diff options
877 files changed, 24107 insertions, 11248 deletions
@@ -205,6 +205,7 @@ Juha Yrjola <at solidboot.com> Juha Yrjola <juha.yrjola@nokia.com> Juha Yrjola <juha.yrjola@solidboot.com> Julien Thierry <julien.thierry.kdev@gmail.com> <julien.thierry@arm.com> +Kalle Valo <kvalo@kernel.org> <kvalo@codeaurora.org> Kalyan Thota <quic_kalyant@quicinc.com> <kalyan_t@codeaurora.org> Kay Sievers <kay.sievers@vrfy.org> Kees Cook <keescook@chromium.org> <kees.cook@canonical.com> @@ -250,6 +251,7 @@ Mark Yao <markyao0591@gmail.com> <mark.yao@rock-chips.com> Martin Kepplinger <martink@posteo.de> <martin.kepplinger@ginzinger.com> Martin Kepplinger <martink@posteo.de> <martin.kepplinger@puri.sm> Martin Kepplinger <martink@posteo.de> <martin.kepplinger@theobroma-systems.com> +Martyna Szapar-Mudlaw <martyna.szapar-mudlaw@linux.intel.com> <martyna.szapar-mudlaw@intel.com> Mathieu Othacehe <m.othacehe@gmail.com> Matthew Wilcox <willy@infradead.org> <matthew.r.wilcox@intel.com> Matthew Wilcox <willy@infradead.org> <matthew@wil.cx> diff --git a/Documentation/ABI/testing/securityfs-secrets-coco b/Documentation/ABI/testing/securityfs-secrets-coco new file mode 100644 index 000000000000..f2b6909155f9 --- /dev/null +++ b/Documentation/ABI/testing/securityfs-secrets-coco @@ -0,0 +1,51 @@ +What: security/secrets/coco +Date: February 2022 +Contact: Dov Murik <dovmurik@linux.ibm.com> +Description: + Exposes confidential computing (coco) EFI secrets to + userspace via securityfs. + + EFI can declare memory area used by confidential computing + platforms (such as AMD SEV and SEV-ES) for secret injection by + the Guest Owner during VM's launch. The secrets are encrypted + by the Guest Owner and decrypted inside the trusted enclave, + and therefore are not readable by the untrusted host. + + The efi_secret module exposes the secrets to userspace. Each + secret appears as a file under <securityfs>/secrets/coco, + where the filename is the GUID of the entry in the secrets + table. This module is loaded automatically by the EFI driver + if the EFI secret area is populated. + + Two operations are supported for the files: read and unlink. + Reading the file returns the content of secret entry. + Unlinking the file overwrites the secret data with zeroes and + removes the entry from the filesystem. A secret cannot be read + after it has been unlinked. + + For example, listing the available secrets:: + + # modprobe efi_secret + # ls -l /sys/kernel/security/secrets/coco + -r--r----- 1 root root 0 Jun 28 11:54 736870e5-84f0-4973-92ec-06879ce3da0b + -r--r----- 1 root root 0 Jun 28 11:54 83c83f7f-1356-4975-8b7e-d3a0b54312c6 + -r--r----- 1 root root 0 Jun 28 11:54 9553f55d-3da2-43ee-ab5d-ff17f78864d2 + -r--r----- 1 root root 0 Jun 28 11:54 e6f5a162-d67f-4750-a67c-5d065f2a9910 + + Reading the secret data by reading a file:: + + # cat /sys/kernel/security/secrets/coco/e6f5a162-d67f-4750-a67c-5d065f2a9910 + the-content-of-the-secret-data + + Wiping a secret by unlinking a file:: + + # rm /sys/kernel/security/secrets/coco/e6f5a162-d67f-4750-a67c-5d065f2a9910 + # ls -l /sys/kernel/security/secrets/coco + -r--r----- 1 root root 0 Jun 28 11:54 736870e5-84f0-4973-92ec-06879ce3da0b + -r--r----- 1 root root 0 Jun 28 11:54 83c83f7f-1356-4975-8b7e-d3a0b54312c6 + -r--r----- 1 root root 0 Jun 28 11:54 9553f55d-3da2-43ee-ab5d-ff17f78864d2 + + Note: The binary format of the secrets table injected by the + Guest Owner is described in + drivers/virt/coco/efi_secret/efi_secret.c under "Structure of + the EFI secret area". diff --git a/Documentation/RCU/Design/Data-Structures/Data-Structures.rst b/Documentation/RCU/Design/Data-Structures/Data-Structures.rst index f4efd6897b09..b34990c7c377 100644 --- a/Documentation/RCU/Design/Data-Structures/Data-Structures.rst +++ b/Documentation/RCU/Design/Data-Structures/Data-Structures.rst @@ -973,7 +973,7 @@ 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). +for user mode adaptive-ticks support (see Documentation/timers/no_hz.rst). 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 diff --git a/Documentation/RCU/Design/Expedited-Grace-Periods/Expedited-Grace-Periods.rst b/Documentation/RCU/Design/Expedited-Grace-Periods/Expedited-Grace-Periods.rst index 6f89cf1e567d..c9c957c85bac 100644 --- a/Documentation/RCU/Design/Expedited-Grace-Periods/Expedited-Grace-Periods.rst +++ b/Documentation/RCU/Design/Expedited-Grace-Periods/Expedited-Grace-Periods.rst @@ -406,7 +406,7 @@ 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>`__. +workqueues (see 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 diff --git a/Documentation/RCU/Design/Requirements/Requirements.rst b/Documentation/RCU/Design/Requirements/Requirements.rst index 45278e2974c0..04ed8bf27a0e 100644 --- a/Documentation/RCU/Design/Requirements/Requirements.rst +++ b/Documentation/RCU/Design/Requirements/Requirements.rst @@ -370,8 +370,8 @@ 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>`__. +mechanism, most commonly locking or reference counting +(see ../../rcuref.rst). .. |high-quality implementation of C11 memory_order_consume [PDF]| replace:: high-quality implementation of C11 ``memory_order_consume`` [PDF] .. _high-quality implementation of C11 memory_order_consume [PDF]: http://www.rdrop.com/users/paulmck/RCU/consume.2015.07.13a.pdf @@ -2654,6 +2654,38 @@ synchronize_rcu(), and rcu_barrier(), respectively. In three APIs are therefore implemented by separate functions that check for voluntary context switches. +Tasks Rude RCU +~~~~~~~~~~~~~~ + +Some forms of tracing need to wait for all preemption-disabled regions +of code running on any online CPU, including those executed when RCU is +not watching. This means that synchronize_rcu() is insufficient, and +Tasks Rude RCU must be used instead. This flavor of RCU does its work by +forcing a workqueue to be scheduled on each online CPU, hence the "Rude" +moniker. And this operation is considered to be quite rude by real-time +workloads that don't want their ``nohz_full`` CPUs receiving IPIs and +by battery-powered systems that don't want their idle CPUs to be awakened. + +The tasks-rude-RCU API is also reader-marking-free and thus quite compact, +consisting of call_rcu_tasks_rude(), synchronize_rcu_tasks_rude(), +and rcu_barrier_tasks_rude(). + +Tasks Trace RCU +~~~~~~~~~~~~~~~ + +Some forms of tracing need to sleep in readers, but cannot tolerate +SRCU's read-side overhead, which includes a full memory barrier in both +srcu_read_lock() and srcu_read_unlock(). This need is handled by a +Tasks Trace RCU that uses scheduler locking and IPIs to synchronize with +readers. Real-time systems that cannot tolerate IPIs may build their +kernels with ``CONFIG_TASKS_TRACE_RCU_READ_MB=y``, which avoids the IPIs at +the expense of adding full memory barriers to the read-side primitives. + +The tasks-trace-RCU API is also reasonably compact, +consisting of rcu_read_lock_trace(), rcu_read_unlock_trace(), +rcu_read_lock_trace_held(), call_rcu_tasks_trace(), +synchronize_rcu_tasks_trace(), and rcu_barrier_tasks_trace(). + Possible Future Changes ----------------------- diff --git a/Documentation/RCU/arrayRCU.rst b/Documentation/RCU/arrayRCU.rst index 4051ea3871ef..a5f2ff8fc54c 100644 --- a/Documentation/RCU/arrayRCU.rst +++ b/Documentation/RCU/arrayRCU.rst @@ -33,8 +33,8 @@ Situation 1: Hash Tables Hash tables are often implemented as an array, where each array entry has a linked-list hash chain. Each hash chain can be protected by RCU -as described in the listRCU.txt document. This approach also applies -to other array-of-list situations, such as radix trees. +as described in listRCU.rst. This approach also applies to other +array-of-list situations, such as radix trees. .. _static_arrays: diff --git a/Documentation/RCU/checklist.rst b/Documentation/RCU/checklist.rst index f4545b7c9a63..42cc5d891bd2 100644 --- a/Documentation/RCU/checklist.rst +++ b/Documentation/RCU/checklist.rst @@ -140,8 +140,7 @@ over a rather long period of time, but improvements are always welcome! prevents destructive compiler optimizations. However, with a bit of devious creativity, it is possible to mishandle the return value from rcu_dereference(). - Please see rcu_dereference.txt in this directory for - more information. + Please see rcu_dereference.rst for more information. The rcu_dereference() primitive is used by the various "_rcu()" list-traversal primitives, such @@ -151,7 +150,7 @@ over a rather long period of time, but improvements are always welcome! primitives. This is particularly useful in code that is common to readers and updaters. However, lockdep will complain if you access rcu_dereference() outside - of an RCU read-side critical section. See lockdep.txt + of an RCU read-side critical section. See lockdep.rst to learn what to do about this. Of course, neither rcu_dereference() nor the "_rcu()" @@ -323,7 +322,7 @@ over a rather long period of time, but improvements are always welcome! primitives when the update-side lock is held is that doing so can be quite helpful in reducing code bloat when common code is shared between readers and updaters. Additional primitives - are provided for this case, as discussed in lockdep.txt. + are provided for this case, as discussed in lockdep.rst. One exception to this rule is when data is only ever added to the linked data structure, and is never removed during any @@ -480,4 +479,4 @@ over a rather long period of time, but improvements are always welcome! both rcu_barrier() and synchronize_rcu(), if necessary, using something like workqueues to to execute them concurrently. - See rcubarrier.txt for more information. + See rcubarrier.rst for more information. diff --git a/Documentation/RCU/rcu.rst b/Documentation/RCU/rcu.rst index 0e03c6ef3147..3cfe01ba9a49 100644 --- a/Documentation/RCU/rcu.rst +++ b/Documentation/RCU/rcu.rst @@ -10,9 +10,8 @@ A "grace period" must elapse between the two parts, and this grace period must be long enough that any readers accessing the item being deleted have since dropped their references. For example, an RCU-protected deletion from a linked list would first remove the item from the list, wait for -a grace period to elapse, then free the element. See the -:ref:`Documentation/RCU/listRCU.rst <list_rcu_doc>` for more information on -using RCU with linked lists. +a grace period to elapse, then free the element. See listRCU.rst for more +information on using RCU with linked lists. Frequently Asked Questions -------------------------- @@ -50,7 +49,7 @@ Frequently Asked Questions - If I am running on a uniprocessor kernel, which can only do one thing at a time, why should I wait for a grace period? - See :ref:`Documentation/RCU/UP.rst <up_doc>` for more information. + See UP.rst for more information. - How can I see where RCU is currently used in the Linux kernel? @@ -64,13 +63,13 @@ Frequently Asked Questions - What guidelines should I follow when writing code that uses RCU? - See the checklist.txt file in this directory. + See checklist.rst. - Why the name "RCU"? "RCU" stands for "read-copy update". - :ref:`Documentation/RCU/listRCU.rst <list_rcu_doc>` has more information on where - this name came from, search for "read-copy update" to find it. + listRCU.rst has more information on where this name came from, search + for "read-copy update" to find it. - I hear that RCU is patented? What is with that? diff --git a/Documentation/RCU/rculist_nulls.rst b/Documentation/RCU/rculist_nulls.rst index a9fc774bc400..ca4692775ad4 100644 --- a/Documentation/RCU/rculist_nulls.rst +++ b/Documentation/RCU/rculist_nulls.rst @@ -8,7 +8,7 @@ This section describes how to use hlist_nulls to protect read-mostly linked lists and objects using SLAB_TYPESAFE_BY_RCU allocations. -Please read the basics in Documentation/RCU/listRCU.rst +Please read the basics in listRCU.rst. Using 'nulls' ============= diff --git a/Documentation/RCU/stallwarn.rst b/Documentation/RCU/stallwarn.rst index 78404625bad2..794837eb519b 100644 --- a/Documentation/RCU/stallwarn.rst +++ b/Documentation/RCU/stallwarn.rst @@ -162,6 +162,26 @@ CONFIG_RCU_CPU_STALL_TIMEOUT Stall-warning messages may be enabled and disabled completely via /sys/module/rcupdate/parameters/rcu_cpu_stall_suppress. +CONFIG_RCU_EXP_CPU_STALL_TIMEOUT +-------------------------------- + + Same as the CONFIG_RCU_CPU_STALL_TIMEOUT parameter but only for + the expedited grace period. This parameter defines the period + of time that RCU will wait from the beginning of an expedited + grace period until it issues an RCU CPU stall warning. This time + period is normally 20 milliseconds on Android devices. A zero + value causes the CONFIG_RCU_CPU_STALL_TIMEOUT value to be used, + after conversion to milliseconds. + + This configuration parameter may be changed at runtime via the + /sys/module/rcupdate/parameters/rcu_exp_cpu_stall_timeout, however + this parameter is checked only at the beginning of a cycle. If you + are in a current stall cycle, setting it to a new value will change + the timeout for the -next- stall. + + Stall-warning messages may be enabled and disabled completely via + /sys/module/rcupdate/parameters/rcu_cpu_stall_suppress. + RCU_STALL_DELAY_DELTA --------------------- diff --git a/Documentation/RCU/whatisRCU.rst b/Documentation/RCU/whatisRCU.rst index c34d2212eaca..77ea260efd12 100644 --- a/Documentation/RCU/whatisRCU.rst +++ b/Documentation/RCU/whatisRCU.rst @@ -224,7 +224,7 @@ synchronize_rcu() be delayed. This property results in system resilience in face of denial-of-service attacks. Code using call_rcu() should limit update rate in order to gain this same sort of resilience. See - checklist.txt for some approaches to limiting the update rate. + checklist.rst for some approaches to limiting the update rate. rcu_assign_pointer() ^^^^^^^^^^^^^^^^^^^^ @@ -318,7 +318,7 @@ 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 Documentation/RCU/Design/Requirements/Requirements.rst + a lockdep splat is emitted. See 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 @@ -399,8 +399,7 @@ for specialized uses, but are relatively uncommon. This section shows a simple use of the core RCU API to protect a global pointer to a dynamically allocated structure. More-typical -uses of RCU may be found in :ref:`listRCU.rst <list_rcu_doc>`, -:ref:`arrayRCU.rst <array_rcu_doc>`, and :ref:`NMI-RCU.rst <NMI_rcu_doc>`. +uses of RCU may be found in listRCU.rst, arrayRCU.rst, and NMI-RCU.rst. :: struct foo { @@ -482,10 +481,9 @@ So, to sum up: RCU read-side critical sections that might be referencing that data item. -See checklist.txt for additional rules to follow when using RCU. -And again, more-typical uses of RCU may be found in :ref:`listRCU.rst -<list_rcu_doc>`, :ref:`arrayRCU.rst <array_rcu_doc>`, and :ref:`NMI-RCU.rst -<NMI_rcu_doc>`. +See checklist.rst for additional rules to follow when using RCU. +And again, more-typical uses of RCU may be found in listRCU.rst, +arrayRCU.rst, and NMI-RCU.rst. .. _4_whatisRCU: @@ -579,7 +577,7 @@ to avoid having to write your own callback:: kfree_rcu(old_fp, rcu); -Again, see checklist.txt for additional rules governing the use of RCU. +Again, see checklist.rst for additional rules governing the use of RCU. .. _5_whatisRCU: @@ -663,7 +661,7 @@ 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.rst + 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/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index 3f1cc5e317ed..c63384ede958 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -631,12 +631,17 @@ Defaults to zero when built as a module and to 10 seconds when built into the kernel. - clearcpuid=BITNUM[,BITNUM...] [X86] + clearcpuid=X[,X...] [X86] Disable CPUID feature X for the kernel. See arch/x86/include/asm/cpufeatures.h for the valid bit - numbers. Note the Linux specific bits are not necessarily - stable over kernel options, but the vendor specific + numbers X. Note the Linux-specific bits are not necessarily + stable over kernel options, but the vendor-specific ones should be. + X can also be a string as appearing in the flags: line + in /proc/cpuinfo which does not have the above + instability issue. However, not all features have names + in /proc/cpuinfo. + Note that using this option will taint your kernel. Also note that user programs calling CPUID directly or using the feature without checking anything will still see it. This just prevents it from @@ -2622,14 +2627,14 @@ when set. Format: <int> - libata.force= [LIBATA] Force configurations. The format is comma- - separated list of "[ID:]VAL" where ID is - PORT[.DEVICE]. PORT and DEVICE are decimal numbers - matching port, link or device. Basically, it matches - the ATA ID string printed on console by libata. If - the whole ID part is omitted, the last PORT and DEVICE - values are used. If ID hasn't been specified yet, the - configuration applies to all ports, links and devices. + libata.force= [LIBATA] Force configurations. The format is a comma- + separated list of "[ID:]VAL" where ID is PORT[.DEVICE]. + PORT and DEVICE are decimal numbers matching port, link + or device. Basically, it matches the ATA ID string + printed on console by libata. If the whole ID part is + omitted, the last PORT and DEVICE values are used. If + ID hasn't been specified yet, the configuration applies + to all ports, links and devices. If only DEVICE is omitted, the parameter applies to the port and all links and devices behind it. DEVICE @@ -2639,7 +2644,7 @@ host link and device attached to it. The VAL specifies the configuration to force. As long - as there's no ambiguity shortcut notation is allowed. + as there is no ambiguity, shortcut notation is allowed. For example, both 1.5 and 1.5G would work for 1.5Gbps. The following configurations can be forced. @@ -2652,19 +2657,58 @@ udma[/][16,25,33,44,66,100,133] notation is also allowed. + * nohrst, nosrst, norst: suppress hard, soft and both + resets. + + * rstonce: only attempt one reset during hot-unplug + link recovery. + + * [no]dbdelay: Enable or disable the extra 200ms delay + before debouncing a link PHY and device presence + detection. + * [no]ncq: Turn on or off NCQ. - * [no]ncqtrim: Turn off queued DSM TRIM. + * [no]ncqtrim: Enable or disable queued DSM TRIM. + + * [no]ncqati: Enable or disable NCQ trim on ATI chipset. + + * [no]trim: Enable or disable (unqueued) TRIM. + + * trim_zero: Indicate that TRIM command zeroes data. + + * max_trim_128m: Set 128M maximum trim size limit. + + * [no]dma: Turn on or off DMA transfers. + + * atapi_dmadir: Enable ATAPI DMADIR bridge support. + + * atapi_mod16_dma: Enable the use of ATAPI DMA for + commands that are not a multiple of 16 bytes. + + * [no]dmalog: Enable or disable the use of the + READ LOG DMA EXT command to access logs. + + * [no]iddevlog: Enable or disable access to the + identify device data log. - * nohrst, nosrst, norst: suppress hard, soft - and both resets. + * [no]logdir: Enable or disable access to the general + purpose log directory. - * rstonce: only attempt one reset during - hot-unplug link recovery + * max_sec_128: Set transfer size limit to 128 sectors. - * dump_id: dump IDENTIFY data. + * max_sec_1024: Set or clear transfer size limit to + 1024 sectors. - * atapi_dmadir: Enable ATAPI DMADIR bridge support + * max_sec_lba48: Set or clear transfer size limit to + 65535 sectors. + + * [no]lpm: Enable or disable link power management. + + * [no]setxfer: Indicate if transfer speed mode setting + should be skipped. + + * dump_id: Dump IDENTIFY data. * disable: Disable this device. @@ -3103,6 +3147,7 @@ mds=off [X86] tsx_async_abort=off [X86] kvm.nx_huge_pages=off [X86] + srbds=off [X86,INTEL] no_entry_flush [PPC] no_uaccess_flush [PPC] @@ -3439,8 +3484,6 @@ nocache [ARM] - noclflush [BUGS=X86] Don't use the CLFLUSH instruction - delayacct [KNL] Enable per-task delay accounting nodsp [SH] Disable hardware DSP at boot time. @@ -3451,16 +3494,11 @@ noexec [IA-64] - noexec [X86] - On X86-32 available only on PAE configured kernels. - noexec=on: enable non-executable mappings (default) - noexec=off: disable non-executable mappings - - nosmap [X86,PPC] + nosmap [PPC] Disable SMAP (Supervisor Mode Access Prevention) even if it is supported by processor. - nosmep [X86,PPC64s] + nosmep [PPC64s] Disable SMEP (Supervisor Mode Execution Prevention) even if it is supported by processor. @@ -3660,8 +3698,6 @@ nosbagart [IA-64] - nosep [BUGS=X86-32] Disables x86 SYSENTER/SYSEXIT support. - nosgx [X86-64,SGX] Disables Intel SGX kernel support. nosmp [SMP] Tells an SMP kernel to act as a UP kernel, @@ -4893,6 +4929,18 @@ rcupdate.rcu_cpu_stall_timeout= [KNL] Set timeout for RCU CPU stall warning messages. + The value is in seconds and the maximum allowed + value is 300 seconds. + + rcupdate.rcu_exp_cpu_stall_timeout= [KNL] + Set timeout for expedited RCU CPU stall warning + messages. The value is in milliseconds + and the maximum allowed value is 21000 + milliseconds. Please note that this value is + adjusted to an arch timer tick resolution. + Setting this to zero causes the value from + rcupdate.rcu_cpu_stall_timeout to be used (after + conversion from seconds to milliseconds). rcupdate.rcu_expedited= [KNL] Use expedited grace-period primitives, for @@ -4955,10 +5003,34 @@ number avoids disturbing real-time workloads, but lengthens grace periods. + rcupdate.rcu_task_stall_info= [KNL] + Set initial timeout in jiffies for RCU task stall + informational messages, which give some indication + of the problem for those not patient enough to + wait for ten minutes. Informational messages are + only printed prior to the stall-warning message + for a given grace period. Disable with a value + less than or equal to zero. Defaults to ten + seconds. A change in value does not take effect + until the beginning of the next grace period. + + rcupdate.rcu_task_stall_info_mult= [KNL] + Multiplier for time interval between successive + RCU task stall informational messages for a given + RCU tasks grace period. This value is clamped + to one through ten, inclusive. It defaults to + the value three, so that the first informational + message is printed 10 seconds into the grace + period, the second at 40 seconds, the third at + 160 seconds, and then the stall warning at 600 + seconds would prevent a fourth at 640 seconds. + rcupdate.rcu_task_stall_timeout= [KNL] - Set timeout in jiffies for RCU task stall warning - messages. Disable with a value less than or equal - to zero. + Set timeout in jiffies for RCU task stall + warning messages. Disable with a value less + than or equal to zero. Defaults to ten minutes. + A change in value does not take effect until + the beginning of the next grace period. rcupdate.rcu_self_test= [KNL] Run the RCU early boot self tests @@ -5308,6 +5380,8 @@ serialnumber [BUGS=X86-32] + sev=option[,option...] [X86-64] See Documentation/x86/x86_64/boot-options.rst + shapers= [NET] Maximal number of shapers. @@ -5377,6 +5451,17 @@ smart2= [HW] Format: <io1>[,<io2>[,...,<io8>]] + smp.csd_lock_timeout= [KNL] + Specify the period of time in milliseconds + that smp_call_function() and friends will wait + for a CPU to release the CSD lock. This is + useful when diagnosing bugs involving CPUs + disabling interrupts for extended periods + of time. Defaults to 5,000 milliseconds, and + setting a value of zero disables this feature. + This feature may be more efficiently disabled + using the csdlock_debug- kernel parameter. + smsc-ircc2.nopnp [HW] Don't use PNP to discover SMC devices smsc-ircc2.ircc_cfg= [HW] Device configuration I/O port smsc-ircc2.ircc_sir= [HW] SIR base I/O port @@ -5608,6 +5693,30 @@ off: Disable mitigation and remove performance impact to RDRAND and RDSEED + srcutree.big_cpu_lim [KNL] + Specifies the number of CPUs constituting a + large system, such that srcu_struct structures + should immediately allocate an srcu_node array. + This kernel-boot parameter defaults to 128, + but takes effect only when the low-order four + bits of srcutree.convert_to_big is equal to 3 + (decide at boot). + + srcutree.convert_to_big [KNL] + Specifies under what conditions an SRCU tree + srcu_struct structure will be converted to big + form, that is, with an rcu_node tree: + + 0: Never. + 1: At init_srcu_struct() time. + 2: When rcutorture decides to. + 3: Decide at boot time (default). + 0x1X: Above plus if high contention. + + Either way, the srcu_node tree will be sized based + on the actual runtime number of CPUs (nr_cpu_ids) + instead of the compile-time CONFIG_NR_CPUS. + srcutree.counter_wrap_check [KNL] Specifies how frequently to check for grace-period sequence counter wrap for the @@ -5625,6 +5734,14 @@ expediting. Set to zero to disable automatic expediting. + srcutree.small_contention_lim [KNL] + Specifies the number of update-side contention + events per jiffy will be tolerated before + initiating a conversion of an srcu_struct + structure to big form. Note that the value of + srcutree.convert_to_big must have the 0x10 bit + set for contention-based conversions to occur. + ssbd= [ARM64,HW] Speculative Store Bypass Disable control diff --git a/Documentation/arm64/silicon-errata.rst b/Documentation/arm64/silicon-errata.rst index 466cb9e89047..d27db84d585e 100644 --- a/Documentation/arm64/silicon-errata.rst +++ b/Documentation/arm64/silicon-errata.rst @@ -189,6 +189,9 @@ stable kernels. +----------------+-----------------+-----------------+-----------------------------+ | Qualcomm Tech. | Kryo4xx Silver | N/A | ARM64_ERRATUM_1024718 | +----------------+-----------------+-----------------+-----------------------------+ +| Qualcomm Tech. | Kryo4xx Gold | N/A | ARM64_ERRATUM_1286807 | ++----------------+-----------------+-----------------+-----------------------------+ + +----------------+-----------------+-----------------+-----------------------------+ | Fujitsu | A64FX | E#010001 | FUJITSU_ERRATUM_010001 | +----------------+-----------------+-----------------+-----------------------------+ diff --git a/Documentation/cdrom/cdrom-standard.rst b/Documentation/cdrom/cdrom-standard.rst index 52ea7b6b2fe8..7964fe134277 100644 --- a/Documentation/cdrom/cdrom-standard.rst +++ b/Documentation/cdrom/cdrom-standard.rst @@ -218,7 +218,6 @@ current *struct* is:: int (*tray_move)(struct cdrom_device_info *, int); int (*lock_door)(struct cdrom_device_info *, int); int (*select_speed)(struct cdrom_device_info *, int); - int (*select_disc)(struct cdrom_device_info *, int); int (*get_last_session) (struct cdrom_device_info *, struct cdrom_multisession *); int (*get_mcn)(struct cdrom_device_info *, struct cdrom_mcn *); @@ -421,15 +420,6 @@ return value indicates an error. :: - int select_disc(struct cdrom_device_info *cdi, int number) - -If the drive can store multiple discs (a juke-box) this function -will perform disc selection. It should return the number of the -selected disc on success, a negative value on error. Currently, only -the ide-cd driver supports this functionality. - -:: - int get_last_session(struct cdrom_device_info *cdi, struct cdrom_multisession *ms_info) diff --git a/Documentation/core-api/timekeeping.rst b/Documentation/core-api/timekeeping.rst index 729e24864fe7..22ec68f24421 100644 --- a/Documentation/core-api/timekeeping.rst +++ b/Documentation/core-api/timekeeping.rst @@ -132,6 +132,7 @@ Some additional variants exist for more specialized cases: .. c:function:: u64 ktime_get_mono_fast_ns( void ) u64 ktime_get_raw_fast_ns( void ) u64 ktime_get_boot_fast_ns( void ) + u64 ktime_get_tai_fast_ns( void ) u64 ktime_get_real_fast_ns( void ) These variants are safe to call from any context, including from diff --git a/Documentation/devicetree/bindings/ata/renesas,rcar-sata.yaml b/Documentation/devicetree/bindings/ata/renesas,rcar-sata.yaml index c060c7914cae..c4e4a9eab658 100644 --- a/Documentation/devicetree/bindings/ata/renesas,rcar-sata.yaml +++ b/Documentation/devicetree/bindings/ata/renesas,rcar-sata.yaml @@ -26,6 +26,7 @@ properties: - items: - enum: - renesas,sata-r8a774b1 # RZ/G2N + - renesas,sata-r8a774e1 # RZ/G2H - renesas,sata-r8a7795 # R-Car H3 - renesas,sata-r8a77965 # R-Car M3-N - const: renesas,rcar-gen3-sata # generic R-Car Gen3 or RZ/G2 diff --git a/Documentation/devicetree/bindings/input/mediatek,mt6779-keypad.yaml b/Documentation/devicetree/bindings/input/mediatek,mt6779-keypad.yaml index b1770640f94b..03ebd2665d07 100644 --- a/Documentation/devicetree/bindings/input/mediatek,mt6779-keypad.yaml +++ b/Documentation/devicetree/bindings/input/mediatek,mt6779-keypad.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Mediatek's Keypad Controller device tree bindings maintainers: - - Fengping Yu <fengping.yu@mediatek.com> + - Mattijs Korpershoek <mkorpershoek@baylibre.com> allOf: - $ref: "/schemas/input/matrix-keymap.yaml#" diff --git a/Documentation/devicetree/bindings/interrupt-controller/arm,gic-v3.yaml b/Documentation/devicetree/bindings/interrupt-controller/arm,gic-v3.yaml index b7197f78e158..3912a89162f0 100644 --- a/Documentation/devicetree/bindings/interrupt-controller/arm,gic-v3.yaml +++ b/Documentation/devicetree/bindings/interrupt-controller/arm,gic-v3.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: ARM Generic Interrupt Controller, version 3 maintainers: - - Marc Zyngier <marc.zyngier@arm.com> + - Marc Zyngier <maz@kernel.org> description: | AArch64 SMP cores are often associated with a GICv3, providing Private @@ -78,7 +78,11 @@ properties: - GIC Hypervisor interface (GICH) - GIC Virtual CPU interface (GICV) - GICC, GICH and GICV are optional. + GICC, GICH and GICV are optional, but must be described if the CPUs + support them. Examples of such CPUs are ARM's implementations of the + ARMv8.0 architecture such as Cortex-A32, A34, A35, A53, A57, A72 and + A73 (this list is not exhaustive). + minItems: 2 maxItems: 4096 # Should be enough? diff --git a/Documentation/devicetree/bindings/memory-controllers/fsl/fsl,ddr.yaml b/Documentation/devicetree/bindings/memory-controllers/fsl/fsl,ddr.yaml index af5147f9da72..84f778a99546 100644 --- a/Documentation/devicetree/bindings/memory-controllers/fsl/fsl,ddr.yaml +++ b/Documentation/devicetree/bindings/memory-controllers/fsl/fsl,ddr.yaml @@ -25,12 +25,6 @@ properties: - const: fsl,qoriq-memory-controller - enum: - fsl,bsc9132-memory-controller - - fsl,8540-memory-controller - - fsl,8541-memory-controller - - fsl,8544-memory-controller - - fsl,8548-memory-controller - - fsl,8555-memory-controller - - fsl,8568-memory-controller - fsl,mpc8536-memory-controller - fsl,mpc8540-memory-controller - fsl,mpc8541-memory-controller diff --git a/Documentation/devicetree/bindings/pinctrl/aspeed,ast2600-pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/aspeed,ast2600-pinctrl.yaml index 57b68d6c7c70..3666ac5b6518 100644 --- a/Documentation/devicetree/bindings/pinctrl/aspeed,ast2600-pinctrl.yaml +++ b/Documentation/devicetree/bindings/pinctrl/aspeed,ast2600-pinctrl.yaml @@ -33,7 +33,7 @@ patternProperties: $ref: "/schemas/types.yaml#/definitions/string" enum: [ ADC0, ADC1, ADC10, ADC11, ADC12, ADC13, ADC14, ADC15, ADC2, ADC3, ADC4, ADC5, ADC6, ADC7, ADC8, ADC9, BMCINT, EMMC, ESPI, ESPIALT, - FSI1, FSI2, FWSPIABR, FWSPID, FWSPIWP, GPIT0, GPIT1, GPIT2, GPIT3, + FSI1, FSI2, FWQSPI, FWSPIABR, FWSPID, FWSPIWP, GPIT0, GPIT1, GPIT2, GPIT3, GPIT4, GPIT5, GPIT6, GPIT7, GPIU0, GPIU1, GPIU2, GPIU3, GPIU4, GPIU5, GPIU6, GPIU7, I2C1, I2C10, I2C11, I2C12, I2C13, I2C14, I2C15, I2C16, I2C2, I2C3, I2C4, I2C5, I2C6, I2C7, I2C8, I2C9, I3C3, I3C4, I3C5, @@ -58,7 +58,7 @@ patternProperties: $ref: "/schemas/types.yaml#/definitions/string" enum: [ ADC0, ADC1, ADC10, ADC11, ADC12, ADC13, ADC14, ADC15, ADC2, ADC3, ADC4, ADC5, ADC6, ADC7, ADC8, ADC9, BMCINT, EMMCG1, EMMCG4, - EMMCG8, ESPI, ESPIALT, FSI1, FSI2, FWSPIABR, FWSPID, FWQSPID, FWSPIWP, + EMMCG8, ESPI, ESPIALT, FSI1, FSI2, FWQSPI, FWSPIABR, FWSPID, FWSPIWP, GPIT0, GPIT1, GPIT2, GPIT3, GPIT4, GPIT5, GPIT6, GPIT7, GPIU0, GPIU1, GPIU2, GPIU3, GPIU4, GPIU5, GPIU6, GPIU7, HVI3C3, HVI3C4, I2C1, I2C10, I2C11, I2C12, I2C13, I2C14, I2C15, I2C16, I2C2, I2C3, I2C4, I2C5, diff --git a/Documentation/devicetree/bindings/powerpc/fsl/l2cache.txt b/Documentation/devicetree/bindings/powerpc/fsl/l2cache.txt index 8a70696395a7..22ad012660e9 100644 --- a/Documentation/devicetree/bindings/powerpc/fsl/l2cache.txt +++ b/Documentation/devicetree/bindings/powerpc/fsl/l2cache.txt @@ -6,12 +6,6 @@ The cache bindings explained below are Devicetree Specification compliant Required Properties: - compatible : Should include one of the following: - "fsl,8540-l2-cache-controller" - "fsl,8541-l2-cache-controller" - "fsl,8544-l2-cache-controller" - "fsl,8548-l2-cache-controller" - "fsl,8555-l2-cache-controller" - "fsl,8568-l2-cache-controller" "fsl,b4420-l2-cache-controller" "fsl,b4860-l2-cache-controller" "fsl,bsc9131-l2-cache-controller" diff --git a/Documentation/driver-api/gpio/driver.rst b/Documentation/driver-api/gpio/driver.rst index bbc53920d4dd..a1ddefa1f55f 100644 --- a/Documentation/driver-api/gpio/driver.rst +++ b/Documentation/driver-api/gpio/driver.rst @@ -417,30 +417,66 @@ struct gpio_irq_chip inside struct gpio_chip before adding the gpio_chip. If you do this, the additional irq_chip will be set up by gpiolib at the same time as setting up the rest of the GPIO functionality. The following is a typical example of a chained cascaded interrupt handler using -the gpio_irq_chip: +the gpio_irq_chip. Note how the mask/unmask (or disable/enable) functions +call into the core gpiolib code: .. code-block:: c - /* Typical state container with dynamic irqchip */ + /* Typical state container */ struct my_gpio { struct gpio_chip gc; - struct irq_chip irq; + }; + + static void my_gpio_mask_irq(struct irq_data *d) + { + struct gpio_chip *gc = irq_desc_get_handler_data(d); + + /* + * Perform any necessary action to mask the interrupt, + * and then call into the core code to synchronise the + * state. + */ + + gpiochip_disable_irq(gc, d->hwirq); + } + + static void my_gpio_unmask_irq(struct irq_data *d) + { + struct gpio_chip *gc = irq_desc_get_handler_data(d); + + gpiochip_enable_irq(gc, d->hwirq); + + /* + * Perform any necessary action to unmask the interrupt, + * after having called into the core code to synchronise + * the state. + */ + } + + /* + * Statically populate the irqchip. Note that it is made const + * (further indicated by the IRQCHIP_IMMUTABLE flag), and that + * the GPIOCHIP_IRQ_RESOURCE_HELPER macro adds some extra + * callbacks to the structure. + */ + static const struct irq_chip my_gpio_irq_chip = { + .name = "my_gpio_irq", + .irq_ack = my_gpio_ack_irq, + .irq_mask = my_gpio_mask_irq, + .irq_unmask = my_gpio_unmask_irq, + .irq_set_type = my_gpio_set_irq_type, + .flags = IRQCHIP_IMMUTABLE, + /* Provide the gpio resource callbacks */ + GPIOCHIP_IRQ_RESOURCE_HELPERS, }; int irq; /* from platform etc */ struct my_gpio *g; struct gpio_irq_chip *girq; - /* Set up the irqchip dynamically */ - g->irq.name = "my_gpio_irq"; - g->irq.irq_ack = my_gpio_ack_irq; - g->irq.irq_mask = my_gpio_mask_irq; - g->irq.irq_unmask = my_gpio_unmask_irq; - g->irq.irq_set_type = my_gpio_set_irq_type; - /* Get a pointer to the gpio_irq_chip */ girq = &g->gc.irq; - girq->chip = &g->irq; + gpio_irq_chip_set_chip(girq, &my_gpio_irq_chip); girq->parent_handler = ftgpio_gpio_irq_handler; girq->num_parents = 1; girq->parents = devm_kcalloc(dev, 1, sizeof(*girq->parents), @@ -458,23 +494,58 @@ the interrupt separately and go with it: .. code-block:: c - /* Typical state container with dynamic irqchip */ + /* Typical state container */ struct my_gpio { struct gpio_chip gc; - struct irq_chip irq; + }; + + static void my_gpio_mask_irq(struct irq_data *d) + { + struct gpio_chip *gc = irq_desc_get_handler_data(d); + + /* + * Perform any necessary action to mask the interrupt, + * and then call into the core code to synchronise the + * state. + */ + + gpiochip_disable_irq(gc, d->hwirq); + } + + static void my_gpio_unmask_irq(struct irq_data *d) + { + struct gpio_chip *gc = irq_desc_get_handler_data(d); + + gpiochip_enable_irq(gc, d->hwirq); + + /* + * Perform any necessary action to unmask the interrupt, + * after having called into the core code to synchronise + * the state. + */ + } + + /* + * Statically populate the irqchip. Note that it is made const + * (further indicated by the IRQCHIP_IMMUTABLE flag), and that + * the GPIOCHIP_IRQ_RESOURCE_HELPER macro adds some extra + * callbacks to the structure. + */ + static const struct irq_chip my_gpio_irq_chip = { + .name = "my_gpio_irq", + .irq_ack = my_gpio_ack_irq, + .irq_mask = my_gpio_mask_irq, + .irq_unmask = my_gpio_unmask_irq, + .irq_set_type = my_gpio_set_irq_type, + .flags = IRQCHIP_IMMUTABLE, + /* Provide the gpio resource callbacks */ + GPIOCHIP_IRQ_RESOURCE_HELPERS, }; int irq; /* from platform etc */ struct my_gpio *g; struct gpio_irq_chip *girq; - /* Set up the irqchip dynamically */ - g->irq.name = "my_gpio_irq"; - g->irq.irq_ack = my_gpio_ack_irq; - g->irq.irq_mask = my_gpio_mask_irq; - g->irq.irq_unmask = my_gpio_unmask_irq; - g->irq.irq_set_type = my_gpio_set_irq_type; - ret = devm_request_threaded_irq(dev, irq, NULL, irq_thread_fn, IRQF_ONESHOT, "my-chip", g); if (ret < 0) @@ -482,7 +553,7 @@ the interrupt separately and go with it: /* Get a pointer to the gpio_irq_chip */ girq = &g->gc.irq; - girq->chip = &g->irq; + gpio_irq_chip_set_chip(girq, &my_gpio_irq_chip); /* This will let us handle the parent IRQ in the driver */ girq->parent_handler = NULL; girq->num_parents = 0; @@ -500,24 +571,61 @@ In this case the typical set-up will look like this: /* Typical state container with dynamic irqchip */ struct my_gpio { struct gpio_chip gc; - struct irq_chip irq; struct fwnode_handle *fwnode; }; - int irq; /* from platform etc */ + static void my_gpio_mask_irq(struct irq_data *d) + { + struct gpio_chip *gc = irq_desc_get_handler_data(d); + + /* + * Perform any necessary action to mask the interrupt, + * and then call into the core code to synchronise the + * state. + */ + + gpiochip_disable_irq(gc, d->hwirq); + irq_mask_mask_parent(d); + } + + static void my_gpio_unmask_irq(struct irq_data *d) + { + struct gpio_chip *gc = irq_desc_get_handler_data(d); + + gpiochip_enable_irq(gc, d->hwirq); + + /* + * Perform any necessary action to unmask the interrupt, + * after having called into the core code to synchronise + * the state. + */ + + irq_mask_unmask_parent(d); + } + + /* + * Statically populate the irqchip. Note that it is made const + * (further indicated by the IRQCHIP_IMMUTABLE flag), and that + * the GPIOCHIP_IRQ_RESOURCE_HELPER macro adds some extra + * callbacks to the structure. + */ + static const struct irq_chip my_gpio_irq_chip = { + .name = "my_gpio_irq", + .irq_ack = my_gpio_ack_irq, + .irq_mask = my_gpio_mask_irq, + .irq_unmask = my_gpio_unmask_irq, + .irq_set_type = my_gpio_set_irq_type, + .flags = IRQCHIP_IMMUTABLE, + /* Provide the gpio resource callbacks */ + GPIOCHIP_IRQ_RESOURCE_HELPERS, + }; + struct my_gpio *g; struct gpio_irq_chip *girq; - /* Set up the irqchip dynamically */ - g->irq.name = "my_gpio_irq"; - g->irq.irq_ack = my_gpio_ack_irq; - g->irq.irq_mask = my_gpio_mask_irq; - g->irq.irq_unmask = my_gpio_unmask_irq; - g->irq.irq_set_type = my_gpio_set_irq_type; - /* Get a pointer to the gpio_irq_chip */ girq = &g->gc.irq; - girq->chip = &g->irq; + gpio_irq_chip_set_chip(girq, &my_gpio_irq_chip); girq->default_type = IRQ_TYPE_NONE; girq->handler = handle_bad_irq; girq->fwnode = g->fwnode; @@ -605,8 +713,9 @@ When implementing an irqchip inside a GPIO driver, these two functions should typically be called in the .irq_disable() and .irq_enable() callbacks from the irqchip. -When using the gpiolib irqchip helpers, these callbacks are automatically -assigned. +When IRQCHIP_IMMUTABLE is not advertised by the irqchip, these callbacks +are automatically assigned. This behaviour is deprecated and on its way +to be removed from the kernel. Real-Time compliance for GPIO IRQ chips diff --git a/Documentation/driver-api/libata.rst b/Documentation/driver-api/libata.rst index d477e296bda5..311af516a3fd 100644 --- a/Documentation/driver-api/libata.rst +++ b/Documentation/driver-api/libata.rst @@ -424,12 +424,6 @@ How commands are issued ----------------------- Internal commands - First, qc is allocated and initialized using :c:func:`ata_qc_new_init`. - Although :c:func:`ata_qc_new_init` doesn't implement any wait or retry - mechanism when qc is not available, internal commands are currently - issued only during initialization and error recovery, so no other - command is active and allocation is guaranteed to succeed. - Once allocated qc's taskfile is initialized for the command to be executed. qc currently has two mechanisms to notify completion. One is via ``qc->complete_fn()`` callback and the other is completion @@ -447,11 +441,6 @@ SCSI commands translated. No qc is involved in processing a simulated scmd. The result is computed right away and the scmd is completed. - For a translated scmd, :c:func:`ata_qc_new_init` is invoked to allocate a - qc and the scmd is translated into the qc. SCSI midlayer's - completion notification function pointer is stored into - ``qc->scsidone``. - ``qc->complete_fn()`` callback is used for completion notification. ATA commands use :c:func:`ata_scsi_qc_complete` while ATAPI commands use :c:func:`atapi_qc_complete`. Both functions end up calling ``qc->scsidone`` diff --git a/Documentation/filesystems/proc.rst b/Documentation/filesystems/proc.rst index 061744c436d9..6a0dd99786f9 100644 --- a/Documentation/filesystems/proc.rst +++ b/Documentation/filesystems/proc.rst @@ -1183,85 +1183,7 @@ Provides counts of softirq handlers serviced since boot time, for each CPU. HRTIMER: 0 0 0 0 RCU: 1678 1769 2178 2250 - -1.3 IDE devices in /proc/ide ----------------------------- - -The subdirectory /proc/ide contains information about all IDE devices of which -the kernel is aware. There is one subdirectory for each IDE controller, the -file drivers and a link for each IDE device, pointing to the device directory -in the controller specific subtree. - -The file 'drivers' contains general information about the drivers used for the -IDE devices:: - - > cat /proc/ide/drivers - ide-cdrom version 4.53 - ide-disk version 1.08 - -More detailed information can be found in the controller specific -subdirectories. These are named ide0, ide1 and so on. Each of these -directories contains the files shown in table 1-6. - - -.. table:: Table 1-6: IDE controller info in /proc/ide/ide? - - ======= ======================================= - File Content - ======= ======================================= - channel IDE channel (0 or 1) - config Configuration (only for PCI/IDE bridge) - mate Mate name - model Type/Chipset of IDE controller - ======= ======================================= - -Each device connected to a controller has a separate subdirectory in the -controllers directory. The files listed in table 1-7 are contained in these -directories. - - -.. table:: Table 1-7: IDE device information - - ================ ========================================== - File Content - ================ ========================================== - cache The cache - capacity Capacity of the medium (in 512Byte blocks) - driver driver and version - geometry physical and logical geometry - identify device identify block - media media type - model device identifier - settings device setup - smart_thresholds IDE disk management thresholds - smart_values IDE disk management values - ================ ========================================== - -The most interesting file is ``settings``. This file contains a nice -overview of the drive parameters:: - - # cat /proc/ide/ide0/hda/settings - name value min max mode - ---- ----- --- --- ---- - bios_cyl 526 0 65535 rw - bios_head 255 0 255 rw - bios_sect 63 0 63 rw - breada_readahead 4 0 127 rw - bswap 0 0 1 r - file_readahead 72 0 2097151 rw - io_32bit 0 0 3 rw - keepsettings 0 0 1 rw - max_kb_per_request 122 1 127 rw - multcount 0 0 8 rw - nice1 1 0 1 rw - nowerr 0 0 1 rw - pio_mode write-only 0 255 w - slow 0 0 1 rw - unmaskirq 0 0 1 rw - using_dma 0 0 1 rw - - -1.4 Networking info in /proc/net +1.3 Networking info in /proc/net -------------------------------- The subdirectory /proc/net follows the usual pattern. Table 1-8 shows the @@ -1340,7 +1262,7 @@ It will contain information that is specific to that bond, such as the current slaves of the bond, the link status of the slaves, and how many times the slaves link has failed. -1.5 SCSI info +1.4 SCSI info ------------- If you have a SCSI host adapter in your system, you'll find a subdirectory @@ -1403,7 +1325,7 @@ AHA-2940 SCSI adapter:: Total transfers 0 (0 reads and 0 writes) -1.6 Parallel port info in /proc/parport +1.5 Parallel port info in /proc/parport --------------------------------------- The directory /proc/parport contains information about the parallel ports of @@ -1428,7 +1350,7 @@ These directories contain the four files shown in Table 1-10. number or none). ========= ==================================================================== -1.7 TTY info in /proc/tty +1.6 TTY info in /proc/tty ------------------------- Information about the available and actually used tty's can be found in the @@ -1463,7 +1385,7 @@ To see which tty's are currently in use, you can simply look into the file unknown /dev/tty 4 1-63 console -1.8 Miscellaneous kernel statistics in /proc/stat +1.7 Miscellaneous kernel statistics in /proc/stat ------------------------------------------------- Various pieces of information about kernel activity are available in the @@ -1536,7 +1458,7 @@ softirqs serviced; each subsequent column is the total for that particular softirq. -1.9 Ext4 file system parameters +1.8 Ext4 file system parameters ------------------------------- Information about mounted ext4 file systems can be found in @@ -1552,7 +1474,7 @@ in Table 1-12, below. mb_groups details of multiblock allocator buddy cache of free blocks ============== ========================================================== -1.10 /proc/consoles +1.9 /proc/consoles ------------------- Shows registered system console lines. diff --git a/Documentation/filesystems/zonefs.rst b/Documentation/filesystems/zonefs.rst index 6b213fe9a33e..394b9f15dce0 100644 --- a/Documentation/filesystems/zonefs.rst +++ b/Documentation/filesystems/zonefs.rst @@ -306,8 +306,15 @@ Further notes: Mount options ------------- -zonefs define the "errors=<behavior>" mount option to allow the user to specify -zonefs behavior in response to I/O errors, inode size inconsistencies or zone +zonefs defines several mount options: +* errors=<behavior> +* explicit-open + +"errors=<behavior>" option +~~~~~~~~~~~~~~~~~~~~~~~~~~ + +The "errors=<behavior>" option mount option allows the user to specify zonefs +behavior in response to I/O errors, inode size inconsistencies or zone condition changes. The defined behaviors are as follow: * remount-ro (default) @@ -326,6 +333,9 @@ discover the amount of data that has been written to the zone. In the case of a read-only zone discovered at run-time, as indicated in the previous section. The size of the zone file is left unchanged from its last updated value. +"explicit-open" option +~~~~~~~~~~~~~~~~~~~~~~ + A zoned block device (e.g. an NVMe Zoned Namespace device) may have limits on the number of zones that can be active, that is, zones that are in the implicit open, explicit open or closed conditions. This potential limitation @@ -341,6 +351,44 @@ guaranteed that write requests can be processed. Conversely, the to the device on the last close() of a zone file if the zone is not full nor empty. +Runtime sysfs attributes +------------------------ + +zonefs defines several sysfs attributes for mounted devices. All attributes +are user readable and can be found in the directory /sys/fs/zonefs/<dev>/, +where <dev> is the name of the mounted zoned block device. + +The attributes defined are as follows. + +* **max_wro_seq_files**: This attribute reports the maximum number of + sequential zone files that can be open for writing. This number corresponds + to the maximum number of explicitly or implicitly open zones that the device + supports. A value of 0 means that the device has no limit and that any zone + (any file) can be open for writing and written at any time, regardless of the + state of other zones. When the *explicit-open* mount option is used, zonefs + will fail any open() system call requesting to open a sequential zone file for + writing when the number of sequential zone files already open for writing has + reached the *max_wro_seq_files* limit. +* **nr_wro_seq_files**: This attribute reports the current number of sequential + zone files open for writing. When the "explicit-open" mount option is used, + this number can never exceed *max_wro_seq_files*. If the *explicit-open* + mount option is not used, the reported number can be greater than + *max_wro_seq_files*. In such case, it is the responsibility of the + application to not write simultaneously more than *max_wro_seq_files* + sequential zone files. Failure to do so can result in write errors. +* **max_active_seq_files**: This attribute reports the maximum number of + sequential zone files that are in an active state, that is, sequential zone + files that are partially writen (not empty nor full) or that have a zone that + is explicitly open (which happens only if the *explicit-open* mount option is + used). This number is always equal to the maximum number of active zones that + the device supports. A value of 0 means that the mounted device has no limit + on the number of sequential zone files that can be active. +* **nr_active_seq_files**: This attributes reports the current number of + sequential zone files that are active. If *max_active_seq_files* is not 0, + then the value of *nr_active_seq_files* can never exceed the value of + *nr_active_seq_files*, regardless of the use of the *explicit-open* mount + option. + Zonefs User Space Tools ======================= diff --git a/Documentation/process/embargoed-hardware-issues.rst b/Documentation/process/embargoed-hardware-issues.rst index 6f8f36e10e8b..95999302d279 100644 --- a/Documentation/process/embargoed-hardware-issues.rst +++ b/Documentation/process/embargoed-hardware-issues.rst @@ -244,10 +244,11 @@ disclosure of a particular issue, unless requested by a response team or by an involved disclosed party. The current ambassadors list: ============= ======================================================== - ARM Grant Likely <grant.likely@arm.com> AMD Tom Lendacky <tom.lendacky@amd.com> - IBM Z Christian Borntraeger <borntraeger@de.ibm.com> - IBM Power Anton Blanchard <anton@linux.ibm.com> + Ampere Darren Hart <darren@os.amperecomputing.com> + ARM Catalin Marinas <catalin.marinas@arm.com> + IBM Power Anton Blanchard <anton@linux.ibm.com> + IBM Z Christian Borntraeger <borntraeger@de.ibm.com> Intel Tony Luck <tony.luck@intel.com> Qualcomm Trilok Soni <tsoni@codeaurora.org> diff --git a/Documentation/process/maintainer-tip.rst b/Documentation/process/maintainer-tip.rst index c74f4a81588b..572a3289c9cb 100644 --- a/Documentation/process/maintainer-tip.rst +++ b/Documentation/process/maintainer-tip.rst @@ -437,6 +437,20 @@ in a private repository which allows interested people to easily pull the series for testing. The usual way to offer this is a git URL in the cover letter of the patch series. +Testing +^^^^^^^ + +Code should be tested before submitting to the tip maintainers. Anything +other than minor changes should be built, booted and tested with +comprehensive (and heavyweight) kernel debugging options enabled. + +These debugging options can be found in kernel/configs/x86_debug.config +and can be added to an existing kernel config by running: + + make x86_debug.config + +Some of these options are x86-specific and can be left out when testing +on other architectures. Coding style notes ------------------ diff --git a/Documentation/security/index.rst b/Documentation/security/index.rst index 16335de04e8c..6ed8d2fa6f9e 100644 --- a/Documentation/security/index.rst +++ b/Documentation/security/index.rst @@ -17,3 +17,4 @@ Security Documentation tpm/index digsig landlock + secrets/index diff --git a/Documentation/security/secrets/coco.rst b/Documentation/security/secrets/coco.rst new file mode 100644 index 000000000000..262e7abb1b24 --- /dev/null +++ b/Documentation/security/secrets/coco.rst @@ -0,0 +1,103 @@ +.. SPDX-License-Identifier: GPL-2.0 + +============================== +Confidential Computing secrets +============================== + +This document describes how Confidential Computing secret injection is handled +from the firmware to the operating system, in the EFI driver and the efi_secret +kernel module. + + +Introduction +============ + +Confidential Computing (coco) hardware such as AMD SEV (Secure Encrypted +Virtualization) allows guest owners to inject secrets into the VMs +memory without the host/hypervisor being able to read them. In SEV, +secret injection is performed early in the VM launch process, before the +guest starts running. + +The efi_secret kernel module allows userspace applications to access these +secrets via securityfs. + + +Secret data flow +================ + +The guest firmware may reserve a designated memory area for secret injection, +and publish its location (base GPA and length) in the EFI configuration table +under a ``LINUX_EFI_COCO_SECRET_AREA_GUID`` entry +(``adf956ad-e98c-484c-ae11-b51c7d336447``). This memory area should be marked +by the firmware as ``EFI_RESERVED_TYPE``, and therefore the kernel should not +be use it for its own purposes. + +During the VM's launch, the virtual machine manager may inject a secret to that +area. In AMD SEV and SEV-ES this is performed using the +``KVM_SEV_LAUNCH_SECRET`` command (see [sev]_). The strucutre of the injected +Guest Owner secret data should be a GUIDed table of secret values; the binary +format is described in ``drivers/virt/coco/efi_secret/efi_secret.c`` under +"Structure of the EFI secret area". + +On kernel start, the kernel's EFI driver saves the location of the secret area +(taken from the EFI configuration table) in the ``efi.coco_secret`` field. +Later it checks if the secret area is populated: it maps the area and checks +whether its content begins with ``EFI_SECRET_TABLE_HEADER_GUID`` +(``1e74f542-71dd-4d66-963e-ef4287ff173b``). If the secret area is populated, +the EFI driver will autoload the efi_secret kernel module, which exposes the +secrets to userspace applications via securityfs. The details of the +efi_secret filesystem interface are in [secrets-coco-abi]_. + + +Application usage example +========================= + +Consider a guest performing computations on encrypted files. The Guest Owner +provides the decryption key (= secret) using the secret injection mechanism. +The guest application reads the secret from the efi_secret filesystem and +proceeds to decrypt the files into memory and then performs the needed +computations on the content. + +In this example, the host can't read the files from the disk image +because they are encrypted. Host can't read the decryption key because +it is passed using the secret injection mechanism (= secure channel). +Host can't read the decrypted content from memory because it's a +confidential (memory-encrypted) guest. + +Here is a simple example for usage of the efi_secret module in a guest +to which an EFI secret area with 4 secrets was injected during launch:: + + # ls -la /sys/kernel/security/secrets/coco + total 0 + drwxr-xr-x 2 root root 0 Jun 28 11:54 . + drwxr-xr-x 3 root root 0 Jun 28 11:54 .. + -r--r----- 1 root root 0 Jun 28 11:54 736870e5-84f0-4973-92ec-06879ce3da0b + -r--r----- 1 root root 0 Jun 28 11:54 83c83f7f-1356-4975-8b7e-d3a0b54312c6 + -r--r----- 1 root root 0 Jun 28 11:54 9553f55d-3da2-43ee-ab5d-ff17f78864d2 + -r--r----- 1 root root 0 Jun 28 11:54 e6f5a162-d67f-4750-a67c-5d065f2a9910 + + # hd /sys/kernel/security/secrets/coco/e6f5a162-d67f-4750-a67c-5d065f2a9910 + 00000000 74 68 65 73 65 2d 61 72 65 2d 74 68 65 2d 6b 61 |these-are-the-ka| + 00000010 74 61 2d 73 65 63 72 65 74 73 00 01 02 03 04 05 |ta-secrets......| + 00000020 06 07 |..