_size,
-				cx231xx_isoc_copy);
-	else {
-		cx231xx_init_bulk(dev, 320,
-				5,
-				dev->ts1_mode.max_pkt_size,
-				cx231xx_bulk_copy);
-	}
-	dprintk(3, "exit vidioc_streamon()\n");
-	return videobuf_streamon(&fh->vidq);
-}
-
-static int vidioc_streamoff(struct file *file, void *priv, enum v4l2_buf_type i)
-{
-	struct cx231xx_fh  *fh  = file->private_data;
-
-	return videobuf_streamoff(&fh->vidq);
-}
-
 static int vidioc_log_status(struct file *file, void *priv)
 {
-	struct cx231xx_fh  *fh  = priv;
-	struct cx231xx *dev = fh->dev;
+	struct cx231xx *dev = video_drvdata(file);
 
 	call_all(dev, core, log_status);
 	return v4l2_ctrl_log_status(file, priv);
 }
 
-static int mpeg_open(struct file *file)
-{
-	struct video_device *vdev = video_devdata(file);
-	struct cx231xx *dev = video_drvdata(file);
-	struct cx231xx_fh *fh;
-
-	dprintk(2, "%s()\n", __func__);
-
-	if (mutex_lock_interruptible(&dev->lock))
-		return -ERESTARTSYS;
-
-	/* allocate + initialize per filehandle data */
-	fh = kzalloc(sizeof(*fh), GFP_KERNEL);
-	if (NULL == fh) {
-		mutex_unlock(&dev->lock);
-		return -ENOMEM;
-	}
-
-	file->private_data = fh;
-	v4l2_fh_init(&fh->fh, vdev);
-	fh->dev = dev;
-
-
-	videobuf_queue_vmalloc_init(&fh->vidq, &cx231xx_qops,
-			    NULL, &dev->video_mode.slock,
-			    V4L2_BUF_TYPE_VIDEO_CAPTURE, V4L2_FIELD_INTERLACED,
-			    sizeof(struct cx231xx_buffer), fh, &dev->lock);
-/*
-	videobuf_queue_sg_init(&fh->vidq, &cx231xx_qops,
-			    dev->dev, &dev->ts1.slock,
-			    V4L2_BUF_TYPE_VIDEO_CAPTURE,
-			    V4L2_FIELD_INTERLACED,
-			    sizeof(struct cx231xx_buffer),
-			    fh, &dev->lock);
-*/
-
-	cx231xx_set_alt_setting(dev, INDEX_VANC, 1);
-	cx231xx_set_gpio_value(dev, 2, 0);
-
-	cx231xx_initialize_codec(dev);
-
-	mutex_unlock(&dev->lock);
-	v4l2_fh_add(&fh->fh);
-	cx231xx_start_TS1(dev);
-
-	return 0;
-}
-
-static int mpeg_release(struct file *file)
-{
-	struct cx231xx_fh  *fh  = file->private_data;
-	struct cx231xx *dev = fh->dev;
-
-	dprintk(3, "mpeg_release()! dev=0x%p\n", dev);
-
-	mutex_lock(&dev->lock);
-
-	cx231xx_stop_TS1(dev);
-
-	/* do this before setting alternate! */
-	if (dev->USE_ISO)
-		cx231xx_uninit_isoc(dev);
-	else
-		cx231xx_uninit_bulk(dev);
-	cx231xx_set_mode(dev, CX231XX_SUSPEND);
-
-	cx231xx_api_cmd(fh->dev, CX2341X_ENC_STOP_CAPTURE, 3, 0,
-			CX231xx_END_NOW, CX231xx_MPEG_CAPTURE,
-			CX231xx_RAW_BITS_NONE);
-
-	/* FIXME: Review this crap */
-	/* Shut device down on last close */
-	if (atomic_cmpxchg(&fh->v4l_reading, 1, 0) == 1) {
-		if (atomic_dec_return(&dev->v4l_reader_count) == 0) {
-			/* stop mpeg capture */
-
-			msleep(500);
-			cx231xx_417_check_encoder(dev);
-
-		}
-	}
-
-	if (fh->vidq.streaming)
-		videobuf_streamoff(&fh->vidq);
-	if (fh->vidq.reading)
-		videobuf_read_stop(&fh->vidq);
-
-	videobuf_mmap_free(&fh->vidq);
-	v4l2_fh_del(&fh->fh);
-	v4l2_fh_exit(&fh->fh);
-	kfree(fh);
-	mutex_unlock(&dev->lock);
-	return 0;
-}
-
-static ssize_t mpeg_read(struct file *file, char __user *data,
-	size_t count, loff_t *ppos)
-{
-	struct cx231xx_fh *fh = file->private_data;
-	struct cx231xx *dev = fh->dev;
-
-	/* Deal w/ A/V decoder * and mpeg encoder sync issues. */
-	/* Start mpeg encoder on first read. */
-	if (atomic_cmpxchg(&fh->v4l_reading, 0, 1) == 0) {
-		if (atomic_inc_return(&dev->v4l_reader_count) == 1) {
-			if (cx231xx_initialize_codec(dev) < 0)
-				return -EINVAL;
-		}
-	}
-
-	return videobuf_read_stream(&fh->vidq, data, count, ppos, 0,
-				    file->f_flags & O_NONBLOCK);
-}
-
-static __poll_t mpeg_poll(struct file *file,
-	struct poll_table_struct *wait)
-{
-	__poll_t req_events = poll_requested_events(wait);
-	struct cx231xx_fh *fh = file->private_data;
-	struct cx231xx *dev = fh->dev;
-	__poll_t res = 0;
-
-	if (v4l2_event_pending(&fh->fh))
-		res |= EPOLLPRI;
-	else
-		poll_wait(file, &fh->fh.wait, wait);
-
-	if (!(req_events & (EPOLLIN | EPOLLRDNORM)))
-		return res;
-
-	mutex_lock(&dev->lock);
-	res |= videobuf_poll_stream(file, &fh->vidq, wait);
-	mutex_unlock(&dev->lock);
-	return res;
-}
-
-static int mpeg_mmap(struct file *file, struct vm_area_struct *vma)
-{
-	struct cx231xx_fh *fh = file->private_data;
-
-	dprintk(2, "%s()\n", __func__);
-
-	return videobuf_mmap_mapper(&fh->vidq, vma);
-}
-
 static const struct v4l2_file_operations mpeg_fops = {
 	.owner	       = THIS_MODULE,
-	.open	       = mpeg_open,
-	.release       = mpeg_release,
-	.read	       = mpeg_read,
-	.poll          = mpeg_poll,
-	.mmap	       = mpeg_mmap,
+	.open	       = v4l2_fh_open,
+	.release       = vb2_fop_release,
+	.read	       = vb2_fop_read,
+	.poll          = vb2_fop_poll,
+	.mmap	       = vb2_fop_mmap,
 	.unlocked_ioctl = video_ioctl2,
 };
 
@@ -1881,12 +1637,12 @@ static const struct v4l2_ioctl_ops mpeg_ioctl_ops = {
 	.vidioc_g_fmt_vid_cap	 = vidioc_g_fmt_vid_cap,
 	.vidioc_try_fmt_vid_cap	 = vidioc_try_fmt_vid_cap,
 	.vidioc_s_fmt_vid_cap	 = vidioc_try_fmt_vid_cap,
-	.vidioc_reqbufs		 = vidioc_reqbufs,
-	.vidioc_querybuf	 = vidioc_querybuf,
-	.vidioc_qbuf		 = vidioc_qbuf,
-	.vidioc_dqbuf		 = vidioc_dqbuf,
-	.vidioc_streamon	 = vidioc_streamon,
-	.vidioc_streamoff	 = vidioc_streamoff,
+	.vidioc_reqbufs		 = vb2_ioctl_reqbufs,
+	.vidioc_querybuf	 = vb2_ioctl_querybuf,
+	.vidioc_qbuf		 = vb2_ioctl_qbuf,
+	.vidioc_dqbuf		 = vb2_ioctl_dqbuf,
+	.vidioc_streamon	 = vb2_ioctl_streamon,
+	.vidioc_streamoff	 = vb2_ioctl_streamoff,
 	.vidioc_log_status	 = vidioc_log_status,
 #ifdef CONFIG_VIDEO_ADV_DEBUG
 	.vidioc_g_register	 = cx231xx_g_register,
@@ -1980,6 +1736,7 @@ int cx231xx_417_register(struct cx231xx *dev)
 	/* FIXME: Port1 hardcoded here */
 	int err = -ENODEV;
 	struct cx231xx_tsport *tsport = &dev->ts1;
+	struct vb2_queue *q;
 
 	dprintk(1, "%s()\n", __func__);
 
@@ -2017,6 +1774,21 @@ int cx231xx_417_register(struct cx231xx *dev)
 	/* Allocate and initialize V4L video device */
 	cx231xx_video_dev_init(dev, dev->udev,
 			&dev->v4l_device, &cx231xx_mpeg_template, "mpeg");
+	q = &dev->mpegq;
+	q->type = V4L2_BUF_TYPE_VIDEO_CAPTURE;
+	q->io_modes = VB2_USERPTR | VB2_MMAP | VB2_DMABUF | VB2_READ;
+	q->drv_priv = dev;
+	q->buf_struct_size = sizeof(struct cx231xx_buffer);
+	q->ops = &cx231xx_video_qops;
+	q->mem_ops = &vb2_vmalloc_memops;
+	q->timestamp_flags = V4L2_BUF_FLAG_TIMESTAMP_MONOTONIC;
+	q->min_buffers_needed = 1;
+	q->lock = &dev->lock;
+	err = vb2_queue_init(q);
+	if (err)
+		return err;
+	dev->v4l_device.queue = q;
+
 	err = video_register_device(&dev->v4l_device,
 		VFL_TYPE_GRABBER, -1);
 	if (err < 0) {
diff --git a/drivers/media/usb/cx231xx/cx231xx-audio.c b/drivers/media/usb/cx231xx/cx231xx-audio.c
index 9ef362e221df..fd6e2df3d1b7 100644
--- a/drivers/media/usb/cx231xx/cx231xx-audio.c
+++ b/drivers/media/usb/cx231xx/cx231xx-audio.c
@@ -14,7 +14,6 @@
 #include <linux/soundcard.h>
 #include <linux/slab.h>
 #include <linux/vmalloc.h>
-#include <linux/proc_fs.h>
 #include <linux/module.h>
 #include <sound/core.h>
 #include <sound/pcm.h>
diff --git a/drivers/media/usb/cx231xx/cx231xx-avcore.c b/drivers/media/usb/cx231xx/cx231xx-avcore.c
index d417b5fe4093..0974965e848f 100644
--- a/drivers/media/usb/cx231xx/cx231xx-avcore.c
+++ b/drivers/media/usb/cx231xx/cx231xx-avcore.c
@@ -1240,7 +1240,7 @@ int cx231xx_init_ctrl_pin_status(struct cx231xx *dev)
 int cx231xx_set_agc_analog_digital_mux_select(struct cx231xx *dev,
 					      u8 analog_or_digital)
 {
-	int status = 0;
+	int status;
 
 	/* first set the direction to output */
 	status = cx231xx_set_gpio_direction(dev,
diff --git a/drivers/media/usb/cx231xx/cx231xx-cards.c b/drivers/media/usb/cx231xx/cx231xx-cards.c
index e123e74c549e..92efe6c1f47b 100644
--- a/drivers/media/usb/cx231xx/cx231xx-cards.c
+++ b/drivers/media/usb/cx231xx/cx231xx-cards.c
@@ -1479,13 +1479,11 @@ static int cx231xx_init_dev(struct cx231xx *dev, struct usb_device *udev,
 		goto err_dev_init;
 	}
 
-	/* init video dma queues */
+	/* init video dma queue */
 	INIT_LIST_HEAD(&dev->video_mode.vidq.active);
-	INIT_LIST_HEAD(&dev->video_mode.vidq.queued);
 
-	/* init vbi dma queues */
+	/* init vbi dma queue */
 	INIT_LIST_HEAD(&dev->vbi_mode.vidq.active);
-	INIT_LIST_HEAD(&dev->vbi_mode.vidq.queued);
 
 	/* Reset other chips required if they are tied up with GPIO pins */
 	cx231xx_add_into_devlist(dev);
diff --git a/drivers/media/usb/cx231xx/cx231xx-vbi.c b/drivers/media/usb/cx231xx/cx231xx-vbi.c
index fba7ccdf5a25..d2f143a096d1 100644
--- a/drivers/media/usb/cx231xx/cx231xx-vbi.c
+++ b/drivers/media/usb/cx231xx/cx231xx-vbi.c
@@ -153,131 +153,98 @@ static inline int cx231xx_isoc_vbi_copy(struct cx231xx *dev, struct urb *urb)
 	Vbi buf operations
    ------------------------------------------------------------------*/
 
-static int
-vbi_buffer_setup(struct videobuf_queue *vq, unsigned int *count,
-		 unsigned int *size)
+static int vbi_queue_setup(struct vb2_queue *vq,
+			   unsigned int *nbuffers, unsigned int *nplanes,
+			   unsigned int sizes[], struct device *alloc_devs[])
 {
-	struct cx231xx_fh *fh = vq->priv_data;
-	struct cx231xx *dev = fh->dev;
+	struct cx231xx *dev = vb2_get_drv_priv(vq);
 	u32 height = 0;
 
 	height = ((dev->norm & V4L2_STD_625_50) ?
 		  PAL_VBI_LINES : NTSC_VBI_LINES);
 
-	*size = (dev->width * height * 2 * 2);
-	if (0 == *count)
-		*count = CX231XX_DEF_VBI_BUF;
-
-	if (*count < CX231XX_MIN_BUF)
-		*count = CX231XX_MIN_BUF;
-
+	*nplanes = 1;
+	sizes[0] = (dev->width * height * 2 * 2);
 	return 0;
 }
 
 /* This is called *without* dev->slock held; please keep it that way */
-static void free_buffer(struct videobuf_queue *vq, struct cx231xx_buffer *buf)
-{
-	struct cx231xx_fh *fh = vq->priv_data;
-	struct cx231xx *dev = fh->dev;
-	unsigned long flags = 0;
-	BUG_ON(in_interrupt());
-
-	/* We used to wait for the buffer to finish here, but this didn't work
-	   because, as we were keeping the state as VIDEOBUF_QUEUED,
-	   videobuf_queue_cancel marked it as finished for us.
-	   (Also, it could wedge forever if the hardware was misconfigured.)
-
-	   This should be safe; by the time we get here, the buffer isn't
-	   queued anymore. If we ever start marking the buffers as
-	   VIDEOBUF_ACTIVE, it won't be, though.
-	 */
-	spin_lock_irqsave(&dev->vbi_mode.slock, flags);
-	if (dev->vbi_mode.bulk_ctl.buf == buf)
-		dev->vbi_mode.bulk_ctl.buf = NULL;
-	spin_unlock_irqrestore(&dev->vbi_mode.slock, flags);
-
-	videobuf_vmalloc_free(&buf->vb);
-	buf->vb.state = VIDEOBUF_NEEDS_INIT;
-}
-
-static int
-vbi_buffer_prepare(struct videobuf_queue *vq, struct videobuf_buffer *vb,
-		   enum v4l2_field field)
+static int vbi_buf_prepare(struct vb2_buffer *vb)
 {
-	struct cx231xx_fh *fh = vq->priv_data;
-	struct cx231xx_buffer *buf =
-	    container_of(vb, struct cx231xx_buffer, vb);
-	struct cx231xx *dev = fh->dev;
-	int rc = 0, urb_init = 0;
+	struct cx231xx *dev = vb2_get_drv_priv(vb->vb2_queue);
 	u32 height = 0;
+	u32 size;
 
 	height = ((dev->norm & V4L2_STD_625_50) ?
 		  PAL_VBI_LINES : NTSC_VBI_LINES);
-	buf->vb.size = ((dev->width << 1) * height * 2);
+	size = ((dev->width << 1) * height * 2);
 
-	if (0 != buf->vb.baddr && buf->vb.bsize < buf->vb.size)
+	if (vb2_plane_size(vb, 0) < size)
 		return -EINVAL;
-
-	buf->vb.width = dev->width;
-	buf->vb.height = height;
-	buf->vb.field = field;
-	buf->vb.field = V4L2_FIELD_SEQ_TB;
-
-	if (VIDEOBUF_NEEDS_INIT == buf->vb.state) {
-		rc = videobuf_iolock(vq, &buf->vb, NULL);
-		if (rc < 0)
-			goto fail;
-	}
-
-	if (!dev->vbi_mode.bulk_ctl.num_bufs)
-		urb_init = 1;
-
-	if (urb_init) {
-		rc = cx231xx_init_vbi_isoc(dev, CX231XX_NUM_VBI_PACKETS,
-					   CX231XX_NUM_VBI_BUFS,
-					   dev->vbi_mode.alt_max_pkt_size[0],
-					   cx231xx_isoc_vbi_copy);
-		if (rc < 0)
-			goto fail;
-	}
-
-	buf->vb.state = VIDEOBUF_PREPARED;
+	vb2_set_plane_payload(vb, 0, size);
 	return 0;
-
-fail:
-	free_buffer(vq, buf);
-	return rc;
 }
 
-static void
-vbi_buffer_queue(struct videobuf_queue *vq, struct videobuf_buffer *vb)
+static void vbi_buf_queue(struct vb2_buffer *vb)
 {
+	struct cx231xx *dev = vb2_get_drv_priv(vb->vb2_queue);
 	struct cx231xx_buffer *buf =
-	    container_of(vb, struct cx231xx_buffer, vb);
-	struct cx231xx_fh *fh = vq->priv_data;
-	struct cx231xx *dev = fh->dev;
+	    container_of(vb, struct cx231xx_buffer, vb.vb2_buf);
 	struct cx231xx_dmaqueue *vidq = &dev->vbi_mode.vidq;
+	unsigned long flags;
 
-	buf->vb.state = VIDEOBUF_QUEUED;
-	list_add_tail(&buf->vb.queue, &vidq->active);
+	spin_lock_irqsave(&dev->vbi_mode.slock, flags);
+	list_add_tail(&buf->list, &vidq->active);
+	spin_unlock_irqrestore(&dev->vbi_mode.slock, flags);
+}
+
+static void return_all_buffers(struct cx231xx *dev,
+			       enum vb2_buffer_state state)
+{
+	struct cx231xx_dmaqueue *vidq = &dev->vbi_mode.vidq;
+	struct cx231xx_buffer *buf, *node;
+	unsigned long flags;
 
+	spin_lock_irqsave(&dev->vbi_mode.slock, flags);
+	dev->vbi_mode.bulk_ctl.buf = NULL;
+	list_for_each_entry_safe(buf, node, &vidq->active, list) {
+		list_del(&buf->list);
+		vb2_buffer_done(&buf->vb.vb2_buf, state);
+	}
+	spin_unlock_irqrestore(&dev->vbi_mode.slock, flags);
 }
 
-static void vbi_buffer_release(struct videobuf_queue *vq,
-			       struct videobuf_buffer *vb)
+static int vbi_start_streaming(struct vb2_queue *vq, unsigned int count)
 {
-	struct cx231xx_buffer *buf =
-	    container_of(vb, struct cx231xx_buffer, vb);
+	struct cx231xx *dev = vb2_get_drv_priv(vq);
+	struct cx231xx_dmaqueue *vidq = &dev->vbi_mode.vidq;
+	int ret;
+
+	vidq->sequence = 0;
+	ret = cx231xx_init_vbi_isoc(dev, CX231XX_NUM_VBI_PACKETS,
+				    CX231XX_NUM_VBI_BUFS,
+				    dev->vbi_mode.alt_max_pkt_size[0],
+				    cx231xx_isoc_vbi_copy);
+	if (ret)
+		return_all_buffers(dev, VB2_BUF_STATE_QUEUED);
+	return ret;
+}
 
+static void vbi_stop_streaming(struct vb2_queue *vq)
+{
+	struct cx231xx *dev = vb2_get_drv_priv(vq);
 
-	free_buffer(vq, buf);
+	return_all_buffers(dev, VB2_BUF_STATE_ERROR);
 }
 
-const struct videobuf_queue_ops cx231xx_vbi_qops = {
-	.buf_setup   = vbi_buffer_setup,
-	.buf_prepare = vbi_buffer_prepare,
-	.buf_queue   = vbi_buffer_queue,
-	.buf_release = vbi_buffer_release,
+struct vb2_ops cx231xx_vbi_qops = {
+	.queue_setup = vbi_queue_setup,
+	.buf_prepare = vbi_buf_prepare,
+	.buf_queue = vbi_buf_queue,
+	.start_streaming = vbi_start_streaming,
+	.stop_streaming = vbi_stop_streaming,
+	.wait_prepare = vb2_ops_wait_prepare,
+	.wait_finish = vb2_ops_wait_finish,
 };
 
 /* ------------------------------------------------------------------
@@ -512,16 +479,15 @@ static inline void vbi_buffer_filled(struct cx231xx *dev,
 				     struct cx231xx_buffer *buf)
 {
 	/* Advice that buffer was filled */
-	/* dev_dbg(dev->dev, "[%p/%d] wakeup\n", buf, buf->vb.i); */
+	/* dev_dbg(dev->dev, "[%p/%d] wakeup\n", buf, buf->vb.index); */
 
-	buf->vb.state = VIDEOBUF_DONE;
-	buf->vb.field_count++;
-	buf->vb.ts = ktime_get_ns();
+	buf->vb.sequence = dma_q->sequence++;
+	buf->vb.vb2_buf.timestamp = ktime_get_ns();
 
 	dev->vbi_mode.bulk_ctl.buf = NULL;
 
-	list_del(&buf->vb.queue);
-	wake_up(&buf->vb.done);
+	list_del(&buf->list);
+	vb2_buffer_done(&buf->vb.vb2_buf, VB2_BUF_STATE_DONE);
 }
 
 u32 cx231xx_copy_vbi_line(struct cx231xx *dev, struct cx231xx_dmaqueue *dma_q,
@@ -611,11 +577,11 @@ static inline void get_next_vbi_buf(struct cx231xx_dmaqueue *dma_q,
 	}
 
 	/* Get the next buffer */
-	*buf = list_entry(dma_q->active.next, struct cx231xx_buffer, vb.queue);
+	*buf = list_entry(dma_q->active.next, struct cx231xx_buffer, list);
 
 	/* Cleans up buffer - Useful for testing for frame/URB loss */
-	outp = videobuf_to_vmalloc(&(*buf)->vb);
-	memset(outp, 0, (*buf)->vb.size);
+	outp = vb2_plane_vaddr(&(*buf)->vb.vb2_buf, 0);
+	memset(outp, 0, vb2_plane_size(&(*buf)->vb.vb2_buf, 0));
 
 	dev->vbi_mode.bulk_ctl.buf = *buf;
 
@@ -656,7 +622,7 @@ int cx231xx_do_vbi_copy(struct cx231xx *dev, struct cx231xx_dmaqueue *dma_q,
 	if (buf == NULL)
 		return -EINVAL;
 
-	p_out_buffer = videobuf_to_vmalloc(&buf->vb);
+	p_out_buffer = vb2_plane_vaddr(&buf->vb.vb2_buf, 0);
 
 	if (dma_q->bytes_left_in_line != _line_size) {
 		current_line_bytes_copied =
diff --git a/drivers/media/usb/cx231xx/cx231xx-vbi.h b/drivers/media/usb/cx231xx/cx231xx-vbi.h
index 7cddd629fbfc..0b21bee5fa30 100644
--- a/drivers/media/usb/cx231xx/cx231xx-vbi.h
+++ b/drivers/media/usb/cx231xx/cx231xx-vbi.h
@@ -10,7 +10,7 @@
 #ifndef _CX231XX_VBI_H
 #define _CX231XX_VBI_H
 
-extern const struct videobuf_queue_ops cx231xx_vbi_qops;
+extern struct vb2_ops cx231xx_vbi_qops;
 
 #define   NTSC_VBI_START_LINE 10	/* line 10 - 21 */
 #define   NTSC_VBI_END_LINE   21
diff --git a/drivers/media/usb/cx231xx/cx231xx-video.c b/drivers/media/usb/cx231xx/cx231xx-video.c
index 9b51f07a729e..69abafaebbf3 100644
--- a/drivers/media/usb/cx231xx/cx231xx-video.c
+++ b/drivers/media/usb/cx231xx/cx231xx-video.c
@@ -58,10 +58,10 @@ MODULE_DESCRIPTION(DRIVER_DESC);
 MODULE_LICENSE("GPL");
 MODULE_VERSION(CX231XX_VERSION);
 
-static unsigned int card[]     = {[0 ... (CX231XX_MAXBOARDS - 1)] = UNSET };
-static unsigned int video_nr[] = {[0 ... (CX231XX_MAXBOARDS - 1)] = UNSET };
-static unsigned int vbi_nr[]   = {[0 ... (CX231XX_MAXBOARDS - 1)] = UNSET };
-static unsigned int radio_nr[] = {[0 ... (CX231XX_MAXBOARDS - 1)] = UNSET };
+static unsigned int card[]     = {[0 ... (CX231XX_MAXBOARDS - 1)] = -1U };
+static unsigned int video_nr[] = {[0 ... (CX231XX_MAXBOARDS - 1)] = -1U };
+static unsigned int vbi_nr[]   = {[0 ... (CX231XX_MAXBOARDS - 1)] = -1U };
+static unsigned int radio_nr[] = {[0 ... (CX231XX_MAXBOARDS - 1)] = -1U };
 
 module_param_array(card, int, NULL, 0444);
 module_param_array(video_nr, int, NULL, 0444);
@@ -166,18 +166,19 @@ static inline void buffer_filled(struct cx231xx *dev,
 				 struct cx231xx_buffer *buf)
 {
 	/* Advice that buffer was filled */
-	cx231xx_isocdbg("[%p/%d] wakeup\n", buf, buf->vb.i);
-	buf->vb.state = VIDEOBUF_DONE;
-	buf->vb.field_count++;
-	buf->vb.ts = ktime_get_ns();
+	cx231xx_isocdbg("[%p/%d] wakeup\n", buf, buf->vb.vb2_buf.index);
+	buf->vb.sequence = dma_q->sequence++;
+	buf->vb.field = V4L2_FIELD_INTERLACED;
+	buf->vb.vb2_buf.timestamp = ktime_get_ns();
+	vb2_set_plane_payload(&buf->vb.vb2_buf, 0, dev->size);
 
 	if (dev->USE_ISO)
 		dev->video_mode.isoc_ctl.buf = NULL;
 	else
 		dev->video_mode.bulk_ctl.buf = NULL;
 
-	list_del(&buf->vb.queue);
-	wake_up(&buf->vb.done);
+	list_del(&buf->list);
+	vb2_buffer_done(&buf->vb.vb2_buf, VB2_BUF_STATE_DONE);
 }
 
 static inline void print_err_status(struct cx231xx *dev, int packet, int status)
@@ -241,11 +242,11 @@ static inline void get_next_buf(struct cx231xx_dmaqueue *dma_q,
 	}
 
 	/* Get the next buffer */
-	*buf = list_entry(dma_q->active.next, struct cx231xx_buffer, vb.queue);
+	*buf = list_entry(dma_q->active.next, struct cx231xx_buffer, list);
 
 	/* Cleans up buffer - Useful for testing for frame/URB loss */
-	outp = videobuf_to_vmalloc(&(*buf)->vb);
-	memset(outp, 0, (*buf)->vb.size);
+	outp = vb2_plane_vaddr(&(*buf)->vb.vb2_buf, 0);
+	memset(outp, 0, dev->size);
 
 	if (dev->USE_ISO)
 		dev->video_mode.isoc_ctl.buf = *buf;
@@ -653,7 +654,7 @@ int cx231xx_do_copy(struct cx231xx *dev, struct cx231xx_dmaqueue *dma_q,
 	if (buf == NULL)
 		return -1;
 
-	p_out_buffer = videobuf_to_vmalloc(&buf->vb);
+	p_out_buffer = vb2_plane_vaddr(&buf->vb.vb2_buf, 0);
 
 	current_line_bytes_copied = _line_size - dma_q->bytes_left_in_line;
 
@@ -672,7 +673,7 @@ int cx231xx_do_copy(struct cx231xx *dev, struct cx231xx_dmaqueue *dma_q,
 	lencopy = dma_q->bytes_left_in_line > bytes_to_copy ?
 		  bytes_to_copy : dma_q->bytes_left_in_line;
 
-	if ((u8 *)(startwrite + lencopy) > (u8 *)(p_out_buffer + buf->vb.size))
+	if ((u8 *)(startwrite + lencopy) > (u8 *)(p_out_buffer + dev->size))
 		return 0;
 
 	/* The below copies the UYVY data straight into video buffer */
@@ -708,149 +709,98 @@ u8 cx231xx_is_buffer_done(struct cx231xx *dev, struct cx231xx_dmaqueue *dma_q)
 	Videobuf operations
    ------------------------------------------------------------------*/
 
-static int
-buffer_setup(struct videobuf_queue *vq, unsigned int *count, unsigned int *size)
+static int queue_setup(struct vb2_queue *vq,
+		       unsigned int *nbuffers, unsigned int *nplanes,
+		       unsigned int sizes[], struct device *alloc_devs[])
 {
-	struct cx231xx_fh *fh = vq->priv_data;
-	struct cx231xx *dev = fh->dev;
+	struct cx231xx *dev = vb2_get_drv_priv(vq);
 
-	*size = (fh->dev->width * fh->dev->height * dev->format->depth + 7)>>3;
-	if (0 == *count)
-		*count = CX231XX_DEF_BUF;
+	dev->size = (dev->width * dev->height * dev->format->depth + 7) >> 3;
 
-	if (*count < CX231XX_MIN_BUF)
-		*count = CX231XX_MIN_BUF;
+	if (vq->num_buffers + *nbuffers < CX231XX_MIN_BUF)
+		*nbuffers = CX231XX_MIN_BUF - vq->num_buffers;
 
-
-	cx231xx_enable_analog_tuner(dev);
+	if (*nplanes)
+		return sizes[0] < dev->size ? -EINVAL : 0;
+	*nplanes = 1;
+	sizes[0] = dev->size;
 
 	return 0;
 }
 
-/* This is called *without* dev->slock held; please keep it that way */
-static void free_buffer(struct videobuf_queue *vq, struct cx231xx_buffer *buf)
+static void buffer_queue(struct vb2_buffer *vb)
 {
-	struct cx231xx_fh *fh = vq->priv_data;
-	struct cx231xx *dev = fh->dev;
-	unsigned long flags = 0;
-
-	BUG_ON(in_interrupt());
-
-	/* We used to wait for the buffer to finish here, but this didn't work
-	   because, as we were keeping the state as VIDEOBUF_QUEUED,
-	   videobuf_queue_cancel marked it as finished for us.
-	   (Also, it could wedge forever if the hardware was misconfigured.)
+	struct cx231xx_buffer *buf =
+	    container_of(vb, struct cx231xx_buffer, vb.vb2_buf);
+	struct cx231xx *dev = vb2_get_drv_priv(vb->vb2_queue);
+	struct cx231xx_dmaqueue *vidq = &dev->video_mode.vidq;
+	unsigned long flags;
 
-	   This should be safe; by the time we get here, the buffer isn't
-	   queued anymore. If we ever start marking the buffers as
-	   VIDEOBUF_ACTIVE, it won't be, though.
-	 */
 	spin_lock_irqsave(&dev->video_mode.slock, flags);
-	if (dev->USE_ISO) {
-		if (dev->video_mode.isoc_ctl.buf == buf)
-			dev->video_mode.isoc_ctl.buf = NULL;
-	} else {
-		if (dev->video_mode.bulk_ctl.buf == buf)
-			dev->video_mode.bulk_ctl.buf = NULL;
-	}
+	list_add_tail(&buf->list, &vidq->active);
 	spin_unlock_irqrestore(&dev->video_mode.slock, flags);
-
-	videobuf_vmalloc_free(&buf->vb);
-	buf->vb.state = VIDEOBUF_NEEDS_INIT;
 }
 
-static int
-buffer_prepare(struct videobuf_queue *vq, struct videobuf_buffer *vb,
-	       enum v4l2_field field)
+static void return_all_buffers(struct cx231xx *dev,
+			       enum vb2_buffer_state state)
 {
-	struct cx231xx_fh *fh = vq->priv_data;
-	struct cx231xx_buffer *buf =
-	    container_of(vb, struct cx231xx_buffer, vb);
-	struct cx231xx *dev = fh->dev;
-	int rc = 0, urb_init = 0;
-
-	/* The only currently supported format is 16 bits/pixel */
-	buf->vb.size = (fh->dev->width * fh->dev->height * dev->format->depth
-			+ 7) >> 3;
-	if (0 != buf->vb.baddr && buf->vb.bsize < buf->vb.size)
-		return -EINVAL;
-
-	buf->vb.width = dev->width;
-	buf->vb.height = dev->height;
-	buf->vb.field = field;
-
-	if (VIDEOBUF_NEEDS_INIT == buf->vb.state) {
-		rc = videobuf_iolock(vq, &buf->vb, NULL);
-		if (rc < 0)
-			goto fail;
-	}
+	struct cx231xx_dmaqueue *vidq = &dev->video_mode.vidq;
+	struct cx231xx_buffer *buf, *node;
+	unsigned long flags;
 
-	if (dev->USE_ISO) {
-		if (!dev->video_mode.isoc_ctl.num_bufs)
-			urb_init = 1;
-	} else {
-		if (!dev->video_mode.bulk_ctl.num_bufs)
-			urb_init = 1;
-	}
-	dev_dbg(dev->dev,
-		"urb_init=%d dev->video_mode.max_pkt_size=%d\n",
-		urb_init, dev->video_mode.max_pkt_size);
-	if (urb_init) {
-		dev->mode_tv = 0;
-		if (dev->USE_ISO)
-			rc = cx231xx_init_isoc(dev, CX231XX_NUM_PACKETS,
-				       CX231XX_NUM_BUFS,
-				       dev->video_mode.max_pkt_size,
-				       cx231xx_isoc_copy);
-		else
-			rc = cx231xx_init_bulk(dev, CX231XX_NUM_PACKETS,
-				       CX231XX_NUM_BUFS,
-				       dev->video_mode.max_pkt_size,
-				       cx231xx_bulk_copy);
-		if (rc < 0)
-			goto fail;
+	spin_lock_irqsave(&dev->video_mode.slock, flags);
+	if (dev->USE_ISO)
+		dev->video_mode.isoc_ctl.buf = NULL;
+	else
+		dev->video_mode.bulk_ctl.buf = NULL;
+	list_for_each_entry_safe(buf, node, &vidq->active, list) {
+		list_del(&buf->list);
+		vb2_buffer_done(&buf->vb.vb2_buf, state);
 	}
-
-	buf->vb.state = VIDEOBUF_PREPARED;
-
-	return 0;
-
-fail:
-	free_buffer(vq, buf);
-	return rc;
+	spin_unlock_irqrestore(&dev->video_mode.slock, flags);
 }
 
-static void buffer_queue(struct videobuf_queue *vq, struct videobuf_buffer *vb)
+static int start_streaming(struct vb2_queue *vq, unsigned int count)
 {
-	struct cx231xx_buffer *buf =
-	    container_of(vb, struct cx231xx_buffer, vb);
-	struct cx231xx_fh *fh = vq->priv_data;
-	struct cx231xx *dev = fh->dev;
+	struct cx231xx *dev = vb2_get_drv_priv(vq);
 	struct cx231xx_dmaqueue *vidq = &dev->video_mode.vidq;
+	int ret = 0;
 
-	buf->vb.state = VIDEOBUF_QUEUED;
-	list_add_tail(&buf->vb.queue, &vidq->active);
+	vidq->sequence = 0;
+	dev->mode_tv = 0;
 
+	cx231xx_enable_analog_tuner(dev);
+	if (dev->USE_ISO)
+		ret = cx231xx_init_isoc(dev, CX231XX_NUM_PACKETS,
+					CX231XX_NUM_BUFS,
+					dev->video_mode.max_pkt_size,
+					cx231xx_isoc_copy);
+	else
+		ret = cx231xx_init_bulk(dev, CX231XX_NUM_PACKETS,
+					CX231XX_NUM_BUFS,
+					dev->video_mode.max_pkt_size,
+					cx231xx_bulk_copy);
+	if (ret)
+		return_all_buffers(dev, VB2_BUF_STATE_QUEUED);
+	call_all(dev, video, s_stream, 1);
+	return ret;
 }
 
-static void buffer_release(struct videobuf_queue *vq,
-			   struct videobuf_buffer *vb)
+static void stop_streaming(struct vb2_queue *vq)
 {
-	struct cx231xx_buffer *buf =
-	    container_of(vb, struct cx231xx_buffer, vb);
-	struct cx231xx_fh *fh = vq->priv_data;
-	struct cx231xx *dev = (struct cx231xx *)fh->dev;
-
-	cx231xx_isocdbg("cx231xx: called buffer_release\n");
+	struct cx231xx *dev = vb2_get_drv_priv(vq);
 
-	free_buffer(vq, buf);
+	call_all(dev, video, s_stream, 0);
+	return_all_buffers(dev, VB2_BUF_STATE_ERROR);
 }
 
-static const struct videobuf_queue_ops cx231xx_video_qops = {
-	.buf_setup = buffer_setup,
-	.buf_prepare = buffer_prepare,
-	.buf_queue = buffer_queue,
-	.buf_release = buffer_release,
+static struct vb2_ops cx231xx_video_qops = {
+	.queue_setup		= queue_setup,
+	.buf_queue		= buffer_queue,
+	.start_streaming	= start_streaming,
+	.stop_streaming		= stop_streaming,
+	.wait_prepare		= vb2_ops_wait_prepare,
+	.wait_finish		= vb2_ops_wait_finish,
 };
 
 /*********************  v4l2 interface  **************************************/
@@ -872,58 +822,6 @@ void video_mux(struct cx231xx *dev, int index)
 	cx231xx_do_mode_ctrl_overrides(dev);
 }
 
-/* Usage lock check functions */
-static int res_get(struct cx231xx_fh *fh)
-{
-	struct cx231xx *dev = fh->dev;
-	int rc = 0;
-
-	/* This instance already has stream_on */
-	if (fh->stream_on)
-		return rc;
-
-	if (fh->type == V4L2_BUF_TYPE_VIDEO_CAPTURE) {
-		if (dev->stream_on)
-			return -EBUSY;
-		dev->stream_on = 1;
-	} else if (fh->type == V4L2_BUF_TYPE_VBI_CAPTURE) {
-		if (dev->vbi_stream_on)
-			return -EBUSY;
-		dev->vbi_stream_on = 1;
-	} else
-		return -EINVAL;
-
-	fh->stream_on = 1;
-
-	return rc;
-}
-
-static int res_check(struct cx231xx_fh *fh)
-{
-	return fh->stream_on;
-}
-
-static void res_free(struct cx231xx_fh *fh)
-{
-	struct cx231xx *dev = fh->dev;
-
-	fh->stream_on = 0;
-
-	if (fh->type == V4L2_BUF_TYPE_VIDEO_CAPTURE)
-		dev->stream_on = 0;
-	if (fh->type == V4L2_BUF_TYPE_VBI_CAPTURE)
-		dev->vbi_stream_on = 0;
-}
-
-static int check_dev(struct cx231xx *dev)
-{
-	if (dev->state & DEV_DISCONNECTED) {
-		dev_err(dev->dev, "v4l2 ioctl: device not present\n");
-		return -ENODEV;
-	}
-	return 0;
-}
-
 /* ------------------------------------------------------------------
 	IOCTL vidioc handling
    ------------------------------------------------------------------*/
@@ -931,8 +829,7 @@ static int check_dev(struct cx231xx *dev)
 static int vidioc_g_fmt_vid_cap(struct file *file, void *priv,
 				struct v4l2_format *f)
 {
-	struct cx231xx_fh *fh = priv;
-	struct cx231xx *dev = fh->dev;
+	struct cx231xx *dev = video_drvdata(file);
 
 	f->fmt.pix.width = dev->width;
 	f->fmt.pix.height = dev->height;
@@ -960,8 +857,7 @@ static struct cx231xx_fmt *format_by_fourcc(unsigned int fourcc)
 static int vidioc_try_fmt_vid_cap(struct file *file, void *priv,
 				  struct v4l2_format *f)
 {
-	struct cx231xx_fh *fh = priv;
-	struct cx231xx *dev = fh->dev;
+	struct cx231xx *dev = video_drvdata(file);
 	unsigned int width = f->fmt.pix.width;
 	unsigned int height = f->fmt.pix.height;
 	unsigned int maxw = norm_maxw(dev);
@@ -993,39 +889,25 @@ static int vidioc_try_fmt_vid_cap(struct file *file, void *priv,
 static int vidioc_s_fmt_vid_cap(struct file *file, void *priv,
 				struct v4l2_format *f)
 {
-	struct cx231xx_fh *fh = priv;
-	struct cx231xx *dev = fh->dev;
-	int rc;
-	struct cx231xx_fmt *fmt;
+	struct cx231xx *dev = video_drvdata(file);
 	struct v4l2_subdev_format format = {
 		.which = V4L2_SUBDEV_FORMAT_ACTIVE,
 	};
+	int rc;
 
-	rc = check_dev(dev);
-	if (rc < 0)
+	rc = vidioc_try_fmt_vid_cap(file, priv, f);
+	if (rc)
 		return rc;
 
-	vidioc_try_fmt_vid_cap(file, priv, f);
-
-	fmt = format_by_fourcc(f->fmt.pix.pixelformat);
-	if (!fmt)
-		return -EINVAL;
-
-	if (videobuf_queue_is_busy(&fh->vb_vidq)) {
+	if (vb2_is_busy(&dev->vidq)) {
 		dev_err(dev->dev, "%s: queue busy\n", __func__);
 		return -EBUSY;
 	}
 
-	if (dev->stream_on && !fh->stream_on) {
-		dev_err(dev->dev,
-			"%s: device in use by another fh\n", __func__);
-		return -EBUSY;
-	}
-
 	/* set new image size */
 	dev->width = f->fmt.pix.width;
 	dev->height = f->fmt.pix.height;
-	dev->format = fmt;
+	dev->format = format_by_fourcc(f->fmt.pix.pixelformat);
 
 	v4l2_fill_mbus_format(&format.format, &f->fmt.pix, MEDIA_BUS_FMT_FIXED);
 	call_all(dev, pad, set_fmt, NULL, &format);
@@ -1036,8 +918,7 @@ static int vidioc_s_fmt_vid_cap(struct file *file, void *priv,
 
 static int vidioc_g_std(struct file *file, void *priv, v4l2_std_id *id)
 {
-	struct cx231xx_fh *fh = priv;
-	struct cx231xx *dev = fh->dev;
+	struct cx231xx *dev = video_drvdata(file);
 
 	*id = dev->norm;
 	return 0;
@@ -1045,21 +926,15 @@ static int vidioc_g_std(struct file *file, void *priv, v4l2_std_id *id)
 
 static int vidioc_s_std(struct file *file, void *priv, v4l2_std_id norm)
 {
-	struct cx231xx_fh *fh = priv;
-	struct cx231xx *dev = fh->dev;
+	struct cx231xx *dev = video_drvdata(file);
 	struct v4l2_subdev_format format = {
 		.which = V4L2_SUBDEV_FORMAT_ACTIVE,
 	};
-	int rc;
-
-	rc = check_dev(dev);
-	if (rc < 0)
-		return rc;
 
 	if (dev->norm == norm)
 		return 0;
 
-	if (videobuf_queue_is_busy(&fh->vb_vidq))
+	if (vb2_is_busy(&dev->vidq))
 		return -EBUSY;
 
 	dev->norm = norm;
@@ -1141,8 +1016,7 @@ void cx231xx_v4l2_create_entities(struct cx231xx *dev)
 int cx231xx_enum_input(struct file *file, void *priv,
 			     struct v4l2_input *i)
 {
-	struct cx231xx_fh *fh = priv;
-	struct cx231xx *dev = fh->dev;
+	struct cx231xx *dev = video_drvdata(file);
 	u32 gen_stat;
 	unsigned int n;
 	int ret;
@@ -1181,8 +1055,7 @@ int cx231xx_enum_input(struct file *file, void *priv,
 
 int cx231xx_g_input(struct file *file, void *priv, unsigned int *i)
 {
-	struct cx231xx_fh *fh = priv;
-	struct cx231xx *dev = fh->dev;
+	struct cx231xx *dev = video_drvdata(file);
 
 	*i = dev->video_input;
 
@@ -1191,14 +1064,9 @@ int cx231xx_g_input(struct file *file, void *priv, unsigned int *i)
 
 int cx231xx_s_input(struct file *file, void *priv, unsigned int i)
 {
-	struct cx231xx_fh *fh = priv;
-	struct cx231xx *dev = fh->dev;
-	int rc;
+	struct cx231xx *dev = video_drvdata(file);
 
 	dev->mode_tv = 0;
-	rc = check_dev(dev);
-	if (rc < 0)
-		return rc;
 
 	if (i >= MAX_CX231XX_INPUT)
 		return -EINVAL;
@@ -1220,13 +1088,7 @@ int cx231xx_s_input(struct file *file, void *priv, unsigned int i)
 
 int cx231xx_g_tuner(struct file *file, void *priv, struct v4l2_tuner *t)
 {
-	struct cx231xx_fh *fh = priv;
-	struct cx231xx *dev = fh->dev;
-	int rc;
-
-	rc = check_dev(dev);
-	if (rc < 0)
-		return rc;
+	struct cx231xx *dev = video_drvdata(file);
 
 	if (0 != t->index)
 		return -EINVAL;
@@ -1244,27 +1106,15 @@ int cx231xx_g_tuner(struct file *file, void *priv, struct v4l2_tuner *t)
 
 int cx231xx_s_tuner(struct file *file, void *priv, const struct v4l2_tuner *t)
 {
-	struct cx231xx_fh *fh = priv;
-	struct cx231xx *dev = fh->dev;
-	int rc;
-
-	rc = check_dev(dev);
-	if (rc < 0)
-		return rc;
-
 	if (0 != t->index)
 		return -EINVAL;
-#if 0
-	call_all(dev, tuner, s_tuner, t);
-#endif
 	return 0;
 }
 
 int cx231xx_g_frequency(struct file *file, void *priv,
 			      struct v4l2_frequency *f)
 {
-	struct cx231xx_fh *fh = priv;
-	struct cx231xx *dev = fh->dev;
+	struct cx231xx *dev = video_drvdata(file);
 
 	if (f->tuner)
 		return -EINVAL;
@@ -1277,8 +1127,7 @@ int cx231xx_g_frequency(struct file *file, void *priv,
 int cx231xx_s_frequency(struct file *file, void *priv,
 			      const struct v4l2_frequency *f)
 {
-	struct cx231xx_fh *fh = priv;
-	struct cx231xx *dev = fh->dev;
+	struct cx231xx *dev = video_drvdata(file);
 	struct v4l2_frequency new_freq = *f;
 	int rc;
 	u32 if_frequency = 5400000;
@@ -1287,10 +1136,6 @@ int cx231xx_s_frequency(struct file *file, void *priv,
 		"Enter vidioc_s_frequency()f->frequency=%d;f->type=%d\n",
 		f->frequency, f->type);
 
-	rc = check_dev(dev);
-	if (rc < 0)
-		return rc;
-
 	if (0 != f->tuner)
 		return -EINVAL;
 
@@ -1365,8 +1210,7 @@ int cx231xx_g_chip_info(struct file *file, void *fh,
 int cx231xx_g_register(struct file *file, void *priv,
 			     struct v4l2_dbg_register *reg)
 {
-	struct cx231xx_fh *fh = priv;
-	struct cx231xx *dev = fh->dev;
+	struct cx231xx *dev = video_drvdata(file);
 	int ret;
 	u8 value[4] = { 0, 0, 0, 0 };
 	u32 data = 0;
@@ -1424,8 +1268,7 @@ int cx231xx_g_register(struct file *file, void *priv,
 int cx231xx_s_register(struct file *file, void *priv,
 			     const struct v4l2_dbg_register *reg)
 {
-	struct cx231xx_fh *fh = priv;
-	struct cx231xx *dev = fh->dev;
+	struct cx231xx *dev = video_drvdata(file);
 	int ret;
 	u8 data[4] = { 0, 0, 0, 0 };
 
@@ -1472,8 +1315,7 @@ int cx231xx_s_register(struct file *file, void *priv,
 static int vidioc_g_pixelaspect(struct file *file, void *priv,
 				int type, struct v4l2_fract *f)
 {
-	struct cx231xx_fh *fh = priv;
-	struct cx231xx *dev = fh->dev;
+	struct cx231xx *dev = video_drvdata(file);
 	bool is_50hz = dev->norm & V4L2_STD_625_50;
 
 	if (type != V4L2_BUF_TYPE_VIDEO_CAPTURE)
@@ -1488,8 +1330,7 @@ static int vidioc_g_pixelaspect(struct file *file, void *priv,
 static int vidioc_g_selection(struct file *file, void *priv,
 			      struct v4l2_selection *s)
 {
-	struct cx231xx_fh *fh = priv;
-	struct cx231xx *dev = fh->dev;
+	struct cx231xx *dev = video_drvdata(file);
 
 	if (s->type != V4L2_BUF_TYPE_VIDEO_CAPTURE)
 		return -EINVAL;
@@ -1508,54 +1349,10 @@ static int vidioc_g_selection(struct file *file, void *priv,
 	return 0;
 }
 
-static int vidioc_streamon(struct file *file, void *priv,
-			   enum v4l2_buf_type type)
-{
-	struct cx231xx_fh *fh = priv;
-	struct cx231xx *dev = fh->dev;
-	int rc;
-
-	rc = check_dev(dev);
-	if (rc < 0)
-		return rc;
-
-	rc = res_get(fh);
-
-	if (likely(rc >= 0))
-		rc = videobuf_streamon(&fh->vb_vidq);
-
-	call_all(dev, video, s_stream, 1);
-
-	return rc;
-}
-
-static int vidioc_streamoff(struct file *file, void *priv,
-			    enum v4l2_buf_type type)
-{
-	struct cx231xx_fh *fh = priv;
-	struct cx231xx *dev = fh->dev;
-	int rc;
-
-	rc = check_dev(dev);
-	if (rc < 0)
-		return rc;
-
-	if (type != fh->type)
-		return -EINVAL;
-
-	cx25840_call(dev, video, s_stream, 0);
-
-	videobuf_streamoff(&fh->vb_vidq);
-	res_free(fh);
-
-	return 0;
-}
-
 int cx231xx_querycap(struct file *file, void *priv,
 			   struct v4l2_capability *cap)
 {
-	struct cx231xx_fh *fh = priv;
-	struct cx231xx *dev = fh->dev;
+	struct cx231xx *dev = video_drvdata(file);
 
 	strscpy(cap->driver, "cx231xx", sizeof(cap->driver));
 	strscpy(cap->card, cx231xx_boards[dev->model].name, sizeof(cap->card));
@@ -1587,8 +1384,7 @@ static int vidioc_enum_fmt_vid_cap(struct file *file, void *priv,
 static int vidioc_g_fmt_vbi_cap(struct file *file, void *priv,
 				struct v4l2_format *f)
 {
-	struct cx231xx_fh *fh = priv;
-	struct cx231xx *dev = fh->dev;
+	struct cx231xx *dev = video_drvdata(file);
 
 	f->fmt.vbi.sampling_rate = 6750000 * 4;
 	f->fmt.vbi.samples_per_line = VBI_LINE_LENGTH;
@@ -1610,8 +1406,7 @@ static int vidioc_g_fmt_vbi_cap(struct file *file, void *priv,
 static int vidioc_try_fmt_vbi_cap(struct file *file, void *priv,
 				  struct v4l2_format *f)
 {
-	struct cx231xx_fh *fh = priv;
-	struct cx231xx *dev = fh->dev;
+	struct cx231xx *dev = video_drvdata(file);
 
 	f->fmt.vbi.sampling_rate = 6750000 * 4;
 	f->fmt.vbi.samples_per_line = VBI_LINE_LENGTH;
@@ -1634,77 +1429,16 @@ static int vidioc_try_fmt_vbi_cap(struct file *file, void *priv,
 static int vidioc_s_fmt_vbi_cap(struct file *file, void *priv,
 				  struct v4l2_format *f)
 {
-	struct cx231xx_fh *fh = priv;
-	struct cx231xx *dev = fh->dev;
-
-	if (dev->vbi_stream_on && !fh->stream_on) {
-		dev_err(dev->dev,
-			"%s device in use by another fh\n", __func__);
-		return -EBUSY;
-	}
 	return vidioc_try_fmt_vbi_cap(file, priv, f);
 }
 
-static int vidioc_reqbufs(struct file *file, void *priv,
-			  struct v4l2_requestbuffers *rb)
-{
-	struct cx231xx_fh *fh = priv;
-	struct cx231xx *dev = fh->dev;
-	int rc;
-
-	rc = check_dev(dev);
-	if (rc < 0)
-		return rc;
-
-	return videobuf_reqbufs(&fh->vb_vidq, rb);
-}
-
-static int vidioc_querybuf(struct file *file, void *priv, struct v4l2_buffer *b)
-{
-	struct cx231xx_fh *fh = priv;
-	struct cx231xx *dev = fh->dev;
-	int rc;
-
-	rc = check_dev(dev);
-	if (rc < 0)
-		return rc;
-
-	return videobuf_querybuf(&fh->vb_vidq, b);
-}
-
-static int vidioc_qbuf(struct file *file, void *priv, struct v4l2_buffer *b)
-{
-	struct cx231xx_fh *fh = priv;
-	struct cx231xx *dev = fh->dev;
-	int rc;
-
-	rc = check_dev(dev);
-	if (rc < 0)
-		return rc;
-
-	return videobuf_qbuf(&fh->vb_vidq, b);
-}
-
-static int vidioc_dqbuf(struct file *file, void *priv, struct v4l2_buffer *b)
-{
-	struct cx231xx_fh *fh = priv;
-	struct cx231xx *dev = fh->dev;
-	int rc;
-
-	rc = check_dev(dev);
-	if (rc < 0)
-		return rc;
-
-	return videobuf_dqbuf(&fh->vb_vidq, b, file->f_flags & O_NONBLOCK);
-}
-
 /* ----------------------------------------------------------- */
 /* RADIO ESPECIFIC IOCTLS                                      */
 /* ----------------------------------------------------------- */
 
 static int radio_g_tuner(struct file *file, void *priv, struct v4l2_tuner *t)
 {
-	struct cx231xx *dev = ((struct cx231xx_fh *)priv)->dev;
+	struct cx231xx *dev = video_drvdata(file);
 
 	if (t->index)
 		return -EINVAL;
@@ -1717,7 +1451,7 @@ static int radio_g_tuner(struct file *file, void *priv, struct v4l2_tuner *t)
 }
 static int radio_s_tuner(struct file *file, void *priv, const struct v4l2_tuner *t)
 {
-	struct cx231xx *dev = ((struct cx231xx_fh *)priv)->dev;
+	struct cx231xx *dev = video_drvdata(file);
 
 	if (t->index)
 		return -EINVAL;
@@ -1733,52 +1467,20 @@ static int radio_s_tuner(struct file *file, void *priv, const struct v4l2_tuner
  */
 static int cx231xx_v4l2_open(struct file *filp)
 {
-	int radio = 0;
 	struct video_device *vdev = video_devdata(filp);
 	struct cx231xx *dev = video_drvdata(filp);
-	struct cx231xx_fh *fh;
-	enum v4l2_buf_type fh_type = 0;
-
-	switch (vdev->vfl_type) {
-	case VFL_TYPE_GRABBER:
-		fh_type = V4L2_BUF_TYPE_VIDEO_CAPTURE;
-		break;
-	case VFL_TYPE_VBI:
-		fh_type = V4L2_BUF_TYPE_VBI_CAPTURE;
-		break;
-	case VFL_TYPE_RADIO:
-		radio = 1;
-		break;
-	default:
-		return -EINVAL;
-	}
-
-	cx231xx_videodbg("open dev=%s type=%s users=%d\n",
-			 video_device_node_name(vdev), v4l2_type_names[fh_type],
-			 dev->users);
-
-#if 0
-	errCode = cx231xx_set_mode(dev, CX231XX_ANALOG_MODE);
-	if (errCode < 0) {
-		dev_err(dev->dev,
-			"Device locked on digital mode. Can't open analog\n");
-		return -EBUSY;
-	}
-#endif
+	int ret;
 
-	fh = kzalloc(sizeof(struct cx231xx_fh), GFP_KERNEL);
-	if (!fh)
-		return -ENOMEM;
-	if (mutex_lock_interruptible(&dev->lock)) {
-		kfree(fh);
+	if (mutex_lock_interruptible(&dev->lock))
 		return -ERESTARTSYS;
+
+	ret = v4l2_fh_open(filp);
+	if (ret) {
+		mutex_unlock(&dev->lock);
+		return ret;
 	}
-	fh->dev = dev;
-	fh->type = fh_type;
-	filp->private_data = fh;
-	v4l2_fh_init(&fh->fh, vdev);
 
-	if (fh->type == V4L2_BUF_TYPE_VIDEO_CAPTURE && dev->users == 0) {
+	if (dev->users++ == 0) {
 		/* Power up in Analog TV mode */
 		if (dev->board.external_av)
 			cx231xx_set_power_mode(dev,
@@ -1786,10 +1488,6 @@ static int cx231xx_v4l2_open(struct file *filp)
 		else
 			cx231xx_set_power_mode(dev, POLARIS_AVMODE_ANALOGT_TV);
 
-#if 0
-		cx231xx_set_mode(dev, CX231XX_ANALOG_MODE);
-#endif
-
 		/* set video alternate setting */
 		cx231xx_set_video_alternate(dev);
 
@@ -1799,38 +1497,21 @@ static int cx231xx_v4l2_open(struct file *filp)
 
 		/* device needs to be initialized before isoc transfer */
 		dev->video_input = dev->video_input > 2 ? 2 : dev->video_input;
-
 	}
-	if (radio) {
+
+	if (vdev->vfl_type == VFL_TYPE_RADIO) {
 		cx231xx_videodbg("video_open: setting radio device\n");
 
 		/* cx231xx_start_radio(dev); */
 
 		call_all(dev, tuner, s_radio);
 	}
-
-	dev->users++;
-
-	if (fh->type == V4L2_BUF_TYPE_VIDEO_CAPTURE)
-		videobuf_queue_vmalloc_init(&fh->vb_vidq, &cx231xx_video_qops,
-					    NULL, &dev->video_mode.slock,
-					    fh->type, V4L2_FIELD_INTERLACED,
-					    sizeof(struct cx231xx_buffer),
-					    fh, &dev->lock);
-	if (fh->type == V4L2_BUF_TYPE_VBI_CAPTURE) {
+	if (vdev->vfl_type == VFL_TYPE_VBI) {
 		/* Set the required alternate setting  VBI interface works in
 		   Bulk mode only */
 		cx231xx_set_alt_setting(dev, INDEX_VANC, 0);
-
-		videobuf_queue_vmalloc_init(&fh->vb_vidq, &cx231xx_vbi_qops,
-					    NULL, &dev->vbi_mode.slock,
-					    fh->type, V4L2_FIELD_SEQ_TB,
-					    sizeof(struct cx231xx_buffer),
-					    fh, &dev->lock);
 	}
 	mutex_unlock(&dev->lock);
-	v4l2_fh_add(&fh->fh);
-
 	return 0;
 }
 
@@ -1871,68 +1552,12 @@ void cx231xx_release_analog_resources(struct cx231xx *dev)
  */
 static int cx231xx_close(struct file *filp)
 {
-	struct cx231xx_fh *fh = filp->private_data;
-	struct cx231xx *dev = fh->dev;
-
-	cx231xx_videodbg("users=%d\n", dev->users);
-
-	cx231xx_videodbg("users=%d\n", dev->users);
-	if (res_check(fh))
-		res_free(fh);
-
-	/*
-	 * To workaround error number=-71 on EP0 for VideoGrabber,
-	 *	 need exclude following.
-	 * FIXME: It is probably safe to remove most of these, as we're
-	 * now avoiding the alternate setting for INDEX_VANC
-	 */
-	if (!dev->board.no_alt_vanc)
-		if (fh->type == V4L2_BUF_TYPE_VBI_CAPTURE) {
-			videobuf_stop(&fh->vb_vidq);
-			videobuf_mmap_free(&fh->vb_vidq);
-
-			/* the device is already disconnect,
-			   free the remaining resources */
-			if (dev->state & DEV_DISCONNECTED) {
-				if (atomic_read(&dev->devlist_count) > 0) {
-					cx231xx_release_resources(dev);
-					fh->dev = NULL;
-					return 0;
-				}
-				return 0;
-			}
-
-			/* do this before setting alternate! */
-			cx231xx_uninit_vbi_isoc(dev);
-
-			/* set alternate 0 */
-			if (!dev->vbi_or_sliced_cc_mode)
-				cx231xx_set_alt_setting(dev, INDEX_VANC, 0);
-			else
-				cx231xx_set_alt_setting(dev, INDEX_HANC, 0);
-
-			v4l2_fh_del(&fh->fh);
-			v4l2_fh_exit(&fh->fh);
-			kfree(fh);
-			dev->users--;
-			wake_up_interruptible(&dev->open);
-			return 0;
-		}
+	struct cx231xx *dev = video_drvdata(filp);
+	struct video_device *vdev = video_devdata(filp);
 
-	v4l2_fh_del(&fh->fh);
-	dev->users--;
-	if (!dev->users) {
-		videobuf_stop(&fh->vb_vidq);
-		videobuf_mmap_free(&fh->vb_vidq);
-
-		/* the device is already disconnect,
-		   free the remaining resources */
-		if (dev->state & DEV_DISCONNECTED) {
-			cx231xx_release_resources(dev);
-			fh->dev = NULL;
-			return 0;
-		}
+	_vb2_fop_release(filp, NULL);
 
+	if (--dev->users == 0) {
 		/* Save some power by putting tuner to sleep */
 		call_all(dev, tuner, standby);
 
@@ -1942,20 +1567,40 @@ static int cx231xx_close(struct file *filp)
 		else
 			cx231xx_uninit_bulk(dev);
 		cx231xx_set_mode(dev, CX231XX_SUSPEND);
+	}
+
+	/*
+	 * To workaround error number=-71 on EP0 for VideoGrabber,
+	 *	 need exclude following.
+	 * FIXME: It is probably safe to remove most of these, as we're
+	 * now avoiding the alternate setting for INDEX_VANC
+	 */
+	if (!dev->board.no_alt_vanc && vdev->vfl_type == VFL_TYPE_VBI) {
+		/* do this before setting alternate! */
+		cx231xx_uninit_vbi_isoc(dev);
 
 		/* set alternate 0 */
+		if (!dev->vbi_or_sliced_cc_mode)
+			cx231xx_set_alt_setting(dev, INDEX_VANC, 0);
+		else
+			cx231xx_set_alt_setting(dev, INDEX_HANC, 0);
+
+		wake_up_interruptible_nr(&dev->open, 1);
+		return 0;
+	}
+
+	if (dev->users == 0) {
+		/* set alternate 0 */
 		cx231xx_set_alt_setting(dev, INDEX_VIDEO, 0);
 	}
-	v4l2_fh_exit(&fh->fh);
-	kfree(fh);
+
 	wake_up_interruptible(&dev->open);
 	return 0;
 }
 
 static int cx231xx_v4l2_close(struct file *filp)
 {
-	struct cx231xx_fh *fh = filp->private_data;
-	struct cx231xx *dev = fh->dev;
+	struct cx231xx *dev = video_drvdata(filp);
 	int rc;
 
 	mutex_lock(&dev->lock);
@@ -1964,116 +1609,13 @@ static int cx231xx_v4l2_close(struct file *filp)
 	return rc;
 }
 
-/*
- * cx231xx_v4l2_read()
- * will allocate buffers when called for the first time
- */
-static ssize_t
-cx231xx_v4l2_read(struct file *filp, char __user *buf, size_t count,
-		  loff_t *pos)
-{
-	struct cx231xx_fh *fh = filp->private_data;
-	struct cx231xx *dev = fh->dev;
-	int rc;
-
-	rc = check_dev(dev);
-	if (rc < 0)
-		return rc;
-
-	if ((fh->type == V4L2_BUF_TYPE_VIDEO_CAPTURE) ||
-	    (fh->type == V4L2_BUF_TYPE_VBI_CAPTURE)) {
-		rc = res_get(fh);
-
-		if (unlikely(rc < 0))
-			return rc;
-
-		if (mutex_lock_interruptible(&dev->lock))
-			return -ERESTARTSYS;
-		rc = videobuf_read_stream(&fh->vb_vidq, buf, count, pos, 0,
-					    filp->f_flags & O_NONBLOCK);
-		mutex_unlock(&dev->lock);
-		return rc;
-	}
-	return 0;
-}
-
-/*
- * cx231xx_v4l2_poll()
- * will allocate buffers when called for the first time
- */
-static __poll_t cx231xx_v4l2_poll(struct file *filp, poll_table *wait)
-{
-	__poll_t req_events = poll_requested_events(wait);
-	struct cx231xx_fh *fh = filp->private_data;
-	struct cx231xx *dev = fh->dev;
-	__poll_t res = 0;
-	int rc;
-
-	rc = check_dev(dev);
-	if (rc < 0)
-		return EPOLLERR;
-
-	rc = res_get(fh);
-
-	if (unlikely(rc < 0))
-		return EPOLLERR;
-
-	if (v4l2_event_pending(&fh->fh))
-		res |= EPOLLPRI;
-	else
-		poll_wait(filp, &fh->fh.wait, wait);
-
-	if (!(req_events & (EPOLLIN | EPOLLRDNORM)))
-		return res;
-
-	if ((V4L2_BUF_TYPE_VIDEO_CAPTURE == fh->type) ||
-	    (V4L2_BUF_TYPE_VBI_CAPTURE == fh->type)) {
-		mutex_lock(&dev->lock);
-		res |= videobuf_poll_stream(filp, &fh->vb_vidq, wait);
-		mutex_unlock(&dev->lock);
-		return res;
-	}
-	return res | EPOLLERR;
-}
-
-/*
- * cx231xx_v4l2_mmap()
- */
-static int cx231xx_v4l2_mmap(struct file *filp, struct vm_area_struct *vma)
-{
-	struct cx231xx_fh *fh = filp->private_data;
-	struct cx231xx *dev = fh->dev;
-	int rc;
-
-	rc = check_dev(dev);
-	if (rc < 0)
-		return rc;
-
-	rc = res_get(fh);
-
-	if (unlikely(rc < 0))
-		return rc;
-
-	if (mutex_lock_interruptible(&dev->lock))
-		return -ERESTARTSYS;
-	rc = videobuf_mmap_mapper(&fh->vb_vidq, vma);
-	mutex_unlock(&dev->lock);
-
-	cx231xx_videodbg("vma start=0x%08lx, size=%ld, ret=%d\n",
-			 (unsigned long)vma->vm_start,
-			 (unsigned long)vma->vm_end -
-			 (unsigned long)vma->vm_start, rc);
-
-	return rc;
-}
-
 static const struct v4l2_file_operations cx231xx_v4l_fops = {
 	.owner   = THIS_MODULE,
 	.open    = cx231xx_v4l2_open,
 	.release = cx231xx_v4l2_close,
-	.read    = cx231xx_v4l2_read,
-	.poll    = cx231xx_v4l2_poll,
-	.mmap    = cx231xx_v4l2_mmap,
+	.read    = vb2_fop_read,
+	.poll    = vb2_fop_poll,
+	.mmap    = vb2_fop_mmap,
 	.unlocked_ioctl   = video_ioctl2,
 };
 
@@ -2088,17 +1630,17 @@ static const struct v4l2_ioctl_ops video_ioctl_ops = {
 	.vidioc_s_fmt_vbi_cap          = vidioc_s_fmt_vbi_cap,
 	.vidioc_g_pixelaspect          = vidioc_g_pixelaspect,
 	.vidioc_g_selection            = vidioc_g_selection,
-	.vidioc_reqbufs                = vidioc_reqbufs,
-	.vidioc_querybuf               = vidioc_querybuf,
-	.vidioc_qbuf                   = vidioc_qbuf,
-	.vidioc_dqbuf                  = vidioc_dqbuf,
+	.vidioc_reqbufs                = vb2_ioctl_reqbufs,
+	.vidioc_querybuf               = vb2_ioctl_querybuf,
+	.vidioc_qbuf                   = vb2_ioctl_qbuf,
+	.vidioc_dqbuf                  = vb2_ioctl_dqbuf,
 	.vidioc_s_std                  = vidioc_s_std,
 	.vidioc_g_std                  = vidioc_g_std,
 	.vidioc_enum_input             = cx231xx_enum_input,
 	.vidioc_g_input                = cx231xx_g_input,
 	.vidioc_s_input                = cx231xx_s_input,
-	.vidioc_streamon               = vidioc_streamon,
-	.vidioc_streamoff              = vidioc_streamoff,
+	.vidioc_streamon               = vb2_ioctl_streamon,
+	.vidioc_streamoff              = vb2_ioctl_streamoff,
 	.vidioc_g_tuner                = cx231xx_g_tuner,
 	.vidioc_s_tuner                = cx231xx_s_tuner,
 	.vidioc_g_frequency            = cx231xx_g_frequency,
@@ -2175,6 +1717,7 @@ static void cx231xx_vdev_init(struct cx231xx *dev,
 
 int cx231xx_register_analog_devices(struct cx231xx *dev)
 {
+	struct vb2_queue *q;
 	int ret;
 
 	dev_info(dev->dev, "v4l2 driver version %s\n", CX231XX_VERSION);
@@ -2221,6 +1764,21 @@ int cx231xx_register_analog_devices(struct cx231xx *dev)
 		dev_err(dev->dev, "failed to initialize video media entity!\n");
 #endif
 	dev->vdev.ctrl_handler = &dev->ctrl_handler;
+
+	q = &dev->vidq;
+	q->type = V4L2_BUF_TYPE_VIDEO_CAPTURE;
+	q->io_modes = VB2_USERPTR | VB2_MMAP | VB2_DMABUF | VB2_READ;
+	q->drv_priv = dev;
+	q->buf_struct_size = sizeof(struct cx231xx_buffer);
+	q->ops = &cx231xx_video_qops;
+	q->mem_ops = &vb2_vmalloc_memops;
+	q->timestamp_flags = V4L2_BUF_FLAG_TIMESTAMP_MONOTONIC;
+	q->min_buffers_needed = 1;
+	q->lock = &dev->lock;
+	ret = vb2_queue_init(q);
+	if (ret)
+		return ret;
+	dev->vdev.queue = q;
 	dev->vdev.device_caps = V4L2_CAP_READWRITE | V4L2_CAP_STREAMING |
 				V4L2_CAP_VIDEO_CAPTURE;
 	if (dev->tuner_type != TUNER_ABSENT)
@@ -2254,6 +1812,21 @@ int cx231xx_register_analog_devices(struct cx231xx *dev)
 		dev_err(dev->dev, "failed to initialize vbi media entity!\n");
 #endif
 	dev->vbi_dev.ctrl_handler = &dev->ctrl_handler;
+
+	q = &dev->vbiq;
+	q->type = V4L2_BUF_TYPE_VBI_CAPTURE;
+	q->io_modes = VB2_USERPTR | VB2_MMAP | VB2_DMABUF | VB2_READ;
+	q->drv_priv = dev;
+	q->buf_struct_size = sizeof(struct cx231xx_buffer);
+	q->ops = &cx231xx_vbi_qops;
+	q->mem_ops = &vb2_vmalloc_memops;
+	q->timestamp_flags = V4L2_BUF_FLAG_TIMESTAMP_MONOTONIC;
+	q->min_buffers_needed = 1;
+	q->lock = &dev->lock;
+	ret = vb2_queue_init(q);
+	if (ret)
+		return ret;
+	dev->vbi_dev.queue = q;
 	dev->vbi_dev.device_caps = V4L2_CAP_READWRITE | V4L2_CAP_STREAMING |
 				   V4L2_CAP_VBI_CAPTURE;
 	if (dev->tuner_type != TUNER_ABSENT)
diff --git a/drivers/media/usb/cx231xx/cx231xx.h b/drivers/media/usb/cx231xx/cx231xx.h
index b007611abc37..b32eab641793 100644
--- a/drivers/media/usb/cx231xx/cx231xx.h
+++ b/drivers/media/usb/cx231xx/cx231xx.h
@@ -20,7 +20,7 @@
 
 #include <media/drv-intf/cx2341x.h>
 
-#include <media/videobuf-vmalloc.h>
+#include <media/videobuf2-vmalloc.h>
 #include <media/v4l2-device.h>
 #include <media/v4l2-ctrls.h>
 #include <media/v4l2-fh.h>
@@ -223,8 +223,8 @@ struct cx231xx_fmt {
 /* buffer for one video frame */
 struct cx231xx_buffer {
 	/* common v4l buffer stuff -- must be first */
-	struct videobuf_buffer vb;
-
+	struct vb2_v4l2_buffer vb;
+	struct list_head list;
 	struct list_head frame;
 	int top_field;
 	int receiving;
@@ -237,7 +237,6 @@ enum ps_package_head {
 
 struct cx231xx_dmaqueue {
 	struct list_head active;
-	struct list_head queued;
 
 	wait_queue_head_t wq;
 
@@ -251,6 +250,7 @@ struct cx231xx_dmaqueue {
 	u32 lines_completed;
 	u8 field1_done;
 	u32 lines_per_field;
+	u32 sequence;
 
 	/*Mpeg2 control buffer*/
 	u8 *p_left_data;
@@ -427,23 +427,6 @@ struct cx231xx_audio {
 
 struct cx231xx;
 
-struct cx231xx_fh {
-	struct v4l2_fh fh;
-	struct cx231xx *dev;
-	unsigned int stream_on:1;	/* Locks streams */
-	enum v4l2_buf_type type;
-
-	struct videobuf_queue vb_vidq;
-
-	/* vbi capture */
-	struct videobuf_queue      vidq;
-	struct videobuf_queue      vbiq;
-
-	/* MPEG Encoder specifics ONLY */
-
-	atomic_t                   v4l_reading;
-};
-
 /*****************************************************************/
 /* set/get i2c */
 /* 00--1Mb/s, 01-400kb/s, 10--100kb/s, 11--5Mb/s */
@@ -634,6 +617,7 @@ struct cx231xx {
 	int width;		/* current frame width */
 	int height;		/* current frame height */
 	int interlaced;		/* 1=interlace fields, 0=just top fields */
+	unsigned int size;
 
 	struct cx231xx_audio adev;
 
@@ -657,6 +641,9 @@ struct cx231xx {
 	struct media_pad input_pad[MAX_CX231XX_INPUT];
 #endif
 
+	struct vb2_queue vidq;
+	struct vb2_queue vbiq;
+
 	unsigned char eedata[256];
 
 	struct cx231xx_video_mode video_mode;
@@ -717,6 +704,7 @@ struct cx231xx {
 	u8 USE_ISO;
 	struct cx231xx_tvnorm      encodernorm;
 	struct cx231xx_tsport      ts1, ts2;
+	struct vb2_queue	   mpegq;
 	struct video_device        v4l_device;
 	atomic_t                   v4l_reader_count;
 	u32                        freq;
diff --git a/drivers/media/usb/dvb-usb-v2/af9035.c b/drivers/media/usb/dvb-usb-v2/af9035.c
index 3afd18733614..792667ee5ebc 100644
--- a/drivers/media/usb/dvb-usb-v2/af9035.c
+++ b/drivers/media/usb/dvb-usb-v2/af9035.c
@@ -1197,6 +1197,15 @@ err:
 	return ret;
 }
 
+/*
+ * The I2C speed register is calculated with:
+ *	I2C speed register = (1000000000 / (24.4 * 16 * I2C_speed))
+ *
+ * The default speed register for it930x is 7, with means a
+ * speed of ~366 kbps
+ */
+#define I2C_SPEED_366K 7
+
 static int it930x_frontend_attach(struct dvb_usb_adapter *adap)
 {
 	struct state *state = adap_to_priv(adap);
@@ -1208,13 +1217,13 @@ static int it930x_frontend_attach(struct dvb_usb_adapter *adap)
 
 	dev_dbg(&intf->dev, "adap->id=%d\n", adap->id);
 
-	/* I2C master bus 2 clock speed 300k */
-	ret = af9035_wr_reg(d, 0x00f6a7, 0x07);
+	/* I2C master bus 2 clock speed 366k */
+	ret = af9035_wr_reg(d, 0x00f6a7, I2C_SPEED_366K);
 	if (ret < 0)
 		goto err;
 
-	/* I2C master bus 1,3 clock speed 300k */
-	ret = af9035_wr_reg(d, 0x00f103, 0x07);
+	/* I2C master bus 1,3 clock speed 366k */
+	ret = af9035_wr_reg(d, 0x00f103, I2C_SPEED_366K);
 	if (ret < 0)
 		goto err;
 
@@ -1610,6 +1619,24 @@ static int it930x_tuner_attach(struct dvb_usb_adapter *adap)
 
 	memset(&si2157_config, 0, sizeof(si2157_config));
 	si2157_config.fe = adap->fe[0];
+
+	/*
+	 * HACK: The Logilink VG0022A has a bug: when the si2157
+	 * firmware that came with the device is replaced by a new
+	 * one, the I2C transfers to the tuner will return just 0xff.
+	 *
+	 * Probably, the vendor firmware has some patch specifically
+	 * designed for this device. So, we can't replace by the
+	 * generic firmware. The right solution would be to extract
+	 * the si2157 firmware from the original driver and ask the
+	 * driver to load the specifically designed firmware, but,
+	 * while we don't have that, the next best solution is to just
+	 * keep the original firmware at the device.
+	 */
+	if (le16_to_cpu(d->udev->descriptor.idVendor) == USB_VID_DEXATEK &&
+	    le16_to_cpu(d->udev->descriptor.idProduct) == 0x0100)
+		si2157_config.dont_load_firmware = true;
+
 	si2157_config.if_port = it930x_addresses_table[state->it930x_addresses].tuner_if_port;
 	ret = af9035_add_i2c_dev(d, "si2157",
 				 it930x_addresses_table[state->it930x_addresses].tuner_i2c_addr,
@@ -2121,6 +2148,8 @@ static const struct usb_device_id af9035_id_table[] = {
 		&it930x_props, "ITE 9303 Generic", NULL) },
 	{ DVB_USB_DEVICE(USB_VID_AVERMEDIA, USB_PID_AVERMEDIA_TD310,
 		&it930x_props, "AVerMedia TD310 DVB-T2", NULL) },
+	{ DVB_USB_DEVICE(USB_VID_DEXATEK, 0x0100,
+		&it930x_props, "Logilink VG0022A", NULL) },
 	{ }
 };
 MODULE_DEVICE_TABLE(usb, af9035_id_table);
diff --git a/drivers/media/usb/dvb-usb-v2/dvb_usb.h b/drivers/media/usb/dvb-usb-v2/dvb_usb.h
index b874a49ececf..52bcc2d2efe5 100644
--- a/drivers/media/usb/dvb-usb-v2/dvb_usb.h
+++ b/drivers/media/usb/dvb-usb-v2/dvb_usb.h
@@ -121,6 +121,7 @@ struct dvb_usb_driver_info {
  * @interval: time in ms between two queries
  * @driver_type: used to point if a device supports raw mode
  * @bulk_mode: device supports bulk mode for rc (disable polling mode)
+ * @timeout: set to length of last space before raw IR goes idle
  */
 struct dvb_usb_rc {
 	const char *map_name;
@@ -130,6 +131,7 @@ struct dvb_usb_rc {
 	unsigned int interval;
 	enum rc_driver_type driver_type;
 	bool bulk_mode;
+	int timeout;
 };
 
 /**
diff --git a/drivers/media/usb/dvb-usb-v2/dvb_usb_core.c b/drivers/media/usb/dvb-usb-v2/dvb_usb_core.c
index e5e056bf9dfa..f1c79f351ec8 100644
--- a/drivers/media/usb/dvb-usb-v2/dvb_usb_core.c
+++ b/drivers/media/usb/dvb-usb-v2/dvb_usb_core.c
@@ -150,6 +150,7 @@ static int dvb_usbv2_remote_init(struct dvb_usb_device *d)
 	dev->map_name = d->rc.map_name;
 	dev->allowed_protocols = d->rc.allowed_protos;
 	dev->change_protocol = d->rc.change_protocol;
+	dev->timeout = d->rc.timeout;
 	dev->priv = d;
 
 	ret = rc_register_device(dev);
diff --git a/drivers/media/usb/dvb-usb-v2/dvbsky.c b/drivers/media/usb/dvb-usb-v2/dvbsky.c
index 617a306f6815..356fd8e66834 100644
--- a/drivers/media/usb/dvb-usb-v2/dvbsky.c
+++ b/drivers/media/usb/dvb-usb-v2/dvbsky.c
@@ -22,7 +22,6 @@ MODULE_PARM_DESC(disable_rc, "Disable inbuilt IR receiver.");
 DVB_DEFINE_MOD_OPT_ADAPTER_NR(adapter_nr);
 
 struct dvbsky_state {
-	struct mutex stream_mutex;
 	u8 ibuf[DVBSKY_BUF_LEN];
 	u8 obuf[DVBSKY_BUF_LEN];
 	u8 last_lock;
@@ -60,17 +59,19 @@ static int dvbsky_usb_generic_rw(struct dvb_usb_device *d,
 static int dvbsky_stream_ctrl(struct dvb_usb_device *d, u8 onoff)
 {
 	struct dvbsky_state *state = d_to_priv(d);
+	static const u8 obuf_pre[3] = { 0x37, 0, 0 };
+	static const u8 obuf_post[3] = { 0x36, 3, 0 };
 	int ret;
-	u8 obuf_pre[3] = { 0x37, 0, 0 };
-	u8 obuf_post[3] = { 0x36, 3, 0 };
 
-	mutex_lock(&state->stream_mutex);
-	ret = dvbsky_usb_generic_rw(d, obuf_pre, 3, NULL, 0);
+	mutex_lock(&d->usb_mutex);
+	memcpy(state->obuf, obuf_pre, 3);
+	ret = dvb_usbv2_generic_write_locked(d, state->obuf, 3);
 	if (!ret && onoff) {
 		msleep(20);
-		ret = dvbsky_usb_generic_rw(d, obuf_post, 3, NULL, 0);
+		memcpy(state->obuf, obuf_post, 3);
+		ret = dvb_usbv2_generic_write_locked(d, state->obuf, 3);
 	}
-	mutex_unlock(&state->stream_mutex);
+	mutex_unlock(&d->usb_mutex);
 	return ret;
 }
 
@@ -591,17 +592,7 @@ static int dvbsky_identify_state(struct dvb_usb_device *d, const char **name)
 static int dvbsky_init(struct dvb_usb_device *d)
 {
 	struct dvbsky_state *state = d_to_priv(d);
-
-	/* use default interface */
-	/*
-	ret = usb_set_interface(d->udev, 0, 0);
-	if (ret)
-		return ret;
-	*/
-	mutex_init(&state->stream_mutex);
-
 	state->last_lock = 0;
-
 	return 0;
 }
 
@@ -792,6 +783,9 @@ static const struct usb_device_id dvbsky_id_table[] = {
 	{ DVB_USB_DEVICE(USB_VID_CONEXANT, USB_PID_MYGICA_T230C,
 		&mygica_t230c_props, "MyGica Mini DVB-T2 USB Stick T230C",
 		RC_MAP_TOTAL_MEDIA_IN_HAND_02) },
+	{ DVB_USB_DEVICE(USB_VID_CONEXANT, USB_PID_MYGICA_T230C_LITE,
+		&mygica_t230c_props, "MyGica Mini DVB-T2 USB Stick T230C Lite",
+		NULL) },
 	{ DVB_USB_DEVICE(USB_VID_CONEXANT, USB_PID_MYGICA_T230C2,
 		&mygica_t230c_props, "MyGica Mini DVB-T2 USB Stick T230C v2",
 		RC_MAP_TOTAL_MEDIA_IN_HAND_02) },
diff --git a/drivers/media/usb/dvb-usb-v2/gl861.c b/drivers/media/usb/dvb-usb-v2/gl861.c
index c7197e534c02..19217dcf20f1 100644
--- a/drivers/media/usb/dvb-usb-v2/gl861.c
+++ b/drivers/media/usb/dvb-usb-v2/gl861.c
@@ -5,7 +5,7 @@
  */
 #include <linux/string.h>
 
-#include "gl861.h"
+#include "dvb_usb.h"
 
 #include "zl10353.h"
 #include "qt1010.h"
@@ -14,93 +14,157 @@
 
 DVB_DEFINE_MOD_OPT_ADAPTER_NR(adapter_nr);
 
-static int gl861_i2c_msg(struct dvb_usb_device *d, u8 addr,
-			 u8 *wbuf, u16 wlen, u8 *rbuf, u16 rlen)
-{
-	u16 index;
-	u16 value = addr << (8 + 1);
-	int wo = (rbuf == NULL || rlen == 0); /* write-only */
-	u8 req, type;
-	u8 *buf;
-	int ret;
+struct gl861 {
+	/* USB control message buffer */
+	u8 buf[16];
 
-	if (wo) {
-		req = GL861_REQ_I2C_WRITE;
-		type = GL861_WRITE;
-		buf = kmemdup(wbuf, wlen, GFP_KERNEL);
-	} else { /* rw */
-		req = GL861_REQ_I2C_READ;
-		type = GL861_READ;
-		buf = kmalloc(rlen, GFP_KERNEL);
-	}
-	if (!buf)
-		return -ENOMEM;
+	struct i2c_adapter *demod_sub_i2c;
+	struct i2c_client  *i2c_client_demod;
+	struct i2c_client  *i2c_client_tuner;
+};
 
-	switch (wlen) {
-	case 1:
-		index = wbuf[0];
+#define CMD_WRITE_SHORT     0x01
+#define CMD_READ            0x02
+#define CMD_WRITE           0x03
+
+static int gl861_ctrl_msg(struct dvb_usb_device *d, u8 request, u16 value,
+			  u16 index, void *data, u16 size)
+{
+	struct gl861 *ctx = d_to_priv(d);
+	struct usb_interface *intf = d->intf;
+	int ret;
+	unsigned int pipe;
+	u8 requesttype;
+
+	mutex_lock(&d->usb_mutex);
+
+	switch (request) {
+	case CMD_WRITE:
+		memcpy(ctx->buf, data, size);
+		/* Fall through */
+	case CMD_WRITE_SHORT:
+		pipe = usb_sndctrlpipe(d->udev, 0);
+		requesttype = USB_TYPE_VENDOR | USB_DIR_OUT;
 		break;
-	case 2:
-		index = wbuf[0];
-		value = value + wbuf[1];
+	case CMD_READ:
+		pipe = usb_rcvctrlpipe(d->udev, 0);
+		requesttype = USB_TYPE_VENDOR | USB_DIR_IN;
 		break;
 	default:
-		dev_err(&d->udev->dev, "%s: wlen=%d, aborting\n",
-				KBUILD_MODNAME, wlen);
-		kfree(buf);
-		return -EINVAL;
+		ret = -EINVAL;
+		goto err_mutex_unlock;
 	}
 
-	usleep_range(1000, 2000); /* avoid I2C errors */
+	ret = usb_control_msg(d->udev, pipe, request, requesttype, value,
+			      index, ctx->buf, size, 200);
+	dev_dbg(&intf->dev, "%d | %02x %02x %*ph %*ph %*ph %s %*ph\n",
+		ret, requesttype, request, 2, &value, 2, &index, 2, &size,
+		(requesttype & USB_DIR_IN) ? "<<<" : ">>>", size, ctx->buf);
+	if (ret < 0)
+		goto err_mutex_unlock;
 
-	ret = usb_control_msg(d->udev, usb_rcvctrlpipe(d->udev, 0), req, type,
-			      value, index, buf, rlen, 2000);
+	if (request == CMD_READ)
+		memcpy(data, ctx->buf, size);
 
-	if (!wo && ret > 0)
-		memcpy(rbuf, buf, rlen);
+	usleep_range(1000, 2000); /* Avoid I2C errors */
 
-	kfree(buf);
+	mutex_unlock(&d->usb_mutex);
+
+	return 0;
+
+err_mutex_unlock:
+	mutex_unlock(&d->usb_mutex);
+	dev_dbg(&intf->dev, "failed %d\n", ret);
 	return ret;
 }
 
-/* I2C */
-static int gl861_i2c_xfer(struct i2c_adapter *adap, struct i2c_msg msg[],
-			  int num)
+static int gl861_short_write(struct dvb_usb_device *d, u8 addr, u8 reg, u8 val)
+{
+	return gl861_ctrl_msg(d, CMD_WRITE_SHORT,
+			      (addr << 9) | val, reg, NULL, 0);
+}
+
+static int gl861_i2c_master_xfer(struct i2c_adapter *adap, struct i2c_msg msg[],
+				 int num)
 {
 	struct dvb_usb_device *d = i2c_get_adapdata(adap);
-	int i;
+	struct usb_interface *intf = d->intf;
+	struct gl861 *ctx = d_to_priv(d);
+	int ret;
+	u8 request, *data;
+	u16 value, index, size;
+
+	/* XXX: I2C adapter maximum data lengths are not tested */
+	if (num == 1 && !(msg[0].flags & I2C_M_RD)) {
+		/* I2C write */
+		if (msg[0].len < 2 || msg[0].len > sizeof(ctx->buf)) {
+			ret = -EOPNOTSUPP;
+			goto err;
+		}
+
+		value = (msg[0].addr << 1) << 8;
+		index = msg[0].buf[0];
+
+		if (msg[0].len == 2) {
+			request = CMD_WRITE_SHORT;
+			value |= msg[0].buf[1];
+			size = 0;
+			data = NULL;
+		} else {
+			request = CMD_WRITE;
+			size = msg[0].len - 1;
+			data = &msg[0].buf[1];
+		}
+
+		ret = gl861_ctrl_msg(d, request, value, index, data, size);
+	} else if (num == 2 && !(msg[0].flags & I2C_M_RD) &&
+		   (msg[1].flags & I2C_M_RD)) {
+		/* I2C write + read */
+		if (msg[0].len > 1 || msg[1].len > sizeof(ctx->buf)) {
+			ret = -EOPNOTSUPP;
+			goto err;
+		}
 
-	if (num > 2)
-		return -EINVAL;
-
-	if (mutex_lock_interruptible(&d->i2c_mutex) < 0)
-		return -EAGAIN;
-
-	for (i = 0; i < num; i++) {
-		/* write/read request */
-		if (i+1 < num && (msg[i+1].flags & I2C_M_RD)) {
-			if (gl861_i2c_msg(d, msg[i].addr, msg[i].buf,
-				msg[i].len, msg[i+1].buf, msg[i+1].len) < 0)
-				break;
-			i++;
-		} else
-			if (gl861_i2c_msg(d, msg[i].addr, msg[i].buf,
-					  msg[i].len, NULL, 0) < 0)
-				break;
+		value = (msg[0].addr << 1) << 8;
+		index = msg[0].buf[0];
+		request = CMD_READ;
+
+		ret = gl861_ctrl_msg(d, request, value, index,
+				     msg[1].buf, msg[1].len);
+	} else if (num == 1 && (msg[0].flags & I2C_M_RD)) {
+		/* I2C read */
+		if (msg[0].len > sizeof(ctx->buf)) {
+			ret = -EOPNOTSUPP;
+			goto err;
+		}
+		value = (msg[0].addr << 1) << 8;
+		index = 0x0100;
+		request = CMD_READ;
+
+		ret = gl861_ctrl_msg(d, request, value, index,
+				     msg[0].buf, msg[0].len);
+	} else {
+		/* Unsupported I2C message */
+		dev_dbg(&intf->dev, "unknown i2c msg, num %u\n", num);
+		ret = -EOPNOTSUPP;
 	}
+	if (ret)
+		goto err;
 
-	mutex_unlock(&d->i2c_mutex);
-	return i;
+	return num;
+err:
+	dev_dbg(&intf->dev, "failed %d\n", ret);
+	return ret;
 }
 
-static u32 gl861_i2c_func(struct i2c_adapter *adapter)
+static u32 gl861_i2c_functionality(struct i2c_adapter *adapter)
 {
 	return I2C_FUNC_I2C;
 }
 
 static struct i2c_algorithm gl861_i2c_algo = {
-	.master_xfer   = gl861_i2c_xfer,
-	.functionality = gl861_i2c_func,
+	.master_xfer   = gl861_i2c_master_xfer,
+	.functionality = gl861_i2c_functionality,
 };
 
 /* Callbacks for DVB USB */
@@ -149,6 +213,8 @@ static struct dvb_usb_device_properties gl861_props = {
 	.owner = THIS_MODULE,
 	.adapter_nr = adapter_nr,
 
+	.size_of_priv = sizeof(struct gl861),
+
 	.i2c_algo = &gl861_i2c_algo,
 	.frontend_attach = gl861_frontend_attach,
 	.tuner_attach = gl861_tuner_attach,
@@ -166,14 +232,6 @@ static struct dvb_usb_device_properties gl861_props = {
 /*
  * For Friio
  */
-
-struct friio_priv {
-	struct i2c_adapter *demod_sub_i2c;
-	struct i2c_client  *i2c_client_demod;
-	struct i2c_client  *i2c_client_tuner;
-	struct i2c_adapter tuner_adap;
-};
-
 struct friio_config {
 	struct i2c_board_info demod_info;
 	struct tc90522_config demod_cfg;
@@ -184,132 +242,10 @@ struct friio_config {
 
 static const struct friio_config friio_config = {
 	.demod_info = { I2C_BOARD_INFO(TC90522_I2C_DEV_TER, 0x18), },
+	.demod_cfg = { .split_tuner_read_i2c = true, },
 	.tuner_info = { I2C_BOARD_INFO("tua6034_friio", 0x60), },
 };
 
-/* For another type of I2C:
- * message sent by a USB control-read/write transaction with data stage.
- * Used in init/config of Friio.
- */
-static int
-gl861_i2c_write_ex(struct dvb_usb_device *d, u8 addr, u8 *wbuf, u16 wlen)
-{
-	u8 *buf;
-	int ret;
-
-	buf = kmemdup(wbuf, wlen, GFP_KERNEL);
-	if (!buf)
-		return -ENOMEM;
-
-	ret = usb_control_msg(d->udev, usb_sndctrlpipe(d->udev, 0),
-				 GL861_REQ_I2C_RAW, GL861_WRITE,
-				 addr << (8 + 1), 0x0100, buf, wlen, 2000);
-	kfree(buf);
-	return ret;
-}
-
-static int
-gl861_i2c_read_ex(struct dvb_usb_device *d, u8 addr, u8 *rbuf, u16 rlen)
-{
-	u8 *buf;
-	int ret;
-
-	buf = kmalloc(rlen, GFP_KERNEL);
-	if (!buf)
-		return -ENOMEM;
-
-	ret = usb_control_msg(d->udev, usb_rcvctrlpipe(d->udev, 0),
-				 GL861_REQ_I2C_READ, GL861_READ,
-				 addr << (8 + 1), 0x0100, buf, rlen, 2000);
-	if (ret > 0 && rlen > 0)
-		memcpy(buf, rbuf, rlen);
-	kfree(buf);
-	return ret;
-}
-
-/* For I2C transactions to the tuner of Friio (dvb_pll).
- *
- * Friio uses irregular USB encapsulation for tuner i2c transactions:
- * write transacions are encapsulated with a different USB 'request' value.
- *
- * Although all transactions are sent via the demod(tc90522)
- * and the demod provides an i2c adapter for them, it cannot be used in Friio
- * since it assumes using the same parent adapter with the demod,
- * which does not use the request value and uses same one for both read/write.
- * So we define a dedicated i2c adapter here.
- */
-
-static int
-friio_i2c_tuner_read(struct dvb_usb_device *d, struct i2c_msg *msg)
-{
-	struct friio_priv *priv;
-	u8 addr;
-
-	priv = d_to_priv(d);
-	addr = priv->i2c_client_demod->addr;
-	return gl861_i2c_read_ex(d, addr, msg->buf, msg->len);
-}
-
-static int
-friio_i2c_tuner_write(struct dvb_usb_device *d, struct i2c_msg *msg)
-{
-	u8 *buf;
-	int ret;
-	struct friio_priv *priv;
-
-	priv = d_to_priv(d);
-
-	if (msg->len < 1)
-		return -EINVAL;
-
-	buf = kmalloc(msg->len + 1, GFP_KERNEL);
-	if (!buf)
-		return -ENOMEM;
-	buf[0] = msg->addr << 1;
-	memcpy(buf + 1, msg->buf, msg->len);
-
-	ret = usb_control_msg(d->udev, usb_sndctrlpipe(d->udev, 0),
-				 GL861_REQ_I2C_RAW, GL861_WRITE,
-				 priv->i2c_client_demod->addr << (8 + 1),
-				 0xFE, buf, msg->len + 1, 2000);
-	kfree(buf);
-	return ret;
-}
-
-static int friio_tuner_i2c_xfer(struct i2c_adapter *adap, struct i2c_msg msg[],
-				int num)
-{
-	struct dvb_usb_device *d = i2c_get_adapdata(adap);
-	int i;
-
-	if (num > 2)
-		return -EINVAL;
-
-	if (mutex_lock_interruptible(&d->i2c_mutex) < 0)
-		return -EAGAIN;
-
-	for (i = 0; i < num; i++) {
-		int ret;
-
-		if (msg[i].flags & I2C_M_RD)
-			ret = friio_i2c_tuner_read(d, &msg[i]);
-		else
-			ret = friio_i2c_tuner_write(d, &msg[i]);
-
-		if (ret < 0)
-			break;
-
-		usleep_range(1000, 2000); /* avoid I2C errors */
-	}
-
-	mutex_unlock(&d->i2c_mutex);
-	return i;
-}
-
-static struct i2c_algorithm friio_tuner_i2c_algo = {
-	.master_xfer   = friio_tuner_i2c_xfer,
-	.functionality = gl861_i2c_func,
-};
 
 /* GPIO control in Friio */
 
@@ -377,9 +313,11 @@ static int friio_ext_ctl(struct dvb_usb_device *d,
 /* init/config of gl861 for Friio */
 /* NOTE:
  * This function cannot be moved to friio_init()/dvb_usbv2_init(),
- * because the init defined here must be done before any activities like I2C,
+ * because the init defined here includes a whole device reset,
+ * it must be run early before any activities like I2C,
  * but friio_init() is called by dvb-usbv2 after {_frontend, _tuner}_attach(),
  * where I2C communication is used.
+ * In addition, this reset is required in reset_resume() as well.
  * Thus this function is set to be called from _power_ctl().
  *
  * Since it will be called on the early init stage
@@ -389,7 +327,7 @@ static int friio_ext_ctl(struct dvb_usb_device *d,
 static int friio_reset(struct dvb_usb_device *d)
 {
 	int i, ret;
-	u8 wbuf[2], rbuf[2];
+	u8 wbuf[1], rbuf[2];
 
 	static const u8 friio_init_cmds[][2] = {
 		{0x33, 0x08}, {0x37, 0x40}, {0x3a, 0x1f}, {0x3b, 0xff},
@@ -401,16 +339,12 @@ static int friio_reset(struct dvb_usb_device *d)
 	if (ret < 0)
 		return ret;
 
-	wbuf[0] = 0x11;
-	wbuf[1] = 0x02;
-	ret = gl861_i2c_msg(d, 0x00, wbuf, 2, NULL, 0);
+	ret = gl861_short_write(d, 0x00, 0x11, 0x02);
 	if (ret < 0)
 		return ret;
 	usleep_range(2000, 3000);
 
-	wbuf[0] = 0x11;
-	wbuf[1] = 0x00;
-	ret = gl861_i2c_msg(d, 0x00, wbuf, 2, NULL, 0);
+	ret = gl861_short_write(d, 0x00, 0x11, 0x00);
 	if (ret < 0)
 		return ret;
 
@@ -420,14 +354,13 @@ static int friio_reset(struct dvb_usb_device *d)
 	 */
 
 	usleep_range(1000, 2000);
-	wbuf[0] = 0x03;
-	wbuf[1] = 0x80;
-	ret = gl861_i2c_write_ex(d, 0x09, wbuf, 2);
+	wbuf[0] = 0x80;
+	ret = gl861_ctrl_msg(d, CMD_WRITE, 0x09 << 9, 0x03, wbuf, 1);
 	if (ret < 0)
 		return ret;
 
 	usleep_range(2000, 3000);
-	ret = gl861_i2c_read_ex(d, 0x09, rbuf, 2);
+	ret = gl861_ctrl_msg(d, CMD_READ, 0x09 << 9, 0x0100, rbuf, 2);
 	if (ret < 0)
 		return ret;
 	if (rbuf[0] != 0xff || rbuf[1] != 0xff)
@@ -435,38 +368,33 @@ static int friio_reset(struct dvb_usb_device *d)
 
 
 	usleep_range(1000, 2000);
-	ret = gl861_i2c_write_ex(d, 0x48, wbuf, 2);
+	wbuf[0] = 0x80;
+	ret = gl861_ctrl_msg(d, CMD_WRITE, 0x48 << 9, 0x03, wbuf, 1);
 	if (ret < 0)
 		return ret;
 
 	usleep_range(2000, 3000);
-	ret = gl861_i2c_read_ex(d, 0x48, rbuf, 2);
+	ret = gl861_ctrl_msg(d, CMD_READ, 0x48 << 9, 0x0100, rbuf, 2);
 	if (ret < 0)
 		return ret;
 	if (rbuf[0] != 0xff || rbuf[1] != 0xff)
 		return -ENODEV;
 
-	wbuf[0] = 0x30;
-	wbuf[1] = 0x04;
-	ret = gl861_i2c_msg(d, 0x00, wbuf, 2, NULL, 0);
+	ret = gl861_short_write(d, 0x00, 0x30, 0x04);
 	if (ret < 0)
 		return ret;
 
-	wbuf[0] = 0x00;
-	wbuf[1] = 0x01;
-	ret = gl861_i2c_msg(d, 0x00, wbuf, 2, NULL, 0);
+	ret = gl861_short_write(d, 0x00, 0x00, 0x01);
 	if (ret < 0)
 		return ret;
 
-	wbuf[0] = 0x06;
-	wbuf[1] = 0x0f;
-	ret = gl861_i2c_msg(d, 0x00, wbuf, 2, NULL, 0);
+	ret = gl861_short_write(d, 0x00, 0x06, 0x0f);
 	if (ret < 0)
 		return ret;
 
 	for (i = 0; i < ARRAY_SIZE(friio_init_cmds); i++) {
-		ret = gl861_i2c_msg(d, 0x00, (u8 *)friio_init_cmds[i], 2,
-				      NULL, 0);
+		ret = gl861_short_write(d, 0x00, friio_init_cmds[i][0],
+					friio_init_cmds[i][1]);
 		if (ret < 0)
 			return ret;
 	}
@@ -488,9 +416,10 @@ static int friio_frontend_attach(struct dvb_usb_adapter *adap)
 	struct dvb_usb_device *d;
 	struct tc90522_config cfg;
 	struct i2c_client *cl;
-	struct friio_priv *priv;
+	struct gl861 *priv;
 
 	info = &friio_config.demod_info;
+	cfg = friio_config.demod_cfg;
 	d = adap_to_d(adap);
 	cl = dvb_module_probe("tc90522", info->type,
 			      &d->i2c_adap, info->addr, &cfg);
@@ -498,25 +427,17 @@ static int friio_frontend_attach(struct dvb_usb_adapter *adap)
 		return -ENODEV;
 	adap->fe[0] = cfg.fe;
 
-	/* ignore cfg.tuner_i2c and create new one */
 	priv = adap_to_priv(adap);
 	priv->i2c_client_demod = cl;
-	priv->tuner_adap.algo = &friio_tuner_i2c_algo;
-	priv->tuner_adap.dev.parent = &d->udev->dev;
-	strscpy(priv->tuner_adap.name, d->name, sizeof(priv->tuner_adap.name));
-	strlcat(priv->tuner_adap.name, "-tuner", sizeof(priv->tuner_adap.name));
-	priv->demod_sub_i2c = &priv->tuner_adap;
-	i2c_set_adapdata(&priv->tuner_adap, d);
-
-	return i2c_add_adapter(&priv->tuner_adap);
+	priv->demod_sub_i2c = cfg.tuner_i2c;
+	return 0;
 }
 
 static int friio_frontend_detach(struct dvb_usb_adapter *adap)
 {
-	struct friio_priv *priv;
+	struct gl861 *priv;
 
 	priv = adap_to_priv(adap);
-	i2c_del_adapter(&priv->tuner_adap);
 	dvb_module_release(priv->i2c_client_demod);
 	return 0;
 }
@@ -526,7 +447,7 @@ static int friio_tuner_attach(struct dvb_usb_adapter *adap)
 	const struct i2c_board_info *info;
 	struct dvb_pll_config cfg;
 	struct i2c_client *cl;
-	struct friio_priv *priv;
+	struct gl861 *priv;
 
 	priv = adap_to_priv(adap);
 	info = &friio_config.tuner_info;
@@ -543,7 +464,7 @@ static int friio_tuner_attach(struct dvb_usb_adapter *adap)
 
 static int friio_tuner_detach(struct dvb_usb_adapter *adap)
 {
-	struct friio_priv *priv;
+	struct gl861 *priv;
 
 	priv = adap_to_priv(adap);
 	dvb_module_release(priv->i2c_client_tuner);
@@ -554,7 +475,7 @@ static int friio_init(struct dvb_usb_device *d)
 {
 	int i;
 	int ret;
-	struct friio_priv *priv;
+	struct gl861 *priv;
 
 	static const u8 demod_init[][2] = {
 		{0x01, 0x40}, {0x04, 0x38}, {0x05, 0x40}, {0x07, 0x40},
@@ -606,7 +527,7 @@ static struct dvb_usb_device_properties friio_props = {
 	.owner = THIS_MODULE,
 	.adapter_nr = adapter_nr,
 
-	.size_of_priv = sizeof(struct friio_priv),
+	.size_of_priv = sizeof(struct gl861),
 
 	.i2c_algo = &gl861_i2c_algo,
 	.power_ctrl = friio_power_ctrl,
diff --git a/drivers/media/usb/dvb-usb-v2/gl861.h b/drivers/media/usb/dvb-usb-v2/gl861.h
deleted file mode 100644
index 02c00e10748a..000000000000
--- a/drivers/media/usb/dvb-usb-v2/gl861.h
+++ /dev/null
@@ -1,14 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _DVB_USB_GL861_H_
-#define _DVB_USB_GL861_H_
-
-#include "dvb_usb.h"
-
-#define GL861_WRITE		0x40
-#define GL861_READ		0xc0
-
-#define GL861_REQ_I2C_WRITE	0x01
-#define GL861_REQ_I2C_READ	0x02
-#define GL861_REQ_I2C_RAW	0x03
-
-#endif
diff --git a/drivers/media/usb/dvb-usb-v2/rtl28xxu.c b/drivers/media/usb/dvb-usb-v2/rtl28xxu.c
index 1a36bda28542..5016ede7b35f 100644
--- a/drivers/media/usb/dvb-usb-v2/rtl28xxu.c
+++ b/drivers/media/usb/dvb-usb-v2/rtl28xxu.c
@@ -1781,7 +1781,6 @@ static int rtl2832u_rc_query(struct dvb_usb_device *d)
 	}
 
 	/* 'flush' ir_raw_event_store_with_filter() */
-	ir_raw_event_set_idle(d->rc_dev, true);
 	ir_raw_event_handle(d->rc_dev);
 exit:
 	return ret;
@@ -1804,6 +1803,8 @@ static int rtl2832u_get_rc_config(struct dvb_usb_device *d,
 	rc->driver_type = RC_DRIVER_IR_RAW;
 	rc->query = rtl2832u_rc_query;
 	rc->interval = 200;
+	/* we program idle len to 0xc0, set timeout to one less */
+	rc->timeout = 0xbf * 50800;
 
 	return 0;
 }
@@ -1957,7 +1958,8 @@ static const struct usb_device_id rtl28xxu_id_table[] = {
 
 	/* RTL2832P devices: */
 	{ DVB_USB_DEVICE(USB_VID_HANFTEK, 0x0131,
-		&rtl28xxu_props, "Astrometa DVB-T2", NULL) },
+		&rtl28xxu_props, "Astrometa DVB-T2",
+		RC_MAP_ASTROMETA_T2HYBRID) },
 	{ DVB_USB_DEVICE(0x5654, 0xca42,
 		&rtl28xxu_props, "GoTView MasterHD 3", NULL) },
 	{ }
diff --git a/drivers/media/usb/dvb-usb/af9005.c b/drivers/media/usb/dvb-usb/af9005.c
index 02697d86e8c1..ac93e88d7038 100644
--- a/drivers/media/usb/dvb-usb/af9005.c
+++ b/drivers/media/usb/dvb-usb/af9005.c
@@ -976,8 +976,9 @@ static int af9005_identify_state(struct usb_device *udev,
 	else if (reply == 0x02)
 		*cold = 0;
 	else
-		return -EIO;
-	deb_info("Identify state cold = %d\n", *cold);
+		ret = -EIO;
+	if (!ret)
+		deb_info("Identify state cold = %d\n", *cold);
 
 err:
 	kfree(buf);
diff --git a/drivers/media/usb/dvb-usb/cxusb.c b/drivers/media/usb/dvb-usb/cxusb.c
index f02fa0a67aa4..fac19ec46089 100644
--- a/drivers/media/usb/dvb-usb/cxusb.c
+++ b/drivers/media/usb/dvb-usb/cxusb.c
@@ -521,7 +521,8 @@ static int cxusb_rc_query(struct dvb_usb_device *d)
 {
 	u8 ircode[4];
 
-	cxusb_ctrl_msg(d, CMD_GET_IR_CODE, NULL, 0, ircode, 4);
+	if (cxusb_ctrl_msg(d, CMD_GET_IR_CODE, NULL, 0, ircode, 4) < 0)
+		return 0;
 
 	if (ircode[2] || ircode[3])
 		rc_keydown(d->rc_dev, RC_PROTO_NEC,
diff --git a/drivers/media/usb/em28xx/em28xx-audio.c b/drivers/media/usb/em28xx/em28xx-audio.c
index 49c9b70b632b..79dfbb25714b 100644
--- a/drivers/media/usb/em28xx/em28xx-audio.c
+++ b/drivers/media/usb/em28xx/em28xx-audio.c
@@ -31,7 +31,6 @@
 #include <linux/soundcard.h>
 #include <linux/slab.h>
 #include <linux/vmalloc.h>
-#include <linux/proc_fs.h>
 #include <linux/module.h>
 #include <sound/core.h>
 #include <sound/pcm.h>
diff --git a/drivers/media/usb/em28xx/em28xx-cards.c b/drivers/media/usb/em28xx/em28xx-cards.c
index 5983e72a0622..def9cdd931a9 100644
--- a/drivers/media/usb/em28xx/em28xx-cards.c
+++ b/drivers/media/usb/em28xx/em28xx-cards.c
@@ -2487,6 +2487,24 @@ const struct em28xx_board em28xx_boards[] = {
 		.ir_codes      = RC_MAP_HAUPPAUGE,
 		.leds          = hauppauge_dualhd_leds,
 	},
+	/*
+	 * 1b80:e349 Magix USB Videowandler-2
+	 * (same chips as Honestech VIDBOX NW03)
+	 * Empia EM2860, Philips SAA7113, Empia EMP202, No Tuner
+	 */
+	[EM2861_BOARD_MAGIX_VIDEOWANDLER2] = {
+		.name                = "Magix USB Videowandler-2",
+		.tuner_type          = TUNER_ABSENT,
+		.decoder             = EM28XX_SAA711X,
+		.input               = { {
+			.type     = EM28XX_VMUX_COMPOSITE,
+			.vmux     = SAA7115_COMPOSITE0,
+			.amux     = EM28XX_AMUX_LINE_IN,
+		}, {
+			.type     = EM28XX_VMUX_SVIDEO,
+			.amux     = EM28XX_AMUX_LINE_IN,
+		} },
+	},
 };
 EXPORT_SYMBOL_GPL(em28xx_boards);
 
@@ -2696,6 +2714,8 @@ struct usb_device_id em28xx_id_table[] = {
 			.driver_info = EM28178_BOARD_PLEX_PX_BCUD },
 	{ USB_DEVICE(0xeb1a, 0x5051), /* Ion Video 2 PC MKII / Startech svid2usb23 / Raygo R12-41373 */
 			.driver_info = EM2860_BOARD_TVP5150_REFERENCE_DESIGN },
+	{ USB_DEVICE(0x1b80, 0xe349), /* Magix USB Videowandler-2 */
+		.driver_info = EM2861_BOARD_MAGIX_VIDEOWANDLER2 },
 	{ },
 };
 MODULE_DEVICE_TABLE(usb, em28xx_id_table);
diff --git a/drivers/media/usb/em28xx/em28xx-dvb.c b/drivers/media/usb/em28xx/em28xx-dvb.c
index a73faf12f7e4..0ab6c493bc74 100644
--- a/drivers/media/usb/em28xx/em28xx-dvb.c
+++ b/drivers/media/usb/em28xx/em28xx-dvb.c
@@ -471,13 +471,13 @@ static void hauppauge_hvr930c_init(struct em28xx *dev)
 {
 	int i;
 
-	struct em28xx_reg_seq hauppauge_hvr930c_init[] = {
+	static const struct em28xx_reg_seq hauppauge_hvr930c_init[] = {
 		{EM2874_R80_GPIO_P0_CTRL,	0xff,	0xff,	0x65},
 		{EM2874_R80_GPIO_P0_CTRL,	0xfb,	0xff,	0x32},
 		{EM2874_R80_GPIO_P0_CTRL,	0xff,	0xff,	0xb8},
 		{	-1,			-1,	-1,	-1},
 	};
-	struct em28xx_reg_seq hauppauge_hvr930c_end[] = {
+	static const struct em28xx_reg_seq hauppauge_hvr930c_end[] = {
 		{EM2874_R80_GPIO_P0_CTRL,	0xef,	0xff,	0x01},
 		{EM2874_R80_GPIO_P0_CTRL,	0xaf,	0xff,	0x65},
 		{EM2874_R80_GPIO_P0_CTRL,	0xef,	0xff,	0x76},
@@ -493,7 +493,7 @@ static void hauppauge_hvr930c_init(struct em28xx *dev)
 		{	-1,			-1,	-1,	-1},
 	};
 
-	struct {
+	static const struct {
 		unsigned char r[4];
 		int len;
 	} regs[] = {
@@ -537,20 +537,20 @@ static void hauppauge_hvr930c_init(struct em28xx *dev)
 static void terratec_h5_init(struct em28xx *dev)
 {
 	int i;
-	struct em28xx_reg_seq terratec_h5_init[] = {
+	static const struct em28xx_reg_seq terratec_h5_init[] = {
 		{EM2820_R08_GPIO_CTRL,		0xff,	0xff,	10},
 		{EM2874_R80_GPIO_P0_CTRL,	0xf6,	0xff,	100},
 		{EM2874_R80_GPIO_P0_CTRL,	0xf2,	0xff,	50},
 		{EM2874_R80_GPIO_P0_CTRL,	0xf6,	0xff,	100},
 		{	-1,			-1,	-1,	-1},
 	};
-	struct em28xx_reg_seq terratec_h5_end[] = {
+	static const struct em28xx_reg_seq terratec_h5_end[] = {
 		{EM2874_R80_GPIO_P0_CTRL,	0xe6,	0xff,	100},
 		{EM2874_R80_GPIO_P0_CTRL,	0xa6,	0xff,	50},
 		{EM2874_R80_GPIO_P0_CTRL,	0xe6,	0xff,	100},
 		{	-1,			-1,	-1,	-1},
 	};
-	struct {
+	static const struct {
 		unsigned char r[4];
 		int len;
 	} regs[] = {
@@ -594,14 +594,14 @@ static void terratec_htc_stick_init(struct em28xx *dev)
 	 * 0xe6: unknown (does not affect DVB-T).
 	 * 0xb6: unknown (does not affect DVB-T).
 	 */
-	struct em28xx_reg_seq terratec_htc_stick_init[] = {
+	static const struct em28xx_reg_seq terratec_htc_stick_init[] = {
 		{EM2820_R08_GPIO_CTRL,		0xff,	0xff,	10},
 		{EM2874_R80_GPIO_P0_CTRL,	0xf6,	0xff,	100},
 		{EM2874_R80_GPIO_P0_CTRL,	0xe6,	0xff,	50},
 		{EM2874_R80_GPIO_P0_CTRL,	0xf6,	0xff,	100},
 		{	-1,			-1,	-1,	-1},
 	};
-	struct em28xx_reg_seq terratec_htc_stick_end[] = {
+	static const struct em28xx_reg_seq terratec_htc_stick_end[] = {
 		{EM2874_R80_GPIO_P0_CTRL,	0xb6,	0xff,	100},
 		{EM2874_R80_GPIO_P0_CTRL,	0xf6,	0xff,	50},
 		{	-1,			-1,	-1,	-1},
@@ -611,7 +611,7 @@ static void terratec_htc_stick_init(struct em28xx *dev)
 	 * Init the analog decoder (not yet supported), but
 	 * it's probably still a good idea.
 	 */
-	struct {
+	static const struct {
 		unsigned char r[4];
 		int len;
 	} regs[] = {
@@ -642,14 +642,14 @@ static void terratec_htc_usb_xs_init(struct em28xx *dev)
 {
 	int i;
 
-	struct em28xx_reg_seq terratec_htc_usb_xs_init[] = {
+	static const struct em28xx_reg_seq terratec_htc_usb_xs_init[] = {
 		{EM2820_R08_GPIO_CTRL,		0xff,	0xff,	10},
 		{EM2874_R80_GPIO_P0_CTRL,	0xb2,	0xff,	100},
 		{EM2874_R80_GPIO_P0_CTRL,	0xb2,	0xff,	50},
 		{EM2874_R80_GPIO_P0_CTRL,	0xb6,	0xff,	100},
 		{	-1,			-1,	-1,	-1},
 	};
-	struct em28xx_reg_seq terratec_htc_usb_xs_end[] = {
+	static const struct em28xx_reg_seq terratec_htc_usb_xs_end[] = {
 		{EM2874_R80_GPIO_P0_CTRL,	0xa6,	0xff,	100},
 		{EM2874_R80_GPIO_P0_CTRL,	0xa6,	0xff,	50},
 		{EM2874_R80_GPIO_P0_CTRL,	0xe6,	0xff,	100},
@@ -660,7 +660,7 @@ static void terratec_htc_usb_xs_init(struct em28xx *dev)
 	 * Init the analog decoder (not yet supported), but
 	 * it's probably still a good idea.
 	 */
-	struct {
+	static const struct {
 		unsigned char r[4];
 		int len;
 	} regs[] = {
@@ -704,7 +704,7 @@ static void pctv_520e_init(struct em28xx *dev)
 	 * digital demodulator and tuner are routed via AVF4910B.
 	 */
 	int i;
-	struct {
+	static const struct {
 		unsigned char r[4];
 		int len;
 	} regs[] = {
@@ -800,7 +800,7 @@ static int em28xx_mt352_terratec_xs_init(struct dvb_frontend *fe)
 static void px_bcud_init(struct em28xx *dev)
 {
 	int i;
-	struct {
+	static const struct {
 		unsigned char r[4];
 		int len;
 	} regs1[] = {
@@ -818,7 +818,7 @@ static void px_bcud_init(struct em28xx *dev)
 		{{ 0x85, 0x7a }, 2},
 		{{ 0x87, 0x04 }, 2},
 	};
-	static struct em28xx_reg_seq gpio[] = {
+	static const struct em28xx_reg_seq gpio[] = {
 		{EM28XX_R06_I2C_CLK,		0x40,	0xff,	300},
 		{EM2874_R80_GPIO_P0_CTRL,	0xfd,	0xff,	60},
 		{EM28XX_R15_RGAIN,		0x20,	0xff,	0},
diff --git a/drivers/media/usb/em28xx/em28xx-i2c.c b/drivers/media/usb/em28xx/em28xx-i2c.c
index a3155ec196cc..592b98b3643a 100644
--- a/drivers/media/usb/em28xx/em28xx-i2c.c
+++ b/drivers/media/usb/em28xx/em28xx-i2c.c
@@ -949,7 +949,7 @@ void em28xx_do_i2c_scan(struct em28xx *dev, unsigned int bus)
 	unsigned char buf;
 	int i, rc;
 
-	memset(i2c_devicelist, 0, ARRAY_SIZE(i2c_devicelist));
+	memset(i2c_devicelist, 0, sizeof(i2c_devicelist));
 
 	for (i = 0; i < ARRAY_SIZE(i2c_devs); i++) {
 		dev->i2c_client[bus].addr = i;
@@ -964,7 +964,7 @@ void em28xx_do_i2c_scan(struct em28xx *dev, unsigned int bus)
 
 	if (bus == dev->def_i2c_bus)
 		dev->i2c_hash = em28xx_hash_mem(i2c_devicelist,
-						ARRAY_SIZE(i2c_devicelist), 32);
+						sizeof(i2c_devicelist), 32);
 }
 
 /*
diff --git a/drivers/media/usb/em28xx/em28xx.h b/drivers/media/usb/em28xx/em28xx.h
index c8bc59059a19..4ecadd57dac7 100644
--- a/drivers/media/usb/em28xx/em28xx.h
+++ b/drivers/media/usb/em28xx/em28xx.h
@@ -149,6 +149,7 @@
 #define EM28174_BOARD_HAUPPAUGE_WINTV_DUALHD_01595 100
 #define EM2884_BOARD_TERRATEC_H6		  101
 #define EM2882_BOARD_ZOLID_HYBRID_TV_STICK		102
+#define EM2861_BOARD_MAGIX_VIDEOWANDLER2          103
 
 /* Limits minimum and default number of buffers */
 #define EM28XX_MIN_BUF 4
diff --git a/drivers/media/usb/gspca/sq905.c b/drivers/media/usb/gspca/sq905.c
index 863c485f4275..97799cfb832e 100644
--- a/drivers/media/usb/gspca/sq905.c
+++ b/drivers/media/usb/gspca/sq905.c
@@ -378,6 +378,9 @@ static int sd_start(struct gspca_dev *gspca_dev)
 	}
 	/* Start the workqueue function to do the streaming */
 	dev->work_thread = create_singlethread_workqueue(MODULE_NAME);
+	if (!dev->work_thread)
+		return -ENOMEM;
+
 	queue_work(dev->work_thread, &dev->work_struct);
 
 	return 0;
diff --git a/drivers/media/usb/gspca/sq905c.c b/drivers/media/usb/gspca/sq905c.c
index 3d7f6dcdd7a8..6ca947aef298 100644
--- a/drivers/media/usb/gspca/sq905c.c
+++ b/drivers/media/usb/gspca/sq905c.c
@@ -276,6 +276,9 @@ static int sd_start(struct gspca_dev *gspca_dev)
 	}
 	/* Start the workqueue function to do the streaming */
 	dev->work_thread = create_singlethread_workqueue(MODULE_NAME);
+	if (!dev->work_thread)
+		return -ENOMEM;
+
 	queue_work(dev->work_thread, &dev->work_struct);
 
 	return 0;
diff --git a/drivers/media/usb/gspca/stv0680.c b/drivers/media/usb/gspca/stv0680.c
index f869eb6065ce..b23988d8c7bc 100644
--- a/drivers/media/usb/gspca/stv0680.c
+++ b/drivers/media/usb/gspca/stv0680.c
@@ -35,7 +35,7 @@ struct sd {
 static int stv_sndctrl(struct gspca_dev *gspca_dev, int set, u8 req, u16 val,
 		       int size)
 {
-	int ret = -1;
+	int ret;
 	u8 req_type = 0;
 	unsigned int pipe = 0;
 
diff --git a/drivers/media/usb/gspca/stv06xx/stv06xx_st6422.c b/drivers/media/usb/gspca/stv06xx/stv06xx_st6422.c
index 7104a88b1e43..aac19d449be2 100644
--- a/drivers/media/usb/gspca/stv06xx/stv06xx_st6422.c
+++ b/drivers/media/usb/gspca/stv06xx/stv06xx_st6422.c
@@ -117,7 +117,7 @@ static int st6422_init(struct sd *sd)
 {
 	int err = 0, i;
 
-	const u16 st6422_bridge_init[][2] = {
+	static const u16 st6422_bridge_init[][2] = {
 		{ STV_ISO_ENABLE, 0x00 }, /* disable capture */
 		{ 0x1436, 0x00 },
 		{ 0x1432, 0x03 },	/* 0x00-0x1F brightness */
diff --git a/drivers/media/usb/pvrusb2/pvrusb2-v4l2.c b/drivers/media/usb/pvrusb2/pvrusb2-v4l2.c
index a34717eba409..eaa08c7999d4 100644
--- a/drivers/media/usb/pvrusb2/pvrusb2-v4l2.c
+++ b/drivers/media/usb/pvrusb2/pvrusb2-v4l2.c
@@ -898,8 +898,12 @@ static void pvr2_v4l2_internal_check(struct pvr2_channel *chp)
 	pvr2_v4l2_dev_disassociate_parent(vp->dev_video);
 	pvr2_v4l2_dev_disassociate_parent(vp->dev_radio);
 	if (!list_empty(&vp->dev_video->devbase.fh_list) ||
-	    !list_empty(&vp->dev_radio->devbase.fh_list))
+	    (vp->dev_radio &&
+	     !list_empty(&vp->dev_radio->devbase.fh_list))) {
+		pvr2_trace(PVR2_TRACE_STRUCT,
+			   "pvr2_v4l2 internal_check exit-empty id=%p", vp);
 		return;
+	}
 	pvr2_v4l2_destroy_no_lock(vp);
 }
 
@@ -935,7 +939,8 @@ static int pvr2_v4l2_release(struct file *file)
 	kfree(fhp);
 	if (vp->channel.mc_head->disconnect_flag &&
 	    list_empty(&vp->dev_video->devbase.fh_list) &&
-	    list_empty(&vp->dev_radio->devbase.fh_list)) {
+	    (!vp->dev_radio ||
+	     list_empty(&vp->dev_radio->devbase.fh_list))) {
 		pvr2_v4l2_destroy_no_lock(vp);
 	}
 	return 0;
diff --git a/drivers/media/usb/tm6000/tm6000-regs.h b/drivers/media/usb/tm6000/tm6000-regs.h
index d10424673db9..6a181f2e7ef2 100644
--- a/drivers/media/usb/tm6000/tm6000-regs.h
+++ b/drivers/media/usb/tm6000/tm6000-regs.h
@@ -1,5 +1,5 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 /*
- * SPDX-License-Identifier: GPL-2.0
  * tm6000-regs.h - driver for TM5600/TM6000/TM6010 USB video capture devices
  *
  * Copyright (c) 2006-2007 Mauro Carvalho Chehab <mchehab@kernel.org>
diff --git a/drivers/media/usb/tm6000/tm6000-usb-isoc.h b/drivers/media/usb/tm6000/tm6000-usb-isoc.h
index b275dbce3a1b..e3c6933f854d 100644
--- a/drivers/media/usb/tm6000/tm6000-usb-isoc.h
+++ b/drivers/media/usb/tm6000/tm6000-usb-isoc.h
@@ -1,5 +1,5 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 /*
- * SPDX-License-Identifier: GPL-2.0
  * tm6000-buf.c - driver for TM5600/TM6000/TM6010 USB video capture devices
  *
  * Copyright (c) 2006-2007 Mauro Carvalho Chehab <mchehab@kernel.org>
diff --git a/drivers/media/usb/tm6000/tm6000.h b/drivers/media/usb/tm6000/tm6000.h
index bf396544da9a..c08c95312739 100644
--- a/drivers/media/usb/tm6000/tm6000.h
+++ b/drivers/media/usb/tm6000/tm6000.h
@@ -1,5 +1,5 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 /*
- * SPDX-License-Identifier: GPL-2.0
  * tm6000.h - driver for TM5600/TM6000/TM6010 USB video capture devices
  *
  * Copyright (c) 2006-2007 Mauro Carvalho Chehab <mchehab@kernel.org>
diff --git a/drivers/media/usb/usbtv/usbtv-audio.c b/drivers/media/usb/usbtv/usbtv-audio.c
index 6f108996142d..e746c8ddfc49 100644
--- a/drivers/media/usb/usbtv/usbtv-audio.c
+++ b/drivers/media/usb/usbtv/usbtv-audio.c
@@ -378,8 +378,7 @@ int usbtv_audio_init(struct usbtv *usbtv)
 
 	snd_pcm_set_ops(pcm, SNDRV_PCM_STREAM_CAPTURE, &snd_usbtv_pcm_ops);
 	snd_pcm_lib_preallocate_pages_for_all(pcm, SNDRV_DMA_TYPE_CONTINUOUS,
-		snd_dma_continuous_data(GFP_KERNEL), USBTV_AUDIO_BUFFER,
-		USBTV_AUDIO_BUFFER);
+		NULL, USBTV_AUDIO_BUFFER, USBTV_AUDIO_BUFFER);
 
 	rv = snd_card_register(card);
 	if (rv)
diff --git a/drivers/media/usb/usbvision/usbvision-video.c b/drivers/media/usb/usbvision/usbvision-video.c
index cdc66adda755..93d36aab824f 100644
--- a/drivers/media/usb/usbvision/usbvision-video.c
+++ b/drivers/media/usb/usbvision/usbvision-video.c
@@ -314,6 +314,10 @@ static int usbvision_v4l2_open(struct file *file)
 	if (mutex_lock_interruptible(&usbvision->v4l2_lock))
 		return -ERESTARTSYS;
 
+	if (usbvision->remove_pending) {
+		err_code = -ENODEV;
+		goto unlock;
+	}
 	if (usbvision->user) {
 		err_code = -EBUSY;
 	} else {
@@ -377,6 +381,7 @@ unlock:
 static int usbvision_v4l2_close(struct file *file)
 {
 	struct usb_usbvision *usbvision = video_drvdata(file);
+	int r;
 
 	PDEBUG(DBG_IO, "close");
 
@@ -391,9 +396,10 @@ static int usbvision_v4l2_close(struct file *file)
 	usbvision_scratch_free(usbvision);
 
 	usbvision->user--;
+	r = usbvision->remove_pending;
 	mutex_unlock(&usbvision->v4l2_lock);
 
-	if (usbvision->remove_pending) {
+	if (r) {
 		printk(KERN_INFO "%s: Final disconnect\n", __func__);
 		usbvision_release(usbvision);
 		return 0;
@@ -453,6 +459,9 @@ static int vidioc_querycap(struct file *file, void  *priv,
 {
 	struct usb_usbvision *usbvision = video_drvdata(file);
 
+	if (!usbvision->dev)
+		return -ENODEV;
+
 	strscpy(vc->driver, "USBVision", sizeof(vc->driver));
 	strscpy(vc->card,
 		usbvision_device_data[usbvision->dev_model].model_string,
@@ -1061,6 +1070,11 @@ static int usbvision_radio_open(struct file *file)
 
 	if (mutex_lock_interruptible(&usbvision->v4l2_lock))
 		return -ERESTARTSYS;
+
+	if (usbvision->remove_pending) {
+		err_code = -ENODEV;
+		goto out;
+	}
 	err_code = v4l2_fh_open(file);
 	if (err_code)
 		goto out;
@@ -1093,21 +1107,24 @@ out:
 static int usbvision_radio_close(struct file *file)
 {
 	struct usb_usbvision *usbvision = video_drvdata(file);
+	int r;
 
 	PDEBUG(DBG_IO, "");
 
 	mutex_lock(&usbvision->v4l2_lock);
 	/* Set packet size to 0 */
 	usbvision->iface_alt = 0;
-	usb_set_interface(usbvision->dev, usbvision->iface,
-				    usbvision->iface_alt);
+	if (usbvision->dev)
+		usb_set_interface(usbvision->dev, usbvision->iface,
+				  usbvision->iface_alt);
 
 	usbvision_audio_off(usbvision);
 	usbvision->radio = 0;
 	usbvision->user--;
+	r = usbvision->remove_pending;
 	mutex_unlock(&usbvision->v4l2_lock);
 
-	if (usbvision->remove_pending) {
+	if (r) {
 		printk(KERN_INFO "%s: Final disconnect\n", __func__);
 		v4l2_fh_release(file);
 		usbvision_release(usbvision);
@@ -1539,6 +1556,7 @@ err_usb:
 static void usbvision_disconnect(struct usb_interface *intf)
 {
 	struct usb_usbvision *usbvision = to_usbvision(usb_get_intfdata(intf));
+	int u;
 
 	PDEBUG(DBG_PROBE, "");
 
@@ -1555,13 +1573,14 @@ static void usbvision_disconnect(struct usb_interface *intf)
 	v4l2_device_disconnect(&usbvision->v4l2_dev);
 	usbvision_i2c_unregister(usbvision);
 	usbvision->remove_pending = 1;	/* Now all ISO data will be ignored */
+	u = usbvision->user;
 
 	usb_put_dev(usbvision->dev);
 	usbvision->dev = NULL;	/* USB device is no more */
 
 	mutex_unlock(&usbvision->v4l2_lock);
 
-	if (usbvision->user) {
+	if (u) {
 		printk(KERN_INFO "%s: In use, disconnect pending\n",
 		       __func__);
 		wake_up_interruptible(&usbvision->wait_frame);
diff --git a/drivers/media/usb/uvc/uvc_driver.c b/drivers/media/usb/uvc/uvc_driver.c
index 66ee168ddc7e..428235ca2635 100644
--- a/drivers/media/usb/uvc/uvc_driver.c
+++ b/drivers/media/usb/uvc/uvc_driver.c
@@ -2151,6 +2151,20 @@ static int uvc_probe(struct usb_interface *intf,
 			   sizeof(dev->name) - len);
 	}
 
+	/* Initialize the media device. */
+#ifdef CONFIG_MEDIA_CONTROLLER
+	dev->mdev.dev = &intf->dev;
+	strscpy(dev->mdev.model, dev->name, sizeof(dev->mdev.model));
+	if (udev->serial)
+		strscpy(dev->mdev.serial, udev->serial,
+			sizeof(dev->mdev.serial));
+	usb_make_path(udev, dev->mdev.bus_info, sizeof(dev->mdev.bus_info));
+	dev->mdev.hw_revision = le16_to_cpu(udev->descriptor.bcdDevice);
+	media_device_init(&dev->mdev);
+
+	dev->vdev.mdev = &dev->mdev;
+#endif
+
 	/* Parse the Video Class control descriptor. */
 	if (uvc_parse_control(dev) < 0) {
 		uvc_trace(UVC_TRACE_PROBE, "Unable to parse UVC "
@@ -2171,19 +2185,7 @@ static int uvc_probe(struct usb_interface *intf,
 			"linux-uvc-devel mailing list.\n");
 	}
 
-	/* Initialize the media device and register the V4L2 device. */
-#ifdef CONFIG_MEDIA_CONTROLLER
-	dev->mdev.dev = &intf->dev;
-	strscpy(dev->mdev.model, dev->name, sizeof(dev->mdev.model));
-	if (udev->serial)
-		strscpy(dev->mdev.serial, udev->serial,
-			sizeof(dev->mdev.serial));
-	usb_make_path(udev, dev->mdev.bus_info, sizeof(dev->mdev.bus_info));
-	dev->mdev.hw_revision = le16_to_cpu(udev->descriptor.bcdDevice);
-	media_device_init(&dev->mdev);
-
-	dev->vdev.mdev = &dev->mdev;
-#endif
+	/* Register the V4L2 device. */
 	if (v4l2_device_register(&intf->dev, &dev->vdev) < 0)
 		goto error;
 
diff --git a/drivers/media/usb/uvc/uvc_metadata.c b/drivers/media/usb/uvc/uvc_metadata.c
index 99bb71b47117..b6279ad7ac84 100644
--- a/drivers/media/usb/uvc/uvc_metadata.c
+++ b/drivers/media/usb/uvc/uvc_metadata.c
@@ -51,7 +51,7 @@ static int uvc_meta_v4l2_get_format(struct file *file, void *fh,
 	memset(fmt, 0, sizeof(*fmt));
 
 	fmt->dataformat = stream->meta.format;
-	fmt->buffersize = UVC_METATADA_BUF_SIZE;
+	fmt->buffersize = UVC_METADATA_BUF_SIZE;
 
 	return 0;
 }
@@ -72,7 +72,7 @@ static int uvc_meta_v4l2_try_format(struct file *file, void *fh,
 
 	fmt->dataformat = fmeta == dev->info->meta_format
 			? fmeta : V4L2_META_FMT_UVC;
-	fmt->buffersize = UVC_METATADA_BUF_SIZE;
+	fmt->buffersize = UVC_METADATA_BUF_SIZE;
 
 	return 0;
 }
diff --git a/drivers/media/usb/uvc/uvc_queue.c b/drivers/media/usb/uvc/uvc_queue.c
index da72577c2998..cd60c6c1749e 100644
--- a/drivers/media/usb/uvc/uvc_queue.c
+++ b/drivers/media/usb/uvc/uvc_queue.c
@@ -79,7 +79,7 @@ static int uvc_queue_setup(struct vb2_queue *vq,
 
 	switch (vq->type) {
 	case V4L2_BUF_TYPE_META_CAPTURE:
-		size = UVC_METATADA_BUF_SIZE;
+		size = UVC_METADATA_BUF_SIZE;
 		break;
 
 	default:
diff --git a/drivers/media/usb/uvc/uvcvideo.h b/drivers/media/usb/uvc/uvcvideo.h
index c7c1baa90dea..f773dc5d802c 100644
--- a/drivers/media/usb/uvc/uvcvideo.h
+++ b/drivers/media/usb/uvc/uvcvideo.h
@@ -491,7 +491,7 @@ struct uvc_stats_stream {
 	unsigned int max_sof;		/* Maximum STC.SOF value */
 };
 
-#define UVC_METATADA_BUF_SIZE 1024
+#define UVC_METADATA_BUF_SIZE 1024
 
 /**
  * struct uvc_copy_op: Context structure to schedule asynchronous memcpy
diff --git a/drivers/media/usb/zr364xx/zr364xx.c b/drivers/media/usb/zr364xx/zr364xx.c
index 637962825d7a..57dbcc8083bf 100644
--- a/drivers/media/usb/zr364xx/zr364xx.c
+++ b/drivers/media/usb/zr364xx/zr364xx.c
@@ -20,7 +20,6 @@
 #include <linux/usb.h>
 #include <linux/vmalloc.h>
 #include <linux/slab.h>
-#include <linux/proc_fs.h>
 #include <linux/highmem.h>
 #include <media/v4l2-common.h>
 #include <media/v4l2-ioctl.h>
@@ -556,14 +555,12 @@ static int zr364xx_read_video_callback(struct zr364xx_camera *cam,
 {
 	unsigned char *pdest;
 	unsigned char *psrc;
-	s32 idx = -1;
-	struct zr364xx_framei *frm;
+	s32 idx = cam->cur_frame;
+	struct zr364xx_framei *frm = &cam->buffer.frame[idx];
 	int i = 0;
 	unsigned char *ptr = NULL;
 
 	_DBG("buffer to user\n");
-	idx = cam->cur_frame;
-	frm = &cam->buffer.frame[idx];
 
 	/* swap bytes if camera needs it */
 	if (cam->method == METHOD0) {
diff --git a/drivers/media/v4l2-core/v4l2-common.c b/drivers/media/v4l2-core/v4l2-common.c
index 62f7aa92ac29..d0e5ebc736f9 100644
--- a/drivers/media/v4l2-core/v4l2-common.c
+++ b/drivers/media/v4l2-core/v4l2-common.c
@@ -236,77 +236,79 @@ const struct v4l2_format_info *v4l2_format_info(u32 format)
 {
 	static const struct v4l2_format_info formats[] = {
 		/* RGB formats */
-		{ .format = V4L2_PIX_FMT_BGR24,   .mem_planes = 1, .comp_planes = 1, .bpp = { 3, 0, 0, 0 }, .hdiv = 1, .vdiv = 1 },
-		{ .format = V4L2_PIX_FMT_RGB24,   .mem_planes = 1, .comp_planes = 1, .bpp = { 3, 0, 0, 0 }, .hdiv = 1, .vdiv = 1 },
-		{ .format = V4L2_PIX_FMT_HSV24,   .mem_planes = 1, .comp_planes = 1, .bpp = { 3, 0, 0, 0 }, .hdiv = 1, .vdiv = 1 },
-		{ .format = V4L2_PIX_FMT_BGR32,   .mem_planes = 1, .comp_planes = 1, .bpp = { 4, 0, 0, 0 }, .hdiv = 1, .vdiv = 1 },
-		{ .format = V4L2_PIX_FMT_XBGR32,  .mem_planes = 1, .comp_planes = 1, .bpp = { 4, 0, 0, 0 }, .hdiv = 1, .vdiv = 1 },
-		{ .format = V4L2_PIX_FMT_BGRX32,  .mem_planes = 1, .comp_planes = 1, .bpp = { 4, 0, 0, 0 }, .hdiv = 1, .vdiv = 1 },
-		{ .format = V4L2_PIX_FMT_RGB32,   .mem_planes = 1, .comp_planes = 1, .bpp = { 4, 0, 0, 0 }, .hdiv = 1, .vdiv = 1 },
-		{ .format = V4L2_PIX_FMT_XRGB32,  .mem_planes = 1, .comp_planes = 1, .bpp = { 4, 0, 0, 0 }, .hdiv = 1, .vdiv = 1 },
-		{ .format = V4L2_PIX_FMT_RGBX32,  .mem_planes = 1, .comp_planes = 1, .bpp = { 4, 0, 0, 0 }, .hdiv = 1, .vdiv = 1 },
-		{ .format = V4L2_PIX_FMT_HSV32,   .mem_planes = 1, .comp_planes = 1, .bpp = { 4, 0, 0, 0 }, .hdiv = 1, .vdiv = 1 },
-		{ .format = V4L2_PIX_FMT_ARGB32,  .mem_planes = 1, .comp_planes = 1, .bpp = { 4, 0, 0, 0 }, .hdiv = 1, .vdiv = 1 },
-		{ .format = V4L2_PIX_FMT_RGBA32,  .mem_planes = 1, .comp_planes = 1, .bpp = { 4, 0, 0, 0 }, .hdiv = 1, .vdiv = 1 },
-		{ .format = V4L2_PIX_FMT_ABGR32,  .mem_planes = 1, .comp_planes = 1, .bpp = { 4, 0, 0, 0 }, .hdiv = 1, .vdiv = 1 },
-		{ .format = V4L2_PIX_FMT_BGRA32,  .mem_planes = 1, .comp_planes = 1, .bpp = { 4, 0, 0, 0 }, .hdiv = 1, .vdiv = 1 },
-		{ .format = V4L2_PIX_FMT_GREY,    .mem_planes = 1, .comp_planes = 1, .bpp = { 1, 0, 0, 0 }, .hdiv = 1, .vdiv = 1 },
+		{ .format = V4L2_PIX_FMT_BGR24,   .pixel_enc = V4L2_PIXEL_ENC_RGB, .mem_planes = 1, .comp_planes = 1, .bpp = { 3, 0, 0, 0 }, .hdiv = 1, .vdiv = 1 },
+		{ .format = V4L2_PIX_FMT_RGB24,   .pixel_enc = V4L2_PIXEL_ENC_RGB, .mem_planes = 1, .comp_planes = 1, .bpp = { 3, 0, 0, 0 }, .hdiv = 1, .vdiv = 1 },
+		{ .format = V4L2_PIX_FMT_HSV24,   .pixel_enc = V4L2_PIXEL_ENC_RGB, .mem_planes = 1, .comp_planes = 1, .bpp = { 3, 0, 0, 0 }, .hdiv = 1, .vdiv = 1 },
+		{ .format = V4L2_PIX_FMT_BGR32,   .pixel_enc = V4L2_PIXEL_ENC_RGB, .mem_planes = 1, .comp_planes = 1, .bpp = { 4, 0, 0, 0 }, .hdiv = 1, .vdiv = 1 },
+		{ .format = V4L2_PIX_FMT_XBGR32,  .pixel_enc = V4L2_PIXEL_ENC_RGB, .mem_planes = 1, .comp_planes = 1, .bpp = { 4, 0, 0, 0 }, .hdiv = 1, .vdiv = 1 },
+		{ .format = V4L2_PIX_FMT_BGRX32,  .pixel_enc = V4L2_PIXEL_ENC_RGB, .mem_planes = 1, .comp_planes = 1, .bpp = { 4, 0, 0, 0 }, .hdiv = 1, .vdiv = 1 },
+		{ .format = V4L2_PIX_FMT_RGB32,   .pixel_enc = V4L2_PIXEL_ENC_RGB, .mem_planes = 1, .comp_planes = 1, .bpp = { 4, 0, 0, 0 }, .hdiv = 1, .vdiv = 1 },
+		{ .format = V4L2_PIX_FMT_XRGB32,  .pixel_enc = V4L2_PIXEL_ENC_RGB, .mem_planes = 1, .comp_planes = 1, .bpp = { 4, 0, 0, 0 }, .hdiv = 1, .vdiv = 1 },
+		{ .format = V4L2_PIX_FMT_RGBX32,  .pixel_enc = V4L2_PIXEL_ENC_RGB, .mem_planes = 1, .comp_planes = 1, .bpp = { 4, 0, 0, 0 }, .hdiv = 1, .vdiv = 1 },
+		{ .format = V4L2_PIX_FMT_HSV32,   .pixel_enc = V4L2_PIXEL_ENC_RGB, .mem_planes = 1, .comp_planes = 1, .bpp = { 4, 0, 0, 0 }, .hdiv = 1, .vdiv = 1 },
+		{ .format = V4L2_PIX_FMT_ARGB32,  .pixel_enc = V4L2_PIXEL_ENC_RGB, .mem_planes = 1, .comp_planes = 1, .bpp = { 4, 0, 0, 0 }, .hdiv = 1, .vdiv = 1 },
+		{ .format = V4L2_PIX_FMT_RGBA32,  .pixel_enc = V4L2_PIXEL_ENC_RGB, .mem_planes = 1, .comp_planes = 1, .bpp = { 4, 0, 0, 0 }, .hdiv = 1, .vdiv = 1 },
+		{ .format = V4L2_PIX_FMT_ABGR32,  .pixel_enc = V4L2_PIXEL_ENC_RGB, .mem_planes = 1, .comp_planes = 1, .bpp = { 4, 0, 0, 0 }, .hdiv = 1, .vdiv = 1 },
+		{ .format = V4L2_PIX_FMT_BGRA32,  .pixel_enc = V4L2_PIXEL_ENC_RGB, .mem_planes = 1, .comp_planes = 1, .bpp = { 4, 0, 0, 0 }, .hdiv = 1, .vdiv = 1 },
+		{ .format = V4L2_PIX_FMT_GREY,    .pixel_enc = V4L2_PIXEL_ENC_RGB, .mem_planes = 1, .comp_planes = 1, .bpp = { 1, 0, 0, 0 }, .hdiv = 1, .vdiv = 1 },
+		{ .format = V4L2_PIX_FMT_RGB565,  .pixel_enc = V4L2_PIXEL_ENC_RGB, .mem_planes = 1, .comp_planes = 1, .bpp = { 2, 0, 0, 0 }, .hdiv = 1, .vdiv = 1 },
+		{ .format = V4L2_PIX_FMT_RGB555,  .pixel_enc = V4L2_PIXEL_ENC_RGB, .mem_planes = 1, .comp_planes = 1, .bpp = { 2, 0, 0, 0 }, .hdiv = 1, .vdiv = 1 },
 
 		/* YUV packed formats */
-		{ .format = V4L2_PIX_FMT_YUYV,    .mem_planes = 1, .comp_planes = 1, .bpp = { 2, 0, 0, 0 }, .hdiv = 2, .vdiv = 1 },
-		{ .format = V4L2_PIX_FMT_YVYU,    .mem_planes = 1, .comp_planes = 1, .bpp = { 2, 0, 0, 0 }, .hdiv = 2, .vdiv = 1 },
-		{ .format = V4L2_PIX_FMT_UYVY,    .mem_planes = 1, .comp_planes = 1, .bpp = { 2, 0, 0, 0 }, .hdiv = 2, .vdiv = 1 },
-		{ .format = V4L2_PIX_FMT_VYUY,    .mem_planes = 1, .comp_planes = 1, .bpp = { 2, 0, 0, 0 }, .hdiv = 2, .vdiv = 1 },
+		{ .format = V4L2_PIX_FMT_YUYV,    .pixel_enc = V4L2_PIXEL_ENC_YUV, .mem_planes = 1, .comp_planes = 1, .bpp = { 2, 0, 0, 0 }, .hdiv = 2, .vdiv = 1 },
+		{ .format = V4L2_PIX_FMT_YVYU,    .pixel_enc = V4L2_PIXEL_ENC_YUV, .mem_planes = 1, .comp_planes = 1, .bpp = { 2, 0, 0, 0 }, .hdiv = 2, .vdiv = 1 },
+		{ .format = V4L2_PIX_FMT_UYVY,    .pixel_enc = V4L2_PIXEL_ENC_YUV, .mem_planes = 1, .comp_planes = 1, .bpp = { 2, 0, 0, 0 }, .hdiv = 2, .vdiv = 1 },
+		{ .format = V4L2_PIX_FMT_VYUY,    .pixel_enc = V4L2_PIXEL_ENC_YUV, .mem_planes = 1, .comp_planes = 1, .bpp = { 2, 0, 0, 0 }, .hdiv = 2, .vdiv = 1 },
 
 		/* YUV planar formats */
-		{ .format = V4L2_PIX_FMT_NV12,    .mem_planes = 1, .comp_planes = 2, .bpp = { 1, 2, 0, 0 }, .hdiv = 2, .vdiv = 2 },
-		{ .format = V4L2_PIX_FMT_NV21,    .mem_planes = 1, .comp_planes = 2, .bpp = { 1, 2, 0, 0 }, .hdiv = 2, .vdiv = 2 },
-		{ .format = V4L2_PIX_FMT_NV16,    .mem_planes = 1, .comp_planes = 2, .bpp = { 1, 2, 0, 0 }, .hdiv = 2, .vdiv = 1 },
-		{ .format = V4L2_PIX_FMT_NV61,    .mem_planes = 1, .comp_planes = 2, .bpp = { 1, 2, 0, 0 }, .hdiv = 2, .vdiv = 1 },
-		{ .format = V4L2_PIX_FMT_NV24,    .mem_planes = 1, .comp_planes = 2, .bpp = { 1, 2, 0, 0 }, .hdiv = 1, .vdiv = 1 },
-		{ .format = V4L2_PIX_FMT_NV42,    .mem_planes = 1, .comp_planes = 2, .bpp = { 1, 2, 0, 0 }, .hdiv = 1, .vdiv = 1 },
-
-		{ .format = V4L2_PIX_FMT_YUV410,  .mem_planes = 1, .comp_planes = 3, .bpp = { 1, 1, 1, 0 }, .hdiv = 4, .vdiv = 4 },
-		{ .format = V4L2_PIX_FMT_YVU410,  .mem_planes = 1, .comp_planes = 3, .bpp = { 1, 1, 1, 0 }, .hdiv = 4, .vdiv = 4 },
-		{ .format = V4L2_PIX_FMT_YUV411P, .mem_planes = 1, .comp_planes = 3, .bpp = { 1, 1, 1, 0 }, .hdiv = 4, .vdiv = 1 },
-		{ .format = V4L2_PIX_FMT_YUV420,  .mem_planes = 1, .comp_planes = 3, .bpp = { 1, 1, 1, 0 }, .hdiv = 2, .vdiv = 2 },
-		{ .format = V4L2_PIX_FMT_YVU420,  .mem_planes = 1, .comp_planes = 3, .bpp = { 1, 1, 1, 0 }, .hdiv = 2, .vdiv = 2 },
-		{ .format = V4L2_PIX_FMT_YUV422P, .mem_planes = 1, .comp_planes = 3, .bpp = { 1, 1, 1, 0 }, .hdiv = 2, .vdiv = 1 },
+		{ .format = V4L2_PIX_FMT_NV12,    .pixel_enc = V4L2_PIXEL_ENC_YUV, .mem_planes = 1, .comp_planes = 2, .bpp = { 1, 2, 0, 0 }, .hdiv = 2, .vdiv = 2 },
+		{ .format = V4L2_PIX_FMT_NV21,    .pixel_enc = V4L2_PIXEL_ENC_YUV, .mem_planes = 1, .comp_planes = 2, .bpp = { 1, 2, 0, 0 }, .hdiv = 2, .vdiv = 2 },
+		{ .format = V4L2_PIX_FMT_NV16,    .pixel_enc = V4L2_PIXEL_ENC_YUV, .mem_planes = 1, .comp_planes = 2, .bpp = { 1, 2, 0, 0 }, .hdiv = 2, .vdiv = 1 },
+		{ .format = V4L2_PIX_FMT_NV61,    .pixel_enc = V4L2_PIXEL_ENC_YUV, .mem_planes = 1, .comp_planes = 2, .bpp = { 1, 2, 0, 0 }, .hdiv = 2, .vdiv = 1 },
+		{ .format = V4L2_PIX_FMT_NV24,    .pixel_enc = V4L2_PIXEL_ENC_YUV, .mem_planes = 1, .comp_planes = 2, .bpp = { 1, 2, 0, 0 }, .hdiv = 1, .vdiv = 1 },
+		{ .format = V4L2_PIX_FMT_NV42,    .pixel_enc = V4L2_PIXEL_ENC_YUV, .mem_planes = 1, .comp_planes = 2, .bpp = { 1, 2, 0, 0 }, .hdiv = 1, .vdiv = 1 },
+
+		{ .format = V4L2_PIX_FMT_YUV410,  .pixel_enc = V4L2_PIXEL_ENC_YUV, .mem_planes = 1, .comp_planes = 3, .bpp = { 1, 1, 1, 0 }, .hdiv = 4, .vdiv = 4 },
+		{ .format = V4L2_PIX_FMT_YVU410,  .pixel_enc = V4L2_PIXEL_ENC_YUV, .mem_planes = 1, .comp_planes = 3, .bpp = { 1, 1, 1, 0 }, .hdiv = 4, .vdiv = 4 },
+		{ .format = V4L2_PIX_FMT_YUV411P, .pixel_enc = V4L2_PIXEL_ENC_YUV, .mem_planes = 1, .comp_planes = 3, .bpp = { 1, 1, 1, 0 }, .hdiv = 4, .vdiv = 1 },
+		{ .format = V4L2_PIX_FMT_YUV420,  .pixel_enc = V4L2_PIXEL_ENC_YUV, .mem_planes = 1, .comp_planes = 3, .bpp = { 1, 1, 1, 0 }, .hdiv = 2, .vdiv = 2 },
+		{ .format = V4L2_PIX_FMT_YVU420,  .pixel_enc = V4L2_PIXEL_ENC_YUV, .mem_planes = 1, .comp_planes = 3, .bpp = { 1, 1, 1, 0 }, .hdiv = 2, .vdiv = 2 },
+		{ .format = V4L2_PIX_FMT_YUV422P, .pixel_enc = V4L2_PIXEL_ENC_YUV, .mem_planes = 1, .comp_planes = 3, .bpp = { 1, 1, 1, 0 }, .hdiv = 2, .vdiv = 1 },
 
 		/* YUV planar formats, non contiguous variant */
-		{ .format = V4L2_PIX_FMT_YUV420M, .mem_planes = 3, .comp_planes = 3, .bpp = { 1, 1, 1, 0 }, .hdiv = 2, .vdiv = 2 },
-		{ .format = V4L2_PIX_FMT_YVU420M, .mem_planes = 3, .comp_planes = 3, .bpp = { 1, 1, 1, 0 }, .hdiv = 2, .vdiv = 2 },
-		{ .format = V4L2_PIX_FMT_YUV422M, .mem_planes = 3, .comp_planes = 3, .bpp = { 1, 1, 1, 0 }, .hdiv = 2, .vdiv = 1 },
-		{ .format = V4L2_PIX_FMT_YVU422M, .mem_planes = 3, .comp_planes = 3, .bpp = { 1, 1, 1, 0 }, .hdiv = 2, .vdiv = 1 },
-		{ .format = V4L2_PIX_FMT_YUV444M, .mem_planes = 3, .comp_planes = 3, .bpp = { 1, 1, 1, 0 }, .hdiv = 1, .vdiv = 1 },
-		{ .format = V4L2_PIX_FMT_YVU444M, .mem_planes = 3, .comp_planes = 3, .bpp = { 1, 1, 1, 0 }, .hdiv = 1, .vdiv = 1 },
-
-		{ .format = V4L2_PIX_FMT_NV12M,   .mem_planes = 2, .comp_planes = 2, .bpp = { 1, 2, 0, 0 }, .hdiv = 2, .vdiv = 2 },
-		{ .format = V4L2_PIX_FMT_NV21M,   .mem_planes = 2, .comp_planes = 2, .bpp = { 1, 2, 0, 0 }, .hdiv = 2, .vdiv = 2 },
-		{ .format = V4L2_PIX_FMT_NV16M,   .mem_planes = 2, .comp_planes = 2, .bpp = { 1, 2, 0, 0 }, .hdiv = 2, .vdiv = 1 },
-		{ .format = V4L2_PIX_FMT_NV61M,   .mem_planes = 2, .comp_planes = 2, .bpp = { 1, 2, 0, 0 }, .hdiv = 2, .vdiv = 1 },
+		{ .format = V4L2_PIX_FMT_YUV420M, .pixel_enc = V4L2_PIXEL_ENC_YUV, .mem_planes = 3, .comp_planes = 3, .bpp = { 1, 1, 1, 0 }, .hdiv = 2, .vdiv = 2 },
+		{ .format = V4L2_PIX_FMT_YVU420M, .pixel_enc = V4L2_PIXEL_ENC_YUV, .mem_planes = 3, .comp_planes = 3, .bpp = { 1, 1, 1, 0 }, .hdiv = 2, .vdiv = 2 },
+		{ .format = V4L2_PIX_FMT_YUV422M, .pixel_enc = V4L2_PIXEL_ENC_YUV, .mem_planes = 3, .comp_planes = 3, .bpp = { 1, 1, 1, 0 }, .hdiv = 2, .vdiv = 1 },
+		{ .format = V4L2_PIX_FMT_YVU422M, .pixel_enc = V4L2_PIXEL_ENC_YUV, .mem_planes = 3, .comp_planes = 3, .bpp = { 1, 1, 1, 0 }, .hdiv = 2, .vdiv = 1 },
+		{ .format = V4L2_PIX_FMT_YUV444M, .pixel_enc = V4L2_PIXEL_ENC_YUV, .mem_planes = 3, .comp_planes = 3, .bpp = { 1, 1, 1, 0 }, .hdiv = 1, .vdiv = 1 },
+		{ .format = V4L2_PIX_FMT_YVU444M, .pixel_enc = V4L2_PIXEL_ENC_YUV, .mem_planes = 3, .comp_planes = 3, .bpp = { 1, 1, 1, 0 }, .hdiv = 1, .vdiv = 1 },
+
+		{ .format = V4L2_PIX_FMT_NV12M,   .pixel_enc = V4L2_PIXEL_ENC_YUV, .mem_planes = 2, .comp_planes = 2, .bpp = { 1, 2, 0, 0 }, .hdiv = 2, .vdiv = 2 },
+		{ .format = V4L2_PIX_FMT_NV21M,   .pixel_enc = V4L2_PIXEL_ENC_YUV, .mem_planes = 2, .comp_planes = 2, .bpp = { 1, 2, 0, 0 }, .hdiv = 2, .vdiv = 2 },
+		{ .format = V4L2_PIX_FMT_NV16M,   .pixel_enc = V4L2_PIXEL_ENC_YUV, .mem_planes = 2, .comp_planes = 2, .bpp = { 1, 2, 0, 0 }, .hdiv = 2, .vdiv = 1 },
+		{ .format = V4L2_PIX_FMT_NV61M,   .pixel_enc = V4L2_PIXEL_ENC_YUV, .mem_planes = 2, .comp_planes = 2, .bpp = { 1, 2, 0, 0 }, .hdiv = 2, .vdiv = 1 },
 
 		/* Bayer RGB formats */
-		{ .format = V4L2_PIX_FMT_SBGGR8,	.mem_planes = 1, .comp_planes = 1, .bpp = { 1, 0, 0, 0 }, .hdiv = 1, .vdiv = 1 },
-		{ .format = V4L2_PIX_FMT_SGBRG8,	.mem_planes = 1, .comp_planes = 1, .bpp = { 1, 0, 0, 0 }, .hdiv = 1, .vdiv = 1 },
-		{ .format = V4L2_PIX_FMT_SGRBG8,	.mem_planes = 1, .comp_planes = 1, .bpp = { 1, 0, 0, 0 }, .hdiv = 1, .vdiv = 1 },
-		{ .format = V4L2_PIX_FMT_SRGGB8,	.mem_planes = 1, .comp_planes = 1, .bpp = { 1, 0, 0, 0 }, .hdiv = 1, .vdiv = 1 },
-		{ .format = V4L2_PIX_FMT_SBGGR10,	.mem_planes = 1, .comp_planes = 1, .bpp = { 2, 0, 0, 0 }, .hdiv = 1, .vdiv = 1 },
-		{ .format = V4L2_PIX_FMT_SGBRG10,	.mem_planes = 1, .comp_planes = 1, .bpp = { 2, 0, 0, 0 }, .hdiv = 1, .vdiv = 1 },
-		{ .format = V4L2_PIX_FMT_SGRBG10,	.mem_planes = 1, .comp_planes = 1, .bpp = { 2, 0, 0, 0 }, .hdiv = 1, .vdiv = 1 },
-		{ .format = V4L2_PIX_FMT_SRGGB10,	.mem_planes = 1, .comp_planes = 1, .bpp = { 2, 0, 0, 0 }, .hdiv = 1, .vdiv = 1 },
-		{ .format = V4L2_PIX_FMT_SBGGR10ALAW8,	.mem_planes = 1, .comp_planes = 1, .bpp = { 1, 0, 0, 0 }, .hdiv = 1, .vdiv = 1 },
-		{ .format = V4L2_PIX_FMT_SGBRG10ALAW8,	.mem_planes = 1, .comp_planes = 1, .bpp = { 1, 0, 0, 0 }, .hdiv = 1, .vdiv = 1 },
-		{ .format = V4L2_PIX_FMT_SGRBG10ALAW8,	.mem_planes = 1, .comp_planes = 1, .bpp = { 1, 0, 0, 0 }, .hdiv = 1, .vdiv = 1 },
-		{ .format = V4L2_PIX_FMT_SRGGB10ALAW8,	.mem_planes = 1, .comp_planes = 1, .bpp = { 1, 0, 0, 0 }, .hdiv = 1, .vdiv = 1 },
-		{ .format = V4L2_PIX_FMT_SBGGR10DPCM8,	.mem_planes = 1, .comp_planes = 1, .bpp = { 1, 0, 0, 0 }, .hdiv = 1, .vdiv = 1 },
-		{ .format = V4L2_PIX_FMT_SGBRG10DPCM8,	.mem_planes = 1, .comp_planes = 1, .bpp = { 1, 0, 0, 0 }, .hdiv = 1, .vdiv = 1 },
-		{ .format = V4L2_PIX_FMT_SGRBG10DPCM8,	.mem_planes = 1, .comp_planes = 1, .bpp = { 1, 0, 0, 0 }, .hdiv = 1, .vdiv = 1 },
-		{ .format = V4L2_PIX_FMT_SRGGB10DPCM8,	.mem_planes = 1, .comp_planes = 1, .bpp = { 1, 0, 0, 0 }, .hdiv = 1, .vdiv = 1 },
-		{ .format = V4L2_PIX_FMT_SBGGR12,	.mem_planes = 1, .comp_planes = 1, .bpp = { 2, 0, 0, 0 }, .hdiv = 1, .vdiv = 1 },
-		{ .format = V4L2_PIX_FMT_SGBRG12,	.mem_planes = 1, .comp_planes = 1, .bpp = { 2, 0, 0, 0 }, .hdiv = 1, .vdiv = 1 },
-		{ .format = V4L2_PIX_FMT_SGRBG12,	.mem_planes = 1, .comp_planes = 1, .bpp = { 2, 0, 0, 0 }, .hdiv = 1, .vdiv = 1 },
-		{ .format = V4L2_PIX_FMT_SRGGB12,	.mem_planes = 1, .comp_planes = 1, .bpp = { 2, 0, 0, 0 }, .hdiv = 1, .vdiv = 1 },
+		{ .format = V4L2_PIX_FMT_SBGGR8,	.pixel_enc = V4L2_PIXEL_ENC_BAYER, .mem_planes = 1, .comp_planes = 1, .bpp = { 1, 0, 0, 0 }, .hdiv = 1, .vdiv = 1 },
+		{ .format = V4L2_PIX_FMT_SGBRG8,	.pixel_enc = V4L2_PIXEL_ENC_BAYER, .mem_planes = 1, .comp_planes = 1, .bpp = { 1, 0, 0, 0 }, .hdiv = 1, .vdiv = 1 },
+		{ .format = V4L2_PIX_FMT_SGRBG8,	.pixel_enc = V4L2_PIXEL_ENC_BAYER, .mem_planes = 1, .comp_planes = 1, .bpp = { 1, 0, 0, 0 }, .hdiv = 1, .vdiv = 1 },
+		{ .format = V4L2_PIX_FMT_SRGGB8,	.pixel_enc = V4L2_PIXEL_ENC_BAYER, .mem_planes = 1, .comp_planes = 1, .bpp = { 1, 0, 0, 0 }, .hdiv = 1, .vdiv = 1 },
+		{ .format = V4L2_PIX_FMT_SBGGR10,	.pixel_enc = V4L2_PIXEL_ENC_BAYER, .mem_planes = 1, .comp_planes = 1, .bpp = { 2, 0, 0, 0 }, .hdiv = 1, .vdiv = 1 },
+		{ .format = V4L2_PIX_FMT_SGBRG10,	.pixel_enc = V4L2_PIXEL_ENC_BAYER, .mem_planes = 1, .comp_planes = 1, .bpp = { 2, 0, 0, 0 }, .hdiv = 1, .vdiv = 1 },
+		{ .format = V4L2_PIX_FMT_SGRBG10,	.pixel_enc = V4L2_PIXEL_ENC_BAYER, .mem_planes = 1, .comp_planes = 1, .bpp = { 2, 0, 0, 0 }, .hdiv = 1, .vdiv = 1 },
+		{ .format = V4L2_PIX_FMT_SRGGB10,	.pixel_enc = V4L2_PIXEL_ENC_BAYER, .mem_planes = 1, .comp_planes = 1, .bpp = { 2, 0, 0, 0 }, .hdiv = 1, .vdiv = 1 },
+		{ .format = V4L2_PIX_FMT_SBGGR10ALAW8,	.pixel_enc = V4L2_PIXEL_ENC_BAYER, .mem_planes = 1, .comp_planes = 1, .bpp = { 1, 0, 0, 0 }, .hdiv = 1, .vdiv = 1 },
+		{ .format = V4L2_PIX_FMT_SGBRG10ALAW8,	.pixel_enc = V4L2_PIXEL_ENC_BAYER, .mem_planes = 1, .comp_planes = 1, .bpp = { 1, 0, 0, 0 }, .hdiv = 1, .vdiv = 1 },
+		{ .format = V4L2_PIX_FMT_SGRBG10ALAW8,	.pixel_enc = V4L2_PIXEL_ENC_BAYER, .mem_planes = 1, .comp_planes = 1, .bpp = { 1, 0, 0, 0 }, .hdiv = 1, .vdiv = 1 },
+		{ .format = V4L2_PIX_FMT_SRGGB10ALAW8,	.pixel_enc = V4L2_PIXEL_ENC_BAYER, .mem_planes = 1, .comp_planes = 1, .bpp = { 1, 0, 0, 0 }, .hdiv = 1, .vdiv = 1 },
+		{ .format = V4L2_PIX_FMT_SBGGR10DPCM8,	.pixel_enc = V4L2_PIXEL_ENC_BAYER, .mem_planes = 1, .comp_planes = 1, .bpp = { 1, 0, 0, 0 }, .hdiv = 1, .vdiv = 1 },
+		{ .format = V4L2_PIX_FMT_SGBRG10DPCM8,	.pixel_enc = V4L2_PIXEL_ENC_BAYER, .mem_planes = 1, .comp_planes = 1, .bpp = { 1, 0, 0, 0 }, .hdiv = 1, .vdiv = 1 },
+		{ .format = V4L2_PIX_FMT_SGRBG10DPCM8,	.pixel_enc = V4L2_PIXEL_ENC_BAYER, .mem_planes = 1, .comp_planes = 1, .bpp = { 1, 0, 0, 0 }, .hdiv = 1, .vdiv = 1 },
+		{ .format = V4L2_PIX_FMT_SRGGB10DPCM8,	.pixel_enc = V4L2_PIXEL_ENC_BAYER, .mem_planes = 1, .comp_planes = 1, .bpp = { 1, 0, 0, 0 }, .hdiv = 1, .vdiv = 1 },
+		{ .format = V4L2_PIX_FMT_SBGGR12,	.pixel_enc = V4L2_PIXEL_ENC_BAYER, .mem_planes = 1, .comp_planes = 1, .bpp = { 2, 0, 0, 0 }, .hdiv = 1, .vdiv = 1 },
+		{ .format = V4L2_PIX_FMT_SGBRG12,	.pixel_enc = V4L2_PIXEL_ENC_BAYER, .mem_planes = 1, .comp_planes = 1, .bpp = { 2, 0, 0, 0 }, .hdiv = 1, .vdiv = 1 },
+		{ .format = V4L2_PIX_FMT_SGRBG12,	.pixel_enc = V4L2_PIXEL_ENC_BAYER, .mem_planes = 1, .comp_planes = 1, .bpp = { 2, 0, 0, 0 }, .hdiv = 1, .vdiv = 1 },
+		{ .format = V4L2_PIX_FMT_SRGGB12,	.pixel_enc = V4L2_PIXEL_ENC_BAYER, .mem_planes = 1, .comp_planes = 1, .bpp = { 2, 0, 0, 0 }, .hdiv = 1, .vdiv = 1 },
 	};
 	unsigned int i;
 
diff --git a/drivers/media/v4l2-core/v4l2-ctrls.c b/drivers/media/v4l2-core/v4l2-ctrls.c
index 1d8f38824631..2928c5e0a73d 100644
--- a/drivers/media/v4l2-core/v4l2-ctrls.c
+++ b/drivers/media/v4l2-core/v4l2-ctrls.c
@@ -29,6 +29,8 @@
 #define call_op(master, op) \
 	(has_op(master, op) ? master->ops->op(master) : 0)
 
+static const union v4l2_ctrl_ptr ptr_null;
+
 /* Internal temporary helper struct, one for each v4l2_ext_control */
 struct v4l2_ctrl_helper {
 	/* Pointer to the control reference of the master control */
@@ -566,6 +568,16 @@ const char * const *v4l2_ctrl_get_menu(u32 id)
 		"Disabled at slice boundary",
 		"NULL",
 	};
+	static const char * const hevc_decode_mode[] = {
+		"Slice-Based",
+		"Frame-Based",
+		NULL,
+	};
+	static const char * const hevc_start_code[] = {
+		"No Start Code",
+		"Annex B Start Code",
+		NULL,
+	};
 
 	switch (id) {
 	case V4L2_CID_MPEG_AUDIO_SAMPLING_FREQ:
@@ -687,7 +699,10 @@ const char * const *v4l2_ctrl_get_menu(u32 id)
 		return hevc_tier;
 	case V4L2_CID_MPEG_VIDEO_HEVC_LOOP_FILTER_MODE:
 		return hevc_loop_filter_mode;
-
+	case V4L2_CID_MPEG_VIDEO_HEVC_DECODE_MODE:
+		return hevc_decode_mode;
+	case V4L2_CID_MPEG_VIDEO_HEVC_START_CODE:
+		return hevc_start_code;
 	default:
 		return NULL;
 	}
@@ -957,6 +972,11 @@ const char *v4l2_ctrl_get_name(u32 id)
 	case V4L2_CID_MPEG_VIDEO_HEVC_SIZE_OF_LENGTH_FIELD:	return "HEVC Size of Length Field";
 	case V4L2_CID_MPEG_VIDEO_REF_NUMBER_FOR_PFRAMES:	return "Reference Frames for a P-Frame";
 	case V4L2_CID_MPEG_VIDEO_PREPEND_SPSPPS_TO_IDR:		return "Prepend SPS and PPS to IDR";
+	case V4L2_CID_MPEG_VIDEO_HEVC_SPS:			return "HEVC Sequence Parameter Set";
+	case V4L2_CID_MPEG_VIDEO_HEVC_PPS:			return "HEVC Picture Parameter Set";
+	case V4L2_CID_MPEG_VIDEO_HEVC_SLICE_PARAMS:		return "HEVC Slice Parameters";
+	case V4L2_CID_MPEG_VIDEO_HEVC_DECODE_MODE:		return "HEVC Decode Mode";
+	case V4L2_CID_MPEG_VIDEO_HEVC_START_CODE:		return "HEVC Start Code";
 
 	/* CAMERA controls */
 	/* Keep the order of the 'case's the same as in v4l2-controls.h! */
@@ -994,6 +1014,7 @@ const char *v4l2_ctrl_get_name(u32 id)
 	case V4L2_CID_AUTO_FOCUS_RANGE:		return "Auto Focus, Range";
 	case V4L2_CID_PAN_SPEED:		return "Pan, Speed";
 	case V4L2_CID_TILT_SPEED:		return "Tilt, Speed";
+	case V4L2_CID_UNIT_CELL_SIZE:		return "Unit Cell Size";
 
 	/* FM Radio Modulator controls */
 	/* Keep the order of the 'case's the same as in v4l2-controls.h! */
@@ -1265,6 +1286,8 @@ void v4l2_ctrl_fill(u32 id, const char **name, enum v4l2_ctrl_type *type,
 	case V4L2_CID_MPEG_VIDEO_HEVC_SIZE_OF_LENGTH_FIELD:
 	case V4L2_CID_MPEG_VIDEO_HEVC_TIER:
 	case V4L2_CID_MPEG_VIDEO_HEVC_LOOP_FILTER_MODE:
+	case V4L2_CID_MPEG_VIDEO_HEVC_DECODE_MODE:
+	case V4L2_CID_MPEG_VIDEO_HEVC_START_CODE:
 		*type = V4L2_CTRL_TYPE_MENU;
 		break;
 	case V4L2_CID_LINK_FREQ:
@@ -1375,6 +1398,19 @@ void v4l2_ctrl_fill(u32 id, const char **name, enum v4l2_ctrl_type *type,
 	case V4L2_CID_MPEG_VIDEO_VP8_FRAME_HEADER:
 		*type = V4L2_CTRL_TYPE_VP8_FRAME_HEADER;
 		break;
+	case V4L2_CID_MPEG_VIDEO_HEVC_SPS:
+		*type = V4L2_CTRL_TYPE_HEVC_SPS;
+		break;
+	case V4L2_CID_MPEG_VIDEO_HEVC_PPS:
+		*type = V4L2_CTRL_TYPE_HEVC_PPS;
+		break;
+	case V4L2_CID_MPEG_VIDEO_HEVC_SLICE_PARAMS:
+		*type = V4L2_CTRL_TYPE_HEVC_SLICE_PARAMS;
+		break;
+	case V4L2_CID_UNIT_CELL_SIZE:
+		*type = V4L2_CTRL_TYPE_AREA;
+		*flags |= V4L2_CTRL_FLAG_READ_ONLY;
+		break;
 	default:
 		*type = V4L2_CTRL_TYPE_INTEGER;
 		break;
@@ -1520,7 +1556,8 @@ static bool std_equal(const struct v4l2_ctrl *ctrl, u32 idx,
 		if (ctrl->is_int)
 			return ptr1.p_s32[idx] == ptr2.p_s32[idx];
 		idx *= ctrl->elem_size;
-		return !memcmp(ptr1.p + idx, ptr2.p + idx, ctrl->elem_size);
+		return !memcmp(ptr1.p_const + idx, ptr2.p_const + idx,
+			       ctrl->elem_size);
 	}
 }
 
@@ -1530,7 +1567,10 @@ static void std_init_compound(const struct v4l2_ctrl *ctrl, u32 idx,
 	struct v4l2_ctrl_mpeg2_slice_params *p_mpeg2_slice_params;
 	void *p = ptr.p + idx * ctrl->elem_size;
 
-	memset(p, 0, ctrl->elem_size);
+	if (ctrl->p_def.p_const)
+		memcpy(p, ctrl->p_def.p_const, ctrl->elem_size);
+	else
+		memset(p, 0, ctrl->elem_size);
 
 	/*
 	 * The cast is needed to get rid of a gcc warning complaining that
@@ -1672,7 +1712,12 @@ static int std_validate_compound(const struct v4l2_ctrl *ctrl, u32 idx,
 {
 	struct v4l2_ctrl_mpeg2_slice_params *p_mpeg2_slice_params;
 	struct v4l2_ctrl_vp8_frame_header *p_vp8_frame_header;
+	struct v4l2_ctrl_hevc_sps *p_hevc_sps;
+	struct v4l2_ctrl_hevc_pps *p_hevc_pps;
+	struct v4l2_ctrl_hevc_slice_params *p_hevc_slice_params;
+	struct v4l2_area *area;
 	void *p = ptr.p + idx * ctrl->elem_size;
+	unsigned int i;
 
 	switch ((u32)ctrl->type) {
 	case V4L2_CTRL_TYPE_MPEG2_SLICE_PARAMS:
@@ -1748,6 +1793,76 @@ static int std_validate_compound(const struct v4l2_ctrl *ctrl, u32 idx,
 		zero_padding(p_vp8_frame_header->entropy_header);
 		zero_padding(p_vp8_frame_header->coder_state);
 		break;
+
+	case V4L2_CTRL_TYPE_HEVC_SPS:
+		p_hevc_sps = p;
+
+		if (!(p_hevc_sps->flags & V4L2_HEVC_SPS_FLAG_PCM_ENABLED)) {
+			p_hevc_sps->pcm_sample_bit_depth_luma_minus1 = 0;
+			p_hevc_sps->pcm_sample_bit_depth_chroma_minus1 = 0;
+			p_hevc_sps->log2_min_pcm_luma_coding_block_size_minus3 = 0;
+			p_hevc_sps->log2_diff_max_min_pcm_luma_coding_block_size = 0;
+		}
+
+		if (!(p_hevc_sps->flags &
+		      V4L2_HEVC_SPS_FLAG_LONG_TERM_REF_PICS_PRESENT))
+			p_hevc_sps->num_long_term_ref_pics_sps = 0;
+		break;
+
+	case V4L2_CTRL_TYPE_HEVC_PPS:
+		p_hevc_pps = p;
+
+		if (!(p_hevc_pps->flags &
+		      V4L2_HEVC_PPS_FLAG_CU_QP_DELTA_ENABLED))
+			p_hevc_pps->diff_cu_qp_delta_depth = 0;
+
+		if (!(p_hevc_pps->flags & V4L2_HEVC_PPS_FLAG_TILES_ENABLED)) {
+			p_hevc_pps->num_tile_columns_minus1 = 0;
+			p_hevc_pps->num_tile_rows_minus1 = 0;
+			memset(&p_hevc_pps->column_width_minus1, 0,
+			       sizeof(p_hevc_pps->column_width_minus1));
+			memset(&p_hevc_pps->row_height_minus1, 0,
+			       sizeof(p_hevc_pps->row_height_minus1));
+
+			p_hevc_pps->flags &=
+				~V4L2_HEVC_PPS_FLAG_PPS_LOOP_FILTER_ACROSS_SLICES_ENABLED;
+		}
+
+		if (p_hevc_pps->flags &
+		    V4L2_HEVC_PPS_FLAG_PPS_DISABLE_DEBLOCKING_FILTER) {
+			p_hevc_pps->pps_beta_offset_div2 = 0;
+			p_hevc_pps->pps_tc_offset_div2 = 0;
+		}
+
+		zero_padding(*p_hevc_pps);
+		break;
+
+	case V4L2_CTRL_TYPE_HEVC_SLICE_PARAMS:
+		p_hevc_slice_params = p;
+
+		if (p_hevc_slice_params->num_active_dpb_entries >
+		    V4L2_HEVC_DPB_ENTRIES_NUM_MAX)
+			return -EINVAL;
+
+		zero_padding(p_hevc_slice_params->pred_weight_table);
+
+		for (i = 0; i < p_hevc_slice_params->num_active_dpb_entries;
+		     i++) {
+			struct v4l2_hevc_dpb_entry *dpb_entry =
+				&p_hevc_slice_params->dpb[i];
+
+			zero_padding(*dpb_entry);
+		}
+
+		zero_padding(*p_hevc_slice_params);
+		break;
+
+	case V4L2_CTRL_TYPE_AREA:
+		area = p;
+		if (!area->width || !area->height)
+			return -EINVAL;
+		break;
+
 	default:
 		return -EINVAL;
 	}
@@ -1840,7 +1955,7 @@ static int ptr_to_user(struct v4l2_ext_control *c,
 	u32 len;
 
 	if (ctrl->is_ptr && !ctrl->is_string)
-		return copy_to_user(c->ptr, ptr.p, c->size) ?
+		return copy_to_user(c->ptr, ptr.p_const, c->size) ?
 		       -EFAULT : 0;
 
 	switch (ctrl->type) {
@@ -1955,7 +2070,7 @@ static void ptr_to_ptr(struct v4l2_ctrl *ctrl,
 {
 	if (ctrl == NULL)
 		return;
-	memcpy(to.p, from.p, ctrl->elems * ctrl->elem_size);
+	memcpy(to.p, from.p_const, ctrl->elems * ctrl->elem_size);
 }
 
 /* Copy the new value to the current value. */
@@ -2354,7 +2469,8 @@ static struct v4l2_ctrl *v4l2_ctrl_new(struct v4l2_ctrl_handler *hdl,
 			s64 min, s64 max, u64 step, s64 def,
 			const u32 dims[V4L2_CTRL_MAX_DIMS], u32 elem_size,
 			u32 flags, const char * const *qmenu,
-			const s64 *qmenu_int, void *priv)
+			const s64 *qmenu_int, const union v4l2_ctrl_ptr p_def,
+			void *priv)
 {
 	struct v4l2_ctrl *ctrl;
 	unsigned sz_extra;
@@ -2421,6 +2537,18 @@ static struct v4l2_ctrl *v4l2_ctrl_new(struct v4l2_ctrl_handler *hdl,
 	case V4L2_CTRL_TYPE_VP8_FRAME_HEADER:
 		elem_size = sizeof(struct v4l2_ctrl_vp8_frame_header);
 		break;
+	case V4L2_CTRL_TYPE_HEVC_SPS:
+		elem_size = sizeof(struct v4l2_ctrl_hevc_sps);
+		break;
+	case V4L2_CTRL_TYPE_HEVC_PPS:
+		elem_size = sizeof(struct v4l2_ctrl_hevc_pps);
+		break;
+	case V4L2_CTRL_TYPE_HEVC_SLICE_PARAMS:
+		elem_size = sizeof(struct v4l2_ctrl_hevc_slice_params);
+		break;
+	case V4L2_CTRL_TYPE_AREA:
+		elem_size = sizeof(struct v4l2_area);
+		break;
 	default:
 		if (type < V4L2_CTRL_COMPOUND_TYPES)
 			elem_size = sizeof(s32);
@@ -2460,6 +2588,9 @@ static struct v4l2_ctrl *v4l2_ctrl_new(struct v4l2_ctrl_handler *hdl,
 		 is_array)
 		sz_extra += 2 * tot_ctrl_size;
 
+	if (type >= V4L2_CTRL_COMPOUND_TYPES && p_def.p_const)
+		sz_extra += elem_size;
+
 	ctrl = kvzalloc(sizeof(*ctrl) + sz_extra, GFP_KERNEL);
 	if (ctrl == NULL) {
 		handler_set_err(hdl, -ENOMEM);
@@ -2503,6 +2634,12 @@ static struct v4l2_ctrl *v4l2_ctrl_new(struct v4l2_ctrl_handler *hdl,
 		ctrl->p_new.p = &ctrl->val;
 		ctrl->p_cur.p = &ctrl->cur.val;
 	}
+
+	if (type >= V4L2_CTRL_COMPOUND_TYPES && p_def.p_const) {
+		ctrl->p_def.p = ctrl->p_cur.p + tot_ctrl_size;
+		memcpy(ctrl->p_def.p, p_def.p_const, elem_size);
+	}
+
 	for (idx = 0; idx < elems; idx++) {
 		ctrl->type_ops->init(ctrl, idx, ctrl->p_cur);
 		ctrl->type_ops->init(ctrl, idx, ctrl->p_new);
@@ -2554,7 +2691,7 @@ struct v4l2_ctrl *v4l2_ctrl_new_custom(struct v4l2_ctrl_handler *hdl,
 			type, min, max,
 			is_menu ? cfg->menu_skip_mask : step, def,
 			cfg->dims, cfg->elem_size,
-			flags, qmenu, qmenu_int, priv);
+			flags, qmenu, qmenu_int, cfg->p_def, priv);
 	if (ctrl)
 		ctrl->is_private = cfg->is_private;
 	return ctrl;
@@ -2579,7 +2716,7 @@ struct v4l2_ctrl *v4l2_ctrl_new_std(struct v4l2_ctrl_handler *hdl,
 	}
 	return v4l2_ctrl_new(hdl, ops, NULL, id, name, type,
 			     min, max, step, def, NULL, 0,
-			     flags, NULL, NULL, NULL);
+			     flags, NULL, NULL, ptr_null, NULL);
 }
 EXPORT_SYMBOL(v4l2_ctrl_new_std);
 
@@ -2612,7 +2749,7 @@ struct v4l2_ctrl *v4l2_ctrl_new_std_menu(struct v4l2_ctrl_handler *hdl,
 	}
 	return v4l2_ctrl_new(hdl, ops, NULL, id, name, type,
 			     0, max, mask, def, NULL, 0,
-			     flags, qmenu, qmenu_int, NULL);
+			     flags, qmenu, qmenu_int, ptr_null, NULL);
 }
 EXPORT_SYMBOL(v4l2_ctrl_new_std_menu);
 
@@ -2644,11 +2781,32 @@ struct v4l2_ctrl *v4l2_ctrl_new_std_menu_items(struct v4l2_ctrl_handler *hdl,
 	}
 	return v4l2_ctrl_new(hdl, ops, NULL, id, name, type,
 			     0, max, mask, def, NULL, 0,
-			     flags, qmenu, NULL, NULL);
+			     flags, qmenu, NULL, ptr_null, NULL);
 
 }
 EXPORT_SYMBOL(v4l2_ctrl_new_std_menu_items);
 
+/* Helper function for standard compound controls */
+struct v4l2_ctrl *v4l2_ctrl_new_std_compound(struct v4l2_ctrl_handler *hdl,
+				const struct v4l2_ctrl_ops *ops, u32 id,
+				const union v4l2_ctrl_ptr p_def)
+{
+	const char *name;
+	enum v4l2_ctrl_type type;
+	u32 flags;
+	s64 min, max, step, def;
+
+	v4l2_ctrl_fill(id, &name, &type, &min, &max, &step, &def, &flags);
+	if (type < V4L2_CTRL_COMPOUND_TYPES) {
+		handler_set_err(hdl, -EINVAL);
+		return NULL;
+	}
+	return v4l2_ctrl_new(hdl, ops, NULL, id, name, type,
+			     min, max, step, def, NULL, 0,
+			     flags, NULL, NULL, p_def, NULL);
+}
+EXPORT_SYMBOL(v4l2_ctrl_new_std_compound);
+
 /* Helper function for standard integer menu controls */
 struct v4l2_ctrl *v4l2_ctrl_new_int_menu(struct v4l2_ctrl_handler *hdl,
 			const struct v4l2_ctrl_ops *ops,
@@ -2669,7 +2827,7 @@ struct v4l2_ctrl *v4l2_ctrl_new_int_menu(struct v4l2_ctrl_handler *hdl,
 	}
 	return v4l2_ctrl_new(hdl, ops, NULL, id, name, type,
 			     0, max, 0, def, NULL, 0,
-			     flags, NULL, qmenu_int, NULL);
+			     flags, NULL, qmenu_int, ptr_null, NULL);
 }
 EXPORT_SYMBOL(v4l2_ctrl_new_int_menu);
 
@@ -3144,6 +3302,7 @@ static void v4l2_ctrl_request_queue(struct media_request_object *obj)
 	struct v4l2_ctrl_handler *prev_hdl = NULL;
 	struct v4l2_ctrl_ref *ref_ctrl, *ref_ctrl_prev = NULL;
 
+	mutex_lock(main_hdl->lock);
 	if (list_empty(&main_hdl->requests_queued))
 		goto queue;
 
@@ -3175,18 +3334,22 @@ static void v4l2_ctrl_request_queue(struct media_request_object *obj)
 queue:
 	list_add_tail(&hdl->requests_queued, &main_hdl->requests_queued);
 	hdl->request_is_queued = true;
+	mutex_unlock(main_hdl->lock);
 }
 
 static void v4l2_ctrl_request_unbind(struct media_request_object *obj)
 {
 	struct v4l2_ctrl_handler *hdl =
 		container_of(obj, struct v4l2_ctrl_handler, req_obj);
+	struct v4l2_ctrl_handler *main_hdl = obj->priv;
 
 	list_del_init(&hdl->requests);
+	mutex_lock(main_hdl->lock);
 	if (hdl->request_is_queued) {
 		list_del_init(&hdl->requests_queued);
 		hdl->request_is_queued = false;
 	}
+	mutex_unlock(main_hdl->lock);
 }
 
 static void v4l2_ctrl_request_release(struct media_request_object *obj)
@@ -4080,6 +4243,18 @@ int __v4l2_ctrl_s_ctrl_string(struct v4l2_ctrl *ctrl, const char *s)
 }
 EXPORT_SYMBOL(__v4l2_ctrl_s_ctrl_string);
 
+int __v4l2_ctrl_s_ctrl_area(struct v4l2_ctrl *ctrl,
+			    const struct v4l2_area *area)
+{
+	lockdep_assert_held(ctrl->handler->lock);
+
+	/* It's a driver bug if this happens. */
+	WARN_ON(ctrl->type != V4L2_CTRL_TYPE_AREA);
+	*ctrl->p_new.p_area = *area;
+	return set_ctrl(NULL, ctrl, 0);
+}
+EXPORT_SYMBOL(__v4l2_ctrl_s_ctrl_area);
+
 void v4l2_ctrl_request_complete(struct media_request *req,
 				struct v4l2_ctrl_handler *main_hdl)
 {
@@ -4128,9 +4303,11 @@ void v4l2_ctrl_request_complete(struct media_request *req,
 		v4l2_ctrl_unlock(ctrl);
 	}
 
+	mutex_lock(main_hdl->lock);
 	WARN_ON(!hdl->request_is_queued);
 	list_del_init(&hdl->requests_queued);
 	hdl->request_is_queued = false;
+	mutex_unlock(main_hdl->lock);
 	media_request_object_complete(obj);
 	media_request_object_put(obj);
 }
diff --git a/drivers/media/v4l2-core/v4l2-dev.c b/drivers/media/v4l2-core/v4l2-dev.c
index 4037689a945a..da42d172714a 100644
--- a/drivers/media/v4l2-core/v4l2-dev.c
+++ b/drivers/media/v4l2-core/v4l2-dev.c
@@ -533,13 +533,23 @@ static int get_index(struct video_device *vdev)
  */
 static void determine_valid_ioctls(struct video_device *vdev)
 {
+	const u32 vid_caps = V4L2_CAP_VIDEO_CAPTURE |
+			     V4L2_CAP_VIDEO_CAPTURE_MPLANE |
+			     V4L2_CAP_VIDEO_OUTPUT |
+			     V4L2_CAP_VIDEO_OUTPUT_MPLANE |
+			     V4L2_CAP_VIDEO_M2M | V4L2_CAP_VIDEO_M2M_MPLANE;
+	const u32 meta_caps = V4L2_CAP_META_CAPTURE |
+			      V4L2_CAP_META_OUTPUT;
 	DECLARE_BITMAP(valid_ioctls, BASE_VIDIOC_PRIVATE);
 	const struct v4l2_ioctl_ops *ops = vdev->ioctl_ops;
-	bool is_vid = vdev->vfl_type == VFL_TYPE_GRABBER;
+	bool is_vid = vdev->vfl_type == VFL_TYPE_GRABBER &&
+		      (vdev->device_caps & vid_caps);
 	bool is_vbi = vdev->vfl_type == VFL_TYPE_VBI;
 	bool is_radio = vdev->vfl_type == VFL_TYPE_RADIO;
 	bool is_sdr = vdev->vfl_type == VFL_TYPE_SDR;
 	bool is_tch = vdev->vfl_type == VFL_TYPE_TOUCH;
+	bool is_meta = vdev->vfl_type == VFL_TYPE_GRABBER &&
+		       (vdev->device_caps & meta_caps);
 	bool is_rx = vdev->vfl_dir != VFL_DIR_TX;
 	bool is_tx = vdev->vfl_dir != VFL_DIR_RX;
 
@@ -571,8 +581,10 @@ static void determine_valid_ioctls(struct video_device *vdev)
 		set_bit(_IOC_NR(VIDIOC_TRY_EXT_CTRLS), valid_ioctls);
 	if (vdev->ctrl_handler || ops->vidioc_querymenu)
 		set_bit(_IOC_NR(VIDIOC_QUERYMENU), valid_ioctls);
-	SET_VALID_IOCTL(ops, VIDIOC_G_FREQUENCY, vidioc_g_frequency);
-	SET_VALID_IOCTL(ops, VIDIOC_S_FREQUENCY, vidioc_s_frequency);
+	if (!is_tch) {
+		SET_VALID_IOCTL(ops, VIDIOC_G_FREQUENCY, vidioc_g_frequency);
+		SET_VALID_IOCTL(ops, VIDIOC_S_FREQUENCY, vidioc_s_frequency);
+	}
 	SET_VALID_IOCTL(ops, VIDIOC_LOG_STATUS, vidioc_log_status);
 #ifdef CONFIG_VIDEO_ADV_DEBUG
 	set_bit(_IOC_NR(VIDIOC_DBG_G_CHIP_INFO), valid_ioctls);
@@ -586,40 +598,32 @@ static void determine_valid_ioctls(struct video_device *vdev)
 	if (ops->vidioc_enum_freq_bands || ops->vidioc_g_tuner || ops->vidioc_g_modulator)
 		set_bit(_IOC_NR(VIDIOC_ENUM_FREQ_BANDS), valid_ioctls);
 
-	if (is_vid || is_tch) {
-		/* video and metadata specific ioctls */
+	if (is_vid) {
+		/* video specific ioctls */
 		if ((is_rx && (ops->vidioc_enum_fmt_vid_cap ||
-			       ops->vidioc_enum_fmt_vid_overlay ||
-			       ops->vidioc_enum_fmt_meta_cap)) ||
-		    (is_tx && (ops->vidioc_enum_fmt_vid_out ||
-			       ops->vidioc_enum_fmt_meta_out)))
+			       ops->vidioc_enum_fmt_vid_overlay)) ||
+		    (is_tx && ops->vidioc_enum_fmt_vid_out))
 			set_bit(_IOC_NR(VIDIOC_ENUM_FMT), valid_ioctls);
 		if ((is_rx && (ops->vidioc_g_fmt_vid_cap ||
 			       ops->vidioc_g_fmt_vid_cap_mplane ||
-			       ops->vidioc_g_fmt_vid_overlay ||
-			       ops->vidioc_g_fmt_meta_cap)) ||
+			       ops->vidioc_g_fmt_vid_overlay)) ||
 		    (is_tx && (ops->vidioc_g_fmt_vid_out ||
 			       ops->vidioc_g_fmt_vid_out_mplane ||
-			       ops->vidioc_g_fmt_vid_out_overlay ||
-			       ops->vidioc_g_fmt_meta_out)))
+			       ops->vidioc_g_fmt_vid_out_overlay)))
 			 set_bit(_IOC_NR(VIDIOC_G_FMT), valid_ioctls);
 		if ((is_rx && (ops->vidioc_s_fmt_vid_cap ||
 			       ops->vidioc_s_fmt_vid_cap_mplane ||
-			       ops->vidioc_s_fmt_vid_overlay ||
-			       ops->vidioc_s_fmt_meta_cap)) ||
+			       ops->vidioc_s_fmt_vid_overlay)) ||
 		    (is_tx && (ops->vidioc_s_fmt_vid_out ||
 			       ops->vidioc_s_fmt_vid_out_mplane ||
-			       ops->vidioc_s_fmt_vid_out_overlay ||
-			       ops->vidioc_s_fmt_meta_out)))
+			       ops->vidioc_s_fmt_vid_out_overlay)))
 			 set_bit(_IOC_NR(VIDIOC_S_FMT), valid_ioctls);
 		if ((is_rx && (ops->vidioc_try_fmt_vid_cap ||
 			       ops->vidioc_try_fmt_vid_cap_mplane ||
-			       ops->vidioc_try_fmt_vid_overlay ||
-			       ops->vidioc_try_fmt_meta_cap)) ||
+			       ops->vidioc_try_fmt_vid_overlay)) ||
 		    (is_tx && (ops->vidioc_try_fmt_vid_out ||
 			       ops->vidioc_try_fmt_vid_out_mplane ||
-			       ops->vidioc_try_fmt_vid_out_overlay ||
-			       ops->vidioc_try_fmt_meta_out)))
+			       ops->vidioc_try_fmt_vid_out_overlay)))
 			 set_bit(_IOC_NR(VIDIOC_TRY_FMT), valid_ioctls);
 		SET_VALID_IOCTL(ops, VIDIOC_OVERLAY, vidioc_overlay);
 		SET_VALID_IOCTL(ops, VIDIOC_G_FBUF, vidioc_g_fbuf);
@@ -641,7 +645,21 @@ static void determine_valid_ioctls(struct video_device *vdev)
 			set_bit(_IOC_NR(VIDIOC_S_CROP), valid_ioctls);
 		SET_VALID_IOCTL(ops, VIDIOC_G_SELECTION, vidioc_g_selection);
 		SET_VALID_IOCTL(ops, VIDIOC_S_SELECTION, vidioc_s_selection);
-	} else if (is_vbi) {
+	}
+	if (is_meta && is_rx) {
+		/* metadata capture specific ioctls */
+		SET_VALID_IOCTL(ops, VIDIOC_ENUM_FMT, vidioc_enum_fmt_meta_cap);
+		SET_VALID_IOCTL(ops, VIDIOC_G_FMT, vidioc_g_fmt_meta_cap);
+		SET_VALID_IOCTL(ops, VIDIOC_S_FMT, vidioc_s_fmt_meta_cap);
+		SET_VALID_IOCTL(ops, VIDIOC_TRY_FMT, vidioc_try_fmt_meta_cap);
+	} else if (is_meta && is_tx) {
+		/* metadata output specific ioctls */
+		SET_VALID_IOCTL(ops, VIDIOC_ENUM_FMT, vidioc_enum_fmt_meta_out);
+		SET_VALID_IOCTL(ops, VIDIOC_G_FMT, vidioc_g_fmt_meta_out);
+		SET_VALID_IOCTL(ops, VIDIOC_S_FMT, vidioc_s_fmt_meta_out);
+		SET_VALID_IOCTL(ops, VIDIOC_TRY_FMT, vidioc_try_fmt_meta_out);
+	}
+	if (is_vbi) {
 		/* vbi specific ioctls */
 		if ((is_rx && (ops->vidioc_g_fmt_vbi_cap ||
 			       ops->vidioc_g_fmt_sliced_vbi_cap)) ||
@@ -659,30 +677,35 @@ static void determine_valid_ioctls(struct video_device *vdev)
 			       ops->vidioc_try_fmt_sliced_vbi_out)))
 			set_bit(_IOC_NR(VIDIOC_TRY_FMT), valid_ioctls);
 		SET_VALID_IOCTL(ops, VIDIOC_G_SLICED_VBI_CAP, vidioc_g_sliced_vbi_cap);
+	} else if (is_tch) {
+		/* touch specific ioctls */
+		SET_VALID_IOCTL(ops, VIDIOC_ENUM_FMT, vidioc_enum_fmt_vid_cap);
+		SET_VALID_IOCTL(ops, VIDIOC_G_FMT, vidioc_g_fmt_vid_cap);
+		SET_VALID_IOCTL(ops, VIDIOC_S_FMT, vidioc_s_fmt_vid_cap);
+		SET_VALID_IOCTL(ops, VIDIOC_TRY_FMT, vidioc_try_fmt_vid_cap);
+		SET_VALID_IOCTL(ops, VIDIOC_ENUM_FRAMESIZES, vidioc_enum_framesizes);
+		SET_VALID_IOCTL(ops, VIDIOC_ENUM_FRAMEINTERVALS, vidioc_enum_frameintervals);
+		SET_VALID_IOCTL(ops, VIDIOC_ENUMINPUT, vidioc_enum_input);
+		SET_VALID_IOCTL(ops, VIDIOC_G_INPUT, vidioc_g_input);
+		SET_VALID_IOCTL(ops, VIDIOC_S_INPUT, vidioc_s_input);
+		SET_VALID_IOCTL(ops, VIDIOC_G_PARM, vidioc_g_parm);
+		SET_VALID_IOCTL(ops, VIDIOC_S_PARM, vidioc_s_parm);
 	} else if (is_sdr && is_rx) {
 		/* SDR receiver specific ioctls */
-		if (ops->vidioc_enum_fmt_sdr_cap)
-			set_bit(_IOC_NR(VIDIOC_ENUM_FMT), valid_ioctls);
-		if (ops->vidioc_g_fmt_sdr_cap)
-			set_bit(_IOC_NR(VIDIOC_G_FMT), valid_ioctls);
-		if (ops->vidioc_s_fmt_sdr_cap)
-			set_bit(_IOC_NR(VIDIOC_S_FMT), valid_ioctls);
-		if (ops->vidioc_try_fmt_sdr_cap)
-			set_bit(_IOC_NR(VIDIOC_TRY_FMT), valid_ioctls);
+		SET_VALID_IOCTL(ops, VIDIOC_ENUM_FMT, vidioc_enum_fmt_sdr_cap);
+		SET_VALID_IOCTL(ops, VIDIOC_G_FMT, vidioc_g_fmt_sdr_cap);
+		SET_VALID_IOCTL(ops, VIDIOC_S_FMT, vidioc_s_fmt_sdr_cap);
+		SET_VALID_IOCTL(ops, VIDIOC_TRY_FMT, vidioc_try_fmt_sdr_cap);
 	} else if (is_sdr && is_tx) {
 		/* SDR transmitter specific ioctls */
-		if (ops->vidioc_enum_fmt_sdr_out)
-			set_bit(_IOC_NR(VIDIOC_ENUM_FMT), valid_ioctls);
-		if (ops->vidioc_g_fmt_sdr_out)
-			set_bit(_IOC_NR(VIDIOC_G_FMT), valid_ioctls);
-		if (ops->vidioc_s_fmt_sdr_out)
-			set_bit(_IOC_NR(VIDIOC_S_FMT), valid_ioctls);
-		if (ops->vidioc_try_fmt_sdr_out)
-			set_bit(_IOC_NR(VIDIOC_TRY_FMT), valid_ioctls);
+		SET_VALID_IOCTL(ops, VIDIOC_ENUM_FMT, vidioc_enum_fmt_sdr_out);
+		SET_VALID_IOCTL(ops, VIDIOC_G_FMT, vidioc_g_fmt_sdr_out);
+		SET_VALID_IOCTL(ops, VIDIOC_S_FMT, vidioc_s_fmt_sdr_out);
+		SET_VALID_IOCTL(ops, VIDIOC_TRY_FMT, vidioc_try_fmt_sdr_out);
 	}
 
-	if (is_vid || is_vbi || is_sdr || is_tch) {
-		/* ioctls valid for video, metadata, vbi or sdr */
+	if (is_vid || is_vbi || is_sdr || is_tch || is_meta) {
+		/* ioctls valid for video, vbi, sdr, touch and metadata */
 		SET_VALID_IOCTL(ops, VIDIOC_REQBUFS, vidioc_reqbufs);
 		SET_VALID_IOCTL(ops, VIDIOC_QUERYBUF, vidioc_querybuf);
 		SET_VALID_IOCTL(ops, VIDIOC_QBUF, vidioc_qbuf);
@@ -694,8 +717,8 @@ static void determine_valid_ioctls(struct video_device *vdev)
 		SET_VALID_IOCTL(ops, VIDIOC_STREAMOFF, vidioc_streamoff);
 	}
 
-	if (is_vid || is_vbi || is_tch) {
-		/* ioctls valid for video or vbi */
+	if (is_vid || is_vbi || is_meta) {
+		/* ioctls valid for video, vbi and metadata */
 		if (ops->vidioc_s_std)
 			set_bit(_IOC_NR(VIDIOC_ENUMSTD), valid_ioctls);
 		SET_VALID_IOCTL(ops, VIDIOC_S_STD, vidioc_s_std);
@@ -719,8 +742,7 @@ static void determine_valid_ioctls(struct video_device *vdev)
 			SET_VALID_IOCTL(ops, VIDIOC_G_AUDOUT, vidioc_g_audout);
 			SET_VALID_IOCTL(ops, VIDIOC_S_AUDOUT, vidioc_s_audout);
 		}
-		if (ops->vidioc_g_parm || (vdev->vfl_type == VFL_TYPE_GRABBER &&
-					ops->vidioc_g_std))
+		if (ops->vidioc_g_parm || ops->vidioc_g_std)
 			set_bit(_IOC_NR(VIDIOC_G_PARM), valid_ioctls);
 		SET_VALID_IOCTL(ops, VIDIOC_S_PARM, vidioc_s_parm);
 		SET_VALID_IOCTL(ops, VIDIOC_S_DV_TIMINGS, vidioc_s_dv_timings);
@@ -734,7 +756,7 @@ static void determine_valid_ioctls(struct video_device *vdev)
 		SET_VALID_IOCTL(ops, VIDIOC_G_MODULATOR, vidioc_g_modulator);
 		SET_VALID_IOCTL(ops, VIDIOC_S_MODULATOR, vidioc_s_modulator);
 	}
-	if (is_rx) {
+	if (is_rx && !is_tch) {
 		/* receiver only ioctls */
 		SET_VALID_IOCTL(ops, VIDIOC_G_TUNER, vidioc_g_tuner);
 		SET_VALID_IOCTL(ops, VIDIOC_S_TUNER, vidioc_s_tuner);
diff --git a/drivers/media/v4l2-core/v4l2-dv-timings.c b/drivers/media/v4l2-core/v4l2-dv-timings.c
index 4f23e939ead0..230d65a64217 100644
--- a/drivers/media/v4l2-core/v4l2-dv-timings.c
+++ b/drivers/media/v4l2-core/v4l2-dv-timings.c
@@ -293,7 +293,7 @@ void v4l2_print_dv_timings(const char *dev_prefix, const char *prefix,
 	if (prefix == NULL)
 		prefix = "";
 
-	pr_info("%s: %s%ux%u%s%u.%u (%ux%u)\n", dev_prefix, prefix,
+	pr_info("%s: %s%ux%u%s%u.%02u (%ux%u)\n", dev_prefix, prefix,
 		bt->width, bt->height, bt->interlaced ? "i" : "p",
 		fps / 100, fps % 100, htot, vtot);
 
@@ -757,7 +757,7 @@ bool v4l2_detect_gtf(unsigned frame_height,
 	pix_clk = pix_clk / GTF_PXL_CLK_GRAN * GTF_PXL_CLK_GRAN;
 
 	hsync = (frame_width * 8 + 50) / 100;
-	hsync = ((hsync + GTF_CELL_GRAN / 2) / GTF_CELL_GRAN) * GTF_CELL_GRAN;
+	hsync = DIV_ROUND_CLOSEST(hsync, GTF_CELL_GRAN) * GTF_CELL_GRAN;
 
 	h_fp = h_blank / 2 - hsync;
 
diff --git a/drivers/media/v4l2-core/v4l2-fwnode.c b/drivers/media/v4l2-core/v4l2-fwnode.c
index 3bd1888787eb..192cac076761 100644
--- a/drivers/media/v4l2-core/v4l2-fwnode.c
+++ b/drivers/media/v4l2-core/v4l2-fwnode.c
@@ -512,6 +512,7 @@ void v4l2_fwnode_endpoint_free(struct v4l2_fwnode_endpoint *vep)
 		return;
 
 	kfree(vep->link_frequencies);
+	vep->link_frequencies = NULL;
 }
 EXPORT_SYMBOL_GPL(v4l2_fwnode_endpoint_free);
 
diff --git a/drivers/media/v4l2-core/v4l2-ioctl.c b/drivers/media/v4l2-core/v4l2-ioctl.c
index 51b912743f0f..4e700583659b 100644
--- a/drivers/media/v4l2-core/v4l2-ioctl.c
+++ b/drivers/media/v4l2-core/v4l2-ioctl.c
@@ -932,12 +932,22 @@ static int check_ext_ctrls(struct v4l2_ext_controls *c, int allow_priv)
 
 static int check_fmt(struct file *file, enum v4l2_buf_type type)
 {
+	const u32 vid_caps = V4L2_CAP_VIDEO_CAPTURE |
+			     V4L2_CAP_VIDEO_CAPTURE_MPLANE |
+			     V4L2_CAP_VIDEO_OUTPUT |
+			     V4L2_CAP_VIDEO_OUTPUT_MPLANE |
+			     V4L2_CAP_VIDEO_M2M | V4L2_CAP_VIDEO_M2M_MPLANE;
+	const u32 meta_caps = V4L2_CAP_META_CAPTURE |
+			      V4L2_CAP_META_OUTPUT;
 	struct video_device *vfd = video_devdata(file);
 	const struct v4l2_ioctl_ops *ops = vfd->ioctl_ops;
-	bool is_vid = vfd->vfl_type == VFL_TYPE_GRABBER;
+	bool is_vid = vfd->vfl_type == VFL_TYPE_GRABBER &&
+		      (vfd->device_caps & vid_caps);
 	bool is_vbi = vfd->vfl_type == VFL_TYPE_VBI;
 	bool is_sdr = vfd->vfl_type == VFL_TYPE_SDR;
 	bool is_tch = vfd->vfl_type == VFL_TYPE_TOUCH;
+	bool is_meta = vfd->vfl_type == VFL_TYPE_GRABBER &&
+		       (vfd->device_caps & meta_caps);
 	bool is_rx = vfd->vfl_dir != VFL_DIR_TX;
 	bool is_tx = vfd->vfl_dir != VFL_DIR_RX;
 
@@ -996,11 +1006,11 @@ static int check_fmt(struct file *file, enum v4l2_buf_type type)
 			return 0;
 		break;
 	case V4L2_BUF_TYPE_META_CAPTURE:
-		if (is_vid && is_rx && ops->vidioc_g_fmt_meta_cap)
+		if (is_meta && is_rx && ops->vidioc_g_fmt_meta_cap)
 			return 0;
 		break;
 	case V4L2_BUF_TYPE_META_OUTPUT:
-		if (is_vid && is_tx && ops->vidioc_g_fmt_meta_out)
+		if (is_meta && is_tx && ops->vidioc_g_fmt_meta_out)
 			return 0;
 		break;
 	default:
@@ -1330,6 +1340,7 @@ static void v4l_fill_fmtdesc(struct v4l2_fmtdesc *fmt)
 	case V4L2_META_FMT_VSP1_HGT:	descr = "R-Car VSP1 2-D Histogram"; break;
 	case V4L2_META_FMT_UVC:		descr = "UVC Payload Header Metadata"; break;
 	case V4L2_META_FMT_D4XX:	descr = "Intel D4xx UVC Metadata"; break;
+	case V4L2_META_FMT_VIVID:       descr = "Vivid Metadata"; break;
 
 	default:
 		/* Compressed formats */
@@ -1356,6 +1367,7 @@ static void v4l_fill_fmtdesc(struct v4l2_fmtdesc *fmt)
 		case V4L2_PIX_FMT_VP8_FRAME:    descr = "VP8 Frame"; break;
 		case V4L2_PIX_FMT_VP9:		descr = "VP9"; break;
 		case V4L2_PIX_FMT_HEVC:		descr = "HEVC"; break; /* aka H.265 */
+		case V4L2_PIX_FMT_HEVC_SLICE:	descr = "HEVC Parsed Slice Data"; break;
 		case V4L2_PIX_FMT_FWHT:		descr = "FWHT"; break; /* used in vicodec */
 		case V4L2_PIX_FMT_FWHT_STATELESS:	descr = "FWHT Stateless"; break; /* used in vicodec */
 		case V4L2_PIX_FMT_CPIA1:	descr = "GSPCA CPiA YUV"; break;
@@ -1466,10 +1478,26 @@ static int v4l_enum_fmt(const struct v4l2_ioctl_ops *ops,
 	return ret;
 }
 
+static void v4l_pix_format_touch(struct v4l2_pix_format *p)
+{
+	/*
+	 * The v4l2_pix_format structure contains fields that make no sense for
+	 * touch. Set them to default values in this case.
+	 */
+
+	p->field = V4L2_FIELD_NONE;
+	p->colorspace = V4L2_COLORSPACE_RAW;
+	p->flags = 0;
+	p->ycbcr_enc = 0;
+	p->quantization = 0;
+	p->xfer_func = 0;
+}
+
 static int v4l_g_fmt(const struct v4l2_ioctl_ops *ops,
 				struct file *file, void *fh, void *arg)
 {
 	struct v4l2_format *p = arg;
+	struct video_device *vfd = video_devdata(file);
 	int ret = check_fmt(file, p->type);
 
 	if (ret)
@@ -1507,6 +1535,8 @@ static int v4l_g_fmt(const struct v4l2_ioctl_ops *ops,
 		ret = ops->vidioc_g_fmt_vid_cap(file, fh, arg);
 		/* just in case the driver zeroed it again */
 		p->fmt.pix.priv = V4L2_PIX_FMT_PRIV_MAGIC;
+		if (vfd->vfl_type == VFL_TYPE_TOUCH)
+			v4l_pix_format_touch(&p->fmt.pix);
 		return ret;
 	case V4L2_BUF_TYPE_VIDEO_CAPTURE_MPLANE:
 		return ops->vidioc_g_fmt_vid_cap_mplane(file, fh, arg);
@@ -1544,21 +1574,6 @@ static int v4l_g_fmt(const struct v4l2_ioctl_ops *ops,
 	return -EINVAL;
 }
 
-static void v4l_pix_format_touch(struct v4l2_pix_format *p)
-{
-	/*
-	 * The v4l2_pix_format structure contains fields that make no sense for
-	 * touch. Set them to default values in this case.
-	 */
-
-	p->field = V4L2_FIELD_NONE;
-	p->colorspace = V4L2_COLORSPACE_RAW;
-	p->flags = 0;
-	p->ycbcr_enc = 0;
-	p->quantization = 0;
-	p->xfer_func = 0;
-}
-
 static int v4l_s_fmt(const struct v4l2_ioctl_ops *ops,
 				struct file *file, void *fh, void *arg)
 {
@@ -1602,12 +1617,12 @@ static int v4l_s_fmt(const struct v4l2_ioctl_ops *ops,
 	case V4L2_BUF_TYPE_VBI_CAPTURE:
 		if (unlikely(!ops->vidioc_s_fmt_vbi_cap))
 			break;
-		CLEAR_AFTER_FIELD(p, fmt.vbi);
+		CLEAR_AFTER_FIELD(p, fmt.vbi.flags);
 		return ops->vidioc_s_fmt_vbi_cap(file, fh, arg);
 	case V4L2_BUF_TYPE_SLICED_VBI_CAPTURE:
 		if (unlikely(!ops->vidioc_s_fmt_sliced_vbi_cap))
 			break;
-		CLEAR_AFTER_FIELD(p, fmt.sliced);
+		CLEAR_AFTER_FIELD(p, fmt.sliced.io_size);
 		return ops->vidioc_s_fmt_sliced_vbi_cap(file, fh, arg);
 	case V4L2_BUF_TYPE_VIDEO_OUTPUT:
 		if (unlikely(!ops->vidioc_s_fmt_vid_out))
@@ -1633,22 +1648,22 @@ static int v4l_s_fmt(const struct v4l2_ioctl_ops *ops,
 	case V4L2_BUF_TYPE_VBI_OUTPUT:
 		if (unlikely(!ops->vidioc_s_fmt_vbi_out))
 			break;
-		CLEAR_AFTER_FIELD(p, fmt.vbi);
+		CLEAR_AFTER_FIELD(p, fmt.vbi.flags);
 		return ops->vidioc_s_fmt_vbi_out(file, fh, arg);
 	case V4L2_BUF_TYPE_SLICED_VBI_OUTPUT:
 		if (unlikely(!ops->vidioc_s_fmt_sliced_vbi_out))
 			break;
-		CLEAR_AFTER_FIELD(p, fmt.sliced);
+		CLEAR_AFTER_FIELD(p, fmt.sliced.io_size);
 		return ops->vidioc_s_fmt_sliced_vbi_out(file, fh, arg);
 	case V4L2_BUF_TYPE_SDR_CAPTURE:
 		if (unlikely(!ops->vidioc_s_fmt_sdr_cap))
 			break;
-		CLEAR_AFTER_FIELD(p, fmt.sdr);
+		CLEAR_AFTER_FIELD(p, fmt.sdr.buffersize);
 		return ops->vidioc_s_fmt_sdr_cap(file, fh, arg);
 	case V4L2_BUF_TYPE_SDR_OUTPUT:
 		if (unlikely(!ops->vidioc_s_fmt_sdr_out))
 			break;
-		CLEAR_AFTER_FIELD(p, fmt.sdr);
+		CLEAR_AFTER_FIELD(p, fmt.sdr.buffersize);
 		return ops->vidioc_s_fmt_sdr_out(file, fh, arg);
 	case V4L2_BUF_TYPE_META_CAPTURE:
 		if (unlikely(!ops->vidioc_s_fmt_meta_cap))
@@ -1704,12 +1719,12 @@ static int v4l_try_fmt(const struct v4l2_ioctl_ops *ops,
 	case V4L2_BUF_TYPE_VBI_CAPTURE:
 		if (unlikely(!ops->vidioc_try_fmt_vbi_cap))
 			break;
-		CLEAR_AFTER_FIELD(p, fmt.vbi);
+		CLEAR_AFTER_FIELD(p, fmt.vbi.flags);
 		return ops->vidioc_try_fmt_vbi_cap(file, fh, arg);
 	case V4L2_BUF_TYPE_SLICED_VBI_CAPTURE:
 		if (unlikely(!ops->vidioc_try_fmt_sliced_vbi_cap))
 			break;
-		CLEAR_AFTER_FIELD(p, fmt.sliced);
+		CLEAR_AFTER_FIELD(p, fmt.sliced.io_size);
 		return ops->vidioc_try_fmt_sliced_vbi_cap(file, fh, arg);
 	case V4L2_BUF_TYPE_VIDEO_OUTPUT:
 		if (unlikely(!ops->vidioc_try_fmt_vid_out))
@@ -1735,22 +1750,22 @@ static int v4l_try_fmt(const struct v4l2_ioctl_ops *ops,
 	case V4L2_BUF_TYPE_VBI_OUTPUT:
 		if (unlikely(!ops->vidioc_try_fmt_vbi_out))
 			break;
-		CLEAR_AFTER_FIELD(p, fmt.vbi);
+		CLEAR_AFTER_FIELD(p, fmt.vbi.flags);
 		return ops->vidioc_try_fmt_vbi_out(file, fh, arg);
 	case V4L2_BUF_TYPE_SLICED_VBI_OUTPUT:
 		if (unlikely(!ops->vidioc_try_fmt_sliced_vbi_out))
 			break;
-		CLEAR_AFTER_FIELD(p, fmt.sliced);
+		CLEAR_AFTER_FIELD(p, fmt.sliced.io_size);
 		return ops->vidioc_try_fmt_sliced_vbi_out(file, fh, arg);
 	case V4L2_BUF_TYPE_SDR_CAPTURE:
 		if (unlikely(!ops->vidioc_try_fmt_sdr_cap))
 			break;
-		CLEAR_AFTER_FIELD(p, fmt.sdr);
+		CLEAR_AFTER_FIELD(p, fmt.sdr.buffersize);
 		return ops->vidioc_try_fmt_sdr_cap(file, fh, arg);
 	case V4L2_BUF_TYPE_SDR_OUTPUT:
 		if (unlikely(!ops->vidioc_try_fmt_sdr_out))
 			break;
-		CLEAR_AFTER_FIELD(p, fmt.sdr);
+		CLEAR_AFTER_FIELD(p, fmt.sdr.buffersize);
 		return ops->vidioc_try_fmt_sdr_out(file, fh, arg);
 	case V4L2_BUF_TYPE_META_CAPTURE:
 		if (unlikely(!ops->vidioc_try_fmt_meta_cap))
@@ -2637,7 +2652,7 @@ struct v4l2_ioctl_info {
 /* Zero struct from after the field to the end */
 #define INFO_FL_CLEAR(v4l2_struct, field)			\
 	((offsetof(struct v4l2_struct, field) +			\
-	  sizeof(((struct v4l2_struct *)0)->field)) << 16)
+	  FIELD_SIZEOF(struct v4l2_struct, field)) << 16)
 #define INFO_FL_CLEAR_MASK	(_IOC_SIZEMASK << 16)
 
 #define DEFINE_V4L_STUB_FUNC(_vidioc)				\
diff --git a/drivers/media/v4l2-core/v4l2-mem2mem.c b/drivers/media/v4l2-core/v4l2-mem2mem.c
index 19937dd3c6f6..1afd9c6ad908 100644
--- a/drivers/media/v4l2-core/v4l2-mem2mem.c
+++ b/drivers/media/v4l2-core/v4l2-mem2mem.c
@@ -284,7 +284,8 @@ static void v4l2_m2m_try_run(struct v4l2_m2m_dev *m2m_dev)
 static void __v4l2_m2m_try_queue(struct v4l2_m2m_dev *m2m_dev,
 				 struct v4l2_m2m_ctx *m2m_ctx)
 {
-	unsigned long flags_job, flags_out, flags_cap;
+	unsigned long flags_job;
+	struct vb2_v4l2_buffer *dst, *src;
 
 	dprintk("Trying to schedule a job for m2m_ctx: %p\n", m2m_ctx);
 
@@ -307,20 +308,37 @@ static void __v4l2_m2m_try_queue(struct v4l2_m2m_dev *m2m_dev,
 		goto job_unlock;
 	}
 
-	spin_lock_irqsave(&m2m_ctx->out_q_ctx.rdy_spinlock, flags_out);
-	if (list_empty(&m2m_ctx->out_q_ctx.rdy_queue)
-	    && !m2m_ctx->out_q_ctx.buffered) {
+	src = v4l2_m2m_next_src_buf(m2m_ctx);
+	dst = v4l2_m2m_next_dst_buf(m2m_ctx);
+	if (!src && !m2m_ctx->out_q_ctx.buffered) {
 		dprintk("No input buffers available\n");
-		goto out_unlock;
+		goto job_unlock;
 	}
-	spin_lock_irqsave(&m2m_ctx->cap_q_ctx.rdy_spinlock, flags_cap);
-	if (list_empty(&m2m_ctx->cap_q_ctx.rdy_queue)
-	    && !m2m_ctx->cap_q_ctx.buffered) {
+	if (!dst && !m2m_ctx->cap_q_ctx.buffered) {
 		dprintk("No output buffers available\n");
-		goto cap_unlock;
+		goto job_unlock;
 	}
-	spin_unlock_irqrestore(&m2m_ctx->cap_q_ctx.rdy_spinlock, flags_cap);
-	spin_unlock_irqrestore(&m2m_ctx->out_q_ctx.rdy_spinlock, flags_out);
+
+	m2m_ctx->new_frame = true;
+
+	if (src && dst && dst->is_held &&
+	    dst->vb2_buf.copied_timestamp &&
+	    dst->vb2_buf.timestamp != src->vb2_buf.timestamp) {
+		dst->is_held = false;
+		v4l2_m2m_dst_buf_remove(m2m_ctx);
+		v4l2_m2m_buf_done(dst, VB2_BUF_STATE_DONE);
+		dst = v4l2_m2m_next_dst_buf(m2m_ctx);
+
+		if (!dst && !m2m_ctx->cap_q_ctx.buffered) {
+			dprintk("No output buffers available after returning held buffer\n");
+			goto job_unlock;
+		}
+	}
+
+	if (src && dst && (m2m_ctx->out_q_ctx.q.subsystem_flags &
+			   VB2_V4L2_FL_SUPPORTS_M2M_HOLD_CAPTURE_BUF))
+		m2m_ctx->new_frame = !dst->vb2_buf.copied_timestamp ||
+			dst->vb2_buf.timestamp != src->vb2_buf.timestamp;
 
 	if (m2m_dev->m2m_ops->job_ready
 		&& (!m2m_dev->m2m_ops->job_ready(m2m_ctx->priv))) {
@@ -331,13 +349,6 @@ static void __v4l2_m2m_try_queue(struct v4l2_m2m_dev *m2m_dev,
 	list_add_tail(&m2m_ctx->queue, &m2m_dev->job_queue);
 	m2m_ctx->job_flags |= TRANS_QUEUED;
 
-	spin_unlock_irqrestore(&m2m_dev->job_spinlock, flags_job);
-	return;
-
-cap_unlock:
-	spin_unlock_irqrestore(&m2m_ctx->cap_q_ctx.rdy_spinlock, flags_cap);
-out_unlock:
-	spin_unlock_irqrestore(&m2m_ctx->out_q_ctx.rdy_spinlock, flags_out);
 job_unlock:
 	spin_unlock_irqrestore(&m2m_dev->job_spinlock, flags_job);
 }
@@ -412,37 +423,97 @@ static void v4l2_m2m_cancel_job(struct v4l2_m2m_ctx *m2m_ctx)
 	}
 }
 
-void v4l2_m2m_job_finish(struct v4l2_m2m_dev *m2m_dev,
-			 struct v4l2_m2m_ctx *m2m_ctx)
+/*
+ * Schedule the next job, called from v4l2_m2m_job_finish() or
+ * v4l2_m2m_buf_done_and_job_finish().
+ */
+static void v4l2_m2m_schedule_next_job(struct v4l2_m2m_dev *m2m_dev,
+				       struct v4l2_m2m_ctx *m2m_ctx)
 {
-	unsigned long flags;
+	/*
+	 * This instance might have more buffers ready, but since we do not
+	 * allow more than one job on the job_queue per instance, each has
+	 * to be scheduled separately after the previous one finishes.
+	 */
+	__v4l2_m2m_try_queue(m2m_dev, m2m_ctx);
 
-	spin_lock_irqsave(&m2m_dev->job_spinlock, flags);
+	/*
+	 * We might be running in atomic context,
+	 * but the job must be run in non-atomic context.
+	 */
+	schedule_work(&m2m_dev->job_work);
+}
+
+/*
+ * Assumes job_spinlock is held, called from v4l2_m2m_job_finish() or
+ * v4l2_m2m_buf_done_and_job_finish().
+ */
+static bool _v4l2_m2m_job_finish(struct v4l2_m2m_dev *m2m_dev,
+				 struct v4l2_m2m_ctx *m2m_ctx)
+{
 	if (!m2m_dev->curr_ctx || m2m_dev->curr_ctx != m2m_ctx) {
-		spin_unlock_irqrestore(&m2m_dev->job_spinlock, flags);
 		dprintk("Called by an instance not currently running\n");
-		return;
+		return false;
 	}
 
 	list_del(&m2m_dev->curr_ctx->queue);
 	m2m_dev->curr_ctx->job_flags &= ~(TRANS_QUEUED | TRANS_RUNNING);
 	wake_up(&m2m_dev->curr_ctx->finished);
 	m2m_dev->curr_ctx = NULL;
+	return true;
+}
 
-	spin_unlock_irqrestore(&m2m_dev->job_spinlock, flags);
-
-	/* This instance might have more buffers ready, but since we do not
-	 * allow more than one job on the job_queue per instance, each has
-	 * to be scheduled separately after the previous one finishes. */
-	__v4l2_m2m_try_queue(m2m_dev, m2m_ctx);
+void v4l2_m2m_job_finish(struct v4l2_m2m_dev *m2m_dev,
+			 struct v4l2_m2m_ctx *m2m_ctx)
+{
+	unsigned long flags;
+	bool schedule_next;
 
-	/* We might be running in atomic context,
-	 * but the job must be run in non-atomic context.
+	/*
+	 * This function should not be used for drivers that support
+	 * holding capture buffers. Those should use
+	 * v4l2_m2m_buf_done_and_job_finish() instead.
 	 */
-	schedule_work(&m2m_dev->job_work);
+	WARN_ON(m2m_ctx->out_q_ctx.q.subsystem_flags &
+		VB2_V4L2_FL_SUPPORTS_M2M_HOLD_CAPTURE_BUF);
+	spin_lock_irqsave(&m2m_dev->job_spinlock, flags);
+	schedule_next = _v4l2_m2m_job_finish(m2m_dev, m2m_ctx);
+	spin_unlock_irqrestore(&m2m_dev->job_spinlock, flags);
+
+	if (schedule_next)
+		v4l2_m2m_schedule_next_job(m2m_dev, m2m_ctx);
 }
 EXPORT_SYMBOL(v4l2_m2m_job_finish);
 
+void v4l2_m2m_buf_done_and_job_finish(struct v4l2_m2m_dev *m2m_dev,
+				      struct v4l2_m2m_ctx *m2m_ctx,
+				      enum vb2_buffer_state state)
+{
+	struct vb2_v4l2_buffer *src_buf, *dst_buf;
+	bool schedule_next = false;
+	unsigned long flags;
+
+	spin_lock_irqsave(&m2m_dev->job_spinlock, flags);
+	src_buf = v4l2_m2m_src_buf_remove(m2m_ctx);
+	dst_buf = v4l2_m2m_next_dst_buf(m2m_ctx);
+
+	if (WARN_ON(!src_buf || !dst_buf))
+		goto unlock;
+	v4l2_m2m_buf_done(src_buf, state);
+	dst_buf->is_held = src_buf->flags & V4L2_BUF_FLAG_M2M_HOLD_CAPTURE_BUF;
+	if (!dst_buf->is_held) {
+		v4l2_m2m_dst_buf_remove(m2m_ctx);
+		v4l2_m2m_buf_done(dst_buf, state);
+	}
+	schedule_next = _v4l2_m2m_job_finish(m2m_dev, m2m_ctx);
+unlock:
+	spin_unlock_irqrestore(&m2m_dev->job_spinlock, flags);
+
+	if (schedule_next)
+		v4l2_m2m_schedule_next_job(m2m_dev, m2m_ctx);
+}
+EXPORT_SYMBOL(v4l2_m2m_buf_done_and_job_finish);
+
 int v4l2_m2m_reqbufs(struct file *file, struct v4l2_m2m_ctx *m2m_ctx,
 		     struct v4l2_requestbuffers *reqbufs)
 {
@@ -1154,6 +1225,59 @@ int v4l2_m2m_ioctl_try_decoder_cmd(struct file *file, void *fh,
 }
 EXPORT_SYMBOL_GPL(v4l2_m2m_ioctl_try_decoder_cmd);
 
+int v4l2_m2m_ioctl_stateless_try_decoder_cmd(struct file *file, void *fh,
+					     struct v4l2_decoder_cmd *dc)
+{
+	if (dc->cmd != V4L2_DEC_CMD_FLUSH)
+		return -EINVAL;
+
+	dc->flags = 0;
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(v4l2_m2m_ioctl_stateless_try_decoder_cmd);
+
+int v4l2_m2m_ioctl_stateless_decoder_cmd(struct file *file, void *priv,
+					 struct v4l2_decoder_cmd *dc)
+{
+	struct v4l2_fh *fh = file->private_data;
+	struct vb2_v4l2_buffer *out_vb, *cap_vb;
+	struct v4l2_m2m_dev *m2m_dev = fh->m2m_ctx->m2m_dev;
+	unsigned long flags;
+	int ret;
+
+	ret = v4l2_m2m_ioctl_stateless_try_decoder_cmd(file, priv, dc);
+	if (ret < 0)
+		return ret;
+
+	spin_lock_irqsave(&m2m_dev->job_spinlock, flags);
+	out_vb = v4l2_m2m_last_src_buf(fh->m2m_ctx);
+	cap_vb = v4l2_m2m_last_dst_buf(fh->m2m_ctx);
+
+	/*
+	 * If there is an out buffer pending, then clear any HOLD flag.
+	 *
+	 * By clearing this flag we ensure that when this output
+	 * buffer is processed any held capture buffer will be released.
+	 */
+	if (out_vb) {
+		out_vb->flags &= ~V4L2_BUF_FLAG_M2M_HOLD_CAPTURE_BUF;
+	} else if (cap_vb && cap_vb->is_held) {
+		/*
+		 * If there were no output buffers, but there is a
+		 * capture buffer that is held, then release that
+		 * buffer.
+		 */
+		cap_vb->is_held = false;
+		v4l2_m2m_dst_buf_remove(fh->m2m_ctx);
+		v4l2_m2m_buf_done(cap_vb, VB2_BUF_STATE_DONE);
+	}
+	spin_unlock_irqrestore(&m2m_dev->job_spinlock, flags);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(v4l2_m2m_ioctl_stateless_decoder_cmd);
+
 /*
  * v4l2_file_operations helpers. It is assumed here same lock is used
  * for the output and the capture buffer queue.
diff --git a/drivers/media/v4l2-core/v4l2-subdev.c b/drivers/media/v4l2-core/v4l2-subdev.c
index f725cd9b66b9..9e987c0f840e 100644
--- a/drivers/media/v4l2-core/v4l2-subdev.c
+++ b/drivers/media/v4l2-core/v4l2-subdev.c
@@ -112,7 +112,7 @@ static int subdev_close(struct file *file)
 	return 0;
 }
 
-static inline int check_which(__u32 which)
+static inline int check_which(u32 which)
 {
 	if (which != V4L2_SUBDEV_FORMAT_TRY &&
 	    which != V4L2_SUBDEV_FORMAT_ACTIVE)
@@ -121,7 +121,7 @@ static inline int check_which(__u32 which)
 	return 0;
 }
 
-static inline int check_pad(struct v4l2_subdev *sd, __u32 pad)
+static inline int check_pad(struct v4l2_subdev *sd, u32 pad)
 {
 #if defined(CONFIG_MEDIA_CONTROLLER)
 	if (sd->entity.num_pads) {
@@ -136,7 +136,7 @@ static inline int check_pad(struct v4l2_subdev *sd, __u32 pad)
 	return 0;
 }
 
-static int check_cfg(__u32 which, struct v4l2_subdev_pad_config *cfg)
+static int check_cfg(u32 which, struct v4l2_subdev_pad_config *cfg)
 {
 	if (which == V4L2_SUBDEV_FORMAT_TRY && !cfg)
 		return -EINVAL;
diff --git a/drivers/mfd/intel_soc_pmic_crc.c b/drivers/mfd/intel_soc_pmic_crc.c
index b6ab72fa0569..ab09b8225b76 100644
--- a/drivers/mfd/intel_soc_pmic_crc.c
+++ b/drivers/mfd/intel_soc_pmic_crc.c
@@ -75,7 +75,7 @@ static struct mfd_cell crystal_cove_byt_dev[] = {
 		.resources = gpio_resources,
 	},
 	{
-		.name = "crystal_cove_pmic",
+		.name = "byt_crystal_cove_pmic",
 	},
 	{
 		.name = "crystal_cove_pwm",
diff --git a/drivers/misc/lkdtm/refcount.c b/drivers/misc/lkdtm/refcount.c
index 0a146b32da13..de7c5ab528d9 100644
--- a/drivers/misc/lkdtm/refcount.c
+++ b/drivers/misc/lkdtm/refcount.c
@@ -6,14 +6,6 @@
 #include "lkdtm.h"
 #include <linux/refcount.h>
 
-#ifdef CONFIG_REFCOUNT_FULL
-#define REFCOUNT_MAX		(UINT_MAX - 1)
-#define REFCOUNT_SATURATED	UINT_MAX
-#else
-#define REFCOUNT_MAX		INT_MAX
-#define REFCOUNT_SATURATED	(INT_MIN / 2)
-#endif
-
 static void overflow_check(refcount_t *ref)
 {
 	switch (refcount_read(ref)) {
@@ -127,7 +119,7 @@ void lkdtm_REFCOUNT_DEC_ZERO(void)
 static void check_negative(refcount_t *ref, int start)
 {
 	/*
-	 * CONFIG_REFCOUNT_FULL refuses to move a refcount at all on an
+	 * refcount_t refuses to move a refcount at all on an
 	 * over-sub, so we have to track our starting position instead of
 	 * looking only at zero-pinning.
 	 */
@@ -210,7 +202,6 @@ static void check_from_zero(refcount_t *ref)
 
 /*
  * A refcount_inc() from zero should pin to zero or saturate and may WARN.
- * Only CONFIG_REFCOUNT_FULL provides this protection currently.
  */
 void lkdtm_REFCOUNT_INC_ZERO(void)
 {
diff --git a/drivers/mmc/host/sdhci-acpi.c b/drivers/mmc/host/sdhci-acpi.c
index 1604f512c7bd..105e73d4a3b9 100644
--- a/drivers/mmc/host/sdhci-acpi.c
+++ b/drivers/mmc/host/sdhci-acpi.c
@@ -61,7 +61,7 @@ struct sdhci_acpi_slot {
 	mmc_pm_flag_t	pm_caps;
 	unsigned int	flags;
 	size_t		priv_size;
-	int (*probe_slot)(struct platform_device *, const char *, const char *);
+	int (*probe_slot)(struct platform_device *, struct acpi_device *);
 	int (*remove_slot)(struct platform_device *);
 	int (*free_slot)(struct platform_device *pdev);
 	int (*setup_host)(struct platform_device *pdev);
@@ -325,12 +325,10 @@ static bool sdhci_acpi_cht_pci_wifi(unsigned int vendor, unsigned int device,
  * wifi card in the expected slot with an ACPI companion node, is used to
  * indicate that acpi_device_fix_up_power() should be avoided.
  */
-static inline bool sdhci_acpi_no_fixup_child_power(const char *hid,
-						   const char *uid)
+static inline bool sdhci_acpi_no_fixup_child_power(struct acpi_device *adev)
 {
 	return sdhci_acpi_cht() &&
-	       !strcmp(hid, "80860F14") &&
-	       !strcmp(uid, "2") &&
+	       acpi_dev_hid_uid_match(adev, "80860F14", "2") &&
 	       sdhci_acpi_cht_pci_wifi(0x14e4, 0x43ec, 0, 28);
 }
 
@@ -345,8 +343,7 @@ static inline bool sdhci_acpi_byt_defer(struct device *dev)
 	return false;
 }
 
-static inline bool sdhci_acpi_no_fixup_child_power(const char *hid,
-						   const char *uid)
+static inline bool sdhci_acpi_no_fixup_child_power(struct acpi_device *adev)
 {
 	return false;
 }
@@ -375,19 +372,18 @@ out:
 	return ret;
 }
 
-static int intel_probe_slot(struct platform_device *pdev, const char *hid,
-			    const char *uid)
+static int intel_probe_slot(struct platform_device *pdev, struct acpi_device *adev)
 {
 	struct sdhci_acpi_host *c = platform_get_drvdata(pdev);
 	struct intel_host *intel_host = sdhci_acpi_priv(c);
 	struct sdhci_host *host = c->host;
 
-	if (hid && uid && !strcmp(hid, "80860F14") && !strcmp(uid, "1") &&
+	if (acpi_dev_hid_uid_match(adev, "80860F14", "1") &&
 	    sdhci_readl(host, SDHCI_CAPABILITIES) == 0x446cc8b2 &&
 	    sdhci_readl(host, SDHCI_CAPABILITIES_1) == 0x00000807)
 		host->timeout_clk = 1000; /* 1000 kHz i.e. 1 MHz */
 
-	if (hid && !strcmp(hid, "80865ACA"))
+	if (acpi_dev_hid_uid_match(adev, "80865ACA", NULL))
 		host->mmc_host_ops.get_cd = bxt_get_cd;
 
 	intel_dsm_init(intel_host, &pdev->dev, host->mmc);
@@ -473,8 +469,7 @@ static irqreturn_t sdhci_acpi_qcom_handler(int irq, void *ptr)
 	return IRQ_HANDLED;
 }
 
-static int qcom_probe_slot(struct platform_device *pdev, const char *hid,
-			   const char *uid)
+static int qcom_probe_slot(struct platform_device *pdev, struct acpi_device *adev)
 {
 	struct sdhci_acpi_host *c = platform_get_drvdata(pdev);
 	struct sdhci_host *host = c->host;
@@ -482,7 +477,7 @@ static int qcom_probe_slot(struct platform_device *pdev, const char *hid,
 
 	*irq = -EINVAL;
 
-	if (strcmp(hid, "QCOM8051"))
+	if (!acpi_dev_hid_uid_match(adev, "QCOM8051", NULL))
 		return 0;
 
 	*irq = platform_get_irq(pdev, 1);
@@ -501,14 +496,12 @@ static int qcom_free_slot(struct platform_device *pdev)
 	struct sdhci_host *host = c->host;
 	struct acpi_device *adev;
 	int *irq = sdhci_acpi_priv(c);
-	const char *hid;
 
 	adev = ACPI_COMPANION(dev);
 	if (!adev)
 		return -ENODEV;
 
-	hid = acpi_device_hid(adev);
-	if (strcmp(hid, "QCOM8051"))
+	if (!acpi_dev_hid_uid_match(adev, "QCOM8051", NULL))
 		return 0;
 
 	if (*irq < 0)
@@ -583,7 +576,7 @@ static const struct sdhci_acpi_chip sdhci_acpi_chip_amd = {
 };
 
 static int sdhci_acpi_emmc_amd_probe_slot(struct platform_device *pdev,
-					  const char *hid, const char *uid)
+					  struct acpi_device *adev)
 {
 	struct sdhci_acpi_host *c = platform_get_drvdata(pdev);
 	struct sdhci_host *host   = c->host;
@@ -654,17 +647,12 @@ static const struct acpi_device_id sdhci_acpi_ids[] = {
 };
 MODULE_DEVICE_TABLE(acpi, sdhci_acpi_ids);
 
-static const struct sdhci_acpi_slot *sdhci_acpi_get_slot(const char *hid,
-							 const char *uid)
+static const struct sdhci_acpi_slot *sdhci_acpi_get_slot(struct acpi_device *adev)
 {
 	const struct sdhci_acpi_uid_slot *u;
 
 	for (u = sdhci_acpi_uids; u->hid; u++) {
-		if (strcmp(u->hid, hid))
-			continue;
-		if (!u->uid)
-			return u->slot;
-		if (uid && !strcmp(u->uid, uid))
+		if (acpi_dev_hid_uid_match(adev, u->hid, u->uid))
 			return u->slot;
 	}
 	return NULL;
@@ -680,22 +668,17 @@ static int sdhci_acpi_probe(struct platform_device *pdev)
 	struct resource *iomem;
 	resource_size_t len;
 	size_t priv_size;
-	const char *hid;
-	const char *uid;
 	int err;
 
 	device = ACPI_COMPANION(dev);
 	if (!device)
 		return -ENODEV;
 
-	hid = acpi_device_hid(device);
-	uid = acpi_device_uid(device);
-
-	slot = sdhci_acpi_get_slot(hid, uid);
+	slot = sdhci_acpi_get_slot(device);
 
 	/* Power on the SDHCI controller and its children */
 	acpi_device_fix_up_power(device);
-	if (!sdhci_acpi_no_fixup_child_power(hid, uid)) {
+	if (!sdhci_acpi_no_fixup_child_power(device)) {
 		list_for_each_entry(child, &device->children, node)
 			if (child->status.present && child->status.enabled)
 				acpi_device_fix_up_power(child);
@@ -745,7 +728,7 @@ static int sdhci_acpi_probe(struct platform_device *pdev)
 
 	if (c->slot) {
 		if (c->slot->probe_slot) {
-			err = c->slot->probe_slot(pdev, hid, uid);
+			err = c->slot->probe_slot(pdev, device);
 			if (err)
 				goto err_free;
 		}
diff --git a/drivers/mmc/host/tmio_mmc.h b/drivers/mmc/host/tmio_mmc.h
index 2f0b092d6dcc..c5ba13fae399 100644
--- a/drivers/mmc/host/tmio_mmc.h
+++ b/drivers/mmc/host/tmio_mmc.h
@@ -163,7 +163,6 @@ struct tmio_mmc_host {
 	unsigned long		last_req_ts;
 	struct mutex		ios_lock;	/* protect set_ios() context */
 	bool			native_hotplug;
-	bool			runtime_synced;
 	bool			sdio_irq_enabled;
 
 	/* Mandatory callback */
diff --git a/drivers/mmc/host/tmio_mmc_core.c b/drivers/mmc/host/tmio_mmc_core.c
index 9b6e1001e77c..86b591100f16 100644
--- a/drivers/mmc/host/tmio_mmc_core.c
+++ b/drivers/mmc/host/tmio_mmc_core.c
@@ -39,6 +39,7 @@
 #include <linux/module.h>
 #include <linux/pagemap.h>
 #include <linux/platform_device.h>
+#include <linux/pm_domain.h>
 #include <linux/pm_qos.h>
 #include <linux/pm_runtime.h>
 #include <linux/regulator/consumer.h>
@@ -1248,10 +1249,12 @@ int tmio_mmc_host_probe(struct tmio_mmc_host *_host)
 	/* See if we also get DMA */
 	tmio_mmc_request_dma(_host, pdata);
 
+	dev_pm_domain_start(&pdev->dev);
+	pm_runtime_get_noresume(&pdev->dev);
+	pm_runtime_set_active(&pdev->dev);
 	pm_runtime_set_autosuspend_delay(&pdev->dev, 50);
 	pm_runtime_use_autosuspend(&pdev->dev);
 	pm_runtime_enable(&pdev->dev);
-	pm_runtime_get_sync(&pdev->dev);
 
 	ret = mmc_add_host(mmc);
 	if (ret)
@@ -1333,11 +1336,6 @@ int tmio_mmc_host_runtime_resume(struct device *dev)
 {
 	struct tmio_mmc_host *host = dev_get_drvdata(dev);
 
-	if (!host->runtime_synced) {
-		host->runtime_synced = true;
-		return 0;
-	}
-
 	tmio_mmc_clk_enable(host);
 	tmio_mmc_hw_reset(host->mmc);
 
diff --git a/drivers/nvdimm/Kconfig b/drivers/nvdimm/Kconfig
index 36af7af6b7cf..b7d1eb38b27d 100644
--- a/drivers/nvdimm/Kconfig
+++ b/drivers/nvdimm/Kconfig
@@ -4,6 +4,7 @@ menuconfig LIBNVDIMM
 	depends on PHYS_ADDR_T_64BIT
 	depends on HAS_IOMEM
 	depends on BLK_DEV
+	select MEMREGION
 	help
 	  Generic support for non-volatile memory devices including
 	  ACPI-6-NFIT defined resources.  On platforms that define an
diff --git a/drivers/nvdimm/core.c b/drivers/nvdimm/core.c
index 9204f1e9fd14..e592c4964674 100644
--- a/drivers/nvdimm/core.c
+++ b/drivers/nvdimm/core.c
@@ -455,7 +455,6 @@ static __exit void libnvdimm_exit(void)
 	nd_region_exit();
 	nvdimm_exit();
 	nvdimm_bus_exit();
-	nd_region_devs_exit();
 	nvdimm_devs_exit();
 }
 
diff --git a/drivers/nvdimm/nd-core.h b/drivers/nvdimm/nd-core.h
index 25fa121104d0..aa059439fca0 100644
--- a/drivers/nvdimm/nd-core.h
+++ b/drivers/nvdimm/nd-core.h
@@ -114,7 +114,6 @@ struct nvdimm_bus *walk_to_nvdimm_bus(struct device *nd_dev);
 int __init nvdimm_bus_init(void);
 void nvdimm_bus_exit(void);
 void nvdimm_devs_exit(void);
-void nd_region_devs_exit(void);
 struct nd_region;
 void nd_region_advance_seeds(struct nd_region *nd_region, struct device *dev);
 void nd_region_create_ns_seed(struct nd_region *nd_region);
diff --git a/drivers/nvdimm/region_devs.c b/drivers/nvdimm/region_devs.c
index ef423ba1a711..fbf34cf688f4 100644
--- a/drivers/nvdimm/region_devs.c
+++ b/drivers/nvdimm/region_devs.c
@@ -3,6 +3,7 @@
  * Copyright(c) 2013-2015 Intel Corporation. All rights reserved.
  */
 #include <linux/scatterlist.h>
+#include <linux/memregion.h>
 #include <linux/highmem.h>
 #include <linux/sched.h>
 #include <linux/slab.h>
@@ -19,7 +20,6 @@
  */
 #include <linux/io-64-nonatomic-hi-lo.h>
 
-static DEFINE_IDA(region_ida);
 static DEFINE_PER_CPU(int, flush_idx);
 
 static int nvdimm_map_flush(struct device *dev, struct nvdimm *nvdimm, int dimm,
@@ -133,7 +133,7 @@ static void nd_region_release(struct device *dev)
 		put_device(&nvdimm->dev);
 	}
 	free_percpu(nd_region->lane);
-	ida_simple_remove(&region_ida, nd_region->id);
+	memregion_free(nd_region->id);
 	if (is_nd_blk(dev))
 		kfree(to_nd_blk_region(dev));
 	else
@@ -985,7 +985,7 @@ static struct nd_region *nd_region_create(struct nvdimm_bus *nvdimm_bus,
 
 	if (!region_buf)
 		return NULL;
-	nd_region->id = ida_simple_get(&region_ida, 0, 0, GFP_KERNEL);
+	nd_region->id = memregion_alloc(GFP_KERNEL);
 	if (nd_region->id < 0)
 		goto err_id;
 
@@ -1044,7 +1044,7 @@ static struct nd_region *nd_region_create(struct nvdimm_bus *nvdimm_bus,
 	return nd_region;
 
  err_percpu:
-	ida_simple_remove(&region_ida, nd_region->id);
+	memregion_free(nd_region->id);
  err_id:
 	kfree(region_buf);
 	return NULL;
@@ -1216,8 +1216,3 @@ int nd_region_conflict(struct nd_region *nd_region, resource_size_t start,
 
 	return device_for_each_child(&nvdimm_bus->dev, &ctx, region_conflict);
 }
-
-void __exit nd_region_devs_exit(void)
-{
-	ida_destroy(&region_ida);
-}
diff --git a/drivers/of/property.c b/drivers/of/property.c
index d7fa75e31f22..e8202f61a5d9 100644
--- a/drivers/of/property.c
+++ b/drivers/of/property.c
@@ -872,6 +872,20 @@ of_fwnode_property_read_string_array(const struct fwnode_handle *fwnode,
 		of_property_count_strings(node, propname);
 }
 
+static const char *of_fwnode_get_name(const struct fwnode_handle *fwnode)
+{
+	return kbasename(to_of_node(fwnode)->full_name);
+}
+
+static const char *of_fwnode_get_name_prefix(const struct fwnode_handle *fwnode)
+{
+	/* Root needs no prefix here (its name is "/"). */
+	if (!to_of_node(fwnode)->parent)
+		return "";
+
+	return "/";
+}
+
 static struct fwnode_handle *
 of_fwnode_get_parent(const struct fwnode_handle *fwnode)
 {
@@ -993,6 +1007,8 @@ const struct fwnode_operations of_fwnode_ops = {
 	.property_present = of_fwnode_property_present,
 	.property_read_int_array = of_fwnode_property_read_int_array,
 	.property_read_string_array = of_fwnode_property_read_string_array,
+	.get_name = of_fwnode_get_name,
+	.get_name_prefix = of_fwnode_get_name_prefix,
 	.get_parent = of_fwnode_get_parent,
 	.get_next_child_node = of_fwnode_get_next_child_node,
 	.get_named_child_node = of_fwnode_get_named_child_node,
diff --git a/drivers/opp/core.c b/drivers/opp/core.c
index 9ff0538ee83a..be7a7d332332 100644
--- a/drivers/opp/core.c
+++ b/drivers/opp/core.c
@@ -2103,6 +2103,75 @@ put_table:
 }
 
 /**
+ * dev_pm_opp_adjust_voltage() - helper to change the voltage of an OPP
+ * @dev:		device for which we do this operation
+ * @freq:		OPP frequency to adjust voltage of
+ * @u_volt:		new OPP target voltage
+ * @u_volt_min:		new OPP min voltage
+ * @u_volt_max:		new OPP max voltage
+ *
+ * Return: -EINVAL for bad pointers, -ENOMEM if no memory available for the
+ * copy operation, returns 0 if no modifcation was done OR modification was
+ * successful.
+ */
+int dev_pm_opp_adjust_voltage(struct device *dev, unsigned long freq,
+			      unsigned long u_volt, unsigned long u_volt_min,
+			      unsigned long u_volt_max)
+
+{
+	struct opp_table *opp_table;
+	struct dev_pm_opp *tmp_opp, *opp = ERR_PTR(-ENODEV);
+	int r = 0;
+
+	/* Find the opp_table */
+	opp_table = _find_opp_table(dev);
+	if (IS_ERR(opp_table)) {
+		r = PTR_ERR(opp_table);
+		dev_warn(dev, "%s: Device OPP not found (%d)\n", __func__, r);
+		return r;
+	}
+
+	mutex_lock(&opp_table->lock);
+
+	/* Do we have the frequency? */
+	list_for_each_entry(tmp_opp, &opp_table->opp_list, node) {
+		if (tmp_opp->rate == freq) {
+			opp = tmp_opp;
+			break;
+		}
+	}
+
+	if (IS_ERR(opp)) {
+		r = PTR_ERR(opp);
+		goto adjust_unlock;
+	}
+
+	/* Is update really needed? */
+	if (opp->supplies->u_volt == u_volt)
+		goto adjust_unlock;
+
+	opp->supplies->u_volt = u_volt;
+	opp->supplies->u_volt_min = u_volt_min;
+	opp->supplies->u_volt_max = u_volt_max;
+
+	dev_pm_opp_get(opp);
+	mutex_unlock(&opp_table->lock);
+
+	/* Notify the voltage change of the OPP */
+	blocking_notifier_call_chain(&opp_table->head, OPP_EVENT_ADJUST_VOLTAGE,
+				     opp);
+
+	dev_pm_opp_put(opp);
+	goto adjust_put_table;
+
+adjust_unlock:
+	mutex_unlock(&opp_table->lock);
+adjust_put_table:
+	dev_pm_opp_put_opp_table(opp_table);
+	return r;
+}
+
+/**
  * dev_pm_opp_enable() - Enable a specific OPP
  * @dev:	device for which we do this operation
  * @freq:	OPP frequency to enable
diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c
index a97e2571a527..fcfaadc774ee 100644
--- a/drivers/pci/pci.c
+++ b/drivers/pci/pci.c
@@ -5854,6 +5854,24 @@ int pci_set_vga_state(struct pci_dev *dev, bool decode,
 	return 0;
 }
 
+#ifdef CONFIG_ACPI
+bool pci_pr3_present(struct pci_dev *pdev)
+{
+	struct acpi_device *adev;
+
+	if (acpi_disabled)
+		return false;
+
+	adev = ACPI_COMPANION(&pdev->dev);
+	if (!adev)
+		return false;
+
+	return adev->power.flags.power_resources &&
+		acpi_has_method(adev->handle, "_PR3");
+}
+EXPORT_SYMBOL_GPL(pci_pr3_present);
+#endif
+
 /**
  * pci_add_dma_alias - Add a DMA devfn alias for a device
  * @dev: the PCI device for which alias is added
diff --git a/drivers/platform/chrome/cros_ec_trace.c b/drivers/platform/chrome/cros_ec_trace.c
index 6f80ff4532ae..5af1d66d9eca 100644
--- a/drivers/platform/chrome/cros_ec_trace.c
+++ b/drivers/platform/chrome/cros_ec_trace.c
@@ -98,7 +98,10 @@
 	TRACE_SYMBOL(EC_CMD_SB_READ_BLOCK), \
 	TRACE_SYMBOL(EC_CMD_SB_WRITE_BLOCK), \
 	TRACE_SYMBOL(EC_CMD_BATTERY_VENDOR_PARAM), \
-	TRACE_SYMBOL(EC_CMD_CODEC_I2S), \
+	TRACE_SYMBOL(EC_CMD_EC_CODEC), \
+	TRACE_SYMBOL(EC_CMD_EC_CODEC_DMIC), \
+	TRACE_SYMBOL(EC_CMD_EC_CODEC_I2S_RX), \
+	TRACE_SYMBOL(EC_CMD_EC_CODEC_WOV), \
 	TRACE_SYMBOL(EC_CMD_REBOOT_EC), \
 	TRACE_SYMBOL(EC_CMD_GET_PANIC_INFO), \
 	TRACE_SYMBOL(EC_CMD_ACPI_READ), \
diff --git a/drivers/power/avs/smartreflex.c b/drivers/power/avs/smartreflex.c
index 4684e7df833a..5376f3d22f31 100644
--- a/drivers/power/avs/smartreflex.c
+++ b/drivers/power/avs/smartreflex.c
@@ -905,7 +905,7 @@ static int omap_sr_probe(struct platform_device *pdev)
 	sr_info->dbg_dir = debugfs_create_dir(sr_info->name, sr_dbg_dir);
 
 	debugfs_create_file("autocomp", S_IRUGO | S_IWUSR, sr_info->dbg_dir,
-			    (void *)sr_info, &pm_sr_fops);
+			    sr_info, &pm_sr_fops);
 	debugfs_create_x32("errweight", S_IRUGO, sr_info->dbg_dir,
 			   &sr_info->err_weight);
 	debugfs_create_x32("errmaxlimit", S_IRUGO, sr_info->dbg_dir,
diff --git a/drivers/powercap/intel_rapl_common.c b/drivers/powercap/intel_rapl_common.c
index 94ddd7d659c8..a67701ed93e8 100644
--- a/drivers/powercap/intel_rapl_common.c
+++ b/drivers/powercap/intel_rapl_common.c
@@ -978,6 +978,8 @@ static const struct x86_cpu_id rapl_ids[] __initconst = {
 	INTEL_CPU_FAM6(ICELAKE_NNPI, rapl_defaults_core),
 	INTEL_CPU_FAM6(ICELAKE_X, rapl_defaults_hsw_server),
 	INTEL_CPU_FAM6(ICELAKE_D, rapl_defaults_hsw_server),
+	INTEL_CPU_FAM6(COMETLAKE_L, rapl_defaults_core),
+	INTEL_CPU_FAM6(COMETLAKE, rapl_defaults_core),
 
 	INTEL_CPU_FAM6(ATOM_SILVERMONT, rapl_defaults_byt),
 	INTEL_CPU_FAM6(ATOM_AIRMONT, rapl_defaults_cht),
diff --git a/drivers/scsi/scsi.c b/drivers/scsi/scsi.c
index 1f5b5c8a7f72..7a1b6c76f263 100644
--- a/drivers/scsi/scsi.c
+++ b/drivers/scsi/scsi.c
@@ -434,8 +434,8 @@ static void scsi_update_vpd_page(struct scsi_device *sdev, u8 page,
 		return;
 
 	mutex_lock(&sdev->inquiry_mutex);
-	rcu_swap_protected(*sdev_vpd_buf, vpd_buf,
-			   lockdep_is_held(&sdev->inquiry_mutex));
+	vpd_buf = rcu_replace_pointer(*sdev_vpd_buf, vpd_buf,
+				      lockdep_is_held(&sdev->inquiry_mutex));
 	mutex_unlock(&sdev->inquiry_mutex);
 
 	if (vpd_buf)
diff --git a/drivers/scsi/scsi_sysfs.c b/drivers/scsi/scsi_sysfs.c
index 6d7362e7367e..cc51f4756077 100644
--- a/drivers/scsi/scsi_sysfs.c
+++ b/drivers/scsi/scsi_sysfs.c
@@ -466,10 +466,10 @@ static void scsi_device_dev_release_usercontext(struct work_struct *work)
 	sdev->request_queue = NULL;
 
 	mutex_lock(&sdev->inquiry_mutex);
-	rcu_swap_protected(sdev->vpd_pg80, vpd_pg80,
-			   lockdep_is_held(&sdev->inquiry_mutex));
-	rcu_swap_protected(sdev->vpd_pg83, vpd_pg83,
-			   lockdep_is_held(&sdev->inquiry_mutex));
+	vpd_pg80 = rcu_replace_pointer(sdev->vpd_pg80, vpd_pg80,
+				       lockdep_is_held(&sdev->inquiry_mutex));
+	vpd_pg83 = rcu_replace_pointer(sdev->vpd_pg83, vpd_pg83,
+				       lockdep_is_held(&sdev->inquiry_mutex));
 	mutex_unlock(&sdev->inquiry_mutex);
 
 	if (vpd_pg83)
diff --git a/drivers/staging/media/allegro-dvt/nal-h264.c b/drivers/staging/media/allegro-dvt/nal-h264.c
index 4e14b77851e1..bd48b8883572 100644
--- a/drivers/staging/media/allegro-dvt/nal-h264.c
+++ b/drivers/staging/media/allegro-dvt/nal-h264.c
@@ -235,7 +235,7 @@ static inline int rbsp_write_bit(struct rbsp *rbsp, bool value)
 
 	rbsp->pos++;
 
-	if (value == 1 ||
+	if (value ||
 	    (rbsp->num_consecutive_zeros < 7 && (rbsp->pos % 8 == 0))) {
 		rbsp->num_consecutive_zeros = 0;
 	} else {
diff --git a/drivers/staging/media/hantro/hantro.h b/drivers/staging/media/hantro/hantro.h
index f670bbde4159..deb90ae37859 100644
--- a/drivers/staging/media/hantro/hantro.h
+++ b/drivers/staging/media/hantro/hantro.h
@@ -26,21 +26,9 @@
 
 #include "hantro_hw.h"
 
-#define VP8_MB_DIM			16
-#define VP8_MB_WIDTH(w)			DIV_ROUND_UP(w, VP8_MB_DIM)
-#define VP8_MB_HEIGHT(h)		DIV_ROUND_UP(h, VP8_MB_DIM)
-
-#define H264_MB_DIM			16
-#define H264_MB_WIDTH(w)		DIV_ROUND_UP(w, H264_MB_DIM)
-#define H264_MB_HEIGHT(h)		DIV_ROUND_UP(h, H264_MB_DIM)
-
-#define MPEG2_MB_DIM			16
-#define MPEG2_MB_WIDTH(w)		DIV_ROUND_UP(w, MPEG2_MB_DIM)
-#define MPEG2_MB_HEIGHT(h)		DIV_ROUND_UP(h, MPEG2_MB_DIM)
-
-#define JPEG_MB_DIM			16
-#define JPEG_MB_WIDTH(w)		DIV_ROUND_UP(w, JPEG_MB_DIM)
-#define JPEG_MB_HEIGHT(h)		DIV_ROUND_UP(h, JPEG_MB_DIM)
+#define MB_DIM			16
+#define MB_WIDTH(w)		DIV_ROUND_UP(w, MB_DIM)
+#define MB_HEIGHT(h)		DIV_ROUND_UP(h, MB_DIM)
 
 struct hantro_ctx;
 struct hantro_codec_ops;
@@ -379,7 +367,7 @@ static inline void hantro_reg_write(struct hantro_dev *vpu,
 bool hantro_is_encoder_ctx(const struct hantro_ctx *ctx);
 
 void *hantro_get_ctrl(struct hantro_ctx *ctx, u32 id);
-dma_addr_t hantro_get_ref(struct vb2_queue *q, u64 ts);
+dma_addr_t hantro_get_ref(struct hantro_ctx *ctx, u64 ts);
 
 static inline struct vb2_v4l2_buffer *
 hantro_get_src_buf(struct hantro_ctx *ctx)
diff --git a/drivers/staging/media/hantro/hantro_drv.c b/drivers/staging/media/hantro/hantro_drv.c
index 6d9d41170832..26108c96b674 100644
--- a/drivers/staging/media/hantro/hantro_drv.c
+++ b/drivers/staging/media/hantro/hantro_drv.c
@@ -43,8 +43,9 @@ void *hantro_get_ctrl(struct hantro_ctx *ctx, u32 id)
 	return ctrl ? ctrl->p_cur.p : NULL;
 }
 
-dma_addr_t hantro_get_ref(struct vb2_queue *q, u64 ts)
+dma_addr_t hantro_get_ref(struct hantro_ctx *ctx, u64 ts)
 {
+	struct vb2_queue *q = v4l2_m2m_get_dst_vq(ctx->fh.m2m_ctx);
 	struct vb2_buffer *buf;
 	int index;
 
@@ -413,20 +414,18 @@ static int hantro_open(struct file *filp)
 	if (func->id == MEDIA_ENT_F_PROC_VIDEO_ENCODER) {
 		allowed_codecs = vpu->variant->codec & HANTRO_ENCODERS;
 		ctx->buf_finish = hantro_enc_buf_finish;
-		ctx->fh.m2m_ctx = v4l2_m2m_ctx_init(vpu->m2m_dev, ctx,
-						    queue_init);
 	} else if (func->id == MEDIA_ENT_F_PROC_VIDEO_DECODER) {
 		allowed_codecs = vpu->variant->codec & HANTRO_DECODERS;
 		ctx->buf_finish = hantro_dec_buf_finish;
-		ctx->fh.m2m_ctx = v4l2_m2m_ctx_init(vpu->m2m_dev, ctx,
-						    queue_init);
 	} else {
-		ctx->fh.m2m_ctx = ERR_PTR(-ENODEV);
+		ret = -ENODEV;
+		goto err_ctx_free;
 	}
+
+	ctx->fh.m2m_ctx = v4l2_m2m_ctx_init(vpu->m2m_dev, ctx, queue_init);
 	if (IS_ERR(ctx->fh.m2m_ctx)) {
 		ret = PTR_ERR(ctx->fh.m2m_ctx);
-		kfree(ctx);
-		return ret;
+		goto err_ctx_free;
 	}
 
 	v4l2_fh_init(&ctx->fh, vdev);
@@ -447,6 +446,7 @@ static int hantro_open(struct file *filp)
 err_fh_free:
 	v4l2_fh_del(&ctx->fh);
 	v4l2_fh_exit(&ctx->fh);
+err_ctx_free:
 	kfree(ctx);
 	return ret;
 }
diff --git a/drivers/staging/media/hantro/hantro_g1_h264_dec.c b/drivers/staging/media/hantro/hantro_g1_h264_dec.c
index 7ab534936843..3cd40a8f0daa 100644
--- a/drivers/staging/media/hantro/hantro_g1_h264_dec.c
+++ b/drivers/staging/media/hantro/hantro_g1_h264_dec.c
@@ -34,9 +34,11 @@ static void set_params(struct hantro_ctx *ctx)
 	reg = G1_REG_DEC_CTRL0_DEC_AXI_WR_ID(0x0);
 	if (sps->flags & V4L2_H264_SPS_FLAG_MB_ADAPTIVE_FRAME_FIELD)
 		reg |= G1_REG_DEC_CTRL0_SEQ_MBAFF_E;
-	reg |= G1_REG_DEC_CTRL0_PICORD_COUNT_E;
-	if (dec_param->nal_ref_idc)
-		reg |= G1_REG_DEC_CTRL0_WRITE_MVS_E;
+	if (sps->profile_idc > 66) {
+		reg |= G1_REG_DEC_CTRL0_PICORD_COUNT_E;
+		if (dec_param->nal_ref_idc)
+			reg |= G1_REG_DEC_CTRL0_WRITE_MVS_E;
+	}
 
 	if (!(sps->flags & V4L2_H264_SPS_FLAG_FRAME_MBS_ONLY) &&
 	    (sps->flags & V4L2_H264_SPS_FLAG_MB_ADAPTIVE_FRAME_FIELD ||
@@ -49,8 +51,8 @@ static void set_params(struct hantro_ctx *ctx)
 	vdpu_write_relaxed(vpu, reg, G1_REG_DEC_CTRL0);
 
 	/* Decoder control register 1. */
-	reg = G1_REG_DEC_CTRL1_PIC_MB_WIDTH(sps->pic_width_in_mbs_minus1 + 1) |
-	      G1_REG_DEC_CTRL1_PIC_MB_HEIGHT_P(sps->pic_height_in_map_units_minus1 + 1) |
+	reg = G1_REG_DEC_CTRL1_PIC_MB_WIDTH(MB_WIDTH(ctx->src_fmt.width)) |
+	      G1_REG_DEC_CTRL1_PIC_MB_HEIGHT_P(MB_HEIGHT(ctx->src_fmt.height)) |
 	      G1_REG_DEC_CTRL1_REF_FRAMES(sps->max_num_ref_frames);
 	vdpu_write_relaxed(vpu, reg, G1_REG_DEC_CTRL1);
 
@@ -61,7 +63,7 @@ static void set_params(struct hantro_ctx *ctx)
 	/* always use the matrix sent from userspace */
 	reg |= G1_REG_DEC_CTRL2_TYPE1_QUANT_E;
 
-	if (slices[0].flags &  V4L2_H264_SLICE_FLAG_FIELD_PIC)
+	if (!(sps->flags & V4L2_H264_SPS_FLAG_FRAME_MBS_ONLY))
 		reg |= G1_REG_DEC_CTRL2_FIELDPIC_FLAG_E;
 	vdpu_write_relaxed(vpu, reg, G1_REG_DEC_CTRL2);
 
@@ -79,7 +81,7 @@ static void set_params(struct hantro_ctx *ctx)
 		reg |= G1_REG_DEC_CTRL4_CABAC_E;
 	if (sps->flags & V4L2_H264_SPS_FLAG_DIRECT_8X8_INFERENCE)
 		reg |= G1_REG_DEC_CTRL4_DIR_8X8_INFER_E;
-	if (sps->chroma_format_idc == 0)
+	if (sps->profile_idc >= 100 && sps->chroma_format_idc == 0)
 		reg |= G1_REG_DEC_CTRL4_BLACKWHITE_E;
 	if (pps->flags & V4L2_H264_PPS_FLAG_WEIGHTED_PRED)
 		reg |= G1_REG_DEC_CTRL4_WEIGHT_PRED_E;
@@ -220,10 +222,9 @@ static void set_ref(struct hantro_ctx *ctx)
 
 	/* Set up addresses of DPB buffers. */
 	for (i = 0; i < HANTRO_H264_DPB_SIZE; i++) {
-		struct vb2_buffer *buf =  hantro_h264_get_ref_buf(ctx, i);
+		dma_addr_t dma_addr = hantro_h264_get_ref_buf(ctx, i);
 
-		vdpu_write_relaxed(vpu, vb2_dma_contig_plane_dma_addr(buf, 0),
-				   G1_REG_ADDR_REF(i));
+		vdpu_write_relaxed(vpu, dma_addr, G1_REG_ADDR_REF(i));
 	}
 }
 
@@ -233,6 +234,7 @@ static void set_buffers(struct hantro_ctx *ctx)
 	struct vb2_v4l2_buffer *src_buf, *dst_buf;
 	struct hantro_dev *vpu = ctx->dev;
 	dma_addr_t src_dma, dst_dma;
+	size_t offset = 0;
 
 	src_buf = hantro_get_src_buf(ctx);
 	dst_buf = hantro_get_dst_buf(ctx);
@@ -243,18 +245,30 @@ static void set_buffers(struct hantro_ctx *ctx)
 
 	/* Destination (decoded frame) buffer. */
 	dst_dma = vb2_dma_contig_plane_dma_addr(&dst_buf->vb2_buf, 0);
-	vdpu_write_relaxed(vpu, dst_dma, G1_REG_ADDR_DST);
+	/* Adjust dma addr to start at second line for bottom field */
+	if (ctrls->slices[0].flags & V4L2_H264_SLICE_FLAG_BOTTOM_FIELD)
+		offset = ALIGN(ctx->src_fmt.width, MB_DIM);
+	vdpu_write_relaxed(vpu, dst_dma + offset, G1_REG_ADDR_DST);
 
 	/* Higher profiles require DMV buffer appended to reference frames. */
-	if (ctrls->sps->profile_idc > 66) {
-		size_t pic_size = ctx->h264_dec.pic_size;
-		size_t mv_offset = round_up(pic_size, 8);
-
+	if (ctrls->sps->profile_idc > 66 && ctrls->decode->nal_ref_idc) {
+		unsigned int bytes_per_mb = 384;
+
+		/* DMV buffer for monochrome start directly after Y-plane */
+		if (ctrls->sps->profile_idc >= 100 &&
+		    ctrls->sps->chroma_format_idc == 0)
+			bytes_per_mb = 256;
+		offset = bytes_per_mb * MB_WIDTH(ctx->src_fmt.width) *
+			 MB_HEIGHT(ctx->src_fmt.height);
+
+		/*
+		 * DMV buffer is split in two for field encoded frames,
+		 * adjust offset for bottom field
+		 */
 		if (ctrls->slices[0].flags & V4L2_H264_SLICE_FLAG_BOTTOM_FIELD)
-			mv_offset += 32 * H264_MB_WIDTH(ctx->dst_fmt.width);
-
-		vdpu_write_relaxed(vpu, dst_dma + mv_offset,
-				   G1_REG_ADDR_DIR_MV);
+			offset += 32 * MB_WIDTH(ctx->src_fmt.width) *
+				  MB_HEIGHT(ctx->src_fmt.height);
+		vdpu_write_relaxed(vpu, dst_dma + offset, G1_REG_ADDR_DIR_MV);
 	}
 
 	/* Auxiliary buffer prepared in hantro_g1_h264_dec_prepare_table(). */
diff --git a/drivers/staging/media/hantro/hantro_g1_mpeg2_dec.c b/drivers/staging/media/hantro/hantro_g1_mpeg2_dec.c
index 80f0e94f8afa..f3bf67d8a289 100644
--- a/drivers/staging/media/hantro/hantro_g1_mpeg2_dec.c
+++ b/drivers/staging/media/hantro/hantro_g1_mpeg2_dec.c
@@ -105,17 +105,14 @@ hantro_g1_mpeg2_dec_set_buffers(struct hantro_dev *vpu, struct hantro_ctx *ctx,
 {
 	dma_addr_t forward_addr = 0, backward_addr = 0;
 	dma_addr_t current_addr, addr;
-	struct vb2_queue *vq;
-
-	vq = v4l2_m2m_get_dst_vq(ctx->fh.m2m_ctx);
 
 	switch (picture->picture_coding_type) {
 	case V4L2_MPEG2_PICTURE_CODING_TYPE_B:
-		backward_addr = hantro_get_ref(vq,
+		backward_addr = hantro_get_ref(ctx,
 					       slice_params->backward_ref_ts);
 		/* fall-through */
 	case V4L2_MPEG2_PICTURE_CODING_TYPE_P:
-		forward_addr = hantro_get_ref(vq,
+		forward_addr = hantro_get_ref(ctx,
 					      slice_params->forward_ref_ts);
 	}
 
@@ -207,8 +204,8 @@ void hantro_g1_mpeg2_dec_run(struct hantro_ctx *ctx)
 	      G1_REG_DEC_AXI_WR_ID(0);
 	vdpu_write_relaxed(vpu, reg, G1_SWREG(3));
 
-	reg = G1_REG_PIC_MB_WIDTH(MPEG2_MB_WIDTH(ctx->dst_fmt.width)) |
-	      G1_REG_PIC_MB_HEIGHT_P(MPEG2_MB_HEIGHT(ctx->dst_fmt.height)) |
+	reg = G1_REG_PIC_MB_WIDTH(MB_WIDTH(ctx->dst_fmt.width)) |
+	      G1_REG_PIC_MB_HEIGHT_P(MB_HEIGHT(ctx->dst_fmt.height)) |
 	      G1_REG_ALT_SCAN_E(picture->alternate_scan) |
 	      G1_REG_TOPFIELDFIRST_E(picture->top_field_first);
 	vdpu_write_relaxed(vpu, reg, G1_SWREG(4));
diff --git a/drivers/staging/media/hantro/hantro_g1_vp8_dec.c b/drivers/staging/media/hantro/hantro_g1_vp8_dec.c
index 6d99c2be01cf..cad18094fee0 100644
--- a/drivers/staging/media/hantro/hantro_g1_vp8_dec.c
+++ b/drivers/staging/media/hantro/hantro_g1_vp8_dec.c
@@ -370,19 +370,18 @@ static void cfg_tap(struct hantro_ctx *ctx,
 static void cfg_ref(struct hantro_ctx *ctx,
 		    const struct v4l2_ctrl_vp8_frame_header *hdr)
 {
-	struct vb2_queue *cap_q = &ctx->fh.m2m_ctx->cap_q_ctx.q;
 	struct hantro_dev *vpu = ctx->dev;
 	struct vb2_v4l2_buffer *vb2_dst;
 	dma_addr_t ref;
 
 	vb2_dst = hantro_get_dst_buf(ctx);
 
-	ref = hantro_get_ref(cap_q, hdr->last_frame_ts);
+	ref = hantro_get_ref(ctx, hdr->last_frame_ts);
 	if (!ref)
 		ref = vb2_dma_contig_plane_dma_addr(&vb2_dst->vb2_buf, 0);
 	vdpu_write_relaxed(vpu, ref, G1_REG_ADDR_REF(0));
 
-	ref = hantro_get_ref(cap_q, hdr->golden_frame_ts);
+	ref = hantro_get_ref(ctx, hdr->golden_frame_ts);
 	WARN_ON(!ref && hdr->golden_frame_ts);
 	if (!ref)
 		ref = vb2_dma_contig_plane_dma_addr(&vb2_dst->vb2_buf, 0);
@@ -390,7 +389,7 @@ static void cfg_ref(struct hantro_ctx *ctx,
 		ref |= G1_REG_ADDR_REF_TOPC_E;
 	vdpu_write_relaxed(vpu, ref, G1_REG_ADDR_REF(4));
 
-	ref = hantro_get_ref(cap_q, hdr->alt_frame_ts);
+	ref = hantro_get_ref(ctx, hdr->alt_frame_ts);
 	WARN_ON(!ref && hdr->alt_frame_ts);
 	if (!ref)
 		ref = vb2_dma_contig_plane_dma_addr(&vb2_dst->vb2_buf, 0);
@@ -470,8 +469,8 @@ void hantro_g1_vp8_dec_run(struct hantro_ctx *ctx)
 	vdpu_write_relaxed(vpu, reg, G1_REG_DEC_CTRL0);
 
 	/* Frame dimensions */
-	mb_width = VP8_MB_WIDTH(width);
-	mb_height = VP8_MB_HEIGHT(height);
+	mb_width = MB_WIDTH(width);
+	mb_height = MB_HEIGHT(height);
 	reg = G1_REG_DEC_CTRL1_PIC_MB_WIDTH(mb_width) |
 	      G1_REG_DEC_CTRL1_PIC_MB_HEIGHT_P(mb_height) |
 	      G1_REG_DEC_CTRL1_PIC_MB_W_EXT(mb_width >> 9) |
diff --git a/drivers/staging/media/hantro/hantro_h1_jpeg_enc.c b/drivers/staging/media/hantro/hantro_h1_jpeg_enc.c
index ecd34a7db190..938b48d4d3d9 100644
--- a/drivers/staging/media/hantro/hantro_h1_jpeg_enc.c
+++ b/drivers/staging/media/hantro/hantro_h1_jpeg_enc.c
@@ -116,8 +116,8 @@ void hantro_h1_jpeg_enc_run(struct hantro_ctx *ctx)
 	/* Make sure that all registers are written at this point. */
 	vepu_write(vpu, reg, H1_REG_AXI_CTRL);
 
-	reg = H1_REG_ENC_CTRL_WIDTH(JPEG_MB_WIDTH(ctx->src_fmt.width))
-		| H1_REG_ENC_CTRL_HEIGHT(JPEG_MB_HEIGHT(ctx->src_fmt.height))
+	reg = H1_REG_ENC_CTRL_WIDTH(MB_WIDTH(ctx->src_fmt.width))
+		| H1_REG_ENC_CTRL_HEIGHT(MB_HEIGHT(ctx->src_fmt.height))
 		| H1_REG_ENC_CTRL_ENC_MODE_JPEG
 		| H1_REG_ENC_PIC_INTRA
 		| H1_REG_ENC_CTRL_EN_BIT;
diff --git a/drivers/staging/media/hantro/hantro_h264.c b/drivers/staging/media/hantro/hantro_h264.c
index 0d758e0c0f99..568640eab3a6 100644
--- a/drivers/staging/media/hantro/hantro_h264.c
+++ b/drivers/staging/media/hantro/hantro_h264.c
@@ -20,9 +20,9 @@
 /* Size with u32 units. */
 #define CABAC_INIT_BUFFER_SIZE		(460 * 2)
 #define POC_BUFFER_SIZE			34
-#define SCALING_LIST_SIZE		(6 * 16 + 6 * 64)
+#define SCALING_LIST_SIZE		(6 * 16 + 2 * 64)
 
-#define POC_CMP(p0, p1) ((p0) < (p1) ? -1 : 1)
+#define HANTRO_CMP(a, b) ((a) < (b) ? -1 : 1)
 
 /* Data structure describing auxiliary buffer format. */
 struct hantro_h264_dec_priv_tbl {
@@ -194,23 +194,6 @@ static const u32 h264_cabac_table[] = {
 	0x1f0c2517, 0x1f261440
 };
 
-/*
- * NOTE: The scaling lists are in zig-zag order, apply inverse scanning process
- * to get the values in matrix order. In addition, the hardware requires bytes
- * swapped within each subsequent 4 bytes. Both arrays below include both
- * transformations.
- */
-static const u32 zig_zag_4x4[] = {
-	3, 2, 7, 11, 6, 1, 0, 5, 10, 15, 14, 9, 4, 8, 13, 12
-};
-
-static const u32 zig_zag_8x8[] = {
-	3, 2, 11, 19, 10, 1, 0, 9, 18, 27, 35, 26, 17, 8, 7, 6,
-	15, 16, 25, 34, 43, 51, 42, 33, 24, 23, 14, 5, 4, 13, 22, 31,
-	32, 41, 50, 59, 58, 49, 40, 39, 30, 21, 12, 20, 29, 38, 47, 48,
-	57, 56, 55, 46, 37, 28, 36, 45, 54, 63, 62, 53, 44, 52, 61, 60
-};
-
 static void
 reorder_scaling_list(struct hantro_ctx *ctx)
 {
@@ -218,33 +201,23 @@ reorder_scaling_list(struct hantro_ctx *ctx)
 	const struct v4l2_ctrl_h264_scaling_matrix *scaling = ctrls->scaling;
 	const size_t num_list_4x4 = ARRAY_SIZE(scaling->scaling_list_4x4);
 	const size_t list_len_4x4 = ARRAY_SIZE(scaling->scaling_list_4x4[0]);
-	const size_t num_list_8x8 = ARRAY_SIZE(scaling->scaling_list_8x8);
 	const size_t list_len_8x8 = ARRAY_SIZE(scaling->scaling_list_8x8[0]);
 	struct hantro_h264_dec_priv_tbl *tbl = ctx->h264_dec.priv.cpu;
-	u8 *dst = tbl->scaling_list;
-	const u8 *src;
+	u32 *dst = (u32 *)tbl->scaling_list;
+	const u32 *src;
 	int i, j;
 
-	BUILD_BUG_ON(ARRAY_SIZE(zig_zag_4x4) != list_len_4x4);
-	BUILD_BUG_ON(ARRAY_SIZE(zig_zag_8x8) != list_len_8x8);
-	BUILD_BUG_ON(ARRAY_SIZE(tbl->scaling_list) !=
-		     num_list_4x4 * list_len_4x4 +
-		     num_list_8x8 * list_len_8x8);
-
-	src = &scaling->scaling_list_4x4[0][0];
-	for (i = 0; i < num_list_4x4; ++i) {
-		for (j = 0; j < list_len_4x4; ++j)
-			dst[zig_zag_4x4[j]] = src[j];
-		src += list_len_4x4;
-		dst += list_len_4x4;
+	for (i = 0; i < num_list_4x4; i++) {
+		src = (u32 *)&scaling->scaling_list_4x4[i];
+		for (j = 0; j < list_len_4x4 / 4; j++)
+			*dst++ = swab32(src[j]);
 	}
 
-	src = &scaling->scaling_list_8x8[0][0];
-	for (i = 0; i < num_list_8x8; ++i) {
-		for (j = 0; j < list_len_8x8; ++j)
-			dst[zig_zag_8x8[j]] = src[j];
-		src += list_len_8x8;
-		dst += list_len_8x8;
+	/* Only Intra/Inter Y lists */
+	for (i = 0; i < 2; i++) {
+		src = (u32 *)&scaling->scaling_list_8x8[i];
+		for (j = 0; j < list_len_8x8 / 4; j++)
+			*dst++ = swab32(src[j]);
 	}
 }
 
@@ -271,6 +244,7 @@ struct hantro_h264_reflist_builder {
 	const struct v4l2_h264_dpb_entry *dpb;
 	s32 pocs[HANTRO_H264_DPB_SIZE];
 	u8 unordered_reflist[HANTRO_H264_DPB_SIZE];
+	int frame_nums[HANTRO_H264_DPB_SIZE];
 	s32 curpoc;
 	u8 num_valid;
 };
@@ -294,13 +268,20 @@ static void
 init_reflist_builder(struct hantro_ctx *ctx,
 		     struct hantro_h264_reflist_builder *b)
 {
+	const struct v4l2_ctrl_h264_slice_params *slice_params;
 	const struct v4l2_ctrl_h264_decode_params *dec_param;
+	const struct v4l2_ctrl_h264_sps *sps;
 	struct vb2_v4l2_buffer *buf = hantro_get_dst_buf(ctx);
 	const struct v4l2_h264_dpb_entry *dpb = ctx->h264_dec.dpb;
 	struct vb2_queue *cap_q = &ctx->fh.m2m_ctx->cap_q_ctx.q;
+	int cur_frame_num, max_frame_num;
 	unsigned int i;
 
 	dec_param = ctx->h264_dec.ctrls.decode;
+	slice_params = &ctx->h264_dec.ctrls.slices[0];
+	sps = ctx->h264_dec.ctrls.sps;
+	max_frame_num = 1 << (sps->log2_max_frame_num_minus4 + 4);
+	cur_frame_num = slice_params->frame_num;
 
 	memset(b, 0, sizeof(*b));
 	b->dpb = dpb;
@@ -318,6 +299,18 @@ init_reflist_builder(struct hantro_ctx *ctx,
 			continue;
 
 		buf = to_vb2_v4l2_buffer(vb2_get_buffer(cap_q, buf_idx));
+
+		/*
+		 * Handle frame_num wraparound as described in section
+		 * '8.2.4.1 Decoding process for picture numbers' of the spec.
+		 * TODO: This logic will have to be adjusted when we start
+		 * supporting interlaced content.
+		 */
+		if (dpb[i].frame_num > cur_frame_num)
+			b->frame_nums[i] = (int)dpb[i].frame_num - max_frame_num;
+		else
+			b->frame_nums[i] = dpb[i].frame_num;
+
 		b->pocs[i] = get_poc(buf->field, dpb[i].top_field_order_cnt,
 				     dpb[i].bottom_field_order_cnt);
 		b->unordered_reflist[b->num_valid] = i;
@@ -353,9 +346,10 @@ static int p_ref_list_cmp(const void *ptra, const void *ptrb, const void *data)
 	 * ascending order.
 	 */
 	if (!(a->flags & V4L2_H264_DPB_ENTRY_FLAG_LONG_TERM))
-		return b->frame_num - a->frame_num;
+		return HANTRO_CMP(builder->frame_nums[idxb],
+				  builder->frame_nums[idxa]);
 
-	return a->pic_num - b->pic_num;
+	return HANTRO_CMP(a->pic_num, b->pic_num);
 }
 
 static int b0_ref_list_cmp(const void *ptra, const void *ptrb, const void *data)
@@ -381,7 +375,7 @@ static int b0_ref_list_cmp(const void *ptra, const void *ptrb, const void *data)
 
 	/* Long term pics in ascending pic num order. */
 	if (a->flags & V4L2_H264_DPB_ENTRY_FLAG_LONG_TERM)
-		return a->pic_num - b->pic_num;
+		return HANTRO_CMP(a->pic_num, b->pic_num);
 
 	poca = builder->pocs[idxa];
 	pocb = builder->pocs[idxb];
@@ -392,11 +386,11 @@ static int b0_ref_list_cmp(const void *ptra, const void *ptrb, const void *data)
 	 * order.
 	 */
 	if ((poca < builder->curpoc) != (pocb < builder->curpoc))
-		return POC_CMP(poca, pocb);
+		return HANTRO_CMP(poca, pocb);
 	else if (poca < builder->curpoc)
-		return POC_CMP(pocb, poca);
+		return HANTRO_CMP(pocb, poca);
 
-	return POC_CMP(poca, pocb);
+	return HANTRO_CMP(poca, pocb);
 }
 
 static int b1_ref_list_cmp(const void *ptra, const void *ptrb, const void *data)
@@ -422,22 +416,22 @@ static int b1_ref_list_cmp(const void *ptra, const void *ptrb, const void *data)
 
 	/* Long term pics in ascending pic num order. */
 	if (a->flags & V4L2_H264_DPB_ENTRY_FLAG_LONG_TERM)
-		return a->pic_num - b->pic_num;
+		return HANTRO_CMP(a->pic_num, b->pic_num);
 
 	poca = builder->pocs[idxa];
 	pocb = builder->pocs[idxb];
 
 	/*
 	 * Short term pics with POC > cur POC first in POC ascending order
-	 * followed by short term pics with POC > cur POC in POC descending
+	 * followed by short term pics with POC < cur POC in POC descending
 	 * order.
 	 */
 	if ((poca < builder->curpoc) != (pocb < builder->curpoc))
-		return POC_CMP(pocb, poca);
+		return HANTRO_CMP(pocb, poca);
 	else if (poca < builder->curpoc)
-		return POC_CMP(pocb, poca);
+		return HANTRO_CMP(pocb, poca);
 
-	return POC_CMP(poca, pocb);
+	return HANTRO_CMP(poca, pocb);
 }
 
 static void
@@ -537,22 +531,18 @@ static void update_dpb(struct hantro_ctx *ctx)
 	}
 }
 
-struct vb2_buffer *hantro_h264_get_ref_buf(struct hantro_ctx *ctx,
-					   unsigned int dpb_idx)
+dma_addr_t hantro_h264_get_ref_buf(struct hantro_ctx *ctx,
+				   unsigned int dpb_idx)
 {
-	struct vb2_queue *cap_q = &ctx->fh.m2m_ctx->cap_q_ctx.q;
 	struct v4l2_h264_dpb_entry *dpb = ctx->h264_dec.dpb;
-	struct vb2_buffer *buf;
-	int buf_idx = -1;
+	dma_addr_t dma_addr = 0;
 
 	if (dpb[dpb_idx].flags & V4L2_H264_DPB_ENTRY_FLAG_ACTIVE)
-		buf_idx = vb2_find_timestamp(cap_q,
-					     dpb[dpb_idx].reference_ts, 0);
+		dma_addr = hantro_get_ref(ctx, dpb[dpb_idx].reference_ts);
 
-	if (buf_idx >= 0) {
-		buf = vb2_get_buffer(cap_q, buf_idx);
-	} else {
+	if (!dma_addr) {
 		struct vb2_v4l2_buffer *dst_buf;
+		struct vb2_buffer *buf;
 
 		/*
 		 * If a DPB entry is unused or invalid, address of current
@@ -560,9 +550,10 @@ struct vb2_buffer *hantro_h264_get_ref_buf(struct hantro_ctx *ctx,
 		 */
 		dst_buf = hantro_get_dst_buf(ctx);
 		buf = &dst_buf->vb2_buf;
+		dma_addr = vb2_dma_contig_plane_dma_addr(buf, 0);
 	}
 
-	return buf;
+	return dma_addr;
 }
 
 int hantro_h264_dec_prepare_run(struct hantro_ctx *ctx)
@@ -627,7 +618,6 @@ int hantro_h264_dec_init(struct hantro_ctx *ctx)
 	struct hantro_h264_dec_hw_ctx *h264_dec = &ctx->h264_dec;
 	struct hantro_aux_buf *priv = &h264_dec->priv;
 	struct hantro_h264_dec_priv_tbl *tbl;
-	struct v4l2_pix_format_mplane pix_mp;
 
 	priv->cpu = dma_alloc_coherent(vpu->dev, sizeof(*tbl), &priv->dma,
 				       GFP_KERNEL);
@@ -638,9 +628,5 @@ int hantro_h264_dec_init(struct hantro_ctx *ctx)
 	tbl = priv->cpu;
 	memcpy(tbl->cabac_table, h264_cabac_table, sizeof(tbl->cabac_table));
 
-	v4l2_fill_pixfmt_mp(&pix_mp, ctx->dst_fmt.pixelformat,
-			    ctx->dst_fmt.width, ctx->dst_fmt.height);
-	h264_dec->pic_size = pix_mp.plane_fmt[0].sizeimage;
-
 	return 0;
 }
diff --git a/drivers/staging/media/hantro/hantro_hw.h b/drivers/staging/media/hantro/hantro_hw.h
index 2fab655bf098..fa91dd1848b7 100644
--- a/drivers/staging/media/hantro/hantro_hw.h
+++ b/drivers/staging/media/hantro/hantro_hw.h
@@ -80,15 +80,12 @@ struct hantro_h264_dec_reflists {
  * @dpb:	DPB
  * @reflists:	P/B0/B1 reflists
  * @ctrls:	V4L2 controls attached to a run
- * @pic_size:	Size in bytes of decoded picture, this is needed
- *		to pass the location of motion vectors.
  */
 struct hantro_h264_dec_hw_ctx {
 	struct hantro_aux_buf priv;
 	struct v4l2_h264_dpb_entry dpb[HANTRO_H264_DPB_SIZE];
 	struct hantro_h264_dec_reflists reflists;
 	struct hantro_h264_dec_ctrls ctrls;
-	size_t pic_size;
 };
 
 /**
@@ -158,8 +155,8 @@ void rk3399_vpu_jpeg_enc_run(struct hantro_ctx *ctx);
 int hantro_jpeg_enc_init(struct hantro_ctx *ctx);
 void hantro_jpeg_enc_exit(struct hantro_ctx *ctx);
 
-struct vb2_buffer *hantro_h264_get_ref_buf(struct hantro_ctx *ctx,
-					   unsigned int dpb_idx);
+dma_addr_t hantro_h264_get_ref_buf(struct hantro_ctx *ctx,
+				   unsigned int dpb_idx);
 int hantro_h264_dec_prepare_run(struct hantro_ctx *ctx);
 void hantro_g1_h264_dec_run(struct hantro_ctx *ctx);
 int hantro_h264_dec_init(struct hantro_ctx *ctx);
diff --git a/drivers/staging/media/hantro/hantro_v4l2.c b/drivers/staging/media/hantro/hantro_v4l2.c
index 3dae52abb96c..1dae76f20034 100644
--- a/drivers/staging/media/hantro/hantro_v4l2.c
+++ b/drivers/staging/media/hantro/hantro_v4l2.c
@@ -240,14 +240,30 @@ static int vidioc_try_fmt(struct file *file, void *priv, struct v4l2_format *f,
 		v4l2_fill_pixfmt_mp(pix_mp, fmt->fourcc, pix_mp->width,
 				    pix_mp->height);
 		/*
+		 * A decoded 8-bit 4:2:0 NV12 frame may need memory for up to
+		 * 448 bytes per macroblock with additional 32 bytes on
+		 * multi-core variants.
+		 *
 		 * The H264 decoder needs extra space on the output buffers
 		 * to store motion vectors. This is needed for reference
 		 * frames.
+		 *
+		 * Memory layout is as follow:
+		 *
+		 * +---------------------------+
+		 * | Y-plane   256 bytes x MBs |
+		 * +---------------------------+
+		 * | UV-plane  128 bytes x MBs |
+		 * +---------------------------+
+		 * | MV buffer  64 bytes x MBs |
+		 * +---------------------------+
+		 * | MC sync          32 bytes |
+		 * +---------------------------+
 		 */
 		if (ctx->vpu_src_fmt->fourcc == V4L2_PIX_FMT_H264_SLICE)
 			pix_mp->plane_fmt[0].sizeimage +=
-				128 * DIV_ROUND_UP(pix_mp->width, 16) *
-				      DIV_ROUND_UP(pix_mp->height, 16);
+				64 * MB_WIDTH(pix_mp->width) *
+				     MB_WIDTH(pix_mp->height) + 32;
 	} else if (!pix_mp->plane_fmt[0].sizeimage) {
 		/*
 		 * For coded formats the application can specify
@@ -367,20 +383,27 @@ vidioc_s_fmt_out_mplane(struct file *file, void *priv, struct v4l2_format *f)
 {
 	struct v4l2_pix_format_mplane *pix_mp = &f->fmt.pix_mp;
 	struct hantro_ctx *ctx = fh_to_ctx(priv);
+	struct vb2_queue *vq = v4l2_m2m_get_vq(ctx->fh.m2m_ctx, f->type);
 	const struct hantro_fmt *formats;
 	unsigned int num_fmts;
-	struct vb2_queue *vq;
 	int ret;
 
-	/* Change not allowed if queue is busy. */
-	vq = v4l2_m2m_get_vq(ctx->fh.m2m_ctx, f->type);
-	if (vb2_is_busy(vq))
-		return -EBUSY;
+	ret = vidioc_try_fmt_out_mplane(file, priv, f);
+	if (ret)
+		return ret;
 
 	if (!hantro_is_encoder_ctx(ctx)) {
 		struct vb2_queue *peer_vq;
 
 		/*
+		 * In order to support dynamic resolution change,
+		 * the decoder admits a resolution change, as long
+		 * as the pixelformat remains. Can't be done if streaming.
+		 */
+		if (vb2_is_streaming(vq) || (vb2_is_busy(vq) &&
+		    pix_mp->pixelformat != ctx->src_fmt.pixelformat))
+			return -EBUSY;
+		/*
 		 * Since format change on the OUTPUT queue will reset
 		 * the CAPTURE queue, we can't allow doing so
 		 * when the CAPTURE queue has buffers allocated.
@@ -389,12 +412,15 @@ vidioc_s_fmt_out_mplane(struct file *file, void *priv, struct v4l2_format *f)
 					  V4L2_BUF_TYPE_VIDEO_CAPTURE_MPLANE);
 		if (vb2_is_busy(peer_vq))
 			return -EBUSY;
+	} else {
+		/*
+		 * The encoder doesn't admit a format change if
+		 * there are OUTPUT buffers allocated.
+		 */
+		if (vb2_is_busy(vq))
+			return -EBUSY;
 	}
 
-	ret = vidioc_try_fmt_out_mplane(file, priv, f);
-	if (ret)
-		return ret;
-
 	formats = hantro_get_formats(ctx, &num_fmts);
 	ctx->vpu_src_fmt = hantro_find_format(formats, num_fmts,
 					      pix_mp->pixelformat);
diff --git a/drivers/staging/media/hantro/rk3288_vpu_hw.c b/drivers/staging/media/hantro/rk3288_vpu_hw.c
index 6bfcc47d1e58..f8db6fcaad73 100644
--- a/drivers/staging/media/hantro/rk3288_vpu_hw.c
+++ b/drivers/staging/media/hantro/rk3288_vpu_hw.c
@@ -48,10 +48,10 @@ static const struct hantro_fmt rk3288_vpu_enc_fmts[] = {
 		.frmsize = {
 			.min_width = 96,
 			.max_width = 8192,
-			.step_width = JPEG_MB_DIM,
+			.step_width = MB_DIM,
 			.min_height = 32,
 			.max_height = 8192,
-			.step_height = JPEG_MB_DIM,
+			.step_height = MB_DIM,
 		},
 	},
 };
@@ -67,11 +67,11 @@ static const struct hantro_fmt rk3288_vpu_dec_fmts[] = {
 		.max_depth = 2,
 		.frmsize = {
 			.min_width = 48,
-			.max_width = 3840,
-			.step_width = H264_MB_DIM,
+			.max_width = 4096,
+			.step_width = MB_DIM,
 			.min_height = 48,
-			.max_height = 2160,
-			.step_height = H264_MB_DIM,
+			.max_height = 2304,
+			.step_height = MB_DIM,
 		},
 	},
 	{
@@ -81,10 +81,10 @@ static const struct hantro_fmt rk3288_vpu_dec_fmts[] = {
 		.frmsize = {
 			.min_width = 48,
 			.max_width = 1920,
-			.step_width = MPEG2_MB_DIM,
+			.step_width = MB_DIM,
 			.min_height = 48,
 			.max_height = 1088,
-			.step_height = MPEG2_MB_DIM,
+			.step_height = MB_DIM,
 		},
 	},
 	{
@@ -94,10 +94,10 @@ static const struct hantro_fmt rk3288_vpu_dec_fmts[] = {
 		.frmsize = {
 			.min_width = 48,
 			.max_width = 3840,
-			.step_width = VP8_MB_DIM,
+			.step_width = MB_DIM,
 			.min_height = 48,
 			.max_height = 2160,
-			.step_height = VP8_MB_DIM,
+			.step_height = MB_DIM,
 		},
 	},
 };
diff --git a/drivers/staging/media/hantro/rk3399_vpu_hw.c b/drivers/staging/media/hantro/rk3399_vpu_hw.c
index 14d14bc6b12b..9ac1f2cb6a16 100644
--- a/drivers/staging/media/hantro/rk3399_vpu_hw.c
+++ b/drivers/staging/media/hantro/rk3399_vpu_hw.c
@@ -47,10 +47,10 @@ static const struct hantro_fmt rk3399_vpu_enc_fmts[] = {
 		.frmsize = {
 			.min_width = 96,
 			.max_width = 8192,
-			.step_width = JPEG_MB_DIM,
+			.step_width = MB_DIM,
 			.min_height = 32,
 			.max_height = 8192,
-			.step_height = JPEG_MB_DIM,
+			.step_height = MB_DIM,
 		},
 	},
 };
@@ -67,10 +67,10 @@ static const struct hantro_fmt rk3399_vpu_dec_fmts[] = {
 		.frmsize = {
 			.min_width = 48,
 			.max_width = 1920,
-			.step_width = MPEG2_MB_DIM,
+			.step_width = MB_DIM,
 			.min_height = 48,
 			.max_height = 1088,
-			.step_height = MPEG2_MB_DIM,
+			.step_height = MB_DIM,
 		},
 	},
 	{
@@ -80,10 +80,10 @@ static const struct hantro_fmt rk3399_vpu_dec_fmts[] = {
 		.frmsize = {
 			.min_width = 48,
 			.max_width = 3840,
-			.step_width = VP8_MB_DIM,
+			.step_width = MB_DIM,
 			.min_height = 48,
 			.max_height = 2160,
-			.step_height = VP8_MB_DIM,
+			.step_height = MB_DIM,
 		},
 	},
 };
diff --git a/drivers/staging/media/hantro/rk3399_vpu_hw_jpeg_enc.c b/drivers/staging/media/hantro/rk3399_vpu_hw_jpeg_enc.c
index 06162f569b5e..067892345b5d 100644
--- a/drivers/staging/media/hantro/rk3399_vpu_hw_jpeg_enc.c
+++ b/drivers/staging/media/hantro/rk3399_vpu_hw_jpeg_enc.c
@@ -149,8 +149,8 @@ void rk3399_vpu_jpeg_enc_run(struct hantro_ctx *ctx)
 	reg = VEPU_REG_AXI_CTRL_BURST_LEN(16);
 	vepu_write_relaxed(vpu, reg, VEPU_REG_AXI_CTRL);
 
-	reg = VEPU_REG_MB_WIDTH(JPEG_MB_WIDTH(ctx->src_fmt.width))
-		| VEPU_REG_MB_HEIGHT(JPEG_MB_HEIGHT(ctx->src_fmt.height))
+	reg = VEPU_REG_MB_WIDTH(MB_WIDTH(ctx->src_fmt.width))
+		| VEPU_REG_MB_HEIGHT(MB_HEIGHT(ctx->src_fmt.height))
 		| VEPU_REG_FRAME_TYPE_INTRA
 		| VEPU_REG_ENCODE_FORMAT_JPEG
 		| VEPU_REG_ENCODE_ENABLE;
diff --git a/drivers/staging/media/hantro/rk3399_vpu_hw_mpeg2_dec.c b/drivers/staging/media/hantro/rk3399_vpu_hw_mpeg2_dec.c
index e7ba5c0441cc..b40d2cdf832f 100644
--- a/drivers/staging/media/hantro/rk3399_vpu_hw_mpeg2_dec.c
+++ b/drivers/staging/media/hantro/rk3399_vpu_hw_mpeg2_dec.c
@@ -107,17 +107,14 @@ rk3399_vpu_mpeg2_dec_set_buffers(struct hantro_dev *vpu,
 {
 	dma_addr_t forward_addr = 0, backward_addr = 0;
 	dma_addr_t current_addr, addr;
-	struct vb2_queue *vq;
-
-	vq = v4l2_m2m_get_dst_vq(ctx->fh.m2m_ctx);
 
 	switch (picture->picture_coding_type) {
 	case V4L2_MPEG2_PICTURE_CODING_TYPE_B:
-		backward_addr = hantro_get_ref(vq,
+		backward_addr = hantro_get_ref(ctx,
 					       slice_params->backward_ref_ts);
 		/* fall-through */
 	case V4L2_MPEG2_PICTURE_CODING_TYPE_P:
-		forward_addr = hantro_get_ref(vq,
+		forward_addr = hantro_get_ref(ctx,
 					      slice_params->forward_ref_ts);
 	}
 
@@ -223,8 +220,8 @@ void rk3399_vpu_mpeg2_dec_run(struct hantro_ctx *ctx)
 	      VDPU_REG_DEC_CLK_GATE_E(1);
 	vdpu_write_relaxed(vpu, reg, VDPU_SWREG(57));
 
-	reg = VDPU_REG_PIC_MB_WIDTH(MPEG2_MB_WIDTH(ctx->dst_fmt.width)) |
-	      VDPU_REG_PIC_MB_HEIGHT_P(MPEG2_MB_HEIGHT(ctx->dst_fmt.height)) |
+	reg = VDPU_REG_PIC_MB_WIDTH(MB_WIDTH(ctx->dst_fmt.width)) |
+	      VDPU_REG_PIC_MB_HEIGHT_P(MB_HEIGHT(ctx->dst_fmt.height)) |
 	      VDPU_REG_ALT_SCAN_E(picture->alternate_scan) |
 	      VDPU_REG_TOPFIELDFIRST_E(picture->top_field_first);
 	vdpu_write_relaxed(vpu, reg, VDPU_SWREG(120));
diff --git a/drivers/staging/media/hantro/rk3399_vpu_hw_vp8_dec.c b/drivers/staging/media/hantro/rk3399_vpu_hw_vp8_dec.c
index f17e32620b08..76d7ed3fd69a 100644
--- a/drivers/staging/media/hantro/rk3399_vpu_hw_vp8_dec.c
+++ b/drivers/staging/media/hantro/rk3399_vpu_hw_vp8_dec.c
@@ -449,18 +449,16 @@ static void cfg_ref(struct hantro_ctx *ctx,
 {
 	struct hantro_dev *vpu = ctx->dev;
 	struct vb2_v4l2_buffer *vb2_dst;
-	struct vb2_queue *cap_q;
 	dma_addr_t ref;
 
-	cap_q = v4l2_m2m_get_vq(ctx->fh.m2m_ctx, V4L2_BUF_TYPE_VIDEO_CAPTURE);
 	vb2_dst = hantro_get_dst_buf(ctx);
 
-	ref = hantro_get_ref(cap_q, hdr->last_frame_ts);
+	ref = hantro_get_ref(ctx, hdr->last_frame_ts);
 	if (!ref)
 		ref = vb2_dma_contig_plane_dma_addr(&vb2_dst->vb2_buf, 0);
 	vdpu_write_relaxed(vpu, ref, VDPU_REG_VP8_ADDR_REF0);
 
-	ref = hantro_get_ref(cap_q, hdr->golden_frame_ts);
+	ref = hantro_get_ref(ctx, hdr->golden_frame_ts);
 	WARN_ON(!ref && hdr->golden_frame_ts);
 	if (!ref)
 		ref = vb2_dma_contig_plane_dma_addr(&vb2_dst->vb2_buf, 0);
@@ -468,7 +466,7 @@ static void cfg_ref(struct hantro_ctx *ctx,
 		ref |= VDPU_REG_VP8_GREF_SIGN_BIAS;
 	vdpu_write_relaxed(vpu, ref, VDPU_REG_VP8_ADDR_REF2_5(2));
 
-	ref = hantro_get_ref(cap_q, hdr->alt_frame_ts);
+	ref = hantro_get_ref(ctx, hdr->alt_frame_ts);
 	WARN_ON(!ref && hdr->alt_frame_ts);
 	if (!ref)
 		ref = vb2_dma_contig_plane_dma_addr(&vb2_dst->vb2_buf, 0);
@@ -563,8 +561,8 @@ void rk3399_vpu_vp8_dec_run(struct hantro_ctx *ctx)
 		hantro_reg_write(vpu, &vp8_dec_filter_disable, 1);
 
 	/* Frame dimensions */
-	mb_width = VP8_MB_WIDTH(width);
-	mb_height = VP8_MB_HEIGHT(height);
+	mb_width = MB_WIDTH(width);
+	mb_height = MB_HEIGHT(height);
 
 	hantro_reg_write(vpu, &vp8_dec_mb_width, mb_width);
 	hantro_reg_write(vpu, &vp8_dec_mb_height, mb_height);
diff --git a/drivers/staging/media/imx/imx-ic-prp.c b/drivers/staging/media/imx/imx-ic-prp.c
index 35e60a120dc1..2a4f77e83ed3 100644
--- a/drivers/staging/media/imx/imx-ic-prp.c
+++ b/drivers/staging/media/imx/imx-ic-prp.c
@@ -428,32 +428,19 @@ static int prp_s_frame_interval(struct v4l2_subdev *sd,
 	return 0;
 }
 
-/*
- * retrieve our pads parsed from the OF graph by the media device
- */
 static int prp_registered(struct v4l2_subdev *sd)
 {
 	struct prp_priv *priv = sd_to_priv(sd);
-	int i, ret;
 	u32 code;
 
-	for (i = 0; i < PRP_NUM_PADS; i++) {
-		priv->pad[i].flags = (i == PRP_SINK_PAD) ?
-			MEDIA_PAD_FL_SINK : MEDIA_PAD_FL_SOURCE;
-	}
-
 	/* init default frame interval */
 	priv->frame_interval.numerator = 1;
 	priv->frame_interval.denominator = 30;
 
 	/* set a default mbus format  */
 	imx_media_enum_ipu_format(&code, 0, CS_SEL_YUV);
-	ret = imx_media_init_mbus_fmt(&priv->format_mbus, 640, 480, code,
-				      V4L2_FIELD_NONE, NULL);
-	if (ret)
-		return ret;
-
-	return media_entity_pads_init(&sd->entity, PRP_NUM_PADS, priv->pad);
+	return imx_media_init_mbus_fmt(&priv->format_mbus, 640, 480, code,
+				       V4L2_FIELD_NONE, NULL);
 }
 
 static const struct v4l2_subdev_pad_ops prp_pad_ops = {
@@ -487,6 +474,7 @@ static const struct v4l2_subdev_internal_ops prp_internal_ops = {
 static int prp_init(struct imx_ic_priv *ic_priv)
 {
 	struct prp_priv *priv;
+	int i;
 
 	priv = devm_kzalloc(ic_priv->ipu_dev, sizeof(*priv), GFP_KERNEL);
 	if (!priv)
@@ -496,7 +484,12 @@ static int prp_init(struct imx_ic_priv *ic_priv)
 	ic_priv->task_priv = priv;
 	priv->ic_priv = ic_priv;
 
-	return 0;
+	for (i = 0; i < PRP_NUM_PADS; i++)
+		priv->pad[i].flags = (i == PRP_SINK_PAD) ?
+			MEDIA_PAD_FL_SINK : MEDIA_PAD_FL_SOURCE;
+
+	return media_entity_pads_init(&ic_priv->sd.entity, PRP_NUM_PADS,
+				      priv->pad);
 }
 
 static void prp_remove(struct imx_ic_priv *ic_priv)
diff --git a/drivers/staging/media/imx/imx-ic-prpencvf.c b/drivers/staging/media/imx/imx-ic-prpencvf.c
index 67ffa46a8e96..09c4e3f33807 100644
--- a/drivers/staging/media/imx/imx-ic-prpencvf.c
+++ b/drivers/staging/media/imx/imx-ic-prpencvf.c
@@ -1240,21 +1240,16 @@ static int prp_s_frame_interval(struct v4l2_subdev *sd,
 	return 0;
 }
 
-/*
- * retrieve our pads parsed from the OF graph by the media device
- */
 static int prp_registered(struct v4l2_subdev *sd)
 {
 	struct prp_priv *priv = sd_to_priv(sd);
+	struct imx_ic_priv *ic_priv = priv->ic_priv;
 	int i, ret;
 	u32 code;
 
+	/* set a default mbus format  */
+	imx_media_enum_ipu_format(&code, 0, CS_SEL_YUV);
 	for (i = 0; i < PRPENCVF_NUM_PADS; i++) {
-		priv->pad[i].flags = (i == PRPENCVF_SINK_PAD) ?
-			MEDIA_PAD_FL_SINK : MEDIA_PAD_FL_SOURCE;
-
-		/* set a default mbus format  */
-		imx_media_enum_ipu_format(&code, 0, CS_SEL_YUV);
 		ret = imx_media_init_mbus_fmt(&priv->format_mbus[i],
 					      640, 480, code, V4L2_FIELD_NONE,
 					      &priv->cc[i]);
@@ -1266,22 +1261,26 @@ static int prp_registered(struct v4l2_subdev *sd)
 	priv->frame_interval.numerator = 1;
 	priv->frame_interval.denominator = 30;
 
-	ret = media_entity_pads_init(&sd->entity, PRPENCVF_NUM_PADS,
-				     priv->pad);
-	if (ret)
-		return ret;
+	priv->vdev = imx_media_capture_device_init(ic_priv->ipu_dev,
+						   &ic_priv->sd,
+						   PRPENCVF_SRC_PAD);
+	if (IS_ERR(priv->vdev))
+		return PTR_ERR(priv->vdev);
 
 	ret = imx_media_capture_device_register(priv->vdev);
 	if (ret)
-		return ret;
+		goto remove_vdev;
 
 	ret = prp_init_controls(priv);
 	if (ret)
-		goto unreg;
+		goto unreg_vdev;
 
 	return 0;
-unreg:
+
+unreg_vdev:
 	imx_media_capture_device_unregister(priv->vdev);
+remove_vdev:
+	imx_media_capture_device_remove(priv->vdev);
 	return ret;
 }
 
@@ -1290,6 +1289,8 @@ static void prp_unregistered(struct v4l2_subdev *sd)
 	struct prp_priv *priv = sd_to_priv(sd);
 
 	imx_media_capture_device_unregister(priv->vdev);
+	imx_media_capture_device_remove(priv->vdev);
+
 	v4l2_ctrl_handler_free(&priv->ctrl_hdlr);
 }
 
@@ -1325,6 +1326,7 @@ static const struct v4l2_subdev_internal_ops prp_internal_ops = {
 static int prp_init(struct imx_ic_priv *ic_priv)
 {
 	struct prp_priv *priv;
+	int i, ret;
 
 	priv = devm_kzalloc(ic_priv->ipu_dev, sizeof(*priv), GFP_KERNEL);
 	if (!priv)
@@ -1336,15 +1338,19 @@ static int prp_init(struct imx_ic_priv *ic_priv)
 	spin_lock_init(&priv->irqlock);
 	timer_setup(&priv->eof_timeout_timer, prp_eof_timeout, 0);
 
-	priv->vdev = imx_media_capture_device_init(ic_priv->ipu_dev,
-						   &ic_priv->sd,
-						   PRPENCVF_SRC_PAD);
-	if (IS_ERR(priv->vdev))
-		return PTR_ERR(priv->vdev);
-
 	mutex_init(&priv->lock);
 
-	return 0;
+	for (i = 0; i < PRPENCVF_NUM_PADS; i++) {
+		priv->pad[i].flags = (i == PRPENCVF_SINK_PAD) ?
+			MEDIA_PAD_FL_SINK : MEDIA_PAD_FL_SOURCE;
+	}
+
+	ret = media_entity_pads_init(&ic_priv->sd.entity, PRPENCVF_NUM_PADS,
+				     priv->pad);
+	if (ret)
+		mutex_destroy(&priv->lock);
+
+	return ret;
 }
 
 static void prp_remove(struct imx_ic_priv *ic_priv)
@@ -1352,7 +1358,6 @@ static void prp_remove(struct imx_ic_priv *ic_priv)
 	struct prp_priv *priv = ic_priv->task_priv;
 
 	mutex_destroy(&priv->lock);
-	imx_media_capture_device_remove(priv->vdev);
 }
 
 struct imx_ic_ops imx_ic_prpencvf_ops = {
diff --git a/drivers/staging/media/imx/imx-media-capture.c b/drivers/staging/media/imx/imx-media-capture.c
index b33a07bc9105..7712e7be8625 100644
--- a/drivers/staging/media/imx/imx-media-capture.c
+++ b/drivers/staging/media/imx/imx-media-capture.c
@@ -26,6 +26,8 @@
 #include <media/imx.h>
 #include "imx-media.h"
 
+#define IMX_CAPTURE_NAME "imx-capture"
+
 struct capture_priv {
 	struct imx_media_video_dev vdev;
 
@@ -69,8 +71,8 @@ static int vidioc_querycap(struct file *file, void *fh,
 {
 	struct capture_priv *priv = video_drvdata(file);
 
-	strscpy(cap->driver, "imx-media-capture", sizeof(cap->driver));
-	strscpy(cap->card, "imx-media-capture", sizeof(cap->card));
+	strscpy(cap->driver, IMX_CAPTURE_NAME, sizeof(cap->driver));
+	strscpy(cap->card, IMX_CAPTURE_NAME, sizeof(cap->card));
 	snprintf(cap->bus_info, sizeof(cap->bus_info),
 		 "platform:%s", priv->src_sd->name);
 
@@ -765,13 +767,6 @@ int imx_media_capture_device_register(struct imx_media_video_dev *vdev)
 
 	INIT_LIST_HEAD(&priv->ready_q);
 
-	priv->vdev_pad.flags = MEDIA_PAD_FL_SINK;
-	ret = media_entity_pads_init(&vfd->entity, 1, &priv->vdev_pad);
-	if (ret) {
-		v4l2_err(sd, "failed to init dev pad\n");
-		goto unreg;
-	}
-
 	/* create the link from the src_sd devnode pad to device node */
 	ret = media_create_pad_link(&sd->entity, priv->src_sd_pad,
 				    &vfd->entity, 0, 0);
@@ -834,6 +829,7 @@ imx_media_capture_device_init(struct device *dev, struct v4l2_subdev *src_sd,
 {
 	struct capture_priv *priv;
 	struct video_device *vfd;
+	int ret;
 
 	priv = devm_kzalloc(dev, sizeof(*priv), GFP_KERNEL);
 	if (!priv)
@@ -858,6 +854,13 @@ imx_media_capture_device_init(struct device *dev, struct v4l2_subdev *src_sd,
 	vfd->queue = &priv->q;
 	priv->vdev.vfd = vfd;
 
+	priv->vdev_pad.flags = MEDIA_PAD_FL_SINK;
+	ret = media_entity_pads_init(&vfd->entity, 1, &priv->vdev_pad);
+	if (ret) {
+		video_device_release(vfd);
+		return ERR_PTR(ret);
+	}
+
 	INIT_LIST_HEAD(&priv->vdev.list);
 
 	video_set_drvdata(vfd, priv);
diff --git a/drivers/staging/media/imx/imx-media-csi.c b/drivers/staging/media/imx/imx-media-csi.c
index 367e39f5b382..b60ed4f22f6d 100644
--- a/drivers/staging/media/imx/imx-media-csi.c
+++ b/drivers/staging/media/imx/imx-media-csi.c
@@ -627,8 +627,8 @@ static int csi_idmac_start(struct csi_priv *priv)
 	}
 
 	priv->nfb4eof_irq = ipu_idmac_channel_irq(priv->ipu,
-						 priv->idmac_ch,
-						 IPU_IRQ_NFB4EOF);
+						  priv->idmac_ch,
+						  IPU_IRQ_NFB4EOF);
 	ret = devm_request_irq(priv->dev, priv->nfb4eof_irq,
 			       csi_idmac_nfb4eof_interrupt, 0,
 			       "imx-smfc-nfb4eof", priv);
@@ -1472,7 +1472,7 @@ static void csi_try_fmt(struct csi_priv *priv,
 			imx_media_enum_mbus_format(&code, 0,
 						   CS_SEL_ANY, false);
 			*cc = imx_media_find_mbus_format(code,
-							CS_SEL_ANY, false);
+							 CS_SEL_ANY, false);
 			sdformat->format.code = (*cc)->codes[0];
 		}
 
@@ -1740,9 +1740,6 @@ static int csi_unsubscribe_event(struct v4l2_subdev *sd, struct v4l2_fh *fh,
 	return v4l2_event_unsubscribe(fh, sub);
 }
 
-/*
- * retrieve our pads parsed from the OF graph by the media device
- */
 static int csi_registered(struct v4l2_subdev *sd)
 {
 	struct csi_priv *priv = v4l2_get_subdevdata(sd);
@@ -1759,9 +1756,6 @@ static int csi_registered(struct v4l2_subdev *sd)
 	priv->csi = csi;
 
 	for (i = 0; i < CSI_NUM_PADS; i++) {
-		priv->pad[i].flags = (i == CSI_SINK_PAD) ?
-			MEDIA_PAD_FL_SINK : MEDIA_PAD_FL_SOURCE;
-
 		code = 0;
 		if (i != CSI_SINK_PAD)
 			imx_media_enum_ipu_format(&code, 0, CS_SEL_YUV);
@@ -1793,16 +1787,22 @@ static int csi_registered(struct v4l2_subdev *sd)
 		goto put_csi;
 	}
 
-	ret = media_entity_pads_init(&sd->entity, CSI_NUM_PADS, priv->pad);
-	if (ret)
+	priv->vdev = imx_media_capture_device_init(priv->sd.dev,
+						   &priv->sd,
+						   CSI_SRC_PAD_IDMAC);
+	if (IS_ERR(priv->vdev)) {
+		ret = PTR_ERR(priv->vdev);
 		goto free_fim;
+	}
 
 	ret = imx_media_capture_device_register(priv->vdev);
 	if (ret)
-		goto free_fim;
+		goto remove_vdev;
 
 	return 0;
 
+remove_vdev:
+	imx_media_capture_device_remove(priv->vdev);
 free_fim:
 	if (priv->fim)
 		imx_media_fim_free(priv->fim);
@@ -1816,6 +1816,7 @@ static void csi_unregistered(struct v4l2_subdev *sd)
 	struct csi_priv *priv = v4l2_get_subdevdata(sd);
 
 	imx_media_capture_device_unregister(priv->vdev);
+	imx_media_capture_device_remove(priv->vdev);
 
 	if (priv->fim)
 		imx_media_fim_free(priv->fim);
@@ -1923,7 +1924,7 @@ static int imx_csi_probe(struct platform_device *pdev)
 	struct ipu_client_platformdata *pdata;
 	struct pinctrl *pinctrl;
 	struct csi_priv *priv;
-	int ret;
+	int i, ret;
 
 	priv = devm_kzalloc(&pdev->dev, sizeof(*priv), GFP_KERNEL);
 	if (!priv)
@@ -1963,10 +1964,14 @@ static int imx_csi_probe(struct platform_device *pdev)
 	imx_media_grp_id_to_sd_name(priv->sd.name, sizeof(priv->sd.name),
 				    priv->sd.grp_id, ipu_get_num(priv->ipu));
 
-	priv->vdev = imx_media_capture_device_init(priv->sd.dev, &priv->sd,
-						   CSI_SRC_PAD_IDMAC);
-	if (IS_ERR(priv->vdev))
-		return PTR_ERR(priv->vdev);
+	for (i = 0; i < CSI_NUM_PADS; i++)
+		priv->pad[i].flags = (i == CSI_SINK_PAD) ?
+			MEDIA_PAD_FL_SINK : MEDIA_PAD_FL_SOURCE;
+
+	ret = media_entity_pads_init(&priv->sd.entity, CSI_NUM_PADS,
+				     priv->pad);
+	if (ret)
+		return ret;
 
 	mutex_init(&priv->lock);
 
@@ -1997,7 +2002,6 @@ static int imx_csi_probe(struct platform_device *pdev)
 free:
 	v4l2_ctrl_handler_free(&priv->ctrl_hdlr);
 	mutex_destroy(&priv->lock);
-	imx_media_capture_device_remove(priv->vdev);
 	return ret;
 }
 
@@ -2008,7 +2012,6 @@ static int imx_csi_remove(struct platform_device *pdev)
 
 	v4l2_ctrl_handler_free(&priv->ctrl_hdlr);
 	mutex_destroy(&priv->lock);
-	imx_media_capture_device_remove(priv->vdev);
 	v4l2_async_unregister_subdev(sd);
 	media_entity_cleanup(&sd->entity);
 
diff --git a/drivers/staging/media/imx/imx-media-utils.c b/drivers/staging/media/imx/imx-media-utils.c
index 4cc6a7462ae2..0788a1874557 100644
--- a/drivers/staging/media/imx/imx-media-utils.c
+++ b/drivers/staging/media/imx/imx-media-utils.c
@@ -184,7 +184,15 @@ static const struct imx_media_pixfmt rgb_formats[] = {
 		.cs     = IPUV3_COLORSPACE_RGB,
 		.bpp    = 24,
 	}, {
-		.fourcc	= V4L2_PIX_FMT_BGR32,
+		.fourcc	= V4L2_PIX_FMT_XBGR32,
+		.cs     = IPUV3_COLORSPACE_RGB,
+		.bpp    = 32,
+	}, {
+		.fourcc	= V4L2_PIX_FMT_BGRX32,
+		.cs     = IPUV3_COLORSPACE_RGB,
+		.bpp    = 32,
+	}, {
+		.fourcc	= V4L2_PIX_FMT_RGBX32,
 		.cs     = IPUV3_COLORSPACE_RGB,
 		.bpp    = 32,
 	},
diff --git a/drivers/staging/media/imx/imx-media-vdic.c b/drivers/staging/media/imx/imx-media-vdic.c
index cfad65a16917..0d83c2c41606 100644
--- a/drivers/staging/media/imx/imx-media-vdic.c
+++ b/drivers/staging/media/imx/imx-media-vdic.c
@@ -841,9 +841,6 @@ out:
 	return ret;
 }
 
-/*
- * retrieve our pads parsed from the OF graph by the media device
- */
 static int vdic_registered(struct v4l2_subdev *sd)
 {
 	struct vdic_priv *priv = v4l2_get_subdevdata(sd);
@@ -851,9 +848,6 @@ static int vdic_registered(struct v4l2_subdev *sd)
 	u32 code;
 
 	for (i = 0; i < VDIC_NUM_PADS; i++) {
-		priv->pad[i].flags = (i == VDIC_SRC_PAD_DIRECT) ?
-			MEDIA_PAD_FL_SOURCE : MEDIA_PAD_FL_SINK;
-
 		code = 0;
 		if (i != VDIC_SINK_PAD_IDMAC)
 			imx_media_enum_ipu_format(&code, 0, CS_SEL_YUV);
@@ -874,15 +868,7 @@ static int vdic_registered(struct v4l2_subdev *sd)
 
 	priv->active_input_pad = VDIC_SINK_PAD_DIRECT;
 
-	ret = vdic_init_controls(priv);
-	if (ret)
-		return ret;
-
-	ret = media_entity_pads_init(&sd->entity, VDIC_NUM_PADS, priv->pad);
-	if (ret)
-		v4l2_ctrl_handler_free(&priv->ctrl_hdlr);
-
-	return ret;
+	return vdic_init_controls(priv);
 }
 
 static void vdic_unregistered(struct v4l2_subdev *sd)
@@ -927,7 +913,7 @@ struct v4l2_subdev *imx_media_vdic_register(struct v4l2_device *v4l2_dev,
 					    u32 grp_id)
 {
 	struct vdic_priv *priv;
-	int ret;
+	int i, ret;
 
 	priv = devm_kzalloc(ipu_dev, sizeof(*priv), GFP_KERNEL);
 	if (!priv)
@@ -949,6 +935,15 @@ struct v4l2_subdev *imx_media_vdic_register(struct v4l2_device *v4l2_dev,
 
 	mutex_init(&priv->lock);
 
+	for (i = 0; i < VDIC_NUM_PADS; i++)
+		priv->pad[i].flags = (i == VDIC_SRC_PAD_DIRECT) ?
+			MEDIA_PAD_FL_SOURCE : MEDIA_PAD_FL_SINK;
+
+	ret = media_entity_pads_init(&priv->sd.entity, VDIC_NUM_PADS,
+				     priv->pad);
+	if (ret)
+		goto free;
+
 	ret = v4l2_device_register_subdev(v4l2_dev, &priv->sd);
 	if (ret)
 		goto free;
diff --git a/drivers/staging/media/imx/imx6-mipi-csi2.c b/drivers/staging/media/imx/imx6-mipi-csi2.c
index bfa4b254c4e4..cd3dd6e33ef0 100644
--- a/drivers/staging/media/imx/imx6-mipi-csi2.c
+++ b/drivers/staging/media/imx/imx6-mipi-csi2.c
@@ -497,26 +497,13 @@ out:
 	return ret;
 }
 
-/*
- * retrieve our pads parsed from the OF graph by the media device
- */
 static int csi2_registered(struct v4l2_subdev *sd)
 {
 	struct csi2_dev *csi2 = sd_to_dev(sd);
-	int i, ret;
-
-	for (i = 0; i < CSI2_NUM_PADS; i++) {
-		csi2->pad[i].flags = (i == CSI2_SINK_PAD) ?
-		MEDIA_PAD_FL_SINK : MEDIA_PAD_FL_SOURCE;
-	}
 
 	/* set a default mbus format  */
-	ret = imx_media_init_mbus_fmt(&csi2->format_mbus,
+	return imx_media_init_mbus_fmt(&csi2->format_mbus,
 				      640, 480, 0, V4L2_FIELD_NONE, NULL);
-	if (ret)
-		return ret;
-
-	return media_entity_pads_init(&sd->entity, CSI2_NUM_PADS, csi2->pad);
 }
 
 static const struct media_entity_operations csi2_entity_ops = {
@@ -573,7 +560,7 @@ static int csi2_probe(struct platform_device *pdev)
 	unsigned int sink_port = 0;
 	struct csi2_dev *csi2;
 	struct resource *res;
-	int ret;
+	int i, ret;
 
 	csi2 = devm_kzalloc(&pdev->dev, sizeof(*csi2), GFP_KERNEL);
 	if (!csi2)
@@ -592,6 +579,16 @@ static int csi2_probe(struct platform_device *pdev)
 	csi2->sd.entity.function = MEDIA_ENT_F_VID_IF_BRIDGE;
 	csi2->sd.grp_id = IMX_MEDIA_GRP_ID_CSI2;
 
+	for (i = 0; i < CSI2_NUM_PADS; i++) {
+		csi2->pad[i].flags = (i == CSI2_SINK_PAD) ?
+		MEDIA_PAD_FL_SINK : MEDIA_PAD_FL_SOURCE;
+	}
+
+	ret = media_entity_pads_init(&csi2->sd.entity, CSI2_NUM_PADS,
+				     csi2->pad);
+	if (ret)
+		return ret;
+
 	csi2->pllref_clk = devm_clk_get(&pdev->dev, "ref");
 	if (IS_ERR(csi2->pllref_clk)) {
 		v4l2_err(&csi2->sd, "failed to get pll reference clock\n");
diff --git a/drivers/staging/media/imx/imx7-media-csi.c b/drivers/staging/media/imx/imx7-media-csi.c
index bfd6b5fbf484..db30e2c70f2f 100644
--- a/drivers/staging/media/imx/imx7-media-csi.c
+++ b/drivers/staging/media/imx/imx7-media-csi.c
@@ -1100,9 +1100,6 @@ static int imx7_csi_registered(struct v4l2_subdev *sd)
 	int i;
 
 	for (i = 0; i < IMX7_CSI_PADS_NUM; i++) {
-		csi->pad[i].flags = (i == IMX7_CSI_PAD_SINK) ?
-			MEDIA_PAD_FL_SINK : MEDIA_PAD_FL_SOURCE;
-
 		/* set a default mbus format  */
 		ret = imx_media_init_mbus_fmt(&csi->format_mbus[i],
 					      800, 600, 0, V4L2_FIELD_NONE,
@@ -1115,11 +1112,16 @@ static int imx7_csi_registered(struct v4l2_subdev *sd)
 		csi->frame_interval[i].denominator = 30;
 	}
 
-	ret = media_entity_pads_init(&sd->entity, IMX7_CSI_PADS_NUM, csi->pad);
-	if (ret < 0)
-		return ret;
+	csi->vdev = imx_media_capture_device_init(csi->sd.dev, &csi->sd,
+						  IMX7_CSI_PAD_SRC);
+	if (IS_ERR(csi->vdev))
+		return PTR_ERR(csi->vdev);
+
+	ret = imx_media_capture_device_register(csi->vdev);
+	if (ret)
+		imx_media_capture_device_remove(csi->vdev);
 
-	return imx_media_capture_device_register(csi->vdev);
+	return ret;
 }
 
 static void imx7_csi_unregistered(struct v4l2_subdev *sd)
@@ -1127,6 +1129,7 @@ static void imx7_csi_unregistered(struct v4l2_subdev *sd)
 	struct imx7_csi *csi = v4l2_get_subdevdata(sd);
 
 	imx_media_capture_device_unregister(csi->vdev);
+	imx_media_capture_device_remove(csi->vdev);
 }
 
 static int imx7_csi_init_cfg(struct v4l2_subdev *sd,
@@ -1189,7 +1192,7 @@ static int imx7_csi_probe(struct platform_device *pdev)
 	struct device_node *node = dev->of_node;
 	struct imx_media_dev *imxmd;
 	struct imx7_csi *csi;
-	int ret;
+	int i, ret;
 
 	csi = devm_kzalloc(&pdev->dev, sizeof(*csi), GFP_KERNEL);
 	if (!csi)
@@ -1251,14 +1254,18 @@ static int imx7_csi_probe(struct platform_device *pdev)
 	csi->sd.grp_id = IMX_MEDIA_GRP_ID_CSI;
 	snprintf(csi->sd.name, sizeof(csi->sd.name), "csi");
 
-	csi->vdev = imx_media_capture_device_init(csi->sd.dev, &csi->sd,
-						  IMX7_CSI_PAD_SRC);
-	if (IS_ERR(csi->vdev))
-		return PTR_ERR(csi->vdev);
-
 	v4l2_ctrl_handler_init(&csi->ctrl_hdlr, 0);
 	csi->sd.ctrl_handler = &csi->ctrl_hdlr;
 
+	for (i = 0; i < IMX7_CSI_PADS_NUM; i++)
+		csi->pad[i].flags = (i == IMX7_CSI_PAD_SINK) ?
+			MEDIA_PAD_FL_SINK : MEDIA_PAD_FL_SOURCE;
+
+	ret = media_entity_pads_init(&csi->sd.entity, IMX7_CSI_PADS_NUM,
+				     csi->pad);
+	if (ret < 0)
+		goto free;
+
 	ret = v4l2_async_register_fwnode_subdev(&csi->sd,
 						sizeof(struct v4l2_async_subdev),
 						NULL, 0,
@@ -1269,8 +1276,6 @@ static int imx7_csi_probe(struct platform_device *pdev)
 	return 0;
 
 free:
-	imx_media_capture_device_unregister(csi->vdev);
-	imx_media_capture_device_remove(csi->vdev);
 	v4l2_ctrl_handler_free(&csi->ctrl_hdlr);
 
 cleanup:
@@ -1298,9 +1303,6 @@ static int imx7_csi_remove(struct platform_device *pdev)
 	v4l2_device_unregister(&imxmd->v4l2_dev);
 	media_device_cleanup(&imxmd->md);
 
-	imx_media_capture_device_unregister(csi->vdev);
-	imx_media_capture_device_remove(csi->vdev);
-
 	v4l2_async_unregister_subdev(sd);
 	v4l2_ctrl_handler_free(&csi->ctrl_hdlr);
 
diff --git a/drivers/staging/media/imx/imx7-mipi-csis.c b/drivers/staging/media/imx/imx7-mipi-csis.c
index 73d8354e618c..99166afca071 100644
--- a/drivers/staging/media/imx/imx7-mipi-csis.c
+++ b/drivers/staging/media/imx/imx7-mipi-csis.c
@@ -293,7 +293,7 @@ static int mipi_csis_dump_regs(struct csi_state *state)
 	struct device *dev = &state->pdev->dev;
 	unsigned int i;
 	u32 cfg;
-	struct {
+	static const struct {
 		u32 offset;
 		const char * const name;
 	} registers[] = {
@@ -350,6 +350,8 @@ static void mipi_csis_sw_reset(struct csi_state *state)
 static int mipi_csis_phy_init(struct csi_state *state)
 {
 	state->mipi_phy_regulator = devm_regulator_get(state->dev, "phy");
+	if (IS_ERR(state->mipi_phy_regulator))
+		return PTR_ERR(state->mipi_phy_regulator);
 
 	return regulator_set_voltage(state->mipi_phy_regulator, 1000000,
 				     1000000);
@@ -780,17 +782,6 @@ static irqreturn_t mipi_csis_irq_handler(int irq, void *dev_id)
 	return IRQ_HANDLED;
 }
 
-static int mipi_csis_registered(struct v4l2_subdev *mipi_sd)
-{
-	struct csi_state *state = mipi_sd_to_csis_state(mipi_sd);
-
-	state->pads[CSIS_PAD_SINK].flags = MEDIA_PAD_FL_SINK;
-	state->pads[CSIS_PAD_SOURCE].flags = MEDIA_PAD_FL_SOURCE;
-
-	return media_entity_pads_init(&state->mipi_sd.entity, CSIS_PADS_NUM,
-				      state->pads);
-}
-
 static const struct v4l2_subdev_core_ops mipi_csis_core_ops = {
 	.log_status	= mipi_csis_log_status,
 };
@@ -816,10 +807,6 @@ static const struct v4l2_subdev_ops mipi_csis_subdev_ops = {
 	.pad	= &mipi_csis_pad_ops,
 };
 
-static const struct v4l2_subdev_internal_ops mipi_csis_internal_ops = {
-	.registered = mipi_csis_registered,
-};
-
 static int mipi_csis_parse_dt(struct platform_device *pdev,
 			      struct csi_state *state)
 {
@@ -880,7 +867,6 @@ static int mipi_csis_subdev_init(struct v4l2_subdev *mipi_sd,
 
 	mipi_sd->entity.function = MEDIA_ENT_F_VID_IF_BRIDGE;
 	mipi_sd->entity.ops = &mipi_csis_entity_ops;
-	mipi_sd->internal_ops = &mipi_csis_internal_ops;
 
 	mipi_sd->dev = &pdev->dev;
 
@@ -892,6 +878,13 @@ static int mipi_csis_subdev_init(struct v4l2_subdev *mipi_sd,
 
 	v4l2_set_subdevdata(mipi_sd, &pdev->dev);
 
+	state->pads[CSIS_PAD_SINK].flags = MEDIA_PAD_FL_SINK;
+	state->pads[CSIS_PAD_SOURCE].flags = MEDIA_PAD_FL_SOURCE;
+	ret = media_entity_pads_init(&mipi_sd->entity, CSIS_PADS_NUM,
+				     state->pads);
+	if (ret)
+		return ret;
+
 	ret = v4l2_async_register_fwnode_subdev(mipi_sd,
 						sizeof(struct v4l2_async_subdev),
 						&sink_port, 1,
@@ -947,7 +940,6 @@ static void mipi_csis_debugfs_exit(struct csi_state *state)
 static int mipi_csis_probe(struct platform_device *pdev)
 {
 	struct device *dev = &pdev->dev;
-	struct resource *mem_res;
 	struct csi_state *state;
 	int ret;
 
@@ -966,11 +958,13 @@ static int mipi_csis_probe(struct platform_device *pdev)
 		return ret;
 	}
 
-	mipi_csis_phy_init(state);
+	ret = mipi_csis_phy_init(state);
+	if (ret < 0)
+		return ret;
+
 	mipi_csis_phy_reset(state);
 
-	mem_res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	state->regs = devm_ioremap_resource(dev, mem_res);
+	state->regs = devm_platform_ioremap_resource(pdev, 0);
 	if (IS_ERR(state->regs))
 		return PTR_ERR(state->regs);
 
diff --git a/drivers/staging/media/ipu3/Makefile b/drivers/staging/media/ipu3/Makefile
index cc288ae6d5f2..9def80ef28f3 100644
--- a/drivers/staging/media/ipu3/Makefile
+++ b/drivers/staging/media/ipu3/Makefile
@@ -10,9 +10,3 @@ ipu3-imgu-objs += \
 		ipu3-css.o ipu3-v4l2.o ipu3.o
 
 obj-$(CONFIG_VIDEO_IPU3_IMGU) += ipu3-imgu.o
-
-# HACK! While this driver is in bad shape, don't enable several warnings
-#       that would be otherwise enabled with W=1
-ccflags-y += $(call cc-disable-warning, packed-not-aligned)
-ccflags-y += $(call cc-disable-warning, type-limits)
-ccflags-y += $(call cc-disable-warning, unused-const-variable)
diff --git a/drivers/staging/media/ipu3/TODO b/drivers/staging/media/ipu3/TODO
index 5e55baeaea1a..b44bb4a72ca7 100644
--- a/drivers/staging/media/ipu3/TODO
+++ b/drivers/staging/media/ipu3/TODO
@@ -9,12 +9,9 @@ staging directory.
   relevant. (Sakari)
 
 - IPU3 driver documentation (Laurent)
-  Add diagram in driver rst to describe output capability.
   Comments on configuring v4l2 subdevs for CIO2 and ImgU.
 
 - uAPI documentation:
-  Further clarification on some ambiguities such as data type conversion of
-  IEFD CU inputs. (Sakari)
   Move acronyms to doc-rst file. (Mauro)
 
 - Switch to yavta from v4l2n in driver docs.
@@ -27,5 +24,3 @@ staging directory.
 - Document different operation modes, and which buffer queues are relevant
   in each mode. To process an image, which queues require a buffer an in
   which ones is it optional?
-
-- Make sure it builds fine with no warnings with W=1
diff --git a/drivers/staging/media/ipu3/include/intel-ipu3.h b/drivers/staging/media/ipu3/include/intel-ipu3.h
index c7cd27efac8a..08eaa0bad0de 100644
--- a/drivers/staging/media/ipu3/include/intel-ipu3.h
+++ b/drivers/staging/media/ipu3/include/intel-ipu3.h
@@ -1217,6 +1217,11 @@ struct ipu3_uapi_shd_config {
  *
  * All CU inputs are unsigned, they will be converted to signed when written
  * to register, i.e. a01 will be written to 9 bit register in s4.4 format.
+ * The data precision s4.4 means 4 bits for integer parts and 4 bits for the
+ * fractional part, the first bit indicates positive or negative value.
+ * For userspace software (commonly the imaging library), the computation for
+ * the CU slope values should be based on the slope resolution 1/16 (binary
+ * 0.0001 - the minimal interval value), the slope value range is [-256, +255].
  * This applies to &ipu3_uapi_iefd_cux6_ed, &ipu3_uapi_iefd_cux2_1,
  * &ipu3_uapi_iefd_cux2_1, &ipu3_uapi_iefd_cux4 and &ipu3_uapi_iefd_cux6_rad.
  */
diff --git a/drivers/staging/media/omap4iss/iss.c b/drivers/staging/media/omap4iss/iss.c
index 1a966cb2f3a6..6fb60b58447a 100644
--- a/drivers/staging/media/omap4iss/iss.c
+++ b/drivers/staging/media/omap4iss/iss.c
@@ -908,11 +908,7 @@ static int iss_map_mem_resource(struct platform_device *pdev,
 				struct iss_device *iss,
 				enum iss_mem_resources res)
 {
-	struct resource *mem;
-
-	mem = platform_get_resource(pdev, IORESOURCE_MEM, res);
-
-	iss->regs[res] = devm_ioremap_resource(iss->dev, mem);
+	iss->regs[res] = devm_platform_ioremap_resource(pdev, res);
 
 	return PTR_ERR_OR_ZERO(iss->regs[res]);
 }
diff --git a/drivers/staging/media/omap4iss/iss_video.c b/drivers/staging/media/omap4iss/iss_video.c
index 54144dc9f509..673aa3a5f2bd 100644
--- a/drivers/staging/media/omap4iss/iss_video.c
+++ b/drivers/staging/media/omap4iss/iss_video.c
@@ -671,7 +671,7 @@ iss_video_get_selection(struct file *file, void *fh, struct v4l2_selection *sel)
 		return -EINVAL;
 	}
 	subdev = iss_video_remote_subdev(video, &pad);
-	if (subdev == NULL)
+	if (!subdev)
 		return -EINVAL;
 
 	/*
@@ -726,7 +726,7 @@ iss_video_set_selection(struct file *file, void *fh, struct v4l2_selection *sel)
 		return -EINVAL;
 	}
 	subdev = iss_video_remote_subdev(video, &pad);
-	if (subdev == NULL)
+	if (!subdev)
 		return -EINVAL;
 
 	sdsel.pad = pad;
diff --git a/drivers/staging/media/sunxi/cedrus/Makefile b/drivers/staging/media/sunxi/cedrus/Makefile
index c85ac6db0302..1bce49d3e7e2 100644
--- a/drivers/staging/media/sunxi/cedrus/Makefile
+++ b/drivers/staging/media/sunxi/cedrus/Makefile
@@ -2,4 +2,4 @@
 obj-$(CONFIG_VIDEO_SUNXI_CEDRUS) += sunxi-cedrus.o
 
 sunxi-cedrus-y = cedrus.o cedrus_video.o cedrus_hw.o cedrus_dec.o \
-		 cedrus_mpeg2.o cedrus_h264.o
+		 cedrus_mpeg2.o cedrus_h264.o cedrus_h265.o
diff --git a/drivers/staging/media/sunxi/cedrus/cedrus.c b/drivers/staging/media/sunxi/cedrus/cedrus.c
index 2d3ea8b74dfd..c6ddd46eff82 100644
--- a/drivers/staging/media/sunxi/cedrus/cedrus.c
+++ b/drivers/staging/media/sunxi/cedrus/cedrus.c
@@ -95,6 +95,45 @@ static const struct cedrus_control cedrus_controls[] = {
 		.codec		= CEDRUS_CODEC_H264,
 		.required	= false,
 	},
+	{
+		.cfg = {
+			.id	= V4L2_CID_MPEG_VIDEO_HEVC_SPS,
+		},
+		.codec		= CEDRUS_CODEC_H265,
+		.required	= true,
+	},
+	{
+		.cfg = {
+			.id	= V4L2_CID_MPEG_VIDEO_HEVC_PPS,
+		},
+		.codec		= CEDRUS_CODEC_H265,
+		.required	= true,
+	},
+	{
+		.cfg = {
+			.id	= V4L2_CID_MPEG_VIDEO_HEVC_SLICE_PARAMS,
+		},
+		.codec		= CEDRUS_CODEC_H265,
+		.required	= true,
+	},
+	{
+		.cfg = {
+			.id	= V4L2_CID_MPEG_VIDEO_HEVC_DECODE_MODE,
+			.max	= V4L2_MPEG_VIDEO_HEVC_DECODE_MODE_SLICE_BASED,
+			.def	= V4L2_MPEG_VIDEO_HEVC_DECODE_MODE_SLICE_BASED,
+		},
+		.codec		= CEDRUS_CODEC_H265,
+		.required	= false,
+	},
+	{
+		.cfg = {
+			.id	= V4L2_CID_MPEG_VIDEO_HEVC_START_CODE,
+			.max	= V4L2_MPEG_VIDEO_HEVC_START_CODE_NONE,
+			.def	= V4L2_MPEG_VIDEO_HEVC_START_CODE_NONE,
+		},
+		.codec		= CEDRUS_CODEC_H265,
+		.required	= false,
+	},
 };
 
 #define CEDRUS_CONTROLS_COUNT	ARRAY_SIZE(cedrus_controls)
@@ -241,6 +280,16 @@ static int cedrus_open(struct file *file)
 		ret = PTR_ERR(ctx->fh.m2m_ctx);
 		goto err_ctrls;
 	}
+	ctx->dst_fmt.pixelformat = V4L2_PIX_FMT_SUNXI_TILED_NV12;
+	cedrus_prepare_format(&ctx->dst_fmt);
+	ctx->src_fmt.pixelformat = V4L2_PIX_FMT_MPEG2_SLICE;
+	/*
+	 * TILED_NV12 has more strict requirements, so copy the width and
+	 * height to src_fmt to ensure that is matches the dst_fmt resolution.
+	 */
+	ctx->src_fmt.width = ctx->dst_fmt.width;
+	ctx->src_fmt.height = ctx->dst_fmt.height;
+	cedrus_prepare_format(&ctx->src_fmt);
 
 	v4l2_fh_add(&ctx->fh);
 
@@ -330,6 +379,7 @@ static int cedrus_probe(struct platform_device *pdev)
 
 	dev->dec_ops[CEDRUS_CODEC_MPEG2] = &cedrus_dec_ops_mpeg2;
 	dev->dec_ops[CEDRUS_CODEC_H264] = &cedrus_dec_ops_h264;
+	dev->dec_ops[CEDRUS_CODEC_H265] = &cedrus_dec_ops_h265;
 
 	mutex_init(&dev->dev_mutex);
 
@@ -357,6 +407,8 @@ static int cedrus_probe(struct platform_device *pdev)
 
 	dev->mdev.dev = &pdev->dev;
 	strscpy(dev->mdev.model, CEDRUS_NAME, sizeof(dev->mdev.model));
+	strscpy(dev->mdev.bus_info, "platform:" CEDRUS_NAME,
+		sizeof(dev->mdev.bus_info));
 
 	media_device_init(&dev->mdev);
 	dev->mdev.ops = &cedrus_m2m_media_ops;
@@ -438,22 +490,26 @@ static const struct cedrus_variant sun8i_a33_cedrus_variant = {
 };
 
 static const struct cedrus_variant sun8i_h3_cedrus_variant = {
-	.capabilities	= CEDRUS_CAPABILITY_UNTILED,
+	.capabilities	= CEDRUS_CAPABILITY_UNTILED |
+			  CEDRUS_CAPABILITY_H265_DEC,
 	.mod_rate	= 402000000,
 };
 
 static const struct cedrus_variant sun50i_a64_cedrus_variant = {
-	.capabilities	= CEDRUS_CAPABILITY_UNTILED,
+	.capabilities	= CEDRUS_CAPABILITY_UNTILED |
+			  CEDRUS_CAPABILITY_H265_DEC,
 	.mod_rate	= 402000000,
 };
 
 static const struct cedrus_variant sun50i_h5_cedrus_variant = {
-	.capabilities	= CEDRUS_CAPABILITY_UNTILED,
+	.capabilities	= CEDRUS_CAPABILITY_UNTILED |
+			  CEDRUS_CAPABILITY_H265_DEC,
 	.mod_rate	= 402000000,
 };
 
 static const struct cedrus_variant sun50i_h6_cedrus_variant = {
-	.capabilities	= CEDRUS_CAPABILITY_UNTILED,
+	.capabilities	= CEDRUS_CAPABILITY_UNTILED |
+			  CEDRUS_CAPABILITY_H265_DEC,
 	.quirks		= CEDRUS_QUIRK_NO_DMA_OFFSET,
 	.mod_rate	= 600000000,
 };
diff --git a/drivers/staging/media/sunxi/cedrus/cedrus.h b/drivers/staging/media/sunxi/cedrus/cedrus.h
index 2f017a651848..96765555ab8a 100644
--- a/drivers/staging/media/sunxi/cedrus/cedrus.h
+++ b/drivers/staging/media/sunxi/cedrus/cedrus.h
@@ -27,12 +27,14 @@
 #define CEDRUS_NAME			"cedrus"
 
 #define CEDRUS_CAPABILITY_UNTILED	BIT(0)
+#define CEDRUS_CAPABILITY_H265_DEC	BIT(1)
 
 #define CEDRUS_QUIRK_NO_DMA_OFFSET	BIT(0)
 
 enum cedrus_codec {
 	CEDRUS_CODEC_MPEG2,
 	CEDRUS_CODEC_H264,
+	CEDRUS_CODEC_H265,
 	CEDRUS_CODEC_LAST,
 };
 
@@ -67,6 +69,12 @@ struct cedrus_mpeg2_run {
 	const struct v4l2_ctrl_mpeg2_quantization	*quantization;
 };
 
+struct cedrus_h265_run {
+	const struct v4l2_ctrl_hevc_sps			*sps;
+	const struct v4l2_ctrl_hevc_pps			*pps;
+	const struct v4l2_ctrl_hevc_slice_params	*slice_params;
+};
+
 struct cedrus_run {
 	struct vb2_v4l2_buffer	*src;
 	struct vb2_v4l2_buffer	*dst;
@@ -74,6 +82,7 @@ struct cedrus_run {
 	union {
 		struct cedrus_h264_run	h264;
 		struct cedrus_mpeg2_run	mpeg2;
+		struct cedrus_h265_run	h265;
 	};
 };
 
@@ -107,9 +116,24 @@ struct cedrus_ctx {
 			ssize_t		mv_col_buf_size;
 			void		*pic_info_buf;
 			dma_addr_t	pic_info_buf_dma;
+			ssize_t		pic_info_buf_size;
 			void		*neighbor_info_buf;
 			dma_addr_t	neighbor_info_buf_dma;
+			void		*deblk_buf;
+			dma_addr_t	deblk_buf_dma;
+			ssize_t		deblk_buf_size;
+			void		*intra_pred_buf;
+			dma_addr_t	intra_pred_buf_dma;
+			ssize_t		intra_pred_buf_size;
 		} h264;
+		struct {
+			void		*mv_col_buf;
+			dma_addr_t	mv_col_buf_addr;
+			ssize_t		mv_col_buf_size;
+			ssize_t		mv_col_buf_unit_size;
+			void		*neighbor_info_buf;
+			dma_addr_t	neighbor_info_buf_addr;
+		} h265;
 	} codec;
 };
 
@@ -155,6 +179,7 @@ struct cedrus_dev {
 
 extern struct cedrus_dec_ops cedrus_dec_ops_mpeg2;
 extern struct cedrus_dec_ops cedrus_dec_ops_h264;
+extern struct cedrus_dec_ops cedrus_dec_ops_h265;
 
 static inline void cedrus_write(struct cedrus_dev *dev, u32 reg, u32 val)
 {
@@ -179,12 +204,16 @@ static inline dma_addr_t cedrus_buf_addr(struct vb2_buffer *buf,
 static inline dma_addr_t cedrus_dst_buf_addr(struct cedrus_ctx *ctx,
 					     int index, unsigned int plane)
 {
-	struct vb2_buffer *buf;
+	struct vb2_buffer *buf = NULL;
+	struct vb2_queue *vq;
 
 	if (index < 0)
 		return 0;
 
-	buf = ctx->fh.m2m_ctx->cap_q_ctx.q.bufs[index];
+	vq = v4l2_m2m_get_vq(ctx->fh.m2m_ctx, V4L2_BUF_TYPE_VIDEO_CAPTURE);
+	if (vq)
+		buf = vb2_get_buffer(vq, index);
+
 	return buf ? cedrus_buf_addr(buf, &ctx->dst_fmt, plane) : 0;
 }
 
diff --git a/drivers/staging/media/sunxi/cedrus/cedrus_dec.c b/drivers/staging/media/sunxi/cedrus/cedrus_dec.c
index 56ca4c9ad01c..4a2fc33a1d79 100644
--- a/drivers/staging/media/sunxi/cedrus/cedrus_dec.c
+++ b/drivers/staging/media/sunxi/cedrus/cedrus_dec.c
@@ -59,6 +59,15 @@ void cedrus_device_run(void *priv)
 			V4L2_CID_MPEG_VIDEO_H264_SPS);
 		break;
 
+	case V4L2_PIX_FMT_HEVC_SLICE:
+		run.h265.sps = cedrus_find_control_data(ctx,
+			V4L2_CID_MPEG_VIDEO_HEVC_SPS);
+		run.h265.pps = cedrus_find_control_data(ctx,
+			V4L2_CID_MPEG_VIDEO_HEVC_PPS);
+		run.h265.slice_params = cedrus_find_control_data(ctx,
+			V4L2_CID_MPEG_VIDEO_HEVC_SLICE_PARAMS);
+		break;
+
 	default:
 		break;
 	}
diff --git a/drivers/staging/media/sunxi/cedrus/cedrus_h264.c b/drivers/staging/media/sunxi/cedrus/cedrus_h264.c
index d6a782703c9b..bfb4a4820a67 100644
--- a/drivers/staging/media/sunxi/cedrus/cedrus_h264.c
+++ b/drivers/staging/media/sunxi/cedrus/cedrus_h264.c
@@ -6,6 +6,7 @@
  * Copyright (c) 2018 Bootlin
  */
 
+#include <linux/delay.h>
 #include <linux/types.h>
 
 #include <media/videobuf2-dma-contig.h>
@@ -38,7 +39,7 @@ struct cedrus_h264_sram_ref_pic {
 #define CEDRUS_H264_FRAME_NUM		18
 
 #define CEDRUS_NEIGHBOR_INFO_BUF_SIZE	(16 * SZ_1K)
-#define CEDRUS_PIC_INFO_BUF_SIZE	(128 * SZ_1K)
+#define CEDRUS_MIN_PIC_INFO_BUF_SIZE       (130 * SZ_1K)
 
 static void cedrus_h264_write_sram(struct cedrus_dev *dev,
 				   enum cedrus_h264_sram_off off,
@@ -96,7 +97,7 @@ static void cedrus_write_frame_list(struct cedrus_ctx *ctx,
 	const struct v4l2_ctrl_h264_decode_params *decode = run->h264.decode_params;
 	const struct v4l2_ctrl_h264_slice_params *slice = run->h264.slice_params;
 	const struct v4l2_ctrl_h264_sps *sps = run->h264.sps;
-	struct vb2_queue *cap_q = &ctx->fh.m2m_ctx->cap_q_ctx.q;
+	struct vb2_queue *cap_q;
 	struct cedrus_buffer *output_buf;
 	struct cedrus_dev *dev = ctx->dev;
 	unsigned long used_dpbs = 0;
@@ -104,6 +105,8 @@ static void cedrus_write_frame_list(struct cedrus_ctx *ctx,
 	unsigned int output = 0;
 	unsigned int i;
 
+	cap_q = v4l2_m2m_get_vq(ctx->fh.m2m_ctx, V4L2_BUF_TYPE_VIDEO_CAPTURE);
+
 	memset(pic_list, 0, sizeof(pic_list));
 
 	for (i = 0; i < ARRAY_SIZE(decode->dpb); i++) {
@@ -167,12 +170,14 @@ static void _cedrus_write_ref_list(struct cedrus_ctx *ctx,
 				   enum cedrus_h264_sram_off sram)
 {
 	const struct v4l2_ctrl_h264_decode_params *decode = run->h264.decode_params;
-	struct vb2_queue *cap_q = &ctx->fh.m2m_ctx->cap_q_ctx.q;
+	struct vb2_queue *cap_q;
 	struct cedrus_dev *dev = ctx->dev;
 	u8 sram_array[CEDRUS_MAX_REF_IDX];
 	unsigned int i;
 	size_t size;
 
+	cap_q = v4l2_m2m_get_vq(ctx->fh.m2m_ctx, V4L2_BUF_TYPE_VIDEO_CAPTURE);
+
 	memset(sram_array, 0, sizeof(sram_array));
 
 	for (i = 0; i < num_ref; i++) {
@@ -240,8 +245,8 @@ static void cedrus_write_scaling_lists(struct cedrus_ctx *ctx,
 			       sizeof(scaling->scaling_list_8x8[0]));
 
 	cedrus_h264_write_sram(dev, CEDRUS_SRAM_H264_SCALING_LIST_8x8_1,
-			       scaling->scaling_list_8x8[3],
-			       sizeof(scaling->scaling_list_8x8[3]));
+			       scaling->scaling_list_8x8[1],
+			       sizeof(scaling->scaling_list_8x8[1]));
 
 	cedrus_h264_write_sram(dev, CEDRUS_SRAM_H264_SCALING_LIST_4x4,
 			       scaling->scaling_list_4x4,
@@ -289,6 +294,28 @@ static void cedrus_write_pred_weight_table(struct cedrus_ctx *ctx,
 	}
 }
 
+/*
+ * It turns out that using VE_H264_VLD_OFFSET to skip bits is not reliable. In
+ * rare cases frame is not decoded correctly. However, setting offset to 0 and
+ * skipping appropriate amount of bits with flush bits trigger always works.
+ */
+static void cedrus_skip_bits(struct cedrus_dev *dev, int num)
+{
+	int count = 0;
+
+	while (count < num) {
+		int tmp = min(num - count, 32);
+
+		cedrus_write(dev, VE_H264_TRIGGER_TYPE,
+			     VE_H264_TRIGGER_TYPE_FLUSH_BITS |
+			     VE_H264_TRIGGER_TYPE_N_BITS(tmp));
+		while (cedrus_read(dev, VE_H264_STATUS) & VE_H264_STATUS_VLD_BUSY)
+			udelay(1);
+
+		count += tmp;
+	}
+}
+
 static void cedrus_set_params(struct cedrus_ctx *ctx,
 			      struct cedrus_run *run)
 {
@@ -299,12 +326,13 @@ static void cedrus_set_params(struct cedrus_ctx *ctx,
 	struct vb2_buffer *src_buf = &run->src->vb2_buf;
 	struct cedrus_dev *dev = ctx->dev;
 	dma_addr_t src_buf_addr;
-	u32 offset = slice->header_bit_size;
-	u32 len = (slice->size * 8) - offset;
+	u32 len = slice->size * 8;
+	unsigned int pic_width_in_mbs;
+	bool mbaff_pic;
 	u32 reg;
 
 	cedrus_write(dev, VE_H264_VLD_LEN, len);
-	cedrus_write(dev, VE_H264_VLD_OFFSET, offset);
+	cedrus_write(dev, VE_H264_VLD_OFFSET, 0);
 
 	src_buf_addr = vb2_dma_contig_plane_dma_addr(src_buf, 0);
 	cedrus_write(dev, VE_H264_VLD_END,
@@ -314,6 +342,20 @@ static void cedrus_set_params(struct cedrus_ctx *ctx,
 		     VE_H264_VLD_ADDR_FIRST | VE_H264_VLD_ADDR_VALID |
 		     VE_H264_VLD_ADDR_LAST);
 
+	if (ctx->src_fmt.width > 2048) {
+		cedrus_write(dev, VE_BUF_CTRL,
+			     VE_BUF_CTRL_INTRAPRED_MIXED_RAM |
+			     VE_BUF_CTRL_DBLK_MIXED_RAM);
+		cedrus_write(dev, VE_DBLK_DRAM_BUF_ADDR,
+			     ctx->codec.h264.deblk_buf_dma);
+		cedrus_write(dev, VE_INTRAPRED_DRAM_BUF_ADDR,
+			     ctx->codec.h264.intra_pred_buf_dma);
+	} else {
+		cedrus_write(dev, VE_BUF_CTRL,
+			     VE_BUF_CTRL_INTRAPRED_INT_SRAM |
+			     VE_BUF_CTRL_DBLK_INT_SRAM);
+	}
+
 	/*
 	 * FIXME: Since the bitstream parsing is done in software, and
 	 * in userspace, this shouldn't be needed anymore. But it
@@ -323,6 +365,8 @@ static void cedrus_set_params(struct cedrus_ctx *ctx,
 	cedrus_write(dev, VE_H264_TRIGGER_TYPE,
 		     VE_H264_TRIGGER_TYPE_INIT_SWDEC);
 
+	cedrus_skip_bits(dev, slice->header_bit_size);
+
 	if (((pps->flags & V4L2_H264_PPS_FLAG_WEIGHTED_PRED) &&
 	     (slice->slice_type == V4L2_H264_SLICE_TYPE_P ||
 	      slice->slice_type == V4L2_H264_SLICE_TYPE_SP)) ||
@@ -370,12 +414,20 @@ static void cedrus_set_params(struct cedrus_ctx *ctx,
 		reg |= VE_H264_SPS_DIRECT_8X8_INFERENCE;
 	cedrus_write(dev, VE_H264_SPS, reg);
 
+	mbaff_pic = !(slice->flags & V4L2_H264_SLICE_FLAG_FIELD_PIC) &&
+		    (sps->flags & V4L2_H264_SPS_FLAG_MB_ADAPTIVE_FRAME_FIELD);
+	pic_width_in_mbs = sps->pic_width_in_mbs_minus1 + 1;
+
 	// slice parameters
 	reg = 0;
+	reg |= ((slice->first_mb_in_slice % pic_width_in_mbs) & 0xff) << 24;
+	reg |= (((slice->first_mb_in_slice / pic_width_in_mbs) *
+		 (mbaff_pic + 1)) & 0xff) << 16;
 	reg |= decode->nal_ref_idc ? BIT(12) : 0;
 	reg |= (slice->slice_type & 0xf) << 8;
 	reg |= slice->cabac_init_idc & 0x3;
-	reg |= VE_H264_SHS_FIRST_SLICE_IN_PIC;
+	if (ctx->fh.m2m_ctx->new_frame)
+		reg |= VE_H264_SHS_FIRST_SLICE_IN_PIC;
 	if (slice->flags & V4L2_H264_SLICE_FLAG_FIELD_PIC)
 		reg |= VE_H264_SHS_FIELD_PIC;
 	if (slice->flags & V4L2_H264_SLICE_FLAG_BOTTOM_FIELD)
@@ -447,7 +499,7 @@ static void cedrus_h264_setup(struct cedrus_ctx *ctx,
 {
 	struct cedrus_dev *dev = ctx->dev;
 
-	cedrus_engine_enable(dev, CEDRUS_CODEC_H264);
+	cedrus_engine_enable(ctx, CEDRUS_CODEC_H264);
 
 	cedrus_write(dev, VE_H264_SDROT_CTRL, 0);
 	cedrus_write(dev, VE_H264_EXTRA_BUFFER1,
@@ -464,18 +516,30 @@ static void cedrus_h264_setup(struct cedrus_ctx *ctx,
 static int cedrus_h264_start(struct cedrus_ctx *ctx)
 {
 	struct cedrus_dev *dev = ctx->dev;
+	unsigned int pic_info_size;
 	unsigned int field_size;
 	unsigned int mv_col_size;
 	int ret;
 
+	/* Formula for picture buffer size is taken from CedarX source. */
+
+	if (ctx->src_fmt.width > 2048)
+		pic_info_size = CEDRUS_H264_FRAME_NUM * 0x4000;
+	else
+		pic_info_size = CEDRUS_H264_FRAME_NUM * 0x1000;
+
 	/*
-	 * FIXME: It seems that the H6 cedarX code is using a formula
-	 * here based on the size of the frame, while all the older
-	 * code is using a fixed size, so that might need to be
-	 * changed at some point.
+	 * FIXME: If V4L2_H264_SPS_FLAG_FRAME_MBS_ONLY is set,
+	 * there is no need to multiply by 2.
 	 */
+	pic_info_size += ctx->src_fmt.height * 2 * 64;
+
+	if (pic_info_size < CEDRUS_MIN_PIC_INFO_BUF_SIZE)
+		pic_info_size = CEDRUS_MIN_PIC_INFO_BUF_SIZE;
+
+	ctx->codec.h264.pic_info_buf_size = pic_info_size;
 	ctx->codec.h264.pic_info_buf =
-		dma_alloc_coherent(dev->dev, CEDRUS_PIC_INFO_BUF_SIZE,
+		dma_alloc_coherent(dev->dev, ctx->codec.h264.pic_info_buf_size,
 				   &ctx->codec.h264.pic_info_buf_dma,
 				   GFP_KERNEL);
 	if (!ctx->codec.h264.pic_info_buf)
@@ -528,15 +592,56 @@ static int cedrus_h264_start(struct cedrus_ctx *ctx)
 		goto err_neighbor_buf;
 	}
 
+	if (ctx->src_fmt.width > 2048) {
+		/*
+		 * Formulas for deblock and intra prediction buffer sizes
+		 * are taken from CedarX source.
+		 */
+
+		ctx->codec.h264.deblk_buf_size =
+			ALIGN(ctx->src_fmt.width, 32) * 12;
+		ctx->codec.h264.deblk_buf =
+			dma_alloc_coherent(dev->dev,
+					   ctx->codec.h264.deblk_buf_size,
+					   &ctx->codec.h264.deblk_buf_dma,
+					   GFP_KERNEL);
+		if (!ctx->codec.h264.deblk_buf) {
+			ret = -ENOMEM;
+			goto err_mv_col_buf;
+		}
+
+		ctx->codec.h264.intra_pred_buf_size =
+			ALIGN(ctx->src_fmt.width, 64) * 5;
+		ctx->codec.h264.intra_pred_buf =
+			dma_alloc_coherent(dev->dev,
+					   ctx->codec.h264.intra_pred_buf_size,
+					   &ctx->codec.h264.intra_pred_buf_dma,
+					   GFP_KERNEL);
+		if (!ctx->codec.h264.intra_pred_buf) {
+			ret = -ENOMEM;
+			goto err_deblk_buf;
+		}
+	}
+
 	return 0;
 
+err_deblk_buf:
+	dma_free_coherent(dev->dev, ctx->codec.h264.deblk_buf_size,
+			  ctx->codec.h264.deblk_buf,
+			  ctx->codec.h264.deblk_buf_dma);
+
+err_mv_col_buf:
+	dma_free_coherent(dev->dev, ctx->codec.h264.mv_col_buf_size,
+			  ctx->codec.h264.mv_col_buf,
+			  ctx->codec.h264.mv_col_buf_dma);
+
 err_neighbor_buf:
 	dma_free_coherent(dev->dev, CEDRUS_NEIGHBOR_INFO_BUF_SIZE,
 			  ctx->codec.h264.neighbor_info_buf,
 			  ctx->codec.h264.neighbor_info_buf_dma);
 
 err_pic_buf:
-	dma_free_coherent(dev->dev, CEDRUS_PIC_INFO_BUF_SIZE,
+	dma_free_coherent(dev->dev, ctx->codec.h264.pic_info_buf_size,
 			  ctx->codec.h264.pic_info_buf,
 			  ctx->codec.h264.pic_info_buf_dma);
 	return ret;
@@ -552,9 +657,17 @@ static void cedrus_h264_stop(struct cedrus_ctx *ctx)
 	dma_free_coherent(dev->dev, CEDRUS_NEIGHBOR_INFO_BUF_SIZE,
 			  ctx->codec.h264.neighbor_info_buf,
 			  ctx->codec.h264.neighbor_info_buf_dma);
-	dma_free_coherent(dev->dev, CEDRUS_PIC_INFO_BUF_SIZE,
+	dma_free_coherent(dev->dev, ctx->codec.h264.pic_info_buf_size,
 			  ctx->codec.h264.pic_info_buf,
 			  ctx->codec.h264.pic_info_buf_dma);
+	if (ctx->codec.h264.deblk_buf_size)
+		dma_free_coherent(dev->dev, ctx->codec.h264.deblk_buf_size,
+				  ctx->codec.h264.deblk_buf,
+				  ctx->codec.h264.deblk_buf_dma);
+	if (ctx->codec.h264.intra_pred_buf_size)
+		dma_free_coherent(dev->dev, ctx->codec.h264.intra_pred_buf_size,
+				  ctx->codec.h264.intra_pred_buf,
+				  ctx->codec.h264.intra_pred_buf_dma);
 }
 
 static void cedrus_h264_trigger(struct cedrus_ctx *ctx)
diff --git a/drivers/staging/media/sunxi/cedrus/cedrus_h265.c b/drivers/staging/media/sunxi/cedrus/cedrus_h265.c
new file mode 100644
index 000000000000..6945dc74e1d7
--- /dev/null
+++ b/drivers/staging/media/sunxi/cedrus/cedrus_h265.c
@@ -0,0 +1,616 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Cedrus VPU driver
+ *
+ * Copyright (C) 2013 Jens Kuske <jenskuske@gmail.com>
+ * Copyright (C) 2018 Paul Kocialkowski <paul.kocialkowski@bootlin.com>
+ * Copyright (C) 2018 Bootlin
+ */
+
+#include <linux/types.h>
+
+#include <media/videobuf2-dma-contig.h>
+
+#include "cedrus.h"
+#include "cedrus_hw.h"
+#include "cedrus_regs.h"
+
+/*
+ * These are the sizes for side buffers required by the hardware for storing
+ * internal decoding metadata. They match the values used by the early BSP
+ * implementations, that were initially exposed in libvdpau-sunxi.
+ * Subsequent BSP implementations seem to double the neighbor info buffer size
+ * for the H6 SoC, which may be related to 10 bit H265 support.
+ */
+#define CEDRUS_H265_NEIGHBOR_INFO_BUF_SIZE	(397 * SZ_1K)
+#define CEDRUS_H265_ENTRY_POINTS_BUF_SIZE	(4 * SZ_1K)
+#define CEDRUS_H265_MV_COL_BUF_UNIT_CTB_SIZE	160
+
+struct cedrus_h265_sram_frame_info {
+	__le32	top_pic_order_cnt;
+	__le32	bottom_pic_order_cnt;
+	__le32	top_mv_col_buf_addr;
+	__le32	bottom_mv_col_buf_addr;
+	__le32	luma_addr;
+	__le32	chroma_addr;
+} __packed;
+
+struct cedrus_h265_sram_pred_weight {
+	__s8	delta_weight;
+	__s8	offset;
+} __packed;
+
+static enum cedrus_irq_status cedrus_h265_irq_status(struct cedrus_ctx *ctx)
+{
+	struct cedrus_dev *dev = ctx->dev;
+	u32 reg;
+
+	reg = cedrus_read(dev, VE_DEC_H265_STATUS);
+	reg &= VE_DEC_H265_STATUS_CHECK_MASK;
+
+	if (reg & VE_DEC_H265_STATUS_CHECK_ERROR ||
+	    !(reg & VE_DEC_H265_STATUS_SUCCESS))
+		return CEDRUS_IRQ_ERROR;
+
+	return CEDRUS_IRQ_OK;
+}
+
+static void cedrus_h265_irq_clear(struct cedrus_ctx *ctx)
+{
+	struct cedrus_dev *dev = ctx->dev;
+
+	cedrus_write(dev, VE_DEC_H265_STATUS, VE_DEC_H265_STATUS_CHECK_MASK);
+}
+
+static void cedrus_h265_irq_disable(struct cedrus_ctx *ctx)
+{
+	struct cedrus_dev *dev = ctx->dev;
+	u32 reg = cedrus_read(dev, VE_DEC_H265_CTRL);
+
+	reg &= ~VE_DEC_H265_CTRL_IRQ_MASK;
+
+	cedrus_write(dev, VE_DEC_H265_CTRL, reg);
+}
+
+static void cedrus_h265_sram_write_offset(struct cedrus_dev *dev, u32 offset)
+{
+	cedrus_write(dev, VE_DEC_H265_SRAM_OFFSET, offset);
+}
+
+static void cedrus_h265_sram_write_data(struct cedrus_dev *dev, void *data,
+					unsigned int size)
+{
+	u32 *word = data;
+
+	while (size >= sizeof(u32)) {
+		cedrus_write(dev, VE_DEC_H265_SRAM_DATA, *word++);
+		size -= sizeof(u32);
+	}
+}
+
+static inline dma_addr_t
+cedrus_h265_frame_info_mv_col_buf_addr(struct cedrus_ctx *ctx,
+				       unsigned int index, unsigned int field)
+{
+	return ctx->codec.h265.mv_col_buf_addr + index *
+	       ctx->codec.h265.mv_col_buf_unit_size +
+	       field * ctx->codec.h265.mv_col_buf_unit_size / 2;
+}
+
+static void cedrus_h265_frame_info_write_single(struct cedrus_ctx *ctx,
+						unsigned int index,
+						bool field_pic,
+						u32 pic_order_cnt[],
+						int buffer_index)
+{
+	struct cedrus_dev *dev = ctx->dev;
+	dma_addr_t dst_luma_addr = cedrus_dst_buf_addr(ctx, buffer_index, 0);
+	dma_addr_t dst_chroma_addr = cedrus_dst_buf_addr(ctx, buffer_index, 1);
+	dma_addr_t mv_col_buf_addr[2] = {
+		cedrus_h265_frame_info_mv_col_buf_addr(ctx, buffer_index, 0),
+		cedrus_h265_frame_info_mv_col_buf_addr(ctx, buffer_index,
+						       field_pic ? 1 : 0)
+	};
+	u32 offset = VE_DEC_H265_SRAM_OFFSET_FRAME_INFO +
+		     VE_DEC_H265_SRAM_OFFSET_FRAME_INFO_UNIT * index;
+	struct cedrus_h265_sram_frame_info frame_info = {
+		.top_pic_order_cnt = cpu_to_le32(pic_order_cnt[0]),
+		.bottom_pic_order_cnt = cpu_to_le32(field_pic ?
+						    pic_order_cnt[1] :
+						    pic_order_cnt[0]),
+		.top_mv_col_buf_addr =
+			cpu_to_le32(VE_DEC_H265_SRAM_DATA_ADDR_BASE(mv_col_buf_addr[0])),
+		.bottom_mv_col_buf_addr = cpu_to_le32(field_pic ?
+			VE_DEC_H265_SRAM_DATA_ADDR_BASE(mv_col_buf_addr[1]) :
+			VE_DEC_H265_SRAM_DATA_ADDR_BASE(mv_col_buf_addr[0])),
+		.luma_addr = cpu_to_le32(VE_DEC_H265_SRAM_DATA_ADDR_BASE(dst_luma_addr)),
+		.chroma_addr = cpu_to_le32(VE_DEC_H265_SRAM_DATA_ADDR_BASE(dst_chroma_addr)),
+	};
+
+	cedrus_h265_sram_write_offset(dev, offset);
+	cedrus_h265_sram_write_data(dev, &frame_info, sizeof(frame_info));
+}
+
+static void cedrus_h265_frame_info_write_dpb(struct cedrus_ctx *ctx,
+					     const struct v4l2_hevc_dpb_entry *dpb,
+					     u8 num_active_dpb_entries)
+{
+	struct vb2_queue *vq = v4l2_m2m_get_vq(ctx->fh.m2m_ctx,
+					       V4L2_BUF_TYPE_VIDEO_CAPTURE);
+	unsigned int i;
+
+	for (i = 0; i < num_active_dpb_entries; i++) {
+		int buffer_index = vb2_find_timestamp(vq, dpb[i].timestamp, 0);
+		u32 pic_order_cnt[2] = {
+			dpb[i].pic_order_cnt[0],
+			dpb[i].pic_order_cnt[1]
+		};
+
+		cedrus_h265_frame_info_write_single(ctx, i, dpb[i].field_pic,
+						    pic_order_cnt,
+						    buffer_index);
+	}
+}
+
+static void cedrus_h265_ref_pic_list_write(struct cedrus_dev *dev,
+					   const struct v4l2_hevc_dpb_entry *dpb,
+					   const u8 list[],
+					   u8 num_ref_idx_active,
+					   u32 sram_offset)
+{
+	unsigned int i;
+	u32 word = 0;
+
+	cedrus_h265_sram_write_offset(dev, sram_offset);
+
+	for (i = 0; i < num_ref_idx_active; i++) {
+		unsigned int shift = (i % 4) * 8;
+		unsigned int index = list[i];
+		u8 value = list[i];
+
+		if (dpb[index].rps == V4L2_HEVC_DPB_ENTRY_RPS_LT_CURR)
+			value |= VE_DEC_H265_SRAM_REF_PIC_LIST_LT_REF;
+
+		/* Each SRAM word gathers up to 4 references. */
+		word |= value << shift;
+
+		/* Write the word to SRAM and clear it for the next batch. */
+		if ((i % 4) == 3 || i == (num_ref_idx_active - 1)) {
+			cedrus_h265_sram_write_data(dev, &word, sizeof(word));
+			word = 0;
+		}
+	}
+}
+
+static void cedrus_h265_pred_weight_write(struct cedrus_dev *dev,
+					  const s8 delta_luma_weight[],
+					  const s8 luma_offset[],
+					  const s8 delta_chroma_weight[][2],
+					  const s8 chroma_offset[][2],
+					  u8 num_ref_idx_active,
+					  u32 sram_luma_offset,
+					  u32 sram_chroma_offset)
+{
+	struct cedrus_h265_sram_pred_weight pred_weight[2] = { { 0 } };
+	unsigned int i, j;
+
+	cedrus_h265_sram_write_offset(dev, sram_luma_offset);
+
+	for (i = 0; i < num_ref_idx_active; i++) {
+		unsigned int index = i % 2;
+
+		pred_weight[index].delta_weight = delta_luma_weight[i];
+		pred_weight[index].offset = luma_offset[i];
+
+		if (index == 1 || i == (num_ref_idx_active - 1))
+			cedrus_h265_sram_write_data(dev, (u32 *)&pred_weight,
+						    sizeof(pred_weight));
+	}
+
+	cedrus_h265_sram_write_offset(dev, sram_chroma_offset);
+
+	for (i = 0; i < num_ref_idx_active; i++) {
+		for (j = 0; j < 2; j++) {
+			pred_weight[j].delta_weight = delta_chroma_weight[i][j];
+			pred_weight[j].offset = chroma_offset[i][j];
+		}
+
+		cedrus_h265_sram_write_data(dev, &pred_weight,
+					    sizeof(pred_weight));
+	}
+}
+
+static void cedrus_h265_setup(struct cedrus_ctx *ctx,
+			      struct cedrus_run *run)
+{
+	struct cedrus_dev *dev = ctx->dev;
+	const struct v4l2_ctrl_hevc_sps *sps;
+	const struct v4l2_ctrl_hevc_pps *pps;
+	const struct v4l2_ctrl_hevc_slice_params *slice_params;
+	const struct v4l2_hevc_pred_weight_table *pred_weight_table;
+	dma_addr_t src_buf_addr;
+	dma_addr_t src_buf_end_addr;
+	u32 chroma_log2_weight_denom;
+	u32 output_pic_list_index;
+	u32 pic_order_cnt[2];
+	u32 reg;
+
+	sps = run->h265.sps;
+	pps = run->h265.pps;
+	slice_params = run->h265.slice_params;
+	pred_weight_table = &slice_params->pred_weight_table;
+
+	/* MV column buffer size and allocation. */
+	if (!ctx->codec.h265.mv_col_buf_size) {
+		unsigned int num_buffers =
+			run->dst->vb2_buf.vb2_queue->num_buffers;
+		unsigned int log2_max_luma_coding_block_size =
+			sps->log2_min_luma_coding_block_size_minus3 + 3 +
+			sps->log2_diff_max_min_luma_coding_block_size;
+		unsigned int ctb_size_luma =
+			1UL << log2_max_luma_coding_block_size;
+
+		/*
+		 * Each CTB requires a MV col buffer with a specific unit size.
+		 * Since the address is given with missing lsb bits, 1 KiB is
+		 * added to each buffer to ensure proper alignment.
+		 */
+		ctx->codec.h265.mv_col_buf_unit_size =
+			DIV_ROUND_UP(ctx->src_fmt.width, ctb_size_luma) *
+			DIV_ROUND_UP(ctx->src_fmt.height, ctb_size_luma) *
+			CEDRUS_H265_MV_COL_BUF_UNIT_CTB_SIZE + SZ_1K;
+
+		ctx->codec.h265.mv_col_buf_size = num_buffers *
+			ctx->codec.h265.mv_col_buf_unit_size;
+
+		ctx->codec.h265.mv_col_buf =
+			dma_alloc_coherent(dev->dev,
+					   ctx->codec.h265.mv_col_buf_size,
+					   &ctx->codec.h265.mv_col_buf_addr,
+					   GFP_KERNEL);
+		if (!ctx->codec.h265.mv_col_buf) {
+			ctx->codec.h265.mv_col_buf_size = 0;
+			// TODO: Abort the process here.
+			return;
+		}
+	}
+
+	/* Activate H265 engine. */
+	cedrus_engine_enable(ctx, CEDRUS_CODEC_H265);
+
+	/* Source offset and length in bits. */
+
+	reg = slice_params->data_bit_offset;
+	cedrus_write(dev, VE_DEC_H265_BITS_OFFSET, reg);
+
+	reg = slice_params->bit_size - slice_params->data_bit_offset;
+	cedrus_write(dev, VE_DEC_H265_BITS_LEN, reg);
+
+	/* Source beginning and end addresses. */
+
+	src_buf_addr = vb2_dma_contig_plane_dma_addr(&run->src->vb2_buf, 0);
+
+	reg = VE_DEC_H265_BITS_ADDR_BASE(src_buf_addr);
+	reg |= VE_DEC_H265_BITS_ADDR_VALID_SLICE_DATA;
+	reg |= VE_DEC_H265_BITS_ADDR_LAST_SLICE_DATA;
+	reg |= VE_DEC_H265_BITS_ADDR_FIRST_SLICE_DATA;
+
+	cedrus_write(dev, VE_DEC_H265_BITS_ADDR, reg);
+
+	src_buf_end_addr = src_buf_addr +
+			   DIV_ROUND_UP(slice_params->bit_size, 8);
+
+	reg = VE_DEC_H265_BITS_END_ADDR_BASE(src_buf_end_addr);
+	cedrus_write(dev, VE_DEC_H265_BITS_END_ADDR, reg);
+
+	/* Coding tree block address: start at the beginning. */
+	reg = VE_DEC_H265_DEC_CTB_ADDR_X(0) | VE_DEC_H265_DEC_CTB_ADDR_Y(0);
+	cedrus_write(dev, VE_DEC_H265_DEC_CTB_ADDR, reg);
+
+	cedrus_write(dev, VE_DEC_H265_TILE_START_CTB, 0);
+	cedrus_write(dev, VE_DEC_H265_TILE_END_CTB, 0);
+
+	/* Clear the number of correctly-decoded coding tree blocks. */
+	cedrus_write(dev, VE_DEC_H265_DEC_CTB_NUM, 0);
+
+	/* Initialize bitstream access. */
+	cedrus_write(dev, VE_DEC_H265_TRIGGER, VE_DEC_H265_TRIGGER_INIT_SWDEC);
+
+	/* Bitstream parameters. */
+
+	reg = VE_DEC_H265_DEC_NAL_HDR_NAL_UNIT_TYPE(slice_params->nal_unit_type) |
+	      VE_DEC_H265_DEC_NAL_HDR_NUH_TEMPORAL_ID_PLUS1(slice_params->nuh_temporal_id_plus1);
+
+	cedrus_write(dev, VE_DEC_H265_DEC_NAL_HDR, reg);
+
+	/* SPS. */
+
+	reg = VE_DEC_H265_DEC_SPS_HDR_MAX_TRANSFORM_HIERARCHY_DEPTH_INTRA(sps->max_transform_hierarchy_depth_intra) |
+	      VE_DEC_H265_DEC_SPS_HDR_MAX_TRANSFORM_HIERARCHY_DEPTH_INTER(sps->max_transform_hierarchy_depth_inter) |
+	      VE_DEC_H265_DEC_SPS_HDR_LOG2_DIFF_MAX_MIN_TRANSFORM_BLOCK_SIZE(sps->log2_diff_max_min_luma_transform_block_size) |
+	      VE_DEC_H265_DEC_SPS_HDR_LOG2_MIN_TRANSFORM_BLOCK_SIZE_MINUS2(sps->log2_min_luma_transform_block_size_minus2) |
+	      VE_DEC_H265_DEC_SPS_HDR_LOG2_DIFF_MAX_MIN_LUMA_CODING_BLOCK_SIZE(sps->log2_diff_max_min_luma_coding_block_size) |
+	      VE_DEC_H265_DEC_SPS_HDR_LOG2_MIN_LUMA_CODING_BLOCK_SIZE_MINUS3(sps->log2_min_luma_coding_block_size_minus3) |
+	      VE_DEC_H265_DEC_SPS_HDR_BIT_DEPTH_CHROMA_MINUS8(sps->bit_depth_chroma_minus8) |
+	      VE_DEC_H265_DEC_SPS_HDR_CHROMA_FORMAT_IDC(sps->chroma_format_idc);
+
+	reg |= VE_DEC_H265_FLAG(VE_DEC_H265_DEC_SPS_HDR_FLAG_STRONG_INTRA_SMOOTHING_ENABLE,
+				V4L2_HEVC_SPS_FLAG_STRONG_INTRA_SMOOTHING_ENABLED,
+				sps->flags);
+
+	reg |= VE_DEC_H265_FLAG(VE_DEC_H265_DEC_SPS_HDR_FLAG_SPS_TEMPORAL_MVP_ENABLED,
+				V4L2_HEVC_SPS_FLAG_SPS_TEMPORAL_MVP_ENABLED,
+				sps->flags);
+
+	reg |= VE_DEC_H265_FLAG(VE_DEC_H265_DEC_SPS_HDR_FLAG_SAMPLE_ADAPTIVE_OFFSET_ENABLED,
+				V4L2_HEVC_SPS_FLAG_SAMPLE_ADAPTIVE_OFFSET,
+				sps->flags);
+
+	reg |= VE_DEC_H265_FLAG(VE_DEC_H265_DEC_SPS_HDR_FLAG_AMP_ENABLED,
+				V4L2_HEVC_SPS_FLAG_AMP_ENABLED, sps->flags);
+
+	reg |= VE_DEC_H265_FLAG(VE_DEC_H265_DEC_SPS_HDR_FLAG_SEPARATE_COLOUR_PLANE,
+				V4L2_HEVC_SPS_FLAG_SEPARATE_COLOUR_PLANE,
+				sps->flags);
+
+	cedrus_write(dev, VE_DEC_H265_DEC_SPS_HDR, reg);
+
+	reg = VE_DEC_H265_DEC_PCM_CTRL_LOG2_DIFF_MAX_MIN_PCM_LUMA_CODING_BLOCK_SIZE(sps->log2_diff_max_min_pcm_luma_coding_block_size) |
+	      VE_DEC_H265_DEC_PCM_CTRL_LOG2_MIN_PCM_LUMA_CODING_BLOCK_SIZE_MINUS3(sps->log2_min_pcm_luma_coding_block_size_minus3) |
+	      VE_DEC_H265_DEC_PCM_CTRL_PCM_SAMPLE_BIT_DEPTH_CHROMA_MINUS1(sps->pcm_sample_bit_depth_chroma_minus1) |
+	      VE_DEC_H265_DEC_PCM_CTRL_PCM_SAMPLE_BIT_DEPTH_LUMA_MINUS1(sps->pcm_sample_bit_depth_luma_minus1);
+
+	reg |= VE_DEC_H265_FLAG(VE_DEC_H265_DEC_PCM_CTRL_FLAG_PCM_ENABLED,
+				V4L2_HEVC_SPS_FLAG_PCM_ENABLED, sps->flags);
+
+	reg |= VE_DEC_H265_FLAG(VE_DEC_H265_DEC_PCM_CTRL_FLAG_PCM_LOOP_FILTER_DISABLED,
+				V4L2_HEVC_SPS_FLAG_PCM_LOOP_FILTER_DISABLED,
+				sps->flags);
+
+	cedrus_write(dev, VE_DEC_H265_DEC_PCM_CTRL, reg);
+
+	/* PPS. */
+
+	reg = VE_DEC_H265_DEC_PPS_CTRL0_PPS_CR_QP_OFFSET(pps->pps_cr_qp_offset) |
+	      VE_DEC_H265_DEC_PPS_CTRL0_PPS_CB_QP_OFFSET(pps->pps_cb_qp_offset) |
+	      VE_DEC_H265_DEC_PPS_CTRL0_INIT_QP_MINUS26(pps->init_qp_minus26) |
+	      VE_DEC_H265_DEC_PPS_CTRL0_DIFF_CU_QP_DELTA_DEPTH(pps->diff_cu_qp_delta_depth);
+
+	reg |= VE_DEC_H265_FLAG(VE_DEC_H265_DEC_PPS_CTRL0_FLAG_CU_QP_DELTA_ENABLED,
+				V4L2_HEVC_PPS_FLAG_CU_QP_DELTA_ENABLED,
+				pps->flags);
+
+	reg |= VE_DEC_H265_FLAG(VE_DEC_H265_DEC_PPS_CTRL0_FLAG_TRANSFORM_SKIP_ENABLED,
+				V4L2_HEVC_PPS_FLAG_TRANSFORM_SKIP_ENABLED,
+				pps->flags);
+
+	reg |= VE_DEC_H265_FLAG(VE_DEC_H265_DEC_PPS_CTRL0_FLAG_CONSTRAINED_INTRA_PRED,
+				V4L2_HEVC_PPS_FLAG_CONSTRAINED_INTRA_PRED,
+				pps->flags);
+
+	reg |= VE_DEC_H265_FLAG(VE_DEC_H265_DEC_PPS_CTRL0_FLAG_SIGN_DATA_HIDING_ENABLED,
+				V4L2_HEVC_PPS_FLAG_SIGN_DATA_HIDING_ENABLED,
+				pps->flags);
+
+	cedrus_write(dev, VE_DEC_H265_DEC_PPS_CTRL0, reg);
+
+	reg = VE_DEC_H265_DEC_PPS_CTRL1_LOG2_PARALLEL_MERGE_LEVEL_MINUS2(pps->log2_parallel_merge_level_minus2);
+
+	reg |= VE_DEC_H265_FLAG(VE_DEC_H265_DEC_PPS_CTRL1_FLAG_PPS_LOOP_FILTER_ACROSS_SLICES_ENABLED,
+				V4L2_HEVC_PPS_FLAG_PPS_LOOP_FILTER_ACROSS_SLICES_ENABLED,
+				pps->flags);
+
+	reg |= VE_DEC_H265_FLAG(VE_DEC_H265_DEC_PPS_CTRL1_FLAG_LOOP_FILTER_ACROSS_TILES_ENABLED,
+				V4L2_HEVC_PPS_FLAG_LOOP_FILTER_ACROSS_TILES_ENABLED,
+				pps->flags);
+
+	reg |= VE_DEC_H265_FLAG(VE_DEC_H265_DEC_PPS_CTRL1_FLAG_ENTROPY_CODING_SYNC_ENABLED,
+				V4L2_HEVC_PPS_FLAG_ENTROPY_CODING_SYNC_ENABLED,
+				pps->flags);
+
+	/* TODO: VE_DEC_H265_DEC_PPS_CTRL1_FLAG_TILES_ENABLED */
+
+	reg |= VE_DEC_H265_FLAG(VE_DEC_H265_DEC_PPS_CTRL1_FLAG_TRANSQUANT_BYPASS_ENABLED,
+				V4L2_HEVC_PPS_FLAG_TRANSQUANT_BYPASS_ENABLED,
+				pps->flags);
+
+	reg |= VE_DEC_H265_FLAG(VE_DEC_H265_DEC_PPS_CTRL1_FLAG_WEIGHTED_BIPRED,
+				V4L2_HEVC_PPS_FLAG_WEIGHTED_BIPRED, pps->flags);
+
+	reg |= VE_DEC_H265_FLAG(VE_DEC_H265_DEC_PPS_CTRL1_FLAG_WEIGHTED_PRED,
+				V4L2_HEVC_PPS_FLAG_WEIGHTED_PRED, pps->flags);
+
+	cedrus_write(dev, VE_DEC_H265_DEC_PPS_CTRL1, reg);
+
+	/* Slice Parameters. */
+
+	reg = VE_DEC_H265_DEC_SLICE_HDR_INFO0_PICTURE_TYPE(slice_params->pic_struct) |
+	      VE_DEC_H265_DEC_SLICE_HDR_INFO0_FIVE_MINUS_MAX_NUM_MERGE_CAND(slice_params->five_minus_max_num_merge_cand) |
+	      VE_DEC_H265_DEC_SLICE_HDR_INFO0_NUM_REF_IDX_L1_ACTIVE_MINUS1(slice_params->num_ref_idx_l1_active_minus1) |
+	      VE_DEC_H265_DEC_SLICE_HDR_INFO0_NUM_REF_IDX_L0_ACTIVE_MINUS1(slice_params->num_ref_idx_l0_active_minus1) |
+	      VE_DEC_H265_DEC_SLICE_HDR_INFO0_COLLOCATED_REF_IDX(slice_params->collocated_ref_idx) |
+	      VE_DEC_H265_DEC_SLICE_HDR_INFO0_COLOUR_PLANE_ID(slice_params->colour_plane_id) |
+	      VE_DEC_H265_DEC_SLICE_HDR_INFO0_SLICE_TYPE(slice_params->slice_type);
+
+	reg |= VE_DEC_H265_FLAG(VE_DEC_H265_DEC_SLICE_HDR_INFO0_FLAG_COLLOCATED_FROM_L0,
+				V4L2_HEVC_SLICE_PARAMS_FLAG_COLLOCATED_FROM_L0,
+				slice_params->flags);
+
+	reg |= VE_DEC_H265_FLAG(VE_DEC_H265_DEC_SLICE_HDR_INFO0_FLAG_CABAC_INIT,
+				V4L2_HEVC_SLICE_PARAMS_FLAG_CABAC_INIT,
+				slice_params->flags);
+
+	reg |= VE_DEC_H265_FLAG(VE_DEC_H265_DEC_SLICE_HDR_INFO0_FLAG_MVD_L1_ZERO,
+				V4L2_HEVC_SLICE_PARAMS_FLAG_MVD_L1_ZERO,
+				slice_params->flags);
+
+	reg |= VE_DEC_H265_FLAG(VE_DEC_H265_DEC_SLICE_HDR_INFO0_FLAG_SLICE_SAO_CHROMA,
+				V4L2_HEVC_SLICE_PARAMS_FLAG_SLICE_SAO_CHROMA,
+				slice_params->flags);
+
+	reg |= VE_DEC_H265_FLAG(VE_DEC_H265_DEC_SLICE_HDR_INFO0_FLAG_SLICE_SAO_LUMA,
+				V4L2_HEVC_SLICE_PARAMS_FLAG_SLICE_SAO_LUMA,
+				slice_params->flags);
+
+	reg |= VE_DEC_H265_FLAG(VE_DEC_H265_DEC_SLICE_HDR_INFO0_FLAG_SLICE_TEMPORAL_MVP_ENABLE,
+				V4L2_HEVC_SLICE_PARAMS_FLAG_SLICE_TEMPORAL_MVP_ENABLED,
+				slice_params->flags);
+
+	reg |= VE_DEC_H265_FLAG(VE_DEC_H265_DEC_SLICE_HDR_INFO0_FLAG_DEPENDENT_SLICE_SEGMENT,
+				V4L2_HEVC_PPS_FLAG_DEPENDENT_SLICE_SEGMENT,
+				pps->flags);
+
+	/* FIXME: For multi-slice support. */
+	reg |= VE_DEC_H265_DEC_SLICE_HDR_INFO0_FLAG_FIRST_SLICE_SEGMENT_IN_PIC;
+
+	cedrus_write(dev, VE_DEC_H265_DEC_SLICE_HDR_INFO0, reg);
+
+	reg = VE_DEC_H265_DEC_SLICE_HDR_INFO1_SLICE_TC_OFFSET_DIV2(slice_params->slice_tc_offset_div2) |
+	      VE_DEC_H265_DEC_SLICE_HDR_INFO1_SLICE_BETA_OFFSET_DIV2(slice_params->slice_beta_offset_div2) |
+	      VE_DEC_H265_DEC_SLICE_HDR_INFO1_SLICE_POC_BIGEST_IN_RPS_ST(slice_params->num_rps_poc_st_curr_after == 0) |
+	      VE_DEC_H265_DEC_SLICE_HDR_INFO1_SLICE_CR_QP_OFFSET(slice_params->slice_cr_qp_offset) |
+	      VE_DEC_H265_DEC_SLICE_HDR_INFO1_SLICE_CB_QP_OFFSET(slice_params->slice_cb_qp_offset) |
+	      VE_DEC_H265_DEC_SLICE_HDR_INFO1_SLICE_QP_DELTA(slice_params->slice_qp_delta);
+
+	reg |= VE_DEC_H265_FLAG(VE_DEC_H265_DEC_SLICE_HDR_INFO1_FLAG_SLICE_DEBLOCKING_FILTER_DISABLED,
+				V4L2_HEVC_SLICE_PARAMS_FLAG_SLICE_DEBLOCKING_FILTER_DISABLED,
+				slice_params->flags);
+
+	reg |= VE_DEC_H265_FLAG(VE_DEC_H265_DEC_SLICE_HDR_INFO1_FLAG_SLICE_LOOP_FILTER_ACROSS_SLICES_ENABLED,
+				V4L2_HEVC_SLICE_PARAMS_FLAG_SLICE_LOOP_FILTER_ACROSS_SLICES_ENABLED,
+				slice_params->flags);
+
+	cedrus_write(dev, VE_DEC_H265_DEC_SLICE_HDR_INFO1, reg);
+
+	chroma_log2_weight_denom = pred_weight_table->luma_log2_weight_denom +
+				   pred_weight_table->delta_chroma_log2_weight_denom;
+	reg = VE_DEC_H265_DEC_SLICE_HDR_INFO2_NUM_ENTRY_POINT_OFFSETS(0) |
+	      VE_DEC_H265_DEC_SLICE_HDR_INFO2_CHROMA_LOG2_WEIGHT_DENOM(chroma_log2_weight_denom) |
+	      VE_DEC_H265_DEC_SLICE_HDR_INFO2_LUMA_LOG2_WEIGHT_DENOM(pred_weight_table->luma_log2_weight_denom);
+
+	cedrus_write(dev, VE_DEC_H265_DEC_SLICE_HDR_INFO2, reg);
+
+	/* Decoded picture size. */
+
+	reg = VE_DEC_H265_DEC_PIC_SIZE_WIDTH(ctx->src_fmt.width) |
+	      VE_DEC_H265_DEC_PIC_SIZE_HEIGHT(ctx->src_fmt.height);
+
+	cedrus_write(dev, VE_DEC_H265_DEC_PIC_SIZE, reg);
+
+	/* Scaling list. */
+
+	reg = VE_DEC_H265_SCALING_LIST_CTRL0_DEFAULT;
+	cedrus_write(dev, VE_DEC_H265_SCALING_LIST_CTRL0, reg);
+
+	/* Neightbor information address. */
+	reg = VE_DEC_H265_NEIGHBOR_INFO_ADDR_BASE(ctx->codec.h265.neighbor_info_buf_addr);
+	cedrus_write(dev, VE_DEC_H265_NEIGHBOR_INFO_ADDR, reg);
+
+	/* Write decoded picture buffer in pic list. */
+	cedrus_h265_frame_info_write_dpb(ctx, slice_params->dpb,
+					 slice_params->num_active_dpb_entries);
+
+	/* Output frame. */
+
+	output_pic_list_index = V4L2_HEVC_DPB_ENTRIES_NUM_MAX;
+	pic_order_cnt[0] = slice_params->slice_pic_order_cnt;
+	pic_order_cnt[1] = slice_params->slice_pic_order_cnt;
+
+	cedrus_h265_frame_info_write_single(ctx, output_pic_list_index,
+					    slice_params->pic_struct != 0,
+					    pic_order_cnt,
+					    run->dst->vb2_buf.index);
+
+	cedrus_write(dev, VE_DEC_H265_OUTPUT_FRAME_IDX, output_pic_list_index);
+
+	/* Reference picture list 0 (for P/B frames). */
+	if (slice_params->slice_type != V4L2_HEVC_SLICE_TYPE_I) {
+		cedrus_h265_ref_pic_list_write(dev, slice_params->dpb,
+					       slice_params->ref_idx_l0,
+					       slice_params->num_ref_idx_l0_active_minus1 + 1,
+					       VE_DEC_H265_SRAM_OFFSET_REF_PIC_LIST0);
+
+		if ((pps->flags & V4L2_HEVC_PPS_FLAG_WEIGHTED_PRED) ||
+		    (pps->flags & V4L2_HEVC_PPS_FLAG_WEIGHTED_BIPRED))
+			cedrus_h265_pred_weight_write(dev,
+						      pred_weight_table->delta_luma_weight_l0,
+						      pred_weight_table->luma_offset_l0,
+						      pred_weight_table->delta_chroma_weight_l0,
+						      pred_weight_table->chroma_offset_l0,
+						      slice_params->num_ref_idx_l0_active_minus1 + 1,
+						      VE_DEC_H265_SRAM_OFFSET_PRED_WEIGHT_LUMA_L0,
+						      VE_DEC_H265_SRAM_OFFSET_PRED_WEIGHT_CHROMA_L0);
+	}
+
+	/* Reference picture list 1 (for B frames). */
+	if (slice_params->slice_type == V4L2_HEVC_SLICE_TYPE_B) {
+		cedrus_h265_ref_pic_list_write(dev, slice_params->dpb,
+					       slice_params->ref_idx_l1,
+					       slice_params->num_ref_idx_l1_active_minus1 + 1,
+					       VE_DEC_H265_SRAM_OFFSET_REF_PIC_LIST1);
+
+		if (pps->flags & V4L2_HEVC_PPS_FLAG_WEIGHTED_BIPRED)
+			cedrus_h265_pred_weight_write(dev,
+						      pred_weight_table->delta_luma_weight_l1,
+						      pred_weight_table->luma_offset_l1,
+						      pred_weight_table->delta_chroma_weight_l1,
+						      pred_weight_table->chroma_offset_l1,
+						      slice_params->num_ref_idx_l1_active_minus1 + 1,
+						      VE_DEC_H265_SRAM_OFFSET_PRED_WEIGHT_LUMA_L1,
+						      VE_DEC_H265_SRAM_OFFSET_PRED_WEIGHT_CHROMA_L1);
+	}
+
+	/* Enable appropriate interruptions. */
+	cedrus_write(dev, VE_DEC_H265_CTRL, VE_DEC_H265_CTRL_IRQ_MASK);
+}
+
+static int cedrus_h265_start(struct cedrus_ctx *ctx)
+{
+	struct cedrus_dev *dev = ctx->dev;
+
+	/* The buffer size is calculated at setup time. */
+	ctx->codec.h265.mv_col_buf_size = 0;
+
+	ctx->codec.h265.neighbor_info_buf =
+		dma_alloc_coherent(dev->dev, CEDRUS_H265_NEIGHBOR_INFO_BUF_SIZE,
+				   &ctx->codec.h265.neighbor_info_buf_addr,
+				   GFP_KERNEL);
+	if (!ctx->codec.h265.neighbor_info_buf)
+		return -ENOMEM;
+
+	return 0;
+}
+
+static void cedrus_h265_stop(struct cedrus_ctx *ctx)
+{
+	struct cedrus_dev *dev = ctx->dev;
+
+	if (ctx->codec.h265.mv_col_buf_size > 0) {
+		dma_free_coherent(dev->dev, ctx->codec.h265.mv_col_buf_size,
+				  ctx->codec.h265.mv_col_buf,
+				  ctx->codec.h265.mv_col_buf_addr);
+
+		ctx->codec.h265.mv_col_buf_size = 0;
+	}
+
+	dma_free_coherent(dev->dev, CEDRUS_H265_NEIGHBOR_INFO_BUF_SIZE,
+			  ctx->codec.h265.neighbor_info_buf,
+			  ctx->codec.h265.neighbor_info_buf_addr);
+}
+
+static void cedrus_h265_trigger(struct cedrus_ctx *ctx)
+{
+	struct cedrus_dev *dev = ctx->dev;
+
+	cedrus_write(dev, VE_DEC_H265_TRIGGER, VE_DEC_H265_TRIGGER_DEC_SLICE);
+}
+
+struct cedrus_dec_ops cedrus_dec_ops_h265 = {
+	.irq_clear	= cedrus_h265_irq_clear,
+	.irq_disable	= cedrus_h265_irq_disable,
+	.irq_status	= cedrus_h265_irq_status,
+	.setup		= cedrus_h265_setup,
+	.start		= cedrus_h265_start,
+	.stop		= cedrus_h265_stop,
+	.trigger	= cedrus_h265_trigger,
+};
diff --git a/drivers/staging/media/sunxi/cedrus/cedrus_hw.c b/drivers/staging/media/sunxi/cedrus/cedrus_hw.c
index a942cd9bed57..daf5f244f93b 100644
--- a/drivers/staging/media/sunxi/cedrus/cedrus_hw.c
+++ b/drivers/staging/media/sunxi/cedrus/cedrus_hw.c
@@ -30,7 +30,7 @@
 #include "cedrus_hw.h"
 #include "cedrus_regs.h"
 
-int cedrus_engine_enable(struct cedrus_dev *dev, enum cedrus_codec codec)
+int cedrus_engine_enable(struct cedrus_ctx *ctx, enum cedrus_codec codec)
 {
 	u32 reg = 0;
 
@@ -50,11 +50,20 @@ int cedrus_engine_enable(struct cedrus_dev *dev, enum cedrus_codec codec)
 		reg |= VE_MODE_DEC_H264;
 		break;
 
+	case CEDRUS_CODEC_H265:
+		reg |= VE_MODE_DEC_H265;
+		break;
+
 	default:
 		return -EINVAL;
 	}
 
-	cedrus_write(dev, VE_MODE, reg);
+	if (ctx->src_fmt.width == 4096)
+		reg |= VE_MODE_PIC_WIDTH_IS_4096;
+	if (ctx->src_fmt.width > 2048)
+		reg |= VE_MODE_PIC_WIDTH_MORE_2048;
+
+	cedrus_write(ctx->dev, VE_MODE, reg);
 
 	return 0;
 }
@@ -103,7 +112,6 @@ static irqreturn_t cedrus_irq(int irq, void *data)
 {
 	struct cedrus_dev *dev = data;
 	struct cedrus_ctx *ctx;
-	struct vb2_v4l2_buffer *src_buf, *dst_buf;
 	enum vb2_buffer_state state;
 	enum cedrus_irq_status status;
 
@@ -121,24 +129,13 @@ static irqreturn_t cedrus_irq(int irq, void *data)
 	dev->dec_ops[ctx->current_codec]->irq_disable(ctx);
 	dev->dec_ops[ctx->current_codec]->irq_clear(ctx);
 
-	src_buf = v4l2_m2m_src_buf_remove(ctx->fh.m2m_ctx);
-	dst_buf = v4l2_m2m_dst_buf_remove(ctx->fh.m2m_ctx);
-
-	if (!src_buf || !dst_buf) {
-		v4l2_err(&dev->v4l2_dev,
-			 "Missing source and/or destination buffers\n");
-		return IRQ_HANDLED;
-	}
-
 	if (status == CEDRUS_IRQ_ERROR)
 		state = VB2_BUF_STATE_ERROR;
 	else
 		state = VB2_BUF_STATE_DONE;
 
-	v4l2_m2m_buf_done(src_buf, state);
-	v4l2_m2m_buf_done(dst_buf, state);
-
-	v4l2_m2m_job_finish(ctx->dev->m2m_dev, ctx->fh.m2m_ctx);
+	v4l2_m2m_buf_done_and_job_finish(ctx->dev->m2m_dev, ctx->fh.m2m_ctx,
+					 state);
 
 	return IRQ_HANDLED;
 }
@@ -146,7 +143,6 @@ static irqreturn_t cedrus_irq(int irq, void *data)
 int cedrus_hw_probe(struct cedrus_dev *dev)
 {
 	const struct cedrus_variant *variant;
-	struct resource *res;
 	int irq_dec;
 	int ret;
 
@@ -225,8 +221,7 @@ int cedrus_hw_probe(struct cedrus_dev *dev)
 		goto err_sram;
 	}
 
-	res = platform_get_resource(dev->pdev, IORESOURCE_MEM, 0);
-	dev->base = devm_ioremap_resource(dev->dev, res);
+	dev->base = devm_platform_ioremap_resource(dev->pdev, 0);
 	if (IS_ERR(dev->base)) {
 		dev_err(dev->dev, "Failed to map registers\n");
 
diff --git a/drivers/staging/media/sunxi/cedrus/cedrus_hw.h b/drivers/staging/media/sunxi/cedrus/cedrus_hw.h
index 27d0882397aa..604ff932fbf5 100644
--- a/drivers/staging/media/sunxi/cedrus/cedrus_hw.h
+++ b/drivers/staging/media/sunxi/cedrus/cedrus_hw.h
@@ -16,7 +16,7 @@
 #ifndef _CEDRUS_HW_H_
 #define _CEDRUS_HW_H_
 
-int cedrus_engine_enable(struct cedrus_dev *dev, enum cedrus_codec codec);
+int cedrus_engine_enable(struct cedrus_ctx *ctx, enum cedrus_codec codec);
 void cedrus_engine_disable(struct cedrus_dev *dev);
 
 void cedrus_dst_format_set(struct cedrus_dev *dev,
diff --git a/drivers/staging/media/sunxi/cedrus/cedrus_mpeg2.c b/drivers/staging/media/sunxi/cedrus/cedrus_mpeg2.c
index 13c34927bad5..8bcd6b8f9e2d 100644
--- a/drivers/staging/media/sunxi/cedrus/cedrus_mpeg2.c
+++ b/drivers/staging/media/sunxi/cedrus/cedrus_mpeg2.c
@@ -96,7 +96,7 @@ static void cedrus_mpeg2_setup(struct cedrus_ctx *ctx, struct cedrus_run *run)
 	quantization = run->mpeg2.quantization;
 
 	/* Activate MPEG engine. */
-	cedrus_engine_enable(dev, CEDRUS_CODEC_MPEG2);
+	cedrus_engine_enable(ctx, CEDRUS_CODEC_MPEG2);
 
 	/* Set intra quantization matrix. */
 
diff --git a/drivers/staging/media/sunxi/cedrus/cedrus_regs.h b/drivers/staging/media/sunxi/cedrus/cedrus_regs.h
index ddd29788d685..7beb03d3bb39 100644
--- a/drivers/staging/media/sunxi/cedrus/cedrus_regs.h
+++ b/drivers/staging/media/sunxi/cedrus/cedrus_regs.h
@@ -10,6 +10,9 @@
 #ifndef _CEDRUS_REGS_H_
 #define _CEDRUS_REGS_H_
 
+#define SHIFT_AND_MASK_BITS(v, h, l) \
+	(((unsigned long)(v) << (l)) & GENMASK(h, l))
+
 /*
  * Common acronyms and contractions used in register descriptions:
  * * VLD : Variable-Length Decoder
@@ -18,13 +21,22 @@
  * * MC: Motion Compensation
  * * STCD: Start Code Detect
  * * SDRT: Scale Down and Rotate
+ * * WB: Writeback
+ * * BITS/BS: Bitstream
+ * * MB: Macroblock
+ * * CTU: Coding Tree Unit
+ * * CTB: Coding Tree Block
+ * * IDX: Index
  */
 
 #define VE_ENGINE_DEC_MPEG			0x100
 #define VE_ENGINE_DEC_H264			0x200
+#define VE_ENGINE_DEC_H265			0x500
 
 #define VE_MODE					0x00
 
+#define VE_MODE_PIC_WIDTH_IS_4096		BIT(22)
+#define VE_MODE_PIC_WIDTH_MORE_2048		BIT(21)
 #define VE_MODE_REC_WR_MODE_2MB			(0x01 << 20)
 #define VE_MODE_REC_WR_MODE_1MB			(0x00 << 20)
 #define VE_MODE_DDR_MODE_BW_128			(0x03 << 16)
@@ -34,11 +46,22 @@
 #define VE_MODE_DEC_H264			(0x01 << 0)
 #define VE_MODE_DEC_MPEG			(0x00 << 0)
 
+#define VE_BUF_CTRL				0x50
+
+#define VE_BUF_CTRL_INTRAPRED_EXT_RAM		(0x02 << 2)
+#define VE_BUF_CTRL_INTRAPRED_MIXED_RAM		(0x01 << 2)
+#define VE_BUF_CTRL_INTRAPRED_INT_SRAM		(0x00 << 2)
+#define VE_BUF_CTRL_DBLK_EXT_RAM		(0x02 << 0)
+#define VE_BUF_CTRL_DBLK_MIXED_RAM		(0x01 << 0)
+#define VE_BUF_CTRL_DBLK_INT_SRAM		(0x00 << 0)
+
+#define VE_DBLK_DRAM_BUF_ADDR			0x54
+#define VE_INTRAPRED_DRAM_BUF_ADDR		0x58
 #define VE_PRIMARY_CHROMA_BUF_LEN		0xc4
 #define VE_PRIMARY_FB_LINE_STRIDE		0xc8
 
-#define VE_PRIMARY_FB_LINE_STRIDE_CHROMA(s)	(((s) << 16) & GENMASK(31, 16))
-#define VE_PRIMARY_FB_LINE_STRIDE_LUMA(s)	(((s) << 0) & GENMASK(15, 0))
+#define VE_PRIMARY_FB_LINE_STRIDE_CHROMA(s)	SHIFT_AND_MASK_BITS(s, 31, 16)
+#define VE_PRIMARY_FB_LINE_STRIDE_LUMA(s)	SHIFT_AND_MASK_BITS(s, 15, 0)
 
 #define VE_CHROMA_BUF_LEN			0xe8
 
@@ -46,7 +69,7 @@
 #define VE_SECONDARY_OUT_FMT_EXT		(0x01 << 30)
 #define VE_SECONDARY_OUT_FMT_YU12		(0x02 << 30)
 #define VE_SECONDARY_OUT_FMT_YV12		(0x03 << 30)
-#define VE_CHROMA_BUF_LEN_SDRT(l)		((l) & GENMASK(27, 0))
+#define VE_CHROMA_BUF_LEN_SDRT(l)		SHIFT_AND_MASK_BITS(l, 27, 0)
 
 #define VE_PRIMARY_OUT_FMT			0xec
 
@@ -69,15 +92,15 @@
 
 #define VE_DEC_MPEG_MP12HDR			(VE_ENGINE_DEC_MPEG + 0x00)
 
-#define VE_DEC_MPEG_MP12HDR_SLICE_TYPE(t)	(((t) << 28) & GENMASK(30, 28))
+#define VE_DEC_MPEG_MP12HDR_SLICE_TYPE(t)	SHIFT_AND_MASK_BITS(t, 30, 28)
 #define VE_DEC_MPEG_MP12HDR_F_CODE_SHIFT(x, y)	(24 - 4 * (y) - 8 * (x))
 #define VE_DEC_MPEG_MP12HDR_F_CODE(__x, __y, __v) \
-	(((__v) & GENMASK(3, 0)) << VE_DEC_MPEG_MP12HDR_F_CODE_SHIFT(__x, __y))
+	(((unsigned long)(__v) & GENMASK(3, 0)) << VE_DEC_MPEG_MP12HDR_F_CODE_SHIFT(__x, __y))
 
 #define VE_DEC_MPEG_MP12HDR_INTRA_DC_PRECISION(p) \
-	(((p) << 10) & GENMASK(11, 10))
+	SHIFT_AND_MASK_BITS(p, 11, 10)
 #define VE_DEC_MPEG_MP12HDR_INTRA_PICTURE_STRUCTURE(s) \
-	(((s) << 8) & GENMASK(9, 8))
+	SHIFT_AND_MASK_BITS(s, 9, 8)
 #define VE_DEC_MPEG_MP12HDR_TOP_FIELD_FIRST(v) \
 	((v) ? BIT(7) : 0)
 #define VE_DEC_MPEG_MP12HDR_FRAME_PRED_FRAME_DCT(v) \
@@ -98,19 +121,19 @@
 #define VE_DEC_MPEG_PICCODEDSIZE		(VE_ENGINE_DEC_MPEG + 0x08)
 
 #define VE_DEC_MPEG_PICCODEDSIZE_WIDTH(w) \
-	((DIV_ROUND_UP((w), 16) << 8) & GENMASK(15, 8))
+	SHIFT_AND_MASK_BITS(DIV_ROUND_UP(w, 16), 15, 8)
 #define VE_DEC_MPEG_PICCODEDSIZE_HEIGHT(h) \
-	((DIV_ROUND_UP((h), 16) << 0) & GENMASK(7, 0))
+	SHIFT_AND_MASK_BITS(DIV_ROUND_UP(h, 16), 7, 0)
 
 #define VE_DEC_MPEG_PICBOUNDSIZE		(VE_ENGINE_DEC_MPEG + 0x0c)
 
-#define VE_DEC_MPEG_PICBOUNDSIZE_WIDTH(w)	(((w) << 16) & GENMASK(27, 16))
-#define VE_DEC_MPEG_PICBOUNDSIZE_HEIGHT(h)	(((h) << 0) & GENMASK(11, 0))
+#define VE_DEC_MPEG_PICBOUNDSIZE_WIDTH(w)	SHIFT_AND_MASK_BITS(w, 27, 16)
+#define VE_DEC_MPEG_PICBOUNDSIZE_HEIGHT(h)	SHIFT_AND_MASK_BITS(h, 11, 0)
 
 #define VE_DEC_MPEG_MBADDR			(VE_ENGINE_DEC_MPEG + 0x10)
 
-#define VE_DEC_MPEG_MBADDR_X(w)			(((w) << 8) & GENMASK(15, 8))
-#define VE_DEC_MPEG_MBADDR_Y(h)			(((h) << 0) & GENMASK(7, 0))
+#define VE_DEC_MPEG_MBADDR_X(w)			SHIFT_AND_MASK_BITS(w, 15, 8)
+#define VE_DEC_MPEG_MBADDR_Y(h)			SHIFT_AND_MASK_BITS(h, 7, 0)
 
 #define VE_DEC_MPEG_CTRL			(VE_ENGINE_DEC_MPEG + 0x14)
 
@@ -225,13 +248,277 @@
 #define VE_DEC_MPEG_IQMINPUT_FLAG_INTRA		(0x01 << 14)
 #define VE_DEC_MPEG_IQMINPUT_FLAG_NON_INTRA	(0x00 << 14)
 #define VE_DEC_MPEG_IQMINPUT_WEIGHT(i, v) \
-	(((v) & GENMASK(7, 0)) | (((i) << 8) & GENMASK(13, 8)))
+	(SHIFT_AND_MASK_BITS(i, 13, 8) | SHIFT_AND_MASK_BITS(v, 7, 0))
 
 #define VE_DEC_MPEG_ERROR			(VE_ENGINE_DEC_MPEG + 0xc4)
 #define VE_DEC_MPEG_CRTMBADDR			(VE_ENGINE_DEC_MPEG + 0xc8)
 #define VE_DEC_MPEG_ROT_LUMA			(VE_ENGINE_DEC_MPEG + 0xcc)
 #define VE_DEC_MPEG_ROT_CHROMA			(VE_ENGINE_DEC_MPEG + 0xd0)
 
+#define VE_DEC_H265_DEC_NAL_HDR			(VE_ENGINE_DEC_H265 + 0x00)
+
+#define VE_DEC_H265_DEC_NAL_HDR_NUH_TEMPORAL_ID_PLUS1(v) \
+	SHIFT_AND_MASK_BITS(v, 8, 6)
+#define VE_DEC_H265_DEC_NAL_HDR_NAL_UNIT_TYPE(v) \
+	SHIFT_AND_MASK_BITS(v, 5, 0)
+
+#define VE_DEC_H265_FLAG(reg_flag, ctrl_flag, flags) \
+	(((flags) & (ctrl_flag)) ? reg_flag : 0)
+
+#define VE_DEC_H265_DEC_SPS_HDR			(VE_ENGINE_DEC_H265 + 0x04)
+
+#define VE_DEC_H265_DEC_SPS_HDR_FLAG_STRONG_INTRA_SMOOTHING_ENABLE	BIT(26)
+#define VE_DEC_H265_DEC_SPS_HDR_FLAG_SPS_TEMPORAL_MVP_ENABLED		BIT(25)
+#define VE_DEC_H265_DEC_SPS_HDR_FLAG_SAMPLE_ADAPTIVE_OFFSET_ENABLED	BIT(24)
+#define VE_DEC_H265_DEC_SPS_HDR_FLAG_AMP_ENABLED			BIT(23)
+#define VE_DEC_H265_DEC_SPS_HDR_FLAG_SEPARATE_COLOUR_PLANE		BIT(2)
+
+#define VE_DEC_H265_DEC_SPS_HDR_MAX_TRANSFORM_HIERARCHY_DEPTH_INTRA(v) \
+	SHIFT_AND_MASK_BITS(v, 22, 20)
+#define VE_DEC_H265_DEC_SPS_HDR_MAX_TRANSFORM_HIERARCHY_DEPTH_INTER(v) \
+	SHIFT_AND_MASK_BITS(v, 19, 17)
+#define VE_DEC_H265_DEC_SPS_HDR_LOG2_DIFF_MAX_MIN_TRANSFORM_BLOCK_SIZE(v) \
+	SHIFT_AND_MASK_BITS(v, 16, 15)
+#define VE_DEC_H265_DEC_SPS_HDR_LOG2_MIN_TRANSFORM_BLOCK_SIZE_MINUS2(v) \
+	SHIFT_AND_MASK_BITS(v, 14, 13)
+#define VE_DEC_H265_DEC_SPS_HDR_LOG2_DIFF_MAX_MIN_LUMA_CODING_BLOCK_SIZE(v) \
+	SHIFT_AND_MASK_BITS(v, 12, 11)
+#define VE_DEC_H265_DEC_SPS_HDR_LOG2_MIN_LUMA_CODING_BLOCK_SIZE_MINUS3(v) \
+	SHIFT_AND_MASK_BITS(v, 10, 9)
+#define VE_DEC_H265_DEC_SPS_HDR_BIT_DEPTH_CHROMA_MINUS8(v) \
+	SHIFT_AND_MASK_BITS(v, 8, 6)
+#define VE_DEC_H265_DEC_SPS_HDR_BIT_DEPTH_LUMA_MINUS8(v) \
+	SHIFT_AND_MASK_BITS(v, 5, 3)
+#define VE_DEC_H265_DEC_SPS_HDR_CHROMA_FORMAT_IDC(v) \
+	SHIFT_AND_MASK_BITS(v, 1, 0)
+
+#define VE_DEC_H265_DEC_PIC_SIZE		(VE_ENGINE_DEC_H265 + 0x08)
+
+#define VE_DEC_H265_DEC_PIC_SIZE_WIDTH(w)	(((w) << 0) & GENMASK(13, 0))
+#define VE_DEC_H265_DEC_PIC_SIZE_HEIGHT(h)	(((h) << 16) & GENMASK(29, 16))
+
+#define VE_DEC_H265_DEC_PCM_CTRL		(VE_ENGINE_DEC_H265 + 0x0c)
+
+#define VE_DEC_H265_DEC_PCM_CTRL_FLAG_PCM_ENABLED		BIT(15)
+#define VE_DEC_H265_DEC_PCM_CTRL_FLAG_PCM_LOOP_FILTER_DISABLED	BIT(14)
+
+#define VE_DEC_H265_DEC_PCM_CTRL_LOG2_DIFF_MAX_MIN_PCM_LUMA_CODING_BLOCK_SIZE(v) \
+	SHIFT_AND_MASK_BITS(v, 11, 10)
+#define VE_DEC_H265_DEC_PCM_CTRL_LOG2_MIN_PCM_LUMA_CODING_BLOCK_SIZE_MINUS3(v) \
+	SHIFT_AND_MASK_BITS(v, 9, 8)
+#define VE_DEC_H265_DEC_PCM_CTRL_PCM_SAMPLE_BIT_DEPTH_CHROMA_MINUS1(v) \
+	SHIFT_AND_MASK_BITS(v, 7, 4)
+#define VE_DEC_H265_DEC_PCM_CTRL_PCM_SAMPLE_BIT_DEPTH_LUMA_MINUS1(v) \
+	SHIFT_AND_MASK_BITS(v, 3, 0)
+
+#define VE_DEC_H265_DEC_PPS_CTRL0		(VE_ENGINE_DEC_H265 + 0x10)
+
+#define VE_DEC_H265_DEC_PPS_CTRL0_FLAG_CU_QP_DELTA_ENABLED	BIT(3)
+#define VE_DEC_H265_DEC_PPS_CTRL0_FLAG_TRANSFORM_SKIP_ENABLED	BIT(2)
+#define VE_DEC_H265_DEC_PPS_CTRL0_FLAG_CONSTRAINED_INTRA_PRED	BIT(1)
+#define VE_DEC_H265_DEC_PPS_CTRL0_FLAG_SIGN_DATA_HIDING_ENABLED	BIT(0)
+
+#define VE_DEC_H265_DEC_PPS_CTRL0_PPS_CR_QP_OFFSET(v) \
+	SHIFT_AND_MASK_BITS(v, 29, 24)
+#define VE_DEC_H265_DEC_PPS_CTRL0_PPS_CB_QP_OFFSET(v) \
+	SHIFT_AND_MASK_BITS(v, 21, 16)
+#define VE_DEC_H265_DEC_PPS_CTRL0_INIT_QP_MINUS26(v) \
+	SHIFT_AND_MASK_BITS(v, 14, 8)
+#define VE_DEC_H265_DEC_PPS_CTRL0_DIFF_CU_QP_DELTA_DEPTH(v) \
+	SHIFT_AND_MASK_BITS(v, 5, 4)
+
+#define VE_DEC_H265_DEC_PPS_CTRL1		(VE_ENGINE_DEC_H265 + 0x14)
+
+#define VE_DEC_H265_DEC_PPS_CTRL1_FLAG_PPS_LOOP_FILTER_ACROSS_SLICES_ENABLED BIT(6)
+#define VE_DEC_H265_DEC_PPS_CTRL1_FLAG_LOOP_FILTER_ACROSS_TILES_ENABLED	BIT(5)
+#define VE_DEC_H265_DEC_PPS_CTRL1_FLAG_ENTROPY_CODING_SYNC_ENABLED	BIT(4)
+#define VE_DEC_H265_DEC_PPS_CTRL1_FLAG_TILES_ENABLED			BIT(3)
+#define VE_DEC_H265_DEC_PPS_CTRL1_FLAG_TRANSQUANT_BYPASS_ENABLED	BIT(2)
+#define VE_DEC_H265_DEC_PPS_CTRL1_FLAG_WEIGHTED_BIPRED			BIT(1)
+#define VE_DEC_H265_DEC_PPS_CTRL1_FLAG_WEIGHTED_PRED			BIT(0)
+
+#define VE_DEC_H265_DEC_PPS_CTRL1_LOG2_PARALLEL_MERGE_LEVEL_MINUS2(v) \
+	SHIFT_AND_MASK_BITS(v, 10, 8)
+
+#define VE_DEC_H265_SCALING_LIST_CTRL0		(VE_ENGINE_DEC_H265 + 0x18)
+
+#define VE_DEC_H265_SCALING_LIST_CTRL0_FLAG_ENABLED			BIT(31)
+
+#define VE_DEC_H265_SCALING_LIST_CTRL0_SRAM	(0 << 30)
+#define VE_DEC_H265_SCALING_LIST_CTRL0_DEFAULT	(1 << 30)
+
+#define VE_DEC_H265_DEC_SLICE_HDR_INFO0		(VE_ENGINE_DEC_H265 + 0x20)
+
+#define VE_DEC_H265_DEC_SLICE_HDR_INFO0_FLAG_COLLOCATED_FROM_L0		BIT(11)
+#define VE_DEC_H265_DEC_SLICE_HDR_INFO0_FLAG_CABAC_INIT			BIT(10)
+#define VE_DEC_H265_DEC_SLICE_HDR_INFO0_FLAG_MVD_L1_ZERO		BIT(9)
+#define VE_DEC_H265_DEC_SLICE_HDR_INFO0_FLAG_SLICE_SAO_CHROMA		BIT(8)
+#define VE_DEC_H265_DEC_SLICE_HDR_INFO0_FLAG_SLICE_SAO_LUMA		BIT(7)
+#define VE_DEC_H265_DEC_SLICE_HDR_INFO0_FLAG_SLICE_TEMPORAL_MVP_ENABLE	BIT(6)
+#define VE_DEC_H265_DEC_SLICE_HDR_INFO0_FLAG_DEPENDENT_SLICE_SEGMENT	BIT(1)
+#define VE_DEC_H265_DEC_SLICE_HDR_INFO0_FLAG_FIRST_SLICE_SEGMENT_IN_PIC	BIT(0)
+
+#define VE_DEC_H265_DEC_SLICE_HDR_INFO0_PICTURE_TYPE(v) \
+	SHIFT_AND_MASK_BITS(v, 29, 28)
+#define VE_DEC_H265_DEC_SLICE_HDR_INFO0_FIVE_MINUS_MAX_NUM_MERGE_CAND(v) \
+	SHIFT_AND_MASK_BITS(v, 26, 24)
+#define VE_DEC_H265_DEC_SLICE_HDR_INFO0_NUM_REF_IDX_L1_ACTIVE_MINUS1(v) \
+	SHIFT_AND_MASK_BITS(v, 23, 20)
+#define VE_DEC_H265_DEC_SLICE_HDR_INFO0_NUM_REF_IDX_L0_ACTIVE_MINUS1(v) \
+	SHIFT_AND_MASK_BITS(v, 19, 16)
+#define VE_DEC_H265_DEC_SLICE_HDR_INFO0_COLLOCATED_REF_IDX(v) \
+	SHIFT_AND_MASK_BITS(v, 15, 12)
+#define VE_DEC_H265_DEC_SLICE_HDR_INFO0_COLOUR_PLANE_ID(v) \
+	SHIFT_AND_MASK_BITS(v, 5, 4)
+#define VE_DEC_H265_DEC_SLICE_HDR_INFO0_SLICE_TYPE(v) \
+	SHIFT_AND_MASK_BITS(v, 3, 2)
+
+#define VE_DEC_H265_DEC_SLICE_HDR_INFO1		(VE_ENGINE_DEC_H265 + 0x24)
+
+#define VE_DEC_H265_DEC_SLICE_HDR_INFO1_FLAG_SLICE_DEBLOCKING_FILTER_DISABLED BIT(23)
+#define VE_DEC_H265_DEC_SLICE_HDR_INFO1_FLAG_SLICE_LOOP_FILTER_ACROSS_SLICES_ENABLED BIT(22)
+
+#define VE_DEC_H265_DEC_SLICE_HDR_INFO1_SLICE_TC_OFFSET_DIV2(v) \
+	SHIFT_AND_MASK_BITS(v, 31, 28)
+#define VE_DEC_H265_DEC_SLICE_HDR_INFO1_SLICE_BETA_OFFSET_DIV2(v) \
+	SHIFT_AND_MASK_BITS(v, 27, 24)
+#define VE_DEC_H265_DEC_SLICE_HDR_INFO1_SLICE_POC_BIGEST_IN_RPS_ST(v) \
+	((v) ? BIT(21) : 0)
+#define VE_DEC_H265_DEC_SLICE_HDR_INFO1_SLICE_CR_QP_OFFSET(v) \
+	SHIFT_AND_MASK_BITS(v, 20, 16)
+#define VE_DEC_H265_DEC_SLICE_HDR_INFO1_SLICE_CB_QP_OFFSET(v) \
+	SHIFT_AND_MASK_BITS(v, 12, 8)
+#define VE_DEC_H265_DEC_SLICE_HDR_INFO1_SLICE_QP_DELTA(v) \
+	SHIFT_AND_MASK_BITS(v, 6, 0)
+
+#define VE_DEC_H265_DEC_SLICE_HDR_INFO2		(VE_ENGINE_DEC_H265 + 0x28)
+
+#define VE_DEC_H265_DEC_SLICE_HDR_INFO2_NUM_ENTRY_POINT_OFFSETS(v) \
+	SHIFT_AND_MASK_BITS(v, 21, 8)
+#define VE_DEC_H265_DEC_SLICE_HDR_INFO2_CHROMA_LOG2_WEIGHT_DENOM(v) \
+	SHIFT_AND_MASK_BITS(v, 6, 4)
+#define VE_DEC_H265_DEC_SLICE_HDR_INFO2_LUMA_LOG2_WEIGHT_DENOM(v) \
+	SHIFT_AND_MASK_BITS(v, 2, 0)
+
+#define VE_DEC_H265_DEC_CTB_ADDR		(VE_ENGINE_DEC_H265 + 0x2c)
+
+#define VE_DEC_H265_DEC_CTB_ADDR_Y(y)		SHIFT_AND_MASK_BITS(y, 25, 16)
+#define VE_DEC_H265_DEC_CTB_ADDR_X(x)		SHIFT_AND_MASK_BITS(x, 9, 0)
+
+#define VE_DEC_H265_CTRL			(VE_ENGINE_DEC_H265 + 0x30)
+
+#define VE_DEC_H265_CTRL_DDR_CONSISTENCY_EN	BIT(31)
+#define VE_DEC_H265_CTRL_STCD_EN		BIT(25)
+#define VE_DEC_H265_CTRL_EPTB_DEC_BYPASS_EN	BIT(24)
+#define VE_DEC_H265_CTRL_TQ_BYPASS_EN		BIT(12)
+#define VE_DEC_H265_CTRL_VLD_BYPASS_EN		BIT(11)
+#define VE_DEC_H265_CTRL_NCRI_CACHE_DISABLE	BIT(10)
+#define VE_DEC_H265_CTRL_ROTATE_SCALE_OUT_EN	BIT(9)
+#define VE_DEC_H265_CTRL_MC_NO_WRITEBACK	BIT(8)
+#define VE_DEC_H265_CTRL_VLD_DATA_REQ_IRQ_EN	BIT(2)
+#define VE_DEC_H265_CTRL_ERROR_IRQ_EN		BIT(1)
+#define VE_DEC_H265_CTRL_FINISH_IRQ_EN		BIT(0)
+#define VE_DEC_H265_CTRL_IRQ_MASK \
+	(VE_DEC_H265_CTRL_FINISH_IRQ_EN | VE_DEC_H265_CTRL_ERROR_IRQ_EN | \
+	 VE_DEC_H265_CTRL_VLD_DATA_REQ_IRQ_EN)
+
+#define VE_DEC_H265_TRIGGER			(VE_ENGINE_DEC_H265 + 0x34)
+
+#define VE_DEC_H265_TRIGGER_STCD_VC1		(0x02 << 4)
+#define VE_DEC_H265_TRIGGER_STCD_AVS		(0x01 << 4)
+#define VE_DEC_H265_TRIGGER_STCD_HEVC		(0x00 << 4)
+#define VE_DEC_H265_TRIGGER_DEC_SLICE		(0x08 << 0)
+#define VE_DEC_H265_TRIGGER_INIT_SWDEC		(0x07 << 0)
+#define VE_DEC_H265_TRIGGER_BYTE_ALIGN		(0x06 << 0)
+#define VE_DEC_H265_TRIGGER_GET_VLCUE		(0x05 << 0)
+#define VE_DEC_H265_TRIGGER_GET_VLCSE		(0x04 << 0)
+#define VE_DEC_H265_TRIGGER_FLUSH_BITS		(0x03 << 0)
+#define VE_DEC_H265_TRIGGER_GET_BITS		(0x02 << 0)
+#define VE_DEC_H265_TRIGGER_SHOW_BITS		(0x01 << 0)
+
+#define VE_DEC_H265_STATUS			(VE_ENGINE_DEC_H265 + 0x38)
+
+#define VE_DEC_H265_STATUS_STCD			BIT(24)
+#define VE_DEC_H265_STATUS_STCD_BUSY		BIT(21)
+#define VE_DEC_H265_STATUS_WB_BUSY		BIT(20)
+#define VE_DEC_H265_STATUS_BS_DMA_BUSY		BIT(19)
+#define VE_DEC_H265_STATUS_IQIT_BUSY		BIT(18)
+#define VE_DEC_H265_STATUS_INTER_BUSY		BIT(17)
+#define VE_DEC_H265_STATUS_MORE_DATA		BIT(16)
+#define VE_DEC_H265_STATUS_VLD_BUSY		BIT(14)
+#define VE_DEC_H265_STATUS_DEBLOCKING_BUSY	BIT(13)
+#define VE_DEC_H265_STATUS_DEBLOCKING_DRAM_BUSY	BIT(12)
+#define VE_DEC_H265_STATUS_INTRA_BUSY		BIT(11)
+#define VE_DEC_H265_STATUS_SAO_BUSY		BIT(10)
+#define VE_DEC_H265_STATUS_MVP_BUSY		BIT(9)
+#define VE_DEC_H265_STATUS_SWDEC_BUSY		BIT(8)
+#define VE_DEC_H265_STATUS_OVER_TIME		BIT(3)
+#define VE_DEC_H265_STATUS_VLD_DATA_REQ		BIT(2)
+#define VE_DEC_H265_STATUS_ERROR		BIT(1)
+#define VE_DEC_H265_STATUS_SUCCESS		BIT(0)
+#define VE_DEC_H265_STATUS_STCD_TYPE_MASK	GENMASK(23, 22)
+#define VE_DEC_H265_STATUS_CHECK_MASK \
+	(VE_DEC_H265_STATUS_SUCCESS | VE_DEC_H265_STATUS_ERROR | \
+	 VE_DEC_H265_STATUS_VLD_DATA_REQ)
+#define VE_DEC_H265_STATUS_CHECK_ERROR \
+	(VE_DEC_H265_STATUS_ERROR | VE_DEC_H265_STATUS_VLD_DATA_REQ)
+
+#define VE_DEC_H265_DEC_CTB_NUM			(VE_ENGINE_DEC_H265 + 0x3c)
+
+#define VE_DEC_H265_BITS_ADDR			(VE_ENGINE_DEC_H265 + 0x40)
+
+#define VE_DEC_H265_BITS_ADDR_FIRST_SLICE_DATA	BIT(30)
+#define VE_DEC_H265_BITS_ADDR_LAST_SLICE_DATA	BIT(29)
+#define VE_DEC_H265_BITS_ADDR_VALID_SLICE_DATA	BIT(28)
+#define VE_DEC_H265_BITS_ADDR_BASE(a)		(((a) >> 8) & GENMASK(27, 0))
+
+#define VE_DEC_H265_BITS_OFFSET			(VE_ENGINE_DEC_H265 + 0x44)
+#define VE_DEC_H265_BITS_LEN			(VE_ENGINE_DEC_H265 + 0x48)
+
+#define VE_DEC_H265_BITS_END_ADDR		(VE_ENGINE_DEC_H265 + 0x4c)
+
+#define VE_DEC_H265_BITS_END_ADDR_BASE(a)	((a) >> 8)
+
+#define VE_DEC_H265_SDRT_CTRL			(VE_ENGINE_DEC_H265 + 0x50)
+#define VE_DEC_H265_SDRT_LUMA_ADDR		(VE_ENGINE_DEC_H265 + 0x54)
+#define VE_DEC_H265_SDRT_CHROMA_ADDR		(VE_ENGINE_DEC_H265 + 0x58)
+
+#define VE_DEC_H265_OUTPUT_FRAME_IDX		(VE_ENGINE_DEC_H265 + 0x5c)
+
+#define VE_DEC_H265_NEIGHBOR_INFO_ADDR		(VE_ENGINE_DEC_H265 + 0x60)
+
+#define VE_DEC_H265_NEIGHBOR_INFO_ADDR_BASE(a)	((a) >> 8)
+
+#define VE_DEC_H265_ENTRY_POINT_OFFSET_ADDR	(VE_ENGINE_DEC_H265 + 0x64)
+#define VE_DEC_H265_TILE_START_CTB		(VE_ENGINE_DEC_H265 + 0x68)
+#define VE_DEC_H265_TILE_END_CTB		(VE_ENGINE_DEC_H265 + 0x6c)
+
+#define VE_DEC_H265_LOW_ADDR			(VE_ENGINE_DEC_H265 + 0x80)
+
+#define VE_DEC_H265_LOW_ADDR_PRIMARY_CHROMA(a) \
+	SHIFT_AND_MASK_BITS(a, 31, 24)
+#define VE_DEC_H265_LOW_ADDR_SECONDARY_CHROMA(a) \
+	SHIFT_AND_MASK_BITS(a, 23, 16)
+#define VE_DEC_H265_LOW_ADDR_ENTRY_POINTS_BUF(a) \
+	SHIFT_AND_MASK_BITS(a, 7, 0)
+
+#define VE_DEC_H265_SRAM_OFFSET			(VE_ENGINE_DEC_H265 + 0xe0)
+
+#define VE_DEC_H265_SRAM_OFFSET_PRED_WEIGHT_LUMA_L0	0x00
+#define VE_DEC_H265_SRAM_OFFSET_PRED_WEIGHT_CHROMA_L0	0x20
+#define VE_DEC_H265_SRAM_OFFSET_PRED_WEIGHT_LUMA_L1	0x60
+#define VE_DEC_H265_SRAM_OFFSET_PRED_WEIGHT_CHROMA_L1	0x80
+#define VE_DEC_H265_SRAM_OFFSET_FRAME_INFO		0x400
+#define VE_DEC_H265_SRAM_OFFSET_FRAME_INFO_UNIT		0x20
+#define VE_DEC_H265_SRAM_OFFSET_SCALING_LISTS		0x800
+#define VE_DEC_H265_SRAM_OFFSET_REF_PIC_LIST0		0xc00
+#define VE_DEC_H265_SRAM_OFFSET_REF_PIC_LIST1		0xc10
+
+#define VE_DEC_H265_SRAM_DATA			(VE_ENGINE_DEC_H265 + 0xe4)
+
+#define VE_DEC_H265_SRAM_DATA_ADDR_BASE(a)	((a) >> 8)
+#define VE_DEC_H265_SRAM_REF_PIC_LIST_LT_REF	BIT(7)
+
 #define VE_H264_SPS			0x200
 #define VE_H264_SPS_MBS_ONLY			BIT(18)
 #define VE_H264_SPS_MB_ADAPTIVE_FRAME_FIELD	BIT(17)
@@ -267,13 +554,16 @@
 					 VE_H264_CTRL_SLICE_DECODE_INT)
 
 #define VE_H264_TRIGGER_TYPE		0x224
+#define VE_H264_TRIGGER_TYPE_N_BITS(x)		(((x) & 0x3f) << 8)
 #define VE_H264_TRIGGER_TYPE_AVC_SLICE_DECODE	(8 << 0)
 #define VE_H264_TRIGGER_TYPE_INIT_SWDEC		(7 << 0)
+#define VE_H264_TRIGGER_TYPE_FLUSH_BITS		(3 << 0)
 
 #define VE_H264_STATUS			0x228
 #define VE_H264_STATUS_VLD_DATA_REQ_INT		VE_H264_CTRL_VLD_DATA_REQ_INT
 #define VE_H264_STATUS_DECODE_ERR_INT		VE_H264_CTRL_DECODE_ERR_INT
 #define VE_H264_STATUS_SLICE_DECODE_INT		VE_H264_CTRL_SLICE_DECODE_INT
+#define VE_H264_STATUS_VLD_BUSY			BIT(8)
 
 #define VE_H264_STATUS_INT_MASK			VE_H264_CTRL_INT_MASK
 
diff --git a/drivers/staging/media/sunxi/cedrus/cedrus_video.c b/drivers/staging/media/sunxi/cedrus/cedrus_video.c
index eeee3efd247b..15cf1f10221b 100644
--- a/drivers/staging/media/sunxi/cedrus/cedrus_video.c
+++ b/drivers/staging/media/sunxi/cedrus/cedrus_video.c
@@ -29,8 +29,8 @@
 
 #define CEDRUS_MIN_WIDTH	16U
 #define CEDRUS_MIN_HEIGHT	16U
-#define CEDRUS_MAX_WIDTH	3840U
-#define CEDRUS_MAX_HEIGHT	2160U
+#define CEDRUS_MAX_WIDTH	4096U
+#define CEDRUS_MAX_HEIGHT	2304U
 
 static struct cedrus_format cedrus_formats[] = {
 	{
@@ -42,6 +42,11 @@ static struct cedrus_format cedrus_formats[] = {
 		.directions	= CEDRUS_DECODE_SRC,
 	},
 	{
+		.pixelformat	= V4L2_PIX_FMT_HEVC_SLICE,
+		.directions	= CEDRUS_DECODE_SRC,
+		.capabilities	= CEDRUS_CAPABILITY_H265_DEC,
+	},
+	{
 		.pixelformat	= V4L2_PIX_FMT_SUNXI_TILED_NV12,
 		.directions	= CEDRUS_DECODE_DST,
 	},
@@ -62,34 +67,31 @@ static inline struct cedrus_ctx *cedrus_file2ctx(struct file *file)
 static struct cedrus_format *cedrus_find_format(u32 pixelformat, u32 directions,
 						unsigned int capabilities)
 {
+	struct cedrus_format *first_valid_fmt = NULL;
 	struct cedrus_format *fmt;
 	unsigned int i;
 
 	for (i = 0; i < CEDRUS_FORMATS_COUNT; i++) {
 		fmt = &cedrus_formats[i];
 
-		if (fmt->capabilities && (fmt->capabilities & capabilities) !=
-		    fmt->capabilities)
+		if ((fmt->capabilities & capabilities) != fmt->capabilities ||
+		    !(fmt->directions & directions))
 			continue;
 
-		if (fmt->pixelformat == pixelformat &&
-		    (fmt->directions & directions) != 0)
+		if (fmt->pixelformat == pixelformat)
 			break;
+
+		if (!first_valid_fmt)
+			first_valid_fmt = fmt;
 	}
 
 	if (i == CEDRUS_FORMATS_COUNT)
-		return NULL;
+		return first_valid_fmt;
 
 	return &cedrus_formats[i];
 }
 
-static bool cedrus_check_format(u32 pixelformat, u32 directions,
-				unsigned int capabilities)
-{
-	return cedrus_find_format(pixelformat, directions, capabilities);
-}
-
-static void cedrus_prepare_format(struct v4l2_pix_format *pix_fmt)
+void cedrus_prepare_format(struct v4l2_pix_format *pix_fmt)
 {
 	unsigned int width = pix_fmt->width;
 	unsigned int height = pix_fmt->height;
@@ -105,9 +107,11 @@ static void cedrus_prepare_format(struct v4l2_pix_format *pix_fmt)
 	switch (pix_fmt->pixelformat) {
 	case V4L2_PIX_FMT_MPEG2_SLICE:
 	case V4L2_PIX_FMT_H264_SLICE:
+	case V4L2_PIX_FMT_HEVC_SLICE:
 		/* Zero bytes per line for encoded source. */
 		bytesperline = 0;
-
+		/* Choose some minimum size since this can't be 0 */
+		sizeimage = max_t(u32, SZ_1K, sizeimage);
 		break;
 
 	case V4L2_PIX_FMT_SUNXI_TILED_NV12:
@@ -214,16 +218,7 @@ static int cedrus_g_fmt_vid_cap(struct file *file, void *priv,
 {
 	struct cedrus_ctx *ctx = cedrus_file2ctx(file);
 
-	/* Fall back to dummy default by lack of hardware configuration. */
-	if (!ctx->dst_fmt.width || !ctx->dst_fmt.height) {
-		f->fmt.pix.pixelformat = V4L2_PIX_FMT_SUNXI_TILED_NV12;
-		cedrus_prepare_format(&f->fmt.pix);
-
-		return 0;
-	}
-
 	f->fmt.pix = ctx->dst_fmt;
-
 	return 0;
 }
 
@@ -232,17 +227,7 @@ static int cedrus_g_fmt_vid_out(struct file *file, void *priv,
 {
 	struct cedrus_ctx *ctx = cedrus_file2ctx(file);
 
-	/* Fall back to dummy default by lack of hardware configuration. */
-	if (!ctx->dst_fmt.width || !ctx->dst_fmt.height) {
-		f->fmt.pix.pixelformat = V4L2_PIX_FMT_MPEG2_SLICE;
-		f->fmt.pix.sizeimage = SZ_1K;
-		cedrus_prepare_format(&f->fmt.pix);
-
-		return 0;
-	}
-
 	f->fmt.pix = ctx->src_fmt;
-
 	return 0;
 }
 
@@ -252,11 +237,14 @@ static int cedrus_try_fmt_vid_cap(struct file *file, void *priv,
 	struct cedrus_ctx *ctx = cedrus_file2ctx(file);
 	struct cedrus_dev *dev = ctx->dev;
 	struct v4l2_pix_format *pix_fmt = &f->fmt.pix;
+	struct cedrus_format *fmt =
+		cedrus_find_format(pix_fmt->pixelformat, CEDRUS_DECODE_DST,
+				   dev->capabilities);
 
-	if (!cedrus_check_format(pix_fmt->pixelformat, CEDRUS_DECODE_DST,
-				 dev->capabilities))
+	if (!fmt)
 		return -EINVAL;
 
+	pix_fmt->pixelformat = fmt->pixelformat;
 	cedrus_prepare_format(pix_fmt);
 
 	return 0;
@@ -268,15 +256,14 @@ static int cedrus_try_fmt_vid_out(struct file *file, void *priv,
 	struct cedrus_ctx *ctx = cedrus_file2ctx(file);
 	struct cedrus_dev *dev = ctx->dev;
 	struct v4l2_pix_format *pix_fmt = &f->fmt.pix;
+	struct cedrus_format *fmt =
+		cedrus_find_format(pix_fmt->pixelformat, CEDRUS_DECODE_SRC,
+				   dev->capabilities);
 
-	if (!cedrus_check_format(pix_fmt->pixelformat, CEDRUS_DECODE_SRC,
-				 dev->capabilities))
-		return -EINVAL;
-
-	/* Source image size has to be provided by userspace. */
-	if (pix_fmt->sizeimage == 0)
+	if (!fmt)
 		return -EINVAL;
 
+	pix_fmt->pixelformat = fmt->pixelformat;
 	cedrus_prepare_format(pix_fmt);
 
 	return 0;
@@ -322,6 +309,17 @@ static int cedrus_s_fmt_vid_out(struct file *file, void *priv,
 
 	ctx->src_fmt = f->fmt.pix;
 
+	switch (ctx->src_fmt.pixelformat) {
+	case V4L2_PIX_FMT_H264_SLICE:
+		vq->subsystem_flags |=
+			VB2_V4L2_FL_SUPPORTS_M2M_HOLD_CAPTURE_BUF;
+		break;
+	default:
+		vq->subsystem_flags &=
+			~VB2_V4L2_FL_SUPPORTS_M2M_HOLD_CAPTURE_BUF;
+		break;
+	}
+
 	/* Propagate colorspace information to capture. */
 	ctx->dst_fmt.colorspace = f->fmt.pix.colorspace;
 	ctx->dst_fmt.xfer_func = f->fmt.pix.xfer_func;
@@ -355,6 +353,9 @@ const struct v4l2_ioctl_ops cedrus_ioctl_ops = {
 	.vidioc_streamon		= v4l2_m2m_ioctl_streamon,
 	.vidioc_streamoff		= v4l2_m2m_ioctl_streamoff,
 
+	.vidioc_try_decoder_cmd		= v4l2_m2m_ioctl_stateless_try_decoder_cmd,
+	.vidioc_decoder_cmd		= v4l2_m2m_ioctl_stateless_decoder_cmd,
+
 	.vidioc_subscribe_event		= v4l2_ctrl_subscribe_event,
 	.vidioc_unsubscribe_event	= v4l2_event_unsubscribe,
 };
@@ -364,21 +365,12 @@ static int cedrus_queue_setup(struct vb2_queue *vq, unsigned int *nbufs,
 			      struct device *alloc_devs[])
 {
 	struct cedrus_ctx *ctx = vb2_get_drv_priv(vq);
-	struct cedrus_dev *dev = ctx->dev;
 	struct v4l2_pix_format *pix_fmt;
-	u32 directions;
 
-	if (V4L2_TYPE_IS_OUTPUT(vq->type)) {
-		directions = CEDRUS_DECODE_SRC;
+	if (V4L2_TYPE_IS_OUTPUT(vq->type))
 		pix_fmt = &ctx->src_fmt;
-	} else {
-		directions = CEDRUS_DECODE_DST;
+	else
 		pix_fmt = &ctx->dst_fmt;
-	}
-
-	if (!cedrus_check_format(pix_fmt->pixelformat, directions,
-				 dev->capabilities))
-		return -EINVAL;
 
 	if (*nplanes) {
 		if (sizes[0] < pix_fmt->sizeimage)
@@ -453,6 +445,10 @@ static int cedrus_start_streaming(struct vb2_queue *vq, unsigned int count)
 		ctx->current_codec = CEDRUS_CODEC_H264;
 		break;
 
+	case V4L2_PIX_FMT_HEVC_SLICE:
+		ctx->current_codec = CEDRUS_CODEC_H265;
+		break;
+
 	default:
 		return -EINVAL;
 	}
diff --git a/drivers/staging/media/sunxi/cedrus/cedrus_video.h b/drivers/staging/media/sunxi/cedrus/cedrus_video.h
index 0e4f7a8cccf2..05050c0a0921 100644
--- a/drivers/staging/media/sunxi/cedrus/cedrus_video.h
+++ b/drivers/staging/media/sunxi/cedrus/cedrus_video.h
@@ -26,5 +26,6 @@ extern const struct v4l2_ioctl_ops cedrus_ioctl_ops;
 
 int cedrus_queue_init(void *priv, struct vb2_queue *src_vq,
 		      struct vb2_queue *dst_vq);
+void cedrus_prepare_format(struct v4l2_pix_format *pix_fmt);
 
 #endif
diff --git a/drivers/staging/most/sound/sound.c b/drivers/staging/most/sound/sound.c
index 79817061fcfa..add16997f129 100644
--- a/drivers/staging/most/sound/sound.c
+++ b/drivers/staging/most/sound/sound.c
@@ -344,8 +344,7 @@ static int pcm_hw_params(struct snd_pcm_substream *substream,
 		pr_err("Requested number of channels not supported.\n");
 		return -EINVAL;
 	}
-	return snd_pcm_lib_alloc_vmalloc_buffer(substream,
-						params_buffer_bytes(hw_params));
+	return snd_pcm_lib_malloc_pages(substream, params_buffer_bytes(hw_params));
 }
 
 /**
@@ -359,7 +358,7 @@ static int pcm_hw_params(struct snd_pcm_substream *substream,
  */
 static int pcm_hw_free(struct snd_pcm_substream *substream)
 {
-	return snd_pcm_lib_free_vmalloc_buffer(substream);
+	return snd_pcm_lib_free_pages(substream);
 }
 
 /**
@@ -469,7 +468,6 @@ static const struct snd_pcm_ops pcm_ops = {
 	.prepare    = pcm_prepare,
 	.trigger    = pcm_trigger,
 	.pointer    = pcm_pointer,
-	.page       = snd_pcm_lib_get_vmalloc_page,
 };
 
 static int split_arg_list(char *buf, u16 *ch_num, char **sample_res)
@@ -663,6 +661,8 @@ skip_adpt_alloc:
 	pcm->private_data = channel;
 	strscpy(pcm->name, device_name, sizeof(pcm->name));
 	snd_pcm_set_ops(pcm, direction, &pcm_ops);
+	snd_pcm_lib_preallocate_pages_for_all(pcm, SNDRV_DMA_TYPE_VMALLOC,
+					      NULL, 0, 0);
 
 	return 0;
 
diff --git a/drivers/tty/tty_ldsem.c b/drivers/tty/tty_ldsem.c
index 60ff236a3d63..ce8291053af3 100644
--- a/drivers/tty/tty_ldsem.c
+++ b/drivers/tty/tty_ldsem.c
@@ -303,7 +303,7 @@ static int __ldsem_down_read_nested(struct ld_semaphore *sem,
 	if (count <= 0) {
 		lock_contended(&sem->dep_map, _RET_IP_);
 		if (!down_read_failed(sem, count, timeout)) {
-			rwsem_release(&sem->dep_map, 1, _RET_IP_);
+			rwsem_release(&sem->dep_map, _RET_IP_);
 			return 0;
 		}
 	}
@@ -322,7 +322,7 @@ static int __ldsem_down_write_nested(struct ld_semaphore *sem,
 	if ((count & LDSEM_ACTIVE_MASK) != LDSEM_ACTIVE_BIAS) {
 		lock_contended(&sem->dep_map, _RET_IP_);
 		if (!down_write_failed(sem, count, timeout)) {
-			rwsem_release(&sem->dep_map, 1, _RET_IP_);
+			rwsem_release(&sem->dep_map, _RET_IP_);
 			return 0;
 		}
 	}
@@ -390,7 +390,7 @@ void ldsem_up_read(struct ld_semaphore *sem)
 {
 	long count;
 
-	rwsem_release(&sem->dep_map, 1, _RET_IP_);
+	rwsem_release(&sem->dep_map, _RET_IP_);
 
 	count = atomic_long_add_return(-LDSEM_READ_BIAS, &sem->count);
 	if (count < 0 && (count & LDSEM_ACTIVE_MASK) == 0)
@@ -404,7 +404,7 @@ void ldsem_up_write(struct ld_semaphore *sem)
 {
 	long count;
 
-	rwsem_release(&sem->dep_map, 1, _RET_IP_);
+	rwsem_release(&sem->dep_map, _RET_IP_);
 
 	count = atomic_long_add_return(-LDSEM_WRITE_BIAS, &sem->count);
 	if (count < 0)
diff --git a/drivers/usb/gadget/function/u_audio.c b/drivers/usb/gadget/function/u_audio.c
index 56906d15fb55..7ec6a996af26 100644
--- a/drivers/usb/gadget/function/u_audio.c
+++ b/drivers/usb/gadget/function/u_audio.c
@@ -585,7 +585,7 @@ int g_audio_setup(struct g_audio *g_audio, const char *pcm_name,
 	sprintf(card->longname, "%s %i", card_name, card->dev->id);
 
 	snd_pcm_lib_preallocate_pages_for_all(pcm, SNDRV_DMA_TYPE_CONTINUOUS,
-		snd_dma_continuous_data(GFP_KERNEL), 0, BUFF_SIZE_MAX);
+					      NULL, 0, BUFF_SIZE_MAX);
 
 	err = snd_card_register(card);
 
diff --git a/fs/afs/vl_list.c b/fs/afs/vl_list.c
index 21eb0c0be912..8fea54eba0c2 100644
--- a/fs/afs/vl_list.c
+++ b/fs/afs/vl_list.c
@@ -279,8 +279,8 @@ struct afs_vlserver_list *afs_extract_vlserver_list(struct afs_cell *cell,
 			struct afs_addr_list *old = addrs;
 
 			write_lock(&server->lock);
-			rcu_swap_protected(server->addresses, old,
-					   lockdep_is_held(&server->lock));
+			old = rcu_replace_pointer(server->addresses, old,
+						  lockdep_is_held(&server->lock));
 			write_unlock(&server->lock);
 			afs_put_addrlist(old);
 		}
diff --git a/fs/dcache.c b/fs/dcache.c
index e88cf0554e65..f7931b682a0d 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -1319,7 +1319,7 @@ resume:
 
 		if (!list_empty(&dentry->d_subdirs)) {
 			spin_unlock(&this_parent->d_lock);
-			spin_release(&dentry->d_lock.dep_map, 1, _RET_IP_);
+			spin_release(&dentry->d_lock.dep_map, _RET_IP_);
 			this_parent = dentry;
 			spin_acquire(&this_parent->d_lock.dep_map, 0, 1, _RET_IP_);
 			goto repeat;
diff --git a/fs/exec.c b/fs/exec.c
index 555e93c7dec8..c27231234764 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -1015,7 +1015,7 @@ static int exec_mmap(struct mm_struct *mm)
 	/* Notify parent that we're no longer interested in the old VM */
 	tsk = current;
 	old_mm = current->mm;
-	mm_release(tsk, old_mm);
+	exec_mm_release(tsk, old_mm);
 
 	if (old_mm) {
 		sync_mm_rss(old_mm);
diff --git a/fs/file.c b/fs/file.c
index b241ea7f1aa4..3da91a112bab 100644
--- a/fs/file.c
+++ b/fs/file.c
@@ -795,7 +795,7 @@ unsigned long __fdget_pos(unsigned int fd)
 	unsigned long v = __fdget(fd);
 	struct file *file = (struct file *)(v & ~3);
 
-	if (file && !(file->f_mode & FMODE_STREAM)) {
+	if (file && (file->f_mode & FMODE_ATOMIC_POS)) {
 		if (file_count(file) > 1) {
 			v |= FDPUT_POS_UNLOCK;
 			mutex_lock(&file->f_pos_lock);
diff --git a/fs/jbd2/transaction.c b/fs/jbd2/transaction.c
index bee8498d7792..b25ebdcabfa3 100644
--- a/fs/jbd2/transaction.c
+++ b/fs/jbd2/transaction.c
@@ -713,7 +713,7 @@ int jbd2__journal_restart(handle_t *handle, int nblocks, gfp_t gfp_mask)
 	if (need_to_start)
 		jbd2_log_start_commit(journal, tid);
 
-	rwsem_release(&journal->j_trans_commit_map, 1, _THIS_IP_);
+	rwsem_release(&journal->j_trans_commit_map, _THIS_IP_);
 	handle->h_buffer_credits = nblocks;
 	/*
 	 * Restore the original nofs context because the journal restart
@@ -1848,7 +1848,7 @@ int jbd2_journal_stop(handle_t *handle)
 			wake_up(&journal->j_wait_transaction_locked);
 	}
 
-	rwsem_release(&journal->j_trans_commit_map, 1, _THIS_IP_);
+	rwsem_release(&journal->j_trans_commit_map, _THIS_IP_);
 
 	if (wait_for_commit)
 		err = jbd2_log_wait_commit(journal, tid);
diff --git a/fs/kernfs/dir.c b/fs/kernfs/dir.c
index b2d9f79c4a7c..9d96e6871e1a 100644
--- a/fs/kernfs/dir.c
+++ b/fs/kernfs/dir.c
@@ -438,7 +438,7 @@ void kernfs_put_active(struct kernfs_node *kn)
 		return;
 
 	if (kernfs_lockdep(kn))
-		rwsem_release(&kn->dep_map, 1, _RET_IP_);
+		rwsem_release(&kn->dep_map, _RET_IP_);
 	v = atomic_dec_return(&kn->active);
 	if (likely(v != KN_DEACTIVATED_BIAS))
 		return;
@@ -476,7 +476,7 @@ static void kernfs_drain(struct kernfs_node *kn)
 
 	if (kernfs_lockdep(kn)) {
 		lock_acquired(&kn->dep_map, _RET_IP_);
-		rwsem_release(&kn->dep_map, 1, _RET_IP_);
+		rwsem_release(&kn->dep_map, _RET_IP_);
 	}
 
 	kernfs_drain_open_files(kn);
diff --git a/fs/ocfs2/dlmglue.c b/fs/ocfs2/dlmglue.c
index 6e774c5ea13b..1c4c51f3df60 100644
--- a/fs/ocfs2/dlmglue.c
+++ b/fs/ocfs2/dlmglue.c
@@ -1687,7 +1687,7 @@ static void __ocfs2_cluster_unlock(struct ocfs2_super *osb,
 	spin_unlock_irqrestore(&lockres->l_lock, flags);
 #ifdef CONFIG_DEBUG_LOCK_ALLOC
 	if (lockres->l_lockdep_map.key != NULL)
-		rwsem_release(&lockres->l_lockdep_map, 1, caller_ip);
+		rwsem_release(&lockres->l_lockdep_map, caller_ip);
 #endif
 }
 
diff --git a/fs/open.c b/fs/open.c
index 5c68282ea79e..b62f5c0923a8 100644
--- a/fs/open.c
+++ b/fs/open.c
@@ -771,6 +771,10 @@ static int do_dentry_open(struct file *f,
 		f->f_mode |= FMODE_WRITER;
 	}
 
+	/* POSIX.1-2008/SUSv4 Section XSI 2.9.7 */
+	if (S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode))
+		f->f_mode |= FMODE_ATOMIC_POS;
+
 	f->f_op = fops_get(inode->i_fop);
 	if (WARN_ON(!f->f_op)) {
 		error = -ENODEV;
@@ -1252,7 +1256,7 @@ EXPORT_SYMBOL(nonseekable_open);
  */
 int stream_open(struct inode *inode, struct file *filp)
 {
-	filp->f_mode &= ~(FMODE_LSEEK | FMODE_PREAD | FMODE_PWRITE);
+	filp->f_mode &= ~(FMODE_LSEEK | FMODE_PREAD | FMODE_PWRITE | FMODE_ATOMIC_POS);
 	filp->f_mode |= FMODE_STREAM;
 	return 0;
 }
diff --git a/fs/proc/stat.c b/fs/proc/stat.c
index 80c305f206bb..37bdbec5b402 100644
--- a/fs/proc/stat.c
+++ b/fs/proc/stat.c
@@ -120,20 +120,23 @@ static int show_stat(struct seq_file *p, void *v)
 	getboottime64(&boottime);
 
 	for_each_possible_cpu(i) {
-		struct kernel_cpustat *kcs = &kcpustat_cpu(i);
-
-		user += kcs->cpustat[CPUTIME_USER];
-		nice += kcs->cpustat[CPUTIME_NICE];
-		system += kcs->cpustat[CPUTIME_SYSTEM];
-		idle += get_idle_time(kcs, i);
-		iowait += get_iowait_time(kcs, i);
-		irq += kcs->cpustat[CPUTIME_IRQ];
-		softirq += kcs->cpustat[CPUTIME_SOFTIRQ];
-		steal += kcs->cpustat[CPUTIME_STEAL];
-		guest += kcs->cpustat[CPUTIME_GUEST];
-		guest_nice += kcs->cpustat[CPUTIME_GUEST_NICE];
-		sum += kstat_cpu_irqs_sum(i);
-		sum += arch_irq_stat_cpu(i);
+		struct kernel_cpustat kcpustat;
+		u64 *cpustat = kcpustat.cpustat;
+
+		kcpustat_cpu_fetch(&kcpustat, i);
+
+		user		+= cpustat[CPUTIME_USER];
+		nice		+= cpustat[CPUTIME_NICE];
+		system		+= cpustat[CPUTIME_SYSTEM];
+		idle		+= get_idle_time(&kcpustat, i);
+		iowait		+= get_iowait_time(&kcpustat, i);
+		irq		+= cpustat[CPUTIME_IRQ];
+		softirq		+= cpustat[CPUTIME_SOFTIRQ];
+		steal		+= cpustat[CPUTIME_STEAL];
+		guest		+= cpustat[CPUTIME_GUEST];
+		guest_nice	+= cpustat[CPUTIME_USER];
+		sum		+= kstat_cpu_irqs_sum(i);
+		sum		+= arch_irq_stat_cpu(i);
 
 		for (j = 0; j < NR_SOFTIRQS; j++) {
 			unsigned int softirq_stat = kstat_softirqs_cpu(j, i);
@@ -157,19 +160,22 @@ static int show_stat(struct seq_file *p, void *v)
 	seq_putc(p, '\n');
 
 	for_each_online_cpu(i) {
-		struct kernel_cpustat *kcs = &kcpustat_cpu(i);
+		struct kernel_cpustat kcpustat;
+		u64 *cpustat = kcpustat.cpustat;
+
+		kcpustat_cpu_fetch(&kcpustat, i);
 
 		/* Copy values here to work around gcc-2.95.3, gcc-2.96 */
-		user = kcs->cpustat[CPUTIME_USER];
-		nice = kcs->cpustat[CPUTIME_NICE];
-		system = kcs->cpustat[CPUTIME_SYSTEM];
-		idle = get_idle_time(kcs, i);
-		iowait = get_iowait_time(kcs, i);
-		irq = kcs->cpustat[CPUTIME_IRQ];
-		softirq = kcs->cpustat[CPUTIME_SOFTIRQ];
-		steal = kcs->cpustat[CPUTIME_STEAL];
-		guest = kcs->cpustat[CPUTIME_GUEST];
-		guest_nice = kcs->cpustat[CPUTIME_GUEST_NICE];
+		user		= cpustat[CPUTIME_USER];
+		nice		= cpustat[CPUTIME_NICE];
+		system		= cpustat[CPUTIME_SYSTEM];
+		idle		= get_idle_time(&kcpustat, i);
+		iowait		= get_iowait_time(&kcpustat, i);
+		irq		= cpustat[CPUTIME_IRQ];
+		softirq		= cpustat[CPUTIME_SOFTIRQ];
+		steal		= cpustat[CPUTIME_STEAL];
+		guest		= cpustat[CPUTIME_GUEST];
+		guest_nice	= cpustat[CPUTIME_USER];
 		seq_printf(p, "cpu%d", i);
 		seq_put_decimal_ull(p, " ", nsec_to_clock_t(user));
 		seq_put_decimal_ull(p, " ", nsec_to_clock_t(nice));
diff --git a/include/acpi/acpi_bus.h b/include/acpi/acpi_bus.h
index 175f7b40c585..0c23fd0548d1 100644
--- a/include/acpi/acpi_bus.h
+++ b/include/acpi/acpi_bus.h
@@ -78,9 +78,6 @@ acpi_evaluate_dsm_typed(acpi_handle handle, const guid_t *guid, u64 rev,
 bool acpi_dev_found(const char *hid);
 bool acpi_dev_present(const char *hid, const char *uid, s64 hrv);
 
-struct acpi_device *
-acpi_dev_get_first_match_dev(const char *hid, const char *uid, s64 hrv);
-
 #ifdef CONFIG_ACPI
 
 #include <linux/proc_fs.h>
@@ -683,6 +680,11 @@ static inline bool acpi_device_can_poweroff(struct acpi_device *adev)
 		adev->power.states[ACPI_STATE_D3_HOT].flags.explicit_set);
 }
 
+bool acpi_dev_hid_uid_match(struct acpi_device *adev, const char *hid2, const char *uid2);
+
+struct acpi_device *
+acpi_dev_get_first_match_dev(const char *hid, const char *uid, s64 hrv);
+
 static inline void acpi_dev_put(struct acpi_device *adev)
 {
 	put_device(&adev->dev);
diff --git a/include/acpi/acpixf.h b/include/acpi/acpixf.h
index e5e041413581..18790b9e16b5 100644
--- a/include/acpi/acpixf.h
+++ b/include/acpi/acpixf.h
@@ -12,7 +12,7 @@
 
 /* Current ACPICA subsystem version in YYYYMMDD format */
 
-#define ACPI_CA_VERSION                 0x20190816
+#define ACPI_CA_VERSION                 0x20191018
 
 #include <acpi/acconfig.h>
 #include <acpi/actypes.h>
@@ -458,7 +458,11 @@ ACPI_EXTERNAL_RETURN_STATUS(acpi_status ACPI_INIT_FUNCTION
 					       u8 physical))
 
 ACPI_EXTERNAL_RETURN_STATUS(acpi_status
-			    acpi_load_table(struct acpi_table_header *table))
+			    acpi_load_table(struct acpi_table_header *table,
+					    u32 *table_idx))
+
+ACPI_EXTERNAL_RETURN_STATUS(acpi_status
+			    acpi_unload_table(u32 table_index))
 
 ACPI_EXTERNAL_RETURN_STATUS(acpi_status
 			    acpi_unload_parent_table(acpi_handle object))
diff --git a/include/acpi/button.h b/include/acpi/button.h
index 3a2b8535dec6..340da7784cc8 100644
--- a/include/acpi/button.h
+++ b/include/acpi/button.h
@@ -2,21 +2,9 @@
 #ifndef ACPI_BUTTON_H
 #define ACPI_BUTTON_H
 
-#include <linux/notifier.h>
-
 #if IS_ENABLED(CONFIG_ACPI_BUTTON)
-extern int acpi_lid_notifier_register(struct notifier_block *nb);
-extern int acpi_lid_notifier_unregister(struct notifier_block *nb);
 extern int acpi_lid_open(void);
 #else
-static inline int acpi_lid_notifier_register(struct notifier_block *nb)
-{
-	return 0;
-}
-static inline int acpi_lid_notifier_unregister(struct notifier_block *nb)
-{
-	return 0;
-}
 static inline int acpi_lid_open(void)
 {
 	return 1;
diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h
index a9c4e4721434..63cedc3c0c77 100644
--- a/include/asm-generic/vmlinux.lds.h
+++ b/include/asm-generic/vmlinux.lds.h
@@ -23,12 +23,11 @@
  *	_etext = .;
  *
  *      _sdata = .;
- *	RO_DATA_SECTION(PAGE_SIZE)
- *	RW_DATA_SECTION(...)
+ *	RO_DATA(PAGE_SIZE)
+ *	RW_DATA(...)
  *	_edata = .;
  *
  *	EXCEPTION_TABLE(...)
- *	NOTES
  *
  *	BSS_SECTION(0, 0, 0)
  *	_end = .;
@@ -54,6 +53,33 @@
 #define LOAD_OFFSET 0
 #endif
 
+/*
+ * Only some architectures want to have the .notes segment visible in
+ * a separate PT_NOTE ELF Program Header. When this happens, it needs
+ * to be visible in both the kernel text's PT_LOAD and the PT_NOTE
+ * Program Headers. In this case, though, the PT_LOAD needs to be made
+ * the default again so that all the following sections don't also end
+ * up in the PT_NOTE Program Header.
+ */
+#ifdef EMITS_PT_NOTE
+#define NOTES_HEADERS		:text :note
+#define NOTES_HEADERS_RESTORE	__restore_ph : { *(.__restore_ph) } :text
+#else
+#define NOTES_HEADERS
+#define NOTES_HEADERS_RESTORE
+#endif
+
+/*
+ * Some architectures have non-executable read-only exception tables.
+ * They can be added to the RO_DATA segment by specifying their desired
+ * alignment.
+ */
+#ifdef RO_EXCEPTION_TABLE_ALIGN
+#define RO_EXCEPTION_TABLE	EXCEPTION_TABLE(RO_EXCEPTION_TABLE_ALIGN)
+#else
+#define RO_EXCEPTION_TABLE
+#endif
+
 /* Align . to a 8 byte boundary equals to maximum function alignment. */
 #define ALIGN_FUNCTION()  . = ALIGN(8)
 
@@ -348,7 +374,7 @@
 /*
  * Read only Data
  */
-#define RO_DATA_SECTION(align)						\
+#define RO_DATA(align)							\
 	. = ALIGN((align));						\
 	.rodata           : AT(ADDR(.rodata) - LOAD_OFFSET) {		\
 		__start_rodata = .;					\
@@ -496,15 +522,13 @@
 		__start___modver = .;					\
 		KEEP(*(__modver))					\
 		__stop___modver = .;					\
-		. = ALIGN((align));					\
-		__end_rodata = .;					\
 	}								\
-	. = ALIGN((align));
-
-/* RODATA & RO_DATA provided for backward compatibility.
- * All archs are supposed to use RO_DATA() */
-#define RODATA          RO_DATA_SECTION(4096)
-#define RO_DATA(align)  RO_DATA_SECTION(align)
+									\
+	RO_EXCEPTION_TABLE						\
+	NOTES								\
+									\
+	. = ALIGN((align));						\
+	__end_rodata = .;
 
 /*
  * .text section. Map to function alignment to avoid address changes
@@ -790,7 +814,8 @@
 		__start_notes = .;					\
 		KEEP(*(.note.*))					\
 		__stop_notes = .;					\
-	}
+	} NOTES_HEADERS							\
+	NOTES_HEADERS_RESTORE
 
 #define INIT_SETUP(initsetup_align)					\
 		. = ALIGN(initsetup_align);				\
@@ -962,7 +987,7 @@
  * matches the requirement of PAGE_ALIGNED_DATA.
  *
  * use 0 as page_align if page_aligned data is not used */
-#define RW_DATA_SECTION(cacheline, pagealigned, inittask)		\
+#define RW_DATA(cacheline, pagealigned, inittask)			\
 	. = ALIGN(PAGE_SIZE);						\
 	.data : AT(ADDR(.data) - LOAD_OFFSET) {				\
 		INIT_TASK_DATA(inittask)				\
diff --git a/include/clocksource/hyperv_timer.h b/include/clocksource/hyperv_timer.h
index 422f5e5237be..553e539469f0 100644
--- a/include/clocksource/hyperv_timer.h
+++ b/include/clocksource/hyperv_timer.h
@@ -21,10 +21,11 @@
 #define HV_MIN_DELTA_TICKS 1
 
 /* Routines called by the VMbus driver */
-extern int hv_stimer_alloc(int sint);
+extern int hv_stimer_alloc(void);
 extern void hv_stimer_free(void);
-extern void hv_stimer_init(unsigned int cpu);
-extern void hv_stimer_cleanup(unsigned int cpu);
+extern int hv_stimer_cleanup(unsigned int cpu);
+extern void hv_stimer_legacy_init(unsigned int cpu, int sint);
+extern void hv_stimer_legacy_cleanup(unsigned int cpu);
 extern void hv_stimer_global_cleanup(void);
 extern void hv_stimer0_isr(void);
 
diff --git a/include/drm/bridge/dw_hdmi.h b/include/drm/bridge/dw_hdmi.h
index cf528c289857..9a0c8381a069 100644
--- a/include/drm/bridge/dw_hdmi.h
+++ b/include/drm/bridge/dw_hdmi.h
@@ -6,6 +6,8 @@
 #ifndef __DW_HDMI__
 #define __DW_HDMI__
 
+#include <sound/hdmi-codec.h>
+
 struct drm_connector;
 struct drm_display_mode;
 struct drm_encoder;
@@ -154,6 +156,8 @@ void dw_hdmi_resume(struct dw_hdmi *hdmi);
 
 void dw_hdmi_setup_rx_sense(struct dw_hdmi *hdmi, bool hpd, bool rx_sense);
 
+int dw_hdmi_set_plugged_cb(struct dw_hdmi *hdmi, hdmi_codec_plugged_cb fn,
+			   struct device *codec_dev);
 void dw_hdmi_set_sample_rate(struct dw_hdmi *hdmi, unsigned int rate);
 void dw_hdmi_set_channel_count(struct dw_hdmi *hdmi, unsigned int cnt);
 void dw_hdmi_set_channel_allocation(struct dw_hdmi *hdmi, unsigned int ca);
diff --git a/include/dt-bindings/pmu/exynos_ppmu.h b/include/dt-bindings/pmu/exynos_ppmu.h
new file mode 100644
index 000000000000..8724abe130f3
--- /dev/null
+++ b/include/dt-bindings/pmu/exynos_ppmu.h
@@ -0,0 +1,25 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Samsung Exynos PPMU event types for counting in regs
+ *
+ * Copyright (c) 2019, Samsung Electronics
+ * Author: Lukasz Luba <l.luba@partner.samsung.com>
+ */
+
+#ifndef __DT_BINDINGS_PMU_EXYNOS_PPMU_H
+#define __DT_BINDINGS_PMU_EXYNOS_PPMU_H
+
+#define PPMU_RO_BUSY_CYCLE_CNT		0x0
+#define PPMU_WO_BUSY_CYCLE_CNT		0x1
+#define PPMU_RW_BUSY_CYCLE_CNT		0x2
+#define PPMU_RO_REQUEST_CNT		0x3
+#define PPMU_WO_REQUEST_CNT		0x4
+#define PPMU_RO_DATA_CNT		0x5
+#define PPMU_WO_DATA_CNT		0x6
+#define PPMU_RO_LATENCY			0x12
+#define PPMU_WO_LATENCY			0x16
+#define PPMU_V2_RO_DATA_CNT		0x4
+#define PPMU_V2_WO_DATA_CNT		0x5
+#define PPMU_V2_EVT3_RW_DATA_CNT	0x22
+
+#endif
diff --git a/include/dt-bindings/sound/samsung-i2s.h b/include/dt-bindings/sound/samsung-i2s.h
index 77545f14c379..250de0d6c734 100644
--- a/include/dt-bindings/sound/samsung-i2s.h
+++ b/include/dt-bindings/sound/samsung-i2s.h
@@ -2,8 +2,14 @@
 #ifndef _DT_BINDINGS_SAMSUNG_I2S_H
 #define _DT_BINDINGS_SAMSUNG_I2S_H
 
-#define CLK_I2S_CDCLK		0
-#define CLK_I2S_RCLK_SRC	1
-#define CLK_I2S_RCLK_PSR	2
+#define CLK_I2S_CDCLK		0 /* the CDCLK (CODECLKO) gate clock */
+
+#define CLK_I2S_RCLK_SRC	1 /* the RCLKSRC mux clock (corresponding to
+				   * RCLKSRC bit in IISMOD register)
+				   */
+
+#define CLK_I2S_RCLK_PSR	2 /* the RCLK prescaler divider clock
+				   * (corresponding to the IISPSR register)
+				   */
 
 #endif /* _DT_BINDINGS_SAMSUNG_I2S_H */
diff --git a/include/linux/acpi.h b/include/linux/acpi.h
index 8b4e516bac00..0f37a7d5fa77 100644
--- a/include/linux/acpi.h
+++ b/include/linux/acpi.h
@@ -678,6 +678,14 @@ static inline bool acpi_dev_present(const char *hid, const char *uid, s64 hrv)
 	return false;
 }
 
+struct acpi_device;
+
+static inline bool
+acpi_dev_hid_uid_match(struct acpi_device *adev, const char *hid2, const char *uid2)
+{
+	return false;
+}
+
 static inline struct acpi_device *
 acpi_dev_get_first_match_dev(const char *hid, const char *uid, s64 hrv)
 {
diff --git a/include/linux/compat.h b/include/linux/compat.h
index 16dafd9f4b86..c4c389c7e1b4 100644
--- a/include/linux/compat.h
+++ b/include/linux/compat.h
@@ -410,8 +410,6 @@ struct compat_kexec_segment;
 struct compat_mq_attr;
 struct compat_msgbuf;
 
-extern void compat_exit_robust_list(struct task_struct *curr);
-
 #define BITS_PER_COMPAT_LONG    (8*sizeof(compat_long_t))
 
 #define BITS_TO_COMPAT_LONGS(bits) DIV_ROUND_UP(bits, BITS_PER_COMPAT_LONG)
diff --git a/include/linux/context_tracking.h b/include/linux/context_tracking.h
index d05609ad329d..64ec82851aa3 100644
--- a/include/linux/context_tracking.h
+++ b/include/linux/context_tracking.h
@@ -22,26 +22,26 @@ extern void context_tracking_user_exit(void);
 
 static inline void user_enter(void)
 {
-	if (context_tracking_is_enabled())
+	if (context_tracking_enabled())
 		context_tracking_enter(CONTEXT_USER);
 
 }
 static inline void user_exit(void)
 {
-	if (context_tracking_is_enabled())
+	if (context_tracking_enabled())
 		context_tracking_exit(CONTEXT_USER);
 }
 
 /* Called with interrupts disabled.  */
 static inline void user_enter_irqoff(void)
 {
-	if (context_tracking_is_enabled())
+	if (context_tracking_enabled())
 		__context_tracking_enter(CONTEXT_USER);
 
 }
 static inline void user_exit_irqoff(void)
 {
-	if (context_tracking_is_enabled())
+	if (context_tracking_enabled())
 		__context_tracking_exit(CONTEXT_USER);
 }
 
@@ -49,7 +49,7 @@ static inline enum ctx_state exception_enter(void)
 {
 	enum ctx_state prev_ctx;
 
-	if (!context_tracking_is_enabled())
+	if (!context_tracking_enabled())
 		return 0;
 
 	prev_ctx = this_cpu_read(context_tracking.state);
@@ -61,7 +61,7 @@ static inline enum ctx_state exception_enter(void)
 
 static inline void exception_exit(enum ctx_state prev_ctx)
 {
-	if (context_tracking_is_enabled()) {
+	if (context_tracking_enabled()) {
 		if (prev_ctx != CONTEXT_KERNEL)
 			context_tracking_enter(prev_ctx);
 	}
@@ -77,7 +77,7 @@ static inline void exception_exit(enum ctx_state prev_ctx)
  */
 static inline enum ctx_state ct_state(void)
 {
-	return context_tracking_is_enabled() ?
+	return context_tracking_enabled() ?
 		this_cpu_read(context_tracking.state) : CONTEXT_DISABLED;
 }
 #else
@@ -90,7 +90,7 @@ static inline void exception_exit(enum ctx_state prev_ctx) { }
 static inline enum ctx_state ct_state(void) { return CONTEXT_DISABLED; }
 #endif /* !CONFIG_CONTEXT_TRACKING */
 
-#define CT_WARN_ON(cond) WARN_ON(context_tracking_is_enabled() && (cond))
+#define CT_WARN_ON(cond) WARN_ON(context_tracking_enabled() && (cond))
 
 #ifdef CONFIG_CONTEXT_TRACKING_FORCE
 extern void context_tracking_init(void);
@@ -103,12 +103,12 @@ static inline void context_tracking_init(void) { }
 /* must be called with irqs disabled */
 static inline void guest_enter_irqoff(void)
 {
-	if (vtime_accounting_cpu_enabled())
+	if (vtime_accounting_enabled_this_cpu())
 		vtime_guest_enter(current);
 	else
 		current->flags |= PF_VCPU;
 
-	if (context_tracking_is_enabled())
+	if (context_tracking_enabled())
 		__context_tracking_enter(CONTEXT_GUEST);
 
 	/* KVM does not hold any references to rcu protected data when it
@@ -118,16 +118,16 @@ static inline void guest_enter_irqoff(void)
 	 * one time slice). Lets treat guest mode as quiescent state, just like
 	 * we do with user-mode execution.
 	 */
-	if (!context_tracking_cpu_is_enabled())
+	if (!context_tracking_enabled_this_cpu())
 		rcu_virt_note_context_switch(smp_processor_id());
 }
 
 static inline void guest_exit_irqoff(void)
 {
-	if (context_tracking_is_enabled())
+	if (context_tracking_enabled())
 		__context_tracking_exit(CONTEXT_GUEST);
 
-	if (vtime_accounting_cpu_enabled())
+	if (vtime_accounting_enabled_this_cpu())
 		vtime_guest_exit(current);
 	else
 		current->flags &= ~PF_VCPU;
@@ -141,7 +141,7 @@ static inline void guest_enter_irqoff(void)
 	 * to assume that it's the stime pending cputime
 	 * to flush.
 	 */
-	vtime_account_system(current);
+	vtime_account_kernel(current);
 	current->flags |= PF_VCPU;
 	rcu_virt_note_context_switch(smp_processor_id());
 }
@@ -149,7 +149,7 @@ static inline void guest_enter_irqoff(void)
 static inline void guest_exit_irqoff(void)
 {
 	/* Flush the guest cputime we spent on the guest */
-	vtime_account_system(current);
+	vtime_account_kernel(current);
 	current->flags &= ~PF_VCPU;
 }
 #endif /* CONFIG_VIRT_CPU_ACCOUNTING_GEN */
diff --git a/include/linux/context_tracking_state.h b/include/linux/context_tracking_state.h
index f128dc3be0df..e7fe6678b7ad 100644
--- a/include/linux/context_tracking_state.h
+++ b/include/linux/context_tracking_state.h
@@ -23,17 +23,22 @@ struct context_tracking {
 };
 
 #ifdef CONFIG_CONTEXT_TRACKING
-extern struct static_key_false context_tracking_enabled;
+extern struct static_key_false context_tracking_key;
 DECLARE_PER_CPU(struct context_tracking, context_tracking);
 
-static inline bool context_tracking_is_enabled(void)
+static inline bool context_tracking_enabled(void)
 {
-	return static_branch_unlikely(&context_tracking_enabled);
+	return static_branch_unlikely(&context_tracking_key);
 }
 
-static inline bool context_tracking_cpu_is_enabled(void)
+static inline bool context_tracking_enabled_cpu(int cpu)
 {
-	return __this_cpu_read(context_tracking.active);
+	return context_tracking_enabled() && per_cpu(context_tracking.active, cpu);
+}
+
+static inline bool context_tracking_enabled_this_cpu(void)
+{
+	return context_tracking_enabled() && __this_cpu_read(context_tracking.active);
 }
 
 static inline bool context_tracking_in_user(void)
@@ -42,9 +47,9 @@ static inline bool context_tracking_in_user(void)
 }
 #else
 static inline bool context_tracking_in_user(void) { return false; }
-static inline bool context_tracking_active(void) { return false; }
-static inline bool context_tracking_is_enabled(void) { return false; }
-static inline bool context_tracking_cpu_is_enabled(void) { return false; }
+static inline bool context_tracking_enabled(void) { return false; }
+static inline bool context_tracking_enabled_cpu(int cpu) { return false; }
+static inline bool context_tracking_enabled_this_cpu(void) { return false; }
 #endif /* CONFIG_CONTEXT_TRACKING */
 
 #endif
diff --git a/include/linux/cpu.h b/include/linux/cpu.h
index bc6c879bd110..1ca2baf817ed 100644
--- a/include/linux/cpu.h
+++ b/include/linux/cpu.h
@@ -184,7 +184,12 @@ void arch_cpu_idle_dead(void);
 int cpu_report_state(int cpu);
 int cpu_check_up_prepare(int cpu);
 void cpu_set_state_online(int cpu);
-void play_idle(unsigned long duration_us);
+void play_idle_precise(u64 duration_ns, u64 latency_ns);
+
+static inline void play_idle(unsigned long duration_us)
+{
+	play_idle_precise(duration_us * NSEC_PER_USEC, U64_MAX);
+}
 
 #ifdef CONFIG_HOTPLUG_CPU
 bool cpu_wait_death(unsigned int cpu, int seconds);
diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h
index 89d75edb5750..e51ee772b9f5 100644
--- a/include/linux/cpuhotplug.h
+++ b/include/linux/cpuhotplug.h
@@ -129,6 +129,7 @@ enum cpuhp_state {
 	CPUHP_AP_ARC_TIMER_STARTING,
 	CPUHP_AP_RISCV_TIMER_STARTING,
 	CPUHP_AP_CSKY_TIMER_STARTING,
+	CPUHP_AP_HYPERV_TIMER_STARTING,
 	CPUHP_AP_KVM_STARTING,
 	CPUHP_AP_KVM_ARM_VGIC_INIT_STARTING,
 	CPUHP_AP_KVM_ARM_VGIC_STARTING,
diff --git a/include/linux/cpuidle.h b/include/linux/cpuidle.h
index 4b6b5bea8f79..2dbe46b7c213 100644
--- a/include/linux/cpuidle.h
+++ b/include/linux/cpuidle.h
@@ -29,10 +29,13 @@ struct cpuidle_driver;
  * CPUIDLE DEVICE INTERFACE *
  ****************************/
 
+#define CPUIDLE_STATE_DISABLED_BY_USER		BIT(0)
+#define CPUIDLE_STATE_DISABLED_BY_DRIVER	BIT(1)
+
 struct cpuidle_state_usage {
 	unsigned long long	disable;
 	unsigned long long	usage;
-	unsigned long long	time; /* in US */
+	u64			time_ns;
 	unsigned long long	above; /* Number of times it's been too deep */
 	unsigned long long	below; /* Number of times it's been too shallow */
 #ifdef CONFIG_SUSPEND
@@ -45,6 +48,8 @@ struct cpuidle_state {
 	char		name[CPUIDLE_NAME_LEN];
 	char		desc[CPUIDLE_DESC_LEN];
 
+	u64		exit_latency_ns;
+	u64		target_residency_ns;
 	unsigned int	flags;
 	unsigned int	exit_latency; /* in US */
 	int		power_usage; /* in mW */
@@ -80,14 +85,14 @@ struct cpuidle_driver_kobj;
 struct cpuidle_device {
 	unsigned int		registered:1;
 	unsigned int		enabled:1;
-	unsigned int		use_deepest_state:1;
 	unsigned int		poll_time_limit:1;
 	unsigned int		cpu;
 	ktime_t			next_hrtimer;
 
 	int			last_state_idx;
-	int			last_residency;
+	u64			last_residency_ns;
 	u64			poll_limit_ns;
+	u64			forced_idle_latency_limit_ns;
 	struct cpuidle_state_usage	states_usage[CPUIDLE_STATE_MAX];
 	struct cpuidle_state_kobj *kobjs[CPUIDLE_STATE_MAX];
 	struct cpuidle_driver_kobj *kobj_driver;
@@ -144,6 +149,8 @@ extern int cpuidle_register_driver(struct cpuidle_driver *drv);
 extern struct cpuidle_driver *cpuidle_get_driver(void);
 extern struct cpuidle_driver *cpuidle_driver_ref(void);
 extern void cpuidle_driver_unref(void);
+extern void cpuidle_driver_state_disabled(struct cpuidle_driver *drv, int idx,
+					bool disable);
 extern void cpuidle_unregister_driver(struct cpuidle_driver *drv);
 extern int cpuidle_register_device(struct cpuidle_device *dev);
 extern void cpuidle_unregister_device(struct cpuidle_device *dev);
@@ -181,6 +188,8 @@ static inline int cpuidle_register_driver(struct cpuidle_driver *drv)
 static inline struct cpuidle_driver *cpuidle_get_driver(void) {return NULL; }
 static inline struct cpuidle_driver *cpuidle_driver_ref(void) {return NULL; }
 static inline void cpuidle_driver_unref(void) {}
+static inline void cpuidle_driver_state_disabled(struct cpuidle_driver *drv,
+					       int idx, bool disable) { }
 static inline void cpuidle_unregister_driver(struct cpuidle_driver *drv) { }
 static inline int cpuidle_register_device(struct cpuidle_device *dev)
 {return -ENODEV; }
@@ -204,18 +213,20 @@ static inline struct cpuidle_device *cpuidle_get_device(void) {return NULL; }
 
 #ifdef CONFIG_CPU_IDLE
 extern int cpuidle_find_deepest_state(struct cpuidle_driver *drv,
-				      struct cpuidle_device *dev);
+				      struct cpuidle_device *dev,
+				      u64 latency_limit_ns);
 extern int cpuidle_enter_s2idle(struct cpuidle_driver *drv,
 				struct cpuidle_device *dev);
-extern void cpuidle_use_deepest_state(bool enable);
+extern void cpuidle_use_deepest_state(u64 latency_limit_ns);
 #else
 static inline int cpuidle_find_deepest_state(struct cpuidle_driver *drv,
-					     struct cpuidle_device *dev)
+					     struct cpuidle_device *dev,
+					     u64 latency_limit_ns)
 {return -ENODEV; }
 static inline int cpuidle_enter_s2idle(struct cpuidle_driver *drv,
 				       struct cpuidle_device *dev)
 {return -ENODEV; }
-static inline void cpuidle_use_deepest_state(bool enable)
+static inline void cpuidle_use_deepest_state(u64 latency_limit_ns)
 {
 }
 #endif
@@ -260,7 +271,7 @@ struct cpuidle_governor {
 
 #ifdef CONFIG_CPU_IDLE
 extern int cpuidle_register_governor(struct cpuidle_governor *gov);
-extern int cpuidle_governor_latency_req(unsigned int cpu);
+extern s64 cpuidle_governor_latency_req(unsigned int cpu);
 #else
 static inline int cpuidle_register_governor(struct cpuidle_governor *gov)
 {return 0;}
diff --git a/include/linux/efi.h b/include/linux/efi.h
index d87acf62958e..99dfea595c8c 100644
--- a/include/linux/efi.h
+++ b/include/linux/efi.h
@@ -112,6 +112,7 @@ typedef	struct {
 #define EFI_MEMORY_MORE_RELIABLE \
 				((u64)0x0000000000010000ULL)	/* higher reliability */
 #define EFI_MEMORY_RO		((u64)0x0000000000020000ULL)	/* read-only */
+#define EFI_MEMORY_SP		((u64)0x0000000000040000ULL)	/* soft reserved */
 #define EFI_MEMORY_RUNTIME	((u64)0x8000000000000000ULL)	/* range requires runtime mapping */
 #define EFI_MEMORY_DESCRIPTOR_VERSION	1
 
@@ -1044,7 +1045,6 @@ extern void efi_enter_virtual_mode (void);	/* switch EFI to virtual mode, if pos
 extern efi_status_t efi_query_variable_store(u32 attributes,
 					     unsigned long size,
 					     bool nonblocking);
-extern void efi_find_mirror(void);
 #else
 
 static inline efi_status_t efi_query_variable_store(u32 attributes,
@@ -1202,6 +1202,7 @@ extern int __init efi_setup_pcdp_console(char *);
 #define EFI_DBG			8	/* Print additional debug info at runtime */
 #define EFI_NX_PE_DATA		9	/* Can runtime data regions be mapped non-executable? */
 #define EFI_MEM_ATTR		10	/* Did firmware publish an EFI_MEMORY_ATTRIBUTES table? */
+#define EFI_MEM_NO_SOFT_RESERVE	11	/* Is the kernel configured to ignore soft reservations? */
 
 #ifdef CONFIG_EFI
 /*
@@ -1212,6 +1213,14 @@ static inline bool efi_enabled(int feature)
 	return test_bit(feature, &efi.flags) != 0;
 }
 extern void efi_reboot(enum reboot_mode reboot_mode, const char *__unused);
+
+bool __pure __efi_soft_reserve_enabled(void);
+
+static inline bool __pure efi_soft_reserve_enabled(void)
+{
+	return IS_ENABLED(CONFIG_EFI_SOFT_RESERVE)
+		&& __efi_soft_reserve_enabled();
+}
 #else
 static inline bool efi_enabled(int feature)
 {
@@ -1225,6 +1234,11 @@ efi_capsule_pending(int *reset_type)
 {
 	return false;
 }
+
+static inline bool efi_soft_reserve_enabled(void)
+{
+	return false;
+}
 #endif
 
 extern int efi_status_to_err(efi_status_t status);
@@ -1645,6 +1659,8 @@ static inline void
 efi_enable_reset_attack_mitigation(efi_system_table_t *sys_table_arg) { }
 #endif
 
+efi_status_t efi_random_get_seed(efi_system_table_t *sys_table_arg);
+
 void efi_retrieve_tpm2_eventlog(efi_system_table_t *sys_table);
 
 /*
diff --git a/include/linux/fs.h b/include/linux/fs.h
index dde6dc4492a0..ae6c5c37f3ae 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -148,6 +148,8 @@ typedef int (dio_iodone_t)(struct kiocb *iocb, loff_t offset,
 /* File is opened with O_PATH; almost nothing can be done with it */
 #define FMODE_PATH		((__force fmode_t)0x4000)
 
+/* File needs atomic accesses to f_pos */
+#define FMODE_ATOMIC_POS	((__force fmode_t)0x8000)
 /* Write access to underlying fs */
 #define FMODE_WRITER		((__force fmode_t)0x10000)
 /* Has read method(s) */
diff --git a/include/linux/futex.h b/include/linux/futex.h
index ccaef0097785..5cc3fed27d4c 100644
--- a/include/linux/futex.h
+++ b/include/linux/futex.h
@@ -2,7 +2,9 @@
 #ifndef _LINUX_FUTEX_H
 #define _LINUX_FUTEX_H
 
+#include <linux/sched.h>
 #include <linux/ktime.h>
+
 #include <uapi/linux/futex.h>
 
 struct inode;
@@ -48,15 +50,35 @@ union futex_key {
 #define FUTEX_KEY_INIT (union futex_key) { .both = { .ptr = NULL } }
 
 #ifdef CONFIG_FUTEX
-extern void exit_robust_list(struct task_struct *curr);
+enum {
+	FUTEX_STATE_OK,
+	FUTEX_STATE_EXITING,
+	FUTEX_STATE_DEAD,
+};
 
-long do_futex(u32 __user *uaddr, int op, u32 val, ktime_t *timeout,
-	      u32 __user *uaddr2, u32 val2, u32 val3);
-#else
-static inline void exit_robust_list(struct task_struct *curr)
+static inline void futex_init_task(struct task_struct *tsk)
 {
+	tsk->robust_list = NULL;
+#ifdef CONFIG_COMPAT
+	tsk->compat_robust_list = NULL;
+#endif
+	INIT_LIST_HEAD(&tsk->pi_state_list);
+	tsk->pi_state_cache = NULL;
+	tsk->futex_state = FUTEX_STATE_OK;
+	mutex_init(&tsk->futex_exit_mutex);
 }
 
+void futex_exit_recursive(struct task_struct *tsk);
+void futex_exit_release(struct task_struct *tsk);
+void futex_exec_release(struct task_struct *tsk);
+
+long do_futex(u32 __user *uaddr, int op, u32 val, ktime_t *timeout,
+	      u32 __user *uaddr2, u32 val2, u32 val3);
+#else
+static inline void futex_init_task(struct task_struct *tsk) { }
+static inline void futex_exit_recursive(struct task_struct *tsk) { }
+static inline void futex_exit_release(struct task_struct *tsk) { }
+static inline void futex_exec_release(struct task_struct *tsk) { }
 static inline long do_futex(u32 __user *uaddr, int op, u32 val,
 			    ktime_t *timeout, u32 __user *uaddr2,
 			    u32 val2, u32 val3)
@@ -65,12 +87,4 @@ static inline long do_futex(u32 __user *uaddr, int op, u32 val,
 }
 #endif
 
-#ifdef CONFIG_FUTEX_PI
-extern void exit_pi_state_list(struct task_struct *curr);
-#else
-static inline void exit_pi_state_list(struct task_struct *curr)
-{
-}
-#endif
-
 #endif
diff --git a/include/linux/fwnode.h b/include/linux/fwnode.h
index ababd6bc82f3..9d9dc444d787 100644
--- a/include/linux/fwnode.h
+++ b/include/linux/fwnode.h
@@ -49,13 +49,15 @@ struct fwnode_reference_args {
  * struct fwnode_operations - Operations for fwnode interface
  * @get: Get a reference to an fwnode.
  * @put: Put a reference to an fwnode.
+ * @device_is_available: Return true if the device is available.
  * @device_get_match_data: Return the device driver match data.
  * @property_present: Return true if a property is present.
- * @property_read_integer_array: Read an array of integer properties. Return
- *				 zero on success, a negative error code
- *				 otherwise.
+ * @property_read_int_array: Read an array of integer properties. Return zero on
+ *			     success, a negative error code otherwise.
  * @property_read_string_array: Read an array of string properties. Return zero
  *				on success, a negative error code otherwise.
+ * @get_name: Return the name of an fwnode.
+ * @get_name_prefix: Get a prefix for a node (for printing purposes).
  * @get_parent: Return the parent of an fwnode.
  * @get_next_child_node: Return the next child node in an iteration.
  * @get_named_child_node: Return a child node with a given name.
@@ -82,6 +84,8 @@ struct fwnode_operations {
 	(*property_read_string_array)(const struct fwnode_handle *fwnode_handle,
 				      const char *propname, const char **val,
 				      size_t nval);
+	const char *(*get_name)(const struct fwnode_handle *fwnode);
+	const char *(*get_name_prefix)(const struct fwnode_handle *fwnode);
 	struct fwnode_handle *(*get_parent)(const struct fwnode_handle *fwnode);
 	struct fwnode_handle *
 	(*get_next_child_node)(const struct fwnode_handle *fwnode,
diff --git a/include/linux/ioport.h b/include/linux/ioport.h
index 7bddddfc76d6..a9b9170b5dd2 100644
--- a/include/linux/ioport.h
+++ b/include/linux/ioport.h
@@ -134,6 +134,7 @@ enum {
 	IORES_DESC_PERSISTENT_MEMORY_LEGACY	= 5,
 	IORES_DESC_DEVICE_PRIVATE_MEMORY	= 6,
 	IORES_DESC_RESERVED			= 7,
+	IORES_DESC_SOFT_RESERVED		= 8,
 };
 
 /*
diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h
index 603fbc4e2f70..564793c24d12 100644
--- a/include/linux/jbd2.h
+++ b/include/linux/jbd2.h
@@ -1170,7 +1170,7 @@ struct journal_s
 #define jbd2_might_wait_for_commit(j) \
 	do { \
 		rwsem_acquire(&j->j_trans_commit_map, 0, 0, _THIS_IP_); \
-		rwsem_release(&j->j_trans_commit_map, 1, _THIS_IP_); \
+		rwsem_release(&j->j_trans_commit_map, _THIS_IP_); \
 	} while (0)
 
 /* journal feature predicate functions */
diff --git a/include/linux/kernel.h b/include/linux/kernel.h
index d83d403dac2e..09f759228e3f 100644
--- a/include/linux/kernel.h
+++ b/include/linux/kernel.h
@@ -328,13 +328,6 @@ extern int oops_may_print(void);
 void do_exit(long error_code) __noreturn;
 void complete_and_exit(struct completion *, long) __noreturn;
 
-#ifdef CONFIG_ARCH_HAS_REFCOUNT
-void refcount_error_report(struct pt_regs *regs, const char *err);
-#else
-static inline void refcount_error_report(struct pt_regs *regs, const char *err)
-{ }
-#endif
-
 /* Internal, do not use. */
 int __must_check _kstrtoul(const char *s, unsigned int base, unsigned long *res);
 int __must_check _kstrtol(const char *s, unsigned int base, long *res);
diff --git a/include/linux/kernel_stat.h b/include/linux/kernel_stat.h
index 7ee2bb43b251..89f0745c096d 100644
--- a/include/linux/kernel_stat.h
+++ b/include/linux/kernel_stat.h
@@ -78,6 +78,24 @@ static inline unsigned int kstat_cpu_irqs_sum(unsigned int cpu)
 	return kstat_cpu(cpu).irqs_sum;
 }
 
+#ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN
+extern u64 kcpustat_field(struct kernel_cpustat *kcpustat,
+			  enum cpu_usage_stat usage, int cpu);
+extern void kcpustat_cpu_fetch(struct kernel_cpustat *dst, int cpu);
+#else
+static inline u64 kcpustat_field(struct kernel_cpustat *kcpustat,
+				 enum cpu_usage_stat usage, int cpu)
+{
+	return kcpustat->cpustat[usage];
+}
+
+static inline void kcpustat_cpu_fetch(struct kernel_cpustat *dst, int cpu)
+{
+	*dst = kcpustat_cpu(cpu);
+}
+
+#endif
+
 extern void account_user_time(struct task_struct *, u64);
 extern void account_guest_time(struct task_struct *, u64);
 extern void account_system_time(struct task_struct *, int, u64);
diff --git a/include/linux/linkage.h b/include/linux/linkage.h
index 7e020782ade2..9280209d1f62 100644
--- a/include/linux/linkage.h
+++ b/include/linux/linkage.h
@@ -75,32 +75,61 @@
 
 #ifdef __ASSEMBLY__
 
+/* SYM_T_FUNC -- type used by assembler to mark functions */
+#ifndef SYM_T_FUNC
+#define SYM_T_FUNC				STT_FUNC
+#endif
+
+/* SYM_T_OBJECT -- type used by assembler to mark data */
+#ifndef SYM_T_OBJECT
+#define SYM_T_OBJECT				STT_OBJECT
+#endif
+
+/* SYM_T_NONE -- type used by assembler to mark entries of unknown type */
+#ifndef SYM_T_NONE
+#define SYM_T_NONE				STT_NOTYPE
+#endif
+
+/* SYM_A_* -- align the symbol? */
+#define SYM_A_ALIGN				ALIGN
+#define SYM_A_NONE				/* nothing */
+
+/* SYM_L_* -- linkage of symbols */
+#define SYM_L_GLOBAL(name)			.globl name
+#define SYM_L_WEAK(name)			.weak name
+#define SYM_L_LOCAL(name)			/* nothing */
+
 #ifndef LINKER_SCRIPT
 #define ALIGN __ALIGN
 #define ALIGN_STR __ALIGN_STR
 
+/* === DEPRECATED annotations === */
+
+#ifndef CONFIG_X86
 #ifndef GLOBAL
+/* deprecated, use SYM_DATA*, SYM_ENTRY, or similar */
 #define GLOBAL(name) \
 	.globl name ASM_NL \
 	name:
 #endif
 
 #ifndef ENTRY
+/* deprecated, use SYM_FUNC_START */
 #define ENTRY(name) \
-	.globl name ASM_NL \
-	ALIGN ASM_NL \
-	name:
+	SYM_FUNC_START(name)
 #endif
+#endif /* CONFIG_X86 */
 #endif /* LINKER_SCRIPT */
 
+#ifndef CONFIG_X86
 #ifndef WEAK
+/* deprecated, use SYM_FUNC_START_WEAK* */
 #define WEAK(name)	   \
-	.weak name ASM_NL   \
-	ALIGN ASM_NL \
-	name:
+	SYM_FUNC_START_WEAK(name)
 #endif
 
 #ifndef END
+/* deprecated, use SYM_FUNC_END, SYM_DATA_END, or SYM_END */
 #define END(name) \
 	.size name, .-name
 #endif
@@ -110,11 +139,215 @@
  * static analysis tools such as stack depth analyzer.
  */
 #ifndef ENDPROC
+/* deprecated, use SYM_FUNC_END */
 #define ENDPROC(name) \
-	.type name, @function ASM_NL \
-	END(name)
+	SYM_FUNC_END(name)
+#endif
+#endif /* CONFIG_X86 */
+
+/* === generic annotations === */
+
+/* SYM_ENTRY -- use only if you have to for non-paired symbols */
+#ifndef SYM_ENTRY
+#define SYM_ENTRY(name, linkage, align...)		\
+	linkage(name) ASM_NL				\
+	align ASM_NL					\
+	name:
+#endif
+
+/* SYM_START -- use only if you have to */
+#ifndef SYM_START
+#define SYM_START(name, linkage, align...)		\
+	SYM_ENTRY(name, linkage, align)
+#endif
+
+/* SYM_END -- use only if you have to */
+#ifndef SYM_END
+#define SYM_END(name, sym_type)				\
+	.type name sym_type ASM_NL			\
+	.size name, .-name
+#endif
+
+/* === code annotations === */
+
+/*
+ * FUNC -- C-like functions (proper stack frame etc.)
+ * CODE -- non-C code (e.g. irq handlers with different, special stack etc.)
+ *
+ * Objtool validates stack for FUNC, but not for CODE.
+ * Objtool generates debug info for both FUNC & CODE, but needs special
+ * annotations for each CODE's start (to describe the actual stack frame).
+ *
+ * ALIAS -- does not generate debug info -- the aliased function will
+ */
+
+/* SYM_INNER_LABEL_ALIGN -- only for labels in the middle of code */
+#ifndef SYM_INNER_LABEL_ALIGN
+#define SYM_INNER_LABEL_ALIGN(name, linkage)	\
+	.type name SYM_T_NONE ASM_NL			\
+	SYM_ENTRY(name, linkage, SYM_A_ALIGN)
+#endif
+
+/* SYM_INNER_LABEL -- only for labels in the middle of code */
+#ifndef SYM_INNER_LABEL
+#define SYM_INNER_LABEL(name, linkage)		\
+	.type name SYM_T_NONE ASM_NL			\
+	SYM_ENTRY(name, linkage, SYM_A_NONE)
+#endif
+
+/*
+ * SYM_FUNC_START_LOCAL_ALIAS -- use where there are two local names for one
+ * function
+ */
+#ifndef SYM_FUNC_START_LOCAL_ALIAS
+#define SYM_FUNC_START_LOCAL_ALIAS(name)		\
+	SYM_START(name, SYM_L_LOCAL, SYM_A_ALIGN)
+#endif
+
+/*
+ * SYM_FUNC_START_ALIAS -- use where there are two global names for one
+ * function
+ */
+#ifndef SYM_FUNC_START_ALIAS
+#define SYM_FUNC_START_ALIAS(name)			\
+	SYM_START(name, SYM_L_GLOBAL, SYM_A_ALIGN)
+#endif
+
+/* SYM_FUNC_START -- use for global functions */
+#ifndef SYM_FUNC_START
+/*
+ * The same as SYM_FUNC_START_ALIAS, but we will need to distinguish these two
+ * later.
+ */
+#define SYM_FUNC_START(name)				\
+	SYM_START(name, SYM_L_GLOBAL, SYM_A_ALIGN)
+#endif
+
+/* SYM_FUNC_START_NOALIGN -- use for global functions, w/o alignment */
+#ifndef SYM_FUNC_START_NOALIGN
+#define SYM_FUNC_START_NOALIGN(name)			\
+	SYM_START(name, SYM_L_GLOBAL, SYM_A_NONE)
+#endif
+
+/* SYM_FUNC_START_LOCAL -- use for local functions */
+#ifndef SYM_FUNC_START_LOCAL
+/* the same as SYM_FUNC_START_LOCAL_ALIAS, see comment near SYM_FUNC_START */
+#define SYM_FUNC_START_LOCAL(name)			\
+	SYM_START(name, SYM_L_LOCAL, SYM_A_ALIGN)
 #endif
 
+/* SYM_FUNC_START_LOCAL_NOALIGN -- use for local functions, w/o alignment */
+#ifndef SYM_FUNC_START_LOCAL_NOALIGN
+#define SYM_FUNC_START_LOCAL_NOALIGN(name)		\
+	SYM_START(name, SYM_L_LOCAL, SYM_A_NONE)
 #endif
 
+/* SYM_FUNC_START_WEAK -- use for weak functions */
+#ifndef SYM_FUNC_START_WEAK
+#define SYM_FUNC_START_WEAK(name)			\
+	SYM_START(name, SYM_L_WEAK, SYM_A_ALIGN)
 #endif
+
+/* SYM_FUNC_START_WEAK_NOALIGN -- use for weak functions, w/o alignment */
+#ifndef SYM_FUNC_START_WEAK_NOALIGN
+#define SYM_FUNC_START_WEAK_NOALIGN(name)		\
+	SYM_START(name, SYM_L_WEAK, SYM_A_NONE)
+#endif
+
+/* SYM_FUNC_END_ALIAS -- the end of LOCAL_ALIASed or ALIASed function */
+#ifndef SYM_FUNC_END_ALIAS
+#define SYM_FUNC_END_ALIAS(name)			\
+	SYM_END(name, SYM_T_FUNC)
+#endif
+
+/*
+ * SYM_FUNC_END -- the end of SYM_FUNC_START_LOCAL, SYM_FUNC_START,
+ * SYM_FUNC_START_WEAK, ...
+ */
+#ifndef SYM_FUNC_END
+/* the same as SYM_FUNC_END_ALIAS, see comment near SYM_FUNC_START */
+#define SYM_FUNC_END(name)				\
+	SYM_END(name, SYM_T_FUNC)
+#endif
+
+/* SYM_CODE_START -- use for non-C (special) functions */
+#ifndef SYM_CODE_START
+#define SYM_CODE_START(name)				\
+	SYM_START(name, SYM_L_GLOBAL, SYM_A_ALIGN)
+#endif
+
+/* SYM_CODE_START_NOALIGN -- use for non-C (special) functions, w/o alignment */
+#ifndef SYM_CODE_START_NOALIGN
+#define SYM_CODE_START_NOALIGN(name)			\
+	SYM_START(name, SYM_L_GLOBAL, SYM_A_NONE)
+#endif
+
+/* SYM_CODE_START_LOCAL -- use for local non-C (special) functions */
+#ifndef SYM_CODE_START_LOCAL
+#define SYM_CODE_START_LOCAL(name)			\
+	SYM_START(name, SYM_L_LOCAL, SYM_A_ALIGN)
+#endif
+
+/*
+ * SYM_CODE_START_LOCAL_NOALIGN -- use for local non-C (special) functions,
+ * w/o alignment
+ */
+#ifndef SYM_CODE_START_LOCAL_NOALIGN
+#define SYM_CODE_START_LOCAL_NOALIGN(name)		\
+	SYM_START(name, SYM_L_LOCAL, SYM_A_NONE)
+#endif
+
+/* SYM_CODE_END -- the end of SYM_CODE_START_LOCAL, SYM_CODE_START, ... */
+#ifndef SYM_CODE_END
+#define SYM_CODE_END(name)				\
+	SYM_END(name, SYM_T_NONE)
+#endif
+
+/* === data annotations === */
+
+/* SYM_DATA_START -- global data symbol */
+#ifndef SYM_DATA_START
+#define SYM_DATA_START(name)				\
+	SYM_START(name, SYM_L_GLOBAL, SYM_A_NONE)
+#endif
+
+/* SYM_DATA_START -- local data symbol */
+#ifndef SYM_DATA_START_LOCAL
+#define SYM_DATA_START_LOCAL(name)			\
+	SYM_START(name, SYM_L_LOCAL, SYM_A_NONE)
+#endif
+
+/* SYM_DATA_END -- the end of SYM_DATA_START symbol */
+#ifndef SYM_DATA_END
+#define SYM_DATA_END(name)				\
+	SYM_END(name, SYM_T_OBJECT)
+#endif
+
+/* SYM_DATA_END_LABEL -- the labeled end of SYM_DATA_START symbol */
+#ifndef SYM_DATA_END_LABEL
+#define SYM_DATA_END_LABEL(name, linkage, label)	\
+	linkage(label) ASM_NL				\
+	.type label SYM_T_OBJECT ASM_NL			\
+	label:						\
+	SYM_END(name, SYM_T_OBJECT)
+#endif
+
+/* SYM_DATA -- start+end wrapper around simple global data */
+#ifndef SYM_DATA
+#define SYM_DATA(name, data...)				\
+	SYM_DATA_START(name) ASM_NL				\
+	data ASM_NL						\
+	SYM_DATA_END(name)
+#endif
+
+/* SYM_DATA_LOCAL -- start+end wrapper around simple local data */
+#ifndef SYM_DATA_LOCAL
+#define SYM_DATA_LOCAL(name, data...)			\
+	SYM_DATA_START_LOCAL(name) ASM_NL			\
+	data ASM_NL						\
+	SYM_DATA_END(name)
+#endif
+
+#endif /* __ASSEMBLY__ */
+
+#endif /* _LINUX_LINKAGE_H */
diff --git a/include/linux/lockdep.h b/include/linux/lockdep.h
index b8a835fd611b..c50d01ef1414 100644
--- a/include/linux/lockdep.h
+++ b/include/linux/lockdep.h
@@ -349,8 +349,7 @@ extern void lock_acquire(struct lockdep_map *lock, unsigned int subclass,
 			 int trylock, int read, int check,
 			 struct lockdep_map *nest_lock, unsigned long ip);
 
-extern void lock_release(struct lockdep_map *lock, int nested,
-			 unsigned long ip);
+extern void lock_release(struct lockdep_map *lock, unsigned long ip);
 
 /*
  * Same "read" as for lock_acquire(), except -1 means any.
@@ -428,7 +427,7 @@ static inline void lockdep_set_selftest_task(struct task_struct *task)
 }
 
 # define lock_acquire(l, s, t, r, c, n, i)	do { } while (0)
-# define lock_release(l, n, i)			do { } while (0)
+# define lock_release(l, i)			do { } while (0)
 # define lock_downgrade(l, i)			do { } while (0)
 # define lock_set_class(l, n, k, s, i)		do { } while (0)
 # define lock_set_subclass(l, s, i)		do { } while (0)
@@ -591,42 +590,42 @@ static inline void print_irqtrace_events(struct task_struct *curr)
 
 #define spin_acquire(l, s, t, i)		lock_acquire_exclusive(l, s, t, NULL, i)
 #define spin_acquire_nest(l, s, t, n, i)	lock_acquire_exclusive(l, s, t, n, i)
-#define spin_release(l, n, i)			lock_release(l, n, i)
+#define spin_release(l, i)			lock_release(l, i)
 
 #define rwlock_acquire(l, s, t, i)		lock_acquire_exclusive(l, s, t, NULL, i)
 #define rwlock_acquire_read(l, s, t, i)		lock_acquire_shared_recursive(l, s, t, NULL, i)
-#define rwlock_release(l, n, i)			lock_release(l, n, i)
+#define rwlock_release(l, i)			lock_release(l, i)
 
 #define seqcount_acquire(l, s, t, i)		lock_acquire_exclusive(l, s, t, NULL, i)
 #define seqcount_acquire_read(l, s, t, i)	lock_acquire_shared_recursive(l, s, t, NULL, i)
-#define seqcount_release(l, n, i)		lock_release(l, n, i)
+#define seqcount_release(l, i)			lock_release(l, i)
 
 #define mutex_acquire(l, s, t, i)		lock_acquire_exclusive(l, s, t, NULL, i)
 #define mutex_acquire_nest(l, s, t, n, i)	lock_acquire_exclusive(l, s, t, n, i)
-#define mutex_release(l, n, i)			lock_release(l, n, i)
+#define mutex_release(l, i)			lock_release(l, i)
 
 #define rwsem_acquire(l, s, t, i)		lock_acquire_exclusive(l, s, t, NULL, i)
 #define rwsem_acquire_nest(l, s, t, n, i)	lock_acquire_exclusive(l, s, t, n, i)
 #define rwsem_acquire_read(l, s, t, i)		lock_acquire_shared(l, s, t, NULL, i)
-#define rwsem_release(l, n, i)			lock_release(l, n, i)
+#define rwsem_release(l, i)			lock_release(l, i)
 
 #define lock_map_acquire(l)			lock_acquire_exclusive(l, 0, 0, NULL, _THIS_IP_)
 #define lock_map_acquire_read(l)		lock_acquire_shared_recursive(l, 0, 0, NULL, _THIS_IP_)
 #define lock_map_acquire_tryread(l)		lock_acquire_shared_recursive(l, 0, 1, NULL, _THIS_IP_)
-#define lock_map_release(l)			lock_release(l, 1, _THIS_IP_)
+#define lock_map_release(l)			lock_release(l, _THIS_IP_)
 
 #ifdef CONFIG_PROVE_LOCKING
 # define might_lock(lock) 						\
 do {									\
 	typecheck(struct lockdep_map *, &(lock)->dep_map);		\
 	lock_acquire(&(lock)->dep_map, 0, 0, 0, 1, NULL, _THIS_IP_);	\
-	lock_release(&(lock)->dep_map, 0, _THIS_IP_);			\
+	lock_release(&(lock)->dep_map, _THIS_IP_);			\
 } while (0)
 # define might_lock_read(lock) 						\
 do {									\
 	typecheck(struct lockdep_map *, &(lock)->dep_map);		\
 	lock_acquire(&(lock)->dep_map, 0, 0, 1, 1, NULL, _THIS_IP_);	\
-	lock_release(&(lock)->dep_map, 0, _THIS_IP_);			\
+	lock_release(&(lock)->dep_map, _THIS_IP_);			\
 } while (0)
 
 #define lockdep_assert_irqs_enabled()	do {				\
diff --git a/include/linux/memregion.h b/include/linux/memregion.h
new file mode 100644
index 000000000000..e11595256cac
--- /dev/null
+++ b/include/linux/memregion.h
@@ -0,0 +1,23 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _MEMREGION_H_
+#define _MEMREGION_H_
+#include <linux/types.h>
+#include <linux/errno.h>
+
+struct memregion_info {
+	int target_node;
+};
+
+#ifdef CONFIG_MEMREGION
+int memregion_alloc(gfp_t gfp);
+void memregion_free(int id);
+#else
+static inline int memregion_alloc(gfp_t gfp)
+{
+	return -ENOMEM;
+}
+void memregion_free(int id)
+{
+}
+#endif
+#endif /* _MEMREGION_H_ */
diff --git a/include/linux/pci.h b/include/linux/pci.h
index 1a6cf19eac2d..eb9f371aa77c 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -2311,9 +2311,11 @@ struct irq_domain *pci_host_bridge_acpi_msi_domain(struct pci_bus *bus);
 
 void
 pci_msi_register_fwnode_provider(struct fwnode_handle *(*fn)(struct device *));
+bool pci_pr3_present(struct pci_dev *pdev);
 #else
 static inline struct irq_domain *
 pci_host_bridge_acpi_msi_domain(struct pci_bus *bus) { return NULL; }
+static inline bool pci_pr3_present(struct pci_dev *pdev) { return false; }
 #endif
 
 #ifdef CONFIG_EEH
diff --git a/include/linux/percpu-rwsem.h b/include/linux/percpu-rwsem.h
index 3998cdf9cd14..ad2ca2a89d5b 100644
--- a/include/linux/percpu-rwsem.h
+++ b/include/linux/percpu-rwsem.h
@@ -93,7 +93,7 @@ static inline void percpu_up_read(struct percpu_rw_semaphore *sem)
 		__percpu_up_read(sem); /* Unconditional memory barrier */
 	preempt_enable();
 
-	rwsem_release(&sem->rw_sem.dep_map, 1, _RET_IP_);
+	rwsem_release(&sem->rw_sem.dep_map, _RET_IP_);
 }
 
 extern void percpu_down_write(struct percpu_rw_semaphore *);
@@ -118,7 +118,7 @@ extern void percpu_free_rwsem(struct percpu_rw_semaphore *);
 static inline void percpu_rwsem_release(struct percpu_rw_semaphore *sem,
 					bool read, unsigned long ip)
 {
-	lock_release(&sem->rw_sem.dep_map, 1, ip);
+	lock_release(&sem->rw_sem.dep_map, ip);
 #ifdef CONFIG_RWSEM_SPIN_ON_OWNER
 	if (!read)
 		atomic_long_set(&sem->rw_sem.owner, RWSEM_OWNER_UNKNOWN);
diff --git a/include/linux/platform_data/cros_ec_commands.h b/include/linux/platform_data/cros_ec_commands.h
index 98415686cbfa..69210881ebac 100644
--- a/include/linux/platform_data/cros_ec_commands.h
+++ b/include/linux/platform_data/cros_ec_commands.h
@@ -556,6 +556,9 @@ enum host_event_code {
 	/* Keyboard recovery combo with hardware reinitialization */
 	EC_HOST_EVENT_KEYBOARD_RECOVERY_HW_REINIT = 30,
 
+	/* WoV */
+	EC_HOST_EVENT_WOV = 31,
+
 	/*
 	 * The high bit of the event mask is not used as a host event code.  If
 	 * it reads back as set, then the entire event mask should be
@@ -1277,8 +1280,6 @@ enum ec_feature_code {
 	 * MOTIONSENSE_CMD_TABLET_MODE_LID_ANGLE.
 	 */
 	EC_FEATURE_REFINED_TABLET_MODE_HYSTERESIS = 37,
-	/* EC supports audio codec. */
-	EC_FEATURE_AUDIO_CODEC = 38,
 	/* The MCU is a System Companion Processor (SCP). */
 	EC_FEATURE_SCP = 39,
 	/* The MCU is an Integrated Sensor Hub */
@@ -4468,92 +4469,246 @@ enum mkbp_cec_event {
 
 /*****************************************************************************/
 
-/* Commands for I2S recording on audio codec. */
+/* Commands for audio codec. */
+#define EC_CMD_EC_CODEC 0x00BC
 
-#define EC_CMD_CODEC_I2S 0x00BC
-#define EC_WOV_I2S_SAMPLE_RATE 48000
+enum ec_codec_subcmd {
+	EC_CODEC_GET_CAPABILITIES = 0x0,
+	EC_CODEC_GET_SHM_ADDR = 0x1,
+	EC_CODEC_SET_SHM_ADDR = 0x2,
+	EC_CODEC_SUBCMD_COUNT,
+};
 
-enum ec_codec_i2s_subcmd {
-	EC_CODEC_SET_SAMPLE_DEPTH = 0x0,
-	EC_CODEC_SET_GAIN = 0x1,
-	EC_CODEC_GET_GAIN = 0x2,
-	EC_CODEC_I2S_ENABLE = 0x3,
-	EC_CODEC_I2S_SET_CONFIG = 0x4,
-	EC_CODEC_I2S_SET_TDM_CONFIG = 0x5,
-	EC_CODEC_I2S_SET_BCLK = 0x6,
-	EC_CODEC_I2S_SUBCMD_COUNT = 0x7,
+enum ec_codec_cap {
+	EC_CODEC_CAP_WOV_AUDIO_SHM = 0,
+	EC_CODEC_CAP_WOV_LANG_SHM = 1,
+	EC_CODEC_CAP_LAST = 32,
 };
 
-enum ec_sample_depth_value {
-	EC_CODEC_SAMPLE_DEPTH_16 = 0,
-	EC_CODEC_SAMPLE_DEPTH_24 = 1,
+enum ec_codec_shm_id {
+	EC_CODEC_SHM_ID_WOV_AUDIO = 0x0,
+	EC_CODEC_SHM_ID_WOV_LANG = 0x1,
+	EC_CODEC_SHM_ID_LAST,
 };
 
-enum ec_i2s_config {
-	EC_DAI_FMT_I2S = 0,
-	EC_DAI_FMT_RIGHT_J = 1,
-	EC_DAI_FMT_LEFT_J = 2,
-	EC_DAI_FMT_PCM_A = 3,
-	EC_DAI_FMT_PCM_B = 4,
-	EC_DAI_FMT_PCM_TDM = 5,
+enum ec_codec_shm_type {
+	EC_CODEC_SHM_TYPE_EC_RAM = 0x0,
+	EC_CODEC_SHM_TYPE_SYSTEM_RAM = 0x1,
 };
 
-/*
- * For subcommand EC_CODEC_GET_GAIN.
- */
-struct __ec_align1 ec_codec_i2s_gain {
+struct __ec_align1 ec_param_ec_codec_get_shm_addr {
+	uint8_t shm_id;
+	uint8_t reserved[3];
+};
+
+struct __ec_align4 ec_param_ec_codec_set_shm_addr {
+	uint64_t phys_addr;
+	uint32_t len;
+	uint8_t shm_id;
+	uint8_t reserved[3];
+};
+
+struct __ec_align4 ec_param_ec_codec {
+	uint8_t cmd; /* enum ec_codec_subcmd */
+	uint8_t reserved[3];
+
+	union {
+		struct ec_param_ec_codec_get_shm_addr
+				get_shm_addr_param;
+		struct ec_param_ec_codec_set_shm_addr
+				set_shm_addr_param;
+	};
+};
+
+struct __ec_align4 ec_response_ec_codec_get_capabilities {
+	uint32_t capabilities;
+};
+
+struct __ec_align4 ec_response_ec_codec_get_shm_addr {
+	uint64_t phys_addr;
+	uint32_t len;
+	uint8_t type;
+	uint8_t reserved[3];
+};
+
+/*****************************************************************************/
+
+/* Commands for DMIC on audio codec. */
+#define EC_CMD_EC_CODEC_DMIC 0x00BD
+
+enum ec_codec_dmic_subcmd {
+	EC_CODEC_DMIC_GET_MAX_GAIN = 0x0,
+	EC_CODEC_DMIC_SET_GAIN_IDX = 0x1,
+	EC_CODEC_DMIC_GET_GAIN_IDX = 0x2,
+	EC_CODEC_DMIC_SUBCMD_COUNT,
+};
+
+enum ec_codec_dmic_channel {
+	EC_CODEC_DMIC_CHANNEL_0 = 0x0,
+	EC_CODEC_DMIC_CHANNEL_1 = 0x1,
+	EC_CODEC_DMIC_CHANNEL_2 = 0x2,
+	EC_CODEC_DMIC_CHANNEL_3 = 0x3,
+	EC_CODEC_DMIC_CHANNEL_4 = 0x4,
+	EC_CODEC_DMIC_CHANNEL_5 = 0x5,
+	EC_CODEC_DMIC_CHANNEL_6 = 0x6,
+	EC_CODEC_DMIC_CHANNEL_7 = 0x7,
+	EC_CODEC_DMIC_CHANNEL_COUNT,
+};
+
+struct __ec_align1 ec_param_ec_codec_dmic_set_gain_idx {
+	uint8_t channel; /* enum ec_codec_dmic_channel */
+	uint8_t gain;
+	uint8_t reserved[2];
+};
+
+struct __ec_align1 ec_param_ec_codec_dmic_get_gain_idx {
+	uint8_t channel; /* enum ec_codec_dmic_channel */
+	uint8_t reserved[3];
+};
+
+struct __ec_align4 ec_param_ec_codec_dmic {
+	uint8_t cmd; /* enum ec_codec_dmic_subcmd */
+	uint8_t reserved[3];
+
+	union {
+		struct ec_param_ec_codec_dmic_set_gain_idx
+				set_gain_idx_param;
+		struct ec_param_ec_codec_dmic_get_gain_idx
+				get_gain_idx_param;
+	};
+};
+
+struct __ec_align1 ec_response_ec_codec_dmic_get_max_gain {
+	uint8_t max_gain;
+};
+
+struct __ec_align1 ec_response_ec_codec_dmic_get_gain_idx {
+	uint8_t gain;
+};
+
+/*****************************************************************************/
+
+/* Commands for I2S RX on audio codec. */
+
+#define EC_CMD_EC_CODEC_I2S_RX 0x00BE
+
+enum ec_codec_i2s_rx_subcmd {
+	EC_CODEC_I2S_RX_ENABLE = 0x0,
+	EC_CODEC_I2S_RX_DISABLE = 0x1,
+	EC_CODEC_I2S_RX_SET_SAMPLE_DEPTH = 0x2,
+	EC_CODEC_I2S_RX_SET_DAIFMT = 0x3,
+	EC_CODEC_I2S_RX_SET_BCLK = 0x4,
+	EC_CODEC_I2S_RX_SUBCMD_COUNT,
+};
+
+enum ec_codec_i2s_rx_sample_depth {
+	EC_CODEC_I2S_RX_SAMPLE_DEPTH_16 = 0x0,
+	EC_CODEC_I2S_RX_SAMPLE_DEPTH_24 = 0x1,
+	EC_CODEC_I2S_RX_SAMPLE_DEPTH_COUNT,
+};
+
+enum ec_codec_i2s_rx_daifmt {
+	EC_CODEC_I2S_RX_DAIFMT_I2S = 0x0,
+	EC_CODEC_I2S_RX_DAIFMT_RIGHT_J = 0x1,
+	EC_CODEC_I2S_RX_DAIFMT_LEFT_J = 0x2,
+	EC_CODEC_I2S_RX_DAIFMT_COUNT,
+};
+
+struct __ec_align1 ec_param_ec_codec_i2s_rx_set_sample_depth {
+	uint8_t depth;
+	uint8_t reserved[3];
+};
+
+struct __ec_align1 ec_param_ec_codec_i2s_rx_set_gain {
 	uint8_t left;
 	uint8_t right;
+	uint8_t reserved[2];
 };
 
-struct __ec_todo_unpacked ec_param_codec_i2s_tdm {
-	int16_t ch0_delay; /* 0 to 496 */
-	int16_t ch1_delay; /* -1 to 496 */
-	uint8_t adjacent_to_ch0;
-	uint8_t adjacent_to_ch1;
+struct __ec_align1 ec_param_ec_codec_i2s_rx_set_daifmt {
+	uint8_t daifmt;
+	uint8_t reserved[3];
 };
 
-struct __ec_todo_packed ec_param_codec_i2s {
-	/* enum ec_codec_i2s_subcmd */
-	uint8_t cmd;
+struct __ec_align4 ec_param_ec_codec_i2s_rx_set_bclk {
+	uint32_t bclk;
+};
+
+struct __ec_align4 ec_param_ec_codec_i2s_rx {
+	uint8_t cmd; /* enum ec_codec_i2s_rx_subcmd */
+	uint8_t reserved[3];
+
 	union {
-		/*
-		 * EC_CODEC_SET_SAMPLE_DEPTH
-		 * Value should be one of ec_sample_depth_value.
-		 */
-		uint8_t depth;
+		struct ec_param_ec_codec_i2s_rx_set_sample_depth
+				set_sample_depth_param;
+		struct ec_param_ec_codec_i2s_rx_set_daifmt
+				set_daifmt_param;
+		struct ec_param_ec_codec_i2s_rx_set_bclk
+				set_bclk_param;
+	};
+};
 
-		/*
-		 * EC_CODEC_SET_GAIN
-		 * Value should be 0~43 for both channels.
-		 */
-		struct ec_codec_i2s_gain gain;
+/*****************************************************************************/
+/* Commands for WoV on audio codec. */
+
+#define EC_CMD_EC_CODEC_WOV 0x00BF
+
+enum ec_codec_wov_subcmd {
+	EC_CODEC_WOV_SET_LANG = 0x0,
+	EC_CODEC_WOV_SET_LANG_SHM = 0x1,
+	EC_CODEC_WOV_GET_LANG = 0x2,
+	EC_CODEC_WOV_ENABLE = 0x3,
+	EC_CODEC_WOV_DISABLE = 0x4,
+	EC_CODEC_WOV_READ_AUDIO = 0x5,
+	EC_CODEC_WOV_READ_AUDIO_SHM = 0x6,
+	EC_CODEC_WOV_SUBCMD_COUNT,
+};
 
-		/*
-		 * EC_CODEC_I2S_ENABLE
-		 * 1 to enable, 0 to disable.
-		 */
-		uint8_t i2s_enable;
+/*
+ * @hash is SHA256 of the whole language model.
+ * @total_len indicates the length of whole language model.
+ * @offset is the cursor from the beginning of the model.
+ * @buf is the packet buffer.
+ * @len denotes how many bytes in the buf.
+ */
+struct __ec_align4 ec_param_ec_codec_wov_set_lang {
+	uint8_t hash[32];
+	uint32_t total_len;
+	uint32_t offset;
+	uint8_t buf[128];
+	uint32_t len;
+};
 
-		/*
-		 * EC_CODEC_I2S_SET_CONFIG
-		 * Value should be one of ec_i2s_config.
-		 */
-		uint8_t i2s_config;
+struct __ec_align4 ec_param_ec_codec_wov_set_lang_shm {
+	uint8_t hash[32];
+	uint32_t total_len;
+};
 
-		/*
-		 * EC_CODEC_I2S_SET_TDM_CONFIG
-		 * Value should be one of ec_i2s_config.
-		 */
-		struct ec_param_codec_i2s_tdm tdm_param;
+struct __ec_align4 ec_param_ec_codec_wov {
+	uint8_t cmd; /* enum ec_codec_wov_subcmd */
+	uint8_t reserved[3];
 
-		/*
-		 * EC_CODEC_I2S_SET_BCLK
-		 */
-		uint32_t bclk;
+	union {
+		struct ec_param_ec_codec_wov_set_lang
+				set_lang_param;
+		struct ec_param_ec_codec_wov_set_lang_shm
+				set_lang_shm_param;
 	};
 };
 
+struct __ec_align4 ec_response_ec_codec_wov_get_lang {
+	uint8_t hash[32];
+};
+
+struct __ec_align4 ec_response_ec_codec_wov_read_audio {
+	uint8_t buf[128];
+	uint32_t len;
+};
+
+struct __ec_align4 ec_response_ec_codec_wov_read_audio_shm {
+	uint32_t offset;
+	uint32_t len;
+};
 
 /*****************************************************************************/
 /* System commands */
diff --git a/include/linux/pm.h b/include/linux/pm.h
index 4c441be03079..e057d1fa2469 100644
--- a/include/linux/pm.h
+++ b/include/linux/pm.h
@@ -637,6 +637,7 @@ extern void dev_pm_put_subsys_data(struct device *dev);
  * struct dev_pm_domain - power management domain representation.
  *
  * @ops: Power management operations associated with this domain.
+ * @start: Called when a user needs to start the device via the domain.
  * @detach: Called when removing a device from the domain.
  * @activate: Called before executing probe routines for bus types and drivers.
  * @sync: Called after successful driver probe.
@@ -648,6 +649,7 @@ extern void dev_pm_put_subsys_data(struct device *dev);
  */
 struct dev_pm_domain {
 	struct dev_pm_ops	ops;
+	int (*start)(struct device *dev);
 	void (*detach)(struct device *dev, bool power_off);
 	int (*activate)(struct device *dev);
 	void (*sync)(struct device *dev);
diff --git a/include/linux/pm_domain.h b/include/linux/pm_domain.h
index baf02ff91a31..5a31c711b896 100644
--- a/include/linux/pm_domain.h
+++ b/include/linux/pm_domain.h
@@ -366,6 +366,7 @@ struct device *dev_pm_domain_attach_by_id(struct device *dev,
 struct device *dev_pm_domain_attach_by_name(struct device *dev,
 					    const char *name);
 void dev_pm_domain_detach(struct device *dev, bool power_off);
+int dev_pm_domain_start(struct device *dev);
 void dev_pm_domain_set(struct device *dev, struct dev_pm_domain *pd);
 #else
 static inline int dev_pm_domain_attach(struct device *dev, bool power_on)
@@ -383,6 +384,10 @@ static inline struct device *dev_pm_domain_attach_by_name(struct device *dev,
 	return NULL;
 }
 static inline void dev_pm_domain_detach(struct device *dev, bool power_off) {}
+static inline int dev_pm_domain_start(struct device *dev)
+{
+	return 0;
+}
 static inline void dev_pm_domain_set(struct device *dev,
 				     struct dev_pm_domain *pd) {}
 #endif
diff --git a/include/linux/pm_opp.h b/include/linux/pm_opp.h
index b8197ab014f2..747861816f4f 100644
--- a/include/linux/pm_opp.h
+++ b/include/linux/pm_opp.h
@@ -22,6 +22,7 @@ struct opp_table;
 
 enum dev_pm_opp_event {
 	OPP_EVENT_ADD, OPP_EVENT_REMOVE, OPP_EVENT_ENABLE, OPP_EVENT_DISABLE,
+	OPP_EVENT_ADJUST_VOLTAGE,
 };
 
 /**
@@ -113,6 +114,10 @@ int dev_pm_opp_add(struct device *dev, unsigned long freq,
 void dev_pm_opp_remove(struct device *dev, unsigned long freq);
 void dev_pm_opp_remove_all_dynamic(struct device *dev);
 
+int dev_pm_opp_adjust_voltage(struct device *dev, unsigned long freq,
+			      unsigned long u_volt, unsigned long u_volt_min,
+			      unsigned long u_volt_max);
+
 int dev_pm_opp_enable(struct device *dev, unsigned long freq);
 
 int dev_pm_opp_disable(struct device *dev, unsigned long freq);
@@ -242,6 +247,14 @@ static inline void dev_pm_opp_remove_all_dynamic(struct device *dev)
 {
 }
 
+static inline int
+dev_pm_opp_adjust_voltage(struct device *dev, unsigned long freq,
+			  unsigned long u_volt, unsigned long u_volt_min,
+			  unsigned long u_volt_max)
+{
+	return 0;
+}
+
 static inline int dev_pm_opp_enable(struct device *dev, unsigned long freq)
 {
 	return 0;
diff --git a/include/linux/power/smartreflex.h b/include/linux/power/smartreflex.h
index d0b37e937037..971c9264179e 100644
--- a/include/linux/power/smartreflex.h
+++ b/include/linux/power/smartreflex.h
@@ -293,6 +293,9 @@ struct omap_sr_data {
 	struct voltagedomain		*voltdm;
 };
 
+
+extern struct omap_sr_data omap_sr_pdata[OMAP_SR_NR];
+
 #ifdef CONFIG_POWER_AVS_OMAP
 
 /* Smartreflex module enable/disable interface */
diff --git a/include/linux/property.h b/include/linux/property.h
index 9b3d4ca3a73a..48335288c2a9 100644
--- a/include/linux/property.h
+++ b/include/linux/property.h
@@ -22,7 +22,6 @@ enum dev_prop_type {
 	DEV_PROP_U32,
 	DEV_PROP_U64,
 	DEV_PROP_STRING,
-	DEV_PROP_MAX,
 };
 
 enum dev_dma_attr {
@@ -80,9 +79,14 @@ struct fwnode_handle *fwnode_find_reference(const struct fwnode_handle *fwnode,
 					    const char *name,
 					    unsigned int index);
 
+const char *fwnode_get_name(const struct fwnode_handle *fwnode);
+const char *fwnode_get_name_prefix(const struct fwnode_handle *fwnode);
 struct fwnode_handle *fwnode_get_parent(const struct fwnode_handle *fwnode);
 struct fwnode_handle *fwnode_get_next_parent(
 	struct fwnode_handle *fwnode);
+unsigned int fwnode_count_parents(const struct fwnode_handle *fwn);
+struct fwnode_handle *fwnode_get_nth_parent(struct fwnode_handle *fwn,
+					    unsigned int depth);
 struct fwnode_handle *fwnode_get_next_child_node(
 	const struct fwnode_handle *fwnode, struct fwnode_handle *child);
 struct fwnode_handle *fwnode_get_next_available_child_node(
@@ -234,13 +238,7 @@ struct property_entry {
 	bool is_array;
 	enum dev_prop_type type;
 	union {
-		union {
-			const u8 *u8_data;
-			const u16 *u16_data;
-			const u32 *u32_data;
-			const u64 *u64_data;
-			const char * const *str;
-		} pointer;
+		const void *pointer;
 		union {
 			u8 u8_data;
 			u16 u16_data;
@@ -252,62 +250,63 @@ struct property_entry {
 };
 
 /*
- * Note: the below four initializers for the anonymous union are carefully
+ * Note: the below initializers for the anonymous union are carefully
  * crafted to avoid gcc-4.4.4's problems with initialization of anon unions
  * and structs.
  */
 
-#define PROPERTY_ENTRY_INTEGER_ARRAY(_name_, _type_, _Type_, _val_)	\
+#define __PROPERTY_ENTRY_ELEMENT_SIZE(_elem_)				\
+	sizeof(((struct property_entry *)NULL)->value._elem_)
+
+#define __PROPERTY_ENTRY_ARRAY_LEN(_name_, _elem_, _Type_, _val_, _len_)\
 (struct property_entry) {						\
 	.name = _name_,							\
-	.length = ARRAY_SIZE(_val_) * sizeof(_type_),			\
+	.length = (_len_) * __PROPERTY_ENTRY_ELEMENT_SIZE(_elem_),	\
 	.is_array = true,						\
 	.type = DEV_PROP_##_Type_,					\
-	{ .pointer = { ._type_##_data = _val_ } },			\
+	{ .pointer = _val_ },						\
 }
 
-#define PROPERTY_ENTRY_U8_ARRAY(_name_, _val_)			\
-	PROPERTY_ENTRY_INTEGER_ARRAY(_name_, u8, U8, _val_)
-#define PROPERTY_ENTRY_U16_ARRAY(_name_, _val_)			\
-	PROPERTY_ENTRY_INTEGER_ARRAY(_name_, u16, U16, _val_)
-#define PROPERTY_ENTRY_U32_ARRAY(_name_, _val_)			\
-	PROPERTY_ENTRY_INTEGER_ARRAY(_name_, u32, U32, _val_)
-#define PROPERTY_ENTRY_U64_ARRAY(_name_, _val_)			\
-	PROPERTY_ENTRY_INTEGER_ARRAY(_name_, u64, U64, _val_)
-
-#define PROPERTY_ENTRY_STRING_ARRAY(_name_, _val_)		\
-(struct property_entry) {					\
-	.name = _name_,						\
-	.length = ARRAY_SIZE(_val_) * sizeof(const char *),	\
-	.is_array = true,					\
-	.type = DEV_PROP_STRING,				\
-	{ .pointer = { .str = _val_ } },			\
-}
-
-#define PROPERTY_ENTRY_INTEGER(_name_, _type_, _Type_, _val_)	\
-(struct property_entry) {					\
-	.name = _name_,						\
-	.length = sizeof(_type_),				\
-	.type = DEV_PROP_##_Type_,				\
-	{ .value = { ._type_##_data = _val_ } },		\
+#define PROPERTY_ENTRY_U8_ARRAY_LEN(_name_, _val_, _len_)		\
+	__PROPERTY_ENTRY_ARRAY_LEN(_name_, u8_data, U8, _val_, _len_)
+#define PROPERTY_ENTRY_U16_ARRAY_LEN(_name_, _val_, _len_)		\
+	__PROPERTY_ENTRY_ARRAY_LEN(_name_, u16_data, U16, _val_, _len_)
+#define PROPERTY_ENTRY_U32_ARRAY_LEN(_name_, _val_, _len_)		\
+	__PROPERTY_ENTRY_ARRAY_LEN(_name_, u32_data, U32, _val_, _len_)
+#define PROPERTY_ENTRY_U64_ARRAY_LEN(_name_, _val_, _len_)		\
+	__PROPERTY_ENTRY_ARRAY_LEN(_name_, u64_data, U64, _val_, _len_)
+#define PROPERTY_ENTRY_STRING_ARRAY_LEN(_name_, _val_, _len_)		\
+	__PROPERTY_ENTRY_ARRAY_LEN(_name_, str, STRING, _val_, _len_)
+
+#define PROPERTY_ENTRY_U8_ARRAY(_name_, _val_)				\
+	PROPERTY_ENTRY_U8_ARRAY_LEN(_name_, _val_, ARRAY_SIZE(_val_))
+#define PROPERTY_ENTRY_U16_ARRAY(_name_, _val_)				\
+	PROPERTY_ENTRY_U16_ARRAY_LEN(_name_, _val_, ARRAY_SIZE(_val_))
+#define PROPERTY_ENTRY_U32_ARRAY(_name_, _val_)				\
+	PROPERTY_ENTRY_U32_ARRAY_LEN(_name_, _val_, ARRAY_SIZE(_val_))
+#define PROPERTY_ENTRY_U64_ARRAY(_name_, _val_)				\
+	PROPERTY_ENTRY_U64_ARRAY_LEN(_name_, _val_, ARRAY_SIZE(_val_))
+#define PROPERTY_ENTRY_STRING_ARRAY(_name_, _val_)			\
+	PROPERTY_ENTRY_STRING_ARRAY_LEN(_name_, _val_, ARRAY_SIZE(_val_))
+
+#define __PROPERTY_ENTRY_ELEMENT(_name_, _elem_, _Type_, _val_)		\
+(struct property_entry) {						\
+	.name = _name_,							\
+	.length = __PROPERTY_ENTRY_ELEMENT_SIZE(_elem_),		\
+	.type = DEV_PROP_##_Type_,					\
+	{ .value = { ._elem_ = _val_ } },				\
 }
 
-#define PROPERTY_ENTRY_U8(_name_, _val_)		\
-	PROPERTY_ENTRY_INTEGER(_name_, u8, U8, _val_)
-#define PROPERTY_ENTRY_U16(_name_, _val_)		\
-	PROPERTY_ENTRY_INTEGER(_name_, u16, U16, _val_)
-#define PROPERTY_ENTRY_U32(_name_, _val_)		\
-	PROPERTY_ENTRY_INTEGER(_name_, u32, U32, _val_)
-#define PROPERTY_ENTRY_U64(_name_, _val_)		\
-	PROPERTY_ENTRY_INTEGER(_name_, u64, U64, _val_)
-
-#define PROPERTY_ENTRY_STRING(_name_, _val_)		\
-(struct property_entry) {				\
-	.name = _name_,					\
-	.length = sizeof(const char *),			\
-	.type = DEV_PROP_STRING,			\
-	{ .value = { .str = _val_ } },			\
-}
+#define PROPERTY_ENTRY_U8(_name_, _val_)				\
+	__PROPERTY_ENTRY_ELEMENT(_name_, u8_data, U8, _val_)
+#define PROPERTY_ENTRY_U16(_name_, _val_)				\
+	__PROPERTY_ENTRY_ELEMENT(_name_, u16_data, U16, _val_)
+#define PROPERTY_ENTRY_U32(_name_, _val_)				\
+	__PROPERTY_ENTRY_ELEMENT(_name_, u32_data, U32, _val_)
+#define PROPERTY_ENTRY_U64(_name_, _val_)				\
+	__PROPERTY_ENTRY_ELEMENT(_name_, u64_data, U64, _val_)
+#define PROPERTY_ENTRY_STRING(_name_, _val_)				\
+	__PROPERTY_ENTRY_ELEMENT(_name_, str, STRING, _val_)
 
 #define PROPERTY_ENTRY_BOOL(_name_)		\
 (struct property_entry) {			\
@@ -418,7 +417,8 @@ struct software_node {
 };
 
 bool is_software_node(const struct fwnode_handle *fwnode);
-const struct software_node *to_software_node(struct fwnode_handle *fwnode);
+const struct software_node *
+to_software_node(const struct fwnode_handle *fwnode);
 struct fwnode_handle *software_node_fwnode(const struct software_node *node);
 
 const struct software_node *
diff --git a/include/linux/rculist_bl.h b/include/linux/rculist_bl.h
index 66e73ec1aa99..0b952d06eb0b 100644
--- a/include/linux/rculist_bl.h
+++ b/include/linux/rculist_bl.h
@@ -25,34 +25,6 @@ static inline struct hlist_bl_node *hlist_bl_first_rcu(struct hlist_bl_head *h)
 }
 
 /**
- * hlist_bl_del_init_rcu - deletes entry from hash list with re-initialization
- * @n: the element to delete from the hash list.
- *
- * Note: hlist_bl_unhashed() on the node returns true after this. It is
- * useful for RCU based read lockfree traversal if the writer side
- * must know if the list entry is still hashed or already unhashed.
- *
- * In particular, it means that we can not poison the forward pointers
- * that may still be used for walking the hash list and we can only
- * zero the pprev pointer so list_unhashed() will return true after
- * this.
- *
- * The caller must take whatever precautions are necessary (such as
- * holding appropriate locks) to avoid racing with another
- * list-mutation primitive, such as hlist_bl_add_head_rcu() or
- * hlist_bl_del_rcu(), running on this same list.  However, it is
- * perfectly legal to run concurrently with the _rcu list-traversal
- * primitives, such as hlist_bl_for_each_entry_rcu().
- */
-static inline void hlist_bl_del_init_rcu(struct hlist_bl_node *n)
-{
-	if (!hlist_bl_unhashed(n)) {
-		__hlist_bl_del(n);
-		n->pprev = NULL;
-	}
-}
-
-/**
  * hlist_bl_del_rcu - deletes entry from hash list without re-initialization
  * @n: the element to delete from the hash list.
  *
diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h
index 75a2eded7aa2..0b7506330c87 100644
--- a/include/linux/rcupdate.h
+++ b/include/linux/rcupdate.h
@@ -210,7 +210,7 @@ static inline void rcu_lock_acquire(struct lockdep_map *map)
 
 static inline void rcu_lock_release(struct lockdep_map *map)
 {
-	lock_release(map, 1, _THIS_IP_);
+	lock_release(map, _THIS_IP_);
 }
 
 extern struct lockdep_map rcu_lock_map;
@@ -383,6 +383,24 @@ do {									      \
 } while (0)
 
 /**
+ * rcu_replace_pointer() - replace an RCU pointer, returning its old value
+ * @rcu_ptr: RCU pointer, whose old value is returned
+ * @ptr: regular pointer
+ * @c: the lockdep conditions under which the dereference will take place
+ *
+ * Perform a replacement, where @rcu_ptr is an RCU-annotated
+ * pointer and @c is the lockdep argument that is passed to the
+ * rcu_dereference_protected() call used to read that pointer.  The old
+ * value of @rcu_ptr is returned, and @rcu_ptr is set to @ptr.
+ */
+#define rcu_replace_pointer(rcu_ptr, ptr, c)				\
+({									\
+	typeof(ptr) __tmp = rcu_dereference_protected((rcu_ptr), (c));	\
+	rcu_assign_pointer((rcu_ptr), (ptr));				\
+	__tmp;								\
+})
+
+/**
  * rcu_swap_protected() - swap an RCU and a regular pointer
  * @rcu_ptr: RCU pointer
  * @ptr: regular pointer
diff --git a/include/linux/rcutiny.h b/include/linux/rcutiny.h
index 9bf1dfe7781f..37b6f0c2b79d 100644
--- a/include/linux/rcutiny.h
+++ b/include/linux/rcutiny.h
@@ -84,6 +84,7 @@ static inline void rcu_scheduler_starting(void) { }
 #endif /* #else #ifndef CONFIG_SRCU */
 static inline void rcu_end_inkernel_boot(void) { }
 static inline bool rcu_is_watching(void) { return true; }
+static inline void rcu_momentary_dyntick_idle(void) { }
 
 /* Avoid RCU read-side critical sections leaking across. */
 static inline void rcu_all_qs(void) { barrier(); }
diff --git a/include/linux/rcutree.h b/include/linux/rcutree.h
index 18b1ed9864b0..c5147de885ec 100644
--- a/include/linux/rcutree.h
+++ b/include/linux/rcutree.h
@@ -37,6 +37,7 @@ void kfree_call_rcu(struct rcu_head *head, rcu_callback_t func);
 
 void rcu_barrier(void);
 bool rcu_eqs_special_set(int cpu);
+void rcu_momentary_dyntick_idle(void);
 unsigned long get_state_synchronize_rcu(void);
 void cond_synchronize_rcu(unsigned long oldstate);
 
diff --git a/include/linux/refcount.h b/include/linux/refcount.h
index e28cce21bad6..0ac50cf62d06 100644
--- a/include/linux/refcount.h
+++ b/include/linux/refcount.h
@@ -1,9 +1,88 @@
 /* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Variant of atomic_t specialized for reference counts.
+ *
+ * The interface matches the atomic_t interface (to aid in porting) but only
+ * provides the few functions one should use for reference counting.
+ *
+ * Saturation semantics
+ * ====================
+ *
+ * refcount_t differs from atomic_t in that the counter saturates at
+ * REFCOUNT_SATURATED and will not move once there. This avoids wrapping the
+ * counter and causing 'spurious' use-after-free issues. In order to avoid the
+ * cost associated with introducing cmpxchg() loops into all of the saturating
+ * operations, we temporarily allow the counter to take on an unchecked value
+ * and then explicitly set it to REFCOUNT_SATURATED on detecting that underflow
+ * or overflow has occurred. Although this is racy when multiple threads
+ * access the refcount concurrently, by placing REFCOUNT_SATURATED roughly
+ * equidistant from 0 and INT_MAX we minimise the scope for error:
+ *
+ * 	                           INT_MAX     REFCOUNT_SATURATED   UINT_MAX
+ *   0                          (0x7fff_ffff)    (0xc000_0000)    (0xffff_ffff)
+ *   +--------------------------------+----------------+----------------+
+ *                                     <---------- bad value! ---------->
+ *
+ * (in a signed view of the world, the "bad value" range corresponds to
+ * a negative counter value).
+ *
+ * As an example, consider a refcount_inc() operation that causes the counter
+ * to overflow:
+ *
+ * 	int old = atomic_fetch_add_relaxed(r);
+ *	// old is INT_MAX, refcount now INT_MIN (0x8000_0000)
+ *	if (old < 0)
+ *		atomic_set(r, REFCOUNT_SATURATED);
+ *
+ * If another thread also performs a refcount_inc() operation between the two
+ * atomic operations, then the count will continue to edge closer to 0. If it
+ * reaches a value of 1 before /any/ of the threads reset it to the saturated
+ * value, then a concurrent refcount_dec_and_test() may erroneously free the
+ * underlying object. Given the precise timing details involved with the
+ * round-robin scheduling of each thread manipulating the refcount and the need
+ * to hit the race multiple times in succession, there doesn't appear to be a
+ * practical avenue of attack even if using refcount_add() operations with
+ * larger increments.
+ *
+ * Memory ordering
+ * ===============
+ *
+ * Memory ordering rules are slightly relaxed wrt regular atomic_t functions
+ * and provide only what is strictly required for refcounts.
+ *
+ * The increments are fully relaxed; these will not provide ordering. The
+ * rationale is that whatever is used to obtain the object we're increasing the
+ * reference count on will provide the ordering. For locked data structures,
+ * its the lock acquire, for RCU/lockless data structures its the dependent
+ * load.
+ *
+ * Do note that inc_not_zero() provides a control dependency which will order
+ * future stores against the inc, this ensures we'll never modify the object
+ * if we did not in fact acquire a reference.
+ *
+ * The decrements will provide release order, such that all the prior loads and
+ * stores will be issued before, it also provides a control dependency, which
+ * will order us against the subsequent free().
+ *
+ * The control dependency is against the load of the cmpxchg (ll/sc) that
+ * succeeded. This means the stores aren't fully ordered, but this is fine
+ * because the 1->0 transition indicates no concurrency.
+ *
+ * Note that the allocator is responsible for ordering things between free()
+ * and alloc().
+ *
+ * The decrements dec_and_test() and sub_and_test() also provide acquire
+ * ordering on success.
+ *
+ */
+
 #ifndef _LINUX_REFCOUNT_H
 #define _LINUX_REFCOUNT_H
 
 #include <linux/atomic.h>
+#include <linux/bug.h>
 #include <linux/compiler.h>
+#include <linux/limits.h>
 #include <linux/spinlock_types.h>
 
 struct mutex;
@@ -12,7 +91,7 @@ struct mutex;
  * struct refcount_t - variant of atomic_t specialized for reference counts
  * @refs: atomic_t counter field
  *
- * The counter saturates at UINT_MAX and will not move once
+ * The counter saturates at REFCOUNT_SATURATED and will not move once
  * there. This avoids wrapping the counter and causing 'spurious'
  * use-after-free bugs.
  */
@@ -21,13 +100,25 @@ typedef struct refcount_struct {
 } refcount_t;
 
 #define REFCOUNT_INIT(n)	{ .refs = ATOMIC_INIT(n), }
+#define REFCOUNT_MAX		INT_MAX
+#define REFCOUNT_SATURATED	(INT_MIN / 2)
+
+enum refcount_saturation_type {
+	REFCOUNT_ADD_NOT_ZERO_OVF,
+	REFCOUNT_ADD_OVF,
+	REFCOUNT_ADD_UAF,
+	REFCOUNT_SUB_UAF,
+	REFCOUNT_DEC_LEAK,
+};
+
+void refcount_warn_saturate(refcount_t *r, enum refcount_saturation_type t);
 
 /**
  * refcount_set - set a refcount's value
  * @r: the refcount
  * @n: value to which the refcount will be set
  */
-static inline void refcount_set(refcount_t *r, unsigned int n)
+static inline void refcount_set(refcount_t *r, int n)
 {
 	atomic_set(&r->refs, n);
 }
@@ -43,70 +134,168 @@ static inline unsigned int refcount_read(const refcount_t *r)
 	return atomic_read(&r->refs);
 }
 
-extern __must_check bool refcount_add_not_zero_checked(unsigned int i, refcount_t *r);
-extern void refcount_add_checked(unsigned int i, refcount_t *r);
-
-extern __must_check bool refcount_inc_not_zero_checked(refcount_t *r);
-extern void refcount_inc_checked(refcount_t *r);
-
-extern __must_check bool refcount_sub_and_test_checked(unsigned int i, refcount_t *r);
-
-extern __must_check bool refcount_dec_and_test_checked(refcount_t *r);
-extern void refcount_dec_checked(refcount_t *r);
-
-#ifdef CONFIG_REFCOUNT_FULL
-
-#define refcount_add_not_zero	refcount_add_not_zero_checked
-#define refcount_add		refcount_add_checked
-
-#define refcount_inc_not_zero	refcount_inc_not_zero_checked
-#define refcount_inc		refcount_inc_checked
+/**
+ * refcount_add_not_zero - add a value to a refcount unless it is 0
+ * @i: the value to add to the refcount
+ * @r: the refcount
+ *
+ * Will saturate at REFCOUNT_SATURATED and WARN.
+ *
+ * Provides no memory ordering, it is assumed the caller has guaranteed the
+ * object memory to be stable (RCU, etc.). It does provide a control dependency
+ * and thereby orders future stores. See the comment on top.
+ *
+ * Use of this function is not recommended for the normal reference counting
+ * use case in which references are taken and released one at a time.  In these
+ * cases, refcount_inc(), or one of its variants, should instead be used to
+ * increment a reference count.
+ *
+ * Return: false if the passed refcount is 0, true otherwise
+ */
+static inline __must_check bool refcount_add_not_zero(int i, refcount_t *r)
+{
+	int old = refcount_read(r);
 
-#define refcount_sub_and_test	refcount_sub_and_test_checked
+	do {
+		if (!old)
+			break;
+	} while (!atomic_try_cmpxchg_relaxed(&r->refs, &old, old + i));
 
-#define refcount_dec_and_test	refcount_dec_and_test_checked
-#define refcount_dec		refcount_dec_checked
+	if (unlikely(old < 0 || old + i < 0))
+		refcount_warn_saturate(r, REFCOUNT_ADD_NOT_ZERO_OVF);
 
-#else
-# ifdef CONFIG_ARCH_HAS_REFCOUNT
-#  include <asm/refcount.h>
-# else
-static inline __must_check bool refcount_add_not_zero(unsigned int i, refcount_t *r)
-{
-	return atomic_add_unless(&r->refs, i, 0);
+	return old;
 }
 
-static inline void refcount_add(unsigned int i, refcount_t *r)
+/**
+ * refcount_add - add a value to a refcount
+ * @i: the value to add to the refcount
+ * @r: the refcount
+ *
+ * Similar to atomic_add(), but will saturate at REFCOUNT_SATURATED and WARN.
+ *
+ * Provides no memory ordering, it is assumed the caller has guaranteed the
+ * object memory to be stable (RCU, etc.). It does provide a control dependency
+ * and thereby orders future stores. See the comment on top.
+ *
+ * Use of this function is not recommended for the normal reference counting
+ * use case in which references are taken and released one at a time.  In these
+ * cases, refcount_inc(), or one of its variants, should instead be used to
+ * increment a reference count.
+ */
+static inline void refcount_add(int i, refcount_t *r)
 {
-	atomic_add(i, &r->refs);
+	int old = atomic_fetch_add_relaxed(i, &r->refs);
+
+	if (unlikely(!old))
+		refcount_warn_saturate(r, REFCOUNT_ADD_UAF);
+	else if (unlikely(old < 0 || old + i < 0))
+		refcount_warn_saturate(r, REFCOUNT_ADD_OVF);
 }
 
+/**
+ * refcount_inc_not_zero - increment a refcount unless it is 0
+ * @r: the refcount to increment
+ *
+ * Similar to atomic_inc_not_zero(), but will saturate at REFCOUNT_SATURATED
+ * and WARN.
+ *
+ * Provides no memory ordering, it is assumed the caller has guaranteed the
+ * object memory to be stable (RCU, etc.). It does provide a control dependency
+ * and thereby orders future stores. See the comment on top.
+ *
+ * Return: true if the increment was successful, false otherwise
+ */
 static inline __must_check bool refcount_inc_not_zero(refcount_t *r)
 {
-	return atomic_add_unless(&r->refs, 1, 0);
+	return refcount_add_not_zero(1, r);
 }
 
+/**
+ * refcount_inc - increment a refcount
+ * @r: the refcount to increment
+ *
+ * Similar to atomic_inc(), but will saturate at REFCOUNT_SATURATED and WARN.
+ *
+ * Provides no memory ordering, it is assumed the caller already has a
+ * reference on the object.
+ *
+ * Will WARN if the refcount is 0, as this represents a possible use-after-free
+ * condition.
+ */
 static inline void refcount_inc(refcount_t *r)
 {
-	atomic_inc(&r->refs);
+	refcount_add(1, r);
 }
 
-static inline __must_check bool refcount_sub_and_test(unsigned int i, refcount_t *r)
+/**
+ * refcount_sub_and_test - subtract from a refcount and test if it is 0
+ * @i: amount to subtract from the refcount
+ * @r: the refcount
+ *
+ * Similar to atomic_dec_and_test(), but it will WARN, return false and
+ * ultimately leak on underflow and will fail to decrement when saturated
+ * at REFCOUNT_SATURATED.
+ *
+ * Provides release memory ordering, such that prior loads and stores are done
+ * before, and provides an acquire ordering on success such that free()
+ * must come after.
+ *
+ * Use of this function is not recommended for the normal reference counting
+ * use case in which references are taken and released one at a time.  In these
+ * cases, refcount_dec(), or one of its variants, should instead be used to
+ * decrement a reference count.
+ *
+ * Return: true if the resulting refcount is 0, false otherwise
+ */
+static inline __must_check bool refcount_sub_and_test(int i, refcount_t *r)
 {
-	return atomic_sub_and_test(i, &r->refs);
+	int old = atomic_fetch_sub_release(i, &r->refs);
+
+	if (old == i) {
+		smp_acquire__after_ctrl_dep();
+		return true;
+	}
+
+	if (unlikely(old < 0 || old - i < 0))
+		refcount_warn_saturate(r, REFCOUNT_SUB_UAF);
+
+	return false;
 }
 
+/**
+ * refcount_dec_and_test - decrement a refcount and test if it is 0
+ * @r: the refcount
+ *
+ * Similar to atomic_dec_and_test(), it will WARN on underflow and fail to
+ * decrement when saturated at REFCOUNT_SATURATED.
+ *
+ * Provides release memory ordering, such that prior loads and stores are done
+ * before, and provides an acquire ordering on success such that free()
+ * must come after.
+ *
+ * Return: true if the resulting refcount is 0, false otherwise
+ */
 static inline __must_check bool refcount_dec_and_test(refcount_t *r)
 {
-	return atomic_dec_and_test(&r->refs);
+	return refcount_sub_and_test(1, r);
 }
 
+/**
+ * refcount_dec - decrement a refcount
+ * @r: the refcount
+ *
+ * Similar to atomic_dec(), it will WARN on underflow and fail to decrement
+ * when saturated at REFCOUNT_SATURATED.
+ *
+ * Provides release memory ordering, such that prior loads and stores are done
+ * before.
+ */
 static inline void refcount_dec(refcount_t *r)
 {
-	atomic_dec(&r->refs);
+	if (unlikely(atomic_fetch_sub_release(1, &r->refs) <= 1))
+		refcount_warn_saturate(r, REFCOUNT_DEC_LEAK);
 }
-# endif /* !CONFIG_ARCH_HAS_REFCOUNT */
-#endif /* CONFIG_REFCOUNT_FULL */
 
 extern __must_check bool refcount_dec_if_one(refcount_t *r);
 extern __must_check bool refcount_dec_not_one(refcount_t *r);
diff --git a/include/linux/rwlock_api_smp.h b/include/linux/rwlock_api_smp.h
index 86ebb4bf9c6e..abfb53ab11be 100644
--- a/include/linux/rwlock_api_smp.h
+++ b/include/linux/rwlock_api_smp.h
@@ -215,14 +215,14 @@ static inline void __raw_write_lock(rwlock_t *lock)
 
 static inline void __raw_write_unlock(rwlock_t *lock)
 {
-	rwlock_release(&lock->dep_map, 1, _RET_IP_);
+	rwlock_release(&lock->dep_map, _RET_IP_);
 	do_raw_write_unlock(lock);
 	preempt_enable();
 }
 
 static inline void __raw_read_unlock(rwlock_t *lock)
 {
-	rwlock_release(&lock->dep_map, 1, _RET_IP_);
+	rwlock_release(&lock->dep_map, _RET_IP_);
 	do_raw_read_unlock(lock);
 	preempt_enable();
 }
@@ -230,7 +230,7 @@ static inline void __raw_read_unlock(rwlock_t *lock)
 static inline void
 __raw_read_unlock_irqrestore(rwlock_t *lock, unsigned long flags)
 {
-	rwlock_release(&lock->dep_map, 1, _RET_IP_);
+	rwlock_release(&lock->dep_map, _RET_IP_);
 	do_raw_read_unlock(lock);
 	local_irq_restore(flags);
 	preempt_enable();
@@ -238,7 +238,7 @@ __raw_read_unlock_irqrestore(rwlock_t *lock, unsigned long flags)
 
 static inline void __raw_read_unlock_irq(rwlock_t *lock)
 {
-	rwlock_release(&lock->dep_map, 1, _RET_IP_);
+	rwlock_release(&lock->dep_map, _RET_IP_);
 	do_raw_read_unlock(lock);
 	local_irq_enable();
 	preempt_enable();
@@ -246,7 +246,7 @@ static inline void __raw_read_unlock_irq(rwlock_t *lock)
 
 static inline void __raw_read_unlock_bh(rwlock_t *lock)
 {
-	rwlock_release(&lock->dep_map, 1, _RET_IP_);
+	rwlock_release(&lock->dep_map, _RET_IP_);
 	do_raw_read_unlock(lock);
 	__local_bh_enable_ip(_RET_IP_, SOFTIRQ_LOCK_OFFSET);
 }
@@ -254,7 +254,7 @@ static inline void __raw_read_unlock_bh(rwlock_t *lock)
 static inline void __raw_write_unlock_irqrestore(rwlock_t *lock,
 					     unsigned long flags)
 {
-	rwlock_release(&lock->dep_map, 1, _RET_IP_);
+	rwlock_release(&lock->dep_map, _RET_IP_);
 	do_raw_write_unlock(lock);
 	local_irq_restore(flags);
 	preempt_enable();
@@ -262,7 +262,7 @@ static inline void __raw_write_unlock_irqrestore(rwlock_t *lock,
 
 static inline void __raw_write_unlock_irq(rwlock_t *lock)
 {
-	rwlock_release(&lock->dep_map, 1, _RET_IP_);
+	rwlock_release(&lock->dep_map, _RET_IP_);
 	do_raw_write_unlock(lock);
 	local_irq_enable();
 	preempt_enable();
@@ -270,7 +270,7 @@ static inline void __raw_write_unlock_irq(rwlock_t *lock)
 
 static inline void __raw_write_unlock_bh(rwlock_t *lock)
 {
-	rwlock_release(&lock->dep_map, 1, _RET_IP_);
+	rwlock_release(&lock->dep_map, _RET_IP_);
 	do_raw_write_unlock(lock);
 	__local_bh_enable_ip(_RET_IP_, SOFTIRQ_LOCK_OFFSET);
 }
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 6666e25606b7..07e68d9f5dc4 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -250,16 +250,21 @@ struct prev_cputime {
 enum vtime_state {
 	/* Task is sleeping or running in a CPU with VTIME inactive: */
 	VTIME_INACTIVE = 0,
-	/* Task runs in userspace in a CPU with VTIME active: */
-	VTIME_USER,
+	/* Task is idle */
+	VTIME_IDLE,
 	/* Task runs in kernelspace in a CPU with VTIME active: */
 	VTIME_SYS,
+	/* Task runs in userspace in a CPU with VTIME active: */
+	VTIME_USER,
+	/* Task runs as guests in a CPU with VTIME active: */
+	VTIME_GUEST,
 };
 
 struct vtime {
 	seqcount_t		seqcount;
 	unsigned long long	starttime;
 	enum vtime_state	state;
+	unsigned int		cpu;
 	u64			utime;
 	u64			stime;
 	u64			gtime;
@@ -1054,6 +1059,8 @@ struct task_struct {
 #endif
 	struct list_head		pi_state_list;
 	struct futex_pi_state		*pi_state_cache;
+	struct mutex			futex_exit_mutex;
+	unsigned int			futex_state;
 #endif
 #ifdef CONFIG_PERF_EVENTS
 	struct perf_event_context	*perf_event_ctxp[perf_nr_task_contexts];
@@ -1442,7 +1449,6 @@ extern struct pid *cad_pid;
  */
 #define PF_IDLE			0x00000002	/* I am an IDLE thread */
 #define PF_EXITING		0x00000004	/* Getting shut down */
-#define PF_EXITPIDONE		0x00000008	/* PI exit done on shut down */
 #define PF_VCPU			0x00000010	/* I'm a virtual CPU */
 #define PF_WQ_WORKER		0x00000020	/* I'm a workqueue worker */
 #define PF_FORKNOEXEC		0x00000040	/* Forked but didn't exec */
diff --git a/include/linux/sched/mm.h b/include/linux/sched/mm.h
index e6770012db18..c49257a3b510 100644
--- a/include/linux/sched/mm.h
+++ b/include/linux/sched/mm.h
@@ -117,8 +117,10 @@ extern struct mm_struct *get_task_mm(struct task_struct *task);
  * succeeds.
  */
 extern struct mm_struct *mm_access(struct task_struct *task, unsigned int mode);
-/* Remove the current tasks stale references to the old mm_struct */
-extern void mm_release(struct task_struct *, struct mm_struct *);
+/* Remove the current tasks stale references to the old mm_struct on exit() */
+extern void exit_mm_release(struct task_struct *, struct mm_struct *);
+/* Remove the current tasks stale references to the old mm_struct on exec() */
+extern void exec_mm_release(struct task_struct *, struct mm_struct *);
 
 #ifdef CONFIG_MEMCG
 extern void mm_update_next_owner(struct mm_struct *mm);
diff --git a/include/linux/seqlock.h b/include/linux/seqlock.h
index bcf4cf26b8c8..0491d963d47e 100644
--- a/include/linux/seqlock.h
+++ b/include/linux/seqlock.h
@@ -79,7 +79,7 @@ static inline void seqcount_lockdep_reader_access(const seqcount_t *s)
 
 	local_irq_save(flags);
 	seqcount_acquire_read(&l->dep_map, 0, 0, _RET_IP_);
-	seqcount_release(&l->dep_map, 1, _RET_IP_);
+	seqcount_release(&l->dep_map, _RET_IP_);
 	local_irq_restore(flags);
 }
 
@@ -384,7 +384,7 @@ static inline void write_seqcount_begin(seqcount_t *s)
 
 static inline void write_seqcount_end(seqcount_t *s)
 {
-	seqcount_release(&s->dep_map, 1, _RET_IP_);
+	seqcount_release(&s->dep_map, _RET_IP_);
 	raw_write_seqcount_end(s);
 }
 
diff --git a/include/linux/spinlock_api_smp.h b/include/linux/spinlock_api_smp.h
index b762eaba4cdf..19a9be9d97ee 100644
--- a/include/linux/spinlock_api_smp.h
+++ b/include/linux/spinlock_api_smp.h
@@ -147,7 +147,7 @@ static inline void __raw_spin_lock(raw_spinlock_t *lock)
 
 static inline void __raw_spin_unlock(raw_spinlock_t *lock)
 {
-	spin_release(&lock->dep_map, 1, _RET_IP_);
+	spin_release(&lock->dep_map, _RET_IP_);
 	do_raw_spin_unlock(lock);
 	preempt_enable();
 }
@@ -155,7 +155,7 @@ static inline void __raw_spin_unlock(raw_spinlock_t *lock)
 static inline void __raw_spin_unlock_irqrestore(raw_spinlock_t *lock,
 					    unsigned long flags)
 {
-	spin_release(&lock->dep_map, 1, _RET_IP_);
+	spin_release(&lock->dep_map, _RET_IP_);
 	do_raw_spin_unlock(lock);
 	local_irq_restore(flags);
 	preempt_enable();
@@ -163,7 +163,7 @@ static inline void __raw_spin_unlock_irqrestore(raw_spinlock_t *lock,
 
 static inline void __raw_spin_unlock_irq(raw_spinlock_t *lock)
 {
-	spin_release(&lock->dep_map, 1, _RET_IP_);
+	spin_release(&lock->dep_map, _RET_IP_);
 	do_raw_spin_unlock(lock);
 	local_irq_enable();
 	preempt_enable();
@@ -171,7 +171,7 @@ static inline void __raw_spin_unlock_irq(raw_spinlock_t *lock)
 
 static inline void __raw_spin_unlock_bh(raw_spinlock_t *lock)
 {
-	spin_release(&lock->dep_map, 1, _RET_IP_);
+	spin_release(&lock->dep_map, _RET_IP_);
 	do_raw_spin_unlock(lock);
 	__local_bh_enable_ip(_RET_IP_, SOFTIRQ_LOCK_OFFSET);
 }
diff --git a/include/linux/tick.h b/include/linux/tick.h
index f92a10b5e112..7896f792d3b0 100644
--- a/include/linux/tick.h
+++ b/include/linux/tick.h
@@ -108,7 +108,8 @@ enum tick_dep_bits {
 	TICK_DEP_BIT_POSIX_TIMER	= 0,
 	TICK_DEP_BIT_PERF_EVENTS	= 1,
 	TICK_DEP_BIT_SCHED		= 2,
-	TICK_DEP_BIT_CLOCK_UNSTABLE	= 3
+	TICK_DEP_BIT_CLOCK_UNSTABLE	= 3,
+	TICK_DEP_BIT_RCU		= 4
 };
 
 #define TICK_DEP_MASK_NONE		0
@@ -116,6 +117,7 @@ enum tick_dep_bits {
 #define TICK_DEP_MASK_PERF_EVENTS	(1 << TICK_DEP_BIT_PERF_EVENTS)
 #define TICK_DEP_MASK_SCHED		(1 << TICK_DEP_BIT_SCHED)
 #define TICK_DEP_MASK_CLOCK_UNSTABLE	(1 << TICK_DEP_BIT_CLOCK_UNSTABLE)
+#define TICK_DEP_MASK_RCU		(1 << TICK_DEP_BIT_RCU)
 
 #ifdef CONFIG_NO_HZ_COMMON
 extern bool tick_nohz_enabled;
@@ -174,7 +176,7 @@ extern cpumask_var_t tick_nohz_full_mask;
 
 static inline bool tick_nohz_full_enabled(void)
 {
-	if (!context_tracking_is_enabled())
+	if (!context_tracking_enabled())
 		return false;
 
 	return tick_nohz_full_running;
@@ -268,6 +270,9 @@ static inline bool tick_nohz_full_enabled(void) { return false; }
 static inline bool tick_nohz_full_cpu(int cpu) { return false; }
 static inline void tick_nohz_full_add_cpus_to(struct cpumask *mask) { }
 
+static inline void tick_nohz_dep_set_cpu(int cpu, enum tick_dep_bits bit) { }
+static inline void tick_nohz_dep_clear_cpu(int cpu, enum tick_dep_bits bit) { }
+
 static inline void tick_dep_set(enum tick_dep_bits bit) { }
 static inline void tick_dep_clear(enum tick_dep_bits bit) { }
 static inline void tick_dep_set_cpu(int cpu, enum tick_dep_bits bit) { }
diff --git a/include/linux/vtime.h b/include/linux/vtime.h
index a26ed10a4eac..2cdeca062db3 100644
--- a/include/linux/vtime.h
+++ b/include/linux/vtime.h
@@ -11,11 +11,15 @@
 struct task_struct;
 
 /*
- * vtime_accounting_cpu_enabled() definitions/declarations
+ * vtime_accounting_enabled_this_cpu() definitions/declarations
  */
 #if defined(CONFIG_VIRT_CPU_ACCOUNTING_NATIVE)
-static inline bool vtime_accounting_cpu_enabled(void) { return true; }
+
+static inline bool vtime_accounting_enabled_this_cpu(void) { return true; }
+extern void vtime_task_switch(struct task_struct *prev);
+
 #elif defined(CONFIG_VIRT_CPU_ACCOUNTING_GEN)
+
 /*
  * Checks if vtime is enabled on some CPU. Cputime readers want to be careful
  * in that case and compute the tickless cputime.
@@ -24,46 +28,43 @@ static inline bool vtime_accounting_cpu_enabled(void) { return true; }
  */
 static inline bool vtime_accounting_enabled(void)
 {
-	return context_tracking_is_enabled();
+	return context_tracking_enabled();
 }
 
-static inline bool vtime_accounting_cpu_enabled(void)
+static inline bool vtime_accounting_enabled_cpu(int cpu)
 {
-	if (vtime_accounting_enabled()) {
-		if (context_tracking_cpu_is_enabled())
-			return true;
-	}
-
-	return false;
+	return context_tracking_enabled_cpu(cpu);
 }
-#else /* !CONFIG_VIRT_CPU_ACCOUNTING */
-static inline bool vtime_accounting_cpu_enabled(void) { return false; }
-#endif
 
+static inline bool vtime_accounting_enabled_this_cpu(void)
+{
+	return context_tracking_enabled_this_cpu();
+}
 
-/*
- * Common vtime APIs
- */
-#ifdef CONFIG_VIRT_CPU_ACCOUNTING
+extern void vtime_task_switch_generic(struct task_struct *prev);
 
-#ifdef __ARCH_HAS_VTIME_TASK_SWITCH
-extern void vtime_task_switch(struct task_struct *prev);
-#else
-extern void vtime_common_task_switch(struct task_struct *prev);
 static inline void vtime_task_switch(struct task_struct *prev)
 {
-	if (vtime_accounting_cpu_enabled())
-		vtime_common_task_switch(prev);
+	if (vtime_accounting_enabled_this_cpu())
+		vtime_task_switch_generic(prev);
 }
-#endif /* __ARCH_HAS_VTIME_TASK_SWITCH */
-
-extern void vtime_account_system(struct task_struct *tsk);
-extern void vtime_account_idle(struct task_struct *tsk);
 
 #else /* !CONFIG_VIRT_CPU_ACCOUNTING */
 
+static inline bool vtime_accounting_enabled_cpu(int cpu) {return false; }
+static inline bool vtime_accounting_enabled_this_cpu(void) { return false; }
 static inline void vtime_task_switch(struct task_struct *prev) { }
-static inline void vtime_account_system(struct task_struct *tsk) { }
+
+#endif
+
+/*
+ * Common vtime APIs
+ */
+#ifdef CONFIG_VIRT_CPU_ACCOUNTING
+extern void vtime_account_kernel(struct task_struct *tsk);
+extern void vtime_account_idle(struct task_struct *tsk);
+#else /* !CONFIG_VIRT_CPU_ACCOUNTING */
+static inline void vtime_account_kernel(struct task_struct *tsk) { }
 #endif /* !CONFIG_VIRT_CPU_ACCOUNTING */
 
 #ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN
@@ -86,7 +87,7 @@ extern void vtime_account_irq_enter(struct task_struct *tsk);
 static inline void vtime_account_irq_exit(struct task_struct *tsk)
 {
 	/* On hard|softirq exit we always account to hard|softirq cputime */
-	vtime_account_system(tsk);
+	vtime_account_kernel(tsk);
 }
 extern void vtime_flush(struct task_struct *tsk);
 #else /* !CONFIG_VIRT_CPU_ACCOUNTING_NATIVE */
diff --git a/include/linux/ww_mutex.h b/include/linux/ww_mutex.h
index 3af7c0e03be5..d7554252404c 100644
--- a/include/linux/ww_mutex.h
+++ b/include/linux/ww_mutex.h
@@ -182,7 +182,7 @@ static inline void ww_acquire_done(struct ww_acquire_ctx *ctx)
 static inline void ww_acquire_fini(struct ww_acquire_ctx *ctx)
 {
 #ifdef CONFIG_DEBUG_MUTEXES
-	mutex_release(&ctx->dep_map, 0, _THIS_IP_);
+	mutex_release(&ctx->dep_map, _THIS_IP_);
 
 	DEBUG_LOCKS_WARN_ON(ctx->acquired);
 	if (!IS_ENABLED(CONFIG_PROVE_LOCKING))
diff --git a/include/media/cec-pin.h b/include/media/cec-pin.h
index 604e79cb6cbf..88c8b016eb09 100644
--- a/include/media/cec-pin.h
+++ b/include/media/cec-pin.h
@@ -29,8 +29,11 @@
  *		an error if negative. If NULL or -ENOTTY is returned,
  *		then this is not supported.
  *
- * These operations are used by the cec pin framework to manipulate
- * the CEC pin.
+ * @received:	optional. High-level CEC message callback. Allows the driver
+ *		to process CEC messages.
+ *
+ * These operations (except for the @received op) are used by the
+ * cec pin framework to manipulate the CEC pin.
  */
 struct cec_pin_ops {
 	bool (*read)(struct cec_adapter *adap);
@@ -42,6 +45,9 @@ struct cec_pin_ops {
 	void (*status)(struct cec_adapter *adap, struct seq_file *file);
 	int  (*read_hpd)(struct cec_adapter *adap);
 	int  (*read_5v)(struct cec_adapter *adap);
+
+	/* High-level CEC message callback */
+	int (*received)(struct cec_adapter *adap, struct cec_msg *msg);
 };
 
 /**
diff --git a/include/media/cec.h b/include/media/cec.h
index 4d59387bc61b..0a4f69cc9dd4 100644
--- a/include/media/cec.h
+++ b/include/media/cec.h
@@ -18,9 +18,6 @@
 #include <linux/cec-funcs.h>
 #include <media/rc-core.h>
 
-/* CEC_ADAP_G_CONNECTOR_INFO is available */
-#define CEC_CAP_CONNECTOR_INFO	(1 << 8)
-
 #define CEC_CAP_DEFAULTS (CEC_CAP_LOG_ADDRS | CEC_CAP_TRANSMIT | \
 			  CEC_CAP_PASSTHROUGH | CEC_CAP_RC)
 
@@ -147,34 +144,6 @@ struct cec_adap_ops {
  */
 #define CEC_MAX_MSG_TX_QUEUE_SZ		(18 * 1)
 
-/**
- * struct cec_drm_connector_info - tells which drm connector is
- * associated with the CEC adapter.
- * @card_no: drm card number
- * @connector_id: drm connector ID
- */
-struct cec_drm_connector_info {
-	__u32 card_no;
-	__u32 connector_id;
-};
-
-#define CEC_CONNECTOR_TYPE_NO_CONNECTOR	0
-#define CEC_CONNECTOR_TYPE_DRM		1
-
-/**
- * struct cec_connector_info - tells if and which connector is
- * associated with the CEC adapter.
- * @type: connector type (if any)
- * @drm: drm connector info
- */
-struct cec_connector_info {
-	__u32 type;
-	union {
-		struct cec_drm_connector_info drm;
-		__u32 raw[16];
-	};
-};
-
 struct cec_adapter {
 	struct module *owner;
 	char name[32];
diff --git a/include/media/dvb-usb-ids.h b/include/media/dvb-usb-ids.h
index 7ce4e8332421..1409230ad3a4 100644
--- a/include/media/dvb-usb-ids.h
+++ b/include/media/dvb-usb-ids.h
@@ -389,6 +389,7 @@
 #define USB_PID_MYGICA_T230				0xc688
 #define USB_PID_MYGICA_T230C				0xc689
 #define USB_PID_MYGICA_T230C2				0xc68a
+#define USB_PID_MYGICA_T230C_LITE			0xc699
 #define USB_PID_ELGATO_EYETV_DIVERSITY			0x0011
 #define USB_PID_ELGATO_EYETV_DTT			0x0021
 #define USB_PID_ELGATO_EYETV_DTT_2			0x003f
diff --git a/include/media/hevc-ctrls.h b/include/media/hevc-ctrls.h
new file mode 100644
index 000000000000..1009cf0891cc
--- /dev/null
+++ b/include/media/hevc-ctrls.h
@@ -0,0 +1,212 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * These are the HEVC state controls for use with stateless HEVC
+ * codec drivers.
+ *
+ * It turns out that these structs are not stable yet and will undergo
+ * more changes. So keep them private until they are stable and ready to
+ * become part of the official public API.
+ */
+
+#ifndef _HEVC_CTRLS_H_
+#define _HEVC_CTRLS_H_
+
+#include <linux/videodev2.h>
+
+/* The pixel format isn't stable at the moment and will likely be renamed. */
+#define V4L2_PIX_FMT_HEVC_SLICE v4l2_fourcc('S', '2', '6', '5') /* HEVC parsed slices */
+
+#define V4L2_CID_MPEG_VIDEO_HEVC_SPS		(V4L2_CID_MPEG_BASE + 1008)
+#define V4L2_CID_MPEG_VIDEO_HEVC_PPS		(V4L2_CID_MPEG_BASE + 1009)
+#define V4L2_CID_MPEG_VIDEO_HEVC_SLICE_PARAMS	(V4L2_CID_MPEG_BASE + 1010)
+#define V4L2_CID_MPEG_VIDEO_HEVC_DECODE_MODE	(V4L2_CID_MPEG_BASE + 1015)
+#define V4L2_CID_MPEG_VIDEO_HEVC_START_CODE	(V4L2_CID_MPEG_BASE + 1016)
+
+/* enum v4l2_ctrl_type type values */
+#define V4L2_CTRL_TYPE_HEVC_SPS 0x0120
+#define V4L2_CTRL_TYPE_HEVC_PPS 0x0121
+#define V4L2_CTRL_TYPE_HEVC_SLICE_PARAMS 0x0122
+
+enum v4l2_mpeg_video_hevc_decode_mode {
+	V4L2_MPEG_VIDEO_HEVC_DECODE_MODE_SLICE_BASED,
+	V4L2_MPEG_VIDEO_HEVC_DECODE_MODE_FRAME_BASED,
+};
+
+enum v4l2_mpeg_video_hevc_start_code {
+	V4L2_MPEG_VIDEO_HEVC_START_CODE_NONE,
+	V4L2_MPEG_VIDEO_HEVC_START_CODE_ANNEX_B,
+};
+
+#define V4L2_HEVC_SLICE_TYPE_B	0
+#define V4L2_HEVC_SLICE_TYPE_P	1
+#define V4L2_HEVC_SLICE_TYPE_I	2
+
+#define V4L2_HEVC_SPS_FLAG_SEPARATE_COLOUR_PLANE		(1ULL << 0)
+#define V4L2_HEVC_SPS_FLAG_SCALING_LIST_ENABLED			(1ULL << 1)
+#define V4L2_HEVC_SPS_FLAG_AMP_ENABLED				(1ULL << 2)
+#define V4L2_HEVC_SPS_FLAG_SAMPLE_ADAPTIVE_OFFSET		(1ULL << 3)
+#define V4L2_HEVC_SPS_FLAG_PCM_ENABLED				(1ULL << 4)
+#define V4L2_HEVC_SPS_FLAG_PCM_LOOP_FILTER_DISABLED		(1ULL << 5)
+#define V4L2_HEVC_SPS_FLAG_LONG_TERM_REF_PICS_PRESENT		(1ULL << 6)
+#define V4L2_HEVC_SPS_FLAG_SPS_TEMPORAL_MVP_ENABLED		(1ULL << 7)
+#define V4L2_HEVC_SPS_FLAG_STRONG_INTRA_SMOOTHING_ENABLED	(1ULL << 8)
+
+/* The controls are not stable at the moment and will likely be reworked. */
+struct v4l2_ctrl_hevc_sps {
+	/* ISO/IEC 23008-2, ITU-T Rec. H.265: Sequence parameter set */
+	__u16	pic_width_in_luma_samples;
+	__u16	pic_height_in_luma_samples;
+	__u8	bit_depth_luma_minus8;
+	__u8	bit_depth_chroma_minus8;
+	__u8	log2_max_pic_order_cnt_lsb_minus4;
+	__u8	sps_max_dec_pic_buffering_minus1;
+	__u8	sps_max_num_reorder_pics;
+	__u8	sps_max_latency_increase_plus1;
+	__u8	log2_min_luma_coding_block_size_minus3;
+	__u8	log2_diff_max_min_luma_coding_block_size;
+	__u8	log2_min_luma_transform_block_size_minus2;
+	__u8	log2_diff_max_min_luma_transform_block_size;
+	__u8	max_transform_hierarchy_depth_inter;
+	__u8	max_transform_hierarchy_depth_intra;
+	__u8	pcm_sample_bit_depth_luma_minus1;
+	__u8	pcm_sample_bit_depth_chroma_minus1;
+	__u8	log2_min_pcm_luma_coding_block_size_minus3;
+	__u8	log2_diff_max_min_pcm_luma_coding_block_size;
+	__u8	num_short_term_ref_pic_sets;
+	__u8	num_long_term_ref_pics_sps;
+	__u8	chroma_format_idc;
+
+	__u8	padding;
+
+	__u64	flags;
+};
+
+#define V4L2_HEVC_PPS_FLAG_DEPENDENT_SLICE_SEGMENT		(1ULL << 0)
+#define V4L2_HEVC_PPS_FLAG_OUTPUT_FLAG_PRESENT			(1ULL << 1)
+#define V4L2_HEVC_PPS_FLAG_SIGN_DATA_HIDING_ENABLED		(1ULL << 2)
+#define V4L2_HEVC_PPS_FLAG_CABAC_INIT_PRESENT			(1ULL << 3)
+#define V4L2_HEVC_PPS_FLAG_CONSTRAINED_INTRA_PRED		(1ULL << 4)
+#define V4L2_HEVC_PPS_FLAG_TRANSFORM_SKIP_ENABLED		(1ULL << 5)
+#define V4L2_HEVC_PPS_FLAG_CU_QP_DELTA_ENABLED			(1ULL << 6)
+#define V4L2_HEVC_PPS_FLAG_PPS_SLICE_CHROMA_QP_OFFSETS_PRESENT	(1ULL << 7)
+#define V4L2_HEVC_PPS_FLAG_WEIGHTED_PRED			(1ULL << 8)
+#define V4L2_HEVC_PPS_FLAG_WEIGHTED_BIPRED			(1ULL << 9)
+#define V4L2_HEVC_PPS_FLAG_TRANSQUANT_BYPASS_ENABLED		(1ULL << 10)
+#define V4L2_HEVC_PPS_FLAG_TILES_ENABLED			(1ULL << 11)
+#define V4L2_HEVC_PPS_FLAG_ENTROPY_CODING_SYNC_ENABLED		(1ULL << 12)
+#define V4L2_HEVC_PPS_FLAG_LOOP_FILTER_ACROSS_TILES_ENABLED	(1ULL << 13)
+#define V4L2_HEVC_PPS_FLAG_PPS_LOOP_FILTER_ACROSS_SLICES_ENABLED (1ULL << 14)
+#define V4L2_HEVC_PPS_FLAG_DEBLOCKING_FILTER_OVERRIDE_ENABLED	(1ULL << 15)
+#define V4L2_HEVC_PPS_FLAG_PPS_DISABLE_DEBLOCKING_FILTER	(1ULL << 16)
+#define V4L2_HEVC_PPS_FLAG_LISTS_MODIFICATION_PRESENT		(1ULL << 17)
+#define V4L2_HEVC_PPS_FLAG_SLICE_SEGMENT_HEADER_EXTENSION_PRESENT (1ULL << 18)
+
+struct v4l2_ctrl_hevc_pps {
+	/* ISO/IEC 23008-2, ITU-T Rec. H.265: Picture parameter set */
+	__u8	num_extra_slice_header_bits;
+	__s8	init_qp_minus26;
+	__u8	diff_cu_qp_delta_depth;
+	__s8	pps_cb_qp_offset;
+	__s8	pps_cr_qp_offset;
+	__u8	num_tile_columns_minus1;
+	__u8	num_tile_rows_minus1;
+	__u8	column_width_minus1[20];
+	__u8	row_height_minus1[22];
+	__s8	pps_beta_offset_div2;
+	__s8	pps_tc_offset_div2;
+	__u8	log2_parallel_merge_level_minus2;
+
+	__u8	padding[4];
+	__u64	flags;
+};
+
+#define V4L2_HEVC_DPB_ENTRY_RPS_ST_CURR_BEFORE	0x01
+#define V4L2_HEVC_DPB_ENTRY_RPS_ST_CURR_AFTER	0x02
+#define V4L2_HEVC_DPB_ENTRY_RPS_LT_CURR		0x03
+
+#define V4L2_HEVC_DPB_ENTRIES_NUM_MAX		16
+
+struct v4l2_hevc_dpb_entry {
+	__u64	timestamp;
+	__u8	rps;
+	__u8	field_pic;
+	__u16	pic_order_cnt[2];
+	__u8	padding[2];
+};
+
+struct v4l2_hevc_pred_weight_table {
+	__s8	delta_luma_weight_l0[V4L2_HEVC_DPB_ENTRIES_NUM_MAX];
+	__s8	luma_offset_l0[V4L2_HEVC_DPB_ENTRIES_NUM_MAX];
+	__s8	delta_chroma_weight_l0[V4L2_HEVC_DPB_ENTRIES_NUM_MAX][2];
+	__s8	chroma_offset_l0[V4L2_HEVC_DPB_ENTRIES_NUM_MAX][2];
+
+	__s8	delta_luma_weight_l1[V4L2_HEVC_DPB_ENTRIES_NUM_MAX];
+	__s8	luma_offset_l1[V4L2_HEVC_DPB_ENTRIES_NUM_MAX];
+	__s8	delta_chroma_weight_l1[V4L2_HEVC_DPB_ENTRIES_NUM_MAX][2];
+	__s8	chroma_offset_l1[V4L2_HEVC_DPB_ENTRIES_NUM_MAX][2];
+
+	__u8	padding[6];
+
+	__u8	luma_log2_weight_denom;
+	__s8	delta_chroma_log2_weight_denom;
+};
+
+#define V4L2_HEVC_SLICE_PARAMS_FLAG_SLICE_SAO_LUMA		(1ULL << 0)
+#define V4L2_HEVC_SLICE_PARAMS_FLAG_SLICE_SAO_CHROMA		(1ULL << 1)
+#define V4L2_HEVC_SLICE_PARAMS_FLAG_SLICE_TEMPORAL_MVP_ENABLED	(1ULL << 2)
+#define V4L2_HEVC_SLICE_PARAMS_FLAG_MVD_L1_ZERO			(1ULL << 3)
+#define V4L2_HEVC_SLICE_PARAMS_FLAG_CABAC_INIT			(1ULL << 4)
+#define V4L2_HEVC_SLICE_PARAMS_FLAG_COLLOCATED_FROM_L0		(1ULL << 5)
+#define V4L2_HEVC_SLICE_PARAMS_FLAG_USE_INTEGER_MV		(1ULL << 6)
+#define V4L2_HEVC_SLICE_PARAMS_FLAG_SLICE_DEBLOCKING_FILTER_DISABLED (1ULL << 7)
+#define V4L2_HEVC_SLICE_PARAMS_FLAG_SLICE_LOOP_FILTER_ACROSS_SLICES_ENABLED (1ULL << 8)
+
+struct v4l2_ctrl_hevc_slice_params {
+	__u32	bit_size;
+	__u32	data_bit_offset;
+
+	/* ISO/IEC 23008-2, ITU-T Rec. H.265: NAL unit header */
+	__u8	nal_unit_type;
+	__u8	nuh_temporal_id_plus1;
+
+	/* ISO/IEC 23008-2, ITU-T Rec. H.265: General slice segment header */
+	__u8	slice_type;
+	__u8	colour_plane_id;
+	__u16	slice_pic_order_cnt;
+	__u8	num_ref_idx_l0_active_minus1;
+	__u8	num_ref_idx_l1_active_minus1;
+	__u8	collocated_ref_idx;
+	__u8	five_minus_max_num_merge_cand;
+	__s8	slice_qp_delta;
+	__s8	slice_cb_qp_offset;
+	__s8	slice_cr_qp_offset;
+	__s8	slice_act_y_qp_offset;
+	__s8	slice_act_cb_qp_offset;
+	__s8	slice_act_cr_qp_offset;
+	__s8	slice_beta_offset_div2;
+	__s8	slice_tc_offset_div2;
+
+	/* ISO/IEC 23008-2, ITU-T Rec. H.265: Picture timing SEI message */
+	__u8	pic_struct;
+
+	/* ISO/IEC 23008-2, ITU-T Rec. H.265: General slice segment header */
+	__u8	num_active_dpb_entries;
+	__u8	ref_idx_l0[V4L2_HEVC_DPB_ENTRIES_NUM_MAX];
+	__u8	ref_idx_l1[V4L2_HEVC_DPB_ENTRIES_NUM_MAX];
+
+	__u8	num_rps_poc_st_curr_before;
+	__u8	num_rps_poc_st_curr_after;
+	__u8	num_rps_poc_lt_curr;
+
+	__u8	padding;
+
+	/* ISO/IEC 23008-2, ITU-T Rec. H.265: General slice segment header */
+	struct v4l2_hevc_dpb_entry dpb[V4L2_HEVC_DPB_ENTRIES_NUM_MAX];
+
+	/* ISO/IEC 23008-2, ITU-T Rec. H.265: Weighted prediction parameter */
+	struct v4l2_hevc_pred_weight_table pred_weight_table;
+
+	__u64	flags;
+};
+
+#endif
diff --git a/include/media/i2c/smiapp.h b/include/media/i2c/smiapp.h
index d6ccc859bfcd..80f8251d87a3 100644
--- a/include/media/i2c/smiapp.h
+++ b/include/media/i2c/smiapp.h
@@ -49,7 +49,6 @@ struct smiapp_hwconfig {
 	unsigned short i2c_addr_dfl;	/* Default i2c addr */
 	unsigned short i2c_addr_alt;	/* Alternate i2c addr */
 
-	uint32_t nvm_size;		/* bytes */
 	uint32_t ext_clk;		/* sensor external clk */
 
 	unsigned int lanes;		/* Number of CSI-2 lanes */
diff --git a/include/media/rc-map.h b/include/media/rc-map.h
index afd2ab31bdf2..f99575a0d29c 100644
--- a/include/media/rc-map.h
+++ b/include/media/rc-map.h
@@ -159,21 +159,22 @@ struct rc_map *rc_map_get(const char *name);
 #define RC_MAP_ASUS_PS3_100              "rc-asus-ps3-100"
 #define RC_MAP_ATI_TV_WONDER_HD_600      "rc-ati-tv-wonder-hd-600"
 #define RC_MAP_ATI_X10                   "rc-ati-x10"
+#define RC_MAP_AVERMEDIA                 "rc-avermedia"
 #define RC_MAP_AVERMEDIA_A16D            "rc-avermedia-a16d"
 #define RC_MAP_AVERMEDIA_CARDBUS         "rc-avermedia-cardbus"
 #define RC_MAP_AVERMEDIA_DVBT            "rc-avermedia-dvbt"
 #define RC_MAP_AVERMEDIA_M135A           "rc-avermedia-m135a"
 #define RC_MAP_AVERMEDIA_M733A_RM_K6     "rc-avermedia-m733a-rm-k6"
 #define RC_MAP_AVERMEDIA_RM_KS           "rc-avermedia-rm-ks"
-#define RC_MAP_AVERMEDIA                 "rc-avermedia"
 #define RC_MAP_AVERTV_303                "rc-avertv-303"
 #define RC_MAP_AZUREWAVE_AD_TU700        "rc-azurewave-ad-tu700"
-#define RC_MAP_BEHOLD_COLUMBUS           "rc-behold-columbus"
+#define RC_MAP_BEELINK_GS1               "rc-beelink-gs1"
 #define RC_MAP_BEHOLD                    "rc-behold"
+#define RC_MAP_BEHOLD_COLUMBUS           "rc-behold-columbus"
 #define RC_MAP_BUDGET_CI_OLD             "rc-budget-ci-old"
 #define RC_MAP_CEC                       "rc-cec"
-#define RC_MAP_CINERGY_1400              "rc-cinergy-1400"
 #define RC_MAP_CINERGY                   "rc-cinergy"
+#define RC_MAP_CINERGY_1400              "rc-cinergy-1400"
 #define RC_MAP_D680_DMB                  "rc-d680-dmb"
 #define RC_MAP_DELOCK_61959              "rc-delock-61959"
 #define RC_MAP_DIB0700_NEC_TABLE         "rc-dib0700-nec"
@@ -181,17 +182,17 @@ struct rc_map *rc_map_get(const char *name);
 #define RC_MAP_DIGITALNOW_TINYTWIN       "rc-digitalnow-tinytwin"
 #define RC_MAP_DIGITTRADE                "rc-digittrade"
 #define RC_MAP_DM1105_NEC                "rc-dm1105-nec"
-#define RC_MAP_DNTV_LIVE_DVBT_PRO        "rc-dntv-live-dvbt-pro"
 #define RC_MAP_DNTV_LIVE_DVB_T           "rc-dntv-live-dvb-t"
+#define RC_MAP_DNTV_LIVE_DVBT_PRO        "rc-dntv-live-dvbt-pro"
 #define RC_MAP_DTT200U                   "rc-dtt200u"
 #define RC_MAP_DVBSKY                    "rc-dvbsky"
 #define RC_MAP_DVICO_MCE		 "rc-dvico-mce"
 #define RC_MAP_DVICO_PORTABLE		 "rc-dvico-portable"
 #define RC_MAP_EMPTY                     "rc-empty"
 #define RC_MAP_EM_TERRATEC               "rc-em-terratec"
+#define RC_MAP_ENCORE_ENLTV              "rc-encore-enltv"
 #define RC_MAP_ENCORE_ENLTV2             "rc-encore-enltv2"
 #define RC_MAP_ENCORE_ENLTV_FM53         "rc-encore-enltv-fm53"
-#define RC_MAP_ENCORE_ENLTV              "rc-encore-enltv"
 #define RC_MAP_EVGA_INDTUBE              "rc-evga-indtube"
 #define RC_MAP_EZTV                      "rc-eztv"
 #define RC_MAP_FLYDVB                    "rc-flydvb"
@@ -201,6 +202,7 @@ struct rc_map *rc_map_get(const char *name);
 #define RC_MAP_GEEKBOX                   "rc-geekbox"
 #define RC_MAP_GENIUS_TVGO_A11MCE        "rc-genius-tvgo-a11mce"
 #define RC_MAP_GOTVIEW7135               "rc-gotview7135"
+#define RC_MAP_HAUPPAUGE                 "rc-hauppauge"
 #define RC_MAP_HAUPPAUGE_NEW             "rc-hauppauge"
 #define RC_MAP_HISI_POPLAR               "rc-hisi-poplar"
 #define RC_MAP_HISI_TV_DEMO              "rc-hisi-tv-demo"
@@ -223,8 +225,8 @@ struct rc_map *rc_map_get(const char *name);
 #define RC_MAP_MEDION_X10_OR2X           "rc-medion-x10-or2x"
 #define RC_MAP_MSI_DIGIVOX_II            "rc-msi-digivox-ii"
 #define RC_MAP_MSI_DIGIVOX_III           "rc-msi-digivox-iii"
-#define RC_MAP_MSI_TVANYWHERE_PLUS       "rc-msi-tvanywhere-plus"
 #define RC_MAP_MSI_TVANYWHERE            "rc-msi-tvanywhere"
+#define RC_MAP_MSI_TVANYWHERE_PLUS       "rc-msi-tvanywhere-plus"
 #define RC_MAP_NEBULA                    "rc-nebula"
 #define RC_MAP_NEC_TERRATEC_CINERGY_XS   "rc-nec-terratec-cinergy-xs"
 #define RC_MAP_NORWOOD                   "rc-norwood"
@@ -234,21 +236,21 @@ struct rc_map *rc_map_get(const char *name);
 #define RC_MAP_PINNACLE_COLOR            "rc-pinnacle-color"
 #define RC_MAP_PINNACLE_GREY             "rc-pinnacle-grey"
 #define RC_MAP_PINNACLE_PCTV_HD          "rc-pinnacle-pctv-hd"
-#define RC_MAP_PIXELVIEW_NEW             "rc-pixelview-new"
 #define RC_MAP_PIXELVIEW                 "rc-pixelview"
-#define RC_MAP_PIXELVIEW_002T		 "rc-pixelview-002t"
+#define RC_MAP_PIXELVIEW_002T            "rc-pixelview-002t"
 #define RC_MAP_PIXELVIEW_MK12            "rc-pixelview-mk12"
+#define RC_MAP_PIXELVIEW_NEW             "rc-pixelview-new"
 #define RC_MAP_POWERCOLOR_REAL_ANGEL     "rc-powercolor-real-angel"
 #define RC_MAP_PROTEUS_2309              "rc-proteus-2309"
 #define RC_MAP_PURPLETV                  "rc-purpletv"
 #define RC_MAP_PV951                     "rc-pv951"
-#define RC_MAP_HAUPPAUGE                 "rc-hauppauge"
 #define RC_MAP_RC5_TV                    "rc-rc5-tv"
 #define RC_MAP_RC6_MCE                   "rc-rc6-mce"
 #define RC_MAP_REAL_AUDIO_220_32_KEYS    "rc-real-audio-220-32-keys"
 #define RC_MAP_REDDO                     "rc-reddo"
 #define RC_MAP_SNAPSTREAM_FIREFLY        "rc-snapstream-firefly"
 #define RC_MAP_STREAMZAP                 "rc-streamzap"
+#define RC_MAP_SU3000                    "rc-su3000"
 #define RC_MAP_TANGO                     "rc-tango"
 #define RC_MAP_TANIX_TX3MINI             "rc-tanix-tx3mini"
 #define RC_MAP_TANIX_TX5MAX              "rc-tanix-tx5max"
@@ -268,6 +270,7 @@ struct rc_map *rc_map_get(const char *name);
 #define RC_MAP_TT_1500                   "rc-tt-1500"
 #define RC_MAP_TWINHAN_DTV_CAB_CI        "rc-twinhan-dtv-cab-ci"
 #define RC_MAP_TWINHAN_VP1027_DVBS       "rc-twinhan1027"
+#define RC_MAP_VEGA_S9X                  "rc-vega-s9x"
 #define RC_MAP_VIDEOMATE_K100            "rc-videomate-k100"
 #define RC_MAP_VIDEOMATE_S350            "rc-videomate-s350"
 #define RC_MAP_VIDEOMATE_TV_PVR          "rc-videomate-tv-pvr"
@@ -275,9 +278,8 @@ struct rc_map *rc_map_get(const char *name);
 #define RC_MAP_WETEK_PLAY2               "rc-wetek-play2"
 #define RC_MAP_WINFAST                   "rc-winfast"
 #define RC_MAP_WINFAST_USBII_DELUXE      "rc-winfast-usbii-deluxe"
-#define RC_MAP_SU3000                    "rc-su3000"
-#define RC_MAP_XBOX_DVD                  "rc-xbox-dvd"
 #define RC_MAP_X96MAX                    "rc-x96max"
+#define RC_MAP_XBOX_DVD                  "rc-xbox-dvd"
 #define RC_MAP_ZX_IRDEC                  "rc-zx-irdec"
 
 /*
diff --git a/include/media/v4l2-common.h b/include/media/v4l2-common.h
index c070d8ae11e5..d8c29e089000 100644
--- a/include/media/v4l2-common.h
+++ b/include/media/v4l2-common.h
@@ -457,8 +457,24 @@ int v4l2_s_parm_cap(struct video_device *vdev,
 /* Pixel format and FourCC helpers */
 