| + 00000022 + + # rm /sys/kernel/security/secrets/coco/e6f5a162-d67f-4750-a67c-5d065f2a9910 + + # ls -la /sys/kernel/security/secrets/coco + total 0 + drwxr-xr-x 2 root root 0 Jun 28 11:55 . + drwxr-xr-x 3 root root 0 Jun 28 11:54 .. + -r--r----- 1 root root 0 Jun 28 11:54 736870e5-84f0-4973-92ec-06879ce3da0b + -r--r----- 1 root root 0 Jun 28 11:54 83c83f7f-1356-4975-8b7e-d3a0b54312c6 + -r--r----- 1 root root 0 Jun 28 11:54 9553f55d-3da2-43ee-ab5d-ff17f78864d2 + + +References +========== + +See [sev-api-spec]_ for more info regarding SEV ``LAUNCH_SECRET`` operation. + +.. [sev] Documentation/virt/kvm/amd-memory-encryption.rst +.. [secrets-coco-abi] Documentation/ABI/testing/securityfs-secrets-coco +.. [sev-api-spec] https://www.amd.com/system/files/TechDocs/55766_SEV-KM_API_Specification.pdf diff --git a/Documentation/security/secrets/index.rst b/Documentation/security/secrets/index.rst new file mode 100644 index 000000000000..ced34e9c43bd --- /dev/null +++ b/Documentation/security/secrets/index.rst @@ -0,0 +1,9 @@ +.. SPDX-License-Identifier: GPL-2.0 + +===================== +Secrets documentation +===================== + +.. toctree:: + + coco diff --git a/Documentation/userspace-api/ioctl/cdrom.rst b/Documentation/userspace-api/ioctl/cdrom.rst index 682948fc88a3..2ad91dbebd7c 100644 --- a/Documentation/userspace-api/ioctl/cdrom.rst +++ b/Documentation/userspace-api/ioctl/cdrom.rst @@ -718,6 +718,9 @@ CDROMPLAYBLK CDROMGETSPINDOWN + Obsolete, was ide-cd only + + usage:: char spindown; @@ -736,6 +739,9 @@ CDROMGETSPINDOWN CDROMSETSPINDOWN + Obsolete, was ide-cd only + + usage:: char spindown diff --git a/Documentation/virt/coco/sev-guest.rst b/Documentation/virt/coco/sev-guest.rst new file mode 100644 index 000000000000..bf593e88cfd9 --- /dev/null +++ b/Documentation/virt/coco/sev-guest.rst @@ -0,0 +1,155 @@ +.. SPDX-License-Identifier: GPL-2.0 + +=================================================================== +The Definitive SEV Guest API Documentation +=================================================================== + +1. General description +====================== + +The SEV API is a set of ioctls that are used by the guest or hypervisor +to get or set a certain aspect of the SEV virtual machine. The ioctls belong +to the following classes: + + - Hypervisor ioctls: These query and set global attributes which affect the + whole SEV firmware. These ioctl are used by platform provisioning tools. + + - Guest ioctls: These query and set attributes of the SEV virtual machine. + +2. API description +================== + +This section describes ioctls that is used for querying the SEV guest report +from the SEV firmware. For each ioctl, the following information is provided +along with a description: + + Technology: + which SEV technology provides this ioctl. SEV, SEV-ES, SEV-SNP or all. + + Type: + hypervisor or guest. The ioctl can be used inside the guest or the + hypervisor. + + Parameters: + what parameters are accepted by the ioctl. + + Returns: + the return value. General error numbers (-ENOMEM, -EINVAL) + are not detailed, but errors with specific meanings are. + +The guest ioctl should be issued on a file descriptor of the /dev/sev-guest device. +The ioctl accepts struct snp_user_guest_request. The input and output structure is +specified through the req_data and resp_data field respectively. If the ioctl fails +to execute due to a firmware error, then fw_err code will be set otherwise the +fw_err will be set to 0x00000000000000ff. + +The firmware checks that the message sequence counter is one greater than +the guests message sequence counter. If guest driver fails to increment message +counter (e.g. counter overflow), then -EIO will be returned. + +:: + + struct snp_guest_request_ioctl { + /* Message version number */ + __u32 msg_version; + + /* Request and response structure address */ + __u64 req_data; + __u64 resp_data; + + /* firmware error code on failure (see psp-sev.h) */ + __u64 fw_err; + }; + +2.1 SNP_GET_REPORT +------------------ + +:Technology: sev-snp +:Type: guest ioctl +:Parameters (in): struct snp_report_req +:Returns (out): struct snp_report_resp on success, -negative on error + +The SNP_GET_REPORT ioctl can be used to query the attestation report from the +SEV-SNP firmware. The ioctl uses the SNP_GUEST_REQUEST (MSG_REPORT_REQ) command +provided by the SEV-SNP firmware to query the attestation report. + +On success, the snp_report_resp.data will contains the report. The report +contain the format described in the SEV-SNP specification. See the SEV-SNP +specification for further details. + +2.2 SNP_GET_DERIVED_KEY +----------------------- +:Technology: sev-snp +:Type: guest ioctl +:Parameters (in): struct snp_derived_key_req +:Returns (out): struct snp_derived_key_resp on success, -negative on error + +The SNP_GET_DERIVED_KEY ioctl can be used to get a key derive from a root key. +The derived key can be used by the guest for any purpose, such as sealing keys +or communicating with external entities. + +The ioctl uses the SNP_GUEST_REQUEST (MSG_KEY_REQ) command provided by the +SEV-SNP firmware to derive the key. See SEV-SNP specification for further details +on the various fields passed in the key derivation request. + +On success, the snp_derived_key_resp.data contains the derived key value. See +the SEV-SNP specification for further details. + + +2.3 SNP_GET_EXT_REPORT +---------------------- +:Technology: sev-snp +:Type: guest ioctl +:Parameters (in/out): struct snp_ext_report_req +:Returns (out): struct snp_report_resp on success, -negative on error + +The SNP_GET_EXT_REPORT ioctl is similar to the SNP_GET_REPORT. The difference is +related to the additional certificate data that is returned with the report. +The certificate data returned is being provided by the hypervisor through the +SNP_SET_EXT_CONFIG. + +The ioctl uses the SNP_GUEST_REQUEST (MSG_REPORT_REQ) command provided by the SEV-SNP +firmware to get the attestation report. + +On success, the snp_ext_report_resp.data will contain the attestation report +and snp_ext_report_req.certs_address will contain the certificate blob. If the +length of the blob is smaller than expected then snp_ext_report_req.certs_len will +be updated with the expected value. + +See GHCB specification for further detail on how to parse the certificate blob. + +3. SEV-SNP CPUID Enforcement +============================ + +SEV-SNP guests can access a special page that contains a table of CPUID values +that have been validated by the PSP as part of the SNP_LAUNCH_UPDATE firmware +command. It provides the following assurances regarding the validity of CPUID +values: + + - Its address is obtained via bootloader/firmware (via CC blob), and those + binaries will be measured as part of the SEV-SNP attestation report. + - Its initial state will be encrypted/pvalidated, so attempts to modify + it during run-time will result in garbage being written, or #VC exceptions + being generated due to changes in validation state if the hypervisor tries + to swap the backing page. + - Attempts to bypass PSP checks by the hypervisor by using a normal page, or + a non-CPUID encrypted page will change the measurement provided by the + SEV-SNP attestation report. + - The CPUID page contents are *not* measured, but attempts to modify the + expected contents of a CPUID page as part of guest initialization will be + gated by the PSP CPUID enforcement policy checks performed on the page + during SNP_LAUNCH_UPDATE, and noticeable later if the guest owner + implements their own checks of the CPUID values. + +It is important to note that this last assurance is only useful if the kernel +has taken care to make use of the SEV-SNP CPUID throughout all stages of boot. +Otherwise, guest owner attestation provides no assurance that the kernel wasn't +fed incorrect values at some point during boot. + + +Reference +--------- + +SEV-SNP and GHCB specification: developer.amd.com/sev + +The driver is based on SEV-SNP firmware spec 0.9 and GHCB spec version 2.0. diff --git a/Documentation/virt/index.rst b/Documentation/virt/index.rst index edea7fea95a8..492f0920b988 100644 --- a/Documentation/virt/index.rst +++ b/Documentation/virt/index.rst @@ -13,6 +13,7 @@ Linux Virtualization Support guest-halt-polling ne_overview acrn/index + coco/sev-guest .. only:: html and subproject diff --git a/Documentation/x86/cpuinfo.rst b/Documentation/x86/cpuinfo.rst index 5d54c39a063f..08246e8ac835 100644 --- a/Documentation/x86/cpuinfo.rst +++ b/Documentation/x86/cpuinfo.rst @@ -140,9 +140,8 @@ from #define X86_FEATURE_UMIP (16*32 + 2). In addition, there exists a variety of custom command-line parameters that disable specific features. The list of parameters includes, but is not limited -to, nofsgsbase, nosmap, and nosmep. 5-level paging can also be disabled using -"no5lvl". SMAP and SMEP are disabled with the aforementioned parameters, -respectively. +to, nofsgsbase, nosgx, noxsave, etc. 5-level paging can also be disabled using +"no5lvl". e: The feature was known to be non-functional. ---------------------------------------------- diff --git a/Documentation/x86/index.rst b/Documentation/x86/index.rst index 91b2fa456618..51982dee6c2a 100644 --- a/Documentation/x86/index.rst +++ b/Documentation/x86/index.rst @@ -26,6 +26,7 @@ x86-specific Documentation intel_txt amd-memory-encryption amd_hsmp + tdx pti mds microcode diff --git a/Documentation/x86/tdx.rst b/Documentation/x86/tdx.rst new file mode 100644 index 000000000000..b8fa4329e1a5 --- /dev/null +++ b/Documentation/x86/tdx.rst @@ -0,0 +1,218 @@ +.. SPDX-License-Identifier: GPL-2.0 + +===================================== +Intel Trust Domain Extensions (TDX) +===================================== + +Intel's Trust Domain Extensions (TDX) protect confidential guest VMs from +the host and physical attacks by isolating the guest register state and by +encrypting the guest memory. In TDX, a special module running in a special +mode sits between the host and the guest and manages the guest/host +separation. + +Since the host cannot directly access guest registers or memory, much +normal functionality of a hypervisor must be moved into the guest. This is +implemented using a Virtualization Exception (#VE) that is handled by the +guest kernel. A #VE is handled entirely inside the guest kernel, but some +require the hypervisor to be consulted. + +TDX includes new hypercall-like mechanisms for communicating from the +guest to the hypervisor or the TDX module. + +New TDX Exceptions +================== + +TDX guests behave differently from bare-metal and traditional VMX guests. +In TDX guests, otherwise normal instructions or memory accesses can cause +#VE or #GP exceptions. + +Instructions marked with an '*' conditionally cause exceptions. The +details for these instructions are discussed below. + +Instruction-based #VE +--------------------- + +- Port I/O (INS, OUTS, IN, OUT) +- HLT +- MONITOR, MWAIT +- WBINVD, INVD +- VMCALL +- RDMSR*,WRMSR* +- CPUID* + +Instruction-based #GP +--------------------- + +- All VMX instructions: INVEPT, INVVPID, VMCLEAR, VMFUNC, VMLAUNCH, + VMPTRLD, VMPTRST, VMREAD, VMRESUME, VMWRITE, VMXOFF, VMXON +- ENCLS, ENCLU +- GETSEC +- RSM +- ENQCMD +- RDMSR*,WRMSR* + +RDMSR/WRMSR Behavior +-------------------- + +MSR access behavior falls into three categories: + +- #GP generated +- #VE generated +- "Just works" + +In general, the #GP MSRs should not be used in guests. Their use likely +indicates a bug in the guest. The guest may try to handle the #GP with a +hypercall but it is unlikely to succeed. + +The #VE MSRs are typically able to be handled by the hypervisor. Guests +can make a hypercall to the hypervisor to handle the #VE. + +The "just works" MSRs do not need any special guest handling. They might +be implemented by directly passing through the MSR to the hardware or by +trapping and handling in the TDX module. Other than possibly being slow, +these MSRs appear to function just as they would on bare metal. + +CPUID Behavior +-------------- + +For some CPUID leaves and sub-leaves, the virtualized bit fields of CPUID +return values (in guest EAX/EBX/ECX/EDX) are configurable by the +hypervisor. For such cases, the Intel TDX module architecture defines two +virtualization types: + +- Bit fields for which the hypervisor controls the value seen by the guest + TD. + +- Bit fields for which the hypervisor configures the value such that the + guest TD either sees their native value or a value of 0. For these bit + fields, the hypervisor can mask off the native values, but it can not + turn *on* values. + +A #VE is generated for CPUID leaves and sub-leaves that the TDX module does +not know how to handle. The guest kernel may ask the hypervisor for the +value with a hypercall. + +#VE on Memory Accesses +====================== + +There are essentially two classes of TDX memory: private and shared. +Private memory receives full TDX protections. Its content is protected +against access from the hypervisor. Shared memory is expected to be +shared between guest and hypervisor and does not receive full TDX +protections. + +A TD guest is in control of whether its memory accesses are treated as +private or shared. It selects the behavior with a bit in its page table +entries. This helps ensure that a guest does not place sensitive +information in shared memory, exposing it to the untrusted hypervisor. + +#VE on Shared Memory +-------------------- + +Access to shared mappings can cause a #VE. The hypervisor ultimately +controls whether a shared memory access causes a #VE, so the guest must be +careful to only reference shared pages it can safely handle a #VE. For +instance, the guest should be careful not to access shared memory in the +#VE handler before it reads the #VE info structure (TDG.VP.VEINFO.GET). + +Shared mapping content is entirely controlled by the hypervisor. The guest +should only use shared mappings for communicating with the hypervisor. +Shared mappings must never be used for sensitive memory content like kernel +stacks. A good rule of thumb is that hypervisor-shared memory should be +treated the same as memory mapped to userspace. Both the hypervisor and +userspace are completely untrusted. + +MMIO for virtual devices is implemented as shared memory. The guest must +be careful not to access device MMIO regions unless it is also prepared to +handle a #VE. + +#VE on Private Pages +-------------------- + +An access to private mappings can also cause a #VE. Since all kernel +memory is also private memory, the kernel might theoretically need to +handle a #VE on arbitrary kernel memory accesses. This is not feasible, so +TDX guests ensure that all guest memory has been "accepted" before memory +is used by the kernel. + +A modest amount of memory (typically 512M) is pre-accepted by the firmware +before the kernel runs to ensure that the kernel can start up without +being subjected to a #VE. + +The hypervisor is permitted to unilaterally move accepted pages to a +"blocked" state. However, if it does this, page access will not generate a +#VE. It will, instead, cause a "TD Exit" where the hypervisor is required +to handle the exception. + +Linux #VE handler +================= + +Just like page faults or #GP's, #VE exceptions can be either handled or be +fatal. Typically, an unhandled userspace #VE results in a SIGSEGV. +An unhandled kernel #VE results in an oops. + +Handling nested exceptions on x86 is typically nasty business. A #VE +could be interrupted by an NMI which triggers another #VE and hilarity +ensues. The TDX #VE architecture anticipated this scenario and includes a +feature to make it slightly less nasty. + +During #VE handling, the TDX module ensures that all interrupts (including +NMIs) are blocked. The block remains in place until the guest makes a +TDG.VP.VEINFO.GET TDCALL. This allows the guest to control when interrupts +or a new #VE can be delivered. + +However, the guest kernel must still be careful to avoid potential +#VE-triggering actions (discussed above) while this block is in place. +While the block is in place, any #VE is elevated to a double fault (#DF) +which is not recoverable. + +MMIO handling +============= + +In non-TDX VMs, MMIO is usually implemented by giving a guest access to a +mapping which will cause a VMEXIT on access, and then the hypervisor +emulates the access. That is not possible in TDX guests because VMEXIT +will expose the register state to the host. TDX guests don't trust the host +and can't have their state exposed to the host. + +In TDX, MMIO regions typically trigger a #VE exception in the guest. The +guest #VE handler then emulates the MMIO instruction inside the guest and +converts it into a controlled TDCALL to the host, rather than exposing +guest state to the host. + +MMIO addresses on x86 are just special physical addresses. They can +theoretically be accessed with any instruction that accesses memory. +However, the kernel instruction decoding method is limited. It is only +designed to decode instructions like those generated by io.h macros. + +MMIO access via other means (like structure overlays) may result in an +oops. + +Shared Memory Conversions +========================= + +All TDX guest memory starts out as private at boot. This memory can not +be accessed by the hypervisor. However, some kernel users like device +drivers might have a need to share data with the hypervisor. To do this, +memory must be converted between shared and private. This can be +accomplished using some existing memory encryption helpers: + + * set_memory_decrypted() converts a range of pages to shared. + * set_memory_encrypted() converts memory back to private. + +Device drivers are the primary user of shared memory, but there's no need +to touch every driver. DMA buffers and ioremap() do the conversions +automatically. + +TDX uses SWIOTLB for most DMA allocations. The SWIOTLB buffer is +converted to shared on boot. + +For coherent DMA allocation, the DMA buffer gets converted on the +allocation. Check force_dma_unencrypted() for details. + +References +========== + +TDX reference material is collected here: + +https://www.intel.com/content/www/us/en/developer/articles/technical/intel-trust-domain-extensions.html diff --git a/Documentation/x86/x86_64/boot-options.rst b/Documentation/x86/x86_64/boot-options.rst index 07aa0007f346..03ec9cf01181 100644 --- a/Documentation/x86/x86_64/boot-options.rst +++ b/Documentation/x86/x86_64/boot-options.rst @@ -157,15 +157,6 @@ Rebooting newer BIOS, or newer board) using this option will ignore the built-in quirk table, and use the generic default reboot actions. -Non Executable Mappings -======================= - - noexec=on|off - on - Enable(default) - off - Disable - NUMA ==== @@ -310,3 +301,17 @@ Miscellaneous Do not use GB pages for kernel direct mappings. gbpages Use GB pages for kernel direct mappings. + + +AMD SEV (Secure Encrypted Virtualization) +========================================= +Options relating to AMD SEV, specified via the following format: + +:: + + sev=option1[,option2] + +The available options are: + + debug + Enable debug messages. diff --git a/Documentation/x86/zero-page.rst b/Documentation/x86/zero-page.rst index f088f5881666..45aa9cceb4f1 100644 --- a/Documentation/x86/zero-page.rst +++ b/Documentation/x86/zero-page.rst @@ -19,6 +19,7 @@ Offset/Size Proto Name Meaning 058/008 ALL tboot_addr Physical address of tboot shared page 060/010 ALL ist_info Intel SpeedStep (IST) BIOS support information (struct ist_info) +070/008 ALL acpi_rsdp_addr Physical address of ACPI RSDP table 080/010 ALL hd0_info hd0 disk parameter, OBSOLETE!! 090/010 ALL hd1_info hd1 disk parameter, OBSOLETE!! 0A0/010 ALL sys_desc_table System description table (struct sys_desc_table), @@ -27,6 +28,7 @@ Offset/Size Proto Name Meaning 0C0/004 ALL ext_ramdisk_image ramdisk_image high 32bits 0C4/004 ALL ext_ramdisk_size ramdisk_size high 32bits 0C8/004 ALL ext_cmd_line_ptr cmd_line_ptr high 32bits +13C/004 ALL cc_blob_address Physical address of Confidential Computing blob 140/080 ALL edid_info Video mode setup (struct edid_info) 1C0/020 ALL efi_info EFI 32 information (struct efi_info) 1E0/004 ALL alt_mem_k Alternative mem check, in KB diff --git a/MAINTAINERS b/MAINTAINERS index e8c52d0192a6..496f5e281776 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -3571,8 +3571,9 @@ M: Andy Gospodarek <andy@greyhouse.net> L: netdev@vger.kernel.org S: Supported W: http://sourceforge.net/projects/bonding/ +F: Documentation/networking/bonding.rst F: drivers/net/bonding/ -F: include/net/bonding.h +F: include/net/bond* F: include/uapi/linux/if_bonding.h BOSCH SENSORTEC BMA400 ACCELEROMETER IIO DRIVER @@ -5439,6 +5440,7 @@ F: net/ax25/sysctl_net_ax25.c DATA ACCESS MONITOR M: SeongJae Park <sj@kernel.org> +L: damon@lists.linux.dev L: linux-mm@kvack.org S: Maintained F: Documentation/ABI/testing/sysfs-kernel-mm-damon @@ -7383,7 +7385,6 @@ L: linux-mm@kvack.org S: Supported T: git git://git.kernel.org/pub/scm/linux/kernel/git/kees/linux.git for-next/execve F: arch/alpha/kernel/binfmt_loader.c -F: arch/x86/ia32/ia32_aout.c F: fs/*binfmt_*.c F: fs/exec.c F: include/linux/binfmts.h @@ -10131,7 +10132,7 @@ S: Supported F: drivers/net/wireless/intel/iwlegacy/ INTEL WIRELESS WIFI LINK (iwlwifi) -M: Luca Coelho <luciano.coelho@intel.com> +M: Gregory Greenman <gregory.greenman@intel.com> L: linux-wireless@vger.kernel.org S: Supported W: https://wireless.wiki.kernel.org/en/users/drivers/iwlwifi @@ -14372,7 +14373,6 @@ F: arch/arm/*omap*/*pm* F: drivers/cpufreq/omap-cpufreq.c OMAP POWERDOMAIN SOC ADAPTATION LAYER SUPPORT -M: Rajendra Nayak <rnayak@codeaurora.org> M: Paul Walmsley <paul@pwsan.com> L: linux-omap@vger.kernel.org S: Maintained @@ -15475,7 +15475,8 @@ F: tools/perf/ PERFORMANCE EVENTS TOOLING ARM64 R: John Garry <john.garry@huawei.com> R: Will Deacon <will@kernel.org> -R: Mathieu Poirier <mathieu.poirier@linaro.org> +R: James Clark <james.clark@arm.com> +R: Mike Leach <mike.leach@linaro.org> R: Leo Yan <leo.yan@linaro.org> L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) S: Supported @@ -2,7 +2,7 @@ VERSION = 5 PATCHLEVEL = 18 SUBLEVEL = 0 -EXTRAVERSION = -rc6 +EXTRAVERSION = NAME = Superb Owl # *DOCUMENTATION* diff --git a/arch/Kconfig b/arch/Kconfig index 31c4fdc4a4ba..513a29c62a9b 100644 --- a/arch/Kconfig +++ b/arch/Kconfig @@ -35,6 +35,7 @@ config KPROBES depends on MODULES depends on HAVE_KPROBES select KALLSYMS + select TASKS_RCU if PREEMPTION help Kprobes allows you to trap at almost any kernel address and execute a callback function. register_kprobe() establishes diff --git a/arch/arm/boot/dts/aspeed-bmc-asrock-romed8hm3.dts b/arch/arm/boot/dts/aspeed-bmc-asrock-romed8hm3.dts index e71ccfd1df63..ff4c07c69af1 100644 --- a/arch/arm/boot/dts/aspeed-bmc-asrock-romed8hm3.dts +++ b/arch/arm/boot/dts/aspeed-bmc-asrock-romed8hm3.dts @@ -100,12 +100,14 @@ lm25066@40 { compatible = "lm25066"; reg = <0x40>; + shunt-resistor-micro-ohms = <1000>; }; /* 12VSB PMIC */ lm25066@41 { compatible = "lm25066"; reg = <0x41>; + shunt-resistor-micro-ohms = <10000>; }; }; @@ -196,7 +198,7 @@ gpio-line-names = /* A */ "LOCATORLED_STATUS_N", "BMC_MAC2_INTB", "NMI_BTN_N", "BMC_NMI", "", "", "", "", - /* B */ "DDR_MEM_TEMP", "", "", "", "", "", "", "", + /* B */ "POST_COMPLETE_N", "", "", "", "", "", "", "", /* C */ "", "", "", "", "PCIE_HP_SEL_N", "PCIE_SATA_SEL_N", "LOCATORBTN", "", /* D */ "BMC_PSIN", "BMC_PSOUT", "BMC_RESETCON", "RESETCON", "", "", "", "PSU_FAN_FAIL_N", diff --git a/arch/arm/boot/dts/aspeed-g6-pinctrl.dtsi b/arch/arm/boot/dts/aspeed-g6-pinctrl.dtsi index e4775bbceecc..7cd4f075e325 100644 --- a/arch/arm/boot/dts/aspeed-g6-pinctrl.dtsi +++ b/arch/arm/boot/dts/aspeed-g6-pinctrl.dtsi @@ -117,9 +117,9 @@ groups = "FWSPID"; }; - pinctrl_fwqspid_default: fwqspid_default { - function = "FWSPID"; - groups = "FWQSPID"; + pinctrl_fwqspi_default: fwqspi_default { + function = "FWQSPI"; + groups = "FWQSPI"; }; pinctrl_fwspiwp_default: fwspiwp_default { @@ -653,12 +653,12 @@ }; pinctrl_qspi1_default: qspi1_default { - function = "QSPI1"; + function = "SPI1"; groups = "QSPI1"; }; pinctrl_qspi2_default: qspi2_default { - function = "QSPI2"; + function = "SPI2"; groups = "QSPI2"; }; diff --git a/arch/arm/boot/dts/aspeed-g6.dtsi b/arch/arm/boot/dts/aspeed-g6.dtsi index 3d5ce9da42c3..9d2a0ce4ca06 100644 --- a/arch/arm/boot/dts/aspeed-g6.dtsi +++ b/arch/arm/boot/dts/aspeed-g6.dtsi @@ -389,6 +389,16 @@ reg = <0x1e6f2000 0x1000>; }; + video: video@1e700000 { + compatible = "aspeed,ast2600-video-engine"; + reg = <0x1e700000 0x1000>; + clocks = <&syscon ASPEED_CLK_GATE_VCLK>, + <&syscon ASPEED_CLK_GATE_ECLK>; + clock-names = "vclk", "eclk"; + interrupts = <GIC_SPI 7 IRQ_TYPE_LEVEL_HIGH>; + status = "disabled"; + }; + gpio0: gpio@1e780000 { #gpio-cells = <2>; gpio-controller; diff --git a/arch/arm/include/asm/arch_gicv3.h b/arch/arm/include/asm/arch_gicv3.h index 413abfb42989..f82a819eb0db 100644 --- a/arch/arm/include/asm/arch_gicv3.h +++ b/arch/arm/include/asm/arch_gicv3.h @@ -48,6 +48,7 @@ static inline u32 read_ ## a64(void) \ return read_sysreg(a32); \ } \ +CPUIF_MAP(ICC_EOIR1, ICC_EOIR1_EL1) CPUIF_MAP(ICC_PMR, ICC_PMR_EL1) CPUIF_MAP(ICC_AP0R0, ICC_AP0R0_EL1) CPUIF_MAP(ICC_AP0R1, ICC_AP0R1_EL1) @@ -63,12 +64,6 @@ CPUIF_MAP(ICC_AP1R3, ICC_AP1R3_EL1) /* Low-level accessors */ -static inline void gic_write_eoir(u32 irq) -{ - write_sysreg(irq, ICC_EOIR1); - isb(); -} - static inline void gic_write_dir(u32 val) { write_sysreg(val, ICC_DIR); diff --git a/arch/arm/include/asm/io.h b/arch/arm/include/asm/io.h index 0c70eb688a00..2a0739a2350b 100644 --- a/arch/arm/include/asm/io.h +++ b/arch/arm/include/asm/io.h @@ -440,6 +440,9 @@ extern void pci_iounmap(struct pci_dev *dev, void __iomem *addr); #define ARCH_HAS_VALID_PHYS_ADDR_RANGE extern int valid_phys_addr_range(phys_addr_t addr, size_t size); extern int valid_mmap_phys_addr_range(unsigned long pfn, size_t size); +extern bool arch_memremap_can_ram_remap(resource_size_t offset, size_t size, + unsigned long flags); +#define arch_memremap_can_ram_remap arch_memremap_can_ram_remap #endif /* diff --git a/arch/arm/kernel/entry-armv.S b/arch/arm/kernel/entry-armv.S index 06508698abb8..7a8682468a84 100644 --- a/arch/arm/kernel/entry-armv.S +++ b/arch/arm/kernel/entry-armv.S @@ -1145,7 +1145,7 @@ vector_bhb_loop8_\name: @ bhb workaround mov r0, #8 -3: b . + 4 +3: W(b) . + 4 subs r0, r0, #1 bne 3b dsb diff --git a/arch/arm/mach-sunxi/Kconfig b/arch/arm/mach-sunxi/Kconfig index e5c2fce281cd..abdb99fe1e97 100644 --- a/arch/arm/mach-sunxi/Kconfig +++ b/arch/arm/mach-sunxi/Kconfig @@ -4,10 +4,7 @@ menuconfig ARCH_SUNXI depends on ARCH_MULTI_V5 || ARCH_MULTI_V7 select ARCH_HAS_RESET_CONTROLLER select CLKSRC_MMIO - select GENERIC_IRQ_CHIP select GPIOLIB - select IRQ_DOMAIN_HIERARCHY - select IRQ_FASTEOI_HIERARCHY_HANDLERS select PINCTRL select PM_OPP select SUN4I_TIMER @@ -22,10 +19,12 @@ if ARCH_MULTI_V7 config MACH_SUN4I bool "Allwinner A10 (sun4i) SoCs support" default ARCH_SUNXI + select SUN4I_INTC config MACH_SUN5I bool "Allwinner A10s / A13 (sun5i) SoCs support" default ARCH_SUNXI + select SUN4I_INTC select SUN5I_HSTIMER config MACH_SUN6I @@ -34,6 +33,8 @@ config MACH_SUN6I select ARM_GIC select MFD_SUN6I_PRCM select SUN5I_HSTIMER + select SUN6I_R_INTC + select SUNXI_NMI_INTC config MACH_SUN7I bool "Allwinner A20 (sun7i) SoCs support" @@ -43,17 +44,21 @@ config MACH_SUN7I select ARCH_SUPPORTS_BIG_ENDIAN select HAVE_ARM_ARCH_TIMER select SUN5I_HSTIMER + select SUNXI_NMI_INTC config MACH_SUN8I bool "Allwinner sun8i Family SoCs support" default ARCH_SUNXI select ARM_GIC select MFD_SUN6I_PRCM + select SUN6I_R_INTC + select SUNXI_NMI_INTC config MACH_SUN9I bool "Allwinner (sun9i) SoCs support" default ARCH_SUNXI select ARM_GIC + select SUNXI_NMI_INTC config ARCH_SUNXI_MC_SMP bool @@ -69,6 +74,7 @@ if ARCH_MULTI_V5 config MACH_SUNIV bool "Allwinner ARMv5 F-series (suniv) SoCs support" default ARCH_SUNXI + select SUN4I_INTC help Support for Allwinner suniv ARMv5 SoCs. (F1C100A, F1C100s, F1C200s, F1C500, F1C600) diff --git a/arch/arm/mm/ioremap.c b/arch/arm/mm/ioremap.c index aa08bcb72db9..290702328a33 100644 --- a/arch/arm/mm/ioremap.c +++ b/arch/arm/mm/ioremap.c @@ -493,3 +493,11 @@ void __init early_ioremap_init(void) { early_ioremap_setup(); } + +bool arch_memremap_can_ram_remap(resource_size_t offset, size_t size, + unsigned long flags) +{ + unsigned long pfn = PHYS_PFN(offset); + + return memblock_is_map_memory(pfn); +} diff --git a/arch/arm/mm/proc-v7-bugs.c b/arch/arm/mm/proc-v7-bugs.c index 06dbfb968182..fb9f3eb6bf48 100644 --- a/arch/arm/mm/proc-v7-bugs.c +++ b/arch/arm/mm/proc-v7-bugs.c @@ -288,6 +288,7 @@ void cpu_v7_ca15_ibe(void) { if (check_spectre_auxcr(this_cpu_ptr(&spectre_warned), BIT(0))) cpu_v7_spectre_v2_init(); + cpu_v7_spectre_bhb_init(); } void cpu_v7_bugs_init(void) diff --git a/arch/arm64/Kconfig.platforms b/arch/arm64/Kconfig.platforms index 30b123cde02c..6a6457fed7b2 100644 --- a/arch/arm64/Kconfig.platforms +++ b/arch/arm64/Kconfig.platforms @@ -11,12 +11,11 @@ config ARCH_ACTIONS config ARCH_SUNXI bool "Allwinner sunxi 64-bit SoC Family" select ARCH_HAS_RESET_CONTROLLER - select GENERIC_IRQ_CHIP - select IRQ_DOMAIN_HIERARCHY - select IRQ_FASTEOI_HIERARCHY_HANDLERS select PINCTRL select RESET_CONTROLLER select SUN4I_TIMER + select SUN6I_R_INTC + select SUNXI_NMI_INTC help This enables support for Allwinner sunxi based SoCs like the A64. @@ -253,6 +252,7 @@ config ARCH_INTEL_SOCFPGA config ARCH_SYNQUACER bool "Socionext SynQuacer SoC Family" + select IRQ_FASTEOI_HIERARCHY_HANDLERS config ARCH_TEGRA bool "NVIDIA Tegra SoC Family" diff --git a/arch/arm64/boot/dts/qcom/sm8250-mtp.dts b/arch/arm64/boot/dts/qcom/sm8250-mtp.dts index fb99cc2827c7..7ab3627cc347 100644 --- a/arch/arm64/boot/dts/qcom/sm8250-mtp.dts +++ b/arch/arm64/boot/dts/qcom/sm8250-mtp.dts @@ -622,6 +622,10 @@ status = "okay"; }; +&rxmacro { + status = "okay"; +}; + &slpi { status = "okay"; firmware-name = "qcom/sm8250/slpi.mbn"; @@ -773,6 +777,8 @@ }; &swr1 { + status = "okay"; + wcd_rx: wcd9380-rx@0,4 { compatible = "sdw20217010d00"; reg = <0 4>; @@ -781,6 +787,8 @@ }; &swr2 { + status = "okay"; + wcd_tx: wcd9380-tx@0,3 { compatible = "sdw20217010d00"; reg = <0 3>; @@ -819,6 +827,10 @@ }; }; +&txmacro { + status = "okay"; +}; + &uart12 { status = "okay"; }; diff --git a/arch/arm64/boot/dts/qcom/sm8250.dtsi b/arch/arm64/boot/dts/qcom/sm8250.dtsi index af8f22636436..1304b86af1a0 100644 --- a/arch/arm64/boot/dts/qcom/sm8250.dtsi +++ b/arch/arm64/boot/dts/qcom/sm8250.dtsi @@ -2255,6 +2255,7 @@ pinctrl-0 = <&rx_swr_active>; compatible = "qcom,sm8250-lpass-rx-macro"; reg = <0 0x3200000 0 0x1000>; + status = "disabled"; clocks = <&q6afecc LPASS_CLK_ID_TX_CORE_MCLK LPASS_CLK_ATTRIBUTE_COUPLE_NO>, <&q6afecc LPASS_CLK_ID_TX_CORE_NPL_MCLK LPASS_CLK_ATTRIBUTE_COUPLE_NO>, @@ -2273,6 +2274,7 @@ swr1: soundwire-controller@3210000 { reg = <0 0x3210000 0 0x2000>; compatible = "qcom,soundwire-v1.5.1"; + status = "disabled"; interrupts = <GIC_SPI 298 IRQ_TYPE_LEVEL_HIGH>; clocks = <&rxmacro>; clock-names = "iface"; @@ -2300,6 +2302,7 @@ pinctrl-0 = <&tx_swr_active>; compatible = "qcom,sm8250-lpass-tx-macro"; reg = <0 0x3220000 0 0x1000>; + status = "disabled"; clocks = <&q6afecc LPASS_CLK_ID_TX_CORE_MCLK LPASS_CLK_ATTRIBUTE_COUPLE_NO>, <&q6afecc LPASS_CLK_ID_TX_CORE_NPL_MCLK LPASS_CLK_ATTRIBUTE_COUPLE_NO>, @@ -2323,6 +2326,7 @@ compatible = "qcom,soundwire-v1.5.1"; interrupts-extended = <&intc GIC_SPI 297 IRQ_TYPE_LEVEL_HIGH>; interrupt-names = "core"; + status = "disabled"; clocks = <&txmacro>; clock-names = "iface"; diff --git a/arch/arm64/boot/dts/rockchip/rk3568-bpi-r2-pro.dts b/arch/arm64/boot/dts/rockchip/rk3568-bpi-r2-pro.dts index a01886b467ed..067fe4a6b178 100644 --- a/arch/arm64/boot/dts/rockchip/rk3568-bpi-r2-pro.dts +++ b/arch/arm64/boot/dts/rockchip/rk3568-bpi-r2-pro.dts @@ -16,6 +16,7 @@ aliases { ethernet0 = &gmac0; + ethernet1 = &gmac1; mmc0 = &sdmmc0; mmc1 = &sdhci; }; @@ -78,7 +79,6 @@ assigned-clocks = <&cru SCLK_GMAC0_RX_TX>, <&cru SCLK_GMAC0>; assigned-clock-parents = <&cru SCLK_GMAC0_RGMII_SPEED>, <&cru CLK_MAC0_2TOP>; clock_in_out = "input"; - phy-handle = <&rgmii_phy0>; phy-mode = "rgmii"; pinctrl-names = "default"; pinctrl-0 = <&gmac0_miim @@ -90,8 +90,38 @@ snps,reset-active-low; /* Reset time is 20ms, 100ms for rtl8211f */ snps,reset-delays-us = <0 20000 100000>; + tx_delay = <0x4f>; + rx_delay = <0x0f>; + status = "okay"; + + fixed-link { + speed = <1000>; + full-duplex; + pause; + }; +}; + +&gmac1 { + assigned-clocks = <&cru SCLK_GMAC1_RX_TX>, <&cru SCLK_GMAC1>; + assigned-clock-parents = <&cru SCLK_GMAC1_RGMII_SPEED>, <&cru CLK_MAC1_2TOP>; + clock_in_out = "output"; + phy-handle = <&rgmii_phy1>; + phy-mode = "rgmii"; + pinctrl-names = "default"; + pinctrl-0 = <&gmac1m1_miim + &gmac1m1_tx_bus2 + &gmac1m1_rx_bus2 + &gmac1m1_rgmii_clk + &gmac1m1_rgmii_bus>; + + snps,reset-gpio = <&gpio3 RK_PB0 GPIO_ACTIVE_LOW>; + snps,reset-active-low; + /* Reset time is 20ms, 100ms for rtl8211f */ + snps,reset-delays-us = <0 20000 100000>; + tx_delay = <0x3c>; rx_delay = <0x2f>; + status = "okay"; }; @@ -315,8 +345,8 @@ status = "disabled"; }; -&mdio0 { - rgmii_phy0: ethernet-phy@0 { +&mdio1 { + rgmii_phy1: ethernet-phy@0 { compatible = "ethernet-phy-ieee802.3-c22"; reg = <0x0>; }; @@ -345,9 +375,9 @@ pmuio2-supply = <&vcc3v3_pmu>; vccio1-supply = <&vccio_acodec>; vccio3-supply = <&vccio_sd>; - vccio4-supply = <&vcc_1v8>; + vccio4-supply = <&vcc_3v3>; vccio5-supply = <&vcc_3v3>; - vccio6-supply = <&vcc_3v3>; + vccio6-supply = <&vcc_1v8>; vccio7-supply = <&vcc_3v3>; status = "okay"; }; diff --git a/arch/arm64/include/asm/arch_gicv3.h b/arch/arm64/include/asm/arch_gicv3.h index 8bd5afc7b692..48d4473e8eee 100644 --- a/arch/arm64/include/asm/arch_gicv3.h +++ b/arch/arm64/include/asm/arch_gicv3.h @@ -26,12 +26,6 @@ * sets the GP register's most significant bits to 0 with an explicit cast. */ -static inline void gic_write_eoir(u32 irq) -{ - write_sysreg_s(irq, SYS_ICC_EOIR1_EL1); - isb(); -} - static __always_inline void gic_write_dir(u32 irq) { write_sysreg_s(irq, SYS_ICC_DIR_EL1); diff --git a/arch/arm64/include/asm/asm-bug.h b/arch/arm64/include/asm/asm-bug.h index 03f52f84a4f3..c762038ba400 100644 --- a/arch/arm64/include/asm/asm-bug.h +++ b/arch/arm64/include/asm/asm-bug.h @@ -14,7 +14,7 @@ 14472: .string file; \ .popsection; \ \ - .long 14472b - 14470b; \ + .long 14472b - .; \ .short line; #else #define _BUGVERBOSE_LOCATION(file, line) @@ -25,7 +25,7 @@ #define __BUG_ENTRY(flags) \ .pushsection __bug_table,"aw"; \ .align 2; \ - 14470: .long 14471f - 14470b; \ + 14470: .long 14471f - .; \ _BUGVERBOSE_LOCATION(__FILE__, __LINE__) \ .short flags; \ .popsection; \ diff --git a/arch/arm64/include/asm/io.h b/arch/arm64/include/asm/io.h index 7fd836bea7eb..3995652daf81 100644 --- a/arch/arm64/include/asm/io.h +++ b/arch/arm64/include/asm/io.h @@ -192,4 +192,8 @@ extern void __iomem *ioremap_cache(phys_addr_t phys_addr, size_t size); extern int valid_phys_addr_range(phys_addr_t addr, size_t size); extern int valid_mmap_phys_addr_range(unsigned long pfn, size_t size); +extern bool arch_memremap_can_ram_remap(resource_size_t offset, size_t size, + unsigned long flags); +#define arch_memremap_can_ram_remap arch_memremap_can_ram_remap + #endif /* __ASM_IO_H */ diff --git a/arch/arm64/kernel/Makefile b/arch/arm64/kernel/Makefile index 986837d7ec82..fa7981d0d917 100644 --- a/arch/arm64/kernel/Makefile +++ b/arch/arm64/kernel/Makefile @@ -75,6 +75,10 @@ obj-$(CONFIG_ARM64_MTE) += mte.o obj-y += vdso-wrap.o obj-$(CONFIG_COMPAT_VDSO) += vdso32-wrap.o +# Force dependency (vdso*-wrap.S includes vdso.so through incbin) +$(obj)/vdso-wrap.o: $(obj)/vdso/vdso.so +$(obj)/vdso32-wrap.o: $(obj)/vdso32/vdso.so + obj-y += probes/ head-y := head.o extra-y += $(head-y) vmlinux.lds diff --git a/arch/arm64/kernel/cpu_errata.c b/arch/arm64/kernel/cpu_errata.c index 4c9b5b4b7a0b..a0f3d0aaa3c5 100644 --- a/arch/arm64/kernel/cpu_errata.c +++ b/arch/arm64/kernel/cpu_errata.c @@ -208,6 +208,8 @@ static const struct arm64_cpu_capabilities arm64_repeat_tlbi_list[] = { #ifdef CONFIG_ARM64_ERRATUM_1286807 { ERRATA_MIDR_RANGE(MIDR_CORTEX_A76, 0, 0, 3, 0), + /* Kryo4xx Gold (rcpe to rfpe) => (r0p0 to r3p0) */ + ERRATA_MIDR_RANGE(MIDR_QCOM_KRYO_4XX_GOLD, 0xc, 0xe, 0xf, 0xe), }, #endif {}, diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c index d72c4b4d389c..2cb9cc9e0eff 100644 --- a/arch/arm64/kernel/cpufeature.c +++ b/arch/arm64/kernel/cpufeature.c @@ -654,7 +654,6 @@ static const struct __ftr_reg_entry { ARM64_FTR_REG(SYS_ID_AA64ISAR0_EL1, ftr_id_aa64isar0), ARM64_FTR_REG_OVERRIDE(SYS_ID_AA64ISAR1_EL1, ftr_id_aa64isar1, &id_aa64isar1_override), - ARM64_FTR_REG(SYS_ID_AA64ISAR2_EL1, ftr_id_aa64isar2), ARM64_FTR_REG_OVERRIDE(SYS_ID_AA64ISAR2_EL1, ftr_id_aa64isar2, &id_aa64isar2_override), @@ -810,7 +809,7 @@ static void __init sort_ftr_regs(void) * to sys_id for subsequent binary search in get_arm64_ftr_reg() * to work correctly. */ - BUG_ON(arm64_ftr_regs[i].sys_id < arm64_ftr_regs[i - 1].sys_id); + BUG_ON(arm64_ftr_regs[i].sys_id <= arm64_ftr_regs[i - 1].sys_id); } } diff --git a/arch/arm64/kernel/mte.c b/arch/arm64/kernel/mte.c index 78b3e0f8e997..d502703e8373 100644 --- a/arch/arm64/kernel/mte.c +++ b/arch/arm64/kernel/mte.c @@ -76,6 +76,9 @@ void mte_sync_tags(pte_t old_pte, pte_t pte) mte_sync_page_tags(page, old_pte, check_swap, pte_is_tagged); } + + /* ensure the tags are visible before the PTE is set */ + smp_wmb(); } int memcmp_pages(struct page *page1, struct page *page2) diff --git a/arch/arm64/kernel/paravirt.c b/arch/arm64/kernel/paravirt.c index 75fed4460407..57c7c211f8c7 100644 --- a/arch/arm64/kernel/paravirt.c +++ b/arch/arm64/kernel/paravirt.c @@ -35,7 +35,7 @@ static u64 native_steal_clock(int cpu) DEFINE_STATIC_CALL(pv_steal_clock, native_steal_clock); struct pv_time_stolen_time_region { - struct pvclock_vcpu_stolen_time *kaddr; + struct pvclock_vcpu_stolen_time __rcu *kaddr; }; static DEFINE_PER_CPU(struct pv_time_stolen_time_region, stolen_time_region); @@ -52,7 +52,9 @@ early_param("no-steal-acc", parse_no_stealacc); /* return stolen time in ns by asking the hypervisor */ static u64 para_steal_clock(int cpu) { + struct pvclock_vcpu_stolen_time *kaddr = NULL; struct pv_time_stolen_time_region *reg; + u64 ret = 0; reg = per_cpu_ptr(&stolen_time_region, cpu); @@ -61,28 +63,37 @@ static u64 para_steal_clock(int cpu) * online notification callback runs. Until the callback * has run we just return zero. */ - if (!reg->kaddr) + rcu_read_lock(); + kaddr = rcu_dereference(reg->kaddr); + if (!kaddr) { + rcu_read_unlock(); return 0; + } - return le64_to_cpu(READ_ONCE(reg->kaddr->stolen_time)); + ret = le64_to_cpu(READ_ONCE(kaddr->stolen_time)); + rcu_read_unlock(); + return ret; } static int stolen_time_cpu_down_prepare(unsigned int cpu) { + struct pvclock_vcpu_stolen_time *kaddr = NULL; struct pv_time_stolen_time_region *reg; reg = this_cpu_ptr(&stolen_time_region); if (!reg->kaddr) return 0; - memunmap(reg->kaddr); - memset(reg, 0, sizeof(*reg)); + kaddr = rcu_replace_pointer(reg->kaddr, NULL, true); + synchronize_rcu(); + memunmap(kaddr); return 0; } static int stolen_time_cpu_online(unsigned int cpu) { + struct pvclock_vcpu_stolen_time *kaddr = NULL; struct pv_time_stolen_time_region *reg; struct arm_smccc_res res; @@ -93,17 +104,19 @@ static int stolen_time_cpu_online(unsigned int cpu) if (res.a0 == SMCCC_RET_NOT_SUPPORTED) return -EINVAL; - reg->kaddr = memremap(res.a0, + kaddr = memremap(res.a0, sizeof(struct pvclock_vcpu_stolen_time), MEMREMAP_WB); + rcu_assign_pointer(reg->kaddr, kaddr); + if (!reg->kaddr) { pr_warn("Failed to map stolen time data structure\n"); return -ENOMEM; } - if (le32_to_cpu(reg->kaddr->revision) != 0 || - le32_to_cpu(reg->kaddr->attributes) != 0) { + if (le32_to_cpu(kaddr->revision) != 0 || + le32_to_cpu(kaddr->attributes) != 0) { pr_warn_once("Unexpected revision or attributes in stolen time data\n"); return -ENXIO; } diff --git a/arch/arm64/kernel/relocate_kernel.S b/arch/arm64/kernel/relocate_kernel.S index f0a3df9e18a3..413f899e4ac6 100644 --- a/arch/arm64/kernel/relocate_kernel.S +++ b/arch/arm64/kernel/relocate_kernel.S @@ -37,6 +37,15 @@ * safe memory that has been set up to be preserved during the copy operation. */ SYM_CODE_START(arm64_relocate_new_kernel) + /* + * The kimage structure isn't allocated specially and may be clobbered + * during relocation. We must load any values we need from it prior to + * any relocation occurring. + */ + ldr x28, [x0, #KIMAGE_START] + ldr x27, [x0, #KIMAGE_ARCH_EL2_VECTORS] + ldr x26, [x0, #KIMAGE_ARCH_DTB_MEM] + /* Setup the list loop variables. */ ldr x18, [x0, #KIMAGE_ARCH_ZERO_PAGE] /* x18 = zero page for BBM */ ldr x17, [x0, #KIMAGE_ARCH_TTBR1] /* x17 = linear map copy */ @@ -72,21 +81,20 @@ SYM_CODE_START(arm64_relocate_new_kernel) ic iallu dsb nsh isb - ldr x4, [x0, #KIMAGE_START] /* relocation start */ - ldr x1, [x0, #KIMAGE_ARCH_EL2_VECTORS] /* relocation start */ - ldr x0, [x0, #KIMAGE_ARCH_DTB_MEM] /* dtb address */ turn_off_mmu x12, x13 /* Start new image. */ - cbz x1, .Lel1 - mov x1, x4 /* relocation start */ - mov x2, x0 /* dtb address */ + cbz x27, .Lel1 + mov x1, x28 /* kernel entry point */ + mov x2, x26 /* dtb address */ mov x3, xzr mov x4, xzr mov x0, #HVC_SOFT_RESTART hvc #0 /* Jumps from el2 */ .Lel1: + mov x0, x26 /* dtb address */ + mov x1, xzr mov x2, xzr mov x3, xzr - br x4 /* Jumps from el1 */ + br x28 /* Jumps from el1 */ SYM_CODE_END(arm64_relocate_new_kernel) diff --git a/arch/arm64/kernel/vdso/Makefile b/arch/arm64/kernel/vdso/Makefile index 172452f79e46..ac1964ebed1e 100644 --- a/arch/arm64/kernel/vdso/Makefile +++ b/arch/arm64/kernel/vdso/Makefile @@ -52,9 +52,6 @@ GCOV_PROFILE := n targets += vdso.lds CPPFLAGS_vdso.lds += -P -C -U$(ARCH) -# Force dependency (incbin is bad) -$(obj)/vdso.o : $(obj)/vdso.so - # Link rule for the .so file, .lds has to be first $(obj)/vdso.so.dbg: $(obj)/vdso.lds $(obj-vdso) FORCE $(call if_changed,vdsold_and_vdso_check) diff --git a/arch/arm64/kernel/vdso32/Makefile b/arch/arm64/kernel/vdso32/Makefile index ed181bedbffc..05ba1aae1b6f 100644 --- a/arch/arm64/kernel/vdso32/Makefile +++ b/arch/arm64/kernel/vdso32/Makefile @@ -131,9 +131,6 @@ obj-vdso := $(c-obj-vdso) $(c-obj-vdso-gettimeofday) $(asm-obj-vdso) targets += vdso.lds CPPFLAGS_vdso.lds += -P -C -U$(ARCH) -# Force dependency (vdso.s includes vdso.so through incbin) -$(obj)/vdso.o: $(obj)/vdso.so - include/generated/vdso32-offsets.h: $(obj)/vdso.so.dbg FORCE $(call if_changed,vdsosym) diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c index 523bc934fe2f..a66d83540c15 100644 --- a/arch/arm64/kvm/arm.c +++ b/arch/arm64/kvm/arm.c @@ -1436,7 +1436,8 @@ static int kvm_init_vector_slots(void) base = kern_hyp_va(kvm_ksym_ref(__bp_harden_hyp_vecs)); kvm_init_vector_slot(base, HYP_VECTOR_SPECTRE_DIRECT); - if (kvm_system_needs_idmapped_vectors() && !has_vhe()) { + if (kvm_system_needs_idmapped_vectors() && + !is_protected_kvm_enabled()) { err = create_hyp_exec_mappings(__pa_symbol(__bp_harden_hyp_vecs), __BP_HARDEN_HYP_VECS_SZ, &base); if (err) diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c index 7b45c040cc27..adf408c09cdb 100644 --- a/arch/arm64/kvm/sys_regs.c +++ b/arch/arm64/kvm/sys_regs.c @@ -1123,8 +1123,7 @@ static u64 read_id_reg(const struct kvm_vcpu *vcpu, val |= FIELD_PREP(ARM64_FEATURE_MASK(ID_AA64PFR0_CSV2), (u64)vcpu->kvm->arch.pfr0_csv2); val &= ~ARM64_FEATURE_MASK(ID_AA64PFR0_CSV3); val |= FIELD_PREP(ARM64_FEATURE_MASK(ID_AA64PFR0_CSV3), (u64)vcpu->kvm->arch.pfr0_csv3); - if (irqchip_in_kernel(vcpu->kvm) && - vcpu->kvm->arch.vgic.vgic_model == KVM_DEV_TYPE_ARM_VGIC_V3) { + if (kvm_vgic_global_state.type == VGIC_V3) { val &= ~ARM64_FEATURE_MASK(ID_AA64PFR0_GIC); val |= FIELD_PREP(ARM64_FEATURE_MASK(ID_AA64PFR0_GIC), 1); } diff --git a/arch/arm64/mm/ioremap.c b/arch/arm64/mm/ioremap.c index b7c81dacabf0..b21f91cd830d 100644 --- a/arch/arm64/mm/ioremap.c +++ b/arch/arm64/mm/ioremap.c @@ -99,3 +99,11 @@ void __init early_ioremap_init(void) { early_ioremap_setup(); } + +bool arch_memremap_can_ram_remap(resource_size_t offset, size_t size, + unsigned long flags) +{ + unsigned long pfn = PHYS_PFN(offset); + + return pfn_is_map_memory(pfn); +} diff --git a/arch/parisc/include/asm/cacheflush.h b/arch/parisc/include/asm/cacheflush.h index e8b4a03343d3..8d03b3b26229 100644 --- a/arch/parisc/include/asm/cacheflush.h +++ b/arch/parisc/include/asm/cacheflush.h @@ -59,20 +59,12 @@ void flush_dcache_page(struct page *page); flush_kernel_icache_range_asm(s,e); \ } while (0) -#define copy_to_user_page(vma, page, vaddr, dst, src, len) \ -do { \ - flush_cache_page(vma, vaddr, page_to_pfn(page)); \ - memcpy(dst, src, len); \ - flush_kernel_dcache_range_asm((unsigned long)dst, (unsigned long)dst + len); \ -} while (0) - -#define copy_from_user_page(vma, page, vaddr, dst, src, len) \ -do { \ - flush_cache_page(vma, vaddr, page_to_pfn(page)); \ - memcpy(dst, src, len); \ -} while (0) - -void flush_cache_page(struct vm_area_struct *vma, unsigned long vmaddr, unsigned long pfn); +void copy_to_user_page(struct vm_area_struct *vma, struct page *page, + unsigned long user_vaddr, void *dst, void *src, int len); +void copy_from_user_page(struct vm_area_struct *vma, struct page *page, + unsigned long user_vaddr, void *dst, void *src, int len); +void flush_cache_page(struct vm_area_struct *vma, unsigned long vmaddr, + unsigned long pfn); void flush_cache_range(struct vm_area_struct *vma, unsigned long start, unsigned long end); @@ -80,16 +72,7 @@ void flush_cache_range(struct vm_area_struct *vma, void flush_dcache_page_asm(unsigned long phys_addr, unsigned long vaddr); #define ARCH_HAS_FLUSH_ANON_PAGE -static inline void -flush_anon_page(struct vm_area_struct *vma, struct page *page, unsigned long vmaddr) -{ - if (PageAnon(page)) { - flush_tlb_page(vma, vmaddr); - preempt_disable(); - flush_dcache_page_asm(page_to_phys(page), vmaddr); - preempt_enable(); - } -} +void flush_anon_page(struct vm_area_struct *vma, struct page *page, unsigned long vmaddr); #define ARCH_HAS_FLUSH_ON_KUNMAP static inline void kunmap_flush_on_unmap(void *addr) diff --git a/arch/parisc/include/asm/page.h b/arch/parisc/include/asm/page.h index 0561568f7b48..6faaaa3ebe9b 100644 --- a/arch/parisc/include/asm/page.h +++ b/arch/parisc/include/asm/page.h @@ -26,12 +26,14 @@ #define copy_page(to, from) copy_page_asm((void *)(to), (void *)(from)) struct page; +struct vm_area_struct; void clear_page_asm(void *page); void copy_page_asm(void *to, void *from); #define clear_user_page(vto, vaddr, page) clear_page_asm(vto) -void copy_user_page(void *vto, void *vfrom, unsigned long vaddr, - struct page *pg); +void copy_user_highpage(struct page *to, struct page *from, unsigned long vaddr, + struct vm_area_struct *vma); +#define __HAVE_ARCH_COPY_USER_HIGHPAGE /* * These are used to make use of C type-checking.. diff --git a/arch/parisc/kernel/cache.c b/arch/parisc/kernel/cache.c index e7911225a4f8..0fd04073d4b6 100644 --- a/arch/parisc/kernel/cache.c +++ b/arch/parisc/kernel/cache.c @@ -27,6 +27,7 @@ #include <asm/processor.h> #include <asm/sections.h> #include <asm/shmparam.h> +#include <asm/mmu_context.h> int split_tlb __ro_after_init; int dcache_stride __ro_after_init; @@ -91,7 +92,7 @@ static inline void flush_data_cache(void) } -/* Virtual address of pfn. */ +/* Kernel virtual address of pfn. */ #define pfn_va(pfn) __va(PFN_PHYS(pfn)) void @@ -124,11 +125,13 @@ show_cache_info(struct seq_file *m) cache_info.ic_size/1024 ); if (cache_info.dc_loop != 1) snprintf(buf, 32, "%lu-way associative", cache_info.dc_loop); - seq_printf(m, "D-cache\t\t: %ld KB (%s%s, %s)\n", + seq_printf(m, "D-cache\t\t: %ld KB (%s%s, %s, alias=%d)\n", cache_info.dc_size/1024, (cache_info.dc_conf.cc_wt ? "WT":"WB"), (cache_info.dc_conf.cc_sh ? ", shared I/D":""), - ((cache_info.dc_loop == 1) ? "direct mapped" : buf)); + ((cache_info.dc_loop == 1) ? "direct mapped" : buf), + cache_info.dc_conf.cc_alias + ); seq_printf(m, "ITLB entries\t: %ld\n" "DTLB entries\t: %ld%s\n", cache_info.it_size, cache_info.dt_size, @@ -324,25 +327,81 @@ __flush_cache_page(struct vm_area_struct *vma, unsigned long vmaddr, preempt_enable(); } -static inline void -__purge_cache_page(struct vm_area_struct *vma, unsigned long vmaddr, - unsigned long physaddr) +static void flush_user_cache_page(struct vm_area_struct *vma, unsigned long vmaddr) { - if (!static_branch_likely(&parisc_has_cache)) - return; + unsigned long flags, space, pgd, prot; +#ifdef CONFIG_TLB_PTLOCK + unsigned long pgd_lock; +#endif + + vmaddr &= PAGE_MASK; + preempt_disable(); - purge_dcache_page_asm(physaddr, vmaddr); + + /* Set context for flush */ + local_irq_save(flags); + prot = mfctl(8); + space = mfsp(SR_USER); + pgd = mfctl(25); +#ifdef CONFIG_TLB_PTLOCK + pgd_lock = mfctl(28); +#endif + switch_mm_irqs_off(NULL, vma->vm_mm, NULL); + local_irq_restore(flags); + + flush_user_dcache_range_asm(vmaddr, vmaddr + PAGE_SIZE); if (vma->vm_flags & VM_EXEC) - flush_icache_page_asm(physaddr, vmaddr); + flush_user_icache_range_asm(vmaddr, vmaddr + PAGE_SIZE); + flush_tlb_page(vma, vmaddr); + + /* Restore previous context */ + local_irq_save(flags); +#ifdef CONFIG_TLB_PTLOCK + mtctl(pgd_lock, 28); +#endif + mtctl(pgd, 25); + mtsp(space, SR_USER); + mtctl(prot, 8); + local_irq_restore(flags); + preempt_enable(); } +static inline pte_t *get_ptep(struct mm_struct *mm, unsigned long addr) +{ + pte_t *ptep = NULL; + pgd_t *pgd = mm->pgd; + p4d_t *p4d; + pud_t *pud; + pmd_t *pmd; + + if (!pgd_none(*pgd)) { + p4d = p4d_offset(pgd, addr); + if (!p4d_none(*p4d)) { + pud = pud_offset(p4d, addr); + if (!pud_none(*pud)) { + pmd = pmd_offset(pud, addr); + if (!pmd_none(*pmd)) + ptep = pte_offset_map(pmd, addr); + } + } + } + return ptep; +} + +static inline bool pte_needs_flush(pte_t pte) +{ + return (pte_val(pte) & (_PAGE_PRESENT | _PAGE_ACCESSED | _PAGE_NO_CACHE)) + == (_PAGE_PRESENT | _PAGE_ACCESSED); +} + void flush_dcache_page(struct page *page) { struct address_space *mapping = page_mapping_file(page); struct vm_area_struct *mpnt; unsigned long offset; unsigned long addr, old_addr = 0; + unsigned long count = 0; pgoff_t pgoff; if (mapping && !mapping_mapped(mapping)) { @@ -357,33 +416,52 @@ void flush_dcache_page(struct page *page) pgoff = page->index; - /* We have carefully arranged in arch_get_unmapped_area() that + /* + * We have carefully arranged in arch_get_unmapped_area() that * *any* mappings of a file are always congruently mapped (whether * declared as MAP_PRIVATE or MAP_SHARED), so we only need - * to flush one address here for them all to become coherent */ - + * to flush one address here for them all to become coherent + * on machines that support equivalent aliasing + */ flush_dcache_mmap_lock(mapping); vma_interval_tree_foreach(mpnt, &mapping->i_mmap, pgoff, pgoff) { offset = (pgoff - mpnt->vm_pgoff) << PAGE_SHIFT; addr = mpnt->vm_start + offset; + if (parisc_requires_coherency()) { + pte_t *ptep; - /* The TLB is the engine of coherence on parisc: The - * CPU is entitled to speculate any page with a TLB - * mapping, so here we kill the mapping then flush the - * page along a special flush only alias mapping. - * This guarantees that the page is no-longer in the - * cache for any process and nor may it be - * speculatively read in (until the user or kernel - * specifically accesses it, of course) */ - - flush_tlb_page(mpnt, addr); - if (old_addr == 0 || (old_addr & (SHM_COLOUR - 1)) - != (addr & (SHM_COLOUR - 1))) { - __flush_cache_page(mpnt, addr, page_to_phys(page)); - if (parisc_requires_coherency() && old_addr) - printk(KERN_ERR "INEQUIVALENT ALIASES 0x%lx and 0x%lx in file %pD\n", old_addr, addr, mpnt->vm_file); - old_addr = addr; + ptep = get_ptep(mpnt->vm_mm, addr); + if (ptep && pte_needs_flush(*ptep)) + flush_user_cache_page(mpnt, addr); + } else { + /* + * The TLB is the engine of coherence on parisc: + * The CPU is entitled to speculate any page + * with a TLB mapping, so here we kill the + * mapping then flush the page along a special + * flush only alias mapping. This guarantees that + * the page is no-longer in the cache for any + * process and nor may it be speculatively read + * in (until the user or kernel specifically + * accesses it, of course) + */ + flush_tlb_page(mpnt, addr); + if (old_addr == 0 || (old_addr & (SHM_COLOUR - 1)) + != (addr & (SHM_COLOUR - 1))) { + __flush_cache_page(mpnt, addr, page_to_phys(page)); + /* + * Software is allowed to have any number + * of private mappings to a page. + */ + if (!