 /**
+ * enum v4l2_pixel_encoding - specifies the pixel encoding value
+ *
+ * @V4L2_PIXEL_ENC_UNKNOWN:	Pixel encoding is unknown/un-initialized
+ * @V4L2_PIXEL_ENC_YUV:		Pixel encoding is YUV
+ * @V4L2_PIXEL_ENC_RGB:		Pixel encoding is RGB
+ * @V4L2_PIXEL_ENC_BAYER:	Pixel encoding is Bayer
+ */
+enum v4l2_pixel_encoding {
+	V4L2_PIXEL_ENC_UNKNOWN = 0,
+	V4L2_PIXEL_ENC_YUV = 1,
+	V4L2_PIXEL_ENC_RGB = 2,
+	V4L2_PIXEL_ENC_BAYER = 3,
+};
+
+/**
  * struct v4l2_format_info - information about a V4L2 format
  * @format: 4CC format identifier (V4L2_PIX_FMT_*)
+ * @pixel_enc: Pixel encoding (see enum v4l2_pixel_encoding above)
  * @mem_planes: Number of memory planes, which includes the alpha plane (1 to 4).
  * @comp_planes: Number of component planes, which includes the alpha plane (1 to 4).
  * @bpp: Array of per-plane bytes per pixel
@@ -469,6 +485,7 @@ int v4l2_s_parm_cap(struct video_device *vdev,
  */
 struct v4l2_format_info {
 	u32 format;
+	u8 pixel_enc;
 	u8 mem_planes;
 	u8 comp_planes;
 	u8 bpp[4];
@@ -478,8 +495,22 @@ struct v4l2_format_info {
 	u8 block_h[4];
 };
 
-const struct v4l2_format_info *v4l2_format_info(u32 format);
+static inline bool v4l2_is_format_rgb(const struct v4l2_format_info *f)
+{
+	return f && f->pixel_enc == V4L2_PIXEL_ENC_RGB;
+}
 
+static inline bool v4l2_is_format_yuv(const struct v4l2_format_info *f)
+{
+	return f && f->pixel_enc == V4L2_PIXEL_ENC_YUV;
+}
+
+static inline bool v4l2_is_format_bayer(const struct v4l2_format_info *f)
+{
+	return f && f->pixel_enc == V4L2_PIXEL_ENC_BAYER;
+}
+
+const struct v4l2_format_info *v4l2_format_info(u32 format);
 void v4l2_apply_frmsize_constraints(u32 *width, u32 *height,
 				    const struct v4l2_frmsize_stepwise *frmsize);
 int v4l2_fill_pixfmt(struct v4l2_pix_format *pixfmt, u32 pixelformat,
diff --git a/include/media/v4l2-ctrls.h b/include/media/v4l2-ctrls.h
index 570ff4b0205a..7db9e719a583 100644
--- a/include/media/v4l2-ctrls.h
+++ b/include/media/v4l2-ctrls.h
@@ -21,6 +21,7 @@
 #include <media/fwht-ctrls.h>
 #include <media/h264-ctrls.h>
 #include <media/vp8-ctrls.h>
+#include <media/hevc-ctrls.h>
 
 /* forward references */
 struct file;
@@ -50,7 +51,12 @@ struct poll_table_struct;
  * @p_h264_slice_params:	Pointer to a struct v4l2_ctrl_h264_slice_params.
  * @p_h264_decode_params:	Pointer to a struct v4l2_ctrl_h264_decode_params.
  * @p_vp8_frame_header:		Pointer to a VP8 frame header structure.
+ * @p_hevc_sps:			Pointer to an HEVC sequence parameter set structure.
+ * @p_hevc_pps:			Pointer to an HEVC picture parameter set structure.
+ * @p_hevc_slice_params:	Pointer to an HEVC slice parameters structure.
+ * @p_area:			Pointer to an area.
  * @p:				Pointer to a compound value.
+ * @p_const:			Pointer to a constant compound value.
  */
 union v4l2_ctrl_ptr {
 	s32 *p_s32;
@@ -68,10 +74,27 @@ union v4l2_ctrl_ptr {
 	struct v4l2_ctrl_h264_slice_params *p_h264_slice_params;
 	struct v4l2_ctrl_h264_decode_params *p_h264_decode_params;
 	struct v4l2_ctrl_vp8_frame_header *p_vp8_frame_header;
+	struct v4l2_ctrl_hevc_sps *p_hevc_sps;
+	struct v4l2_ctrl_hevc_pps *p_hevc_pps;
+	struct v4l2_ctrl_hevc_slice_params *p_hevc_slice_params;
+	struct v4l2_area *p_area;
 	void *p;
+	const void *p_const;
 };
 
 /**
+ * v4l2_ctrl_ptr_create() - Helper function to return a v4l2_ctrl_ptr from a
+ * void pointer
+ * @ptr:	The void pointer
+ */
+static inline union v4l2_ctrl_ptr v4l2_ctrl_ptr_create(void *ptr)
+{
+	union v4l2_ctrl_ptr p = { .p = ptr };
+
+	return p;
+}
+
+/**
  * struct v4l2_ctrl_ops - The control operations that the driver has to provide.
  *
  * @g_volatile_ctrl: Get a new value for this control. Generally only relevant
@@ -200,6 +223,9 @@ typedef void (*v4l2_ctrl_notify_fnc)(struct v4l2_ctrl *ctrl, void *priv);
  *		not freed when the control is deleted. Should this be needed
  *		then a new internal bitfield can be added to tell the framework
  *		to free this pointer.
+ * @p_def:	The control's default value represented via a union which
+ *		provides a standard way of accessing control types
+ *		through a pointer (for compound controls only).
  * @p_cur:	The control's current value represented via a union which
  *		provides a standard way of accessing control types
  *		through a pointer.
@@ -254,6 +280,7 @@ struct v4l2_ctrl {
 		s32 val;
 	} cur;
 
+	union v4l2_ctrl_ptr p_def;
 	union v4l2_ctrl_ptr p_new;
 	union v4l2_ctrl_ptr p_cur;
 };
@@ -357,6 +384,7 @@ struct v4l2_ctrl_handler {
  * @max:	The control's maximum value.
  * @step:	The control's step value for non-menu controls.
  * @def:	The control's default value.
+ * @p_def:	The control's default value for compound controls.
  * @dims:	The size of each dimension.
  * @elem_size:	The size in bytes of the control.
  * @flags:	The control's flags.
@@ -385,6 +413,7 @@ struct v4l2_ctrl_config {
 	s64 max;
 	u64 step;
 	s64 def;
+	union v4l2_ctrl_ptr p_def;
 	u32 dims[V4L2_CTRL_MAX_DIMS];
 	u32 elem_size;
 	u32 flags;
@@ -647,6 +676,24 @@ struct v4l2_ctrl *v4l2_ctrl_new_std_menu_items(struct v4l2_ctrl_handler *hdl,
 					       const char * const *qmenu);
 
 /**
+ * v4l2_ctrl_new_std_compound() - Allocate and initialize a new standard V4L2
+ *      compound control.
+ *
+ * @hdl:       The control handler.
+ * @ops:       The control ops.
+ * @id:        The control ID.
+ * @p_def:     The control's default value.
+ *
+ * Sames as v4l2_ctrl_new_std(), but with support to compound controls, thanks
+ * to the @p_def field.
+ *
+ */
+struct v4l2_ctrl *v4l2_ctrl_new_std_compound(struct v4l2_ctrl_handler *hdl,
+					     const struct v4l2_ctrl_ops *ops,
+					     u32 id,
+					     const union v4l2_ctrl_ptr p_def);
+
+/**
  * v4l2_ctrl_new_int_menu() - Create a new standard V4L2 integer menu control.
  *
  * @hdl:	The control handler.
@@ -1065,6 +1112,46 @@ static inline int v4l2_ctrl_s_ctrl_string(struct v4l2_ctrl *ctrl, const char *s)
 	return rval;
 }
 
+/**
+ * __v4l2_ctrl_s_ctrl_area() - Unlocked variant of v4l2_ctrl_s_ctrl_area().
+ *
+ * @ctrl:	The control.
+ * @area:	The new area.
+ *
+ * This sets the control's new area safely by going through the control
+ * framework. This function assumes the control's handler is already locked,
+ * allowing it to be used from within the &v4l2_ctrl_ops functions.
+ *
+ * This function is for area type controls only.
+ */
+int __v4l2_ctrl_s_ctrl_area(struct v4l2_ctrl *ctrl,
+			    const struct v4l2_area *area);
+
+/**
+ * v4l2_ctrl_s_ctrl_area() - Helper function to set a control's area value
+ *	 from within a driver.
+ *
+ * @ctrl:	The control.
+ * @area:	The new area.
+ *
+ * This sets the control's new area safely by going through the control
+ * framework. This function will lock the control's handler, so it cannot be
+ * used from within the &v4l2_ctrl_ops functions.
+ *
+ * This function is for area type controls only.
+ */
+static inline int v4l2_ctrl_s_ctrl_area(struct v4l2_ctrl *ctrl,
+					const struct v4l2_area *area)
+{
+	int rval;
+
+	v4l2_ctrl_lock(ctrl);
+	rval = __v4l2_ctrl_s_ctrl_area(ctrl, area);
+	v4l2_ctrl_unlock(ctrl);
+
+	return rval;
+}
+
 /* Internal helper functions that deal with control events. */
 extern const struct v4l2_subscribed_event_ops v4l2_ctrl_sub_ev_ops;
 
diff --git a/include/media/v4l2-device.h b/include/media/v4l2-device.h
index e0b8f2602670..5f36e0d2ede6 100644
--- a/include/media/v4l2-device.h
+++ b/include/media/v4l2-device.h
@@ -72,7 +72,7 @@ static inline void v4l2_device_get(struct v4l2_device *v4l2_dev)
 }
 
 /**
- * v4l2_device_put - putss a V4L2 device reference
+ * v4l2_device_put - puts a V4L2 device reference
  *
  * @v4l2_dev: pointer to struct &v4l2_device
  *
diff --git a/include/media/v4l2-mem2mem.h b/include/media/v4l2-mem2mem.h
index 0b9c3a287061..1d85e24791e4 100644
--- a/include/media/v4l2-mem2mem.h
+++ b/include/media/v4l2-mem2mem.h
@@ -21,7 +21,8 @@
  *		callback.
  *		The job does NOT have to end before this callback returns
  *		(and it will be the usual case). When the job finishes,
- *		v4l2_m2m_job_finish() has to be called.
+ *		v4l2_m2m_job_finish() or v4l2_m2m_buf_done_and_job_finish()
+ *		has to be called.
  * @job_ready:	optional. Should return 0 if the driver does not have a job
  *		fully prepared to run yet (i.e. it will not be able to finish a
  *		transaction without sleeping). If not provided, it will be
@@ -33,7 +34,8 @@
  *		stop the device safely; e.g. in the next interrupt handler),
  *		even if the transaction would not have been finished by then.
  *		After the driver performs the necessary steps, it has to call
- *		v4l2_m2m_job_finish() (as if the transaction ended normally).
+ *		v4l2_m2m_job_finish() or v4l2_m2m_buf_done_and_job_finish() as
+ *		if the transaction ended normally.
  *		This function does not have to (and will usually not) wait
  *		until the device enters a state when it can be stopped.
  */
@@ -73,6 +75,11 @@ struct v4l2_m2m_queue_ctx {
  * struct v4l2_m2m_ctx - Memory to memory context structure
  *
  * @q_lock: struct &mutex lock
+ * @new_frame: valid in the device_run callback: if true, then this
+ *		starts a new frame; if false, then this is a new slice
+ *		for an existing frame. This is always true unless
+ *		V4L2_BUF_CAP_SUPPORTS_M2M_HOLD_CAPTURE_BUF is set, which
+ *		indicates slicing support.
  * @m2m_dev: opaque pointer to the internal data to handle M2M context
  * @cap_q_ctx: Capture (output to memory) queue context
  * @out_q_ctx: Output (input from memory) queue context
@@ -89,6 +96,8 @@ struct v4l2_m2m_ctx {
 	/* optional cap/out vb2 queues lock */
 	struct mutex			*q_lock;
 
+	bool				new_frame;
+
 	/* internal use only */
 	struct v4l2_m2m_dev		*m2m_dev;
 
@@ -173,6 +182,33 @@ void v4l2_m2m_try_schedule(struct v4l2_m2m_ctx *m2m_ctx);
 void v4l2_m2m_job_finish(struct v4l2_m2m_dev *m2m_dev,
 			 struct v4l2_m2m_ctx *m2m_ctx);
 
+/**
+ * v4l2_m2m_buf_done_and_job_finish() - return source/destination buffers with
+ * state and inform the framework that a job has been finished and have it
+ * clean up
+ *
+ * @m2m_dev: opaque pointer to the internal data to handle M2M context
+ * @m2m_ctx: m2m context assigned to the instance given by struct &v4l2_m2m_ctx
+ * @state: vb2 buffer state passed to v4l2_m2m_buf_done().
+ *
+ * Drivers that set V4L2_BUF_CAP_SUPPORTS_M2M_HOLD_CAPTURE_BUF must use this
+ * function instead of job_finish() to take held buffers into account. It is
+ * optional for other drivers.
+ *
+ * This function removes the source buffer from the ready list and returns
+ * it with the given state. The same is done for the destination buffer, unless
+ * it is marked 'held'. In that case the buffer is kept on the ready list.
+ *
+ * After that the job is finished (see job_finish()).
+ *
+ * This allows for multiple output buffers to be used to fill in a single
+ * capture buffer. This is typically used by stateless decoders where
+ * multiple e.g. H.264 slices contribute to a single decoded frame.
+ */
+void v4l2_m2m_buf_done_and_job_finish(struct v4l2_m2m_dev *m2m_dev,
+				      struct v4l2_m2m_ctx *m2m_ctx,
+				      enum vb2_buffer_state state);
+
 static inline void
 v4l2_m2m_buf_done(struct vb2_v4l2_buffer *buf, enum vb2_buffer_state state)
 {
@@ -672,6 +708,10 @@ int v4l2_m2m_ioctl_try_encoder_cmd(struct file *file, void *fh,
 				   struct v4l2_encoder_cmd *ec);
 int v4l2_m2m_ioctl_try_decoder_cmd(struct file *file, void *fh,
 				   struct v4l2_decoder_cmd *dc);
+int v4l2_m2m_ioctl_stateless_try_decoder_cmd(struct file *file, void *fh,
+					     struct v4l2_decoder_cmd *dc);
+int v4l2_m2m_ioctl_stateless_decoder_cmd(struct file *file, void *priv,
+					 struct v4l2_decoder_cmd *dc);
 int v4l2_m2m_fop_mmap(struct file *file, struct vm_area_struct *vma);
 __poll_t v4l2_m2m_fop_poll(struct file *file, poll_table *wait);
 
diff --git a/include/media/videobuf2-core.h b/include/media/videobuf2-core.h
index 640aabe69450..a2b2208b02da 100644
--- a/include/media/videobuf2-core.h
+++ b/include/media/videobuf2-core.h
@@ -505,6 +505,8 @@ struct vb2_buf_ops {
  * @buf_ops:	callbacks to deliver buffer information.
  *		between user-space and kernel-space.
  * @drv_priv:	driver private data.
+ * @subsystem_flags: Flags specific to the subsystem (V4L2/DVB/etc.). Not used
+ *		by the vb2 core.
  * @buf_struct_size: size of the driver-specific buffer structure;
  *		"0" indicates the driver doesn't want to use a custom buffer
  *		structure type. for example, ``sizeof(struct vb2_v4l2_buffer)``
@@ -571,6 +573,7 @@ struct vb2_queue {
 	const struct vb2_buf_ops	*buf_ops;
 
 	void				*drv_priv;
+	u32				subsystem_flags;
 	unsigned int			buf_struct_size;
 	u32				timestamp_flags;
 	gfp_t				gfp_flags;
diff --git a/include/media/videobuf2-v4l2.h b/include/media/videobuf2-v4l2.h
index 8a10889dc2fd..59bf33a12648 100644
--- a/include/media/videobuf2-v4l2.h
+++ b/include/media/videobuf2-v4l2.h
@@ -33,6 +33,7 @@
  * @timecode:	frame timecode.
  * @sequence:	sequence count of this frame.
  * @request_fd:	the request_fd associated with this buffer
+ * @is_held:	if true, then this capture buffer was held
  * @planes:	plane information (userptr/fd, length, bytesused, data_offset).
  *
  * Should contain enough information to be able to cover all the fields
@@ -46,9 +47,13 @@ struct vb2_v4l2_buffer {
 	struct v4l2_timecode	timecode;
 	__u32			sequence;
 	__s32			request_fd;
+	bool			is_held;
 	struct vb2_plane	planes[VB2_MAX_PLANES];
 };
 
+/* VB2 V4L2 flags as set in vb2_queue.subsystem_flags */
+#define VB2_V4L2_FL_SUPPORTS_M2M_HOLD_CAPTURE_BUF (1 << 0)
+
 /*
  * to_vb2_v4l2_buffer() - cast struct vb2_buffer * to struct vb2_v4l2_buffer *
  */
diff --git a/include/net/sock.h b/include/net/sock.h
index e7f697174f84..87d54ef57f00 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -1488,7 +1488,7 @@ static inline void sock_release_ownership(struct sock *sk)
 		sk->sk_lock.owned = 0;
 
 		/* The sk_lock has mutex_unlock() semantics: */
-		mutex_release(&sk->sk_lock.dep_map, 1, _RET_IP_);
+		mutex_release(&sk->sk_lock.dep_map, _RET_IP_);
 	}
 }
 
diff --git a/include/sound/core.h b/include/sound/core.h
index ee238f100f73..af3dce956c17 100644
--- a/include/sound/core.h
+++ b/include/sound/core.h
@@ -117,6 +117,7 @@ struct snd_card {
 	struct device card_dev;		/* cardX object for sysfs */
 	const struct attribute_group *dev_groups[4]; /* assigned sysfs attr */
 	bool registered;		/* card_dev is registered? */
+	int sync_irq;			/* assigned irq, used for PCM sync */
 	wait_queue_head_t remove_sleep;
 
 #ifdef CONFIG_PM
diff --git a/include/sound/dmaengine_pcm.h b/include/sound/dmaengine_pcm.h
index c679f6116580..b65220685920 100644
--- a/include/sound/dmaengine_pcm.h
+++ b/include/sound/dmaengine_pcm.h
@@ -83,6 +83,11 @@ void snd_dmaengine_pcm_set_config_from_dai_data(
 	const struct snd_dmaengine_dai_dma_data *dma_data,
 	struct dma_slave_config *config);
 
+int snd_dmaengine_pcm_refine_runtime_hwparams(
+	struct snd_pcm_substream *substream,
+	struct snd_dmaengine_dai_dma_data *dma_data,
+	struct snd_pcm_hardware *hw,
+	struct dma_chan *chan);
 
 /*
  * Try to request the DMA channel using compat_request_channel or
diff --git a/include/sound/hda_codec.h b/include/sound/hda_codec.h
index 9a0393cf024c..ac18f428eda6 100644
--- a/include/sound/hda_codec.h
+++ b/include/sound/hda_codec.h
@@ -254,6 +254,7 @@ struct hda_codec {
 	unsigned int force_pin_prefix:1; /* Add location prefix */
 	unsigned int link_down_at_suspend:1; /* link down at runtime suspend */
 	unsigned int relaxed_resume:1;	/* don't resume forcibly for jack */
+	unsigned int mst_no_extra_pcms:1; /* no backup PCMs for DP-MST */
 
 #ifdef CONFIG_PM
 	unsigned long power_on_acct;
diff --git a/include/sound/intel-dsp-config.h b/include/sound/intel-dsp-config.h
new file mode 100644
index 000000000000..c36622bee3f8
--- /dev/null
+++ b/include/sound/intel-dsp-config.h
@@ -0,0 +1,34 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ *  intel-dsp-config.h - Intel DSP config
+ *
+ *  Copyright (c) 2019 Jaroslav Kysela <perex@perex.cz>
+ */
+
+#ifndef __INTEL_DSP_CONFIG_H__
+#define __INTEL_DSP_CONFIG_H__
+
+struct pci_dev;
+
+enum {
+	SND_INTEL_DSP_DRIVER_ANY = 0,
+	SND_INTEL_DSP_DRIVER_LEGACY,
+	SND_INTEL_DSP_DRIVER_SST,
+	SND_INTEL_DSP_DRIVER_SOF,
+	SND_INTEL_DSP_DRIVER_LAST = SND_INTEL_DSP_DRIVER_SOF
+};
+
+#if IS_ENABLED(CONFIG_SND_INTEL_DSP_CONFIG)
+
+int snd_intel_dsp_driver_probe(struct pci_dev *pci);
+
+#else
+
+static inline int snd_intel_dsp_driver_probe(struct pci_dev *pci)
+{
+	return SND_INTEL_DSP_DRIVER_ANY;
+}
+
+#endif
+
+#endif
diff --git a/include/sound/memalloc.h b/include/sound/memalloc.h
index 240622d89c0b..3b47832b1c1f 100644
--- a/include/sound/memalloc.h
+++ b/include/sound/memalloc.h
@@ -21,7 +21,6 @@ struct snd_dma_device {
 	struct device *dev;		/* generic device */
 };
 
-#define snd_dma_pci_data(pci)	(&(pci)->dev)
 #define snd_dma_continuous_data(x)	((struct device *)(__force unsigned long)(x))
 
 
@@ -44,6 +43,7 @@ struct snd_dma_device {
 #else
 #define SNDRV_DMA_TYPE_DEV_IRAM	SNDRV_DMA_TYPE_DEV
 #endif
+#define SNDRV_DMA_TYPE_VMALLOC		7	/* vmalloc'ed buffer */
 
 /*
  * info for buffer allocation
diff --git a/include/sound/pcm.h b/include/sound/pcm.h
index bbe6eb1ff5d2..8a89fa6fdd5e 100644
--- a/include/sound/pcm.h
+++ b/include/sound/pcm.h
@@ -59,6 +59,7 @@ struct snd_pcm_ops {
 	int (*hw_free)(struct snd_pcm_substream *substream);
 	int (*prepare)(struct snd_pcm_substream *substream);
 	int (*trigger)(struct snd_pcm_substream *substream, int cmd);
+	int (*sync_stop)(struct snd_pcm_substream *substream);
 	snd_pcm_uframes_t (*pointer)(struct snd_pcm_substream *substream);
 	int (*get_time_info)(struct snd_pcm_substream *substream,
 			struct timespec *system_ts, struct timespec *audio_ts,
@@ -395,6 +396,7 @@ struct snd_pcm_runtime {
 	wait_queue_head_t sleep;	/* poll sleep */
 	wait_queue_head_t tsleep;	/* transfer sleep */
 	struct fasync_struct *fasync;
+	bool stop_operating;		/* sync_stop will be called */
 
 	/* -- private section -- */
 	void *private_data;
@@ -414,6 +416,7 @@ struct snd_pcm_runtime {
 	size_t dma_bytes;		/* size of DMA area */
 
 	struct snd_dma_buffer *dma_buffer_p;	/* allocated buffer */
+	unsigned int buffer_changed:1;	/* buffer allocation changed; set only in managed mode */
 
 	/* -- audio timestamp config -- */
 	struct snd_pcm_audio_tstamp_config audio_tstamp_config;
@@ -475,6 +478,7 @@ struct snd_pcm_substream {
 #endif /* CONFIG_SND_VERBOSE_PROCFS */
 	/* misc flags */
 	unsigned int hw_opened: 1;
+	unsigned int managed_buffer_alloc:1;
 };
 
 #define SUBSTREAM_BUSY(substream) ((substream)->ref_count > 0)
@@ -1186,6 +1190,12 @@ void snd_pcm_lib_preallocate_pages_for_all(struct snd_pcm *pcm,
 int snd_pcm_lib_malloc_pages(struct snd_pcm_substream *substream, size_t size);
 int snd_pcm_lib_free_pages(struct snd_pcm_substream *substream);
 
+void snd_pcm_set_managed_buffer(struct snd_pcm_substream *substream, int type,
+				struct device *data, size_t size, size_t max);
+void snd_pcm_set_managed_buffer_all(struct snd_pcm *pcm, int type,
+				    struct device *data,
+				    size_t size, size_t max);
+
 int _snd_pcm_lib_alloc_vmalloc_buffer(struct snd_pcm_substream *substream,
 				      size_t size, gfp_t gfp_flags);
 int snd_pcm_lib_free_vmalloc_buffer(struct snd_pcm_substream *substream);
@@ -1236,14 +1246,6 @@ static inline int snd_pcm_lib_alloc_vmalloc_32_buffer
  */
 #define snd_pcm_substream_sgbuf(substream) \
 	snd_pcm_get_dma_buf(substream)->private_data
-
-struct page *snd_pcm_sgbuf_ops_page(struct snd_pcm_substream *substream,
-				    unsigned long offset);
-#else /* !SND_DMA_SGBUF */
-/*
- * fake using a continuous buffer
- */
-#define snd_pcm_sgbuf_ops_page	NULL
 #endif /* SND_DMA_SGBUF */
 
 /**
@@ -1336,8 +1338,6 @@ static inline void snd_pcm_limit_isa_dma_size(int dma, size_t *max)
 					 (IEC958_AES1_CON_PCM_CODER<<8)|\
 					 (IEC958_AES3_CON_FS_48000<<24))
 
-#define PCM_RUNTIME_CHECK(sub) snd_BUG_ON(!(sub) || !(sub)->runtime)
-
 const char *snd_pcm_format_name(snd_pcm_format_t format);
 
 /**
diff --git a/include/sound/pxa2xx-lib.h b/include/sound/pxa2xx-lib.h
index 6758fc12fa84..0feaf16e6ac0 100644
--- a/include/sound/pxa2xx-lib.h
+++ b/include/sound/pxa2xx-lib.h
@@ -10,6 +10,7 @@ struct snd_pcm_substream;
 struct snd_pcm_hw_params;
 struct snd_soc_pcm_runtime;
 struct snd_pcm;
+struct snd_soc_component;
 
 extern int pxa2xx_pcm_hw_params(struct snd_pcm_substream *substream,
 				struct snd_pcm_hw_params *params);
@@ -23,8 +24,29 @@ extern int pxa2xx_pcm_mmap(struct snd_pcm_substream *substream,
 	struct vm_area_struct *vma);
 extern int pxa2xx_pcm_preallocate_dma_buffer(struct snd_pcm *pcm, int stream);
 extern void pxa2xx_pcm_free_dma_buffers(struct snd_pcm *pcm);
-extern int pxa2xx_soc_pcm_new(struct snd_soc_pcm_runtime *rtd);
-extern const struct snd_pcm_ops pxa2xx_pcm_ops;
+extern void pxa2xx_soc_pcm_free(struct snd_soc_component *component,
+				struct snd_pcm *pcm);
+extern int pxa2xx_soc_pcm_new(struct snd_soc_component *component,
+			      struct snd_soc_pcm_runtime *rtd);
+extern int pxa2xx_soc_pcm_open(struct snd_soc_component *component,
+			       struct snd_pcm_substream *substream);
+extern int pxa2xx_soc_pcm_close(struct snd_soc_component *component,
+				struct snd_pcm_substream *substream);
+extern int pxa2xx_soc_pcm_hw_params(struct snd_soc_component *component,
+				    struct snd_pcm_substream *substream,
+				    struct snd_pcm_hw_params *params);
+extern int pxa2xx_soc_pcm_hw_free(struct snd_soc_component *component,
+				  struct snd_pcm_substream *substream);
+extern int pxa2xx_soc_pcm_prepare(struct snd_soc_component *component,
+				  struct snd_pcm_substream *substream);
+extern int pxa2xx_soc_pcm_trigger(struct snd_soc_component *component,
+				  struct snd_pcm_substream *substream, int cmd);
+extern snd_pcm_uframes_t
+pxa2xx_soc_pcm_pointer(struct snd_soc_component *component,
+		       struct snd_pcm_substream *substream);
+extern int pxa2xx_soc_pcm_mmap(struct snd_soc_component *component,
+			       struct snd_pcm_substream *substream,
+			       struct vm_area_struct *vma);
 
 /* AC97 */
 
diff --git a/include/sound/rt5682.h b/include/sound/rt5682.h
index bf2ee75aabb1..bc2c31734df1 100644
--- a/include/sound/rt5682.h
+++ b/include/sound/rt5682.h
@@ -31,6 +31,7 @@ struct rt5682_platform_data {
 	enum rt5682_dmic1_data_pin dmic1_data_pin;
 	enum rt5682_dmic1_clk_pin dmic1_clk_pin;
 	enum rt5682_jd_src jd_src;
+	unsigned int btndet_delay;
 };
 
 #endif
diff --git a/include/sound/simple_card_utils.h b/include/sound/simple_card_utils.h
index 31f76b6abf71..bbdd1542d6f1 100644
--- a/include/sound/simple_card_utils.h
+++ b/include/sound/simple_card_utils.h
@@ -8,6 +8,7 @@
 #ifndef __SIMPLE_CARD_UTILS_H
 #define __SIMPLE_CARD_UTILS_H
 
+#include <linux/clk.h>
 #include <sound/soc.h>
 
 #define asoc_simple_init_hp(card, sjack, prefix) \
diff --git a/include/sound/soc-acpi-intel-match.h b/include/sound/soc-acpi-intel-match.h
index 6c9929abd90b..20c0bee3b959 100644
--- a/include/sound/soc-acpi-intel-match.h
+++ b/include/sound/soc-acpi-intel-match.h
@@ -24,9 +24,12 @@ extern struct snd_soc_acpi_mach snd_soc_acpi_intel_kbl_machines[];
 extern struct snd_soc_acpi_mach snd_soc_acpi_intel_bxt_machines[];
 extern struct snd_soc_acpi_mach snd_soc_acpi_intel_glk_machines[];
 extern struct snd_soc_acpi_mach snd_soc_acpi_intel_cnl_machines[];
+extern struct snd_soc_acpi_mach snd_soc_acpi_intel_cfl_machines[];
+extern struct snd_soc_acpi_mach snd_soc_acpi_intel_cml_machines[];
 extern struct snd_soc_acpi_mach snd_soc_acpi_intel_icl_machines[];
 extern struct snd_soc_acpi_mach snd_soc_acpi_intel_tgl_machines[];
 extern struct snd_soc_acpi_mach snd_soc_acpi_intel_ehl_machines[];
+extern struct snd_soc_acpi_mach snd_soc_acpi_intel_jsl_machines[];
 
 /*
  * generic table used for HDA codec-based platforms, possibly with
diff --git a/include/sound/soc-acpi.h b/include/sound/soc-acpi.h
index 35b38e41e5b2..c4c997bd0379 100644
--- a/include/sound/soc-acpi.h
+++ b/include/sound/soc-acpi.h
@@ -60,12 +60,14 @@ static inline struct snd_soc_acpi_mach *snd_soc_acpi_codec_list(void *arg)
  * @acpi_ipc_irq_index: used for BYT-CR detection
  * @platform: string used for HDaudio codec support
  * @codec_mask: used for HDAudio support
+ * @common_hdmi_codec_drv: use commom HDAudio HDMI codec driver
  */
 struct snd_soc_acpi_mach_params {
 	u32 acpi_ipc_irq_index;
 	const char *platform;
 	u32 codec_mask;
 	u32 dmic_num;
+	bool common_hdmi_codec_drv;
 };
 
 /**
@@ -75,6 +77,7 @@ struct snd_soc_acpi_mach_params {
  * all firmware/topology related fields.
  *
  * @id: ACPI ID (usually the codec's) used to find a matching machine driver.
+ * @link_mask: describes required board layout, e.g. for SoundWire.
  * @drv_name: machine driver name
  * @fw_filename: firmware file name. Used when SOF is not enabled.
  * @board: board name
@@ -90,6 +93,7 @@ struct snd_soc_acpi_mach_params {
 /* Descriptor for SST ASoC machine driver */
 struct snd_soc_acpi_mach {
 	const u8 id[ACPI_ID_LEN];
+	const u32 link_mask;
 	const char *drv_name;
 	const char *fw_filename;
 	const char *board;
diff --git a/include/sound/soc-component.h b/include/sound/soc-component.h
index 5d80b2eef525..506f72a6b2c2 100644
--- a/include/sound/soc-component.h
+++ b/include/sound/soc-component.h
@@ -3,10 +3,6 @@
  * soc-component.h
  *
  * Copyright (c) 2019 Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
  */
 #ifndef __SOC_COMPONENT_H
 #define __SOC_COMPONENT_H
@@ -51,8 +47,10 @@ struct snd_soc_component_driver {
 		     unsigned int reg, unsigned int val);
 
 	/* pcm creation and destruction */
-	int (*pcm_new)(struct snd_soc_pcm_runtime *rtd);
-	void (*pcm_free)(struct snd_pcm *pcm);
+	int (*pcm_construct)(struct snd_soc_component *component,
+			     struct snd_soc_pcm_runtime *rtd);
+	void (*pcm_destruct)(struct snd_soc_component *component,
+			     struct snd_pcm *pcm);
 
 	/* component wide operations */
 	int (*set_sysclk)(struct snd_soc_component *component,
@@ -74,7 +72,42 @@ struct snd_soc_component_driver {
 	int (*set_bias_level)(struct snd_soc_component *component,
 			      enum snd_soc_bias_level level);
 
-	const struct snd_pcm_ops *ops;
+	int (*open)(struct snd_soc_component *component,
+		    struct snd_pcm_substream *substream);
+	int (*close)(struct snd_soc_component *component,
+		     struct snd_pcm_substream *substream);
+	int (*ioctl)(struct snd_soc_component *component,
+		     struct snd_pcm_substream *substream,
+		     unsigned int cmd, void *arg);
+	int (*hw_params)(struct snd_soc_component *component,
+			 struct snd_pcm_substream *substream,
+			 struct snd_pcm_hw_params *params);
+	int (*hw_free)(struct snd_soc_component *component,
+		       struct snd_pcm_substream *substream);
+	int (*prepare)(struct snd_soc_component *component,
+		       struct snd_pcm_substream *substream);
+	int (*trigger)(struct snd_soc_component *component,
+		       struct snd_pcm_substream *substream, int cmd);
+	int (*sync_stop)(struct snd_soc_component *component,
+			 struct snd_pcm_substream *substream);
+	snd_pcm_uframes_t (*pointer)(struct snd_soc_component *component,
+				     struct snd_pcm_substream *substream);
+	int (*get_time_info)(struct snd_soc_component *component,
+		struct snd_pcm_substream *substream, struct timespec *system_ts,
+		struct timespec *audio_ts,
+		struct snd_pcm_audio_tstamp_config *audio_tstamp_config,
+		struct snd_pcm_audio_tstamp_report *audio_tstamp_report);
+	int (*copy_user)(struct snd_soc_component *component,
+			 struct snd_pcm_substream *substream, int channel,
+			 unsigned long pos, void __user *buf,
+			 unsigned long bytes);
+	struct page *(*page)(struct snd_soc_component *component,
+			     struct snd_pcm_substream *substream,
+			     unsigned long offset);
+	int (*mmap)(struct snd_soc_component *component,
+		    struct snd_pcm_substream *substream,
+		    struct vm_area_struct *vma);
+
 	const struct snd_compr_ops *compr_ops;
 
 	/* probe ordering - for components with runtime dependencies */
@@ -374,6 +407,7 @@ int snd_soc_component_of_xlate_dai_name(struct snd_soc_component *component,
 int snd_soc_pcm_component_pointer(struct snd_pcm_substream *substream);
 int snd_soc_pcm_component_ioctl(struct snd_pcm_substream *substream,
 				unsigned int cmd, void *arg);
+int snd_soc_pcm_component_sync_stop(struct snd_pcm_substream *substream);
 int snd_soc_pcm_component_copy_user(struct snd_pcm_substream *substream,
 				    int channel, unsigned long pos,
 				    void __user *buf, unsigned long bytes);
@@ -381,7 +415,7 @@ struct page *snd_soc_pcm_component_page(struct snd_pcm_substream *substream,
 					unsigned long offset);
 int snd_soc_pcm_component_mmap(struct snd_pcm_substream *substream,
 			       struct vm_area_struct *vma);
-int snd_soc_pcm_component_new(struct snd_pcm *pcm);
-void snd_soc_pcm_component_free(struct snd_pcm *pcm);
+int snd_soc_pcm_component_new(struct snd_soc_pcm_runtime *rtd);
+void snd_soc_pcm_component_free(struct snd_soc_pcm_runtime *rtd);
 
 #endif /* __SOC_COMPONENT_H */
diff --git a/include/sound/soc-dpcm.h b/include/sound/soc-dpcm.h
index e55aeb00ce2d..b654ebfc8766 100644
--- a/include/sound/soc-dpcm.h
+++ b/include/sound/soc-dpcm.h
@@ -103,15 +103,15 @@ struct snd_soc_dpcm_runtime {
 	int trigger_pending; /* trigger cmd + 1 if pending, 0 if not */
 };
 
-#define for_each_dpcm_fe(be, stream, dpcm)				\
-	list_for_each_entry(dpcm, &(be)->dpcm[stream].fe_clients, list_fe)
-
-#define for_each_dpcm_be(fe, stream, dpcm)				\
-	list_for_each_entry(dpcm, &(fe)->dpcm[stream].be_clients, list_be)
-#define for_each_dpcm_be_safe(fe, stream, dpcm, _dpcm)			\
-	list_for_each_entry_safe(dpcm, _dpcm, &(fe)->dpcm[stream].be_clients, list_be)
-#define for_each_dpcm_be_rollback(fe, stream, dpcm)			\
-	list_for_each_entry_continue_reverse(dpcm, &(fe)->dpcm[stream].be_clients, list_be)
+#define for_each_dpcm_fe(be, stream, _dpcm)				\
+	list_for_each_entry(_dpcm, &(be)->dpcm[stream].fe_clients, list_fe)
+
+#define for_each_dpcm_be(fe, stream, _dpcm)				\
+	list_for_each_entry(_dpcm, &(fe)->dpcm[stream].be_clients, list_be)
+#define for_each_dpcm_be_safe(fe, stream, _dpcm, __dpcm)			\
+	list_for_each_entry_safe(_dpcm, __dpcm, &(fe)->dpcm[stream].be_clients, list_be)
+#define for_each_dpcm_be_rollback(fe, stream, _dpcm)			\
+	list_for_each_entry_continue_reverse(_dpcm, &(fe)->dpcm[stream].be_clients, list_be)
 
 /* can this BE stop and free */
 int snd_soc_dpcm_can_be_free_stop(struct snd_soc_pcm_runtime *fe,
diff --git a/include/sound/soc.h b/include/sound/soc.h
index f264c6509f00..c28a1ed5e8df 100644
--- a/include/sound/soc.h
+++ b/include/sound/soc.h
@@ -299,6 +299,12 @@
 	.put = snd_soc_bytes_put, .private_value =	      \
 		((unsigned long)&(struct soc_bytes)           \
 		{.base = xbase, .num_regs = xregs }) }
+#define SND_SOC_BYTES_E(xname, xbase, xregs, xhandler_get, xhandler_put) \
+{	.iface = SNDRV_CTL_ELEM_IFACE_MIXER, .name = xname, \
+	.info = snd_soc_bytes_info, .get = xhandler_get, \
+	.put = xhandler_put, .private_value = \
+		((unsigned long)&(struct soc_bytes) \
+		{.base = xbase, .num_regs = xregs }) }
 
 #define SND_SOC_BYTES_MASK(xname, xbase, xregs, xmask)	      \
 {	.iface = SNDRV_CTL_ELEM_IFACE_MIXER, .name = xname,   \
@@ -739,10 +745,12 @@ struct snd_soc_rtdcom_list {
 struct snd_soc_component*
 snd_soc_rtdcom_lookup(struct snd_soc_pcm_runtime *rtd,
 		       const char *driver_name);
-#define for_each_rtdcom(rtd, rtdcom) \
-	list_for_each_entry(rtdcom, &(rtd)->component_list, list)
-#define for_each_rtdcom_safe(rtd, rtdcom1, rtdcom2) \
-	list_for_each_entry_safe(rtdcom1, rtdcom2, &(rtd)->component_list, list)
+#define for_each_rtd_components(rtd, rtdcom, _component)		\
+	for (rtdcom = list_first_entry(&(rtd)->component_list,		\
+				       typeof(*rtdcom), list);		\
+	     (&rtdcom->list != &(rtd)->component_list) &&		\
+		     (_component = rtdcom->component);			\
+	     rtdcom = list_next_entry(rtdcom, list))
 
 struct snd_soc_dai_link_component {
 	const char *name;
@@ -845,7 +853,9 @@ struct snd_soc_dai_link {
 	unsigned int ignore:1;
 
 	struct list_head list; /* DAI link list of the soc card */
+#ifdef CONFIG_SND_SOC_TOPOLOGY
 	struct snd_soc_dobj dobj; /* For topology */
+#endif
 };
 #define for_each_link_codecs(link, i, codec)				\
 	for ((i) = 0;							\
@@ -978,6 +988,7 @@ struct snd_soc_card {
 	const char *name;
 	const char *long_name;
 	const char *driver_name;
+	const char *components;
 	char dmi_longname[80];
 	char topology_shortname[32];
 
@@ -1148,7 +1159,6 @@ struct snd_soc_pcm_runtime {
 	struct list_head component_list; /* list of connected components */
 
 	/* bit field */
-	unsigned int dev_registered:1;
 	unsigned int pop_wait:1;
 	unsigned int fe_compr:1; /* for Dynamic PCM */
 };
@@ -1168,7 +1178,9 @@ struct soc_mixer_control {
 	unsigned int sign_bit;
 	unsigned int invert:1;
 	unsigned int autodisable:1;
+#ifdef CONFIG_SND_SOC_TOPOLOGY
 	struct snd_soc_dobj dobj;
+#endif
 };
 
 struct soc_bytes {
@@ -1179,8 +1191,9 @@ struct soc_bytes {
 
 struct soc_bytes_ext {
 	int max;
+#ifdef CONFIG_SND_SOC_TOPOLOGY
 	struct snd_soc_dobj dobj;
-
+#endif
 	/* used for TLV byte control */
 	int (*get)(struct snd_kcontrol *kcontrol, unsigned int __user *bytes,
 			unsigned int size);
@@ -1204,7 +1217,9 @@ struct soc_enum {
 	const char * const *texts;
 	const unsigned int *values;
 	unsigned int autodisable:1;
+#ifdef CONFIG_SND_SOC_TOPOLOGY
 	struct snd_soc_dobj dobj;
+#endif
 };
 
 /* device driver data */
@@ -1325,8 +1340,10 @@ struct snd_soc_dai_link *snd_soc_find_dai_link(struct snd_soc_card *card,
 					       int id, const char *name,
 					       const char *stream_name);
 
-int snd_soc_register_dai(struct snd_soc_component *component,
-	struct snd_soc_dai_driver *dai_drv);
+struct snd_soc_dai *snd_soc_register_dai(struct snd_soc_component *component,
+					 struct snd_soc_dai_driver *dai_drv,
+					 bool legacy_dai_naming);
+void snd_soc_unregister_dai(struct snd_soc_dai *dai);
 
 struct snd_soc_dai *snd_soc_find_dai(
 	const struct snd_soc_dai_link_component *dlc);
@@ -1391,6 +1408,11 @@ static inline void snd_soc_dapm_mutex_unlock(struct snd_soc_dapm_context *dapm)
 	mutex_unlock(&dapm->card->dapm_mutex);
 }
 
+/* bypass */
+int snd_soc_pcm_lib_ioctl(struct snd_soc_component *component,
+			  struct snd_pcm_substream *substream,
+			  unsigned int cmd, void *arg);
+
 #include <sound/soc-component.h>
 
 #endif
diff --git a/include/sound/sof.h b/include/sound/sof.h
index 4640566b54fe..479101736ee0 100644
--- a/include/sound/sof.h
+++ b/include/sound/sof.h
@@ -61,6 +61,9 @@ struct sof_dev_desc {
 	/* list of machines using this configuration */
 	struct snd_soc_acpi_mach *machines;
 
+	/* alternate list of machines using this configuration */
+	struct snd_soc_acpi_mach *alt_machines;
+
 	/* Platform resource indexes in BAR / ACPI resources. */
 	/* Must set to -1 if not used - add new items to end */
 	int resindex_lpe_base;
diff --git a/include/sound/sof/dai-imx.h b/include/sound/sof/dai-imx.h
new file mode 100644
index 000000000000..e02fb0b0fae1
--- /dev/null
+++ b/include/sound/sof/dai-imx.h
@@ -0,0 +1,34 @@
+/* SPDX-License-Identifier: (GPL-2.0 OR BSD-3-Clause) */
+/*
+ * Copyright 2019 NXP
+ *
+ * Author: Daniel Baluta <daniel.baluta@nxp.com>
+ */
+
+#ifndef __INCLUDE_SOUND_SOF_DAI_IMX_H__
+#define __INCLUDE_SOUND_SOF_DAI_IMX_H__
+
+#include <sound/sof/header.h>
+
+/* ESAI Configuration Request - SOF_IPC_DAI_ESAI_CONFIG */
+struct sof_ipc_dai_esai_params {
+	struct sof_ipc_hdr hdr;
+
+	/* MCLK */
+	uint16_t reserved1;
+	uint16_t mclk_id;
+	uint32_t mclk_direction;
+
+	uint32_t mclk_rate;	/* MCLK frequency in Hz */
+	uint32_t fsync_rate;	/* FSYNC frequency in Hz */
+	uint32_t bclk_rate;	/* BCLK frequency in Hz */
+
+	/* TDM */
+	uint32_t tdm_slots;
+	uint32_t rx_slots;
+	uint32_t tx_slots;
+	uint16_t tdm_slot_width;
+	uint16_t reserved2;	/* alignment */
+} __packed;
+
+#endif
diff --git a/include/sound/sof/dai.h b/include/sound/sof/dai.h
index 0f1235022146..c229565767e5 100644
--- a/include/sound/sof/dai.h
+++ b/include/sound/sof/dai.h
@@ -11,6 +11,7 @@
 
 #include <sound/sof/header.h>
 #include <sound/sof/dai-intel.h>
+#include <sound/sof/dai-imx.h>
 
 /*
  * DAI Configuration.
@@ -73,6 +74,7 @@ struct sof_ipc_dai_config {
 		struct sof_ipc_dai_dmic_params dmic;
 		struct sof_ipc_dai_hda_params hda;
 		struct sof_ipc_dai_alh_params alh;
+		struct sof_ipc_dai_esai_params esai;
 	};
 } __packed;
 
diff --git a/include/sound/sof/header.h b/include/sound/sof/header.h
index 10f00c08dbb7..bf3edd9c08b4 100644
--- a/include/sound/sof/header.h
+++ b/include/sound/sof/header.h
@@ -9,6 +9,7 @@
 #ifndef __INCLUDE_SOUND_SOF_HEADER_H__
 #define __INCLUDE_SOUND_SOF_HEADER_H__
 
+#include <linux/types.h>
 #include <uapi/sound/sof/abi.h>
 
 /** \addtogroup sof_uapi uAPI
@@ -74,6 +75,7 @@
 #define SOF_IPC_PM_CLK_GET			SOF_CMD_TYPE(0x005)
 #define SOF_IPC_PM_CLK_REQ			SOF_CMD_TYPE(0x006)
 #define SOF_IPC_PM_CORE_ENABLE			SOF_CMD_TYPE(0x007)
+#define SOF_IPC_PM_GATE				SOF_CMD_TYPE(0x008)
 
 /* component runtime config - multiple different types */
 #define SOF_IPC_COMP_SET_VALUE			SOF_CMD_TYPE(0x001)
diff --git a/include/sound/sof/pm.h b/include/sound/sof/pm.h
index 003879401d63..3cf2e0f39d94 100644
--- a/include/sound/sof/pm.h
+++ b/include/sound/sof/pm.h
@@ -45,4 +45,12 @@ struct sof_ipc_pm_core_config {
 	uint32_t enable_mask;
 } __packed;
 
+struct sof_ipc_pm_gate {
+	struct sof_ipc_cmd_hdr hdr;
+	uint32_t flags;	/* platform specific */
+
+	/* reserved for future use */
+	uint32_t reserved[5];
+} __packed;
+
 #endif
diff --git a/include/sound/sof/stream.h b/include/sound/sof/stream.h
index 0b71b381b952..7facefb541b3 100644
--- a/include/sound/sof/stream.h
+++ b/include/sound/sof/stream.h
@@ -83,10 +83,10 @@ struct sof_ipc_stream_params {
 	uint16_t sample_valid_bytes;
 	uint16_t sample_container_bytes;
 
-	/* for notifying host period has completed - 0 means no period IRQ */
 	uint32_t host_period_bytes;
+	uint16_t no_stream_position; /**< 1 means don't send stream position */
 
-	uint32_t reserved[2];
+	uint16_t reserved[3];
 	uint16_t chmap[SOF_IPC_MAX_CHANNELS];	/**< channel map - SOF_CHMAP_ */
 } __packed;
 
diff --git a/include/sound/timer.h b/include/sound/timer.h
index 199c36295a0d..a53e37bcd746 100644
--- a/include/sound/timer.h
+++ b/include/sound/timer.h
@@ -118,8 +118,10 @@ int snd_timer_global_new(char *id, int device, struct snd_timer **rtimer);
 int snd_timer_global_free(struct snd_timer *timer);
 int snd_timer_global_register(struct snd_timer *timer);
 
-int snd_timer_open(struct snd_timer_instance **ti, char *owner, struct snd_timer_id *tid, unsigned int slave_id);
-int snd_timer_close(struct snd_timer_instance *timeri);
+struct snd_timer_instance *snd_timer_instance_new(const char *owner);
+void snd_timer_instance_free(struct snd_timer_instance *timeri);
+int snd_timer_open(struct snd_timer_instance *timeri, struct snd_timer_id *tid, unsigned int slave_id);
+void snd_timer_close(struct snd_timer_instance *timeri);
 unsigned long snd_timer_resolution(struct snd_timer_instance *timeri);
 int snd_timer_start(struct snd_timer_instance *timeri, unsigned int ticks);
 int snd_timer_stop(struct snd_timer_instance *timeri);
diff --git a/include/sound/wm8904.h b/include/sound/wm8904.h
index 14074405f501..88ac1870510e 100644
--- a/include/sound/wm8904.h
+++ b/include/sound/wm8904.h
@@ -120,7 +120,7 @@
  * DRC configurations are specified with a label and a set of register
  * values to write (the enable bits will be ignored).  At runtime an
  * enumerated control will be presented for each DRC block allowing
- * the user to choose the configration to use.
+ * the user to choose the configuration to use.
  *
  * Configurations may be generated by hand or by using the DRC control
  * panel provided by the WISCE - see  http://www.wolfsonmicro.com/wisce/
diff --git a/include/trace/events/rcu.h b/include/trace/events/rcu.h
index 694bd040cf51..66122602bd08 100644
--- a/include/trace/events/rcu.h
+++ b/include/trace/events/rcu.h
@@ -93,16 +93,16 @@ TRACE_EVENT_RCU(rcu_grace_period,
  * the data from the rcu_node structure, other than rcuname, which comes
  * from the rcu_state structure, and event, which is one of the following:
  *
- * "Startleaf": Request a grace period based on leaf-node data.
+ * "Cleanup": Clean up rcu_node structure after previous GP.
+ * "CleanupMore": Clean up, and another GP is needed.
+ * "EndWait": Complete wait.
+ * "NoGPkthread": The RCU grace-period kthread has not yet started.
  * "Prestarted": Someone beat us to the request
  * "Startedleaf": Leaf node marked for future GP.
  * "Startedleafroot": All nodes from leaf to root marked for future GP.
  * "Startedroot": Requested a nocb grace period based on root-node data.
- * "NoGPkthread": The RCU grace-period kthread has not yet started.
+ * "Startleaf": Request a grace period based on leaf-node data.
  * "StartWait": Start waiting for the requested grace period.
- * "EndWait": Complete wait.
- * "Cleanup": Clean up rcu_node structure after previous GP.
- * "CleanupMore": Clean up, and another GP is needed.
  */
 TRACE_EVENT_RCU(rcu_future_grace_period,
 
@@ -258,20 +258,27 @@ TRACE_EVENT_RCU(rcu_exp_funnel_lock,
  * the number of the offloaded CPU are extracted.  The third and final
  * argument is a string as follows:
  *
- *	"WakeEmpty": Wake rcuo kthread, first CB to empty list.
- *	"WakeEmptyIsDeferred": Wake rcuo kthread later, first CB to empty list.
- *	"WakeOvf": Wake rcuo kthread, CB list is huge.
- *	"WakeOvfIsDeferred": Wake rcuo kthread later, CB list is huge.
- *	"WakeNot": Don't wake rcuo kthread.
- *	"WakeNotPoll": Don't wake rcuo kthread because it is polling.
- *	"DeferredWake": Carried out the "IsDeferred" wakeup.
- *	"Poll": Start of new polling cycle for rcu_nocb_poll.
- *	"Sleep": Sleep waiting for GP for !rcu_nocb_poll.
- *	"CBSleep": Sleep waiting for CBs for !rcu_nocb_poll.
- *	"WokeEmpty": rcuo kthread woke to find empty list.
- *	"WokeNonEmpty": rcuo kthread woke to find non-empty list.
- *	"WaitQueue": Enqueue partially done, timed wait for it to complete.
- *	"WokeQueue": Partial enqueue now complete.
+ * "AlreadyAwake": The to-be-awakened rcuo kthread is already awake.
+ * "Bypass": rcuo GP kthread sees non-empty ->nocb_bypass.
+ * "CBSleep": rcuo CB kthread sleeping waiting for CBs.
+ * "Check": rcuo GP kthread checking specified CPU for work.
+ * "DeferredWake": Timer expired or polled check, time to wake.
+ * "DoWake": The to-be-awakened rcuo kthread needs to be awakened.
+ * "EndSleep": Done waiting for GP for !rcu_nocb_poll.
+ * "FirstBQ": New CB to empty ->nocb_bypass (->cblist maybe non-empty).
+ * "FirstBQnoWake": FirstBQ plus rcuo kthread need not be awakened.
+ * "FirstBQwake": FirstBQ plus rcuo kthread must be awakened.
+ * "FirstQ": New CB to empty ->cblist (->nocb_bypass maybe non-empty).
+ * "NeedWaitGP": rcuo GP kthread must wait on a grace period.
+ * "Poll": Start of new polling cycle for rcu_nocb_poll.
+ * "Sleep": Sleep waiting for GP for !rcu_nocb_poll.
+ * "Timer": Deferred-wake timer expired.
+ * "WakeEmptyIsDeferred": Wake rcuo kthread later, first CB to empty list.
+ * "WakeEmpty": Wake rcuo kthread, first CB to empty list.
+ * "WakeNot": Don't wake rcuo kthread.
+ * "WakeNotPoll": Don't wake rcuo kthread because it is polling.
+ * "WakeOvfIsDeferred": Wake rcuo kthread later, CB list is huge.
+ * "WokeEmpty": rcuo CB kthread woke to find empty list.
  */
 TRACE_EVENT_RCU(rcu_nocb_wake,
 
@@ -713,8 +720,6 @@ TRACE_EVENT_RCU(rcu_torture_read,
  *	"Begin": rcu_barrier() started.
  *	"EarlyExit": rcu_barrier() piggybacked, thus early exit.
  *	"Inc1": rcu_barrier() piggyback check counter incremented.
- *	"OfflineNoCB": rcu_barrier() found callback on never-online CPU
- *	"OnlineNoCB": rcu_barrier() found online no-CBs CPU.
  *	"OnlineQ": rcu_barrier() found online CPU with callbacks.
  *	"OnlineNQ": rcu_barrier() found online CPU, no callbacks.
  *	"IRQ": An rcu_barrier_callback() callback posted on remote CPU.
diff --git a/include/trace/events/timer.h b/include/trace/events/timer.h
index b7a904825e7d..295517f109d7 100644
--- a/include/trace/events/timer.h
+++ b/include/trace/events/timer.h
@@ -367,7 +367,8 @@ TRACE_EVENT(itimer_expire,
 		tick_dep_name(POSIX_TIMER)		\
 		tick_dep_name(PERF_EVENTS)		\
 		tick_dep_name(SCHED)			\
-		tick_dep_name_end(CLOCK_UNSTABLE)
+		tick_dep_name(CLOCK_UNSTABLE)		\
+		tick_dep_name_end(RCU)
 
 #undef tick_dep_name
 #undef tick_dep_mask_name
diff --git a/include/uapi/linux/cec-funcs.h b/include/uapi/linux/cec-funcs.h
index 8997d5068c08..37590027b604 100644
--- a/include/uapi/linux/cec-funcs.h
+++ b/include/uapi/linux/cec-funcs.h
@@ -923,7 +923,8 @@ static inline void cec_msg_give_deck_status(struct cec_msg *msg,
 	msg->len = 3;
 	msg->msg[1] = CEC_MSG_GIVE_DECK_STATUS;
 	msg->msg[2] = status_req;
-	msg->reply = reply ? CEC_MSG_DECK_STATUS : 0;
+	msg->reply = (reply && status_req != CEC_OP_STATUS_REQ_OFF) ?
+				CEC_MSG_DECK_STATUS : 0;
 }
 
 static inline void cec_ops_give_deck_status(const struct cec_msg *msg,
@@ -1027,7 +1028,8 @@ static inline void cec_msg_give_tuner_device_status(struct cec_msg *msg,
 	msg->len = 3;
 	msg->msg[1] = CEC_MSG_GIVE_TUNER_DEVICE_STATUS;
 	msg->msg[2] = status_req;
-	msg->reply = reply ? CEC_MSG_TUNER_DEVICE_STATUS : 0;
+	msg->reply = (reply && status_req != CEC_OP_STATUS_REQ_OFF) ?
+				CEC_MSG_TUNER_DEVICE_STATUS : 0;
 }
 
 static inline void cec_ops_give_tuner_device_status(const struct cec_msg *msg,
@@ -1302,17 +1304,17 @@ static inline void cec_msg_user_control_pressed(struct cec_msg *msg,
 	if (!ui_cmd->has_opt_arg)
 		return;
 	switch (ui_cmd->ui_cmd) {
-	case 0x56:
-	case 0x57:
-	case 0x60:
-	case 0x68:
-	case 0x69:
-	case 0x6a:
+	case CEC_OP_UI_CMD_SELECT_BROADCAST_TYPE:
+	case CEC_OP_UI_CMD_SELECT_SOUND_PRESENTATION:
+	case CEC_OP_UI_CMD_PLAY_FUNCTION:
+	case CEC_OP_UI_CMD_SELECT_MEDIA_FUNCTION:
+	case CEC_OP_UI_CMD_SELECT_AV_INPUT_FUNCTION:
+	case CEC_OP_UI_CMD_SELECT_AUDIO_INPUT_FUNCTION:
 		/* The optional operand is one byte for all these ui commands */
 		msg->len++;
 		msg->msg[3] = ui_cmd->play_mode;
 		break;
-	case 0x67:
+	case CEC_OP_UI_CMD_TUNE_FUNCTION:
 		msg->len += 4;
 		msg->msg[3] = (ui_cmd->channel_identifier.channel_number_fmt << 2) |
 			      (ui_cmd->channel_identifier.major >> 8);
@@ -1331,17 +1333,17 @@ static inline void cec_ops_user_control_pressed(const struct cec_msg *msg,
 	if (msg->len == 3)
 		return;
 	switch (ui_cmd->ui_cmd) {
-	case 0x56:
-	case 0x57:
-	case 0x60:
-	case 0x68:
-	case 0x69:
-	case 0x6a:
+	case CEC_OP_UI_CMD_SELECT_BROADCAST_TYPE:
+	case CEC_OP_UI_CMD_SELECT_SOUND_PRESENTATION:
+	case CEC_OP_UI_CMD_PLAY_FUNCTION:
+	case CEC_OP_UI_CMD_SELECT_MEDIA_FUNCTION:
+	case CEC_OP_UI_CMD_SELECT_AV_INPUT_FUNCTION:
+	case CEC_OP_UI_CMD_SELECT_AUDIO_INPUT_FUNCTION:
 		/* The optional operand is one byte for all these ui commands */
 		ui_cmd->play_mode = msg->msg[3];
 		ui_cmd->has_opt_arg = 1;
 		break;
-	case 0x67:
+	case CEC_OP_UI_CMD_TUNE_FUNCTION:
 		if (msg->len < 7)
 			break;
 		ui_cmd->has_opt_arg = 1;
diff --git a/include/uapi/linux/cec.h b/include/uapi/linux/cec.h
index 5704fa0292b5..7d1a06c52469 100644
--- a/include/uapi/linux/cec.h
+++ b/include/uapi/linux/cec.h
@@ -317,6 +317,8 @@ static inline int cec_is_unconfigured(__u16 log_addr_mask)
 #define CEC_CAP_NEEDS_HPD	(1 << 6)
 /* Hardware can monitor CEC pin transitions */
 #define CEC_CAP_MONITOR_PIN	(1 << 7)
+/* CEC_ADAP_G_CONNECTOR_INFO is available */
+#define CEC_CAP_CONNECTOR_INFO	(1 << 8)
 
 /**
  * struct cec_caps - CEC capabilities structure.
@@ -375,6 +377,34 @@ struct cec_log_addrs {
 /* CDC-Only device: supports only CDC messages */
 #define CEC_LOG_ADDRS_FL_CDC_ONLY		(1 << 2)
 
+/**
+ * struct cec_drm_connector_info - tells which drm connector is
+ * associated with the CEC adapter.
+ * @card_no: drm card number
+ * @connector_id: drm connector ID
+ */
+struct cec_drm_connector_info {
+	__u32 card_no;
+	__u32 connector_id;
+};
+
+#define CEC_CONNECTOR_TYPE_NO_CONNECTOR	0
+#define CEC_CONNECTOR_TYPE_DRM		1
+
+/**
+ * struct cec_connector_info - tells if and which connector is
+ * associated with the CEC adapter.
+ * @type: connector type (if any)
+ * @drm: drm connector info
+ */
+struct cec_connector_info {
+	__u32 type;
+	union {
+		struct cec_drm_connector_info drm;
+		__u32 raw[16];
+	};
+};
+
 /* Events */
 
 /* Event that occurs when the adapter state changes */
@@ -398,10 +428,17 @@ struct cec_log_addrs {
  * struct cec_event_state_change - used when the CEC adapter changes state.
  * @phys_addr: the current physical address
  * @log_addr_mask: the current logical address mask
+ * @have_conn_info: if non-zero, then HDMI connector information is available.
+ *	This field is only valid if CEC_CAP_CONNECTOR_INFO is set. If that
+ *	capability is set and @have_conn_info is zero, then that indicates
+ *	that the HDMI connector device is not instantiated, either because
+ *	the HDMI driver is still configuring the device or because the HDMI
+ *	device was unbound.
  */
 struct cec_event_state_change {
 	__u16 phys_addr;
 	__u16 log_addr_mask;
+	__u16 have_conn_info;
 };
 
 /**
@@ -476,6 +513,9 @@ struct cec_event {
 #define CEC_G_MODE		_IOR('a',  8, __u32)
 #define CEC_S_MODE		_IOW('a',  9, __u32)
 
+/* Get the connector info */
+#define CEC_ADAP_G_CONNECTOR_INFO _IOR('a',  10, struct cec_connector_info)
+
 /*
  * The remainder of this header defines all CEC messages and operands.
  * The format matters since it the cec-ctl utility parses it to generate
@@ -768,8 +808,8 @@ struct cec_event {
 #define CEC_MSG_SELECT_DIGITAL_SERVICE			0x93
 #define CEC_MSG_TUNER_DEVICE_STATUS			0x07
 /* Recording Flag Operand (rec_flag) */
-#define CEC_OP_REC_FLAG_USED				0
-#define CEC_OP_REC_FLAG_NOT_USED			1
+#define CEC_OP_REC_FLAG_NOT_USED			0
+#define CEC_OP_REC_FLAG_USED				1
 /* Tuner Display Info Operand (tuner_display_info) */
 #define CEC_OP_TUNER_DISPLAY_INFO_DIGITAL		0
 #define CEC_OP_TUNER_DISPLAY_INFO_NONE			1
@@ -820,6 +860,95 @@ struct cec_event {
 #define CEC_OP_MENU_STATE_DEACTIVATED			0x01
 
 #define CEC_MSG_USER_CONTROL_PRESSED			0x44
+/* UI Command Operand (ui_cmd) */
+#define CEC_OP_UI_CMD_SELECT				0x00
+#define CEC_OP_UI_CMD_UP				0x01
+#define CEC_OP_UI_CMD_DOWN				0x02
+#define CEC_OP_UI_CMD_LEFT				0x03
+#define CEC_OP_UI_CMD_RIGHT				0x04
+#define CEC_OP_UI_CMD_RIGHT_UP				0x05
+#define CEC_OP_UI_CMD_RIGHT_DOWN			0x06
+#define CEC_OP_UI_CMD_LEFT_UP				0x07
+#define CEC_OP_UI_CMD_LEFT_DOWN				0x08
+#define CEC_OP_UI_CMD_DEVICE_ROOT_MENU			0x09
+#define CEC_OP_UI_CMD_DEVICE_SETUP_MENU			0x0a
+#define CEC_OP_UI_CMD_CONTENTS_MENU			0x0b
+#define CEC_OP_UI_CMD_FAVORITE_MENU			0x0c
+#define CEC_OP_UI_CMD_BACK				0x0d
+#define CEC_OP_UI_CMD_MEDIA_TOP_MENU			0x10
+#define CEC_OP_UI_CMD_MEDIA_CONTEXT_SENSITIVE_MENU	0x11
+#define CEC_OP_UI_CMD_NUMBER_ENTRY_MODE			0x1d
+#define CEC_OP_UI_CMD_NUMBER_11				0x1e
+#define CEC_OP_UI_CMD_NUMBER_12				0x1f
+#define CEC_OP_UI_CMD_NUMBER_0_OR_NUMBER_10		0x20
+#define CEC_OP_UI_CMD_NUMBER_1				0x21
+#define CEC_OP_UI_CMD_NUMBER_2				0x22
+#define CEC_OP_UI_CMD_NUMBER_3				0x23
+#define CEC_OP_UI_CMD_NUMBER_4				0x24
+#define CEC_OP_UI_CMD_NUMBER_5				0x25
+#define CEC_OP_UI_CMD_NUMBER_6				0x26
+#define CEC_OP_UI_CMD_NUMBER_7				0x27
+#define CEC_OP_UI_CMD_NUMBER_8				0x28
+#define CEC_OP_UI_CMD_NUMBER_9				0x29
+#define CEC_OP_UI_CMD_DOT				0x2a
+#define CEC_OP_UI_CMD_ENTER				0x2b
+#define CEC_OP_UI_CMD_CLEAR				0x2c
+#define CEC_OP_UI_CMD_NEXT_FAVORITE			0x2f
+#define CEC_OP_UI_CMD_CHANNEL_UP			0x30
+#define CEC_OP_UI_CMD_CHANNEL_DOWN			0x31
+#define CEC_OP_UI_CMD_PREVIOUS_CHANNEL			0x32
+#define CEC_OP_UI_CMD_SOUND_SELECT			0x33
+#define CEC_OP_UI_CMD_INPUT_SELECT			0x34
+#define CEC_OP_UI_CMD_DISPLAY_INFORMATION		0x35
+#define CEC_OP_UI_CMD_HELP				0x36
+#define CEC_OP_UI_CMD_PAGE_UP				0x37
+#define CEC_OP_UI_CMD_PAGE_DOWN				0x38
+#define CEC_OP_UI_CMD_POWER				0x40
+#define CEC_OP_UI_CMD_VOLUME_UP				0x41
+#define CEC_OP_UI_CMD_VOLUME_DOWN			0x42
+#define CEC_OP_UI_CMD_MUTE				0x43
+#define CEC_OP_UI_CMD_PLAY				0x44
+#define CEC_OP_UI_CMD_STOP				0x45
+#define CEC_OP_UI_CMD_PAUSE				0x46
+#define CEC_OP_UI_CMD_RECORD				0x47
+#define CEC_OP_UI_CMD_REWIND				0x48
+#define CEC_OP_UI_CMD_FAST_FORWARD			0x49
+#define CEC_OP_UI_CMD_EJECT				0x4a
+#define CEC_OP_UI_CMD_SKIP_FORWARD			0x4b
+#define CEC_OP_UI_CMD_SKIP_BACKWARD			0x4c
+#define CEC_OP_UI_CMD_STOP_RECORD			0x4d
+#define CEC_OP_UI_CMD_PAUSE_RECORD			0x4e
+#define CEC_OP_UI_CMD_ANGLE				0x50
+#define CEC_OP_UI_CMD_SUB_PICTURE			0x51
+#define CEC_OP_UI_CMD_VIDEO_ON_DEMAND			0x52
+#define CEC_OP_UI_CMD_ELECTRONIC_PROGRAM_GUIDE		0x53
+#define CEC_OP_UI_CMD_TIMER_PROGRAMMING			0x54
+#define CEC_OP_UI_CMD_INITIAL_CONFIGURATION		0x55
+#define CEC_OP_UI_CMD_SELECT_BROADCAST_TYPE		0x56
+#define CEC_OP_UI_CMD_SELECT_SOUND_PRESENTATION		0x57
+#define CEC_OP_UI_CMD_AUDIO_DESCRIPTION			0x58
+#define CEC_OP_UI_CMD_INTERNET				0x59
+#define CEC_OP_UI_CMD_3D_MODE				0x5a
+#define CEC_OP_UI_CMD_PLAY_FUNCTION			0x60
+#define CEC_OP_UI_CMD_PAUSE_PLAY_FUNCTION		0x61
+#define CEC_OP_UI_CMD_RECORD_FUNCTION			0x62
+#define CEC_OP_UI_CMD_PAUSE_RECORD_FUNCTION		0x63
+#define CEC_OP_UI_CMD_STOP_FUNCTION			0x64
+#define CEC_OP_UI_CMD_MUTE_FUNCTION			0x65
+#define CEC_OP_UI_CMD_RESTORE_VOLUME_FUNCTION		0x66
+#define CEC_OP_UI_CMD_TUNE_FUNCTION			0x67
+#define CEC_OP_UI_CMD_SELECT_MEDIA_FUNCTION		0x68
+#define CEC_OP_UI_CMD_SELECT_AV_INPUT_FUNCTION		0x69
+#define CEC_OP_UI_CMD_SELECT_AUDIO_INPUT_FUNCTION	0x6a
+#define CEC_OP_UI_CMD_POWER_TOGGLE_FUNCTION		0x6b
+#define CEC_OP_UI_CMD_POWER_OFF_FUNCTION		0x6c
+#define CEC_OP_UI_CMD_POWER_ON_FUNCTION			0x6d
+#define CEC_OP_UI_CMD_F1_BLUE				0x71
+#define CEC_OP_UI_CMD_F2_RED				0x72
+#define CEC_OP_UI_CMD_F3_GREEN				0x73
+#define CEC_OP_UI_CMD_F4_YELLOW				0x74
+#define CEC_OP_UI_CMD_F5				0x75
+#define CEC_OP_UI_CMD_DATA				0x76
 /* UI Broadcast Type Operand (ui_bcast_type) */
 #define CEC_OP_UI_BCAST_TYPE_TOGGLE_ALL			0x00
 #define CEC_OP_UI_BCAST_TYPE_TOGGLE_DIG_ANA		0x01
diff --git a/include/uapi/linux/v4l2-controls.h b/include/uapi/linux/v4l2-controls.h
index a2669b79b294..5a7bedee2b0e 100644
--- a/include/uapi/linux/v4l2-controls.h
+++ b/include/uapi/linux/v4l2-controls.h
@@ -1034,6 +1034,7 @@ enum v4l2_jpeg_chroma_subsampling {
 #define V4L2_CID_TEST_PATTERN_GREENR		(V4L2_CID_IMAGE_SOURCE_CLASS_BASE + 5)
 #define V4L2_CID_TEST_PATTERN_BLUE		(V4L2_CID_IMAGE_SOURCE_CLASS_BASE + 6)
 #define V4L2_CID_TEST_PATTERN_GREENB		(V4L2_CID_IMAGE_SOURCE_CLASS_BASE + 7)
+#define V4L2_CID_UNIT_CELL_SIZE			(V4L2_CID_IMAGE_SOURCE_CLASS_BASE + 8)
 
 
 /* Image processing controls */
diff --git a/include/uapi/linux/videodev2.h b/include/uapi/linux/videodev2.h
index 530638dffd93..04481c717fee 100644
--- a/include/uapi/linux/videodev2.h
+++ b/include/uapi/linux/videodev2.h
@@ -422,6 +422,11 @@ struct v4l2_fract {
 	__u32   denominator;
 };
 
+struct v4l2_area {
+	__u32   width;
+	__u32   height;
+};
+
 /**
   * struct v4l2_capability - Describes V4L2 device caps returned by VIDIOC_QUERYCAP
   *
@@ -755,6 +760,7 @@ struct v4l2_pix_format {
 #define V4L2_META_FMT_VSP1_HGT    v4l2_fourcc('V', 'S', 'P', 'T') /* R-Car VSP1 2-D Histogram */
 #define V4L2_META_FMT_UVC         v4l2_fourcc('U', 'V', 'C', 'H') /* UVC Payload Header metadata */
 #define V4L2_META_FMT_D4XX        v4l2_fourcc('D', '4', 'X', 'X') /* D4XX Payload Header metadata */
+#define V4L2_META_FMT_VIVID	  v4l2_fourcc('V', 'I', 'V', 'D') /* Vivid Metadata */
 
 /* priv field value to indicates that subsequent fields are valid. */
 #define V4L2_PIX_FMT_PRIV_MAGIC		0xfeedcafe
@@ -915,11 +921,12 @@ struct v4l2_requestbuffers {
 };
 
 /* capabilities for struct v4l2_requestbuffers and v4l2_create_buffers */
-#define V4L2_BUF_CAP_SUPPORTS_MMAP	(1 << 0)
-#define V4L2_BUF_CAP_SUPPORTS_USERPTR	(1 << 1)
-#define V4L2_BUF_CAP_SUPPORTS_DMABUF	(1 << 2)
-#define V4L2_BUF_CAP_SUPPORTS_REQUESTS	(1 << 3)
-#define V4L2_BUF_CAP_SUPPORTS_ORPHANED_BUFS (1 << 4)
+#define V4L2_BUF_CAP_SUPPORTS_MMAP			(1 << 0)
+#define V4L2_BUF_CAP_SUPPORTS_USERPTR			(1 << 1)
+#define V4L2_BUF_CAP_SUPPORTS_DMABUF			(1 << 2)
+#define V4L2_BUF_CAP_SUPPORTS_REQUESTS			(1 << 3)
+#define V4L2_BUF_CAP_SUPPORTS_ORPHANED_BUFS		(1 << 4)
+#define V4L2_BUF_CAP_SUPPORTS_M2M_HOLD_CAPTURE_BUF	(1 << 5)
 
 /**
  * struct v4l2_plane - plane info for multi-planar buffers
@@ -1041,6 +1048,8 @@ static inline __u64 v4l2_timeval_to_ns(const struct timeval *tv)
 #define V4L2_BUF_FLAG_IN_REQUEST		0x00000080
 /* timecode field is valid */
 #define V4L2_BUF_FLAG_TIMECODE			0x00000100
+/* Don't return the capture buffer until OUTPUT timestamp changes */
+#define V4L2_BUF_FLAG_M2M_HOLD_CAPTURE_BUF	0x00000200
 /* Buffer is prepared for queuing */
 #define V4L2_BUF_FLAG_PREPARED			0x00000400
 /* Cache handling flags */
@@ -1675,6 +1684,7 @@ struct v4l2_ext_control {
 		__u8 __user *p_u8;
 		__u16 __user *p_u16;
 		__u32 __user *p_u32;
+		struct v4l2_area __user *p_area;
 		void __user *ptr;
 	};
 } __attribute__ ((packed));
@@ -1720,6 +1730,7 @@ enum v4l2_ctrl_type {
 	V4L2_CTRL_TYPE_U8	     = 0x0100,
 	V4L2_CTRL_TYPE_U16	     = 0x0101,
 	V4L2_CTRL_TYPE_U32	     = 0x0102,
+	V4L2_CTRL_TYPE_AREA          = 0x0106,
 };
 
 /*  Used in the VIDIOC_QUERYCTRL ioctl for querying controls */
@@ -1975,6 +1986,7 @@ struct v4l2_encoder_cmd {
 #define V4L2_DEC_CMD_STOP        (1)
 #define V4L2_DEC_CMD_PAUSE       (2)
 #define V4L2_DEC_CMD_RESUME      (3)
+#define V4L2_DEC_CMD_FLUSH       (4)
 
 /* Flags for V4L2_DEC_CMD_START */
 #define V4L2_DEC_CMD_START_MUTE_AUDIO	(1 << 0)
diff --git a/include/uapi/sound/compress_params.h b/include/uapi/sound/compress_params.h
index 3d4d6de66a17..9c96fb0e4d90 100644
--- a/include/uapi/sound/compress_params.h
+++ b/include/uapi/sound/compress_params.h
@@ -317,12 +317,22 @@ struct snd_enc_generic {
 	__s32 reserved[15];	/* Can be used for SND_AUDIOCODEC_BESPOKE */
 } __attribute__((packed, aligned(4)));
 
+struct snd_dec_flac {
+	__u16 sample_size;
+	__u16 min_blk_size;
+	__u16 max_blk_size;
+	__u16 min_frame_size;
+	__u16 max_frame_size;
+	__u16 reserved;
+} __attribute__((packed, aligned(4)));
+
 union snd_codec_options {
 	struct snd_enc_wma wma;
 	struct snd_enc_vorbis vorbis;
 	struct snd_enc_real real;
 	struct snd_enc_flac flac;
 	struct snd_enc_generic generic;
+	struct snd_dec_flac flac_d;
 } __attribute__((packed, aligned(4)));
 
 /** struct snd_codec_desc - description of codec capabilities
diff --git a/include/uapi/sound/sof/abi.h b/include/uapi/sound/sof/abi.h
index a0fe0d4c4b66..ebfdc20ca081 100644
--- a/include/uapi/sound/sof/abi.h
+++ b/include/uapi/sound/sof/abi.h
@@ -26,7 +26,7 @@
 
 /* SOF ABI version major, minor and patch numbers */
 #define SOF_ABI_MAJOR 3
-#define SOF_ABI_MINOR 10
+#define SOF_ABI_MINOR 11
 #define SOF_ABI_PATCH 0
 
 /* SOF ABI version number. Format within 32bit word is MMmmmppp */
diff --git a/include/uapi/sound/sof/tokens.h b/include/uapi/sound/sof/tokens.h
index 8f996857fb24..76883e6fb750 100644
--- a/include/uapi/sound/sof/tokens.h
+++ b/include/uapi/sound/sof/tokens.h
@@ -111,7 +111,14 @@
 /* TODO: Add SAI tokens */
 
 /* ESAI */
-#define SOF_TKN_IMX_ESAI_FIRST_TOKEN		1100
-/* TODO: Add ESAI tokens */
+#define SOF_TKN_IMX_ESAI_MCLK_ID		1100
+
+/* Stream */
+#define SOF_TKN_STREAM_PLAYBACK_COMPATIBLE_D0I3	1200
+#define SOF_TKN_STREAM_CAPTURE_COMPATIBLE_D0I3	1201
+
+/* Led control for mute switches */
+#define SOF_TKN_MUTE_LED_USE			1300
+#define SOF_TKN_MUTE_LED_DIRECTION		1301
 
 #endif
diff --git a/kernel/Kconfig.preempt b/kernel/Kconfig.preempt
index deff97217496..bf82259cff96 100644
--- a/kernel/Kconfig.preempt
+++ b/kernel/Kconfig.preempt
@@ -65,7 +65,7 @@ config PREEMPT_RT
 	  preemptible priority-inheritance aware variants, enforcing
 	  interrupt threading and introducing mechanisms to break up long
 	  non-preemptible sections. This makes the kernel, except for very
-	  low level and critical code pathes (entry code, scheduler, low
+	  low level and critical code paths (entry code, scheduler, low
 	  level interrupt handling) fully preemptible and brings most
 	  execution contexts under scheduler control.
 
diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c
index a3eaf08e7dd3..9f90d3c92bda 100644
--- a/kernel/bpf/cgroup.c
+++ b/kernel/bpf/cgroup.c
@@ -180,8 +180,8 @@ static void activate_effective_progs(struct cgroup *cgrp,
 				     enum bpf_attach_type type,
 				     struct bpf_prog_array *old_array)
 {
-	rcu_swap_protected(cgrp->bpf.effective[type], old_array,
-			   lockdep_is_held(&cgroup_mutex));
+	old_array = rcu_replace_pointer(cgrp->bpf.effective[type], old_array,
+					lockdep_is_held(&cgroup_mutex));
 	/* free prog array after grace period, since __cgroup_bpf_run_*()
 	 * might be still walking the array
 	 */
diff --git a/kernel/bpf/stackmap.c b/kernel/bpf/stackmap.c
index 173e983619d7..caca752ee5e6 100644
--- a/kernel/bpf/stackmap.c
+++ b/kernel/bpf/stackmap.c
@@ -339,7 +339,7 @@ static void stack_map_get_build_id_offset(struct bpf_stack_build_id *id_offs,
 		 * up_read_non_owner(). The rwsem_release() is called
 		 * here to release the lock from lockdep's perspective.
 		 */
-		rwsem_release(&current->mm->mmap_sem.dep_map, 1, _RET_IP_);
+		rwsem_release(&current->mm->mmap_sem.dep_map, _RET_IP_);
 	}
 }
 
diff --git a/kernel/context_tracking.c b/kernel/context_tracking.c
index be01a4d627c9..0296b4bda8f1 100644
--- a/kernel/context_tracking.c
+++ b/kernel/context_tracking.c
@@ -25,8 +25,8 @@
 #define CREATE_TRACE_POINTS
 #include <trace/events/context_tracking.h>
 
-DEFINE_STATIC_KEY_FALSE(context_tracking_enabled);
-EXPORT_SYMBOL_GPL(context_tracking_enabled);
+DEFINE_STATIC_KEY_FALSE(context_tracking_key);
+EXPORT_SYMBOL_GPL(context_tracking_key);
 
 DEFINE_PER_CPU(struct context_tracking, context_tracking);
 EXPORT_SYMBOL_GPL(context_tracking);
@@ -192,7 +192,7 @@ void __init context_tracking_cpu_set(int cpu)
 
 	if (!per_cpu(context_tracking.active, cpu)) {
 		per_cpu(context_tracking.active, cpu) = true;
-		static_branch_inc(&context_tracking_enabled);
+		static_branch_inc(&context_tracking_key);
 	}
 
 	if (initialized)
diff --git a/kernel/cpu.c b/kernel/cpu.c
index e2cad3ee2ead..a59cc980adad 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -336,7 +336,7 @@ static void lockdep_acquire_cpus_lock(void)
 
 static void lockdep_release_cpus_lock(void)
 {
-	rwsem_release(&cpu_hotplug_lock.rw_sem.dep_map, 1, _THIS_IP_);
+	rwsem_release(&cpu_hotplug_lock.rw_sem.dep_map, _THIS_IP_);
 }
 
 /*
diff --git a/kernel/exit.c b/kernel/exit.c
index f2d20ab74422..0bac4b60d5f3 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -437,7 +437,7 @@ static void exit_mm(void)
 	struct mm_struct *mm = current->mm;
 	struct core_state *core_state;
 
-	mm_release(current, mm);
+	exit_mm_release(current, mm);
 	if (!mm)
 		return;
 	sync_mm_rss(mm);
@@ -746,32 +746,12 @@ void __noreturn do_exit(long code)
 	 */
 	if (unlikely(tsk->flags & PF_EXITING)) {
 		pr_alert("Fixing recursive fault but reboot is needed!\n");
-		/*
-		 * We can do this unlocked here. The futex code uses
-		 * this flag just to verify whether the pi state
-		 * cleanup has been done or not. In the worst case it
-		 * loops once more. We pretend that the cleanup was
-		 * done as there is no way to return. Either the
-		 * OWNER_DIED bit is set by now or we push the blocked
-		 * task into the wait for ever nirwana as well.
-		 */
-		tsk->flags |= PF_EXITPIDONE;
+		futex_exit_recursive(tsk);
 		set_current_state(TASK_UNINTERRUPTIBLE);
 		schedule();
 	}
 
 	exit_signals(tsk);  /* sets PF_EXITING */
-	/*
-	 * Ensure that all new tsk->pi_lock acquisitions must observe
-	 * PF_EXITING. Serializes against futex.c:attach_to_pi_owner().
-	 */
-	smp_mb();
-	/*
-	 * Ensure that we must observe the pi_state in exit_mm() ->
-	 * mm_release() -> exit_pi_state_list().
-	 */
-	raw_spin_lock_irq(&tsk->pi_lock);
-	raw_spin_unlock_irq(&tsk->pi_lock);
 
 	if (unlikely(in_atomic())) {
 		pr_info("note: %s[%d] exited with preempt_count %d\n",
@@ -846,12 +826,6 @@ void __noreturn do_exit(long code)
 	 * Make sure we are holding no locks:
 	 */
 	debug_check_no_locks_held();
-	/*
-	 * We can do this unlocked here. The futex code uses this flag
-	 * just to verify whether the pi state cleanup has been done
-	 * or not. In the worst case it loops once more.
-	 */
-	tsk->flags |= PF_EXITPIDONE;
 
 	if (tsk->io_context)
 		exit_io_context(tsk);
diff --git a/kernel/fork.c b/kernel/fork.c
index 35f91ee91057..00b64f41c2b4 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -1283,24 +1283,8 @@ static int wait_for_vfork_done(struct task_struct *child,
  * restoring the old one. . .
  * Eric Biederman 10 January 1998
  */
-void mm_release(struct task_struct *tsk, struct mm_struct *mm)
+static void mm_release(struct task_struct *tsk, struct mm_struct *mm)
 {
-	/* Get rid of any futexes when releasing the mm */
-#ifdef CONFIG_FUTEX
-	if (unlikely(tsk->robust_list)) {
-		exit_robust_list(tsk);
-		tsk->robust_list = NULL;
-	}
-#ifdef CONFIG_COMPAT
-	if (unlikely(tsk->compat_robust_list)) {
-		compat_exit_robust_list(tsk);
-		tsk->compat_robust_list = NULL;
-	}
-#endif
-	if (unlikely(!list_empty(&tsk->pi_state_list)))
-		exit_pi_state_list(tsk);
-#endif
-
 	uprobe_free_utask(tsk);
 
 	/* Get rid of any cached register state */
@@ -1333,6 +1317,18 @@ void mm_release(struct task_struct *tsk, struct mm_struct *mm)
 		complete_vfork_done(tsk);
 }
 
+void exit_mm_release(struct task_struct *tsk, struct mm_struct *mm)
+{
+	futex_exit_release(tsk);
+	mm_release(tsk, mm);
+}
+
+void exec_mm_release(struct task_struct *tsk, struct mm_struct *mm)
+{
+	futex_exec_release(tsk);
+	mm_release(tsk, mm);
+}
+
 /**
  * dup_mm() - duplicates an existing mm structure
  * @tsk: the task_struct with which the new mm will be associated.
@@ -2124,14 +2120,8 @@ static __latent_entropy struct task_struct *copy_process(
 #ifdef CONFIG_BLOCK
 	p->plug = NULL;
 #endif
-#ifdef CONFIG_FUTEX
-	p->robust_list = NULL;
-#ifdef CONFIG_COMPAT
-	p->compat_robust_list = NULL;
-#endif
-	INIT_LIST_HEAD(&p->pi_state_list);
-	p->pi_state_cache = NULL;
-#endif
+	futex_init_task(p);
+
 	/*
 	 * sigaltstack should be cleared when sharing the same VM
 	 */
diff --git a/kernel/futex.c b/kernel/futex.c
index bd18f60e4c6c..03c518e9747e 100644
--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -325,6 +325,12 @@ static inline bool should_fail_futex(bool fshared)
 }
 #endif /* CONFIG_FAIL_FUTEX */
 
+#ifdef CONFIG_COMPAT
+static void compat_exit_robust_list(struct task_struct *curr);
+#else
+static inline void compat_exit_robust_list(struct task_struct *curr) { }
+#endif
+
 static inline void futex_get_mm(union futex_key *key)
 {
 	mmgrab(key->private.mm);
@@ -890,7 +896,7 @@ static void put_pi_state(struct futex_pi_state *pi_state)
  * Kernel cleans up PI-state, but userspace is likely hosed.
  * (Robust-futex cleanup is separate and might save the day for userspace.)
  */
-void exit_pi_state_list(struct task_struct *curr)
+static void exit_pi_state_list(struct task_struct *curr)
 {
 	struct list_head *next, *head = &curr->pi_state_list;
 	struct futex_pi_state *pi_state;
@@ -960,7 +966,8 @@ void exit_pi_state_list(struct task_struct *curr)
 	}
 	raw_spin_unlock_irq(&curr->pi_lock);
 }
-
+#else
+static inline void exit_pi_state_list(struct task_struct *curr) { }
 #endif
 
 /*
@@ -1169,16 +1176,47 @@ out_error:
 	return ret;
 }
 
+/**
+ * wait_for_owner_exiting - Block until the owner has exited
+ * @exiting:	Pointer to the exiting task
+ *
+ * Caller must hold a refcount on @exiting.
+ */
+static void wait_for_owner_exiting(int ret, struct task_struct *exiting)
+{
+	if (ret != -EBUSY) {
+		WARN_ON_ONCE(exiting);
+		return;
+	}
+
+	if (WARN_ON_ONCE(ret == -EBUSY && !exiting))
+		return;
+
+	mutex_lock(&exiting->futex_exit_mutex);
+	/*
+	 * No point in doing state checking here. If the waiter got here
+	 * while the task was in exec()->exec_futex_release() then it can
+	 * have any FUTEX_STATE_* value when the waiter has acquired the
+	 * mutex. OK, if running, EXITING or DEAD if it reached exit()
+	 * already. Highly unlikely and not a problem. Just one more round
+	 * through the futex maze.
+	 */
+	mutex_unlock(&exiting->futex_exit_mutex);
+
+	put_task_struct(exiting);
+}
+
 static int handle_exit_race(u32 __user *uaddr, u32 uval,
 			    struct task_struct *tsk)
 {
 	u32 uval2;
 
 	/*
-	 * If PF_EXITPIDONE is not yet set, then try again.
+	 * If the futex exit state is not yet FUTEX_STATE_DEAD, tell the
+	 * caller that the alleged owner is busy.
 	 */
-	if (tsk && !(tsk->flags & PF_EXITPIDONE))
-		return -EAGAIN;
+	if (tsk && tsk->futex_state != FUTEX_STATE_DEAD)
+		return -EBUSY;
 
 	/*
 	 * Reread the user space value to handle the following situation:
@@ -1196,8 +1234,9 @@ static int handle_exit_race(u32 __user *uaddr, u32 uval,
 	 *    *uaddr = 0xC0000000;	     tsk = get_task(PID);
 	 *   }				     if (!tsk->flags & PF_EXITING) {
 	 *  ...				       attach();
-	 *  tsk->flags |= PF_EXITPIDONE;     } else {
-	 *				       if (!(tsk->flags & PF_EXITPIDONE))
+	 *  tsk->futex_state =               } else {
+	 *	FUTEX_STATE_DEAD;              if (tsk->futex_state !=
+	 *					  FUTEX_STATE_DEAD)
 	 *				         return -EAGAIN;
 	 *				       return -ESRCH; <--- FAIL
 	 *				     }
@@ -1228,7 +1267,8 @@ static int handle_exit_race(u32 __user *uaddr, u32 uval,
  * it after doing proper sanity checks.
  */
 static int attach_to_pi_owner(u32 __user *uaddr, u32 uval, union futex_key *key,
-			      struct futex_pi_state **ps)
+			      struct futex_pi_state **ps,
+			      struct task_struct **exiting)
 {
 	pid_t pid = uval & FUTEX_TID_MASK;
 	struct futex_pi_state *pi_state;
@@ -1253,22 +1293,33 @@ static int attach_to_pi_owner(u32 __user *uaddr, u32 uval, union futex_key *key,
 	}
 
 	/*
-	 * We need to look at the task state flags to figure out,
-	 * whether the task is exiting. To protect against the do_exit
-	 * change of the task flags, we do this protected by
-	 * p->pi_lock:
+	 * We need to look at the task state to figure out, whether the
+	 * task is exiting. To protect against the change of the task state
+	 * in futex_exit_release(), we do this protected by p->pi_lock:
 	 */
 	raw_spin_lock_irq(&p->pi_lock);
-	if (unlikely(p->flags & PF_EXITING)) {
+	if (unlikely(p->futex_state != FUTEX_STATE_OK)) {
 		/*
-		 * The task is on the way out. When PF_EXITPIDONE is
-		 * set, we know that the task has finished the
-		 * cleanup:
+		 * The task is on the way out. When the futex state is
+		 * FUTEX_STATE_DEAD, we know that the task has finished
+		 * the cleanup:
 		 */
 		int ret = handle_exit_race(uaddr, uval, p);
 
 		raw_spin_unlock_irq(&p->pi_lock);
-		put_task_struct(p);
+		/*
+		 * If the owner task is between FUTEX_STATE_EXITING and
+		 * FUTEX_STATE_DEAD then store the task pointer and keep
+		 * the reference on the task struct. The calling code will
+		 * drop all locks, wait for the task to reach
+		 * FUTEX_STATE_DEAD and then drop the refcount. This is
+		 * required to prevent a live lock when the current task
+		 * preempted the exiting task between the two states.
+		 */
+		if (ret == -EBUSY)
+			*exiting = p;
+		else
+			put_task_struct(p);
 		return ret;
 	}
 
@@ -1307,7 +1358,8 @@ static int attach_to_pi_owner(u32 __user *uaddr, u32 uval, union futex_key *key,
 
 static int lookup_pi_state(u32 __user *uaddr, u32 uval,
 			   struct futex_hash_bucket *hb,
-			   union futex_key *key, struct futex_pi_state **ps)
+			   union futex_key *key, struct futex_pi_state **ps,
+			   struct task_struct **exiting)
 {
 	struct futex_q *top_waiter = futex_top_waiter(hb, key);
 
@@ -1322,7 +1374,7 @@ static int lookup_pi_state(u32 __user *uaddr, u32 uval,
 	 * We are the first waiter - try to look up the owner based on
 	 * @uval and attach to it.
 	 */
-	return attach_to_pi_owner(uaddr, uval, key, ps);
+	return attach_to_pi_owner(uaddr, uval, key, ps, exiting);
 }
 
 static int lock_pi_update_atomic(u32 __user *uaddr, u32 uval, u32 newval)
@@ -1350,6 +1402,8 @@ static int lock_pi_update_atomic(u32 __user *uaddr, u32 uval, u32 newval)
  *			lookup
  * @task:		the task to perform the atomic lock work for.  This will
  *			be "current" except in the case of requeue pi.
+ * @exiting:		Pointer to store the task pointer of the owner task
+ *			which is in the middle of exiting
  * @set_waiters:	force setting the FUTEX_WAITERS bit (1) or not (0)
  *
  * Return:
@@ -1358,11 +1412,17 @@ static int lock_pi_update_atomic(u32 __user *uaddr, u32 uval, u32 newval)
  *  - <0 - error
  *
  * The hb->lock and futex_key refs shall be held by the caller.
+ *
+ * @exiting is only set when the return value is -EBUSY. If so, this holds
+ * a refcount on the exiting task on return and the caller needs to drop it
+ * after waiting for the exit to complete.
  */
 static int futex_lock_pi_atomic(u32 __user *uaddr, struct futex_hash_bucket *hb,
 				union futex_key *key,
 				struct futex_pi_state **ps,
-				struct task_struct *task, int set_waiters)
+				struct task_struct *task,
+				struct task_struct **exiting,
+				int set_waiters)
 {
 	u32 uval, newval, vpid = task_pid_vnr(task);
 	struct futex_q *top_waiter;
@@ -1432,7 +1492,7 @@ static int futex_lock_pi_atomic(u32 __user *uaddr, struct futex_hash_bucket *hb,
 	 * attach to the owner. If that fails, no harm done, we only
 	 * set the FUTEX_WAITERS bit in the user space variable.
 	 */
-	return attach_to_pi_owner(uaddr, newval, key, ps);
+	return attach_to_pi_owner(uaddr, newval, key, ps, exiting);
 }
 
 /**
@@ -1480,7 +1540,7 @@ static void mark_wake_futex(struct wake_q_head *wake_q, struct futex_q *q)
 
 	/*
 	 * Queue the task for later wakeup for after we've released
-	 * the hb->lock. wake_q_add() grabs reference to p.
+	 * the hb->lock.
 	 */
 	wake_q_add_safe(wake_q, p);
 }
@@ -1850,6 +1910,8 @@ void requeue_pi_wake_futex(struct futex_q *q, union futex_key *key,
  * @key1:		the from futex key
  * @key2:		the to futex key
  * @ps:			address to store the pi_state pointer
+ * @exiting:		Pointer to store the task pointer of the owner task
+ *			which is in the middle of exiting
  * @set_waiters:	force setting the FUTEX_WAITERS bit (1) or not (0)
  *
  * Try and get the lock on behalf of the top waiter if we can do it atomically.
@@ -1857,16 +1919,20 @@ void requeue_pi_wake_futex(struct futex_q *q, union futex_key *key,
  * then direct futex_lock_pi_atomic() to force setting the FUTEX_WAITERS bit.
  * hb1 and hb2 must be held by the caller.
  *
+ * @exiting is only set when the return value is -EBUSY. If so, this holds
+ * a refcount on the exiting task on return and the caller needs to drop it
+ * after waiting for the exit to complete.
+ *
  * Return:
  *  -  0 - failed to acquire the lock atomically;
  *  - >0 - acquired the lock, return value is vpid of the top_waiter
  *  - <0 - error
  */
-static int futex_proxy_trylock_atomic(u32 __user *pifutex,
-				 struct futex_hash_bucket *hb1,
-				 struct futex_hash_bucket *hb2,
-				 union futex_key *key1, union futex_key *key2,
-				 struct futex_pi_state **ps, int set_waiters)
+static int
+futex_proxy_trylock_atomic(u32 __user *pifutex, struct futex_hash_bucket *hb1,
+			   struct futex_hash_bucket *hb2, union futex_key *key1,
+			   union futex_key *key2, struct futex_pi_state **ps,
+			   struct task_struct **exiting, int set_waiters)
 {
 	struct futex_q *top_waiter = NULL;
 	u32 curval;
@@ -1903,7 +1969,7 @@ static int futex_proxy_trylock_atomic(u32 __user *pifutex,
 	 */
 	vpid = task_pid_vnr(top_waiter->task);
 	ret = futex_lock_pi_atomic(pifutex, hb2, key2, ps, top_waiter->task,
-				   set_waiters);
+				   exiting, set_waiters);
 	if (ret == 1) {
 		requeue_pi_wake_futex(top_waiter, key2, hb2);
 		return vpid;
@@ -2032,6 +2098,8 @@ retry_private:
 	}
 
 	if (requeue_pi && (task_count - nr_wake < nr_requeue)) {
+		struct task_struct *exiting = NULL;
+
 		/*
 		 * Attempt to acquire uaddr2 and wake the top waiter. If we
 		 * intend to requeue waiters, force setting the FUTEX_WAITERS
@@ -2039,7 +2107,8 @@ retry_private:
 		 * faults rather in the requeue loop below.
 		 */
 		ret = futex_proxy_trylock_atomic(uaddr2, hb1, hb2, &key1,
-						 &key2, &pi_state, nr_requeue);
+						 &key2, &pi_state,
+						 &exiting, nr_requeue);
 
 		/*
 		 * At this point the top_waiter has either taken uaddr2 or is
@@ -2066,7 +2135,8 @@ retry_private:
 			 * If that call succeeds then we have pi_state and an
 			 * initial refcount on it.
 			 */
-			ret = lookup_pi_state(uaddr2, ret, hb2, &key2, &pi_state);
+			ret = lookup_pi_state(uaddr2, ret, hb2, &key2,
+					      &pi_state, &exiting);
 		}
 
 		switch (ret) {
@@ -2084,17 +2154,24 @@ retry_private:
 			if (!ret)
 				goto retry;
 			goto out;
+		case -EBUSY:
 		case -EAGAIN:
 			/*
 			 * Two reasons for this:
-			 * - Owner is exiting and we just wait for the
+			 * - EBUSY: Owner is exiting and we just wait for the
 			 *   exit to complete.
-			 * - The user space value changed.
+			 * - EAGAIN: The user space value changed.
 			 */
 			double_unlock_hb(hb1, hb2);
 			hb_waiters_dec(hb2);
 			put_futex_key(&key2);
 			put_futex_key(&key1);
+			/*
+			 * Handle the case where the owner is in the middle of
+			 * exiting. Wait for the exit to complete otherwise
+			 * this task might loop forever, aka. live lock.
+			 */
+			wait_for_owner_exiting(ret, exiting);
 			cond_resched();
 			goto retry;
 		default:
@@ -2801,6 +2878,7 @@ static int futex_lock_pi(u32 __user *uaddr, unsigned int flags,
 {
 	struct hrtimer_sleeper timeout, *to;
 	struct futex_pi_state *pi_state = NULL;
+	struct task_struct *exiting = NULL;
 	struct rt_mutex_waiter rt_waiter;
 	struct futex_hash_bucket *hb;
 	struct futex_q q = futex_q_init;
@@ -2822,7 +2900,8 @@ retry:
 retry_private:
 	hb = queue_lock(&q);
 
-	ret = futex_lock_pi_atomic(uaddr, hb, &q.key, &q.pi_state, current, 0);
+	ret = futex_lock_pi_atomic(uaddr, hb, &q.key, &q.pi_state, current,
+				   &exiting, 0);
 	if (unlikely(ret)) {
 		/*
 		 * Atomic work succeeded and we got the lock,
@@ -2835,15 +2914,22 @@ retry_private:
 			goto out_unlock_put_key;
 		case -EFAULT:
 			goto uaddr_faulted;
+		case -EBUSY:
 		case -EAGAIN:
 			/*
 			 * Two reasons for this:
-			 * - Task is exiting and we just wait for the
+			 * - EBUSY: Task is exiting and we just wait for the
 			 *   exit to complete.
-			 * - The user space value changed.
+			 * - EAGAIN: The user space value changed.
 			 */
 			queue_unlock(hb);
 			put_futex_key(&q.key);
+			/*
+			 * Handle the case where the owner is in the middle of
+			 * exiting. Wait for the exit to complete otherwise
+			 * this task might loop forever, aka. live lock.
+			 */
+			wait_for_owner_exiting(ret, exiting);
 			cond_resched();
 			goto retry;
 		default:
@@ -3452,11 +3538,16 @@ err_unlock:
 	return ret;
 }
 
+/* Constants for the pending_op argument of handle_futex_death */
+#define HANDLE_DEATH_PENDING	true
+#define HANDLE_DEATH_LIST	false
+
 /*
  * Process a futex-list entry, check whether it's owned by the
  * dying task, and do notification if so:
  */
-static int handle_futex_death(u32 __user *uaddr, struct task_struct *curr, int pi)
+static int handle_futex_death(u32 __user *uaddr, struct task_struct *curr,
+			      bool pi, bool pending_op)
 {
 	u32 uval, uninitialized_var(nval), mval;
 	int err;
@@ -3469,6 +3560,42 @@ retry:
 	if (get_user(uval, uaddr))
 		return -1;
 
+	/*
+	 * Special case for regular (non PI) futexes. The unlock path in
+	 * user space has two race scenarios:
+	 *
+	 * 1. The unlock path releases the user space futex value and
+	 *    before it can execute the futex() syscall to wake up
+	 *    waiters it is killed.
+	 *
+	 * 2. A woken up waiter is killed before it can acquire the
+	 *    futex in user space.
+	 *
+	 * In both cases the TID validation below prevents a wakeup of
+	 * potential waiters which can cause these waiters to block
+	 * forever.
+	 *
+	 * In both cases the following conditions are met:
+	 *
+	 *	1) task->robust_list->list_op_pending != NULL
+	 *	   @pending_op == true
+	 *	2) User space futex value == 0
+	 *	3) Regular futex: @pi == false
+	 *
+	 * If these conditions are met, it is safe to attempt waking up a
+	 * potential waiter without touching the user space futex value and
+	 * trying to set the OWNER_DIED bit. The user space futex value is
+	 * uncontended and the rest of the user space mutex state is
+	 * consistent, so a woken waiter will just take over the
+	 * uncontended futex. Setting the OWNER_DIED bit would create
+	 * inconsistent state and malfunction of the user space owner died
+	 * handling.
+	 */
+	if (pending_op && !pi && !uval) {
+		futex_wake(uaddr, 1, 1, FUTEX_BITSET_MATCH_ANY);
+		return 0;
+	}
+
 	if ((uval & FUTEX_TID_MASK) != task_pid_vnr(curr))
 		return 0;
 
@@ -3547,7 +3674,7 @@ static inline int fetch_robust_entry(struct robust_list __user **entry,
  *
  * We silently return on any sign of list-walking problem.
  */
-void exit_robust_list(struct task_struct *curr)
+static void exit_robust_list(struct task_struct *curr)
 {
 	struct robust_list_head __user *head = curr->robust_list;
 	struct robust_list __user *entry, *next_entry, *pending;
@@ -3588,10 +3715,11 @@ void exit_robust_list(struct task_struct *curr)
 		 * A pending lock might already be on the list, so
 		 * don't process it twice:
 		 */
-		if (entry != pending)
+		if (entry != pending) {
 			if (handle_futex_death((void __user *)entry + futex_offset,
-						curr, pi))
+						curr, pi, HANDLE_DEATH_LIST))
 				return;
+		}
 		if (rc)
 			return;
 		entry = next_entry;
@@ -3605,9 +3733,118 @@ void exit_robust_list(struct task_struct *curr)
 		cond_resched();
 	}
 
-	if (pending)
+	if (pending) {
 		handle_futex_death((void __user *)pending + futex_offset,
-				   curr, pip);
+				   curr, pip, HANDLE_DEATH_PENDING);
+	}
+}
+
+static void futex_cleanup(struct task_struct *tsk)
+{
+	if (unlikely(tsk->robust_list)) {
+		exit_robust_list(tsk);
+		tsk->robust_list = NULL;
+	}
+
+#ifdef CONFIG_COMPAT
+	if (unlikely(tsk->compat_robust_list)) {
+		compat_exit_robust_list(tsk);
+		tsk->compat_robust_list = NULL;
+	}
+#endif
+
+	if (unlikely(!list_empty(&tsk->pi_state_list)))
+		exit_pi_state_list(tsk);
+}
+
+/**
+ * futex_exit_recursive - Set the tasks futex state to FUTEX_STATE_DEAD
+ * @tsk:	task to set the state on
+ *
+ * Set the futex exit state of the task lockless. The futex waiter code
+ * observes that state when a task is exiting and loops until the task has
+ * actually finished the futex cleanup. The worst case for this is that the
+ * waiter runs through the wait loop until the state becomes visible.
+ *
+ * This is called from the recursive fault handling path in do_exit().
+ *
+ * This is best effort. Either the futex exit code has run already or
+ * not. If the OWNER_DIED bit has been set on the futex then the waiter can
+ * take it over. If not, the problem is pushed back to user space. If the
+ * futex exit code did not run yet, then an already queued waiter might
+ * block forever, but there is nothing which can be done about that.
+ */
+void futex_exit_recursive(struct task_struct *tsk)
+{
+	/* If the state is FUTEX_STATE_EXITING then futex_exit_mutex is held */
+	if (tsk->futex_state == FUTEX_STATE_EXITING)
+		mutex_unlock(&tsk->futex_exit_mutex);
+	tsk->futex_state = FUTEX_STATE_DEAD;
+}
+
+static void futex_cleanup_begin(struct task_struct *tsk)
+{
+	/*
+	 * Prevent various race issues against a concurrent incoming waiter
+	 * including live locks by forcing the waiter to block on
+	 * tsk->futex_exit_mutex when it observes FUTEX_STATE_EXITING in
+	 * attach_to_pi_owner().
+	 */
+	mutex_lock(&tsk->futex_exit_mutex);
+
+	/*
+	 * Switch the state to FUTEX_STATE_EXITING under tsk->pi_lock.
+	 *
+	 * This ensures that all subsequent checks of tsk->futex_state in
+	 * attach_to_pi_owner() must observe FUTEX_STATE_EXITING with
+	 * tsk->pi_lock held.
+	 *
+	 * It guarantees also that a pi_state which was queued right before
+	 * the state change under tsk->pi_lock by a concurrent waiter must
+	 * be observed in exit_pi_state_list().
+	 */
+	raw_spin_lock_irq(&tsk->pi_lock);
+	tsk->futex_state = FUTEX_STATE_EXITING;
+	raw_spin_unlock_irq(&tsk->pi_lock);
+}
+
+static void futex_cleanup_end(struct task_struct *tsk, int state)
+{
+	/*
+	 * Lockless store. The only side effect is that an observer might
+	 * take another loop until it becomes visible.
+	 */
+	tsk->futex_state = state;
+	/*
+	 * Drop the exit protection. This unblocks waiters which observed
+	 * FUTEX_STATE_EXITING to reevaluate the state.
+	 */
+	mutex_unlock(&tsk->futex_exit_mutex);
+}
+
+void futex_exec_release(struct task_struct *tsk)
+{
+	/*
+	 * The state handling is done for consistency, but in the case of
+	 * exec() there is no way to prevent futher damage as the PID stays
+	 * the same. But for the unlikely and arguably buggy case that a
+	 * futex is held on exec(), this provides at least as much state
+	 * consistency protection which is possible.
+	 */
+	futex_cleanup_begin(tsk);
+	futex_cleanup(tsk);
+	/*
+	 * Reset the state to FUTEX_STATE_OK. The task is alive and about
+	 * exec a new binary.
+	 */
+	futex_cleanup_end(tsk, FUTEX_STATE_OK);
+}
+
+void futex_exit_release(struct task_struct *tsk)
+{
+	futex_cleanup_begin(tsk);
+	futex_cleanup(tsk);
+	futex_cleanup_end(tsk, FUTEX_STATE_DEAD);
 }
 
 long do_futex(u32 __user *uaddr, int op, u32 val, ktime_t *timeout,
@@ -3737,7 +3974,7 @@ static void __user *futex_uaddr(struct robust_list __user *entry,
  *
  * We silently return on any sign of list-walking problem.
  */
-void compat_exit_robust_list(struct task_struct *curr)
+static void compat_exit_robust_list(struct task_struct *curr)
 {
 	struct compat_robust_list_head __user *head = curr->compat_robust_list;
 	struct robust_list __user *entry, *next_entry, *pending;
@@ -3784,7 +4021,8 @@ void compat_exit_robust_list(struct task_struct *curr)
 		if (entry != pending) {
 			void __user *uaddr = futex_uaddr(entry, futex_offset);
 
-			if (handle_futex_death(uaddr, curr, pi))
+			if (handle_futex_death(uaddr, curr, pi,
+					       HANDLE_DEATH_LIST))
 				return;
 		}
 		if (rc)
@@ -3803,7 +4041,7 @@ void compat_exit_robust_list(struct task_struct *curr)
 	if (pending) {
 		void __user *uaddr = futex_uaddr(pending, futex_offset);
 
-		handle_futex_death(uaddr, curr, pip);
+		handle_futex_death(uaddr, curr, pip, HANDLE_DEATH_PENDING);
 	}
 }
 
diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c
index 233459c03b5a..32282e7112d3 100644
--- a/kernel/locking/lockdep.c
+++ b/kernel/locking/lockdep.c
@@ -4208,11 +4208,9 @@ static int __lock_downgrade(struct lockdep_map *lock, unsigned long ip)
 }
 
 /*
- * Remove the lock to the list of currently held locks - this gets
+ * Remove the lock from the list of currently held locks - this gets
  * called on mutex_unlock()/spin_unlock*() (or on a failed
  * mutex_lock_interruptible()).
- *
- * @nested is an hysterical artifact, needs a tree wide cleanup.
  */
 static int
 __lock_release(struct lockdep_map *lock, unsigned long ip)
@@ -4491,8 +4489,7 @@ void lock_acquire(struct lockdep_map *lock, unsigned int subclass,
 }
 EXPORT_SYMBOL_GPL(lock_acquire);
 
-void lock_release(struct lockdep_map *lock, int nested,
-			  unsigned long ip)
+void lock_release(struct lockdep_map *lock, unsigned long ip)
 {
 	unsigned long flags;
 
diff --git a/kernel/locking/locktorture.c b/kernel/locking/locktorture.c
index c513031cd7e3..99475a66c94f 100644
--- a/kernel/locking/locktorture.c
+++ b/kernel/locking/locktorture.c
@@ -16,7 +16,6 @@
 #include <linux/kthread.h>
 #include <linux/sched/rt.h>
 #include <linux/spinlock.h>
-#include <linux/rwlock.h>
 #include <linux/mutex.h>
 #include <linux/rwsem.h>
 #include <linux/smp.h>
@@ -889,16 +888,16 @@ static int __init lock_torture_init(void)
 		cxt.nrealwriters_stress = 2 * num_online_cpus();
 
 #ifdef CONFIG_DEBUG_MUTEXES
-	if (strncmp(torture_type, "mutex", 5) == 0)
+	if (str_has_prefix(torture_type, "mutex"))
 		cxt.debug_lock = true;
 #endif
 #ifdef CONFIG_DEBUG_RT_MUTEXES
-	if (strncmp(torture_type, "rtmutex", 7) == 0)
+	if (str_has_prefix(torture_type, "rtmutex"))
 		cxt.debug_lock = true;
 #endif
 #ifdef CONFIG_DEBUG_SPINLOCK
-	if ((strncmp(torture_type, "spin", 4) == 0) ||
-	    (strncmp(torture_type, "rw_lock", 7) == 0))
+	if ((str_has_prefix(torture_type, "spin")) ||
+	    (str_has_prefix(torture_type, "rw_lock")))
 		cxt.debug_lock = true;
 #endif
 
diff --git a/kernel/locking/mutex.c b/kernel/locking/mutex.c
index 468a9b8422e3..54cc5f9286e9 100644
--- a/kernel/locking/mutex.c
+++ b/kernel/locking/mutex.c
@@ -733,6 +733,9 @@ static noinline void __sched __mutex_unlock_slowpath(struct mutex *lock, unsigne
  */
 void __sched mutex_unlock(struct mutex *lock)
 {
+#ifdef CONFIG_DEBUG_MUTEXES
+	WARN_ON(in_interrupt());
+#endif
 #ifndef CONFIG_DEBUG_LOCK_ALLOC
 	if (__mutex_unlock_fast(lock))
 		return;
@@ -1091,7 +1094,7 @@ err:
 err_early_kill:
 	spin_unlock(&lock->wait_lock);
 	debug_mutex_free_waiter(&waiter);
-	mutex_release(&lock->dep_map, 1, ip);
+	mutex_release(&lock->dep_map, ip);
 	preempt_enable();
 	return ret;
 }
@@ -1225,7 +1228,7 @@ static noinline void __sched __mutex_unlock_slowpath(struct mutex *lock, unsigne
 	DEFINE_WAKE_Q(wake_q);
 	unsigned long owner;
 
-	mutex_release(&lock->dep_map, 1, ip);
+	mutex_release(&lock->dep_map, ip);
 
 	/*
 	 * Release the lock before (potentially) taking the spinlock such that
@@ -1413,6 +1416,7 @@ int __sched mutex_trylock(struct mutex *lock)
 
 #ifdef CONFIG_DEBUG_MUTEXES
 	DEBUG_LOCKS_WARN_ON(lock->magic != lock);
+	WARN_ON(in_interrupt());
 #endif
 
 	locked = __mutex_trylock(lock);
diff --git a/kernel/locking/rtmutex.c b/kernel/locking/rtmutex.c
index 2874bf556162..851bbb10819d 100644
--- a/kernel/locking/rtmutex.c
+++ b/kernel/locking/rtmutex.c
@@ -1517,7 +1517,7 @@ int __sched rt_mutex_lock_interruptible(struct rt_mutex *lock)
 	mutex_acquire(&lock->dep_map, 0, 0, _RET_IP_);
 	ret = rt_mutex_fastlock(lock, TASK_INTERRUPTIBLE, rt_mutex_slowlock);
 	if (ret)
-		mutex_release(&lock->dep_map, 1, _RET_IP_);
+		mutex_release(&lock->dep_map, _RET_IP_);
 
 	return ret;
 }
@@ -1561,7 +1561,7 @@ rt_mutex_timed_lock(struct rt_mutex *lock, struct hrtimer_sleeper *timeout)
 				       RT_MUTEX_MIN_CHAINWALK,
 				       rt_mutex_slowlock);
 	if (ret)
-		mutex_release(&lock->dep_map, 1, _RET_IP_);
+		mutex_release(&lock->dep_map, _RET_IP_);
 
 	return ret;
 }
@@ -1600,7 +1600,7 @@ EXPORT_SYMBOL_GPL(rt_mutex_trylock);
  */
 void __sched rt_mutex_unlock(struct rt_mutex *lock)
 {
-	mutex_release(&lock->dep_map, 1, _RET_IP_);
+	mutex_release(&lock->dep_map, _RET_IP_);
 	rt_mutex_fastunlock(lock, rt_mutex_slowunlock);
 }
 EXPORT_SYMBOL_GPL(rt_mutex_unlock);
diff --git a/kernel/locking/rwsem.c b/kernel/locking/rwsem.c
index eef04551eae7..44e68761f432 100644
--- a/kernel/locking/rwsem.c
+++ b/kernel/locking/rwsem.c
@@ -1504,7 +1504,7 @@ int __sched down_read_killable(struct rw_semaphore *sem)
 	rwsem_acquire_read(&sem->dep_map, 0, 0, _RET_IP_);
 
 	if (LOCK_CONTENDED_RETURN(sem, __down_read_trylock, __down_read_killable)) {
-		rwsem_release(&sem->dep_map, 1, _RET_IP_);
+		rwsem_release(&sem->dep_map, _RET_IP_);
 		return -EINTR;
 	}
 
@@ -1546,7 +1546,7 @@ int __sched down_write_killable(struct rw_semaphore *sem)
 
 	if (LOCK_CONTENDED_RETURN(sem, __down_write_trylock,
 				  __down_write_killable)) {
-		rwsem_release(&sem->dep_map, 1, _RET_IP_);
+		rwsem_release(&sem->dep_map, _RET_IP_);
 		return -EINTR;
 	}
 
@@ -1573,7 +1573,7 @@ EXPORT_SYMBOL(down_write_trylock);
  */
 void up_read(struct rw_semaphore *sem)
 {
-	rwsem_release(&sem->dep_map, 1, _RET_IP_);
+	rwsem_release(&sem->dep_map, _RET_IP_);
 	__up_read(sem);
 }
 EXPORT_SYMBOL(up_read);
@@ -1583,7 +1583,7 @@ EXPORT_SYMBOL(up_read);
  */
 void up_write(struct rw_semaphore *sem)
 {
-	rwsem_release(&sem->dep_map, 1, _RET_IP_);
+	rwsem_release(&sem->dep_map, _RET_IP_);
 	__up_write(sem);
 }
 EXPORT_SYMBOL(up_write);
@@ -1639,7 +1639,7 @@ int __sched down_write_killable_nested(struct rw_semaphore *sem, int subclass)
 
 	if (LOCK_CONTENDED_RETURN(sem, __down_write_trylock,
 				  __down_write_killable)) {
-		rwsem_release(&sem->dep_map, 1, _RET_IP_);
+		rwsem_release(&sem->dep_map, _RET_IP_);
 		return -EINTR;
 	}
 
diff --git a/kernel/panic.c b/kernel/panic.c
index f470a038b05b..b69ee9e76cb2 100644
--- a/kernel/panic.c
+++ b/kernel/panic.c
@@ -671,17 +671,6 @@ EXPORT_SYMBOL(__stack_chk_fail);
 
 #endif
 
-#ifdef CONFIG_ARCH_HAS_REFCOUNT
-void refcount_error_report(struct pt_regs *regs, const char *err)
-{
-	WARN_RATELIMIT(1, "refcount_t %s at %pB in %s[%d], uid/euid: %u/%u\n",
-		err, (void *)instruction_pointer(regs),
-		current->comm, task_pid_nr(current),
-		from_kuid_munged(&init_user_ns, current_uid()),
-		from_kuid_munged(&init_user_ns, current_euid()));
-}
-#endif
-
 core_param(panic, panic_timeout, int, 0644);
 core_param(panic_print, panic_print, ulong, 0644);
 core_param(pause_on_oops, pause_on_oops, int, 0644);
diff --git a/kernel/power/snapshot.c b/kernel/power/snapshot.c
index 83105874f255..26b9168321e7 100644
--- a/kernel/power/snapshot.c
+++ b/kernel/power/snapshot.c
@@ -734,8 +734,15 @@ zone_found:
 	 * We have found the zone. Now walk the radix tree to find the leaf node
 	 * for our PFN.
 	 */
+
+	/*
+	 * If the zone we wish to scan is the the current zone and the
+	 * pfn falls into the current node then we do not need to walk
+	 * the tree.
+	 */
 	node = bm->cur.node;
-	if (((pfn - zone->start_pfn) & ~BM_BLOCK_MASK) == bm->cur.node_pfn)
+	if (zone == bm->cur.zone &&
+	    ((pfn - zone->start_pfn) & ~BM_BLOCK_MASK) == bm->cur.node_pfn)
 		goto node_found;
 
 	node      = zone->rtree;
diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c
index ca65327a6de8..c8be5a0f5259 100644
--- a/kernel/printk/printk.c
+++ b/kernel/printk/printk.c
@@ -248,7 +248,7 @@ static void __up_console_sem(unsigned long ip)
 {
 	unsigned long flags;
 
-	mutex_release(&console_lock_dep_map, 1, ip);
+	mutex_release(&console_lock_dep_map, ip);
 
 	printk_safe_enter_irqsave(flags);
 	up(&console_sem);
@@ -1679,20 +1679,20 @@ static int console_lock_spinning_disable_and_check(void)
 	raw_spin_unlock(&console_owner_lock);
 
 	if (!waiter) {
-		spin_release(&console_owner_dep_map, 1, _THIS_IP_);
+		spin_release(&console_owner_dep_map, _THIS_IP_);
 		return 0;
 	}
 
 	/* The waiter is now free to continue */
 	WRITE_ONCE(console_waiter, false);
 
-	spin_release(&console_owner_dep_map, 1, _THIS_IP_);
+	spin_release(&console_owner_dep_map, _THIS_IP_);
 
 	/*
 	 * Hand off console_lock to waiter. The waiter will perform
 	 * the up(). After this, the waiter is the console_lock owner.
 	 */
-	mutex_release(&console_lock_dep_map, 1, _THIS_IP_);
+	mutex_release(&console_lock_dep_map, _THIS_IP_);
 	return 1;
 }
 
@@ -1746,7 +1746,7 @@ static int console_trylock_spinning(void)
 	/* Owner will clear console_waiter on hand off */
 	while (READ_ONCE(console_waiter))
 		cpu_relax();
-	spin_release(&console_owner_dep_map, 1, _THIS_IP_);
+	spin_release(&console_owner_dep_map, _THIS_IP_);
 
 	printk_safe_exit_irqrestore(flags);
 	/*
diff --git a/kernel/rcu/rcu.h b/kernel/rcu/rcu.h
index 8fd4f82c9b3d..ab504fbc76ca 100644
--- a/kernel/rcu/rcu.h
+++ b/kernel/rcu/rcu.h
@@ -299,6 +299,8 @@ static inline void rcu_init_levelspread(int *levelspread, const int *levelcnt)
 {
 	int i;
 
+	for (i = 0; i < RCU_NUM_LVLS; i++)
+		levelspread[i] = INT_MIN;
 	if (rcu_fanout_exact) {
 		levelspread[rcu_num_lvls - 1] = rcu_fanout_leaf;
 		for (i = rcu_num_lvls - 2; i >= 0; i--)
@@ -455,7 +457,6 @@ enum rcutorture_type {
 #if defined(CONFIG_TREE_RCU) || defined(CONFIG_PREEMPT_RCU)
 void rcutorture_get_gp_data(enum rcutorture_type test_type, int *flags,
 			    unsigned long *gp_seq);
-void rcutorture_record_progress(unsigned long vernum);
 void do_trace_rcu_torture_read(const char *rcutorturename,
 			       struct rcu_head *rhp,
 			       unsigned long secs,
@@ -468,7 +469,6 @@ static inline void rcutorture_get_gp_data(enum rcutorture_type test_type,
 	*flags = 0;
 	*gp_seq = 0;
 }
-static inline void rcutorture_record_progress(unsigned long vernum) { }
 #ifdef CONFIG_RCU_TRACE
 void do_trace_rcu_torture_read(const char *rcutorturename,
 			       struct rcu_head *rhp,
diff --git a/kernel/rcu/rcu_segcblist.c b/kernel/rcu/rcu_segcblist.c
index 495c58ce1640..cbc87b804db9 100644
--- a/kernel/rcu/rcu_segcblist.c
+++ b/kernel/rcu/rcu_segcblist.c
@@ -88,7 +88,7 @@ struct rcu_head *rcu_cblist_dequeue(struct rcu_cblist *rclp)
 }
 
 /* Set the length of an rcu_segcblist structure. */
-void rcu_segcblist_set_len(struct rcu_segcblist *rsclp, long v)
+static void rcu_segcblist_set_len(struct rcu_segcblist *rsclp, long v)
 {
 #ifdef CONFIG_RCU_NOCB_CPU
 	atomic_long_set(&rsclp->len, v);
@@ -104,7 +104,7 @@ void rcu_segcblist_set_len(struct rcu_segcblist *rsclp, long v)
  * This increase is fully ordered with respect to the callers accesses
  * both before and after.
  */
-void rcu_segcblist_add_len(struct rcu_segcblist *rsclp, long v)
+static void rcu_segcblist_add_len(struct rcu_segcblist *rsclp, long v)
 {
 #ifdef CONFIG_RCU_NOCB_CPU
 	smp_mb__before_atomic(); /* Up to the caller! */
@@ -134,7 +134,7 @@ void rcu_segcblist_inc_len(struct rcu_segcblist *rsclp)
  * with the actual number of callbacks on the structure.  This exchange is
  * fully ordered with respect to the callers accesses both before and after.
  */
-long rcu_segcblist_xchg_len(struct rcu_segcblist *rsclp, long v)
+static long rcu_segcblist_xchg_len(struct rcu_segcblist *rsclp, long v)
 {
 #ifdef CONFIG_RCU_NOCB_CPU
 	return atomic_long_xchg(&rsclp->len, v);
diff --git a/kernel/rcu/rcuperf.c b/kernel/rcu/rcuperf.c
index 5a879d073c1c..5f884d560384 100644
--- a/kernel/rcu/rcuperf.c
+++ b/kernel/rcu/rcuperf.c
@@ -109,15 +109,6 @@ static unsigned long b_rcu_perf_writer_started;
 static unsigned long b_rcu_perf_writer_finished;
 static DEFINE_PER_CPU(atomic_t, n_async_inflight);
 
-static int rcu_perf_writer_state;
-#define RTWS_INIT		0
-#define RTWS_ASYNC		1
-#define RTWS_BARRIER		2
-#define RTWS_EXP_SYNC		3
-#define RTWS_SYNC		4
-#define RTWS_IDLE		5
-#define RTWS_STOPPING		6
-
 #define MAX_MEAS 10000
 #define MIN_MEAS 100
 
@@ -404,25 +395,20 @@ retry:
 			if (!rhp)
 				rhp = kmalloc(sizeof(*rhp), GFP_KERNEL);
 			if (rhp && atomic_read(this_cpu_ptr(&n_async_inflight)) < gp_async_max) {
-				rcu_perf_writer_state = RTWS_ASYNC;
 				atomic_inc(this_cpu_ptr(&n_async_inflight));
 				cur_ops->async(rhp, rcu_perf_async_cb);
 				rhp = NULL;
 			} else if (!kthread_should_stop()) {
-				rcu_perf_writer_state = RTWS_BARRIER;
 				cur_ops->gp_barrier();
 				goto retry;
 			} else {
 				kfree(rhp); /* Because we are stopping. */
 			}
 		} else if (gp_exp) {
-			rcu_perf_writer_state = RTWS_EXP_SYNC;
 			cur_ops->exp_sync();
 		} else {
-			rcu_perf_writer_state = RTWS_SYNC;
 			cur_ops->sync();
 		}
-		rcu_perf_writer_state = RTWS_IDLE;
 		t = ktime_get_mono_fast_ns();
 		*wdp = t - *wdp;
 		i_max = i;
@@ -463,10 +449,8 @@ retry:
 		rcu_perf_wait_shutdown();
 	} while (!torture_must_stop());
 	if (gp_async) {
-		rcu_perf_writer_state = RTWS_BARRIER;
 		cur_ops->gp_barrier();
 	}
-	rcu_perf_writer_state = RTWS_STOPPING;
 	writer_n_durations[me] = i_max;
 	torture_kthread_stopping("rcu_perf_writer");
 	return 0;
diff --git a/kernel/rcu/rcutorture.c b/kernel/rcu/rcutorture.c
index 3c9feca1eab1..dee043feb71f 100644
--- a/kernel/rcu/rcutorture.c
+++ b/kernel/rcu/rcutorture.c
@@ -44,6 +44,7 @@
 #include <linux/sched/debug.h>
 #include <linux/sched/sysctl.h>
 #include <linux/oom.h>
+#include <linux/tick.h>
 
 #include "rcu.h"
 
@@ -1363,15 +1364,15 @@ rcu_torture_reader(void *arg)
 	set_user_nice(current, MAX_NICE);
 	if (irqreader && cur_ops->irq_capable)
 		timer_setup_on_stack(&t, rcu_torture_timer, 0);
-
+	tick_dep_set_task(current, TICK_DEP_BIT_RCU);
 	do {
 		if (irqreader && cur_ops->irq_capable) {
 			if (!timer_pending(&t))
 				mod_timer(&t, jiffies + 1);
 		}
-		if (!rcu_torture_one_read(&rand))
+		if (!rcu_torture_one_read(&rand) && !torture_must_stop())
 			schedule_timeout_interruptible(HZ);
-		if (time_after(jiffies, lastsleep)) {
+		if (time_after(jiffies, lastsleep) && !torture_must_stop()) {
 			schedule_timeout_interruptible(1);
 			lastsleep = jiffies + 10;
 		}
@@ -1383,6 +1384,7 @@ rcu_torture_reader(void *arg)
 		del_timer_sync(&t);
 		destroy_timer_on_stack(&t);
 	}
+	tick_dep_clear_task(current, TICK_DEP_BIT_RCU);
 	torture_kthread_stopping("rcu_torture_reader");
 	return 0;
 }
@@ -1442,15 +1444,18 @@ rcu_torture_stats_print(void)
 		n_rcu_torture_barrier_error);
 
 	pr_alert("%s%s ", torture_type, TORTURE_FLAG);
-	if (atomic_read(&n_rcu_torture_mberror) != 0 ||
-	    n_rcu_torture_barrier_error != 0 ||
-	    n_rcu_torture_boost_ktrerror != 0 ||
-	    n_rcu_torture_boost_rterror != 0 ||
-	    n_rcu_torture_boost_failure != 0 ||
+	if (atomic_read(&n_rcu_torture_mberror) ||
+	    n_rcu_torture_barrier_error || n_rcu_torture_boost_ktrerror ||
+	    n_rcu_torture_boost_rterror || n_rcu_torture_boost_failure ||
 	    i > 1) {
 		pr_cont("%s", "!!! ");
 		atomic_inc(&n_rcu_torture_error);
-		WARN_ON_ONCE(1);
+		WARN_ON_ONCE(atomic_read(&n_rcu_torture_mberror));
+		WARN_ON_ONCE(n_rcu_torture_barrier_error);  // rcu_barrier()
+		WARN_ON_ONCE(n_rcu_torture_boost_ktrerror); // no boost kthread
+		WARN_ON_ONCE(n_rcu_torture_boost_rterror); // can't set RT prio
+		WARN_ON_ONCE(n_rcu_torture_boost_failure); // RCU boost failed
+		WARN_ON_ONCE(i > 1); // Too-short grace period
 	}
 	pr_cont("Reader Pipe: ");
 	for (i = 0; i < RCU_TORTURE_PIPE_LEN + 1; i++)
@@ -1729,10 +1734,10 @@ static void rcu_torture_fwd_prog_cond_resched(unsigned long iter)
 		// Real call_rcu() floods hit userspace, so emulate that.
 		if (need_resched() || (iter & 0xfff))
 			schedule();
-	} else {
-		// No userspace emulation: CB invocation throttles call_rcu()
-		cond_resched();
+		return;
 	}
+	// No userspace emulation: CB invocation throttles call_rcu()
+	cond_resched();
 }
 
 /*
@@ -1759,6 +1764,11 @@ static unsigned long rcu_torture_fwd_prog_cbfree(void)
 		kfree(rfcp);
 		freed++;
 		rcu_torture_fwd_prog_cond_resched(freed);
+		if (tick_nohz_full_enabled()) {
+			local_irq_save(flags);
+			rcu_momentary_dyntick_idle();
+			local_irq_restore(flags);
+		}
 	}
 	return freed;
 }
@@ -1803,7 +1813,7 @@ static void rcu_torture_fwd_prog_nr(int *tested, int *tested_tries)
 		udelay(10);
 		cur_ops->readunlock(idx);
 		if (!fwd_progress_need_resched || need_resched())
-			rcu_torture_fwd_prog_cond_resched(1);
+			cond_resched();
 	}
 	(*tested_tries)++;
 	if (!time_before(jiffies, stopat) &&
@@ -1833,6 +1843,7 @@ static void rcu_torture_fwd_prog_nr(int *tested, int *tested_tries)
 static void rcu_torture_fwd_prog_cr(void)
 {
 	unsigned long cver;
+	unsigned long flags;
 	unsigned long gps;
 	int i;
 	long n_launders;
@@ -1865,6 +1876,7 @@ static void rcu_torture_fwd_prog_cr(void)
 	cver = READ_ONCE(rcu_torture_current_version);
 	gps = cur_ops->get_gp_seq();
 	rcu_launder_gp_seq_start = gps;
+	tick_dep_set_task(current, TICK_DEP_BIT_RCU);
 	while (time_before(jiffies, stopat) &&
 	       !shutdown_time_arrived() &&
 	       !READ_ONCE(rcu_fwd_emergency_stop) && !torture_must_stop()) {
@@ -1891,6 +1903,11 @@ static void rcu_torture_fwd_prog_cr(void)
 		}
 		cur_ops->call(&rfcp->rh, rcu_torture_fwd_cb_cr);
 		rcu_torture_fwd_prog_cond_resched(n_launders + n_max_cbs);
+		if (tick_nohz_full_enabled()) {
+			local_irq_save(flags);
+			rcu_momentary_dyntick_idle();
+			local_irq_restore(flags);
+		}
 	}
 	stoppedat = jiffies;
 	n_launders_cb_snap = READ_ONCE(n_launders_cb);
@@ -1911,6 +1928,7 @@ static void rcu_torture_fwd_prog_cr(void)
 		rcu_torture_fwd_cb_hist();
 	}
 	schedule_timeout_uninterruptible(HZ); /* Let CBs drain. */
+	tick_dep_clear_task(current, TICK_DEP_BIT_RCU);
 	WRITE_ONCE(rcu_fwd_cb_nodelay, false);
 }
 
diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index 81105141b6a8..1694a6b57ad8 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -364,7 +364,7 @@ bool rcu_eqs_special_set(int cpu)
  *
  * The caller must have disabled interrupts and must not be idle.
  */
-static void __maybe_unused rcu_momentary_dyntick_idle(void)
+void rcu_momentary_dyntick_idle(void)
 {
 	int special;
 
@@ -375,6 +375,7 @@ static void __maybe_unused rcu_momentary_dyntick_idle(void)
 	WARN_ON_ONCE(!(special & RCU_DYNTICK_CTRL_CTR));
 	rcu_preempt_deferred_qs(current);
 }
+EXPORT_SYMBOL_GPL(rcu_momentary_dyntick_idle);
 
 /**
  * rcu_is_cpu_rrupt_from_idle - see if interrupted from idle
@@ -496,7 +497,7 @@ module_param_cb(jiffies_till_next_fqs, &next_fqs_jiffies_ops, &jiffies_till_next
 module_param(rcu_kick_kthreads, bool, 0644);
 
 static void force_qs_rnp(int (*f)(struct rcu_data *rdp));
-static int rcu_pending(void);
+static int rcu_pending(int user);
 
 /*
  * Return the number of RCU GPs completed thus far for debug & stats.
@@ -824,6 +825,11 @@ static __always_inline void rcu_nmi_enter_common(bool irq)
 			rcu_cleanup_after_idle();
 
 		incby = 1;
+	} else if (tick_nohz_full_cpu(rdp->cpu) &&
+		   rdp->dynticks_nmi_nesting == DYNTICK_IRQ_NONIDLE &&
+		   READ_ONCE(rdp->rcu_urgent_qs) && !rdp->rcu_forced_tick) {
+		rdp->rcu_forced_tick = true;
+		tick_dep_set_cpu(rdp->cpu, TICK_DEP_BIT_RCU);
 	}
 	trace_rcu_dyntick(incby == 1 ? TPS("Endirq") : TPS("++="),
 			  rdp->dynticks_nmi_nesting,
@@ -885,6 +891,21 @@ void rcu_irq_enter_irqson(void)
 	local_irq_restore(flags);
 }
 
+/*
+ * If any sort of urgency was applied to the current CPU (for example,
+ * the scheduler-clock interrupt was enabled on a nohz_full CPU) in order
+ * to get to a quiescent state, disable it.
+ */
+static void rcu_disable_urgency_upon_qs(struct rcu_data *rdp)
+{
+	WRITE_ONCE(rdp->rcu_urgent_qs, false);
+	WRITE_ONCE(rdp->rcu_need_heavy_qs, false);
+	if (tick_nohz_full_cpu(rdp->cpu) && rdp->rcu_forced_tick) {
+		tick_dep_clear_cpu(rdp->cpu, TICK_DEP_BIT_RCU);
+		rdp->rcu_forced_tick = false;
+	}
+}
+
 /**
  * rcu_is_watching - see if RCU thinks that the current CPU is not idle
  *
@@ -1073,6 +1094,7 @@ static int rcu_implicit_dynticks_qs(struct rcu_data *rdp)
 	if (tick_nohz_full_cpu(rdp->cpu) &&
 		   time_after(jiffies,
 			      READ_ONCE(rdp->last_fqs_resched) + jtsq * 3)) {
+		WRITE_ONCE(*ruqp, true);
 		resched_cpu(rdp->cpu);
 		WRITE_ONCE(rdp->last_fqs_resched, jiffies);
 	}
@@ -1968,7 +1990,6 @@ rcu_report_qs_rdp(int cpu, struct rcu_data *rdp)
 		return;
 	}
 	mask = rdp->grpmask;
-	rdp->core_needs_qs = false;
 	if ((rnp->qsmask & mask) == 0) {
 		raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
 	} else {
@@ -1979,6 +2000,7 @@ rcu_report_qs_rdp(int cpu, struct rcu_data *rdp)
 		if (!offloaded)
 			needwake = rcu_accelerate_cbs(rnp, rdp);
 
+		rcu_disable_urgency_upon_qs(rdp);
 		rcu_report_qs_rnp(mask, rnp, rnp->gp_seq, flags);
 		/* ^^^ Released rnp->lock */
 		if (needwake)
@@ -2101,6 +2123,9 @@ int rcutree_dead_cpu(unsigned int cpu)
 	rcu_boost_kthread_setaffinity(rnp, -1);
 	/* Do any needed no-CB deferred wakeups from this CPU. */
 	do_nocb_deferred_wakeup(per_cpu_ptr(&rcu_data, cpu));
+
+	// Stop-machine done, so allow nohz_full to disable tick.
+	tick_dep_clear(TICK_DEP_BIT_RCU);
 	return 0;
 }
 
@@ -2151,6 +2176,7 @@ static void rcu_do_batch(struct rcu_data *rdp)
 	rcu_nocb_unlock_irqrestore(rdp, flags);
 
 	/* Invoke callbacks. */
+	tick_dep_set_task(current, TICK_DEP_BIT_RCU);
 	rhp = rcu_cblist_dequeue(&rcl);
 	for (; rhp; rhp = rcu_cblist_dequeue(&rcl)) {
 		debug_rcu_head_unqueue(rhp);
@@ -2217,6 +2243,7 @@ static void rcu_do_batch(struct rcu_data *rdp)
 	/* Re-invoke RCU core processing if there are callbacks remaining. */
 	if (!offloaded && rcu_segcblist_ready_cbs(&rdp->cblist))
 		invoke_rcu_core();
+	tick_dep_clear_task(current, TICK_DEP_BIT_RCU);
 }
 
 /*
@@ -2241,7 +2268,7 @@ void rcu_sched_clock_irq(int user)
 		__this_cpu_write(rcu_data.rcu_urgent_qs, false);
 	}
 	rcu_flavor_sched_clock_irq(user);
-	if (rcu_pending())
+	if (rcu_pending(user))
 		invoke_rcu_core();
 
 	trace_rcu_utilization(TPS("End scheduler-tick"));
@@ -2259,6 +2286,7 @@ static void force_qs_rnp(int (*f)(struct rcu_data *rdp))
 	int cpu;
 	unsigned long flags;
 	unsigned long mask;
+	struct rcu_data *rdp;
 	struct rcu_node *rnp;
 
 	rcu_for_each_leaf_node(rnp) {
@@ -2283,8 +2311,11 @@ static void force_qs_rnp(int (*f)(struct rcu_data *rdp))
 		for_each_leaf_node_possible_cpu(rnp, cpu) {
 			unsigned long bit = leaf_node_cpu_bit(rnp, cpu);
 			if ((rnp->qsmask & bit) != 0) {
-				if (f(per_cpu_ptr(&rcu_data, cpu)))
+				rdp = per_cpu_ptr(&rcu_data, cpu);
+				if (f(rdp)) {
 					mask |= bit;
+					rcu_disable_urgency_upon_qs(rdp);
+				}
 			}
 		}
 		if (mask != 0) {
@@ -2312,7 +2343,7 @@ void rcu_force_quiescent_state(void)
 	rnp = __this_cpu_read(rcu_data.mynode);
 	for (; rnp != NULL; rnp = rnp->parent) {
 		ret = (READ_ONCE(rcu_state.gp_flags) & RCU_GP_FLAG_FQS) ||
-		      !raw_spin_trylock(&rnp->fqslock);
+		       !raw_spin_trylock(&rnp->fqslock);
 		if (rnp_old != NULL)
 			raw_spin_unlock(&rnp_old->fqslock);
 		if (ret)
@@ -2786,8 +2817,9 @@ EXPORT_SYMBOL_GPL(cond_synchronize_rcu);
  * CPU-local state are performed first.  However, we must check for CPU
  * stalls first, else we might not get a chance.
  */
-static int rcu_pending(void)
+static int rcu_pending(int user)
 {
+	bool gp_in_progress;
 	struct rcu_data *rdp = this_cpu_ptr(&rcu_data);
 	struct rcu_node *rnp = rdp->mynode;
 
@@ -2798,12 +2830,13 @@ static int rcu_pending(void)
 	if (rcu_nocb_need_deferred_wakeup(rdp))
 		return 1;
 
-	/* Is this CPU a NO_HZ_FULL CPU that should ignore RCU? */
-	if (rcu_nohz_full_cpu())
+	/* Is this a nohz_full CPU in userspace or idle?  (Ignore RCU if so.) */
+	if ((user || rcu_is_cpu_rrupt_from_idle()) && rcu_nohz_full_cpu())
 		return 0;
 
 	/* Is the RCU core waiting for a quiescent state from this CPU? */
-	if (rdp->core_needs_qs && !rdp->cpu_no_qs.b.norm)
+	gp_in_progress = rcu_gp_in_progress();
+	if (rdp->core_needs_qs && !rdp->cpu_no_qs.b.norm && gp_in_progress)
 		return 1;
 
 	/* Does this CPU have callbacks ready to invoke? */
@@ -2811,8 +2844,7 @@ static int rcu_pending(void)
 		return 1;
 
 	/* Has RCU gone idle with this CPU needing another grace period? */
-	if (!rcu_gp_in_progress() &&
-	    rcu_segcblist_is_enabled(&rdp->cblist) &&
+	if (!gp_in_progress && rcu_segcblist_is_enabled(&rdp->cblist) &&
 	    (!IS_ENABLED(CONFIG_RCU_NOCB_CPU) ||
 	     !rcu_segcblist_is_offloaded(&rdp->cblist)) &&
 	    !rcu_segcblist_restempty(&rdp->cblist, RCU_NEXT_READY_TAIL))
@@ -2845,7 +2877,7 @@ static void rcu_barrier_callback(struct rcu_head *rhp)
 {
 	if (atomic_dec_and_test(&rcu_state.barrier_cpu_count)) {
 		rcu_barrier_trace(TPS("LastCB"), -1,
-				   rcu_state.barrier_sequence);
+				  rcu_state.barrier_sequence);
 		complete(&rcu_state.barrier_completion);
 	} else {
 		rcu_barrier_trace(TPS("CB"), -1, rcu_state.barrier_sequence);
@@ -2869,7 +2901,7 @@ static void rcu_barrier_func(void *unused)
 	} else {
 		debug_rcu_head_unqueue(&rdp->barrier_head);
 		rcu_barrier_trace(TPS("IRQNQ"), -1,
-				   rcu_state.barrier_sequence);
+				  rcu_state.barrier_sequence);
 	}
 	rcu_nocb_unlock(rdp);
 }
@@ -2896,7 +2928,7 @@ void rcu_barrier(void)
 	/* Did someone else do our work for us? */
 	if (rcu_seq_done(&rcu_state.barrier_sequence, s)) {
 		rcu_barrier_trace(TPS("EarlyExit"), -1,
-				   rcu_state.barrier_sequence);
+				  rcu_state.barrier_sequence);
 		smp_mb(); /* caller's subsequent code after above check. */
 		mutex_unlock(&rcu_state.barrier_mutex);
 		return;
@@ -2928,11 +2960,11 @@ void rcu_barrier(void)
 			continue;
 		if (rcu_segcblist_n_cbs(&rdp->cblist)) {
 			rcu_barrier_trace(TPS("OnlineQ"), cpu,
-					   rcu_state.barrier_sequence);
+					  rcu_state.barrier_sequence);
 			smp_call_function_single(cpu, rcu_barrier_func, NULL, 1);
 		} else {
 			rcu_barrier_trace(TPS("OnlineNQ"), cpu,
-					   rcu_state.barrier_sequence);
+					  rcu_state.barrier_sequence);
 		}
 	}
 	put_online_cpus();
@@ -3083,6 +3115,9 @@ int rcutree_online_cpu(unsigned int cpu)
 		return 0; /* Too early in boot for scheduler work. */
 	sync_sched_exp_online_cleanup(cpu);
 	rcutree_affinity_setting(cpu, -1);
+
+	// Stop-machine done, so allow nohz_full to disable tick.
+	tick_dep_clear(TICK_DEP_BIT_RCU);
 	return 0;
 }
 
@@ -3103,6 +3138,9 @@ int rcutree_offline_cpu(unsigned int cpu)
 	raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
 
 	rcutree_affinity_setting(cpu, cpu);
+
+	// nohz_full CPUs need the tick for stop-machine to work quickly
+	tick_dep_set(TICK_DEP_BIT_RCU);
 	return 0;
 }
 
@@ -3148,6 +3186,7 @@ void rcu_cpu_starting(unsigned int cpu)
 	rdp->rcu_onl_gp_seq = READ_ONCE(rcu_state.gp_seq);
 	rdp->rcu_onl_gp_flags = READ_ONCE(rcu_state.gp_flags);
 	if (rnp->qsmask & mask) { /* RCU waiting on incoming CPU? */
+		rcu_disable_urgency_upon_qs(rdp);
 		/* Report QS -after- changing ->qsmaskinitnext! */
 		rcu_report_qs_rnp(mask, rnp, rnp->gp_seq, flags);
 	} else {
diff --git a/kernel/rcu/tree.h b/kernel/rcu/tree.h
index c612f306fe89..055c31781d3a 100644
--- a/kernel/rcu/tree.h
+++ b/kernel/rcu/tree.h
@@ -181,6 +181,7 @@ struct rcu_data {
 	atomic_t dynticks;		/* Even value for idle, else odd. */
 	bool rcu_need_heavy_qs;		/* GP old, so heavy quiescent state! */
 	bool rcu_urgent_qs;		/* GP old need light quiescent state. */
+	bool rcu_forced_tick;		/* Forced tick to provide QS. */
 #ifdef CONFIG_RCU_FAST_NO_HZ
 	bool all_lazy;			/* All CPU's CBs lazy at idle start? */
 	unsigned long last_accelerate;	/* Last jiffy CBs were accelerated. */
diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h
index 2defc7fe74c3..fa08d55f7040 100644
--- a/kernel/rcu/tree_plugin.h
+++ b/kernel/rcu/tree_plugin.h
@@ -1946,7 +1946,7 @@ static void nocb_gp_wait(struct rcu_data *my_rdp)
 	int __maybe_unused cpu = my_rdp->cpu;
 	unsigned long cur_gp_seq;
 	unsigned long flags;
-	bool gotcbs;
+	bool gotcbs = false;
 	unsigned long j = jiffies;
 	bool needwait_gp = false; // This prevents actual uninitialized use.
 	bool needwake;
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 80b60ca7767f..90e4b00ace89 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -811,7 +811,7 @@ static inline unsigned int uclamp_bucket_base_value(unsigned int clamp_value)
 	return UCLAMP_BUCKET_DELTA * uclamp_bucket_id(clamp_value);
 }
 
-static inline enum uclamp_id uclamp_none(enum uclamp_id clamp_id)
+static inline unsigned int uclamp_none(enum uclamp_id clamp_id)
 {
 	if (clamp_id == UCLAMP_MIN)
 		return 0;
@@ -854,7 +854,7 @@ static inline void uclamp_idle_reset(struct rq *rq, enum uclamp_id clamp_id,
 }
 
 static inline
-enum uclamp_id uclamp_rq_max_value(struct rq *rq, enum uclamp_id clamp_id,
+unsigned int uclamp_rq_max_value(struct rq *rq, enum uclamp_id clamp_id,
 				   unsigned int clamp_value)
 {
 	struct uclamp_bucket *bucket = rq->uclamp[clamp_id].bucket;
@@ -919,7 +919,7 @@ uclamp_eff_get(struct task_struct *p, enum uclamp_id clamp_id)
 	return uc_req;
 }
 
-enum uclamp_id uclamp_eff_value(struct task_struct *p, enum uclamp_id clamp_id)
+unsigned int uclamp_eff_value(struct task_struct *p, enum uclamp_id clamp_id)
 {
 	struct uclamp_se uc_eff;
 
@@ -3106,7 +3106,7 @@ prepare_lock_switch(struct rq *rq, struct task_struct *next, struct rq_flags *rf
 	 * do an early lockdep release here:
 	 */
 	rq_unpin_lock(rq, rf);
-	spin_release(&rq->lock.dep_map, 1, _THIS_IP_);
+	spin_release(&rq->lock.dep_map, _THIS_IP_);
 #ifdef CONFIG_DEBUG_SPINLOCK
 	/* this is a valid case when another task releases the spinlock */
 	rq->lock.owner = next;
@@ -3918,13 +3918,15 @@ pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
 		    prev->sched_class == &fair_sched_class) &&
 		   rq->nr_running == rq->cfs.h_nr_running)) {
 
-		p = fair_sched_class.pick_next_task(rq, prev, rf);
+		p = pick_next_task_fair(rq, prev, rf);
 		if (unlikely(p == RETRY_TASK))
 			goto restart;
 
 		/* Assumes fair_sched_class->next == idle_sched_class */
-		if (unlikely(!p))
-			p = idle_sched_class.pick_next_task(rq, prev, rf);
+		if (!p) {
+			put_prev_task(rq, prev);
+			p = pick_next_task_idle(rq);
+		}
 
 		return p;
 	}
@@ -3948,7 +3950,7 @@ restart:
 	put_prev_task(rq, prev);
 
 	for_each_class(class) {
-		p = class->pick_next_task(rq, NULL, NULL);
+		p = class->pick_next_task(rq);
 		if (p)
 			return p;
 	}
@@ -6217,7 +6219,7 @@ static struct task_struct *__pick_migrate_task(struct rq *rq)
 	struct task_struct *next;
 
 	for_each_class(class) {
-		next = class->pick_next_task(rq, NULL, NULL);
+		next = class->pick_next_task(rq);
 		if (next) {
 			next->sched_class->put_prev_task(rq, next);
 			return next;
diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c
index 46ed4e1383e2..d43318a489f2 100644
--- a/kernel/sched/cputime.c
+++ b/kernel/sched/cputime.c
@@ -405,27 +405,25 @@ static inline void irqtime_account_process_tick(struct task_struct *p, int user_
 /*
  * Use precise platform statistics if available:
  */
-#ifdef CONFIG_VIRT_CPU_ACCOUNTING
+#ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE
+
 # ifndef __ARCH_HAS_VTIME_TASK_SWITCH
-void vtime_common_task_switch(struct task_struct *prev)
+void vtime_task_switch(struct task_struct *prev)
 {
 	if (is_idle_task(prev))
 		vtime_account_idle(prev);
 	else
-		vtime_account_system(prev);
+		vtime_account_kernel(prev);
 
 	vtime_flush(prev);
 	arch_vtime_task_switch(prev);
 }
 # endif
-#endif /* CONFIG_VIRT_CPU_ACCOUNTING */
 
-
-#ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE
 /*
  * Archs that account the whole time spent in the idle task
  * (outside irq) as idle time can rely on this and just implement
- * vtime_account_system() and vtime_account_idle(). Archs that
+ * vtime_account_kernel() and vtime_account_idle(). Archs that
  * have other meaning of the idle time (s390 only includes the
  * time spent by the CPU when it's in low power mode) must override
  * vtime_account().
@@ -436,7 +434,7 @@ void vtime_account_irq_enter(struct task_struct *tsk)
 	if (!in_interrupt() && is_idle_task(tsk))
 		vtime_account_idle(tsk);
 	else
-		vtime_account_system(tsk);
+		vtime_account_kernel(tsk);
 }
 EXPORT_SYMBOL_GPL(vtime_account_irq_enter);
 #endif /* __ARCH_HAS_VTIME_ACCOUNT */
@@ -477,7 +475,7 @@ void account_process_tick(struct task_struct *p, int user_tick)
 	u64 cputime, steal;
 	struct rq *rq = this_rq();
 
-	if (vtime_accounting_cpu_enabled())
+	if (vtime_accounting_enabled_this_cpu())
 		return;
 
 	if (sched_clock_irqtime) {
@@ -711,8 +709,8 @@ static u64 get_vtime_delta(struct vtime *vtime)
 	return delta - other;
 }
 
-static void __vtime_account_system(struct task_struct *tsk,
-				   struct vtime *vtime)
+static void vtime_account_system(struct task_struct *tsk,
+				 struct vtime *vtime)
 {
 	vtime->stime += get_vtime_delta(vtime);
 	if (vtime->stime >= TICK_NSEC) {
@@ -731,7 +729,17 @@ static void vtime_account_guest(struct task_struct *tsk,
 	}
 }
 
-void vtime_account_system(struct task_struct *tsk)
+static void __vtime_account_kernel(struct task_struct *tsk,
+				   struct vtime *vtime)
+{
+	/* We might have scheduled out from guest path */
+	if (vtime->state == VTIME_GUEST)
+		vtime_account_guest(tsk, vtime);
+	else
+		vtime_account_system(tsk, vtime);
+}
+
+void vtime_account_kernel(struct task_struct *tsk)
 {
 	struct vtime *vtime = &tsk->vtime;
 
@@ -739,11 +747,7 @@ void vtime_account_system(struct task_struct *tsk)
 		return;
 
 	write_seqcount_begin(&vtime->seqcount);
-	/* We might have scheduled out from guest path */
-	if (tsk->flags & PF_VCPU)
-		vtime_account_guest(tsk, vtime);
-	else
-		__vtime_account_system(tsk, vtime);
+	__vtime_account_kernel(tsk, vtime);
 	write_seqcount_end(&vtime->seqcount);
 }
 
@@ -752,7 +756,7 @@ void vtime_user_enter(struct task_struct *tsk)
 	struct vtime *vtime = &tsk->vtime;
 
 	write_seqcount_begin(&vtime->seqcount);
-	__vtime_account_system(tsk, vtime);
+	vtime_account_system(tsk, vtime);
 	vtime->state = VTIME_USER;
 	write_seqcount_end(&vtime->seqcount);
 }
@@ -782,8 +786,9 @@ void vtime_guest_enter(struct task_struct *tsk)
 	 * that can thus safely catch up with a tickless delta.
 	 */
 	write_seqcount_begin(&vtime->seqcount);
-	__vtime_account_system(tsk, vtime);
+	vtime_account_system(tsk, vtime);
 	tsk->flags |= PF_VCPU;
+	vtime->state = VTIME_GUEST;
 	write_seqcount_end(&vtime->seqcount);
 }
 EXPORT_SYMBOL_GPL(vtime_guest_enter);
@@ -795,6 +800,7 @@ void vtime_guest_exit(struct task_struct *tsk)
 	write_seqcount_begin(&vtime->seqcount);
 	vtime_account_guest(tsk, vtime);
 	tsk->flags &= ~PF_VCPU;
+	vtime->state = VTIME_SYS;
 	write_seqcount_end(&vtime->seqcount);
 }
 EXPORT_SYMBOL_GPL(vtime_guest_exit);
@@ -804,19 +810,30 @@ void vtime_account_idle(struct task_struct *tsk)
 	account_idle_time(get_vtime_delta(&tsk->vtime));
 }
 
-void arch_vtime_task_switch(struct task_struct *prev)
+void vtime_task_switch_generic(struct task_struct *prev)
 {
 	struct vtime *vtime = &prev->vtime;
 
 	write_seqcount_begin(&vtime->seqcount);
+	if (vtime->state == VTIME_IDLE)
+		vtime_account_idle(prev);
+	else
+		__vtime_account_kernel(prev, vtime);
 	vtime->state = VTIME_INACTIVE;
+	vtime->cpu = -1;
 	write_seqcount_end(&vtime->seqcount);
 
 	vtime = &current->vtime;
 
 	write_seqcount_begin(&vtime->seqcount);
-	vtime->state = VTIME_SYS;
+	if (is_idle_task(current))
+		vtime->state = VTIME_IDLE;
+	else if (current->flags & PF_VCPU)
+		vtime->state = VTIME_GUEST;
+	else
+		vtime->state = VTIME_SYS;
 	vtime->starttime = sched_clock();
+	vtime->cpu = smp_processor_id();
 	write_seqcount_end(&vtime->seqcount);
 }
 
@@ -827,8 +844,9 @@ void vtime_init_idle(struct task_struct *t, int cpu)
 
 	local_irq_save(flags);
 	write_seqcount_begin(&vtime->seqcount);
-	vtime->state = VTIME_SYS;
+	vtime->state = VTIME_IDLE;
 	vtime->starttime = sched_clock();
+	vtime->cpu = cpu;
 	write_seqcount_end(&vtime->seqcount);
 	local_irq_restore(flags);
 }
@@ -846,7 +864,7 @@ u64 task_gtime(struct task_struct *t)
 		seq = read_seqcount_begin(&vtime->seqcount);
 
 		gtime = t->gtime;
-		if (vtime->state == VTIME_SYS && t->flags & PF_VCPU)
+		if (vtime->state == VTIME_GUEST)
 			gtime += vtime->gtime + vtime_delta(vtime);
 
 	} while (read_seqcount_retry(&vtime->seqcount, seq));
@@ -877,20 +895,230 @@ void task_cputime(struct task_struct *t, u64 *utime, u64 *stime)
 		*utime = t->utime;
 		*stime = t->stime;
 
-		/* Task is sleeping, nothing to add */
-		if (vtime->state == VTIME_INACTIVE || is_idle_task(t))
+		/* Task is sleeping or idle, nothing to add */
+		if (vtime->state < VTIME_SYS)
 			continue;
 
 		delta = vtime_delta(vtime);
 
 		/*
-		 * Task runs either in user or kernel space, add pending nohz time to
-		 * the right place.
+		 * Task runs either in user (including guest) or kernel space,
+		 * add pending nohz time to the right place.
 		 */
-		if (vtime->state == VTIME_USER || t->flags & PF_VCPU)
-			*utime += vtime->utime + delta;
-		else if (vtime->state == VTIME_SYS)
+		if (vtime->state == VTIME_SYS)
 			*stime += vtime->stime + delta;
+		else
+			*utime += vtime->utime + delta;
+	} while (read_seqcount_retry(&vtime->seqcount, seq));
+}
+
+static int vtime_state_check(struct vtime *vtime, int cpu)
+{
+	/*
+	 * We raced against a context switch, fetch the
+	 * kcpustat task again.
+	 */
+	if (vtime->cpu != cpu && vtime->cpu != -1)
+		return -EAGAIN;
+
+	/*
+	 * Two possible things here:
+	 * 1) We are seeing the scheduling out task (prev) or any past one.
+	 * 2) We are seeing the scheduling in task (next) but it hasn't
+	 *    passed though vtime_task_switch() yet so the pending
+	 *    cputime of the prev task may not be flushed yet.
+	 *
+	 * Case 1) is ok but 2) is not. So wait for a safe VTIME state.
+	 */
+	if (vtime->state == VTIME_INACTIVE)
+		return -EAGAIN;
+
+	return 0;
+}
+
+static u64 kcpustat_user_vtime(struct vtime *vtime)
+{
+	if (vtime->state == VTIME_USER)
+		return vtime->utime + vtime_delta(vtime);
+	else if (vtime->state == VTIME_GUEST)
+		return vtime->gtime + vtime_delta(vtime);
+	return 0;
+}
+
+static int kcpustat_field_vtime(u64 *cpustat,
+				struct task_struct *tsk,
+				enum cpu_usage_stat usage,
+				int cpu, u64 *val)
+{
+	struct vtime *vtime = &tsk->vtime;
+	unsigned int seq;
+	int err;
+
+	do {
+		seq = read_seqcount_begin(&vtime->seqcount);
+
+		err = vtime_state_check(vtime, cpu);
+		if (err < 0)
+			return err;
+
+		*val = cpustat[usage];
+
+		/*
+		 * Nice VS unnice cputime accounting may be inaccurate if
+		 * the nice value has changed since the last vtime update.
+		 * But proper fix would involve interrupting target on nice
+		 * updates which is a no go on nohz_full (although the scheduler
+		 * may still interrupt the target if rescheduling is needed...)
+		 */
+		switch (usage) {
+		case CPUTIME_SYSTEM:
+			if (vtime->state == VTIME_SYS)
+				*val += vtime->stime + vtime_delta(vtime);
+			break;
+		case CPUTIME_USER:
+			if (task_nice(tsk) <= 0)
+				*val += kcpustat_user_vtime(vtime);
+			break;
+		case CPUTIME_NICE:
+			if (task_nice(tsk) > 0)
+				*val += kcpustat_user_vtime(vtime);
+			break;
+		case CPUTIME_GUEST:
+			if (vtime->state == VTIME_GUEST && task_nice(tsk) <= 0)
+				*val += vtime->gtime + vtime_delta(vtime);
+			break;
+		case CPUTIME_GUEST_NICE:
+			if (vtime->state == VTIME_GUEST && task_nice(tsk) > 0)
+				*val += vtime->gtime + vtime_delta(vtime);
+			break;
+		default:
+			break;
+		}
+	} while (read_seqcount_retry(&vtime->seqcount, seq));
+
+	return 0;
+}
+
+u64 kcpustat_field(struct kernel_cpustat *kcpustat,
+		   enum cpu_usage_stat usage, int cpu)
+{
+	u64 *cpustat = kcpustat->cpustat;
+	struct rq *rq;
+	u64 val;
+	int err;
+
+	if (!vtime_accounting_enabled_cpu(cpu))
+		return cpustat[usage];
+
+	rq = cpu_rq(cpu);
+
+	for (;;) {
+		struct task_struct *curr;
+
+		rcu_read_lock();
+		curr = rcu_dereference(rq->curr);
+		if (WARN_ON_ONCE(!curr)) {
+			rcu_read_unlock();
+			return cpustat[usage];
+		}
+
+		err = kcpustat_field_vtime(cpustat, curr, usage, cpu, &val);
+		rcu_read_unlock();
+
+		if (!err)
+			return val;
+
+		cpu_relax();
+	}
+}
+EXPORT_SYMBOL_GPL(kcpustat_field);
+
+static int kcpustat_cpu_fetch_vtime(struct kernel_cpustat *dst,
+				    const struct kernel_cpustat *src,
+				    struct task_struct *tsk, int cpu)
+{
+	struct vtime *vtime = &tsk->vtime;
+	unsigned int seq;
+	int err;
+
+	do {
+		u64 *cpustat;
+		u64 delta;
+
+		seq = read_seqcount_begin(&vtime->seqcount);
+
+		err = vtime_state_check(vtime, cpu);
+		if (err < 0)
+			return err;
+
+		*dst = *src;
+		cpustat = dst->cpustat;
+
+		/* Task is sleeping, dead or idle, nothing to add */
+		if (vtime->state < VTIME_SYS)
+			continue;
+
+		delta = vtime_delta(vtime);
+
+		/*
+		 * Task runs either in user (including guest) or kernel space,
+		 * add pending nohz time to the right place.
+		 */
+		if (vtime->state == VTIME_SYS) {
+			cpustat[CPUTIME_SYSTEM] += vtime->stime + delta;
+		} else if (vtime->state == VTIME_USER) {
+			if (task_nice(tsk) > 0)
+				cpustat[CPUTIME_NICE] += vtime->utime + delta;
+			else
+				cpustat[CPUTIME_USER] += vtime->utime + delta;
+		} else {
+			WARN_ON_ONCE(vtime->state != VTIME_GUEST);
+			if (task_nice(tsk) > 0) {
+				cpustat[CPUTIME_GUEST_NICE] += vtime->gtime + delta;
+				cpustat[CPUTIME_NICE] += vtime->gtime + delta;
+			} else {
+				cpustat[CPUTIME_GUEST] += vtime->gtime + delta;
+				cpustat[CPUTIME_USER] += vtime->gtime + delta;
+			}
+		}
 	} while (read_seqcount_retry(&vtime->seqcount, seq));
+
+	return err;
+}
+
+void kcpustat_cpu_fetch(struct kernel_cpustat *dst, int cpu)
+{
+	const struct kernel_cpustat *src = &kcpustat_cpu(cpu);
+	struct rq *rq;
+	int err;
+
+	if (!vtime_accounting_enabled_cpu(cpu)) {
+		*dst = *src;
+		return;
+	}
+
+	rq = cpu_rq(cpu);
+
+	for (;;) {
+		struct task_struct *curr;
+
+		rcu_read_lock();
+		curr = rcu_dereference(rq->curr);
+		if (WARN_ON_ONCE(!curr)) {
+			rcu_read_unlock();
+			*dst = *src;
+			return;
+		}
+
+		err = kcpustat_cpu_fetch_vtime(dst, src, curr, cpu);
+		rcu_read_unlock();
+
+		if (!err)
+			return;
+
+		cpu_relax();
+	}
 }
+EXPORT_SYMBOL_GPL(kcpustat_cpu_fetch);
+
 #endif /* CONFIG_VIRT_CPU_ACCOUNTING_GEN */
diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index a8a08030a8f7..43323f875cb9 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -1743,13 +1743,16 @@ static void start_hrtick_dl(struct rq *rq, struct task_struct *p)
 }
 #endif
 
-static void set_next_task_dl(struct rq *rq, struct task_struct *p)
+static void set_next_task_dl(struct rq *rq, struct task_struct *p, bool first)
 {
 	p->se.exec_start = rq_clock_task(rq);
 
 	/* You can't push away the running task */
 	dequeue_pushable_dl_task(rq, p);
 
+	if (!first)
+		return;
+
 	if (hrtick_enabled(rq))
 		start_hrtick_dl(rq, p);
 
@@ -1770,22 +1773,19 @@ static struct sched_dl_entity *pick_next_dl_entity(struct rq *rq,
 	return rb_entry(left, struct sched_dl_entity, rb_node);
 }
 
-static struct task_struct *
-pick_next_task_dl(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
+static struct task_struct *pick_next_task_dl(struct rq *rq)
 {
 	struct sched_dl_entity *dl_se;
 	struct dl_rq *dl_rq = &rq->dl;
 	struct task_struct *p;
 
-	WARN_ON_ONCE(prev || rf);
-
 	if (!sched_dl_runnable(rq))
 		return NULL;
 
 	dl_se = pick_next_dl_entity(rq, dl_rq);
 	BUG_ON(!dl_se);
 	p = dl_task_of(dl_se);
-	set_next_task_dl(rq, p);
+	set_next_task_dl(rq, p, true);
 	return p;
 }
 
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 69a81a5709ff..08a233e97a01 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -229,8 +229,7 @@ static u64 __calc_delta(u64 delta_exec, unsigned long weight, struct load_weight
 		}
 	}
 
-	/* hint to use a 32x32->64 mul */
-	fact = (u64)(u32)fact * lw->inv_weight;
+	fact = mul_u32_u32(fact, lw->inv_weight);
 
 	while (fact >> 32) {
 		fact >>= 1;
@@ -1474,7 +1473,12 @@ bool should_numa_migrate_memory(struct task_struct *p, struct page * page,
 	       group_faults_cpu(ng, src_nid) * group_faults(p, dst_nid) * 4;
 }
 
-static unsigned long cpu_runnable_load(struct rq *rq);
+static inline unsigned long cfs_rq_runnable_load_avg(struct cfs_rq *cfs_rq);
+
+static unsigned long cpu_runnable_load(struct rq *rq)
+{
+	return cfs_rq_runnable_load_avg(&rq->cfs);
+}
 
 /* Cached statistics for all CPUs within a node */
 struct numa_stats {
@@ -3504,9 +3508,6 @@ update_cfs_rq_load_avg(u64 now, struct cfs_rq *cfs_rq)
 	cfs_rq->load_last_update_time_copy = sa->last_update_time;
 #endif
 
-	if (decayed)
-		cfs_rq_util_change(cfs_rq, 0);
-
 	return decayed;
 }
 
@@ -3616,8 +3617,12 @@ static inline void update_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *s
 		attach_entity_load_avg(cfs_rq, se, SCHED_CPUFREQ_MIGRATION);
 		update_tg_load_avg(cfs_rq, 0);
 
-	} else if (decayed && (flags & UPDATE_TG))
-		update_tg_load_avg(cfs_rq, 0);
+	} else if (decayed) {
+		cfs_rq_util_change(cfs_rq, 0);
+
+		if (flags & UPDATE_TG)
+			update_tg_load_avg(cfs_rq, 0);
+	}
 }
 
 #ifndef CONFIG_64BIT
@@ -3764,10 +3769,21 @@ util_est_dequeue(struct cfs_rq *cfs_rq, struct task_struct *p, bool task_sleep)
 		return;
 
 	/*
+	 * Reset EWMA on utilization increases, the moving average is used only
+	 * to smooth utilization decreases.
+	 */
+	ue.enqueued = (task_util(p) | UTIL_AVG_UNCHANGED);
+	if (sched_feat(UTIL_EST_FASTUP)) {
+		if (ue.ewma < ue.enqueued) {
+			ue.ewma = ue.enqueued;
+			goto done;
+		}
+	}
+
+	/*
 	 * Skip update of task's estimated utilization when its EWMA is
 	 * already ~1% close to its last activation value.
 	 */
-	ue.enqueued = (task_util(p) | UTIL_AVG_UNCHANGED);
 	last_ewma_diff = ue.enqueued - ue.ewma;
 	if (within_margin(last_ewma_diff, (SCHED_CAPACITY_SCALE / 100)))
 		return;
@@ -3800,6 +3816,7 @@ util_est_dequeue(struct cfs_rq *cfs_rq, struct task_struct *p, bool task_sleep)
 	ue.ewma <<= UTIL_EST_WEIGHT_SHIFT;
 	ue.ewma  += last_ewma_diff;
 	ue.ewma >>= UTIL_EST_WEIGHT_SHIFT;
+done:
 	WRITE_ONCE(p->se.avg.util_est, ue);
 }
 
@@ -5370,26 +5387,45 @@ static int sched_idle_cpu(int cpu)
 			rq->nr_running);
 }
 
-static unsigned long cpu_runnable_load(struct rq *rq)
+static unsigned long cpu_load(struct rq *rq)
 {
-	return cfs_rq_runnable_load_avg(&rq->cfs);
+	return cfs_rq_load_avg(&rq->cfs);
 }
 
-static unsigned long capacity_of(int cpu)
+/*
+ * cpu_load_without - compute CPU load without any contributions from *p
+ * @cpu: the CPU which load is requested
+ * @p: the task which load should be discounted
+ *
+ * The load of a CPU is defined by the load of tasks currently enqueued on that
+ * CPU as well as tasks which are currently sleeping after an execution on that
+ * CPU.
+ *
+ * This method returns the load of the specified CPU by discounting the load of
+ * the specified task, whenever the task is currently contributing to the CPU
+ * load.
+ */
+static unsigned long cpu_load_without(struct rq *rq, struct task_struct *p)
 {
-	return cpu_rq(cpu)->cpu_capacity;
-}
+	struct cfs_rq *cfs_rq;
+	unsigned int load;
 
-static unsigned long cpu_avg_load_per_task(int cpu)
-{
-	struct rq *rq = cpu_rq(cpu);
-	unsigned long nr_running = READ_ONCE(rq->cfs.h_nr_running);
-	unsigned long load_avg = cpu_runnable_load(rq);
+	/* Task has no contribution or is new */
+	if (cpu_of(rq) != task_cpu(p) || !READ_ONCE(p->se.avg.last_update_time))
+		return cpu_load(rq);
 
-	if (nr_running)
-		return load_avg / nr_running;
+	cfs_rq = &rq->cfs;
+	load = READ_ONCE(cfs_rq->avg.load_avg);
 
-	return 0;
+	/* Discount task's util from CPU's util */
+	lsub_positive(&load, task_h_load(p));
+
+	return load;
+}
+
+static unsigned long capacity_of(int cpu)
+{
+	return cpu_rq(cpu)->cpu_capacity;
 }
 
 static void record_wakee(struct task_struct *p)
@@ -5482,7 +5518,7 @@ wake_affine_weight(struct sched_domain *sd, struct task_struct *p,
 	s64 this_eff_load, prev_eff_load;
 	unsigned long task_load;
 
-	this_eff_load = cpu_runnable_load(cpu_rq(this_cpu));
+	this_eff_load = cpu_load(cpu_rq(this_cpu));
 
 	if (sync) {
 		unsigned long current_load = task_h_load(current);
@@ -5500,7 +5536,7 @@ wake_affine_weight(struct sched_domain *sd, struct task_struct *p,
 		this_eff_load *= 100;
 	this_eff_load *= capacity_of(prev_cpu);
 
-	prev_eff_load = cpu_runnable_load(cpu_rq(prev_cpu));
+	prev_eff_load = cpu_load(cpu_rq(prev_cpu));
 	prev_eff_load -= task_load;
 	if (sched_feat(WA_BIAS))
 		prev_eff_load *= 100 + (sd->imbalance_pct - 100) / 2;
@@ -5538,149 +5574,9 @@ static int wake_affine(struct sched_domain *sd, struct task_struct *p,
 	return target;
 }
 
-static unsigned long cpu_util_without(int cpu, struct task_struct *p);
-
-static unsigned long capacity_spare_without(int cpu, struct task_struct *p)
-{
-	return max_t(long, capacity_of(cpu) - cpu_util_without(cpu, p), 0);
-}
-
-/*
- * find_idlest_group finds and returns the least busy CPU group within the
- * domain.
- *
- * Assumes p is allowed on at least one CPU in sd.
- */
 static struct sched_group *
 find_idlest_group(struct sched_domain *sd, struct task_struct *p,
-		  int this_cpu, int sd_flag)
-{
-	struct sched_group *idlest = NULL, *group = sd->groups;
-	struct sched_group *most_spare_sg = NULL;
-	unsigned long min_runnable_load = ULONG_MAX;
-	unsigned long this_runnable_load = ULONG_MAX;
-	unsigned long min_avg_load = ULONG_MAX, this_avg_load = ULONG_MAX;
-	unsigned long most_spare = 0, this_spare = 0;
-	int imbalance_scale = 100 + (sd->imbalance_pct-100)/2;
-	unsigned long imbalance = scale_load_down(NICE_0_LOAD) *
-				(sd->imbalance_pct-100) / 100;
-
-	do {
-		unsigned long load, avg_load, runnable_load;
-		unsigned long spare_cap, max_spare_cap;
-		int local_group;
-		int i;
-
-		/* Skip over this group if it has no CPUs allowed */
-		if (!cpumask_intersects(sched_group_span(group),
-					p->cpus_ptr))
-			continue;
-
-		local_group = cpumask_test_cpu(this_cpu,
-					       sched_group_span(group));
-
-		/*
-		 * Tally up the load of all CPUs in the group and find
-		 * the group containing the CPU with most spare capacity.
-		 */
-		avg_load = 0;
-		runnable_load = 0;
-		max_spare_cap = 0;
-
-		for_each_cpu(i, sched_group_span(group)) {
-			load = cpu_runnable_load(cpu_rq(i));
-			runnable_load += load;
-
-			avg_load += cfs_rq_load_avg(&cpu_rq(i)->cfs);
-
-			spare_cap = capacity_spare_without(i, p);
-
-			if (spare_cap > max_spare_cap)
-				max_spare_cap = spare_cap;
-		}
-
-		/* Adjust by relative CPU capacity of the group */
-		avg_load = (avg_load * SCHED_CAPACITY_SCALE) /
-					group->sgc->capacity;
-		runnable_load = (runnable_load * SCHED_CAPACITY_SCALE) /
-					group->sgc->capacity;
-
-		if (local_group) {
-			this_runnable_load = runnable_load;
-			this_avg_load = avg_load;
-			this_spare = max_spare_cap;
-		} else {
-			if (min_runnable_load > (runnable_load + imbalance)) {
-				/*
-				 * The runnable load is significantly smaller
-				 * so we can pick this new CPU:
-				 */
-				min_runnable_load = runnable_load;
-				min_avg_load = avg_load;
-				idlest = group;
-			} else if ((runnable_load < (min_runnable_load + imbalance)) &&
-				   (100*min_avg_load > imbalance_scale*avg_load)) {
-				/*
-				 * The runnable loads are close so take the
-				 * blocked load into account through avg_load:
-				 */
-				min_avg_load = avg_load;
-				idlest = group;
-			}
-
-			if (most_spare < max_spare_cap) {
-				most_spare = max_spare_cap;
-				most_spare_sg = group;
-			}
-		}
-	} while (group = group->next, group != sd->groups);
-
-	/*
-	 * The cross-over point between using spare capacity or least load
-	 * is too conservative for high utilization tasks on partially
-	 * utilized systems if we require spare_capacity > task_util(p),
-	 * so we allow for some task stuffing by using
-	 * spare_capacity > task_util(p)/2.
-	 *
-	 * Spare capacity can't be used for fork because the utilization has
-	 * not been set yet, we must first select a rq to compute the initial
-	 * utilization.
-	 */
-	if (sd_flag & SD_BALANCE_FORK)
-		goto skip_spare;
-
-	if (this_spare > task_util(p) / 2 &&
-	    imbalance_scale*this_spare > 100*most_spare)
-		return NULL;
-
-	if (most_spare > task_util(p) / 2)
-		return most_spare_sg;
-
-skip_spare:
-	if (!idlest)
-		return NULL;
-
-	/*
-	 * When comparing groups across NUMA domains, it's possible for the
-	 * local domain to be very lightly loaded relative to the remote
-	 * domains but "imbalance" skews the comparison making remote CPUs
-	 * look much more favourable. When considering cross-domain, add
-	 * imbalance to the runnable load on the remote node and consider
-	 * staying local.
-	 */
-	if ((sd->flags & SD_NUMA) &&
-	    min_runnable_load + imbalance >= this_runnable_load)
-		return NULL;
-
-	if (min_runnable_load > (this_runnable_load + imbalance))
-		return NULL;
-
-	if ((this_runnable_load < (min_runnable_load + imbalance)) &&
-	     (100*this_avg_load < imbalance_scale*min_avg_load))
-		return NULL;
-
-	return idlest;
-}
+		  int this_cpu, int sd_flag);
 
 /*
  * find_idlest_group_cpu - find the idlest CPU among the CPUs in the group.
@@ -5729,7 +5625,7 @@ find_idlest_group_cpu(struct sched_group *group, struct task_struct *p, int this
 				continue;
 			}
 
-			load = cpu_runnable_load(cpu_rq(i));
+			load = cpu_load(cpu_rq(i));
 			if (load < min_load) {
 				min_load = load;
 				least_loaded_cpu = i;
@@ -5753,7 +5649,7 @@ static inline int find_idlest_cpu(struct sched_domain *sd, struct task_struct *p
 		return prev_cpu;
 
 	/*
-	 * We need task's util for capacity_spare_without, sync it up to
+	 * We need task's util for cpu_util_without, sync it up to
 	 * prev_cpu's last_update_time.
 	 */
 	if (!(sd_flag & SD_BALANCE_FORK))
@@ -6746,7 +6642,7 @@ preempt:
 		set_last_buddy(se);
 }
 
-static struct task_struct *
+struct task_struct *
 pick_next_task_fair(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
 {
 	struct cfs_rq *cfs_rq = &rq->cfs;
@@ -6890,6 +6786,11 @@ idle:
 	return NULL;
 }
 
+static struct task_struct *__pick_next_task_fair(struct rq *rq)
+{
+	return pick_next_task_fair(rq, NULL, NULL);
+}
+
 /*
  * Account for a descheduled task:
  */
@@ -7079,11 +6980,49 @@ static unsigned long __read_mostly max_load_balance_interval = HZ/10;
 
 enum fbq_type { regular, remote, all };
 
+/*
+ * 'group_type' describes the group of CPUs at the moment of load balancing.
+ *
+ * The enum is ordered by pulling priority, with the group with lowest priority
+ * first so the group_type can simply be compared when selecting the busiest
+ * group. See update_sd_pick_busiest().
+ */
 enum group_type {
-	group_other = 0,
+	/* The group has spare capacity that can be used to run more tasks.  */
+	group_has_spare = 0,
+	/*
+	 * The group is fully used and the tasks don't compete for more CPU
+	 * cycles. Nevertheless, some tasks might wait before running.
+	 */
+	group_fully_busy,
+	/*
+	 * SD_ASYM_CPUCAPACITY only: One task doesn't fit with CPU's capacity
+	 * and must be migrated to a more powerful CPU.
+	 */
 	group_misfit_task,
+	/*
+	 * SD_ASYM_PACKING only: One local CPU with higher capacity is available,
+	 * and the task should be migrated to it instead of running on the
+	 * current CPU.
+	 */
+	group_asym_packing,
+	/*
+	 * The tasks' affinity constraints previously prevented the scheduler
+	 * from balancing the load across the system.
+	 */
 	group_imbalanced,
-	group_overloaded,
+	/*
+	 * The CPU is overloaded and can't provide expected CPU cycles to all
+	 * tasks.
+	 */
+	group_overloaded
+};
+
+enum migration_type {
+	migrate_load = 0,
+	migrate_util,
+	migrate_task,
+	migrate_misfit
 };
 
 #define LBF_ALL_PINNED	0x01
@@ -7116,7 +7055,7 @@ struct lb_env {
 	unsigned int		loop_max;
 
 	enum fbq_type		fbq_type;
-	enum group_type		src_grp_type;
+	enum migration_type	migration_type;
 	struct list_head	tasks;
 };
 
@@ -7339,7 +7278,7 @@ static struct task_struct *detach_one_task(struct lb_env *env)
 static const unsigned int sched_nr_migrate_break = 32;
 
 /*
- * detach_tasks() -- tries to detach up to imbalance runnable load from
+ * detach_tasks() -- tries to detach up to imbalance load/util/tasks from
  * busiest_rq, as part of a balancing operation within domain "sd".
  *
  * Returns number of detached tasks if successful and 0 otherwise.
@@ -7347,8 +7286,8 @@ static const unsigned int sched_nr_migrate_break = 32;
 static int detach_tasks(struct lb_env *env)
 {
 	struct list_head *tasks = &env->src_rq->cfs_tasks;
+	unsigned long util, load;
 	struct task_struct *p;
-	unsigned long load;
 	int detached = 0;
 
 	lockdep_assert_held(&env->src_rq->lock);
@@ -7381,19 +7320,46 @@ static int detach_tasks(struct lb_env *env)
 		if (!can_migrate_task(p, env))
 			goto next;
 
-		load = task_h_load(p);
+		switch (env->migration_type) {
+		case migrate_load:
+			load = task_h_load(p);
 
-		if (sched_feat(LB_MIN) && load < 16 && !env->sd->nr_balance_failed)
-			goto next;
+			if (sched_feat(LB_MIN) &&
+			    load < 16 && !env->sd->nr_balance_failed)
+				goto next;
 
-		if ((load / 2) > env->imbalance)
-			goto next;
+			if (load/2 > env->imbalance)
+				goto next;
+
+			env->imbalance -= load;
+			break;
+
+		case migrate_util:
+			util = task_util_est(p);
+
+			if (util > env->imbalance)
+				goto next;
+
+			env->imbalance -= util;
+			break;
+
+		case migrate_task:
+			env->imbalance--;
+			break;
+
+		case migrate_misfit:
+			/* This is not a misfit task */
+			if (task_fits_capacity(p, capacity_of(env->src_cpu)))
+				goto next;
+
+			env->imbalance = 0;
+			break;
+		}
 
 		detach_task(p, env);
 		list_add(&p->se.group_node, &env->tasks);
 
 		detached++;
-		env->imbalance -= load;
 
 #ifdef CONFIG_PREEMPTION
 		/*
@@ -7407,7 +7373,7 @@ static int detach_tasks(struct lb_env *env)
 
 		/*
 		 * We only want to steal up to the prescribed amount of
-		 * runnable load.
+		 * load/util/tasks.
 		 */
 		if (env->imbalance <= 0)
 			break;
@@ -7517,6 +7483,28 @@ static inline bool others_have_blocked(struct rq *rq) { return false; }
 static inline void update_blocked_load_status(struct rq *rq, bool has_blocked) {}
 #endif
 
+static bool __update_blocked_others(struct rq *rq, bool *done)
+{
+	const struct sched_class *curr_class;
+	u64 now = rq_clock_pelt(rq);
+	bool decayed;
+
+	/*
+	 * update_load_avg() can call cpufreq_update_util(). Make sure that RT,
+	 * DL and IRQ signals have been updated before updating CFS.
+	 */
+	curr_class = rq->curr->sched_class;
+
+	decayed = update_rt_rq_load_avg(now, rq, curr_class == &rt_sched_class) |
+		  update_dl_rq_load_avg(now, rq, curr_class == &dl_sched_class) |
+		  update_irq_load_avg(rq, 0);
+
+	if (others_have_blocked(rq))
+		*done = false;
+
+	return decayed;
+}
+
 #ifdef CONFIG_FAIR_GROUP_SCHED
 
 static inline bool cfs_rq_is_decayed(struct cfs_rq *cfs_rq)
@@ -7536,29 +7524,11 @@ static inline bool cfs_rq_is_decayed(struct cfs_rq *cfs_rq)
 	return true;
 }
 
-static void update_blocked_averages(int cpu)
+static bool __update_blocked_fair(struct rq *rq, bool *done)
 {
-	struct rq *rq = cpu_rq(cpu);
 	struct cfs_rq *cfs_rq, *pos;
-	const struct sched_class *curr_class;
-	struct rq_flags rf;
-	bool done = true;
-
-	rq_lock_irqsave(rq, &rf);
-	update_rq_clock(rq);
-
-	/*
-	 * update_cfs_rq_load_avg() can call cpufreq_update_util(). Make sure
-	 * that RT, DL and IRQ signals have been updated before updating CFS.
-	 */
-	curr_class = rq->curr->sched_class;
-	update_rt_rq_load_avg(rq_clock_pelt(rq), rq, curr_class == &rt_sched_class);
-	update_dl_rq_load_avg(rq_clock_pelt(rq), rq, curr_class == &dl_sched_class);
-	update_irq_load_avg(rq, 0);
-
-	/* Don't need periodic decay once load/util_avg are null */
-	if (others_have_blocked(rq))
-		done = false;
+	bool decayed = false;
+	int cpu = cpu_of(rq);
 
 	/*
 	 * Iterates the task_group tree in a bottom up fashion, see
@@ -7567,9 +7537,13 @@ static void update_blocked_averages(int cpu)
 	for_each_leaf_cfs_rq_safe(rq, cfs_rq, pos) {
 		struct sched_entity *se;
 
-		if (update_cfs_rq_load_avg(cfs_rq_clock_pelt(cfs_rq), cfs_rq))
+		if (update_cfs_rq_load_avg(cfs_rq_clock_pelt(cfs_rq), cfs_rq)) {
 			update_tg_load_avg(cfs_rq, 0);
 
+			if (cfs_rq == &rq->cfs)
+				decayed = true;
+		}
+
 		/* Propagate pending load changes to the parent, if any: */
 		se = cfs_rq->tg->se[cpu];
 		if (se && !skip_blocked_update(se))
@@ -7584,11 +7558,10 @@ static void update_blocked_averages(int cpu)
 
 		/* Don't need periodic decay once load/util_avg are null */
 		if (cfs_rq_has_blocked(cfs_rq))
-			done = false;
+			*done = false;
 	}
 
-	update_blocked_load_status(rq, !done);
-	rq_unlock_irqrestore(rq, &rf);
+	return decayed;
 }
 
 /*
@@ -7638,29 +7611,16 @@ static unsigned long task_h_load(struct task_struct *p)
 			cfs_rq_load_avg(cfs_rq) + 1);
 }
 #else
-static inline void update_blocked_averages(int cpu)
+static bool __update_blocked_fair(struct rq *rq, bool *done)
 {
-	struct rq *rq = cpu_rq(cpu);
 	struct cfs_rq *cfs_rq = &rq->cfs;
-	const struct sched_class *curr_class;
-	struct rq_flags rf;
-
-	rq_lock_irqsave(rq, &rf);
-	update_rq_clock(rq);
-
-	/*
-	 * update_cfs_rq_load_avg() can call cpufreq_update_util(). Make sure
-	 * that RT, DL and IRQ signals have been updated before updating CFS.
-	 */
-	curr_class = rq->curr->sched_class;
-	update_rt_rq_load_avg(rq_clock_pelt(rq), rq, curr_class == &rt_sched_class);
-	update_dl_rq_load_avg(rq_clock_pelt(rq), rq, curr_class == &dl_sched_class);
-	update_irq_load_avg(rq, 0);
+	bool decayed;
 
-	update_cfs_rq_load_avg(cfs_rq_clock_pelt(cfs_rq), cfs_rq);
+	decayed = update_cfs_rq_load_avg(cfs_rq_clock_pelt(cfs_rq), cfs_rq);
+	if (cfs_rq_has_blocked(cfs_rq))
+		*done = false;
 
-	update_blocked_load_status(rq, cfs_rq_has_blocked(cfs_rq) || others_have_blocked(rq));
-	rq_unlock_irqrestore(rq, &rf);
+	return decayed;
 }
 
 static unsigned long task_h_load(struct task_struct *p)
@@ -7669,6 +7629,24 @@ static unsigned long task_h_load(struct task_struct *p)
 }
 #endif
 
+static void update_blocked_averages(int cpu)
+{
+	bool decayed = false, done = true;
+	struct rq *rq = cpu_rq(cpu);
+	struct rq_flags rf;
+
+	rq_lock_irqsave(rq, &rf);
+	update_rq_clock(rq);
+
+	decayed |= __update_blocked_others(rq, &done);
+	decayed |= __update_blocked_fair(rq, &done);
+
+	update_blocked_load_status(rq, !done);
+	if (decayed)
+		cpufreq_update_util(rq, 0);
+	rq_unlock_irqrestore(rq, &rf);
+}
+
 /********** Helpers for find_busiest_group ************************/
 
 /*
@@ -7677,14 +7655,14 @@ static unsigned long task_h_load(struct task_struct *p)
 struct sg_lb_stats {
 	unsigned long avg_load; /*Avg load across the CPUs of the group */
 	unsigned long group_load; /* Total load over the CPUs of the group */
-	unsigned long load_per_task;
 	unsigned long group_capacity;
 	unsigned long group_util; /* Total utilization of the group */
-	unsigned int sum_nr_running; /* Nr tasks running in the group */
+	unsigned int sum_nr_running; /* Nr of tasks running in the group */
+	unsigned int sum_h_nr_running; /* Nr of CFS tasks running in the group */
 	unsigned int idle_cpus;
 	unsigned int group_weight;
 	enum group_type group_type;
-	int group_no_capacity;
+	unsigned int group_asym_packing; /* Tasks should be moved to preferred CPU */
 	unsigned long group_misfit_task_load; /* A CPU has a task too big for its capacity */
 #ifdef CONFIG_NUMA_BALANCING
 	unsigned int nr_numa_running;
@@ -7699,10 +7677,10 @@ struct sg_lb_stats {
 struct sd_lb_stats {
 	struct sched_group *busiest;	/* Busiest group in this sd */
 	struct sched_group *local;	/* Local group in this sd */
-	unsigned long total_running;
 	unsigned long total_load;	/* Total load of all groups in sd */
 	unsigned long total_capacity;	/* Total capacity of all groups in sd */
 	unsigned long avg_load;	/* Average load across all groups in sd */
+	unsigned int prefer_sibling; /* tasks should go to sibling first */
 
 	struct sg_lb_stats busiest_stat;/* Statistics of the busiest group */
 	struct sg_lb_stats local_stat;	/* Statistics of the local group */
@@ -7713,19 +7691,18 @@ static inline void init_sd_lb_stats(struct sd_lb_stats *sds)
 	/*
 	 * Skimp on the clearing to avoid duplicate work. We can avoid clearing
 	 * local_stat because update_sg_lb_stats() does a full clear/assignment.
-	 * We must however clear busiest_stat::avg_load because
-	 * update_sd_pick_busiest() reads this before assignment.
+	 * We must however set busiest_stat::group_type and
+	 * busiest_stat::idle_cpus to the worst busiest group because
+	 * update_sd_pick_busiest() reads these before assignment.
 	 */
 	*sds = (struct sd_lb_stats){
 		.busiest = NULL,
 		.local = NULL,
-		.total_running = 0UL,
 		.total_load = 0UL,
 		.total_capacity = 0UL,
 		.busiest_stat = {
-			.avg_load = 0UL,
-			.sum_nr_running = 0,
-			.group_type = group_other,
+			.idle_cpus = UINT_MAX,
+			.group_type = group_has_spare,
 		},
 	};
 }
@@ -7913,13 +7890,13 @@ static inline int sg_imbalanced(struct sched_group *group)
  * any benefit for the load balance.
  */
 static inline bool
-group_has_capacity(struct lb_env *env, struct sg_lb_stats *sgs)
+group_has_capacity(unsigned int imbalance_pct, struct sg_lb_stats *sgs)
 {
 	if (sgs->sum_nr_running < sgs->group_weight)
 		return true;
 
 	if ((sgs->group_capacity * 100) >
-			(sgs->group_util * env->sd->imbalance_pct))
+			(sgs->group_util * imbalance_pct))
 		return true;
 
 	return false;
@@ -7934,13 +7911,13 @@ group_has_capacity(struct lb_env *env, struct sg_lb_stats *sgs)
  *  false.
  */
 static inline bool
-group_is_overloaded(struct lb_env *env, struct sg_lb_stats *sgs)
+group_is_overloaded(unsigned int imbalance_pct, struct sg_lb_stats *sgs)
 {
 	if (sgs->sum_nr_running <= sgs->group_weight)
 		return false;
 
 	if ((sgs->group_capacity * 100) <
-			(sgs->group_util * env->sd->imbalance_pct))
+			(sgs->group_util * imbalance_pct))
 		return true;
 
 	return false;
@@ -7967,19 +7944,26 @@ group_smaller_max_cpu_capacity(struct sched_group *sg, struct sched_group *ref)
 }
 
 static inline enum
-group_type group_classify(struct sched_group *group,
+group_type group_classify(unsigned int imbalance_pct,
+			  struct sched_group *group,
 			  struct sg_lb_stats *sgs)
 {
-	if (sgs->group_no_capacity)
+	if (group_is_overloaded(imbalance_pct, sgs))
 		return group_overloaded;
 
 	if (sg_imbalanced(group))
 		return group_imbalanced;
 
+	if (sgs->group_asym_packing)
+		return group_asym_packing;
+
 	if (sgs->group_misfit_task_load)
 		return group_misfit_task;
 
-	return group_other;
+	if (!group_has_capacity(imbalance_pct, sgs))
+		return group_fully_busy;
+
+	return group_has_spare;
 }
 
 static bool update_nohz_stats(struct rq *rq, bool force)
@@ -8016,21 +8000,25 @@ static inline void update_sg_lb_stats(struct lb_env *env,
 				      struct sg_lb_stats *sgs,
 				      int *sg_status)
 {
-	int i, nr_running;
+	int i, nr_running, local_group;
 
 	memset(sgs, 0, sizeof(*sgs));
 
+	local_group = cpumask_test_cpu(env->dst_cpu, sched_group_span(group));
+
 	for_each_cpu_and(i, sched_group_span(group), env->cpus) {
 		struct rq *rq = cpu_rq(i);
 
 		if ((env->flags & LBF_NOHZ_STATS) && update_nohz_stats(rq, false))
 			env->flags |= LBF_NOHZ_AGAIN;
 
-		sgs->group_load += cpu_runnable_load(rq);
+		sgs->group_load += cpu_load(rq);
 		sgs->group_util += cpu_util(i);
-		sgs->sum_nr_running += rq->cfs.h_nr_running;
+		sgs->sum_h_nr_running += rq->cfs.h_nr_running;
 
 		nr_running = rq->nr_running;
+		sgs->sum_nr_running += nr_running;
+
 		if (nr_running > 1)
 			*sg_status |= SG_OVERLOAD;
 
@@ -8044,9 +8032,16 @@ static inline void update_sg_lb_stats(struct lb_env *env,
 		/*
 		 * No need to call idle_cpu() if nr_running is not 0
 		 */
-		if (!nr_running && idle_cpu(i))
+		if (!nr_running && idle_cpu(i)) {
 			sgs->idle_cpus++;
+			/* Idle cpu can't have misfit task */
+			continue;
+		}
 
+		if (local_group)
+			continue;
+
+		/* Check for a misfit task on the cpu */
 		if (env->sd->flags & SD_ASYM_CPUCAPACITY &&
 		    sgs->group_misfit_task_load < rq->misfit_task_load) {
 			sgs->group_misfit_task_load = rq->misfit_task_load;
@@ -8054,17 +8049,24 @@ static inline void update_sg_lb_stats(struct lb_env *env,
 		}
 	}
 
-	/* Adjust by relative CPU capacity of the group */
-	sgs->group_capacity = group->sgc->capacity;
-	sgs->avg_load = (sgs->group_load*SCHED_CAPACITY_SCALE) / sgs->group_capacity;
+	/* Check if dst CPU is idle and preferred to this group */
+	if (env->sd->flags & SD_ASYM_PACKING &&
+	    env->idle != CPU_NOT_IDLE &&
+	    sgs->sum_h_nr_running &&
+	    sched_asym_prefer(env->dst_cpu, group->asym_prefer_cpu)) {
+		sgs->group_asym_packing = 1;
+	}
 
-	if (sgs->sum_nr_running)
-		sgs->load_per_task = sgs->group_load / sgs->sum_nr_running;
+	sgs->group_capacity = group->sgc->capacity;
 
 	sgs->group_weight = group->group_weight;
 
-	sgs->group_no_capacity = group_is_overloaded(env, sgs);
-	sgs->group_type = group_classify(group, sgs);
+	sgs->group_type = group_classify(env->sd->imbalance_pct, group, sgs);
+
+	/* Computing avg_load makes sense only when group is overloaded */
+	if (sgs->group_type == group_overloaded)
+		sgs->avg_load = (sgs->group_load * SCHED_CAPACITY_SCALE) /
+				sgs->group_capacity;
 }
 
 /**
@@ -8087,6 +8089,10 @@ static bool update_sd_pick_busiest(struct lb_env *env,
 {
 	struct sg_lb_stats *busiest = &sds->busiest_stat;
 
+	/* Make sure that there is at least one task to pull */
+	if (!sgs->sum_h_nr_running)
+		return false;
+
 	/*
 	 * Don't try to pull misfit tasks we can't help.
 	 * We can use max_capacity here as reduction in capacity on some
@@ -8095,7 +8101,7 @@ static bool update_sd_pick_busiest(struct lb_env *env,
 	 */
 	if (sgs->group_type == group_misfit_task &&
 	    (!group_smaller_max_cpu_capacity(sg, sds->local) ||
-	     !group_has_capacity(env, &sds->local_stat)))
+	     sds->local_stat.group_type != group_has_spare))
 		return false;
 
 	if (sgs->group_type > busiest->group_type)
@@ -8104,62 +8110,88 @@ static bool update_sd_pick_busiest(struct lb_env *env,
 	if (sgs->group_type < busiest->group_type)
 		return false;
 
-	if (sgs->avg_load <= busiest->avg_load)
-		return false;
-
-	if (!(env->sd->flags & SD_ASYM_CPUCAPACITY))
-		goto asym_packing;
-
 	/*
-	 * Candidate sg has no more than one task per CPU and
-	 * has higher per-CPU capacity. Migrating tasks to less
-	 * capable CPUs may harm throughput. Maximize throughput,
-	 * power/energy consequences are not considered.
+	 * The candidate and the current busiest group are the same type of
+	 * group. Let check which one is the busiest according to the type.
 	 */
-	if (sgs->sum_nr_running <= sgs->group_weight &&
-	    group_smaller_min_cpu_capacity(sds->local, sg))
-		return false;
 
-	/*
-	 * If we have more than one misfit sg go with the biggest misfit.
-	 */
-	if (sgs->group_type == group_misfit_task &&
-	    sgs->group_misfit_task_load < busiest->group_misfit_task_load)
+	switch (sgs->group_type) {
+	case group_overloaded:
+		/* Select the overloaded group with highest avg_load. */
+		if (sgs->avg_load <= busiest->avg_load)
+			return false;
+		break;
+
+	case group_imbalanced:
+		/*
+		 * Select the 1st imbalanced group as we don't have any way to
+		 * choose one more than another.
+		 */
 		return false;
 
-asym_packing:
-	/* This is the busiest node in its class. */
-	if (!(env->sd->flags & SD_ASYM_PACKING))
-		return true;
+	case group_asym_packing:
+		/* Prefer to move from lowest priority CPU's work */
+		if (sched_asym_prefer(sg->asym_prefer_cpu, sds->busiest->asym_prefer_cpu))
+			return false;
+		break;
 
-	/* No ASYM_PACKING if target CPU is already busy */
-	if (env->idle == CPU_NOT_IDLE)
-		return true;
-	/*
-	 * ASYM_PACKING needs to move all the work to the highest
-	 * prority CPUs in the group, therefore mark all groups
-	 * of lower priority than ourself as busy.
-	 */
-	if (sgs->sum_nr_running &&
-	    sched_asym_prefer(env->dst_cpu, sg->asym_prefer_cpu)) {
-		if (!sds->busiest)
-			return true;
+	case group_misfit_task:
+		/*
+		 * If we have more than one misfit sg go with the biggest
+		 * misfit.
+		 */
+		if (sgs->group_misfit_task_load < busiest->group_misfit_task_load)
+			return false;
+		break;
 
-		/* Prefer to move from lowest priority CPU's work */
-		if (sched_asym_prefer(sds->busiest->asym_prefer_cpu,
-				      sg->asym_prefer_cpu))
-			return true;
+	case group_fully_busy:
+		/*
+		 * Select the fully busy group with highest avg_load. In
+		 * theory, there is no need to pull task from such kind of
+		 * group because tasks have all compute capacity that they need
+		 * but we can still improve the overall throughput by reducing
+		 * contention when accessing shared HW resources.
+		 *
+		 * XXX for now avg_load is not computed and always 0 so we
+		 * select the 1st one.
+		 */
+		if (sgs->avg_load <= busiest->avg_load)
+			return false;
+		break;
+
+	case group_has_spare:
+		/*
+		 * Select not overloaded group with lowest number of
+		 * idle cpus. We could also compare the spare capacity
+		 * which is more stable but it can end up that the
+		 * group has less spare capacity but finally more idle
+		 * CPUs which means less opportunity to pull tasks.
+		 */
+		if (sgs->idle_cpus >= busiest->idle_cpus)
+			return false;
+		break;
 	}
 
-	return false;
+	/*
+	 * Candidate sg has no more than one task per CPU and has higher
+	 * per-CPU capacity. Migrating tasks to less capable CPUs may harm
+	 * throughput. Maximize throughput, power/energy consequences are not
+	 * considered.
+	 */
+	if ((env->sd->flags & SD_ASYM_CPUCAPACITY) &&
+	    (sgs->group_type <= group_fully_busy) &&
+	    (group_smaller_min_cpu_capacity(sds->local, sg)))
+		return false;
+
+	return true;
 }
 
 #ifdef CONFIG_NUMA_BALANCING
 static inline enum fbq_type fbq_classify_group(struct sg_lb_stats *sgs)
 {
-	if (sgs->sum_nr_running > sgs->nr_numa_running)
+	if (sgs->sum_h_nr_running > sgs->nr_numa_running)
 		return regular;
-	if (sgs->sum_nr_running > sgs->nr_preferred_running)
+	if (sgs->sum_h_nr_running > sgs->nr_preferred_running)
 		return remote;
 	return all;
 }
@@ -8184,18 +8216,310 @@ static inline enum fbq_type fbq_classify_rq(struct rq *rq)
 }
 #endif /* CONFIG_NUMA_BALANCING */
 
+
+struct sg_lb_stats;
+
+/*
+ * task_running_on_cpu - return 1 if @p is running on @cpu.
+ */
+
+static unsigned int task_running_on_cpu(int cpu, struct task_struct *p)
+{
+	/* Task has no contribution or is new */
+	if (cpu != task_cpu(p) || !READ_ONCE(p->se.avg.last_update_time))
+		return 0;
+
+	if (task_on_rq_queued(p))
+		return 1;
+
+	return 0;
+}
+
+/**
+ * idle_cpu_without - would a given CPU be idle without p ?
+ * @cpu: the processor on which idleness is tested.
+ * @p: task which should be ignored.
+ *
+ * Return: 1 if the CPU would be idle. 0 otherwise.
+ */
+static int idle_cpu_without(int cpu, struct task_struct *p)
+{
+	struct rq *rq = cpu_rq(cpu);
+
+	if (rq->curr != rq->idle && rq->curr != p)
+		return 0;
+
+	/*
+	 * rq->nr_running can't be used but an updated version without the
+	 * impact of p on cpu must be used instead. The updated nr_running
+	 * be computed and tested before calling idle_cpu_without().
+	 */
+
+#ifdef CONFIG_SMP
+	if (!llist_empty(&rq->wake_list))
+		return 0;
+#endif
+
+	return 1;
+}
+
+/*
+ * update_sg_wakeup_stats - Update sched_group's statistics for wakeup.
+ * @sd: The sched_domain level to look for idlest group.
+ * @group: sched_group whose statistics are to be updated.
+ * @sgs: variable to hold the statistics for this group.
+ * @p: The task for which we look for the idlest group/CPU.
+ */
+static inline void update_sg_wakeup_stats(struct sched_domain *sd,
+					  struct sched_group *group,
+					  struct sg_lb_stats *sgs,
+					  struct task_struct *p)
+{
+	int i, nr_running;
+
+	memset(sgs, 0, sizeof(*sgs));
+
+	for_each_cpu(i, sched_group_span(group)) {
+		struct rq *rq = cpu_rq(i);
+		unsigned int local;
+
+		sgs->group_load += cpu_load_without(rq, p);
+		sgs->group_util += cpu_util_without(i, p);
+		local = task_running_on_cpu(i, p);
+		sgs->sum_h_nr_running += rq->cfs.h_nr_running - local;
+
+		nr_running = rq->nr_running - local;
+		sgs->sum_nr_running += nr_running;
+
+		/*
+		 * No need to call idle_cpu_without() if nr_running is not 0
+		 */
+		if (!nr_running && idle_cpu_without(i, p))
+			sgs->idle_cpus++;
+
+	}
+
+	/* Check if task fits in the group */
+	if (sd->flags & SD_ASYM_CPUCAPACITY &&
+	    !task_fits_capacity(p, group->sgc->max_capacity)) {
+		sgs->group_misfit_task_load = 1;
+	}
+
+	sgs->group_capacity = group->sgc->capacity;
+
+	sgs->group_type = group_classify(sd->imbalance_pct, group, sgs);
+
+	/*
+	 * Computing avg_load makes sense only when group is fully busy or
+	 * overloaded
+	 */
+	if (sgs->group_type < group_fully_busy)
+		sgs->avg_load = (sgs->group_load * SCHED_CAPACITY_SCALE) /
+				sgs->group_capacity;
+}
+
+static bool update_pick_idlest(struct sched_group *idlest,
+			       struct sg_lb_stats *idlest_sgs,
+			       struct sched_group *group,
+			       struct sg_lb_stats *sgs)
+{
+	if (sgs->group_type < idlest_sgs->group_type)
+		return true;
+
+	if (sgs->group_type > idlest_sgs->group_type)
+		return false;
+
+	/*
+	 * The candidate and the current idlest group are the same type of
+	 * group. Let check which one is the idlest according to the type.
+	 */
+
+	switch (sgs->group_type) {
+	case group_overloaded:
+	case group_fully_busy:
+		/* Select the group with lowest avg_load. */
+		if (idlest_sgs->avg_load <= sgs->avg_load)
+			return false;
+		break;
+
+	case group_imbalanced:
+	case group_asym_packing:
+		/* Those types are not used in the slow wakeup path */
+		return false;
+
+	case group_misfit_task:
+		/* Select group with the highest max capacity */
+		if (idlest->sgc->max_capacity >= group->sgc->max_capacity)
+			return false;
+		break;
+
+	case group_has_spare:
+		/* Select group with most idle CPUs */
+		if (idlest_sgs->idle_cpus >= sgs->idle_cpus)
+			return false;
+		break;
+	}
+
+	return true;
+}
+
+/*
+ * find_idlest_group() finds and returns the least busy CPU group within the
+ * domain.
+ *
+ * Assumes p is allowed on at least one CPU in sd.
+ */
+static struct sched_group *
+find_idlest_group(struct sched_domain *sd, struct task_struct *p,
+		  int this_cpu, int sd_flag)
+{
+	struct sched_group *idlest = NULL, *local = NULL, *group = sd->groups;
+	struct sg_lb_stats local_sgs, tmp_sgs;
+	struct sg_lb_stats *sgs;
+	unsigned long imbalance;
+	struct sg_lb_stats idlest_sgs = {
+			.avg_load = UINT_MAX,
+			.group_type = group_overloaded,
+	};
+
+	imbalance = scale_load_down(NICE_0_LOAD) *
+				(sd->imbalance_pct-100) / 100;
+
+	do {
+		int local_group;
+
+		/* Skip over this group if it has no CPUs allowed */
+		if (!cpumask_intersects(sched_group_span(group),
+					p->cpus_ptr))
+			continue;
+
+		local_group = cpumask_test_cpu(this_cpu,
+					       sched_group_span(group));
+
+		if (local_group) {
+			sgs = &local_sgs;
+			local = group;
+		} else {
+			sgs = &tmp_sgs;
+		}
+
+		update_sg_wakeup_stats(sd, group, sgs, p);
+
+		if (!local_group && update_pick_idlest(idlest, &idlest_sgs, group, sgs)) {
+			idlest = group;
+			idlest_sgs = *sgs;
+		}
+
+	} while (group = group->next, group != sd->groups);
+
+
+	/* There is no idlest group to push tasks to */
+	if (!idlest)
+		return NULL;
+
+	/*
+	 * If the local group is idler than the selected idlest group
+	 * don't try and push the task.
+	 */
+	if (local_sgs.group_type < idlest_sgs.group_type)
+		return NULL;
+
+	/*
+	 * If the local group is busier than the selected idlest group
+	 * try and push the task.
+	 */
+	if (local_sgs.group_type > idlest_sgs.group_type)
+		return idlest;
+
+	switch (local_sgs.group_type) {
+	case group_overloaded:
+	case group_fully_busy:
+		/*
+		 * When comparing groups across NUMA domains, it's possible for
+		 * the local domain to be very lightly loaded relative to the
+		 * remote domains but "imbalance" skews the comparison making
+		 * remote CPUs look much more favourable. When considering
+		 * cross-domain, add imbalance to the load on the remote node
+		 * and consider staying local.
+		 */
+
+		if ((sd->flags & SD_NUMA) &&
+		    ((idlest_sgs.avg_load + imbalance) >= local_sgs.avg_load))
+			return NULL;
+
+		/*
+		 * If the local group is less loaded than the selected
+		 * idlest group don't try and push any tasks.
+		 */
+		if (idlest_sgs.avg_load >= (local_sgs.avg_load + imbalance))
+			return NULL;
+
+		if (100 * local_sgs.avg_load <= sd->imbalance_pct * idlest_sgs.avg_load)
+			return NULL;
+		break;
+
+	case group_imbalanced:
+	case group_asym_packing:
+		/* Those type are not used in the slow wakeup path */
+		return NULL;
+
+	case group_misfit_task:
+		/* Select group with the highest max capacity */
+		if (local->sgc->max_capacity >= idlest->sgc->max_capacity)
+			return NULL;
+		break;
+
+	case group_has_spare:
+		if (sd->flags & SD_NUMA) {
+#ifdef CONFIG_NUMA_BALANCING
+			int idlest_cpu;
+			/*
+			 * If there is spare capacity at NUMA, try to select
+			 * the preferred node
+			 */
+			if (cpu_to_node(this_cpu) == p->numa_preferred_nid)
+				return NULL;
+
+			idlest_cpu = cpumask_first(sched_group_span(idlest));
+			if (cpu_to_node(idlest_cpu) == p->numa_preferred_nid)
+				return idlest;
+#endif
+			/*
+			 * Otherwise, keep the task on this node to stay close
+			 * its wakeup source and improve locality. If there is
+			 * a real need of migration, periodic load balance will
+			 * take care of it.
+			 */
+			if (local_sgs.idle_cpus)
+				return NULL;
+		}
+
+		/*
+		 * Select group with highest number of idle CPUs. We could also
+		 * compare the utilization which is more stable but it can end
+		 * up that the group has less spare capacity but finally more
+		 * idle CPUs which means more opportunity to run task.
+		 */
+		if (local_sgs.idle_cpus >= idlest_sgs.idle_cpus)
+			return NULL;
+		break;
+	}
+
+	return idlest;
+}
+
 /**
  * update_sd_lb_stats - Update sched_domain's statistics for load balancing.
  * @env: The load balancing environment.
  * @sds: variable to hold the statistics for this sched_domain.
  */
+
 static inline void update_sd_lb_stats(struct lb_env *env, struct sd_lb_stats *sds)
 {
 	struct sched_domain *child = env->sd->child;
 	struct sched_group *sg = env->sd->groups;
 	struct sg_lb_stats *local = &sds->local_stat;
 	struct sg_lb_stats tmp_sgs;
-	bool prefer_sibling = child && child->flags & SD_PREFER_SIBLING;
 	int sg_status = 0;
 
 #ifdef CONFIG_NO_HZ_COMMON
@@ -8222,22 +8546,6 @@ static inline void update_sd_lb_stats(struct lb_env *env, struct sd_lb_stats *sd
 		if (local_group)
 			goto next_group;
 
-		/*
-		 * In case the child domain prefers tasks go to siblings
-		 * first, lower the sg capacity so that we'll try
-		 * and move all the excess tasks away. We lower the capacity
-		 * of a group only if the local group has the capacity to fit
-		 * these excess tasks. The extra check prevents the case where
-		 * you always pull from the heaviest group when it is already
-		 * under-utilized (possible with a large weight task outweighs
-		 * the tasks on the system).
-		 */
-		if (prefer_sibling && sds->local &&
-		    group_has_capacity(env, local) &&
-		    (sgs->sum_nr_running > local->sum_nr_running + 1)) {
-			sgs->group_no_capacity = 1;
-			sgs->group_type = group_classify(sg, sgs);
-		}
 
 		if (update_sd_pick_busiest(env, sds, sg, sgs)) {
 			sds->busiest = sg;
@@ -8246,13 +8554,15 @@ static inline void update_sd_lb_stats(struct lb_env *env, struct sd_lb_stats *sd
 
 next_group:
 		/* Now, start updating sd_lb_stats */
-		sds->total_running += sgs->sum_nr_running;
 		sds->total_load += sgs->group_load;
 		sds->total_capacity += sgs->group_capacity;
 
 		sg = sg->next;
 	} while (sg != env->sd->groups);
 
+	/* Tag domain that child domain prefers tasks go to siblings first */
+	sds->prefer_sibling = child && child->flags & SD_PREFER_SIBLING;
+
 #ifdef CONFIG_NO_HZ_COMMON
 	if ((env->flags & LBF_NOHZ_AGAIN) &&
 	    cpumask_subset(nohz.idle_cpus_mask, sched_domain_span(env->sd))) {
@@ -8283,203 +8593,160 @@ next_group:
 }
 
 /**
- * check_asym_packing - Check to see if the group is packed into the
- *			sched domain.
- *
- * This is primarily intended to used at the sibling level.  Some
- * cores like POWER7 prefer to use lower numbered SMT threads.  In the
- * case of POWER7, it can move to lower SMT modes only when higher
- * threads are idle.  When in lower SMT modes, the threads will
- * perform better since they share less core resources.  Hence when we
- * have idle threads, we want them to be the higher ones.
- *
- * This packing function is run on idle threads.  It checks to see if
- * the busiest CPU in this domain (core in the P7 case) has a higher
- * CPU number than the packing function is being run on.  Here we are
- * assuming lower CPU number will be equivalent to lower a SMT thread
- * number.
- *
- * Return: 1 when packing is required and a task should be moved to
- * this CPU.  The amount of the imbalance is returned in env->imbalance.
- *
- * @env: The load balancing environment.
- * @sds: Statistics of the sched_domain which is to be packed
- */
-static int check_asym_packing(struct lb_env *env, struct sd_lb_stats *sds)
-{
-	int busiest_cpu;
-
-	if (!(env->sd->flags & SD_ASYM_PACKING))
-		return 0;
-
-	if (env->idle == CPU_NOT_IDLE)
-		return 0;
-
-	if (!sds->busiest)
-		return 0;
-
-	busiest_cpu = sds->busiest->asym_prefer_cpu;
-	if (sched_asym_prefer(busiest_cpu, env->dst_cpu))
-		return 0;
-
-	env->imbalance = sds->busiest_stat.group_load;
-
-	return 1;
-}
-
-/**
- * fix_small_imbalance - Calculate the minor imbalance that exists
- *			amongst the groups of a sched_domain, during
- *			load balancing.
- * @env: The load balancing environment.
- * @sds: Statistics of the sched_domain whose imbalance is to be calculated.
+ * calculate_imbalance - Calculate the amount of imbalance present within the
+ *			 groups of a given sched_domain during load balance.
+ * @env: load balance environment
+ * @sds: statistics of the sched_domain whose imbalance is to be calculated.
  */
-static inline
-void fix_small_imbalance(struct lb_env *env, struct sd_lb_stats *sds)
+static inline void calculate_imbalance(struct lb_env *env, struct sd_lb_stats *sds)
 {
-	unsigned long tmp, capa_now = 0, capa_move = 0;
-	unsigned int imbn = 2;
-	unsigned long scaled_busy_load_per_task;
 	struct sg_lb_stats *local, *busiest;
 
 	local = &sds->local_stat;
 	busiest = &sds->busiest_stat;
 
-	if (!local->sum_nr_running)
-		local->load_per_task = cpu_avg_load_per_task(env->dst_cpu);
-	else if (busiest->load_per_task > local->load_per_task)
-		imbn = 1;
+	if (busiest->group_type == group_misfit_task) {
+		/* Set imbalance to allow misfit tasks to be balanced. */
+		env->migration_type = migrate_misfit;
+		env->imbalance = 1;
+		return;
+	}
 
-	scaled_busy_load_per_task =
-		(busiest->load_per_task * SCHED_CAPACITY_SCALE) /
-		busiest->group_capacity;
+	if (busiest->group_type == group_asym_packing) {
+		/*
+		 * In case of asym capacity, we will try to migrate all load to
+		 * the preferred CPU.
+		 */
+		env->migration_type = migrate_task;
+		env->imbalance = busiest->sum_h_nr_running;
+		return;
+	}
 
-	if (busiest->avg_load + scaled_busy_load_per_task >=
-	    local->avg_load + (scaled_busy_load_per_task * imbn)) {
-		env->imbalance = busiest->load_per_task;
+	if (busiest->group_type == group_imbalanced) {
+		/*
+		 * In the group_imb case we cannot rely on group-wide averages
+		 * to ensure CPU-load equilibrium, try to move any task to fix
+		 * the imbalance. The next load balance will take care of
+		 * balancing back the system.
+		 */
+		env->migration_type = migrate_task;
+		env->imbalance = 1;
 		return;
 	}
 
 	/*
-	 * OK, we don't have enough imbalance to justify moving tasks,
-	 * however we may be able to increase total CPU capacity used by
-	 * moving them.
+	 * Try to use spare capacity of local group without overloading it or
+	 * emptying busiest.
+	 * XXX Spreading tasks across NUMA nodes is not always the best policy
+	 * and special care should be taken for SD_NUMA domain level before
+	 * spreading the tasks. For now, load_balance() fully relies on
+	 * NUMA_BALANCING and fbq_classify_group/rq to override the decision.
 	 */
+	if (local->group_type == group_has_spare) {
+		if (busiest->group_type > group_fully_busy) {
+			/*
+			 * If busiest is overloaded, try to fill spare
+			 * capacity. This might end up creating spare capacity
+			 * in busiest or busiest still being overloaded but
+			 * there is no simple way to directly compute the
+			 * amount of load to migrate in order to balance the
+			 * system.
+			 */
+			env->migration_type = migrate_util;
+			env->imbalance = max(local->group_capacity, local->group_util) -
+					 local->group_util;
 
-	capa_now += busiest->group_capacity *
-			min(busiest->load_per_task, busiest->avg_load);
-	capa_now += local->group_capacity *
-			min(local->load_per_task, local->avg_load);
-	capa_now /= SCHED_CAPACITY_SCALE;
-
-	/* Amount of load we'd subtract */
-	if (busiest->avg_load > scaled_busy_load_per_task) {
-		capa_move += busiest->group_capacity *
-			    min(busiest->load_per_task,
-				busiest->avg_load - scaled_busy_load_per_task);
-	}
-
-	/* Amount of load we'd add */
-	if (busiest->avg_load * busiest->group_capacity <
-	    busiest->load_per_task * SCHED_CAPACITY_SCALE) {
-		tmp = (busiest->avg_load * busiest->group_capacity) /
-		      local->group_capacity;
-	} else {
-		tmp = (busiest->load_per_task * SCHED_CAPACITY_SCALE) /
-		      local->group_capacity;
-	}
-	capa_move += local->group_capacity *
-		    min(local->load_per_task, local->avg_load + tmp);
-	capa_move /= SCHED_CAPACITY_SCALE;
-
-	/* Move if we gain throughput */
-	if (capa_move > capa_now)
-		env->imbalance = busiest->load_per_task;
-}
+			/*
+			 * In some cases, the group's utilization is max or even
+			 * higher than capacity because of migrations but the
+			 * local CPU is (newly) idle. There is at least one
+			 * waiting task in this overloaded busiest group. Let's
+			 * try to pull it.
+			 */
+			if (env->idle != CPU_NOT_IDLE && env->imbalance == 0) {
+				env->migration_type = migrate_task;
+				env->imbalance = 1;
+			}
 
-/**
- * calculate_imbalance - Calculate the amount of imbalance present within the
- *			 groups of a given sched_domain during load balance.
- * @env: load balance environment
- * @sds: statistics of the sched_domain whose imbalance is to be calculated.
- */
-static inline void calculate_imbalance(struct lb_env *env, struct sd_lb_stats *sds)
-{
-	unsigned long max_pull, load_above_capacity = ~0UL;
-	struct sg_lb_stats *local, *busiest;
+			return;
+		}
 
-	local = &sds->local_stat;
-	busiest = &sds->busiest_stat;
+		if (busiest->group_weight == 1 || sds->prefer_sibling) {
+			unsigned int nr_diff = busiest->sum_nr_running;
+			/*
+			 * When prefer sibling, evenly spread running tasks on
+			 * groups.
+			 */
+			env->migration_type = migrate_task;
+			lsub_positive(&nr_diff, local->sum_nr_running);
+			env->imbalance = nr_diff >> 1;
+			return;
+		}
 
-	if (busiest->group_type == group_imbalanced) {
 		/*
-		 * In the group_imb case we cannot rely on group-wide averages
-		 * to ensure CPU-load equilibrium, look at wider averages. XXX
+		 * If there is no overload, we just want to even the number of
+		 * idle cpus.
 		 */
-		busiest->load_per_task =
-			min(busiest->load_per_task, sds->avg_load);
+		env->migration_type = migrate_task;
+		env->imbalance = max_t(long, 0, (local->idle_cpus -
+						 busiest->idle_cpus) >> 1);
+		return;
 	}
 
 	/*
-	 * Avg load of busiest sg can be less and avg load of local sg can
-	 * be greater than avg load across all sgs of sd because avg load
-	 * factors in sg capacity and sgs with smaller group_type are
-	 * skipped when updating the busiest sg:
+	 * Local is fully busy but has to take more load to relieve the
+	 * busiest group
 	 */
-	if (busiest->group_type != group_misfit_task &&
-	    (busiest->avg_load <= sds->avg_load ||
-	     local->avg_load >= sds->avg_load)) {
-		env->imbalance = 0;
-		return fix_small_imbalance(env, sds);
-	}
+	if (local->group_type < group_overloaded) {
+		/*
+		 * Local will become overloaded so the avg_load metrics are
+		 * finally needed.
+		 */
 
-	/*
-	 * If there aren't any idle CPUs, avoid creating some.
-	 */
-	if (busiest->group_type == group_overloaded &&
-	    local->group_type   == group_overloaded) {
-		load_above_capacity = busiest->sum_nr_running * SCHED_CAPACITY_SCALE;
-		if (load_above_capacity > busiest->group_capacity) {
-			load_above_capacity -= busiest->group_capacity;
-			load_above_capacity *= scale_load_down(NICE_0_LOAD);
-			load_above_capacity /= busiest->group_capacity;
-		} else
-			load_above_capacity = ~0UL;
+		local->avg_load = (local->group_load * SCHED_CAPACITY_SCALE) /
+				  local->group_capacity;
+
+		sds->avg_load = (sds->total_load * SCHED_CAPACITY_SCALE) /
+				sds->total_capacity;
 	}
 
 	/*
-	 * We're trying to get all the CPUs to the average_load, so we don't
-	 * want to push ourselves above the average load, nor do we wish to
-	 * reduce the max loaded CPU below the average load. At the same time,
-	 * we also don't want to reduce the group load below the group
-	 * capacity. Thus we look for the minimum possible imbalance.
+	 * Both group are or will become overloaded and we're trying to get all
+	 * the CPUs to the average_load, so we don't want to push ourselves
+	 * above the average load, nor do we wish to reduce the max loaded CPU
+	 * below the average load. At the same time, we also don't want to
+	 * reduce the group load below the group capacity. Thus we look for
+	 * the minimum possible imbalance.
 	 */
-	max_pull = min(busiest->avg_load - sds->avg_load, load_above_capacity);
-
-	/* How much load to actually move to equalise the imbalance */
+	env->migration_type = migrate_load;
 	env->imbalance = min(
-		max_pull * busiest->group_capacity,
+		(busiest->avg_load - sds->avg_load) * busiest->group_capacity,
 		(sds->avg_load - local->avg_load) * local->group_capacity
 	) / SCHED_CAPACITY_SCALE;
-
-	/* Boost imbalance to allow misfit task to be balanced. */
-	if (busiest->group_type == group_misfit_task) {
-		env->imbalance = max_t(long, env->imbalance,
-				       busiest->group_misfit_task_load);
-	}
-
-	/*
-	 * if *imbalance is less than the average load per runnable task
-	 * there is no guarantee that any tasks will be moved so we'll have
-	 * a think about bumping its value to force at least one task to be
-	 * moved
-	 */
-	if (env->imbalance < busiest->load_per_task)
-		return fix_small_imbalance(env, sds);
 }
 
 /******* find_busiest_group() helpers end here *********************/
 
+/*
+ * Decision matrix according to the local and busiest group type:
+ *
+ * busiest \ local has_spare fully_busy misfit asym imbalanced overloaded
+ * has_spare        nr_idle   balanced   N/A    N/A  balanced   balanced
+ * fully_busy       nr_idle   nr_idle    N/A    N/A  balanced   balanced
+ * misfit_task      force     N/A        N/A    N/A  force      force
+ * asym_packing     force     force      N/A    N/A  force      force
+ * imbalanced       force     force      N/A    N/A  force      force
+ * overloaded       force     force      N/A    N/A  force      avg_load
+ *
+ * N/A :      Not Applicable because already filtered while updating
+ *            statistics.
+ * balanced : The system is balanced for these 2 groups.
+ * force :    Calculate the imbalance as load migration is probably needed.
+ * avg_load : Only if imbalance is significant enough.
+ * nr_idle :  dst_cpu is not busy and the number of idle CPUs is quite
+ *            different in groups.
+ */
+
 /**
  * find_busiest_group - Returns the busiest group within the sched_domain
  * if there is an imbalance.
@@ -8499,7 +8766,7 @@ static struct sched_group *find_busiest_group(struct lb_env *env)
 	init_sd_lb_stats(&sds);
 
 	/*
-	 * Compute the various statistics relavent for load balancing at
+	 * Compute the various statistics relevant for load balancing at
 	 * this level.
 	 */
 	update_sd_lb_stats(env, &sds);
@@ -8514,17 +8781,17 @@ static struct sched_group *find_busiest_group(struct lb_env *env)
 	local = &sds.local_stat;
 	busiest = &sds.busiest_stat;
 
-	/* ASYM feature bypasses nice load balance check */
-	if (check_asym_packing(env, &sds))
-		return sds.busiest;
-
 	/* There is no busy sibling group to pull tasks from */
-	if (!sds.busiest || busiest->sum_nr_running == 0)
+	if (!sds.busiest)
 		goto out_balanced;
 
-	/* XXX broken for overlapping NUMA groups */
-	sds.avg_load = (SCHED_CAPACITY_SCALE * sds.total_load)
-						/ sds.total_capacity;
+	/* Misfit tasks should be dealt with regardless of the avg load */
+	if (busiest->group_type == group_misfit_task)
+		goto force_balance;
+
+	/* ASYM feature bypasses nice load balance check */
+	if (busiest->group_type == group_asym_packing)
+		goto force_balance;
 
 	/*
 	 * If the busiest group is imbalanced the below checks don't
@@ -8535,55 +8802,80 @@ static struct sched_group *find_busiest_group(struct lb_env *env)
 		goto force_balance;
 
 	/*
-	 * When dst_cpu is idle, prevent SMP nice and/or asymmetric group
-	 * capacities from resulting in underutilization due to avg_load.
-	 */
-	if (env->idle != CPU_NOT_IDLE && group_has_capacity(env, local) &&
-	    busiest->group_no_capacity)
-		goto force_balance;
-
-	/* Misfit tasks should be dealt with regardless of the avg load */
-	if (busiest->group_type == group_misfit_task)
-		goto force_balance;
-
-	/*
 	 * If the local group is busier than the selected busiest group
 	 * don't try and pull any tasks.
 	 */
-	if (local->avg_load >= busiest->avg_load)
+	if (local->group_type > busiest->group_type)
 		goto out_balanced;
 
 	/*
-	 * Don't pull any tasks if this group is already above the domain
-	 * average load.
+	 * When groups are overloaded, use the avg_load to ensure fairness
+	 * between tasks.
 	 */
-	if (local->avg_load >= sds.avg_load)
-		goto out_balanced;
+	if (local->group_type == group_overloaded) {
+		/*
+		 * If the local group is more loaded than the selected
+		 * busiest group don't try to pull any tasks.
+		 */
+		if (local->avg_load >= busiest->avg_load)
+			goto out_balanced;
+
+		/* XXX broken for overlapping NUMA groups */
+		sds.avg_load = (sds.total_load * SCHED_CAPACITY_SCALE) /
+				sds.total_capacity;
 
-	if (env->idle == CPU_IDLE) {
 		/*
-		 * This CPU is idle. If the busiest group is not overloaded
-		 * and there is no imbalance between this and busiest group
-		 * wrt idle CPUs, it is balanced. The imbalance becomes
-		 * significant if the diff is greater than 1 otherwise we
-		 * might end up to just move the imbalance on another group
+		 * Don't pull any tasks if this group is already above the
+		 * domain average load.
 		 */
-		if ((busiest->group_type != group_overloaded) &&
-				(local->idle_cpus <= (busiest->idle_cpus + 1)))
+		if (local->avg_load >= sds.avg_load)
 			goto out_balanced;
-	} else {
+
 		/*
-		 * In the CPU_NEWLY_IDLE, CPU_NOT_IDLE cases, use
-		 * imbalance_pct to be conservative.
+		 * If the busiest group is more loaded, use imbalance_pct to be
+		 * conservative.
 		 */
 		if (100 * busiest->avg_load <=
 				env->sd->imbalance_pct * local->avg_load)
 			goto out_balanced;
 	}
 
+	/* Try to move all excess tasks to child's sibling domain */
+	if (sds.prefer_sibling && local->group_type == group_has_spare &&
+	    busiest->sum_nr_running > local->sum_nr_running + 1)
+		goto force_balance;
+
+	if (busiest->group_type != group_overloaded) {
+		if (env->idle == CPU_NOT_IDLE)
+			/*
+			 * If the busiest group is not overloaded (and as a
+			 * result the local one too) but this CPU is already
+			 * busy, let another idle CPU try to pull task.
+			 */
+			goto out_balanced;
+
+		if (busiest->group_weight > 1 &&
+		    local->idle_cpus <= (busiest->idle_cpus + 1))
+			/*
+			 * If the busiest group is not overloaded
+			 * and there is no imbalance between this and busiest
+			 * group wrt idle CPUs, it is balanced. The imbalance
+			 * becomes significant if the diff is greater than 1
+			 * otherwise we might end up to just move the imbalance
+			 * on another group. Of course this applies only if
+			 * there is more than 1 CPU per group.
+			 */
+			goto out_balanced;
+
+		if (busiest->sum_h_nr_running == 1)
+			/*
+			 * busiest doesn't have any tasks waiting to run
+			 */
+			goto out_balanced;
+	}
+
 force_balance:
 	/* Looks like there is an imbalance. Compute it */
-	env->src_grp_type = busiest->group_type;
 	calculate_imbalance(env, &sds);
 	return env->imbalance ? sds.busiest : NULL;
 
@@ -8599,11 +8891,13 @@ static struct rq *find_busiest_queue(struct lb_env *env,
 				     struct sched_group *group)
 {
 	struct rq *busiest = NULL, *rq;
-	unsigned long busiest_load = 0, busiest_capacity = 1;
+	unsigned long busiest_util = 0, busiest_load = 0, busiest_capacity = 1;
+	unsigned int busiest_nr = 0;
 	int i;
 
 	for_each_cpu_and(i, sched_group_span(group), env->cpus) {
-		unsigned long capacity, load;
+		unsigned long capacity, load, util;
+		unsigned int nr_running;
 		enum fbq_type rt;
 
 		rq = cpu_rq(i);
@@ -8631,20 +8925,8 @@ static struct rq *find_busiest_queue(struct lb_env *env,
 		if (rt > env->fbq_type)
 			continue;
 
-		/*
-		 * For ASYM_CPUCAPACITY domains with misfit tasks we simply
-		 * seek the "biggest" misfit task.
-		 */
-		if (env->src_grp_type == group_misfit_task) {
-			if (rq->misfit_task_load > busiest_load) {
-				busiest_load = rq->misfit_task_load;
-				busiest = rq;
-			}
-
-			continue;
-		}
-
 		capacity = capacity_of(i);
+		nr_running = rq->cfs.h_nr_running;
 
 		/*
 		 * For ASYM_CPUCAPACITY domains, don't pick a CPU that could
@@ -8654,35 +8936,69 @@ static struct rq *find_busiest_queue(struct lb_env *env,
 		 */
 		if (env->sd->flags & SD_ASYM_CPUCAPACITY &&
 		    capacity_of(env->dst_cpu) < capacity &&
-		    rq->nr_running == 1)
+		    nr_running == 1)
 			continue;
 
-		load = cpu_runnable_load(rq);
+		switch (env->migration_type) {
+		case migrate_load:
+			/*
+			 * When comparing with load imbalance, use cpu_load()
+			 * which is not scaled with the CPU capacity.
+			 */
+			load = cpu_load(rq);
 
-		/*
-		 * When comparing with imbalance, use cpu_runnable_load()
-		 * which is not scaled with the CPU capacity.
-		 */
+			if (nr_running == 1 && load > env->imbalance &&
+			    !check_cpu_capacity(rq, env->sd))
+				break;
 
-		if (rq->nr_running == 1 && load > env->imbalance &&
-		    !check_cpu_capacity(rq, env->sd))
-			continue;
+			/*
+			 * For the load comparisons with the other CPUs,
+			 * consider the cpu_load() scaled with the CPU
+			 * capacity, so that the load can be moved away
+			 * from the CPU that is potentially running at a
+			 * lower capacity.
+			 *
+			 * Thus we're looking for max(load_i / capacity_i),
+			 * crosswise multiplication to rid ourselves of the
+			 * division works out to:
+			 * load_i * capacity_j > load_j * capacity_i;
+			 * where j is our previous maximum.
+			 */
+			if (load * busiest_capacity > busiest_load * capacity) {
+				busiest_load = load;
+				busiest_capacity = capacity;
+				busiest = rq;
+			}
+			break;
+
+		case migrate_util:
+			util = cpu_util(cpu_of(rq));
+
+			if (busiest_util < util) {
+				busiest_util = util;
+				busiest = rq;
+			}
+			break;
+
+		case migrate_task:
+			if (busiest_nr < nr_running) {
+				busiest_nr = nr_running;
+				busiest = rq;
+			}
+			break;
+
+		case migrate_misfit:
+			/*
+			 * For ASYM_CPUCAPACITY domains with misfit tasks we
+			 * simply seek the "biggest" misfit task.
+			 */
+			if (rq->misfit_task_load > busiest_load) {
+				busiest_load = rq->misfit_task_load;
+				busiest = rq;
+			}
+
+			break;
 
-		/*
-		 * For the load comparisons with the other CPU's, consider
-		 * the cpu_runnable_load() scaled with the CPU capacity, so
-		 * that the load can be moved away from the CPU that is
-		 * potentially running at a lower capacity.
-		 *
-		 * Thus we're looking for max(load_i / capacity_i), crosswise
-		 * multiplication to rid ourselves of the division works out
-		 * to: load_i * capacity_j > load_j * capacity_i;  where j is
-		 * our previous maximum.
-		 */
-		if (load * busiest_capacity > busiest_load * capacity) {
-			busiest_load = load;
-			busiest_capacity = capacity;
-			busiest = rq;
 		}
 	}
 
@@ -8728,7 +9044,7 @@ voluntary_active_balance(struct lb_env *env)
 			return 1;
 	}
 
-	if (env->src_grp_type == group_misfit_task)
+	if (env->migration_type == migrate_misfit)
 		return 1;
 
 	return 0;
@@ -9757,6 +10073,11 @@ static inline void nohz_newidle_balance(struct rq *this_rq) { }
 /*
  * idle_balance is called by schedule() if this_cpu is about to become
  * idle. Attempts to pull tasks from other CPUs.
+ *
+ * Returns:
+ *   < 0 - we released the lock and there are !fair tasks present
+ *     0 - failed, no new tasks
+ *   > 0 - success, new (fair) tasks present
  */
 int newidle_balance(struct rq *this_rq, struct rq_flags *rf)
 {
@@ -10151,7 +10472,7 @@ static void switched_to_fair(struct rq *rq, struct task_struct *p)
  * This routine is mostly called to set cfs_rq->curr field when a task
  * migrates between groups/classes.
  */
-static void set_next_task_fair(struct rq *rq, struct task_struct *p)
+static void set_next_task_fair(struct rq *rq, struct task_struct *p, bool first)
 {
 	struct sched_entity *se = &p->se;
 
@@ -10433,7 +10754,7 @@ const struct sched_class fair_sched_class = {
 
 	.check_preempt_curr	= check_preempt_wakeup,
 
-	.pick_next_task		= pick_next_task_fair,
+	.pick_next_task		= __pick_next_task_fair,
 	.put_prev_task		= put_prev_task_fair,
 	.set_next_task          = set_next_task_fair,
 
diff --git a/kernel/sched/features.h b/kernel/sched/features.h
index 2410db5e9a35..7481cd96f391 100644
--- a/kernel/sched/features.h
+++ b/kernel/sched/features.h
@@ -89,3 +89,4 @@ SCHED_FEAT(WA_BIAS, true)
  * UtilEstimation. Use estimated CPU utilization.
  */
 SCHED_FEAT(UTIL_EST, true)
+SCHED_FEAT(UTIL_EST_FASTUP, true)
diff --git a/kernel/sched/idle.c b/kernel/sched/idle.c
index f65ef1e2f204..ffa959e91227 100644
--- a/kernel/sched/idle.c
+++ b/kernel/sched/idle.c
@@ -104,7 +104,7 @@ static int call_cpuidle(struct cpuidle_driver *drv, struct cpuidle_device *dev,
 	 * update no idle residency and return.
 	 */
 	if (current_clr_polling_and_test()) {
-		dev->last_residency = 0;
+		dev->last_residency_ns = 0;
 		local_irq_enable();
 		return -EBUSY;
 	}
@@ -165,7 +165,9 @@ static void cpuidle_idle_call(void)
 	 * until a proper wakeup interrupt happens.
 	 */
 
-	if (idle_should_enter_s2idle() || dev->use_deepest_state) {
+	if (idle_should_enter_s2idle() || dev->forced_idle_latency_limit_ns) {
+		u64 max_latency_ns;
+
 		if (idle_should_enter_s2idle()) {
 			rcu_idle_enter();
 
@@ -176,12 +178,16 @@ static void cpuidle_idle_call(void)
 			}
 
 			rcu_idle_exit();
+
+			max_latency_ns = U64_MAX;
+		} else {
+			max_latency_ns = dev->forced_idle_latency_limit_ns;
 		}
 
 		tick_nohz_idle_stop_tick();
 		rcu_idle_enter();
 
-		next_state = cpuidle_find_deepest_state(drv, dev);
+		next_state = cpuidle_find_deepest_state(drv, dev, max_latency_ns);
 		call_cpuidle(drv, dev, next_state);
 	} else {
 		bool stop_tick = true;
@@ -311,7 +317,7 @@ static enum hrtimer_restart idle_inject_timer_fn(struct hrtimer *timer)
 	return HRTIMER_NORESTART;
 }
 
-void play_idle(unsigned long duration_us)
+void play_idle_precise(u64 duration_ns, u64 latency_ns)
 {
 	struct idle_timer it;
 
@@ -323,29 +329,29 @@ void play_idle(unsigned long duration_us)
 	WARN_ON_ONCE(current->nr_cpus_allowed != 1);
 	WARN_ON_ONCE(!(current->flags & PF_KTHREAD));
 	WARN_ON_ONCE(!(current->flags & PF_NO_SETAFFINITY));
-	WARN_ON_ONCE(!duration_us);
+	WARN_ON_ONCE(!duration_ns);
 
 	rcu_sleep_check();
 	preempt_disable();
 	current->flags |= PF_IDLE;
-	cpuidle_use_deepest_state(true);
+	cpuidle_use_deepest_state(latency_ns);
 
 	it.done = 0;
 	hrtimer_init_on_stack(&it.timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
 	it.timer.function = idle_inject_timer_fn;
-	hrtimer_start(&it.timer, ns_to_ktime(duration_us * NSEC_PER_USEC),
+	hrtimer_start(&it.timer, ns_to_ktime(duration_ns),
 		      HRTIMER_MODE_REL_PINNED);
 
 	while (!READ_ONCE(it.done))
 		do_idle();
 
-	cpuidle_use_deepest_state(false);
+	cpuidle_use_deepest_state(0);
 	current->flags &= ~PF_IDLE;
 
 	preempt_fold_need_resched();
 	preempt_enable();
 }
-EXPORT_SYMBOL_GPL(play_idle);
+EXPORT_SYMBOL_GPL(play_idle_precise);
 
 void cpu_startup_entry(enum cpuhp_state state)
 {
@@ -385,21 +391,17 @@ static void put_prev_task_idle(struct rq *rq, struct task_struct *prev)
 {
 }
 
-static void set_next_task_idle(struct rq *rq, struct task_struct *next)
+static void set_next_task_idle(struct rq *rq, struct task_struct *next, bool first)
 {
 	update_idle_core(rq);
 	schedstat_inc(rq->sched_goidle);
 }
 
-static struct task_struct *
-pick_next_task_idle(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
+struct task_struct *pick_next_task_idle(struct rq *rq)
 {
 	struct task_struct *next = rq->idle;
 
-	if (prev)
-		put_prev_task(rq, prev);
-
-	set_next_task_idle(rq, next);
+	set_next_task_idle(rq, next, true);
 
 	return next;
 }
diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c
index 9b8adc01be3d..e591d40fd645 100644
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -1515,13 +1515,16 @@ static void check_preempt_curr_rt(struct rq *rq, struct task_struct *p, int flag
 #endif
 }
 
-static inline void set_next_task_rt(struct rq *rq, struct task_struct *p)
+static inline void set_next_task_rt(struct rq *rq, struct task_struct *p, bool first)
 {
 	p->se.exec_start = rq_clock_task(rq);
 
 	/* The running task is never eligible for pushing */
 	dequeue_pushable_task(rq, p);
 
+	if (!first)
+		return;
+
 	/*
 	 * If prev task was rt, put_prev_task() has already updated the
 	 * utilization. We only care of the case where we start to schedule a
@@ -1564,18 +1567,15 @@ static struct task_struct *_pick_next_task_rt(struct rq *rq)
 	return rt_task_of(rt_se);
 }
 
-static struct task_struct *
-pick_next_task_rt(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
+static struct task_struct *pick_next_task_rt(struct rq *rq)
 {
 	struct task_struct *p;
 
-	WARN_ON_ONCE(prev || rf);
-
 	if (!sched_rt_runnable(rq))
 		return NULL;
 
 	p = _pick_next_task_rt(rq);
-	set_next_task_rt(rq, p);
+	set_next_task_rt(rq, p, true);
 	return p;
 }
 
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index c8870c5bd7df..280a3c735935 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -1713,22 +1713,10 @@ struct sched_class {
 
 	void (*check_preempt_curr)(struct rq *rq, struct task_struct *p, int flags);
 
-	/*
-	 * Both @prev and @rf are optional and may be NULL, in which case the
-	 * caller must already have invoked put_prev_task(rq, prev, rf).
-	 *
-	 * Otherwise it is the responsibility of the pick_next_task() to call
-	 * put_prev_task() on the @prev task or something equivalent, IFF it
-	 * returns a next task.
-	 *
-	 * In that case (@rf != NULL) it may return RETRY_TASK when it finds a
-	 * higher prio class has runnable tasks.
-	 */
-	struct task_struct * (*pick_next_task)(struct rq *rq,
-					       struct task_struct *prev,
-					       struct rq_flags *rf);
+	struct task_struct *(*pick_next_task)(struct rq *rq);
+
 	void (*put_prev_task)(struct rq *rq, struct task_struct *p);
-	void (*set_next_task)(struct rq *rq, struct task_struct *p);
+	void (*set_next_task)(struct rq *rq, struct task_struct *p, bool first);
 
 #ifdef CONFIG_SMP
 	int (*balance)(struct rq *rq, struct task_struct *prev, struct rq_flags *rf);
@@ -1780,7 +1768,7 @@ static inline void put_prev_task(struct rq *rq, struct task_struct *prev)
 static inline void set_next_task(struct rq *rq, struct task_struct *next)
 {
 	WARN_ON_ONCE(rq->curr != next);
-	next->sched_class->set_next_task(rq, next);
+	next->sched_class->set_next_task(rq, next, false);
 }
 
 #ifdef CONFIG_SMP
@@ -1821,6 +1809,9 @@ static inline bool sched_fair_runnable(struct rq *rq)
 	return rq->cfs.nr_running > 0;
 }
 
+extern struct task_struct *pick_next_task_fair(struct rq *rq, struct task_struct *prev, struct rq_flags *rf);
+extern struct task_struct *pick_next_task_idle(struct rq *rq);
+
 #ifdef CONFIG_SMP
 
 extern void update_group_capacity(struct sched_domain *sd, int cpu);
@@ -2309,7 +2300,7 @@ static inline void cpufreq_update_util(struct rq *rq, unsigned int flags) {}
 #endif /* CONFIG_CPU_FREQ */
 
 #ifdef CONFIG_UCLAMP_TASK
-enum uclamp_id uclamp_eff_value(struct task_struct *p, enum uclamp_id clamp_id);
+unsigned int uclamp_eff_value(struct task_struct *p, enum uclamp_id clamp_id);
 
 static __always_inline
 unsigned int uclamp_util_with(struct rq *rq, unsigned int util,
diff --git a/kernel/sched/stop_task.c b/kernel/sched/stop_task.c
index c0640739e05e..4c9e9975684f 100644
--- a/kernel/sched/stop_task.c
+++ b/kernel/sched/stop_task.c
@@ -29,20 +29,17 @@ check_preempt_curr_stop(struct rq *rq, struct task_struct *p, int flags)
 	/* we're never preempted */
 }
 
-static void set_next_task_stop(struct rq *rq, struct task_struct *stop)
+static void set_next_task_stop(struct rq *rq, struct task_struct *stop, bool first)
 {
 	stop->se.exec_start = rq_clock_task(rq);
 }
 
-static struct task_struct *
-pick_next_task_stop(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
+static struct task_struct *pick_next_task_stop(struct rq *rq)
 {
-	WARN_ON_ONCE(prev || rf);
-
 	if (!sched_stop_runnable(rq))
 		return NULL;
 
-	set_next_task_stop(rq, rq->stop);
+	set_next_task_stop(rq, rq->stop, true);
 	return rq->stop;
 }
 
diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c
index 49b835f1305f..6ec1e595b1d4 100644
--- a/kernel/sched/topology.c
+++ b/kernel/sched/topology.c
@@ -1201,16 +1201,13 @@ static void set_domain_attribute(struct sched_domain *sd,
 	if (!attr || attr->relax_domain_level < 0) {
 		if (default_relax_domain_level < 0)
 			return;
-		else
-			request = default_relax_domain_level;
+		request = default_relax_domain_level;
 	} else
 		request = attr->relax_domain_level;
-	if (request < sd->level) {
+
+	if (sd->level > request) {
 		/* Turn off idle balance on this domain: */
 		sd->flags &= ~(SD_BALANCE_WAKE|SD_BALANCE_NEWIDLE);
-	} else {
-		/* Turn on idle balance on this domain: */
-		sd->flags |= (SD_BALANCE_WAKE|SD_BALANCE_NEWIDLE);
 	}
 }
 
diff --git a/kernel/stacktrace.c b/kernel/stacktrace.c
index c9ea7eb2cb1a..2af66e449aa6 100644
--- a/kernel/stacktrace.c
+++ b/kernel/stacktrace.c
@@ -142,7 +142,7 @@ unsigned int stack_trace_save_tsk(struct task_struct *tsk, unsigned long *store,
 		.store	= store,
 		.size	= size,
 		/* skip this function if they are tracing us */
-		.skip	= skipnr + !!(current == tsk),
+		.skip	= skipnr + (current == tsk),
 	};
 
 	if (!try_get_task_stack(tsk))
@@ -300,7 +300,7 @@ unsigned int stack_trace_save_tsk(struct task_struct *task,
 		.entries	= store,
 		.max_entries	= size,
 		/* skip this function if they are tracing us */
-		.skip	= skipnr + !!(current == task),
+		.skip	= skipnr + (current == task),
 	};
 
 	save_stack_trace_tsk(task, &trace);
diff --git a/kernel/stop_machine.c b/kernel/stop_machine.c
index 998d50ee2d9b..1fe34a9fabc2 100644
--- a/kernel/stop_machine.c
+++ b/kernel/stop_machine.c
@@ -235,6 +235,7 @@ static int multi_cpu_stop(void *data)
 			 */
 			touch_nmi_watchdog();
 		}
+		rcu_momentary_dyntick_idle();
 	} while (curstate != MULTI_STOP_EXIT);
 
 	local_irq_restore(flags);
diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index 955851748dc3..8b192e67aabc 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -172,6 +172,7 @@ static void tick_sched_handle(struct tick_sched *ts, struct pt_regs *regs)
 #ifdef CONFIG_NO_HZ_FULL
 cpumask_var_t tick_nohz_full_mask;
 bool tick_nohz_full_running;
+EXPORT_SYMBOL_GPL(tick_nohz_full_running);
 static atomic_t tick_dep_mask;
 
 static bool check_tick_dependency(atomic_t *dep)
@@ -198,6 +199,11 @@ static bool check_tick_dependency(atomic_t *dep)
 		return true;
 	}
 
+	if (val & TICK_DEP_MASK_RCU) {
+		trace_tick_stop(0, TICK_DEP_MASK_RCU);
+		return true;
+	}
+
 	return false;
 }
 
@@ -324,6 +330,7 @@ void tick_nohz_dep_set_cpu(int cpu, enum tick_dep_bits bit)
 		preempt_enable();
 	}
 }
+EXPORT_SYMBOL_GPL(tick_nohz_dep_set_cpu);
 
 void tick_nohz_dep_clear_cpu(int cpu, enum tick_dep_bits bit)
 {
@@ -331,6 +338,7 @@ void tick_nohz_dep_clear_cpu(int cpu, enum tick_dep_bits bit)
 
 	atomic_andnot(BIT(bit), &ts->tick_dep_mask);
 }
+EXPORT_SYMBOL_GPL(tick_nohz_dep_clear_cpu);
 
 /*
  * Set a per-task tick dependency. Posix CPU timers need this in order to elapse
@@ -344,11 +352,13 @@ void tick_nohz_dep_set_task(struct task_struct *tsk, enum tick_dep_bits bit)
 	 */
 	tick_nohz_dep_set_all(&tsk->tick_dep_mask, bit);
 }
+EXPORT_SYMBOL_GPL(tick_nohz_dep_set_task);
 
 void tick_nohz_dep_clear_task(struct task_struct *tsk, enum tick_dep_bits bit)
 {
 	atomic_andnot(BIT(bit), &tsk->tick_dep_mask);
 }
+EXPORT_SYMBOL_GPL(tick_nohz_dep_clear_task);
 
 /*
  * Set a per-taskgroup tick dependency. Posix CPU timers need this in order to elapse
@@ -397,6 +407,7 @@ void __init tick_nohz_full_setup(cpumask_var_t cpumask)
 	cpumask_copy(tick_nohz_full_mask, cpumask);
 	tick_nohz_full_running = true;
 }
+EXPORT_SYMBOL_GPL(tick_nohz_full_setup);
 
 static int tick_nohz_cpu_down(unsigned int cpu)
 {
@@ -1119,7 +1130,7 @@ static void tick_nohz_account_idle_ticks(struct tick_sched *ts)
 #ifndef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE
 	unsigned long ticks;
 
-	if (vtime_accounting_cpu_enabled())
+	if (vtime_accounting_enabled_this_cpu())
 		return;
 	/*
 	 * We stopped the tick in idle. Update process times would miss the
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index 914b845ad4ff..bc88fd939f4e 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -365,11 +365,6 @@ static void show_pwq(struct pool_workqueue *pwq);
 			 !lockdep_is_held(&wq_pool_mutex),		\
 			 "RCU or wq_pool_mutex should be held")
 
-#define assert_rcu_or_wq_mutex(wq)					\
-	RCU_LOCKDEP_WARN(!rcu_read_lock_held() &&			\
-			 !lockdep_is_held(&wq->mutex),			\
-			 "RCU or wq->mutex should be held")
-
 #define assert_rcu_or_wq_mutex_or_pool_mutex(wq)			\
 	RCU_LOCKDEP_WARN(!rcu_read_lock_held() &&			\
 			 !lockdep_is_held(&wq->mutex) &&		\
@@ -427,9 +422,7 @@ static void show_pwq(struct pool_workqueue *pwq);
  */
 #define for_each_pwq(pwq, wq)						\
 	list_for_each_entry_rcu((pwq), &(wq)->pwqs, pwqs_node,		\
-				lockdep_is_held(&wq->mutex))		\
-		if (({ assert_rcu_or_wq_mutex(wq); false; })) { }	\
-		else
+				 lockdep_is_held(&(wq->mutex)))
 
 #ifdef CONFIG_DEBUG_OBJECTS_WORK
 
diff --git a/lib/Kconfig b/lib/Kconfig
index 3321d04dfa5a..681b7e50490e 100644
--- a/lib/Kconfig
+++ b/lib/Kconfig
@@ -605,6 +605,9 @@ config ARCH_NO_SG_CHAIN
 config ARCH_HAS_PMEM_API
 	bool
 
+config MEMREGION
+	bool
+
 # use memcpy to implement user copies for nommu architectures
 config UACCESS_MEMCPY
 	bool
diff --git a/lib/Makefile b/lib/Makefile
index b7f0ea999d48..c2f0e2a4e4e8 100644
--- a/lib/Makefile
+++ b/lib/Makefile
@@ -214,6 +214,7 @@ obj-$(CONFIG_GENERIC_NET_UTILS) += net_utils.o
 
 obj-$(CONFIG_SG_SPLIT) += sg_split.o
 obj-$(CONFIG_SG_POOL) += sg_pool.o
+obj-$(CONFIG_MEMREGION) += memregion.o
 obj-$(CONFIG_STMP_DEVICE) += stmp_device.o
 obj-$(CONFIG_IRQ_POLL) += irq_poll.o
 
diff --git a/lib/locking-selftest.c b/lib/locking-selftest.c
index a1705545e6ac..14f44f59e733 100644
--- a/lib/locking-selftest.c
+++ b/lib/locking-selftest.c
@@ -1475,7 +1475,7 @@ static void ww_test_edeadlk_normal(void)
 
 	mutex_lock(&o2.base);
 	o2.ctx = &t2;
-	mutex_release(&o2.base.dep_map, 1, _THIS_IP_);
+	mutex_release(&o2.base.dep_map, _THIS_IP_);
 
 	WWAI(&t);
 	t2 = t;
@@ -1500,7 +1500,7 @@ static void ww_test_edeadlk_normal_slow(void)
 	int ret;
 
 	mutex_lock(&o2.base);
-	mutex_release(&o2.base.dep_map, 1, _THIS_IP_);
+	mutex_release(&o2.base.dep_map, _THIS_IP_);
 	o2.ctx = &t2;
 
 	WWAI(&t);
@@ -1527,7 +1527,7 @@ static void ww_test_edeadlk_no_unlock(void)
 
 	mutex_lock(&o2.base);
 	o2.ctx = &t2;
-	mutex_release(&o2.base.dep_map, 1, _THIS_IP_);
+	mutex_release(&o2.base.dep_map, _THIS_IP_);
 
 	WWAI(&t);
 	t2 = t;
@@ -1551,7 +1551,7 @@ static void ww_test_edeadlk_no_unlock_slow(void)
 	int ret;
 
 	mutex_lock(&o2.base);
-	mutex_release(&o2.base.dep_map, 1, _THIS_IP_);
+	mutex_release(&o2.base.dep_map, _THIS_IP_);
 	o2.ctx = &t2;
 
 	WWAI(&t);
@@ -1576,7 +1576,7 @@ static void ww_test_edeadlk_acquire_more(void)
 	int ret;
 
 	mutex_lock(&o2.base);
-	mutex_release(&o2.base.dep_map, 1, _THIS_IP_);
+	mutex_release(&o2.base.dep_map, _THIS_IP_);
 	o2.ctx = &t2;
 
 	WWAI(&t);
@@ -1597,7 +1597,7 @@ static void ww_test_edeadlk_acquire_more_slow(void)
 	int ret;
 
 	mutex_lock(&o2.base);
-	mutex_release(&o2.base.dep_map, 1, _THIS_IP_);
+	mutex_release(&o2.base.dep_map, _THIS_IP_);
 	o2.ctx = &t2;
 
 	WWAI(&t);
@@ -1618,11 +1618,11 @@ static void ww_test_edeadlk_acquire_more_edeadlk(void)
 	int ret;
 
 	mutex_lock(&o2.base);
-	mutex_release(&o2.base.dep_map, 1, _THIS_IP_);
+	mutex_release(&o2.base.dep_map, _THIS_IP_);
 	o2.ctx = &t2;
 
 	mutex_lock(&o3.base);
-	mutex_release(&o3.base.dep_map, 1, _THIS_IP_);
+	mutex_release(&o3.base.dep_map, _THIS_IP_);
 	o3.ctx = &t2;
 
 	WWAI(&t);
@@ -1644,11 +1644,11 @@ static void ww_test_edeadlk_acquire_more_edeadlk_slow(void)
 	int ret;
 
 	mutex_lock(&o2.base);
-	mutex_release(&o2.base.dep_map, 1, _THIS_IP_);
+	mutex_release(&o2.base.dep_map, _THIS_IP_);
 	o2.ctx = &t2;
 
 	mutex_lock(&o3.base);
-	mutex_release(&o3.base.dep_map, 1, _THIS_IP_);
+	mutex_release(&o3.base.dep_map, _THIS_IP_);
 	o3.ctx = &t2;
 
 	WWAI(&t);
@@ -1669,7 +1669,7 @@ static void ww_test_edeadlk_acquire_wrong(void)
 	int ret;
 
 	mutex_lock(&o2.base);
-	mutex_release(&o2.base.dep_map, 1, _THIS_IP_);
+	mutex_release(&o2.base.dep_map, _THIS_IP_);
 	o2.ctx = &t2;
 
 	WWAI(&t);
@@ -1694,7 +1694,7 @@ static void ww_test_edeadlk_acquire_wrong_slow(void)
 	int ret;
 
 	mutex_lock(&o2.base);
-	mutex_release(&o2.base.dep_map, 1, _THIS_IP_);
+	mutex_release(&o2.base.dep_map, _THIS_IP_);
 	o2.ctx = &t2;
 
 	WWAI(&t);
diff --git a/lib/memregion.c b/lib/memregion.c
new file mode 100644
index 000000000000..77c85b5251da
--- /dev/null
+++ b/lib/memregion.c
@@ -0,0 +1,18 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* identifiers for device / performance-differentiated memory regions */
+#include <linux/idr.h>
+#include <linux/types.h>
+
+static DEFINE_IDA(memregion_ids);
+
+int memregion_alloc(gfp_t gfp)
+{
+	return ida_alloc(&memregion_ids, gfp);
+}
+EXPORT_SYMBOL(memregion_alloc);
+
+void memregion_free(int id)
+{
+	ida_free(&memregion_ids, id);
+}
+EXPORT_SYMBOL(memregion_free);
diff --git a/lib/refcount.c b/lib/refcount.c
index 6e904af0fb3e..ebac8b7d15a7 100644
--- a/lib/refcount.c
+++ b/lib/refcount.c
@@ -1,41 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
 /*
- * Variant of atomic_t specialized for reference counts.
- *
- * The interface matches the atomic_t interface (to aid in porting) but only
- * provides the few functions one should use for reference counting.
- *
- * It differs in that the counter saturates at UINT_MAX and will not move once
- * there. This avoids wrapping the counter and causing 'spurious'
- * use-after-free issues.
- *
- * Memory ordering rules are slightly relaxed wrt regular atomic_t functions
- * and provide only what is strictly required for refcounts.
- *
- * The increments are fully relaxed; these will not provide ordering. The
- * rationale is that whatever is used to obtain the object we're increasing the
- * reference count on will provide the ordering. For locked data structures,
- * its the lock acquire, for RCU/lockless data structures its the dependent
- * load.
- *
- * Do note that inc_not_zero() provides a control dependency which will order
- * future stores against the inc, this ensures we'll never modify the object
- * if we did not in fact acquire a reference.
- *
- * The decrements will provide release order, such that all the prior loads and
- * stores will be issued before, it also provides a control dependency, which
- * will order us against the subsequent free().
- *
- * The control dependency is against the load of the cmpxchg (ll/sc) that
- * succeeded. This means the stores aren't fully ordered, but this is fine
- * because the 1->0 transition indicates no concurrency.
- *
- * Note that the allocator is responsible for ordering things between free()
- * and alloc().
- *
- * The decrements dec_and_test() and sub_and_test() also provide acquire
- * ordering on success.
- *
+ * Out-of-line refcount functions.
  */
 
 #include <linux/mutex.h>
@@ -43,199 +8,33 @@
 #include <linux/spinlock.h>
 #include <linux/bug.h>
 
-/**
- * refcount_add_not_zero_checked - add a value to a refcount unless it is 0
- * @i: the value to add to the refcount
- * @r: the refcount
- *
- * Will saturate at UINT_MAX and WARN.
- *
- * Provides no memory ordering, it is assumed the caller has guaranteed the
- * object memory to be stable (RCU, etc.). It does provide a control dependency
- * and thereby orders future stores. See the comment on top.
- *
- * Use of this function is not recommended for the normal reference counting
- * use case in which references are taken and released one at a time.  In these
- * cases, refcount_inc(), or one of its variants, should instead be used to
- * increment a reference count.
- *
- * Return: false if the passed refcount is 0, true otherwise
- */
-bool refcount_add_not_zero_checked(unsigned int i, refcount_t *r)
-{
-	unsigned int new, val = atomic_read(&r->refs);
-
-	do {
-		if (!val)
-			return false;
-
-		if (unlikely(val == UINT_MAX))
-			return true;
-
-		new = val + i;
-		if (new < val)
-			new = UINT_MAX;
-
-	} while (!atomic_try_cmpxchg_relaxed(&r->refs, &val, new));
-
-	WARN_ONCE(new == UINT_MAX, "refcount_t: saturated; leaking memory.\n");
-
-	return true;
-}
-EXPORT_SYMBOL(refcount_add_not_zero_checked);
-
-/**
- * refcount_add_checked - add a value to a refcount
- * @i: the value to add to the refcount
- * @r: the refcount
- *
- * Similar to atomic_add(), but will saturate at UINT_MAX and WARN.
- *
- * Provides no memory ordering, it is assumed the caller has guaranteed the
- * object memory to be stable (RCU, etc.). It does provide a control dependency
- * and thereby orders future stores. See the comment on top.
- *
- * Use of this function is not recommended for the normal reference counting
- * use case in which references are taken and released one at a time.  In these
- * cases, refcount_inc(), or one of its variants, should instead be used to
- * increment a reference count.
- */
-void refcount_add_checked(unsigned int i, refcount_t *r)
-{
-	WARN_ONCE(!refcount_add_not_zero_checked(i, r), "refcount_t: addition on 0; use-after-free.\n");
-}
-EXPORT_SYMBOL(refcount_add_checked);
-
-/**
- * refcount_inc_not_zero_checked - increment a refcount unless it is 0
- * @r: the refcount to increment
- *
- * Similar to atomic_inc_not_zero(), but will saturate at UINT_MAX and WARN.
- *
- * Provides no memory ordering, it is assumed the caller has guaranteed the
- * object memory to be stable (RCU, etc.). It does provide a control dependency
- * and thereby orders future stores. See the comment on top.
- *
- * Return: true if the increment was successful, false otherwise
- */
-bool refcount_inc_not_zero_checked(refcount_t *r)
-{
-	unsigned int new, val = atomic_read(&r->refs);
-
-	do {
-		new = val + 1;
-
-		if (!val)
-			return false;
-
-		if (unlikely(!new))
-			return true;
-
-	} while (!atomic_try_cmpxchg_relaxed(&r->refs, &val, new));
+#define REFCOUNT_WARN(str)	WARN_ONCE(1, "refcount_t: " str ".\n")
 
-	WARN_ONCE(new == UINT_MAX, "refcount_t: saturated; leaking memory.\n");
-
-	return true;
-}
-EXPORT_SYMBOL(refcount_inc_not_zero_checked);
-
-/**
- * refcount_inc_checked - increment a refcount
- * @r: the refcount to increment
- *
- * Similar to atomic_inc(), but will saturate at UINT_MAX and WARN.
- *
- * Provides no memory ordering, it is assumed the caller already has a
- * reference on the object.
- *
- * Will WARN if the refcount is 0, as this represents a possible use-after-free
- * condition.
- */
-void refcount_inc_checked(refcount_t *r)
+void refcount_warn_saturate(refcount_t *r, enum refcount_saturation_type t)
 {
-	WARN_ONCE(!refcount_inc_not_zero_checked(r), "refcount_t: increment on 0; use-after-free.\n");
-}
-EXPORT_SYMBOL(refcount_inc_checked);
-
-/**
- * refcount_sub_and_test_checked - subtract from a refcount and test if it is 0
- * @i: amount to subtract from the refcount
- * @r: the refcount
- *
- * Similar to atomic_dec_and_test(), but it will WARN, return false and
- * ultimately leak on underflow and will fail to decrement when saturated
- * at UINT_MAX.
- *
- * Provides release memory ordering, such that prior loads and stores are done
- * before, and provides an acquire ordering on success such that free()
- * must come after.
- *
- * Use of this function is not recommended for the normal reference counting
- * use case in which references are taken and released one at a time.  In these
- * cases, refcount_dec(), or one of its variants, should instead be used to
- * decrement a reference count.
- *
- * Return: true if the resulting refcount is 0, false otherwise
- */
-bool refcount_sub_and_test_checked(unsigned int i, refcount_t *r)
-{
-	unsigned int new, val = atomic_read(&r->refs);
-
-	do {
-		if (unlikely(val == UINT_MAX))
-			return false;
-
-		new = val - i;
-		if (new > val) {
-			WARN_ONCE(new > val, "refcount_t: underflow; use-after-free.\n");
-			return false;
-		}
-
-	} while (!atomic_try_cmpxchg_release(&r->refs, &val, new));
-
-	if (!new) {
-		smp_acquire__after_ctrl_dep();
-		return true;
+	refcount_set(r, REFCOUNT_SATURATED);
+
+	switch (t) {
+	case REFCOUNT_ADD_NOT_ZERO_OVF:
+		REFCOUNT_WARN("saturated; leaking memory");
+		break;
+	case REFCOUNT_ADD_OVF:
+		REFCOUNT_WARN("saturated; leaking memory");
+		break;
+	case REFCOUNT_ADD_UAF:
+		REFCOUNT_WARN("addition on 0; use-after-free");
+		break;
+	case REFCOUNT_SUB_UAF:
+		REFCOUNT_WARN("underflow; use-after-free");
+		break;
+	case REFCOUNT_DEC_LEAK:
+		REFCOUNT_WARN("decrement hit 0; leaking memory");
+		break;
+	default:
+		REFCOUNT_WARN("unknown saturation event!?");
 	}
-	return false;
-
-}
-EXPORT_SYMBOL(refcount_sub_and_test_checked);
-
-/**
- * refcount_dec_and_test_checked - decrement a refcount and test if it is 0
- * @r: the refcount
- *
- * Similar to atomic_dec_and_test(), it will WARN on underflow and fail to
- * decrement when saturated at UINT_MAX.
- *
- * Provides release memory ordering, such that prior loads and stores are done
- * before, and provides an acquire ordering on success such that free()
- * must come after.
- *
- * Return: true if the resulting refcount is 0, false otherwise
- */
-bool refcount_dec_and_test_checked(refcount_t *r)
-{
-	return refcount_sub_and_test_checked(1, r);
-}
-EXPORT_SYMBOL(refcount_dec_and_test_checked);
-
-/**
- * refcount_dec_checked - decrement a refcount
- * @r: the refcount
- *
- * Similar to atomic_dec(), it will WARN on underflow and fail to decrement
- * when saturated at UINT_MAX.
- *
- * Provides release memory ordering, such that prior loads and stores are done
- * before.
- */
-void refcount_dec_checked(refcount_t *r)
-{
-	WARN_ONCE(refcount_dec_and_test_checked(r), "refcount_t: decrement hit 0; leaking memory.\n");
 }
-EXPORT_SYMBOL(refcount_dec_checked);
+EXPORT_SYMBOL(refcount_warn_saturate);
 
 /**
  * refcount_dec_if_one - decrement a refcount if it is 1
@@ -277,7 +76,7 @@ bool refcount_dec_not_one(refcount_t *r)
 	unsigned int new, val = atomic_read(&r->refs);
 
 	do {
-		if (unlikely(val == UINT_MAX))
+		if (unlikely(val == REFCOUNT_SATURATED))
 			return true;
 
 		if (val == 1)
@@ -302,7 +101,7 @@ EXPORT_SYMBOL(refcount_dec_not_one);
  * @lock: the mutex to be locked
  *
  * Similar to atomic_dec_and_mutex_lock(), it will WARN on underflow and fail
- * to decrement when saturated at UINT_MAX.
+ * to decrement when saturated at REFCOUNT_SATURATED.
  *
  * Provides release memory ordering, such that prior loads and stores are done
  * before, and provides a control dependency such that free() must come after.
@@ -333,7 +132,7 @@ EXPORT_SYMBOL(refcount_dec_and_mutex_lock);
  * @lock: the spinlock to be locked
  *
  * Similar to atomic_dec_and_lock(), it will WARN on underflow and fail to
- * decrement when saturated at UINT_MAX.
+ * decrement when saturated at REFCOUNT_SATURATED.
  *
  * Provides release memory ordering, such that prior loads and stores are done
  * before, and provides a control dependency such that free() must come after.
diff --git a/lib/smp_processor_id.c b/lib/smp_processor_id.c
index 60ba93fc42ce..bd9571653288 100644
--- a/lib/smp_processor_id.c
+++ b/lib/smp_processor_id.c
@@ -23,7 +23,7 @@ unsigned int check_preemption_disabled(const char *what1, const char *what2)
 	 * Kernel threads bound to a single CPU can safely use
 	 * smp_processor_id():
 	 */
-	if (cpumask_equal(current->cpus_ptr, cpumask_of(this_cpu)))
+	if (current->nr_cpus_allowed == 1)
 		goto out;
 
 	/*
diff --git a/lib/test_printf.c b/lib/test_printf.c
index 030daeb4fe21..2d9f520d2f27 100644
--- a/lib/test_printf.c
+++ b/lib/test_printf.c
@@ -22,6 +22,8 @@
 #include <linux/gfp.h>
 #include <linux/mm.h>
 
+#include <linux/property.h>
+
 #include "../tools/testing/selftests/kselftest_module.h"
 
 #define BUF_SIZE 256
@@ -593,6 +595,35 @@ flags(void)
 	kfree(cmp_buffer);
 }
 
+static void __init fwnode_pointer(void)
+{
+	const struct software_node softnodes[] = {
+		{ .name = "first", },
+		{ .name = "second", .parent = &softnodes[0], },
+		{ .name = "third", .parent = &softnodes[1], },
+		{ NULL /* Guardian */ }
+	};
+	const char * const full_name = "first/second/third";
+	const char * const full_name_second = "first/second";
+	const char * const second_name = "second";
+	const char * const third_name = "third";
+	int rval;
+
+	rval = software_node_register_nodes(softnodes);
+	if (rval) {
+		pr_warn("cannot register softnodes; rval %d\n", rval);
+		return;
+	}
+
+	test(full_name_second, "%pfw", software_node_fwnode(&softnodes[1]));
+	test(full_name, "%pfw", software_node_fwnode(&softnodes[2]));
+	test(full_name, "%pfwf", software_node_fwnode(&softnodes[2]));
+	test(second_name, "%pfwP", software_node_fwnode(&softnodes[1]));
+	test(third_name, "%pfwP", software_node_fwnode(&softnodes[2]));
+
+	software_node_unregister_nodes(softnodes);
+}
+
 static void __init
 errptr(void)
 {
@@ -636,6 +667,7 @@ test_pointer(void)
 	netdev_features();
 	flags();
 	errptr();
+	fwnode_pointer();
 }
 
 static void __init selftest(void)
diff --git a/lib/ubsan.c b/lib/ubsan.c
index b652cc14dd60..fc552d524ef7 100644
--- a/lib/ubsan.c
+++ b/lib/ubsan.c
@@ -374,9 +374,10 @@ void __ubsan_handle_shift_out_of_bounds(struct shift_out_of_bounds_data *data,
 	struct type_descriptor *lhs_type = data->lhs_type;
 	char rhs_str[VALUE_LENGTH];
 	char lhs_str[VALUE_LENGTH];
+	unsigned long ua_flags = user_access_save();
 
 	if (suppress_report(&data->location))
-		return;
+		goto out;
 
 	ubsan_prologue(&data->location, &flags);
 
@@ -402,6 +403,8 @@ void __ubsan_handle_shift_out_of_bounds(struct shift_out_of_bounds_data *data,
 			lhs_type->type_name);
 
 	ubsan_epilogue(&flags);
+out:
+	user_access_restore(ua_flags);
 }
 EXPORT_SYMBOL(__ubsan_handle_shift_out_of_bounds);
 
diff --git a/lib/vsprintf.c b/lib/vsprintf.c
index b54d252b398e..dee8fc467fcf 100644
--- a/lib/vsprintf.c
+++ b/lib/vsprintf.c
@@ -39,6 +39,7 @@
 #include <net/addrconf.h>
 #include <linux/siphash.h>
 #include <linux/compiler.h>
+#include <linux/property.h>
 #ifdef CONFIG_BLOCK
 #include <linux/blkdev.h>
 #endif
@@ -938,7 +939,7 @@ char *symbol_string(char *buf, char *end, void *ptr,
 #ifdef CONFIG_KALLSYMS
 	if (*fmt == 'B')
 		sprint_backtrace(sym, value);
-	else if (*fmt != 'f' && *fmt != 's')
+	else if (*fmt != 's')
 		sprint_symbol(sym, value);
 	else
 		sprint_symbol_no_offset(sym, value);
@@ -1892,32 +1893,25 @@ char *flags_string(char *buf, char *end, void *flags_ptr,
 	return format_flags(buf, end, flags, names);
 }
 
-static const char *device_node_name_for_depth(const struct device_node *np, int depth)
-{
-	for ( ; np && depth; depth--)
-		np = np->parent;
-
-	return kbasename(np->full_name);
-}
-
 static noinline_for_stack
-char *device_node_gen_full_name(const struct device_node *np, char *buf, char *end)
+char *fwnode_full_name_string(struct fwnode_handle *fwnode, char *buf,
+			      char *end)
 {
 	int depth;
-	const struct device_node *parent = np->parent;
-
-	/* special case for root node */
-	if (!parent)
-		return string_nocheck(buf, end, "/", default_str_spec);
 
-	for (depth = 0; parent->parent; depth++)
-		parent = parent->parent;
+	/* Loop starting from the root node to the current node. */
+	for (depth = fwnode_count_parents(fwnode); depth >= 0; depth--) {
+		struct fwnode_handle *__fwnode =
+			fwnode_get_nth_parent(fwnode, depth);
 
-	for ( ; depth >= 0; depth--) {
-		buf = string_nocheck(buf, end, "/", default_str_spec);
-		buf = string(buf, end, device_node_name_for_depth(np, depth),
+		buf = string(buf, end, fwnode_get_name_prefix(__fwnode),
 			     default_str_spec);
+		buf = string(buf, end, fwnode_get_name(__fwnode),
+			     default_str_spec);
+
+		fwnode_handle_put(__fwnode);
 	}
+
 	return buf;
 }
 
@@ -1941,6 +1935,9 @@ char *device_node_string(char *buf, char *end, struct device_node *dn,
 	struct printf_spec str_spec = spec;
 	str_spec.field_width = -1;
 
+	if (fmt[0] != 'F')
+		return error_string(buf, end, "(%pO?)", spec);
+
 	if (!IS_ENABLED(CONFIG_OF))
 		return error_string(buf, end, "(%pOF?)", spec);
 
@@ -1962,10 +1959,11 @@ char *device_node_string(char *buf, char *end, struct device_node *dn,
 
 		switch (*fmt) {
 		case 'f':	/* full_name */
-			buf = device_node_gen_full_name(dn, buf, end);
+			buf = fwnode_full_name_string(of_fwnode_handle(dn), buf,
+						      end);
 			break;
 		case 'n':	/* name */
-			p = kbasename(of_node_full_name(dn));
+			p = fwnode_get_name(of_fwnode_handle(dn));
 			precision = str_spec.precision;
 			str_spec.precision = strchrnul(p, '@') - p;
 			buf = string(buf, end, p, str_spec);
@@ -1975,7 +1973,7 @@ char *device_node_string(char *buf, char *end, struct device_node *dn,
 			buf = number(buf, end, (unsigned int)dn->phandle, num_spec);
 			break;
 		case 'P':	/* path-spec */
-			p = kbasename(of_node_full_name(dn));
+			p = fwnode_get_name(of_fwnode_handle(dn));
 			if (!p[1])
 				p = "/";
 			buf = string(buf, end, p, str_spec);
@@ -2013,15 +2011,34 @@ char *device_node_string(char *buf, char *end, struct device_node *dn,
 	return widen_string(buf, buf - buf_start, end, spec);
 }
 
-static char *kobject_string(char *buf, char *end, void *ptr,
-			    struct printf_spec spec, const char *fmt)
+static noinline_for_stack
+char *fwnode_string(char *buf, char *end, struct fwnode_handle *fwnode,
+		    struct printf_spec spec, const char *fmt)
 {
-	switch (fmt[1]) {
-	case 'F':
-		return device_node_string(buf, end, ptr, spec, fmt + 1);
+	struct printf_spec str_spec = spec;
+	char *buf_start = buf;
+
+	str_spec.field_width = -1;
+
+	if (*fmt != 'w')
+		return error_string(buf, end, "(%pf?)", spec);
+
+	if (check_pointer(&buf, end, fwnode, spec))
+		return buf;
+
+	fmt++;
+
+	switch (*fmt) {
+	case 'P':	/* name */
+		buf = string(buf, end, fwnode_get_name(fwnode), str_spec);
+		break;
+	case 'f':	/* full_name */
+	default:
+		buf = fwnode_full_name_string(fwnode, buf, end);
+		break;
 	}
 
-	return error_string(buf, end, "(%pO?)", spec);
+	return widen_string(buf, buf - buf_start, end, spec);
 }
 
 /*
@@ -2036,9 +2053,9 @@ static char *kobject_string(char *buf, char *end, void *ptr,
  *
  * - 'S' For symbolic direct pointers (or function descriptors) with offset
  * - 's' For symbolic direct pointers (or function descriptors) without offset
- * - 'F' Same as 'S'
- * - 'f' Same as 's'
- * - '[FfSs]R' as above with __builtin_extract_return_addr() translation
+ * - '[Ss]R' as above with __builtin_extract_return_addr() translation
+ * - '[Ff]' %pf and %pF were obsoleted and later removed in favor of
+ *	    %ps and %pS. Be careful when re-using these specifiers.
  * - 'B' For backtraced symbolic direct pointers with offset
  * - 'R' For decoded struct resource, e.g., [mem 0x0-0x1f 64bit pref]
  * - 'r' For raw struct resource, e.g., [mem 0x0-0x1f flags 0x201]
@@ -2128,6 +2145,10 @@ static char *kobject_string(char *buf, char *end, void *ptr,
  *                  F device node flags
  *                  c major compatible string
  *                  C full compatible string
+ * - 'fw[fP]'	For a firmware node (struct fwnode_handle) pointer
+ *		Without an option prints the full name of the node
+ *		f full name
+ *		P node name, including a possible unit address
  * - 'x' For printing the address. Equivalent to "%lx".
  *
  * ** When making changes please also update:
@@ -2141,8 +2162,6 @@ char *pointer(const char *fmt, char *buf, char *end, void *ptr,
 	      struct printf_spec spec)
 {
 	switch (*fmt) {
-	case 'F':
-	case 'f':
 	case 'S':
 	case 's':
 		ptr = dereference_symbol_descriptor(ptr);
@@ -2204,7 +2223,9 @@ char *pointer(const char *fmt, char *buf, char *end, void *ptr,
 	case 'G':
 		return flags_string(buf, end, ptr, spec, fmt);
 	case 'O':
-		return kobject_string(buf, end, ptr, spec, fmt);
+		return device_node_string(buf, end, ptr, spec, fmt + 1);
+	case 'f':
+		return fwnode_string(buf, end, ptr, spec, fmt + 1);
 	case 'x':
 		return pointer_string(buf, end, ptr, spec);
 	case 'e':
@@ -2844,8 +2865,6 @@ int vbin_printf(u32 *bin_buf, size_t size, const char *fmt, va_list args)
 			/* Dereference of functions is still OK */
 			case 'S':
 			case 's':
-			case 'F':
-			case 'f':
 			case 'x':
 			case 'K':
 			case 'e':
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 46ad252e6d6a..01f3f8b665e9 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -1800,7 +1800,7 @@ static void mem_cgroup_oom_unlock(struct mem_cgroup *memcg)
 	struct mem_cgroup *iter;
 
 	spin_lock(&memcg_oom_lock);
-	mutex_release(&memcg_oom_lock_dep_map, 1, _RET_IP_);
+	mutex_release(&memcg_oom_lock_dep_map, _RET_IP_);
 	for_each_mem_cgroup_tree(iter, memcg)
 		iter->oom_lock = false;
 	spin_unlock(&memcg_oom_lock);
diff --git a/net/core/dev.c b/net/core/dev.c
index c7fc902ccbdc..46580b290450 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -1314,8 +1314,8 @@ int dev_set_alias(struct net_device *dev, const char *alias, size_t len)
 	}
 
 	mutex_lock(&ifalias_mutex);
-	rcu_swap_protected(dev->ifalias, new_alias,
-			   mutex_is_locked(&ifalias_mutex));
+	new_alias = rcu_replace_pointer(dev->ifalias, new_alias,
+					mutex_is_locked(&ifalias_mutex));
 	mutex_unlock(&ifalias_mutex);
 
 	if (new_alias)
diff --git a/net/core/sock.c b/net/core/sock.c
index 71787f7c4f8c..043db3ce023e 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -518,7 +518,7 @@ int __sk_receive_skb(struct sock *sk, struct sk_buff *skb,
 
 		rc = sk_backlog_rcv(sk, skb);
 
-		mutex_release(&sk->sk_lock.dep_map, 1, _RET_IP_);
+		mutex_release(&sk->sk_lock.dep_map, _RET_IP_);
 	} else if (sk_add_backlog(sk, skb, READ_ONCE(sk->sk_rcvbuf))) {
 		bh_unlock_sock(sk);
 		atomic_inc(&sk->sk_drops);
diff --git a/net/core/sock_reuseport.c b/net/core/sock_reuseport.c
index f3ceec93f392..f19f179538b9 100644
--- a/net/core/sock_reuseport.c
+++ b/net/core/sock_reuseport.c
@@ -356,8 +356,8 @@ int reuseport_detach_prog(struct sock *sk)
 	spin_lock_bh(&reuseport_lock);
 	reuse = rcu_dereference_protected(sk->sk_reuseport_cb,
 					  lockdep_is_held(&reuseport_lock));
-	rcu_swap_protected(reuse->prog, old_prog,
-			   lockdep_is_held(&reuseport_lock));
+	old_prog = rcu_replace_pointer(reuse->prog, old_prog,
+				       lockdep_is_held(&reuseport_lock));
 	spin_unlock_bh(&reuseport_lock);
 
 	if (!old_prog)
diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index ff04cdc87f76..062b73a83af0 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -1557,8 +1557,9 @@ static void nft_chain_stats_replace(struct nft_trans *trans)
 	if (!nft_trans_chain_stats(trans))
 		return;
 
-	rcu_swap_protected(chain->stats, nft_trans_chain_stats(trans),
-			   lockdep_commit_lock_is_held(trans->ctx.net));
+	nft_trans_chain_stats(trans) =
+		rcu_replace_pointer(chain->stats, nft_trans_chain_stats(trans),
+				    lockdep_commit_lock_is_held(trans->ctx.net));
 
 	if (!nft_trans_chain_stats(trans))
 		static_branch_inc(&nft_counters_enabled);
diff --git a/net/sched/act_api.c b/net/sched/act_api.c
index 7fc1e2c1b656..90a31b15585f 100644
--- a/net/sched/act_api.c
+++ b/net/sched/act_api.c
@@ -88,7 +88,7 @@ struct tcf_chain *tcf_action_set_ctrlact(struct tc_action *a, int action,
 					 struct tcf_chain *goto_chain)
 {
 	a->tcfa_action = action;
-	rcu_swap_protected(a->goto_chain, goto_chain, 1);
+	goto_chain = rcu_replace_pointer(a->goto_chain, goto_chain, 1);
 	return goto_chain;
 }
 EXPORT_SYMBOL(tcf_action_set_ctrlact);
diff --git a/net/sched/act_csum.c b/net/sched/act_csum.c
index 16e67e1c1db1..cb8608f0a77a 100644
--- a/net/sched/act_csum.c
+++ b/net/sched/act_csum.c
@@ -101,8 +101,8 @@ static int tcf_csum_init(struct net *net, struct nlattr *nla,
 
 	spin_lock_bh(&p->tcf_lock);
 	goto_ch = tcf_action_set_ctrlact(*a, parm->action, goto_ch);
-	rcu_swap_protected(p->params, params_new,
-			   lockdep_is_held(&p->tcf_lock));
+	params_new = rcu_replace_pointer(p->params, params_new,
+					 lockdep_is_held(&p->tcf_lock));
 	spin_unlock_bh(&p->tcf_lock);
 
 	if (goto_ch)
diff --git a/net/sched/act_ct.c b/net/sched/act_ct.c
index c13638aeef46..ae0de372b1c8 100644
--- a/net/sched/act_ct.c
+++ b/net/sched/act_ct.c
@@ -721,7 +721,8 @@ static int tcf_ct_init(struct net *net, struct nlattr *nla,
 
 	spin_lock_bh(&c->tcf_lock);
 	goto_ch = tcf_action_set_ctrlact(*a, parm->action, goto_ch);
-	rcu_swap_protected(c->params, params, lockdep_is_held(&c->tcf_lock));
+	params = rcu_replace_pointer(c->params, params,
+				     lockdep_is_held(&c->tcf_lock));
 	spin_unlock_bh(&c->tcf_lock);
 
 	if (goto_ch)
diff --git a/net/sched/act_ctinfo.c b/net/sched/act_ctinfo.c
index b1e601007242..40038c321b4a 100644
--- a/net/sched/act_ctinfo.c
+++ b/net/sched/act_ctinfo.c
@@ -257,8 +257,8 @@ static int tcf_ctinfo_init(struct net *net, struct nlattr *nla,
 
 	spin_lock_bh(&ci->tcf_lock);
 	goto_ch = tcf_action_set_ctrlact(*a, actparm->action, goto_ch);
-	rcu_swap_protected(ci->params, cp_new,
-			   lockdep_is_held(&ci->tcf_lock));
+	cp_new = rcu_replace_pointer(ci->params, cp_new,
+				     lockdep_is_held(&ci->tcf_lock));
 	spin_unlock_bh(&ci->tcf_lock);
 
 	if (goto_ch)
diff --git a/net/sched/act_ife.c b/net/sched/act_ife.c
index d562c88cccbe..5e6379028fc3 100644
--- a/net/sched/act_ife.c
+++ b/net/sched/act_ife.c
@@ -595,7 +595,7 @@ static int tcf_ife_init(struct net *net, struct nlattr *nla,
 		spin_lock_bh(&ife->tcf_lock);
 	/* protected by tcf_lock when modifying existing action */
 	goto_ch = tcf_action_set_ctrlact(*a, parm->action, goto_ch);
-	rcu_swap_protected(ife->params, p, 1);
+	p = rcu_replace_pointer(ife->params, p, 1);
 
 	if (exists)
 		spin_unlock_bh(&ife->tcf_lock);
diff --git a/net/sched/act_mirred.c b/net/sched/act_mirred.c
index b6e1b5bbb4da..1e3eb3a97532 100644
--- a/net/sched/act_mirred.c
+++ b/net/sched/act_mirred.c
@@ -178,8 +178,8 @@ static int tcf_mirred_init(struct net *net, struct nlattr *nla,
 			goto put_chain;
 		}
 		mac_header_xmit = dev_is_mac_header_xmit(dev);
-		rcu_swap_protected(m->tcfm_dev, dev,
-				   lockdep_is_held(&m->tcf_lock));
+		dev = rcu_replace_pointer(m->tcfm_dev, dev,
+					  lockdep_is_held(&m->tcf_lock));
 		if (dev)
 			dev_put(dev);
 		m->tcfm_mac_header_xmit = mac_header_xmit;
diff --git a/net/sched/act_mpls.c b/net/sched/act_mpls.c
index c7d5e12ee919..325eddcc6621 100644
--- a/net/sched/act_mpls.c
+++ b/net/sched/act_mpls.c
@@ -262,7 +262,7 @@ static int tcf_mpls_init(struct net *net, struct nlattr *nla,
 
 	spin_lock_bh(&m->tcf_lock);
 	goto_ch = tcf_action_set_ctrlact(*a, parm->action, goto_ch);
-	rcu_swap_protected(m->mpls_p, p, lockdep_is_held(&m->tcf_lock));
+	p = rcu_replace_pointer(m->mpls_p, p, lockdep_is_held(&m->tcf_lock));
 	spin_unlock_bh(&m->tcf_lock);
 
 	if (goto_ch)
diff --git a/net/sched/act_police.c b/net/sched/act_police.c
index d96271590268..8b7a0ac96c51 100644
--- a/net/sched/act_police.c
+++ b/net/sched/act_police.c
@@ -191,9 +191,9 @@ static int tcf_police_init(struct net *net, struct nlattr *nla,
 		police->tcfp_ptoks = new->tcfp_mtu_ptoks;
 	spin_unlock_bh(&police->tcfp_lock);
 	goto_ch = tcf_action_set_ctrlact(*a, parm->action, goto_ch);
-	rcu_swap_protected(police->params,
-			   new,
-			   lockdep_is_held(&police->tcf_lock));
+	new = rcu_replace_pointer(police->params,
+				  new,
+				  lockdep_is_held(&police->tcf_lock));
 	spin_unlock_bh(&police->tcf_lock);
 
 	if (goto_ch)
diff --git a/net/sched/act_sample.c b/net/sched/act_sample.c
index 29b23bfaf10d..ce948c1e24dc 100644
--- a/net/sched/act_sample.c
+++ b/net/sched/act_sample.c
@@ -102,8 +102,8 @@ static int tcf_sample_init(struct net *net, struct nlattr *nla,
 	goto_ch = tcf_action_set_ctrlact(*a, parm->action, goto_ch);
 	s->rate = rate;
 	s->psample_group_num = psample_group_num;
-	rcu_swap_protected(s->psample_group, psample_group,
-			   lockdep_is_held(&s->tcf_lock));
+	psample_group = rcu_replace_pointer(s->psample_group, psample_group,
+					    lockdep_is_held(&s->tcf_lock));
 
 	if (tb[TCA_SAMPLE_TRUNC_SIZE]) {
 		s->truncate = true;
diff --git a/net/sched/act_skbedit.c b/net/sched/act_skbedit.c
index 5f7ca7f89ca2..e857424c387c 100644
--- a/net/sched/act_skbedit.c
+++ b/net/sched/act_skbedit.c
@@ -206,8 +206,8 @@ static int tcf_skbedit_init(struct net *net, struct nlattr *nla,
 
 	spin_lock_bh(&d->tcf_lock);
 	goto_ch = tcf_action_set_ctrlact(*a, parm->action, goto_ch);
-	rcu_swap_protected(d->params, params_new,
-			   lockdep_is_held(&d->tcf_lock));
+	params_new = rcu_replace_pointer(d->params, params_new,
+					 lockdep_is_held(&d->tcf_lock));
 	spin_unlock_bh(&d->tcf_lock);
 	if (params_new)
 		kfree_rcu(params_new, rcu);
diff --git a/net/sched/act_tunnel_key.c b/net/sched/act_tunnel_key.c
index 6379f9568ab8..536c4bc31be6 100644
--- a/net/sched/act_tunnel_key.c
+++ b/net/sched/act_tunnel_key.c
@@ -529,8 +529,8 @@ static int tunnel_key_init(struct net *net, struct nlattr *nla,
 
 	spin_lock_bh(&t->tcf_lock);
 	goto_ch = tcf_action_set_ctrlact(*a, parm->action, goto_ch);
-	rcu_swap_protected(t->params, params_new,
-			   lockdep_is_held(&t->tcf_lock));
+	params_new = rcu_replace_pointer(t->params, params_new,
+					 lockdep_is_held(&t->tcf_lock));
 	spin_unlock_bh(&t->tcf_lock);
 	tunnel_key_release_params(params_new);
 	if (goto_ch)
diff --git a/net/sched/act_vlan.c b/net/sched/act_vlan.c
index b6939abc61eb..c91d3958fcbb 100644
--- a/net/sched/act_vlan.c
+++ b/net/sched/act_vlan.c
@@ -221,7 +221,7 @@ static int tcf_vlan_init(struct net *net, struct nlattr *nla,
 
 	spin_lock_bh(&v->tcf_lock);
 	goto_ch = tcf_action_set_ctrlact(*a, parm->action, goto_ch);
-	rcu_swap_protected(v->vlan_p, p, lockdep_is_held(&v->tcf_lock));
+	p = rcu_replace_pointer(v->vlan_p, p, lockdep_is_held(&v->tcf_lock));
 	spin_unlock_bh(&v->tcf_lock);
 
 	if (goto_ch)
diff --git a/scripts/checkpatch.pl b/scripts/checkpatch.pl
index 4b40445938dc..64890be3c8fd 100755
--- a/scripts/checkpatch.pl
+++ b/scripts/checkpatch.pl
@@ -6015,14 +6015,18 @@ sub process {
 		        for (my $count = $linenr; $count <= $lc; $count++) {
 				my $specifier;
 				my $extension;
+				my $qualifier;
 				my $bad_specifier = "";
 				my $fmt = get_quoted_string($lines[$count - 1], raw_line($count, 0));
 				$fmt =~ s/%%//g;
 
-				while ($fmt =~ /(\%[\*\d\.]*p(\w))/g) {
+				while ($fmt =~ /(\%[\*\d\.]*p(\w)(\w*))/g) {
 					$specifier = $1;
 					$extension = $2;
-					if ($extension !~ /[SsBKRraEehMmIiUDdgVCbGNOxt]/) {
+					$qualifier = $3;
+					if ($extension !~ /[SsBKRraEehMmIiUDdgVCbGNOxtf]/ ||
+					    ($extension eq "f" &&
+					     defined $qualifier && $qualifier !~ /^w/)) {
 						$bad_specifier = $specifier;
 						last;
 					}
@@ -6039,7 +6043,6 @@ sub process {
 					my $ext_type = "Invalid";
 					my $use = "";
 					if ($bad_specifier =~ /p[Ff]/) {
-						$ext_type = "Deprecated";
 						$use = " - use %pS instead";
 						$use =~ s/pS/ps/ if ($bad_specifier =~ /pf/);
 					}
diff --git a/security/safesetid/securityfs.c b/security/safesetid/securityfs.c
index 74a13d432ed8..f8bc574cea9c 100644
--- a/security/safesetid/securityfs.c
+++ b/security/safesetid/securityfs.c
@@ -179,8 +179,8 @@ out_free_rule:
 	 * doesn't currently exist, just use a spinlock for now.
 	 */
 	mutex_lock(&policy_update_lock);
-	rcu_swap_protected(safesetid_setuid_rules, pol,
-			   lockdep_is_held(&policy_update_lock));
+	pol = rcu_replace_pointer(safesetid_setuid_rules, pol,
+				  lockdep_is_held(&policy_update_lock));
 	mutex_unlock(&policy_update_lock);
 	err = len;
 
diff --git a/sound/aoa/soundbus/i2sbus/pcm.c b/sound/aoa/soundbus/i2sbus/pcm.c
index 7f0754dd3d7d..a94e4023fadf 100644
--- a/sound/aoa/soundbus/i2sbus/pcm.c
+++ b/sound/aoa/soundbus/i2sbus/pcm.c
@@ -1028,7 +1028,7 @@ i2sbus_attach_codec(struct soundbus_dev *dev, struct snd_card *card,
 	/* well, we really should support scatter/gather DMA */
 	snd_pcm_lib_preallocate_pages_for_all(
 		dev->pcm, SNDRV_DMA_TYPE_DEV,
-		snd_dma_pci_data(macio_get_pci_dev(i2sdev->macio)),
+		&macio_get_pci_dev(i2sdev->macio)->dev,
 		64 * 1024, 64 * 1024);
 
 	return 0;
diff --git a/sound/arm/pxa2xx-pcm-lib.c b/sound/arm/pxa2xx-pcm-lib.c
index 54500bd098f9..a86c95d89824 100644
--- a/sound/arm/pxa2xx-pcm-lib.c
+++ b/sound/arm/pxa2xx-pcm-lib.c
@@ -175,7 +175,15 @@ void pxa2xx_pcm_free_dma_buffers(struct snd_pcm *pcm)
 }
 EXPORT_SYMBOL(pxa2xx_pcm_free_dma_buffers);
 
-int pxa2xx_soc_pcm_new(struct snd_soc_pcm_runtime *rtd)
+void pxa2xx_soc_pcm_free(struct snd_soc_component *component,
+			 struct snd_pcm *pcm)
+{
+	pxa2xx_pcm_free_dma_buffers(pcm);
+}
+EXPORT_SYMBOL(pxa2xx_soc_pcm_free);
+
+int pxa2xx_soc_pcm_new(struct snd_soc_component *component,
+		       struct snd_soc_pcm_runtime *rtd)
 {
 	struct snd_card *card = rtd->card->snd_card;
 	struct snd_pcm *pcm = rtd->pcm;
@@ -203,18 +211,64 @@ int pxa2xx_soc_pcm_new(struct snd_soc_pcm_runtime *rtd)
 }
 EXPORT_SYMBOL(pxa2xx_soc_pcm_new);
 
-const struct snd_pcm_ops pxa2xx_pcm_ops = {
-	.open		= pxa2xx_pcm_open,
-	.close		= pxa2xx_pcm_close,
-	.ioctl		= snd_pcm_lib_ioctl,
-	.hw_params	= pxa2xx_pcm_hw_params,
-	.hw_free	= pxa2xx_pcm_hw_free,
-	.prepare	= pxa2xx_pcm_prepare,
-	.trigger	= pxa2xx_pcm_trigger,
-	.pointer	= pxa2xx_pcm_pointer,
-	.mmap		= pxa2xx_pcm_mmap,
-};
-EXPORT_SYMBOL(pxa2xx_pcm_ops);
+int pxa2xx_soc_pcm_open(struct snd_soc_component *component,
+			struct snd_pcm_substream *substream)
+{
+	return pxa2xx_pcm_open(substream);
+}
+EXPORT_SYMBOL(pxa2xx_soc_pcm_open);
+
+int pxa2xx_soc_pcm_close(struct snd_soc_component *component,
+			 struct snd_pcm_substream *substream)
+{
+	return pxa2xx_pcm_close(substream);
+}
+EXPORT_SYMBOL(pxa2xx_soc_pcm_close);
+
+int pxa2xx_soc_pcm_hw_params(struct snd_soc_component *component,
+			     struct snd_pcm_substream *substream,
+			     struct snd_pcm_hw_params *params)
+{
+	return pxa2xx_pcm_hw_params(substream, params);
+}
+EXPORT_SYMBOL(pxa2xx_soc_pcm_hw_params);
+
+int pxa2xx_soc_pcm_hw_free(struct snd_soc_component *component,
+			   struct snd_pcm_substream *substream)
+{
+	return pxa2xx_pcm_hw_free(substream);
+}
+EXPORT_SYMBOL(pxa2xx_soc_pcm_hw_free);
+
+int pxa2xx_soc_pcm_prepare(struct snd_soc_component *component,
+			   struct snd_pcm_substream *substream)
+{
+	return pxa2xx_pcm_prepare(substream);
+}
+EXPORT_SYMBOL(pxa2xx_soc_pcm_prepare);
+
+int pxa2xx_soc_pcm_trigger(struct snd_soc_component *component,
+			   struct snd_pcm_substream *substream, int cmd)
+{
+	return pxa2xx_pcm_trigger(substream, cmd);
+}
+EXPORT_SYMBOL(pxa2xx_soc_pcm_trigger);
+
+snd_pcm_uframes_t
+pxa2xx_soc_pcm_pointer(struct snd_soc_component *component,
+		       struct snd_pcm_substream *substream)
+{
+	return pxa2xx_pcm_pointer(substream);
+}
+EXPORT_SYMBOL(pxa2xx_soc_pcm_pointer);
+
+int pxa2xx_soc_pcm_mmap(struct snd_soc_component *component,
+			struct snd_pcm_substream *substream,
+			struct vm_area_struct *vma)
+{
+	return pxa2xx_pcm_mmap(substream, vma);
+}
+EXPORT_SYMBOL(pxa2xx_soc_pcm_mmap);
 
 MODULE_AUTHOR("Nicolas Pitre");
 MODULE_DESCRIPTION("Intel PXA2xx sound library");
diff --git a/sound/core/Kconfig b/sound/core/Kconfig
index 4ee79ad6ae22..4044c42d8595 100644
--- a/sound/core/Kconfig
+++ b/sound/core/Kconfig
@@ -72,11 +72,11 @@ config SND_PCM_OSS
 config SND_PCM_OSS_PLUGINS
 	bool "OSS PCM (digital audio) API - Include plugin system"
 	depends on SND_PCM_OSS
-        default y
+	default y
 	help
-          If you disable this option, the ALSA's OSS PCM API will not
-          support conversion of channels, formats and rates. It will
-          behave like most of new OSS/Free drivers in 2.4/2.6 kernels.
+	  If you disable this option, the ALSA's OSS PCM API will not
+	  support conversion of channels, formats and rates. It will
+	  behave like most of new OSS/Free drivers in 2.4/2.6 kernels.
 
 config SND_PCM_TIMER
 	bool "PCM timer interface" if EXPERT
@@ -128,13 +128,13 @@ config SND_SUPPORT_OLD_API
 	  or older).
 
 config SND_PROC_FS
-        bool "Sound Proc FS Support" if EXPERT
-        depends on PROC_FS
-        default y
-        help
-          Say 'N' to disable Sound proc FS, which may reduce code size about
-          9KB on x86_64 platform.
-          If unsure say Y.
+	bool "Sound Proc FS Support" if EXPERT
+	depends on PROC_FS
+	default y
+	help
+	  Say 'N' to disable Sound proc FS, which may reduce code size about
+	  9KB on x86_64 platform.
+	  If unsure say Y.
 
 config SND_VERBOSE_PROCFS
 	bool "Verbose procfs contents"
@@ -142,8 +142,8 @@ config SND_VERBOSE_PROCFS
 	default y
 	help
 	  Say Y here to include code for verbose procfs contents (provides
-          useful information to developers when a problem occurs).  On the
-          other side, it makes the ALSA subsystem larger.
+	  useful information to developers when a problem occurs).  On the
+	  other side, it makes the ALSA subsystem larger.
 
 config SND_VERBOSE_PRINTK
 	bool "Verbose printk"
@@ -164,7 +164,7 @@ config SND_DEBUG_VERBOSE
 	depends on SND_DEBUG
 	help
 	  Say Y here to enable extra-verbose debugging messages.
-	  
+
 	  Let me repeat: it enables EXTRA-VERBOSE DEBUGGING messages.
 	  So, say Y only if you are ready to be annoyed.
 
diff --git a/sound/core/init.c b/sound/core/init.c
index db99b7fad6ad..faa9f03c01ca 100644
--- a/sound/core/init.c
+++ b/sound/core/init.c
@@ -215,6 +215,7 @@ int snd_card_new(struct device *parent, int idx, const char *xid,
 	init_waitqueue_head(&card->power_sleep);
 #endif
 	init_waitqueue_head(&card->remove_sleep);
+	card->sync_irq = -1;
 
 	device_initialize(&card->card_dev);
 	card->card_dev.parent = parent;
diff --git a/sound/core/memalloc.c b/sound/core/memalloc.c
index 6850d13aa98c..a83553fbedf0 100644
--- a/sound/core/memalloc.c
+++ b/sound/core/memalloc.c
@@ -10,6 +10,7 @@
 #include <linux/mm.h>
 #include <linux/dma-mapping.h>
 #include <linux/genalloc.h>
+#include <linux/vmalloc.h>
 #ifdef CONFIG_X86
 #include <asm/set_memory.h>
 #endif
@@ -99,6 +100,14 @@ static void snd_free_dev_iram(struct snd_dma_buffer *dmab)
  *
  */
 
+static inline gfp_t snd_mem_get_gfp_flags(const struct device *dev,
+					  gfp_t default_gfp)
+{
+	if (!dev)
+		return default_gfp;
+	else
+		return (__force gfp_t)(unsigned long)dev;
+}
 
 /**
  * snd_dma_alloc_pages - allocate the buffer area according to the given type
@@ -116,20 +125,25 @@ static void snd_free_dev_iram(struct snd_dma_buffer *dmab)
 int snd_dma_alloc_pages(int type, struct device *device, size_t size,
 			struct snd_dma_buffer *dmab)
 {
+	gfp_t gfp;
+
 	if (WARN_ON(!size))
 		return -ENXIO;
 	if (WARN_ON(!dmab))
 		return -ENXIO;
-	if (WARN_ON(!device))
-		return -EINVAL;
 
 	dmab->dev.type = type;
 	dmab->dev.dev = device;
 	dmab->bytes = 0;
 	switch (type) {
 	case SNDRV_DMA_TYPE_CONTINUOUS:
-		dmab->area = alloc_pages_exact(size,
-					       (__force gfp_t)(unsigned long)device);
+		gfp = snd_mem_get_gfp_flags(device, GFP_KERNEL);
+		dmab->area = alloc_pages_exact(size, gfp);
+		dmab->addr = 0;
+		break;
+	case SNDRV_DMA_TYPE_VMALLOC:
+		gfp = snd_mem_get_gfp_flags(device, GFP_KERNEL | __GFP_HIGHMEM);
+		dmab->area = __vmalloc(size, gfp, PAGE_KERNEL);
 		dmab->addr = 0;
 		break;
 #ifdef CONFIG_HAS_DMA
@@ -215,6 +229,9 @@ void snd_dma_free_pages(struct snd_dma_buffer *dmab)
 	case SNDRV_DMA_TYPE_CONTINUOUS:
 		free_pages_exact(dmab->area, dmab->bytes);
 		break;
+	case SNDRV_DMA_TYPE_VMALLOC:
+		vfree(dmab->area);
+		break;
 #ifdef CONFIG_HAS_DMA
 #ifdef CONFIG_GENERIC_ALLOCATOR
 	case SNDRV_DMA_TYPE_DEV_IRAM:
diff --git a/sound/core/pcm_dmaengine.c b/sound/core/pcm_dmaengine.c
index 89a05926ac73..5749a8a49784 100644
--- a/sound/core/pcm_dmaengine.c
+++ b/sound/core/pcm_dmaengine.c
@@ -369,4 +369,87 @@ int snd_dmaengine_pcm_close_release_chan(struct snd_pcm_substream *substream)
 }
 EXPORT_SYMBOL_GPL(snd_dmaengine_pcm_close_release_chan);
 
+/**
+ * snd_dmaengine_pcm_refine_runtime_hwparams - Refine runtime hw params
+ * @substream: PCM substream
+ * @dma_data: DAI DMA data
+ * @hw: PCM hw params
+ * @chan: DMA channel to use for data transfers
+ *
+ * Returns 0 on success, a negative error code otherwise.
+ *
+ * This function will query DMA capability, then refine the pcm hardware
+ * parameters.
+ */
+int snd_dmaengine_pcm_refine_runtime_hwparams(
+	struct snd_pcm_substream *substream,
+	struct snd_dmaengine_dai_dma_data *dma_data,
+	struct snd_pcm_hardware *hw,
+	struct dma_chan *chan)
+{
+	struct dma_slave_caps dma_caps;
+	u32 addr_widths = BIT(DMA_SLAVE_BUSWIDTH_1_BYTE) |
+			  BIT(DMA_SLAVE_BUSWIDTH_2_BYTES) |
+			  BIT(DMA_SLAVE_BUSWIDTH_4_BYTES);
+	snd_pcm_format_t i;
+	int ret = 0;
+
+	if (!hw || !chan || !dma_data)
+		return -EINVAL;
+
+	ret = dma_get_slave_caps(chan, &dma_caps);
+	if (ret == 0) {
+		if (dma_caps.cmd_pause && dma_caps.cmd_resume)
+			hw->info |= SNDRV_PCM_INFO_PAUSE | SNDRV_PCM_INFO_RESUME;
+		if (dma_caps.residue_granularity <= DMA_RESIDUE_GRANULARITY_SEGMENT)
+			hw->info |= SNDRV_PCM_INFO_BATCH;
+
+		if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK)
+			addr_widths = dma_caps.dst_addr_widths;
+		else
+			addr_widths = dma_caps.src_addr_widths;
+	}
+
+	/*
+	 * If SND_DMAENGINE_PCM_DAI_FLAG_PACK is set keep
+	 * hw.formats set to 0, meaning no restrictions are in place.
+	 * In this case it's the responsibility of the DAI driver to
+	 * provide the supported format information.
+	 */
+	if (!(dma_data->flags & SND_DMAENGINE_PCM_DAI_FLAG_PACK))
+		/*
+		 * Prepare formats mask for valid/allowed sample types. If the
+		 * dma does not have support for the given physical word size,
+		 * it needs to be masked out so user space can not use the
+		 * format which produces corrupted audio.
+		 * In case the dma driver does not implement the slave_caps the
+		 * default assumption is that it supports 1, 2 and 4 bytes
+		 * widths.
+		 */
+		for (i = SNDRV_PCM_FORMAT_FIRST; i <= SNDRV_PCM_FORMAT_LAST; i++) {
+			int bits = snd_pcm_format_physical_width(i);
+
+			/*
+			 * Enable only samples with DMA supported physical
+			 * widths
+			 */
+			switch (bits) {
+			case 8:
+			case 16:
+			case 24:
+			case 32:
+			case 64:
+				if (addr_widths & (1 << (bits / 8)))
+					hw->formats |= pcm_format_to_bits(i);
+				break;
+			default:
+				/* Unsupported types */
+				break;
+			}
+		}
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(snd_dmaengine_pcm_refine_runtime_hwparams);
+
 MODULE_LICENSE("GPL");
diff --git a/sound/core/pcm_local.h b/sound/core/pcm_local.h
index 1161ab2d6a5b..384efd002984 100644
--- a/sound/core/pcm_local.h
+++ b/sound/core/pcm_local.h
@@ -67,4 +67,11 @@ static inline void snd_pcm_timer_done(struct snd_pcm_substream *substream) {}
 void __snd_pcm_xrun(struct snd_pcm_substream *substream);
 void snd_pcm_group_init(struct snd_pcm_group *group);
 
+#ifdef CONFIG_SND_DMA_SGBUF
+struct page *snd_pcm_sgbuf_ops_page(struct snd_pcm_substream *substream,
+				    unsigned long offset);
+#endif
+
+#define PCM_RUNTIME_CHECK(sub) snd_BUG_ON(!(sub) || !(sub)->runtime)
+
 #endif	/* __SOUND_CORE_PCM_LOCAL_H */
diff --git a/sound/core/pcm_memory.c b/sound/core/pcm_memory.c
index 7600dcdf5fd4..d4702cc1d376 100644
--- a/sound/core/pcm_memory.c
+++ b/sound/core/pcm_memory.c
@@ -15,6 +15,7 @@
 #include <sound/pcm.h>
 #include <sound/info.h>
 #include <sound/initval.h>
+#include "pcm_local.h"
 
 static int preallocate_dma = 1;
 module_param(preallocate_dma, int, 0444);
@@ -193,9 +194,15 @@ static inline void preallocate_info_init(struct snd_pcm_substream *substream)
 /*
  * pre-allocate the buffer and create a proc file for the substream
  */
-static void snd_pcm_lib_preallocate_pages1(struct snd_pcm_substream *substream,
-					  size_t size, size_t max)
+static void preallocate_pages(struct snd_pcm_substream *substream,
+			      int type, struct device *data,
+			      size_t size, size_t max, bool managed)
 {
+	if (snd_BUG_ON(substream->dma_buffer.dev.type))
+		return;
+
+	substream->dma_buffer.dev.type = type;
+	substream->dma_buffer.dev.dev = data;
 
 	if (size > 0 && preallocate_dma && substream->number < maximum_substreams)
 		preallocate_pcm_pages(substream, size);
@@ -203,9 +210,25 @@ static void snd_pcm_lib_preallocate_pages1(struct snd_pcm_substream *substream,
 	if (substream->dma_buffer.bytes > 0)
 		substream->buffer_bytes_max = substream->dma_buffer.bytes;
 	substream->dma_max = max;
-	preallocate_info_init(substream);
+	if (max > 0)
+		preallocate_info_init(substream);
+	if (managed)
+		substream->managed_buffer_alloc = 1;
 }
 
+static void preallocate_pages_for_all(struct snd_pcm *pcm, int type,
+				      void *data, size_t size, size_t max,
+				      bool managed)
+{
+	struct snd_pcm_substream *substream;
+	int stream;
+
+	for (stream = 0; stream < 2; stream++)
+		for (substream = pcm->streams[stream].substream; substream;
+		     substream = substream->next)
+			preallocate_pages(substream, type, data, size, max,
+					  managed);
+}
 
 /**
  * snd_pcm_lib_preallocate_pages - pre-allocation for the given DMA type
@@ -221,9 +244,7 @@ void snd_pcm_lib_preallocate_pages(struct snd_pcm_substream *substream,
 				  int type, struct device *data,
 				  size_t size, size_t max)
 {
-	substream->dma_buffer.dev.type = type;
-	substream->dma_buffer.dev.dev = data;
-	snd_pcm_lib_preallocate_pages1(substream, size, max);
+	preallocate_pages(substream, type, data, size, max, false);
 }
 EXPORT_SYMBOL(snd_pcm_lib_preallocate_pages);
 
@@ -242,17 +263,57 @@ void snd_pcm_lib_preallocate_pages_for_all(struct snd_pcm *pcm,
 					  int type, void *data,
 					  size_t size, size_t max)
 {
-	struct snd_pcm_substream *substream;
-	int stream;
-
-	for (stream = 0; stream < 2; stream++)
-		for (substream = pcm->streams[stream].substream; substream; substream = substream->next)
-			snd_pcm_lib_preallocate_pages(substream, type, data, size, max);
+	preallocate_pages_for_all(pcm, type, data, size, max, false);
 }
 EXPORT_SYMBOL(snd_pcm_lib_preallocate_pages_for_all);
 
-#ifdef CONFIG_SND_DMA_SGBUF
 /**
+ * snd_pcm_set_managed_buffer - set up buffer management for a substream
+ * @substream: the pcm substream instance
+ * @type: DMA type (SNDRV_DMA_TYPE_*)
+ * @data: DMA type dependent data
+ * @size: the requested pre-allocation size in bytes
+ * @max: the max. allowed pre-allocation size
+ *
+ * Do pre-allocation for the given DMA buffer type, and set the managed
+ * buffer allocation mode to the given substream.
+ * In this mode, PCM core will allocate a buffer automatically before PCM
+ * hw_params ops call, and release the buffer after PCM hw_free ops call
+ * as well, so that the driver doesn't need to invoke the allocation and
+ * the release explicitly in its callback.
+ * When a buffer is actually allocated before the PCM hw_params call, it
+ * turns on the runtime buffer_changed flag for drivers changing their h/w
+ * parameters accordingly.
+ */
+void snd_pcm_set_managed_buffer(struct snd_pcm_substream *substream, int type,
+				struct device *data, size_t size, size_t max)
+{
+	preallocate_pages(substream, type, data, size, max, true);
+}
+EXPORT_SYMBOL(snd_pcm_set_managed_buffer);
+
+/**
+ * snd_pcm_set_managed_buffer_all - set up buffer management for all substreams
+ *	for all substreams
+ * @pcm: the pcm instance
+ * @type: DMA type (SNDRV_DMA_TYPE_*)
+ * @data: DMA type dependent data
+ * @size: the requested pre-allocation size in bytes
+ * @max: the max. allowed pre-allocation size
+ *
+ * Do pre-allocation to all substreams of the given pcm for the specified DMA
+ * type and size, and set the managed_buffer_alloc flag to each substream.
+ */
+void snd_pcm_set_managed_buffer_all(struct snd_pcm *pcm, int type,
+				    struct device *data,
+				    size_t size, size_t max)
+{
+	preallocate_pages_for_all(pcm, type, data, size, max, true);
+}
+EXPORT_SYMBOL(snd_pcm_set_managed_buffer_all);
+
+#ifdef CONFIG_SND_DMA_SGBUF
+/*
  * snd_pcm_sgbuf_ops_page - get the page struct at the given offset
  * @substream: the pcm substream instance
  * @offset: the buffer offset
@@ -270,7 +331,6 @@ struct page *snd_pcm_sgbuf_ops_page(struct snd_pcm_substream *substream, unsigne
 		return NULL;
 	return sgbuf->page_table[idx];
 }
-EXPORT_SYMBOL(snd_pcm_sgbuf_ops_page);
 #endif /* CONFIG_SND_DMA_SGBUF */
 
 /**
diff --git a/sound/core/pcm_native.c b/sound/core/pcm_native.c
index 91c6ad58729f..1fe581167b7b 100644
--- a/sound/core/pcm_native.c
+++ b/sound/core/pcm_native.c
@@ -13,6 +13,7 @@
 #include <linux/pm_qos.h>
 #include <linux/io.h>
 #include <linux/dma-mapping.h>
+#include <linux/vmalloc.h>
 #include <sound/core.h>
 #include <sound/control.h>
 #include <sound/info.h>
@@ -177,6 +178,16 @@ void snd_pcm_stream_unlock_irqrestore(struct snd_pcm_substream *substream,
 }
 EXPORT_SYMBOL_GPL(snd_pcm_stream_unlock_irqrestore);
 
+/* Run PCM ioctl ops */
+static int snd_pcm_ops_ioctl(struct snd_pcm_substream *substream,
+			     unsigned cmd, void *arg)
+{
+	if (substream->ops->ioctl)
+		return substream->ops->ioctl(substream, cmd, arg);
+	else
+		return snd_pcm_lib_ioctl(substream, cmd, arg);
+}
+
 int snd_pcm_info(struct snd_pcm_substream *substream, struct snd_pcm_info *info)
 {
 	struct snd_pcm *pcm = substream->pcm;
@@ -222,7 +233,8 @@ static bool hw_support_mmap(struct snd_pcm_substream *substream)
 		return false;
 
 	if (substream->ops->mmap ||
-	    substream->dma_buffer.dev.type != SNDRV_DMA_TYPE_DEV)
+	    (substream->dma_buffer.dev.type != SNDRV_DMA_TYPE_DEV &&
+	     substream->dma_buffer.dev.type != SNDRV_DMA_TYPE_DEV_UC))
 		return true;
 
 	return dma_can_mmap(substream->dma_buffer.dev.dev);
@@ -446,8 +458,9 @@ static int fixup_unreferenced_params(struct snd_pcm_substream *substream,
 		m = hw_param_mask_c(params, SNDRV_PCM_HW_PARAM_FORMAT);
 		i = hw_param_interval_c(params, SNDRV_PCM_HW_PARAM_CHANNELS);
 		if (snd_mask_single(m) && snd_interval_single(i)) {
-			err = substream->ops->ioctl(substream,
-					SNDRV_PCM_IOCTL1_FIFO_SIZE, params);
+			err = snd_pcm_ops_ioctl(substream,
+						SNDRV_PCM_IOCTL1_FIFO_SIZE,
+						params);
 			if (err < 0)
 				return err;
 		}
@@ -555,6 +568,17 @@ static inline void snd_pcm_timer_notify(struct snd_pcm_substream *substream,
 #endif
 }
 
+static void snd_pcm_sync_stop(struct snd_pcm_substream *substream)
+{
+	if (substream->runtime->stop_operating) {
+		substream->runtime->stop_operating = false;
+		if (substream->ops->sync_stop)
+			substream->ops->sync_stop(substream);
+		else if (substream->pcm->card->sync_irq > 0)
+			synchronize_irq(substream->pcm->card->sync_irq);
+	}
+}
+
 /**
  * snd_pcm_hw_param_choose - choose a configuration defined by @params
  * @pcm: PCM instance
@@ -647,6 +671,8 @@ static int snd_pcm_hw_params(struct snd_pcm_substream *substream,
 		if (atomic_read(&substream->mmap_count))
 			return -EBADFD;
 
+	snd_pcm_sync_stop(substream);
+
 	params->rmask = ~0U;
 	err = snd_pcm_hw_refine(substream, params);
 	if (err < 0)
@@ -660,6 +686,14 @@ static int snd_pcm_hw_params(struct snd_pcm_substream *substream,
 	if (err < 0)
 		goto _error;
 
+	if (substream->managed_buffer_alloc) {
+		err = snd_pcm_lib_malloc_pages(substream,
+					       params_buffer_bytes(params));
+		if (err < 0)
+			goto _error;
+		runtime->buffer_changed = err > 0;
+	}
+
 	if (substream->ops->hw_params != NULL) {
 		err = substream->ops->hw_params(substream, params);
 		if (err < 0)
@@ -721,6 +755,8 @@ static int snd_pcm_hw_params(struct snd_pcm_substream *substream,
 	snd_pcm_set_state(substream, SNDRV_PCM_STATE_OPEN);
 	if (substream->ops->hw_free != NULL)
 		substream->ops->hw_free(substream);
+	if (substream->managed_buffer_alloc)
+		snd_pcm_lib_free_pages(substream);
 	return err;
 }
 
@@ -765,8 +801,11 @@ static int snd_pcm_hw_free(struct snd_pcm_substream *substream)
 	snd_pcm_stream_unlock_irq(substream);
 	if (atomic_read(&substream->mmap_count))
 		return -EBADFD;
+	snd_pcm_sync_stop(substream);
 	if (substream->ops->hw_free)
 		result = substream->ops->hw_free(substream);
+	if (substream->managed_buffer_alloc)
+		snd_pcm_lib_free_pages(substream);
 	snd_pcm_set_state(substream, SNDRV_PCM_STATE_OPEN);
 	pm_qos_remove_request(&substream->latency_pm_qos_req);
 	return result;
@@ -957,7 +996,7 @@ static int snd_pcm_channel_info(struct snd_pcm_substream *substream,
 		return -EINVAL;
 	memset(info, 0, sizeof(*info));
 	info->channel = channel;
-	return substream->ops->ioctl(substream, SNDRV_PCM_IOCTL1_CHANNEL_INFO, info);
+	return snd_pcm_ops_ioctl(substream, SNDRV_PCM_IOCTL1_CHANNEL_INFO, info);
 }
 
 static int snd_pcm_channel_info_user(struct snd_pcm_substream *substream,
@@ -1288,6 +1327,7 @@ static void snd_pcm_post_stop(struct snd_pcm_substream *substream, int state)
 		runtime->status->state = state;
 		snd_pcm_timer_notify(substream, SNDRV_TIMER_EVENT_MSTOP);
 	}
+	runtime->stop_operating = true;
 	wake_up(&runtime->sleep);
 	wake_up(&runtime->tsleep);
 }
@@ -1564,6 +1604,7 @@ static void snd_pcm_post_resume(struct snd_pcm_substream *substream, int state)
 	snd_pcm_trigger_tstamp(substream);
 	runtime->status->state = runtime->status->suspended_state;
 	snd_pcm_timer_notify(substream, SNDRV_TIMER_EVENT_MRESUME);
+	snd_pcm_sync_stop(substream);
 }
 
 static const struct action_ops snd_pcm_action_resume = {
@@ -1633,7 +1674,7 @@ static int snd_pcm_pre_reset(struct snd_pcm_substream *substream, int state)
 static int snd_pcm_do_reset(struct snd_pcm_substream *substream, int state)
 {
 	struct snd_pcm_runtime *runtime = substream->runtime;
-	int err = substream->ops->ioctl(substream, SNDRV_PCM_IOCTL1_RESET, NULL);
+	int err = snd_pcm_ops_ioctl(substream, SNDRV_PCM_IOCTL1_RESET, NULL);
 	if (err < 0)
 		return err;
 	runtime->hw_ptr_base = 0;
@@ -1684,6 +1725,7 @@ static int snd_pcm_pre_prepare(struct snd_pcm_substream *substream,
 static int snd_pcm_do_prepare(struct snd_pcm_substream *substream, int state)
 {
 	int err;
+	snd_pcm_sync_stop(substream);
 	err = substream->ops->prepare(substream);
 	if (err < 0)
 		return err;
@@ -3334,7 +3376,18 @@ static inline struct page *
 snd_pcm_default_page_ops(struct snd_pcm_substream *substream, unsigned long ofs)
 {
 	void *vaddr = substream->runtime->dma_area + ofs;
-	return virt_to_page(vaddr);
+
+	switch (substream->dma_buffer.dev.type) {
+#ifdef CONFIG_SND_DMA_SGBUF
+	case SNDRV_DMA_TYPE_DEV_SG:
+	case SNDRV_DMA_TYPE_DEV_UC_SG:
+		return snd_pcm_sgbuf_ops_page(substream, ofs);
+#endif /* CONFIG_SND_DMA_SGBUF */
+	case SNDRV_DMA_TYPE_VMALLOC:
+		return vmalloc_to_page(vaddr);
+	default:
+		return virt_to_page(vaddr);
+	}
 }
 
 /*
@@ -3403,7 +3456,8 @@ int snd_pcm_lib_default_mmap(struct snd_pcm_substream *substream,
 #endif /* CONFIG_GENERIC_ALLOCATOR */
 #ifndef CONFIG_X86 /* for avoiding warnings arch/x86/mm/pat.c */
 	if (IS_ENABLED(CONFIG_HAS_DMA) && !substream->ops->page &&
-	    substream->dma_buffer.dev.type == SNDRV_DMA_TYPE_DEV)
+	    (substream->dma_buffer.dev.type == SNDRV_DMA_TYPE_DEV ||
+	     substream->dma_buffer.dev.type == SNDRV_DMA_TYPE_DEV_UC))
 		return dma_mmap_coherent(substream->dma_buffer.dev.dev,
 					 area,
 					 substream->runtime->dma_area,
diff --git a/sound/core/seq/seq_timer.c b/sound/core/seq/seq_timer.c
index 161f3170bd7e..63dc7bdb622d 100644
--- a/sound/core/seq/seq_timer.c
+++ b/sound/core/seq/seq_timer.c
@@ -272,7 +272,13 @@ int snd_seq_timer_open(struct snd_seq_queue *q)
 		return -EINVAL;
 	if (tmr->alsa_id.dev_class != SNDRV_TIMER_CLASS_SLAVE)
 		tmr->alsa_id.dev_sclass = SNDRV_TIMER_SCLASS_SEQUENCER;
-	err = snd_timer_open(&t, str, &tmr->alsa_id, q->queue);
+	t = snd_timer_instance_new(str);
+	if (!t)
+		return -ENOMEM;
+	t->callback = snd_seq_timer_interrupt;
+	t->callback_data = q;
+	t->flags |= SNDRV_TIMER_IFLG_AUTO;
+	err = snd_timer_open(t, &tmr->alsa_id, q->queue);
 	if (err < 0 && tmr->alsa_id.dev_class != SNDRV_TIMER_CLASS_SLAVE) {
 		if (tmr->alsa_id.dev_class != SNDRV_TIMER_CLASS_GLOBAL ||
 		    tmr->alsa_id.device != SNDRV_TIMER_GLOBAL_SYSTEM) {
@@ -282,16 +288,14 @@ int snd_seq_timer_open(struct snd_seq_queue *q)
 			tid.dev_sclass = SNDRV_TIMER_SCLASS_SEQUENCER;
 			tid.card = -1;
 			tid.device = SNDRV_TIMER_GLOBAL_SYSTEM;
-			err = snd_timer_open(&t, str, &tid, q->queue);
+			err = snd_timer_open(t, &tid, q->queue);
 		}
 	}
 	if (err < 0) {
 		pr_err("ALSA: seq fatal error: cannot create timer (%i)\n", err);
+		snd_timer_instance_free(t);
 		return err;
 	}
-	t->callback = snd_seq_timer_interrupt;
-	t->callback_data = q;
-	t->flags |= SNDRV_TIMER_IFLG_AUTO;
 	spin_lock_irq(&tmr->lock);
 	tmr->timeri = t;
 	spin_unlock_irq(&tmr->lock);
@@ -310,8 +314,10 @@ int snd_seq_timer_close(struct snd_seq_queue *q)
 	t = tmr->timeri;
 	tmr->timeri = NULL;
 	spin_unlock_irq(&tmr->lock);
-	if (t)
+	if (t) {
 		snd_timer_close(t);
+		snd_timer_instance_free(t);
+	}
 	return 0;
 }
 
diff --git a/sound/core/timer.c b/sound/core/timer.c
index 59ae21b0bb93..24fed5c78273 100644
--- a/sound/core/timer.c
+++ b/sound/core/timer.c
@@ -74,6 +74,9 @@ static LIST_HEAD(snd_timer_slave_list);
 /* lock for slave active lists */
 static DEFINE_SPINLOCK(slave_active_lock);
 
+#define MAX_SLAVE_INSTANCES	1000
+static int num_slaves;
+
 static DEFINE_MUTEX(register_mutex);
 
 static int snd_timer_free(struct snd_timer *timer);
@@ -85,12 +88,11 @@ static void snd_timer_reschedule(struct snd_timer * timer, unsigned long ticks_l
 
 /*
  * create a timer instance with the given owner string.
- * when timer is not NULL, increments the module counter
  */
-static struct snd_timer_instance *snd_timer_instance_new(char *owner,
-							 struct snd_timer *timer)
+struct snd_timer_instance *snd_timer_instance_new(const char *owner)
 {
 	struct snd_timer_instance *timeri;
+
 	timeri = kzalloc(sizeof(*timeri), GFP_KERNEL);
 	if (timeri == NULL)
 		return NULL;
@@ -105,15 +107,20 @@ static struct snd_timer_instance *snd_timer_instance_new(char *owner,
 	INIT_LIST_HEAD(&timeri->slave_list_head);
 	INIT_LIST_HEAD(&timeri->slave_active_head);
 
-	timeri->timer = timer;
-	if (timer && !try_module_get(timer->module)) {
+	return timeri;
+}
+EXPORT_SYMBOL(snd_timer_instance_new);
+
+void snd_timer_instance_free(struct snd_timer_instance *timeri)
+{
+	if (timeri) {
+		if (timeri->private_free)
+			timeri->private_free(timeri);
 		kfree(timeri->owner);
 		kfree(timeri);
-		return NULL;
 	}
-
-	return timeri;
 }
+EXPORT_SYMBOL(snd_timer_instance_free);
 
 /*
  * find a timer instance from the given timer id
@@ -160,6 +167,28 @@ static void snd_timer_request(struct snd_timer_id *tid)
 
 #endif
 
+/* move the slave if it belongs to the master; return 1 if match */
+static int check_matching_master_slave(struct snd_timer_instance *master,
+				       struct snd_timer_instance *slave)
+{
+	if (slave->slave_class != master->slave_class ||
+	    slave->slave_id != master->slave_id)
+		return 0;
+	if (master->timer->num_instances >= master->timer->max_instances)
+		return -EBUSY;
+	list_move_tail(&slave->open_list, &master->slave_list_head);
+	master->timer->num_instances++;
+	spin_lock_irq(&slave_active_lock);
+	spin_lock(&master->timer->lock);
+	slave->master = master;
+	slave->timer = master->timer;
+	if (slave->flags & SNDRV_TIMER_IFLG_RUNNING)
+		list_add_tail(&slave->active_list, &master->slave_active_head);
+	spin_unlock(&master->timer->lock);
+	spin_unlock_irq(&slave_active_lock);
+	return 1;
+}
+
 /*
  * look for a master instance matching with the slave id of the given slave.
  * when found, relink the open_link of the slave.
@@ -170,27 +199,18 @@ static int snd_timer_check_slave(struct snd_timer_instance *slave)
 {
 	struct snd_timer *timer;
 	struct snd_timer_instance *master;
+	int err = 0;
 
 	/* FIXME: it's really dumb to look up all entries.. */
 	list_for_each_entry(timer, &snd_timer_list, device_list) {
 		list_for_each_entry(master, &timer->open_list_head, open_list) {
-			if (slave->slave_class == master->slave_class &&
-			    slave->slave_id == master->slave_id) {
-				if (master->timer->num_instances >=
-				    master->timer->max_instances)
-					return -EBUSY;
-				list_move_tail(&slave->open_list,
-					       &master->slave_list_head);
-				master->timer->num_instances++;
-				spin_lock_irq(&slave_active_lock);
-				slave->master = master;
-				slave->timer = master->timer;
-				spin_unlock_irq(&slave_active_lock);
-				return 0;
-			}
+			err = check_matching_master_slave(master, slave);
+			if (err != 0) /* match found or error */
+				goto out;
 		}
 	}
-	return 0;
+ out:
+	return err < 0 ? err : 0;
 }
 
 /*
@@ -202,43 +222,29 @@ static int snd_timer_check_slave(struct snd_timer_instance *slave)
 static int snd_timer_check_master(struct snd_timer_instance *master)
 {
 	struct snd_timer_instance *slave, *tmp;
+	int err = 0;
 
 	/* check all pending slaves */
 	list_for_each_entry_safe(slave, tmp, &snd_timer_slave_list, open_list) {
-		if (slave->slave_class == master->slave_class &&
-		    slave->slave_id == master->slave_id) {
-			if (master->timer->num_instances >=
-			    master->timer->max_instances)
-				return -EBUSY;
-			list_move_tail(&slave->open_list, &master->slave_list_head);
-			master->timer->num_instances++;
-			spin_lock_irq(&slave_active_lock);
-			spin_lock(&master->timer->lock);
-			slave->master = master;
-			slave->timer = master->timer;
-			if (slave->flags & SNDRV_TIMER_IFLG_RUNNING)
-				list_add_tail(&slave->active_list,
-					      &master->slave_active_head);
-			spin_unlock(&master->timer->lock);
-			spin_unlock_irq(&slave_active_lock);
-		}
+		err = check_matching_master_slave(master, slave);
+		if (err < 0)
+			break;
 	}
-	return 0;
+	return err < 0 ? err : 0;
 }
 
-static int snd_timer_close_locked(struct snd_timer_instance *timeri,
-				  struct device **card_devp_to_put);
+static void snd_timer_close_locked(struct snd_timer_instance *timeri,
+				   struct device **card_devp_to_put);
 
 /*
  * open a timer instance
  * when opening a master, the slave id must be here given.
  */
-int snd_timer_open(struct snd_timer_instance **ti,
-		   char *owner, struct snd_timer_id *tid,
+int snd_timer_open(struct snd_timer_instance *timeri,
+		   struct snd_timer_id *tid,
 		   unsigned int slave_id)
 {
 	struct snd_timer *timer;
-	struct snd_timer_instance *timeri = NULL;
 	struct device *card_dev_to_put = NULL;
 	int err;
 
@@ -252,21 +258,17 @@ int snd_timer_open(struct snd_timer_instance **ti,
 			err = -EINVAL;
 			goto unlock;
 		}
-		timeri = snd_timer_instance_new(owner, NULL);
-		if (!timeri) {
-			err = -ENOMEM;
+		if (num_slaves >= MAX_SLAVE_INSTANCES) {
+			err = -EBUSY;
 			goto unlock;
 		}
 		timeri->slave_class = tid->dev_sclass;
 		timeri->slave_id = tid->device;
 		timeri->flags |= SNDRV_TIMER_IFLG_SLAVE;
 		list_add_tail(&timeri->open_list, &snd_timer_slave_list);
+		num_slaves++;
 		err = snd_timer_check_slave(timeri);
-		if (err < 0) {
-			snd_timer_close_locked(timeri, &card_dev_to_put);
-			timeri = NULL;
-		}
-		goto unlock;
+		goto list_added;
 	}
 
 	/* open a master instance */
@@ -296,45 +298,40 @@ int snd_timer_open(struct snd_timer_instance **ti,
 		err = -EBUSY;
 		goto unlock;
 	}
-	timeri = snd_timer_instance_new(owner, timer);
-	if (!timeri) {
-		err = -ENOMEM;
+	if (!try_module_get(timer->module)) {
+		err = -EBUSY;
 		goto unlock;
 	}
 	/* take a card refcount for safe disconnection */
-	if (timer->card)
+	if (timer->card) {
 		get_device(&timer->card->card_dev);
-	timeri->slave_class = tid->dev_sclass;
-	timeri->slave_id = slave_id;
+		card_dev_to_put = &timer->card->card_dev;
+	}
 
 	if (list_empty(&timer->open_list_head) && timer->hw.open) {
 		err = timer->hw.open(timer);
 		if (err) {
-			kfree(timeri->owner);
-			kfree(timeri);
-			timeri = NULL;
-
-			if (timer->card)
-				card_dev_to_put = &timer->card->card_dev;
 			module_put(timer->module);
 			goto unlock;
 		}
 	}
 
+	timeri->timer = timer;
+	timeri->slave_class = tid->dev_sclass;
+	timeri->slave_id = slave_id;
+
 	list_add_tail(&timeri->open_list, &timer->open_list_head);
 	timer->num_instances++;
 	err = snd_timer_check_master(timeri);
-	if (err < 0) {
+list_added:
+	if (err < 0)
 		snd_timer_close_locked(timeri, &card_dev_to_put);
-		timeri = NULL;
-	}
 
  unlock:
 	mutex_unlock(&register_mutex);
 	/* put_device() is called after unlock for avoiding deadlock */
-	if (card_dev_to_put)
+	if (err < 0 && card_dev_to_put)
 		put_device(card_dev_to_put);
-	*ti = timeri;
 	return err;
 }
 EXPORT_SYMBOL(snd_timer_open);
@@ -343,8 +340,8 @@ EXPORT_SYMBOL(snd_timer_open);
  * close a timer instance
  * call this with register_mutex down.
  */
-static int snd_timer_close_locked(struct snd_timer_instance *timeri,
-				  struct device **card_devp_to_put)
+static void snd_timer_close_locked(struct snd_timer_instance *timeri,
+				   struct device **card_devp_to_put)
 {
 	struct snd_timer *timer = timeri->timer;
 	struct snd_timer_instance *slave, *tmp;
@@ -355,7 +352,11 @@ static int snd_timer_close_locked(struct snd_timer_instance *timeri,
 		spin_unlock_irq(&timer->lock);
 	}
 
-	list_del(&timeri->open_list);
+	if (!list_empty(&timeri->open_list)) {
+		list_del_init(&timeri->open_list);
+		if (timeri->flags & SNDRV_TIMER_IFLG_SLAVE)
+			num_slaves--;
+	}
 
 	/* force to stop the timer */
 	snd_timer_stop(timeri);
@@ -374,6 +375,7 @@ static int snd_timer_close_locked(struct snd_timer_instance *timeri,
 		/* remove slave links */
 		spin_lock_irq(&slave_active_lock);
 		spin_lock(&timer->lock);
+		timeri->timer = NULL;
 		list_for_each_entry_safe(slave, tmp, &timeri->slave_list_head,
 					 open_list) {
 			list_move_tail(&slave->open_list, &snd_timer_slave_list);
@@ -391,11 +393,6 @@ static int snd_timer_close_locked(struct snd_timer_instance *timeri,
 			timer = NULL;
 	}
 
-	if (timeri->private_free)
-		timeri->private_free(timeri);
-	kfree(timeri->owner);
-	kfree(timeri);
-
 	if (timer) {
 		if (list_empty(&timer->open_list_head) && timer->hw.close)
 			timer->hw.close(timer);
@@ -404,28 +401,24 @@ static int snd_timer_close_locked(struct snd_timer_instance *timeri,
 			*card_devp_to_put = &timer->card->card_dev;
 		module_put(timer->module);
 	}
-
-	return 0;
 }
 
 /*
  * close a timer instance
  */
-int snd_timer_close(struct snd_timer_instance *timeri)
+void snd_timer_close(struct snd_timer_instance *timeri)
 {
 	struct device *card_dev_to_put = NULL;
-	int err;
 
 	if (snd_BUG_ON(!timeri))
-		return -ENXIO;
+		return;
 
 	mutex_lock(&register_mutex);
-	err = snd_timer_close_locked(timeri, &card_dev_to_put);
+	snd_timer_close_locked(timeri, &card_dev_to_put);
 	mutex_unlock(&register_mutex);
 	/* put_device() is called after unlock for avoiding deadlock */
 	if (card_dev_to_put)
 		put_device(card_dev_to_put);
-	return err;
 }
 EXPORT_SYMBOL(snd_timer_close);
 
@@ -1474,8 +1467,10 @@ static int snd_timer_user_release(struct inode *inode, struct file *file)
 		tu = file->private_data;
 		file->private_data = NULL;
 		mutex_lock(&tu->ioctl_lock);
-		if (tu->timeri)
+		if (tu->timeri) {
 			snd_timer_close(tu->timeri);
+			snd_timer_instance_free(tu->timeri);
+		}
 		mutex_unlock(&tu->ioctl_lock);
 		kfree(tu->queue);
 		kfree(tu->tqueue);
@@ -1716,6 +1711,7 @@ static int snd_timer_user_tselect(struct file *file,
 	tu = file->private_data;
 	if (tu->timeri) {
 		snd_timer_close(tu->timeri);
+		snd_timer_instance_free(tu->timeri);
 		tu->timeri = NULL;
 	}
 	if (copy_from_user(&tselect, _tselect, sizeof(tselect))) {
@@ -1725,9 +1721,11 @@ static int snd_timer_user_tselect(struct file *file,
 	sprintf(str, "application %i", current->pid);
 	if (tselect.id.dev_class != SNDRV_TIMER_CLASS_SLAVE)
 		tselect.id.dev_sclass = SNDRV_TIMER_SCLASS_APPLICATION;
-	err = snd_timer_open(&tu->timeri, str, &tselect.id, current->pid);
-	if (err < 0)
+	tu->timeri = snd_timer_instance_new(str);
+	if (!tu->timeri) {
+		err = -ENOMEM;
 		goto __err;
+	}
 
 	tu->timeri->flags |= SNDRV_TIMER_IFLG_FAST;
 	tu->timeri->callback = tu->tread
@@ -1736,6 +1734,12 @@ static int snd_timer_user_tselect(struct file *file,
 	tu->timeri->callback_data = (void *)tu;
 	tu->timeri->disconnect = snd_timer_user_disconnect;
 
+	err = snd_timer_open(tu->timeri, &tselect.id, current->pid);
+	if (err < 0) {
+		snd_timer_instance_free(tu->timeri);
+		tu->timeri = NULL;
+	}
+
       __err:
 	return err;
 }
diff --git a/sound/drivers/Kconfig b/sound/drivers/Kconfig
index 09932cc98e9d..577c8e03ec4d 100644
--- a/sound/drivers/Kconfig
+++ b/sound/drivers/Kconfig
@@ -1,7 +1,7 @@
 # SPDX-License-Identifier: GPL-2.0-only
 config SND_MPU401_UART
-        tristate
-        select SND_RAWMIDI
+	tristate
+	select SND_RAWMIDI
 
 config SND_OPL3_LIB
 	tristate
@@ -90,16 +90,17 @@ config SND_DUMMY
 	  will be called snd-dummy.
 
 config SND_ALOOP
-        tristate "Generic loopback driver (PCM)"
-        select SND_PCM
-        help
-          Say 'Y' or 'M' to include support for the PCM loopback device.
+	tristate "Generic loopback driver (PCM)"
+	select SND_PCM
+	select SND_TIMER
+	help
+	  Say 'Y' or 'M' to include support for the PCM loopback device.
 	  This module returns played samples back to the user space using
 	  the standard ALSA PCM device. The devices are routed 0->1 and
-          1->0, where first number is the playback PCM device and second
+	  1->0, where first number is the playback PCM device and second
 	  number is the capture device. Module creates two PCM devices and
 	  configured number of substreams (see the pcm_substreams module
-          parameter).
+	  parameter).
 
 	  The loopback device allows time sychronization with an external
 	  timing source using the time shift universal control (+-20%
@@ -142,12 +143,12 @@ config SND_MTS64
 	select SND_RAWMIDI
 	help
 	  The ESI Miditerminal 4140 is a 4 In 4 Out MIDI Interface with 
-          additional SMPTE Timecode capabilities for the parallel port.
+	  additional SMPTE Timecode capabilities for the parallel port.
 
 	  Say 'Y' to include support for this device.
 
 	  To compile this driver as a module, chose 'M' here: the module 
-          will be called snd-mts64.
+	  will be called snd-mts64.
 
 config SND_SERIAL_U16550
 	tristate "UART16550 serial MIDI driver"
diff --git a/sound/drivers/aloop.c b/sound/drivers/aloop.c
index 9ccdad89c288..0ebfbe70db00 100644
--- a/sound/drivers/aloop.c
+++ b/sound/drivers/aloop.c
@@ -28,6 +28,7 @@
 #include <sound/pcm_params.h>
 #include <sound/info.h>
 #include <sound/initval.h>
+#include <sound/timer.h>
 
 MODULE_AUTHOR("Jaroslav Kysela <perex@perex.cz>");
 MODULE_DESCRIPTION("A loopback soundcard");
@@ -41,6 +42,7 @@ static char *id[SNDRV_CARDS] = SNDRV_DEFAULT_STR;	/* ID for this card */
 static bool enable[SNDRV_CARDS] = {1, [1 ... (SNDRV_CARDS - 1)] = 0};
 static int pcm_substreams[SNDRV_CARDS] = {[0 ... (SNDRV_CARDS - 1)] = 8};
 static int pcm_notify[SNDRV_CARDS];
+static char *timer_source[SNDRV_CARDS];
 
 module_param_array(index, int, NULL, 0444);
 MODULE_PARM_DESC(index, "Index value for loopback soundcard.");
@@ -52,11 +54,48 @@ module_param_array(pcm_substreams, int, NULL, 0444);
 MODULE_PARM_DESC(pcm_substreams, "PCM substreams # (1-8) for loopback driver.");
 module_param_array(pcm_notify, int, NULL, 0444);
 MODULE_PARM_DESC(pcm_notify, "Break capture when PCM format/rate/channels changes.");
+module_param_array(timer_source, charp, NULL, 0444);
+MODULE_PARM_DESC(timer_source, "Sound card name or number and device/subdevice number of timer to be used. Empty string for jiffies timer [default].");
 
 #define NO_PITCH 100000
 
+#define CABLE_VALID_PLAYBACK	BIT(SNDRV_PCM_STREAM_PLAYBACK)
+#define CABLE_VALID_CAPTURE	BIT(SNDRV_PCM_STREAM_CAPTURE)
+#define CABLE_VALID_BOTH	(CABLE_VALID_PLAYBACK | CABLE_VALID_CAPTURE)
+
+struct loopback_cable;
 struct loopback_pcm;
 
+struct loopback_ops {
+	/* optional
+	 * call in loopback->cable_lock
+	 */
+	int (*open)(struct loopback_pcm *dpcm);
+	/* required
+	 * call in cable->lock
+	 */
+	int (*start)(struct loopback_pcm *dpcm);
+	/* required
+	 * call in cable->lock
+	 */
+	int (*stop)(struct loopback_pcm *dpcm);
+	/* optional */
+	int (*stop_sync)(struct loopback_pcm *dpcm);
+	/* optional */
+	int (*close_substream)(struct loopback_pcm *dpcm);
+	/* optional
+	 * call in loopback->cable_lock
+	 */
+	int (*close_cable)(struct loopback_pcm *dpcm);
+	/* optional
+	 * call in cable->lock
+	 */
+	unsigned int (*pos_update)(struct loopback_cable *cable);
+	/* optional */
+	void (*dpcm_info)(struct loopback_pcm *dpcm,
+			  struct snd_info_buffer *buffer);
+};
+
 struct loopback_cable {
 	spinlock_t lock;
 	struct loopback_pcm *streams[2];
@@ -65,6 +104,15 @@ struct loopback_cable {
 	unsigned int valid;
 	unsigned int running;
 	unsigned int pause;
+	/* timer specific */
+	struct loopback_ops *ops;
+	/* If sound timer is used */
+	struct {
+		int stream;
+		struct snd_timer_id id;
+		struct tasklet_struct event_tasklet;
+		struct snd_timer_instance *instance;
+	} snd_timer;
 };
 
 struct loopback_setup {
@@ -85,6 +133,7 @@ struct loopback {
 	struct loopback_cable *cables[MAX_PCM_SUBSTREAMS][2];
 	struct snd_pcm *pcm[2];
 	struct loopback_setup setup[MAX_PCM_SUBSTREAMS][2];
+	const char *timer_source;
 };
 
 struct loopback_pcm {
@@ -102,10 +151,13 @@ struct loopback_pcm {
 	/* flags */
 	unsigned int period_update_pending :1;
 	/* timer stuff */
-	unsigned int irq_pos;		/* fractional IRQ position */
-	unsigned int period_size_frac;
+	unsigned int irq_pos;		/* fractional IRQ position in jiffies
+					 * ticks
+					 */
+	unsigned int period_size_frac;	/* period size in jiffies ticks */
 	unsigned int last_drift;
 	unsigned long last_jiffies;
+	/* If jiffies timer is used */
 	struct timer_list timer;
 };
 
@@ -153,7 +205,7 @@ static inline unsigned int get_rate_shift(struct loopback_pcm *dpcm)
 }
 
 /* call in cable->lock */
-static void loopback_timer_start(struct loopback_pcm *dpcm)
+static int loopback_jiffies_timer_start(struct loopback_pcm *dpcm)
 {
 	unsigned long tick;
 	unsigned int rate_shift = get_rate_shift(dpcm);
@@ -169,23 +221,102 @@ static void loopback_timer_start(struct loopback_pcm *dpcm)
 	tick = dpcm->period_size_frac - dpcm->irq_pos;
 	tick = (tick + dpcm->pcm_bps - 1) / dpcm->pcm_bps;
 	mod_timer(&dpcm->timer, jiffies + tick);
+
+	return 0;
 }
 
 /* call in cable->lock */
-static inline void loopback_timer_stop(struct loopback_pcm *dpcm)
+static int loopback_snd_timer_start(struct loopback_pcm *dpcm)
+{
+	struct loopback_cable *cable = dpcm->cable;
+	int err;
+
+	/* Loopback device has to use same period as timer card. Therefore
+	 * wake up for each snd_pcm_period_elapsed() call of timer card.
+	 */
+	err = snd_timer_start(cable->snd_timer.instance, 1);
+	if (err < 0) {
+		/* do not report error if trying to start but already
+		 * running. For example called by opposite substream
+		 * of the same cable
+		 */
+		if (err == -EBUSY)
+			return 0;
+
+		pcm_err(dpcm->substream->pcm,
+			"snd_timer_start(%d,%d,%d) failed with %d",
+			cable->snd_timer.id.card,
+			cable->snd_timer.id.device,
+			cable->snd_timer.id.subdevice,
+			err);
+	}
+
+	return err;
+}
+
+/* call in cable->lock */
+static inline int loopback_jiffies_timer_stop(struct loopback_pcm *dpcm)
 {
 	del_timer(&dpcm->timer);
 	dpcm->timer.expires = 0;
+
+	return 0;
 }
 
-static inline void loopback_timer_stop_sync(struct loopback_pcm *dpcm)
+/* call in cable->lock */
+static int loopback_snd_timer_stop(struct loopback_pcm *dpcm)
+{
+	struct loopback_cable *cable = dpcm->cable;
+	int err;
+
+	/* only stop if both devices (playback and capture) are not running */
+	if (cable->running ^ cable->pause)
+		return 0;
+
+	err = snd_timer_stop(cable->snd_timer.instance);
+	if (err < 0) {
+		pcm_err(dpcm->substream->pcm,
+			"snd_timer_stop(%d,%d,%d) failed with %d",
+			cable->snd_timer.id.card,
+			cable->snd_timer.id.device,
+			cable->snd_timer.id.subdevice,
+			err);
+	}
+
+	return err;
+}
+
+static inline int loopback_jiffies_timer_stop_sync(struct loopback_pcm *dpcm)
 {
 	del_timer_sync(&dpcm->timer);
+
+	return 0;
 }
 
-#define CABLE_VALID_PLAYBACK	(1 << SNDRV_PCM_STREAM_PLAYBACK)
-#define CABLE_VALID_CAPTURE	(1 << SNDRV_PCM_STREAM_CAPTURE)
-#define CABLE_VALID_BOTH	(CABLE_VALID_PLAYBACK|CABLE_VALID_CAPTURE)
+/* call in loopback->cable_lock */
+static int loopback_snd_timer_close_cable(struct loopback_pcm *dpcm)
+{
+	struct loopback_cable *cable = dpcm->cable;
+
+	/* snd_timer was not opened */
+	if (!cable->snd_timer.instance)
+		return 0;
+
+	/* will only be called from free_cable() when other stream was
+	 * already closed. Other stream cannot be reopened as long as
+	 * loopback->cable_lock is locked. Therefore no need to lock
+	 * cable->lock;
+	 */
+	snd_timer_close(cable->snd_timer.instance);
+
+	/* wait till drain tasklet has finished if requested */
+	tasklet_kill(&cable->snd_timer.event_tasklet);
+
+	snd_timer_instance_free(cable->snd_timer.instance);
+	memset(&cable->snd_timer, 0, sizeof(cable->snd_timer));
+
+	return 0;
+}
 
 static int loopback_check_format(struct loopback_cable *cable, int stream)
 {
@@ -249,7 +380,7 @@ static int loopback_trigger(struct snd_pcm_substream *substream, int cmd)
 	struct snd_pcm_runtime *runtime = substream->runtime;
 	struct loopback_pcm *dpcm = runtime->private_data;
 	struct loopback_cable *cable = dpcm->cable;
-	int err, stream = 1 << substream->stream;
+	int err = 0, stream = 1 << substream->stream;
 
 	switch (cmd) {
 	case SNDRV_PCM_TRIGGER_START:
@@ -262,7 +393,7 @@ static int loopback_trigger(struct snd_pcm_substream *substream, int cmd)
 		spin_lock(&cable->lock);	
 		cable->running |= stream;
 		cable->pause &= ~stream;
-		loopback_timer_start(dpcm);
+		err = cable->ops->start(dpcm);
 		spin_unlock(&cable->lock);
 		if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK)
 			loopback_active_notify(dpcm);
@@ -271,7 +402,7 @@ static int loopback_trigger(struct snd_pcm_substream *substream, int cmd)
 		spin_lock(&cable->lock);	
 		cable->running &= ~stream;
 		cable->pause &= ~stream;
-		loopback_timer_stop(dpcm);
+		err = cable->ops->stop(dpcm);
 		spin_unlock(&cable->lock);
 		if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK)
 			loopback_active_notify(dpcm);
@@ -280,7 +411,7 @@ static int loopback_trigger(struct snd_pcm_substream *substream, int cmd)
 	case SNDRV_PCM_TRIGGER_SUSPEND:
 		spin_lock(&cable->lock);	
 		cable->pause |= stream;
-		loopback_timer_stop(dpcm);
+		err = cable->ops->stop(dpcm);
 		spin_unlock(&cable->lock);
 		if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK)
 			loopback_active_notify(dpcm);
@@ -290,7 +421,7 @@ static int loopback_trigger(struct snd_pcm_substream *substream, int cmd)
 		spin_lock(&cable->lock);
 		dpcm->last_jiffies = jiffies;
 		cable->pause &= ~stream;
-		loopback_timer_start(dpcm);
+		err = cable->ops->start(dpcm);
 		spin_unlock(&cable->lock);
 		if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK)
 			loopback_active_notify(dpcm);
@@ -298,7 +429,7 @@ static int loopback_trigger(struct snd_pcm_substream *substream, int cmd)
 	default:
 		return -EINVAL;
 	}
-	return 0;
+	return err;
 }
 
 static void params_change(struct snd_pcm_substream *substream)
@@ -312,6 +443,13 @@ static void params_change(struct snd_pcm_substream *substream)
 	cable->hw.rate_max = runtime->rate;
 	cable->hw.channels_min = runtime->channels;
 	cable->hw.channels_max = runtime->channels;
+
+	if (cable->snd_timer.instance) {
+		cable->hw.period_bytes_min =
+				frames_to_bytes(runtime, runtime->period_size);
+		cable->hw.period_bytes_max = cable->hw.period_bytes_min;
+	}
+
 }
 
 static int loopback_prepare(struct snd_pcm_substream *substream)
@@ -319,9 +457,13 @@ static int loopback_prepare(struct snd_pcm_substream *substream)
 	struct snd_pcm_runtime *runtime = substream->runtime;
 	struct loopback_pcm *dpcm = runtime->private_data;
 	struct loopback_cable *cable = dpcm->cable;
-	int bps, salign;
+	int err, bps, salign;
 
-	loopback_timer_stop_sync(dpcm);
+	if (cable->ops->stop_sync) {
+		err = cable->ops->stop_sync(dpcm);
+		if (err < 0)
+			return err;
+	}
 
 	salign = (snd_pcm_format_physical_width(runtime->format) *
 						runtime->channels) / 8;
@@ -457,7 +599,8 @@ static inline void bytepos_finish(struct loopback_pcm *dpcm,
 }
 
 /* call in cable->lock */
-static unsigned int loopback_pos_update(struct loopback_cable *cable)
+static unsigned int loopback_jiffies_timer_pos_update
+		(struct loopback_cable *cable)
 {
 	struct loopback_pcm *dpcm_play =
 			cable->streams[SNDRV_PCM_STREAM_PLAYBACK];
@@ -510,14 +653,15 @@ static unsigned int loopback_pos_update(struct loopback_cable *cable)
 	return running;
 }
 
-static void loopback_timer_function(struct timer_list *t)
+static void loopback_jiffies_timer_function(struct timer_list *t)
 {
 	struct loopback_pcm *dpcm = from_timer(dpcm, t, timer);
 	unsigned long flags;
 
 	spin_lock_irqsave(&dpcm->cable->lock, flags);
-	if (loopback_pos_update(dpcm->cable) & (1 << dpcm->substream->stream)) {
-		loopback_timer_start(dpcm);
+	if (loopback_jiffies_timer_pos_update(dpcm->cable) &
+			(1 << dpcm->substream->stream)) {
+		loopback_jiffies_timer_start(dpcm);
 		if (dpcm->period_update_pending) {
 			dpcm->period_update_pending = 0;
 			spin_unlock_irqrestore(&dpcm->cable->lock, flags);
@@ -529,6 +673,193 @@ static void loopback_timer_function(struct timer_list *t)
 	spin_unlock_irqrestore(&dpcm->cable->lock, flags);
 }
 
+/* call in cable->lock */
+static int loopback_snd_timer_check_resolution(struct snd_pcm_runtime *runtime,
+					       unsigned long resolution)
+{
+	if (resolution != runtime->timer_resolution) {
+		struct loopback_pcm *dpcm = runtime->private_data;
+		struct loopback_cable *cable = dpcm->cable;
+		/* Worst case estimation of possible values for resolution
+		 * resolution <= (512 * 1024) frames / 8kHz in nsec
+		 * resolution <= 65.536.000.000 nsec
+		 *
+		 * period_size <= 65.536.000.000 nsec / 1000nsec/usec * 192kHz +
+		 *  500.000
+		 * period_size <= 12.582.912.000.000  <64bit
+		 *  / 1.000.000 usec/sec
+		 */
+		snd_pcm_uframes_t period_size_usec =
+				resolution / 1000 * runtime->rate;
+		/* round to nearest sample rate */
+		snd_pcm_uframes_t period_size =
+				(period_size_usec + 500 * 1000) / (1000 * 1000);
+
+		pcm_err(dpcm->substream->pcm,
+			"Period size (%lu frames) of loopback device is not corresponding to timer resolution (%lu nsec = %lu frames) of card timer %d,%d,%d. Use period size of %lu frames for loopback device.",
+			runtime->period_size, resolution, period_size,
+			cable->snd_timer.id.card,
+			cable->snd_timer.id.device,
+			cable->snd_timer.id.subdevice,
+			period_size);
+		return -EINVAL;
+	}
+	return 0;
+}
+
+static void loopback_snd_timer_period_elapsed(struct loopback_cable *cable,
+					      int event,
+					      unsigned long resolution)
+{
+	struct loopback_pcm *dpcm_play, *dpcm_capt;
+	struct snd_pcm_substream *substream_play, *substream_capt;
+	struct snd_pcm_runtime *valid_runtime;
+	unsigned int running, elapsed_bytes;
+	unsigned long flags;
+
+	spin_lock_irqsave(&cable->lock, flags);
+	running = cable->running ^ cable->pause;
+	/* no need to do anything if no stream is running */
+	if (!running) {
+		spin_unlock_irqrestore(&cable->lock, flags);
+		return;
+	}
+
+	dpcm_play = cable->streams[SNDRV_PCM_STREAM_PLAYBACK];
+	dpcm_capt = cable->streams[SNDRV_PCM_STREAM_CAPTURE];
+	substream_play = (running & (1 << SNDRV_PCM_STREAM_PLAYBACK)) ?
+			dpcm_play->substream : NULL;
+	substream_capt = (running & (1 << SNDRV_PCM_STREAM_CAPTURE)) ?
+			dpcm_capt->substream : NULL;
+
+	if (event == SNDRV_TIMER_EVENT_MSTOP) {
+		if (!dpcm_play ||
+		    dpcm_play->substream->runtime->status->state !=
+				SNDRV_PCM_STATE_DRAINING) {
+			spin_unlock_irqrestore(&cable->lock, flags);
+			return;
+		}
+	}
+
+	valid_runtime = (running & (1 << SNDRV_PCM_STREAM_PLAYBACK)) ?
+				dpcm_play->substream->runtime :
+				dpcm_capt->substream->runtime;
+
+	/* resolution is only valid for SNDRV_TIMER_EVENT_TICK events */
+	if (event == SNDRV_TIMER_EVENT_TICK) {
+		/* The hardware rules guarantee that playback and capture period
+		 * are the same. Therefore only one device has to be checked
+		 * here.
+		 */
+		if (loopback_snd_timer_check_resolution(valid_runtime,
+							resolution) < 0) {
+			spin_unlock_irqrestore(&cable->lock, flags);
+			if (substream_play)
+				snd_pcm_stop_xrun(substream_play);
+			if (substream_capt)
+				snd_pcm_stop_xrun(substream_capt);
+			return;
+		}
+	}
+
+	elapsed_bytes = frames_to_bytes(valid_runtime,
+					valid_runtime->period_size);
+	/* The same timer interrupt is used for playback and capture device */
+	if ((running & (1 << SNDRV_PCM_STREAM_PLAYBACK)) &&
+	    (running & (1 << SNDRV_PCM_STREAM_CAPTURE))) {
+		copy_play_buf(dpcm_play, dpcm_capt, elapsed_bytes);
+		bytepos_finish(dpcm_play, elapsed_bytes);
+		bytepos_finish(dpcm_capt, elapsed_bytes);
+	} else if (running & (1 << SNDRV_PCM_STREAM_PLAYBACK)) {
+		bytepos_finish(dpcm_play, elapsed_bytes);
+	} else if (running & (1 << SNDRV_PCM_STREAM_CAPTURE)) {
+		clear_capture_buf(dpcm_capt, elapsed_bytes);
+		bytepos_finish(dpcm_capt, elapsed_bytes);
+	}
+	spin_unlock_irqrestore(&cable->lock, flags);
+
+	if (substream_play)
+		snd_pcm_period_elapsed(substream_play);
+	if (substream_capt)
+		snd_pcm_period_elapsed(substream_capt);
+}
+
+static void loopback_snd_timer_function(struct snd_timer_instance *timeri,
+					unsigned long resolution,
+					unsigned long ticks)
+{
+	struct loopback_cable *cable = timeri->callback_data;
+
+	loopback_snd_timer_period_elapsed(cable, SNDRV_TIMER_EVENT_TICK,
+					  resolution);
+}
+
+static void loopback_snd_timer_tasklet(unsigned long arg)
+{
+	struct snd_timer_instance *timeri = (struct snd_timer_instance *)arg;
+	struct loopback_cable *cable = timeri->callback_data;
+
+	loopback_snd_timer_period_elapsed(cable, SNDRV_TIMER_EVENT_MSTOP, 0);
+}
+
+static void loopback_snd_timer_event(struct snd_timer_instance *timeri,
+				     int event,
+				     struct timespec *tstamp,
+				     unsigned long resolution)
+{
+	/* Do not lock cable->lock here because timer->lock is already hold.
+	 * There are other functions which first lock cable->lock and than
+	 * timer->lock e.g.
+	 * loopback_trigger()
+	 * spin_lock(&cable->lock)
+	 * loopback_snd_timer_start()
+	 * snd_timer_start()
+	 * spin_lock(&timer->lock)
+	 * Therefore when using the oposit order of locks here it could result
+	 * in a deadlock.
+	 */
+
+	if (event == SNDRV_TIMER_EVENT_MSTOP) {
+		struct loopback_cable *cable = timeri->callback_data;
+
+		/* sound card of the timer was stopped. Therefore there will not
+		 * be any further timer callbacks. Due to this forward audio
+		 * data from here if in draining state. When still in running
+		 * state the streaming will be aborted by the usual timeout. It
+		 * should not be aborted here because may be the timer sound
+		 * card does only a recovery and the timer is back soon.
+		 * This tasklet triggers loopback_snd_timer_tasklet()
+		 */
+		tasklet_schedule(&cable->snd_timer.event_tasklet);
+	}
+}
+
+static void loopback_jiffies_timer_dpcm_info(struct loopback_pcm *dpcm,
+					     struct snd_info_buffer *buffer)
+{
+	snd_iprintf(buffer, "    update_pending:\t%u\n",
+		    dpcm->period_update_pending);
+	snd_iprintf(buffer, "    irq_pos:\t\t%u\n", dpcm->irq_pos);
+	snd_iprintf(buffer, "    period_frac:\t%u\n", dpcm->period_size_frac);
+	snd_iprintf(buffer, "    last_jiffies:\t%lu (%lu)\n",
+		    dpcm->last_jiffies, jiffies);
+	snd_iprintf(buffer, "    timer_expires:\t%lu\n", dpcm->timer.expires);
+}
+
+static void loopback_snd_timer_dpcm_info(struct loopback_pcm *dpcm,
+					 struct snd_info_buffer *buffer)
+{
+	struct loopback_cable *cable = dpcm->cable;
+
+	snd_iprintf(buffer, "    sound timer:\thw:%d,%d,%d\n",
+		    cable->snd_timer.id.card,
+		    cable->snd_timer.id.device,
+		    cable->snd_timer.id.subdevice);
+	snd_iprintf(buffer, "    timer open:\t\t%s\n",
+		    (cable->snd_timer.stream == SNDRV_PCM_STREAM_CAPTURE) ?
+			    "capture" : "playback");
+}
+
 static snd_pcm_uframes_t loopback_pointer(struct snd_pcm_substream *substream)
 {
 	struct snd_pcm_runtime *runtime = substream->runtime;
@@ -536,7 +867,8 @@ static snd_pcm_uframes_t loopback_pointer(struct snd_pcm_substream *substream)
 	snd_pcm_uframes_t pos;
 
 	spin_lock(&dpcm->cable->lock);
-	loopback_pos_update(dpcm->cable);
+	if (dpcm->cable->ops->pos_update)
+		dpcm->cable->ops->pos_update(dpcm->cable);
 	pos = dpcm->buf_pos;
 	spin_unlock(&dpcm->cable->lock);
 	return bytes_to_frames(runtime, pos);
@@ -576,8 +908,7 @@ static void loopback_runtime_free(struct snd_pcm_runtime *runtime)
 static int loopback_hw_params(struct snd_pcm_substream *substream,
 			      struct snd_pcm_hw_params *params)
 {
-	return snd_pcm_lib_alloc_vmalloc_buffer(substream,
-						params_buffer_bytes(params));
+	return snd_pcm_lib_malloc_pages(substream, params_buffer_bytes(params));
 }
 
 static int loopback_hw_free(struct snd_pcm_substream *substream)
@@ -589,7 +920,7 @@ static int loopback_hw_free(struct snd_pcm_substream *substream)
 	mutex_lock(&dpcm->loopback->cable_lock);
 	cable->valid &= ~(1 << substream->stream);
 	mutex_unlock(&dpcm->loopback->cable_lock);
-	return snd_pcm_lib_free_vmalloc_buffer(substream);
+	return snd_pcm_lib_free_pages(substream);
 }
 
 static unsigned int get_cable_index(struct snd_pcm_substream *substream)
@@ -647,6 +978,23 @@ static int rule_channels(struct snd_pcm_hw_params *params,
 	return snd_interval_refine(hw_param_interval(params, rule->var), &t);
 }
 
+static int rule_period_bytes(struct snd_pcm_hw_params *params,
+			     struct snd_pcm_hw_rule *rule)
+{
+	struct loopback_pcm *dpcm = rule->private;
+	struct loopback_cable *cable = dpcm->cable;
+	struct snd_interval t;
+
+	mutex_lock(&dpcm->loopback->cable_lock);
+	t.min = cable->hw.period_bytes_min;
+	t.max = cable->hw.period_bytes_max;
+	mutex_unlock(&dpcm->loopback->cable_lock);
+	t.openmin = 0;
+	t.openmax = 0;
+	t.integer = 0;
+	return snd_interval_refine(hw_param_interval(params, rule->var), &t);
+}
+
 static void free_cable(struct snd_pcm_substream *substream)
 {
 	struct loopback *loopback = substream->private_data;
@@ -662,12 +1010,183 @@ static void free_cable(struct snd_pcm_substream *substream)
 		cable->streams[substream->stream] = NULL;
 		spin_unlock_irq(&cable->lock);
 	} else {
+		struct loopback_pcm *dpcm = substream->runtime->private_data;
+
+		if (cable->ops && cable->ops->close_cable && dpcm)
+			cable->ops->close_cable(dpcm);
 		/* free the cable */
 		loopback->cables[substream->number][dev] = NULL;
 		kfree(cable);
 	}
 }
 
+static int loopback_jiffies_timer_open(struct loopback_pcm *dpcm)
+{
+	timer_setup(&dpcm->timer, loopback_jiffies_timer_function, 0);
+
+	return 0;
+}
+
+static struct loopback_ops loopback_jiffies_timer_ops = {
+	.open = loopback_jiffies_timer_open,
+	.start = loopback_jiffies_timer_start,
+	.stop = loopback_jiffies_timer_stop,
+	.stop_sync = loopback_jiffies_timer_stop_sync,
+	.close_substream = loopback_jiffies_timer_stop_sync,
+	.pos_update = loopback_jiffies_timer_pos_update,
+	.dpcm_info = loopback_jiffies_timer_dpcm_info,
+};
+
+static int loopback_parse_timer_id(const char *str,
+				   struct snd_timer_id *tid)
+{
+	/* [<pref>:](<card name>|<card idx>)[{.,}<dev idx>[{.,}<subdev idx>]] */
+	const char * const sep_dev = ".,";
+	const char * const sep_pref = ":";
+	const char *name = str;
+	char *sep, save = '\0';
+	int card_idx = 0, dev = 0, subdev = 0;
+	int err;
+
+	sep = strpbrk(str, sep_pref);
+	if (sep)
+		name = sep + 1;
+	sep = strpbrk(name, sep_dev);
+	if (sep) {
+		save = *sep;
+		*sep = '\0';
+	}
+	err = kstrtoint(name, 0, &card_idx);
+	if (err == -EINVAL) {
+		/* Must be the name, not number */
+		for (card_idx = 0; card_idx < snd_ecards_limit; card_idx++) {
+			struct snd_card *card = snd_card_ref(card_idx);
+
+			if (card) {
+				if (!strcmp(card->id, name))
+					err = 0;
+				snd_card_unref(card);
+			}
+			if (!err)
+				break;
+		}
+	}
+	if (sep) {
+		*sep = save;
+		if (!err) {
+			char *sep2, save2 = '\0';
+
+			sep2 = strpbrk(sep + 1, sep_dev);
+			if (sep2) {
+				save2 = *sep2;
+				*sep2 = '\0';
+			}
+			err = kstrtoint(sep + 1, 0, &dev);
+			if (sep2) {
+				*sep2 = save2;
+				if (!err)
+					err = kstrtoint(sep2 + 1, 0, &subdev);
+			}
+		}
+	}
+	if (!err && tid) {
+		tid->card = card_idx;
+		tid->device = dev;
+		tid->subdevice = subdev;
+	}
+	return err;
+}
+
+/* call in loopback->cable_lock */
+static int loopback_snd_timer_open(struct loopback_pcm *dpcm)
+{
+	int err = 0;
+	struct snd_timer_id tid = {
+		.dev_class = SNDRV_TIMER_CLASS_PCM,
+		.dev_sclass = SNDRV_TIMER_SCLASS_APPLICATION,
+	};
+	struct snd_timer_instance *timeri;
+	struct loopback_cable *cable = dpcm->cable;
+
+	/* check if timer was already opened. It is only opened once
+	 * per playback and capture subdevice (aka cable).
+	 */
+	if (cable->snd_timer.instance)
+		goto exit;
+
+	err = loopback_parse_timer_id(dpcm->loopback->timer_source, &tid);
+	if (err < 0) {
+		pcm_err(dpcm->substream->pcm,
+			"Parsing timer source \'%s\' failed with %d",
+			dpcm->loopback->timer_source, err);
+		goto exit;
+	}
+
+	cable->snd_timer.stream = dpcm->substream->stream;
+	cable->snd_timer.id = tid;
+
+	timeri = snd_timer_instance_new(dpcm->loopback->card->id);
+	if (!timeri) {
+		err = -ENOMEM;
+		goto exit;
+	}
+	/* The callback has to be called from another tasklet. If
+	 * SNDRV_TIMER_IFLG_FAST is specified it will be called from the
+	 * snd_pcm_period_elapsed() call of the selected sound card.
+	 * snd_pcm_period_elapsed() helds snd_pcm_stream_lock_irqsave().
+	 * Due to our callback loopback_snd_timer_function() also calls
+	 * snd_pcm_period_elapsed() which calls snd_pcm_stream_lock_irqsave().
+	 * This would end up in a dead lock.
+	 */
+	timeri->flags |= SNDRV_TIMER_IFLG_AUTO;
+	timeri->callback = loopback_snd_timer_function;
+	timeri->callback_data = (void *)cable;
+	timeri->ccallback = loopback_snd_timer_event;
+
+	/* initialise a tasklet used for draining */
+	tasklet_init(&cable->snd_timer.event_tasklet,
+		     loopback_snd_timer_tasklet, (unsigned long)timeri);
+
+	/* The mutex loopback->cable_lock is kept locked.
+	 * Therefore snd_timer_open() cannot be called a second time
+	 * by the other device of the same cable.
+	 * Therefore the following issue cannot happen:
+	 * [proc1] Call loopback_timer_open() ->
+	 *	   Unlock cable->lock for snd_timer_close/open() call
+	 * [proc2] Call loopback_timer_open() -> snd_timer_open(),
+	 *	   snd_timer_start()
+	 * [proc1] Call snd_timer_open() and overwrite running timer
+	 *	   instance
+	 */
+	err = snd_timer_open(timeri, &cable->snd_timer.id, current->pid);
+	if (err < 0) {
+		pcm_err(dpcm->substream->pcm,
+			"snd_timer_open (%d,%d,%d) failed with %d",
+			cable->snd_timer.id.card,
+			cable->snd_timer.id.device,
+			cable->snd_timer.id.subdevice,
+			err);
+		snd_timer_instance_free(timeri);
+		goto exit;
+	}
+
+	cable->snd_timer.instance = timeri;
+
+exit:
+	return err;
+}
+
+/* stop_sync() is not required for sound timer because it does not need to be
+ * restarted in loopback_prepare() on Xrun recovery
+ */
+static struct loopback_ops loopback_snd_timer_ops = {
+	.open = loopback_snd_timer_open,
+	.start = loopback_snd_timer_start,
+	.stop = loopback_snd_timer_stop,
+	.close_cable = loopback_snd_timer_close_cable,
+	.dpcm_info = loopback_snd_timer_dpcm_info,
+};
+
 static int loopback_open(struct snd_pcm_substream *substream)
 {
 	struct snd_pcm_runtime *runtime = substream->runtime;
@@ -685,7 +1204,6 @@ static int loopback_open(struct snd_pcm_substream *substream)
 	}
 	dpcm->loopback = loopback;
 	dpcm->substream = substream;
-	timer_setup(&dpcm->timer, loopback_timer_function, 0);
 
 	cable = loopback->cables[substream->number][dev];
 	if (!cable) {
@@ -696,9 +1214,20 @@ static int loopback_open(struct snd_pcm_substream *substream)
 		}
 		spin_lock_init(&cable->lock);
 		cable->hw = loopback_pcm_hardware;
+		if (loopback->timer_source)
+			cable->ops = &loopback_snd_timer_ops;
+		else
+			cable->ops = &loopback_jiffies_timer_ops;
 		loopback->cables[substream->number][dev] = cable;
 	}
 	dpcm->cable = cable;
+	runtime->private_data = dpcm;
+
+	if (cable->ops->open) {
+		err = cable->ops->open(dpcm);
+		if (err < 0)
+			goto unlock;
+	}
 
 	snd_pcm_hw_constraint_integer(runtime, SNDRV_PCM_HW_PARAM_PERIODS);
 
@@ -724,7 +1253,22 @@ static int loopback_open(struct snd_pcm_substream *substream)
 	if (err < 0)
 		goto unlock;
 
-	runtime->private_data = dpcm;
+	/* In case of sound timer the period time of both devices of the same
+	 * loop has to be the same.
+	 * This rule only takes effect if a sound timer was chosen
+	 */
+	if (cable->snd_timer.instance) {
+		err = snd_pcm_hw_rule_add(runtime, 0,
+					  SNDRV_PCM_HW_PARAM_PERIOD_BYTES,
+					  rule_period_bytes, dpcm,
+					  SNDRV_PCM_HW_PARAM_PERIOD_BYTES, -1);
+		if (err < 0)
+			goto unlock;
+	}
+
+	/* loopback_runtime_free() has not to be called if kfree(dpcm) was
+	 * already called here. Otherwise it will end up with a double free.
+	 */
 	runtime->private_free = loopback_runtime_free;
 	if (get_notify(dpcm))
 		runtime->hw = loopback_pcm_hardware;
@@ -748,12 +1292,14 @@ static int loopback_close(struct snd_pcm_substream *substream)
 {
 	struct loopback *loopback = substream->private_data;
 	struct loopback_pcm *dpcm = substream->runtime->private_data;
+	int err = 0;
 
-	loopback_timer_stop_sync(dpcm);
+	if (dpcm->cable->ops->close_substream)
+		err = dpcm->cable->ops->close_substream(dpcm);
 	mutex_lock(&loopback->cable_lock);
 	free_cable(substream);
 	mutex_unlock(&loopback->cable_lock);
-	return 0;
+	return err;
 }
 
 static const struct snd_pcm_ops loopback_pcm_ops = {
@@ -765,7 +1311,6 @@ static const struct snd_pcm_ops loopback_pcm_ops = {
 	.prepare =	loopback_prepare,
 	.trigger =	loopback_trigger,
 	.pointer =	loopback_pointer,
-	.page =		snd_pcm_lib_get_vmalloc_page,
 };
 
 static int loopback_pcm_new(struct loopback *loopback,
@@ -780,6 +1325,8 @@ static int loopback_pcm_new(struct loopback *loopback,
 		return err;
 	snd_pcm_set_ops(pcm, SNDRV_PCM_STREAM_PLAYBACK, &loopback_pcm_ops);
 	snd_pcm_set_ops(pcm, SNDRV_PCM_STREAM_CAPTURE, &loopback_pcm_ops);
+	snd_pcm_lib_preallocate_pages_for_all(pcm, SNDRV_DMA_TYPE_VMALLOC,
+					      NULL, 0, 0);
 
 	pcm->private_data = loopback;
 	pcm->info_flags = 0;
@@ -1076,13 +1623,8 @@ static void print_dpcm_info(struct snd_info_buffer *buffer,
 	snd_iprintf(buffer, "    bytes_per_sec:\t%u\n", dpcm->pcm_bps);
 	snd_iprintf(buffer, "    sample_align:\t%u\n", dpcm->pcm_salign);
 	snd_iprintf(buffer, "    rate_shift:\t\t%u\n", dpcm->pcm_rate_shift);
-	snd_iprintf(buffer, "    update_pending:\t%u\n",
-						dpcm->period_update_pending);
-	snd_iprintf(buffer, "    irq_pos:\t\t%u\n", dpcm->irq_pos);
-	snd_iprintf(buffer, "    period_frac:\t%u\n", dpcm->period_size_frac);
-	snd_iprintf(buffer, "    last_jiffies:\t%lu (%lu)\n",
-					dpcm->last_jiffies, jiffies);
-	snd_iprintf(buffer, "    timer_expires:\t%lu\n", dpcm->timer.expires);
+	if (dpcm->cable->ops->dpcm_info)
+		dpcm->cable->ops->dpcm_info(dpcm, buffer);
 }
 
 static void print_substream_info(struct snd_info_buffer *buffer,
@@ -1118,7 +1660,7 @@ static void print_cable_info(struct snd_info_entry *entry,
 	mutex_unlock(&loopback->cable_lock);
 }
 
-static int loopback_proc_new(struct loopback *loopback, int cidx)
+static int loopback_cable_proc_new(struct loopback *loopback, int cidx)
 {
 	char name[32];
 
@@ -1127,6 +1669,48 @@ static int loopback_proc_new(struct loopback *loopback, int cidx)
 				    print_cable_info);
 }
 
+static void loopback_set_timer_source(struct loopback *loopback,
+				      const char *value)
+{
+	if (loopback->timer_source) {
+		devm_kfree(loopback->card->dev, loopback->timer_source);
+		loopback->timer_source = NULL;
+	}
+	if (value && *value)
+		loopback->timer_source = devm_kstrdup(loopback->card->dev,
+						      value, GFP_KERNEL);
+}
+
+static void print_timer_source_info(struct snd_info_entry *entry,
+				    struct snd_info_buffer *buffer)
+{
+	struct loopback *loopback = entry->private_data;
+
+	mutex_lock(&loopback->cable_lock);
+	snd_iprintf(buffer, "%s\n",
+		    loopback->timer_source ? loopback->timer_source : "");
+	mutex_unlock(&loopback->cable_lock);
+}
+
+static void change_timer_source_info(struct snd_info_entry *entry,
+				     struct snd_info_buffer *buffer)
+{
+	struct loopback *loopback = entry->private_data;
+	char line[64];
+
+	mutex_lock(&loopback->cable_lock);
+	if (!snd_info_get_line(buffer, line, sizeof(line)))
+		loopback_set_timer_source(loopback, strim(line));
+	mutex_unlock(&loopback->cable_lock);
+}
+
+static int loopback_timer_source_proc_new(struct loopback *loopback)
+{
+	return snd_card_rw_proc_new(loopback->card, "timer_source", loopback,
+				    print_timer_source_info,
+				    change_timer_source_info);
+}
+
 static int loopback_probe(struct platform_device *devptr)
 {
 	struct snd_card *card;
@@ -1146,6 +1730,8 @@ static int loopback_probe(struct platform_device *devptr)
 		pcm_substreams[dev] = MAX_PCM_SUBSTREAMS;
 	
 	loopback->card = card;
+	loopback_set_timer_source(loopback, timer_source[dev]);
+
 	mutex_init(&loopback->cable_lock);
 
 	err = loopback_pcm_new(loopback, 0, pcm_substreams[dev]);
@@ -1157,8 +1743,9 @@ static int loopback_probe(struct platform_device *devptr)
 	err = loopback_mixer_new(loopback, pcm_notify[dev] ? 1 : 0);
 	if (err < 0)
 		goto __nodev;
-	loopback_proc_new(loopback, 0);
-	loopback_proc_new(loopback, 1);
+	loopback_cable_proc_new(loopback, 0);
+	loopback_cable_proc_new(loopback, 1);
+	loopback_timer_source_proc_new(loopback);
 	strcpy(card->driver, "Loopback");
 	strcpy(card->shortname, "Loopback");
 	sprintf(card->longname, "Loopback %i", dev + 1);
diff --git a/sound/drivers/dummy.c b/sound/drivers/dummy.c
index aee7c04d49e5..022a0db692e0 100644
--- a/sound/drivers/dummy.c
+++ b/sound/drivers/dummy.c
@@ -702,7 +702,7 @@ static int snd_card_dummy_pcm(struct snd_dummy *dummy, int device,
 	if (!fake_buffer) {
 		snd_pcm_lib_preallocate_pages_for_all(pcm,
 			SNDRV_DMA_TYPE_CONTINUOUS,
-			snd_dma_continuous_data(GFP_KERNEL),
+			NULL,
 			0, 64*1024);
 	}
 	return 0;
diff --git a/sound/drivers/ml403-ac97cr.c b/sound/drivers/ml403-ac97cr.c
index a3c1c064d1b5..70a6d1832698 100644
--- a/sound/drivers/ml403-ac97cr.c
+++ b/sound/drivers/ml403-ac97cr.c
@@ -1242,7 +1242,7 @@ snd_ml403_ac97cr_pcm(struct snd_ml403_ac97cr *ml403_ac97cr, int device)
 	ml403_ac97cr->pcm = pcm;
 
 	snd_pcm_lib_preallocate_pages_for_all(pcm, SNDRV_DMA_TYPE_CONTINUOUS,
-					  snd_dma_continuous_data(GFP_KERNEL),
+					  NULL,
 					  64 * 1024,
 					  128 * 1024);
 	return 0;
diff --git a/sound/drivers/pcsp/pcsp_lib.c b/sound/drivers/pcsp/pcsp_lib.c
index 8f0f05bbc081..f91316bf01cb 100644
--- a/sound/drivers/pcsp/pcsp_lib.c
+++ b/sound/drivers/pcsp/pcsp_lib.c
@@ -352,8 +352,8 @@ int snd_pcsp_new_pcm(struct snd_pcsp *chip)
 
 	snd_pcm_lib_preallocate_pages_for_all(chip->pcm,
 					      SNDRV_DMA_TYPE_CONTINUOUS,
-					      snd_dma_continuous_data
-					      (GFP_KERNEL), PCSP_BUFFER_SIZE,
+					      NULL,
+					      PCSP_BUFFER_SIZE,
 					      PCSP_BUFFER_SIZE);
 
 	return 0;
diff --git a/sound/drivers/vx/vx_pcm.c b/sound/drivers/vx/vx_pcm.c
index 4705c50fbf4f..f17e0a76c73c 100644
--- a/sound/drivers/vx/vx_pcm.c
+++ b/sound/drivers/vx/vx_pcm.c
@@ -778,8 +778,7 @@ static snd_pcm_uframes_t vx_pcm_playback_pointer(struct snd_pcm_substream *subs)
 static int vx_pcm_hw_params(struct snd_pcm_substream *subs,
 				     struct snd_pcm_hw_params *hw_params)
 {
-	return snd_pcm_lib_alloc_vmalloc_32_buffer
-					(subs, params_buffer_bytes(hw_params));
+	return snd_pcm_lib_malloc_pages(subs, params_buffer_bytes(hw_params));
 }
 
 /*
@@ -787,7 +786,7 @@ static int vx_pcm_hw_params(struct snd_pcm_substream *subs,
  */
 static int vx_pcm_hw_free(struct snd_pcm_substream *subs)
 {
-	return snd_pcm_lib_free_vmalloc_buffer(subs);
+	return snd_pcm_lib_free_pages(subs);
 }
 
 /*
@@ -867,7 +866,6 @@ static const struct snd_pcm_ops vx_pcm_playback_ops = {
 	.prepare =	vx_pcm_prepare,
 	.trigger =	vx_pcm_trigger,
 	.pointer =	vx_pcm_playback_pointer,
-	.page =		snd_pcm_lib_get_vmalloc_page,
 };
 
 
@@ -1088,7 +1086,6 @@ static const struct snd_pcm_ops vx_pcm_capture_ops = {
 	.prepare =	vx_pcm_prepare,
 	.trigger =	vx_pcm_trigger,
 	.pointer =	vx_pcm_capture_pointer,
-	.page =		snd_pcm_lib_get_vmalloc_page,
 };
 
 
@@ -1233,6 +1230,9 @@ int snd_vx_pcm_new(struct vx_core *chip)
 			snd_pcm_set_ops(pcm, SNDRV_PCM_STREAM_PLAYBACK, &vx_pcm_playback_ops);
 		if (ins)
 			snd_pcm_set_ops(pcm, SNDRV_PCM_STREAM_CAPTURE, &vx_pcm_capture_ops);
+		snd_pcm_lib_preallocate_pages_for_all(pcm, SNDRV_DMA_TYPE_VMALLOC,
+						      snd_dma_continuous_data(GFP_KERNEL | GFP_DMA32),
+						      0, 0);
 
 		pcm->private_data = chip;
 		pcm->private_free = snd_vx_pcm_free;
diff --git a/sound/firewire/Kconfig b/sound/firewire/Kconfig
index b0a904cdb932..995c2cefc222 100644
--- a/sound/firewire/Kconfig
+++ b/sound/firewire/Kconfig
@@ -77,7 +77,7 @@ config SND_BEBOB
 	tristate "BridgeCo DM1000/DM1100/DM1500 with BeBoB firmware"
 	select SND_FIREWIRE_LIB
 	select SND_HWDEP
-        help
+	help
 	 Say Y here to include support for FireWire devices based
 	 on BridgeCo DM1000/DM1100/DM1500 with BeBoB firmware:
 	  * Edirol FA-66/FA-101
@@ -111,8 +111,8 @@ config SND_BEBOB
 	  * M-Audio FireWire 1814/ProjectMix IO
 	  * Digidesign Mbox 2 Pro
 
-          To compile this driver as a module, choose M here: the module
-          will be called snd-bebob.
+	  To compile this driver as a module, choose M here: the module
+	  will be called snd-bebob.
 
 config SND_FIREWIRE_DIGI00X
 	tristate "Digidesign Digi 002/003 family support"
diff --git a/sound/firewire/amdtp-stream.c b/sound/firewire/amdtp-stream.c
index e50e28f77e74..37d38efb4c87 100644
--- a/sound/firewire/amdtp-stream.c
+++ b/sound/firewire/amdtp-stream.c
@@ -9,6 +9,7 @@
 #include <linux/device.h>
 #include <linux/err.h>
 #include <linux/firewire.h>
+#include <linux/firewire-constants.h>
 #include <linux/module.h>
 #include <linux/slab.h>
 #include <sound/pcm.h>
@@ -52,10 +53,6 @@
 #define CIP_FMT_AM		0x10
 #define AMDTP_FDF_NO_DATA	0xff
 
-/* TODO: make these configurable */
-#define INTERRUPT_INTERVAL	16
-#define QUEUE_LENGTH		48
-
 // For iso header, tstamp and 2 CIP header.
 #define IR_CTX_HEADER_SIZE_CIP		16
 // For iso header and tstamp.
@@ -180,6 +177,8 @@ int amdtp_stream_add_pcm_hw_constraints(struct amdtp_stream *s,
 					struct snd_pcm_runtime *runtime)
 {
 	struct snd_pcm_hardware *hw = &runtime->hw;
+	unsigned int ctx_header_size;
+	unsigned int maximum_usec_per_period;
 	int err;
 
 	hw->info = SNDRV_PCM_INFO_BATCH |
@@ -200,19 +199,36 @@ int amdtp_stream_add_pcm_hw_constraints(struct amdtp_stream *s,
 	hw->period_bytes_max = hw->period_bytes_min * 2048;
 	hw->buffer_bytes_max = hw->period_bytes_max * hw->periods_min;
 
-	/*
-	 * Currently firewire-lib processes 16 packets in one software
-	 * interrupt callback. This equals to 2msec but actually the
-	 * interval of the interrupts has a jitter.
-	 * Additionally, even if adding a constraint to fit period size to
-	 * 2msec, actual calculated frames per period doesn't equal to 2msec,
-	 * depending on sampling rate.
-	 * Anyway, the interval to call snd_pcm_period_elapsed() cannot 2msec.
-	 * Here let us use 5msec for safe period interrupt.
-	 */
+	// Linux driver for 1394 OHCI controller voluntarily flushes isoc
+	// context when total size of accumulated context header reaches
+	// PAGE_SIZE. This kicks tasklet for the isoc context and brings
+	// callback in the middle of scheduled interrupts.
+	// Although AMDTP streams in the same domain use the same events per
+	// IRQ, use the largest size of context header between IT/IR contexts.
+	// Here, use the value of context header in IR context is for both
+	// contexts.
+	if (!(s->flags & CIP_NO_HEADER))
+		ctx_header_size = IR_CTX_HEADER_SIZE_CIP;
+	else
+		ctx_header_size = IR_CTX_HEADER_SIZE_NO_CIP;
+	maximum_usec_per_period = USEC_PER_SEC * PAGE_SIZE /
+				  CYCLES_PER_SECOND / ctx_header_size;
+
+	// In IEC 61883-6, one isoc packet can transfer events up to the value
+	// of syt interval. This comes from the interval of isoc cycle. As 1394
+	// OHCI controller can generate hardware IRQ per isoc packet, the
+	// interval is 125 usec.
+	// However, there are two ways of transmission in IEC 61883-6; blocking
+	// and non-blocking modes. In blocking mode, the sequence of isoc packet
+	// includes 'empty' or 'NODATA' packets which include no event. In
+	// non-blocking mode, the number of events per packet is variable up to
+	// the syt interval.
+	// Due to the above protocol design, the minimum PCM frames per
+	// interrupt should be double of the value of syt interval, thus it is
+	// 250 usec.
 	err = snd_pcm_hw_constraint_minmax(runtime,
 					   SNDRV_PCM_HW_PARAM_PERIOD_TIME,
-					   5000, UINT_MAX);
+					   250, maximum_usec_per_period);
 	if (err < 0)
 		goto end;
 
@@ -436,11 +452,12 @@ static void pcm_period_tasklet(unsigned long data)
 		snd_pcm_period_elapsed(pcm);
 }
 
-static int queue_packet(struct amdtp_stream *s, struct fw_iso_packet *params)
+static int queue_packet(struct amdtp_stream *s, struct fw_iso_packet *params,
+			bool sched_irq)
 {
 	int err;
 
-	params->interrupt = IS_ALIGNED(s->packet_index + 1, INTERRUPT_INTERVAL);
+	params->interrupt = sched_irq;
 	params->tag = s->tag;
 	params->sy = 0;
 
@@ -451,18 +468,18 @@ static int queue_packet(struct amdtp_stream *s, struct fw_iso_packet *params)
 		goto end;
 	}
 
-	if (++s->packet_index >= QUEUE_LENGTH)
+	if (++s->packet_index >= s->queue_size)
 		s->packet_index = 0;
 end:
 	return err;
 }
 
 static inline int queue_out_packet(struct amdtp_stream *s,
-				   struct fw_iso_packet *params)
+				   struct fw_iso_packet *params, bool sched_irq)
 {
 	params->skip =
 		!!(params->header_length == 0 && params->payload_length == 0);
-	return queue_packet(s, params);
+	return queue_packet(s, params, sched_irq);
 }
 
 static inline int queue_in_packet(struct amdtp_stream *s,
@@ -472,7 +489,7 @@ static inline int queue_in_packet(struct amdtp_stream *s,
 	params->header_length = s->ctx_data.tx.ctx_header_size;
 	params->payload_length = s->ctx_data.tx.max_ctx_payload_length;
 	params->skip = false;
-	return queue_packet(s, params);
+	return queue_packet(s, params, false);
 }
 
 static void generate_cip_header(struct amdtp_stream *s, __be32 cip_header[2],
@@ -669,13 +686,14 @@ static inline u32 increment_cycle_count(u32 cycle, unsigned int addend)
 }
 
 // Align to actual cycle count for the packet which is going to be scheduled.
-// This module queued the same number of isochronous cycle as QUEUE_LENGTH to
-// skip isochronous cycle, therefore it's OK to just increment the cycle by
-// QUEUE_LENGTH for scheduled cycle.
-static inline u32 compute_it_cycle(const __be32 ctx_header_tstamp)
+// This module queued the same number of isochronous cycle as the size of queue
+// to kip isochronous cycle, therefore it's OK to just increment the cycle by
+// the size of queue for scheduled cycle.
+static inline u32 compute_it_cycle(const __be32 ctx_header_tstamp,
+				   unsigned int queue_size)
 {
 	u32 cycle = compute_cycle_count(ctx_header_tstamp);
-	return increment_cycle_count(cycle, QUEUE_LENGTH);
+	return increment_cycle_count(cycle, queue_size);
 }
 
 static int generate_device_pkt_descs(struct amdtp_stream *s,
@@ -689,7 +707,7 @@ static int generate_device_pkt_descs(struct amdtp_stream *s,
 
 	for (i = 0; i < packets; ++i) {
 		struct pkt_desc *desc = descs + i;
-		unsigned int index = (s->packet_index + i) % QUEUE_LENGTH;
+		unsigned int index = (s->packet_index + i) % s->queue_size;
 		unsigned int cycle;
 		unsigned int payload_length;
 		unsigned int data_blocks;
@@ -730,9 +748,9 @@ static void generate_ideal_pkt_descs(struct amdtp_stream *s,
 
 	for (i = 0; i < packets; ++i) {
 		struct pkt_desc *desc = descs + i;
-		unsigned int index = (s->packet_index + i) % QUEUE_LENGTH;
+		unsigned int index = (s->packet_index + i) % s->queue_size;
 
-		desc->cycle = compute_it_cycle(*ctx_header);
+		desc->cycle = compute_it_cycle(*ctx_header, s->queue_size);
 		desc->syt = calculate_syt(s, desc->cycle);
 		desc->data_blocks = calculate_data_blocks(s, desc->syt);
 
@@ -773,22 +791,40 @@ static void process_ctx_payloads(struct amdtp_stream *s,
 		update_pcm_pointers(s, pcm, pcm_frames);
 }
 
+static void amdtp_stream_master_callback(struct fw_iso_context *context,
+					 u32 tstamp, size_t header_length,
+					 void *header, void *private_data);
+
+static void amdtp_stream_master_first_callback(struct fw_iso_context *context,
+					u32 tstamp, size_t header_length,
+					void *header, void *private_data);
+
 static void out_stream_callback(struct fw_iso_context *context, u32 tstamp,
 				size_t header_length, void *header,
 				void *private_data)
 {
 	struct amdtp_stream *s = private_data;
 	const __be32 *ctx_header = header;
-	unsigned int packets = header_length / sizeof(*ctx_header);
+	unsigned int events_per_period = s->ctx_data.rx.events_per_period;
+	unsigned int event_count = s->ctx_data.rx.event_count;
+	unsigned int packets;
+	bool is_irq_target;
 	int i;
 
 	if (s->packet_index < 0)
 		return;
 
+	// Calculate the number of packets in buffer and check XRUN.
+	packets = header_length / sizeof(*ctx_header);
+
 	generate_ideal_pkt_descs(s, s->pkt_descs, ctx_header, packets);
 
 	process_ctx_payloads(s, s->pkt_descs, packets);
 
+	is_irq_target =
+		!!(context->callback.sc == amdtp_stream_master_callback ||
+		   context->callback.sc == amdtp_stream_master_first_callback);
+
 	for (i = 0; i < packets; ++i) {
 		const struct pkt_desc *desc = s->pkt_descs + i;
 		unsigned int syt;
@@ -796,6 +832,7 @@ static void out_stream_callback(struct fw_iso_context *context, u32 tstamp,
 			struct fw_iso_packet params;
 			__be32 header[IT_PKT_HEADER_SIZE_CIP / sizeof(__be32)];
 		} template = { {0}, {0} };
+		bool sched_irq = false;
 
 		if (s->ctx_data.rx.syt_override < 0)
 			syt = desc->syt;
@@ -806,13 +843,21 @@ static void out_stream_callback(struct fw_iso_context *context, u32 tstamp,
 				    desc->data_blocks, desc->data_block_counter,
 				    syt, i);
 
-		if (queue_out_packet(s, &template.params) < 0) {
+		if (is_irq_target) {
+			event_count += desc->data_blocks;
+			if (event_count >= events_per_period) {
+				event_count -= events_per_period;
+				sched_irq = true;
+			}
+		}
+
+		if (queue_out_packet(s, &template.params, sched_irq) < 0) {
 			cancel_stream(s);
 			return;
 		}
 	}
 
-	fw_iso_context_queue_flush(s->context);
+	s->ctx_data.rx.event_count = event_count;
 }
 
 static void in_stream_callback(struct fw_iso_context *context, u32 tstamp,
@@ -820,15 +865,15 @@ static void in_stream_callback(struct fw_iso_context *context, u32 tstamp,
 			       void *private_data)
 {
 	struct amdtp_stream *s = private_data;
-	unsigned int packets;
 	__be32 *ctx_header = header;
+	unsigned int packets;
 	int i;
 	int err;
 
 	if (s->packet_index < 0)
 		return;
 
-	// The number of packets in buffer.
+	// Calculate the number of packets in buffer and check XRUN.
 	packets = header_length / s->ctx_data.tx.ctx_header_size;
 
 	err = generate_device_pkt_descs(s, s->pkt_descs, ctx_header, packets);
@@ -849,11 +894,40 @@ static void in_stream_callback(struct fw_iso_context *context, u32 tstamp,
 			return;
 		}
 	}
+}
+
+static void amdtp_stream_master_callback(struct fw_iso_context *context,
+					 u32 tstamp, size_t header_length,
+					 void *header, void *private_data)
+{
+	struct amdtp_domain *d = private_data;
+	struct amdtp_stream *irq_target = d->irq_target;
+	struct amdtp_stream *s;
+
+	out_stream_callback(context, tstamp, header_length, header, irq_target);
+	if (amdtp_streaming_error(irq_target))
+		goto error;
+
+	list_for_each_entry(s, &d->streams, list) {
+		if (s != irq_target && amdtp_stream_running(s)) {
+			fw_iso_context_flush_completions(s->context);
+			if (amdtp_streaming_error(s))
+				goto error;
+		}
+	}
 
-	fw_iso_context_queue_flush(s->context);
+	return;
+error:
+	if (amdtp_stream_running(irq_target))
+		cancel_stream(irq_target);
+
+	list_for_each_entry(s, &d->streams, list) {
+		if (amdtp_stream_running(s))
+			cancel_stream(s);
+	}
 }
 
-/* this is executed one time */
+// this is executed one time.
 static void amdtp_stream_first_callback(struct fw_iso_context *context,
 					u32 tstamp, size_t header_length,
 					void *header, void *private_data)
@@ -874,7 +948,7 @@ static void amdtp_stream_first_callback(struct fw_iso_context *context,
 
 		context->callback.sc = in_stream_callback;
 	} else {
-		cycle = compute_it_cycle(*ctx_header);
+		cycle = compute_it_cycle(*ctx_header, s->queue_size);
 
 		context->callback.sc = out_stream_callback;
 	}
@@ -884,17 +958,42 @@ static void amdtp_stream_first_callback(struct fw_iso_context *context,
 	context->callback.sc(context, tstamp, header_length, header, s);
 }
 
+static void amdtp_stream_master_first_callback(struct fw_iso_context *context,
+					       u32 tstamp, size_t header_length,
+					       void *header, void *private_data)
+{
+	struct amdtp_domain *d = private_data;
+	struct amdtp_stream *s = d->irq_target;
+	const __be32 *ctx_header = header;
+
+	s->callbacked = true;
+	wake_up(&s->callback_wait);
+
+	s->start_cycle = compute_it_cycle(*ctx_header, s->queue_size);
+
+	context->callback.sc = amdtp_stream_master_callback;
+
+	context->callback.sc(context, tstamp, header_length, header, d);
+}
+
 /**
  * amdtp_stream_start - start transferring packets
  * @s: the AMDTP stream to start
  * @channel: the isochronous channel on the bus
  * @speed: firewire speed code
+ * @d: the AMDTP domain to which the AMDTP stream belongs
+ * @is_irq_target: whether isoc context for the AMDTP stream is used to generate
+ *		   hardware IRQ.
+ * @start_cycle: the isochronous cycle to start the context. Start immediately
+ *		 if negative value is given.
  *
  * The stream cannot be started until it has been configured with
  * amdtp_stream_set_parameters() and it must be started before any PCM or MIDI
  * device can be started.
  */
-static int amdtp_stream_start(struct amdtp_stream *s, int channel, int speed)
+static int amdtp_stream_start(struct amdtp_stream *s, int channel, int speed,
+			      struct amdtp_domain *d, bool is_irq_target,
+			      int start_cycle)
 {
 	static const struct {
 		unsigned int data_block;
@@ -908,10 +1007,15 @@ static int amdtp_stream_start(struct amdtp_stream *s, int channel, int speed)
 		[CIP_SFC_88200]  = {  0,   67 },
 		[CIP_SFC_176400] = {  0,   67 },
 	};
+	unsigned int events_per_buffer = d->events_per_buffer;
+	unsigned int events_per_period = d->events_per_period;
+	unsigned int idle_irq_interval;
 	unsigned int ctx_header_size;
 	unsigned int max_ctx_payload_size;
 	enum dma_data_direction dir;
 	int type, tag, err;
+	fw_iso_callback_t ctx_cb;
+	void *ctx_data;
 
 	mutex_lock(&s->mutex);
 
@@ -922,6 +1026,12 @@ static int amdtp_stream_start(struct amdtp_stream *s, int channel, int speed)
 	}
 
 	if (s->direction == AMDTP_IN_STREAM) {
+		// NOTE: IT context should be used for constant IRQ.
+		if (is_irq_target) {
+			err = -EINVAL;
+			goto err_unlock;
+		}
+
 		s->data_block_counter = UINT_MAX;
 	} else {
 		entry = &initial_state[s->sfc];
@@ -953,14 +1063,37 @@ static int amdtp_stream_start(struct amdtp_stream *s, int channel, int speed)
 			max_ctx_payload_size -= IT_PKT_HEADER_SIZE_CIP;
 	}
 
-	err = iso_packets_buffer_init(&s->buffer, s->unit, QUEUE_LENGTH,
+	// This is a case that AMDTP streams in domain run just for MIDI
+	// substream. Use the number of events equivalent to 10 msec as
+	// interval of hardware IRQ.
+	if (events_per_period == 0)
+		events_per_period = amdtp_rate_table[s->sfc] / 100;
+	if (events_per_buffer == 0)
+		events_per_buffer = events_per_period * 3;
+
+	idle_irq_interval = DIV_ROUND_UP(CYCLES_PER_SECOND * events_per_period,
+					 amdtp_rate_table[s->sfc]);
+	s->queue_size = DIV_ROUND_UP(CYCLES_PER_SECOND * events_per_buffer,
+				     amdtp_rate_table[s->sfc]);
+
+	err = iso_packets_buffer_init(&s->buffer, s->unit, s->queue_size,
 				      max_ctx_payload_size, dir);
 	if (err < 0)
 		goto err_unlock;
 
+	if (is_irq_target) {
+		s->ctx_data.rx.events_per_period = events_per_period;
+		s->ctx_data.rx.event_count = 0;
+		ctx_cb = amdtp_stream_master_first_callback;
+		ctx_data = d;
+	} else {
+		ctx_cb = amdtp_stream_first_callback;
+		ctx_data = s;
+	}
+
 	s->context = fw_iso_context_create(fw_parent_device(s->unit)->card,
 					  type, channel, speed, ctx_header_size,
-					  amdtp_stream_first_callback, s);
+					  ctx_cb, ctx_data);
 	if (IS_ERR(s->context)) {
 		err = PTR_ERR(s->context);
 		if (err == -EBUSY)
@@ -981,7 +1114,7 @@ static int amdtp_stream_start(struct amdtp_stream *s, int channel, int speed)
 	else
 		s->tag = TAG_CIP;
 
-	s->pkt_descs = kcalloc(INTERRUPT_INTERVAL, sizeof(*s->pkt_descs),
+	s->pkt_descs = kcalloc(s->queue_size, sizeof(*s->pkt_descs),
 			       GFP_KERNEL);
 	if (!s->pkt_descs) {
 		err = -ENOMEM;
@@ -991,12 +1124,21 @@ static int amdtp_stream_start(struct amdtp_stream *s, int channel, int speed)
 	s->packet_index = 0;
 	do {
 		struct fw_iso_packet params;
+
 		if (s->direction == AMDTP_IN_STREAM) {
 			err = queue_in_packet(s, &params);
 		} else {
+			bool sched_irq = false;
+
 			params.header_length = 0;
 			params.payload_length = 0;
-			err = queue_out_packet(s, &params);
+
+			if (is_irq_target) {
+				sched_irq = !((s->packet_index + 1) %
+					      idle_irq_interval);
+			}
+
+			err = queue_out_packet(s, &params, sched_irq);
 		}
 		if (err < 0)
 			goto err_pkt_descs;
@@ -1008,7 +1150,7 @@ static int amdtp_stream_start(struct amdtp_stream *s, int channel, int speed)
 		tag |= FW_ISO_CONTEXT_MATCH_TAG0;
 
 	s->callbacked = false;
-	err = fw_iso_context_start(s->context, -1, 0, tag);
+	err = fw_iso_context_start(s->context, start_cycle, 0, tag);
 	if (err < 0)
 		goto err_pkt_descs;
 
@@ -1029,54 +1171,69 @@ err_unlock:
 }
 
 /**
- * amdtp_stream_pcm_pointer - get the PCM buffer position
+ * amdtp_domain_stream_pcm_pointer - get the PCM buffer position
+ * @d: the AMDTP domain.
  * @s: the AMDTP stream that transports the PCM data
  *
  * Returns the current buffer position, in frames.
  */
-unsigned long amdtp_stream_pcm_pointer(struct amdtp_stream *s)
+unsigned long amdtp_domain_stream_pcm_pointer(struct amdtp_domain *d,
+					      struct amdtp_stream *s)
 {
-	/*
-	 * This function is called in software IRQ context of period_tasklet or
-	 * process context.
-	 *
-	 * When the software IRQ context was scheduled by software IRQ context
-	 * of IR/IT contexts, queued packets were already handled. Therefore,
-	 * no need to flush the queue in buffer anymore.
-	 *
-	 * When the process context reach here, some packets will be already
-	 * queued in the buffer. These packets should be handled immediately
-	 * to keep better granularity of PCM pointer.
-	 *
-	 * Later, the process context will sometimes schedules software IRQ
-	 * context of the period_tasklet. Then, no need to flush the queue by
-	 * the same reason as described for IR/IT contexts.
-	 */
-	if (!in_interrupt() && amdtp_stream_running(s))
-		fw_iso_context_flush_completions(s->context);
+	struct amdtp_stream *irq_target = d->irq_target;
+
+	if (irq_target && amdtp_stream_running(irq_target)) {
+		// This function is called in software IRQ context of
+		// period_tasklet or process context.
+		//
+		// When the software IRQ context was scheduled by software IRQ
+		// context of IT contexts, queued packets were already handled.
+		// Therefore, no need to flush the queue in buffer furthermore.
+		//
+		// When the process context reach here, some packets will be
+		// already queued in the buffer. These packets should be handled
+		// immediately to keep better granularity of PCM pointer.
+		//
+		// Later, the process context will sometimes schedules software
+		// IRQ context of the period_tasklet. Then, no need to flush the
+		// queue by the same reason as described in the above
+		if (!in_interrupt()) {
+			// Queued packet should be processed without any kernel
+			// preemption to keep latency against bus cycle.
+			preempt_disable();
+			fw_iso_context_flush_completions(irq_target->context);
+			preempt_enable();
+		}
+	}
 
 	return READ_ONCE(s->pcm_buffer_pointer);
 }
-EXPORT_SYMBOL(amdtp_stream_pcm_pointer);
+EXPORT_SYMBOL_GPL(amdtp_domain_stream_pcm_pointer);
 
 /**
- * amdtp_stream_pcm_ack - acknowledge queued PCM frames
+ * amdtp_domain_stream_pcm_ack - acknowledge queued PCM frames
+ * @d: the AMDTP domain.
  * @s: the AMDTP stream that transfers the PCM frames
  *
  * Returns zero always.
  */
-int amdtp_stream_pcm_ack(struct amdtp_stream *s)
+int amdtp_domain_stream_pcm_ack(struct amdtp_domain *d, struct amdtp_stream *s)
 {
-	/*
-	 * Process isochronous packets for recent isochronous cycle to handle
-	 * queued PCM frames.
-	 */
-	if (amdtp_stream_running(s))
-		fw_iso_context_flush_completions(s->context);
+	struct amdtp_stream *irq_target = d->irq_target;
+
+	// Process isochronous packets for recent isochronous cycle to handle
+	// queued PCM frames.
+	if (irq_target && amdtp_stream_running(irq_target)) {
+		// Queued packet should be processed without any kernel
+		// preemption to keep latency against bus cycle.
+		preempt_disable();
+		fw_iso_context_flush_completions(irq_target->context);
+		preempt_enable();
+	}
 
 	return 0;
 }
-EXPORT_SYMBOL(amdtp_stream_pcm_ack);
+EXPORT_SYMBOL_GPL(amdtp_domain_stream_pcm_ack);
 
 /**
  * amdtp_stream_update - update the stream after a bus reset
@@ -1143,6 +1300,8 @@ int amdtp_domain_init(struct amdtp_domain *d)
 {
 	INIT_LIST_HEAD(&d->streams);
 
+	d->events_per_period = 0;
+
 	return 0;
 }
 EXPORT_SYMBOL_GPL(amdtp_domain_init);
@@ -1184,26 +1343,105 @@ int amdtp_domain_add_stream(struct amdtp_domain *d, struct amdtp_stream *s,
 }
 EXPORT_SYMBOL_GPL(amdtp_domain_add_stream);
 
+static int get_current_cycle_time(struct fw_card *fw_card, int *cur_cycle)
+{
+	int generation;
+	int rcode;
+	__be32 reg;
+	u32 data;
+
+	// This is a request to local 1394 OHCI controller and expected to
+	// complete without any event waiting.
+	generation = fw_card->generation;
+	smp_rmb();	// node_id vs. generation.
+	rcode = fw_run_transaction(fw_card, TCODE_READ_QUADLET_REQUEST,
+				   fw_card->node_id, generation, SCODE_100,
+				   CSR_REGISTER_BASE + CSR_CYCLE_TIME,
+				   &reg, sizeof(reg));
+	if (rcode != RCODE_COMPLETE)
+		return -EIO;
+
+	data = be32_to_cpu(reg);
+	*cur_cycle = data >> 12;
+
+	return 0;
+}
+
 /**
  * amdtp_domain_start - start sending packets for isoc context in the domain.
  * @d: the AMDTP domain.
+ * @ir_delay_cycle: the cycle delay to start all IR contexts.
  */
-int amdtp_domain_start(struct amdtp_domain *d)
+int amdtp_domain_start(struct amdtp_domain *d, unsigned int ir_delay_cycle)
 {
 	struct amdtp_stream *s;
-	int err = 0;
+	int cycle;
+	int err;
 
+	// Select an IT context as IRQ target.
 	list_for_each_entry(s, &d->streams, list) {
-		err = amdtp_stream_start(s, s->channel, s->speed);
-		if (err < 0)
+		if (s->direction == AMDTP_OUT_STREAM)
 			break;
 	}
+	if (!s)
+		return -ENXIO;
+	d->irq_target = s;
 
-	if (err < 0) {
-		list_for_each_entry(s, &d->streams, list)
-			amdtp_stream_stop(s);
+	if (ir_delay_cycle > 0) {
+		struct fw_card *fw_card = fw_parent_device(s->unit)->card;
+
+		err = get_current_cycle_time(fw_card, &cycle);
+		if (err < 0)
+			return err;
+
+		// No need to care overflow in cycle field because of enough
+		// width.
+		cycle += ir_delay_cycle;
+
+		// Round up to sec field.
+		if ((cycle & 0x00001fff) >= CYCLES_PER_SECOND) {
+			unsigned int sec;
+
+			// The sec field can overflow.
+			sec = (cycle & 0xffffe000) >> 13;
+			cycle = (++sec << 13) |
+				((cycle & 0x00001fff) / CYCLES_PER_SECOND);
+		}
+
+		// In OHCI 1394 specification, lower 2 bits are available for
+		// sec field.
+		cycle &= 0x00007fff;
+	} else {
+		cycle = -1;
+	}
+
+	list_for_each_entry(s, &d->streams, list) {
+		int cycle_match;
+
+		if (s->direction == AMDTP_IN_STREAM) {
+			cycle_match = cycle;
+		} else {
+			// IT context starts immediately.
+			cycle_match = -1;
+		}
+
+		if (s != d->irq_target) {
+			err = amdtp_stream_start(s, s->channel, s->speed, d,
+						 false, cycle_match);
+			if (err < 0)
+				goto error;
+		}
 	}
 
+	s = d->irq_target;
+	err = amdtp_stream_start(s, s->channel, s->speed, d, true, -1);
+	if (err < 0)
+		goto error;
+
+	return 0;
+error:
+	list_for_each_entry(s, &d->streams, list)
+		amdtp_stream_stop(s);
 	return err;
 }
 EXPORT_SYMBOL_GPL(amdtp_domain_start);
@@ -1216,10 +1454,17 @@ void amdtp_domain_stop(struct amdtp_domain *d)
 {
 	struct amdtp_stream *s, *next;
 
+	if (d->irq_target)
+		amdtp_stream_stop(d->irq_target);
+
 	list_for_each_entry_safe(s, next, &d->streams, list) {
 		list_del(&s->list);
 
-		amdtp_stream_stop(s);
+		if (s != d->irq_target)
+			amdtp_stream_stop(s);
 	}
+
+	d->events_per_period = 0;
+	d->irq_target = NULL;
 }
 EXPORT_SYMBOL_GPL(amdtp_domain_stop);
diff --git a/sound/firewire/amdtp-stream.h b/sound/firewire/amdtp-stream.h
index bbbca964b9b4..f2d44e2dc3c8 100644
--- a/sound/firewire/amdtp-stream.h
+++ b/sound/firewire/amdtp-stream.h
@@ -117,6 +117,7 @@ struct amdtp_stream {
 	/* For packet processing. */
 	struct fw_iso_context *context;
 	struct iso_packets_buffer buffer;
+	unsigned int queue_size;
 	int packet_index;
 	struct pkt_desc *pkt_descs;
 	int tag;
@@ -142,6 +143,10 @@ struct amdtp_stream {
 			// To generate CIP header.
 			unsigned int fdf;
 			int syt_override;
+
+			// To generate constant hardware IRQ.
+			unsigned int event_count;
+			unsigned int events_per_period;
 		} rx;
 	} ctx_data;
 
@@ -194,8 +199,6 @@ int amdtp_stream_add_pcm_hw_constraints(struct amdtp_stream *s,
 					struct snd_pcm_runtime *runtime);
 
 void amdtp_stream_pcm_prepare(struct amdtp_stream *s);
-unsigned long amdtp_stream_pcm_pointer(struct amdtp_stream *s);
-int amdtp_stream_pcm_ack(struct amdtp_stream *s);
 void amdtp_stream_pcm_abort(struct amdtp_stream *s);
 
 extern const unsigned int amdtp_syt_intervals[CIP_SFC_COUNT];
@@ -272,6 +275,11 @@ static inline bool amdtp_stream_wait_callback(struct amdtp_stream *s,
 
 struct amdtp_domain {
 	struct list_head streams;
+
+	unsigned int events_per_period;
+	unsigned int events_per_buffer;
+
+	struct amdtp_stream *irq_target;
 };
 
 int amdtp_domain_init(struct amdtp_domain *d);
@@ -280,7 +288,21 @@ void amdtp_domain_destroy(struct amdtp_domain *d);
 int amdtp_domain_add_stream(struct amdtp_domain *d, struct amdtp_stream *s,
 			    int channel, int speed);
 
-int amdtp_domain_start(struct amdtp_domain *d);
+int amdtp_domain_start(struct amdtp_domain *d, unsigned int ir_delay_cycle);
 void amdtp_domain_stop(struct amdtp_domain *d);
 
+static inline int amdtp_domain_set_events_per_period(struct amdtp_domain *d,
+						unsigned int events_per_period,
+						unsigned int events_per_buffer)
+{
+	d->events_per_period = events_per_period;
+	d->events_per_buffer = events_per_buffer;
+
+	return 0;
+}
+
+unsigned long amdtp_domain_stream_pcm_pointer(struct amdtp_domain *d,
+					      struct amdtp_stream *s);
+int amdtp_domain_stream_pcm_ack(struct amdtp_domain *d, struct amdtp_stream *s);
+
 #endif
diff --git a/sound/firewire/bebob/bebob.h b/sound/firewire/bebob/bebob.h
index 356d6ba60959..d1ad9a8451bc 100644
--- a/sound/firewire/bebob/bebob.h
+++ b/sound/firewire/bebob/bebob.h
@@ -217,7 +217,9 @@ int snd_bebob_stream_get_clock_src(struct snd_bebob *bebob,
 				   enum snd_bebob_clock_type *src);
 int snd_bebob_stream_discover(struct snd_bebob *bebob);
 int snd_bebob_stream_init_duplex(struct snd_bebob *bebob);
-int snd_bebob_stream_reserve_duplex(struct snd_bebob *bebob, unsigned int rate);
+int snd_bebob_stream_reserve_duplex(struct snd_bebob *bebob, unsigned int rate,
+				    unsigned int frames_per_period,
+				    unsigned int frames_per_buffer);
 int snd_bebob_stream_start_duplex(struct snd_bebob *bebob);
 void snd_bebob_stream_stop_duplex(struct snd_bebob *bebob);
 void snd_bebob_stream_destroy_duplex(struct snd_bebob *bebob);
diff --git a/sound/firewire/bebob/bebob_midi.c b/sound/firewire/bebob/bebob_midi.c
index 4d8805fa8a00..6f597d03e7c1 100644
--- a/sound/firewire/bebob/bebob_midi.c
+++ b/sound/firewire/bebob/bebob_midi.c
@@ -17,7 +17,7 @@ static int midi_open(struct snd_rawmidi_substream *substream)
 		return err;
 
 	mutex_lock(&bebob->mutex);
-	err = snd_bebob_stream_reserve_duplex(bebob, 0);
+	err = snd_bebob_stream_reserve_duplex(bebob, 0, 0, 0);
 	if (err >= 0) {
 		++bebob->substreams_counter;
 		err = snd_bebob_stream_start_duplex(bebob);
diff --git a/sound/firewire/bebob/bebob_pcm.c b/sound/firewire/bebob/bebob_pcm.c
index 0fb9eed46837..d4edd06d32cf 100644
--- a/sound/firewire/bebob/bebob_pcm.c
+++ b/sound/firewire/bebob/bebob_pcm.c
@@ -129,18 +129,17 @@ end:
 	return err;
 }
 
-static int
-pcm_open(struct snd_pcm_substream *substream)
+static int pcm_open(struct snd_pcm_substream *substream)
 {
 	struct snd_bebob *bebob = substream->private_data;
 	const struct snd_bebob_rate_spec *spec = bebob->spec->rate;
-	unsigned int sampling_rate;
+	struct amdtp_domain *d = &bebob->domain;
 	enum snd_bebob_clock_type src;
 	int err;
 
 	err = snd_bebob_stream_lock_try(bebob);
 	if (err < 0)
-		goto end;
+		return err;
 
 	err = pcm_init_hw_params(bebob, substream);
 	if (err < 0)
@@ -150,15 +149,20 @@ pcm_open(struct snd_pcm_substream *substream)
 	if (err < 0)
 		goto err_locked;
 
-	/*
-	 * When source of clock is internal or any PCM stream are running,
-	 * the available sampling rate is limited at current sampling rate.
-	 */
+	mutex_lock(&bebob->mutex);
+
+	// When source of clock is not internal or any stream is reserved for
+	// transmission of PCM frames, the available sampling rate is limited
+	// at current one.
 	if (src == SND_BEBOB_CLOCK_TYPE_EXTERNAL ||
-	    amdtp_stream_pcm_running(&bebob->tx_stream) ||
-	    amdtp_stream_pcm_running(&bebob->rx_stream)) {
+	    (bebob->substreams_counter > 0 && d->events_per_period > 0)) {
+		unsigned int frames_per_period = d->events_per_period;
+		unsigned int frames_per_buffer = d->events_per_buffer;
+		unsigned int sampling_rate;
+
 		err = spec->get(bebob, &sampling_rate);
 		if (err < 0) {
+			mutex_unlock(&bebob->mutex);
 			dev_err(&bebob->unit->device,
 				"fail to get sampling rate: %d\n", err);
 			goto err_locked;
@@ -166,11 +170,31 @@ pcm_open(struct snd_pcm_substream *substream)
 
 		substream->runtime->hw.rate_min = sampling_rate;
 		substream->runtime->hw.rate_max = sampling_rate;
+
+		if (frames_per_period > 0) {
+			err = snd_pcm_hw_constraint_minmax(substream->runtime,
+					SNDRV_PCM_HW_PARAM_PERIOD_SIZE,
+					frames_per_period, frames_per_period);
+			if (err < 0) {
+				mutex_unlock(&bebob->mutex);
+				goto err_locked;
+			}
+
+			err = snd_pcm_hw_constraint_minmax(substream->runtime,
+					SNDRV_PCM_HW_PARAM_BUFFER_SIZE,
+					frames_per_buffer, frames_per_buffer);
+			if (err < 0) {
+				mutex_unlock(&bebob->mutex);
+				goto err_locked;
+			}
+		}
 	}
 
+	mutex_unlock(&bebob->mutex);
+
 	snd_pcm_set_sync(substream);
-end:
-	return err;
+
+	return 0;
 err_locked:
 	snd_bebob_stream_lock_release(bebob);
 	return err;
@@ -190,16 +214,18 @@ static int pcm_hw_params(struct snd_pcm_substream *substream,
 	struct snd_bebob *bebob = substream->private_data;
 	int err;
 
-	err = snd_pcm_lib_alloc_vmalloc_buffer(substream,
-					       params_buffer_bytes(hw_params));
+	err = snd_pcm_lib_malloc_pages(substream, params_buffer_bytes(hw_params));
 	if (err < 0)
 		return err;
 
 	if (substream->runtime->status->state == SNDRV_PCM_STATE_OPEN) {
 		unsigned int rate = params_rate(hw_params);
+		unsigned int frames_per_period = params_period_size(hw_params);
+		unsigned int frames_per_buffer = params_buffer_size(hw_params);
 
 		mutex_lock(&bebob->mutex);
-		err = snd_bebob_stream_reserve_duplex(bebob, rate);
+		err = snd_bebob_stream_reserve_duplex(bebob, rate,
+					frames_per_period, frames_per_buffer);
 		if (err >= 0)
 			++bebob->substreams_counter;
 		mutex_unlock(&bebob->mutex);
@@ -221,7 +247,7 @@ static int pcm_hw_free(struct snd_pcm_substream *substream)
 
 	mutex_unlock(&bebob->mutex);
 
-	return snd_pcm_lib_free_vmalloc_buffer(substream);
+	return snd_pcm_lib_free_pages(substream);
 }
 
 static int
@@ -286,31 +312,33 @@ pcm_playback_trigger(struct snd_pcm_substream *substream, int cmd)
 	return 0;
 }
 
-static snd_pcm_uframes_t
-pcm_capture_pointer(struct snd_pcm_substream *sbstrm)
+static snd_pcm_uframes_t pcm_capture_pointer(struct snd_pcm_substream *sbstrm)
 {
 	struct snd_bebob *bebob = sbstrm->private_data;
-	return amdtp_stream_pcm_pointer(&bebob->tx_stream);
+
+	return amdtp_domain_stream_pcm_pointer(&bebob->domain,
+					       &bebob->tx_stream);
 }
-static snd_pcm_uframes_t
-pcm_playback_pointer(struct snd_pcm_substream *sbstrm)
+static snd_pcm_uframes_t pcm_playback_pointer(struct snd_pcm_substream *sbstrm)
 {
 	struct snd_bebob *bebob = sbstrm->private_data;
-	return amdtp_stream_pcm_pointer(&bebob->rx_stream);
+
+	return amdtp_domain_stream_pcm_pointer(&bebob->domain,
+					       &bebob->rx_stream);
 }
 
 static int pcm_capture_ack(struct snd_pcm_substream *substream)
 {
 	struct snd_bebob *bebob = substream->private_data;
 
-	return amdtp_stream_pcm_ack(&bebob->tx_stream);
+	return amdtp_domain_stream_pcm_ack(&bebob->domain, &bebob->tx_stream);
 }
 
 static int pcm_playback_ack(struct snd_pcm_substream *substream)
 {
 	struct snd_bebob *bebob = substream->private_data;
 
-	return amdtp_stream_pcm_ack(&bebob->rx_stream);
+	return amdtp_domain_stream_pcm_ack(&bebob->domain, &bebob->rx_stream);
 }
 
 int snd_bebob_create_pcm_devices(struct snd_bebob *bebob)
@@ -325,7 +353,6 @@ int snd_bebob_create_pcm_devices(struct snd_bebob *bebob)
 		.trigger	= pcm_capture_trigger,
 		.pointer	= pcm_capture_pointer,
 		.ack		= pcm_capture_ack,
-		.page		= snd_pcm_lib_get_vmalloc_page,
 	};
 	static const struct snd_pcm_ops playback_ops = {
 		.open		= pcm_open,
@@ -337,7 +364,6 @@ int snd_bebob_create_pcm_devices(struct snd_bebob *bebob)
 		.trigger	= pcm_playback_trigger,
 		.pointer	= pcm_playback_pointer,
 		.ack		= pcm_playback_ack,
-		.page		= snd_pcm_lib_get_vmalloc_page,
 	};
 	struct snd_pcm *pcm;
 	int err;
@@ -351,6 +377,8 @@ int snd_bebob_create_pcm_devices(struct snd_bebob *bebob)
 		 "%s PCM", bebob->card->shortname);
 	snd_pcm_set_ops(pcm, SNDRV_PCM_STREAM_PLAYBACK, &playback_ops);
 	snd_pcm_set_ops(pcm, SNDRV_PCM_STREAM_CAPTURE, &capture_ops);
+	snd_pcm_lib_preallocate_pages_for_all(pcm, SNDRV_DMA_TYPE_VMALLOC,
+					      NULL, 0, 0);
 end:
 	return err;
 }
diff --git a/sound/firewire/bebob/bebob_stream.c b/sound/firewire/bebob/bebob_stream.c
index 6c1497d9f52b..bbae04793c50 100644
--- a/sound/firewire/bebob/bebob_stream.c
+++ b/sound/firewire/bebob/bebob_stream.c
@@ -7,7 +7,7 @@
 
 #include "./bebob.h"
 
-#define CALLBACK_TIMEOUT	2000
+#define CALLBACK_TIMEOUT	2500
 #define FW_ISO_RESOURCE_DELAY	1000
 
 /*
@@ -398,36 +398,19 @@ check_connection_used_by_others(struct snd_bebob *bebob, struct amdtp_stream *s)
 	return err;
 }
 
-static int make_both_connections(struct snd_bebob *bebob)
-{
-	int err = 0;
-
-	err = cmp_connection_establish(&bebob->out_conn);
-	if (err < 0)
-		return err;
-
-	err = cmp_connection_establish(&bebob->in_conn);
-	if (err < 0) {
-		cmp_connection_break(&bebob->out_conn);
-		return err;
-	}
-
-	return 0;
-}
-
-static void
-break_both_connections(struct snd_bebob *bebob)
+static void break_both_connections(struct snd_bebob *bebob)
 {
 	cmp_connection_break(&bebob->in_conn);
 	cmp_connection_break(&bebob->out_conn);
 
-	/* These models seems to be in transition state for a longer time. */
-	if (bebob->maudio_special_quirk != NULL)
-		msleep(200);
+	// These models seem to be in transition state for a longer time. When
+	// accessing in the state, any transactions is corrupted. In the worst
+	// case, the device is going to reboot.
+	if (bebob->version < 2)
+		msleep(600);
 }
 
-static int
-start_stream(struct snd_bebob *bebob, struct amdtp_stream *stream)
+static int start_stream(struct snd_bebob *bebob, struct amdtp_stream *stream)
 {
 	struct cmp_connection *conn;
 	int err = 0;
@@ -437,18 +420,19 @@ start_stream(struct snd_bebob *bebob, struct amdtp_stream *stream)
 	else
 		conn = &bebob->out_conn;
 
-	/* channel mapping */
+	// channel mapping.
 	if (bebob->maudio_special_quirk == NULL) {
 		err = map_data_channels(bebob, stream);
 		if (err < 0)
-			goto end;
+			return err;
 	}
 
-	// start amdtp stream.
-	err = amdtp_domain_add_stream(&bebob->domain, stream,
-				      conn->resources.channel, conn->speed);
-end:
-	return err;
+	err = cmp_connection_establish(conn);
+	if (err < 0)
+		return err;
+
+	return amdtp_domain_add_stream(&bebob->domain, stream,
+				       conn->resources.channel, conn->speed);
 }
 
 static int init_stream(struct snd_bebob *bebob, struct amdtp_stream *stream)
@@ -553,7 +537,9 @@ static int keep_resources(struct snd_bebob *bebob, struct amdtp_stream *stream,
 	return cmp_connection_reserve(conn, amdtp_stream_get_max_payload(stream));
 }
 
-int snd_bebob_stream_reserve_duplex(struct snd_bebob *bebob, unsigned int rate)
+int snd_bebob_stream_reserve_duplex(struct snd_bebob *bebob, unsigned int rate,
+				    unsigned int frames_per_period,
+				    unsigned int frames_per_buffer)
 {
 	unsigned int curr_rate;
 	int err;
@@ -606,6 +592,14 @@ int snd_bebob_stream_reserve_duplex(struct snd_bebob *bebob, unsigned int rate)
 			cmp_connection_release(&bebob->out_conn);
 			return err;
 		}
+
+		err = amdtp_domain_set_events_per_period(&bebob->domain,
+					frames_per_period, frames_per_buffer);
+		if (err < 0) {
+			cmp_connection_release(&bebob->out_conn);
+			cmp_connection_release(&bebob->in_conn);
+			return err;
+		}
 	}
 
 	return 0;
@@ -627,7 +621,10 @@ int snd_bebob_stream_start_duplex(struct snd_bebob *bebob)
 	}
 
 	if (!amdtp_stream_running(&bebob->rx_stream)) {
+		enum snd_bebob_clock_type src;
+		struct amdtp_stream *master, *slave;
 		unsigned int curr_rate;
+		unsigned int ir_delay_cycle;
 
 		if (bebob->maudio_special_quirk) {
 			err = bebob->spec->rate->get(bebob, &curr_rate);
@@ -635,19 +632,40 @@ int snd_bebob_stream_start_duplex(struct snd_bebob *bebob)
 				return err;
 		}
 
-		err = make_both_connections(bebob);
+		err = snd_bebob_stream_get_clock_src(bebob, &src);
 		if (err < 0)
 			return err;
 
-		err = start_stream(bebob, &bebob->rx_stream);
+		if (src != SND_BEBOB_CLOCK_TYPE_SYT) {
+			master = &bebob->tx_stream;
+			slave = &bebob->rx_stream;
+		} else {
+			master = &bebob->rx_stream;
+			slave = &bebob->tx_stream;
+		}
+
+		err = start_stream(bebob, master);
 		if (err < 0)
 			goto error;
 
-		err = start_stream(bebob, &bebob->tx_stream);
+		err = start_stream(bebob, slave);
 		if (err < 0)
 			goto error;
 
-		err = amdtp_domain_start(&bebob->domain);
+		// The device postpones start of transmission mostly for 1 sec
+		// after receives packets firstly. For safe, IR context starts
+		// 0.4 sec (=3200 cycles) later to version 1 or 2 firmware,
+		// 2.0 sec (=16000 cycles) for version 3 firmware. This is
+		// within 2.5 sec (=CALLBACK_TIMEOUT).
+		// Furthermore, some devices transfer isoc packets with
+		// discontinuous counter in the beginning of packet streaming.
+		// The delay has an effect to avoid detection of this
+		// discontinuity.
+		if (bebob->version < 2)
+			ir_delay_cycle = 3200;
+		else
+			ir_delay_cycle = 16000;
+		err = amdtp_domain_start(&bebob->domain, ir_delay_cycle);
 		if (err < 0)
 			goto error;
 
diff --git a/sound/firewire/dice/dice-midi.c b/sound/firewire/dice/dice-midi.c
index c9e19bddfc09..4c2998034313 100644
--- a/sound/firewire/dice/dice-midi.c
+++ b/sound/firewire/dice/dice-midi.c
@@ -17,7 +17,7 @@ static int midi_open(struct snd_rawmidi_substream *substream)
 
 	mutex_lock(&dice->mutex);
 
-	err = snd_dice_stream_reserve_duplex(dice, 0);
+	err = snd_dice_stream_reserve_duplex(dice, 0, 0, 0);
 	if (err >= 0) {
 		++dice->substreams_counter;
 		err = snd_dice_stream_start_duplex(dice);
diff --git a/sound/firewire/dice/dice-pcm.c b/sound/firewire/dice/dice-pcm.c
index 94a4dccfc381..be79d659eedf 100644
--- a/sound/firewire/dice/dice-pcm.c
+++ b/sound/firewire/dice/dice-pcm.c
@@ -164,13 +164,14 @@ static int init_hw_info(struct snd_dice *dice,
 static int pcm_open(struct snd_pcm_substream *substream)
 {
 	struct snd_dice *dice = substream->private_data;
+	struct amdtp_domain *d = &dice->domain;
 	unsigned int source;
 	bool internal;
 	int err;
 
 	err = snd_dice_stream_lock_try(dice);
 	if (err < 0)
-		goto end;
+		return err;
 
 	err = init_hw_info(dice, substream);
 	if (err < 0)
@@ -195,27 +196,56 @@ static int pcm_open(struct snd_pcm_substream *substream)
 		break;
 	}
 
-	/*
-	 * When source of clock is not internal or any PCM streams are running,
-	 * available sampling rate is limited at current sampling rate.
-	 */
+	mutex_lock(&dice->mutex);
+
+	// When source of clock is not internal or any stream is reserved for
+	// transmission of PCM frames, the available sampling rate is limited
+	// at current one.
 	if (!internal ||
-	    amdtp_stream_pcm_running(&dice->tx_stream[0]) ||
-	    amdtp_stream_pcm_running(&dice->tx_stream[1]) ||
-	    amdtp_stream_pcm_running(&dice->rx_stream[0]) ||
-	    amdtp_stream_pcm_running(&dice->rx_stream[1])) {
+	    (dice->substreams_counter > 0 && d->events_per_period > 0)) {
+		unsigned int frames_per_period = d->events_per_period;
+		unsigned int frames_per_buffer = d->events_per_buffer;
 		unsigned int rate;
 
 		err = snd_dice_transaction_get_rate(dice, &rate);
-		if (err < 0)
+		if (err < 0) {
+			mutex_unlock(&dice->mutex);
 			goto err_locked;
+		}
+
 		substream->runtime->hw.rate_min = rate;
 		substream->runtime->hw.rate_max = rate;
+
+		if (frames_per_period > 0) {
+			// For double_pcm_frame quirk.
+			if (rate > 96000) {
+				frames_per_period *= 2;
+				frames_per_buffer *= 2;
+			}
+
+			err = snd_pcm_hw_constraint_minmax(substream->runtime,
+					SNDRV_PCM_HW_PARAM_PERIOD_SIZE,
+					frames_per_period, frames_per_period);
+			if (err < 0) {
+				mutex_unlock(&dice->mutex);
+				goto err_locked;
+			}
+
+			err = snd_pcm_hw_constraint_minmax(substream->runtime,
+					SNDRV_PCM_HW_PARAM_BUFFER_SIZE,
+					frames_per_buffer, frames_per_buffer);
+			if (err < 0) {
+				mutex_unlock(&dice->mutex);
+				goto err_locked;
+			}
+		}
 	}
 
+	mutex_unlock(&dice->mutex);
+
 	snd_pcm_set_sync(substream);
-end:
-	return err;
+
+	return 0;
 err_locked:
 	snd_dice_stream_lock_release(dice);
 	return err;
@@ -236,16 +266,23 @@ static int pcm_hw_params(struct snd_pcm_substream *substream,
 	struct snd_dice *dice = substream->private_data;
 	int err;
 
-	err = snd_pcm_lib_alloc_vmalloc_buffer(substream,
-					       params_buffer_bytes(hw_params));
+	err = snd_pcm_lib_malloc_pages(substream, params_buffer_bytes(hw_params));
 	if (err < 0)
 		return err;
 
 	if (substream->runtime->status->state == SNDRV_PCM_STATE_OPEN) {
 		unsigned int rate = params_rate(hw_params);
+		unsigned int events_per_period = params_period_size(hw_params);
+		unsigned int events_per_buffer = params_buffer_size(hw_params);
 
 		mutex_lock(&dice->mutex);
-		err = snd_dice_stream_reserve_duplex(dice, rate);
+		// For double_pcm_frame quirk.
+		if (rate > 96000) {
+			events_per_period /= 2;
+			events_per_buffer /= 2;
+		}
+		err = snd_dice_stream_reserve_duplex(dice, rate,
+					events_per_period, events_per_buffer);
 		if (err >= 0)
 			++dice->substreams_counter;
 		mutex_unlock(&dice->mutex);
@@ -267,7 +304,7 @@ static int pcm_hw_free(struct snd_pcm_substream *substream)
 
 	mutex_unlock(&dice->mutex);
 
-	return snd_pcm_lib_free_vmalloc_buffer(substream);
+	return snd_pcm_lib_free_pages(substream);
 }
 
 static int capture_prepare(struct snd_pcm_substream *substream)
@@ -341,14 +378,14 @@ static snd_pcm_uframes_t capture_pointer(struct snd_pcm_substream *substream)
 	struct snd_dice *dice = substream->private_data;
 	struct amdtp_stream *stream = &dice->tx_stream[substream->pcm->device];
 
-	return amdtp_stream_pcm_pointer(stream);
+	return amdtp_domain_stream_pcm_pointer(&dice->domain, stream);
 }
 static snd_pcm_uframes_t playback_pointer(struct snd_pcm_substream *substream)
 {
 	struct snd_dice *dice = substream->private_data;
 	struct amdtp_stream *stream = &dice->rx_stream[substream->pcm->device];
 
-	return amdtp_stream_pcm_pointer(stream);
+	return amdtp_domain_stream_pcm_pointer(&dice->domain, stream);
 }
 
 static int capture_ack(struct snd_pcm_substream *substream)
@@ -356,7 +393,7 @@ static int capture_ack(struct snd_pcm_substream *substream)
 	struct snd_dice *dice = substream->private_data;
 	struct amdtp_stream *stream = &dice->tx_stream[substream->pcm->device];
 
-	return amdtp_stream_pcm_ack(stream);
+	return amdtp_domain_stream_pcm_ack(&dice->domain, stream);
 }
 
 static int playback_ack(struct snd_pcm_substream *substream)
@@ -364,7 +401,7 @@ static int playback_ack(struct snd_pcm_substream *substream)
 	struct snd_dice *dice = substream->private_data;
 	struct amdtp_stream *stream = &dice->rx_stream[substream->pcm->device];
 
-	return amdtp_stream_pcm_ack(stream);
+	return amdtp_domain_stream_pcm_ack(&dice->domain, stream);
 }
 
 int snd_dice_create_pcm(struct snd_dice *dice)
@@ -379,7 +416,6 @@ int snd_dice_create_pcm(struct snd_dice *dice)
 		.trigger   = capture_trigger,
 		.pointer   = capture_pointer,
 		.ack       = capture_ack,
-		.page      = snd_pcm_lib_get_vmalloc_page,
 	};
 	static const struct snd_pcm_ops playback_ops = {
 		.open      = pcm_open,
@@ -391,7 +427,6 @@ int snd_dice_create_pcm(struct snd_dice *dice)
 		.trigger   = playback_trigger,
 		.pointer   = playback_pointer,
 		.ack       = playback_ack,
-		.page      = snd_pcm_lib_get_vmalloc_page,
 	};
 	struct snd_pcm *pcm;
 	unsigned int capture, playback;
@@ -421,6 +456,10 @@ int snd_dice_create_pcm(struct snd_dice *dice)
 		if (playback > 0)
 			snd_pcm_set_ops(pcm, SNDRV_PCM_STREAM_PLAYBACK,
 					&playback_ops);
+
+		snd_pcm_lib_preallocate_pages_for_all(pcm,
+						      SNDRV_DMA_TYPE_VMALLOC,
+						      NULL, 0, 0);
 	}
 
 	return 0;
diff --git a/sound/firewire/dice/dice-stream.c b/sound/firewire/dice/dice-stream.c
index f6a8627ae5a2..6a3d60913e10 100644
--- a/sound/firewire/dice/dice-stream.c
+++ b/sound/firewire/dice/dice-stream.c
@@ -278,7 +278,9 @@ static void finish_session(struct snd_dice *dice, struct reg_params *tx_params,
 	snd_dice_transaction_clear_enable(dice);
 }
 
-int snd_dice_stream_reserve_duplex(struct snd_dice *dice, unsigned int rate)
+int snd_dice_stream_reserve_duplex(struct snd_dice *dice, unsigned int rate,
+				   unsigned int events_per_period,
+				   unsigned int events_per_buffer)
 {
 	unsigned int curr_rate;
 	int err;
@@ -324,6 +326,11 @@ int snd_dice_stream_reserve_duplex(struct snd_dice *dice, unsigned int rate)
 					  &rx_params);
 		if (err < 0)
 			goto error;
+
+		err = amdtp_domain_set_events_per_period(&dice->domain,
+					events_per_period, events_per_buffer);
+		if (err < 0)
+			goto error;
 	}
 
 	return 0;
@@ -455,7 +462,7 @@ int snd_dice_stream_start_duplex(struct snd_dice *dice)
 			goto error;
 		}
 
-		err = amdtp_domain_start(&dice->domain);
+		err = amdtp_domain_start(&dice->domain, 0);
 		if (err < 0)
 			goto error;
 
diff --git a/sound/firewire/dice/dice.h b/sound/firewire/dice/dice.h
index fa6d74303f54..16366773e22e 100644
--- a/sound/firewire/dice/dice.h
+++ b/sound/firewire/dice/dice.h
@@ -210,7 +210,9 @@ int snd_dice_stream_start_duplex(struct snd_dice *dice);
 void snd_dice_stream_stop_duplex(struct snd_dice *dice);
 int snd_dice_stream_init_duplex(struct snd_dice *dice);
 void snd_dice_stream_destroy_duplex(struct snd_dice *dice);
-int snd_dice_stream_reserve_duplex(struct snd_dice *dice, unsigned int rate);
+int snd_dice_stream_reserve_duplex(struct snd_dice *dice, unsigned int rate,
+				   unsigned int events_per_period,
+				   unsigned int events_per_buffer);
 void snd_dice_stream_update_duplex(struct snd_dice *dice);
 int snd_dice_stream_detect_current_formats(struct snd_dice *dice);
 
diff --git a/sound/firewire/digi00x/digi00x-midi.c b/sound/firewire/digi00x/digi00x-midi.c
index 2b57ece89101..68eb8c39afa6 100644
--- a/sound/firewire/digi00x/digi00x-midi.c
+++ b/sound/firewire/digi00x/digi00x-midi.c
@@ -17,7 +17,7 @@ static int midi_open(struct snd_rawmidi_substream *substream)
 		return err;
 
 	mutex_lock(&dg00x->mutex);
-	err = snd_dg00x_stream_reserve_duplex(dg00x, 0);
+	err = snd_dg00x_stream_reserve_duplex(dg00x, 0, 0, 0);
 	if (err >= 0) {
 		++dg00x->substreams_counter;
 		err = snd_dg00x_stream_start_duplex(dg00x);
diff --git a/sound/firewire/digi00x/digi00x-pcm.c b/sound/firewire/digi00x/digi00x-pcm.c
index 18e561b26625..57cbce4fd836 100644
--- a/sound/firewire/digi00x/digi00x-pcm.c
+++ b/sound/firewire/digi00x/digi00x-pcm.c
@@ -100,14 +100,14 @@ static int pcm_init_hw_params(struct snd_dg00x *dg00x,
 static int pcm_open(struct snd_pcm_substream *substream)
 {
 	struct snd_dg00x *dg00x = substream->private_data;
+	struct amdtp_domain *d = &dg00x->domain;
 	enum snd_dg00x_clock clock;
 	bool detect;
-	unsigned int rate;
 	int err;
 
 	err = snd_dg00x_stream_lock_try(dg00x);
 	if (err < 0)
-		goto end;
+		return err;
 
 	err = pcm_init_hw_params(dg00x, substream);
 	if (err < 0)
@@ -127,19 +127,49 @@ static int pcm_open(struct snd_pcm_substream *substream)
 		}
 	}
 
+	mutex_lock(&dg00x->mutex);
+
+	// When source of clock is not internal or any stream is reserved for
+	// transmission of PCM frames, the available sampling rate is limited
+	// at current one.
 	if ((clock != SND_DG00X_CLOCK_INTERNAL) ||
-	    amdtp_stream_pcm_running(&dg00x->rx_stream) ||
-	    amdtp_stream_pcm_running(&dg00x->tx_stream)) {
+	    (dg00x->substreams_counter > 0 && d->events_per_period > 0)) {
+		unsigned int frames_per_period = d->events_per_period;
+		unsigned int frames_per_buffer = d->events_per_buffer;
+		unsigned int rate;
+
 		err = snd_dg00x_stream_get_external_rate(dg00x, &rate);
-		if (err < 0)
+		if (err < 0) {
+			mutex_unlock(&dg00x->mutex);
 			goto err_locked;
+		}
 		substream->runtime->hw.rate_min = rate;
 		substream->runtime->hw.rate_max = rate;
+
+		if (frames_per_period > 0) {
+			err = snd_pcm_hw_constraint_minmax(substream->runtime,
+					SNDRV_PCM_HW_PARAM_PERIOD_SIZE,
+					frames_per_period, frames_per_period);
+			if (err < 0) {
+				mutex_unlock(&dg00x->mutex);
+				goto err_locked;
+			}
+
+			err = snd_pcm_hw_constraint_minmax(substream->runtime,
+					SNDRV_PCM_HW_PARAM_BUFFER_SIZE,
+					frames_per_buffer, frames_per_buffer);
+			if (err < 0) {
+				mutex_unlock(&dg00x->mutex);
+				goto err_locked;
+			}
+		}
 	}
 
+	mutex_unlock(&dg00x->mutex);
+
 	snd_pcm_set_sync(substream);
-end:
-	return err;
+
+	return 0;
 err_locked:
 	snd_dg00x_stream_lock_release(dg00x);
 	return err;
@@ -160,16 +190,18 @@ static int pcm_hw_params(struct snd_pcm_substream *substream,
 	struct snd_dg00x *dg00x = substream->private_data;
 	int err;
 
-	err = snd_pcm_lib_alloc_vmalloc_buffer(substream,
-					       params_buffer_bytes(hw_params));
+	err = snd_pcm_lib_malloc_pages(substream, params_buffer_bytes(hw_params));
 	if (err < 0)
 		return err;
 
 	if (substream->runtime->status->state == SNDRV_PCM_STATE_OPEN) {
 		unsigned int rate = params_rate(hw_params);
+		unsigned int frames_per_period = params_period_size(hw_params);
+		unsigned int frames_per_buffer = params_buffer_size(hw_params);
 
 		mutex_lock(&dg00x->mutex);
-		err = snd_dg00x_stream_reserve_duplex(dg00x, rate);
+		err = snd_dg00x_stream_reserve_duplex(dg00x, rate,
+					frames_per_period, frames_per_buffer);
 		if (err >= 0)
 			++dg00x->substreams_counter;
 		mutex_unlock(&dg00x->mutex);
@@ -191,7 +223,7 @@ static int pcm_hw_free(struct snd_pcm_substream *substream)
 
 	mutex_unlock(&dg00x->mutex);
 
-	return snd_pcm_lib_free_vmalloc_buffer(substream);
+	return snd_pcm_lib_free_pages(substream);
 }
 
 static int pcm_capture_prepare(struct snd_pcm_substream *substream)
@@ -268,28 +300,28 @@ static snd_pcm_uframes_t pcm_capture_pointer(struct snd_pcm_substream *sbstrm)
 {
 	struct snd_dg00x *dg00x = sbstrm->private_data;
 
-	return amdtp_stream_pcm_pointer(&dg00x->tx_stream);
+	return amdtp_domain_stream_pcm_pointer(&dg00x->domain, &dg00x->tx_stream);
 }
 
 static snd_pcm_uframes_t pcm_playback_pointer(struct snd_pcm_substream *sbstrm)
 {
 	struct snd_dg00x *dg00x = sbstrm->private_data;
 
-	return amdtp_stream_pcm_pointer(&dg00x->rx_stream);
+	return amdtp_domain_stream_pcm_pointer(&dg00x->domain, &dg00x->rx_stream);
 }
 
 static int pcm_capture_ack(struct snd_pcm_substream *substream)
 {
 	struct snd_dg00x *dg00x = substream->private_data;
 
-	return amdtp_stream_pcm_ack(&dg00x->tx_stream);
+	return amdtp_domain_stream_pcm_ack(&dg00x->domain, &dg00x->tx_stream);
 }
 
 static int pcm_playback_ack(struct snd_pcm_substream *substream)
 {
 	struct snd_dg00x *dg00x = substream->private_data;
 
-	return amdtp_stream_pcm_ack(&dg00x->rx_stream);
+	return amdtp_domain_stream_pcm_ack(&dg00x->domain, &dg00x->rx_stream);
 }
 
 int snd_dg00x_create_pcm_devices(struct snd_dg00x *dg00x)
@@ -304,7 +336,6 @@ int snd_dg00x_create_pcm_devices(struct snd_dg00x *dg00x)
 		.trigger	= pcm_capture_trigger,
 		.pointer	= pcm_capture_pointer,
 		.ack		= pcm_capture_ack,
-		.page		= snd_pcm_lib_get_vmalloc_page,
 	};
 	static const struct snd_pcm_ops playback_ops = {
 		.open		= pcm_open,
@@ -316,7 +347,6 @@ int snd_dg00x_create_pcm_devices(struct snd_dg00x *dg00x)
 		.trigger	= pcm_playback_trigger,
 		.pointer	= pcm_playback_pointer,
 		.ack		= pcm_playback_ack,
-		.page		= snd_pcm_lib_get_vmalloc_page,
 	};
 	struct snd_pcm *pcm;
 	int err;
@@ -330,6 +360,8 @@ int snd_dg00x_create_pcm_devices(struct snd_dg00x *dg00x)
 		 "%s PCM", dg00x->card->shortname);
 	snd_pcm_set_ops(pcm, SNDRV_PCM_STREAM_PLAYBACK, &playback_ops);
 	snd_pcm_set_ops(pcm, SNDRV_PCM_STREAM_CAPTURE, &capture_ops);
+	snd_pcm_lib_preallocate_pages_for_all(pcm, SNDRV_DMA_TYPE_VMALLOC,
+					      NULL, 0, 0);
 
 	return 0;
 }
diff --git a/sound/firewire/digi00x/digi00x-stream.c b/sound/firewire/digi00x/digi00x-stream.c
index d6a92460060f..405d6903bfbc 100644
--- a/sound/firewire/digi00x/digi00x-stream.c
+++ b/sound/firewire/digi00x/digi00x-stream.c
@@ -283,7 +283,9 @@ void snd_dg00x_stream_destroy_duplex(struct snd_dg00x *dg00x)
 	destroy_stream(dg00x, &dg00x->tx_stream);
 }
 
-int snd_dg00x_stream_reserve_duplex(struct snd_dg00x *dg00x, unsigned int rate)
+int snd_dg00x_stream_reserve_duplex(struct snd_dg00x *dg00x, unsigned int rate,
+				    unsigned int frames_per_period,
+				    unsigned int frames_per_buffer)
 {
 	unsigned int curr_rate;
 	int err;
@@ -315,6 +317,14 @@ int snd_dg00x_stream_reserve_duplex(struct snd_dg00x *dg00x, unsigned int rate)
 			fw_iso_resources_free(&dg00x->rx_resources);
 			return err;
 		}
+
+		err = amdtp_domain_set_events_per_period(&dg00x->domain,
+					frames_per_period, frames_per_buffer);
+		if (err < 0) {
+			fw_iso_resources_free(&dg00x->rx_resources);
+			fw_iso_resources_free(&dg00x->tx_resources);
+			return err;
+		}
 	}
 
 	return 0;
@@ -365,7 +375,7 @@ int snd_dg00x_stream_start_duplex(struct snd_dg00x *dg00x)
 		if (err < 0)
 			goto error;
 
-		err = amdtp_domain_start(&dg00x->domain);
+		err = amdtp_domain_start(&dg00x->domain, 0);
 		if (err < 0)
 			goto error;
 
diff --git a/sound/firewire/digi00x/digi00x.h b/sound/firewire/digi00x/digi00x.h
index 8041c65f2736..129de8edd5ea 100644
--- a/sound/firewire/digi00x/digi00x.h
+++ b/sound/firewire/digi00x/digi00x.h
@@ -141,7 +141,9 @@ int snd_dg00x_stream_get_clock(struct snd_dg00x *dg00x,
 int snd_dg00x_stream_check_external_clock(struct snd_dg00x *dg00x,
 					  bool *detect);
 int snd_dg00x_stream_init_duplex(struct snd_dg00x *dg00x);
-int snd_dg00x_stream_reserve_duplex(struct snd_dg00x *dg00x, unsigned int rate);
+int snd_dg00x_stream_reserve_duplex(struct snd_dg00x *dg00x, unsigned int rate,
+				    unsigned int frames_per_period,
+				    unsigned int frames_per_buffer);
 int snd_dg00x_stream_start_duplex(struct snd_dg00x *dg00x);
 void snd_dg00x_stream_stop_duplex(struct snd_dg00x *dg00x);
 void snd_dg00x_stream_update_duplex(struct snd_dg00x *dg00x);
diff --git a/sound/firewire/fireface/ff-pcm.c b/sound/firewire/fireface/ff-pcm.c
index 9eab3ad283ce..4e3bd9a2bec0 100644
--- a/sound/firewire/fireface/ff-pcm.c
+++ b/sound/firewire/fireface/ff-pcm.c
@@ -139,6 +139,7 @@ static int pcm_init_hw_params(struct snd_ff *ff,
 static int pcm_open(struct snd_pcm_substream *substream)
 {
 	struct snd_ff *ff = substream->private_data;
+	struct amdtp_domain *d = &ff->domain;
 	unsigned int rate;
 	enum snd_ff_clock_src src;
 	int i, err;
@@ -155,16 +156,21 @@ static int pcm_open(struct snd_pcm_substream *substream)
 	if (err < 0)
 		goto release_lock;
 
+	mutex_lock(&ff->mutex);
+
+	// When source of clock is not internal or any stream is reserved for
+	// transmission of PCM frames, the available sampling rate is limited
+	// at current one.
 	if (src != SND_FF_CLOCK_SRC_INTERNAL) {
 		for (i = 0; i < CIP_SFC_COUNT; ++i) {
 			if (amdtp_rate_table[i] == rate)
 				break;
 		}
-		/*
-		 * The unit is configured at sampling frequency which packet
-		 * streaming engine can't support.
-		 */
+
+		// The unit is configured at sampling frequency which packet
+		// streaming engine can't support.
 		if (i >= CIP_SFC_COUNT) {
+			mutex_unlock(&ff->mutex);
 			err = -EIO;
 			goto release_lock;
 		}
@@ -172,14 +178,34 @@ static int pcm_open(struct snd_pcm_substream *substream)
 		substream->runtime->hw.rate_min = rate;
 		substream->runtime->hw.rate_max = rate;
 	} else {
-		if (amdtp_stream_pcm_running(&ff->rx_stream) ||
-		    amdtp_stream_pcm_running(&ff->tx_stream)) {
+		if (ff->substreams_counter > 0) {
+			unsigned int frames_per_period = d->events_per_period;
+			unsigned int frames_per_buffer = d->events_per_buffer;
+
 			rate = amdtp_rate_table[ff->rx_stream.sfc];
 			substream->runtime->hw.rate_min = rate;
 			substream->runtime->hw.rate_max = rate;
+
+			err = snd_pcm_hw_constraint_minmax(substream->runtime,
+					SNDRV_PCM_HW_PARAM_PERIOD_SIZE,
+					frames_per_period, frames_per_period);
+			if (err < 0) {
+				mutex_unlock(&ff->mutex);
+				goto release_lock;
+			}
+
+			err = snd_pcm_hw_constraint_minmax(substream->runtime,
+					SNDRV_PCM_HW_PARAM_BUFFER_SIZE,
+					frames_per_buffer, frames_per_buffer);
+			if (err < 0) {
+				mutex_unlock(&ff->mutex);
+				goto release_lock;
+			}
 		}
 	}
 
+	mutex_unlock(&ff->mutex);
+
 	snd_pcm_set_sync(substream);
 
 	return 0;
@@ -204,16 +230,18 @@ static int pcm_hw_params(struct snd_pcm_substream *substream,
 	struct snd_ff *ff = substream->private_data;
 	int err;
 
-	err = snd_pcm_lib_alloc_vmalloc_buffer(substream,
-					       params_buffer_bytes(hw_params));
+	err = snd_pcm_lib_malloc_pages(substream, params_buffer_bytes(hw_params));
 	if (err < 0)
 		return err;
 
 	if (substream->runtime->status->state == SNDRV_PCM_STATE_OPEN) {
 		unsigned int rate = params_rate(hw_params);
+		unsigned int frames_per_period = params_period_size(hw_params);
+		unsigned int frames_per_buffer = params_buffer_size(hw_params);
 
 		mutex_lock(&ff->mutex);
-		err = snd_ff_stream_reserve_duplex(ff, rate);
+		err = snd_ff_stream_reserve_duplex(ff, rate, frames_per_period,
+						   frames_per_buffer);
 		if (err >= 0)
 			++ff->substreams_counter;
 		mutex_unlock(&ff->mutex);
@@ -235,7 +263,7 @@ static int pcm_hw_free(struct snd_pcm_substream *substream)
 
 	mutex_unlock(&ff->mutex);
 
-	return snd_pcm_lib_free_vmalloc_buffer(substream);
+	return snd_pcm_lib_free_pages(substream);
 }
 
 static int pcm_capture_prepare(struct snd_pcm_substream *substream)
@@ -312,28 +340,28 @@ static snd_pcm_uframes_t pcm_capture_pointer(struct snd_pcm_substream *sbstrm)
 {
 	struct snd_ff *ff = sbstrm->private_data;
 
-	return amdtp_stream_pcm_pointer(&ff->tx_stream);
+	return amdtp_domain_stream_pcm_pointer(&ff->domain, &ff->tx_stream);
 }
 
 static snd_pcm_uframes_t pcm_playback_pointer(struct snd_pcm_substream *sbstrm)
 {
 	struct snd_ff *ff = sbstrm->private_data;
 
-	return amdtp_stream_pcm_pointer(&ff->rx_stream);
+	return amdtp_domain_stream_pcm_pointer(&ff->domain, &ff->rx_stream);
 }
 
 static int pcm_capture_ack(struct snd_pcm_substream *substream)
 {
 	struct snd_ff *ff = substream->private_data;
 
-	return amdtp_stream_pcm_ack(&ff->tx_stream);
+	return amdtp_domain_stream_pcm_ack(&ff->domain, &ff->tx_stream);
 }
 
 static int pcm_playback_ack(struct snd_pcm_substream *substream)
 {
 	struct snd_ff *ff = substream->private_data;
 
-	return amdtp_stream_pcm_ack(&ff->rx_stream);
+	return amdtp_domain_stream_pcm_ack(&ff->domain, &ff->rx_stream);
 }
 
 int snd_ff_create_pcm_devices(struct snd_ff *ff)
@@ -348,7 +376,6 @@ int snd_ff_create_pcm_devices(struct snd_ff *ff)
 		.trigger	= pcm_capture_trigger,
 		.pointer	= pcm_capture_pointer,
 		.ack		= pcm_capture_ack,
-		.page		= snd_pcm_lib_get_vmalloc_page,
 	};
 	static const struct snd_pcm_ops pcm_playback_ops = {
 		.open		= pcm_open,
@@ -360,7 +387,6 @@ int snd_ff_create_pcm_devices(struct snd_ff *ff)
 		.trigger	= pcm_playback_trigger,
 		.pointer	= pcm_playback_pointer,
 		.ack		= pcm_playback_ack,
-		.page		= snd_pcm_lib_get_vmalloc_page,
 	};
 	struct snd_pcm *pcm;
 	int err;
@@ -374,6 +400,8 @@ int snd_ff_create_pcm_devices(struct snd_ff *ff)
 		 "%s PCM", ff->card->shortname);
 	snd_pcm_set_ops(pcm, SNDRV_PCM_STREAM_PLAYBACK, &pcm_playback_ops);
 	snd_pcm_set_ops(pcm, SNDRV_PCM_STREAM_CAPTURE, &pcm_capture_ops);
+	snd_pcm_lib_preallocate_pages_for_all(pcm, SNDRV_DMA_TYPE_VMALLOC,
+					      NULL, 0, 0);
 
 	return 0;
 }
diff --git a/sound/firewire/fireface/ff-stream.c b/sound/firewire/fireface/ff-stream.c
index e8e6f9fd6433..63b79c4a5405 100644
--- a/sound/firewire/fireface/ff-stream.c
+++ b/sound/firewire/fireface/ff-stream.c
@@ -106,7 +106,9 @@ void snd_ff_stream_destroy_duplex(struct snd_ff *ff)
 	destroy_stream(ff, &ff->tx_stream);
 }
 
-int snd_ff_stream_reserve_duplex(struct snd_ff *ff, unsigned int rate)
+int snd_ff_stream_reserve_duplex(struct snd_ff *ff, unsigned int rate,
+				 unsigned int frames_per_period,
+				 unsigned int frames_per_buffer)
 {
 	unsigned int curr_rate;
 	enum snd_ff_clock_src src;
@@ -150,6 +152,14 @@ int snd_ff_stream_reserve_duplex(struct snd_ff *ff, unsigned int rate)
 		err = ff->spec->protocol->allocate_resources(ff, rate);
 		if (err < 0)
 			return err;
+
+		err = amdtp_domain_set_events_per_period(&ff->domain,
+					frames_per_period, frames_per_buffer);
+		if (err < 0) {
+			fw_iso_resources_free(&ff->tx_resources);
+			fw_iso_resources_free(&ff->rx_resources);
+			return err;
+		}
 	}
 
 	return 0;
@@ -174,6 +184,7 @@ int snd_ff_stream_start_duplex(struct snd_ff *ff, unsigned int rate)
 	 */
 	if (!amdtp_stream_running(&ff->rx_stream)) {
 		int spd = fw_parent_device(ff->unit)->max_speed;
+		unsigned int ir_delay_cycle;
 
 		err = ff->spec->protocol->begin_session(ff, rate);
 		if (err < 0)
@@ -189,7 +200,14 @@ int snd_ff_stream_start_duplex(struct snd_ff *ff, unsigned int rate)
 		if (err < 0)
 			goto error;
 
-		err = amdtp_domain_start(&ff->domain);
+		// The device postpones start of transmission mostly for several
+		// cycles after receiving packets firstly.
+		if (ff->spec->protocol == &snd_ff_protocol_ff800)
+			ir_delay_cycle = 800;	// = 100 msec
+		else
+			ir_delay_cycle = 16;	// = 2 msec
+
+		err = amdtp_domain_start(&ff->domain, ir_delay_cycle);
 		if (err < 0)
 			goto error;
 
diff --git a/sound/firewire/fireface/ff.h b/sound/firewire/fireface/ff.h
index b4c22ca6079e..dc7a20f75983 100644
--- a/sound/firewire/fireface/ff.h
+++ b/sound/firewire/fireface/ff.h
@@ -139,7 +139,9 @@ int snd_ff_stream_get_multiplier_mode(enum cip_sfc sfc,
 				      enum snd_ff_stream_mode *mode);
 int snd_ff_stream_init_duplex(struct snd_ff *ff);
 void snd_ff_stream_destroy_duplex(struct snd_ff *ff);
-int snd_ff_stream_reserve_duplex(struct snd_ff *ff, unsigned int rate);
+int snd_ff_stream_reserve_duplex(struct snd_ff *ff, unsigned int rate,
+				 unsigned int frames_per_period,
+				 unsigned int frames_per_buffer);
 int snd_ff_stream_start_duplex(struct snd_ff *ff, unsigned int rate);
 void snd_ff_stream_stop_duplex(struct snd_ff *ff);
 void snd_ff_stream_update_duplex(struct snd_ff *ff);
diff --git a/sound/firewire/fireworks/fireworks.h b/sound/firewire/fireworks/fireworks.h
index 4cda297f8438..dda797209a27 100644
--- a/sound/firewire/fireworks/fireworks.h
+++ b/sound/firewire/fireworks/fireworks.h
@@ -207,7 +207,9 @@ int snd_efw_command_get_sampling_rate(struct snd_efw *efw, unsigned int *rate);
 int snd_efw_command_set_sampling_rate(struct snd_efw *efw, unsigned int rate);
 
 int snd_efw_stream_init_duplex(struct snd_efw *efw);
-int snd_efw_stream_reserve_duplex(struct snd_efw *efw, unsigned int rate);
+int snd_efw_stream_reserve_duplex(struct snd_efw *efw, unsigned int rate,
+				  unsigned int frames_per_period,
+				  unsigned int frames_per_buffer);
 int snd_efw_stream_start_duplex(struct snd_efw *efw);
 void snd_efw_stream_stop_duplex(struct snd_efw *efw);
 void snd_efw_stream_update_duplex(struct snd_efw *efw);
diff --git a/sound/firewire/fireworks/fireworks_midi.c b/sound/firewire/fireworks/fireworks_midi.c
index a9f4a9630d15..84621e356848 100644
--- a/sound/firewire/fireworks/fireworks_midi.c
+++ b/sound/firewire/fireworks/fireworks_midi.c
@@ -17,7 +17,7 @@ static int midi_open(struct snd_rawmidi_substream *substream)
 		goto end;
 
 	mutex_lock(&efw->mutex);
-	err = snd_efw_stream_reserve_duplex(efw, 0);
+	err = snd_efw_stream_reserve_duplex(efw, 0, 0, 0);
 	if (err >= 0) {
 		++efw->substreams_counter;
 		err = snd_efw_stream_start_duplex(efw);
diff --git a/sound/firewire/fireworks/fireworks_pcm.c b/sound/firewire/fireworks/fireworks_pcm.c
index a7025dccc754..e69896d748df 100644
--- a/sound/firewire/fireworks/fireworks_pcm.c
+++ b/sound/firewire/fireworks/fireworks_pcm.c
@@ -173,13 +173,13 @@ end:
 static int pcm_open(struct snd_pcm_substream *substream)
 {
 	struct snd_efw *efw = substream->private_data;
-	unsigned int sampling_rate;
+	struct amdtp_domain *d = &efw->domain;
 	enum snd_efw_clock_source clock_source;
 	int err;
 
 	err = snd_efw_stream_lock_try(efw);
 	if (err < 0)
-		goto end;
+		return err;
 
 	err = pcm_init_hw_params(efw, substream);
 	if (err < 0)
@@ -189,23 +189,49 @@ static int pcm_open(struct snd_pcm_substream *substream)
 	if (err < 0)
 		goto err_locked;
 
-	/*
-	 * When source of clock is not internal or any PCM streams are running,
-	 * available sampling rate is limited at current sampling rate.
-	 */
+	mutex_lock(&efw->mutex);
+
+	// When source of clock is not internal or any stream is reserved for
+	// transmission of PCM frames, the available sampling rate is limited
+	// at current one.
 	if ((clock_source != SND_EFW_CLOCK_SOURCE_INTERNAL) ||
-	    amdtp_stream_pcm_running(&efw->tx_stream) ||
-	    amdtp_stream_pcm_running(&efw->rx_stream)) {
+	    (efw->substreams_counter > 0 && d->events_per_period > 0)) {
+		unsigned int frames_per_period = d->events_per_period;
+		unsigned int frames_per_buffer = d->events_per_buffer;
+		unsigned int sampling_rate;
+
 		err = snd_efw_command_get_sampling_rate(efw, &sampling_rate);
-		if (err < 0)
+		if (err < 0) {
+			mutex_unlock(&efw->mutex);
 			goto err_locked;
+		}
 		substream->runtime->hw.rate_min = sampling_rate;
 		substream->runtime->hw.rate_max = sampling_rate;
+
+		if (frames_per_period > 0) {
+			err = snd_pcm_hw_constraint_minmax(substream->runtime,
+					SNDRV_PCM_HW_PARAM_PERIOD_SIZE,
+					frames_per_period, frames_per_period);
+			if (err < 0) {
+				mutex_unlock(&efw->mutex);
+				goto err_locked;
+			}
+
+			err = snd_pcm_hw_constraint_minmax(substream->runtime,
+					SNDRV_PCM_HW_PARAM_BUFFER_SIZE,
+					frames_per_buffer, frames_per_buffer);
+			if (err < 0) {
+				mutex_unlock(&efw->mutex);
+				goto err_locked;
+			}
+		}
 	}
 
+	mutex_unlock(&efw->mutex);
+
 	snd_pcm_set_sync(substream);
-end:
-	return err;
+
+	return 0;
 err_locked:
 	snd_efw_stream_lock_release(efw);
 	return err;
@@ -224,16 +250,18 @@ static int pcm_hw_params(struct snd_pcm_substream *substream,
 	struct snd_efw *efw = substream->private_data;
 	int err;
 
-	err = snd_pcm_lib_alloc_vmalloc_buffer(substream,
-					       params_buffer_bytes(hw_params));
+	err = snd_pcm_lib_malloc_pages(substream, params_buffer_bytes(hw_params));
 	if (err < 0)
 		return err;
 
 	if (substream->runtime->status->state == SNDRV_PCM_STATE_OPEN) {
 		unsigned int rate = params_rate(hw_params);
+		unsigned int frames_per_period = params_period_size(hw_params);
+		unsigned int frames_per_buffer = params_buffer_size(hw_params);
 
 		mutex_lock(&efw->mutex);
-		err = snd_efw_stream_reserve_duplex(efw, rate);
+		err = snd_efw_stream_reserve_duplex(efw, rate,
+					frames_per_period, frames_per_buffer);
 		if (err >= 0)
 			++efw->substreams_counter;
 		mutex_unlock(&efw->mutex);
@@ -255,7 +283,7 @@ static int pcm_hw_free(struct snd_pcm_substream *substream)
 
 	mutex_unlock(&efw->mutex);
 
-	return snd_pcm_lib_free_vmalloc_buffer(substream);
+	return snd_pcm_lib_free_pages(substream);
 }
 
 static int pcm_capture_prepare(struct snd_pcm_substream *substream)
@@ -319,26 +347,28 @@ static int pcm_playback_trigger(struct snd_pcm_substream *substream, int cmd)
 static snd_pcm_uframes_t pcm_capture_pointer(struct snd_pcm_substream *sbstrm)
 {
 	struct snd_efw *efw = sbstrm->private_data;
-	return amdtp_stream_pcm_pointer(&efw->tx_stream);
+
+	return amdtp_domain_stream_pcm_pointer(&efw->domain, &efw->tx_stream);
 }
 static snd_pcm_uframes_t pcm_playback_pointer(struct snd_pcm_substream *sbstrm)
 {
 	struct snd_efw *efw = sbstrm->private_data;
-	return amdtp_stream_pcm_pointer(&efw->rx_stream);
+
+	return amdtp_domain_stream_pcm_pointer(&efw->domain, &efw->rx_stream);
 }
 
 static int pcm_capture_ack(struct snd_pcm_substream *substream)
 {
 	struct snd_efw *efw = substream->private_data;
 
-	return amdtp_stream_pcm_ack(&efw->tx_stream);
+	return amdtp_domain_stream_pcm_ack(&efw->domain, &efw->tx_stream);
 }
 
 static int pcm_playback_ack(struct snd_pcm_substream *substream)
 {
 	struct snd_efw *efw = substream->private_data;
 
-	return amdtp_stream_pcm_ack(&efw->rx_stream);
+	return amdtp_domain_stream_pcm_ack(&efw->domain, &efw->rx_stream);
 }
 
 int snd_efw_create_pcm_devices(struct snd_efw *efw)
@@ -353,7 +383,6 @@ int snd_efw_create_pcm_devices(struct snd_efw *efw)
 		.trigger	= pcm_capture_trigger,
 		.pointer	= pcm_capture_pointer,
 		.ack		= pcm_capture_ack,
-		.page		= snd_pcm_lib_get_vmalloc_page,
 	};
 	static const struct snd_pcm_ops playback_ops = {
 		.open		= pcm_open,
@@ -365,7 +394,6 @@ int snd_efw_create_pcm_devices(struct snd_efw *efw)
 		.trigger	= pcm_playback_trigger,
 		.pointer	= pcm_playback_pointer,
 		.ack		= pcm_playback_ack,
-		.page		= snd_pcm_lib_get_vmalloc_page,
 	};
 	struct snd_pcm *pcm;
 	int err;
@@ -378,6 +406,8 @@ int snd_efw_create_pcm_devices(struct snd_efw *efw)
 	snprintf(pcm->name, sizeof(pcm->name), "%s PCM", efw->card->shortname);
 	snd_pcm_set_ops(pcm, SNDRV_PCM_STREAM_PLAYBACK, &playback_ops);
 	snd_pcm_set_ops(pcm, SNDRV_PCM_STREAM_CAPTURE, &capture_ops);
+	snd_pcm_lib_preallocate_pages_for_all(pcm, SNDRV_DMA_TYPE_VMALLOC,
+					      NULL, 0, 0);
 end:
 	return err;
 }
diff --git a/sound/firewire/fireworks/fireworks_stream.c b/sound/firewire/fireworks/fireworks_stream.c
index f2de304d2f26..2206af0fef42 100644
--- a/sound/firewire/fireworks/fireworks_stream.c
+++ b/sound/firewire/fireworks/fireworks_stream.c
@@ -181,7 +181,9 @@ static int keep_resources(struct snd_efw *efw, struct amdtp_stream *stream,
 	return cmp_connection_reserve(conn, amdtp_stream_get_max_payload(stream));
 }
 
-int snd_efw_stream_reserve_duplex(struct snd_efw *efw, unsigned int rate)
+int snd_efw_stream_reserve_duplex(struct snd_efw *efw, unsigned int rate,
+				  unsigned int frames_per_period,
+				  unsigned int frames_per_buffer)
 {
 	unsigned int curr_rate;
 	int err;
@@ -228,6 +230,14 @@ int snd_efw_stream_reserve_duplex(struct snd_efw *efw, unsigned int rate)
 			cmp_connection_release(&efw->in_conn);
 			return err;
 		}
+
+		err = amdtp_domain_set_events_per_period(&efw->domain,
+					frames_per_period, frames_per_buffer);
+		if (err < 0) {
+			cmp_connection_release(&efw->in_conn);
+			cmp_connection_release(&efw->out_conn);
+			return err;
+		}
 	}
 
 	return 0;
@@ -262,7 +272,7 @@ int snd_efw_stream_start_duplex(struct snd_efw *efw)
 		if (err < 0)
 			goto error;
 
-		err = amdtp_domain_start(&efw->domain);
+		err = amdtp_domain_start(&efw->domain, 0);
 		if (err < 0)
 			goto error;
 
diff --git a/sound/firewire/isight.c b/sound/firewire/isight.c
index a16beda7c530..d9f1b962bfef 100644
--- a/sound/firewire/isight.c
+++ b/sound/firewire/isight.c
@@ -288,8 +288,7 @@ static int isight_hw_params(struct snd_pcm_substream *substream,
 	struct isight *isight = substream->private_data;
 	int err;
 
-	err = snd_pcm_lib_alloc_vmalloc_buffer(substream,
-					       params_buffer_bytes(hw_params));
+	err = snd_pcm_lib_malloc_pages(substream, params_buffer_bytes(hw_params));
 	if (err < 0)
 		return err;
 
@@ -337,7 +336,7 @@ static int isight_hw_free(struct snd_pcm_substream *substream)
 	isight_stop_streaming(isight);
 	mutex_unlock(&isight->mutex);
 
-	return snd_pcm_lib_free_vmalloc_buffer(substream);
+	return snd_pcm_lib_free_pages(substream);
 }
 
 static int isight_start_streaming(struct isight *isight)
@@ -453,7 +452,6 @@ static int isight_create_pcm(struct isight *isight)
 		.prepare   = isight_prepare,
 		.trigger   = isight_trigger,
 		.pointer   = isight_pointer,
-		.page      = snd_pcm_lib_get_vmalloc_page,
 	};
 	struct snd_pcm *pcm;
 	int err;
@@ -465,6 +463,8 @@ static int isight_create_pcm(struct isight *isight)
 	strcpy(pcm->name, "iSight");
 	isight->pcm = pcm->streams[SNDRV_PCM_STREAM_CAPTURE].substream;
 	isight->pcm->ops = &ops;
+	snd_pcm_lib_preallocate_pages_for_all(pcm, SNDRV_DMA_TYPE_VMALLOC,
+					      NULL, 0, 0);
 
 	return 0;
 }
diff --git a/sound/firewire/motu/motu-midi.c b/sound/firewire/motu/motu-midi.c
index 46a0035df31e..2365f7dfde26 100644
--- a/sound/firewire/motu/motu-midi.c
+++ b/sound/firewire/motu/motu-midi.c
@@ -17,7 +17,7 @@ static int midi_open(struct snd_rawmidi_substream *substream)
 
 	mutex_lock(&motu->mutex);
 
-	err = snd_motu_stream_reserve_duplex(motu, 0);
+	err = snd_motu_stream_reserve_duplex(motu, 0, 0, 0);
 	if (err >= 0) {
 		++motu->substreams_counter;
 		err = snd_motu_stream_start_duplex(motu);
diff --git a/sound/firewire/motu/motu-pcm.c b/sound/firewire/motu/motu-pcm.c
index aa2e584da6fe..349b4d09e84f 100644
--- a/sound/firewire/motu/motu-pcm.c
+++ b/sound/firewire/motu/motu-pcm.c
@@ -134,8 +134,8 @@ static int pcm_open(struct snd_pcm_substream *substream)
 {
 	struct snd_motu *motu = substream->private_data;
 	const struct snd_motu_protocol *const protocol = motu->spec->protocol;
+	struct amdtp_domain *d = &motu->domain;
 	enum snd_motu_clock_source src;
-	unsigned int rate;
 	int err;
 
 	err = snd_motu_stream_lock_try(motu);
@@ -152,28 +152,51 @@ static int pcm_open(struct snd_pcm_substream *substream)
 	if (err < 0)
 		goto err_locked;
 
-	/*
-	 * When source of clock is not internal or any PCM streams are running,
-	 * available sampling rate is limited at current sampling rate.
-	 */
 	err = protocol->get_clock_source(motu, &src);
 	if (err < 0)
 		goto err_locked;
-	if (src != SND_MOTU_CLOCK_SOURCE_INTERNAL ||
-	    amdtp_stream_pcm_running(&motu->tx_stream) ||
-	    amdtp_stream_pcm_running(&motu->rx_stream)) {
+
+	// When source of clock is not internal or any stream is reserved for
+	// transmission of PCM frames, the available sampling rate is limited
+	// at current one.
+	if ((src != SND_MOTU_CLOCK_SOURCE_INTERNAL &&
+	     src != SND_MOTU_CLOCK_SOURCE_SPH) ||
+	    (motu->substreams_counter > 0 && d->events_per_period > 0)) {
+		unsigned int frames_per_period = d->events_per_period;
+		unsigned int frames_per_buffer = d->events_per_buffer;
+		unsigned int rate;
+
 		err = protocol->get_clock_rate(motu, &rate);
 		if (err < 0)
 			goto err_locked;
+
 		substream->runtime->hw.rate_min = rate;
 		substream->runtime->hw.rate_max = rate;
+
+		if (frames_per_period > 0) {
+			err = snd_pcm_hw_constraint_minmax(substream->runtime,
+					SNDRV_PCM_HW_PARAM_PERIOD_SIZE,
+					frames_per_period, frames_per_period);
+			if (err < 0) {
+				mutex_unlock(&motu->mutex);
+				goto err_locked;
+			}
+
+			err = snd_pcm_hw_constraint_minmax(substream->runtime,
+					SNDRV_PCM_HW_PARAM_BUFFER_SIZE,
+					frames_per_buffer, frames_per_buffer);
+			if (err < 0) {
+				mutex_unlock(&motu->mutex);
+				goto err_locked;
+			}
+		}
 	}
 
 	snd_pcm_set_sync(substream);
 
 	mutex_unlock(&motu->mutex);
 
-	return err;
+	return 0;
 err_locked:
 	mutex_unlock(&motu->mutex);
 	snd_motu_stream_lock_release(motu);
@@ -195,16 +218,18 @@ static int pcm_hw_params(struct snd_pcm_substream *substream,
 	struct snd_motu *motu = substream->private_data;
 	int err;
 
-	err = snd_pcm_lib_alloc_vmalloc_buffer(substream,
-					       params_buffer_bytes(hw_params));
+	err = snd_pcm_lib_malloc_pages(substream, params_buffer_bytes(hw_params));
 	if (err < 0)
 		return err;
 
 	if (substream->runtime->status->state == SNDRV_PCM_STATE_OPEN) {
 		unsigned int rate = params_rate(hw_params);
+		unsigned int frames_per_period = params_period_size(hw_params);
+		unsigned int frames_per_buffer = params_buffer_size(hw_params);
 
 		mutex_lock(&motu->mutex);
-		err = snd_motu_stream_reserve_duplex(motu, rate);
+		err = snd_motu_stream_reserve_duplex(motu, rate,
+					frames_per_period, frames_per_buffer);
 		if (err >= 0)
 			++motu->substreams_counter;
 		mutex_unlock(&motu->mutex);
@@ -226,7 +251,7 @@ static int pcm_hw_free(struct snd_pcm_substream *substream)
 
 	mutex_unlock(&motu->mutex);
 
-	return snd_pcm_lib_free_vmalloc_buffer(substream);
+	return snd_pcm_lib_free_pages(substream);
 }
 
 static int capture_prepare(struct snd_pcm_substream *substream)
@@ -295,27 +320,27 @@ static snd_pcm_uframes_t capture_pointer(struct snd_pcm_substream *substream)
 {
 	struct snd_motu *motu = substream->private_data;
 
-	return amdtp_stream_pcm_pointer(&motu->tx_stream);
+	return amdtp_domain_stream_pcm_pointer(&motu->domain, &motu->tx_stream);
 }
 static snd_pcm_uframes_t playback_pointer(struct snd_pcm_substream *substream)
 {
 	struct snd_motu *motu = substream->private_data;
 
-	return amdtp_stream_pcm_pointer(&motu->rx_stream);
+	return amdtp_domain_stream_pcm_pointer(&motu->domain, &motu->rx_stream);
 }
 
 static int capture_ack(struct snd_pcm_substream *substream)
 {
 	struct snd_motu *motu = substream->private_data;
 
-	return amdtp_stream_pcm_ack(&motu->tx_stream);
+	return amdtp_domain_stream_pcm_ack(&motu->domain, &motu->tx_stream);
 }
 
 static int playback_ack(struct snd_pcm_substream *substream)
 {
 	struct snd_motu *motu = substream->private_data;
 
-	return amdtp_stream_pcm_ack(&motu->rx_stream);
+	return amdtp_domain_stream_pcm_ack(&motu->domain, &motu->rx_stream);
 }
 
 int snd_motu_create_pcm_devices(struct snd_motu *motu)
@@ -330,7 +355,6 @@ int snd_motu_create_pcm_devices(struct snd_motu *motu)
 		.trigger   = capture_trigger,
 		.pointer   = capture_pointer,
 		.ack       = capture_ack,
-		.page      = snd_pcm_lib_get_vmalloc_page,
 	};
 	static const struct snd_pcm_ops playback_ops = {
 		.open      = pcm_open,
@@ -342,7 +366,6 @@ int snd_motu_create_pcm_devices(struct snd_motu *motu)
 		.trigger   = playback_trigger,
 		.pointer   = playback_pointer,
 		.ack       = playback_ack,
-		.page      = snd_pcm_lib_get_vmalloc_page,
 	};
 	struct snd_pcm *pcm;
 	int err;
@@ -355,6 +378,8 @@ int snd_motu_create_pcm_devices(struct snd_motu *motu)
 
 	snd_pcm_set_ops(pcm, SNDRV_PCM_STREAM_CAPTURE, &capture_ops);
 	snd_pcm_set_ops(pcm, SNDRV_PCM_STREAM_PLAYBACK, &playback_ops);
+	snd_pcm_lib_preallocate_pages_for_all(pcm, SNDRV_DMA_TYPE_VMALLOC,
+					      NULL, 0, 0);
 
 	return 0;
 }
diff --git a/sound/firewire/motu/motu-proc.c b/sound/firewire/motu/motu-proc.c
index ea46fb4c1b5a..187f6abd878c 100644
--- a/sound/firewire/motu/motu-proc.c
+++ b/sound/firewire/motu/motu-proc.c
@@ -16,9 +16,11 @@ static const char *const clock_names[] = {
 	[SND_MOTU_CLOCK_SOURCE_SPDIF_ON_OPT] = "S/PDIF on optical interface",
 	[SND_MOTU_CLOCK_SOURCE_SPDIF_ON_OPT_A] = "S/PDIF on optical interface A",
 	[SND_MOTU_CLOCK_SOURCE_SPDIF_ON_OPT_B] = "S/PDIF on optical interface B",
-	[SND_MOTU_CLOCK_SOURCE_SPDIF_ON_COAX] = "S/PCIF on coaxial interface",
+	[SND_MOTU_CLOCK_SOURCE_SPDIF_ON_COAX] = "S/PDIF on coaxial interface",
 	[SND_MOTU_CLOCK_SOURCE_AESEBU_ON_XLR] = "AESEBU on XLR interface",
 	[SND_MOTU_CLOCK_SOURCE_WORD_ON_BNC] = "Word clock on BNC interface",
+	[SND_MOTU_CLOCK_SOURCE_SPH] = "Source packet header",
+	[SND_MOTU_CLOCK_SOURCE_UNKNOWN] = "Unknown",
 };
 
 static void proc_read_clock(struct snd_info_entry *entry,
diff --git a/sound/firewire/motu/motu-protocol-v2.c b/sound/firewire/motu/motu-protocol-v2.c
index 9e2f16eebe0a..619b6ae73f62 100644
--- a/sound/firewire/motu/motu-protocol-v2.c
+++ b/sound/firewire/motu/motu-protocol-v2.c
@@ -12,10 +12,8 @@
 #define  V2_CLOCK_RATE_SHIFT			3
 #define  V2_CLOCK_SRC_MASK			0x00000007
 #define  V2_CLOCK_SRC_SHIFT			0
-#define  V2_CLOCK_TRAVELER_FETCH_DISABLE	0x04000000
-#define  V2_CLOCK_TRAVELER_FETCH_ENABLE		0x03000000
-#define  V2_CLOCK_8PRE_FETCH_DISABLE		0x02000000
-#define  V2_CLOCK_8PRE_FETCH_ENABLE		0x00000000
+#define  V2_CLOCK_FETCH_ENABLE			0x02000000
+#define  V2_CLOCK_MODEL_SPECIFIC		0x04000000
 
 #define V2_IN_OUT_CONF_OFFSET			0x0c04
 #define  V2_OPT_OUT_IFACE_MASK			0x00000c00
@@ -26,10 +24,20 @@
 #define  V2_OPT_IFACE_MODE_ADAT			1
 #define  V2_OPT_IFACE_MODE_SPDIF		2
 
+static int get_clock_rate(u32 data, unsigned int *rate)
+{
+	unsigned int index = (data & V2_CLOCK_RATE_MASK) >> V2_CLOCK_RATE_SHIFT;
+	if (index >= ARRAY_SIZE(snd_motu_clock_rates))
+		return -EIO;
+
+	*rate = snd_motu_clock_rates[index];
+
+	return 0;
+}
+
 static int v2_get_clock_rate(struct snd_motu *motu, unsigned int *rate)
 {
 	__be32 reg;
-	unsigned int index;
 	int err;
 
 	err = snd_motu_transaction_read(motu, V2_CLOCK_STATUS_OFFSET, &reg,
@@ -37,13 +45,7 @@ static int v2_get_clock_rate(struct snd_motu *motu, unsigned int *rate)
 	if (err < 0)
 		return err;
 
-	index = (be32_to_cpu(reg) & V2_CLOCK_RATE_MASK) >> V2_CLOCK_RATE_SHIFT;
-	if (index >= ARRAY_SIZE(snd_motu_clock_rates))
-		return -EIO;
-
-	*rate = snd_motu_clock_rates[index];
-
-	return 0;
+	return get_clock_rate(be32_to_cpu(reg), rate);
 }
 
 static int v2_set_clock_rate(struct snd_motu *motu, unsigned int rate)
@@ -69,51 +71,44 @@ static int v2_set_clock_rate(struct snd_motu *motu, unsigned int rate)
 	data &= ~V2_CLOCK_RATE_MASK;
 	data |= i << V2_CLOCK_RATE_SHIFT;
 
-	if (motu->spec == &snd_motu_spec_traveler) {
-		data &= ~V2_CLOCK_TRAVELER_FETCH_ENABLE;
-		data |= V2_CLOCK_TRAVELER_FETCH_DISABLE;
-	}
-
 	reg = cpu_to_be32(data);
 	return snd_motu_transaction_write(motu, V2_CLOCK_STATUS_OFFSET, &reg,
 					  sizeof(reg));
 }
 
-static int v2_get_clock_source(struct snd_motu *motu,
-			       enum snd_motu_clock_source *src)
+static int get_clock_source(struct snd_motu *motu, u32 data,
+			    enum snd_motu_clock_source *src)
 {
-	__be32 reg;
-	unsigned int index;
-	int err;
-
-	err = snd_motu_transaction_read(motu, V2_CLOCK_STATUS_OFFSET, &reg,
-					sizeof(reg));
-	if (err < 0)
-		return err;
-
-	index = be32_to_cpu(reg) & V2_CLOCK_SRC_MASK;
+	unsigned int index = data & V2_CLOCK_SRC_MASK;
 	if (index > 5)
 		return -EIO;
 
-	/* To check the configuration of optical interface. */
-	err = snd_motu_transaction_read(motu, V2_IN_OUT_CONF_OFFSET, &reg,
-					sizeof(reg));
-	if (err < 0)
-		return err;
-
 	switch (index) {
 	case 0:
 		*src = SND_MOTU_CLOCK_SOURCE_INTERNAL;
 		break;
 	case 1:
+	{
+		__be32 reg;
+
+		// To check the configuration of optical interface.
+		int err = snd_motu_transaction_read(motu, V2_IN_OUT_CONF_OFFSET,
+						    &reg, sizeof(reg));
+		if (err < 0)
+			return err;
+
 		if (be32_to_cpu(reg) & 0x00000200)
 			*src = SND_MOTU_CLOCK_SOURCE_SPDIF_ON_OPT;
 		else
 			*src = SND_MOTU_CLOCK_SOURCE_ADAT_ON_OPT;
 		break;
+	}
 	case 2:
 		*src = SND_MOTU_CLOCK_SOURCE_SPDIF_ON_COAX;
 		break;
+	case 3:
+		*src = SND_MOTU_CLOCK_SOURCE_SPH;
+		break;
 	case 4:
 		*src = SND_MOTU_CLOCK_SOURCE_WORD_ON_BNC;
 		break;
@@ -127,44 +122,65 @@ static int v2_get_clock_source(struct snd_motu *motu,
 	return 0;
 }
 
+static int v2_get_clock_source(struct snd_motu *motu,
+			       enum snd_motu_clock_source *src)
+{
+	__be32 reg;
+	int err;
+
+	err = snd_motu_transaction_read(motu, V2_CLOCK_STATUS_OFFSET, &reg,
+					sizeof(reg));
+	if (err < 0)
+		return err;
+
+	return get_clock_source(motu, be32_to_cpu(reg), src);
+}
+
 static int v2_switch_fetching_mode(struct snd_motu *motu, bool enable)
 {
+	enum snd_motu_clock_source src;
 	__be32 reg;
 	u32 data;
 	int err = 0;
 
-	if (motu->spec == &snd_motu_spec_traveler ||
-	    motu->spec == &snd_motu_spec_8pre) {
-		err = snd_motu_transaction_read(motu, V2_CLOCK_STATUS_OFFSET,
-						&reg, sizeof(reg));
+	// 828mkII implements Altera ACEX 1K EP1K30. Nothing to do.
+	if (motu->spec == &snd_motu_spec_828mk2)
+		return 0;
+
+	err = snd_motu_transaction_read(motu, V2_CLOCK_STATUS_OFFSET, &reg,
+					sizeof(reg));
+	if (err < 0)
+		return err;
+	data = be32_to_cpu(reg);
+
+	err = get_clock_source(motu, data, &src);
+	if (err < 0)
+		return err;
+
+	data &= ~(V2_CLOCK_FETCH_ENABLE | V2_CLOCK_MODEL_SPECIFIC);
+	if (enable)
+		data |= V2_CLOCK_FETCH_ENABLE;
+
+	if (motu->spec->flags & SND_MOTU_SPEC_SUPPORT_CLOCK_X4) {
+		// Expected for Traveler and 896HD, which implements Altera
+		// Cyclone EP1C3.
+		data |= V2_CLOCK_MODEL_SPECIFIC;
+	} else {
+		// For UltraLite and 8pre, which implements Xilinx Spartan
+		// XC3S200.
+		unsigned int rate;
+
+		err = get_clock_rate(data, &rate);
 		if (err < 0)
 			return err;
-		data = be32_to_cpu(reg);
-
-		if (motu->spec == &snd_motu_spec_traveler) {
-			data &= ~(V2_CLOCK_TRAVELER_FETCH_DISABLE |
-				  V2_CLOCK_TRAVELER_FETCH_ENABLE);
-
-			if (enable)
-				data |= V2_CLOCK_TRAVELER_FETCH_ENABLE;
-			else
-				data |= V2_CLOCK_TRAVELER_FETCH_DISABLE;
-		} else if (motu->spec == &snd_motu_spec_8pre) {
-			data &= ~(V2_CLOCK_8PRE_FETCH_DISABLE |
-				  V2_CLOCK_8PRE_FETCH_ENABLE);
-
-			if (enable)
-				data |= V2_CLOCK_8PRE_FETCH_DISABLE;
-			else
-				data |= V2_CLOCK_8PRE_FETCH_ENABLE;
-		}
 
-		reg = cpu_to_be32(data);
-		err = snd_motu_transaction_write(motu, V2_CLOCK_STATUS_OFFSET,
-						 &reg, sizeof(reg));
+		if (src == SND_MOTU_CLOCK_SOURCE_SPH && rate > 48000)
+			data |= V2_CLOCK_MODEL_SPECIFIC;
 	}
 
-	return err;
+	reg = cpu_to_be32(data);
+	return snd_motu_transaction_write(motu, V2_CLOCK_STATUS_OFFSET, &reg,
+					  sizeof(reg));
 }
 
 static void calculate_fixed_part(struct snd_motu_packet_format *formats,
@@ -191,7 +207,7 @@ static void calculate_fixed_part(struct snd_motu_packet_format *formats,
 			pcm_chunks[1] += 2;
 		}
 	} else {
-		if (flags & SND_MOTU_SPEC_RX_SEPARETED_MAIN) {
+		if (flags & SND_MOTU_SPEC_RX_SEPARATED_MAIN) {
 			pcm_chunks[0] += 2;
 			pcm_chunks[1] += 2;
 		}
diff --git a/sound/firewire/motu/motu-protocol-v3.c b/sound/firewire/motu/motu-protocol-v3.c
index 5eafa506e8a9..d1545e2b5caa 100644
--- a/sound/firewire/motu/motu-protocol-v3.c
+++ b/sound/firewire/motu/motu-protocol-v3.c
@@ -104,6 +104,8 @@ static int v3_get_clock_source(struct snd_motu *motu,
 		*src = SND_MOTU_CLOCK_SOURCE_INTERNAL;
 	} else if (val == 0x01) {
 		*src = SND_MOTU_CLOCK_SOURCE_WORD_ON_BNC;
+	} else if (val == 0x02) {
+		*src = SND_MOTU_CLOCK_SOURCE_SPH;
 	} else if (val == 0x10) {
 		*src = SND_MOTU_CLOCK_SOURCE_SPDIF_ON_COAX;
 	} else if (val == 0x18 || val == 0x19) {
@@ -187,7 +189,7 @@ static void calculate_fixed_part(struct snd_motu_packet_format *formats,
 			pcm_chunks[1] += 2;
 		}
 	} else {
-		if (flags & SND_MOTU_SPEC_RX_SEPARETED_MAIN) {
+		if (flags & SND_MOTU_SPEC_RX_SEPARATED_MAIN) {
 			pcm_chunks[0] += 2;
 			pcm_chunks[1] += 2;
 		}
diff --git a/sound/firewire/motu/motu-stream.c b/sound/firewire/motu/motu-stream.c
index 813e38e6a86e..a17ddceb1bec 100644
--- a/sound/firewire/motu/motu-stream.c
+++ b/sound/firewire/motu/motu-stream.c
@@ -133,7 +133,9 @@ int snd_motu_stream_cache_packet_formats(struct snd_motu *motu)
 	return 0;
 }
 
-int snd_motu_stream_reserve_duplex(struct snd_motu *motu, unsigned int rate)
+int snd_motu_stream_reserve_duplex(struct snd_motu *motu, unsigned int rate,
+				   unsigned int frames_per_period,
+				   unsigned int frames_per_buffer)
 {
 	unsigned int curr_rate;
 	int err;
@@ -171,6 +173,14 @@ int snd_motu_stream_reserve_duplex(struct snd_motu *motu, unsigned int rate)
 			fw_iso_resources_free(&motu->tx_resources);
 			return err;
 		}
+
+		err = amdtp_domain_set_events_per_period(&motu->domain,
+					frames_per_period, frames_per_buffer);
+		if (err < 0) {
+			fw_iso_resources_free(&motu->tx_resources);
+			fw_iso_resources_free(&motu->rx_resources);
+			return err;
+		}
 	}
 
 	return 0;
@@ -250,7 +260,7 @@ int snd_motu_stream_start_duplex(struct snd_motu *motu)
 		if (err < 0)
 			goto stop_streams;
 
-		err = amdtp_domain_start(&motu->domain);
+		err = amdtp_domain_start(&motu->domain, 0);
 		if (err < 0)
 			goto stop_streams;
 
diff --git a/sound/firewire/motu/motu.c b/sound/firewire/motu/motu.c
index 72908b4de77c..f2080d720aa9 100644
--- a/sound/firewire/motu/motu.c
+++ b/sound/firewire/motu/motu.c
@@ -172,13 +172,13 @@ static void motu_bus_update(struct fw_unit *unit)
 	snd_motu_transaction_reregister(motu);
 }
 
-static const struct snd_motu_spec motu_828mk2 = {
+const struct snd_motu_spec snd_motu_spec_828mk2 = {
 	.name = "828mk2",
 	.protocol = &snd_motu_protocol_v2,
 	.flags = SND_MOTU_SPEC_SUPPORT_CLOCK_X2 |
 		 SND_MOTU_SPEC_TX_MICINST_CHUNK |
 		 SND_MOTU_SPEC_TX_RETURN_CHUNK |
-		 SND_MOTU_SPEC_RX_SEPARETED_MAIN |
+		 SND_MOTU_SPEC_RX_SEPARATED_MAIN |
 		 SND_MOTU_SPEC_HAS_OPT_IFACE_A |
 		 SND_MOTU_SPEC_RX_MIDI_2ND_Q |
 		 SND_MOTU_SPEC_TX_MIDI_2ND_Q,
@@ -187,7 +187,7 @@ static const struct snd_motu_spec motu_828mk2 = {
 	.analog_out_ports = 8,
 };
 
-const struct snd_motu_spec snd_motu_spec_traveler = {
+static const struct snd_motu_spec motu_traveler = {
 	.name = "Traveler",
 	.protocol = &snd_motu_protocol_v2,
 	.flags = SND_MOTU_SPEC_SUPPORT_CLOCK_X2 |
@@ -202,7 +202,20 @@ const struct snd_motu_spec snd_motu_spec_traveler = {
 	.analog_out_ports = 8,
 };
 
-const struct snd_motu_spec snd_motu_spec_8pre = {
+static const struct snd_motu_spec motu_ultralite = {
+	.name = "UltraLite",
+	.protocol = &snd_motu_protocol_v2,
+	.flags = SND_MOTU_SPEC_SUPPORT_CLOCK_X2 |
+		 SND_MOTU_SPEC_TX_MICINST_CHUNK | // padding.
+		 SND_MOTU_SPEC_TX_RETURN_CHUNK |
+		 SND_MOTU_SPEC_RX_MIDI_2ND_Q |
+		 SND_MOTU_SPEC_TX_MIDI_2ND_Q |
+		 SND_MOTU_SPEC_RX_SEPARATED_MAIN,
+	.analog_in_ports = 8,
+	.analog_out_ports = 8,
+};
+
+static const struct snd_motu_spec motu_8pre = {
 	.name = "8pre",
 	.protocol = &snd_motu_protocol_v2,
 	// In tx, use coax chunks for mix-return 1/2. In rx, use coax chunks for
@@ -224,7 +237,7 @@ static const struct snd_motu_spec motu_828mk3 = {
 		 SND_MOTU_SPEC_TX_MICINST_CHUNK |
 		 SND_MOTU_SPEC_TX_RETURN_CHUNK |
 		 SND_MOTU_SPEC_TX_REVERB_CHUNK |
-		 SND_MOTU_SPEC_RX_SEPARETED_MAIN |
+		 SND_MOTU_SPEC_RX_SEPARATED_MAIN |
 		 SND_MOTU_SPEC_HAS_OPT_IFACE_A |
 		 SND_MOTU_SPEC_HAS_OPT_IFACE_B |
 		 SND_MOTU_SPEC_RX_MIDI_3RD_Q |
@@ -240,7 +253,7 @@ static const struct snd_motu_spec motu_audio_express = {
 	.flags = SND_MOTU_SPEC_SUPPORT_CLOCK_X2 |
 		 SND_MOTU_SPEC_TX_MICINST_CHUNK |
 		 SND_MOTU_SPEC_TX_RETURN_CHUNK |
-		 SND_MOTU_SPEC_RX_SEPARETED_MAIN |
+		 SND_MOTU_SPEC_RX_SEPARATED_MAIN |
 		 SND_MOTU_SPEC_RX_MIDI_2ND_Q |
 		 SND_MOTU_SPEC_TX_MIDI_3RD_Q,
 	.analog_in_ports = 2,
@@ -253,7 +266,7 @@ static const struct snd_motu_spec motu_4pre = {
 	.flags = SND_MOTU_SPEC_SUPPORT_CLOCK_X2 |
 		 SND_MOTU_SPEC_TX_MICINST_CHUNK |
 		 SND_MOTU_SPEC_TX_RETURN_CHUNK |
-		 SND_MOTU_SPEC_RX_SEPARETED_MAIN,
+		 SND_MOTU_SPEC_RX_SEPARATED_MAIN,
 	.analog_in_ports = 2,
 	.analog_out_ports = 2,
 };
@@ -270,9 +283,10 @@ static const struct snd_motu_spec motu_4pre = {
 }
 
 static const struct ieee1394_device_id motu_id_table[] = {
-	SND_MOTU_DEV_ENTRY(0x000003, &motu_828mk2),
-	SND_MOTU_DEV_ENTRY(0x000009, &snd_motu_spec_traveler),
-	SND_MOTU_DEV_ENTRY(0x00000f, &snd_motu_spec_8pre),
+	SND_MOTU_DEV_ENTRY(0x000003, &snd_motu_spec_828mk2),
+	SND_MOTU_DEV_ENTRY(0x000009, &motu_traveler),
+	SND_MOTU_DEV_ENTRY(0x00000d, &motu_ultralite),
+	SND_MOTU_DEV_ENTRY(0x00000f, &motu_8pre),
 	SND_MOTU_DEV_ENTRY(0x000015, &motu_828mk3),	/* FireWire only. */
 	SND_MOTU_DEV_ENTRY(0x000035, &motu_828mk3),	/* Hybrid. */
 	SND_MOTU_DEV_ENTRY(0x000033, &motu_audio_express),
diff --git a/sound/firewire/motu/motu.h b/sound/firewire/motu/motu.h
index 350ee2c16f4a..6efbde405a0d 100644
--- a/sound/firewire/motu/motu.h
+++ b/sound/firewire/motu/motu.h
@@ -86,7 +86,7 @@ enum snd_motu_spec_flags {
 	SND_MOTU_SPEC_RX_MIDI_3RD_Q	= 0x0200,
 	SND_MOTU_SPEC_TX_MIDI_2ND_Q	= 0x0400,
 	SND_MOTU_SPEC_TX_MIDI_3RD_Q	= 0x0800,
-	SND_MOTU_SPEC_RX_SEPARETED_MAIN	= 0x1000,
+	SND_MOTU_SPEC_RX_SEPARATED_MAIN	= 0x1000,
 };
 
 #define SND_MOTU_CLOCK_RATE_COUNT	6
@@ -104,6 +104,7 @@ enum snd_motu_clock_source {
 	SND_MOTU_CLOCK_SOURCE_SPDIF_ON_COAX,
 	SND_MOTU_CLOCK_SOURCE_AESEBU_ON_XLR,
 	SND_MOTU_CLOCK_SOURCE_WORD_ON_BNC,
+	SND_MOTU_CLOCK_SOURCE_SPH,
 	SND_MOTU_CLOCK_SOURCE_UNKNOWN,
 };
 
@@ -129,8 +130,7 @@ struct snd_motu_spec {
 extern const struct snd_motu_protocol snd_motu_protocol_v2;
 extern const struct snd_motu_protocol snd_motu_protocol_v3;
 
-extern const struct snd_motu_spec snd_motu_spec_traveler;
-extern const struct snd_motu_spec snd_motu_spec_8pre;
+extern const struct snd_motu_spec snd_motu_spec_828mk2;
 
 int amdtp_motu_init(struct amdtp_stream *s, struct fw_unit *unit,
 		    enum amdtp_stream_direction dir,
@@ -154,7 +154,9 @@ void snd_motu_transaction_unregister(struct snd_motu *motu);
 int snd_motu_stream_init_duplex(struct snd_motu *motu);
 void snd_motu_stream_destroy_duplex(struct snd_motu *motu);
 int snd_motu_stream_cache_packet_formats(struct snd_motu *motu);
-int snd_motu_stream_reserve_duplex(struct snd_motu *motu, unsigned int rate);
+int snd_motu_stream_reserve_duplex(struct snd_motu *motu, unsigned int rate,
+				   unsigned int frames_per_period,
+				   unsigned int frames_per_buffer);
 int snd_motu_stream_start_duplex(struct snd_motu *motu);
 void snd_motu_stream_stop_duplex(struct snd_motu *motu);
 int snd_motu_stream_lock_try(struct snd_motu *motu);
diff --git a/sound/firewire/oxfw/oxfw-midi.c b/sound/firewire/oxfw/oxfw-midi.c
index 9bdec08cb8ea..775cba3f1f02 100644
--- a/sound/firewire/oxfw/oxfw-midi.c
+++ b/sound/firewire/oxfw/oxfw-midi.c
@@ -18,7 +18,7 @@ static int midi_capture_open(struct snd_rawmidi_substream *substream)
 
 	mutex_lock(&oxfw->mutex);
 
-	err = snd_oxfw_stream_reserve_duplex(oxfw, &oxfw->tx_stream, 0, 0);
+	err = snd_oxfw_stream_reserve_duplex(oxfw, &oxfw->tx_stream, 0, 0, 0, 0);
 	if (err >= 0) {
 		++oxfw->substreams_count;
 		err = snd_oxfw_stream_start_duplex(oxfw);
@@ -45,7 +45,7 @@ static int midi_playback_open(struct snd_rawmidi_substream *substream)
 
 	mutex_lock(&oxfw->mutex);
 
-	err = snd_oxfw_stream_reserve_duplex(oxfw, &oxfw->rx_stream, 0, 0);
+	err = snd_oxfw_stream_reserve_duplex(oxfw, &oxfw->rx_stream, 0, 0, 0, 0);
 	if (err >= 0) {
 		++oxfw->substreams_count;
 		err = snd_oxfw_stream_start_duplex(oxfw);
diff --git a/sound/firewire/oxfw/oxfw-pcm.c b/sound/firewire/oxfw/oxfw-pcm.c
index 7c6d1c277d4d..9124603edabe 100644
--- a/sound/firewire/oxfw/oxfw-pcm.c
+++ b/sound/firewire/oxfw/oxfw-pcm.c
@@ -170,30 +170,56 @@ end:
 static int pcm_open(struct snd_pcm_substream *substream)
 {
 	struct snd_oxfw *oxfw = substream->private_data;
+	struct amdtp_domain *d = &oxfw->domain;
 	int err;
 
 	err = snd_oxfw_stream_lock_try(oxfw);
 	if (err < 0)
-		goto end;
+		return err;
 
 	err = init_hw_params(oxfw, substream);
 	if (err < 0)
 		goto err_locked;
 
-	/*
-	 * When any PCM streams are already running, the available sampling
-	 * rate is limited at current value.
-	 */
-	if (amdtp_stream_pcm_running(&oxfw->tx_stream) ||
-	    amdtp_stream_pcm_running(&oxfw->rx_stream)) {
+	mutex_lock(&oxfw->mutex);
+
+	// When source of clock is not internal or any stream is reserved for
+	// transmission of PCM frames, the available sampling rate is limited
+	// at current one.
+	if (oxfw->substreams_count > 0 && d->events_per_period > 0) {
+		unsigned int frames_per_period = d->events_per_period;
+		unsigned int frames_per_buffer = d->events_per_buffer;
+
 		err = limit_to_current_params(substream);
-		if (err < 0)
-			goto end;
+		if (err < 0) {
+			mutex_unlock(&oxfw->mutex);
+			goto err_locked;
+		}
+
+		if (frames_per_period > 0) {
+			err = snd_pcm_hw_constraint_minmax(substream->runtime,
+					SNDRV_PCM_HW_PARAM_PERIOD_SIZE,
+					frames_per_period, frames_per_period);
+			if (err < 0) {
+				mutex_unlock(&oxfw->mutex);
+				goto err_locked;
+			}
+
+			err = snd_pcm_hw_constraint_minmax(substream->runtime,
+					SNDRV_PCM_HW_PARAM_BUFFER_SIZE,
+					frames_per_buffer, frames_per_buffer);
+			if (err < 0) {
+				mutex_unlock(&oxfw->mutex);
+				goto err_locked;
+			}
+		}
 	}
 
+	mutex_unlock(&oxfw->mutex);
+
 	snd_pcm_set_sync(substream);
-end:
-	return err;
+
+	return 0;
 err_locked:
 	snd_oxfw_stream_lock_release(oxfw);
 	return err;
@@ -213,18 +239,20 @@ static int pcm_capture_hw_params(struct snd_pcm_substream *substream,
 	struct snd_oxfw *oxfw = substream->private_data;
 	int err;
 
-	err = snd_pcm_lib_alloc_vmalloc_buffer(substream,
-					       params_buffer_bytes(hw_params));
+	err = snd_pcm_lib_malloc_pages(substream, params_buffer_bytes(hw_params));
 	if (err < 0)
 		return err;
 
 	if (substream->runtime->status->state == SNDRV_PCM_STATE_OPEN) {
 		unsigned int rate = params_rate(hw_params);
 		unsigned int channels = params_channels(hw_params);
+		unsigned int frames_per_period = params_period_size(hw_params);
+		unsigned int frames_per_buffer = params_buffer_size(hw_params);
 
 		mutex_lock(&oxfw->mutex);
 		err = snd_oxfw_stream_reserve_duplex(oxfw, &oxfw->tx_stream,
-						     rate, channels);
+					rate, channels, frames_per_period,
+					frames_per_buffer);
 		if (err >= 0)
 			++oxfw->substreams_count;
 		mutex_unlock(&oxfw->mutex);
@@ -238,18 +266,20 @@ static int pcm_playback_hw_params(struct snd_pcm_substream *substream,
 	struct snd_oxfw *oxfw = substream->private_data;
 	int err;
 
-	err = snd_pcm_lib_alloc_vmalloc_buffer(substream,
-					       params_buffer_bytes(hw_params));
+	err = snd_pcm_lib_malloc_pages(substream, params_buffer_bytes(hw_params));
 	if (err < 0)
 		return err;
 
 	if (substream->runtime->status->state == SNDRV_PCM_STATE_OPEN) {
 		unsigned int rate = params_rate(hw_params);
 		unsigned int channels = params_channels(hw_params);
+		unsigned int frames_per_period = params_period_size(hw_params);
+		unsigned int frames_per_buffer = params_buffer_size(hw_params);
 
 		mutex_lock(&oxfw->mutex);
 		err = snd_oxfw_stream_reserve_duplex(oxfw, &oxfw->rx_stream,
-						     rate, channels);
+					rate, channels, frames_per_period,
+					frames_per_buffer);
 		if (err >= 0)
 			++oxfw->substreams_count;
 		mutex_unlock(&oxfw->mutex);
@@ -271,7 +301,7 @@ static int pcm_capture_hw_free(struct snd_pcm_substream *substream)
 
 	mutex_unlock(&oxfw->mutex);
 
-	return snd_pcm_lib_free_vmalloc_buffer(substream);
+	return snd_pcm_lib_free_pages(substream);
 }
 static int pcm_playback_hw_free(struct snd_pcm_substream *substream)
 {
@@ -286,7 +316,7 @@ static int pcm_playback_hw_free(struct snd_pcm_substream *substream)
 
 	mutex_unlock(&oxfw->mutex);
 
-	return snd_pcm_lib_free_vmalloc_buffer(substream);
+	return snd_pcm_lib_free_pages(substream);
 }
 
 static int pcm_capture_prepare(struct snd_pcm_substream *substream)
@@ -361,27 +391,27 @@ static snd_pcm_uframes_t pcm_capture_pointer(struct snd_pcm_substream *sbstm)
 {
 	struct snd_oxfw *oxfw = sbstm->private_data;
 
-	return amdtp_stream_pcm_pointer(&oxfw->tx_stream);
+	return amdtp_domain_stream_pcm_pointer(&oxfw->domain, &oxfw->tx_stream);
 }
 static snd_pcm_uframes_t pcm_playback_pointer(struct snd_pcm_substream *sbstm)
 {
 	struct snd_oxfw *oxfw = sbstm->private_data;
 
-	return amdtp_stream_pcm_pointer(&oxfw->rx_stream);
+	return amdtp_domain_stream_pcm_pointer(&oxfw->domain, &oxfw->rx_stream);
 }
 
 static int pcm_capture_ack(struct snd_pcm_substream *substream)
 {
 	struct snd_oxfw *oxfw = substream->private_data;
 
-	return amdtp_stream_pcm_ack(&oxfw->tx_stream);
+	return amdtp_domain_stream_pcm_ack(&oxfw->domain, &oxfw->tx_stream);
 }
 
 static int pcm_playback_ack(struct snd_pcm_substream *substream)
 {
 	struct snd_oxfw *oxfw = substream->private_data;
 
-	return amdtp_stream_pcm_ack(&oxfw->rx_stream);
+	return amdtp_domain_stream_pcm_ack(&oxfw->domain, &oxfw->rx_stream);
 }
 
 int snd_oxfw_create_pcm(struct snd_oxfw *oxfw)
@@ -396,7 +426,6 @@ int snd_oxfw_create_pcm(struct snd_oxfw *oxfw)
 		.trigger   = pcm_capture_trigger,
 		.pointer   = pcm_capture_pointer,
 		.ack       = pcm_capture_ack,
-		.page      = snd_pcm_lib_get_vmalloc_page,
 	};
 	static const struct snd_pcm_ops playback_ops = {
 		.open      = pcm_open,
@@ -408,7 +437,6 @@ int snd_oxfw_create_pcm(struct snd_oxfw *oxfw)
 		.trigger   = pcm_playback_trigger,
 		.pointer   = pcm_playback_pointer,
 		.ack       = pcm_playback_ack,
-		.page      = snd_pcm_lib_get_vmalloc_page,
 	};
 	struct snd_pcm *pcm;
 	unsigned int cap = 0;
@@ -426,6 +454,8 @@ int snd_oxfw_create_pcm(struct snd_oxfw *oxfw)
 	snd_pcm_set_ops(pcm, SNDRV_PCM_STREAM_PLAYBACK, &playback_ops);
 	if (cap > 0)
 		snd_pcm_set_ops(pcm, SNDRV_PCM_STREAM_CAPTURE, &capture_ops);
+	snd_pcm_lib_preallocate_pages_for_all(pcm, SNDRV_DMA_TYPE_VMALLOC,
+					      NULL, 0, 0);
 
 	return 0;
 }
diff --git a/sound/firewire/oxfw/oxfw-stream.c b/sound/firewire/oxfw/oxfw-stream.c
index 3c9a796b6526..501a80094bf7 100644
--- a/sound/firewire/oxfw/oxfw-stream.c
+++ b/sound/firewire/oxfw/oxfw-stream.c
@@ -244,7 +244,9 @@ static int keep_resources(struct snd_oxfw *oxfw, struct amdtp_stream *stream)
 
 int snd_oxfw_stream_reserve_duplex(struct snd_oxfw *oxfw,
 				   struct amdtp_stream *stream,
-				   unsigned int rate, unsigned int pcm_channels)
+				   unsigned int rate, unsigned int pcm_channels,
+				   unsigned int frames_per_period,
+				   unsigned int frames_per_buffer)
 {
 	struct snd_oxfw_stream_formation formation;
 	enum avc_general_plug_dir dir;
@@ -305,6 +307,15 @@ int snd_oxfw_stream_reserve_duplex(struct snd_oxfw *oxfw,
 				return err;
 			}
 		}
+
+		err = amdtp_domain_set_events_per_period(&oxfw->domain,
+					frames_per_period, frames_per_buffer);
+		if (err < 0) {
+			cmp_connection_release(&oxfw->in_conn);
+			if (oxfw->has_output)
+				cmp_connection_release(&oxfw->out_conn);
+			return err;
+		}
 	}
 
 	return 0;
@@ -344,7 +355,7 @@ int snd_oxfw_stream_start_duplex(struct snd_oxfw *oxfw)
 			}
 		}
 
-		err = amdtp_domain_start(&oxfw->domain);
+		err = amdtp_domain_start(&oxfw->domain, 0);
 		if (err < 0)
 			goto error;
 
diff --git a/sound/firewire/oxfw/oxfw.h b/sound/firewire/oxfw/oxfw.h
index c9627b8c5d6e..c30e537087b0 100644
--- a/sound/firewire/oxfw/oxfw.h
+++ b/sound/firewire/oxfw/oxfw.h
@@ -103,7 +103,9 @@ int avc_general_inquiry_sig_fmt(struct fw_unit *unit, unsigned int rate,
 int snd_oxfw_stream_init_duplex(struct snd_oxfw *oxfw);
 int snd_oxfw_stream_reserve_duplex(struct snd_oxfw *oxfw,
 				   struct amdtp_stream *stream,
-				   unsigned int rate, unsigned int pcm_channels);
+				   unsigned int rate, unsigned int pcm_channels,
+				   unsigned int frames_per_period,
+				   unsigned int frames_per_buffer);
 int snd_oxfw_stream_start_duplex(struct snd_oxfw *oxfw);
 void snd_oxfw_stream_stop_duplex(struct snd_oxfw *oxfw);
 void snd_oxfw_stream_destroy_duplex(struct snd_oxfw *oxfw);
diff --git a/sound/firewire/tascam/tascam-pcm.c b/sound/firewire/tascam/tascam-pcm.c
index 2377732caa52..8e9b444c8bff 100644
--- a/sound/firewire/tascam/tascam-pcm.c
+++ b/sound/firewire/tascam/tascam-pcm.c
@@ -43,13 +43,13 @@ static int pcm_init_hw_params(struct snd_tscm *tscm,
 static int pcm_open(struct snd_pcm_substream *substream)
 {
 	struct snd_tscm *tscm = substream->private_data;
+	struct amdtp_domain *d = &tscm->domain;
 	enum snd_tscm_clock clock;
-	unsigned int rate;
 	int err;
 
 	err = snd_tscm_stream_lock_try(tscm);
 	if (err < 0)
-		goto end;
+		return err;
 
 	err = pcm_init_hw_params(tscm, substream);
 	if (err < 0)
@@ -59,19 +59,46 @@ static int pcm_open(struct snd_pcm_substream *substream)
 	if (err < 0)
 		goto err_locked;
 
-	if (clock != SND_TSCM_CLOCK_INTERNAL ||
-	    amdtp_stream_pcm_running(&tscm->rx_stream) ||
-	    amdtp_stream_pcm_running(&tscm->tx_stream)) {
+	mutex_lock(&tscm->mutex);
+
+	// When source of clock is not internal or any stream is reserved for
+	// transmission of PCM frames, the available sampling rate is limited
+	// at current one.
+	if (clock != SND_TSCM_CLOCK_INTERNAL || tscm->substreams_counter > 0) {
+		unsigned int frames_per_period = d->events_per_period;
+		unsigned int frames_per_buffer = d->events_per_buffer;
+		unsigned int rate;
+
 		err = snd_tscm_stream_get_rate(tscm, &rate);
-		if (err < 0)
+		if (err < 0) {
+			mutex_unlock(&tscm->mutex);
 			goto err_locked;
+		}
 		substream->runtime->hw.rate_min = rate;
 		substream->runtime->hw.rate_max = rate;
+
+		err = snd_pcm_hw_constraint_minmax(substream->runtime,
+					SNDRV_PCM_HW_PARAM_PERIOD_SIZE,
+					frames_per_period, frames_per_period);
+		if (err < 0) {
+			mutex_unlock(&tscm->mutex);
+			goto err_locked;
+		}
+
+		err = snd_pcm_hw_constraint_minmax(substream->runtime,
+					SNDRV_PCM_HW_PARAM_BUFFER_SIZE,
+					frames_per_buffer, frames_per_buffer);
+		if (err < 0) {
+			mutex_unlock(&tscm->mutex);
+			goto err_locked;
+		}
 	}
 
+	mutex_unlock(&tscm->mutex);
+
 	snd_pcm_set_sync(substream);
-end:
-	return err;
+
+	return 0;
 err_locked:
 	snd_tscm_stream_lock_release(tscm);
 	return err;
@@ -92,16 +119,18 @@ static int pcm_hw_params(struct snd_pcm_substream *substream,
 	struct snd_tscm *tscm = substream->private_data;
 	int err;
 
-	err = snd_pcm_lib_alloc_vmalloc_buffer(substream,
-					       params_buffer_bytes(hw_params));
+	err = snd_pcm_lib_malloc_pages(substream, params_buffer_bytes(hw_params));
 	if (err < 0)
 		return err;
 
 	if (substream->runtime->status->state == SNDRV_PCM_STATE_OPEN) {
 		unsigned int rate = params_rate(hw_params);
+		unsigned int frames_per_period = params_period_size(hw_params);
+		unsigned int frames_per_buffer = params_buffer_size(hw_params);
 
 		mutex_lock(&tscm->mutex);
-		err = snd_tscm_stream_reserve_duplex(tscm, rate);
+		err = snd_tscm_stream_reserve_duplex(tscm, rate,
+					frames_per_period, frames_per_buffer);
 		if (err >= 0)
 			++tscm->substreams_counter;
 		mutex_unlock(&tscm->mutex);
@@ -123,7 +152,7 @@ static int pcm_hw_free(struct snd_pcm_substream *substream)
 
 	mutex_unlock(&tscm->mutex);
 
-	return snd_pcm_lib_free_vmalloc_buffer(substream);
+	return snd_pcm_lib_free_pages(substream);
 }
 
 static int pcm_capture_prepare(struct snd_pcm_substream *substream)
@@ -200,28 +229,28 @@ static snd_pcm_uframes_t pcm_capture_pointer(struct snd_pcm_substream *sbstrm)
 {
 	struct snd_tscm *tscm = sbstrm->private_data;
 
-	return amdtp_stream_pcm_pointer(&tscm->tx_stream);
+	return amdtp_domain_stream_pcm_pointer(&tscm->domain, &tscm->tx_stream);
 }
 
 static snd_pcm_uframes_t pcm_playback_pointer(struct snd_pcm_substream *sbstrm)
 {
 	struct snd_tscm *tscm = sbstrm->private_data;
 
-	return amdtp_stream_pcm_pointer(&tscm->rx_stream);
+	return amdtp_domain_stream_pcm_pointer(&tscm->domain, &tscm->rx_stream);
 }
 
 static int pcm_capture_ack(struct snd_pcm_substream *substream)
 {
 	struct snd_tscm *tscm = substream->private_data;
 
-	return amdtp_stream_pcm_ack(&tscm->tx_stream);
+	return amdtp_domain_stream_pcm_ack(&tscm->domain, &tscm->tx_stream);
 }
 
 static int pcm_playback_ack(struct snd_pcm_substream *substream)
 {
 	struct snd_tscm *tscm = substream->private_data;
 
-	return amdtp_stream_pcm_ack(&tscm->rx_stream);
+	return amdtp_domain_stream_pcm_ack(&tscm->domain, &tscm->rx_stream);
 }
 
 int snd_tscm_create_pcm_devices(struct snd_tscm *tscm)
@@ -236,7 +265,6 @@ int snd_tscm_create_pcm_devices(struct snd_tscm *tscm)
 		.trigger	= pcm_capture_trigger,
 		.pointer	= pcm_capture_pointer,
 		.ack		= pcm_capture_ack,
-		.page		= snd_pcm_lib_get_vmalloc_page,
 	};
 	static const struct snd_pcm_ops playback_ops = {
 		.open		= pcm_open,
@@ -248,7 +276,6 @@ int snd_tscm_create_pcm_devices(struct snd_tscm *tscm)
 		.trigger	= pcm_playback_trigger,
 		.pointer	= pcm_playback_pointer,
 		.ack		= pcm_playback_ack,
-		.page		= snd_pcm_lib_get_vmalloc_page,
 	};
 	struct snd_pcm *pcm;
 	int err;
@@ -262,6 +289,8 @@ int snd_tscm_create_pcm_devices(struct snd_tscm *tscm)
 		 "%s PCM", tscm->card->shortname);
 	snd_pcm_set_ops(pcm, SNDRV_PCM_STREAM_PLAYBACK, &playback_ops);
 	snd_pcm_set_ops(pcm, SNDRV_PCM_STREAM_CAPTURE, &capture_ops);
+	snd_pcm_lib_preallocate_pages_for_all(pcm, SNDRV_DMA_TYPE_VMALLOC,
+					      NULL, 0, 0);
 
 	return 0;
 }
diff --git a/sound/firewire/tascam/tascam-stream.c b/sound/firewire/tascam/tascam-stream.c
index adf69a520b80..eb07e1decf9b 100644
--- a/sound/firewire/tascam/tascam-stream.c
+++ b/sound/firewire/tascam/tascam-stream.c
@@ -383,7 +383,9 @@ void snd_tscm_stream_destroy_duplex(struct snd_tscm *tscm)
 	destroy_stream(tscm, &tscm->tx_stream);
 }
 
-int snd_tscm_stream_reserve_duplex(struct snd_tscm *tscm, unsigned int rate)
+int snd_tscm_stream_reserve_duplex(struct snd_tscm *tscm, unsigned int rate,
+				   unsigned int frames_per_period,
+				   unsigned int frames_per_buffer)
 {
 	unsigned int curr_rate;
 	int err;
@@ -413,6 +415,14 @@ int snd_tscm_stream_reserve_duplex(struct snd_tscm *tscm, unsigned int rate)
 			fw_iso_resources_free(&tscm->tx_resources);
 			return err;
 		}
+
+		err = amdtp_domain_set_events_per_period(&tscm->domain,
+					frames_per_period, frames_per_buffer);
+		if (err < 0) {
+			fw_iso_resources_free(&tscm->tx_resources);
+			fw_iso_resources_free(&tscm->rx_resources);
+			return err;
+		}
 	}
 
 	return 0;
@@ -463,7 +473,7 @@ int snd_tscm_stream_start_duplex(struct snd_tscm *tscm, unsigned int rate)
 		if (err < 0)
 			goto error;
 
-		err = amdtp_domain_start(&tscm->domain);
+		err = amdtp_domain_start(&tscm->domain, 0);
 		if (err < 0)
 			return err;
 
diff --git a/sound/firewire/tascam/tascam.h b/sound/firewire/tascam/tascam.h
index 15bd335fa07f..78b7a08986a1 100644
--- a/sound/firewire/tascam/tascam.h
+++ b/sound/firewire/tascam/tascam.h
@@ -168,7 +168,9 @@ int snd_tscm_stream_get_clock(struct snd_tscm *tscm,
 int snd_tscm_stream_init_duplex(struct snd_tscm *tscm);
 void snd_tscm_stream_update_duplex(struct snd_tscm *tscm);
 void snd_tscm_stream_destroy_duplex(struct snd_tscm *tscm);
-int snd_tscm_stream_reserve_duplex(struct snd_tscm *tscm, unsigned int rate);
+int snd_tscm_stream_reserve_duplex(struct snd_tscm *tscm, unsigned int rate,
+				   unsigned int frames_per_period,
+				   unsigned int frames_per_buffer);
 int snd_tscm_stream_start_duplex(struct snd_tscm *tscm, unsigned int rate);
 void snd_tscm_stream_stop_duplex(struct snd_tscm *tscm);
 
diff --git a/sound/hda/Kconfig b/sound/hda/Kconfig
index 3d33fc1757ba..b0c88fe040ee 100644
--- a/sound/hda/Kconfig
+++ b/sound/hda/Kconfig
@@ -34,6 +34,12 @@ config SND_HDA_PREALLOC_SIZE
 	  via a proc file (/proc/asound/card*/pcm*/sub*/prealloc), too.
 
 config SND_INTEL_NHLT
-	tristate
+	bool
 	# this config should be selected only for Intel ACPI platforms.
-	# A fallback is provided so that the code compiles in all cases.
-\ No newline at end of file
+	# A fallback is provided so that the code compiles in all cases.
+
+config SND_INTEL_DSP_CONFIG
+	tristate
+	select SND_INTEL_NHLT if ACPI
+	# this config should be selected only for Intel DSP platforms.
+	# A fallback is provided so that the code compiles in all cases.
diff --git a/sound/hda/Makefile b/sound/hda/Makefile
index 8560f6ef1b19..601e617918b8 100644
--- a/sound/hda/Makefile
+++ b/sound/hda/Makefile
@@ -14,5 +14,6 @@ obj-$(CONFIG_SND_HDA_CORE) += snd-hda-core.o
 #extended hda
 obj-$(CONFIG_SND_HDA_EXT_CORE) += ext/
 
-snd-intel-nhlt-objs := intel-nhlt.o
-obj-$(CONFIG_SND_INTEL_NHLT) += snd-intel-nhlt.o
+snd-intel-dspcfg-objs := intel-dsp-config.o
+snd-intel-dspcfg-$(CONFIG_SND_INTEL_NHLT) += intel-nhlt.o
+obj-$(CONFIG_SND_INTEL_DSP_CONFIG) += snd-intel-dspcfg.o
diff --git a/sound/hda/hdac_regmap.c b/sound/hda/hdac_regmap.c
index 286361ecd640..906b1e20bae0 100644
--- a/sound/hda/hdac_regmap.c
+++ b/sound/hda/hdac_regmap.c
@@ -363,6 +363,7 @@ static const struct regmap_config hda_regmap_cfg = {
 	.reg_write = hda_reg_write,
 	.use_single_read = true,
 	.use_single_write = true,
+	.disable_locking = true,
 };
 
 /**
diff --git a/sound/hda/intel-dsp-config.c b/sound/hda/intel-dsp-config.c
new file mode 100644
index 000000000000..be1df80ed013
--- /dev/null
+++ b/sound/hda/intel-dsp-config.c
@@ -0,0 +1,357 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) 2019 Jaroslav Kysela <perex@perex.cz>
+
+#include <linux/bits.h>
+#include <linux/dmi.h>
+#include <linux/module.h>
+#include <linux/pci.h>
+#include <sound/core.h>
+#include <sound/intel-dsp-config.h>
+#include <sound/intel-nhlt.h>
+
+static int dsp_driver;
+
+module_param(dsp_driver, int, 0444);
+MODULE_PARM_DESC(dsp_driver, "Force the DSP driver for Intel DSP (0=auto, 1=legacy, 2=SST, 3=SOF)");
+
+#define FLAG_SST		BIT(0)
+#define FLAG_SOF		BIT(1)
+#define FLAG_SOF_ONLY_IF_DMIC	BIT(16)
+
+struct config_entry {
+	u32 flags;
+	u16 device;
+	const struct dmi_system_id *dmi_table;
+};
+
+/*
+ * configuration table
+ * - the order of similar PCI ID entries is important!
+ * - the first successful match will win
+ */
+static const struct config_entry config_table[] = {
+/* Merrifield */
+#if IS_ENABLED(CONFIG_SND_SOC_SOF_MERRIFIELD)
+	{
+		.flags = FLAG_SOF,
+		.device = 0x119a,
+	},
+#endif
+/* Broxton-T */
+#if IS_ENABLED(CONFIG_SND_SOC_SOF_APOLLOLAKE)
+	{
+		.flags = FLAG_SOF,
+		.device = 0x1a98,
+	},
+#endif
+/*
+ * Apollolake (Broxton-P)
+ * the legacy HDaudio driver is used except on Up Squared (SOF) and
+ * Chromebooks (SST)
+ */
+#if IS_ENABLED(CONFIG_SND_SOC_SOF_APOLLOLAKE)
+	{
+		.flags = FLAG_SOF,
+		.device = 0x5a98,
+		.dmi_table = (const struct dmi_system_id []) {
+			{
+				.ident = "Up Squared",
+				.matches = {
+					DMI_MATCH(DMI_SYS_VENDOR, "AAEON"),
+					DMI_MATCH(DMI_BOARD_NAME, "UP-APL01"),
+				}
+			},
+			{}
+		}
+	},
+#endif
+#if IS_ENABLED(CONFIG_SND_SOC_INTEL_APL)
+	{
+		.flags = FLAG_SST,
+		.device = 0x5a98,
+		.dmi_table = (const struct dmi_system_id []) {
+			{
+				.ident = "Google Chromebooks",
+				.matches = {
+					DMI_MATCH(DMI_SYS_VENDOR, "Google"),
+				}
+			},
+			{}
+		}
+	},
+#endif
+/*
+ * Skylake and Kabylake use legacy HDaudio driver except for Google
+ * Chromebooks (SST)
+ */
+
+/* Sunrise Point-LP */
+#if IS_ENABLED(CONFIG_SND_SOC_INTEL_SKL)
+	{
+		.flags = FLAG_SST,
+		.device = 0x9d70,
+		.dmi_table = (const struct dmi_system_id []) {
+			{
+				.ident = "Google Chromebooks",
+				.matches = {
+					DMI_MATCH(DMI_SYS_VENDOR, "Google"),
+				}
+			},
+			{}
+		}
+	},
+#endif
+/* Kabylake-LP */
+#if IS_ENABLED(CONFIG_SND_SOC_INTEL_KBL)
+	{
+		.flags = FLAG_SST,
+		.device = 0x9d71,
+		.dmi_table = (const struct dmi_system_id []) {
+			{
+				.ident = "Google Chromebooks",
+				.matches = {
+					DMI_MATCH(DMI_SYS_VENDOR, "Google"),
+				}
+			},
+			{}
+		}
+	},
+#endif
+
+/*
+ * Geminilake uses legacy HDaudio driver except for Google
+ * Chromebooks
+ */
+/* Geminilake */
+#if IS_ENABLED(CONFIG_SND_SOC_SOF_GEMINILAKE)
+	{
+		.flags = FLAG_SOF,
+		.device = 0x3198,
+		.dmi_table = (const struct dmi_system_id []) {
+			{
+				.ident = "Google Chromebooks",
+				.matches = {
+					DMI_MATCH(DMI_SYS_VENDOR, "Google"),
+				}
+			},
+			{}
+		}
+	},
+#endif
+
+/*
+ * CoffeeLake, CannonLake, CometLake, IceLake, TigerLake use legacy
+ * HDaudio driver except for Google Chromebooks and when DMICs are
+ * present. Two cases are required since Coreboot does not expose NHLT
+ * tables.
+ *
+ * When the Chromebook quirk is not present, it's based on information
+ * that no such device exists. When the quirk is present, it could be
+ * either based on product information or a placeholder.
+ */
+
+/* Cannonlake */
+#if IS_ENABLED(CONFIG_SND_SOC_SOF_CANNONLAKE)
+	{
+		.flags = FLAG_SOF,
+		.device = 0x9dc8,
+		.dmi_table = (const struct dmi_system_id []) {
+			{
+				.ident = "Google Chromebooks",
+				.matches = {
+					DMI_MATCH(DMI_SYS_VENDOR, "Google"),
+				}
+			},
+			{}
+		}
+	},
+	{
+		.flags = FLAG_SOF | FLAG_SOF_ONLY_IF_DMIC,
+		.device = 0x9dc8,
+	},
+#endif
+
+/* Coffelake */
+#if IS_ENABLED(CONFIG_SND_SOC_SOF_COFFEELAKE)
+	{
+		.flags = FLAG_SOF,
+		.device = 0xa348,
+		.dmi_table = (const struct dmi_system_id []) {
+			{
+				.ident = "Google Chromebooks",
+				.matches = {
+					DMI_MATCH(DMI_SYS_VENDOR, "Google"),
+				}
+			},
+			{}
+		}
+	},
+	{
+		.flags = FLAG_SOF | FLAG_SOF_ONLY_IF_DMIC,
+		.device = 0xa348,
+	},
+#endif
+
+/* Cometlake-LP */
+#if IS_ENABLED(CONFIG_SND_SOC_SOF_COMETLAKE_LP)
+	{
+		.flags = FLAG_SOF,
+		.device = 0x02c8,
+		.dmi_table = (const struct dmi_system_id []) {
+			{
+				.ident = "Google Chromebooks",
+				.matches = {
+					DMI_MATCH(DMI_SYS_VENDOR, "Google"),
+				}
+			},
+			{}
+		}
+	},
+	{
+		.flags = FLAG_SOF | FLAG_SOF_ONLY_IF_DMIC,
+		.device = 0x02c8,
+	},
+#endif
+/* Cometlake-H */
+#if IS_ENABLED(CONFIG_SND_SOC_SOF_COMETLAKE_H)
+	{
+		.flags = FLAG_SOF | FLAG_SOF_ONLY_IF_DMIC,
+		.device = 0x06c8,
+	},
+#endif
+
+/* Icelake */
+#if IS_ENABLED(CONFIG_SND_SOC_SOF_ICELAKE)
+	{
+		.flags = FLAG_SOF,
+		.device = 0x34c8,
+		.dmi_table = (const struct dmi_system_id []) {
+			{
+				.ident = "Google Chromebooks",
+				.matches = {
+					DMI_MATCH(DMI_SYS_VENDOR, "Google"),
+				}
+			},
+			{}
+		}
+	},
+	{
+		.flags = FLAG_SOF | FLAG_SOF_ONLY_IF_DMIC,
+		.device = 0x34c8,
+	},
+#endif
+
+/* Tigerlake */
+#if IS_ENABLED(CONFIG_SND_SOC_SOF_TIGERLAKE)
+	{
+		.flags = FLAG_SOF,
+		.device = 0xa0c8,
+		.dmi_table = (const struct dmi_system_id []) {
+			{
+				.ident = "Google Chromebooks",
+				.matches = {
+					DMI_MATCH(DMI_SYS_VENDOR, "Google"),
+				}
+			},
+			{}
+		}
+	},
+
+	{
+		.flags = FLAG_SOF | FLAG_SOF_ONLY_IF_DMIC,
+		.device = 0xa0c8,
+	},
+#endif
+
+/* Elkhart Lake */
+#if IS_ENABLED(CONFIG_SND_SOC_SOF_ELKHARTLAKE)
+	{
+		.flags = FLAG_SOF | FLAG_SOF_ONLY_IF_DMIC,
+		.device = 0x4b55,
+	},
+#endif
+
+};
+
+static const struct config_entry *snd_intel_dsp_find_config
+		(struct pci_dev *pci, const struct config_entry *table, u32 len)
+{
+	u16 device;
+
+	device = pci->device;
+	for (; len > 0; len--, table++) {
+		if (table->device != device)
+			continue;
+		if (table->dmi_table && !dmi_check_system(table->dmi_table))
+			continue;
+		return table;
+	}
+	return NULL;
+}
+
+static int snd_intel_dsp_check_dmic(struct pci_dev *pci)
+{
+	struct nhlt_acpi_table *nhlt;
+	int ret = 0;
+
+	nhlt = intel_nhlt_init(&pci->dev);
+	if (nhlt) {
+		if (intel_nhlt_get_dmic_geo(&pci->dev, nhlt))
+			ret = 1;
+		intel_nhlt_free(nhlt);
+	}
+	return ret;
+}
+
+int snd_intel_dsp_driver_probe(struct pci_dev *pci)
+{
+	const struct config_entry *cfg;
+
+	/* Intel vendor only */
+	if (pci->vendor != 0x8086)
+		return SND_INTEL_DSP_DRIVER_ANY;
+
+	if (dsp_driver > 0 && dsp_driver <= SND_INTEL_DSP_DRIVER_LAST)
+		return dsp_driver;
+
+	/*
+	 * detect DSP by checking class/subclass/prog-id information
+	 * class=04 subclass 03 prog-if 00: no DSP, use legacy driver
+	 * class=04 subclass 01 prog-if 00: DSP is present
+	 *  (and may be required e.g. for DMIC or SSP support)
+	 * class=04 subclass 03 prog-if 80: use DSP or legacy mode
+	 */
+	if (pci->class == 0x040300)
+		return SND_INTEL_DSP_DRIVER_LEGACY;
+	if (pci->class != 0x040100 && pci->class != 0x040380) {
+		dev_err(&pci->dev, "Unknown PCI class/subclass/prog-if information (0x%06x) found, selecting HDA legacy driver\n", pci->class);
+		return SND_INTEL_DSP_DRIVER_LEGACY;
+	}
+
+	dev_info(&pci->dev, "DSP detected with PCI class/subclass/prog-if info 0x%06x\n", pci->class);
+
+	/* find the configuration for the specific device */
+	cfg = snd_intel_dsp_find_config(pci, config_table, ARRAY_SIZE(config_table));
+	if (!cfg)
+		return SND_INTEL_DSP_DRIVER_ANY;
+
+	if (cfg->flags & FLAG_SOF) {
+		if (cfg->flags & FLAG_SOF_ONLY_IF_DMIC) {
+			if (snd_intel_dsp_check_dmic(pci)) {
+				dev_info(&pci->dev, "Digital mics found on Skylake+ platform, using SOF driver\n");
+				return SND_INTEL_DSP_DRIVER_SOF;
+			}
+		} else {
+			return SND_INTEL_DSP_DRIVER_SOF;
+		}
+	}
+
+	if (cfg->flags & FLAG_SST)
+		return SND_INTEL_DSP_DRIVER_SST;
+
+	return SND_INTEL_DSP_DRIVER_LEGACY;
+}
+EXPORT_SYMBOL_GPL(snd_intel_dsp_driver_probe);
+
+MODULE_LICENSE("GPL v2");
+MODULE_DESCRIPTION("Intel DSP config driver");
diff --git a/sound/hda/intel-nhlt.c b/sound/hda/intel-nhlt.c
index daede96f28ee..097ff6c10099 100644
--- a/sound/hda/intel-nhlt.c
+++ b/sound/hda/intel-nhlt.c
@@ -102,6 +102,3 @@ int intel_nhlt_get_dmic_geo(struct device *dev, struct nhlt_acpi_table *nhlt)
 	return dmic_geo;
 }
 EXPORT_SYMBOL_GPL(intel_nhlt_get_dmic_geo);
-
-MODULE_LICENSE("GPL v2");
-MODULE_DESCRIPTION("Intel NHLT driver");
diff --git a/sound/isa/Kconfig b/sound/isa/Kconfig
index b690ed937cbe..6ffa48dd5983 100644
--- a/sound/isa/Kconfig
+++ b/sound/isa/Kconfig
@@ -2,22 +2,22 @@
 # ALSA ISA drivers
 
 config SND_WSS_LIB
-        tristate
-        select SND_PCM
+	tristate
+	select SND_PCM
 	select SND_TIMER
 
 config SND_SB_COMMON
-        tristate
+	tristate
 
 config SND_SB8_DSP
-        tristate
-        select SND_PCM
-        select SND_SB_COMMON
+	tristate
+	select SND_PCM
+	select SND_SB_COMMON
 
 config SND_SB16_DSP
-        tristate
-        select SND_PCM
-        select SND_SB_COMMON
+	tristate
+	select SND_PCM
+	select SND_SB_COMMON
 
 menuconfig SND_ISA
 	bool "ISA sound devices"
diff --git a/sound/isa/cs423x/cs4236.c b/sound/isa/cs423x/cs4236.c
index 78dd213589b4..fa3c39cff5f8 100644
--- a/sound/isa/cs423x/cs4236.c
+++ b/sound/isa/cs423x/cs4236.c
@@ -278,7 +278,8 @@ static int snd_cs423x_pnp_init_mpu(int dev, struct pnp_dev *pdev)
 	} else {
 		mpu_port[dev] = pnp_port_start(pdev, 0);
 		if (mpu_irq[dev] >= 0 &&
-		    pnp_irq_valid(pdev, 0) && pnp_irq(pdev, 0) >= 0) {
+		    pnp_irq_valid(pdev, 0) &&
+		    pnp_irq(pdev, 0) != (resource_size_t)-1) {
 			mpu_irq[dev] = pnp_irq(pdev, 0);
 		} else {
 			mpu_irq[dev] = -1;	/* disable interrupt */
diff --git a/sound/mips/Kconfig b/sound/mips/Kconfig
index 8a33402fd415..b497b803c834 100644
--- a/sound/mips/Kconfig
+++ b/sound/mips/Kconfig
@@ -14,15 +14,15 @@ config SND_SGI_O2
 	tristate "SGI O2 Audio"
 	depends on SGI_IP32
 	select SND_PCM
-        help
-                Sound support for the SGI O2 Workstation. 
+	help
+	  Sound support for the SGI O2 Workstation.
 
 config SND_SGI_HAL2
-        tristate "SGI HAL2 Audio"
-        depends on SGI_HAS_HAL2
+	tristate "SGI HAL2 Audio"
+	depends on SGI_HAS_HAL2
 	select SND_PCM
-        help
-                Sound support for the SGI Indy and Indigo2 Workstation.
+	help
+	  Sound support for the SGI Indy and Indigo2 Workstation.
 
 endif	# SND_MIPS
 
diff --git a/sound/mips/hal2.c b/sound/mips/hal2.c
index 6676bcbd769f..c9e060939708 100644
--- a/sound/mips/hal2.c
+++ b/sound/mips/hal2.c
@@ -741,8 +741,7 @@ static int hal2_pcm_create(struct snd_hal2 *hal2)
 	snd_pcm_set_ops(pcm, SNDRV_PCM_STREAM_CAPTURE,
 			&hal2_capture_ops);
 	snd_pcm_lib_preallocate_pages_for_all(pcm, SNDRV_DMA_TYPE_CONTINUOUS,
-					   snd_dma_continuous_data(GFP_KERNEL),
-					   0, 1024 * 1024);
+					   NULL, 0, 1024 * 1024);
 
 	return 0;
 }
diff --git a/sound/mips/sgio2audio.c b/sound/mips/sgio2audio.c
index fadc1194b136..9d20ce6118a0 100644
--- a/sound/mips/sgio2audio.c
+++ b/sound/mips/sgio2audio.c
@@ -582,14 +582,13 @@ static int snd_sgio2audio_pcm_close(struct snd_pcm_substream *substream)
 static int snd_sgio2audio_pcm_hw_params(struct snd_pcm_substream *substream,
 					struct snd_pcm_hw_params *hw_params)
 {
-	return snd_pcm_lib_alloc_vmalloc_buffer(substream,
-						params_buffer_bytes(hw_params));
+	return snd_pcm_lib_malloc_pages(substream, params_buffer_bytes(hw_params));
 }
 
 /* hw_free callback */
 static int snd_sgio2audio_pcm_hw_free(struct snd_pcm_substream *substream)
 {
-	return snd_pcm_lib_free_vmalloc_buffer(substream);
+	return snd_pcm_lib_free_pages(substream);
 }
 
 /* prepare callback */
@@ -670,7 +669,6 @@ static const struct snd_pcm_ops snd_sgio2audio_playback1_ops = {
 	.prepare =     snd_sgio2audio_pcm_prepare,
 	.trigger =     snd_sgio2audio_pcm_trigger,
 	.pointer =     snd_sgio2audio_pcm_pointer,
-	.page =        snd_pcm_lib_get_vmalloc_page,
 };
 
 static const struct snd_pcm_ops snd_sgio2audio_playback2_ops = {
@@ -682,7 +680,6 @@ static const struct snd_pcm_ops snd_sgio2audio_playback2_ops = {
 	.prepare =     snd_sgio2audio_pcm_prepare,
 	.trigger =     snd_sgio2audio_pcm_trigger,
 	.pointer =     snd_sgio2audio_pcm_pointer,
-	.page =        snd_pcm_lib_get_vmalloc_page,
 };
 
 static const struct snd_pcm_ops snd_sgio2audio_capture_ops = {
@@ -694,7 +691,6 @@ static const struct snd_pcm_ops snd_sgio2audio_capture_ops = {
 	.prepare =     snd_sgio2audio_pcm_prepare,
 	.trigger =     snd_sgio2audio_pcm_trigger,
 	.pointer =     snd_sgio2audio_pcm_pointer,
-	.page =        snd_pcm_lib_get_vmalloc_page,
 };
 
 /*
@@ -720,6 +716,8 @@ static int snd_sgio2audio_new_pcm(struct snd_sgio2audio *chip)
 			&snd_sgio2audio_playback1_ops);
 	snd_pcm_set_ops(pcm, SNDRV_PCM_STREAM_CAPTURE,
 			&snd_sgio2audio_capture_ops);
+	snd_pcm_lib_preallocate_pages_for_all(pcm, SNDRV_DMA_TYPE_VMALLOC,
+					      NULL, 0, 0);
 
 	/* create second  pcm device with one outputs and no input */
 	err = snd_pcm_new(chip->card, "SGI O2 Audio", 1, 1, 0, &pcm);
@@ -732,6 +730,8 @@ static int snd_sgio2audio_new_pcm(struct snd_sgio2audio *chip)
 	/* set operators */
 	snd_pcm_set_ops(pcm, SNDRV_PCM_STREAM_PLAYBACK,
 			&snd_sgio2audio_playback2_ops);
+	snd_pcm_lib_preallocate_pages_for_all(pcm, SNDRV_DMA_TYPE_VMALLOC,
+					      NULL, 0, 0);
 
 	return 0;
 }
diff --git a/sound/pci/Kconfig b/sound/pci/Kconfig
index 7630f808d087..93bc9bef7641 100644
--- a/sound/pci/Kconfig
+++ b/sound/pci/Kconfig
@@ -217,7 +217,7 @@ config SND_CMIPCI
 	  will be called snd-cmipci.
 
 config SND_OXYGEN_LIB
-        tristate
+	tristate
 
 config SND_OXYGEN
 	tristate "C-Media 8786, 8787, 8788 (Oxygen)"
diff --git a/sound/pci/ad1889.c b/sound/pci/ad1889.c
index 4b2451287e2c..5b6452df8bbd 100644
--- a/sound/pci/ad1889.c
+++ b/sound/pci/ad1889.c
@@ -633,9 +633,9 @@ snd_ad1889_pcm_init(struct snd_ad1889 *chip, int device)
 	chip->csubs = NULL;
 
 	snd_pcm_lib_preallocate_pages_for_all(pcm, SNDRV_DMA_TYPE_DEV,
-						snd_dma_pci_data(chip->pci),
-						BUFFER_BYTES_MAX / 2,
-						BUFFER_BYTES_MAX);
+					      &chip->pci->dev,
+					      BUFFER_BYTES_MAX / 2,
+					      BUFFER_BYTES_MAX);
 
 	return 0;
 }
diff --git a/sound/pci/ali5451/ali5451.c b/sound/pci/ali5451/ali5451.c
index 6e28e381c21a..ae29df085ae1 100644
--- a/sound/pci/ali5451/ali5451.c
+++ b/sound/pci/ali5451/ali5451.c
@@ -1672,7 +1672,7 @@ static int snd_ali_pcm(struct snd_ali *codec, int device,
 				desc->capture_ops);
 
 	snd_pcm_lib_preallocate_pages_for_all(pcm, SNDRV_DMA_TYPE_DEV,
-					      snd_dma_pci_data(codec->pci),
+					      &codec->pci->dev,
 					      64*1024, 128*1024);
 
 	pcm->info_flags = 0;
diff --git a/sound/pci/als300.c b/sound/pci/als300.c
index 530799c8d3ce..cfbb8cacaaac 100644
--- a/sound/pci/als300.c
+++ b/sound/pci/als300.c
@@ -592,7 +592,8 @@ static int snd_als300_new_pcm(struct snd_als300 *chip)
 
 	/* pre-allocation of buffers */
 	snd_pcm_lib_preallocate_pages_for_all(pcm, SNDRV_DMA_TYPE_DEV,
-	snd_dma_pci_data(chip->pci), 64*1024, 64*1024);
+					      &chip->pci->dev,
+					      64*1024, 64*1024);
 	return 0;
 }
 
diff --git a/sound/pci/als4000.c b/sound/pci/als4000.c
index b06c3dbb525d..d6f5487afe52 100644
--- a/sound/pci/als4000.c
+++ b/sound/pci/als4000.c
@@ -693,7 +693,8 @@ static int snd_als4000_pcm(struct snd_sb *chip, int device)
 	snd_pcm_set_ops(pcm, SNDRV_PCM_STREAM_PLAYBACK, &snd_als4000_playback_ops);
 	snd_pcm_set_ops(pcm, SNDRV_PCM_STREAM_CAPTURE, &snd_als4000_capture_ops);
 
-	snd_pcm_lib_preallocate_pages_for_all(pcm, SNDRV_DMA_TYPE_DEV, snd_dma_pci_data(chip->pci),
+	snd_pcm_lib_preallocate_pages_for_all(pcm, SNDRV_DMA_TYPE_DEV,
+					      &chip->pci->dev,
 					      64*1024, 64*1024);
 
 	chip->pcm = pcm;
diff --git a/sound/pci/asihpi/asihpi.c b/sound/pci/asihpi/asihpi.c
index 2a21a3d99719..147005fdd3ea 100644
--- a/sound/pci/asihpi/asihpi.c
+++ b/sound/pci/asihpi/asihpi.c
@@ -1325,8 +1325,8 @@ static int snd_card_asihpi_pcm_new(struct snd_card_asihpi *asihpi, int device)
 	/*? do we want to emulate MMAP for non-BBM cards?
 	Jack doesn't work with ALSAs MMAP emulation - WHY NOT? */
 	snd_pcm_lib_preallocate_pages_for_all(pcm, SNDRV_DMA_TYPE_DEV,
-						snd_dma_pci_data(asihpi->pci),
-						64*1024, BUFFER_BYTES_MAX);
+					      &asihpi->pci->dev,
+					      64*1024, BUFFER_BYTES_MAX);
 
 	return 0;
 }
diff --git a/sound/pci/atiixp.c b/sound/pci/atiixp.c
index c953bd73a48c..1e1ededf8eb2 100644
--- a/sound/pci/atiixp.c
+++ b/sound/pci/atiixp.c
@@ -353,7 +353,7 @@ static int atiixp_build_dma_packets(struct atiixp *chip, struct atiixp_dma *dma,
 
 	if (dma->desc_buf.area == NULL) {
 		if (snd_dma_alloc_pages(SNDRV_DMA_TYPE_DEV,
-					snd_dma_pci_data(chip->pci),
+					&chip->pci->dev,
 					ATI_DESC_LIST_SIZE,
 					&dma->desc_buf) < 0)
 			return -ENOMEM;
@@ -1284,7 +1284,7 @@ static int snd_atiixp_pcm_new(struct atiixp *chip)
 	chip->pcmdevs[ATI_PCMDEV_ANALOG] = pcm;
 
 	snd_pcm_lib_preallocate_pages_for_all(pcm, SNDRV_DMA_TYPE_DEV,
-					      snd_dma_pci_data(chip->pci),
+					      &chip->pci->dev,
 					      64*1024, 128*1024);
 
 	err = snd_pcm_add_chmap_ctls(pcm, SNDRV_PCM_STREAM_PLAYBACK,
@@ -1317,7 +1317,7 @@ static int snd_atiixp_pcm_new(struct atiixp *chip)
 	chip->pcmdevs[ATI_PCMDEV_DIGITAL] = pcm;
 
 	snd_pcm_lib_preallocate_pages_for_all(pcm, SNDRV_DMA_TYPE_DEV,
-					      snd_dma_pci_data(chip->pci),
+					      &chip->pci->dev,
 					      64*1024, 128*1024);
 
 	/* pre-select AC97 SPDIF slots 10/11 */
diff --git a/sound/pci/atiixp_modem.c b/sound/pci/atiixp_modem.c
index 95d209f96581..6f088c1949f3 100644
--- a/sound/pci/atiixp_modem.c
+++ b/sound/pci/atiixp_modem.c
@@ -321,7 +321,7 @@ static int atiixp_build_dma_packets(struct atiixp_modem *chip,
 		return -ENOMEM;
 
 	if (dma->desc_buf.area == NULL) {
-		if (snd_dma_alloc_pages(SNDRV_DMA_TYPE_DEV, snd_dma_pci_data(chip->pci),
+		if (snd_dma_alloc_pages(SNDRV_DMA_TYPE_DEV, &chip->pci->dev,
 					ATI_DESC_LIST_SIZE, &dma->desc_buf) < 0)
 			return -ENOMEM;
 		dma->period_bytes = dma->periods = 0; /* clear */
@@ -995,7 +995,7 @@ static int snd_atiixp_pcm_new(struct atiixp_modem *chip)
 	chip->pcmdevs[ATI_PCMDEV_ANALOG] = pcm;
 
 	snd_pcm_lib_preallocate_pages_for_all(pcm, SNDRV_DMA_TYPE_DEV,
-					      snd_dma_pci_data(chip->pci),
+					      &chip->pci->dev,
 					      64*1024, 128*1024);
 
 	return 0;
diff --git a/sound/pci/au88x0/au88x0_pcm.c b/sound/pci/au88x0/au88x0_pcm.c
index 39ea9ef00f47..a2dcf43beedf 100644
--- a/sound/pci/au88x0/au88x0_pcm.c
+++ b/sound/pci/au88x0/au88x0_pcm.c
@@ -436,7 +436,6 @@ static const struct snd_pcm_ops snd_vortex_playback_ops = {
 	.prepare = snd_vortex_pcm_prepare,
 	.trigger = snd_vortex_pcm_trigger,
 	.pointer = snd_vortex_pcm_pointer,
-	.page = snd_pcm_sgbuf_ops_page,
 };
 
 /*
@@ -638,7 +637,7 @@ static int snd_vortex_new_pcm(vortex_t *chip, int idx, int nr)
 	/* pre-allocation of Scatter-Gather buffers */
 	
 	snd_pcm_lib_preallocate_pages_for_all(pcm, SNDRV_DMA_TYPE_DEV_SG,
-					      snd_dma_pci_data(chip->pci_dev),
+					      &chip->pci_dev->dev,
 					      0x10000, 0x10000);
 
 	switch (VORTEX_PCM_TYPE(pcm)) {
diff --git a/sound/pci/aw2/aw2-alsa.c b/sound/pci/aw2/aw2-alsa.c
index e413414181df..1cbfae856a2a 100644
--- a/sound/pci/aw2/aw2-alsa.c
+++ b/sound/pci/aw2/aw2-alsa.c
@@ -613,7 +613,7 @@ static int snd_aw2_new_pcm(struct aw2 *chip)
 	/* Preallocate continuous pages. */
 	snd_pcm_lib_preallocate_pages_for_all(pcm_playback_ana,
 					      SNDRV_DMA_TYPE_DEV,
-					      snd_dma_pci_data(chip->pci),
+					      &chip->pci->dev,
 					      64 * 1024, 64 * 1024);
 
 	err = snd_pcm_new(chip->card, "Audiowerk2 digital playback", 1, 1, 0,
@@ -645,7 +645,7 @@ static int snd_aw2_new_pcm(struct aw2 *chip)
 	/* Preallocate continuous pages. */
 	snd_pcm_lib_preallocate_pages_for_all(pcm_playback_num,
 					      SNDRV_DMA_TYPE_DEV,
-					      snd_dma_pci_data(chip->pci),
+					      &chip->pci->dev,
 					      64 * 1024, 64 * 1024);
 
 	err = snd_pcm_new(chip->card, "Audiowerk2 capture", 2, 0, 1,
@@ -678,7 +678,7 @@ static int snd_aw2_new_pcm(struct aw2 *chip)
 	/* Preallocate continuous pages. */
 	snd_pcm_lib_preallocate_pages_for_all(pcm_capture,
 					      SNDRV_DMA_TYPE_DEV,
-					      snd_dma_pci_data(chip->pci),
+					      &chip->pci->dev,
 					      64 * 1024, 64 * 1024);
 
 	/* Create control */
diff --git a/sound/pci/azt3328.c b/sound/pci/azt3328.c
index f92c9cbb955a..f475370faaaa 100644
--- a/sound/pci/azt3328.c
+++ b/sound/pci/azt3328.c
@@ -2135,8 +2135,8 @@ snd_azf3328_pcm(struct snd_azf3328 *chip)
 	chip->pcm[AZF_CODEC_CAPTURE] = pcm;
 
 	snd_pcm_lib_preallocate_pages_for_all(pcm, SNDRV_DMA_TYPE_DEV,
-						snd_dma_pci_data(chip->pci),
-							64*1024, 64*1024);
+					      &chip->pci->dev,
+					      64*1024, 64*1024);
 
 	err = snd_pcm_new(chip->card, "AZF3328 I2S OUT", AZF_PCMDEV_I2S_OUT,
 								1, 0, &pcm);
@@ -2151,8 +2151,8 @@ snd_azf3328_pcm(struct snd_azf3328 *chip)
 	chip->pcm[AZF_CODEC_I2S_OUT] = pcm;
 
 	snd_pcm_lib_preallocate_pages_for_all(pcm, SNDRV_DMA_TYPE_DEV,
-						snd_dma_pci_data(chip->pci),
-							64*1024, 64*1024);
+					      &chip->pci->dev,
+					      64*1024, 64*1024);
 
 	return 0;
 }
diff --git a/sound/pci/bt87x.c b/sound/pci/bt87x.c
index 66a5a24e7558..6bf5ac3600c5 100644
--- a/sound/pci/bt87x.c
+++ b/sound/pci/bt87x.c
@@ -217,7 +217,7 @@ static int snd_bt87x_create_risc(struct snd_bt87x *chip, struct snd_pcm_substrea
 	__le32 *risc;
 
 	if (chip->dma_risc.area == NULL) {
-		if (snd_dma_alloc_pages(SNDRV_DMA_TYPE_DEV, snd_dma_pci_data(chip->pci),
+		if (snd_dma_alloc_pages(SNDRV_DMA_TYPE_DEV, &chip->pci->dev,
 					PAGE_ALIGN(MAX_RISC_SIZE), &chip->dma_risc) < 0)
 			return -ENOMEM;
 	}
@@ -545,7 +545,6 @@ static const struct snd_pcm_ops snd_bt87x_pcm_ops = {
 	.prepare = snd_bt87x_prepare,
 	.trigger = snd_bt87x_trigger,
 	.pointer = snd_bt87x_pointer,
-	.page = snd_pcm_sgbuf_ops_page,
 };
 
 static int snd_bt87x_capture_volume_info(struct snd_kcontrol *kcontrol,
@@ -701,7 +700,7 @@ static int snd_bt87x_pcm(struct snd_bt87x *chip, int device, char *name)
 	strcpy(pcm->name, name);
 	snd_pcm_set_ops(pcm, SNDRV_PCM_STREAM_CAPTURE, &snd_bt87x_pcm_ops);
 	snd_pcm_lib_preallocate_pages_for_all(pcm, SNDRV_DMA_TYPE_DEV_SG,
-					      snd_dma_pci_data(chip->pci),
+					      &chip->pci->dev,
 					      128 * 1024,
 					      ALIGN(255 * 4092, 1024));
 	return 0;
diff --git a/sound/pci/ca0106/ca0106_main.c b/sound/pci/ca0106/ca0106_main.c
index 478412e0aa3c..abc2440dc2d9 100644
--- a/sound/pci/ca0106/ca0106_main.c
+++ b/sound/pci/ca0106/ca0106_main.c
@@ -1389,7 +1389,7 @@ static int snd_ca0106_pcm(struct snd_ca0106 *emu, int device)
 	    substream; 
 	    substream = substream->next) {
 		snd_pcm_lib_preallocate_pages(substream, SNDRV_DMA_TYPE_DEV,
-					      snd_dma_pci_data(emu->pci),
+					      &emu->pci->dev,
 					      64*1024, 64*1024);
 	}
 
@@ -1397,7 +1397,7 @@ static int snd_ca0106_pcm(struct snd_ca0106 *emu, int device)
 	      substream; 
 	      substream = substream->next) {
 		snd_pcm_lib_preallocate_pages(substream, SNDRV_DMA_TYPE_DEV,
-					      snd_dma_pci_data(emu->pci),
+					      &emu->pci->dev,
 					      64*1024, 64*1024);
 	}
   
@@ -1692,7 +1692,7 @@ static int snd_ca0106_create(int dev, struct snd_card *card,
 	chip->irq = pci->irq;
 
 	/* This stores the periods table. */
-	if (snd_dma_alloc_pages(SNDRV_DMA_TYPE_DEV, snd_dma_pci_data(pci),
+	if (snd_dma_alloc_pages(SNDRV_DMA_TYPE_DEV, &pci->dev,
 				1024, &chip->buffer) < 0) {
 		snd_ca0106_free(chip);
 		return -ENOMEM;
diff --git a/sound/pci/cmipci.c b/sound/pci/cmipci.c
index df720881eb99..dd9d62e2b633 100644
--- a/sound/pci/cmipci.c
+++ b/sound/pci/cmipci.c
@@ -1902,7 +1902,7 @@ static int snd_cmipci_pcm_new(struct cmipci *cm, int device)
 	cm->pcm = pcm;
 
 	snd_pcm_lib_preallocate_pages_for_all(pcm, SNDRV_DMA_TYPE_DEV,
-					      snd_dma_pci_data(cm->pci), 64*1024, 128*1024);
+					      &cm->pci->dev, 64*1024, 128*1024);
 
 	return 0;
 }
@@ -1924,7 +1924,7 @@ static int snd_cmipci_pcm2_new(struct cmipci *cm, int device)
 	cm->pcm2 = pcm;
 
 	snd_pcm_lib_preallocate_pages_for_all(pcm, SNDRV_DMA_TYPE_DEV,
-					      snd_dma_pci_data(cm->pci), 64*1024, 128*1024);
+					      &cm->pci->dev, 64*1024, 128*1024);
 
 	return 0;
 }
@@ -1947,7 +1947,7 @@ static int snd_cmipci_pcm_spdif_new(struct cmipci *cm, int device)
 	cm->pcm_spdif = pcm;
 
 	snd_pcm_lib_preallocate_pages_for_all(pcm, SNDRV_DMA_TYPE_DEV,
-					      snd_dma_pci_data(cm->pci), 64*1024, 128*1024);
+					      &cm->pci->dev, 64*1024, 128*1024);
 
 	err = snd_pcm_add_chmap_ctls(pcm, SNDRV_PCM_STREAM_PLAYBACK,
 				     snd_pcm_alt_chmaps, cm->max_channels, 0,
diff --git a/sound/pci/cs4281.c b/sound/pci/cs4281.c
index 04c712647853..058c1414b777 100644
--- a/sound/pci/cs4281.c
+++ b/sound/pci/cs4281.c
@@ -975,7 +975,8 @@ static int snd_cs4281_pcm(struct cs4281 *chip, int device)
 	chip->pcm = pcm;
 
 	snd_pcm_lib_preallocate_pages_for_all(pcm, SNDRV_DMA_TYPE_DEV,
-					      snd_dma_pci_data(chip->pci), 64*1024, 512*1024);
+					      &chip->pci->dev,
+					      64*1024, 512*1024);
 
 	return 0;
 }
diff --git a/sound/pci/cs46xx/cs46xx_lib.c b/sound/pci/cs46xx/cs46xx_lib.c
index 5b888b795f7e..102a62965ac1 100644
--- a/sound/pci/cs46xx/cs46xx_lib.c
+++ b/sound/pci/cs46xx/cs46xx_lib.c
@@ -1494,7 +1494,7 @@ static int _cs46xx_playback_open_channel (struct snd_pcm_substream *substream,in
 	cpcm = kzalloc(sizeof(*cpcm), GFP_KERNEL);
 	if (cpcm == NULL)
 		return -ENOMEM;
-	if (snd_dma_alloc_pages(SNDRV_DMA_TYPE_DEV, snd_dma_pci_data(chip->pci),
+	if (snd_dma_alloc_pages(SNDRV_DMA_TYPE_DEV, &chip->pci->dev,
 				PAGE_SIZE, &cpcm->hw_buf) < 0) {
 		kfree(cpcm);
 		return -ENOMEM;
@@ -1582,7 +1582,7 @@ static int snd_cs46xx_capture_open(struct snd_pcm_substream *substream)
 {
 	struct snd_cs46xx *chip = snd_pcm_substream_chip(substream);
 
-	if (snd_dma_alloc_pages(SNDRV_DMA_TYPE_DEV, snd_dma_pci_data(chip->pci),
+	if (snd_dma_alloc_pages(SNDRV_DMA_TYPE_DEV, &chip->pci->dev,
 				PAGE_SIZE, &chip->capt.hw_buf) < 0)
 		return -ENOMEM;
 	chip->capt.substream = substream;
@@ -1784,7 +1784,8 @@ int snd_cs46xx_pcm(struct snd_cs46xx *chip, int device)
 	chip->pcm = pcm;
 
 	snd_pcm_lib_preallocate_pages_for_all(pcm, SNDRV_DMA_TYPE_DEV,
-					      snd_dma_pci_data(chip->pci), 64*1024, 256*1024);
+					      &chip->pci->dev,
+					      64*1024, 256*1024);
 
 	return 0;
 }
@@ -1809,7 +1810,8 @@ int snd_cs46xx_pcm_rear(struct snd_cs46xx *chip, int device)
 	chip->pcm_rear = pcm;
 
 	snd_pcm_lib_preallocate_pages_for_all(pcm, SNDRV_DMA_TYPE_DEV,
-					      snd_dma_pci_data(chip->pci), 64*1024, 256*1024);
+					      &chip->pci->dev,
+					      64*1024, 256*1024);
 
 	return 0;
 }
@@ -1832,7 +1834,8 @@ int snd_cs46xx_pcm_center_lfe(struct snd_cs46xx *chip, int device)
 	chip->pcm_center_lfe = pcm;
 
 	snd_pcm_lib_preallocate_pages_for_all(pcm, SNDRV_DMA_TYPE_DEV,
-					      snd_dma_pci_data(chip->pci), 64*1024, 256*1024);
+					      &chip->pci->dev,
+					      64*1024, 256*1024);
 
 	return 0;
 }
@@ -1855,7 +1858,8 @@ int snd_cs46xx_pcm_iec958(struct snd_cs46xx *chip, int device)
 	chip->pcm_iec958 = pcm;
 
 	snd_pcm_lib_preallocate_pages_for_all(pcm, SNDRV_DMA_TYPE_DEV,
-					      snd_dma_pci_data(chip->pci), 64*1024, 256*1024);
+					      &chip->pci->dev,
+					      64*1024, 256*1024);
 
 	return 0;
 }
diff --git a/sound/pci/cs5535audio/cs5535audio_pcm.c b/sound/pci/cs5535audio/cs5535audio_pcm.c
index 04822bf2f987..4642e5384e83 100644
--- a/sound/pci/cs5535audio/cs5535audio_pcm.c
+++ b/sound/pci/cs5535audio/cs5535audio_pcm.c
@@ -117,7 +117,7 @@ static int cs5535audio_build_dma_packets(struct cs5535audio *cs5535au,
 
 	if (dma->desc_buf.area == NULL) {
 		if (snd_dma_alloc_pages(SNDRV_DMA_TYPE_DEV,
-					snd_dma_pci_data(cs5535au->pci),
+					&cs5535au->pci->dev,
 					CS5535AUDIO_DESC_LIST_SIZE+1,
 					&dma->desc_buf) < 0)
 			return -ENOMEM;
@@ -432,8 +432,8 @@ int snd_cs5535audio_pcm(struct cs5535audio *cs5535au)
 	strcpy(pcm->name, "CS5535 Audio");
 
 	snd_pcm_lib_preallocate_pages_for_all(pcm, SNDRV_DMA_TYPE_DEV,
-					snd_dma_pci_data(cs5535au->pci),
-					64*1024, 128*1024);
+					      &cs5535au->pci->dev,
+					      64*1024, 128*1024);
 	cs5535au->pcm = pcm;
 
 	return 0;
diff --git a/sound/pci/ctxfi/ctpcm.c b/sound/pci/ctxfi/ctpcm.c
index 89923399e646..7ae5b238703c 100644
--- a/sound/pci/ctxfi/ctpcm.c
+++ b/sound/pci/ctxfi/ctpcm.c
@@ -379,7 +379,6 @@ static const struct snd_pcm_ops ct_pcm_playback_ops = {
 	.prepare	= ct_pcm_playback_prepare,
 	.trigger	= ct_pcm_playback_trigger,
 	.pointer	= ct_pcm_playback_pointer,
-	.page		= snd_pcm_sgbuf_ops_page,
 };
 
 /* PCM operators for capture */
@@ -392,7 +391,6 @@ static const struct snd_pcm_ops ct_pcm_capture_ops = {
 	.prepare	= ct_pcm_capture_prepare,
 	.trigger	= ct_pcm_capture_trigger,
 	.pointer	= ct_pcm_capture_pointer,
-	.page		= snd_pcm_sgbuf_ops_page,
 };
 
 static const struct snd_pcm_chmap_elem surround_map[] = {
@@ -452,7 +450,8 @@ int ct_alsa_pcm_create(struct ct_atc *atc,
 				SNDRV_PCM_STREAM_CAPTURE, &ct_pcm_capture_ops);
 
 	snd_pcm_lib_preallocate_pages_for_all(pcm, SNDRV_DMA_TYPE_DEV_SG,
-			snd_dma_pci_data(atc->pci), 128*1024, 128*1024);
+					      &atc->pci->dev,
+					      128*1024, 128*1024);
 
 	chs = 2;
 	switch (device) {
diff --git a/sound/pci/ctxfi/ctvmem.c b/sound/pci/ctxfi/ctvmem.c
index 2e80b17a7104..bde28aa9e139 100644
--- a/sound/pci/ctxfi/ctvmem.c
+++ b/sound/pci/ctxfi/ctvmem.c
@@ -183,7 +183,7 @@ int ct_vm_create(struct ct_vm **rvm, struct pci_dev *pci)
 	/* Allocate page table pages */
 	for (i = 0; i < CT_PTP_NUM; i++) {
 		err = snd_dma_alloc_pages(SNDRV_DMA_TYPE_DEV,
-					  snd_dma_pci_data(pci),
+					  &pci->dev,
 					  PAGE_SIZE, &vm->ptp[i]);
 		if (err < 0)
 			break;
diff --git a/sound/pci/echoaudio/echoaudio.c b/sound/pci/echoaudio/echoaudio.c
index ca9125726be2..1465813bf7c6 100644
--- a/sound/pci/echoaudio/echoaudio.c
+++ b/sound/pci/echoaudio/echoaudio.c
@@ -324,7 +324,7 @@ static int pcm_open(struct snd_pcm_substream *substream,
 
 	/* Finally allocate a page for the scatter-gather list */
 	if ((err = snd_dma_alloc_pages(SNDRV_DMA_TYPE_DEV,
-				       snd_dma_pci_data(chip->pci),
+				       &chip->pci->dev,
 				       PAGE_SIZE, &pipe->sgpage)) < 0) {
 		dev_err(chip->card->dev, "s-g list allocation failed\n");
 		return err;
@@ -824,7 +824,6 @@ static const struct snd_pcm_ops analog_playback_ops = {
 	.prepare = pcm_prepare,
 	.trigger = pcm_trigger,
 	.pointer = pcm_pointer,
-	.page = snd_pcm_sgbuf_ops_page,
 };
 static const struct snd_pcm_ops analog_capture_ops = {
 	.open = pcm_analog_in_open,
@@ -835,7 +834,6 @@ static const struct snd_pcm_ops analog_capture_ops = {
 	.prepare = pcm_prepare,
 	.trigger = pcm_trigger,
 	.pointer = pcm_pointer,
-	.page = snd_pcm_sgbuf_ops_page,
 };
 #ifdef ECHOCARD_HAS_DIGITAL_IO
 #ifndef ECHOCARD_HAS_VMIXER
@@ -848,7 +846,6 @@ static const struct snd_pcm_ops digital_playback_ops = {
 	.prepare = pcm_prepare,
 	.trigger = pcm_trigger,
 	.pointer = pcm_pointer,
-	.page = snd_pcm_sgbuf_ops_page,
 };
 #endif /* !ECHOCARD_HAS_VMIXER */
 static const struct snd_pcm_ops digital_capture_ops = {
@@ -860,7 +857,6 @@ static const struct snd_pcm_ops digital_capture_ops = {
 	.prepare = pcm_prepare,
 	.trigger = pcm_trigger,
 	.pointer = pcm_pointer,
-	.page = snd_pcm_sgbuf_ops_page,
 };
 #endif /* ECHOCARD_HAS_DIGITAL_IO */
 
@@ -869,7 +865,7 @@ static const struct snd_pcm_ops digital_capture_ops = {
 /* Preallocate memory only for the first substream because it's the most
  * used one
  */
-static int snd_echo_preallocate_pages(struct snd_pcm *pcm, struct device *dev)
+static void snd_echo_preallocate_pages(struct snd_pcm *pcm, struct device *dev)
 {
 	struct snd_pcm_substream *ss;
 	int stream;
@@ -880,8 +876,6 @@ static int snd_echo_preallocate_pages(struct snd_pcm *pcm, struct device *dev)
 						      dev,
 						      ss->number ? 0 : 128<<10,
 						      256<<10);
-
-	return 0;
 }
 
 
@@ -908,8 +902,7 @@ static int snd_echo_new_pcm(struct echoaudio *chip)
 	strcpy(pcm->name, chip->card->shortname);
 	snd_pcm_set_ops(pcm, SNDRV_PCM_STREAM_PLAYBACK, &analog_playback_ops);
 	snd_pcm_set_ops(pcm, SNDRV_PCM_STREAM_CAPTURE, &analog_capture_ops);
-	if ((err = snd_echo_preallocate_pages(pcm, snd_dma_pci_data(chip->pci))) < 0)
-		return err;
+	snd_echo_preallocate_pages(pcm, &chip->pci->dev);
 
 #ifdef ECHOCARD_HAS_DIGITAL_IO
 	/* PCM#1 Digital inputs, no outputs */
@@ -920,8 +913,7 @@ static int snd_echo_new_pcm(struct echoaudio *chip)
 	chip->digital_pcm = pcm;
 	strcpy(pcm->name, chip->card->shortname);
 	snd_pcm_set_ops(pcm, SNDRV_PCM_STREAM_CAPTURE, &digital_capture_ops);
-	if ((err = snd_echo_preallocate_pages(pcm, snd_dma_pci_data(chip->pci))) < 0)
-		return err;
+	snd_echo_preallocate_pages(pcm, &chip->pci->dev);
 #endif /* ECHOCARD_HAS_DIGITAL_IO */
 
 #else /* ECHOCARD_HAS_VMIXER */
@@ -941,8 +933,7 @@ static int snd_echo_new_pcm(struct echoaudio *chip)
 	strcpy(pcm->name, chip->card->shortname);
 	snd_pcm_set_ops(pcm, SNDRV_PCM_STREAM_PLAYBACK, &analog_playback_ops);
 	snd_pcm_set_ops(pcm, SNDRV_PCM_STREAM_CAPTURE, &analog_capture_ops);
-	if ((err = snd_echo_preallocate_pages(pcm, snd_dma_pci_data(chip->pci))) < 0)
-		return err;
+	snd_echo_preallocate_pages(pcm, &chip->pci->dev);
 
 #ifdef ECHOCARD_HAS_DIGITAL_IO
 	/* PCM#1 Digital i/o */
@@ -955,8 +946,7 @@ static int snd_echo_new_pcm(struct echoaudio *chip)
 	strcpy(pcm->name, chip->card->shortname);
 	snd_pcm_set_ops(pcm, SNDRV_PCM_STREAM_PLAYBACK, &digital_playback_ops);
 	snd_pcm_set_ops(pcm, SNDRV_PCM_STREAM_CAPTURE, &digital_capture_ops);
-	if ((err = snd_echo_preallocate_pages(pcm, snd_dma_pci_data(chip->pci))) < 0)
-		return err;
+	snd_echo_preallocate_pages(pcm, &chip->pci->dev);
 #endif /* ECHOCARD_HAS_DIGITAL_IO */
 
 #endif /* ECHOCARD_HAS_VMIXER */
@@ -1958,7 +1948,7 @@ static int snd_echo_create(struct snd_card *card,
 
 	/* Create the DSP comm page - this is the area of memory used for most
 	of the communication with the DSP, which accesses it via bus mastering */
-	if (snd_dma_alloc_pages(SNDRV_DMA_TYPE_DEV, snd_dma_pci_data(chip->pci),
+	if (snd_dma_alloc_pages(SNDRV_DMA_TYPE_DEV, &chip->pci->dev,
 				sizeof(struct comm_page),
 				&chip->commpage_dma_buf) < 0) {
 		dev_err(chip->card->dev, "cannot allocate the comm page\n");
diff --git a/sound/pci/emu10k1/emu10k1.c b/sound/pci/emu10k1/emu10k1.c
index f208b6e217fd..29b7720d7961 100644
--- a/sound/pci/emu10k1/emu10k1.c
+++ b/sound/pci/emu10k1/emu10k1.c
@@ -124,8 +124,9 @@ static int snd_card_emu10k1_probe(struct pci_dev *pci,
 		goto error;
 	/* This stores the periods table. */
 	if (emu->card_capabilities->ca0151_chip) { /* P16V */	
-		if ((err = snd_dma_alloc_pages(SNDRV_DMA_TYPE_DEV, snd_dma_pci_data(pci),
-					       1024, &emu->p16v_buffer)) < 0)
+		err = snd_dma_alloc_pages(SNDRV_DMA_TYPE_DEV, &pci->dev,
+					  1024, &emu->p16v_buffer);
+		if (err < 0)
 			goto error;
 	}
 
diff --git a/sound/pci/emu10k1/emu10k1x.c b/sound/pci/emu10k1/emu10k1x.c
index 9cf81832259c..241b4a0631ab 100644
--- a/sound/pci/emu10k1/emu10k1x.c
+++ b/sound/pci/emu10k1/emu10k1x.c
@@ -877,7 +877,7 @@ static int snd_emu10k1x_pcm(struct emu10k1x *emu, int device)
 	emu->pcm = pcm;
 
 	snd_pcm_lib_preallocate_pages_for_all(pcm, SNDRV_DMA_TYPE_DEV,
-					      snd_dma_pci_data(emu->pci), 
+					      &emu->pci->dev,
 					      32*1024, 32*1024);
   
 	return snd_pcm_add_chmap_ctls(pcm, SNDRV_PCM_STREAM_PLAYBACK, map, 2,
@@ -936,8 +936,8 @@ static int snd_emu10k1x_create(struct snd_card *card,
 	}
 	chip->irq = pci->irq;
   
-	if(snd_dma_alloc_pages(SNDRV_DMA_TYPE_DEV, snd_dma_pci_data(pci),
-			       4 * 1024, &chip->dma_buffer) < 0) {
+	if (snd_dma_alloc_pages(SNDRV_DMA_TYPE_DEV, &pci->dev,
+				4 * 1024, &chip->dma_buffer) < 0) {
 		snd_emu10k1x_free(chip);
 		return -ENOMEM;
 	}
diff --git a/sound/pci/emu10k1/emufx.c b/sound/pci/emu10k1/emufx.c
index e053f0d58bdd..a31adecfe608 100644
--- a/sound/pci/emu10k1/emufx.c
+++ b/sound/pci/emu10k1/emufx.c
@@ -2464,7 +2464,7 @@ int snd_emu10k1_fx8010_tram_setup(struct snd_emu10k1 *emu, u32 size)
 	}
 
 	if (size > 0) {
-		if (snd_dma_alloc_pages(SNDRV_DMA_TYPE_DEV, snd_dma_pci_data(emu->pci),
+		if (snd_dma_alloc_pages(SNDRV_DMA_TYPE_DEV, &emu->pci->dev,
 					size * 2, &emu->fx8010.etram_pages) < 0)
 			return -ENOMEM;
 		memset(emu->fx8010.etram_pages.area, 0, size * 2);
diff --git a/sound/pci/emu10k1/emupcm.c b/sound/pci/emu10k1/emupcm.c
index 6530a55fb878..9a8cf3c7dd67 100644
--- a/sound/pci/emu10k1/emupcm.c
+++ b/sound/pci/emu10k1/emupcm.c
@@ -1366,7 +1366,6 @@ static const struct snd_pcm_ops snd_emu10k1_playback_ops = {
 	.prepare =		snd_emu10k1_playback_prepare,
 	.trigger =		snd_emu10k1_playback_trigger,
 	.pointer =		snd_emu10k1_playback_pointer,
-	.page =			snd_pcm_sgbuf_ops_page,
 };
 
 static const struct snd_pcm_ops snd_emu10k1_capture_ops = {
@@ -1390,7 +1389,6 @@ static const struct snd_pcm_ops snd_emu10k1_efx_playback_ops = {
 	.prepare =		snd_emu10k1_efx_playback_prepare,
 	.trigger =		snd_emu10k1_efx_playback_trigger,
 	.pointer =		snd_emu10k1_efx_playback_pointer,
-	.page =			snd_pcm_sgbuf_ops_page,
 };
 
 int snd_emu10k1_pcm(struct snd_emu10k1 *emu, int device)
@@ -1414,12 +1412,12 @@ int snd_emu10k1_pcm(struct snd_emu10k1 *emu, int device)
 
 	for (substream = pcm->streams[SNDRV_PCM_STREAM_PLAYBACK].substream; substream; substream = substream->next)
 		snd_pcm_lib_preallocate_pages(substream, SNDRV_DMA_TYPE_DEV_SG,
-					      snd_dma_pci_data(emu->pci),
+					      &emu->pci->dev,
 					      64*1024, 64*1024);
 
 	for (substream = pcm->streams[SNDRV_PCM_STREAM_CAPTURE].substream; substream; substream = substream->next)
 		snd_pcm_lib_preallocate_pages(substream, SNDRV_DMA_TYPE_DEV,
-					      snd_dma_pci_data(emu->pci),
+					      &emu->pci->dev,
 					      64*1024, 64*1024);
 
 	return 0;
@@ -1445,7 +1443,7 @@ int snd_emu10k1_pcm_multi(struct snd_emu10k1 *emu, int device)
 
 	for (substream = pcm->streams[SNDRV_PCM_STREAM_PLAYBACK].substream; substream; substream = substream->next)
 		snd_pcm_lib_preallocate_pages(substream, SNDRV_DMA_TYPE_DEV_SG,
-					      snd_dma_pci_data(emu->pci),
+					      &emu->pci->dev,
 					      64*1024, 64*1024);
 
 	return 0;
@@ -1480,7 +1478,7 @@ int snd_emu10k1_pcm_mic(struct snd_emu10k1 *emu, int device)
 	emu->pcm_mic = pcm;
 
 	snd_pcm_lib_preallocate_pages_for_all(pcm, SNDRV_DMA_TYPE_DEV,
-					      snd_dma_pci_data(emu->pci),
+					      &emu->pci->dev,
 					      64*1024, 64*1024);
 
 	return 0;
@@ -1855,7 +1853,7 @@ int snd_emu10k1_pcm_efx(struct snd_emu10k1 *emu, int device)
 		return err;
 
 	snd_pcm_lib_preallocate_pages_for_all(pcm, SNDRV_DMA_TYPE_DEV,
-					      snd_dma_pci_data(emu->pci),
+					      &emu->pci->dev,
 					      64*1024, 64*1024);
 
 	return 0;
diff --git a/sound/pci/emu10k1/memory.c b/sound/pci/emu10k1/memory.c
index 135e26544275..94b8d5b08225 100644
--- a/sound/pci/emu10k1/memory.c
+++ b/sound/pci/emu10k1/memory.c
@@ -387,7 +387,7 @@ int snd_emu10k1_alloc_pages_maybe_wider(struct snd_emu10k1 *emu, size_t size,
 	}
 
 	return snd_dma_alloc_pages(SNDRV_DMA_TYPE_DEV,
-				   snd_dma_pci_data(emu->pci), size, dmab);
+				   &emu->pci->dev, size, dmab);
 }
 
 /*
@@ -477,7 +477,7 @@ static void __synth_free_pages(struct snd_emu10k1 *emu, int first_page,
 	int page;
 
 	dmab.dev.type = SNDRV_DMA_TYPE_DEV;
-	dmab.dev.dev = snd_dma_pci_data(emu->pci);
+	dmab.dev.dev = &emu->pci->dev;
 
 	for (page = first_page; page <= last_page; page++) {
 		if (emu->page_ptr_table[page] == NULL)
diff --git a/sound/pci/emu10k1/p16v.c b/sound/pci/emu10k1/p16v.c
index eeaed555185c..ab8876855989 100644
--- a/sound/pci/emu10k1/p16v.c
+++ b/sound/pci/emu10k1/p16v.c
@@ -643,7 +643,7 @@ int snd_p16v_pcm(struct snd_emu10k1 *emu, int device)
 	    substream; 
 	    substream = substream->next) {
 		snd_pcm_lib_preallocate_pages(substream, SNDRV_DMA_TYPE_DEV,
-					      snd_dma_pci_data(emu->pci),
+					      &emu->pci->dev,
 					      (65536 - 64) * 8,
 					      (65536 - 64) * 8);
 		/*
@@ -656,7 +656,7 @@ int snd_p16v_pcm(struct snd_emu10k1 *emu, int device)
 	      substream; 
 	      substream = substream->next) {
 		snd_pcm_lib_preallocate_pages(substream, SNDRV_DMA_TYPE_DEV,
-					      snd_dma_pci_data(emu->pci),
+					      &emu->pci->dev,
 					      65536 - 64, 65536 - 64);
 		/*
 		dev_dbg(emu->card->dev,
diff --git a/sound/pci/ens1370.c b/sound/pci/ens1370.c
index b767df8181b5..0499dc863202 100644
--- a/sound/pci/ens1370.c
+++ b/sound/pci/ens1370.c
@@ -1275,7 +1275,8 @@ static int snd_ensoniq_pcm(struct ensoniq *ensoniq, int device)
 	ensoniq->pcm1 = pcm;
 
 	snd_pcm_lib_preallocate_pages_for_all(pcm, SNDRV_DMA_TYPE_DEV,
-					      snd_dma_pci_data(ensoniq->pci), 64*1024, 128*1024);
+					      &ensoniq->pci->dev,
+					      64*1024, 128*1024);
 
 #ifdef CHIP1370
 	err = snd_pcm_add_chmap_ctls(pcm, SNDRV_PCM_STREAM_PLAYBACK,
@@ -1307,7 +1308,8 @@ static int snd_ensoniq_pcm2(struct ensoniq *ensoniq, int device)
 	ensoniq->pcm2 = pcm;
 
 	snd_pcm_lib_preallocate_pages_for_all(pcm, SNDRV_DMA_TYPE_DEV,
-					      snd_dma_pci_data(ensoniq->pci), 64*1024, 128*1024);
+					      &ensoniq->pci->dev,
+					      64*1024, 128*1024);
 
 #ifdef CHIP1370
 	err = snd_pcm_add_chmap_ctls(pcm, SNDRV_PCM_STREAM_PLAYBACK,
@@ -2095,7 +2097,7 @@ static int snd_ensoniq_create(struct snd_card *card,
 	}
 	ensoniq->irq = pci->irq;
 #ifdef CHIP1370
-	if (snd_dma_alloc_pages(SNDRV_DMA_TYPE_DEV, snd_dma_pci_data(pci),
+	if (snd_dma_alloc_pages(SNDRV_DMA_TYPE_DEV, &pci->dev,
 				16, &ensoniq->dma_bug) < 0) {
 		dev_err(card->dev, "unable to allocate space for phantom area - dma_bug\n");
 		snd_ensoniq_free(ensoniq);
diff --git a/sound/pci/es1938.c b/sound/pci/es1938.c
index ecf77c8c9e59..c571c5d380ca 100644
--- a/sound/pci/es1938.c
+++ b/sound/pci/es1938.c
@@ -1032,7 +1032,8 @@ static int snd_es1938_new_pcm(struct es1938 *chip, int device)
 	strcpy(pcm->name, "ESS Solo-1");
 
 	snd_pcm_lib_preallocate_pages_for_all(pcm, SNDRV_DMA_TYPE_DEV,
-					      snd_dma_pci_data(chip->pci), 64*1024, 64*1024);
+					      &chip->pci->dev,
+					      64*1024, 64*1024);
 
 	chip->pcm = pcm;
 	return 0;
diff --git a/sound/pci/es1968.c b/sound/pci/es1968.c
index 974142535a25..7017ca9dea4a 100644
--- a/sound/pci/es1968.c
+++ b/sound/pci/es1968.c
@@ -1422,10 +1422,8 @@ snd_es1968_init_dmabuf(struct es1968 *chip)
 	int err;
 	struct esm_memory *chunk;
 
-	chip->dma.dev.type = SNDRV_DMA_TYPE_DEV;
-	chip->dma.dev.dev = snd_dma_pci_data(chip->pci);
 	err = snd_dma_alloc_pages_fallback(SNDRV_DMA_TYPE_DEV,
-					   snd_dma_pci_data(chip->pci),
+					   &chip->pci->dev,
 					   chip->total_bufsize, &chip->dma);
 	if (err < 0 || ! chip->dma.area) {
 		dev_err(chip->card->dev,
diff --git a/sound/pci/fm801.c b/sound/pci/fm801.c
index 3ef7d507eb9b..a7f8109acced 100644
--- a/sound/pci/fm801.c
+++ b/sound/pci/fm801.c
@@ -721,7 +721,7 @@ static int snd_fm801_pcm(struct fm801 *chip, int device)
 	chip->pcm = pcm;
 
 	snd_pcm_lib_preallocate_pages_for_all(pcm, SNDRV_DMA_TYPE_DEV,
-					      snd_dma_pci_data(pdev),
+					      &pdev->dev,
 					      chip->multichannel ? 128*1024 : 64*1024, 128*1024);
 
 	return snd_pcm_add_chmap_ctls(pcm, SNDRV_PCM_STREAM_PLAYBACK,
diff --git a/sound/pci/hda/Kconfig b/sound/pci/hda/Kconfig
index dae47a45b2b8..bd48335d09d7 100644
--- a/sound/pci/hda/Kconfig
+++ b/sound/pci/hda/Kconfig
@@ -12,7 +12,7 @@ config SND_HDA_INTEL
 	tristate "HD Audio PCI"
 	depends on SND_PCI
 	select SND_HDA
-	select SND_INTEL_NHLT if ACPI
+	select SND_INTEL_DSP_CONFIG
 	help
 	  Say Y here to include support for Intel "High Definition
 	  Audio" (Azalia) and its compatible devices.
@@ -23,15 +23,6 @@ config SND_HDA_INTEL
 	  To compile this driver as a module, choose M here: the module
 	  will be called snd-hda-intel.
 