(mpnt->vm_flags & VM_SHARED)) + continue; + if (old_addr) + pr_err("INEQUIVALENT ALIASES 0x%lx and 0x%lx in file %pD\n", + old_addr, addr, mpnt->vm_file); + old_addr = addr; + } } + WARN_ON(++count == 4096); } flush_dcache_mmap_unlock(mapping); } @@ -403,7 +481,7 @@ void __init parisc_setup_cache_timing(void) { unsigned long rangetime, alltime; unsigned long size; - unsigned long threshold; + unsigned long threshold, threshold2; alltime = mfctl(16); flush_data_cache(); @@ -417,11 +495,16 @@ void __init parisc_setup_cache_timing(void) printk(KERN_DEBUG "Whole cache flush %lu cycles, flushing %lu bytes %lu cycles\n", alltime, size, rangetime); - threshold = L1_CACHE_ALIGN(size * alltime / rangetime); - if (threshold > cache_info.dc_size) - threshold = cache_info.dc_size; - if (threshold) - parisc_cache_flush_threshold = threshold; + threshold = L1_CACHE_ALIGN((unsigned long)((uint64_t)size * alltime / rangetime)); + pr_info("Calculated flush threshold is %lu KiB\n", + threshold/1024); + + /* + * The threshold computed above isn't very reliable. The following + * heuristic works reasonably well on c8000/rp3440. + */ + threshold2 = cache_info.dc_size * num_online_cpus(); + parisc_cache_flush_threshold = threshold2; printk(KERN_INFO "Cache flush threshold set to %lu KiB\n", parisc_cache_flush_threshold/1024); @@ -477,19 +560,47 @@ void flush_kernel_dcache_page_addr(void *addr) } EXPORT_SYMBOL(flush_kernel_dcache_page_addr); -void copy_user_page(void *vto, void *vfrom, unsigned long vaddr, - struct page *pg) +static void flush_cache_page_if_present(struct vm_area_struct *vma, + unsigned long vmaddr, unsigned long pfn) { - /* Copy using kernel mapping. No coherency is needed (all in - kunmap) for the `to' page. However, the `from' page needs to - be flushed through a mapping equivalent to the user mapping - before it can be accessed through the kernel mapping. */ - preempt_disable(); - flush_dcache_page_asm(__pa(vfrom), vaddr); - copy_page_asm(vto, vfrom); - preempt_enable(); + pte_t *ptep = get_ptep(vma->vm_mm, vmaddr); + + /* + * The pte check is racy and sometimes the flush will trigger + * a non-access TLB miss. Hopefully, the page has already been + * flushed. + */ + if (ptep && pte_needs_flush(*ptep)) + flush_cache_page(vma, vmaddr, pfn); +} + +void copy_user_highpage(struct page *to, struct page *from, + unsigned long vaddr, struct vm_area_struct *vma) +{ + void *kto, *kfrom; + + kfrom = kmap_local_page(from); + kto = kmap_local_page(to); + flush_cache_page_if_present(vma, vaddr, page_to_pfn(from)); + copy_page_asm(kto, kfrom); + kunmap_local(kto); + kunmap_local(kfrom); +} + +void copy_to_user_page(struct vm_area_struct *vma, struct page *page, + unsigned long user_vaddr, void *dst, void *src, int len) +{ + flush_cache_page_if_present(vma, user_vaddr, page_to_pfn(page)); + memcpy(dst, src, len); + flush_kernel_dcache_range_asm((unsigned long)dst, (unsigned long)dst + len); +} + +void copy_from_user_page(struct vm_area_struct *vma, struct page *page, + unsigned long user_vaddr, void *dst, void *src, int len) +{ + flush_cache_page_if_present(vma, user_vaddr, page_to_pfn(page)); + memcpy(dst, src, len); } -EXPORT_SYMBOL(copy_user_page); /* __flush_tlb_range() * @@ -520,92 +631,105 @@ int __flush_tlb_range(unsigned long sid, unsigned long start, return 0; } -static inline unsigned long mm_total_size(struct mm_struct *mm) +static void flush_cache_pages(struct vm_area_struct *vma, unsigned long start, unsigned long end) { - struct vm_area_struct *vma; - unsigned long usize = 0; - - for (vma = mm->mmap; vma; vma = vma->vm_next) - usize += vma->vm_end - vma->vm_start; - return usize; -} - -static inline pte_t *get_ptep(pgd_t *pgd, unsigned long addr) -{ - pte_t *ptep = NULL; + unsigned long addr, pfn; + pte_t *ptep; - if (!pgd_none(*pgd)) { - p4d_t *p4d = p4d_offset(pgd, addr); - if (!p4d_none(*p4d)) { - pud_t *pud = pud_offset(p4d, addr); - if (!pud_none(*pud)) { - pmd_t *pmd = pmd_offset(pud, addr); - if (!pmd_none(*pmd)) - ptep = pte_offset_map(pmd, addr); + for (addr = start; addr < end; addr += PAGE_SIZE) { + /* + * The vma can contain pages that aren't present. Although + * the pte search is expensive, we need the pte to find the + * page pfn and to check whether the page should be flushed. + */ + ptep = get_ptep(vma->vm_mm, addr); + if (ptep && pte_needs_flush(*ptep)) { + if (parisc_requires_coherency()) { + flush_user_cache_page(vma, addr); + } else { + pfn = pte_pfn(*ptep); + if (WARN_ON(!pfn_valid(pfn))) + return; + __flush_cache_page(vma, addr, PFN_PHYS(pfn)); } } } - return ptep; } -static void flush_cache_pages(struct vm_area_struct *vma, struct mm_struct *mm, - unsigned long start, unsigned long end) +static inline unsigned long mm_total_size(struct mm_struct *mm) { - unsigned long addr, pfn; - pte_t *ptep; + struct vm_area_struct *vma; + unsigned long usize = 0; - for (addr = start; addr < end; addr += PAGE_SIZE) { - ptep = get_ptep(mm->pgd, addr); - if (ptep) { - pfn = pte_pfn(*ptep); - flush_cache_page(vma, addr, pfn); - } - } + for (vma = mm->mmap; vma && usize < parisc_cache_flush_threshold; vma = vma->vm_next) + usize += vma->vm_end - vma->vm_start; + return usize; } void flush_cache_mm(struct mm_struct *mm) { struct vm_area_struct *vma; - /* Flushing the whole cache on each cpu takes forever on - rp3440, etc. So, avoid it if the mm isn't too big. */ - if ((!IS_ENABLED(CONFIG_SMP) || !arch_irqs_disabled()) && - mm_total_size(mm) >= parisc_cache_flush_threshold) { - if (mm->context.space_id) - flush_tlb_all(); + /* + * Flushing the whole cache on each cpu takes forever on + * rp3440, etc. So, avoid it if the mm isn't too big. + * + * Note that we must flush the entire cache on machines + * with aliasing caches to prevent random segmentation + * faults. + */ + if (!parisc_requires_coherency() + || mm_total_size(mm) >= parisc_cache_flush_threshold) { + if (WARN_ON(IS_ENABLED(CONFIG_SMP) && arch_irqs_disabled())) + return; + flush_tlb_all(); flush_cache_all(); return; } + /* Flush mm */ for (vma = mm->mmap; vma; vma = vma->vm_next) - flush_cache_pages(vma, mm, vma->vm_start, vma->vm_end); + flush_cache_pages(vma, vma->vm_start, vma->vm_end); } -void flush_cache_range(struct vm_area_struct *vma, - unsigned long start, unsigned long end) +void flush_cache_range(struct vm_area_struct *vma, unsigned long start, unsigned long end) { - if ((!IS_ENABLED(CONFIG_SMP) || !arch_irqs_disabled()) && - end - start >= parisc_cache_flush_threshold) { - if (vma->vm_mm->context.space_id) - flush_tlb_range(vma, start, end); + if (!parisc_requires_coherency() + || end - start >= parisc_cache_flush_threshold) { + if (WARN_ON(IS_ENABLED(CONFIG_SMP) && arch_irqs_disabled())) + return; + flush_tlb_range(vma, start, end); flush_cache_all(); return; } - flush_cache_pages(vma, vma->vm_mm, start, end); + flush_cache_pages(vma, start, end); } -void -flush_cache_page(struct vm_area_struct *vma, unsigned long vmaddr, unsigned long pfn) +void flush_cache_page(struct vm_area_struct *vma, unsigned long vmaddr, unsigned long pfn) { - if (pfn_valid(pfn)) { - if (likely(vma->vm_mm->context.space_id)) { - flush_tlb_page(vma, vmaddr); - __flush_cache_page(vma, vmaddr, PFN_PHYS(pfn)); - } else { - __purge_cache_page(vma, vmaddr, PFN_PHYS(pfn)); - } + if (WARN_ON(!pfn_valid(pfn))) + return; + if (parisc_requires_coherency()) + flush_user_cache_page(vma, vmaddr); + else + __flush_cache_page(vma, vmaddr, PFN_PHYS(pfn)); +} + +void flush_anon_page(struct vm_area_struct *vma, struct page *page, unsigned long vmaddr) +{ + if (!PageAnon(page)) + return; + + if (parisc_requires_coherency()) { + flush_user_cache_page(vma, vmaddr); + return; } + + flush_tlb_page(vma, vmaddr); + preempt_disable(); + flush_dcache_page_asm(page_to_phys(page), vmaddr); + preempt_enable(); } void flush_kernel_vmap_range(void *vaddr, int size) diff --git a/arch/parisc/kernel/patch.c b/arch/parisc/kernel/patch.c index 80a0ab372802..e59574f65e64 100644 --- a/arch/parisc/kernel/patch.c +++ b/arch/parisc/kernel/patch.c @@ -40,10 +40,7 @@ static void __kprobes *patch_map(void *addr, int fixmap, unsigned long *flags, *need_unmap = 1; set_fixmap(fixmap, page_to_phys(page)); - if (flags) - raw_spin_lock_irqsave(&patch_lock, *flags); - else - __acquire(&patch_lock); + raw_spin_lock_irqsave(&patch_lock, *flags); return (void *) (__fix_to_virt(fixmap) + (uintaddr & ~PAGE_MASK)); } @@ -52,10 +49,7 @@ static void __kprobes patch_unmap(int fixmap, unsigned long *flags) { clear_fixmap(fixmap); - if (flags) - raw_spin_unlock_irqrestore(&patch_lock, *flags); - else - __release(&patch_lock); + raw_spin_unlock_irqrestore(&patch_lock, *flags); } void __kprobes __patch_text_multiple(void *addr, u32 *insn, unsigned int len) @@ -67,8 +61,9 @@ void __kprobes __patch_text_multiple(void *addr, u32 *insn, unsigned int len) int mapped; /* Make sure we don't have any aliases in cache */ - flush_kernel_vmap_range(addr, len); - flush_icache_range(start, end); + flush_kernel_dcache_range_asm(start, end); + flush_kernel_icache_range_asm(start, end); + flush_tlb_kernel_range(start, end); p = fixmap = patch_map(addr, FIX_TEXT_POKE0, &flags, &mapped); @@ -81,8 +76,10 @@ void __kprobes __patch_text_multiple(void *addr, u32 *insn, unsigned int len) * We're crossing a page boundary, so * need to remap */ - flush_kernel_vmap_range((void *)fixmap, - (p-fixmap) * sizeof(*p)); + flush_kernel_dcache_range_asm((unsigned long)fixmap, + (unsigned long)p); + flush_tlb_kernel_range((unsigned long)fixmap, + (unsigned long)p); if (mapped) patch_unmap(FIX_TEXT_POKE0, &flags); p = fixmap = patch_map(addr, FIX_TEXT_POKE0, &flags, @@ -90,10 +87,10 @@ void __kprobes __patch_text_multiple(void *addr, u32 *insn, unsigned int len) } } - flush_kernel_vmap_range((void *)fixmap, (p-fixmap) * sizeof(*p)); + flush_kernel_dcache_range_asm((unsigned long)fixmap, (unsigned long)p); + flush_tlb_kernel_range((unsigned long)fixmap, (unsigned long)p); if (mapped) patch_unmap(FIX_TEXT_POKE0, &flags); - flush_icache_range(start, end); } void __kprobes __patch_text(void *addr, u32 insn) diff --git a/arch/parisc/mm/fault.c b/arch/parisc/mm/fault.c index f114e102aaf2..84bc437be5cd 100644 --- a/arch/parisc/mm/fault.c +++ b/arch/parisc/mm/fault.c @@ -22,6 +22,8 @@ #include <asm/traps.h> +#define DEBUG_NATLB 0 + /* Various important other fields */ #define bit22set(x) (x & 0x00000200) #define bits23_25set(x) (x & 0x000001c0) @@ -450,8 +452,8 @@ handle_nadtlb_fault(struct pt_regs *regs) fallthrough; case 0x380: /* PDC and FIC instructions */ - if (printk_ratelimit()) { - pr_warn("BUG: nullifying cache flush/purge instruction\n"); + if (DEBUG_NATLB && printk_ratelimit()) { + pr_warn("WARNING: nullifying cache flush/purge instruction\n"); show_regs(regs); } if (insn & 0x20) { diff --git a/arch/powerpc/include/asm/bug.h b/arch/powerpc/include/asm/bug.h index ecbae1832de3..61a4736355c2 100644 --- a/arch/powerpc/include/asm/bug.h +++ b/arch/powerpc/include/asm/bug.h @@ -13,7 +13,8 @@ #ifdef CONFIG_DEBUG_BUGVERBOSE .macro __EMIT_BUG_ENTRY addr,file,line,flags .section __bug_table,"aw" -5001: .4byte \addr - 5001b, 5002f - 5001b +5001: .4byte \addr - . + .4byte 5002f - . .short \line, \flags .org 5001b+BUG_ENTRY_SIZE .previous @@ -24,7 +25,7 @@ #else .macro __EMIT_BUG_ENTRY addr,file,line,flags .section __bug_table,"aw" -5001: .4byte \addr - 5001b +5001: .4byte \addr - . .short \flags .org 5001b+BUG_ENTRY_SIZE .previous @@ -49,15 +50,16 @@ #ifdef CONFIG_DEBUG_BUGVERBOSE #define _EMIT_BUG_ENTRY \ ".section __bug_table,\"aw\"\n" \ - "2:\t.4byte 1b - 2b, %0 - 2b\n" \ - "\t.short %1, %2\n" \ + "2: .4byte 1b - .\n" \ + " .4byte %0 - .\n" \ + " .short %1, %2\n" \ ".org 2b+%3\n" \ ".previous\n" #else #define _EMIT_BUG_ENTRY \ ".section __bug_table,\"aw\"\n" \ - "2:\t.4byte 1b - 2b\n" \ - "\t.short %2\n" \ + "2: .4byte 1b - .\n" \ + " .short %2\n" \ ".org 2b+%3\n" \ ".previous\n" #endif diff --git a/arch/powerpc/kernel/fadump.c b/arch/powerpc/kernel/fadump.c index 65562c4a0a69..4c09c6688ac6 100644 --- a/arch/powerpc/kernel/fadump.c +++ b/arch/powerpc/kernel/fadump.c @@ -752,7 +752,7 @@ u32 *__init fadump_regs_to_elf_notes(u32 *buf, struct pt_regs *regs) * FIXME: How do i get PID? Do I really need it? * prstatus.pr_pid = ???? */ - elf_core_copy_kernel_regs(&prstatus.pr_reg, regs); + elf_core_copy_regs(&prstatus.pr_reg, regs); buf = append_elf_note(buf, CRASH_CORE_NOTE_NAME, NT_PRSTATUS, &prstatus, sizeof(prstatus)); return buf; diff --git a/arch/powerpc/kvm/book3s_32_sr.S b/arch/powerpc/kvm/book3s_32_sr.S index e3ab9df6cf19..6cfcd20d4668 100644 --- a/arch/powerpc/kvm/book3s_32_sr.S +++ b/arch/powerpc/kvm/book3s_32_sr.S @@ -122,11 +122,27 @@ /* 0x0 - 0xb */ - /* 'current->mm' needs to be in r4 */ - tophys(r4, r2) - lwz r4, MM(r4) - tophys(r4, r4) - /* This only clobbers r0, r3, r4 and r5 */ + /* switch_mmu_context() needs paging, let's enable it */ + mfmsr r9 + ori r11, r9, MSR_DR + mtmsr r11 + sync + + /* switch_mmu_context() clobbers r12, rescue it */ + SAVE_GPR(12, r1) + + /* Calling switch_mmu_context(<inv>, current->mm, <inv>); */ + lwz r4, MM(r2) bl switch_mmu_context + /* restore r12 */ + REST_GPR(12, r1) + + /* Disable paging again */ + mfmsr r9 + li r6, MSR_DR + andc r9, r9, r6 + mtmsr r9 + sync + .endm diff --git a/arch/powerpc/platforms/powernv/opal-core.c b/arch/powerpc/platforms/powernv/opal-core.c index b97bc179f65a..adcb1a1a2bfe 100644 --- a/arch/powerpc/platforms/powernv/opal-core.c +++ b/arch/powerpc/platforms/powernv/opal-core.c @@ -112,7 +112,7 @@ static void __init fill_prstatus(struct elf_prstatus *prstatus, int pir, struct pt_regs *regs) { memset(prstatus, 0, sizeof(struct elf_prstatus)); - elf_core_copy_kernel_regs(&(prstatus->pr_reg), regs); + elf_core_copy_regs(&(prstatus->pr_reg), regs); /* * Overload PID with PIR value. diff --git a/arch/riscv/boot/dts/microchip/microchip-mpfs.dtsi b/arch/riscv/boot/dts/microchip/microchip-mpfs.dtsi index 746c4d4e7686..cf2f55e1dcb6 100644 --- a/arch/riscv/boot/dts/microchip/microchip-mpfs.dtsi +++ b/arch/riscv/boot/dts/microchip/microchip-mpfs.dtsi @@ -366,7 +366,7 @@ gpio1: gpio@20121000 { compatible = "microchip,mpfs-gpio"; - reg = <000 0x20121000 0x0 0x1000>; + reg = <0x0 0x20121000 0x0 0x1000>; interrupt-parent = <&plic>; interrupt-controller; #interrupt-cells = <1>; diff --git a/arch/riscv/boot/dts/sifive/fu540-c000.dtsi b/arch/riscv/boot/dts/sifive/fu540-c000.dtsi index aad45d7f498f..5c638fd5b35c 100644 --- a/arch/riscv/boot/dts/sifive/fu540-c000.dtsi +++ b/arch/riscv/boot/dts/sifive/fu540-c000.dtsi @@ -167,7 +167,7 @@ clocks = <&prci FU540_PRCI_CLK_TLCLK>; status = "disabled"; }; - dma: dma@3000000 { + dma: dma-controller@3000000 { compatible = "sifive,fu540-c000-pdma"; reg = <0x0 0x3000000 0x0 0x8000>; interrupt-parent = <&plic0>; diff --git a/arch/riscv/include/asm/bug.h b/arch/riscv/include/asm/bug.h index d3804a2f9aad..1aaea81fb141 100644 --- a/arch/riscv/include/asm/bug.h +++ b/arch/riscv/include/asm/bug.h @@ -30,8 +30,8 @@ typedef u32 bug_insn_t; #ifdef CONFIG_GENERIC_BUG_RELATIVE_POINTERS -#define __BUG_ENTRY_ADDR RISCV_INT " 1b - 2b" -#define __BUG_ENTRY_FILE RISCV_INT " %0 - 2b" +#define __BUG_ENTRY_ADDR RISCV_INT " 1b - ." +#define __BUG_ENTRY_FILE RISCV_INT " %0 - ." #else #define __BUG_ENTRY_ADDR RISCV_PTR " 1b" #define __BUG_ENTRY_FILE RISCV_PTR " %0" diff --git a/arch/s390/include/asm/bug.h b/arch/s390/include/asm/bug.h index 0b25f28351ed..aebe1e22c7be 100644 --- a/arch/s390/include/asm/bug.h +++ b/arch/s390/include/asm/bug.h @@ -15,7 +15,8 @@ "1: .asciz \""__FILE__"\"\n" \ ".previous\n" \ ".section __bug_table,\"awM\",@progbits,%2\n" \ - "2: .long 0b-2b,1b-2b\n" \ + "2: .long 0b-.\n" \ + " .long 1b-.\n" \ " .short %0,%1\n" \ " .org 2b+%2\n" \ ".previous\n" \ @@ -30,7 +31,7 @@ asm_inline volatile( \ "0: mc 0,0\n" \ ".section __bug_table,\"awM\",@progbits,%1\n" \ - "1: .long 0b-1b\n" \ + "1: .long 0b-.\n" \ " .short %0\n" \ " .org 1b+%1\n" \ ".previous\n" \ diff --git a/arch/um/drivers/ubd_kern.c b/arch/um/drivers/ubd_kern.c index b03269faef71..c4344b67628d 100644 --- a/arch/um/drivers/ubd_kern.c +++ b/arch/um/drivers/ubd_kern.c @@ -483,7 +483,6 @@ static void ubd_handler(void) if ((io_req->error == BLK_STS_NOTSUPP) && (req_op(io_req->req) == REQ_OP_DISCARD)) { blk_queue_max_discard_sectors(io_req->req->q, 0); blk_queue_max_write_zeroes_sectors(io_req->req->q, 0); - blk_queue_flag_clear(QUEUE_FLAG_DISCARD, io_req->req->q); } blk_mq_end_request(io_req->req, io_req->error); kfree(io_req); @@ -800,10 +799,8 @@ static int ubd_open_dev(struct ubd *ubd_dev) } if (ubd_dev->no_trim == 0) { ubd_dev->queue->limits.discard_granularity = SECTOR_SIZE; - ubd_dev->queue->limits.discard_alignment = SECTOR_SIZE; blk_queue_max_discard_sectors(ubd_dev->queue, UBD_MAX_REQUEST); blk_queue_max_write_zeroes_sectors(ubd_dev->queue, UBD_MAX_REQUEST); - blk_queue_flag_set(QUEUE_FLAG_DISCARD, ubd_dev->queue); } blk_queue_flag_set(QUEUE_FLAG_NONROT, ubd_dev->queue); return 0; diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 68c669680c16..2e8f6fd28e59 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -878,6 +878,21 @@ config ACRN_GUEST IOT with small footprint and real-time features. More details can be found in https://projectacrn.org/. +config INTEL_TDX_GUEST + bool "Intel TDX (Trust Domain Extensions) - Guest Support" + depends on X86_64 && CPU_SUP_INTEL + depends on X86_X2APIC + select ARCH_HAS_CC_PLATFORM + select X86_MEM_ENCRYPT + select X86_MCE + help + Support running as a guest under Intel TDX. Without this support, + the guest kernel can not boot or run under TDX. + TDX includes memory encryption and integrity capabilities + which protect the confidentiality and integrity of guest + memory contents and CPU state. TDX guests are protected from + some attacks from the VMM. + endif #HYPERVISOR_GUEST source "arch/x86/Kconfig.cpu" @@ -1313,7 +1328,7 @@ config MICROCODE config MICROCODE_INTEL bool "Intel microcode loading support" - depends on MICROCODE + depends on CPU_SUP_INTEL && MICROCODE default MICROCODE help This options enables microcode patch loading support for Intel @@ -1325,7 +1340,7 @@ config MICROCODE_INTEL config MICROCODE_AMD bool "AMD microcode loading support" - depends on MICROCODE + depends on CPU_SUP_AMD && MICROCODE help If you select this option, microcode patch loading support for AMD processors will be enabled. @@ -1816,17 +1831,6 @@ config ARCH_RANDOM If supported, this is a high bandwidth, cryptographically secure hardware random number generator. -config X86_SMAP - def_bool y - prompt "Supervisor Mode Access Prevention" if EXPERT - help - Supervisor Mode Access Prevention (SMAP) is a security - feature in newer Intel processors. There is a small - performance cost if this enabled and turned on; there is - also a small increase in the kernel size if this is enabled. - - If unsure, say Y. - config X86_UMIP def_bool y prompt "User Mode Instruction Prevention" if EXPERT @@ -2826,13 +2830,6 @@ config IA32_EMULATION 64-bit kernel. You should likely turn this on, unless you're 100% sure that you don't have any 32-bit programs left. -config IA32_AOUT - tristate "IA32 a.out support" - depends on IA32_EMULATION - depends on BROKEN - help - Support old a.out binaries in the 32bit emulation. - config X86_X32_ABI bool "x32 ABI for 64-bit mode" depends on X86_64 diff --git a/arch/x86/Makefile b/arch/x86/Makefile index 63d50f65b828..1abd7cc9d6cd 100644 --- a/arch/x86/Makefile +++ b/arch/x86/Makefile @@ -313,5 +313,6 @@ define archhelp echo '' echo ' kvm_guest.config - Enable Kconfig items for running this kernel as a KVM guest' echo ' xen.config - Enable Kconfig items for running this kernel as a Xen guest' + echo ' x86_debug.config - Enable tip tree debugging options for testing' endef diff --git a/arch/x86/boot/boot.h b/arch/x86/boot/boot.h index 34c9dbb6a47d..148ba5c5106e 100644 --- a/arch/x86/boot/boot.h +++ b/arch/x86/boot/boot.h @@ -26,6 +26,7 @@ #include "bitops.h" #include "ctype.h" #include "cpuflags.h" +#include "io.h" /* Useful macros */ #define ARRAY_SIZE(x) (sizeof(x) / sizeof(*(x))) @@ -35,44 +36,10 @@ extern struct boot_params boot_params; #define cpu_relax() asm volatile("rep; nop") -/* Basic port I/O */ -static inline void outb(u8 v, u16 port) -{ - asm volatile("outb %0,%1" : : "a" (v), "dN" (port)); -} -static inline u8 inb(u16 port) -{ - u8 v; - asm volatile("inb %1,%0" : "=a" (v) : "dN" (port)); - return v; -} - -static inline void outw(u16 v, u16 port) -{ - asm volatile("outw %0,%1" : : "a" (v), "dN" (port)); -} -static inline u16 inw(u16 port) -{ - u16 v; - asm volatile("inw %1,%0" : "=a" (v) : "dN" (port)); - return v; -} - -static inline void outl(u32 v, u16 port) -{ - asm volatile("outl %0,%1" : : "a" (v), "dN" (port)); -} -static inline u32 inl(u16 port) -{ - u32 v; - asm volatile("inl %1,%0" : "=a" (v) : "dN" (port)); - return v; -} - static inline void io_delay(void) { const u16 DELAY_PORT = 0x80; - asm volatile("outb %%al,%0" : : "dN" (DELAY_PORT)); + outb(0, DELAY_PORT); } /* These functions are used to reference data in other segments. */ @@ -110,66 +77,78 @@ typedef unsigned int addr_t; static inline u8 rdfs8(addr_t addr) { + u8 *ptr = (u8 *)absolute_pointer(addr); u8 v; - asm volatile("movb %%fs:%1,%0" : "=q" (v) : "m" (*(u8 *)addr)); + asm volatile("movb %%fs:%1,%0" : "=q" (v) : "m" (*ptr)); return v; } static inline u16 rdfs16(addr_t addr) { + u16 *ptr = (u16 *)absolute_pointer(addr); u16 v; - asm volatile("movw %%fs:%1,%0" : "=r" (v) : "m" (*(u16 *)addr)); + asm volatile("movw %%fs:%1,%0" : "=r" (v) : "m" (*ptr)); return v; } static inline u32 rdfs32(addr_t addr) { + u32 *ptr = (u32 *)absolute_pointer(addr); u32 v; - asm volatile("movl %%fs:%1,%0" : "=r" (v) : "m" (*(u32 *)addr)); + asm volatile("movl %%fs:%1,%0" : "=r" (v) : "m" (*ptr)); return v; } static inline void wrfs8(u8 v, addr_t addr) { - asm volatile("movb %1,%%fs:%0" : "+m" (*(u8 *)addr) : "qi" (v)); + u8 *ptr = (u8 *)absolute_pointer(addr); + asm volatile("movb %1,%%fs:%0" : "+m" (*ptr) : "qi" (v)); } static inline void wrfs16(u16 v, addr_t addr) { - asm volatile("movw %1,%%fs:%0" : "+m" (*(u16 *)addr) : "ri" (v)); + u16 *ptr = (u16 *)absolute_pointer(addr); + asm volatile("movw %1,%%fs:%0" : "+m" (*ptr) : "ri" (v)); } static inline void wrfs32(u32 v, addr_t addr) { - asm volatile("movl %1,%%fs:%0" : "+m" (*(u32 *)addr) : "ri" (v)); + u32 *ptr = (u32 *)absolute_pointer(addr); + asm volatile("movl %1,%%fs:%0" : "+m" (*ptr) : "ri" (v)); } static inline u8 rdgs8(addr_t addr) { + u8 *ptr = (u8 *)absolute_pointer(addr); u8 v; - asm volatile("movb %%gs:%1,%0" : "=q" (v) : "m" (*(u8 *)addr)); + asm volatile("movb %%gs:%1,%0" : "=q" (v) : "m" (*ptr)); return v; } static inline u16 rdgs16(addr_t addr) { + u16 *ptr = (u16 *)absolute_pointer(addr); u16 v; - asm volatile("movw %%gs:%1,%0" : "=r" (v) : "m" (*(u16 *)addr)); + asm volatile("movw %%gs:%1,%0" : "=r" (v) : "m" (*ptr)); return v; } static inline u32 rdgs32(addr_t addr) { + u32 *ptr = (u32 *)absolute_pointer(addr); u32 v; - asm volatile("movl %%gs:%1,%0" : "=r" (v) : "m" (*(u32 *)addr)); + asm volatile("movl %%gs:%1,%0" : "=r" (v) : "m" (*ptr)); return v; } static inline void wrgs8(u8 v, addr_t addr) { - asm volatile("movb %1,%%gs:%0" : "+m" (*(u8 *)addr) : "qi" (v)); + u8 *ptr = (u8 *)absolute_pointer(addr); + asm volatile("movb %1,%%gs:%0" : "+m" (*ptr) : "qi" (v)); } static inline void wrgs16(u16 v, addr_t addr) { - asm volatile("movw %1,%%gs:%0" : "+m" (*(u16 *)addr) : "ri" (v)); + u16 *ptr = (u16 *)absolute_pointer(addr); + asm volatile("movw %1,%%gs:%0" : "+m" (*ptr) : "ri" (v)); } static inline void wrgs32(u32 v, addr_t addr) { - asm volatile("movl %1,%%gs:%0" : "+m" (*(u32 *)addr) : "ri" (v)); + u32 *ptr = (u32 *)absolute_pointer(addr); + asm volatile("movl %1,%%gs:%0" : "+m" (*ptr) : "ri" (v)); } /* Note: these only return true/false, not a signed return value! */ diff --git a/arch/x86/boot/compressed/Makefile b/arch/x86/boot/compressed/Makefile index 6115274fe10f..19e1905dcbf6 100644 --- a/arch/x86/boot/compressed/Makefile +++ b/arch/x86/boot/compressed/Makefile @@ -101,8 +101,10 @@ ifdef CONFIG_X86_64 endif vmlinux-objs-$(CONFIG_ACPI) += $(obj)/acpi.o +vmlinux-objs-$(CONFIG_INTEL_TDX_GUEST) += $(obj)/tdx.o $(obj)/tdcall.o vmlinux-objs-$(CONFIG_EFI_MIXED) += $(obj)/efi_thunk_$(BITS).o +vmlinux-objs-$(CONFIG_EFI) += $(obj)/efi.o efi-obj-$(CONFIG_EFI_STUB) = $(objtree)/drivers/firmware/efi/libstub/lib.a $(obj)/vmlinux: $(vmlinux-objs-y) $(efi-obj-y) FORCE diff --git a/arch/x86/boot/compressed/acpi.c b/arch/x86/boot/compressed/acpi.c index 8bcbcee54aa1..9caf89063e77 100644 --- a/arch/x86/boot/compressed/acpi.c +++ b/arch/x86/boot/compressed/acpi.c @@ -3,10 +3,9 @@ #include "misc.h" #include "error.h" #include "../string.h" +#include "efi.h" #include <linux/numa.h> -#include <linux/efi.h> -#include <asm/efi.h> /* * Longest parameter of 'acpi=' is 'copy_dsdt', plus an extra '\0' @@ -20,153 +19,56 @@ */ struct mem_vector immovable_mem[MAX_NUMNODES*2]; -/* - * Search EFI system tables for RSDP. If both ACPI_20_TABLE_GUID and - * ACPI_TABLE_GUID are found, take the former, which has more features. - */ static acpi_physical_address -__efi_get_rsdp_addr(unsigned long config_tables, unsigned int nr_tables, - bool efi_64) +__efi_get_rsdp_addr(unsigned long cfg_tbl_pa, unsigned int cfg_tbl_len) { - acpi_physical_address rsdp_addr = 0; - #ifdef CONFIG_EFI - int i; - - /* Get EFI tables from systab. */ - for (i = 0; i < nr_tables; i++) { - acpi_physical_address table; - efi_guid_t guid; - - if (efi_64) { - efi_config_table_64_t *tbl = (efi_config_table_64_t *)config_tables + i; - - guid = tbl->guid; - table = tbl->table; - - if (!IS_ENABLED(CONFIG_X86_64) && table >> 32) { - debug_putstr("Error getting RSDP address: EFI config table located above 4GB.\n"); - return 0; - } - } else { - efi_config_table_32_t *tbl = (efi_config_table_32_t *)config_tables + i; - - guid = tbl->guid; - table = tbl->table; - } + unsigned long rsdp_addr; + int ret; - if (!(efi_guidcmp(guid, ACPI_TABLE_GUID))) - rsdp_addr = table; - else if (!(efi_guidcmp(guid, ACPI_20_TABLE_GUID))) - return table; - } + /* + * Search EFI system tables for RSDP. Preferred is ACPI_20_TABLE_GUID to + * ACPI_TABLE_GUID because it has more features. + */ + rsdp_addr = efi_find_vendor_table(boot_params, cfg_tbl_pa, cfg_tbl_len, + ACPI_20_TABLE_GUID); + if (rsdp_addr) + return (acpi_physical_address)rsdp_addr; + + /* No ACPI_20_TABLE_GUID found, fallback to ACPI_TABLE_GUID. */ + rsdp_addr = efi_find_vendor_table(boot_params, cfg_tbl_pa, cfg_tbl_len, + ACPI_TABLE_GUID); + if (rsdp_addr) + return (acpi_physical_address)rsdp_addr; + + debug_putstr("Error getting RSDP address.\n"); #endif - return rsdp_addr; -} - -/* EFI/kexec support is 64-bit only. */ -#ifdef CONFIG_X86_64 -static struct efi_setup_data *get_kexec_setup_data_addr(void) -{ - struct setup_data *data; - u64 pa_data; - - pa_data = boot_params->hdr.setup_data; - while (pa_data) { - data = (struct setup_data *)pa_data; - if (data->type == SETUP_EFI) - return (struct efi_setup_data *)(pa_data + sizeof(struct setup_data)); - - pa_data = data->next; - } - return NULL; -} - -static acpi_physical_address kexec_get_rsdp_addr(void) -{ - efi_system_table_64_t *systab; - struct efi_setup_data *esd; - struct efi_info *ei; - char *sig; - - esd = (struct efi_setup_data *)get_kexec_setup_data_addr(); - if (!esd) - return 0; - - if (!esd->tables) { - debug_putstr("Wrong kexec SETUP_EFI data.\n"); - return 0; - } - - ei = &boot_params->efi_info; - sig = (char *)&ei->efi_loader_signature; - if (strncmp(sig, EFI64_LOADER_SIGNATURE, 4)) { - debug_putstr("Wrong kexec EFI loader signature.\n"); - return 0; - } - - /* Get systab from boot params. */ - systab = (efi_system_table_64_t *) (ei->efi_systab | ((__u64)ei->efi_systab_hi << 32)); - if (!systab) - error("EFI system table not found in kexec boot_params."); - - return __efi_get_rsdp_addr((unsigned long)esd->tables, systab->nr_tables, true); + return 0; } -#else -static acpi_physical_address kexec_get_rsdp_addr(void) { return 0; } -#endif /* CONFIG_X86_64 */ static acpi_physical_address efi_get_rsdp_addr(void) { #ifdef CONFIG_EFI - unsigned long systab, config_tables; + unsigned long cfg_tbl_pa = 0; + unsigned int cfg_tbl_len; + unsigned long systab_pa; unsigned int nr_tables; - struct efi_info *ei; - bool efi_64; - char *sig; - - ei = &boot_params->efi_info; - sig = (char *)&ei->efi_loader_signature; - - if (!strncmp(sig, EFI64_LOADER_SIGNATURE, 4)) { - efi_64 = true; - } else if (!strncmp(sig, EFI32_LOADER_SIGNATURE, 4)) { - efi_64 = false; - } else { - debug_putstr("Wrong EFI loader signature.\n"); - return 0; - } + enum efi_type et; + int ret; - /* Get systab from boot params. */ -#ifdef CONFIG_X86_64 - systab = ei->efi_systab | ((__u64)ei->efi_systab_hi << 32); -#else - if (ei->efi_systab_hi || ei->efi_memmap_hi) { - debug_putstr("Error getting RSDP address: EFI system table located above 4GB.\n"); + et = efi_get_type(boot_params); + if (et == EFI_TYPE_NONE) return 0; - } - systab = ei->efi_systab; -#endif - if (!systab) - error("EFI system table not found."); - /* Handle EFI bitness properly */ - if (efi_64) { - efi_system_table_64_t *stbl = (efi_system_table_64_t *)systab; + systab_pa = efi_get_system_table(boot_params); + if (!systab_pa) + error("EFI support advertised, but unable to locate system table."); - config_tables = stbl->tables; - nr_tables = stbl->nr_tables; - } else { - efi_system_table_32_t *stbl = (efi_system_table_32_t *)systab; + ret = efi_get_conf_table(boot_params, &cfg_tbl_pa, &cfg_tbl_len); + if (ret || !cfg_tbl_pa) + error("EFI config table not found."); - config_tables = stbl->tables; - nr_tables = stbl->nr_tables; - } - - if (!config_tables) - error("EFI config tables not found."); - - return __efi_get_rsdp_addr(config_tables, nr_tables, efi_64); + return __efi_get_rsdp_addr(cfg_tbl_pa, cfg_tbl_len); #else return 0; #endif @@ -256,14 +158,6 @@ acpi_physical_address get_rsdp_addr(void) pa = boot_params->acpi_rsdp_addr; - /* - * Try to get EFI data from setup_data. This can happen when we're a - * kexec'ed kernel and kexec(1) has passed all the required EFI info to - * us. - */ - if (!pa) - pa = kexec_get_rsdp_addr(); - if (!pa) pa = efi_get_rsdp_addr(); diff --git a/arch/x86/boot/compressed/early_serial_console.c b/arch/x86/boot/compressed/early_serial_console.c index 261e81fb9582..70a8d1706d0f 100644 --- a/arch/x86/boot/compressed/early_serial_console.c +++ b/arch/x86/boot/compressed/early_serial_console.c @@ -1,5 +1,6 @@ #include "misc.h" -int early_serial_base; +/* This might be accessed before .bss is cleared, so use .data instead. */ +int early_serial_base __section(".data"); #include "../early_serial_console.c" diff --git a/arch/x86/boot/compressed/efi.c b/arch/x86/boot/compressed/efi.c new file mode 100644 index 000000000000..6edd034b0b30 --- /dev/null +++ b/arch/x86/boot/compressed/efi.c @@ -0,0 +1,234 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Helpers for early access to EFI configuration table. + * + * Originally derived from arch/x86/boot/compressed/acpi.c + */ + +#include "misc.h" + +/** + * efi_get_type - Given a pointer to boot_params, determine the type of EFI environment. + * + * @bp: pointer to boot_params + * + * Return: EFI_TYPE_{32,64} for valid EFI environments, EFI_TYPE_NONE otherwise. + */ +enum efi_type efi_get_type(struct boot_params *bp) +{ + struct efi_info *ei; + enum efi_type et; + const char *sig; + + ei = &bp->efi_info; + sig = (char *)&ei->efi_loader_signature; + + if (!strncmp(sig, EFI64_LOADER_SIGNATURE, 4)) { + et = EFI_TYPE_64; + } else if (!strncmp(sig, EFI32_LOADER_SIGNATURE, 4)) { + et = EFI_TYPE_32; + } else { + debug_putstr("No EFI environment detected.\n"); + et = EFI_TYPE_NONE; + } + +#ifndef CONFIG_X86_64 + /* + * Existing callers like acpi.c treat this case as an indicator to + * fall-through to non-EFI, rather than an error, so maintain that + * functionality here as well. + */ + if (ei->efi_systab_hi || ei->efi_memmap_hi) { + debug_putstr("EFI system table is located above 4GB and cannot be accessed.\n"); + et = EFI_TYPE_NONE; + } +#endif + + return et; +} + +/** + * efi_get_system_table - Given a pointer to boot_params, retrieve the physical address + * of the EFI system table. + * + * @bp: pointer to boot_params + * + * Return: EFI system table address on success. On error, return 0. + */ +unsigned long efi_get_system_table(struct boot_params *bp) +{ + unsigned long sys_tbl_pa; + struct efi_info *ei; + enum efi_type et; + + /* Get systab from boot params. */ + ei = &bp->efi_info; +#ifdef CONFIG_X86_64 + sys_tbl_pa = ei->efi_systab | ((__u64)ei->efi_systab_hi << 32); +#else + sys_tbl_pa = ei->efi_systab; +#endif + if (!sys_tbl_pa) { + debug_putstr("EFI system table not found."); + return 0; + } + + return sys_tbl_pa; +} + +/* + * EFI config table address changes to virtual address after boot, which may + * not be accessible for the kexec'd kernel. To address this, kexec provides + * the initial physical address via a struct setup_data entry, which is + * checked for here, along with some sanity checks. + */ +static struct efi_setup_data *get_kexec_setup_data(struct boot_params *bp, + enum efi_type et) +{ +#ifdef CONFIG_X86_64 + struct efi_setup_data *esd = NULL; + struct setup_data *data; + u64 pa_data; + + pa_data = bp->hdr.setup_data; + while (pa_data) { + data = (struct setup_data *)pa_data; + if (data->type == SETUP_EFI) { + esd = (struct efi_setup_data *)(pa_data + sizeof(struct setup_data)); + break; + } + + pa_data = data->next; + } + + /* + * Original ACPI code falls back to attempting normal EFI boot in these + * cases, so maintain existing behavior by indicating non-kexec + * environment to the caller, but print them for debugging. + */ + if (esd && !esd->tables) { + debug_putstr("kexec EFI environment missing valid configuration table.\n"); + return NULL; + } + + return esd; +#endif + return NULL; +} + +/** + * efi_get_conf_table - Given a pointer to boot_params, locate and return the physical + * address of EFI configuration table. + * + * @bp: pointer to boot_params + * @cfg_tbl_pa: location to store physical address of config table + * @cfg_tbl_len: location to store number of config table entries + * + * Return: 0 on success. On error, return params are left unchanged. + */ +int efi_get_conf_table(struct boot_params *bp, unsigned long *cfg_tbl_pa, + unsigned int *cfg_tbl_len) +{ + unsigned long sys_tbl_pa; + enum efi_type et; + int ret; + + if (!cfg_tbl_pa || !cfg_tbl_len) + return -EINVAL; + + sys_tbl_pa = efi_get_system_table(bp); + if (!sys_tbl_pa) + return -EINVAL; + + /* Handle EFI bitness properly */ + et = efi_get_type(bp); + if (et == EFI_TYPE_64) { + efi_system_table_64_t *stbl = (efi_system_table_64_t *)sys_tbl_pa; + struct efi_setup_data *esd; + + /* kexec provides an alternative EFI conf table, check for it. */ + esd = get_kexec_setup_data(bp, et); + + *cfg_tbl_pa = esd ? esd->tables : stbl->tables; + *cfg_tbl_len = stbl->nr_tables; + } else if (et == EFI_TYPE_32) { + efi_system_table_32_t *stbl = (efi_system_table_32_t *)sys_tbl_pa; + + *cfg_tbl_pa = stbl->tables; + *cfg_tbl_len = stbl->nr_tables; + } else { + return -EINVAL; + } + + return 0; +} + +/* Get vendor table address/guid from EFI config table at the given index */ +static int get_vendor_table(void *cfg_tbl, unsigned int idx, + unsigned long *vendor_tbl_pa, + efi_guid_t *vendor_tbl_guid, + enum efi_type et) +{ + if (et == EFI_TYPE_64) { + efi_config_table_64_t *tbl_entry = (efi_config_table_64_t *)cfg_tbl + idx; + + if (!IS_ENABLED(CONFIG_X86_64) && tbl_entry->table >> 32) { + debug_putstr("Error: EFI config table entry located above 4GB.\n"); + return -EINVAL; + } + + *vendor_tbl_pa = tbl_entry->table; + *vendor_tbl_guid = tbl_entry->guid; + + } else if (et == EFI_TYPE_32) { + efi_config_table_32_t *tbl_entry = (efi_config_table_32_t *)cfg_tbl + idx; + + *vendor_tbl_pa = tbl_entry->table; + *vendor_tbl_guid = tbl_entry->guid; + } else { + return -EINVAL; + } + + return 0; +} + +/** + * efi_find_vendor_table - Given EFI config table, search it for the physical + * address of the vendor table associated with GUID. + * + * @bp: pointer to boot_params + * @cfg_tbl_pa: pointer to EFI configuration table + * @cfg_tbl_len: number of entries in EFI configuration table + * @guid: GUID of vendor table + * + * Return: vendor table address on success. On error, return 0. + */ +unsigned long efi_find_vendor_table(struct boot_params *bp, + unsigned long cfg_tbl_pa, + unsigned int cfg_tbl_len, + efi_guid_t guid) +{ + enum efi_type et; + unsigned int i; + + et = efi_get_type(bp); + if (et == EFI_TYPE_NONE) + return 0; + + for (i = 0; i < cfg_tbl_len; i++) { + unsigned long vendor_tbl_pa; + efi_guid_t vendor_tbl_guid; + int ret; + + ret = get_vendor_table((void *)cfg_tbl_pa, i, + &vendor_tbl_pa, + &vendor_tbl_guid, et); + if (ret) + return 0; + + if (!efi_guidcmp(guid, vendor_tbl_guid)) + return vendor_tbl_pa; + } + + return 0; +} diff --git a/arch/x86/boot/compressed/efi.h b/arch/x86/boot/compressed/efi.h new file mode 100644 index 000000000000..7db2f41b54cd --- /dev/null +++ b/arch/x86/boot/compressed/efi.h @@ -0,0 +1,126 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef BOOT_COMPRESSED_EFI_H +#define BOOT_COMPRESSED_EFI_H + +#if defined(_LINUX_EFI_H) || defined(_ASM_X86_EFI_H) +#error Please do not include kernel proper namespace headers +#endif + +typedef guid_t efi_guid_t __aligned(__alignof__(u32)); + +#define EFI_GUID(a, b, c, d...) (efi_guid_t){ { \ + (a) & 0xff, ((a) >> 8) & 0xff, ((a) >> 16) & 0xff, ((a) >> 24) & 0xff, \ + (b) & 0xff, ((b) >> 8) & 0xff, \ + (c) & 0xff, ((c) >> 8) & 0xff, d } } + +#define ACPI_TABLE_GUID EFI_GUID(0xeb9d2d30, 0x2d88, 0x11d3, 0x9a, 0x16, 0x00, 0x90, 0x27, 0x3f, 0xc1, 0x4d) +#define ACPI_20_TABLE_GUID EFI_GUID(0x8868e871, 0xe4f1, 0x11d3, 0xbc, 0x22, 0x00, 0x80, 0xc7, 0x3c, 0x88, 0x81) +#define EFI_CC_BLOB_GUID EFI_GUID(0x067b1f5f, 0xcf26, 0x44c5, 0x85, 0x54, 0x93, 0xd7, 0x77, 0x91, 0x2d, 0x42) + +#define EFI32_LOADER_SIGNATURE "EL32" +#define EFI64_LOADER_SIGNATURE "EL64" + +/* + * Generic EFI table header + */ +typedef struct { + u64 signature; + u32 revision; + u32 headersize; + u32 crc32; + u32 reserved; +} efi_table_hdr_t; + +#define EFI_CONVENTIONAL_MEMORY 7 + +#define EFI_MEMORY_MORE_RELIABLE \ + ((u64)0x0000000000010000ULL) /* higher reliability */ +#define EFI_MEMORY_SP ((u64)0x0000000000040000ULL) /* soft reserved */ + +#define EFI_PAGE_SHIFT 12 + +typedef struct { + u32 type; + u32 pad; + u64 phys_addr; + u64 virt_addr; + u64 num_pages; + u64 attribute; +} efi_memory_desc_t; + +#define efi_early_memdesc_ptr(map, desc_size, n) \ + (efi_memory_desc_t *)((void *)(map) + ((n) * (desc_size))) + +typedef struct { + efi_guid_t guid; + u64 table; +} efi_config_table_64_t; + +typedef struct { + efi_guid_t guid; + u32 table; +} efi_config_table_32_t; + +typedef struct { + efi_table_hdr_t hdr; + u64 fw_vendor; /* physical addr of CHAR16 vendor string */ + u32 fw_revision; + u32 __pad1; + u64 con_in_handle; + u64 con_in; + u64 con_out_handle; + u64 con_out; + u64 stderr_handle; + u64 stderr; + u64 runtime; + u64 boottime; + u32 nr_tables; + u32 __pad2; + u64 tables; +} efi_system_table_64_t; + +typedef struct { + efi_table_hdr_t hdr; + u32 fw_vendor; /* physical addr of CHAR16 vendor string */ + u32 fw_revision; + u32 con_in_handle; + u32 con_in; + u32 con_out_handle; + u32 con_out; + u32 stderr_handle; + u32 stderr; + u32 runtime; + u32 boottime; + u32 nr_tables; + u32 tables; +} efi_system_table_32_t; + +/* kexec external ABI */ +struct efi_setup_data { + u64 fw_vendor; + u64 __unused; + u64 tables; + u64 smbios; + u64 reserved[8]; +}; + +static inline int efi_guidcmp (efi_guid_t left, efi_guid_t right) +{ + return memcmp(&left, &right, sizeof (efi_guid_t)); +} + +#ifdef CONFIG_EFI +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_soft_reserve_enabled(void) +{ + return false; +} +#endif /* CONFIG_EFI */ +#endif /* BOOT_COMPRESSED_EFI_H */ diff --git a/arch/x86/boot/compressed/head_64.S b/arch/x86/boot/compressed/head_64.S index dea95301196b..d33f060900d2 100644 --- a/arch/x86/boot/compressed/head_64.S +++ b/arch/x86/boot/compressed/head_64.S @@ -189,11 +189,11 @@ SYM_FUNC_START(startup_32) subl $32, %eax /* Encryption bit is always above bit 31 */ bts %eax, %edx /* Set encryption mask for page tables */ /* - * Mark SEV as active in sev_status so that startup32_check_sev_cbit() - * will do a check. The sev_status memory will be fully initialized - * with the contents of MSR_AMD_SEV_STATUS later in - * set_sev_encryption_mask(). For now it is sufficient to know that SEV - * is active. + * Set MSR_AMD64_SEV_ENABLED_BIT in sev_status so that + * startup32_check_sev_cbit() will do a check. sev_enable() will + * initialize sev_status with all the bits reported by + * MSR_AMD_SEV_STATUS later, but only MSR_AMD64_SEV_ENABLED_BIT + * needs to be set for now. */ movl $1, rva(sev_status)(%ebp) 1: @@ -289,7 +289,7 @@ SYM_FUNC_START(startup_32) pushl %eax /* Enter paged protected Mode, activating Long Mode */ - movl $(X86_CR0_PG | X86_CR0_PE), %eax /* Enable Paging and Protected mode */ + movl $CR0_STATE, %eax movl %eax, %cr0 /* Jump from 32bit compatibility mode into 64bit mode. */ @@ -447,6 +447,23 @@ SYM_CODE_START(startup_64) call load_stage1_idt popq %rsi +#ifdef CONFIG_AMD_MEM_ENCRYPT + /* + * Now that the stage1 interrupt handlers are set up, #VC exceptions from + * CPUID instructions can be properly handled for SEV-ES guests. + * + * For SEV-SNP, the CPUID table also needs to be set up in advance of any + * CPUID instructions being issued, so go ahead and do that now via + * sev_enable(), which will also handle the rest of the SEV-related + * detection/setup to ensure that has been done in advance of any dependent + * code. + */ + pushq %rsi + movq %rsi, %rdi /* real mode address */ + call sev_enable + popq %rsi +#endif + /* * paging_prepare() sets up the trampoline and checks if we need to * enable 5-level paging. @@ -558,17 +575,7 @@ SYM_FUNC_START_LOCAL_NOALIGN(.Lrelocated) shrq $3, %rcx rep stosq -/* - * If running as an SEV guest, the encryption mask is required in the - * page-table setup code below. When the guest also has SEV-ES enabled - * set_sev_encryption_mask() will cause #VC exceptions, but the stage2 - * handler can't map its GHCB because the page-table is not set up yet. - * So set up the encryption mask here while still on the stage1 #VC - * handler. Then load stage2 IDT and switch to the kernel's own - * page-table. - */ pushq %rsi - call set_sev_encryption_mask call load_stage2_idt /* Pass boot_params to initialize_identity_maps() */ @@ -642,12 +649,28 @@ SYM_CODE_START(trampoline_32bit_src) movl $MSR_EFER, %ecx rdmsr btsl $_EFER_LME, %eax + /* Avoid writing EFER if no change was made (for TDX guest) */ + jc 1f wrmsr - popl %edx +1: popl %edx popl %ecx +#ifdef CONFIG_X86_MCE + /* + * Preserve CR4.MCE if the kernel will enable #MC support. + * Clearing MCE may fault in some environments (that also force #MC + * support). Any machine check that occurs before #MC support is fully + * configured will crash the system regardless of the CR4.MCE value set + * here. + */ + movl %cr4, %eax + andl $X86_CR4_MCE, %eax +#else + movl $0, %eax +#endif + /* Enable PAE and LA57 (if required) paging modes */ - movl $X86_CR4_PAE, %eax + orl $X86_CR4_PAE, %eax testl %edx, %edx jz 1f orl $X86_CR4_LA57, %eax @@ -661,8 +684,9 @@ SYM_CODE_START(trampoline_32bit_src) pushl $__KERNEL_CS pushl %eax - /* Enable paging again */ - movl $(X86_CR0_PG | X86_CR0_PE), %eax + /* Enable paging again. */ + movl %cr0, %eax + btsl $X86_CR0_PG_BIT, %eax movl %eax, %cr0 lret diff --git a/arch/x86/boot/compressed/ident_map_64.c b/arch/x86/boot/compressed/ident_map_64.c index f7213d0943b8..44c350d627c7 100644 --- a/arch/x86/boot/compressed/ident_map_64.c +++ b/arch/x86/boot/compressed/ident_map_64.c @@ -90,7 +90,7 @@ static struct x86_mapping_info mapping_info; /* * Adds the specified range to the identity mappings. */ -static void add_identity_map(unsigned long start, unsigned long end) +void kernel_add_identity_map(unsigned long start, unsigned long end) { int ret; @@ -157,14 +157,15 @@ void initialize_identity_maps(void *rmode) * explicitly here in case the compressed kernel does not touch them, * or does not touch all the pages covering them. */ - add_identity_map((unsigned long)_head, (unsigned long)_end); + kernel_add_identity_map((unsigned long)_head, (unsigned long)_end); boot_params = rmode; - add_identity_map((unsigned long)boot_params, (unsigned long)(boot_params + 1)); + kernel_add_identity_map((unsigned long)boot_params, (unsigned long)(boot_params + 1)); cmdline = get_cmd_line_ptr(); - add_identity_map(cmdline, cmdline + COMMAND_LINE_SIZE); + kernel_add_identity_map(cmdline, cmdline + COMMAND_LINE_SIZE); + + sev_prep_identity_maps(top_level_pgt); /* Load the new page-table. */ - sev_verify_cbit(top_level_pgt); write_cr3(top_level_pgt); } @@ -246,10 +247,10 @@ static int set_clr_page_flags(struct x86_mapping_info *info, * It should already exist, but keep things generic. * * To map the page just read from it and fault it in if there is no - * mapping yet. add_identity_map() can't be called here because that - * would unconditionally map the address on PMD level, destroying any - * PTE-level mappings that might already exist. Use assembly here so - * the access won't be optimized away. + * mapping yet. kernel_add_identity_map() can't be called here because + * that would unconditionally map the address on PMD level, destroying + * any PTE-level mappings that might already exist. Use assembly here + * so the access won't be optimized away. */ asm volatile("mov %[address], %%r9" :: [address] "g" (*(unsigned long *)address) @@ -275,15 +276,31 @@ static int set_clr_page_flags(struct x86_mapping_info *info, * Changing encryption attributes of a page requires to flush it from * the caches. */ - if ((set | clr) & _PAGE_ENC) + if ((set | clr) & _PAGE_ENC) { clflush_page(address); + /* + * If the encryption attribute is being cleared, change the page state + * to shared in the RMP table. + */ + if (clr) + snp_set_page_shared(__pa(address & PAGE_MASK)); + } + /* Update PTE */ pte = *ptep; pte = pte_set_flags(pte, set); pte = pte_clear_flags(pte, clr); set_pte(ptep, pte); + /* + * If the encryption attribute is being set, then change the page state to + * private in the RMP entry. The page state change must be done after the PTE + * is updated. + */ + if (set & _PAGE_ENC) + snp_set_page_private(__pa(address & PAGE_MASK)); + /* Flush TLB after changing encryption attribute */ write_cr3(top_level_pgt); @@ -347,5 +364,5 @@ void do_boot_page_fault(struct pt_regs *regs, unsigned long error_code) * Error code is sane - now identity map the 2M region around * the faulting address. */ - add_identity_map(address, end); + kernel_add_identity_map(address, end); } diff --git a/arch/x86/boot/compressed/idt_64.c b/arch/x86/boot/compressed/idt_64.c index 9b93567d663a..6debb816e83d 100644 --- a/arch/x86/boot/compressed/idt_64.c +++ b/arch/x86/boot/compressed/idt_64.c @@ -39,7 +39,23 @@ void load_stage1_idt(void) load_boot_idt(&boot_idt_desc); } -/* Setup IDT after kernel jumping to .Lrelocated */ +/* + * Setup IDT after kernel jumping to .Lrelocated. + * + * initialize_identity_maps() needs a #PF handler to be setup + * in order to be able to fault-in identity mapping ranges; see + * do_boot_page_fault(). + * + * This #PF handler setup needs to happen in load_stage2_idt() where the + * IDT is loaded and there the #VC IDT entry gets setup too. + * + * In order to be able to handle #VCs, one needs a GHCB which + * gets setup with an already set up pagetable, which is done in + * initialize_identity_maps(). And there's the catch 22: the boot #VC + * handler do_boot_stage2_vc() needs to call early_setup_ghcb() itself + * (and, especially set_page_decrypted()) because the SEV-ES setup code + * cannot initialize a GHCB as there's no #PF handler yet... + */ void load_stage2_idt(void) { boot_idt_desc.address = (unsigned long)boot_idt; diff --git a/arch/x86/boot/compressed/kaslr.c b/arch/x86/boot/compressed/kaslr.c index 411b268bc0a2..4a3f223973f4 100644 --- a/arch/x86/boot/compressed/kaslr.c +++ b/arch/x86/boot/compressed/kaslr.c @@ -22,15 +22,14 @@ #include "misc.h" #include "error.h" #include "../string.h" +#include "efi.h" #include <generated/compile.h> #include <linux/module.h> #include <linux/uts.h> #include <linux/utsname.h> #include <linux/ctype.h> -#include <linux/efi.h> #include <generated/utsrelease.h> -#include <asm/efi.h> #define _SETUP #include <asm/setup.h> /* For COMMAND_LINE_SIZE */ diff --git a/arch/x86/boot/compressed/mem_encrypt.S b/arch/x86/boot/compressed/mem_encrypt.S index a63424d13627..a73e4d783cae 100644 --- a/arch/x86/boot/compressed/mem_encrypt.S +++ b/arch/x86/boot/compressed/mem_encrypt.S @@ -187,42 +187,6 @@ SYM_CODE_END(startup32_vc_handler) .code64 #include "../../kernel/sev_verify_cbit.S" -SYM_FUNC_START(set_sev_encryption_mask) -#ifdef CONFIG_AMD_MEM_ENCRYPT - push %rbp - push %rdx - - movq %rsp, %rbp /* Save current stack pointer */ - - call get_sev_encryption_bit /* Get the encryption bit position */ - testl %eax, %eax - jz .Lno_sev_mask - - bts %rax, sme_me_mask(%rip) /* Create the encryption mask */ - - /* - * Read MSR_AMD64_SEV again and store it to sev_status. Can't do this in - * get_sev_encryption_bit() because this function is 32-bit code and - * shared between 64-bit and 32-bit boot path. - */ - movl $MSR_AMD64_SEV, %ecx /* Read the SEV MSR */ - rdmsr - - /* Store MSR value in sev_status */ - shlq $32, %rdx - orq %rdx, %rax - movq %rax, sev_status(%rip) - -.Lno_sev_mask: - movq %rbp, %rsp /* Restore original stack pointer */ - - pop %rdx - pop %rbp -#endif - - xor %rax, %rax - RET -SYM_FUNC_END(set_sev_encryption_mask) .data diff --git a/arch/x86/boot/compressed/misc.c b/arch/x86/boot/compressed/misc.c index 1cdcaf34ee36..cf690d8712f4 100644 --- a/arch/x86/boot/compressed/misc.c +++ b/arch/x86/boot/compressed/misc.c @@ -48,12 +48,17 @@ void *memmove(void *dest, const void *src, size_t n); */ struct boot_params *boot_params; +struct port_io_ops pio_ops; + memptr free_mem_ptr; memptr free_mem_end_ptr; static char *vidmem; static int vidport; -static int lines, cols; + +/* These might be accessed before .bss is cleared, so use .data instead. */ +static int lines __section(".data"); +static int cols __section(".data"); #ifdef CONFIG_KERNEL_GZIP #include "../../../../lib/decompress_inflate.c" @@ -371,6 +376,16 @@ asmlinkage __visible void *extract_kernel(void *rmode, memptr heap, lines = boot_params->screen_info.orig_video_lines; cols = boot_params->screen_info.orig_video_cols; + init_default_io_ops(); + + /* + * Detect TDX guest environment. + * + * It has to be done before console_init() in order to use + * paravirtualized port I/O operations if needed. + */ + early_tdx_detect(); + console_init(); /* diff --git a/arch/x86/boot/compressed/misc.h b/arch/x86/boot/compressed/misc.h index 16ed360b6692..4910bf230d7b 100644 --- a/arch/x86/boot/compressed/misc.h +++ b/arch/x86/boot/compressed/misc.h @@ -22,17 +22,21 @@ #include <linux/linkage.h> #include <linux/screen_info.h> #include <linux/elf.h> -#include <linux/io.h> #include <asm/page.h> #include <asm/boot.h> #include <asm/bootparam.h> #include <asm/desc_defs.h> +#include "tdx.h" + #define BOOT_CTYPE_H #include <linux/acpi.h> #define BOOT_BOOT_H #include "../ctype.h" +#include "../io.h" + +#include "efi.h" #ifdef CONFIG_X86_64 #define memptr long @@ -120,17 +124,23 @@ static inline void console_init(void) { } #endif -void set_sev_encryption_mask(void); - #ifdef CONFIG_AMD_MEM_ENCRYPT +void sev_enable(struct boot_params *bp); void sev_es_shutdown_ghcb(void); extern bool sev_es_check_ghcb_fault(unsigned long address); +void snp_set_page_private(unsigned long paddr); +void snp_set_page_shared(unsigned long paddr); +void sev_prep_identity_maps(unsigned long top_level_pgt); #else +static inline void sev_enable(struct boot_params *bp) { } static inline void sev_es_shutdown_ghcb(void) { } static inline bool sev_es_check_ghcb_fault(unsigned long address) { return false; } +static inline void snp_set_page_private(unsigned long paddr) { } +static inline void snp_set_page_shared(unsigned long paddr) { } +static inline void sev_prep_identity_maps(unsigned long top_level_pgt) { } #endif /* acpi.c */ @@ -151,6 +161,7 @@ static inline int count_immovable_mem_regions(void) { return 0; } #ifdef CONFIG_X86_5LEVEL extern unsigned int __pgtable_l5_enabled, pgdir_shift, ptrs_per_p4d; #endif +extern void kernel_add_identity_map(unsigned long start, unsigned long end); /* Used by PAGE_KERN* macros: */ extern pteval_t __default_kernel_pte_mask; @@ -172,4 +183,47 @@ void boot_stage2_vc(void); unsigned long sev_verify_cbit(unsigned long cr3); +enum efi_type { + EFI_TYPE_64, + EFI_TYPE_32, + EFI_TYPE_NONE, +}; + +#ifdef CONFIG_EFI +/* helpers for early EFI config table access */ +enum efi_type efi_get_type(struct boot_params *bp); +unsigned long efi_get_system_table(struct boot_params *bp); +int efi_get_conf_table(struct boot_params *bp, unsigned long *cfg_tbl_pa, + unsigned int *cfg_tbl_len); +unsigned long efi_find_vendor_table(struct boot_params *bp, + unsigned long cfg_tbl_pa, + unsigned int cfg_tbl_len, + efi_guid_t guid); +#else +static inline enum efi_type efi_get_type(struct boot_params *bp) +{ + return EFI_TYPE_NONE; +} + +static inline unsigned long efi_get_system_table(struct boot_params *bp) +{ + return 0; +} + +static inline int efi_get_conf_table(struct boot_params *bp, + unsigned long *cfg_tbl_pa, + unsigned int *cfg_tbl_len) +{ + return -ENOENT; +} + +static inline unsigned long efi_find_vendor_table(struct boot_params *bp, + unsigned long cfg_tbl_pa, + unsigned int cfg_tbl_len, + efi_guid_t guid) +{ + return 0; +} +#endif /* CONFIG_EFI */ + #endif /* BOOT_COMPRESSED_MISC_H */ diff --git a/arch/x86/boot/compressed/pgtable.h b/arch/x86/boot/compressed/pgtable.h index 6ff7e81b5628..cc9b2529a086 100644 --- a/arch/x86/boot/compressed/pgtable.h +++ b/arch/x86/boot/compressed/pgtable.h @@ -6,7 +6,7 @@ #define TRAMPOLINE_32BIT_PGTABLE_OFFSET 0 #define TRAMPOLINE_32BIT_CODE_OFFSET PAGE_SIZE -#define TRAMPOLINE_32BIT_CODE_SIZE 0x70 +#define TRAMPOLINE_32BIT_CODE_SIZE 0x80 #define TRAMPOLINE_32BIT_STACK_END TRAMPOLINE_32BIT_SIZE diff --git a/arch/x86/boot/compressed/pgtable_64.c b/arch/x86/boot/compressed/pgtable_64.c index a1733319a22a..2ac12ff4111b 100644 --- a/arch/x86/boot/compressed/pgtable_64.c +++ b/arch/x86/boot/compressed/pgtable_64.c @@ -1,11 +1,10 @@ // SPDX-License-Identifier: GPL-2.0 #include "misc.h" -#include <linux/efi.h> #include <asm/e820/types.h> #include <asm/processor.h> -#include <asm/efi.h> #include "pgtable.h" #include "../string.h" +#include "efi.h" #define BIOS_START_MIN 0x20000U /* 128K, less than this is insane */ #define BIOS_START_MAX 0x9f000U /* 640K, absolute maximum */ diff --git a/arch/x86/boot/compressed/sev.c b/arch/x86/boot/compressed/sev.c index 28bcf04c022e..52f989f6acc2 100644 --- a/arch/x86/boot/compressed/sev.c +++ b/arch/x86/boot/compressed/sev.c @@ -20,8 +20,10 @@ #include <asm/fpu/xcr.h> #include <asm/ptrace.h> #include <asm/svm.h> +#include <asm/cpuid.h> #include "error.h" +#include "../msr.h" struct ghcb boot_ghcb_page __aligned(PAGE_SIZE); struct ghcb *boot_ghcb; @@ -56,23 +58,19 @@ static unsigned long insn_get_seg_base(struct pt_regs *regs, int seg_reg_idx) static inline u64 sev_es_rd_ghcb_msr(void) { - unsigned long low, high; + struct msr m; - asm volatile("rdmsr" : "=a" (low), "=d" (high) : - "c" (MSR_AMD64_SEV_ES_GHCB)); + boot_rdmsr(MSR_AMD64_SEV_ES_GHCB, &m); - return ((high << 32) | low); + return m.q; } static inline void sev_es_wr_ghcb_msr(u64 val) { - u32 low, high; + struct msr m; - low = val & 0xffffffffUL; - high = val >> 32; - - asm volatile("wrmsr" : : "c" (MSR_AMD64_SEV_ES_GHCB), - "a"(low), "d" (high) : "memory"); + m.q = val; + boot_wrmsr(MSR_AMD64_SEV_ES_GHCB, &m); } static enum es_result vc_decode_insn(struct es_em_ctxt *ctxt) @@ -119,11 +117,54 @@ static enum es_result vc_read_mem(struct es_em_ctxt *ctxt, /* Include code for early handlers */ #include "../../kernel/sev-shared.c" -static bool early_setup_sev_es(void) +static inline bool sev_snp_enabled(void) +{ + return sev_status & MSR_AMD64_SEV_SNP_ENABLED; +} + +static void __page_state_change(unsigned long paddr, enum psc_op op) +{ + u64 val; + + if (!sev_snp_enabled()) + return; + + /* + * If private -> shared then invalidate the page before requesting the + * state change in the RMP table. + */ + if (op == SNP_PAGE_STATE_SHARED && pvalidate(paddr, RMP_PG_SIZE_4K, 0)) + sev_es_terminate(SEV_TERM_SET_LINUX, GHCB_TERM_PVALIDATE); + + /* Issue VMGEXIT to change the page state in RMP table. */ + sev_es_wr_ghcb_msr(GHCB_MSR_PSC_REQ_GFN(paddr >> PAGE_SHIFT, op)); + VMGEXIT(); + + /* Read the response of the VMGEXIT. */ + val = sev_es_rd_ghcb_msr(); + if ((GHCB_RESP_CODE(val) != GHCB_MSR_PSC_RESP) || GHCB_MSR_PSC_RESP_VAL(val)) + sev_es_terminate(SEV_TERM_SET_LINUX, GHCB_TERM_PSC); + + /* + * Now that page state is changed in the RMP table, validate it so that it is + * consistent with the RMP entry. + */ + if (op == SNP_PAGE_STATE_PRIVATE && pvalidate(paddr, RMP_PG_SIZE_4K, 1)) + sev_es_terminate(SEV_TERM_SET_LINUX, GHCB_TERM_PVALIDATE); +} + +void snp_set_page_private(unsigned long paddr) +{ + __page_state_change(paddr, SNP_PAGE_STATE_PRIVATE); +} + +void snp_set_page_shared(unsigned long paddr) { - if (!sev_es_negotiate_protocol()) - sev_es_terminate(GHCB_SEV_ES_PROT_UNSUPPORTED); + __page_state_change(paddr, SNP_PAGE_STATE_SHARED); +} +static bool early_setup_ghcb(void) +{ if (set_page_decrypted((unsigned long)&boot_ghcb_page)) return false; @@ -135,6 +176,10 @@ static bool early_setup_sev_es(void) /* Initialize lookup tables for the instruction decoder */ inat_init_tables(); + /* SNP guest requires the GHCB GPA must be registered */ + if (sev_snp_enabled()) + snp_register_ghcb_early(__pa(&boot_ghcb_page)); + return true; } @@ -174,8 +219,8 @@ void do_boot_stage2_vc(struct pt_regs *regs, unsigned long exit_code) struct es_em_ctxt ctxt; enum es_result result; - if (!boot_ghcb && !early_setup_sev_es()) - sev_es_terminate(GHCB_SEV_ES_GEN_REQ); + if (!boot_ghcb && !early_setup_ghcb()) + sev_es_terminate(SEV_TERM_SET_GEN, GHCB_SEV_ES_GEN_REQ); vc_ghcb_invalidate(boot_ghcb); result = vc_init_em_ctxt(&ctxt, regs, exit_code); @@ -202,5 +247,191 @@ finish: if (result == ES_OK) vc_finish_insn(&ctxt); else if (result != ES_RETRY) - sev_es_terminate(GHCB_SEV_ES_GEN_REQ); + sev_es_terminate(SEV_TERM_SET_GEN, GHCB_SEV_ES_GEN_REQ); +} + +static void enforce_vmpl0(void) +{ + u64 attrs; + int err; + + /* + * RMPADJUST modifies RMP permissions of a lesser-privileged (numerically + * higher) privilege level. Here, clear the VMPL1 permission mask of the + * GHCB page. If the guest is not running at VMPL0, this will fail. + * + * If the guest is running at VMPL0, it will succeed. Even if that operation + * modifies permission bits, it is still ok to do so currently because Linux + * SNP guests are supported only on VMPL0 so VMPL1 or higher permission masks + * changing is a don't-care. + */ + attrs = 1; + if (rmpadjust((unsigned long)&boot_ghcb_page, RMP_PG_SIZE_4K, attrs)) + sev_es_terminate(SEV_TERM_SET_LINUX, GHCB_TERM_NOT_VMPL0); +} + +void sev_enable(struct boot_params *bp) +{ + unsigned int eax, ebx, ecx, edx; + struct msr m; + bool snp; + + /* + * Setup/preliminary detection of SNP. This will be sanity-checked + * against CPUID/MSR values later. + */ + snp = snp_init(bp); + + /* Check for the SME/SEV support leaf */ + eax = 0x80000000; + ecx = 0; + native_cpuid(&eax, &ebx, &ecx, &edx); + if (eax < 0x8000001f) + return; + + /* + * Check for the SME/SEV feature: + * CPUID Fn8000_001F[EAX] + * - Bit 0 - Secure Memory Encryption support + * - Bit 1 - Secure Encrypted Virtualization support + * CPUID Fn8000_001F[EBX] + * - Bits 5:0 - Pagetable bit position used to indicate encryption + */ + eax = 0x8000001f; + ecx = 0; + native_cpuid(&eax, &ebx, &ecx, &edx); + /* Check whether SEV is supported */ + if (!(eax & BIT(1))) { + if (snp) + error("SEV-SNP support indicated by CC blob, but not CPUID."); + return; + } + + /* Set the SME mask if this is an SEV guest. */ + boot_rdmsr(MSR_AMD64_SEV, &m); + sev_status = m.q; + if (!(sev_status & MSR_AMD64_SEV_ENABLED)) + return; + + /* Negotiate the GHCB protocol version. */ + if (sev_status & MSR_AMD64_SEV_ES_ENABLED) { + if (!sev_es_negotiate_protocol()) + sev_es_terminate(SEV_TERM_SET_GEN, GHCB_SEV_ES_PROT_UNSUPPORTED); + } + + /* + * SNP is supported in v2 of the GHCB spec which mandates support for HV + * features. + */ + if (sev_status & MSR_AMD64_SEV_SNP_ENABLED) { + if (!(get_hv_features() & GHCB_HV_FT_SNP)) + sev_es_terminate(SEV_TERM_SET_GEN, GHCB_SNP_UNSUPPORTED); + + enforce_vmpl0(); + } + + if (snp && !