-config SND_HDA_INTEL_DETECT_DMIC
-	bool "DMIC detection and probe abort"
-	depends on SND_HDA_INTEL
-	help
-	  Say Y to detect digital microphones on SKL+ devices. DMICs
-	  cannot be handled by the HDaudio legacy driver and are
-	  currently only supported by the SOF driver.
-	  If unsure say N.
-
 config SND_HDA_TEGRA
 	tristate "NVIDIA Tegra HD Audio"
 	depends on ARCH_TEGRA
diff --git a/sound/pci/hda/hda_bind.c b/sound/pci/hda/hda_bind.c
index 8272b50b8349..6a8564566375 100644
--- a/sound/pci/hda/hda_bind.c
+++ b/sound/pci/hda/hda_bind.c
@@ -43,6 +43,10 @@ static void hda_codec_unsol_event(struct hdac_device *dev, unsigned int ev)
 {
 	struct hda_codec *codec = container_of(dev, struct hda_codec, core);
 
+	/* ignore unsol events during shutdown */
+	if (codec->bus->shutdown)
+		return;
+
 	if (codec->patch_ops.unsol_event)
 		codec->patch_ops.unsol_event(codec, ev);
 }
diff --git a/sound/pci/hda/hda_controller.c b/sound/pci/hda/hda_controller.c
index 6387c7e90918..2f3b7a35f2d9 100644
--- a/sound/pci/hda/hda_controller.c
+++ b/sound/pci/hda/hda_controller.c
@@ -701,7 +701,6 @@ static const struct snd_pcm_ops azx_pcm_ops = {
 	.pointer = azx_pcm_pointer,
 	.get_time_info =  azx_get_time_info,
 	.mmap = azx_pcm_mmap,
-	.page = snd_pcm_sgbuf_ops_page,
 };
 
 static void azx_pcm_free(struct snd_pcm *pcm)
diff --git a/sound/pci/hda/hda_intel.c b/sound/pci/hda/hda_intel.c
index c52419376c74..e76a0bb6d3cf 100644
--- a/sound/pci/hda/hda_intel.c
+++ b/sound/pci/hda/hda_intel.c
@@ -46,7 +46,7 @@
 #include <sound/initval.h>
 #include <sound/hdaudio.h>
 #include <sound/hda_i915.h>
-#include <sound/intel-nhlt.h>
+#include <sound/intel-dsp-config.h>
 #include <linux/vgaarb.h>
 #include <linux/vga_switcheroo.h>
 #include <linux/firmware.h>
@@ -124,7 +124,7 @@ static char *patch[SNDRV_CARDS];
 static bool beep_mode[SNDRV_CARDS] = {[0 ... (SNDRV_CARDS-1)] =
 					CONFIG_SND_HDA_INPUT_BEEP_MODE};
 #endif
-static bool dmic_detect = IS_ENABLED(CONFIG_SND_HDA_INTEL_DETECT_DMIC);
+static bool dsp_driver = 1;
 
 module_param_array(index, int, NULL, 0444);
 MODULE_PARM_DESC(index, "Index value for Intel HD audio interface.");
@@ -159,8 +159,9 @@ module_param_array(beep_mode, bool, NULL, 0444);
 MODULE_PARM_DESC(beep_mode, "Select HDA Beep registration mode "
 			    "(0=off, 1=on) (default=1).");
 #endif
-module_param(dmic_detect, bool, 0444);
-MODULE_PARM_DESC(dmic_detect, "DMIC detect on SKL+ platforms");
+module_param(dsp_driver, bool, 0444);
+MODULE_PARM_DESC(dsp_driver, "Allow DSP driver selection (bypass this driver) "
+			     "(0=off, 1=on) (default=1)");
 
 #ifdef CONFIG_PM
 static int param_set_xint(const char *val, const struct kernel_param *kp);
@@ -368,8 +369,6 @@ enum {
 					((pci)->device == 0x160c))
 
 #define IS_BXT(pci) ((pci)->vendor == 0x8086 && (pci)->device == 0x5a98)
-#define IS_CFL(pci) ((pci)->vendor == 0x8086 && (pci)->device == 0xa348)
-#define IS_CNL(pci) ((pci)->vendor == 0x8086 && (pci)->device == 0x9dc8)
 
 static char *driver_short_names[] = {
 	[AZX_DRIVER_ICH] = "HDA Intel",
@@ -1280,11 +1279,17 @@ static void init_vga_switcheroo(struct azx *chip)
 {
 	struct hda_intel *hda = container_of(chip, struct hda_intel, chip);
 	struct pci_dev *p = get_bound_vga(chip->pci);
+	struct pci_dev *parent;
 	if (p) {
 		dev_info(chip->card->dev,
 			 "Handle vga_switcheroo audio client\n");
 		hda->use_vga_switcheroo = 1;
-		chip->bus.keep_power = 1; /* cleared in either gpu_bound op or codec probe */
+
+		/* cleared in either gpu_bound op or codec probe, or when its
+		 * upstream port has _PR3 (i.e. dGPU).
+		 */
+		parent = pci_upstream_bridge(p);
+		chip->bus.keep_power = parent ? !pci_pr3_present(parent) : 1;
 		chip->driver_caps |= AZX_DCAPS_PM_RUNTIME;
 		pci_dev_put(p);
 	}
@@ -1382,8 +1387,11 @@ static int azx_free(struct azx *chip)
 static int azx_dev_disconnect(struct snd_device *device)
 {
 	struct azx *chip = device->device_data;
+	struct hdac_bus *bus = azx_bus(chip);
 
 	chip->bus.shutdown = 1;
+	cancel_work_sync(&bus->unsol_work);
+
 	return 0;
 }
 
@@ -1753,10 +1761,6 @@ static int azx_create(struct snd_card *card, struct pci_dev *pci,
 	if (!azx_snoop(chip))
 		azx_bus(chip)->dma_type = SNDRV_DMA_TYPE_DEV_UC;
 
-	/* Workaround for a communication error on CFL (bko#199007) and CNL */
-	if (IS_CFL(pci) || IS_CNL(pci))
-		azx_bus(chip)->polling_mode = 1;
-
 	if (chip->driver_type == AZX_DRIVER_NVIDIA) {
 		dev_dbg(chip->card->dev, "Enable delay in RIRB handling\n");
 		chip->bus.needs_damn_long_delay = 1;
@@ -2020,25 +2024,6 @@ static const struct hda_controller_ops pci_hda_ops = {
 	.position_check = azx_position_check,
 };
 
-static int azx_check_dmic(struct pci_dev *pci, struct azx *chip)
-{
-	struct nhlt_acpi_table *nhlt;
-	int ret = 0;
-
-	if (chip->driver_type == AZX_DRIVER_SKL &&
-	    pci->class != 0x040300) {
-		nhlt = intel_nhlt_init(&pci->dev);
-		if (nhlt) {
-			if (intel_nhlt_get_dmic_geo(&pci->dev, nhlt)) {
-				ret = -ENODEV;
-				dev_info(&pci->dev, "Digital mics found on Skylake+ platform, aborting probe\n");
-			}
-			intel_nhlt_free(nhlt);
-		}
-	}
-	return ret;
-}
-
 static int azx_probe(struct pci_dev *pci,
 		     const struct pci_device_id *pci_id)
 {
@@ -2056,6 +2041,16 @@ static int azx_probe(struct pci_dev *pci,
 		return -ENOENT;
 	}
 
+	/*
+	 * stop probe if another Intel's DSP driver should be activated
+	 */
+	if (dsp_driver) {
+		err = snd_intel_dsp_driver_probe(pci);
+		if (err != SND_INTEL_DSP_DRIVER_ANY &&
+		    err != SND_INTEL_DSP_DRIVER_LEGACY)
+			return -ENODEV;
+	}
+
 	err = snd_card_new(&pci->dev, index[dev], id[dev], THIS_MODULE,
 			   0, &card);
 	if (err < 0) {
@@ -2069,17 +2064,6 @@ static int azx_probe(struct pci_dev *pci,
 	card->private_data = chip;
 	hda = container_of(chip, struct hda_intel, chip);
 
-	/*
-	 * stop probe if digital microphones detected on Skylake+ platform
-	 * with the DSP enabled. This is an opt-in behavior defined at build
-	 * time or at run-time with a module parameter
-	 */
-	if (dmic_detect) {
-		err = azx_check_dmic(pci, chip);
-		if (err < 0)
-			goto out_free;
-	}
-
 	pci_set_drvdata(pci, card);
 
 	err = register_vga_switcheroo(chip);
diff --git a/sound/pci/hda/hda_jack.c b/sound/pci/hda/hda_jack.c
index 1fb7b06457ae..bf0255cb0515 100644
--- a/sound/pci/hda/hda_jack.c
+++ b/sound/pci/hda/hda_jack.c
@@ -43,7 +43,7 @@ bool is_jack_detectable(struct hda_codec *codec, hda_nid_t nid)
 EXPORT_SYMBOL_GPL(is_jack_detectable);
 
 /* execute pin sense measurement */
-static u32 read_pin_sense(struct hda_codec *codec, hda_nid_t nid)
+static u32 read_pin_sense(struct hda_codec *codec, hda_nid_t nid, int dev_id)
 {
 	u32 pincap;
 	u32 val;
@@ -55,19 +55,20 @@ static u32 read_pin_sense(struct hda_codec *codec, hda_nid_t nid)
 					AC_VERB_SET_PIN_SENSE, 0);
 	}
 	val = snd_hda_codec_read(codec, nid, 0,
-				  AC_VERB_GET_PIN_SENSE, 0);
+				  AC_VERB_GET_PIN_SENSE, dev_id);
 	if (codec->inv_jack_detect)
 		val ^= AC_PINSENSE_PRESENCE;
 	return val;
 }
 
 /**
- * snd_hda_jack_tbl_get - query the jack-table entry for the given NID
+ * snd_hda_jack_tbl_get_mst - query the jack-table entry for the given NID
  * @codec: the HDA codec
  * @nid: pin NID to refer to
+ * @dev_id: pin device entry id
  */
 struct hda_jack_tbl *
-snd_hda_jack_tbl_get(struct hda_codec *codec, hda_nid_t nid)
+snd_hda_jack_tbl_get_mst(struct hda_codec *codec, hda_nid_t nid, int dev_id)
 {
 	struct hda_jack_tbl *jack = codec->jacktbl.list;
 	int i;
@@ -75,19 +76,21 @@ snd_hda_jack_tbl_get(struct hda_codec *codec, hda_nid_t nid)
 	if (!nid || !jack)
 		return NULL;
 	for (i = 0; i < codec->jacktbl.used; i++, jack++)
-		if (jack->nid == nid)
+		if (jack->nid == nid && jack->dev_id == dev_id)
 			return jack;
 	return NULL;
 }
-EXPORT_SYMBOL_GPL(snd_hda_jack_tbl_get);
+EXPORT_SYMBOL_GPL(snd_hda_jack_tbl_get_mst);
 
 /**
  * snd_hda_jack_tbl_get_from_tag - query the jack-table entry for the given tag
  * @codec: the HDA codec
  * @tag: tag value to refer to
+ * @dev_id: pin device entry id
  */
 struct hda_jack_tbl *
-snd_hda_jack_tbl_get_from_tag(struct hda_codec *codec, unsigned char tag)
+snd_hda_jack_tbl_get_from_tag(struct hda_codec *codec,
+			      unsigned char tag, int dev_id)
 {
 	struct hda_jack_tbl *jack = codec->jacktbl.list;
 	int i;
@@ -95,29 +98,62 @@ snd_hda_jack_tbl_get_from_tag(struct hda_codec *codec, unsigned char tag)
 	if (!tag || !jack)
 		return NULL;
 	for (i = 0; i < codec->jacktbl.used; i++, jack++)
-		if (jack->tag == tag)
+		if (jack->tag == tag && jack->dev_id == dev_id)
 			return jack;
 	return NULL;
 }
 EXPORT_SYMBOL_GPL(snd_hda_jack_tbl_get_from_tag);
 
+static struct hda_jack_tbl *
+any_jack_tbl_get_from_nid(struct hda_codec *codec, hda_nid_t nid)
+{
+	struct hda_jack_tbl *jack = codec->jacktbl.list;
+	int i;
+
+	if (!nid || !jack)
+		return NULL;
+	for (i = 0; i < codec->jacktbl.used; i++, jack++)
+		if (jack->nid == nid)
+			return jack;
+	return NULL;
+}
+
 /**
  * snd_hda_jack_tbl_new - create a jack-table entry for the given NID
  * @codec: the HDA codec
  * @nid: pin NID to assign
  */
 static struct hda_jack_tbl *
-snd_hda_jack_tbl_new(struct hda_codec *codec, hda_nid_t nid)
+snd_hda_jack_tbl_new(struct hda_codec *codec, hda_nid_t nid, int dev_id)
 {
-	struct hda_jack_tbl *jack = snd_hda_jack_tbl_get(codec, nid);
+	struct hda_jack_tbl *jack =
+		snd_hda_jack_tbl_get_mst(codec, nid, dev_id);
+	struct hda_jack_tbl *existing_nid_jack =
+		any_jack_tbl_get_from_nid(codec, nid);
+
+	WARN_ON(dev_id != 0 && !codec->dp_mst);
+
 	if (jack)
 		return jack;
 	jack = snd_array_new(&codec->jacktbl);
 	if (!jack)
 		return NULL;
 	jack->nid = nid;
+	jack->dev_id = dev_id;
 	jack->jack_dirty = 1;
-	jack->tag = codec->jacktbl.used;
+	if (existing_nid_jack) {
+		jack->tag = existing_nid_jack->tag;
+
+		/*
+		 * Copy jack_detect from existing_nid_jack to avoid
+		 * snd_hda_jack_detect_enable_callback_mst() making multiple
+		 * SET_UNSOLICITED_ENABLE calls on the same pin.
+		 */
+		jack->jack_detect = existing_nid_jack->jack_detect;
+	} else {
+		jack->tag = codec->jacktbl.used;
+	}
+
 	return jack;
 }
 
@@ -153,10 +189,12 @@ static void jack_detect_update(struct hda_codec *codec,
 	if (jack->phantom_jack)
 		jack->pin_sense = AC_PINSENSE_PRESENCE;
 	else
-		jack->pin_sense = read_pin_sense(codec, jack->nid);
+		jack->pin_sense = read_pin_sense(codec, jack->nid,
+						 jack->dev_id);
 
 	/* A gating jack indicates the jack is invalid if gating is unplugged */
-	if (jack->gating_jack && !snd_hda_jack_detect(codec, jack->gating_jack))
+	if (jack->gating_jack &&
+	    !snd_hda_jack_detect_mst(codec, jack->gating_jack, jack->dev_id))
 		jack->pin_sense &= ~AC_PINSENSE_PRESENCE;
 
 	jack->jack_dirty = 0;
@@ -164,7 +202,8 @@ static void jack_detect_update(struct hda_codec *codec,
 	/* If a jack is gated by this one update it. */
 	if (jack->gated_jack) {
 		struct hda_jack_tbl *gated =
-			snd_hda_jack_tbl_get(codec, jack->gated_jack);
+			snd_hda_jack_tbl_get_mst(codec, jack->gated_jack,
+						 jack->dev_id);
 		if (gated) {
 			gated->jack_dirty = 1;
 			jack_detect_update(codec, gated);
@@ -191,63 +230,69 @@ void snd_hda_jack_set_dirty_all(struct hda_codec *codec)
 EXPORT_SYMBOL_GPL(snd_hda_jack_set_dirty_all);
 
 /**
- * snd_hda_pin_sense - execute pin sense measurement
+ * snd_hda_jack_pin_sense - execute pin sense measurement
  * @codec: the CODEC to sense
  * @nid: the pin NID to sense
  *
  * Execute necessary pin sense measurement and return its Presence Detect,
  * Impedance, ELD Valid etc. status bits.
  */
-u32 snd_hda_pin_sense(struct hda_codec *codec, hda_nid_t nid)
+u32 snd_hda_jack_pin_sense(struct hda_codec *codec, hda_nid_t nid, int dev_id)
 {
-	struct hda_jack_tbl *jack = snd_hda_jack_tbl_get(codec, nid);
+	struct hda_jack_tbl *jack =
+		snd_hda_jack_tbl_get_mst(codec, nid, dev_id);
 	if (jack) {
 		jack_detect_update(codec, jack);
 		return jack->pin_sense;
 	}
-	return read_pin_sense(codec, nid);
+	return read_pin_sense(codec, nid, dev_id);
 }
-EXPORT_SYMBOL_GPL(snd_hda_pin_sense);
+EXPORT_SYMBOL_GPL(snd_hda_jack_pin_sense);
 
 /**
- * snd_hda_jack_detect_state - query pin Presence Detect status
+ * snd_hda_jack_detect_state_mst - query pin Presence Detect status
  * @codec: the CODEC to sense
  * @nid: the pin NID to sense
+ * @dev_id: pin device entry id
  *
  * Query and return the pin's Presence Detect status, as either
  * HDA_JACK_NOT_PRESENT, HDA_JACK_PRESENT or HDA_JACK_PHANTOM.
  */
-int snd_hda_jack_detect_state(struct hda_codec *codec, hda_nid_t nid)
+int snd_hda_jack_detect_state_mst(struct hda_codec *codec,
+				  hda_nid_t nid, int dev_id)
 {
-	struct hda_jack_tbl *jack = snd_hda_jack_tbl_get(codec, nid);
+	struct hda_jack_tbl *jack =
+		snd_hda_jack_tbl_get_mst(codec, nid, dev_id);
 	if (jack && jack->phantom_jack)
 		return HDA_JACK_PHANTOM;
-	else if (snd_hda_pin_sense(codec, nid) & AC_PINSENSE_PRESENCE)
+	else if (snd_hda_jack_pin_sense(codec, nid, dev_id) &
+		 AC_PINSENSE_PRESENCE)
 		return HDA_JACK_PRESENT;
 	else
 		return HDA_JACK_NOT_PRESENT;
 }
-EXPORT_SYMBOL_GPL(snd_hda_jack_detect_state);
+EXPORT_SYMBOL_GPL(snd_hda_jack_detect_state_mst);
 
 /**
- * snd_hda_jack_detect_enable - enable the jack-detection
+ * snd_hda_jack_detect_enable_mst - enable the jack-detection
  * @codec: the HDA codec
  * @nid: pin NID to enable
  * @func: callback function to register
+ * @dev_id: pin device entry id
  *
  * In the case of error, the return value will be a pointer embedded with
  * errno.  Check and handle the return value appropriately with standard
  * macros such as @IS_ERR() and @PTR_ERR().
  */
 struct hda_jack_callback *
-snd_hda_jack_detect_enable_callback(struct hda_codec *codec, hda_nid_t nid,
-				    hda_jack_callback_fn func)
+snd_hda_jack_detect_enable_callback_mst(struct hda_codec *codec, hda_nid_t nid,
+					int dev_id, hda_jack_callback_fn func)
 {
 	struct hda_jack_tbl *jack;
 	struct hda_jack_callback *callback = NULL;
 	int err;
 
-	jack = snd_hda_jack_tbl_new(codec, nid);
+	jack = snd_hda_jack_tbl_new(codec, nid, dev_id);
 	if (!jack)
 		return ERR_PTR(-ENOMEM);
 	if (func) {
@@ -256,6 +301,7 @@ snd_hda_jack_detect_enable_callback(struct hda_codec *codec, hda_nid_t nid,
 			return ERR_PTR(-ENOMEM);
 		callback->func = func;
 		callback->nid = jack->nid;
+		callback->dev_id = jack->dev_id;
 		callback->next = jack->callback;
 		jack->callback = callback;
 	}
@@ -272,19 +318,24 @@ snd_hda_jack_detect_enable_callback(struct hda_codec *codec, hda_nid_t nid,
 		return ERR_PTR(err);
 	return callback;
 }
-EXPORT_SYMBOL_GPL(snd_hda_jack_detect_enable_callback);
+EXPORT_SYMBOL_GPL(snd_hda_jack_detect_enable_callback_mst);
 
 /**
  * snd_hda_jack_detect_enable - Enable the jack detection on the given pin
  * @codec: the HDA codec
  * @nid: pin NID to enable jack detection
+ * @dev_id: pin device entry id
  *
  * Enable the jack detection with the default callback.  Returns zero if
  * successful or a negative error code.
  */
-int snd_hda_jack_detect_enable(struct hda_codec *codec, hda_nid_t nid)
+int snd_hda_jack_detect_enable(struct hda_codec *codec, hda_nid_t nid,
+			       int dev_id)
 {
-	return PTR_ERR_OR_ZERO(snd_hda_jack_detect_enable_callback(codec, nid, NULL));
+	return PTR_ERR_OR_ZERO(snd_hda_jack_detect_enable_callback_mst(codec,
+								       nid,
+								       dev_id,
+								       NULL));
 }
 EXPORT_SYMBOL_GPL(snd_hda_jack_detect_enable);
 
@@ -299,8 +350,11 @@ EXPORT_SYMBOL_GPL(snd_hda_jack_detect_enable);
 int snd_hda_jack_set_gating_jack(struct hda_codec *codec, hda_nid_t gated_nid,
 				 hda_nid_t gating_nid)
 {
-	struct hda_jack_tbl *gated = snd_hda_jack_tbl_new(codec, gated_nid);
-	struct hda_jack_tbl *gating = snd_hda_jack_tbl_new(codec, gating_nid);
+	struct hda_jack_tbl *gated = snd_hda_jack_tbl_new(codec, gated_nid, 0);
+	struct hda_jack_tbl *gating =
+		snd_hda_jack_tbl_new(codec, gating_nid, 0);
+
+	WARN_ON(codec->dp_mst);
 
 	if (!gated || !gating)
 		return -EINVAL;
@@ -376,9 +430,10 @@ static void hda_free_jack_priv(struct snd_jack *jack)
 }
 
 /**
- * snd_hda_jack_add_kctl - Add a kctl for the given pin
+ * snd_hda_jack_add_kctl_mst - Add a kctl for the given pin
  * @codec: the HDA codec
  * @nid: pin NID to assign
+ * @dev_id : pin device entry id
  * @name: string name for the jack
  * @phantom_jack: flag to deal as a phantom jack
  * @type: jack type bits to be reported, 0 for guessing from pincfg
@@ -387,15 +442,15 @@ static void hda_free_jack_priv(struct snd_jack *jack)
  * This assigns a jack-detection kctl to the given pin.  The kcontrol
  * will have the given name and index.
  */
-int snd_hda_jack_add_kctl(struct hda_codec *codec, hda_nid_t nid,
-			  const char *name, bool phantom_jack,
-			  int type, const struct hda_jack_keymap *keymap)
+int snd_hda_jack_add_kctl_mst(struct hda_codec *codec, hda_nid_t nid,
+			      int dev_id, const char *name, bool phantom_jack,
+			      int type, const struct hda_jack_keymap *keymap)
 {
 	struct hda_jack_tbl *jack;
 	const struct hda_jack_keymap *map;
 	int err, state, buttons;
 
-	jack = snd_hda_jack_tbl_new(codec, nid);
+	jack = snd_hda_jack_tbl_new(codec, nid, dev_id);
 	if (!jack)
 		return 0;
 	if (jack->jack)
@@ -425,12 +480,12 @@ int snd_hda_jack_add_kctl(struct hda_codec *codec, hda_nid_t nid,
 			snd_jack_set_key(jack->jack, map->type, map->key);
 	}
 
-	state = snd_hda_jack_detect(codec, nid);
+	state = snd_hda_jack_detect_mst(codec, nid, dev_id);
 	snd_jack_report(jack->jack, state ? jack->type : 0);
 
 	return 0;
 }
-EXPORT_SYMBOL_GPL(snd_hda_jack_add_kctl);
+EXPORT_SYMBOL_GPL(snd_hda_jack_add_kctl_mst);
 
 static int add_jack_kctl(struct hda_codec *codec, hda_nid_t nid,
 			 const struct auto_pin_cfg *cfg,
@@ -441,6 +496,8 @@ static int add_jack_kctl(struct hda_codec *codec, hda_nid_t nid,
 	int err;
 	bool phantom_jack;
 
+	WARN_ON(codec->dp_mst);
+
 	if (!nid)
 		return 0;
 	def_conf = snd_hda_codec_get_pincfg(codec, nid);
@@ -462,7 +519,7 @@ static int add_jack_kctl(struct hda_codec *codec, hda_nid_t nid,
 		return err;
 
 	if (!phantom_jack)
-		return snd_hda_jack_detect_enable(codec, nid);
+		return snd_hda_jack_detect_enable(codec, nid, 0);
 	return 0;
 }
 
@@ -540,7 +597,8 @@ static void call_jack_callback(struct hda_codec *codec, unsigned int res,
 	}
 	if (jack->gated_jack) {
 		struct hda_jack_tbl *gated =
-			snd_hda_jack_tbl_get(codec, jack->gated_jack);
+			snd_hda_jack_tbl_get_mst(codec, jack->gated_jack,
+						 jack->dev_id);
 		if (gated) {
 			for (cb = gated->callback; cb; cb = cb->next) {
 				cb->jack = gated;
@@ -561,7 +619,14 @@ void snd_hda_jack_unsol_event(struct hda_codec *codec, unsigned int res)
 	struct hda_jack_tbl *event;
 	int tag = (res & AC_UNSOL_RES_TAG) >> AC_UNSOL_RES_TAG_SHIFT;
 
-	event = snd_hda_jack_tbl_get_from_tag(codec, tag);
+	if (codec->dp_mst) {
+		int dev_entry =
+			(res & AC_UNSOL_RES_DE) >> AC_UNSOL_RES_DE_SHIFT;
+
+		event = snd_hda_jack_tbl_get_from_tag(codec, tag, dev_entry);
+	} else {
+		event = snd_hda_jack_tbl_get_from_tag(codec, tag, 0);
+	}
 	if (!event)
 		return;
 	event->jack_dirty = 1;
diff --git a/sound/pci/hda/hda_jack.h b/sound/pci/hda/hda_jack.h
index 22fe7ee43e82..727b6d3ba454 100644
--- a/sound/pci/hda/hda_jack.h
+++ b/sound/pci/hda/hda_jack.h
@@ -19,6 +19,7 @@ typedef void (*hda_jack_callback_fn) (struct hda_codec *, struct hda_jack_callba
 
 struct hda_jack_callback {
 	hda_nid_t nid;
+	int dev_id;
 	hda_jack_callback_fn func;
 	unsigned int private_data;	/* arbitrary data */
 	unsigned int unsol_res;		/* unsolicited event bits */
@@ -28,6 +29,7 @@ struct hda_jack_callback {
 
 struct hda_jack_tbl {
 	hda_nid_t nid;
+	int dev_id;
 	unsigned char tag;		/* unsol event tag */
 	struct hda_jack_callback *callback;
 	/* jack-detection stuff */
@@ -49,46 +51,129 @@ struct hda_jack_keymap {
 };
 
 struct hda_jack_tbl *
-snd_hda_jack_tbl_get(struct hda_codec *codec, hda_nid_t nid);
+snd_hda_jack_tbl_get_mst(struct hda_codec *codec, hda_nid_t nid, int dev_id);
+
+/**
+ * snd_hda_jack_tbl_get - query the jack-table entry for the given NID
+ * @codec: the HDA codec
+ * @nid: pin NID to refer to
+ */
+static inline struct hda_jack_tbl *
+snd_hda_jack_tbl_get(struct hda_codec *codec, hda_nid_t nid)
+{
+	return snd_hda_jack_tbl_get_mst(codec, nid, 0);
+}
+
 struct hda_jack_tbl *
-snd_hda_jack_tbl_get_from_tag(struct hda_codec *codec, unsigned char tag);
+snd_hda_jack_tbl_get_from_tag(struct hda_codec *codec,
+			      unsigned char tag, int dev_id);
 
 void snd_hda_jack_tbl_clear(struct hda_codec *codec);
 
 void snd_hda_jack_set_dirty_all(struct hda_codec *codec);
 
-int snd_hda_jack_detect_enable(struct hda_codec *codec, hda_nid_t nid);
+int snd_hda_jack_detect_enable(struct hda_codec *codec, hda_nid_t nid,
+			       int dev_id);
+
 struct hda_jack_callback *
+snd_hda_jack_detect_enable_callback_mst(struct hda_codec *codec, hda_nid_t nid,
+					int dev_id, hda_jack_callback_fn cb);
+
+/**
+ * snd_hda_jack_detect_enable - enable the jack-detection
+ * @codec: the HDA codec
+ * @nid: pin NID to enable
+ * @func: callback function to register
+ *
+ * In the case of error, the return value will be a pointer embedded with
+ * errno.  Check and handle the return value appropriately with standard
+ * macros such as @IS_ERR() and @PTR_ERR().
+ */
+static inline struct hda_jack_callback *
 snd_hda_jack_detect_enable_callback(struct hda_codec *codec, hda_nid_t nid,
-				    hda_jack_callback_fn cb);
+				    hda_jack_callback_fn cb)
+{
+	return snd_hda_jack_detect_enable_callback_mst(codec, nid, 0, cb);
+}
 
 int snd_hda_jack_set_gating_jack(struct hda_codec *codec, hda_nid_t gated_nid,
 				 hda_nid_t gating_nid);
 
-u32 snd_hda_pin_sense(struct hda_codec *codec, hda_nid_t nid);
+u32 snd_hda_jack_pin_sense(struct hda_codec *codec, hda_nid_t nid, int dev_id);
 
 /* the jack state returned from snd_hda_jack_detect_state() */
 enum {
 	HDA_JACK_NOT_PRESENT, HDA_JACK_PRESENT, HDA_JACK_PHANTOM,
 };
 
-int snd_hda_jack_detect_state(struct hda_codec *codec, hda_nid_t nid);
+int snd_hda_jack_detect_state_mst(struct hda_codec *codec, hda_nid_t nid,
+				  int dev_id);
+
+/**
+ * snd_hda_jack_detect_state - query pin Presence Detect status
+ * @codec: the CODEC to sense
+ * @nid: the pin NID to sense
+ *
+ * Query and return the pin's Presence Detect status, as either
+ * HDA_JACK_NOT_PRESENT, HDA_JACK_PRESENT or HDA_JACK_PHANTOM.
+ */
+static inline int
+snd_hda_jack_detect_state(struct hda_codec *codec, hda_nid_t nid)
+{
+	return snd_hda_jack_detect_state_mst(codec, nid, 0);
+}
+
+/**
+ * snd_hda_jack_detect_mst - Detect the jack
+ * @codec: the HDA codec
+ * @nid: pin NID to check jack detection
+ * @dev_id: pin device entry id
+ */
+static inline bool
+snd_hda_jack_detect_mst(struct hda_codec *codec, hda_nid_t nid, int dev_id)
+{
+	return snd_hda_jack_detect_state_mst(codec, nid, dev_id) !=
+			HDA_JACK_NOT_PRESENT;
+}
 
 /**
  * snd_hda_jack_detect - Detect the jack
  * @codec: the HDA codec
  * @nid: pin NID to check jack detection
  */
-static inline bool snd_hda_jack_detect(struct hda_codec *codec, hda_nid_t nid)
+static inline bool
+snd_hda_jack_detect(struct hda_codec *codec, hda_nid_t nid)
 {
-	return snd_hda_jack_detect_state(codec, nid) != HDA_JACK_NOT_PRESENT;
+	return snd_hda_jack_detect_mst(codec, nid, 0);
 }
 
 bool is_jack_detectable(struct hda_codec *codec, hda_nid_t nid);
 
-int snd_hda_jack_add_kctl(struct hda_codec *codec, hda_nid_t nid,
-			  const char *name, bool phantom_jack,
-			  int type, const struct hda_jack_keymap *keymap);
+int snd_hda_jack_add_kctl_mst(struct hda_codec *codec, hda_nid_t nid,
+			      int dev_id, const char *name, bool phantom_jack,
+			      int type, const struct hda_jack_keymap *keymap);
+
+/**
+ * snd_hda_jack_add_kctl - Add a kctl for the given pin
+ * @codec: the HDA codec
+ * @nid: pin NID to assign
+ * @name: string name for the jack
+ * @phantom_jack: flag to deal as a phantom jack
+ * @type: jack type bits to be reported, 0 for guessing from pincfg
+ * @keymap: optional jack / key mapping
+ *
+ * This assigns a jack-detection kctl to the given pin.  The kcontrol
+ * will have the given name and index.
+ */
+static inline int
+snd_hda_jack_add_kctl(struct hda_codec *codec, hda_nid_t nid,
+		      const char *name, bool phantom_jack,
+		      int type, const struct hda_jack_keymap *keymap)
+{
+	return snd_hda_jack_add_kctl_mst(codec, nid, 0,
+					 name, phantom_jack, type, keymap);
+}
+
 int snd_hda_jack_add_kctls(struct hda_codec *codec,
 			   const struct auto_pin_cfg *cfg);
 
diff --git a/sound/pci/hda/patch_conexant.c b/sound/pci/hda/patch_conexant.c
index 968d3caab6ac..90aa0f400a57 100644
--- a/sound/pci/hda/patch_conexant.c
+++ b/sound/pci/hda/patch_conexant.c
@@ -910,6 +910,7 @@ static const struct snd_pci_quirk cxt5066_fixups[] = {
 	SND_PCI_QUIRK(0x103c, 0x837f, "HP ProBook 470 G5", CXT_FIXUP_MUTE_LED_GPIO),
 	SND_PCI_QUIRK(0x103c, 0x8299, "HP 800 G3 SFF", CXT_FIXUP_HP_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x103c, 0x829a, "HP 800 G3 DM", CXT_FIXUP_HP_MIC_NO_PRESENCE),
+	SND_PCI_QUIRK(0x103c, 0x8402, "HP ProBook 645 G4", CXT_FIXUP_MUTE_LED_GPIO),
 	SND_PCI_QUIRK(0x103c, 0x8455, "HP Z2 G4", CXT_FIXUP_HP_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x103c, 0x8456, "HP Z2 G4 SFF", CXT_FIXUP_HP_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x103c, 0x8457, "HP Z2 G4 mini", CXT_FIXUP_HP_MIC_NO_PRESENCE),
diff --git a/sound/pci/hda/patch_hdmi.c b/sound/pci/hda/patch_hdmi.c
index 78bd2e3722c7..bffde594e204 100644
--- a/sound/pci/hda/patch_hdmi.c
+++ b/sound/pci/hda/patch_hdmi.c
@@ -37,25 +37,6 @@ static bool static_hdmi_pcm;
 module_param(static_hdmi_pcm, bool, 0644);
 MODULE_PARM_DESC(static_hdmi_pcm, "Don't restrict PCM parameters per ELD info");
 
-#define is_haswell(codec)  ((codec)->core.vendor_id == 0x80862807)
-#define is_broadwell(codec)    ((codec)->core.vendor_id == 0x80862808)
-#define is_skylake(codec) ((codec)->core.vendor_id == 0x80862809)
-#define is_broxton(codec) ((codec)->core.vendor_id == 0x8086280a)
-#define is_kabylake(codec) ((codec)->core.vendor_id == 0x8086280b)
-#define is_geminilake(codec) (((codec)->core.vendor_id == 0x8086280d) || \
-				((codec)->core.vendor_id == 0x80862800))
-#define is_cannonlake(codec) ((codec)->core.vendor_id == 0x8086280c)
-#define is_icelake(codec) ((codec)->core.vendor_id == 0x8086280f)
-#define is_tigerlake(codec) ((codec)->core.vendor_id == 0x80862812)
-#define is_haswell_plus(codec) (is_haswell(codec) || is_broadwell(codec) \
-				|| is_skylake(codec) || is_broxton(codec) \
-				|| is_kabylake(codec) || is_geminilake(codec) \
-				|| is_cannonlake(codec) || is_icelake(codec) \
-				|| is_tigerlake(codec))
-#define is_valleyview(codec) ((codec)->core.vendor_id == 0x80862882)
-#define is_cherryview(codec) ((codec)->core.vendor_id == 0x80862883)
-#define is_valleyview_plus(codec) (is_valleyview(codec) || is_cherryview(codec))
-
 struct hdmi_spec_per_cvt {
 	hda_nid_t cvt_nid;
 	int assigned;
@@ -99,16 +80,19 @@ struct hdmi_spec_per_pin {
 /* operations used by generic code that can be overridden by patches */
 struct hdmi_ops {
 	int (*pin_get_eld)(struct hda_codec *codec, hda_nid_t pin_nid,
-			   unsigned char *buf, int *eld_size);
+			   int dev_id, unsigned char *buf, int *eld_size);
 
 	void (*pin_setup_infoframe)(struct hda_codec *codec, hda_nid_t pin_nid,
+				    int dev_id,
 				    int ca, int active_channels, int conn_type);
 
 	/* enable/disable HBR (HD passthrough) */
-	int (*pin_hbr_setup)(struct hda_codec *codec, hda_nid_t pin_nid, bool hbr);
+	int (*pin_hbr_setup)(struct hda_codec *codec, hda_nid_t pin_nid,
+			     int dev_id, bool hbr);
 
 	int (*setup_stream)(struct hda_codec *codec, hda_nid_t cvt_nid,
-			    hda_nid_t pin_nid, u32 stream_tag, int format);
+			    hda_nid_t pin_nid, int dev_id, u32 stream_tag,
+			    int format);
 
 	void (*pin_cvt_fixup)(struct hda_codec *codec,
 			      struct hdmi_spec_per_pin *per_pin,
@@ -162,6 +146,7 @@ struct hdmi_spec {
 
 	bool dyn_pin_out;
 	bool dyn_pcm_assign;
+	bool intel_hsw_fixup;	/* apply Intel platform-specific fixups */
 	/*
 	 * Non-generic VIA/NVIDIA specific
 	 */
@@ -654,8 +639,16 @@ static bool hdmi_infoframe_uptodate(struct hda_codec *codec, hda_nid_t pin_nid,
 	return true;
 }
 
+static int hdmi_pin_get_eld(struct hda_codec *codec, hda_nid_t nid,
+			    int dev_id, unsigned char *buf, int *eld_size)
+{
+	snd_hda_set_dev_select(codec, nid, dev_id);
+
+	return snd_hdmi_get_eld(codec, nid, buf, eld_size);
+}
+
 static void hdmi_pin_setup_infoframe(struct hda_codec *codec,
-				     hda_nid_t pin_nid,
+				     hda_nid_t pin_nid, int dev_id,
 				     int ca, int active_channels,
 				     int conn_type)
 {
@@ -685,6 +678,8 @@ static void hdmi_pin_setup_infoframe(struct hda_codec *codec,
 		return;
 	}
 
+	snd_hda_set_dev_select(codec, pin_nid, dev_id);
+
 	/*
 	 * sizeof(ai) is used instead of sizeof(*hdmi_ai) or
 	 * sizeof(*dp_ai) to avoid partial match/update problems when
@@ -710,6 +705,7 @@ static void hdmi_setup_audio_infoframe(struct hda_codec *codec,
 	struct hdmi_spec *spec = codec->spec;
 	struct hdac_chmap *chmap = &spec->chmap;
 	hda_nid_t pin_nid = per_pin->pin_nid;
+	int dev_id = per_pin->dev_id;
 	int channels = per_pin->channels;
 	int active_channels;
 	struct hdmi_eld *eld;
@@ -718,6 +714,8 @@ static void hdmi_setup_audio_infoframe(struct hda_codec *codec,
 	if (!channels)
 		return;
 
+	snd_hda_set_dev_select(codec, pin_nid, dev_id);
+
 	/* some HW (e.g. HSW+) needs reprogramming the amp at each time */
 	if (get_wcaps(codec, pin_nid) & AC_WCAP_OUT_AMP)
 		snd_hda_codec_write(codec, pin_nid, 0,
@@ -743,8 +741,8 @@ static void hdmi_setup_audio_infoframe(struct hda_codec *codec,
 				pin_nid, non_pcm, ca, channels,
 				per_pin->chmap, per_pin->chmap_set);
 
-	spec->ops.pin_setup_infoframe(codec, pin_nid, ca, active_channels,
-				      eld->info.conn_type);
+	spec->ops.pin_setup_infoframe(codec, pin_nid, dev_id,
+				      ca, active_channels, eld->info.conn_type);
 
 	per_pin->non_pcm = non_pcm;
 }
@@ -776,34 +774,32 @@ static void jack_callback(struct hda_codec *codec,
 	if (codec_has_acomp(codec))
 		return;
 
-	/* hda_jack don't support DP MST */
-	check_presence_and_report(codec, jack->nid, 0);
+	check_presence_and_report(codec, jack->nid, jack->dev_id);
 }
 
 static void hdmi_intrinsic_event(struct hda_codec *codec, unsigned int res)
 {
 	int tag = res >> AC_UNSOL_RES_TAG_SHIFT;
 	struct hda_jack_tbl *jack;
-	int dev_entry = (res & AC_UNSOL_RES_DE) >> AC_UNSOL_RES_DE_SHIFT;
 
-	/*
-	 * assume DP MST uses dyn_pcm_assign and acomp and
-	 * never comes here
-	 * if DP MST supports unsol event, below code need
-	 * consider dev_entry
-	 */
-	jack = snd_hda_jack_tbl_get_from_tag(codec, tag);
+	if (codec->dp_mst) {
+		int dev_entry =
+			(res & AC_UNSOL_RES_DE) >> AC_UNSOL_RES_DE_SHIFT;
+
+		jack = snd_hda_jack_tbl_get_from_tag(codec, tag, dev_entry);
+	} else {
+		jack = snd_hda_jack_tbl_get_from_tag(codec, tag, 0);
+	}
 	if (!jack)
 		return;
 	jack->jack_dirty = 1;
 
 	codec_dbg(codec,
 		"HDMI hot plug event: Codec=%d Pin=%d Device=%d Inactive=%d Presence_Detect=%d ELD_Valid=%d\n",
-		codec->addr, jack->nid, dev_entry, !!(res & AC_UNSOL_RES_IA),
+		codec->addr, jack->nid, jack->dev_id, !!(res & AC_UNSOL_RES_IA),
 		!!(res & AC_UNSOL_RES_PD), !!(res & AC_UNSOL_RES_ELDV));
 
-	/* hda_jack don't support DP MST */
-	check_presence_and_report(codec, jack->nid, 0);
+	check_presence_and_report(codec, jack->nid, jack->dev_id);
 }
 
 static void hdmi_non_intrinsic_event(struct hda_codec *codec, unsigned int res)
@@ -833,11 +829,21 @@ static void hdmi_unsol_event(struct hda_codec *codec, unsigned int res)
 {
 	int tag = res >> AC_UNSOL_RES_TAG_SHIFT;
 	int subtag = (res & AC_UNSOL_RES_SUBTAG) >> AC_UNSOL_RES_SUBTAG_SHIFT;
+	struct hda_jack_tbl *jack;
 
 	if (codec_has_acomp(codec))
 		return;
 
-	if (!snd_hda_jack_tbl_get_from_tag(codec, tag)) {
+	if (codec->dp_mst) {
+		int dev_entry =
+			(res & AC_UNSOL_RES_DE) >> AC_UNSOL_RES_DE_SHIFT;
+
+		jack = snd_hda_jack_tbl_get_from_tag(codec, tag, dev_entry);
+	} else {
+		jack = snd_hda_jack_tbl_get_from_tag(codec, tag, 0);
+	}
+
+	if (!jack) {
 		codec_dbg(codec, "Unexpected HDMI event tag 0x%x\n", tag);
 		return;
 	}
@@ -878,11 +884,12 @@ static void haswell_verify_D0(struct hda_codec *codec,
 	((format & AC_FMT_TYPE_NON_PCM) && (format & AC_FMT_CHAN_MASK) == 7)
 
 static int hdmi_pin_hbr_setup(struct hda_codec *codec, hda_nid_t pin_nid,
-			      bool hbr)
+			      int dev_id, bool hbr)
 {
 	int pinctl, new_pinctl;
 
 	if (snd_hda_query_pin_caps(codec, pin_nid) & AC_PINCAP_HBR) {
+		snd_hda_set_dev_select(codec, pin_nid, dev_id);
 		pinctl = snd_hda_codec_read(codec, pin_nid, 0,
 					    AC_VERB_GET_PIN_WIDGET_CONTROL, 0);
 
@@ -912,20 +919,22 @@ static int hdmi_pin_hbr_setup(struct hda_codec *codec, hda_nid_t pin_nid,
 }
 
 static int hdmi_setup_stream(struct hda_codec *codec, hda_nid_t cvt_nid,
-			      hda_nid_t pin_nid, u32 stream_tag, int format)
+			      hda_nid_t pin_nid, int dev_id,
+			      u32 stream_tag, int format)
 {
 	struct hdmi_spec *spec = codec->spec;
 	unsigned int param;
 	int err;
 
-	err = spec->ops.pin_hbr_setup(codec, pin_nid, is_hbr_format(format));
+	err = spec->ops.pin_hbr_setup(codec, pin_nid, dev_id,
+				      is_hbr_format(format));
 
 	if (err) {
 		codec_dbg(codec, "hdmi_setup_stream: HBR is not supported\n");
 		return err;
 	}
 
-	if (is_haswell_plus(codec)) {
+	if (spec->intel_hsw_fixup) {
 
 		/*
 		 * on recent platforms IEC Coding Type is required for HBR
@@ -1292,6 +1301,7 @@ static int hdmi_read_pin_conn(struct hda_codec *codec, int pin_idx)
 	struct hdmi_spec *spec = codec->spec;
 	struct hdmi_spec_per_pin *per_pin = get_pin(spec, pin_idx);
 	hda_nid_t pin_nid = per_pin->pin_nid;
+	int dev_id = per_pin->dev_id;
 
 	if (!(get_wcaps(codec, pin_nid) & AC_WCAP_CONN_LIST)) {
 		codec_warn(codec,
@@ -1300,24 +1310,43 @@ static int hdmi_read_pin_conn(struct hda_codec *codec, int pin_idx)
 		return -EINVAL;
 	}
 
+	snd_hda_set_dev_select(codec, pin_nid, dev_id);
+
 	/* all the device entries on the same pin have the same conn list */
-	per_pin->num_mux_nids = snd_hda_get_connections(codec, pin_nid,
-							per_pin->mux_nids,
-							HDA_MAX_CONNECTIONS);
+	per_pin->num_mux_nids =
+		snd_hda_get_raw_connections(codec, pin_nid, per_pin->mux_nids,
+					    HDA_MAX_CONNECTIONS);
 
 	return 0;
 }
 
 static int hdmi_find_pcm_slot(struct hdmi_spec *spec,
-				struct hdmi_spec_per_pin *per_pin)
+			      struct hdmi_spec_per_pin *per_pin)
 {
 	int i;
 
-	/* try the prefer PCM */
-	if (!test_bit(per_pin->pin_nid_idx, &spec->pcm_bitmap))
+	/*
+	 * generic_hdmi_build_pcms() allocates (num_nids + dev_num - 1)
+	 * number of pcms.
+	 *
+	 * The per_pin of pin_nid_idx=n and dev_id=m prefers to get pcm-n
+	 * if m==0. This guarantees that dynamic pcm assignments are compatible
+	 * with the legacy static per_pin-pmc assignment that existed in the
+	 * days before DP-MST.
+	 *
+	 * per_pin of m!=0 prefers to get pcm=(num_nids + (m - 1)).
+	 */
+	if (per_pin->dev_id == 0 &&
+	    !test_bit(per_pin->pin_nid_idx, &spec->pcm_bitmap))
 		return per_pin->pin_nid_idx;
 
-	/* have a second try; check the "reserved area" over num_pins */
+	if (per_pin->dev_id != 0 &&
+	    !(test_bit(spec->num_nids + (per_pin->dev_id - 1),
+		&spec->pcm_bitmap))) {
+		return spec->num_nids + (per_pin->dev_id - 1);
+	}
+
+	/* have a second try; check the area over num_nids */
 	for (i = spec->num_nids; i < spec->pcm_used; i++) {
 		if (!test_bit(i, &spec->pcm_bitmap))
 			return i;
@@ -1511,6 +1540,7 @@ static bool hdmi_present_sense_via_verbs(struct hdmi_spec_per_pin *per_pin,
 	struct hdmi_spec *spec = codec->spec;
 	struct hdmi_eld *eld = &spec->temp_eld;
 	hda_nid_t pin_nid = per_pin->pin_nid;
+	int dev_id = per_pin->dev_id;
 	/*
 	 * Always execute a GetPinSense verb here, even when called from
 	 * hdmi_intrinsic_event; for some NVIDIA HW, the unsolicited
@@ -1523,7 +1553,7 @@ static bool hdmi_present_sense_via_verbs(struct hdmi_spec_per_pin *per_pin,
 	bool ret;
 	bool do_repoll = false;
 
-	present = snd_hda_pin_sense(codec, pin_nid);
+	present = snd_hda_jack_pin_sense(codec, pin_nid, dev_id);
 
 	mutex_lock(&per_pin->lock);
 	eld->monitor_present = !!(present & AC_PINSENSE_PRESENCE);
@@ -1537,8 +1567,8 @@ static bool hdmi_present_sense_via_verbs(struct hdmi_spec_per_pin *per_pin,
 		codec->addr, pin_nid, eld->monitor_present, eld->eld_valid);
 
 	if (eld->eld_valid) {
-		if (spec->ops.pin_get_eld(codec, pin_nid, eld->eld_buffer,
-						     &eld->eld_size) < 0)
+		if (spec->ops.pin_get_eld(codec, pin_nid, dev_id,
+					  eld->eld_buffer, &eld->eld_size) < 0)
 			eld->eld_valid = false;
 		else {
 			if (snd_hdmi_parse_eld(codec, &eld->info, eld->eld_buffer,
@@ -1556,7 +1586,7 @@ static bool hdmi_present_sense_via_verbs(struct hdmi_spec_per_pin *per_pin,
 
 	ret = !repoll || !eld->monitor_present || eld->eld_valid;
 
-	jack = snd_hda_jack_tbl_get(codec, pin_nid);
+	jack = snd_hda_jack_tbl_get_mst(codec, pin_nid, per_pin->dev_id);
 	if (jack) {
 		jack->block_report = !ret;
 		jack->pin_sense = (eld->monitor_present && eld->eld_valid) ?
@@ -1587,7 +1617,8 @@ static struct snd_jack *pin_idx_to_jack(struct hda_codec *codec,
 		 * DP MST will use dyn_pcm_assign,
 		 * so DP MST will never come here
 		 */
-		jack_tbl = snd_hda_jack_tbl_get(codec, per_pin->pin_nid);
+		jack_tbl = snd_hda_jack_tbl_get_mst(codec, per_pin->pin_nid,
+						    per_pin->dev_id);
 		if (jack_tbl)
 			jack = jack_tbl->jack;
 	}
@@ -1668,7 +1699,8 @@ static void hdmi_repoll_eld(struct work_struct *work)
 	struct hdmi_spec *spec = codec->spec;
 	struct hda_jack_tbl *jack;
 
-	jack = snd_hda_jack_tbl_get(codec, per_pin->pin_nid);
+	jack = snd_hda_jack_tbl_get_mst(codec, per_pin->pin_nid,
+					per_pin->dev_id);
 	if (jack)
 		jack->jack_dirty = 1;
 
@@ -1709,7 +1741,7 @@ static int hdmi_add_pin(struct hda_codec *codec, hda_nid_t pin_nid)
 	 * To simplify the implementation, malloc all
 	 * the virtual pins in the initialization statically
 	 */
-	if (is_haswell_plus(codec)) {
+	if (spec->intel_hsw_fixup) {
 		/*
 		 * On Intel platforms, device entries number is
 		 * changed dynamically. If there is a DP MST
@@ -1758,7 +1790,7 @@ static int hdmi_add_pin(struct hda_codec *codec, hda_nid_t pin_nid)
 		per_pin->dev_id = i;
 		per_pin->non_pcm = false;
 		snd_hda_set_dev_select(codec, pin_nid, i);
-		if (is_haswell_plus(codec))
+		if (spec->intel_hsw_fixup)
 			intel_haswell_fixup_connect_list(codec, pin_nid);
 		err = hdmi_read_pin_conn(codec, pin_idx);
 		if (err < 0)
@@ -1873,7 +1905,6 @@ static int generic_hdmi_playback_pcm_prepare(struct hda_pcm_stream *hinfo,
 	struct hdmi_spec *spec = codec->spec;
 	int pin_idx;
 	struct hdmi_spec_per_pin *per_pin;
-	hda_nid_t pin_nid;
 	struct snd_pcm_runtime *runtime = substream->runtime;
 	bool non_pcm;
 	int pinctl, stripe;
@@ -1897,7 +1928,6 @@ static int generic_hdmi_playback_pcm_prepare(struct hda_pcm_stream *hinfo,
 		goto unlock;
 	}
 	per_pin = get_pin(spec, pin_idx);
-	pin_nid = per_pin->pin_nid;
 
 	/* Verify pin:cvt selections to avoid silent audio after S3.
 	 * After S3, the audio driver restores pin:cvt selections
@@ -1912,8 +1942,8 @@ static int generic_hdmi_playback_pcm_prepare(struct hda_pcm_stream *hinfo,
 	/* Call sync_audio_rate to set the N/CTS/M manually if necessary */
 	/* Todo: add DP1.2 MST audio support later */
 	if (codec_has_acomp(codec))
-		snd_hdac_sync_audio_rate(&codec->core, pin_nid, per_pin->dev_id,
-					 runtime->rate);
+		snd_hdac_sync_audio_rate(&codec->core, per_pin->pin_nid,
+					 per_pin->dev_id, runtime->rate);
 
 	non_pcm = check_non_pcm_per_cvt(codec, cvt_nid);
 	mutex_lock(&per_pin->lock);
@@ -1931,16 +1961,18 @@ static int generic_hdmi_playback_pcm_prepare(struct hda_pcm_stream *hinfo,
 	hdmi_setup_audio_infoframe(codec, per_pin, non_pcm);
 	mutex_unlock(&per_pin->lock);
 	if (spec->dyn_pin_out) {
-		pinctl = snd_hda_codec_read(codec, pin_nid, 0,
+		snd_hda_set_dev_select(codec, per_pin->pin_nid,
+				       per_pin->dev_id);
+		pinctl = snd_hda_codec_read(codec, per_pin->pin_nid, 0,
 					    AC_VERB_GET_PIN_WIDGET_CONTROL, 0);
-		snd_hda_codec_write(codec, pin_nid, 0,
+		snd_hda_codec_write(codec, per_pin->pin_nid, 0,
 				    AC_VERB_SET_PIN_WIDGET_CONTROL,
 				    pinctl | PIN_OUT);
 	}
 
 	/* snd_hda_set_dev_select() has been called before */
-	err = spec->ops.setup_stream(codec, cvt_nid, pin_nid,
-				 stream_tag, format);
+	err = spec->ops.setup_stream(codec, cvt_nid, per_pin->pin_nid,
+				     per_pin->dev_id, stream_tag, format);
  unlock:
 	mutex_unlock(&spec->pcm_lock);
 	return err;
@@ -1992,6 +2024,8 @@ static int hdmi_pcm_close(struct hda_pcm_stream *hinfo,
 		per_pin = get_pin(spec, pin_idx);
 
 		if (spec->dyn_pin_out) {
+			snd_hda_set_dev_select(codec, per_pin->pin_nid,
+					       per_pin->dev_id);
 			pinctl = snd_hda_codec_read(codec, per_pin->pin_nid, 0,
 					AC_VERB_GET_PIN_WIDGET_CONTROL, 0);
 			snd_hda_codec_write(codec, per_pin->pin_nid, 0,
@@ -2075,15 +2109,24 @@ static bool is_hdmi_pcm_attached(struct hdac_device *hdac, int pcm_idx)
 static int generic_hdmi_build_pcms(struct hda_codec *codec)
 {
 	struct hdmi_spec *spec = codec->spec;
-	int idx;
+	int idx, pcm_num;
 
 	/*
 	 * for non-mst mode, pcm number is the same as before
-	 * for DP MST mode, pcm number is (nid number + dev_num - 1)
-	 *  dev_num is the device entry number in a pin
-	 *
+	 * for DP MST mode without extra PCM, pcm number is same
+	 * for DP MST mode with extra PCMs, pcm number is
+	 *  (nid number + dev_num - 1)
+	 * dev_num is the device entry number in a pin
 	 */
-	for (idx = 0; idx < spec->num_nids + spec->dev_num - 1; idx++) {
+
+	if (codec->mst_no_extra_pcms)
+		pcm_num = spec->num_nids;
+	else
+		pcm_num = spec->num_nids + spec->dev_num - 1;
+
+	codec_dbg(codec, "hdmi: pcm_num set to %d\n", pcm_num);
+
+	for (idx = 0; idx < pcm_num; idx++) {
 		struct hda_pcm *info;
 		struct hda_pcm_stream *pstr;
 
@@ -2160,11 +2203,13 @@ static int generic_hdmi_build_jack(struct hda_codec *codec, int pcm_idx)
 	if (phantom_jack)
 		strncat(hdmi_str, " Phantom",
 			sizeof(hdmi_str) - strlen(hdmi_str) - 1);
-	ret = snd_hda_jack_add_kctl(codec, per_pin->pin_nid, hdmi_str,
-				    phantom_jack, 0, NULL);
+	ret = snd_hda_jack_add_kctl_mst(codec, per_pin->pin_nid,
+					per_pin->dev_id, hdmi_str, phantom_jack,
+					0, NULL);
 	if (ret < 0)
 		return ret;
-	jack = snd_hda_jack_tbl_get(codec, per_pin->pin_nid);
+	jack = snd_hda_jack_tbl_get_mst(codec, per_pin->pin_nid,
+					per_pin->dev_id);
 	if (jack == NULL)
 		return 0;
 	/* assign jack->jack to pcm_rec[].jack to
@@ -2273,10 +2318,11 @@ static int generic_hdmi_init(struct hda_codec *codec)
 		if (codec_has_acomp(codec))
 			continue;
 		if (spec->use_jack_detect)
-			snd_hda_jack_detect_enable(codec, pin_nid);
+			snd_hda_jack_detect_enable(codec, pin_nid, dev_id);
 		else
-			snd_hda_jack_detect_enable_callback(codec, pin_nid,
-							    jack_callback);
+			snd_hda_jack_detect_enable_callback_mst(codec, pin_nid,
+								dev_id,
+								jack_callback);
 	}
 	mutex_unlock(&spec->bind_lock);
 	return 0;
@@ -2315,8 +2361,8 @@ static void generic_hdmi_free(struct hda_codec *codec)
 		snd_hdac_acomp_exit(&codec->bus->core);
 	} else if (codec_has_acomp(codec)) {
 		snd_hdac_acomp_register_notifier(&codec->bus->core, NULL);
-		codec->relaxed_resume = 0;
 	}
+	codec->relaxed_resume = 0;
 
 	for (pin_idx = 0; pin_idx < spec->num_pins; pin_idx++) {
 		struct hdmi_spec_per_pin *per_pin = get_pin(spec, pin_idx);
@@ -2366,7 +2412,7 @@ static const struct hda_codec_ops generic_hdmi_patch_ops = {
 };
 
 static const struct hdmi_ops generic_standard_hdmi_ops = {
-	.pin_get_eld				= snd_hdmi_get_eld,
+	.pin_get_eld				= hdmi_pin_get_eld,
 	.pin_setup_infoframe			= hdmi_pin_setup_infoframe,
 	.pin_hbr_setup				= hdmi_pin_hbr_setup,
 	.setup_stream				= hdmi_setup_stream,
@@ -2426,11 +2472,11 @@ static int patch_generic_hdmi(struct hda_codec *codec)
 
 /* turn on / off the unsol event jack detection dynamically */
 static void reprogram_jack_detect(struct hda_codec *codec, hda_nid_t nid,
-				  bool use_acomp)
+				  int dev_id, bool use_acomp)
 {
 	struct hda_jack_tbl *tbl;
 
-	tbl = snd_hda_jack_tbl_get(codec, nid);
+	tbl = snd_hda_jack_tbl_get_mst(codec, nid, dev_id);
 	if (tbl) {
 		/* clear unsol even if component notifier is used, or re-enable
 		 * if notifier is cleared
@@ -2443,7 +2489,7 @@ static void reprogram_jack_detect(struct hda_codec *codec, hda_nid_t nid,
 		 * at need (i.e. only when notifier is cleared)
 		 */
 		if (!use_acomp)
-			snd_hda_jack_detect_enable(codec, nid);
+			snd_hda_jack_detect_enable(codec, nid, dev_id);
 	}
 }
 
@@ -2463,6 +2509,7 @@ static void generic_acomp_notifier_set(struct drm_audio_component *acomp,
 		for (i = 0; i < spec->num_pins; i++)
 			reprogram_jack_detect(spec->codec,
 					      get_pin(spec, i)->pin_nid,
+					      get_pin(spec, i)->dev_id,
 					      use_acomp);
 	}
 	mutex_unlock(&spec->bind_lock);
@@ -2563,7 +2610,8 @@ static void intel_haswell_fixup_connect_list(struct hda_codec *codec,
 	hda_nid_t conns[4];
 	int nconns;
 
-	nconns = snd_hda_get_connections(codec, nid, conns, ARRAY_SIZE(conns));
+	nconns = snd_hda_get_raw_connections(codec, nid, conns,
+					     ARRAY_SIZE(conns));
 	if (nconns == spec->num_cvts &&
 	    !memcmp(conns, spec->cvt_nids, spec->num_cvts * sizeof(hda_nid_t)))
 		return;
@@ -2664,7 +2712,7 @@ static int intel_pin2port(void *audio_ptr, int pin_nid)
 		base_nid = intel_base_nid(codec);
 		if (WARN_ON(pin_nid < base_nid || pin_nid >= base_nid + 3))
 			return -1;
-		return pin_nid - base_nid + 1; /* intel port is 1-based */
+		return pin_nid - base_nid + 1;
 	}
 
 	/*
@@ -2673,10 +2721,9 @@ static int intel_pin2port(void *audio_ptr, int pin_nid)
 	 */
 	for (i = 0; i < spec->port_num; i++) {
 		if (pin_nid == spec->port_map[i])
-			return i + 1;
+			return i;
 	}
 
-	/* return -1 if pin number exceeds our expectation */
 	codec_info(codec, "Can't find the HDMI/DP port for pin %d\n", pin_nid);
 	return -1;
 }
@@ -2689,13 +2736,12 @@ static int intel_port2pin(struct hda_codec *codec, int port)
 		/* we assume only from port-B to port-D */
 		if (port < 1 || port > 3)
 			return 0;
-		/* intel port is 1-based */
 		return port + intel_base_nid(codec) - 1;
 	}
 
-	if (port < 1 || port > spec->port_num)
+	if (port < 0 || port >= spec->port_num)
 		return 0;
-	return spec->port_map[port - 1];
+	return spec->port_map[port];
 }
 
 static void intel_pin_eld_notify(void *audio_ptr, int port, int pipe)
@@ -2741,10 +2787,12 @@ static void register_i915_notifier(struct hda_codec *codec)
 
 /* setup_stream ops override for HSW+ */
 static int i915_hsw_setup_stream(struct hda_codec *codec, hda_nid_t cvt_nid,
-				 hda_nid_t pin_nid, u32 stream_tag, int format)
+				 hda_nid_t pin_nid, int dev_id, u32 stream_tag,
+				 int format)
 {
 	haswell_verify_D0(codec, cvt_nid, pin_nid);
-	return hdmi_setup_stream(codec, cvt_nid, pin_nid, stream_tag, format);
+	return hdmi_setup_stream(codec, cvt_nid, pin_nid, dev_id,
+				 stream_tag, format);
 }
 
 /* pin_cvt_fixup ops override for HSW+ and VLV+ */
@@ -2816,6 +2864,7 @@ static int intel_hsw_common_init(struct hda_codec *codec, hda_nid_t vendor_nid,
 	spec->vendor_nid = vendor_nid;
 	spec->port_map = port_map;
 	spec->port_num = port_num;
+	spec->intel_hsw_fixup = true;
 
 	intel_haswell_enable_all_pins(codec, true);
 	intel_haswell_fixup_enable_dp12(codec);
@@ -2846,9 +2895,9 @@ static int patch_i915_icl_hdmi(struct hda_codec *codec)
 {
 	/*
 	 * pin to port mapping table where the value indicate the pin number and
-	 * the index indicate the port number with 1 base.
+	 * the index indicate the port number.
 	 */
-	static const int map[] = {0x4, 0x6, 0x8, 0xa, 0xb};
+	static const int map[] = {0x0, 0x4, 0x6, 0x8, 0xa, 0xb};
 
 	return intel_hsw_common_init(codec, 0x02, map, ARRAY_SIZE(map));
 }
@@ -2857,14 +2906,13 @@ static int patch_i915_tgl_hdmi(struct hda_codec *codec)
 {
 	/*
 	 * pin to port mapping table where the value indicate the pin number and
-	 * the index indicate the port number with 1 base.
+	 * the index indicate the port number.
 	 */
 	static const int map[] = {0x4, 0x6, 0x8, 0xa, 0xb, 0xc, 0xd, 0xe, 0xf};
 
 	return intel_hsw_common_init(codec, 0x02, map, ARRAY_SIZE(map));
 }
 
-
 /* Intel Baytrail and Braswell; with eld notifier */
 static int patch_i915_byt_hdmi(struct hda_codec *codec)
 {
@@ -2970,7 +3018,7 @@ static int simple_playback_init(struct hda_codec *codec)
 	if (get_wcaps(codec, pin) & AC_WCAP_OUT_AMP)
 		snd_hda_codec_write(codec, pin, 0, AC_VERB_SET_AMP_GAIN_MUTE,
 				    AMP_OUT_UNMUTE);
-	snd_hda_jack_detect_enable(codec, pin);
+	snd_hda_jack_detect_enable(codec, pin, per_pin->dev_id);
 	return 0;
 }
 
@@ -3479,11 +3527,22 @@ static int patch_nvhdmi(struct hda_codec *codec)
 	struct hdmi_spec *spec;
 	int err;
 
-	err = patch_generic_hdmi(codec);
-	if (err)
+	err = alloc_generic_hdmi(codec);
+	if (err < 0)
 		return err;
+	codec->dp_mst = true;
 
 	spec = codec->spec;
+	spec->dyn_pcm_assign = true;
+
+	err = hdmi_parse_codec(codec);
+	if (err < 0) {
+		generic_spec_free(codec);
+		return err;
+	}
+
+	generic_hdmi_init_per_pins(codec);
+
 	spec->dyn_pin_out = true;
 
 	spec->chmap.ops.chmap_cea_alloc_validate_get_type =
@@ -3497,6 +3556,27 @@ static int patch_nvhdmi(struct hda_codec *codec)
 	return 0;
 }
 
+static int patch_nvhdmi_legacy(struct hda_codec *codec)
+{
+	struct hdmi_spec *spec;
+	int err;
+
+	err = patch_generic_hdmi(codec);
+	if (err)
+		return err;
+
+	spec = codec->spec;
+	spec->dyn_pin_out = true;
+
+	spec->chmap.ops.chmap_cea_alloc_validate_get_type =
+		nvhdmi_chmap_cea_alloc_validate_get_type;
+	spec->chmap.ops.chmap_validate = nvhdmi_chmap_validate;
+
+	codec->link_down_at_suspend = 1;
+
+	return 0;
+}
+
 /*
  * The HDA codec on NVIDIA Tegra contains two scratch registers that are
  * accessed using vendor-defined verbs. These registers can be used for
@@ -3710,16 +3790,19 @@ static int patch_tegra_hdmi(struct hda_codec *codec)
 #define ATI_HBR_ENABLE 0x10
 
 static int atihdmi_pin_get_eld(struct hda_codec *codec, hda_nid_t nid,
-			   unsigned char *buf, int *eld_size)
+			       int dev_id, unsigned char *buf, int *eld_size)
 {
+	WARN_ON(dev_id != 0);
 	/* call hda_eld.c ATI/AMD-specific function */
 	return snd_hdmi_get_eld_ati(codec, nid, buf, eld_size,
 				    is_amdhdmi_rev3_or_later(codec));
 }
 
-static void atihdmi_pin_setup_infoframe(struct hda_codec *codec, hda_nid_t pin_nid, int ca,
+static void atihdmi_pin_setup_infoframe(struct hda_codec *codec,
+					hda_nid_t pin_nid, int dev_id, int ca,
 					int active_channels, int conn_type)
 {
+	WARN_ON(dev_id != 0);
 	snd_hda_codec_write(codec, pin_nid, 0, ATI_VERB_SET_CHANNEL_ALLOCATION, ca);
 }
 
@@ -3910,10 +3993,12 @@ static void atihdmi_paired_cea_alloc_to_tlv_chmap(struct hdac_chmap *hchmap,
 }
 
 static int atihdmi_pin_hbr_setup(struct hda_codec *codec, hda_nid_t pin_nid,
-				 bool hbr)
+				 int dev_id, bool hbr)
 {
 	int hbr_ctl, hbr_ctl_new;
 
+	WARN_ON(dev_id != 0);
+
 	hbr_ctl = snd_hda_codec_read(codec, pin_nid, 0, ATI_VERB_GET_HBR_CONTROL, 0);
 	if (hbr_ctl >= 0 && (hbr_ctl & ATI_HBR_CAPABLE)) {
 		if (hbr)
@@ -3939,9 +4024,9 @@ static int atihdmi_pin_hbr_setup(struct hda_codec *codec, hda_nid_t pin_nid,
 }
 
 static int atihdmi_setup_stream(struct hda_codec *codec, hda_nid_t cvt_nid,
-				hda_nid_t pin_nid, u32 stream_tag, int format)
+				hda_nid_t pin_nid, int dev_id,
+				u32 stream_tag, int format)
 {
-
 	if (is_amdhdmi_rev3_or_later(codec)) {
 		int ramp_rate = 180; /* default as per AMD spec */
 		/* disable ramp-up/down for non-pcm as per AMD spec */
@@ -3951,7 +4036,8 @@ static int atihdmi_setup_stream(struct hda_codec *codec, hda_nid_t cvt_nid,
 		snd_hda_codec_write(codec, cvt_nid, 0, ATI_VERB_SET_RAMP_RATE, ramp_rate);
 	}
 
-	return hdmi_setup_stream(codec, cvt_nid, pin_nid, stream_tag, format);
+	return hdmi_setup_stream(codec, cvt_nid, pin_nid, dev_id,
+				 stream_tag, format);
 }
 
 
@@ -4081,25 +4167,25 @@ HDA_CODEC_ENTRY(0x10de0004, "GPU 04 HDMI",	patch_nvhdmi_8ch_7x),
 HDA_CODEC_ENTRY(0x10de0005, "MCP77/78 HDMI",	patch_nvhdmi_8ch_7x),
 HDA_CODEC_ENTRY(0x10de0006, "MCP77/78 HDMI",	patch_nvhdmi_8ch_7x),
 HDA_CODEC_ENTRY(0x10de0007, "MCP79/7A HDMI",	patch_nvhdmi_8ch_7x),
-HDA_CODEC_ENTRY(0x10de0008, "GPU 08 HDMI/DP",	patch_nvhdmi),
-HDA_CODEC_ENTRY(0x10de0009, "GPU 09 HDMI/DP",	patch_nvhdmi),
-HDA_CODEC_ENTRY(0x10de000a, "GPU 0a HDMI/DP",	patch_nvhdmi),
-HDA_CODEC_ENTRY(0x10de000b, "GPU 0b HDMI/DP",	patch_nvhdmi),
-HDA_CODEC_ENTRY(0x10de000c, "MCP89 HDMI",	patch_nvhdmi),
-HDA_CODEC_ENTRY(0x10de000d, "GPU 0d HDMI/DP",	patch_nvhdmi),
-HDA_CODEC_ENTRY(0x10de0010, "GPU 10 HDMI/DP",	patch_nvhdmi),
-HDA_CODEC_ENTRY(0x10de0011, "GPU 11 HDMI/DP",	patch_nvhdmi),
-HDA_CODEC_ENTRY(0x10de0012, "GPU 12 HDMI/DP",	patch_nvhdmi),
-HDA_CODEC_ENTRY(0x10de0013, "GPU 13 HDMI/DP",	patch_nvhdmi),
-HDA_CODEC_ENTRY(0x10de0014, "GPU 14 HDMI/DP",	patch_nvhdmi),
-HDA_CODEC_ENTRY(0x10de0015, "GPU 15 HDMI/DP",	patch_nvhdmi),
-HDA_CODEC_ENTRY(0x10de0016, "GPU 16 HDMI/DP",	patch_nvhdmi),
+HDA_CODEC_ENTRY(0x10de0008, "GPU 08 HDMI/DP",	patch_nvhdmi_legacy),
+HDA_CODEC_ENTRY(0x10de0009, "GPU 09 HDMI/DP",	patch_nvhdmi_legacy),
+HDA_CODEC_ENTRY(0x10de000a, "GPU 0a HDMI/DP",	patch_nvhdmi_legacy),
+HDA_CODEC_ENTRY(0x10de000b, "GPU 0b HDMI/DP",	patch_nvhdmi_legacy),
+HDA_CODEC_ENTRY(0x10de000c, "MCP89 HDMI",	patch_nvhdmi_legacy),
+HDA_CODEC_ENTRY(0x10de000d, "GPU 0d HDMI/DP",	patch_nvhdmi_legacy),
+HDA_CODEC_ENTRY(0x10de0010, "GPU 10 HDMI/DP",	patch_nvhdmi_legacy),
+HDA_CODEC_ENTRY(0x10de0011, "GPU 11 HDMI/DP",	patch_nvhdmi_legacy),
+HDA_CODEC_ENTRY(0x10de0012, "GPU 12 HDMI/DP",	patch_nvhdmi_legacy),
+HDA_CODEC_ENTRY(0x10de0013, "GPU 13 HDMI/DP",	patch_nvhdmi_legacy),
+HDA_CODEC_ENTRY(0x10de0014, "GPU 14 HDMI/DP",	patch_nvhdmi_legacy),
+HDA_CODEC_ENTRY(0x10de0015, "GPU 15 HDMI/DP",	patch_nvhdmi_legacy),
+HDA_CODEC_ENTRY(0x10de0016, "GPU 16 HDMI/DP",	patch_nvhdmi_legacy),
 /* 17 is known to be absent */
-HDA_CODEC_ENTRY(0x10de0018, "GPU 18 HDMI/DP",	patch_nvhdmi),
-HDA_CODEC_ENTRY(0x10de0019, "GPU 19 HDMI/DP",	patch_nvhdmi),
-HDA_CODEC_ENTRY(0x10de001a, "GPU 1a HDMI/DP",	patch_nvhdmi),
-HDA_CODEC_ENTRY(0x10de001b, "GPU 1b HDMI/DP",	patch_nvhdmi),
-HDA_CODEC_ENTRY(0x10de001c, "GPU 1c HDMI/DP",	patch_nvhdmi),
+HDA_CODEC_ENTRY(0x10de0018, "GPU 18 HDMI/DP",	patch_nvhdmi_legacy),
+HDA_CODEC_ENTRY(0x10de0019, "GPU 19 HDMI/DP",	patch_nvhdmi_legacy),
+HDA_CODEC_ENTRY(0x10de001a, "GPU 1a HDMI/DP",	patch_nvhdmi_legacy),
+HDA_CODEC_ENTRY(0x10de001b, "GPU 1b HDMI/DP",	patch_nvhdmi_legacy),
+HDA_CODEC_ENTRY(0x10de001c, "GPU 1c HDMI/DP",	patch_nvhdmi_legacy),
 HDA_CODEC_ENTRY(0x10de0020, "Tegra30 HDMI",	patch_tegra_hdmi),
 HDA_CODEC_ENTRY(0x10de0022, "Tegra114 HDMI",	patch_tegra_hdmi),
 HDA_CODEC_ENTRY(0x10de0028, "Tegra124 HDMI",	patch_tegra_hdmi),
diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c
index 80f66ba85f87..d2bf70a1d2fd 100644
--- a/sound/pci/hda/patch_realtek.c
+++ b/sound/pci/hda/patch_realtek.c
@@ -5892,6 +5892,7 @@ enum {
 	ALC299_FIXUP_PREDATOR_SPK,
 	ALC294_FIXUP_ASUS_INTSPK_HEADSET_MIC,
 	ALC256_FIXUP_MEDION_HEADSET_NO_PRESENCE,
+	ALC294_FIXUP_ASUS_INTSPK_GPIO,
 };
 
 static const struct hda_fixup alc269_fixups[] = {
@@ -6982,6 +6983,13 @@ static const struct hda_fixup alc269_fixups[] = {
 		.chained = true,
 		.chain_id = ALC256_FIXUP_ASUS_HEADSET_MODE
 	},
+	[ALC294_FIXUP_ASUS_INTSPK_GPIO] = {
+		.type = HDA_FIXUP_FUNC,
+		/* The GPIO must be pulled to initialize the AMP */
+		.v.func = alc_fixup_gpio4,
+		.chained = true,
+		.chain_id = ALC294_FIXUP_ASUS_INTSPK_HEADSET_MIC
+	},
 };
 
 static const struct snd_pci_quirk alc269_fixup_tbl[] = {
@@ -7141,7 +7149,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x1043, 0x1427, "Asus Zenbook UX31E", ALC269VB_FIXUP_ASUS_ZENBOOK),
 	SND_PCI_QUIRK(0x1043, 0x1517, "Asus Zenbook UX31A", ALC269VB_FIXUP_ASUS_ZENBOOK_UX31A),
 	SND_PCI_QUIRK(0x1043, 0x16e3, "ASUS UX50", ALC269_FIXUP_STEREO_DMIC),
-	SND_PCI_QUIRK(0x1043, 0x17d1, "ASUS UX431FL", ALC294_FIXUP_ASUS_INTSPK_HEADSET_MIC),
+	SND_PCI_QUIRK(0x1043, 0x17d1, "ASUS UX431FL", ALC294_FIXUP_ASUS_INTSPK_GPIO),
 	SND_PCI_QUIRK(0x1043, 0x18b1, "Asus MJ401TA", ALC256_FIXUP_ASUS_HEADSET_MIC),
 	SND_PCI_QUIRK(0x1043, 0x1a13, "Asus G73Jw", ALC269_FIXUP_ASUS_G73JW),
 	SND_PCI_QUIRK(0x1043, 0x1a30, "ASUS X705UD", ALC256_FIXUP_ASUS_MIC),
@@ -7248,6 +7256,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x17aa, 0x9e54, "LENOVO NB", ALC269_FIXUP_LENOVO_EAPD),
 	SND_PCI_QUIRK(0x19e5, 0x3204, "Huawei MACH-WX9", ALC256_FIXUP_HUAWEI_MACH_WX9_PINS),
 	SND_PCI_QUIRK(0x1b7d, 0xa831, "Ordissimo EVE2 ", ALC269VB_FIXUP_ORDISSIMO_EVE2), /* Also known as Malata PC-B1303 */
+	SND_PCI_QUIRK(0x1d72, 0x1901, "RedmiBook 14", ALC256_FIXUP_ASUS_HEADSET_MIC),
 	SND_PCI_QUIRK(0x10ec, 0x118c, "Medion EE4254 MD62100", ALC256_FIXUP_MEDION_HEADSET_NO_PRESENCE),
 
 #if 0
@@ -7512,20 +7521,6 @@ static const struct snd_hda_pin_quirk alc269_pin_fixup_tbl[] = {
 		{0x19, 0x02a11020},
 		{0x1a, 0x02a11030},
 		{0x21, 0x0221101f}),
-	SND_HDA_PIN_QUIRK(0x10ec0236, 0x1028, "Dell", ALC255_FIXUP_DELL1_MIC_NO_PRESENCE,
-		{0x12, 0x90a60140},
-		{0x14, 0x90170110},
-		{0x21, 0x02211020}),
-	SND_HDA_PIN_QUIRK(0x10ec0236, 0x1028, "Dell", ALC255_FIXUP_DELL1_MIC_NO_PRESENCE,
-		{0x12, 0x90a60140},
-		{0x14, 0x90170150},
-		{0x21, 0x02211020}),
-	SND_HDA_PIN_QUIRK(0x10ec0236, 0x1028, "Dell", ALC255_FIXUP_DELL1_MIC_NO_PRESENCE,
-		{0x21, 0x02211020}),
-	SND_HDA_PIN_QUIRK(0x10ec0236, 0x1028, "Dell", ALC255_FIXUP_DELL1_MIC_NO_PRESENCE,
-		{0x12, 0x40000000},
-		{0x14, 0x90170110},
-		{0x21, 0x02211020}),
 	SND_HDA_PIN_QUIRK(0x10ec0255, 0x1028, "Dell", ALC255_FIXUP_DELL2_MIC_NO_PRESENCE,
 		{0x14, 0x90170110},
 		{0x21, 0x02211020}),
@@ -7608,38 +7603,6 @@ static const struct snd_hda_pin_quirk alc269_pin_fixup_tbl[] = {
 	SND_HDA_PIN_QUIRK(0x10ec0255, 0x1028, "Dell", ALC255_FIXUP_DELL1_MIC_NO_PRESENCE,
 		{0x1b, 0x01011020},
 		{0x21, 0x02211010}),
-	SND_HDA_PIN_QUIRK(0x10ec0256, 0x1028, "Dell", ALC255_FIXUP_DELL1_MIC_NO_PRESENCE,
-		{0x12, 0x90a60130},
-		{0x14, 0x90170110},
-		{0x1b, 0x01011020},
-		{0x21, 0x0221101f}),
-	SND_HDA_PIN_QUIRK(0x10ec0256, 0x1028, "Dell", ALC255_FIXUP_DELL1_MIC_NO_PRESENCE,
-		{0x12, 0x90a60160},
-		{0x14, 0x90170120},
-		{0x21, 0x02211030}),
-	SND_HDA_PIN_QUIRK(0x10ec0256, 0x1028, "Dell", ALC255_FIXUP_DELL1_MIC_NO_PRESENCE,
-		{0x12, 0x90a60170},
-		{0x14, 0x90170120},
-		{0x21, 0x02211030}),
-	SND_HDA_PIN_QUIRK(0x10ec0256, 0x1028, "Dell Inspiron 5468", ALC255_FIXUP_DELL1_MIC_NO_PRESENCE,
-		{0x12, 0x90a60180},
-		{0x14, 0x90170120},
-		{0x21, 0x02211030}),
-	SND_HDA_PIN_QUIRK(0x10ec0256, 0x1028, "Dell", ALC255_FIXUP_DELL1_MIC_NO_PRESENCE,
-		{0x12, 0xb7a60130},
-		{0x14, 0x90170110},
-		{0x21, 0x02211020}),
-	SND_HDA_PIN_QUIRK(0x10ec0256, 0x1028, "Dell", ALC255_FIXUP_DELL1_MIC_NO_PRESENCE,
-		{0x12, 0x90a60130},
-		{0x14, 0x90170110},
-		{0x14, 0x01011020},
-		{0x21, 0x0221101f}),
-	SND_HDA_PIN_QUIRK(0x10ec0256, 0x1028, "Dell", ALC255_FIXUP_DELL1_MIC_NO_PRESENCE,
-		ALC256_STANDARD_PINS),
-	SND_HDA_PIN_QUIRK(0x10ec0256, 0x1028, "Dell", ALC255_FIXUP_DELL1_MIC_NO_PRESENCE,
-		{0x14, 0x90170110},
-		{0x1b, 0x01011020},
-		{0x21, 0x0221101f}),
 	SND_HDA_PIN_QUIRK(0x10ec0256, 0x1043, "ASUS", ALC256_FIXUP_ASUS_MIC,
 		{0x14, 0x90170110},
 		{0x1b, 0x90a70130},
@@ -7852,6 +7815,12 @@ static const struct snd_hda_pin_quirk alc269_fallback_pin_fixup_tbl[] = {
 	SND_HDA_PIN_QUIRK(0x10ec0289, 0x1028, "Dell", ALC269_FIXUP_DELL4_MIC_NO_PRESENCE,
 		{0x19, 0x40000000},
 		{0x1b, 0x40000000}),
+	SND_HDA_PIN_QUIRK(0x10ec0256, 0x1028, "Dell", ALC255_FIXUP_DELL1_MIC_NO_PRESENCE,
+		{0x19, 0x40000000},
+		{0x1a, 0x40000000}),
+	SND_HDA_PIN_QUIRK(0x10ec0236, 0x1028, "Dell", ALC255_FIXUP_DELL1_MIC_NO_PRESENCE,
+		{0x19, 0x40000000},
+		{0x1a, 0x40000000}),
 	{}
 };
 
diff --git a/sound/pci/ice1712/ice1712.c b/sound/pci/ice1712/ice1712.c
index 4b0dea7f7669..deadba40131c 100644
--- a/sound/pci/ice1712/ice1712.c
+++ b/sound/pci/ice1712/ice1712.c
@@ -884,7 +884,8 @@ static int snd_ice1712_pcm(struct snd_ice1712 *ice, int device)
 	ice->pcm = pcm;
 
 	snd_pcm_lib_preallocate_pages_for_all(pcm, SNDRV_DMA_TYPE_DEV,
-					      snd_dma_pci_data(ice->pci), 64*1024, 64*1024);
+					      &ice->pci->dev,
+					      64*1024, 64*1024);
 
 	dev_warn(ice->card->dev,
 		 "Consumer PCM code does not work well at the moment --jk\n");
@@ -909,7 +910,8 @@ static int snd_ice1712_pcm_ds(struct snd_ice1712 *ice, int device)
 	ice->pcm_ds = pcm;
 
 	snd_pcm_lib_preallocate_pages_for_all(pcm, SNDRV_DMA_TYPE_DEV,
-					      snd_dma_pci_data(ice->pci), 64*1024, 128*1024);
+					      &ice->pci->dev,
+					      64*1024, 128*1024);
 
 	return 0;
 }
@@ -1253,7 +1255,8 @@ static int snd_ice1712_pcm_profi(struct snd_ice1712 *ice, int device)
 	strcpy(pcm->name, "ICE1712 multi");
 
 	snd_pcm_lib_preallocate_pages_for_all(pcm, SNDRV_DMA_TYPE_DEV,
-					      snd_dma_pci_data(ice->pci), 256*1024, 256*1024);
+					      &ice->pci->dev,
+					      256*1024, 256*1024);
 
 	ice->pcm_pro = pcm;
 
diff --git a/sound/pci/ice1712/ice1724.c b/sound/pci/ice1712/ice1724.c
index e62c11816683..c80a16ee6e76 100644
--- a/sound/pci/ice1712/ice1724.c
+++ b/sound/pci/ice1712/ice1724.c
@@ -1143,7 +1143,7 @@ static int snd_vt1724_pcm_profi(struct snd_ice1712 *ice, int device)
 	strcpy(pcm->name, "ICE1724");
 
 	snd_pcm_lib_preallocate_pages_for_all(pcm, SNDRV_DMA_TYPE_DEV,
-					      snd_dma_pci_data(ice->pci),
+					      &ice->pci->dev,
 					      256*1024, 256*1024);
 
 	ice->pcm_pro = pcm;
@@ -1341,7 +1341,7 @@ static int snd_vt1724_pcm_spdif(struct snd_ice1712 *ice, int device)
 	strcpy(pcm->name, name);
 
 	snd_pcm_lib_preallocate_pages_for_all(pcm, SNDRV_DMA_TYPE_DEV,
-					      snd_dma_pci_data(ice->pci),
+					      &ice->pci->dev,
 					      256*1024, 256*1024);
 
 	ice->pcm = pcm;
@@ -1455,7 +1455,7 @@ static int snd_vt1724_pcm_indep(struct snd_ice1712 *ice, int device)
 	strcpy(pcm->name, "ICE1724 Surround PCM");
 
 	snd_pcm_lib_preallocate_pages_for_all(pcm, SNDRV_DMA_TYPE_DEV,
-					      snd_dma_pci_data(ice->pci),
+					      &ice->pci->dev,
 					      256*1024, 256*1024);
 
 	ice->pcm_ds = pcm;
diff --git a/sound/pci/intel8x0.c b/sound/pci/intel8x0.c
index 6ff94d8ad86e..12374ba08ca2 100644
--- a/sound/pci/intel8x0.c
+++ b/sound/pci/intel8x0.c
@@ -1488,7 +1488,7 @@ static int snd_intel8x0_pcm1(struct intel8x0 *chip, int device,
 	chip->pcm[device] = pcm;
 
 	snd_pcm_lib_preallocate_pages_for_all(pcm, intel8x0_dma_type(chip),
-					      snd_dma_pci_data(chip->pci),
+					      &chip->pci->dev,
 					      rec->prealloc_size, rec->prealloc_max_size);
 
 	if (rec->playback_ops &&
@@ -3047,7 +3047,7 @@ static int snd_intel8x0_create(struct snd_card *card,
 
 	/* allocate buffer descriptor lists */
 	/* the start of each lists must be aligned to 8 bytes */
-	if (snd_dma_alloc_pages(intel8x0_dma_type(chip), snd_dma_pci_data(pci),
+	if (snd_dma_alloc_pages(intel8x0_dma_type(chip), &pci->dev,
 				chip->bdbars_count * sizeof(u32) * ICH_MAX_FRAGS * 2,
 				&chip->bdbars) < 0) {
 		snd_intel8x0_free(chip);
diff --git a/sound/pci/intel8x0m.c b/sound/pci/intel8x0m.c
index 2f960fb092df..a9add5fedfcb 100644
--- a/sound/pci/intel8x0m.c
+++ b/sound/pci/intel8x0m.c
@@ -734,7 +734,7 @@ static int snd_intel8x0m_pcm1(struct intel8x0m *chip, int device,
 	chip->pcm[device] = pcm;
 
 	snd_pcm_lib_preallocate_pages_for_all(pcm, SNDRV_DMA_TYPE_DEV,
-					      snd_dma_pci_data(chip->pci),
+					      &chip->pci->dev,
 					      rec->prealloc_size,
 					      rec->prealloc_max_size);
 
@@ -1176,7 +1176,7 @@ static int snd_intel8x0m_create(struct snd_card *card,
 
 	/* allocate buffer descriptor lists */
 	/* the start of each lists must be aligned to 8 bytes */
-	if (snd_dma_alloc_pages(SNDRV_DMA_TYPE_DEV, snd_dma_pci_data(pci),
+	if (snd_dma_alloc_pages(SNDRV_DMA_TYPE_DEV, &pci->dev,
 				chip->bdbars_count * sizeof(u32) * ICH_MAX_FRAGS * 2,
 				&chip->bdbars) < 0) {
 		snd_intel8x0m_free(chip);
diff --git a/sound/pci/korg1212/korg1212.c b/sound/pci/korg1212/korg1212.c
index 0d81eac0a478..2b8204a13c69 100644
--- a/sound/pci/korg1212/korg1212.c
+++ b/sound/pci/korg1212/korg1212.c
@@ -2275,7 +2275,7 @@ static int snd_korg1212_create(struct snd_card *card, struct pci_dev *pci,
                    korg1212->idRegPtr,
 		   stateName[korg1212->cardState]);
 
-	if (snd_dma_alloc_pages(SNDRV_DMA_TYPE_DEV, snd_dma_pci_data(pci),
+	if (snd_dma_alloc_pages(SNDRV_DMA_TYPE_DEV, &pci->dev,
 				sizeof(struct KorgSharedBuffer), &korg1212->dma_shared) < 0) {
 		snd_printk(KERN_ERR "korg1212: can not allocate shared buffer memory (%zd bytes)\n", sizeof(struct KorgSharedBuffer));
                 snd_korg1212_free(korg1212);
@@ -2290,7 +2290,7 @@ static int snd_korg1212_create(struct snd_card *card, struct pci_dev *pci,
 
         korg1212->DataBufsSize = sizeof(struct KorgAudioBuffer) * kNumBuffers;
 
-	if (snd_dma_alloc_pages(SNDRV_DMA_TYPE_DEV, snd_dma_pci_data(pci),
+	if (snd_dma_alloc_pages(SNDRV_DMA_TYPE_DEV, &pci->dev,
 				korg1212->DataBufsSize, &korg1212->dma_play) < 0) {
 		snd_printk(KERN_ERR "korg1212: can not allocate play data buffer memory (%d bytes)\n", korg1212->DataBufsSize);
                 snd_korg1212_free(korg1212);
@@ -2302,7 +2302,7 @@ static int snd_korg1212_create(struct snd_card *card, struct pci_dev *pci,
         K1212_DEBUG_PRINTK("K1212_DEBUG: Play Data Area = 0x%p (0x%08x), %d bytes\n",
 		korg1212->playDataBufsPtr, korg1212->PlayDataPhy, korg1212->DataBufsSize);
 
-	if (snd_dma_alloc_pages(SNDRV_DMA_TYPE_DEV, snd_dma_pci_data(pci),
+	if (snd_dma_alloc_pages(SNDRV_DMA_TYPE_DEV, &pci->dev,
 				korg1212->DataBufsSize, &korg1212->dma_rec) < 0) {
 		snd_printk(KERN_ERR "korg1212: can not allocate record data buffer memory (%d bytes)\n", korg1212->DataBufsSize);
                 snd_korg1212_free(korg1212);
@@ -2337,7 +2337,7 @@ static int snd_korg1212_create(struct snd_card *card, struct pci_dev *pci,
 		return err;
 	}
 
-	if (snd_dma_alloc_pages(SNDRV_DMA_TYPE_DEV, snd_dma_pci_data(pci),
+	if (snd_dma_alloc_pages(SNDRV_DMA_TYPE_DEV, &pci->dev,
 				dsp_code->size, &korg1212->dma_dsp) < 0) {
 		snd_printk(KERN_ERR "korg1212: cannot allocate dsp code memory (%zd bytes)\n", dsp_code->size);
                 snd_korg1212_free(korg1212);
diff --git a/sound/pci/lola/lola.c b/sound/pci/lola/lola.c
index 5cda3488ceab..21ac9d003e8e 100644
--- a/sound/pci/lola/lola.c
+++ b/sound/pci/lola/lola.c
@@ -350,7 +350,7 @@ static int setup_corb_rirb(struct lola *chip)
 	unsigned long end_time;
 
 	err = snd_dma_alloc_pages(SNDRV_DMA_TYPE_DEV,
-				  snd_dma_pci_data(chip->pci),
+				  &chip->pci->dev,
 				  PAGE_SIZE, &chip->rb);
 	if (err < 0)
 		return err;
diff --git a/sound/pci/lola/lola_pcm.c b/sound/pci/lola/lola_pcm.c
index 151f7cf5ce0e..856bcca60128 100644
--- a/sound/pci/lola/lola_pcm.c
+++ b/sound/pci/lola/lola_pcm.c
@@ -582,7 +582,6 @@ static const struct snd_pcm_ops lola_pcm_ops = {
 	.prepare = lola_pcm_prepare,
 	.trigger = lola_pcm_trigger,
 	.pointer = lola_pcm_pointer,
-	.page = snd_pcm_sgbuf_ops_page,
 };
 
 int lola_create_pcm(struct lola *chip)
@@ -592,7 +591,7 @@ int lola_create_pcm(struct lola *chip)
 
 	for (i = 0; i < 2; i++) {
 		err = snd_dma_alloc_pages(SNDRV_DMA_TYPE_DEV,
-					  snd_dma_pci_data(chip->pci),
+					  &chip->pci->dev,
 					  PAGE_SIZE, &chip->pcm[i].bdl);
 		if (err < 0)
 			return err;
@@ -612,7 +611,7 @@ int lola_create_pcm(struct lola *chip)
 	}
 	/* buffer pre-allocation */
 	snd_pcm_lib_preallocate_pages_for_all(pcm, SNDRV_DMA_TYPE_DEV_SG,
-					      snd_dma_pci_data(chip->pci),
+					      &chip->pci->dev,
 					      1024 * 64, 32 * 1024 * 1024);
 	return 0;
 }
diff --git a/sound/pci/lx6464es/lx6464es.c b/sound/pci/lx6464es/lx6464es.c
index fe10714380f2..d0f63fa54121 100644
--- a/sound/pci/lx6464es/lx6464es.c
+++ b/sound/pci/lx6464es/lx6464es.c
@@ -846,7 +846,7 @@ static int lx_pcm_create(struct lx6464es *chip)
 	strcpy(pcm->name, card_name);
 
 	snd_pcm_lib_preallocate_pages_for_all(pcm, SNDRV_DMA_TYPE_DEV,
-					      snd_dma_pci_data(chip->pci),
+					      &chip->pci->dev,
 					      size, size);
 
 	chip->pcm = pcm;
diff --git a/sound/pci/maestro3.c b/sound/pci/maestro3.c
index 19fa73df0846..cc8594d76c70 100644
--- a/sound/pci/maestro3.c
+++ b/sound/pci/maestro3.c
@@ -1861,7 +1861,8 @@ snd_m3_pcm(struct snd_m3 * chip, int device)
 	chip->pcm = pcm;
 	
 	snd_pcm_lib_preallocate_pages_for_all(pcm, SNDRV_DMA_TYPE_DEV,
-					      snd_dma_pci_data(chip->pci), 64*1024, 64*1024);
+					      &chip->pci->dev,
+					      64*1024, 64*1024);
 
 	return 0;
 }
diff --git a/sound/pci/mixart/mixart.c b/sound/pci/mixart/mixart.c
index e5279ce54ee1..674d37ec96b3 100644
--- a/sound/pci/mixart/mixart.c
+++ b/sound/pci/mixart/mixart.c
@@ -948,7 +948,8 @@ static void preallocate_buffers(struct snd_mixart *chip, struct snd_pcm *pcm)
 	}
 #endif
 	snd_pcm_lib_preallocate_pages_for_all(pcm, SNDRV_DMA_TYPE_DEV,
-					      snd_dma_pci_data(chip->mgr->pci), 32*1024, 32*1024);
+					      &chip->mgr->pci->dev,
+					      32*1024, 32*1024);
 }
 
 /*
@@ -1360,7 +1361,7 @@ static int snd_mixart_probe(struct pci_dev *pci,
 	/* create array of streaminfo */
 	size = PAGE_ALIGN( (MIXART_MAX_STREAM_PER_CARD * MIXART_MAX_CARDS *
 			    sizeof(struct mixart_flowinfo)) );
-	if (snd_dma_alloc_pages(SNDRV_DMA_TYPE_DEV, snd_dma_pci_data(pci),
+	if (snd_dma_alloc_pages(SNDRV_DMA_TYPE_DEV, &pci->dev,
 				size, &mgr->flowinfo) < 0) {
 		snd_mixart_free(mgr);
 		return -ENOMEM;
@@ -1371,7 +1372,7 @@ static int snd_mixart_probe(struct pci_dev *pci,
 	/* create array of bufferinfo */
 	size = PAGE_ALIGN( (MIXART_MAX_STREAM_PER_CARD * MIXART_MAX_CARDS *
 			    sizeof(struct mixart_bufferinfo)) );
-	if (snd_dma_alloc_pages(SNDRV_DMA_TYPE_DEV, snd_dma_pci_data(pci),
+	if (snd_dma_alloc_pages(SNDRV_DMA_TYPE_DEV, &pci->dev,
 				size, &mgr->bufferinfo) < 0) {
 		snd_mixart_free(mgr);
 		return -ENOMEM;
diff --git a/sound/pci/oxygen/oxygen_pcm.c b/sound/pci/oxygen/oxygen_pcm.c
index e6aa16646fd4..203c8fe48a01 100644
--- a/sound/pci/oxygen/oxygen_pcm.c
+++ b/sound/pci/oxygen/oxygen_pcm.c
@@ -713,13 +713,13 @@ int oxygen_pcm_init(struct oxygen *chip)
 		if (outs)
 			snd_pcm_lib_preallocate_pages(pcm->streams[SNDRV_PCM_STREAM_PLAYBACK].substream,
 						      SNDRV_DMA_TYPE_DEV,
-						      snd_dma_pci_data(chip->pci),
+						      &chip->pci->dev,
 						      DEFAULT_BUFFER_BYTES_MULTICH,
 						      BUFFER_BYTES_MAX_MULTICH);
 		if (ins)
 			snd_pcm_lib_preallocate_pages(pcm->streams[SNDRV_PCM_STREAM_CAPTURE].substream,
 						      SNDRV_DMA_TYPE_DEV,
-						      snd_dma_pci_data(chip->pci),
+						      &chip->pci->dev,
 						      DEFAULT_BUFFER_BYTES,
 						      BUFFER_BYTES_MAX);
 	}
@@ -739,7 +739,7 @@ int oxygen_pcm_init(struct oxygen *chip)
 		pcm->private_data = chip;
 		strcpy(pcm->name, "Digital");
 		snd_pcm_lib_preallocate_pages_for_all(pcm, SNDRV_DMA_TYPE_DEV,
-						      snd_dma_pci_data(chip->pci),
+						      &chip->pci->dev,
 						      DEFAULT_BUFFER_BYTES,
 						      BUFFER_BYTES_MAX);
 	}
@@ -769,7 +769,7 @@ int oxygen_pcm_init(struct oxygen *chip)
 		pcm->private_data = chip;
 		strcpy(pcm->name, outs ? "Front Panel" : "Analog 2");
 		snd_pcm_lib_preallocate_pages_for_all(pcm, SNDRV_DMA_TYPE_DEV,
-						      snd_dma_pci_data(chip->pci),
+						      &chip->pci->dev,
 						      DEFAULT_BUFFER_BYTES,
 						      BUFFER_BYTES_MAX);
 	}
@@ -787,7 +787,7 @@ int oxygen_pcm_init(struct oxygen *chip)
 		pcm->private_data = chip;
 		strcpy(pcm->name, "Analog 3");
 		snd_pcm_lib_preallocate_pages_for_all(pcm, SNDRV_DMA_TYPE_DEV,
-						      snd_dma_pci_data(chip->pci),
+						      &chip->pci->dev,
 						      DEFAULT_BUFFER_BYTES,
 						      BUFFER_BYTES_MAX);
 	}
diff --git a/sound/pci/pcxhr/pcxhr.c b/sound/pci/pcxhr/pcxhr.c
index e493962d8455..4af34d6d92df 100644
--- a/sound/pci/pcxhr/pcxhr.c
+++ b/sound/pci/pcxhr/pcxhr.c
@@ -1171,7 +1171,7 @@ int pcxhr_create_pcm(struct snd_pcxhr *chip)
 	strcpy(pcm->name, name);
 
 	snd_pcm_lib_preallocate_pages_for_all(pcm, SNDRV_DMA_TYPE_DEV,
-					      snd_dma_pci_data(chip->mgr->pci),
+					      &chip->mgr->pci->dev,
 					      32*1024, 32*1024);
 	chip->pcm = pcm;
 	return 0;
@@ -1644,7 +1644,7 @@ static int pcxhr_probe(struct pci_dev *pci,
 
 	/* create hostport purgebuffer */
 	size = PAGE_ALIGN(sizeof(struct pcxhr_hostport));
-	if (snd_dma_alloc_pages(SNDRV_DMA_TYPE_DEV, snd_dma_pci_data(pci),
+	if (snd_dma_alloc_pages(SNDRV_DMA_TYPE_DEV, &pci->dev,
 				size, &mgr->hostport) < 0) {
 		pcxhr_free(mgr);
 		return -ENOMEM;
diff --git a/sound/pci/riptide/riptide.c b/sound/pci/riptide/riptide.c
index 58771ae0ed63..abcea86045ec 100644
--- a/sound/pci/riptide/riptide.c
+++ b/sound/pci/riptide/riptide.c
@@ -1550,7 +1550,7 @@ snd_riptide_hw_params(struct snd_pcm_substream *substream,
 	if (sgdlist->area)
 		snd_dma_free_pages(sgdlist);
 	if ((err = snd_dma_alloc_pages(SNDRV_DMA_TYPE_DEV,
-				       snd_dma_pci_data(chip->pci),
+				       &chip->pci->dev,
 				       sizeof(struct sgd) * (DESC_MAX_MASK + 1),
 				       sgdlist)) < 0) {
 		snd_printk(KERN_ERR "Riptide: failed to alloc %d dma bytes\n",
@@ -1661,7 +1661,6 @@ static const struct snd_pcm_ops snd_riptide_playback_ops = {
 	.hw_params = snd_riptide_hw_params,
 	.hw_free = snd_riptide_hw_free,
 	.prepare = snd_riptide_prepare,
-	.page = snd_pcm_sgbuf_ops_page,
 	.trigger = snd_riptide_trigger,
 	.pointer = snd_riptide_pointer,
 };
@@ -1672,7 +1671,6 @@ static const struct snd_pcm_ops snd_riptide_capture_ops = {
 	.hw_params = snd_riptide_hw_params,
 	.hw_free = snd_riptide_hw_free,
 	.prepare = snd_riptide_prepare,
-	.page = snd_pcm_sgbuf_ops_page,
 	.trigger = snd_riptide_trigger,
 	.pointer = snd_riptide_pointer,
 };
@@ -1695,7 +1693,7 @@ static int snd_riptide_pcm(struct snd_riptide *chip, int device)
 	strcpy(pcm->name, "RIPTIDE");
 	chip->pcm = pcm;
 	snd_pcm_lib_preallocate_pages_for_all(pcm, SNDRV_DMA_TYPE_DEV_SG,
-					      snd_dma_pci_data(chip->pci),
+					      &chip->pci->dev,
 					      64 * 1024, 128 * 1024);
 	return 0;
 }
diff --git a/sound/pci/rme32.c b/sound/pci/rme32.c
index 40cc6ca88f7b..58a4b8df25d4 100644
--- a/sound/pci/rme32.c
+++ b/sound/pci/rme32.c
@@ -1375,7 +1375,7 @@ static int snd_rme32_create(struct rme32 *rme32)
 		snd_pcm_set_ops(rme32->spdif_pcm, SNDRV_PCM_STREAM_CAPTURE,
 				&snd_rme32_capture_spdif_fd_ops);
 		snd_pcm_lib_preallocate_pages_for_all(rme32->spdif_pcm, SNDRV_DMA_TYPE_CONTINUOUS,
-						      snd_dma_continuous_data(GFP_KERNEL),
+						      NULL,
 						      0, RME32_MID_BUFFER_SIZE);
 		rme32->spdif_pcm->info_flags = SNDRV_PCM_INFO_JOINT_DUPLEX;
 	} else {
@@ -1407,7 +1407,7 @@ static int snd_rme32_create(struct rme32 *rme32)
 			snd_pcm_set_ops(rme32->adat_pcm, SNDRV_PCM_STREAM_CAPTURE, 
 					&snd_rme32_capture_adat_fd_ops);
 			snd_pcm_lib_preallocate_pages_for_all(rme32->adat_pcm, SNDRV_DMA_TYPE_CONTINUOUS,
-							      snd_dma_continuous_data(GFP_KERNEL),
+							      NULL,
 							      0, RME32_MID_BUFFER_SIZE);
 			rme32->adat_pcm->info_flags = SNDRV_PCM_INFO_JOINT_DUPLEX;
 		} else {
diff --git a/sound/pci/rme9652/hdsp.c b/sound/pci/rme9652/hdsp.c
index 5cbdc9be9c7e..cd20af465d8e 100644
--- a/sound/pci/rme9652/hdsp.c
+++ b/sound/pci/rme9652/hdsp.c
@@ -569,12 +569,7 @@ static char channel_map_H9632_qs[HDSP_MAX_CHANNELS] = {
 
 static int snd_hammerfall_get_buffer(struct pci_dev *pci, struct snd_dma_buffer *dmab, size_t size)
 {
-	dmab->dev.type = SNDRV_DMA_TYPE_DEV;
-	dmab->dev.dev = snd_dma_pci_data(pci);
-	if (snd_dma_alloc_pages(SNDRV_DMA_TYPE_DEV, snd_dma_pci_data(pci),
-				size, dmab) < 0)
-		return -ENOMEM;
-	return 0;
+	return snd_dma_alloc_pages(SNDRV_DMA_TYPE_DEV, &pci->dev, size, dmab);
 }
 
 static void snd_hammerfall_free_buffer(struct snd_dma_buffer *dmab, struct pci_dev *pci)
diff --git a/sound/pci/rme9652/hdspm.c b/sound/pci/rme9652/hdspm.c
index 81a6f4b2bd3c..75c06a7cc779 100644
--- a/sound/pci/rme9652/hdspm.c
+++ b/sound/pci/rme9652/hdspm.c
@@ -6368,7 +6368,6 @@ static const struct snd_pcm_ops snd_hdspm_ops = {
 	.prepare = snd_hdspm_prepare,
 	.trigger = snd_hdspm_trigger,
 	.pointer = snd_hdspm_hw_pointer,
-	.page = snd_pcm_sgbuf_ops_page,
 };
 
 static int snd_hdspm_create_hwdep(struct snd_card *card,
@@ -6407,7 +6406,7 @@ static int snd_hdspm_preallocate_memory(struct hdspm *hdspm)
 	wanted = HDSPM_DMA_AREA_BYTES;
 
 	snd_pcm_lib_preallocate_pages_for_all(pcm, SNDRV_DMA_TYPE_DEV_SG,
-					      snd_dma_pci_data(hdspm->pci),
+					      &hdspm->pci->dev,
 					      wanted, wanted);
 	dev_dbg(hdspm->card->dev, " Preallocated %zd Bytes\n", wanted);
 	return 0;
diff --git a/sound/pci/rme9652/rme9652.c b/sound/pci/rme9652/rme9652.c
index 4c851f8dcaf8..ef5c2f8e17c7 100644
--- a/sound/pci/rme9652/rme9652.c
+++ b/sound/pci/rme9652/rme9652.c
@@ -279,12 +279,7 @@ static char channel_map_9636_ds[26] = {
 
 static int snd_hammerfall_get_buffer(struct pci_dev *pci, struct snd_dma_buffer *dmab, size_t size)
 {
-	dmab->dev.type = SNDRV_DMA_TYPE_DEV;
-	dmab->dev.dev = snd_dma_pci_data(pci);
-	if (snd_dma_alloc_pages(SNDRV_DMA_TYPE_DEV, snd_dma_pci_data(pci),
-				size, dmab) < 0)
-		return -ENOMEM;
-	return 0;
+	return snd_dma_alloc_pages(SNDRV_DMA_TYPE_DEV, &pci->dev, size, dmab);
 }
 
 static void snd_hammerfall_free_buffer(struct snd_dma_buffer *dmab, struct pci_dev *pci)
diff --git a/sound/pci/sis7019.c b/sound/pci/sis7019.c
index b0b5e74e776c..ef7dd290ae05 100644
--- a/sound/pci/sis7019.c
+++ b/sound/pci/sis7019.c
@@ -905,7 +905,8 @@ static int sis_pcm_create(struct sis7019 *sis)
 	 * world if this fails.
 	 */
 	snd_pcm_lib_preallocate_pages_for_all(pcm, SNDRV_DMA_TYPE_DEV,
-				snd_dma_pci_data(sis->pci), 64*1024, 128*1024);
+					      &sis->pci->dev,
+					      64*1024, 128*1024);
 
 	return 0;
 }
diff --git a/sound/pci/sonicvibes.c b/sound/pci/sonicvibes.c
index 13103f5c309b..31cbc811ad37 100644
--- a/sound/pci/sonicvibes.c
+++ b/sound/pci/sonicvibes.c
@@ -884,7 +884,8 @@ static int snd_sonicvibes_pcm(struct sonicvibes *sonic, int device)
 	sonic->pcm = pcm;
 
 	snd_pcm_lib_preallocate_pages_for_all(pcm, SNDRV_DMA_TYPE_DEV,
-					      snd_dma_pci_data(sonic->pci), 64*1024, 128*1024);
+					      &sonic->pci->dev,
+					      64*1024, 128*1024);
 
 	return 0;
 }
diff --git a/sound/pci/trident/trident_main.c b/sound/pci/trident/trident_main.c
index 1a6f6202fd16..07022c0dad40 100644
--- a/sound/pci/trident/trident_main.c
+++ b/sound/pci/trident/trident_main.c
@@ -2076,7 +2076,6 @@ static const struct snd_pcm_ops snd_trident_nx_playback_ops = {
 	.prepare =	snd_trident_playback_prepare,
 	.trigger =	snd_trident_trigger,
 	.pointer =	snd_trident_playback_pointer,
-	.page =		snd_pcm_sgbuf_ops_page,
 };
 
 static const struct snd_pcm_ops snd_trident_capture_ops = {
@@ -2121,7 +2120,6 @@ static const struct snd_pcm_ops snd_trident_nx_foldback_ops = {
 	.prepare =	snd_trident_foldback_prepare,
 	.trigger =	snd_trident_trigger,
 	.pointer =	snd_trident_playback_pointer,
-	.page =		snd_pcm_sgbuf_ops_page,
 };
 
 static const struct snd_pcm_ops snd_trident_spdif_ops = {
@@ -2186,14 +2184,16 @@ int snd_trident_pcm(struct snd_trident *trident, int device)
 		struct snd_pcm_substream *substream;
 		for (substream = pcm->streams[SNDRV_PCM_STREAM_PLAYBACK].substream; substream; substream = substream->next)
 			snd_pcm_lib_preallocate_pages(substream, SNDRV_DMA_TYPE_DEV_SG,
-						      snd_dma_pci_data(trident->pci),
+						      &trident->pci->dev,
 						      64*1024, 128*1024);
 		snd_pcm_lib_preallocate_pages(pcm->streams[SNDRV_PCM_STREAM_CAPTURE].substream,
-					      SNDRV_DMA_TYPE_DEV, snd_dma_pci_data(trident->pci),
+					      SNDRV_DMA_TYPE_DEV,
+					      &trident->pci->dev,
 					      64*1024, 128*1024);
 	} else {
 		snd_pcm_lib_preallocate_pages_for_all(pcm, SNDRV_DMA_TYPE_DEV,
-						      snd_dma_pci_data(trident->pci), 64*1024, 128*1024);
+						      &trident->pci->dev,
+						      64*1024, 128*1024);
 	}
 
 	return 0;
@@ -2243,10 +2243,12 @@ int snd_trident_foldback_pcm(struct snd_trident *trident, int device)
 
 	if (trident->tlb.entries)
 		snd_pcm_lib_preallocate_pages_for_all(foldback, SNDRV_DMA_TYPE_DEV_SG,
-						      snd_dma_pci_data(trident->pci), 0, 128*1024);
+						      &trident->pci->dev,
+						      0, 128*1024);
 	else
 		snd_pcm_lib_preallocate_pages_for_all(foldback, SNDRV_DMA_TYPE_DEV,
-						      snd_dma_pci_data(trident->pci), 64*1024, 128*1024);
+						      &trident->pci->dev,
+						      64*1024, 128*1024);
 
 	return 0;
 }
@@ -2280,7 +2282,9 @@ int snd_trident_spdif_pcm(struct snd_trident *trident, int device)
 	strcpy(spdif->name, "Trident 4DWave IEC958");
 	trident->spdif = spdif;
 
-	snd_pcm_lib_preallocate_pages_for_all(spdif, SNDRV_DMA_TYPE_DEV, snd_dma_pci_data(trident->pci), 64*1024, 128*1024);
+	snd_pcm_lib_preallocate_pages_for_all(spdif, SNDRV_DMA_TYPE_DEV,
+					      &trident->pci->dev,
+					      64*1024, 128*1024);
 
 	return 0;
 }
@@ -3338,7 +3342,7 @@ static int snd_trident_tlb_alloc(struct snd_trident *trident)
 	/* TLB array must be aligned to 16kB !!! so we allocate
 	   32kB region and correct offset when necessary */
 
-	if (snd_dma_alloc_pages(SNDRV_DMA_TYPE_DEV, snd_dma_pci_data(trident->pci),
+	if (snd_dma_alloc_pages(SNDRV_DMA_TYPE_DEV, &trident->pci->dev,
 				2 * SNDRV_TRIDENT_MAX_PAGES * 4, &trident->tlb.buffer) < 0) {
 		dev_err(trident->card->dev, "unable to allocate TLB buffer\n");
 		return -ENOMEM;
@@ -3353,7 +3357,7 @@ static int snd_trident_tlb_alloc(struct snd_trident *trident)
 		return -ENOMEM;
 
 	/* allocate and setup silent page and initialise TLB entries */
-	if (snd_dma_alloc_pages(SNDRV_DMA_TYPE_DEV, snd_dma_pci_data(trident->pci),
+	if (snd_dma_alloc_pages(SNDRV_DMA_TYPE_DEV, &trident->pci->dev,
 				SNDRV_TRIDENT_PAGE_SIZE, &trident->tlb.silent_page) < 0) {
 		dev_err(trident->card->dev, "unable to allocate silent page\n");
 		return -ENOMEM;
diff --git a/sound/pci/via82xx.c b/sound/pci/via82xx.c
index 38601d0dfb73..30c817b6b635 100644
--- a/sound/pci/via82xx.c
+++ b/sound/pci/via82xx.c
@@ -419,7 +419,7 @@ static int build_via_table(struct viadev *dev, struct snd_pcm_substream *substre
 		/* the start of each lists must be aligned to 8 bytes,
 		 * but the kernel pages are much bigger, so we don't care
 		 */
-		if (snd_dma_alloc_pages(SNDRV_DMA_TYPE_DEV, snd_dma_pci_data(chip->pci),
+		if (snd_dma_alloc_pages(SNDRV_DMA_TYPE_DEV, &chip->pci->dev,
 					PAGE_ALIGN(VIA_TABLE_SIZE * 2 * 8),
 					&dev->table) < 0)
 			return -ENOMEM;
@@ -1363,7 +1363,6 @@ static const struct snd_pcm_ops snd_via686_playback_ops = {
 	.prepare =	snd_via686_playback_prepare,
 	.trigger =	snd_via82xx_pcm_trigger,
 	.pointer =	snd_via686_pcm_pointer,
-	.page =		snd_pcm_sgbuf_ops_page,
 };
 
 /* via686 capture callbacks */
@@ -1376,7 +1375,6 @@ static const struct snd_pcm_ops snd_via686_capture_ops = {
 	.prepare =	snd_via686_capture_prepare,
 	.trigger =	snd_via82xx_pcm_trigger,
 	.pointer =	snd_via686_pcm_pointer,
-	.page =		snd_pcm_sgbuf_ops_page,
 };
 
 /* via823x DSX playback callbacks */
@@ -1389,7 +1387,6 @@ static const struct snd_pcm_ops snd_via8233_playback_ops = {
 	.prepare =	snd_via8233_playback_prepare,
 	.trigger =	snd_via82xx_pcm_trigger,
 	.pointer =	snd_via8233_pcm_pointer,
-	.page =		snd_pcm_sgbuf_ops_page,
 };
 
 /* via823x multi-channel playback callbacks */
@@ -1402,7 +1399,6 @@ static const struct snd_pcm_ops snd_via8233_multi_ops = {
 	.prepare =	snd_via8233_multi_prepare,
 	.trigger =	snd_via82xx_pcm_trigger,
 	.pointer =	snd_via8233_pcm_pointer,
-	.page =		snd_pcm_sgbuf_ops_page,
 };
 
 /* via823x capture callbacks */
@@ -1415,7 +1411,6 @@ static const struct snd_pcm_ops snd_via8233_capture_ops = {
 	.prepare =	snd_via8233_capture_prepare,
 	.trigger =	snd_via82xx_pcm_trigger,
 	.pointer =	snd_via8233_pcm_pointer,
-	.page =		snd_pcm_sgbuf_ops_page,
 };
 
 
@@ -1459,7 +1454,7 @@ static int snd_via8233_pcm_new(struct via82xx *chip)
 	init_viadev(chip, chip->capture_devno, VIA_REG_CAPTURE_8233_STATUS, 6, 1);
 
 	snd_pcm_lib_preallocate_pages_for_all(pcm, SNDRV_DMA_TYPE_DEV_SG,
-					      snd_dma_pci_data(chip->pci),
+					      &chip->pci->dev,
 					      64*1024, VIA_MAX_BUFSIZE);
 
 	err = snd_pcm_add_chmap_ctls(pcm, SNDRV_PCM_STREAM_PLAYBACK,
@@ -1483,7 +1478,7 @@ static int snd_via8233_pcm_new(struct via82xx *chip)
 	init_viadev(chip, chip->capture_devno + 1, VIA_REG_CAPTURE_8233_STATUS + 0x10, 7, 1);
 
 	snd_pcm_lib_preallocate_pages_for_all(pcm, SNDRV_DMA_TYPE_DEV_SG,
-					      snd_dma_pci_data(chip->pci),
+					      &chip->pci->dev,
 					      64*1024, VIA_MAX_BUFSIZE);
 
 	err = snd_pcm_add_chmap_ctls(pcm, SNDRV_PCM_STREAM_PLAYBACK,
@@ -1526,7 +1521,7 @@ static int snd_via8233a_pcm_new(struct via82xx *chip)
 	init_viadev(chip, chip->capture_devno, VIA_REG_CAPTURE_8233_STATUS, 6, 1);
 
 	snd_pcm_lib_preallocate_pages_for_all(pcm, SNDRV_DMA_TYPE_DEV_SG,
-					      snd_dma_pci_data(chip->pci),
+					      &chip->pci->dev,
 					      64*1024, VIA_MAX_BUFSIZE);
 
 	err = snd_pcm_add_chmap_ctls(pcm, SNDRV_PCM_STREAM_PLAYBACK,
@@ -1552,7 +1547,7 @@ static int snd_via8233a_pcm_new(struct via82xx *chip)
 	init_viadev(chip, chip->playback_devno, 0x30, 3, 0);
 
 	snd_pcm_lib_preallocate_pages_for_all(pcm, SNDRV_DMA_TYPE_DEV_SG,
-					      snd_dma_pci_data(chip->pci),
+					      &chip->pci->dev,
 					      64*1024, VIA_MAX_BUFSIZE);
 	return 0;
 }
@@ -1582,7 +1577,7 @@ static int snd_via686_pcm_new(struct via82xx *chip)
 	init_viadev(chip, 1, VIA_REG_CAPTURE_STATUS, 0, 1);
 
 	snd_pcm_lib_preallocate_pages_for_all(pcm, SNDRV_DMA_TYPE_DEV_SG,
-					      snd_dma_pci_data(chip->pci),
+					      &chip->pci->dev,
 					      64*1024, VIA_MAX_BUFSIZE);
 	return 0;
 }
diff --git a/sound/pci/via82xx_modem.c b/sound/pci/via82xx_modem.c
index bfb5e1b89d5f..0edb9ea6e8a6 100644
--- a/sound/pci/via82xx_modem.c
+++ b/sound/pci/via82xx_modem.c
@@ -272,7 +272,7 @@ static int build_via_table(struct viadev *dev, struct snd_pcm_substream *substre
 		/* the start of each lists must be aligned to 8 bytes,
 		 * but the kernel pages are much bigger, so we don't care
 		 */
-		if (snd_dma_alloc_pages(SNDRV_DMA_TYPE_DEV, snd_dma_pci_data(chip->pci),
+		if (snd_dma_alloc_pages(SNDRV_DMA_TYPE_DEV, &chip->pci->dev,
 					PAGE_ALIGN(VIA_TABLE_SIZE * 2 * 8),
 					&dev->table) < 0)
 			return -ENOMEM;
@@ -801,7 +801,6 @@ static const struct snd_pcm_ops snd_via686_playback_ops = {
 	.prepare =	snd_via82xx_pcm_prepare,
 	.trigger =	snd_via82xx_pcm_trigger,
 	.pointer =	snd_via686_pcm_pointer,
-	.page =		snd_pcm_sgbuf_ops_page,
 };
 
 /* via686 capture callbacks */
@@ -814,7 +813,6 @@ static const struct snd_pcm_ops snd_via686_capture_ops = {
 	.prepare =	snd_via82xx_pcm_prepare,
 	.trigger =	snd_via82xx_pcm_trigger,
 	.pointer =	snd_via686_pcm_pointer,
-	.page =		snd_pcm_sgbuf_ops_page,
 };
 
 
@@ -852,7 +850,7 @@ static int snd_via686_pcm_new(struct via82xx_modem *chip)
 	init_viadev(chip, 1, VIA_REG_MI_STATUS, 1);
 
 	snd_pcm_lib_preallocate_pages_for_all(pcm, SNDRV_DMA_TYPE_DEV_SG,
-					      snd_dma_pci_data(chip->pci),
+					      &chip->pci->dev,
 					      64*1024, 128*1024);
 	return 0;
 }
diff --git a/sound/pci/ymfpci/ymfpci_main.c b/sound/pci/ymfpci/ymfpci_main.c
index 90400ebb64af..125c11ed5064 100644
--- a/sound/pci/ymfpci/ymfpci_main.c
+++ b/sound/pci/ymfpci/ymfpci_main.c
@@ -587,7 +587,7 @@ static void snd_ymfpci_pcm_init_voice(struct snd_ymfpci_pcm *ypcm, unsigned int
 
 static int snd_ymfpci_ac3_init(struct snd_ymfpci *chip)
 {
-	if (snd_dma_alloc_pages(SNDRV_DMA_TYPE_DEV, snd_dma_pci_data(chip->pci),
+	if (snd_dma_alloc_pages(SNDRV_DMA_TYPE_DEV, &chip->pci->dev,
 				4096, &chip->ac3_tmp_base) < 0)
 		return -ENOMEM;
 
@@ -1149,7 +1149,8 @@ int snd_ymfpci_pcm(struct snd_ymfpci *chip, int device)
 	chip->pcm = pcm;
 
 	snd_pcm_lib_preallocate_pages_for_all(pcm, SNDRV_DMA_TYPE_DEV,
-					      snd_dma_pci_data(chip->pci), 64*1024, 256*1024);
+					      &chip->pci->dev,
+					      64*1024, 256*1024);
 
 	return snd_pcm_add_chmap_ctls(pcm, SNDRV_PCM_STREAM_PLAYBACK,
 				     snd_pcm_std_chmaps, 2, 0, NULL);
@@ -1184,7 +1185,8 @@ int snd_ymfpci_pcm2(struct snd_ymfpci *chip, int device)
 	chip->pcm2 = pcm;
 
 	snd_pcm_lib_preallocate_pages_for_all(pcm, SNDRV_DMA_TYPE_DEV,
-					      snd_dma_pci_data(chip->pci), 64*1024, 256*1024);
+					      &chip->pci->dev,
+					      64*1024, 256*1024);
 
 	return 0;
 }
@@ -1217,7 +1219,8 @@ int snd_ymfpci_pcm_spdif(struct snd_ymfpci *chip, int device)
 	chip->pcm_spdif = pcm;
 
 	snd_pcm_lib_preallocate_pages_for_all(pcm, SNDRV_DMA_TYPE_DEV,
-					      snd_dma_pci_data(chip->pci), 64*1024, 256*1024);
+					      &chip->pci->dev,
+					      64*1024, 256*1024);
 
 	return 0;
 }
@@ -1258,7 +1261,8 @@ int snd_ymfpci_pcm_4ch(struct snd_ymfpci *chip, int device)
 	chip->pcm_4ch = pcm;
 
 	snd_pcm_lib_preallocate_pages_for_all(pcm, SNDRV_DMA_TYPE_DEV,
-					      snd_dma_pci_data(chip->pci), 64*1024, 256*1024);
+					      &chip->pci->dev,
+					      64*1024, 256*1024);
 
 	return snd_pcm_add_chmap_ctls(pcm, SNDRV_PCM_STREAM_PLAYBACK,
 				     surround_map, 2, 0, NULL);
@@ -2108,7 +2112,7 @@ static int snd_ymfpci_memalloc(struct snd_ymfpci *chip)
 	       chip->work_size;
 	/* work_ptr must be aligned to 256 bytes, but it's already
 	   covered with the kernel page allocation mechanism */
-	if (snd_dma_alloc_pages(SNDRV_DMA_TYPE_DEV, snd_dma_pci_data(chip->pci),
+	if (snd_dma_alloc_pages(SNDRV_DMA_TYPE_DEV, &chip->pci->dev,
 				size, &chip->work_ptr) < 0) 
 		return -ENOMEM;
 	ptr = chip->work_ptr.area;
diff --git a/sound/pcmcia/pdaudiocf/pdaudiocf_pcm.c b/sound/pcmcia/pdaudiocf/pdaudiocf_pcm.c
index c21fec60cd98..067b1c3a3e02 100644
--- a/sound/pcmcia/pdaudiocf/pdaudiocf_pcm.c
+++ b/sound/pcmcia/pdaudiocf/pdaudiocf_pcm.c
@@ -89,8 +89,7 @@ static int pdacf_pcm_trigger(struct snd_pcm_substream *subs, int cmd)
 static int pdacf_pcm_hw_params(struct snd_pcm_substream *subs,
 				     struct snd_pcm_hw_params *hw_params)
 {
-	return snd_pcm_lib_alloc_vmalloc_32_buffer
-					(subs, params_buffer_bytes(hw_params));
+	return snd_pcm_lib_malloc_pages(subs, params_buffer_bytes(hw_params));
 }
 
 /*
@@ -98,7 +97,7 @@ static int pdacf_pcm_hw_params(struct snd_pcm_substream *subs,
  */
 static int pdacf_pcm_hw_free(struct snd_pcm_substream *subs)
 {
-	return snd_pcm_lib_free_vmalloc_buffer(subs);
+	return snd_pcm_lib_free_pages(subs);
 }
 
 /*
@@ -262,7 +261,6 @@ static const struct snd_pcm_ops pdacf_pcm_capture_ops = {
 	.prepare =	pdacf_pcm_prepare,
 	.trigger =	pdacf_pcm_trigger,
 	.pointer =	pdacf_pcm_capture_pointer,
-	.page =		snd_pcm_lib_get_vmalloc_page,
 };
 
 
@@ -279,6 +277,9 @@ int snd_pdacf_pcm_new(struct snd_pdacf *chip)
 		return err;
 		
 	snd_pcm_set_ops(pcm, SNDRV_PCM_STREAM_CAPTURE, &pdacf_pcm_capture_ops);
+	snd_pcm_lib_preallocate_pages_for_all(pcm, SNDRV_DMA_TYPE_VMALLOC,
+					      snd_dma_continuous_data(GFP_KERNEL | GFP_DMA32),
+					      0, 0);
 
 	pcm->private_data = chip;
 	pcm->info_flags = 0;
diff --git a/sound/sh/aica.c b/sound/sh/aica.c
index 52e9cfb4f819..bf1fb0d8a930 100644
--- a/sound/sh/aica.c
+++ b/sound/sh/aica.c
@@ -443,7 +443,7 @@ static int __init snd_aicapcmchip(struct snd_card_aica
 	/* Allocate the DMA buffers */
 	snd_pcm_lib_preallocate_pages_for_all(pcm,
 					      SNDRV_DMA_TYPE_CONTINUOUS,
-					      snd_dma_continuous_data(GFP_KERNEL),
+					      NULL,
 					      AICA_BUFFER_SIZE,
 					      AICA_BUFFER_SIZE);
 	return 0;
diff --git a/sound/sh/sh_dac_audio.c b/sound/sh/sh_dac_audio.c
index ed877a138965..f9e36abc98ac 100644
--- a/sound/sh/sh_dac_audio.c
+++ b/sound/sh/sh_dac_audio.c
@@ -268,7 +268,7 @@ static int snd_sh_dac_pcm(struct snd_sh_dac *chip, int device)
 
 	/* buffer size=48K */
 	snd_pcm_lib_preallocate_pages_for_all(pcm, SNDRV_DMA_TYPE_CONTINUOUS,
-					  snd_dma_continuous_data(GFP_KERNEL),
+					      NULL,
 							48 * 1024,
 							48 * 1024);
 
diff --git a/sound/soc/amd/acp-pcm-dma.c b/sound/soc/amd/acp-pcm-dma.c
index 52225b4b6382..4b9a27e25206 100644
--- a/sound/soc/amd/acp-pcm-dma.c
+++ b/sound/soc/amd/acp-pcm-dma.c
@@ -759,14 +759,12 @@ static irqreturn_t dma_irq_handler(int irq, void *arg)
 		return IRQ_NONE;
 }
 
-static int acp_dma_open(struct snd_pcm_substream *substream)
+static int acp_dma_open(struct snd_soc_component *component,
+			struct snd_pcm_substream *substream)
 {
 	u16 bank;
 	int ret = 0;
 	struct snd_pcm_runtime *runtime = substream->runtime;
-	struct snd_soc_pcm_runtime *prtd = substream->private_data;
-	struct snd_soc_component *component = snd_soc_rtdcom_lookup(prtd,
-								    DRV_NAME);
 	struct audio_drv_data *intr_data = dev_get_drvdata(component->dev);
 	struct audio_substream_data *adata =
 		kzalloc(sizeof(struct audio_substream_data), GFP_KERNEL);
@@ -834,7 +832,8 @@ static int acp_dma_open(struct snd_pcm_substream *substream)
 	return 0;
 }
 
-static int acp_dma_hw_params(struct snd_pcm_substream *substream,
+static int acp_dma_hw_params(struct snd_soc_component *component,
+			     struct snd_pcm_substream *substream,
 			     struct snd_pcm_hw_params *params)
 {
 	int status;
@@ -843,8 +842,6 @@ static int acp_dma_hw_params(struct snd_pcm_substream *substream,
 	struct snd_pcm_runtime *runtime;
 	struct audio_substream_data *rtd;
 	struct snd_soc_pcm_runtime *prtd = substream->private_data;
-	struct snd_soc_component *component = snd_soc_rtdcom_lookup(prtd,
-								    DRV_NAME);
 	struct audio_drv_data *adata = dev_get_drvdata(component->dev);
 	struct snd_soc_card *card = prtd->card;
 	struct acp_platform_info *pinfo = snd_soc_card_get_drvdata(card);
@@ -995,7 +992,8 @@ static int acp_dma_hw_params(struct snd_pcm_substream *substream,
 	return status;
 }
 
-static int acp_dma_hw_free(struct snd_pcm_substream *substream)
+static int acp_dma_hw_free(struct snd_soc_component *component,
+			   struct snd_pcm_substream *substream)
 {
 	return snd_pcm_lib_free_pages(substream);
 }
@@ -1011,7 +1009,8 @@ static u64 acp_get_byte_count(struct audio_substream_data *rtd)
 	return byte_count.bytescount;
 }
 
-static snd_pcm_uframes_t acp_dma_pointer(struct snd_pcm_substream *substream)
+static snd_pcm_uframes_t acp_dma_pointer(struct snd_soc_component *component,
+					 struct snd_pcm_substream *substream)
 {
 	u32 buffersize;
 	u32 pos = 0;
@@ -1053,13 +1052,15 @@ static snd_pcm_uframes_t acp_dma_pointer(struct snd_pcm_substream *substream)
 	return bytes_to_frames(runtime, pos);
 }
 
-static int acp_dma_mmap(struct snd_pcm_substream *substream,
+static int acp_dma_mmap(struct snd_soc_component *component,
+			struct snd_pcm_substream *substream,
 			struct vm_area_struct *vma)
 {
 	return snd_pcm_lib_default_mmap(substream, vma);
 }
 
-static int acp_dma_prepare(struct snd_pcm_substream *substream)
+static int acp_dma_prepare(struct snd_soc_component *component,
+			   struct snd_pcm_substream *substream)
 {
 	struct snd_pcm_runtime *runtime = substream->runtime;
 	struct audio_substream_data *rtd = runtime->private_data;
@@ -1086,7 +1087,8 @@ static int acp_dma_prepare(struct snd_pcm_substream *substream)
 	return 0;
 }
 
-static int acp_dma_trigger(struct snd_pcm_substream *substream, int cmd)
+static int acp_dma_trigger(struct snd_soc_component *component,
+			   struct snd_pcm_substream *substream, int cmd)
 {
 	int ret;
 
@@ -1132,10 +1134,9 @@ static int acp_dma_trigger(struct snd_pcm_substream *substream, int cmd)
 	return ret;
 }
 
-static int acp_dma_new(struct snd_soc_pcm_runtime *rtd)
+static int acp_dma_new(struct snd_soc_component *component,
+		       struct snd_soc_pcm_runtime *rtd)
 {
-	struct snd_soc_component *component = snd_soc_rtdcom_lookup(rtd,
-								    DRV_NAME);
 	struct audio_drv_data *adata = dev_get_drvdata(component->dev);
 	struct device *parent = component->dev->parent;
 
@@ -1158,14 +1159,12 @@ static int acp_dma_new(struct snd_soc_pcm_runtime *rtd)
 	return 0;
 }
 
-static int acp_dma_close(struct snd_pcm_substream *substream)
+static int acp_dma_close(struct snd_soc_component *component,
+			 struct snd_pcm_substream *substream)
 {
 	u16 bank;
 	struct snd_pcm_runtime *runtime = substream->runtime;
 	struct audio_substream_data *rtd = runtime->private_data;
-	struct snd_soc_pcm_runtime *prtd = substream->private_data;
-	struct snd_soc_component *component = snd_soc_rtdcom_lookup(prtd,
-								    DRV_NAME);
 	struct audio_drv_data *adata = dev_get_drvdata(component->dev);
 
 	if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK) {
@@ -1216,22 +1215,18 @@ static int acp_dma_close(struct snd_pcm_substream *substream)
 	return 0;
 }
 
-static const struct snd_pcm_ops acp_dma_ops = {
-	.open = acp_dma_open,
-	.close = acp_dma_close,
-	.ioctl = snd_pcm_lib_ioctl,
-	.hw_params = acp_dma_hw_params,
-	.hw_free = acp_dma_hw_free,
-	.trigger = acp_dma_trigger,
-	.pointer = acp_dma_pointer,
-	.mmap = acp_dma_mmap,
-	.prepare = acp_dma_prepare,
-};
-
 static const struct snd_soc_component_driver acp_asoc_platform = {
-	.name = DRV_NAME,
-	.ops = &acp_dma_ops,
-	.pcm_new = acp_dma_new,
+	.name		= DRV_NAME,
+	.open		= acp_dma_open,
+	.close		= acp_dma_close,
+	.ioctl		= snd_soc_pcm_lib_ioctl,
+	.hw_params	= acp_dma_hw_params,
+	.hw_free	= acp_dma_hw_free,
+	.trigger	= acp_dma_trigger,
+	.pointer	= acp_dma_pointer,
+	.mmap		= acp_dma_mmap,
+	.prepare	= acp_dma_prepare,
+	.pcm_construct	= acp_dma_new,
 };
 
 static int acp_audio_probe(struct platform_device *pdev)
diff --git a/sound/soc/amd/raven/acp3x-pcm-dma.c b/sound/soc/amd/raven/acp3x-pcm-dma.c
index bc4dfafdfcd1..60709e3ba99d 100644
--- a/sound/soc/amd/raven/acp3x-pcm-dma.c
+++ b/sound/soc/amd/raven/acp3x-pcm-dma.c
@@ -275,16 +275,12 @@ static void config_acp3x_dma(struct i2s_stream_instance *rtd, int direction)
 		  rtd->acp3x_base + mmACP_EXTERNAL_INTR_CNTL);
 }
 
-static int acp3x_dma_open(struct snd_pcm_substream *substream)
+static int acp3x_dma_open(struct snd_soc_component *component,
+			  struct snd_pcm_substream *substream)
 {
 	int ret = 0;
-
 	struct snd_pcm_runtime *runtime = substream->runtime;
-	struct snd_soc_pcm_runtime *prtd = substream->private_data;
-	struct snd_soc_component *component = snd_soc_rtdcom_lookup(prtd,
-								    DRV_NAME);
 	struct i2s_dev_data *adata = dev_get_drvdata(component->dev);
-
 	struct i2s_stream_instance *i2s_data = kzalloc(sizeof(struct i2s_stream_instance),
 						       GFP_KERNEL);
 	if (!i2s_data)
@@ -334,7 +330,8 @@ static u64 acp_get_byte_count(struct i2s_stream_instance *rtd, int direction)
 	return byte_count;
 }
 
-static int acp3x_dma_hw_params(struct snd_pcm_substream *substream,
+static int acp3x_dma_hw_params(struct snd_soc_component *component,
+			       struct snd_pcm_substream *substream,
 			       struct snd_pcm_hw_params *params)
 {
 	int status;
@@ -362,7 +359,8 @@ static int acp3x_dma_hw_params(struct snd_pcm_substream *substream,
 	return status;
 }
 
-static snd_pcm_uframes_t acp3x_dma_pointer(struct snd_pcm_substream *substream)
+static snd_pcm_uframes_t acp3x_dma_pointer(struct snd_soc_component *component,
+					   struct snd_pcm_substream *substream)
 {
 	u32 pos = 0;
 	u32 buffersize = 0;
@@ -379,33 +377,32 @@ static snd_pcm_uframes_t acp3x_dma_pointer(struct snd_pcm_substream *substream)
 	return bytes_to_frames(substream->runtime, pos);
 }
 
-static int acp3x_dma_new(struct snd_soc_pcm_runtime *rtd)
+static int acp3x_dma_new(struct snd_soc_component *component,
+			 struct snd_soc_pcm_runtime *rtd)
 {
-	struct snd_soc_component *component = snd_soc_rtdcom_lookup(rtd,
-								    DRV_NAME);
 	struct device *parent = component->dev->parent;
 	snd_pcm_lib_preallocate_pages_for_all(rtd->pcm, SNDRV_DMA_TYPE_DEV,
 					      parent, MIN_BUFFER, MAX_BUFFER);
 	return 0;
 }
 
-static int acp3x_dma_hw_free(struct snd_pcm_substream *substream)
+static int acp3x_dma_hw_free(struct snd_soc_component *component,
+			     struct snd_pcm_substream *substream)
 {
 	return snd_pcm_lib_free_pages(substream);
 }
 
-static int acp3x_dma_mmap(struct snd_pcm_substream *substream,
+static int acp3x_dma_mmap(struct snd_soc_component *component,
+			  struct snd_pcm_substream *substream,
 			  struct vm_area_struct *vma)
 {
 	return snd_pcm_lib_default_mmap(substream, vma);
 }
 
-static int acp3x_dma_close(struct snd_pcm_substream *substream)
+static int acp3x_dma_close(struct snd_soc_component *component,
+			   struct snd_pcm_substream *substream)
 {
-	struct snd_soc_pcm_runtime *prtd = substream->private_data;
 	struct i2s_stream_instance *rtd = substream->runtime->private_data;
-	struct snd_soc_component *component = snd_soc_rtdcom_lookup(prtd,
-								    DRV_NAME);
 	struct i2s_dev_data *adata = dev_get_drvdata(component->dev);
 
 	if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK)
@@ -422,17 +419,6 @@ static int acp3x_dma_close(struct snd_pcm_substream *substream)
 	return 0;
 }
 
-static struct snd_pcm_ops acp3x_dma_ops = {
-	.open = acp3x_dma_open,
-	.close = acp3x_dma_close,
-	.ioctl = snd_pcm_lib_ioctl,
-	.hw_params = acp3x_dma_hw_params,
-	.hw_free = acp3x_dma_hw_free,
-	.pointer = acp3x_dma_pointer,
-	.mmap = acp3x_dma_mmap,
-};
-
-
 static int acp3x_dai_i2s_set_fmt(struct snd_soc_dai *cpu_dai, unsigned int fmt)
 {
 
@@ -610,9 +596,15 @@ static struct snd_soc_dai_driver acp3x_i2s_dai_driver = {
 };
 
 static const struct snd_soc_component_driver acp3x_i2s_component = {
-	.name           = DRV_NAME,
-	.ops		= &acp3x_dma_ops,
-	.pcm_new	= acp3x_dma_new,
+	.name		= DRV_NAME,
+	.open		= acp3x_dma_open,
+	.close		= acp3x_dma_close,
+	.ioctl		= snd_soc_pcm_lib_ioctl,
+	.hw_params	= acp3x_dma_hw_params,
+	.hw_free	= acp3x_dma_hw_free,
+	.pointer	= acp3x_dma_pointer,
+	.mmap		= acp3x_dma_mmap,
+	.pcm_construct	= acp3x_dma_new,
 };
 
 static int acp3x_audio_probe(struct platform_device *pdev)
@@ -631,7 +623,7 @@ static int acp3x_audio_probe(struct platform_device *pdev)
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	if (!res) {
 		dev_err(&pdev->dev, "IORESOURCE_IRQ FAILED\n");
-			return -ENODEV;
+		return -ENODEV;
 	}
 
 	adata = devm_kzalloc(&pdev->dev, sizeof(*adata), GFP_KERNEL);
diff --git a/sound/soc/atmel/atmel-pcm-pdc.c b/sound/soc/atmel/atmel-pcm-pdc.c
index ed095af866db..18a2fd02fffe 100644
--- a/sound/soc/atmel/atmel-pcm-pdc.c
+++ b/sound/soc/atmel/atmel-pcm-pdc.c
@@ -56,15 +56,17 @@ static int atmel_pcm_preallocate_dma_buffer(struct snd_pcm *pcm,
 	return 0;
 }
 
-static int atmel_pcm_mmap(struct snd_pcm_substream *substream,
-	struct vm_area_struct *vma)
+static int atmel_pcm_mmap(struct snd_soc_component *component,
+			  struct snd_pcm_substream *substream,
+			  struct vm_area_struct *vma)
 {
 	return remap_pfn_range(vma, vma->vm_start,
 		       substream->dma_buffer.addr >> PAGE_SHIFT,
 		       vma->vm_end - vma->vm_start, vma->vm_page_prot);
 }
 
-static int atmel_pcm_new(struct snd_soc_pcm_runtime *rtd)
+static int atmel_pcm_new(struct snd_soc_component *component,
+			 struct snd_soc_pcm_runtime *rtd)
 {
 	struct snd_card *card = rtd->card->snd_card;
 	struct snd_pcm *pcm = rtd->pcm;
@@ -93,7 +95,8 @@ static int atmel_pcm_new(struct snd_soc_pcm_runtime *rtd)
 	return ret;
 }
 
-static void atmel_pcm_free(struct snd_pcm *pcm)
+static void atmel_pcm_free(struct snd_soc_component *component,
+			   struct snd_pcm *pcm)
 {
 	struct snd_pcm_substream *substream;
 	struct snd_dma_buffer *buf;
@@ -196,8 +199,9 @@ static void atmel_pcm_dma_irq(u32 ssc_sr,
 /*--------------------------------------------------------------------------*\
  * PCM operations
 \*--------------------------------------------------------------------------*/
-static int atmel_pcm_hw_params(struct snd_pcm_substream *substream,
-	struct snd_pcm_hw_params *params)
+static int atmel_pcm_hw_params(struct snd_soc_component *component,
+			       struct snd_pcm_substream *substream,
+			       struct snd_pcm_hw_params *params)
 {
 	struct snd_pcm_runtime *runtime = substream->runtime;
 	struct atmel_runtime_data *prtd = runtime->private_data;
@@ -225,7 +229,8 @@ static int atmel_pcm_hw_params(struct snd_pcm_substream *substream,
 	return 0;
 }
 
-static int atmel_pcm_hw_free(struct snd_pcm_substream *substream)
+static int atmel_pcm_hw_free(struct snd_soc_component *component,
+			     struct snd_pcm_substream *substream)
 {
 	struct atmel_runtime_data *prtd = substream->runtime->private_data;
 	struct atmel_pcm_dma_params *params = prtd->params;
@@ -239,7 +244,8 @@ static int atmel_pcm_hw_free(struct snd_pcm_substream *substream)
 	return 0;
 }
 
-static int atmel_pcm_prepare(struct snd_pcm_substream *substream)
+static int atmel_pcm_prepare(struct snd_soc_component *component,
+			     struct snd_pcm_substream *substream)
 {
 	struct atmel_runtime_data *prtd = substream->runtime->private_data;
 	struct atmel_pcm_dma_params *params = prtd->params;
@@ -251,8 +257,8 @@ static int atmel_pcm_prepare(struct snd_pcm_substream *substream)
 	return 0;
 }
 
-static int atmel_pcm_trigger(struct snd_pcm_substream *substream,
-	int cmd)
+static int atmel_pcm_trigger(struct snd_soc_component *component,
+			     struct snd_pcm_substream *substream, int cmd)
 {
 	struct snd_pcm_runtime *rtd = substream->runtime;
 	struct atmel_runtime_data *prtd = rtd->private_data;
@@ -317,8 +323,8 @@ static int atmel_pcm_trigger(struct snd_pcm_substream *substream,
 	return ret;
 }
 
-static snd_pcm_uframes_t atmel_pcm_pointer(
-	struct snd_pcm_substream *substream)
+static snd_pcm_uframes_t atmel_pcm_pointer(struct snd_soc_component *component,
+					   struct snd_pcm_substream *substream)
 {
 	struct snd_pcm_runtime *runtime = substream->runtime;
 	struct atmel_runtime_data *prtd = runtime->private_data;
@@ -335,7 +341,8 @@ static snd_pcm_uframes_t atmel_pcm_pointer(
 	return x;
 }
 
-static int atmel_pcm_open(struct snd_pcm_substream *substream)
+static int atmel_pcm_open(struct snd_soc_component *component,
+			  struct snd_pcm_substream *substream)
 {
 	struct snd_pcm_runtime *runtime = substream->runtime;
 	struct atmel_runtime_data *prtd;
@@ -360,7 +367,8 @@ static int atmel_pcm_open(struct snd_pcm_substream *substream)
 	return ret;
 }
 
-static int atmel_pcm_close(struct snd_pcm_substream *substream)
+static int atmel_pcm_close(struct snd_soc_component *component,
+			   struct snd_pcm_substream *substream)
 {
 	struct atmel_runtime_data *prtd = substream->runtime->private_data;
 
@@ -368,22 +376,18 @@ static int atmel_pcm_close(struct snd_pcm_substream *substream)
 	return 0;
 }
 
-static const struct snd_pcm_ops atmel_pcm_ops = {
+static const struct snd_soc_component_driver atmel_soc_platform = {
 	.open		= atmel_pcm_open,
 	.close		= atmel_pcm_close,
-	.ioctl		= snd_pcm_lib_ioctl,
+	.ioctl		= snd_soc_pcm_lib_ioctl,
 	.hw_params	= atmel_pcm_hw_params,
 	.hw_free	= atmel_pcm_hw_free,
 	.prepare	= atmel_pcm_prepare,
 	.trigger	= atmel_pcm_trigger,
 	.pointer	= atmel_pcm_pointer,
 	.mmap		= atmel_pcm_mmap,
-};
-
-static struct snd_soc_component_driver atmel_soc_platform = {
-	.ops		= &atmel_pcm_ops,
-	.pcm_new	= atmel_pcm_new,
-	.pcm_free	= atmel_pcm_free,
+	.pcm_construct	= atmel_pcm_new,
+	.pcm_destruct	= atmel_pcm_free,
 };
 
 int atmel_pcm_pdc_platform_register(struct device *dev)
diff --git a/sound/soc/au1x/dbdma2.c b/sound/soc/au1x/dbdma2.c
index d56092a5ee11..4553108ec92a 100644
--- a/sound/soc/au1x/dbdma2.c
+++ b/sound/soc/au1x/dbdma2.c
@@ -182,15 +182,15 @@ out:
 	return 0;
 }
 
-static inline struct au1xpsc_audio_dmadata *to_dmadata(struct snd_pcm_substream *ss)
+static inline struct au1xpsc_audio_dmadata *to_dmadata(struct snd_pcm_substream *ss,
+						       struct snd_soc_component *component)
 {
-	struct snd_soc_pcm_runtime *rtd = ss->private_data;
-	struct snd_soc_component *component = snd_soc_rtdcom_lookup(rtd, DRV_NAME);
 	struct au1xpsc_audio_dmadata *pcd = snd_soc_component_get_drvdata(component);
 	return &pcd[ss->stream];
 }
 
-static int au1xpsc_pcm_hw_params(struct snd_pcm_substream *substream,
+static int au1xpsc_pcm_hw_params(struct snd_soc_component *component,
+				 struct snd_pcm_substream *substream,
 				 struct snd_pcm_hw_params *params)
 {
 	struct snd_pcm_runtime *runtime = substream->runtime;
@@ -202,7 +202,7 @@ static int au1xpsc_pcm_hw_params(struct snd_pcm_substream *substream,
 		goto out;
 
 	stype = substream->stream;
-	pcd = to_dmadata(substream);
+	pcd = to_dmadata(substream, component);
 
 	DBG("runtime->dma_area = 0x%08lx dma_addr_t = 0x%08lx dma_size = %zu "
 	    "runtime->min_align %lu\n",
@@ -232,15 +232,17 @@ out:
 	return ret;
 }
 
-static int au1xpsc_pcm_hw_free(struct snd_pcm_substream *substream)
+static int au1xpsc_pcm_hw_free(struct snd_soc_component *component,
+			       struct snd_pcm_substream *substream)
 {
 	snd_pcm_lib_free_pages(substream);
 	return 0;
 }
 
-static int au1xpsc_pcm_prepare(struct snd_pcm_substream *substream)
+static int au1xpsc_pcm_prepare(struct snd_soc_component *component,
+			       struct snd_pcm_substream *substream)
 {
-	struct au1xpsc_audio_dmadata *pcd = to_dmadata(substream);
+	struct au1xpsc_audio_dmadata *pcd = to_dmadata(substream, component);
 
 	au1xxx_dbdma_reset(pcd->ddma_chan);
 
@@ -255,9 +257,10 @@ static int au1xpsc_pcm_prepare(struct snd_pcm_substream *substream)
 	return 0;
 }
 
-static int au1xpsc_pcm_trigger(struct snd_pcm_substream *substream, int cmd)
+static int au1xpsc_pcm_trigger(struct snd_soc_component *component,
+			       struct snd_pcm_substream *substream, int cmd)
 {
-	u32 c = to_dmadata(substream)->ddma_chan;
+	u32 c = to_dmadata(substream, component)->ddma_chan;
 
 	switch (cmd) {
 	case SNDRV_PCM_TRIGGER_START:
@@ -275,14 +278,17 @@ static int au1xpsc_pcm_trigger(struct snd_pcm_substream *substream, int cmd)
 }
 
 static snd_pcm_uframes_t
-au1xpsc_pcm_pointer(struct snd_pcm_substream *substream)
+au1xpsc_pcm_pointer(struct snd_soc_component *component,
+		    struct snd_pcm_substream *substream)
 {
-	return bytes_to_frames(substream->runtime, to_dmadata(substream)->pos);
+	return bytes_to_frames(substream->runtime,
+			       to_dmadata(substream, component)->pos);
 }
 
-static int au1xpsc_pcm_open(struct snd_pcm_substream *substream)
+static int au1xpsc_pcm_open(struct snd_soc_component *component,
+			    struct snd_pcm_substream *substream)
 {
-	struct au1xpsc_audio_dmadata *pcd = to_dmadata(substream);
+	struct au1xpsc_audio_dmadata *pcd = to_dmadata(substream, component);
 	struct snd_soc_pcm_runtime *rtd = substream->private_data;
 	int stype = substream->stream, *dmaids;
 
@@ -296,24 +302,15 @@ static int au1xpsc_pcm_open(struct snd_pcm_substream *substream)
 	return 0;
 }
 
-static int au1xpsc_pcm_close(struct snd_pcm_substream *substream)
+static int au1xpsc_pcm_close(struct snd_soc_component *component,
+			     struct snd_pcm_substream *substream)
 {
-	au1x_pcm_dbdma_free(to_dmadata(substream));
+	au1x_pcm_dbdma_free(to_dmadata(substream, component));
 	return 0;
 }
 
-static const struct snd_pcm_ops au1xpsc_pcm_ops = {
-	.open		= au1xpsc_pcm_open,
-	.close		= au1xpsc_pcm_close,
-	.ioctl		= snd_pcm_lib_ioctl,
-	.hw_params	= au1xpsc_pcm_hw_params,
-	.hw_free	= au1xpsc_pcm_hw_free,
-	.prepare	= au1xpsc_pcm_prepare,
-	.trigger	= au1xpsc_pcm_trigger,
-	.pointer	= au1xpsc_pcm_pointer,
-};
-
-static int au1xpsc_pcm_new(struct snd_soc_pcm_runtime *rtd)
+static int au1xpsc_pcm_new(struct snd_soc_component *component,
+			   struct snd_soc_pcm_runtime *rtd)
 {
 	struct snd_card *card = rtd->card->snd_card;
 	struct snd_pcm *pcm = rtd->pcm;
@@ -327,8 +324,15 @@ static int au1xpsc_pcm_new(struct snd_soc_pcm_runtime *rtd)
 /* au1xpsc audio platform */
 static struct snd_soc_component_driver au1xpsc_soc_component = {
 	.name		= DRV_NAME,
-	.ops		= &au1xpsc_pcm_ops,
-	.pcm_new	= au1xpsc_pcm_new,
+	.open		= au1xpsc_pcm_open,
+	.close		= au1xpsc_pcm_close,
+	.ioctl		= snd_soc_pcm_lib_ioctl,
+	.hw_params	= au1xpsc_pcm_hw_params,
+	.hw_free	= au1xpsc_pcm_hw_free,
+	.prepare	= au1xpsc_pcm_prepare,
+	.trigger	= au1xpsc_pcm_trigger,
+	.pointer	= au1xpsc_pcm_pointer,
+	.pcm_construct	= au1xpsc_pcm_new,
 };
 
 static int au1xpsc_pcm_drvprobe(struct platform_device *pdev)
diff --git a/sound/soc/au1x/dma.c b/sound/soc/au1x/dma.c
index 1e98cc4f9e27..054dfda89d3e 100644
--- a/sound/soc/au1x/dma.c
+++ b/sound/soc/au1x/dma.c
@@ -174,22 +174,23 @@ static const struct snd_pcm_hardware alchemy_pcm_hardware = {
 	.fifo_size	  = 16,
 };
 
-static inline struct alchemy_pcm_ctx *ss_to_ctx(struct snd_pcm_substream *ss)
+static inline struct alchemy_pcm_ctx *ss_to_ctx(struct snd_pcm_substream *ss,
+						struct snd_soc_component *component)
 {
-	struct snd_soc_pcm_runtime *rtd = ss->private_data;
-	struct snd_soc_component *component = snd_soc_rtdcom_lookup(rtd, DRV_NAME);
 	return snd_soc_component_get_drvdata(component);
 }
 
-static inline struct audio_stream *ss_to_as(struct snd_pcm_substream *ss)
+static inline struct audio_stream *ss_to_as(struct snd_pcm_substream *ss,
+					    struct snd_soc_component *component)
 {
-	struct alchemy_pcm_ctx *ctx = ss_to_ctx(ss);
+	struct alchemy_pcm_ctx *ctx = ss_to_ctx(ss, component);
 	return &(ctx->stream[ss->stream]);
 }
 
-static int alchemy_pcm_open(struct snd_pcm_substream *substream)
+static int alchemy_pcm_open(struct snd_soc_component *component,
+			    struct snd_pcm_substream *substream)
 {
-	struct alchemy_pcm_ctx *ctx = ss_to_ctx(substream);
+	struct alchemy_pcm_ctx *ctx = ss_to_ctx(substream, component);
 	struct snd_soc_pcm_runtime *rtd = substream->private_data;
 	int *dmaids, s = substream->stream;
 	char *name;
@@ -213,9 +214,10 @@ static int alchemy_pcm_open(struct snd_pcm_substream *substream)
 	return 0;
 }
 
-static int alchemy_pcm_close(struct snd_pcm_substream *substream)
+static int alchemy_pcm_close(struct snd_soc_component *component,
+			     struct snd_pcm_substream *substream)
 {
-	struct alchemy_pcm_ctx *ctx = ss_to_ctx(substream);
+	struct alchemy_pcm_ctx *ctx = ss_to_ctx(substream, component);
 	int stype = substream->stream;
 
 	ctx->stream[stype].substream = NULL;
@@ -224,10 +226,11 @@ static int alchemy_pcm_close(struct snd_pcm_substream *substream)
 	return 0;
 }
 
-static int alchemy_pcm_hw_params(struct snd_pcm_substream *substream,
+static int alchemy_pcm_hw_params(struct snd_soc_component *component,
+				 struct snd_pcm_substream *substream,
 				 struct snd_pcm_hw_params *hw_params)
 {
-	struct audio_stream *stream = ss_to_as(substream);
+	struct audio_stream *stream = ss_to_as(substream, component);
 	int err;
 
 	err = snd_pcm_lib_malloc_pages(substream,
@@ -243,16 +246,18 @@ static int alchemy_pcm_hw_params(struct snd_pcm_substream *substream,
 	return err;
 }
 
-static int alchemy_pcm_hw_free(struct snd_pcm_substream *substream)
+static int alchemy_pcm_hw_free(struct snd_soc_component *component,
+			       struct snd_pcm_substream *substream)
 {
-	struct audio_stream *stream = ss_to_as(substream);
+	struct audio_stream *stream = ss_to_as(substream, component);
 	au1000_release_dma_link(stream);
 	return snd_pcm_lib_free_pages(substream);
 }
 
-static int alchemy_pcm_trigger(struct snd_pcm_substream *substream, int cmd)
+static int alchemy_pcm_trigger(struct snd_soc_component *component,
+			       struct snd_pcm_substream *substream, int cmd)
 {
-	struct audio_stream *stream = ss_to_as(substream);
+	struct audio_stream *stream = ss_to_as(substream, component);
 	int err = 0;
 
 	switch (cmd) {
@@ -269,9 +274,10 @@ static int alchemy_pcm_trigger(struct snd_pcm_substream *substream, int cmd)
 	return err;
 }
 
-static snd_pcm_uframes_t alchemy_pcm_pointer(struct snd_pcm_substream *ss)
+static snd_pcm_uframes_t alchemy_pcm_pointer(struct snd_soc_component *component,
+					     struct snd_pcm_substream *ss)
 {
-	struct audio_stream *stream = ss_to_as(ss);
+	struct audio_stream *stream = ss_to_as(ss, component);
 	long location;
 
 	location = get_dma_residue(stream->dma);
@@ -281,30 +287,27 @@ static snd_pcm_uframes_t alchemy_pcm_pointer(struct snd_pcm_substream *ss)
 	return bytes_to_frames(ss->runtime, location);
 }
 
-static const struct snd_pcm_ops alchemy_pcm_ops = {
-	.open			= alchemy_pcm_open,
-	.close			= alchemy_pcm_close,
-	.ioctl			= snd_pcm_lib_ioctl,
-	.hw_params	        = alchemy_pcm_hw_params,
-	.hw_free	        = alchemy_pcm_hw_free,
-	.trigger		= alchemy_pcm_trigger,
-	.pointer		= alchemy_pcm_pointer,
-};
-
-static int alchemy_pcm_new(struct snd_soc_pcm_runtime *rtd)
+static int alchemy_pcm_new(struct snd_soc_component *component,
+			   struct snd_soc_pcm_runtime *rtd)
 {
 	struct snd_pcm *pcm = rtd->pcm;
 
 	snd_pcm_lib_preallocate_pages_for_all(pcm, SNDRV_DMA_TYPE_CONTINUOUS,
-		snd_dma_continuous_data(GFP_KERNEL), 65536, (4096 * 1024) - 1);
+					      NULL, 65536, (4096 * 1024) - 1);
 
 	return 0;
 }
 
 static struct snd_soc_component_driver alchemy_pcm_soc_component = {
 	.name		= DRV_NAME,
-	.ops		= &alchemy_pcm_ops,
-	.pcm_new	= alchemy_pcm_new,
+	.open		= alchemy_pcm_open,
+	.close		= alchemy_pcm_close,
+	.ioctl		= snd_soc_pcm_lib_ioctl,
+	.hw_params	= alchemy_pcm_hw_params,
+	.hw_free	= alchemy_pcm_hw_free,
+	.trigger	= alchemy_pcm_trigger,
+	.pointer	= alchemy_pcm_pointer,
+	.pcm_construct	= alchemy_pcm_new,
 };
 
 static int alchemy_pcm_drvprobe(struct platform_device *pdev)
diff --git a/sound/soc/bcm/cygnus-pcm.c b/sound/soc/bcm/cygnus-pcm.c
index 8966b02844dc..c65408085c1d 100644
--- a/sound/soc/bcm/cygnus-pcm.c
+++ b/sound/soc/bcm/cygnus-pcm.c
@@ -376,7 +376,8 @@ static void disable_intr(struct snd_pcm_substream *substream)
 
 }
 
-static int cygnus_pcm_trigger(struct snd_pcm_substream *substream, int cmd)
+static int cygnus_pcm_trigger(struct snd_soc_component *component,
+			      struct snd_pcm_substream *substream, int cmd)
 {
 	int ret = 0;
 
@@ -577,7 +578,8 @@ static irqreturn_t cygnus_dma_irq(int irq, void *data)
 	return IRQ_HANDLED;
 }
 
-static int cygnus_pcm_open(struct snd_pcm_substream *substream)
+static int cygnus_pcm_open(struct snd_soc_component *component,
+			   struct snd_pcm_substream *substream)
 {
 	struct snd_soc_pcm_runtime *rtd = substream->private_data;
 	struct snd_pcm_runtime *runtime = substream->runtime;
@@ -613,7 +615,8 @@ static int cygnus_pcm_open(struct snd_pcm_substream *substream)
 	return 0;
 }
 
-static int cygnus_pcm_close(struct snd_pcm_substream *substream)
+static int cygnus_pcm_close(struct snd_soc_component *component,
+			    struct snd_pcm_substream *substream)
 {
 	struct snd_soc_pcm_runtime *rtd = substream->private_data;
 	struct cygnus_aio_port *aio;
@@ -633,8 +636,9 @@ static int cygnus_pcm_close(struct snd_pcm_substream *substream)
 	return 0;
 }
 
-static int cygnus_pcm_hw_params(struct snd_pcm_substream *substream,
-	struct snd_pcm_hw_params *params)
+static int cygnus_pcm_hw_params(struct snd_soc_component *component,
+				struct snd_pcm_substream *substream,
+				struct snd_pcm_hw_params *params)
 {
 	struct snd_soc_pcm_runtime *rtd = substream->private_data;
 	struct snd_pcm_runtime *runtime = substream->runtime;
@@ -649,7 +653,8 @@ static int cygnus_pcm_hw_params(struct snd_pcm_substream *substream,
 	return 0;
 }
 
-static int cygnus_pcm_hw_free(struct snd_pcm_substream *substream)
+static int cygnus_pcm_hw_free(struct snd_soc_component *component,
+			      struct snd_pcm_substream *substream)
 {
 	struct snd_soc_pcm_runtime *rtd = substream->private_data;
 	struct cygnus_aio_port *aio;
@@ -661,7 +666,8 @@ static int cygnus_pcm_hw_free(struct snd_pcm_substream *substream)
 	return 0;
 }
 
-static int cygnus_pcm_prepare(struct snd_pcm_substream *substream)
+static int cygnus_pcm_prepare(struct snd_soc_component *component,
+			      struct snd_pcm_substream *substream)
 {
 	struct snd_soc_pcm_runtime *rtd = substream->private_data;
 	struct snd_pcm_runtime *runtime = substream->runtime;
@@ -694,7 +700,8 @@ static int cygnus_pcm_prepare(struct snd_pcm_substream *substream)
 	return 0;
 }
 
-static snd_pcm_uframes_t cygnus_pcm_pointer(struct snd_pcm_substream *substream)
+static snd_pcm_uframes_t cygnus_pcm_pointer(struct snd_soc_component *component,
+					    struct snd_pcm_substream *substream)
 {
 	struct cygnus_aio_port *aio;
 	unsigned int res = 0, cur = 0, base = 0;
@@ -750,19 +757,8 @@ static int cygnus_pcm_preallocate_dma_buffer(struct snd_pcm *pcm, int stream)
 	return 0;
 }
 
-
-static const struct snd_pcm_ops cygnus_pcm_ops = {
-	.open		= cygnus_pcm_open,
-	.close		= cygnus_pcm_close,
-	.ioctl		= snd_pcm_lib_ioctl,
-	.hw_params	= cygnus_pcm_hw_params,
-	.hw_free	= cygnus_pcm_hw_free,
-	.prepare	= cygnus_pcm_prepare,
-	.trigger	= cygnus_pcm_trigger,
-	.pointer	= cygnus_pcm_pointer,
-};
-
-static void cygnus_dma_free_dma_buffers(struct snd_pcm *pcm)
+static void cygnus_dma_free_dma_buffers(struct snd_soc_component *component,
+					struct snd_pcm *pcm)
 {
 	struct snd_pcm_substream *substream;
 	struct snd_dma_buffer *buf;
@@ -788,7 +784,8 @@ static void cygnus_dma_free_dma_buffers(struct snd_pcm *pcm)
 	}
 }
 
-static int cygnus_dma_new(struct snd_soc_pcm_runtime *rtd)
+static int cygnus_dma_new(struct snd_soc_component *component,
+			  struct snd_soc_pcm_runtime *rtd)
 {
 	struct snd_card *card = rtd->card->snd_card;
 	struct snd_pcm *pcm = rtd->pcm;
@@ -810,7 +807,7 @@ static int cygnus_dma_new(struct snd_soc_pcm_runtime *rtd)
 		ret = cygnus_pcm_preallocate_dma_buffer(pcm,
 				SNDRV_PCM_STREAM_CAPTURE);
 		if (ret) {
-			cygnus_dma_free_dma_buffers(pcm);
+			cygnus_dma_free_dma_buffers(component, pcm);
 			return ret;
 		}
 	}
@@ -819,9 +816,16 @@ static int cygnus_dma_new(struct snd_soc_pcm_runtime *rtd)
 }
 
 static struct snd_soc_component_driver cygnus_soc_platform = {
-	.ops		= &cygnus_pcm_ops,
-	.pcm_new	= cygnus_dma_new,
-	.pcm_free	= cygnus_dma_free_dma_buffers,
+	.open		= cygnus_pcm_open,
+	.close		= cygnus_pcm_close,
+	.ioctl		= snd_soc_pcm_lib_ioctl,
+	.hw_params	= cygnus_pcm_hw_params,
+	.hw_free	= cygnus_pcm_hw_free,
+	.prepare	= cygnus_pcm_prepare,
+	.trigger	= cygnus_pcm_trigger,
+	.pointer	= cygnus_pcm_pointer,
+	.pcm_construct	= cygnus_dma_new,
+	.pcm_destruct	= cygnus_dma_free_dma_buffers,
 };
 
 int cygnus_soc_platform_register(struct device *dev,
diff --git a/sound/soc/cirrus/Kconfig b/sound/soc/cirrus/Kconfig
index 2333efac758a..8039a8febefa 100644
--- a/sound/soc/cirrus/Kconfig
+++ b/sound/soc/cirrus/Kconfig
@@ -33,13 +33,13 @@ config SND_EP93XX_SOC_AC97
 	select SND_SOC_AC97_BUS
 
 config SND_EP93XX_SOC_SNAPPERCL15
-        tristate "SoC Audio support for Bluewater Systems Snapper CL15 module"
-        depends on SND_EP93XX_SOC && MACH_SNAPPER_CL15 && I2C
-        select SND_EP93XX_SOC_I2S
-        select SND_SOC_TLV320AIC23_I2C
-        help
-          Say Y or M here if you want to add support for I2S audio on the
-          Bluewater Systems Snapper CL15 module.
+	tristate "SoC Audio support for Bluewater Systems Snapper CL15 module"
+	depends on SND_EP93XX_SOC && MACH_SNAPPER_CL15 && I2C
+	select SND_EP93XX_SOC_I2S
+	select SND_SOC_TLV320AIC23_I2C
+	help
+	  Say Y or M here if you want to add support for I2S audio on the
+	  Bluewater Systems Snapper CL15 module.
 
 config SND_EP93XX_SOC_SIMONE
 	tristate "SoC Audio support for Simplemachines Sim.One board"
diff --git a/sound/soc/codecs/Kconfig b/sound/soc/codecs/Kconfig
index 229cc89f8c5a..4abf37b5083f 100644
--- a/sound/soc/codecs/Kconfig
+++ b/sound/soc/codecs/Kconfig
@@ -34,6 +34,8 @@ config SND_SOC_ALL_CODECS
 	select SND_SOC_ADAU1977_I2C if I2C
 	select SND_SOC_ADAU1701 if I2C
 	select SND_SOC_ADAU7002
+	select SND_SOC_ADAU7118_I2C if I2C
+	select SND_SOC_ADAU7118_HW
 	select SND_SOC_ADS117X
 	select SND_SOC_AK4104 if SPI_MASTER
 	select SND_SOC_AK4118 if I2C
@@ -179,6 +181,8 @@ config SND_SOC_ALL_CODECS
 	select SND_SOC_STAC9766 if SND_SOC_AC97_BUS
 	select SND_SOC_STI_SAS
 	select SND_SOC_TAS2552 if I2C
+	select SND_SOC_TAS2562 if I2C
+	select SND_SOC_TAS2770 if I2C
 	select SND_SOC_TAS5086 if I2C
 	select SND_SOC_TAS571X if I2C
 	select SND_SOC_TAS5720 if I2C
@@ -257,16 +261,16 @@ config SND_SOC_ALL_CODECS
 	select SND_SOC_WM9705 if (SND_SOC_AC97_BUS || SND_SOC_AC97_BUS_NEW)
 	select SND_SOC_WM9712 if (SND_SOC_AC97_BUS || SND_SOC_AC97_BUS_NEW)
 	select SND_SOC_WM9713 if (SND_SOC_AC97_BUS || SND_SOC_AC97_BUS_NEW)
-        help
-          Normally ASoC codec drivers are only built if a machine driver which
-          uses them is also built since they are only usable with a machine
-          driver.  Selecting this option will allow these drivers to be built
-          without an explicit machine driver for test and development purposes.
+	help
+	  Normally ASoC codec drivers are only built if a machine driver which
+	  uses them is also built since they are only usable with a machine
+	  driver.  Selecting this option will allow these drivers to be built
+	  without an explicit machine driver for test and development purposes.
 
 	  Support for the bus types used to access the codecs to be built must
 	  be selected separately.
 
-          If unsure select "N".
+	  If unsure select "N".
 
 config SND_SOC_88PM860X
 	tristate
@@ -395,6 +399,33 @@ config SND_SOC_ADAU1977_I2C
 config SND_SOC_ADAU7002
 	tristate "Analog Devices ADAU7002 Stereo PDM-to-I2S/TDM Converter"
 
+config SND_SOC_ADAU7118
+	tristate
+
+config SND_SOC_ADAU7118_HW
+	tristate "Analog Devices ADAU7118 8 Channel PDM-to-I2S/TDM Converter - HW Mode"
+	select SND_SOC_ADAU7118
+	help
+	  Enable support for the Analog Devices ADAU7118 8 Channel PDM-to-I2S/TDM
+	  Converter. In this mode, the device works in standalone mode which
+	  means that there is no bus to comunicate with it. Stereo mode is not
+	  supported in this mode.
+
+	  To compile this driver as a module, choose M here: the module
+	  will be called snd-soc-adau7118-hw.
+
+config SND_SOC_ADAU7118_I2C
+	tristate "Analog Devices ADAU7118 8 Channel PDM-to-I2S/TDM Converter - I2C"
+	depends on I2C
+	select SND_SOC_ADAU7118
+	select REGMAP_I2C
+	help
+	  Enable support for the Analog Devices ADAU7118 8 Channel PDM-to-I2S/TDM
+	  Converter over I2C. This gives full support over the device.
+
+	  To compile this driver as a module, choose M here: the module
+	  will be called snd-soc-adau7118-i2c.
+
 config SND_SOC_ADAV80X
 	tristate
 
@@ -478,6 +509,8 @@ config SND_SOC_CQ0093VC
 config SND_SOC_CROS_EC_CODEC
 	tristate "codec driver for ChromeOS EC"
 	depends on CROS_EC
+	select CRYPTO
+	select CRYPTO_SHA256
 	help
 	  If you say yes here you will get support for the
 	  ChromeOS Embedded Controller's Audio Codec.
@@ -570,8 +603,8 @@ config SND_SOC_CS42XX8_I2C
 
 # Cirrus Logic CS43130 HiFi DAC
 config SND_SOC_CS43130
-        tristate "Cirrus Logic CS43130 CODEC"
-        depends on I2C
+	tristate "Cirrus Logic CS43130 CODEC"
+	depends on I2C
 
 config SND_SOC_CS4341
 	tristate "Cirrus Logic CS4341 CODEC"
@@ -643,19 +676,20 @@ config SND_SOC_L3
        tristate
 
 config SND_SOC_DA7210
-        tristate
+	tristate
 
 config SND_SOC_DA7213
-        tristate
+	tristate "Dialog DA7213 CODEC"
+	depends on I2C
 
 config SND_SOC_DA7218
 	tristate
 
 config SND_SOC_DA7219
-        tristate
+	tristate
 
 config SND_SOC_DA732X
-        tristate
+	tristate
 
 config SND_SOC_DA9055
 	tristate
@@ -717,7 +751,7 @@ config SND_SOC_INNO_RK3036
 	select REGMAP_MMIO
 
 config SND_SOC_ISABELLE
-        tristate
+	tristate
 
 config SND_SOC_LM49453
 	tristate
@@ -988,7 +1022,7 @@ config SND_SOC_RT5640
 	tristate
 
 config SND_SOC_RT5645
-        tristate
+	tristate
 
 config SND_SOC_RT5651
 	tristate
@@ -1104,6 +1138,14 @@ config SND_SOC_TAS2552
 	tristate "Texas Instruments TAS2552 Mono Audio amplifier"
 	depends on I2C
 
+config SND_SOC_TAS2562
+	tristate "Texas Instruments TAS2562 Mono Audio amplifier"
+	depends on I2C
+
+config SND_SOC_TAS2770
+	tristate "Texas Instruments TAS2770 speaker amplifier"
+	depends on I2C
+
 config SND_SOC_TAS5086
 	tristate "Texas Instruments TAS5086 speaker amplifier"
 	depends on I2C
@@ -1220,7 +1262,7 @@ config SND_SOC_UDA134X
        tristate
 
 config SND_SOC_UDA1380
-        tristate
+	tristate
 	depends on I2C
 
 config SND_SOC_WCD9335
@@ -1348,7 +1390,7 @@ config SND_SOC_WM8904
 	depends on I2C
 
 config SND_SOC_WM8940
-        tristate
+	tristate
 
 config SND_SOC_WM8955
 	tristate
diff --git a/sound/soc/codecs/Makefile b/sound/soc/codecs/Makefile
index c498373dcc5f..ddfd07071925 100644
--- a/sound/soc/codecs/Makefile
+++ b/sound/soc/codecs/Makefile
@@ -22,6 +22,9 @@ snd-soc-adau1977-objs := adau1977.o
 snd-soc-adau1977-spi-objs := adau1977-spi.o
 snd-soc-adau1977-i2c-objs := adau1977-i2c.o
 snd-soc-adau7002-objs := adau7002.o
+snd-soc-adau7118-objs := adau7118.o
+snd-soc-adau7118-i2c-objs := adau7118-i2c.o
+snd-soc-adau7118-hw-objs := adau7118-hw.o
 snd-soc-adav80x-objs := adav80x.o
 snd-soc-adav801-objs := adav801.o
 snd-soc-adav803-objs := adav803.o
@@ -196,6 +199,7 @@ snd-soc-tas571x-objs := tas571x.o
 snd-soc-tas5720-objs := tas5720.o
 snd-soc-tas6424-objs := tas6424.o
 snd-soc-tda7419-objs := tda7419.o
+snd-soc-tas2770-objs := tas2770.o
 snd-soc-tfa9879-objs := tfa9879.o
 snd-soc-tlv320aic23-objs := tlv320aic23.o
 snd-soc-tlv320aic23-i2c-objs := tlv320aic23-i2c.o
@@ -280,6 +284,7 @@ snd-soc-max98504-objs := max98504.o
 snd-soc-simple-amplifier-objs := simple-amplifier.o
 snd-soc-tpa6130a2-objs := tpa6130a2.o
 snd-soc-tas2552-objs := tas2552.o
+snd-soc-tas2562-objs := tas2562.o
 
 obj-$(CONFIG_SND_SOC_88PM860X)	+= snd-soc-88pm860x.o
 obj-$(CONFIG_SND_SOC_AB8500_CODEC)	+= snd-soc-ab8500-codec.o
@@ -304,6 +309,9 @@ obj-$(CONFIG_SND_SOC_ADAU1977)		+= snd-soc-adau1977.o
 obj-$(CONFIG_SND_SOC_ADAU1977_SPI)	+= snd-soc-adau1977-spi.o
 obj-$(CONFIG_SND_SOC_ADAU1977_I2C)	+= snd-soc-adau1977-i2c.o
 obj-$(CONFIG_SND_SOC_ADAU7002)	+= snd-soc-adau7002.o
+obj-$(CONFIG_SND_SOC_ADAU7118)	+= snd-soc-adau7118.o
+obj-$(CONFIG_SND_SOC_ADAU7118_I2C)	+= snd-soc-adau7118-i2c.o
+obj-$(CONFIG_SND_SOC_ADAU7118_HW)	+= snd-soc-adau7118-hw.o
 obj-$(CONFIG_SND_SOC_ADAV80X)  += snd-soc-adav80x.o
 obj-$(CONFIG_SND_SOC_ADAV801)  += snd-soc-adav801.o
 obj-$(CONFIG_SND_SOC_ADAV803)  += snd-soc-adav803.o
@@ -474,11 +482,13 @@ obj-$(CONFIG_SND_SOC_STA529)   += snd-soc-sta529.o
 obj-$(CONFIG_SND_SOC_STAC9766)	+= snd-soc-stac9766.o
 obj-$(CONFIG_SND_SOC_STI_SAS)	+= snd-soc-sti-sas.o
 obj-$(CONFIG_SND_SOC_TAS2552)	+= snd-soc-tas2552.o
+obj-$(CONFIG_SND_SOC_TAS2562)	+= snd-soc-tas2562.o
 obj-$(CONFIG_SND_SOC_TAS5086)	+= snd-soc-tas5086.o
 obj-$(CONFIG_SND_SOC_TAS571X)	+= snd-soc-tas571x.o
 obj-$(CONFIG_SND_SOC_TAS5720)	+= snd-soc-tas5720.o
 obj-$(CONFIG_SND_SOC_TAS6424)	+= snd-soc-tas6424.o
 obj-$(CONFIG_SND_SOC_TDA7419)	+= snd-soc-tda7419.o
+obj-$(CONFIG_SND_SOC_TAS2770) += snd-soc-tas2770.o
 obj-$(CONFIG_SND_SOC_TFA9879)	+= snd-soc-tfa9879.o
 obj-$(CONFIG_SND_SOC_TLV320AIC23)	+= snd-soc-tlv320aic23.o
 obj-$(CONFIG_SND_SOC_TLV320AIC23_I2C)	+= snd-soc-tlv320aic23-i2c.o
diff --git a/sound/soc/codecs/adau1761.c b/sound/soc/codecs/adau1761.c
index 977f5a63be3f..5ca9b744b7d8 100644
--- a/sound/soc/codecs/adau1761.c
+++ b/sound/soc/codecs/adau1761.c
@@ -28,6 +28,10 @@
 #define ADAU1761_REC_MIXER_RIGHT1	0x400d
 #define ADAU1761_LEFT_DIFF_INPUT_VOL	0x400e
 #define ADAU1761_RIGHT_DIFF_INPUT_VOL	0x400f
+#define ADAU1761_ALC_CTRL0		0x4011
+#define ADAU1761_ALC_CTRL1		0x4012
+#define ADAU1761_ALC_CTRL2		0x4013
+#define ADAU1761_ALC_CTRL3		0x4014
 #define ADAU1761_PLAY_LR_MIXER_LEFT	0x4020
 #define ADAU1761_PLAY_MIXER_LEFT0	0x401c
 #define ADAU1761_PLAY_MIXER_LEFT1	0x401d
@@ -71,6 +75,10 @@ static const struct reg_default adau1761_reg_defaults[] = {
 	{ ADAU1761_REC_MIXER_RIGHT0,		0x00 },
 	{ ADAU1761_REC_MIXER_RIGHT1,		0x00 },
 	{ ADAU1761_LEFT_DIFF_INPUT_VOL,		0x00 },
+	{ ADAU1761_ALC_CTRL0,			0x00 },
+	{ ADAU1761_ALC_CTRL1,			0x00 },
+	{ ADAU1761_ALC_CTRL2,			0x00 },
+	{ ADAU1761_ALC_CTRL3,			0x00 },
 	{ ADAU1761_RIGHT_DIFF_INPUT_VOL,	0x00 },
 	{ ADAU1761_PLAY_LR_MIXER_LEFT,		0x00 },
 	{ ADAU1761_PLAY_MIXER_LEFT0,		0x00 },
@@ -121,6 +129,10 @@ static const DECLARE_TLV_DB_SCALE(adau1761_sidetone_tlv, -1800, 300, 1);
 static const DECLARE_TLV_DB_SCALE(adau1761_boost_tlv, -600, 600, 1);
 static const DECLARE_TLV_DB_SCALE(adau1761_pga_boost_tlv, -2000, 2000, 1);
 
+static const DECLARE_TLV_DB_SCALE(adau1761_alc_max_gain_tlv, -1200, 600, 0);
+static const DECLARE_TLV_DB_SCALE(adau1761_alc_target_tlv, -2850, 150, 0);
+static const DECLARE_TLV_DB_SCALE(adau1761_alc_ng_threshold_tlv, -7650, 150, 0);
+
 static const unsigned int adau1761_bias_select_values[] = {
 	0, 2, 3,
 };
@@ -147,6 +159,103 @@ static SOC_VALUE_ENUM_SINGLE_DECL(adau1761_capture_bias_enum,
 		ADAU17X1_REC_POWER_MGMT, 1, 0x3, adau1761_bias_select_text,
 		adau1761_bias_select_values);
 
+static const unsigned int adau1761_pga_slew_time_values[] = {
+	3, 0, 1, 2,
+};
+
+static const char * const adau1761_pga_slew_time_text[] = {
+	"Off",
+	"24 ms",
+	"48 ms",
+	"96 ms",
+};
+
+static const char * const adau1761_alc_function_text[] = {
+	"Off",
+	"Right",
+	"Left",
+	"Stereo",
+	"DSP control",
+};
+
+static const char * const adau1761_alc_hold_time_text[] = {
+	"2.67 ms",
+	"5.34 ms",
+	"10.68 ms",
+	"21.36 ms",
+	"42.72 ms",
+	"85.44 ms",
+	"170.88 ms",
+	"341.76 ms",
+	"683.52 ms",
+	"1367 ms",
+	"2734.1 ms",
+	"5468.2 ms",
+	"10936 ms",
+	"21873 ms",
+	"43745 ms",
+	"87491 ms",
+};
+
+static const char * const adau1761_alc_attack_time_text[] = {
+	"6 ms",
+	"12 ms",
+	"24 ms",
+	"48 ms",
+	"96 ms",
+	"192 ms",
+	"384 ms",
+	"768 ms",
+	"1540 ms",
+	"3070 ms",
+	"6140 ms",
+	"12290 ms",
+	"24580 ms",
+	"49150 ms",
+	"98300 ms",
+	"196610 ms",
+};
+
+static const char * const adau1761_alc_decay_time_text[] = {
+	"24 ms",
+	"48 ms",
+	"96 ms",
+	"192 ms",
+	"384 ms",
+	"768 ms",
+	"15400 ms",
+	"30700 ms",
+	"61400 ms",
+	"12290 ms",
+	"24580 ms",
+	"49150 ms",
+	"98300 ms",
+	"196610 ms",
+	"393220 ms",
+	"786430 ms",
+};
+
+static const char * const adau1761_alc_ng_type_text[] = {
+	"Hold",
+	"Mute",
+	"Fade",
+	"Fade + Mute",
+};
+
+static SOC_VALUE_ENUM_SINGLE_DECL(adau1761_pga_slew_time_enum,
+		ADAU1761_ALC_CTRL0, 6, 0x3, adau1761_pga_slew_time_text,
+		adau1761_pga_slew_time_values);
+static SOC_ENUM_SINGLE_DECL(adau1761_alc_function_enum,
+		ADAU1761_ALC_CTRL0, 0, adau1761_alc_function_text);
+static SOC_ENUM_SINGLE_DECL(adau1761_alc_hold_time_enum,
+		ADAU1761_ALC_CTRL1, 4, adau1761_alc_hold_time_text);
+static SOC_ENUM_SINGLE_DECL(adau1761_alc_attack_time_enum,
+		ADAU1761_ALC_CTRL2, 4, adau1761_alc_attack_time_text);
+static SOC_ENUM_SINGLE_DECL(adau1761_alc_decay_time_enum,
+		ADAU1761_ALC_CTRL2, 0, adau1761_alc_decay_time_text);
+static SOC_ENUM_SINGLE_DECL(adau1761_alc_ng_type_enum,
+		ADAU1761_ALC_CTRL3, 6, adau1761_alc_ng_type_text);
+
 static const struct snd_kcontrol_new adau1761_jack_detect_controls[] = {
 	SOC_SINGLE("Speaker Auto-mute Switch", ADAU1761_DIGMIC_JACKDETECT,
 		4, 1, 0),
@@ -161,6 +270,22 @@ static const struct snd_kcontrol_new adau1761_differential_mode_controls[] = {
 
 	SOC_DOUBLE_R_TLV("PGA Boost Capture Volume", ADAU1761_REC_MIXER_LEFT1,
 		ADAU1761_REC_MIXER_RIGHT1, 3, 2, 0, adau1761_pga_boost_tlv),
+
+	SOC_ENUM("PGA Capture Slew Time", adau1761_pga_slew_time_enum),
+
+	SOC_SINGLE_TLV("ALC Capture Max Gain Volume", ADAU1761_ALC_CTRL0,
+		3, 7, 0, adau1761_alc_max_gain_tlv),
+	SOC_ENUM("ALC Capture Function", adau1761_alc_function_enum),
+	SOC_ENUM("ALC Capture Hold Time", adau1761_alc_hold_time_enum),
+	SOC_SINGLE_TLV("ALC Capture Target Volume", ADAU1761_ALC_CTRL1,
+		0, 15, 0, adau1761_alc_target_tlv),
+	SOC_ENUM("ALC Capture Attack Time", adau1761_alc_decay_time_enum),
+	SOC_ENUM("ALC Capture Decay Time", adau1761_alc_attack_time_enum),
+	SOC_ENUM("ALC Capture Noise Gate Type", adau1761_alc_ng_type_enum),
+	SOC_SINGLE("ALC Capture Noise Gate Switch",
+		ADAU1761_ALC_CTRL3, 5, 1, 0),
+	SOC_SINGLE_TLV("ALC Capture Noise Gate Threshold Volume",
+		ADAU1761_ALC_CTRL3, 0, 31, 0, adau1761_alc_ng_threshold_tlv),
 };
 
 static const struct snd_kcontrol_new adau1761_single_mode_controls[] = {
@@ -632,6 +757,10 @@ static bool adau1761_readable_register(struct device *dev, unsigned int reg)
 	case ADAU1761_DEJITTER:
 	case ADAU1761_CLK_ENABLE0:
 	case ADAU1761_CLK_ENABLE1:
+	case ADAU1761_ALC_CTRL0:
+	case ADAU1761_ALC_CTRL1:
+	case ADAU1761_ALC_CTRL2:
+	case ADAU1761_ALC_CTRL3:
 		return true;
 	default:
 		break;
diff --git a/sound/soc/codecs/adau7118-hw.c b/sound/soc/codecs/adau7118-hw.c
new file mode 100644
index 000000000000..45a5d2dcc0f2
--- /dev/null
+++ b/sound/soc/codecs/adau7118-hw.c
@@ -0,0 +1,43 @@
+// SPDX-License-Identifier: GPL-2.0
+//
+// Analog Devices ADAU7118 8 channel PDM-to-I2S/TDM Converter Standalone Hw
+// driver
+//
+// Copyright 2019 Analog Devices Inc.
+
+#include <linux/module.h>
+#include <linux/mod_devicetable.h>
+#include <linux/platform_device.h>
+
+#include "adau7118.h"
+
+static int adau7118_probe_hw(struct platform_device *pdev)
+{
+	return adau7118_probe(&pdev->dev, NULL, true);
+}
+
+static const struct of_device_id adau7118_of_match[] = {
+	{ .compatible = "adi,adau7118" },
+	{}
+};
+MODULE_DEVICE_TABLE(of, adau7118_of_match);
+
+static const struct platform_device_id adau7118_id[] = {
+	{ .name	= "adau7118" },
+	{ }
+};
+MODULE_DEVICE_TABLE(platform, adau7118_id);
+
+static struct platform_driver adau7118_driver_hw = {
+	.driver = {
+		.name = "adau7118",
+		.of_match_table = adau7118_of_match,
+	},
+	.probe = adau7118_probe_hw,
+	.id_table = adau7118_id,
+};
+module_platform_driver(adau7118_driver_hw);
+
+MODULE_AUTHOR("Nuno Sa <nuno.sa@analog.com>");
+MODULE_DESCRIPTION("ADAU7118 8 channel PDM-to-I2S/TDM Converter driver for standalone hw mode");
+MODULE_LICENSE("GPL");
diff --git a/sound/soc/codecs/adau7118-i2c.c b/sound/soc/codecs/adau7118-i2c.c
new file mode 100644
index 000000000000..a8211362fe82
--- /dev/null
+++ b/sound/soc/codecs/adau7118-i2c.c
@@ -0,0 +1,82 @@
+// SPDX-License-Identifier: GPL-2.0
+//
+// Analog Devices ADAU7118 8 channel PDM-to-I2S/TDM Converter driver over I2C
+//
+// Copyright 2019 Analog Devices Inc.
+
+#include <linux/i2c.h>
+#include <linux/module.h>
+#include <linux/regmap.h>
+
+#include "adau7118.h"
+
+static const struct reg_default adau7118_reg_defaults[] = {
+	{ ADAU7118_REG_VENDOR_ID, 0x41 },
+	{ ADAU7118_REG_DEVICE_ID1, 0x71 },
+	{ ADAU7118_REG_DEVICE_ID2, 0x18 },
+	{ ADAU7118_REG_REVISION_ID, 0x00 },
+	{ ADAU7118_REG_ENABLES, 0x3F },
+	{ ADAU7118_REG_DEC_RATIO_CLK_MAP, 0xC0 },
+	{ ADAU7118_REG_HPF_CONTROL, 0xD0 },
+	{ ADAU7118_REG_SPT_CTRL1, 0x41 },
+	{ ADAU7118_REG_SPT_CTRL2, 0x00 },
+	{ ADAU7118_REG_SPT_CX(0), 0x01 },
+	{ ADAU7118_REG_SPT_CX(1), 0x11 },
+	{ ADAU7118_REG_SPT_CX(2), 0x21 },
+	{ ADAU7118_REG_SPT_CX(3), 0x31 },
+	{ ADAU7118_REG_SPT_CX(4), 0x41 },
+	{ ADAU7118_REG_SPT_CX(5), 0x51 },
+	{ ADAU7118_REG_SPT_CX(6), 0x61 },
+	{ ADAU7118_REG_SPT_CX(7), 0x71 },
+	{ ADAU7118_REG_DRIVE_STRENGTH, 0x2a },
+	{ ADAU7118_REG_RESET, 0x00 },
+};
+
+static const struct regmap_config adau7118_regmap_config = {
+	.reg_bits = 8,
+	.val_bits = 8,
+	.reg_defaults = adau7118_reg_defaults,
+	.num_reg_defaults = ARRAY_SIZE(adau7118_reg_defaults),
+	.cache_type = REGCACHE_RBTREE,
+	.max_register = ADAU7118_REG_RESET,
+};
+
+static int adau7118_probe_i2c(struct i2c_client *i2c,
+			      const struct i2c_device_id *id)
+{
+	struct regmap *map;
+
+	map = devm_regmap_init_i2c(i2c, &adau7118_regmap_config);
+	if (IS_ERR(map)) {
+		dev_err(&i2c->dev, "Failed to init regmap %ld\n", PTR_ERR(map));
+		return PTR_ERR(map);
+	}
+
+	return adau7118_probe(&i2c->dev, map, false);
+}
+
+static const struct of_device_id adau7118_of_match[] = {
+	{ .compatible = "adi,adau7118" },
+	{}
+};
+MODULE_DEVICE_TABLE(of, adau7118_of_match);
+
+static const struct i2c_device_id adau7118_id[] = {
+	{"adau7118", 0},
+	{}
+};
+MODULE_DEVICE_TABLE(i2c, adau7118_id);
+
+static struct i2c_driver adau7118_driver = {
+	.driver = {
+		.name = "adau7118",
+		.of_match_table = adau7118_of_match,
+	},
+	.probe = adau7118_probe_i2c,
+	.id_table = adau7118_id,
+};
+module_i2c_driver(adau7118_driver);
+
+MODULE_AUTHOR("Nuno Sa <nuno.sa@analog.com>");
+MODULE_DESCRIPTION("ADAU7118 8 channel PDM-to-I2S/TDM Converter driver over I2C");
+MODULE_LICENSE("GPL");
diff --git a/sound/soc/codecs/adau7118.c b/sound/soc/codecs/adau7118.c
new file mode 100644
index 000000000000..841229dcbca1
--- /dev/null
+++ b/sound/soc/codecs/adau7118.c
@@ -0,0 +1,586 @@
+// SPDX-License-Identifier: GPL-2.0
+//
+// Analog Devices ADAU7118 8 channel PDM-to-I2S/TDM Converter driver
+//
+// Copyright 2019 Analog Devices Inc.
+
+#include <linux/bitfield.h>
+#include <linux/module.h>
+#include <linux/regmap.h>
+#include <linux/regulator/consumer.h>
+#include <sound/pcm_params.h>
+#include <sound/soc.h>
+
+#include "adau7118.h"
+
+#define ADAU7118_DEC_RATIO_MASK		GENMASK(1, 0)
+#define ADAU7118_DEC_RATIO(x)		FIELD_PREP(ADAU7118_DEC_RATIO_MASK, x)
+#define ADAU7118_CLK_MAP_MASK		GENMASK(7, 4)
+#define ADAU7118_SLOT_WIDTH_MASK	GENMASK(5, 4)
+#define ADAU7118_SLOT_WIDTH(x)		FIELD_PREP(ADAU7118_SLOT_WIDTH_MASK, x)
+#define ADAU7118_TRISTATE_MASK		BIT(6)
+#define ADAU7118_TRISTATE(x)		FIELD_PREP(ADAU7118_TRISTATE_MASK, x)
+#define ADAU7118_DATA_FMT_MASK		GENMASK(3, 1)
+#define ADAU7118_DATA_FMT(x)		FIELD_PREP(ADAU7118_DATA_FMT_MASK, x)
+#define ADAU7118_SAI_MODE_MASK		BIT(0)
+#define ADAU7118_SAI_MODE(x)		FIELD_PREP(ADAU7118_SAI_MODE_MASK, x)
+#define ADAU7118_LRCLK_BCLK_POL_MASK	GENMASK(1, 0)
+#define ADAU7118_LRCLK_BCLK_POL(x) \
+				FIELD_PREP(ADAU7118_LRCLK_BCLK_POL_MASK, x)
+#define ADAU7118_SPT_SLOT_MASK		GENMASK(7, 4)
+#define ADAU7118_SPT_SLOT(x)		FIELD_PREP(ADAU7118_SPT_SLOT_MASK, x)
+#define ADAU7118_FULL_SOFT_R_MASK	BIT(1)
+#define ADAU7118_FULL_SOFT_R(x)		FIELD_PREP(ADAU7118_FULL_SOFT_R_MASK, x)
+
+struct adau7118_data {
+	struct regmap *map;
+	struct device *dev;
+	struct regulator *iovdd;
+	struct regulator *dvdd;
+	u32 slot_width;
+	u32 slots;
+	bool hw_mode;
+	bool right_j;
+};
+
+/* Input Enable */
+static const struct snd_kcontrol_new adau7118_dapm_pdm_control[4] = {
+	SOC_DAPM_SINGLE("Capture Switch", ADAU7118_REG_ENABLES, 0, 1, 0),
+	SOC_DAPM_SINGLE("Capture Switch", ADAU7118_REG_ENABLES, 1, 1, 0),
+	SOC_DAPM_SINGLE("Capture Switch", ADAU7118_REG_ENABLES, 2, 1, 0),
+	SOC_DAPM_SINGLE("Capture Switch", ADAU7118_REG_ENABLES, 3, 1, 0),
+};
+
+static const struct snd_soc_dapm_widget adau7118_widgets_sw[] = {
+	/* Input Enable Switches */
+	SND_SOC_DAPM_SWITCH("PDM0", SND_SOC_NOPM, 0, 0,
+			    &adau7118_dapm_pdm_control[0]),
+	SND_SOC_DAPM_SWITCH("PDM1", SND_SOC_NOPM, 0, 0,
+			    &adau7118_dapm_pdm_control[1]),
+	SND_SOC_DAPM_SWITCH("PDM2", SND_SOC_NOPM, 0, 0,
+			    &adau7118_dapm_pdm_control[2]),
+	SND_SOC_DAPM_SWITCH("PDM3", SND_SOC_NOPM, 0, 0,
+			    &adau7118_dapm_pdm_control[3]),
+
+	/* PDM Clocks */
+	SND_SOC_DAPM_SUPPLY("PDM_CLK0", ADAU7118_REG_ENABLES, 4, 0, NULL, 0),
+	SND_SOC_DAPM_SUPPLY("PDM_CLK1", ADAU7118_REG_ENABLES, 5, 0, NULL, 0),
+
+	/* Output channels */
+	SND_SOC_DAPM_AIF_OUT("AIF1TX1", "Capture", 0, ADAU7118_REG_SPT_CX(0),
+			     0, 0),
+	SND_SOC_DAPM_AIF_OUT("AIF1TX2", "Capture", 0, ADAU7118_REG_SPT_CX(1),
+			     0, 0),
+	SND_SOC_DAPM_AIF_OUT("AIF1TX3", "Capture", 0, ADAU7118_REG_SPT_CX(2),
+			     0, 0),
+	SND_SOC_DAPM_AIF_OUT("AIF1TX4", "Capture", 0, ADAU7118_REG_SPT_CX(3),
+			     0, 0),
+	SND_SOC_DAPM_AIF_OUT("AIF1TX5", "Capture", 0, ADAU7118_REG_SPT_CX(4),
+			     0, 0),
+	SND_SOC_DAPM_AIF_OUT("AIF1TX6", "Capture", 0, ADAU7118_REG_SPT_CX(5),
+			     0, 0),
+	SND_SOC_DAPM_AIF_OUT("AIF1TX7", "Capture", 0, ADAU7118_REG_SPT_CX(6),
+			     0, 0),
+	SND_SOC_DAPM_AIF_OUT("AIF1TX8", "Capture", 0, ADAU7118_REG_SPT_CX(7),
+			     0, 0),
+};
+
+static const struct snd_soc_dapm_route adau7118_routes_sw[] = {
+	{ "PDM0", "Capture Switch", "PDM_DAT0" },
+	{ "PDM1", "Capture Switch", "PDM_DAT1" },
+	{ "PDM2", "Capture Switch", "PDM_DAT2" },
+	{ "PDM3", "Capture Switch", "PDM_DAT3" },
+	{ "AIF1TX1", NULL, "PDM0" },
+	{ "AIF1TX2", NULL, "PDM0" },
+	{ "AIF1TX3", NULL, "PDM1" },
+	{ "AIF1TX4", NULL, "PDM1" },
+	{ "AIF1TX5", NULL, "PDM2" },
+	{ "AIF1TX6", NULL, "PDM2" },
+	{ "AIF1TX7", NULL, "PDM3" },
+	{ "AIF1TX8", NULL, "PDM3" },
+	{ "Capture", NULL, "PDM_CLK0" },
+	{ "Capture", NULL, "PDM_CLK1" },
+};
+
+static const struct snd_soc_dapm_widget adau7118_widgets_hw[] = {
+	SND_SOC_DAPM_AIF_OUT("AIF1TX", "Capture", 0, SND_SOC_NOPM, 0, 0),
+};
+
+static const struct snd_soc_dapm_route adau7118_routes_hw[] = {
+	{ "AIF1TX", NULL, "PDM_DAT0" },
+	{ "AIF1TX", NULL, "PDM_DAT1" },
+	{ "AIF1TX", NULL, "PDM_DAT2" },
+	{ "AIF1TX", NULL, "PDM_DAT3" },
+};
+
+static const struct snd_soc_dapm_widget adau7118_widgets[] = {
+	SND_SOC_DAPM_INPUT("PDM_DAT0"),
+	SND_SOC_DAPM_INPUT("PDM_DAT1"),
+	SND_SOC_DAPM_INPUT("PDM_DAT2"),
+	SND_SOC_DAPM_INPUT("PDM_DAT3"),
+};
+
+static int adau7118_set_channel_map(struct snd_soc_dai *dai,
+				    unsigned int tx_num, unsigned int *tx_slot,
+				    unsigned int rx_num, unsigned int *rx_slot)
+{
+	struct adau7118_data *st =
+		snd_soc_component_get_drvdata(dai->component);
+	int chan, ret;
+
+	dev_dbg(st->dev, "Set channel map, %d", tx_num);
+
+	for (chan = 0; chan < tx_num; chan++) {
+		ret = snd_soc_component_update_bits(dai->component,
+					ADAU7118_REG_SPT_CX(chan),
+					ADAU7118_SPT_SLOT_MASK,
+					ADAU7118_SPT_SLOT(tx_slot[chan]));
+		if (ret < 0)
+			return ret;
+	}
+
+	return 0;
+}
+
+static int adau7118_set_fmt(struct snd_soc_dai *dai, unsigned int fmt)
+{
+	struct adau7118_data *st =
+		snd_soc_component_get_drvdata(dai->component);
+	int ret = 0;
+	u32 regval;
+
+	dev_dbg(st->dev, "Set format, fmt:%d\n", fmt);
+
+	switch (fmt & SND_SOC_DAIFMT_FORMAT_MASK) {
+	case SND_SOC_DAIFMT_I2S:
+		ret = snd_soc_component_update_bits(dai->component,
+						    ADAU7118_REG_SPT_CTRL1,
+						    ADAU7118_DATA_FMT_MASK,
+						    ADAU7118_DATA_FMT(0));
+		break;
+	case SND_SOC_DAIFMT_LEFT_J:
+		ret = snd_soc_component_update_bits(dai->component,
+						    ADAU7118_REG_SPT_CTRL1,
+						    ADAU7118_DATA_FMT_MASK,
+						    ADAU7118_DATA_FMT(1));
+		break;
+	case SND_SOC_DAIFMT_RIGHT_J:
+		st->right_j = true;
+		break;
+	default:
+		dev_err(st->dev, "Invalid format %d",
+			fmt & SND_SOC_DAIFMT_FORMAT_MASK);
+		return -EINVAL;
+	}
+
+	if (ret < 0)
+		return ret;
+
+	switch (fmt & SND_SOC_DAIFMT_INV_MASK) {
+	case SND_SOC_DAIFMT_NB_NF:
+		regval = ADAU7118_LRCLK_BCLK_POL(0);
+		break;
+	case SND_SOC_DAIFMT_NB_IF:
+		regval = ADAU7118_LRCLK_BCLK_POL(2);
+		break;
+	case SND_SOC_DAIFMT_IB_NF:
+		regval = ADAU7118_LRCLK_BCLK_POL(1);
+		break;
+	case SND_SOC_DAIFMT_IB_IF:
+		regval = ADAU7118_LRCLK_BCLK_POL(3);
+		break;
+	default:
+		dev_err(st->dev, "Invalid Inv mask %d",
+			fmt & SND_SOC_DAIFMT_INV_MASK);
+		return -EINVAL;
+	}
+
+	ret = snd_soc_component_update_bits(dai->component,
+					    ADAU7118_REG_SPT_CTRL2,
+					    ADAU7118_LRCLK_BCLK_POL_MASK,
+					    regval);
+	if (ret < 0)
+		return ret;
+
+	return 0;
+}
+
+static int adau7118_set_tristate(struct snd_soc_dai *dai, int tristate)
+{
+	struct adau7118_data *st =
+		snd_soc_component_get_drvdata(dai->component);
+	int ret;
+
+	dev_dbg(st->dev, "Set tristate, %d\n", tristate);
+
+	ret = snd_soc_component_update_bits(dai->component,
+					    ADAU7118_REG_SPT_CTRL1,
+					    ADAU7118_TRISTATE_MASK,
+					    ADAU7118_TRISTATE(tristate));
+	if (ret < 0)
+		return ret;
+
+	return 0;
+}
+
+static int adau7118_set_tdm_slot(struct snd_soc_dai *dai, unsigned int tx_mask,
+				 unsigned int rx_mask, int slots,
+				 int slot_width)
+{
+	struct adau7118_data *st =
+		snd_soc_component_get_drvdata(dai->component);
+	int ret = 0;
+	u32 regval;
+
+	dev_dbg(st->dev, "Set tdm, slots:%d width:%d\n", slots, slot_width);
+
+	switch (slot_width) {
+	case 32:
+		regval = ADAU7118_SLOT_WIDTH(0);
+		break;
+	case 24:
+		regval = ADAU7118_SLOT_WIDTH(2);
+		break;
+	case 16:
+		regval = ADAU7118_SLOT_WIDTH(1);
+		break;
+	default:
+		dev_err(st->dev, "Invalid slot width:%d\n", slot_width);
+		return -EINVAL;
+	}
+
+	ret = snd_soc_component_update_bits(dai->component,
+					    ADAU7118_REG_SPT_CTRL1,
+					    ADAU7118_SLOT_WIDTH_MASK, regval);
+	if (ret < 0)
+		return ret;
+
+	st->slot_width = slot_width;
+	st->slots = slots;
+
+	return 0;
+}
+
+static int adau7118_hw_params(struct snd_pcm_substream *substream,
+			      struct snd_pcm_hw_params *params,
+			      struct snd_soc_dai *dai)
+{
+	struct adau7118_data *st =
+		snd_soc_component_get_drvdata(dai->component);
+	u32 data_width = params_width(params), slots_width;
+	int ret;
+	u32 regval;
+
+	if (!st->slots) {
+		/* set stereo mode */
+		ret = snd_soc_component_update_bits(dai->component,
+						    ADAU7118_REG_SPT_CTRL1,
+						    ADAU7118_SAI_MODE_MASK,
+						    ADAU7118_SAI_MODE(0));
+		if (ret < 0)
+			return ret;
+
+		slots_width = 32;
+	} else {
+		slots_width = st->slot_width;
+	}
+
+	if (data_width > slots_width) {
+		dev_err(st->dev, "Invalid data_width:%d, slots_width:%d",
+			data_width, slots_width);
+		return -EINVAL;
+	}
+
+	if (st->right_j) {
+		switch (slots_width - data_width) {
+		case 8:
+			/* delay bclck by 8 */
+			regval = ADAU7118_DATA_FMT(2);
+			break;
+		case 12:
+			/* delay bclck by 12 */
+			regval = ADAU7118_DATA_FMT(3);
+			break;
+		case 16:
+			/* delay bclck by 16 */
+			regval = ADAU7118_DATA_FMT(4);
+			break;
+		default:
+			dev_err(st->dev,
+				"Cannot set right_j setting, slot_w:%d, data_w:%d\n",
+					slots_width, data_width);
+			return -EINVAL;
+		}
+
+		ret = snd_soc_component_update_bits(dai->component,
+						    ADAU7118_REG_SPT_CTRL1,
+						    ADAU7118_DATA_FMT_MASK,
+						    regval);
+		if (ret < 0)
+			return ret;
+	}
+
+	return 0;
+}
+
+static int adau7118_set_bias_level(struct snd_soc_component *component,
+				   enum snd_soc_bias_level level)
+{
+	struct adau7118_data *st = snd_soc_component_get_drvdata(component);
+	int ret = 0;
+
+	dev_dbg(st->dev, "Set bias level %d\n", level);
+
+	switch (level) {
+	case SND_SOC_BIAS_ON:
+	case SND_SOC_BIAS_PREPARE:
+		break;
+
+	case SND_SOC_BIAS_STANDBY:
+		if (snd_soc_component_get_bias_level(component) ==
+							SND_SOC_BIAS_OFF) {
+			/* power on */
+			ret = regulator_enable(st->iovdd);
+			if (ret)
+				return ret;
+
+			/* there's no timing constraints before enabling dvdd */
+			ret = regulator_enable(st->dvdd);
+			if (ret) {
+				regulator_disable(st->iovdd);
+				return ret;
+			}
+
+			if (st->hw_mode)
+				return 0;
+
+			regcache_cache_only(st->map, false);
+			/* sync cache */
+			ret = snd_soc_component_cache_sync(component);
+		}
+		break;
+	case SND_SOC_BIAS_OFF:
+		/* power off */
+		ret = regulator_disable(st->dvdd);
+		if (ret)
+			return ret;
+
+		ret = regulator_disable(st->iovdd);
+		if (ret)
+			return ret;
+
+		if (st->hw_mode)
+			return 0;
+
+		/* cache only */
+		regcache_mark_dirty(st->map);
+		regcache_cache_only(st->map, true);
+
+		break;
+	}
+
+	return ret;
+}
+
+static int adau7118_component_probe(struct snd_soc_component *component)
+{
+	struct adau7118_data *st = snd_soc_component_get_drvdata(component);
+	struct snd_soc_dapm_context *dapm =
+					snd_soc_component_get_dapm(component);
+	int ret = 0;
+
+	if (st->hw_mode) {
+		ret = snd_soc_dapm_new_controls(dapm, adau7118_widgets_hw,
+					ARRAY_SIZE(adau7118_widgets_hw));
+		if (ret)
+			return ret;
+
+		ret = snd_soc_dapm_add_routes(dapm, adau7118_routes_hw,
+					      ARRAY_SIZE(adau7118_routes_hw));
+	} else {
+		snd_soc_component_init_regmap(component, st->map);
+		ret = snd_soc_dapm_new_controls(dapm, adau7118_widgets_sw,
+					ARRAY_SIZE(adau7118_widgets_sw));
+		if (ret)
+			return ret;
+
+		ret = snd_soc_dapm_add_routes(dapm, adau7118_routes_sw,
+					      ARRAY_SIZE(adau7118_routes_sw));
+	}
+
+	return ret;
+}
+
+static const struct snd_soc_dai_ops adau7118_ops = {
+	.hw_params = adau7118_hw_params,
+	.set_channel_map = adau7118_set_channel_map,
+	.set_fmt = adau7118_set_fmt,
+	.set_tdm_slot = adau7118_set_tdm_slot,
+	.set_tristate = adau7118_set_tristate,
+};
+
+static struct snd_soc_dai_driver adau7118_dai = {
+	.name = "adau7118-hifi-capture",
+	.capture = {
+		.stream_name = "Capture",
+		.channels_min = 1,
+		.channels_max = 8,
+		.formats = SNDRV_PCM_FMTBIT_S16_LE | SNDRV_PCM_FMTBIT_S20_3LE |
+			SNDRV_PCM_FMTBIT_S20_LE | SNDRV_PCM_FMTBIT_S24_LE |
+			SNDRV_PCM_FMTBIT_S24_3LE,
+		.rates = SNDRV_PCM_RATE_CONTINUOUS,
+		.rate_min = 4000,
+		.rate_max = 192000,
+		.sig_bits = 24,
+	},
+};
+
+static const struct snd_soc_component_driver adau7118_component_driver = {
+	.probe			= adau7118_component_probe,
+	.set_bias_level		= adau7118_set_bias_level,
+	.dapm_widgets		= adau7118_widgets,
+	.num_dapm_widgets	= ARRAY_SIZE(adau7118_widgets),
+	.use_pmdown_time	= 1,
+	.endianness		= 1,
+	.non_legacy_dai_naming	= 1,
+};
+
+static void adau7118_regulator_disable(void *data)
+{
+	struct adau7118_data *st = data;
+	int ret;
+	/*
+	 * If we fail to disable DVDD, don't bother in trying IOVDD. We
+	 * actually don't want to be left in the situation where DVDD
+	 * is enabled and IOVDD is disabled.
+	 */
+	ret = regulator_disable(st->dvdd);
+	if (ret)
+		return;
+
+	regulator_disable(st->iovdd);
+}
+
+static int adau7118_regulator_setup(struct adau7118_data *st)
+{
+	st->iovdd = devm_regulator_get(st->dev, "iovdd");
+	if (IS_ERR(st->iovdd)) {
+		dev_err(st->dev, "Could not get iovdd: %ld\n",
+			PTR_ERR(st->iovdd));
+		return PTR_ERR(st->iovdd);
+	}
+
+	st->dvdd = devm_regulator_get(st->dev, "dvdd");
+	if (IS_ERR(st->dvdd)) {
+		dev_err(st->dev, "Could not get dvdd: %ld\n",
+			PTR_ERR(st->dvdd));
+		return PTR_ERR(st->dvdd);
+	}
+	/* just assume the device is in reset */
+	if (!st->hw_mode) {
+		regcache_mark_dirty(st->map);
+		regcache_cache_only(st->map, true);
+	}
+
+	return devm_add_action_or_reset(st->dev, adau7118_regulator_disable,
+					st);
+}
+
+static int adau7118_parset_dt(const struct adau7118_data *st)
+{
+	int ret;
+	u32 dec_ratio = 0;
+	/* 4 inputs */
+	u32 clk_map[4], regval;
+
+	if (st->hw_mode)
+		return 0;
+
+	ret = device_property_read_u32(st->dev, "adi,decimation-ratio",
+				       &dec_ratio);
+	if (!ret) {
+		switch (dec_ratio) {
+		case 64:
+			regval = ADAU7118_DEC_RATIO(0);
+			break;
+		case 32:
+			regval = ADAU7118_DEC_RATIO(1);
+			break;
+		case 16:
+			regval = ADAU7118_DEC_RATIO(2);
+			break;
+		default:
+			dev_err(st->dev, "Invalid dec ratio: %u", dec_ratio);
+			return -EINVAL;
+		}
+
+		ret = regmap_update_bits(st->map,
+					 ADAU7118_REG_DEC_RATIO_CLK_MAP,
+					 ADAU7118_DEC_RATIO_MASK, regval);
+		if (ret)
+			return ret;
+	}
+
+	ret = device_property_read_u32_array(st->dev, "adi,pdm-clk-map",
+					     clk_map, ARRAY_SIZE(clk_map));
+	if (!ret) {
+		int pdm;
+		u32 _clk_map = 0;
+
+		for (pdm = 0; pdm < ARRAY_SIZE(clk_map); pdm++)
+			_clk_map |= (clk_map[pdm] << (pdm + 4));
+
+		ret = regmap_update_bits(st->map,
+					 ADAU7118_REG_DEC_RATIO_CLK_MAP,
+					 ADAU7118_CLK_MAP_MASK, _clk_map);
+		if (ret)
+			return ret;
+	}
+
+	return 0;
+}
+
+int adau7118_probe(struct device *dev, struct regmap *map, bool hw_mode)
+{
+	struct adau7118_data *st;
+	int ret;
+
+	st = devm_kzalloc(dev, sizeof(*st), GFP_KERNEL);
+	if (!st)
+		return -ENOMEM;
+
+	st->dev = dev;
+	st->hw_mode = hw_mode;
+	dev_set_drvdata(dev, st);
+
+	if (!hw_mode) {
+		st->map = map;
+		adau7118_dai.ops = &adau7118_ops;
+		/*
+		 * Perform a full soft reset. This will set all register's
+		 * with their reset values.
+		 */
+		ret = regmap_update_bits(map, ADAU7118_REG_RESET,
+					 ADAU7118_FULL_SOFT_R_MASK,
+					 ADAU7118_FULL_SOFT_R(1));
+		if (ret)
+			return ret;
+	}
+
+	ret = adau7118_parset_dt(st);
+	if (ret)
+		return ret;
+
+	ret = adau7118_regulator_setup(st);
+	if (ret)
+		return ret;
+
+	return devm_snd_soc_register_component(dev,
+					       &adau7118_component_driver,
+					       &adau7118_dai, 1);
+}
+EXPORT_SYMBOL_GPL(adau7118_probe);
+
+MODULE_AUTHOR("Nuno Sa <nuno.sa@analog.com>");
+MODULE_DESCRIPTION("ADAU7118 8 channel PDM-to-I2S/TDM Converter driver");
+MODULE_LICENSE("GPL");
diff --git a/sound/soc/codecs/adau7118.h b/sound/soc/codecs/adau7118.h
new file mode 100644
index 000000000000..c65679a4dff1
--- /dev/null
+++ b/sound/soc/codecs/adau7118.h
@@ -0,0 +1,24 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _LINUX_ADAU7118_H
+#define _LINUX_ADAU7118_H
+
+struct regmap;
+struct device;
+
+/* register map */
+#define ADAU7118_REG_VENDOR_ID		0x00
+#define ADAU7118_REG_DEVICE_ID1		0x01
+#define ADAU7118_REG_DEVICE_ID2		0x02
+#define ADAU7118_REG_REVISION_ID	0x03
+#define ADAU7118_REG_ENABLES		0x04
+#define ADAU7118_REG_DEC_RATIO_CLK_MAP	0x05
+#define ADAU7118_REG_HPF_CONTROL	0x06
+#define ADAU7118_REG_SPT_CTRL1		0x07
+#define ADAU7118_REG_SPT_CTRL2		0x08
+#define ADAU7118_REG_SPT_CX(num)	(0x09 + (num))
+#define ADAU7118_REG_DRIVE_STRENGTH	0x11
+#define ADAU7118_REG_RESET		0x12
+
+int adau7118_probe(struct device *dev, struct regmap *map, bool hw_mode);
+
+#endif
diff --git a/sound/soc/codecs/cros_ec_codec.c b/sound/soc/codecs/cros_ec_codec.c
index 3c1bd24a1057..7b17f39a6a10 100644
--- a/sound/soc/codecs/cros_ec_codec.c
+++ b/sound/soc/codecs/cros_ec_codec.c
@@ -1,15 +1,23 @@
 // SPDX-License-Identifier: GPL-2.0
 /*
- * Driver for ChromeOS Embedded Controller codec.
+ * Copyright 2019 Google, Inc.
+ *
+ * ChromeOS Embedded Controller codec driver.
  *
  * This driver uses the cros-ec interface to communicate with the ChromeOS
  * EC for audio function.
  */
 
+#include <crypto/hash.h>
+#include <crypto/sha.h>
 #include <linux/delay.h>
 #include <linux/device.h>
+#include <linux/io.h>
+#include <linux/jiffies.h>
 #include <linux/kernel.h>
 #include <linux/module.h>
+#include <linux/of.h>
+#include <linux/of_address.h>
 #include <linux/platform_data/cros_ec_commands.h>
 #include <linux/platform_data/cros_ec_proto.h>
 #include <linux/platform_device.h>
@@ -18,92 +26,279 @@
 #include <sound/soc.h>
 #include <sound/tlv.h>
 
-#define DRV_NAME "cros-ec-codec"
-
-/**
- * struct cros_ec_codec_data - ChromeOS EC codec driver data.
- * @dev:		Device structure used in sysfs.
- * @ec_device:		cros_ec_device structure to talk to the physical device.
- * @component:		Pointer to the component.
- * @max_dmic_gain:	Maximum gain in dB supported by EC codec.
- */
-struct cros_ec_codec_data {
+struct cros_ec_codec_priv {
 	struct device *dev;
 	struct cros_ec_device *ec_device;
-	struct snd_soc_component *component;
-	unsigned int max_dmic_gain;
+
+	/* common */
+	uint32_t ec_capabilities;
+
+	uint64_t ec_shm_addr;
+	uint32_t ec_shm_len;
+
+	uint64_t ap_shm_phys_addr;
+	uint32_t ap_shm_len;
+	uint64_t ap_shm_addr;
+	uint64_t ap_shm_last_alloc;
+
+	/* DMIC */
+	atomic_t dmic_probed;
+
+	/* WoV */
+	bool wov_enabled;
+	uint8_t *wov_audio_shm_p;
+	uint32_t wov_audio_shm_len;
+	uint8_t wov_audio_shm_type;
+	uint8_t *wov_lang_shm_p;
+	uint32_t wov_lang_shm_len;
+	uint8_t wov_lang_shm_type;
+
+	struct mutex wov_dma_lock;
+	uint8_t wov_buf[64000];
+	uint32_t wov_rp, wov_wp;
+	size_t wov_dma_offset;
+	bool wov_burst_read;
+	struct snd_pcm_substream *wov_substream;
+	struct delayed_work wov_copy_work;
+	struct notifier_block wov_notifier;
 };
 
-static const DECLARE_TLV_DB_SCALE(ec_mic_gain_tlv, 0, 100, 0);
+static int ec_codec_capable(struct cros_ec_codec_priv *priv, uint8_t cap)
+{
+	return priv->ec_capabilities & BIT(cap);
+}
 
-static int ec_command_get_gain(struct snd_soc_component *component,
-			       struct ec_param_codec_i2s *param,
-			       struct ec_codec_i2s_gain *resp)
+static int send_ec_host_command(struct cros_ec_device *ec_dev, uint32_t cmd,
+				uint8_t *out, size_t outsize,
+				uint8_t *in, size_t insize)
 {
-	struct cros_ec_codec_data *codec_data =
-		snd_soc_component_get_drvdata(component);
-	struct cros_ec_device *ec_device = codec_data->ec_device;
-	u8 buffer[sizeof(struct cros_ec_command) +
-		  max(sizeof(struct ec_param_codec_i2s),
-		      sizeof(struct ec_codec_i2s_gain))];
-	struct cros_ec_command *msg = (struct cros_ec_command *)&buffer;
 	int ret;
+	struct cros_ec_command *msg;
+
+	msg = kmalloc(sizeof(*msg) + max(outsize, insize), GFP_KERNEL);
+	if (!msg)
+		return -ENOMEM;
 
 	msg->version = 0;
-	msg->command = EC_CMD_CODEC_I2S;
-	msg->outsize = sizeof(struct ec_param_codec_i2s);
-	msg->insize = sizeof(struct ec_codec_i2s_gain);
+	msg->command = cmd;
+	msg->outsize = outsize;
+	msg->insize = insize;
 
-	memcpy(msg->data, param, msg->outsize);
+	if (outsize)
+		memcpy(msg->data, out, outsize);
 
-	ret = cros_ec_cmd_xfer_status(ec_device, msg);
-	if (ret > 0)
-		memcpy(resp, msg->data, msg->insize);
+	ret = cros_ec_cmd_xfer_status(ec_dev, msg);
+	if (ret < 0)
+		goto error;
+
+	if (insize)
+		memcpy(in, msg->data, insize);
 
+	ret = 0;
+error:
+	kfree(msg);
 	return ret;
 }
 
-/*
- * Wrapper for EC command without response.
- */
-static int ec_command_no_resp(struct snd_soc_component *component,
-			      struct ec_param_codec_i2s *param)
+static int calculate_sha256(struct cros_ec_codec_priv *priv,
+			    uint8_t *buf, uint32_t size, uint8_t *digest)
 {
-	struct cros_ec_codec_data *codec_data =
+	struct crypto_shash *tfm;
+
+	tfm = crypto_alloc_shash("sha256", CRYPTO_ALG_TYPE_SHASH, 0);
+	if (IS_ERR(tfm)) {
+		dev_err(priv->dev, "can't alloc shash\n");
+		return PTR_ERR(tfm);
+	}
+
+	{
+		SHASH_DESC_ON_STACK(desc, tfm);
+
+		desc->tfm = tfm;
+
+		crypto_shash_digest(desc, buf, size, digest);
+		shash_desc_zero(desc);
+	}
+
+	crypto_free_shash(tfm);
+
+#ifdef DEBUG
+	{
+		char digest_str[65];
+
+		bin2hex(digest_str, digest, 32);
+		digest_str[64] = 0;
+		dev_dbg(priv->dev, "hash=%s\n", digest_str);
+	}
+#endif
+
+	return 0;
+}
+
+static int dmic_get_gain(struct snd_kcontrol *kcontrol,
+			 struct snd_ctl_elem_value *ucontrol)
+{
+	struct snd_soc_component *component =
+		snd_soc_kcontrol_component(kcontrol);
+	struct cros_ec_codec_priv *priv =
 		snd_soc_component_get_drvdata(component);
-	struct cros_ec_device *ec_device = codec_data->ec_device;
-	u8 buffer[sizeof(struct cros_ec_command) +
-		  sizeof(struct ec_param_codec_i2s)];
-	struct cros_ec_command *msg = (struct cros_ec_command *)&buffer;
+	struct ec_param_ec_codec_dmic p;
+	struct ec_response_ec_codec_dmic_get_gain_idx r;
+	int ret;
 
-	msg->version = 0;
-	msg->command = EC_CMD_CODEC_I2S;
-	msg->outsize = sizeof(struct ec_param_codec_i2s);
-	msg->insize = 0;
+	p.cmd = EC_CODEC_DMIC_GET_GAIN_IDX;
+	p.get_gain_idx_param.channel = EC_CODEC_DMIC_CHANNEL_0;
+	ret = send_ec_host_command(priv->ec_device, EC_CMD_EC_CODEC_DMIC,
+				   (uint8_t *)&p, sizeof(p),
+				   (uint8_t *)&r, sizeof(r));
+	if (ret < 0)
+		return ret;
+	ucontrol->value.integer.value[0] = r.gain;
 
-	memcpy(msg->data, param, msg->outsize);
+	p.cmd = EC_CODEC_DMIC_GET_GAIN_IDX;
+	p.get_gain_idx_param.channel = EC_CODEC_DMIC_CHANNEL_1;
+	ret = send_ec_host_command(priv->ec_device, EC_CMD_EC_CODEC_DMIC,
+				   (uint8_t *)&p, sizeof(p),
+				   (uint8_t *)&r, sizeof(r));
+	if (ret < 0)
+		return ret;
+	ucontrol->value.integer.value[1] = r.gain;
 
-	return cros_ec_cmd_xfer_status(ec_device, msg);
+	return 0;
 }
 
-static int set_i2s_config(struct snd_soc_component *component,
-			  enum ec_i2s_config i2s_config)
+static int dmic_put_gain(struct snd_kcontrol *kcontrol,
+			 struct snd_ctl_elem_value *ucontrol)
 {
-	struct ec_param_codec_i2s param;
+	struct snd_soc_component *component =
+		snd_soc_kcontrol_component(kcontrol);
+	struct cros_ec_codec_priv *priv =
+		snd_soc_component_get_drvdata(component);
+	struct soc_mixer_control *control =
+		(struct soc_mixer_control *)kcontrol->private_value;
+	int max_dmic_gain = control->max;
+	int left = ucontrol->value.integer.value[0];
+	int right = ucontrol->value.integer.value[1];
+	struct ec_param_ec_codec_dmic p;
+	int ret;
+
+	if (left > max_dmic_gain || right > max_dmic_gain)
+		return -EINVAL;
 
-	dev_dbg(component->dev, "%s set I2S format to %u\n", __func__,
-		i2s_config);
+	dev_dbg(component->dev, "set mic gain to %u, %u\n", left, right);
 
-	param.cmd = EC_CODEC_I2S_SET_CONFIG;
-	param.i2s_config = i2s_config;
+	p.cmd = EC_CODEC_DMIC_SET_GAIN_IDX;
+	p.set_gain_idx_param.channel = EC_CODEC_DMIC_CHANNEL_0;
+	p.set_gain_idx_param.gain = left;
+	ret = send_ec_host_command(priv->ec_device, EC_CMD_EC_CODEC_DMIC,
+				   (uint8_t *)&p, sizeof(p), NULL, 0);
+	if (ret < 0)
+		return ret;
+
+	p.cmd = EC_CODEC_DMIC_SET_GAIN_IDX;
+	p.set_gain_idx_param.channel = EC_CODEC_DMIC_CHANNEL_1;
+	p.set_gain_idx_param.gain = right;
+	return send_ec_host_command(priv->ec_device, EC_CMD_EC_CODEC_DMIC,
+				    (uint8_t *)&p, sizeof(p), NULL, 0);
+}
+
+static const DECLARE_TLV_DB_SCALE(dmic_gain_tlv, 0, 100, 0);
+
+enum {
+	DMIC_CTL_GAIN = 0,
+};
+
+static struct snd_kcontrol_new dmic_controls[] = {
+	[DMIC_CTL_GAIN] =
+		SOC_DOUBLE_EXT_TLV("EC Mic Gain", SND_SOC_NOPM, SND_SOC_NOPM,
+				   0, 0, 0, dmic_get_gain, dmic_put_gain,
+				   dmic_gain_tlv),
+};
+
+static int dmic_probe(struct snd_soc_component *component)
+{
+	struct cros_ec_codec_priv *priv =
+		snd_soc_component_get_drvdata(component);
+	struct device *dev = priv->dev;
+	struct soc_mixer_control *control;
+	struct ec_param_ec_codec_dmic p;
+	struct ec_response_ec_codec_dmic_get_max_gain r;
+	int ret;
+
+	if (!atomic_add_unless(&priv->dmic_probed, 1, 1))
+		return 0;
+
+	p.cmd = EC_CODEC_DMIC_GET_MAX_GAIN;
+
+	ret = send_ec_host_command(priv->ec_device, EC_CMD_EC_CODEC_DMIC,
+				   (uint8_t *)&p, sizeof(p),
+				   (uint8_t *)&r, sizeof(r));
+	if (ret < 0) {
+		dev_warn(dev, "get_max_gain() unsupported\n");
+		return 0;
+	}
+
+	dev_dbg(dev, "max gain = %d\n", r.max_gain);
+
+	control = (struct soc_mixer_control *)
+		dmic_controls[DMIC_CTL_GAIN].private_value;
+	control->max = r.max_gain;
+	control->platform_max = r.max_gain;
 
-	return ec_command_no_resp(component, &param);
+	return snd_soc_add_component_controls(component,
+			&dmic_controls[DMIC_CTL_GAIN], 1);
 }
 
-static int cros_ec_i2s_set_dai_fmt(struct snd_soc_dai *dai, unsigned int fmt)
+static int i2s_rx_hw_params(struct snd_pcm_substream *substream,
+			    struct snd_pcm_hw_params *params,
+			    struct snd_soc_dai *dai)
 {
 	struct snd_soc_component *component = dai->component;
-	enum ec_i2s_config i2s_config;
+	struct cros_ec_codec_priv *priv =
+		snd_soc_component_get_drvdata(component);
+	struct ec_param_ec_codec_i2s_rx p;
+	enum ec_codec_i2s_rx_sample_depth depth;
+	int ret;
+
+	if (params_rate(params) != 48000)
+		return -EINVAL;
+
+	switch (params_format(params)) {
+	case SNDRV_PCM_FORMAT_S16_LE:
+		depth = EC_CODEC_I2S_RX_SAMPLE_DEPTH_16;
+		break;
+	case SNDRV_PCM_FORMAT_S24_LE:
+		depth = EC_CODEC_I2S_RX_SAMPLE_DEPTH_24;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	dev_dbg(component->dev, "set depth to %u\n", depth);
+
+	p.cmd = EC_CODEC_I2S_RX_SET_SAMPLE_DEPTH;
+	p.set_sample_depth_param.depth = depth;
+	ret = send_ec_host_command(priv->ec_device, EC_CMD_EC_CODEC_I2S_RX,
+				   (uint8_t *)&p, sizeof(p), NULL, 0);
+	if (ret < 0)
+		return ret;
+
+	dev_dbg(component->dev, "set bclk to %u\n",
+		snd_soc_params_to_bclk(params));
+
+	p.cmd = EC_CODEC_I2S_RX_SET_BCLK;
+	p.set_bclk_param.bclk = snd_soc_params_to_bclk(params);
+	return send_ec_host_command(priv->ec_device, EC_CMD_EC_CODEC_I2S_RX,
+				    (uint8_t *)&p, sizeof(p), NULL, 0);
+}
+
+static int i2s_rx_set_fmt(struct snd_soc_dai *dai, unsigned int fmt)
+{
+	struct snd_soc_component *component = dai->component;
+	struct cros_ec_codec_priv *priv =
+		snd_soc_component_get_drvdata(component);
+	struct ec_param_ec_codec_i2s_rx p;
+	enum ec_codec_i2s_rx_daifmt daifmt;
 
 	switch (fmt & SND_SOC_DAIFMT_MASTER_MASK) {
 	case SND_SOC_DAIFMT_CBS_CFS:
@@ -121,300 +316,727 @@ static int cros_ec_i2s_set_dai_fmt(struct snd_soc_dai *dai, unsigned int fmt)
 
 	switch (fmt & SND_SOC_DAIFMT_FORMAT_MASK) {
 	case SND_SOC_DAIFMT_I2S:
-		i2s_config = EC_DAI_FMT_I2S;
+		daifmt = EC_CODEC_I2S_RX_DAIFMT_I2S;
 		break;
-
 	case SND_SOC_DAIFMT_RIGHT_J:
-		i2s_config = EC_DAI_FMT_RIGHT_J;
+		daifmt = EC_CODEC_I2S_RX_DAIFMT_RIGHT_J;
 		break;
-
 	case SND_SOC_DAIFMT_LEFT_J:
-		i2s_config = EC_DAI_FMT_LEFT_J;
+		daifmt = EC_CODEC_I2S_RX_DAIFMT_LEFT_J;
 		break;
+	default:
+		return -EINVAL;
+	}
 
-	case SND_SOC_DAIFMT_DSP_A:
-		i2s_config = EC_DAI_FMT_PCM_A;
-		break;
+	dev_dbg(component->dev, "set format to %u\n", daifmt);
 
-	case SND_SOC_DAIFMT_DSP_B:
-		i2s_config = EC_DAI_FMT_PCM_B;
-		break;
+	p.cmd = EC_CODEC_I2S_RX_SET_DAIFMT;
+	p.set_daifmt_param.daifmt = daifmt;
+	return send_ec_host_command(priv->ec_device, EC_CMD_EC_CODEC_I2S_RX,
+				    (uint8_t *)&p, sizeof(p), NULL, 0);
+}
+
+static const struct snd_soc_dai_ops i2s_rx_dai_ops = {
+	.hw_params = i2s_rx_hw_params,
+	.set_fmt = i2s_rx_set_fmt,
+};
 
+static int i2s_rx_event(struct snd_soc_dapm_widget *w,
+			struct snd_kcontrol *kcontrol, int event)
+{
+	struct snd_soc_component *component =
+		snd_soc_dapm_to_component(w->dapm);
+	struct cros_ec_codec_priv *priv =
+		snd_soc_component_get_drvdata(component);
+	struct ec_param_ec_codec_i2s_rx p;
+
+	switch (event) {
+	case SND_SOC_DAPM_PRE_PMU:
+		dev_dbg(component->dev, "enable I2S RX\n");
+		p.cmd = EC_CODEC_I2S_RX_ENABLE;
+		break;
+	case SND_SOC_DAPM_PRE_PMD:
+		dev_dbg(component->dev, "disable I2S RX\n");
+		p.cmd = EC_CODEC_I2S_RX_DISABLE;
+		break;
 	default:
-		return -EINVAL;
+		return 0;
 	}
 
-	return set_i2s_config(component, i2s_config);
+	return send_ec_host_command(priv->ec_device, EC_CMD_EC_CODEC_I2S_RX,
+				    (uint8_t *)&p, sizeof(p), NULL, 0);
+}
+
+static struct snd_soc_dapm_widget i2s_rx_dapm_widgets[] = {
+	SND_SOC_DAPM_INPUT("DMIC"),
+	SND_SOC_DAPM_SUPPLY("I2S RX Enable", SND_SOC_NOPM, 0, 0, i2s_rx_event,
+			    SND_SOC_DAPM_PRE_PMU | SND_SOC_DAPM_PRE_PMD),
+	SND_SOC_DAPM_AIF_OUT("I2S RX", "I2S Capture", 0, SND_SOC_NOPM, 0, 0),
+};
+
+static struct snd_soc_dapm_route i2s_rx_dapm_routes[] = {
+	{"I2S RX", NULL, "DMIC"},
+	{"I2S RX", NULL, "I2S RX Enable"},
+};
+
+static struct snd_soc_dai_driver i2s_rx_dai_driver = {
+	.name = "EC Codec I2S RX",
+	.capture = {
+		.stream_name = "I2S Capture",
+		.channels_min = 2,
+		.channels_max = 2,
+		.rates = SNDRV_PCM_RATE_48000,
+		.formats = SNDRV_PCM_FMTBIT_S16_LE |
+			SNDRV_PCM_FMTBIT_S24_LE,
+	},
+	.ops = &i2s_rx_dai_ops,
+};
+
+static int i2s_rx_probe(struct snd_soc_component *component)
+{
+	return dmic_probe(component);
 }
 
-static int set_i2s_sample_depth(struct snd_soc_component *component,
-				enum ec_sample_depth_value depth)
+static const struct snd_soc_component_driver i2s_rx_component_driver = {
+	.probe			= i2s_rx_probe,
+	.dapm_widgets		= i2s_rx_dapm_widgets,
+	.num_dapm_widgets	= ARRAY_SIZE(i2s_rx_dapm_widgets),
+	.dapm_routes		= i2s_rx_dapm_routes,
+	.num_dapm_routes	= ARRAY_SIZE(i2s_rx_dapm_routes),
+};
+
+static void *wov_map_shm(struct cros_ec_codec_priv *priv,
+			 uint8_t shm_id, uint32_t *len, uint8_t *type)
 {
-	struct ec_param_codec_i2s param;
+	struct ec_param_ec_codec p;
+	struct ec_response_ec_codec_get_shm_addr r;
+	uint32_t req, offset;
+
+	p.cmd = EC_CODEC_GET_SHM_ADDR;
+	p.get_shm_addr_param.shm_id = shm_id;
+	if (send_ec_host_command(priv->ec_device, EC_CMD_EC_CODEC,
+				 (uint8_t *)&p, sizeof(p),
+				 (uint8_t *)&r, sizeof(r)) < 0) {
+		dev_err(priv->dev, "failed to EC_CODEC_GET_SHM_ADDR\n");
+		return NULL;
+	}
 
-	dev_dbg(component->dev, "%s set depth to %u\n", __func__, depth);
+	dev_dbg(priv->dev, "phys_addr=%#llx, len=%#x\n", r.phys_addr, r.len);
+
+	*len = r.len;
+	*type = r.type;
+
+	switch (r.type) {
+	case EC_CODEC_SHM_TYPE_EC_RAM:
+		return (void __force *)devm_ioremap_wc(priv->dev,
+				r.phys_addr + priv->ec_shm_addr, r.len);
+	case EC_CODEC_SHM_TYPE_SYSTEM_RAM:
+		if (r.phys_addr) {
+			dev_err(priv->dev, "unknown status\n");
+			return NULL;
+		}
+
+		req = round_up(r.len, PAGE_SIZE);
+		dev_dbg(priv->dev, "round up from %u to %u\n", r.len, req);
+
+		if (priv->ap_shm_last_alloc + req >
+		    priv->ap_shm_phys_addr + priv->ap_shm_len) {
+			dev_err(priv->dev, "insufficient space for AP SHM\n");
+			return NULL;
+		}
+
+		dev_dbg(priv->dev, "alloc AP SHM addr=%#llx, len=%#x\n",
+			priv->ap_shm_last_alloc, req);
+
+		p.cmd = EC_CODEC_SET_SHM_ADDR;
+		p.set_shm_addr_param.phys_addr = priv->ap_shm_last_alloc;
+		p.set_shm_addr_param.len = req;
+		p.set_shm_addr_param.shm_id = shm_id;
+		if (send_ec_host_command(priv->ec_device, EC_CMD_EC_CODEC,
+					 (uint8_t *)&p, sizeof(p),
+					 NULL, 0) < 0) {
+			dev_err(priv->dev, "failed to EC_CODEC_SET_SHM_ADDR\n");
+			return NULL;
+		}
+
+		/*
+		 * Note: EC codec only requests for `r.len' but we allocate
+		 * round up PAGE_SIZE `req'.
+		 */
+		offset = priv->ap_shm_last_alloc - priv->ap_shm_phys_addr;
+		priv->ap_shm_last_alloc += req;
+
+		return (void *)(uintptr_t)(priv->ap_shm_addr + offset);
+	default:
+		return NULL;
+	}
+}
 
-	param.cmd = EC_CODEC_SET_SAMPLE_DEPTH;
-	param.depth = depth;
+static bool wov_queue_full(struct cros_ec_codec_priv *priv)
+{
+	return ((priv->wov_wp + 1) % sizeof(priv->wov_buf)) == priv->wov_rp;
+}
 
-	return ec_command_no_resp(component, &param);
+static size_t wov_queue_size(struct cros_ec_codec_priv *priv)
+{
+	if (priv->wov_wp >= priv->wov_rp)
+		return priv->wov_wp - priv->wov_rp;
+	else
+		return sizeof(priv->wov_buf) - priv->wov_rp + priv->wov_wp;
 }
 
-static int set_i2s_bclk(struct snd_soc_component *component, uint32_t bclk)
+static void wov_queue_dequeue(struct cros_ec_codec_priv *priv, size_t len)
 {
-	struct ec_param_codec_i2s param;
+	struct snd_pcm_runtime *runtime = priv->wov_substream->runtime;
+	size_t req;
+
+	while (len) {
+		req = min(len, runtime->dma_bytes - priv->wov_dma_offset);
+		if (priv->wov_wp >= priv->wov_rp)
+			req = min(req, (size_t)priv->wov_wp - priv->wov_rp);
+		else
+			req = min(req, sizeof(priv->wov_buf) - priv->wov_rp);
 
-	dev_dbg(component->dev, "%s set i2s bclk to %u\n", __func__, bclk);
+		memcpy(runtime->dma_area + priv->wov_dma_offset,
+		       priv->wov_buf + priv->wov_rp, req);
 
-	param.cmd = EC_CODEC_I2S_SET_BCLK;
-	param.bclk = bclk;
+		priv->wov_dma_offset += req;
+		if (priv->wov_dma_offset == runtime->dma_bytes)
+			priv->wov_dma_offset = 0;
 
-	return ec_command_no_resp(component, &param);
+		priv->wov_rp += req;
+		if (priv->wov_rp == sizeof(priv->wov_buf))
+			priv->wov_rp = 0;
+
+		len -= req;
+	}
+
+	snd_pcm_period_elapsed(priv->wov_substream);
 }
 
-static int cros_ec_i2s_hw_params(struct snd_pcm_substream *substream,
-				 struct snd_pcm_hw_params *params,
-				 struct snd_soc_dai *dai)
+static void wov_queue_try_dequeue(struct cros_ec_codec_priv *priv)
 {
-	struct snd_soc_component *component = dai->component;
-	unsigned int rate, bclk;
-	int ret;
+	size_t period_bytes = snd_pcm_lib_period_bytes(priv->wov_substream);
 
-	rate = params_rate(params);
-	if (rate != 48000)
-		return -EINVAL;
+	while (period_bytes && wov_queue_size(priv) >= period_bytes) {
+		wov_queue_dequeue(priv, period_bytes);
+		period_bytes = snd_pcm_lib_period_bytes(priv->wov_substream);
+	}
+}
 
-	switch (params_format(params)) {
-	case SNDRV_PCM_FORMAT_S16_LE:
-		ret = set_i2s_sample_depth(component, EC_CODEC_SAMPLE_DEPTH_16);
-		break;
-	case SNDRV_PCM_FORMAT_S24_LE:
-		ret = set_i2s_sample_depth(component, EC_CODEC_SAMPLE_DEPTH_24);
-		break;
-	default:
-		return -EINVAL;
+static void wov_queue_enqueue(struct cros_ec_codec_priv *priv,
+			      uint8_t *addr, size_t len, bool iomem)
+{
+	size_t req;
+
+	while (len) {
+		if (wov_queue_full(priv)) {
+			wov_queue_try_dequeue(priv);
+
+			if (wov_queue_full(priv)) {
+				dev_err(priv->dev, "overrun detected\n");
+				return;
+			}
+		}
+
+		if (priv->wov_wp >= priv->wov_rp)
+			req = sizeof(priv->wov_buf) - priv->wov_wp;
+		else
+			/* Note: waste 1-byte to differentiate full and empty */
+			req = priv->wov_rp - priv->wov_wp - 1;
+		req = min(req, len);
+
+		if (iomem)
+			memcpy_fromio(priv->wov_buf + priv->wov_wp,
+				      (void __force __iomem *)addr, req);
+		else
+			memcpy(priv->wov_buf + priv->wov_wp, addr, req);
+
+		priv->wov_wp += req;
+		if (priv->wov_wp == sizeof(priv->wov_buf))
+			priv->wov_wp = 0;
+
+		addr += req;
+		len -= req;
 	}
-	if (ret < 0)
+
+	wov_queue_try_dequeue(priv);
+}
+
+static int wov_read_audio_shm(struct cros_ec_codec_priv *priv)
+{
+	struct ec_param_ec_codec_wov p;
+	struct ec_response_ec_codec_wov_read_audio_shm r;
+	int ret;
+
+	p.cmd = EC_CODEC_WOV_READ_AUDIO_SHM;
+	ret = send_ec_host_command(priv->ec_device, EC_CMD_EC_CODEC_WOV,
+				   (uint8_t *)&p, sizeof(p),
+				   (uint8_t *)&r, sizeof(r));
+	if (ret) {
+		dev_err(priv->dev, "failed to EC_CODEC_WOV_READ_AUDIO_SHM\n");
 		return ret;
+	}
 
-	bclk = snd_soc_params_to_bclk(params);
-	return set_i2s_bclk(component, bclk);
+	if (!r.len)
+		dev_dbg(priv->dev, "no data, sleep\n");
+	else
+		wov_queue_enqueue(priv, priv->wov_audio_shm_p + r.offset, r.len,
+			priv->wov_audio_shm_type == EC_CODEC_SHM_TYPE_EC_RAM);
+	return -EAGAIN;
 }
 
-static const struct snd_soc_dai_ops cros_ec_i2s_dai_ops = {
-	.hw_params = cros_ec_i2s_hw_params,
-	.set_fmt = cros_ec_i2s_set_dai_fmt,
-};
+static int wov_read_audio(struct cros_ec_codec_priv *priv)
+{
+	struct ec_param_ec_codec_wov p;
+	struct ec_response_ec_codec_wov_read_audio r;
+	int remain = priv->wov_burst_read ? 16000 : 320;
+	int ret;
 
-static struct snd_soc_dai_driver cros_ec_dai[] = {
-	{
-		.name = "cros_ec_codec I2S",
-		.id = 0,
-		.capture = {
-			.stream_name = "I2S Capture",
-			.channels_min = 2,
-			.channels_max = 2,
-			.rates = SNDRV_PCM_RATE_48000,
-			.formats = SNDRV_PCM_FMTBIT_S16_LE |
-				   SNDRV_PCM_FMTBIT_S24_LE,
-		},
-		.ops = &cros_ec_i2s_dai_ops,
+	while (remain >= 0) {
+		p.cmd = EC_CODEC_WOV_READ_AUDIO;
+		ret = send_ec_host_command(priv->ec_device, EC_CMD_EC_CODEC_WOV,
+					   (uint8_t *)&p, sizeof(p),
+					   (uint8_t *)&r, sizeof(r));
+		if (ret) {
+			dev_err(priv->dev,
+				"failed to EC_CODEC_WOV_READ_AUDIO\n");
+			return ret;
+		}
+
+		if (!r.len) {
+			dev_dbg(priv->dev, "no data, sleep\n");
+			priv->wov_burst_read = false;
+			break;
+		}
+
+		wov_queue_enqueue(priv, r.buf, r.len, false);
+		remain -= r.len;
 	}
-};
 
-static int get_ec_mic_gain(struct snd_soc_component *component,
-			   u8 *left, u8 *right)
+	return -EAGAIN;
+}
+
+static void wov_copy_work(struct work_struct *w)
 {
-	struct ec_param_codec_i2s param;
-	struct ec_codec_i2s_gain resp;
+	struct cros_ec_codec_priv *priv =
+		container_of(w, struct cros_ec_codec_priv, wov_copy_work.work);
 	int ret;
 
-	param.cmd = EC_CODEC_GET_GAIN;
+	mutex_lock(&priv->wov_dma_lock);
+	if (!priv->wov_substream) {
+		dev_warn(priv->dev, "no pcm substream\n");
+		goto leave;
+	}
 
-	ret = ec_command_get_gain(component, &param, &resp);
-	if (ret < 0)
-		return ret;
+	if (ec_codec_capable(priv, EC_CODEC_CAP_WOV_AUDIO_SHM))
+		ret = wov_read_audio_shm(priv);
+	else
+		ret = wov_read_audio(priv);
+
+	if (ret == -EAGAIN)
+		schedule_delayed_work(&priv->wov_copy_work,
+				      msecs_to_jiffies(10));
+	else if (ret)
+		dev_err(priv->dev, "failed to read audio data\n");
+leave:
+	mutex_unlock(&priv->wov_dma_lock);
+}
 
-	*left = resp.left;
-	*right = resp.right;
+static int wov_enable_get(struct snd_kcontrol *kcontrol,
+			  struct snd_ctl_elem_value *ucontrol)
+{
+	struct snd_soc_component *c = snd_soc_kcontrol_component(kcontrol);
+	struct cros_ec_codec_priv *priv = snd_soc_component_get_drvdata(c);
 
+	ucontrol->value.integer.value[0] = priv->wov_enabled;
 	return 0;
 }
 
-static int mic_gain_get(struct snd_kcontrol *kcontrol,
-			struct snd_ctl_elem_value *ucontrol)
+static int wov_enable_put(struct snd_kcontrol *kcontrol,
+			  struct snd_ctl_elem_value *ucontrol)
 {
-	struct snd_soc_component *component =
-		snd_soc_kcontrol_component(kcontrol);
-	u8 left, right;
+	struct snd_soc_component *c = snd_soc_kcontrol_component(kcontrol);
+	struct cros_ec_codec_priv *priv = snd_soc_component_get_drvdata(c);
+	int enabled = ucontrol->value.integer.value[0];
+	struct ec_param_ec_codec_wov p;
 	int ret;
 
-	ret = get_ec_mic_gain(component, &left, &right);
-	if (ret)
-		return ret;
-
-	ucontrol->value.integer.value[0] = left;
-	ucontrol->value.integer.value[1] = right;
+	if (priv->wov_enabled != enabled) {
+		if (enabled)
+			p.cmd = EC_CODEC_WOV_ENABLE;
+		else
+			p.cmd = EC_CODEC_WOV_DISABLE;
+
+		ret = send_ec_host_command(priv->ec_device, EC_CMD_EC_CODEC_WOV,
+					   (uint8_t *)&p, sizeof(p), NULL, 0);
+		if (ret) {
+			dev_err(priv->dev, "failed to %s wov\n",
+				enabled ? "enable" : "disable");
+			return ret;
+		}
+
+		priv->wov_enabled = enabled;
+	}
 
 	return 0;
 }
 
-static int set_ec_mic_gain(struct snd_soc_component *component,
-			   u8 left, u8 right)
+static int wov_set_lang_shm(struct cros_ec_codec_priv *priv,
+			    uint8_t *buf, size_t size, uint8_t *digest)
 {
-	struct ec_param_codec_i2s param;
+	struct ec_param_ec_codec_wov p;
+	struct ec_param_ec_codec_wov_set_lang_shm *pp = &p.set_lang_shm_param;
+	int ret;
 
-	dev_dbg(component->dev, "%s set mic gain to %u, %u\n",
-		__func__, left, right);
+	if (size > priv->wov_lang_shm_len) {
+		dev_err(priv->dev, "no enough SHM size: %d\n",
+			priv->wov_lang_shm_len);
+		return -EIO;
+	}
 
-	param.cmd = EC_CODEC_SET_GAIN;
-	param.gain.left = left;
-	param.gain.right = right;
+	switch (priv->wov_lang_shm_type) {
+	case EC_CODEC_SHM_TYPE_EC_RAM:
+		memcpy_toio((void __force __iomem *)priv->wov_lang_shm_p,
+			    buf, size);
+		memset_io((void __force __iomem *)priv->wov_lang_shm_p + size,
+			  0, priv->wov_lang_shm_len - size);
+		break;
+	case EC_CODEC_SHM_TYPE_SYSTEM_RAM:
+		memcpy(priv->wov_lang_shm_p, buf, size);
+		memset(priv->wov_lang_shm_p + size, 0,
+		       priv->wov_lang_shm_len - size);
 
-	return ec_command_no_resp(component, &param);
+		/* make sure write to memory before calling host command */
+		wmb();
+		break;
+	}
+
+	p.cmd = EC_CODEC_WOV_SET_LANG_SHM;
+	memcpy(pp->hash, digest, SHA256_DIGEST_SIZE);
+	pp->total_len = size;
+	ret = send_ec_host_command(priv->ec_device, EC_CMD_EC_CODEC_WOV,
+				   (uint8_t *)&p, sizeof(p), NULL, 0);
+	if (ret) {
+		dev_err(priv->dev, "failed to EC_CODEC_WOV_SET_LANG_SHM\n");
+		return ret;
+	}
+
+	return 0;
 }
 
-static int mic_gain_put(struct snd_kcontrol *kcontrol,
-			struct snd_ctl_elem_value *ucontrol)
+static int wov_set_lang(struct cros_ec_codec_priv *priv,
+			uint8_t *buf, size_t size, uint8_t *digest)
 {
-	struct snd_soc_component *component =
-		snd_soc_kcontrol_component(kcontrol);
-	struct cros_ec_codec_data *codec_data =
-		snd_soc_component_get_drvdata(component);
-	int left = ucontrol->value.integer.value[0];
-	int right = ucontrol->value.integer.value[1];
-	unsigned int max_dmic_gain = codec_data->max_dmic_gain;
+	struct ec_param_ec_codec_wov p;
+	struct ec_param_ec_codec_wov_set_lang *pp = &p.set_lang_param;
+	size_t i, req;
+	int ret;
 
-	if (left > max_dmic_gain || right > max_dmic_gain)
-		return -EINVAL;
+	for (i = 0; i < size; i += req) {
+		req = min(size - i, ARRAY_SIZE(pp->buf));
+
+		p.cmd = EC_CODEC_WOV_SET_LANG;
+		memcpy(pp->hash, digest, SHA256_DIGEST_SIZE);
+		pp->total_len = size;
+		pp->offset = i;
+		memcpy(pp->buf, buf + i, req);
+		pp->len = req;
+		ret = send_ec_host_command(priv->ec_device, EC_CMD_EC_CODEC_WOV,
+					   (uint8_t *)&p, sizeof(p), NULL, 0);
+		if (ret) {
+			dev_err(priv->dev, "failed to EC_CODEC_WOV_SET_LANG\n");
+			return ret;
+		}
+	}
 
-	return set_ec_mic_gain(component, (u8)left, (u8)right);
+	return 0;
 }
 
-static struct snd_kcontrol_new mic_gain_control =
-	SOC_DOUBLE_EXT_TLV("EC Mic Gain", SND_SOC_NOPM, SND_SOC_NOPM, 0, 0, 0,
-			   mic_gain_get, mic_gain_put, ec_mic_gain_tlv);
-
-static int enable_i2s(struct snd_soc_component *component, int enable)
+static int wov_hotword_model_put(struct snd_kcontrol *kcontrol,
+				 const unsigned int __user *bytes,
+				 unsigned int size)
 {
-	struct ec_param_codec_i2s param;
+	struct snd_soc_component *component = snd_kcontrol_chip(kcontrol);
+	struct cros_ec_codec_priv *priv =
+		snd_soc_component_get_drvdata(component);
+	struct ec_param_ec_codec_wov p;
+	struct ec_response_ec_codec_wov_get_lang r;
+	uint8_t digest[SHA256_DIGEST_SIZE];
+	uint8_t *buf;
+	int ret;
+
+	/* Skips the TLV header. */
+	bytes += 2;
+	size -= 8;
+
+	dev_dbg(priv->dev, "%s: size=%d\n", __func__, size);
+
+	buf = memdup_user(bytes, size);
+	if (IS_ERR(buf))
+		return PTR_ERR(buf);
+
+	ret = calculate_sha256(priv, buf, size, digest);
+	if (ret)
+		goto leave;
+
+	p.cmd = EC_CODEC_WOV_GET_LANG;
+	ret = send_ec_host_command(priv->ec_device, EC_CMD_EC_CODEC_WOV,
+				   (uint8_t *)&p, sizeof(p),
+				   (uint8_t *)&r, sizeof(r));
+	if (ret)
+		goto leave;
 
-	dev_dbg(component->dev, "%s set i2s to %u\n", __func__, enable);
+	if (memcmp(digest, r.hash, SHA256_DIGEST_SIZE) == 0) {
+		dev_dbg(priv->dev, "not updated");
+		goto leave;
+	}
 
-	param.cmd = EC_CODEC_I2S_ENABLE;
-	param.i2s_enable = enable;
+	if (ec_codec_capable(priv, EC_CODEC_CAP_WOV_LANG_SHM))
+		ret = wov_set_lang_shm(priv, buf, size, digest);
+	else
+		ret = wov_set_lang(priv, buf, size, digest);
 
-	return ec_command_no_resp(component, &param);
+leave:
+	kfree(buf);
+	return ret;
 }
 
-static int cros_ec_i2s_enable_event(struct snd_soc_dapm_widget *w,
-				    struct snd_kcontrol *kcontrol, int event)
+static struct snd_kcontrol_new wov_controls[] = {
+	SOC_SINGLE_BOOL_EXT("Wake-on-Voice Switch", 0,
+			    wov_enable_get, wov_enable_put),
+	SND_SOC_BYTES_TLV("Hotword Model", 0x11000, NULL,
+			  wov_hotword_model_put),
+};
+
+static struct snd_soc_dai_driver wov_dai_driver = {
+	.name = "Wake on Voice",
+	.capture = {
+		.stream_name = "WoV Capture",
+		.channels_min = 1,
+		.channels_max = 1,
+		.rates = SNDRV_PCM_RATE_16000,
+		.formats = SNDRV_PCM_FMTBIT_S16_LE,
+	},
+};
+
+static int wov_host_event(struct notifier_block *nb,
+			  unsigned long queued_during_suspend, void *notify)
 {
-	struct snd_soc_component *component =
-		snd_soc_dapm_to_component(w->dapm);
+	struct cros_ec_codec_priv *priv =
+		container_of(nb, struct cros_ec_codec_priv, wov_notifier);
+	u32 host_event;
+
+	dev_dbg(priv->dev, "%s\n", __func__);
+
+	host_event = cros_ec_get_host_event(priv->ec_device);
+	if (host_event & EC_HOST_EVENT_MASK(EC_HOST_EVENT_WOV)) {
+		schedule_delayed_work(&priv->wov_copy_work, 0);
+		return NOTIFY_OK;
+	} else {
+		return NOTIFY_DONE;
+	}
+}
 
-	switch (event) {
-	case SND_SOC_DAPM_PRE_PMU:
-		dev_dbg(component->dev,
-			"%s got SND_SOC_DAPM_PRE_PMU event\n", __func__);
-		return enable_i2s(component, 1);
+static int wov_probe(struct snd_soc_component *component)
+{
+	struct cros_ec_codec_priv *priv =
+		snd_soc_component_get_drvdata(component);
+	int ret;
 
-	case SND_SOC_DAPM_PRE_PMD:
-		dev_dbg(component->dev,
-			"%s got SND_SOC_DAPM_PRE_PMD event\n", __func__);
-		return enable_i2s(component, 0);
+	mutex_init(&priv->wov_dma_lock);
+	INIT_DELAYED_WORK(&priv->wov_copy_work, wov_copy_work);
+
+	priv->wov_notifier.notifier_call = wov_host_event;
+	ret = blocking_notifier_chain_register(
+			&priv->ec_device->event_notifier, &priv->wov_notifier);
+	if (ret)
+		return ret;
+
+	if (ec_codec_capable(priv, EC_CODEC_CAP_WOV_LANG_SHM)) {
+		priv->wov_lang_shm_p = wov_map_shm(priv,
+				EC_CODEC_SHM_ID_WOV_LANG,
+				&priv->wov_lang_shm_len,
+				&priv->wov_lang_shm_type);
+		if (!priv->wov_lang_shm_p)
+			return -EFAULT;
 	}
 
-	return 0;
+	if (ec_codec_capable(priv, EC_CODEC_CAP_WOV_AUDIO_SHM)) {
+		priv->wov_audio_shm_p = wov_map_shm(priv,
+				EC_CODEC_SHM_ID_WOV_AUDIO,
+				&priv->wov_audio_shm_len,
+				&priv->wov_audio_shm_type);
+		if (!priv->wov_audio_shm_p)
+			return -EFAULT;
+	}
+
+	return dmic_probe(component);
 }
 
-/*
- * The goal of this DAPM route is to turn on/off I2S using EC
- * host command when capture stream is started/stopped.
- */
-static const struct snd_soc_dapm_widget cros_ec_codec_dapm_widgets[] = {
-	SND_SOC_DAPM_INPUT("DMIC"),
+static void wov_remove(struct snd_soc_component *component)
+{
+	struct cros_ec_codec_priv *priv =
+		snd_soc_component_get_drvdata(component);
 
-	/*
-	 * Control EC to enable/disable I2S.
-	 */
-	SND_SOC_DAPM_SUPPLY("I2S Enable", SND_SOC_NOPM,
-			    0, 0, cros_ec_i2s_enable_event,
-			    SND_SOC_DAPM_PRE_PMU | SND_SOC_DAPM_PRE_PMD),
+	blocking_notifier_chain_unregister(
+			&priv->ec_device->event_notifier, &priv->wov_notifier);
+}
 
-	SND_SOC_DAPM_AIF_OUT("I2STX", "I2S Capture", 0, SND_SOC_NOPM, 0, 0),
-};
+static int wov_pcm_open(struct snd_soc_component *component,
+			struct snd_pcm_substream *substream)
+{
+	static const struct snd_pcm_hardware hw_param = {
+		.info = SNDRV_PCM_INFO_MMAP |
+			SNDRV_PCM_INFO_INTERLEAVED |
+			SNDRV_PCM_INFO_MMAP_VALID,
+		.formats = SNDRV_PCM_FMTBIT_S16_LE,
+		.rates = SNDRV_PCM_RATE_16000,
+		.channels_min = 1,
+		.channels_max = 1,
+		.period_bytes_min = PAGE_SIZE,
+		.period_bytes_max = 0x20000 / 8,
+		.periods_min = 8,
+		.periods_max = 8,
+		.buffer_bytes_max = 0x20000,
+	};
+
+	return snd_soc_set_runtime_hwparams(substream, &hw_param);
+}
 
-static const struct snd_soc_dapm_route cros_ec_codec_dapm_routes[] = {
-	{ "I2STX", NULL, "DMIC" },
-	{ "I2STX", NULL, "I2S Enable" },
-};
+static int wov_pcm_hw_params(struct snd_soc_component *component,
+			     struct snd_pcm_substream *substream,
+			     struct snd_pcm_hw_params *hw_params)
+{
+	struct cros_ec_codec_priv *priv =
+		snd_soc_component_get_drvdata(component);
 
-/*
- * Read maximum gain from device property and set it to mixer control.
- */
-static int cros_ec_set_gain_range(struct device *dev)
+	mutex_lock(&priv->wov_dma_lock);
+	priv->wov_substream = substream;
+	priv->wov_rp = priv->wov_wp = 0;
+	priv->wov_dma_offset = 0;
+	priv->wov_burst_read = true;
+	mutex_unlock(&priv->wov_dma_lock);
+
+	return snd_pcm_lib_malloc_pages(substream, params_buffer_bytes(hw_params));
+}
+
+static int wov_pcm_hw_free(struct snd_soc_component *component,
+			   struct snd_pcm_substream *substream)
 {
-	struct soc_mixer_control *control;
-	struct cros_ec_codec_data *codec_data = dev_get_drvdata(dev);
-	int rc;
+	struct cros_ec_codec_priv *priv =
+		snd_soc_component_get_drvdata(component);
 
-	rc = device_property_read_u32(dev, "max-dmic-gain",
-				      &codec_data->max_dmic_gain);
-	if (rc)
-		return rc;
+	mutex_lock(&priv->wov_dma_lock);
+	wov_queue_dequeue(priv, wov_queue_size(priv));
+	priv->wov_substream = NULL;
+	mutex_unlock(&priv->wov_dma_lock);
 
-	control = (struct soc_mixer_control *)
-				mic_gain_control.private_value;
-	control->max = codec_data->max_dmic_gain;
-	control->platform_max = codec_data->max_dmic_gain;
+	cancel_delayed_work_sync(&priv->wov_copy_work);
 
-	return 0;
+	return snd_pcm_lib_free_pages(substream);
 }
 
-static int cros_ec_codec_probe(struct snd_soc_component *component)
+static snd_pcm_uframes_t wov_pcm_pointer(struct snd_soc_component *component,
+					 struct snd_pcm_substream *substream)
 {
-	int rc;
-
-	struct cros_ec_codec_data *codec_data =
+	struct snd_pcm_runtime *runtime = substream->runtime;
+	struct cros_ec_codec_priv *priv =
 		snd_soc_component_get_drvdata(component);
 
-	rc = cros_ec_set_gain_range(codec_data->dev);
-	if (rc)
-		return rc;
+	return bytes_to_frames(runtime, priv->wov_dma_offset);
+}
 
-	return snd_soc_add_component_controls(component, &mic_gain_control, 1);
+static int wov_pcm_new(struct snd_soc_component *component,
+		       struct snd_soc_pcm_runtime *rtd)
+{
+	snd_pcm_lib_preallocate_pages_for_all(rtd->pcm, SNDRV_DMA_TYPE_VMALLOC,
+					      NULL, 0, 0);
+	return 0;
 }
 
-static const struct snd_soc_component_driver cros_ec_component_driver = {
-	.probe			= cros_ec_codec_probe,
-	.dapm_widgets		= cros_ec_codec_dapm_widgets,
-	.num_dapm_widgets	= ARRAY_SIZE(cros_ec_codec_dapm_widgets),
-	.dapm_routes		= cros_ec_codec_dapm_routes,
-	.num_dapm_routes	= ARRAY_SIZE(cros_ec_codec_dapm_routes),
+static const struct snd_soc_component_driver wov_component_driver = {
+	.probe		= wov_probe,
+	.remove		= wov_remove,
+	.controls	= wov_controls,
+	.num_controls	= ARRAY_SIZE(wov_controls),
+	.open		= wov_pcm_open,
+	.hw_params	= wov_pcm_hw_params,
+	.hw_free	= wov_pcm_hw_free,
+	.pointer	= wov_pcm_pointer,
+	.pcm_construct	= wov_pcm_new,
 };
 
-/*
- * Platform device and platform driver fro cros-ec-codec.
- */
-static int cros_ec_codec_platform_probe(struct platform_device *pd)
+static int cros_ec_codec_platform_probe(struct platform_device *pdev)
 {
-	struct device *dev = &pd->dev;
-	struct cros_ec_device *ec_device = dev_get_drvdata(pd->dev.parent);
-	struct cros_ec_codec_data *codec_data;
+	struct device *dev = &pdev->dev;
+	struct cros_ec_device *ec_device = dev_get_drvdata(pdev->dev.parent);
+	struct cros_ec_codec_priv *priv;
+	struct ec_param_ec_codec p;
+	struct ec_response_ec_codec_get_capabilities r;
+	int ret;
+#ifdef CONFIG_OF
+	struct device_node *node;
+	struct resource res;
+	u64 ec_shm_size;
+	const __be32 *regaddr_p;
+#endif
 
-	codec_data = devm_kzalloc(dev, sizeof(struct cros_ec_codec_data),
-				  GFP_KERNEL);
-	if (!codec_data)
+	priv = devm_kzalloc(dev, sizeof(*priv), GFP_KERNEL);
+	if (!priv)
 		return -ENOMEM;
 
-	codec_data->dev = dev;
-	codec_data->ec_device = ec_device;
+#ifdef CONFIG_OF
+	regaddr_p = of_get_address(dev->of_node, 0, &ec_shm_size, NULL);
+	if (regaddr_p) {
+		priv->ec_shm_addr = of_read_number(regaddr_p, 2);
+		priv->ec_shm_len = ec_shm_size;
 
-	platform_set_drvdata(pd, codec_data);
+		dev_dbg(dev, "ec_shm_addr=%#llx len=%#x\n",
+			priv->ec_shm_addr, priv->ec_shm_len);
+	}
+
+	node = of_parse_phandle(dev->of_node, "memory-region", 0);
+	if (node) {
+		ret = of_address_to_resource(node, 0, &res);
+		if (!ret) {
+			priv->ap_shm_phys_addr = res.start;
+			priv->ap_shm_len = resource_size(&res);
+			priv->ap_shm_addr =
+				(uint64_t)(uintptr_t)devm_ioremap_wc(
+					dev, priv->ap_shm_phys_addr,
+					priv->ap_shm_len);
+			priv->ap_shm_last_alloc = priv->ap_shm_phys_addr;
+
+			dev_dbg(dev, "ap_shm_phys_addr=%#llx len=%#x\n",
+				priv->ap_shm_phys_addr, priv->ap_shm_len);
+		}
+	}
+#endif
+
+	priv->dev = dev;
+	priv->ec_device = ec_device;
+	atomic_set(&priv->dmic_probed, 0);
+
+	p.cmd = EC_CODEC_GET_CAPABILITIES;
+	ret = send_ec_host_command(priv->ec_device, EC_CMD_EC_CODEC,
+				   (uint8_t *)&p, sizeof(p),
+				   (uint8_t *)&r, sizeof(r));
+	if (ret) {
+		dev_err(dev, "failed to EC_CODEC_GET_CAPABILITIES\n");
+		return ret;
+	}
+	priv->ec_capabilities = r.capabilities;
+
+	platform_set_drvdata(pdev, priv);
+
+	ret = devm_snd_soc_register_component(dev, &i2s_rx_component_driver,
+					      &i2s_rx_dai_driver, 1);
+	if (ret)
+		return ret;
 
-	return devm_snd_soc_register_component(dev, &cros_ec_component_driver,
-					  cros_ec_dai, ARRAY_SIZE(cros_ec_dai));
+	return devm_snd_soc_register_component(dev, &wov_component_driver,
+					       &wov_dai_driver, 1);
 }
 
 #ifdef CONFIG_OF
@@ -427,7 +1049,7 @@ MODULE_DEVICE_TABLE(of, cros_ec_codec_of_match);
 
 static struct platform_driver cros_ec_codec_platform_driver = {
 	.driver = {
-		.name = DRV_NAME,
+		.name = "cros-ec-codec",
 		.of_match_table = of_match_ptr(cros_ec_codec_of_match),
 	},
 	.probe = cros_ec_codec_platform_probe,
@@ -438,4 +1060,4 @@ module_platform_driver(cros_ec_codec_platform_driver);
 MODULE_LICENSE("GPL v2");
 MODULE_DESCRIPTION("ChromeOS EC codec driver");
 MODULE_AUTHOR("Cheng-Yi Chiang <cychiang@chromium.org>");
-MODULE_ALIAS("platform:" DRV_NAME);
+MODULE_ALIAS("platform:cros-ec-codec");
diff --git a/sound/soc/codecs/cx2072x.c b/sound/soc/codecs/cx2072x.c
index 1c1ba7bea4d8..2ad00ed21bec 100644
--- a/sound/soc/codecs/cx2072x.c
+++ b/sound/soc/codecs/cx2072x.c
@@ -1507,7 +1507,7 @@ static int cx2072x_probe(struct snd_soc_component *codec)
 	regmap_multi_reg_write(cx2072x->regmap, cx2072x_reg_init,
 			       ARRAY_SIZE(cx2072x_reg_init));
 
-	/* configre PortC as input device */
+	/* configure PortC as input device */
 	regmap_update_bits(cx2072x->regmap, CX2072X_PORTC_PIN_CTRL,
 			   0x20, 0x20);
 
diff --git a/sound/soc/codecs/hdac_hda.c b/sound/soc/codecs/hdac_hda.c
index 4570f662fb48..6803d39e09a5 100644
--- a/sound/soc/codecs/hdac_hda.c
+++ b/sound/soc/codecs/hdac_hda.c
@@ -14,13 +14,11 @@
 #include <sound/pcm_params.h>
 #include <sound/soc.h>
 #include <sound/hdaudio_ext.h>
+#include <sound/hda_i915.h>
 #include <sound/hda_codec.h>
 #include <sound/hda_register.h>
-#include "hdac_hda.h"
 
-#define HDAC_ANALOG_DAI_ID		0
-#define HDAC_DIGITAL_DAI_ID		1
-#define HDAC_ALT_ANALOG_DAI_ID		2
+#include "hdac_hda.h"
 
 #define STUB_FORMATS	(SNDRV_PCM_FMTBIT_S8 | \
 			SNDRV_PCM_FMTBIT_U8 | \
@@ -32,6 +30,11 @@
 			SNDRV_PCM_FMTBIT_U32_LE | \
 			SNDRV_PCM_FMTBIT_IEC958_SUBFRAME_LE)
 
+#define STUB_HDMI_RATES	(SNDRV_PCM_RATE_32000 | SNDRV_PCM_RATE_44100 |\
+				 SNDRV_PCM_RATE_48000 | SNDRV_PCM_RATE_88200 |\
+				 SNDRV_PCM_RATE_96000 | SNDRV_PCM_RATE_176400 |\
+				 SNDRV_PCM_RATE_192000)
+
 static int hdac_hda_dai_open(struct snd_pcm_substream *substream,
 			     struct snd_soc_dai *dai);
 static void hdac_hda_dai_close(struct snd_pcm_substream *substream,
@@ -121,7 +124,46 @@ static struct snd_soc_dai_driver hdac_hda_dais[] = {
 		.formats = STUB_FORMATS,
 		.sig_bits = 24,
 	},
-}
+},
+{
+	.id = HDAC_HDMI_0_DAI_ID,
+	.name = "intel-hdmi-hifi1",
+	.ops = &hdac_hda_dai_ops,
+	.playback = {
+		.stream_name    = "hifi1",
+		.channels_min   = 1,
+		.channels_max   = 32,
+		.rates          = STUB_HDMI_RATES,
+		.formats        = STUB_FORMATS,
+		.sig_bits = 24,
+	},
+},
+{
+	.id = HDAC_HDMI_1_DAI_ID,
+	.name = "intel-hdmi-hifi2",
+	.ops = &hdac_hda_dai_ops,
+	.playback = {
+		.stream_name    = "hifi2",
+		.channels_min   = 1,
+		.channels_max   = 32,
+		.rates          = STUB_HDMI_RATES,
+		.formats        = STUB_FORMATS,
+		.sig_bits = 24,
+	},
+},
+{
+	.id = HDAC_HDMI_2_DAI_ID,
+	.name = "intel-hdmi-hifi3",
+	.ops = &hdac_hda_dai_ops,
+	.playback = {
+		.stream_name    = "hifi3",
+		.channels_min   = 1,
+		.channels_max   = 32,
+		.rates          = STUB_HDMI_RATES,
+		.formats        = STUB_FORMATS,
+		.sig_bits = 24,
+	},
+},
 
 };
 
@@ -135,10 +177,11 @@ static int hdac_hda_dai_set_tdm_slot(struct snd_soc_dai *dai,
 
 	hda_pvt = snd_soc_component_get_drvdata(component);
 	pcm = &hda_pvt->pcm[dai->id];
+
 	if (tx_mask)
-		pcm[dai->id].stream_tag[SNDRV_PCM_STREAM_PLAYBACK] = tx_mask;
+		pcm->stream_tag[SNDRV_PCM_STREAM_PLAYBACK] = tx_mask;
 	else
-		pcm[dai->id].stream_tag[SNDRV_PCM_STREAM_CAPTURE] = rx_mask;
+		pcm->stream_tag[SNDRV_PCM_STREAM_CAPTURE] = rx_mask;
 
 	return 0;
 }
@@ -278,6 +321,12 @@ static struct hda_pcm *snd_soc_find_pcm_from_dai(struct hdac_hda_priv *hda_pvt,
 	struct hda_pcm *cpcm;
 	const char *pcm_name;
 
+	/*
+	 * map DAI ID to the closest matching PCM name, using the naming
+	 * scheme used by hda-codec snd_hda_gen_build_pcms() and for
+	 * HDMI in hda_codec patch_hdmi.c)
+	 */
+
 	switch (dai->id) {
 	case HDAC_ANALOG_DAI_ID:
 		pcm_name = "Analog";
@@ -288,13 +337,22 @@ static struct hda_pcm *snd_soc_find_pcm_from_dai(struct hdac_hda_priv *hda_pvt,
 	case HDAC_ALT_ANALOG_DAI_ID:
 		pcm_name = "Alt Analog";
 		break;
+	case HDAC_HDMI_0_DAI_ID:
+		pcm_name = "HDMI 0";
+		break;
+	case HDAC_HDMI_1_DAI_ID:
+		pcm_name = "HDMI 1";
+		break;
+	case HDAC_HDMI_2_DAI_ID:
+		pcm_name = "HDMI 2";
+		break;
 	default:
 		dev_err(&hcodec->core.dev, "invalid dai id %d\n", dai->id);
 		return NULL;
 	}
 
 	list_for_each_entry(cpcm, &hcodec->pcm_list_head, list) {
-		if (strpbrk(cpcm->name, pcm_name))
+		if (strstr(cpcm->name, pcm_name))
 			return cpcm;
 	}
 
@@ -302,6 +360,18 @@ static struct hda_pcm *snd_soc_find_pcm_from_dai(struct hdac_hda_priv *hda_pvt,
 	return NULL;
 }
 
+static bool is_hdmi_codec(struct hda_codec *hcodec)
+{
+	struct hda_pcm *cpcm;
+
+	list_for_each_entry(cpcm, &hcodec->pcm_list_head, list) {
+		if (cpcm->pcm_type == HDA_PCM_TYPE_HDMI)
+			return true;
+	}
+
+	return false;
+}
+
 static int hdac_hda_codec_probe(struct snd_soc_component *component)
 {
 	struct hdac_hda_priv *hda_pvt =
@@ -322,6 +392,15 @@ static int hdac_hda_codec_probe(struct snd_soc_component *component)
 
 	snd_hdac_ext_bus_link_get(hdev->bus, hlink);
 
+	/*
+	 * Ensure any HDA display is powered at codec probe.
+	 * After snd_hda_codec_device_new(), display power is
+	 * managed by runtime PM.
+	 */
+	if (hda_pvt->need_display_power)
+		snd_hdac_display_power(hdev->bus,
+				       HDA_CODEC_IDX_CONTROLLER, true);
+
 	ret = snd_hda_codec_device_new(hcodec->bus, component->card->snd_card,
 				       hdev->addr, hcodec);
 	if (ret < 0) {
@@ -366,20 +445,31 @@ static int hdac_hda_codec_probe(struct snd_soc_component *component)
 		dev_dbg(&hdev->dev, "no patch file found\n");
 	}
 
+	/* configure codec for 1:1 PCM:DAI mapping */
+	hcodec->mst_no_extra_pcms = 1;
+
 	ret = snd_hda_codec_parse_pcms(hcodec);
 	if (ret < 0) {
 		dev_err(&hdev->dev, "unable to map pcms to dai %d\n", ret);
 		goto error;
 	}
 
-	ret = snd_hda_codec_build_controls(hcodec);
-	if (ret < 0) {
-		dev_err(&hdev->dev, "unable to create controls %d\n", ret);
-		goto error;
+	/* HDMI controls need to be created in machine drivers */
+	if (!is_hdmi_codec(hcodec)) {
+		ret = snd_hda_codec_build_controls(hcodec);
+		if (ret < 0) {
+			dev_err(&hdev->dev, "unable to create controls %d\n",
+				ret);
+			goto error;
+		}
 	}
 
 	hcodec->core.lazy_cache = true;
 
+	if (hda_pvt->need_display_power)
+		snd_hdac_display_power(hdev->bus,
+				       HDA_CODEC_IDX_CONTROLLER, false);
+
 	/*
 	 * hdac_device core already sets the state to active and calls
 	 * get_noresume. So enable runtime and set the device to suspend.
diff --git a/sound/soc/codecs/hdac_hda.h b/sound/soc/codecs/hdac_hda.h
index 6b1bd4f428e7..e145cec085b8 100644
--- a/sound/soc/codecs/hdac_hda.h
+++ b/sound/soc/codecs/hdac_hda.h
@@ -6,6 +6,16 @@
 #ifndef __HDAC_HDA_H__
 #define __HDAC_HDA_H__
 
+enum {
+	HDAC_ANALOG_DAI_ID = 0,
+	HDAC_DIGITAL_DAI_ID,
+	HDAC_ALT_ANALOG_DAI_ID,
+	HDAC_HDMI_0_DAI_ID,
+	HDAC_HDMI_1_DAI_ID,
+	HDAC_HDMI_2_DAI_ID,
+	HDAC_LAST_DAI_ID = HDAC_HDMI_2_DAI_ID,
+};
+
 struct hdac_hda_pcm {
 	int stream_tag[2];
 	unsigned int format_val[2];
@@ -13,7 +23,8 @@ struct hdac_hda_pcm {
 
 struct hdac_hda_priv {
 	struct hda_codec codec;
-	struct hdac_hda_pcm pcm[2];
+	struct hdac_hda_pcm pcm[HDAC_LAST_DAI_ID];
+	bool need_display_power;
 };
 
 #define hdac_to_hda_priv(_hdac) \
diff --git a/sound/soc/codecs/madera.h b/sound/soc/codecs/madera.h
index 1f3e8e230cf2..6d8938a3fb64 100644
--- a/sound/soc/codecs/madera.h
+++ b/sound/soc/codecs/madera.h
@@ -27,6 +27,7 @@
 #define MADERA_FLL_SRC_NONE		-1
 #define MADERA_FLL_SRC_MCLK1		0
 #define MADERA_FLL_SRC_MCLK2		1
+#define MADERA_FLL_SRC_MCLK3		2
 #define MADERA_FLL_SRC_SLIMCLK		3
 #define MADERA_FLL_SRC_FLL1		4
 #define MADERA_FLL_SRC_FLL2		5
@@ -51,6 +52,7 @@
 
 #define MADERA_CLK_SRC_MCLK1		0x0
 #define MADERA_CLK_SRC_MCLK2		0x1
+#define MADERA_CLK_SRC_MCLK3		0x2
 #define MADERA_CLK_SRC_FLL1		0x4
 #define MADERA_CLK_SRC_FLL2		0x5
 #define MADERA_CLK_SRC_FLL3		0x6
diff --git a/sound/soc/codecs/msm8916-wcd-analog.c b/sound/soc/codecs/msm8916-wcd-analog.c
index e3d311fb510e..f53235be77d9 100644
--- a/sound/soc/codecs/msm8916-wcd-analog.c
+++ b/sound/soc/codecs/msm8916-wcd-analog.c
@@ -228,6 +228,10 @@
 #define CDC_A_RX_EAR_CTL			(0xf19E)
 #define RX_EAR_CTL_SPK_VBAT_LDO_EN_MASK		BIT(0)
 #define RX_EAR_CTL_SPK_VBAT_LDO_EN_ENABLE	BIT(0)
+#define RX_EAR_CTL_PA_EAR_PA_EN_MASK		BIT(6)
+#define RX_EAR_CTL_PA_EAR_PA_EN_ENABLE		BIT(6)
+#define RX_EAR_CTL_PA_SEL_MASK			BIT(7)
+#define RX_EAR_CTL_PA_SEL			BIT(7)
 
 #define CDC_A_SPKR_DAC_CTL		(0xf1B0)
 #define SPKR_DAC_CTL_DAC_RESET_MASK	BIT(4)
@@ -312,6 +316,7 @@ static const char *const hph_text[] = { "ZERO", "Switch", };
 static const struct soc_enum hph_enum = SOC_ENUM_SINGLE_VIRT(
 					ARRAY_SIZE(hph_text), hph_text);
 
+static const struct snd_kcontrol_new ear_mux = SOC_DAPM_ENUM("EAR_S", hph_enum);
 static const struct snd_kcontrol_new hphl_mux = SOC_DAPM_ENUM("HPHL", hph_enum);
 static const struct snd_kcontrol_new hphr_mux = SOC_DAPM_ENUM("HPHR", hph_enum);
 
@@ -685,6 +690,34 @@ static int pm8916_wcd_analog_enable_spk_pa(struct snd_soc_dapm_widget *w,
 	return 0;
 }
 
+static int pm8916_wcd_analog_enable_ear_pa(struct snd_soc_dapm_widget *w,
+					    struct snd_kcontrol *kcontrol,
+					    int event)
+{
+	struct snd_soc_component *component = snd_soc_dapm_to_component(w->dapm);
+
+	switch (event) {
+	case SND_SOC_DAPM_PRE_PMU:
+		snd_soc_component_update_bits(component, CDC_A_RX_EAR_CTL,
+				    RX_EAR_CTL_PA_SEL_MASK, RX_EAR_CTL_PA_SEL);
+		break;
+	case SND_SOC_DAPM_POST_PMU:
+		snd_soc_component_update_bits(component, CDC_A_RX_EAR_CTL,
+				    RX_EAR_CTL_PA_EAR_PA_EN_MASK,
+				    RX_EAR_CTL_PA_EAR_PA_EN_ENABLE);
+		break;
+	case SND_SOC_DAPM_POST_PMD:
+		snd_soc_component_update_bits(component, CDC_A_RX_EAR_CTL,
+				    RX_EAR_CTL_PA_EAR_PA_EN_MASK, 0);
+		/* Delay to reduce ear turn off pop */
+		usleep_range(7000, 7100);
+		snd_soc_component_update_bits(component, CDC_A_RX_EAR_CTL,
+				    RX_EAR_CTL_PA_SEL_MASK, 0);
+		break;
+	}
+	return 0;
+}
+
 static const struct reg_default wcd_reg_defaults_2_0[] = {
 	{CDC_A_RX_COM_OCP_CTL, 0xD1},
 	{CDC_A_RX_COM_OCP_COUNT, 0xFF},
@@ -801,12 +834,20 @@ static const struct snd_soc_dapm_route pm8916_wcd_analog_audio_map[] = {
 	{"PDM_TX", NULL, "A_MCLK2"},
 	{"A_MCLK2", NULL, "A_MCLK"},
 
+	/* Earpiece (RX MIX1) */
+	{"EAR", NULL, "EAR_S"},
+	{"EAR_S", "Switch", "EAR PA"},
+	{"EAR PA", NULL, "RX_BIAS"},
+	{"EAR PA", NULL, "HPHL DAC"},
+	{"EAR PA", NULL, "HPHR DAC"},
+	{"EAR PA", NULL, "EAR CP"},
+
 	/* Headset (RX MIX1 and RX MIX2) */
 	{"HEADPHONE", NULL, "HPHL PA"},
 	{"HEADPHONE", NULL, "HPHR PA"},
 
-	{"HPHL PA", NULL, "EAR_HPHL_CLK"},
-	{"HPHR PA", NULL, "EAR_HPHR_CLK"},
+	{"HPHL DAC", NULL, "EAR_HPHL_CLK"},
+	{"HPHR DAC", NULL, "EAR_HPHR_CLK"},
 
 	{"CP", NULL, "NCP_CLK"},
 
@@ -847,11 +888,20 @@ static const struct snd_soc_dapm_widget pm8916_wcd_analog_dapm_widgets[] = {
 	SND_SOC_DAPM_INPUT("AMIC1"),
 	SND_SOC_DAPM_INPUT("AMIC3"),
 	SND_SOC_DAPM_INPUT("AMIC2"),
+	SND_SOC_DAPM_OUTPUT("EAR"),
 	SND_SOC_DAPM_OUTPUT("HEADPHONE"),
 
 	/* RX stuff */
 	SND_SOC_DAPM_SUPPLY("INT_LDO_H", SND_SOC_NOPM, 1, 0, NULL, 0),
 
+	SND_SOC_DAPM_PGA_E("EAR PA", SND_SOC_NOPM,
+			   0, 0, NULL, 0,
+			   pm8916_wcd_analog_enable_ear_pa,
+			   SND_SOC_DAPM_PRE_PMU | SND_SOC_DAPM_POST_PMU |
+			   SND_SOC_DAPM_PRE_PMD | SND_SOC_DAPM_POST_PMD),
+	SND_SOC_DAPM_MUX("EAR_S", SND_SOC_NOPM, 0, 0, &ear_mux),
+	SND_SOC_DAPM_SUPPLY("EAR CP", CDC_A_NCP_EN, 4, 0, NULL, 0),
+
 	SND_SOC_DAPM_PGA("HPHL PA", CDC_A_RX_HPH_CNP_EN, 5, 0, NULL, 0),
 	SND_SOC_DAPM_MUX("HPHL", SND_SOC_NOPM, 0, 0, &hphl_mux),
 	SND_SOC_DAPM_MIXER("HPHL DAC", CDC_A_RX_HPH_L_PA_DAC_CTL, 3, 0, NULL,
diff --git a/sound/soc/codecs/mt6358.c b/sound/soc/codecs/mt6358.c
index bb737fd678cc..1b830ea4f6ed 100644
--- a/sound/soc/codecs/mt6358.c
+++ b/sound/soc/codecs/mt6358.c
@@ -93,6 +93,8 @@ struct mt6358_priv {
 	int mtkaif_protocol;
 
 	struct regulator *avdd_reg;
+
+	int wov_enabled;
 };
 
 int mt6358_set_mtkaif_protocol(struct snd_soc_component *cmpnt,
@@ -464,6 +466,106 @@ static int mt6358_put_volsw(struct snd_kcontrol *kcontrol,
 	return ret;
 }
 
+static void mt6358_restore_pga(struct mt6358_priv *priv);
+
+static int mt6358_enable_wov_phase2(struct mt6358_priv *priv)
+{
+	/* analog */
+	regmap_update_bits(priv->regmap, MT6358_AUDDEC_ANA_CON13,
+			   0xffff, 0x0000);
+	regmap_update_bits(priv->regmap, MT6358_DCXO_CW14, 0xffff, 0xa2b5);
+	regmap_update_bits(priv->regmap, MT6358_AUDENC_ANA_CON1,
+			   0xffff, 0x0800);
+	mt6358_restore_pga(priv);
+
+	regmap_update_bits(priv->regmap, MT6358_DCXO_CW13, 0xffff, 0x9929);
+	regmap_update_bits(priv->regmap, MT6358_AUDENC_ANA_CON9,
+			   0xffff, 0x0025);
+	regmap_update_bits(priv->regmap, MT6358_AUDENC_ANA_CON8,
+			   0xffff, 0x0005);
+
+	/* digital */
+	regmap_update_bits(priv->regmap, MT6358_AUD_TOP_CKPDN_CON0,
+			   0xffff, 0x0000);
+	regmap_update_bits(priv->regmap, MT6358_GPIO_MODE3, 0xffff, 0x0120);
+	regmap_update_bits(priv->regmap, MT6358_AFE_VOW_CFG0, 0xffff, 0xffff);
+	regmap_update_bits(priv->regmap, MT6358_AFE_VOW_CFG1, 0xffff, 0x0200);
+	regmap_update_bits(priv->regmap, MT6358_AFE_VOW_CFG2, 0xffff, 0x2424);
+	regmap_update_bits(priv->regmap, MT6358_AFE_VOW_CFG3, 0xffff, 0xdbac);
+	regmap_update_bits(priv->regmap, MT6358_AFE_VOW_CFG4, 0xffff, 0x029e);
+	regmap_update_bits(priv->regmap, MT6358_AFE_VOW_CFG5, 0xffff, 0x0000);
+	regmap_update_bits(priv->regmap, MT6358_AFE_VOW_POSDIV_CFG0,
+			   0xffff, 0x0000);
+	regmap_update_bits(priv->regmap, MT6358_AFE_VOW_HPF_CFG0,
+			   0xffff, 0x0451);
+	regmap_update_bits(priv->regmap, MT6358_AFE_VOW_TOP, 0xffff, 0x68d1);
+
+	return 0;
+}
+
+static int mt6358_disable_wov_phase2(struct mt6358_priv *priv)
+{
+	/* digital */
+	regmap_update_bits(priv->regmap, MT6358_AFE_VOW_TOP, 0xffff, 0xc000);
+	regmap_update_bits(priv->regmap, MT6358_AFE_VOW_HPF_CFG0,
+			   0xffff, 0x0450);
+	regmap_update_bits(priv->regmap, MT6358_AFE_VOW_POSDIV_CFG0,
+			   0xffff, 0x0c00);
+	regmap_update_bits(priv->regmap, MT6358_AFE_VOW_CFG5, 0xffff, 0x0100);
+	regmap_update_bits(priv->regmap, MT6358_AFE_VOW_CFG4, 0xffff, 0x006c);
+	regmap_update_bits(priv->regmap, MT6358_AFE_VOW_CFG3, 0xffff, 0xa879);
+	regmap_update_bits(priv->regmap, MT6358_AFE_VOW_CFG2, 0xffff, 0x2323);
+	regmap_update_bits(priv->regmap, MT6358_AFE_VOW_CFG1, 0xffff, 0x0400);
+	regmap_update_bits(priv->regmap, MT6358_AFE_VOW_CFG0, 0xffff, 0x0000);
+	regmap_update_bits(priv->regmap, MT6358_GPIO_MODE3, 0xffff, 0x02d8);
+	regmap_update_bits(priv->regmap, MT6358_AUD_TOP_CKPDN_CON0,
+			   0xffff, 0x0000);
+
+	/* analog */
+	regmap_update_bits(priv->regmap, MT6358_AUDENC_ANA_CON8,
+			   0xffff, 0x0004);
+	regmap_update_bits(priv->regmap, MT6358_AUDENC_ANA_CON9,
+			   0xffff, 0x0000);
+	regmap_update_bits(priv->regmap, MT6358_DCXO_CW13, 0xffff, 0x9829);
+	regmap_update_bits(priv->regmap, MT6358_AUDENC_ANA_CON1,
+			   0xffff, 0x0000);
+	mt6358_restore_pga(priv);
+	regmap_update_bits(priv->regmap, MT6358_DCXO_CW14, 0xffff, 0xa2b5);
+	regmap_update_bits(priv->regmap, MT6358_AUDDEC_ANA_CON13,
+			   0xffff, 0x0010);
+
+	return 0;
+}
+
+static int mt6358_get_wov(struct snd_kcontrol *kcontrol,
+			  struct snd_ctl_elem_value *ucontrol)
+{
+	struct snd_soc_component *c = snd_soc_kcontrol_component(kcontrol);
+	struct mt6358_priv *priv = snd_soc_component_get_drvdata(c);
+
+	ucontrol->value.integer.value[0] = priv->wov_enabled;
+	return 0;
+}
+
+static int mt6358_put_wov(struct snd_kcontrol *kcontrol,
+			  struct snd_ctl_elem_value *ucontrol)
+{
+	struct snd_soc_component *c = snd_soc_kcontrol_component(kcontrol);
+	struct mt6358_priv *priv = snd_soc_component_get_drvdata(c);
+	int enabled = ucontrol->value.integer.value[0];
+
+	if (priv->wov_enabled != enabled) {
+		if (enabled)
+			mt6358_enable_wov_phase2(priv);
+		else
+			mt6358_disable_wov_phase2(priv);
+
+		priv->wov_enabled = enabled;
+	}
+
+	return 0;
+}
+
 static const DECLARE_TLV_DB_SCALE(playback_tlv, -1000, 100, 0);
 static const DECLARE_TLV_DB_SCALE(pga_tlv, 0, 600, 0);
 
@@ -483,6 +585,9 @@ static const struct snd_kcontrol_new mt6358_snd_controls[] = {
 			     MT6358_AUDENC_ANA_CON0, MT6358_AUDENC_ANA_CON1,
 			     8, 4, 0,
 			     snd_soc_get_volsw, mt6358_put_volsw, pga_tlv),
+
+	SOC_SINGLE_BOOL_EXT("Wake-on-Voice Phase2 Switch", 0,
+			    mt6358_get_wov, mt6358_put_wov),
 };
 
 /* MUX */
diff --git a/sound/soc/codecs/pcm3168a.c b/sound/soc/codecs/pcm3168a.c
index 88b75695fbf7..9711fab296eb 100644
--- a/sound/soc/codecs/pcm3168a.c
+++ b/sound/soc/codecs/pcm3168a.c
@@ -9,7 +9,9 @@
 
 #include <linux/clk.h>
 #include <linux/delay.h>
+#include <linux/gpio/consumer.h>
 #include <linux/module.h>
+#include <linux/of_gpio.h>
 #include <linux/pm_runtime.h>
 #include <linux/regulator/consumer.h>
 
@@ -59,9 +61,11 @@ struct pcm3168a_priv {
 	struct regulator_bulk_data supplies[PCM3168A_NUM_SUPPLIES];
 	struct regmap *regmap;
 	struct clk *scki;
+	struct gpio_desc *gpio_rst;
 	unsigned long sysclk;
 
 	struct pcm3168a_io_params io_params[2];
+	struct snd_soc_dai_driver dai_drv[2];
 };
 
 static const char *const pcm3168a_roll_off[] = { "Sharp", "Slow" };
@@ -314,6 +318,34 @@ static int pcm3168a_set_dai_sysclk(struct snd_soc_dai *dai,
 	return 0;
 }
 
+static void pcm3168a_update_fixup_pcm_stream(struct snd_soc_dai *dai)
+{
+	struct snd_soc_component *component = dai->component;
+	struct pcm3168a_priv *pcm3168a = snd_soc_component_get_drvdata(component);
+	u64 formats = SNDRV_PCM_FMTBIT_S24_3LE | SNDRV_PCM_FMTBIT_S24_LE;
+	unsigned int channel_max = dai->id == PCM3168A_DAI_DAC ? 8 : 6;
+
+	if (pcm3168a->io_params[dai->id].fmt == PCM3168A_FMT_RIGHT_J) {
+		/* S16_LE is only supported in RIGHT_J mode */
+		formats |= SNDRV_PCM_FMTBIT_S16_LE;
+
+		/*
+		 * If multi DIN/DOUT is not selected, RIGHT_J can only support
+		 * two channels (no TDM support)
+		 */
+		if (pcm3168a->io_params[dai->id].tdm_slots != 2)
+			channel_max = 2;
+	}
+
+	if (dai->id == PCM3168A_DAI_DAC) {
+		dai->driver->playback.channels_max = channel_max;
+		dai->driver->playback.formats = formats;
+	} else {
+		dai->driver->capture.channels_max = channel_max;
+		dai->driver->capture.formats = formats;
+	}
+}
+
 static int pcm3168a_set_dai_fmt(struct snd_soc_dai *dai, unsigned int format)
 {
 	struct snd_soc_component *component = dai->component;
@@ -376,6 +408,8 @@ static int pcm3168a_set_dai_fmt(struct snd_soc_dai *dai, unsigned int format)
 
 	regmap_update_bits(pcm3168a->regmap, reg, mask, fmt << shift);
 
+	pcm3168a_update_fixup_pcm_stream(dai);
+
 	return 0;
 }
 
@@ -409,6 +443,8 @@ static int pcm3168a_set_tdm_slot(struct snd_soc_dai *dai, unsigned int tx_mask,
 	else
 		io_params->tdm_mask = rx_mask;
 
+	pcm3168a_update_fixup_pcm_stream(dai);
+
 	return 0;
 }
 
@@ -530,63 +566,7 @@ static int pcm3168a_hw_params(struct snd_pcm_substream *substream,
 	return 0;
 }
 
-static int pcm3168a_startup(struct snd_pcm_substream *substream,
-			    struct snd_soc_dai *dai)
-{
-	struct snd_soc_component *component = dai->component;
-	struct pcm3168a_priv *pcm3168a = snd_soc_component_get_drvdata(component);
-	unsigned int sample_min;
-	unsigned int channel_max;
-	unsigned int channel_maxs[] = {
-		8, /* DAC */
-		6  /* ADC */
-	};
-
-	/*
-	 * Available Data Bits
-	 *
-	 * RIGHT_J : 24 / 16
-	 * LEFT_J  : 24
-	 * I2S     : 24
-	 *
-	 * TDM available
-	 *
-	 * I2S
-	 * LEFT_J
-	 */
-	switch (pcm3168a->io_params[dai->id].fmt) {
-	case PCM3168A_FMT_RIGHT_J:
-		sample_min  = 16;
-		channel_max =  2;
-		break;
-	case PCM3168A_FMT_LEFT_J:
-	case PCM3168A_FMT_I2S:
-	case PCM3168A_FMT_DSP_A:
-	case PCM3168A_FMT_DSP_B:
-		sample_min  = 24;
-		channel_max = channel_maxs[dai->id];
-		break;
-	default:
-		sample_min  = 24;
-		channel_max =  2;
-	}
-
-	snd_pcm_hw_constraint_minmax(substream->runtime,
-				     SNDRV_PCM_HW_PARAM_SAMPLE_BITS,
-				     sample_min, 32);
-
-	/* Allow all channels in multi DIN/DOUT mode */
-	if (pcm3168a->io_params[dai->id].tdm_slots == 2)
-		channel_max = channel_maxs[dai->id];
-
-	snd_pcm_hw_constraint_minmax(substream->runtime,
-				     SNDRV_PCM_HW_PARAM_CHANNELS,
-				     2, channel_max);
-
-	return 0;
-}
 static const struct snd_soc_dai_ops pcm3168a_dai_ops = {
-	.startup	= pcm3168a_startup,
 	.set_fmt	= pcm3168a_set_dai_fmt,
 	.set_sysclk	= pcm3168a_set_dai_sysclk,
 	.hw_params	= pcm3168a_hw_params,
@@ -666,6 +646,7 @@ static bool pcm3168a_readable_register(struct device *dev, unsigned int reg)
 static bool pcm3168a_volatile_register(struct device *dev, unsigned int reg)
 {
 	switch (reg) {
+	case PCM3168A_RST_SMODE:
 	case PCM3168A_DAC_ZERO:
 	case PCM3168A_ADC_OV:
 		return true;
@@ -725,6 +706,25 @@ int pcm3168a_probe(struct device *dev, struct regmap *regmap)
 
 	dev_set_drvdata(dev, pcm3168a);
 
+	/*
+	 * Request the reset (connected to RST pin) gpio line as non exclusive
+	 * as the same reset line might be connected to multiple pcm3168a codec
+	 *
+	 * The RST is low active, we want the GPIO line to be high initially, so
+	 * request the initial level to LOW which in practice means DEASSERTED:
+	 * The deasserted level of GPIO_ACTIVE_LOW is HIGH.
+	 */
+	pcm3168a->gpio_rst = devm_gpiod_get_optional(dev, "reset",
+						GPIOD_OUT_LOW |
+						GPIOD_FLAGS_BIT_NONEXCLUSIVE);
+	if (IS_ERR(pcm3168a->gpio_rst)) {
+		ret = PTR_ERR(pcm3168a->gpio_rst);
+		if (ret != -EPROBE_DEFER )
+			dev_err(dev, "failed to acquire RST gpio: %d\n", ret);
+
+		return ret;
+	}
+
 	pcm3168a->scki = devm_clk_get(dev, "scki");
 	if (IS_ERR(pcm3168a->scki)) {
 		ret = PTR_ERR(pcm3168a->scki);
@@ -766,18 +766,28 @@ int pcm3168a_probe(struct device *dev, struct regmap *regmap)
 		goto err_regulator;
 	}
 
-	ret = pcm3168a_reset(pcm3168a);
-	if (ret) {
-		dev_err(dev, "Failed to reset device: %d\n", ret);
-		goto err_regulator;
+	if (pcm3168a->gpio_rst) {
+		/*
+		 * The device is taken out from reset via GPIO line, wait for
+		 * 3846 SCKI clock cycles for the internal reset de-assertion
+		 */
+		msleep(DIV_ROUND_UP(3846 * 1000, pcm3168a->sysclk));
+	} else {
+		ret = pcm3168a_reset(pcm3168a);
+		if (ret) {
+			dev_err(dev, "Failed to reset device: %d\n", ret);
+			goto err_regulator;
+		}
 	}
 
 	pm_runtime_set_active(dev);
 	pm_runtime_enable(dev);
 	pm_runtime_idle(dev);
 
-	ret = devm_snd_soc_register_component(dev, &pcm3168a_driver, pcm3168a_dais,
-			ARRAY_SIZE(pcm3168a_dais));
+	memcpy(pcm3168a->dai_drv, pcm3168a_dais, sizeof(pcm3168a->dai_drv));
+	ret = devm_snd_soc_register_component(dev, &pcm3168a_driver,
+					      pcm3168a->dai_drv,
+					      ARRAY_SIZE(pcm3168a->dai_drv));
 	if (ret) {
 		dev_err(dev, "failed to register component: %d\n", ret);
 		goto err_regulator;
@@ -806,6 +816,15 @@ static void pcm3168a_disable(struct device *dev)
 
 void pcm3168a_remove(struct device *dev)
 {
+	struct pcm3168a_priv *pcm3168a = dev_get_drvdata(dev);
+
+	/*
+	 * The RST is low active, we want the GPIO line to be low when the
+	 * driver is removed, so set level to 1 which in practice means
+	 * ASSERTED:
+	 * The asserted level of GPIO_ACTIVE_LOW is LOW.
+	 */
+	gpiod_set_value_cansleep(pcm3168a->gpio_rst, 1);
 	pm_runtime_disable(dev);
 #ifndef CONFIG_PM
 	pcm3168a_disable(dev);
diff --git a/sound/soc/codecs/rt1011.c b/sound/soc/codecs/rt1011.c
index be1e276e3631..2552073e54ce 100644
--- a/sound/soc/codecs/rt1011.c
+++ b/sound/soc/codecs/rt1011.c
@@ -61,7 +61,6 @@ static const struct reg_sequence init_list[] = {
 	{ RT1011_DAC_SET_1, 0xe702 },
 	{ RT1011_DAC_SET_3, 0x2004 },
 };
-#define RT1011_INIT_REG_LEN ARRAY_SIZE(init_list)
 
 static const struct reg_default rt1011_reg[] = {
 	{0x0000, 0x0000},
@@ -684,7 +683,8 @@ static int rt1011_reg_init(struct snd_soc_component *component)
 {
 	struct rt1011_priv *rt1011 = snd_soc_component_get_drvdata(component);
 
-	regmap_multi_reg_write(rt1011->regmap, init_list, RT1011_INIT_REG_LEN);
+	regmap_multi_reg_write(rt1011->regmap,
+		init_list, ARRAY_SIZE(init_list));
 	return 0;
 }
 
@@ -989,7 +989,7 @@ static SOC_ENUM_SINGLE_DECL(rt1011_din_source_enum, RT1011_CROSS_BQ_SET_1, 5,
 
 static const char * const rt1011_tdm_data_out_select[] = {
 	"TDM_O_LR", "BQ1", "DVOL", "BQ10", "ALC", "DMIX", "ADC_SRC_LR",
-	"ADC_O_LR",	"ADC_MONO", "RSPK_BPF_LR", "DMIX_ADD", "ENVELOPE_FS",
+	"ADC_O_LR", "ADC_MONO", "RSPK_BPF_LR", "DMIX_ADD", "ENVELOPE_FS",
 	"SEP_O_GAIN", "ALC_BK_GAIN", "STP_V_C", "DMIX_ABST"
 };
 
@@ -1002,7 +1002,7 @@ static SOC_ENUM_SINGLE_DECL(rt1011_tdm2_l_dac1_enum, RT1011_TDM2_SET_4, 12,
 	rt1011_tdm_l_ch_data_select);
 
 static SOC_ENUM_SINGLE_DECL(rt1011_tdm1_adc1_dat_enum,
-	RT1011_ADCDAT_OUT_SOURCE, 0,	rt1011_tdm_data_out_select);
+	RT1011_ADCDAT_OUT_SOURCE, 0, rt1011_tdm_data_out_select);
 static SOC_ENUM_SINGLE_DECL(rt1011_tdm1_adc1_loc_enum, RT1011_TDM1_SET_2, 0,
 	rt1011_tdm_l_ch_data_select);
 
@@ -1024,9 +1024,9 @@ static const char * const rt1011_tdm_adc_swap_select[] = {
 	"L/R", "R/L", "L/L", "R/R"
 };
 
-static SOC_ENUM_SINGLE_DECL(rt1011_tdm_adc1_1_enum,	RT1011_TDM1_SET_3, 6,
+static SOC_ENUM_SINGLE_DECL(rt1011_tdm_adc1_1_enum, RT1011_TDM1_SET_3, 6,
 	rt1011_tdm_adc_swap_select);
-static SOC_ENUM_SINGLE_DECL(rt1011_tdm_adc2_1_enum,	RT1011_TDM1_SET_3, 4,
+static SOC_ENUM_SINGLE_DECL(rt1011_tdm_adc2_1_enum, RT1011_TDM1_SET_3, 4,
 	rt1011_tdm_adc_swap_select);
 
 static void rt1011_reset(struct regmap *regmap)
@@ -1092,9 +1092,9 @@ static bool rt1011_validate_bq_drc_coeff(unsigned short reg)
 {
 	if ((reg == RT1011_DAC_SET_1) |
 		(reg >= RT1011_ADC_SET && reg <= RT1011_ADC_SET_1) |
-		(reg == RT1011_ADC_SET_4) |	(reg == RT1011_ADC_SET_5) |
+		(reg == RT1011_ADC_SET_4) | (reg == RT1011_ADC_SET_5) |
 		(reg == RT1011_MIXER_1) |
-		(reg == RT1011_A_TIMING_1) |	(reg >= RT1011_POWER_7 &&
+		(reg == RT1011_A_TIMING_1) | (reg >= RT1011_POWER_7 &&
 		reg <= RT1011_POWER_8) |
 		(reg == RT1011_CLASS_D_POS) | (reg == RT1011_ANALOG_CTRL) |
 		(reg >= RT1011_SPK_TEMP_PROTECT_0 &&
@@ -1163,9 +1163,6 @@ static int rt1011_bq_drc_coeff_put(struct snd_kcontrol *kcontrol,
 		(struct rt1011_bq_drc_params *)ucontrol->value.integer.value;
 	unsigned int i, mode_idx = 0;
 
-	if (!component->card->instantiated)
-		return 0;
-
 	if (strstr(ucontrol->id.name, "AdvanceMode Initial Set"))
 		mode_idx = RT1011_ADVMODE_INITIAL_SET;
 	else if (strstr(ucontrol->id.name, "AdvanceMode SEP BQ Coeff"))
@@ -1236,9 +1233,6 @@ static int rt1011_r0_cali_put(struct snd_kcontrol *kcontrol,
 	struct snd_soc_component *component = snd_kcontrol_chip(kcontrol);
 	struct rt1011_priv *rt1011 = snd_soc_component_get_drvdata(component);
 
-	if (!component->card->instantiated)
-		return 0;
-
 	rt1011->cali_done = 0;
 	if (snd_soc_component_get_bias_level(component) == SND_SOC_BIAS_OFF &&
 		ucontrol->value.integer.value[0])
@@ -1284,9 +1278,6 @@ static int rt1011_r0_load_mode_put(struct snd_kcontrol *kcontrol,
 	if (ucontrol->value.integer.value[0] == rt1011->r0_reg)
 		return 0;
 
-	if (!component->card->instantiated)
-		return 0;
-
 	if (ucontrol->value.integer.value[0] == 0)
 		return -EINVAL;
 
@@ -1298,7 +1289,7 @@ static int rt1011_r0_load_mode_put(struct snd_kcontrol *kcontrol,
 		r0_integer = format / rt1011->r0_reg / 128;
 		r0_factor = ((format / rt1011->r0_reg * 100) / 128)
 						- (r0_integer * 100);
-		dev_info(dev,	"New r0 resistance about %d.%02d ohm, reg=0x%X\n",
+		dev_info(dev, "New r0 resistance about %d.%02d ohm, reg=0x%X\n",
 			r0_integer, r0_factor, rt1011->r0_reg);
 
 		if (rt1011->r0_reg)
@@ -1640,6 +1631,7 @@ static int rt1011_set_dai_fmt(struct snd_soc_dai *dai, unsigned int fmt)
 		break;
 	default:
 		ret = -EINVAL;
+		goto _set_fmt_err_;
 	}
 
 	switch (fmt & SND_SOC_DAIFMT_INV_MASK) {
@@ -1650,6 +1642,7 @@ static int rt1011_set_dai_fmt(struct snd_soc_dai *dai, unsigned int fmt)
 		break;
 	default:
 		ret = -EINVAL;
+		goto _set_fmt_err_;
 	}
 
 	switch (fmt & SND_SOC_DAIFMT_FORMAT_MASK) {
@@ -1666,6 +1659,7 @@ static int rt1011_set_dai_fmt(struct snd_soc_dai *dai, unsigned int fmt)
 		break;
 	default:
 		ret = -EINVAL;
+		goto _set_fmt_err_;
 	}
 
 	switch (dai->id) {
@@ -1683,6 +1677,7 @@ static int rt1011_set_dai_fmt(struct snd_soc_dai *dai, unsigned int fmt)
 		ret = -EINVAL;
 	}
 
+_set_fmt_err_:
 	snd_soc_dapm_mutex_unlock(dapm);
 	return ret;
 }
@@ -1778,7 +1773,8 @@ static int rt1011_set_component_pll(struct snd_soc_component *component,
 
 	ret = rl6231_pll_calc(freq_in, freq_out, &pll_code);
 	if (ret < 0) {
-		dev_err(component->dev, "Unsupport input clock %d\n", freq_in);
+		dev_err(component->dev, "Unsupported input clock %d\n",
+			freq_in);
 		return ret;
 	}
 
@@ -1805,8 +1801,8 @@ static int rt1011_set_tdm_slot(struct snd_soc_dai *dai,
 	struct snd_soc_component *component = dai->component;
 	struct snd_soc_dapm_context *dapm =
 		snd_soc_component_get_dapm(component);
-	unsigned int val = 0, tdm_en = 0;
-	int ret = 0;
+	unsigned int val = 0, tdm_en = 0, rx_slotnum, tx_slotnum;
+	int ret = 0, first_bit, last_bit;
 
 	snd_soc_dapm_mutex_lock(dapm);
 	if (rx_mask || tx_mask)
@@ -1829,6 +1825,7 @@ static int rt1011_set_tdm_slot(struct snd_soc_dai *dai,
 		break;
 	default:
 		ret = -EINVAL;
+		goto _set_tdm_err_;
 	}
 
 	switch (slot_width) {
@@ -1848,22 +1845,153 @@ static int rt1011_set_tdm_slot(struct snd_soc_dai *dai,
 		break;
 	default:
 		ret = -EINVAL;
+		goto _set_tdm_err_;
+	}
+
+	/* Rx slot configuration */
+	rx_slotnum = hweight_long(rx_mask);
+	first_bit = find_next_bit((unsigned long *)&rx_mask, 32, 0);
+	if (rx_slotnum > 1 || rx_slotnum == 0) {
+		ret = -EINVAL;
+		dev_dbg(component->dev, "too many rx slots or zero slot\n");
+		goto _set_tdm_err_;
+	}
+
+	switch (first_bit) {
+	case 0:
+	case 2:
+	case 4:
+	case 6:
+		snd_soc_component_update_bits(component,
+			RT1011_CROSS_BQ_SET_1, RT1011_MONO_LR_SEL_MASK,
+			RT1011_MONO_L_CHANNEL);
+		snd_soc_component_update_bits(component,
+			RT1011_TDM1_SET_4,
+			RT1011_TDM_I2S_TX_L_DAC1_1_MASK |
+			RT1011_TDM_I2S_TX_R_DAC1_1_MASK,
+			(first_bit << RT1011_TDM_I2S_TX_L_DAC1_1_SFT) |
+			((first_bit+1) << RT1011_TDM_I2S_TX_R_DAC1_1_SFT));
+		break;
+	case 1:
+	case 3:
+	case 5:
+	case 7:
+		snd_soc_component_update_bits(component,
+			RT1011_CROSS_BQ_SET_1, RT1011_MONO_LR_SEL_MASK,
+			RT1011_MONO_R_CHANNEL);
+		snd_soc_component_update_bits(component,
+			RT1011_TDM1_SET_4,
+			RT1011_TDM_I2S_TX_L_DAC1_1_MASK |
+			RT1011_TDM_I2S_TX_R_DAC1_1_MASK,
+			((first_bit-1) << RT1011_TDM_I2S_TX_L_DAC1_1_SFT) |
+			(first_bit << RT1011_TDM_I2S_TX_R_DAC1_1_SFT));
+		break;
+	default:
+		ret = -EINVAL;
+		goto _set_tdm_err_;
+	}
+
+	/* Tx slot configuration */
+	tx_slotnum = hweight_long(tx_mask);
+	first_bit = find_next_bit((unsigned long *)&tx_mask, 32, 0);
+	last_bit = find_last_bit((unsigned long *)&tx_mask, 32);
+	if (tx_slotnum > 2 || (last_bit-first_bit) > 1) {
+		ret = -EINVAL;
+		dev_dbg(component->dev, "too many tx slots or tx slot location error\n");
+		goto _set_tdm_err_;
+	}
+
+	if (tx_slotnum == 1) {
+		snd_soc_component_update_bits(component, RT1011_TDM1_SET_2,
+			RT1011_TDM_I2S_DOCK_ADCDAT_LEN_1_MASK |
+			RT1011_TDM_ADCDAT1_DATA_LOCATION, first_bit);
+		switch (first_bit) {
+		case 1:
+			snd_soc_component_update_bits(component,
+				RT1011_TDM1_SET_3,
+				RT1011_TDM_I2S_RX_ADC1_1_MASK,
+				RT1011_TDM_I2S_RX_ADC1_1_LL);
+			break;
+		case 3:
+			snd_soc_component_update_bits(component,
+				RT1011_TDM1_SET_3,
+				RT1011_TDM_I2S_RX_ADC2_1_MASK,
+				RT1011_TDM_I2S_RX_ADC2_1_LL);
+			break;
+		case 5:
+			snd_soc_component_update_bits(component,
+				RT1011_TDM1_SET_3,
+				RT1011_TDM_I2S_RX_ADC3_1_MASK,
+				RT1011_TDM_I2S_RX_ADC3_1_LL);
+			break;
+		case 7:
+			snd_soc_component_update_bits(component,
+				RT1011_TDM1_SET_3,
+				RT1011_TDM_I2S_RX_ADC4_1_MASK,
+				RT1011_TDM_I2S_RX_ADC4_1_LL);
+			break;
+		case 0:
+			snd_soc_component_update_bits(component,
+				RT1011_TDM1_SET_3,
+				RT1011_TDM_I2S_RX_ADC1_1_MASK, 0);
+			break;
+		case 2:
+			snd_soc_component_update_bits(component,
+				RT1011_TDM1_SET_3,
+				RT1011_TDM_I2S_RX_ADC2_1_MASK, 0);
+			break;
+		case 4:
+			snd_soc_component_update_bits(component,
+				RT1011_TDM1_SET_3,
+				RT1011_TDM_I2S_RX_ADC3_1_MASK, 0);
+			break;
+		case 6:
+			snd_soc_component_update_bits(component,
+				RT1011_TDM1_SET_3,
+				RT1011_TDM_I2S_RX_ADC4_1_MASK, 0);
+			break;
+		default:
+			ret = -EINVAL;
+			dev_dbg(component->dev,
+				"tx slot location error\n");
+			goto _set_tdm_err_;
+		}
+	} else if (tx_slotnum == 2) {
+		switch (first_bit) {
+		case 0:
+		case 2:
+		case 4:
+		case 6:
+			snd_soc_component_update_bits(component,
+				RT1011_TDM1_SET_2,
+				RT1011_TDM_I2S_DOCK_ADCDAT_LEN_1_MASK |
+				RT1011_TDM_ADCDAT1_DATA_LOCATION,
+				RT1011_TDM_I2S_DOCK_ADCDAT_2CH | first_bit);
+			break;
+		default:
+			ret = -EINVAL;
+			dev_dbg(component->dev,
+				"tx slot location should be paired and start from slot0/2/4/6\n");
+			goto _set_tdm_err_;
+		}
 	}
 
 	snd_soc_component_update_bits(component, RT1011_TDM1_SET_1,
 		RT1011_I2S_CH_TX_MASK | RT1011_I2S_CH_RX_MASK |
-		RT1011_I2S_CH_TX_LEN_MASK |	RT1011_I2S_CH_RX_LEN_MASK, val);
+		RT1011_I2S_CH_TX_LEN_MASK | RT1011_I2S_CH_RX_LEN_MASK, val);
 	snd_soc_component_update_bits(component, RT1011_TDM2_SET_1,
 		RT1011_I2S_CH_TX_MASK | RT1011_I2S_CH_RX_MASK |
-		RT1011_I2S_CH_TX_LEN_MASK |	RT1011_I2S_CH_RX_LEN_MASK, val);
+		RT1011_I2S_CH_TX_LEN_MASK | RT1011_I2S_CH_RX_LEN_MASK, val);
 	snd_soc_component_update_bits(component, RT1011_TDM1_SET_2,
-		RT1011_TDM_I2S_DOCK_EN_1_MASK,	tdm_en);
+		RT1011_TDM_I2S_DOCK_EN_1_MASK, tdm_en);
 	snd_soc_component_update_bits(component, RT1011_TDM2_SET_2,
-		RT1011_TDM_I2S_DOCK_EN_2_MASK,	tdm_en);
-	snd_soc_component_update_bits(component, RT1011_TDM_TOTAL_SET,
-		RT1011_ADCDAT1_PIN_CONFIG | RT1011_ADCDAT2_PIN_CONFIG,
-		RT1011_ADCDAT1_OUTPUT | RT1011_ADCDAT2_OUTPUT);
+		RT1011_TDM_I2S_DOCK_EN_2_MASK, tdm_en);
+	if (tx_slotnum)
+		snd_soc_component_update_bits(component, RT1011_TDM_TOTAL_SET,
+			RT1011_ADCDAT1_PIN_CONFIG | RT1011_ADCDAT2_PIN_CONFIG,
+			RT1011_ADCDAT1_OUTPUT | RT1011_ADCDAT2_OUTPUT);
 
+_set_tdm_err_:
 	snd_soc_dapm_mutex_unlock(dapm);
 	return ret;
 }
@@ -1982,7 +2110,7 @@ static const struct snd_soc_component_driver soc_component_dev_rt1011 = {
 	.remove = rt1011_remove,
 	.suspend = rt1011_suspend,
 	.resume = rt1011_resume,
-	.set_bias_level		= rt1011_set_bias_level,
+	.set_bias_level = rt1011_set_bias_level,
 	.controls = rt1011_snd_controls,
 	.num_controls = ARRAY_SIZE(rt1011_snd_controls),
 	.dapm_widgets = rt1011_dapm_widgets,
@@ -1991,9 +2119,9 @@ static const struct snd_soc_component_driver soc_component_dev_rt1011 = {
 	.num_dapm_routes = ARRAY_SIZE(rt1011_dapm_routes),
 	.set_sysclk = rt1011_set_component_sysclk,
 	.set_pll = rt1011_set_component_pll,
-	.use_pmdown_time	= 1,
-	.endianness		= 1,
-	.non_legacy_dai_naming	= 1,
+	.use_pmdown_time = 1,
+	.endianness = 1,
+	.non_legacy_dai_naming = 1,
 };
 
 static const struct regmap_config rt1011_regmap = {
@@ -2095,17 +2223,17 @@ static int rt1011_calibrate(struct rt1011_priv *rt1011, unsigned char cali_flag)
 	dc_offset = value << 16;
 	regmap_read(rt1011->regmap, RT1011_EFUSE_ADC_OFFSET_15_0, &value);
 	dc_offset |= (value & 0xffff);
-	dev_info(dev,	"ADC offset=0x%x\n", dc_offset);
+	dev_info(dev, "ADC offset=0x%x\n", dc_offset);
 	regmap_read(rt1011->regmap, RT1011_EFUSE_DAC_OFFSET_G0_20_16, &value);
 	dc_offset = value << 16;
 	regmap_read(rt1011->regmap, RT1011_EFUSE_DAC_OFFSET_G0_15_0, &value);
 	dc_offset |= (value & 0xffff);
-	dev_info(dev,	"Gain0 offset=0x%x\n", dc_offset);
+	dev_info(dev, "Gain0 offset=0x%x\n", dc_offset);
 	regmap_read(rt1011->regmap, RT1011_EFUSE_DAC_OFFSET_G1_20_16, &value);
 	dc_offset = value << 16;
 	regmap_read(rt1011->regmap, RT1011_EFUSE_DAC_OFFSET_G1_15_0, &value);
 	dc_offset |= (value & 0xffff);
-	dev_info(dev,	"Gain1 offset=0x%x\n", dc_offset);
+	dev_info(dev, "Gain1 offset=0x%x\n", dc_offset);
 
 
 	if (cali_flag) {
@@ -2125,7 +2253,7 @@ static int rt1011_calibrate(struct rt1011_priv *rt1011, unsigned char cali_flag)
 		while (count < chk_cnt) {
 			msleep(100);
 			regmap_read(rt1011->regmap,
-				RT1011_INIT_RECIPROCAL_SYN_24_16,	&value);
+				RT1011_INIT_RECIPROCAL_SYN_24_16, &value);
 			r0[count%3] = value << 16;
 			regmap_read(rt1011->regmap,
 				RT1011_INIT_RECIPROCAL_SYN_15_0, &value);
@@ -2140,7 +2268,7 @@ static int rt1011_calibrate(struct rt1011_priv *rt1011, unsigned char cali_flag)
 				break;
 		}
 		if (count > chk_cnt) {
-			dev_err(dev,	"Calibrate R0 Failure\n");
+			dev_err(dev, "Calibrate R0 Failure\n");
 			ret = -EAGAIN;
 		} else {
 			format = 2147483648U; /* 2^24 * 128 */
@@ -2149,7 +2277,7 @@ static int rt1011_calibrate(struct rt1011_priv *rt1011, unsigned char cali_flag)
 							- (r0_integer * 100);
 			rt1011->r0_reg = r0[0];
 			rt1011->cali_done = 1;
-			dev_info(dev,	"r0 resistance about %d.%02d ohm, reg=0x%X\n",
+			dev_info(dev, "r0 resistance about %d.%02d ohm, reg=0x%X\n",
 				r0_integer, r0_factor, r0[0]);
 		}
 	}
@@ -2196,8 +2324,12 @@ static void rt1011_calibration_work(struct work_struct *work)
 	struct rt1011_priv *rt1011 =
 		container_of(work, struct rt1011_priv, cali_work);
 	struct snd_soc_component *component = rt1011->component;
+	unsigned int r0_integer, r0_factor, format;
 
-	rt1011_calibrate(rt1011, 1);
+	if (rt1011->r0_calib)
+		rt1011_calibrate(rt1011, 0);
+	else
+		rt1011_calibrate(rt1011, 1);
 
 	/*
 	 * This flag should reset after booting.
@@ -2208,6 +2340,40 @@ static void rt1011_calibration_work(struct work_struct *work)
 
 	/* initial */
 	rt1011_reg_init(component);
+
+	/* Apply temperature and calibration data from device property */
+	if (rt1011->temperature_calib <= 0xff &&
+		rt1011->temperature_calib > 0) {
+		snd_soc_component_update_bits(component,
+			RT1011_STP_INITIAL_RESISTANCE_TEMP, 0x3ff,
+			(rt1011->temperature_calib << 2));
+	}
+
+	if (rt1011->r0_calib) {
+		rt1011->r0_reg = rt1011->r0_calib;
+
+		format = 2147483648U; /* 2^24 * 128 */
+		r0_integer = format / rt1011->r0_reg / 128;
+		r0_factor = ((format / rt1011->r0_reg * 100) / 128)
+						- (r0_integer * 100);
+		dev_info(component->dev, "DP r0 resistance about %d.%02d ohm, reg=0x%X\n",
+			r0_integer, r0_factor, rt1011->r0_reg);
+
+		rt1011_r0_load(rt1011);
+	}
+}
+
+static int rt1011_parse_dp(struct rt1011_priv *rt1011, struct device *dev)
+{
+	device_property_read_u32(dev, "realtek,temperature_calib",
+		&rt1011->temperature_calib);
+	device_property_read_u32(dev, "realtek,r0_calib",
+		&rt1011->r0_calib);
+
+	dev_dbg(dev, "%s: r0_calib: 0x%x, temperature_calib: 0x%x",
+		__func__, rt1011->r0_calib, rt1011->temperature_calib);
+
+	return 0;
 }
 
 static int rt1011_i2c_probe(struct i2c_client *i2c,
@@ -2219,11 +2385,13 @@ static int rt1011_i2c_probe(struct i2c_client *i2c,
 
 	rt1011 = devm_kzalloc(&i2c->dev, sizeof(struct rt1011_priv),
 				GFP_KERNEL);
-	if (rt1011 == NULL)
+	if (!rt1011)
 		return -ENOMEM;
 
 	i2c_set_clientdata(i2c, rt1011);
 
+	rt1011_parse_dp(rt1011, &i2c->dev);
+
 	rt1011->regmap = devm_regmap_init_i2c(i2c, &rt1011_regmap);
 	if (IS_ERR(rt1011->regmap)) {
 		ret = PTR_ERR(rt1011->regmap);
@@ -2254,7 +2422,6 @@ static void rt1011_i2c_shutdown(struct i2c_client *client)
 	rt1011_reset(rt1011->regmap);
 }
 
-
 static struct i2c_driver rt1011_i2c_driver = {
 	.driver = {
 		.name = "rt1011",
diff --git a/sound/soc/codecs/rt1011.h b/sound/soc/codecs/rt1011.h
index 2d65983f3d0f..68fadc15fa8c 100644
--- a/sound/soc/codecs/rt1011.h
+++ b/sound/soc/codecs/rt1011.h
@@ -460,6 +460,23 @@
 #define RT1011_TDM_I2S_DOCK_EN_1_MASK			(0x1 << 3)
 #define RT1011_TDM_I2S_DOCK_EN_1_SFT			3
 #define RT1011_TDM_I2S_DOCK_EN_1		(0x1 << 3)
+#define RT1011_TDM_ADCDAT1_DATA_LOCATION			(0x7 << 0)
+
+/* TDM1 Setting-3 (0x0118) */
+#define RT1011_TDM_I2S_RX_ADC1_1_MASK			(0x3 << 6)
+#define RT1011_TDM_I2S_RX_ADC2_1_MASK			(0x3 << 4)
+#define RT1011_TDM_I2S_RX_ADC3_1_MASK			(0x3 << 2)
+#define RT1011_TDM_I2S_RX_ADC4_1_MASK			(0x3 << 0)
+#define RT1011_TDM_I2S_RX_ADC1_1_LL			(0x2 << 6)
+#define RT1011_TDM_I2S_RX_ADC2_1_LL			(0x2 << 4)
+#define RT1011_TDM_I2S_RX_ADC3_1_LL			(0x2 << 2)
+#define RT1011_TDM_I2S_RX_ADC4_1_LL			(0x2 << 0)
+
+/* TDM1 Setting-4 (0x011a) */
+#define RT1011_TDM_I2S_TX_L_DAC1_1_MASK			(0x7 << 12)
+#define RT1011_TDM_I2S_TX_R_DAC1_1_MASK			(0x7 << 8)
+#define RT1011_TDM_I2S_TX_L_DAC1_1_SFT 12
+#define RT1011_TDM_I2S_TX_R_DAC1_1_SFT 8
 
 /* TDM2 Setting-2 (0x0120) */
 #define RT1011_TDM_I2S_DOCK_ADCDAT_LEN_2_MASK			(0x7 << 13)
@@ -585,6 +602,12 @@
 #define RT1011_STP_T0_EN_BIT		6
 #define RT1011_STP_T0_EN		(0x1 << 6)
 
+/* Cross Biquad Setting-1 (0x0702) */
+#define RT1011_MONO_LR_SEL_MASK			(0x3 << 5)
+#define RT1011_MONO_L_CHANNEL			(0x0 << 5)
+#define RT1011_MONO_R_CHANNEL			(0x1 << 5)
+#define RT1011_MONO_LR_MIX_CHANNEL			(0x2 << 5)
+
 /* ClassD Internal Setting-1 (0x1300) */
 #define RT1011_DRIVER_READY_SPK			(0x1 << 12)
 #define RT1011_DRIVER_READY_SPK_BIT		12
@@ -667,6 +690,7 @@ struct rt1011_priv {
 
 	int bq_drc_set;
 	unsigned int r0_reg, cali_done;
+	unsigned int r0_calib, temperature_calib;
 	int recv_spk_mode;
 };
 
diff --git a/sound/soc/codecs/rt5514-spi.c b/sound/soc/codecs/rt5514-spi.c
index 892ea406a69b..f1b7b947ecbd 100644
--- a/sound/soc/codecs/rt5514-spi.c
+++ b/sound/soc/codecs/rt5514-spi.c
@@ -201,26 +201,25 @@ static irqreturn_t rt5514_spi_irq(int irq, void *data)
 }
 
 /* PCM for streaming audio from the DSP buffer */
-static int rt5514_spi_pcm_open(struct snd_pcm_substream *substream)
+static int rt5514_spi_pcm_open(struct snd_soc_component *component,
+			       struct snd_pcm_substream *substream)
 {
 	snd_soc_set_runtime_hwparams(substream, &rt5514_spi_pcm_hardware);
 
 	return 0;
 }
 
-static int rt5514_spi_hw_params(struct snd_pcm_substream *substream,
-			       struct snd_pcm_hw_params *hw_params)
+static int rt5514_spi_hw_params(struct snd_soc_component *component,
+				struct snd_pcm_substream *substream,
+				struct snd_pcm_hw_params *hw_params)
 {
-	struct snd_soc_pcm_runtime *rtd = substream->private_data;
-	struct snd_soc_component *component = snd_soc_rtdcom_lookup(rtd, DRV_NAME);
 	struct rt5514_dsp *rt5514_dsp =
 		snd_soc_component_get_drvdata(component);
 	int ret;
 	u8 buf[8];
 
 	mutex_lock(&rt5514_dsp->dma_lock);
-	ret = snd_pcm_lib_alloc_vmalloc_buffer(substream,
-			params_buffer_bytes(hw_params));
+	ret = snd_pcm_lib_malloc_pages(substream, params_buffer_bytes(hw_params));
 	rt5514_dsp->substream = substream;
 	rt5514_dsp->dma_offset = 0;
 
@@ -234,10 +233,9 @@ static int rt5514_spi_hw_params(struct snd_pcm_substream *substream,
 	return ret;
 }
 
-static int rt5514_spi_hw_free(struct snd_pcm_substream *substream)
+static int rt5514_spi_hw_free(struct snd_soc_component *component,
+			      struct snd_pcm_substream *substream)
 {
-	struct snd_soc_pcm_runtime *rtd = substream->private_data;
-	struct snd_soc_component *component = snd_soc_rtdcom_lookup(rtd, DRV_NAME);
 	struct rt5514_dsp *rt5514_dsp =
 		snd_soc_component_get_drvdata(component);
 
@@ -247,28 +245,20 @@ static int rt5514_spi_hw_free(struct snd_pcm_substream *substream)
 
 	cancel_delayed_work_sync(&rt5514_dsp->copy_work);
 
-	return snd_pcm_lib_free_vmalloc_buffer(substream);
+	return snd_pcm_lib_free_pages(substream);
 }
 
 static snd_pcm_uframes_t rt5514_spi_pcm_pointer(
+		struct snd_soc_component *component,
 		struct snd_pcm_substream *substream)
 {
 	struct snd_pcm_runtime *runtime = substream->runtime;
-	struct snd_soc_pcm_runtime *rtd = substream->private_data;
-	struct snd_soc_component *component = snd_soc_rtdcom_lookup(rtd, DRV_NAME);
 	struct rt5514_dsp *rt5514_dsp =
 		snd_soc_component_get_drvdata(component);
 
 	return bytes_to_frames(runtime, rt5514_dsp->dma_offset);
 }
 
-static const struct snd_pcm_ops rt5514_spi_pcm_ops = {
-	.open		= rt5514_spi_pcm_open,
-	.hw_params	= rt5514_spi_hw_params,
-	.hw_free	= rt5514_spi_hw_free,
-	.pointer	= rt5514_spi_pcm_pointer,
-	.page		= snd_pcm_lib_get_vmalloc_page,
-};
 
 static int rt5514_spi_pcm_probe(struct snd_soc_component *component)
 {
@@ -301,10 +291,22 @@ static int rt5514_spi_pcm_probe(struct snd_soc_component *component)
 	return 0;
 }
 
+static int rt5514_spi_pcm_new(struct snd_soc_component *component,
+			      struct snd_soc_pcm_runtime *rtd)
+{
+	snd_pcm_lib_preallocate_pages_for_all(rtd->pcm, SNDRV_DMA_TYPE_VMALLOC,
+					      NULL, 0, 0);
+	return 0;
+}
+
 static const struct snd_soc_component_driver rt5514_spi_component = {
-	.name  = DRV_NAME,
-	.probe = rt5514_spi_pcm_probe,
-	.ops = &rt5514_spi_pcm_ops,
+	.name		= DRV_NAME,
+	.probe		= rt5514_spi_pcm_probe,
+	.open		= rt5514_spi_pcm_open,
+	.hw_params	= rt5514_spi_hw_params,
+	.hw_free	= rt5514_spi_hw_free,
+	.pointer	= rt5514_spi_pcm_pointer,
+	.pcm_construct	= rt5514_spi_pcm_new,
 };
 
 /**
diff --git a/sound/soc/codecs/rt5645.c b/sound/soc/codecs/rt5645.c
index 1c06b3b9218c..92d67010aeed 100644
--- a/sound/soc/codecs/rt5645.c
+++ b/sound/soc/codecs/rt5645.c
@@ -3270,6 +3270,9 @@ static void rt5645_jack_detect_work(struct work_struct *work)
 		snd_soc_jack_report(rt5645->mic_jack,
 				    report, SND_JACK_MICROPHONE);
 		return;
+	case 4:
+		val = snd_soc_component_read32(rt5645->component, RT5645_A_JD_CTRL1) & 0x0020;
+		break;
 	default: /* read rt5645 jd1_1 status */
 		val = snd_soc_component_read32(rt5645->component, RT5645_INT_IRQ_ST) & 0x1000;
 		break;
@@ -3603,7 +3606,7 @@ static const struct rt5645_platform_data intel_braswell_platform_data = {
 static const struct rt5645_platform_data buddy_platform_data = {
 	.dmic1_data_pin = RT5645_DMIC_DATA_GPIO5,
 	.dmic2_data_pin = RT5645_DMIC_DATA_IN2P,
-	.jd_mode = 3,
+	.jd_mode = 4,
 	.level_trigger_irq = true,
 };
 
@@ -3636,6 +3639,12 @@ static const struct rt5645_platform_data lattepanda_board_platform_data = {
 	.inv_jd1_1 = true
 };
 
+static const struct rt5645_platform_data kahlee_platform_data = {
+	.dmic1_data_pin = RT5645_DMIC_DATA_GPIO5,
+	.dmic2_data_pin = RT5645_DMIC_DATA_IN2P,
+	.jd_mode = 3,
+};
+
 static const struct dmi_system_id dmi_platform_data[] = {
 	{
 		.ident = "Chrome Buddy",
@@ -3742,6 +3751,13 @@ static const struct dmi_system_id dmi_platform_data[] = {
 		},
 		.driver_data = (void *)&lattepanda_board_platform_data,
 	},
+	{
+		.ident = "Chrome Kahlee",
+		.matches = {
+			DMI_MATCH(DMI_PRODUCT_NAME, "Kahlee"),
+		},
+		.driver_data = (void *)&kahlee_platform_data,
+	},
 	{ }
 };
 
@@ -3999,6 +4015,7 @@ static int rt5645_i2c_probe(struct i2c_client *i2c,
 					   RT5645_JD1_MODE_1);
 			break;
 		case 3:
+		case 4:
 			regmap_update_bits(rt5645->regmap, RT5645_A_JD_CTRL1,
 					   RT5645_JD1_MODE_MASK,
 					   RT5645_JD1_MODE_2);
diff --git a/sound/soc/codecs/rt5663.c b/sound/soc/codecs/rt5663.c
index 2943692f66ed..e6c1ec6c426e 100644
--- a/sound/soc/codecs/rt5663.c
+++ b/sound/soc/codecs/rt5663.c
@@ -3644,7 +3644,7 @@ static int rt5663_i2c_probe(struct i2c_client *i2c,
 		regmap_update_bits(rt5663->regmap, RT5663_PWR_ANLG_1,
 			RT5663_LDO1_DVO_MASK | RT5663_AMP_HP_MASK,
 			RT5663_LDO1_DVO_0_9V | RT5663_AMP_HP_3X);
-			break;
+		break;
 	case CODEC_VER_0:
 		regmap_update_bits(rt5663->regmap, RT5663_DIG_MISC,
 			RT5663_DIG_GATE_CTRL_MASK, RT5663_DIG_GATE_CTRL_EN);
@@ -3663,7 +3663,7 @@ static int rt5663_i2c_probe(struct i2c_client *i2c,
 		regmap_update_bits(rt5663->regmap, RT5663_TDM_2,
 			RT5663_DATA_SWAP_ADCDAT1_MASK,
 			RT5663_DATA_SWAP_ADCDAT1_LL);
-			break;
+		break;
 	default:
 		dev_err(&i2c->dev, "%s:Unknown codec type\n", __func__);
 	}
diff --git a/sound/soc/codecs/rt5677-spi.c b/sound/soc/codecs/rt5677-spi.c
index d681488f5312..7810b1d7de32 100644
--- a/sound/soc/codecs/rt5677-spi.c
+++ b/sound/soc/codecs/rt5677-spi.c
@@ -24,6 +24,9 @@
 #include <linux/firmware.h>
 #include <linux/acpi.h>
 
+#include <sound/soc.h>
+
+#include "rt5677.h"
 #include "rt5677-spi.h"
 
 #define DRV_NAME "rt5677spi"
@@ -45,9 +48,367 @@
 #define RT5677_SPI_WRITE_16	0x1
 #define RT5677_SPI_READ_16	0x0
 
+#define RT5677_BUF_BYTES_TOTAL		0x20000
+#define RT5677_MIC_BUF_ADDR		0x60030000
+#define RT5677_MODEL_ADDR		0x5FFC9800
+#define RT5677_MIC_BUF_BYTES		((u32)(RT5677_BUF_BYTES_TOTAL - \
+					sizeof(u32)))
+#define RT5677_MIC_BUF_FIRST_READ_SIZE	0x10000
+
 static struct spi_device *g_spi;
 static DEFINE_MUTEX(spi_mutex);
 
+struct rt5677_dsp {
+	struct device *dev;
+	struct delayed_work copy_work;
+	struct mutex dma_lock;
+	struct snd_pcm_substream *substream;
+	size_t dma_offset;	/* zero-based offset into runtime->dma_area */
+	size_t avail_bytes;	/* number of new bytes since last period */
+	u32 mic_read_offset;	/* zero-based offset into DSP's mic buffer */
+	bool new_hotword;	/* a new hotword is fired */
+};
+
+static const struct snd_pcm_hardware rt5677_spi_pcm_hardware = {
+	.info			= SNDRV_PCM_INFO_MMAP |
+				  SNDRV_PCM_INFO_MMAP_VALID |
+				  SNDRV_PCM_INFO_INTERLEAVED,
+	.formats		= SNDRV_PCM_FMTBIT_S16_LE,
+	.period_bytes_min	= PAGE_SIZE,
+	.period_bytes_max	= RT5677_BUF_BYTES_TOTAL / 8,
+	.periods_min		= 8,
+	.periods_max		= 8,
+	.channels_min		= 1,
+	.channels_max		= 1,
+	.buffer_bytes_max	= RT5677_BUF_BYTES_TOTAL,
+};
+
+static struct snd_soc_dai_driver rt5677_spi_dai = {
+	/* The DAI name "rt5677-dsp-cpu-dai" is not used. The actual DAI name
+	 * registered with ASoC is the name of the device "spi-RT5677AA:00",
+	 * because we only have one DAI. See snd_soc_register_dais().
+	 */
+	.name = "rt5677-dsp-cpu-dai",
+	.id = 0,
+	.capture = {
+		.stream_name = "DSP Capture",
+		.channels_min = 1,
+		.channels_max = 1,
+		.rates = SNDRV_PCM_RATE_16000,
+		.formats = SNDRV_PCM_FMTBIT_S16_LE,
+	},
+};
+
+/* PCM for streaming audio from the DSP buffer */
+static int rt5677_spi_pcm_open(
+		struct snd_soc_component *component,
+		struct snd_pcm_substream *substream)
+{
+	snd_soc_set_runtime_hwparams(substream, &rt5677_spi_pcm_hardware);
+	return 0;
+}
+
+static int rt5677_spi_pcm_close(
+		struct snd_soc_component *component,
+		struct snd_pcm_substream *substream)
+{
+	struct snd_soc_pcm_runtime *rtd = substream->private_data;
+	struct snd_soc_component *codec_component =
+			snd_soc_rtdcom_lookup(rtd, "rt5677");
+	struct rt5677_priv *rt5677 =
+			snd_soc_component_get_drvdata(codec_component);
+	struct rt5677_dsp *rt5677_dsp =
+			snd_soc_component_get_drvdata(component);
+
+	cancel_delayed_work_sync(&rt5677_dsp->copy_work);
+	rt5677->set_dsp_vad(codec_component, false);
+	return 0;
+}
+
+static int rt5677_spi_hw_params(
+		struct snd_soc_component *component,
+		struct snd_pcm_substream *substream,
+		struct snd_pcm_hw_params *hw_params)
+{
+	struct rt5677_dsp *rt5677_dsp =
+			snd_soc_component_get_drvdata(component);
+	int ret;
+
+	mutex_lock(&rt5677_dsp->dma_lock);
+	ret = snd_pcm_lib_malloc_pages(substream, params_buffer_bytes(hw_params));
+	rt5677_dsp->substream = substream;
+	mutex_unlock(&rt5677_dsp->dma_lock);
+
+	return ret;
+}
+
+static int rt5677_spi_hw_free(
+		struct snd_soc_component *component,
+		struct snd_pcm_substream *substream)
+{
+	struct rt5677_dsp *rt5677_dsp =
+			snd_soc_component_get_drvdata(component);
+
+	mutex_lock(&rt5677_dsp->dma_lock);
+	rt5677_dsp->substream = NULL;
+	mutex_unlock(&rt5677_dsp->dma_lock);
+
+	return snd_pcm_lib_free_pages(substream);
+}
+
+static int rt5677_spi_prepare(
+		struct snd_soc_component *component,
+		struct snd_pcm_substream *substream)
+{
+	struct snd_soc_pcm_runtime *rtd = substream->private_data;
+	struct snd_soc_component *rt5677_component =
+			snd_soc_rtdcom_lookup(rtd, "rt5677");
+	struct rt5677_priv *rt5677 =
+			snd_soc_component_get_drvdata(rt5677_component);
+	struct rt5677_dsp *rt5677_dsp =
+			snd_soc_component_get_drvdata(component);
+
+	rt5677->set_dsp_vad(rt5677_component, true);
+	rt5677_dsp->dma_offset = 0;
+	rt5677_dsp->avail_bytes = 0;
+	return 0;
+}
+
+static snd_pcm_uframes_t rt5677_spi_pcm_pointer(
+		struct snd_soc_component *component,
+		struct snd_pcm_substream *substream)
+{
+	struct snd_pcm_runtime *runtime = substream->runtime;
+	struct rt5677_dsp *rt5677_dsp =
+			snd_soc_component_get_drvdata(component);
+
+	return bytes_to_frames(runtime, rt5677_dsp->dma_offset);
+}
+
+static int rt5677_spi_mic_write_offset(u32 *mic_write_offset)
+{
+	int ret;
+	/* Grab the first 4 bytes that hold the write pointer on the
+	 * dsp, and check to make sure that it points somewhere inside the
+	 * buffer.
+	 */
+	ret = rt5677_spi_read(RT5677_MIC_BUF_ADDR, mic_write_offset,
+			sizeof(u32));
+	if (ret)
+		return ret;
+	/* Adjust the offset so that it's zero-based */
+	*mic_write_offset = *mic_write_offset - sizeof(u32);
+	return *mic_write_offset < RT5677_MIC_BUF_BYTES ? 0 : -EFAULT;
+}
+
+/*
+ * Copy one contiguous block of audio samples from the DSP mic buffer to the
+ * dma_area of the pcm runtime. The receiving buffer may wrap around.
+ * @begin: start offset of the block to copy, in bytes.
+ * @end:   offset of the first byte after the block to copy, must be greater
+ *         than or equal to begin.
+ *
+ * Return: Zero if successful, or a negative error code on failure.
+ */
+static int rt5677_spi_copy_block(struct rt5677_dsp *rt5677_dsp,
+		u32 begin, u32 end)
+{
+	struct snd_pcm_runtime *runtime = rt5677_dsp->substream->runtime;
+	size_t bytes_per_frame = frames_to_bytes(runtime, 1);
+	size_t first_chunk_len, second_chunk_len;
+	int ret;
+
+	if (begin > end || runtime->dma_bytes < 2 * bytes_per_frame) {
+		dev_err(rt5677_dsp->dev,
+			"Invalid copy from (%u, %u), dma_area size %zu\n",
+			begin, end, runtime->dma_bytes);
+		return -EINVAL;
+	}
+
+	/* The block to copy is empty */
+	if (begin == end)
+		return 0;
+
+	/* If the incoming chunk is too big for the receiving buffer, only the
+	 * last "receiving buffer size - one frame" bytes are copied.
+	 */
+	if (end - begin > runtime->dma_bytes - bytes_per_frame)
+		begin = end - (runtime->dma_bytes - bytes_per_frame);
+
+	/* May need to split to two chunks, calculate the size of each */
+	first_chunk_len = end - begin;
+	second_chunk_len = 0;
+	if (rt5677_dsp->dma_offset + first_chunk_len > runtime->dma_bytes) {
+		/* Receiving buffer wrapped around */
+		second_chunk_len = first_chunk_len;
+		first_chunk_len = runtime->dma_bytes - rt5677_dsp->dma_offset;
+		second_chunk_len -= first_chunk_len;
+	}
+
+	/* Copy first chunk */
+	ret = rt5677_spi_read(RT5677_MIC_BUF_ADDR + sizeof(u32) + begin,
+			runtime->dma_area + rt5677_dsp->dma_offset,
+			first_chunk_len);
+	if (ret)
+		return ret;
+	rt5677_dsp->dma_offset += first_chunk_len;
+	if (rt5677_dsp->dma_offset == runtime->dma_bytes)
+		rt5677_dsp->dma_offset = 0;
+
+	/* Copy second chunk */
+	if (second_chunk_len) {
+		ret = rt5677_spi_read(RT5677_MIC_BUF_ADDR + sizeof(u32) +
+				begin + first_chunk_len, runtime->dma_area,
+				second_chunk_len);
+		if (!ret)
+			rt5677_dsp->dma_offset = second_chunk_len;
+	}
+	return ret;
+}
+
+/*
+ * Copy a given amount of audio samples from the DSP mic buffer starting at
+ * mic_read_offset, to the dma_area of the pcm runtime. The source buffer may
+ * wrap around. mic_read_offset is updated after successful copy.
+ * @amount: amount of samples to copy, in bytes.
+ *
+ * Return: Zero if successful, or a negative error code on failure.
+ */
+static int rt5677_spi_copy(struct rt5677_dsp *rt5677_dsp, u32 amount)
+{
+	int ret = 0;
+	u32 target;
+
+	if (amount == 0)
+		return ret;
+
+	target = rt5677_dsp->mic_read_offset + amount;
+	/* Copy the first chunk in DSP's mic buffer */
+	ret |= rt5677_spi_copy_block(rt5677_dsp, rt5677_dsp->mic_read_offset,
+			min(target, RT5677_MIC_BUF_BYTES));
+
+	if (target >= RT5677_MIC_BUF_BYTES) {
+		/* Wrap around, copy the second chunk */
+		target -= RT5677_MIC_BUF_BYTES;
+		ret |= rt5677_spi_copy_block(rt5677_dsp, 0, target);
+	}
+
+	if (!ret)
+		rt5677_dsp->mic_read_offset = target;
+	return ret;
+}
+
+/*
+ * A delayed work that streams audio samples from the DSP mic buffer to the
+ * dma_area of the pcm runtime via SPI.
+ */
+static void rt5677_spi_copy_work(struct work_struct *work)
+{
+	struct rt5677_dsp *rt5677_dsp =
+		container_of(work, struct rt5677_dsp, copy_work.work);
+	struct snd_pcm_runtime *runtime;
+	u32 mic_write_offset;
+	size_t new_bytes, copy_bytes, period_bytes;
+	unsigned int delay;
+	int ret = 0;
+
+	/* Ensure runtime->dma_area buffer does not go away while copying. */
+	mutex_lock(&rt5677_dsp->dma_lock);
+	if (!rt5677_dsp->substream) {
+		dev_err(rt5677_dsp->dev, "No pcm substream\n");
+		goto done;
+	}
+
+	runtime = rt5677_dsp->substream->runtime;
+
+	if (rt5677_spi_mic_write_offset(&mic_write_offset)) {
+		dev_err(rt5677_dsp->dev, "No mic_write_offset\n");
+		goto done;
+	}
+
+	/* If this is the first time that we've asked for streaming data after
+	 * a hotword is fired, we should start reading from the previous 2
+	 * seconds of audio from wherever the mic_write_offset is currently.
+	 */
+	if (rt5677_dsp->new_hotword) {
+		rt5677_dsp->new_hotword = false;
+		/* See if buffer wraparound happens */
+		if (mic_write_offset < RT5677_MIC_BUF_FIRST_READ_SIZE)
+			rt5677_dsp->mic_read_offset = RT5677_MIC_BUF_BYTES -
+					(RT5677_MIC_BUF_FIRST_READ_SIZE -
+					mic_write_offset);
+		else
+			rt5677_dsp->mic_read_offset = mic_write_offset -
+					RT5677_MIC_BUF_FIRST_READ_SIZE;
+	}
+
+	/* Calculate the amount of new samples in bytes */
+	if (rt5677_dsp->mic_read_offset <= mic_write_offset)
+		new_bytes = mic_write_offset - rt5677_dsp->mic_read_offset;
+	else
+		new_bytes = RT5677_MIC_BUF_BYTES + mic_write_offset
+				- rt5677_dsp->mic_read_offset;
+
+	/* Copy all new samples from DSP mic buffer, one period at a time */
+	period_bytes = snd_pcm_lib_period_bytes(rt5677_dsp->substream);
+	while (new_bytes) {
+		copy_bytes = min(new_bytes, period_bytes
+				- rt5677_dsp->avail_bytes);
+		ret = rt5677_spi_copy(rt5677_dsp, copy_bytes);
+		if (ret) {
+			dev_err(rt5677_dsp->dev, "Copy failed %d\n", ret);
+			goto done;
+		}
+		rt5677_dsp->avail_bytes += copy_bytes;
+		if (rt5677_dsp->avail_bytes >= period_bytes) {
+			snd_pcm_period_elapsed(rt5677_dsp->substream);
+			rt5677_dsp->avail_bytes = 0;
+		}
+		new_bytes -= copy_bytes;
+	}
+
+	delay = bytes_to_frames(runtime, period_bytes) / (runtime->rate / 1000);
+	schedule_delayed_work(&rt5677_dsp->copy_work, msecs_to_jiffies(delay));
+done:
+	mutex_unlock(&rt5677_dsp->dma_lock);
+}
+
+static int rt5677_spi_pcm_new(struct snd_soc_component *component,
+			      struct snd_soc_pcm_runtime *rtd)
+{
+	snd_pcm_lib_preallocate_pages_for_all(rtd->pcm, SNDRV_DMA_TYPE_VMALLOC,
+					      NULL, 0, 0);
+	return 0;
+}
+
+static int rt5677_spi_pcm_probe(struct snd_soc_component *component)
+{
+	struct rt5677_dsp *rt5677_dsp;
+
+	rt5677_dsp = devm_kzalloc(component->dev, sizeof(*rt5677_dsp),
+			GFP_KERNEL);
+	if (!rt5677_dsp)
+		return -ENOMEM;
+	rt5677_dsp->dev = &g_spi->dev;
+	mutex_init(&rt5677_dsp->dma_lock);
+	INIT_DELAYED_WORK(&rt5677_dsp->copy_work, rt5677_spi_copy_work);
+
+	snd_soc_component_set_drvdata(component, rt5677_dsp);
+	return 0;
+}
+
+static const struct snd_soc_component_driver rt5677_spi_dai_component = {
+	.name		= DRV_NAME,
+	.probe		= rt5677_spi_pcm_probe,
+	.open		= rt5677_spi_pcm_open,
+	.close		= rt5677_spi_pcm_close,
+	.hw_params	= rt5677_spi_hw_params,
+	.hw_free	= rt5677_spi_hw_free,
+	.prepare	= rt5677_spi_prepare,
+	.pointer	= rt5677_spi_pcm_pointer,
+	.pcm_construct	= rt5677_spi_pcm_new,
+};
+
 /* Select a suitable transfer command for the next transfer to ensure
  * the transfer address is always naturally aligned while minimizing
  * the total number of transfers required.
@@ -218,9 +579,45 @@ int rt5677_spi_write_firmware(u32 addr, const struct firmware *fw)
 }
 EXPORT_SYMBOL_GPL(rt5677_spi_write_firmware);
 
+void rt5677_spi_hotword_detected(void)
+{
+	struct rt5677_dsp *rt5677_dsp;
+
+	if (!g_spi)
+		return;
+
+	rt5677_dsp = dev_get_drvdata(&g_spi->dev);
+	if (!rt5677_dsp) {
+		dev_err(&g_spi->dev, "Can't get rt5677_dsp\n");
+		return;
+	}
+
+	mutex_lock(&rt5677_dsp->dma_lock);
+	dev_info(rt5677_dsp->dev, "Hotword detected\n");
+	rt5677_dsp->new_hotword = true;
+	mutex_unlock(&rt5677_dsp->dma_lock);
+
+	schedule_delayed_work(&rt5677_dsp->copy_work, 0);
+}
+EXPORT_SYMBOL_GPL(rt5677_spi_hotword_detected);
+
 static int rt5677_spi_probe(struct spi_device *spi)
 {
+	int ret;
+
 	g_spi = spi;
+
+	ret = snd_soc_register_component(&spi->dev, &rt5677_spi_dai_component,
+					 &rt5677_spi_dai, 1);
+	if (ret < 0)
+		dev_err(&spi->dev, "Failed to register component.\n");
+
+	return ret;
+}
+
+static int rt5677_spi_remove(struct spi_device *spi)
+{
+	snd_soc_unregister_component(&spi->dev);
 	return 0;
 }
 
@@ -236,6 +633,7 @@ static struct spi_driver rt5677_spi_driver = {
 		.acpi_match_table = ACPI_PTR(rt5677_spi_acpi_id),
 	},
 	.probe = rt5677_spi_probe,
+	.remove = rt5677_spi_remove,
 };
 module_spi_driver(rt5677_spi_driver);
 
diff --git a/sound/soc/codecs/rt5677-spi.h b/sound/soc/codecs/rt5677-spi.h
index 6ba3369dc235..3af36ec928e9 100644
--- a/sound/soc/codecs/rt5677-spi.h
+++ b/sound/soc/codecs/rt5677-spi.h
@@ -12,5 +12,6 @@
 int rt5677_spi_read(u32 addr, void *rxbuf, size_t len);
 int rt5677_spi_write(u32 addr, const void *txbuf, size_t len);
 int rt5677_spi_write_firmware(u32 addr, const struct firmware *fw);
+void rt5677_spi_hotword_detected(void);
 
 #endif /* __RT5677_SPI_H__ */
diff --git a/sound/soc/codecs/rt5677.c b/sound/soc/codecs/rt5677.c
index 315a3d39bc09..e9a051a50ab2 100644
--- a/sound/soc/codecs/rt5677.c
+++ b/sound/soc/codecs/rt5677.c
@@ -38,6 +38,10 @@
 
 #define RT5677_DEVICE_ID 0x6327
 
+/* Register controlling boot vector */
+#define RT5677_DSP_BOOT_VECTOR		0x1801f090
+#define RT5677_MODEL_ADDR		0x5FFC9800
+
 #define RT5677_PR_RANGE_BASE (0xff + 1)
 #define RT5677_PR_SPACING 0x100
 
@@ -298,6 +302,7 @@ static bool rt5677_volatile_register(struct device *dev, unsigned int reg)
 	case RT5677_I2C_MASTER_CTRL7:
 	case RT5677_I2C_MASTER_CTRL8:
 	case RT5677_HAP_GENE_CTRL2:
+	case RT5677_PWR_ANLG2: /* Modified by DSP firmware */
 	case RT5677_PWR_DSP_ST:
 	case RT5677_PRIV_DATA:
 	case RT5677_ASRC_22:
@@ -308,6 +313,8 @@ static bool rt5677_volatile_register(struct device *dev, unsigned int reg)
 	case RT5677_IRQ_CTRL1:
 	case RT5677_IRQ_CTRL2:
 	case RT5677_GPIO_ST:
+	case RT5677_GPIO_CTRL1: /* Modified by DSP firmware */
+	case RT5677_GPIO_CTRL2: /* Modified by DSP firmware */
 	case RT5677_DSP_INB1_SRC_CTRL4:
 	case RT5677_DSP_INB2_SRC_CTRL4:
 	case RT5677_DSP_INB3_SRC_CTRL4:
@@ -686,10 +693,8 @@ static int rt5677_dsp_mode_i2c_read(
 	return ret;
 }
 
-static void rt5677_set_dsp_mode(struct snd_soc_component *component, bool on)
+static void rt5677_set_dsp_mode(struct rt5677_priv *rt5677, bool on)
 {
-	struct rt5677_priv *rt5677 = snd_soc_component_get_drvdata(component);
-
 	if (on) {
 		regmap_update_bits(rt5677->regmap, RT5677_PWR_DSP1,
 			RT5677_PWR_DSP, RT5677_PWR_DSP);
@@ -701,86 +706,259 @@ static void rt5677_set_dsp_mode(struct snd_soc_component *component, bool on)
 	}
 }
 
+static unsigned int rt5677_set_vad_source(struct rt5677_priv *rt5677)
+{
+	struct snd_soc_dapm_context *dapm =
+			snd_soc_component_get_dapm(rt5677->component);
+	/* Force dapm to sync before we enable the
+	 * DSP to prevent write corruption
+	 */
+	snd_soc_dapm_sync(dapm);
+
+	/* DMIC1 power = enabled
+	 * DMIC CLK = 256 * fs / 12
+	 */
+	regmap_update_bits(rt5677->regmap, RT5677_DMIC_CTRL1,
+		RT5677_DMIC_CLK_MASK, 5 << RT5677_DMIC_CLK_SFT);
+
+	/* I2S pre divide 2 = /6 (clk_sys2) */
+	regmap_update_bits(rt5677->regmap, RT5677_CLK_TREE_CTRL1,
+		RT5677_I2S_PD2_MASK, RT5677_I2S_PD2_6);
+
+	/* DSP Clock = MCLK1 (bypassed PLL2) */
+	regmap_write(rt5677->regmap, RT5677_GLB_CLK2,
+		RT5677_DSP_CLK_SRC_BYPASS);
+
+	/* SAD Threshold1 */
+	regmap_write(rt5677->regmap, RT5677_VAD_CTRL2, 0x013f);
+	/* SAD Threshold2 */
+	regmap_write(rt5677->regmap, RT5677_VAD_CTRL3, 0x0ae5);
+	/* SAD Sample Rate Converter = Up 6 (8K to 48K)
+	 * SAD Output Sample Rate = Same as I2S
+	 * SAD Threshold3
+	 */
+	regmap_update_bits(rt5677->regmap, RT5677_VAD_CTRL4,
+		RT5677_VAD_OUT_SRC_RATE_MASK | RT5677_VAD_OUT_SRC_MASK |
+		RT5677_VAD_LV_DIFF_MASK, 0x7f << RT5677_VAD_LV_DIFF_SFT);
+	/* Minimum frame level within a pre-determined duration = 32 frames
+	 * Bypass ADPCM Encoder/Decoder = Bypass ADPCM
+	 * Automatic Push Data to SAD Buffer Once SAD Flag is triggered = enable
+	 * SAD Buffer Over-Writing = enable
+	 * SAD Buffer Pop Mode Control = disable
+	 * SAD Buffer Push Mode Control = enable
+	 * SAD Detector Control = enable
+	 * SAD Function Control = enable
+	 * SAD Function Reset = normal
+	 */
+	regmap_write(rt5677->regmap, RT5677_VAD_CTRL1,
+		RT5677_VAD_FUNC_RESET | RT5677_VAD_FUNC_ENABLE |
+		RT5677_VAD_DET_ENABLE | RT5677_VAD_BUF_PUSH |
+		RT5677_VAD_BUF_OW | RT5677_VAD_FG2ENC |
+		RT5677_VAD_ADPCM_BYPASS | 1 << RT5677_VAD_MIN_DUR_SFT);
+
+	/* VAD/SAD is not routed to the IRQ output (i.e. MX-BE[14] = 0), but it
+	 * is routed to DSP_IRQ_0, so DSP firmware may use it to sleep and save
+	 * power. See ALC5677 datasheet section 9.17 "GPIO, Interrupt and Jack
+	 * Detection" for more info.
+	 */
+
+	/* Private register, no doc */
+	regmap_update_bits(rt5677->regmap, RT5677_PR_BASE + RT5677_BIAS_CUR4,
+		0x0f00, 0x0100);
+
+	/* LDO2 output = 1.2V
+	 * LDO1 output = 1.2V (LDO_IN = 1.8V)
+	 */
+	regmap_update_bits(rt5677->regmap, RT5677_PWR_ANLG1,
+		RT5677_LDO1_SEL_MASK | RT5677_LDO2_SEL_MASK,
+		5 << RT5677_LDO1_SEL_SFT | 5 << RT5677_LDO2_SEL_SFT);
+
+	/* Codec core power =  power on
+	 * LDO1 power = power on
+	 */
+	regmap_update_bits(rt5677->regmap, RT5677_PWR_ANLG2,
+		RT5677_PWR_CORE | RT5677_PWR_LDO1,
+		RT5677_PWR_CORE | RT5677_PWR_LDO1);
+
+	/* Isolation for DCVDD4 = normal (set during probe)
+	 * Isolation for DCVDD2 = normal (set during probe)
+	 * Isolation for DSP = normal
+	 * Isolation for Band 0~7 = disable
+	 * Isolation for InBound 4~10 and OutBound 4~10 = disable
+	 */
+	regmap_write(rt5677->regmap, RT5677_PWR_DSP2,
+		RT5677_PWR_CORE_ISO | RT5677_PWR_DSP_ISO |
+		RT5677_PWR_SR7_ISO | RT5677_PWR_SR6_ISO |
+		RT5677_PWR_SR5_ISO | RT5677_PWR_SR4_ISO |
+		RT5677_PWR_SR3_ISO | RT5677_PWR_SR2_ISO |
+		RT5677_PWR_SR1_ISO | RT5677_PWR_SR0_ISO |
+		RT5677_PWR_MLT_ISO);
+
+	/* System Band 0~7 = power on
+	 * InBound 4~10 and OutBound 4~10 = power on
+	 * DSP = power on
+	 * DSP CPU = stop (will be set to "run" after firmware loaded)
+	 */
+	regmap_write(rt5677->regmap, RT5677_PWR_DSP1,
+		RT5677_PWR_SR7 | RT5677_PWR_SR6 |
+		RT5677_PWR_SR5 | RT5677_PWR_SR4 |
+		RT5677_PWR_SR3 | RT5677_PWR_SR2 |
+		RT5677_PWR_SR1 | RT5677_PWR_SR0 |
+		RT5677_PWR_MLT | RT5677_PWR_DSP |
+		RT5677_PWR_DSP_CPU);
+
+	return 0;
+}
+
+static int rt5677_parse_and_load_dsp(struct rt5677_priv *rt5677, const u8 *buf,
+		unsigned int len)
+{
+	struct snd_soc_component *component = rt5677->component;
+	Elf32_Ehdr *elf_hdr;
+	Elf32_Phdr *pr_hdr;
+	Elf32_Half i;
+	int ret = 0;
+
+	if (!buf || (len < sizeof(Elf32_Ehdr)))
+		return -ENOMEM;
+
+	elf_hdr = (Elf32_Ehdr *)buf;
+#ifndef EM_XTENSA
+#define EM_XTENSA	94
+#endif
+	if (strncmp(elf_hdr->e_ident, ELFMAG, sizeof(ELFMAG) - 1))
+		dev_err(component->dev, "Wrong ELF header prefix\n");
+	if (elf_hdr->e_ehsize != sizeof(Elf32_Ehdr))
+		dev_err(component->dev, "Wrong Elf header size\n");
+	if (elf_hdr->e_machine != EM_XTENSA)
+		dev_err(component->dev, "Wrong DSP code file\n");
+
+	if (len < elf_hdr->e_phoff)
+		return -ENOMEM;
+	pr_hdr = (Elf32_Phdr *)(buf + elf_hdr->e_phoff);
+	for (i = 0; i < elf_hdr->e_phnum; i++) {
+		/* TODO: handle p_memsz != p_filesz */
+		if (pr_hdr->p_paddr && pr_hdr->p_filesz) {
+			dev_info(component->dev, "Load 0x%x bytes to 0x%x\n",
+					pr_hdr->p_filesz, pr_hdr->p_paddr);
+
+			ret = rt5677_spi_write(pr_hdr->p_paddr,
+					buf + pr_hdr->p_offset,
+					pr_hdr->p_filesz);
+			if (ret)
+				dev_err(component->dev, "Load firmware failed %d\n",
+						ret);
+		}
+		pr_hdr++;
+	}
+	return ret;
+}
+
+static int rt5677_load_dsp_from_file(struct rt5677_priv *rt5677)
+{
+	const struct firmware *fwp;
+	struct device *dev = rt5677->component->dev;
+	int ret = 0;
+
+	/* Load dsp firmware from rt5677_elf_vad file */
+	ret = request_firmware(&fwp, "rt5677_elf_vad", dev);
+	if (ret) {
+		dev_err(dev, "Request rt5677_elf_vad failed %d\n", ret);
+		return ret;
+	}
+	dev_info(dev, "Requested rt5677_elf_vad (%zu)\n", fwp->size);
+
+	ret = rt5677_parse_and_load_dsp(rt5677, fwp->data, fwp->size);
+	release_firmware(fwp);
+	return ret;
+}
+
 static int rt5677_set_dsp_vad(struct snd_soc_component *component, bool on)
 {
 	struct rt5677_priv *rt5677 = snd_soc_component_get_drvdata(component);
-	static bool activity;
-	int ret;
+	rt5677->dsp_vad_en_request = on;
+	rt5677->dsp_vad_en = on;
 
 	if (!IS_ENABLED(CONFIG_SND_SOC_RT5677_SPI))
 		return -ENXIO;
 
-	if (on && !activity) {
+	schedule_delayed_work(&rt5677->dsp_work, 0);
+	return 0;
+}
+
+static void rt5677_dsp_work(struct work_struct *work)
+{
+	struct rt5677_priv *rt5677 =
+		container_of(work, struct rt5677_priv, dsp_work.work);
+	static bool activity;
+	bool enable = rt5677->dsp_vad_en;
+	int i, val;
+
+
+	dev_info(rt5677->component->dev, "DSP VAD: enable=%d, activity=%d\n",
+			enable, activity);
+
+	if (enable && !activity) {
 		activity = true;
 
-		regcache_cache_only(rt5677->regmap, false);
-		regcache_cache_bypass(rt5677->regmap, true);
+		/* Before a hotword is detected, GPIO1 pin is configured as IRQ
+		 * output so that jack detect works. When a hotword is detected,
+		 * the DSP firmware configures the GPIO1 pin as GPIO1 and
+		 * drives a 1. rt5677_irq() is called after a rising edge on
+		 * the GPIO1 pin, due to either jack detect event or hotword
+		 * event, or both. All possible events are checked and handled
+		 * in rt5677_irq() where GPIO1 pin is configured back to IRQ
+		 * output if a hotword is detected.
+		 */
 
-		regmap_update_bits(rt5677->regmap, RT5677_DIG_MISC, 0x1, 0x1);
-		regmap_update_bits(rt5677->regmap,
-			RT5677_PR_BASE + RT5677_BIAS_CUR4, 0x0f00, 0x0f00);
-		regmap_update_bits(rt5677->regmap, RT5677_PWR_ANLG1,
-			RT5677_LDO1_SEL_MASK, 0x0);
-		regmap_update_bits(rt5677->regmap, RT5677_PWR_ANLG2,
-			RT5677_PWR_LDO1, RT5677_PWR_LDO1);
-		switch (rt5677->type) {
-		case RT5677:
-			regmap_update_bits(rt5677->regmap, RT5677_GLB_CLK1,
-				RT5677_MCLK_SRC_MASK, RT5677_MCLK2_SRC);
-			regmap_update_bits(rt5677->regmap, RT5677_GLB_CLK2,
-				RT5677_PLL2_PR_SRC_MASK |
-				RT5677_DSP_CLK_SRC_MASK,
-				RT5677_PLL2_PR_SRC_MCLK2 |
-				RT5677_DSP_CLK_SRC_BYPASS);
-			break;
-		case RT5676:
-			regmap_update_bits(rt5677->regmap, RT5677_GLB_CLK2,
-				RT5677_DSP_CLK_SRC_MASK,
-				RT5677_DSP_CLK_SRC_BYPASS);
-			break;
-		default:
-			break;
+		rt5677_set_vad_source(rt5677);
+		rt5677_set_dsp_mode(rt5677, true);
+
+#define RT5677_BOOT_RETRY 20
+		for (i = 0; i < RT5677_BOOT_RETRY; i++) {
+			regmap_read(rt5677->regmap, RT5677_PWR_DSP_ST, &val);
+			if (val == 0x3ff)
+				break;
+			udelay(500);
 		}
-		regmap_write(rt5677->regmap, RT5677_PWR_DSP2, 0x07ff);
-		regmap_write(rt5677->regmap, RT5677_PWR_DSP1, 0x07fd);
-		rt5677_set_dsp_mode(component, true);
-
-		ret = request_firmware(&rt5677->fw1, RT5677_FIRMWARE1,
-			component->dev);
-		if (ret == 0) {
-			rt5677_spi_write_firmware(0x50000000, rt5677->fw1);
-			release_firmware(rt5677->fw1);
+		if (i == RT5677_BOOT_RETRY && val != 0x3ff) {
+			dev_err(rt5677->component->dev, "DSP Boot Timed Out!");
+			return;
 		}
 
-		ret = request_firmware(&rt5677->fw2, RT5677_FIRMWARE2,
-			component->dev);
-		if (ret == 0) {
-			rt5677_spi_write_firmware(0x60000000, rt5677->fw2);
-			release_firmware(rt5677->fw2);
-		}
+		/* Boot the firmware from IRAM instead of SRAM0. */
+		rt5677_dsp_mode_i2c_write_addr(rt5677, RT5677_DSP_BOOT_VECTOR,
+			0x0009, 0x0003);
+		rt5677_dsp_mode_i2c_write_addr(rt5677, RT5677_DSP_BOOT_VECTOR,
+			0x0019, 0x0003);
+		rt5677_dsp_mode_i2c_write_addr(rt5677, RT5677_DSP_BOOT_VECTOR,
+			0x0009, 0x0003);
 
-		regmap_update_bits(rt5677->regmap, RT5677_PWR_DSP1, 0x1, 0x0);
+		rt5677_load_dsp_from_file(rt5677);
 
-		regcache_cache_bypass(rt5677->regmap, false);
-		regcache_cache_only(rt5677->regmap, true);
-	} else if (!on && activity) {
+		/* Set DSP CPU to Run */
+		regmap_update_bits(rt5677->regmap, RT5677_PWR_DSP1,
+			RT5677_PWR_DSP_CPU, 0x0);
+	} else if (!enable && activity) {
 		activity = false;
 
-		regcache_cache_only(rt5677->regmap, false);
-		regcache_cache_bypass(rt5677->regmap, true);
+		/* Don't turn off the DSP while handling irqs */
+		mutex_lock(&rt5677->irq_lock);
+		/* Set DSP CPU to Stop */
+		regmap_update_bits(rt5677->regmap, RT5677_PWR_DSP1,
+			RT5677_PWR_DSP_CPU, RT5677_PWR_DSP_CPU);
 
-		regmap_update_bits(rt5677->regmap, RT5677_PWR_DSP1, 0x1, 0x1);
-		rt5677_set_dsp_mode(component, false);
-		regmap_write(rt5677->regmap, RT5677_PWR_DSP1, 0x0001);
+		rt5677_set_dsp_mode(rt5677, false);
 
-		regmap_write(rt5677->regmap, RT5677_RESET, 0x10ec);
+		/* Disable and clear VAD interrupt */
+		regmap_write(rt5677->regmap, RT5677_VAD_CTRL1, 0x2184);
 
-		regcache_cache_bypass(rt5677->regmap, false);
-		regcache_mark_dirty(rt5677->regmap);
-		regcache_sync(rt5677->regmap);
-	}
+		/* Set GPIO1 pin back to be IRQ output for jack detect */
+		regmap_update_bits(rt5677->regmap, RT5677_GPIO_CTRL1,
+			RT5677_GPIO1_PIN_MASK, RT5677_GPIO1_PIN_IRQ);
 
-	return 0;
+		mutex_unlock(&rt5677->irq_lock);
+	}
 }
 
 static const DECLARE_TLV_DB_SCALE(dac_vol_tlv, -6525, 75, 0);
@@ -805,7 +983,7 @@ static int rt5677_dsp_vad_get(struct snd_kcontrol *kcontrol,
 	struct snd_soc_component *component = snd_kcontrol_chip(kcontrol);
 	struct rt5677_priv *rt5677 = snd_soc_component_get_drvdata(component);
 
-	ucontrol->value.integer.value[0] = rt5677->dsp_vad_en;
+	ucontrol->value.integer.value[0] = rt5677->dsp_vad_en_request;
 
 	return 0;
 }
@@ -814,12 +992,8 @@ static int rt5677_dsp_vad_put(struct snd_kcontrol *kcontrol,
 		struct snd_ctl_elem_value *ucontrol)
 {
 	struct snd_soc_component *component = snd_kcontrol_chip(kcontrol);
-	struct rt5677_priv *rt5677 = snd_soc_component_get_drvdata(component);
-
-	rt5677->dsp_vad_en = !!ucontrol->value.integer.value[0];
 
-	if (snd_soc_component_get_bias_level(component) == SND_SOC_BIAS_OFF)
-		rt5677_set_dsp_vad(component, rt5677->dsp_vad_en);
+	rt5677_set_dsp_vad(component, !!ucontrol->value.integer.value[0]);
 
 	return 0;
 }
@@ -3010,6 +3184,7 @@ static const struct snd_soc_dapm_widget rt5677_dapm_widgets[] = {
 	SND_SOC_DAPM_AIF_OUT("AIF4TX", "AIF4 Capture", 0, SND_SOC_NOPM, 0, 0),
 	SND_SOC_DAPM_AIF_IN("SLBRX", "SLIMBus Playback", 0, SND_SOC_NOPM, 0, 0),
 	SND_SOC_DAPM_AIF_OUT("SLBTX", "SLIMBus Capture", 0, SND_SOC_NOPM, 0, 0),
+	SND_SOC_DAPM_AIF_OUT("DSPTX", "DSP Buffer", 0, SND_SOC_NOPM, 0, 0),
 
 	/* Sidetone Mux */
 	SND_SOC_DAPM_MUX("Sidetone Mux", SND_SOC_NOPM, 0, 0,
@@ -3544,11 +3719,24 @@ static const struct snd_soc_dapm_route rt5677_dapm_routes[] = {
 	{ "SLBTX", NULL, "SLB ADC3 Mux" },
 	{ "SLBTX", NULL, "SLB ADC4 Mux" },
 
+	{ "DSPTX", NULL, "IB01 Bypass Mux" },
+
 	{ "IB01 Mux", "IF1 DAC 01", "IF1 DAC01" },
 	{ "IB01 Mux", "IF2 DAC 01", "IF2 DAC01" },
 	{ "IB01 Mux", "SLB DAC 01", "SLB DAC01" },
 	{ "IB01 Mux", "STO1 ADC MIX", "Stereo1 ADC MIX" },
-	{ "IB01 Mux", "VAD ADC/DAC1 FS", "DAC1 FS" },
+	/* The IB01 Mux controls the source for InBound0 and InBound1.
+	 * When the mux option "VAD ADC/DAC1 FS" is selected, "VAD ADC" goes to
+	 * InBound0 and "DAC1 FS" goes to InBound1. "VAD ADC" is used for
+	 * hotwording. "DAC1 FS" is not used currently.
+	 *
+	 * Creating a common widget node for "VAD ADC" + "DAC1 FS" and
+	 * connecting the common widget to IB01 Mux causes the issue where
+	 * there is an active path going from system playback -> "DAC1 FS" ->
+	 * IB01 Mux -> DSP Buffer -> hotword stream. This wrong path confuses
+	 * DAPM. Therefore "DAC1 FS" is ignored for now.
+	 */
+	{ "IB01 Mux", "VAD ADC/DAC1 FS", "VAD ADC Mux" },
 
 	{ "IB01 Bypass Mux", "Bypass", "IB01 Mux" },
 	{ "IB01 Bypass Mux", "Pass SRC", "IB01 Mux" },
@@ -4457,14 +4645,15 @@ static int rt5677_set_bias_level(struct snd_soc_component *component,
 			enum snd_soc_bias_level level)
 {
 	struct rt5677_priv *rt5677 = snd_soc_component_get_drvdata(component);
+	enum snd_soc_bias_level prev_bias =
+		snd_soc_component_get_bias_level(component);
 
 	switch (level) {
 	case SND_SOC_BIAS_ON:
 		break;
 
 	case SND_SOC_BIAS_PREPARE:
-		if (snd_soc_component_get_bias_level(component) == SND_SOC_BIAS_STANDBY) {
-			rt5677_set_dsp_vad(component, false);
+		if (prev_bias == SND_SOC_BIAS_STANDBY) {
 
 			regmap_update_bits(rt5677->regmap, RT5677_PWR_ANLG1,
 				RT5677_LDO1_SEL_MASK | RT5677_LDO2_SEL_MASK,
@@ -4488,9 +4677,25 @@ static int rt5677_set_bias_level(struct snd_soc_component *component,
 		break;
 
 	case SND_SOC_BIAS_STANDBY:
+		if (prev_bias == SND_SOC_BIAS_OFF &&
+				rt5677->dsp_vad_en_request) {
+			/* Re-enable the DSP if it was turned off at suspend */
+			rt5677->dsp_vad_en = true;
+			/* The delay is to wait for MCLK */
+			schedule_delayed_work(&rt5677->dsp_work,
+					msecs_to_jiffies(1000));
+		}
 		break;
 
 	case SND_SOC_BIAS_OFF:
+		flush_delayed_work(&rt5677->dsp_work);
+		if (rt5677->is_dsp_mode) {
+			/* Turn off the DSP before suspend */
+			rt5677->dsp_vad_en = false;
+			schedule_delayed_work(&rt5677->dsp_work, 0);
+			flush_delayed_work(&rt5677->dsp_work);
+		}
+
 		regmap_update_bits(rt5677->regmap, RT5677_DIG_MISC, 0x1, 0x0);
 		regmap_write(rt5677->regmap, RT5677_PWR_DIG1, 0x0000);
 		regmap_write(rt5677->regmap, RT5677_PWR_ANLG1,
@@ -4740,6 +4945,8 @@ static void rt5677_remove(struct snd_soc_component *component)
 {
 	struct rt5677_priv *rt5677 = snd_soc_component_get_drvdata(component);
 
+	cancel_delayed_work_sync(&rt5677->dsp_work);
+
 	regmap_write(rt5677->regmap, RT5677_RESET, 0x10ec);
 	gpiod_set_value_cansleep(rt5677->pow_ldo2, 0);
 	gpiod_set_value_cansleep(rt5677->reset_pin, 1);
@@ -4750,6 +4957,11 @@ static int rt5677_suspend(struct snd_soc_component *component)
 {
 	struct rt5677_priv *rt5677 = snd_soc_component_get_drvdata(component);
 
+	if (rt5677->irq) {
+		cancel_delayed_work_sync(&rt5677->resume_irq_check);
+		disable_irq(rt5677->irq);
+	}
+
 	if (!rt5677->dsp_vad_en) {
 		regcache_cache_only(rt5677->regmap, true);
 		regcache_mark_dirty(rt5677->regmap);
@@ -4778,6 +4990,11 @@ static int rt5677_resume(struct snd_soc_component *component)
 		regcache_sync(rt5677->regmap);
 	}
 
+	if (rt5677->irq) {
+		enable_irq(rt5677->irq);
+		schedule_delayed_work(&rt5677->resume_irq_check, 0);
+	}
+
 	return 0;
 }
 #else
@@ -4842,6 +5059,11 @@ static const struct snd_soc_dai_ops rt5677_aif_dai_ops = {
 	.set_tdm_slot = rt5677_set_tdm_slot,
 };
 
+static const struct snd_soc_dai_ops rt5677_dsp_dai_ops = {
+	.set_sysclk = rt5677_set_dai_sysclk,
+	.set_pll = rt5677_set_dai_pll,
+};
+
 static struct snd_soc_dai_driver rt5677_dai[] = {
 	{
 		.name = "rt5677-aif1",
@@ -4938,6 +5160,18 @@ static struct snd_soc_dai_driver rt5677_dai[] = {
 		},
 		.ops = &rt5677_aif_dai_ops,
 	},
+	{
+		.name = "rt5677-dspbuffer",
+		.id = RT5677_DSPBUFF,
+		.capture = {
+			.stream_name = "DSP Buffer",
+			.channels_min = 1,
+			.channels_max = 1,
+			.rates = SNDRV_PCM_RATE_16000,
+			.formats = SNDRV_PCM_FMTBIT_S16_LE,
+		},
+		.ops = &rt5677_dsp_dai_ops,
+	},
 };
 
 static const struct snd_soc_component_driver soc_component_dev_rt5677 = {
@@ -5073,6 +5307,28 @@ static const struct rt5677_irq_desc rt5677_irq_descs[] = {
 	},
 };
 
+static bool rt5677_check_hotword(struct rt5677_priv *rt5677)
+{
+	int reg_gpio;
+
+	if (!rt5677->is_dsp_mode)
+		return false;
+
+	if (regmap_read(rt5677->regmap, RT5677_GPIO_CTRL1, &reg_gpio))
+		return false;
+
+	/* Firmware sets GPIO1 pin to be GPIO1 after hotword is detected */
+	if ((reg_gpio & RT5677_GPIO1_PIN_MASK) == RT5677_GPIO1_PIN_IRQ)
+		return false;
+
+	/* Set GPIO1 pin back to be IRQ output for jack detect */
+	regmap_update_bits(rt5677->regmap, RT5677_GPIO_CTRL1,
+			RT5677_GPIO1_PIN_MASK, RT5677_GPIO1_PIN_IRQ);
+
+	rt5677_spi_hotword_detected();
+	return true;
+}
+
 static irqreturn_t rt5677_irq(int unused, void *data)
 {
 	struct rt5677_priv *rt5677 = data;
@@ -5118,7 +5374,13 @@ static irqreturn_t rt5677_irq(int unused, void *data)
 				reg_irq ^= rt5677_irq_descs[i].polarity_mask;
 			}
 		}
-		if (!irq_fired)
+
+		/* Exit the loop only when we know for sure that GPIO1 pin
+		 * was low at some point since irq_lock was acquired. Any event
+		 * after that point creates a rising edge that triggers another
+		 * call to rt5677_irq().
+		 */
+		if (!irq_fired && !rt5677_check_hotword(rt5677))
 			goto exit;
 
 		ret = regmap_write(rt5677->regmap, RT5677_IRQ_CTRL1, reg_irq);
@@ -5129,6 +5391,7 @@ static irqreturn_t rt5677_irq(int unused, void *data)
 		}
 	}
 exit:
+	WARN_ON_ONCE(loop == 20);
 	mutex_unlock(&rt5677->irq_lock);
 	if (irq_fired)
 		return IRQ_HANDLED;
@@ -5136,6 +5399,39 @@ exit:
 		return IRQ_NONE;
 }
 
+static void rt5677_resume_irq_check(struct work_struct *work)
+{
+	int i, virq;
+	struct rt5677_priv *rt5677 =
+		container_of(work, struct rt5677_priv, resume_irq_check.work);
+
+	/* This is needed to check and clear the interrupt status register
+	 * at resume. If the headset is plugged/unplugged when the device is
+	 * fully suspended, there won't be a rising edge at resume to trigger
+	 * the interrupt. Without this, we miss the next unplug/plug event.
+	 */
+	rt5677_irq(0, rt5677);
+
+	/* Call all enabled jack detect irq handlers again. This is needed in
+	 * addition to the above check for a corner case caused by jack gpio
+	 * debounce. After codec irq is disabled at suspend, the delayed work
+	 * scheduled by soc-jack may run and read wrong jack gpio values, since
+	 * the regmap is in cache only mode. At resume, there is no irq because
+	 * rt5677_irq has already ran and cleared the irq status at suspend.
+	 * Without this explicit check, unplug the headset right after suspend
+	 * starts, then after resume the headset is still shown as plugged in.
+	 */
+	mutex_lock(&rt5677->irq_lock);
+	for (i = 0; i < RT5677_IRQ_NUM; i++) {
+		if (rt5677->irq_en & rt5677_irq_descs[i].enable_mask) {
+			virq = irq_find_mapping(rt5677->domain, i);
+			if (virq)
+				handle_nested_irq(virq);
+		}
+	}
+	mutex_unlock(&rt5677->irq_lock);
+}
+
 static void rt5677_irq_bus_lock(struct irq_data *data)
 {
 	struct rt5677_priv *rt5677 = irq_data_get_irq_chip_data(data);
@@ -5211,6 +5507,7 @@ static int rt5677_init_irq(struct i2c_client *i2c)
 	}
 
 	mutex_init(&rt5677->irq_lock);
+	INIT_DELAYED_WORK(&rt5677->resume_irq_check, rt5677_resume_irq_check);
 
 	/*
 	 * Select RC as the debounce clock so that GPIO works even when
@@ -5256,6 +5553,8 @@ static int rt5677_init_irq(struct i2c_client *i2c)
 	if (ret)
 		dev_err(&i2c->dev, "Failed to request IRQ: %d\n", ret);
 
+	rt5677->irq = i2c->irq;
+
 	return ret;
 }
 
@@ -5271,6 +5570,8 @@ static int rt5677_i2c_probe(struct i2c_client *i2c)
 		return -ENOMEM;
 
 	rt5677->dev = &i2c->dev;
+	rt5677->set_dsp_vad = rt5677_set_dsp_vad;
+	INIT_DELAYED_WORK(&rt5677->dsp_work, rt5677_dsp_work);
 	i2c_set_clientdata(i2c, rt5677);
 
 	if (i2c->dev.of_node) {
diff --git a/sound/soc/codecs/rt5677.h b/sound/soc/codecs/rt5677.h
index 213f4b8ca269..944ae02aafc2 100644
--- a/sound/soc/codecs/rt5677.h
+++ b/sound/soc/codecs/rt5677.h
@@ -1336,6 +1336,8 @@
 #define RT5677_PLL_M_SFT			12
 #define RT5677_PLL_M_BP				(0x1 << 11)
 #define RT5677_PLL_M_BP_SFT			11
+#define RT5677_PLL_UPDATE_PLL1			(0x1 << 1)
+#define RT5677_PLL_UPDATE_PLL1_SFT		1
 
 /* Global Clock Control 1 (0x80) */
 #define RT5677_SCLK_SRC_MASK			(0x3 << 14)
@@ -1730,6 +1732,7 @@ enum {
 	RT5677_AIF4,
 	RT5677_AIF5,
 	RT5677_AIFS,
+	RT5677_DSPBUFF,
 };
 
 enum {
@@ -1845,14 +1848,20 @@ struct rt5677_priv {
 #ifdef CONFIG_GPIOLIB
 	struct gpio_chip gpio_chip;
 #endif
-	bool dsp_vad_en;
+	bool dsp_vad_en_request; /* DSP VAD enable/disable request */
+	bool dsp_vad_en; /* dsp_work parameter */
 	bool is_dsp_mode;
 	bool is_vref_slow;
+	struct delayed_work dsp_work;
 
 	/* Interrupt handling */
 	struct irq_domain *domain;
 	struct mutex irq_lock;
 	unsigned int irq_en;
+	struct delayed_work resume_irq_check;
+	int irq;
+
+	int (*set_dsp_vad)(struct snd_soc_component *component, bool on);
 };
 
 int rt5677_sel_asrc_clk_src(struct snd_soc_component *component,
diff --git a/sound/soc/codecs/rt5682.c b/sound/soc/codecs/rt5682.c
index c50b75ce82e0..b1713fffa3eb 100644
--- a/sound/soc/codecs/rt5682.c
+++ b/sound/soc/codecs/rt5682.c
@@ -44,6 +44,7 @@ static const struct rt5682_platform_data i2s_default_platform_data = {
 	.dmic1_data_pin = RT5682_DMIC1_DATA_GPIO2,
 	.dmic1_clk_pin = RT5682_DMIC1_CLK_GPIO3,
 	.jd_src = RT5682_JD1,
+	.btndet_delay = 16,
 };
 
 struct rt5682_priv {
@@ -1002,6 +1003,7 @@ static int rt5682_set_jack_detect(struct snd_soc_component *component,
 				   RT5682_JD1_EN_MASK, RT5682_JD1_DIS);
 		regmap_update_bits(rt5682->regmap, RT5682_RC_CLK_CTRL,
 				   RT5682_POW_JDH | RT5682_POW_JDL, 0);
+		cancel_delayed_work_sync(&rt5682->jack_detect_work);
 		return 0;
 	}
 
@@ -1026,6 +1028,18 @@ static int rt5682_set_jack_detect(struct snd_soc_component *component,
 		regmap_update_bits(rt5682->regmap, RT5682_IRQ_CTRL_2,
 			RT5682_JD1_EN_MASK | RT5682_JD1_POL_MASK,
 			RT5682_JD1_EN | RT5682_JD1_POL_NOR);
+		regmap_update_bits(rt5682->regmap, RT5682_4BTN_IL_CMD_4,
+			0x7f7f, (rt5682->pdata.btndet_delay << 8 |
+			rt5682->pdata.btndet_delay));
+		regmap_update_bits(rt5682->regmap, RT5682_4BTN_IL_CMD_5,
+			0x7f7f, (rt5682->pdata.btndet_delay << 8 |
+			rt5682->pdata.btndet_delay));
+		regmap_update_bits(rt5682->regmap, RT5682_4BTN_IL_CMD_6,
+			0x7f7f, (rt5682->pdata.btndet_delay << 8 |
+			rt5682->pdata.btndet_delay));
+		regmap_update_bits(rt5682->regmap, RT5682_4BTN_IL_CMD_7,
+			0x7f7f, (rt5682->pdata.btndet_delay << 8 |
+			rt5682->pdata.btndet_delay));
 		mod_delayed_work(system_power_efficient_wq,
 			   &rt5682->jack_detect_work, msecs_to_jiffies(250));
 		break;
@@ -1450,28 +1464,6 @@ static const struct snd_kcontrol_new hpor_switch =
 	SOC_DAPM_SINGLE_AUTODISABLE("Switch", RT5682_HP_CTRL_1,
 					RT5682_R_MUTE_SFT, 1, 1);
 
-static int rt5682_charge_pump_event(struct snd_soc_dapm_widget *w,
-	struct snd_kcontrol *kcontrol, int event)
-{
-	struct snd_soc_component *component =
-		snd_soc_dapm_to_component(w->dapm);
-
-	switch (event) {
-	case SND_SOC_DAPM_PRE_PMU:
-		snd_soc_component_update_bits(component,
-			RT5682_HP_CHARGE_PUMP_1, RT5682_PM_HP_MASK, RT5682_PM_HP_HV);
-		break;
-	case SND_SOC_DAPM_POST_PMD:
-		snd_soc_component_update_bits(component,
-			RT5682_HP_CHARGE_PUMP_1, RT5682_PM_HP_MASK, RT5682_PM_HP_LV);
-		break;
-	default:
-		return 0;
-	}
-
-	return 0;
-}
-
 static int rt5682_hp_event(struct snd_soc_dapm_widget *w,
 	struct snd_kcontrol *kcontrol, int event)
 {
@@ -1755,8 +1747,7 @@ static const struct snd_soc_dapm_widget rt5682_dapm_widgets[] = {
 	SND_SOC_DAPM_SUPPLY("HP Amp R", RT5682_PWR_ANLG_1,
 		RT5682_PWR_HA_R_BIT, 0, NULL, 0),
 	SND_SOC_DAPM_SUPPLY_S("Charge Pump", 1, RT5682_DEPOP_1,
-		RT5682_PUMP_EN_SFT, 0, rt5682_charge_pump_event,
-		SND_SOC_DAPM_PRE_PMU | SND_SOC_DAPM_POST_PMD),
+		RT5682_PUMP_EN_SFT, 0, NULL, 0),
 	SND_SOC_DAPM_SUPPLY_S("Capless", 2, RT5682_DEPOP_1,
 		RT5682_CAPLESS_EN_SFT, 0, NULL, 0),
 
@@ -2467,6 +2458,8 @@ static int rt5682_parse_dt(struct rt5682_priv *rt5682, struct device *dev)
 		&rt5682->pdata.dmic1_clk_pin);
 	device_property_read_u32(dev, "realtek,jd-src",
 		&rt5682->pdata.jd_src);
+	device_property_read_u32(dev, "realtek,btndet-delay",
+		&rt5682->pdata.btndet_delay);
 
 	rt5682->pdata.ldo1_en = of_get_named_gpio(dev->of_node,
 		"realtek,ldo1-en-gpios", 0);
@@ -2654,6 +2647,8 @@ static int rt5682_i2c_probe(struct i2c_client *i2c,
 			RT5682_HPA_CP_BIAS_CTRL_MASK, RT5682_HPA_CP_BIAS_3UA);
 	regmap_update_bits(rt5682->regmap, RT5682_CHARGE_PUMP_1,
 			RT5682_CP_CLK_HP_MASK, RT5682_CP_CLK_HP_300KHZ);
+	regmap_update_bits(rt5682->regmap, RT5682_HP_CHARGE_PUMP_1,
+			RT5682_PM_HP_MASK, RT5682_PM_HP_HV);
 
 	INIT_DELAYED_WORK(&rt5682->jack_detect_work,
 				rt5682_jack_detect_handler);
diff --git a/sound/soc/codecs/tas2562.c b/sound/soc/codecs/tas2562.c
new file mode 100644
index 000000000000..729acd874c48
--- /dev/null
+++ b/sound/soc/codecs/tas2562.c
@@ -0,0 +1,590 @@
+// SPDX-License-Identifier: GPL-2.0
+//
+// Driver for the Texas Instruments TAS2562 CODEC
+// Copyright (C) 2019 Texas Instruments Inc.
+
+
+#include <linux/module.h>
+#include <linux/errno.h>
+#include <linux/device.h>
+#include <linux/i2c.h>
+#include <linux/pm_runtime.h>
+#include <linux/regmap.h>
+#include <linux/slab.h>
+#include <linux/gpio/consumer.h>
+#include <linux/regulator/consumer.h>
+#include <linux/delay.h>
+
+#include <sound/pcm.h>
+#include <sound/pcm_params.h>
+#include <sound/soc.h>
+#include <sound/soc-dapm.h>
+#include <sound/tlv.h>
+
+#include "tas2562.h"
+
+#define TAS2562_FORMATS (SNDRV_PCM_FMTBIT_S16_LE | SNDRV_PCM_FMTBIT_S24_LE |\
+			 SNDRV_PCM_FORMAT_S32_LE)
+
+struct tas2562_data {
+	struct snd_soc_component *component;
+	struct gpio_desc *sdz_gpio;
+	struct regmap *regmap;
+	struct device *dev;
+	struct i2c_client *client;
+	int v_sense_slot;
+	int i_sense_slot;
+};
+
+static int tas2562_set_bias_level(struct snd_soc_component *component,
+				 enum snd_soc_bias_level level)
+{
+	struct tas2562_data *tas2562 =
+			snd_soc_component_get_drvdata(component);
+
+	switch (level) {
+	case SND_SOC_BIAS_ON:
+		snd_soc_component_update_bits(component,
+			TAS2562_PWR_CTRL,
+			TAS2562_MODE_MASK, TAS2562_ACTIVE);
+		break;
+	case SND_SOC_BIAS_STANDBY:
+	case SND_SOC_BIAS_PREPARE:
+		snd_soc_component_update_bits(component,
+			TAS2562_PWR_CTRL,
+			TAS2562_MODE_MASK, TAS2562_MUTE);
+		break;
+	case SND_SOC_BIAS_OFF:
+		snd_soc_component_update_bits(component,
+			TAS2562_PWR_CTRL,
+			TAS2562_MODE_MASK, TAS2562_SHUTDOWN);
+		break;
+
+	default:
+		dev_err(tas2562->dev,
+				"wrong power level setting %d\n", level);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int tas2562_set_samplerate(struct tas2562_data *tas2562, int samplerate)
+{
+	int samp_rate;
+	int ramp_rate;
+
+	switch (samplerate) {
+	case 7350:
+		ramp_rate = TAS2562_TDM_CFG0_RAMPRATE_44_1;
+		samp_rate = TAS2562_TDM_CFG0_SAMPRATE_7305_8KHZ;
+		break;
+	case 8000:
+		ramp_rate = 0;
+		samp_rate = TAS2562_TDM_CFG0_SAMPRATE_7305_8KHZ;
+		break;
+	case 14700:
+		ramp_rate = TAS2562_TDM_CFG0_RAMPRATE_44_1;
+		samp_rate = TAS2562_TDM_CFG0_SAMPRATE_14_7_16KHZ;
+		break;
+	case 16000:
+		ramp_rate = 0;
+		samp_rate = TAS2562_TDM_CFG0_SAMPRATE_14_7_16KHZ;
+		break;
+	case 22050:
+		ramp_rate = TAS2562_TDM_CFG0_RAMPRATE_44_1;
+		samp_rate = TAS2562_TDM_CFG0_SAMPRATE_22_05_24KHZ;
+		break;
+	case 24000:
+		ramp_rate = 0;
+		samp_rate = TAS2562_TDM_CFG0_SAMPRATE_22_05_24KHZ;
+		break;
+	case 29400:
+		ramp_rate = TAS2562_TDM_CFG0_RAMPRATE_44_1;
+		samp_rate = TAS2562_TDM_CFG0_SAMPRATE_29_4_32KHZ;
+		break;
+	case 32000:
+		ramp_rate = 0;
+		samp_rate = TAS2562_TDM_CFG0_SAMPRATE_29_4_32KHZ;
+		break;
+	case 44100:
+		ramp_rate = TAS2562_TDM_CFG0_RAMPRATE_44_1;
+		samp_rate = TAS2562_TDM_CFG0_SAMPRATE_44_1_48KHZ;
+		break;
+	case 48000:
+		ramp_rate = 0;
+		samp_rate = TAS2562_TDM_CFG0_SAMPRATE_44_1_48KHZ;
+		break;
+	case 88200:
+		ramp_rate = TAS2562_TDM_CFG0_RAMPRATE_44_1;
+		samp_rate = TAS2562_TDM_CFG0_SAMPRATE_88_2_96KHZ;
+		break;
+	case 96000:
+		ramp_rate = 0;
+		samp_rate = TAS2562_TDM_CFG0_SAMPRATE_88_2_96KHZ;
+		break;
+	case 176400:
+		ramp_rate = TAS2562_TDM_CFG0_RAMPRATE_44_1;
+		samp_rate = TAS2562_TDM_CFG0_SAMPRATE_176_4_192KHZ;
+		break;
+	case 192000:
+		ramp_rate = 0;
+		samp_rate = TAS2562_TDM_CFG0_SAMPRATE_176_4_192KHZ;
+		break;
+	default:
+		dev_info(tas2562->dev, "%s, unsupported sample rate, %d\n",
+			__func__, samplerate);
+		return -EINVAL;
+	}
+
+	snd_soc_component_update_bits(tas2562->component, TAS2562_TDM_CFG0,
+		TAS2562_TDM_CFG0_RAMPRATE_MASK,	ramp_rate);
+	snd_soc_component_update_bits(tas2562->component, TAS2562_TDM_CFG0,
+		TAS2562_TDM_CFG0_SAMPRATE_MASK,	samp_rate);
+
+	return 0;
+}
+
+static int tas2562_set_dai_tdm_slot(struct snd_soc_dai *dai,
+		unsigned int tx_mask, unsigned int rx_mask,
+		int slots, int slot_width)
+{
+	struct snd_soc_component *component = dai->component;
+	struct tas2562_data *tas2562 = snd_soc_component_get_drvdata(component);
+	int ret = 0;
+
+	switch (slot_width) {
+	case 16:
+		ret = snd_soc_component_update_bits(component,
+						    TAS2562_TDM_CFG2,
+						    TAS2562_TDM_CFG2_RXLEN_MASK,
+						    TAS2562_TDM_CFG2_RXLEN_16B);
+		break;
+	case 24:
+		ret = snd_soc_component_update_bits(component,
+						    TAS2562_TDM_CFG2,
+						    TAS2562_TDM_CFG2_RXLEN_MASK,
+						    TAS2562_TDM_CFG2_RXLEN_24B);
+		break;
+	case 32:
+		ret = snd_soc_component_update_bits(component,
+						    TAS2562_TDM_CFG2,
+						    TAS2562_TDM_CFG2_RXLEN_MASK,
+						    TAS2562_TDM_CFG2_RXLEN_32B);
+		break;
+
+	case 0:
+		/* Do not change slot width */
+		break;
+	default:
+		dev_err(tas2562->dev, "slot width not supported");
+		ret = -EINVAL;
+	}
+
+	if (ret < 0)
+		return ret;
+
+	return 0;
+}
+
+static int tas2562_set_bitwidth(struct tas2562_data *tas2562, int bitwidth)
+{
+	int ret;
+
+	switch (bitwidth) {
+	case SNDRV_PCM_FORMAT_S16_LE:
+		snd_soc_component_update_bits(tas2562->component,
+					      TAS2562_TDM_CFG2,
+					      TAS2562_TDM_CFG2_RXWLEN_MASK,
+					      TAS2562_TDM_CFG2_RXWLEN_16B);
+		tas2562->v_sense_slot = tas2562->i_sense_slot + 2;
+		break;
+	case SNDRV_PCM_FORMAT_S24_LE:
+		snd_soc_component_update_bits(tas2562->component,
+					      TAS2562_TDM_CFG2,
+					      TAS2562_TDM_CFG2_RXWLEN_MASK,
+					      TAS2562_TDM_CFG2_RXWLEN_24B);
+		tas2562->v_sense_slot = tas2562->i_sense_slot + 4;
+		break;
+	case SNDRV_PCM_FORMAT_S32_LE:
+		snd_soc_component_update_bits(tas2562->component,
+					      TAS2562_TDM_CFG2,
+					      TAS2562_TDM_CFG2_RXWLEN_MASK,
+					      TAS2562_TDM_CFG2_RXWLEN_32B);
+		tas2562->v_sense_slot = tas2562->i_sense_slot + 4;
+		break;
+
+	default:
+		dev_info(tas2562->dev, "Not supported params format\n");
+	}
+
+	ret = snd_soc_component_update_bits(tas2562->component,
+		TAS2562_TDM_CFG5,
+		TAS2562_TDM_CFG5_VSNS_EN | TAS2562_TDM_CFG5_VSNS_SLOT_MASK,
+		TAS2562_TDM_CFG5_VSNS_EN | tas2562->v_sense_slot);
+	if (ret < 0)
+		return ret;
+
+	ret = snd_soc_component_update_bits(tas2562->component,
+		TAS2562_TDM_CFG6,
+		TAS2562_TDM_CFG6_ISNS_EN | TAS2562_TDM_CFG6_ISNS_SLOT_MASK,
+		TAS2562_TDM_CFG6_ISNS_EN | tas2562->i_sense_slot);
+	if (ret < 0)
+		return ret;
+
+	return 0;
+}
+
+static int tas2562_hw_params(struct snd_pcm_substream *substream,
+			     struct snd_pcm_hw_params *params,
+			     struct snd_soc_dai *dai)
+{
+	struct snd_soc_component *component = dai->component;
+	struct tas2562_data *tas2562 = snd_soc_component_get_drvdata(component);
+	int ret;
+
+	ret = tas2562_set_bitwidth(tas2562, params_format(params));
+	if (ret) {
+		dev_err(tas2562->dev, "set bitwidth failed, %d\n", ret);
+		return ret;
+	}
+
+	ret = tas2562_set_samplerate(tas2562, params_rate(params));
+	if (ret)
+		dev_err(tas2562->dev, "set bitwidth failed, %d\n", ret);
+
+	return ret;
+}
+
+static int tas2562_set_dai_fmt(struct snd_soc_dai *dai, unsigned int fmt)
+{
+	struct snd_soc_component *component = dai->component;
+	struct tas2562_data *tas2562 = snd_soc_component_get_drvdata(component);
+	u8 tdm_rx_start_slot = 0, asi_cfg_1 = 0;
+	int ret;
+
+	switch (fmt & SND_SOC_DAIFMT_INV_MASK) {
+	case SND_SOC_DAIFMT_NB_NF:
+		asi_cfg_1 = 0;
+		break;
+	case SND_SOC_DAIFMT_IB_NF:
+		asi_cfg_1 |= TAS2562_TDM_CFG1_RX_FALLING;
+		break;
+	default:
+		dev_err(tas2562->dev, "ASI format Inverse is not found\n");
+		return -EINVAL;
+	}
+
+	ret = snd_soc_component_update_bits(component, TAS2562_TDM_CFG1,
+					    TAS2562_TDM_CFG1_RX_EDGE_MASK,
+					    asi_cfg_1);
+	if (ret < 0) {
+		dev_err(tas2562->dev, "Failed to set RX edge\n");
+		return ret;
+	}
+
+	switch (fmt & SND_SOC_DAIFMT_FORMAT_MASK) {
+	case (SND_SOC_DAIFMT_I2S):
+	case (SND_SOC_DAIFMT_DSP_A):
+	case (SND_SOC_DAIFMT_DSP_B):
+		tdm_rx_start_slot = BIT(1);
+		break;
+	case (SND_SOC_DAIFMT_LEFT_J):
+		tdm_rx_start_slot = 0;
+		break;
+	default:
+		dev_err(tas2562->dev, "DAI Format is not found, fmt=0x%x\n",
+			fmt);
+		ret = -EINVAL;
+		break;
+	}
+
+	ret = snd_soc_component_update_bits(component, TAS2562_TDM_CFG1,
+					    TAS2562_TDM_CFG1_RX_OFFSET_MASK,
+					    tdm_rx_start_slot);
+
+	if (ret < 0)
+		return ret;
+
+	return 0;
+}
+
+static int tas2562_mute(struct snd_soc_dai *dai, int mute)
+{
+	struct snd_soc_component *component = dai->component;
+
+	return snd_soc_component_update_bits(component, TAS2562_PWR_CTRL,
+					     TAS2562_MODE_MASK,
+					     mute ? TAS2562_MUTE : 0);
+}
+
+static int tas2562_codec_probe(struct snd_soc_component *component)
+{
+	struct tas2562_data *tas2562 = snd_soc_component_get_drvdata(component);
+	int ret;
+
+	tas2562->component = component;
+
+	if (tas2562->sdz_gpio)
+		gpiod_set_value_cansleep(tas2562->sdz_gpio, 1);
+
+	ret = snd_soc_component_update_bits(component, TAS2562_PWR_CTRL,
+					    TAS2562_MODE_MASK, TAS2562_MUTE);
+	if (ret < 0)
+		return ret;
+
+	return 0;
+}
+
+#ifdef CONFIG_PM
+static int tas2562_suspend(struct snd_soc_component *component)
+{
+	struct tas2562_data *tas2562 = snd_soc_component_get_drvdata(component);
+
+	regcache_cache_only(tas2562->regmap, true);
+	regcache_mark_dirty(tas2562->regmap);
+
+	if (tas2562->sdz_gpio)
+		gpiod_set_value_cansleep(tas2562->sdz_gpio, 0);
+
+	return 0;
+}
+
+static int tas2562_resume(struct snd_soc_component *component)
+{
+	struct tas2562_data *tas2562 = snd_soc_component_get_drvdata(component);
+
+	if (tas2562->sdz_gpio)
+		gpiod_set_value_cansleep(tas2562->sdz_gpio, 1);
+
+	regcache_cache_only(tas2562->regmap, false);
+
+	return regcache_sync(tas2562->regmap);
+}
+#else
+#define tas2562_suspend NULL
+#define tas2562_resume NULL
+#endif
+
+static const char * const tas2562_ASI1_src[] = {
+	"I2C offset", "Left", "Right", "LeftRightDiv2",
+};
+
+static SOC_ENUM_SINGLE_DECL(tas2562_ASI1_src_enum, TAS2562_TDM_CFG2, 4,
+			    tas2562_ASI1_src);
+
+static const struct snd_kcontrol_new tas2562_asi1_mux =
+	SOC_DAPM_ENUM("ASI1 Source", tas2562_ASI1_src_enum);
+
+static int tas2562_dac_event(struct snd_soc_dapm_widget *w,
+			     struct snd_kcontrol *kcontrol, int event)
+{
+	struct snd_soc_component *component =
+					snd_soc_dapm_to_component(w->dapm);
+	struct tas2562_data *tas2562 = snd_soc_component_get_drvdata(component);
+
+	switch (event) {
+	case SND_SOC_DAPM_POST_PMU:
+		dev_info(tas2562->dev, "SND_SOC_DAPM_POST_PMU\n");
+		break;
+	case SND_SOC_DAPM_PRE_PMD:
+		dev_info(tas2562->dev, "SND_SOC_DAPM_PRE_PMD\n");
+		break;
+	default:
+		break;
+	}
+
+	return 0;
+}
+
+static DECLARE_TLV_DB_SCALE(tas2562_dac_tlv, 850, 50, 0);
+
+static const struct snd_kcontrol_new isense_switch =
+	SOC_DAPM_SINGLE("Switch", TAS2562_PWR_CTRL, TAS2562_ISENSE_POWER_EN,
+			1, 1);
+
+static const struct snd_kcontrol_new vsense_switch =
+	SOC_DAPM_SINGLE("Switch", TAS2562_PWR_CTRL, TAS2562_VSENSE_POWER_EN,
+			1, 1);
+
+static const struct snd_kcontrol_new tas2562_snd_controls[] = {
+	SOC_SINGLE_TLV("Amp Gain Volume", TAS2562_PB_CFG1, 0, 0x1c, 0,
+		       tas2562_dac_tlv),
+};
+
+static const struct snd_soc_dapm_widget tas2562_dapm_widgets[] = {
+	SND_SOC_DAPM_AIF_IN("ASI1", "ASI1 Playback", 0, SND_SOC_NOPM, 0, 0),
+	SND_SOC_DAPM_MUX("ASI1 Sel", SND_SOC_NOPM, 0, 0, &tas2562_asi1_mux),
+	SND_SOC_DAPM_AIF_IN("DAC IN", "Playback", 0, SND_SOC_NOPM, 0, 0),
+	SND_SOC_DAPM_DAC_E("DAC", NULL, SND_SOC_NOPM, 0, 0, tas2562_dac_event,
+			   SND_SOC_DAPM_POST_PMU | SND_SOC_DAPM_PRE_PMD),
+	SND_SOC_DAPM_SWITCH("ISENSE", TAS2562_PWR_CTRL, 3, 1, &isense_switch),
+	SND_SOC_DAPM_SWITCH("VSENSE", TAS2562_PWR_CTRL, 2, 1, &vsense_switch),
+	SND_SOC_DAPM_SIGGEN("VMON"),
+	SND_SOC_DAPM_SIGGEN("IMON"),
+	SND_SOC_DAPM_OUTPUT("OUT"),
+};
+
+static const struct snd_soc_dapm_route tas2562_audio_map[] = {
+	{"ASI1 Sel", "I2C offset", "ASI1"},
+	{"ASI1 Sel", "Left", "ASI1"},
+	{"ASI1 Sel", "Right", "ASI1"},
+	{"ASI1 Sel", "LeftRightDiv2", "ASI1"},
+	{ "DAC", NULL, "DAC IN" },
+	{ "OUT", NULL, "DAC" },
+	{"ISENSE", "Switch", "IMON"},
+	{"VSENSE", "Switch", "VMON"},
+};
+
+static const struct snd_soc_component_driver soc_component_dev_tas2562 = {
+	.probe			= tas2562_codec_probe,
+	.suspend		= tas2562_suspend,
+	.resume			= tas2562_resume,
+	.set_bias_level		= tas2562_set_bias_level,
+	.controls		= tas2562_snd_controls,
+	.num_controls		= ARRAY_SIZE(tas2562_snd_controls),
+	.dapm_widgets		= tas2562_dapm_widgets,
+	.num_dapm_widgets	= ARRAY_SIZE(tas2562_dapm_widgets),
+	.dapm_routes		= tas2562_audio_map,
+	.num_dapm_routes	= ARRAY_SIZE(tas2562_audio_map),
+	.idle_bias_on		= 1,
+	.use_pmdown_time	= 1,
+	.endianness		= 1,
+	.non_legacy_dai_naming	= 1,
+};
+
+static const struct snd_soc_dai_ops tas2562_speaker_dai_ops = {
+	.hw_params	= tas2562_hw_params,
+	.set_fmt	= tas2562_set_dai_fmt,
+	.set_tdm_slot	= tas2562_set_dai_tdm_slot,
+	.digital_mute	= tas2562_mute,
+};
+
+static struct snd_soc_dai_driver tas2562_dai[] = {
+	{
+		.name = "tas2562-amplifier",
+		.id = 0,
+		.playback = {
+			.stream_name    = "ASI1 Playback",
+			.channels_min   = 2,
+			.channels_max   = 2,
+			.rates      = SNDRV_PCM_RATE_8000_192000,
+			.formats    = TAS2562_FORMATS,
+		},
+		.ops = &tas2562_speaker_dai_ops,
+	},
+};
+
+static const struct regmap_range_cfg tas2562_ranges[] = {
+	{
+		.range_min = 0,
+		.range_max = 5 * 128,
+		.selector_reg = TAS2562_PAGE_CTRL,
+		.selector_mask = 0xff,
+		.selector_shift = 0,
+		.window_start = 0,
+		.window_len = 128,
+	},
+};
+
+static const struct reg_default tas2562_reg_defaults[] = {
+	{ TAS2562_PAGE_CTRL, 0x00 },
+	{ TAS2562_SW_RESET, 0x00 },
+	{ TAS2562_PWR_CTRL, 0x0e },
+	{ TAS2562_PB_CFG1, 0x20 },
+	{ TAS2562_TDM_CFG0, 0x09 },
+	{ TAS2562_TDM_CFG1, 0x02 },
+};
+
+static const struct regmap_config tas2562_regmap_config = {
+	.reg_bits = 8,
+	.val_bits = 8,
+
+	.max_register = 5 * 128,
+	.cache_type = REGCACHE_RBTREE,
+	.reg_defaults = tas2562_reg_defaults,
+	.num_reg_defaults = ARRAY_SIZE(tas2562_reg_defaults),
+	.ranges = tas2562_ranges,
+	.num_ranges = ARRAY_SIZE(tas2562_ranges),
+};
+
+static int tas2562_parse_dt(struct tas2562_data *tas2562)
+{
+	struct device *dev = tas2562->dev;
+	int ret = 0;
+
+	tas2562->sdz_gpio = devm_gpiod_get_optional(dev, "shut-down-gpio",
+						      GPIOD_OUT_HIGH);
+	if (IS_ERR(tas2562->sdz_gpio)) {
+		if (PTR_ERR(tas2562->sdz_gpio) == -EPROBE_DEFER) {
+			tas2562->sdz_gpio = NULL;
+			return -EPROBE_DEFER;
+		}
+	}
+
+	ret = fwnode_property_read_u32(dev->fwnode, "ti,imon-slot-no",
+			&tas2562->i_sense_slot);
+	if (ret)
+		dev_err(dev, "Looking up %s property failed %d\n",
+			"ti,imon-slot-no", ret);
+
+	return ret;
+}
+
+static int tas2562_probe(struct i2c_client *client,
+			 const struct i2c_device_id *id)
+{
+	struct device *dev = &client->dev;
+	struct tas2562_data *data;
+	int ret;
+
+	data = devm_kzalloc(dev, sizeof(*data), GFP_KERNEL);
+	if (!data)
+		return -ENOMEM;
+
+	data->client = client;
+	data->dev = &client->dev;
+
+	tas2562_parse_dt(data);
+
+	data->regmap = devm_regmap_init_i2c(client, &tas2562_regmap_config);
+	if (IS_ERR(data->regmap)) {
+		ret = PTR_ERR(data->regmap);
+		dev_err(dev, "failed to allocate register map: %d\n", ret);
+		return ret;
+	}
+
+	dev_set_drvdata(&client->dev, data);
+
+	return devm_snd_soc_register_component(dev, &soc_component_dev_tas2562,
+					       tas2562_dai,
+					       ARRAY_SIZE(tas2562_dai));
+
+}
+
+static const struct i2c_device_id tas2562_id[] = {
+	{ "tas2562", 0 },
+	{ }
+};
+MODULE_DEVICE_TABLE(i2c, tas2562_id);
+
+static const struct of_device_id tas2562_of_match[] = {
+	{ .compatible = "ti,tas2562", },
+	{ },
+};
+MODULE_DEVICE_TABLE(of, tas2562_of_match);
+
+static struct i2c_driver tas2562_i2c_driver = {
+	.driver = {
+		.name = "tas2562",
+		.of_match_table = of_match_ptr(tas2562_of_match),
+	},
+	.probe = tas2562_probe,
+	.id_table = tas2562_id,
+};
+
+module_i2c_driver(tas2562_i2c_driver);
+
+MODULE_AUTHOR("Dan Murphy <dmurphy@ti.com>");
+MODULE_DESCRIPTION("TAS2562 Audio amplifier driver");
+MODULE_LICENSE("GPL");
diff --git a/sound/soc/codecs/tas2562.h b/sound/soc/codecs/tas2562.h
new file mode 100644
index 000000000000..62e659ab786d
--- /dev/null
+++ b/sound/soc/codecs/tas2562.h
@@ -0,0 +1,85 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * tas2562.h - ALSA SoC Texas Instruments TAS2562 Mono Audio Amplifier
+ *
+ * Copyright (C) 2019 Texas Instruments Incorporated -  http://www.ti.com
+ *
+ * Author: Dan Murphy <dmurphy@ti.com>
+ */
+
+#ifndef __TAS2562_H__
+#define __TAS2562_H__
+
+#define TAS2562_PAGE_CTRL	0x00
+
+#define TAS2562_REG(page, reg)	((page * 128) + reg)
+
+#define TAS2562_SW_RESET	TAS2562_REG(0, 0x01)
+#define TAS2562_PWR_CTRL	TAS2562_REG(0, 0x02)
+#define TAS2562_PB_CFG1		TAS2562_REG(0, 0x03)
+#define TAS2562_MISC_CFG1	TAS2562_REG(0, 0x04)
+#define TAS2562_MISC_CFG2	TAS2562_REG(0, 0x05)
+
+#define TAS2562_TDM_CFG0	TAS2562_REG(0, 0x06)
+#define TAS2562_TDM_CFG1	TAS2562_REG(0, 0x07)
+#define TAS2562_TDM_CFG2	TAS2562_REG(0, 0x08)
+#define TAS2562_TDM_CFG3	TAS2562_REG(0, 0x09)
+#define TAS2562_TDM_CFG4	TAS2562_REG(0, 0x0a)
+#define TAS2562_TDM_CFG5	TAS2562_REG(0, 0x0b)
+#define TAS2562_TDM_CFG6	TAS2562_REG(0, 0x0c)
+#define TAS2562_TDM_CFG7	TAS2562_REG(0, 0x0d)
+#define TAS2562_TDM_CFG8	TAS2562_REG(0, 0x0e)
+#define TAS2562_TDM_CFG9	TAS2562_REG(0, 0x0f)
+#define TAS2562_TDM_CFG10	TAS2562_REG(0, 0x10)
+#define TAS2562_TDM_DET		TAS2562_REG(0, 0x11)
+#define TAS2562_REV_ID		TAS2562_REG(0, 0x7d)
+
+/* Page 2 */
+#define TAS2562_DVC_CFG1	TAS2562_REG(2, 0x01)
+#define TAS2562_DVC_CFG2	TAS2562_REG(2, 0x02)
+
+#define TAS2562_RESET	BIT(0)
+
+#define TAS2562_MODE_MASK	0x3
+#define TAS2562_ACTIVE		0x0
+#define TAS2562_MUTE		0x1
+#define TAS2562_SHUTDOWN	0x2
+
+#define TAS2562_TDM_CFG1_RX_EDGE_MASK	BIT(0)
+#define TAS2562_TDM_CFG1_RX_FALLING	1
+#define TAS2562_TDM_CFG1_RX_OFFSET_MASK	GENMASK(4, 0)
+
+#define TAS2562_TDM_CFG0_RAMPRATE_MASK		BIT(5)
+#define TAS2562_TDM_CFG0_RAMPRATE_44_1		BIT(5)
+#define TAS2562_TDM_CFG0_SAMPRATE_MASK		GENMASK(3, 1)
+#define TAS2562_TDM_CFG0_SAMPRATE_7305_8KHZ	0x0
+#define TAS2562_TDM_CFG0_SAMPRATE_14_7_16KHZ	0x1
+#define TAS2562_TDM_CFG0_SAMPRATE_22_05_24KHZ	0x2
+#define TAS2562_TDM_CFG0_SAMPRATE_29_4_32KHZ	0x3
+#define TAS2562_TDM_CFG0_SAMPRATE_44_1_48KHZ	0x4
+#define TAS2562_TDM_CFG0_SAMPRATE_88_2_96KHZ	0x5
+#define TAS2562_TDM_CFG0_SAMPRATE_176_4_192KHZ	0x6
+
+#define TAS2562_TDM_CFG2_RIGHT_JUSTIFY	BIT(6)
+
+#define TAS2562_TDM_CFG2_RXLEN_MASK	GENMASK(1, 0)
+#define TAS2562_TDM_CFG2_RXLEN_16B	0x0
+#define TAS2562_TDM_CFG2_RXLEN_24B	BIT(0)
+#define TAS2562_TDM_CFG2_RXLEN_32B	BIT(1)
+
+#define TAS2562_TDM_CFG2_RXWLEN_MASK	GENMASK(3, 2)
+#define TAS2562_TDM_CFG2_RXWLEN_16B	0x0
+#define TAS2562_TDM_CFG2_RXWLEN_20B	BIT(2)
+#define TAS2562_TDM_CFG2_RXWLEN_24B	BIT(3)
+#define TAS2562_TDM_CFG2_RXWLEN_32B	(BIT(2) | BIT(3))
+
+#define TAS2562_VSENSE_POWER_EN		BIT(2)
+#define TAS2562_ISENSE_POWER_EN		BIT(3)
+
+#define TAS2562_TDM_CFG5_VSNS_EN	BIT(6)
+#define TAS2562_TDM_CFG5_VSNS_SLOT_MASK	GENMASK(5, 0)
+
+#define TAS2562_TDM_CFG6_ISNS_EN	BIT(6)
+#define TAS2562_TDM_CFG6_ISNS_SLOT_MASK	GENMASK(5, 0)
+
+#endif /* __TAS2562_H__ */
diff --git a/sound/soc/codecs/tas2770.c b/sound/soc/codecs/tas2770.c
new file mode 100644
index 000000000000..54c8135fe43c
--- /dev/null
+++ b/sound/soc/codecs/tas2770.c
@@ -0,0 +1,819 @@
+// SPDX-License-Identifier: GPL-2.0
+//
+// ALSA SoC Texas Instruments TAS2770 20-W Digital Input Mono Class-D
+// Audio Amplifier with Speaker I/V Sense
+//
+// Copyright (C) 2016-2017 Texas Instruments Incorporated - http://www.ti.com/
+//	Author: Tracy Yi <tracy-yi@ti.com>
+//	Frank Shi <shifu0704@thundersoft.com>
+
+#include <linux/module.h>
+#include <linux/moduleparam.h>
+#include <linux/err.h>
+#include <linux/init.h>
+#include <linux/delay.h>
+#include <linux/pm.h>
+#include <linux/i2c.h>
+#include <linux/gpio.h>
+#include <linux/gpio/consumer.h>
+#include <linux/pm_runtime.h>
+#include <linux/regulator/consumer.h>
+#include <linux/firmware.h>
+#include <linux/regmap.h>
+#include <linux/of.h>
+#include <linux/of_gpio.h>
+#include <linux/slab.h>
+#include <sound/soc.h>
+#include <sound/pcm.h>
+#include <sound/pcm_params.h>
+#include <sound/initval.h>
+#include <sound/tlv.h>
+
+#include "tas2770.h"
+
+#define TAS2770_MDELAY 0xFFFFFFFE
+
+static void tas2770_reset(struct tas2770_priv *tas2770)
+{
+	if (tas2770->reset_gpio) {
+		gpiod_set_value_cansleep(tas2770->reset_gpio, 0);
+		msleep(20);
+		gpiod_set_value_cansleep(tas2770->reset_gpio, 1);
+	}
+	snd_soc_component_write(tas2770->component, TAS2770_SW_RST,
+		TAS2770_RST);
+}
+
+static int tas2770_set_bias_level(struct snd_soc_component *component,
+				 enum snd_soc_bias_level level)
+{
+	struct tas2770_priv *tas2770 =
+			snd_soc_component_get_drvdata(component);
+
+	switch (level) {
+	case SND_SOC_BIAS_ON:
+		snd_soc_component_update_bits(component,
+			TAS2770_PWR_CTRL,
+			TAS2770_PWR_CTRL_MASK,
+			TAS2770_PWR_CTRL_ACTIVE);
+		break;
+
+	case SND_SOC_BIAS_OFF:
+		snd_soc_component_update_bits(component,
+			TAS2770_PWR_CTRL,
+			TAS2770_PWR_CTRL_MASK,
+			TAS2770_PWR_CTRL_SHUTDOWN);
+		break;
+
+	default:
+		dev_err(tas2770->dev,
+				"wrong power level setting %d\n", level);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+#ifdef CONFIG_PM
+static int tas2770_codec_suspend(struct snd_soc_component *component)
+{
+	int ret;
+
+	ret = snd_soc_component_update_bits(component,
+		TAS2770_PWR_CTRL,
+		TAS2770_PWR_CTRL_MASK,
+		TAS2770_PWR_CTRL_SHUTDOWN);
+
+	if (ret < 0)
+		return ret;
+
+	return 0;
+}
+
+static int tas2770_codec_resume(struct snd_soc_component *component)
+{
+	int ret;
+
+	ret = snd_soc_component_update_bits(component,
+		TAS2770_PWR_CTRL,
+		TAS2770_PWR_CTRL_MASK,
+		TAS2770_PWR_CTRL_ACTIVE);
+
+	if (ret < 0)
+		return ret;
+
+	return 0;
+}
+#else
+#define tas2770_codec_suspend NULL
+#define tas2770_codec_resume NULL
+#endif
+
+static const char * const tas2770_ASI1_src[] = {
+	"I2C offset", "Left", "Right", "LeftRightDiv2",
+};
+
+static SOC_ENUM_SINGLE_DECL(
+	tas2770_ASI1_src_enum, TAS2770_TDM_CFG_REG2,
+	4, tas2770_ASI1_src);
+
+static const struct snd_kcontrol_new tas2770_asi1_mux =
+	SOC_DAPM_ENUM("ASI1 Source", tas2770_ASI1_src_enum);
+
+static int tas2770_dac_event(struct snd_soc_dapm_widget *w,
+			     struct snd_kcontrol *kcontrol, int event)
+{
+	struct snd_soc_component *component =
+			snd_soc_dapm_to_component(w->dapm);
+	struct tas2770_priv *tas2770 =
+			snd_soc_component_get_drvdata(component);
+	int ret;
+
+	switch (event) {
+	case SND_SOC_DAPM_POST_PMU:
+		ret = snd_soc_component_update_bits(component,
+			TAS2770_PWR_CTRL,
+			TAS2770_PWR_CTRL_MASK,
+			TAS2770_PWR_CTRL_MUTE);
+		if (ret)
+			goto end;
+		break;
+	case SND_SOC_DAPM_PRE_PMD:
+		ret = snd_soc_component_update_bits(component,
+			TAS2770_PWR_CTRL,
+			TAS2770_PWR_CTRL_MASK,
+			TAS2770_PWR_CTRL_SHUTDOWN);
+		if (ret)
+			goto end;
+		break;
+	default:
+		dev_err(tas2770->dev, "Not supported evevt\n");
+		return -EINVAL;
+	}
+
+end:
+	if (ret < 0)
+		return ret;
+
+	return 0;
+}
+
+static const struct snd_kcontrol_new isense_switch =
+	SOC_DAPM_SINGLE("Switch", TAS2770_PWR_CTRL, 3, 1, 1);
+static const struct snd_kcontrol_new vsense_switch =
+	SOC_DAPM_SINGLE("Switch", TAS2770_PWR_CTRL, 2, 1, 1);
+
+static const struct snd_soc_dapm_widget tas2770_dapm_widgets[] = {
+	SND_SOC_DAPM_AIF_IN("ASI1", "ASI1 Playback", 0, SND_SOC_NOPM, 0, 0),
+	SND_SOC_DAPM_MUX("ASI1 Sel", SND_SOC_NOPM, 0, 0,
+				&tas2770_asi1_mux),
+	SND_SOC_DAPM_SWITCH("ISENSE", TAS2770_PWR_CTRL, 3, 1,
+			&isense_switch),
+	SND_SOC_DAPM_SWITCH("VSENSE", TAS2770_PWR_CTRL, 2, 1,
+			&vsense_switch),
+	SND_SOC_DAPM_DAC_E("DAC", NULL, SND_SOC_NOPM, 0, 0, tas2770_dac_event,
+	SND_SOC_DAPM_POST_PMU | SND_SOC_DAPM_PRE_PMD),
+	SND_SOC_DAPM_OUTPUT("OUT"),
+	SND_SOC_DAPM_SIGGEN("VMON"),
+	SND_SOC_DAPM_SIGGEN("IMON")
+};
+
+static const struct snd_soc_dapm_route tas2770_audio_map[] = {
+	{"ASI1 Sel", "I2C offset", "ASI1"},
+	{"ASI1 Sel", "Left", "ASI1"},
+	{"ASI1 Sel", "Right", "ASI1"},
+	{"ASI1 Sel", "LeftRightDiv2", "ASI1"},
+	{"DAC", NULL, "ASI1 Sel"},
+	{"OUT", NULL, "DAC"},
+	{"ISENSE", "Switch", "IMON"},
+	{"VSENSE", "Switch", "VMON"},
+};
+
+static int tas2770_mute(struct snd_soc_dai *dai, int mute)
+{
+	struct snd_soc_component *component = dai->component;
+	int ret;
+
+	if (mute)
+		ret = snd_soc_component_update_bits(component,
+			TAS2770_PWR_CTRL,
+			TAS2770_PWR_CTRL_MASK,
+			TAS2770_PWR_CTRL_MUTE);
+	else
+		ret = snd_soc_component_update_bits(component,
+			TAS2770_PWR_CTRL,
+			TAS2770_PWR_CTRL_MASK,
+			TAS2770_PWR_CTRL_ACTIVE);
+
+	if (ret < 0)
+		return ret;
+
+	return 0;
+}
+
+static int tas2770_set_bitwidth(struct tas2770_priv *tas2770, int bitwidth)
+{
+	int ret;
+	struct snd_soc_component *component = tas2770->component;
+
+	switch (bitwidth) {
+	case SNDRV_PCM_FORMAT_S16_LE:
+		ret = snd_soc_component_update_bits(component,
+			TAS2770_TDM_CFG_REG2,
+			TAS2770_TDM_CFG_REG2_RXW_MASK,
+			TAS2770_TDM_CFG_REG2_RXW_16BITS);
+		tas2770->v_sense_slot = tas2770->i_sense_slot + 2;
+		break;
+	case SNDRV_PCM_FORMAT_S24_LE:
+		ret = snd_soc_component_update_bits(component,
+			TAS2770_TDM_CFG_REG2,
+			TAS2770_TDM_CFG_REG2_RXW_MASK,
+			TAS2770_TDM_CFG_REG2_RXW_24BITS);
+		tas2770->v_sense_slot = tas2770->i_sense_slot + 4;
+		break;
+	case SNDRV_PCM_FORMAT_S32_LE:
+		ret = snd_soc_component_update_bits(component,
+			TAS2770_TDM_CFG_REG2,
+			TAS2770_TDM_CFG_REG2_RXW_MASK,
+			TAS2770_TDM_CFG_REG2_RXW_32BITS);
+		tas2770->v_sense_slot = tas2770->i_sense_slot + 4;
+		break;
+
+	default:
+		return -EINVAL;
+	}
+
+	tas2770->channel_size = bitwidth;
+
+	ret = snd_soc_component_update_bits(component,
+		TAS2770_TDM_CFG_REG5,
+		TAS2770_TDM_CFG_REG5_VSNS_MASK |
+		TAS2770_TDM_CFG_REG5_50_MASK,
+		TAS2770_TDM_CFG_REG5_VSNS_ENABLE |
+		tas2770->v_sense_slot);
+	if (ret)
+		goto end;
+	ret = snd_soc_component_update_bits(component,
+		TAS2770_TDM_CFG_REG6,
+		TAS2770_TDM_CFG_REG6_ISNS_MASK |
+		TAS2770_TDM_CFG_REG6_50_MASK,
+		TAS2770_TDM_CFG_REG6_ISNS_ENABLE |
+		tas2770->i_sense_slot);
+
+end:
+	if (ret < 0)
+		return ret;
+
+	return 0;
+}
+
+static int tas2770_set_samplerate(struct tas2770_priv *tas2770, int samplerate)
+{
+	int ret;
+	struct snd_soc_component *component = tas2770->component;
+
+	switch (samplerate) {
+	case 48000:
+		ret = snd_soc_component_update_bits(component,
+			TAS2770_TDM_CFG_REG0,
+			TAS2770_TDM_CFG_REG0_SMP_MASK,
+			TAS2770_TDM_CFG_REG0_SMP_48KHZ);
+		if (ret)
+			goto end;
+		ret = snd_soc_component_update_bits(component,
+			TAS2770_TDM_CFG_REG0,
+			TAS2770_TDM_CFG_REG0_31_MASK,
+			TAS2770_TDM_CFG_REG0_31_44_1_48KHZ);
+		if (ret)
+			goto end;
+		break;
+	case 44100:
+		ret = snd_soc_component_update_bits(component,
+			TAS2770_TDM_CFG_REG0,
+			TAS2770_TDM_CFG_REG0_SMP_MASK,
+			TAS2770_TDM_CFG_REG0_SMP_44_1KHZ);
+		if (ret)
+			goto end;
+		ret = snd_soc_component_update_bits(component,
+			TAS2770_TDM_CFG_REG0,
+			TAS2770_TDM_CFG_REG0_31_MASK,
+			TAS2770_TDM_CFG_REG0_31_44_1_48KHZ);
+		if (ret)
+			goto end;
+		break;
+	case 96000:
+		ret = snd_soc_component_update_bits(component,
+			TAS2770_TDM_CFG_REG0,
+			TAS2770_TDM_CFG_REG0_SMP_MASK,
+			TAS2770_TDM_CFG_REG0_SMP_48KHZ);
+		if (ret)
+			goto end;
+		ret = snd_soc_component_update_bits(component,
+			TAS2770_TDM_CFG_REG0,
+			TAS2770_TDM_CFG_REG0_31_MASK,
+			TAS2770_TDM_CFG_REG0_31_88_2_96KHZ);
+		break;
+	case 88200:
+		ret = snd_soc_component_update_bits(component,
+			TAS2770_TDM_CFG_REG0,
+			TAS2770_TDM_CFG_REG0_SMP_MASK,
+			TAS2770_TDM_CFG_REG0_SMP_44_1KHZ);
+		if (ret)
+			goto end;
+		ret = snd_soc_component_update_bits(component,
+			TAS2770_TDM_CFG_REG0,
+			TAS2770_TDM_CFG_REG0_31_MASK,
+			TAS2770_TDM_CFG_REG0_31_88_2_96KHZ);
+		break;
+	case 19200:
+		ret = snd_soc_component_update_bits(component,
+			TAS2770_TDM_CFG_REG0,
+			TAS2770_TDM_CFG_REG0_SMP_MASK,
+			TAS2770_TDM_CFG_REG0_SMP_48KHZ);
+		if (ret)
+			goto end;
+		ret = snd_soc_component_update_bits(component,
+			TAS2770_TDM_CFG_REG0,
+			TAS2770_TDM_CFG_REG0_31_MASK,
+			TAS2770_TDM_CFG_REG0_31_176_4_192KHZ);
+		if (ret)
+			goto end;
+		break;
+	case 17640:
+		ret = snd_soc_component_update_bits(component,
+			TAS2770_TDM_CFG_REG0,
+			TAS2770_TDM_CFG_REG0_SMP_MASK,
+			TAS2770_TDM_CFG_REG0_SMP_44_1KHZ);
+		if (ret)
+			goto end;
+		ret = snd_soc_component_update_bits(component,
+			TAS2770_TDM_CFG_REG0,
+			TAS2770_TDM_CFG_REG0_31_MASK,
+			TAS2770_TDM_CFG_REG0_31_176_4_192KHZ);
+		break;
+	default:
+		ret = -EINVAL;
+	}
+
+end:
+	if (ret < 0)
+		return ret;
+
+	tas2770->sampling_rate = samplerate;
+	return 0;
+}
+
+static int tas2770_hw_params(struct snd_pcm_substream *substream,
+			     struct snd_pcm_hw_params *params,
+			     struct snd_soc_dai *dai)
+{
+	struct snd_soc_component *component = dai->component;
+	struct tas2770_priv *tas2770 =
+			snd_soc_component_get_drvdata(component);
+	int ret;
+
+	ret = tas2770_set_bitwidth(tas2770, params_format(params));
+	if (ret < 0)
+		goto end;
+
+
+	ret = tas2770_set_samplerate(tas2770, params_rate(params));
+
+end:
+	return ret;
+}
+
+static int tas2770_set_fmt(struct snd_soc_dai *dai, unsigned int fmt)
+{
+	u8 tdm_rx_start_slot = 0, asi_cfg_1 = 0;
+	int ret;
+	struct snd_soc_component *component = dai->component;
+	struct tas2770_priv *tas2770 =
+			snd_soc_component_get_drvdata(component);
+
+	switch (fmt & SND_SOC_DAIFMT_MASTER_MASK) {
+	case SND_SOC_DAIFMT_CBS_CFS:
+		break;
+	default:
+		dev_err(tas2770->dev, "ASI format master is not found\n");
+		return -EINVAL;
+	}
+
+	switch (fmt & SND_SOC_DAIFMT_INV_MASK) {
+	case SND_SOC_DAIFMT_NB_NF:
+		asi_cfg_1 |= TAS2770_TDM_CFG_REG1_RX_RSING;
+		break;
+	case SND_SOC_DAIFMT_IB_NF:
+		asi_cfg_1 |= TAS2770_TDM_CFG_REG1_RX_FALING;
+		break;
+	default:
+		dev_err(tas2770->dev, "ASI format Inverse is not found\n");
+		return -EINVAL;
+	}
+
+	ret = snd_soc_component_update_bits(component, TAS2770_TDM_CFG_REG1,
+		TAS2770_TDM_CFG_REG1_RX_MASK,
+		asi_cfg_1);
+	if (ret < 0)
+		return ret;
+
+	switch (fmt & SND_SOC_DAIFMT_FORMAT_MASK) {
+	case SND_SOC_DAIFMT_I2S:
+		tdm_rx_start_slot = 1;
+		break;
+	case SND_SOC_DAIFMT_DSP_A:
+		tdm_rx_start_slot = 0;
+		break;
+	case SND_SOC_DAIFMT_DSP_B:
+		tdm_rx_start_slot = 1;
+		break;
+	case SND_SOC_DAIFMT_LEFT_J:
+		tdm_rx_start_slot = 0;
+		break;
+	default:
+		dev_err(tas2770->dev,
+			"DAI Format is not found, fmt=0x%x\n", fmt);
+		return -EINVAL;
+	}
+
+	ret = snd_soc_component_update_bits(component, TAS2770_TDM_CFG_REG1,
+		TAS2770_TDM_CFG_REG1_MASK,
+	(tdm_rx_start_slot << TAS2770_TDM_CFG_REG1_51_SHIFT));
+	if (ret < 0)
+		return ret;
+
+	tas2770->asi_format = fmt;
+
+	return 0;
+}
+
+static int tas2770_set_dai_tdm_slot(struct snd_soc_dai *dai,
+				unsigned int tx_mask,
+				unsigned int rx_mask,
+				int slots, int slot_width)
+{
+	struct snd_soc_component *component = dai->component;
+	struct tas2770_priv *tas2770 =
+			snd_soc_component_get_drvdata(component);
+	int left_slot, right_slot;
+	int ret;
+
+	if (tx_mask == 0 || rx_mask != 0)
+		return -EINVAL;
+
+	if (slots == 1) {
+		if (tx_mask != 1)
+			return -EINVAL;
+		left_slot = 0;
+		right_slot = 0;
+	} else {
+		left_slot = __ffs(tx_mask);
+		tx_mask &= ~(1 << left_slot);
+		if (tx_mask == 0) {
+			right_slot = left_slot;
+		} else {
+			right_slot = __ffs(tx_mask);
+			tx_mask &= ~(1 << right_slot);
+		}
+	}
+
+	if (tx_mask != 0 || left_slot >= slots || right_slot >= slots)
+		return -EINVAL;
+
+	ret = snd_soc_component_update_bits(component, TAS2770_TDM_CFG_REG3,
+		TAS2770_TDM_CFG_REG3_30_MASK,
+		(left_slot << TAS2770_TDM_CFG_REG3_30_SHIFT));
+	if (ret < 0)
+		return ret;
+	ret = snd_soc_component_update_bits(component, TAS2770_TDM_CFG_REG3,
+		TAS2770_TDM_CFG_REG3_RXS_MASK,
+	(right_slot << TAS2770_TDM_CFG_REG3_RXS_SHIFT));
+	if (ret < 0)
+		return ret;
+
+	switch (slot_width) {
+	case 16:
+		ret = snd_soc_component_update_bits(component,
+			TAS2770_TDM_CFG_REG2,
+			TAS2770_TDM_CFG_REG2_RXS_MASK,
+			TAS2770_TDM_CFG_REG2_RXS_16BITS);
+		break;
+
+	case 24:
+		ret = snd_soc_component_update_bits(component,
+			TAS2770_TDM_CFG_REG2,
+			TAS2770_TDM_CFG_REG2_RXS_MASK,
+			TAS2770_TDM_CFG_REG2_RXS_24BITS);
+		break;
+
+	case 32:
+		ret = snd_soc_component_update_bits(component,
+			TAS2770_TDM_CFG_REG2,
+			TAS2770_TDM_CFG_REG2_RXS_MASK,
+			TAS2770_TDM_CFG_REG2_RXS_32BITS);
+		break;
+
+	case 0:
+		/* Do not change slot width */
+		ret = 0;
+		break;
+
+	default:
+		ret = -EINVAL;
+	}
+
+	if (ret < 0)
+		return ret;
+
+	tas2770->slot_width = slot_width;
+	return 0;
+}
+
+static struct snd_soc_dai_ops tas2770_dai_ops = {
+	.digital_mute = tas2770_mute,
+	.hw_params  = tas2770_hw_params,
+	.set_fmt    = tas2770_set_fmt,
+	.set_tdm_slot = tas2770_set_dai_tdm_slot,
+};
+
+#define TAS2770_FORMATS (SNDRV_PCM_FMTBIT_S16_LE | SNDRV_PCM_FMTBIT_S20_3LE |\
+		SNDRV_PCM_FMTBIT_S24_LE | SNDRV_PCM_FMTBIT_S32_LE)
+
+#define TAS2770_RATES (SNDRV_PCM_RATE_44100 | SNDRV_PCM_RATE_48000 |\
+					   SNDRV_PCM_RATE_96000 |\
+					    SNDRV_PCM_RATE_192000\
+					  )
+
+static struct snd_soc_dai_driver tas2770_dai_driver[] = {
+	{
+		.name = "tas2770 ASI1",
+		.id = 0,
+		.playback = {
+			.stream_name    = "ASI1 Playback",
+			.channels_min   = 2,
+			.channels_max   = 2,
+			.rates      = TAS2770_RATES,
+			.formats    = TAS2770_FORMATS,
+		},
+		.capture = {
+			.stream_name    = "ASI1 Capture",
+			.channels_min   = 0,
+			.channels_max   = 2,
+			.rates          = TAS2770_RATES,
+			.formats    = TAS2770_FORMATS,
+		},
+		.ops = &tas2770_dai_ops,
+		.symmetric_rates = 1,
+	},
+};
+
+static int tas2770_codec_probe(struct snd_soc_component *component)
+{
+	struct tas2770_priv *tas2770 =
+			snd_soc_component_get_drvdata(component);
+
+	tas2770->component = component;
+
+	return 0;
+}
+
+static DECLARE_TLV_DB_SCALE(tas2770_digital_tlv, 1100, 50, 0);
+static DECLARE_TLV_DB_SCALE(tas2770_playback_volume, -12750, 50, 0);
+
+static const struct snd_kcontrol_new tas2770_snd_controls[] = {
+	SOC_SINGLE_TLV("Speaker Playback Volume", TAS2770_PLAY_CFG_REG2,
+		0, TAS2770_PLAY_CFG_REG2_VMAX, 1,
+		tas2770_playback_volume),
+	SOC_SINGLE_TLV("Amp Gain Volume", TAS2770_PLAY_CFG_REG0,
+		0, 0x14, 0,
+		tas2770_digital_tlv),
+};
+
+static const struct snd_soc_component_driver soc_component_driver_tas2770 = {
+	.probe			= tas2770_codec_probe,
+	.suspend		= tas2770_codec_suspend,
+	.resume			= tas2770_codec_resume,
+	.set_bias_level = tas2770_set_bias_level,
+	.controls		= tas2770_snd_controls,
+	.num_controls		= ARRAY_SIZE(tas2770_snd_controls),
+	.dapm_widgets		= tas2770_dapm_widgets,
+	.num_dapm_widgets	= ARRAY_SIZE(tas2770_dapm_widgets),
+	.dapm_routes		= tas2770_audio_map,
+	.num_dapm_routes	= ARRAY_SIZE(tas2770_audio_map),
+	.idle_bias_on		= 1,
+	.endianness		= 1,
+	.non_legacy_dai_naming	= 1,
+};
+
+static int tas2770_register_codec(struct tas2770_priv *tas2770)
+{
+	return devm_snd_soc_register_component(tas2770->dev,
+		&soc_component_driver_tas2770,
+		tas2770_dai_driver, ARRAY_SIZE(tas2770_dai_driver));
+}
+
+static const struct reg_default tas2770_reg_defaults[] = {
+	{ TAS2770_PAGE, 0x00 },
+	{ TAS2770_SW_RST, 0x00 },
+	{ TAS2770_PWR_CTRL, 0x0e },
+	{ TAS2770_PLAY_CFG_REG0, 0x10 },
+	{ TAS2770_PLAY_CFG_REG1, 0x01 },
+	{ TAS2770_PLAY_CFG_REG2, 0x00 },
+	{ TAS2770_MSC_CFG_REG0, 0x07 },
+	{ TAS2770_TDM_CFG_REG1, 0x02 },
+	{ TAS2770_TDM_CFG_REG2, 0x0a },
+	{ TAS2770_TDM_CFG_REG3, 0x10 },
+	{ TAS2770_INT_MASK_REG0, 0xfc },
+	{ TAS2770_INT_MASK_REG1, 0xb1 },
+	{ TAS2770_INT_CFG, 0x05 },
+	{ TAS2770_MISC_IRQ, 0x81 },
+	{ TAS2770_CLK_CGF, 0x0c },
+
+};
+
+static bool tas2770_volatile(struct device *dev, unsigned int reg)
+{
+	switch (reg) {
+	case TAS2770_PAGE: /* regmap implementation requires this */
+	case TAS2770_SW_RST: /* always clears after write */
+	case TAS2770_BO_PRV_REG0:/* has a self clearing bit */
+	case TAS2770_LVE_INT_REG0:
+	case TAS2770_LVE_INT_REG1:
+	case TAS2770_LAT_INT_REG0:/* Sticky interrupt flags */
+	case TAS2770_LAT_INT_REG1:/* Sticky interrupt flags */
+	case TAS2770_VBAT_MSB:
+	case TAS2770_VBAT_LSB:
+	case TAS2770_TEMP_MSB:
+	case TAS2770_TEMP_LSB:
+		return true;
+	}
+	return false;
+}
+
+static bool tas2770_writeable(struct device *dev, unsigned int reg)
+{
+	switch (reg) {
+	case TAS2770_LVE_INT_REG0:
+	case TAS2770_LVE_INT_REG1:
+	case TAS2770_LAT_INT_REG0:
+	case TAS2770_LAT_INT_REG1:
+	case TAS2770_VBAT_MSB:
+	case TAS2770_VBAT_LSB:
+	case TAS2770_TEMP_MSB:
+	case TAS2770_TEMP_LSB:
+	case TAS2770_TDM_CLK_DETC:
+	case TAS2770_REV_AND_GPID:
+		return false;
+	}
+	return true;
+}
+
+static const struct regmap_range_cfg tas2770_regmap_ranges[] = {
+	{
+		.range_min = 0,
+		.range_max = 1 * 128,
+		.selector_reg = TAS2770_PAGE,
+		.selector_mask = 0xff,
+		.selector_shift = 0,
+		.window_start = 0,
+		.window_len = 128,
+	},
+};
+
+static const struct regmap_config tas2770_i2c_regmap = {
+	.reg_bits = 8,
+	.val_bits = 8,
+	.writeable_reg = tas2770_writeable,
+	.volatile_reg = tas2770_volatile,
+	.reg_defaults = tas2770_reg_defaults,
+	.num_reg_defaults = ARRAY_SIZE(tas2770_reg_defaults),
+	.cache_type = REGCACHE_RBTREE,
+	.ranges = tas2770_regmap_ranges,
+	.num_ranges = ARRAY_SIZE(tas2770_regmap_ranges),
+	.max_register = 1 * 128,
+};
+
+static int tas2770_parse_dt(struct device *dev, struct tas2770_priv *tas2770)
+{
+	int rc = 0;
+
+	rc = fwnode_property_read_u32(dev->fwnode, "ti,asi-format",
+					&tas2770->asi_format);
+	if (rc) {
+		dev_err(tas2770->dev, "Looking up %s property failed %d\n",
+			"ti,asi-format", rc);
+		goto end;
+	}
+
+	rc = fwnode_property_read_u32(dev->fwnode, "ti,imon-slot-no",
+			&tas2770->i_sense_slot);
+	if (rc) {
+		dev_err(tas2770->dev, "Looking up %s property failed %d\n",
+			"ti,imon-slot-no", rc);
+		goto end;
+	}
+
+	rc = fwnode_property_read_u32(dev->fwnode, "ti,vmon-slot-no",
+				&tas2770->v_sense_slot);
+	if (rc) {
+		dev_err(tas2770->dev, "Looking up %s property failed %d\n",
+			"ti,vmon-slot-no", rc);
+		goto end;
+	}
+
+end:
+	return rc;
+}
+
+static int tas2770_i2c_probe(struct i2c_client *client,
+			const struct i2c_device_id *id)
+{
+	struct tas2770_priv *tas2770;
+	int result;
+
+	tas2770 = devm_kzalloc(&client->dev,
+		sizeof(struct tas2770_priv), GFP_KERNEL);
+	if (!tas2770)
+		return -ENOMEM;
+	tas2770->dev = &client->dev;
+
+	i2c_set_clientdata(client, tas2770);
+	dev_set_drvdata(&client->dev, tas2770);
+	tas2770->power_state = TAS2770_POWER_SHUTDOWN;
+
+	tas2770->regmap = devm_regmap_init_i2c(client, &tas2770_i2c_regmap);
+	if (IS_ERR(tas2770->regmap)) {
+		result = PTR_ERR(tas2770->regmap);
+		dev_err(&client->dev, "Failed to allocate register map: %d\n",
+					result);
+		goto end;
+	}
+
+	if (client->dev.of_node) {
+		result = tas2770_parse_dt(&client->dev, tas2770);
+		if (result) {
+			dev_err(tas2770->dev, "%s: Failed to parse devicetree\n",
+				__func__);
+			goto end;
+		}
+	}
+
+	tas2770->reset_gpio = devm_gpiod_get_optional(tas2770->dev,
+							  "reset-gpio",
+						      GPIOD_OUT_HIGH);
+	if (IS_ERR(tas2770->reset_gpio)) {
+		if (PTR_ERR(tas2770->reset_gpio) == -EPROBE_DEFER) {
+			tas2770->reset_gpio = NULL;
+			return -EPROBE_DEFER;
+		}
+	}
+
+	tas2770->channel_size = 0;
+	tas2770->slot_width = 0;
+
+	tas2770_reset(tas2770);
+
+	result = tas2770_register_codec(tas2770);
+	if (result)
+		dev_err(tas2770->dev, "Register codec failed.\n");
+
+end:
+	return result;
+}
+
+static int tas2770_i2c_remove(struct i2c_client *client)
+{
+	pm_runtime_disable(&client->dev);
+	return 0;
+}
+
+
+static const struct i2c_device_id tas2770_i2c_id[] = {
+	{ "tas2770", 0},
+	{ }
+};
+MODULE_DEVICE_TABLE(i2c, tas2770_i2c_id);
+
+#if defined(CONFIG_OF)
+static const struct of_device_id tas2770_of_match[] = {
+	{ .compatible = "ti,tas2770" },
+	{},
+};
+MODULE_DEVICE_TABLE(of, tas2770_of_match);
+#endif
+
+static struct i2c_driver tas2770_i2c_driver = {
+	.driver = {
+		.name   = "tas2770",
+		.of_match_table = of_match_ptr(tas2770_of_match),
+	},
+	.probe      = tas2770_i2c_probe,
+	.remove     = tas2770_i2c_remove,
+	.id_table   = tas2770_i2c_id,
+};
+
+module_i2c_driver(tas2770_i2c_driver);
+
+MODULE_AUTHOR("Shi Fu <shifu0704@thundersoft.com>");
+MODULE_DESCRIPTION("TAS2770 I2C Smart Amplifier driver");
+MODULE_LICENSE("GPL v2");
diff --git a/sound/soc/codecs/tas2770.h b/sound/soc/codecs/tas2770.h
new file mode 100644
index 000000000000..cbb858369fe6
--- /dev/null
+++ b/sound/soc/codecs/tas2770.h
@@ -0,0 +1,143 @@
+/* SPDX-License-Identifier: GPL-2.0
+ *
+ * ALSA SoC TAS2770 codec driver
+ *
+ *  Copyright (C) 2016-2017 Texas Instruments Incorporated - http://www.ti.com/
+ */
+#ifndef __TAS2770__
+#define __TAS2770__
+
+/* Book Control Register (available in page0 of each book) */
+#define TAS2770_BOOKCTL_PAGE            0
+#define TAS2770_BOOKCTL_REG         127
+#define TAS2770_REG(page, reg)        ((page * 128) + reg)
+    /* Page */
+#define TAS2770_PAGE  TAS2770_REG(0X0, 0x00)
+#define TAS2770_PAGE_PAGE_MASK  255
+    /* Software Reset */
+#define TAS2770_SW_RST  TAS2770_REG(0X0, 0x01)
+#define TAS2770_RST  BIT(0)
+    /* Power Control */
+#define TAS2770_PWR_CTRL  TAS2770_REG(0X0, 0x02)
+#define TAS2770_PWR_CTRL_MASK  0x3
+#define TAS2770_PWR_CTRL_ACTIVE  0x0
+#define TAS2770_PWR_CTRL_MUTE  BIT(0)
+#define TAS2770_PWR_CTRL_SHUTDOWN  0x2
+    /* Playback Configuration Reg0 */
+#define TAS2770_PLAY_CFG_REG0  TAS2770_REG(0X0, 0x03)
+    /* Playback Configuration Reg1 */
+#define TAS2770_PLAY_CFG_REG1  TAS2770_REG(0X0, 0x04)
+    /* Playback Configuration Reg2 */
+#define TAS2770_PLAY_CFG_REG2  TAS2770_REG(0X0, 0x05)
+#define TAS2770_PLAY_CFG_REG2_VMAX 0xc9
+    /* Misc Configuration Reg0 */
+#define TAS2770_MSC_CFG_REG0  TAS2770_REG(0X0, 0x07)
+    /* TDM Configuration Reg0 */
+#define TAS2770_TDM_CFG_REG0  TAS2770_REG(0X0, 0x0A)
+#define TAS2770_TDM_CFG_REG0_SMP_MASK  BIT(5)
+#define TAS2770_TDM_CFG_REG0_SMP_48KHZ  0x0
+#define TAS2770_TDM_CFG_REG0_SMP_44_1KHZ  BIT(5)
+#define TAS2770_TDM_CFG_REG0_31_MASK  0xe
+#define TAS2770_TDM_CFG_REG0_31_44_1_48KHZ  0x6
+#define TAS2770_TDM_CFG_REG0_31_88_2_96KHZ  0x8
+#define TAS2770_TDM_CFG_REG0_31_176_4_192KHZ  0xa
+    /* TDM Configuration Reg1 */
+#define TAS2770_TDM_CFG_REG1  TAS2770_REG(0X0, 0x0B)
+#define TAS2770_TDM_CFG_REG1_MASK 0x3e
+#define TAS2770_TDM_CFG_REG1_51_SHIFT  1
+#define TAS2770_TDM_CFG_REG1_RX_MASK  BIT(0)
+#define TAS2770_TDM_CFG_REG1_RX_RSING  0x0
+#define TAS2770_TDM_CFG_REG1_RX_FALING  BIT(0)
+    /* TDM Configuration Reg2 */
+#define TAS2770_TDM_CFG_REG2  TAS2770_REG(0X0, 0x0C)
+#define TAS2770_TDM_CFG_REG2_RXW_MASK  0xc
+#define TAS2770_TDM_CFG_REG2_RXW_16BITS  0x0
+#define TAS2770_TDM_CFG_REG2_RXW_24BITS  0x8
+#define TAS2770_TDM_CFG_REG2_RXW_32BITS  0xc
+#define TAS2770_TDM_CFG_REG2_RXS_MASK    0x3
+#define TAS2770_TDM_CFG_REG2_RXS_16BITS  0x0
+#define TAS2770_TDM_CFG_REG2_RXS_24BITS  BIT(0)
+#define TAS2770_TDM_CFG_REG2_RXS_32BITS  0x2
+    /* TDM Configuration Reg3 */
+#define TAS2770_TDM_CFG_REG3  TAS2770_REG(0X0, 0x0D)
+#define TAS2770_TDM_CFG_REG3_RXS_MASK  0xf0
+#define TAS2770_TDM_CFG_REG3_RXS_SHIFT 0x4
+#define TAS2770_TDM_CFG_REG3_30_MASK  0xf
+#define TAS2770_TDM_CFG_REG3_30_SHIFT 0
+    /* TDM Configuration Reg5 */
+#define TAS2770_TDM_CFG_REG5  TAS2770_REG(0X0, 0x0F)
+#define TAS2770_TDM_CFG_REG5_VSNS_MASK  BIT(6)
+#define TAS2770_TDM_CFG_REG5_VSNS_ENABLE  BIT(6)
+#define TAS2770_TDM_CFG_REG5_50_MASK  0x3f
+    /* TDM Configuration Reg6 */
+#define TAS2770_TDM_CFG_REG6  TAS2770_REG(0X0, 0x10)
+#define TAS2770_TDM_CFG_REG6_ISNS_MASK  BIT(6)
+#define TAS2770_TDM_CFG_REG6_ISNS_ENABLE  BIT(6)
+#define TAS2770_TDM_CFG_REG6_50_MASK  0x3f
+    /* Brown Out Prevention Reg0 */
+#define TAS2770_BO_PRV_REG0  TAS2770_REG(0X0, 0x1B)
+    /* Interrupt MASK Reg0 */
+#define TAS2770_INT_MASK_REG0  TAS2770_REG(0X0, 0x20)
+#define TAS2770_INT_REG0_DEFAULT  0xfc
+#define TAS2770_INT_MASK_REG0_DISABLE 0xff
+    /* Interrupt MASK Reg1 */
+#define TAS2770_INT_MASK_REG1  TAS2770_REG(0X0, 0x21)
+#define TAS2770_INT_REG1_DEFAULT  0xb1
+#define TAS2770_INT_MASK_REG1_DISABLE 0xff
+    /* Live-Interrupt Reg0 */
+#define TAS2770_LVE_INT_REG0  TAS2770_REG(0X0, 0x22)
+    /* Live-Interrupt Reg1 */
+#define TAS2770_LVE_INT_REG1  TAS2770_REG(0X0, 0x23)
+    /* Latched-Interrupt Reg0 */
+#define TAS2770_LAT_INT_REG0  TAS2770_REG(0X0, 0x24)
+#define TAS2770_LAT_INT_REG0_OCE_FLG  BIT(1)
+#define TAS2770_LAT_INT_REG0_OTE_FLG  BIT(0)
+    /* Latched-Interrupt Reg1 */
+#define TAS2770_LAT_INT_REG1  TAS2770_REG(0X0, 0x25)
+#define TAS2770_LAT_INT_REG1_VBA_TOV  BIT(3)
+#define TAS2770_LAT_INT_REG1_VBA_TUV  BIT(2)
+#define TAS2770_LAT_INT_REG1_BOUT_FLG  BIT(1)
+    /* VBAT MSB */
+#define TAS2770_VBAT_MSB  TAS2770_REG(0X0, 0x27)
+    /* VBAT LSB */
+#define TAS2770_VBAT_LSB  TAS2770_REG(0X0, 0x28)
+    /* TEMP MSB */
+#define TAS2770_TEMP_MSB  TAS2770_REG(0X0, 0x29)
+    /* TEMP LSB */
+#define TAS2770_TEMP_LSB  TAS2770_REG(0X0, 0x2A)
+    /* Interrupt Configuration */
+#define TAS2770_INT_CFG  TAS2770_REG(0X0, 0x30)
+    /* Misc IRQ */
+#define TAS2770_MISC_IRQ  TAS2770_REG(0X0, 0x32)
+    /* Clock Configuration */
+#define TAS2770_CLK_CGF  TAS2770_REG(0X0, 0x3C)
+    /* TDM Clock detection monitor */
+#define TAS2770_TDM_CLK_DETC  TAS2770_REG(0X0, 0x77)
+    /* Revision and PG ID */
+#define TAS2770_REV_AND_GPID  TAS2770_REG(0X0, 0x7D)
+
+#define TAS2770_POWER_ACTIVE 0
+#define TAS2770_POWER_MUTE 1
+#define TAS2770_POWER_SHUTDOWN 2
+#define ERROR_OVER_CURRENT  0x0000001
+#define ERROR_DIE_OVERTEMP  0x0000002
+#define ERROR_OVER_VOLTAGE  0x0000004
+#define ERROR_UNDER_VOLTAGE 0x0000008
+#define ERROR_BROWNOUT      0x0000010
+#define ERROR_CLASSD_PWR    0x0000020
+
+struct tas2770_priv {
+	struct device *dev;
+	struct regmap *regmap;
+	struct snd_soc_component *component;
+	int power_state;
+	int asi_format;
+	struct gpio_desc *reset_gpio;
+	int sampling_rate;
+	int channel_size;
+	int slot_width;
+	int v_sense_slot;
+	int i_sense_slot;
+};
+
+#endif /* __TAS2770__ */
diff --git a/sound/soc/codecs/tlv320aic31xx.c b/sound/soc/codecs/tlv320aic31xx.c
index df627a08def9..f6f19fdc72f5 100644
--- a/sound/soc/codecs/tlv320aic31xx.c
+++ b/sound/soc/codecs/tlv320aic31xx.c
@@ -171,6 +171,7 @@ struct aic31xx_priv {
 	int rate_div_line;
 	bool master_dapm_route_applied;
 	int irq;
+	u8 ocmv; /* output common-mode voltage */
 };
 
 struct aic31xx_rate_divs {
@@ -1312,6 +1313,11 @@ static int aic31xx_codec_probe(struct snd_soc_component *component)
 	if (ret)
 		return ret;
 
+	/* set output common-mode voltage */
+	snd_soc_component_update_bits(component, AIC31XX_HPDRIVER,
+				      AIC31XX_HPD_OCMV_MASK,
+				      aic31xx->ocmv << AIC31XX_HPD_OCMV_SHIFT);
+
 	return 0;
 }
 
@@ -1501,6 +1507,43 @@ exit:
 		return IRQ_NONE;
 }
 
+static void aic31xx_configure_ocmv(struct aic31xx_priv *priv)
+{
+	struct device *dev = priv->dev;
+	int dvdd, avdd;
+	u32 value;
+
+	if (dev->fwnode &&
+	    fwnode_property_read_u32(dev->fwnode, "ai31xx-ocmv", &value)) {
+		/* OCMV setting is forced by DT */
+		if (value <= 3) {
+			priv->ocmv = value;
+			return;
+		}
+	}
+
+	avdd = regulator_get_voltage(priv->supplies[3].consumer);
+	dvdd = regulator_get_voltage(priv->supplies[5].consumer);
+
+	if (avdd > 3600000 || dvdd > 1950000) {
+		dev_warn(dev,
+			 "Too high supply voltage(s) AVDD: %d, DVDD: %d\n",
+			 avdd, dvdd);
+	} else if (avdd == 3600000 && dvdd == 1950000) {
+		priv->ocmv = AIC31XX_HPD_OCMV_1_8V;
+	} else if (avdd >= 3300000 && dvdd >= 1800000) {
+		priv->ocmv = AIC31XX_HPD_OCMV_1_65V;
+	} else if (avdd >= 3000000 && dvdd >= 1650000) {
+		priv->ocmv = AIC31XX_HPD_OCMV_1_5V;
+	} else if (avdd >= 2700000 && dvdd >= 1525000) {
+		priv->ocmv = AIC31XX_HPD_OCMV_1_35V;
+	} else {
+		dev_warn(dev,
+			 "Invalid supply voltage(s) AVDD: %d, DVDD: %d\n",
+			 avdd, dvdd);
+	}
+}
+
 static int aic31xx_i2c_probe(struct i2c_client *i2c,
 			     const struct i2c_device_id *id)
 {
@@ -1570,6 +1613,8 @@ static int aic31xx_i2c_probe(struct i2c_client *i2c,
 		return ret;
 	}
 
+	aic31xx_configure_ocmv(aic31xx);
+
 	if (aic31xx->irq > 0) {
 		regmap_update_bits(aic31xx->regmap, AIC31XX_GPIO1,
 				   AIC31XX_GPIO1_FUNC_MASK,
diff --git a/sound/soc/codecs/tlv320aic31xx.h b/sound/soc/codecs/tlv320aic31xx.h
index cb024955c978..83a8c7604cc3 100644
--- a/sound/soc/codecs/tlv320aic31xx.h
+++ b/sound/soc/codecs/tlv320aic31xx.h
@@ -232,6 +232,14 @@ struct aic31xx_pdata {
 #define AIC31XX_HSD_HP			0x01
 #define AIC31XX_HSD_HS			0x03
 
+/* AIC31XX_HPDRIVER */
+#define AIC31XX_HPD_OCMV_MASK		GENMASK(4, 3)
+#define AIC31XX_HPD_OCMV_SHIFT		3
+#define AIC31XX_HPD_OCMV_1_35V		0x0
+#define AIC31XX_HPD_OCMV_1_5V		0x1
+#define AIC31XX_HPD_OCMV_1_65V		0x2
+#define AIC31XX_HPD_OCMV_1_8V		0x3
+
 /* AIC31XX_MICBIAS */
 #define AIC31XX_MICBIAS_MASK		GENMASK(1, 0)
 #define AIC31XX_MICBIAS_SHIFT		0
diff --git a/sound/soc/codecs/tlv320aic32x4.c b/sound/soc/codecs/tlv320aic32x4.c
index 68165de1c8de..b4e9a6c73f90 100644
--- a/sound/soc/codecs/tlv320aic32x4.c
+++ b/sound/soc/codecs/tlv320aic32x4.c
@@ -573,6 +573,9 @@ static int aic32x4_set_dai_sysclk(struct snd_soc_dai *codec_dai,
 	struct clk *pll;
 
 	pll = devm_clk_get(component->dev, "pll");
+	if (IS_ERR(pll))
+		return PTR_ERR(pll);
+
 	mclk = clk_get_parent(pll);
 
 	return clk_set_rate(mclk, freq);
diff --git a/sound/soc/codecs/wcd9335.c b/sound/soc/codecs/wcd9335.c
index f318403133e9..f11ffa28683b 100644
--- a/sound/soc/codecs/wcd9335.c
+++ b/sound/soc/codecs/wcd9335.c
@@ -2837,11 +2837,11 @@ static int wcd9335_codec_enable_dec(struct snd_soc_dapm_widget *w,
 				   TX_HPF_CUT_OFF_FREQ_MASK) >> 5;
 		snd_soc_component_update_bits(comp, tx_vol_ctl_reg, 0x10, 0x10);
 		snd_soc_component_update_bits(comp, dec_cfg_reg, 0x08, 0x00);
-			if (hpf_coff_freq != CF_MIN_3DB_150HZ) {
-				snd_soc_component_update_bits(comp, dec_cfg_reg,
-						    TX_HPF_CUT_OFF_FREQ_MASK,
-						    hpf_coff_freq << 5);
-			}
+		if (hpf_coff_freq != CF_MIN_3DB_150HZ) {
+			snd_soc_component_update_bits(comp, dec_cfg_reg,
+						      TX_HPF_CUT_OFF_FREQ_MASK,
+						      hpf_coff_freq << 5);
+		}
 		break;
 	case SND_SOC_DAPM_POST_PMD:
 		snd_soc_component_update_bits(comp, tx_vol_ctl_reg, 0x10, 0x00);
diff --git a/sound/soc/codecs/wm2200.c b/sound/soc/codecs/wm2200.c
index cf64e109c658..7b087d94141b 100644
--- a/sound/soc/codecs/wm2200.c
+++ b/sound/soc/codecs/wm2200.c
@@ -2410,6 +2410,8 @@ static int wm2200_i2c_probe(struct i2c_client *i2c,
 
 err_pm_runtime:
 	pm_runtime_disable(&i2c->dev);
+	if (i2c->irq)
+		free_irq(i2c->irq, wm2200);
 err_reset:
 	if (wm2200->pdata.reset)
 		gpio_set_value_cansleep(wm2200->pdata.reset, 0);
@@ -2426,12 +2428,15 @@ static int wm2200_i2c_remove(struct i2c_client *i2c)
 {
 	struct wm2200_priv *wm2200 = i2c_get_clientdata(i2c);
 
+	pm_runtime_disable(&i2c->dev);
 	if (i2c->irq)
 		free_irq(i2c->irq, wm2200);
 	if (wm2200->pdata.reset)
 		gpio_set_value_cansleep(wm2200->pdata.reset, 0);
 	if (wm2200->pdata.ldo_ena)
 		gpio_set_value_cansleep(wm2200->pdata.ldo_ena, 0);
+	regulator_bulk_disable(ARRAY_SIZE(wm2200->core_supplies),
+			       wm2200->core_supplies);
 
 	return 0;
 }
diff --git a/sound/soc/codecs/wm5100.c b/sound/soc/codecs/wm5100.c
index 4af0e519e623..91cc63c5a51f 100644
--- a/sound/soc/codecs/wm5100.c
+++ b/sound/soc/codecs/wm5100.c
@@ -2617,6 +2617,7 @@ static int wm5100_i2c_probe(struct i2c_client *i2c,
 	return ret;
 
 err_reset:
+	pm_runtime_disable(&i2c->dev);
 	if (i2c->irq)
 		free_irq(i2c->irq, wm5100);
 	wm5100_free_gpio(i2c);
@@ -2640,6 +2641,7 @@ static int wm5100_i2c_remove(struct i2c_client *i2c)
 {
 	struct wm5100_priv *wm5100 = i2c_get_clientdata(i2c);
 
+	pm_runtime_disable(&i2c->dev);
 	if (i2c->irq)
 		free_irq(i2c->irq, wm5100);
 	wm5100_free_gpio(i2c);
diff --git a/sound/soc/codecs/wm8904.c b/sound/soc/codecs/wm8904.c
index bcb3c9d5abf0..7d7ea15d73e0 100644
--- a/sound/soc/codecs/wm8904.c
+++ b/sound/soc/codecs/wm8904.c
@@ -1410,34 +1410,6 @@ static int wm8904_hw_params(struct snd_pcm_substream *substream,
 	return 0;
 }
 
-
-static int wm8904_set_sysclk(struct snd_soc_dai *dai, int clk_id,
-			     unsigned int freq, int dir)
-{
-	struct snd_soc_component *component = dai->component;
-	struct wm8904_priv *priv = snd_soc_component_get_drvdata(component);
-
-	switch (clk_id) {
-	case WM8904_CLK_MCLK:
-		priv->sysclk_src = clk_id;
-		priv->mclk_rate = freq;
-		break;
-
-	case WM8904_CLK_FLL:
-		priv->sysclk_src = clk_id;
-		break;
-
-	default:
-		return -EINVAL;
-	}
-
-	dev_dbg(dai->dev, "Clock source is %d at %uHz\n", clk_id, freq);
-
-	wm8904_configure_clocking(component);
-
-	return 0;
-}
-
 static int wm8904_set_fmt(struct snd_soc_dai *dai, unsigned int fmt)
 {
 	struct snd_soc_component *component = dai->component;
@@ -1824,6 +1796,50 @@ out:
 	return 0;
 }
 
+static int wm8904_set_sysclk(struct snd_soc_dai *dai, int clk_id,
+			     unsigned int freq, int dir)
+{
+	struct snd_soc_component *component = dai->component;
+	struct wm8904_priv *priv = snd_soc_component_get_drvdata(component);
+	unsigned long mclk_freq;
+	int ret;
+
+	switch (clk_id) {
+	case WM8904_CLK_AUTO:
+		mclk_freq = clk_get_rate(priv->mclk);
+		/* enable FLL if a different sysclk is desired */
+		if (mclk_freq != freq) {
+			priv->sysclk_src = WM8904_CLK_FLL;
+			ret = wm8904_set_fll(dai, WM8904_FLL_MCLK,
+					     WM8904_FLL_MCLK,
+					     mclk_freq, freq);
+			if (ret)
+				return ret;
+			break;
+		}
+		clk_id = WM8904_CLK_MCLK;
+		/* fallthrough */
+
+	case WM8904_CLK_MCLK:
+		priv->sysclk_src = clk_id;
+		priv->mclk_rate = freq;
+		break;
+
+	case WM8904_CLK_FLL:
+		priv->sysclk_src = clk_id;
+		break;
+
+	default:
+		return -EINVAL;
+	}
+
+	dev_dbg(dai->dev, "Clock source is %d at %uHz\n", clk_id, freq);
+
+	wm8904_configure_clocking(component);
+
+	return 0;
+}
+
 static int wm8904_digital_mute(struct snd_soc_dai *codec_dai, int mute)
 {
 	struct snd_soc_component *component = codec_dai->component;
@@ -1917,6 +1933,7 @@ static int wm8904_set_bias_level(struct snd_soc_component *component,
 		snd_soc_component_update_bits(component, WM8904_BIAS_CONTROL_0,
 				    WM8904_BIAS_ENA, 0);
 
+		snd_soc_component_write(component, WM8904_SW_RESET_AND_ID, 0);
 		regcache_cache_only(wm8904->regmap, true);
 		regcache_mark_dirty(wm8904->regmap);
 
diff --git a/sound/soc/codecs/wm8904.h b/sound/soc/codecs/wm8904.h
index c1bca52f9927..de6340446b1f 100644
--- a/sound/soc/codecs/wm8904.h
+++ b/sound/soc/codecs/wm8904.h
@@ -10,6 +10,7 @@
 #ifndef _WM8904_H
 #define _WM8904_H
 
+#define WM8904_CLK_AUTO 0
 #define WM8904_CLK_MCLK 1
 #define WM8904_CLK_FLL  2
 
diff --git a/sound/soc/codecs/wm8958-dsp2.c b/sound/soc/codecs/wm8958-dsp2.c
index 18535b326680..ca42445b649d 100644
--- a/sound/soc/codecs/wm8958-dsp2.c
+++ b/sound/soc/codecs/wm8958-dsp2.c
@@ -25,6 +25,8 @@
 #include <linux/mfd/wm8994/pdata.h>
 #include <linux/mfd/wm8994/gpio.h>
 
+#include <asm/unaligned.h>
+
 #include "wm8994.h"
 
 #define WM_FW_BLOCK_INFO 0xff
@@ -58,18 +60,15 @@ static int wm8958_dsp2_fw(struct snd_soc_component *component, const char *name,
 	}
 
 	if (memcmp(fw->data, "WMFW", 4) != 0) {
-		memcpy(&data32, fw->data, sizeof(data32));
-		data32 = be32_to_cpu(data32);
+		data32 = get_unaligned_be32(fw->data);
 		dev_err(component->dev, "%s: firmware has bad file magic %08x\n",
 			name, data32);
 		goto err;
 	}
 
-	memcpy(&data32, fw->data + 4, sizeof(data32));
-	len = be32_to_cpu(data32);
+	len = get_unaligned_be32(fw->data + 4);
+	data32 = get_unaligned_be32(fw->data + 8);
 
-	memcpy(&data32, fw->data + 8, sizeof(data32));
-	data32 = be32_to_cpu(data32);
 	if ((data32 >> 24) & 0xff) {
 		dev_err(component->dev, "%s: unsupported firmware version %d\n",
 			name, (data32 >> 24) & 0xff);
@@ -87,9 +86,8 @@ static int wm8958_dsp2_fw(struct snd_soc_component *component, const char *name,
 	}
 
 	if (check) {
-		memcpy(&data64, fw->data + 24, sizeof(u64));
-		dev_info(component->dev, "%s timestamp %llx\n",
-			 name, be64_to_cpu(data64));
+		data64 = get_unaligned_be64(fw->data + 24);
+		dev_info(component->dev, "%s timestamp %llx\n",  name, data64);
 	} else {
 		snd_soc_component_write(component, 0x102, 0x2);
 		snd_soc_component_write(component, 0x900, 0x2);
@@ -104,8 +102,7 @@ static int wm8958_dsp2_fw(struct snd_soc_component *component, const char *name,
 			goto err;
 		}
 
-		memcpy(&data32, data + 4, sizeof(data32));
-		block_len = be32_to_cpu(data32);
+		block_len = get_unaligned_be32(data + 4);
 		if (block_len + 8 > len) {
 			dev_err(component->dev, "%zd byte block longer than file\n",
 				block_len);
@@ -116,8 +113,7 @@ static int wm8958_dsp2_fw(struct snd_soc_component *component, const char *name,
 			goto err;
 		}
 
-		memcpy(&data32, data, sizeof(data32));
-		data32 = be32_to_cpu(data32);
+		data32 = get_unaligned_be32(data);
 
 		switch ((data32 >> 24) & 0xff) {
 		case WM_FW_BLOCK_INFO:
diff --git a/sound/soc/codecs/wm8994.c b/sound/soc/codecs/wm8994.c
index d5fb7f5dd551..15ce64a48a87 100644
--- a/sound/soc/codecs/wm8994.c
+++ b/sound/soc/codecs/wm8994.c
@@ -167,12 +167,12 @@ static int configure_aif_clock(struct snd_soc_component *component, int aif)
 
 	switch (wm8994->sysclk[aif]) {
 	case WM8994_SYSCLK_MCLK1:
-		rate = wm8994->mclk[0];
+		rate = wm8994->mclk_rate[0];
 		break;
 
 	case WM8994_SYSCLK_MCLK2:
 		reg1 |= 0x8;
-		rate = wm8994->mclk[1];
+		rate = wm8994->mclk_rate[1];
 		break;
 
 	case WM8994_SYSCLK_FLL1:
@@ -1038,6 +1038,45 @@ static bool wm8994_check_class_w_digital(struct snd_soc_component *component)
 	return true;
 }
 
+static int aif_mclk_set(struct snd_soc_component *component, int aif, bool enable)
+{
+	struct wm8994_priv *wm8994 = snd_soc_component_get_drvdata(component);
+	unsigned int offset, val, clk_idx;
+	int ret;
+
+	if (aif)
+		offset = 4;
+	else
+		offset = 0;
+
+	val = snd_soc_component_read32(component, WM8994_AIF1_CLOCKING_1 + offset);
+	val &= WM8994_AIF1CLK_SRC_MASK;
+
+	switch (val) {
+	case 0:
+		clk_idx = WM8994_MCLK1;
+		break;
+	case 1:
+		clk_idx = WM8994_MCLK2;
+		break;
+	default:
+		return 0;
+	}
+
+	if (enable) {
+		ret = clk_prepare_enable(wm8994->mclk[clk_idx].clk);
+		if (ret < 0) {
+			dev_err(component->dev,	"Failed to enable MCLK%d\n",
+				clk_idx);
+			return ret;
+		}
+	} else {
+		clk_disable_unprepare(wm8994->mclk[clk_idx].clk);
+	}
+
+	return 0;
+}
+
 static int aif1clk_ev(struct snd_soc_dapm_widget *w,
 		      struct snd_kcontrol *kcontrol, int event)
 {
@@ -1045,7 +1084,7 @@ static int aif1clk_ev(struct snd_soc_dapm_widget *w,
 	struct wm8994_priv *wm8994 = snd_soc_component_get_drvdata(component);
 	struct wm8994 *control = wm8994->wm8994;
 	int mask = WM8994_AIF1DAC1L_ENA | WM8994_AIF1DAC1R_ENA;
-	int i;
+	int ret, i;
 	int dac;
 	int adc;
 	int val;
@@ -1061,6 +1100,10 @@ static int aif1clk_ev(struct snd_soc_dapm_widget *w,
 
 	switch (event) {
 	case SND_SOC_DAPM_PRE_PMU:
+		ret = aif_mclk_set(component, 0, true);
+		if (ret < 0)
+			return ret;
+
 		/* Don't enable timeslot 2 if not in use */
 		if (wm8994->channels[0] <= 2)
 			mask &= ~(WM8994_AIF1DAC2L_ENA | WM8994_AIF1DAC2R_ENA);
@@ -1133,6 +1176,12 @@ static int aif1clk_ev(struct snd_soc_dapm_widget *w,
 		break;
 	}
 
+	switch (event) {
+	case SND_SOC_DAPM_POST_PMD:
+		aif_mclk_set(component, 0, false);
+		break;
+	}
+
 	return 0;
 }
 
@@ -1140,13 +1189,17 @@ static int aif2clk_ev(struct snd_soc_dapm_widget *w,
 		      struct snd_kcontrol *kcontrol, int event)
 {
 	struct snd_soc_component *component = snd_soc_dapm_to_component(w->dapm);
-	int i;
+	int ret, i;
 	int dac;
 	int adc;
 	int val;
 
 	switch (event) {
 	case SND_SOC_DAPM_PRE_PMU:
+		ret = aif_mclk_set(component, 1, true);
+		if (ret < 0)
+			return ret;
+
 		val = snd_soc_component_read32(component, WM8994_AIF2_CONTROL_1);
 		if ((val & WM8994_AIF2ADCL_SRC) &&
 		    (val & WM8994_AIF2ADCR_SRC))
@@ -1218,6 +1271,12 @@ static int aif2clk_ev(struct snd_soc_dapm_widget *w,
 		break;
 	}
 
+	switch (event) {
+	case SND_SOC_DAPM_POST_PMD:
+		aif_mclk_set(component, 1, false);
+		break;
+	}
+
 	return 0;
 }
 
@@ -1623,10 +1682,10 @@ SND_SOC_DAPM_POST("Late Disable PGA", late_disable_ev)
 static const struct snd_soc_dapm_widget wm8994_lateclk_widgets[] = {
 SND_SOC_DAPM_SUPPLY("AIF1CLK", WM8994_AIF1_CLOCKING_1, 0, 0, aif1clk_ev,
 		    SND_SOC_DAPM_PRE_PMU | SND_SOC_DAPM_POST_PMU |
-		    SND_SOC_DAPM_PRE_PMD),
+		    SND_SOC_DAPM_PRE_PMD | SND_SOC_DAPM_POST_PMD),
 SND_SOC_DAPM_SUPPLY("AIF2CLK", WM8994_AIF2_CLOCKING_1, 0, 0, aif2clk_ev,
 		    SND_SOC_DAPM_PRE_PMU | SND_SOC_DAPM_POST_PMU |
-		    SND_SOC_DAPM_PRE_PMD),
+		    SND_SOC_DAPM_PRE_PMD | SND_SOC_DAPM_POST_PMD),
 SND_SOC_DAPM_PGA("Direct Voice", SND_SOC_NOPM, 0, 0, NULL, 0),
 SND_SOC_DAPM_MIXER("SPKL", WM8994_POWER_MANAGEMENT_3, 8, 0,
 		   left_speaker_mixer, ARRAY_SIZE(left_speaker_mixer)),
@@ -2141,6 +2200,7 @@ static int _wm8994_set_fll(struct snd_soc_component *component, int id, int src,
 	u16 reg, clk1, aif_reg, aif_src;
 	unsigned long timeout;
 	bool was_enabled;
+	struct clk *mclk;
 
 	switch (id) {
 	case WM8994_FLL1:
@@ -2216,6 +2276,27 @@ static int _wm8994_set_fll(struct snd_soc_component *component, int id, int src,
 	snd_soc_component_update_bits(component, WM8994_FLL1_CONTROL_1 + reg_offset,
 			    WM8994_FLL1_ENA, 0);
 
+	/* Disable MCLK if needed before we possibly change to new clock parent */
+	if (was_enabled) {
+		reg = snd_soc_component_read32(component, WM8994_FLL1_CONTROL_5
+							+ reg_offset);
+		reg = ((reg & WM8994_FLL1_REFCLK_SRC_MASK)
+			>> WM8994_FLL1_REFCLK_SRC_SHIFT) + 1;
+
+		switch (reg) {
+		case WM8994_FLL_SRC_MCLK1:
+			mclk = wm8994->mclk[WM8994_MCLK1].clk;
+			break;
+		case WM8994_FLL_SRC_MCLK2:
+			mclk = wm8994->mclk[WM8994_MCLK2].clk;
+			break;
+		default:
+			mclk = NULL;
+		}
+
+		clk_disable_unprepare(mclk);
+	}
+
 	if (wm8994->fll_byp && src == WM8994_FLL_SRC_BCLK &&
 	    freq_in == freq_out && freq_out) {
 		dev_dbg(component->dev, "Bypassing FLL%d\n", id + 1);
@@ -2260,10 +2341,29 @@ static int _wm8994_set_fll(struct snd_soc_component *component, int id, int src,
 	/* Clear any pending completion from a previous failure */
 	try_wait_for_completion(&wm8994->fll_locked[id]);
 
+	switch (src) {
+	case WM8994_FLL_SRC_MCLK1:
+		mclk = wm8994->mclk[WM8994_MCLK1].clk;
+		break;
+	case WM8994_FLL_SRC_MCLK2:
+		mclk = wm8994->mclk[WM8994_MCLK2].clk;
+		break;
+	default:
+		mclk = NULL;
+	}
+
 	/* Enable (with fractional mode if required) */
 	if (freq_out) {
+		ret = clk_prepare_enable(mclk);
+		if (ret < 0) {
+			dev_err(component->dev, "Failed to enable MCLK for FLL%d\n",
+				id + 1);
+			return ret;
+		}
+
 		/* Enable VMID if we need it */
 		if (!was_enabled) {
+
 			active_reference(component);
 
 			switch (control->type) {
@@ -2372,12 +2472,29 @@ static int wm8994_set_fll(struct snd_soc_dai *dai, int id, int src,
 	return _wm8994_set_fll(dai->component, id, src, freq_in, freq_out);
 }
 
+static int wm8994_set_mclk_rate(struct wm8994_priv *wm8994, unsigned int id,
+				unsigned int *freq)
+{
+	int ret;
+
+	if (!wm8994->mclk[id].clk || *freq == wm8994->mclk_rate[id])
+		return 0;
+
+	ret = clk_set_rate(wm8994->mclk[id].clk, *freq);
+	if (ret < 0)
+		return ret;
+
+	*freq = clk_get_rate(wm8994->mclk[id].clk);
+
+	return 0;
+}
+
 static int wm8994_set_dai_sysclk(struct snd_soc_dai *dai,
 		int clk_id, unsigned int freq, int dir)
 {
 	struct snd_soc_component *component = dai->component;
 	struct wm8994_priv *wm8994 = snd_soc_component_get_drvdata(component);
-	int i;
+	int ret, i;
 
 	switch (dai->id) {
 	case 1:
@@ -2392,7 +2509,12 @@ static int wm8994_set_dai_sysclk(struct snd_soc_dai *dai,
 	switch (clk_id) {
 	case WM8994_SYSCLK_MCLK1:
 		wm8994->sysclk[dai->id - 1] = WM8994_SYSCLK_MCLK1;
-		wm8994->mclk[0] = freq;
+
+		ret = wm8994_set_mclk_rate(wm8994, dai->id - 1, &freq);
+		if (ret < 0)
+			return ret;
+
+		wm8994->mclk_rate[0] = freq;
 		dev_dbg(dai->dev, "AIF%d using MCLK1 at %uHz\n",
 			dai->id, freq);
 		break;
@@ -2400,7 +2522,12 @@ static int wm8994_set_dai_sysclk(struct snd_soc_dai *dai,
 	case WM8994_SYSCLK_MCLK2:
 		/* TODO: Set GPIO AF */
 		wm8994->sysclk[dai->id - 1] = WM8994_SYSCLK_MCLK2;
-		wm8994->mclk[1] = freq;
+
+		ret = wm8994_set_mclk_rate(wm8994, dai->id - 1, &freq);
+		if (ret < 0)
+			return ret;
+
+		wm8994->mclk_rate[1] = freq;
 		dev_dbg(dai->dev, "AIF%d using MCLK2 at %uHz\n",
 			dai->id, freq);
 		break;
@@ -4456,6 +4583,7 @@ static const struct snd_soc_component_driver soc_component_dev_wm8994 = {
 static int wm8994_probe(struct platform_device *pdev)
 {
 	struct wm8994_priv *wm8994;
+	int ret;
 
 	wm8994 = devm_kzalloc(&pdev->dev, sizeof(struct wm8994_priv),
 			      GFP_KERNEL);
@@ -4467,6 +4595,16 @@ static int wm8994_probe(struct platform_device *pdev)
 
 	wm8994->wm8994 = dev_get_drvdata(pdev->dev.parent);
 
+	wm8994->mclk[WM8994_MCLK1].id = "MCLK1";
+	wm8994->mclk[WM8994_MCLK2].id = "MCLK2";
+
+	ret = devm_clk_bulk_get_optional(pdev->dev.parent, ARRAY_SIZE(wm8994->mclk),
+					 wm8994->mclk);
+	if (ret < 0) {
+		dev_err(&pdev->dev, "Failed to get clocks: %d\n", ret);
+		return ret;
+	}
+
 	pm_runtime_enable(&pdev->dev);
 	pm_runtime_idle(&pdev->dev);
 
diff --git a/sound/soc/codecs/wm8994.h b/sound/soc/codecs/wm8994.h
index 1d6f2abe1c11..41c4b126114d 100644
--- a/sound/soc/codecs/wm8994.h
+++ b/sound/soc/codecs/wm8994.h
@@ -6,6 +6,7 @@
 #ifndef _WM8994_H
 #define _WM8994_H
 
+#include <linux/clk.h>
 #include <sound/soc.h>
 #include <linux/firmware.h>
 #include <linux/completion.h>
@@ -14,6 +15,12 @@
 
 #include "wm_hubs.h"
 
+enum {
+	WM8994_MCLK1,
+	WM8994_MCLK2,
+	WM8994_NUM_MCLK
+};
+
 /* Sources for AIF1/2 SYSCLK - use with set_dai_sysclk() */
 #define WM8994_SYSCLK_MCLK1 1
 #define WM8994_SYSCLK_MCLK2 2
@@ -73,9 +80,10 @@ struct wm8994;
 struct wm8994_priv {
 	struct wm_hubs_data hubs;
 	struct wm8994 *wm8994;
+	struct clk_bulk_data mclk[WM8994_NUM_MCLK];
 	int sysclk[2];
 	int sysclk_rate[2];
-	int mclk[2];
+	int mclk_rate[2];
 	int aifclk[2];
 	int aifdiv[2];
 	int channels[2];
diff --git a/sound/soc/codecs/wm_adsp.c b/sound/soc/codecs/wm_adsp.c
index 9b8bb7bbe945..2a9b610f6d43 100644
--- a/sound/soc/codecs/wm_adsp.c
+++ b/sound/soc/codecs/wm_adsp.c
@@ -599,6 +599,9 @@ struct wm_coeff_ctl_ops {
 struct wm_coeff_ctl {
 	const char *name;
 	const char *fw_name;
+	/* Subname is needed to match with firmware */
+	const char *subname;
+	unsigned int subname_len;
 	struct wm_adsp_alg_region alg_region;
 	struct wm_coeff_ctl_ops ops;
 	struct wm_adsp *dsp;
@@ -1399,6 +1402,7 @@ static void wm_adsp_free_ctl_blk(struct wm_coeff_ctl *ctl)
 {
 	kfree(ctl->cache);
 	kfree(ctl->name);
+	kfree(ctl->subname);
 	kfree(ctl);
 }
 
@@ -1472,6 +1476,15 @@ static int wm_adsp_create_control(struct wm_adsp *dsp,
 		ret = -ENOMEM;
 		goto err_ctl;
 	}
+	if (subname) {
+		ctl->subname_len = subname_len;
+		ctl->subname = kmemdup(subname,
+				       strlen(subname) + 1, GFP_KERNEL);
+		if (!ctl->subname) {
+			ret = -ENOMEM;
+			goto err_ctl_name;
+		}
+	}
 	ctl->enabled = 1;
 	ctl->set = 0;
 	ctl->ops.xget = wm_coeff_get;
@@ -1485,7 +1498,7 @@ static int wm_adsp_create_control(struct wm_adsp *dsp,
 	ctl->cache = kzalloc(ctl->len, GFP_KERNEL);
 	if (!ctl->cache) {
 		ret = -ENOMEM;
-		goto err_ctl_name;
+		goto err_ctl_subname;
 	}
 
 	list_add(&ctl->list, &dsp->ctl_list);
@@ -1508,6 +1521,8 @@ static int wm_adsp_create_control(struct wm_adsp *dsp,
 
 err_ctl_cache:
 	kfree(ctl->cache);
+err_ctl_subname:
+	kfree(ctl->subname);
 err_ctl_name:
 	kfree(ctl->name);
 err_ctl:
@@ -1995,6 +2010,70 @@ out:
 	return ret;
 }
 
+/*
+ * Find wm_coeff_ctl with input name as its subname
+ * If not found, return NULL
+ */
+static struct wm_coeff_ctl *wm_adsp_get_ctl(struct wm_adsp *dsp,
+					     const char *name, int type,
+					     unsigned int alg)
+{
+	struct wm_coeff_ctl *pos, *rslt = NULL;
+
+	list_for_each_entry(pos, &dsp->ctl_list, list) {
+		if (!pos->subname)
+			continue;
+		if (strncmp(pos->subname, name, pos->subname_len) == 0 &&
+				pos->alg_region.alg == alg &&
+				pos->alg_region.type == type) {
+			rslt = pos;
+			break;
+		}
+	}
+
+	return rslt;
+}
+
+int wm_adsp_write_ctl(struct wm_adsp *dsp, const char *name, int type,
+		      unsigned int alg, void *buf, size_t len)
+{
+	struct wm_coeff_ctl *ctl;
+	struct snd_kcontrol *kcontrol;
+	int ret;
+
+	ctl = wm_adsp_get_ctl(dsp, name, type, alg);
+	if (!ctl)
+		return -EINVAL;
+
+	if (len > ctl->len)
+		return -EINVAL;
+
+	ret = wm_coeff_write_control(ctl, buf, len);
+
+	kcontrol = snd_soc_card_get_kcontrol(dsp->component->card, ctl->name);
+	snd_ctl_notify(dsp->component->card->snd_card,
+		       SNDRV_CTL_EVENT_MASK_VALUE, &kcontrol->id);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(wm_adsp_write_ctl);
+
+int wm_adsp_read_ctl(struct wm_adsp *dsp, const char *name, int type,
+		     unsigned int alg, void *buf, size_t len)
+{
+	struct wm_coeff_ctl *ctl;
+
+	ctl = wm_adsp_get_ctl(dsp, name, type, alg);
+	if (!ctl)
+		return -EINVAL;
+
+	if (len > ctl->len)
+		return -EINVAL;
+
+	return wm_coeff_read_control(ctl, buf, len);
+}
+EXPORT_SYMBOL_GPL(wm_adsp_read_ctl);
+
 static void wm_adsp_ctl_fixup_base(struct wm_adsp *dsp,
 				  const struct wm_adsp_alg_region *alg_region)
 {
diff --git a/sound/soc/codecs/wm_adsp.h b/sound/soc/codecs/wm_adsp.h
index aa634ef6c9f5..4c481cf20275 100644
--- a/sound/soc/codecs/wm_adsp.h
+++ b/sound/soc/codecs/wm_adsp.h
@@ -201,5 +201,9 @@ int wm_adsp_compr_pointer(struct snd_compr_stream *stream,
 			  struct snd_compr_tstamp *tstamp);
 int wm_adsp_compr_copy(struct snd_compr_stream *stream,
 		       char __user *buf, size_t count);
+int wm_adsp_write_ctl(struct wm_adsp *dsp, const char *name,  int type,
+		      unsigned int alg, void *buf, size_t len);
+int wm_adsp_read_ctl(struct wm_adsp *dsp, const char *name,  int type,
+		      unsigned int alg, void *buf, size_t len);
 
 #endif
diff --git a/sound/soc/dwc/dwc-pcm.c b/sound/soc/dwc/dwc-pcm.c
index a9ae91c4597f..4771eb5fbe2a 100644
--- a/sound/soc/dwc/dwc-pcm.c
+++ b/sound/soc/dwc/dwc-pcm.c
@@ -135,7 +135,8 @@ void dw_pcm_pop_rx(struct dw_i2s_dev *dev)
 	dw_pcm_transfer(dev, false);
 }
 
-static int dw_pcm_open(struct snd_pcm_substream *substream)
+static int dw_pcm_open(struct snd_soc_component *component,
+		       struct snd_pcm_substream *substream)
 {
 	struct snd_pcm_runtime *runtime = substream->runtime;
 	struct snd_soc_pcm_runtime *rtd = substream->private_data;
@@ -148,14 +149,16 @@ static int dw_pcm_open(struct snd_pcm_substream *substream)
 	return 0;
 }
 
-static int dw_pcm_close(struct snd_pcm_substream *substream)
+static int dw_pcm_close(struct snd_soc_component *component,
+			struct snd_pcm_substream *substream)
 {
 	synchronize_rcu();
 	return 0;
 }
 
-static int dw_pcm_hw_params(struct snd_pcm_substream *substream,
-		struct snd_pcm_hw_params *hw_params)
+static int dw_pcm_hw_params(struct snd_soc_component *component,
+			    struct snd_pcm_substream *substream,
+			    struct snd_pcm_hw_params *hw_params)
 {
 	struct snd_pcm_runtime *runtime = substream->runtime;
 	struct dw_i2s_dev *dev = runtime->private_data;
@@ -192,12 +195,14 @@ static int dw_pcm_hw_params(struct snd_pcm_substream *substream,
 		return 0;
 }
 
-static int dw_pcm_hw_free(struct snd_pcm_substream *substream)
+static int dw_pcm_hw_free(struct snd_soc_component *component,
+			  struct snd_pcm_substream *substream)
 {
 	return snd_pcm_lib_free_pages(substream);
 }
 
-static int dw_pcm_trigger(struct snd_pcm_substream *substream, int cmd)
+static int dw_pcm_trigger(struct snd_soc_component *component,
+			  struct snd_pcm_substream *substream, int cmd)
 {
 	struct snd_pcm_runtime *runtime = substream->runtime;
 	struct dw_i2s_dev *dev = runtime->private_data;
@@ -231,7 +236,8 @@ static int dw_pcm_trigger(struct snd_pcm_substream *substream, int cmd)
 	return ret;
 }
 
-static snd_pcm_uframes_t dw_pcm_pointer(struct snd_pcm_substream *substream)
+static snd_pcm_uframes_t dw_pcm_pointer(struct snd_soc_component *component,
+					struct snd_pcm_substream *substream)
 {
 	struct snd_pcm_runtime *runtime = substream->runtime;
 	struct dw_i2s_dev *dev = runtime->private_data;
@@ -245,35 +251,33 @@ static snd_pcm_uframes_t dw_pcm_pointer(struct snd_pcm_substream *substream)
 	return pos < runtime->buffer_size ? pos : 0;
 }
 
-static int dw_pcm_new(struct snd_soc_pcm_runtime *rtd)
+static int dw_pcm_new(struct snd_soc_component *component,
+		      struct snd_soc_pcm_runtime *rtd)
 {
 	size_t size = dw_pcm_hardware.buffer_bytes_max;
 
 	snd_pcm_lib_preallocate_pages_for_all(rtd->pcm,
 			SNDRV_DMA_TYPE_CONTINUOUS,
-			snd_dma_continuous_data(GFP_KERNEL), size, size);
+			NULL, size, size);
 	return 0;
 }
 
-static void dw_pcm_free(struct snd_pcm *pcm)
+static void dw_pcm_free(struct snd_soc_component *component,
+			struct snd_pcm *pcm)
 {
 	snd_pcm_lib_preallocate_free_for_all(pcm);
 }
 
-static const struct snd_pcm_ops dw_pcm_ops = {
-	.open = dw_pcm_open,
-	.close = dw_pcm_close,
-	.ioctl = snd_pcm_lib_ioctl,
-	.hw_params = dw_pcm_hw_params,
-	.hw_free = dw_pcm_hw_free,
-	.trigger = dw_pcm_trigger,
-	.pointer = dw_pcm_pointer,
-};
-
 static const struct snd_soc_component_driver dw_pcm_component = {
-	.pcm_new = dw_pcm_new,
-	.pcm_free = dw_pcm_free,
-	.ops = &dw_pcm_ops,
+	.open		= dw_pcm_open,
+	.close		= dw_pcm_close,
+	.ioctl		= snd_soc_pcm_lib_ioctl,
+	.hw_params	= dw_pcm_hw_params,
+	.hw_free	= dw_pcm_hw_free,
+	.trigger	= dw_pcm_trigger,
+	.pointer	= dw_pcm_pointer,
+	.pcm_construct	= dw_pcm_new,
+	.pcm_destruct	= dw_pcm_free,
 };
 
 int dw_pcm_register(struct platform_device *pdev)
diff --git a/sound/soc/fsl/Kconfig b/sound/soc/fsl/Kconfig
index aa99c008a925..65e8cd4be930 100644
--- a/sound/soc/fsl/Kconfig
+++ b/sound/soc/fsl/Kconfig
@@ -25,6 +25,16 @@ config SND_SOC_FSL_SAI
 	  This option is only useful for out-of-tree drivers since
 	  in-tree drivers select it automatically.
 
+config SND_SOC_FSL_MQS
+	tristate "Medium Quality Sound (MQS) module support"
+	depends on SND_SOC_FSL_SAI
+	select REGMAP_MMIO
+	help
+	  Say Y if you want to add Medium Quality Sound (MQS)
+	  support for the Freescale CPUs.
+	  This option is only useful for out-of-tree drivers since
+	  in-tree drivers select it automatically.
+
 config SND_SOC_FSL_AUDMIX
 	tristate "Audio Mixer (AUDMIX) module support"
 	select REGMAP_MMIO
diff --git a/sound/soc/fsl/Makefile b/sound/soc/fsl/Makefile
index c0dd04422fe9..8cde88c72d93 100644
--- a/sound/soc/fsl/Makefile
+++ b/sound/soc/fsl/Makefile
@@ -23,6 +23,7 @@ snd-soc-fsl-esai-objs := fsl_esai.o
 snd-soc-fsl-micfil-objs := fsl_micfil.o
 snd-soc-fsl-utils-objs := fsl_utils.o
 snd-soc-fsl-dma-objs := fsl_dma.o
+snd-soc-fsl-mqs-objs := fsl_mqs.o
 
 obj-$(CONFIG_SND_SOC_FSL_AUDMIX) += snd-soc-fsl-audmix.o
 obj-$(CONFIG_SND_SOC_FSL_ASOC_CARD) += snd-soc-fsl-asoc-card.o
@@ -33,6 +34,7 @@ obj-$(CONFIG_SND_SOC_FSL_SPDIF) += snd-soc-fsl-spdif.o
 obj-$(CONFIG_SND_SOC_FSL_ESAI) += snd-soc-fsl-esai.o
 obj-$(CONFIG_SND_SOC_FSL_MICFIL) += snd-soc-fsl-micfil.o
 obj-$(CONFIG_SND_SOC_FSL_UTILS) += snd-soc-fsl-utils.o
+obj-$(CONFIG_SND_SOC_FSL_MQS) += snd-soc-fsl-mqs.o
 obj-$(CONFIG_SND_SOC_POWERPC_DMA) += snd-soc-fsl-dma.o
 
 # MPC5200 Platform Support
diff --git a/sound/soc/fsl/fsl_asrc.c b/sound/soc/fsl/fsl_asrc.c
index cfa40ef6b1ca..a3cfceea7d2f 100644
--- a/sound/soc/fsl/fsl_asrc.c
+++ b/sound/soc/fsl/fsl_asrc.c
@@ -115,7 +115,7 @@ static void fsl_asrc_sel_proc(int inrate, int outrate,
  * within range [ANCA, ANCA+ANCB-1], depends on the channels of pair A
  * while pair A and pair C are comparatively independent.
  */
-static int fsl_asrc_request_pair(int channels, struct fsl_asrc_pair *pair)
+int fsl_asrc_request_pair(int channels, struct fsl_asrc_pair *pair)
 {
 	enum asrc_pair_index index = ASRC_INVALID_PAIR;
 	struct fsl_asrc *asrc_priv = pair->asrc_priv;
@@ -158,7 +158,7 @@ static int fsl_asrc_request_pair(int channels, struct fsl_asrc_pair *pair)
  *
  * It clears the resource from asrc_priv and releases the occupied channels.
  */
-static void fsl_asrc_release_pair(struct fsl_asrc_pair *pair)
+void fsl_asrc_release_pair(struct fsl_asrc_pair *pair)
 {
 	struct fsl_asrc *asrc_priv = pair->asrc_priv;
 	enum asrc_pair_index index = pair->index;
@@ -259,14 +259,24 @@ static int fsl_asrc_set_ideal_ratio(struct fsl_asrc_pair *pair,
  * It configures those ASRC registers according to a configuration instance
  * of struct asrc_config which includes in/output sample rate, width, channel
  * and clock settings.
+ *
+ * Note:
+ * The ideal ratio configuration can work with a flexible clock rate setting.
+ * Using IDEAL_RATIO_RATE gives a faster converting speed but overloads ASRC.
+ * For a regular audio playback, the clock rate should not be slower than an
+ * clock rate aligning with the output sample rate; For a use case requiring
+ * faster conversion, set use_ideal_rate to have the faster speed.
  */
-static int fsl_asrc_config_pair(struct fsl_asrc_pair *pair)
+static int fsl_asrc_config_pair(struct fsl_asrc_pair *pair, bool use_ideal_rate)
 {
 	struct asrc_config *config = pair->config;
 	struct fsl_asrc *asrc_priv = pair->asrc_priv;
 	enum asrc_pair_index index = pair->index;
+	enum asrc_word_width input_word_width;
+	enum asrc_word_width output_word_width;
 	u32 inrate, outrate, indiv, outdiv;
-	u32 clk_index[2], div[2];
+	u32 clk_index[2], div[2], rem[2];
+	u64 clk_rate;
 	int in, out, channels;
 	int pre_proc, post_proc;
 	struct clk *clk;
@@ -283,9 +293,32 @@ static int fsl_asrc_config_pair(struct fsl_asrc_pair *pair)
 		return -EINVAL;
 	}
 
-	/* Validate output width */
-	if (config->output_word_width == ASRC_WIDTH_8_BIT) {
-		pair_err("does not support 8bit width output\n");
+	switch (snd_pcm_format_width(config->input_format)) {
+	case 8:
+		input_word_width = ASRC_WIDTH_8_BIT;
+		break;
+	case 16:
+		input_word_width = ASRC_WIDTH_16_BIT;
+		break;
+	case 24:
+		input_word_width = ASRC_WIDTH_24_BIT;
+		break;
+	default:
+		pair_err("does not support this input format, %d\n",
+			 config->input_format);
+		return -EINVAL;
+	}
+
+	switch (snd_pcm_format_width(config->output_format)) {
+	case 16:
+		output_word_width = ASRC_WIDTH_16_BIT;
+		break;
+	case 24:
+		output_word_width = ASRC_WIDTH_24_BIT;
+		break;
+	default:
+		pair_err("does not support this output format, %d\n",
+			 config->output_format);
 		return -EINVAL;
 	}
 
@@ -326,27 +359,42 @@ static int fsl_asrc_config_pair(struct fsl_asrc_pair *pair)
 	/* We only have output clock for ideal ratio mode */
 	clk = asrc_priv->asrck_clk[clk_index[ideal ? OUT : IN]];
 
-	div[IN] = clk_get_rate(clk) / inrate;
-	if (div[IN] == 0) {
+	clk_rate = clk_get_rate(clk);
+	rem[IN] = do_div(clk_rate, inrate);
+	div[IN] = (u32)clk_rate;
+
+	/*
+	 * The divider range is [1, 1024], defined by the hardware. For non-
+	 * ideal ratio configuration, clock rate has to be strictly aligned
+	 * with the sample rate. For ideal ratio configuration, clock rates
+	 * only result in different converting speeds. So remainder does not
+	 * matter, as long as we keep the divider within its valid range.
+	 */
+	if (div[IN] == 0 || (!ideal && (div[IN] > 1024 || rem[IN] != 0))) {
 		pair_err("failed to support input sample rate %dHz by asrck_%x\n",
 				inrate, clk_index[ideal ? OUT : IN]);
 		return -EINVAL;
 	}
 
-	clk = asrc_priv->asrck_clk[clk_index[OUT]];
+	div[IN] = min_t(u32, 1024, div[IN]);
 
-	/* Use fixed output rate for Ideal Ratio mode (INCLK_NONE) */
-	if (ideal)
-		div[OUT] = clk_get_rate(clk) / IDEAL_RATIO_RATE;
+	clk = asrc_priv->asrck_clk[clk_index[OUT]];
+	clk_rate = clk_get_rate(clk);
+	if (ideal && use_ideal_rate)
+		rem[OUT] = do_div(clk_rate, IDEAL_RATIO_RATE);
 	else
-		div[OUT] = clk_get_rate(clk) / outrate;
+		rem[OUT] = do_div(clk_rate, outrate);
+	div[OUT] = clk_rate;
 
-	if (div[OUT] == 0) {
+	/* Output divider has the same limitation as the input one */
+	if (div[OUT] == 0 || (!ideal && (div[OUT] > 1024 || rem[OUT] != 0))) {
 		pair_err("failed to support output sample rate %dHz by asrck_%x\n",
 				outrate, clk_index[OUT]);
 		return -EINVAL;
 	}
 
+	div[OUT] = min_t(u32, 1024, div[OUT]);
+
 	/* Set the channel number */
 	channels = config->channel_num;
 
@@ -383,8 +431,8 @@ static int fsl_asrc_config_pair(struct fsl_asrc_pair *pair)
 	/* Implement word_width configurations */
 	regmap_update_bits(asrc_priv->regmap, REG_ASRMCR1(index),
 			   ASRMCR1i_OW16_MASK | ASRMCR1i_IWD_MASK,
-			   ASRMCR1i_OW16(config->output_word_width) |
-			   ASRMCR1i_IWD(config->input_word_width));
+			   ASRMCR1i_OW16(output_word_width) |
+			   ASRMCR1i_IWD(input_word_width));
 
 	/* Enable BUFFER STALL */
 	regmap_update_bits(asrc_priv->regmap, REG_ASRMCR(index),
@@ -497,13 +545,13 @@ static int fsl_asrc_dai_hw_params(struct snd_pcm_substream *substream,
 				  struct snd_soc_dai *dai)
 {
 	struct fsl_asrc *asrc_priv = snd_soc_dai_get_drvdata(dai);
-	int width = params_width(params);
 	struct snd_pcm_runtime *runtime = substream->runtime;
 	struct fsl_asrc_pair *pair = runtime->private_data;
 	unsigned int channels = params_channels(params);
 	unsigned int rate = params_rate(params);
 	struct asrc_config config;
-	int word_width, ret;
+	snd_pcm_format_t format;
+	int ret;
 
 	ret = fsl_asrc_request_pair(channels, pair);
 	if (ret) {
@@ -513,15 +561,10 @@ static int fsl_asrc_dai_hw_params(struct snd_pcm_substream *substream,
 
 	pair->config = &config;
 
-	if (width == 16)
-		width = ASRC_WIDTH_16_BIT;
-	else
-		width = ASRC_WIDTH_24_BIT;
-
 	if (asrc_priv->asrc_width == 16)
-		word_width = ASRC_WIDTH_16_BIT;
+		format = SNDRV_PCM_FORMAT_S16_LE;
 	else
-		word_width = ASRC_WIDTH_24_BIT;
+		format = SNDRV_PCM_FORMAT_S24_LE;
 
 	config.pair = pair->index;
 	config.channel_num = channels;
@@ -529,18 +572,18 @@ static int fsl_asrc_dai_hw_params(struct snd_pcm_substream *substream,
 	config.outclk = OUTCLK_ASRCK1_CLK;
 
 	if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK) {
-		config.input_word_width   = width;
-		config.output_word_width  = word_width;
+		config.input_format   = params_format(params);
+		config.output_format  = format;
 		config.input_sample_rate  = rate;
 		config.output_sample_rate = asrc_priv->asrc_rate;
 	} else {
-		config.input_word_width   = word_width;
-		config.output_word_width  = width;
+		config.input_format   = format;
+		config.output_format  = params_format(params);
 		config.input_sample_rate  = asrc_priv->asrc_rate;
 		config.output_sample_rate = rate;
 	}
 
-	ret = fsl_asrc_config_pair(pair);
+	ret = fsl_asrc_config_pair(pair, false);
 	if (ret) {
 		dev_err(dai->dev, "fail to config asrc pair\n");
 		return ret;
@@ -604,7 +647,7 @@ static int fsl_asrc_dai_probe(struct snd_soc_dai *dai)
 
 #define FSL_ASRC_FORMATS	(SNDRV_PCM_FMTBIT_S24_LE | \
 				 SNDRV_PCM_FMTBIT_S16_LE | \
-				 SNDRV_PCM_FMTBIT_S20_3LE)
+				 SNDRV_PCM_FMTBIT_S24_3LE)
 
 static struct snd_soc_dai_driver fsl_asrc_dai = {
 	.probe = fsl_asrc_dai_probe,
@@ -615,7 +658,8 @@ static struct snd_soc_dai_driver fsl_asrc_dai = {
 		.rate_min = 5512,
 		.rate_max = 192000,
 		.rates = SNDRV_PCM_RATE_KNOT,
-		.formats = FSL_ASRC_FORMATS,
+		.formats = FSL_ASRC_FORMATS |
+			   SNDRV_PCM_FMTBIT_S8,
 	},
 	.capture = {
 		.stream_name = "ASRC-Capture",
diff --git a/sound/soc/fsl/fsl_asrc.h b/sound/soc/fsl/fsl_asrc.h
index c60075112570..2b57e8c53728 100644
--- a/sound/soc/fsl/fsl_asrc.h
+++ b/sound/soc/fsl/fsl_asrc.h
@@ -342,8 +342,8 @@ struct asrc_config {
 	unsigned int dma_buffer_size;
 	unsigned int input_sample_rate;
 	unsigned int output_sample_rate;
-	enum asrc_word_width input_word_width;
-	enum asrc_word_width output_word_width;
+	snd_pcm_format_t input_format;
+	snd_pcm_format_t output_format;
 	enum asrc_inclk inclk;
 	enum asrc_outclk outclk;
 };
@@ -462,4 +462,7 @@ struct fsl_asrc {
 #define DRV_NAME "fsl-asrc-dai"
 extern struct snd_soc_component_driver fsl_asrc_component;
 struct dma_chan *fsl_asrc_get_dma_channel(struct fsl_asrc_pair *pair, bool dir);
+int fsl_asrc_request_pair(int channels, struct fsl_asrc_pair *pair);
+void fsl_asrc_release_pair(struct fsl_asrc_pair *pair);
+
 #endif /* _FSL_ASRC_H */
diff --git a/sound/soc/fsl/fsl_asrc_dma.c b/sound/soc/fsl/fsl_asrc_dma.c
index 01052a0808b0..d6146de9acd2 100644
--- a/sound/soc/fsl/fsl_asrc_dma.c
+++ b/sound/soc/fsl/fsl_asrc_dma.c
@@ -16,13 +16,11 @@
 
 #define FSL_ASRC_DMABUF_SIZE	(256 * 1024)
 
-static const struct snd_pcm_hardware snd_imx_hardware = {
+static struct snd_pcm_hardware snd_imx_hardware = {
 	.info = SNDRV_PCM_INFO_INTERLEAVED |
 		SNDRV_PCM_INFO_BLOCK_TRANSFER |
 		SNDRV_PCM_INFO_MMAP |
-		SNDRV_PCM_INFO_MMAP_VALID |
-		SNDRV_PCM_INFO_PAUSE |
-		SNDRV_PCM_INFO_RESUME,
+		SNDRV_PCM_INFO_MMAP_VALID,
 	.buffer_bytes_max = FSL_ASRC_DMABUF_SIZE,
 	.period_bytes_min = 128,
 	.period_bytes_max = 65535, /* Limited by SDMA engine */
@@ -54,13 +52,12 @@ static void fsl_asrc_dma_complete(void *arg)
 	snd_pcm_period_elapsed(substream);
 }
 
-static int fsl_asrc_dma_prepare_and_submit(struct snd_pcm_substream *substream)
+static int fsl_asrc_dma_prepare_and_submit(struct snd_pcm_substream *substream,
+					   struct snd_soc_component *component)
 {
 	u8 dir = substream->stream == SNDRV_PCM_STREAM_PLAYBACK ? OUT : IN;
-	struct snd_soc_pcm_runtime *rtd = substream->private_data;
 	struct snd_pcm_runtime *runtime = substream->runtime;
 	struct fsl_asrc_pair *pair = runtime->private_data;
-	struct snd_soc_component *component = snd_soc_rtdcom_lookup(rtd, DRV_NAME);
 	struct device *dev = component->dev;
 	unsigned long flags = DMA_CTRL_ACK;
 
@@ -97,7 +94,8 @@ static int fsl_asrc_dma_prepare_and_submit(struct snd_pcm_substream *substream)
 	return 0;
 }
 
-static int fsl_asrc_dma_trigger(struct snd_pcm_substream *substream, int cmd)
+static int fsl_asrc_dma_trigger(struct snd_soc_component *component,
+				struct snd_pcm_substream *substream, int cmd)
 {
 	struct snd_pcm_runtime *runtime = substream->runtime;
 	struct fsl_asrc_pair *pair = runtime->private_data;
@@ -107,7 +105,7 @@ static int fsl_asrc_dma_trigger(struct snd_pcm_substream *substream, int cmd)
 	case SNDRV_PCM_TRIGGER_START:
 	case SNDRV_PCM_TRIGGER_RESUME:
 	case SNDRV_PCM_TRIGGER_PAUSE_RELEASE:
-		ret = fsl_asrc_dma_prepare_and_submit(substream);
+		ret = fsl_asrc_dma_prepare_and_submit(substream, component);
 		if (ret)
 			return ret;
 		dma_async_issue_pending(pair->dma_chan[IN]);
@@ -126,7 +124,8 @@ static int fsl_asrc_dma_trigger(struct snd_pcm_substream *substream, int cmd)
 	return 0;
 }
 
-static int fsl_asrc_dma_hw_params(struct snd_pcm_substream *substream,
+static int fsl_asrc_dma_hw_params(struct snd_soc_component *component,
+				  struct snd_pcm_substream *substream,
 				  struct snd_pcm_hw_params *params)
 {
 	enum dma_slave_buswidth buswidth = DMA_SLAVE_BUSWIDTH_2_BYTES;
@@ -134,7 +133,6 @@ static int fsl_asrc_dma_hw_params(struct snd_pcm_substream *substream,
 	bool tx = substream->stream == SNDRV_PCM_STREAM_PLAYBACK;
 	struct snd_dmaengine_dai_dma_data *dma_params_fe = NULL;
 	struct snd_dmaengine_dai_dma_data *dma_params_be = NULL;
-	struct snd_soc_component *component = snd_soc_rtdcom_lookup(rtd, DRV_NAME);
 	struct snd_pcm_runtime *runtime = substream->runtime;
 	struct fsl_asrc_pair *pair = runtime->private_data;
 	struct fsl_asrc *asrc_priv = pair->asrc_priv;
@@ -249,7 +247,8 @@ static int fsl_asrc_dma_hw_params(struct snd_pcm_substream *substream,
 	return 0;
 }
 
-static int fsl_asrc_dma_hw_free(struct snd_pcm_substream *substream)
+static int fsl_asrc_dma_hw_free(struct snd_soc_component *component,
+				struct snd_pcm_substream *substream)
 {
 	struct snd_pcm_runtime *runtime = substream->runtime;
 	struct fsl_asrc_pair *pair = runtime->private_data;
@@ -268,14 +267,27 @@ static int fsl_asrc_dma_hw_free(struct snd_pcm_substream *substream)
 	return 0;
 }
 
-static int fsl_asrc_dma_startup(struct snd_pcm_substream *substream)
+static int fsl_asrc_dma_startup(struct snd_soc_component *component,
+				struct snd_pcm_substream *substream)
 {
+	bool tx = substream->stream == SNDRV_PCM_STREAM_PLAYBACK;
 	struct snd_soc_pcm_runtime *rtd = substream->private_data;
 	struct snd_pcm_runtime *runtime = substream->runtime;
-	struct snd_soc_component *component = snd_soc_rtdcom_lookup(rtd, DRV_NAME);
+	struct snd_dmaengine_dai_dma_data *dma_data;
 	struct device *dev = component->dev;
 	struct fsl_asrc *asrc_priv = dev_get_drvdata(dev);
 	struct fsl_asrc_pair *pair;
+	struct dma_chan *tmp_chan = NULL;
+	u8 dir = tx ? OUT : IN;
+	bool release_pair = true;
+	int ret = 0;
+
+	ret = snd_pcm_hw_constraint_integer(substream->runtime,
+					    SNDRV_PCM_HW_PARAM_PERIODS);
+	if (ret < 0) {
+		dev_err(dev, "failed to set pcm hw params periods\n");
+		return ret;
+	}
 
 	pair = kzalloc(sizeof(struct fsl_asrc_pair), GFP_KERNEL);
 	if (!pair)
@@ -285,14 +297,54 @@ static int fsl_asrc_dma_startup(struct snd_pcm_substream *substream)
 
 	runtime->private_data = pair;
 
-	snd_pcm_hw_constraint_integer(substream->runtime,
-				      SNDRV_PCM_HW_PARAM_PERIODS);
+	/* Request a dummy pair, which will be released later.
+	 * Request pair function needs channel num as input, for this
+	 * dummy pair, we just request "1" channel temporarily.
+	 */
+	ret = fsl_asrc_request_pair(1, pair);
+	if (ret < 0) {
+		dev_err(dev, "failed to request asrc pair\n");
+		goto req_pair_err;
+	}
+
+	/* Request a dummy dma channel, which will be released later. */
+	tmp_chan = fsl_asrc_get_dma_channel(pair, dir);
+	if (!tmp_chan) {
+		dev_err(dev, "failed to get dma channel\n");
+		ret = -EINVAL;
+		goto dma_chan_err;
+	}
+
+	dma_data = snd_soc_dai_get_dma_data(rtd->cpu_dai, substream);
+
+	/* Refine the snd_imx_hardware according to caps of DMA. */
+	ret = snd_dmaengine_pcm_refine_runtime_hwparams(substream,
+							dma_data,
+							&snd_imx_hardware,
+							tmp_chan);
+	if (ret < 0) {
+		dev_err(dev, "failed to refine runtime hwparams\n");
+		goto out;
+	}
+
+	release_pair = false;
 	snd_soc_set_runtime_hwparams(substream, &snd_imx_hardware);
 
-	return 0;
+out:
+	dma_release_channel(tmp_chan);
+
+dma_chan_err:
+	fsl_asrc_release_pair(pair);
+
+req_pair_err:
+	if (release_pair)
+		kfree(pair);
+
+	return ret;
 }
 
-static int fsl_asrc_dma_shutdown(struct snd_pcm_substream *substream)
+static int fsl_asrc_dma_shutdown(struct snd_soc_component *component,
+				 struct snd_pcm_substream *substream)
 {
 	struct snd_pcm_runtime *runtime = substream->runtime;
 	struct fsl_asrc_pair *pair = runtime->private_data;
@@ -311,7 +363,9 @@ static int fsl_asrc_dma_shutdown(struct snd_pcm_substream *substream)
 	return 0;
 }
 
-static snd_pcm_uframes_t fsl_asrc_dma_pcm_pointer(struct snd_pcm_substream *substream)
+static snd_pcm_uframes_t
+fsl_asrc_dma_pcm_pointer(struct snd_soc_component *component,
+			 struct snd_pcm_substream *substream)
 {
 	struct snd_pcm_runtime *runtime = substream->runtime;
 	struct fsl_asrc_pair *pair = runtime->private_data;
@@ -319,17 +373,8 @@ static snd_pcm_uframes_t fsl_asrc_dma_pcm_pointer(struct snd_pcm_substream *subs
 	return bytes_to_frames(substream->runtime, pair->pos);
 }
 
-static const struct snd_pcm_ops fsl_asrc_dma_pcm_ops = {
-	.ioctl		= snd_pcm_lib_ioctl,
-	.hw_params	= fsl_asrc_dma_hw_params,
-	.hw_free	= fsl_asrc_dma_hw_free,
-	.trigger	= fsl_asrc_dma_trigger,
-	.open		= fsl_asrc_dma_startup,
-	.close		= fsl_asrc_dma_shutdown,
-	.pointer	= fsl_asrc_dma_pcm_pointer,
-};
-
-static int fsl_asrc_dma_pcm_new(struct snd_soc_pcm_runtime *rtd)
+static int fsl_asrc_dma_pcm_new(struct snd_soc_component *component,
+				struct snd_soc_pcm_runtime *rtd)
 {
 	struct snd_card *card = rtd->card->snd_card;
 	struct snd_pcm_substream *substream;
@@ -364,7 +409,8 @@ err:
 	return ret;
 }
 
-static void fsl_asrc_dma_pcm_free(struct snd_pcm *pcm)
+static void fsl_asrc_dma_pcm_free(struct snd_soc_component *component,
+				  struct snd_pcm *pcm)
 {
 	struct snd_pcm_substream *substream;
 	int i;
@@ -382,8 +428,14 @@ static void fsl_asrc_dma_pcm_free(struct snd_pcm *pcm)
 
 struct snd_soc_component_driver fsl_asrc_component = {
 	.name		= DRV_NAME,
-	.ops		= &fsl_asrc_dma_pcm_ops,
-	.pcm_new	= fsl_asrc_dma_pcm_new,
-	.pcm_free	= fsl_asrc_dma_pcm_free,
+	.ioctl		= snd_soc_pcm_lib_ioctl,
+	.hw_params	= fsl_asrc_dma_hw_params,
+	.hw_free	= fsl_asrc_dma_hw_free,
+	.trigger	= fsl_asrc_dma_trigger,
+	.open		= fsl_asrc_dma_startup,
+	.close		= fsl_asrc_dma_shutdown,
+	.pointer	= fsl_asrc_dma_pcm_pointer,
+	.pcm_construct	= fsl_asrc_dma_pcm_new,
+	.pcm_destruct	= fsl_asrc_dma_pcm_free,
 };
 EXPORT_SYMBOL_GPL(fsl_asrc_component);
diff --git a/sound/soc/fsl/fsl_audmix.c b/sound/soc/fsl/fsl_audmix.c
index c7e4e9757dce..a1db1bce330f 100644
--- a/sound/soc/fsl/fsl_audmix.c
+++ b/sound/soc/fsl/fsl_audmix.c
@@ -286,6 +286,7 @@ static int fsl_audmix_dai_trigger(struct snd_pcm_substream *substream, int cmd,
 				  struct snd_soc_dai *dai)
 {
 	struct fsl_audmix *priv = snd_soc_dai_get_drvdata(dai);
+	unsigned long lock_flags;
 
 	/* Capture stream shall not be handled */
 	if (substream->stream == SNDRV_PCM_STREAM_CAPTURE)
@@ -295,12 +296,16 @@ static int fsl_audmix_dai_trigger(struct snd_pcm_substream *substream, int cmd,
 	case SNDRV_PCM_TRIGGER_START:
 	case SNDRV_PCM_TRIGGER_RESUME:
 	case SNDRV_PCM_TRIGGER_PAUSE_RELEASE:
+		spin_lock_irqsave(&priv->lock, lock_flags);
 		priv->tdms |= BIT(dai->driver->id);
+		spin_unlock_irqrestore(&priv->lock, lock_flags);
 		break;
 	case SNDRV_PCM_TRIGGER_STOP:
 	case SNDRV_PCM_TRIGGER_SUSPEND:
 	case SNDRV_PCM_TRIGGER_PAUSE_PUSH:
+		spin_lock_irqsave(&priv->lock, lock_flags);
 		priv->tdms &= ~BIT(dai->driver->id);
+		spin_unlock_irqrestore(&priv->lock, lock_flags);
 		break;
 	default:
 		return -EINVAL;
@@ -491,6 +496,7 @@ static int fsl_audmix_probe(struct platform_device *pdev)
 		return PTR_ERR(priv->ipg_clk);
 	}
 
+	spin_lock_init(&priv->lock);
 	platform_set_drvdata(pdev, priv);
 	pm_runtime_enable(dev);
 
diff --git a/sound/soc/fsl/fsl_audmix.h b/sound/soc/fsl/fsl_audmix.h
index 7812ffec45c5..479f05695d53 100644
--- a/sound/soc/fsl/fsl_audmix.h
+++ b/sound/soc/fsl/fsl_audmix.h
@@ -96,6 +96,7 @@ struct fsl_audmix {
 	struct platform_device *pdev;
 	struct regmap *regmap;
 	struct clk *ipg_clk;
+	spinlock_t lock; /* Protect tdms */
 	u8 tdms;
 };
 
diff --git a/sound/soc/fsl/fsl_dma.c b/sound/soc/fsl/fsl_dma.c
index e22508301412..2868c4f97cb2 100644
--- a/sound/soc/fsl/fsl_dma.c
+++ b/sound/soc/fsl/fsl_dma.c
@@ -201,8 +201,7 @@ static irqreturn_t fsl_dma_isr(int irq, void *dev_id)
 	struct fsl_dma_private *dma_private = dev_id;
 	struct snd_pcm_substream *substream = dma_private->substream;
 	struct snd_soc_pcm_runtime *rtd = substream->private_data;
-	struct snd_soc_component *component = snd_soc_rtdcom_lookup(rtd, DRV_NAME);
-	struct device *dev = component->dev;
+	struct device *dev = rtd->dev;
 	struct ccsr_dma_channel __iomem *dma_channel = dma_private->dma_channel;
 	irqreturn_t ret = IRQ_NONE;
 	u32 sr, sr2 = 0;
@@ -280,7 +279,8 @@ static irqreturn_t fsl_dma_isr(int irq, void *dev_id)
  * Regardless of where the memory is actually allocated, since the device can
  * technically DMA to any 36-bit address, we do need to set the DMA mask to 36.
  */
-static int fsl_dma_new(struct snd_soc_pcm_runtime *rtd)
+static int fsl_dma_new(struct snd_soc_component *component,
+		       struct snd_soc_pcm_runtime *rtd)
 {
 	struct snd_card *card = rtd->card->snd_card;
 	struct snd_pcm *pcm = rtd->pcm;
@@ -380,11 +380,10 @@ static int fsl_dma_new(struct snd_soc_pcm_runtime *rtd)
  *    buffer, which is what ALSA expects.  We're just dividing it into
  *    contiguous parts, and creating a link descriptor for each one.
  */
-static int fsl_dma_open(struct snd_pcm_substream *substream)
+static int fsl_dma_open(struct snd_soc_component *component,
+			struct snd_pcm_substream *substream)
 {
 	struct snd_pcm_runtime *runtime = substream->runtime;
-	struct snd_soc_pcm_runtime *rtd = substream->private_data;
-	struct snd_soc_component *component = snd_soc_rtdcom_lookup(rtd, DRV_NAME);
 	struct device *dev = component->dev;
 	struct dma_object *dma =
 		container_of(component->driver, struct dma_object, dai);
@@ -533,13 +532,12 @@ static int fsl_dma_open(struct snd_pcm_substream *substream)
  * and 8 bytes at a time).  So we do not support packed 24-bit samples.
  * 24-bit data must be padded to 32 bits.
  */
-static int fsl_dma_hw_params(struct snd_pcm_substream *substream,
-	struct snd_pcm_hw_params *hw_params)
+static int fsl_dma_hw_params(struct snd_soc_component *component,
+			     struct snd_pcm_substream *substream,
+			     struct snd_pcm_hw_params *hw_params)
 {
 	struct snd_pcm_runtime *runtime = substream->runtime;
 	struct fsl_dma_private *dma_private = runtime->private_data;
-	struct snd_soc_pcm_runtime *rtd = substream->private_data;
-	struct snd_soc_component *component = snd_soc_rtdcom_lookup(rtd, DRV_NAME);
 	struct device *dev = component->dev;
 
 	/* Number of bits per sample */
@@ -698,12 +696,11 @@ static int fsl_dma_hw_params(struct snd_pcm_substream *substream,
  * The base address of the buffer is stored in the source_addr field of the
  * first link descriptor.
  */
-static snd_pcm_uframes_t fsl_dma_pointer(struct snd_pcm_substream *substream)
+static snd_pcm_uframes_t fsl_dma_pointer(struct snd_soc_component *component,
+					 struct snd_pcm_substream *substream)
 {
 	struct snd_pcm_runtime *runtime = substream->runtime;
 	struct fsl_dma_private *dma_private = runtime->private_data;
-	struct snd_soc_pcm_runtime *rtd = substream->private_data;
-	struct snd_soc_component *component = snd_soc_rtdcom_lookup(rtd, DRV_NAME);
 	struct device *dev = component->dev;
 	struct ccsr_dma_channel __iomem *dma_channel = dma_private->dma_channel;
 	dma_addr_t position;
@@ -763,7 +760,8 @@ static snd_pcm_uframes_t fsl_dma_pointer(struct snd_pcm_substream *substream)
  *
  * This function can be called multiple times.
  */
-static int fsl_dma_hw_free(struct snd_pcm_substream *substream)
+static int fsl_dma_hw_free(struct snd_soc_component *component,
+			   struct snd_pcm_substream *substream)
 {
 	struct snd_pcm_runtime *runtime = substream->runtime;
 	struct fsl_dma_private *dma_private = runtime->private_data;
@@ -796,12 +794,11 @@ static int fsl_dma_hw_free(struct snd_pcm_substream *substream)
 /**
  * fsl_dma_close: close the stream.
  */
-static int fsl_dma_close(struct snd_pcm_substream *substream)
+static int fsl_dma_close(struct snd_soc_component *component,
+			 struct snd_pcm_substream *substream)
 {
 	struct snd_pcm_runtime *runtime = substream->runtime;
 	struct fsl_dma_private *dma_private = runtime->private_data;
-	struct snd_soc_pcm_runtime *rtd = substream->private_data;
-	struct snd_soc_component *component = snd_soc_rtdcom_lookup(rtd, DRV_NAME);
 	struct device *dev = component->dev;
 	struct dma_object *dma =
 		container_of(component->driver, struct dma_object, dai);
@@ -824,7 +821,8 @@ static int fsl_dma_close(struct snd_pcm_substream *substream)
 /*
  * Remove this PCM driver.
  */
-static void fsl_dma_free_dma_buffers(struct snd_pcm *pcm)
+static void fsl_dma_free_dma_buffers(struct snd_soc_component *component,
+				     struct snd_pcm *pcm)
 {
 	struct snd_pcm_substream *substream;
 	unsigned int i;
@@ -872,15 +870,6 @@ static struct device_node *find_ssi_node(struct device_node *dma_channel_np)
 	return NULL;
 }
 
-static const struct snd_pcm_ops fsl_dma_ops = {
-	.open   	= fsl_dma_open,
-	.close  	= fsl_dma_close,
-	.ioctl  	= snd_pcm_lib_ioctl,
-	.hw_params      = fsl_dma_hw_params,
-	.hw_free	= fsl_dma_hw_free,
-	.pointer	= fsl_dma_pointer,
-};
-
 static int fsl_soc_dma_probe(struct platform_device *pdev)
 {
 	struct dma_object *dma;
@@ -912,9 +901,14 @@ static int fsl_soc_dma_probe(struct platform_device *pdev)
 	}
 
 	dma->dai.name = DRV_NAME;
-	dma->dai.ops = &fsl_dma_ops;
-	dma->dai.pcm_new = fsl_dma_new;
-	dma->dai.pcm_free = fsl_dma_free_dma_buffers;
+	dma->dai.open = fsl_dma_open;
+	dma->dai.close = fsl_dma_close;
+	dma->dai.ioctl = snd_soc_pcm_lib_ioctl;
+	dma->dai.hw_params = fsl_dma_hw_params;
+	dma->dai.hw_free = fsl_dma_hw_free;
+	dma->dai.pointer = fsl_dma_pointer;
+	dma->dai.pcm_construct = fsl_dma_new;
+	dma->dai.pcm_destruct = fsl_dma_free_dma_buffers;
 
 	/* Store the SSI-specific information that we need */
 	dma->ssi_stx_phys = res.start + REG_SSI_STX0;
diff --git a/sound/soc/fsl/fsl_esai.c b/sound/soc/fsl/fsl_esai.c
index a78e4ab478df..c7a49d03463a 100644
--- a/sound/soc/fsl/fsl_esai.c
+++ b/sound/soc/fsl/fsl_esai.c
@@ -33,6 +33,7 @@
  * @fsysclk: system clock source to derive HCK, SCK and FS
  * @spbaclk: SPBA clock (optional, depending on SoC design)
  * @task: tasklet to handle the reset operation
+ * @lock: spin lock between hw_reset() and trigger()
  * @fifo_depth: depth of tx/rx FIFO
  * @slot_width: width of each DAI slot
  * @slots: number of slots
@@ -56,6 +57,7 @@ struct fsl_esai {
 	struct clk *fsysclk;
 	struct clk *spbaclk;
 	struct tasklet_struct task;
+	spinlock_t lock; /* Protect hw_reset and trigger */
 	u32 fifo_depth;
 	u32 slot_width;
 	u32 slots;
@@ -676,8 +678,10 @@ static void fsl_esai_hw_reset(unsigned long arg)
 {
 	struct fsl_esai *esai_priv = (struct fsl_esai *)arg;
 	bool tx = true, rx = false, enabled[2];
+	unsigned long lock_flags;
 	u32 tfcr, rfcr;
 
+	spin_lock_irqsave(&esai_priv->lock, lock_flags);
 	/* Save the registers */
 	regmap_read(esai_priv->regmap, REG_ESAI_TFCR, &tfcr);
 	regmap_read(esai_priv->regmap, REG_ESAI_RFCR, &rfcr);
@@ -715,6 +719,8 @@ static void fsl_esai_hw_reset(unsigned long arg)
 		fsl_esai_trigger_start(esai_priv, tx);
 	if (enabled[rx])
 		fsl_esai_trigger_start(esai_priv, rx);
+
+	spin_unlock_irqrestore(&esai_priv->lock, lock_flags);
 }
 
 static int fsl_esai_trigger(struct snd_pcm_substream *substream, int cmd,
@@ -722,6 +728,7 @@ static int fsl_esai_trigger(struct snd_pcm_substream *substream, int cmd,
 {
 	struct fsl_esai *esai_priv = snd_soc_dai_get_drvdata(dai);
 	bool tx = substream->stream == SNDRV_PCM_STREAM_PLAYBACK;
+	unsigned long lock_flags;
 
 	esai_priv->channels[tx] = substream->runtime->channels;
 
@@ -729,12 +736,16 @@ static int fsl_esai_trigger(struct snd_pcm_substream *substream, int cmd,
 	case SNDRV_PCM_TRIGGER_START:
 	case SNDRV_PCM_TRIGGER_RESUME:
 	case SNDRV_PCM_TRIGGER_PAUSE_RELEASE:
+		spin_lock_irqsave(&esai_priv->lock, lock_flags);
 		fsl_esai_trigger_start(esai_priv, tx);
+		spin_unlock_irqrestore(&esai_priv->lock, lock_flags);
 		break;
 	case SNDRV_PCM_TRIGGER_SUSPEND:
 	case SNDRV_PCM_TRIGGER_STOP:
 	case SNDRV_PCM_TRIGGER_PAUSE_PUSH:
+		spin_lock_irqsave(&esai_priv->lock, lock_flags);
 		fsl_esai_trigger_stop(esai_priv, tx);
+		spin_unlock_irqrestore(&esai_priv->lock, lock_flags);
 		break;
 	default:
 		return -EINVAL;
@@ -1002,6 +1013,7 @@ static int fsl_esai_probe(struct platform_device *pdev)
 
 	dev_set_drvdata(&pdev->dev, esai_priv);
 
+	spin_lock_init(&esai_priv->lock);
 	ret = fsl_esai_hw_init(esai_priv);
 	if (ret)
 		return ret;
diff --git a/sound/soc/fsl/fsl_mqs.c b/sound/soc/fsl/fsl_mqs.c
new file mode 100644
index 000000000000..0c813a45bba7
--- /dev/null
+++ b/sound/soc/fsl/fsl_mqs.c
@@ -0,0 +1,335 @@
+// SPDX-License-Identifier: GPL-2.0
+//
+// ALSA SoC IMX MQS driver
+//
+// Copyright (C) 2014-2015 Freescale Semiconductor, Inc.
+// Copyright 2019 NXP
+
+#include <linux/clk.h>
+#include <linux/module.h>
+#include <linux/moduleparam.h>
+#include <linux/mfd/syscon.h>
+#include <linux/mfd/syscon/imx6q-iomuxc-gpr.h>
+#include <linux/pm_runtime.h>
+#include <linux/of.h>
+#include <linux/pm.h>
+#include <linux/slab.h>
+#include <sound/soc.h>
+#include <sound/pcm.h>
+#include <sound/initval.h>
+
+#define REG_MQS_CTRL		0x00
+
+#define MQS_EN_MASK			(0x1 << 28)
+#define MQS_EN_SHIFT			(28)
+#define MQS_SW_RST_MASK			(0x1 << 24)
+#define MQS_SW_RST_SHIFT		(24)
+#define MQS_OVERSAMPLE_MASK		(0x1 << 20)
+#define MQS_OVERSAMPLE_SHIFT		(20)
+#define MQS_CLK_DIV_MASK		(0xFF << 0)
+#define MQS_CLK_DIV_SHIFT		(0)
+
+/* codec private data */
+struct fsl_mqs {
+	struct regmap *regmap;
+	struct clk *mclk;
+	struct clk *ipg;
+
+	unsigned int reg_iomuxc_gpr2;
+	unsigned int reg_mqs_ctrl;
+	bool use_gpr;
+};
+
+#define FSL_MQS_RATES	(SNDRV_PCM_RATE_44100 | SNDRV_PCM_RATE_48000)
+#define FSL_MQS_FORMATS	SNDRV_PCM_FMTBIT_S16_LE
+
+static int fsl_mqs_hw_params(struct snd_pcm_substream *substream,
+			     struct snd_pcm_hw_params *params,
+			     struct snd_soc_dai *dai)
+{
+	struct snd_soc_component *component = dai->component;
+	struct fsl_mqs *mqs_priv = snd_soc_component_get_drvdata(component);
+	unsigned long mclk_rate;
+	int div, res;
+	int lrclk;
+
+	mclk_rate = clk_get_rate(mqs_priv->mclk);
+	lrclk = params_rate(params);
+
+	/*
+	 * mclk_rate / (oversample(32,64) * FS * 2 * divider ) = repeat_rate;
+	 * if repeat_rate is 8, mqs can achieve better quality.
+	 * oversample rate is fix to 32 currently.
+	 */
+	div = mclk_rate / (32 * lrclk * 2 * 8);
+	res = mclk_rate % (32 * lrclk * 2 * 8);
+
+	if (res == 0 && div > 0 && div <= 256) {
+		if (mqs_priv->use_gpr) {
+			regmap_update_bits(mqs_priv->regmap, IOMUXC_GPR2,
+					   IMX6SX_GPR2_MQS_CLK_DIV_MASK,
+					   (div - 1) << IMX6SX_GPR2_MQS_CLK_DIV_SHIFT);
+			regmap_update_bits(mqs_priv->regmap, IOMUXC_GPR2,
+					   IMX6SX_GPR2_MQS_OVERSAMPLE_MASK, 0);
+		} else {
+			regmap_update_bits(mqs_priv->regmap, REG_MQS_CTRL,
+					   MQS_CLK_DIV_MASK,
+					   (div - 1) << MQS_CLK_DIV_SHIFT);
+			regmap_update_bits(mqs_priv->regmap, REG_MQS_CTRL,
+					   MQS_OVERSAMPLE_MASK, 0);
+		}
+	} else {
+		dev_err(component->dev, "can't get proper divider\n");
+	}
+
+	return 0;
+}
+
+static int fsl_mqs_set_dai_fmt(struct snd_soc_dai *dai, unsigned int fmt)
+{
+	/* Only LEFT_J & SLAVE mode is supported. */
+	switch (fmt & SND_SOC_DAIFMT_FORMAT_MASK) {
+	case SND_SOC_DAIFMT_LEFT_J:
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	switch (fmt & SND_SOC_DAIFMT_INV_MASK) {
+	case SND_SOC_DAIFMT_NB_NF:
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	switch (fmt & SND_SOC_DAIFMT_MASTER_MASK) {
+	case SND_SOC_DAIFMT_CBS_CFS:
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int fsl_mqs_startup(struct snd_pcm_substream *substream,
+			   struct snd_soc_dai *dai)
+{
+	struct snd_soc_component *component = dai->component;
+	struct fsl_mqs *mqs_priv = snd_soc_component_get_drvdata(component);
+
+	if (mqs_priv->use_gpr)
+		regmap_update_bits(mqs_priv->regmap, IOMUXC_GPR2,
+				   IMX6SX_GPR2_MQS_EN_MASK,
+				   1 << IMX6SX_GPR2_MQS_EN_SHIFT);
+	else
+		regmap_update_bits(mqs_priv->regmap, REG_MQS_CTRL,
+				   MQS_EN_MASK,
+				   1 << MQS_EN_SHIFT);
+	return 0;
+}
+
+static void fsl_mqs_shutdown(struct snd_pcm_substream *substream,
+			     struct snd_soc_dai *dai)
+{
+	struct snd_soc_component *component = dai->component;
+	struct fsl_mqs *mqs_priv = snd_soc_component_get_drvdata(component);
+
+	if (mqs_priv->use_gpr)
+		regmap_update_bits(mqs_priv->regmap, IOMUXC_GPR2,
+				   IMX6SX_GPR2_MQS_EN_MASK, 0);
+	else
+		regmap_update_bits(mqs_priv->regmap, REG_MQS_CTRL,
+				   MQS_EN_MASK, 0);
+}
+
+static const struct snd_soc_component_driver soc_codec_fsl_mqs = {
+	.idle_bias_on = 1,
+	.non_legacy_dai_naming	= 1,
+};
+
+static const struct snd_soc_dai_ops fsl_mqs_dai_ops = {
+	.startup = fsl_mqs_startup,
+	.shutdown = fsl_mqs_shutdown,
+	.hw_params = fsl_mqs_hw_params,
+	.set_fmt = fsl_mqs_set_dai_fmt,
+};
+
+static struct snd_soc_dai_driver fsl_mqs_dai = {
+	.name		= "fsl-mqs-dai",
+	.playback	= {
+		.stream_name	= "Playback",
+		.channels_min	= 2,
+		.channels_max	= 2,
+		.rates		= FSL_MQS_RATES,
+		.formats	= FSL_MQS_FORMATS,
+	},
+	.ops = &fsl_mqs_dai_ops,
+};
+
+static const struct regmap_config fsl_mqs_regmap_config = {
+	.reg_bits = 32,
+	.reg_stride = 4,
+	.val_bits = 32,
+	.max_register = REG_MQS_CTRL,
+	.cache_type = REGCACHE_NONE,
+};
+
+static int fsl_mqs_probe(struct platform_device *pdev)
+{
+	struct device_node *np = pdev->dev.of_node;
+	struct device_node *gpr_np = NULL;
+	struct fsl_mqs *mqs_priv;
+	void __iomem *regs;
+	int ret;
+
+	mqs_priv = devm_kzalloc(&pdev->dev, sizeof(*mqs_priv), GFP_KERNEL);
+	if (!mqs_priv)
+		return -ENOMEM;
+
+	/* On i.MX6sx the MQS control register is in GPR domain
+	 * But in i.MX8QM/i.MX8QXP the control register is moved
+	 * to its own domain.
+	 */
+	if (of_device_is_compatible(np, "fsl,imx8qm-mqs"))
+		mqs_priv->use_gpr = false;
+	else
+		mqs_priv->use_gpr = true;
+
+	if (mqs_priv->use_gpr) {
+		gpr_np = of_parse_phandle(np, "gpr", 0);
+		if (!gpr_np) {
+			dev_err(&pdev->dev, "failed to get gpr node by phandle\n");
+			return -EINVAL;
+		}
+
+		mqs_priv->regmap = syscon_node_to_regmap(gpr_np);
+		if (IS_ERR(mqs_priv->regmap)) {
+			dev_err(&pdev->dev, "failed to get gpr regmap\n");
+			ret = PTR_ERR(mqs_priv->regmap);
+			goto err_free_gpr_np;
+		}
+	} else {
+		regs = devm_platform_ioremap_resource(pdev, 0);
+		if (IS_ERR(regs))
+			return PTR_ERR(regs);
+
+		mqs_priv->regmap = devm_regmap_init_mmio_clk(&pdev->dev,
+							     "core",
+							     regs,
+							     &fsl_mqs_regmap_config);
+		if (IS_ERR(mqs_priv->regmap)) {
+			dev_err(&pdev->dev, "failed to init regmap: %ld\n",
+				PTR_ERR(mqs_priv->regmap));
+			return PTR_ERR(mqs_priv->regmap);
+		}
+
+		mqs_priv->ipg = devm_clk_get(&pdev->dev, "core");
+		if (IS_ERR(mqs_priv->ipg)) {
+			dev_err(&pdev->dev, "failed to get the clock: %ld\n",
+				PTR_ERR(mqs_priv->ipg));
+			return PTR_ERR(mqs_priv->ipg);
+		}
+	}
+
+	mqs_priv->mclk = devm_clk_get(&pdev->dev, "mclk");
+	if (IS_ERR(mqs_priv->mclk)) {
+		dev_err(&pdev->dev, "failed to get the clock: %ld\n",
+			PTR_ERR(mqs_priv->mclk));
+		ret = PTR_ERR(mqs_priv->mclk);
+		goto err_free_gpr_np;
+	}
+
+	dev_set_drvdata(&pdev->dev, mqs_priv);
+	pm_runtime_enable(&pdev->dev);
+
+	ret = devm_snd_soc_register_component(&pdev->dev, &soc_codec_fsl_mqs,
+			&fsl_mqs_dai, 1);
+	if (ret)
+		goto err_free_gpr_np;
+	return 0;
+
+err_free_gpr_np:
+	of_node_put(gpr_np);
+
+	return ret;
+}
+
+static int fsl_mqs_remove(struct platform_device *pdev)
+{
+	pm_runtime_disable(&pdev->dev);
+	return 0;
+}
+
+#ifdef CONFIG_PM
+static int fsl_mqs_runtime_resume(struct device *dev)
+{
+	struct fsl_mqs *mqs_priv = dev_get_drvdata(dev);
+
+	if (mqs_priv->ipg)
+		clk_prepare_enable(mqs_priv->ipg);
+
+	if (mqs_priv->mclk)
+		clk_prepare_enable(mqs_priv->mclk);
+
+	if (mqs_priv->use_gpr)
+		regmap_write(mqs_priv->regmap, IOMUXC_GPR2,
+			     mqs_priv->reg_iomuxc_gpr2);
+	else
+		regmap_write(mqs_priv->regmap, REG_MQS_CTRL,
+			     mqs_priv->reg_mqs_ctrl);
+	return 0;
+}
+
+static int fsl_mqs_runtime_suspend(struct device *dev)
+{
+	struct fsl_mqs *mqs_priv = dev_get_drvdata(dev);
+
+	if (mqs_priv->use_gpr)
+		regmap_read(mqs_priv->regmap, IOMUXC_GPR2,
+			    &mqs_priv->reg_iomuxc_gpr2);
+	else
+		regmap_read(mqs_priv->regmap, REG_MQS_CTRL,
+			    &mqs_priv->reg_mqs_ctrl);
+
+	if (mqs_priv->mclk)
+		clk_disable_unprepare(mqs_priv->mclk);
+
+	if (mqs_priv->ipg)
+		clk_disable_unprepare(mqs_priv->ipg);
+
+	return 0;
+}
+#endif
+
+static const struct dev_pm_ops fsl_mqs_pm_ops = {
+	SET_RUNTIME_PM_OPS(fsl_mqs_runtime_suspend,
+			   fsl_mqs_runtime_resume,
+			   NULL)
+	SET_SYSTEM_SLEEP_PM_OPS(pm_runtime_force_suspend,
+				pm_runtime_force_resume)
+};
+
+static const struct of_device_id fsl_mqs_dt_ids[] = {
+	{ .compatible = "fsl,imx8qm-mqs", },
+	{ .compatible = "fsl,imx6sx-mqs", },
+	{}
+};
+MODULE_DEVICE_TABLE(of, fsl_mqs_dt_ids);
+
+static struct platform_driver fsl_mqs_driver = {
+	.probe		= fsl_mqs_probe,
+	.remove		= fsl_mqs_remove,
+	.driver		= {
+		.name	= "fsl-mqs",
+		.of_match_table = fsl_mqs_dt_ids,
+		.pm = &fsl_mqs_pm_ops,
+	},
+};
+
+module_platform_driver(fsl_mqs_driver);
+
+MODULE_AUTHOR("Shengjiu Wang <Shengjiu.Wang@nxp.com>");
+MODULE_DESCRIPTION("MQS codec driver");
+MODULE_LICENSE("GPL v2");
+MODULE_ALIAS("platform: fsl-mqs");
diff --git a/sound/soc/fsl/imx-pcm-fiq.c b/sound/soc/fsl/imx-pcm-fiq.c
index c49aea4fba56..08131d147983 100644
--- a/sound/soc/fsl/imx-pcm-fiq.c
+++ b/sound/soc/fsl/imx-pcm-fiq.c
@@ -69,8 +69,9 @@ static struct fiq_handler fh = {
 	.name		= DRV_NAME,
 };
 
-static int snd_imx_pcm_hw_params(struct snd_pcm_substream *substream,
-				struct snd_pcm_hw_params *params)
+static int snd_imx_pcm_hw_params(struct snd_soc_component *component,
+				 struct snd_pcm_substream *substream,
+				 struct snd_pcm_hw_params *params)
 {
 	struct snd_pcm_runtime *runtime = substream->runtime;
 	struct imx_pcm_runtime_data *iprtd = runtime->private_data;
@@ -85,7 +86,8 @@ static int snd_imx_pcm_hw_params(struct snd_pcm_substream *substream,
 	return 0;
 }
 
-static int snd_imx_pcm_prepare(struct snd_pcm_substream *substream)
+static int snd_imx_pcm_prepare(struct snd_soc_component *component,
+			       struct snd_pcm_substream *substream)
 {
 	struct snd_pcm_runtime *runtime = substream->runtime;
 	struct imx_pcm_runtime_data *iprtd = runtime->private_data;
@@ -104,7 +106,8 @@ static int snd_imx_pcm_prepare(struct snd_pcm_substream *substream)
 
 static int imx_pcm_fiq;
 
-static int snd_imx_pcm_trigger(struct snd_pcm_substream *substream, int cmd)
+static int snd_imx_pcm_trigger(struct snd_soc_component *component,
+			       struct snd_pcm_substream *substream, int cmd)
 {
 	struct snd_pcm_runtime *runtime = substream->runtime;
 	struct imx_pcm_runtime_data *iprtd = runtime->private_data;
@@ -141,7 +144,9 @@ static int snd_imx_pcm_trigger(struct snd_pcm_substream *substream, int cmd)
 	return 0;
 }
 
-static snd_pcm_uframes_t snd_imx_pcm_pointer(struct snd_pcm_substream *substream)
+static snd_pcm_uframes_t
+snd_imx_pcm_pointer(struct snd_soc_component *component,
+		    struct snd_pcm_substream *substream)
 {
 	struct snd_pcm_runtime *runtime = substream->runtime;
 	struct imx_pcm_runtime_data *iprtd = runtime->private_data;
@@ -165,7 +170,8 @@ static const struct snd_pcm_hardware snd_imx_hardware = {
 	.fifo_size = 0,
 };
 
-static int snd_imx_open(struct snd_pcm_substream *substream)
+static int snd_imx_open(struct snd_soc_component *component,
+			struct snd_pcm_substream *substream)
 {
 	struct snd_pcm_runtime *runtime = substream->runtime;
 	struct imx_pcm_runtime_data *iprtd;
@@ -194,7 +200,8 @@ static int snd_imx_open(struct snd_pcm_substream *substream)
 	return 0;
 }
 
-static int snd_imx_close(struct snd_pcm_substream *substream)
+static int snd_imx_close(struct snd_soc_component *component,
+			 struct snd_pcm_substream *substream)
 {
 	struct snd_pcm_runtime *runtime = substream->runtime;
 	struct imx_pcm_runtime_data *iprtd = runtime->private_data;
@@ -206,8 +213,9 @@ static int snd_imx_close(struct snd_pcm_substream *substream)
 	return 0;
 }
 
-static int snd_imx_pcm_mmap(struct snd_pcm_substream *substream,
-		struct vm_area_struct *vma)
+static int snd_imx_pcm_mmap(struct snd_soc_component *component,
+			    struct snd_pcm_substream *substream,
+			    struct vm_area_struct *vma)
 {
 	struct snd_pcm_runtime *runtime = substream->runtime;
 	int ret;
@@ -222,17 +230,6 @@ static int snd_imx_pcm_mmap(struct snd_pcm_substream *substream,
 	return ret;
 }
 
-static const struct snd_pcm_ops imx_pcm_ops = {
-	.open		= snd_imx_open,
-	.close		= snd_imx_close,
-	.ioctl		= snd_pcm_lib_ioctl,
-	.hw_params	= snd_imx_pcm_hw_params,
-	.prepare	= snd_imx_pcm_prepare,
-	.trigger	= snd_imx_pcm_trigger,
-	.pointer	= snd_imx_pcm_pointer,
-	.mmap		= snd_imx_pcm_mmap,
-};
-
 static int imx_pcm_preallocate_dma_buffer(struct snd_pcm *pcm, int stream)
 {
 	struct snd_pcm_substream *substream = pcm->streams[stream].substream;
@@ -279,7 +276,8 @@ static int imx_pcm_new(struct snd_soc_pcm_runtime *rtd)
 
 static int ssi_irq;
 
-static int imx_pcm_fiq_new(struct snd_soc_pcm_runtime *rtd)
+static int snd_imx_pcm_new(struct snd_soc_component *component,
+			   struct snd_soc_pcm_runtime *rtd)
 {
 	struct snd_pcm *pcm = rtd->pcm;
 	struct snd_pcm_substream *substream;
@@ -329,7 +327,8 @@ static void imx_pcm_free(struct snd_pcm *pcm)
 	}
 }
 
-static void imx_pcm_fiq_free(struct snd_pcm *pcm)
+static void snd_imx_pcm_free(struct snd_soc_component *component,
+			     struct snd_pcm *pcm)
 {
 	mxc_set_irq_fiq(ssi_irq, 0);
 	release_fiq(&fh);
@@ -337,9 +336,16 @@ static void imx_pcm_fiq_free(struct snd_pcm *pcm)
 }
 
 static const struct snd_soc_component_driver imx_soc_component_fiq = {
-	.ops		= &imx_pcm_ops,
-	.pcm_new	= imx_pcm_fiq_new,
-	.pcm_free	= imx_pcm_fiq_free,
+	.open		= snd_imx_open,
+	.close		= snd_imx_close,
+	.ioctl		= snd_soc_pcm_lib_ioctl,
+	.hw_params	= snd_imx_pcm_hw_params,
+	.prepare	= snd_imx_pcm_prepare,
+	.trigger	= snd_imx_pcm_trigger,
+	.pointer	= snd_imx_pcm_pointer,
+	.mmap		= snd_imx_pcm_mmap,
+	.pcm_construct	= snd_imx_pcm_new,
+	.pcm_destruct	= snd_imx_pcm_free,
 };
 
 int imx_pcm_fiq_init(struct platform_device *pdev,
diff --git a/sound/soc/fsl/mpc5200_dma.c b/sound/soc/fsl/mpc5200_dma.c
index ccf9301889fe..5237ac96b756 100644
--- a/sound/soc/fsl/mpc5200_dma.c
+++ b/sound/soc/fsl/mpc5200_dma.c
@@ -98,7 +98,8 @@ static irqreturn_t psc_dma_bcom_irq(int irq, void *_psc_dma_stream)
 	return IRQ_HANDLED;
 }
 
-static int psc_dma_hw_free(struct snd_pcm_substream *substream)
+static int psc_dma_hw_free(struct snd_soc_component *component,
+			   struct snd_pcm_substream *substream)
 {
 	snd_pcm_set_runtime_buffer(substream, NULL);
 	return 0;
@@ -110,7 +111,8 @@ static int psc_dma_hw_free(struct snd_pcm_substream *substream)
  * This function is called by ALSA to start, stop, pause, and resume the DMA
  * transfer of data.
  */
-static int psc_dma_trigger(struct snd_pcm_substream *substream, int cmd)
+static int psc_dma_trigger(struct snd_soc_component *component,
+			   struct snd_pcm_substream *substream, int cmd)
 {
 	struct snd_soc_pcm_runtime *rtd = substream->private_data;
 	struct psc_dma *psc_dma = snd_soc_dai_get_drvdata(rtd->cpu_dai);
@@ -210,7 +212,8 @@ static const struct snd_pcm_hardware psc_dma_hardware = {
 	.fifo_size		= 512,
 };
 
-static int psc_dma_open(struct snd_pcm_substream *substream)
+static int psc_dma_open(struct snd_soc_component *component,
+			struct snd_pcm_substream *substream)
 {
 	struct snd_pcm_runtime *runtime = substream->runtime;
 	struct snd_soc_pcm_runtime *rtd = substream->private_data;
@@ -238,7 +241,8 @@ static int psc_dma_open(struct snd_pcm_substream *substream)
 	return 0;
 }
 
-static int psc_dma_close(struct snd_pcm_substream *substream)
+static int psc_dma_close(struct snd_soc_component *component,
+			 struct snd_pcm_substream *substream)
 {
 	struct snd_soc_pcm_runtime *rtd = substream->private_data;
 	struct psc_dma *psc_dma = snd_soc_dai_get_drvdata(rtd->cpu_dai);
@@ -263,7 +267,8 @@ static int psc_dma_close(struct snd_pcm_substream *substream)
 }
 
 static snd_pcm_uframes_t
-psc_dma_pointer(struct snd_pcm_substream *substream)
+psc_dma_pointer(struct snd_soc_component *component,
+		struct snd_pcm_substream *substream)
 {
 	struct snd_soc_pcm_runtime *rtd = substream->private_data;
 	struct psc_dma *psc_dma = snd_soc_dai_get_drvdata(rtd->cpu_dai);
@@ -280,29 +285,19 @@ psc_dma_pointer(struct snd_pcm_substream *substream)
 	return bytes_to_frames(substream->runtime, count);
 }
 
-static int
-psc_dma_hw_params(struct snd_pcm_substream *substream,
-			 struct snd_pcm_hw_params *params)
+static int psc_dma_hw_params(struct snd_soc_component *component,
+			     struct snd_pcm_substream *substream,
+			     struct snd_pcm_hw_params *params)
 {
 	snd_pcm_set_runtime_buffer(substream, &substream->dma_buffer);
 
 	return 0;
 }
 
-static const struct snd_pcm_ops psc_dma_ops = {
-	.open		= psc_dma_open,
-	.close		= psc_dma_close,
-	.hw_free	= psc_dma_hw_free,
-	.ioctl		= snd_pcm_lib_ioctl,
-	.pointer	= psc_dma_pointer,
-	.trigger	= psc_dma_trigger,
-	.hw_params	= psc_dma_hw_params,
-};
-
-static int psc_dma_new(struct snd_soc_pcm_runtime *rtd)
+static int psc_dma_new(struct snd_soc_component *component,
+		       struct snd_soc_pcm_runtime *rtd)
 {
 	struct snd_card *card = rtd->card->snd_card;
-	struct snd_soc_component *component = snd_soc_rtdcom_lookup(rtd, DRV_NAME);
 	struct snd_soc_dai *dai = rtd->cpu_dai;
 	struct snd_pcm *pcm = rtd->pcm;
 	size_t size = psc_dma_hardware.buffer_bytes_max;
@@ -341,10 +336,10 @@ static int psc_dma_new(struct snd_soc_pcm_runtime *rtd)
 	return -ENOMEM;
 }
 
-static void psc_dma_free(struct snd_pcm *pcm)
+static void psc_dma_free(struct snd_soc_component *component,
+			 struct snd_pcm *pcm)
 {
 	struct snd_soc_pcm_runtime *rtd = pcm->private_data;
-	struct snd_soc_component *component = snd_soc_rtdcom_lookup(rtd, DRV_NAME);
 	struct snd_pcm_substream *substream;
 	int stream;
 
@@ -362,9 +357,15 @@ static void psc_dma_free(struct snd_pcm *pcm)
 
 static const struct snd_soc_component_driver mpc5200_audio_dma_component = {
 	.name		= DRV_NAME,
-	.ops		= &psc_dma_ops,
-	.pcm_new	= &psc_dma_new,
-	.pcm_free	= &psc_dma_free,
+	.open		= psc_dma_open,
+	.close		= psc_dma_close,
+	.hw_free	= psc_dma_hw_free,
+	.ioctl		= snd_soc_pcm_lib_ioctl,
+	.pointer	= psc_dma_pointer,
+	.trigger	= psc_dma_trigger,
+	.hw_params	= psc_dma_hw_params,
+	.pcm_construct	= psc_dma_new,
+	.pcm_destruct	= psc_dma_free,
 };
 
 int mpc5200_audio_dma_create(struct platform_device *op)
diff --git a/sound/soc/generic/audio-graph-card.c b/sound/soc/generic/audio-graph-card.c
index 6007e6305735..9ad35d9940fe 100644
--- a/sound/soc/generic/audio-graph-card.c
+++ b/sound/soc/generic/audio-graph-card.c
@@ -232,7 +232,7 @@ static int graph_dai_link_of_dpcm(struct asoc_simple_priv *priv,
 	if (li->cpu) {
 		int is_single_links = 0;
 
-		/* BE is dummy */
+		/* Codec is dummy */
 		codecs->of_node		= NULL;
 		codecs->dai_name	= "snd-soc-dummy-dai";
 		codecs->name		= "snd-soc-dummy";
@@ -263,7 +263,7 @@ static int graph_dai_link_of_dpcm(struct asoc_simple_priv *priv,
 	} else {
 		struct snd_soc_codec_conf *cconf;
 
-		/* FE is dummy */
+		/* CPU is dummy */
 		cpus->of_node		= NULL;
 		cpus->dai_name		= "snd-soc-dummy-dai";
 		cpus->name		= "snd-soc-dummy";
diff --git a/sound/soc/generic/simple-card.c b/sound/soc/generic/simple-card.c
index fc9c753db8dd..10b82bf043d1 100644
--- a/sound/soc/generic/simple-card.c
+++ b/sound/soc/generic/simple-card.c
@@ -149,7 +149,7 @@ static int simple_dai_link_of_dpcm(struct asoc_simple_priv *priv,
 	if (li->cpu) {
 		int is_single_links = 0;
 
-		/* BE is dummy */
+		/* Codec is dummy */
 		codecs->of_node		= NULL;
 		codecs->dai_name	= "snd-soc-dummy-dai";
 		codecs->name		= "snd-soc-dummy";
@@ -179,7 +179,7 @@ static int simple_dai_link_of_dpcm(struct asoc_simple_priv *priv,
 	} else {
 		struct snd_soc_codec_conf *cconf;
 
-		/* FE is dummy */
+		/* CPU is dummy */
 		cpus->of_node		= NULL;
 		cpus->dai_name		= "snd-soc-dummy-dai";
 		cpus->name		= "snd-soc-dummy";
diff --git a/sound/soc/intel/Kconfig b/sound/soc/intel/Kconfig
index 01c99750212a..c8de0bb5bed9 100644
--- a/sound/soc/intel/Kconfig
+++ b/sound/soc/intel/Kconfig
@@ -59,10 +59,13 @@ config SND_SOC_INTEL_HASWELL
 	  If you have a Intel Haswell or Broadwell platform connected to
 	  an I2S codec, then enable this option by saying Y or m. This is
 	  typically used for Chromebooks. This is a recommended option.
+	  This option is mutually exclusive with the SOF support on
+	  Broadwell. If you want to enable SOF on Broadwell, you need to
+	  deselect this option first.
 
 config SND_SOC_INTEL_BAYTRAIL
 	tristate "Baytrail (legacy) Platforms"
-	depends on DMADEVICES && ACPI && SND_SST_ATOM_HIFI2_PLATFORM=n
+	depends on DMADEVICES && ACPI && SND_SST_ATOM_HIFI2_PLATFORM=n && SND_SOC_SOF_BAYTRAIL=n
 	select SND_SOC_INTEL_SST
 	select SND_SOC_INTEL_SST_ACPI
 	select SND_SOC_INTEL_SST_FIRMWARE
@@ -101,6 +104,9 @@ config SND_SST_ATOM_HIFI2_PLATFORM_ACPI
 	  If you have a Intel Baytrail or Cherrytrail platform with an I2S
 	  codec, then enable this option by saying Y or m. This is a
 	  recommended option
+	  This option is mutually exclusive with the SOF support on
+	  Baytrail/Cherrytrail. If you want to enable SOF on
+	  Baytrail/Cherrytrail, you need to deselect this option first.
 
 config SND_SOC_INTEL_SKYLAKE
 	tristate "All Skylake/SST Platforms"
@@ -113,7 +119,7 @@ config SND_SOC_INTEL_SKYLAKE
 	select SND_SOC_INTEL_CNL
 	select SND_SOC_INTEL_CFL
 	help
-          This is a backwards-compatible option to select all devices
+	  This is a backwards-compatible option to select all devices
 	  supported by the Intel SST/Skylake driver. This option is no
 	  longer recommended and will be deprecated when the SOF
 	  driver is introduced.  Distributions should explicitly
@@ -203,9 +209,12 @@ config SND_SOC_INTEL_SKYLAKE_SSP_CLK
 config SND_SOC_INTEL_SKYLAKE_HDAUDIO_CODEC
 	bool "HDAudio codec support"
 	help
-	  If you have a Intel Skylake/Broxton/ApolloLake/KabyLake/
-	  GeminiLake or CannonLake platform with an HDaudio codec
-	  then enable this option by saying Y
+	  This option broke audio on Linus' Skylake laptop in December 2018
+	  and the race conditions during the probe were not fixed since.
+	  This option is DEPRECATED, all HDaudio codec support needs
+	  to be handled by the SOF driver.
+	  Distributions should not enable this option and there are no known
+	  users of this capability.
 
 config SND_SOC_INTEL_SKYLAKE_COMMON
 	tristate
@@ -215,7 +224,7 @@ config SND_SOC_INTEL_SKYLAKE_COMMON
 	select SND_SOC_INTEL_SST
 	select SND_SOC_HDAC_HDA if SND_SOC_INTEL_SKYLAKE_HDAUDIO_CODEC
 	select SND_SOC_ACPI_INTEL_MATCH
-	select SND_INTEL_NHLT if ACPI
+	select SND_INTEL_DSP_CONFIG
 	help
 	  If you have a Intel Skylake/Broxton/ApolloLake/KabyLake/
 	  GeminiLake or CannonLake platform with the DSP enabled in the BIOS
diff --git a/sound/soc/intel/atom/sst-mfld-platform-pcm.c b/sound/soc/intel/atom/sst-mfld-platform-pcm.c
index 8cc3cc363eb0..47e3d1943d7e 100644
--- a/sound/soc/intel/atom/sst-mfld-platform-pcm.c
+++ b/sound/soc/intel/atom/sst-mfld-platform-pcm.c
@@ -586,7 +586,8 @@ static struct snd_soc_dai_driver sst_platform_dai[] = {
 },
 };
 
-static int sst_platform_open(struct snd_pcm_substream *substream)
+static int sst_soc_open(struct snd_soc_component *component,
+			struct snd_pcm_substream *substream)
 {
 	struct snd_pcm_runtime *runtime;
 
@@ -598,15 +599,15 @@ static int sst_platform_open(struct snd_pcm_substream *substream)
 	return 0;
 }
 
-static int sst_platform_pcm_trigger(struct snd_pcm_substream *substream,
-					int cmd)
+static int sst_soc_trigger(struct snd_soc_component *component,
+			   struct snd_pcm_substream *substream, int cmd)
 {
 	int ret_val = 0, str_id;
 	struct sst_runtime_stream *stream;
 	int status;
 	struct snd_soc_pcm_runtime *rtd = substream->private_data;
 
-	dev_dbg(rtd->dev, "sst_platform_pcm_trigger called\n");
+	dev_dbg(rtd->dev, "%s called\n", __func__);
 	if (substream->pcm->internal)
 		return 0;
 	stream = substream->runtime->private_data;
@@ -646,8 +647,8 @@ static int sst_platform_pcm_trigger(struct snd_pcm_substream *substream,
 }
 
 
-static snd_pcm_uframes_t sst_platform_pcm_pointer
-			(struct snd_pcm_substream *substream)
+static snd_pcm_uframes_t sst_soc_pointer(struct snd_soc_component *component,
+					 struct snd_pcm_substream *substream)
 {
 	struct sst_runtime_stream *stream;
 	int ret_val, status;
@@ -668,14 +669,8 @@ static snd_pcm_uframes_t sst_platform_pcm_pointer
 	return str_info->buffer_ptr;
 }
 
-static const struct snd_pcm_ops sst_platform_ops = {
-	.open = sst_platform_open,
-	.ioctl = snd_pcm_lib_ioctl,
-	.trigger = sst_platform_pcm_trigger,
-	.pointer = sst_platform_pcm_pointer,
-};
-
-static int sst_pcm_new(struct snd_soc_pcm_runtime *rtd)
+static int sst_soc_pcm_new(struct snd_soc_component *component,
+			   struct snd_soc_pcm_runtime *rtd)
 {
 	struct snd_soc_dai *dai = rtd->cpu_dai;
 	struct snd_pcm *pcm = rtd->pcm;
@@ -709,9 +704,12 @@ static const struct snd_soc_component_driver sst_soc_platform_drv  = {
 	.name		= DRV_NAME,
 	.probe		= sst_soc_probe,
 	.remove		= sst_soc_remove,
-	.ops		= &sst_platform_ops,
+	.open		= sst_soc_open,
+	.ioctl		= snd_soc_pcm_lib_ioctl,
+	.trigger	= sst_soc_trigger,
+	.pointer	= sst_soc_pointer,
 	.compr_ops	= &sst_platform_compr_ops,
-	.pcm_new	= sst_pcm_new,
+	.pcm_construct	= sst_soc_pcm_new,
 };
 
 static int sst_platform_probe(struct platform_device *pdev)
diff --git a/sound/soc/intel/baytrail/sst-baytrail-pcm.c b/sound/soc/intel/baytrail/sst-baytrail-pcm.c
index 54f2ee3010ee..1d780fcc448c 100644
--- a/sound/soc/intel/baytrail/sst-baytrail-pcm.c
+++ b/sound/soc/intel/baytrail/sst-baytrail-pcm.c
@@ -58,11 +58,11 @@ struct sst_byt_priv_data {
 };
 
 /* this may get called several times by oss emulation */
-static int sst_byt_pcm_hw_params(struct snd_pcm_substream *substream,
+static int sst_byt_pcm_hw_params(struct snd_soc_component *component,
+				 struct snd_pcm_substream *substream,
 				 struct snd_pcm_hw_params *params)
 {
 	struct snd_soc_pcm_runtime *rtd = substream->private_data;
-	struct snd_soc_component *component = snd_soc_rtdcom_lookup(rtd, DRV_NAME);
 	struct sst_byt_priv_data *pdata = snd_soc_component_get_drvdata(component);
 	struct sst_byt_pcm_data *pcm_data = &pdata->pcm[substream->stream];
 	struct sst_byt *byt = pdata->byt;
@@ -121,7 +121,8 @@ static int sst_byt_pcm_hw_params(struct snd_pcm_substream *substream,
 	return 0;
 }
 
-static int sst_byt_pcm_hw_free(struct snd_pcm_substream *substream)
+static int sst_byt_pcm_hw_free(struct snd_soc_component *component,
+			       struct snd_pcm_substream *substream)
 {
 	struct snd_soc_pcm_runtime *rtd = substream->private_data;
 
@@ -164,10 +165,10 @@ static void sst_byt_pcm_work(struct work_struct *work)
 		sst_byt_pcm_restore_stream_context(pcm_data->substream);
 }
 
-static int sst_byt_pcm_trigger(struct snd_pcm_substream *substream, int cmd)
+static int sst_byt_pcm_trigger(struct snd_soc_component *component,
+			       struct snd_pcm_substream *substream, int cmd)
 {
 	struct snd_soc_pcm_runtime *rtd = substream->private_data;
-	struct snd_soc_component *component = snd_soc_rtdcom_lookup(rtd, DRV_NAME);
 	struct sst_byt_priv_data *pdata = snd_soc_component_get_drvdata(component);
 	struct sst_byt_pcm_data *pcm_data = &pdata->pcm[substream->stream];
 	struct sst_byt *byt = pdata->byt;
@@ -228,11 +229,11 @@ static u32 byt_notify_pointer(struct sst_byt_stream *stream, void *data)
 	return pos;
 }
 
-static snd_pcm_uframes_t sst_byt_pcm_pointer(struct snd_pcm_substream *substream)
+static snd_pcm_uframes_t sst_byt_pcm_pointer(struct snd_soc_component *component,
+					     struct snd_pcm_substream *substream)
 {
 	struct snd_soc_pcm_runtime *rtd = substream->private_data;
 	struct snd_pcm_runtime *runtime = substream->runtime;
-	struct snd_soc_component *component = snd_soc_rtdcom_lookup(rtd, DRV_NAME);
 	struct sst_byt_priv_data *pdata = snd_soc_component_get_drvdata(component);
 	struct sst_byt_pcm_data *pcm_data = &pdata->pcm[substream->stream];
 
@@ -241,10 +242,10 @@ static snd_pcm_uframes_t sst_byt_pcm_pointer(struct snd_pcm_substream *substream
 	return bytes_to_frames(runtime, pcm_data->hw_ptr);
 }
 
-static int sst_byt_pcm_open(struct snd_pcm_substream *substream)
+static int sst_byt_pcm_open(struct snd_soc_component *component,
+			    struct snd_pcm_substream *substream)
 {
 	struct snd_soc_pcm_runtime *rtd = substream->private_data;
-	struct snd_soc_component *component = snd_soc_rtdcom_lookup(rtd, DRV_NAME);
 	struct sst_byt_priv_data *pdata = snd_soc_component_get_drvdata(component);
 	struct sst_byt_pcm_data *pcm_data = &pdata->pcm[substream->stream];
 	struct sst_byt *byt = pdata->byt;
@@ -269,10 +270,10 @@ static int sst_byt_pcm_open(struct snd_pcm_substream *substream)
 	return 0;
 }
 
-static int sst_byt_pcm_close(struct snd_pcm_substream *substream)
+static int sst_byt_pcm_close(struct snd_soc_component *component,
+			     struct snd_pcm_substream *substream)
 {
 	struct snd_soc_pcm_runtime *rtd = substream->private_data;
-	struct snd_soc_component *component = snd_soc_rtdcom_lookup(rtd, DRV_NAME);
 	struct sst_byt_priv_data *pdata = snd_soc_component_get_drvdata(component);
 	struct sst_byt_pcm_data *pcm_data = &pdata->pcm[substream->stream];
 	struct sst_byt *byt = pdata->byt;
@@ -294,7 +295,8 @@ out:
 	return ret;
 }
 
-static int sst_byt_pcm_mmap(struct snd_pcm_substream *substream,
+static int sst_byt_pcm_mmap(struct snd_soc_component *component,
+			    struct snd_pcm_substream *substream,
 			    struct vm_area_struct *vma)
 {
 	struct snd_soc_pcm_runtime *rtd = substream->private_data;
@@ -303,22 +305,11 @@ static int sst_byt_pcm_mmap(struct snd_pcm_substream *substream,
 	return snd_pcm_lib_default_mmap(substream, vma);
 }
 
-static const struct snd_pcm_ops sst_byt_pcm_ops = {
-	.open		= sst_byt_pcm_open,
-	.close		= sst_byt_pcm_close,
-	.ioctl		= snd_pcm_lib_ioctl,
-	.hw_params	= sst_byt_pcm_hw_params,
-	.hw_free	= sst_byt_pcm_hw_free,
-	.trigger	= sst_byt_pcm_trigger,
-	.pointer	= sst_byt_pcm_pointer,
-	.mmap		= sst_byt_pcm_mmap,
-};
-
-static int sst_byt_pcm_new(struct snd_soc_pcm_runtime *rtd)
+static int sst_byt_pcm_new(struct snd_soc_component *component,
+			   struct snd_soc_pcm_runtime *rtd)
 {
 	struct snd_pcm *pcm = rtd->pcm;
 	size_t size;
-	struct snd_soc_component *component = snd_soc_rtdcom_lookup(rtd, DRV_NAME);
 	struct sst_pdata *pdata = dev_get_platdata(component->dev);
 
 	if (pcm->streams[SNDRV_PCM_STREAM_PLAYBACK].substream ||
@@ -380,8 +371,15 @@ static int sst_byt_pcm_probe(struct snd_soc_component *component)
 static const struct snd_soc_component_driver byt_dai_component = {
 	.name		= DRV_NAME,
 	.probe		= sst_byt_pcm_probe,
-	.ops		= &sst_byt_pcm_ops,
-	.pcm_new	= sst_byt_pcm_new,
+	.open		= sst_byt_pcm_open,
+	.close		= sst_byt_pcm_close,
+	.ioctl		= snd_soc_pcm_lib_ioctl,
+	.hw_params	= sst_byt_pcm_hw_params,
+	.hw_free	= sst_byt_pcm_hw_free,
+	.trigger	= sst_byt_pcm_trigger,
+	.pointer	= sst_byt_pcm_pointer,
+	.mmap		= sst_byt_pcm_mmap,
+	.pcm_construct	= sst_byt_pcm_new,
 };
 
 #ifdef CONFIG_PM
diff --git a/sound/soc/intel/boards/Kconfig b/sound/soc/intel/boards/Kconfig
index 5c27f7ab4a5f..ef20316e83d1 100644
--- a/sound/soc/intel/boards/Kconfig
+++ b/sound/soc/intel/boards/Kconfig
@@ -3,13 +3,13 @@ menuconfig SND_SOC_INTEL_MACH
 	bool "Intel Machine drivers"
 	depends on SND_SOC_INTEL_SST_TOPLEVEL || SND_SOC_SOF_INTEL_TOPLEVEL
 	help
-         Intel ASoC Machine Drivers. If you have a Intel machine that
-         has an audio controller with a DSP and I2S or DMIC port, then
-         enable this option by saying Y
+	 Intel ASoC Machine Drivers. If you have a Intel machine that
+	 has an audio controller with a DSP and I2S or DMIC port, then
+	 enable this option by saying Y
 
-         Note that the answer to this question doesn't directly affect the
-         kernel: saying N will just cause the configurator to skip all
-         the questions about Intel ASoC machine drivers.
+	 Note that the answer to this question doesn't directly affect the
+	 kernel: saying N will just cause the configurator to skip all
+	 the questions about Intel ASoC machine drivers.
 
 if SND_SOC_INTEL_MACH
 
@@ -114,11 +114,11 @@ config SND_SOC_INTEL_CHT_BSW_RT5672_MACH
 	depends on X86_INTEL_LPSS || COMPILE_TEST
 	select SND_SOC_ACPI
 	select SND_SOC_RT5670
-        help
-          This adds support for ASoC machine driver for Intel(R) Cherrytrail & Braswell
-          platforms with RT5672 audio codec.
-          Say Y or m if you have such a device. This is a recommended option.
-          If unsure select "N".
+	help
+	  This adds support for ASoC machine driver for Intel(R) Cherrytrail & Braswell
+	  platforms with RT5672 audio codec.
+	  Say Y or m if you have such a device. This is a recommended option.
+	  If unsure select "N".
 
 config SND_SOC_INTEL_CHT_BSW_RT5645_MACH
 	tristate "Cherrytrail & Braswell with RT5645/5650 codec"
@@ -263,14 +263,17 @@ config SND_SOC_INTEL_DA7219_MAX98357A_GENERIC
 	select SND_SOC_DMIC
 	select SND_SOC_HDAC_HDMI
 
+config SND_SOC_INTEL_BXT_DA7219_MAX98357A_COMMON
+	tristate
+	select SND_SOC_INTEL_DA7219_MAX98357A_GENERIC
+
 if SND_SOC_INTEL_APL
 
 config SND_SOC_INTEL_BXT_DA7219_MAX98357A_MACH
 	tristate "Broxton with DA7219 and MAX98357A in I2S Mode"
 	depends on I2C && ACPI
 	depends on MFD_INTEL_LPSS || COMPILE_TEST
-	select SND_SOC_INTEL_DA7219_MAX98357A_GENERIC
-	select SND_HDA_DSP_LOADER
+	select SND_SOC_INTEL_BXT_DA7219_MAX98357A_COMMON
 	help
 	   This adds support for ASoC machine driver for Broxton-P platforms
 	   with DA7219 + MAX98357A I2S audio codec.
@@ -284,7 +287,6 @@ config SND_SOC_INTEL_BXT_RT298_MACH
 	select SND_SOC_RT298
 	select SND_SOC_DMIC
 	select SND_SOC_HDAC_HDMI
-	select SND_HDA_DSP_LOADER
 	help
 	   This adds support for ASoC machine driver for Broxton platforms
 	   with RT286 I2S audio codec.
@@ -311,20 +313,21 @@ config SND_SOC_INTEL_KBL_RT5663_MAX98927_MACH
 	  If unsure select "N".
 
 config SND_SOC_INTEL_KBL_RT5663_RT5514_MAX98927_MACH
-        tristate "KBL with RT5663, RT5514 and MAX98927 in I2S Mode"
+	tristate "KBL with RT5663, RT5514 and MAX98927 in I2S Mode"
 	depends on I2C && ACPI
 	depends on MFD_INTEL_LPSS || COMPILE_TEST
-        depends on SPI
-        select SND_SOC_RT5663
-        select SND_SOC_RT5514
-        select SND_SOC_RT5514_SPI
-        select SND_SOC_MAX98927
-        select SND_SOC_HDAC_HDMI
-        help
-          This adds support for ASoC Onboard Codec I2S machine driver. This will
-          create an alsa sound card for RT5663 + RT5514 + MAX98927.
-          Say Y or m if you have such a device. This is a recommended option.
-          If unsure select "N".
+	depends on SPI
+	select SND_SOC_RT5663
+	select SND_SOC_RT5514
+	select SND_SOC_RT5514_SPI
+	select SND_SOC_MAX98927
+	select SND_SOC_HDAC_HDMI
+	select SND_SOC_INTEL_SKYLAKE_SSP_CLK
+	help
+	  This adds support for ASoC Onboard Codec I2S machine driver. This will
+	  create an alsa sound card for RT5663 + RT5514 + MAX98927.
+	  Say Y or m if you have such a device. This is a recommended option.
+	  If unsure select "N".
 
 config SND_SOC_INTEL_KBL_DA7219_MAX98357A_MACH
 	tristate "KBL with DA7219 and MAX98357A in I2S Mode"
@@ -364,7 +367,18 @@ config SND_SOC_INTEL_KBL_RT5660_MACH
 
 endif ## SND_SOC_INTEL_KBL
 
-if SND_SOC_INTEL_GLK || (SND_SOC_SOF_GEMINILAKE  && SND_SOC_SOF_HDA_LINK)
+if SND_SOC_SOF_GEMINILAKE  && SND_SOC_SOF_HDA_LINK
+
+config SND_SOC_INTEL_GLK_DA7219_MAX98357A_MACH
+	tristate "GLK with DA7219 and MAX98357A in I2S Mode"
+	depends on I2C && ACPI
+	depends on MFD_INTEL_LPSS || COMPILE_TEST
+	select SND_SOC_INTEL_BXT_DA7219_MAX98357A_COMMON
+	help
+	   This adds support for ASoC machine driver for Geminilake platforms
+	   with DA7219 + MAX98357A I2S audio codec.
+	   Say Y or m if you have such a device. This is a recommended option.
+	   If unsure select "N".
 
 config SND_SOC_INTEL_GLK_RT5682_MAX98357A_MACH
 	tristate "GLK with RT5682 and MAX98357A in I2S Mode"
@@ -374,14 +388,13 @@ config SND_SOC_INTEL_GLK_RT5682_MAX98357A_MACH
 	select SND_SOC_MAX98357A
 	select SND_SOC_DMIC
 	select SND_SOC_HDAC_HDMI
-	select SND_HDA_DSP_LOADER
 	help
 	   This adds support for ASoC machine driver for Geminilake platforms
 	   with RT5682 + MAX98357A I2S audio codec.
 	   Say Y if you have such a device.
 	   If unsure select "N".
 