(sev_status & MSR_AMD64_SEV_SNP_ENABLED)) + error("SEV-SNP supported indicated by CC blob, but not SEV status MSR."); + + sme_me_mask = BIT_ULL(ebx & 0x3f); +} + +/* Search for Confidential Computing blob in the EFI config table. */ +static struct cc_blob_sev_info *find_cc_blob_efi(struct boot_params *bp) +{ + unsigned long cfg_table_pa; + unsigned int cfg_table_len; + int ret; + + ret = efi_get_conf_table(bp, &cfg_table_pa, &cfg_table_len); + if (ret) + return NULL; + + return (struct cc_blob_sev_info *)efi_find_vendor_table(bp, cfg_table_pa, + cfg_table_len, + EFI_CC_BLOB_GUID); +} + +/* + * Initial set up of SNP relies on information provided by the + * Confidential Computing blob, which can be passed to the boot kernel + * by firmware/bootloader in the following ways: + * + * - via an entry in the EFI config table + * - via a setup_data structure, as defined by the Linux Boot Protocol + * + * Scan for the blob in that order. + */ +static struct cc_blob_sev_info *find_cc_blob(struct boot_params *bp) +{ + struct cc_blob_sev_info *cc_info; + + cc_info = find_cc_blob_efi(bp); + if (cc_info) + goto found_cc_info; + + cc_info = find_cc_blob_setup_data(bp); + if (!cc_info) + return NULL; + +found_cc_info: + if (cc_info->magic != CC_BLOB_SEV_HDR_MAGIC) + sev_es_terminate(SEV_TERM_SET_GEN, GHCB_SNP_UNSUPPORTED); + + return cc_info; +} + +/* + * Indicate SNP based on presence of SNP-specific CC blob. Subsequent checks + * will verify the SNP CPUID/MSR bits. + */ +bool snp_init(struct boot_params *bp) +{ + struct cc_blob_sev_info *cc_info; + + if (!bp) + return false; + + cc_info = find_cc_blob(bp); + if (!cc_info) + return false; + + /* + * If a SNP-specific Confidential Computing blob is present, then + * firmware/bootloader have indicated SNP support. Verifying this + * involves CPUID checks which will be more reliable if the SNP + * CPUID table is used. See comments over snp_setup_cpuid_table() for + * more details. + */ + setup_cpuid_table(cc_info); + + /* + * Pass run-time kernel a pointer to CC info via boot_params so EFI + * config table doesn't need to be searched again during early startup + * phase. + */ + bp->cc_blob_address = (u32)(unsigned long)cc_info; + + return true; +} + +void sev_prep_identity_maps(unsigned long top_level_pgt) +{ + /* + * The Confidential Computing blob is used very early in uncompressed + * kernel to find the in-memory CPUID table to handle CPUID + * instructions. Make sure an identity-mapping exists so it can be + * accessed after switchover. + */ + if (sev_snp_enabled()) { + unsigned long cc_info_pa = boot_params->cc_blob_address; + struct cc_blob_sev_info *cc_info; + + kernel_add_identity_map(cc_info_pa, cc_info_pa + sizeof(*cc_info)); + + cc_info = (struct cc_blob_sev_info *)cc_info_pa; + kernel_add_identity_map(cc_info->cpuid_phys, cc_info->cpuid_phys + cc_info->cpuid_len); + } + + sev_verify_cbit(top_level_pgt); } diff --git a/arch/x86/boot/compressed/tdcall.S b/arch/x86/boot/compressed/tdcall.S new file mode 100644 index 000000000000..46d0495e0d3a --- /dev/null +++ b/arch/x86/boot/compressed/tdcall.S @@ -0,0 +1,3 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +#include "../../coco/tdx/tdcall.S" diff --git a/arch/x86/boot/compressed/tdx.c b/arch/x86/boot/compressed/tdx.c new file mode 100644 index 000000000000..918a7606f53c --- /dev/null +++ b/arch/x86/boot/compressed/tdx.c @@ -0,0 +1,77 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include "../cpuflags.h" +#include "../string.h" +#include "../io.h" +#include "error.h" + +#include <vdso/limits.h> +#include <uapi/asm/vmx.h> + +#include <asm/shared/tdx.h> + +/* Called from __tdx_hypercall() for unrecoverable failure */ +void __tdx_hypercall_failed(void) +{ + error("TDVMCALL failed. TDX module bug?"); +} + +static inline unsigned int tdx_io_in(int size, u16 port) +{ + struct tdx_hypercall_args args = { + .r10 = TDX_HYPERCALL_STANDARD, + .r11 = EXIT_REASON_IO_INSTRUCTION, + .r12 = size, + .r13 = 0, + .r14 = port, + }; + + if (__tdx_hypercall(&args, TDX_HCALL_HAS_OUTPUT)) + return UINT_MAX; + + return args.r11; +} + +static inline void tdx_io_out(int size, u16 port, u32 value) +{ + struct tdx_hypercall_args args = { + .r10 = TDX_HYPERCALL_STANDARD, + .r11 = EXIT_REASON_IO_INSTRUCTION, + .r12 = size, + .r13 = 1, + .r14 = port, + .r15 = value, + }; + + __tdx_hypercall(&args, 0); +} + +static inline u8 tdx_inb(u16 port) +{ + return tdx_io_in(1, port); +} + +static inline void tdx_outb(u8 value, u16 port) +{ + tdx_io_out(1, port, value); +} + +static inline void tdx_outw(u16 value, u16 port) +{ + tdx_io_out(2, port, value); +} + +void early_tdx_detect(void) +{ + u32 eax, sig[3]; + + cpuid_count(TDX_CPUID_LEAF_ID, 0, &eax, &sig[0], &sig[2], &sig[1]); + + if (memcmp(TDX_IDENT, sig, sizeof(sig))) + return; + + /* Use hypercalls instead of I/O instructions */ + pio_ops.f_inb = tdx_inb; + pio_ops.f_outb = tdx_outb; + pio_ops.f_outw = tdx_outw; +} diff --git a/arch/x86/boot/compressed/tdx.h b/arch/x86/boot/compressed/tdx.h new file mode 100644 index 000000000000..9055482cd35c --- /dev/null +++ b/arch/x86/boot/compressed/tdx.h @@ -0,0 +1,13 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef BOOT_COMPRESSED_TDX_H +#define BOOT_COMPRESSED_TDX_H + +#include <linux/types.h> + +#ifdef CONFIG_INTEL_TDX_GUEST +void early_tdx_detect(void); +#else +static inline void early_tdx_detect(void) { }; +#endif + +#endif /* BOOT_COMPRESSED_TDX_H */ diff --git a/arch/x86/boot/cpucheck.c b/arch/x86/boot/cpucheck.c index e1478d32de1a..fed8d13ce252 100644 --- a/arch/x86/boot/cpucheck.c +++ b/arch/x86/boot/cpucheck.c @@ -27,6 +27,7 @@ #include <asm/required-features.h> #include <asm/msr-index.h> #include "string.h" +#include "msr.h" static u32 err_flags[NCAPINTS]; @@ -130,12 +131,11 @@ int check_cpu(int *cpu_level_ptr, int *req_level_ptr, u32 **err_flags_ptr) /* If this is an AMD and we're only missing SSE+SSE2, try to turn them on */ - u32 ecx = MSR_K7_HWCR; - u32 eax, edx; + struct msr m; - asm("rdmsr" : "=a" (eax), "=d" (edx) : "c" (ecx)); - eax &= ~(1 << 15); - asm("wrmsr" : : "a" (eax), "d" (edx), "c" (ecx)); + boot_rdmsr(MSR_K7_HWCR, &m); + m.l &= ~(1 << 15); + boot_wrmsr(MSR_K7_HWCR, &m); get_cpuflags(); /* Make sure it really did something */ err = check_cpuflags(); @@ -145,28 +145,28 @@ int check_cpu(int *cpu_level_ptr, int *req_level_ptr, u32 **err_flags_ptr) /* If this is a VIA C3, we might have to enable CX8 explicitly */ - u32 ecx = MSR_VIA_FCR; - u32 eax, edx; + struct msr m; - asm("rdmsr" : "=a" (eax), "=d" (edx) : "c" (ecx)); - eax |= (1<<1)|(1<<7); - asm("wrmsr" : : "a" (eax), "d" (edx), "c" (ecx)); + boot_rdmsr(MSR_VIA_FCR, &m); + m.l |= (1 << 1) | (1 << 7); + boot_wrmsr(MSR_VIA_FCR, &m); set_bit(X86_FEATURE_CX8, cpu.flags); err = check_cpuflags(); } else if (err == 0x01 && is_transmeta()) { /* Transmeta might have masked feature bits in word 0 */ - u32 ecx = 0x80860004; - u32 eax, edx; + struct msr m, m_tmp; u32 level = 1; - asm("rdmsr" : "=a" (eax), "=d" (edx) : "c" (ecx)); - asm("wrmsr" : : "a" (~0), "d" (edx), "c" (ecx)); + boot_rdmsr(0x80860004, &m); + m_tmp = m; + m_tmp.l = ~0; + boot_wrmsr(0x80860004, &m_tmp); asm("cpuid" : "+a" (level), "=d" (cpu.flags[0]) : : "ecx", "ebx"); - asm("wrmsr" : : "a" (eax), "d" (edx), "c" (ecx)); + boot_wrmsr(0x80860004, &m); err = check_cpuflags(); } else if (err == 0x01 && diff --git a/arch/x86/boot/cpuflags.c b/arch/x86/boot/cpuflags.c index a0b75f73dc63..a83d67ec627d 100644 --- a/arch/x86/boot/cpuflags.c +++ b/arch/x86/boot/cpuflags.c @@ -71,8 +71,7 @@ int has_eflag(unsigned long mask) # define EBX_REG "=b" #endif -static inline void cpuid_count(u32 id, u32 count, - u32 *a, u32 *b, u32 *c, u32 *d) +void cpuid_count(u32 id, u32 count, u32 *a, u32 *b, u32 *c, u32 *d) { asm volatile(".ifnc %%ebx,%3 ; movl %%ebx,%3 ; .endif \n\t" "cpuid \n\t" diff --git a/arch/x86/boot/cpuflags.h b/arch/x86/boot/cpuflags.h index 2e20814d3ce3..475b8fde90f7 100644 --- a/arch/x86/boot/cpuflags.h +++ b/arch/x86/boot/cpuflags.h @@ -17,5 +17,6 @@ extern u32 cpu_vendor[3]; int has_eflag(unsigned long mask); void get_cpuflags(void); +void cpuid_count(u32 id, u32 count, u32 *a, u32 *b, u32 *c, u32 *d); #endif diff --git a/arch/x86/boot/header.S b/arch/x86/boot/header.S index 6dbd7e9f74c9..0352e4589efa 100644 --- a/arch/x86/boot/header.S +++ b/arch/x86/boot/header.S @@ -163,7 +163,11 @@ extra_header_fields: .long 0x200 # SizeOfHeaders .long 0 # CheckSum .word IMAGE_SUBSYSTEM_EFI_APPLICATION # Subsystem (EFI application) +#ifdef CONFIG_DXE_MEM_ATTRIBUTES + .word IMAGE_DLL_CHARACTERISTICS_NX_COMPAT # DllCharacteristics +#else .word 0 # DllCharacteristics +#endif #ifdef CONFIG_X86_32 .long 0 # SizeOfStackReserve .long 0 # SizeOfStackCommit diff --git a/arch/x86/boot/io.h b/arch/x86/boot/io.h new file mode 100644 index 000000000000..110880907f87 --- /dev/null +++ b/arch/x86/boot/io.h @@ -0,0 +1,41 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef BOOT_IO_H +#define BOOT_IO_H + +#include <asm/shared/io.h> + +#undef inb +#undef inw +#undef inl +#undef outb +#undef outw +#undef outl + +struct port_io_ops { + u8 (*f_inb)(u16 port); + void (*f_outb)(u8 v, u16 port); + void (*f_outw)(u16 v, u16 port); +}; + +extern struct port_io_ops pio_ops; + +/* + * Use the normal I/O instructions by default. + * TDX guests override these to use hypercalls. + */ +static inline void init_default_io_ops(void) +{ + pio_ops.f_inb = __inb; + pio_ops.f_outb = __outb; + pio_ops.f_outw = __outw; +} + +/* + * Redirect port I/O operations via pio_ops callbacks. + * TDX guests override these callbacks with TDX-specific helpers. + */ +#define inb pio_ops.f_inb +#define outb pio_ops.f_outb +#define outw pio_ops.f_outw + +#endif diff --git a/arch/x86/boot/main.c b/arch/x86/boot/main.c index e3add857c2c9..c4ea5258ab55 100644 --- a/arch/x86/boot/main.c +++ b/arch/x86/boot/main.c @@ -17,6 +17,8 @@ struct boot_params boot_params __attribute__((aligned(16))); +struct port_io_ops pio_ops; + char *HEAP = _end; char *heap_end = _end; /* Default end of heap = no heap */ @@ -33,7 +35,7 @@ static void copy_boot_params(void) u16 cl_offset; }; const struct old_cmdline * const oldcmd = - (const struct old_cmdline *)OLD_CL_ADDRESS; + absolute_pointer(OLD_CL_ADDRESS); BUILD_BUG_ON(sizeof(boot_params) != 4096); memcpy(&boot_params.hdr, &hdr, sizeof(hdr)); @@ -133,6 +135,8 @@ static void init_heap(void) void main(void) { + init_default_io_ops(); + /* First, copy the boot header into the "zeropage" */ copy_boot_params(); diff --git a/arch/x86/boot/msr.h b/arch/x86/boot/msr.h new file mode 100644 index 000000000000..aed66f7ae199 --- /dev/null +++ b/arch/x86/boot/msr.h @@ -0,0 +1,26 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Helpers/definitions related to MSR access. + */ + +#ifndef BOOT_MSR_H +#define BOOT_MSR_H + +#include <asm/shared/msr.h> + +/* + * The kernel proper already defines rdmsr()/wrmsr(), but they are not for the + * boot kernel since they rely on tracepoint/exception handling infrastructure + * that's not available here. + */ +static inline void boot_rdmsr(unsigned int reg, struct msr *m) +{ + asm volatile("rdmsr" : "=a" (m->l), "=d" (m->h) : "c" (reg)); +} + +static inline void boot_wrmsr(unsigned int reg, const struct msr *m) +{ + asm volatile("wrmsr" : : "c" (reg), "a"(m->l), "d" (m->h) : "memory"); +} + +#endif /* BOOT_MSR_H */ diff --git a/arch/x86/coco/Makefile b/arch/x86/coco/Makefile index c1ead00017a7..c816acf78b6a 100644 --- a/arch/x86/coco/Makefile +++ b/arch/x86/coco/Makefile @@ -4,3 +4,5 @@ KASAN_SANITIZE_core.o := n CFLAGS_core.o += -fno-stack-protector obj-y += core.o + +obj-$(CONFIG_INTEL_TDX_GUEST) += tdx/ diff --git a/arch/x86/coco/core.c b/arch/x86/coco/core.c index fc1365dd927e..49b44f881484 100644 --- a/arch/x86/coco/core.c +++ b/arch/x86/coco/core.c @@ -18,7 +18,15 @@ static u64 cc_mask __ro_after_init; static bool intel_cc_platform_has(enum cc_attr attr) { - return false; + switch (attr) { + case CC_ATTR_GUEST_UNROLL_STRING_IO: + case CC_ATTR_HOTPLUG_DISABLED: + case CC_ATTR_GUEST_MEM_ENCRYPT: + case CC_ATTR_MEM_ENCRYPT: + return true; + default: + return false; + } } /* @@ -57,6 +65,9 @@ static bool amd_cc_platform_has(enum cc_attr attr) return (sev_status & MSR_AMD64_SEV_ENABLED) && !(sev_status & MSR_AMD64_SEV_ES_ENABLED); + case CC_ATTR_GUEST_SEV_SNP: + return sev_status & MSR_AMD64_SEV_SNP_ENABLED; + default: return false; } @@ -87,9 +98,18 @@ EXPORT_SYMBOL_GPL(cc_platform_has); u64 cc_mkenc(u64 val) { + /* + * Both AMD and Intel use a bit in the page table to indicate + * encryption status of the page. + * + * - for AMD, bit *set* means the page is encrypted + * - for Intel *clear* means encrypted. + */ switch (vendor) { case CC_VENDOR_AMD: return val | cc_mask; + case CC_VENDOR_INTEL: + return val & ~cc_mask; default: return val; } @@ -97,9 +117,12 @@ u64 cc_mkenc(u64 val) u64 cc_mkdec(u64 val) { + /* See comment in cc_mkenc() */ switch (vendor) { case CC_VENDOR_AMD: return val & ~cc_mask; + case CC_VENDOR_INTEL: + return val | cc_mask; default: return val; } diff --git a/arch/x86/coco/tdx/Makefile b/arch/x86/coco/tdx/Makefile new file mode 100644 index 000000000000..46c55998557d --- /dev/null +++ b/arch/x86/coco/tdx/Makefile @@ -0,0 +1,3 @@ +# SPDX-License-Identifier: GPL-2.0 + +obj-y += tdx.o tdcall.o diff --git a/arch/x86/coco/tdx/tdcall.S b/arch/x86/coco/tdx/tdcall.S new file mode 100644 index 000000000000..f9eb1134f22d --- /dev/null +++ b/arch/x86/coco/tdx/tdcall.S @@ -0,0 +1,205 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#include <asm/asm-offsets.h> +#include <asm/asm.h> +#include <asm/frame.h> +#include <asm/unwind_hints.h> + +#include <linux/linkage.h> +#include <linux/bits.h> +#include <linux/errno.h> + +#include "../../virt/vmx/tdx/tdxcall.S" + +/* + * Bitmasks of exposed registers (with VMM). + */ +#define TDX_R10 BIT(10) +#define TDX_R11 BIT(11) +#define TDX_R12 BIT(12) +#define TDX_R13 BIT(13) +#define TDX_R14 BIT(14) +#define TDX_R15 BIT(15) + +/* + * These registers are clobbered to hold arguments for each + * TDVMCALL. They are safe to expose to the VMM. + * Each bit in this mask represents a register ID. Bit field + * details can be found in TDX GHCI specification, section + * titled "TDCALL [TDG.VP.VMCALL] leaf". + */ +#define TDVMCALL_EXPOSE_REGS_MASK ( TDX_R10 | TDX_R11 | \ + TDX_R12 | TDX_R13 | \ + TDX_R14 | TDX_R15 ) + +/* + * __tdx_module_call() - Used by TDX guests to request services from + * the TDX module (does not include VMM services) using TDCALL instruction. + * + * Transforms function call register arguments into the TDCALL register ABI. + * After TDCALL operation, TDX module output is saved in @out (if it is + * provided by the user). + * + *------------------------------------------------------------------------- + * TDCALL ABI: + *------------------------------------------------------------------------- + * Input Registers: + * + * RAX - TDCALL Leaf number. + * RCX,RDX,R8-R9 - TDCALL Leaf specific input registers. + * + * Output Registers: + * + * RAX - TDCALL instruction error code. + * RCX,RDX,R8-R11 - TDCALL Leaf specific output registers. + * + *------------------------------------------------------------------------- + * + * __tdx_module_call() function ABI: + * + * @fn (RDI) - TDCALL Leaf ID, moved to RAX + * @rcx (RSI) - Input parameter 1, moved to RCX + * @rdx (RDX) - Input parameter 2, moved to RDX + * @r8 (RCX) - Input parameter 3, moved to R8 + * @r9 (R8) - Input parameter 4, moved to R9 + * + * @out (R9) - struct tdx_module_output pointer + * stored temporarily in R12 (not + * shared with the TDX module). It + * can be NULL. + * + * Return status of TDCALL via RAX. + */ +SYM_FUNC_START(__tdx_module_call) + FRAME_BEGIN + TDX_MODULE_CALL host=0 + FRAME_END + RET +SYM_FUNC_END(__tdx_module_call) + +/* + * __tdx_hypercall() - Make hypercalls to a TDX VMM using TDVMCALL leaf + * of TDCALL instruction + * + * Transforms values in function call argument struct tdx_hypercall_args @args + * into the TDCALL register ABI. After TDCALL operation, VMM output is saved + * back in @args. + * + *------------------------------------------------------------------------- + * TD VMCALL ABI: + *------------------------------------------------------------------------- + * + * Input Registers: + * + * RAX - TDCALL instruction leaf number (0 - TDG.VP.VMCALL) + * RCX - BITMAP which controls which part of TD Guest GPR + * is passed as-is to the VMM and back. + * R10 - Set 0 to indicate TDCALL follows standard TDX ABI + * specification. Non zero value indicates vendor + * specific ABI. + * R11 - VMCALL sub function number + * RBX, RBP, RDI, RSI - Used to pass VMCALL sub function specific arguments. + * R8-R9, R12-R15 - Same as above. + * + * Output Registers: + * + * RAX - TDCALL instruction status (Not related to hypercall + * output). + * R10 - Hypercall output error code. + * R11-R15 - Hypercall sub function specific output values. + * + *------------------------------------------------------------------------- + * + * __tdx_hypercall() function ABI: + * + * @args (RDI) - struct tdx_hypercall_args for input and output + * @flags (RSI) - TDX_HCALL_* flags + * + * On successful completion, return the hypercall error code. + */ +SYM_FUNC_START(__tdx_hypercall) + FRAME_BEGIN + + /* Save callee-saved GPRs as mandated by the x86_64 ABI */ + push %r15 + push %r14 + push %r13 + push %r12 + + /* Mangle function call ABI into TDCALL ABI: */ + /* Set TDCALL leaf ID (TDVMCALL (0)) in RAX */ + xor %eax, %eax + + /* Copy hypercall registers from arg struct: */ + movq TDX_HYPERCALL_r10(%rdi), %r10 + movq TDX_HYPERCALL_r11(%rdi), %r11 + movq TDX_HYPERCALL_r12(%rdi), %r12 + movq TDX_HYPERCALL_r13(%rdi), %r13 + movq TDX_HYPERCALL_r14(%rdi), %r14 + movq TDX_HYPERCALL_r15(%rdi), %r15 + + movl $TDVMCALL_EXPOSE_REGS_MASK, %ecx + + /* + * For the idle loop STI needs to be called directly before the TDCALL + * that enters idle (EXIT_REASON_HLT case). STI instruction enables + * interrupts only one instruction later. If there is a window between + * STI and the instruction that emulates the HALT state, there is a + * chance for interrupts to happen in this window, which can delay the + * HLT operation indefinitely. Since this is the not the desired + * result, conditionally call STI before TDCALL. + */ + testq $TDX_HCALL_ISSUE_STI, %rsi + jz .Lskip_sti + sti +.Lskip_sti: + tdcall + + /* + * RAX==0 indicates a failure of the TDVMCALL mechanism itself and that + * something has gone horribly wrong with the TDX module. + * + * The return status of the hypercall operation is in a separate + * register (in R10). Hypercall errors are a part of normal operation + * and are handled by callers. + */ + testq %rax, %rax + jne .Lpanic + + /* TDVMCALL leaf return code is in R10 */ + movq %r10, %rax + + /* Copy hypercall result registers to arg struct if needed */ + testq $TDX_HCALL_HAS_OUTPUT, %rsi + jz .Lout + + movq %r10, TDX_HYPERCALL_r10(%rdi) + movq %r11, TDX_HYPERCALL_r11(%rdi) + movq %r12, TDX_HYPERCALL_r12(%rdi) + movq %r13, TDX_HYPERCALL_r13(%rdi) + movq %r14, TDX_HYPERCALL_r14(%rdi) + movq %r15, TDX_HYPERCALL_r15(%rdi) +.Lout: + /* + * Zero out registers exposed to the VMM to avoid speculative execution + * with VMM-controlled values. This needs to include all registers + * present in TDVMCALL_EXPOSE_REGS_MASK (except R12-R15). R12-R15 + * context will be restored. + */ + xor %r10d, %r10d + xor %r11d, %r11d + + /* Restore callee-saved GPRs as mandated by the x86_64 ABI */ + pop %r12 + pop %r13 + pop %r14 + pop %r15 + + FRAME_END + + RET +.Lpanic: + call __tdx_hypercall_failed + /* __tdx_hypercall_failed never returns */ + REACHABLE + jmp .Lpanic +SYM_FUNC_END(__tdx_hypercall) diff --git a/arch/x86/coco/tdx/tdx.c b/arch/x86/coco/tdx/tdx.c new file mode 100644 index 000000000000..03deb4d6920d --- /dev/null +++ b/arch/x86/coco/tdx/tdx.c @@ -0,0 +1,692 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (C) 2021-2022 Intel Corporation */ + +#undef pr_fmt +#define pr_fmt(fmt) "tdx: " fmt + +#include <linux/cpufeature.h> +#include <asm/coco.h> +#include <asm/tdx.h> +#include <asm/vmx.h> +#include <asm/insn.h> +#include <asm/insn-eval.h> +#include <asm/pgtable.h> + +/* TDX module Call Leaf IDs */ +#define TDX_GET_INFO 1 +#define TDX_GET_VEINFO 3 +#define TDX_ACCEPT_PAGE 6 + +/* TDX hypercall Leaf IDs */ +#define TDVMCALL_MAP_GPA 0x10001 + +/* MMIO direction */ +#define EPT_READ 0 +#define EPT_WRITE 1 + +/* Port I/O direction */ +#define PORT_READ 0 +#define PORT_WRITE 1 + +/* See Exit Qualification for I/O Instructions in VMX documentation */ +#define VE_IS_IO_IN(e) ((e) & BIT(3)) +#define VE_GET_IO_SIZE(e) (((e) & GENMASK(2, 0)) + 1) +#define VE_GET_PORT_NUM(e) ((e) >> 16) +#define VE_IS_IO_STRING(e) ((e) & BIT(4)) + +/* + * Wrapper for standard use of __tdx_hypercall with no output aside from + * return code. + */ +static inline u64 _tdx_hypercall(u64 fn, u64 r12, u64 r13, u64 r14, u64 r15) +{ + struct tdx_hypercall_args args = { + .r10 = TDX_HYPERCALL_STANDARD, + .r11 = fn, + .r12 = r12, + .r13 = r13, + .r14 = r14, + .r15 = r15, + }; + + return __tdx_hypercall(&args, 0); +} + +/* Called from __tdx_hypercall() for unrecoverable failure */ +void __tdx_hypercall_failed(void) +{ + panic("TDVMCALL failed. TDX module bug?"); +} + +/* + * The TDG.VP.VMCALL-Instruction-execution sub-functions are defined + * independently from but are currently matched 1:1 with VMX EXIT_REASONs. + * Reusing the KVM EXIT_REASON macros makes it easier to connect the host and + * guest sides of these calls. + */ +static u64 hcall_func(u64 exit_reason) +{ + return exit_reason; +} + +#ifdef CONFIG_KVM_GUEST +long tdx_kvm_hypercall(unsigned int nr, unsigned long p1, unsigned long p2, + unsigned long p3, unsigned long p4) +{ + struct tdx_hypercall_args args = { + .r10 = nr, + .r11 = p1, + .r12 = p2, + .r13 = p3, + .r14 = p4, + }; + + return __tdx_hypercall(&args, 0); +} +EXPORT_SYMBOL_GPL(tdx_kvm_hypercall); +#endif + +/* + * Used for TDX guests to make calls directly to the TD module. This + * should only be used for calls that have no legitimate reason to fail + * or where the kernel can not survive the call failing. + */ +static inline void tdx_module_call(u64 fn, u64 rcx, u64 rdx, u64 r8, u64 r9, + struct tdx_module_output *out) +{ + if (__tdx_module_call(fn, rcx, rdx, r8, r9, out)) + panic("TDCALL %lld failed (Buggy TDX module!)\n", fn); +} + +static u64 get_cc_mask(void) +{ + struct tdx_module_output out; + unsigned int gpa_width; + + /* + * TDINFO TDX module call is used to get the TD execution environment + * information like GPA width, number of available vcpus, debug mode + * information, etc. More details about the ABI can be found in TDX + * Guest-Host-Communication Interface (GHCI), section 2.4.2 TDCALL + * [TDG.VP.INFO]. + * + * The GPA width that comes out of this call is critical. TDX guests + * can not meaningfully run without it. + */ + tdx_module_call(TDX_GET_INFO, 0, 0, 0, 0, &out); + + gpa_width = out.rcx & GENMASK(5, 0); + + /* + * The highest bit of a guest physical address is the "sharing" bit. + * Set it for shared pages and clear it for private pages. + */ + return BIT_ULL(gpa_width - 1); +} + +static u64 __cpuidle __halt(const bool irq_disabled, const bool do_sti) +{ + struct tdx_hypercall_args args = { + .r10 = TDX_HYPERCALL_STANDARD, + .r11 = hcall_func(EXIT_REASON_HLT), + .r12 = irq_disabled, + }; + + /* + * Emulate HLT operation via hypercall. More info about ABI + * can be found in TDX Guest-Host-Communication Interface + * (GHCI), section 3.8 TDG.VP.VMCALL<Instruction.HLT>. + * + * The VMM uses the "IRQ disabled" param to understand IRQ + * enabled status (RFLAGS.IF) of the TD guest and to determine + * whether or not it should schedule the halted vCPU if an + * IRQ becomes pending. E.g. if IRQs are disabled, the VMM + * can keep the vCPU in virtual HLT, even if an IRQ is + * pending, without hanging/breaking the guest. + */ + return __tdx_hypercall(&args, do_sti ? TDX_HCALL_ISSUE_STI : 0); +} + +static bool handle_halt(void) +{ + /* + * Since non safe halt is mainly used in CPU offlining + * and the guest will always stay in the halt state, don't + * call the STI instruction (set do_sti as false). + */ + const bool irq_disabled = irqs_disabled(); + const bool do_sti = false; + + if (__halt(irq_disabled, do_sti)) + return false; + + return true; +} + +void __cpuidle tdx_safe_halt(void) +{ + /* + * For do_sti=true case, __tdx_hypercall() function enables + * interrupts using the STI instruction before the TDCALL. So + * set irq_disabled as false. + */ + const bool irq_disabled = false; + const bool do_sti = true; + + /* + * Use WARN_ONCE() to report the failure. + */ + if (__halt(irq_disabled, do_sti)) + WARN_ONCE(1, "HLT instruction emulation failed\n"); +} + +static bool read_msr(struct pt_regs *regs) +{ + struct tdx_hypercall_args args = { + .r10 = TDX_HYPERCALL_STANDARD, + .r11 = hcall_func(EXIT_REASON_MSR_READ), + .r12 = regs->cx, + }; + + /* + * Emulate the MSR read via hypercall. More info about ABI + * can be found in TDX Guest-Host-Communication Interface + * (GHCI), section titled "TDG.VP.VMCALL<Instruction.RDMSR>". + */ + if (__tdx_hypercall(&args, TDX_HCALL_HAS_OUTPUT)) + return false; + + regs->ax = lower_32_bits(args.r11); + regs->dx = upper_32_bits(args.r11); + return true; +} + +static bool write_msr(struct pt_regs *regs) +{ + struct tdx_hypercall_args args = { + .r10 = TDX_HYPERCALL_STANDARD, + .r11 = hcall_func(EXIT_REASON_MSR_WRITE), + .r12 = regs->cx, + .r13 = (u64)regs->dx << 32 | regs->ax, + }; + + /* + * Emulate the MSR write via hypercall. More info about ABI + * can be found in TDX Guest-Host-Communication Interface + * (GHCI) section titled "TDG.VP.VMCALL<Instruction.WRMSR>". + */ + return !__tdx_hypercall(&args, 0); +} + +static bool handle_cpuid(struct pt_regs *regs) +{ + struct tdx_hypercall_args args = { + .r10 = TDX_HYPERCALL_STANDARD, + .r11 = hcall_func(EXIT_REASON_CPUID), + .r12 = regs->ax, + .r13 = regs->cx, + }; + + /* + * Only allow VMM to control range reserved for hypervisor + * communication. + * + * Return all-zeros for any CPUID outside the range. It matches CPU + * behaviour for non-supported leaf. + */ + if (regs->ax < 0x40000000 || regs->ax > 0x4FFFFFFF) { + regs->ax = regs->bx = regs->cx = regs->dx = 0; + return true; + } + + /* + * Emulate the CPUID instruction via a hypercall. More info about + * ABI can be found in TDX Guest-Host-Communication Interface + * (GHCI), section titled "VP.VMCALL<Instruction.CPUID>". + */ + if (__tdx_hypercall(&args, TDX_HCALL_HAS_OUTPUT)) + return false; + + /* + * As per TDX GHCI CPUID ABI, r12-r15 registers contain contents of + * EAX, EBX, ECX, EDX registers after the CPUID instruction execution. + * So copy the register contents back to pt_regs. + */ + regs->ax = args.r12; + regs->bx = args.r13; + regs->cx = args.r14; + regs->dx = args.r15; + + return true; +} + +static bool mmio_read(int size, unsigned long addr, unsigned long *val) +{ + struct tdx_hypercall_args args = { + .r10 = TDX_HYPERCALL_STANDARD, + .r11 = hcall_func(EXIT_REASON_EPT_VIOLATION), + .r12 = size, + .r13 = EPT_READ, + .r14 = addr, + .r15 = *val, + }; + + if (__tdx_hypercall(&args, TDX_HCALL_HAS_OUTPUT)) + return false; + *val = args.r11; + return true; +} + +static bool mmio_write(int size, unsigned long addr, unsigned long val) +{ + return !_tdx_hypercall(hcall_func(EXIT_REASON_EPT_VIOLATION), size, + EPT_WRITE, addr, val); +} + +static bool handle_mmio(struct pt_regs *regs, struct ve_info *ve) +{ + char buffer[MAX_INSN_SIZE]; + unsigned long *reg, val; + struct insn insn = {}; + enum mmio_type mmio; + int size, extend_size; + u8 extend_val = 0; + + /* Only in-kernel MMIO is supported */ + if (WARN_ON_ONCE(user_mode(regs))) + return false; + + if (copy_from_kernel_nofault(buffer, (void *)regs->ip, MAX_INSN_SIZE)) + return false; + + if (insn_decode(&insn, buffer, MAX_INSN_SIZE, INSN_MODE_64)) + return false; + + mmio = insn_decode_mmio(&insn, &size); + if (WARN_ON_ONCE(mmio == MMIO_DECODE_FAILED)) + return false; + + if (mmio != MMIO_WRITE_IMM && mmio != MMIO_MOVS) { + reg = insn_get_modrm_reg_ptr(&insn, regs); + if (!reg) + return false; + } + + ve->instr_len = insn.length; + + /* Handle writes first */ + switch (mmio) { + case MMIO_WRITE: + memcpy(&val, reg, size); + return mmio_write(size, ve->gpa, val); + case MMIO_WRITE_IMM: + val = insn.immediate.value; + return mmio_write(size, ve->gpa, val); + case MMIO_READ: + case MMIO_READ_ZERO_EXTEND: + case MMIO_READ_SIGN_EXTEND: + /* Reads are handled below */ + break; + case MMIO_MOVS: + case MMIO_DECODE_FAILED: + /* + * MMIO was accessed with an instruction that could not be + * decoded or handled properly. It was likely not using io.h + * helpers or accessed MMIO accidentally. + */ + return false; + default: + WARN_ONCE(1, "Unknown insn_decode_mmio() decode value?"); + return false; + } + + /* Handle reads */ + if (!mmio_read(size, ve->gpa, &val)) + return false; + + switch (mmio) { + case MMIO_READ: + /* Zero-extend for 32-bit operation */ + extend_size = size == 4 ? sizeof(*reg) : 0; + break; + case MMIO_READ_ZERO_EXTEND: + /* Zero extend based on operand size */ + extend_size = insn.opnd_bytes; + break; + case MMIO_READ_SIGN_EXTEND: + /* Sign extend based on operand size */ + extend_size = insn.opnd_bytes; + if (size == 1 && val & BIT(7)) + extend_val = 0xFF; + else if (size > 1 && val & BIT(15)) + extend_val = 0xFF; + break; + default: + /* All other cases has to be covered with the first switch() */ + WARN_ON_ONCE(1); + return false; + } + + if (extend_size) + memset(reg, extend_val, extend_size); + memcpy(reg, &val, size); + return true; +} + +static bool handle_in(struct pt_regs *regs, int size, int port) +{ + struct tdx_hypercall_args args = { + .r10 = TDX_HYPERCALL_STANDARD, + .r11 = hcall_func(EXIT_REASON_IO_INSTRUCTION), + .r12 = size, + .r13 = PORT_READ, + .r14 = port, + }; + u64 mask = GENMASK(BITS_PER_BYTE * size, 0); + bool success; + + /* + * Emulate the I/O read via hypercall. More info about ABI can be found + * in TDX Guest-Host-Communication Interface (GHCI) section titled + * "TDG.VP.VMCALL<Instruction.IO>". + */ + success = !__tdx_hypercall(&args, TDX_HCALL_HAS_OUTPUT); + + /* Update part of the register affected by the emulated instruction */ + regs->ax &= ~mask; + if (success) + regs->ax |= args.r11 & mask; + + return success; +} + +static bool handle_out(struct pt_regs *regs, int size, int port) +{ + u64 mask = GENMASK(BITS_PER_BYTE * size, 0); + + /* + * Emulate the I/O write via hypercall. More info about ABI can be found + * in TDX Guest-Host-Communication Interface (GHCI) section titled + * "TDG.VP.VMCALL<Instruction.IO>". + */ + return !_tdx_hypercall(hcall_func(EXIT_REASON_IO_INSTRUCTION), size, + PORT_WRITE, port, regs->ax & mask); +} + +/* + * Emulate I/O using hypercall. + * + * Assumes the IO instruction was using ax, which is enforced + * by the standard io.h macros. + * + * Return True on success or False on failure. + */ +static bool handle_io(struct pt_regs *regs, u32 exit_qual) +{ + int size, port; + bool in; + + if (VE_IS_IO_STRING(exit_qual)) + return false; + + in = VE_IS_IO_IN(exit_qual); + size = VE_GET_IO_SIZE(exit_qual); + port = VE_GET_PORT_NUM(exit_qual); + + + if (in) + return handle_in(regs, size, port); + else + return handle_out(regs, size, port); +} + +/* + * Early #VE exception handler. Only handles a subset of port I/O. + * Intended only for earlyprintk. If failed, return false. + */ +__init bool tdx_early_handle_ve(struct pt_regs *regs) +{ + struct ve_info ve; + + tdx_get_ve_info(&ve); + + if (ve.exit_reason != EXIT_REASON_IO_INSTRUCTION) + return false; + + return handle_io(regs, ve.exit_qual); +} + +void tdx_get_ve_info(struct ve_info *ve) +{ + struct tdx_module_output out; + + /* + * Called during #VE handling to retrieve the #VE info from the + * TDX module. + * + * This has to be called early in #VE handling. A "nested" #VE which + * occurs before this will raise a #DF and is not recoverable. + * + * The call retrieves the #VE info from the TDX module, which also + * clears the "#VE valid" flag. This must be done before anything else + * because any #VE that occurs while the valid flag is set will lead to + * #DF. + * + * Note, the TDX module treats virtual NMIs as inhibited if the #VE + * valid flag is set. It means that NMI=>#VE will not result in a #DF. + */ + tdx_module_call(TDX_GET_VEINFO, 0, 0, 0, 0, &out); + + /* Transfer the output parameters */ + ve->exit_reason = out.rcx; + ve->exit_qual = out.rdx; + ve->gla = out.r8; + ve->gpa = out.r9; + ve->instr_len = lower_32_bits(out.r10); + ve->instr_info = upper_32_bits(out.r10); +} + +/* Handle the user initiated #VE */ +static bool virt_exception_user(struct pt_regs *regs, struct ve_info *ve) +{ + switch (ve->exit_reason) { + case EXIT_REASON_CPUID: + return handle_cpuid(regs); + default: + pr_warn("Unexpected #VE: %lld\n", ve->exit_reason); + return false; + } +} + +/* Handle the kernel #VE */ +static bool virt_exception_kernel(struct pt_regs *regs, struct ve_info *ve) +{ + switch (ve->exit_reason) { + case EXIT_REASON_HLT: + return handle_halt(); + case EXIT_REASON_MSR_READ: + return read_msr(regs); + case EXIT_REASON_MSR_WRITE: + return write_msr(regs); + case EXIT_REASON_CPUID: + return handle_cpuid(regs); + case EXIT_REASON_EPT_VIOLATION: + return handle_mmio(regs, ve); + case EXIT_REASON_IO_INSTRUCTION: + return handle_io(regs, ve->exit_qual); + default: + pr_warn("Unexpected #VE: %lld\n", ve->exit_reason); + return false; + } +} + +bool tdx_handle_virt_exception(struct pt_regs *regs, struct ve_info *ve) +{ + bool ret; + + if (user_mode(regs)) + ret = virt_exception_user(regs, ve); + else + ret = virt_exception_kernel(regs, ve); + + /* After successful #VE handling, move the IP */ + if (ret) + regs->ip += ve->instr_len; + + return ret; +} + +static bool tdx_tlb_flush_required(bool private) +{ + /* + * TDX guest is responsible for flushing TLB on private->shared + * transition. VMM is responsible for flushing on shared->private. + * + * The VMM _can't_ flush private addresses as it can't generate PAs + * with the guest's HKID. Shared memory isn't subject to integrity + * checking, i.e. the VMM doesn't need to flush for its own protection. + * + * There's no need to flush when converting from shared to private, + * as flushing is the VMM's responsibility in this case, e.g. it must + * flush to avoid integrity failures in the face of a buggy or + * malicious guest. + */ + return !private; +} + +static bool tdx_cache_flush_required(void) +{ + /* + * AMD SME/SEV can avoid cache flushing if HW enforces cache coherence. + * TDX doesn't have such capability. + * + * Flush cache unconditionally. + */ + return true; +} + +static bool try_accept_one(phys_addr_t *start, unsigned long len, + enum pg_level pg_level) +{ + unsigned long accept_size = page_level_size(pg_level); + u64 tdcall_rcx; + u8 page_size; + + if (!IS_ALIGNED(*start, accept_size)) + return false; + + if (len < accept_size) + return false; + + /* + * Pass the page physical address to the TDX module to accept the + * pending, private page. + * + * Bits 2:0 of RCX encode page size: 0 - 4K, 1 - 2M, 2 - 1G. + */ + switch (pg_level) { + case PG_LEVEL_4K: + page_size = 0; + break; + case PG_LEVEL_2M: + page_size = 1; + break; + case PG_LEVEL_1G: + page_size = 2; + break; + default: + return false; + } + + tdcall_rcx = *start | page_size; + if (__tdx_module_call(TDX_ACCEPT_PAGE, tdcall_rcx, 0, 0, 0, NULL)) + return false; + + *start += accept_size; + return true; +} + +/* + * Inform the VMM of the guest's intent for this physical page: shared with + * the VMM or private to the guest. The VMM is expected to change its mapping + * of the page in response. + */ +static bool tdx_enc_status_changed(unsigned long vaddr, int numpages, bool enc) +{ + phys_addr_t start = __pa(vaddr); + phys_addr_t end = __pa(vaddr + numpages * PAGE_SIZE); + + if (!enc) { + /* Set the shared (decrypted) bits: */ + start |= cc_mkdec(0); + end |= cc_mkdec(0); + } + + /* + * Notify the VMM about page mapping conversion. More info about ABI + * can be found in TDX Guest-Host-Communication Interface (GHCI), + * section "TDG.VP.VMCALL<MapGPA>" + */ + if (_tdx_hypercall(TDVMCALL_MAP_GPA, start, end - start, 0, 0)) + return false; + + /* private->shared conversion requires only MapGPA call */ + if (!enc) + return true; + + /* + * For shared->private conversion, accept the page using + * TDX_ACCEPT_PAGE TDX module call. + */ + while (start < end) { + unsigned long len = end - start; + + /* + * Try larger accepts first. It gives chance to VMM to keep + * 1G/2M SEPT entries where possible and speeds up process by + * cutting number of hypercalls (if successful). + */ + + if (try_accept_one(&start, len, PG_LEVEL_1G)) + continue; + + if (try_accept_one(&start, len, PG_LEVEL_2M)) + continue; + + if (!try_accept_one(&start, len, PG_LEVEL_4K)) + return false; + } + + return true; +} + +void __init tdx_early_init(void) +{ + u64 cc_mask; + u32 eax, sig[3]; + + cpuid_count(TDX_CPUID_LEAF_ID, 0, &eax, &sig[0], &sig[2], &sig[1]); + + if (memcmp(TDX_IDENT, sig, sizeof(sig))) + return; + + setup_force_cpu_cap(X86_FEATURE_TDX_GUEST); + + cc_set_vendor(CC_VENDOR_INTEL); + cc_mask = get_cc_mask(); + cc_set_mask(cc_mask); + + /* + * All bits above GPA width are reserved and kernel treats shared bit + * as flag, not as part of physical address. + * + * Adjust physical mask to only cover valid GPA bits. + */ + physical_mask &= cc_mask - 1; + + x86_platform.guest.enc_cache_flush_required = tdx_cache_flush_required; + x86_platform.guest.enc_tlb_flush_required = tdx_tlb_flush_required; + x86_platform.guest.enc_status_change_finish = tdx_enc_status_changed; + + pr_info("Guest detected\n"); +} diff --git a/arch/x86/entry/calling.h b/arch/x86/entry/calling.h index a4c061fb7c6e..29b36e9e4e74 100644 --- a/arch/x86/entry/calling.h +++ b/arch/x86/entry/calling.h @@ -63,7 +63,7 @@ For 32-bit we have the following conventions - kernel is built with * for assembly code: */ -.macro PUSH_REGS rdx=%rdx rax=%rax save_ret=0 +.macro PUSH_REGS rdx=%rdx rcx=%rcx rax=%rax save_ret=0 .if \save_ret pushq %rsi /* pt_regs->si */ movq 8(%rsp), %rsi /* temporarily store the return address in %rsi */ @@ -73,7 +73,7 @@ For 32-bit we have the following conventions - kernel is built with pushq %rsi /* pt_regs->si */ .endif pushq \rdx /* pt_regs->dx */ - pushq %rcx /* pt_regs->cx */ + pushq \rcx /* pt_regs->cx */ pushq \rax /* pt_regs->ax */ pushq %r8 /* pt_regs->r8 */ pushq %r9 /* pt_regs->r9 */ @@ -99,6 +99,7 @@ For 32-bit we have the following conventions - kernel is built with * well before they could be put to use in a speculative execution * gadget. */ + xorl %esi, %esi /* nospec si */ xorl %edx, %edx /* nospec dx */ xorl %ecx, %ecx /* nospec cx */ xorl %r8d, %r8d /* nospec r8 */ @@ -114,32 +115,24 @@ For 32-bit we have the following conventions - kernel is built with .endm -.macro PUSH_AND_CLEAR_REGS rdx=%rdx rax=%rax save_ret=0 - PUSH_REGS rdx=\rdx, rax=\rax, save_ret=\save_ret +.macro PUSH_AND_CLEAR_REGS rdx=%rdx rcx=%rcx rax=%rax save_ret=0 + PUSH_REGS rdx=\rdx, rcx=\rcx, rax=\rax, save_ret=\save_ret CLEAR_REGS .endm -.macro POP_REGS pop_rdi=1 skip_r11rcx=0 +.macro POP_REGS pop_rdi=1 popq %r15 popq %r14 popq %r13 popq %r12 popq %rbp popq %rbx - .if \skip_r11rcx - popq %rsi - .else popq %r11 - .endif popq %r10 popq %r9 popq %r8 popq %rax - .if \skip_r11rcx - popq %rsi - .else popq %rcx - .endif popq %rdx popq %rsi .if \pop_rdi diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S index 73d958522b6a..4300ba49b5ee 100644 --- a/arch/x86/entry/entry_64.S +++ b/arch/x86/entry/entry_64.S @@ -191,8 +191,7 @@ SYM_INNER_LABEL(entry_SYSCALL_64_after_hwframe, SYM_L_GLOBAL) * perf profiles. Nothing jumps here. */ syscall_return_via_sysret: - /* rcx and r11 are already restored (see code above) */ - POP_REGS pop_rdi=0 skip_r11rcx=1 + POP_REGS pop_rdi=0 /* * Now all regs are restored except RSP and RDI. @@ -215,8 +214,13 @@ syscall_return_via_sysret: popq %rdi popq %rsp +SYM_INNER_LABEL(entry_SYSRETQ_unsafe_stack, SYM_L_GLOBAL) + ANNOTATE_NOENDBR swapgs sysretq +SYM_INNER_LABEL(entry_SYSRETQ_end, SYM_L_GLOBAL) + ANNOTATE_NOENDBR + int3 SYM_CODE_END(entry_SYSCALL_64) /* @@ -318,6 +322,14 @@ SYM_CODE_END(ret_from_fork) #endif .endm +/* Save all registers in pt_regs */ +SYM_CODE_START_LOCAL(push_and_clear_regs) + UNWIND_HINT_FUNC + PUSH_AND_CLEAR_REGS save_ret=1 + ENCODE_FRAME_POINTER 8 + RET +SYM_CODE_END(push_and_clear_regs) + /** * idtentry_body - Macro to emit code calling the C function * @cfunc: C function to be called @@ -325,7 +337,21 @@ SYM_CODE_END(ret_from_fork) */ .macro idtentry_body cfunc has_error_code:req - call error_entry + call push_and_clear_regs + UNWIND_HINT_REGS + + /* + * Call error_entry() and switch to the task stack if from userspace. + * + * When in XENPV, it is already in the task stack, and it can't fault + * for native_iret() nor native_load_gs_index() since XENPV uses its + * own pvops for IRET and load_gs_index(). And it doesn't need to + * switch the CR3. So it can skip invoking error_entry(). + */ + ALTERNATIVE "call error_entry; movq %rax, %rsp", \ + "", X86_FEATURE_XENPV + + ENCODE_FRAME_POINTER UNWIND_HINT_REGS movq %rsp, %rdi /* pt_regs pointer into 1st argument*/ @@ -358,6 +384,7 @@ SYM_CODE_START(\asmsym) UNWIND_HINT_IRET_REGS offset=\has_error_code*8 ENDBR ASM_CLAC + cld .if \has_error_code == 0 pushq $-1 /* ORIG_RAX: no syscall to restart */ @@ -426,6 +453,7 @@ SYM_CODE_START(\asmsym) UNWIND_HINT_IRET_REGS ENDBR ASM_CLAC + cld pushq $-1 /* ORIG_RAX: no syscall to restart */ @@ -482,6 +510,7 @@ SYM_CODE_START(\asmsym) UNWIND_HINT_IRET_REGS ENDBR ASM_CLAC + cld /* * If the entry is from userspace, switch stacks and treat it as @@ -508,6 +537,7 @@ SYM_CODE_START(\asmsym) call vc_switch_off_ist movq %rax, %rsp /* Switch to new stack */ + ENCODE_FRAME_POINTER UNWIND_HINT_REGS /* Update pt_regs */ @@ -544,6 +574,7 @@ SYM_CODE_START(\asmsym) UNWIND_HINT_IRET_REGS offset=8 ENDBR ASM_CLAC + cld /* paranoid_entry returns GS information for paranoid_exit in EBX. */ call paranoid_entry @@ -869,7 +900,6 @@ SYM_CODE_END(xen_failsafe_callback) */ SYM_CODE_START_LOCAL(paranoid_entry) UNWIND_HINT_FUNC - cld PUSH_AND_CLEAR_REGS save_ret=1 ENCODE_FRAME_POINTER 8 @@ -983,13 +1013,10 @@ SYM_CODE_START_LOCAL(paranoid_exit) SYM_CODE_END(paranoid_exit) /* - * Save all registers in pt_regs, and switch GS if needed. + * Switch GS and CR3 if needed. */ SYM_CODE_START_LOCAL(error_entry) UNWIND_HINT_FUNC - cld - PUSH_AND_CLEAR_REGS save_ret=1 - ENCODE_FRAME_POINTER 8 testb $3, CS+8(%rsp) jz .Lerror_kernelspace @@ -997,19 +1024,15 @@ SYM_CODE_START_LOCAL(error_entry) * We entered from user mode or we're pretending to have entered * from user mode due to an IRET fault. */ - SWAPGS + swapgs FENCE_SWAPGS_USER_ENTRY /* We have user CR3. Change to kernel CR3. */ SWITCH_TO_KERNEL_CR3 scratch_reg=%rax + leaq 8(%rsp), %rdi /* arg0 = pt_regs pointer */ .Lerror_entry_from_usermode_after_swapgs: /* Put us onto the real thread stack. */ - popq %r12 /* save return addr in %12 */ - movq %rsp, %rdi /* arg0 = pt_regs pointer */ call sync_regs - movq %rax, %rsp /* switch stack */ - ENCODE_FRAME_POINTER - pushq %r12 RET /* @@ -1033,7 +1056,7 @@ SYM_CODE_START_LOCAL(error_entry) * gsbase and proceed. We'll fix up the exception and land in * .Lgs_change's error handler with kernel gsbase. */ - SWAPGS + swapgs /* * Issue an LFENCE to prevent GS speculation, regardless of whether it is a @@ -1041,6 +1064,7 @@ SYM_CODE_START_LOCAL(error_entry) */ .Lerror_entry_done_lfence: FENCE_SWAPGS_KERNEL_ENTRY + leaq 8(%rsp), %rax /* return pt_regs pointer */ RET .Lbstep_iret: @@ -1053,7 +1077,7 @@ SYM_CODE_START_LOCAL(error_entry) * We came from an IRET to user mode, so we have user * gsbase and CR3. Switch to kernel gsbase and CR3: */ - SWAPGS + swapgs FENCE_SWAPGS_USER_ENTRY SWITCH_TO_KERNEL_CR3 scratch_reg=%rax @@ -1061,9 +1085,9 @@ SYM_CODE_START_LOCAL(error_entry) * Pretend that the exception came from user mode: set up pt_regs * as if we faulted immediately after IRET. */ - mov %rsp, %rdi + leaq 8(%rsp), %rdi /* arg0 = pt_regs pointer */ call fixup_bad_iret - mov %rax, %rsp + mov %rax, %rdi jmp .Lerror_entry_from_usermode_after_swapgs SYM_CODE_END(error_entry) @@ -1126,6 +1150,7 @@ SYM_CODE_START(asm_exc_nmi) */ ASM_CLAC + cld /* Use %rdx as our temp variable throughout */ pushq %rdx @@ -1145,7 +1170,6 @@ SYM_CODE_START(asm_exc_nmi) */ swapgs - cld FENCE_SWAPGS_USER_ENTRY SWITCH_TO_KERNEL_CR3 scratch_reg=%rdx movq %rsp, %rdx diff --git a/arch/x86/entry/entry_64_compat.S b/arch/x86/entry/entry_64_compat.S index 4fdb007cddbd..d1052742ad0c 100644 --- a/arch/x86/entry/entry_64_compat.S +++ b/arch/x86/entry/entry_64_compat.S @@ -50,7 +50,7 @@ SYM_CODE_START(entry_SYSENTER_compat) UNWIND_HINT_EMPTY ENDBR /* Interrupts are off on entry. */ - SWAPGS + swapgs pushq %rax SWITCH_TO_KERNEL_CR3 scratch_reg=%rax @@ -83,32 +83,7 @@ SYM_INNER_LABEL(entry_SYSENTER_compat_after_hwframe, SYM_L_GLOBAL) movl %eax, %eax pushq %rax /* pt_regs->orig_ax */ - pushq %rdi /* pt_regs->di */ - pushq %rsi /* pt_regs->si */ - pushq %rdx /* pt_regs->dx */ - pushq %rcx /* pt_regs->cx */ - pushq $-ENOSYS /* pt_regs->ax */ - pushq $0 /* pt_regs->r8 = 0 */ - xorl %r8d, %r8d /* nospec r8 */ - pushq $0 /* pt_regs->r9 = 0 */ - xorl %r9d, %r9d /* nospec r9 */ - pushq $0 /* pt_regs->r10 = 0 */ - xorl %r10d, %r10d /* nospec r10 */ - pushq $0 /* pt_regs->r11 = 0 */ - xorl %r11d, %r11d /* nospec r11 */ - pushq %rbx /* pt_regs->rbx */ - xorl %ebx, %ebx /* nospec rbx */ - pushq %rbp /* pt_regs->rbp (will be overwritten) */ - xorl %ebp, %ebp /* nospec rbp */ - pushq $0 /* pt_regs->r12 = 0 */ - xorl %r12d, %r12d /* nospec r12 */ - pushq $0 /* pt_regs->r13 = 0 */ - xorl %r13d, %r13d /* nospec r13 */ - pushq $0 /* pt_regs->r14 = 0 */ - xorl %r14d, %r14d /* nospec r14 */ - pushq $0 /* pt_regs->r15 = 0 */ - xorl %r15d, %r15d /* nospec r15 */ - + PUSH_AND_CLEAR_REGS rax=$-ENOSYS UNWIND_HINT_REGS cld @@ -225,35 +200,7 @@ SYM_INNER_LABEL(entry_SYSCALL_compat_safe_stack, SYM_L_GLOBAL) 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 */ - pushq %rsi /* pt_regs->si */ - xorl %esi, %esi /* nospec si */ - pushq %rdx /* pt_regs->dx */ - xorl %edx, %edx /* nospec dx */ - pushq %rbp /* pt_regs->cx (stashed in bp) */ - xorl %ecx, %ecx /* nospec cx */ - pushq $-ENOSYS /* pt_regs->ax */ - pushq $0 /* pt_regs->r8 = 0 */ - xorl %r8d, %r8d /* nospec r8 */ - pushq $0 /* pt_regs->r9 = 0 */ - xorl %r9d, %r9d /* nospec r9 */ - pushq $0 /* pt_regs->r10 = 0 */ - xorl %r10d, %r10d /* nospec r10 */ - pushq $0 /* pt_regs->r11 = 0 */ - xorl %r11d, %r11d /* nospec r11 */ - pushq %rbx /* pt_regs->rbx */ - xorl %ebx, %ebx /* nospec rbx */ - pushq %rbp /* pt_regs->rbp (will be overwritten) */ - xorl %ebp, %ebp /* nospec rbp */ - pushq $0 /* pt_regs->r12 = 0 */ - xorl %r12d, %r12d /* nospec r12 */ - pushq $0 /* pt_regs->r13 = 0 */ - xorl %r13d, %r13d /* nospec r13 */ - pushq $0 /* pt_regs->r14 = 0 */ - xorl %r14d, %r14d /* nospec r14 */ - pushq $0 /* pt_regs->r15 = 0 */ - xorl %r15d, %r15d /* nospec r15 */ - + PUSH_AND_CLEAR_REGS rcx=%rbp rax=$-ENOSYS UNWIND_HINT_REGS movq %rsp, %rdi @@ -297,6 +244,8 @@ sysret32_from_system_call: * code. We zero R8-R10 to avoid info leaks. */ movq RSP-ORIG_RAX(%rsp), %rsp +SYM_INNER_LABEL(entry_SYSRETL_compat_unsafe_stack, SYM_L_GLOBAL) + ANNOTATE_NOENDBR /* * The original userspace %rsp (RSP-ORIG_RAX(%rsp)) is stored @@ -314,6 +263,9 @@ sysret32_from_system_call: xorl %r10d, %r10d swapgs sysretl +SYM_INNER_LABEL(entry_SYSRETL_compat_end, SYM_L_GLOBAL) + ANNOTATE_NOENDBR + int3 SYM_CODE_END(entry_SYSCALL_compat) /* @@ -362,54 +314,25 @@ SYM_CODE_START(entry_INT80_compat) /* switch to thread stack expects orig_ax and rdi to be pushed */ pushq %rax /* pt_regs->orig_ax */ - pushq %rdi /* pt_regs->di */ /* Need to switch before accessing the thread stack. */ - SWITCH_TO_KERNEL_CR3 scratch_reg=%rdi + SWITCH_TO_KERNEL_CR3 scratch_reg=%rax /* In the Xen PV case we already run on the thread stack. */ ALTERNATIVE "", "jmp .Lint80_keep_stack", X86_FEATURE_XENPV - movq %rsp, %rdi + movq %rsp, %rax movq PER_CPU_VAR(cpu_current_top_of_stack), %rsp - pushq 6*8(%rdi) /* regs->ss */ - pushq 5*8(%rdi) /* regs->rsp */ - pushq 4*8(%rdi) /* regs->eflags */ - pushq 3*8(%rdi) /* regs->cs */ - pushq 2*8(%rdi) /* regs->ip */ - pushq 1*8(%rdi) /* regs->orig_ax */ - pushq (%rdi) /* pt_regs->di */ + pushq 5*8(%rax) /* regs->ss */ + pushq 4*8(%rax) /* regs->rsp */ + pushq 3*8(%rax) /* regs->eflags */ + pushq 2*8(%rax) /* regs->cs */ + pushq 1*8(%rax) /* regs->ip */ + pushq 0*8(%rax) /* regs->orig_ax */ .Lint80_keep_stack: - pushq %rsi /* pt_regs->si */ - xorl %esi, %esi /* nospec si */ - pushq %rdx /* pt_regs->dx */ - xorl %edx, %edx /* nospec dx */ - pushq %rcx /* pt_regs->cx */ - xorl %ecx, %ecx /* nospec cx */ - pushq $-ENOSYS /* pt_regs->ax */ - pushq %r8 /* pt_regs->r8 */ - xorl %r8d, %r8d /* nospec r8 */ - pushq %r9 /* pt_regs->r9 */ - xorl %r9d, %r9d /* nospec r9 */ - pushq %r10 /* pt_regs->r10*/ - xorl %r10d, %r10d /* nospec r10 */ - pushq %r11 /* pt_regs->r11 */ - xorl %r11d, %r11d /* nospec r11 */ - pushq %rbx /* pt_regs->rbx */ - xorl %ebx, %ebx /* nospec rbx */ - pushq %rbp /* pt_regs->rbp */ - xorl %ebp, %ebp /* nospec rbp */ - pushq %r12 /* pt_regs->r12 */ - xorl %r12d, %r12d /* nospec r12 */ - pushq %r13 /* pt_regs->r13 */ - xorl %r13d, %r13d /* nospec r13 */ - pushq %r14 /* pt_regs->r14 */ - xorl %r14d, %r14d /* nospec r14 */ - pushq %r15 /* pt_regs->r15 */ - xorl %r15d, %r15d /* nospec r15 */ - + PUSH_AND_CLEAR_REGS rax=$-ENOSYS UNWIND_HINT_REGS cld diff --git a/arch/x86/entry/vdso/vma.c b/arch/x86/entry/vdso/vma.c index 235a5794296a..1000d457c332 100644 --- a/arch/x86/entry/vdso/vma.c +++ b/arch/x86/entry/vdso/vma.c @@ -438,7 +438,7 @@ bool arch_syscall_is_vdso_sigreturn(struct pt_regs *regs) static __init int vdso_setup(char *s) { vdso64_enabled = simple_strtoul(s, NULL, 0); - return 0; + return 1; } __setup("vdso=", vdso_setup); diff --git a/arch/x86/ia32/Makefile b/arch/x86/ia32/Makefile index 8e4d0391ff6c..e481056698de 100644 --- a/arch/x86/ia32/Makefile +++ b/arch/x86/ia32/Makefile @@ -5,7 +5,5 @@ obj-$(CONFIG_IA32_EMULATION) := ia32_signal.o -obj-$(CONFIG_IA32_AOUT) += ia32_aout.o - audit-class-$(CONFIG_AUDIT) := audit.o obj-$(CONFIG_IA32_EMULATION) += $(audit-class-y) diff --git a/arch/x86/ia32/ia32_aout.c b/arch/x86/ia32/ia32_aout.c deleted file mode 100644 index 9bd15241fadb..000000000000 --- a/arch/x86/ia32/ia32_aout.c +++ /dev/null @@ -1,325 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* - * a.out loader for x86-64 - * - * Copyright (C) 1991, 1992, 1996 Linus Torvalds - * Hacked together by Andi Kleen - */ - -#include <linux/module.h> - -#include <linux/time.h> -#include <linux/kernel.h> -#include <linux/mm.h> -#include <linux/mman.h> -#include <linux/a.out.h> -#include <linux/errno.h> -#include <linux/signal.h> -#include <linux/string.h> -#include <linux/fs.h> -#include <linux/file.h> -#include <linux/stat.h> -#include <linux/fcntl.h> -#include <linux/ptrace.h> -#include <linux/user.h> -#include <linux/binfmts.h> -#include <linux/personality.h> -#include <linux/init.h> -#include <linux/jiffies.h> -#include <linux/perf_event.h> -#include <linux/sched/task_stack.h> - -#include <linux/uaccess.h> -#include <asm/cacheflush.h> -#include <asm/user32.h> -#include <asm/ia32.h> - -#undef WARN_OLD - -static int load_aout_binary(struct linux_binprm *); -static int load_aout_library(struct file *); - -static struct linux_binfmt aout_format = { - .module = THIS_MODULE, - .load_binary = load_aout_binary, - .load_shlib = load_aout_library, -}; - -static int set_brk(unsigned long start, unsigned long end) -{ - start = PAGE_ALIGN(start); - end = PAGE_ALIGN(end); - if (end <= start) - return 0; - return vm_brk(start, end - start); -} - - -/* - * create_aout_tables() parses the env- and arg-strings in new user - * memory and creates the pointer tables from them, and puts their - * addresses on the "stack", returning the new stack pointer value. - */ -static u32 __user *create_aout_tables(char __user *p, struct linux_binprm *bprm) -{ - u32 __user *argv, *envp, *sp; - int argc = bprm->argc, envc = bprm->envc; - - sp = (u32 __user *) ((-(unsigned long)sizeof(u32)) & (unsigned long) p); - sp -= envc+1; - envp = sp; - sp -= argc+1; - argv = sp; - put_user((unsigned long) envp, --sp); - put_user((unsigned long) argv, --sp); - put_user(argc, --sp); - current->mm->arg_start = (unsigned long) p; - while (argc-- > 0) { - char c; - - put_user((u32)(unsigned long)p, argv++); - do { - get_user(c, p++); - } while (c); - } - put_user(0, argv); - current->mm->arg_end = current->mm->env_start = (unsigned long) p; - while (envc-- > 0) { - char c; - - put_user((u32)(unsigned long)p, envp++); - do { - get_user(c, p++); - } while (c); - } - put_user(0, envp); - current->mm->env_end = (unsigned long) p; - return sp; -} - -/* - * These are the functions used to load a.out style executables and shared - * libraries. There is no binary dependent code anywhere else. - */ -static int load_aout_binary(struct linux_binprm *bprm) -{ - unsigned long error, fd_offset, rlim; - struct pt_regs *regs = current_pt_regs(); - struct exec ex; - int retval; - - ex = *((struct exec *) bprm->buf); /* exec-header */ - if ((N_MAGIC(ex) != ZMAGIC && N_MAGIC(ex) != OMAGIC && - N_MAGIC(ex) != QMAGIC && N_MAGIC(ex) != NMAGIC) || - N_TRSIZE(ex) || N_DRSIZE(ex) || - i_size_read(file_inode(bprm->file)) < - ex.a_text+ex.a_data+N_SYMSIZE(ex)+N_TXTOFF(ex)) { - return -ENOEXEC; - } - - fd_offset = N_TXTOFF(ex); - - /* Check initial limits. This avoids letting people circumvent - * size limits imposed on them by creating programs with large - * arrays in the data or bss. - */ - rlim = rlimit(RLIMIT_DATA); - if (rlim >= RLIM_INFINITY) - rlim = ~0; - if (ex.a_data + ex.a_bss > rlim) - return -ENOMEM; - - /* Flush all traces of the currently running executable */ - retval = begin_new_exec(bprm); - if (retval) - return retval; - - /* OK, This is the point of no return */ - set_personality(PER_LINUX); - set_personality_ia32(false); - - setup_new_exec(bprm); - - regs->cs = __USER32_CS; - regs->r8 = regs->r9 = regs->r10 = regs->r11 = regs->r12 = - regs->r13 = regs->r14 = regs->r15 = 0; - - current->mm->end_code = ex.a_text + - (current->mm->start_code = N_TXTADDR(ex)); - current->mm->end_data = ex.a_data + - (current->mm->start_data = N_DATADDR(ex)); - current->mm->brk = ex.a_bss + - (current->mm->start_brk = N_BSSADDR(ex)); - - retval = setup_arg_pages(bprm, IA32_STACK_TOP, EXSTACK_DEFAULT); - if (retval < 0) - return retval; - - if (N_MAGIC(ex) == OMAGIC) { - unsigned long text_addr, map_size; - - text_addr = N_TXTADDR(ex); - map_size = ex.a_text+ex.a_data; - - error = vm_brk(text_addr & PAGE_MASK, map_size); - - if (error) - return error; - - error = read_code(bprm->file, text_addr, 32, - ex.a_text + ex.a_data); - if ((signed long)error < 0) - return error; - } else { -#ifdef WARN_OLD - static unsigned long error_time, error_time2; - if ((ex.a_text & 0xfff || ex.a_data & 0xfff) && - (N_MAGIC(ex) != NMAGIC) && - time_after(jiffies, error_time2 + 5*HZ)) { - printk(KERN_NOTICE "executable not page aligned\n"); - error_time2 = jiffies; - } - - if ((fd_offset & ~PAGE_MASK) != 0 && - time_after(jiffies, error_time + 5*HZ)) { - printk(KERN_WARNING - "fd_offset is not page aligned. Please convert " - "program: %pD\n", - bprm->file); - error_time = jiffies; - } -#endif - - if (!bprm->file->f_op->mmap || (fd_offset & ~PAGE_MASK) != 0) { - error = vm_brk(N_TXTADDR(ex), ex.a_text+ex.a_data); - if (error) - return error; - - read_code(bprm->file, N_TXTADDR(ex), fd_offset, - ex.a_text+ex.a_data); - goto beyond_if; - } - - error = vm_mmap(bprm->file, N_TXTADDR(ex), ex.a_text, - PROT_READ | PROT_EXEC, - MAP_FIXED | MAP_PRIVATE | MAP_32BIT, - fd_offset); - - if (error != N_TXTADDR(ex)) - return error; - - error = vm_mmap(bprm->file, N_DATADDR(ex), ex.a_data, - PROT_READ | PROT_WRITE | PROT_EXEC, - MAP_FIXED | MAP_PRIVATE | MAP_32BIT, - fd_offset + ex.a_text); - if (error != N_DATADDR(ex)) - return error; - } - -beyond_if: - error = set_brk(current->mm->start_brk, current->mm->brk); - if (error) - return error; - - set_binfmt(&aout_format); - - current->mm->start_stack = - (unsigned long)create_aout_tables((char __user *)bprm->p, bprm); - /* start thread */ - loadsegment(fs, 0); - loadsegment(ds, __USER32_DS); - loadsegment(es, __USER32_DS); - load_gs_index(0); - (regs)->ip = ex.a_entry; - (regs)->sp = current->mm->start_stack; - (regs)->flags = 0x200; - (regs)->cs = __USER32_CS; - (regs)->ss = __USER32_DS; - regs->r8 = regs->r9 = regs->r10 = regs->r11 = - regs->r12 = regs->r13 = regs->r14 = regs->r15 = 0; - return 0; -} - -static int load_aout_library(struct file *file) -{ - unsigned long bss, start_addr, len, error; - int retval; - struct exec ex; - loff_t pos = 0; - - retval = -ENOEXEC; - error = kernel_read(file, &ex, sizeof(ex), &pos); - if (error != sizeof(ex)) - goto out; - - /* We come in here for the regular a.out style of shared libraries */ - if ((N_MAGIC(ex) != ZMAGIC && N_MAGIC(ex) != QMAGIC) || N_TRSIZE(ex) || - N_DRSIZE(ex) || ((ex.a_entry & 0xfff) && N_MAGIC(ex) == ZMAGIC) || - i_size_read(file_inode(file)) < - ex.a_text+ex.a_data+N_SYMSIZE(ex)+N_TXTOFF(ex)) { - goto out; - } - - if (N_FLAGS(ex)) - goto out; - - /* For QMAGIC, the starting address is 0x20 into the page. We mask - this off to get the starting address for the page */ - - start_addr = ex.a_entry & 0xfffff000; - - if ((N_TXTOFF(ex) & ~PAGE_MASK) != 0) { -#ifdef WARN_OLD - static unsigned long error_time; - if (time_after(jiffies, error_time + 5*HZ)) { - printk(KERN_WARNING - "N_TXTOFF is not page aligned. Please convert " - "library: %pD\n", - file); - error_time = jiffies; - } -#endif - retval = vm_brk(start_addr, ex.a_text + ex.a_data + ex.a_bss); - if (retval) - goto out; - - read_code(file, start_addr, N_TXTOFF(ex), - ex.a_text + ex.a_data); - retval = 0; - goto out; - } - /* Now use mmap to map the library into memory. */ - error = vm_mmap(file, start_addr, ex.a_text + ex.a_data, - PROT_READ | PROT_WRITE | PROT_EXEC, - MAP_FIXED | MAP_PRIVATE | MAP_32BIT, - N_TXTOFF(ex)); - retval = error; - if (error != start_addr) - goto out; - - len = PAGE_ALIGN(ex.a_text + ex.a_data); - bss = ex.a_text + ex.a_data + ex.a_bss; - if (bss > len) { - retval = vm_brk(start_addr + len, bss - len); - if (retval) - goto out; - } - retval = 0; -out: - return retval; -} - -static int __init init_aout_binfmt(void) -{ - register_binfmt(&aout_format); - return 0; -} - -static void __exit exit_aout_binfmt(void) -{ - unregister_binfmt(&aout_format); -} - -module_init(init_aout_binfmt); -module_exit(exit_aout_binfmt); -MODULE_LICENSE("GPL"); diff --git a/arch/x86/include/asm/acenv.h b/arch/x86/include/asm/acenv.h index 9aff97f0de7f..d937c55e717e 100644 --- a/arch/x86/include/asm/acenv.h +++ b/arch/x86/include/asm/acenv.h @@ -13,7 +13,19 @@ /* Asm macros */ -#define ACPI_FLUSH_CPU_CACHE() wbinvd() +/* + * ACPI_FLUSH_CPU_CACHE() flushes caches on entering sleep states. + * It is required to prevent data loss. + * + * While running inside virtual machine, the kernel can bypass cache flushing. + * Changing sleep state in a virtual machine doesn't affect the host system + * sleep state and cannot lead to data loss. + */ +#define ACPI_FLUSH_CPU_CACHE() \ +do { \ + if (!cpu_feature_enabled(X86_FEATURE_HYPERVISOR)) \ + wbinvd(); \ +} while (0) int __acpi_acquire_global_lock(unsigned int *lock); int __acpi_release_global_lock(unsigned int *lock); diff --git a/arch/x86/include/asm/amd_nb.h b/arch/x86/include/asm/amd_nb.h index 00d1a400b7a1..ed0eaf65c437 100644 --- a/arch/x86/include/asm/amd_nb.h +++ b/arch/x86/include/asm/amd_nb.h @@ -16,7 +16,6 @@ extern const struct amd_nb_bus_dev_range amd_nb_bus_dev_ranges[]; extern bool early_is_amd_nb(u32 value); extern struct resource *amd_get_mmconfig_range(struct resource *res); -extern int amd_cache_northbridges(void); extern void amd_flush_garts(void); extern int amd_numa_init(void); extern int amd_get_subcaches(int); diff --git a/arch/x86/include/asm/apic.h b/arch/x86/include/asm/apic.h index 48067af94678..bd8ae0a7010a 100644 --- a/arch/x86/include/asm/apic.h +++ b/arch/x86/include/asm/apic.h @@ -328,6 +328,8 @@ struct apic { /* wakeup_secondary_cpu */ int (*wakeup_secondary_cpu)(int apicid, unsigned long start_eip); + /* wakeup secondary CPU using 64-bit wakeup point */ + int (*wakeup_secondary_cpu_64)(int apicid, unsigned long start_eip); void (*inquire_remote_apic)(int apicid); @@ -488,6 +490,11 @@ static inline unsigned int read_apic_id(void) return apic->get_apic_id(reg); } +#ifdef CONFIG_X86_64 +typedef int (*wakeup_cpu_handler)(int apicid, unsigned long start_eip); +extern void acpi_wake_cpu_handler_update(wakeup_cpu_handler handler); +#endif + extern int default_apic_id_valid(u32 apicid); extern int default_acpi_madt_oem_check(char *, char *); extern void default_setup_apic_routing(void); diff --git a/arch/x86/include/asm/apicdef.h b/arch/x86/include/asm/apicdef.h index 5716f22f81ac..92035eb3afee 100644 --- a/arch/x86/include/asm/apicdef.h +++ b/arch/x86/include/asm/apicdef.h @@ -95,12 +95,6 @@ #define APIC_LVTTHMR 0x330 #define APIC_LVTPC 0x340 #define APIC_LVT0 0x350 -#define APIC_LVT_TIMER_BASE_MASK (0x3 << 18) -#define GET_APIC_TIMER_BASE(x) (((x) >> 18) & 0x3) -#define SET_APIC_TIMER_BASE(x) (((x) << 18)) -#define APIC_TIMER_BASE_CLKIN 0x0 -#define APIC_TIMER_BASE_TMBASE 0x1 -#define APIC_TIMER_BASE_DIV 0x2 #define APIC_LVT_TIMER_ONESHOT (0 << 17) #define APIC_LVT_TIMER_PERIODIC (1 << 17) #define APIC_LVT_TIMER_TSCDEADLINE (2 << 17) diff --git a/arch/x86/include/asm/bootparam_utils.h b/arch/x86/include/asm/bootparam_utils.h index 981fe923a59f..53e9b0620d96 100644 --- a/arch/x86/include/asm/bootparam_utils.h +++ b/arch/x86/include/asm/bootparam_utils.h @@ -74,6 +74,7 @@ static void sanitize_boot_params(struct boot_params *boot_params) BOOT_PARAM_PRESERVE(hdr), BOOT_PARAM_PRESERVE(e820_table), BOOT_PARAM_PRESERVE(eddbuf), + BOOT_PARAM_PRESERVE(cc_blob_address), }; memset(&scratch, 0, sizeof(scratch)); diff --git a/arch/x86/include/asm/bug.h b/arch/x86/include/asm/bug.h index aaf0cb0db4ae..a3ec87d198ac 100644 --- a/arch/x86/include/asm/bug.h +++ b/arch/x86/include/asm/bug.h @@ -18,7 +18,7 @@ #ifdef CONFIG_X86_32 # define __BUG_REL(val) ".long " __stringify(val) #else -# define __BUG_REL(val) ".long " __stringify(val) " - 2b" +# define __BUG_REL(val) ".long " __stringify(val) " - ." #endif #ifdef CONFIG_DEBUG_BUGVERBOSE diff --git a/arch/x86/include/asm/cpu.h b/arch/x86/include/asm/cpu.h index 86e5e4e26fcb..2178b36a179a 100644 --- a/arch/x86/include/asm/cpu.h +++ b/arch/x86/include/asm/cpu.h @@ -36,6 +36,8 @@ extern int _debug_hotplug_cpu(int cpu, int action); #endif #endif +extern void ap_init_aperfmperf(void); + int mwait_usable(const struct cpuinfo_x86 *); unsigned int x86_family(unsigned int sig); @@ -43,14 +45,12 @@ unsigned int x86_model(unsigned int sig); unsigned int x86_stepping(unsigned int sig); #ifdef CONFIG_CPU_SUP_INTEL extern void __init sld_setup(struct cpuinfo_x86 *c); -extern void switch_to_sld(unsigned long tifn); extern bool handle_user_split_lock(struct pt_regs *regs, long error_code); extern bool handle_guest_split_lock(unsigned long ip); extern void handle_bus_lock(struct pt_regs *regs); u8 get_this_hybrid_cpu_type(void); #else static inline void __init sld_setup(struct cpuinfo_x86 *c) {} -static inline void switch_to_sld(unsigned long tifn) {} static inline bool handle_user_split_lock(struct pt_regs *regs, long error_code) { return false; diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h index 1261842d006c..66d3e3b1d24d 100644 --- a/arch/x86/include/asm/cpufeature.h +++ b/arch/x86/include/asm/cpufeature.h @@ -34,14 +34,17 @@ enum cpuid_leafs CPUID_8000_001F_EAX, }; +#define X86_CAP_FMT_NUM "%d:%d" +#define x86_cap_flag_num(flag) ((flag) >> 5), ((flag) & 31) + #ifdef CONFIG_X86_FEATURE_NAMES extern const char * const x86_cap_flags[NCAPINTS*32]; extern const char * const x86_power_flags[32]; #define X86_CAP_FMT "%s" #define x86_cap_flag(flag) x86_cap_flags[flag] #else -#define X86_CAP_FMT "%d:%d" -#define x86_cap_flag(flag) ((flag) >> 5), ((flag) & 31) +#define X86_CAP_FMT X86_CAP_FMT_NUM +#define x86_cap_flag x86_cap_flag_num #endif /* diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h index 73e643ae94b6..6e0dbbf847f3 100644 --- a/arch/x86/include/asm/cpufeatures.h +++ b/arch/x86/include/asm/cpufeatures.h @@ -201,7 +201,7 @@ #define X86_FEATURE_INVPCID_SINGLE ( 7*32+ 7) /* Effectively INVPCID && CR4.PCIDE=1 */ #define X86_FEATURE_HW_PSTATE ( 7*32+ 8) /* AMD HW-PState */ #define X86_FEATURE_PROC_FEEDBACK ( 7*32+ 9) /* AMD ProcFeedbackInterface */ -/* FREE! ( 7*32+10) */ +#define X86_FEATURE_XCOMPACTED ( 7*32+10) /* "" Use compacted XSTATE (XSAVES or XSAVEC) */ #define X86_FEATURE_PTI ( 7*32+11) /* Kernel Page Table Isolation enabled */ #define X86_FEATURE_RETPOLINE ( 7*32+12) /* "" Generic Retpoline mitigation for Spectre variant 2 */ #define X86_FEATURE_RETPOLINE_LFENCE ( 7*32+13) /* "" Use LFENCE for Spectre variant 2 */ @@ -238,6 +238,7 @@ #define X86_FEATURE_VMW_VMMCALL ( 8*32+19) /* "" VMware prefers VMMCALL hypercall instruction */ #define X86_FEATURE_PVUNLOCK ( 8*32+20) /* "" PV unlock function */ #define X86_FEATURE_VCPUPREEMPT ( 8*32+21) /* "" PV vcpu_is_preempted function */ +#define X86_FEATURE_TDX_GUEST ( 8*32+22) /* Intel Trust Domain Extensions Guest */ /* Intel-defined CPU features, CPUID level 0x00000007:0 (EBX), word 9 */ #define X86_FEATURE_FSGSBASE ( 9*32+ 0) /* RDFSBASE, WRFSBASE, RDGSBASE, WRGSBASE instructions*/ diff --git a/arch/x86/include/asm/cpuid.h b/arch/x86/include/asm/cpuid.h new file mode 100644 index 000000000000..70b2db18165e --- /dev/null +++ b/arch/x86/include/asm/cpuid.h @@ -0,0 +1,34 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * CPUID-related helpers/definitions + * + * Derived from arch/x86/kvm/cpuid.c + */ + +#ifndef _ASM_X86_CPUID_H +#define _ASM_X86_CPUID_H + +static __always_inline bool cpuid_function_is_indexed(u32 function) +{ + switch (function) { + case 4: + case 7: + case 0xb: + case 0xd: + case 0xf: + case 0x10: + case 0x12: + case 0x14: + case 0x17: + case 0x18: + case 0x1d: + case 0x1e: + case 0x1f: + case 0x8000001d: + return true; + } + + return false; +} + +#endif /* _ASM_X86_CPUID_H */ diff --git a/arch/x86/include/asm/disabled-features.h b/arch/x86/include/asm/disabled-features.h index 1231d63f836d..36369e76cc63 100644 --- a/arch/x86/include/asm/disabled-features.h +++ b/arch/x86/include/asm/disabled-features.h @@ -10,12 +10,6 @@ * cpu_feature_enabled(). */ -#ifdef CONFIG_X86_SMAP -# define DISABLE_SMAP 0 -#else -# define DISABLE_SMAP (1<<(X86_FEATURE_SMAP & 31)) -#endif - #ifdef CONFIG_X86_UMIP # define DISABLE_UMIP 0 #else @@ -68,6 +62,12 @@ # define DISABLE_SGX (1 << (X86_FEATURE_SGX & 31)) #endif +#ifdef CONFIG_INTEL_TDX_GUEST +# define DISABLE_TDX_GUEST 0 +#else +# define DISABLE_TDX_GUEST (1 << (X86_FEATURE_TDX_GUEST & 31)) +#endif + /* * Make sure to add features to the correct mask */ @@ -79,8 +79,8 @@ #define DISABLED_MASK5 0 #define DISABLED_MASK6 0 #define DISABLED_MASK7 (DISABLE_PTI) -#define DISABLED_MASK8 0 -#define DISABLED_MASK9 (DISABLE_SMAP|DISABLE_SGX) +#define DISABLED_MASK8 (DISABLE_TDX_GUEST) +#define DISABLED_MASK9 (DISABLE_SGX) #define DISABLED_MASK10 0 #define DISABLED_MASK11 0 #define DISABLED_MASK12 0 diff --git a/arch/x86/include/asm/efi.h b/arch/x86/include/asm/efi.h index 98938a68251c..bed74a0f2932 100644 --- a/arch/x86/include/asm/efi.h +++ b/arch/x86/include/asm/efi.h @@ -357,6 +357,11 @@ static inline u32 efi64_convert_status(efi_status_t status) runtime), \ func, __VA_ARGS__)) +#define efi_dxe_call(func, ...) \ + (efi_is_native() \ + ? efi_dxe_table->func(__VA_ARGS__) \ + : __efi64_thunk_map(efi_dxe_table, func, __VA_ARGS__)) + #else /* CONFIG_EFI_MIXED */ static inline bool efi_is_64bit(void) diff --git a/arch/x86/include/asm/elf.h b/arch/x86/include/asm/elf.h index 29fea180a665..cb0ff1055ab1 100644 --- a/arch/x86/include/asm/elf.h +++ b/arch/x86/include/asm/elf.h @@ -116,7 +116,7 @@ extern unsigned int vdso32_enabled; * now struct_user_regs, they are different) */ -#define ELF_CORE_COPY_REGS_COMMON(pr_reg, regs) \ +#define ELF_CORE_COPY_REGS(pr_reg, regs) \ do { \ pr_reg[0] = regs->bx; \ pr_reg[1] = regs->cx; \ @@ -128,6 +128,7 @@ do { \ pr_reg[7] = regs->ds; \ pr_reg[8] = regs->es; \ pr_reg[9] = regs->fs; \ + savesegment(gs, pr_reg[10]); \ pr_reg[11] = regs->orig_ax; \ pr_reg[12] = regs->ip; \ pr_reg[13] = regs->cs; \ @@ -136,18 +137,6 @@ do { \ pr_reg[16] = regs->ss; \ } while (0); -#define ELF_CORE_COPY_REGS(pr_reg, regs) \ -do { \ - ELF_CORE_COPY_REGS_COMMON(pr_reg, regs);\ - pr_reg[10] = get_user_gs(regs); \ -} while (0); - -#define ELF_CORE_COPY_KERNEL_REGS(pr_reg, regs) \ -do { \ - ELF_CORE_COPY_REGS_COMMON(pr_reg, regs);\ - savesegment(gs, pr_reg[10]); \ -} while (0); - #define ELF_PLATFORM (utsname()->machine) #define set_personality_64bit() do { } while (0) diff --git a/arch/x86/include/asm/fpu/api.h b/arch/x86/include/asm/fpu/api.h index c83b3020350a..6b0f31fb53f7 100644 --- a/arch/x86/include/asm/fpu/api.h +++ b/arch/x86/include/asm/fpu/api.h @@ -162,7 +162,6 @@ static inline bool fpstate_is_confidential(struct fpu_guest *gfpu) } /* prctl */ -struct task_struct; -extern long fpu_xstate_prctl(struct task_struct *tsk, int option, unsigned long arg2); +extern long fpu_xstate_prctl(int option, unsigned long arg2); #endif /* _ASM_X86_FPU_API_H */ diff --git a/arch/x86/include/asm/fpu/internal.h b/arch/x86/include/asm/fpu/internal.h deleted file mode 100644 index e69de29bb2d1..000000000000 --- a/arch/x86/include/asm/fpu/internal.h +++ /dev/null diff --git a/arch/x86/include/asm/idtentry.h b/arch/x86/include/asm/idtentry.h index 7924f27f5c8b..72184b0b2219 100644 --- a/arch/x86/include/asm/idtentry.h +++ b/arch/x86/include/asm/idtentry.h @@ -632,6 +632,10 @@ DECLARE_IDTENTRY_XENCB(X86_TRAP_OTHER, exc_xen_hypervisor_callback); DECLARE_IDTENTRY_RAW(X86_TRAP_OTHER, exc_xen_unknown_trap); #endif +#ifdef CONFIG_INTEL_TDX_GUEST +DECLARE_IDTENTRY(X86_TRAP_VE, exc_virtualization_exception); +#endif + /* Device interrupts common/spurious */ DECLARE_IDTENTRY_IRQ(X86_TRAP_OTHER, common_interrupt); #ifdef CONFIG_X86_LOCAL_APIC diff --git a/arch/x86/include/asm/io.h b/arch/x86/include/asm/io.h index e9736af126b2..1870b99c3356 100644 --- a/arch/x86/include/asm/io.h +++ b/arch/x86/include/asm/io.h @@ -44,6 +44,7 @@ #include <asm/page.h> #include <asm/early_ioremap.h> #include <asm/pgtable_types.h> +#include <asm/shared/io.h> #define build_mmio_read(name, size, type, reg, barrier) \ static inline type name(const volatile void __iomem *addr) \ @@ -256,37 +257,23 @@ static inline void slow_down_io(void) #endif #define BUILDIO(bwl, bw, type) \ -static inline void out##bwl(unsigned type value, int port) \ -{ \ - asm volatile("out" #bwl " %" #bw "0, %w1" \ - : : "a"(value), "Nd"(port)); \ -} \ - \ -static inline unsigned type in##bwl(int port) \ -{ \ - unsigned type value; \ - asm volatile("in" #bwl " %w1, %" #bw "0" \ - : "=a"(value) : "Nd"(port)); \ - return value; \ -} \ - \ -static inline void out##bwl##_p(unsigned type value, int port) \ +static inline void out##bwl##_p(type value, u16 port) \ { \ out##bwl(value, port); \ slow_down_io(); \ } \ \ -static inline unsigned type in##bwl##_p(int port) \ +static inline type in##bwl##_p(u16 port) \ { \ - unsigned type value = in##bwl(port); \ + type value = in##bwl(port); \ slow_down_io(); \ return value; \ } \ \ -static inline void outs##bwl(int port, const void *addr, unsigned long count) \ +static inline void outs##bwl(u16 port, const void *addr, unsigned long count) \ { \ if (cc_platform_has(CC_ATTR_GUEST_UNROLL_STRING_IO)) { \ - unsigned type *value = (unsigned type *)addr; \ + type *value = (type *)addr; \ while (count) { \ out##bwl(*value, port); \ value++; \ @@ -299,10 +286,10 @@ static inline void outs##bwl(int port, const void *addr, unsigned long count) \ } \ } \ \ -static inline void ins##bwl(int port, void *addr, unsigned long count) \ +static inline void ins##bwl(u16 port, void *addr, unsigned long count) \ { \ if (cc_platform_has(CC_ATTR_GUEST_UNROLL_STRING_IO)) { \ - unsigned type *value = (unsigned type *)addr; \ + type *value = (type *)addr; \ while (count) { \ *value = in##bwl(port); \ value++; \ @@ -315,13 +302,11 @@ static inline void ins##bwl(int port, void *addr, unsigned long count) \ } \ } -BUILDIO(b, b, char) -BUILDIO(w, w, short) -BUILDIO(l, , int) +BUILDIO(b, b, u8) +BUILDIO(w, w, u16) +BUILDIO(l, , u32) +#undef BUILDIO -#define inb inb -#define inw inw -#define inl inl #define inb_p inb_p #define inw_p inw_p #define inl_p inl_p @@ -329,9 +314,6 @@ BUILDIO(l, , int) #define insw insw #define insl insl -#define outb outb -#define outw outw -#define outl outl #define outb_p outb_p #define outw_p outw_p #define outl_p outl_p diff --git a/arch/x86/include/asm/irqflags.h b/arch/x86/include/asm/irqflags.h index 111104d1c2cd..7793e52d6237 100644 --- a/arch/x86/include/asm/irqflags.h +++ b/arch/x86/include/asm/irqflags.h @@ -137,14 +137,6 @@ static __always_inline void arch_local_irq_restore(unsigned long flags) if (!arch_irqs_disabled_flags(flags)) arch_local_irq_enable(); } -#else -#ifdef CONFIG_X86_64 -#ifdef CONFIG_XEN_PV -#define SWAPGS ALTERNATIVE "swapgs", "", X86_FEATURE_XENPV -#else -#define SWAPGS swapgs -#endif -#endif #endif /* !__ASSEMBLY__ */ #endif diff --git a/arch/x86/include/asm/kvm_para.h b/arch/x86/include/asm/kvm_para.h index 56935ebb1dfe..57bc74e112f2 100644 --- a/arch/x86/include/asm/kvm_para.h +++ b/arch/x86/include/asm/kvm_para.h @@ -7,6 +7,8 @@ #include <linux/interrupt.h> #include <uapi/asm/kvm_para.h> +#include <asm/tdx.h> + #ifdef CONFIG_KVM_GUEST bool kvm_check_and_clear_guest_paused(void); #else @@ -32,6 +34,10 @@ static inline bool kvm_check_and_clear_guest_paused(void) static inline long kvm_hypercall0(unsigned int nr) { long ret; + + if (cpu_feature_enabled(X86_FEATURE_TDX_GUEST)) + return tdx_kvm_hypercall(nr, 0, 0, 0, 0); + asm volatile(KVM_HYPERCALL : "=a"(ret) : "a"(nr) @@ -42,6 +48,10 @@ static inline long kvm_hypercall0(unsigned int nr) static inline long kvm_hypercall1(unsigned int nr, unsigned long p1) { long ret; + + if (cpu_feature_enabled(X86_FEATURE_TDX_GUEST)) + return tdx_kvm_hypercall(nr, p1, 0, 0, 0); + asm volatile(KVM_HYPERCALL : "=a"(ret) : "a"(nr), "b"(p1) @@ -53,6 +63,10 @@ static inline long kvm_hypercall2(unsigned int nr, unsigned long p1, unsigned long p2) { long ret; + + if (cpu_feature_enabled(X86_FEATURE_TDX_GUEST)) + return tdx_kvm_hypercall(nr, p1, p2, 0, 0); + asm volatile(KVM_HYPERCALL : "=a"(ret) : "a"(nr), "b"(p1), "c"(p2) @@ -64,6 +78,10 @@ static inline long kvm_hypercall3(unsigned int nr, unsigned long p1, unsigned long p2, unsigned long p3) { long ret; + + if (cpu_feature_enabled(X86_FEATURE_TDX_GUEST)) + return tdx_kvm_hypercall(nr, p1, p2, p3, 0); + asm volatile(KVM_HYPERCALL : "=a"(ret) : "a"(nr), "b"(p1), "c"(p2), "d"(p3) @@ -76,6 +94,10 @@ static inline long kvm_hypercall4(unsigned int nr, unsigned long p1, unsigned long p4) { long ret; + + if (cpu_feature_enabled(X86_FEATURE_TDX_GUEST)) + return tdx_kvm_hypercall(nr, p1, p2, p3, p4); + asm volatile(KVM_HYPERCALL : "=a"(ret) : "a"(nr), "b"(p1), "c"(p2), "d"(p3), "S"(p4) diff --git a/arch/x86/include/asm/mem_encrypt.h b/arch/x86/include/asm/mem_encrypt.h index e2c6f433ed10..88ceaf3648b3 100644 --- a/arch/x86/include/asm/mem_encrypt.h +++ b/arch/x86/include/asm/mem_encrypt.h @@ -49,9 +49,6 @@ void __init early_set_mem_enc_dec_hypercall(unsigned long vaddr, int npages, void __init mem_encrypt_free_decrypted_mem(void); -/* Architecture __weak replacement functions */ -void __init mem_encrypt_init(void); - void __init sev_es_init_vc_handling(void); #define __bss_decrypted __section(".bss..decrypted") @@ -89,6 +86,9 @@ static inline void mem_encrypt_free_decrypted_mem(void) { } #endif /* CONFIG_AMD_MEM_ENCRYPT */ +/* Architecture __weak replacement functions */ +void __init mem_encrypt_init(void); + /* * The __sme_pa() and __sme_pa_nodebug() macros are meant for use when * writing to or comparing values from the cr3 register. Having the diff --git a/arch/x86/include/asm/mmu_context.h b/arch/x86/include/asm/mmu_context.h index 27516046117a..b8d40ddeab00 100644 --- a/arch/x86/include/asm/mmu_context.h +++ b/arch/x86/include/asm/mmu_context.h @@ -141,7 +141,7 @@ do { \ #ifdef CONFIG_X86_32 #define deactivate_mm(tsk, mm) \ do { \ - lazy_load_gs(0); \ + loadsegment(gs, 0); \ } while (0) #else #define deactivate_mm(tsk, mm) \ diff --git a/arch/x86/include/asm/mmx.h b/arch/x86/include/asm/mmx.h deleted file mode 100644 index e69de29bb2d1..000000000000 --- a/arch/x86/include/asm/mmx.h +++ /dev/null diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h index ee15311b6be1..5555b2f9af46 100644 --- a/arch/x86/include/asm/msr-index.h +++ b/arch/x86/include/asm/msr-index.h @@ -502,8 +502,10 @@ #define MSR_AMD64_SEV 0xc0010131 #define MSR_AMD64_SEV_ENABLED_BIT 0 #define MSR_AMD64_SEV_ES_ENABLED_BIT 1 +#define MSR_AMD64_SEV_SNP_ENABLED_BIT 2 #define MSR_AMD64_SEV_ENABLED BIT_ULL(MSR_AMD64_SEV_ENABLED_BIT) #define MSR_AMD64_SEV_ES_ENABLED BIT_ULL(MSR_AMD64_SEV_ES_ENABLED_BIT) +#define MSR_AMD64_SEV_SNP_ENABLED BIT_ULL(MSR_AMD64_SEV_SNP_ENABLED_BIT) #define MSR_AMD64_VIRT_SPEC_CTRL 0xc001011f diff --git a/arch/x86/include/asm/msr.h b/arch/x86/include/asm/msr.h index d42e6c6b47b1..65ec1965cd28 100644 --- a/arch/x86/include/asm/msr.h +++ b/arch/x86/include/asm/msr.h @@ -10,16 +10,7 @@ #include <asm/errno.h> #include <asm/cpumask.h> #include <uapi/asm/msr.h> - -struct msr { - union { - struct { - u32 l; - u32 h; - }; - u64 q; - }; -}; +#include <asm/shared/msr.h> struct msr_info { u32 msr_no; diff --git a/arch/x86/include/asm/nmi.h b/arch/x86/include/asm/nmi.h index 1cb9c17a4cb4..5c5f1e56c404 100644 --- a/arch/x86/include/asm/nmi.h +++ b/arch/x86/include/asm/nmi.h @@ -47,6 +47,7 @@ struct nmiaction { #define register_nmi_handler(t, fn, fg, n, init...) \ ({ \ static struct nmiaction init fn##_na = { \ + .list = LIST_HEAD_INIT(fn##_na.list), \ .handler = (fn), \ .name = (n), \ .flags = (fg), \ diff --git a/arch/x86/include/asm/pci_x86.h b/arch/x86/include/asm/pci_x86.h index a0627dfae541..1307cd689d2a 100644 --- a/arch/x86/include/asm/pci_x86.h +++ b/arch/x86/include/asm/pci_x86.h @@ -93,6 +93,15 @@ struct irq_routing_table { struct irq_info slots[]; } __attribute__((packed)); +struct irt_routing_table { + u32 signature; /* IRT_SIGNATURE should be here */ + u8 size; /* Number of entries provided */ + u8 used; /* Number of entries actually used */ + u16 exclusive_irqs; /* IRQs devoted exclusively to + PCI usage */ + struct irq_info slots[]; +} __attribute__((packed)); + extern unsigned int pcibios_irq_mask; extern raw_spinlock_t pci_config_lock; diff --git a/arch/x86/include/asm/pkeys.h b/arch/x86/include/asm/pkeys.h index 1d5f14aff5f6..2e6c04d8a45b 100644 --- a/arch/x86/include/asm/pkeys.h +++ b/arch/x86/include/asm/pkeys.h @@ -41,9 +41,6 @@ static inline int arch_override_mprotect_pkey(struct vm_area_struct *vma, return __arch_override_mprotect_pkey(vma, prot, pkey); } -extern int __arch_set_user_pkey_access(struct task_struct *tsk, int pkey, - unsigned long init_val); - #define ARCH_VM_PKEY_FLAGS (VM_PKEY_BIT0 | VM_PKEY_BIT1 | VM_PKEY_BIT2 | VM_PKEY_BIT3) #define mm_pkey_allocation_map(mm) (mm->context.pkey_allocation_map) @@ -118,11 +115,6 @@ int mm_pkey_free(struct mm_struct *mm, int pkey) return 0; } -extern int arch_set_user_pkey_access(struct task_struct *tsk, int pkey, - unsigned long init_val); -extern int __arch_set_user_pkey_access(struct task_struct *tsk, int pkey, - unsigned long init_val); - static inline int vma_pkey(struct vm_area_struct *vma) { unsigned long vma_pkey_mask = VM_PKEY_BIT0 | VM_PKEY_BIT1 | diff --git a/arch/x86/include/asm/proto.h b/arch/x86/include/asm/proto.h index feed36d44d04..12ef86b19910 100644 --- a/arch/x86/include/asm/proto.h +++ b/arch/x86/include/asm/proto.h @@ -13,6 +13,8 @@ void syscall_init(void); #ifdef CONFIG_X86_64 void entry_SYSCALL_64(void); void entry_SYSCALL_64_safe_stack(void); +void entry_SYSRETQ_unsafe_stack(void); +void entry_SYSRETQ_end(void); long do_arch_prctl_64(struct task_struct *task, int option, unsigned long arg2); #endif @@ -28,6 +30,8 @@ void entry_SYSENTER_compat(void); void __end_entry_SYSENTER_compat(void); void entry_SYSCALL_compat(void); void entry_SYSCALL_compat_safe_stack(void); +void entry_SYSRETL_compat_unsafe_stack(void); +void entry_SYSRETL_compat_end(void); void entry_INT80_compat(void); #ifdef CONFIG_XEN_PV void xen_entry_INT80_compat(void); @@ -35,11 +39,9 @@ void xen_entry_INT80_compat(void); #endif void x86_configure_nx(void); -void x86_report_nx(void); extern int reboot_force; -long do_arch_prctl_common(struct task_struct *task, int option, - unsigned long arg2); +long do_arch_prctl_common(int option, unsigned long arg2); #endif /* _ASM_X86_PROTO_H */ diff --git a/arch/x86/include/asm/ptrace.h b/arch/x86/include/asm/ptrace.h index 4357e0f2cd5f..f4db78b09c8f 100644 --- a/arch/x86/include/asm/ptrace.h +++ b/arch/x86/include/asm/ptrace.h @@ -186,9 +186,13 @@ static __always_inline bool ip_within_syscall_gap(struct pt_regs *regs) bool ret = (regs->ip >= (unsigned long)entry_SYSCALL_64 && regs->ip < (unsigned long)entry_SYSCALL_64_safe_stack); + ret = ret || (regs->ip >= (unsigned long)entry_SYSRETQ_unsafe_stack && + regs->ip < (unsigned long)entry_SYSRETQ_end); #ifdef CONFIG_IA32_EMULATION ret = ret || (regs->ip >= (unsigned long)entry_SYSCALL_compat && regs->ip < (unsigned long)entry_SYSCALL_compat_safe_stack); + ret = ret || (regs->ip >= (unsigned long)entry_SYSRETL_compat_unsafe_stack && + regs->ip < (unsigned long)entry_SYSRETL_compat_end); #endif return ret; diff --git a/arch/x86/include/asm/realmode.h b/arch/x86/include/asm/realmode.h index 331474b150f1..fd6f6e5b755a 100644 --- a/arch/x86/include/asm/realmode.h +++ b/arch/x86/include/asm/realmode.h @@ -25,6 +25,7 @@ struct real_mode_header { u32 sev_es_trampoline_start; #endif #ifdef CONFIG_X86_64 + u32 trampoline_start64; u32 trampoline_pgd; #endif /* ACPI S3 wakeup */ diff --git a/arch/x86/include/asm/segment.h b/arch/x86/include/asm/segment.h index 656ed6531d03..2e7890dd58a4 100644 --- a/arch/x86/include/asm/segment.h +++ b/arch/x86/include/asm/segment.h @@ -350,18 +350,6 @@ static inline void __loadsegment_fs(unsigned short value) #define savesegment(seg, value) \ asm("mov %%" #seg ",%0":"=r" (value) : : "memory") -/* - * x86-32 user GS accessors. This is ugly and could do with some cleaning up. - */ -#ifdef CONFIG_X86_32 -# define get_user_gs(regs) (u16)({ unsigned long v; savesegment(gs, v); v; }) -# define set_user_gs(regs, v) loadsegment(gs, (unsigned long)(v)) -# define task_user_gs(tsk) ((tsk)->thread.gs) -# define lazy_save_gs(v) savesegment(gs, (v)) -# define lazy_load_gs(v) loadsegment(gs, (v)) -# define load_gs_index(v) loadsegment(gs, (v)) -#endif /* X86_32 */ - #endif /* !__ASSEMBLY__ */ #endif /* __KERNEL__ */ diff --git a/arch/x86/include/asm/setup.h b/arch/x86/include/asm/setup.h index 896e48d45828..7590ac2570b9 100644 --- a/arch/x86/include/asm/setup.h +++ b/arch/x86/include/asm/setup.h @@ -50,7 +50,6 @@ extern unsigned long saved_video_mode; extern void reserve_standard_io_resources(void); extern void i386_reserve_resources(void); extern unsigned long __startup_64(unsigned long physaddr, struct boot_params *bp); -extern unsigned long __startup_secondary_64(void); extern void startup_64_setup_env(unsigned long physbase); extern void early_setup_idt(void); extern void __init do_early_exception(struct pt_regs *regs, int trapnr); @@ -109,27 +108,19 @@ extern unsigned long _brk_end; void *extend_brk(size_t size, size_t align); /* - * Reserve space in the brk section. The name must be unique within - * the file, and somewhat descriptive. The size is in bytes. Must be - * used at file scope. + * Reserve space in the brk section. The name must be unique within the file, + * and somewhat descriptive. The size is in bytes. * - * (This uses a temp function to wrap the asm so we can pass it the - * size parameter; otherwise we wouldn't be able to. We can't use a - * "section" attribute on a normal variable because it always ends up - * being @progbits, which ends up allocating space in the vmlinux - * executable.) + * The allocation is done using inline asm (rather than using a section + * attribute on a normal variable) in order to allow the use of @nobits, so + * that it doesn't take up any space in the vmlinux file. */ -#define RESERVE_BRK(name,sz) \ - static void __section(".discard.text") __noendbr __used notrace \ - __brk_reservation_fn_##name##__(void) { \ - asm volatile ( \ - ".pushsection .brk_reservation,\"aw\",@nobits;" \ - ".brk." #name ":" \ - " 1:.skip %c0;" \ - " .size .brk." #name ", . - 1b;" \ - " .popsection" \ - : : "i" (sz)); \ - } +#define RESERVE_BRK(name, size) \ + asm(".pushsection .brk_reservation,\"aw\",@nobits\n\t" \ + ".brk." #name ":\n\t" \ + ".skip " __stringify(size) "\n\t" \ + ".size .brk." #name ", " __stringify(size) "\n\t" \ + ".popsection\n\t") extern void probe_roms(void); #ifdef __i386__ diff --git a/arch/x86/include/asm/sev-common.h b/arch/x86/include/asm/sev-common.h index 1b2fd32b42fe..b8357d6ecd47 100644 --- a/arch/x86/include/asm/sev-common.h +++ b/arch/x86/include/asm/sev-common.h @@ -57,9 +57,79 @@ #define GHCB_MSR_AP_RESET_HOLD_REQ 0x006 #define GHCB_MSR_AP_RESET_HOLD_RESP 0x007 +/* GHCB GPA Register */ +#define GHCB_MSR_REG_GPA_REQ 0x012 +#define GHCB_MSR_REG_GPA_REQ_VAL(v) \ + /* GHCBData[63:12] */ \ + (((u64)((v) & GENMASK_ULL(51, 0)) << 12) | \ + /* GHCBData[11:0] */ \ + GHCB_MSR_REG_GPA_REQ) + +#define GHCB_MSR_REG_GPA_RESP 0x013 +#define GHCB_MSR_REG_GPA_RESP_VAL(v) \ + /* GHCBData[63:12] */ \ + (((u64)(v) & GENMASK_ULL(63, 12)) >> 12) + +/* + * SNP Page State Change Operation + * + * GHCBData[55:52] - Page operation: + * 0x0001 Page assignment, Private + * 0x0002 Page assignment, Shared + */ +enum psc_op { + SNP_PAGE_STATE_PRIVATE = 1, + SNP_PAGE_STATE_SHARED, +}; + +#define GHCB_MSR_PSC_REQ 0x014 +#define GHCB_MSR_PSC_REQ_GFN(gfn, op) \ + /* GHCBData[55:52] */ \ + (((u64)((op) & 0xf) << 52) | \ + /* GHCBData[51:12] */ \ + ((u64)((gfn) & GENMASK_ULL(39, 0)) << 12) | \ + /* GHCBData[11:0] */ \ + GHCB_MSR_PSC_REQ) + +#define GHCB_MSR_PSC_RESP 0x015 +#define GHCB_MSR_PSC_RESP_VAL(val) \ + /* GHCBData[63:32] */ \ + (((u64)(val) & GENMASK_ULL(63, 32)) >> 32) + /* GHCB Hypervisor Feature Request/Response */ #define GHCB_MSR_HV_FT_REQ 0x080 #define GHCB_MSR_HV_FT_RESP 0x081 +#define GHCB_MSR_HV_FT_RESP_VAL(v) \ + /* GHCBData[63:12] */ \ + (((u64)(v) & GENMASK_ULL(63, 12)) >> 12) + +#define GHCB_HV_FT_SNP BIT_ULL(0) +#define GHCB_HV_FT_SNP_AP_CREATION BIT_ULL(1) + +/* SNP Page State Change NAE event */ +#define VMGEXIT_PSC_MAX_ENTRY 253 + +struct psc_hdr { + u16 cur_entry; + u16 end_entry; + u32 reserved; +} __packed; + +struct psc_entry { + u64 cur_page : 12, + gfn : 40, + operation : 4, + pagesize : 1, + reserved : 7; +} __packed; + +struct snp_psc_desc { + struct psc_hdr hdr; + struct psc_entry entries[VMGEXIT_PSC_MAX_ENTRY]; +} __packed; + +/* Guest message request error code */ +#define SNP_GUEST_REQ_INVALID_LEN BIT_ULL(32) #define GHCB_MSR_TERM_REQ 0x100 #define GHCB_MSR_TERM_REASON_SET_POS 12 @@ -73,8 +143,20 @@ /* GHCBData[23:16] */ \ ((((u64)reason_val) & 0xff) << 16)) +/* Error codes from reason set 0 */ +#define SEV_TERM_SET_GEN 0 #define GHCB_SEV_ES_GEN_REQ 0 #define GHCB_SEV_ES_PROT_UNSUPPORTED 1 +#define GHCB_SNP_UNSUPPORTED 2 + +/* Linux-specific reason codes (used with reason set 1) */ +#define SEV_TERM_SET_LINUX 1 +#define GHCB_TERM_REGISTER 0 /* GHCB GPA registration failure */ +#define GHCB_TERM_PSC 1 /* Page State Change failure */ +#define GHCB_TERM_PVALIDATE 2 /* Pvalidate failure */ +#define GHCB_TERM_NOT_VMPL0 3 /* SNP guest is not running at VMPL-0 */ +#define GHCB_TERM_CPUID 4 /* CPUID-validation failure */ +#define GHCB_TERM_CPUID_HV 5 /* CPUID failure during hypervisor fallback */ #define GHCB_RESP_CODE(v) ((v) & GHCB_MSR_INFO_MASK) diff --git a/arch/x86/include/asm/sev.h b/arch/x86/include/asm/sev.h index ec060c433589..19514524f0f8 100644 --- a/arch/x86/include/asm/sev.h +++ b/arch/x86/include/asm/sev.h @@ -11,9 +11,10 @@ #include <linux/types.h> #include <asm/insn.h> #include <asm/sev-common.h> +#include <asm/bootparam.h> -#define GHCB_PROTO_OUR 0x0001UL -#define GHCB_PROTOCOL_MAX 1ULL +#define GHCB_PROTOCOL_MIN 1ULL +#define GHCB_PROTOCOL_MAX 2ULL #define GHCB_DEFAULT_USAGE 0ULL #define VMGEXIT() { asm volatile("rep; vmmcall\n\r"); } @@ -42,6 +43,24 @@ struct es_em_ctxt { struct es_fault_info fi; }; +/* + * AMD SEV Confidential computing blob structure. The structure is + * defined in OVMF UEFI firmware header: + * https://github.com/tianocore/edk2/blob/master/OvmfPkg/Include/Guid/ConfidentialComputingSevSnpBlob.h + */ +#define CC_BLOB_SEV_HDR_MAGIC 0x45444d41 +struct cc_blob_sev_info { + u32 magic; + u16 version; + u16 reserved; + u64 secrets_phys; + u32 secrets_len; + u32 rsvd1; + u64 cpuid_phys; + u32 cpuid_len; + u32 rsvd2; +} __packed; + void do_vc_no_ghcb(struct pt_regs *regs, unsigned long exit_code); static inline u64 lower_bits(u64 val, unsigned int bits) @@ -60,6 +79,61 @@ extern void vc_no_ghcb(void); extern void vc_boot_ghcb(void); extern bool handle_vc_boot_ghcb(struct pt_regs *regs); +/* Software defined (when rFlags.CF = 1) */ +#define PVALIDATE_FAIL_NOUPDATE 255 + +/* RMP page size */ +#define RMP_PG_SIZE_4K 0 + +#define RMPADJUST_VMSA_PAGE_BIT BIT(16) + +/* SNP Guest message request */ +struct snp_req_data { + unsigned long req_gpa; + unsigned long resp_gpa; + unsigned long data_gpa; + unsigned int data_npages; +}; + +struct sev_guest_platform_data { + u64 secrets_gpa; +}; + +/* + * The secrets page contains 96-bytes of reserved field that can be used by + * the guest OS. The guest OS uses the area to save the message sequence + * number for each VMPCK. + * + * See the GHCB spec section Secret page layout for the format for this area. + */ +struct secrets_os_area { + u32 msg_seqno_0; + u32 msg_seqno_1; + u32 msg_seqno_2; + u32 msg_seqno_3; + u64 ap_jump_table_pa; + u8 rsvd[40]; + u8 guest_usage[32]; +} __packed; + +#define VMPCK_KEY_LEN 32 + +/* See the SNP spec version 0.9 for secrets page format */ +struct snp_secrets_page_layout { + u32 version; + u32 imien : 1, + rsvd1 : 31; + u32 fms; + u32 rsvd2; + u8 gosvw[16]; + u8 vmpck0[VMPCK_KEY_LEN]; + u8 vmpck1[VMPCK_KEY_LEN]; + u8 vmpck2[VMPCK_KEY_LEN]; + u8 vmpck3[VMPCK_KEY_LEN]; + struct secrets_os_area os_area; + u8 rsvd3[3840]; +} __packed; + #ifdef CONFIG_AMD_MEM_ENCRYPT extern struct static_key_false sev_es_enable_key; extern void __sev_es_ist_enter(struct pt_regs *regs); @@ -87,12 +161,71 @@ extern enum es_result sev_es_ghcb_hv_call(struct ghcb *ghcb, struct es_em_ctxt *ctxt, u64 exit_code, u64 exit_info_1, u64 exit_info_2); +static inline int rmpadjust(unsigned long vaddr, bool rmp_psize, unsigned long attrs) +{ + int rc; + + /* "rmpadjust" mnemonic support in binutils 2.36 and newer */ + asm volatile(".byte 0xF3,0x0F,0x01,0xFE\n\t" + : "=a"(rc) + : "a"(vaddr), "c"(rmp_psize), "d"(attrs) + : "memory", "cc"); + + return rc; +} +static inline int pvalidate(unsigned long vaddr, bool rmp_psize, bool validate) +{ + bool no_rmpupdate; + int rc; + + /* "pvalidate" mnemonic support in binutils 2.36 and newer */ + asm volatile(".byte 0xF2, 0x0F, 0x01, 0xFF\n\t" + CC_SET(c) + : CC_OUT(c) (no_rmpupdate), "=a"(rc) + : "a"(vaddr), "c"(rmp_psize), "d"(validate) + : "memory", "cc"); + + if (no_rmpupdate) + return PVALIDATE_FAIL_NOUPDATE; + + return rc; +} +void setup_ghcb(void); +void __init early_snp_set_memory_private(unsigned long vaddr, unsigned long paddr, + unsigned int npages); +void __init early_snp_set_memory_shared(unsigned long vaddr, unsigned long paddr, + unsigned int npages); +void __init snp_prep_memory(unsigned long paddr, unsigned int sz, enum psc_op op); +void snp_set_memory_shared(unsigned long vaddr, unsigned int npages); +void snp_set_memory_private(unsigned long vaddr, unsigned int npages); +void snp_set_wakeup_secondary_cpu(void); +bool snp_init(struct boot_params *bp); +void snp_abort(void); +int snp_issue_guest_request(u64 exit_code, struct snp_req_data *input, unsigned long *fw_err); #else static inline void sev_es_ist_enter(struct pt_regs *regs) { } static inline void sev_es_ist_exit(void) { } static inline int sev_es_setup_ap_jump_table(struct real_mode_header *rmh) { return 0; } static inline void sev_es_nmi_complete(void) { } static inline int sev_es_efi_map_ghcbs(pgd_t *pgd) { return 0; } +static inline int pvalidate(unsigned long vaddr, bool rmp_psize, bool validate) { return 0; } +static inline int rmpadjust(unsigned long vaddr, bool rmp_psize, unsigned long attrs) { return 0; } +static inline void setup_ghcb(void) { } +static inline void __init +early_snp_set_memory_private(unsigned long vaddr, unsigned long paddr, unsigned int npages) { } +static inline void __init +early_snp_set_memory_shared(unsigned long vaddr, unsigned long paddr, unsigned int npages) { } +static inline void __init snp_prep_memory(unsigned long paddr, unsigned int sz, enum psc_op op) { } +static inline void snp_set_memory_shared(unsigned long vaddr, unsigned int npages) { } +static inline void snp_set_memory_private(unsigned long vaddr, unsigned int npages) { } +static inline void snp_set_wakeup_secondary_cpu(void) { } +static inline bool snp_init(struct boot_params *bp) { return false; } +static inline void snp_abort(void) { } +static inline int snp_issue_guest_request(u64 exit_code, struct snp_req_data *input, + unsigned long *fw_err) +{ + return -ENOTTY; +} #endif #endif diff --git a/arch/x86/include/asm/shared/io.h b/arch/x86/include/asm/shared/io.h new file mode 100644 index 000000000000..c0ef921c0586 --- /dev/null +++ b/arch/x86/include/asm/shared/io.h @@ -0,0 +1,34 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_SHARED_IO_H +#define _ASM_X86_SHARED_IO_H + +#include <linux/types.h> + +#define BUILDIO(bwl, bw, type) \ +static inline void __out##bwl(type value, u16 port) \ +{ \ + asm volatile("out" #bwl " %" #bw "0, %w1" \ + : : "a"(value), "Nd"(port)); \ +} \ + \ +static inline type __in##bwl(u16 port) \ +{ \ + type value; \ + asm volatile("in" #bwl " %w1, %" #bw "0" \ + : "=a"(value) : "Nd"(port)); \ + return value; \ +} + +BUILDIO(b, b, u8) +BUILDIO(w, w, u16) +BUILDIO(l, , u32) +#undef BUILDIO + +#define inb __inb +#define inw __inw +#define inl __inl +#define outb __outb +#define outw __outw +#define outl __outl + +#endif diff --git a/arch/x86/include/asm/shared/msr.h b/arch/x86/include/asm/shared/msr.h new file mode 100644 index 000000000000..1e6ec10b3a15 --- /dev/null +++ b/arch/x86/include/asm/shared/msr.h @@ -0,0 +1,15 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_SHARED_MSR_H +#define _ASM_X86_SHARED_MSR_H + +struct msr { + union { + struct { + u32 l; + u32 h; + }; + u64 q; + }; +}; + +#endif /* _ASM_X86_SHARED_MSR_H */ diff --git a/arch/x86/include/asm/shared/tdx.h b/arch/x86/include/asm/shared/tdx.h new file mode 100644 index 000000000000..e53f26228fbb --- /dev/null +++ b/arch/x86/include/asm/shared/tdx.h @@ -0,0 +1,40 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_SHARED_TDX_H +#define _ASM_X86_SHARED_TDX_H + +#include <linux/bits.h> +#include <linux/types.h> + +#define TDX_HYPERCALL_STANDARD 0 + +#define TDX_HCALL_HAS_OUTPUT BIT(0) +#define TDX_HCALL_ISSUE_STI BIT(1) + +#define TDX_CPUID_LEAF_ID 0x21 +#define TDX_IDENT "IntelTDX " + +#ifndef __ASSEMBLY__ + +/* + * Used in __tdx_hypercall() to pass down and get back registers' values of + * the TDCALL instruction when requesting services from the VMM. + * + * This is a software only structure and not part of the TDX module/VMM ABI. + */ +struct tdx_hypercall_args { + u64 r10; + u64 r11; + u64 r12; + u64 r13; + u64 r14; + u64 r15; +}; + +/* Used to request services from the VMM */ +u64 __tdx_hypercall(struct tdx_hypercall_args *args, unsigned long flags); + +/* Called from __tdx_hypercall() for unrecoverable failure */ +void __tdx_hypercall_failed(void); + +#endif /* !__ASSEMBLY__ */ +#endif /* _ASM_X86_SHARED_TDX_H */ diff --git a/arch/x86/include/asm/smap.h b/arch/x86/include/asm/smap.h index d17b39893b79..bab490379c65 100644 --- a/arch/x86/include/asm/smap.h +++ b/arch/x86/include/asm/smap.h @@ -19,25 +19,14 @@ #ifdef __ASSEMBLY__ -#ifdef CONFIG_X86_SMAP - #define ASM_CLAC \ ALTERNATIVE "", __ASM_CLAC, X86_FEATURE_SMAP #define ASM_STAC \ ALTERNATIVE "", __ASM_STAC, X86_FEATURE_SMAP -#else /* CONFIG_X86_SMAP */ - -#define ASM_CLAC -#define ASM_STAC - -#endif /* CONFIG_X86_SMAP */ - #else /* __ASSEMBLY__ */ -#ifdef CONFIG_X86_SMAP - static __always_inline void clac(void) { /* Note: a barrier is implicit in alternative() */ @@ -76,19 +65,6 @@ static __always_inline void smap_restore(unsigned long flags) #define ASM_STAC \ ALTERNATIVE("", __ASM_STAC, X86_FEATURE_SMAP) -#else /* CONFIG_X86_SMAP */ - -static inline void clac(void) { } -static inline void stac(void) { } - -static inline unsigned long smap_save(void) { return 0; } -static inline void smap_restore(unsigned long flags) { } - -#define ASM_CLAC -#define ASM_STAC - -#endif /* CONFIG_X86_SMAP */ - #endif /* __ASSEMBLY__ */ #endif /* _ASM_X86_SMAP_H */ diff --git a/arch/x86/include/asm/special_insns.h b/arch/x86/include/asm/special_insns.h index 68c257a3de0d..45b18eb94fa1 100644 --- a/arch/x86/include/asm/special_insns.h +++ b/arch/x86/include/asm/special_insns.h @@ -184,14 +184,15 @@ static inline void wbinvd(void) native_wbinvd(); } -#ifdef CONFIG_X86_64 static inline void load_gs_index(unsigned int selector) { +#ifdef CONFIG_X86_64 native_load_gs_index(selector); -} - +#else + loadsegment(gs, selector); #endif +} #endif /* CONFIG_PARAVIRT_XXL */ diff --git a/arch/x86/include/asm/suspend_32.h b/arch/x86/include/asm/suspend_32.h index 7b132d0312eb..a800abb1a992 100644 --- a/arch/x86/include/asm/suspend_32.h +++ b/arch/x86/include/asm/suspend_32.h @@ -19,7 +19,6 @@ struct saved_context { u16 gs; unsigned long cr0, cr2, cr3, cr4; u64 misc_enable; - bool misc_enable_saved; struct saved_msrs saved_msrs; struct desc_ptr gdt_desc; struct desc_ptr idt; @@ -28,6 +27,7 @@ struct saved_context { unsigned long tr; unsigned long safety; unsigned long return_address; + bool misc_enable_saved; } __attribute__((packed)); /* routines for saving/restoring kernel state */ diff --git a/arch/x86/include/asm/suspend_64.h b/arch/x86/include/asm/suspend_64.h index 35bb35d28733..54df06687d83 100644 --- a/arch/x86/include/asm/suspend_64.h +++ b/arch/x86/include/asm/suspend_64.h @@ -14,9 +14,13 @@ * Image of the saved processor state, used by the low level ACPI suspend to * RAM code and by the low level hibernation code. * - * If you modify it, fix arch/x86/kernel/acpi/wakeup_64.S and make sure that - * __save/__restore_processor_state(), defined in arch/x86/kernel/suspend_64.c, - * still work as required. + * If you modify it, check how it is used in arch/x86/kernel/acpi/wakeup_64.S + * and make sure that __save/__restore_processor_state(), defined in + * arch/x86/power/cpu.c, still work as required. + * + * Because the structure is packed, make sure to avoid unaligned members. For + * optimisation purposes but also because tools like kmemleak only search for + * pointers that are aligned. */ struct saved_context { struct pt_regs regs; @@ -36,7 +40,6 @@ struct saved_context { unsigned long cr0, cr2, cr3, cr4; u64 misc_enable; - bool misc_enable_saved; struct saved_msrs saved_msrs; unsigned long efer; u16 gdt_pad; /* Unused */ @@ -48,6 +51,7 @@ struct saved_context { unsigned long tr; unsigned long safety; unsigned long return_address; + bool misc_enable_saved; } __attribute__((packed)); #define loaddebug(thread,register) \ diff --git a/arch/x86/include/asm/svm.h b/arch/x86/include/asm/svm.h index f70a5108d464..ec623e7da33d 100644 --- a/arch/x86/include/asm/svm.h +++ b/arch/x86/include/asm/svm.h @@ -271,6 +271,7 @@ struct vmcb_seg { u64 base; } __packed; +/* Save area definition for legacy and SEV-MEM guests */ struct vmcb_save_area { struct vmcb_seg es; struct vmcb_seg cs; @@ -282,12 +283,12 @@ struct vmcb_save_area { struct vmcb_seg ldtr; struct vmcb_seg idtr; struct vmcb_seg tr; - u8 reserved_1[43]; + u8 reserved_1[42]; + u8 vmpl; u8 cpl; u8 reserved_2[4]; u64 efer; - u8 reserved_3[104]; - u64 xss; /* Valid for SEV-ES only */ + u8 reserved_3[112]; u64 cr4; u64 cr3; u64 cr0; @@ -297,7 +298,9 @@ struct vmcb_save_area { u64 rip; u8 reserved_4[88]; u64 rsp; - u8 reserved_5[24]; + u64 s_cet; + u64 ssp; + u64 isst_addr; u64 rax; u64 star; u64 lstar; @@ -308,29 +311,145 @@ struct vmcb_save_area { u64 sysenter_esp; u64 sysenter_eip; u64 cr2; - u8 reserved_6[32]; + u8 reserved_5[32]; u64 g_pat; u64 dbgctl; u64 br_from; u64 br_to; u64 last_excp_from; u64 last_excp_to; - - /* - * The following part of the save area is valid only for - * SEV-ES guests when referenced through the GHCB or for - * saving to the host save area. - */ - u8 reserved_7[72]; + u8 reserved_6[72]; u32 spec_ctrl; /* Guest version of SPEC_CTRL at 0x2E0 */ - u8 reserved_7b[4]; +} __packed; + +/* Save area definition for SEV-ES and SEV-SNP guests */ +struct sev_es_save_area { + struct vmcb_seg es; + struct vmcb_seg cs; + struct vmcb_seg ss; + struct vmcb_seg ds; + struct vmcb_seg fs; + struct vmcb_seg gs; + struct vmcb_seg gdtr; + struct vmcb_seg ldtr; + struct vmcb_seg idtr; + struct vmcb_seg tr; + u64 vmpl0_ssp; + u64 vmpl1_ssp; + u64 vmpl2_ssp; + u64 vmpl3_ssp; + u64 u_cet; + u8 reserved_1[2]; + u8 vmpl; + u8 cpl; + u8 reserved_2[4]; + u64 efer; + u8 reserved_3[104]; + u64 xss; + u64 cr4; + u64 cr3; + u64 cr0; + u64 dr7; + u64 dr6; + u64 rflags; + u64 rip; + u64 dr0; + u64 dr1; + u64 dr2; + u64 dr3; + u64 dr0_addr_mask; + u64 dr1_addr_mask; + u64 dr2_addr_mask; + u64 dr3_addr_mask; + u8 reserved_4[24]; + u64 rsp; + u64 s_cet; + u64 ssp; + u64 isst_addr; + u64 rax; + u64 star; + u64 lstar; + u64 cstar; + u64 sfmask; + u64 kernel_gs_base; + u64 sysenter_cs; + u64 sysenter_esp; + u64 sysenter_eip; + u64 cr2; + u8 reserved_5[32]; + u64 g_pat; + u64 dbgctl; + u64 br_from; + u64 br_to; + u64 last_excp_from; + u64 last_excp_to; + u8 reserved_7[80]; u32 pkru; - u8 reserved_7a[20]; - u64 reserved_8; /* rax already available at 0x01f8 */ + u8 reserved_8[20]; + u64 reserved_9; /* rax already available at 0x01f8 */ + u64 rcx; + u64 rdx; + u64 rbx; + u64 reserved_10; /* rsp already available at 0x01d8 */ + u64 rbp; + u64 rsi; + u64 rdi; + u64 r8; + u64 r9; + u64 r10; + u64 r11; + u64 r12; + u64 r13; + u64 r14; + u64 r15; + u8 reserved_11[16]; + u64 guest_exit_info_1; + u64 guest_exit_info_2; + u64 guest_exit_int_info; + u64 guest_nrip; + u64 sev_features; + u64 vintr_ctrl; + u64 guest_exit_code; + u64 virtual_tom; + u64 tlb_id; + u64 pcpu_id; + u64 event_inj; + u64 xcr0; + u8 reserved_12[16]; + + /* Floating point area */ + u64 x87_dp; + u32 mxcsr; + u16 x87_ftw; + u16 x87_fsw; + u16 x87_fcw; + u16 x87_fop; + u16 x87_ds; + u16 x87_cs; + u64 x87_rip; + u8 fpreg_x87[80]; + u8 fpreg_xmm[256]; + u8 fpreg_ymm[256]; +} __packed; + +struct ghcb_save_area { + u8 reserved_1[203]; + u8 cpl; + u8 reserved_2[116]; + u64 xss; + u8 reserved_3[24]; + u64 dr7; + u8 reserved_4[16]; + u64 rip; + u8 reserved_5[88]; + u64 rsp; + u8 reserved_6[24]; + u64 rax; + u8 reserved_7[264]; u64 rcx; u64 rdx; u64 rbx; - u64 reserved_9; /* rsp already available at 0x01d8 */ + u8 reserved_8[8]; u64 rbp; u64 rsi; u64 rdi; @@ -342,22 +461,24 @@ struct vmcb_save_area { u64 r13; u64 r14; u64 r15; - u8 reserved_10[16]; + u8 reserved_9[16]; u64 sw_exit_code; u64 sw_exit_info_1; u64 sw_exit_info_2; u64 sw_scratch; - u8 reserved_11[56]; + u8 reserved_10[56]; u64 xcr0; u8 valid_bitmap[16]; u64 x87_state_gpa; } __packed; +#define GHCB_SHARED_BUF_SIZE 2032 + struct ghcb { - struct vmcb_save_area save; - u8 reserved_save[2048 - sizeof(struct vmcb_save_area)]; + struct ghcb_save_area save; + u8 reserved_save[2048 - sizeof(struct ghcb_save_area)]; - u8 shared_buffer[2032]; + u8 shared_buffer[GHCB_SHARED_BUF_SIZE]; u8 reserved_1[10]; u16 protocol_version; /* negotiated SEV-ES/GHCB protocol version */ @@ -365,13 +486,17 @@ struct ghcb { } __packed; -#define EXPECTED_VMCB_SAVE_AREA_SIZE 1032 +#define EXPECTED_VMCB_SAVE_AREA_SIZE 740 +#define EXPECTED_GHCB_SAVE_AREA_SIZE 1032 +#define EXPECTED_SEV_ES_SAVE_AREA_SIZE 1648 #define EXPECTED_VMCB_CONTROL_AREA_SIZE 1024 #define EXPECTED_GHCB_SIZE PAGE_SIZE static inline void __unused_size_checks(void) { BUILD_BUG_ON(sizeof(struct vmcb_save_area) != EXPECTED_VMCB_SAVE_AREA_SIZE); + BUILD_BUG_ON(sizeof(struct ghcb_save_area) != EXPECTED_GHCB_SAVE_AREA_SIZE); + BUILD_BUG_ON(sizeof(struct sev_es_save_area) != EXPECTED_SEV_ES_SAVE_AREA_SIZE); BUILD_BUG_ON(sizeof(struct vmcb_control_area) != EXPECTED_VMCB_CONTROL_AREA_SIZE); BUILD_BUG_ON(sizeof(struct ghcb) != EXPECTED_GHCB_SIZE); } @@ -441,7 +566,7 @@ struct vmcb { /* GHCB Accessor functions */ #define GHCB_BITMAP_IDX(field) \ - (offsetof(struct vmcb_save_area, field) / sizeof(u64)) + (offsetof(struct ghcb_save_area, field) / sizeof(u64)) #define DEFINE_GHCB_ACCESSORS(field) \ static inline bool ghcb_##field##_is_valid(const struct ghcb *ghcb) \ diff --git a/arch/x86/include/asm/tdx.h b/arch/x86/include/asm/tdx.h new file mode 100644 index 000000000000..020c81a7c729 --- /dev/null +++ b/arch/x86/include/asm/tdx.h @@ -0,0 +1,91 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (C) 2021-2022 Intel Corporation */ +#ifndef _ASM_X86_TDX_H +#define _ASM_X86_TDX_H + +#include <linux/init.h> +#include <linux/bits.h> +#include <asm/ptrace.h> +#include <asm/shared/tdx.h> + +/* + * SW-defined error codes. + * + * Bits 47:40 == 0xFF indicate Reserved status code class that never used by + * TDX module. + */ +#define TDX_ERROR _BITUL(63) +#define TDX_SW_ERROR (TDX_ERROR | GENMASK_ULL(47, 40)) +#define TDX_SEAMCALL_VMFAILINVALID (TDX_SW_ERROR | _UL(0xFFFF0000)) + +#ifndef __ASSEMBLY__ + +/* + * Used to gather the output registers values of the TDCALL and SEAMCALL + * instructions when requesting services from the TDX module. + * + * This is a software only structure and not part of the TDX module/VMM ABI. + */ +struct tdx_module_output { + u64 rcx; + u64 rdx; + u64 r8; + u64 r9; + u64 r10; + u64 r11; +}; + +/* + * Used by the #VE exception handler to gather the #VE exception + * info from the TDX module. This is a software only structure + * and not part of the TDX module/VMM ABI. + */ +struct ve_info { + u64 exit_reason; + u64 exit_qual; + /* Guest Linear (virtual) Address */ + u64 gla; + /* Guest Physical Address */ + u64 gpa; + u32 instr_len; + u32 instr_info; +}; + +#ifdef CONFIG_INTEL_TDX_GUEST + +void __init tdx_early_init(void); + +/* Used to communicate with the TDX module */ +u64 __tdx_module_call(u64 fn, u64 rcx, u64 rdx, u64 r8, u64 r9, + struct tdx_module_output *out); + +void tdx_get_ve_info(struct ve_info *ve); + +bool tdx_handle_virt_exception(struct pt_regs *regs, struct ve_info *ve); + +void tdx_safe_halt(void); + +bool tdx_early_handle_ve(struct pt_regs *regs); + +#else + +static inline void tdx_early_init(void) { }; +static inline void tdx_safe_halt(void) { }; + +static inline bool tdx_early_handle_ve(struct pt_regs *regs) { return false; } + +#endif /* CONFIG_INTEL_TDX_GUEST */ + +#if defined(CONFIG_KVM_GUEST) && defined(CONFIG_INTEL_TDX_GUEST) +long tdx_kvm_hypercall(unsigned int nr, unsigned long p1, unsigned long p2, + unsigned long p3, unsigned long p4); +#else +static inline long tdx_kvm_hypercall(unsigned int nr, unsigned long p1, + unsigned long p2, unsigned long p3, + unsigned long p4) +{ + return -ENODEV; +} +#endif /* CONFIG_INTEL_TDX_GUEST && CONFIG_KVM_GUEST */ +#endif /* !