-endif ## SND_SOC_INTEL_GLK || (SND_SOC_SOF_GEMINILAKE  && SND_SOC_SOF_HDA_LINK)
+endif ## SND_SOC_SOF_GEMINILAKE  && SND_SOC_SOF_HDA_LINK
 
 if SND_SOC_INTEL_SKYLAKE_HDAUDIO_CODEC || SND_SOC_SOF_HDA_AUDIO_CODEC
 
@@ -393,16 +406,16 @@ config SND_SOC_INTEL_SKL_HDA_DSP_GENERIC_MACH
 	help
 	  This adds support for ASoC machine driver for Intel platforms
 	  SKL/KBL/BXT/APL with iDisp, HDA audio codecs.
-          Say Y or m if you have such a device. This is a recommended option.
+	  Say Y or m if you have such a device. This is a recommended option.
 	  If unsure select "N".
 
 endif ## SND_SOC_INTEL_SKYLAKE_HDAUDIO_CODEC || SND_SOC_SOF_HDA_AUDIO_CODEC
 
-if SND_SOC_SOF_HDA_COMMON || SND_SOC_SOF_BAYTRAIL
+if SND_SOC_SOF_HDA_LINK || SND_SOC_SOF_BAYTRAIL
 config SND_SOC_INTEL_SOF_RT5682_MACH
 	tristate "SOF with rt5682 codec in I2S Mode"
 	depends on I2C && ACPI
-	depends on (SND_SOC_SOF_HDA_COMMON && (MFD_INTEL_LPSS || COMPILE_TEST)) ||\
+	depends on (SND_SOC_SOF_HDA_LINK && (MFD_INTEL_LPSS || COMPILE_TEST)) ||\
 		   (SND_SOC_SOF_BAYTRAIL && (X86_INTEL_LPSS || COMPILE_TEST))
 	select SND_SOC_RT5682
 	select SND_SOC_DMIC
@@ -412,7 +425,7 @@ config SND_SOC_INTEL_SOF_RT5682_MACH
 	   with rt5682 codec.
 	   Say Y if you have such a device.
 	   If unsure select "N".
-endif ## SND_SOC_SOF_HDA_COMMON || SND_SOC_SOF_BAYTRAIL
+endif ## SND_SOC_SOF_HDA_LINK || SND_SOC_SOF_BAYTRAIL
 
 if (SND_SOC_SOF_COMETLAKE_LP && SND_SOC_SOF_HDA_LINK)
 
@@ -420,7 +433,26 @@ config SND_SOC_INTEL_CML_LP_DA7219_MAX98357A_MACH
 	tristate "CML_LP with DA7219 and MAX98357A in I2S Mode"
 	depends on I2C && ACPI
 	depends on MFD_INTEL_LPSS || COMPILE_TEST
-	select SND_SOC_INTEL_DA7219_MAX98357A_GENERIC
+	select SND_SOC_INTEL_BXT_DA7219_MAX98357A_COMMON
+	help
+	   This adds support for ASoC machine driver for Cometlake platforms
+	   with DA7219 + MAX98357A I2S audio codec.
+	   Say Y or m if you have such a device. This is a recommended option.
+	   If unsure select "N".
+
+config SND_SOC_INTEL_SOF_CML_RT1011_RT5682_MACH
+	tristate "CML with RT1011 and RT5682 in I2S Mode"
+	depends on I2C && ACPI
+	depends on MFD_INTEL_LPSS || COMPILE_TEST
+	select SND_SOC_RT1011
+	select SND_SOC_RT5682
+	select SND_SOC_DMIC
+	select SND_SOC_HDAC_HDMI
+	help
+	  This adds support for ASoC machine driver for SOF platform with
+	  RT1011 + RT5682 I2S codec.
+	  Say Y if you have such a device.
+	  If unsure select "N".
 
 endif ## SND_SOC_SOF_COMETLAKE_LP && SND_SOC_SOF_HDA_LINK
 
diff --git a/sound/soc/intel/boards/Makefile b/sound/soc/intel/boards/Makefile
index 6445f90ea542..ba1aa89db09d 100644
--- a/sound/soc/intel/boards/Makefile
+++ b/sound/soc/intel/boards/Makefile
@@ -4,9 +4,9 @@ snd-soc-sst-byt-rt5640-mach-objs := byt-rt5640.o
 snd-soc-sst-byt-max98090-mach-objs := byt-max98090.o
 snd-soc-sst-bdw-rt5677-mach-objs := bdw-rt5677.o
 snd-soc-sst-broadwell-objs := broadwell.o
-snd-soc-sst-bxt-da7219_max98357a-objs := bxt_da7219_max98357a.o
-snd-soc-sst-bxt-rt298-objs := bxt_rt298.o
-snd-soc-sst-glk-rt5682_max98357a-objs := glk_rt5682_max98357a.o
+snd-soc-sst-bxt-da7219_max98357a-objs := bxt_da7219_max98357a.o hda_dsp_common.o
+snd-soc-sst-bxt-rt298-objs := bxt_rt298.o hda_dsp_common.o
+snd-soc-sst-glk-rt5682_max98357a-objs := glk_rt5682_max98357a.o hda_dsp_common.o
 snd-soc-sst-bytcr-rt5640-objs := bytcr_rt5640.o
 snd-soc-sst-bytcr-rt5651-objs := bytcr_rt5651.o
 snd-soc-sst-cht-bsw-rt5672-objs := cht_bsw_rt5672.o
@@ -17,14 +17,15 @@ snd-soc-sst-byt-cht-cx2072x-objs := bytcht_cx2072x.o
 snd-soc-sst-byt-cht-da7213-objs := bytcht_da7213.o
 snd-soc-sst-byt-cht-es8316-objs := bytcht_es8316.o
 snd-soc-sst-byt-cht-nocodec-objs := bytcht_nocodec.o
-snd-soc-sof_rt5682-objs := sof_rt5682.o
+snd-soc-sof_rt5682-objs := sof_rt5682.o hda_dsp_common.o
+snd-soc-cml_rt1011_rt5682-objs := cml_rt1011_rt5682.o hda_dsp_common.o
 snd-soc-kbl_da7219_max98357a-objs := kbl_da7219_max98357a.o
 snd-soc-kbl_da7219_max98927-objs := kbl_da7219_max98927.o
 snd-soc-kbl_rt5663_max98927-objs := kbl_rt5663_max98927.o
 snd-soc-kbl_rt5663_rt5514_max98927-objs := kbl_rt5663_rt5514_max98927.o
 snd-soc-kbl_rt5660-objs := kbl_rt5660.o
 snd-soc-skl_rt286-objs := skl_rt286.o
-snd-soc-skl_hda_dsp-objs := skl_hda_dsp_generic.o skl_hda_dsp_common.o
+snd-soc-skl_hda_dsp-objs := skl_hda_dsp_generic.o skl_hda_dsp_common.o hda_dsp_common.o
 snd-skl_nau88l25_max98357a-objs := skl_nau88l25_max98357a.o
 snd-soc-skl_nau88l25_ssm4567-objs := skl_nau88l25_ssm4567.o
 
@@ -32,7 +33,7 @@ obj-$(CONFIG_SND_SOC_INTEL_SOF_RT5682_MACH) += snd-soc-sof_rt5682.o
 obj-$(CONFIG_SND_SOC_INTEL_HASWELL_MACH) += snd-soc-sst-haswell.o
 obj-$(CONFIG_SND_SOC_INTEL_BYT_RT5640_MACH) += snd-soc-sst-byt-rt5640-mach.o
 obj-$(CONFIG_SND_SOC_INTEL_BYT_MAX98090_MACH) += snd-soc-sst-byt-max98090-mach.o
-obj-$(CONFIG_SND_SOC_INTEL_BXT_DA7219_MAX98357A_MACH) += snd-soc-sst-bxt-da7219_max98357a.o
+obj-$(CONFIG_SND_SOC_INTEL_BXT_DA7219_MAX98357A_COMMON) += snd-soc-sst-bxt-da7219_max98357a.o
 obj-$(CONFIG_SND_SOC_INTEL_BXT_RT298_MACH) += snd-soc-sst-bxt-rt298.o
 obj-$(CONFIG_SND_SOC_INTEL_GLK_RT5682_MAX98357A_MACH) += snd-soc-sst-glk-rt5682_max98357a.o
 obj-$(CONFIG_SND_SOC_INTEL_BROADWELL_MACH) += snd-soc-sst-broadwell.o
@@ -47,6 +48,7 @@ obj-$(CONFIG_SND_SOC_INTEL_BYT_CHT_CX2072X_MACH) += snd-soc-sst-byt-cht-cx2072x.
 obj-$(CONFIG_SND_SOC_INTEL_BYT_CHT_DA7213_MACH) += snd-soc-sst-byt-cht-da7213.o
 obj-$(CONFIG_SND_SOC_INTEL_BYT_CHT_ES8316_MACH) += snd-soc-sst-byt-cht-es8316.o
 obj-$(CONFIG_SND_SOC_INTEL_BYT_CHT_NOCODEC_MACH) += snd-soc-sst-byt-cht-nocodec.o
+obj-$(CONFIG_SND_SOC_INTEL_SOF_CML_RT1011_RT5682_MACH) += snd-soc-cml_rt1011_rt5682.o
 obj-$(CONFIG_SND_SOC_INTEL_KBL_DA7219_MAX98357A_MACH) += snd-soc-kbl_da7219_max98357a.o
 obj-$(CONFIG_SND_SOC_INTEL_KBL_DA7219_MAX98927_MACH) += snd-soc-kbl_da7219_max98927.o
 obj-$(CONFIG_SND_SOC_INTEL_KBL_RT5663_MAX98927_MACH) += snd-soc-kbl_rt5663_max98927.o
diff --git a/sound/soc/intel/boards/bdw-rt5677.c b/sound/soc/intel/boards/bdw-rt5677.c
index 4a4d3353e26d..2af8e5a62da8 100644
--- a/sound/soc/intel/boards/bdw-rt5677.c
+++ b/sound/soc/intel/boards/bdw-rt5677.c
@@ -74,6 +74,11 @@ static const struct snd_soc_dapm_route bdw_rt5677_map[] = {
 	/* CODEC BE connections */
 	{"SSP0 CODEC IN", NULL, "AIF1 Capture"},
 	{"AIF1 Playback", NULL, "SSP0 CODEC OUT"},
+	{"DSP Capture", NULL, "DSP Buffer"},
+
+	/* DSP Clock Connections */
+	{ "DSP Buffer", NULL, "SSP0 CODEC IN" },
+	{ "SSP0 CODEC IN", NULL, "DSPTX" },
 };
 
 static const struct snd_kcontrol_new bdw_rt5677_controls[] = {
@@ -165,10 +170,37 @@ static int bdw_rt5677_hw_params(struct snd_pcm_substream *substream,
 	return ret;
 }
 
+static int bdw_rt5677_dsp_hw_params(struct snd_pcm_substream *substream,
+	struct snd_pcm_hw_params *params)
+{
+	struct snd_soc_pcm_runtime *rtd = substream->private_data;
+	struct snd_soc_dai *codec_dai = rtd->codec_dai;
+	int ret;
+
+	ret = snd_soc_dai_set_sysclk(codec_dai, RT5677_SCLK_S_PLL1, 24576000,
+		SND_SOC_CLOCK_IN);
+	if (ret < 0) {
+		dev_err(rtd->dev, "can't set codec sysclk configuration\n");
+		return ret;
+	}
+	ret = snd_soc_dai_set_pll(codec_dai, 0, RT5677_PLL1_S_MCLK,
+		24000000, 24576000);
+	if (ret < 0) {
+		dev_err(rtd->dev, "can't set codec pll configuration\n");
+		return ret;
+	}
+
+	return 0;
+}
+
 static const struct snd_soc_ops bdw_rt5677_ops = {
 	.hw_params = bdw_rt5677_hw_params,
 };
 
+static const struct snd_soc_ops bdw_rt5677_dsp_ops = {
+	.hw_params = bdw_rt5677_dsp_hw_params,
+};
+
 #if !IS_ENABLED(CONFIG_SND_SOC_SOF_BROADWELL)
 static int bdw_rt5677_rtd_init(struct snd_soc_pcm_runtime *rtd)
 {
@@ -208,6 +240,11 @@ static int bdw_rt5677_init(struct snd_soc_pcm_runtime *rtd)
 	rt5677_sel_asrc_clk_src(component, RT5677_DA_STEREO_FILTER |
 			RT5677_AD_STEREO1_FILTER | RT5677_I2S1_SOURCE,
 			RT5677_CLK_SEL_I2S1_ASRC);
+	/* Enable codec ASRC function for Mono ADC L.
+	 * The ASRC clock source is clk_sys2_asrc.
+	 */
+	rt5677_sel_asrc_clk_src(component, RT5677_AD_MONO_L_FILTER,
+			RT5677_CLK_SEL_SYS2);
 
 	/* Request rt5677 GPIO for headphone amp control */
 	bdw_rt5677->gpio_hp_en = devm_gpiod_get(component->dev, "headphone-enable",
@@ -258,6 +295,12 @@ SND_SOC_DAILINK_DEF(platform,
 SND_SOC_DAILINK_DEF(be,
 	DAILINK_COMP_ARRAY(COMP_CODEC("i2c-RT5677CE:00", "rt5677-aif1")));
 
+/* Wake on voice interface */
+SND_SOC_DAILINK_DEFS(dsp,
+	DAILINK_COMP_ARRAY(COMP_CPU("spi-RT5677AA:00")),
+	DAILINK_COMP_ARRAY(COMP_CODEC("i2c-RT5677CE:00", "rt5677-dspbuffer")),
+	DAILINK_COMP_ARRAY(COMP_PLATFORM("spi-RT5677AA:00")));
+
 static struct snd_soc_dai_link bdw_rt5677_dais[] = {
 	/* Front End DAI links */
 	{
@@ -276,6 +319,14 @@ static struct snd_soc_dai_link bdw_rt5677_dais[] = {
 		SND_SOC_DAILINK_REG(fe, dummy, platform),
 	},
 
+	/* Non-DPCM links */
+	{
+		.name = "Codec DSP",
+		.stream_name = "Wake on Voice",
+		.ops = &bdw_rt5677_dsp_ops,
+		SND_SOC_DAILINK_REG(dsp),
+	},
+
 	/* Back End DAI links */
 	{
 		/* SSP0 - Codec */
diff --git a/sound/soc/intel/boards/bxt_da7219_max98357a.c b/sound/soc/intel/boards/bxt_da7219_max98357a.c
index ac1dea5f9d11..5873abb46441 100644
--- a/sound/soc/intel/boards/bxt_da7219_max98357a.c
+++ b/sound/soc/intel/boards/bxt_da7219_max98357a.c
@@ -21,6 +21,7 @@
 #include "../../codecs/da7219.h"
 #include "../../codecs/da7219-aad.h"
 #include "../common/soc-intel-quirks.h"
+#include "hda_dsp_common.h"
 
 #define BXT_DIALOG_CODEC_DAI	"da7219-hifi"
 #define BXT_MAXIM_CODEC_DAI	"HiFi"
@@ -38,6 +39,7 @@ struct bxt_hdmi_pcm {
 
 struct bxt_card_private {
 	struct list_head hdmi_pcm_list;
+	bool common_hdmi_codec_drv;
 };
 
 enum {
@@ -615,6 +617,13 @@ static int bxt_card_late_probe(struct snd_soc_card *card)
 		snd_soc_dapm_add_routes(&card->dapm, broxton_map,
 					ARRAY_SIZE(broxton_map));
 
+	pcm = list_first_entry(&ctx->hdmi_pcm_list, struct bxt_hdmi_pcm,
+			       head);
+	component = pcm->codec_dai->component;
+
+	if (ctx->common_hdmi_codec_drv)
+		return hda_dsp_hdmi_build_controls(card, component);
+
 	list_for_each_entry(pcm, &ctx->hdmi_pcm_list, head) {
 		component = pcm->codec_dai->component;
 		snprintf(jack_name, sizeof(jack_name),
@@ -720,6 +729,8 @@ static int broxton_audio_probe(struct platform_device *pdev)
 	if (ret)
 		return ret;
 
+	ctx->common_hdmi_codec_drv = mach->mach_params.common_hdmi_codec_drv;
+
 	return devm_snd_soc_register_card(&pdev->dev, &broxton_audio_card);
 }
 
diff --git a/sound/soc/intel/boards/bxt_rt298.c b/sound/soc/intel/boards/bxt_rt298.c
index adf416a49b48..eabf9d8468ae 100644
--- a/sound/soc/intel/boards/bxt_rt298.c
+++ b/sound/soc/intel/boards/bxt_rt298.c
@@ -18,6 +18,7 @@
 #include <sound/pcm_params.h>
 #include "../../codecs/hdac_hdmi.h"
 #include "../../codecs/rt298.h"
+#include "hda_dsp_common.h"
 
 /* Headset jack detection DAPM pins */
 static struct snd_soc_jack broxton_headset;
@@ -31,6 +32,7 @@ struct bxt_hdmi_pcm {
 
 struct bxt_rt286_private {
 	struct list_head hdmi_pcm_list;
+	bool common_hdmi_codec_drv;
 };
 
 enum {
@@ -527,6 +529,13 @@ static int bxt_card_late_probe(struct snd_soc_card *card)
 	int err, i = 0;
 	char jack_name[NAME_SIZE];
 
+	pcm = list_first_entry(&ctx->hdmi_pcm_list, struct bxt_hdmi_pcm,
+			       head);
+	component = pcm->codec_dai->component;
+
+	if (ctx->common_hdmi_codec_drv)
+		return hda_dsp_hdmi_build_controls(card, component);
+
 	list_for_each_entry(pcm, &ctx->hdmi_pcm_list, head) {
 		component = pcm->codec_dai->component;
 		snprintf(jack_name, sizeof(jack_name),
@@ -626,6 +635,8 @@ static int broxton_audio_probe(struct platform_device *pdev)
 	if (ret)
 		return ret;
 
+	ctx->common_hdmi_codec_drv = mach->mach_params.common_hdmi_codec_drv;
+
 	return devm_snd_soc_register_card(&pdev->dev, card);
 }
 
diff --git a/sound/soc/intel/boards/bytcr_rt5640.c b/sound/soc/intel/boards/bytcr_rt5640.c
index 9c1aa4ec9cba..dd2b5ad08659 100644
--- a/sound/soc/intel/boards/bytcr_rt5640.c
+++ b/sound/soc/intel/boards/bytcr_rt5640.c
@@ -405,10 +405,12 @@ static const struct dmi_system_id byt_rt5640_quirk_table[] = {
 			DMI_MATCH(DMI_SYS_VENDOR, "Acer"),
 			DMI_MATCH(DMI_PRODUCT_NAME, "Aspire SW5-012"),
 		},
-		.driver_data = (void *)(BYT_RT5640_IN1_MAP |
-						 BYT_RT5640_MCLK_EN |
-						 BYT_RT5640_SSP0_AIF1),
-
+		.driver_data = (void *)(BYT_RT5640_DMIC1_MAP |
+					BYT_RT5640_JD_SRC_JD2_IN4N |
+					BYT_RT5640_OVCD_TH_2000UA |
+					BYT_RT5640_OVCD_SF_0P75 |
+					BYT_RT5640_SSP0_AIF1 |
+					BYT_RT5640_MCLK_EN),
 	},
 	{
 		.matches = {
diff --git a/sound/soc/intel/boards/cht_bsw_rt5645.c b/sound/soc/intel/boards/cht_bsw_rt5645.c
index 8879c3be29d5..c68a5b85a4a0 100644
--- a/sound/soc/intel/boards/cht_bsw_rt5645.c
+++ b/sound/soc/intel/boards/cht_bsw_rt5645.c
@@ -48,6 +48,7 @@ struct cht_mc_private {
 #define CHT_RT5645_SSP2_AIF2     BIT(16) /* default is using AIF1  */
 #define CHT_RT5645_SSP0_AIF1     BIT(17)
 #define CHT_RT5645_SSP0_AIF2     BIT(18)
+#define CHT_RT5645_PMC_PLT_CLK_0 BIT(19)
 
 static unsigned long cht_rt5645_quirk = 0;
 
@@ -59,6 +60,8 @@ static void log_quirks(struct device *dev)
 		dev_info(dev, "quirk SSP0_AIF1 enabled");
 	if (cht_rt5645_quirk & CHT_RT5645_SSP0_AIF2)
 		dev_info(dev, "quirk SSP0_AIF2 enabled");
+	if (cht_rt5645_quirk & CHT_RT5645_PMC_PLT_CLK_0)
+		dev_info(dev, "quirk PMC_PLT_CLK_0 enabled");
 }
 
 static int platform_clock_control(struct snd_soc_dapm_widget *w,
@@ -226,16 +229,22 @@ static int cht_aif1_hw_params(struct snd_pcm_substream *substream,
 	return 0;
 }
 
-/* uncomment when we have a real quirk
 static int cht_rt5645_quirk_cb(const struct dmi_system_id *id)
 {
 	cht_rt5645_quirk = (unsigned long)id->driver_data;
 	return 1;
 }
-*/
 
 static const struct dmi_system_id cht_rt5645_quirk_table[] = {
 	{
+		/* Strago family Chromebooks */
+		.callback = cht_rt5645_quirk_cb,
+		.matches = {
+			DMI_MATCH(DMI_PRODUCT_FAMILY, "Intel_Strago"),
+		},
+		.driver_data = (void *)CHT_RT5645_PMC_PLT_CLK_0,
+	},
+	{
 	},
 };
 
@@ -526,6 +535,7 @@ static int snd_cht_mc_probe(struct platform_device *pdev)
 	int dai_index = 0;
 	int ret_val = 0;
 	int i;
+	const char *mclk_name;
 
 	drv = devm_kzalloc(&pdev->dev, sizeof(*drv), GFP_KERNEL);
 	if (!drv)
@@ -662,11 +672,15 @@ static int snd_cht_mc_probe(struct platform_device *pdev)
 	if (ret_val)
 		return ret_val;
 
-	drv->mclk = devm_clk_get(&pdev->dev, "pmc_plt_clk_3");
+	if (cht_rt5645_quirk & CHT_RT5645_PMC_PLT_CLK_0)
+		mclk_name = "pmc_plt_clk_0";
+	else
+		mclk_name = "pmc_plt_clk_3";
+
+	drv->mclk = devm_clk_get(&pdev->dev, mclk_name);
 	if (IS_ERR(drv->mclk)) {
-		dev_err(&pdev->dev,
-			"Failed to get MCLK from pmc_plt_clk_3: %ld\n",
-			PTR_ERR(drv->mclk));
+		dev_err(&pdev->dev, "Failed to get MCLK from %s: %ld\n",
+			mclk_name, PTR_ERR(drv->mclk));
 		return PTR_ERR(drv->mclk);
 	}
 
diff --git a/sound/soc/intel/boards/cml_rt1011_rt5682.c b/sound/soc/intel/boards/cml_rt1011_rt5682.c
new file mode 100644
index 000000000000..a22f97234201
--- /dev/null
+++ b/sound/soc/intel/boards/cml_rt1011_rt5682.c
@@ -0,0 +1,487 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright(c) 2019 Intel Corporation.
+
+/*
+ * Intel Cometlake I2S Machine driver for RT1011 + RT5682 codec
+ */
+
+#include <linux/input.h>
+#include <linux/module.h>
+#include <linux/platform_device.h>
+#include <linux/clk.h>
+#include <linux/dmi.h>
+#include <linux/slab.h>
+#include <asm/cpu_device_id.h>
+#include <linux/acpi.h>
+#include <sound/core.h>
+#include <sound/jack.h>
+#include <sound/pcm.h>
+#include <sound/pcm_params.h>
+#include <sound/soc.h>
+#include <sound/rt5682.h>
+#include <sound/soc-acpi.h>
+#include "../../codecs/rt1011.h"
+#include "../../codecs/rt5682.h"
+#include "../../codecs/hdac_hdmi.h"
+#include "hda_dsp_common.h"
+
+/* The platform clock outputs 24Mhz clock to codec as I2S MCLK */
+#define CML_PLAT_CLK	24000000
+#define CML_RT1011_CODEC_DAI "rt1011-aif"
+#define CML_RT5682_CODEC_DAI "rt5682-aif1"
+#define NAME_SIZE 32
+
+static struct snd_soc_jack hdmi_jack[3];
+
+struct hdmi_pcm {
+	struct list_head head;
+	struct snd_soc_dai *codec_dai;
+	int device;
+};
+
+struct card_private {
+	char codec_name[SND_ACPI_I2C_ID_LEN];
+	struct snd_soc_jack headset;
+	struct list_head hdmi_pcm_list;
+	bool common_hdmi_codec_drv;
+};
+
+static const struct snd_kcontrol_new cml_controls[] = {
+	SOC_DAPM_PIN_SWITCH("Headphone Jack"),
+	SOC_DAPM_PIN_SWITCH("Headset Mic"),
+	SOC_DAPM_PIN_SWITCH("TL Ext Spk"),
+	SOC_DAPM_PIN_SWITCH("TR Ext Spk"),
+	SOC_DAPM_PIN_SWITCH("WL Ext Spk"),
+	SOC_DAPM_PIN_SWITCH("WR Ext Spk"),
+};
+
+static const struct snd_soc_dapm_widget cml_rt1011_rt5682_widgets[] = {
+	SND_SOC_DAPM_SPK("TL Ext Spk", NULL),
+	SND_SOC_DAPM_SPK("TR Ext Spk", NULL),
+	SND_SOC_DAPM_SPK("WL Ext Spk", NULL),
+	SND_SOC_DAPM_SPK("WR Ext Spk", NULL),
+	SND_SOC_DAPM_HP("Headphone Jack", NULL),
+	SND_SOC_DAPM_MIC("Headset Mic", NULL),
+	SND_SOC_DAPM_MIC("SoC DMIC", NULL),
+};
+
+static const struct snd_soc_dapm_route cml_rt1011_rt5682_map[] = {
+	/*speaker*/
+	{"TL Ext Spk", NULL, "TL SPO"},
+	{"TR Ext Spk", NULL, "TR SPO"},
+	{"WL Ext Spk", NULL, "WL SPO"},
+	{"WR Ext Spk", NULL, "WR SPO"},
+
+	/* HP jack connectors - unknown if we have jack detection */
+	{ "Headphone Jack", NULL, "HPOL" },
+	{ "Headphone Jack", NULL, "HPOR" },
+
+	/* other jacks */
+	{ "IN1P", NULL, "Headset Mic" },
+
+	/* DMIC */
+	{"DMic", NULL, "SoC DMIC"},
+};
+
+static int cml_rt5682_codec_init(struct snd_soc_pcm_runtime *rtd)
+{
+	struct card_private *ctx = snd_soc_card_get_drvdata(rtd->card);
+	struct snd_soc_component *component = rtd->codec_dai->component;
+	struct snd_soc_jack *jack;
+	int ret;
+
+	/* need to enable ASRC function for 24MHz mclk rate */
+	rt5682_sel_asrc_clk_src(component, RT5682_DA_STEREO1_FILTER |
+					RT5682_AD_STEREO1_FILTER,
+					RT5682_CLK_SEL_I2S1_ASRC);
+
+	/*
+	 * Headset buttons map to the google Reference headset.
+	 * These can be configured by userspace.
+	 */
+	ret = snd_soc_card_jack_new(rtd->card, "Headset Jack",
+				    SND_JACK_HEADSET | SND_JACK_BTN_0 |
+				    SND_JACK_BTN_1 | SND_JACK_BTN_2 |
+				    SND_JACK_BTN_3,
+				    &ctx->headset, NULL, 0);
+	if (ret) {
+		dev_err(rtd->dev, "Headset Jack creation failed: %d\n", ret);
+		return ret;
+	}
+
+	jack = &ctx->headset;
+
+	snd_jack_set_key(jack->jack, SND_JACK_BTN_0, KEY_PLAYPAUSE);
+	snd_jack_set_key(jack->jack, SND_JACK_BTN_1, KEY_VOICECOMMAND);
+	snd_jack_set_key(jack->jack, SND_JACK_BTN_2, KEY_VOLUMEUP);
+	snd_jack_set_key(jack->jack, SND_JACK_BTN_3, KEY_VOLUMEDOWN);
+	ret = snd_soc_component_set_jack(component, jack, NULL);
+	if (ret)
+		dev_err(rtd->dev, "Headset Jack call-back failed: %d\n", ret);
+
+	return ret;
+};
+
+static int cml_rt5682_hw_params(struct snd_pcm_substream *substream,
+				struct snd_pcm_hw_params *params)
+{
+	struct snd_soc_pcm_runtime *rtd = substream->private_data;
+	struct snd_soc_dai *codec_dai = rtd->codec_dai;
+	int clk_id, clk_freq, pll_out, ret;
+
+	clk_id = RT5682_PLL1_S_MCLK;
+	clk_freq = CML_PLAT_CLK;
+
+	pll_out = params_rate(params) * 512;
+
+	ret = snd_soc_dai_set_pll(codec_dai, 0, clk_id, clk_freq, pll_out);
+	if (ret < 0)
+		dev_warn(rtd->dev, "snd_soc_dai_set_pll err = %d\n", ret);
+
+	/* Configure sysclk for codec */
+	ret = snd_soc_dai_set_sysclk(codec_dai, RT5682_SCLK_S_PLL1,
+				     pll_out, SND_SOC_CLOCK_IN);
+	if (ret < 0)
+		dev_warn(rtd->dev, "snd_soc_dai_set_sysclk err = %d\n", ret);
+
+	/*
+	 * slot_width should be equal or large than data length, set them
+	 * be the same
+	 */
+	ret = snd_soc_dai_set_tdm_slot(codec_dai, 0x0, 0x0, 2,
+				       params_width(params));
+	if (ret < 0)
+		dev_warn(rtd->dev, "set TDM slot err:%d\n", ret);
+	return ret;
+}
+
+static int cml_rt1011_hw_params(struct snd_pcm_substream *substream,
+				struct snd_pcm_hw_params *params)
+{
+	struct snd_soc_pcm_runtime *rtd = substream->private_data;
+	struct snd_soc_dai *codec_dai;
+	struct snd_soc_card *card = rtd->card;
+	int srate, i, ret = 0;
+
+	srate = params_rate(params);
+
+	for (i = 0; i < rtd->num_codecs; i++) {
+		codec_dai = rtd->codec_dais[i];
+
+		/* 100 Fs to drive 24 bit data */
+		ret = snd_soc_dai_set_pll(codec_dai, 0, RT1011_PLL1_S_BCLK,
+					  100 * srate, 256 * srate);
+		if (ret < 0) {
+			dev_err(card->dev, "codec_dai clock not set\n");
+			return ret;
+		}
+
+		ret = snd_soc_dai_set_sysclk(codec_dai,
+					     RT1011_FS_SYS_PRE_S_PLL1,
+					     256 * srate, SND_SOC_CLOCK_IN);
+		if (ret < 0) {
+			dev_err(card->dev, "codec_dai clock not set\n");
+			return ret;
+		}
+
+		/*
+		 * Codec TDM is configured as 24 bit capture/ playback.
+		 * 2 CH PB is done over 4 codecs - 2 Woofers and 2 Tweeters.
+		 * The Left woofer and tweeter plays the Left playback data
+		 * and  similar by the Right.
+		 * Hence 2 codecs (1 T and 1 W pair) share same Rx slot.
+		 * The feedback is captured for each codec individually.
+		 * Hence all 4 codecs use 1 Tx slot each for feedback.
+		 */
+		if (!strcmp(codec_dai->component->name, "i2c-10EC1011:00")) {
+			ret = snd_soc_dai_set_tdm_slot(codec_dai,
+						       0x4, 0x1, 4, 24);
+			if (ret < 0)
+				break;
+		}
+		if (!strcmp(codec_dai->component->name, "i2c-10EC1011:02")) {
+			ret = snd_soc_dai_set_tdm_slot(codec_dai,
+						       0x1, 0x1, 4, 24);
+			if (ret < 0)
+				break;
+		}
+		/* TDM Rx slot 2 is used for Right Woofer & Tweeters pair */
+		if (!strcmp(codec_dai->component->name, "i2c-10EC1011:01")) {
+			ret = snd_soc_dai_set_tdm_slot(codec_dai,
+						       0x8, 0x2, 4, 24);
+			if (ret < 0)
+				break;
+		}
+		if (!strcmp(codec_dai->component->name, "i2c-10EC1011:03")) {
+			ret = snd_soc_dai_set_tdm_slot(codec_dai,
+						       0x2, 0x2, 4, 24);
+			if (ret < 0)
+				break;
+		}
+	}
+	if (ret < 0)
+		dev_err(rtd->dev,
+			"set codec TDM slot for %s failed with error %d\n",
+			codec_dai->component->name, ret);
+	return ret;
+}
+
+static struct snd_soc_ops cml_rt5682_ops = {
+	.hw_params = cml_rt5682_hw_params,
+};
+
+static const struct snd_soc_ops cml_rt1011_ops = {
+	.hw_params = cml_rt1011_hw_params,
+};
+
+static int sof_card_late_probe(struct snd_soc_card *card)
+{
+	struct card_private *ctx = snd_soc_card_get_drvdata(card);
+	struct snd_soc_component *component = NULL;
+	char jack_name[NAME_SIZE];
+	struct hdmi_pcm *pcm;
+	int ret, i = 0;
+
+	pcm = list_first_entry(&ctx->hdmi_pcm_list, struct hdmi_pcm,
+			       head);
+	component = pcm->codec_dai->component;
+
+	if (ctx->common_hdmi_codec_drv)
+		return hda_dsp_hdmi_build_controls(card, component);
+
+	list_for_each_entry(pcm, &ctx->hdmi_pcm_list, head) {
+		component = pcm->codec_dai->component;
+		snprintf(jack_name, sizeof(jack_name),
+			 "HDMI/DP, pcm=%d Jack", pcm->device);
+		ret = snd_soc_card_jack_new(card, jack_name,
+					    SND_JACK_AVOUT, &hdmi_jack[i],
+					    NULL, 0);
+		if (ret)
+			return ret;
+
+		ret = hdac_hdmi_jack_init(pcm->codec_dai, pcm->device,
+					  &hdmi_jack[i]);
+		if (ret < 0)
+			return ret;
+
+		i++;
+	}
+	if (!component)
+		return -EINVAL;
+
+	return hdac_hdmi_jack_port_init(component, &card->dapm);
+}
+
+static int hdmi_init(struct snd_soc_pcm_runtime *rtd)
+{
+	struct card_private *ctx = snd_soc_card_get_drvdata(rtd->card);
+	struct snd_soc_dai *dai = rtd->codec_dai;
+	struct hdmi_pcm *pcm;
+
+	pcm = devm_kzalloc(rtd->card->dev, sizeof(*pcm), GFP_KERNEL);
+	if (!pcm)
+		return -ENOMEM;
+
+	pcm->device = dai->id;
+	pcm->codec_dai = dai;
+
+	list_add_tail(&pcm->head, &ctx->hdmi_pcm_list);
+
+	return 0;
+}
+
+/* Cometlake digital audio interface glue - connects codec <--> CPU */
+
+SND_SOC_DAILINK_DEF(ssp0_pin,
+	DAILINK_COMP_ARRAY(COMP_CPU("SSP0 Pin")));
+SND_SOC_DAILINK_DEF(ssp0_codec,
+	DAILINK_COMP_ARRAY(COMP_CODEC("i2c-10EC5682:00",
+				CML_RT5682_CODEC_DAI)));
+
+SND_SOC_DAILINK_DEF(ssp1_pin,
+	DAILINK_COMP_ARRAY(COMP_CPU("SSP1 Pin")));
+SND_SOC_DAILINK_DEF(ssp1_codec,
+	DAILINK_COMP_ARRAY(
+	/* WL */ COMP_CODEC("i2c-10EC1011:00", CML_RT1011_CODEC_DAI),
+	/* WR */ COMP_CODEC("i2c-10EC1011:01", CML_RT1011_CODEC_DAI),
+	/* TL */ COMP_CODEC("i2c-10EC1011:02", CML_RT1011_CODEC_DAI),
+	/* TR */ COMP_CODEC("i2c-10EC1011:03", CML_RT1011_CODEC_DAI)));
+
+SND_SOC_DAILINK_DEF(dmic_pin,
+	DAILINK_COMP_ARRAY(COMP_CPU("DMIC01 Pin")));
+
+SND_SOC_DAILINK_DEF(dmic16k_pin,
+	DAILINK_COMP_ARRAY(COMP_CPU("DMIC16k Pin")));
+
+SND_SOC_DAILINK_DEF(dmic_codec,
+	DAILINK_COMP_ARRAY(COMP_CODEC("dmic-codec", "dmic-hifi")));
+
+SND_SOC_DAILINK_DEF(idisp1_pin,
+	DAILINK_COMP_ARRAY(COMP_CPU("iDisp1 Pin")));
+SND_SOC_DAILINK_DEF(idisp1_codec,
+	DAILINK_COMP_ARRAY(COMP_CODEC("ehdaudio0D2", "intel-hdmi-hifi1")));
+
+SND_SOC_DAILINK_DEF(idisp2_pin,
+	DAILINK_COMP_ARRAY(COMP_CPU("iDisp2 Pin")));
+SND_SOC_DAILINK_DEF(idisp2_codec,
+	DAILINK_COMP_ARRAY(COMP_CODEC("ehdaudio0D2", "intel-hdmi-hifi2")));
+
+SND_SOC_DAILINK_DEF(idisp3_pin,
+	DAILINK_COMP_ARRAY(COMP_CPU("iDisp3 Pin")));
+SND_SOC_DAILINK_DEF(idisp3_codec,
+	DAILINK_COMP_ARRAY(COMP_CODEC("ehdaudio0D2", "intel-hdmi-hifi3")));
+
+SND_SOC_DAILINK_DEF(platform,
+	DAILINK_COMP_ARRAY(COMP_PLATFORM("0000:00:1f.3")));
+
+static struct snd_soc_dai_link cml_rt1011_rt5682_dailink[] = {
+	/* Back End DAI links */
+	{
+		/* SSP0 - Codec */
+		.name = "SSP0-Codec",
+		.id = 0,
+		.init = cml_rt5682_codec_init,
+		.ignore_pmdown_time = 1,
+		.ops = &cml_rt5682_ops,
+		.dpcm_playback = 1,
+		.dpcm_capture = 1,
+		.no_pcm = 1,
+		SND_SOC_DAILINK_REG(ssp0_pin, ssp0_codec, platform),
+	},
+	{
+		.name = "dmic01",
+		.id = 1,
+		.ignore_suspend = 1,
+		.dpcm_capture = 1,
+		.no_pcm = 1,
+		SND_SOC_DAILINK_REG(dmic_pin, dmic_codec, platform),
+	},
+	{
+		.name = "dmic16k",
+		.id = 2,
+		.ignore_suspend = 1,
+		.dpcm_capture = 1,
+		.no_pcm = 1,
+		SND_SOC_DAILINK_REG(dmic16k_pin, dmic_codec, platform),
+	},
+	{
+		.name = "iDisp1",
+		.id = 3,
+		.init = hdmi_init,
+		.dpcm_playback = 1,
+		.no_pcm = 1,
+		SND_SOC_DAILINK_REG(idisp1_pin, idisp1_codec, platform),
+	},
+	{
+		.name = "iDisp2",
+		.id = 4,
+		.init = hdmi_init,
+		.dpcm_playback = 1,
+		.no_pcm = 1,
+		SND_SOC_DAILINK_REG(idisp2_pin, idisp2_codec, platform),
+	},
+	{
+		.name = "iDisp3",
+		.id = 5,
+		.init = hdmi_init,
+		.dpcm_playback = 1,
+		.no_pcm = 1,
+		SND_SOC_DAILINK_REG(idisp3_pin, idisp3_codec, platform),
+	},
+	{
+		/*
+		 * SSP1 - Codec : added to end of list ensuring
+		 * reuse of common topologies for other end points
+		 * and changing only SSP1's codec
+		 */
+		.name = "SSP1-Codec",
+		.id = 6,
+		.dpcm_playback = 1,
+		.dpcm_capture = 1, /* Capture stream provides Feedback */
+		.no_pcm = 1,
+		.ops = &cml_rt1011_ops,
+		SND_SOC_DAILINK_REG(ssp1_pin, ssp1_codec, platform),
+	},
+};
+
+static struct snd_soc_codec_conf rt1011_conf[] = {
+	{
+		.dev_name = "i2c-10EC1011:00",
+		.name_prefix = "WL",
+	},
+	{
+		.dev_name = "i2c-10EC1011:01",
+		.name_prefix = "WR",
+	},
+	{
+		.dev_name = "i2c-10EC1011:02",
+		.name_prefix = "TL",
+	},
+	{
+		.dev_name = "i2c-10EC1011:03",
+		.name_prefix = "TR",
+	},
+};
+
+/* Cometlake audio machine driver for RT1011 and RT5682 */
+static struct snd_soc_card snd_soc_card_cml = {
+	.name = "cml_rt1011_rt5682",
+	.dai_link = cml_rt1011_rt5682_dailink,
+	.num_links = ARRAY_SIZE(cml_rt1011_rt5682_dailink),
+	.codec_conf = rt1011_conf,
+	.num_configs = ARRAY_SIZE(rt1011_conf),
+	.dapm_widgets = cml_rt1011_rt5682_widgets,
+	.num_dapm_widgets = ARRAY_SIZE(cml_rt1011_rt5682_widgets),
+	.dapm_routes = cml_rt1011_rt5682_map,
+	.num_dapm_routes = ARRAY_SIZE(cml_rt1011_rt5682_map),
+	.controls = cml_controls,
+	.num_controls = ARRAY_SIZE(cml_controls),
+	.fully_routed = true,
+	.late_probe = sof_card_late_probe,
+};
+
+static int snd_cml_rt1011_probe(struct platform_device *pdev)
+{
+	struct card_private *ctx;
+	struct snd_soc_acpi_mach *mach;
+	const char *platform_name;
+	int ret;
+
+	ctx = devm_kzalloc(&pdev->dev, sizeof(*ctx), GFP_ATOMIC);
+	if (!ctx)
+		return -ENOMEM;
+
+	INIT_LIST_HEAD(&ctx->hdmi_pcm_list);
+	mach = (&pdev->dev)->platform_data;
+	snd_soc_card_cml.dev = &pdev->dev;
+	platform_name = mach->mach_params.platform;
+
+	/* set platform name for each dailink */
+	ret = snd_soc_fixup_dai_links_platform_name(&snd_soc_card_cml,
+						    platform_name);
+	if (ret)
+		return ret;
+
+	ctx->common_hdmi_codec_drv = mach->mach_params.common_hdmi_codec_drv;
+
+	snd_soc_card_set_drvdata(&snd_soc_card_cml, ctx);
+
+	return devm_snd_soc_register_card(&pdev->dev, &snd_soc_card_cml);
+}
+
+static struct platform_driver snd_cml_rt1011_rt5682_driver = {
+	.probe = snd_cml_rt1011_probe,
+	.driver = {
+		.name = "cml_rt1011_rt5682",
+		.pm = &snd_soc_pm_ops,
+	},
+};
+module_platform_driver(snd_cml_rt1011_rt5682_driver);
+
+/* Module information */
+MODULE_DESCRIPTION("Cometlake Audio Machine driver - RT1011 and RT5682 in I2S mode");
+MODULE_AUTHOR("Naveen Manohar <naveen.m@intel.com>");
+MODULE_AUTHOR("Sathya Prakash M R <sathya.prakash.m.r@intel.com>");
+MODULE_AUTHOR("Shuming Fan <shumingf@realtek.com>");
+MODULE_LICENSE("GPL v2");
+MODULE_ALIAS("platform:cml_rt1011_rt5682");
diff --git a/sound/soc/intel/boards/glk_rt5682_max98357a.c b/sound/soc/intel/boards/glk_rt5682_max98357a.c
index bd2d371f2acd..b36264d1d1cd 100644
--- a/sound/soc/intel/boards/glk_rt5682_max98357a.c
+++ b/sound/soc/intel/boards/glk_rt5682_max98357a.c
@@ -19,6 +19,7 @@
 #include <sound/soc-acpi.h>
 #include "../../codecs/rt5682.h"
 #include "../../codecs/hdac_hdmi.h"
+#include "hda_dsp_common.h"
 
 /* The platform clock outputs 19.2Mhz clock to codec as I2S MCLK */
 #define GLK_PLAT_CLK_FREQ 19200000
@@ -41,6 +42,7 @@ struct glk_hdmi_pcm {
 struct glk_card_private {
 	struct snd_soc_jack geminilake_headset;
 	struct list_head hdmi_pcm_list;
+	bool common_hdmi_codec_drv;
 };
 
 enum {
@@ -545,6 +547,13 @@ static int glk_card_late_probe(struct snd_soc_card *card)
 	int err = 0;
 	int i = 0;
 
+	pcm = list_first_entry(&ctx->hdmi_pcm_list, struct glk_hdmi_pcm,
+			       head);
+	component = pcm->codec_dai->component;
+
+	if (ctx->common_hdmi_codec_drv)
+		return hda_dsp_hdmi_build_controls(card, component);
+
 	list_for_each_entry(pcm, &ctx->hdmi_pcm_list, head) {
 		component = pcm->codec_dai->component;
 		snprintf(jack_name, sizeof(jack_name),
@@ -612,6 +621,8 @@ static int geminilake_audio_probe(struct platform_device *pdev)
 	if (ret)
 		return ret;
 
+	ctx->common_hdmi_codec_drv = mach->mach_params.common_hdmi_codec_drv;
+
 	return devm_snd_soc_register_card(&pdev->dev, card);
 }
 
diff --git a/sound/soc/intel/boards/hda_dsp_common.c b/sound/soc/intel/boards/hda_dsp_common.c
new file mode 100644
index 000000000000..ed36b68d6705
--- /dev/null
+++ b/sound/soc/intel/boards/hda_dsp_common.c
@@ -0,0 +1,85 @@
+// SPDX-License-Identifier: GPL-2.0
+//
+// Copyright(c) 2019 Intel Corporation. All rights reserved.
+
+#include <sound/pcm.h>
+#include <sound/soc.h>
+#include <sound/hda_codec.h>
+#include <sound/hda_i915.h>
+#include "../../codecs/hdac_hda.h"
+
+#include "hda_dsp_common.h"
+
+/*
+ * Search card topology and return PCM device number
+ * matching Nth HDMI device (zero-based index).
+ */
+struct snd_pcm *hda_dsp_hdmi_pcm_handle(struct snd_soc_card *card,
+					int hdmi_idx)
+{
+	struct snd_soc_pcm_runtime *rtd;
+	struct snd_pcm *spcm;
+	int i = 0;
+
+	for_each_card_rtds(card, rtd) {
+		spcm = rtd->pcm ?
+			rtd->pcm->streams[SNDRV_PCM_STREAM_PLAYBACK].pcm : NULL;
+		if (spcm && strstr(spcm->id, "HDMI")) {
+			if (i == hdmi_idx)
+				return rtd->pcm;
+			++i;
+		}
+	}
+
+	return NULL;
+}
+
+#if IS_ENABLED(CONFIG_SND_SOC_SOF_HDA_AUDIO_CODEC)
+/*
+ * Search card topology and register HDMI PCM related controls
+ * to codec driver.
+ */
+int hda_dsp_hdmi_build_controls(struct snd_soc_card *card,
+				struct snd_soc_component *comp)
+{
+	struct hdac_hda_priv *hda_pvt;
+	struct hda_codec *hcodec;
+	struct snd_pcm *spcm;
+	struct hda_pcm *hpcm;
+	int err = 0, i = 0;
+
+	if (!comp)
+		return -EINVAL;
+
+	hda_pvt = snd_soc_component_get_drvdata(comp);
+	hcodec = &hda_pvt->codec;
+
+	list_for_each_entry(hpcm, &hcodec->pcm_list_head, list) {
+		spcm = hda_dsp_hdmi_pcm_handle(card, i);
+		if (spcm) {
+			hpcm->pcm = spcm;
+			hpcm->device = spcm->device;
+			dev_dbg(card->dev,
+				"%s: mapping HDMI converter %d to PCM %d (%p)\n",
+				__func__, i, hpcm->device, spcm);
+		} else {
+			hpcm->pcm = 0;
+			hpcm->device = SNDRV_PCM_INVALID_DEVICE;
+			dev_warn(card->dev,
+				 "%s: no PCM in topology for HDMI converter %d\n\n",
+				 __func__, i);
+		}
+		i++;
+	}
+	snd_hdac_display_power(hcodec->core.bus,
+			       HDA_CODEC_IDX_CONTROLLER, true);
+	err = snd_hda_codec_build_controls(hcodec);
+	if (err < 0)
+		dev_err(card->dev, "unable to create controls %d\n", err);
+	snd_hdac_display_power(hcodec->core.bus,
+			       HDA_CODEC_IDX_CONTROLLER, false);
+
+	return err;
+}
+
+#endif
diff --git a/sound/soc/intel/boards/hda_dsp_common.h b/sound/soc/intel/boards/hda_dsp_common.h
new file mode 100644
index 000000000000..431f7f09dccb
--- /dev/null
+++ b/sound/soc/intel/boards/hda_dsp_common.h
@@ -0,0 +1,32 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright(c) 2019 Intel Corporation.
+ */
+
+/*
+ * This file defines helper functions used by multiple
+ * Intel HDA based machine drivers.
+ */
+
+#ifndef __HDA_DSP_COMMON_H
+#define __HDA_DSP_COMMON_H
+
+#include <sound/hda_codec.h>
+#include <sound/hda_i915.h>
+#include "../../codecs/hdac_hda.h"
+
+struct snd_pcm *hda_dsp_hdmi_pcm_handle(struct snd_soc_card *card,
+					int hdmi_idx);
+
+#if IS_ENABLED(CONFIG_SND_SOC_SOF_HDA_AUDIO_CODEC)
+int hda_dsp_hdmi_build_controls(struct snd_soc_card *card,
+				struct snd_soc_component *comp);
+#else
+static inline int hda_dsp_hdmi_build_controls(struct snd_soc_card *card,
+					      struct snd_soc_component *comp)
+{
+	return -EINVAL;
+}
+#endif
+
+#endif /* __HDA_DSP_COMMON_H */
diff --git a/sound/soc/intel/boards/kbl_rt5663_rt5514_max98927.c b/sound/soc/intel/boards/kbl_rt5663_rt5514_max98927.c
index 74dda8784f1a..3e5f6bead229 100644
--- a/sound/soc/intel/boards/kbl_rt5663_rt5514_max98927.c
+++ b/sound/soc/intel/boards/kbl_rt5663_rt5514_max98927.c
@@ -22,6 +22,9 @@
 #include "../../codecs/rt5514.h"
 #include "../../codecs/rt5663.h"
 #include "../../codecs/hdac_hdmi.h"
+#include <linux/clk.h>
+#include <linux/clk-provider.h>
+#include <linux/clkdev.h>
 
 #define KBL_REALTEK_CODEC_DAI "rt5663-aif"
 #define KBL_REALTEK_DMIC_CODEC_DAI "rt5514-aif1"
@@ -50,6 +53,8 @@ struct kbl_codec_private {
 	struct snd_soc_jack kabylake_headset;
 	struct list_head hdmi_pcm_list;
 	struct snd_soc_jack kabylake_hdmi[2];
+	struct clk *mclk;
+	struct clk *sclk;
 };
 
 enum {
@@ -71,6 +76,61 @@ static const struct snd_kcontrol_new kabylake_controls[] = {
 	SOC_DAPM_PIN_SWITCH("DMIC"),
 };
 
+static int platform_clock_control(struct snd_soc_dapm_widget *w,
+			struct snd_kcontrol *k, int  event)
+{
+	struct snd_soc_dapm_context *dapm = w->dapm;
+	struct snd_soc_card *card = dapm->card;
+	struct kbl_codec_private *priv = snd_soc_card_get_drvdata(card);
+	int ret = 0;
+
+	/*
+	 * MCLK/SCLK need to be ON early for a successful synchronization of
+	 * codec internal clock. And the clocks are turned off during
+	 * POST_PMD after the stream is stopped.
+	 */
+	switch (event) {
+	case SND_SOC_DAPM_PRE_PMU:
+		/* Enable MCLK */
+		ret = clk_set_rate(priv->mclk, 24000000);
+		if (ret < 0) {
+			dev_err(card->dev, "Can't set rate for mclk, err: %d\n",
+				ret);
+			return ret;
+		}
+
+		ret = clk_prepare_enable(priv->mclk);
+		if (ret < 0) {
+			dev_err(card->dev, "Can't enable mclk, err: %d\n", ret);
+			return ret;
+		}
+
+		/* Enable SCLK */
+		ret = clk_set_rate(priv->sclk, 3072000);
+		if (ret < 0) {
+			dev_err(card->dev, "Can't set rate for sclk, err: %d\n",
+				ret);
+			clk_disable_unprepare(priv->mclk);
+			return ret;
+		}
+
+		ret = clk_prepare_enable(priv->sclk);
+		if (ret < 0) {
+			dev_err(card->dev, "Can't enable sclk, err: %d\n", ret);
+			clk_disable_unprepare(priv->mclk);
+		}
+		break;
+	case SND_SOC_DAPM_POST_PMD:
+		clk_disable_unprepare(priv->mclk);
+		clk_disable_unprepare(priv->sclk);
+		break;
+	default:
+		return 0;
+	}
+
+	return 0;
+}
+
 static const struct snd_soc_dapm_widget kabylake_widgets[] = {
 	SND_SOC_DAPM_HP("Headphone Jack", NULL),
 	SND_SOC_DAPM_MIC("Headset Mic", NULL),
@@ -79,11 +139,15 @@ static const struct snd_soc_dapm_widget kabylake_widgets[] = {
 	SND_SOC_DAPM_MIC("DMIC", NULL),
 	SND_SOC_DAPM_SPK("HDMI1", NULL),
 	SND_SOC_DAPM_SPK("HDMI2", NULL),
+	SND_SOC_DAPM_SUPPLY("Platform Clock", SND_SOC_NOPM, 0, 0,
+			platform_clock_control, SND_SOC_DAPM_PRE_PMU |
+			SND_SOC_DAPM_POST_PMD),
 
 };
 
 static const struct snd_soc_dapm_route kabylake_map[] = {
 	/* Headphones */
+	{ "Headphone Jack", NULL, "Platform Clock" },
 	{ "Headphone Jack", NULL, "HPOL" },
 	{ "Headphone Jack", NULL, "HPOR" },
 
@@ -92,6 +156,7 @@ static const struct snd_soc_dapm_route kabylake_map[] = {
 	{ "Right Spk", NULL, "Right BE_OUT" },
 
 	/* other jacks */
+	{ "Headset Mic", NULL, "Platform Clock" },
 	{ "IN1P", NULL, "Headset Mic" },
 	{ "IN1N", NULL, "Headset Mic" },
 
@@ -400,6 +465,9 @@ static int kabylake_dmic_startup(struct snd_pcm_substream *substream)
 	snd_pcm_hw_constraint_list(runtime, 0, SNDRV_PCM_HW_PARAM_CHANNELS,
 			dmic_constraints);
 
+	runtime->hw.formats = SNDRV_PCM_FMTBIT_S16_LE;
+	snd_pcm_hw_constraint_msbits(runtime, 0, 16, 16);
+
 	return snd_pcm_hw_constraint_list(substream->runtime, 0,
 			SNDRV_PCM_HW_PARAM_RATE, &constraints_rates);
 }
@@ -588,6 +656,55 @@ static struct snd_soc_dai_link kabylake_dais[] = {
 	},
 };
 
+static int kabylake_set_bias_level(struct snd_soc_card *card,
+	struct snd_soc_dapm_context *dapm, enum snd_soc_bias_level level)
+{
+	struct snd_soc_component *component = dapm->component;
+	struct kbl_codec_private *priv = snd_soc_card_get_drvdata(card);
+	int ret = 0;
+
+	if (!component || strcmp(component->name, RT5514_DEV_NAME))
+		return 0;
+
+	if (IS_ERR(priv->mclk))
+		return 0;
+
+	/*
+	 * It's required to control mclk directly in the set_bias_level
+	 * function for rt5514 codec or the recording function could
+	 * break.
+	 */
+	switch (level) {
+	case SND_SOC_BIAS_PREPARE:
+		if (dapm->bias_level == SND_SOC_BIAS_ON) {
+			dev_dbg(card->dev, "Disable mclk");
+			clk_disable_unprepare(priv->mclk);
+		} else {
+			dev_dbg(card->dev, "Enable mclk");
+			ret = clk_set_rate(priv->mclk, 24000000);
+			if (ret) {
+				dev_err(card->dev, "Can't set rate for mclk, err: %d\n",
+					ret);
+				return ret;
+			}
+
+			ret = clk_prepare_enable(priv->mclk);
+			if (ret) {
+				dev_err(card->dev, "Can't enable mclk, err: %d\n",
+					ret);
+
+				/* mclk is already enabled in FW */
+				ret = 0;
+			}
+		}
+		break;
+	default:
+		break;
+	}
+
+	return ret;
+}
+
 static int kabylake_card_late_probe(struct snd_soc_card *card)
 {
 	struct kbl_codec_private *ctx = snd_soc_card_get_drvdata(card);
@@ -623,10 +740,11 @@ static int kabylake_card_late_probe(struct snd_soc_card *card)
  * kabylake audio machine driver for  MAX98927 + RT5514 + RT5663
  */
 static struct snd_soc_card kabylake_audio_card = {
-	.name = "kbl_r5514_5663_max",
+	.name = "kbl-r5514-5663-max",
 	.owner = THIS_MODULE,
 	.dai_link = kabylake_dais,
 	.num_links = ARRAY_SIZE(kabylake_dais),
+	.set_bias_level = kabylake_set_bias_level,
 	.controls = kabylake_controls,
 	.num_controls = ARRAY_SIZE(kabylake_controls),
 	.dapm_widgets = kabylake_widgets,
@@ -643,6 +761,7 @@ static int kabylake_audio_probe(struct platform_device *pdev)
 {
 	struct kbl_codec_private *ctx;
 	struct snd_soc_acpi_mach *mach;
+	int ret = 0;
 
 	ctx = devm_kzalloc(&pdev->dev, sizeof(*ctx), GFP_KERNEL);
 	if (!ctx)
@@ -658,6 +777,34 @@ static int kabylake_audio_probe(struct platform_device *pdev)
 		dmic_constraints = mach->mach_params.dmic_num == 2 ?
 			&constraints_dmic_2ch : &constraints_dmic_channels;
 
+	ctx->mclk = devm_clk_get(&pdev->dev, "ssp1_mclk");
+	if (IS_ERR(ctx->mclk)) {
+		ret = PTR_ERR(ctx->mclk);
+		if (ret == -ENOENT) {
+			dev_info(&pdev->dev,
+				"Failed to get ssp1_mclk, defer probe\n");
+			return -EPROBE_DEFER;
+		}
+
+		dev_err(&pdev->dev, "Failed to get ssp1_mclk with err:%d\n",
+								ret);
+		return ret;
+	}
+
+	ctx->sclk = devm_clk_get(&pdev->dev, "ssp1_sclk");
+	if (IS_ERR(ctx->sclk)) {
+		ret = PTR_ERR(ctx->sclk);
+		if (ret == -ENOENT) {
+			dev_info(&pdev->dev,
+				"Failed to get ssp1_sclk, defer probe\n");
+			return -EPROBE_DEFER;
+		}
+
+		dev_err(&pdev->dev, "Failed to get ssp1_sclk with err:%d\n",
+								ret);
+		return ret;
+	}
+
 	return devm_snd_soc_register_card(&pdev->dev, &kabylake_audio_card);
 }
 
diff --git a/sound/soc/intel/boards/skl_hda_dsp_common.c b/sound/soc/intel/boards/skl_hda_dsp_common.c
index 58409b6e476e..eb419e1ec42b 100644
--- a/sound/soc/intel/boards/skl_hda_dsp_common.c
+++ b/sound/soc/intel/boards/skl_hda_dsp_common.c
@@ -14,6 +14,9 @@
 #include "../../codecs/hdac_hdmi.h"
 #include "skl_hda_dsp_common.h"
 
+#include <sound/hda_codec.h>
+#include "../../codecs/hdac_hda.h"
+
 #define NAME_SIZE	32
 
 int skl_hda_hdmi_add_pcm(struct snd_soc_card *card, int device)
@@ -136,6 +139,9 @@ int skl_hda_hdmi_jack_init(struct snd_soc_card *card)
 	char jack_name[NAME_SIZE];
 	int err;
 
+	if (ctx->common_hdmi_codec_drv)
+		return skl_hda_hdmi_build_controls(card);
+
 	list_for_each_entry(pcm, &ctx->hdmi_pcm_list, head) {
 		component = pcm->codec_dai->component;
 		snprintf(jack_name, sizeof(jack_name),
diff --git a/sound/soc/intel/boards/skl_hda_dsp_common.h b/sound/soc/intel/boards/skl_hda_dsp_common.h
index daa582e513b2..d6150670ca05 100644
--- a/sound/soc/intel/boards/skl_hda_dsp_common.h
+++ b/sound/soc/intel/boards/skl_hda_dsp_common.h
@@ -8,12 +8,15 @@
  * platforms with HDA Codecs.
  */
 
-#ifndef __SOUND_SOC_HDA_DSP_COMMON_H
-#define __SOUND_SOC_HDA_DSP_COMMON_H
+#ifndef __SKL_HDA_DSP_COMMON_H
+#define __SKL_HDA_DSP_COMMON_H
 #include <linux/module.h>
 #include <linux/platform_device.h>
 #include <sound/core.h>
 #include <sound/jack.h>
+#include <sound/hda_codec.h>
+#include "../../codecs/hdac_hda.h"
+#include "hda_dsp_common.h"
 
 #define HDA_DSP_MAX_BE_DAI_LINKS 7
 
@@ -29,10 +32,30 @@ struct skl_hda_private {
 	int pcm_count;
 	int dai_index;
 	const char *platform_name;
+	bool common_hdmi_codec_drv;
 };
 
 extern struct snd_soc_dai_link skl_hda_be_dai_links[HDA_DSP_MAX_BE_DAI_LINKS];
 int skl_hda_hdmi_jack_init(struct snd_soc_card *card);
 int skl_hda_hdmi_add_pcm(struct snd_soc_card *card, int device);
 
+/*
+ * Search card topology and register HDMI PCM related controls
+ * to codec driver.
+ */
+static inline int skl_hda_hdmi_build_controls(struct snd_soc_card *card)
+{
+	struct skl_hda_private *ctx = snd_soc_card_get_drvdata(card);
+	struct snd_soc_component *component;
+	struct skl_hda_hdmi_pcm *pcm;
+
+	pcm = list_first_entry(&ctx->hdmi_pcm_list, struct skl_hda_hdmi_pcm,
+			       head);
+	component = pcm->codec_dai->component;
+	if (!component)
+		return -EINVAL;
+
+	return hda_dsp_hdmi_build_controls(card, component);
+}
+
 #endif /* __SOUND_SOC_HDA_DSP_COMMON_H */
diff --git a/sound/soc/intel/boards/skl_hda_dsp_generic.c b/sound/soc/intel/boards/skl_hda_dsp_generic.c
index 1778acdc367c..4e45901e3a2f 100644
--- a/sound/soc/intel/boards/skl_hda_dsp_generic.c
+++ b/sound/soc/intel/boards/skl_hda_dsp_generic.c
@@ -90,7 +90,7 @@ skl_hda_add_dai_link(struct snd_soc_card *card, struct snd_soc_dai_link *link)
 }
 
 static struct snd_soc_card hda_soc_card = {
-	.name = "skl_hda_card",
+	.name = "hda-dsp",
 	.owner = THIS_MODULE,
 	.dai_link = skl_hda_be_dai_links,
 	.dapm_widgets = skl_hda_widgets,
@@ -178,6 +178,7 @@ static int skl_hda_audio_probe(struct platform_device *pdev)
 	ctx->pcm_count = hda_soc_card.num_links;
 	ctx->dai_index = 1; /* hdmi codec dai name starts from index 1 */
 	ctx->platform_name = mach->mach_params.platform;
+	ctx->common_hdmi_codec_drv = mach->mach_params.common_hdmi_codec_drv;
 
 	hda_soc_card.dev = &pdev->dev;
 	snd_soc_card_set_drvdata(&hda_soc_card, ctx);
diff --git a/sound/soc/intel/boards/sof_rt5682.c b/sound/soc/intel/boards/sof_rt5682.c
index 4f6e58c3954a..751b8ea6ae1f 100644
--- a/sound/soc/intel/boards/sof_rt5682.c
+++ b/sound/soc/intel/boards/sof_rt5682.c
@@ -21,6 +21,7 @@
 #include "../../codecs/rt5682.h"
 #include "../../codecs/hdac_hdmi.h"
 #include "../common/soc-intel-quirks.h"
+#include "hda_dsp_common.h"
 
 #define NAME_SIZE 32
 
@@ -53,6 +54,7 @@ struct sof_card_private {
 	struct clk *mclk;
 	struct snd_soc_jack sof_headset;
 	struct list_head hdmi_pcm_list;
+	bool common_hdmi_codec_drv;
 };
 
 static int sof_rt5682_quirk_cb(const struct dmi_system_id *id)
@@ -274,6 +276,13 @@ static int sof_card_late_probe(struct snd_soc_card *card)
 	if (is_legacy_cpu)
 		return 0;
 
+	pcm = list_first_entry(&ctx->hdmi_pcm_list, struct sof_hdmi_pcm,
+			       head);
+	component = pcm->codec_dai->component;
+
+	if (ctx->common_hdmi_codec_drv)
+		return hda_dsp_hdmi_build_controls(card, component);
+
 	list_for_each_entry(pcm, &ctx->hdmi_pcm_list, head) {
 		component = pcm->codec_dai->component;
 		snprintf(jack_name, sizeof(jack_name),
@@ -370,7 +379,7 @@ static int dmic_init(struct snd_soc_pcm_runtime *rtd)
 
 /* sof audio machine driver for rt5682 codec */
 static struct snd_soc_card sof_audio_card_rt5682 = {
-	.name = "sof_rt5682",
+	.name = "rt5682", /* the sof- prefix is added by the core */
 	.owner = THIS_MODULE,
 	.controls = sof_controls,
 	.num_controls = ARRAY_SIZE(sof_controls),
@@ -651,6 +660,8 @@ static int sof_audio_probe(struct platform_device *pdev)
 	if (ret)
 		return ret;
 
+	ctx->common_hdmi_codec_drv = mach->mach_params.common_hdmi_codec_drv;
+
 	snd_soc_card_set_drvdata(&sof_audio_card_rt5682, ctx);
 
 	return devm_snd_soc_register_card(&pdev->dev,
diff --git a/sound/soc/intel/common/Makefile b/sound/soc/intel/common/Makefile
index 18d9630ae9a2..bd352878f89a 100644
--- a/sound/soc/intel/common/Makefile
+++ b/sound/soc/intel/common/Makefile
@@ -7,8 +7,10 @@ snd-soc-acpi-intel-match-objs := soc-acpi-intel-byt-match.o soc-acpi-intel-cht-m
 	soc-acpi-intel-hsw-bdw-match.o \
 	soc-acpi-intel-skl-match.o soc-acpi-intel-kbl-match.o \
 	soc-acpi-intel-bxt-match.o soc-acpi-intel-glk-match.o \
-	soc-acpi-intel-cnl-match.o soc-acpi-intel-icl-match.o \
+	soc-acpi-intel-cnl-match.o soc-acpi-intel-cfl-match.o \
+	soc-acpi-intel-cml-match.o soc-acpi-intel-icl-match.o \
 	soc-acpi-intel-tgl-match.o soc-acpi-intel-ehl-match.o \
+	soc-acpi-intel-jsl-match.o \
 	soc-acpi-intel-hda-match.o
 
 obj-$(CONFIG_SND_SOC_INTEL_SST) += snd-soc-sst-dsp.o snd-soc-sst-ipc.o
diff --git a/sound/soc/intel/common/soc-acpi-intel-cfl-match.c b/sound/soc/intel/common/soc-acpi-intel-cfl-match.c
new file mode 100644
index 000000000000..d6fd2026d0b8
--- /dev/null
+++ b/sound/soc/intel/common/soc-acpi-intel-cfl-match.c
@@ -0,0 +1,18 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * soc-apci-intel-cfl-match.c - tables and support for CFL ACPI enumeration.
+ *
+ * Copyright (c) 2019, Intel Corporation.
+ *
+ */
+
+#include <sound/soc-acpi.h>
+#include <sound/soc-acpi-intel-match.h>
+
+struct snd_soc_acpi_mach snd_soc_acpi_intel_cfl_machines[] = {
+	{},
+};
+EXPORT_SYMBOL_GPL(snd_soc_acpi_intel_cfl_machines);
+
+MODULE_LICENSE("GPL v2");
+MODULE_DESCRIPTION("Intel Common ACPI Match module");
diff --git a/sound/soc/intel/common/soc-acpi-intel-cml-match.c b/sound/soc/intel/common/soc-acpi-intel-cml-match.c
new file mode 100644
index 000000000000..5d08ae066738
--- /dev/null
+++ b/sound/soc/intel/common/soc-acpi-intel-cml-match.c
@@ -0,0 +1,56 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * soc-acpi-intel-cml-match.c - tables and support for CML ACPI enumeration.
+ *
+ * Copyright (c) 2019, Intel Corporation.
+ *
+ */
+
+#include <sound/soc-acpi.h>
+#include <sound/soc-acpi-intel-match.h>
+
+static struct snd_soc_acpi_codecs cml_codecs = {
+	.num_codecs = 1,
+	.codecs = {"10EC5682"}
+};
+
+static struct snd_soc_acpi_codecs cml_spk_codecs = {
+	.num_codecs = 1,
+	.codecs = {"MX98357A"}
+};
+
+struct snd_soc_acpi_mach snd_soc_acpi_intel_cml_machines[] = {
+	{
+		.id = "DLGS7219",
+		.drv_name = "cml_da7219_max98357a",
+		.quirk_data = &cml_spk_codecs,
+		.sof_fw_filename = "sof-cml.ri",
+		.sof_tplg_filename = "sof-cml-da7219-max98357a.tplg",
+	},
+	{
+		.id = "MX98357A",
+		.drv_name = "sof_rt5682",
+		.quirk_data = &cml_codecs,
+		.sof_fw_filename = "sof-cml.ri",
+		.sof_tplg_filename = "sof-cml-rt5682-max98357a.tplg",
+	},
+	{
+		.id = "10EC1011",
+		.drv_name = "cml_rt1011_rt5682",
+		.quirk_data = &cml_codecs,
+		.sof_fw_filename = "sof-cml.ri",
+		.sof_tplg_filename = "sof-cml-rt1011-rt5682.tplg",
+	},
+	{
+		.id = "10EC5682",
+		.drv_name = "sof_rt5682",
+		.sof_fw_filename = "sof-cml.ri",
+		.sof_tplg_filename = "sof-cml-rt5682.tplg",
+	},
+
+	{},
+};
+EXPORT_SYMBOL_GPL(snd_soc_acpi_intel_cml_machines);
+
+MODULE_LICENSE("GPL v2");
+MODULE_DESCRIPTION("Intel Common ACPI Match module");
diff --git a/sound/soc/intel/common/soc-acpi-intel-cnl-match.c b/sound/soc/intel/common/soc-acpi-intel-cnl-match.c
index 985aa366c9e8..27588841c8b0 100644
--- a/sound/soc/intel/common/soc-acpi-intel-cnl-match.c
+++ b/sound/soc/intel/common/soc-acpi-intel-cnl-match.c
@@ -14,16 +14,6 @@ static struct skl_machine_pdata cnl_pdata = {
 	.use_tplg_pcm = true,
 };
 
-static struct snd_soc_acpi_codecs cml_codecs = {
-	.num_codecs = 1,
-	.codecs = {"10EC5682"}
-};
-
-static struct snd_soc_acpi_codecs cml_spk_codecs = {
-	.num_codecs = 1,
-	.codecs = {"MX98357A"}
-};
-
 struct snd_soc_acpi_mach snd_soc_acpi_intel_cnl_machines[] = {
 	{
 		.id = "INT34C2",
@@ -33,27 +23,6 @@ struct snd_soc_acpi_mach snd_soc_acpi_intel_cnl_machines[] = {
 		.sof_fw_filename = "sof-cnl.ri",
 		.sof_tplg_filename = "sof-cnl-rt274.tplg",
 	},
-	{
-		.id = "DLGS7219",
-		.drv_name = "cml_da7219_max98357a",
-		.quirk_data = &cml_spk_codecs,
-		.sof_fw_filename = "sof-cnl.ri",
-		.sof_tplg_filename = "sof-cml-da7219-max98357a.tplg",
-	},
-	{
-		.id = "MX98357A",
-		.drv_name = "sof_rt5682",
-		.quirk_data = &cml_codecs,
-		.sof_fw_filename = "sof-cnl.ri",
-		.sof_tplg_filename = "sof-cml-rt5682-max98357a.tplg",
-	},
-	{
-		.id = "10EC5682",
-		.drv_name = "sof_rt5682",
-		.sof_fw_filename = "sof-cnl.ri",
-		.sof_tplg_filename = "sof-cml-rt5682.tplg",
-	},
-
 	{},
 };
 EXPORT_SYMBOL_GPL(snd_soc_acpi_intel_cnl_machines);
diff --git a/sound/soc/intel/common/soc-acpi-intel-jsl-match.c b/sound/soc/intel/common/soc-acpi-intel-jsl-match.c
new file mode 100644
index 000000000000..1c68a04f0c6e
--- /dev/null
+++ b/sound/soc/intel/common/soc-acpi-intel-jsl-match.c
@@ -0,0 +1,18 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * soc-apci-intel-jsl-match.c - tables and support for JSL ACPI enumeration.
+ *
+ * Copyright (c) 2019, Intel Corporation.
+ *
+ */
+
+#include <sound/soc-acpi.h>
+#include <sound/soc-acpi-intel-match.h>
+
+struct snd_soc_acpi_mach snd_soc_acpi_intel_jsl_machines[] = {
+	{},
+};
+EXPORT_SYMBOL_GPL(snd_soc_acpi_intel_jsl_machines);
+
+MODULE_LICENSE("GPL v2");
+MODULE_DESCRIPTION("Intel Common ACPI Match module");
diff --git a/sound/soc/intel/haswell/sst-haswell-pcm.c b/sound/soc/intel/haswell/sst-haswell-pcm.c
index 7f4f6b755760..a3a5bba2fbd9 100644
--- a/sound/soc/intel/haswell/sst-haswell-pcm.c
+++ b/sound/soc/intel/haswell/sst-haswell-pcm.c
@@ -458,12 +458,12 @@ static int create_adsp_page_table(struct snd_pcm_substream *substream,
 }
 
 /* this may get called several times by oss emulation */
-static int hsw_pcm_hw_params(struct snd_pcm_substream *substream,
-			      struct snd_pcm_hw_params *params)
+static int hsw_pcm_hw_params(struct snd_soc_component *component,
+			     struct snd_pcm_substream *substream,
+			     struct snd_pcm_hw_params *params)
 {
 	struct snd_soc_pcm_runtime *rtd = substream->private_data;
 	struct snd_pcm_runtime *runtime = substream->runtime;
-	struct snd_soc_component *component = snd_soc_rtdcom_lookup(rtd, DRV_NAME);
 	struct hsw_priv_data *pdata = snd_soc_component_get_drvdata(component);
 	struct hsw_pcm_data *pcm_data;
 	struct sst_hsw *hsw = pdata->hsw;
@@ -656,16 +656,17 @@ static int hsw_pcm_hw_params(struct snd_pcm_substream *substream,
 	return 0;
 }
 
-static int hsw_pcm_hw_free(struct snd_pcm_substream *substream)
+static int hsw_pcm_hw_free(struct snd_soc_component *component,
+			   struct snd_pcm_substream *substream)
 {
 	snd_pcm_lib_free_pages(substream);
 	return 0;
 }
 
-static int hsw_pcm_trigger(struct snd_pcm_substream *substream, int cmd)
+static int hsw_pcm_trigger(struct snd_soc_component *component,
+			   struct snd_pcm_substream *substream, int cmd)
 {
 	struct snd_soc_pcm_runtime *rtd = substream->private_data;
-	struct snd_soc_component *component = snd_soc_rtdcom_lookup(rtd, DRV_NAME);
 	struct hsw_priv_data *pdata = snd_soc_component_get_drvdata(component);
 	struct hsw_pcm_data *pcm_data;
 	struct sst_hsw_stream *sst_stream;
@@ -770,11 +771,11 @@ static u32 hsw_notify_pointer(struct sst_hsw_stream *stream, void *data)
 	return pos;
 }
 
-static snd_pcm_uframes_t hsw_pcm_pointer(struct snd_pcm_substream *substream)
+static snd_pcm_uframes_t hsw_pcm_pointer(struct snd_soc_component *component,
+					 struct snd_pcm_substream *substream)
 {
 	struct snd_soc_pcm_runtime *rtd = substream->private_data;
 	struct snd_pcm_runtime *runtime = substream->runtime;
-	struct snd_soc_component *component = snd_soc_rtdcom_lookup(rtd, DRV_NAME);
 	struct hsw_priv_data *pdata = snd_soc_component_get_drvdata(component);
 	struct hsw_pcm_data *pcm_data;
 	struct sst_hsw *hsw = pdata->hsw;
@@ -795,10 +796,10 @@ static snd_pcm_uframes_t hsw_pcm_pointer(struct snd_pcm_substream *substream)
 	return offset;
 }
 
-static int hsw_pcm_open(struct snd_pcm_substream *substream)
+static int hsw_pcm_open(struct snd_soc_component *component,
+			struct snd_pcm_substream *substream)
 {
 	struct snd_soc_pcm_runtime *rtd = substream->private_data;
-	struct snd_soc_component *component = snd_soc_rtdcom_lookup(rtd, DRV_NAME);
 	struct hsw_priv_data *pdata = snd_soc_component_get_drvdata(component);
 	struct hsw_pcm_data *pcm_data;
 	struct sst_hsw *hsw = pdata->hsw;
@@ -828,10 +829,10 @@ static int hsw_pcm_open(struct snd_pcm_substream *substream)
 	return 0;
 }
 
-static int hsw_pcm_close(struct snd_pcm_substream *substream)
+static int hsw_pcm_close(struct snd_soc_component *component,
+			 struct snd_pcm_substream *substream)
 {
 	struct snd_soc_pcm_runtime *rtd = substream->private_data;
-	struct snd_soc_component *component = snd_soc_rtdcom_lookup(rtd, DRV_NAME);
 	struct hsw_priv_data *pdata = snd_soc_component_get_drvdata(component);
 	struct hsw_pcm_data *pcm_data;
 	struct sst_hsw *hsw = pdata->hsw;
@@ -862,17 +863,6 @@ out:
 	return ret;
 }
 
-static const struct snd_pcm_ops hsw_pcm_ops = {
-	.open		= hsw_pcm_open,
-	.close		= hsw_pcm_close,
-	.ioctl		= snd_pcm_lib_ioctl,
-	.hw_params	= hsw_pcm_hw_params,
-	.hw_free	= hsw_pcm_hw_free,
-	.trigger	= hsw_pcm_trigger,
-	.pointer	= hsw_pcm_pointer,
-	.page		= snd_pcm_sgbuf_ops_page,
-};
-
 static int hsw_pcm_create_modules(struct hsw_priv_data *pdata)
 {
 	struct sst_hsw *hsw = pdata->hsw;
@@ -930,10 +920,10 @@ static void hsw_pcm_free_modules(struct hsw_priv_data *pdata)
 	}
 }
 
-static int hsw_pcm_new(struct snd_soc_pcm_runtime *rtd)
+static int hsw_pcm_new(struct snd_soc_component *component,
+		       struct snd_soc_pcm_runtime *rtd)
 {
 	struct snd_pcm *pcm = rtd->pcm;
-	struct snd_soc_component *component = snd_soc_rtdcom_lookup(rtd, DRV_NAME);
 	struct sst_pdata *pdata = dev_get_platdata(component->dev);
 	struct hsw_priv_data *priv_data = dev_get_drvdata(component->dev);
 	struct device *dev = pdata->dma_dev;
@@ -1121,8 +1111,14 @@ static const struct snd_soc_component_driver hsw_dai_component = {
 	.name		= DRV_NAME,
 	.probe		= hsw_pcm_probe,
 	.remove		= hsw_pcm_remove,
-	.ops		= &hsw_pcm_ops,
-	.pcm_new	= hsw_pcm_new,
+	.open		= hsw_pcm_open,
+	.close		= hsw_pcm_close,
+	.hw_params	= hsw_pcm_hw_params,
+	.hw_free	= hsw_pcm_hw_free,
+	.trigger	= hsw_pcm_trigger,
+	.pointer	= hsw_pcm_pointer,
+	.ioctl		= snd_soc_pcm_lib_ioctl,
+	.pcm_construct	= hsw_pcm_new,
 	.controls	= hsw_volume_controls,
 	.num_controls	= ARRAY_SIZE(hsw_volume_controls),
 	.dapm_widgets	= widgets,
diff --git a/sound/soc/intel/skylake/skl-pcm.c b/sound/soc/intel/skylake/skl-pcm.c
index 7f287424af9b..8b9abb79a69e 100644
--- a/sound/soc/intel/skylake/skl-pcm.c
+++ b/sound/soc/intel/skylake/skl-pcm.c
@@ -1081,7 +1081,8 @@ int skl_dai_load(struct snd_soc_component *cmp, int index,
 	return 0;
 }
 
-static int skl_platform_open(struct snd_pcm_substream *substream)
+static int skl_platform_soc_open(struct snd_soc_component *component,
+				 struct snd_pcm_substream *substream)
 {
 	struct snd_soc_pcm_runtime *rtd = substream->private_data;
 	struct snd_soc_dai_link *dai_link = rtd->dai_link;
@@ -1167,8 +1168,9 @@ static int skl_coupled_trigger(struct snd_pcm_substream *substream,
 	return 0;
 }
 
-static int skl_platform_pcm_trigger(struct snd_pcm_substream *substream,
-					int cmd)
+static int skl_platform_soc_trigger(struct snd_soc_component *component,
+				    struct snd_pcm_substream *substream,
+				    int cmd)
 {
 	struct hdac_bus *bus = get_bus_ctx(substream);
 
@@ -1178,8 +1180,9 @@ static int skl_platform_pcm_trigger(struct snd_pcm_substream *substream,
 	return 0;
 }
 
-static snd_pcm_uframes_t skl_platform_pcm_pointer
-			(struct snd_pcm_substream *substream)
+static snd_pcm_uframes_t skl_platform_soc_pointer(
+	struct snd_soc_component *component,
+	struct snd_pcm_substream *substream)
 {
 	struct hdac_ext_stream *hstream = get_hdac_ext_stream(substream);
 	struct hdac_bus *bus = get_bus_ctx(substream);
@@ -1225,6 +1228,13 @@ static snd_pcm_uframes_t skl_platform_pcm_pointer
 	return bytes_to_frames(substream->runtime, pos);
 }
 
+static int skl_platform_soc_mmap(struct snd_soc_component *component,
+				 struct snd_pcm_substream *substream,
+				 struct vm_area_struct *area)
+{
+	return snd_pcm_lib_default_mmap(substream, area);
+}
+
 static u64 skl_adjust_codec_delay(struct snd_pcm_substream *substream,
 				u64 nsec)
 {
@@ -1245,7 +1255,9 @@ static u64 skl_adjust_codec_delay(struct snd_pcm_substream *substream,
 	return (nsec > codec_nsecs) ? nsec - codec_nsecs : 0;
 }
 
-static int skl_get_time_info(struct snd_pcm_substream *substream,
+static int skl_platform_soc_get_time_info(
+			struct snd_soc_component *component,
+			struct snd_pcm_substream *substream,
 			struct timespec *system_ts, struct timespec *audio_ts,
 			struct snd_pcm_audio_tstamp_config *audio_tstamp_config,
 			struct snd_pcm_audio_tstamp_report *audio_tstamp_report)
@@ -1277,24 +1289,16 @@ static int skl_get_time_info(struct snd_pcm_substream *substream,
 	return 0;
 }
 
-static const struct snd_pcm_ops skl_platform_ops = {
-	.open = skl_platform_open,
-	.ioctl = snd_pcm_lib_ioctl,
-	.trigger = skl_platform_pcm_trigger,
-	.pointer = skl_platform_pcm_pointer,
-	.get_time_info =  skl_get_time_info,
-	.mmap = snd_pcm_lib_default_mmap,
-	.page = snd_pcm_sgbuf_ops_page,
-};
-
-static void skl_pcm_free(struct snd_pcm *pcm)
+static void skl_platform_soc_free(struct snd_soc_component *component,
+				  struct snd_pcm *pcm)
 {
 	snd_pcm_lib_preallocate_free_for_all(pcm);
 }
 
 #define MAX_PREALLOC_SIZE	(32 * 1024 * 1024)
 
-static int skl_pcm_new(struct snd_soc_pcm_runtime *rtd)
+static int skl_platform_soc_new(struct snd_soc_component *component,
+				struct snd_soc_pcm_runtime *rtd)
 {
 	struct snd_soc_dai *dai = rtd->cpu_dai;
 	struct hdac_bus *bus = dev_get_drvdata(dai->dev);
@@ -1310,7 +1314,7 @@ static int skl_pcm_new(struct snd_soc_pcm_runtime *rtd)
 			size = MAX_PREALLOC_SIZE;
 		snd_pcm_lib_preallocate_pages_for_all(pcm,
 						SNDRV_DMA_TYPE_DEV_SG,
-						snd_dma_pci_data(skl->pci),
+						&skl->pci->dev,
 						size, MAX_PREALLOC_SIZE);
 	}
 
@@ -1458,7 +1462,7 @@ static int skl_platform_soc_probe(struct snd_soc_component *component)
 	return 0;
 }
 
-static void skl_pcm_remove(struct snd_soc_component *component)
+static void skl_platform_soc_remove(struct snd_soc_component *component)
 {
 	struct hdac_bus *bus = dev_get_drvdata(component->dev);
 	struct skl_dev *skl = bus_to_skl(bus);
@@ -1471,10 +1475,15 @@ static void skl_pcm_remove(struct snd_soc_component *component)
 static const struct snd_soc_component_driver skl_component  = {
 	.name		= "pcm",
 	.probe		= skl_platform_soc_probe,
-	.remove		= skl_pcm_remove,
-	.ops		= &skl_platform_ops,
-	.pcm_new	= skl_pcm_new,
-	.pcm_free	= skl_pcm_free,
+	.remove		= skl_platform_soc_remove,
+	.open		= skl_platform_soc_open,
+	.ioctl		= snd_soc_pcm_lib_ioctl,
+	.trigger	= skl_platform_soc_trigger,
+	.pointer	= skl_platform_soc_pointer,
+	.get_time_info	= skl_platform_soc_get_time_info,
+	.mmap		= skl_platform_soc_mmap,
+	.pcm_construct	= skl_platform_soc_new,
+	.pcm_destruct	= skl_platform_soc_free,
 	.module_get_upon_open = 1, /* increment refcount when a pcm is opened */
 };
 
diff --git a/sound/soc/intel/skylake/skl.c b/sound/soc/intel/skylake/skl.c
index 141dbbf975ac..58ba3e9469ba 100644
--- a/sound/soc/intel/skylake/skl.c
+++ b/sound/soc/intel/skylake/skl.c
@@ -27,6 +27,7 @@
 #include <sound/hda_i915.h>
 #include <sound/hda_codec.h>
 #include <sound/intel-nhlt.h>
+#include <sound/intel-dsp-config.h>
 #include "skl.h"
 #include "skl-sst-dsp.h"
 #include "skl-sst-ipc.h"
@@ -987,22 +988,10 @@ static int skl_probe(struct pci_dev *pci,
 
 	switch (skl_pci_binding) {
 	case SND_SKL_PCI_BIND_AUTO:
-		/*
-		 * detect DSP by checking class/subclass/prog-id information
-		 * class=04 subclass 03 prog-if 00: no DSP, use legacy driver
-		 * class=04 subclass 01 prog-if 00: DSP is present
-		 *   (and may be required e.g. for DMIC or SSP support)
-		 * class=04 subclass 03 prog-if 80: use DSP or legacy mode
-		 */
-		if (pci->class == 0x040300) {
-			dev_info(&pci->dev, "The DSP is not enabled on this platform, aborting probe\n");
+		err = snd_intel_dsp_driver_probe(pci);
+		if (err != SND_INTEL_DSP_DRIVER_ANY &&
+		    err != SND_INTEL_DSP_DRIVER_SST)
 			return -ENODEV;
-		}
-		if (pci->class != 0x040100 && pci->class != 0x040380) {
-			dev_err(&pci->dev, "Unknown PCI class/subclass/prog-if information (0x%06x) found, aborting probe\n", pci->class);
-			return -ENODEV;
-		}
-		dev_info(&pci->dev, "DSP detected with PCI class/subclass/prog-if info 0x%06x\n", pci->class);
 		break;
 	case SND_SKL_PCI_BIND_LEGACY:
 		dev_info(&pci->dev, "Module parameter forced binding with HDaudio legacy, aborting probe\n");
diff --git a/sound/soc/jz4740/jz4740-i2s.c b/sound/soc/jz4740/jz4740-i2s.c
index 13408de34055..38d48d101783 100644
--- a/sound/soc/jz4740/jz4740-i2s.c
+++ b/sound/soc/jz4740/jz4740-i2s.c
@@ -497,15 +497,13 @@ static int jz4740_i2s_dev_probe(struct platform_device *pdev)
 	struct jz4740_i2s *i2s;
 	struct resource *mem;
 	int ret;
-	const struct of_device_id *match;
 
 	i2s = devm_kzalloc(&pdev->dev, sizeof(*i2s), GFP_KERNEL);
 	if (!i2s)
 		return -ENOMEM;
 
-	match = of_match_device(jz4740_of_matches, &pdev->dev);
-	if (match)
-		i2s->version = (enum jz47xx_i2s_version)match->data;
+	i2s->version =
+		(enum jz47xx_i2s_version)of_device_get_match_data(&pdev->dev);
 
 	mem = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	i2s->base = devm_ioremap_resource(&pdev->dev, mem);
diff --git a/sound/soc/kirkwood/kirkwood-dma.c b/sound/soc/kirkwood/kirkwood-dma.c
index 6f69f314f2c2..e28fb3449f1d 100644
--- a/sound/soc/kirkwood/kirkwood-dma.c
+++ b/sound/soc/kirkwood/kirkwood-dma.c
@@ -98,7 +98,8 @@ kirkwood_dma_conf_mbus_windows(void __iomem *base, int win,
 	}
 }
 
-static int kirkwood_dma_open(struct snd_pcm_substream *substream)
+static int kirkwood_dma_open(struct snd_soc_component *component,
+			     struct snd_pcm_substream *substream)
 {
 	int err;
 	struct snd_pcm_runtime *runtime = substream->runtime;
@@ -132,7 +133,7 @@ static int kirkwood_dma_open(struct snd_pcm_substream *substream)
 		err = request_irq(priv->irq, kirkwood_dma_irq, IRQF_SHARED,
 				  "kirkwood-i2s", priv);
 		if (err)
-			return -EBUSY;
+			return err;
 
 		/*
 		 * Enable Error interrupts. We're only ack'ing them but
@@ -160,7 +161,8 @@ static int kirkwood_dma_open(struct snd_pcm_substream *substream)
 	return 0;
 }
 
-static int kirkwood_dma_close(struct snd_pcm_substream *substream)
+static int kirkwood_dma_close(struct snd_soc_component *component,
+			      struct snd_pcm_substream *substream)
 {
 	struct kirkwood_dma_data *priv = kirkwood_priv(substream);
 
@@ -180,8 +182,9 @@ static int kirkwood_dma_close(struct snd_pcm_substream *substream)
 	return 0;
 }
 
-static int kirkwood_dma_hw_params(struct snd_pcm_substream *substream,
-				struct snd_pcm_hw_params *params)
+static int kirkwood_dma_hw_params(struct snd_soc_component *component,
+				  struct snd_pcm_substream *substream,
+				  struct snd_pcm_hw_params *params)
 {
 	struct snd_pcm_runtime *runtime = substream->runtime;
 
@@ -191,13 +194,15 @@ static int kirkwood_dma_hw_params(struct snd_pcm_substream *substream,
 	return 0;
 }
 
-static int kirkwood_dma_hw_free(struct snd_pcm_substream *substream)
+static int kirkwood_dma_hw_free(struct snd_soc_component *component,
+				struct snd_pcm_substream *substream)
 {
 	snd_pcm_set_runtime_buffer(substream, NULL);
 	return 0;
 }
 
-static int kirkwood_dma_prepare(struct snd_pcm_substream *substream)
+static int kirkwood_dma_prepare(struct snd_soc_component *component,
+				struct snd_pcm_substream *substream)
 {
 	struct snd_pcm_runtime *runtime = substream->runtime;
 	struct kirkwood_dma_data *priv = kirkwood_priv(substream);
@@ -222,8 +227,9 @@ static int kirkwood_dma_prepare(struct snd_pcm_substream *substream)
 	return 0;
 }
 
-static snd_pcm_uframes_t kirkwood_dma_pointer(struct snd_pcm_substream
-						*substream)
+static snd_pcm_uframes_t kirkwood_dma_pointer(
+	struct snd_soc_component *component,
+	struct snd_pcm_substream *substream)
 {
 	struct kirkwood_dma_data *priv = kirkwood_priv(substream);
 	snd_pcm_uframes_t count;
@@ -238,16 +244,6 @@ static snd_pcm_uframes_t kirkwood_dma_pointer(struct snd_pcm_substream
 	return count;
 }
 
-static const struct snd_pcm_ops kirkwood_dma_ops = {
-	.open =		kirkwood_dma_open,
-	.close =        kirkwood_dma_close,
-	.ioctl =	snd_pcm_lib_ioctl,
-	.hw_params =	kirkwood_dma_hw_params,
-	.hw_free =      kirkwood_dma_hw_free,
-	.prepare =      kirkwood_dma_prepare,
-	.pointer =	kirkwood_dma_pointer,
-};
-
 static int kirkwood_dma_preallocate_dma_buffer(struct snd_pcm *pcm,
 		int stream)
 {
@@ -267,7 +263,8 @@ static int kirkwood_dma_preallocate_dma_buffer(struct snd_pcm *pcm,
 	return 0;
 }
 
-static int kirkwood_dma_new(struct snd_soc_pcm_runtime *rtd)
+static int kirkwood_dma_new(struct snd_soc_component *component,
+			    struct snd_soc_pcm_runtime *rtd)
 {
 	struct snd_card *card = rtd->card->snd_card;
 	struct snd_pcm *pcm = rtd->pcm;
@@ -294,7 +291,8 @@ static int kirkwood_dma_new(struct snd_soc_pcm_runtime *rtd)
 	return 0;
 }
 
-static void kirkwood_dma_free_dma_buffers(struct snd_pcm *pcm)
+static void kirkwood_dma_free_dma_buffers(struct snd_soc_component *component,
+					  struct snd_pcm *pcm)
 {
 	struct snd_pcm_substream *substream;
 	struct snd_dma_buffer *buf;
@@ -316,7 +314,13 @@ static void kirkwood_dma_free_dma_buffers(struct snd_pcm *pcm)
 
 const struct snd_soc_component_driver kirkwood_soc_component = {
 	.name		= DRV_NAME,
-	.ops		= &kirkwood_dma_ops,
-	.pcm_new	= kirkwood_dma_new,
-	.pcm_free	= kirkwood_dma_free_dma_buffers,
+	.open		= kirkwood_dma_open,
+	.close		= kirkwood_dma_close,
+	.ioctl		= snd_soc_pcm_lib_ioctl,
+	.hw_params	= kirkwood_dma_hw_params,
+	.hw_free	= kirkwood_dma_hw_free,
+	.prepare	= kirkwood_dma_prepare,
+	.pointer	= kirkwood_dma_pointer,
+	.pcm_construct	= kirkwood_dma_new,
+	.pcm_destruct	= kirkwood_dma_free_dma_buffers,
 };
diff --git a/sound/soc/mediatek/Kconfig b/sound/soc/mediatek/Kconfig
index 111e44b64b38..a656d2014127 100644
--- a/sound/soc/mediatek/Kconfig
+++ b/sound/soc/mediatek/Kconfig
@@ -125,6 +125,7 @@ config SND_SOC_MT8183_MT6358_TS3A227E_MAX98357A
 	select SND_SOC_MAX98357A
 	select SND_SOC_BT_SCO
 	select SND_SOC_TS3A227E
+	select SND_SOC_CROS_EC_CODEC if CROS_EC
 	help
 	  This adds ASoC driver for Mediatek MT8183 boards
 	  with the MT6358 TS3A227E MAX98357A audio codec.
diff --git a/sound/soc/mediatek/common/mtk-afe-platform-driver.c b/sound/soc/mediatek/common/mtk-afe-platform-driver.c
index 3ce527ce30ce..b6624d8d084b 100644
--- a/sound/soc/mediatek/common/mtk-afe-platform-driver.c
+++ b/sound/soc/mediatek/common/mtk-afe-platform-driver.c
@@ -77,11 +77,10 @@ int mtk_afe_add_sub_dai_control(struct snd_soc_component *component)
 }
 EXPORT_SYMBOL_GPL(mtk_afe_add_sub_dai_control);
 
-static snd_pcm_uframes_t mtk_afe_pcm_pointer
-			 (struct snd_pcm_substream *substream)
+snd_pcm_uframes_t mtk_afe_pcm_pointer(struct snd_soc_component *component,
+				      struct snd_pcm_substream *substream)
 {
 	struct snd_soc_pcm_runtime *rtd = substream->private_data;
-	struct snd_soc_component *component = snd_soc_rtdcom_lookup(rtd, AFE_PCM_NAME);
 	struct mtk_base_afe *afe = snd_soc_component_get_drvdata(component);
 	struct mtk_base_afe_memif *memif = &afe->memif[rtd->cpu_dai->id];
 	const struct mtk_base_memif_data *memif_data = memif->data;
@@ -111,18 +110,13 @@ static snd_pcm_uframes_t mtk_afe_pcm_pointer
 POINTER_RETURN_FRAMES:
 	return bytes_to_frames(substream->runtime, pcm_ptr_bytes);
 }
+EXPORT_SYMBOL_GPL(mtk_afe_pcm_pointer);
 
-const struct snd_pcm_ops mtk_afe_pcm_ops = {
-	.ioctl = snd_pcm_lib_ioctl,
-	.pointer = mtk_afe_pcm_pointer,
-};
-EXPORT_SYMBOL_GPL(mtk_afe_pcm_ops);
-
-int mtk_afe_pcm_new(struct snd_soc_pcm_runtime *rtd)
+int mtk_afe_pcm_new(struct snd_soc_component *component,
+		    struct snd_soc_pcm_runtime *rtd)
 {
 	size_t size;
 	struct snd_pcm *pcm = rtd->pcm;
-	struct snd_soc_component *component = snd_soc_rtdcom_lookup(rtd, AFE_PCM_NAME);
 	struct mtk_base_afe *afe = snd_soc_component_get_drvdata(component);
 
 	size = afe->mtk_afe_hardware->buffer_bytes_max;
@@ -132,17 +126,19 @@ int mtk_afe_pcm_new(struct snd_soc_pcm_runtime *rtd)
 }
 EXPORT_SYMBOL_GPL(mtk_afe_pcm_new);
 
-void mtk_afe_pcm_free(struct snd_pcm *pcm)
+void mtk_afe_pcm_free(struct snd_soc_component *component,
+		      struct snd_pcm *pcm)
 {
 	snd_pcm_lib_preallocate_free_for_all(pcm);
 }
 EXPORT_SYMBOL_GPL(mtk_afe_pcm_free);
 
 const struct snd_soc_component_driver mtk_afe_pcm_platform = {
-	.name = AFE_PCM_NAME,
-	.ops = &mtk_afe_pcm_ops,
-	.pcm_new = mtk_afe_pcm_new,
-	.pcm_free = mtk_afe_pcm_free,
+	.name		= AFE_PCM_NAME,
+	.ioctl		= snd_soc_pcm_lib_ioctl,
+	.pointer	= mtk_afe_pcm_pointer,
+	.pcm_construct	= mtk_afe_pcm_new,
+	.pcm_destruct	= mtk_afe_pcm_free,
 };
 EXPORT_SYMBOL_GPL(mtk_afe_pcm_platform);
 
diff --git a/sound/soc/mediatek/common/mtk-afe-platform-driver.h b/sound/soc/mediatek/common/mtk-afe-platform-driver.h
index 88df6797732f..e550d11568c3 100644
--- a/sound/soc/mediatek/common/mtk-afe-platform-driver.h
+++ b/sound/soc/mediatek/common/mtk-afe-platform-driver.h
@@ -10,7 +10,6 @@
 #define _MTK_AFE_PLATFORM_DRIVER_H_
 
 #define AFE_PCM_NAME "mtk-afe-pcm"
-extern const struct snd_pcm_ops mtk_afe_pcm_ops;
 extern const struct snd_soc_component_driver mtk_afe_pcm_platform;
 
 struct mtk_base_afe;
@@ -18,9 +17,12 @@ struct snd_pcm;
 struct snd_soc_component;
 struct snd_soc_pcm_runtime;
 
-
-int mtk_afe_pcm_new(struct snd_soc_pcm_runtime *rtd);
-void mtk_afe_pcm_free(struct snd_pcm *pcm);
+snd_pcm_uframes_t mtk_afe_pcm_pointer(struct snd_soc_component *component,
+				      struct snd_pcm_substream *substream);
+int mtk_afe_pcm_new(struct snd_soc_component *component,
+		    struct snd_soc_pcm_runtime *rtd);
+void mtk_afe_pcm_free(struct snd_soc_component *component,
+		      struct snd_pcm *pcm);
 
 int mtk_afe_combine_sub_dai(struct mtk_base_afe *afe);
 int mtk_afe_add_sub_dai_control(struct snd_soc_component *component);
diff --git a/sound/soc/mediatek/common/mtk-btcvsd.c b/sound/soc/mediatek/common/mtk-btcvsd.c
index d00608c73c6e..2b490ae2e642 100644
--- a/sound/soc/mediatek/common/mtk-btcvsd.c
+++ b/sound/soc/mediatek/common/mtk-btcvsd.c
@@ -875,11 +875,9 @@ static const struct snd_pcm_hardware mtk_btcvsd_hardware = {
 	.fifo_size = 0,
 };
 
-static int mtk_pcm_btcvsd_open(struct snd_pcm_substream *substream)
+static int mtk_pcm_btcvsd_open(struct snd_soc_component *component,
+			       struct snd_pcm_substream *substream)
 {
-	struct snd_soc_pcm_runtime *rtd = substream->private_data;
-	struct snd_soc_component *component =
-		snd_soc_rtdcom_lookup(rtd, BTCVSD_SND_NAME);
 	struct mtk_btcvsd_snd *bt = snd_soc_component_get_drvdata(component);
 	int ret;
 
@@ -899,11 +897,9 @@ static int mtk_pcm_btcvsd_open(struct snd_pcm_substream *substream)
 	return ret;
 }
 
-static int mtk_pcm_btcvsd_close(struct snd_pcm_substream *substream)
+static int mtk_pcm_btcvsd_close(struct snd_soc_component *component,
+				struct snd_pcm_substream *substream)
 {
-	struct snd_soc_pcm_runtime *rtd = substream->private_data;
-	struct snd_soc_component *component =
-		snd_soc_rtdcom_lookup(rtd, BTCVSD_SND_NAME);
 	struct mtk_btcvsd_snd *bt = snd_soc_component_get_drvdata(component);
 	struct mtk_btcvsd_snd_stream *bt_stream = get_bt_stream(bt, substream);
 
@@ -914,12 +910,10 @@ static int mtk_pcm_btcvsd_close(struct snd_pcm_substream *substream)
 	return 0;
 }
 
-static int mtk_pcm_btcvsd_hw_params(struct snd_pcm_substream *substream,
+static int mtk_pcm_btcvsd_hw_params(struct snd_soc_component *component,
+				    struct snd_pcm_substream *substream,
 				    struct snd_pcm_hw_params *hw_params)
 {
-	struct snd_soc_pcm_runtime *rtd = substream->private_data;
-	struct snd_soc_component *component =
-		snd_soc_rtdcom_lookup(rtd, BTCVSD_SND_NAME);
 	struct mtk_btcvsd_snd *bt = snd_soc_component_get_drvdata(component);
 
 	if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK &&
@@ -934,11 +928,9 @@ static int mtk_pcm_btcvsd_hw_params(struct snd_pcm_substream *substream,
 	return 0;
 }
 
-static int mtk_pcm_btcvsd_hw_free(struct snd_pcm_substream *substream)
+static int mtk_pcm_btcvsd_hw_free(struct snd_soc_component *component,
+				  struct snd_pcm_substream *substream)
 {
-	struct snd_soc_pcm_runtime *rtd = substream->private_data;
-	struct snd_soc_component *component =
-		snd_soc_rtdcom_lookup(rtd, BTCVSD_SND_NAME);
 	struct mtk_btcvsd_snd *bt = snd_soc_component_get_drvdata(component);
 
 	if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK)
@@ -947,11 +939,9 @@ static int mtk_pcm_btcvsd_hw_free(struct snd_pcm_substream *substream)
 	return 0;
 }
 
-static int mtk_pcm_btcvsd_prepare(struct snd_pcm_substream *substream)
+static int mtk_pcm_btcvsd_prepare(struct snd_soc_component *component,
+				  struct snd_pcm_substream *substream)
 {
-	struct snd_soc_pcm_runtime *rtd = substream->private_data;
-	struct snd_soc_component *component =
-		snd_soc_rtdcom_lookup(rtd, BTCVSD_SND_NAME);
 	struct mtk_btcvsd_snd *bt = snd_soc_component_get_drvdata(component);
 	struct mtk_btcvsd_snd_stream *bt_stream = get_bt_stream(bt, substream);
 
@@ -961,11 +951,9 @@ static int mtk_pcm_btcvsd_prepare(struct snd_pcm_substream *substream)
 	return 0;
 }
 
-static int mtk_pcm_btcvsd_trigger(struct snd_pcm_substream *substream, int cmd)
+static int mtk_pcm_btcvsd_trigger(struct snd_soc_component *component,
+				  struct snd_pcm_substream *substream, int cmd)
 {
-	struct snd_soc_pcm_runtime *rtd = substream->private_data;
-	struct snd_soc_component *component =
-		snd_soc_rtdcom_lookup(rtd, BTCVSD_SND_NAME);
 	struct mtk_btcvsd_snd *bt = snd_soc_component_get_drvdata(component);
 	struct mtk_btcvsd_snd_stream *bt_stream = get_bt_stream(bt, substream);
 	int stream = substream->stream;
@@ -993,12 +981,10 @@ static int mtk_pcm_btcvsd_trigger(struct snd_pcm_substream *substream, int cmd)
 	}
 }
 
-static snd_pcm_uframes_t mtk_pcm_btcvsd_pointer
-	(struct snd_pcm_substream *substream)
+static snd_pcm_uframes_t mtk_pcm_btcvsd_pointer(
+	struct snd_soc_component *component,
+	struct snd_pcm_substream *substream)
 {
-	struct snd_soc_pcm_runtime *rtd = substream->private_data;
-	struct snd_soc_component *component =
-		snd_soc_rtdcom_lookup(rtd, BTCVSD_SND_NAME);
 	struct mtk_btcvsd_snd *bt = snd_soc_component_get_drvdata(component);
 	struct mtk_btcvsd_snd_stream *bt_stream;
 	snd_pcm_uframes_t frame = 0;
@@ -1044,13 +1030,11 @@ static snd_pcm_uframes_t mtk_pcm_btcvsd_pointer
 	return frame;
 }
 
-static int mtk_pcm_btcvsd_copy(struct snd_pcm_substream *substream,
+static int mtk_pcm_btcvsd_copy(struct snd_soc_component *component,
+			       struct snd_pcm_substream *substream,
 			       int channel, unsigned long pos,
 			       void __user *buf, unsigned long count)
 {
-	struct snd_soc_pcm_runtime *rtd = substream->private_data;
-	struct snd_soc_component *component =
-		snd_soc_rtdcom_lookup(rtd, BTCVSD_SND_NAME);
 	struct mtk_btcvsd_snd *bt = snd_soc_component_get_drvdata(component);
 
 	if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK)
@@ -1061,18 +1045,6 @@ static int mtk_pcm_btcvsd_copy(struct snd_pcm_substream *substream,
 	return 0;
 }
 
-static struct snd_pcm_ops mtk_btcvsd_ops = {
-	.open = mtk_pcm_btcvsd_open,
-	.close = mtk_pcm_btcvsd_close,
-	.ioctl = snd_pcm_lib_ioctl,
-	.hw_params = mtk_pcm_btcvsd_hw_params,
-	.hw_free = mtk_pcm_btcvsd_hw_free,
-	.prepare = mtk_pcm_btcvsd_prepare,
-	.trigger = mtk_pcm_btcvsd_trigger,
-	.pointer = mtk_pcm_btcvsd_pointer,
-	.copy_user = mtk_pcm_btcvsd_copy,
-};
-
 /* kcontrol */
 static const char *const btsco_band_str[] = {"NB", "WB"};
 
@@ -1295,9 +1267,17 @@ static int mtk_btcvsd_snd_component_probe(struct snd_soc_component *component)
 }
 
 static const struct snd_soc_component_driver mtk_btcvsd_snd_platform = {
-	.name = BTCVSD_SND_NAME,
-	.ops = &mtk_btcvsd_ops,
-	.probe = mtk_btcvsd_snd_component_probe,
+	.name		= BTCVSD_SND_NAME,
+	.probe		= mtk_btcvsd_snd_component_probe,
+	.open		= mtk_pcm_btcvsd_open,
+	.close		= mtk_pcm_btcvsd_close,
+	.ioctl		= snd_soc_pcm_lib_ioctl,
+	.hw_params	= mtk_pcm_btcvsd_hw_params,
+	.hw_free	= mtk_pcm_btcvsd_hw_free,
+	.prepare	= mtk_pcm_btcvsd_prepare,
+	.trigger	= mtk_pcm_btcvsd_trigger,
+	.pointer	= mtk_pcm_btcvsd_pointer,
+	.copy_user	= mtk_pcm_btcvsd_copy,
 };
 
 static int mtk_btcvsd_snd_probe(struct platform_device *pdev)
diff --git a/sound/soc/mediatek/mt6797/mt6797-afe-pcm.c b/sound/soc/mediatek/mt6797/mt6797-afe-pcm.c
index e52c032d53aa..033c07fb599c 100644
--- a/sound/soc/mediatek/mt6797/mt6797-afe-pcm.c
+++ b/sound/soc/mediatek/mt6797/mt6797-afe-pcm.c
@@ -710,11 +710,12 @@ static int mt6797_afe_component_probe(struct snd_soc_component *component)
 }
 
 static const struct snd_soc_component_driver mt6797_afe_component = {
-	.name = AFE_PCM_NAME,
-	.ops = &mtk_afe_pcm_ops,
-	.pcm_new = mtk_afe_pcm_new,
-	.pcm_free = mtk_afe_pcm_free,
-	.probe = mt6797_afe_component_probe,
+	.name		= AFE_PCM_NAME,
+	.probe		= mt6797_afe_component_probe,
+	.ioctl		= snd_soc_pcm_lib_ioctl,
+	.pointer	= mtk_afe_pcm_pointer,
+	.pcm_construct	= mtk_afe_pcm_new,
+	.pcm_destruct	= mtk_afe_pcm_free,
 };
 
 static int mt6797_dai_memif_register(struct mtk_base_afe *afe)
diff --git a/sound/soc/mediatek/mt8183/mt8183-afe-pcm.c b/sound/soc/mediatek/mt8183/mt8183-afe-pcm.c
index 4a31106d3471..76af09d8f1af 100644
--- a/sound/soc/mediatek/mt8183/mt8183-afe-pcm.c
+++ b/sound/soc/mediatek/mt8183/mt8183-afe-pcm.c
@@ -11,6 +11,7 @@
 #include <linux/of.h>
 #include <linux/of_address.h>
 #include <linux/pm_runtime.h>
+#include <linux/reset.h>
 
 #include "mt8183-afe-common.h"
 #include "mt8183-afe-clk.h"
@@ -1047,11 +1048,12 @@ static int mt8183_afe_component_probe(struct snd_soc_component *component)
 }
 
 static const struct snd_soc_component_driver mt8183_afe_component = {
-	.name = AFE_PCM_NAME,
-	.ops = &mtk_afe_pcm_ops,
-	.pcm_new = mtk_afe_pcm_new,
-	.pcm_free = mtk_afe_pcm_free,
-	.probe = mt8183_afe_component_probe,
+	.name		= AFE_PCM_NAME,
+	.probe		= mt8183_afe_component_probe,
+	.ioctl		= snd_soc_pcm_lib_ioctl,
+	.pointer	= mtk_afe_pcm_pointer,
+	.pcm_construct	= mtk_afe_pcm_new,
+	.pcm_destruct	= mtk_afe_pcm_free,
 };
 
 static int mt8183_dai_memif_register(struct mtk_base_afe *afe)
@@ -1089,6 +1091,7 @@ static int mt8183_afe_pcm_dev_probe(struct platform_device *pdev)
 	struct mtk_base_afe *afe;
 	struct mt8183_afe_private *afe_priv;
 	struct device *dev;
+	struct reset_control *rstc;
 	int i, irq_id, ret;
 
 	afe = devm_kzalloc(&pdev->dev, sizeof(*afe), GFP_KERNEL);
@@ -1126,6 +1129,19 @@ static int mt8183_afe_pcm_dev_probe(struct platform_device *pdev)
 		return ret;
 	}
 
+	rstc = devm_reset_control_get(dev, "audiosys");
+	if (IS_ERR(rstc)) {
+		ret = PTR_ERR(rstc);
+		dev_err(dev, "could not get audiosys reset:%d\n", ret);
+		return ret;
+	}
+
+	ret = reset_control_reset(rstc);
+	if (ret) {
+		dev_err(dev, "failed to trigger audio reset:%d\n", ret);
+		return ret;
+	}
+
 	/* enable clock for regcache get default value from hw */
 	afe_priv->pm_runtime_bypass_reg_ctl = true;
 	pm_runtime_get_sync(&pdev->dev);
diff --git a/sound/soc/mediatek/mt8183/mt8183-mt6358-ts3a227-max98357.c b/sound/soc/mediatek/mt8183/mt8183-mt6358-ts3a227-max98357.c
index bb9cdc0d6552..0555f7d73d05 100644
--- a/sound/soc/mediatek/mt8183/mt8183-mt6358-ts3a227-max98357.c
+++ b/sound/soc/mediatek/mt8183/mt8183-mt6358-ts3a227-max98357.c
@@ -19,11 +19,12 @@ enum PINCTRL_PIN_STATE {
 	PIN_STATE_DEFAULT = 0,
 	PIN_TDM_OUT_ON,
 	PIN_TDM_OUT_OFF,
+	PIN_WOV,
 	PIN_STATE_MAX
 };
 
 static const char * const mt8183_pin_str[PIN_STATE_MAX] = {
-	"default", "aud_tdm_out_on", "aud_tdm_out_off",
+	"default", "aud_tdm_out_on", "aud_tdm_out_off", "wov",
 };
 
 struct mt8183_mt6358_ts3a227_max98357_priv {
@@ -142,6 +143,11 @@ SND_SOC_DAILINK_DEFS(playback_hdmi,
 	DAILINK_COMP_ARRAY(COMP_DUMMY()),
 	DAILINK_COMP_ARRAY(COMP_EMPTY()));
 
+SND_SOC_DAILINK_DEFS(wake_on_voice,
+	DAILINK_COMP_ARRAY(COMP_DUMMY()),
+	DAILINK_COMP_ARRAY(COMP_DUMMY()),
+	DAILINK_COMP_ARRAY(COMP_EMPTY()));
+
 /* BE */
 SND_SOC_DAILINK_DEFS(primary_codec,
 	DAILINK_COMP_ARRAY(COMP_CPU("ADDA")),
@@ -229,6 +235,41 @@ static struct snd_soc_ops mt8183_mt6358_tdm_ops = {
 	.shutdown = mt8183_mt6358_tdm_shutdown,
 };
 
+static int
+mt8183_mt6358_ts3a227_max98357_wov_startup(
+	struct snd_pcm_substream *substream)
+{
+	struct snd_soc_pcm_runtime *rtd = substream->private_data;
+	struct snd_soc_card *card = rtd->card;
+	struct mt8183_mt6358_ts3a227_max98357_priv *priv =
+			snd_soc_card_get_drvdata(card);
+
+	return pinctrl_select_state(priv->pinctrl,
+				    priv->pin_states[PIN_WOV]);
+}
+
+static void
+mt8183_mt6358_ts3a227_max98357_wov_shutdown(
+	struct snd_pcm_substream *substream)
+{
+	struct snd_soc_pcm_runtime *rtd = substream->private_data;
+	struct snd_soc_card *card = rtd->card;
+	struct mt8183_mt6358_ts3a227_max98357_priv *priv =
+			snd_soc_card_get_drvdata(card);
+	int ret;
+
+	ret = pinctrl_select_state(priv->pinctrl,
+				   priv->pin_states[PIN_STATE_DEFAULT]);
+	if (ret)
+		dev_err(card->dev, "%s failed to select state %d\n",
+			__func__, ret);
+}
+
+static const struct snd_soc_ops mt8183_mt6358_ts3a227_max98357_wov_ops = {
+	.startup = mt8183_mt6358_ts3a227_max98357_wov_startup,
+	.shutdown = mt8183_mt6358_ts3a227_max98357_wov_shutdown,
+};
+
 static struct snd_soc_dai_link
 mt8183_mt6358_ts3a227_max98357_dai_links[] = {
 	/* FE */
@@ -306,6 +347,15 @@ mt8183_mt6358_ts3a227_max98357_dai_links[] = {
 		.dpcm_playback = 1,
 		SND_SOC_DAILINK_REG(playback_hdmi),
 	},
+	{
+		.name = "Wake on Voice",
+		.stream_name = "Wake on Voice",
+		.ignore_suspend = 1,
+		.ignore = 1,
+		SND_SOC_DAILINK_REG(wake_on_voice),
+		.ops = &mt8183_mt6358_ts3a227_max98357_wov_ops,
+	},
+
 	/* BE */
 	{
 		.name = "Primary Codec",
@@ -429,7 +479,7 @@ static int
 mt8183_mt6358_ts3a227_max98357_dev_probe(struct platform_device *pdev)
 {
 	struct snd_soc_card *card = &mt8183_mt6358_ts3a227_max98357_card;
-	struct device_node *platform_node;
+	struct device_node *platform_node, *ec_codec;
 	struct snd_soc_dai_link *dai_link;
 	struct mt8183_mt6358_ts3a227_max98357_priv *priv;
 	int ret;
@@ -444,10 +494,24 @@ mt8183_mt6358_ts3a227_max98357_dev_probe(struct platform_device *pdev)
 		return -EINVAL;
 	}
 
+	ec_codec = of_parse_phandle(pdev->dev.of_node, "mediatek,ec-codec", 0);
+
 	for_each_card_prelinks(card, i, dai_link) {
 		if (dai_link->platforms->name)
 			continue;
-		dai_link->platforms->of_node = platform_node;
+
+		if (ec_codec && strcmp(dai_link->name, "Wake on Voice") == 0) {
+			dai_link->cpus[0].name = NULL;
+			dai_link->cpus[0].of_node = ec_codec;
+			dai_link->cpus[0].dai_name = NULL;
+			dai_link->codecs[0].name = NULL;
+			dai_link->codecs[0].of_node = ec_codec;
+			dai_link->codecs[0].dai_name = "Wake on Voice";
+			dai_link->platforms[0].of_node = ec_codec;
+			dai_link->ignore = 0;
+		} else {
+			dai_link->platforms->of_node = platform_node;
+		}
 	}
 
 	mt8183_mt6358_ts3a227_max98357_headset_dev.dlc.of_node =
diff --git a/sound/soc/meson/axg-fifo.c b/sound/soc/meson/axg-fifo.c
index 5a3749938900..d6f3eefb8f09 100644
--- a/sound/soc/meson/axg-fifo.c
+++ b/sound/soc/meson/axg-fifo.c
@@ -70,7 +70,8 @@ static void __dma_enable(struct axg_fifo *fifo,  bool enable)
 			   enable ? CTRL0_DMA_EN : 0);
 }
 
-static int axg_fifo_pcm_trigger(struct snd_pcm_substream *ss, int cmd)
+int axg_fifo_pcm_trigger(struct snd_soc_component *component,
+			 struct snd_pcm_substream *ss, int cmd)
 {
 	struct axg_fifo *fifo = axg_fifo_data(ss);
 
@@ -91,8 +92,10 @@ static int axg_fifo_pcm_trigger(struct snd_pcm_substream *ss, int cmd)
 
 	return 0;
 }
+EXPORT_SYMBOL_GPL(axg_fifo_pcm_trigger);
 
-static snd_pcm_uframes_t axg_fifo_pcm_pointer(struct snd_pcm_substream *ss)
+snd_pcm_uframes_t axg_fifo_pcm_pointer(struct snd_soc_component *component,
+				       struct snd_pcm_substream *ss)
 {
 	struct axg_fifo *fifo = axg_fifo_data(ss);
 	struct snd_pcm_runtime *runtime = ss->runtime;
@@ -102,9 +105,11 @@ static snd_pcm_uframes_t axg_fifo_pcm_pointer(struct snd_pcm_substream *ss)
 
 	return bytes_to_frames(runtime, addr - (unsigned int)runtime->dma_addr);
 }
+EXPORT_SYMBOL_GPL(axg_fifo_pcm_pointer);
 
-static int axg_fifo_pcm_hw_params(struct snd_pcm_substream *ss,
-				  struct snd_pcm_hw_params *params)
+int axg_fifo_pcm_hw_params(struct snd_soc_component *component,
+			   struct snd_pcm_substream *ss,
+			   struct snd_pcm_hw_params *params)
 {
 	struct snd_pcm_runtime *runtime = ss->runtime;
 	struct axg_fifo *fifo = axg_fifo_data(ss);
@@ -132,15 +137,17 @@ static int axg_fifo_pcm_hw_params(struct snd_pcm_substream *ss,
 
 	return 0;
 }
+EXPORT_SYMBOL_GPL(axg_fifo_pcm_hw_params);
 
-static int g12a_fifo_pcm_hw_params(struct snd_pcm_substream *ss,
-				   struct snd_pcm_hw_params *params)
+int g12a_fifo_pcm_hw_params(struct snd_soc_component *component,
+			    struct snd_pcm_substream *ss,
+			    struct snd_pcm_hw_params *params)
 {
 	struct axg_fifo *fifo = axg_fifo_data(ss);
 	struct snd_pcm_runtime *runtime = ss->runtime;
 	int ret;
 
-	ret = axg_fifo_pcm_hw_params(ss, params);
+	ret = axg_fifo_pcm_hw_params(component, ss, params);
 	if (ret)
 		return ret;
 
@@ -149,8 +156,10 @@ static int g12a_fifo_pcm_hw_params(struct snd_pcm_substream *ss,
 
 	return 0;
 }
+EXPORT_SYMBOL_GPL(g12a_fifo_pcm_hw_params);
 
-static int axg_fifo_pcm_hw_free(struct snd_pcm_substream *ss)
+int axg_fifo_pcm_hw_free(struct snd_soc_component *component,
+			 struct snd_pcm_substream *ss)
 {
 	struct axg_fifo *fifo = axg_fifo_data(ss);
 
@@ -160,6 +169,7 @@ static int axg_fifo_pcm_hw_free(struct snd_pcm_substream *ss)
 
 	return snd_pcm_lib_free_pages(ss);
 }
+EXPORT_SYMBOL_GPL(axg_fifo_pcm_hw_free);
 
 static void axg_fifo_ack_irq(struct axg_fifo *fifo, u8 mask)
 {
@@ -194,7 +204,8 @@ static irqreturn_t axg_fifo_pcm_irq_block(int irq, void *dev_id)
 	return IRQ_RETVAL(status);
 }
 
-static int axg_fifo_pcm_open(struct snd_pcm_substream *ss)
+int axg_fifo_pcm_open(struct snd_soc_component *component,
+		      struct snd_pcm_substream *ss)
 {
 	struct axg_fifo *fifo = axg_fifo_data(ss);
 	struct device *dev = axg_fifo_dev(ss);
@@ -250,8 +261,10 @@ static int axg_fifo_pcm_open(struct snd_pcm_substream *ss)
 
 	return ret;
 }
+EXPORT_SYMBOL_GPL(axg_fifo_pcm_open);
 
-static int axg_fifo_pcm_close(struct snd_pcm_substream *ss)
+int axg_fifo_pcm_close(struct snd_soc_component *component,
+		       struct snd_pcm_substream *ss)
 {
 	struct axg_fifo *fifo = axg_fifo_data(ss);
 	int ret;
@@ -267,28 +280,7 @@ static int axg_fifo_pcm_close(struct snd_pcm_substream *ss)
 
 	return ret;
 }
-
-const struct snd_pcm_ops axg_fifo_pcm_ops = {
-	.open =		axg_fifo_pcm_open,
-	.close =        axg_fifo_pcm_close,
-	.ioctl =	snd_pcm_lib_ioctl,
-	.hw_params =	axg_fifo_pcm_hw_params,
-	.hw_free =      axg_fifo_pcm_hw_free,
-	.pointer =	axg_fifo_pcm_pointer,
-	.trigger =	axg_fifo_pcm_trigger,
-};
-EXPORT_SYMBOL_GPL(axg_fifo_pcm_ops);
-
-const struct snd_pcm_ops g12a_fifo_pcm_ops = {
-	.open =		axg_fifo_pcm_open,
-	.close =        axg_fifo_pcm_close,
-	.ioctl =	snd_pcm_lib_ioctl,
-	.hw_params =	g12a_fifo_pcm_hw_params,
-	.hw_free =      axg_fifo_pcm_hw_free,
-	.pointer =	axg_fifo_pcm_pointer,
-	.trigger =	axg_fifo_pcm_trigger,
-};
-EXPORT_SYMBOL_GPL(g12a_fifo_pcm_ops);
+EXPORT_SYMBOL_GPL(axg_fifo_pcm_close);
 
 int axg_fifo_pcm_new(struct snd_soc_pcm_runtime *rtd, unsigned int type)
 {
diff --git a/sound/soc/meson/axg-fifo.h b/sound/soc/meson/axg-fifo.h
index bb1e2ce50256..cf928d43b558 100644
--- a/sound/soc/meson/axg-fifo.h
+++ b/sound/soc/meson/axg-fifo.h
@@ -15,7 +15,7 @@ struct reset_control;
 struct snd_soc_component_driver;
 struct snd_soc_dai;
 struct snd_soc_dai_driver;
-struct snd_pcm_ops;
+
 struct snd_soc_pcm_runtime;
 
 #define AXG_FIFO_CH_MAX			128
@@ -75,8 +75,22 @@ struct axg_fifo_match_data {
 	struct snd_soc_dai_driver *dai_drv;
 };
 
-extern const struct snd_pcm_ops axg_fifo_pcm_ops;
-extern const struct snd_pcm_ops g12a_fifo_pcm_ops;
+int axg_fifo_pcm_open(struct snd_soc_component *component,
+		      struct snd_pcm_substream *ss);
+int axg_fifo_pcm_close(struct snd_soc_component *component,
+		       struct snd_pcm_substream *ss);
+int axg_fifo_pcm_hw_params(struct snd_soc_component *component,
+			   struct snd_pcm_substream *ss,
+			   struct snd_pcm_hw_params *params);
+int g12a_fifo_pcm_hw_params(struct snd_soc_component *component,
+			    struct snd_pcm_substream *ss,
+			    struct snd_pcm_hw_params *params);
+int axg_fifo_pcm_hw_free(struct snd_soc_component *component,
+			 struct snd_pcm_substream *ss);
+snd_pcm_uframes_t axg_fifo_pcm_pointer(struct snd_soc_component *component,
+				       struct snd_pcm_substream *ss);
+int axg_fifo_pcm_trigger(struct snd_soc_component *component,
+			 struct snd_pcm_substream *ss, int cmd);
 
 int axg_fifo_pcm_new(struct snd_soc_pcm_runtime *rtd, unsigned int type);
 int axg_fifo_probe(struct platform_device *pdev);
diff --git a/sound/soc/meson/axg-frddr.c b/sound/soc/meson/axg-frddr.c
index 6ab111c31b28..665d75d49d7b 100644
--- a/sound/soc/meson/axg-frddr.c
+++ b/sound/soc/meson/axg-frddr.c
@@ -149,7 +149,13 @@ static const struct snd_soc_component_driver axg_frddr_component_drv = {
 	.num_dapm_widgets	= ARRAY_SIZE(axg_frddr_dapm_widgets),
 	.dapm_routes		= axg_frddr_dapm_routes,
 	.num_dapm_routes	= ARRAY_SIZE(axg_frddr_dapm_routes),
-	.ops			= &axg_fifo_pcm_ops
+	.open			= axg_fifo_pcm_open,
+	.close			= axg_fifo_pcm_close,
+	.ioctl			= snd_soc_pcm_lib_ioctl,
+	.hw_params		= axg_fifo_pcm_hw_params,
+	.hw_free		= axg_fifo_pcm_hw_free,
+	.pointer		= axg_fifo_pcm_pointer,
+	.trigger		= axg_fifo_pcm_trigger,
 };
 
 static const struct axg_fifo_match_data axg_frddr_match_data = {
@@ -267,7 +273,13 @@ static const struct snd_soc_component_driver g12a_frddr_component_drv = {
 	.num_dapm_widgets	= ARRAY_SIZE(g12a_frddr_dapm_widgets),
 	.dapm_routes		= g12a_frddr_dapm_routes,
 	.num_dapm_routes	= ARRAY_SIZE(g12a_frddr_dapm_routes),
-	.ops			= &g12a_fifo_pcm_ops
+	.open			= axg_fifo_pcm_open,
+	.close			= axg_fifo_pcm_close,
+	.ioctl			= snd_soc_pcm_lib_ioctl,
+	.hw_params		= g12a_fifo_pcm_hw_params,
+	.hw_free		= axg_fifo_pcm_hw_free,
+	.pointer		= axg_fifo_pcm_pointer,
+	.trigger		= axg_fifo_pcm_trigger,
 };
 
 static const struct axg_fifo_match_data g12a_frddr_match_data = {
@@ -331,7 +343,13 @@ static const struct snd_soc_component_driver sm1_frddr_component_drv = {
 	.num_dapm_widgets	= ARRAY_SIZE(sm1_frddr_dapm_widgets),
 	.dapm_routes		= g12a_frddr_dapm_routes,
 	.num_dapm_routes	= ARRAY_SIZE(g12a_frddr_dapm_routes),
-	.ops			= &g12a_fifo_pcm_ops
+	.open			= axg_fifo_pcm_open,
+	.close			= axg_fifo_pcm_close,
+	.ioctl			= snd_soc_pcm_lib_ioctl,
+	.hw_params		= g12a_fifo_pcm_hw_params,
+	.hw_free		= axg_fifo_pcm_hw_free,
+	.pointer		= axg_fifo_pcm_pointer,
+	.trigger		= axg_fifo_pcm_trigger,
 };
 
 static const struct axg_fifo_match_data sm1_frddr_match_data = {
diff --git a/sound/soc/meson/axg-toddr.c b/sound/soc/meson/axg-toddr.c
index c8ea2145f576..7fef0b961496 100644
--- a/sound/soc/meson/axg-toddr.c
+++ b/sound/soc/meson/axg-toddr.c
@@ -181,7 +181,13 @@ static const struct snd_soc_component_driver axg_toddr_component_drv = {
 	.num_dapm_widgets	= ARRAY_SIZE(axg_toddr_dapm_widgets),
 	.dapm_routes		= axg_toddr_dapm_routes,
 	.num_dapm_routes	= ARRAY_SIZE(axg_toddr_dapm_routes),
-	.ops			= &axg_fifo_pcm_ops
+	.open			= axg_fifo_pcm_open,
+	.close			= axg_fifo_pcm_close,
+	.ioctl			= snd_soc_pcm_lib_ioctl,
+	.hw_params		= axg_fifo_pcm_hw_params,
+	.hw_free		= axg_fifo_pcm_hw_free,
+	.pointer		= axg_fifo_pcm_pointer,
+	.trigger		= axg_fifo_pcm_trigger,
 };
 
 static const struct axg_fifo_match_data axg_toddr_match_data = {
@@ -214,7 +220,13 @@ static const struct snd_soc_component_driver g12a_toddr_component_drv = {
 	.num_dapm_widgets	= ARRAY_SIZE(axg_toddr_dapm_widgets),
 	.dapm_routes		= axg_toddr_dapm_routes,
 	.num_dapm_routes	= ARRAY_SIZE(axg_toddr_dapm_routes),
-	.ops			= &g12a_fifo_pcm_ops
+	.open			= axg_fifo_pcm_open,
+	.close			= axg_fifo_pcm_close,
+	.ioctl			= snd_soc_pcm_lib_ioctl,
+	.hw_params		= g12a_fifo_pcm_hw_params,
+	.hw_free		= axg_fifo_pcm_hw_free,
+	.pointer		= axg_fifo_pcm_pointer,
+	.trigger		= axg_fifo_pcm_trigger,
 };
 
 static const struct axg_fifo_match_data g12a_toddr_match_data = {
@@ -278,7 +290,13 @@ static const struct snd_soc_component_driver sm1_toddr_component_drv = {
 	.num_dapm_widgets	= ARRAY_SIZE(sm1_toddr_dapm_widgets),
 	.dapm_routes		= sm1_toddr_dapm_routes,
 	.num_dapm_routes	= ARRAY_SIZE(sm1_toddr_dapm_routes),
-	.ops			= &g12a_fifo_pcm_ops
+	.open			= axg_fifo_pcm_open,
+	.close			= axg_fifo_pcm_close,
+	.ioctl			= snd_soc_pcm_lib_ioctl,
+	.hw_params		= g12a_fifo_pcm_hw_params,
+	.hw_free		= axg_fifo_pcm_hw_free,
+	.pointer		= axg_fifo_pcm_pointer,
+	.trigger		= axg_fifo_pcm_trigger,
 };
 
 static const struct axg_fifo_match_data sm1_toddr_match_data = {
diff --git a/sound/soc/pxa/Kconfig b/sound/soc/pxa/Kconfig
index 213d4dab0346..295cfffa4646 100644
--- a/sound/soc/pxa/Kconfig
+++ b/sound/soc/pxa/Kconfig
@@ -190,14 +190,14 @@ config SND_PXA2XX_SOC_MAGICIAN
 	  HTC Magician.
 
 config SND_PXA2XX_SOC_MIOA701
-        tristate "SoC Audio support for MIO A701"
-        depends on SND_PXA2XX_SOC && MACH_MIOA701
+	tristate "SoC Audio support for MIO A701"
+	depends on SND_PXA2XX_SOC && MACH_MIOA701
 	depends on AC97_BUS=n
-        select SND_PXA2XX_SOC_AC97
-        select SND_SOC_WM9713
-        help
-          Say Y if you want to add support for SoC audio on the
-          MIO A701.
+	select SND_PXA2XX_SOC_AC97
+	select SND_SOC_WM9713
+	help
+	  Say Y if you want to add support for SoC audio on the
+	  MIO A701.
 
 config SND_PXA2XX_SOC_IMOTE2
        tristate "SoC Audio support for IMote 2"
@@ -205,7 +205,7 @@ config SND_PXA2XX_SOC_IMOTE2
        select SND_PXA2XX_SOC_I2S
        select SND_SOC_WM8940
        help
-         Say Y if you want to add support for SoC audio on the
+	 Say Y if you want to add support for SoC audio on the
 	 IMote 2.
 
 config SND_MMP_SOC_BROWNSTONE
diff --git a/sound/soc/pxa/mmp-pcm.c b/sound/soc/pxa/mmp-pcm.c
index 7096b5263e25..54a4c9213e83 100644
--- a/sound/soc/pxa/mmp-pcm.c
+++ b/sound/soc/pxa/mmp-pcm.c
@@ -55,8 +55,9 @@ static struct snd_pcm_hardware mmp_pcm_hardware[] = {
 	},
 };
 
-static int mmp_pcm_hw_params(struct snd_pcm_substream *substream,
-			      struct snd_pcm_hw_params *params)
+static int mmp_pcm_hw_params(struct snd_soc_component *component,
+			     struct snd_pcm_substream *substream,
+			     struct snd_pcm_hw_params *params)
 {
 	struct dma_chan *chan = snd_dmaengine_pcm_get_chan(substream);
 	struct dma_slave_config slave_config;
@@ -77,6 +78,18 @@ static int mmp_pcm_hw_params(struct snd_pcm_substream *substream,
 	return 0;
 }
 
+static int mmp_pcm_trigger(struct snd_soc_component *component,
+			   struct snd_pcm_substream *substream, int cmd)
+{
+	return snd_dmaengine_pcm_trigger(substream, cmd);
+}
+
+static snd_pcm_uframes_t mmp_pcm_pointer(struct snd_soc_component *component,
+					 struct snd_pcm_substream *substream)
+{
+	return snd_dmaengine_pcm_pointer(substream);
+}
+
 static bool filter(struct dma_chan *chan, void *param)
 {
 	struct mmp_dma_data *dma_data = param;
@@ -94,10 +107,10 @@ static bool filter(struct dma_chan *chan, void *param)
 	return found;
 }
 
-static int mmp_pcm_open(struct snd_pcm_substream *substream)
+static int mmp_pcm_open(struct snd_soc_component *component,
+			struct snd_pcm_substream *substream)
 {
 	struct snd_soc_pcm_runtime *rtd = substream->private_data;
-	struct snd_soc_component *component = snd_soc_rtdcom_lookup(rtd, DRV_NAME);
 	struct platform_device *pdev = to_platform_device(component->dev);
 	struct snd_soc_dai *cpu_dai = rtd->cpu_dai;
 	struct mmp_dma_data dma_data;
@@ -117,8 +130,15 @@ static int mmp_pcm_open(struct snd_pcm_substream *substream)
 		    &dma_data);
 }
 
-static int mmp_pcm_mmap(struct snd_pcm_substream *substream,
-			 struct vm_area_struct *vma)
+static int mmp_pcm_close(struct snd_soc_component *component,
+			 struct snd_pcm_substream *substream)
+{
+	return snd_dmaengine_pcm_close_release_chan(substream);
+}
+
+static int mmp_pcm_mmap(struct snd_soc_component *component,
+			struct snd_pcm_substream *substream,
+			struct vm_area_struct *vma)
 {
 	struct snd_pcm_runtime *runtime = substream->runtime;
 	unsigned long off = vma->vm_pgoff;
@@ -129,17 +149,8 @@ static int mmp_pcm_mmap(struct snd_pcm_substream *substream,
 		vma->vm_end - vma->vm_start, vma->vm_page_prot);
 }
 
-static const struct snd_pcm_ops mmp_pcm_ops = {
-	.open		= mmp_pcm_open,
-	.close		= snd_dmaengine_pcm_close_release_chan,
-	.ioctl		= snd_pcm_lib_ioctl,
-	.hw_params	= mmp_pcm_hw_params,
-	.trigger	= snd_dmaengine_pcm_trigger,
-	.pointer	= snd_dmaengine_pcm_pointer,
-	.mmap		= mmp_pcm_mmap,
-};
-
-static void mmp_pcm_free_dma_buffers(struct snd_pcm *pcm)
+static void mmp_pcm_free_dma_buffers(struct snd_soc_component *component,
+				     struct snd_pcm *pcm)
 {
 	struct snd_pcm_substream *substream;
 	struct snd_dma_buffer *buf;
@@ -188,7 +199,8 @@ static int mmp_pcm_preallocate_dma_buffer(struct snd_pcm_substream *substream,
 	return 0;
 }
 
-static int mmp_pcm_new(struct snd_soc_pcm_runtime *rtd)
+static int mmp_pcm_new(struct snd_soc_component *component,
+		       struct snd_soc_pcm_runtime *rtd)
 {
 	struct snd_pcm_substream *substream;
 	struct snd_pcm *pcm = rtd->pcm;
@@ -205,15 +217,21 @@ static int mmp_pcm_new(struct snd_soc_pcm_runtime *rtd)
 	return 0;
 
 err:
-	mmp_pcm_free_dma_buffers(pcm);
+	mmp_pcm_free_dma_buffers(component, pcm);
 	return ret;
 }
 
 static const struct snd_soc_component_driver mmp_soc_component = {
 	.name		= DRV_NAME,
-	.ops		= &mmp_pcm_ops,
-	.pcm_new	= mmp_pcm_new,
-	.pcm_free	= mmp_pcm_free_dma_buffers,
+	.open		= mmp_pcm_open,
+	.close		= mmp_pcm_close,
+	.ioctl		= snd_soc_pcm_lib_ioctl,
+	.hw_params	= mmp_pcm_hw_params,
+	.trigger	= mmp_pcm_trigger,
+	.pointer	= mmp_pcm_pointer,
+	.mmap		= mmp_pcm_mmap,
+	.pcm_construct	= mmp_pcm_new,
+	.pcm_destruct	= mmp_pcm_free_dma_buffers,
 };
 
 static int mmp_pcm_probe(struct platform_device *pdev)
diff --git a/sound/soc/pxa/poodle.c b/sound/soc/pxa/poodle.c
index 48d5c2252b10..59ef04d0467a 100644
--- a/sound/soc/pxa/poodle.c
+++ b/sound/soc/pxa/poodle.c
@@ -56,7 +56,7 @@ static void poodle_ext_control(struct snd_soc_dapm_context *dapm)
 		snd_soc_dapm_disable_pin(dapm, "Headphone Jack");
 	}
 
-	/* set the enpoints to their new connetion states */
+	/* set the endpoints to their new connection states */
 	if (poodle_spk_func == POODLE_SPK_ON)
 		snd_soc_dapm_enable_pin(dapm, "Ext Spk");
 	else
diff --git a/sound/soc/pxa/pxa-ssp.c b/sound/soc/pxa/pxa-ssp.c
index 6c5201431f6e..76fdce54f007 100644
--- a/sound/soc/pxa/pxa-ssp.c
+++ b/sound/soc/pxa/pxa-ssp.c
@@ -869,9 +869,17 @@ static struct snd_soc_dai_driver pxa_ssp_dai = {
 
 static const struct snd_soc_component_driver pxa_ssp_component = {
 	.name		= "pxa-ssp",
-	.ops		= &pxa2xx_pcm_ops,
-	.pcm_new	= pxa2xx_soc_pcm_new,
-	.pcm_free	= pxa2xx_pcm_free_dma_buffers,
+	.pcm_construct	= pxa2xx_soc_pcm_new,
+	.pcm_destruct	= pxa2xx_soc_pcm_free,
+	.open		= pxa2xx_soc_pcm_open,
+	.close		= pxa2xx_soc_pcm_close,
+	.ioctl		= snd_soc_pcm_lib_ioctl,
+	.hw_params	= pxa2xx_soc_pcm_hw_params,
+	.hw_free	= pxa2xx_soc_pcm_hw_free,
+	.prepare	= pxa2xx_soc_pcm_prepare,
+	.trigger	= pxa2xx_soc_pcm_trigger,
+	.pointer	= pxa2xx_soc_pcm_pointer,
+	.mmap		= pxa2xx_soc_pcm_mmap,
 };
 
 #ifdef CONFIG_OF
diff --git a/sound/soc/pxa/pxa2xx-ac97.c b/sound/soc/pxa/pxa2xx-ac97.c
index bf28187315db..31e81a6f616f 100644
--- a/sound/soc/pxa/pxa2xx-ac97.c
+++ b/sound/soc/pxa/pxa2xx-ac97.c
@@ -204,9 +204,17 @@ static struct snd_soc_dai_driver pxa_ac97_dai_driver[] = {
 
 static const struct snd_soc_component_driver pxa_ac97_component = {
 	.name		= "pxa-ac97",
-	.ops		= &pxa2xx_pcm_ops,
-	.pcm_new	= pxa2xx_soc_pcm_new,
-	.pcm_free	= pxa2xx_pcm_free_dma_buffers,
+	.pcm_construct	= pxa2xx_soc_pcm_new,
+	.pcm_destruct	= pxa2xx_soc_pcm_free,
+	.open		= pxa2xx_soc_pcm_open,
+	.close		= pxa2xx_soc_pcm_close,
+	.ioctl		= snd_soc_pcm_lib_ioctl,
+	.hw_params	= pxa2xx_soc_pcm_hw_params,
+	.hw_free	= pxa2xx_soc_pcm_hw_free,
+	.prepare	= pxa2xx_soc_pcm_prepare,
+	.trigger	= pxa2xx_soc_pcm_trigger,
+	.pointer	= pxa2xx_soc_pcm_pointer,
+	.mmap		= pxa2xx_soc_pcm_mmap,
 };
 
 #ifdef CONFIG_OF
diff --git a/sound/soc/pxa/pxa2xx-i2s.c b/sound/soc/pxa/pxa2xx-i2s.c
index 9f7fb7335ac0..e77d707efde7 100644
--- a/sound/soc/pxa/pxa2xx-i2s.c
+++ b/sound/soc/pxa/pxa2xx-i2s.c
@@ -360,9 +360,17 @@ static struct snd_soc_dai_driver pxa_i2s_dai = {
 
 static const struct snd_soc_component_driver pxa_i2s_component = {
 	.name		= "pxa-i2s",
-	.ops		= &pxa2xx_pcm_ops,
-	.pcm_new	= pxa2xx_soc_pcm_new,
-	.pcm_free	= pxa2xx_pcm_free_dma_buffers,
+	.pcm_construct	= pxa2xx_soc_pcm_new,
+	.pcm_destruct	= pxa2xx_soc_pcm_free,
+	.open		= pxa2xx_soc_pcm_open,
+	.close		= pxa2xx_soc_pcm_close,
+	.ioctl		= snd_soc_pcm_lib_ioctl,
+	.hw_params	= pxa2xx_soc_pcm_hw_params,
+	.hw_free	= pxa2xx_soc_pcm_hw_free,
+	.prepare	= pxa2xx_soc_pcm_prepare,
+	.trigger	= pxa2xx_soc_pcm_trigger,
+	.pointer	= pxa2xx_soc_pcm_pointer,
+	.mmap		= pxa2xx_soc_pcm_mmap,
 };
 
 static int pxa2xx_i2s_drv_probe(struct platform_device *pdev)
diff --git a/sound/soc/pxa/pxa2xx-pcm.c b/sound/soc/pxa/pxa2xx-pcm.c
index 74b56fa0870f..07b3455a6f23 100644
--- a/sound/soc/pxa/pxa2xx-pcm.c
+++ b/sound/soc/pxa/pxa2xx-pcm.c
@@ -18,9 +18,17 @@
 #include <sound/dmaengine_pcm.h>
 
 static const struct snd_soc_component_driver pxa2xx_soc_platform = {
-	.ops		= &pxa2xx_pcm_ops,
-	.pcm_new	= pxa2xx_soc_pcm_new,
-	.pcm_free	= pxa2xx_pcm_free_dma_buffers,
+	.pcm_construct	= pxa2xx_soc_pcm_new,
+	.pcm_destruct	= pxa2xx_soc_pcm_free,
+	.open		= pxa2xx_soc_pcm_open,
+	.close		= pxa2xx_soc_pcm_close,
+	.ioctl		= snd_soc_pcm_lib_ioctl,
+	.hw_params	= pxa2xx_soc_pcm_hw_params,
+	.hw_free	= pxa2xx_soc_pcm_hw_free,
+	.prepare	= pxa2xx_soc_pcm_prepare,
+	.trigger	= pxa2xx_soc_pcm_trigger,
+	.pointer	= pxa2xx_soc_pcm_pointer,
+	.mmap		= pxa2xx_soc_pcm_mmap,
 };
 
 static int pxa2xx_soc_platform_probe(struct platform_device *pdev)
diff --git a/sound/soc/qcom/Kconfig b/sound/soc/qcom/Kconfig
index 60086858e920..6530d2462a9e 100644
--- a/sound/soc/qcom/Kconfig
+++ b/sound/soc/qcom/Kconfig
@@ -3,8 +3,8 @@ config SND_SOC_QCOM
 	tristate "ASoC support for QCOM platforms"
 	depends on ARCH_QCOM || COMPILE_TEST
 	help
-          Say Y or M if you want to add support to use audio devices
-          in Qualcomm Technologies SOC-based platforms.
+	  Say Y or M if you want to add support to use audio devices
+	  in Qualcomm Technologies SOC-based platforms.
 
 config SND_SOC_LPASS_CPU
 	tristate
@@ -30,17 +30,17 @@ config SND_SOC_STORM
 	select SND_SOC_LPASS_IPQ806X
 	select SND_SOC_MAX98357A
 	help
-          Say Y or M if you want add support for SoC audio on the
-          Qualcomm Technologies IPQ806X-based Storm board.
+	  Say Y or M if you want add support for SoC audio on the
+	  Qualcomm Technologies IPQ806X-based Storm board.
 
 config SND_SOC_APQ8016_SBC
 	tristate "SoC Audio support for APQ8016 SBC platforms"
 	depends on SND_SOC_QCOM
 	select SND_SOC_LPASS_APQ8016
 	help
-          Support for Qualcomm Technologies LPASS audio block in
-          APQ8016 SOC-based systems.
-          Say Y if you want to use audio devices on MI2S.
+	  Support for Qualcomm Technologies LPASS audio block in
+	  APQ8016 SOC-based systems.
+	  Say Y if you want to use audio devices on MI2S.
 
 config SND_SOC_QCOM_COMMON
 	tristate
@@ -93,9 +93,9 @@ config SND_SOC_MSM8996
 	select SND_SOC_QDSP6
 	select SND_SOC_QCOM_COMMON
 	help
-          Support for Qualcomm Technologies LPASS audio block in
-          APQ8096 SoC-based systems.
-          Say Y if you want to use audio device on this SoCs
+	  Support for Qualcomm Technologies LPASS audio block in
+	  APQ8096 SoC-based systems.
+	  Say Y if you want to use audio device on this SoCs
 
 config SND_SOC_SDM845
 	tristate "SoC Machine driver for SDM845 boards"
diff --git a/sound/soc/qcom/lpass-platform.c b/sound/soc/qcom/lpass-platform.c
index 4c745baa39f7..2e8892316423 100644
--- a/sound/soc/qcom/lpass-platform.c
+++ b/sound/soc/qcom/lpass-platform.c
@@ -50,12 +50,12 @@ static const struct snd_pcm_hardware lpass_platform_pcm_hardware = {
 	.fifo_size		=	0,
 };
 
-static int lpass_platform_pcmops_open(struct snd_pcm_substream *substream)
+static int lpass_platform_pcmops_open(struct snd_soc_component *component,
+				      struct snd_pcm_substream *substream)
 {
 	struct snd_pcm_runtime *runtime = substream->runtime;
 	struct snd_soc_pcm_runtime *soc_runtime = substream->private_data;
 	struct snd_soc_dai *cpu_dai = soc_runtime->cpu_dai;
-	struct snd_soc_component *component = snd_soc_rtdcom_lookup(soc_runtime, DRV_NAME);
 	struct lpass_data *drvdata = snd_soc_component_get_drvdata(component);
 	struct lpass_variant *v = drvdata->variant;
 	int ret, dma_ch, dir = substream->stream;
@@ -105,11 +105,10 @@ static int lpass_platform_pcmops_open(struct snd_pcm_substream *substream)
 	return 0;
 }
 
-static int lpass_platform_pcmops_close(struct snd_pcm_substream *substream)
+static int lpass_platform_pcmops_close(struct snd_soc_component *component,
+				       struct snd_pcm_substream *substream)
 {
 	struct snd_pcm_runtime *runtime = substream->runtime;
-	struct snd_soc_pcm_runtime *soc_runtime = substream->private_data;
-	struct snd_soc_component *component = snd_soc_rtdcom_lookup(soc_runtime, DRV_NAME);
 	struct lpass_data *drvdata = snd_soc_component_get_drvdata(component);
 	struct lpass_variant *v = drvdata->variant;
 	struct lpass_pcm_data *data;
@@ -122,11 +121,11 @@ static int lpass_platform_pcmops_close(struct snd_pcm_substream *substream)
 	return 0;
 }
 
-static int lpass_platform_pcmops_hw_params(struct snd_pcm_substream *substream,
-		struct snd_pcm_hw_params *params)
+static int lpass_platform_pcmops_hw_params(struct snd_soc_component *component,
+					   struct snd_pcm_substream *substream,
+					   struct snd_pcm_hw_params *params)
 {
 	struct snd_soc_pcm_runtime *soc_runtime = substream->private_data;
-	struct snd_soc_component *component = snd_soc_rtdcom_lookup(soc_runtime, DRV_NAME);
 	struct lpass_data *drvdata = snd_soc_component_get_drvdata(component);
 	struct snd_pcm_runtime *rt = substream->runtime;
 	struct lpass_pcm_data *pcm_data = rt->private_data;
@@ -216,10 +215,10 @@ static int lpass_platform_pcmops_hw_params(struct snd_pcm_substream *substream,
 	return 0;
 }
 
-static int lpass_platform_pcmops_hw_free(struct snd_pcm_substream *substream)
+static int lpass_platform_pcmops_hw_free(struct snd_soc_component *component,
+					 struct snd_pcm_substream *substream)
 {
 	struct snd_soc_pcm_runtime *soc_runtime = substream->private_data;
-	struct snd_soc_component *component = snd_soc_rtdcom_lookup(soc_runtime, DRV_NAME);
 	struct lpass_data *drvdata = snd_soc_component_get_drvdata(component);
 	struct snd_pcm_runtime *rt = substream->runtime;
 	struct lpass_pcm_data *pcm_data = rt->private_data;
@@ -236,11 +235,11 @@ static int lpass_platform_pcmops_hw_free(struct snd_pcm_substream *substream)
 	return ret;
 }
 
-static int lpass_platform_pcmops_prepare(struct snd_pcm_substream *substream)
+static int lpass_platform_pcmops_prepare(struct snd_soc_component *component,
+					 struct snd_pcm_substream *substream)
 {
 	struct snd_pcm_runtime *runtime = substream->runtime;
 	struct snd_soc_pcm_runtime *soc_runtime = substream->private_data;
-	struct snd_soc_component *component = snd_soc_rtdcom_lookup(soc_runtime, DRV_NAME);
 	struct lpass_data *drvdata = snd_soc_component_get_drvdata(component);
 	struct snd_pcm_runtime *rt = substream->runtime;
 	struct lpass_pcm_data *pcm_data = rt->private_data;
@@ -288,11 +287,11 @@ static int lpass_platform_pcmops_prepare(struct snd_pcm_substream *substream)
 	return 0;
 }
 
-static int lpass_platform_pcmops_trigger(struct snd_pcm_substream *substream,
-		int cmd)
+static int lpass_platform_pcmops_trigger(struct snd_soc_component *component,
+					 struct snd_pcm_substream *substream,
+					 int cmd)
 {
 	struct snd_soc_pcm_runtime *soc_runtime = substream->private_data;
-	struct snd_soc_component *component = snd_soc_rtdcom_lookup(soc_runtime, DRV_NAME);
 	struct lpass_data *drvdata = snd_soc_component_get_drvdata(component);
 	struct snd_pcm_runtime *rt = substream->runtime;
 	struct lpass_pcm_data *pcm_data = rt->private_data;
@@ -363,10 +362,10 @@ static int lpass_platform_pcmops_trigger(struct snd_pcm_substream *substream,
 }
 
 static snd_pcm_uframes_t lpass_platform_pcmops_pointer(
+		struct snd_soc_component *component,
 		struct snd_pcm_substream *substream)
 {
 	struct snd_soc_pcm_runtime *soc_runtime = substream->private_data;
-	struct snd_soc_component *component = snd_soc_rtdcom_lookup(soc_runtime, DRV_NAME);
 	struct lpass_data *drvdata = snd_soc_component_get_drvdata(component);
 	struct snd_pcm_runtime *rt = substream->runtime;
 	struct lpass_pcm_data *pcm_data = rt->private_data;
@@ -395,8 +394,9 @@ static snd_pcm_uframes_t lpass_platform_pcmops_pointer(
 	return bytes_to_frames(substream->runtime, curr_addr - base_addr);
 }
 
-static int lpass_platform_pcmops_mmap(struct snd_pcm_substream *substream,
-		struct vm_area_struct *vma)
+static int lpass_platform_pcmops_mmap(struct snd_soc_component *component,
+				      struct snd_pcm_substream *substream,
+				      struct vm_area_struct *vma)
 {
 	struct snd_pcm_runtime *runtime = substream->runtime;
 
@@ -405,18 +405,6 @@ static int lpass_platform_pcmops_mmap(struct snd_pcm_substream *substream,
 			runtime->dma_bytes);
 }
 
-static const struct snd_pcm_ops lpass_platform_pcm_ops = {
-	.open		= lpass_platform_pcmops_open,
-	.close		= lpass_platform_pcmops_close,
-	.ioctl		= snd_pcm_lib_ioctl,
-	.hw_params	= lpass_platform_pcmops_hw_params,
-	.hw_free	= lpass_platform_pcmops_hw_free,
-	.prepare	= lpass_platform_pcmops_prepare,
-	.trigger	= lpass_platform_pcmops_trigger,
-	.pointer	= lpass_platform_pcmops_pointer,
-	.mmap		= lpass_platform_pcmops_mmap,
-};
-
 static irqreturn_t lpass_dma_interrupt_handler(
 			struct snd_pcm_substream *substream,
 			struct lpass_data *drvdata,
@@ -499,11 +487,11 @@ static irqreturn_t lpass_platform_lpaif_irq(int irq, void *data)
 	return IRQ_HANDLED;
 }
 
-static int lpass_platform_pcm_new(struct snd_soc_pcm_runtime *soc_runtime)
+static int lpass_platform_pcm_new(struct snd_soc_component *component,
+				  struct snd_soc_pcm_runtime *soc_runtime)
 {
 	struct snd_pcm *pcm = soc_runtime->pcm;
 	struct snd_pcm_substream *psubstream, *csubstream;
-	struct snd_soc_component *component = snd_soc_rtdcom_lookup(soc_runtime, DRV_NAME);
 	int ret = -EINVAL;
 	size_t size = lpass_platform_pcm_hardware.buffer_bytes_max;
 
@@ -535,7 +523,8 @@ static int lpass_platform_pcm_new(struct snd_soc_pcm_runtime *soc_runtime)
 	return 0;
 }
 
-static void lpass_platform_pcm_free(struct snd_pcm *pcm)
+static void lpass_platform_pcm_free(struct snd_soc_component *component,
+				    struct snd_pcm *pcm)
 {
 	struct snd_pcm_substream *substream;
 	int i;
@@ -552,9 +541,18 @@ static void lpass_platform_pcm_free(struct snd_pcm *pcm)
 
 static const struct snd_soc_component_driver lpass_component_driver = {
 	.name		= DRV_NAME,
-	.pcm_new	= lpass_platform_pcm_new,
-	.pcm_free	= lpass_platform_pcm_free,
-	.ops		= &lpass_platform_pcm_ops,
+	.open		= lpass_platform_pcmops_open,
+	.close		= lpass_platform_pcmops_close,
+	.ioctl		= snd_soc_pcm_lib_ioctl,
+	.hw_params	= lpass_platform_pcmops_hw_params,
+	.hw_free	= lpass_platform_pcmops_hw_free,
+	.prepare	= lpass_platform_pcmops_prepare,
+	.trigger	= lpass_platform_pcmops_trigger,
+	.pointer	= lpass_platform_pcmops_pointer,
+	.mmap		= lpass_platform_pcmops_mmap,
+	.pcm_construct	= lpass_platform_pcm_new,
+	.pcm_destruct	= lpass_platform_pcm_free,
+
 };
 
 int asoc_qcom_lpass_platform_register(struct platform_device *pdev)
diff --git a/sound/soc/qcom/qdsp6/q6asm-dai.c b/sound/soc/qcom/qdsp6/q6asm-dai.c
index 548eb4fa2da6..8150c10f081e 100644
--- a/sound/soc/qcom/qdsp6/q6asm-dai.c
+++ b/sound/soc/qcom/qdsp6/q6asm-dai.c
@@ -206,16 +206,16 @@ static void event_handler(uint32_t opcode, uint32_t token,
 	}
 }
 
-static int q6asm_dai_prepare(struct snd_pcm_substream *substream)
+static int q6asm_dai_prepare(struct snd_soc_component *component,
+			     struct snd_pcm_substream *substream)
 {
 	struct snd_pcm_runtime *runtime = substream->runtime;
 	struct snd_soc_pcm_runtime *soc_prtd = substream->private_data;
 	struct q6asm_dai_rtd *prtd = runtime->private_data;
-	struct snd_soc_component *c = snd_soc_rtdcom_lookup(soc_prtd, DRV_NAME);
 	struct q6asm_dai_data *pdata;
 	int ret, i;
 
-	pdata = snd_soc_component_get_drvdata(c);
+	pdata = snd_soc_component_get_drvdata(component);
 	if (!pdata)
 		return -EINVAL;
 
@@ -294,7 +294,8 @@ static int q6asm_dai_prepare(struct snd_pcm_substream *substream)
 	return 0;
 }
 
-static int q6asm_dai_trigger(struct snd_pcm_substream *substream, int cmd)
+static int q6asm_dai_trigger(struct snd_soc_component *component,
+			     struct snd_pcm_substream *substream, int cmd)
 {
 	int ret = 0;
 	struct snd_pcm_runtime *runtime = substream->runtime;
@@ -322,21 +323,21 @@ static int q6asm_dai_trigger(struct snd_pcm_substream *substream, int cmd)
 	return ret;
 }
 
-static int q6asm_dai_open(struct snd_pcm_substream *substream)
+static int q6asm_dai_open(struct snd_soc_component *component,
+			  struct snd_pcm_substream *substream)
 {
 	struct snd_pcm_runtime *runtime = substream->runtime;
 	struct snd_soc_pcm_runtime *soc_prtd = substream->private_data;
 	struct snd_soc_dai *cpu_dai = soc_prtd->cpu_dai;
-	struct snd_soc_component *c = snd_soc_rtdcom_lookup(soc_prtd, DRV_NAME);
 	struct q6asm_dai_rtd *prtd;
 	struct q6asm_dai_data *pdata;
-	struct device *dev = c->dev;
+	struct device *dev = component->dev;
 	int ret = 0;
 	int stream_id;
 
 	stream_id = cpu_dai->driver->id;
 
-	pdata = snd_soc_component_get_drvdata(c);
+	pdata = snd_soc_component_get_drvdata(component);
 	if (!pdata) {
 		pr_err("Drv data not found ..\n");
 		return -EINVAL;
@@ -414,7 +415,8 @@ static int q6asm_dai_open(struct snd_pcm_substream *substream)
 	return 0;
 }
 
-static int q6asm_dai_close(struct snd_pcm_substream *substream)
+static int q6asm_dai_close(struct snd_soc_component *component,
+			   struct snd_pcm_substream *substream)
 {
 	struct snd_pcm_runtime *runtime = substream->runtime;
 	struct snd_soc_pcm_runtime *soc_prtd = substream->private_data;
@@ -435,7 +437,8 @@ static int q6asm_dai_close(struct snd_pcm_substream *substream)
 	return 0;
 }
 
-static snd_pcm_uframes_t q6asm_dai_pointer(struct snd_pcm_substream *substream)
+static snd_pcm_uframes_t q6asm_dai_pointer(struct snd_soc_component *component,
+					   struct snd_pcm_substream *substream)
 {
 
 	struct snd_pcm_runtime *runtime = substream->runtime;
@@ -447,22 +450,21 @@ static snd_pcm_uframes_t q6asm_dai_pointer(struct snd_pcm_substream *substream)
 	return bytes_to_frames(runtime, (prtd->pcm_irq_pos));
 }
 
-static int q6asm_dai_mmap(struct snd_pcm_substream *substream,
-				struct vm_area_struct *vma)
+static int q6asm_dai_mmap(struct snd_soc_component *component,
+			  struct snd_pcm_substream *substream,
+			  struct vm_area_struct *vma)
 {
-
 	struct snd_pcm_runtime *runtime = substream->runtime;
-	struct snd_soc_pcm_runtime *soc_prtd = substream->private_data;
-	struct snd_soc_component *c = snd_soc_rtdcom_lookup(soc_prtd, DRV_NAME);
-	struct device *dev = c->dev;
+	struct device *dev = component->dev;
 
 	return dma_mmap_coherent(dev, vma,
 			runtime->dma_area, runtime->dma_addr,
 			runtime->dma_bytes);
 }
 
-static int q6asm_dai_hw_params(struct snd_pcm_substream *substream,
-				struct snd_pcm_hw_params *params)
+static int q6asm_dai_hw_params(struct snd_soc_component *component,
+			       struct snd_pcm_substream *substream,
+			       struct snd_pcm_hw_params *params)
 {
 	struct snd_pcm_runtime *runtime = substream->runtime;
 	struct q6asm_dai_rtd *prtd = runtime->private_data;
@@ -482,17 +484,6 @@ static int q6asm_dai_hw_params(struct snd_pcm_substream *substream,
 	return 0;
 }
 
-static struct snd_pcm_ops q6asm_dai_ops = {
-	.open           = q6asm_dai_open,
-	.hw_params	= q6asm_dai_hw_params,
-	.close          = q6asm_dai_close,
-	.ioctl          = snd_pcm_lib_ioctl,
-	.prepare        = q6asm_dai_prepare,
-	.trigger        = q6asm_dai_trigger,
-	.pointer        = q6asm_dai_pointer,
-	.mmap		= q6asm_dai_mmap,
-};
-
 static void compress_event_handler(uint32_t opcode, uint32_t token,
 				   uint32_t *payload, void *priv)
 {
@@ -635,8 +626,14 @@ static int q6asm_dai_compr_set_params(struct snd_compr_stream *stream,
 	struct snd_soc_component *c = snd_soc_rtdcom_lookup(rtd, DRV_NAME);
 	int dir = stream->direction;
 	struct q6asm_dai_data *pdata;
+	struct q6asm_flac_cfg flac_cfg;
 	struct device *dev = c->dev;
 	int ret;
+	union snd_codec_options *codec_options;
+	struct snd_dec_flac *flac;
+
+	codec_options = &(prtd->codec_param.codec.options);
+
 
 	memcpy(&prtd->codec_param, params, sizeof(*params));
 
@@ -673,6 +670,32 @@ static int q6asm_dai_compr_set_params(struct snd_compr_stream *stream,
 		return ret;
 	}
 
+	switch (params->codec.id) {
+	case SND_AUDIOCODEC_FLAC:
+
+		memset(&flac_cfg, 0x0, sizeof(struct q6asm_flac_cfg));
+		flac = &codec_options->flac_d;
+
+		flac_cfg.ch_cfg = params->codec.ch_in;
+		flac_cfg.sample_rate =  params->codec.sample_rate;
+		flac_cfg.stream_info_present = 1;
+		flac_cfg.sample_size = flac->sample_size;
+		flac_cfg.min_blk_size = flac->min_blk_size;
+		flac_cfg.max_blk_size = flac->max_blk_size;
+		flac_cfg.max_frame_size = flac->max_frame_size;
+		flac_cfg.min_frame_size = flac->min_frame_size;
+
+		ret = q6asm_stream_media_format_block_flac(prtd->audio_client,
+							   &flac_cfg);
+		if (ret < 0) {
+			dev_err(dev, "FLAC CMD Format block failed:%d\n", ret);
+			return -EIO;
+		}
+		break;
+	default:
+		break;
+	}
+
 	ret = q6asm_map_memory_regions(dir, prtd->audio_client, prtd->phys,
 				       (prtd->pcm_size / prtd->periods),
 				       prtd->periods);
@@ -768,8 +791,9 @@ static int q6asm_dai_compr_get_caps(struct snd_compr_stream *stream,
 	caps->max_fragment_size = COMPR_PLAYBACK_MAX_FRAGMENT_SIZE;
 	caps->min_fragments = COMPR_PLAYBACK_MIN_NUM_FRAGMENTS;
 	caps->max_fragments = COMPR_PLAYBACK_MAX_NUM_FRAGMENTS;
-	caps->num_codecs = 1;
+	caps->num_codecs = 2;
 	caps->codecs[0] = SND_AUDIOCODEC_MP3;
+	caps->codecs[1] = SND_AUDIOCODEC_FLAC;
 
 	return 0;
 }
@@ -800,15 +824,15 @@ static struct snd_compr_ops q6asm_dai_compr_ops = {
 	.ack		= q6asm_dai_compr_ack,
 };
 
-static int q6asm_dai_pcm_new(struct snd_soc_pcm_runtime *rtd)
+static int q6asm_dai_pcm_new(struct snd_soc_component *component,
+			     struct snd_soc_pcm_runtime *rtd)
 {
 	struct snd_pcm_substream *psubstream, *csubstream;
-	struct snd_soc_component *c = snd_soc_rtdcom_lookup(rtd, DRV_NAME);
 	struct snd_pcm *pcm = rtd->pcm;
 	struct device *dev;
 	int size, ret;
 
-	dev = c->dev;
+	dev = component->dev;
 	size = q6asm_dai_hardware_playback.buffer_bytes_max;
 	psubstream = pcm->streams[SNDRV_PCM_STREAM_PLAYBACK].substream;
 	if (psubstream) {
@@ -835,7 +859,8 @@ static int q6asm_dai_pcm_new(struct snd_soc_pcm_runtime *rtd)
 	return 0;
 }
 
-static void q6asm_dai_pcm_free(struct snd_pcm *pcm)
+static void q6asm_dai_pcm_free(struct snd_soc_component *component,
+			       struct snd_pcm *pcm)
 {
 	struct snd_pcm_substream *substream;
 	int i;
@@ -852,9 +877,16 @@ static void q6asm_dai_pcm_free(struct snd_pcm *pcm)
 
 static const struct snd_soc_component_driver q6asm_fe_dai_component = {
 	.name		= DRV_NAME,
-	.ops		= &q6asm_dai_ops,
-	.pcm_new	= q6asm_dai_pcm_new,
-	.pcm_free	= q6asm_dai_pcm_free,
+	.open		= q6asm_dai_open,
+	.hw_params	= q6asm_dai_hw_params,
+	.close		= q6asm_dai_close,
+	.ioctl		= snd_soc_pcm_lib_ioctl,
+	.prepare	= q6asm_dai_prepare,
+	.trigger	= q6asm_dai_trigger,
+	.pointer	= q6asm_dai_pointer,
+	.mmap		= q6asm_dai_mmap,
+	.pcm_construct	= q6asm_dai_pcm_new,
+	.pcm_destruct	= q6asm_dai_pcm_free,
 	.compr_ops	= &q6asm_dai_compr_ops,
 };
 
diff --git a/sound/soc/qcom/qdsp6/q6asm.c b/sound/soc/qcom/qdsp6/q6asm.c
index e8141a33a55e..36e0eab13a98 100644
--- a/sound/soc/qcom/qdsp6/q6asm.c
+++ b/sound/soc/qcom/qdsp6/q6asm.c
@@ -38,6 +38,7 @@
 #define ASM_SESSION_CMD_RUN_V2			0x00010DAA
 #define ASM_MEDIA_FMT_MULTI_CHANNEL_PCM_V2	0x00010DA5
 #define ASM_MEDIA_FMT_MP3			0x00010BE9
+#define ASM_MEDIA_FMT_FLAC			0x00010C16
 #define ASM_DATA_CMD_WRITE_V2			0x00010DAB
 #define ASM_DATA_CMD_READ_V2			0x00010DAC
 #define ASM_SESSION_CMD_SUSPEND			0x00010DEC
@@ -89,6 +90,20 @@ struct asm_multi_channel_pcm_fmt_blk_v2 {
 	u8 channel_mapping[PCM_MAX_NUM_CHANNEL];
 } __packed;
 
+struct asm_flac_fmt_blk_v2 {
+	struct asm_data_cmd_media_fmt_update_v2 fmt_blk;
+	u16 is_stream_info_present;
+	u16 num_channels;
+	u16 min_blk_size;
+	u16 max_blk_size;
+	u16 md5_sum[8];
+	u32 sample_rate;
+	u32 min_frame_size;
+	u32 max_frame_size;
+	u16 sample_size;
+	u16 reserved;
+} __packed;
+
 struct asm_stream_cmd_set_encdec_param {
 	u32                  param_id;
 	u32                  param_size;
@@ -876,6 +891,9 @@ int q6asm_open_write(struct audio_client *ac, uint32_t format,
 	case FORMAT_LINEAR_PCM:
 		open->dec_fmt_id = ASM_MEDIA_FMT_MULTI_CHANNEL_PCM_V2;
 		break;
+	case SND_AUDIOCODEC_FLAC:
+		open->dec_fmt_id = ASM_MEDIA_FMT_FLAC;
+		break;
 	default:
 		dev_err(ac->dev, "Invalid format 0x%x\n", format);
 		rc = -EINVAL;
@@ -1021,6 +1039,42 @@ err:
 }
 EXPORT_SYMBOL_GPL(q6asm_media_format_block_multi_ch_pcm);
 
+
+int q6asm_stream_media_format_block_flac(struct audio_client *ac,
+					 struct q6asm_flac_cfg *cfg)
+{
+	struct asm_flac_fmt_blk_v2 *fmt;
+	struct apr_pkt *pkt;
+	void *p;
+	int rc, pkt_size;
+
+	pkt_size = APR_HDR_SIZE + sizeof(*fmt);
+	p = kzalloc(pkt_size, GFP_KERNEL);
+	if (!p)
+		return -ENOMEM;
+
+	pkt = p;
+	fmt = p + APR_HDR_SIZE;
+
+	q6asm_add_hdr(ac, &pkt->hdr, pkt_size, true, ac->stream_id);
+
+	pkt->hdr.opcode = ASM_DATA_CMD_MEDIA_FMT_UPDATE_V2;
+	fmt->fmt_blk.fmt_blk_size = sizeof(*fmt) - sizeof(fmt->fmt_blk);
+	fmt->is_stream_info_present = cfg->stream_info_present;
+	fmt->num_channels = cfg->ch_cfg;
+	fmt->min_blk_size = cfg->min_blk_size;
+	fmt->max_blk_size = cfg->max_blk_size;
+	fmt->sample_rate = cfg->sample_rate;
+	fmt->min_frame_size = cfg->min_frame_size;
+	fmt->max_frame_size = cfg->max_frame_size;
+	fmt->sample_size = cfg->sample_size;
+
+	rc = q6asm_ac_send_cmd_sync(ac, pkt);
+	kfree(pkt);
+
+	return rc;
+}
+EXPORT_SYMBOL_GPL(q6asm_stream_media_format_block_flac);
 /**
  * q6asm_enc_cfg_blk_pcm_format_support() - setup pcm configuration for capture
  *
@@ -1075,6 +1129,7 @@ err:
 }
 EXPORT_SYMBOL_GPL(q6asm_enc_cfg_blk_pcm_format_support);
 
+
 /**
  * q6asm_read() - read data of period size from audio client
  *
diff --git a/sound/soc/qcom/qdsp6/q6asm.h b/sound/soc/qcom/qdsp6/q6asm.h
index 9f5fb573e4a0..6764f55f7078 100644
--- a/sound/soc/qcom/qdsp6/q6asm.h
+++ b/sound/soc/qcom/qdsp6/q6asm.h
@@ -32,6 +32,19 @@ enum {
 #define NO_TIMESTAMP    0xFF00
 #define FORMAT_LINEAR_PCM   0x0000
 
+struct q6asm_flac_cfg {
+        u32 sample_rate;
+        u32 ext_sample_rate;
+        u32 min_frame_size;
+        u32 max_frame_size;
+        u16 stream_info_present;
+        u16 min_blk_size;
+        u16 max_blk_size;
+        u16 ch_cfg;
+        u16 sample_size;
+        u16 md5_sum;
+};
+
 typedef void (*q6asm_cb) (uint32_t opcode, uint32_t token,
 			  void *payload, void *priv);
 struct audio_client;
@@ -54,6 +67,8 @@ int q6asm_media_format_block_multi_ch_pcm(struct audio_client *ac,
 					  uint32_t rate, uint32_t channels,
 					  u8 channel_map[PCM_MAX_NUM_CHANNEL],
 					  uint16_t bits_per_sample);
+int q6asm_stream_media_format_block_flac(struct audio_client *ac,
+					 struct q6asm_flac_cfg *cfg);
 int q6asm_run(struct audio_client *ac, uint32_t flags, uint32_t msw_ts,
 	      uint32_t lsw_ts);
 int q6asm_run_nowait(struct audio_client *ac, uint32_t flags, uint32_t msw_ts,
diff --git a/sound/soc/qcom/qdsp6/q6routing.c b/sound/soc/qcom/qdsp6/q6routing.c
index ddcd9978cf57..20724102e85a 100644
--- a/sound/soc/qcom/qdsp6/q6routing.c
+++ b/sound/soc/qcom/qdsp6/q6routing.c
@@ -939,12 +939,12 @@ static const struct snd_soc_dapm_route intercon[] = {
 
 };
 
-static int routing_hw_params(struct snd_pcm_substream *substream,
-				     struct snd_pcm_hw_params *params)
+static int routing_hw_params(struct snd_soc_component *component,
+			     struct snd_pcm_substream *substream,
+			     struct snd_pcm_hw_params *params)
 {
 	struct snd_soc_pcm_runtime *rtd = substream->private_data;
-	struct snd_soc_component *c = snd_soc_rtdcom_lookup(rtd, DRV_NAME);
-	struct msm_routing_data *data = dev_get_drvdata(c->dev);
+	struct msm_routing_data *data = dev_get_drvdata(component->dev);
 	unsigned int be_id = rtd->cpu_dai->id;
 	struct session_data *session;
 	int path_type;
@@ -980,10 +980,6 @@ static int routing_hw_params(struct snd_pcm_substream *substream,
 	return 0;
 }
 
-static struct snd_pcm_ops q6pcm_routing_ops = {
-	.hw_params = routing_hw_params,
-};
-
 static int msm_routing_probe(struct snd_soc_component *c)
 {
 	int i;
@@ -997,9 +993,9 @@ static int msm_routing_probe(struct snd_soc_component *c)
 }
 
 static const struct snd_soc_component_driver msm_soc_routing_component = {
-	.ops = &q6pcm_routing_ops,
 	.probe = msm_routing_probe,
 	.name = DRV_NAME,
+	.hw_params = routing_hw_params,
 	.dapm_widgets = msm_qdsp6_widgets,
 	.num_dapm_widgets = ARRAY_SIZE(msm_qdsp6_widgets),
 	.dapm_routes = intercon,
diff --git a/sound/soc/rockchip/Kconfig b/sound/soc/rockchip/Kconfig
index b43657e6e655..d610b553ea3b 100644
--- a/sound/soc/rockchip/Kconfig
+++ b/sound/soc/rockchip/Kconfig
@@ -40,9 +40,10 @@ config SND_SOC_ROCKCHIP_MAX98090
 	select SND_SOC_ROCKCHIP_I2S
 	select SND_SOC_MAX98090
 	select SND_SOC_TS3A227E
+	select SND_SOC_HDMI_CODEC
 	help
 	  Say Y or M here if you want to add support for SoC audio on Rockchip
-	  boards using the MAX98090 codec, such as Veyron.
+	  boards using the MAX98090 codec and HDMI codec, such as Veyron.
 
 config SND_SOC_ROCKCHIP_RT5645
 	tristate "ASoC support for Rockchip boards using a RT5645/RT5650 codec"
diff --git a/sound/soc/rockchip/rockchip_max98090.c b/sound/soc/rockchip/rockchip_max98090.c
index e80b09143b63..60930fa85aa4 100644
--- a/sound/soc/rockchip/rockchip_max98090.c
+++ b/sound/soc/rockchip/rockchip_max98090.c
@@ -6,11 +6,13 @@
  */
 
 #include <linux/module.h>
+#include <linux/of_device.h>
 #include <linux/platform_device.h>
 #include <linux/slab.h>
 #include <linux/gpio.h>
 #include <linux/of_gpio.h>
 #include <sound/core.h>
+#include <sound/hdmi-codec.h>
 #include <sound/jack.h>
 #include <sound/pcm.h>
 #include <sound/pcm_params.h>
@@ -36,28 +38,73 @@ static struct snd_soc_jack_pin headset_jack_pins[] = {
 
 };
 
-static const struct snd_soc_dapm_widget rk_dapm_widgets[] = {
-	SND_SOC_DAPM_HP("Headphone", NULL),
-	SND_SOC_DAPM_MIC("Headset Mic", NULL),
-	SND_SOC_DAPM_MIC("Int Mic", NULL),
-	SND_SOC_DAPM_SPK("Speaker", NULL),
+#define RK_MAX98090_WIDGETS \
+	SND_SOC_DAPM_HP("Headphone", NULL), \
+	SND_SOC_DAPM_MIC("Headset Mic", NULL), \
+	SND_SOC_DAPM_MIC("Int Mic", NULL), \
+	SND_SOC_DAPM_SPK("Speaker", NULL)
+
+#define RK_HDMI_WIDGETS \
+	SND_SOC_DAPM_LINE("HDMI", NULL)
+
+static const struct snd_soc_dapm_widget rk_max98090_dapm_widgets[] = {
+	RK_MAX98090_WIDGETS,
+};
+
+static const struct snd_soc_dapm_widget rk_hdmi_dapm_widgets[] = {
+	RK_HDMI_WIDGETS,
+};
+
+static const struct snd_soc_dapm_widget rk_max98090_hdmi_dapm_widgets[] = {
+	RK_MAX98090_WIDGETS,
+	RK_HDMI_WIDGETS,
+};
+
+#define RK_MAX98090_AUDIO_MAP \
+	{"IN34", NULL, "Headset Mic"}, \
+	{"Headset Mic", NULL, "MICBIAS"}, \
+	{"DMICL", NULL, "Int Mic"}, \
+	{"Headphone", NULL, "HPL"}, \
+	{"Headphone", NULL, "HPR"}, \
+	{"Speaker", NULL, "SPKL"}, \
+	{"Speaker", NULL, "SPKR"}
+
+#define RK_HDMI_AUDIO_MAP \
+	{"HDMI", NULL, "TX"}
+
+static const struct snd_soc_dapm_route rk_max98090_audio_map[] = {
+	RK_MAX98090_AUDIO_MAP,
+};
+
+static const struct snd_soc_dapm_route rk_hdmi_audio_map[] = {
+	RK_HDMI_AUDIO_MAP,
+};
+
+static const struct snd_soc_dapm_route rk_max98090_hdmi_audio_map[] = {
+	RK_MAX98090_AUDIO_MAP,
+	RK_HDMI_AUDIO_MAP,
+};
+
+#define RK_MAX98090_CONTROLS \
+	SOC_DAPM_PIN_SWITCH("Headphone"), \
+	SOC_DAPM_PIN_SWITCH("Headset Mic"), \
+	SOC_DAPM_PIN_SWITCH("Int Mic"), \
+	SOC_DAPM_PIN_SWITCH("Speaker")
+
+#define RK_HDMI_CONTROLS \
+	SOC_DAPM_PIN_SWITCH("HDMI")
+
+static const struct snd_kcontrol_new rk_max98090_controls[] = {
+	RK_MAX98090_CONTROLS,
 };
 
-static const struct snd_soc_dapm_route rk_audio_map[] = {
-	{"IN34", NULL, "Headset Mic"},
-	{"Headset Mic", NULL, "MICBIAS"},
-	{"DMICL", NULL, "Int Mic"},
-	{"Headphone", NULL, "HPL"},
-	{"Headphone", NULL, "HPR"},
-	{"Speaker", NULL, "SPKL"},
-	{"Speaker", NULL, "SPKR"},
+static const struct snd_kcontrol_new rk_hdmi_controls[] = {
+	RK_HDMI_CONTROLS,
 };
 
-static const struct snd_kcontrol_new rk_mc_controls[] = {
-	SOC_DAPM_PIN_SWITCH("Headphone"),
-	SOC_DAPM_PIN_SWITCH("Headset Mic"),
-	SOC_DAPM_PIN_SWITCH("Int Mic"),
-	SOC_DAPM_PIN_SWITCH("Speaker"),
+static const struct snd_kcontrol_new rk_max98090_hdmi_controls[] = {
+	RK_MAX98090_CONTROLS,
+	RK_HDMI_CONTROLS,
 };
 
 static int rk_jack_event(struct notifier_block *nb, unsigned long event,
@@ -125,15 +172,20 @@ static int rk_aif1_hw_params(struct snd_pcm_substream *substream,
 
 	ret = snd_soc_dai_set_sysclk(cpu_dai, 0, mclk,
 				     SND_SOC_CLOCK_OUT);
-	if (ret < 0) {
-		dev_err(codec_dai->dev, "Can't set codec clock %d\n", ret);
+	if (ret) {
+		dev_err(cpu_dai->dev, "Can't set cpu dai clock %d\n", ret);
 		return ret;
 	}
 
 	ret = snd_soc_dai_set_sysclk(codec_dai, 0, mclk,
 				     SND_SOC_CLOCK_IN);
-	if (ret < 0) {
-		dev_err(codec_dai->dev, "Can't set codec clock %d\n", ret);
+
+	/* HDMI codec dai does not need to set sysclk. */
+	if (!strcmp(rtd->dai_link->name, "HDMI"))
+		return 0;
+
+	if (ret) {
+		dev_err(codec_dai->dev, "Can't set codec dai clock %d\n", ret);
 		return ret;
 	}
 
@@ -155,20 +207,88 @@ static const struct snd_soc_ops rk_aif1_ops = {
 	.startup = rk_aif1_startup,
 };
 
-SND_SOC_DAILINK_DEFS(hifi,
-	DAILINK_COMP_ARRAY(COMP_EMPTY()),
-	DAILINK_COMP_ARRAY(COMP_CODEC(NULL, "HiFi")),
-	DAILINK_COMP_ARRAY(COMP_EMPTY()));
-
-static struct snd_soc_dai_link rk_dailink = {
-	.name = "max98090",
-	.stream_name = "Audio",
-	.init = rk_init,
-	.ops = &rk_aif1_ops,
-	/* set max98090 as slave */
-	.dai_fmt = SND_SOC_DAIFMT_I2S | SND_SOC_DAIFMT_NB_NF |
-		SND_SOC_DAIFMT_CBS_CFS,
-	SND_SOC_DAILINK_REG(hifi),
+SND_SOC_DAILINK_DEFS(analog,
+		     DAILINK_COMP_ARRAY(COMP_EMPTY()),
+		     DAILINK_COMP_ARRAY(COMP_CODEC(NULL, "HiFi")),
+		     DAILINK_COMP_ARRAY(COMP_EMPTY()));
+
+SND_SOC_DAILINK_DEFS(hdmi,
+		     DAILINK_COMP_ARRAY(COMP_EMPTY()),
+		     DAILINK_COMP_ARRAY(COMP_CODEC(NULL, "i2s-hifi")),
+		     DAILINK_COMP_ARRAY(COMP_EMPTY()));
+
+enum {
+	DAILINK_MAX98090,
+	DAILINK_HDMI,
+};
+
+static struct snd_soc_jack rk_hdmi_jack;
+
+static int rk_hdmi_init(struct snd_soc_pcm_runtime *runtime)
+{
+	struct snd_soc_card *card = runtime->card;
+	struct snd_soc_component *component = runtime->codec_dai->component;
+	int ret;
+
+	/* enable jack detection */
+	ret = snd_soc_card_jack_new(card, "HDMI Jack", SND_JACK_LINEOUT,
+				    &rk_hdmi_jack, NULL, 0);
+	if (ret) {
+		dev_err(card->dev, "Can't new HDMI Jack %d\n", ret);
+		return ret;
+	}
+
+	return hdmi_codec_set_jack_detect(component, &rk_hdmi_jack);
+}
+
+/* max98090 dai_link */
+static struct snd_soc_dai_link rk_max98090_dailinks[] = {
+	{
+		.name = "max98090",
+		.stream_name = "Analog",
+		.init = rk_init,
+		.ops = &rk_aif1_ops,
+		/* set max98090 as slave */
+		.dai_fmt = SND_SOC_DAIFMT_I2S | SND_SOC_DAIFMT_NB_NF |
+			SND_SOC_DAIFMT_CBS_CFS,
+		SND_SOC_DAILINK_REG(analog),
+	},
+};
+
+/* HDMI codec dai_link */
+static struct snd_soc_dai_link rk_hdmi_dailinks[] = {
+	{
+		.name = "HDMI",
+		.stream_name = "HDMI",
+		.init = rk_hdmi_init,
+		.ops = &rk_aif1_ops,
+		.dai_fmt = SND_SOC_DAIFMT_I2S | SND_SOC_DAIFMT_NB_NF |
+			SND_SOC_DAIFMT_CBS_CFS,
+		SND_SOC_DAILINK_REG(hdmi),
+	}
+};
+
+/* max98090 and HDMI codec dai_link */
+static struct snd_soc_dai_link rk_max98090_hdmi_dailinks[] = {
+	[DAILINK_MAX98090] = {
+		.name = "max98090",
+		.stream_name = "Analog",
+		.init = rk_init,
+		.ops = &rk_aif1_ops,
+		/* set max98090 as slave */
+		.dai_fmt = SND_SOC_DAIFMT_I2S | SND_SOC_DAIFMT_NB_NF |
+			SND_SOC_DAIFMT_CBS_CFS,
+		SND_SOC_DAILINK_REG(analog),
+	},
+	[DAILINK_HDMI] = {
+		.name = "HDMI",
+		.stream_name = "HDMI",
+		.init = rk_hdmi_init,
+		.ops = &rk_aif1_ops,
+		.dai_fmt = SND_SOC_DAIFMT_I2S | SND_SOC_DAIFMT_NB_NF |
+			SND_SOC_DAIFMT_CBS_CFS,
+		SND_SOC_DAILINK_REG(hdmi),
+	}
 };
 
 static int rk_98090_headset_init(struct snd_soc_component *component);
@@ -178,19 +298,47 @@ static struct snd_soc_aux_dev rk_98090_headset_dev = {
 	.init = rk_98090_headset_init,
 };
 
-static struct snd_soc_card snd_soc_card_rk = {
+static struct snd_soc_card rockchip_max98090_card = {
 	.name = "ROCKCHIP-I2S",
 	.owner = THIS_MODULE,
-	.dai_link = &rk_dailink,
-	.num_links = 1,
+	.dai_link = rk_max98090_dailinks,
+	.num_links = ARRAY_SIZE(rk_max98090_dailinks),
+	.aux_dev = &rk_98090_headset_dev,
+	.num_aux_devs = 1,
+	.dapm_widgets = rk_max98090_dapm_widgets,
+	.num_dapm_widgets = ARRAY_SIZE(rk_max98090_dapm_widgets),
+	.dapm_routes = rk_max98090_audio_map,
+	.num_dapm_routes = ARRAY_SIZE(rk_max98090_audio_map),
+	.controls = rk_max98090_controls,
+	.num_controls = ARRAY_SIZE(rk_max98090_controls),
+};
+
+static struct snd_soc_card rockchip_hdmi_card = {
+	.name = "ROCKCHIP-HDMI",
+	.owner = THIS_MODULE,
+	.dai_link = rk_hdmi_dailinks,
+	.num_links = ARRAY_SIZE(rk_hdmi_dailinks),
+	.dapm_widgets = rk_hdmi_dapm_widgets,
+	.num_dapm_widgets = ARRAY_SIZE(rk_hdmi_dapm_widgets),
+	.dapm_routes = rk_hdmi_audio_map,
+	.num_dapm_routes = ARRAY_SIZE(rk_hdmi_audio_map),
+	.controls = rk_hdmi_controls,
+	.num_controls = ARRAY_SIZE(rk_hdmi_controls),
+};
+
+static struct snd_soc_card rockchip_max98090_hdmi_card = {
+	.name = "ROCKCHIP-MAX98090-HDMI",
+	.owner = THIS_MODULE,
+	.dai_link = rk_max98090_hdmi_dailinks,
+	.num_links = ARRAY_SIZE(rk_max98090_hdmi_dailinks),
 	.aux_dev = &rk_98090_headset_dev,
 	.num_aux_devs = 1,
-	.dapm_widgets = rk_dapm_widgets,
-	.num_dapm_widgets = ARRAY_SIZE(rk_dapm_widgets),
-	.dapm_routes = rk_audio_map,
-	.num_dapm_routes = ARRAY_SIZE(rk_audio_map),
-	.controls = rk_mc_controls,
-	.num_controls = ARRAY_SIZE(rk_mc_controls),
+	.dapm_widgets = rk_max98090_hdmi_dapm_widgets,
+	.num_dapm_widgets = ARRAY_SIZE(rk_max98090_hdmi_dapm_widgets),
+	.dapm_routes = rk_max98090_hdmi_audio_map,
+	.num_dapm_routes = ARRAY_SIZE(rk_max98090_hdmi_audio_map),
+	.controls = rk_max98090_hdmi_controls,
+	.num_controls = ARRAY_SIZE(rk_max98090_hdmi_controls),
 };
 
 static int rk_98090_headset_init(struct snd_soc_component *component)
@@ -198,7 +346,7 @@ static int rk_98090_headset_init(struct snd_soc_component *component)
 	int ret;
 
 	/* Enable Headset and 4 Buttons Jack detection */
-	ret = snd_soc_card_jack_new(&snd_soc_card_rk, "Headset Jack",
+	ret = snd_soc_card_jack_new(component->card, "Headset Jack",
 				    SND_JACK_HEADSET |
 				    SND_JACK_BTN_0 | SND_JACK_BTN_1 |
 				    SND_JACK_BTN_2 | SND_JACK_BTN_3,
@@ -213,41 +361,75 @@ static int rk_98090_headset_init(struct snd_soc_component *component)
 	return ret;
 }
 
+static int rk_parse_headset_from_of(struct device *dev, struct device_node *np)
+{
+	rk_98090_headset_dev.dlc.of_node = of_parse_phandle(
+			np, "rockchip,headset-codec", 0);
+	if (!rk_98090_headset_dev.dlc.of_node) {
+		dev_err(dev,
+			"Property 'rockchip,headset-codec' missing/invalid\n");
+		return -EINVAL;
+	}
+	return 0;
+}
+
 static int snd_rk_mc_probe(struct platform_device *pdev)
 {
 	int ret = 0;
-	struct snd_soc_card *card = &snd_soc_card_rk;
+	struct snd_soc_card *card;
+	struct device *dev = &pdev->dev;
 	struct device_node *np = pdev->dev.of_node;
+	struct device_node *np_cpu;
+	struct device_node *np_audio, *np_hdmi;
 
-	/* register the soc card */
-	card->dev = &pdev->dev;
+	/* Parse DTS for I2S controller. */
+	np_cpu = of_parse_phandle(np, "rockchip,i2s-controller", 0);
 
-	rk_dailink.codecs->of_node = of_parse_phandle(np,
-			"rockchip,audio-codec", 0);
-	if (!rk_dailink.codecs->of_node) {
+	if (!np_cpu) {
 		dev_err(&pdev->dev,
-			"Property 'rockchip,audio-codec' missing or invalid\n");
+			"Property 'rockchip,i2s-controller missing or invalid\n");
 		return -EINVAL;
 	}
 
-	rk_dailink.cpus->of_node = of_parse_phandle(np,
-			"rockchip,i2s-controller", 0);
-	if (!rk_dailink.cpus->of_node) {
-		dev_err(&pdev->dev,
-			"Property 'rockchip,i2s-controller' missing or invalid\n");
+	/*
+	 * Find the card to use based on the presences of audio codec
+	 * and hdmi codec in device property. Set their of_node accordingly.
+	 */
+	np_audio = of_parse_phandle(np, "rockchip,audio-codec", 0);
+	np_hdmi = of_parse_phandle(np, "rockchip,hdmi-codec", 0);
+	if (np_audio && np_hdmi) {
+		card = &rockchip_max98090_hdmi_card;
+		card->dai_link[DAILINK_MAX98090].codecs->of_node = np_audio;
+		card->dai_link[DAILINK_HDMI].codecs->of_node = np_hdmi;
+		card->dai_link[DAILINK_MAX98090].cpus->of_node = np_cpu;
+		card->dai_link[DAILINK_MAX98090].platforms->of_node = np_cpu;
+		card->dai_link[DAILINK_HDMI].cpus->of_node = np_cpu;
+		card->dai_link[DAILINK_HDMI].platforms->of_node = np_cpu;
+	} else if (np_audio) {
+		card = &rockchip_max98090_card;
+		card->dai_link[0].codecs->of_node = np_audio;
+		card->dai_link[0].cpus->of_node = np_cpu;
+		card->dai_link[0].platforms->of_node = np_cpu;
+	} else if (np_hdmi) {
+		card = &rockchip_hdmi_card;
+		card->dai_link[0].codecs->of_node = np_hdmi;
+		card->dai_link[0].cpus->of_node = np_cpu;
+		card->dai_link[0].platforms->of_node = np_cpu;
+	} else {
+		dev_err(dev, "At least one of codecs should be specified\n");
 		return -EINVAL;
 	}
 
-	rk_dailink.platforms->of_node = rk_dailink.cpus->of_node;
+	card->dev = dev;
 
-	rk_98090_headset_dev.dlc.of_node = of_parse_phandle(np,
-			"rockchip,headset-codec", 0);
-	if (!rk_98090_headset_dev.dlc.of_node) {
-		dev_err(&pdev->dev,
-			"Property 'rockchip,headset-codec' missing/invalid\n");
-		return -EINVAL;
+	/* Parse headset detection codec. */
+	if (np_audio) {
+		ret = rk_parse_headset_from_of(dev, np);
+		if (ret)
+			return ret;
 	}
 
+	/* Parse card name. */
 	ret = snd_soc_of_parse_card_name(card, "rockchip,model");
 	if (ret) {
 		dev_err(&pdev->dev,
@@ -255,6 +437,7 @@ static int snd_rk_mc_probe(struct platform_device *pdev)
 		return ret;
 	}
 
+	/* register the soc card */
 	ret = devm_snd_soc_register_card(&pdev->dev, card);
 	if (ret) {
 		dev_err(&pdev->dev,
diff --git a/sound/soc/samsung/Kconfig b/sound/soc/samsung/Kconfig
index 638983123d8f..1a0b163ca47b 100644
--- a/sound/soc/samsung/Kconfig
+++ b/sound/soc/samsung/Kconfig
@@ -194,11 +194,13 @@ config SND_SOC_ODROID
 	help
 	  Say Y here to enable audio support for the Odroid XU3/XU4.
 
-config SND_SOC_ARNDALE_RT5631_ALC5631
-        tristate "Audio support for RT5631(ALC5631) on Arndale Board"
-        depends on I2C
-        select SND_SAMSUNG_I2S
-        select SND_SOC_RT5631
+config SND_SOC_ARNDALE
+	tristate "Audio support for Arndale Board"
+	depends on I2C
+	select SND_SAMSUNG_I2S
+	select SND_SOC_RT5631
+	select MFD_WM8994
+	select SND_SOC_WM8994
 
 config SND_SOC_SAMSUNG_TM2_WM5110
 	tristate "SoC I2S Audio support for WM5110 on TM2 board"
diff --git a/sound/soc/samsung/Makefile b/sound/soc/samsung/Makefile
index c3b76035f69c..8f5dfe20b9f1 100644
--- a/sound/soc/samsung/Makefile
+++ b/sound/soc/samsung/Makefile
@@ -39,7 +39,7 @@ snd-soc-lowland-objs := lowland.o
 snd-soc-littlemill-objs := littlemill.o
 snd-soc-bells-objs := bells.o
 snd-soc-odroid-objs := odroid.o
-snd-soc-arndale-rt5631-objs := arndale_rt5631.o
+snd-soc-arndale-objs := arndale.o
 snd-soc-tm2-wm5110-objs := tm2_wm5110.o
 
 obj-$(CONFIG_SND_SOC_SAMSUNG_JIVE_WM8750) += snd-soc-jive-wm8750.o
@@ -62,5 +62,5 @@ obj-$(CONFIG_SND_SOC_LOWLAND) += snd-soc-lowland.o
 obj-$(CONFIG_SND_SOC_LITTLEMILL) += snd-soc-littlemill.o
 obj-$(CONFIG_SND_SOC_BELLS) += snd-soc-bells.o
 obj-$(CONFIG_SND_SOC_ODROID) += snd-soc-odroid.o
-obj-$(CONFIG_SND_SOC_ARNDALE_RT5631_ALC5631) += snd-soc-arndale-rt5631.o
+obj-$(CONFIG_SND_SOC_ARNDALE) += snd-soc-arndale.o
 obj-$(CONFIG_SND_SOC_SAMSUNG_TM2_WM5110) += snd-soc-tm2-wm5110.o
diff --git a/sound/soc/samsung/arndale.c b/sound/soc/samsung/arndale.c
new file mode 100644
index 000000000000..d64602950cbd
--- /dev/null
+++ b/sound/soc/samsung/arndale.c
@@ -0,0 +1,217 @@
+// SPDX-License-Identifier: GPL-2.0+
+//
+// Copyright (c) 2014, Insignal Co., Ltd.
+//
+//  Author: Claude <claude@insginal.co.kr>
+
+#include <linux/module.h>
+#include <linux/of_device.h>
+#include <linux/platform_device.h>
+#include <linux/clk.h>
+
+#include <sound/soc.h>
+#include <sound/soc-dapm.h>
+#include <sound/pcm.h>
+#include <sound/pcm_params.h>
+
+#include "../codecs/wm8994.h"
+#include "i2s.h"
+
+static int arndale_rt5631_hw_params(struct snd_pcm_substream *substream,
+				    struct snd_pcm_hw_params *params)
+{
+	struct snd_soc_pcm_runtime *rtd = substream->private_data;
+	struct snd_soc_dai *cpu_dai = rtd->cpu_dai;
+	struct snd_soc_dai *codec_dai = rtd->codec_dai;
+	int rfs, ret;
+	unsigned long rclk;
+
+	rfs = 256;
+
+	rclk = params_rate(params) * rfs;
+
+	ret = snd_soc_dai_set_sysclk(cpu_dai, SAMSUNG_I2S_CDCLK,
+					0, SND_SOC_CLOCK_OUT);
+	if (ret < 0)
+		return ret;
+
+	ret = snd_soc_dai_set_sysclk(cpu_dai, SAMSUNG_I2S_RCLKSRC_0,
+					0, SND_SOC_CLOCK_OUT);
+
+	if (ret < 0)
+		return ret;
+
+	ret = snd_soc_dai_set_sysclk(codec_dai, 0, rclk, SND_SOC_CLOCK_OUT);
+	if (ret < 0)
+		return ret;
+
+	return 0;
+}
+
+static struct snd_soc_ops arndale_rt5631_ops = {
+	.hw_params = arndale_rt5631_hw_params,
+};
+
+static int arndale_wm1811_hw_params(struct snd_pcm_substream *substream,
+				    struct snd_pcm_hw_params *params)
+{
+	struct snd_soc_pcm_runtime *rtd = substream->private_data;
+	struct snd_soc_dai *codec_dai = rtd->codec_dai;
+	unsigned int rfs, rclk;
+
+	/* Ensure AIF1CLK is >= 3 MHz for optimal performance */
+	if (params_width(params) == 24)
+		rfs = 384;
+	else if (params_rate(params) == 8000 || params_rate(params) == 11025)
+		rfs = 512;
+	else
+		rfs = 256;
+
+	rclk = params_rate(params) * rfs;
+
+	/*
+	 * We add 1 to the frequency value to ensure proper EPLL setting
+	 * for each audio sampling rate (see epll_24mhz_tbl in drivers/clk/
+	 * samsung/clk-exynos5250.c for list of available EPLL rates).
+	 * The CODEC uses clk API and the value will be rounded hence the MCLK1
+	 * clock's frequency will still be exact multiple of the sample rate.
+	 */
+	return snd_soc_dai_set_sysclk(codec_dai, WM8994_SYSCLK_MCLK1,
+					rclk + 1, SND_SOC_CLOCK_IN);
+}
+
+static struct snd_soc_ops arndale_wm1811_ops = {
+	.hw_params = arndale_wm1811_hw_params,
+};
+
+SND_SOC_DAILINK_DEFS(rt5631_hifi,
+	DAILINK_COMP_ARRAY(COMP_EMPTY()),
+	DAILINK_COMP_ARRAY(COMP_CODEC(NULL, "rt5631-aif1")),
+	DAILINK_COMP_ARRAY(COMP_EMPTY()));
+
+static struct snd_soc_dai_link arndale_rt5631_dai[] = {
+	{
+		.name = "RT5631 HiFi",
+		.stream_name = "Primary",
+		.dai_fmt = SND_SOC_DAIFMT_I2S
+			| SND_SOC_DAIFMT_NB_NF
+			| SND_SOC_DAIFMT_CBS_CFS,
+		.ops = &arndale_rt5631_ops,
+		SND_SOC_DAILINK_REG(rt5631_hifi),
+	},
+};
+
+SND_SOC_DAILINK_DEFS(wm1811_hifi,
+	DAILINK_COMP_ARRAY(COMP_EMPTY()),
+	DAILINK_COMP_ARRAY(COMP_CODEC(NULL, "wm8994-aif1")),
+	DAILINK_COMP_ARRAY(COMP_EMPTY()));
+
+static struct snd_soc_dai_link arndale_wm1811_dai[] = {
+	{
+		.name = "WM1811 HiFi",
+		.stream_name = "Primary",
+		.dai_fmt = SND_SOC_DAIFMT_I2S
+			| SND_SOC_DAIFMT_NB_NF
+			| SND_SOC_DAIFMT_CBM_CFM,
+		.ops = &arndale_wm1811_ops,
+		SND_SOC_DAILINK_REG(wm1811_hifi),
+	},
+};
+
+static struct snd_soc_card arndale_rt5631 = {
+	.name = "Arndale RT5631",
+	.owner = THIS_MODULE,
+	.dai_link = arndale_rt5631_dai,
+	.num_links = ARRAY_SIZE(arndale_rt5631_dai),
+};
+
+static struct snd_soc_card arndale_wm1811 = {
+	.name = "Arndale WM1811",
+	.owner = THIS_MODULE,
+	.dai_link = arndale_wm1811_dai,
+	.num_links = ARRAY_SIZE(arndale_wm1811_dai),
+};
+
+static void arndale_put_of_nodes(struct snd_soc_card *card)
+{
+	struct snd_soc_dai_link *dai_link;
+	int i;
+
+	for_each_card_prelinks(card, i, dai_link) {
+		of_node_put(dai_link->cpus->of_node);
+		of_node_put(dai_link->codecs->of_node);
+	}
+}
+
+static int arndale_audio_probe(struct platform_device *pdev)
+{
+	struct device_node *np = pdev->dev.of_node;
+	struct snd_soc_card *card;
+	struct snd_soc_dai_link *dai_link;
+	int ret;
+
+	card = (struct snd_soc_card *)of_device_get_match_data(&pdev->dev);
+	card->dev = &pdev->dev;
+	dai_link = card->dai_link;
+
+	dai_link->cpus->of_node = of_parse_phandle(np, "samsung,audio-cpu", 0);
+	if (!dai_link->cpus->of_node) {
+		dev_err(&pdev->dev,
+			"Property 'samsung,audio-cpu' missing or invalid\n");
+		return -EINVAL;
+	}
+
+	if (!dai_link->platforms->name)
+		dai_link->platforms->of_node = dai_link->cpus->of_node;
+
+	dai_link->codecs->of_node = of_parse_phandle(np, "samsung,audio-codec", 0);
+	if (!dai_link->codecs->of_node) {
+		dev_err(&pdev->dev,
+			"Property 'samsung,audio-codec' missing or invalid\n");
+		ret = -EINVAL;
+		goto err_put_of_nodes;
+	}
+
+	ret = devm_snd_soc_register_card(card->dev, card);
+	if (ret) {
+		dev_err(&pdev->dev, "snd_soc_register_card() failed: %d\n", ret);
+		goto err_put_of_nodes;
+	}
+	return 0;
+
+err_put_of_nodes:
+	arndale_put_of_nodes(card);
+	return ret;
+}
+
+static int arndale_audio_remove(struct platform_device *pdev)
+{
+	struct snd_soc_card *card = platform_get_drvdata(pdev);
+
+	arndale_put_of_nodes(card);
+	return 0;
+}
+
+static const struct of_device_id arndale_audio_of_match[] = {
+	{ .compatible = "samsung,arndale-rt5631",  .data = &arndale_rt5631 },
+	{ .compatible = "samsung,arndale-alc5631", .data = &arndale_rt5631 },
+	{ .compatible = "samsung,arndale-wm1811",  .data = &arndale_wm1811 },
+	{},
+};
+MODULE_DEVICE_TABLE(of, arndale_audio_of_match);
+
+static struct platform_driver arndale_audio_driver = {
+	.driver = {
+		.name = "arndale-audio",
+		.pm = &snd_soc_pm_ops,
+		.of_match_table = arndale_audio_of_match,
+	},
+	.probe = arndale_audio_probe,
+	.remove = arndale_audio_remove,
+};
+
+module_platform_driver(arndale_audio_driver);
+
+MODULE_AUTHOR("Claude <claude@insignal.co.kr>");
+MODULE_DESCRIPTION("ALSA SoC Driver for Arndale Board");
+MODULE_LICENSE("GPL");
diff --git a/sound/soc/samsung/arndale_rt5631.c b/sound/soc/samsung/arndale_rt5631.c
deleted file mode 100644
index fd8c6642fb0d..000000000000
--- a/sound/soc/samsung/arndale_rt5631.c
+++ /dev/null
@@ -1,164 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0+
-//
-// Copyright (c) 2014, Insignal Co., Ltd.
-//
-//  Author: Claude <claude@insginal.co.kr>
-
-#include <linux/module.h>
-#include <linux/of_device.h>
-#include <linux/platform_device.h>
-#include <linux/clk.h>
-
-#include <sound/soc.h>
-#include <sound/soc-dapm.h>
-#include <sound/pcm.h>
-#include <sound/pcm_params.h>
-
-#include "i2s.h"
-
-static int arndale_hw_params(struct snd_pcm_substream *substream,
-	struct snd_pcm_hw_params *params)
-{
-	struct snd_soc_pcm_runtime *rtd = substream->private_data;
-	struct snd_soc_dai *cpu_dai = rtd->cpu_dai;
-	struct snd_soc_dai *codec_dai = rtd->codec_dai;
-	int rfs, ret;
-	unsigned long rclk;
-
-	rfs = 256;
-
-	rclk = params_rate(params) * rfs;
-
-	ret = snd_soc_dai_set_sysclk(cpu_dai, SAMSUNG_I2S_CDCLK,
-					0, SND_SOC_CLOCK_OUT);
-	if (ret < 0)
-		return ret;
-
-	ret = snd_soc_dai_set_sysclk(cpu_dai, SAMSUNG_I2S_RCLKSRC_0,
-					0, SND_SOC_CLOCK_OUT);
-
-	if (ret < 0)
-		return ret;
-
-	ret = snd_soc_dai_set_sysclk(codec_dai, 0, rclk, SND_SOC_CLOCK_OUT);
-	if (ret < 0)
-		return ret;
-
-	return 0;
-}
-
-static struct snd_soc_ops arndale_ops = {
-	.hw_params = arndale_hw_params,
-};
-
-SND_SOC_DAILINK_DEFS(rt5631_hifi,
-	DAILINK_COMP_ARRAY(COMP_EMPTY()),
-	DAILINK_COMP_ARRAY(COMP_CODEC(NULL, "rt5631-hifi")),
-	DAILINK_COMP_ARRAY(COMP_EMPTY()));
-
-static struct snd_soc_dai_link arndale_rt5631_dai[] = {
-	{
-		.name = "RT5631 HiFi",
-		.stream_name = "Primary",
-		.dai_fmt = SND_SOC_DAIFMT_I2S
-			| SND_SOC_DAIFMT_NB_NF
-			| SND_SOC_DAIFMT_CBS_CFS,
-		.ops = &arndale_ops,
-		SND_SOC_DAILINK_REG(rt5631_hifi),
-	},
-};
-
-static struct snd_soc_card arndale_rt5631 = {
-	.name = "Arndale RT5631",
-	.owner = THIS_MODULE,
-	.dai_link = arndale_rt5631_dai,
-	.num_links = ARRAY_SIZE(arndale_rt5631_dai),
-};
-
-static void arndale_put_of_nodes(struct snd_soc_card *card)
-{
-	struct snd_soc_dai_link *dai_link;
-	int i;
-
-	for_each_card_prelinks(card, i, dai_link) {
-		of_node_put(dai_link->cpus->of_node);
-		of_node_put(dai_link->codecs->of_node);
-	}
-}
-
-static int arndale_audio_probe(struct platform_device *pdev)
-{
-	int n, ret;
-	struct device_node *np = pdev->dev.of_node;
-	struct snd_soc_card *card = &arndale_rt5631;
-
-	card->dev = &pdev->dev;
-
-	for (n = 0; np && n < ARRAY_SIZE(arndale_rt5631_dai); n++) {
-		if (!arndale_rt5631_dai[n].cpus->dai_name) {
-			arndale_rt5631_dai[n].cpus->of_node = of_parse_phandle(np,
-					"samsung,audio-cpu", n);
-
-			if (!arndale_rt5631_dai[n].cpus->of_node) {
-				dev_err(&pdev->dev,
-				"Property 'samsung,audio-cpu' missing or invalid\n");
-				return -EINVAL;
-			}
-		}
-		if (!arndale_rt5631_dai[n].platforms->name)
-			arndale_rt5631_dai[n].platforms->of_node =
-					arndale_rt5631_dai[n].cpus->of_node;
-
-		arndale_rt5631_dai[n].codecs->name = NULL;
-		arndale_rt5631_dai[n].codecs->of_node = of_parse_phandle(np,
-					"samsung,audio-codec", n);
-		if (!arndale_rt5631_dai[0].codecs->of_node) {
-			dev_err(&pdev->dev,
-			"Property 'samsung,audio-codec' missing or invalid\n");
-			ret = -EINVAL;
-			goto err_put_of_nodes;
-		}
-	}
-
-	ret = devm_snd_soc_register_card(card->dev, card);
-	if (ret) {
-		dev_err(&pdev->dev, "snd_soc_register_card() failed: %d\n", ret);
-		goto err_put_of_nodes;
-	}
-	return 0;
-
-err_put_of_nodes:
-	arndale_put_of_nodes(card);
-	return ret;
-}
-
-static int arndale_audio_remove(struct platform_device *pdev)
-{
-	struct snd_soc_card *card = platform_get_drvdata(pdev);
-
-	arndale_put_of_nodes(card);
-	return 0;
-}
-
-static const struct of_device_id samsung_arndale_rt5631_of_match[] __maybe_unused = {
-	{ .compatible = "samsung,arndale-rt5631", },
-	{ .compatible = "samsung,arndale-alc5631", },
-	{},
-};
-MODULE_DEVICE_TABLE(of, samsung_arndale_rt5631_of_match);
-
-static struct platform_driver arndale_audio_driver = {
-	.driver = {
-		.name   = "arndale-audio",
-		.pm = &snd_soc_pm_ops,
-		.of_match_table = of_match_ptr(samsung_arndale_rt5631_of_match),
-	},
-	.probe = arndale_audio_probe,
-	.remove = arndale_audio_remove,
-};
-
-module_platform_driver(arndale_audio_driver);
-
-MODULE_AUTHOR("Claude <claude@insignal.co.kr>");
-MODULE_DESCRIPTION("ALSA SoC Driver for Arndale Board");
-MODULE_LICENSE("GPL");
diff --git a/sound/soc/samsung/idma.c b/sound/soc/samsung/idma.c
index 65497cd477a5..294dce111b05 100644
--- a/sound/soc/samsung/idma.c
+++ b/sound/soc/samsung/idma.c
@@ -137,8 +137,9 @@ static void idma_done(void *id, int bytes_xfer)
 		snd_pcm_period_elapsed(substream);
 }
 
-static int idma_hw_params(struct snd_pcm_substream *substream,
-				struct snd_pcm_hw_params *params)
+static int idma_hw_params(struct snd_soc_component *component,
+			  struct snd_pcm_substream *substream,
+			  struct snd_pcm_hw_params *params)
 {
 	struct snd_pcm_runtime *runtime = substream->runtime;
 	struct idma_ctrl *prtd = substream->runtime->private_data;
@@ -163,14 +164,16 @@ static int idma_hw_params(struct snd_pcm_substream *substream,
 	return 0;
 }
 
-static int idma_hw_free(struct snd_pcm_substream *substream)
+static int idma_hw_free(struct snd_soc_component *component,
+			struct snd_pcm_substream *substream)
 {
 	snd_pcm_set_runtime_buffer(substream, NULL);
 
 	return 0;
 }
 
-static int idma_prepare(struct snd_pcm_substream *substream)
+static int idma_prepare(struct snd_soc_component *component,
+			struct snd_pcm_substream *substream)
 {
 	struct idma_ctrl *prtd = substream->runtime->private_data;
 
@@ -183,7 +186,8 @@ static int idma_prepare(struct snd_pcm_substream *substream)
 	return 0;
 }
 
-static int idma_trigger(struct snd_pcm_substream *substream, int cmd)
+static int idma_trigger(struct snd_soc_component *component,
+			struct snd_pcm_substream *substream, int cmd)
 {
 	struct idma_ctrl *prtd = substream->runtime->private_data;
 	int ret = 0;
@@ -216,7 +220,8 @@ static int idma_trigger(struct snd_pcm_substream *substream, int cmd)
 }
 
 static snd_pcm_uframes_t
-	idma_pointer(struct snd_pcm_substream *substream)
+idma_pointer(struct snd_soc_component *component,
+	     struct snd_pcm_substream *substream)
 {
 	struct snd_pcm_runtime *runtime = substream->runtime;
 	struct idma_ctrl *prtd = runtime->private_data;
@@ -233,7 +238,8 @@ static snd_pcm_uframes_t
 	return bytes_to_frames(substream->runtime, res);
 }
 
-static int idma_mmap(struct snd_pcm_substream *substream,
+static int idma_mmap(struct snd_soc_component *component,
+		     struct snd_pcm_substream *substream,
 	struct vm_area_struct *vma)
 {
 	struct snd_pcm_runtime *runtime = substream->runtime;
@@ -278,7 +284,8 @@ static irqreturn_t iis_irq(int irqno, void *dev_id)
 	return IRQ_HANDLED;
 }
 
-static int idma_open(struct snd_pcm_substream *substream)
+static int idma_open(struct snd_soc_component *component,
+		     struct snd_pcm_substream *substream)
 {
 	struct snd_pcm_runtime *runtime = substream->runtime;
 	struct idma_ctrl *prtd;
@@ -304,7 +311,8 @@ static int idma_open(struct snd_pcm_substream *substream)
 	return 0;
 }
 
-static int idma_close(struct snd_pcm_substream *substream)
+static int idma_close(struct snd_soc_component *component,
+		      struct snd_pcm_substream *substream)
 {
 	struct snd_pcm_runtime *runtime = substream->runtime;
 	struct idma_ctrl *prtd = runtime->private_data;
@@ -319,19 +327,8 @@ static int idma_close(struct snd_pcm_substream *substream)
 	return 0;
 }
 
-static const struct snd_pcm_ops idma_ops = {
-	.open		= idma_open,
-	.close		= idma_close,
-	.ioctl		= snd_pcm_lib_ioctl,
-	.trigger	= idma_trigger,
-	.pointer	= idma_pointer,
-	.mmap		= idma_mmap,
-	.hw_params	= idma_hw_params,
-	.hw_free	= idma_hw_free,
-	.prepare	= idma_prepare,
-};
-
-static void idma_free(struct snd_pcm *pcm)
+static void idma_free(struct snd_soc_component *component,
+		      struct snd_pcm *pcm)
 {
 	struct snd_pcm_substream *substream;
 	struct snd_dma_buffer *buf;
@@ -367,7 +364,8 @@ static int preallocate_idma_buffer(struct snd_pcm *pcm, int stream)
 	return 0;
 }
 
-static int idma_new(struct snd_soc_pcm_runtime *rtd)
+static int idma_new(struct snd_soc_component *component,
+		    struct snd_soc_pcm_runtime *rtd)
 {
 	struct snd_card *card = rtd->card->snd_card;
 	struct snd_pcm *pcm = rtd->pcm;
@@ -394,9 +392,17 @@ void idma_reg_addr_init(void __iomem *regs, dma_addr_t addr)
 EXPORT_SYMBOL_GPL(idma_reg_addr_init);
 
 static const struct snd_soc_component_driver asoc_idma_platform = {
-	.ops = &idma_ops,
-	.pcm_new = idma_new,
-	.pcm_free = idma_free,
+	.open		= idma_open,
+	.close		= idma_close,
+	.ioctl		= snd_soc_pcm_lib_ioctl,
+	.trigger	= idma_trigger,
+	.pointer	= idma_pointer,
+	.mmap		= idma_mmap,
+	.hw_params	= idma_hw_params,
+	.hw_free	= idma_hw_free,
+	.prepare	= idma_prepare,
+	.pcm_construct	= idma_new,
+	.pcm_destruct	= idma_free,
 };
 
 static int asoc_idma_platform_probe(struct platform_device *pdev)
diff --git a/sound/soc/sh/dma-sh7760.c b/sound/soc/sh/dma-sh7760.c
index 5aee11c94f2a..2b0eca02a8b9 100644
--- a/sound/soc/sh/dma-sh7760.c
+++ b/sound/soc/sh/dma-sh7760.c
@@ -115,7 +115,8 @@ static void camelot_rxdma(void *data)
 	snd_pcm_period_elapsed(cam->rx_ss);
 }
 
-static int camelot_pcm_open(struct snd_pcm_substream *substream)
+static int camelot_pcm_open(struct snd_soc_component *component,
+			    struct snd_pcm_substream *substream)
 {
 	struct snd_soc_pcm_runtime *rtd = substream->private_data;
 	struct camelot_pcm *cam = &cam_pcm_data[rtd->cpu_dai->id];
@@ -148,7 +149,8 @@ static int camelot_pcm_open(struct snd_pcm_substream *substream)
 	return 0;
 }
 
-static int camelot_pcm_close(struct snd_pcm_substream *substream)
+static int camelot_pcm_close(struct snd_soc_component *component,
+			     struct snd_pcm_substream *substream)
 {
 	struct snd_soc_pcm_runtime *rtd = substream->private_data;
 	struct camelot_pcm *cam = &cam_pcm_data[rtd->cpu_dai->id];
@@ -168,7 +170,8 @@ static int camelot_pcm_close(struct snd_pcm_substream *substream)
 	return 0;
 }
 
-static int camelot_hw_params(struct snd_pcm_substream *substream,
+static int camelot_hw_params(struct snd_soc_component *component,
+			     struct snd_pcm_substream *substream,
 			     struct snd_pcm_hw_params *hw_params)
 {
 	struct snd_soc_pcm_runtime *rtd = substream->private_data;
@@ -191,12 +194,14 @@ static int camelot_hw_params(struct snd_pcm_substream *substream,
 	return 0;
 }
 
-static int camelot_hw_free(struct snd_pcm_substream *substream)
+static int camelot_hw_free(struct snd_soc_component *component,
+			   struct snd_pcm_substream *substream)
 {
 	return snd_pcm_lib_free_pages(substream);
 }
 
-static int camelot_prepare(struct snd_pcm_substream *substream)
+static int camelot_prepare(struct snd_soc_component *component,
+			   struct snd_pcm_substream *substream)
 {
 	struct snd_pcm_runtime *runtime = substream->runtime;
 	struct snd_soc_pcm_runtime *rtd = substream->private_data;
@@ -244,7 +249,8 @@ static inline void dmabrg_rec_dma_stop(struct camelot_pcm *cam)
 	BRGREG(BRGACR) = acr | ACR_RDS;
 }
 
-static int camelot_trigger(struct snd_pcm_substream *substream, int cmd)
+static int camelot_trigger(struct snd_soc_component *component,
+			   struct snd_pcm_substream *substream, int cmd)
 {
 	struct snd_soc_pcm_runtime *rtd = substream->private_data;
 	struct camelot_pcm *cam = &cam_pcm_data[rtd->cpu_dai->id];
@@ -270,7 +276,8 @@ static int camelot_trigger(struct snd_pcm_substream *substream, int cmd)
 	return 0;
 }
 
-static snd_pcm_uframes_t camelot_pos(struct snd_pcm_substream *substream)
+static snd_pcm_uframes_t camelot_pos(struct snd_soc_component *component,
+				     struct snd_pcm_substream *substream)
 {
 	struct snd_pcm_runtime *runtime = substream->runtime;
 	struct snd_soc_pcm_runtime *rtd = substream->private_data;
@@ -292,18 +299,8 @@ static snd_pcm_uframes_t camelot_pos(struct snd_pcm_substream *substream)
 	return bytes_to_frames(runtime, pos);
 }
 
-static const struct snd_pcm_ops camelot_pcm_ops = {
-	.open		= camelot_pcm_open,
-	.close		= camelot_pcm_close,
-	.ioctl		= snd_pcm_lib_ioctl,
-	.hw_params	= camelot_hw_params,
-	.hw_free	= camelot_hw_free,
-	.prepare	= camelot_prepare,
-	.trigger	= camelot_trigger,
-	.pointer	= camelot_pos,
-};
-
-static int camelot_pcm_new(struct snd_soc_pcm_runtime *rtd)
+static int camelot_pcm_new(struct snd_soc_component *component,
+			   struct snd_soc_pcm_runtime *rtd)
 {
 	struct snd_pcm *pcm = rtd->pcm;
 
@@ -312,15 +309,22 @@ static int camelot_pcm_new(struct snd_soc_pcm_runtime *rtd)
 	 */
 	snd_pcm_lib_preallocate_pages_for_all(pcm,
 		SNDRV_DMA_TYPE_CONTINUOUS,
-		snd_dma_continuous_data(GFP_KERNEL),
+		NULL,
 		DMABRG_PREALLOC_BUFFER,	DMABRG_PREALLOC_BUFFER_MAX);
 
 	return 0;
 }
 
 static const struct snd_soc_component_driver sh7760_soc_component = {
-	.ops		= &camelot_pcm_ops,
-	.pcm_new	= camelot_pcm_new,
+	.open		= camelot_pcm_open,
+	.close		= camelot_pcm_close,
+	.ioctl		= snd_soc_pcm_lib_ioctl,
+	.hw_params	= camelot_hw_params,
+	.hw_free	= camelot_hw_free,
+	.prepare	= camelot_prepare,
+	.trigger	= camelot_trigger,
+	.pointer	= camelot_pos,
+	.pcm_construct	= camelot_pcm_new,
 };
 
 static int sh7760_soc_platform_probe(struct platform_device *pdev)
diff --git a/sound/soc/sh/fsi.c b/sound/soc/sh/fsi.c
index 3447dbdba1f1..e384fdc8d60e 100644
--- a/sound/soc/sh/fsi.c
+++ b/sound/soc/sh/fsi.c
@@ -1718,7 +1718,8 @@ static const struct snd_pcm_hardware fsi_pcm_hardware = {
 	.fifo_size		= 256,
 };
 
-static int fsi_pcm_open(struct snd_pcm_substream *substream)
+static int fsi_pcm_open(struct snd_soc_component *component,
+			struct snd_pcm_substream *substream)
 {
 	struct snd_pcm_runtime *runtime = substream->runtime;
 	int ret = 0;
@@ -1731,19 +1732,22 @@ static int fsi_pcm_open(struct snd_pcm_substream *substream)
 	return ret;
 }
 
-static int fsi_hw_params(struct snd_pcm_substream *substream,
+static int fsi_hw_params(struct snd_soc_component *component,
+			 struct snd_pcm_substream *substream,
 			 struct snd_pcm_hw_params *hw_params)
 {
 	return snd_pcm_lib_malloc_pages(substream,
 					params_buffer_bytes(hw_params));
 }
 
-static int fsi_hw_free(struct snd_pcm_substream *substream)
+static int fsi_hw_free(struct snd_soc_component *component,
+		       struct snd_pcm_substream *substream)
 {
 	return snd_pcm_lib_free_pages(substream);
 }
 
-static snd_pcm_uframes_t fsi_pointer(struct snd_pcm_substream *substream)
+static snd_pcm_uframes_t fsi_pointer(struct snd_soc_component *component,
+				     struct snd_pcm_substream *substream)
 {
 	struct fsi_priv *fsi = fsi_get_priv(substream);
 	struct fsi_stream *io = fsi_stream_get(fsi, substream);
@@ -1751,14 +1755,6 @@ static snd_pcm_uframes_t fsi_pointer(struct snd_pcm_substream *substream)
 	return fsi_sample2frame(fsi, io->buff_sample_pos);
 }
 
-static const struct snd_pcm_ops fsi_pcm_ops = {
-	.open		= fsi_pcm_open,
-	.ioctl		= snd_pcm_lib_ioctl,
-	.hw_params	= fsi_hw_params,
-	.hw_free	= fsi_hw_free,
-	.pointer	= fsi_pointer,
-};
-
 /*
  *		snd_soc_component
  */
@@ -1766,7 +1762,8 @@ static const struct snd_pcm_ops fsi_pcm_ops = {
 #define PREALLOC_BUFFER		(32 * 1024)
 #define PREALLOC_BUFFER_MAX	(32 * 1024)
 
-static int fsi_pcm_new(struct snd_soc_pcm_runtime *rtd)
+static int fsi_pcm_new(struct snd_soc_component *component,
+		       struct snd_soc_pcm_runtime *rtd)
 {
 	snd_pcm_lib_preallocate_pages_for_all(
 		rtd->pcm,
@@ -1817,8 +1814,12 @@ static struct snd_soc_dai_driver fsi_soc_dai[] = {
 
 static const struct snd_soc_component_driver fsi_soc_component = {
 	.name		= "fsi",
-	.ops		= &fsi_pcm_ops,
-	.pcm_new	= fsi_pcm_new,
+	.open		= fsi_pcm_open,
+	.ioctl		= snd_soc_pcm_lib_ioctl,
+	.hw_params	= fsi_hw_params,
+	.hw_free	= fsi_hw_free,
+	.pointer	= fsi_pointer,
+	.pcm_construct	= fsi_pcm_new,
 };
 
 /*
diff --git a/sound/soc/sh/rcar/core.c b/sound/soc/sh/rcar/core.c
index e9596c2096cd..399dc6e9bde5 100644
--- a/sound/soc/sh/rcar/core.c
+++ b/sound/soc/sh/rcar/core.c
@@ -302,7 +302,7 @@ int rsnd_runtime_channel_after_ctu_with_params(struct rsnd_dai_stream *io,
 
 int rsnd_channel_normalization(int chan)
 {
-	if ((chan > 8) || (chan < 0))
+	if (WARN_ON((chan > 8) || (chan < 0)))
 		return 0;
 
 	/* TDM Extend Mode needs 8ch */
@@ -376,6 +376,17 @@ u32 rsnd_get_adinr_bit(struct rsnd_mod *mod, struct rsnd_dai_stream *io)
  */
 u32 rsnd_get_dalign(struct rsnd_mod *mod, struct rsnd_dai_stream *io)
 {
+	static const u32 dalign_values[8][2] = {
+		{0x76543210, 0x67452301},
+		{0x00000032, 0x00000023},
+		{0x00007654, 0x00006745},
+		{0x00000076, 0x00000067},
+		{0xfedcba98, 0xefcdab89},
+		{0x000000ba, 0x000000ab},
+		{0x0000fedc, 0x0000efcd},
+		{0x000000fe, 0x000000ef},
+	};
+	int id = 0, inv;
 	struct rsnd_mod *ssiu = rsnd_io_to_mod_ssiu(io);
 	struct rsnd_mod *target;
 	struct snd_pcm_runtime *runtime = rsnd_io_to_runtime(io);
@@ -411,13 +422,18 @@ u32 rsnd_get_dalign(struct rsnd_mod *mod, struct rsnd_dai_stream *io)
 		target = cmd ? cmd : ssiu;
 	}
 
+	if (mod == ssiu)
+		id = rsnd_mod_id_sub(mod);
+
 	/* Non target mod or non 16bit needs normal DALIGN */
 	if ((snd_pcm_format_width(runtime->format) != 16) ||
 	    (mod != target))
-		return 0x76543210;
+		inv = 0;
 	/* Target mod needs inverted DALIGN when 16bit */
 	else
-		return 0x67452301;
+		inv = 1;
+
+	return dalign_values[id][inv];
 }
 
 u32 rsnd_get_busif_shift(struct rsnd_dai_stream *io, struct rsnd_mod *mod)
@@ -1076,7 +1092,10 @@ static void rsnd_parse_tdm_split_mode(struct rsnd_priv *priv,
 			j++;
 		}
 
+		of_node_put(node);
 	}
+
+	of_node_put(ssiu_np);
 }
 
 static void rsnd_parse_connect_simple(struct rsnd_priv *priv,
@@ -1094,11 +1113,13 @@ static void rsnd_parse_connect_graph(struct rsnd_priv *priv,
 				     struct device_node *endpoint)
 {
 	struct device *dev = rsnd_priv_to_dev(priv);
-	struct device_node *remote_node = of_graph_get_remote_port_parent(endpoint);
+	struct device_node *remote_node;
 
 	if (!rsnd_io_to_mod_ssi(io))
 		return;
 
+	remote_node = of_graph_get_remote_port_parent(endpoint);
+
 	/* HDMI0 */
 	if (strstr(remote_node->full_name, "hdmi@fead0000")) {
 		rsnd_flags_set(io, RSND_STREAM_HDMI0);
@@ -1112,6 +1133,8 @@ static void rsnd_parse_connect_graph(struct rsnd_priv *priv,
 	}
 
 	rsnd_parse_tdm_split_mode(priv, io, endpoint);
+
+	of_node_put(remote_node);
 }
 
 void rsnd_parse_connect_common(struct rsnd_dai *rdai,
@@ -1374,8 +1397,9 @@ static int rsnd_dai_probe(struct rsnd_priv *priv)
 /*
  *		pcm ops
  */
-static int rsnd_hw_params(struct snd_pcm_substream *substream,
-			 struct snd_pcm_hw_params *hw_params)
+static int rsnd_hw_params(struct snd_soc_component *component,
+			  struct snd_pcm_substream *substream,
+			  struct snd_pcm_hw_params *hw_params)
 {
 	struct snd_soc_dai *dai = rsnd_substream_to_dai(substream);
 	struct rsnd_dai *rdai = rsnd_dai_to_rdai(dai);
@@ -1422,7 +1446,8 @@ static int rsnd_hw_params(struct snd_pcm_substream *substream,
 					params_buffer_bytes(hw_params));
 }
 
-static int rsnd_hw_free(struct snd_pcm_substream *substream)
+static int rsnd_hw_free(struct snd_soc_component *component,
+			struct snd_pcm_substream *substream)
 {
 	struct snd_soc_dai *dai = rsnd_substream_to_dai(substream);
 	struct rsnd_dai *rdai = rsnd_dai_to_rdai(dai);
@@ -1436,7 +1461,8 @@ static int rsnd_hw_free(struct snd_pcm_substream *substream)
 	return snd_pcm_lib_free_pages(substream);
 }
 
-static snd_pcm_uframes_t rsnd_pointer(struct snd_pcm_substream *substream)
+static snd_pcm_uframes_t rsnd_pointer(struct snd_soc_component *component,
+				      struct snd_pcm_substream *substream)
 {
 	struct snd_soc_dai *dai = rsnd_substream_to_dai(substream);
 	struct rsnd_dai *rdai = rsnd_dai_to_rdai(dai);
@@ -1448,13 +1474,6 @@ static snd_pcm_uframes_t rsnd_pointer(struct snd_pcm_substream *substream)
 	return pointer;
 }
 
-static const struct snd_pcm_ops rsnd_pcm_ops = {
-	.ioctl		= snd_pcm_lib_ioctl,
-	.hw_params	= rsnd_hw_params,
-	.hw_free	= rsnd_hw_free,
-	.pointer	= rsnd_pointer,
-};
-
 /*
  *		snd_kcontrol
  */
@@ -1648,8 +1667,11 @@ int rsnd_kctrl_new(struct rsnd_mod *mod,
  *		snd_soc_component
  */
 static const struct snd_soc_component_driver rsnd_soc_component = {
-	.ops		= &rsnd_pcm_ops,
 	.name		= "rsnd",
+	.ioctl		= snd_soc_pcm_lib_ioctl,
+	.hw_params	= rsnd_hw_params,
+	.hw_free	= rsnd_hw_free,
+	.pointer	= rsnd_pointer,
 };
 
 static int rsnd_rdai_continuance_probe(struct rsnd_priv *priv,
diff --git a/sound/soc/sh/rcar/dma.c b/sound/soc/sh/rcar/dma.c
index 28f65eba2bb4..95aa26d62e4f 100644
--- a/sound/soc/sh/rcar/dma.c
+++ b/sound/soc/sh/rcar/dma.c
@@ -165,14 +165,40 @@ static int rsnd_dmaen_start(struct rsnd_mod *mod,
 	struct device *dev = rsnd_priv_to_dev(priv);
 	struct dma_async_tx_descriptor *desc;
 	struct dma_slave_config cfg = {};
+	enum dma_slave_buswidth buswidth = DMA_SLAVE_BUSWIDTH_4_BYTES;
 	int is_play = rsnd_io_is_play(io);
 	int ret;
 
+	/*
+	 * in case of monaural data writing or reading through Audio-DMAC
+	 * data is always in Left Justified format, so both src and dst
+	 * DMA Bus width need to be set equal to physical data width.
+	 */
+	if (rsnd_runtime_channel_original(io) == 1) {
+		struct snd_pcm_runtime *runtime = rsnd_io_to_runtime(io);
+		int bits = snd_pcm_format_physical_width(runtime->format);
+
+		switch (bits) {
+		case 8:
+			buswidth = DMA_SLAVE_BUSWIDTH_1_BYTE;
+			break;
+		case 16:
+			buswidth = DMA_SLAVE_BUSWIDTH_2_BYTES;
+			break;
+		case 32:
+			buswidth = DMA_SLAVE_BUSWIDTH_4_BYTES;
+			break;
+		default:
+			dev_err(dev, "invalid format width %d\n", bits);
+			return -EINVAL;
+		}
+	}
+
 	cfg.direction	= is_play ? DMA_MEM_TO_DEV : DMA_DEV_TO_MEM;
 	cfg.src_addr	= dma->src_addr;
 	cfg.dst_addr	= dma->dst_addr;
-	cfg.src_addr_width = DMA_SLAVE_BUSWIDTH_4_BYTES;
-	cfg.dst_addr_width = DMA_SLAVE_BUSWIDTH_4_BYTES;
+	cfg.src_addr_width = buswidth;
+	cfg.dst_addr_width = buswidth;
 
 	dev_dbg(dev, "%s %pad -> %pad\n",
 		rsnd_mod_name(mod),
diff --git a/sound/soc/sh/siu_pcm.c b/sound/soc/sh/siu_pcm.c
index 78c3145b4109..a5e21e554da2 100644
--- a/sound/soc/sh/siu_pcm.c
+++ b/sound/soc/sh/siu_pcm.c
@@ -281,7 +281,8 @@ static int siu_pcm_stmread_stop(struct siu_port *port_info)
 	return 0;
 }
 
-static int siu_pcm_hw_params(struct snd_pcm_substream *ss,
+static int siu_pcm_hw_params(struct snd_soc_component *component,
+			     struct snd_pcm_substream *ss,
 			     struct snd_pcm_hw_params *hw_params)
 {
 	struct siu_info *info = siu_i2s_data;
@@ -297,7 +298,8 @@ static int siu_pcm_hw_params(struct snd_pcm_substream *ss,
 	return ret;
 }
 
-static int siu_pcm_hw_free(struct snd_pcm_substream *ss)
+static int siu_pcm_hw_free(struct snd_soc_component *component,
+			   struct snd_pcm_substream *ss)
 {
 	struct siu_info *info = siu_i2s_data;
 	struct siu_port	*port_info = siu_port_info(ss);
@@ -324,11 +326,10 @@ static bool filter(struct dma_chan *chan, void *slave)
 	return true;
 }
 
-static int siu_pcm_open(struct snd_pcm_substream *ss)
+static int siu_pcm_open(struct snd_soc_component *component,
+			struct snd_pcm_substream *ss)
 {
 	/* Playback / Capture */
-	struct snd_soc_pcm_runtime *rtd = ss->private_data;
-	struct snd_soc_component *component = snd_soc_rtdcom_lookup(rtd, DRV_NAME);
 	struct siu_platform *pdata = component->dev->platform_data;
 	struct siu_info *info = siu_i2s_data;
 	struct siu_port *port_info = siu_port_info(ss);
@@ -367,7 +368,8 @@ static int siu_pcm_open(struct snd_pcm_substream *ss)
 	return 0;
 }
 
-static int siu_pcm_close(struct snd_pcm_substream *ss)
+static int siu_pcm_close(struct snd_soc_component *component,
+			 struct snd_pcm_substream *ss)
 {
 	struct siu_info *info = siu_i2s_data;
 	struct device *dev = ss->pcm->card->dev;
@@ -389,7 +391,8 @@ static int siu_pcm_close(struct snd_pcm_substream *ss)
 	return 0;
 }
 
-static int siu_pcm_prepare(struct snd_pcm_substream *ss)
+static int siu_pcm_prepare(struct snd_soc_component *component,
+			   struct snd_pcm_substream *ss)
 {
 	struct siu_info *info = siu_i2s_data;
 	struct siu_port *port_info = siu_port_info(ss);
@@ -435,7 +438,8 @@ static int siu_pcm_prepare(struct snd_pcm_substream *ss)
 	return 0;
 }
 
-static int siu_pcm_trigger(struct snd_pcm_substream *ss, int cmd)
+static int siu_pcm_trigger(struct snd_soc_component *component,
+			   struct snd_pcm_substream *ss, int cmd)
 {
 	struct siu_info *info = siu_i2s_data;
 	struct device *dev = ss->pcm->card->dev;
@@ -477,7 +481,9 @@ static int siu_pcm_trigger(struct snd_pcm_substream *ss, int cmd)
  * So far only resolution of one period is supported, subject to extending the
  * dmangine API
  */
-static snd_pcm_uframes_t siu_pcm_pointer_dma(struct snd_pcm_substream *ss)
+static snd_pcm_uframes_t
+siu_pcm_pointer_dma(struct snd_soc_component *component,
+		    struct snd_pcm_substream *ss)
 {
 	struct device *dev = ss->pcm->card->dev;
 	struct siu_info *info = siu_i2s_data;
@@ -512,7 +518,8 @@ static snd_pcm_uframes_t siu_pcm_pointer_dma(struct snd_pcm_substream *ss)
 	return bytes_to_frames(ss->runtime, ptr);
 }
 
-static int siu_pcm_new(struct snd_soc_pcm_runtime *rtd)
+static int siu_pcm_new(struct snd_soc_component *component,
+		       struct snd_soc_pcm_runtime *rtd)
 {
 	/* card->dev == socdev->dev, see snd_soc_new_pcms() */
 	struct snd_card *card = rtd->card->snd_card;
@@ -558,7 +565,8 @@ static int siu_pcm_new(struct snd_soc_pcm_runtime *rtd)
 	return 0;
 }
 
-static void siu_pcm_free(struct snd_pcm *pcm)
+static void siu_pcm_free(struct snd_soc_component *component,
+			 struct snd_pcm *pcm)
 {
 	struct platform_device *pdev = to_platform_device(pcm->card->dev);
 	struct siu_port *port_info = siu_ports[pdev->id];
@@ -571,21 +579,17 @@ static void siu_pcm_free(struct snd_pcm *pcm)
 	dev_dbg(pcm->card->dev, "%s\n", __func__);
 }
 
-static const struct snd_pcm_ops siu_pcm_ops = {
+struct const snd_soc_component_driver siu_component = {
+	.name		= DRV_NAME,
 	.open		= siu_pcm_open,
 	.close		= siu_pcm_close,
-	.ioctl		= snd_pcm_lib_ioctl,
+	.ioctl		= snd_soc_pcm_lib_ioctl,
 	.hw_params	= siu_pcm_hw_params,
 	.hw_free	= siu_pcm_hw_free,
 	.prepare	= siu_pcm_prepare,
 	.trigger	= siu_pcm_trigger,
 	.pointer	= siu_pcm_pointer_dma,
-};
-
-struct snd_soc_component_driver siu_component = {
-	.name		= DRV_NAME,
-	.ops			= &siu_pcm_ops,
-	.pcm_new	= siu_pcm_new,
-	.pcm_free	= siu_pcm_free,
+	.pcm_construct	= siu_pcm_new,
+	.pcm_destruct	= siu_pcm_free,
 };
 EXPORT_SYMBOL_GPL(siu_component);
diff --git a/sound/soc/soc-component.c b/sound/soc/soc-component.c
index 79ffc2820ba9..9054558ce386 100644
--- a/sound/soc/soc-component.c
+++ b/sound/soc/soc-component.c
@@ -314,30 +314,24 @@ void snd_soc_component_module_put(struct snd_soc_component *component,
 int snd_soc_component_open(struct snd_soc_component *component,
 			   struct snd_pcm_substream *substream)
 {
-	if (component->driver->ops &&
-	    component->driver->ops->open)
-		return component->driver->ops->open(substream);
-
+	if (component->driver->open)
+		return component->driver->open(component, substream);
 	return 0;
 }
 
 int snd_soc_component_close(struct snd_soc_component *component,
 			    struct snd_pcm_substream *substream)
 {
-	if (component->driver->ops &&
-	    component->driver->ops->close)
-		return component->driver->ops->close(substream);
-
+	if (component->driver->close)
+		return component->driver->close(component, substream);
 	return 0;
 }
 
 int snd_soc_component_prepare(struct snd_soc_component *component,
 			      struct snd_pcm_substream *substream)
 {
-	if (component->driver->ops &&
-	    component->driver->ops->prepare)
-		return component->driver->ops->prepare(substream);
-
+	if (component->driver->prepare)
+		return component->driver->prepare(component, substream);
 	return 0;
 }
 
@@ -345,20 +339,17 @@ int snd_soc_component_hw_params(struct snd_soc_component *component,
 				struct snd_pcm_substream *substream,
 				struct snd_pcm_hw_params *params)
 {
-	if (component->driver->ops &&
-	    component->driver->ops->hw_params)
-		return component->driver->ops->hw_params(substream, params);
-
+	if (component->driver->hw_params)
+		return component->driver->hw_params(component,
+						    substream, params);
 	return 0;
 }
 
 int snd_soc_component_hw_free(struct snd_soc_component *component,
 			       struct snd_pcm_substream *substream)
 {
-	if (component->driver->ops &&
-	    component->driver->ops->hw_free)
-		return component->driver->ops->hw_free(substream);
-
+	if (component->driver->hw_free)
+		return component->driver->hw_free(component, substream);
 	return 0;
 }
 
@@ -366,10 +357,8 @@ int snd_soc_component_trigger(struct snd_soc_component *component,
 			      struct snd_pcm_substream *substream,
 			      int cmd)
 {
-	if (component->driver->ops &&
-	    component->driver->ops->trigger)
-		return component->driver->ops->trigger(substream, cmd);
-
+	if (component->driver->trigger)
+		return component->driver->trigger(component, substream, cmd);
 	return 0;
 }
 
@@ -431,14 +420,10 @@ int snd_soc_pcm_component_pointer(struct snd_pcm_substream *substream)
 	struct snd_soc_component *component;
 	struct snd_soc_rtdcom_list *rtdcom;
 
-	for_each_rtdcom(rtd, rtdcom) {
-		component = rtdcom->component;
-
-		/* FIXME: use 1st pointer */
-		if (component->driver->ops &&
-		    component->driver->ops->pointer)
-			return component->driver->ops->pointer(substream);
-	}
+	/* FIXME: use 1st pointer */
+	for_each_rtd_components(rtd, rtdcom, component)
+		if (component->driver->pointer)
+			return component->driver->pointer(component, substream);
 
 	return 0;
 }
@@ -450,17 +435,32 @@ int snd_soc_pcm_component_ioctl(struct snd_pcm_substream *substream,
 	struct snd_soc_component *component;
 	struct snd_soc_rtdcom_list *rtdcom;
 
-	for_each_rtdcom(rtd, rtdcom) {
-		component = rtdcom->component;
+	/* FIXME: use 1st ioctl */
+	for_each_rtd_components(rtd, rtdcom, component)
+		if (component->driver->ioctl)
+			return component->driver->ioctl(component, substream,
+							cmd, arg);
+
+	return snd_pcm_lib_ioctl(substream, cmd, arg);
+}
+
+int snd_soc_pcm_component_sync_stop(struct snd_pcm_substream *substream)
+{
+	struct snd_soc_pcm_runtime *rtd = substream->private_data;
+	struct snd_soc_component *component;
+	struct snd_soc_rtdcom_list *rtdcom;
+	int ret;
 
-		/* FIXME: use 1st ioctl */
-		if (component->driver->ops &&
-		    component->driver->ops->ioctl)
-			return component->driver->ops->ioctl(substream,
-							     cmd, arg);
+	for_each_rtd_components(rtd, rtdcom, component) {
+		if (component->driver->ioctl) {
+			ret = component->driver->sync_stop(component,
+							   substream);
+			if (ret < 0)
+				return ret;
+		}
 	}
 
-	return snd_pcm_lib_ioctl(substream, cmd, arg);
+	return 0;
 }
 
 int snd_soc_pcm_component_copy_user(struct snd_pcm_substream *substream,
@@ -471,15 +471,11 @@ int snd_soc_pcm_component_copy_user(struct snd_pcm_substream *substream,
 	struct snd_soc_rtdcom_list *rtdcom;
 	struct snd_soc_component *component;
 
-	for_each_rtdcom(rtd, rtdcom) {
-		component = rtdcom->component;
-
-		/* FIXME. it returns 1st copy now */
-		if (component->driver->ops &&
-		    component->driver->ops->copy_user)
-			return component->driver->ops->copy_user(
-				substream, channel, pos, buf, bytes);
-	}
+	/* FIXME. it returns 1st copy now */
+	for_each_rtd_components(rtd, rtdcom, component)
+		if (component->driver->copy_user)
+			return component->driver->copy_user(
+				component, substream, channel, pos, buf, bytes);
 
 	return -EINVAL;
 }
@@ -492,13 +488,11 @@ struct page *snd_soc_pcm_component_page(struct snd_pcm_substream *substream,
 	struct snd_soc_component *component;
 	struct page *page;
 
-	for_each_rtdcom(rtd, rtdcom) {
-		component = rtdcom->component;
-
-		/* FIXME. it returns 1st page now */
-		if (component->driver->ops &&
-		    component->driver->ops->page) {
-			page = component->driver->ops->page(substream, offset);
+	/* FIXME. it returns 1st page now */
+	for_each_rtd_components(rtd, rtdcom, component) {
+		if (component->driver->page) {
+			page = component->driver->page(component,
+						       substream, offset);
 			if (page)
 				return page;
 		}
@@ -514,30 +508,24 @@ int snd_soc_pcm_component_mmap(struct snd_pcm_substream *substream,
 	struct snd_soc_rtdcom_list *rtdcom;
 	struct snd_soc_component *component;
 
-	for_each_rtdcom(rtd, rtdcom) {
-		component = rtdcom->component;
-
-		/* FIXME. it returns 1st mmap now */
-		if (component->driver->ops &&
-		    component->driver->ops->mmap)
-			return component->driver->ops->mmap(substream, vma);
-	}
+	/* FIXME. it returns 1st mmap now */
+	for_each_rtd_components(rtd, rtdcom, component)
+		if (component->driver->mmap)
+			return component->driver->mmap(component,
+						       substream, vma);
 
 	return -EINVAL;
 }
 
-int snd_soc_pcm_component_new(struct snd_pcm *pcm)
+int snd_soc_pcm_component_new(struct snd_soc_pcm_runtime *rtd)
 {
-	struct snd_soc_pcm_runtime *rtd = pcm->private_data;
 	struct snd_soc_rtdcom_list *rtdcom;
 	struct snd_soc_component *component;
 	int ret;
 
-	for_each_rtdcom(rtd, rtdcom) {
-		component = rtdcom->component;
-
-		if (component->driver->pcm_new) {
-			ret = component->driver->pcm_new(rtd);
+	for_each_rtd_components(rtd, rtdcom, component) {
+		if (component->driver->pcm_construct) {
+			ret = component->driver->pcm_construct(component, rtd);
 			if (ret < 0)
 				return ret;
 		}
@@ -546,16 +534,12 @@ int snd_soc_pcm_component_new(struct snd_pcm *pcm)
 	return 0;
 }
 
-void snd_soc_pcm_component_free(struct snd_pcm *pcm)
+void snd_soc_pcm_component_free(struct snd_soc_pcm_runtime *rtd)
 {
-	struct snd_soc_pcm_runtime *rtd = pcm->private_data;
 	struct snd_soc_rtdcom_list *rtdcom;
 	struct snd_soc_component *component;
 
-	for_each_rtdcom(rtd, rtdcom) {
-		component = rtdcom->component;
-
-		if (component->driver->pcm_free)
-			component->driver->pcm_free(pcm);
-	}
+	for_each_rtd_components(rtd, rtdcom, component)
+		if (component->driver->pcm_destruct)
+			component->driver->pcm_destruct(component, rtd->pcm);
 }
diff --git a/sound/soc/soc-compress.c b/sound/soc/soc-compress.c
index 9e54d8ae6d2c..61f230324164 100644
--- a/sound/soc/soc-compress.c
+++ b/sound/soc/soc-compress.c
@@ -28,9 +28,7 @@ static int soc_compr_components_open(struct snd_compr_stream *cstream,
 	struct snd_soc_rtdcom_list *rtdcom;
 	int ret;
 
-	for_each_rtdcom(rtd, rtdcom) {
-		component = rtdcom->component;
-
+	for_each_rtd_components(rtd, rtdcom, component) {
 		if (!component->driver->compr_ops ||
 		    !component->driver->compr_ops->open)
 			continue;
@@ -57,9 +55,7 @@ static int soc_compr_components_free(struct snd_compr_stream *cstream,
 	struct snd_soc_component *component;
 	struct snd_soc_rtdcom_list *rtdcom;
 
-	for_each_rtdcom(rtd, rtdcom) {
-		component = rtdcom->component;
-
+	for_each_rtd_components(rtd, rtdcom, component) {
 		if (component == last)
 			break;
 
@@ -353,9 +349,7 @@ static int soc_compr_components_trigger(struct snd_compr_stream *cstream,
 	struct snd_soc_rtdcom_list *rtdcom;
 	int ret;
 
-	for_each_rtdcom(rtd, rtdcom) {
-		component = rtdcom->component;
-
+	for_each_rtd_components(rtd, rtdcom, component) {
 		if (!component->driver->compr_ops ||
 		    !component->driver->compr_ops->trigger)
 			continue;
@@ -458,9 +452,7 @@ static int soc_compr_components_set_params(struct snd_compr_stream *cstream,
 	struct snd_soc_rtdcom_list *rtdcom;
 	int ret;
 
-	for_each_rtdcom(rtd, rtdcom) {
-		component = rtdcom->component;
-
+	for_each_rtd_components(rtd, rtdcom, component) {
 		if (!component->driver->compr_ops ||
 		    !component->driver->compr_ops->set_params)
 			continue;
@@ -601,9 +593,7 @@ static int soc_compr_get_params(struct snd_compr_stream *cstream,
 			goto err;
 	}
 
-	for_each_rtdcom(rtd, rtdcom) {
-		component = rtdcom->component;
-
+	for_each_rtd_components(rtd, rtdcom, component) {
 		if (!component->driver->compr_ops ||
 		    !component->driver->compr_ops->get_params)
 			continue;
@@ -627,9 +617,7 @@ static int soc_compr_get_caps(struct snd_compr_stream *cstream,
 
 	mutex_lock_nested(&rtd->card->pcm_mutex, rtd->card->pcm_subclass);
 
-	for_each_rtdcom(rtd, rtdcom) {
-		component = rtdcom->component;
-
+	for_each_rtd_components(rtd, rtdcom, component) {
 		if (!component->driver->compr_ops ||
 		    !component->driver->compr_ops->get_caps)
 			continue;
@@ -652,9 +640,7 @@ static int soc_compr_get_codec_caps(struct snd_compr_stream *cstream,
 
 	mutex_lock_nested(&rtd->card->pcm_mutex, rtd->card->pcm_subclass);
 
-	for_each_rtdcom(rtd, rtdcom) {
-		component = rtdcom->component;
-
+	for_each_rtd_components(rtd, rtdcom, component) {
 		if (!component->driver->compr_ops ||
 		    !component->driver->compr_ops->get_codec_caps)
 			continue;
@@ -684,9 +670,7 @@ static int soc_compr_ack(struct snd_compr_stream *cstream, size_t bytes)
 			goto err;
 	}
 
-	for_each_rtdcom(rtd, rtdcom) {
-		component = rtdcom->component;
-
+	for_each_rtd_components(rtd, rtdcom, component) {
 		if (!component->driver->compr_ops ||
 		    !component->driver->compr_ops->ack)
 			continue;
@@ -715,9 +699,7 @@ static int soc_compr_pointer(struct snd_compr_stream *cstream,
 	if (cpu_dai->driver->cops && cpu_dai->driver->cops->pointer)
 		cpu_dai->driver->cops->pointer(cstream, tstamp, cpu_dai);
 
-	for_each_rtdcom(rtd, rtdcom) {
-		component = rtdcom->component;
-
+	for_each_rtd_components(rtd, rtdcom, component) {
 		if (!component->driver->compr_ops ||
 		    !component->driver->compr_ops->pointer)
 			continue;
@@ -740,9 +722,7 @@ static int soc_compr_copy(struct snd_compr_stream *cstream,
 
 	mutex_lock_nested(&rtd->card->pcm_mutex, rtd->card->pcm_subclass);
 
-	for_each_rtdcom(rtd, rtdcom) {
-		component = rtdcom->component;
-
+	for_each_rtd_components(rtd, rtdcom, component) {
 		if (!component->driver->compr_ops ||
 		    !component->driver->compr_ops->copy)
 			continue;
@@ -770,9 +750,7 @@ static int soc_compr_set_metadata(struct snd_compr_stream *cstream,
 			return ret;
 	}
 
-	for_each_rtdcom(rtd, rtdcom) {
-		component = rtdcom->component;
-
+	for_each_rtd_components(rtd, rtdcom, component) {
 		if (!component->driver->compr_ops ||
 		    !component->driver->compr_ops->set_metadata)
 			continue;
@@ -801,9 +779,7 @@ static int soc_compr_get_metadata(struct snd_compr_stream *cstream,
 			return ret;
 	}
 
-	for_each_rtdcom(rtd, rtdcom) {
-		component = rtdcom->component;
-
+	for_each_rtd_components(rtd, rtdcom, component) {
 		if (!component->driver->compr_ops ||
 		    !component->driver->compr_ops->get_metadata)
 			continue;
@@ -932,9 +908,7 @@ int snd_soc_new_compress(struct snd_soc_pcm_runtime *rtd, int num)
 		memcpy(compr->ops, &soc_compr_ops, sizeof(soc_compr_ops));
 	}
 
-	for_each_rtdcom(rtd, rtdcom) {
-		component = rtdcom->component;
-
+	for_each_rtd_components(rtd, rtdcom, component) {
 		if (!component->driver->compr_ops ||
 		    !component->driver->compr_ops->copy)
 			continue;
diff --git a/sound/soc/soc-core.c b/sound/soc/soc-core.c
index 88978a3036c4..062653ab03a3 100644
--- a/sound/soc/soc-core.c
+++ b/sound/soc/soc-core.c
@@ -125,6 +125,9 @@ static umode_t soc_dev_attr_is_visible(struct kobject *kobj,
 	struct device *dev = kobj_to_dev(kobj);
 	struct snd_soc_pcm_runtime *rtd = dev_get_drvdata(dev);
 
+	if (!rtd)
+		return 0;
+
 	if (attr == &dev_attr_pmdown_time.attr)
 		return attr->mode; /* always visible */
 	return rtd->num_codecs ? attr->mode : 0; /* enabled only with codec */
@@ -274,43 +277,58 @@ static inline void snd_soc_debugfs_exit(void)
 
 #endif
 
+/*
+ * This is glue code between snd_pcm_lib_ioctl() and
+ * snd_soc_component_driver :: ioctl
+ */
+int snd_soc_pcm_lib_ioctl(struct snd_soc_component *component,
+			  struct snd_pcm_substream *substream,
+			  unsigned int cmd, void *arg)
+{
+	return snd_pcm_lib_ioctl(substream, cmd, arg);
+}
+EXPORT_SYMBOL_GPL(snd_soc_pcm_lib_ioctl);
+
 static int snd_soc_rtdcom_add(struct snd_soc_pcm_runtime *rtd,
 			      struct snd_soc_component *component)
 {
 	struct snd_soc_rtdcom_list *rtdcom;
+	struct snd_soc_component *comp;
 
-	for_each_rtdcom(rtd, rtdcom) {
+	for_each_rtd_components(rtd, rtdcom, comp) {
 		/* already connected */
-		if (rtdcom->component == component)
+		if (comp == component)
 			return 0;
 	}
 
-	rtdcom = kmalloc(sizeof(*rtdcom), GFP_KERNEL);
+	/*
+	 * created rtdcom here will be freed when rtd->dev was freed.
+	 * see
+	 *	soc_free_pcm_runtime() :: device_unregister(rtd->dev)
+	 */
+	rtdcom = devm_kzalloc(rtd->dev, sizeof(*rtdcom), GFP_KERNEL);
 	if (!rtdcom)
 		return -ENOMEM;
 
 	rtdcom->component = component;
 	INIT_LIST_HEAD(&rtdcom->list);
 
+	/*
+	 * When rtd was freed, created rtdcom here will be
+	 * also freed.
+	 * And we don't need to call list_del(&rtdcom->list)
+	 * when freed, because rtd is also freed.
+	 */
 	list_add_tail(&rtdcom->list, &rtd->component_list);
 
 	return 0;
 }
 
-static void snd_soc_rtdcom_del_all(struct snd_soc_pcm_runtime *rtd)
-{
-	struct snd_soc_rtdcom_list *rtdcom1, *rtdcom2;
-
-	for_each_rtdcom_safe(rtd, rtdcom1, rtdcom2)
-		kfree(rtdcom1);
-
-	INIT_LIST_HEAD(&rtd->component_list);
-}
-
 struct snd_soc_component *snd_soc_rtdcom_lookup(struct snd_soc_pcm_runtime *rtd,
 						const char *driver_name)
 {
 	struct snd_soc_rtdcom_list *rtdcom;
+	struct snd_soc_component *component;
 
 	if (!driver_name)
 		return NULL;
@@ -323,8 +341,8 @@ struct snd_soc_component *snd_soc_rtdcom_lookup(struct snd_soc_pcm_runtime *rtd,
 	 * But, if many components which have same driver name are connected
 	 * to 1 rtd, this function will return 1st found component.
 	 */
-	for_each_rtdcom(rtd, rtdcom) {
-		const char *component_name = rtdcom->component->driver->name;
+	for_each_rtd_components(rtd, rtdcom, component) {
+		const char *component_name = component->driver->name;
 
 		if (!component_name)
 			continue;
@@ -338,6 +356,39 @@ struct snd_soc_component *snd_soc_rtdcom_lookup(struct snd_soc_pcm_runtime *rtd,
 }
 EXPORT_SYMBOL_GPL(snd_soc_rtdcom_lookup);
 
+static struct snd_soc_component
+*snd_soc_lookup_component_nolocked(struct device *dev, const char *driver_name)
+{
+	struct snd_soc_component *component;
+	struct snd_soc_component *found_component;
+
+	found_component = NULL;
+	for_each_component(component) {
+		if ((dev == component->dev) &&
+		    (!driver_name ||
+		     (driver_name == component->driver->name) ||
+		     (strcmp(component->driver->name, driver_name) == 0))) {
+			found_component = component;
+			break;
+		}
+	}
+
+	return found_component;
+}
+
+struct snd_soc_component *snd_soc_lookup_component(struct device *dev,
+						   const char *driver_name)
+{
+	struct snd_soc_component *component;
+
+	mutex_lock(&client_mutex);
+	component = snd_soc_lookup_component_nolocked(dev, driver_name);
+	mutex_unlock(&client_mutex);
+
+	return component;
+}
+EXPORT_SYMBOL_GPL(snd_soc_lookup_component);
+
 struct snd_pcm_substream *snd_soc_get_dai_substream(struct snd_soc_card *card,
 		const char *dai_link, int stream)
 {
@@ -355,58 +406,104 @@ EXPORT_SYMBOL_GPL(snd_soc_get_dai_substream);
 
 static const struct snd_soc_ops null_snd_soc_ops;
 
+static void soc_release_rtd_dev(struct device *dev)
+{
+	/* "dev" means "rtd->dev" */
+	kfree(dev);
+}
+
+static void soc_free_pcm_runtime(struct snd_soc_pcm_runtime *rtd)
+{
+	if (!rtd)
+		return;
+
+	list_del(&rtd->list);
+
+	flush_delayed_work(&rtd->delayed_work);
+	snd_soc_pcm_component_free(rtd);
+
+	/*
+	 * we don't need to call kfree() for rtd->dev
+	 * see
+	 *	soc_release_rtd_dev()
+	 *
+	 * We don't need rtd->dev NULL check, because
+	 * it is alloced *before* rtd.
+	 * see
+	 *	soc_new_pcm_runtime()
+	 */
+	device_unregister(rtd->dev);
+}
+
 static struct snd_soc_pcm_runtime *soc_new_pcm_runtime(
 	struct snd_soc_card *card, struct snd_soc_dai_link *dai_link)
 {
 	struct snd_soc_pcm_runtime *rtd;
+	struct device *dev;
+	int ret;
 
-	rtd = kzalloc(sizeof(struct snd_soc_pcm_runtime), GFP_KERNEL);
-	if (!rtd)
+	/*
+	 * for rtd->dev
+	 */
+	dev = kzalloc(sizeof(struct device), GFP_KERNEL);
+	if (!dev)
 		return NULL;
 
-	INIT_LIST_HEAD(&rtd->component_list);
-	rtd->card = card;
-	rtd->dai_link = dai_link;
-	if (!rtd->dai_link->ops)
-		rtd->dai_link->ops = &null_snd_soc_ops;
+	dev->parent	= card->dev;
+	dev->release	= soc_release_rtd_dev;
+	dev->groups	= soc_dev_attr_groups;
 
-	rtd->codec_dais = kcalloc(dai_link->num_codecs,
-					sizeof(struct snd_soc_dai *),
-					GFP_KERNEL);
-	if (!rtd->codec_dais) {
-		kfree(rtd);
+	dev_set_name(dev, "%s", dai_link->name);
+
+	ret = device_register(dev);
+	if (ret < 0) {
+		put_device(dev); /* soc_release_rtd_dev */
 		return NULL;
 	}
 
-	return rtd;
-}
+	/*
+	 * for rtd
+	 */
+	rtd = devm_kzalloc(dev, sizeof(*rtd), GFP_KERNEL);
+	if (!rtd)
+		goto free_rtd;
 
-static void soc_free_pcm_runtime(struct snd_soc_pcm_runtime *rtd)
-{
-	kfree(rtd->codec_dais);
-	snd_soc_rtdcom_del_all(rtd);
-	kfree(rtd);
-}
+	rtd->dev = dev;
+	dev_set_drvdata(dev, rtd);
+
+	/*
+	 * for rtd->codec_dais
+	 */
+	rtd->codec_dais = devm_kcalloc(dev, dai_link->num_codecs,
+					sizeof(struct snd_soc_dai *),
+					GFP_KERNEL);
+	if (!rtd->codec_dais)
+		goto free_rtd;
+
+	/*
+	 * rtd remaining settings
+	 */
+	INIT_LIST_HEAD(&rtd->component_list);
+	INIT_LIST_HEAD(&rtd->dpcm[SNDRV_PCM_STREAM_PLAYBACK].be_clients);
+	INIT_LIST_HEAD(&rtd->dpcm[SNDRV_PCM_STREAM_CAPTURE].be_clients);
+	INIT_LIST_HEAD(&rtd->dpcm[SNDRV_PCM_STREAM_PLAYBACK].fe_clients);
+	INIT_LIST_HEAD(&rtd->dpcm[SNDRV_PCM_STREAM_CAPTURE].fe_clients);
+
+	rtd->card = card;
+	rtd->dai_link = dai_link;
+	if (!rtd->dai_link->ops)
+		rtd->dai_link->ops = &null_snd_soc_ops;
 
-static void soc_add_pcm_runtime(struct snd_soc_card *card,
-		struct snd_soc_pcm_runtime *rtd)
-{
 	/* see for_each_card_rtds */
 	list_add_tail(&rtd->list, &card->rtd_list);
 	rtd->num = card->num_rtd;
 	card->num_rtd++;
-}
 
-static void soc_remove_pcm_runtimes(struct snd_soc_card *card)
-{
-	struct snd_soc_pcm_runtime *rtd, *_rtd;
-
-	for_each_card_rtds_safe(card, rtd, _rtd) {
-		list_del(&rtd->list);
-		soc_free_pcm_runtime(rtd);
-	}
+	return rtd;
 
-	card->num_rtd = 0;
+free_rtd:
+	soc_free_pcm_runtime(rtd);
+	return NULL;
 }
 
 struct snd_soc_pcm_runtime *snd_soc_get_pcm_runtime(struct snd_soc_card *card,
@@ -859,37 +956,168 @@ struct snd_soc_dai_link *snd_soc_find_dai_link(struct snd_soc_card *card,
 }
 EXPORT_SYMBOL_GPL(snd_soc_find_dai_link);
 
-static bool soc_is_dai_link_bound(struct snd_soc_card *card,
-		struct snd_soc_dai_link *dai_link)
+static int soc_dai_link_sanity_check(struct snd_soc_card *card,
+				     struct snd_soc_dai_link *link)
 {
-	struct snd_soc_pcm_runtime *rtd;
+	int i;
+	struct snd_soc_dai_link_component *codec, *platform;
 
-	for_each_card_rtds(card, rtd) {
-		if (rtd->dai_link == dai_link)
-			return true;
+	for_each_link_codecs(link, i, codec) {
+		/*
+		 * Codec must be specified by 1 of name or OF node,
+		 * not both or neither.
+		 */
+		if (!!codec->name == !!codec->of_node) {
+			dev_err(card->dev, "ASoC: Neither/both codec name/of_node are set for %s\n",
+				link->name);
+			return -EINVAL;
+		}
+
+		/* Codec DAI name must be specified */
+		if (!codec->dai_name) {
+			dev_err(card->dev, "ASoC: codec_dai_name not set for %s\n",
+				link->name);
+			return -EINVAL;
+		}
+
+		/*
+		 * Defer card registration if codec component is not added to
+		 * component list.
+		 */
+		if (!soc_find_component(codec))
+			return -EPROBE_DEFER;
 	}
 
-	return false;
+	for_each_link_platforms(link, i, platform) {
+		/*
+		 * Platform may be specified by either name or OF node, but it
+		 * can be left unspecified, then no components will be inserted
+		 * in the rtdcom list
+		 */
+		if (!!platform->name == !!platform->of_node) {
+			dev_err(card->dev,
+				"ASoC: Neither/both platform name/of_node are set for %s\n",
+				link->name);
+			return -EINVAL;
+		}
+
+		/*
+		 * Defer card registration if platform component is not added to
+		 * component list.
+		 */
+		if (!soc_find_component(platform))
+			return -EPROBE_DEFER;
+	}
+
+	/* FIXME */
+	if (link->num_cpus > 1) {
+		dev_err(card->dev,
+			"ASoC: multi cpu is not yet supported %s\n",
+			link->name);
+		return -EINVAL;
+	}
+
+	/*
+	 * CPU device may be specified by either name or OF node, but
+	 * can be left unspecified, and will be matched based on DAI
+	 * name alone..
+	 */
+	if (link->cpus->name && link->cpus->of_node) {
+		dev_err(card->dev,
+			"ASoC: Neither/both cpu name/of_node are set for %s\n",
+			link->name);
+		return -EINVAL;
+	}
+
+	/*
+	 * Defer card registration if cpu dai component is not added to
+	 * component list.
+	 */
+	if ((link->cpus->of_node || link->cpus->name) &&
+	    !soc_find_component(link->cpus))
+		return -EPROBE_DEFER;
+
+	/*
+	 * At least one of CPU DAI name or CPU device name/node must be
+	 * specified
+	 */
+	if (!link->cpus->dai_name &&
+	    !(link->cpus->name || link->cpus->of_node)) {
+		dev_err(card->dev,
+			"ASoC: Neither cpu_dai_name nor cpu_name/of_node are set for %s\n",
+			link->name);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+/**
+ * snd_soc_remove_dai_link - Remove a DAI link from the list
+ * @card: The ASoC card that owns the link
+ * @dai_link: The DAI link to remove
+ *
+ * This function removes a DAI link from the ASoC card's link list.
+ *
+ * For DAI links previously added by topology, topology should
+ * remove them by using the dobj embedded in the link.
+ */
+void snd_soc_remove_dai_link(struct snd_soc_card *card,
+			     struct snd_soc_dai_link *dai_link)
+{
+	struct snd_soc_pcm_runtime *rtd;
+
+	lockdep_assert_held(&client_mutex);
+
+	/*
+	 * Notify the machine driver for extra destruction
+	 */
+	if (card->remove_dai_link)
+		card->remove_dai_link(card, dai_link);
+
+	list_del(&dai_link->list);
+
+	rtd = snd_soc_get_pcm_runtime(card, dai_link->name);
+	if (rtd)
+		soc_free_pcm_runtime(rtd);
 }
+EXPORT_SYMBOL_GPL(snd_soc_remove_dai_link);
 
-static int soc_bind_dai_link(struct snd_soc_card *card,
-	struct snd_soc_dai_link *dai_link)
+/**
+ * snd_soc_add_dai_link - Add a DAI link dynamically
+ * @card: The ASoC card to which the DAI link is added
+ * @dai_link: The new DAI link to add
+ *
+ * This function adds a DAI link to the ASoC card's link list.
+ *
+ * Note: Topology can use this API to add DAI links when probing the
+ * topology component. And machine drivers can still define static
+ * DAI links in dai_link array.
+ */
+int snd_soc_add_dai_link(struct snd_soc_card *card,
+			 struct snd_soc_dai_link *dai_link)
 {
 	struct snd_soc_pcm_runtime *rtd;
 	struct snd_soc_dai_link_component *codec, *platform;
 	struct snd_soc_component *component;
-	int i;
+	int i, ret;
+
+	lockdep_assert_held(&client_mutex);
+
+	/*
+	 * Notify the machine driver for extra initialization
+	 */
+	if (card->add_dai_link)
+		card->add_dai_link(card, dai_link);
 
 	if (dai_link->ignore)
 		return 0;
 
 	dev_dbg(card->dev, "ASoC: binding %s\n", dai_link->name);
 
-	if (soc_is_dai_link_bound(card, dai_link)) {
-		dev_dbg(card->dev, "ASoC: dai link %s already bound\n",
-			dai_link->name);
-		return 0;
-	}
+	ret = soc_dai_link_sanity_check(card, dai_link);
+	if (ret < 0)
+		return ret;
 
 	rtd = soc_new_pcm_runtime(card, dai_link);
 	if (!rtd)
@@ -930,13 +1158,16 @@ static int soc_bind_dai_link(struct snd_soc_card *card,
 		}
 	}
 
-	soc_add_pcm_runtime(card, rtd);
+	/* see for_each_card_links */
+	list_add_tail(&dai_link->list, &card->dai_link_list);
+
 	return 0;
 
 _err_defer:
 	soc_free_pcm_runtime(rtd);
 	return -EPROBE_DEFER;
 }
+EXPORT_SYMBOL_GPL(snd_soc_add_dai_link);
 
 static void soc_set_of_name_prefix(struct snd_soc_component *component)
 {
@@ -973,8 +1204,16 @@ static void soc_set_name_prefix(struct snd_soc_card *card,
 	soc_set_of_name_prefix(component);
 }
 
-static void soc_cleanup_component(struct snd_soc_component *component)
+static void soc_remove_component(struct snd_soc_component *component,
+				 int probed)
 {
+
+	if (!component->card)
+		return;
+
+	if (probed)
+		snd_soc_component_remove(component);
+
 	/* For framework level robustness */
 	snd_soc_component_set_jack(component, NULL, NULL);
 
@@ -985,22 +1224,13 @@ static void soc_cleanup_component(struct snd_soc_component *component)
 	snd_soc_component_module_put_when_remove(component);
 }
 
-static void soc_remove_component(struct snd_soc_component *component)
-{
-	if (!component->card)
-		return;
-
-	snd_soc_component_remove(component);
-
-	soc_cleanup_component(component);
-}
-
 static int soc_probe_component(struct snd_soc_card *card,
 			       struct snd_soc_component *component)
 {
 	struct snd_soc_dapm_context *dapm =
 		snd_soc_component_get_dapm(component);
 	struct snd_soc_dai *dai;
+	int probed = 0;
 	int ret;
 
 	if (!strcmp(component->name, "snd-soc-dummy"))
@@ -1056,6 +1286,7 @@ static int soc_probe_component(struct snd_soc_card *card,
 	     dapm->bias_level != SND_SOC_BIAS_OFF,
 	     "codec %s can not start from non-off bias with idle_bias_off==1\n",
 	     component->name);
+	probed = 1;
 
 	/* machine specific init */
 	if (component->init) {
@@ -1084,7 +1315,7 @@ static int soc_probe_component(struct snd_soc_card *card,
 
 err_probe:
 	if (ret < 0)
-		soc_cleanup_component(component);
+		soc_remove_component(component, probed);
 
 	return ret;
 }
@@ -1126,7 +1357,6 @@ static int soc_probe_dai(struct snd_soc_dai *dai, int order)
 	return 0;
 }
 
-static void soc_rtd_free(struct snd_soc_pcm_runtime *rtd); /* remove me */
 static void soc_remove_link_dais(struct snd_soc_card *card)
 {
 	int i;
@@ -1136,10 +1366,6 @@ static void soc_remove_link_dais(struct snd_soc_card *card)
 
 	for_each_comp_order(order) {
 		for_each_card_rtds(card, rtd) {
-
-			/* finalize rtd device */
-			soc_rtd_free(rtd);
-
 			/* remove the CODEC DAI */
 			for_each_rtd_codec_dai(rtd, i, codec_dai)
 				soc_remove_dai(codec_dai, order);
@@ -1187,13 +1413,11 @@ static void soc_remove_link_components(struct snd_soc_card *card)
 
 	for_each_comp_order(order) {
 		for_each_card_rtds(card, rtd) {
-			for_each_rtdcom(rtd, rtdcom) {
-				component = rtdcom->component;
-
+			for_each_rtd_components(rtd, rtdcom, component) {
 				if (component->driver->remove_order != order)
 					continue;
 
-				soc_remove_component(component);
+				soc_remove_component(component, 1);
 			}
 		}
 	}
@@ -1208,9 +1432,7 @@ static int soc_probe_link_components(struct snd_soc_card *card)
 
 	for_each_comp_order(order) {
 		for_each_card_rtds(card, rtd) {
-			for_each_rtdcom(rtd, rtdcom) {
-				component = rtdcom->component;
-
+			for_each_rtd_components(rtd, rtdcom, component) {
 				if (component->driver->probe_order != order)
 					continue;
 
@@ -1224,119 +1446,6 @@ static int soc_probe_link_components(struct snd_soc_card *card)
 	return 0;
 }
 
-static void soc_remove_dai_links(struct snd_soc_card *card)
-{
-	struct snd_soc_dai_link *link, *_link;
-
-	soc_remove_link_dais(card);
-
-	soc_remove_link_components(card);
-
-	for_each_card_links_safe(card, link, _link) {
-		if (link->dobj.type == SND_SOC_DOBJ_DAI_LINK)
-			dev_warn(card->dev, "Topology forgot to remove link %s?\n",
-				link->name);
-
-		list_del(&link->list);
-	}
-}
-
-static int soc_init_dai_link(struct snd_soc_card *card,
-			     struct snd_soc_dai_link *link)
-{
-	int i;
-	struct snd_soc_dai_link_component *codec, *platform;
-
-	for_each_link_codecs(link, i, codec) {
-		/*
-		 * Codec must be specified by 1 of name or OF node,
-		 * not both or neither.
-		 */
-		if (!!codec->name == !!codec->of_node) {
-			dev_err(card->dev, "ASoC: Neither/both codec name/of_node are set for %s\n",
-				link->name);
-			return -EINVAL;
-		}
-
-		/* Codec DAI name must be specified */
-		if (!codec->dai_name) {
-			dev_err(card->dev, "ASoC: codec_dai_name not set for %s\n",
-				link->name);
-			return -EINVAL;
-		}
-
-		/*
-		 * Defer card registration if codec component is not added to
-		 * component list.
-		 */
-		if (!soc_find_component(codec))
-			return -EPROBE_DEFER;
-	}
-
-	for_each_link_platforms(link, i, platform) {
-		/*
-		 * Platform may be specified by either name or OF node, but it
-		 * can be left unspecified, then no components will be inserted
-		 * in the rtdcom list
-		 */
-		if (!!platform->name == !!platform->of_node) {
-			dev_err(card->dev,
-				"ASoC: Neither/both platform name/of_node are set for %s\n",
-				link->name);
-			return -EINVAL;
-		}
-
-		/*
-		 * Defer card registration if platform component is not added to
-		 * component list.
-		 */
-		if (!soc_find_component(platform))
-			return -EPROBE_DEFER;
-	}
-
-	/* FIXME */
-	if (link->num_cpus > 1) {
-		dev_err(card->dev,
-			"ASoC: multi cpu is not yet supported %s\n",
-			link->name);
-		return -EINVAL;
-	}
-
-	/*
-	 * CPU device may be specified by either name or OF node, but
-	 * can be left unspecified, and will be matched based on DAI
-	 * name alone..
-	 */
-	if (link->cpus->name && link->cpus->of_node) {
-		dev_err(card->dev,
-			"ASoC: Neither/both cpu name/of_node are set for %s\n",
-			link->name);
-		return -EINVAL;
-	}
-
-	/*
-	 * Defer card registartion if cpu dai component is not added to
-	 * component list.
-	 */
-	if ((link->cpus->of_node || link->cpus->name) &&
-	    !soc_find_component(link->cpus))
-		return -EPROBE_DEFER;
-
-	/*
-	 * At least one of CPU DAI name or CPU device name/node must be
-	 * specified
-	 */
-	if (!link->cpus->dai_name &&
-	    !(link->cpus->name || link->cpus->of_node)) {
-		dev_err(card->dev,
-			"ASoC: Neither cpu_dai_name nor cpu_name/of_node are set for %s\n",
-			link->name);
-		return -EINVAL;
-	}
-
-	return 0;
-}
-
 void snd_soc_disconnect_sync(struct device *dev)
 {
 	struct snd_soc_component *component =
@@ -1349,117 +1458,6 @@ void snd_soc_disconnect_sync(struct device *dev)
 }
 EXPORT_SYMBOL_GPL(snd_soc_disconnect_sync);
 
-/**
- * snd_soc_add_dai_link - Add a DAI link dynamically
- * @card: The ASoC card to which the DAI link is added
- * @dai_link: The new DAI link to add
- *
- * This function adds a DAI link to the ASoC card's link list.
- *
- * Note: Topology can use this API to add DAI links when probing the
- * topology component. And machine drivers can still define static
- * DAI links in dai_link array.
- */
-int snd_soc_add_dai_link(struct snd_soc_card *card,
-		struct snd_soc_dai_link *dai_link)
-{
-	if (dai_link->dobj.type
-	    && dai_link->dobj.type != SND_SOC_DOBJ_DAI_LINK) {
-		dev_err(card->dev, "Invalid dai link type %d\n",
-			dai_link->dobj.type);
-		return -EINVAL;
-	}
-
-	lockdep_assert_held(&client_mutex);
-	/*
-	 * Notify the machine driver for extra initialization
-	 * on the link created by topology.
-	 */
-	if (dai_link->dobj.type && card->add_dai_link)
-		card->add_dai_link(card, dai_link);
-
-	/* see for_each_card_links */
-	list_add_tail(&dai_link->list, &card->dai_link_list);
-
-	return 0;
-}
-EXPORT_SYMBOL_GPL(snd_soc_add_dai_link);
-
-/**
- * snd_soc_remove_dai_link - Remove a DAI link from the list
- * @card: The ASoC card that owns the link
- * @dai_link: The DAI link to remove
- *
- * This function removes a DAI link from the ASoC card's link list.
- *
- * For DAI links previously added by topology, topology should
- * remove them by using the dobj embedded in the link.
- */
-void snd_soc_remove_dai_link(struct snd_soc_card *card,
-			     struct snd_soc_dai_link *dai_link)
-{
-	if (dai_link->dobj.type
-	    && dai_link->dobj.type != SND_SOC_DOBJ_DAI_LINK) {
-		dev_err(card->dev, "Invalid dai link type %d\n",
-			dai_link->dobj.type);
-		return;
-	}
-
-	lockdep_assert_held(&client_mutex);
-	/*
-	 * Notify the machine driver for extra destruction
-	 * on the link created by topology.
-	 */
-	if (dai_link->dobj.type && card->remove_dai_link)
-		card->remove_dai_link(card, dai_link);
-
-	list_del(&dai_link->list);
-}
-EXPORT_SYMBOL_GPL(snd_soc_remove_dai_link);
-
-static void soc_rtd_free(struct snd_soc_pcm_runtime *rtd)
-{
-	if (rtd->dev_registered) {
-		/* we don't need to call kfree() for rtd->dev */
-		device_unregister(rtd->dev);
-		rtd->dev_registered = 0;
-	}
-}
-
-static void soc_rtd_release(struct device *dev)
-{
-	kfree(dev);
-}
-
-static int soc_rtd_init(struct snd_soc_pcm_runtime *rtd, const char *name)
-{
-	int ret = 0;
-
-	/* register the rtd device */
-	rtd->dev = kzalloc(sizeof(struct device), GFP_KERNEL);
-	if (!rtd->dev)
-		return -ENOMEM;
-	rtd->dev->parent = rtd->card->dev;
-	rtd->dev->release = soc_rtd_release;
-	rtd->dev->groups = soc_dev_attr_groups;
-	dev_set_name(rtd->dev, "%s", name);
-	dev_set_drvdata(rtd->dev, rtd);
-	INIT_LIST_HEAD(&rtd->dpcm[SNDRV_PCM_STREAM_PLAYBACK].be_clients);
-	INIT_LIST_HEAD(&rtd->dpcm[SNDRV_PCM_STREAM_CAPTURE].be_clients);
-	INIT_LIST_HEAD(&rtd->dpcm[SNDRV_PCM_STREAM_PLAYBACK].fe_clients);
-	INIT_LIST_HEAD(&rtd->dpcm[SNDRV_PCM_STREAM_CAPTURE].fe_clients);
-	ret = device_register(rtd->dev);
-	if (ret < 0) {
-		/* calling put_device() here to free the rtd->dev */
-		put_device(rtd->dev);
-		dev_err(rtd->card->dev,
-			"ASoC: failed to register runtime device: %d\n", ret);
-		return ret;
-	}
-	rtd->dev_registered = 1;
-	return 0;
-}
-
 static int soc_link_dai_pcm_new(struct snd_soc_dai **dais, int num_dais,
 				struct snd_soc_pcm_runtime *rtd)
 {
@@ -1509,10 +1507,6 @@ static int soc_link_init(struct snd_soc_card *card,
 			return ret;
 	}
 
-	ret = soc_rtd_init(rtd, dai_link->name);
-	if (ret)
-		return ret;
-
 	/* add DPCM sysfs entries */
 	soc_dpcm_debugfs_add(rtd);
 
@@ -1523,9 +1517,7 @@ static int soc_link_init(struct snd_soc_card *card,
 	 * topology based drivers can use the DAI link id field to set PCM
 	 * device number and then use rtd + a base offset of the BEs.
 	 */
-	for_each_rtdcom(rtd, rtdcom) {
-		component = rtdcom->component;
-
+	for_each_rtd_components(rtd, rtdcom, component) {
 		if (!component->driver->use_dai_pcm_id)
 			continue;
 
@@ -1590,21 +1582,18 @@ static int soc_bind_aux_dev(struct snd_soc_card *card)
 
 static int soc_probe_aux_devices(struct snd_soc_card *card)
 {
-	struct snd_soc_component *comp;
+	struct snd_soc_component *component;
 	int order;
 	int ret;
 
 	for_each_comp_order(order) {
-		for_each_card_auxs(card, comp) {
-			if (comp->driver->probe_order == order) {
-				ret = soc_probe_component(card,	comp);
-				if (ret < 0) {
-					dev_err(card->dev,
-						"ASoC: failed to probe aux component %s %d\n",
-						comp->name, ret);
-					return ret;
-				}
-			}
+		for_each_card_auxs(card, component) {
+			if (component->driver->probe_order != order)
+				continue;
+
+			ret = soc_probe_component(card,	component);
+			if (ret < 0)
+				return ret;
 		}
 	}
 
@@ -1619,7 +1608,7 @@ static void soc_remove_aux_devices(struct snd_soc_card *card)
 	for_each_comp_order(order) {
 		for_each_card_auxs_safe(card, comp, _comp) {
 			if (comp->driver->remove_order == order)
-				soc_remove_component(comp);
+				soc_remove_component(comp, 1);
 		}
 	}
 }
@@ -1729,6 +1718,23 @@ static int is_dmi_valid(const char *field)
 	return 1;
 }
 
+/*
+ * Append a string to card->dmi_longname with character cleanups.
+ */
+static void append_dmi_string(struct snd_soc_card *card, const char *str)
+{
+	char *dst = card->dmi_longname;
+	size_t dst_len = sizeof(card->dmi_longname);
+	size_t len;
+
+	len = strlen(dst);
+	snprintf(dst + len, dst_len - len, "-%s", str);
+
+	len++;	/* skip the separator "-" */
+	if (len < dst_len)
+		cleanup_dmi_name(dst + len);
+}
+
 /**
  * snd_soc_set_dmi_name() - Register DMI names to card
  * @card: The card to register DMI names
@@ -1763,61 +1769,37 @@ static int is_dmi_valid(const char *field)
 int snd_soc_set_dmi_name(struct snd_soc_card *card, const char *flavour)
 {
 	const char *vendor, *product, *product_version, *board;
-	size_t longname_buf_size = sizeof(card->snd_card->longname);
-	size_t len;
 
 	if (card->long_name)
 		return 0; /* long name already set by driver or from DMI */
 
-	/* make up dmi long name as: vendor.product.version.board */
+	/* make up dmi long name as: vendor-product-version-board */
 	vendor = dmi_get_system_info(DMI_BOARD_VENDOR);
 	if (!vendor || !is_dmi_valid(vendor)) {
 		dev_warn(card->dev, "ASoC: no DMI vendor name!\n");
 		return 0;
 	}
 
-	snprintf(card->dmi_longname, sizeof(card->snd_card->longname),
-			 "%s", vendor);
+	snprintf(card->dmi_longname, sizeof(card->dmi_longname), "%s", vendor);
 	cleanup_dmi_name(card->dmi_longname);
 
 	product = dmi_get_system_info(DMI_PRODUCT_NAME);
 	if (product && is_dmi_valid(product)) {
-		len = strlen(card->dmi_longname);
-		snprintf(card->dmi_longname + len,
-			 longname_buf_size - len,
-			 "-%s", product);
-
-		len++;	/* skip the separator "-" */
-		if (len < longname_buf_size)
-			cleanup_dmi_name(card->dmi_longname + len);
+		append_dmi_string(card, product);
 
 		/*
 		 * some vendors like Lenovo may only put a self-explanatory
 		 * name in the product version field
 		 */
 		product_version = dmi_get_system_info(DMI_PRODUCT_VERSION);
-		if (product_version && is_dmi_valid(product_version)) {
-			len = strlen(card->dmi_longname);
-			snprintf(card->dmi_longname + len,
-				 longname_buf_size - len,
-				 "-%s", product_version);
-
-			len++;
-			if (len < longname_buf_size)
-				cleanup_dmi_name(card->dmi_longname + len);
-		}
+		if (product_version && is_dmi_valid(product_version))
+			append_dmi_string(card, product_version);
 	}
 
 	board = dmi_get_system_info(DMI_BOARD_NAME);
 	if (board && is_dmi_valid(board)) {
-		len = strlen(card->dmi_longname);
-		snprintf(card->dmi_longname + len,
-			 longname_buf_size - len,
-			 "-%s", board);
-
-		len++;
-		if (len < longname_buf_size)
-			cleanup_dmi_name(card->dmi_longname + len);
+		if (!product || strcasecmp(board, product))
+			append_dmi_string(card, board);
 	} else if (!product) {
 		/* fall back to using legacy name */
 		dev_warn(card->dev, "ASoC: no DMI board/product name!\n");
@@ -1825,16 +1807,8 @@ int snd_soc_set_dmi_name(struct snd_soc_card *card, const char *flavour)
 	}
 
 	/* Add flavour to dmi long name */
-	if (flavour) {
-		len = strlen(card->dmi_longname);
-		snprintf(card->dmi_longname + len,
-			 longname_buf_size - len,
-			 "-%s", flavour);
-
-		len++;
-		if (len < longname_buf_size)
-			cleanup_dmi_name(card->dmi_longname + len);
-	}
+	if (flavour)
+		append_dmi_string(card, flavour);
 
 	/* set the card long name */
 	card->long_name = card->dmi_longname;
@@ -1853,7 +1827,7 @@ static void soc_check_tplg_fes(struct snd_soc_card *card)
 
 	for_each_component(component) {
 
-		/* does this component override FEs ? */
+		/* does this component override BEs ? */
 		if (!component->driver->ignore_machine)
 			continue;
 
@@ -1874,7 +1848,7 @@ match:
 				continue;
 			}
 
-			dev_info(card->dev, "info: override FE DAI link %s\n",
+			dev_info(card->dev, "info: override BE DAI link %s\n",
 				 card->dai_link[i].name);
 
 			/* override platform component */
@@ -1918,17 +1892,58 @@ match:
 	}
 }
 
-static void soc_cleanup_card_resources(struct snd_soc_card *card)
+#define soc_setup_card_name(name, name1, name2, norm)		\
+	__soc_setup_card_name(name, sizeof(name), name1, name2, norm)
+static void __soc_setup_card_name(char *name, int len,
+				  const char *name1, const char *name2,
+				  int normalization)
 {
-	/* free the ALSA card at first; this syncs with pending operations */
-	if (card->snd_card) {
-		snd_card_free(card->snd_card);
-		card->snd_card = NULL;
+	int i;
+
+	snprintf(name, len, "%s", name1 ? name1 : name2);
+
+	if (!normalization)
+		return;
+
+	/*
+	 * Name normalization
+	 *
+	 * The driver name is somewhat special, as it's used as a key for
+	 * searches in the user-space.
+	 *
+	 * ex)
+	 *	"abcd??efg" -> "abcd__efg"
+	 */
+	for (i = 0; i < len; i++) {
+		switch (name[i]) {
+		case '_':
+		case '-':
+		case '\0':
+			break;
+		default:
+			if (!isalnum(name[i]))
+				name[i] = '_';
+			break;
+		}
 	}
+}
+
+static void soc_cleanup_card_resources(struct snd_soc_card *card,
+				       int card_probed)
+{
+	struct snd_soc_dai_link *link, *_link;
+
+	if (card->snd_card)
+		snd_card_disconnect_sync(card->snd_card);
+
+	snd_soc_dapm_shutdown(card);
 
 	/* remove and free each DAI */
-	soc_remove_dai_links(card);
-	soc_remove_pcm_runtimes(card);
+	soc_remove_link_dais(card);
+	soc_remove_link_components(card);
+
+	for_each_card_links_safe(card, link, _link)
+		snd_soc_remove_dai_link(card, link);
 
 	/* remove auxiliary devices */
 	soc_remove_aux_devices(card);
@@ -1938,26 +1953,39 @@ static void soc_cleanup_card_resources(struct snd_soc_card *card)
 	soc_cleanup_card_debugfs(card);
 
 	/* remove the card */
-	if (card->remove)
+	if (card_probed && card->remove)
 		card->remove(card);
+
+	if (card->snd_card) {
+		snd_card_free(card->snd_card);
+		card->snd_card = NULL;
+	}
+}
+
+static void snd_soc_unbind_card(struct snd_soc_card *card, bool unregister)
+{
+	if (card->instantiated) {
+		int card_probed = 1;
+
+		card->instantiated = false;
+		snd_soc_flush_all_delayed_work(card);
+
+		soc_cleanup_card_resources(card, card_probed);
+		if (!unregister)
+			list_add(&card->list, &unbind_card_list);
+	} else {
+		if (unregister)
+			list_del(&card->list);
+	}
 }
 
-static int snd_soc_instantiate_card(struct snd_soc_card *card)
+static int snd_soc_bind_card(struct snd_soc_card *card)
 {
 	struct snd_soc_pcm_runtime *rtd;
 	struct snd_soc_dai_link *dai_link;
-	int ret, i;
+	int ret, i, card_probed = 0;
 
 	mutex_lock(&client_mutex);
-	for_each_card_prelinks(card, i, dai_link) {
-		ret = soc_init_dai_link(card, dai_link);
-		if (ret) {
-			dev_err(card->dev, "ASoC: failed to init link %s: %d\n",
-				dai_link->name, ret);
-			mutex_unlock(&client_mutex);
-			return ret;
-		}
-	}
 	mutex_lock_nested(&card->mutex, SND_SOC_CARD_CLASS_INIT);
 
 	snd_soc_dapm_init(&card->dapm, card, NULL);
@@ -1965,19 +1993,13 @@ static int snd_soc_instantiate_card(struct snd_soc_card *card)
 	/* check whether any platform is ignore machine FE and using topology */
 	soc_check_tplg_fes(card);
 
-	/* bind DAIs */
-	for_each_card_prelinks(card, i, dai_link) {
-		ret = soc_bind_dai_link(card, dai_link);
-		if (ret != 0)
-			goto probe_end;
-	}
-
 	/* bind aux_devs too */
 	ret = soc_bind_aux_dev(card);
 	if (ret < 0)
 		goto probe_end;
 
 	/* add predefined DAI links to the list */
+	card->num_rtd = 0;
 	for_each_card_prelinks(card, i, dai_link) {
 		ret = snd_soc_add_dai_link(card, dai_link);
 		if (ret < 0)
@@ -2013,6 +2035,7 @@ static int snd_soc_instantiate_card(struct snd_soc_card *card)
 		ret = card->probe(card);
 		if (ret < 0)
 			goto probe_end;
+		card_probed = 1;
 	}
 
 	/* probe all components used by DAI links on this card */
@@ -2025,23 +2048,10 @@ static int snd_soc_instantiate_card(struct snd_soc_card *card)
 
 	/* probe auxiliary components */
 	ret = soc_probe_aux_devices(card);
-	if (ret < 0)
+	if (ret < 0) {
+		dev_err(card->dev,
+			"ASoC: failed to probe aux component %d\n", ret);
 		goto probe_end;
-
-	/*
-	 * Find new DAI links added during probing components and bind them.
-	 * Components with topology may bring new DAIs and DAI links.
-	 */
-	for_each_card_links(card, dai_link) {
-		if (soc_is_dai_link_bound(card, dai_link))
-			continue;
-
-		ret = soc_init_dai_link(card, dai_link);
-		if (ret)
-			goto probe_end;
-		ret = soc_bind_dai_link(card, dai_link);
-		if (ret)
-			goto probe_end;
 	}
 
 	/* probe all DAI links on this card */
@@ -2076,22 +2086,23 @@ static int snd_soc_instantiate_card(struct snd_soc_card *card)
 	/* try to set some sane longname if DMI is available */
 	snd_soc_set_dmi_name(card, NULL);
 
-	snprintf(card->snd_card->shortname, sizeof(card->snd_card->shortname),
-		 "%s", card->name);
-	snprintf(card->snd_card->longname, sizeof(card->snd_card->longname),
-		 "%s", card->long_name ? card->long_name : card->name);
-	snprintf(card->snd_card->driver, sizeof(card->snd_card->driver),
-		 "%s", card->driver_name ? card->driver_name : card->name);
-	for (i = 0; i < ARRAY_SIZE(card->snd_card->driver); i++) {
-		switch (card->snd_card->driver[i]) {
-		case '_':
-		case '-':
-		case '\0':
-			break;
-		default:
-			if (!isalnum(card->snd_card->driver[i]))
-				card->snd_card->driver[i] = '_';
-			break;
+	soc_setup_card_name(card->snd_card->shortname,
+			    card->name, NULL, 0);
+	soc_setup_card_name(card->snd_card->longname,
+			    card->long_name, card->name, 0);
+	soc_setup_card_name(card->snd_card->driver,
+			    card->driver_name, card->name, 1);
+
+	if (card->components) {
+		/* the current implementation of snd_component_add() accepts */
+		/* multiple components in the string separated by space, */
+		/* but the string collision (identical string) check might */
+		/* not work correctly */
+		ret = snd_component_add(card->snd_card, card->components);
+		if (ret < 0) {
+			dev_err(card->dev, "ASoC: %s snd_component_add() failed: %d\n",
+				card->name, ret);
+			goto probe_end;
 		}
 	}
 
@@ -2103,6 +2114,7 @@ static int snd_soc_instantiate_card(struct snd_soc_card *card)
 			goto probe_end;
 		}
 	}
+	card_probed = 1;
 
 	snd_soc_dapm_new_widgets(card);
 
@@ -2117,9 +2129,22 @@ static int snd_soc_instantiate_card(struct snd_soc_card *card)
 	dapm_mark_endpoints_dirty(card);
 	snd_soc_dapm_sync(&card->dapm);
 
+	/* deactivate pins to sleep state */
+	for_each_card_rtds(card, rtd) {
+		struct snd_soc_dai *dai;
+
+		for_each_rtd_codec_dai(rtd, i, dai) {
+			if (!dai->active)
+				pinctrl_pm_select_sleep_state(dai->dev);
+		}
+
+		if (!rtd->cpu_dai->active)
+			pinctrl_pm_select_sleep_state(rtd->cpu_dai->dev);
+	}
+
 probe_end:
 	if (ret < 0)
-		soc_cleanup_card_resources(card);
+		soc_cleanup_card_resources(card, card_probed);
 
 	mutex_unlock(&card->mutex);
 	mutex_unlock(&client_mutex);
@@ -2349,33 +2374,6 @@ int snd_soc_add_dai_controls(struct snd_soc_dai *dai,
 }
 EXPORT_SYMBOL_GPL(snd_soc_add_dai_controls);
 
-static int snd_soc_bind_card(struct snd_soc_card *card)
-{
-	struct snd_soc_pcm_runtime *rtd;
-	int ret;
-
-	ret = snd_soc_instantiate_card(card);
-	if (ret != 0)
-		return ret;
-
-	/* deactivate pins to sleep state */
-	for_each_card_rtds(card, rtd) {
-		struct snd_soc_dai *cpu_dai = rtd->cpu_dai;
-		struct snd_soc_dai *codec_dai;
-		int j;
-
-		for_each_rtd_codec_dai(rtd, j, codec_dai) {
-			if (!codec_dai->active)
-				pinctrl_pm_select_sleep_state(codec_dai->dev);
-		}
-
-		if (!cpu_dai->active)
-			pinctrl_pm_select_sleep_state(cpu_dai->dev);
-	}
-
-	return ret;
-}
-
 /**
  * snd_soc_register_card - Register a card with the ASoC core
  *
@@ -2400,7 +2398,6 @@ int snd_soc_register_card(struct snd_soc_card *card)
 	INIT_LIST_HEAD(&card->dapm_dirty);
 	INIT_LIST_HEAD(&card->dobj_list);
 
-	card->num_rtd = 0;
 	card->instantiated = 0;
 	mutex_init(&card->mutex);
 	mutex_init(&card->dapm_mutex);
@@ -2411,25 +2408,6 @@ int snd_soc_register_card(struct snd_soc_card *card)
 }
 EXPORT_SYMBOL_GPL(snd_soc_register_card);
 
-static void snd_soc_unbind_card(struct snd_soc_card *card, bool unregister)
-{
-	if (card->instantiated) {
-		card->instantiated = false;
-		snd_soc_dapm_shutdown(card);
-		snd_soc_flush_all_delayed_work(card);
-
-		/* remove all components used by DAI links on this card */
-		soc_remove_link_components(card);
-
-		soc_cleanup_card_resources(card);
-		if (!unregister)
-			list_add(&card->list, &unbind_card_list);
-	} else {
-		if (unregister)
-			list_del(&card->list);
-	}
-}
-
 /**
  * snd_soc_unregister_card - Unregister a card with the ASoC core
  *
@@ -2488,7 +2466,7 @@ static char *fmt_single_name(struct device *dev, int *id)
 			*id = 0;
 	}
 
-	return kstrdup(name, GFP_KERNEL);
+	return devm_kstrdup(dev, name, GFP_KERNEL);
 }
 
 /*
@@ -2505,38 +2483,38 @@ static inline char *fmt_multiple_name(struct device *dev,
 		return NULL;
 	}
 
-	return kstrdup(dai_drv->name, GFP_KERNEL);
+	return devm_kstrdup(dev, dai_drv->name, GFP_KERNEL);
 }
 
-/**
- * snd_soc_unregister_dai - Unregister DAIs from the ASoC core
- *
- * @component: The component for which the DAIs should be unregistered
- */
-static void snd_soc_unregister_dais(struct snd_soc_component *component)
+void snd_soc_unregister_dai(struct snd_soc_dai *dai)
 {
-	struct snd_soc_dai *dai, *_dai;
-
-	for_each_component_dais_safe(component, dai, _dai) {
-		dev_dbg(component->dev, "ASoC: Unregistered DAI '%s'\n",
-			dai->name);
-		list_del(&dai->list);
-		kfree(dai->name);
-		kfree(dai);
-	}
+	dev_dbg(dai->dev, "ASoC: Unregistered DAI '%s'\n", dai->name);
+	list_del(&dai->list);
 }
+EXPORT_SYMBOL_GPL(snd_soc_unregister_dai);
 
-/* Create a DAI and add it to the component's DAI list */
-static struct snd_soc_dai *soc_add_dai(struct snd_soc_component *component,
-	struct snd_soc_dai_driver *dai_drv,
-	bool legacy_dai_naming)
+/**
+ * snd_soc_register_dai - Register a DAI dynamically & create its widgets
+ *
+ * @component: The component the DAIs are registered for
+ * @dai_drv: DAI driver to use for the DAI
+ *
+ * Topology can use this API to register DAIs when probing a component.
+ * These DAIs's widgets will be freed in the card cleanup and the DAIs
+ * will be freed in the component cleanup.
+ */
+struct snd_soc_dai *snd_soc_register_dai(struct snd_soc_component *component,
+					 struct snd_soc_dai_driver *dai_drv,
+					 bool legacy_dai_naming)
 {
 	struct device *dev = component->dev;
 	struct snd_soc_dai *dai;
 
 	dev_dbg(dev, "ASoC: dynamically register DAI %s\n", dev_name(dev));
 
-	dai = kzalloc(sizeof(struct snd_soc_dai), GFP_KERNEL);
+	lockdep_assert_held(&client_mutex);
+
+	dai = devm_kzalloc(dev, sizeof(*dai), GFP_KERNEL);
 	if (dai == NULL)
 		return NULL;
 
@@ -2558,10 +2536,8 @@ static struct snd_soc_dai *soc_add_dai(struct snd_soc_component *component,
 		else
 			dai->id = component->num_dai;
 	}
-	if (dai->name == NULL) {
-		kfree(dai);
+	if (!dai->name)
 		return NULL;
-	}
 
 	dai->component = component;
 	dai->dev = dev;
@@ -2578,6 +2554,19 @@ static struct snd_soc_dai *soc_add_dai(struct snd_soc_component *component,
 }
 
 /**
+ * snd_soc_unregister_dai - Unregister DAIs from the ASoC core
+ *
+ * @component: The component for which the DAIs should be unregistered
+ */
+static void snd_soc_unregister_dais(struct snd_soc_component *component)
+{
+	struct snd_soc_dai *dai, *_dai;
+
+	for_each_component_dais_safe(component, dai, _dai)
+		snd_soc_unregister_dai(dai);
+}
+
+/**
  * snd_soc_register_dais - Register a DAI with the ASoC core
  *
  * @component: The component the DAIs are registered for
@@ -2588,16 +2577,12 @@ static int snd_soc_register_dais(struct snd_soc_component *component,
 				 struct snd_soc_dai_driver *dai_drv,
 				 size_t count)
 {
-	struct device *dev = component->dev;
 	struct snd_soc_dai *dai;
 	unsigned int i;
 	int ret;
 
-	dev_dbg(dev, "ASoC: dai register %s #%zu\n", dev_name(dev), count);
-
 	for (i = 0; i < count; i++) {
-
-		dai = soc_add_dai(component, dai_drv + i, count == 1 &&
+		dai = snd_soc_register_dai(component, dai_drv + i, count == 1 &&
 				  !component->driver->non_legacy_dai_naming);
 		if (dai == NULL) {
 			ret = -ENOMEM;
@@ -2613,49 +2598,6 @@ err:
 	return ret;
 }
 
-/**
- * snd_soc_register_dai - Register a DAI dynamically & create its widgets
- *
- * @component: The component the DAIs are registered for
- * @dai_drv: DAI driver to use for the DAI
- *
- * Topology can use this API to register DAIs when probing a component.
- * These DAIs's widgets will be freed in the card cleanup and the DAIs
- * will be freed in the component cleanup.
- */
-int snd_soc_register_dai(struct snd_soc_component *component,
-	struct snd_soc_dai_driver *dai_drv)
-{
-	struct snd_soc_dapm_context *dapm =
-		snd_soc_component_get_dapm(component);
-	struct snd_soc_dai *dai;
-	int ret;
-
-	if (dai_drv->dobj.type != SND_SOC_DOBJ_PCM) {
-		dev_err(component->dev, "Invalid dai type %d\n",
-			dai_drv->dobj.type);
-		return -EINVAL;
-	}
-
-	lockdep_assert_held(&client_mutex);
-	dai = soc_add_dai(component, dai_drv, false);
-	if (!dai)
-		return -ENOMEM;
-
-	/*
-	 * Create the DAI widgets here. After adding DAIs, topology may
-	 * also add routes that need these widgets as source or sink.
-	 */
-	ret = snd_soc_dapm_new_dai_widgets(dapm, dai);
-	if (ret != 0) {
-		dev_err(component->dev,
-			"Failed to create DAI widgets %d\n", ret);
-	}
-
-	return ret;
-}
-EXPORT_SYMBOL_GPL(snd_soc_register_dai);
-
 static int snd_soc_component_initialize(struct snd_soc_component *component,
 	const struct snd_soc_component_driver *driver, struct device *dev)
 {
@@ -2726,40 +2668,6 @@ EXPORT_SYMBOL_GPL(snd_soc_component_exit_regmap);
 
 #endif
 
-static void snd_soc_component_add(struct snd_soc_component *component)
-{
-	mutex_lock(&client_mutex);
-
-	if (!component->driver->write && !component->driver->read) {
-		if (!component->regmap)
-			component->regmap = dev_get_regmap(component->dev,
-							   NULL);
-		if (component->regmap)
-			snd_soc_component_setup_regmap(component);
-	}
-
-	/* see for_each_component */
-	list_add(&component->list, &component_list);
-
-	mutex_unlock(&client_mutex);
-}
-
-static void snd_soc_component_cleanup(struct snd_soc_component *component)
-{
-	snd_soc_unregister_dais(component);
-	kfree(component->name);
-}
-
-static void snd_soc_component_del_unlocked(struct snd_soc_component *component)
-{
-	struct snd_soc_card *card = component->card;
-
-	if (card)
-		snd_soc_unbind_card(card, false);
-
-	list_del(&component->list);
-}
-
 #define ENDIANNESS_MAP(name) \
 	(SNDRV_PCM_FMTBIT_##name##LE | SNDRV_PCM_FMTBIT_##name##BE)
 static u64 endianness_format_map[] = {
@@ -2804,6 +2712,18 @@ static void snd_soc_try_rebind_card(void)
 			list_del(&card->list);
 }
 
+static void snd_soc_del_component_unlocked(struct snd_soc_component *component)
+{
+	struct snd_soc_card *card = component->card;
+
+	snd_soc_unregister_dais(component);
+
+	if (card)
+		snd_soc_unbind_card(card, false);
+
+	list_del(&component->list);
+}
+
 int snd_soc_add_component(struct device *dev,
 			struct snd_soc_component *component,
 			const struct snd_soc_component_driver *component_driver,
@@ -2813,6 +2733,8 @@ int snd_soc_add_component(struct device *dev,
 	int ret;
 	int i;
 
+	mutex_lock(&client_mutex);
+
 	ret = snd_soc_component_initialize(component, component_driver, dev);
 	if (ret)
 		goto err_free;
@@ -2830,14 +2752,26 @@ int snd_soc_add_component(struct device *dev,
 		goto err_cleanup;
 	}
 
-	snd_soc_component_add(component);
-	snd_soc_try_rebind_card();
+	if (!component->driver->write && !component->driver->read) {
+		if (!component->regmap)
+			component->regmap = dev_get_regmap(component->dev,
+							   NULL);
+		if (component->regmap)
+			snd_soc_component_setup_regmap(component);
+	}
 
-	return 0;
+	/* see for_each_component */
+	list_add(&component->list, &component_list);
 
 err_cleanup:
-	snd_soc_component_cleanup(component);
+	if (ret < 0)
+		snd_soc_del_component_unlocked(component);
 err_free:
+	mutex_unlock(&client_mutex);
+
+	if (ret == 0)
+		snd_soc_try_rebind_card();
+
 	return ret;
 }
 EXPORT_SYMBOL_GPL(snd_soc_add_component);
@@ -2864,62 +2798,21 @@ EXPORT_SYMBOL_GPL(snd_soc_register_component);
  *
  * @dev: The device to unregister
  */
-static int __snd_soc_unregister_component(struct device *dev)
-{
-	struct snd_soc_component *component;
-	int found = 0;
-
-	mutex_lock(&client_mutex);
-	for_each_component(component) {
-		if (dev != component->dev)
-			continue;
-
-		snd_soc_tplg_component_remove(component,
-					      SND_SOC_TPLG_INDEX_ALL);
-		snd_soc_component_del_unlocked(component);
-		found = 1;
-		break;
-	}
-	mutex_unlock(&client_mutex);
-
-	if (found)
-		snd_soc_component_cleanup(component);
-
-	return found;
-}
-
 void snd_soc_unregister_component(struct device *dev)
 {
-	while (__snd_soc_unregister_component(dev))
-		;
-}
-EXPORT_SYMBOL_GPL(snd_soc_unregister_component);
-
-struct snd_soc_component *snd_soc_lookup_component(struct device *dev,
-						   const char *driver_name)
-{
 	struct snd_soc_component *component;
-	struct snd_soc_component *ret;
 
-	ret = NULL;
 	mutex_lock(&client_mutex);
-	for_each_component(component) {
-		if (dev != component->dev)
-			continue;
-
-		if (driver_name &&
-		    (driver_name != component->driver->name) &&
-		    (strcmp(component->driver->name, driver_name) != 0))
-			continue;
+	while (1) {
+		component = snd_soc_lookup_component_nolocked(dev, NULL);
+		if (!component)
+			break;
 
-		ret = component;
-		break;
+		snd_soc_del_component_unlocked(component);
 	}
 	mutex_unlock(&client_mutex);
-
-	return ret;
 }
-EXPORT_SYMBOL_GPL(snd_soc_lookup_component);
+EXPORT_SYMBOL_GPL(snd_soc_unregister_component);
 
 /* Retrieve a card's name from device tree */
 int snd_soc_of_parse_card_name(struct snd_soc_card *card,
diff --git a/sound/soc/soc-generic-dmaengine-pcm.c b/sound/soc/soc-generic-dmaengine-pcm.c
index 5552c66ca642..a428ff393ea2 100644
--- a/sound/soc/soc-generic-dmaengine-pcm.c
+++ b/sound/soc/soc-generic-dmaengine-pcm.c
@@ -75,12 +75,10 @@ int snd_dmaengine_pcm_prepare_slave_config(struct snd_pcm_substream *substream,
 }
 EXPORT_SYMBOL_GPL(snd_dmaengine_pcm_prepare_slave_config);
 
-static int dmaengine_pcm_hw_params(struct snd_pcm_substream *substream,
-	struct snd_pcm_hw_params *params)
+static int dmaengine_pcm_hw_params(struct snd_soc_component *component,
+				   struct snd_pcm_substream *substream,
+				   struct snd_pcm_hw_params *params)
 {
-	struct snd_soc_pcm_runtime *rtd = substream->private_data;
-	struct snd_soc_component *component =
-		snd_soc_rtdcom_lookup(rtd, SND_DMAENGINE_PCM_DRV_NAME);
 	struct dmaengine_pcm *pcm = soc_component_to_pcm(component);
 	struct dma_chan *chan = snd_dmaengine_pcm_get_chan(substream);
 	int (*prepare_slave_config)(struct snd_pcm_substream *substream,
@@ -109,21 +107,16 @@ static int dmaengine_pcm_hw_params(struct snd_pcm_substream *substream,
 	return snd_pcm_lib_malloc_pages(substream, params_buffer_bytes(params));
 }
 
-static int dmaengine_pcm_set_runtime_hwparams(struct snd_pcm_substream *substream)
+static int
+dmaengine_pcm_set_runtime_hwparams(struct snd_soc_component *component,
+				   struct snd_pcm_substream *substream)
 {
 	struct snd_soc_pcm_runtime *rtd = substream->private_data;
-	struct snd_soc_component *component =
-		snd_soc_rtdcom_lookup(rtd, SND_DMAENGINE_PCM_DRV_NAME);
 	struct dmaengine_pcm *pcm = soc_component_to_pcm(component);
 	struct device *dma_dev = dmaengine_dma_dev(pcm, substream);
 	struct dma_chan *chan = pcm->chan[substream->stream];
 	struct snd_dmaengine_dai_dma_data *dma_data;
-	struct dma_slave_caps dma_caps;
 	struct snd_pcm_hardware hw;
-	u32 addr_widths = BIT(DMA_SLAVE_BUSWIDTH_1_BYTE) |
-			  BIT(DMA_SLAVE_BUSWIDTH_2_BYTES) |
-			  BIT(DMA_SLAVE_BUSWIDTH_4_BYTES);
-	snd_pcm_format_t i;
 	int ret;
 
 	if (pcm->config && pcm->config->pcm_hardware)
@@ -145,82 +138,53 @@ static int dmaengine_pcm_set_runtime_hwparams(struct snd_pcm_substream *substrea
 	if (pcm->flags & SND_DMAENGINE_PCM_FLAG_NO_RESIDUE)
 		hw.info |= SNDRV_PCM_INFO_BATCH;
 
-	ret = dma_get_slave_caps(chan, &dma_caps);
-	if (ret == 0) {
-		if (dma_caps.cmd_pause && dma_caps.cmd_resume)
-			hw.info |= SNDRV_PCM_INFO_PAUSE | SNDRV_PCM_INFO_RESUME;
-		if (dma_caps.residue_granularity <= DMA_RESIDUE_GRANULARITY_SEGMENT)
-			hw.info |= SNDRV_PCM_INFO_BATCH;
-
-		if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK)
-			addr_widths = dma_caps.dst_addr_widths;
-		else
-			addr_widths = dma_caps.src_addr_widths;
-	}
-
-	/*
-	 * If SND_DMAENGINE_PCM_DAI_FLAG_PACK is set keep
-	 * hw.formats set to 0, meaning no restrictions are in place.
-	 * In this case it's the responsibility of the DAI driver to
-	 * provide the supported format information.
-	 */
-	if (!(dma_data->flags & SND_DMAENGINE_PCM_DAI_FLAG_PACK))
-		/*
-		 * Prepare formats mask for valid/allowed sample types. If the
-		 * dma does not have support for the given physical word size,
-		 * it needs to be masked out so user space can not use the
-		 * format which produces corrupted audio.
-		 * In case the dma driver does not implement the slave_caps the
-		 * default assumption is that it supports 1, 2 and 4 bytes
-		 * widths.
-		 */
-		for (i = SNDRV_PCM_FORMAT_FIRST; i <= SNDRV_PCM_FORMAT_LAST; i++) {
-			int bits = snd_pcm_format_physical_width(i);
-
-			/*
-			 * Enable only samples with DMA supported physical
-			 * widths
-			 */
-			switch (bits) {
-			case 8:
-			case 16:
-			case 24:
-			case 32:
-			case 64:
-				if (addr_widths & (1 << (bits / 8)))
-					hw.formats |= pcm_format_to_bits(i);
-				break;
-			default:
-				/* Unsupported types */
-				break;
-			}
-		}
+	ret = snd_dmaengine_pcm_refine_runtime_hwparams(substream,
+							dma_data,
+							&hw,
+							chan);
+	if (ret)
+		return ret;
 
 	return snd_soc_set_runtime_hwparams(substream, &hw);
 }
 
-static int dmaengine_pcm_open(struct snd_pcm_substream *substream)
+static int dmaengine_pcm_open(struct snd_soc_component *component,
+			      struct snd_pcm_substream *substream)
 {
-	struct snd_soc_pcm_runtime *rtd = substream->private_data;
-	struct snd_soc_component *component =
-		snd_soc_rtdcom_lookup(rtd, SND_DMAENGINE_PCM_DRV_NAME);
 	struct dmaengine_pcm *pcm = soc_component_to_pcm(component);
 	struct dma_chan *chan = pcm->chan[substream->stream];
 	int ret;
 
-	ret = dmaengine_pcm_set_runtime_hwparams(substream);
+	ret = dmaengine_pcm_set_runtime_hwparams(component, substream);
 	if (ret)
 		return ret;
 
 	return snd_dmaengine_pcm_open(substream, chan);
 }
 
+static int dmaengine_pcm_close(struct snd_soc_component *component,
+			       struct snd_pcm_substream *substream)
+{
+	return snd_dmaengine_pcm_close(substream);
+}
+
+static int dmaengine_pcm_hw_free(struct snd_soc_component *component,
+				 struct snd_pcm_substream *substream)
+{
+	return snd_pcm_lib_free_pages(substream);
+}
+
+static int dmaengine_pcm_trigger(struct snd_soc_component *component,
+				 struct snd_pcm_substream *substream, int cmd)
+{
+	return snd_dmaengine_pcm_trigger(substream, cmd);
+}
+
 static struct dma_chan *dmaengine_pcm_compat_request_channel(
+	struct snd_soc_component *component,
 	struct snd_soc_pcm_runtime *rtd,
 	struct snd_pcm_substream *substream)
 {
-	struct snd_soc_component *component =
-		snd_soc_rtdcom_lookup(rtd, SND_DMAENGINE_PCM_DRV_NAME);
 	struct dmaengine_pcm *pcm = soc_component_to_pcm(component);
 	struct snd_dmaengine_dai_dma_data *dma_data;
 	dma_filter_fn fn = NULL;
@@ -258,10 +222,9 @@ static bool dmaengine_pcm_can_report_residue(struct device *dev,
 	return true;
 }
 
-static int dmaengine_pcm_new(struct snd_soc_pcm_runtime *rtd)
+static int dmaengine_pcm_new(struct snd_soc_component *component,
+			     struct snd_soc_pcm_runtime *rtd)
 {
-	struct snd_soc_component *component =
-		snd_soc_rtdcom_lookup(rtd, SND_DMAENGINE_PCM_DRV_NAME);
 	struct dmaengine_pcm *pcm = soc_component_to_pcm(component);
 	const struct snd_dmaengine_pcm_config *config = pcm->config;
 	struct device *dev = component->dev;
@@ -288,8 +251,8 @@ static int dmaengine_pcm_new(struct snd_soc_pcm_runtime *rtd)
 				config->chan_names[i]);
 
 		if (!pcm->chan[i] && (pcm->flags & SND_DMAENGINE_PCM_FLAG_COMPAT)) {
-			pcm->chan[i] = dmaengine_pcm_compat_request_channel(rtd,
-				substream);
+			pcm->chan[i] = dmaengine_pcm_compat_request_channel(
+				component, rtd, substream);
 		}
 
 		if (!pcm->chan[i]) {
@@ -318,11 +281,9 @@ static int dmaengine_pcm_new(struct snd_soc_pcm_runtime *rtd)
 }
 
 static snd_pcm_uframes_t dmaengine_pcm_pointer(
+	struct snd_soc_component *component,
 	struct snd_pcm_substream *substream)
 {
-	struct snd_soc_pcm_runtime *rtd = substream->private_data;
-	struct snd_soc_component *component =
-		snd_soc_rtdcom_lookup(rtd, SND_DMAENGINE_PCM_DRV_NAME);
 	struct dmaengine_pcm *pcm = soc_component_to_pcm(component);
 
 	if (pcm->flags & SND_DMAENGINE_PCM_FLAG_NO_RESIDUE)
@@ -331,13 +292,11 @@ static snd_pcm_uframes_t dmaengine_pcm_pointer(
 		return snd_dmaengine_pcm_pointer(substream);
 }
 
-static int dmaengine_copy_user(struct snd_pcm_substream *substream,
+static int dmaengine_copy_user(struct snd_soc_component *component,
+			       struct snd_pcm_substream *substream,
 			       int channel, unsigned long hwoff,
 			       void __user *buf, unsigned long bytes)
 {
-	struct snd_soc_pcm_runtime *rtd = substream->private_data;
-	struct snd_soc_component *component =
-		snd_soc_rtdcom_lookup(rtd, SND_DMAENGINE_PCM_DRV_NAME);
 	struct snd_pcm_runtime *runtime = substream->runtime;
 	struct dmaengine_pcm *pcm = soc_component_to_pcm(component);
 	int (*process)(struct snd_pcm_substream *substream,
@@ -365,39 +324,31 @@ static int dmaengine_copy_user(struct snd_pcm_substream *substream,
 	return 0;
 }
 
-static const struct snd_pcm_ops dmaengine_pcm_ops = {
+static const struct snd_soc_component_driver dmaengine_pcm_component = {
+	.name		= SND_DMAENGINE_PCM_DRV_NAME,
+	.probe_order	= SND_SOC_COMP_ORDER_LATE,
 	.open		= dmaengine_pcm_open,
-	.close		= snd_dmaengine_pcm_close,
-	.ioctl		= snd_pcm_lib_ioctl,
+	.close		= dmaengine_pcm_close,
+	.ioctl		= snd_soc_pcm_lib_ioctl,
 	.hw_params	= dmaengine_pcm_hw_params,
-	.hw_free	= snd_pcm_lib_free_pages,
-	.trigger	= snd_dmaengine_pcm_trigger,
+	.hw_free	= dmaengine_pcm_hw_free,
+	.trigger	= dmaengine_pcm_trigger,
 	.pointer	= dmaengine_pcm_pointer,
+	.pcm_construct	= dmaengine_pcm_new,
 };
 
-static const struct snd_pcm_ops dmaengine_pcm_process_ops = {
+static const struct snd_soc_component_driver dmaengine_pcm_component_process = {
+	.name		= SND_DMAENGINE_PCM_DRV_NAME,
+	.probe_order	= SND_SOC_COMP_ORDER_LATE,
 	.open		= dmaengine_pcm_open,
-	.close		= snd_dmaengine_pcm_close,
-	.ioctl		= snd_pcm_lib_ioctl,
+	.close		= dmaengine_pcm_close,
+	.ioctl		= snd_soc_pcm_lib_ioctl,
 	.hw_params	= dmaengine_pcm_hw_params,
-	.hw_free	= snd_pcm_lib_free_pages,
-	.trigger	= snd_dmaengine_pcm_trigger,
+	.hw_free	= dmaengine_pcm_hw_free,
+	.trigger	= dmaengine_pcm_trigger,
 	.pointer	= dmaengine_pcm_pointer,
 	.copy_user	= dmaengine_copy_user,
-};
-
-static const struct snd_soc_component_driver dmaengine_pcm_component = {
-	.name		= SND_DMAENGINE_PCM_DRV_NAME,
-	.probe_order	= SND_SOC_COMP_ORDER_LATE,
-	.ops		= &dmaengine_pcm_ops,
-	.pcm_new	= dmaengine_pcm_new,
-};
-
-static const struct snd_soc_component_driver dmaengine_pcm_component_process = {
-	.name		= SND_DMAENGINE_PCM_DRV_NAME,
-	.probe_order	= SND_SOC_COMP_ORDER_LATE,
-	.ops		= &dmaengine_pcm_process_ops,
-	.pcm_new	= dmaengine_pcm_new,
+	.pcm_construct	= dmaengine_pcm_new,
 };
 
 static const char * const dmaengine_pcm_dma_channel_names[] = {
@@ -436,7 +387,7 @@ static int dmaengine_pcm_request_chan_of(struct dmaengine_pcm *pcm,
 			name = dmaengine_pcm_dma_channel_names[i];
 		if (config && config->chan_names[i])
 			name = config->chan_names[i];
-		chan = dma_request_slave_channel_reason(dev, name);
+		chan = dma_request_chan(dev, name);
 		if (IS_ERR(chan)) {
 			if (PTR_ERR(chan) == -EPROBE_DEFER)
 				return -EPROBE_DEFER;
diff --git a/sound/soc/soc-jack.c b/sound/soc/soc-jack.c
index a71d2340eb05..b5748dcd490f 100644
--- a/sound/soc/soc-jack.c
+++ b/sound/soc/soc-jack.c
@@ -82,10 +82,9 @@ void snd_soc_jack_report(struct snd_soc_jack *jack, int status, int mask)
 	unsigned int sync = 0;
 	int enable;
 
-	trace_snd_soc_jack_report(jack, mask, status);
-
 	if (!jack)
 		return;
+	trace_snd_soc_jack_report(jack, mask, status);
 
 	dapm = &jack->card->dapm;
 
diff --git a/sound/soc/soc-ops.c b/sound/soc/soc-ops.c
index f4dc3d445aae..652657dc6809 100644
--- a/sound/soc/soc-ops.c
+++ b/sound/soc/soc-ops.c
@@ -592,23 +592,16 @@ EXPORT_SYMBOL_GPL(snd_soc_get_volsw_range);
 int snd_soc_limit_volume(struct snd_soc_card *card,
 	const char *name, int max)
 {
-	struct snd_card *snd_card = card->snd_card;
 	struct snd_kcontrol *kctl;
 	struct soc_mixer_control *mc;
-	int found = 0;
 	int ret = -EINVAL;
 
 	/* Sanity check for name and max */
 	if (unlikely(!name || max <= 0))
 		return -EINVAL;
 
-	list_for_each_entry(kctl, &snd_card->controls, list) {
-		if (!strncmp(kctl->id.name, name, sizeof(kctl->id.name))) {
-			found = 1;
-			break;
-		}
-	}
-	if (found) {
+	kctl = snd_soc_card_get_kcontrol(card, name);
+	if (kctl) {
 		mc = (struct soc_mixer_control *)kctl->private_value;
 		if (max <= mc->max) {
 			mc->platform_max = max;
diff --git a/sound/soc/soc-pcm.c b/sound/soc/soc-pcm.c
index b600d3eaaf5c..76b7ee637e86 100644
--- a/sound/soc/soc-pcm.c
+++ b/sound/soc/soc-pcm.c
@@ -118,11 +118,8 @@ bool snd_soc_runtime_ignore_pmdown_time(struct snd_soc_pcm_runtime *rtd)
 	if (!rtd->pmdown_time || rtd->dai_link->ignore_pmdown_time)
 		return true;
 
-	for_each_rtdcom(rtd, rtdcom) {
-		component = rtdcom->component;
-
+	for_each_rtd_components(rtd, rtdcom, component)
 		ignore &= !component->driver->use_pmdown_time;
-	}
 
 	return ignore;
 }
@@ -435,8 +432,7 @@ static int soc_pcm_components_open(struct snd_pcm_substream *substream,
 	struct snd_soc_component *component;
 	int ret = 0;
 
-	for_each_rtdcom(rtd, rtdcom) {
-		component = rtdcom->component;
+	for_each_rtd_components(rtd, rtdcom, component) {
 		*last = component;
 
 		ret = snd_soc_component_module_get_when_open(component);
@@ -467,9 +463,7 @@ static int soc_pcm_components_close(struct snd_pcm_substream *substream,
 	struct snd_soc_component *component;
 	int ret = 0;
 
-	for_each_rtdcom(rtd, rtdcom) {
-		component = rtdcom->component;
-
+	for_each_rtd_components(rtd, rtdcom, component) {
 		if (component == last)
 			break;
 
@@ -500,9 +494,7 @@ static int soc_pcm_open(struct snd_pcm_substream *substream)
 	for_each_rtd_codec_dai(rtd, i, codec_dai)
 		pinctrl_pm_select_default_state(codec_dai->dev);
 
-	for_each_rtdcom(rtd, rtdcom) {
-		component = rtdcom->component;
-
+	for_each_rtd_components(rtd, rtdcom, component) {
 		pm_runtime_get_sync(component->dev);
 	}
 
@@ -625,9 +617,7 @@ component_err:
 out:
 	mutex_unlock(&rtd->card->pcm_mutex);
 
-	for_each_rtdcom(rtd, rtdcom) {
-		component = rtdcom->component;
-
+	for_each_rtd_components(rtd, rtdcom, component) {
 		pm_runtime_mark_last_busy(component->dev);
 		pm_runtime_put_autosuspend(component->dev);
 	}
@@ -740,9 +730,7 @@ static int soc_pcm_close(struct snd_pcm_substream *substream)
 
 	mutex_unlock(&rtd->card->pcm_mutex);
 
-	for_each_rtdcom(rtd, rtdcom) {
-		component = rtdcom->component;
-
+	for_each_rtd_components(rtd, rtdcom, component) {
 		pm_runtime_mark_last_busy(component->dev);
 		pm_runtime_put_autosuspend(component->dev);
 	}
@@ -782,9 +770,7 @@ static int soc_pcm_prepare(struct snd_pcm_substream *substream)
 		}
 	}
 
-	for_each_rtdcom(rtd, rtdcom) {
-		component = rtdcom->component;
-
+	for_each_rtd_components(rtd, rtdcom, component) {
 		ret = snd_soc_component_prepare(component, substream);
 		if (ret < 0) {
 			dev_err(component->dev,
@@ -849,9 +835,7 @@ static int soc_pcm_components_hw_free(struct snd_pcm_substream *substream,
 	struct snd_soc_component *component;
 	int ret = 0;
 
-	for_each_rtdcom(rtd, rtdcom) {
-		component = rtdcom->component;
-
+	for_each_rtd_components(rtd, rtdcom, component) {
 		if (component == last)
 			break;
 
@@ -877,6 +861,11 @@ static int soc_pcm_hw_params(struct snd_pcm_substream *substream,
 	int i, ret = 0;
 
 	mutex_lock_nested(&rtd->card->pcm_mutex, rtd->card->pcm_subclass);
+
+	ret = soc_pcm_params_symmetry(substream, params);
+	if (ret)
+		goto out;
+
 	if (rtd->dai_link->ops->hw_params) {
 		ret = rtd->dai_link->ops->hw_params(substream, params);
 		if (ret < 0) {
@@ -945,9 +934,7 @@ static int soc_pcm_hw_params(struct snd_pcm_substream *substream,
 
 	snd_soc_dapm_update_dai(substream, params, cpu_dai);
 
-	for_each_rtdcom(rtd, rtdcom) {
-		component = rtdcom->component;
-
+	for_each_rtd_components(rtd, rtdcom, component) {
 		ret = snd_soc_component_hw_params(component, substream, params);
 		if (ret < 0) {
 			dev_err(component->dev,
@@ -958,9 +945,6 @@ static int soc_pcm_hw_params(struct snd_pcm_substream *substream,
 	}
 	component = NULL;
 
-	ret = soc_pcm_params_symmetry(substream, params);
-        if (ret)
-		goto component_err;
 out:
 	mutex_unlock(&rtd->card->pcm_mutex);
 	return ret;
@@ -1047,7 +1031,7 @@ static int soc_pcm_hw_free(struct snd_pcm_substream *substream)
 	return 0;
 }
 
-static int soc_pcm_trigger(struct snd_pcm_substream *substream, int cmd)
+static int soc_pcm_trigger_start(struct snd_pcm_substream *substream, int cmd)
 {
 	struct snd_soc_pcm_runtime *rtd = substream->private_data;
 	struct snd_soc_component *component;
@@ -1056,16 +1040,42 @@ static int soc_pcm_trigger(struct snd_pcm_substream *substream, int cmd)
 	struct snd_soc_dai *codec_dai;
 	int i, ret;
 
+	if (rtd->dai_link->ops->trigger) {
+		ret = rtd->dai_link->ops->trigger(substream, cmd);
+		if (ret < 0)
+			return ret;
+	}
+
+	for_each_rtd_components(rtd, rtdcom, component) {
+		ret = snd_soc_component_trigger(component, substream, cmd);
+		if (ret < 0)
+			return ret;
+	}
+
+	ret = snd_soc_dai_trigger(cpu_dai, substream, cmd);
+	if (ret < 0)
+		return ret;
+
 	for_each_rtd_codec_dai(rtd, i, codec_dai) {
 		ret = snd_soc_dai_trigger(codec_dai, substream, cmd);
 		if (ret < 0)
 			return ret;
 	}
 
-	for_each_rtdcom(rtd, rtdcom) {
-		component = rtdcom->component;
+	return 0;
+}
 
-		ret = snd_soc_component_trigger(component, substream, cmd);
+static int soc_pcm_trigger_stop(struct snd_pcm_substream *substream, int cmd)
+{
+	struct snd_soc_pcm_runtime *rtd = substream->private_data;
+	struct snd_soc_component *component;
+	struct snd_soc_rtdcom_list *rtdcom;
+	struct snd_soc_dai *cpu_dai = rtd->cpu_dai;
+	struct snd_soc_dai *codec_dai;
+	int i, ret;
+
+	for_each_rtd_codec_dai(rtd, i, codec_dai) {
+		ret = snd_soc_dai_trigger(codec_dai, substream, cmd);
 		if (ret < 0)
 			return ret;
 	}
@@ -1074,6 +1084,12 @@ static int soc_pcm_trigger(struct snd_pcm_substream *substream, int cmd)
 	if (ret < 0)
 		return ret;
 
+	for_each_rtd_components(rtd, rtdcom, component) {
+		ret = snd_soc_component_trigger(component, substream, cmd);
+		if (ret < 0)
+			return ret;
+	}
+
 	if (rtd->dai_link->ops->trigger) {
 		ret = rtd->dai_link->ops->trigger(substream, cmd);
 		if (ret < 0)
@@ -1083,6 +1099,28 @@ static int soc_pcm_trigger(struct snd_pcm_substream *substream, int cmd)
 	return 0;
 }
 
+static int soc_pcm_trigger(struct snd_pcm_substream *substream, int cmd)
+{
+	int ret;
+
+	switch (cmd) {
+	case SNDRV_PCM_TRIGGER_START:
+	case SNDRV_PCM_TRIGGER_RESUME:
+	case SNDRV_PCM_TRIGGER_PAUSE_RELEASE:
+		ret = soc_pcm_trigger_start(substream, cmd);
+		break;
+	case SNDRV_PCM_TRIGGER_STOP:
+	case SNDRV_PCM_TRIGGER_SUSPEND:
+	case SNDRV_PCM_TRIGGER_PAUSE_PUSH:
+		ret = soc_pcm_trigger_stop(substream, cmd);
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	return ret;
+}
+
 static int soc_pcm_bespoke_trigger(struct snd_pcm_substream *substream,
 				   int cmd)
 {
@@ -1146,7 +1184,9 @@ static int dpcm_be_connect(struct snd_soc_pcm_runtime *fe,
 {
 	struct snd_soc_dpcm *dpcm;
 	unsigned long flags;
+#ifdef CONFIG_DEBUG_FS
 	char *name;
+#endif
 
 	/* only add new dpcms */
 	for_each_dpcm_be(fe, stream, dpcm) {
@@ -1385,6 +1425,7 @@ static int dpcm_prune_paths(struct snd_soc_pcm_runtime *fe, int stream,
 	struct snd_soc_dapm_widget *widget;
 	struct snd_soc_dai *dai;
 	int prune = 0;
+	int do_prune;
 
 	/* Destroy any old FE <--> BE connections */
 	for_each_dpcm_be(fe, stream, dpcm) {
@@ -1398,13 +1439,16 @@ static int dpcm_prune_paths(struct snd_soc_pcm_runtime *fe, int stream,
 			continue;
 
 		/* is there a valid CODEC DAI widget for this BE */
+		do_prune = 1;
 		for_each_rtd_codec_dai(dpcm->be, i, dai) {
 			widget = dai_get_widget(dai, stream);
 
 			/* prune the BE if it's no longer in our active list */
 			if (widget && widget_in_list(list, widget))
-				continue;
+				do_prune = 0;
 		}
+		if (!do_prune)
+			continue;
 
 		dev_dbg(fe->dev, "ASoC: pruning %s BE %s for %s\n",
 			stream ? "capture" : "playback",
@@ -2289,42 +2333,81 @@ int dpcm_be_dai_trigger(struct snd_soc_pcm_runtime *fe, int stream,
 }
 EXPORT_SYMBOL_GPL(dpcm_be_dai_trigger);
 
+static int dpcm_dai_trigger_fe_be(struct snd_pcm_substream *substream,
+				  int cmd, bool fe_first)
+{
+	struct snd_soc_pcm_runtime *fe = substream->private_data;
+	int ret;
+
+	/* call trigger on the frontend before the backend. */
+	if (fe_first) {
+		dev_dbg(fe->dev, "ASoC: pre trigger FE %s cmd %d\n",
+			fe->dai_link->name, cmd);
+
+		ret = soc_pcm_trigger(substream, cmd);
+		if (ret < 0)
+			return ret;
+
+		ret = dpcm_be_dai_trigger(fe, substream->stream, cmd);
+		return ret;
+	}
+
+	/* call trigger on the frontend after the backend. */
+	ret = dpcm_be_dai_trigger(fe, substream->stream, cmd);
+	if (ret < 0)
+		return ret;
+
+	dev_dbg(fe->dev, "ASoC: post trigger FE %s cmd %d\n",
+		fe->dai_link->name, cmd);
+
+	ret = soc_pcm_trigger(substream, cmd);
+
+	return ret;
+}
+
 static int dpcm_fe_dai_do_trigger(struct snd_pcm_substream *substream, int cmd)
 {
 	struct snd_soc_pcm_runtime *fe = substream->private_data;
-	int stream = substream->stream, ret;
+	int stream = substream->stream;
+	int ret = 0;
 	enum snd_soc_dpcm_trigger trigger = fe->dai_link->trigger[stream];
 
 	fe->dpcm[stream].runtime_update = SND_SOC_DPCM_UPDATE_FE;
 
 	switch (trigger) {
 	case SND_SOC_DPCM_TRIGGER_PRE:
-		/* call trigger on the frontend before the backend. */
-
-		dev_dbg(fe->dev, "ASoC: pre trigger FE %s cmd %d\n",
-				fe->dai_link->name, cmd);
-
-		ret = soc_pcm_trigger(substream, cmd);
-		if (ret < 0) {
-			dev_err(fe->dev,"ASoC: trigger FE failed %d\n", ret);
-			goto out;
+		switch (cmd) {
+		case SNDRV_PCM_TRIGGER_START:
+		case SNDRV_PCM_TRIGGER_RESUME:
+		case SNDRV_PCM_TRIGGER_PAUSE_RELEASE:
+			ret = dpcm_dai_trigger_fe_be(substream, cmd, true);
+			break;
+		case SNDRV_PCM_TRIGGER_STOP:
+		case SNDRV_PCM_TRIGGER_SUSPEND:
+		case SNDRV_PCM_TRIGGER_PAUSE_PUSH:
+			ret = dpcm_dai_trigger_fe_be(substream, cmd, false);
+			break;
+		default:
+			ret = -EINVAL;
+			break;
 		}
-
-		ret = dpcm_be_dai_trigger(fe, substream->stream, cmd);
 		break;
 	case SND_SOC_DPCM_TRIGGER_POST:
-		/* call trigger on the frontend after the backend. */
-
-		ret = dpcm_be_dai_trigger(fe, substream->stream, cmd);
-		if (ret < 0) {
-			dev_err(fe->dev,"ASoC: trigger FE failed %d\n", ret);
-			goto out;
+		switch (cmd) {
+		case SNDRV_PCM_TRIGGER_START:
+		case SNDRV_PCM_TRIGGER_RESUME:
+		case SNDRV_PCM_TRIGGER_PAUSE_RELEASE:
+			ret = dpcm_dai_trigger_fe_be(substream, cmd, false);
+			break;
+		case SNDRV_PCM_TRIGGER_STOP:
+		case SNDRV_PCM_TRIGGER_SUSPEND:
+		case SNDRV_PCM_TRIGGER_PAUSE_PUSH:
+			ret = dpcm_dai_trigger_fe_be(substream, cmd, true);
+			break;
+		default:
+			ret = -EINVAL;
+			break;
 		}
-
-		dev_dbg(fe->dev, "ASoC: post trigger FE %s cmd %d\n",
-				fe->dai_link->name, cmd);
-
-		ret = soc_pcm_trigger(substream, cmd);
 		break;
 	case SND_SOC_DPCM_TRIGGER_BESPOKE:
 		/* bespoke trigger() - handles both FE and BEs */
@@ -2333,10 +2416,6 @@ static int dpcm_fe_dai_do_trigger(struct snd_pcm_substream *substream, int cmd)
 				fe->dai_link->name, cmd);
 
 		ret = soc_pcm_bespoke_trigger(substream, cmd);
-		if (ret < 0) {
-			dev_err(fe->dev,"ASoC: trigger FE failed %d\n", ret);
-			goto out;
-		}
 		break;
 	default:
 		dev_err(fe->dev, "ASoC: invalid trigger cmd %d for %s\n", cmd,
@@ -2345,6 +2424,12 @@ static int dpcm_fe_dai_do_trigger(struct snd_pcm_substream *substream, int cmd)
 		goto out;
 	}
 
+	if (ret < 0) {
+		dev_err(fe->dev, "ASoC: trigger FE cmd: %d failed: %d\n",
+			cmd, ret);
+		goto out;
+	}
+
 	switch (cmd) {
 	case SNDRV_PCM_TRIGGER_START:
 	case SNDRV_PCM_TRIGGER_RESUME:
@@ -2809,21 +2894,13 @@ static int dpcm_fe_dai_close(struct snd_pcm_substream *fe_substream)
 	return ret;
 }
 
-static void soc_pcm_private_free(struct snd_pcm *pcm)
-{
-	struct snd_soc_pcm_runtime *rtd = pcm->private_data;
-
-	/* need to sync the delayed work before releasing resources */
-	flush_delayed_work(&rtd->delayed_work);
-	snd_soc_pcm_component_free(pcm);
-}
-
 /* create a new pcm */
 int soc_new_pcm(struct snd_soc_pcm_runtime *rtd, int num)
 {
 	struct snd_soc_dai *codec_dai;
 	struct snd_soc_dai *cpu_dai = rtd->cpu_dai;
 	struct snd_soc_rtdcom_list *rtdcom;
+	struct snd_soc_component *component;
 	struct snd_pcm *pcm;
 	char new_name[64];
 	int ret = 0, playback = 0, capture = 0;
@@ -2923,7 +3000,6 @@ int soc_new_pcm(struct snd_soc_pcm_runtime *rtd, int num)
 		rtd->ops.hw_free	= dpcm_fe_dai_hw_free;
 		rtd->ops.close		= dpcm_fe_dai_close;
 		rtd->ops.pointer	= soc_pcm_pointer;
-		rtd->ops.ioctl		= snd_soc_pcm_component_ioctl;
 	} else {
 		rtd->ops.open		= soc_pcm_open;
 		rtd->ops.hw_params	= soc_pcm_hw_params;
@@ -2932,20 +3008,20 @@ int soc_new_pcm(struct snd_soc_pcm_runtime *rtd, int num)
 		rtd->ops.hw_free	= soc_pcm_hw_free;
 		rtd->ops.close		= soc_pcm_close;
 		rtd->ops.pointer	= soc_pcm_pointer;
-		rtd->ops.ioctl		= snd_soc_pcm_component_ioctl;
 	}
 
-	for_each_rtdcom(rtd, rtdcom) {
-		const struct snd_pcm_ops *ops = rtdcom->component->driver->ops;
-
-		if (!ops)
-			continue;
+	for_each_rtd_components(rtd, rtdcom, component) {
+		const struct snd_soc_component_driver *drv = component->driver;
 
-		if (ops->copy_user)
+		if (drv->ioctl)
+			rtd->ops.ioctl		= snd_soc_pcm_component_ioctl;
+		if (drv->sync_stop)
+			rtd->ops.sync_stop	= snd_soc_pcm_component_sync_stop;
+		if (drv->copy_user)
 			rtd->ops.copy_user	= snd_soc_pcm_component_copy_user;
-		if (ops->page)
+		if (drv->page)
 			rtd->ops.page		= snd_soc_pcm_component_page;
-		if (ops->mmap)
+		if (drv->mmap)
 			rtd->ops.mmap		= snd_soc_pcm_component_mmap;
 	}
 
@@ -2955,13 +3031,12 @@ int soc_new_pcm(struct snd_soc_pcm_runtime *rtd, int num)
 	if (capture)
 		snd_pcm_set_ops(pcm, SNDRV_PCM_STREAM_CAPTURE, &rtd->ops);
 
-	ret = snd_soc_pcm_component_new(pcm);
+	ret = snd_soc_pcm_component_new(rtd);
 	if (ret < 0) {
 		dev_err(rtd->dev, "ASoC: pcm constructor failed: %d\n", ret);
 		return ret;
 	}
 
-	pcm->private_free = soc_pcm_private_free;
 	pcm->no_device_suspend = true;
 out:
 	dev_info(rtd->card->dev, "%s <-> %s mapping ok\n",
diff --git a/sound/soc/soc-topology.c b/sound/soc/soc-topology.c
index 0fd032914a31..81d2af000a5c 100644
--- a/sound/soc/soc-topology.c
+++ b/sound/soc/soc-topology.c
@@ -1800,6 +1800,9 @@ static int soc_tplg_dai_create(struct soc_tplg *tplg,
 	struct snd_soc_dai_driver *dai_drv;
 	struct snd_soc_pcm_stream *stream;
 	struct snd_soc_tplg_stream_caps *caps;
+	struct snd_soc_dai *dai;
+	struct snd_soc_dapm_context *dapm =
+		snd_soc_component_get_dapm(tplg->comp);
 	int ret;
 
 	dai_drv = kzalloc(sizeof(struct snd_soc_dai_driver), GFP_KERNEL);
@@ -1842,7 +1845,19 @@ static int soc_tplg_dai_create(struct soc_tplg *tplg,
 	list_add(&dai_drv->dobj.list, &tplg->comp->dobj_list);
 
 	/* register the DAI to the component */
-	return snd_soc_register_dai(tplg->comp, dai_drv);
+	dai = snd_soc_register_dai(tplg->comp, dai_drv, false);
+	if (!dai)
+		return -ENOMEM;
+
+	/* Create the DAI widgets here */
+	ret = snd_soc_dapm_new_dai_widgets(dapm, dai);
+	if (ret != 0) {
+		dev_err(dai->dev, "Failed to create DAI widgets %d\n", ret);
+		snd_soc_unregister_dai(dai);
+		return ret;
+	}
+
+	return ret;
 }
 
 static void set_link_flags(struct snd_soc_dai_link *link,
diff --git a/sound/soc/soc-utils.c b/sound/soc/soc-utils.c
index 54dcece52b0c..2fd4562f5e63 100644
--- a/sound/soc/soc-utils.c
+++ b/sound/soc/soc-utils.c
@@ -63,7 +63,8 @@ static const struct snd_pcm_hardware dummy_dma_hardware = {
 	.periods_max		= 128,
 };
 
-static int dummy_dma_open(struct snd_pcm_substream *substream)
+static int dummy_dma_open(struct snd_soc_component *component,
+			  struct snd_pcm_substream *substream)
 {
 	struct snd_soc_pcm_runtime *rtd = substream->private_data;
 
@@ -74,13 +75,9 @@ static int dummy_dma_open(struct snd_pcm_substream *substream)
 	return 0;
 }
 
-static const struct snd_pcm_ops snd_dummy_dma_ops = {
-	.open		= dummy_dma_open,
-	.ioctl		= snd_pcm_lib_ioctl,
-};
-
 static const struct snd_soc_component_driver dummy_platform = {
-	.ops = &snd_dummy_dma_ops,
+	.open		= dummy_dma_open,
+	.ioctl		= snd_soc_pcm_lib_ioctl,
 };
 
 static const struct snd_soc_component_driver dummy_codec = {
diff --git a/sound/soc/sof/Kconfig b/sound/soc/sof/Kconfig
index bb8036ae567e..71a0fc075a63 100644
--- a/sound/soc/sof/Kconfig
+++ b/sound/soc/sof/Kconfig
@@ -14,8 +14,6 @@ config SND_SOC_SOF_PCI
 	depends on PCI
 	select SND_SOC_SOF
 	select SND_SOC_ACPI if ACPI
-	select SND_SOC_SOF_OPTIONS
-	select SND_SOC_SOF_INTEL_PCI if SND_SOC_SOF_INTEL_TOPLEVEL
 	help
 	  This adds support for PCI enumeration. This option is
 	  required to enable Intel Skylake+ devices
@@ -27,8 +25,6 @@ config SND_SOC_SOF_ACPI
 	depends on ACPI || COMPILE_TEST
 	select SND_SOC_SOF
 	select SND_SOC_ACPI if ACPI
-	select SND_SOC_SOF_OPTIONS
-	select SND_SOC_SOF_INTEL_ACPI if SND_SOC_SOF_INTEL_TOPLEVEL
 	select IOSF_MBI if X86 && PCI
 	help
 	  This adds support for ACPI enumeration. This option is required
@@ -40,19 +36,23 @@ config SND_SOC_SOF_OF
 	tristate "SOF OF enumeration support"
 	depends on OF || COMPILE_TEST
 	select SND_SOC_SOF
-	select SND_SOC_SOF_OPTIONS
 	help
 	  This adds support for Device Tree enumeration. This option is
 	  required to enable i.MX8 devices.
 	  Say Y if you need this option. If unsure select "N".
 
-config SND_SOC_SOF_OPTIONS
-	tristate
+config SND_SOC_SOF_DEVELOPER_SUPPORT
+	bool "SOF developer options support"
+	depends on EXPERT
 	help
-	  This option is not user-selectable but automagically handled by
-	  'select' statements at a higher level
+	  This option unlock SOF developer options for debug/performance/
+	  code hardening.
+	  Distributions should not select this option, only SOF development
+	  teams should select it.
+	  Say Y if you are involved in SOF development and need this option
+	  If not, select N
 
-if SND_SOC_SOF_OPTIONS
+if SND_SOC_SOF_DEVELOPER_SUPPORT
 
 config SND_SOC_SOF_NOCODEC
 	tristate
@@ -64,6 +64,11 @@ config SND_SOC_SOF_NOCODEC_SUPPORT
 	  option if no known codec is detected. This is typically only
 	  enabled for developers or devices where the sound card is
 	  controlled externally
+	  This option is mutually exclusive with the Intel HDaudio support,
+	  selecting it may have negative impacts and prevent e.g. microphone
+	  functionality from being enabled on Intel CoffeeLake and later
+	  platforms.
+	  Distributions should not select this option!
 	  Say Y if you need this nocodec fallback option
 	  If unsure select "N".
 
@@ -142,6 +147,14 @@ config SND_SOC_SOF_DEBUG_ENABLE_DEBUGFS_CACHE
 	  Say Y if you want to enable caching the memory windows.
 	  If unsure, select "N".
 
+config SND_SOC_SOF_DEBUG_ENABLE_FIRMWARE_TRACE
+	bool "SOF enable firmware trace"
+	help
+	  The firmware trace can be enabled either at build-time with
+	  this option, or dynamically by setting flags in the SOF core
+	  module parameter (similar to dynamic debug)
+	  If unsure, select "N".
+
 config SND_SOC_SOF_DEBUG_IPC_FLOOD_TEST
 	bool "SOF enable IPC flood test"
 	help
@@ -150,9 +163,17 @@ config SND_SOC_SOF_DEBUG_IPC_FLOOD_TEST
 	  Say Y if you want to enable IPC flood test.
 	  If unsure, select "N".
 
+config SND_SOC_SOF_DEBUG_RETAIN_DSP_CONTEXT
+	bool "SOF retain DSP context on any FW exceptions"
+	help
+	  This option keeps the DSP in D0 state so that firmware debug
+	  information can be retained and dumped to userspace.
+	  Say Y if you want to retain DSP context for FW exceptions.
+	  If unsure, select "N".
+
 endif ## SND_SOC_SOF_DEBUG
 
-endif ## SND_SOC_SOF_OPTIONS
+endif ## SND_SOC_SOF_DEVELOPER_SUPPORT
 
 config SND_SOC_SOF
 	tristate
diff --git a/sound/soc/sof/control.c b/sound/soc/sof/control.c
index 2b8711eda362..7baf7f1507c3 100644
--- a/sound/soc/sof/control.c
+++ b/sound/soc/sof/control.c
@@ -11,8 +11,39 @@
 /* Mixer Controls */
 
 #include <linux/pm_runtime.h>
+#include <linux/leds.h>
 #include "sof-priv.h"
 
+static void update_mute_led(struct snd_sof_control *scontrol,
+			    struct snd_kcontrol *kcontrol,
+			    struct snd_ctl_elem_value *ucontrol)
+{
+	unsigned int temp = 0;
+	unsigned int mask;
+	int i;
+
+	mask = 1U << snd_ctl_get_ioffidx(kcontrol, &ucontrol->id);
+
+	for (i = 0; i < scontrol->num_channels; i++) {
+		if (ucontrol->value.integer.value[i]) {
+			temp |= mask;
+			break;
+		}
+	}
+
+	if (temp == scontrol->led_ctl.led_value)
+		return;
+
+	scontrol->led_ctl.led_value = temp;
+
+#if IS_REACHABLE(CONFIG_LEDS_TRIGGER_AUDIO)
+	if (!scontrol->led_ctl.direction)
+		ledtrig_audio_set(LED_AUDIO_MUTE, temp ? LED_OFF : LED_ON);
+	else
+		ledtrig_audio_set(LED_AUDIO_MICMUTE, temp ? LED_OFF : LED_ON);
+#endif
+}
+
 static inline u32 mixer_to_ipc(unsigned int value, u32 *volume_map, int size)
 {
 	if (value >= size)
@@ -118,6 +149,9 @@ int snd_sof_switch_put(struct snd_kcontrol *kcontrol,
 		cdata->chanv[i].value = value;
 	}
 
+	if (scontrol->led_ctl.use_led)
+		update_mute_led(scontrol, kcontrol, ucontrol);
+
 	/* notify DSP of mixer updates */
 	if (pm_runtime_active(sdev->dev))
 		snd_sof_ipc_set_get_comp_data(sdev->ipc, scontrol,
diff --git a/sound/soc/sof/core.c b/sound/soc/sof/core.c
index 81f28f7ff1a0..805918d3bcc0 100644
--- a/sound/soc/sof/core.c
+++ b/sound/soc/sof/core.c
@@ -16,6 +16,11 @@
 #include "sof-priv.h"
 #include "ops.h"
 
+/* see SOF_DBG_ flags */
+int sof_core_debug;
+module_param_named(sof_debug, sof_core_debug, int, 0444);
+MODULE_PARM_DESC(sof_debug, "SOF core debug options (0x0 all off)");
+
 /* SOF defaults if not provided by the platform in ms */
 #define TIMEOUT_DEFAULT_IPC_MS  500
 #define TIMEOUT_DEFAULT_BOOT_MS 2000
@@ -127,6 +132,19 @@ struct snd_sof_dai *snd_sof_find_dai(struct snd_sof_dev *sdev,
 	return NULL;
 }
 
+bool snd_sof_dsp_d0i3_on_suspend(struct snd_sof_dev *sdev)
+{
+	struct snd_sof_pcm *spcm;
+
+	list_for_each_entry(spcm, &sdev->pcm_list, list) {
+		if (spcm->stream[SNDRV_PCM_STREAM_PLAYBACK].suspend_ignored ||
+		    spcm->stream[SNDRV_PCM_STREAM_CAPTURE].suspend_ignored)
+			return true;
+	}
+
+	return false;
+}
+
 /*
  * FW Panic/fault handling.
  */
@@ -350,12 +368,20 @@ static int sof_probe_continue(struct snd_sof_dev *sdev)
 		goto fw_run_err;
 	}
 
-	/* init DMA trace */
-	ret = snd_sof_init_trace(sdev);
-	if (ret < 0) {
-		/* non fatal */
-		dev_warn(sdev->dev,
-			 "warning: failed to initialize trace %d\n", ret);
+	if (IS_ENABLED(CONFIG_SND_SOC_SOF_DEBUG_ENABLE_FIRMWARE_TRACE) ||
+	    (sof_core_debug & SOF_DBG_ENABLE_TRACE)) {
+		sdev->dtrace_is_supported = true;
+
+		/* init DMA trace */
+		ret = snd_sof_init_trace(sdev);
+		if (ret < 0) {
+			/* non fatal */
+			dev_warn(sdev->dev,
+				 "warning: failed to initialize trace %d\n",
+				 ret);
+		}
+	} else {
+		dev_dbg(sdev->dev, "SOF firmware trace disabled\n");
 	}
 
 	/* hereafter all FW boot flows are for PM reasons */
@@ -445,6 +471,9 @@ int snd_sof_device_probe(struct device *dev, struct snd_sof_pdata *plat_data)
 	/* initialize sof device */
 	sdev->dev = dev;
 
+	/* initialize default D0 sub-state */
+	sdev->d0_substate = SOF_DSP_D0I0;
+
 	sdev->pdata = plat_data;
 	sdev->first_boot = true;
 	dev_set_drvdata(dev, sdev);
@@ -453,7 +482,8 @@ int snd_sof_device_probe(struct device *dev, struct snd_sof_pdata *plat_data)
 	if (!sof_ops(sdev) || !sof_ops(sdev)->probe || !sof_ops(sdev)->run ||
 	    !sof_ops(sdev)->block_read || !sof_ops(sdev)->block_write ||
 	    !sof_ops(sdev)->send_msg || !sof_ops(sdev)->load_firmware ||
-	    !sof_ops(sdev)->ipc_msg_data || !sof_ops(sdev)->ipc_pcm_params)
+	    !sof_ops(sdev)->ipc_msg_data || !sof_ops(sdev)->ipc_pcm_params ||
+	    !sof_ops(sdev)->fw_ready)
 		return -EINVAL;
 
 	INIT_LIST_HEAD(&sdev->pcm_list);
diff --git a/sound/soc/sof/debug.c b/sound/soc/sof/debug.c
index 5529e8eeca46..d2b3b99d3a20 100644
--- a/sound/soc/sof/debug.c
+++ b/sound/soc/sof/debug.c
@@ -463,3 +463,19 @@ void snd_sof_free_debug(struct snd_sof_dev *sdev)
 	debugfs_remove_recursive(sdev->debugfs_root);
 }
 EXPORT_SYMBOL_GPL(snd_sof_free_debug);
+
+void snd_sof_handle_fw_exception(struct snd_sof_dev *sdev)
+{
+	if (IS_ENABLED(CONFIG_SND_SOC_SOF_DEBUG_RETAIN_DSP_CONTEXT) ||
+	    (sof_core_debug & SOF_DBG_RETAIN_CTX)) {
+		/* should we prevent DSP entering D3 ? */
+		dev_info(sdev->dev, "info: preventing DSP entering D3 state to preserve context\n");
+		pm_runtime_get_noresume(sdev->dev);
+	}
+
+	/* dump vital information to the logs */
+	snd_sof_dsp_dbg_dump(sdev, SOF_DBG_REGS | SOF_DBG_MBOX);
+	snd_sof_ipc_dump(sdev);
+	snd_sof_trace_notify_for_error(sdev);
+}
+EXPORT_SYMBOL(snd_sof_handle_fw_exception);
diff --git a/sound/soc/sof/imx/Kconfig b/sound/soc/sof/imx/Kconfig
index 5acae75f5750..bae4f7bf5f75 100644
--- a/sound/soc/sof/imx/Kconfig
+++ b/sound/soc/sof/imx/Kconfig
@@ -5,19 +5,23 @@ config SND_SOC_SOF_IMX_TOPLEVEL
 	depends on ARM64|| COMPILE_TEST
 	depends on SND_SOC_SOF_OF
 	help
-          This adds support for Sound Open Firmware for NXP i.MX platforms.
-          Say Y if you have such a device.
-          If unsure select "N".
+	  This adds support for Sound Open Firmware for NXP i.MX platforms.
+	  Say Y if you have such a device.
+	  If unsure select "N".
 
 if SND_SOC_SOF_IMX_TOPLEVEL
 
-config SND_SOC_SOF_IMX8
-	tristate "SOF support for i.MX8"
+config SND_SOC_SOF_IMX8_SUPPORT
+	bool "SOF support for i.MX8"
 	depends on IMX_SCU
 	depends on IMX_DSP
 	help
-          This adds support for Sound Open Firmware for NXP i.MX8 platforms
-          Say Y if you have such a device.
-          If unsure select "N".
+	  This adds support for Sound Open Firmware for NXP i.MX8 platforms
+	  Say Y if you have such a device.
+	  If unsure select "N".
+
+config SND_SOC_SOF_IMX8
+	def_tristate SND_SOC_SOF_OF
+	depends on SND_SOC_SOF_IMX8_SUPPORT
 
 endif ## SND_SOC_SOF_IMX_IMX_TOPLEVEL
diff --git a/sound/soc/sof/imx/imx8.c b/sound/soc/sof/imx/imx8.c
index 2a22b18e5ec0..cfefcfd92798 100644
--- a/sound/soc/sof/imx/imx8.c
+++ b/sound/soc/sof/imx/imx8.c
@@ -388,6 +388,13 @@ struct snd_sof_dsp_ops sof_imx8_ops = {
 	/* DAI drivers */
 	.drv = imx8_dai,
 	.num_drv = 1, /* we have only 1 ESAI interface on i.MX8 */
+
+	/* ALSA HW info flags */
+	.hw_info =	SNDRV_PCM_INFO_MMAP |
+			SNDRV_PCM_INFO_MMAP_VALID |
+			SNDRV_PCM_INFO_INTERLEAVED |
+			SNDRV_PCM_INFO_PAUSE |
+			SNDRV_PCM_INFO_NO_PERIOD_WAKEUP
 };
 EXPORT_SYMBOL(sof_imx8_ops);
 
diff --git a/sound/soc/sof/intel/Kconfig b/sound/soc/sof/intel/Kconfig
index d62f51d33be1..cc09bb606f7d 100644
--- a/sound/soc/sof/intel/Kconfig
+++ b/sound/soc/sof/intel/Kconfig
@@ -10,7 +10,7 @@ config SND_SOC_SOF_INTEL_TOPLEVEL
 if SND_SOC_SOF_INTEL_TOPLEVEL
 
 config SND_SOC_SOF_INTEL_ACPI
-	tristate
+	def_tristate SND_SOC_SOF_ACPI
 	select SND_SOC_SOF_BAYTRAIL  if SND_SOC_SOF_BAYTRAIL_SUPPORT
 	select SND_SOC_SOF_BROADWELL if SND_SOC_SOF_BROADWELL_SUPPORT
 	help
@@ -18,7 +18,7 @@ config SND_SOC_SOF_INTEL_ACPI
 	  'select' statements at a higher level
 
 config SND_SOC_SOF_INTEL_PCI
-	tristate
+	def_tristate SND_SOC_SOF_PCI
 	select SND_SOC_SOF_MERRIFIELD  if SND_SOC_SOF_MERRIFIELD_SUPPORT
 	select SND_SOC_SOF_APOLLOLAKE  if SND_SOC_SOF_APOLLOLAKE_SUPPORT
 	select SND_SOC_SOF_GEMINILAKE  if SND_SOC_SOF_GEMINILAKE_SUPPORT
@@ -29,6 +29,7 @@ config SND_SOC_SOF_INTEL_PCI
 	select SND_SOC_SOF_COMETLAKE_H if SND_SOC_SOF_COMETLAKE_H_SUPPORT
 	select SND_SOC_SOF_TIGERLAKE   if SND_SOC_SOF_TIGERLAKE_SUPPORT
 	select SND_SOC_SOF_ELKHARTLAKE if SND_SOC_SOF_ELKHARTLAKE_SUPPORT
+	select SND_SOC_SOF_JASPERLAKE  if SND_SOC_SOF_JASPERLAKE_SUPPORT
 	help
 	  This option is not user-selectable but automagically handled by
 	  'select' statements at a higher level
@@ -36,7 +37,7 @@ config SND_SOC_SOF_INTEL_PCI
 config SND_SOC_SOF_INTEL_HIFI_EP_IPC
 	tristate
 	help
-          This option is not user-selectable but automagically handled by
+	  This option is not user-selectable but automagically handled by
 	  'select' statements at a higher level
 
 config SND_SOC_SOF_INTEL_ATOM_HIFI_EP
@@ -61,10 +62,18 @@ if SND_SOC_SOF_INTEL_ACPI
 
 config SND_SOC_SOF_BAYTRAIL_SUPPORT
 	bool "SOF support for Baytrail, Braswell and Cherrytrail"
+	depends on SND_SST_ATOM_HIFI2_PLATFORM_ACPI=n
 	help
 	  This adds support for Sound Open Firmware for Intel(R) platforms
 	  using the Baytrail, Braswell or Cherrytrail processors.
-	  Say Y if you have such a device.
+	  This option is mutually exclusive with the Atom/SST and Baytrail
+	  legacy drivers. If you want to enable SOF on Baytrail/Cherrytrail,
+	  you need to deselect those options first.
+	  SOF does not support Baytrail-CR for now, so this option is not
+	  recommended for distros. At some point all legacy drivers will be
+	  deprecated but not before all userspace firmware/topology/UCM files
+	  are made available to downstream distros.
+	  Say Y if you want to enable SOF on Baytrail/Cherrytrail
 	  If unsure select "N".
 
 config SND_SOC_SOF_BAYTRAIL
@@ -76,10 +85,18 @@ config SND_SOC_SOF_BAYTRAIL
 
 config SND_SOC_SOF_BROADWELL_SUPPORT
 	bool "SOF support for Broadwell"
+	depends on SND_SOC_INTEL_HASWELL=n
 	help
 	  This adds support for Sound Open Firmware for Intel(R) platforms
 	  using the Broadwell processors.
-	  Say Y if you have such a device.
+	  This option is mutually exclusive with the Haswell/Broadwell legacy
+	  driver. If you want to enable SOF on Broadwell you need to deselect
+	  the legacy driver first.
+	  SOF does fully support Broadwell yet, so this option is not
+	  recommended for distros. At some point all legacy drivers will be
+	  deprecated but not before all userspace firmware/topology/UCM files
+	  are made available to downstream distros.
+	  Say Y if you want to enable SOF on Broadwell
 	  If unsure select "N".
 
 config SND_SOC_SOF_BROADWELL
@@ -217,31 +234,46 @@ config SND_SOC_SOF_COMETLAKE_H_SUPPORT
 config SND_SOC_SOF_TIGERLAKE_SUPPORT
 	bool "SOF support for Tigerlake"
 	help
-          This adds support for Sound Open Firmware for Intel(R) platforms
-          using the Tigerlake processors.
-          Say Y if you have such a device.
-          If unsure select "N".
+	  This adds support for Sound Open Firmware for Intel(R) platforms
+	  using the Tigerlake processors.
+	  Say Y if you have such a device.
+	  If unsure select "N".
 
 config SND_SOC_SOF_TIGERLAKE
 	tristate
 	select SND_SOC_SOF_HDA_COMMON
 	help
-          This option is not user-selectable but automagically handled by
+	  This option is not user-selectable but automagically handled by
 	  'select' statements at a higher level
 
 config SND_SOC_SOF_ELKHARTLAKE_SUPPORT
 	bool "SOF support for ElkhartLake"
 	help
-          This adds support for Sound Open Firmware for Intel(R) platforms
-          using the ElkhartLake processors.
-          Say Y if you have such a device.
-          If unsure select "N".
+	  This adds support for Sound Open Firmware for Intel(R) platforms
+	  using the ElkhartLake processors.
+	  Say Y if you have such a device.
+	  If unsure select "N".
 
 config SND_SOC_SOF_ELKHARTLAKE
 	tristate
 	select SND_SOC_SOF_HDA_COMMON
 	help
-          This option is not user-selectable but automagically handled by
+	  This option is not user-selectable but automagically handled by
+	  'select' statements at a higher level
+
+config SND_SOC_SOF_JASPERLAKE_SUPPORT
+	bool "SOF support for JasperLake"
+	help
+	  This adds support for Sound Open Firmware for Intel(R) platforms
+	  using the JasperLake processors.
+	  Say Y if you have such a device.
+	  If unsure select "N".
+
+config SND_SOC_SOF_JASPERLAKE
+	tristate
+	select SND_SOC_SOF_HDA_COMMON
+	help
+	  This option is not user-selectable but automagically handled by
 	  'select' statements at a higher level
 
 config SND_SOC_SOF_HDA_COMMON
@@ -283,6 +315,16 @@ config SND_SOC_SOF_HDA_ALWAYS_ENABLE_DMI_L1
 	  Say Y if you want to enable DMI Link L1
 	  If unsure, select "N".
 
+config SND_SOC_SOF_HDA_COMMON_HDMI_CODEC
+	bool "SOF common HDA HDMI codec driver"
+	depends on SND_SOC_SOF_HDA_LINK
+	depends on SND_HDA_CODEC_HDMI
+	help
+	  This adds support for HDMI audio by using the common HDA
+	  HDMI/DisplayPort codec driver.
+	  Say Y if you want to use the common codec driver with SOF.
+	  If unsure select "Y".
+
 endif ## SND_SOC_SOF_HDA_COMMON
 
 config SND_SOC_SOF_HDA_LINK_BASELINE
@@ -296,7 +338,7 @@ config SND_SOC_SOF_HDA
 	tristate
 	select SND_HDA_EXT_CORE if SND_SOC_SOF_HDA_LINK
 	select SND_SOC_HDAC_HDA if SND_SOC_SOF_HDA_AUDIO_CODEC
-	select SND_INTEL_NHLT if ACPI
+	select SND_INTEL_DSP_CONFIG
 	help
 	  This option is not user-selectable but automagically handled by
 	  'select' statements at a higher level
diff --git a/sound/soc/sof/intel/apl.c b/sound/soc/sof/intel/apl.c
index 8dc7a5558da4..7daa8eb456c8 100644
--- a/sound/soc/sof/intel/apl.c
+++ b/sound/soc/sof/intel/apl.c
@@ -97,6 +97,14 @@ const struct snd_sof_dsp_ops sof_apl_ops = {
 	.runtime_resume		= hda_dsp_runtime_resume,
 	.runtime_idle		= hda_dsp_runtime_idle,
 	.set_hw_params_upon_resume = hda_dsp_set_hw_params_upon_resume,
+	.set_power_state	= hda_dsp_set_power_state,
+
+	/* ALSA HW info flags */
+	.hw_info =	SNDRV_PCM_INFO_MMAP |
+			SNDRV_PCM_INFO_MMAP_VALID |
+			SNDRV_PCM_INFO_INTERLEAVED |
+			SNDRV_PCM_INFO_PAUSE |
+			SNDRV_PCM_INFO_NO_PERIOD_WAKEUP,
 };
 EXPORT_SYMBOL(sof_apl_ops);
 
diff --git a/sound/soc/sof/intel/bdw.c b/sound/soc/sof/intel/bdw.c
index 80e2826fb447..141dad554764 100644
--- a/sound/soc/sof/intel/bdw.c
+++ b/sound/soc/sof/intel/bdw.c
@@ -247,7 +247,7 @@ static void bdw_dump(struct snd_sof_dev *sdev, u32 flags)
 	struct sof_ipc_dsp_oops_xtensa xoops;
 	struct sof_ipc_panic_info panic_info;
 	u32 stack[BDW_STACK_DUMP_SIZE];
-	u32 status, panic;
+	u32 status, panic, imrx, imrd;
 
 	/* now try generic SOF status messages */
 	status = snd_sof_dsp_read(sdev, BDW_DSP_BAR, SHIM_IPCD);
@@ -256,6 +256,26 @@ static void bdw_dump(struct snd_sof_dev *sdev, u32 flags)
 			  BDW_STACK_DUMP_SIZE);
 	snd_sof_get_status(sdev, status, panic, &xoops, &panic_info, stack,
 			   BDW_STACK_DUMP_SIZE);
+
+	/* provide some context for firmware debug */
+	imrx = snd_sof_dsp_read(sdev, BDW_DSP_BAR, SHIM_IMRX);
+	imrd = snd_sof_dsp_read(sdev, BDW_DSP_BAR, SHIM_IMRD);
+	dev_err(sdev->dev,
+		"error: ipc host -> DSP: pending %s complete %s raw 0x%8.8x\n",
+		(panic & SHIM_IPCX_BUSY) ? "yes" : "no",
+		(panic & SHIM_IPCX_DONE) ? "yes" : "no", panic);
+	dev_err(sdev->dev,
+		"error: mask host: pending %s complete %s raw 0x%8.8x\n",
+		(imrx & SHIM_IMRX_BUSY) ? "yes" : "no",
+		(imrx & SHIM_IMRX_DONE) ? "yes" : "no", imrx);
+	dev_err(sdev->dev,
+		"error: ipc DSP -> host: pending %s complete %s raw 0x%8.8x\n",
+		(status & SHIM_IPCD_BUSY) ? "yes" : "no",
+		(status & SHIM_IPCD_DONE) ? "yes" : "no", status);
+	dev_err(sdev->dev,
+		"error: mask DSP: pending %s complete %s raw 0x%8.8x\n",
+		(imrd & SHIM_IMRD_BUSY) ? "yes" : "no",
+		(imrd & SHIM_IMRD_DONE) ? "yes" : "no", imrd);
 }
 
 /*
@@ -571,7 +591,14 @@ const struct snd_sof_dsp_ops sof_bdw_ops = {
 
 	/* DAI drivers */
 	.drv = bdw_dai,
-	.num_drv = ARRAY_SIZE(bdw_dai)
+	.num_drv = ARRAY_SIZE(bdw_dai),
+
+	/* ALSA HW info flags */
+	.hw_info =	SNDRV_PCM_INFO_MMAP |
+			SNDRV_PCM_INFO_MMAP_VALID |
+			SNDRV_PCM_INFO_INTERLEAVED |
+			SNDRV_PCM_INFO_PAUSE |
+			SNDRV_PCM_INFO_BATCH,
 };
 EXPORT_SYMBOL(sof_bdw_ops);
 
diff --git a/sound/soc/sof/intel/byt.c b/sound/soc/sof/intel/byt.c
index a1e514f71739..2abf80b3eb52 100644
--- a/sound/soc/sof/intel/byt.c
+++ b/sound/soc/sof/intel/byt.c
@@ -145,7 +145,7 @@ static void byt_dump(struct snd_sof_dev *sdev, u32 flags)
 	struct sof_ipc_dsp_oops_xtensa xoops;
 	struct sof_ipc_panic_info panic_info;
 	u32 stack[BYT_STACK_DUMP_SIZE];
-	u32 status, panic;
+	u32 status, panic, imrd, imrx;
 
 	/* now try generic SOF status messages */
 	status = snd_sof_dsp_read(sdev, BYT_DSP_BAR, SHIM_IPCD);
@@ -154,6 +154,27 @@ static void byt_dump(struct snd_sof_dev *sdev, u32 flags)
 			  BYT_STACK_DUMP_SIZE);
 	snd_sof_get_status(sdev, status, panic, &xoops, &panic_info, stack,
 			   BYT_STACK_DUMP_SIZE);
+
+	/* provide some context for firmware debug */
+	imrx = snd_sof_dsp_read(sdev, BYT_DSP_BAR, SHIM_IMRX);
+	imrd = snd_sof_dsp_read(sdev, BYT_DSP_BAR, SHIM_IMRD);
+	dev_err(sdev->dev,
+		"error: ipc host -> DSP: pending %s complete %s raw 0x%8.8x\n",
+		(panic & SHIM_IPCX_BUSY) ? "yes" : "no",
+		(panic & SHIM_IPCX_DONE) ? "yes" : "no", panic);
+	dev_err(sdev->dev,
+		"error: mask host: pending %s complete %s raw 0x%8.8x\n",
+		(imrx & SHIM_IMRX_BUSY) ? "yes" : "no",
+		(imrx & SHIM_IMRX_DONE) ? "yes" : "no", imrx);
+	dev_err(sdev->dev,
+		"error: ipc DSP -> host: pending %s complete %s raw 0x%8.8x\n",
+		(status & SHIM_IPCD_BUSY) ? "yes" : "no",
+		(status & SHIM_IPCD_DONE) ? "yes" : "no", status);
+	dev_err(sdev->dev,
+		"error: mask DSP: pending %s complete %s raw 0x%8.8x\n",
+		(imrd & SHIM_IMRD_BUSY) ? "yes" : "no",
+		(imrd & SHIM_IMRD_DONE) ? "yes" : "no", imrd);
+
 }
 
 /*
@@ -511,6 +532,13 @@ const struct snd_sof_dsp_ops sof_tng_ops = {
 	/* DAI drivers */
 	.drv = byt_dai,
 	.num_drv = 3, /* we have only 3 SSPs on byt*/
+
+	/* ALSA HW info flags */
+	.hw_info =	SNDRV_PCM_INFO_MMAP |
+			SNDRV_PCM_INFO_MMAP_VALID |
+			SNDRV_PCM_INFO_INTERLEAVED |
+			SNDRV_PCM_INFO_PAUSE |
+			SNDRV_PCM_INFO_BATCH,
 };
 EXPORT_SYMBOL(sof_tng_ops);
 
@@ -672,6 +700,13 @@ const struct snd_sof_dsp_ops sof_byt_ops = {
 	/* DAI drivers */
 	.drv = byt_dai,
 	.num_drv = 3, /* we have only 3 SSPs on byt*/
+
+	/* ALSA HW info flags */
+	.hw_info =	SNDRV_PCM_INFO_MMAP |
+			SNDRV_PCM_INFO_MMAP_VALID |
+			SNDRV_PCM_INFO_INTERLEAVED |
+			SNDRV_PCM_INFO_PAUSE |
+			SNDRV_PCM_INFO_BATCH,
 };
 EXPORT_SYMBOL(sof_byt_ops);
 
@@ -732,6 +767,13 @@ const struct snd_sof_dsp_ops sof_cht_ops = {
 	.drv = byt_dai,
 	/* all 6 SSPs may be available for cherrytrail */
 	.num_drv = ARRAY_SIZE(byt_dai),
+
+	/* ALSA HW info flags */
+	.hw_info =	SNDRV_PCM_INFO_MMAP |
+			SNDRV_PCM_INFO_MMAP_VALID |
+			SNDRV_PCM_INFO_INTERLEAVED |
+			SNDRV_PCM_INFO_PAUSE |
+			SNDRV_PCM_INFO_BATCH,
 };
 EXPORT_SYMBOL(sof_cht_ops);
 
diff --git a/sound/soc/sof/intel/cnl.c b/sound/soc/sof/intel/cnl.c
index 4ddd73762d81..0e1e265f3f3b 100644
--- a/sound/soc/sof/intel/cnl.c
+++ b/sound/soc/sof/intel/cnl.c
@@ -17,6 +17,7 @@
 
 #include "../ops.h"
 #include "hda.h"
+#include "hda-ipc.h"
 
 static const struct snd_sof_debugfs_map cnl_dsp_debugfs[] = {
 	{"hda", HDA_DSP_HDA_BAR, 0, 0x4000, SOF_DEBUGFS_ACCESS_ALWAYS},
@@ -150,14 +151,45 @@ static void cnl_ipc_dsp_done(struct snd_sof_dev *sdev)
 				CNL_DSP_REG_HIPCCTL_DONE);
 }
 
+static bool cnl_compact_ipc_compress(struct snd_sof_ipc_msg *msg,
+				     u32 *dr, u32 *dd)
+{
+	struct sof_ipc_pm_gate *pm_gate;
+
+	if (msg->header == (SOF_IPC_GLB_PM_MSG | SOF_IPC_PM_GATE)) {
+		pm_gate = msg->msg_data;
+
+		/* send the compact message via the primary register */
+		*dr = HDA_IPC_MSG_COMPACT | HDA_IPC_PM_GATE;
+
+		/* send payload via the extended data register */
+		*dd = pm_gate->flags;
+
+		return true;
+	}
+
+	return false;
+}
+
 static int cnl_ipc_send_msg(struct snd_sof_dev *sdev,
 			    struct snd_sof_ipc_msg *msg)
 {
-	/* send the message */
-	sof_mailbox_write(sdev, sdev->host_box.offset, msg->msg_data,
-			  msg->msg_size);
-	snd_sof_dsp_write(sdev, HDA_DSP_BAR, CNL_DSP_REG_HIPCIDR,
-			  CNL_DSP_REG_HIPCIDR_BUSY);
+	u32 dr = 0;
+	u32 dd = 0;
+
+	if (cnl_compact_ipc_compress(msg, &dr, &dd)) {
+		/* send the message via IPC registers */
+		snd_sof_dsp_write(sdev, HDA_DSP_BAR, CNL_DSP_REG_HIPCIDD,
+				  dd);
+		snd_sof_dsp_write(sdev, HDA_DSP_BAR, CNL_DSP_REG_HIPCIDR,
+				  CNL_DSP_REG_HIPCIDR_BUSY | dr);
+	} else {
+		/* send the message via mailbox */
+		sof_mailbox_write(sdev, sdev->host_box.offset, msg->msg_data,
+				  msg->msg_size);
+		snd_sof_dsp_write(sdev, HDA_DSP_BAR, CNL_DSP_REG_HIPCIDR,
+				  CNL_DSP_REG_HIPCIDR_BUSY);
+	}
 
 	return 0;
 }
@@ -255,6 +287,14 @@ const struct snd_sof_dsp_ops sof_cnl_ops = {
 	.runtime_resume		= hda_dsp_runtime_resume,
 	.runtime_idle		= hda_dsp_runtime_idle,
 	.set_hw_params_upon_resume = hda_dsp_set_hw_params_upon_resume,
+	.set_power_state	= hda_dsp_set_power_state,
+
+	/* ALSA HW info flags */
+	.hw_info =	SNDRV_PCM_INFO_MMAP |
+			SNDRV_PCM_INFO_MMAP_VALID |
+			SNDRV_PCM_INFO_INTERLEAVED |
+			SNDRV_PCM_INFO_PAUSE |
+			SNDRV_PCM_INFO_NO_PERIOD_WAKEUP,
 };
 EXPORT_SYMBOL(sof_cnl_ops);
 
@@ -327,3 +367,20 @@ const struct sof_intel_dsp_desc ehl_chip_info = {
 	.ssp_base_offset = CNL_SSP_BASE_OFFSET,
 };
 EXPORT_SYMBOL(ehl_chip_info);
+
+const struct sof_intel_dsp_desc jsl_chip_info = {
+	/* Jasperlake */
+	.cores_num = 2,
+	.init_core_mask = 1,
+	.cores_mask = HDA_DSP_CORE_MASK(0) |
+				HDA_DSP_CORE_MASK(1),
+	.ipc_req = CNL_DSP_REG_HIPCIDR,
+	.ipc_req_mask = CNL_DSP_REG_HIPCIDR_BUSY,
+	.ipc_ack = CNL_DSP_REG_HIPCIDA,
+	.ipc_ack_mask = CNL_DSP_REG_HIPCIDA_DONE,
+	.ipc_ctl = CNL_DSP_REG_HIPCCTL,
+	.rom_init_timeout	= 300,
+	.ssp_count = ICL_SSP_COUNT,
+	.ssp_base_offset = CNL_SSP_BASE_OFFSET,
+};
+EXPORT_SYMBOL(jsl_chip_info);
diff --git a/sound/soc/sof/intel/hda-codec.c b/sound/soc/sof/intel/hda-codec.c
index 3ca6795a89ba..827f84a0722e 100644
--- a/sound/soc/sof/intel/hda-codec.c
+++ b/sound/soc/sof/intel/hda-codec.c
@@ -84,6 +84,8 @@ static int hda_codec_probe(struct snd_sof_dev *sdev, int address)
 {
 #if IS_ENABLED(CONFIG_SND_SOC_SOF_HDA_AUDIO_CODEC)
 	struct hdac_hda_priv *hda_priv;
+	struct snd_soc_acpi_mach_params *mach_params = NULL;
+	struct snd_sof_pdata *pdata = sdev->pdata;
 #endif
 	struct hda_bus *hbus = sof_to_hbus(sdev);
 	struct hdac_device *hdev;
@@ -113,8 +115,19 @@ static int hda_codec_probe(struct snd_sof_dev *sdev, int address)
 	if (ret < 0)
 		return ret;
 
-	/* use legacy bus only for HDA codecs, idisp uses ext bus */
-	if ((resp & 0xFFFF0000) != IDISP_VID_INTEL) {
+	if (pdata->machine)
+		mach_params = (struct snd_soc_acpi_mach_params *)
+			&pdata->machine->mach_params;
+
+	if ((resp & 0xFFFF0000) == IDISP_VID_INTEL)
+		hda_priv->need_display_power = true;
+
+	/*
+	 * if common HDMI codec driver is not used, codec load
+	 * is skipped here and hdac_hdmi is used instead
+	 */
+	if ((mach_params && mach_params->common_hdmi_codec_drv) ||
+	    (resp & 0xFFFF0000) != IDISP_VID_INTEL) {
 		hdev->type = HDA_DEV_LEGACY;
 		hda_codec_load_module(&hda_priv->codec);
 	}
@@ -155,7 +168,8 @@ int hda_codec_probe_bus(struct snd_sof_dev *sdev)
 }
 EXPORT_SYMBOL(hda_codec_probe_bus);
 
-#if IS_ENABLED(CONFIG_SND_SOC_HDAC_HDMI)
+#if IS_ENABLED(CONFIG_SND_HDA_CODEC_HDMI) || \
+	IS_ENABLED(CONFIG_SND_SOC_HDAC_HDMI)
 
 void hda_codec_i915_get(struct snd_sof_dev *sdev)
 {
@@ -204,6 +218,6 @@ int hda_codec_i915_exit(struct snd_sof_dev *sdev)
 }
 EXPORT_SYMBOL(hda_codec_i915_exit);
 
-#endif /* CONFIG_SND_SOC_HDAC_HDMI */
+#endif
 
 MODULE_LICENSE("Dual BSD/GPL");
diff --git a/sound/soc/sof/intel/hda-dsp.c b/sound/soc/sof/intel/hda-dsp.c
index fb55a3c5afd0..4a4d318f97ff 100644
--- a/sound/soc/sof/intel/hda-dsp.c
+++ b/sound/soc/sof/intel/hda-dsp.c
@@ -19,6 +19,7 @@
 #include <sound/hda_register.h>
 #include "../ops.h"
 #include "hda.h"
+#include "hda-ipc.h"
 
 /*
  * DSP Core control.
@@ -42,6 +43,12 @@ int hda_dsp_core_reset_enter(struct snd_sof_dev *sdev, unsigned int core_mask)
 					((adspcs & reset) == reset),
 					HDA_DSP_REG_POLL_INTERVAL_US,
 					HDA_DSP_RESET_TIMEOUT_US);
+	if (ret < 0) {
+		dev_err(sdev->dev,
+			"error: %s: timeout on HDA_DSP_REG_ADSPCS read\n",
+			__func__);
+		return ret;
+	}
 
 	/* has core entered reset ? */
 	adspcs = snd_sof_dsp_read(sdev, HDA_DSP_BAR,
@@ -77,6 +84,13 @@ int hda_dsp_core_reset_leave(struct snd_sof_dev *sdev, unsigned int core_mask)
 					    HDA_DSP_REG_POLL_INTERVAL_US,
 					    HDA_DSP_RESET_TIMEOUT_US);
 
+	if (ret < 0) {
+		dev_err(sdev->dev,
+			"error: %s: timeout on HDA_DSP_REG_ADSPCS read\n",
+			__func__);
+		return ret;
+	}
+
 	/* has core left reset ? */
 	adspcs = snd_sof_dsp_read(sdev, HDA_DSP_BAR,
 				  HDA_DSP_REG_ADSPCS);
@@ -151,8 +165,12 @@ int hda_dsp_core_power_up(struct snd_sof_dev *sdev, unsigned int core_mask)
 					    (adspcs & cpa) == cpa,
 					    HDA_DSP_REG_POLL_INTERVAL_US,
 					    HDA_DSP_RESET_TIMEOUT_US);
-	if (ret < 0)
-		dev_err(sdev->dev, "error: timeout on core powerup\n");
+	if (ret < 0) {
+		dev_err(sdev->dev,
+			"error: %s: timeout on HDA_DSP_REG_ADSPCS read\n",
+			__func__);
+		return ret;
+	}
 
 	/* did core power up ? */
 	adspcs = snd_sof_dsp_read(sdev, HDA_DSP_BAR,
@@ -171,17 +189,24 @@ int hda_dsp_core_power_up(struct snd_sof_dev *sdev, unsigned int core_mask)
 int hda_dsp_core_power_down(struct snd_sof_dev *sdev, unsigned int core_mask)
 {
 	u32 adspcs;
+	int ret;
 
 	/* update bits */
 	snd_sof_dsp_update_bits_unlocked(sdev, HDA_DSP_BAR,
 					 HDA_DSP_REG_ADSPCS,
 					 HDA_DSP_ADSPCS_SPA_MASK(core_mask), 0);
 
-	return snd_sof_dsp_read_poll_timeout(sdev, HDA_DSP_BAR,
+	ret = snd_sof_dsp_read_poll_timeout(sdev, HDA_DSP_BAR,
 				HDA_DSP_REG_ADSPCS, adspcs,
 				!(adspcs & HDA_DSP_ADSPCS_SPA_MASK(core_mask)),
 				HDA_DSP_REG_POLL_INTERVAL_US,
 				HDA_DSP_PD_TIMEOUT * USEC_PER_MSEC);
+	if (ret < 0)
+		dev_err(sdev->dev,
+			"error: %s: timeout on HDA_DSP_REG_ADSPCS read\n",
+			__func__);
+
+	return ret;
 }
 
 bool hda_dsp_core_is_enabled(struct snd_sof_dev *sdev,
@@ -282,6 +307,80 @@ void hda_dsp_ipc_int_disable(struct snd_sof_dev *sdev)
 			HDA_DSP_REG_HIPCCTL_BUSY | HDA_DSP_REG_HIPCCTL_DONE, 0);
 }
 
+static int hda_dsp_wait_d0i3c_done(struct snd_sof_dev *sdev)
+{
+	struct hdac_bus *bus = sof_to_bus(sdev);
+	int retry = HDA_DSP_REG_POLL_RETRY_COUNT;
+
+	while (snd_hdac_chip_readb(bus, VS_D0I3C) & SOF_HDA_VS_D0I3C_CIP) {
+		if (!retry--)
+			return -ETIMEDOUT;
+		usleep_range(10, 15);
+	}
+
+	return 0;
+}
+
+static int hda_dsp_send_pm_gate_ipc(struct snd_sof_dev *sdev, u32 flags)
+{
+	struct sof_ipc_pm_gate pm_gate;
+	struct sof_ipc_reply reply;
+
+	memset(&pm_gate, 0, sizeof(pm_gate));
+
+	/* configure pm_gate ipc message */
+	pm_gate.hdr.size = sizeof(pm_gate);
+	pm_gate.hdr.cmd = SOF_IPC_GLB_PM_MSG | SOF_IPC_PM_GATE;
+	pm_gate.flags = flags;
+
+	/* send pm_gate ipc to dsp */
+	return sof_ipc_tx_message(sdev->ipc, pm_gate.hdr.cmd, &pm_gate,
+				  sizeof(pm_gate), &reply, sizeof(reply));
+}
+
+int hda_dsp_set_power_state(struct snd_sof_dev *sdev,
+			    enum sof_d0_substate d0_substate)
+{
+	struct hdac_bus *bus = sof_to_bus(sdev);
+	u32 flags;
+	int ret;
+	u8 value;
+
+	/* Write to D0I3C after Command-In-Progress bit is cleared */
+	ret = hda_dsp_wait_d0i3c_done(sdev);
+	if (ret < 0) {
+		dev_err(bus->dev, "CIP timeout before D0I3C update!\n");
+		return ret;
+	}
+
+	/* Update D0I3C register */
+	value = d0_substate == SOF_DSP_D0I3 ? SOF_HDA_VS_D0I3C_I3 : 0;
+	snd_hdac_chip_updateb(bus, VS_D0I3C, SOF_HDA_VS_D0I3C_I3, value);
+
+	/* Wait for cmd in progress to be cleared before exiting the function */
+	ret = hda_dsp_wait_d0i3c_done(sdev);
+	if (ret < 0) {
+		dev_err(bus->dev, "CIP timeout after D0I3C update!\n");
+		return ret;
+	}
+
+	dev_vdbg(bus->dev, "D0I3C updated, register = 0x%x\n",
+		 snd_hdac_chip_readb(bus, VS_D0I3C));
+
+	if (d0_substate == SOF_DSP_D0I0)
+		flags = HDA_PM_PPG;/* prevent power gating in D0 */
+	else
+		flags = HDA_PM_NO_DMA_TRACE;/* disable DMA trace in D0I3*/
+
+	/* sending pm_gate IPC */
+	ret = hda_dsp_send_pm_gate_ipc(sdev, flags);
+	if (ret < 0)
+		dev_err(sdev->dev,
+			"error: PM_GATE ipc error %d\n", ret);
+
+	return ret;
+}
+
 static int hda_suspend(struct snd_sof_dev *sdev, bool runtime_suspend)
 {
 	struct sof_intel_hda_dev *hda = sdev->pdata->hw_pdata;
@@ -379,6 +478,22 @@ static int hda_resume(struct snd_sof_dev *sdev, bool runtime_resume)
 
 int hda_dsp_resume(struct snd_sof_dev *sdev)
 {
+	struct sof_intel_hda_dev *hda = sdev->pdata->hw_pdata;
+	struct pci_dev *pci = to_pci_dev(sdev->dev);
+
+	if (sdev->s0_suspend) {
+		/* restore L1SEN bit */
+		if (hda->l1_support_changed)
+			snd_sof_dsp_update_bits(sdev, HDA_DSP_HDA_BAR,
+						HDA_VS_INTEL_EM2,
+						HDA_VS_INTEL_EM2_L1SEN, 0);
+
+		/* restore and disable the system wakeup */
+		pci_restore_state(pci);
+		disable_irq_wake(pci->irq);
+		return 0;
+	}
+
 	/* init hda controller. DSP cores will be powered up during fw boot */
 	return hda_resume(sdev, false);
 }
@@ -410,9 +525,25 @@ int hda_dsp_runtime_suspend(struct snd_sof_dev *sdev)
 
 int hda_dsp_suspend(struct snd_sof_dev *sdev)
 {
+	struct sof_intel_hda_dev *hda = sdev->pdata->hw_pdata;
 	struct hdac_bus *bus = sof_to_bus(sdev);
+	struct pci_dev *pci = to_pci_dev(sdev->dev);
 	int ret;
 
+	if (sdev->s0_suspend) {
+		/* enable L1SEN to make sure the system can enter S0Ix */
+		hda->l1_support_changed =
+			snd_sof_dsp_update_bits(sdev, HDA_DSP_HDA_BAR,
+						HDA_VS_INTEL_EM2,
+						HDA_VS_INTEL_EM2_L1SEN,
+						HDA_VS_INTEL_EM2_L1SEN);
+
+		/* enable the system waking up via IPC IRQ */
+		enable_irq_wake(pci->irq);
+		pci_save_state(pci);
+		return 0;
+	}
+
 	/* stop hda controller and power dsp off */
 	ret = hda_suspend(sdev, false);
 	if (ret < 0) {
diff --git a/sound/soc/sof/intel/hda-ipc.c b/sound/soc/sof/intel/hda-ipc.c
index 6aae6f18b3dc..0fd2153c1769 100644
--- a/sound/soc/sof/intel/hda-ipc.c
+++ b/sound/soc/sof/intel/hda-ipc.c
@@ -83,10 +83,12 @@ void hda_dsp_ipc_get_reply(struct snd_sof_dev *sdev)
 	}
 
 	hdr = msg->msg_data;
-	if (hdr->cmd == (SOF_IPC_GLB_PM_MSG | SOF_IPC_PM_CTX_SAVE)) {
+	if (hdr->cmd == (SOF_IPC_GLB_PM_MSG | SOF_IPC_PM_CTX_SAVE) ||
+	    hdr->cmd == (SOF_IPC_GLB_PM_MSG | SOF_IPC_PM_GATE)) {
 		/*
 		 * memory windows are powered off before sending IPC reply,
-		 * so we can't read the mailbox for CTX_SAVE reply.
+		 * so we can't read the mailbox for CTX_SAVE and PM_GATE
+		 * replies.
 		 */
 		reply.error = 0;
 		reply.hdr.cmd = SOF_IPC_GLB_REPLY;
diff --git a/sound/soc/sof/intel/hda-ipc.h b/sound/soc/sof/intel/hda-ipc.h
new file mode 100644
index 000000000000..aef0ceac9803
--- /dev/null
+++ b/sound/soc/sof/intel/hda-ipc.h
@@ -0,0 +1,51 @@
+/* SPDX-License-Identifier: (GPL-2.0 OR BSD-3-Clause) */
+/*
+ * This file is provided under a dual BSD/GPLv2 license.  When using or
+ * redistributing this file, you may do so under either license.
+ *
+ * Copyright(c) 2019 Intel Corporation. All rights reserved.
+ *
+ * Author: Keyon Jie <yang.jie@linux.intel.com>
+ */
+
+#ifndef __SOF_INTEL_HDA_IPC_H
+#define __SOF_INTEL_HDA_IPC_H
+
+/*
+ * Primary register, mapped to
+ * - DIPCTDR (HIPCIDR) in sideband IPC (cAVS 1.8+)
+ * - DIPCT in cAVS 1.5 IPC
+ *
+ * Secondary register, mapped to:
+ * - DIPCTDD (HIPCIDD) in sideband IPC (cAVS 1.8+)
+ * - DIPCTE in cAVS 1.5 IPC
+ */
+
+/* Common bits in primary register */
+
+/* Reserved for doorbell */
+#define HDA_IPC_RSVD_31		BIT(31)
+/* Target, 0 - normal message, 1 - compact message(cAVS compatible) */
+#define HDA_IPC_MSG_COMPACT	BIT(30)
+/* Direction, 0 - request, 1 - response */
+#define HDA_IPC_RSP		BIT(29)
+
+#define HDA_IPC_TYPE_SHIFT	24
+#define HDA_IPC_TYPE_MASK	GENMASK(28, 24)
+#define HDA_IPC_TYPE(x)		((x) << HDA_IPC_TYPE_SHIFT)
+
+#define HDA_IPC_PM_GATE		HDA_IPC_TYPE(0x8U)
+
+/* Command specific payload bits in secondary register */
+
+/* Disable DMA tracing (0 - keep tracing, 1 - to disable DMA trace) */
+#define HDA_PM_NO_DMA_TRACE	BIT(4)
+/* Prevent clock gating (0 - cg allowed, 1 - DSP clock always on) */
+#define HDA_PM_PCG		BIT(3)
+/* Prevent power gating (0 - deep power state transitions allowed) */
+#define HDA_PM_PPG		BIT(2)
+/* Indicates whether streaming is active */
+#define HDA_PM_PG_STREAMING	BIT(1)
+#define HDA_PM_PG_RSVD		BIT(0)
+
+#endif
diff --git a/sound/soc/sof/intel/hda-loader.c b/sound/soc/sof/intel/hda-loader.c
index 65c2af3fcaab..b1783360fe10 100644
--- a/sound/soc/sof/intel/hda-loader.c
+++ b/sound/soc/sof/intel/hda-loader.c
@@ -126,7 +126,8 @@ static int cl_dsp_init(struct snd_sof_dev *sdev, const void *fwdata,
 					    HDA_DSP_INIT_TIMEOUT_US);
 
 	if (ret < 0) {
-		dev_err(sdev->dev, "error: waiting for HIPCIE done\n");
+		dev_err(sdev->dev, "error: %s: timeout for HIPCIE done\n",
+			__func__);
 		goto err;
 	}
 
@@ -152,6 +153,10 @@ static int cl_dsp_init(struct snd_sof_dev *sdev, const void *fwdata,
 	if (!ret)
 		return 0;
 
+	dev_err(sdev->dev,
+		"error: %s: timeout HDA_DSP_SRAM_REG_ROM_STATUS read\n",
+		__func__);
+
 err:
 	hda_dsp_dump(sdev, SOF_DBG_REGS | SOF_DBG_PCI | SOF_DBG_MBOX);
 	hda_dsp_core_reset_power_down(sdev, chip->cores_mask);
@@ -253,10 +258,22 @@ static int cl_copy_fw(struct snd_sof_dev *sdev, struct hdac_ext_stream *stream)
 					HDA_DSP_REG_POLL_INTERVAL_US,
 					HDA_DSP_BASEFW_TIMEOUT_US);
 
+	/*
+	 * even in case of errors we still need to stop the DMAs,
+	 * but we return the initial error should the DMA stop also fail
+	 */
+
+	if (status < 0) {
+		dev_err(sdev->dev,
+			"error: %s: timeout HDA_DSP_SRAM_REG_ROM_STATUS read\n",
+			__func__);
+	}
+
 	ret = cl_trigger(sdev, stream, SNDRV_PCM_TRIGGER_STOP);
 	if (ret < 0) {
 		dev_err(sdev->dev, "error: DMA trigger stop failed\n");
-		return ret;
+		if (!status)
+			status = ret;
 	}
 
 	return status;
@@ -341,13 +358,15 @@ cleanup:
 	/*
 	 * Perform codeloader stream cleanup.
 	 * This should be done even if firmware loading fails.
+	 * If the cleanup also fails, we return the initial error
 	 */
 	ret1 = cl_cleanup(sdev, &sdev->dmab, stream);
 	if (ret1 < 0) {
 		dev_err(sdev->dev, "error: Code loader DSP cleanup failed\n");
 
 		/* set return value to indicate cleanup failure */
-		ret = ret1;
+		if (!ret)
+			ret = ret1;
 	}
 
 	/*
diff --git a/sound/soc/sof/intel/hda-pcm.c b/sound/soc/sof/intel/hda-pcm.c
index 9b730f183529..575f5f5877d8 100644
--- a/sound/soc/sof/intel/hda-pcm.c
+++ b/sound/soc/sof/intel/hda-pcm.c
@@ -89,6 +89,7 @@ int hda_dsp_pcm_hw_params(struct snd_sof_dev *sdev,
 	struct hdac_ext_stream *stream = stream_to_hdac_ext_stream(hstream);
 	struct sof_intel_hda_dev *hda = sdev->pdata->hw_pdata;
 	struct snd_dma_buffer *dmab;
+	struct sof_ipc_fw_version *v = &sdev->fw_ready.version;
 	int ret;
 	u32 size, rate, bits;
 
@@ -116,9 +117,17 @@ int hda_dsp_pcm_hw_params(struct snd_sof_dev *sdev,
 	/* disable SPIB, to enable buffer wrap for stream */
 	hda_dsp_stream_spib_config(sdev, stream, HDA_DSP_SPIB_DISABLE, 0);
 
-	/* set host_period_bytes to 0 if no IPC position */
-	if (hda && hda->no_ipc_position)
-		ipc_params->host_period_bytes = 0;
+	/* update no_stream_position flag for ipc params */
+	if (hda && hda->no_ipc_position) {
+		/* For older ABIs set host_period_bytes to zero to inform
+		 * FW we don't want position updates. Newer versions use
+		 * no_stream_position for this purpose.
+		 */
+		if (v->abi_version < SOF_ABI_VER(3, 10, 0))
+			ipc_params->host_period_bytes = 0;
+		else
+			ipc_params->no_stream_position = 1;
+	}
 
 	ipc_params->stream_tag = hstream->stream_tag;
 
diff --git a/sound/soc/sof/intel/hda-stream.c b/sound/soc/sof/intel/hda-stream.c
index 0c11fceb28a7..29ab43281670 100644
--- a/sound/soc/sof/intel/hda-stream.c
+++ b/sound/soc/sof/intel/hda-stream.c
@@ -275,8 +275,12 @@ int hda_dsp_stream_trigger(struct snd_sof_dev *sdev,
 					HDA_DSP_REG_POLL_INTERVAL_US,
 					HDA_DSP_STREAM_RUN_TIMEOUT);
 
-		if (ret)
+		if (ret < 0) {
+			dev_err(sdev->dev,
+				"error: %s: cmd %d: timeout on STREAM_SD_OFFSET read\n",
+				__func__, cmd);
 			return ret;
+		}
 
 		hstream->running = true;
 		break;
@@ -294,8 +298,12 @@ int hda_dsp_stream_trigger(struct snd_sof_dev *sdev,
 						HDA_DSP_REG_POLL_INTERVAL_US,
 						HDA_DSP_STREAM_RUN_TIMEOUT);
 
-		if (ret)
+		if (ret < 0) {
+			dev_err(sdev->dev,
+				"error: %s: cmd %d: timeout on STREAM_SD_OFFSET read\n",
+				__func__, cmd);
 			return ret;
+		}
 
 		snd_sof_dsp_write(sdev, HDA_DSP_HDA_BAR, sd_offset +
 				  SOF_HDA_ADSP_REG_CL_SD_STS,
@@ -356,8 +364,12 @@ int hda_dsp_stream_hw_params(struct snd_sof_dev *sdev,
 					    HDA_DSP_REG_POLL_INTERVAL_US,
 					    HDA_DSP_STREAM_RUN_TIMEOUT);
 
-	if (ret)
+	if (ret < 0) {
+		dev_err(sdev->dev,
+			"error: %s: timeout on STREAM_SD_OFFSET read1\n",
+			__func__);
 		return ret;
+	}
 
 	snd_sof_dsp_update_bits(sdev, HDA_DSP_HDA_BAR,
 				sd_offset + SOF_HDA_ADSP_REG_CL_SD_STS,
@@ -418,8 +430,12 @@ int hda_dsp_stream_hw_params(struct snd_sof_dev *sdev,
 					    HDA_DSP_REG_POLL_INTERVAL_US,
 					    HDA_DSP_STREAM_RUN_TIMEOUT);
 
-	if (ret)
+	if (ret < 0) {
+		dev_err(sdev->dev,
+			"error: %s: timeout on STREAM_SD_OFFSET read2\n",
+			__func__);
 		return ret;
+	}
 
 	snd_sof_dsp_update_bits(sdev, HDA_DSP_HDA_BAR,
 				sd_offset + SOF_HDA_ADSP_REG_CL_SD_STS,
diff --git a/sound/soc/sof/intel/hda.c b/sound/soc/sof/intel/hda.c
index 06e84679087b..91bd88fddac7 100644
--- a/sound/soc/sof/intel/hda.c
+++ b/sound/soc/sof/intel/hda.c
@@ -32,9 +32,6 @@
 /* platform specific devices */
 #include "shim.h"
 
-#define IS_CFL(pci) ((pci)->vendor == 0x8086 && (pci)->device == 0xa348)
-#define IS_CNL(pci) ((pci)->vendor == 0x8086 && (pci)->device == 0x9dc8)
-
 #define EXCEPT_MAX_HDR_SIZE	0x400
 
 /*
@@ -56,6 +53,11 @@ MODULE_PARM_DESC(use_msi, "SOF HDA use PCI MSI mode");
 static int hda_dmic_num = -1;
 module_param_named(dmic_num, hda_dmic_num, int, 0444);
 MODULE_PARM_DESC(dmic_num, "SOF HDA DMIC number");
+
+static bool hda_codec_use_common_hdmi =
+	IS_ENABLED(CONFIG_SND_SOC_SOF_HDA_COMMON_HDMI_CODEC);
+module_param_named(use_common_hdmi, hda_codec_use_common_hdmi, bool, 0444);
+MODULE_PARM_DESC(use_common_hdmi, "SOF HDA use common HDMI codec driver");
 #endif
 
 static const struct hda_dsp_msg_code hda_dsp_rom_msg[] = {
@@ -262,12 +264,9 @@ static int hda_init(struct snd_sof_dev *sdev)
 	/* HDA bus init */
 	sof_hda_bus_init(bus, &pci->dev);
 
-	/* Workaround for a communication error on CFL (bko#199007) and CNL */
-	if (IS_CFL(pci) || IS_CNL(pci))
-		bus->polling_mode = 1;
-
 	bus->use_posbuf = 1;
 	bus->bdl_pos_adj = 0;
+	bus->sync_write = 1;
 
 	mutex_init(&hbus->prepare_mutex);
 	hbus->pci = pci;
@@ -416,9 +415,16 @@ static int hda_init_caps(struct snd_sof_dev *sdev)
 			pdata->tplg_filename =
 				hda_mach->sof_tplg_filename;
 
-			/* firmware: pick the first in machine list */
+			/*
+			 * firmware: pick the first in machine list,
+			 * or use nocodec firmware name if list is empty
+			 */
 			mach = pdata->desc->machines;
-			pdata->fw_filename = mach->sof_fw_filename;
+			if (mach->id[0])
+				pdata->fw_filename = mach->sof_fw_filename;
+			else
+				pdata->fw_filename =
+					pdata->desc->nocodec_fw_filename;
 
 			dev_info(bus->dev, "using HDA machine driver %s now\n",
 				 hda_mach->drv_name);
@@ -465,6 +471,7 @@ static int hda_init_caps(struct snd_sof_dev *sdev)
 			&pdata->machine->mach_params;
 		mach_params->codec_mask = bus->codec_mask;
 		mach_params->platform = dev_name(sdev->dev);
+		mach_params->common_hdmi_codec_drv = hda_codec_use_common_hdmi;
 	}
 
 	/* create codec instances */
diff --git a/sound/soc/sof/intel/hda.h b/sound/soc/sof/intel/hda.h
index 23e430d3e056..18d7e72bf9b7 100644
--- a/sound/soc/sof/intel/hda.h
+++ b/sound/soc/sof/intel/hda.h
@@ -64,6 +64,13 @@
 #define SOF_HDA_PPCTL_PIE		BIT(31)
 #define SOF_HDA_PPCTL_GPROCEN		BIT(30)
 
+/*Vendor Specific Registers*/
+#define SOF_HDA_VS_D0I3C		0x104A
+
+/* D0I3C Register fields */
+#define SOF_HDA_VS_D0I3C_CIP		BIT(0) /* Command-In-Progress */
+#define SOF_HDA_VS_D0I3C_I3		BIT(2) /* D0i3 enable bit */
+
 /* DPIB entry size: 8 Bytes = 2 DWords */
 #define SOF_HDA_DPIB_ENTRY_SIZE	0x8
 
@@ -207,6 +214,7 @@
 #define HDA_DSP_CTRL_RESET_TIMEOUT		100
 #define HDA_DSP_WAIT_TIMEOUT		500	/* 500 msec */
 #define HDA_DSP_REG_POLL_INTERVAL_US		500	/* 0.5 msec */
+#define HDA_DSP_REG_POLL_RETRY_COUNT		50
 
 #define HDA_DSP_ADSPIC_IPC			1
 #define HDA_DSP_ADSPIS_IPC			1
@@ -304,6 +312,7 @@
 #define CNL_DSP_REG_HIPCTDD		(CNL_DSP_IPC_BASE + 0x08)
 #define CNL_DSP_REG_HIPCIDR		(CNL_DSP_IPC_BASE + 0x10)
 #define CNL_DSP_REG_HIPCIDA		(CNL_DSP_IPC_BASE + 0x14)
+#define CNL_DSP_REG_HIPCIDD		(CNL_DSP_IPC_BASE + 0x18)
 #define CNL_DSP_REG_HIPCCTL		(CNL_DSP_IPC_BASE + 0x28)
 
 /*  HIPCI */
@@ -399,6 +408,9 @@ struct sof_intel_hda_dev {
 
 	int irq;
 
+	/* PM related */
+	bool l1_support_changed;/* during suspend, is L1SEN changed or not */
+
 	/* DMIC device */
 	struct platform_device *dmic_dev;
 };
@@ -455,6 +467,9 @@ int hda_dsp_core_reset_power_down(struct snd_sof_dev *sdev,
 void hda_dsp_ipc_int_enable(struct snd_sof_dev *sdev);
 void hda_dsp_ipc_int_disable(struct snd_sof_dev *sdev);
 
+int hda_dsp_set_power_state(struct snd_sof_dev *sdev,
+			    enum sof_d0_substate d0_substate);
+
 int hda_dsp_suspend(struct snd_sof_dev *sdev);
 int hda_dsp_resume(struct snd_sof_dev *sdev);
 int hda_dsp_runtime_suspend(struct snd_sof_dev *sdev);
@@ -565,7 +580,9 @@ void hda_codec_jack_check(struct snd_sof_dev *sdev);
 
 #endif /* CONFIG_SND_SOC_SOF_HDA */
 
-#if IS_ENABLED(CONFIG_SND_SOC_SOF_HDA) && IS_ENABLED(CONFIG_SND_SOC_HDAC_HDMI)
+#if IS_ENABLED(CONFIG_SND_SOC_SOF_HDA) && \
+	(IS_ENABLED(CONFIG_SND_HDA_CODEC_HDMI) || \
+	 IS_ENABLED(CONFIG_SND_SOC_HDAC_HDMI))
 
 void hda_codec_i915_get(struct snd_sof_dev *sdev);
 void hda_codec_i915_put(struct snd_sof_dev *sdev);
@@ -579,7 +596,7 @@ static inline void hda_codec_i915_put(struct snd_sof_dev *sdev)  { }
 static inline int hda_codec_i915_init(struct snd_sof_dev *sdev) { return 0; }
 static inline int hda_codec_i915_exit(struct snd_sof_dev *sdev) { return 0; }
 
-#endif /* CONFIG_SND_SOC_SOF_HDA && CONFIG_SND_SOC_HDAC_HDMI */
+#endif
 
 /*
  * Trace Control.
@@ -596,7 +613,6 @@ extern struct snd_soc_dai_driver skl_dai[];
  */
 extern const struct snd_sof_dsp_ops sof_apl_ops;
 extern const struct snd_sof_dsp_ops sof_cnl_ops;
-extern const struct snd_sof_dsp_ops sof_skl_ops;
 
 extern const struct sof_intel_dsp_desc apl_chip_info;
 extern const struct sof_intel_dsp_desc cnl_chip_info;
@@ -604,5 +620,6 @@ extern const struct sof_intel_dsp_desc skl_chip_info;
 extern const struct sof_intel_dsp_desc icl_chip_info;
 extern const struct sof_intel_dsp_desc tgl_chip_info;
 extern const struct sof_intel_dsp_desc ehl_chip_info;
+extern const struct sof_intel_dsp_desc jsl_chip_info;
 
 #endif
diff --git a/sound/soc/sof/ipc.c b/sound/soc/sof/ipc.c
index 086eeeab8679..5994e1073364 100644
--- a/sound/soc/sof/ipc.c
+++ b/sound/soc/sof/ipc.c
@@ -210,9 +210,7 @@ static int tx_wait_done(struct snd_sof_ipc *ipc, struct snd_sof_ipc_msg *msg,
 	if (ret == 0) {
 		dev_err(sdev->dev, "error: ipc timed out for 0x%x size %d\n",
 			hdr->cmd, hdr->size);
-		snd_sof_dsp_dbg_dump(ipc->sdev, SOF_DBG_REGS | SOF_DBG_MBOX);
-		snd_sof_ipc_dump(ipc->sdev);
-		snd_sof_trace_notify_for_error(ipc->sdev);
+		snd_sof_handle_fw_exception(ipc->sdev);
 		ret = -ETIMEDOUT;
 	} else {
 		/* copy the data returned from DSP */
@@ -796,12 +794,6 @@ struct snd_sof_ipc *snd_sof_ipc_init(struct snd_sof_dev *sdev)
 	struct snd_sof_ipc *ipc;
 	struct snd_sof_ipc_msg *msg;
 
-	/* check if mandatory ops required for ipc are defined */
-	if (!sof_ops(sdev)->fw_ready) {
-		dev_err(sdev->dev, "error: ipc mandatory ops not defined\n");
-		return NULL;
-	}
-
 	ipc = devm_kzalloc(sdev->dev, sizeof(*ipc), GFP_KERNEL);
 	if (!ipc)
 		return NULL;
diff --git a/sound/soc/sof/ops.h b/sound/soc/sof/ops.h
index 824d36fe59fd..93512dcbaacd 100644
--- a/sound/soc/sof/ops.h
+++ b/sound/soc/sof/ops.h
@@ -193,6 +193,16 @@ static inline int snd_sof_dsp_set_clk(struct snd_sof_dev *sdev, u32 freq)
 	return 0;
 }
 
+static inline int snd_sof_dsp_set_power_state(struct snd_sof_dev *sdev,
+					      enum sof_d0_substate substate)
+{
+	if (sof_ops(sdev)->set_power_state)
+		return sof_ops(sdev)->set_power_state(sdev, substate);
+
+	/* D0 substate is not supported */
+	return -ENOTSUPP;
+}
+
 /* debug */
 static inline void snd_sof_dsp_dbg_dump(struct snd_sof_dev *sdev, u32 flags)
 {
diff --git a/sound/soc/sof/pcm.c b/sound/soc/sof/pcm.c
index 2b876d497447..549238a98b2a 100644
--- a/sound/soc/sof/pcm.c
+++ b/sound/soc/sof/pcm.c
@@ -19,12 +19,11 @@
 #define DRV_NAME	"sof-audio-component"
 
 /* Create DMA buffer page table for DSP */
-static int create_page_table(struct snd_pcm_substream *substream,
+static int create_page_table(struct snd_soc_component *component,
+			     struct snd_pcm_substream *substream,
 			     unsigned char *dma_area, size_t size)
 {
 	struct snd_soc_pcm_runtime *rtd = substream->private_data;
-	struct snd_soc_component *component =
-		snd_soc_rtdcom_lookup(rtd, DRV_NAME);
 	struct snd_sof_dev *sdev = snd_soc_component_get_drvdata(component);
 	struct snd_sof_pcm *spcm;
 	struct snd_dma_buffer *dmab = snd_pcm_get_dma_buf(substream);
@@ -95,13 +94,12 @@ void snd_sof_pcm_period_elapsed(struct snd_pcm_substream *substream)
 EXPORT_SYMBOL(snd_sof_pcm_period_elapsed);
 
 /* this may get called several times by oss emulation */
-static int sof_pcm_hw_params(struct snd_pcm_substream *substream,
+static int sof_pcm_hw_params(struct snd_soc_component *component,
+			     struct snd_pcm_substream *substream,
 			     struct snd_pcm_hw_params *params)
 {
 	struct snd_soc_pcm_runtime *rtd = substream->private_data;
 	struct snd_pcm_runtime *runtime = substream->runtime;
-	struct snd_soc_component *component =
-		snd_soc_rtdcom_lookup(rtd, DRV_NAME);
 	struct snd_sof_dev *sdev = snd_soc_component_get_drvdata(component);
 	struct snd_sof_pcm *spcm;
 	struct sof_ipc_pcm_params pcm;
@@ -135,7 +133,7 @@ static int sof_pcm_hw_params(struct snd_pcm_substream *substream,
 		 * ret == 0 means the buffer is not changed
 		 * so no need to regenerate the page table
 		 */
-		ret = create_page_table(substream, runtime->dma_area,
+		ret = create_page_table(component, substream, runtime->dma_area,
 					runtime->dma_bytes);
 		if (ret < 0)
 			return ret;
@@ -237,11 +235,10 @@ static int sof_pcm_dsp_pcm_free(struct snd_pcm_substream *substream,
 	return ret;
 }
 
-static int sof_pcm_hw_free(struct snd_pcm_substream *substream)
+static int sof_pcm_hw_free(struct snd_soc_component *component,
+			   struct snd_pcm_substream *substream)
 {
 	struct snd_soc_pcm_runtime *rtd = substream->private_data;
-	struct snd_soc_component *component =
-		snd_soc_rtdcom_lookup(rtd, DRV_NAME);
 	struct snd_sof_dev *sdev = snd_soc_component_get_drvdata(component);
 	struct snd_sof_pcm *spcm;
 	int ret, err = 0;
@@ -276,11 +273,10 @@ static int sof_pcm_hw_free(struct snd_pcm_substream *substream)
 	return err;
 }
 
-static int sof_pcm_prepare(struct snd_pcm_substream *substream)
+static int sof_pcm_prepare(struct snd_soc_component *component,
+			   struct snd_pcm_substream *substream)
 {
 	struct snd_soc_pcm_runtime *rtd = substream->private_data;
-	struct snd_soc_component *component =
-		snd_soc_rtdcom_lookup(rtd, DRV_NAME);
 	struct snd_sof_dev *sdev = snd_soc_component_get_drvdata(component);
 	struct snd_sof_pcm *spcm;
 	int ret;
@@ -300,7 +296,8 @@ static int sof_pcm_prepare(struct snd_pcm_substream *substream)
 		substream->stream);
 
 	/* set hw_params */
-	ret = sof_pcm_hw_params(substream, &spcm->params[substream->stream]);
+	ret = sof_pcm_hw_params(component,
+				substream, &spcm->params[substream->stream]);
 	if (ret < 0) {
 		dev_err(sdev->dev, "error: set pcm hw_params after resume\n");
 		return ret;
@@ -313,11 +310,10 @@ static int sof_pcm_prepare(struct snd_pcm_substream *substream)
  * FE dai link trigger actions are always executed in non-atomic context because
  * they involve IPC's.
  */
-static int sof_pcm_trigger(struct snd_pcm_substream *substream, int cmd)
+static int sof_pcm_trigger(struct snd_soc_component *component,
+			   struct snd_pcm_substream *substream, int cmd)
 {
 	struct snd_soc_pcm_runtime *rtd = substream->private_data;
-	struct snd_soc_component *component =
-		snd_soc_rtdcom_lookup(rtd, DRV_NAME);
 	struct snd_sof_dev *sdev = snd_soc_component_get_drvdata(component);
 	struct snd_sof_pcm *spcm;
 	struct sof_ipc_stream stream;
@@ -350,8 +346,18 @@ static int sof_pcm_trigger(struct snd_pcm_substream *substream, int cmd)
 		stream.hdr.cmd |= SOF_IPC_STREAM_TRIG_RELEASE;
 		break;
 	case SNDRV_PCM_TRIGGER_RESUME:
+		if (spcm->stream[substream->stream].suspend_ignored) {
+			/*
+			 * this case will be triggered when INFO_RESUME is
+			 * supported, no need to resume streams that remained
+			 * enabled in D0ix.
+			 */
+			spcm->stream[substream->stream].suspend_ignored = false;
+			return 0;
+		}
+
 		/* set up hw_params */
-		ret = sof_pcm_prepare(substream);
+		ret = sof_pcm_prepare(component, substream);
 		if (ret < 0) {
 			dev_err(sdev->dev,
 				"error: failed to set up hw_params upon resume\n");
@@ -360,9 +366,30 @@ static int sof_pcm_trigger(struct snd_pcm_substream *substream, int cmd)
 
 		/* fallthrough */
 	case SNDRV_PCM_TRIGGER_START:
+		if (spcm->stream[substream->stream].suspend_ignored) {
+			/*
+			 * This case will be triggered when INFO_RESUME is
+			 * not supported, no need to re-start streams that
+			 * remained enabled in D0ix.
+			 */
+			spcm->stream[substream->stream].suspend_ignored = false;
+			return 0;
+		}
 		stream.hdr.cmd |= SOF_IPC_STREAM_TRIG_START;
 		break;
 	case SNDRV_PCM_TRIGGER_SUSPEND:
+		if (sdev->s0_suspend &&
+		    spcm->stream[substream->stream].d0i3_compatible) {
+			/*
+			 * trap the event, not sending trigger stop to
+			 * prevent the FW pipelines from being stopped,
+			 * and mark the flag to ignore the upcoming DAPM
+			 * PM events.
+			 */
+			spcm->stream[substream->stream].suspend_ignored = true;
+			return 0;
+		}
+		/* fallthrough */
 	case SNDRV_PCM_TRIGGER_STOP:
 		stream.hdr.cmd |= SOF_IPC_STREAM_TRIG_STOP;
 		ipc_first = true;
@@ -395,11 +422,10 @@ static int sof_pcm_trigger(struct snd_pcm_substream *substream, int cmd)
 	return ret;
 }
 
-static snd_pcm_uframes_t sof_pcm_pointer(struct snd_pcm_substream *substream)
+static snd_pcm_uframes_t sof_pcm_pointer(struct snd_soc_component *component,
+					 struct snd_pcm_substream *substream)
 {
 	struct snd_soc_pcm_runtime *rtd = substream->private_data;
-	struct snd_soc_component *component =
-		snd_soc_rtdcom_lookup(rtd, DRV_NAME);
 	struct snd_sof_dev *sdev = snd_soc_component_get_drvdata(component);
 	struct snd_sof_pcm *spcm;
 	snd_pcm_uframes_t host, dai;
@@ -428,13 +454,13 @@ static snd_pcm_uframes_t sof_pcm_pointer(struct snd_pcm_substream *substream)
 	return host;
 }
 
-static int sof_pcm_open(struct snd_pcm_substream *substream)
+static int sof_pcm_open(struct snd_soc_component *component,
+			struct snd_pcm_substream *substream)
 {
 	struct snd_soc_pcm_runtime *rtd = substream->private_data;
 	struct snd_pcm_runtime *runtime = substream->runtime;
-	struct snd_soc_component *component =
-		snd_soc_rtdcom_lookup(rtd, DRV_NAME);
 	struct snd_sof_dev *sdev = snd_soc_component_get_drvdata(component);
+	const struct snd_sof_dsp_ops *ops = sof_ops(sdev);
 	struct snd_sof_pcm *spcm;
 	struct snd_soc_tplg_stream_caps *caps;
 	int ret;
@@ -464,11 +490,8 @@ static int sof_pcm_open(struct snd_pcm_substream *substream)
 				   le32_to_cpu(caps->period_size_min));
 
 	/* set runtime config */
-	runtime->hw.info = SNDRV_PCM_INFO_MMAP |
-			  SNDRV_PCM_INFO_MMAP_VALID |
-			  SNDRV_PCM_INFO_INTERLEAVED |
-			  SNDRV_PCM_INFO_PAUSE |
-			  SNDRV_PCM_INFO_NO_PERIOD_WAKEUP;
+	runtime->hw.info = ops->hw_info; /* platform-specific */
+
 	runtime->hw.formats = le64_to_cpu(caps->formats);
 	runtime->hw.period_bytes_min = le32_to_cpu(caps->period_size_min);
 	runtime->hw.period_bytes_max = le32_to_cpu(caps->period_size_max);
@@ -505,11 +528,10 @@ static int sof_pcm_open(struct snd_pcm_substream *substream)
 	return ret;
 }
 
-static int sof_pcm_close(struct snd_pcm_substream *substream)
+static int sof_pcm_close(struct snd_soc_component *component,
+			 struct snd_pcm_substream *substream)
 {
 	struct snd_soc_pcm_runtime *rtd = substream->private_data;
-	struct snd_soc_component *component =
-		snd_soc_rtdcom_lookup(rtd, DRV_NAME);
 	struct snd_sof_dev *sdev = snd_soc_component_get_drvdata(component);
 	struct snd_sof_pcm *spcm;
 	int err;
@@ -538,27 +560,14 @@ static int sof_pcm_close(struct snd_pcm_substream *substream)
 	return 0;
 }
 
-static struct snd_pcm_ops sof_pcm_ops = {
-	.open		= sof_pcm_open,
-	.close		= sof_pcm_close,
-	.ioctl		= snd_pcm_lib_ioctl,
-	.hw_params	= sof_pcm_hw_params,
-	.prepare	= sof_pcm_prepare,
-	.hw_free	= sof_pcm_hw_free,
-	.trigger	= sof_pcm_trigger,
-	.pointer	= sof_pcm_pointer,
-	.page		= snd_pcm_sgbuf_ops_page,
-};
-
 /*
  * Pre-allocate playback/capture audio buffer pages.
  * no need to explicitly release memory preallocated by sof_pcm_new in pcm_free
  * snd_pcm_lib_preallocate_free_for_all() is called by the core.
  */
-static int sof_pcm_new(struct snd_soc_pcm_runtime *rtd)
+static int sof_pcm_new(struct snd_soc_component *component,
+		       struct snd_soc_pcm_runtime *rtd)
 {
-	struct snd_soc_component *component =
-		snd_soc_rtdcom_lookup(rtd, DRV_NAME);
 	struct snd_sof_dev *sdev = snd_soc_component_get_drvdata(component);
 	struct snd_sof_pcm *spcm;
 	struct snd_pcm *pcm = rtd->pcm;
@@ -691,6 +700,14 @@ static int sof_pcm_dai_link_fixup(struct snd_soc_pcm_runtime *rtd,
 	case SOF_DAI_INTEL_ALH:
 		/* do nothing for ALH dai_link */
 		break;
+	case SOF_DAI_IMX_ESAI:
+		channels->min = dai->dai_config->esai.tdm_slots;
+		channels->max = dai->dai_config->esai.tdm_slots;
+
+		dev_dbg(sdev->dev,
+			"channels_min: %d channels_max: %d\n",
+			channels->min, channels->max);
+		break;
 	default:
 		dev_err(sdev->dev, "error: invalid DAI type %d\n",
 			dai->dai_config->type);
@@ -752,11 +769,19 @@ void snd_sof_new_platform_drv(struct snd_sof_dev *sdev)
 	pd->name = "sof-audio-component";
 	pd->probe = sof_pcm_probe;
 	pd->remove = sof_pcm_remove;
-	pd->ops	= &sof_pcm_ops;
+	pd->open = sof_pcm_open;
+	pd->close = sof_pcm_close;
+	pd->ioctl = snd_soc_pcm_lib_ioctl;
+	pd->hw_params = sof_pcm_hw_params;
+	pd->prepare = sof_pcm_prepare;
+	pd->hw_free = sof_pcm_hw_free;
+	pd->trigger = sof_pcm_trigger;
+	pd->pointer = sof_pcm_pointer;
+
 #if IS_ENABLED(CONFIG_SND_SOC_SOF_COMPRESS)
 	pd->compr_ops = &sof_compressed_ops;
 #endif
-	pd->pcm_new = sof_pcm_new;
+	pd->pcm_construct = sof_pcm_new;
 	pd->ignore_machine = drv_name;
 	pd->be_hw_params_fixup = sof_pcm_dai_link_fixup;
 	pd->be_pcm_base = SOF_BE_PCM_BASE;
diff --git a/sound/soc/sof/pm.c b/sound/soc/sof/pm.c
index e23beaeefe00..0fd5567237a8 100644
--- a/sound/soc/sof/pm.c
+++ b/sound/soc/sof/pm.c
@@ -197,7 +197,7 @@ static int sof_restore_pipelines(struct snd_sof_dev *sdev)
 	return ret;
 }
 
-static int sof_send_pm_ipc(struct snd_sof_dev *sdev, int cmd)
+static int sof_send_pm_ctx_ipc(struct snd_sof_dev *sdev, int cmd)
 {
 	struct sof_ipc_pm_ctx pm_ctx;
 	struct sof_ipc_reply reply;
@@ -320,12 +320,15 @@ static int sof_resume(struct device *dev, bool runtime_resume)
 	}
 
 	/* notify DSP of system resume */
-	ret = sof_send_pm_ipc(sdev, SOF_IPC_PM_CTX_RESTORE);
+	ret = sof_send_pm_ctx_ipc(sdev, SOF_IPC_PM_CTX_RESTORE);
 	if (ret < 0)
 		dev_err(sdev->dev,
 			"error: ctx_restore ipc error during resume %d\n",
 			ret);
 
+	/* initialize default D0 sub-state */
+	sdev->d0_substate = SOF_DSP_D0I0;
+
 	return ret;
 }
 
@@ -358,7 +361,7 @@ static int sof_suspend(struct device *dev, bool runtime_suspend)
 		sof_cache_debugfs(sdev);
 #endif
 	/* notify DSP of upcoming power down */
-	ret = sof_send_pm_ipc(sdev, SOF_IPC_PM_CTX_SAVE);
+	ret = sof_send_pm_ctx_ipc(sdev, SOF_IPC_PM_CTX_SAVE);
 	if (ret == -EBUSY || ret == -EAGAIN) {
 		/*
 		 * runtime PM has logic to handle -EBUSY/-EAGAIN so
@@ -408,14 +411,135 @@ int snd_sof_runtime_resume(struct device *dev)
 }
 EXPORT_SYMBOL(snd_sof_runtime_resume);
 
+int snd_sof_set_d0_substate(struct snd_sof_dev *sdev,
+			    enum sof_d0_substate d0_substate)
+{
+	int ret;
+
+	if (sdev->d0_substate == d0_substate)
+		return 0;
+
+	/* do platform specific set_state */
+	ret = snd_sof_dsp_set_power_state(sdev, d0_substate);
+	if (ret < 0)
+		return ret;
+
+	/* update dsp D0 sub-state */
+	sdev->d0_substate = d0_substate;
+
+	return 0;
+}
+EXPORT_SYMBOL(snd_sof_set_d0_substate);
+
+/*
+ * Audio DSP states may transform as below:-
+ *
+ *                                         D0I3 compatible stream
+ *     Runtime    +---------------------+   opened only, timeout
+ *     suspend    |                     +--------------------+
+ *   +------------+       D0(active)    |                    |
+ *   |            |                     <---------------+    |
+ *   |   +-------->                     |               |    |
+ *   |   |Runtime +--^--+---------^--+--+ The last      |    |
+ *   |   |resume     |  |         |  |    opened D0I3   |    |
+ *   |   |           |  |         |  |    compatible    |    |
+ *   |   |     resume|  |         |  |    stream closed |    |
+ *   |   |      from |  | D3      |  |                  |    |
+ *   |   |       D3  |  |suspend  |  | d0i3             |    |
+ *   |   |           |  |         |  |suspend           |    |
+ *   |   |           |  |         |  |                  |    |
+ *   |   |           |  |         |  |                  |    |
+ * +-v---+-----------+--v-------+ |  |           +------+----v----+
+ * |                            | |  +----------->                |
+ * |       D3 (suspended)       | |              |      D0I3      +-----+
+ * |                            | +--------------+                |     |
+ * |                            |  resume from   |                |     |
+ * +-------------------^--------+  d0i3 suspend  +----------------+     |
+ *                     |                                                |
+ *                     |                       D3 suspend               |
+ *                     +------------------------------------------------+
+ *
+ * d0i3_suspend = s0_suspend && D0I3 stream opened,
+ * D3 suspend = !d0i3_suspend,
+ */
+
 int snd_sof_resume(struct device *dev)
 {
+	struct snd_sof_dev *sdev = dev_get_drvdata(dev);
+	int ret;
+
+	if (snd_sof_dsp_d0i3_on_suspend(sdev)) {
+		/* resume from D0I3 */
+		dev_dbg(sdev->dev, "DSP will exit from D0i3...\n");
+		ret = snd_sof_set_d0_substate(sdev, SOF_DSP_D0I0);
+		if (ret == -ENOTSUPP) {
+			/* fallback to resume from D3 */
+			dev_dbg(sdev->dev, "D0i3 not supported, fall back to resume from D3...\n");
+			goto d3_resume;
+		} else if (ret < 0) {
+			dev_err(sdev->dev, "error: failed to exit from D0I3 %d\n",
+				ret);
+			return ret;
+		}
+
+		/* platform-specific resume from D0i3 */
+		return snd_sof_dsp_resume(sdev);
+	}
+
+d3_resume:
+	/* resume from D3 */
 	return sof_resume(dev, false);
 }
 EXPORT_SYMBOL(snd_sof_resume);
 
 int snd_sof_suspend(struct device *dev)
 {
+	struct snd_sof_dev *sdev = dev_get_drvdata(dev);
+	int ret;
+
+	if (snd_sof_dsp_d0i3_on_suspend(sdev)) {
+		/* suspend to D0i3 */
+		dev_dbg(sdev->dev, "DSP is trying to enter D0i3...\n");
+		ret = snd_sof_set_d0_substate(sdev, SOF_DSP_D0I3);
+		if (ret == -ENOTSUPP) {
+			/* fallback to D3 suspend */
+			dev_dbg(sdev->dev, "D0i3 not supported, fall back to D3...\n");
+			goto d3_suspend;
+		} else if (ret < 0) {
+			dev_err(sdev->dev, "error: failed to enter D0I3, %d\n",
+				ret);
+			return ret;
+		}
+
+		/* platform-specific suspend to D0i3 */
+		return snd_sof_dsp_suspend(sdev);
+	}
+
+d3_suspend:
+	/* suspend to D3 */
 	return sof_suspend(dev, false);
 }
 EXPORT_SYMBOL(snd_sof_suspend);
+
+int snd_sof_prepare(struct device *dev)
+{
+	struct snd_sof_dev *sdev = dev_get_drvdata(dev);
+
+#if defined(CONFIG_ACPI)
+	sdev->s0_suspend = acpi_target_system_state() == ACPI_STATE_S0;
+#else
+	/* will suspend to S3 by default */
+	sdev->s0_suspend = false;
+#endif
+
+	return 0;
+}
+EXPORT_SYMBOL(snd_sof_prepare);
+
+void snd_sof_complete(struct device *dev)
+{
+	struct snd_sof_dev *sdev = dev_get_drvdata(dev);
+
+	sdev->s0_suspend = false;
+}
+EXPORT_SYMBOL(snd_sof_complete);
diff --git a/sound/soc/sof/sof-acpi-dev.c b/sound/soc/sof/sof-acpi-dev.c
index ea7b8b895412..df318f50dd0b 100644
--- a/sound/soc/sof/sof-acpi-dev.c
+++ b/sound/soc/sof/sof-acpi-dev.c
@@ -29,6 +29,12 @@ static char *tplg_path;
 module_param(tplg_path, charp, 0444);
 MODULE_PARM_DESC(tplg_path, "alternate path for SOF topology.");
 
+static int sof_acpi_debug;
+module_param_named(sof_acpi_debug, sof_acpi_debug, int, 0444);
+MODULE_PARM_DESC(sof_acpi_debug, "SOF ACPI debug options (0x0 all off)");
+
+#define SOF_ACPI_DISABLE_PM_RUNTIME BIT(0)
+
 #if IS_ENABLED(CONFIG_SND_SOC_SOF_HASWELL)
 static const struct sof_dev_desc sof_acpi_haswell_desc = {
 	.machines = snd_soc_acpi_intel_haswell_machines,
@@ -121,6 +127,9 @@ static const struct dev_pm_ops sof_acpi_pm = {
 
 static void sof_acpi_probe_complete(struct device *dev)
 {
+	if (sof_acpi_debug & SOF_ACPI_DISABLE_PM_RUNTIME)
+		return;
+
 	/* allow runtime_pm */
 	pm_runtime_set_autosuspend_delay(dev, SND_SOF_SUSPEND_DELAY_MS);
 	pm_runtime_use_autosuspend(dev);
@@ -221,7 +230,8 @@ static int sof_acpi_probe(struct platform_device *pdev)
 
 static int sof_acpi_remove(struct platform_device *pdev)
 {
-	pm_runtime_disable(&pdev->dev);
+	if (!(sof_acpi_debug & SOF_ACPI_DISABLE_PM_RUNTIME))
+		pm_runtime_disable(&pdev->dev);
 
 	/* call sof helper for DSP hardware remove */
 	snd_sof_device_remove(&pdev->dev);
diff --git a/sound/soc/sof/sof-pci-dev.c b/sound/soc/sof/sof-pci-dev.c
index d66412a77873..bbeffd932de7 100644
--- a/sound/soc/sof/sof-pci-dev.c
+++ b/sound/soc/sof/sof-pci-dev.c
@@ -12,6 +12,7 @@
 #include <linux/module.h>
 #include <linux/pci.h>
 #include <linux/pm_runtime.h>
+#include <sound/intel-dsp-config.h>
 #include <sound/soc-acpi.h>
 #include <sound/soc-acpi-intel-match.h>
 #include <sound/sof.h>
@@ -29,6 +30,12 @@ static char *tplg_path;
 module_param(tplg_path, charp, 0444);
 MODULE_PARM_DESC(tplg_path, "alternate path for SOF topology.");
 
+static int sof_pci_debug;
+module_param_named(sof_pci_debug, sof_pci_debug, int, 0444);
+MODULE_PARM_DESC(sof_pci_debug, "SOF PCI debug options (0x0 all off)");
+
+#define SOF_PCI_DISABLE_PM_RUNTIME BIT(0)
+
 #if IS_ENABLED(CONFIG_SND_SOC_SOF_APOLLOLAKE)
 static const struct sof_dev_desc bxt_desc = {
 	.machines		= snd_soc_acpi_intel_bxt_machines,
@@ -113,7 +120,7 @@ static const struct sof_dev_desc cnl_desc = {
 
 #if IS_ENABLED(CONFIG_SND_SOC_SOF_COFFEELAKE)
 static const struct sof_dev_desc cfl_desc = {
-	.machines		= snd_soc_acpi_intel_cnl_machines,
+	.machines		= snd_soc_acpi_intel_cfl_machines,
 	.resindex_lpe_base	= 0,
 	.resindex_pcicfg_base	= -1,
 	.resindex_imr_base	= -1,
@@ -122,7 +129,7 @@ static const struct sof_dev_desc cfl_desc = {
 	.chip_info = &cnl_chip_info,
 	.default_fw_path = "intel/sof",
 	.default_tplg_path = "intel/sof-tplg",
-	.nocodec_fw_filename = "sof-cnl.ri",
+	.nocodec_fw_filename = "sof-cfl.ri",
 	.nocodec_tplg_filename = "sof-cnl-nocodec.tplg",
 	.ops = &sof_cnl_ops,
 	.arch_ops = &sof_xtensa_arch_ops
@@ -133,7 +140,7 @@ static const struct sof_dev_desc cfl_desc = {
 	IS_ENABLED(CONFIG_SND_SOC_SOF_COMETLAKE_H)
 
 static const struct sof_dev_desc cml_desc = {
-	.machines		= snd_soc_acpi_intel_cnl_machines,
+	.machines		= snd_soc_acpi_intel_cml_machines,
 	.resindex_lpe_base	= 0,
 	.resindex_pcicfg_base	= -1,
 	.resindex_imr_base	= -1,
@@ -142,7 +149,7 @@ static const struct sof_dev_desc cml_desc = {
 	.chip_info = &cnl_chip_info,
 	.default_fw_path = "intel/sof",
 	.default_tplg_path = "intel/sof-tplg",
-	.nocodec_fw_filename = "sof-cnl.ri",
+	.nocodec_fw_filename = "sof-cml.ri",
 	.nocodec_tplg_filename = "sof-cnl-nocodec.tplg",
 	.ops = &sof_cnl_ops,
 	.arch_ops = &sof_xtensa_arch_ops
@@ -167,42 +174,6 @@ static const struct sof_dev_desc icl_desc = {
 };
 #endif
 
-#if IS_ENABLED(CONFIG_SND_SOC_SOF_SKYLAKE)
-static const struct sof_dev_desc skl_desc = {
-	.machines		= snd_soc_acpi_intel_skl_machines,
-	.resindex_lpe_base	= 0,
-	.resindex_pcicfg_base	= -1,
-	.resindex_imr_base	= -1,
-	.irqindex_host_ipc	= -1,
-	.resindex_dma_base	= -1,
-	.chip_info = &skl_chip_info,
-	.default_fw_path = "intel/sof",
-	.default_tplg_path = "intel/sof-tplg",
-	.nocodec_fw_filename = "sof-skl.ri",
-	.nocodec_tplg_filename = "sof-skl-nocodec.tplg",
-	.ops = &sof_skl_ops,
-	.arch_ops = &sof_xtensa_arch_ops
-};
-#endif
-
-#if IS_ENABLED(CONFIG_SND_SOC_SOF_KABYLAKE)
-static const struct sof_dev_desc kbl_desc = {
-	.machines		= snd_soc_acpi_intel_kbl_machines,
-	.resindex_lpe_base	= 0,
-	.resindex_pcicfg_base	= -1,
-	.resindex_imr_base	= -1,
-	.irqindex_host_ipc	= -1,
-	.resindex_dma_base	= -1,
-	.chip_info = &skl_chip_info,
-	.default_fw_path = "intel/sof",
-	.default_tplg_path = "intel/sof-tplg",
-	.nocodec_fw_filename = "sof-kbl.ri",
-	.nocodec_tplg_filename = "sof-kbl-nocodec.tplg",
-	.ops = &sof_skl_ops,
-	.arch_ops = &sof_xtensa_arch_ops
-};
-#endif
-
 #if IS_ENABLED(CONFIG_SND_SOC_SOF_TIGERLAKE)
 static const struct sof_dev_desc tgl_desc = {
 	.machines               = snd_soc_acpi_intel_tgl_machines,
@@ -239,7 +210,27 @@ static const struct sof_dev_desc ehl_desc = {
 };
 #endif
 
+#if IS_ENABLED(CONFIG_SND_SOC_SOF_JASPERLAKE)
+static const struct sof_dev_desc jsl_desc = {
+	.machines               = snd_soc_acpi_intel_jsl_machines,
+	.resindex_lpe_base      = 0,
+	.resindex_pcicfg_base   = -1,
+	.resindex_imr_base      = -1,
+	.irqindex_host_ipc      = -1,
+	.resindex_dma_base      = -1,
+	.chip_info = &jsl_chip_info,
+	.default_fw_path = "intel/sof",
+	.default_tplg_path = "intel/sof-tplg",
+	.nocodec_fw_filename = "sof-jsl.ri",
+	.nocodec_tplg_filename = "sof-jsl-nocodec.tplg",
+	.ops = &sof_cnl_ops,
+	.arch_ops = &sof_xtensa_arch_ops
+};
+#endif
+
 static const struct dev_pm_ops sof_pci_pm = {
+	.prepare = snd_sof_prepare,
+	.complete = snd_sof_complete,
 	SET_SYSTEM_SLEEP_PM_OPS(snd_sof_suspend, snd_sof_resume)
 	SET_RUNTIME_PM_OPS(snd_sof_runtime_suspend, snd_sof_runtime_resume,
 			   snd_sof_runtime_idle)
@@ -249,6 +240,9 @@ static void sof_pci_probe_complete(struct device *dev)
 {
 	dev_dbg(dev, "Completing SOF PCI probe");
 
+	if (sof_pci_debug & SOF_PCI_DISABLE_PM_RUNTIME)
+		return;
+
 	/* allow runtime_pm */
 	pm_runtime_set_autosuspend_delay(dev, SND_SOF_SUSPEND_DELAY_MS);
 	pm_runtime_use_autosuspend(dev);
@@ -277,6 +271,11 @@ static int sof_pci_probe(struct pci_dev *pci,
 	const struct snd_sof_dsp_ops *ops;
 	int ret;
 
+	ret = snd_intel_dsp_driver_probe(pci);
+	if (ret != SND_INTEL_DSP_DRIVER_ANY &&
+	    ret != SND_INTEL_DSP_DRIVER_SOF)
+		return -ENODEV;
+
 	dev_dbg(&pci->dev, "PCI DSP detected");
 
 	/* get ops for platform */
@@ -370,7 +369,8 @@ static void sof_pci_remove(struct pci_dev *pci)
 	snd_sof_device_remove(&pci->dev);
 
 	/* follow recommendation in pci-driver.c to increment usage counter */
-	pm_runtime_get_noresume(&pci->dev);
+	if (!(sof_pci_debug & SOF_PCI_DISABLE_PM_RUNTIME))
+		pm_runtime_get_noresume(&pci->dev);
 
 	/* release pci regions and disable device */
 	pci_release_regions(pci);
@@ -401,18 +401,14 @@ static const struct pci_device_id sof_pci_ids[] = {
 	{ PCI_DEVICE(0x8086, 0xa348),
 		.driver_data = (unsigned long)&cfl_desc},
 #endif
-#if IS_ENABLED(CONFIG_SND_SOC_SOF_KABYLAKE)
-	{ PCI_DEVICE(0x8086, 0x9d71),
-		.driver_data = (unsigned long)&kbl_desc},
-#endif
-#if IS_ENABLED(CONFIG_SND_SOC_SOF_SKYLAKE)
-	{ PCI_DEVICE(0x8086, 0x9d70),
-		.driver_data = (unsigned long)&skl_desc},
-#endif
 #if IS_ENABLED(CONFIG_SND_SOC_SOF_ICELAKE)
 	{ PCI_DEVICE(0x8086, 0x34C8),
 		.driver_data = (unsigned long)&icl_desc},
 #endif
+#if IS_ENABLED(CONFIG_SND_SOC_SOF_JASPERLAKE)
+	{ PCI_DEVICE(0x8086, 0x38c8),
+		.driver_data = (unsigned long)&jsl_desc},
+#endif
 #if IS_ENABLED(CONFIG_SND_SOC_SOF_COMETLAKE_LP)
 	{ PCI_DEVICE(0x8086, 0x02c8),
 		.driver_data = (unsigned long)&cml_desc},
diff --git a/sound/soc/sof/sof-priv.h b/sound/soc/sof/sof-priv.h
index 730f3259dd02..c7c2c70ee4d0 100644
--- a/sound/soc/sof/sof-priv.h
+++ b/sound/soc/sof/sof-priv.h
@@ -15,6 +15,7 @@
 
 #include <sound/hdaudio.h>
 #include <sound/soc.h>
+#include <sound/control.h>
 
 #include <sound/sof.h>
 #include <sound/sof/stream.h> /* needs to be included before control.h */
@@ -28,10 +29,15 @@
 #include <uapi/sound/sof/fw.h>
 
 /* debug flags */
-#define SOF_DBG_REGS	BIT(1)
-#define SOF_DBG_MBOX	BIT(2)
-#define SOF_DBG_TEXT	BIT(3)
-#define SOF_DBG_PCI	BIT(4)
+#define SOF_DBG_ENABLE_TRACE	BIT(0)
+#define SOF_DBG_REGS		BIT(1)
+#define SOF_DBG_MBOX		BIT(2)
+#define SOF_DBG_TEXT		BIT(3)
+#define SOF_DBG_PCI		BIT(4)
+#define SOF_DBG_RETAIN_CTX	BIT(5)	/* prevent DSP D3 on FW exception */
+
+/* global debug state set by SOF_DBG_ flags */
+extern int sof_core_debug;
 
 /* max BARs mmaped devices can use */
 #define SND_SOF_BARS	8
@@ -62,6 +68,12 @@
 
 #define DMA_CHAN_INVALID	0xFFFFFFFF
 
+/* DSP D0ix sub-state */
+enum sof_d0_substate {
+	SOF_DSP_D0I0 = 0,	/* DSP default D0 substate */
+	SOF_DSP_D0I3,		/* DSP D0i3(low power) substate*/
+};
+
 struct snd_sof_dev;
 struct snd_sof_ipc_msg;
 struct snd_sof_ipc;
@@ -128,7 +140,7 @@ struct snd_sof_dsp_ops {
 	 * FW ready checks for ABI compatibility and creates
 	 * memory windows at first boot
 	 */
-	int (*fw_ready)(struct snd_sof_dev *sdev, u32 msg_id); /* optional */
+	int (*fw_ready)(struct snd_sof_dev *sdev, u32 msg_id); /* mandatory */
 
 	/* connect pcm substream to a host stream */
 	int (*pcm_open)(struct snd_sof_dev *sdev,
@@ -177,6 +189,8 @@ struct snd_sof_dsp_ops {
 	int (*runtime_resume)(struct snd_sof_dev *sof_dev); /* optional */
 	int (*runtime_idle)(struct snd_sof_dev *sof_dev); /* optional */
 	int (*set_hw_params_upon_resume)(struct snd_sof_dev *sdev); /* optional */
+	int (*set_power_state)(struct snd_sof_dev *sdev,
+			       enum sof_d0_substate d0_substate); /* optional */
 
 	/* DSP clocking */
 	int (*set_clk)(struct snd_sof_dev *sof_dev, u32 freq); /* optional */
@@ -205,6 +219,9 @@ struct snd_sof_dsp_ops {
 	/* DAI ops */
 	struct snd_soc_dai_driver *drv;
 	int num_drv;
+
+	/* ALSA HW info flags, will be stored in snd_pcm_runtime.hw.info */
+	u32 hw_info;
 };
 
 /* DSP architecture specific callbacks for oops and stack dumps */
@@ -293,6 +310,12 @@ struct snd_sof_pcm_stream {
 	struct sof_ipc_stream_posn posn;
 	struct snd_pcm_substream *substream;
 	struct work_struct period_elapsed_work;
+	bool d0i3_compatible; /* DSP can be in D0I3 when this pcm is opened */
+	/*
+	 * flag to indicate that the DSP pipelines should be kept
+	 * active or not while suspending the stream
+	 */
+	bool suspend_ignored;
 };
 
 /* ALSA SOF PCM device */
@@ -305,6 +328,12 @@ struct snd_sof_pcm {
 	bool prepared[2]; /* PCM_PARAMS set successfully */
 };
 
+struct snd_sof_led_control {
+	unsigned int use_led;
+	unsigned int direction;
+	unsigned int led_value;
+};
+
 /* ALSA SOF Kcontrol device */
 struct snd_sof_control {
 	struct snd_sof_dev *sdev;
@@ -319,6 +348,8 @@ struct snd_sof_control {
 	u32 *volume_table; /* volume table computed from tlv data*/
 
 	struct list_head list;	/* list in sdev control list */
+
+	struct snd_sof_led_control led_ctl;
 };
 
 /* ASoC SOF DAPM widget */
@@ -370,6 +401,11 @@ struct snd_sof_dev {
 	 */
 	struct snd_soc_component_driver plat_drv;
 
+	/* power states related */
+	enum sof_d0_substate d0_substate;
+	/* flag to track if the intended power target of suspend is S0ix */
+	bool s0_suspend;
+
 	/* DSP firmware boot */
 	wait_queue_head_t boot_wait;
 	u32 boot_complete;
@@ -434,6 +470,7 @@ struct snd_sof_dev {
 	int dma_trace_pages;
 	wait_queue_head_t trace_sleep;
 	u32 host_offset;
+	u32 dtrace_is_supported; /* set with Kconfig or module parameter */
 	u32 dtrace_is_enabled;
 	u32 dtrace_error;
 	u32 dtrace_draining;
@@ -455,6 +492,10 @@ int snd_sof_runtime_resume(struct device *dev);
 int snd_sof_runtime_idle(struct device *dev);
 int snd_sof_resume(struct device *dev);
 int snd_sof_suspend(struct device *dev);
+int snd_sof_prepare(struct device *dev);
+void snd_sof_complete(struct device *dev);
+int snd_sof_set_d0_substate(struct snd_sof_dev *sdev,
+			    enum sof_d0_substate d0_substate);
 
 void snd_sof_new_platform_drv(struct snd_sof_dev *sdev);
 
@@ -512,6 +553,8 @@ struct snd_sof_pcm *snd_sof_find_spcm_dai(struct snd_sof_dev *sdev,
 	return NULL;
 }
 
+bool snd_sof_dsp_d0i3_on_suspend(struct snd_sof_dev *sdev);
+
 struct snd_sof_pcm *snd_sof_find_spcm_name(struct snd_sof_dev *sdev,
 					   const char *name);
 struct snd_sof_pcm *snd_sof_find_spcm_comp(struct snd_sof_dev *sdev,
@@ -575,6 +618,7 @@ void snd_sof_get_status(struct snd_sof_dev *sdev, u32 panic_code,
 			struct sof_ipc_panic_info *panic_info,
 			void *stack, size_t stack_words);
 int snd_sof_init_trace_ipc(struct snd_sof_dev *sdev);
+void snd_sof_handle_fw_exception(struct snd_sof_dev *sdev);
 
 /*
  * Platform specific ops.
diff --git a/sound/soc/sof/topology.c b/sound/soc/sof/topology.c
index 4452594c2e17..d82ab981e840 100644
--- a/sound/soc/sof/topology.c
+++ b/sound/soc/sof/topology.c
@@ -135,7 +135,9 @@ static int sof_keyword_dapm_event(struct snd_soc_dapm_widget *w,
 				  struct snd_kcontrol *k, int event)
 {
 	struct snd_sof_widget *swidget = w->dobj.private;
+	int stream = SNDRV_PCM_STREAM_CAPTURE;
 	struct snd_sof_dev *sdev;
+	struct snd_sof_pcm *spcm;
 	int ret = 0;
 
 	if (!swidget)
@@ -146,11 +148,24 @@ static int sof_keyword_dapm_event(struct snd_soc_dapm_widget *w,
 	dev_dbg(sdev->dev, "received event %d for widget %s\n",
 		event, w->name);
 
+	/* get runtime PCM params using widget's stream name */
+	spcm = snd_sof_find_spcm_name(sdev, swidget->widget->sname);
+	if (!spcm) {
+		dev_err(sdev->dev, "error: cannot find PCM for %s\n",
+			swidget->widget->name);
+		return -EINVAL;
+	}
+
 	/* process events */
 	switch (event) {
 	case SND_SOC_DAPM_PRE_PMU:
+		if (spcm->stream[stream].suspend_ignored) {
+			dev_dbg(sdev->dev, "PRE_PMU event ignored, KWD pipeline is already RUNNING\n");
+			return 0;
+		}
+
 		/* set pcm params */
-		ret = ipc_pcm_params(swidget, SOF_IPC_STREAM_CAPTURE);
+		ret = ipc_pcm_params(swidget, stream);
 		if (ret < 0) {
 			dev_err(sdev->dev,
 				"error: failed to set pcm params for widget %s\n",
@@ -166,6 +181,11 @@ static int sof_keyword_dapm_event(struct snd_soc_dapm_widget *w,
 				swidget->widget->name);
 		break;
 	case SND_SOC_DAPM_POST_PMD:
+		if (spcm->stream[stream].suspend_ignored) {
+			dev_dbg(sdev->dev, "POST_PMD even ignored, KWD pipeline will remain RUNNING\n");
+			return 0;
+		}
+
 		/* stop trigger */
 		ret = ipc_trigger(swidget, SOF_IPC_STREAM_TRIG_STOP);
 		if (ret < 0)
@@ -433,164 +453,6 @@ static enum sof_comp_type find_process_comp_type(enum sof_ipc_process_type type)
 }
 
 /*
- * Standard Kcontrols.
- */
-
-static int sof_control_load_volume(struct snd_soc_component *scomp,
-				   struct snd_sof_control *scontrol,
-				   struct snd_kcontrol_new *kc,
-				   struct snd_soc_tplg_ctl_hdr *hdr)
-{
-	struct snd_sof_dev *sdev = snd_soc_component_get_drvdata(scomp);
-	struct snd_soc_tplg_mixer_control *mc =
-		container_of(hdr, struct snd_soc_tplg_mixer_control, hdr);
-	struct sof_ipc_ctrl_data *cdata;
-	int tlv[TLV_ITEMS];
-	unsigned int i;
-	int ret;
-
-	/* validate topology data */
-	if (le32_to_cpu(mc->num_channels) > SND_SOC_TPLG_MAX_CHAN)
-		return -EINVAL;
-
-	/* init the volume get/put data */
-	scontrol->size = struct_size(scontrol->control_data, chanv,
-				     le32_to_cpu(mc->num_channels));
-	scontrol->control_data = kzalloc(scontrol->size, GFP_KERNEL);
-	if (!scontrol->control_data)
-		return -ENOMEM;
-
-	scontrol->comp_id = sdev->next_comp_id;
-	scontrol->min_volume_step = le32_to_cpu(mc->min);
-	scontrol->max_volume_step = le32_to_cpu(mc->max);
-	scontrol->num_channels = le32_to_cpu(mc->num_channels);
-
-	/* set cmd for mixer control */
-	if (le32_to_cpu(mc->max) == 1) {
-		scontrol->cmd = SOF_CTRL_CMD_SWITCH;
-		goto out;
-	}
-
-	scontrol->cmd = SOF_CTRL_CMD_VOLUME;
-
-	/* extract tlv data */
-	if (get_tlv_data(kc->tlv.p, tlv) < 0) {
-		dev_err(sdev->dev, "error: invalid TLV data\n");
-		return -EINVAL;
-	}
-
-	/* set up volume table */
-	ret = set_up_volume_table(scontrol, tlv, le32_to_cpu(mc->max) + 1);
-	if (ret < 0) {
-		dev_err(sdev->dev, "error: setting up volume table\n");
-		return ret;
-	}
-
-	/* set default volume values to 0dB in control */
-	cdata = scontrol->control_data;
-	for (i = 0; i < scontrol->num_channels; i++) {
-		cdata->chanv[i].channel = i;
-		cdata->chanv[i].value = VOL_ZERO_DB;
-	}
-
-out:
-	dev_dbg(sdev->dev, "tplg: load kcontrol index %d chans %d\n",
-		scontrol->comp_id, scontrol->num_channels);
-
-	return 0;
-}
-
-static int sof_control_load_enum(struct snd_soc_component *scomp,
-				 struct snd_sof_control *scontrol,
-				 struct snd_kcontrol_new *kc,
-				 struct snd_soc_tplg_ctl_hdr *hdr)
-{
-	struct snd_sof_dev *sdev = snd_soc_component_get_drvdata(scomp);
-	struct snd_soc_tplg_enum_control *ec =
-		container_of(hdr, struct snd_soc_tplg_enum_control, hdr);
-
-	/* validate topology data */
-	if (le32_to_cpu(ec->num_channels) > SND_SOC_TPLG_MAX_CHAN)
-		return -EINVAL;
-
-	/* init the enum get/put data */
-	scontrol->size = struct_size(scontrol->control_data, chanv,
-				     le32_to_cpu(ec->num_channels));
-	scontrol->control_data = kzalloc(scontrol->size, GFP_KERNEL);
-	if (!scontrol->control_data)
-		return -ENOMEM;
-
-	scontrol->comp_id = sdev->next_comp_id;
-	scontrol->num_channels = le32_to_cpu(ec->num_channels);
-
-	scontrol->cmd = SOF_CTRL_CMD_ENUM;
-
-	dev_dbg(sdev->dev, "tplg: load kcontrol index %d chans %d comp_id %d\n",
-		scontrol->comp_id, scontrol->num_channels, scontrol->comp_id);
-
-	return 0;
-}
-
-static int sof_control_load_bytes(struct snd_soc_component *scomp,
-				  struct snd_sof_control *scontrol,
-				  struct snd_kcontrol_new *kc,
-				  struct snd_soc_tplg_ctl_hdr *hdr)
-{
-	struct snd_sof_dev *sdev = snd_soc_component_get_drvdata(scomp);
-	struct sof_ipc_ctrl_data *cdata;
-	struct snd_soc_tplg_bytes_control *control =
-		container_of(hdr, struct snd_soc_tplg_bytes_control, hdr);
-	struct soc_bytes_ext *sbe = (struct soc_bytes_ext *)kc->private_value;
-	int max_size = sbe->max;
-
-	/* init the get/put bytes data */
-	scontrol->size = sizeof(struct sof_ipc_ctrl_data) +
-		le32_to_cpu(control->priv.size);
-
-	if (scontrol->size > max_size) {
-		dev_err(sdev->dev, "err: bytes data size %d exceeds max %d.\n",
-			scontrol->size, max_size);
-		return -EINVAL;
-	}
-
-	scontrol->control_data = kzalloc(max_size, GFP_KERNEL);
-	cdata = scontrol->control_data;
-	if (!scontrol->control_data)
-		return -ENOMEM;
-
-	scontrol->comp_id = sdev->next_comp_id;
-	scontrol->cmd = SOF_CTRL_CMD_BINARY;
-
-	dev_dbg(sdev->dev, "tplg: load kcontrol index %d chans %d\n",
-		scontrol->comp_id, scontrol->num_channels);
-
-	if (le32_to_cpu(control->priv.size) > 0) {
-		memcpy(cdata->data, control->priv.data,
-		       le32_to_cpu(control->priv.size));
-
-		if (cdata->data->magic != SOF_ABI_MAGIC) {
-			dev_err(sdev->dev, "error: Wrong ABI magic 0x%08x.\n",
-				cdata->data->magic);
-			return -EINVAL;
-		}
-		if (SOF_ABI_VERSION_INCOMPATIBLE(SOF_ABI_VERSION,
-						 cdata->data->abi)) {
-			dev_err(sdev->dev,
-				"error: Incompatible ABI version 0x%08x.\n",
-				cdata->data->abi);
-			return -EINVAL;
-		}
-		if (cdata->data->size + sizeof(const struct sof_abi_hdr) !=
-		    le32_to_cpu(control->priv.size)) {
-			dev_err(sdev->dev,
-				"error: Conflict in bytes vs. priv size.\n");
-			return -EINVAL;
-		}
-	}
-	return 0;
-}
-
-/*
  * Topology Token Parsing.
  * New tokens should be added to headers and parsing tables below.
  */
@@ -725,6 +587,16 @@ static const struct sof_topology_token pcm_tokens[] = {
 		offsetof(struct sof_ipc_comp_host, dmac_config), 0},
 };
 
+/* PCM */
+static const struct sof_topology_token stream_tokens[] = {
+	{SOF_TKN_STREAM_PLAYBACK_COMPATIBLE_D0I3,
+		SND_SOC_TPLG_TUPLE_TYPE_BOOL, get_token_u16,
+		offsetof(struct snd_sof_pcm, stream[0].d0i3_compatible), 0},
+	{SOF_TKN_STREAM_CAPTURE_COMPATIBLE_D0I3,
+		SND_SOC_TPLG_TUPLE_TYPE_BOOL, get_token_u16,
+		offsetof(struct snd_sof_pcm, stream[1].d0i3_compatible), 0},
+};
+
 /* Generic components */
 static const struct sof_topology_token comp_tokens[] = {
 	{SOF_TKN_COMP_PERIOD_SINK_COUNT,
@@ -799,6 +671,13 @@ static const struct sof_topology_token dmic_tokens[] = {
 
 };
 
+/* ESAI */
+static const struct sof_topology_token esai_tokens[] = {
+	{SOF_TKN_IMX_ESAI_MCLK_ID,
+		SND_SOC_TPLG_TUPLE_TYPE_SHORT, get_token_u16,
+		offsetof(struct sof_ipc_dai_esai_params, mclk_id), 0},
+};
+
 /*
  * DMIC PDM Tokens
  * SOF_TKN_INTEL_DMIC_PDM_CTRL_ID should be the first token
@@ -840,6 +719,14 @@ static const struct sof_topology_token dmic_pdm_tokens[] = {
 static const struct sof_topology_token hda_tokens[] = {
 };
 
+/* Leds */
+static const struct sof_topology_token led_tokens[] = {
+	{SOF_TKN_MUTE_LED_USE, SND_SOC_TPLG_TUPLE_TYPE_WORD, get_token_u32,
+	 offsetof(struct snd_sof_led_control, use_led), 0},
+	{SOF_TKN_MUTE_LED_DIRECTION, SND_SOC_TPLG_TUPLE_TYPE_WORD,
+	 get_token_u32, offsetof(struct snd_sof_led_control, direction), 0},
+};
+
 static void sof_parse_uuid_tokens(struct snd_soc_component *scomp,
 				  void *object,
 				  const struct sof_topology_token *tokens,
@@ -1040,6 +927,200 @@ static void sof_dbg_comp_config(struct snd_soc_component *scomp,
 		config->frame_fmt);
 }
 
+/*
+ * Standard Kcontrols.
+ */
+
+static int sof_control_load_volume(struct snd_soc_component *scomp,
+				   struct snd_sof_control *scontrol,
+				   struct snd_kcontrol_new *kc,
+				   struct snd_soc_tplg_ctl_hdr *hdr)
+{
+	struct snd_sof_dev *sdev = snd_soc_component_get_drvdata(scomp);
+	struct snd_soc_tplg_mixer_control *mc =
+		container_of(hdr, struct snd_soc_tplg_mixer_control, hdr);
+	struct sof_ipc_ctrl_data *cdata;
+	int tlv[TLV_ITEMS];
+	unsigned int i;
+	int ret = 0;
+
+	/* validate topology data */
+	if (le32_to_cpu(mc->num_channels) > SND_SOC_TPLG_MAX_CHAN) {
+		ret = -EINVAL;
+		goto out;
+	}
+
+	/* init the volume get/put data */
+	scontrol->size = struct_size(scontrol->control_data, chanv,
+				     le32_to_cpu(mc->num_channels));
+	scontrol->control_data = kzalloc(scontrol->size, GFP_KERNEL);
+	if (!scontrol->control_data) {
+		ret = -ENOMEM;
+		goto out;
+	}
+
+	scontrol->comp_id = sdev->next_comp_id;
+	scontrol->min_volume_step = le32_to_cpu(mc->min);
+	scontrol->max_volume_step = le32_to_cpu(mc->max);
+	scontrol->num_channels = le32_to_cpu(mc->num_channels);
+
+	/* set cmd for mixer control */
+	if (le32_to_cpu(mc->max) == 1) {
+		scontrol->cmd = SOF_CTRL_CMD_SWITCH;
+		goto skip;
+	}
+
+	scontrol->cmd = SOF_CTRL_CMD_VOLUME;
+
+	/* extract tlv data */
+	if (get_tlv_data(kc->tlv.p, tlv) < 0) {
+		dev_err(sdev->dev, "error: invalid TLV data\n");
+		ret = -EINVAL;
+		goto out_free;
+	}
+
+	/* set up volume table */
+	ret = set_up_volume_table(scontrol, tlv, le32_to_cpu(mc->max) + 1);
+	if (ret < 0) {
+		dev_err(sdev->dev, "error: setting up volume table\n");
+		goto out_free;
+	}
+
+	/* set default volume values to 0dB in control */
+	cdata = scontrol->control_data;
+	for (i = 0; i < scontrol->num_channels; i++) {
+		cdata->chanv[i].channel = i;
+		cdata->chanv[i].value = VOL_ZERO_DB;
+	}
+
+skip:
+	/* set up possible led control from mixer private data */
+	ret = sof_parse_tokens(scomp, &scontrol->led_ctl, led_tokens,
+			       ARRAY_SIZE(led_tokens), mc->priv.array,
+			       le32_to_cpu(mc->priv.size));
+	if (ret != 0) {
+		dev_err(sdev->dev, "error: parse led tokens failed %d\n",
+			le32_to_cpu(mc->priv.size));
+		goto out_free_table;
+	}
+
+	dev_dbg(sdev->dev, "tplg: load kcontrol index %d chans %d\n",
+		scontrol->comp_id, scontrol->num_channels);
+
+	return ret;
+
+out_free_table:
+	if (le32_to_cpu(mc->max) > 1)
+		kfree(scontrol->volume_table);
+out_free:
+	kfree(scontrol->control_data);
+out:
+	return ret;
+}
+
+static int sof_control_load_enum(struct snd_soc_component *scomp,
+				 struct snd_sof_control *scontrol,
+				 struct snd_kcontrol_new *kc,
+				 struct snd_soc_tplg_ctl_hdr *hdr)
+{
+	struct snd_sof_dev *sdev = snd_soc_component_get_drvdata(scomp);
+	struct snd_soc_tplg_enum_control *ec =
+		container_of(hdr, struct snd_soc_tplg_enum_control, hdr);
+
+	/* validate topology data */
+	if (le32_to_cpu(ec->num_channels) > SND_SOC_TPLG_MAX_CHAN)
+		return -EINVAL;
+
+	/* init the enum get/put data */
+	scontrol->size = struct_size(scontrol->control_data, chanv,
+				     le32_to_cpu(ec->num_channels));
+	scontrol->control_data = kzalloc(scontrol->size, GFP_KERNEL);
+	if (!scontrol->control_data)
+		return -ENOMEM;
+
+	scontrol->comp_id = sdev->next_comp_id;
+	scontrol->num_channels = le32_to_cpu(ec->num_channels);
+
+	scontrol->cmd = SOF_CTRL_CMD_ENUM;
+
+	dev_dbg(sdev->dev, "tplg: load kcontrol index %d chans %d comp_id %d\n",
+		scontrol->comp_id, scontrol->num_channels, scontrol->comp_id);
+
+	return 0;
+}
+
+static int sof_control_load_bytes(struct snd_soc_component *scomp,
+				  struct snd_sof_control *scontrol,
+				  struct snd_kcontrol_new *kc,
+				  struct snd_soc_tplg_ctl_hdr *hdr)
+{
+	struct snd_sof_dev *sdev = snd_soc_component_get_drvdata(scomp);
+	struct sof_ipc_ctrl_data *cdata;
+	struct snd_soc_tplg_bytes_control *control =
+		container_of(hdr, struct snd_soc_tplg_bytes_control, hdr);
+	struct soc_bytes_ext *sbe = (struct soc_bytes_ext *)kc->private_value;
+	int max_size = sbe->max;
+	int ret = 0;
+
+	/* init the get/put bytes data */
+	scontrol->size = sizeof(struct sof_ipc_ctrl_data) +
+		le32_to_cpu(control->priv.size);
+
+	if (scontrol->size > max_size) {
+		dev_err(sdev->dev, "err: bytes data size %d exceeds max %d.\n",
+			scontrol->size, max_size);
+		ret = -EINVAL;
+		goto out;
+	}
+
+	scontrol->control_data = kzalloc(max_size, GFP_KERNEL);
+	cdata = scontrol->control_data;
+	if (!scontrol->control_data) {
+		ret = -ENOMEM;
+		goto out;
+	}
+
+	scontrol->comp_id = sdev->next_comp_id;
+	scontrol->cmd = SOF_CTRL_CMD_BINARY;
+
+	dev_dbg(sdev->dev, "tplg: load kcontrol index %d chans %d\n",
+		scontrol->comp_id, scontrol->num_channels);
+
+	if (le32_to_cpu(control->priv.size) > 0) {
+		memcpy(cdata->data, control->priv.data,
+		       le32_to_cpu(control->priv.size));
+
+		if (cdata->data->magic != SOF_ABI_MAGIC) {
+			dev_err(sdev->dev, "error: Wrong ABI magic 0x%08x.\n",
+				cdata->data->magic);
+			ret = -EINVAL;
+			goto out_free;
+		}
+		if (SOF_ABI_VERSION_INCOMPATIBLE(SOF_ABI_VERSION,
+						 cdata->data->abi)) {
+			dev_err(sdev->dev,
+				"error: Incompatible ABI version 0x%08x.\n",
+				cdata->data->abi);
+			ret = -EINVAL;
+			goto out_free;
+		}
+		if (cdata->data->size + sizeof(const struct sof_abi_hdr) !=
+		    le32_to_cpu(control->priv.size)) {
+			dev_err(sdev->dev,
+				"error: Conflict in bytes vs. priv size.\n");
+			ret = -EINVAL;
+			goto out_free;
+		}
+	}
+
+	return ret;
+
+out_free:
+	kfree(scontrol->control_data);
+out:
+	return ret;
+}
+
 /* external kcontrol init - used for any driver specific init */
 static int sof_control_load(struct snd_soc_component *scomp, int index,
 			    struct snd_kcontrol_new *kc,
@@ -1095,6 +1176,11 @@ static int sof_control_load(struct snd_soc_component *scomp, int index,
 		return 0;
 	}
 
+	if (ret < 0) {
+		kfree(scontrol);
+		return ret;
+	}
+
 	dobj->private = scontrol;
 	list_add(&scontrol->list, &sdev->kcontrol_list);
 	return ret;
@@ -1581,7 +1667,7 @@ static int sof_widget_load_pga(struct snd_soc_component *scomp, int index,
 	if (!volume)
 		return -ENOMEM;
 
-	if (le32_to_cpu(tw->num_kcontrols) != 1) {
+	if (!le32_to_cpu(tw->num_kcontrols)) {
 		dev_err(sdev->dev, "error: invalid kcontrol count %d for volume\n",
 			tw->num_kcontrols);
 		ret = -EINVAL;
@@ -1618,7 +1704,8 @@ static int sof_widget_load_pga(struct snd_soc_component *scomp, int index,
 	swidget->private = volume;
 
 	list_for_each_entry(scontrol, &sdev->kcontrol_list, list) {
-		if (scontrol->comp_id == swidget->comp_id) {
+		if (scontrol->comp_id == swidget->comp_id &&
+		    scontrol->volume_table) {
 			min_step = scontrol->min_volume_step;
 			max_step = scontrol->max_volume_step;
 			volume->min_value = scontrol->volume_table[min_step];
@@ -2272,6 +2359,7 @@ static int sof_dai_load(struct snd_soc_component *scomp, int index,
 {
 	struct snd_sof_dev *sdev = snd_soc_component_get_drvdata(scomp);
 	struct snd_soc_tplg_stream_caps *caps;
+	struct snd_soc_tplg_private *private = &pcm->priv;
 	struct snd_sof_pcm *spcm;
 	int stream = SNDRV_PCM_STREAM_PLAYBACK;
 	int ret = 0;
@@ -2288,17 +2376,28 @@ static int sof_dai_load(struct snd_soc_component *scomp, int index,
 	spcm->stream[SNDRV_PCM_STREAM_PLAYBACK].comp_id = COMP_ID_UNASSIGNED;
 	spcm->stream[SNDRV_PCM_STREAM_CAPTURE].comp_id = COMP_ID_UNASSIGNED;
 
-	if (pcm) {
-		spcm->pcm = *pcm;
-		dev_dbg(sdev->dev, "tplg: load pcm %s\n", pcm->dai_name);
-	}
+	spcm->pcm = *pcm;
+	dev_dbg(sdev->dev, "tplg: load pcm %s\n", pcm->dai_name);
+
 	dai_drv->dobj.private = spcm;
 	list_add(&spcm->list, &sdev->pcm_list);
 
+	ret = sof_parse_tokens(scomp, spcm, stream_tokens,
+			       ARRAY_SIZE(stream_tokens), private->array,
+			       le32_to_cpu(private->size));
+	if (ret) {
+		dev_err(sdev->dev, "error: parse stream tokens failed %d\n",
+			le32_to_cpu(private->size));
+		return ret;
+	}
+
 	/* do we need to allocate playback PCM DMA pages */
 	if (!spcm->pcm.playback)
 		goto capture;
 
+	dev_vdbg(sdev->dev, "tplg: pcm %s stream tokens: playback d0i3:%d\n",
+		 spcm->pcm.pcm_name, spcm->stream[0].d0i3_compatible);
+
 	caps = &spcm->pcm.caps[stream];
 
 	/* allocate playback page table buffer */
@@ -2326,6 +2425,9 @@ capture:
 	if (!spcm->pcm.capture)
 		return ret;
 
+	dev_vdbg(sdev->dev, "tplg: pcm %s stream tokens: capture d0i3:%d\n",
+		 spcm->pcm.pcm_name, spcm->stream[1].d0i3_compatible);
+
 	caps = &spcm->pcm.caps[stream];
 
 	/* allocate capture page table buffer */
@@ -2536,8 +2638,66 @@ static int sof_link_esai_load(struct snd_soc_component *scomp, int index,
 			      struct snd_soc_tplg_hw_config *hw_config,
 			      struct sof_ipc_dai_config *config)
 {
-	/*TODO: Add implementation */
-	return 0;
+	struct snd_sof_dev *sdev = snd_soc_component_get_drvdata(scomp);
+	struct snd_soc_tplg_private *private = &cfg->priv;
+	struct sof_ipc_reply reply;
+	u32 size = sizeof(*config);
+	int ret;
+
+	/* handle master/slave and inverted clocks */
+	sof_dai_set_format(hw_config, config);
+
+	/* init IPC */
+	memset(&config->esai, 0, sizeof(struct sof_ipc_dai_esai_params));
+	config->hdr.size = size;
+
+	ret = sof_parse_tokens(scomp, &config->esai, esai_tokens,
+			       ARRAY_SIZE(esai_tokens), private->array,
+			       le32_to_cpu(private->size));
+	if (ret != 0) {
+		dev_err(sdev->dev, "error: parse esai tokens failed %d\n",
+			le32_to_cpu(private->size));
+		return ret;
+	}
+
+	config->esai.mclk_rate = le32_to_cpu(hw_config->mclk_rate);
+	config->esai.bclk_rate = le32_to_cpu(hw_config->bclk_rate);
+	config->esai.fsync_rate = le32_to_cpu(hw_config->fsync_rate);
+	config->esai.mclk_direction = hw_config->mclk_direction;
+	config->esai.tdm_slots = le32_to_cpu(hw_config->tdm_slots);
+	config->esai.tdm_slot_width = le32_to_cpu(hw_config->tdm_slot_width);
+	config->esai.rx_slots = le32_to_cpu(hw_config->rx_slots);
+	config->esai.tx_slots = le32_to_cpu(hw_config->tx_slots);
+
+	dev_info(sdev->dev,
+		 "tplg: config ESAI%d fmt 0x%x mclk %d width %d slots %d mclk id %d\n",
+		config->dai_index, config->format,
+		config->esai.mclk_rate, config->esai.tdm_slot_width,
+		config->esai.tdm_slots, config->esai.mclk_id);
+
+	if (config->esai.tdm_slots < 1 || config->esai.tdm_slots > 8) {
+		dev_err(sdev->dev, "error: invalid channel count for ESAI%d\n",
+			config->dai_index);
+		return -EINVAL;
+	}
+
+	/* send message to DSP */
+	ret = sof_ipc_tx_message(sdev->ipc,
+				 config->hdr.cmd, config, size, &reply,
+				 sizeof(reply));
+	if (ret < 0) {
+		dev_err(sdev->dev, "error: failed to set DAI config for ESAI%d\n",
+			config->dai_index);
+		return ret;
+	}
+
+	/* set config for all DAI's with name matching the link name */
+	ret = sof_set_dai_config(sdev, size, link, config);
+	if (ret < 0)
+		dev_err(sdev->dev, "error: failed to save DAI config for ESAI%d\n",
+			config->dai_index);
+
+	return ret;
 }
 
 static int sof_link_dmic_load(struct snd_soc_component *scomp, int index,
@@ -2828,6 +2988,10 @@ static int sof_link_load(struct snd_soc_component *scomp, int index,
 	if (!link->no_pcm) {
 		link->nonatomic = true;
 
+		/* set trigger order */
+		link->trigger[0] = SND_SOC_DPCM_TRIGGER_POST;
+		link->trigger[1] = SND_SOC_DPCM_TRIGGER_POST;
+
 		/* nothing more to do for FE dai links */
 		return 0;
 	}
diff --git a/sound/soc/sof/trace.c b/sound/soc/sof/trace.c
index 4c3cff031fd6..b0e4556c8536 100644
--- a/sound/soc/sof/trace.c
+++ b/sound/soc/sof/trace.c
@@ -162,6 +162,9 @@ int snd_sof_init_trace_ipc(struct snd_sof_dev *sdev)
 	struct sof_ipc_reply ipc_reply;
 	int ret;
 
+	if (!sdev->dtrace_is_supported)
+		return 0;
+
 	if (sdev->dtrace_is_enabled || !sdev->dma_trace_pages)
 		return -EINVAL;
 
@@ -222,6 +225,9 @@ int snd_sof_init_trace(struct snd_sof_dev *sdev)
 {
 	int ret;
 
+	if (!sdev->dtrace_is_supported)
+		return 0;
+
 	/* set false before start initialization */
 	sdev->dtrace_is_enabled = false;
 
@@ -277,6 +283,9 @@ EXPORT_SYMBOL(snd_sof_init_trace);
 int snd_sof_trace_update_pos(struct snd_sof_dev *sdev,
 			     struct sof_ipc_dma_trace_posn *posn)
 {
+	if (!sdev->dtrace_is_supported)
+		return 0;
+
 	if (sdev->dtrace_is_enabled && sdev->host_offset != posn->host_offset) {
 		sdev->host_offset = posn->host_offset;
 		wake_up(&sdev->trace_sleep);
@@ -293,6 +302,9 @@ int snd_sof_trace_update_pos(struct snd_sof_dev *sdev,
 /* an error has occurred within the DSP that prevents further trace */
 void snd_sof_trace_notify_for_error(struct snd_sof_dev *sdev)
 {
+	if (!sdev->dtrace_is_supported)
+		return;
+
 	if (sdev->dtrace_is_enabled) {
 		dev_err(sdev->dev, "error: waking up any trace sleepers\n");
 		sdev->dtrace_error = true;
@@ -305,7 +317,7 @@ void snd_sof_release_trace(struct snd_sof_dev *sdev)
 {
 	int ret;
 
-	if (!sdev->dtrace_is_enabled)
+	if (!sdev->dtrace_is_supported || !sdev->dtrace_is_enabled)
 		return;
 
 	ret = snd_sof_dma_trace_trigger(sdev, SNDRV_PCM_TRIGGER_STOP);
@@ -326,6 +338,9 @@ EXPORT_SYMBOL(snd_sof_release_trace);
 
 void snd_sof_free_trace(struct snd_sof_dev *sdev)
 {
+	if (!sdev->dtrace_is_supported)
+		return;
+
 	snd_sof_release_trace(sdev);
 
 	snd_dma_free_pages(&sdev->dmatb);
diff --git a/sound/soc/sprd/sprd-pcm-dma.c b/sound/soc/sprd/sprd-pcm-dma.c
index d38ebbbbf169..da4b8f5f192b 100644
--- a/sound/soc/sprd/sprd-pcm-dma.c
+++ b/sound/soc/sprd/sprd-pcm-dma.c
@@ -46,12 +46,10 @@ static const struct snd_pcm_hardware sprd_pcm_hardware = {
 	.buffer_bytes_max = 64 * 1024,
 };
 
-static int sprd_pcm_open(struct snd_pcm_substream *substream)
+static int sprd_pcm_open(struct snd_soc_component *component,
+			 struct snd_pcm_substream *substream)
 {
 	struct snd_pcm_runtime *runtime = substream->runtime;
-	struct snd_soc_pcm_runtime *rtd = substream->private_data;
-	struct snd_soc_component *component =
-		snd_soc_rtdcom_lookup(rtd, DRV_NAME);
 	struct device *dev = component->dev;
 	struct sprd_pcm_dma_private *dma_private;
 	int hw_chan = SPRD_PCM_CHANNEL_MAX;
@@ -111,13 +109,11 @@ error:
 	return ret;
 }
 
-static int sprd_pcm_close(struct snd_pcm_substream *substream)
+static int sprd_pcm_close(struct snd_soc_component *component,
+			  struct snd_pcm_substream *substream)
 {
 	struct snd_pcm_runtime *runtime = substream->runtime;
-	struct snd_soc_pcm_runtime *rtd = substream->private_data;
 	struct sprd_pcm_dma_private *dma_private = runtime->private_data;
-	struct snd_soc_component *component =
-		snd_soc_rtdcom_lookup(rtd, DRV_NAME);
 	struct device *dev = component->dev;
 	int size = runtime->hw.periods_max * SPRD_PCM_DMA_LINKLIST_SIZE;
 	int i;
@@ -157,14 +153,12 @@ static void sprd_pcm_release_dma_channel(struct snd_pcm_substream *substream)
 	}
 }
 
-static int sprd_pcm_request_dma_channel(struct snd_pcm_substream *substream,
+static int sprd_pcm_request_dma_channel(struct snd_soc_component *component,
+					struct snd_pcm_substream *substream,
 					int channels)
 {
 	struct snd_pcm_runtime *runtime = substream->runtime;
 	struct sprd_pcm_dma_private *dma_private = runtime->private_data;
-	struct snd_soc_pcm_runtime *rtd = substream->private_data;
-	struct snd_soc_component *component =
-		snd_soc_rtdcom_lookup(rtd, DRV_NAME);
 	struct device *dev = component->dev;
 	struct sprd_pcm_dma_params *dma_params = dma_private->params;
 	int i;
@@ -190,14 +184,13 @@ static int sprd_pcm_request_dma_channel(struct snd_pcm_substream *substream,
 	return 0;
 }
 
-static int sprd_pcm_hw_params(struct snd_pcm_substream *substream,
+static int sprd_pcm_hw_params(struct snd_soc_component *component,
+			      struct snd_pcm_substream *substream,
 			      struct snd_pcm_hw_params *params)
 {
 	struct snd_pcm_runtime *runtime = substream->runtime;
 	struct sprd_pcm_dma_private *dma_private = runtime->private_data;
 	struct snd_soc_pcm_runtime *rtd = substream->private_data;
-	struct snd_soc_component *component =
-		snd_soc_rtdcom_lookup(rtd, DRV_NAME);
 	struct sprd_pcm_dma_params *dma_params;
 	size_t totsize = params_buffer_bytes(params);
 	size_t period = params_period_bytes(params);
@@ -218,7 +211,8 @@ static int sprd_pcm_hw_params(struct snd_pcm_substream *substream,
 
 	if (!dma_private->params) {
 		dma_private->params = dma_params;
-		ret = sprd_pcm_request_dma_channel(substream, channels);
+		ret = sprd_pcm_request_dma_channel(component,
+						   substream, channels);
 		if (ret)
 			return ret;
 	}
@@ -313,7 +307,8 @@ sg_err:
 	return ret;
 }
 
-static int sprd_pcm_hw_free(struct snd_pcm_substream *substream)
+static int sprd_pcm_hw_free(struct snd_soc_component *component,
+			    struct snd_pcm_substream *substream)
 {
 	snd_pcm_set_runtime_buffer(substream, NULL);
 	sprd_pcm_release_dma_channel(substream);
@@ -321,13 +316,11 @@ static int sprd_pcm_hw_free(struct snd_pcm_substream *substream)
 	return 0;
 }
 
-static int sprd_pcm_trigger(struct snd_pcm_substream *substream, int cmd)
+static int sprd_pcm_trigger(struct snd_soc_component *component,
+			    struct snd_pcm_substream *substream, int cmd)
 {
 	struct sprd_pcm_dma_private *dma_private =
 		substream->runtime->private_data;
-	struct snd_soc_pcm_runtime *rtd = substream->private_data;
-	struct snd_soc_component *component =
-		snd_soc_rtdcom_lookup(rtd, DRV_NAME);
 	int ret = 0, i;
 
 	switch (cmd) {
@@ -387,13 +380,11 @@ static int sprd_pcm_trigger(struct snd_pcm_substream *substream, int cmd)
 	return ret;
 }
 
-static snd_pcm_uframes_t sprd_pcm_pointer(struct snd_pcm_substream *substream)
+static snd_pcm_uframes_t sprd_pcm_pointer(struct snd_soc_component *component,
+					  struct snd_pcm_substream *substream)
 {
 	struct snd_pcm_runtime *runtime = substream->runtime;
-	struct snd_soc_pcm_runtime *rtd = substream->private_data;
 	struct sprd_pcm_dma_private *dma_private = runtime->private_data;
-	struct snd_soc_component *component =
-		snd_soc_rtdcom_lookup(rtd, DRV_NAME);
 	int pointer[SPRD_PCM_CHANNEL_MAX];
 	int bytes_of_pointer = 0, sel_max = 0, i;
 	snd_pcm_uframes_t x;
@@ -444,7 +435,8 @@ static snd_pcm_uframes_t sprd_pcm_pointer(struct snd_pcm_substream *substream)
 	return x;
 }
 
-static int sprd_pcm_mmap(struct snd_pcm_substream *substream,
+static int sprd_pcm_mmap(struct snd_soc_component *component,
+			 struct snd_pcm_substream *substream,
 			 struct vm_area_struct *vma)
 {
 	struct snd_pcm_runtime *runtime = substream->runtime;
@@ -456,18 +448,8 @@ static int sprd_pcm_mmap(struct snd_pcm_substream *substream,
 			       vma->vm_page_prot);
 }
 
-static struct snd_pcm_ops sprd_pcm_ops = {
-	.open = sprd_pcm_open,
-	.close = sprd_pcm_close,
-	.ioctl = snd_pcm_lib_ioctl,
-	.hw_params = sprd_pcm_hw_params,
-	.hw_free = sprd_pcm_hw_free,
-	.trigger = sprd_pcm_trigger,
-	.pointer = sprd_pcm_pointer,
-	.mmap = sprd_pcm_mmap,
-};
-
-static int sprd_pcm_new(struct snd_soc_pcm_runtime *rtd)
+static int sprd_pcm_new(struct snd_soc_component *component,
+			struct snd_soc_pcm_runtime *rtd)
 {
 	struct snd_card *card = rtd->card->snd_card;
 	struct snd_pcm *pcm = rtd->pcm;
@@ -506,7 +488,8 @@ static int sprd_pcm_new(struct snd_soc_pcm_runtime *rtd)
 	return 0;
 }
 
-static void sprd_pcm_free(struct snd_pcm *pcm)
+static void sprd_pcm_free(struct snd_soc_component *component,
+			  struct snd_pcm *pcm)
 {
 	struct snd_pcm_substream *substream;
 	int i;
@@ -523,10 +506,17 @@ static void sprd_pcm_free(struct snd_pcm *pcm)
 
 static const struct snd_soc_component_driver sprd_soc_component = {
 	.name		= DRV_NAME,
-	.ops		= &sprd_pcm_ops,
+	.open		= sprd_pcm_open,
+	.close		= sprd_pcm_close,
+	.ioctl		= snd_soc_pcm_lib_ioctl,
+	.hw_params	= sprd_pcm_hw_params,
+	.hw_free	= sprd_pcm_hw_free,
+	.trigger	= sprd_pcm_trigger,
+	.pointer	= sprd_pcm_pointer,
+	.mmap		= sprd_pcm_mmap,
+	.pcm_construct	= sprd_pcm_new,
+	.pcm_destruct	= sprd_pcm_free,
 	.compr_ops	= &sprd_platform_compr_ops,
-	.pcm_new	= sprd_pcm_new,
-	.pcm_free	= sprd_pcm_free,
 };
 
 static int sprd_soc_platform_probe(struct platform_device *pdev)
diff --git a/sound/soc/stm/stm32_adfsdm.c b/sound/soc/stm/stm32_adfsdm.c
index 3c9a9deec9af..81c407da15c5 100644
--- a/sound/soc/stm/stm32_adfsdm.c
+++ b/sound/soc/stm/stm32_adfsdm.c
@@ -210,7 +210,8 @@ static int stm32_afsdm_pcm_cb(const void *data, size_t size, void *private)
 	return 0;
 }
 
-static int stm32_adfsdm_trigger(struct snd_pcm_substream *substream, int cmd)
+static int stm32_adfsdm_trigger(struct snd_soc_component *component,
+				struct snd_pcm_substream *substream, int cmd)
 {
 	struct snd_soc_pcm_runtime *rtd = substream->private_data;
 	struct stm32_adfsdm_priv *priv =
@@ -230,7 +231,8 @@ static int stm32_adfsdm_trigger(struct snd_pcm_substream *substream, int cmd)
 	return -EINVAL;
 }
 
-static int stm32_adfsdm_pcm_open(struct snd_pcm_substream *substream)
+static int stm32_adfsdm_pcm_open(struct snd_soc_component *component,
+				 struct snd_pcm_substream *substream)
 {
 	struct snd_soc_pcm_runtime *rtd = substream->private_data;
 	struct stm32_adfsdm_priv *priv = snd_soc_dai_get_drvdata(rtd->cpu_dai);
@@ -243,7 +245,8 @@ static int stm32_adfsdm_pcm_open(struct snd_pcm_substream *substream)
 	return ret;
 }
 
-static int stm32_adfsdm_pcm_close(struct snd_pcm_substream *substream)
+static int stm32_adfsdm_pcm_close(struct snd_soc_component *component,
+				  struct snd_pcm_substream *substream)
 {
 	struct snd_soc_pcm_runtime *rtd = substream->private_data;
 	struct stm32_adfsdm_priv *priv =
@@ -256,6 +259,7 @@ static int stm32_adfsdm_pcm_close(struct snd_pcm_substream *substream)
 }
 
 static snd_pcm_uframes_t stm32_adfsdm_pcm_pointer(
+					    struct snd_soc_component *component,
 					    struct snd_pcm_substream *substream)
 {
 	struct snd_soc_pcm_runtime *rtd = substream->private_data;
@@ -265,7 +269,8 @@ static snd_pcm_uframes_t stm32_adfsdm_pcm_pointer(
 	return bytes_to_frames(substream->runtime, priv->pos);
 }
 
-static int stm32_adfsdm_pcm_hw_params(struct snd_pcm_substream *substream,
+static int stm32_adfsdm_pcm_hw_params(struct snd_soc_component *component,
+				      struct snd_pcm_substream *substream,
 				      struct snd_pcm_hw_params *params)
 {
 	struct snd_soc_pcm_runtime *rtd = substream->private_data;
@@ -282,23 +287,16 @@ static int stm32_adfsdm_pcm_hw_params(struct snd_pcm_substream *substream,
 						   params_period_size(params));
 }
 
-static int stm32_adfsdm_pcm_hw_free(struct snd_pcm_substream *substream)
+static int stm32_adfsdm_pcm_hw_free(struct snd_soc_component *component,
+				    struct snd_pcm_substream *substream)
 {
 	snd_pcm_lib_free_pages(substream);
 
 	return 0;
 }
 
-static struct snd_pcm_ops stm32_adfsdm_pcm_ops = {
-	.open		= stm32_adfsdm_pcm_open,
-	.close		= stm32_adfsdm_pcm_close,
-	.hw_params	= stm32_adfsdm_pcm_hw_params,
-	.hw_free	= stm32_adfsdm_pcm_hw_free,
-	.trigger	= stm32_adfsdm_trigger,
-	.pointer	= stm32_adfsdm_pcm_pointer,
-};
-
-static int stm32_adfsdm_pcm_new(struct snd_soc_pcm_runtime *rtd)
+static int stm32_adfsdm_pcm_new(struct snd_soc_component *component,
+				struct snd_soc_pcm_runtime *rtd)
 {
 	struct snd_pcm *pcm = rtd->pcm;
 	struct stm32_adfsdm_priv *priv =
@@ -310,7 +308,8 @@ static int stm32_adfsdm_pcm_new(struct snd_soc_pcm_runtime *rtd)
 	return 0;
 }
 
-static void stm32_adfsdm_pcm_free(struct snd_pcm *pcm)
+static void stm32_adfsdm_pcm_free(struct snd_soc_component *component,
+				  struct snd_pcm *pcm)
 {
 	struct snd_pcm_substream *substream;
 
@@ -320,9 +319,14 @@ static void stm32_adfsdm_pcm_free(struct snd_pcm *pcm)
 }
 
 static struct snd_soc_component_driver stm32_adfsdm_soc_platform = {
-	.ops		= &stm32_adfsdm_pcm_ops,
-	.pcm_new	= stm32_adfsdm_pcm_new,
-	.pcm_free	= stm32_adfsdm_pcm_free,
+	.open		= stm32_adfsdm_pcm_open,
+	.close		= stm32_adfsdm_pcm_close,
+	.hw_params	= stm32_adfsdm_pcm_hw_params,
+	.hw_free	= stm32_adfsdm_pcm_hw_free,
+	.trigger	= stm32_adfsdm_trigger,
+	.pointer	= stm32_adfsdm_pcm_pointer,
+	.pcm_construct	= stm32_adfsdm_pcm_new,
+	.pcm_destruct	= stm32_adfsdm_pcm_free,
 };
 
 static const struct of_device_id stm32_adfsdm_of_match[] = {
diff --git a/sound/soc/stm/stm32_sai.c b/sound/soc/stm/stm32_sai.c
index ef4273361d0d..e20267504b16 100644
--- a/sound/soc/stm/stm32_sai.c
+++ b/sound/soc/stm/stm32_sai.c
@@ -100,7 +100,7 @@ static int stm32_sai_sync_conf_provider(struct stm32_sai_data *sai, int synco)
 		dev_err(&sai->pdev->dev, "%pOFn%s already set as sync provider\n",
 			sai->pdev->dev.of_node,
 			prev_synco == STM_SAI_SYNC_OUT_A ? "A" : "B");
-			stm32_sai_pclk_disable(&sai->pdev->dev);
+		stm32_sai_pclk_disable(&sai->pdev->dev);
 		return -EINVAL;
 	}
 
diff --git a/sound/soc/stm/stm32_spdifrx.c b/sound/soc/stm/stm32_spdifrx.c
index cd4b235fce57..3fd28ee01675 100644
--- a/sound/soc/stm/stm32_spdifrx.c
+++ b/sound/soc/stm/stm32_spdifrx.c
@@ -351,6 +351,8 @@ static int stm32_spdifrx_start_sync(struct stm32_spdifrx_data *spdifrx)
 		     SPDIFRX_CR_CUMSK | SPDIFRX_CR_PTMSK | SPDIFRX_CR_RXSTEO;
 		cr_mask = cr;
 
+		cr |= SPDIFRX_CR_NBTRSET(SPDIFRX_NBTR_63);
+		cr_mask |= SPDIFRX_CR_NBTR_MASK;
 		cr |= SPDIFRX_CR_SPDIFENSET(SPDIFRX_SPDIFEN_SYNC);
 		cr_mask |= SPDIFRX_CR_SPDIFEN_MASK;
 		ret = regmap_update_bits(spdifrx->regmap, STM32_SPDIFRX_CR,
@@ -666,7 +668,7 @@ static irqreturn_t stm32_spdifrx_isr(int irq, void *devid)
 	struct snd_pcm_substream *substream = spdifrx->substream;
 	struct platform_device *pdev = spdifrx->pdev;
 	unsigned int cr, mask, sr, imr;
-	unsigned int flags;
+	unsigned int flags, sync_state;
 	int err = 0, err_xrun = 0;
 
 	regmap_read(spdifrx->regmap, STM32_SPDIFRX_SR, &sr);
@@ -726,11 +728,23 @@ static irqreturn_t stm32_spdifrx_isr(int irq, void *devid)
 	}
 
 	if (err) {
-		/* SPDIFRX in STATE_STOP. Disable SPDIFRX to clear errors */
+		regmap_read(spdifrx->regmap, STM32_SPDIFRX_CR, &cr);
+		sync_state = FIELD_GET(SPDIFRX_CR_SPDIFEN_MASK, cr) &&
+			     SPDIFRX_SPDIFEN_SYNC;
+
+		/* SPDIFRX is in STATE_STOP. Disable SPDIFRX to clear errors */
 		cr = SPDIFRX_CR_SPDIFENSET(SPDIFRX_SPDIFEN_DISABLE);
 		regmap_update_bits(spdifrx->regmap, STM32_SPDIFRX_CR,
 				   SPDIFRX_CR_SPDIFEN_MASK, cr);
 
+		/* If SPDIFRX was in STATE_SYNC, retry synchro */
+		if (sync_state) {
+			cr = SPDIFRX_CR_SPDIFENSET(SPDIFRX_SPDIFEN_SYNC);
+			regmap_update_bits(spdifrx->regmap, STM32_SPDIFRX_CR,
+					   SPDIFRX_CR_SPDIFEN_MASK, cr);
+			return IRQ_HANDLED;
+		}
+
 		if (substream)
 			snd_pcm_stop(substream, SNDRV_PCM_STATE_DISCONNECTED);
 
diff --git a/sound/soc/sunxi/sun4i-codec.c b/sound/soc/sunxi/sun4i-codec.c
index ee448d5e07a6..34f3e0be3058 100644
--- a/sound/soc/sunxi/sun4i-codec.c
+++ b/sound/soc/sunxi/sun4i-codec.c
@@ -1442,7 +1442,7 @@ static struct snd_soc_card *sun8i_a23_codec_create_card(struct device *dev)
 	if (!aux_dev.dlc.of_node) {
 		dev_err(dev, "Can't find analog controls for codec.\n");
 		return ERR_PTR(-EINVAL);
-	};
+	}
 
 	card->dai_link = sun4i_codec_create_link(dev, &card->num_links);
 	if (!card->dai_link)
@@ -1480,7 +1480,7 @@ static struct snd_soc_card *sun8i_h3_codec_create_card(struct device *dev)
 	if (!aux_dev.dlc.of_node) {
 		dev_err(dev, "Can't find analog controls for codec.\n");
 		return ERR_PTR(-EINVAL);
-	};
+	}
 
 	card->dai_link = sun4i_codec_create_link(dev, &card->num_links);
 	if (!card->dai_link)
@@ -1518,7 +1518,7 @@ static struct snd_soc_card *sun8i_v3s_codec_create_card(struct device *dev)
 	if (!aux_dev.dlc.of_node) {
 		dev_err(dev, "Can't find analog controls for codec.\n");
 		return ERR_PTR(-EINVAL);
-	};
+	}
 
 	card->dai_link = sun4i_codec_create_link(dev, &card->num_links);
 	if (!card->dai_link)
diff --git a/sound/soc/tegra/tegra30_i2s.c b/sound/soc/tegra/tegra30_i2s.c
index e6d548fa980b..dbed3c5408e7 100644
--- a/sound/soc/tegra/tegra30_i2s.c
+++ b/sound/soc/tegra/tegra30_i2s.c
@@ -127,7 +127,7 @@ static int tegra30_i2s_hw_params(struct snd_pcm_substream *substream,
 	struct device *dev = dai->dev;
 	struct tegra30_i2s *i2s = snd_soc_dai_get_drvdata(dai);
 	unsigned int mask, val, reg;
-	int ret, sample_size, srate, i2sclock, bitcnt;
+	int ret, sample_size, srate, i2sclock, bitcnt, audio_bits;
 	struct tegra30_ahub_cif_conf cif_conf;
 
 	if (params_channels(params) != 2)
@@ -137,8 +137,19 @@ static int tegra30_i2s_hw_params(struct snd_pcm_substream *substream,
 	switch (params_format(params)) {
 	case SNDRV_PCM_FORMAT_S16_LE:
 		val = TEGRA30_I2S_CTRL_BIT_SIZE_16;
+		audio_bits = TEGRA30_AUDIOCIF_BITS_16;
 		sample_size = 16;
 		break;
+	case SNDRV_PCM_FORMAT_S24_LE:
+		val = TEGRA30_I2S_CTRL_BIT_SIZE_24;
+		audio_bits = TEGRA30_AUDIOCIF_BITS_24;
+		sample_size = 24;
+		break;
+	case SNDRV_PCM_FORMAT_S32_LE:
+		val = TEGRA30_I2S_CTRL_BIT_SIZE_32;
+		audio_bits = TEGRA30_AUDIOCIF_BITS_32;
+		sample_size = 32;
+		break;
 	default:
 		return -EINVAL;
 	}
@@ -170,8 +181,8 @@ static int tegra30_i2s_hw_params(struct snd_pcm_substream *substream,
 	cif_conf.threshold = 0;
 	cif_conf.audio_channels = 2;
 	cif_conf.client_channels = 2;
-	cif_conf.audio_bits = TEGRA30_AUDIOCIF_BITS_16;
-	cif_conf.client_bits = TEGRA30_AUDIOCIF_BITS_16;
+	cif_conf.audio_bits = audio_bits;
+	cif_conf.client_bits = audio_bits;
 	cif_conf.expand = 0;
 	cif_conf.stereo_conv = 0;
 	cif_conf.replicate = 0;
@@ -220,9 +231,9 @@ static void tegra30_i2s_start_capture(struct tegra30_i2s *i2s)
 
 static void tegra30_i2s_stop_capture(struct tegra30_i2s *i2s)
 {
-	tegra30_ahub_disable_rx_fifo(i2s->capture_fifo_cif);
 	regmap_update_bits(i2s->regmap, TEGRA30_I2S_CTRL,
 			   TEGRA30_I2S_CTRL_XFER_EN_RX, 0);
+	tegra30_ahub_disable_rx_fifo(i2s->capture_fifo_cif);
 }
 
 static int tegra30_i2s_trigger(struct snd_pcm_substream *substream, int cmd,
@@ -254,6 +265,34 @@ static int tegra30_i2s_trigger(struct snd_pcm_substream *substream, int cmd,
 	return 0;
 }
 
+static int tegra30_i2s_set_tdm(struct snd_soc_dai *dai,
+			       unsigned int tx_mask, unsigned int rx_mask,
+			       int slots, int slot_width)
+{
+	struct tegra30_i2s *i2s = snd_soc_dai_get_drvdata(dai);
+	unsigned int mask, val;
+
+	dev_dbg(dai->dev, "%s: txmask=0x%08x rxmask=0x%08x slots=%d width=%d\n",
+		 __func__, tx_mask, rx_mask, slots, slot_width);
+
+	mask = TEGRA30_I2S_SLOT_CTRL_TOTAL_SLOTS_MASK |
+	       TEGRA30_I2S_SLOT_CTRL_RX_SLOT_ENABLES_MASK |
+	       TEGRA30_I2S_SLOT_CTRL_TX_SLOT_ENABLES_MASK;
+
+	val = (tx_mask << TEGRA30_I2S_SLOT_CTRL_TX_SLOT_ENABLES_SHIFT) |
+	      (rx_mask << TEGRA30_I2S_SLOT_CTRL_RX_SLOT_ENABLES_SHIFT) |
+	      ((slots - 1) << TEGRA30_I2S_SLOT_CTRL_TOTAL_SLOTS_SHIFT);
+
+	pm_runtime_get_sync(dai->dev);
+	regmap_update_bits(i2s->regmap, TEGRA30_I2S_SLOT_CTRL, mask, val);
+	/* set the fsync width to minimum of 1 clock width */
+	regmap_update_bits(i2s->regmap, TEGRA30_I2S_CH_CTRL,
+			   TEGRA30_I2S_CH_CTRL_FSYNC_WIDTH_MASK, 0x0);
+	pm_runtime_put(dai->dev);
+
+	return 0;
+}
+
 static int tegra30_i2s_probe(struct snd_soc_dai *dai)
 {
 	struct tegra30_i2s *i2s = snd_soc_dai_get_drvdata(dai);
@@ -268,6 +307,7 @@ static const struct snd_soc_dai_ops tegra30_i2s_dai_ops = {
 	.set_fmt	= tegra30_i2s_set_fmt,
 	.hw_params	= tegra30_i2s_hw_params,
 	.trigger	= tegra30_i2s_trigger,
+	.set_tdm_slot	= tegra30_i2s_set_tdm,
 };
 
 static const struct snd_soc_dai_driver tegra30_i2s_dai_template = {
@@ -277,14 +317,18 @@ static const struct snd_soc_dai_driver tegra30_i2s_dai_template = {
 		.channels_min = 2,
 		.channels_max = 2,
 		.rates = SNDRV_PCM_RATE_8000_96000,
-		.formats = SNDRV_PCM_FMTBIT_S16_LE,
+		.formats = SNDRV_PCM_FMTBIT_S32_LE |
+			   SNDRV_PCM_FMTBIT_S24_LE |
+			   SNDRV_PCM_FMTBIT_S16_LE,
 	},
 	.capture = {
 		.stream_name = "Capture",
 		.channels_min = 2,
 		.channels_max = 2,
 		.rates = SNDRV_PCM_RATE_8000_96000,
-		.formats = SNDRV_PCM_FMTBIT_S16_LE,
+		.formats = SNDRV_PCM_FMTBIT_S32_LE |
+			   SNDRV_PCM_FMTBIT_S24_LE |
+			   SNDRV_PCM_FMTBIT_S16_LE,
 	},
 	.ops = &tegra30_i2s_dai_ops,
 	.symmetric_rates = 1,
diff --git a/sound/soc/ti/davinci-mcasp.c b/sound/soc/ti/davinci-mcasp.c
index 7aa3c32e4a49..8e5371801d88 100644
--- a/sound/soc/ti/davinci-mcasp.c
+++ b/sound/soc/ti/davinci-mcasp.c
@@ -1867,7 +1867,7 @@ static int davinci_mcasp_get_dma_type(struct davinci_mcasp *mcasp)
 		return PCM_EDMA;
 
 	tmp = mcasp->dma_data[SNDRV_PCM_STREAM_PLAYBACK].filter_data;
-	chan = dma_request_slave_channel_reason(mcasp->dev, tmp);
+	chan = dma_request_chan(mcasp->dev, tmp);
 	if (IS_ERR(chan)) {
 		if (PTR_ERR(chan) != -EPROBE_DEFER)
 			dev_err(mcasp->dev,
diff --git a/sound/soc/txx9/txx9aclc.c b/sound/soc/txx9/txx9aclc.c
index 66044559f70f..33c78d33e5a1 100644
--- a/sound/soc/txx9/txx9aclc.c
+++ b/sound/soc/txx9/txx9aclc.c
@@ -47,12 +47,12 @@ static const struct snd_pcm_hardware txx9aclc_pcm_hardware = {
 	.buffer_bytes_max = 32 * 1024,
 };
 
-static int txx9aclc_pcm_hw_params(struct snd_pcm_substream *substream,
+static int txx9aclc_pcm_hw_params(struct snd_soc_component *component,
+				  struct snd_pcm_substream *substream,
 				  struct snd_pcm_hw_params *params)
 {
 	struct snd_soc_pcm_runtime *rtd = snd_pcm_substream_chip(substream);
 	struct snd_pcm_runtime *runtime = substream->runtime;
-	struct snd_soc_component *component = snd_soc_rtdcom_lookup(rtd, DRV_NAME);
 	struct txx9aclc_dmadata *dmadata = runtime->private_data;
 	int ret;
 
@@ -76,12 +76,14 @@ static int txx9aclc_pcm_hw_params(struct snd_pcm_substream *substream,
 	return 0;
 }
 
-static int txx9aclc_pcm_hw_free(struct snd_pcm_substream *substream)
+static int txx9aclc_pcm_hw_free(struct snd_soc_component *component,
+				struct snd_pcm_substream *substream)
 {
 	return snd_pcm_lib_free_pages(substream);
 }
 
-static int txx9aclc_pcm_prepare(struct snd_pcm_substream *substream)
+static int txx9aclc_pcm_prepare(struct snd_soc_component *component,
+				struct snd_pcm_substream *substream)
 {
 	struct snd_pcm_runtime *runtime = substream->runtime;
 	struct txx9aclc_dmadata *dmadata = runtime->private_data;
@@ -203,7 +205,8 @@ static void txx9aclc_dma_tasklet(unsigned long data)
 	spin_unlock_irqrestore(&dmadata->dma_lock, flags);
 }
 
-static int txx9aclc_pcm_trigger(struct snd_pcm_substream *substream, int cmd)
+static int txx9aclc_pcm_trigger(struct snd_soc_component *component,
+				struct snd_pcm_substream *substream, int cmd)
 {
 	struct txx9aclc_dmadata *dmadata = substream->runtime->private_data;
 	struct txx9aclc_plat_drvdata *drvdata = txx9aclc_drvdata;
@@ -236,14 +239,16 @@ static int txx9aclc_pcm_trigger(struct snd_pcm_substream *substream, int cmd)
 }
 
 static snd_pcm_uframes_t
-txx9aclc_pcm_pointer(struct snd_pcm_substream *substream)
+txx9aclc_pcm_pointer(struct snd_soc_component *component,
+		     struct snd_pcm_substream *substream)
 {
 	struct txx9aclc_dmadata *dmadata = substream->runtime->private_data;
 
 	return bytes_to_frames(substream->runtime, dmadata->pos);
 }
 
-static int txx9aclc_pcm_open(struct snd_pcm_substream *substream)
+static int txx9aclc_pcm_open(struct snd_soc_component *component,
+			     struct snd_pcm_substream *substream)
 {
 	struct txx9aclc_soc_device *dev = &txx9aclc_soc_device;
 	struct txx9aclc_dmadata *dmadata = &dev->dmadata[substream->stream];
@@ -261,7 +266,8 @@ static int txx9aclc_pcm_open(struct snd_pcm_substream *substream)
 	return 0;
 }
 
-static int txx9aclc_pcm_close(struct snd_pcm_substream *substream)
+static int txx9aclc_pcm_close(struct snd_soc_component *component,
+			      struct snd_pcm_substream *substream)
 {
 	struct txx9aclc_dmadata *dmadata = substream->runtime->private_data;
 	struct dma_chan *chan = dmadata->dma_chan;
@@ -271,23 +277,12 @@ static int txx9aclc_pcm_close(struct snd_pcm_substream *substream)
 	return 0;
 }
 
-static const struct snd_pcm_ops txx9aclc_pcm_ops = {
-	.open		= txx9aclc_pcm_open,
-	.close		= txx9aclc_pcm_close,
-	.ioctl		= snd_pcm_lib_ioctl,
-	.hw_params	= txx9aclc_pcm_hw_params,
-	.hw_free	= txx9aclc_pcm_hw_free,
-	.prepare	= txx9aclc_pcm_prepare,
-	.trigger	= txx9aclc_pcm_trigger,
-	.pointer	= txx9aclc_pcm_pointer,
-};
-
-static int txx9aclc_pcm_new(struct snd_soc_pcm_runtime *rtd)
+static int txx9aclc_pcm_new(struct snd_soc_component *component,
+			    struct snd_soc_pcm_runtime *rtd)
 {
 	struct snd_card *card = rtd->card->snd_card;
 	struct snd_soc_dai *dai = rtd->cpu_dai;
 	struct snd_pcm *pcm = rtd->pcm;
-	struct snd_soc_component *component = snd_soc_rtdcom_lookup(rtd, DRV_NAME);
 	struct platform_device *pdev = to_platform_device(component->dev);
 	struct txx9aclc_soc_device *dev;
 	struct resource *r;
@@ -409,8 +404,15 @@ static const struct snd_soc_component_driver txx9aclc_soc_component = {
 	.name		= DRV_NAME,
 	.probe		= txx9aclc_pcm_probe,
 	.remove		= txx9aclc_pcm_remove,
-	.ops		= &txx9aclc_pcm_ops,
-	.pcm_new	= txx9aclc_pcm_new,
+	.open		= txx9aclc_pcm_open,
+	.close		= txx9aclc_pcm_close,
+	.ioctl		= snd_soc_pcm_lib_ioctl,
+	.hw_params	= txx9aclc_pcm_hw_params,
+	.hw_free	= txx9aclc_pcm_hw_free,
+	.prepare	= txx9aclc_pcm_prepare,
+	.trigger	= txx9aclc_pcm_trigger,
+	.pointer	= txx9aclc_pcm_pointer,
+	.pcm_construct	= txx9aclc_pcm_new,
 };
 
 static int txx9aclc_soc_platform_probe(struct platform_device *pdev)
diff --git a/sound/soc/uniphier/aio-dma.c b/sound/soc/uniphier/aio-dma.c
index e8446cc4e8f8..700d936ed94e 100644
--- a/sound/soc/uniphier/aio-dma.c
+++ b/sound/soc/uniphier/aio-dma.c
@@ -93,7 +93,8 @@ static irqreturn_t aiodma_irq(int irq, void *p)
 	return ret;
 }
 
-static int uniphier_aiodma_open(struct snd_pcm_substream *substream)
+static int uniphier_aiodma_open(struct snd_soc_component *component,
+				struct snd_pcm_substream *substream)
 {
 	struct snd_pcm_runtime *runtime = substream->runtime;
 
@@ -103,7 +104,8 @@ static int uniphier_aiodma_open(struct snd_pcm_substream *substream)
 		SNDRV_PCM_HW_PARAM_BUFFER_BYTES, 256);
 }
 
-static int uniphier_aiodma_hw_params(struct snd_pcm_substream *substream,
+static int uniphier_aiodma_hw_params(struct snd_soc_component *component,
+				     struct snd_pcm_substream *substream,
 				     struct snd_pcm_hw_params *params)
 {
 	snd_pcm_set_runtime_buffer(substream, &substream->dma_buffer);
@@ -112,7 +114,8 @@ static int uniphier_aiodma_hw_params(struct snd_pcm_substream *substream,
 	return 0;
 }
 
-static int uniphier_aiodma_hw_free(struct snd_pcm_substream *substream)
+static int uniphier_aiodma_hw_free(struct snd_soc_component *component,
+				   struct snd_pcm_substream *substream)
 {
 	snd_pcm_set_runtime_buffer(substream, NULL);
 	substream->runtime->dma_bytes = 0;
@@ -120,7 +123,8 @@ static int uniphier_aiodma_hw_free(struct snd_pcm_substream *substream)
 	return 0;
 }
 
-static int uniphier_aiodma_prepare(struct snd_pcm_substream *substream)
+static int uniphier_aiodma_prepare(struct snd_soc_component *component,
+				   struct snd_pcm_substream *substream)
 {
 	struct snd_pcm_runtime *runtime = substream->runtime;
 	struct snd_soc_pcm_runtime *rtd = snd_pcm_substream_chip(substream);
@@ -146,7 +150,8 @@ static int uniphier_aiodma_prepare(struct snd_pcm_substream *substream)
 	return 0;
 }
 
-static int uniphier_aiodma_trigger(struct snd_pcm_substream *substream, int cmd)
+static int uniphier_aiodma_trigger(struct snd_soc_component *component,
+				   struct snd_pcm_substream *substream, int cmd)
 {
 	struct snd_pcm_runtime *runtime = substream->runtime;
 	struct snd_soc_pcm_runtime *rtd = snd_pcm_substream_chip(substream);
@@ -181,6 +186,7 @@ static int uniphier_aiodma_trigger(struct snd_pcm_substream *substream, int cmd)
 }
 
 static snd_pcm_uframes_t uniphier_aiodma_pointer(
+					struct snd_soc_component *component,
 					struct snd_pcm_substream *substream)
 {
 	struct snd_pcm_runtime *runtime = substream->runtime;
@@ -204,7 +210,8 @@ static snd_pcm_uframes_t uniphier_aiodma_pointer(
 	return pos;
 }
 
-static int uniphier_aiodma_mmap(struct snd_pcm_substream *substream,
+static int uniphier_aiodma_mmap(struct snd_soc_component *component,
+				struct snd_pcm_substream *substream,
 				struct vm_area_struct *vma)
 {
 	vma->vm_page_prot = pgprot_writecombine(vma->vm_page_prot);
@@ -214,18 +221,8 @@ static int uniphier_aiodma_mmap(struct snd_pcm_substream *substream,
 			       vma->vm_end - vma->vm_start, vma->vm_page_prot);
 }
 
-static const struct snd_pcm_ops uniphier_aiodma_ops = {
-	.open      = uniphier_aiodma_open,
-	.ioctl     = snd_pcm_lib_ioctl,
-	.hw_params = uniphier_aiodma_hw_params,
-	.hw_free   = uniphier_aiodma_hw_free,
-	.prepare   = uniphier_aiodma_prepare,
-	.trigger   = uniphier_aiodma_trigger,
-	.pointer   = uniphier_aiodma_pointer,
-	.mmap      = uniphier_aiodma_mmap,
-};
-
-static int uniphier_aiodma_new(struct snd_soc_pcm_runtime *rtd)
+static int uniphier_aiodma_new(struct snd_soc_component *component,
+			       struct snd_soc_pcm_runtime *rtd)
 {
 	struct device *dev = rtd->card->snd_card->dev;
 	struct snd_pcm *pcm = rtd->pcm;
@@ -242,16 +239,24 @@ static int uniphier_aiodma_new(struct snd_soc_pcm_runtime *rtd)
 	return 0;
 }
 
-static void uniphier_aiodma_free(struct snd_pcm *pcm)
+static void uniphier_aiodma_free(struct snd_soc_component *component,
+				 struct snd_pcm *pcm)
 {
 	snd_pcm_lib_preallocate_free_for_all(pcm);
 }
 
 static const struct snd_soc_component_driver uniphier_soc_platform = {
-	.pcm_new   = uniphier_aiodma_new,
-	.pcm_free  = uniphier_aiodma_free,
-	.ops       = &uniphier_aiodma_ops,
-	.compr_ops = &uniphier_aio_compr_ops,
+	.open		= uniphier_aiodma_open,
+	.ioctl		= snd_soc_pcm_lib_ioctl,
+	.hw_params	= uniphier_aiodma_hw_params,
+	.hw_free	= uniphier_aiodma_hw_free,
+	.prepare	= uniphier_aiodma_prepare,
+	.trigger	= uniphier_aiodma_trigger,
+	.pointer	= uniphier_aiodma_pointer,
+	.mmap		= uniphier_aiodma_mmap,
+	.pcm_construct	= uniphier_aiodma_new,
+	.pcm_destruct	= uniphier_aiodma_free,
+	.compr_ops	= &uniphier_aio_compr_ops,
 };
 
 static const struct regmap_config aiodma_regmap_config = {
diff --git a/sound/soc/ux500/ux500_msp_i2s.c b/sound/soc/ux500/ux500_msp_i2s.c
index a90e0d7f0b73..394d8b2a4a16 100644
--- a/sound/soc/ux500/ux500_msp_i2s.c
+++ b/sound/soc/ux500/ux500_msp_i2s.c
@@ -533,7 +533,6 @@ static void disable_msp_tx(struct ux500_msp *msp)
 static int disable_msp(struct ux500_msp *msp, unsigned int dir)
 {
 	u32 reg_val_GCR;
-	int status = 0;
 	unsigned int disable_tx, disable_rx;
 
 	reg_val_GCR = readl(msp->registers + MSP_GCR);
@@ -566,7 +565,7 @@ static int disable_msp(struct ux500_msp *msp, unsigned int dir)
 	else if (disable_rx)
 		disable_msp_rx(msp);
 
-	return status;
+	return 0;
 }
 
 int ux500_msp_i2s_trigger(struct ux500_msp *msp, int cmd, int direction)
diff --git a/sound/soc/xilinx/Kconfig b/sound/soc/xilinx/Kconfig
index 69973179ef15..1d3586b68db7 100644
--- a/sound/soc/xilinx/Kconfig
+++ b/sound/soc/xilinx/Kconfig
@@ -9,15 +9,15 @@ config SND_SOC_XILINX_I2S
 	  encapsulates PCM in AES format and sends AES data.
 
 config SND_SOC_XILINX_AUDIO_FORMATTER
-        tristate "Audio support for the the Xilinx audio formatter"
-        help
-          Select this option to enable Xilinx audio formatter
-          support. This provides DMA platform device support for
-          audio functionality.
+	tristate "Audio support for the the Xilinx audio formatter"
+	help
+	  Select this option to enable Xilinx audio formatter
+	  support. This provides DMA platform device support for
+	  audio functionality.
 
 config SND_SOC_XILINX_SPDIF
-        tristate "Audio support for the the Xilinx SPDIF"
-        help
-          Select this option to enable Xilinx SPDIF Audio.
-          This provides playback and capture of SPDIF audio in
-          AES format.
+	tristate "Audio support for the the Xilinx SPDIF"
+	help
+	  Select this option to enable Xilinx SPDIF Audio.
+	  This provides playback and capture of SPDIF audio in
+	  AES format.
diff --git a/sound/soc/xilinx/xlnx_formatter_pcm.c b/sound/soc/xilinx/xlnx_formatter_pcm.c
index 48970efe7838..296c4caf96a0 100644
--- a/sound/soc/xilinx/xlnx_formatter_pcm.c
+++ b/sound/soc/xilinx/xlnx_formatter_pcm.c
@@ -313,16 +313,14 @@ static irqreturn_t xlnx_s2mm_irq_handler(int irq, void *arg)
 	return IRQ_NONE;
 }
 
-static int xlnx_formatter_pcm_open(struct snd_pcm_substream *substream)
+static int xlnx_formatter_pcm_open(struct snd_soc_component *component,
+				   struct snd_pcm_substream *substream)
 {
 	int err;
 	u32 val, data_format_mode;
 	u32 ch_count_mask, ch_count_shift, data_xfer_mode, data_xfer_shift;
 	struct xlnx_pcm_stream_param *stream_data;
 	struct snd_pcm_runtime *runtime = substream->runtime;
-	struct snd_soc_pcm_runtime *prtd = substream->private_data;
-	struct snd_soc_component *component = snd_soc_rtdcom_lookup(prtd,
-								    DRV_NAME);
 	struct xlnx_pcm_drv_data *adata = dev_get_drvdata(component->dev);
 
 	if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK &&
@@ -387,14 +385,12 @@ static int xlnx_formatter_pcm_open(struct snd_pcm_substream *substream)
 	return 0;
 }
 
-static int xlnx_formatter_pcm_close(struct snd_pcm_substream *substream)
+static int xlnx_formatter_pcm_close(struct snd_soc_component *component,
+				    struct snd_pcm_substream *substream)
 {
 	int ret;
 	struct xlnx_pcm_stream_param *stream_data =
 			substream->runtime->private_data;
-	struct snd_soc_pcm_runtime *prtd = substream->private_data;
-	struct snd_soc_component *component = snd_soc_rtdcom_lookup(prtd,
-								    DRV_NAME);
 
 	ret = xlnx_formatter_pcm_reset(stream_data->mmio);
 	if (ret) {
@@ -409,7 +405,8 @@ err_reset:
 }
 
 static snd_pcm_uframes_t
-xlnx_formatter_pcm_pointer(struct snd_pcm_substream *substream)
+xlnx_formatter_pcm_pointer(struct snd_soc_component *component,
+			   struct snd_pcm_substream *substream)
 {
 	u32 pos;
 	struct snd_pcm_runtime *runtime = substream->runtime;
@@ -423,16 +420,14 @@ xlnx_formatter_pcm_pointer(struct snd_pcm_substream *substream)
 	return bytes_to_frames(runtime, pos);
 }
 
-static int xlnx_formatter_pcm_hw_params(struct snd_pcm_substream *substream,
+static int xlnx_formatter_pcm_hw_params(struct snd_soc_component *component,
+					struct snd_pcm_substream *substream,
 					struct snd_pcm_hw_params *params)
 {
 	u32 low, high, active_ch, val, bytes_per_ch, bits_per_sample;
 	u32 aes_reg1_val, aes_reg2_val;
 	int status;
 	u64 size;
-	struct snd_soc_pcm_runtime *prtd = substream->private_data;
-	struct snd_soc_component *component = snd_soc_rtdcom_lookup(prtd,
-								    DRV_NAME);
 	struct snd_pcm_runtime *runtime = substream->runtime;
 	struct xlnx_pcm_stream_param *stream_data = runtime->private_data;
 
@@ -500,12 +495,14 @@ static int xlnx_formatter_pcm_hw_params(struct snd_pcm_substream *substream,
 	return 0;
 }
 
-static int xlnx_formatter_pcm_hw_free(struct snd_pcm_substream *substream)
+static int xlnx_formatter_pcm_hw_free(struct snd_soc_component *component,
+				      struct snd_pcm_substream *substream)
 {
 	return snd_pcm_lib_free_pages(substream);
 }
 
-static int xlnx_formatter_pcm_trigger(struct snd_pcm_substream *substream,
+static int xlnx_formatter_pcm_trigger(struct snd_soc_component *component,
+				      struct snd_pcm_substream *substream,
 				      int cmd)
 {
 	u32 val;
@@ -532,10 +529,9 @@ static int xlnx_formatter_pcm_trigger(struct snd_pcm_substream *substream,
 	return 0;
 }
 
-static int xlnx_formatter_pcm_new(struct snd_soc_pcm_runtime *rtd)
+static int xlnx_formatter_pcm_new(struct snd_soc_component *component,
+				  struct snd_soc_pcm_runtime *rtd)
 {
-	struct snd_soc_component *component = snd_soc_rtdcom_lookup(rtd,
-								    DRV_NAME);
 	snd_pcm_lib_preallocate_pages_for_all(rtd->pcm,
 			SNDRV_DMA_TYPE_DEV, component->dev,
 			xlnx_pcm_hardware.buffer_bytes_max,
@@ -543,20 +539,16 @@ static int xlnx_formatter_pcm_new(struct snd_soc_pcm_runtime *rtd)
 	return 0;
 }
 
-static const struct snd_pcm_ops xlnx_formatter_pcm_ops = {
-	.open = xlnx_formatter_pcm_open,
-	.close = xlnx_formatter_pcm_close,
-	.ioctl = snd_pcm_lib_ioctl,
-	.hw_params = xlnx_formatter_pcm_hw_params,
-	.hw_free = xlnx_formatter_pcm_hw_free,
-	.trigger = xlnx_formatter_pcm_trigger,
-	.pointer = xlnx_formatter_pcm_pointer,
-};
-
 static const struct snd_soc_component_driver xlnx_asoc_component = {
-	.name = DRV_NAME,
-	.ops = &xlnx_formatter_pcm_ops,
-	.pcm_new = xlnx_formatter_pcm_new,
+	.name		= DRV_NAME,
+	.open		= xlnx_formatter_pcm_open,
+	.close		= xlnx_formatter_pcm_close,
+	.ioctl		= snd_soc_pcm_lib_ioctl,
+	.hw_params	= xlnx_formatter_pcm_hw_params,
+	.hw_free	= xlnx_formatter_pcm_hw_free,
+	.trigger	= xlnx_formatter_pcm_trigger,
+	.pointer	= xlnx_formatter_pcm_pointer,
+	.pcm_construct	= xlnx_formatter_pcm_new,
 };
 
 static int xlnx_formatter_pcm_probe(struct platform_device *pdev)
@@ -564,7 +556,6 @@ static int xlnx_formatter_pcm_probe(struct platform_device *pdev)
 	int ret;
 	u32 val;
 	struct xlnx_pcm_drv_data *aud_drv_data;
-	struct resource *res;
 	struct device *dev = &pdev->dev;
 
 	aud_drv_data = devm_kzalloc(dev, sizeof(*aud_drv_data), GFP_KERNEL);
@@ -584,13 +575,7 @@ static int xlnx_formatter_pcm_probe(struct platform_device *pdev)
 		return ret;
 	}
 
-	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	if (!res) {
-		dev_err(dev, "audio formatter node:addr to resource failed\n");
-		ret = -ENXIO;
-		goto clk_err;
-	}
-	aud_drv_data->mmio = devm_ioremap_resource(dev, res);
+	aud_drv_data->mmio = devm_platform_ioremap_resource(pdev, 0);
 	if (IS_ERR(aud_drv_data->mmio)) {
 		dev_err(dev, "audio formatter ioremap failed\n");
 		ret = PTR_ERR(aud_drv_data->mmio);
diff --git a/sound/soc/xtensa/xtfpga-i2s.c b/sound/soc/xtensa/xtfpga-i2s.c
index efd374f114a0..e08f4fee932a 100644
--- a/sound/soc/xtensa/xtfpga-i2s.c
+++ b/sound/soc/xtensa/xtfpga-i2s.c
@@ -365,7 +365,8 @@ static const struct snd_pcm_hardware xtfpga_pcm_hardware = {
 	.fifo_size		= 16,
 };
 
-static int xtfpga_pcm_open(struct snd_pcm_substream *substream)
+static int xtfpga_pcm_open(struct snd_soc_component *component,
+			   struct snd_pcm_substream *substream)
 {
 	struct snd_pcm_runtime *runtime = substream->runtime;
 	struct snd_soc_pcm_runtime *rtd = substream->private_data;
@@ -378,13 +379,15 @@ static int xtfpga_pcm_open(struct snd_pcm_substream *substream)
 	return 0;
 }
 
-static int xtfpga_pcm_close(struct snd_pcm_substream *substream)
+static int xtfpga_pcm_close(struct snd_soc_component *component,
+			    struct snd_pcm_substream *substream)
 {
 	synchronize_rcu();
 	return 0;
 }
 
-static int xtfpga_pcm_hw_params(struct snd_pcm_substream *substream,
+static int xtfpga_pcm_hw_params(struct snd_soc_component *component,
+				struct snd_pcm_substream *substream,
 				struct snd_pcm_hw_params *hw_params)
 {
 	int ret;
@@ -424,7 +427,8 @@ static int xtfpga_pcm_hw_params(struct snd_pcm_substream *substream,
 	return ret;
 }
 
-static int xtfpga_pcm_trigger(struct snd_pcm_substream *substream, int cmd)
+static int xtfpga_pcm_trigger(struct snd_soc_component *component,
+			      struct snd_pcm_substream *substream, int cmd)
 {
 	int ret = 0;
 	struct snd_pcm_runtime *runtime = substream->runtime;
@@ -452,7 +456,8 @@ static int xtfpga_pcm_trigger(struct snd_pcm_substream *substream, int cmd)
 	return ret;
 }
 
-static snd_pcm_uframes_t xtfpga_pcm_pointer(struct snd_pcm_substream *substream)
+static snd_pcm_uframes_t xtfpga_pcm_pointer(struct snd_soc_component *component,
+					    struct snd_pcm_substream *substream)
 {
 	struct snd_pcm_runtime *runtime = substream->runtime;
 	struct xtfpga_i2s *i2s = runtime->private_data;
@@ -461,7 +466,8 @@ static snd_pcm_uframes_t xtfpga_pcm_pointer(struct snd_pcm_substream *substream)
 	return pos < runtime->buffer_size ? pos : 0;
 }
 
-static int xtfpga_pcm_new(struct snd_soc_pcm_runtime *rtd)
+static int xtfpga_pcm_new(struct snd_soc_component *component,
+			  struct snd_soc_pcm_runtime *rtd)
 {
 	struct snd_card *card = rtd->card->snd_card;
 	size_t size = xtfpga_pcm_hardware.buffer_bytes_max;
@@ -471,19 +477,15 @@ static int xtfpga_pcm_new(struct snd_soc_pcm_runtime *rtd)
 	return 0;
 }
 
-static const struct snd_pcm_ops xtfpga_pcm_ops = {
+static const struct snd_soc_component_driver xtfpga_i2s_component = {
+	.name		= DRV_NAME,
 	.open		= xtfpga_pcm_open,
 	.close		= xtfpga_pcm_close,
-	.ioctl		= snd_pcm_lib_ioctl,
+	.ioctl		= snd_soc_pcm_lib_ioctl,
 	.hw_params	= xtfpga_pcm_hw_params,
 	.trigger	= xtfpga_pcm_trigger,
 	.pointer	= xtfpga_pcm_pointer,
-};
-
-static const struct snd_soc_component_driver xtfpga_i2s_component = {
-	.name		= DRV_NAME,
-	.pcm_new	= xtfpga_pcm_new,
-	.ops		= &xtfpga_pcm_ops,
+	.pcm_construct	= xtfpga_pcm_new,
 };
 
 static const struct snd_soc_dai_ops xtfpga_i2s_dai_ops = {
diff --git a/sound/soc/zte/Kconfig b/sound/soc/zte/Kconfig
index a7842e4b791c..a23d4f13ca19 100644
--- a/sound/soc/zte/Kconfig
+++ b/sound/soc/zte/Kconfig
@@ -18,9 +18,9 @@ config ZX_I2S
 	  ZTE ZX I2S interface
 
 config ZX_TDM
-        tristate "ZTE ZX TDM Driver Support"
-        depends on COMMON_CLK
-        select SND_SOC_GENERIC_DMAENGINE_PCM
-        help
-          Say Y or M if you want to add support for codecs attached to the
-          ZTE ZX TDM interface
+	tristate "ZTE ZX TDM Driver Support"
+	depends on COMMON_CLK
+	select SND_SOC_GENERIC_DMAENGINE_PCM
+	help
+	  Say Y or M if you want to add support for codecs attached to the
+	  ZTE ZX TDM interface
diff --git a/sound/sparc/amd7930.c b/sound/sparc/amd7930.c
index 441222c8e223..d4b8ccc61dc2 100644
--- a/sound/sparc/amd7930.c
+++ b/sound/sparc/amd7930.c
@@ -777,7 +777,7 @@ static int snd_amd7930_pcm(struct snd_amd7930 *amd)
 	amd->pcm = pcm;
 
 	snd_pcm_lib_preallocate_pages_for_all(pcm, SNDRV_DMA_TYPE_CONTINUOUS,
-					      snd_dma_continuous_data(GFP_KERNEL),
+					      NULL,
 					      64*1024, 64*1024);
 
 	return 0;
diff --git a/sound/sparc/dbri.c b/sound/sparc/dbri.c
index 6e065d44060e..4911103421ff 100644
--- a/sound/sparc/dbri.c
+++ b/sound/sparc/dbri.c
@@ -2249,7 +2249,7 @@ static int snd_dbri_pcm(struct snd_card *card)
 	strcpy(pcm->name, card->shortname);
 
 	snd_pcm_lib_preallocate_pages_for_all(pcm, SNDRV_DMA_TYPE_CONTINUOUS,
-					      snd_dma_continuous_data(GFP_KERNEL),
+					      NULL,
 					      64 * 1024, 64 * 1024);
 	return 0;
 }
diff --git a/sound/usb/6fire/pcm.c b/sound/usb/6fire/pcm.c
index 88ac1c4ee163..cdc5dd7fbe16 100644
--- a/sound/usb/6fire/pcm.c
+++ b/sound/usb/6fire/pcm.c
@@ -449,13 +449,13 @@ static int usb6fire_pcm_close(struct snd_pcm_substream *alsa_sub)
 static int usb6fire_pcm_hw_params(struct snd_pcm_substream *alsa_sub,
 		struct snd_pcm_hw_params *hw_params)
 {
-	return snd_pcm_lib_alloc_vmalloc_buffer(alsa_sub,
-						params_buffer_bytes(hw_params));
+	return snd_pcm_lib_malloc_pages(alsa_sub,
+					params_buffer_bytes(hw_params));
 }
 
 static int usb6fire_pcm_hw_free(struct snd_pcm_substream *alsa_sub)
 {
-	return snd_pcm_lib_free_vmalloc_buffer(alsa_sub);
+	return snd_pcm_lib_free_pages(alsa_sub);
 }
 
 static int usb6fire_pcm_prepare(struct snd_pcm_substream *alsa_sub)
@@ -560,7 +560,6 @@ static const struct snd_pcm_ops pcm_ops = {
 	.prepare = usb6fire_pcm_prepare,
 	.trigger = usb6fire_pcm_trigger,
 	.pointer = usb6fire_pcm_pointer,
-	.page = snd_pcm_lib_get_vmalloc_page,
 };
 
 static void usb6fire_pcm_init_urb(struct pcm_urb *urb,
@@ -659,14 +658,9 @@ int usb6fire_pcm_init(struct sfire_chip *chip)
 	strcpy(pcm->name, "DMX 6Fire USB");
 	snd_pcm_set_ops(pcm, SNDRV_PCM_STREAM_PLAYBACK, &pcm_ops);
 	snd_pcm_set_ops(pcm, SNDRV_PCM_STREAM_CAPTURE, &pcm_ops);
+	snd_pcm_lib_preallocate_pages_for_all(pcm, SNDRV_DMA_TYPE_VMALLOC,
+					      NULL, 0, 0);
 
-	if (ret) {
-		usb6fire_pcm_buffers_destroy(rt);
-		kfree(rt);
-		dev_err(&chip->dev->dev,
-			"error preallocating pcm buffers.\n");
-		return ret;
-	}
 	rt->instance = pcm;
 
 	chip->pcm = rt;
diff --git a/sound/usb/Kconfig b/sound/usb/Kconfig
index e2c53a0841da..059242f15d75 100644
--- a/sound/usb/Kconfig
+++ b/sound/usb/Kconfig
@@ -107,24 +107,24 @@ config SND_USB_US122L
 	  will be called snd-usb-us122l.
 
 config SND_USB_6FIRE
-        tristate "TerraTec DMX 6Fire USB"
-        select FW_LOADER
-        select BITREVERSE
-        select SND_RAWMIDI
-        select SND_PCM
-        select SND_VMASTER
-        help
-          Say Y here to include support for TerraTec 6fire DMX USB interface.
-
-          You will need firmware files in order to be able to use the device
-          after it has been coldstarted. An install script for the firmware
-          and further help can be found at
-          http://sixfireusb.sourceforge.net
+	tristate "TerraTec DMX 6Fire USB"
+	select FW_LOADER
+	select BITREVERSE
+	select SND_RAWMIDI
+	select SND_PCM
+	select SND_VMASTER
+	help
+	  Say Y here to include support for TerraTec 6fire DMX USB interface.
+
+	  You will need firmware files in order to be able to use the device
+	  after it has been coldstarted. An install script for the firmware
+	  and further help can be found at
+	  http://sixfireusb.sourceforge.net
 
 config SND_USB_HIFACE
-        tristate "M2Tech hiFace USB-SPDIF driver"
-        select SND_PCM
-        help
+	tristate "M2Tech hiFace USB-SPDIF driver"
+	select SND_PCM
+	help
 	  Select this option to include support for M2Tech hiFace USB-SPDIF
 	  interface.
 
diff --git a/sound/usb/caiaq/audio.c b/sound/usb/caiaq/audio.c
index 444bb637ce13..970eb0865ba3 100644
--- a/sound/usb/caiaq/audio.c
+++ b/sound/usb/caiaq/audio.c
@@ -170,15 +170,14 @@ static int snd_usb_caiaq_substream_close(struct snd_pcm_substream *substream)
 static int snd_usb_caiaq_pcm_hw_params(struct snd_pcm_substream *sub,
 				       struct snd_pcm_hw_params *hw_params)
 {
-	return snd_pcm_lib_alloc_vmalloc_buffer(sub,
-						params_buffer_bytes(hw_params));
+	return snd_pcm_lib_malloc_pages(sub, params_buffer_bytes(hw_params));
 }
 
 static int snd_usb_caiaq_pcm_hw_free(struct snd_pcm_substream *sub)
 {
 	struct snd_usb_caiaqdev *cdev = snd_pcm_substream_chip(sub);
 	deactivate_substream(cdev, sub);
-	return snd_pcm_lib_free_vmalloc_buffer(sub);
+	return snd_pcm_lib_free_pages(sub);
 }
 
 /* this should probably go upstream */
@@ -334,7 +333,6 @@ static const struct snd_pcm_ops snd_usb_caiaq_ops = {
 	.prepare =	snd_usb_caiaq_pcm_prepare,
 	.trigger =	snd_usb_caiaq_pcm_trigger,
 	.pointer =	snd_usb_caiaq_pcm_pointer,
-	.page =		snd_pcm_lib_get_vmalloc_page,
 };
 
 static void check_for_elapsed_periods(struct snd_usb_caiaqdev *cdev,
@@ -843,6 +841,8 @@ int snd_usb_caiaq_audio_init(struct snd_usb_caiaqdev *cdev)
 				&snd_usb_caiaq_ops);
 	snd_pcm_set_ops(cdev->pcm, SNDRV_PCM_STREAM_CAPTURE,
 				&snd_usb_caiaq_ops);
+	snd_pcm_lib_preallocate_pages_for_all(cdev->pcm, SNDRV_DMA_TYPE_VMALLOC,
+					      NULL, 0, 0);
 
 	cdev->data_cb_info =
 		kmalloc_array(N_URBS, sizeof(struct snd_usb_caiaq_cb_info),
diff --git a/sound/usb/card.c b/sound/usb/card.c
index db91dc76cc91..9f743ebae615 100644
--- a/sound/usb/card.c
+++ b/sound/usb/card.c
@@ -74,6 +74,7 @@ static bool autoclock = true;
 static char *quirk_alias[SNDRV_CARDS];
 
 bool snd_usb_use_vmalloc = true;
+bool snd_usb_skip_validation;
 
 module_param_array(index, int, NULL, 0444);
 MODULE_PARM_DESC(index, "Index value for the USB audio adapter.");
@@ -96,6 +97,8 @@ module_param_array(quirk_alias, charp, NULL, 0444);
 MODULE_PARM_DESC(quirk_alias, "Quirk aliases, e.g. 0123abcd:5678beef.");
 module_param_named(use_vmalloc, snd_usb_use_vmalloc, bool, 0444);
 MODULE_PARM_DESC(use_vmalloc, "Use vmalloc for PCM intermediate buffers (default: yes).");
+module_param_named(skip_validation, snd_usb_skip_validation, bool, 0444);
+MODULE_PARM_DESC(skip_validation, "Skip unit descriptor validation (default: no).");
 
 /*
  * we keep the snd_usb_audio_t instances by ourselves for merging
diff --git a/sound/usb/clock.c b/sound/usb/clock.c
index 6b8c14f9b5d4..018b1ecb5404 100644
--- a/sound/usb/clock.c
+++ b/sound/usb/clock.c
@@ -165,21 +165,21 @@ static bool uac_clock_source_is_valid(struct snd_usb_audio *chip,
 			snd_usb_find_clock_source_v3(chip->ctrl_intf, source_id);
 
 		if (!cs_desc)
-			return 0;
+			return false;
 		bmControls = le32_to_cpu(cs_desc->bmControls);
 	} else { /* UAC_VERSION_1/2 */
 		struct uac_clock_source_descriptor *cs_desc =
 			snd_usb_find_clock_source(chip->ctrl_intf, source_id);
 
 		if (!cs_desc)
-			return 0;
+			return false;
 		bmControls = cs_desc->bmControls;
 	}
 
 	/* If a clock source can't tell us whether it's valid, we assume it is */
 	if (!uac_v2v3_control_is_readable(bmControls,
 				      UAC2_CS_CONTROL_CLOCK_VALID))
-		return 1;
+		return true;
 
 	err = snd_usb_ctl_msg(dev, usb_rcvctrlpipe(dev, 0), UAC2_CS_CUR,
 			      USB_TYPE_CLASS | USB_RECIP_INTERFACE | USB_DIR_IN,
@@ -191,10 +191,10 @@ static bool uac_clock_source_is_valid(struct snd_usb_audio *chip,
 		dev_warn(&dev->dev,
 			 "%s(): cannot get clock validity for id %d\n",
 			   __func__, source_id);
-		return 0;
+		return false;
 	}
 
-	return !!data;
+	return data ? true :  false;
 }
 
 static int __uac_clock_find_source(struct snd_usb_audio *chip, int entity_id,
diff --git a/sound/usb/hiface/pcm.c b/sound/usb/hiface/pcm.c
index c406497c5919..e0de71917274 100644
--- a/sound/usb/hiface/pcm.c
+++ b/sound/usb/hiface/pcm.c
@@ -418,13 +418,13 @@ static int hiface_pcm_close(struct snd_pcm_substream *alsa_sub)
 static int hiface_pcm_hw_params(struct snd_pcm_substream *alsa_sub,
 				struct snd_pcm_hw_params *hw_params)
 {
-	return snd_pcm_lib_alloc_vmalloc_buffer(alsa_sub,
-						params_buffer_bytes(hw_params));
+	return snd_pcm_lib_malloc_pages(alsa_sub,
+					params_buffer_bytes(hw_params));
 }
 
 static int hiface_pcm_hw_free(struct snd_pcm_substream *alsa_sub)
 {
-	return snd_pcm_lib_free_vmalloc_buffer(alsa_sub);
+	return snd_pcm_lib_free_pages(alsa_sub);
 }
 
 static int hiface_pcm_prepare(struct snd_pcm_substream *alsa_sub)
@@ -518,7 +518,6 @@ static const struct snd_pcm_ops pcm_ops = {
 	.prepare = hiface_pcm_prepare,
 	.trigger = hiface_pcm_trigger,
 	.pointer = hiface_pcm_pointer,
-	.page = snd_pcm_lib_get_vmalloc_page,
 };
 
 static int hiface_pcm_init_urb(struct pcm_urb *urb,
@@ -614,6 +613,8 @@ int hiface_pcm_init(struct hiface_chip *chip, u8 extra_freq)
 
 	strlcpy(pcm->name, "USB-SPDIF Audio", sizeof(pcm->name));
 	snd_pcm_set_ops(pcm, SNDRV_PCM_STREAM_PLAYBACK, &pcm_ops);
+	snd_pcm_lib_preallocate_pages_for_all(pcm, SNDRV_DMA_TYPE_VMALLOC,
+					      NULL, 0, 0);
 
 	rt->instance = pcm;
 
diff --git a/sound/usb/line6/pcm.c b/sound/usb/line6/pcm.c
index f70211e6b174..9c437c716cfd 100644
--- a/sound/usb/line6/pcm.c
+++ b/sound/usb/line6/pcm.c
@@ -502,9 +502,7 @@ static int snd_line6_new_pcm(struct usb_line6 *line6, struct snd_pcm **pcm_ret)
 
 	/* pre-allocation of buffers */
 	snd_pcm_lib_preallocate_pages_for_all(pcm, SNDRV_DMA_TYPE_CONTINUOUS,
-					      snd_dma_continuous_data
-					      (GFP_KERNEL), 64 * 1024,
-					      128 * 1024);
+					      NULL, 64 * 1024, 128 * 1024);
 	return 0;
 }
 
diff --git a/sound/usb/misc/ua101.c b/sound/usb/misc/ua101.c
index 307b72d5fffa..566a4a31528a 100644
--- a/sound/usb/misc/ua101.c
+++ b/sound/usb/misc/ua101.c
@@ -733,8 +733,8 @@ static int capture_pcm_hw_params(struct snd_pcm_substream *substream,
 	if (err < 0)
 		return err;
 
-	return snd_pcm_lib_alloc_vmalloc_buffer(substream,
-						params_buffer_bytes(hw_params));
+	return snd_pcm_lib_malloc_pages(substream,
+					params_buffer_bytes(hw_params));
 }
 
 static int playback_pcm_hw_params(struct snd_pcm_substream *substream,
@@ -751,13 +751,13 @@ static int playback_pcm_hw_params(struct snd_pcm_substream *substream,
 	if (err < 0)
 		return err;
 
-	return snd_pcm_lib_alloc_vmalloc_buffer(substream,
-						params_buffer_bytes(hw_params));
+	return snd_pcm_lib_malloc_pages(substream,
+					params_buffer_bytes(hw_params));
 }
 
 static int ua101_pcm_hw_free(struct snd_pcm_substream *substream)
 {
-	return snd_pcm_lib_free_vmalloc_buffer(substream);
+	return snd_pcm_lib_free_pages(substream);
 }
 
 static int capture_pcm_prepare(struct snd_pcm_substream *substream)
@@ -889,7 +889,6 @@ static const struct snd_pcm_ops capture_pcm_ops = {
 	.prepare = capture_pcm_prepare,
 	.trigger = capture_pcm_trigger,
 	.pointer = capture_pcm_pointer,
-	.page = snd_pcm_lib_get_vmalloc_page,
 };
 
 static const struct snd_pcm_ops playback_pcm_ops = {
@@ -901,7 +900,6 @@ static const struct snd_pcm_ops playback_pcm_ops = {
 	.prepare = playback_pcm_prepare,
 	.trigger = playback_pcm_trigger,
 	.pointer = playback_pcm_pointer,
-	.page = snd_pcm_lib_get_vmalloc_page,
 };
 
 static const struct uac_format_type_i_discrete_descriptor *
@@ -1296,6 +1294,8 @@ static int ua101_probe(struct usb_interface *interface,
 	strcpy(ua->pcm->name, name);
 	snd_pcm_set_ops(ua->pcm, SNDRV_PCM_STREAM_PLAYBACK, &playback_pcm_ops);
 	snd_pcm_set_ops(ua->pcm, SNDRV_PCM_STREAM_CAPTURE, &capture_pcm_ops);
+	snd_pcm_lib_preallocate_pages_for_all(ua->pcm, SNDRV_DMA_TYPE_VMALLOC,
+					      NULL, 0, 0);
 
 	err = snd_usbmidi_create(card, ua->intf[INTF_MIDI],
 				 &ua->midi_list, &midi_quirk);
diff --git a/sound/usb/mixer.c b/sound/usb/mixer.c
index 45eee5cc312e..6cd4ff09c5ee 100644
--- a/sound/usb/mixer.c
+++ b/sound/usb/mixer.c
@@ -2930,6 +2930,9 @@ static int snd_usb_mixer_controls_badd(struct usb_mixer_interface *mixer,
 			continue;
 
 		iface = usb_ifnum_to_if(dev, intf);
+		if (!iface)
+			continue;
+
 		num = iface->num_altsetting;
 
 		if (num < 2)
diff --git a/sound/usb/mixer_scarlett.c b/sound/usb/mixer_scarlett.c
index 83715fd8dfd6..9d10cbf1b5ed 100644
--- a/sound/usb/mixer_scarlett.c
+++ b/sound/usb/mixer_scarlett.c
@@ -142,6 +142,7 @@ enum {
 	SCARLETT_OUTPUTS,
 	SCARLETT_SWITCH_IMPEDANCE,
 	SCARLETT_SWITCH_PAD,
+	SCARLETT_SWITCH_GAIN,
 };
 
 enum {
@@ -192,6 +193,15 @@ static const struct scarlett_mixer_elem_enum_info opt_pad = {
 	}
 };
 
+static const struct scarlett_mixer_elem_enum_info opt_gain = {
+	.start = 0,
+	.len = 2,
+	.offsets = {},
+	.names = (char const * const []){
+		"Lo", "Hi"
+	}
+};
+
 static const struct scarlett_mixer_elem_enum_info opt_impedance = {
 	.start = 0,
 	.len = 2,
@@ -652,8 +662,8 @@ static struct scarlett_device_info s6i6_info = {
 		{ .num = 1, .type = SCARLETT_SWITCH_PAD, .name = NULL},
 		{ .num = 2, .type = SCARLETT_SWITCH_IMPEDANCE, .name = NULL},
 		{ .num = 2, .type = SCARLETT_SWITCH_PAD, .name = NULL},
-		{ .num = 3, .type = SCARLETT_SWITCH_PAD, .name = NULL},
-		{ .num = 4, .type = SCARLETT_SWITCH_PAD, .name = NULL},
+		{ .num = 3, .type = SCARLETT_SWITCH_GAIN, .name = NULL},
+		{ .num = 4, .type = SCARLETT_SWITCH_GAIN, .name = NULL},
 	},
 
 	.matrix_mux_init = {
@@ -883,6 +893,15 @@ static int scarlett_controls_create_generic(struct usb_mixer_interface *mixer,
 			if (err < 0)
 				return err;
 			break;
+		case SCARLETT_SWITCH_GAIN:
+			sprintf(mx, "Input %d Gain Switch", ctl->num);
+			err = add_new_ctl(mixer, &usb_scarlett_ctl_enum,
+					  scarlett_ctl_enum_resume, 0x01,
+					  0x08, ctl->num, USB_MIXER_S16, 1, mx,
+					  &opt_gain, &elem);
+			if (err < 0)
+				return err;
+			break;
 		}
 	}
 
diff --git a/sound/usb/mixer_scarlett_gen2.c b/sound/usb/mixer_scarlett_gen2.c
index 7d460b1f1735..94b903d95afa 100644
--- a/sound/usb/mixer_scarlett_gen2.c
+++ b/sound/usb/mixer_scarlett_gen2.c
@@ -261,34 +261,34 @@ static const struct scarlett2_device_info s6i6_gen2_info = {
 	},
 
 	.ports = {
-		{
+		[SCARLETT2_PORT_TYPE_NONE] = {
 			.id = 0x000,
 			.num = { 1, 0, 8, 8, 8 },
 			.src_descr = "Off",
 			.src_num_offset = 0,
 		},
-		{
+		[SCARLETT2_PORT_TYPE_ANALOGUE] = {
 			.id = 0x080,
 			.num = { 4, 4, 4, 4, 4 },
 			.src_descr = "Analogue %d",
 			.src_num_offset = 1,
 			.dst_descr = "Analogue Output %02d Playback"
 		},
-		{
+		[SCARLETT2_PORT_TYPE_SPDIF] = {
 			.id = 0x180,
 			.num = { 2, 2, 2, 2, 2 },
 			.src_descr = "S/PDIF %d",
 			.src_num_offset = 1,
 			.dst_descr = "S/PDIF Output %d Playback"
 		},
-		{
+		[SCARLETT2_PORT_TYPE_MIX] = {
 			.id = 0x300,
 			.num = { 10, 18, 18, 18, 18 },
 			.src_descr = "Mix %c",
 			.src_num_offset = 65,
 			.dst_descr = "Mixer Input %02d Capture"
 		},
-		{
+		[SCARLETT2_PORT_TYPE_PCM] = {
 			.id = 0x600,
 			.num = { 6, 6, 6, 6, 6 },
 			.src_descr = "PCM %d",
@@ -317,44 +317,44 @@ static const struct scarlett2_device_info s18i8_gen2_info = {
 	},
 
 	.ports = {
-		{
+		[SCARLETT2_PORT_TYPE_NONE] = {
 			.id = 0x000,
 			.num = { 1, 0, 8, 8, 4 },
 			.src_descr = "Off",
 			.src_num_offset = 0,
 		},
-		{
+		[SCARLETT2_PORT_TYPE_ANALOGUE] = {
 			.id = 0x080,
 			.num = { 8, 6, 6, 6, 6 },
 			.src_descr = "Analogue %d",
 			.src_num_offset = 1,
 			.dst_descr = "Analogue Output %02d Playback"
 		},
-		{
+		[SCARLETT2_PORT_TYPE_SPDIF] = {
+			.id = 0x180,
 			/* S/PDIF outputs aren't available at 192KHz
 			 * but are included in the USB mux I/O
 			 * assignment message anyway
 			 */
-			.id = 0x180,
 			.num = { 2, 2, 2, 2, 2 },
 			.src_descr = "S/PDIF %d",
 			.src_num_offset = 1,
 			.dst_descr = "S/PDIF Output %d Playback"
 		},
-		{
+		[SCARLETT2_PORT_TYPE_ADAT] = {
 			.id = 0x200,
 			.num = { 8, 0, 0, 0, 0 },
 			.src_descr = "ADAT %d",
 			.src_num_offset = 1,
 		},
-		{
+		[SCARLETT2_PORT_TYPE_MIX] = {
 			.id = 0x300,
 			.num = { 10, 18, 18, 18, 18 },
 			.src_descr = "Mix %c",
 			.src_num_offset = 65,
 			.dst_descr = "Mixer Input %02d Capture"
 		},
-		{
+		[SCARLETT2_PORT_TYPE_PCM] = {
 			.id = 0x600,
 			.num = { 20, 18, 18, 14, 10 },
 			.src_descr = "PCM %d",
@@ -387,20 +387,20 @@ static const struct scarlett2_device_info s18i20_gen2_info = {
 	},
 
 	.ports = {
-		{
+		[SCARLETT2_PORT_TYPE_NONE] = {
 			.id = 0x000,
 			.num = { 1, 0, 8, 8, 6 },
 			.src_descr = "Off",
 			.src_num_offset = 0,
 		},
-		{
+		[SCARLETT2_PORT_TYPE_ANALOGUE] = {
 			.id = 0x080,
 			.num = { 8, 10, 10, 10, 10 },
 			.src_descr = "Analogue %d",
 			.src_num_offset = 1,
 			.dst_descr = "Analogue Output %02d Playback"
 		},
-		{
+		[SCARLETT2_PORT_TYPE_SPDIF] = {
 			/* S/PDIF outputs aren't available at 192KHz
 			 * but are included in the USB mux I/O
 			 * assignment message anyway
@@ -411,21 +411,21 @@ static const struct scarlett2_device_info s18i20_gen2_info = {
 			.src_num_offset = 1,
 			.dst_descr = "S/PDIF Output %d Playback"
 		},
-		{
+		[SCARLETT2_PORT_TYPE_ADAT] = {
 			.id = 0x200,
 			.num = { 8, 8, 8, 4, 0 },
 			.src_descr = "ADAT %d",
 			.src_num_offset = 1,
 			.dst_descr = "ADAT Output %d Playback"
 		},
-		{
+		[SCARLETT2_PORT_TYPE_MIX] = {
 			.id = 0x300,
 			.num = { 10, 18, 18, 18, 18 },
 			.src_descr = "Mix %c",
 			.src_num_offset = 65,
 			.dst_descr = "Mixer Input %02d Capture"
 		},
-		{
+		[SCARLETT2_PORT_TYPE_PCM] = {
 			.id = 0x600,
 			.num = { 20, 18, 18, 14, 10 },
 			.src_descr = "PCM %d",
diff --git a/sound/usb/pcm.c b/sound/usb/pcm.c
index ff5ab24f3bd1..9c8930bb00c8 100644
--- a/sound/usb/pcm.c
+++ b/sound/usb/pcm.c
@@ -785,12 +785,8 @@ static int snd_usb_hw_params(struct snd_pcm_substream *substream,
 	if (ret)
 		return ret;
 
-	if (snd_usb_use_vmalloc)
-		ret = snd_pcm_lib_alloc_vmalloc_buffer(substream,
-						       params_buffer_bytes(hw_params));
-	else
-		ret = snd_pcm_lib_malloc_pages(substream,
-					       params_buffer_bytes(hw_params));
+	ret = snd_pcm_lib_malloc_pages(substream,
+				       params_buffer_bytes(hw_params));
 	if (ret < 0)
 		goto stop_pipeline;
 
@@ -857,10 +853,7 @@ static int snd_usb_hw_free(struct snd_pcm_substream *substream)
 		snd_usb_unlock_shutdown(subs->stream->chip);
 	}
 
-	if (snd_usb_use_vmalloc)
-		return snd_pcm_lib_free_vmalloc_buffer(substream);
-	else
-		return snd_pcm_lib_free_pages(substream);
+	return snd_pcm_lib_free_pages(substream);
 }
 
 /*
@@ -1781,7 +1774,6 @@ static const struct snd_pcm_ops snd_usb_playback_ops = {
 	.prepare =	snd_usb_pcm_prepare,
 	.trigger =	snd_usb_substream_playback_trigger,
 	.pointer =	snd_usb_pcm_pointer,
-	.page =		snd_pcm_lib_get_vmalloc_page,
 };
 
 static const struct snd_pcm_ops snd_usb_capture_ops = {
@@ -1793,43 +1785,14 @@ static const struct snd_pcm_ops snd_usb_capture_ops = {
 	.prepare =	snd_usb_pcm_prepare,
 	.trigger =	snd_usb_substream_capture_trigger,
 	.pointer =	snd_usb_pcm_pointer,
-	.page =		snd_pcm_lib_get_vmalloc_page,
-};
-
-static const struct snd_pcm_ops snd_usb_playback_dev_ops = {
-	.open =		snd_usb_pcm_open,
-	.close =	snd_usb_pcm_close,
-	.ioctl =	snd_pcm_lib_ioctl,
-	.hw_params =	snd_usb_hw_params,
-	.hw_free =	snd_usb_hw_free,
-	.prepare =	snd_usb_pcm_prepare,
-	.trigger =	snd_usb_substream_playback_trigger,
-	.pointer =	snd_usb_pcm_pointer,
-	.page =		snd_pcm_sgbuf_ops_page,
-};
-
-static const struct snd_pcm_ops snd_usb_capture_dev_ops = {
-	.open =		snd_usb_pcm_open,
-	.close =	snd_usb_pcm_close,
-	.ioctl =	snd_pcm_lib_ioctl,
-	.hw_params =	snd_usb_hw_params,
-	.hw_free =	snd_usb_hw_free,
-	.prepare =	snd_usb_pcm_prepare,
-	.trigger =	snd_usb_substream_capture_trigger,
-	.pointer =	snd_usb_pcm_pointer,
-	.page =		snd_pcm_sgbuf_ops_page,
 };
 
 void snd_usb_set_pcm_ops(struct snd_pcm *pcm, int stream)
 {
 	const struct snd_pcm_ops *ops;
 
-	if (snd_usb_use_vmalloc)
-		ops = stream == SNDRV_PCM_STREAM_PLAYBACK ?
+	ops = stream == SNDRV_PCM_STREAM_PLAYBACK ?
 			&snd_usb_playback_ops : &snd_usb_capture_ops;
-	else
-		ops = stream == SNDRV_PCM_STREAM_PLAYBACK ?
-			&snd_usb_playback_dev_ops : &snd_usb_capture_dev_ops;
 	snd_pcm_set_ops(pcm, stream, ops);
 }
 
@@ -1839,7 +1802,10 @@ void snd_usb_preallocate_buffer(struct snd_usb_substream *subs)
 	struct snd_pcm_substream *s = pcm->streams[subs->direction].substream;
 	struct device *dev = subs->dev->bus->controller;
 
-	if (!snd_usb_use_vmalloc)
+	if (snd_usb_use_vmalloc)
+		snd_pcm_lib_preallocate_pages(s, SNDRV_DMA_TYPE_VMALLOC,
+					      NULL, 0, 0);
+	else
 		snd_pcm_lib_preallocate_pages(s, SNDRV_DMA_TYPE_DEV_SG,
 					      dev, 64*1024, 512*1024);
 }
diff --git a/sound/usb/usbaudio.h b/sound/usb/usbaudio.h
index feb30f9c1716..ff3cbf653de8 100644
--- a/sound/usb/usbaudio.h
+++ b/sound/usb/usbaudio.h
@@ -120,5 +120,6 @@ int snd_usb_lock_shutdown(struct snd_usb_audio *chip);
 void snd_usb_unlock_shutdown(struct snd_usb_audio *chip);
 
 extern bool snd_usb_use_vmalloc;
+extern bool snd_usb_skip_validation;
 
 #endif /* __USBAUDIO_H */
diff --git a/sound/usb/usx2y/usbusx2yaudio.c b/sound/usb/usx2y/usbusx2yaudio.c
index 89fa287678fc..25a0939f410a 100644
--- a/sound/usb/usx2y/usbusx2yaudio.c
+++ b/sound/usb/usx2y/usbusx2yaudio.c
@@ -970,13 +970,13 @@ static int usX2Y_audio_stream_new(struct snd_card *card, int playback_endpoint,
 	if (playback_endpoint) {
 		snd_pcm_lib_preallocate_pages(pcm->streams[SNDRV_PCM_STREAM_PLAYBACK].substream,
 					      SNDRV_DMA_TYPE_CONTINUOUS,
-					      snd_dma_continuous_data(GFP_KERNEL),
+					      NULL,
 					      64*1024, 128*1024);
 	}
 
 	snd_pcm_lib_preallocate_pages(pcm->streams[SNDRV_PCM_STREAM_CAPTURE].substream,
 				      SNDRV_DMA_TYPE_CONTINUOUS,
-				      snd_dma_continuous_data(GFP_KERNEL),
+				      NULL,
 				      64*1024, 128*1024);
 	usX2Y(card)->pcm_devs++;
 
diff --git a/sound/usb/usx2y/usx2yhwdeppcm.c b/sound/usb/usx2y/usx2yhwdeppcm.c
index ac8960b6b299..997493e839ee 100644
--- a/sound/usb/usx2y/usx2yhwdeppcm.c
+++ b/sound/usb/usx2y/usx2yhwdeppcm.c
@@ -728,11 +728,11 @@ int usX2Y_hwdep_pcm_new(struct snd_card *card)
 	sprintf(pcm->name, NAME_ALLCAPS" hwdep Audio");
 	snd_pcm_lib_preallocate_pages(pcm->streams[SNDRV_PCM_STREAM_PLAYBACK].substream,
 				      SNDRV_DMA_TYPE_CONTINUOUS,
-				      snd_dma_continuous_data(GFP_KERNEL),
+				      NULL,
 				      64*1024, 128*1024);
 	snd_pcm_lib_preallocate_pages(pcm->streams[SNDRV_PCM_STREAM_CAPTURE].substream,
 				      SNDRV_DMA_TYPE_CONTINUOUS,
-				      snd_dma_continuous_data(GFP_KERNEL),
+				      NULL,
 				      64*1024, 128*1024);
 
 	return 0;
diff --git a/sound/usb/validate.c b/sound/usb/validate.c
index 389e8657434a..36ae78c3da3d 100644
--- a/sound/usb/validate.c
+++ b/sound/usb/validate.c
@@ -322,11 +322,28 @@ static bool validate_desc(unsigned char *hdr, int protocol,
 
 bool snd_usb_validate_audio_desc(void *p, int protocol)
 {
-	return validate_desc(p, protocol, audio_validators);
+	unsigned char *c = p;
+	bool valid;
+
+	valid = validate_desc(p, protocol, audio_validators);
+	if (!valid && snd_usb_skip_validation) {
+		print_hex_dump(KERN_ERR, "USB-audio: buggy audio desc: ",
+			       DUMP_PREFIX_NONE, 16, 1, c, c[0], true);
+		valid = true;
+	}
+	return valid;
 }
 
 bool snd_usb_validate_midi_desc(void *p)
 {
-	return validate_desc(p, UAC_VERSION_1, midi_validators);
+	unsigned char *c = p;
+	bool valid;
+
+	valid = validate_desc(p, UAC_VERSION_1, midi_validators);
+	if (!valid && snd_usb_skip_validation) {
+		print_hex_dump(KERN_ERR, "USB-audio: buggy midi desc: ",
+			       DUMP_PREFIX_NONE, 16, 1, c, c[0], true);
+		valid = true;
+	}
+	return valid;
 }
-
diff --git a/sound/x86/intel_hdmi_audio.c b/sound/x86/intel_hdmi_audio.c
index 5fd4e32247a6..cd389d21219a 100644
--- a/sound/x86/intel_hdmi_audio.c
+++ b/sound/x86/intel_hdmi_audio.c
@@ -1708,10 +1708,8 @@ static int hdmi_lpe_audio_probe(struct platform_device *pdev)
 
 	/* get resources */
 	irq = platform_get_irq(pdev, 0);
-	if (irq < 0) {
-		dev_err(&pdev->dev, "Could not get irq resource: %d\n", irq);
+	if (irq < 0)
 		return irq;
-	}
 
 	res_mmio = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	if (!res_mmio) {
diff --git a/tools/arch/x86/include/asm/disabled-features.h b/tools/arch/x86/include/asm/disabled-features.h
index a5ea841cc6d2..8e1d0bb46361 100644
--- a/tools/arch/x86/include/asm/disabled-features.h
+++ b/tools/arch/x86/include/asm/disabled-features.h
@@ -22,7 +22,7 @@
 # define DISABLE_SMAP	(1<<(X86_FEATURE_SMAP & 31))
 #endif
 
-#ifdef CONFIG_X86_INTEL_UMIP
+#ifdef CONFIG_X86_UMIP
 # define DISABLE_UMIP	0
 #else
 # define DISABLE_UMIP	(1<<(X86_FEATURE_UMIP & 31))
diff --git a/tools/arch/x86/tools/gen-insn-attr-x86.awk b/tools/arch/x86/tools/gen-insn-attr-x86.awk
index b02a36b2c14f..a42015b305f4 100644
--- a/tools/arch/x86/tools/gen-insn-attr-x86.awk
+++ b/tools/arch/x86/tools/gen-insn-attr-x86.awk
@@ -69,7 +69,7 @@ BEGIN {
 
 	lprefix1_expr = "\\((66|!F3)\\)"
 	lprefix2_expr = "\\(F3\\)"
-	lprefix3_expr = "\\((F2|!F3|66\\&F2)\\)"
+	lprefix3_expr = "\\((F2|!F3|66&F2)\\)"
 	lprefix_expr = "\\((66|F2|F3)\\)"
 	max_lprefix = 4
 
@@ -257,7 +257,7 @@ function convert_operands(count,opnd,       i,j,imm,mod)
 	return add_flags(imm, mod)
 }
 
-/^[0-9a-f]+\:/ {
+/^[0-9a-f]+:/ {
 	if (NR == 1)
 		next
 	# get index
diff --git a/tools/lib/lockdep/include/liblockdep/common.h b/tools/lib/lockdep/include/liblockdep/common.h
index a81d91d4fc78..a6d7ee5f18ba 100644
--- a/tools/lib/lockdep/include/liblockdep/common.h
+++ b/tools/lib/lockdep/include/liblockdep/common.h
@@ -42,8 +42,7 @@ void lockdep_init_map(struct lockdep_map *lock, const char *name,
 void lock_acquire(struct lockdep_map *lock, unsigned int subclass,
 			int trylock, int read, int check,
 			struct lockdep_map *nest_lock, unsigned long ip);
-void lock_release(struct lockdep_map *lock, int nested,
-			unsigned long ip);
+void lock_release(struct lockdep_map *lock, unsigned long ip);
 void lockdep_reset_lock(struct lockdep_map *lock);
 void lockdep_register_key(struct lock_class_key *key);
 void lockdep_unregister_key(struct lock_class_key *key);
diff --git a/tools/lib/lockdep/include/liblockdep/mutex.h b/tools/lib/lockdep/include/liblockdep/mutex.h
index 783dd0df06f9..bd106b82759b 100644
--- a/tools/lib/lockdep/include/liblockdep/mutex.h
+++ b/tools/lib/lockdep/include/liblockdep/mutex.h
@@ -42,7 +42,7 @@ static inline int liblockdep_pthread_mutex_lock(liblockdep_pthread_mutex_t *lock
 
 static inline int liblockdep_pthread_mutex_unlock(liblockdep_pthread_mutex_t *lock)
 {
-	lock_release(&lock->dep_map, 0, (unsigned long)_RET_IP_);
+	lock_release(&lock->dep_map, (unsigned long)_RET_IP_);
 	return pthread_mutex_unlock(&lock->mutex);
 }
 
diff --git a/tools/lib/lockdep/include/liblockdep/rwlock.h b/tools/lib/lockdep/include/liblockdep/rwlock.h
index 365762e3a1ea..6d5d2932bf4d 100644
--- a/tools/lib/lockdep/include/liblockdep/rwlock.h
+++ b/tools/lib/lockdep/include/liblockdep/rwlock.h
@@ -44,7 +44,7 @@ static inline int liblockdep_pthread_rwlock_rdlock(liblockdep_pthread_rwlock_t *
 
 static inline int liblockdep_pthread_rwlock_unlock(liblockdep_pthread_rwlock_t *lock)
 {
-	lock_release(&lock->dep_map, 0, (unsigned long)_RET_IP_);
+	lock_release(&lock->dep_map, (unsigned long)_RET_IP_);
 	return pthread_rwlock_unlock(&lock->rwlock);
 }
 
diff --git a/tools/lib/lockdep/preload.c b/tools/lib/lockdep/preload.c
index 76245d16196d..8f1adbe887b2 100644
--- a/tools/lib/lockdep/preload.c
+++ b/tools/lib/lockdep/preload.c
@@ -270,7 +270,7 @@ int pthread_mutex_lock(pthread_mutex_t *mutex)
 	 */
 	r = ll_pthread_mutex_lock(mutex);
 	if (r)
-		lock_release(&__get_lock(mutex)->dep_map, 0, (unsigned long)_RET_IP_);
+		lock_release(&__get_lock(mutex)->dep_map, (unsigned long)_RET_IP_);
 
 	return r;
 }
@@ -284,7 +284,7 @@ int pthread_mutex_trylock(pthread_mutex_t *mutex)
 	lock_acquire(&__get_lock(mutex)->dep_map, 0, 1, 0, 1, NULL, (unsigned long)_RET_IP_);
 	r = ll_pthread_mutex_trylock(mutex);
 	if (r)
-		lock_release(&__get_lock(mutex)->dep_map, 0, (unsigned long)_RET_IP_);
+		lock_release(&__get_lock(mutex)->dep_map, (unsigned long)_RET_IP_);
 
 	return r;
 }
@@ -295,7 +295,7 @@ int pthread_mutex_unlock(pthread_mutex_t *mutex)
 
 	try_init_preload();
 
-	lock_release(&__get_lock(mutex)->dep_map, 0, (unsigned long)_RET_IP_);
+	lock_release(&__get_lock(mutex)->dep_map, (unsigned long)_RET_IP_);
 	/*
 	 * Just like taking a lock, only in reverse!
 	 *
@@ -355,7 +355,7 @@ int pthread_rwlock_rdlock(pthread_rwlock_t *rwlock)
 	lock_acquire(&__get_lock(rwlock)->dep_map, 0, 0, 2, 1, NULL, (unsigned long)_RET_IP_);
 	r = ll_pthread_rwlock_rdlock(rwlock);
 	if (r)
-		lock_release(&__get_lock(rwlock)->dep_map, 0, (unsigned long)_RET_IP_);
+		lock_release(&__get_lock(rwlock)->dep_map, (unsigned long)_RET_IP_);
 
 	return r;
 }
@@ -369,7 +369,7 @@ int pthread_rwlock_tryrdlock(pthread_rwlock_t *rwlock)
 	lock_acquire(&__get_lock(rwlock)->dep_map, 0, 1, 2, 1, NULL, (unsigned long)_RET_IP_);
 	r = ll_pthread_rwlock_tryrdlock(rwlock);
 	if (r)
-		lock_release(&__get_lock(rwlock)->dep_map, 0, (unsigned long)_RET_IP_);
+		lock_release(&__get_lock(rwlock)->dep_map, (unsigned long)_RET_IP_);
 
 	return r;
 }
@@ -383,7 +383,7 @@ int pthread_rwlock_trywrlock(pthread_rwlock_t *rwlock)
 	lock_acquire(&__get_lock(rwlock)->dep_map, 0, 1, 0, 1, NULL, (unsigned long)_RET_IP_);
 	r = ll_pthread_rwlock_trywrlock(rwlock);
 	if (r)
-                lock_release(&__get_lock(rwlock)->dep_map, 0, (unsigned long)_RET_IP_);
+		lock_release(&__get_lock(rwlock)->dep_map, (unsigned long)_RET_IP_);
 
 	return r;
 }
@@ -397,7 +397,7 @@ int pthread_rwlock_wrlock(pthread_rwlock_t *rwlock)
 	lock_acquire(&__get_lock(rwlock)->dep_map, 0, 0, 0, 1, NULL, (unsigned long)_RET_IP_);
 	r = ll_pthread_rwlock_wrlock(rwlock);
 	if (r)
-		lock_release(&__get_lock(rwlock)->dep_map, 0, (unsigned long)_RET_IP_);
+		lock_release(&__get_lock(rwlock)->dep_map, (unsigned long)_RET_IP_);
 
 	return r;
 }
@@ -408,7 +408,7 @@ int pthread_rwlock_unlock(pthread_rwlock_t *rwlock)
 
         init_preload();
 
-	lock_release(&__get_lock(rwlock)->dep_map, 0, (unsigned long)_RET_IP_);
+	lock_release(&__get_lock(rwlock)->dep_map, (unsigned long)_RET_IP_);
 	r = ll_pthread_rwlock_unlock(rwlock);
 	if (r)
 		lock_acquire(&__get_lock(rwlock)->dep_map, 0, 0, 0, 1, NULL, (unsigned long)_RET_IP_);
diff --git a/tools/memory-model/Documentation/explanation.txt b/tools/memory-model/Documentation/explanation.txt
index 488f11f6c588..e91a2eb19592 100644
--- a/tools/memory-model/Documentation/explanation.txt
+++ b/tools/memory-model/Documentation/explanation.txt
@@ -27,9 +27,10 @@ Explanation of the Linux-Kernel Memory Consistency Model
   19. AND THEN THERE WAS ALPHA
   20. THE HAPPENS-BEFORE RELATION: hb
   21. THE PROPAGATES-BEFORE RELATION: pb
-  22. RCU RELATIONS: rcu-link, rcu-gp, rcu-rscsi, rcu-fence, and rb
+  22. RCU RELATIONS: rcu-link, rcu-gp, rcu-rscsi, rcu-order, rcu-fence, and rb
   23. LOCKING
-  24. ODDS AND ENDS
+  24. PLAIN ACCESSES AND DATA RACES
+  25. ODDS AND ENDS
 
 
 
@@ -42,8 +43,7 @@ linux-kernel.bell and linux-kernel.cat files that make up the formal
 version of the model; they are extremely terse and their meanings are
 far from clear.
 
-This document describes the ideas underlying the LKMM, but excluding
-the modeling of bare C (or plain) shared memory accesses.  It is meant
+This document describes the ideas underlying the LKMM.  It is meant
 for people who want to understand how the model was designed.  It does
 not go into the details of the code in the .bell and .cat files;
 rather, it explains in English what the code expresses symbolically.
@@ -206,7 +206,7 @@ goes like this:
 	P0 stores 1 to buf before storing 1 to flag, since it executes
 	its instructions in order.
 
-	Since an instruction (in this case, P1's store to flag) cannot
+	Since an instruction (in this case, P0's store to flag) cannot
 	execute before itself, the specified outcome is impossible.
 
 However, real computer hardware almost never follows the Sequential
@@ -419,7 +419,7 @@ example:
 
 The object code might call f(5) either before or after g(6); the
 memory model cannot assume there is a fixed program order relation
-between them.  (In fact, if the functions are inlined then the
+between them.  (In fact, if the function calls are inlined then the
 compiler might even interleave their object code.)
 
 
@@ -499,7 +499,7 @@ different CPUs (external reads-from, or rfe).
 
 For our purposes, a memory location's initial value is treated as
 though it had been written there by an imaginary initial store that
-executes on a separate CPU before the program runs.
+executes on a separate CPU before the main program runs.
 
 Usage of the rf relation implicitly assumes that loads will always
 read from a single store.  It doesn't apply properly in the presence
@@ -857,7 +857,7 @@ outlined above.  These restrictions involve the necessity of
 maintaining cache coherence and the fact that a CPU can't operate on a
 value before it knows what that value is, among other things.
 
-The formal version of the LKMM is defined by five requirements, or
+The formal version of the LKMM is defined by six requirements, or
 axioms:
 
 	Sequential consistency per variable: This requires that the
@@ -877,10 +877,14 @@ axioms:
 	grace periods obey the rules of RCU, in particular, the
 	Grace-Period Guarantee.
 
+	Plain-coherence: This requires that plain memory accesses
+	(those not using READ_ONCE(), WRITE_ONCE(), etc.) must obey
+	the operational model's rules regarding cache coherence.
+
 The first and second are quite common; they can be found in many
 memory models (such as those for C11/C++11).  The "happens-before" and
 "propagation" axioms have analogs in other memory models as well.  The
-"rcu" axiom is specific to the LKMM.
+"rcu" and "plain-coherence" axioms are specific to the LKMM.
 
 Each of these axioms is discussed below.
 
@@ -955,7 +959,7 @@ atomic update.  This is what the LKMM's "atomic" axiom says.
 THE PRESERVED PROGRAM ORDER RELATION: ppo
 -----------------------------------------
 
-There are many situations where a CPU is obligated to execute two
+There are many situations where a CPU is obliged to execute two
 instructions in program order.  We amalgamate them into the ppo (for
 "preserved program order") relation, which links the po-earlier
 instruction to the po-later instruction and is thus a sub-relation of
@@ -1425,8 +1429,8 @@ they execute means that it cannot have cycles.  This requirement is
 the content of the LKMM's "propagation" axiom.
 
 
-RCU RELATIONS: rcu-link, rcu-gp, rcu-rscsi, rcu-fence, and rb
--------------------------------------------------------------
+RCU RELATIONS: rcu-link, rcu-gp, rcu-rscsi, rcu-order, rcu-fence, and rb
+------------------------------------------------------------------------
 
 RCU (Read-Copy-Update) is a powerful synchronization mechanism.  It
 rests on two concepts: grace periods and read-side critical sections.
@@ -1536,29 +1540,29 @@ Z's CPU before Z begins but doesn't propagate to some other CPU until
 after X ends.)  Similarly, X ->rcu-rscsi Y ->rcu-link Z says that X is
 the end of a critical section which starts before Z begins.
 
-The LKMM goes on to define the rcu-fence relation as a sequence of
+The LKMM goes on to define the rcu-order relation as a sequence of
 rcu-gp and rcu-rscsi links separated by rcu-link links, in which the
 number of rcu-gp links is >= the number of rcu-rscsi links.  For
 example:
 
 	X ->rcu-gp Y ->rcu-link Z ->rcu-rscsi T ->rcu-link U ->rcu-gp V
 
-would imply that X ->rcu-fence V, because this sequence contains two
+would imply that X ->rcu-order V, because this sequence contains two
 rcu-gp links and one rcu-rscsi link.  (It also implies that
-X ->rcu-fence T and Z ->rcu-fence V.)  On the other hand:
+X ->rcu-order T and Z ->rcu-order V.)  On the other hand:
 
 	X ->rcu-rscsi Y ->rcu-link Z ->rcu-rscsi T ->rcu-link U ->rcu-gp V
 
-does not imply X ->rcu-fence V, because the sequence contains only
+does not imply X ->rcu-order V, because the sequence contains only
 one rcu-gp link but two rcu-rscsi links.
 
-The rcu-fence relation is important because the Grace Period Guarantee
-means that rcu-fence acts kind of like a strong fence.  In particular,
-E ->rcu-fence F implies not only that E begins before F ends, but also
-that any write po-before E will propagate to every CPU before any
-instruction po-after F can execute.  (However, it does not imply that
-E must execute before F; in fact, each synchronize_rcu() fence event
-is linked to itself by rcu-fence as a degenerate case.)
+The rcu-order relation is important because the Grace Period Guarantee
+means that rcu-order links act kind of like strong fences.  In
+particular, E ->rcu-order F implies not only that E begins before F
+ends, but also that any write po-before E will propagate to every CPU
+before any instruction po-after F can execute.  (However, it does not
+imply that E must execute before F; in fact, each synchronize_rcu()
+fence event is linked to itself by rcu-order as a degenerate case.)
 
 To prove this in full generality requires some intellectual effort.
 We'll consider just a very simple case:
@@ -1572,7 +1576,7 @@ and there are events X, Y and a read-side critical section C such that:
 
 	2. X comes "before" Y in some sense (including rfe, co and fr);
 
-	2. Y is po-before Z;
+	3. Y is po-before Z;
 
 	4. Z is the rcu_read_unlock() event marking the end of C;
 
@@ -1585,7 +1589,26 @@ G's CPU before G starts must propagate to every CPU before C starts.
 In particular, the write propagates to every CPU before F finishes
 executing and hence before any instruction po-after F can execute.
 This sort of reasoning can be extended to handle all the situations
-covered by rcu-fence.
+covered by rcu-order.
+
+The rcu-fence relation is a simple extension of rcu-order.  While
+rcu-order only links certain fence events (calls to synchronize_rcu(),
+rcu_read_lock(), or rcu_read_unlock()), rcu-fence links any events
+that are separated by an rcu-order link.  This is analogous to the way
+the strong-fence relation links events that are separated by an
+smp_mb() fence event (as mentioned above, rcu-order links act kind of
+like strong fences).  Written symbolically, X ->rcu-fence Y means
+there are fence events E and F such that:
+
+	X ->po E ->rcu-order F ->po Y.
+
+From the discussion above, we see this implies not only that X
+executes before Y, but also (if X is a store) that X propagates to
+every CPU before Y executes.  Thus rcu-fence is sort of a
+"super-strong" fence: Unlike the original strong fences (smp_mb() and
+synchronize_rcu()), rcu-fence is able to link events on different
+CPUs.  (Perhaps this fact should lead us to say that rcu-fence isn't
+really a fence at all!)
 
 Finally, the LKMM defines the RCU-before (rb) relation in terms of
 rcu-fence.  This is done in essentially the same way as the pb
@@ -1596,7 +1619,7 @@ before F, just as E ->pb F does (and for much the same reasons).
 Putting this all together, the LKMM expresses the Grace Period
 Guarantee by requiring that the rb relation does not contain a cycle.
 Equivalently, this "rcu" axiom requires that there are no events E
-and F with E ->rcu-link F ->rcu-fence E.  Or to put it a third way,
+and F with E ->rcu-link F ->rcu-order E.  Or to put it a third way,
 the axiom requires that there are no cycles consisting of rcu-gp and
 rcu-rscsi alternating with rcu-link, where the number of rcu-gp links
 is >= the number of rcu-rscsi links.
@@ -1750,7 +1773,7 @@ addition to normal RCU.  The ideas involved are much the same as
 above, with new relations srcu-gp and srcu-rscsi added to represent
 SRCU grace periods and read-side critical sections.  There is a
 restriction on the srcu-gp and srcu-rscsi links that can appear in an
-rcu-fence sequence (the srcu-rscsi links must be paired with srcu-gp
+rcu-order sequence (the srcu-rscsi links must be paired with srcu-gp
 links having the same SRCU domain with proper nesting); the details
 are relatively unimportant.
 
@@ -1896,6 +1919,521 @@ architectures supported by the Linux kernel, albeit for various
 differing reasons.
 
 
+PLAIN ACCESSES AND DATA RACES
+-----------------------------
+
+In the LKMM, memory accesses such as READ_ONCE(x), atomic_inc(&y),
+smp_load_acquire(&z), and so on are collectively referred to as
+"marked" accesses, because they are all annotated with special
+operations of one kind or another.  Ordinary C-language memory
+accesses such as x or y = 0 are simply called "plain" accesses.
+
+Early versions of the LKMM had nothing to say about plain accesses.
+The C standard allows compilers to assume that the variables affected
+by plain accesses are not concurrently read or written by any other
+threads or CPUs.  This leaves compilers free to implement all manner
+of transformations or optimizations of code containing plain accesses,
+making such code very difficult for a memory model to handle.
+
+Here is just one example of a possible pitfall:
+
+	int a = 6;
+	int *x = &a;
+
+	P0()
+	{
+		int *r1;
+		int r2 = 0;
+
+		r1 = x;
+		if (r1 != NULL)
+			r2 = READ_ONCE(*r1);
+	}
+
+	P1()
+	{
+		WRITE_ONCE(x, NULL);
+	}
+
+On the face of it, one would expect that when this code runs, the only
+possible final values for r2 are 6 and 0, depending on whether or not
+P1's store to x propagates to P0 before P0's load from x executes.
+But since P0's load from x is a plain access, the compiler may decide
+to carry out the load twice (for the comparison against NULL, then again
+for the READ_ONCE()) and eliminate the temporary variable r1.  The
+object code generated for P0 could therefore end up looking rather
+like this:
+
+	P0()
+	{
+		int r2 = 0;
+
+		if (x != NULL)
+			r2 = READ_ONCE(*x);
+	}
+
+And now it is obvious that this code runs the risk of dereferencing a
+NULL pointer, because P1's store to x might propagate to P0 after the
+test against NULL has been made but before the READ_ONCE() executes.
+If the original code had said "r1 = READ_ONCE(x)" instead of "r1 = x",
+the compiler would not have performed this optimization and there
+would be no possibility of a NULL-pointer dereference.
+
+Given the possibility of transformations like this one, the LKMM
+doesn't try to predict all possible outcomes of code containing plain
+accesses.  It is instead content to determine whether the code
+violates the compiler's assumptions, which would render the ultimate
+outcome undefined.
+
+In technical terms, the compiler is allowed to assume that when the
+program executes, there will not be any data races.  A "data race"
+occurs when two conflicting memory accesses execute concurrently;
+two memory accesses "conflict" if:
+
+	they access the same location,
+
+	they occur on different CPUs (or in different threads on the
+	same CPU),
+
+	at least one of them is a plain access,
+
+	and at least one of them is a store.
+
+The LKMM tries to determine whether a program contains two conflicting
+accesses which may execute concurrently; if it does then the LKMM says
+there is a potential data race and makes no predictions about the
+program's outcome.
+
+Determining whether two accesses conflict is easy; you can see that
+all the concepts involved in the definition above are already part of
+the memory model.  The hard part is telling whether they may execute
+concurrently.  The LKMM takes a conservative attitude, assuming that
+accesses may be concurrent unless it can prove they cannot.
+
+If two memory accesses aren't concurrent then one must execute before
+the other.  Therefore the LKMM decides two accesses aren't concurrent
+if they can be connected by a sequence of hb, pb, and rb links
+(together referred to as xb, for "executes before").  However, there
+are two complicating factors.
+
+If X is a load and X executes before a store Y, then indeed there is
+no danger of X and Y being concurrent.  After all, Y can't have any
+effect on the value obtained by X until the memory subsystem has
+propagated Y from its own CPU to X's CPU, which won't happen until
+some time after Y executes and thus after X executes.  But if X is a
+store, then even if X executes before Y it is still possible that X
+will propagate to Y's CPU just as Y is executing.  In such a case X
+could very well interfere somehow with Y, and we would have to
+consider X and Y to be concurrent.
+
+Therefore when X is a store, for X and Y to be non-concurrent the LKMM
+requires not only that X must execute before Y but also that X must
+propagate to Y's CPU before Y executes.  (Or vice versa, of course, if
+Y executes before X -- then Y must propagate to X's CPU before X
+executes if Y is a store.)  This is expressed by the visibility
+relation (vis), where X ->vis Y is defined to hold if there is an
+intermediate event Z such that:
+
+	X is connected to Z by a possibly empty sequence of
+	cumul-fence links followed by an optional rfe link (if none of
+	these links are present, X and Z are the same event),
+
+and either:
+
+	Z is connected to Y by a strong-fence link followed by a
+	possibly empty sequence of xb links,
+
+or:
+
+	Z is on the same CPU as Y and is connected to Y by a possibly
+	empty sequence of xb links (again, if the sequence is empty it
+	means Z and Y are the same event).
+
+The motivations behind this definition are straightforward:
+
+	cumul-fence memory barriers force stores that are po-before
+	the barrier to propagate to other CPUs before stores that are
+	po-after the barrier.
+
+	An rfe link from an event W to an event R says that R reads
+	from W, which certainly means that W must have propagated to
+	R's CPU before R executed.
+
+	strong-fence memory barriers force stores that are po-before
+	the barrier, or that propagate to the barrier's CPU before the
+	barrier executes, to propagate to all CPUs before any events
+	po-after the barrier can execute.
+
+To see how this works out in practice, consider our old friend, the MP
+pattern (with fences and statement labels, but without the conditional
+test):
+
+	int buf = 0, flag = 0;
+
+	P0()
+	{
+		X: WRITE_ONCE(buf, 1);
+		   smp_wmb();
+		W: WRITE_ONCE(flag, 1);
+	}
+
+	P1()
+	{
+		int r1;
+		int r2 = 0;
+
+		Z: r1 = READ_ONCE(flag);
+		   smp_rmb();
+		Y: r2 = READ_ONCE(buf);
+	}
+
+The smp_wmb() memory barrier gives a cumul-fence link from X to W, and
+assuming r1 = 1 at the end, there is an rfe link from W to Z.  This
+means that the store to buf must propagate from P0 to P1 before Z
+executes.  Next, Z and Y are on the same CPU and the smp_rmb() fence
+provides an xb link from Z to Y (i.e., it forces Z to execute before
+Y).  Therefore we have X ->vis Y: X must propagate to Y's CPU before Y
+executes.
+
+The second complicating factor mentioned above arises from the fact
+that when we are considering data races, some of the memory accesses
+are plain.  Now, although we have not said so explicitly, up to this
+point most of the relations defined by the LKMM (ppo, hb, prop,
+cumul-fence, pb, and so on -- including vis) apply only to marked
+accesses.
+
+There are good reasons for this restriction.  The compiler is not
+allowed to apply fancy transformations to marked accesses, and
+consequently each such access in the source code corresponds more or
+less directly to a single machine instruction in the object code.  But
+plain accesses are a different story; the compiler may combine them,
+split them up, duplicate them, eliminate them, invent new ones, and
+who knows what else.  Seeing a plain access in the source code tells
+you almost nothing about what machine instructions will end up in the
+object code.
+
+Fortunately, the compiler isn't completely free; it is subject to some
+limitations.  For one, it is not allowed to introduce a data race into
+the object code if the source code does not already contain a data
+race (if it could, memory models would be useless and no multithreaded
+code would be safe!).  For another, it cannot move a plain access past
+a compiler barrier.
+
+A compiler barrier is a kind of fence, but as the name implies, it
+only affects the compiler; it does not necessarily have any effect on
+how instructions are executed by the CPU.  In Linux kernel source
+code, the barrier() function is a compiler barrier.  It doesn't give
+rise directly to any machine instructions in the object code; rather,
+it affects how the compiler generates the rest of the object code.
+Given source code like this:
+
+	... some memory accesses ...
+	barrier();
+	... some other memory accesses ...
+
+the barrier() function ensures that the machine instructions
+corresponding to the first group of accesses will all end po-before
+any machine instructions corresponding to the second group of accesses
+-- even if some of the accesses are plain.  (Of course, the CPU may
+then execute some of those accesses out of program order, but we
+already know how to deal with such issues.)  Without the barrier()
+there would be no such guarantee; the two groups of accesses could be
+intermingled or even reversed in the object code.
+
+The LKMM doesn't say much about the barrier() function, but it does
+require that all fences are also compiler barriers.  In addition, it
+requires that the ordering properties of memory barriers such as
+smp_rmb() or smp_store_release() apply to plain accesses as well as to
+marked accesses.
+
+This is the key to analyzing data races.  Consider the MP pattern
+again, now using plain accesses for buf:
+
+	int buf = 0, flag = 0;
+
+	P0()
+	{
+		U: buf = 1;
+		   smp_wmb();
+		X: WRITE_ONCE(flag, 1);
+	}
+
+	P1()
+	{
+		int r1;
+		int r2 = 0;
+
+		Y: r1 = READ_ONCE(flag);
+		   if (r1) {
+			   smp_rmb();
+			V: r2 = buf;
+		   }
+	}
+
+This program does not contain a data race.  Although the U and V
+accesses conflict, the LKMM can prove they are not concurrent as
+follows:
+
+	The smp_wmb() fence in P0 is both a compiler barrier and a
+	cumul-fence.  It guarantees that no matter what hash of
+	machine instructions the compiler generates for the plain
+	access U, all those instructions will be po-before the fence.
+	Consequently U's store to buf, no matter how it is carried out
+	at the machine level, must propagate to P1 before X's store to
+	flag does.
+
+	X and Y are both marked accesses.  Hence an rfe link from X to
+	Y is a valid indicator that X propagated to P1 before Y
+	executed, i.e., X ->vis Y.  (And if there is no rfe link then
+	r1 will be 0, so V will not be executed and ipso facto won't
+	race with U.)
+
+	The smp_rmb() fence in P1 is a compiler barrier as well as a
+	fence.  It guarantees that all the machine-level instructions
+	corresponding to the access V will be po-after the fence, and
+	therefore any loads among those instructions will execute
+	after the fence does and hence after Y does.
+
+Thus U's store to buf is forced to propagate to P1 before V's load
+executes (assuming V does execute), ruling out the possibility of a
+data race between them.
+
+This analysis illustrates how the LKMM deals with plain accesses in
+general.  Suppose R is a plain load and we want to show that R
+executes before some marked access E.  We can do this by finding a
+marked access X such that R and X are ordered by a suitable fence and
+X ->xb* E.  If E was also a plain access, we would also look for a
+marked access Y such that X ->xb* Y, and Y and E are ordered by a
+fence.  We describe this arrangement by saying that R is
+"post-bounded" by X and E is "pre-bounded" by Y.
+
+In fact, we go one step further: Since R is a read, we say that R is
+"r-post-bounded" by X.  Similarly, E would be "r-pre-bounded" or
+"w-pre-bounded" by Y, depending on whether E was a store or a load.
+This distinction is needed because some fences affect only loads
+(i.e., smp_rmb()) and some affect only stores (smp_wmb()); otherwise
+the two types of bounds are the same.  And as a degenerate case, we
+say that a marked access pre-bounds and post-bounds itself (e.g., if R
+above were a marked load then X could simply be taken to be R itself.)
+
+The need to distinguish between r- and w-bounding raises yet another
+issue.  When the source code contains a plain store, the compiler is
+allowed to put plain loads of the same location into the object code.
+For example, given the source code:
+
+	x = 1;
+
+the compiler is theoretically allowed to generate object code that
+looks like:
+
+	if (x != 1)
+		x = 1;
+
+thereby adding a load (and possibly replacing the store entirely).
+For this reason, whenever the LKMM requires a plain store to be
+w-pre-bounded or w-post-bounded by a marked access, it also requires
+the store to be r-pre-bounded or r-post-bounded, so as to handle cases
+where the compiler adds a load.
+
+(This may be overly cautious.  We don't know of any examples where a
+compiler has augmented a store with a load in this fashion, and the
+Linux kernel developers would probably fight pretty hard to change a
+compiler if it ever did this.  Still, better safe than sorry.)
+
+Incidentally, the other tranformation -- augmenting a plain load by
+adding in a store to the same location -- is not allowed.  This is
+because the compiler cannot know whether any other CPUs might perform
+a concurrent load from that location.  Two concurrent loads don't
+constitute a race (they can't interfere with each other), but a store
+does race with a concurrent load.  Thus adding a store might create a
+data race where one was not already present in the source code,
+something the compiler is forbidden to do.  Augmenting a store with a
+load, on the other hand, is acceptable because doing so won't create a
+data race unless one already existed.
+
+The LKMM includes a second way to pre-bound plain accesses, in
+addition to fences: an address dependency from a marked load.  That
+is, in the sequence:
+
+	p = READ_ONCE(ptr);
+	r = *p;
+
+the LKMM says that the marked load of ptr pre-bounds the plain load of
+*p; the marked load must execute before any of the machine
+instructions corresponding to the plain load.  This is a reasonable
+stipulation, since after all, the CPU can't perform the load of *p
+until it knows what value p will hold.  Furthermore, without some
+assumption like this one, some usages typical of RCU would count as
+data races.  For example:
+
+	int a = 1, b;
+	int *ptr = &a;
+
+	P0()
+	{
+		b = 2;
+		rcu_assign_pointer(ptr, &b);
+	}
+
+	P1()
+	{
+		int *p;
+		int r;
+
+		rcu_read_lock();
+		p = rcu_dereference(ptr);
+		r = *p;
+		rcu_read_unlock();
+	}
+
+(In this example the rcu_read_lock() and rcu_read_unlock() calls don't
+really do anything, because there aren't any grace periods.  They are
+included merely for the sake of good form; typically P0 would call
+synchronize_rcu() somewhere after the rcu_assign_pointer().)
+
+rcu_assign_pointer() performs a store-release, so the plain store to b
+is definitely w-post-bounded before the store to ptr, and the two
+stores will propagate to P1 in that order.  However, rcu_dereference()
+is only equivalent to READ_ONCE().  While it is a marked access, it is
+not a fence or compiler barrier.  Hence the only guarantee we have
+that the load of ptr in P1 is r-pre-bounded before the load of *p
+(thus avoiding a race) is the assumption about address dependencies.
+
+This is a situation where the compiler can undermine the memory model,
+and a certain amount of care is required when programming constructs
+like this one.  In particular, comparisons between the pointer and
+other known addresses can cause trouble.  If you have something like:
+
+	p = rcu_dereference(ptr);
+	if (p == &x)
+		r = *p;
+
+then the compiler just might generate object code resembling:
+
+	p = rcu_dereference(ptr);
+	if (p == &x)
+		r = x;
+
+or even:
+
+	rtemp = x;
+	p = rcu_dereference(ptr);
+	if (p == &x)
+		r = rtemp;
+
+which would invalidate the memory model's assumption, since the CPU
+could now perform the load of x before the load of ptr (there might be
+a control dependency but no address dependency at the machine level).
+
+Finally, it turns out there is a situation in which a plain write does
+not need to be w-post-bounded: when it is separated from the
+conflicting access by a fence.  At first glance this may seem
+impossible.  After all, to be conflicting the second access has to be
+on a different CPU from the first, and fences don't link events on
+different CPUs.  Well, normal fences don't -- but rcu-fence can!
+Here's an example:
+
+	int x, y;
+
+	P0()
+	{
+		WRITE_ONCE(x, 1);
+		synchronize_rcu();
+		y = 3;
+	}
+
+	P1()
+	{
+		rcu_read_lock();
+		if (READ_ONCE(x) == 0)
+			y = 2;
+		rcu_read_unlock();
+	}
+
+Do the plain stores to y race?  Clearly not if P1 reads a non-zero
+value for x, so let's assume the READ_ONCE(x) does obtain 0.  This
+means that the read-side critical section in P1 must finish executing
+before the grace period in P0 does, because RCU's Grace-Period
+Guarantee says that otherwise P0's store to x would have propagated to
+P1 before the critical section started and so would have been visible
+to the READ_ONCE().  (Another way of putting it is that the fre link
+from the READ_ONCE() to the WRITE_ONCE() gives rise to an rcu-link
+between those two events.)
+
+This means there is an rcu-fence link from P1's "y = 2" store to P0's
+"y = 3" store, and consequently the first must propagate from P1 to P0
+before the second can execute.  Therefore the two stores cannot be
+concurrent and there is no race, even though P1's plain store to y
+isn't w-post-bounded by any marked accesses.
+
+Putting all this material together yields the following picture.  For
+two conflicting stores W and W', where W ->co W', the LKMM says the
+stores don't race if W can be linked to W' by a
+
+	w-post-bounded ; vis ; w-pre-bounded
+
+sequence.  If W is plain then they also have to be linked by an
+
+	r-post-bounded ; xb* ; w-pre-bounded
+
+sequence, and if W' is plain then they also have to be linked by a
+
+	w-post-bounded ; vis ; r-pre-bounded
+
+sequence.  For a conflicting load R and store W, the LKMM says the two
+accesses don't race if R can be linked to W by an
+
+	r-post-bounded ; xb* ; w-pre-bounded
+
+sequence or if W can be linked to R by a
+
+	w-post-bounded ; vis ; r-pre-bounded
+
+sequence.  For the cases involving a vis link, the LKMM also accepts
+sequences in which W is linked to W' or R by a
+
+	strong-fence ; xb* ; {w and/or r}-pre-bounded
+
+sequence with no post-bounding, and in every case the LKMM also allows
+the link simply to be a fence with no bounding at all.  If no sequence
+of the appropriate sort exists, the LKMM says that the accesses race.
+
+There is one more part of the LKMM related to plain accesses (although
+not to data races) we should discuss.  Recall that many relations such
+as hb are limited to marked accesses only.  As a result, the
+happens-before, propagates-before, and rcu axioms (which state that
+various relation must not contain a cycle) doesn't apply to plain
+accesses.  Nevertheless, we do want to rule out such cycles, because
+they don't make sense even for plain accesses.
+
+To this end, the LKMM imposes three extra restrictions, together
+called the "plain-coherence" axiom because of their resemblance to the
+rules used by the operational model to ensure cache coherence (that
+is, the rules governing the memory subsystem's choice of a store to
+satisfy a load request and its determination of where a store will
+fall in the coherence order):
+
+	If R and W conflict and it is possible to link R to W by one
+	of the xb* sequences listed above, then W ->rfe R is not
+	allowed (i.e., a load cannot read from a store that it
+	executes before, even if one or both is plain).
+
+	If W and R conflict and it is possible to link W to R by one
+	of the vis sequences listed above, then R ->fre W is not
+	allowed (i.e., if a store is visible to a load then the load
+	must read from that store or one coherence-after it).
+
+	If W and W' conflict and it is possible to link W to W' by one
+	of the vis sequences listed above, then W' ->co W is not
+	allowed (i.e., if one store is visible to a second then the
+	second must come after the first in the coherence order).
+
+This is the extent to which the LKMM deals with plain accesses.
+Perhaps it could say more (for example, plain accesses might
+contribute to the ppo relation), but at the moment it seems that this
+minimal, conservative approach is good enough.
+
+
 ODDS AND ENDS
 -------------
 
@@ -1943,6 +2481,16 @@ treated as READ_ONCE() and rcu_assign_pointer() is treated as
 smp_store_release() -- which is basically how the Linux kernel treats
 them.
 
+Although we said that plain accesses are not linked by the ppo
+relation, they do contribute to it indirectly.  Namely, when there is
+an address dependency from a marked load R to a plain store W,
+followed by smp_wmb() and then a marked store W', the LKMM creates a
+ppo link from R to W'.  The reasoning behind this is perhaps a little
+shaky, but essentially it says there is no way to generate object code
+for this source code in which W' could execute before R.  Just as with
+pre-bounding by address dependencies, it is possible for the compiler
+to undermine this relation if sufficient care is not taken.
+
 There are a few oddball fences which need special treatment:
 smp_mb__before_atomic(), smp_mb__after_atomic(), and
 smp_mb__after_spinlock().  The LKMM uses fence events with special
diff --git a/tools/memory-model/linux-kernel.cat b/tools/memory-model/linux-kernel.cat
index ea2ff4b94074..2a9b4fe4a84e 100644
--- a/tools/memory-model/linux-kernel.cat
+++ b/tools/memory-model/linux-kernel.cat
@@ -197,7 +197,7 @@ empty (wr-incoh | rw-incoh | ww-incoh) as plain-coherence
 (* Actual races *)
 let ww-nonrace = ww-vis & ((Marked * W) | rw-xbstar) & ((W * Marked) | wr-vis)
 let ww-race = (pre-race & co) \ ww-nonrace
-let wr-race = (pre-race & (co? ; rf)) \ wr-vis
+let wr-race = (pre-race & (co? ; rf)) \ wr-vis \ rw-xbstar^-1
 let rw-race = (pre-race & fr) \ rw-xbstar
 
 flag ~empty (ww-race | wr-race | rw-race) as data-race
diff --git a/tools/objtool/check.c b/tools/objtool/check.c
index 543c068096b1..4768d91c6d68 100644
--- a/tools/objtool/check.c
+++ b/tools/objtool/check.c
@@ -482,6 +482,7 @@ static const char *uaccess_safe_builtin[] = {
 	"ubsan_type_mismatch_common",
 	"__ubsan_handle_type_mismatch",
 	"__ubsan_handle_type_mismatch_v1",
+	"__ubsan_handle_shift_out_of_bounds",
 	/* misc */
 	"csum_partial_copy_generic",
 	"__memcpy_mcsafe",
diff --git a/tools/power/cpupower/ToDo b/tools/power/cpupower/ToDo
index 6e8b89f282e6..b196a139a3e4 100644
--- a/tools/power/cpupower/ToDo
+++ b/tools/power/cpupower/ToDo
@@ -8,3 +8,17 @@ ToDos sorted by priority:
 - Add another c1e debug idle monitor
   -> Is by design racy with BIOS, but could be added
      with a --force option and some "be careful" messages
+- Add cpu_start()/cpu_stop() callbacks for monitor
+  -> This is to move the per_cpu logic from inside the
+     monitor to outside it. This can be given higher
+     priority in fork_it.
+- Fork as many processes as there are CPUs in case the
+  per_cpu_schedule flag is set.
+  -> Bind forked process to each cpu.
+  -> Execute start measures via the forked processes on
+     each cpu.
+  -> Run test executable in a forked process.
+  -> Execute stop measures via the forked processes on
+     each cpu.
+  This would be ideal as it will not introduce noise in the
+  tested executable.
diff --git a/tools/power/cpupower/utils/cpupower-info.c b/tools/power/cpupower/utils/cpupower-info.c
index 4c9d342b70ff..d3755ea70d4d 100644
--- a/tools/power/cpupower/utils/cpupower-info.c
+++ b/tools/power/cpupower/utils/cpupower-info.c
@@ -10,6 +10,7 @@
 #include <errno.h>
 #include <string.h>
 #include <getopt.h>
+#include <sys/utsname.h>
 
 #include "helpers/helpers.h"
 #include "helpers/sysfs.h"
@@ -30,6 +31,7 @@ int cmd_info(int argc, char **argv)
 	extern char *optarg;
 	extern int optind, opterr, optopt;
 	unsigned int cpu;
+	struct utsname uts;
 
 	union {
 		struct {
@@ -39,6 +41,13 @@ int cmd_info(int argc, char **argv)
 	} params = {};
 	int ret = 0;
 
+	ret = uname(&uts);
+	if (!ret && (!strcmp(uts.machine, "ppc64le") ||
+		     !strcmp(uts.machine, "ppc64"))) {
+		fprintf(stderr, _("Subcommand not supported on POWER.\n"));
+		return ret;
+	}
+
 	setlocale(LC_ALL, "");
 	textdomain(PACKAGE);
 
diff --git a/tools/power/cpupower/utils/cpupower-set.c b/tools/power/cpupower/utils/cpupower-set.c
index 3cd95c6cb974..3cca6f715dd9 100644
--- a/tools/power/cpupower/utils/cpupower-set.c
+++ b/tools/power/cpupower/utils/cpupower-set.c
@@ -10,6 +10,7 @@
 #include <errno.h>
 #include <string.h>
 #include <getopt.h>
+#include <sys/utsname.h>
 
 #include "helpers/helpers.h"
 #include "helpers/sysfs.h"
@@ -31,6 +32,7 @@ int cmd_set(int argc, char **argv)
 	extern char *optarg;
 	extern int optind, opterr, optopt;
 	unsigned int cpu;
+	struct utsname uts;
 
 	union {
 		struct {
@@ -41,6 +43,13 @@ int cmd_set(int argc, char **argv)
 	int perf_bias = 0;
 	int ret = 0;
 
+	ret = uname(&uts);
+	if (!ret && (!strcmp(uts.machine, "ppc64le") ||
+		     !strcmp(uts.machine, "ppc64"))) {
+		fprintf(stderr, _("Subcommand not supported on POWER.\n"));
+		return ret;
+	}
+
 	setlocale(LC_ALL, "");
 	textdomain(PACKAGE);
 
diff --git a/tools/power/cpupower/utils/helpers/cpuid.c b/tools/power/cpupower/utils/helpers/cpuid.c
index 5cc39d4e23ed..73bfafc60e9b 100644
--- a/tools/power/cpupower/utils/helpers/cpuid.c
+++ b/tools/power/cpupower/utils/helpers/cpuid.c
@@ -131,6 +131,10 @@ out:
 		if (ext_cpuid_level >= 0x80000007 &&
 		    (cpuid_edx(0x80000007) & (1 << 9)))
 			cpu_info->caps |= CPUPOWER_CAP_AMD_CBP;
+
+		if (ext_cpuid_level >= 0x80000008 &&
+		    cpuid_ebx(0x80000008) & (1 << 4))
+			cpu_info->caps |= CPUPOWER_CAP_AMD_RDPRU;
 	}
 
 	if (cpu_info->vendor == X86_VENDOR_INTEL) {
diff --git a/tools/power/cpupower/utils/helpers/helpers.h b/tools/power/cpupower/utils/helpers/helpers.h
index 357b19bb136e..c258eeccd05f 100644
--- a/tools/power/cpupower/utils/helpers/helpers.h
+++ b/tools/power/cpupower/utils/helpers/helpers.h
@@ -69,6 +69,7 @@ enum cpupower_cpu_vendor {X86_VENDOR_UNKNOWN = 0, X86_VENDOR_INTEL,
 #define CPUPOWER_CAP_HAS_TURBO_RATIO	0x00000010
 #define CPUPOWER_CAP_IS_SNB		0x00000020
 #define CPUPOWER_CAP_INTEL_IDA		0x00000040
+#define CPUPOWER_CAP_AMD_RDPRU		0x00000080
 
 #define CPUPOWER_AMD_CPBDIS		0x02000000
 
diff --git a/tools/power/cpupower/utils/idle_monitor/amd_fam14h_idle.c b/tools/power/cpupower/utils/idle_monitor/amd_fam14h_idle.c
index 3f893b99b337..33dc34db4f3c 100644
--- a/tools/power/cpupower/utils/idle_monitor/amd_fam14h_idle.c
+++ b/tools/power/cpupower/utils/idle_monitor/amd_fam14h_idle.c
@@ -328,7 +328,7 @@ struct cpuidle_monitor amd_fam14h_monitor = {
 	.stop			= amd_fam14h_stop,
 	.do_register		= amd_fam14h_register,
 	.unregister		= amd_fam14h_unregister,
-	.needs_root		= 1,
+	.flags.needs_root	= 1,
 	.overflow_s		= OVERFLOW_MS / 1000,
 };
 #endif /* #if defined(__i386__) || defined(__x86_64__) */
diff --git a/tools/power/cpupower/utils/idle_monitor/cpuidle_sysfs.c b/tools/power/cpupower/utils/idle_monitor/cpuidle_sysfs.c
index f634aeb65c5f..3c4cee160b0e 100644
--- a/tools/power/cpupower/utils/idle_monitor/cpuidle_sysfs.c
+++ b/tools/power/cpupower/utils/idle_monitor/cpuidle_sysfs.c
@@ -207,6 +207,6 @@ struct cpuidle_monitor cpuidle_sysfs_monitor = {
 	.stop			= cpuidle_stop,
 	.do_register		= cpuidle_register,
 	.unregister		= cpuidle_unregister,
-	.needs_root		= 0,
+	.flags.needs_root	= 0,
 	.overflow_s		= UINT_MAX,
 };
diff --git a/tools/power/cpupower/utils/idle_monitor/cpupower-monitor.c b/tools/power/cpupower/utils/idle_monitor/cpupower-monitor.c
index d3c3e6e7aa26..6d44fec55ad5 100644
--- a/tools/power/cpupower/utils/idle_monitor/cpupower-monitor.c
+++ b/tools/power/cpupower/utils/idle_monitor/cpupower-monitor.c
@@ -408,7 +408,7 @@ int cmd_monitor(int argc, char **argv)
 		dprint("Try to register: %s\n", all_monitors[num]->name);
 		test_mon = all_monitors[num]->do_register();
 		if (test_mon) {
-			if (test_mon->needs_root && !run_as_root) {
+			if (test_mon->flags.needs_root && !run_as_root) {
 				fprintf(stderr, _("Available monitor %s needs "
 					  "root access\n"), test_mon->name);
 				continue;
diff --git a/tools/power/cpupower/utils/idle_monitor/cpupower-monitor.h b/tools/power/cpupower/utils/idle_monitor/cpupower-monitor.h
index a2d901d3bfaf..5b5eb1da0cce 100644
--- a/tools/power/cpupower/utils/idle_monitor/cpupower-monitor.h
+++ b/tools/power/cpupower/utils/idle_monitor/cpupower-monitor.h
@@ -60,7 +60,10 @@ struct cpuidle_monitor {
 	struct cpuidle_monitor* (*do_register) (void);
 	void (*unregister)(void);
 	unsigned int overflow_s;
-	int needs_root;
+	struct {
+		unsigned int needs_root:1;
+		unsigned int per_cpu_schedule:1;
+	} flags;
 };
 
 extern long long timespec_diff_us(struct timespec start, struct timespec end);
diff --git a/tools/power/cpupower/utils/idle_monitor/hsw_ext_idle.c b/tools/power/cpupower/utils/idle_monitor/hsw_ext_idle.c
index 7c7451d3f494..97ad3233a521 100644
--- a/tools/power/cpupower/utils/idle_monitor/hsw_ext_idle.c
+++ b/tools/power/cpupower/utils/idle_monitor/hsw_ext_idle.c
@@ -39,7 +39,6 @@ static cstate_t hsw_ext_cstates[HSW_EXT_CSTATE_COUNT] = {
 	{
 		.name			= "PC9",
 		.desc			= N_("Processor Package C9"),
-		.desc			= N_("Processor Package C2"),
 		.id			= PC9,
 		.range			= RANGE_PACKAGE,
 		.get_count_percent	= hsw_ext_get_count_percent,
@@ -188,7 +187,7 @@ struct cpuidle_monitor intel_hsw_ext_monitor = {
 	.stop			= hsw_ext_stop,
 	.do_register		= hsw_ext_register,
 	.unregister		= hsw_ext_unregister,
-	.needs_root		= 1,
+	.flags.needs_root	= 1,
 	.overflow_s		= 922000000 /* 922337203 seconds TSC overflow
 					       at 20GHz */
 };
diff --git a/tools/power/cpupower/utils/idle_monitor/mperf_monitor.c b/tools/power/cpupower/utils/idle_monitor/mperf_monitor.c
index 44806a6dae11..e7d48cb563c0 100644
--- a/tools/power/cpupower/utils/idle_monitor/mperf_monitor.c
+++ b/tools/power/cpupower/utils/idle_monitor/mperf_monitor.c
@@ -19,6 +19,10 @@
 #define MSR_APERF	0xE8
 #define MSR_MPERF	0xE7
 
+#define RDPRU ".byte 0x0f, 0x01, 0xfd"
+#define RDPRU_ECX_MPERF	0
+#define RDPRU_ECX_APERF	1
+
 #define MSR_TSC	0x10
 
 #define MSR_AMD_HWCR 0xc0010015
@@ -86,15 +90,51 @@ static int mperf_get_tsc(unsigned long long *tsc)
 	return ret;
 }
 
+static int get_aperf_mperf(int cpu, unsigned long long *aval,
+				    unsigned long long *mval)
+{
+	unsigned long low_a, high_a;
+	unsigned long low_m, high_m;
+	int ret;
+
+	/*
+	 * Running on the cpu from which we read the registers will
+	 * prevent APERF/MPERF from going out of sync because of IPI
+	 * latency introduced by read_msr()s.
+	 */
+	if (mperf_monitor.flags.per_cpu_schedule) {
+		if (bind_cpu(cpu))
+			return 1;
+	}
+
+	if (cpupower_cpu_info.caps & CPUPOWER_CAP_AMD_RDPRU) {
+		asm volatile(RDPRU
+			     : "=a" (low_a), "=d" (high_a)
+			     : "c" (RDPRU_ECX_APERF));
+		asm volatile(RDPRU
+			     : "=a" (low_m), "=d" (high_m)
+			     : "c" (RDPRU_ECX_MPERF));
+
+		*aval = ((low_a) | (high_a) << 32);
+		*mval = ((low_m) | (high_m) << 32);
+
+		return 0;
+	}
+
+	ret  = read_msr(cpu, MSR_APERF, aval);
+	ret |= read_msr(cpu, MSR_MPERF, mval);
+
+	return ret;
+}
+
 static int mperf_init_stats(unsigned int cpu)
 {
-	unsigned long long val;
+	unsigned long long aval, mval;
 	int ret;
 
-	ret = read_msr(cpu, MSR_APERF, &val);
-	aperf_previous_count[cpu] = val;
-	ret |= read_msr(cpu, MSR_MPERF, &val);
-	mperf_previous_count[cpu] = val;
+	ret = get_aperf_mperf(cpu, &aval, &mval);
+	aperf_previous_count[cpu] = aval;
+	mperf_previous_count[cpu] = mval;
 	is_valid[cpu] = !ret;
 
 	return 0;
@@ -102,13 +142,12 @@ static int mperf_init_stats(unsigned int cpu)
 
 static int mperf_measure_stats(unsigned int cpu)
 {
-	unsigned long long val;
+	unsigned long long aval, mval;
 	int ret;
 
-	ret = read_msr(cpu, MSR_APERF, &val);
-	aperf_current_count[cpu] = val;
-	ret |= read_msr(cpu, MSR_MPERF, &val);
-	mperf_current_count[cpu] = val;
+	ret = get_aperf_mperf(cpu, &aval, &mval);
+	aperf_current_count[cpu] = aval;
+	mperf_current_count[cpu] = mval;
 	is_valid[cpu] = !ret;
 
 	return 0;
@@ -305,6 +344,9 @@ struct cpuidle_monitor *mperf_register(void)
 	if (init_maxfreq_mode())
 		return NULL;
 
+	if (cpupower_cpu_info.vendor == X86_VENDOR_AMD)
+		mperf_monitor.flags.per_cpu_schedule = 1;
+
 	/* Free this at program termination */
 	is_valid = calloc(cpu_count, sizeof(int));
 	mperf_previous_count = calloc(cpu_count, sizeof(unsigned long long));
@@ -333,7 +375,7 @@ struct cpuidle_monitor mperf_monitor = {
 	.stop			= mperf_stop,
 	.do_register		= mperf_register,
 	.unregister		= mperf_unregister,
-	.needs_root		= 1,
+	.flags.needs_root	= 1,
 	.overflow_s		= 922000000 /* 922337203 seconds TSC overflow
 					       at 20GHz */
 };
diff --git a/tools/power/cpupower/utils/idle_monitor/nhm_idle.c b/tools/power/cpupower/utils/idle_monitor/nhm_idle.c
index be7256696a37..114271165182 100644
--- a/tools/power/cpupower/utils/idle_monitor/nhm_idle.c
+++ b/tools/power/cpupower/utils/idle_monitor/nhm_idle.c
@@ -208,7 +208,7 @@ struct cpuidle_monitor intel_nhm_monitor = {
 	.stop			= nhm_stop,
 	.do_register		= intel_nhm_register,
 	.unregister		= intel_nhm_unregister,
-	.needs_root		= 1,
+	.flags.needs_root	= 1,
 	.overflow_s		= 922000000 /* 922337203 seconds TSC overflow
 					       at 20GHz */
 };
diff --git a/tools/power/cpupower/utils/idle_monitor/snb_idle.c b/tools/power/cpupower/utils/idle_monitor/snb_idle.c
index 968333571cad..df8b223cc096 100644
--- a/tools/power/cpupower/utils/idle_monitor/snb_idle.c
+++ b/tools/power/cpupower/utils/idle_monitor/snb_idle.c
@@ -192,7 +192,7 @@ struct cpuidle_monitor intel_snb_monitor = {
 	.stop			= snb_stop,
 	.do_register		= snb_register,
 	.unregister		= snb_unregister,
-	.needs_root		= 1,
+	.flags.needs_root	= 1,
 	.overflow_s		= 922000000 /* 922337203 seconds TSC overflow
 					       at 20GHz */
 };
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TASKS03 b/tools/testing/selftests/rcutorture/configs/rcu/TASKS03
index 28568b72a31b..ea4399020c6c 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/TASKS03
+++ b/tools/testing/selftests/rcutorture/configs/rcu/TASKS03
@@ -1,8 +1,5 @@
 CONFIG_SMP=y
 CONFIG_NR_CPUS=2
-CONFIG_HOTPLUG_CPU=n
-CONFIG_SUSPEND=n
-CONFIG_HIBERNATION=n
 CONFIG_PREEMPT_NONE=n
 CONFIG_PREEMPT_VOLUNTARY=n
 CONFIG_PREEMPT=y
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE02 b/tools/testing/selftests/rcutorture/configs/rcu/TREE02
index 35e639e39366..65daee4fbf5a 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/TREE02
+++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE02
@@ -9,9 +9,6 @@ CONFIG_NO_HZ_IDLE=y
 CONFIG_NO_HZ_FULL=n
 CONFIG_RCU_FAST_NO_HZ=n
 CONFIG_RCU_TRACE=n
-CONFIG_HOTPLUG_CPU=n
-CONFIG_SUSPEND=n
-CONFIG_HIBERNATION=n
 CONFIG_RCU_FANOUT=3
 CONFIG_RCU_FANOUT_LEAF=3
 CONFIG_RCU_NOCB_CPU=n
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE04 b/tools/testing/selftests/rcutorture/configs/rcu/TREE04
index 24c9f6012e35..f6d6a40c0576 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/TREE04
+++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE04
@@ -9,9 +9,6 @@ CONFIG_NO_HZ_IDLE=n
 CONFIG_NO_HZ_FULL=y
 CONFIG_RCU_FAST_NO_HZ=y
 CONFIG_RCU_TRACE=y
-CONFIG_HOTPLUG_CPU=n
-CONFIG_SUSPEND=n
-CONFIG_HIBERNATION=n
 CONFIG_RCU_FANOUT=4
 CONFIG_RCU_FANOUT_LEAF=3
 CONFIG_DEBUG_LOCK_ALLOC=n
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE06 b/tools/testing/selftests/rcutorture/configs/rcu/TREE06
index 05a4eec3f27b..bf4980d606b5 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/TREE06
+++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE06
@@ -9,9 +9,6 @@ CONFIG_NO_HZ_IDLE=y
 CONFIG_NO_HZ_FULL=n
 CONFIG_RCU_FAST_NO_HZ=n
 CONFIG_RCU_TRACE=n
-CONFIG_HOTPLUG_CPU=n
-CONFIG_SUSPEND=n
-CONFIG_HIBERNATION=n
 CONFIG_RCU_FANOUT=6
 CONFIG_RCU_FANOUT_LEAF=6
 CONFIG_RCU_NOCB_CPU=n
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE08 b/tools/testing/selftests/rcutorture/configs/rcu/TREE08
index fb1c763c10c5..c810c5276a89 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/TREE08
+++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE08
@@ -9,9 +9,6 @@ CONFIG_NO_HZ_IDLE=y
 CONFIG_NO_HZ_FULL=n
 CONFIG_RCU_FAST_NO_HZ=n
 CONFIG_RCU_TRACE=n
-CONFIG_HOTPLUG_CPU=n
-CONFIG_SUSPEND=n
-CONFIG_HIBERNATION=n
 CONFIG_RCU_FANOUT=3
 CONFIG_RCU_FANOUT_LEAF=2
 CONFIG_RCU_NOCB_CPU=y
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE09 b/tools/testing/selftests/rcutorture/configs/rcu/TREE09
index 6710e749d9de..8523a7515cbf 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/TREE09
+++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE09
@@ -8,9 +8,6 @@ CONFIG_HZ_PERIODIC=n
 CONFIG_NO_HZ_IDLE=y
 CONFIG_NO_HZ_FULL=n
 CONFIG_RCU_TRACE=n
-CONFIG_HOTPLUG_CPU=n
-CONFIG_SUSPEND=n
-CONFIG_HIBERNATION=n
 CONFIG_RCU_NOCB_CPU=n
 CONFIG_DEBUG_LOCK_ALLOC=n
 CONFIG_RCU_BOOST=n
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TRIVIAL b/tools/testing/selftests/rcutorture/configs/rcu/TRIVIAL
index 4d8eb5bfb6f6..5d546efa68e8 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/TRIVIAL
+++ b/tools/testing/selftests/rcutorture/configs/rcu/TRIVIAL
@@ -6,9 +6,6 @@ CONFIG_PREEMPT=n
 CONFIG_HZ_PERIODIC=n
 CONFIG_NO_HZ_IDLE=y
 CONFIG_NO_HZ_FULL=n
-CONFIG_HOTPLUG_CPU=n
-CONFIG_SUSPEND=n
-CONFIG_HIBERNATION=n
 CONFIG_DEBUG_LOCK_ALLOC=n
 CONFIG_DEBUG_OBJECTS_RCU_HEAD=n
 CONFIG_RCU_EXPERT=y
diff --git a/tools/testing/selftests/rcutorture/doc/TREE_RCU-kconfig.txt b/tools/testing/selftests/rcutorture/doc/TREE_RCU-kconfig.txt
index af6fca03602f..1b96d68473b8 100644
--- a/tools/testing/selftests/rcutorture/doc/TREE_RCU-kconfig.txt
+++ b/tools/testing/selftests/rcutorture/doc/TREE_RCU-kconfig.txt
@@ -6,7 +6,6 @@ Kconfig Parameters:
 
 CONFIG_DEBUG_LOCK_ALLOC -- Do three, covering CONFIG_PROVE_LOCKING & not.
 CONFIG_DEBUG_OBJECTS_RCU_HEAD -- Do one.
-CONFIG_HOTPLUG_CPU -- Do half.  (Every second.)
 CONFIG_HZ_PERIODIC -- Do one.
 CONFIG_NO_HZ_IDLE -- Do those not otherwise specified. (Groups of two.)
 CONFIG_NO_HZ_FULL -- Do two, one with partial CPU enablement.
diff --git a/tools/testing/selftests/x86/ioperm.c b/tools/testing/selftests/x86/ioperm.c
index 01de41c1b725..57ec5e99edb9 100644
--- a/tools/testing/selftests/x86/ioperm.c
+++ b/tools/testing/selftests/x86/ioperm.c
@@ -131,6 +131,17 @@ int main(void)
 		printf("[RUN]\tchild: check that we inherited permissions\n");
 		expect_ok(0x80);
 		expect_gp(0xed);
+		printf("[RUN]\tchild: Extend permissions to 0x81\n");
+		if (ioperm(0x81, 1, 1) != 0) {
+			printf("[FAIL]\tioperm(0x81, 1, 1) failed (%d)", errno);
+			return 1;
+		}
+		printf("[RUN]\tchild: Drop permissions to 0x80\n");
+		if (ioperm(0x80, 1, 0) != 0) {
+			printf("[FAIL]\tioperm(0x80, 1, 0) failed (%d)", errno);
+			return 1;
+		}
+		expect_gp(0x80);
 		return 0;
 	} else {
 		int status;
@@ -146,8 +157,11 @@ int main(void)
 		}
 	}
 
-	/* Test the capability checks. */
+	/* Verify that the child dropping 0x80 did not affect the parent */
+	printf("\tVerify that unsharing the bitmap worked\n");
+	expect_ok(0x80);
 
+	/* Test the capability checks. */
 	printf("\tDrop privileges\n");
 	if (setresuid(1, 1, 1) != 0) {
 		printf("[WARN]\tDropping privileges failed\n");
diff --git a/tools/testing/selftests/x86/iopl.c b/tools/testing/selftests/x86/iopl.c
index 6aa27f34644c..bab2f6e06b63 100644
--- a/tools/testing/selftests/x86/iopl.c
+++ b/tools/testing/selftests/x86/iopl.c
@@ -35,6 +35,16 @@ static void sethandler(int sig, void (*handler)(int, siginfo_t *, void *),
 
 }
 
+static void clearhandler(int sig)
+{
+	struct sigaction sa;
+	memset(&sa, 0, sizeof(sa));
+	sa.sa_handler = SIG_DFL;
+	sigemptyset(&sa.sa_mask);
+	if (sigaction(sig, &sa, 0))
+		err(1, "sigaction");
+}
+
 static jmp_buf jmpbuf;
 
 static void sigsegv(int sig, siginfo_t *si, void *ctx_void)
@@ -42,25 +52,128 @@ static void sigsegv(int sig, siginfo_t *si, void *ctx_void)
 	siglongjmp(jmpbuf, 1);
 }
 
+static bool try_outb(unsigned short port)
+{
+	sethandler(SIGSEGV, sigsegv, SA_RESETHAND);
+	if (sigsetjmp(jmpbuf, 1) != 0) {
+		return false;
+	} else {
+		asm volatile ("outb %%al, %w[port]"
+			      : : [port] "Nd" (port), "a" (0));
+		return true;
+	}
+	clearhandler(SIGSEGV);
+}
+
+static void expect_ok_outb(unsigned short port)
+{
+	if (!try_outb(port)) {
+		printf("[FAIL]\toutb to 0x%02hx failed\n", port);
+		exit(1);
+	}
+
+	printf("[OK]\toutb to 0x%02hx worked\n", port);
+}
+
+static void expect_gp_outb(unsigned short port)
+{
+	if (try_outb(port)) {
+		printf("[FAIL]\toutb to 0x%02hx worked\n", port);
+		nerrs++;
+	}
+
+	printf("[OK]\toutb to 0x%02hx failed\n", port);
+}
+
+static bool try_cli(void)
+{
+	sethandler(SIGSEGV, sigsegv, SA_RESETHAND);
+	if (sigsetjmp(jmpbuf, 1) != 0) {
+		return false;
+	} else {
+		asm volatile ("cli");
+		return true;
+	}
+	clearhandler(SIGSEGV);
+}
+
+static bool try_sti(void)
+{
+	sethandler(SIGSEGV, sigsegv, SA_RESETHAND);
+	if (sigsetjmp(jmpbuf, 1) != 0) {
+		return false;
+	} else {
+		asm volatile ("sti");
+		return true;
+	}
+	clearhandler(SIGSEGV);
+}
+
+static void expect_gp_sti(void)
+{
+	if (try_sti()) {
+		printf("[FAIL]\tSTI worked\n");
+		nerrs++;
+	} else {
+		printf("[OK]\tSTI faulted\n");
+	}
+}
+
+static void expect_gp_cli(void)
+{
+	if (try_cli()) {
+		printf("[FAIL]\tCLI worked\n");
+		nerrs++;
+	} else {
+		printf("[OK]\tCLI faulted\n");
+	}
+}
+
 int main(void)
 {
 	cpu_set_t cpuset;
+
 	CPU_ZERO(&cpuset);
 	CPU_SET(0, &cpuset);
 	if (sched_setaffinity(0, sizeof(cpuset), &cpuset) != 0)
 		err(1, "sched_setaffinity to CPU 0");
 
 	/* Probe for iopl support.  Note that iopl(0) works even as nonroot. */
-	if (iopl(3) != 0) {
+	switch(iopl(3)) {
+	case 0:
+		break;
+	case -ENOSYS:
+		printf("[OK]\tiopl() nor supported\n");
+		return 0;
+	default:
 		printf("[OK]\tiopl(3) failed (%d) -- try running as root\n",
 		       errno);
 		return 0;
 	}
 
-	/* Restore our original state prior to starting the test. */
+	/* Make sure that CLI/STI are blocked even with IOPL level 3 */
+	expect_gp_cli();
+	expect_gp_sti();
+	expect_ok_outb(0x80);
+
+	/* Establish an I/O bitmap to test the restore */
+	if (ioperm(0x80, 1, 1) != 0)
+		err(1, "ioperm(0x80, 1, 1) failed\n");
+
+	/* Restore our original state prior to starting the fork test. */
 	if (iopl(0) != 0)
 		err(1, "iopl(0)");
 
+	/*
+	 * Verify that IOPL emulation is disabled and the I/O bitmap still
+	 * works.
+	 */
+	expect_ok_outb(0x80);
+	expect_gp_outb(0xed);
+	/* Drop the I/O bitmap */
+	if (ioperm(0x80, 1, 0) != 0)
+		err(1, "ioperm(0x80, 1, 0) failed\n");
+
 	pid_t child = fork();
 	if (child == -1)
 		err(1, "fork");
@@ -90,14 +203,9 @@ int main(void)
 
 	printf("[RUN]\tparent: write to 0x80 (should fail)\n");
 
-	sethandler(SIGSEGV, sigsegv, 0);
-	if (sigsetjmp(jmpbuf, 1) != 0) {
-		printf("[OK]\twrite was denied\n");
-	} else {
-		asm volatile ("outb %%al, $0x80" : : "a" (0));
-		printf("[FAIL]\twrite was allowed\n");
-		nerrs++;
-	}
+	expect_gp_outb(0x80);
+	expect_gp_cli();
+	expect_gp_sti();
 
 	/* Test the capability checks. */
 	printf("\tiopl(3)\n");
@@ -133,4 +241,3 @@ int main(void)
 done:
 	return nerrs ? 1 : 0;
 }
-
diff --git a/tools/testing/selftests/x86/mov_ss_trap.c b/tools/testing/selftests/x86/mov_ss_trap.c
index 3c3a022654f3..6da0ac3f0135 100644
--- a/tools/testing/selftests/x86/mov_ss_trap.c
+++ b/tools/testing/selftests/x86/mov_ss_trap.c
@@ -257,7 +257,8 @@ int main()
 			err(1, "sigaltstack");
 		sethandler(SIGSEGV, handle_and_longjmp, SA_RESETHAND | SA_ONSTACK);
 		nr = SYS_getpid;
-		asm volatile ("mov %[ss], %%ss; SYSENTER" : "+a" (nr)
+		/* Clear EBP first to make sure we segfault cleanly. */
+		asm volatile ("xorl %%ebp, %%ebp; mov %[ss], %%ss; SYSENTER" : "+a" (nr)
 			      : [ss] "m" (ss) : "flags", "rcx"
 #ifdef __x86_64__
 				, "r11"
diff --git a/tools/testing/selftests/x86/sigreturn.c b/tools/testing/selftests/x86/sigreturn.c
index 3e49a7873f3e..57c4f67f16ef 100644
--- a/tools/testing/selftests/x86/sigreturn.c
+++ b/tools/testing/selftests/x86/sigreturn.c
@@ -451,6 +451,19 @@ static void sigusr1(int sig, siginfo_t *info, void *ctx_void)
 	ctx->uc_mcontext.gregs[REG_SP] = (unsigned long)0x8badf00d5aadc0deULL;
 	ctx->uc_mcontext.gregs[REG_CX] = 0;
 
+#ifdef __i386__
+	/*
+	 * Make sure the kernel doesn't inadvertently use DS or ES-relative
+	 * accesses in a region where user DS or ES is loaded.
+	 *
+	 * Skip this for 64-bit builds because long mode doesn't care about
+	 * DS and ES and skipping it increases test coverage a little bit,
+	 * since 64-bit kernels can still run the 32-bit build.
+	 */
+	ctx->uc_mcontext.gregs[REG_DS] = 0;
+	ctx->uc_mcontext.gregs[REG_ES] = 0;
+#endif
+
 	memcpy(&requested_regs, &ctx->uc_mcontext.gregs, sizeof(gregset_t));
 	requested_regs[REG_CX] = *ssptr(ctx);	/* The asm code does this. */