__ASSEMBLY__ */ +#endif /* _ASM_X86_TDX_H */ diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h index ebec69c35e95..f0cb881c1d69 100644 --- a/arch/x86/include/asm/thread_info.h +++ b/arch/x86/include/asm/thread_info.h @@ -92,7 +92,6 @@ struct thread_info { #define TIF_NOCPUID 15 /* CPUID is not accessible in userland */ #define TIF_NOTSC 16 /* TSC is not accessible in userland */ #define TIF_NOTIFY_SIGNAL 17 /* signal notifications exist */ -#define TIF_SLD 18 /* Restore split lock detection on context switch */ #define TIF_MEMDIE 20 /* is terminating due to OOM killer */ #define TIF_POLLING_NRFLAG 21 /* idle is polling for TIF_NEED_RESCHED */ #define TIF_IO_BITMAP 22 /* uses I/O bitmap */ @@ -116,7 +115,6 @@ struct thread_info { #define _TIF_NOCPUID (1 << TIF_NOCPUID) #define _TIF_NOTSC (1 << TIF_NOTSC) #define _TIF_NOTIFY_SIGNAL (1 << TIF_NOTIFY_SIGNAL) -#define _TIF_SLD (1 << TIF_SLD) #define _TIF_POLLING_NRFLAG (1 << TIF_POLLING_NRFLAG) #define _TIF_IO_BITMAP (1 << TIF_IO_BITMAP) #define _TIF_SPEC_FORCE_UPDATE (1 << TIF_SPEC_FORCE_UPDATE) @@ -128,7 +126,7 @@ struct thread_info { /* flags to check in __switch_to() */ #define _TIF_WORK_CTXSW_BASE \ (_TIF_NOCPUID | _TIF_NOTSC | _TIF_BLOCKSTEP | \ - _TIF_SSBD | _TIF_SPEC_FORCE_UPDATE | _TIF_SLD) + _TIF_SSBD | _TIF_SPEC_FORCE_UPDATE) /* * Avoid calls to __switch_to_xtra() on UP as STIBP is not evaluated. diff --git a/arch/x86/include/asm/topology.h b/arch/x86/include/asm/topology.h index 9619385bf749..458c891a8273 100644 --- a/arch/x86/include/asm/topology.h +++ b/arch/x86/include/asm/topology.h @@ -212,30 +212,19 @@ static inline long arch_scale_freq_capacity(int cpu) } #define arch_scale_freq_capacity arch_scale_freq_capacity -extern void arch_scale_freq_tick(void); -#define arch_scale_freq_tick arch_scale_freq_tick - extern void arch_set_max_freq_ratio(bool turbo_disabled); -void init_freq_invariance(bool secondary, bool cppc_ready); +extern void freq_invariance_set_perf_ratio(u64 ratio, bool turbo_disabled); #else -static inline void arch_set_max_freq_ratio(bool turbo_disabled) -{ -} -static inline void init_freq_invariance(bool secondary, bool cppc_ready) -{ -} +static inline void arch_set_max_freq_ratio(bool turbo_disabled) { } +static inline void freq_invariance_set_perf_ratio(u64 ratio, bool turbo_disabled) { } #endif +extern void arch_scale_freq_tick(void); +#define arch_scale_freq_tick arch_scale_freq_tick + #ifdef CONFIG_ACPI_CPPC_LIB void init_freq_invariance_cppc(void); #define arch_init_invariance_cppc init_freq_invariance_cppc - -bool amd_set_max_freq_ratio(u64 *ratio); -#else -static inline bool amd_set_max_freq_ratio(u64 *ratio) -{ - return false; -} #endif #endif /* _ASM_X86_TOPOLOGY_H */ diff --git a/arch/x86/include/asm/traps.h b/arch/x86/include/asm/traps.h index 35317c5c551d..47ecfff2c83d 100644 --- a/arch/x86/include/asm/traps.h +++ b/arch/x86/include/asm/traps.h @@ -13,7 +13,7 @@ #ifdef CONFIG_X86_64 asmlinkage __visible notrace struct pt_regs *sync_regs(struct pt_regs *eregs); asmlinkage __visible notrace -struct bad_iret_stack *fixup_bad_iret(struct bad_iret_stack *s); +struct pt_regs *fixup_bad_iret(struct pt_regs *bad_regs); void __init trap_init(void); asmlinkage __visible noinstr struct pt_regs *vc_switch_off_ist(struct pt_regs *eregs); #endif diff --git a/arch/x86/include/uapi/asm/bootparam.h b/arch/x86/include/uapi/asm/bootparam.h index b25d3f82c2f3..bea5cdcdf532 100644 --- a/arch/x86/include/uapi/asm/bootparam.h +++ b/arch/x86/include/uapi/asm/bootparam.h @@ -10,6 +10,7 @@ #define SETUP_EFI 4 #define SETUP_APPLE_PROPERTIES 5 #define SETUP_JAILHOUSE 6 +#define SETUP_CC_BLOB 7 #define SETUP_INDIRECT (1<<31) @@ -187,7 +188,8 @@ struct boot_params { __u32 ext_ramdisk_image; /* 0x0c0 */ __u32 ext_ramdisk_size; /* 0x0c4 */ __u32 ext_cmd_line_ptr; /* 0x0c8 */ - __u8 _pad4[116]; /* 0x0cc */ + __u8 _pad4[112]; /* 0x0cc */ + __u32 cc_blob_address; /* 0x13c */ struct edid_info edid_info; /* 0x140 */ struct efi_info efi_info; /* 0x1c0 */ __u32 alt_mem_k; /* 0x1e0 */ diff --git a/arch/x86/include/uapi/asm/svm.h b/arch/x86/include/uapi/asm/svm.h index efa969325ede..f69c168391aa 100644 --- a/arch/x86/include/uapi/asm/svm.h +++ b/arch/x86/include/uapi/asm/svm.h @@ -108,6 +108,14 @@ #define SVM_VMGEXIT_AP_JUMP_TABLE 0x80000005 #define SVM_VMGEXIT_SET_AP_JUMP_TABLE 0 #define SVM_VMGEXIT_GET_AP_JUMP_TABLE 1 +#define SVM_VMGEXIT_PSC 0x80000010 +#define SVM_VMGEXIT_GUEST_REQUEST 0x80000011 +#define SVM_VMGEXIT_EXT_GUEST_REQUEST 0x80000012 +#define SVM_VMGEXIT_AP_CREATION 0x80000013 +#define SVM_VMGEXIT_AP_CREATE_ON_INIT 0 +#define SVM_VMGEXIT_AP_CREATE 1 +#define SVM_VMGEXIT_AP_DESTROY 2 +#define SVM_VMGEXIT_HV_FEATURES 0x8000fffd #define SVM_VMGEXIT_UNSUPPORTED_EVENT 0x8000ffff /* Exit code reserved for hypervisor/software use */ @@ -218,6 +226,11 @@ { SVM_VMGEXIT_NMI_COMPLETE, "vmgexit_nmi_complete" }, \ { SVM_VMGEXIT_AP_HLT_LOOP, "vmgexit_ap_hlt_loop" }, \ { SVM_VMGEXIT_AP_JUMP_TABLE, "vmgexit_ap_jump_table" }, \ + { SVM_VMGEXIT_PSC, "vmgexit_page_state_change" }, \ + { SVM_VMGEXIT_GUEST_REQUEST, "vmgexit_guest_request" }, \ + { SVM_VMGEXIT_EXT_GUEST_REQUEST, "vmgexit_ext_guest_request" }, \ + { SVM_VMGEXIT_AP_CREATION, "vmgexit_ap_creation" }, \ + { SVM_VMGEXIT_HV_FEATURES, "vmgexit_hypervisor_feature" }, \ { SVM_EXIT_ERR, "invalid_guest_state" } diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile index c41ef42adbe8..1a2dc328cb5e 100644 --- a/arch/x86/kernel/Makefile +++ b/arch/x86/kernel/Makefile @@ -46,8 +46,6 @@ endif # non-deterministic coverage. KCOV_INSTRUMENT := n -CFLAGS_head$(BITS).o += -fno-stack-protector - CFLAGS_irq.o := -I $(srctree)/$(src)/../include/asm/trace obj-y := process_$(BITS).o signal.o diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c index 0d01e7f5078c..6d2c50819501 100644 --- a/arch/x86/kernel/acpi/boot.c +++ b/arch/x86/kernel/acpi/boot.c @@ -65,6 +65,13 @@ static u64 acpi_lapic_addr __initdata = APIC_DEFAULT_PHYS_BASE; static bool acpi_support_online_capable; #endif +#ifdef CONFIG_X86_64 +/* Physical address of the Multiprocessor Wakeup Structure mailbox */ +static u64 acpi_mp_wake_mailbox_paddr; +/* Virtual address of the Multiprocessor Wakeup Structure mailbox */ +static struct acpi_madt_multiproc_wakeup_mailbox *acpi_mp_wake_mailbox; +#endif + #ifdef CONFIG_X86_IO_APIC /* * Locks related to IOAPIC hotplug @@ -336,7 +343,60 @@ acpi_parse_lapic_nmi(union acpi_subtable_headers * header, const unsigned long e return 0; } -#endif /*CONFIG_X86_LOCAL_APIC */ +#ifdef CONFIG_X86_64 +static int acpi_wakeup_cpu(int apicid, unsigned long start_ip) +{ + /* + * Remap mailbox memory only for the first call to acpi_wakeup_cpu(). + * + * Wakeup of secondary CPUs is fully serialized in the core code. + * No need to protect acpi_mp_wake_mailbox from concurrent accesses. + */ + if (!acpi_mp_wake_mailbox) { + acpi_mp_wake_mailbox = memremap(acpi_mp_wake_mailbox_paddr, + sizeof(*acpi_mp_wake_mailbox), + MEMREMAP_WB); + } + + /* + * Mailbox memory is shared between the firmware and OS. Firmware will + * listen on mailbox command address, and once it receives the wakeup + * command, the CPU associated with the given apicid will be booted. + * + * The value of 'apic_id' and 'wakeup_vector' must be visible to the + * firmware before the wakeup command is visible. smp_store_release() + * ensures ordering and visibility. + */ + acpi_mp_wake_mailbox->apic_id = apicid; + acpi_mp_wake_mailbox->wakeup_vector = start_ip; + smp_store_release(&acpi_mp_wake_mailbox->command, + ACPI_MP_WAKE_COMMAND_WAKEUP); + + /* + * Wait for the CPU to wake up. + * + * The CPU being woken up is essentially in a spin loop waiting to be + * woken up. It should not take long for it wake up and acknowledge by + * zeroing out ->command. + * + * ACPI specification doesn't provide any guidance on how long kernel + * has to wait for a wake up acknowledgement. It also doesn't provide + * a way to cancel a wake up request if it takes too long. + * + * In TDX environment, the VMM has control over how long it takes to + * wake up secondary. It can postpone scheduling secondary vCPU + * indefinitely. Giving up on wake up request and reporting error opens + * possible attack vector for VMM: it can wake up a secondary CPU when + * kernel doesn't expect it. Wait until positive result of the wake up + * request. + */ + while (READ_ONCE(acpi_mp_wake_mailbox->command)) + cpu_relax(); + + return 0; +} +#endif /* CONFIG_X86_64 */ +#endif /* CONFIG_X86_LOCAL_APIC */ #ifdef CONFIG_X86_IO_APIC #define MP_ISA_BUS 0 @@ -1083,6 +1143,29 @@ static int __init acpi_parse_madt_lapic_entries(void) } return 0; } + +#ifdef CONFIG_X86_64 +static int __init acpi_parse_mp_wake(union acpi_subtable_headers *header, + const unsigned long end) +{ + struct acpi_madt_multiproc_wakeup *mp_wake; + + if (!IS_ENABLED(CONFIG_SMP)) + return -ENODEV; + + mp_wake = (struct acpi_madt_multiproc_wakeup *)header; + if (BAD_MADT_ENTRY(mp_wake, end)) + return -EINVAL; + + acpi_table_print_madt_entry(&header->common); + + acpi_mp_wake_mailbox_paddr = mp_wake->base_address; + + acpi_wake_cpu_handler_update(acpi_wakeup_cpu); + + return 0; +} +#endif /* CONFIG_X86_64 */ #endif /* CONFIG_X86_LOCAL_APIC */ #ifdef CONFIG_X86_IO_APIC @@ -1278,6 +1361,14 @@ static void __init acpi_process_madt(void) smp_found_config = 1; } + +#ifdef CONFIG_X86_64 + /* + * Parse MADT MP Wake entry. + */ + acpi_table_parse_madt(ACPI_MADT_TYPE_MULTIPROC_WAKEUP, + acpi_parse_mp_wake, 1); +#endif } if (error == -EINVAL) { /* diff --git a/arch/x86/kernel/acpi/cppc.c b/arch/x86/kernel/acpi/cppc.c index df1644d9b3b6..8b8cbf22461a 100644 --- a/arch/x86/kernel/acpi/cppc.c +++ b/arch/x86/kernel/acpi/cppc.c @@ -50,20 +50,17 @@ int cpc_write_ffh(int cpunum, struct cpc_reg *reg, u64 val) return err; } -bool amd_set_max_freq_ratio(u64 *ratio) +static void amd_set_max_freq_ratio(void) { struct cppc_perf_caps perf_caps; u64 highest_perf, nominal_perf; u64 perf_ratio; int rc; - if (!ratio) - return false; - rc = cppc_get_perf_caps(0, &perf_caps); if (rc) { pr_debug("Could not retrieve perf counters (%d)\n", rc); - return false; + return; } highest_perf = amd_get_highest_perf(); @@ -71,7 +68,7 @@ bool amd_set_max_freq_ratio(u64 *ratio) if (!highest_perf || !nominal_perf) { pr_debug("Could not retrieve highest or nominal performance\n"); - return false; + return; } perf_ratio = div_u64(highest_perf * SCHED_CAPACITY_SCALE, nominal_perf); @@ -79,25 +76,27 @@ bool amd_set_max_freq_ratio(u64 *ratio) perf_ratio = (perf_ratio + SCHED_CAPACITY_SCALE) >> 1; if (!perf_ratio) { pr_debug("Non-zero highest/nominal perf values led to a 0 ratio\n"); - return false; + return; } - *ratio = perf_ratio; - arch_set_max_freq_ratio(false); - - return true; + freq_invariance_set_perf_ratio(perf_ratio, false); } static DEFINE_MUTEX(freq_invariance_lock); void init_freq_invariance_cppc(void) { - static bool secondary; + static bool init_done; - mutex_lock(&freq_invariance_lock); + if (!cpu_feature_enabled(X86_FEATURE_APERFMPERF)) + return; - init_freq_invariance(secondary, true); - secondary = true; + if (boot_cpu_data.x86_vendor != X86_VENDOR_AMD) + return; + mutex_lock(&freq_invariance_lock); + if (!init_done) + amd_set_max_freq_ratio(); + init_done = true; mutex_unlock(&freq_invariance_lock); } diff --git a/arch/x86/kernel/amd_nb.c b/arch/x86/kernel/amd_nb.c index 020c906f7934..190e0f763375 100644 --- a/arch/x86/kernel/amd_nb.c +++ b/arch/x86/kernel/amd_nb.c @@ -188,7 +188,7 @@ int amd_smn_write(u16 node, u32 address, u32 value) EXPORT_SYMBOL_GPL(amd_smn_write); -int amd_cache_northbridges(void) +static int amd_cache_northbridges(void) { const struct pci_device_id *misc_ids = amd_nb_misc_ids; const struct pci_device_id *link_ids = amd_nb_link_ids; @@ -210,14 +210,14 @@ int amd_cache_northbridges(void) } misc = NULL; - while ((misc = next_northbridge(misc, misc_ids)) != NULL) + while ((misc = next_northbridge(misc, misc_ids))) misc_count++; if (!misc_count) return -ENODEV; root = NULL; - while ((root = next_northbridge(root, root_ids)) != NULL) + while ((root = next_northbridge(root, root_ids))) root_count++; if (root_count) { @@ -290,7 +290,6 @@ int amd_cache_northbridges(void) return 0; } -EXPORT_SYMBOL_GPL(amd_cache_northbridges); /* * Ignores subdevice/subvendor but as far as I can figure out diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c index b70344bf6600..189d3a5e471a 100644 --- a/arch/x86/kernel/apic/apic.c +++ b/arch/x86/kernel/apic/apic.c @@ -170,7 +170,7 @@ static __init int setup_apicpmtimer(char *s) { apic_calibrate_pmtmr = 1; notsc_setup(NULL); - return 0; + return 1; } __setup("apicpmtimer", setup_apicpmtimer); #endif @@ -320,6 +320,9 @@ int lapic_get_maxlvt(void) #define APIC_DIVISOR 16 #define TSC_DIVISOR 8 +/* i82489DX specific */ +#define I82489DX_BASE_DIVIDER (((0x2) << 18)) + /* * This function sets up the local APIC timer, with a timeout of * 'clocks' APIC bus clock. During calibration we actually call @@ -340,8 +343,14 @@ static void __setup_APIC_LVTT(unsigned int clocks, int oneshot, int irqen) else if (boot_cpu_has(X86_FEATURE_TSC_DEADLINE_TIMER)) lvtt_value |= APIC_LVT_TIMER_TSCDEADLINE; + /* + * The i82489DX APIC uses bit 18 and 19 for the base divider. This + * overlaps with bit 18 on integrated APICs, but is not documented + * in the SDM. No problem though. i82489DX equipped systems do not + * have TSC deadline timer. + */ if (!lapic_is_integrated()) - lvtt_value |= SET_APIC_TIMER_BASE(APIC_TIMER_BASE_DIV); + lvtt_value |= I82489DX_BASE_DIVIDER; if (!irqen) lvtt_value |= APIC_LVT_MASKED; @@ -1419,22 +1428,21 @@ void __init apic_intr_mode_init(void) return; case APIC_VIRTUAL_WIRE: pr_info("APIC: Switch to virtual wire mode setup\n"); - default_setup_apic_routing(); break; case APIC_VIRTUAL_WIRE_NO_CONFIG: pr_info("APIC: Switch to virtual wire mode setup with no configuration\n"); upmode = true; - default_setup_apic_routing(); break; case APIC_SYMMETRIC_IO: pr_info("APIC: Switch to symmetric I/O mode setup\n"); - default_setup_apic_routing(); break; case APIC_SYMMETRIC_IO_NO_ROUTING: pr_info("APIC: Switch to symmetric I/O mode setup in no SMP routine\n"); break; } + default_setup_apic_routing(); + if (x86_platform.apic_post_init) x86_platform.apic_post_init(); @@ -2551,6 +2559,16 @@ u32 x86_msi_msg_get_destid(struct msi_msg *msg, bool extid) } EXPORT_SYMBOL_GPL(x86_msi_msg_get_destid); +#ifdef CONFIG_X86_64 +void __init acpi_wake_cpu_handler_update(wakeup_cpu_handler handler) +{ + struct apic **drv; + + for (drv = __apicdrivers; drv < __apicdrivers_end; drv++) + (*drv)->wakeup_secondary_cpu_64 = handler; +} +#endif + /* * Override the generic EOI implementation with an optimized version. * Only called during early boot when only one CPU is active and with diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c index c1bb384935b0..a868b76cd3d4 100644 --- a/arch/x86/kernel/apic/io_apic.c +++ b/arch/x86/kernel/apic/io_apic.c @@ -65,6 +65,7 @@ #include <asm/irq_remapping.h> #include <asm/hw_irq.h> #include <asm/apic.h> +#include <asm/pgtable.h> #define for_each_ioapic(idx) \ for ((idx) = 0; (idx) < nr_ioapics; (idx)++) @@ -2677,6 +2678,19 @@ static struct resource * __init ioapic_setup_resources(void) return res; } +static void io_apic_set_fixmap(enum fixed_addresses idx, phys_addr_t phys) +{ + pgprot_t flags = FIXMAP_PAGE_NOCACHE; + + /* + * Ensure fixmaps for IOAPIC MMIO respect memory encryption pgprot + * bits, just like normal ioremap(): + */ + flags = pgprot_decrypted(flags); + + __set_fixmap(idx, phys, flags); +} + void __init io_apic_init_mappings(void) { unsigned long ioapic_phys, idx = FIX_IO_APIC_BASE_0; @@ -2709,7 +2723,7 @@ fake_ioapic_page: __func__, PAGE_SIZE, PAGE_SIZE); ioapic_phys = __pa(ioapic_phys); } - set_fixmap_nocache(idx, ioapic_phys); + io_apic_set_fixmap(idx, ioapic_phys); apic_printk(APIC_VERBOSE, "mapped IOAPIC to %08lx (%08lx)\n", __fix_to_virt(idx) + (ioapic_phys & ~PAGE_MASK), ioapic_phys); @@ -2838,7 +2852,7 @@ int mp_register_ioapic(int id, u32 address, u32 gsi_base, ioapics[idx].mp_config.flags = MPC_APIC_USABLE; ioapics[idx].mp_config.apicaddr = address; - set_fixmap_nocache(FIX_IO_APIC_BASE_0 + idx, address); + io_apic_set_fixmap(FIX_IO_APIC_BASE_0 + idx, address); if (bad_ioapic_register(idx)) { clear_fixmap(FIX_IO_APIC_BASE_0 + idx); return -ENODEV; diff --git a/arch/x86/kernel/apic/x2apic_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c index f5a48e66e4f5..482855227964 100644 --- a/arch/x86/kernel/apic/x2apic_uv_x.c +++ b/arch/x86/kernel/apic/x2apic_uv_x.c @@ -199,7 +199,13 @@ static void __init uv_tsc_check_sync(void) int mmr_shift; char *state; - /* Different returns from different UV BIOS versions */ + /* UV5 guarantees synced TSCs; do not zero TSC_ADJUST */ + if (!is_uv(UV2|UV3|UV4)) { + mark_tsc_async_resets("UV5+"); + return; + } + + /* UV2,3,4, UV BIOS TSC sync state available */ mmr = uv_early_read_mmr(UVH_TSC_SYNC_MMR); mmr_shift = is_uv2_hub() ? UVH_TSC_SYNC_SHIFT_UV2K : UVH_TSC_SYNC_SHIFT; @@ -1340,7 +1346,7 @@ static void __init decode_gam_params(unsigned long ptr) static void __init decode_gam_rng_tbl(unsigned long ptr) { struct uv_gam_range_entry *gre = (struct uv_gam_range_entry *)ptr; - unsigned long lgre = 0; + unsigned long lgre = 0, gend = 0; int index = 0; int sock_min = 999999, pnode_min = 99999; int sock_max = -1, pnode_max = -1; @@ -1374,6 +1380,9 @@ static void __init decode_gam_rng_tbl(unsigned long ptr) flag, size, suffix[order], gre->type, gre->nasid, gre->sockid, gre->pnode); + if (gre->type == UV_GAM_RANGE_TYPE_HOLE) + gend = (unsigned long)gre->limit << UV_GAM_RANGE_SHFT; + /* update to next range start */ lgre = gre->limit; if (sock_min > gre->sockid) @@ -1391,7 +1400,8 @@ static void __init decode_gam_rng_tbl(unsigned long ptr) _max_pnode = pnode_max; _gr_table_len = index; - pr_info("UV: GRT: %d entries, sockets(min:%x,max:%x) pnodes(min:%x,max:%x)\n", index, _min_socket, _max_socket, _min_pnode, _max_pnode); + pr_info("UV: GRT: %d entries, sockets(min:%x,max:%x), pnodes(min:%x,max:%x), gap_end(%d)\n", + index, _min_socket, _max_socket, _min_pnode, _max_pnode, fls64(gend)); } /* Walk through UVsystab decoding the fields */ diff --git a/arch/x86/kernel/asm-offsets.c b/arch/x86/kernel/asm-offsets.c index 9fb0a2f8b62a..437308004ef2 100644 --- a/arch/x86/kernel/asm-offsets.c +++ b/arch/x86/kernel/asm-offsets.c @@ -18,6 +18,7 @@ #include <asm/bootparam.h> #include <asm/suspend.h> #include <asm/tlbflush.h> +#include <asm/tdx.h> #ifdef CONFIG_XEN #include <xen/interface/xen.h> @@ -66,6 +67,22 @@ static void __used common(void) #endif BLANK(); + OFFSET(TDX_MODULE_rcx, tdx_module_output, rcx); + OFFSET(TDX_MODULE_rdx, tdx_module_output, rdx); + OFFSET(TDX_MODULE_r8, tdx_module_output, r8); + OFFSET(TDX_MODULE_r9, tdx_module_output, r9); + OFFSET(TDX_MODULE_r10, tdx_module_output, r10); + OFFSET(TDX_MODULE_r11, tdx_module_output, r11); + + BLANK(); + OFFSET(TDX_HYPERCALL_r10, tdx_hypercall_args, r10); + OFFSET(TDX_HYPERCALL_r11, tdx_hypercall_args, r11); + OFFSET(TDX_HYPERCALL_r12, tdx_hypercall_args, r12); + OFFSET(TDX_HYPERCALL_r13, tdx_hypercall_args, r13); + OFFSET(TDX_HYPERCALL_r14, tdx_hypercall_args, r14); + OFFSET(TDX_HYPERCALL_r15, tdx_hypercall_args, r15); + + BLANK(); OFFSET(BP_scratch, boot_params, scratch); OFFSET(BP_secure_boot, boot_params, secure_boot); OFFSET(BP_loadflags, boot_params, hdr.loadflags); diff --git a/arch/x86/kernel/cpu/aperfmperf.c b/arch/x86/kernel/cpu/aperfmperf.c index 9ca008f9e9b1..1f60a2b27936 100644 --- a/arch/x86/kernel/cpu/aperfmperf.c +++ b/arch/x86/kernel/cpu/aperfmperf.c @@ -6,146 +6,446 @@ * Copyright (C) 2017 Intel Corp. * Author: Len Brown <len.brown@intel.com> */ - +#include <linux/cpufreq.h> #include <linux/delay.h> #include <linux/ktime.h> #include <linux/math64.h> #include <linux/percpu.h> -#include <linux/cpufreq.h> -#include <linux/smp.h> -#include <linux/sched/isolation.h> #include <linux/rcupdate.h> +#include <linux/sched/isolation.h> +#include <linux/sched/topology.h> +#include <linux/smp.h> +#include <linux/syscore_ops.h> + +#include <asm/cpu.h> +#include <asm/cpu_device_id.h> +#include <asm/intel-family.h> #include "cpu.h" -struct aperfmperf_sample { - unsigned int khz; - atomic_t scfpending; - ktime_t time; - u64 aperf; - u64 mperf; +struct aperfmperf { + seqcount_t seq; + unsigned long last_update; + u64 acnt; + u64 mcnt; + u64 aperf; + u64 mperf; }; -static DEFINE_PER_CPU(struct aperfmperf_sample, samples); +static DEFINE_PER_CPU_SHARED_ALIGNED(struct aperfmperf, cpu_samples) = { + .seq = SEQCNT_ZERO(cpu_samples.seq) +}; -#define APERFMPERF_CACHE_THRESHOLD_MS 10 -#define APERFMPERF_REFRESH_DELAY_MS 10 -#define APERFMPERF_STALE_THRESHOLD_MS 1000 +static void init_counter_refs(void) +{ + u64 aperf, mperf; + + rdmsrl(MSR_IA32_APERF, aperf); + rdmsrl(MSR_IA32_MPERF, mperf); + this_cpu_write(cpu_samples.aperf, aperf); + this_cpu_write(cpu_samples.mperf, mperf); +} + +#if defined(CONFIG_X86_64) && defined(CONFIG_SMP) /* - * aperfmperf_snapshot_khz() - * On the current CPU, snapshot APERF, MPERF, and jiffies - * unless we already did it within 10ms - * calculate kHz, save snapshot + * APERF/MPERF frequency ratio computation. + * + * The scheduler wants to do frequency invariant accounting and needs a <1 + * ratio to account for the 'current' frequency, corresponding to + * freq_curr / freq_max. + * + * Since the frequency freq_curr on x86 is controlled by micro-controller and + * our P-state setting is little more than a request/hint, we need to observe + * the effective frequency 'BusyMHz', i.e. the average frequency over a time + * interval after discarding idle time. This is given by: + * + * BusyMHz = delta_APERF / delta_MPERF * freq_base + * + * where freq_base is the max non-turbo P-state. + * + * The freq_max term has to be set to a somewhat arbitrary value, because we + * can't know which turbo states will be available at a given point in time: + * it all depends on the thermal headroom of the entire package. We set it to + * the turbo level with 4 cores active. + * + * Benchmarks show that's a good compromise between the 1C turbo ratio + * (freq_curr/freq_max would rarely reach 1) and something close to freq_base, + * which would ignore the entire turbo range (a conspicuous part, making + * freq_curr/freq_max always maxed out). + * + * An exception to the heuristic above is the Atom uarch, where we choose the + * highest turbo level for freq_max since Atom's are generally oriented towards + * power efficiency. + * + * Setting freq_max to anything less than the 1C turbo ratio makes the ratio + * freq_curr / freq_max to eventually grow >1, in which case we clip it to 1. */ -static void aperfmperf_snapshot_khz(void *dummy) + +DEFINE_STATIC_KEY_FALSE(arch_scale_freq_key); + +static u64 arch_turbo_freq_ratio = SCHED_CAPACITY_SCALE; +static u64 arch_max_freq_ratio = SCHED_CAPACITY_SCALE; + +void arch_set_max_freq_ratio(bool turbo_disabled) { - u64 aperf, aperf_delta; - u64 mperf, mperf_delta; - struct aperfmperf_sample *s = this_cpu_ptr(&samples); - unsigned long flags; + arch_max_freq_ratio = turbo_disabled ? SCHED_CAPACITY_SCALE : + arch_turbo_freq_ratio; +} +EXPORT_SYMBOL_GPL(arch_set_max_freq_ratio); - local_irq_save(flags); - rdmsrl(MSR_IA32_APERF, aperf); - rdmsrl(MSR_IA32_MPERF, mperf); - local_irq_restore(flags); +static bool __init turbo_disabled(void) +{ + u64 misc_en; + int err; + + err = rdmsrl_safe(MSR_IA32_MISC_ENABLE, &misc_en); + if (err) + return false; + + return (misc_en & MSR_IA32_MISC_ENABLE_TURBO_DISABLE); +} + +static bool __init slv_set_max_freq_ratio(u64 *base_freq, u64 *turbo_freq) +{ + int err; + + err = rdmsrl_safe(MSR_ATOM_CORE_RATIOS, base_freq); + if (err) + return false; + + err = rdmsrl_safe(MSR_ATOM_CORE_TURBO_RATIOS, turbo_freq); + if (err) + return false; + + *base_freq = (*base_freq >> 16) & 0x3F; /* max P state */ + *turbo_freq = *turbo_freq & 0x3F; /* 1C turbo */ + + return true; +} + +#define X86_MATCH(model) \ + X86_MATCH_VENDOR_FAM_MODEL_FEATURE(INTEL, 6, \ + INTEL_FAM6_##model, X86_FEATURE_APERFMPERF, NULL) + +static const struct x86_cpu_id has_knl_turbo_ratio_limits[] __initconst = { + X86_MATCH(XEON_PHI_KNL), + X86_MATCH(XEON_PHI_KNM), + {} +}; + +static const struct x86_cpu_id has_skx_turbo_ratio_limits[] __initconst = { + X86_MATCH(SKYLAKE_X), + {} +}; + +static const struct x86_cpu_id has_glm_turbo_ratio_limits[] __initconst = { + X86_MATCH(ATOM_GOLDMONT), + X86_MATCH(ATOM_GOLDMONT_D), + X86_MATCH(ATOM_GOLDMONT_PLUS), + {} +}; + +static bool __init knl_set_max_freq_ratio(u64 *base_freq, u64 *turbo_freq, + int num_delta_fratio) +{ + int fratio, delta_fratio, found; + int err, i; + u64 msr; + + err = rdmsrl_safe(MSR_PLATFORM_INFO, base_freq); + if (err) + return false; + + *base_freq = (*base_freq >> 8) & 0xFF; /* max P state */ + + err = rdmsrl_safe(MSR_TURBO_RATIO_LIMIT, &msr); + if (err) + return false; + + fratio = (msr >> 8) & 0xFF; + i = 16; + found = 0; + do { + if (found >= num_delta_fratio) { + *turbo_freq = fratio; + return true; + } + + delta_fratio = (msr >> (i + 5)) & 0x7; + + if (delta_fratio) { + found += 1; + fratio -= delta_fratio; + } + + i += 8; + } while (i < 64); + + return true; +} + +static bool __init skx_set_max_freq_ratio(u64 *base_freq, u64 *turbo_freq, int size) +{ + u64 ratios, counts; + u32 group_size; + int err, i; + + err = rdmsrl_safe(MSR_PLATFORM_INFO, base_freq); + if (err) + return false; + + *base_freq = (*base_freq >> 8) & 0xFF; /* max P state */ + + err = rdmsrl_safe(MSR_TURBO_RATIO_LIMIT, &ratios); + if (err) + return false; + + err = rdmsrl_safe(MSR_TURBO_RATIO_LIMIT1, &counts); + if (err) + return false; + + for (i = 0; i < 64; i += 8) { + group_size = (counts >> i) & 0xFF; + if (group_size >= size) { + *turbo_freq = (ratios >> i) & 0xFF; + return true; + } + } + + return false; +} - aperf_delta = aperf - s->aperf; - mperf_delta = mperf - s->mperf; +static bool __init core_set_max_freq_ratio(u64 *base_freq, u64 *turbo_freq) +{ + u64 msr; + int err; + + err = rdmsrl_safe(MSR_PLATFORM_INFO, base_freq); + if (err) + return false; + + err = rdmsrl_safe(MSR_TURBO_RATIO_LIMIT, &msr); + if (err) + return false; + + *base_freq = (*base_freq >> 8) & 0xFF; /* max P state */ + *turbo_freq = (msr >> 24) & 0xFF; /* 4C turbo */ + + /* The CPU may have less than 4 cores */ + if (!*turbo_freq) + *turbo_freq = msr & 0xFF; /* 1C turbo */ + + return true; +} + +static bool __init intel_set_max_freq_ratio(void) +{ + u64 base_freq, turbo_freq; + u64 turbo_ratio; + if (slv_set_max_freq_ratio(&base_freq, &turbo_freq)) + goto out; + + if (x86_match_cpu(has_glm_turbo_ratio_limits) && + skx_set_max_freq_ratio(&base_freq, &turbo_freq, 1)) + goto out; + + if (x86_match_cpu(has_knl_turbo_ratio_limits) && + knl_set_max_freq_ratio(&base_freq, &turbo_freq, 1)) + goto out; + + if (x86_match_cpu(has_skx_turbo_ratio_limits) && + skx_set_max_freq_ratio(&base_freq, &turbo_freq, 4)) + goto out; + + if (core_set_max_freq_ratio(&base_freq, &turbo_freq)) + goto out; + + return false; + +out: /* - * There is no architectural guarantee that MPERF - * increments faster than we can read it. + * Some hypervisors advertise X86_FEATURE_APERFMPERF + * but then fill all MSR's with zeroes. + * Some CPUs have turbo boost but don't declare any turbo ratio + * in MSR_TURBO_RATIO_LIMIT. */ - if (mperf_delta == 0) - return; + if (!base_freq || !turbo_freq) { + pr_debug("Couldn't determine cpu base or turbo frequency, necessary for scale-invariant accounting.\n"); + return false; + } - s->time = ktime_get(); - s->aperf = aperf; - s->mperf = mperf; - s->khz = div64_u64((cpu_khz * aperf_delta), mperf_delta); - atomic_set_release(&s->scfpending, 0); + turbo_ratio = div_u64(turbo_freq * SCHED_CAPACITY_SCALE, base_freq); + if (!turbo_ratio) { + pr_debug("Non-zero turbo and base frequencies led to a 0 ratio.\n"); + return false; + } + + arch_turbo_freq_ratio = turbo_ratio; + arch_set_max_freq_ratio(turbo_disabled()); + + return true; } -static bool aperfmperf_snapshot_cpu(int cpu, ktime_t now, bool wait) +#ifdef CONFIG_PM_SLEEP +static struct syscore_ops freq_invariance_syscore_ops = { + .resume = init_counter_refs, +}; + +static void register_freq_invariance_syscore_ops(void) { - s64 time_delta = ktime_ms_delta(now, per_cpu(samples.time, cpu)); - struct aperfmperf_sample *s = per_cpu_ptr(&samples, cpu); + register_syscore_ops(&freq_invariance_syscore_ops); +} +#else +static inline void register_freq_invariance_syscore_ops(void) {} +#endif - /* Don't bother re-computing within the cache threshold time. */ - if (time_delta < APERFMPERF_CACHE_THRESHOLD_MS) - return true; +static void freq_invariance_enable(void) +{ + if (static_branch_unlikely(&arch_scale_freq_key)) { + WARN_ON_ONCE(1); + return; + } + static_branch_enable(&arch_scale_freq_key); + register_freq_invariance_syscore_ops(); + pr_info("Estimated ratio of average max frequency by base frequency (times 1024): %llu\n", arch_max_freq_ratio); +} + +void freq_invariance_set_perf_ratio(u64 ratio, bool turbo_disabled) +{ + arch_turbo_freq_ratio = ratio; + arch_set_max_freq_ratio(turbo_disabled); + freq_invariance_enable(); +} + +static void __init bp_init_freq_invariance(void) +{ + if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL) + return; - if (!atomic_xchg(&s->scfpending, 1) || wait) - smp_call_function_single(cpu, aperfmperf_snapshot_khz, NULL, wait); + if (intel_set_max_freq_ratio()) + freq_invariance_enable(); +} - /* Return false if the previous iteration was too long ago. */ - return time_delta <= APERFMPERF_STALE_THRESHOLD_MS; +static void disable_freq_invariance_workfn(struct work_struct *work) +{ + static_branch_disable(&arch_scale_freq_key); } -unsigned int aperfmperf_get_khz(int cpu) +static DECLARE_WORK(disable_freq_invariance_work, + disable_freq_invariance_workfn); + +DEFINE_PER_CPU(unsigned long, arch_freq_scale) = SCHED_CAPACITY_SCALE; + +static void scale_freq_tick(u64 acnt, u64 mcnt) { - if (!cpu_khz) - return 0; + u64 freq_scale; - if (!boot_cpu_has(X86_FEATURE_APERFMPERF)) - return 0; + if (!arch_scale_freq_invariant()) + return; - if (!housekeeping_cpu(cpu, HK_TYPE_MISC)) - return 0; + if (check_shl_overflow(acnt, 2*SCHED_CAPACITY_SHIFT, &acnt)) + goto error; - if (rcu_is_idle_cpu(cpu)) - return 0; /* Idle CPUs are completely uninteresting. */ + if (check_mul_overflow(mcnt, arch_max_freq_ratio, &mcnt) || !mcnt) + goto error; - aperfmperf_snapshot_cpu(cpu, ktime_get(), true); - return per_cpu(samples.khz, cpu); + freq_scale = div64_u64(acnt, mcnt); + if (!freq_scale) + goto error; + + if (freq_scale > SCHED_CAPACITY_SCALE) + freq_scale = SCHED_CAPACITY_SCALE; + + this_cpu_write(arch_freq_scale, freq_scale); + return; + +error: + pr_warn("Scheduler frequency invariance went wobbly, disabling!\n"); + schedule_work(&disable_freq_invariance_work); } +#else +static inline void bp_init_freq_invariance(void) { } +static inline void scale_freq_tick(u64 acnt, u64 mcnt) { } +#endif /* CONFIG_X86_64 && CONFIG_SMP */ -void arch_freq_prepare_all(void) +void arch_scale_freq_tick(void) { - ktime_t now = ktime_get(); - bool wait = false; - int cpu; + struct aperfmperf *s = this_cpu_ptr(&cpu_samples); + u64 acnt, mcnt, aperf, mperf; - if (!cpu_khz) + if (!cpu_feature_enabled(X86_FEATURE_APERFMPERF)) return; - if (!boot_cpu_has(X86_FEATURE_APERFMPERF)) - return; + rdmsrl(MSR_IA32_APERF, aperf); + rdmsrl(MSR_IA32_MPERF, mperf); + acnt = aperf - s->aperf; + mcnt = mperf - s->mperf; - for_each_online_cpu(cpu) { - if (!housekeeping_cpu(cpu, HK_TYPE_MISC)) - continue; - if (rcu_is_idle_cpu(cpu)) - continue; /* Idle CPUs are completely uninteresting. */ - if (!aperfmperf_snapshot_cpu(cpu, now, false)) - wait = true; - } + s->aperf = aperf; + s->mperf = mperf; + + raw_write_seqcount_begin(&s->seq); + s->last_update = jiffies; + s->acnt = acnt; + s->mcnt = mcnt; + raw_write_seqcount_end(&s->seq); - if (wait) - msleep(APERFMPERF_REFRESH_DELAY_MS); + scale_freq_tick(acnt, mcnt); } +/* + * Discard samples older than the define maximum sample age of 20ms. There + * is no point in sending IPIs in such a case. If the scheduler tick was + * not running then the CPU is either idle or isolated. + */ +#define MAX_SAMPLE_AGE ((unsigned long)HZ / 50) + unsigned int arch_freq_get_on_cpu(int cpu) { - struct aperfmperf_sample *s = per_cpu_ptr(&samples, cpu); + struct aperfmperf *s = per_cpu_ptr(&cpu_samples, cpu); + unsigned int seq, freq; + unsigned long last; + u64 acnt, mcnt; - if (!cpu_khz) - return 0; + if (!cpu_feature_enabled(X86_FEATURE_APERFMPERF)) + goto fallback; - if (!boot_cpu_has(X86_FEATURE_APERFMPERF)) - return 0; + do { + seq = raw_read_seqcount_begin(&s->seq); + last = s->last_update; + acnt = s->acnt; + mcnt = s->mcnt; + } while (read_seqcount_retry(&s->seq, seq)); - if (!housekeeping_cpu(cpu, HK_TYPE_MISC)) - return 0; + /* + * Bail on invalid count and when the last update was too long ago, + * which covers idle and NOHZ full CPUs. + */ + if (!mcnt || (jiffies - last) > MAX_SAMPLE_AGE) + goto fallback; + + return div64_u64((cpu_khz * acnt), mcnt); + +fallback: + freq = cpufreq_quick_get(cpu); + return freq ? freq : cpu_khz; +} - if (aperfmperf_snapshot_cpu(cpu, ktime_get(), true)) - return per_cpu(samples.khz, cpu); +static int __init bp_init_aperfmperf(void) +{ + if (!cpu_feature_enabled(X86_FEATURE_APERFMPERF)) + return 0; - msleep(APERFMPERF_REFRESH_DELAY_MS); - atomic_set(&s->scfpending, 1); - smp_mb(); /* ->scfpending before smp_call_function_single(). */ - smp_call_function_single(cpu, aperfmperf_snapshot_khz, NULL, 1); + init_counter_refs(); + bp_init_freq_invariance(); + return 0; +} +early_initcall(bp_init_aperfmperf); - return per_cpu(samples.khz, cpu); +void ap_init_aperfmperf(void) +{ + if (cpu_feature_enabled(X86_FEATURE_APERFMPERF)) + init_counter_refs(); } diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index 6296e1ebed1d..d879a6c93609 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -446,6 +446,13 @@ void update_srbds_msr(void) if (srbds_mitigation == SRBDS_MITIGATION_UCODE_NEEDED) return; + /* + * A MDS_NO CPU for which SRBDS mitigation is not needed due to TSX + * being disabled and it hasn't received the SRBDS MSR microcode. + */ + if (!boot_cpu_has(X86_FEATURE_SRBDS_CTRL)) + return; + rdmsrl(MSR_IA32_MCU_OPT_CTRL, mcu_ctrl); switch (srbds_mitigation) { diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index e342ae4db3c4..2e9142797c99 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -60,6 +60,7 @@ #include <asm/uv/uv.h> #include <asm/sigframe.h> #include <asm/traps.h> +#include <asm/sev.h> #include "cpu.h" @@ -298,13 +299,6 @@ static int __init cachesize_setup(char *str) } __setup("cachesize=", cachesize_setup); -static int __init x86_sep_setup(char *s) -{ - setup_clear_cpu_cap(X86_FEATURE_SEP); - return 1; -} -__setup("nosep", x86_sep_setup); - /* Standard macro to see if a specific flag is changeable */ static inline int flag_is_changeable_p(u32 flag) { @@ -376,26 +370,12 @@ static inline void squash_the_stupid_serial_number(struct cpuinfo_x86 *c) } #endif -static __init int setup_disable_smep(char *arg) -{ - setup_clear_cpu_cap(X86_FEATURE_SMEP); - return 1; -} -__setup("nosmep", setup_disable_smep); - static __always_inline void setup_smep(struct cpuinfo_x86 *c) { if (cpu_has(c, X86_FEATURE_SMEP)) cr4_set_bits(X86_CR4_SMEP); } -static __init int setup_disable_smap(char *arg) -{ - setup_clear_cpu_cap(X86_FEATURE_SMAP); - return 1; -} -__setup("nosmap", setup_disable_smap); - static __always_inline void setup_smap(struct cpuinfo_x86 *c) { unsigned long eflags = native_save_fl(); @@ -403,14 +383,8 @@ static __always_inline void setup_smap(struct cpuinfo_x86 *c) /* This should have been cleared long ago */ BUG_ON(eflags & X86_EFLAGS_AC); - if (cpu_has(c, X86_FEATURE_SMAP)) { -#ifdef CONFIG_X86_SMAP + if (cpu_has(c, X86_FEATURE_SMAP)) cr4_set_bits(X86_CR4_SMAP); -#else - clear_cpu_cap(c, X86_FEATURE_SMAP); - cr4_clear_bits(X86_CR4_SMAP); -#endif - } } static __always_inline void setup_umip(struct cpuinfo_x86 *c) @@ -1368,8 +1342,8 @@ static void detect_nopl(void) static void __init cpu_parse_early_param(void) { char arg[128]; - char *argptr = arg; - int arglen, res, bit; + char *argptr = arg, *opt; + int arglen, taint = 0; #ifdef CONFIG_X86_32 if (cmdline_find_option_bool(boot_command_line, "no387")) @@ -1397,21 +1371,61 @@ static void __init cpu_parse_early_param(void) return; pr_info("Clearing CPUID bits:"); - do { - res = get_option(&argptr, &bit); - if (res == 0 || res == 3) - break; - /* If the argument was too long, the last bit may be cut off */ - if (res == 1 && arglen >= sizeof(arg)) - break; + while (argptr) { + bool found __maybe_unused = false; + unsigned int bit; + + opt = strsep(&argptr, ","); + + /* + * Handle naked numbers first for feature flags which don't + * have names. + */ + if (!kstrtouint(opt, 10, &bit)) { + if (bit < NCAPINTS * 32) { + +#ifdef CONFIG_X86_FEATURE_NAMES + /* empty-string, i.e., ""-defined feature flags */ + if (!x86_cap_flags[bit]) + pr_cont(" " X86_CAP_FMT_NUM, x86_cap_flag_num(bit)); + else +#endif + pr_cont(" " X86_CAP_FMT, x86_cap_flag(bit)); + + setup_clear_cpu_cap(bit); + taint++; + } + /* + * The assumption is that there are no feature names with only + * numbers in the name thus go to the next argument. + */ + continue; + } + +#ifdef CONFIG_X86_FEATURE_NAMES + for (bit = 0; bit < 32 * NCAPINTS; bit++) { + if (!x86_cap_flag(bit)) + continue; - if (bit >= 0 && bit < NCAPINTS * 32) { - pr_cont(" " X86_CAP_FMT, x86_cap_flag(bit)); + if (strcmp(x86_cap_flag(bit), opt)) + continue; + + pr_cont(" %s", opt); setup_clear_cpu_cap(bit); + taint++; + found = true; + break; } - } while (res == 2); + + if (!found) + pr_cont(" (unknown: %s)", opt); +#endif + } pr_cont("\n"); + + if (taint) + add_taint(TAINT_CPU_OUT_OF_SPEC, LOCKDEP_STILL_OK); } /* @@ -1859,14 +1873,6 @@ void identify_secondary_cpu(struct cpuinfo_x86 *c) tsx_ap_init(); } -static __init int setup_noclflush(char *arg) -{ - setup_clear_cpu_cap(X86_FEATURE_CLFLUSH); - setup_clear_cpu_cap(X86_FEATURE_CLFLUSHOPT); - return 1; -} -__setup("noclflush", setup_noclflush); - void print_cpu_info(struct cpuinfo_x86 *c) { const char *vendor = NULL; @@ -2126,6 +2132,9 @@ void cpu_init_exception_handling(void) load_TR_desc(); + /* GHCB needs to be setup to handle #VC. */ + setup_ghcb(); + /* Finally load the IDT */ load_current_idt(); } diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c index f7a5370a9b3b..7860241a67db 100644 --- a/arch/x86/kernel/cpu/intel.c +++ b/arch/x86/kernel/cpu/intel.c @@ -7,10 +7,13 @@ #include <linux/smp.h> #include <linux/sched.h> #include <linux/sched/clock.h> +#include <linux/semaphore.h> #include <linux/thread_info.h> #include <linux/init.h> #include <linux/uaccess.h> +#include <linux/workqueue.h> #include <linux/delay.h> +#include <linux/cpuhotplug.h> #include <asm/cpufeature.h> #include <asm/msr.h> @@ -91,7 +94,7 @@ static bool ring3mwait_disabled __read_mostly; static int __init ring3mwait_disable(char *__unused) { ring3mwait_disabled = true; - return 0; + return 1; } __setup("ring3mwait=disable", ring3mwait_disable); @@ -999,6 +1002,8 @@ static const struct { static struct ratelimit_state bld_ratelimit; +static DEFINE_SEMAPHORE(buslock_sem); + static inline bool match_option(const char *arg, int arglen, const char *opt) { int len = strlen(opt), ratelimit; @@ -1109,18 +1114,52 @@ static void split_lock_init(void) split_lock_verify_msr(sld_state != sld_off); } +static void __split_lock_reenable(struct work_struct *work) +{ + sld_update_msr(true); + up(&buslock_sem); +} + +/* + * If a CPU goes offline with pending delayed work to re-enable split lock + * detection then the delayed work will be executed on some other CPU. That + * handles releasing the buslock_sem, but because it executes on a + * different CPU probably won't re-enable split lock detection. This is a + * problem on HT systems since the sibling CPU on the same core may then be + * left running with split lock detection disabled. + * + * Unconditionally re-enable detection here. + */ +static int splitlock_cpu_offline(unsigned int cpu) +{ + sld_update_msr(true); + + return 0; +} + +static DECLARE_DELAYED_WORK(split_lock_reenable, __split_lock_reenable); + static void split_lock_warn(unsigned long ip) { - pr_warn_ratelimited("#AC: %s/%d took a split_lock trap at address: 0x%lx\n", - current->comm, current->pid, ip); + int cpu; - /* - * Disable the split lock detection for this task so it can make - * progress and set TIF_SLD so the detection is re-enabled via - * switch_to_sld() when the task is scheduled out. - */ + if (!current->reported_split_lock) + pr_warn_ratelimited("#AC: %s/%d took a split_lock trap at address: 0x%lx\n", + current->comm, current->pid, ip); + current->reported_split_lock = 1; + + /* misery factor #1, sleep 10ms before trying to execute split lock */ + if (msleep_interruptible(10) > 0) + return; + /* Misery factor #2, only allow one buslocked disabled core at a time */ + if (down_interruptible(&buslock_sem) == -EINTR) + return; + cpu = get_cpu(); + schedule_delayed_work_on(cpu, &split_lock_reenable, 2); + + /* Disable split lock detection on this CPU to make progress */ sld_update_msr(false); - set_tsk_thread_flag(current, TIF_SLD); + put_cpu(); } bool handle_guest_split_lock(unsigned long ip) @@ -1194,18 +1233,6 @@ void handle_bus_lock(struct pt_regs *regs) } /* - * This function is called only when switching between tasks with - * different split-lock detection modes. It sets the MSR for the - * mode of the new task. This is right most of the time, but since - * the MSR is shared by hyperthreads on a physical core there can - * be glitches when the two threads need different modes. - */ -void switch_to_sld(unsigned long tifn) -{ - sld_update_msr(!(tifn & _TIF_SLD)); -} - -/* * Bits in the IA32_CORE_CAPABILITIES are not architectural, so they should * only be trusted if it is confirmed that a CPU model implements a * specific feature at a particular bit position. @@ -1230,6 +1257,7 @@ static const struct x86_cpu_id split_lock_cpu_ids[] __initconst = { X86_MATCH_INTEL_FAM6_MODEL(SAPPHIRERAPIDS_X, 1), X86_MATCH_INTEL_FAM6_MODEL(ALDERLAKE, 1), X86_MATCH_INTEL_FAM6_MODEL(ALDERLAKE_L, 1), + X86_MATCH_INTEL_FAM6_MODEL(RAPTORLAKE, 1), {} }; @@ -1274,10 +1302,14 @@ static void sld_state_show(void) pr_info("disabled\n"); break; case sld_warn: - if (boot_cpu_has(X86_FEATURE_SPLIT_LOCK_DETECT)) + if (boot_cpu_has(X86_FEATURE_SPLIT_LOCK_DETECT)) { pr_info("#AC: crashing the kernel on kernel split_locks and warning on user-space split_locks\n"); - else if (boot_cpu_has(X86_FEATURE_BUS_LOCK_DETECT)) + if (cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, + "x86/splitlock", NULL, splitlock_cpu_offline) < 0) + pr_warn("No splitlock CPU offline handler\n"); + } else if (boot_cpu_has(X86_FEATURE_BUS_LOCK_DETECT)) { pr_info("#DB: warning on user-space bus_locks\n"); + } break; case sld_fatal: if (boot_cpu_has(X86_FEATURE_SPLIT_LOCK_DETECT)) { diff --git a/arch/x86/kernel/cpu/mce/amd.c b/arch/x86/kernel/cpu/mce/amd.c index 1940d305db1c..1c87501e0fa3 100644 --- a/arch/x86/kernel/cpu/mce/amd.c +++ b/arch/x86/kernel/cpu/mce/amd.c @@ -1294,10 +1294,23 @@ out_free: kfree(bank); } +static void __threshold_remove_device(struct threshold_bank **bp) +{ + unsigned int bank, numbanks = this_cpu_read(mce_num_banks); + + for (bank = 0; bank < numbanks; bank++) { + if (!bp[bank]) + continue; + + threshold_remove_bank(bp[bank]); + bp[bank] = NULL; + } + kfree(bp); +} + int mce_threshold_remove_device(unsigned int cpu) { struct threshold_bank **bp = this_cpu_read(threshold_banks); - unsigned int bank, numbanks = this_cpu_read(mce_num_banks); if (!bp) return 0; @@ -1308,13 +1321,7 @@ int mce_threshold_remove_device(unsigned int cpu) */ this_cpu_write(threshold_banks, NULL); - for (bank = 0; bank < numbanks; bank++) { - if (bp[bank]) { - threshold_remove_bank(bp[bank]); - bp[bank] = NULL; - } - } - kfree(bp); + __threshold_remove_device(bp); return 0; } @@ -1351,15 +1358,14 @@ int mce_threshold_create_device(unsigned int cpu) if (!(this_cpu_read(bank_map) & (1 << bank))) continue; err = threshold_create_bank(bp, cpu, bank); - if (err) - goto out_err; + if (err) { + __threshold_remove_device(bp); + return err; + } } this_cpu_write(threshold_banks, bp); if (thresholding_irq_en) mce_threshold_vector = amd_threshold_interrupt; return 0; -out_err: - mce_threshold_remove_device(cpu); - return err; } diff --git a/arch/x86/kernel/cpu/mce/core.c b/arch/x86/kernel/cpu/mce/core.c index 981496e6bc0e..d775fcd74e98 100644 --- a/arch/x86/kernel/cpu/mce/core.c +++ b/arch/x86/kernel/cpu/mce/core.c @@ -69,7 +69,9 @@ DEFINE_PER_CPU_READ_MOSTLY(unsigned int, mce_num_banks); struct mce_bank { u64 ctl; /* subevents to enable */ - bool init; /* initialise bank? */ + + __u64 init : 1, /* initialise bank? */ + __reserved_1 : 63; }; static DEFINE_PER_CPU_READ_MOSTLY(struct mce_bank[MAX_NR_BANKS], mce_banks_array); diff --git a/arch/x86/kernel/cpu/mce/severity.c b/arch/x86/kernel/cpu/mce/severity.c index 1add86935349..00483d1c27e4 100644 --- a/arch/x86/kernel/cpu/mce/severity.c +++ b/arch/x86/kernel/cpu/mce/severity.c @@ -301,85 +301,65 @@ static noinstr int error_context(struct mce *m, struct pt_regs *regs) } } -static __always_inline int mce_severity_amd_smca(struct mce *m, enum context err_ctx) +/* See AMD PPR(s) section Machine Check Error Handling. */ +static noinstr int mce_severity_amd(struct mce *m, struct pt_regs *regs, char **msg, bool is_excp) { - u64 mcx_cfg; + char *panic_msg = NULL; + int ret; /* - * We need to look at the following bits: - * - "succor" bit (data poisoning support), and - * - TCC bit (Task Context Corrupt) - * in MCi_STATUS to determine error severity. + * Default return value: Action required, the error must be handled + * immediately. */ - if (!mce_flags.succor) - return MCE_PANIC_SEVERITY; - - mcx_cfg = mce_rdmsrl(MSR_AMD64_SMCA_MCx_CONFIG(m->bank)); - - /* TCC (Task context corrupt). If set and if IN_KERNEL, panic. */ - if ((mcx_cfg & MCI_CONFIG_MCAX) && - (m->status & MCI_STATUS_TCC) && - (err_ctx == IN_KERNEL)) - return MCE_PANIC_SEVERITY; - - /* ...otherwise invoke hwpoison handler. */ - return MCE_AR_SEVERITY; -} - -/* - * See AMD Error Scope Hierarchy table in a newer BKDG. For example - * 49125_15h_Models_30h-3Fh_BKDG.pdf, section "RAS Features" - */ -static noinstr int mce_severity_amd(struct mce *m, struct pt_regs *regs, char **msg, bool is_excp) -{ - enum context ctx = error_context(m, regs); + ret = MCE_AR_SEVERITY; /* Processor Context Corrupt, no need to fumble too much, die! */ - if (m->status & MCI_STATUS_PCC) - return MCE_PANIC_SEVERITY; - - if (m->status & MCI_STATUS_UC) { - - if (ctx == IN_KERNEL) - return MCE_PANIC_SEVERITY; + if (m->status & MCI_STATUS_PCC) { + panic_msg = "Processor Context Corrupt"; + ret = MCE_PANIC_SEVERITY; + goto out; + } - /* - * On older systems where overflow_recov flag is not present, we - * should simply panic if an error overflow occurs. If - * overflow_recov flag is present and set, then software can try - * to at least kill process to prolong system operation. - */ - if (mce_flags.overflow_recov) { - if (mce_flags.smca) - return mce_severity_amd_smca(m, ctx); - - /* kill current process */ - return MCE_AR_SEVERITY; - } else { - /* at least one error was not logged */ - if (m->status & MCI_STATUS_OVER) - return MCE_PANIC_SEVERITY; - } - - /* - * For any other case, return MCE_UC_SEVERITY so that we log the - * error and exit #MC handler. - */ - return MCE_UC_SEVERITY; + if (m->status & MCI_STATUS_DEFERRED) { + ret = MCE_DEFERRED_SEVERITY; + goto out; } /* - * deferred error: poll handler catches these and adds to mce_ring so - * memory-failure can take recovery actions. + * If the UC bit is not set, the system either corrected or deferred + * the error. No action will be required after logging the error. */ - if (m->status & MCI_STATUS_DEFERRED) - return MCE_DEFERRED_SEVERITY; + if (!(m->status & MCI_STATUS_UC)) { + ret = MCE_KEEP_SEVERITY; + goto out; + } /* - * corrected error: poll handler catches these and passes responsibility - * of decoding the error to EDAC + * On MCA overflow, without the MCA overflow recovery feature the + * system will not be able to recover, panic. */ - return MCE_KEEP_SEVERITY; + if ((m->status & MCI_STATUS_OVER) && !mce_flags.overflow_recov) { + panic_msg = "Overflowed uncorrected error without MCA Overflow Recovery"; + ret = MCE_PANIC_SEVERITY; + goto out; + } + + if (!mce_flags.succor) { + panic_msg = "Uncorrected error without MCA Recovery"; + ret = MCE_PANIC_SEVERITY; + goto out; + } + + if (error_context(m, regs) == IN_KERNEL) { + panic_msg = "Uncorrected unrecoverable error in kernel context"; + ret = MCE_PANIC_SEVERITY; + } + +out: + if (msg && panic_msg) + *msg = panic_msg; + + return ret; } static noinstr int mce_severity_intel(struct mce *m, struct pt_regs *regs, char **msg, bool is_excp) diff --git a/arch/x86/kernel/cpu/proc.c b/arch/x86/kernel/cpu/proc.c index 4eec8889b0ff..099b6f0d96bd 100644 --- a/arch/x86/kernel/cpu/proc.c +++ b/arch/x86/kernel/cpu/proc.c @@ -84,14 +84,9 @@ static int show_cpuinfo(struct seq_file *m, void *v) seq_printf(m, "microcode\t: 0x%x\n", c->microcode); if (cpu_has(c, X86_FEATURE_TSC)) { - unsigned int freq = aperfmperf_get_khz(cpu); - - if (!freq) - freq = cpufreq_quick_get(cpu); - if (!freq) - freq = cpu_khz; - seq_printf(m, "cpu MHz\t\t: %u.%03u\n", - freq / 1000, (freq % 1000)); + unsigned int freq = arch_freq_get_on_cpu(cpu); + + seq_printf(m, "cpu MHz\t\t: %u.%03u\n", freq / 1000, (freq % 1000)); } /* Cache size */ diff --git a/arch/x86/kernel/cpu/resctrl/rdtgroup.c b/arch/x86/kernel/cpu/resctrl/rdtgroup.c index 83f901e2c2df..f276aff521e8 100644 --- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c +++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c @@ -341,14 +341,14 @@ static int cpus_mon_write(struct rdtgroup *rdtgrp, cpumask_var_t newmask, /* Check whether cpus belong to parent ctrl group */ cpumask_andnot(tmpmask, newmask, &prgrp->cpu_mask); - if (cpumask_weight(tmpmask)) { + if (!cpumask_empty(tmpmask)) { rdt_last_cmd_puts("Can only add CPUs to mongroup that belong to parent\n"); return -EINVAL; } /* Check whether cpus are dropped from this group */ cpumask_andnot(tmpmask, &rdtgrp->cpu_mask, newmask); - if (cpumask_weight(tmpmask)) { + if (!cpumask_empty(tmpmask)) { /* Give any dropped cpus to parent rdtgroup */ cpumask_or(&prgrp->cpu_mask, &prgrp->cpu_mask, tmpmask); update_closid_rmid(tmpmask, prgrp); @@ -359,7 +359,7 @@ static int cpus_mon_write(struct rdtgroup *rdtgrp, cpumask_var_t newmask, * and update per-cpu rmid */ cpumask_andnot(tmpmask, newmask, &rdtgrp->cpu_mask); - if (cpumask_weight(tmpmask)) { + if (!cpumask_empty(tmpmask)) { head = &prgrp->mon.crdtgrp_list; list_for_each_entry(crgrp, head, mon.crdtgrp_list) { if (crgrp == rdtgrp) @@ -394,7 +394,7 @@ static int cpus_ctrl_write(struct rdtgroup *rdtgrp, cpumask_var_t newmask, /* Check whether cpus are dropped from this group */ cpumask_andnot(tmpmask, &rdtgrp->cpu_mask, newmask); - if (cpumask_weight(tmpmask)) { + if (!cpumask_empty(tmpmask)) { /* Can't drop from default group */ if (rdtgrp == &rdtgroup_default) { rdt_last_cmd_puts("Can't drop CPUs from default group\n"); @@ -413,12 +413,12 @@ static int cpus_ctrl_write(struct rdtgroup *rdtgrp, cpumask_var_t newmask, * and update per-cpu closid/rmid. */ cpumask_andnot(tmpmask, newmask, &rdtgrp->cpu_mask); - if (cpumask_weight(tmpmask)) { + if (!cpumask_empty(tmpmask)) { list_for_each_entry(r, &rdt_all_groups, rdtgroup_list) { if (r == rdtgrp) continue; cpumask_and(tmpmask1, &r->cpu_mask, tmpmask); - if (cpumask_weight(tmpmask1)) + if (!cpumask_empty(tmpmask1)) cpumask_rdtgrp_clear(r, tmpmask1); } update_closid_rmid(tmpmask, rdtgrp); @@ -488,7 +488,7 @@ static ssize_t rdtgroup_cpus_write(struct kernfs_open_file *of, /* check that user didn't specify any offline cpus */ cpumask_andnot(tmpmask, newmask, cpu_online_mask); - if (cpumask_weight(tmpmask)) { + if (!cpumask_empty(tmpmask)) { ret = -EINVAL; rdt_last_cmd_puts("Can only assign online CPUs\n"); goto unlock; diff --git a/arch/x86/kernel/crash.c b/arch/x86/kernel/crash.c index e8326a8d1c5d..9730c88530fc 100644 --- a/arch/x86/kernel/crash.c +++ b/arch/x86/kernel/crash.c @@ -407,7 +407,7 @@ int crash_load_segments(struct kimage *image) } image->elf_load_addr = kbuf.mem; pr_debug("Loaded ELF headers at 0x%lx bufsz=0x%lx memsz=0x%lx\n", - image->elf_load_addr, kbuf.bufsz, kbuf.bufsz); + image->elf_load_addr, kbuf.bufsz, kbuf.memsz); return ret; } diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c index 39e1c8626ab9..c8340156bfd2 100644 --- a/arch/x86/kernel/fpu/xstate.c +++ b/arch/x86/kernel/fpu/xstate.c @@ -142,7 +142,8 @@ static unsigned int xfeature_get_offset(u64 xcomp_bv, int xfeature) * Non-compacted format and legacy features use the cached fixed * offsets. */ - if (!cpu_feature_enabled(X86_FEATURE_XSAVES) || xfeature <= XFEATURE_SSE) + if (!cpu_feature_enabled(X86_FEATURE_XCOMPACTED) || + xfeature <= XFEATURE_SSE) return xstate_offsets[xfeature]; /* @@ -369,12 +370,12 @@ static void __init setup_init_fpu_buf(void) /* * All components are now in init state. Read the state back so * that init_fpstate contains all non-zero init state. This only - * works with XSAVE, but not with XSAVEOPT and XSAVES because + * works with XSAVE, but not with XSAVEOPT and XSAVEC/S because * those use the init optimization which skips writing data for * components in init state. * * XSAVE could be used, but that would require to reshuffle the - * data when XSAVES is available because XSAVES uses xstate + * data when XSAVEC/S is available because XSAVEC/S uses xstate * compaction. But doing so is a pointless exercise because most * components have an all zeros init state except for the legacy * ones (FP and SSE). Those can be saved with FXSAVE into the @@ -584,7 +585,8 @@ static unsigned int xstate_calculate_size(u64 xfeatures, bool compacted) */ static bool __init paranoid_xstate_size_valid(unsigned int kernel_size) { - bool compacted = cpu_feature_enabled(X86_FEATURE_XSAVES); + bool compacted = cpu_feature_enabled(X86_FEATURE_XCOMPACTED); + bool xsaves = cpu_feature_enabled(X86_FEATURE_XSAVES); unsigned int size = FXSAVE_SIZE + XSAVE_HDR_SIZE; int i; @@ -595,7 +597,7 @@ static bool __init paranoid_xstate_size_valid(unsigned int kernel_size) * Supervisor state components can be managed only by * XSAVES. */ - if (!compacted && xfeature_is_supervisor(i)) { + if (!xsaves && xfeature_is_supervisor(i)) { XSTATE_WARN_ON(1); return false; } @@ -612,8 +614,11 @@ static bool __init paranoid_xstate_size_valid(unsigned int kernel_size) * the size of the *user* states. If we use it to size a buffer * that we use 'XSAVES' on, we could potentially overflow the * buffer because 'XSAVES' saves system states too. + * + * This also takes compaction into account. So this works for + * XSAVEC as well. */ -static unsigned int __init get_xsaves_size(void) +static unsigned int __init get_compacted_size(void) { unsigned int eax, ebx, ecx, edx; /* @@ -623,6 +628,10 @@ static unsigned int __init get_xsaves_size(void) * containing all the state components * corresponding to bits currently set in * XCR0 | IA32_XSS. + * + * When XSAVES is not available but XSAVEC is (virt), then there + * are no supervisor states, but XSAVEC still uses compacted + * format. */ cpuid_count(XSTATE_CPUID, 1, &eax, &ebx, &ecx, &edx); return ebx; @@ -632,13 +641,13 @@ static unsigned int __init get_xsaves_size(void) * Get the total size of the enabled xstates without the independent supervisor * features. */ -static unsigned int __init get_xsaves_size_no_independent(void) +static unsigned int __init get_xsave_compacted_size(void) { u64 mask = xfeatures_mask_independent(); unsigned int size; if (!mask) - return get_xsaves_size(); + return get_compacted_size(); /* Disable independent features. */ wrmsrl(MSR_IA32_XSS, xfeatures_mask_supervisor()); @@ -647,7 +656,7 @@ static unsigned int __init get_xsaves_size_no_independent(void) * Ask the hardware what size is required of the buffer. * This is the size required for the task->fpu buffer. */ - size = get_xsaves_size(); + size = get_compacted_size(); /* Re-enable independent features so XSAVES will work on them again. */ wrmsrl(MSR_IA32_XSS, xfeatures_mask_supervisor() | mask); @@ -687,20 +696,21 @@ static int __init init_xstate_size(void) { /* Recompute the context size for enabled features: */ unsigned int user_size, kernel_size, kernel_default_size; - bool compacted = cpu_feature_enabled(X86_FEATURE_XSAVES); + bool compacted = cpu_feature_enabled(X86_FEATURE_XCOMPACTED); /* Uncompacted user space size */ user_size = get_xsave_size_user(); /* - * XSAVES kernel size includes supervisor states and - * uses compacted format when available. + * XSAVES kernel size includes supervisor states and uses compacted + * format. XSAVEC uses compacted format, but does not save + * supervisor states. * - * XSAVE does not support supervisor states so - * kernel and user size is identical. + * XSAVE[OPT] do not support supervisor states so kernel and user + * size is identical. */ if (compacted) - kernel_size = get_xsaves_size_no_independent(); + kernel_size = get_xsave_compacted_size(); else kernel_size = user_size; @@ -813,8 +823,11 @@ void __init fpu__init_system_xstate(unsigned int legacy_size) if (!cpu_feature_enabled(X86_FEATURE_XFD)) fpu_kernel_cfg.max_features &= ~XFEATURE_MASK_USER_DYNAMIC; - fpu_kernel_cfg.max_features &= XFEATURE_MASK_USER_SUPPORTED | - XFEATURE_MASK_SUPERVISOR_SUPPORTED; + if (!cpu_feature_enabled(X86_FEATURE_XSAVES)) + fpu_kernel_cfg.max_features &= XFEATURE_MASK_USER_SUPPORTED; + else + fpu_kernel_cfg.max_features &= XFEATURE_MASK_USER_SUPPORTED | + XFEATURE_MASK_SUPERVISOR_SUPPORTED; fpu_user_cfg.max_features = fpu_kernel_cfg.max_features; fpu_user_cfg.max_features &= XFEATURE_MASK_USER_SUPPORTED; @@ -837,6 +850,11 @@ void __init fpu__init_system_xstate(unsigned int legacy_size) */ init_fpstate.xfd = fpu_user_cfg.max_features & XFEATURE_MASK_USER_DYNAMIC; + /* Set up compaction feature bit */ + if (cpu_feature_enabled(X86_FEATURE_XSAVEC) || + cpu_feature_enabled(X86_FEATURE_XSAVES)) + setup_force_cpu_cap(X86_FEATURE_XCOMPACTED); + /* Enable xstate instructions to be able to continue with initialization: */ fpu__init_cpu_xstate(); @@ -873,7 +891,7 @@ void __init fpu__init_system_xstate(unsigned int legacy_size) pr_info("x86/fpu: Enabled xstate features 0x%llx, context size is %d bytes, using '%s' format.\n", fpu_kernel_cfg.max_features, fpu_kernel_cfg.max_size, - boot_cpu_has(X86_FEATURE_XSAVES) ? "compacted" : "standard"); + boot_cpu_has(X86_FEATURE_XCOMPACTED) ? "compacted" : "standard"); return; out_disable: @@ -917,7 +935,7 @@ static void *__raw_xsave_addr(struct xregs_state *xsave, int xfeature_nr) if (WARN_ON_ONCE(!xfeature_enabled(xfeature_nr))) return NULL; - if (cpu_feature_enabled(X86_FEATURE_XSAVES)) { + if (cpu_feature_enabled(X86_FEATURE_XCOMPACTED)) { if (WARN_ON_ONCE(!(xcomp_bv & BIT_ULL(xfeature_nr)))) return NULL; } @@ -1215,7 +1233,7 @@ static int copy_uabi_to_xstate(struct fpstate *fpstate, const void *kbuf, } for (i = 0; i < XFEATURE_MAX; i++) { - u64 mask = ((u64)1 << i); + mask = BIT_ULL(i); if (hdr.xfeatures & mask) { void *dst = __raw_xsave_addr(xsave, i); @@ -1525,7 +1543,7 @@ static int __xstate_request_perm(u64 permitted, u64 requested, bool guest) * vendors into extending XFD for the pre AMX states, especially * AVX512. */ - bool compacted = cpu_feature_enabled(X86_FEATURE_XSAVES); + bool compacted = cpu_feature_enabled(X86_FEATURE_XCOMPACTED); struct fpu *fpu = ¤t->group_leader->thread.fpu; struct fpu_state_perm *perm; unsigned int ksize, usize; @@ -1687,16 +1705,13 @@ EXPORT_SYMBOL_GPL(xstate_get_guest_group_perm); * e.g. for AMX which requires XFEATURE_XTILE_CFG(17) and * XFEATURE_XTILE_DATA(18) this would be XFEATURE_XTILE_DATA(18). */ -long fpu_xstate_prctl(struct task_struct *tsk, int option, unsigned long arg2) +long fpu_xstate_prctl(int option, unsigned long arg2) { u64 __user *uptr = (u64 __user *)arg2; u64 permitted, supported; unsigned long idx = arg2; bool guest = false; - if (tsk != current) - return -EPERM; - switch (option) { case ARCH_GET_XCOMP_SUPP: supported = fpu_user_cfg.max_features | fpu_user_cfg.legacy_features; diff --git a/arch/x86/kernel/fpu/xstate.h b/arch/x86/kernel/fpu/xstate.h index d22ace092ca2..5ad47031383b 100644 --- a/arch/x86/kernel/fpu/xstate.h +++ b/arch/x86/kernel/fpu/xstate.h @@ -16,7 +16,7 @@ static inline void xstate_init_xcomp_bv(struct xregs_state *xsave, u64 mask) * XRSTORS requires these bits set in xcomp_bv, or it will * trigger #GP: */ - if (cpu_feature_enabled(X86_FEATURE_XSAVES)) + if (cpu_feature_enabled(X86_FEATURE_XCOMPACTED)) xsave->header.xcomp_bv = mask | XCOMP_BV_COMPACTED_FORMAT; } @@ -79,6 +79,7 @@ static inline u64 xfeatures_mask_independent(void) /* These macros all use (%edi)/(%rdi) as the single memory argument. */ #define XSAVE ".byte " REX_PREFIX "0x0f,0xae,0x27" #define XSAVEOPT ".byte " REX_PREFIX "0x0f,0xae,0x37" +#define XSAVEC ".byte " REX_PREFIX "0x0f,0xc7,0x27" #define XSAVES ".byte " REX_PREFIX "0x0f,0xc7,0x2f" #define XRSTOR ".byte " REX_PREFIX "0x0f,0xae,0x2f" #define XRSTORS ".byte " REX_PREFIX "0x0f,0xc7,0x1f" @@ -97,9 +98,11 @@ static inline u64 xfeatures_mask_independent(void) : "memory") /* - * If XSAVES is enabled, it replaces XSAVEOPT because it supports a compact - * format and supervisor states in addition to modified optimization in - * XSAVEOPT. + * If XSAVES is enabled, it replaces XSAVEC because it supports supervisor + * states in addition to XSAVEC. + * + * Otherwise if XSAVEC is enabled, it replaces XSAVEOPT because it supports + * compacted storage format in addition to XSAVEOPT. * * Otherwise, if XSAVEOPT is enabled, XSAVEOPT replaces XSAVE because XSAVEOPT * supports modified optimization which is not supported by XSAVE. @@ -111,8 +114,9 @@ static inline u64 xfeatures_mask_independent(void) * address of the instruction where we might get an exception at. */ #define XSTATE_XSAVE(st, lmask, hmask, err) \ - asm volatile(ALTERNATIVE_2(XSAVE, \ + asm volatile(ALTERNATIVE_3(XSAVE, \ XSAVEOPT, X86_FEATURE_XSAVEOPT, \ + XSAVEC, X86_FEATURE_XSAVEC, \ XSAVES, X86_FEATURE_XSAVES) \ "\n" \ "xor %[err], %[err]\n" \ diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c index 4f5ecbbaae77..bd4a34100ed0 100644 --- a/arch/x86/kernel/head64.c +++ b/arch/x86/kernel/head64.c @@ -40,6 +40,7 @@ #include <asm/extable.h> #include <asm/trapnr.h> #include <asm/sev.h> +#include <asm/tdx.h> /* * Manage page tables very early on. @@ -143,7 +144,20 @@ static unsigned long __head sme_postprocess_startup(struct boot_params *bp, pmdv if (sme_get_me_mask()) { vaddr = (unsigned long)__start_bss_decrypted; vaddr_end = (unsigned long)__end_bss_decrypted; + for (; vaddr < vaddr_end; vaddr += PMD_SIZE) { + /* + * On SNP, transition the page to shared in the RMP table so that + * it is consistent with the page table attribute change. + * + * __start_bss_decrypted has a virtual address in the high range + * mapping (kernel .text). PVALIDATE, by way of + * early_snp_set_memory_shared(), requires a valid virtual + * address but the kernel is currently running off of the identity + * mapping so use __pa() to get a *currently* valid virtual address. + */ + early_snp_set_memory_shared(__pa(vaddr), __pa(vaddr), PTRS_PER_PMD); + i = pmd_index(vaddr); pmd[i] -= sme_get_me_mask(); } @@ -192,9 +206,6 @@ unsigned long __head __startup_64(unsigned long physaddr, if (load_delta & ~PMD_PAGE_MASK) for (;;); - /* Activate Secure Memory Encryption (SME) if supported and enabled */ - sme_enable(bp); - /* Include the SME encryption mask in the fixup value */ load_delta += sme_get_me_mask(); @@ -308,15 +319,6 @@ unsigned long __head __startup_64(unsigned long physaddr, return sme_postprocess_startup(bp, pmd); } -unsigned long __startup_secondary_64(void) -{ - /* - * Return the SME encryption mask (if SME is active) to be used as a - * modifier for the initial pgdir entry programmed into CR3. - */ - return sme_get_me_mask(); -} - /* Wipe all early page tables except for the kernel symbol map */ static void __init reset_early_page_tables(void) { @@ -416,6 +418,9 @@ void __init do_early_exception(struct pt_regs *regs, int trapnr) trapnr == X86_TRAP_VC && handle_vc_boot_ghcb(regs)) return; + if (trapnr == X86_TRAP_VE && tdx_early_handle_ve(regs)) + return; + early_fixup_exception(regs, trapnr); } @@ -514,6 +519,9 @@ asmlinkage __visible void __init x86_64_start_kernel(char * real_mode_data) idt_setup_early_handler(); + /* Needed before cc_platform_has() can be used for TDX */ + tdx_early_init(); + copy_bootdata(__va(real_mode_data)); /* @@ -600,8 +608,10 @@ static void startup_64_load_idt(unsigned long physbase) void early_setup_idt(void) { /* VMM Communication Exception */ - if (IS_ENABLED(CONFIG_AMD_MEM_ENCRYPT)) + if (IS_ENABLED(CONFIG_AMD_MEM_ENCRYPT)) { + setup_ghcb(); set_bringup_idt_handler(bringup_idt_table, X86_TRAP_VC, vc_boot_ghcb); + } bringup_idt_descr.address = (unsigned long)bringup_idt_table; native_load_idt(&bringup_idt_descr); diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S index b8e3019547a5..92c4afa2b729 100644 --- a/arch/x86/kernel/head_64.S +++ b/arch/x86/kernel/head_64.S @@ -65,10 +65,39 @@ SYM_CODE_START_NOALIGN(startup_64) leaq (__end_init_task - FRAME_SIZE)(%rip), %rsp leaq _text(%rip), %rdi + + /* + * initial_gs points to initial fixed_percpu_data struct with storage for + * the stack protector canary. Global pointer fixups are needed at this + * stage, so apply them as is done in fixup_pointer(), and initialize %gs + * such that the canary can be accessed at %gs:40 for subsequent C calls. + */ + movl $MSR_GS_BASE, %ecx + movq initial_gs(%rip), %rax + movq $_text, %rdx + subq %rdx, %rax + addq %rdi, %rax + movq %rax, %rdx + shrq $32, %rdx + wrmsr + pushq %rsi call startup_64_setup_env popq %rsi +#ifdef CONFIG_AMD_MEM_ENCRYPT + /* + * Activate SEV/SME memory encryption if supported/enabled. This needs to + * be done now, since this also includes setup of the SEV-SNP CPUID table, + * which needs to be done before any CPUID instructions are executed in + * subsequent code. + */ + movq %rsi, %rdi + pushq %rsi + call sme_enable + popq %rsi +#endif + /* Now switch to __KERNEL_CS so IRET works reliably */ pushq $__KERNEL_CS leaq .Lon_kernel_cs(%rip), %rax @@ -134,16 +163,32 @@ SYM_INNER_LABEL(secondary_startup_64_no_verify, SYM_L_GLOBAL) * Retrieve the modifier (SME encryption mask if SME is active) to be * added to the initial pgdir entry that will be programmed into CR3. */ - pushq %rsi - call __startup_secondary_64 - popq %rsi +#ifdef CONFIG_AMD_MEM_ENCRYPT + movq sme_me_mask, %rax +#else + xorq %rax, %rax +#endif /* Form the CR3 value being sure to include the CR3 modifier */ addq $(init_top_pgt - __START_KERNEL_map), %rax 1: +#ifdef CONFIG_X86_MCE + /* + * Preserve CR4.MCE if the kernel will enable #MC support. + * Clearing MCE may fault in some environments (that also force #MC + * support). Any machine check that occurs before #MC support is fully + * configured will crash the system regardless of the CR4.MCE value set + * here. + */ + movq %cr4, %rcx + andl $X86_CR4_MCE, %ecx +#else + movl $0, %ecx +#endif + /* Enable PAE mode, PGE and LA57 */ - movl $(X86_CR4_PAE | X86_CR4_PGE), %ecx + orl $(X86_CR4_PAE | X86_CR4_PGE), %ecx #ifdef CONFIG_X86_5LEVEL testl $1, __pgtable_l5_enabled(%rip) jz 1f @@ -249,13 +294,23 @@ SYM_INNER_LABEL(secondary_startup_64_no_verify, SYM_L_GLOBAL) /* Setup EFER (Extended Feature Enable Register) */ movl $MSR_EFER, %ecx rdmsr + /* + * Preserve current value of EFER for comparison and to skip + * EFER writes if no change was made (for TDX guest) + */ + movl %eax, %edx btsl $_EFER_SCE, %eax /* Enable System Call */ btl $20,%edi /* No Execute supported? */ jnc 1f btsl $_EFER_NX, %eax btsq $_PAGE_BIT_NX,early_pmd_flags(%rip) -1: wrmsr /* Make changes effective */ + /* Avoid writing EFER if no change was made (for TDX guest) */ +1: cmpl %edx, %eax + je 1f + xor %edx, %edx + wrmsr /* Make changes effective */ +1: /* Setup cr0 */ movl $CR0_STATE, %eax /* Make changes effective */ diff --git a/arch/x86/kernel/idt.c b/arch/x86/kernel/idt.c index 608eb63bf044..a58c6bc1cd68 100644 --- a/arch/x86/kernel/idt.c +++ b/arch/x86/kernel/idt.c @@ -69,6 +69,9 @@ static const __initconst struct idt_data early_idts[] = { */ INTG(X86_TRAP_PF, asm_exc_page_fault), #endif +#ifdef CONFIG_INTEL_TDX_GUEST + INTG(X86_TRAP_VE, asm_exc_virtualization_exception), +#endif }; /* diff --git a/arch/x86/kernel/nmi.c b/arch/x86/kernel/nmi.c index e73f7df362f5..cec0bfa3bc04 100644 --- a/arch/x86/kernel/nmi.c +++ b/arch/x86/kernel/nmi.c @@ -157,7 +157,7 @@ int __register_nmi_handler(unsigned int type, struct nmiaction *action) struct nmi_desc *desc = nmi_to_desc(type); unsigned long flags; - if (!action->handler) + if (WARN_ON_ONCE(!action->handler || !list_empty(&action->list))) return -EINVAL; raw_spin_lock_irqsave(&desc->lock, flags); @@ -177,7 +177,7 @@ int __register_nmi_handler(unsigned int type, struct nmiaction *action) list_add_rcu(&action->list, &desc->head); else list_add_tail_rcu(&action->list, &desc->head); - + raw_spin_unlock_irqrestore(&desc->lock, flags); return 0; } @@ -186,7 +186,7 @@ EXPORT_SYMBOL(__register_nmi_handler); void unregister_nmi_handler(unsigned int type, const char *name) { struct nmi_desc *desc = nmi_to_desc(type); - struct nmiaction *n; + struct nmiaction *n, *found = NULL; unsigned long flags; raw_spin_lock_irqsave(&desc->lock, flags); @@ -200,12 +200,16 @@ void unregister_nmi_handler(unsigned int type, const char *name) WARN(in_nmi(), "Trying to free NMI (%s) from NMI context!\n", n->name); list_del_rcu(&n->list); + found = n; break; } } raw_spin_unlock_irqrestore(&desc->lock, flags); - synchronize_rcu(); + if (found) { + synchronize_rcu(); + INIT_LIST_HEAD(&found->list); + } } EXPORT_SYMBOL_GPL(unregister_nmi_handler); diff --git a/arch/x86/kernel/probe_roms.c b/arch/x86/kernel/probe_roms.c index 36e84d904260..319fef37d9dc 100644 --- a/arch/x86/kernel/probe_roms.c +++ b/arch/x86/kernel/probe_roms.c @@ -21,6 +21,7 @@ #include <asm/sections.h> #include <asm/io.h> #include <asm/setup_arch.h> +#include <asm/sev.h> static struct resource system_rom_resource = { .name = "System ROM", @@ -197,11 +198,21 @@ static int __init romchecksum(const unsigned char *rom, unsigned long length) void __init probe_roms(void) { - const unsigned char *rom; unsigned long start, length, upper; + const unsigned char *rom; unsigned char c; int i; + /* + * The ROM memory range is not part of the e820 table and is therefore not + * pre-validated by BIOS. The kernel page table maps the ROM region as encrypted + * memory, and SNP requires encrypted memory to be validated before access. + * Do that here. + */ + snp_prep_memory(video_rom_resource.start, + ((system_rom_resource.end + 1) - video_rom_resource.start), + SNP_PAGE_STATE_PRIVATE); + /* video rom */ upper = adapter_rom_resources[0].start; for (start = video_rom_resource.start; start < upper; start += 2048) { diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index b370767f5b19..58fb48d3004f 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -46,6 +46,7 @@ #include <asm/proto.h> #include <asm/frame.h> #include <asm/unwind.h> +#include <asm/tdx.h> #include "process.h" @@ -160,6 +161,7 @@ int copy_thread(unsigned long clone_flags, unsigned long sp, unsigned long arg, savesegment(ds, p->thread.ds); #else p->thread.sp0 = (unsigned long) (childregs + 1); + savesegment(gs, p->thread.gs); /* * Clear all status flags including IF and set fixed bit. 64bit * does not have this initialization as the frame does not contain @@ -191,10 +193,6 @@ int copy_thread(unsigned long clone_flags, unsigned long sp, unsigned long arg, if (sp) childregs->sp = sp; -#ifdef CONFIG_X86_32 - task_user_gs(p) = get_user_gs(current_pt_regs()); -#endif - if (unlikely(p->flags & PF_IO_WORKER)) { /* * An IO thread is a user space thread, but it doesn't @@ -334,7 +332,7 @@ static int get_cpuid_mode(void) return !test_thread_flag(TIF_NOCPUID); } -static int set_cpuid_mode(struct task_struct *task, unsigned long cpuid_enabled) +static int set_cpuid_mode(unsigned long cpuid_enabled) { if (!boot_cpu_has(X86_FEATURE_CPUID_FAULT)) return -ENODEV; @@ -405,7 +403,7 @@ static void tss_copy_io_bitmap(struct tss_struct *tss, struct io_bitmap *iobm) } /** - * tss_update_io_bitmap - Update I/O bitmap before exiting to usermode + * native_tss_update_io_bitmap - Update I/O bitmap before exiting to user mode */ void native_tss_update_io_bitmap(void) { @@ -686,9 +684,6 @@ void __switch_to_xtra(struct task_struct *prev_p, struct task_struct *next_p) /* Enforce MSR update to ensure consistent state */ __speculation_ctrl_update(~tifn, tifn); } - - if ((tifp ^ tifn) & _TIF_SLD) - switch_to_sld(tifn); } /* @@ -873,6 +868,9 @@ void select_idle_routine(const struct cpuinfo_x86 *c) } else if (prefer_mwait_c1_over_halt(c)) { pr_info("using mwait in idle threads\n"); x86_idle = mwait_idle; + } else if (cpu_feature_enabled(X86_FEATURE_TDX_GUEST)) { + pr_info("using TDX aware idle routine\n"); + x86_idle = tdx_safe_halt; } else x86_idle = default_idle; } @@ -985,20 +983,19 @@ unsigned long __get_wchan(struct task_struct *p) return addr; } -long do_arch_prctl_common(struct task_struct *task, int option, - unsigned long arg2) +long do_arch_prctl_common(int option, unsigned long arg2) { switch (option) { case ARCH_GET_CPUID: return get_cpuid_mode(); case ARCH_SET_CPUID: - return set_cpuid_mode(task, arg2); + return set_cpuid_mode(arg2); case ARCH_GET_XCOMP_SUPP: case ARCH_GET_XCOMP_PERM: case ARCH_REQ_XCOMP_PERM: case ARCH_GET_XCOMP_GUEST_PERM: case ARCH_REQ_XCOMP_GUEST_PERM: - return fpu_xstate_prctl(task, option, arg2); + return fpu_xstate_prctl(option, arg2); } return -EINVAL; diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c index 26edb1cd07a4..2f314b170c9f 100644 --- a/arch/x86/kernel/process_32.c +++ b/arch/x86/kernel/process_32.c @@ -63,10 +63,7 @@ void __show_regs(struct pt_regs *regs, enum show_regs_mode mode, unsigned long d0, d1, d2, d3, d6, d7; unsigned short gs; - if (user_mode(regs)) - gs = get_user_gs(regs); - else - savesegment(gs, gs); + savesegment(gs, gs); show_ip(regs, log_lvl); @@ -114,7 +111,7 @@ void release_thread(struct task_struct *dead_task) void start_thread(struct pt_regs *regs, unsigned long new_ip, unsigned long new_sp) { - set_user_gs(regs, 0); + loadsegment(gs, 0); regs->fs = 0; regs->ds = __USER_DS; regs->es = __USER_DS; @@ -177,7 +174,7 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p) * used %fs or %gs (it does not today), or if the kernel is * running inside of a hypervisor layer. */ - lazy_save_gs(prev->gs); + savesegment(gs, prev->gs); /* * Load the per-thread Thread-Local Storage descriptor. @@ -208,7 +205,7 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p) * Restore %gs if needed (which is common) */ if (prev->gs | next->gs) - lazy_load_gs(next->gs); + loadsegment(gs, next->gs); this_cpu_write(current_task, next_p); @@ -222,5 +219,5 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p) SYSCALL_DEFINE2(arch_prctl, int, option, unsigned long, arg2) { - return do_arch_prctl_common(current, option, arg2); + return do_arch_prctl_common(option, arg2); } diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c index e459253649be..1962008fe743 100644 --- a/arch/x86/kernel/process_64.c +++ b/arch/x86/kernel/process_64.c @@ -844,7 +844,7 @@ SYSCALL_DEFINE2(arch_prctl, int, option, unsigned long, arg2) ret = do_arch_prctl_64(current, option, arg2); if (ret == -EINVAL) - ret = do_arch_prctl_common(current, option, arg2); + ret = do_arch_prctl_common(option, arg2); return ret; } @@ -852,7 +852,7 @@ SYSCALL_DEFINE2(arch_prctl, int, option, unsigned long, arg2) #ifdef CONFIG_IA32_EMULATION COMPAT_SYSCALL_DEFINE2(arch_prctl, int, option, unsigned long, arg2) { - return do_arch_prctl_common(current, option, arg2); + return do_arch_prctl_common(option, arg2); } #endif diff --git a/arch/x86/kernel/ptrace.c b/arch/x86/kernel/ptrace.c index 98d10ef60571..37c12fb92906 100644 --- a/arch/x86/kernel/ptrace.c +++ b/arch/x86/kernel/ptrace.c @@ -170,9 +170,9 @@ static u16 get_segment_reg(struct task_struct *task, unsigned long offset) retval = *pt_regs_access(task_pt_regs(task), offset); else { if (task == current) - retval = get_user_gs(task_pt_regs(task)); + savesegment(gs, retval); else - retval = task_user_gs(task); + retval = task->thread.gs; } return retval; } @@ -210,7 +210,7 @@ static int set_segment_reg(struct task_struct *task, break; case offsetof(struct user_regs_struct, gs): - task_user_gs(task) = value; + task->thread.gs = value; } return 0; diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index c95b9ac5a457..249981bf3d8a 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -756,6 +756,30 @@ dump_kernel_offset(struct notifier_block *self, unsigned long v, void *p) return 0; } +void x86_configure_nx(void) +{ + if (boot_cpu_has(X86_FEATURE_NX)) + __supported_pte_mask |= _PAGE_NX; + else + __supported_pte_mask &= ~_PAGE_NX; +} + +static void __init x86_report_nx(void) +{ + if (!boot_cpu_has(X86_FEATURE_NX)) { + printk(KERN_NOTICE "Notice: NX (Execute Disable) protection " + "missing in CPU!\n"); + } else { +#if defined(CONFIG_X86_64) || defined(CONFIG_X86_PAE) + printk(KERN_INFO "NX (Execute Disable) protection: active\n"); +#else + /* 32bit non-PAE kernel, NX cannot be used */ + printk(KERN_NOTICE "Notice: NX (Execute Disable) protection " + "cannot be enabled: non-PAE kernel!\n"); +#endif + } +} + /* * Determine if we were loaded by an EFI loader. If so, then we have also been * passed the efi memmap, systab, etc., so we should use these data structures @@ -896,9 +920,7 @@ void __init setup_arch(char **cmdline_p) /* * x86_configure_nx() is called before parse_early_param() to detect * whether hardware doesn't support NX (so that the early EHCI debug - * console setup can safely call set_fixmap()). It may then be called - * again from within noexec_setup() during parsing early parameters - * to honor the respective command line option. + * console setup can safely call set_fixmap()). */ x86_configure_nx(); diff --git a/arch/x86/kernel/sev-shared.c b/arch/x86/kernel/sev-shared.c index ce987688bbc0..b478edf43bec 100644 --- a/arch/x86/kernel/sev-shared.c +++ b/arch/x86/kernel/sev-shared.c @@ -14,6 +14,68 @@ #define has_cpuflag(f) boot_cpu_has(f) #endif +/* I/O parameters for CPUID-related helpers */ +struct cpuid_leaf { + u32 fn; + u32 subfn; + u32 eax; + u32 ebx; + u32 ecx; + u32 edx; +}; + +/* + * Individual entries of the SNP CPUID table, as defined by the SNP + * Firmware ABI, Revision 0.9, Section 7.1, Table 14. + */ +struct snp_cpuid_fn { + u32 eax_in; + u32 ecx_in; + u64 xcr0_in; + u64 xss_in; + u32 eax; + u32 ebx; + u32 ecx; + u32 edx; + u64 __reserved; +} __packed; + +/* + * SNP CPUID table, as defined by the SNP Firmware ABI, Revision 0.9, + * Section 8.14.2.6. Also noted there is the SNP firmware-enforced limit + * of 64 entries per CPUID table. + */ +#define SNP_CPUID_COUNT_MAX 64 + +struct snp_cpuid_table { + u32 count; + u32 __reserved1; + u64 __reserved2; + struct snp_cpuid_fn fn[SNP_CPUID_COUNT_MAX]; +} __packed; + +/* + * Since feature negotiation related variables are set early in the boot + * process they must reside in the .data section so as not to be zeroed + * out when the .bss section is later cleared. + * + * GHCB protocol version negotiated with the hypervisor. + */ +static u16 ghcb_version __ro_after_init; + +/* Copy of the SNP firmware's CPUID page. */ +static struct snp_cpuid_table cpuid_table_copy __ro_after_init; + +/* + * These will be initialized based on CPUID table so that non-present + * all-zero leaves (for sparse tables) can be differentiated from + * invalid/out-of-range leaves. This is needed since all-zero leaves + * still need to be post-processed. + */ +static u32 cpuid_std_range_max __ro_after_init; +static u32 cpuid_hyp_range_max __ro_after_init; +static u32 cpuid_ext_range_max __ro_after_init; + static bool __init sev_es_check_cpu_features(void) { if (!has_cpuflag(X86_FEATURE_RDRAND)) { @@ -24,15 +86,12 @@ static bool __init sev_es_check_cpu_features(void) return true; } -static void __noreturn sev_es_terminate(unsigned int reason) +static void __noreturn sev_es_terminate(unsigned int set, unsigned int reason) { u64 val = GHCB_MSR_TERM_REQ; - /* - * Tell the hypervisor what went wrong - only reason-set 0 is - * currently supported. - */ - val |= GHCB_SEV_TERM_REASON(0, reason); + /* Tell the hypervisor what went wrong. */ + val |= GHCB_SEV_TERM_REASON(set, reason); /* Request Guest Termination from Hypvervisor */ sev_es_wr_ghcb_msr(val); @@ -42,6 +101,42 @@ static void __noreturn sev_es_terminate(unsigned int reason) asm volatile("hlt\n" : : : "memory"); } +/* + * The hypervisor features are available from GHCB version 2 onward. + */ +static u64 get_hv_features(void) +{ + u64 val; + + if (ghcb_version < 2) + return 0; + + sev_es_wr_ghcb_msr(GHCB_MSR_HV_FT_REQ); + VMGEXIT(); + + val = sev_es_rd_ghcb_msr(); + if (GHCB_RESP_CODE(val) != GHCB_MSR_HV_FT_RESP) + return 0; + + return GHCB_MSR_HV_FT_RESP_VAL(val); +} + +static void snp_register_ghcb_early(unsigned long paddr) +{ + unsigned long pfn = paddr >> PAGE_SHIFT; + u64 val; + + sev_es_wr_ghcb_msr(GHCB_MSR_REG_GPA_REQ_VAL(pfn)); + VMGEXIT(); + + val = sev_es_rd_ghcb_msr(); + + /* If the response GPA is not ours then abort the guest */ + if ((GHCB_RESP_CODE(val) != GHCB_MSR_REG_GPA_RESP) || + (GHCB_MSR_REG_GPA_RESP_VAL(val) != pfn)) + sev_es_terminate(SEV_TERM_SET_LINUX, GHCB_TERM_REGISTER); +} + static bool sev_es_negotiate_protocol(void) { u64 val; @@ -54,10 +149,12 @@ static bool sev_es_negotiate_protocol(void) if (GHCB_MSR_INFO(val) != GHCB_MSR_SEV_INFO_RESP) return false; - if (GHCB_MSR_PROTO_MAX(val) < GHCB_PROTO_OUR || - GHCB_MSR_PROTO_MIN(val) > GHCB_PROTO_OUR) + if (GHCB_MSR_PROTO_MAX(val) < GHCB_PROTOCOL_MIN || + GHCB_MSR_PROTO_MIN(val) > GHCB_PROTOCOL_MAX) return false; + ghcb_version = min_t(size_t, GHCB_MSR_PROTO_MAX(val), GHCB_PROTOCOL_MAX); + return true; } @@ -104,10 +201,7 @@ static enum es_result verify_exception_info(struct ghcb *ghcb, struct es_em_ctxt if (ret == 1) { u64 info = ghcb->save.sw_exit_info_2; - unsigned long v; - - info = ghcb->save.sw_exit_info_2; - v = info & SVM_EVTINJ_VEC_MASK; + unsigned long v = info & SVM_EVTINJ_VEC_MASK; /* Check if exception information from hypervisor is sane. */ if ((info & SVM_EVTINJ_VALID) && @@ -130,7 +224,7 @@ enum es_result sev_es_ghcb_hv_call(struct ghcb *ghcb, bool set_ghcb_msr, u64 exit_info_1, u64 exit_info_2) { /* Fill in protocol and format specifiers */ - ghcb->protocol_version = GHCB_PROTOCOL_MAX; + ghcb->protocol_version = ghcb_version; ghcb->ghcb_usage = GHCB_DEFAULT_USAGE; ghcb_set_sw_exit_code(ghcb, exit_code); @@ -150,6 +244,290 @@ enum es_result sev_es_ghcb_hv_call(struct ghcb *ghcb, bool set_ghcb_msr, return verify_exception_info(ghcb, ctxt); } +static int __sev_cpuid_hv(u32 fn, int reg_idx, u32 *reg) +{ + u64 val; + + sev_es_wr_ghcb_msr(GHCB_CPUID_REQ(fn, reg_idx)); + VMGEXIT(); + val = sev_es_rd_ghcb_msr(); + if (GHCB_RESP_CODE(val) != GHCB_MSR_CPUID_RESP) + return -EIO; + + *reg = (val >> 32); + + return 0; +} + +static int sev_cpuid_hv(struct cpuid_leaf *leaf) +{ + int ret; + + /* + * MSR protocol does not support fetching non-zero subfunctions, but is + * sufficient to handle current early-boot cases. Should that change, + * make sure to report an error rather than ignoring the index and + * grabbing random values. If this issue arises in the future, handling + * can be added here to use GHCB-page protocol for cases that occur late + * enough in boot that GHCB page is available. + */ + if (cpuid_function_is_indexed(leaf->fn) && leaf->subfn) + return -EINVAL; + + ret = __sev_cpuid_hv(leaf->fn, GHCB_CPUID_REQ_EAX, &leaf->eax); + ret = ret ? : __sev_cpuid_hv(leaf->fn, GHCB_CPUID_REQ_EBX, &leaf->ebx); + ret = ret ? : __sev_cpuid_hv(leaf->fn, GHCB_CPUID_REQ_ECX, &leaf->ecx); + ret = ret ? : __sev_cpuid_hv(leaf->fn, GHCB_CPUID_REQ_EDX, &leaf->edx); + + return ret; +} + +/* + * This may be called early while still running on the initial identity + * mapping. Use RIP-relative addressing to obtain the correct address + * while running with the initial identity mapping as well as the + * switch-over to kernel virtual addresses later. + */ +static const struct snp_cpuid_table *snp_cpuid_get_table(void) +{ + void *ptr; + + asm ("lea cpuid_table_copy(%%rip), %0" + : "=r" (ptr) + : "p" (&cpuid_table_copy)); + + return ptr; +} + +/* + * The SNP Firmware ABI, Revision 0.9, Section 7.1, details the use of + * XCR0_IN and XSS_IN to encode multiple versions of 0xD subfunctions 0 + * and 1 based on the corresponding features enabled by a particular + * combination of XCR0 and XSS registers so that a guest can look up the + * version corresponding to the features currently enabled in its XCR0/XSS + * registers. The only values that differ between these versions/table + * entries is the enabled XSAVE area size advertised via EBX. + * + * While hypervisors may choose to make use of this support, it is more + * robust/secure for a guest to simply find the entry corresponding to the + * base/legacy XSAVE area size (XCR0=1 or XCR0=3), and then calculate the + * XSAVE area size using subfunctions 2 through 64, as documented in APM + * Volume 3, Rev 3.31, Appendix E.3.8, which is what is done here. + * + * Since base/legacy XSAVE area size is documented as 0x240, use that value + * directly rather than relying on the base size in the CPUID table. + * + * Return: XSAVE area size on success, 0 otherwise. + */ +static u32 snp_cpuid_calc_xsave_size(u64 xfeatures_en, bool compacted) +{ + const struct snp_cpuid_table *cpuid_table = snp_cpuid_get_table(); + u64 xfeatures_found = 0; + u32 xsave_size = 0x240; + int i; + + for (i = 0; i < cpuid_table->count; i++) { + const struct snp_cpuid_fn *e = &cpuid_table->fn[i]; + + if (!(e->eax_in == 0xD && e->ecx_in > 1 && e->ecx_in < 64)) + continue; + if (!(xfeatures_en & (BIT_ULL(e->ecx_in)))) + continue; + if (xfeatures_found & (BIT_ULL(e->ecx_in))) + continue; + + xfeatures_found |= (BIT_ULL(e->ecx_in)); + + if (compacted) + xsave_size += e->eax; + else + xsave_size = max(xsave_size, e->eax + e->ebx); + } + + /* + * Either the guest set unsupported XCR0/XSS bits, or the corresponding + * entries in the CPUID table were not present. This is not a valid + * state to be in. + */ + if (xfeatures_found != (xfeatures_en & GENMASK_ULL(63, 2))) + return 0; + + return xsave_size; +} + +static bool +snp_cpuid_get_validated_func(struct cpuid_leaf *leaf) +{ + const struct snp_cpuid_table *cpuid_table = snp_cpuid_get_table(); + int i; + + for (i = 0; i < cpuid_table->count; i++) { + const struct snp_cpuid_fn *e = &cpuid_table->fn[i]; + + if (e->eax_in != leaf->fn) + continue; + + if (cpuid_function_is_indexed(leaf->fn) && e->ecx_in != leaf->subfn) + continue; + + /* + * For 0xD subfunctions 0 and 1, only use the entry corresponding + * to the base/legacy XSAVE area size (XCR0=1 or XCR0=3, XSS=0). + * See the comments above snp_cpuid_calc_xsave_size() for more + * details. + */ + if (e->eax_in == 0xD && (e->ecx_in == 0 || e->ecx_in == 1)) + if (!(e->xcr0_in == 1 || e->xcr0_in == 3) || e->xss_in) + continue; + + leaf->eax = e->eax; + leaf->ebx = e->ebx; + leaf->ecx = e->ecx; + leaf->edx = e->edx; + + return true; + } + + return false; +} + +static void snp_cpuid_hv(struct cpuid_leaf *leaf) +{ + if (sev_cpuid_hv(leaf)) + sev_es_terminate(SEV_TERM_SET_LINUX, GHCB_TERM_CPUID_HV); +} + +static int snp_cpuid_postprocess(struct cpuid_leaf *leaf) +{ + struct cpuid_leaf leaf_hv = *leaf; + + switch (leaf->fn) { + case 0x1: + snp_cpuid_hv(&leaf_hv); + + /* initial APIC ID */ + leaf->ebx = (leaf_hv.ebx & GENMASK(31, 24)) | (leaf->ebx & GENMASK(23, 0)); + /* APIC enabled bit */ + leaf->edx = (leaf_hv.edx & BIT(9)) | (leaf->edx & ~BIT(9)); + + /* OSXSAVE enabled bit */ + if (native_read_cr4() & X86_CR4_OSXSAVE) + leaf->ecx |= BIT(27); + break; + case 0x7: + /* OSPKE enabled bit */ + leaf->ecx &= ~BIT(4); + if (native_read_cr4() & X86_CR4_PKE) + leaf->ecx |= BIT(4); + break; + case 0xB: + leaf_hv.subfn = 0; + snp_cpuid_hv(&leaf_hv); + + /* extended APIC ID */ + leaf->edx = leaf_hv.edx; + break; + case 0xD: { + bool compacted = false; + u64 xcr0 = 1, xss = 0; + u32 xsave_size; + + if (leaf->subfn != 0 && leaf->subfn != 1) + return 0; + + if (native_read_cr4() & X86_CR4_OSXSAVE) + xcr0 = xgetbv(XCR_XFEATURE_ENABLED_MASK); + if (leaf->subfn == 1) { + /* Get XSS value if XSAVES is enabled. */ + if (leaf->eax & BIT(3)) { + unsigned long lo, hi; + + asm volatile("rdmsr" : "=a" (lo), "=d" (hi) + : "c" (MSR_IA32_XSS)); + xss = (hi << 32) | lo; + } + + /* + * The PPR and APM aren't clear on what size should be + * encoded in 0xD:0x1:EBX when compaction is not enabled + * by either XSAVEC (feature bit 1) or XSAVES (feature + * bit 3) since SNP-capable hardware has these feature + * bits fixed as 1. KVM sets it to 0 in this case, but + * to avoid this becoming an issue it's safer to simply + * treat this as unsupported for SNP guests. + */ + if (!(leaf->eax & (BIT(1) | BIT(3)))) + return -EINVAL; + + compacted = true; + } + + xsave_size = snp_cpuid_calc_xsave_size(xcr0 | xss, compacted); + if (!xsave_size) + return -EINVAL; + + leaf->ebx = xsave_size; + } + break; + case 0x8000001E: + snp_cpuid_hv(&leaf_hv); + + /* extended APIC ID */ + leaf->eax = leaf_hv.eax; + /* compute ID */ + leaf->ebx = (leaf->ebx & GENMASK(31, 8)) | (leaf_hv.ebx & GENMASK(7, 0)); + /* node ID */ + leaf->ecx = (leaf->ecx & GENMASK(31, 8)) | (leaf_hv.ecx & GENMASK(7, 0)); + break; + default: + /* No fix-ups needed, use values as-is. */ + break; + } + + return 0; +} + +/* + * Returns -EOPNOTSUPP if feature not enabled. Any other non-zero return value + * should be treated as fatal by caller. + */ +static int snp_cpuid(struct cpuid_leaf *leaf) +{ + const struct snp_cpuid_table *cpuid_table = snp_cpuid_get_table(); + + if (!cpuid_table->count) + return -EOPNOTSUPP; + + if (!snp_cpuid_get_validated_func(leaf)) { + /* + * Some hypervisors will avoid keeping track of CPUID entries + * where all values are zero, since they can be handled the + * same as out-of-range values (all-zero). This is useful here + * as well as it allows virtually all guest configurations to + * work using a single SNP CPUID table. + * + * To allow for this, there is a need to distinguish between + * out-of-range entries and in-range zero entries, since the + * CPUID table entries are only a template that may need to be + * augmented with additional values for things like + * CPU-specific information during post-processing. So if it's + * not in the table, set the values to zero. Then, if they are + * within a valid CPUID range, proceed with post-processing + * using zeros as the initial values. Otherwise, skip + * post-processing and just return zeros immediately. + */ + leaf->eax = leaf->ebx = leaf->ecx = leaf->edx = 0; + + /* Skip post-processing for out-of-range zero leafs. */ + if (!(leaf->fn <= cpuid_std_range_max || + (leaf->fn >= 0x40000000 && leaf->fn <= cpuid_hyp_range_max) || + (leaf->fn >= 0x80000000 && leaf->fn <= cpuid_ext_range_max))) + return 0; + } + + return snp_cpuid_postprocess(leaf); +} + /* * Boot VC Handler - This is the first VC handler during boot, there is no GHCB * page yet, so it only supports the MSR based communication with the @@ -157,40 +535,33 @@ enum es_result sev_es_ghcb_hv_call(struct ghcb *ghcb, bool set_ghcb_msr, */ void __init do_vc_no_ghcb(struct pt_regs *regs, unsigned long exit_code) { + unsigned int subfn = lower_bits(regs->cx, 32); unsigned int fn = lower_bits(regs->ax, 32); - unsigned long val; + struct cpuid_leaf leaf; + int ret; /* Only CPUID is supported via MSR protocol */ if (exit_code != SVM_EXIT_CPUID) goto fail; - sev_es_wr_ghcb_msr(GHCB_CPUID_REQ(fn, GHCB_CPUID_REQ_EAX)); - VMGEXIT(); - val = sev_es_rd_ghcb_msr(); - if (GHCB_RESP_CODE(val) != GHCB_MSR_CPUID_RESP) - goto fail; - regs->ax = val >> 32; + leaf.fn = fn; + leaf.subfn = subfn; - sev_es_wr_ghcb_msr(GHCB_CPUID_REQ(fn, GHCB_CPUID_REQ_EBX)); - VMGEXIT(); - val = sev_es_rd_ghcb_msr(); - if (GHCB_RESP_CODE(val) != GHCB_MSR_CPUID_RESP) - goto fail; - regs->bx = val >> 32; + ret = snp_cpuid(&leaf); + if (!ret) + goto cpuid_done; - sev_es_wr_ghcb_msr(GHCB_CPUID_REQ(fn, GHCB_CPUID_REQ_ECX)); - VMGEXIT(); - val = sev_es_rd_ghcb_msr(); - if (GHCB_RESP_CODE(val) != GHCB_MSR_CPUID_RESP) + if (ret != -EOPNOTSUPP) goto fail; - regs->cx = val >> 32; - sev_es_wr_ghcb_msr(GHCB_CPUID_REQ(fn, GHCB_CPUID_REQ_EDX)); - VMGEXIT(); - val = sev_es_rd_ghcb_msr(); - if (GHCB_RESP_CODE(val) != GHCB_MSR_CPUID_RESP) + if (sev_cpuid_hv(&leaf)) goto fail; - regs->dx = val >> 32; + +cpuid_done: + regs->ax = leaf.eax; + regs->bx = leaf.ebx; + regs->cx = leaf.ecx; + regs->dx = leaf.edx; /* * This is a VC handler and the #VC is only raised when SEV-ES is @@ -221,7 +592,7 @@ void __init do_vc_no_ghcb(struct pt_regs *regs, unsigned long exit_code) fail: /* Terminate the guest */ - sev_es_terminate(GHCB_SEV_ES_GEN_REQ); + sev_es_terminate(SEV_TERM_SET_GEN, GHCB_SEV_ES_GEN_REQ); } static enum es_result vc_insn_string_read(struct es_em_ctxt *ctxt, @@ -481,12 +852,37 @@ static enum es_result vc_handle_ioio(struct ghcb *ghcb, struct es_em_ctxt *ctxt) return ret; } +static int vc_handle_cpuid_snp(struct pt_regs *regs) +{ + struct cpuid_leaf leaf; + int ret; + + leaf.fn = regs->ax; + leaf.subfn = regs->cx; + ret = snp_cpuid(&leaf); + if (!ret) { + regs->ax = leaf.eax; + regs->bx = leaf.ebx; + regs->cx = leaf.ecx; + regs->dx = leaf.edx; + } + + return ret; +} + static enum es_result vc_handle_cpuid(struct ghcb *ghcb, struct es_em_ctxt *ctxt) { struct pt_regs *regs = ctxt->regs; u32 cr4 = native_read_cr4(); enum es_result ret; + int snp_cpuid_ret; + + snp_cpuid_ret = vc_handle_cpuid_snp(regs); + if (!snp_cpuid_ret) + return ES_OK; + if (snp_cpuid_ret != -EOPNOTSUPP) + return ES_VMM_ERROR; ghcb_set_rax(ghcb, regs->ax); ghcb_set_rcx(ghcb, regs->cx); @@ -538,3 +934,67 @@ static enum es_result vc_handle_rdtsc(struct ghcb *ghcb, return ES_OK; } + +struct cc_setup_data { + struct setup_data header; + u32 cc_blob_address; +}; + +/* + * Search for a Confidential Computing blob passed in as a setup_data entry + * via the Linux Boot Protocol. + */ +static struct cc_blob_sev_info *find_cc_blob_setup_data(struct boot_params *bp) +{ + struct cc_setup_data *sd = NULL; + struct setup_data *hdr; + + hdr = (struct setup_data *)bp->hdr.setup_data; + + while (hdr) { + if (hdr->type == SETUP_CC_BLOB) { + sd = (struct cc_setup_data *)hdr; + return (struct cc_blob_sev_info *)(unsigned long)sd->cc_blob_address; + } + hdr = (struct setup_data *)hdr->next; + } + + return NULL; +} + +/* + * Initialize the kernel's copy of the SNP CPUID table, and set up the + * pointer that will be used to access it. + * + * Maintaining a direct mapping of the SNP CPUID table used by firmware would + * be possible as an alternative, but the approach is brittle since the + * mapping needs to be updated in sync with all the changes to virtual memory + * layout and related mapping facilities throughout the boot process. + */ +static void __init setup_cpuid_table(const struct cc_blob_sev_info *cc_info) +{ + const struct snp_cpuid_table *cpuid_table_fw, *cpuid_table; + int i; + + if (!cc_info || !cc_info->cpuid_phys || cc_info->cpuid_len < PAGE_SIZE) + sev_es_terminate(SEV_TERM_SET_LINUX, GHCB_TERM_CPUID); + + cpuid_table_fw = (const struct snp_cpuid_table *)cc_info->cpuid_phys; + if (!cpuid_table_fw->count || cpuid_table_fw->count > SNP_CPUID_COUNT_MAX) + sev_es_terminate(SEV_TERM_SET_LINUX, GHCB_TERM_CPUID); + + cpuid_table = snp_cpuid_get_table(); + memcpy((void *)cpuid_table, cpuid_table_fw, sizeof(*cpuid_table)); + + /* Initialize CPUID ranges for range-checking. */ + for (i = 0; i < cpuid_table->count; i++) { + const struct snp_cpuid_fn *fn = &cpuid_table->fn[i]; + + if (fn->eax_in == 0x0) + cpuid_std_range_max = fn->eax; + else if (fn->eax_in == 0x40000000) + cpuid_hyp_range_max = fn->eax; + else if (fn->eax_in == 0x80000000) + cpuid_ext_range_max = fn->eax; + } +} diff --git a/arch/x86/kernel/sev.c b/arch/x86/kernel/sev.c index e6d316a01fdd..c05f0124c410 100644 --- a/arch/x86/kernel/sev.c +++ b/arch/x86/kernel/sev.c @@ -18,6 +18,10 @@ #include <linux/memblock.h> #include <linux/kernel.h> #include <linux/mm.h> +#include <linux/cpumask.h> +#include <linux/efi.h> +#include <linux/platform_device.h> +#include <linux/io.h> #include <asm/cpu_entry_area.h> #include <asm/stacktrace.h> @@ -31,9 +35,28 @@ #include <asm/svm.h> #include <asm/smp.h> #include <asm/cpu.h> +#include <asm/apic.h> +#include <asm/cpuid.h> +#include <asm/cmdline.h> #define DR7_RESET_VALUE 0x400 +/* AP INIT values as documented in the APM2 section "Processor Initialization State" */ +#define AP_INIT_CS_LIMIT 0xffff +#define AP_INIT_DS_LIMIT 0xffff +#define AP_INIT_LDTR_LIMIT 0xffff +#define AP_INIT_GDTR_LIMIT 0xffff +#define AP_INIT_IDTR_LIMIT 0xffff +#define AP_INIT_TR_LIMIT 0xffff +#define AP_INIT_RFLAGS_DEFAULT 0x2 +#define AP_INIT_DR6_DEFAULT 0xffff0ff0 +#define AP_INIT_GPAT_DEFAULT 0x0007040600070406ULL +#define AP_INIT_XCR0_DEFAULT 0x1 +#define AP_INIT_X87_FTW_DEFAULT 0x5555 +#define AP_INIT_X87_FCW_DEFAULT 0x0040 +#define AP_INIT_CR0_DEFAULT 0x60000010 +#define AP_INIT_MXCSR_DEFAULT 0x1f80 + /* For early boot hypervisor communication in SEV-ES enabled guests */ static struct ghcb boot_ghcb_page __bss_decrypted __aligned(PAGE_SIZE); @@ -41,7 +64,10 @@ static struct ghcb boot_ghcb_page __bss_decrypted __aligned(PAGE_SIZE); * Needs to be in the .data section because we need it NULL before bss is * cleared */ -static struct ghcb __initdata *boot_ghcb; +static struct ghcb *boot_ghcb __section(".data"); + +/* Bitmap of SEV features supported by the hypervisor */ +static u64 sev_hv_features __ro_after_init; /* #VC handler runtime per-CPU data */ struct sev_es_runtime_data { @@ -87,6 +113,15 @@ struct ghcb_state { static DEFINE_PER_CPU(struct sev_es_runtime_data*, runtime_data); DEFINE_STATIC_KEY_FALSE(sev_es_enable_key); +static DEFINE_PER_CPU(struct sev_es_save_area *, sev_vmsa); + +struct sev_config { + __u64 debug : 1, + __reserved : 63; +}; + +static struct sev_config sev_cfg __read_mostly; + static __always_inline bool on_vc_stack(struct pt_regs *regs) { unsigned long sp = regs->sp; @@ -523,13 +558,68 @@ void noinstr __sev_es_nmi_complete(void) __sev_put_ghcb(&state); } -static u64 get_jump_table_addr(void) +static u64 __init get_secrets_page(void) +{ + u64 pa_data = boot_params.cc_blob_address; + struct cc_blob_sev_info info; + void *map; + + /* + * The CC blob contains the address of the secrets page, check if the + * blob is present. + */ + if (!pa_data) + return 0; + + map = early_memremap(pa_data, sizeof(info)); + if (!map) { + pr_err("Unable to locate SNP secrets page: failed to map the Confidential Computing blob.\n"); + return 0; + } + memcpy(&info, map, sizeof(info)); + early_memunmap(map, sizeof(info)); + + /* smoke-test the secrets page passed */ + if (!info.secrets_phys || info.secrets_len != PAGE_SIZE) + return 0; + + return info.secrets_phys; +} + +static u64 __init get_snp_jump_table_addr(void) +{ + struct snp_secrets_page_layout *layout; + void __iomem *mem; + u64 pa, addr; + + pa = get_secrets_page(); + if (!pa) + return 0; + + mem = ioremap_encrypted(pa, PAGE_SIZE); + if (!mem) { + pr_err("Unable to locate AP jump table address: failed to map the SNP secrets page.\n"); + return 0; + } + + layout = (__force struct snp_secrets_page_layout *)mem; + + addr = layout->os_area.ap_jump_table_pa; + iounmap(mem); + + return addr; +} + +static u64 __init get_jump_table_addr(void) { struct ghcb_state state; unsigned long flags; struct ghcb *ghcb; u64 ret = 0; + if (cc_platform_has(CC_ATTR_GUEST_SEV_SNP)) + return get_snp_jump_table_addr(); + local_irq_save(flags); ghcb = __sev_get_ghcb(&state); @@ -553,7 +643,496 @@ static u64 get_jump_table_addr(void) return ret; } -int sev_es_setup_ap_jump_table(struct real_mode_header *rmh) +static void pvalidate_pages(unsigned long vaddr, unsigned int npages, bool validate) +{ + unsigned long vaddr_end; + int rc; + + vaddr = vaddr & PAGE_MASK; + vaddr_end = vaddr + (npages << PAGE_SHIFT); + + while (vaddr < vaddr_end) { + rc = pvalidate(vaddr, RMP_PG_SIZE_4K, validate); + if (WARN(rc, "Failed to validate address 0x%lx ret %d", vaddr, rc)) + sev_es_terminate(SEV_TERM_SET_LINUX, GHCB_TERM_PVALIDATE); + + vaddr = vaddr + PAGE_SIZE; + } +} + +static void __init early_set_pages_state(unsigned long paddr, unsigned int npages, enum psc_op op) +{ + unsigned long paddr_end; + u64 val; + + paddr = paddr & PAGE_MASK; + paddr_end = paddr + (npages << PAGE_SHIFT); + + while (paddr < paddr_end) { + /* + * Use the MSR protocol because this function can be called before + * the GHCB is established. + */ + sev_es_wr_ghcb_msr(GHCB_MSR_PSC_REQ_GFN(paddr >> PAGE_SHIFT, op)); + VMGEXIT(); + + val = sev_es_rd_ghcb_msr(); + + if (WARN(GHCB_RESP_CODE(val) != GHCB_MSR_PSC_RESP, + "Wrong PSC response code: 0x%x\n", + (unsigned int)GHCB_RESP_CODE(val))) + goto e_term; + + if (WARN(GHCB_MSR_PSC_RESP_VAL(val), + "Failed to change page state to '%s' paddr 0x%lx error 0x%llx\n", + op == SNP_PAGE_STATE_PRIVATE ? "private" : "shared", + paddr, GHCB_MSR_PSC_RESP_VAL(val))) + goto e_term; + + paddr = paddr + PAGE_SIZE; + } + + return; + +e_term: + sev_es_terminate(SEV_TERM_SET_LINUX, GHCB_TERM_PSC); +} + +void __init early_snp_set_memory_private(unsigned long vaddr, unsigned long paddr, + unsigned int npages) +{ + if (!cc_platform_has(CC_ATTR_GUEST_SEV_SNP)) + return; + + /* + * Ask the hypervisor to mark the memory pages as private in the RMP + * table. + */ + early_set_pages_state(paddr, npages, SNP_PAGE_STATE_PRIVATE); + + /* Validate the memory pages after they've been added in the RMP table. */ + pvalidate_pages(vaddr, npages, true); +} + +void __init early_snp_set_memory_shared(unsigned long vaddr, unsigned long paddr, + unsigned int npages) +{ + if (!cc_platform_has(CC_ATTR_GUEST_SEV_SNP)) + return; + + /* Invalidate the memory pages before they are marked shared in the RMP table. */ + pvalidate_pages(vaddr, npages, false); + + /* Ask hypervisor to mark the memory pages shared in the RMP table. */ + early_set_pages_state(paddr, npages, SNP_PAGE_STATE_SHARED); +} + +void __init snp_prep_memory(unsigned long paddr, unsigned int sz, enum psc_op op) +{ + unsigned long vaddr, npages; + + vaddr = (unsigned long)__va(paddr); + npages = PAGE_ALIGN(sz) >> PAGE_SHIFT; + + if (op == SNP_PAGE_STATE_PRIVATE) + early_snp_set_memory_private(vaddr, paddr, npages); + else if (op == SNP_PAGE_STATE_SHARED) + early_snp_set_memory_shared(vaddr, paddr, npages); + else + WARN(1, "invalid memory op %d\n", op); +} + +static int vmgexit_psc(struct snp_psc_desc *desc) +{ + int cur_entry, end_entry, ret = 0; + struct snp_psc_desc *data; + struct ghcb_state state; + struct es_em_ctxt ctxt; + unsigned long flags; + struct ghcb *ghcb; + + /* + * __sev_get_ghcb() needs to run with IRQs disabled because it is using + * a per-CPU GHCB. + */ + local_irq_save(flags); + + ghcb = __sev_get_ghcb(&state); + if (!ghcb) { + ret = 1; + goto out_unlock; + } + + /* Copy the input desc into GHCB shared buffer */ + data = (struct snp_psc_desc *)ghcb->shared_buffer; + memcpy(ghcb->shared_buffer, desc, min_t(int, GHCB_SHARED_BUF_SIZE, sizeof(*desc))); + + /* + * As per the GHCB specification, the hypervisor can resume the guest + * before processing all the entries. Check whether all the entries + * are processed. If not, then keep retrying. Note, the hypervisor + * will update the data memory directly to indicate the status, so + * reference the data->hdr everywhere. + * + * The strategy here is to wait for the hypervisor to change the page + * state in the RMP table before guest accesses the memory pages. If the + * page state change was not successful, then later memory access will + * result in a crash. + */ + cur_entry = data->hdr.cur_entry; + end_entry = data->hdr.end_entry; + + while (data->hdr.cur_entry <= data->hdr.end_entry) { + ghcb_set_sw_scratch(ghcb, (u64)__pa(data)); + + /* This will advance the shared buffer data points to. */ + ret = sev_es_ghcb_hv_call(ghcb, true, &ctxt, SVM_VMGEXIT_PSC, 0, 0); + + /* + * Page State Change VMGEXIT can pass error code through + * exit_info_2. + */ + if (WARN(ret || ghcb->save.sw_exit_info_2, + "SNP: PSC failed ret=%d exit_info_2=%llx\n", + ret, ghcb->save.sw_exit_info_2)) { + ret = 1; + goto out; + } + + /* Verify that reserved bit is not set */ + if (WARN(data->hdr.reserved, "Reserved bit is set in the PSC header\n")) { + ret = 1; + goto out; + } + + /* + * Sanity check that entry processing is not going backwards. + * This will happen only if hypervisor is tricking us. + */ + if (WARN(data->hdr.end_entry > end_entry || cur_entry > data->hdr.cur_entry, +"SNP: PSC processing going backward, end_entry %d (got %d) cur_entry %d (got %d)\n", + end_entry, data->hdr.end_entry, cur_entry, data->hdr.cur_entry)) { + ret = 1; + goto out; + } + } + +out: + __sev_put_ghcb(&state); + +out_unlock: + local_irq_restore(flags); + + return ret; +} + +static void __set_pages_state(struct snp_psc_desc *data, unsigned long vaddr, + unsigned long vaddr_end, int op) +{ + struct psc_hdr *hdr; + struct psc_entry *e; + unsigned long pfn; + int i; + + hdr = &data->hdr; + e = data->entries; + + memset(data, 0, sizeof(*data)); + i = 0; + + while (vaddr < vaddr_end) { + if (is_vmalloc_addr((void *)vaddr)) + pfn = vmalloc_to_pfn((void *)vaddr); + else + pfn = __pa(vaddr) >> PAGE_SHIFT; + + e->gfn = pfn; + e->operation = op; + hdr->end_entry = i; + + /* + * Current SNP implementation doesn't keep track of the RMP page + * size so use 4K for simplicity. + */ + e->pagesize = RMP_PG_SIZE_4K; + + vaddr = vaddr + PAGE_SIZE; + e++; + i++; + } + + if (vmgexit_psc(data)) + sev_es_terminate(SEV_TERM_SET_LINUX, GHCB_TERM_PSC); +} + +static void set_pages_state(unsigned long vaddr, unsigned int npages, int op) +{ + unsigned long vaddr_end, next_vaddr; + struct snp_psc_desc *desc; + + desc = kmalloc(sizeof(*desc), GFP_KERNEL_ACCOUNT); + if (!desc) + panic("SNP: failed to allocate memory for PSC descriptor\n"); + + vaddr = vaddr & PAGE_MASK; + vaddr_end = vaddr + (npages << PAGE_SHIFT); + + while (vaddr < vaddr_end) { + /* Calculate the last vaddr that fits in one struct snp_psc_desc. */ + next_vaddr = min_t(unsigned long, vaddr_end, + (VMGEXIT_PSC_MAX_ENTRY * PAGE_SIZE) + vaddr); + + __set_pages_state(desc, vaddr, next_vaddr, op); + + vaddr = next_vaddr; + } + + kfree(desc); +} + +void snp_set_memory_shared(unsigned long vaddr, unsigned int npages) +{ + if (!cc_platform_has(CC_ATTR_GUEST_SEV_SNP)) + return; + + pvalidate_pages(vaddr, npages, false); + + set_pages_state(vaddr, npages, SNP_PAGE_STATE_SHARED); +} + +void snp_set_memory_private(unsigned long vaddr, unsigned int npages) +{ + if (!cc_platform_has(CC_ATTR_GUEST_SEV_SNP)) + return; + + set_pages_state(vaddr, npages, SNP_PAGE_STATE_PRIVATE); + + pvalidate_pages(vaddr, npages, true); +} + +static int snp_set_vmsa(void *va, bool vmsa) +{ + u64 attrs; + + /* + * Running at VMPL0 allows the kernel to change the VMSA bit for a page + * using the RMPADJUST instruction. However, for the instruction to + * succeed it must target the permissions of a lesser privileged + * (higher numbered) VMPL level, so use VMPL1 (refer to the RMPADJUST + * instruction in the AMD64 APM Volume 3). + */ + attrs = 1; + if (vmsa) + attrs |= RMPADJUST_VMSA_PAGE_BIT; + + return rmpadjust((unsigned long)va, RMP_PG_SIZE_4K, attrs); +} + +#define __ATTR_BASE (SVM_SELECTOR_P_MASK | SVM_SELECTOR_S_MASK) +#define INIT_CS_ATTRIBS (__ATTR_BASE | SVM_SELECTOR_READ_MASK | SVM_SELECTOR_CODE_MASK) +#define INIT_DS_ATTRIBS (__ATTR_BASE | SVM_SELECTOR_WRITE_MASK) + +#define INIT_LDTR_ATTRIBS (SVM_SELECTOR_P_MASK | 2) +#define INIT_TR_ATTRIBS (SVM_SELECTOR_P_MASK | 3) + +static void *snp_alloc_vmsa_page(void) +{ + struct page *p; + + /* + * Allocate VMSA page to work around the SNP erratum where the CPU will + * incorrectly signal an RMP violation #PF if a large page (2MB or 1GB) + * collides with the RMP entry of VMSA page. The recommended workaround + * is to not use a large page. + * + * Allocate an 8k page which is also 8k-aligned. + */ + p = alloc_pages(GFP_KERNEL_ACCOUNT | __GFP_ZERO, 1); + if (!p) + return NULL; + + split_page(p, 1); + + /* Free the first 4k. This page may be 2M/1G aligned and cannot be used. */ + __free_page(p); + + return page_address(p + 1); +} + +static void snp_cleanup_vmsa(struct sev_es_save_area *vmsa) +{ + int err; + + err = snp_set_vmsa(vmsa, false); + if (err) + pr_err("clear VMSA page failed (%u), leaking page\n", err); + else + free_page((unsigned long)vmsa); +} + +static int wakeup_cpu_via_vmgexit(int apic_id, unsigned long start_ip) +{ + struct sev_es_save_area *cur_vmsa, *vmsa; + struct ghcb_state state; + unsigned long flags; + struct ghcb *ghcb; + u8 sipi_vector; + int cpu, ret; + u64 cr4; + + /* + * The hypervisor SNP feature support check has happened earlier, just check + * the AP_CREATION one here. + */ + if (!(sev_hv_features & GHCB_HV_FT_SNP_AP_CREATION)) + return -EOPNOTSUPP; + + /* + * Verify the desired start IP against the known trampoline start IP + * to catch any future new trampolines that may be introduced that + * would require a new protected guest entry point. + */ + if (WARN_ONCE(start_ip != real_mode_header->trampoline_start, + "Unsupported SNP start_ip: %lx\n", start_ip)) + return -EINVAL; + + /* Override start_ip with known protected guest start IP */ + start_ip = real_mode_header->sev_es_trampoline_start; + + /* Find the logical CPU for the APIC ID */ + for_each_present_cpu(cpu) { + if (arch_match_cpu_phys_id(cpu, apic_id)) + break; + } + if (cpu >= nr_cpu_ids) + return -EINVAL; + + cur_vmsa = per_cpu(sev_vmsa, cpu); + + /* + * A new VMSA is created each time because there is no guarantee that + * the current VMSA is the kernels or that the vCPU is not running. If + * an attempt was done to use the current VMSA with a running vCPU, a + * #VMEXIT of that vCPU would wipe out all of the settings being done + * here. + */ + vmsa = (struct sev_es_save_area *)snp_alloc_vmsa_page(); + if (!vmsa) + return -ENOMEM; + + /* CR4 should maintain the MCE value */ + cr4 = native_read_cr4() & X86_CR4_MCE; + + /* Set the CS value based on the start_ip converted to a SIPI vector */ + sipi_vector = (start_ip >> 12); + vmsa->cs.base = sipi_vector << 12; + vmsa->cs.limit = AP_INIT_CS_LIMIT; + vmsa->cs.attrib = INIT_CS_ATTRIBS; + vmsa->cs.selector = sipi_vector << 8; + + /* Set the RIP value based on start_ip */ + vmsa->rip = start_ip & 0xfff; + + /* Set AP INIT defaults as documented in the APM */ + vmsa->ds.limit = AP_INIT_DS_LIMIT; + vmsa->ds.attrib = INIT_DS_ATTRIBS; + vmsa->es = vmsa->ds; + vmsa->fs = vmsa->ds; + vmsa->gs = vmsa->ds; + vmsa->ss = vmsa->ds; + + vmsa->gdtr.limit = AP_INIT_GDTR_LIMIT; + vmsa->ldtr.limit = AP_INIT_LDTR_LIMIT; + vmsa->ldtr.attrib = INIT_LDTR_ATTRIBS; + vmsa->idtr.limit = AP_INIT_IDTR_LIMIT; + vmsa->tr.limit = AP_INIT_TR_LIMIT; + vmsa->tr.attrib = INIT_TR_ATTRIBS; + + vmsa->cr4 = cr4; + vmsa->cr0 = AP_INIT_CR0_DEFAULT; + vmsa->dr7 = DR7_RESET_VALUE; + vmsa->dr6 = AP_INIT_DR6_DEFAULT; + vmsa->rflags = AP_INIT_RFLAGS_DEFAULT; + vmsa->g_pat = AP_INIT_GPAT_DEFAULT; + vmsa->xcr0 = AP_INIT_XCR0_DEFAULT; + vmsa->mxcsr = AP_INIT_MXCSR_DEFAULT; + vmsa->x87_ftw = AP_INIT_X87_FTW_DEFAULT; + vmsa->x87_fcw = AP_INIT_X87_FCW_DEFAULT; + + /* SVME must be set. */ + vmsa->efer = EFER_SVME; + + /* + * Set the SNP-specific fields for this VMSA: + * VMPL level + * SEV_FEATURES (matches the SEV STATUS MSR right shifted 2 bits) + */ + vmsa->vmpl = 0; + vmsa->sev_features = sev_status >> 2; + + /* Switch the page over to a VMSA page now that it is initialized */ + ret = snp_set_vmsa(vmsa, true); + if (ret) { + pr_err("set VMSA page failed (%u)\n", ret); + free_page((unsigned long)vmsa); + + return -EINVAL; + } + + /* Issue VMGEXIT AP Creation NAE event */ + local_irq_save(flags); + + ghcb = __sev_get_ghcb(&state); + + vc_ghcb_invalidate(ghcb); + ghcb_set_rax(ghcb, vmsa->sev_features); + ghcb_set_sw_exit_code(ghcb, SVM_VMGEXIT_AP_CREATION); + ghcb_set_sw_exit_info_1(ghcb, ((u64)apic_id << 32) | SVM_VMGEXIT_AP_CREATE); + ghcb_set_sw_exit_info_2(ghcb, __pa(vmsa)); + + sev_es_wr_ghcb_msr(__pa(ghcb)); + VMGEXIT(); + + if (!ghcb_sw_exit_info_1_is_valid(ghcb) || + lower_32_bits(ghcb->save.sw_exit_info_1)) { + pr_err("SNP AP Creation error\n"); + ret = -EINVAL; + } + + __sev_put_ghcb(&state); + + local_irq_restore(flags); + + /* Perform cleanup if there was an error */ + if (ret) { + snp_cleanup_vmsa(vmsa); + vmsa = NULL; + } + + /* Free up any previous VMSA page */ + if (cur_vmsa) + snp_cleanup_vmsa(cur_vmsa); + + /* Record the current VMSA page */ + per_cpu(sev_vmsa, cpu) = vmsa; + + return ret; +} + +void snp_set_wakeup_secondary_cpu(void) +{ + if (!cc_platform_has(CC_ATTR_GUEST_SEV_SNP)) + return; + + /* + * Always set this override if SNP is enabled. This makes it the + * required method to start APs under SNP. If the hypervisor does + * not support AP creation, then no APs will be started. + */ + apic->wakeup_secondary_cpu = wakeup_cpu_via_vmgexit; +} + +int __init sev_es_setup_ap_jump_table(struct real_mode_header *rmh) { u16 startup_cs, startup_ip; phys_addr_t jump_table_pa; @@ -644,15 +1223,39 @@ static enum es_result vc_handle_msr(struct ghcb *ghcb, struct es_em_ctxt *ctxt) return ret; } -/* - * This function runs on the first #VC exception after the kernel - * switched to virtual addresses. - */ -static bool __init sev_es_setup_ghcb(void) +static void snp_register_per_cpu_ghcb(void) +{ + struct sev_es_runtime_data *data; + struct ghcb *ghcb; + + data = this_cpu_read(runtime_data); + ghcb = &data->ghcb_page; + + snp_register_ghcb_early(__pa(ghcb)); +} + +void setup_ghcb(void) { + if (!cc_platform_has(CC_ATTR_GUEST_STATE_ENCRYPT)) + return; + /* First make sure the hypervisor talks a supported protocol. */ if (!sev_es_negotiate_protocol()) - return false; + sev_es_terminate(SEV_TERM_SET_GEN, GHCB_SEV_ES_GEN_REQ); + + /* + * Check whether the runtime #VC exception handler is active. It uses + * the per-CPU GHCB page which is set up by sev_es_init_vc_handling(). + * + * If SNP is active, register the per-CPU GHCB page so that the runtime + * exception handler can use it. + */ + if (initial_vc_handler == (unsigned long)kernel_exc_vmm_communication) { + if (cc_platform_has(CC_ATTR_GUEST_SEV_SNP)) + snp_register_per_cpu_ghcb(); + + return; + } /* * Clear the boot_ghcb. The first exception comes in before the bss @@ -663,7 +1266,9 @@ static bool __init sev_es_setup_ghcb(void) /* Alright - Make the boot-ghcb public */ boot_ghcb = &boot_ghcb_page; - return true; + /* SNP guest requires that GHCB GPA must be registered. */ + if (cc_platform_has(CC_ATTR_GUEST_SEV_SNP)) + snp_register_ghcb_early(__pa(&boot_ghcb_page)); } #ifdef CONFIG_HOTPLUG_CPU @@ -766,6 +1371,17 @@ void __init sev_es_init_vc_handling(void) if (!sev_es_check_cpu_features()) panic("SEV-ES CPU Features missing"); + /* + * SNP is supported in v2 of the GHCB spec which mandates support for HV + * features. + */ + if (cc_platform_has(CC_ATTR_GUEST_SEV_SNP)) { + sev_hv_features = get_hv_features(); + + if (!(sev_hv_features & GHCB_HV_FT_SNP)) + sev_es_terminate(SEV_TERM_SET_GEN, GHCB_SNP_UNSUPPORTED); + } + /* Enable SEV-ES special handling */ static_branch_enable(&sev_es_enable_key); @@ -1337,7 +1953,7 @@ DEFINE_IDTENTRY_VC_KERNEL(exc_vmm_communication) show_regs(regs); /* Ask hypervisor to sev_es_terminate */ - sev_es_terminate(GHCB_SEV_ES_GEN_REQ); + sev_es_terminate(SEV_TERM_SET_GEN, GHCB_SEV_ES_GEN_REQ); /* If that fails and we get here - just panic */ panic("Returned from Terminate-Request to Hypervisor\n"); @@ -1383,10 +1999,6 @@ bool __init handle_vc_boot_ghcb(struct pt_regs *regs) struct es_em_ctxt ctxt; enum es_result result; - /* Do initial setup or terminate the guest */ - if (unlikely(boot_ghcb == NULL && !sev_es_setup_ghcb())) - sev_es_terminate(GHCB_SEV_ES_GEN_REQ); - vc_ghcb_invalidate(boot_ghcb); result = vc_init_em_ctxt(&ctxt, regs, exit_code); @@ -1425,6 +2037,215 @@ bool __init handle_vc_boot_ghcb(struct pt_regs *regs) fail: show_regs(regs); - while (true) - halt(); + sev_es_terminate(SEV_TERM_SET_GEN, GHCB_SEV_ES_GEN_REQ); +} + +/* + * Initial set up of SNP relies on information provided by the + * Confidential Computing blob, which can be passed to the kernel + * in the following ways, depending on how it is booted: + * + * - when booted via the boot/decompress kernel: + * - via boot_params + * + * - when booted directly by firmware/bootloader (e.g. CONFIG_PVH): + * - via a setup_data entry, as defined by the Linux Boot Protocol + * + * Scan for the blob in that order. + */ +static __init struct cc_blob_sev_info *find_cc_blob(struct boot_params *bp) +{ + struct cc_blob_sev_info *cc_info; + + /* Boot kernel would have passed the CC blob via boot_params. */ + if (bp->cc_blob_address) { + cc_info = (struct cc_blob_sev_info *)(unsigned long)bp->cc_blob_address; + goto found_cc_info; + } + + /* + * If kernel was booted directly, without the use of the + * boot/decompression kernel, the CC blob may have been passed via + * setup_data instead. + */ + cc_info = find_cc_blob_setup_data(bp); + if (!cc_info) + return NULL; + +found_cc_info: + if (cc_info->magic != CC_BLOB_SEV_HDR_MAGIC) + snp_abort(); + + return cc_info; +} + +bool __init snp_init(struct boot_params *bp) +{ + struct cc_blob_sev_info *cc_info; + + if (!bp) + return false; + + cc_info = find_cc_blob(bp); + if (!cc_info) + return false; + + setup_cpuid_table(cc_info); + + /* + * The CC blob will be used later to access the secrets page. Cache + * it here like the boot kernel does. + */ + bp->cc_blob_address = (u32)(unsigned long)cc_info; + + return true; +} + +void __init snp_abort(void) +{ + sev_es_terminate(SEV_TERM_SET_GEN, GHCB_SNP_UNSUPPORTED); +} + +static void dump_cpuid_table(void) +{ + const struct snp_cpuid_table *cpuid_table = snp_cpuid_get_table(); + int i = 0; + + pr_info("count=%d reserved=0x%x reserved2=0x%llx\n", + cpuid_table->count, cpuid_table->__reserved1, cpuid_table->__reserved2); + + for (i = 0; i < SNP_CPUID_COUNT_MAX; i++) { + const struct snp_cpuid_fn *fn = &cpuid_table->fn[i]; + + pr_info("index=%3d fn=0x%08x subfn=0x%08x: eax=0x%08x ebx=0x%08x ecx=0x%08x edx=0x%08x xcr0_in=0x%016llx xss_in=0x%016llx reserved=0x%016llx\n", + i, fn->eax_in, fn->ecx_in, fn->eax, fn->ebx, fn->ecx, + fn->edx, fn->xcr0_in, fn->xss_in, fn->__reserved); + } +} + +/* + * It is useful from an auditing/testing perspective to provide an easy way + * for the guest owner to know that the CPUID table has been initialized as + * expected, but that initialization happens too early in boot to print any + * sort of indicator, and there's not really any other good place to do it, + * so do it here. + */ +static int __init report_cpuid_table(void) +{ + const struct snp_cpuid_table *cpuid_table = snp_cpuid_get_table(); + + if (!cpuid_table->count) + return 0; + + pr_info("Using SNP CPUID table, %d entries present.\n", + cpuid_table->count); + + if (sev_cfg.debug) + dump_cpuid_table(); + + return 0; +} +arch_initcall(report_cpuid_table); + +static int __init init_sev_config(char *str) +{ + char *s; + + while ((s = strsep(&str, ","))) { + if (!strcmp(s, "debug")) { + sev_cfg.debug = true; + continue; + } + + pr_info("SEV command-line option '%s' was not recognized\n", s); + } + + return 1; +} +__setup("sev=", init_sev_config); + +int snp_issue_guest_request(u64 exit_code, struct snp_req_data *input, unsigned long *fw_err) +{ + struct ghcb_state state; + struct es_em_ctxt ctxt; + unsigned long flags; + struct ghcb *ghcb; + int ret; + + if (!cc_platform_has(CC_ATTR_GUEST_SEV_SNP)) + return -ENODEV; + + if (!fw_err) + return -EINVAL; + + /* + * __sev_get_ghcb() needs to run with IRQs disabled because it is using + * a per-CPU GHCB. + */ + local_irq_save(flags); + + ghcb = __sev_get_ghcb(&state); + if (!ghcb) { + ret = -EIO; + goto e_restore_irq; + } + + vc_ghcb_invalidate(ghcb); + + if (exit_code == SVM_VMGEXIT_EXT_GUEST_REQUEST) { + ghcb_set_rax(ghcb, input->data_gpa); + ghcb_set_rbx(ghcb, input->data_npages); + } + + ret = sev_es_ghcb_hv_call(ghcb, true, &ctxt, exit_code, input->req_gpa, input->resp_gpa); + if (ret) + goto e_put; + + if (ghcb->save.sw_exit_info_2) { + /* Number of expected pages are returned in RBX */ + if (exit_code == SVM_VMGEXIT_EXT_GUEST_REQUEST && + ghcb->save.sw_exit_info_2 == SNP_GUEST_REQ_INVALID_LEN) + input->data_npages = ghcb_get_rbx(ghcb); + + *fw_err = ghcb->save.sw_exit_info_2; + + ret = -EIO; + } + +e_put: + __sev_put_ghcb(&state); +e_restore_irq: + local_irq_restore(flags); + + return ret; +} +EXPORT_SYMBOL_GPL(snp_issue_guest_request); + +static struct platform_device sev_guest_device = { + .name = "sev-guest", + .id = -1, +}; + +static int __init snp_init_platform_device(void) +{ + struct sev_guest_platform_data data; + u64 gpa; + + if (!cc_platform_has(CC_ATTR_GUEST_SEV_SNP)) + return -ENODEV; + + gpa = get_secrets_page(); + if (!gpa) + return -ENODEV; + + data.secrets_gpa = gpa; + if (platform_device_add_data(&sev_guest_device, &data, sizeof(data))) + return -ENODEV; + + if (platform_device_register(&sev_guest_device)) + return -ENODEV; + + pr_info("SNP guest platform device initialized.\n"); + return 0; } +device_initcall(snp_init_platform_device); diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c index e439eb14325f..9c7265b524c7 100644 --- a/arch/x86/kernel/signal.c +++ b/arch/x86/kernel/signal.c @@ -93,7 +93,7 @@ static bool restore_sigcontext(struct pt_regs *regs, return false; #ifdef CONFIG_X86_32 - set_user_gs(regs, sc.gs); + loadsegment(gs, sc.gs); regs->fs = sc.fs; regs->es = sc.es; regs->ds = sc.ds; @@ -146,8 +146,10 @@ __unsafe_setup_sigcontext(struct sigcontext __user *sc, void __user *fpstate, struct pt_regs *regs, unsigned long mask) { #ifdef CONFIG_X86_32 - unsafe_put_user(get_user_gs(regs), - (unsigned int __user *)&sc->gs, Efault); + unsigned int gs; + savesegment(gs, gs); + + unsafe_put_user(gs, (unsigned int __user *)&sc->gs, Efault); unsafe_put_user(regs->fs, (unsigned int __user *)&sc->fs, Efault); unsafe_put_user(regs->es, (unsigned int __user *)&sc->es, Efault); unsafe_put_user(regs->ds, (unsigned int __user *)&sc->ds, Efault); diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index 2ef14772dc04..5e7f9532a10d 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -56,7 +56,6 @@ #include <linux/numa.h> #include <linux/pgtable.h> #include <linux/overflow.h> -#include <linux/syscore_ops.h> #include <asm/acpi.h> #include <asm/desc.h> @@ -82,6 +81,7 @@ #include <asm/spec-ctrl.h> #include <asm/hw_irq.h> #include <asm/stackprotector.h> +#include <asm/sev.h> /* representing HT siblings of each logical CPU */ DEFINE_PER_CPU_READ_MOSTLY(cpumask_var_t, cpu_sibling_map); @@ -187,7 +187,7 @@ static void smp_callin(void) */ set_cpu_sibling_map(raw_smp_processor_id()); - init_freq_invariance(true, false); + ap_init_aperfmperf(); /* * Get our bogomips. @@ -1082,6 +1082,11 @@ static int do_boot_cpu(int apicid, int cpu, struct task_struct *idle, unsigned long boot_error = 0; unsigned long timeout; +#ifdef CONFIG_X86_64 + /* If 64-bit wakeup method exists, use the 64-bit mode trampoline IP */ + if (apic->wakeup_secondary_cpu_64) + start_ip = real_mode_header->trampoline_start64; +#endif idle->thread.sp = (unsigned long)task_pt_regs(idle); early_gdt_descr.address = (unsigned long)get_cpu_gdt_rw(cpu); initial_code = (unsigned long)start_secondary; @@ -1123,11 +1128,14 @@ static int do_boot_cpu(int apicid, int cpu, struct task_struct *idle, /* * Wake up a CPU in difference cases: - * - Use the method in the APIC driver if it's defined + * - Use a method from the APIC driver if one defined, with wakeup + * straight to 64-bit mode preferred over wakeup to RM. * Otherwise, * - Use an INIT boot APIC message for APs or NMI for BSP. */ - if (apic->wakeup_secondary_cpu) + if (apic->wakeup_secondary_cpu_64) + boot_error = apic->wakeup_secondary_cpu_64(apicid, start_ip); + else if (apic->wakeup_secondary_cpu) boot_error = apic->wakeup_secondary_cpu(apicid, start_ip); else boot_error = wakeup_cpu_via_init_nmi(cpu, start_ip, apicid, @@ -1397,7 +1405,6 @@ void __init native_smp_prepare_cpus(unsigned int max_cpus) { smp_prepare_cpus_common(); - init_freq_invariance(false, false); smp_sanity_check(); switch (apic_intr_mode) { @@ -1430,6 +1437,8 @@ void __init native_smp_prepare_cpus(unsigned int max_cpus) smp_quirk_init_udelay(); speculative_store_bypass_ht_init(); + + snp_set_wakeup_secondary_cpu(); } void arch_thaw_secondary_cpus_begin(void) @@ -1847,357 +1856,3 @@ void native_play_dead(void) } #endif - -#ifdef CONFIG_X86_64 -/* - * APERF/MPERF frequency ratio computation. - * - * The scheduler wants to do frequency invariant accounting and needs a <1 - * ratio to account for the 'current' frequency, corresponding to - * freq_curr / freq_max. - * - * Since the frequency freq_curr on x86 is controlled by micro-controller and - * our P-state setting is little more than a request/hint, we need to observe - * the effective frequency 'BusyMHz', i.e. the average frequency over a time - * interval after discarding idle time. This is given by: - * - * BusyMHz = delta_APERF / delta_MPERF * freq_base - * - * where freq_base is the max non-turbo P-state. - * - * The freq_max term has to be set to a somewhat arbitrary value, because we - * can't know which turbo states will be available at a given point in time: - * it all depends on the thermal headroom of the entire package. We set it to - * the turbo level with 4 cores active. - * - * Benchmarks show that's a good compromise between the 1C turbo ratio - * (freq_curr/freq_max would rarely reach 1) and something close to freq_base, - * which would ignore the entire turbo range (a conspicuous part, making - * freq_curr/freq_max always maxed out). - * - * An exception to the heuristic above is the Atom uarch, where we choose the - * highest turbo level for freq_max since Atom's are generally oriented towards - * power efficiency. - * - * Setting freq_max to anything less than the 1C turbo ratio makes the ratio - * freq_curr / freq_max to eventually grow >1, in which case we clip it to 1. - */ - -DEFINE_STATIC_KEY_FALSE(arch_scale_freq_key); - -static DEFINE_PER_CPU(u64, arch_prev_aperf); -static DEFINE_PER_CPU(u64, arch_prev_mperf); -static u64 arch_turbo_freq_ratio = SCHED_CAPACITY_SCALE; -static u64 arch_max_freq_ratio = SCHED_CAPACITY_SCALE; - -void arch_set_max_freq_ratio(bool turbo_disabled) -{ - arch_max_freq_ratio = turbo_disabled ? SCHED_CAPACITY_SCALE : - arch_turbo_freq_ratio; -} -EXPORT_SYMBOL_GPL(arch_set_max_freq_ratio); - -static bool turbo_disabled(void) -{ - u64 misc_en; - int err; - - err = rdmsrl_safe(MSR_IA32_MISC_ENABLE, &misc_en); - if (err) - return false; - - return (misc_en & MSR_IA32_MISC_ENABLE_TURBO_DISABLE); -} - -static bool slv_set_max_freq_ratio(u64 *base_freq, u64 *turbo_freq) -{ - int err; - - err = rdmsrl_safe(MSR_ATOM_CORE_RATIOS, base_freq); - if (err) - return false; - - err = rdmsrl_safe(MSR_ATOM_CORE_TURBO_RATIOS, turbo_freq); - if (err) - return false; - - *base_freq = (*base_freq >> 16) & 0x3F; /* max P state */ - *turbo_freq = *turbo_freq & 0x3F; /* 1C turbo */ - - return true; -} - -#define X86_MATCH(model) \ - X86_MATCH_VENDOR_FAM_MODEL_FEATURE(INTEL, 6, \ - INTEL_FAM6_##model, X86_FEATURE_APERFMPERF, NULL) - -static const struct x86_cpu_id has_knl_turbo_ratio_limits[] = { - X86_MATCH(XEON_PHI_KNL), - X86_MATCH(XEON_PHI_KNM), - {} -}; - -static const struct x86_cpu_id has_skx_turbo_ratio_limits[] = { - X86_MATCH(SKYLAKE_X), - {} -}; - -static const struct x86_cpu_id has_glm_turbo_ratio_limits[] = { - X86_MATCH(ATOM_GOLDMONT), - X86_MATCH(ATOM_GOLDMONT_D), - X86_MATCH(ATOM_GOLDMONT_PLUS), - {} -}; - -static bool knl_set_max_freq_ratio(u64 *base_freq, u64 *turbo_freq, - int num_delta_fratio) -{ - int fratio, delta_fratio, found; - int err, i; - u64 msr; - - err = rdmsrl_safe(MSR_PLATFORM_INFO, base_freq); - if (err) - return false; - - *base_freq = (*base_freq >> 8) & 0xFF; /* max P state */ - - err = rdmsrl_safe(MSR_TURBO_RATIO_LIMIT, &msr); - if (err) - return false; - - fratio = (msr >> 8) & 0xFF; - i = 16; - found = 0; - do { - if (found >= num_delta_fratio) { - *turbo_freq = fratio; - return true; - } - - delta_fratio = (msr >> (i + 5)) & 0x7; - - if (delta_fratio) { - found += 1; - fratio -= delta_fratio; - } - - i += 8; - } while (i < 64); - - return true; -} - -static bool skx_set_max_freq_ratio(u64 *base_freq, u64 *turbo_freq, int size) -{ - u64 ratios, counts; - u32 group_size; - int err, i; - - err = rdmsrl_safe(MSR_PLATFORM_INFO, base_freq); - if (err) - return false; - - *base_freq = (*base_freq >> 8) & 0xFF; /* max P state */ - - err = rdmsrl_safe(MSR_TURBO_RATIO_LIMIT, &ratios); - if (err) - return false; - - err = rdmsrl_safe(MSR_TURBO_RATIO_LIMIT1, &counts); - if (err) - return false; - - for (i = 0; i < 64; i += 8) { - group_size = (counts >> i) & 0xFF; - if (group_size >= size) { - *turbo_freq = (ratios >> i) & 0xFF; - return true; - } - } - - return false; -} - -static bool core_set_max_freq_ratio(u64 *base_freq, u64 *turbo_freq) -{ - u64 msr; - int err; - - err = rdmsrl_safe(MSR_PLATFORM_INFO, base_freq); - if (err) - return false; - - err = rdmsrl_safe(MSR_TURBO_RATIO_LIMIT, &msr); - if (err) - return false; - - *base_freq = (*base_freq >> 8) & 0xFF; /* max P state */ - *turbo_freq = (msr >> 24) & 0xFF; /* 4C turbo */ - - /* The CPU may have less than 4 cores */ - if (!*turbo_freq) - *turbo_freq = msr & 0xFF; /* 1C turbo */ - - return true; -} - -static bool intel_set_max_freq_ratio(void) -{ - u64 base_freq, turbo_freq; - u64 turbo_ratio; - - if (slv_set_max_freq_ratio(&base_freq, &turbo_freq)) - goto out; - - if (x86_match_cpu(has_glm_turbo_ratio_limits) && - skx_set_max_freq_ratio(&base_freq, &turbo_freq, 1)) - goto out; - - if (x86_match_cpu(has_knl_turbo_ratio_limits) && - knl_set_max_freq_ratio(&base_freq, &turbo_freq, 1)) - goto out; - - if (x86_match_cpu(has_skx_turbo_ratio_limits) && - skx_set_max_freq_ratio(&base_freq, &turbo_freq, 4)) - goto out; - - if (core_set_max_freq_ratio(&base_freq, &turbo_freq)) - goto out; - - return false; - -out: - /* - * Some hypervisors advertise X86_FEATURE_APERFMPERF - * but then fill all MSR's with zeroes. - * Some CPUs have turbo boost but don't declare any turbo ratio - * in MSR_TURBO_RATIO_LIMIT. - */ - if (!base_freq || !turbo_freq) { - pr_debug("Couldn't determine cpu base or turbo frequency, necessary for scale-invariant accounting.\n"); - return false; - } - - turbo_ratio = div_u64(turbo_freq * SCHED_CAPACITY_SCALE, base_freq); - if (!turbo_ratio) { - pr_debug("Non-zero turbo and base frequencies led to a 0 ratio.\n"); - return false; - } - - arch_turbo_freq_ratio = turbo_ratio; - arch_set_max_freq_ratio(turbo_disabled()); - - return true; -} - -static void init_counter_refs(void) -{ - u64 aperf, mperf; - - rdmsrl(MSR_IA32_APERF, aperf); - rdmsrl(MSR_IA32_MPERF, mperf); - - this_cpu_write(arch_prev_aperf, aperf); - this_cpu_write(arch_prev_mperf, mperf); -} - -#ifdef CONFIG_PM_SLEEP -static struct syscore_ops freq_invariance_syscore_ops = { - .resume = init_counter_refs, -}; - -static void register_freq_invariance_syscore_ops(void) -{ - /* Bail out if registered already. */ - if (freq_invariance_syscore_ops.node.prev) - return; - - register_syscore_ops(&freq_invariance_syscore_ops); -} -#else -static inline void register_freq_invariance_syscore_ops(void) {} -#endif - -void init_freq_invariance(bool secondary, bool cppc_ready) -{ - bool ret = false; - - if (!boot_cpu_has(X86_FEATURE_APERFMPERF)) - return; - - if (secondary) { - if (static_branch_likely(&arch_scale_freq_key)) { - init_counter_refs(); - } - return; - } - - if (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL) - ret = intel_set_max_freq_ratio(); - else if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD) { - if (!cppc_ready) { - return; - } - ret = amd_set_max_freq_ratio(&arch_turbo_freq_ratio); - } - - if (ret) { - init_counter_refs(); - static_branch_enable(&arch_scale_freq_key); - register_freq_invariance_syscore_ops(); - pr_info("Estimated ratio of average max frequency by base frequency (times 1024): %llu\n", arch_max_freq_ratio); - } else { - pr_debug("Couldn't determine max cpu frequency, necessary for scale-invariant accounting.\n"); - } -} - -static void disable_freq_invariance_workfn(struct work_struct *work) -{ - static_branch_disable(&arch_scale_freq_key); -} - -static DECLARE_WORK(disable_freq_invariance_work, - disable_freq_invariance_workfn); - -DEFINE_PER_CPU(unsigned long, arch_freq_scale) = SCHED_CAPACITY_SCALE; - -void arch_scale_freq_tick(void) -{ - u64 freq_scale; - u64 aperf, mperf; - u64 acnt, mcnt; - - if (!arch_scale_freq_invariant()) - return; - - rdmsrl(MSR_IA32_APERF, aperf); - rdmsrl(MSR_IA32_MPERF, mperf); - - acnt = aperf - this_cpu_read(arch_prev_aperf); - mcnt = mperf - this_cpu_read(arch_prev_mperf); - - this_cpu_write(arch_prev_aperf, aperf); - this_cpu_write(arch_prev_mperf, mperf); - - if (check_shl_overflow(acnt, 2*SCHED_CAPACITY_SHIFT, &acnt)) - goto error; - - if (check_mul_overflow(mcnt, arch_max_freq_ratio, &mcnt) || !mcnt) - goto error; - - freq_scale = div64_u64(acnt, mcnt); - if (!freq_scale) - goto error; - - if (freq_scale > SCHED_CAPACITY_SCALE) - freq_scale = SCHED_CAPACITY_SCALE; - - this_cpu_write(arch_freq_scale, freq_scale); - return; - -error: - pr_warn("Scheduler frequency invariance went wobbly, disabling!\n"); - schedule_work(&disable_freq_invariance_work); -} -#endif /* CONFIG_X86_64 */ diff --git a/arch/x86/kernel/sys_x86_64.c b/arch/x86/kernel/sys_x86_64.c index 660b78827638..8cc653ffdccd 100644 --- a/arch/x86/kernel/sys_x86_64.c +++ b/arch/x86/kernel/sys_x86_64.c @@ -68,9 +68,6 @@ static int __init control_va_addr_alignment(char *str) if (*str == 0) return 1; - if (*str == '=') - str++; - if (!strcmp(str, "32")) va_align.flags = ALIGN_VA_32; else if (!strcmp(str, "64")) @@ -80,11 +77,11 @@ static int __init control_va_addr_alignment(char *str) else if (!strcmp(str, "on")) va_align.flags = ALIGN_VA_32 | ALIGN_VA_64; else - return 0; + pr_warn("invalid option value: 'align_va_addr=%s'\n", str); return 1; } -__setup("align_va_addr", control_va_addr_alignment); +__setup("align_va_addr=", control_va_addr_alignment); SYSCALL_DEFINE6(mmap, unsigned long, addr, unsigned long, len, unsigned long, prot, unsigned long, flags, diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c index 1563fb995005..d62b2cb85cea 100644 --- a/arch/x86/kernel/traps.c +++ b/arch/x86/kernel/traps.c @@ -62,6 +62,7 @@ #include <asm/insn.h> #include <asm/insn-eval.h> #include <asm/vdso.h> +#include <asm/tdx.h> #ifdef CONFIG_X86_64 #include <asm/x86_init.h> @@ -686,13 +687,40 @@ static bool try_fixup_enqcmd_gp(void) #endif } +static bool gp_try_fixup_and_notify(struct pt_regs *regs, int trapnr, + unsigned long error_code, const char *str) +{ + if (fixup_exception(regs, trapnr, error_code, 0)) + return true; + + current->thread.error_code = error_code; + current->thread.trap_nr = trapnr; + + /* + * To be potentially processing a kprobe fault and to trust the result + * from kprobe_running(), we have to be non-preemptible. + */ + if (!preemptible() && kprobe_running() && + kprobe_fault_handler(regs, trapnr)) + return true; + + return notify_die(DIE_GPF, str, regs, error_code, trapnr, SIGSEGV) == NOTIFY_STOP; +} + +static void gp_user_force_sig_segv(struct pt_regs *regs, int trapnr, + unsigned long error_code, const char *str) +{ + current->thread.error_code = error_code; + current->thread.trap_nr = trapnr; + show_signal(current, SIGSEGV, "", str, regs, error_code); + force_sig(SIGSEGV); +} + DEFINE_IDTENTRY_ERRORCODE(exc_general_protection) { char desc[sizeof(GPFSTR) + 50 + 2*sizeof(unsigned long) + 1] = GPFSTR; enum kernel_gp_hint hint = GP_NO_HINT; - struct task_struct *tsk; unsigned long gp_addr; - int ret; if (user_mode(regs) && try_fixup_enqcmd_gp()) return; @@ -711,40 +739,18 @@ DEFINE_IDTENTRY_ERRORCODE(exc_general_protection) return; } - tsk = current; - if (user_mode(regs)) { if (fixup_iopl_exception(regs)) goto exit; - tsk->thread.error_code = error_code; - tsk->thread.trap_nr = X86_TRAP_GP; - if (fixup_vdso_exception(regs, X86_TRAP_GP, error_code, 0)) goto exit; - show_signal(tsk, SIGSEGV, "", desc, regs, error_code); - force_sig(SIGSEGV); + gp_user_force_sig_segv(regs, X86_TRAP_GP, error_code, desc); goto exit; } - if (fixup_exception(regs, X86_TRAP_GP, error_code, 0)) - goto exit; - - tsk->thread.error_code = error_code; - tsk->thread.trap_nr = X86_TRAP_GP; - - /* - * To be potentially processing a kprobe fault and to trust the result - * from kprobe_running(), we have to be non-preemptible. - */ - if (!preemptible() && - kprobe_running() && - kprobe_fault_handler(regs, X86_TRAP_GP)) - goto exit; - - ret = notify_die(DIE_GPF, desc, regs, error_code, X86_TRAP_GP, SIGSEGV); - if (ret == NOTIFY_STOP) + if (gp_try_fixup_and_notify(regs, X86_TRAP_GP, error_code, desc)) goto exit; if (error_code) @@ -892,14 +898,10 @@ sync: } #endif -struct bad_iret_stack { - void *error_entry_ret; - struct pt_regs regs; -}; - -asmlinkage __visible noinstr -struct bad_iret_stack *fixup_bad_iret(struct bad_iret_stack *s) +asmlinkage __visible noinstr struct pt_regs *fixup_bad_iret(struct pt_regs *bad_regs) { + struct pt_regs tmp, *new_stack; + /* * This is called from entry_64.S early in handling a fault * caused by a bad iret to user mode. To handle the fault @@ -908,19 +910,18 @@ struct bad_iret_stack *fixup_bad_iret(struct bad_iret_stack *s) * just below the IRET frame) and we want to pretend that the * exception came from the IRET target. */ - struct bad_iret_stack tmp, *new_stack = - (struct bad_iret_stack *)__this_cpu_read(cpu_tss_rw.x86_tss.sp0) - 1; + new_stack = (struct pt_regs *)__this_cpu_read(cpu_tss_rw.x86_tss.sp0) - 1; /* Copy the IRET target to the temporary storage. */ - __memcpy(&tmp.regs.ip, (void *)s->regs.sp, 5*8); + __memcpy(&tmp.ip, (void *)bad_regs->sp, 5*8); /* Copy the remainder of the stack from the current stack. */ - __memcpy(&tmp, s, offsetof(struct bad_iret_stack, regs.ip)); + __memcpy(&tmp, bad_regs, offsetof(struct pt_regs, ip)); /* Update the entry stack */ __memcpy(new_stack, &tmp, sizeof(tmp)); - BUG_ON(!user_mode(&new_stack->regs)); + BUG_ON(!user_mode(new_stack)); return new_stack; } #endif @@ -1343,6 +1344,91 @@ DEFINE_IDTENTRY(exc_device_not_available) } } +#ifdef CONFIG_INTEL_TDX_GUEST + +#define VE_FAULT_STR "VE fault" + +static void ve_raise_fault(struct pt_regs *regs, long error_code) +{ + if (user_mode(regs)) { + gp_user_force_sig_segv(regs, X86_TRAP_VE, error_code, VE_FAULT_STR); + return; + } + + if (gp_try_fixup_and_notify(regs, X86_TRAP_VE, error_code, VE_FAULT_STR)) + return; + + die_addr(VE_FAULT_STR, regs, error_code, 0); +} + +/* + * Virtualization Exceptions (#VE) are delivered to TDX guests due to + * specific guest actions which may happen in either user space or the + * kernel: + * + * * Specific instructions (WBINVD, for example) + * * Specific MSR accesses + * * Specific CPUID leaf accesses + * * Access to specific guest physical addresses + * + * In the settings that Linux will run in, virtualization exceptions are + * never generated on accesses to normal, TD-private memory that has been + * accepted (by BIOS or with tdx_enc_status_changed()). + * + * Syscall entry code has a critical window where the kernel stack is not + * yet set up. Any exception in this window leads to hard to debug issues + * and can be exploited for privilege escalation. Exceptions in the NMI + * entry code also cause issues. Returning from the exception handler with + * IRET will re-enable NMIs and nested NMI will corrupt the NMI stack. + * + * For these reasons, the kernel avoids #VEs during the syscall gap and + * the NMI entry code. Entry code paths do not access TD-shared memory, + * MMIO regions, use #VE triggering MSRs, instructions, or CPUID leaves + * that might generate #VE. VMM can remove memory from TD at any point, + * but access to unaccepted (or missing) private memory leads to VM + * termination, not to #VE. + * + * Similarly to page faults and breakpoints, #VEs are allowed in NMI + * handlers once the kernel is ready to deal with nested NMIs. + * + * During #VE delivery, all interrupts, including NMIs, are blocked until + * TDGETVEINFO is called. It prevents #VE nesting until the kernel reads + * the VE info. + * + * If a guest kernel action which would normally cause a #VE occurs in + * the interrupt-disabled region before TDGETVEINFO, a #DF (fault + * exception) is delivered to the guest which will result in an oops. + * + * The entry code has been audited carefully for following these expectations. + * Changes in the entry code have to be audited for correctness vs. this + * aspect. Similarly to #PF, #VE in these places will expose kernel to + * privilege escalation or may lead to random crashes. + */ +DEFINE_IDTENTRY(exc_virtualization_exception) +{ + struct ve_info ve; + + /* + * NMIs/Machine-checks/Interrupts will be in a disabled state + * till TDGETVEINFO TDCALL is executed. This ensures that VE + * info cannot be overwritten by a nested #VE. + */ + tdx_get_ve_info(&ve); + + cond_local_irq_enable(regs); + + /* + * If tdx_handle_virt_exception() could not process + * it successfully, treat it as #GP(0) and handle it. + */ + if (!tdx_handle_virt_exception(regs, &ve)) + ve_raise_fault(regs, 0); + + cond_local_irq_disable(regs); +} + +#endif + #ifdef CONFIG_X86_32 DEFINE_IDTENTRY_SW(iret_error) { diff --git a/arch/x86/kernel/vm86_32.c b/arch/x86/kernel/vm86_32.c index c21bcd668284..e9e803a4d44c 100644 --- a/arch/x86/kernel/vm86_32.c +++ b/arch/x86/kernel/vm86_32.c @@ -151,7 +151,7 @@ exit_vm86: memcpy(®s->pt, &vm86->regs32, sizeof(struct pt_regs)); - lazy_load_gs(vm86->regs32.gs); + loadsegment(gs, vm86->regs32.gs); regs->pt.ax = retval; return; @@ -325,7 +325,7 @@ static long do_sys_vm86(struct vm86plus_struct __user *user_vm86, bool plus) * Save old state */ vm86->saved_sp0 = tsk->thread.sp0; - lazy_save_gs(vm86->regs32.gs); + savesegment(gs, vm86->regs32.gs); /* make room for real-mode segments */ preempt_disable(); diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index 0c1ba6aa0765..de6d44e07e34 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -19,6 +19,7 @@ #include <asm/user.h> #include <asm/fpu/xstate.h> #include <asm/sgx.h> +#include <asm/cpuid.h> #include "cpuid.h" #include "lapic.h" #include "mmu.h" @@ -744,24 +745,8 @@ static struct kvm_cpuid_entry2 *do_host_cpuid(struct kvm_cpuid_array *array, cpuid_count(entry->function, entry->index, &entry->eax, &entry->ebx, &entry->ecx, &entry->edx); - switch (function) { - case 4: - case 7: - case 0xb: - case 0xd: - case 0xf: - case 0x10: - case 0x12: - case 0x14: - case 0x17: - case 0x18: - case 0x1d: - case 0x1e: - case 0x1f: - case 0x8000001d: + if (cpuid_function_is_indexed(function)) entry->flags |= KVM_CPUID_FLAG_SIGNIFCANT_INDEX; - break; - } return entry; } diff --git a/arch/x86/kvm/hyperv.c b/arch/x86/kvm/hyperv.c index 46f9dfb60469..a0702b6be3e8 100644 --- a/arch/x86/kvm/hyperv.c +++ b/arch/x86/kvm/hyperv.c @@ -1914,7 +1914,7 @@ static u64 kvm_hv_send_ipi(struct kvm_vcpu *vcpu, struct kvm_hv_hcall *hc) struct hv_send_ipi_ex send_ipi_ex; struct hv_send_ipi send_ipi; DECLARE_BITMAP(vcpu_mask, KVM_MAX_VCPUS); - unsigned long valid_bank_mask; + u64 valid_bank_mask; u64 sparse_banks[KVM_HV_MAX_SPARSE_VCPU_SET_BITS]; u32 vector; bool all_cpus; @@ -1956,7 +1956,7 @@ static u64 kvm_hv_send_ipi(struct kvm_vcpu *vcpu, struct kvm_hv_hcall *hc) valid_bank_mask = send_ipi_ex.vp_set.valid_bank_mask; all_cpus = send_ipi_ex.vp_set.format == HV_GENERIC_SET_ALL; - if (hc->var_cnt != bitmap_weight(&valid_bank_mask, 64)) + if (hc->var_cnt != bitmap_weight((unsigned long *)&valid_bank_mask, 64)) return HV_STATUS_INVALID_HYPERCALL_INPUT; if (all_cpus) diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index 311e4e1d7870..45e1573f8f1d 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -5470,14 +5470,16 @@ void kvm_mmu_invpcid_gva(struct kvm_vcpu *vcpu, gva_t gva, unsigned long pcid) uint i; if (pcid == kvm_get_active_pcid(vcpu)) { - mmu->invlpg(vcpu, gva, mmu->root.hpa); + if (mmu->invlpg) + mmu->invlpg(vcpu, gva, mmu->root.hpa); tlb_flush = true; } for (i = 0; i < KVM_MMU_NUM_PREV_ROOTS; i++) { if (VALID_PAGE(mmu->prev_roots[i].hpa) && pcid == kvm_get_pcid(vcpu, mmu->prev_roots[i].pgd)) { - mmu->invlpg(vcpu, gva, mmu->prev_roots[i].hpa); + if (mmu->invlpg) + mmu->invlpg(vcpu, gva, mmu->prev_roots[i].hpa); tlb_flush = true; } } @@ -5665,6 +5667,7 @@ static void kvm_zap_obsolete_pages(struct kvm *kvm) { struct kvm_mmu_page *sp, *node; int nr_zapped, batch = 0; + bool unstable; restart: list_for_each_entry_safe_reverse(sp, node, @@ -5696,11 +5699,12 @@ restart: goto restart; } - if (__kvm_mmu_prepare_zap_page(kvm, sp, - &kvm->arch.zapped_obsolete_pages, &nr_zapped)) { - batch += nr_zapped; + unstable = __kvm_mmu_prepare_zap_page(kvm, sp, + &kvm->arch.zapped_obsolete_pages, &nr_zapped); + batch += nr_zapped; + + if (unstable) goto restart; - } } /* diff --git a/arch/x86/kvm/pmu.c b/arch/x86/kvm/pmu.c index eca39f56c231..0604bc29f0b8 100644 --- a/arch/x86/kvm/pmu.c +++ b/arch/x86/kvm/pmu.c @@ -171,9 +171,12 @@ static bool pmc_resume_counter(struct kvm_pmc *pmc) return true; } -static int cmp_u64(const void *a, const void *b) +static int cmp_u64(const void *pa, const void *pb) { - return *(__u64 *)a - *(__u64 *)b; + u64 a = *(u64 *)pa; + u64 b = *(u64 *)pb; + + return (a > b) - (a < b); } void reprogram_gp_counter(struct kvm_pmc *pmc, u64 eventsel) diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c index 7c392873626f..636c77ef55fc 100644 --- a/arch/x86/kvm/svm/sev.c +++ b/arch/x86/kvm/svm/sev.c @@ -562,12 +562,20 @@ e_unpin: static int sev_es_sync_vmsa(struct vcpu_svm *svm) { - struct vmcb_save_area *save = &svm->vmcb->save; + struct sev_es_save_area *save = svm->sev_es.vmsa; /* Check some debug related fields before encrypting the VMSA */ - if (svm->vcpu.guest_debug || (save->dr7 & ~DR7_FIXED_1)) + if (svm->vcpu.guest_debug || (svm->vmcb->save.dr7 & ~DR7_FIXED_1)) return -EINVAL; + /* + * SEV-ES will use a VMSA that is pointed to by the VMCB, not + * the traditional VMSA that is part of the VMCB. Copy the + * traditional VMSA as it has been built so far (in prep + * for LAUNCH_UPDATE_VMSA) to be the initial SEV-ES state. + */ + memcpy(save, &svm->vmcb->save, sizeof(svm->vmcb->save)); + /* Sync registgers */ save->rax = svm->vcpu.arch.regs[VCPU_REGS_RAX]; save->rbx = svm->vcpu.arch.regs[VCPU_REGS_RBX]; @@ -595,14 +603,6 @@ static int sev_es_sync_vmsa(struct vcpu_svm *svm) save->xss = svm->vcpu.arch.ia32_xss; save->dr6 = svm->vcpu.arch.dr6; - /* - * SEV-ES will use a VMSA that is pointed to by the VMCB, not - * the traditional VMSA that is part of the VMCB. Copy the - * traditional VMSA as it has been built so far (in prep - * for LAUNCH_UPDATE_VMSA) to be the initial SEV-ES state. - */ - memcpy(svm->sev_es.vmsa, save, sizeof(*save)); - return 0; } @@ -2966,7 +2966,7 @@ void sev_es_vcpu_reset(struct vcpu_svm *svm) sev_enc_bit)); } -void sev_es_prepare_switch_to_guest(struct vmcb_save_area *hostsa) +void sev_es_prepare_switch_to_guest(struct sev_es_save_area *hostsa) { /* * As an SEV-ES guest, hardware will restore the host state on VMEXIT, diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index 7e45d03cd018..17d334ef5430 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -1270,8 +1270,8 @@ static void svm_prepare_switch_to_guest(struct kvm_vcpu *vcpu) */ vmsave(__sme_page_pa(sd->save_area)); if (sev_es_guest(vcpu->kvm)) { - struct vmcb_save_area *hostsa; - hostsa = (struct vmcb_save_area *)(page_address(sd->save_area) + 0x400); + struct sev_es_save_area *hostsa; + hostsa = (struct sev_es_save_area *)(page_address(sd->save_area) + 0x400); sev_es_prepare_switch_to_guest(hostsa); } @@ -3117,8 +3117,8 @@ static void dump_vmcb(struct kvm_vcpu *vcpu) "tr:", save01->tr.selector, save01->tr.attrib, save01->tr.limit, save01->tr.base); - pr_err("cpl: %d efer: %016llx\n", - save->cpl, save->efer); + pr_err("vmpl: %d cpl: %d efer: %016llx\n", + save->vmpl, save->cpl, save->efer); pr_err("%-15s %016llx %-13s %016llx\n", "cr0:", save->cr0, "cr2:", save->cr2); pr_err("%-15s %016llx %-13s %016llx\n", diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h index f76deff71002..2d83845b9032 100644 --- a/arch/x86/kvm/svm/svm.h +++ b/arch/x86/kvm/svm/svm.h @@ -181,7 +181,7 @@ struct svm_nested_state { struct vcpu_sev_es_state { /* SEV-ES support */ - struct vmcb_save_area *vmsa; + struct sev_es_save_area *vmsa; struct ghcb *ghcb; struct kvm_host_map ghcb_map; bool received_first_sipi; @@ -622,7 +622,7 @@ int sev_es_string_io(struct vcpu_svm *svm, int size, unsigned int port, int in); void sev_es_init_vmcb(struct vcpu_svm *svm); void sev_es_vcpu_reset(struct vcpu_svm *svm); void sev_vcpu_deliver_sipi_vector(struct kvm_vcpu *vcpu, u8 vector); -void sev_es_prepare_switch_to_guest(struct vmcb_save_area *hostsa); +void sev_es_prepare_switch_to_guest(struct sev_es_save_area *hostsa); void sev_es_unmap_ghcb(struct vcpu_svm *svm); /* vmenter.S */ diff --git a/arch/x86/lib/delay.c b/arch/x86/lib/delay.c index 65d15df6212d..0e65d00e2339 100644 --- a/arch/x86/lib/delay.c +++ b/arch/x86/lib/delay.c @@ -54,8 +54,8 @@ static void delay_loop(u64 __loops) " jnz 2b \n" "3: dec %0 \n" - : /* we don't need output */ - :"a" (loops) + : "+a" (loops) + : ); } diff --git a/arch/x86/lib/insn-eval.c b/arch/x86/lib/insn-eval.c index b781d324211b..21104c41cba0 100644 --- a/arch/x86/lib/insn-eval.c +++ b/arch/x86/lib/insn-eval.c @@ -342,9 +342,9 @@ static int resolve_seg_reg(struct insn *insn, struct pt_regs *regs, int regoff) */ static short get_segment_selector(struct pt_regs *regs, int seg_reg_idx) { -#ifdef CONFIG_X86_64 unsigned short sel; +#ifdef CONFIG_X86_64 switch (seg_reg_idx) { case INAT_SEG_REG_IGNORE: return 0; @@ -402,7 +402,8 @@ static short get_segment_selector(struct pt_regs *regs, int seg_reg_idx) case INAT_SEG_REG_FS: return (unsigned short)(regs->fs & 0xffff); case INAT_SEG_REG_GS: - return get_user_gs(regs); + savesegment(gs, sel); + return sel; case INAT_SEG_REG_IGNORE: default: return -EINVAL; diff --git a/arch/x86/lib/kaslr.c b/arch/x86/lib/kaslr.c index 2b3eb8c948a3..a58f451a7dd3 100644 --- a/arch/x86/lib/kaslr.c +++ b/arch/x86/lib/kaslr.c @@ -11,7 +11,7 @@ #include <asm/msr.h> #include <asm/archrandom.h> #include <asm/e820/api.h> -#include <asm/io.h> +#include <asm/shared/io.h> /* * When built for the regular kernel, several functions need to be stubbed out diff --git a/arch/x86/lib/mmx_32.c b/arch/x86/lib/mmx_32.c deleted file mode 100644 index e69de29bb2d1..000000000000 --- a/arch/x86/lib/mmx_32.c +++ /dev/null diff --git a/arch/x86/math-emu/get_address.c b/arch/x86/math-emu/get_address.c index b82ca14ba718..4a9fd9029a53 100644 --- a/arch/x86/math-emu/get_address.c +++ b/arch/x86/math-emu/get_address.c @@ -153,7 +153,7 @@ static long pm_address(u_char FPU_modrm, u_char segment, switch (segment) { case PREFIX_GS_ - 1: /* user gs handling can be lazy, use special accessors */ - addr->selector = get_user_gs(FPU_info->regs); + savesegment(gs, addr->selector); break; default: addr->selector = PM_REG_(segment); diff --git a/arch/x86/mm/Makefile b/arch/x86/mm/Makefile index fe3d3061fc11..d957dc15b371 100644 --- a/arch/x86/mm/Makefile +++ b/arch/x86/mm/Makefile @@ -20,13 +20,12 @@ CFLAGS_REMOVE_mem_encrypt_identity.o = -pg endif obj-y := init.o init_$(BITS).o fault.o ioremap.o extable.o mmap.o \ - pgtable.o physaddr.o setup_nx.o tlb.o cpu_entry_area.o maccess.o + pgtable.o physaddr.o tlb.o cpu_entry_area.o maccess.o obj-y += pat/ # Make sure __phys_addr has no stackprotector CFLAGS_physaddr.o := -fno-stack-protector -CFLAGS_setup_nx.o := -fno-stack-protector CFLAGS_mem_encrypt_identity.o := -fno-stack-protector CFLAGS_fault.o := -I $(srctree)/$(src)/../include/asm/trace diff --git a/arch/x86/mm/amdtopology.c b/arch/x86/mm/amdtopology.c index 058b2f36b3a6..b3ca7d23e4b0 100644 --- a/arch/x86/mm/amdtopology.c +++ b/arch/x86/mm/amdtopology.c @@ -154,7 +154,7 @@ int __init amd_numa_init(void) node_set(nodeid, numa_nodes_parsed); } - if (!nodes_weight(numa_nodes_parsed)) + if (nodes_empty(numa_nodes_parsed)) return -ENOENT; /* diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c index d0074c6ed31a..fad8faa29d04 100644 --- a/arch/x86/mm/fault.c +++ b/arch/x86/mm/fault.c @@ -149,7 +149,7 @@ is_prefetch(struct pt_regs *regs, unsigned long error_code, unsigned long addr) unsigned char opcode; if (user_mode(regs)) { - if (get_user(opcode, instr)) + if (get_user(opcode, (unsigned char __user *) instr)) break; } else { if (get_kernel_nofault(opcode, instr)) diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c index 96d34ebb20a9..61d0ab154f96 100644 --- a/arch/x86/mm/init_64.c +++ b/arch/x86/mm/init_64.c @@ -110,7 +110,6 @@ int force_personality32; /* * noexec32=on|off * Control non executable heap for 32bit processes. - * To control the stack too use noexec=off * * on PROT_READ does not imply PROT_EXEC for 32-bit processes (default) * off PROT_READ implies PROT_EXEC @@ -902,6 +901,8 @@ static void __meminit vmemmap_use_sub_pmd(unsigned long start, unsigned long end static void __meminit vmemmap_use_new_sub_pmd(unsigned long start, unsigned long end) { + const unsigned long page = ALIGN_DOWN(start, PMD_SIZE); + vmemmap_flush_unused_pmd(); /* @@ -914,8 +915,7 @@ static void __meminit vmemmap_use_new_sub_pmd(unsigned long start, unsigned long * Mark with PAGE_UNUSED the unused parts of the new memmap range */ if (!IS_ALIGNED(start, PMD_SIZE)) - memset((void *)start, PAGE_UNUSED, - start - ALIGN_DOWN(start, PMD_SIZE)); + memset((void *)page, PAGE_UNUSED, start - page); /* * We want to avoid memset(PAGE_UNUSED) when populating the vmemmap of diff --git a/arch/x86/mm/ioremap.c b/arch/x86/mm/ioremap.c index 17a492c27306..1ad0228f8ceb 100644 --- a/arch/x86/mm/ioremap.c +++ b/arch/x86/mm/ioremap.c @@ -242,10 +242,15 @@ __ioremap_caller(resource_size_t phys_addr, unsigned long size, * If the page being mapped is in memory and SEV is active then * make sure the memory encryption attribute is enabled in the * resulting mapping. + * In TDX guests, memory is marked private by default. If encryption + * is not requested (using encrypted), explicitly set decrypt + * attribute in all IOREMAPPED memory. */ prot = PAGE_KERNEL_IO; if ((io_desc.flags & IORES_MAP_ENCRYPTED) || encrypted) prot = pgprot_encrypted(prot); + else + prot = pgprot_decrypted(prot); switch (pcm) { case _PAGE_CACHE_MODE_UC: diff --git a/arch/x86/mm/mem_encrypt.c b/arch/x86/mm/mem_encrypt.c index 50d209939c66..11350e2fd736 100644 --- a/arch/x86/mm/mem_encrypt.c +++ b/arch/x86/mm/mem_encrypt.c @@ -42,7 +42,14 @@ bool force_dma_unencrypted(struct device *dev) static void print_mem_encrypt_feature_info(void) { - pr_info("AMD Memory Encryption Features active:"); + pr_info("Memory Encryption Features active:"); + + if (cpu_feature_enabled(X86_FEATURE_TDX_GUEST)) { + pr_cont(" Intel TDX\n"); + return; + } + + pr_cont(" AMD"); /* Secure Memory Encryption */ if (cc_platform_has(CC_ATTR_HOST_MEM_ENCRYPT)) { @@ -62,6 +69,10 @@ static void print_mem_encrypt_feature_info(void) if (cc_platform_has(CC_ATTR_GUEST_STATE_ENCRYPT)) pr_cont(" SEV-ES"); + /* Secure Nested Paging */ + if (cc_platform_has(CC_ATTR_GUEST_SEV_SNP)) + pr_cont(" SEV-SNP"); + pr_cont("\n"); } diff --git a/arch/x86/mm/mem_encrypt_amd.c b/arch/x86/mm/mem_encrypt_amd.c index 6169053c2854..d3c88d9ef8d6 100644 --- a/arch/x86/mm/mem_encrypt_amd.c +++ b/arch/x86/mm/mem_encrypt_amd.c @@ -31,6 +31,7 @@ #include <asm/processor-flags.h> #include <asm/msr.h> #include <asm/cmdline.h> +#include <asm/sev.h> #include "mm_internal.h" @@ -48,6 +49,36 @@ EXPORT_SYMBOL(sme_me_mask); static char sme_early_buffer[PAGE_SIZE] __initdata __aligned(PAGE_SIZE); /* + * SNP-specific routine which needs to additionally change the page state from + * private to shared before copying the data from the source to destination and + * restore after the copy. + */ +static inline void __init snp_memcpy(void *dst, void *src, size_t sz, + unsigned long paddr, bool decrypt) +{ + unsigned long npages = PAGE_ALIGN(sz) >> PAGE_SHIFT; + + if (decrypt) { + /* + * @paddr needs to be accessed decrypted, mark the page shared in + * the RMP table before copying it. + */ + early_snp_set_memory_shared((unsigned long)__va(paddr), paddr, npages); + + memcpy(dst, src, sz); + + /* Restore the page state after the memcpy. */ + early_snp_set_memory_private((unsigned long)__va(paddr), paddr, npages); + } else { + /* + * @paddr need to be accessed encrypted, no need for the page state + * change. + */ + memcpy(dst, src, sz); + } +} + +/* * This routine does not change the underlying encryption setting of the * page(s) that map this memory. It assumes that eventually the memory is * meant to be accessed as either encrypted or decrypted but the contents @@ -95,8 +126,13 @@ static void __init __sme_early_enc_dec(resource_size_t paddr, * Use a temporary buffer, of cache-line multiple size, to * avoid data corruption as documented in the APM. */ - memcpy(sme_early_buffer, src, len); - memcpy(dst, sme_early_buffer, len); + if (cc_platform_has(CC_ATTR_GUEST_SEV_SNP)) { + snp_memcpy(sme_early_buffer, src, len, paddr, enc); + snp_memcpy(dst, sme_early_buffer, len, paddr, !enc); + } else { + memcpy(sme_early_buffer, src, len); + memcpy(dst, sme_early_buffer, len); + } early_memunmap(dst, len); early_memunmap(src, len); @@ -280,11 +316,24 @@ static void enc_dec_hypercall(unsigned long vaddr, int npages, bool enc) static void amd_enc_status_change_prepare(unsigned long vaddr, int npages, bool enc) { + /* + * To maintain the security guarantees of SEV-SNP guests, make sure + * to invalidate the memory before encryption attribute is cleared. + */ + if (cc_platform_has(CC_ATTR_GUEST_SEV_SNP) && !enc) + snp_set_memory_shared(vaddr, npages); } /* Return true unconditionally: return value doesn't matter for the SEV side */ static bool amd_enc_status_change_finish(unsigned long vaddr, int npages, bool enc) { + /* + * After memory is mapped encrypted in the page table, validate it + * so that it is consistent with the page table updates. + */ + if (cc_platform_has(CC_ATTR_GUEST_SEV_SNP) && enc) + snp_set_memory_private(vaddr, npages); + if (!cc_platform_has(CC_ATTR_HOST_MEM_ENCRYPT)) enc_dec_hypercall(vaddr, npages, enc); @@ -322,14 +371,28 @@ static void __init __set_clr_pte_enc(pte_t *kpte, int level, bool enc) clflush_cache_range(__va(pa), size); /* Encrypt/decrypt the contents in-place */ - if (enc) + if (enc) { sme_early_encrypt(pa, size); - else + } else { sme_early_decrypt(pa, size); + /* + * ON SNP, the page state in the RMP table must happen + * before the page table updates. + */ + early_snp_set_memory_shared((unsigned long)__va(pa), pa, 1); + } + /* Change the page encryption mask. */ new_pte = pfn_pte(pfn, new_prot); set_pte_atomic(kpte, new_pte); + + /* + * If page is set encrypted in the page table, then update the RMP table to + * add this page as private. + */ + if (enc) + early_snp_set_memory_private((unsigned long)__va(pa), pa, 1); } static int __init early_set_memory_enc_dec(unsigned long vaddr, diff --git a/arch/x86/mm/mem_encrypt_identity.c b/arch/x86/mm/mem_encrypt_identity.c index b43bc24d2bb6..f415498d3175 100644 --- a/arch/x86/mm/mem_encrypt_identity.c +++ b/arch/x86/mm/mem_encrypt_identity.c @@ -45,6 +45,7 @@ #include <asm/sections.h> #include <asm/cmdline.h> #include <asm/coco.h> +#include <asm/sev.h> #include "mm_internal.h" @@ -509,8 +510,11 @@ void __init sme_enable(struct boot_params *bp) bool active_by_default; unsigned long me_mask; char buffer[16]; + bool snp; u64 msr; + snp = snp_init(bp); + /* Check for the SME/SEV support leaf */ eax = 0x80000000; ecx = 0; @@ -542,6 +546,10 @@ void __init sme_enable(struct boot_params *bp) sev_status = __rdmsr(MSR_AMD64_SEV); feature_mask = (sev_status & MSR_AMD64_SEV_ENABLED) ? AMD_SEV_BIT : AMD_SME_BIT; + /* The SEV-SNP CC blob should never be present unless SEV-SNP is enabled. */ + if (snp && !(sev_status & MSR_AMD64_SEV_SNP_ENABLED)) + snp_abort(); + /* Check if memory encryption is enabled */ if (feature_mask == AMD_SME_BIT) { /* diff --git a/arch/x86/mm/mmio-mod.c b/arch/x86/mm/mmio-mod.c index 933a2ebad471..c3317f0650d8 100644 --- a/arch/x86/mm/mmio-mod.c +++ b/arch/x86/mm/mmio-mod.c @@ -400,7 +400,7 @@ static void leave_uniprocessor(void) int cpu; int err; - if (!cpumask_available(downed_cpus) || cpumask_weight(downed_cpus) == 0) + if (!cpumask_available(downed_cpus) || cpumask_empty(downed_cpus)) return; pr_notice("Re-enabling CPUs...\n"); for_each_cpu(cpu, downed_cpus) { diff --git a/arch/x86/mm/numa_emulation.c b/arch/x86/mm/numa_emulation.c index 1a02b791d273..9a9305367fdd 100644 --- a/arch/x86/mm/numa_emulation.c +++ b/arch/x86/mm/numa_emulation.c @@ -123,7 +123,7 @@ static int __init split_nodes_interleave(struct numa_meminfo *ei, * Continue to fill physical nodes with fake nodes until there is no * memory left on any of them. */ - while (nodes_weight(physnode_mask)) { + while (!nodes_empty(physnode_mask)) { for_each_node_mask(i, physnode_mask) { u64 dma32_end = PFN_PHYS(MAX_DMA32_PFN); u64 start, limit, end; @@ -270,7 +270,7 @@ static int __init split_nodes_size_interleave_uniform(struct numa_meminfo *ei, * Fill physical nodes with fake nodes of size until there is no memory * left on any of them. */ - while (nodes_weight(physnode_mask)) { + while (!nodes_empty(physnode_mask)) { for_each_node_mask(i, physnode_mask) { u64 dma32_end = PFN_PHYS(MAX_DMA32_PFN); u64 start, limit, end; diff --git a/arch/x86/mm/pat/memtype.c b/arch/x86/mm/pat/memtype.c index 4ba2a3ee4bce..d5ef64ddd35e 100644 --- a/arch/x86/mm/pat/memtype.c +++ b/arch/x86/mm/pat/memtype.c @@ -101,7 +101,7 @@ int pat_debug_enable; static int __init pat_debug_setup(char *str) { pat_debug_enable = 1; - return 0; + return 1; } __setup("debugpat", pat_debug_setup); diff --git a/arch/x86/mm/setup_nx.c b/arch/x86/mm/setup_nx.c deleted file mode 100644 index ed5667f5169f..000000000000 --- a/arch/x86/mm/setup_nx.c +++ /dev/null @@ -1,62 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -#include <linux/spinlock.h> -#include <linux/errno.h> -#include <linux/init.h> -#include <linux/pgtable.h> - -#include <asm/proto.h> -#include <asm/cpufeature.h> - -static int disable_nx; - -/* - * noexec = on|off - * - * Control non-executable mappings for processes. - * - * on Enable - * off Disable - */ -static int __init noexec_setup(char *str) -{ - if (!str) - return -EINVAL; - if (!strncmp(str, "on", 2)) { - disable_nx = 0; - } else if (!strncmp(str, "off", 3)) { - disable_nx = 1; - } - x86_configure_nx(); - return 0; -} -early_param("noexec", noexec_setup); - -void x86_configure_nx(void) -{ - if (boot_cpu_has(X86_FEATURE_NX) && !disable_nx) - __supported_pte_mask |= _PAGE_NX; - else - __supported_pte_mask &= ~_PAGE_NX; -} - -void __init x86_report_nx(void) -{ - if (!boot_cpu_has(X86_FEATURE_NX)) { - printk(KERN_NOTICE "Notice: NX (Execute Disable) protection " - "missing in CPU!\n"); - } else { -#if defined(CONFIG_X86_64) || defined(CONFIG_X86_PAE) - if (disable_nx) { - printk(KERN_INFO "NX (Execute Disable) protection: " - "disabled by kernel command line option\n"); - } else { - printk(KERN_INFO "NX (Execute Disable) protection: " - "active\n"); - } -#else - /* 32bit non-PAE kernel, NX cannot be used */ - printk(KERN_NOTICE "Notice: NX (Execute Disable) protection " - "cannot be enabled: non-PAE kernel!\n"); -#endif - } -} diff --git a/arch/x86/pci/irq.c b/arch/x86/pci/irq.c index 97b63e35e152..a498b847d740 100644 --- a/arch/x86/pci/irq.c +++ b/arch/x86/pci/irq.c @@ -25,6 +25,8 @@ #define PIRQ_SIGNATURE (('$' << 0) + ('P' << 8) + ('I' << 16) + ('R' << 24)) #define PIRQ_VERSION 0x0100 +#define IRT_SIGNATURE (('$' << 0) + ('I' << 8) + ('R' << 16) + ('T' << 24)) + static int broken_hp_bios_irq9; static int acer_tm360_irqrouting; @@ -68,30 +70,99 @@ void (*pcibios_disable_irq)(struct pci_dev *dev) = pirq_disable_irq; * and perform checksum verification. */ -static inline struct irq_routing_table *pirq_check_routing_table(u8 *addr) +static inline struct irq_routing_table *pirq_check_routing_table(u8 *addr, + u8 *limit) { struct irq_routing_table *rt; int i; u8 sum; - rt = (struct irq_routing_table *) addr; + rt = (struct irq_routing_table *)addr; if (rt->signature != PIRQ_SIGNATURE || rt->version != PIRQ_VERSION || rt->size % 16 || - rt->size < sizeof(struct irq_routing_table)) + rt->size < sizeof(struct irq_routing_table) || + (limit && rt->size > limit - addr)) return NULL; sum = 0; for (i = 0; i < rt->size; i++) sum += addr[i]; if (!sum) { - DBG(KERN_DEBUG "PCI: Interrupt Routing Table found at 0x%p\n", - rt); + DBG(KERN_DEBUG "PCI: Interrupt Routing Table found at 0x%lx\n", + __pa(rt)); return rt; } return NULL; } +/* + * Handle the $IRT PCI IRQ Routing Table format used by AMI for its BCP + * (BIOS Configuration Program) external tool meant for tweaking BIOS + * structures without the need to rebuild it from sources. The $IRT + * format has been invented by AMI before Microsoft has come up with its + * $PIR format and a $IRT table is therefore there in some systems that + * lack a $PIR table. + * + * It uses the same PCI BIOS 2.1 format for interrupt routing entries + * themselves but has a different simpler header prepended instead, + * occupying 8 bytes, where a `$IRT' signature is followed by one byte + * specifying the total number of interrupt routing entries allocated in + * the table, then one byte specifying the actual number of entries used + * (which the BCP tool can take advantage of when modifying the table), + * and finally a 16-bit word giving the IRQs devoted exclusively to PCI. + * Unlike with the $PIR table there is no alignment guarantee. + * + * Given the similarity of the two formats the $IRT one is trivial to + * convert to the $PIR one, which we do here, except that obviously we + * have no information as to the router device to use, but we can handle + * it by matching PCI device IDs actually seen on the bus against ones + * that our individual routers recognise. + * + * Reportedly there is another $IRT table format where a 16-bit word + * follows the header instead that points to interrupt routing entries + * in a $PIR table provided elsewhere. In that case this code will not + * be reached though as the $PIR table will have been chosen instead. + */ +static inline struct irq_routing_table *pirq_convert_irt_table(u8 *addr, + u8 *limit) +{ + struct irt_routing_table *ir; + struct irq_routing_table *rt; + u16 size; + u8 sum; + int i; + + ir = (struct irt_routing_table *)addr; + if (ir->signature != IRT_SIGNATURE || !ir->used || ir->size < ir->used) + return NULL; + + size = sizeof(*ir) + ir->used * sizeof(ir->slots[0]); + if (size > limit - addr) + return NULL; + + DBG(KERN_DEBUG "PCI: $IRT Interrupt Routing Table found at 0x%lx\n", + __pa(ir)); + size = sizeof(*rt) + ir->used * sizeof(rt->slots[0]); + rt = kzalloc(size, GFP_KERNEL); + if (!rt) + return NULL; + + rt->signature = PIRQ_SIGNATURE; + rt->version = PIRQ_VERSION; + rt->size = size; + rt->exclusive_irqs = ir->exclusive_irqs; + for (i = 0; i < ir->used; i++) + rt->slots[i] = ir->slots[i]; + + addr = (u8 *)rt; + sum = 0; + for (i = 0; i < size; i++) + sum += addr[i]; + rt->checksum = -sum; + + return rt; +} /* * Search 0xf0000 -- 0xfffff for the PCI IRQ Routing Table. @@ -99,17 +170,29 @@ static inline struct irq_routing_table *pirq_check_routing_table(u8 *addr) static struct irq_routing_table * __init pirq_find_routing_table(void) { + u8 * const bios_start = (u8 *)__va(0xf0000); + u8 * const bios_end = (u8 *)__va(0x100000); u8 *addr; struct irq_routing_table *rt; if (pirq_table_addr) { - rt = pirq_check_routing_table((u8 *) __va(pirq_table_addr)); + rt = pirq_check_routing_table((u8 *)__va(pirq_table_addr), + NULL); if (rt) return rt; printk(KERN_WARNING "PCI: PIRQ table NOT found at pirqaddr\n"); } - for (addr = (u8 *) __va(0xf0000); addr < (u8 *) __va(0x100000); addr += 16) { - rt = pirq_check_routing_table(addr); + for (addr = bios_start; + addr < bios_end - sizeof(struct irq_routing_table); + addr += 16) { + rt = pirq_check_routing_table(addr, bios_end); + if (rt) + return rt; + } + for (addr = bios_start; + addr < bios_end - sizeof(struct irt_routing_table); + addr++) { + rt = pirq_convert_irt_table(addr, bios_end); if (rt) return rt; } @@ -135,7 +218,8 @@ static void __init pirq_peer_trick(void) #ifdef DEBUG { int j; - DBG(KERN_DEBUG "%02x:%02x slot=%02x", e->bus, e->devfn/8, e->slot); + DBG(KERN_DEBUG "%02x:%02x.%x slot=%02x", + e->bus, e->devfn / 8, e->devfn % 8, e->slot); for (j = 0; j < 4; j++) DBG(" %d:%02x/%04x", j, e->irq[j].link, e->irq[j].bitmap); DBG("\n"); @@ -253,6 +337,15 @@ static void write_pc_conf_nybble(u8 base, u8 index, u8 val) pc_conf_set(reg, x); } +/* + * FinALi pirq rules are as follows: + * + * - bit 0 selects between INTx Routing Table Mapping Registers, + * + * - bit 3 selects the nibble within the INTx Routing Table Mapping Register, + * + * - bits 7:4 map to bits 3:0 of the PCI INTx Sensitivity Register. + */ static int pirq_finali_get(struct pci_dev *router, struct pci_dev *dev, int pirq) { @@ -260,11 +353,13 @@ static int pirq_finali_get(struct pci_dev *router, struct pci_dev *dev, 0, 9, 3, 10, 4, 5, 7, 6, 0, 11, 0, 12, 0, 14, 0, 15 }; unsigned long flags; + u8 index; u8 x; + index = (pirq & 1) << 1 | (pirq & 8) >> 3; raw_spin_lock_irqsave(&pc_conf_lock, flags); pc_conf_set(PC_CONF_FINALI_LOCK, PC_CONF_FINALI_LOCK_KEY); - x = irqmap[read_pc_conf_nybble(PC_CONF_FINALI_PCI_INTX_RT1, pirq - 1)]; + x = irqmap[read_pc_conf_nybble(PC_CONF_FINALI_PCI_INTX_RT1, index)]; pc_conf_set(PC_CONF_FINALI_LOCK, 0); raw_spin_unlock_irqrestore(&pc_conf_lock, flags); return x; @@ -278,13 +373,15 @@ static int pirq_finali_set(struct pci_dev *router, struct pci_dev *dev, }; u8 val = irqmap[irq]; unsigned long flags; + u8 index; if (!val) return 0; + index = (pirq & 1) << 1 | (pirq & 8) >> 3; raw_spin_lock_irqsave(&pc_conf_lock, flags); pc_conf_set(PC_CONF_FINALI_LOCK, PC_CONF_FINALI_LOCK_KEY); - write_pc_conf_nybble(PC_CONF_FINALI_PCI_INTX_RT1, pirq - 1, val); + write_pc_conf_nybble(PC_CONF_FINALI_PCI_INTX_RT1, index, val); pc_conf_set(PC_CONF_FINALI_LOCK, 0); raw_spin_unlock_irqrestore(&pc_conf_lock, flags); return 1; @@ -293,7 +390,7 @@ static int pirq_finali_set(struct pci_dev *router, struct pci_dev *dev, static int pirq_finali_lvl(struct pci_dev *router, struct pci_dev *dev, int pirq, int irq) { - u8 mask = ~(1u << (pirq - 1)); + u8 mask = ~((pirq & 0xf0u) >> 4); unsigned long flags; u8 trig; @@ -579,6 +676,81 @@ static int pirq_cyrix_set(struct pci_dev *router, struct pci_dev *dev, int pirq, return 1; } + +/* + * PIRQ routing for the SiS85C497 AT Bus Controller & Megacell (ATM) + * ISA bridge used with the SiS 85C496/497 486 Green PC VESA/ISA/PCI + * Chipset. + * + * There are four PCI INTx#-to-IRQ Link registers provided in the + * SiS85C497 part of the peculiar combined 85C496/497 configuration + * space decoded by the SiS85C496 PCI & CPU Memory Controller (PCM) + * host bridge, at 0xc0/0xc1/0xc2/0xc3 respectively for the PCI INT + * A/B/C/D lines. Bit 7 enables the respective link if set and bits + * 3:0 select the 8259A IRQ line as follows: + * + * 0000 : Reserved + * 0001 : Reserved + * 0010 : Reserved + * 0011 : IRQ3 + * 0100 : IRQ4 + * 0101 : IRQ5 + * 0110 : IRQ6 + * 0111 : IRQ7 + * 1000 : Reserved + * 1001 : IRQ9 + * 1010 : IRQ10 + * 1011 : IRQ11 + * 1100 : IRQ12 + * 1101 : Reserved + * 1110 : IRQ14 + * 1111 : IRQ15 + * + * We avoid using a reserved value for disabled links, hence the + * choice of IRQ15 for that case. + * + * References: + * + * "486 Green PC VESA/ISA/PCI Chipset, SiS 85C496/497", Rev 3.0, + * Silicon Integrated Systems Corp., July 1995 + */ + +#define PCI_SIS497_INTA_TO_IRQ_LINK 0xc0u + +#define PIRQ_SIS497_IRQ_MASK 0x0fu +#define PIRQ_SIS497_IRQ_ENABLE 0x80u + +static int pirq_sis497_get(struct pci_dev *router, struct pci_dev *dev, + int pirq) +{ + int reg; + u8 x; + + reg = pirq; + if (reg >= 1 && reg <= 4) + reg += PCI_SIS497_INTA_TO_IRQ_LINK - 1; + + pci_read_config_byte(router, reg, &x); + return (x & PIRQ_SIS497_IRQ_ENABLE) ? (x & PIRQ_SIS497_IRQ_MASK) : 0; +} + +static int pirq_sis497_set(struct pci_dev *router, struct pci_dev *dev, + int pirq, int irq) +{ + int reg; + u8 x; + + reg = pirq; + if (reg >= 1 && reg <= 4) + reg += PCI_SIS497_INTA_TO_IRQ_LINK - 1; + + pci_read_config_byte(router, reg, &x); + x &= ~(PIRQ_SIS497_IRQ_MASK | PIRQ_SIS497_IRQ_ENABLE); + x |= irq ? (PIRQ_SIS497_IRQ_ENABLE | irq) : PIRQ_SIS497_IRQ_MASK; + pci_write_config_byte(router, reg, x); + return 1; +} + /* * PIRQ routing for SiS 85C503 router used in several SiS chipsets. * We have to deal with the following issues here: @@ -640,11 +812,12 @@ static int pirq_cyrix_set(struct pci_dev *router, struct pci_dev *dev, int pirq, * bit 6-4 are probably unused, not like 5595 */ -#define PIRQ_SIS_IRQ_MASK 0x0f -#define PIRQ_SIS_IRQ_DISABLE 0x80 -#define PIRQ_SIS_USB_ENABLE 0x40 +#define PIRQ_SIS503_IRQ_MASK 0x0f +#define PIRQ_SIS503_IRQ_DISABLE 0x80 +#define PIRQ_SIS503_USB_ENABLE 0x40 -static int pirq_sis_get(struct pci_dev *router, struct pci_dev *dev, int pirq) +static int pirq_sis503_get(struct pci_dev *router, struct pci_dev *dev, + int pirq) { u8 x; int reg; @@ -653,10 +826,11 @@ static int pirq_sis_get(struct pci_dev *router, struct pci_dev *dev, int pirq) if (reg >= 0x01 && reg <= 0x04) reg += 0x40; pci_read_config_byte(router, reg, &x); - return (x & PIRQ_SIS_IRQ_DISABLE) ? 0 : (x & PIRQ_SIS_IRQ_MASK); + return (x & PIRQ_SIS503_IRQ_DISABLE) ? 0 : (x & PIRQ_SIS503_IRQ_MASK); } -static int pirq_sis_set(struct pci_dev *router, struct pci_dev *dev, int pirq, int irq) +static int pirq_sis503_set(struct pci_dev *router, struct pci_dev *dev, + int pirq, int irq) { u8 x; int reg; @@ -665,8 +839,8 @@ static int pirq_sis_set(struct pci_dev *router, struct pci_dev *dev, int pirq, i if (reg >= 0x01 && reg <= 0x04) reg += 0x40; pci_read_config_byte(router, reg, &x); - x &= ~(PIRQ_SIS_IRQ_MASK | PIRQ_SIS_IRQ_DISABLE); - x |= irq ? irq: PIRQ_SIS_IRQ_DISABLE; + x &= ~(PIRQ_SIS503_IRQ_MASK | PIRQ_SIS503_IRQ_DISABLE); + x |= irq ? irq : PIRQ_SIS503_IRQ_DISABLE; pci_write_config_byte(router, reg, x); return 1; } @@ -958,13 +1132,19 @@ static __init int serverworks_router_probe(struct irq_router *r, static __init int sis_router_probe(struct irq_router *r, struct pci_dev *router, u16 device) { - if (device != PCI_DEVICE_ID_SI_503) - return 0; - - r->name = "SIS"; - r->get = pirq_sis_get; - r->set = pirq_sis_set; - return 1; + switch (device) { + case PCI_DEVICE_ID_SI_496: + r->name = "SiS85C497"; + r->get = pirq_sis497_get; + r->set = pirq_sis497_set; + return 1; + case PCI_DEVICE_ID_SI_503: + r->name = "SiS85C503"; + r->get = pirq_sis503_get; + r->set = pirq_sis503_set; + return 1; + } + return 0; } static __init int cyrix_router_probe(struct irq_router *r, struct pci_dev *router, u16 device) @@ -1084,10 +1264,32 @@ static struct pci_dev *pirq_router_dev; * chipset" ? */ +static bool __init pirq_try_router(struct irq_router *r, + struct irq_routing_table *rt, + struct pci_dev *dev) +{ + struct irq_router_handler *h; + + DBG(KERN_DEBUG "PCI: Trying IRQ router for [%04x:%04x]\n", + dev->vendor, dev->device); + + for (h = pirq_routers; h->vendor; h++) { + /* First look for a router match */ + if (rt->rtr_vendor == h->vendor && + h->probe(r, dev, rt->rtr_device)) + return true; + /* Fall back to a device match */ + if (dev->vendor == h->vendor && + h->probe(r, dev, dev->device)) + return true; + } + return false; +} + static void __init pirq_find_router(struct irq_router *r) { struct irq_routing_table *rt = pirq_table; - struct irq_router_handler *h; + struct pci_dev *dev; #ifdef CONFIG_PCI_BIOS if (!rt->signature) { @@ -1106,50 +1308,94 @@ static void __init pirq_find_router(struct irq_router *r) DBG(KERN_DEBUG "PCI: Attempting to find IRQ router for [%04x:%04x]\n", rt->rtr_vendor, rt->rtr_device); - pirq_router_dev = pci_get_domain_bus_and_slot(0, rt->rtr_bus, - rt->rtr_devfn); - if (!pirq_router_dev) { - DBG(KERN_DEBUG "PCI: Interrupt router not found at " - "%02x:%02x\n", rt->rtr_bus, rt->rtr_devfn); - return; + /* Use any vendor:device provided by the routing table or try all. */ + if (rt->rtr_vendor) { + dev = pci_get_domain_bus_and_slot(0, rt->rtr_bus, + rt->rtr_devfn); + if (dev && pirq_try_router(r, rt, dev)) + pirq_router_dev = dev; + } else { + dev = NULL; + for_each_pci_dev(dev) { + if (pirq_try_router(r, rt, dev)) { + pirq_router_dev = dev; + break; + } + } } - for (h = pirq_routers; h->vendor; h++) { - /* First look for a router match */ - if (rt->rtr_vendor == h->vendor && - h->probe(r, pirq_router_dev, rt->rtr_device)) - break; - /* Fall back to a device match */ - if (pirq_router_dev->vendor == h->vendor && - h->probe(r, pirq_router_dev, pirq_router_dev->device)) - break; - } - dev_info(&pirq_router_dev->dev, "%s IRQ router [%04x:%04x]\n", - pirq_router.name, - pirq_router_dev->vendor, pirq_router_dev->device); + if (pirq_router_dev) + dev_info(&pirq_router_dev->dev, "%s IRQ router [%04x:%04x]\n", + pirq_router.name, + pirq_router_dev->vendor, pirq_router_dev->device); + else + DBG(KERN_DEBUG "PCI: Interrupt router not found at " + "%02x:%02x\n", rt->rtr_bus, rt->rtr_devfn); /* The device remains referenced for the kernel lifetime */ } -static struct irq_info *pirq_get_info(struct pci_dev *dev) +/* + * We're supposed to match on the PCI device only and not the function, + * but some BIOSes build their tables with the PCI function included + * for motherboard devices, so if a complete match is found, then give + * it precedence over a slot match. + */ +static struct irq_info *pirq_get_dev_info(struct pci_dev *dev) { struct irq_routing_table *rt = pirq_table; int entries = (rt->size - sizeof(struct irq_routing_table)) / sizeof(struct irq_info); + struct irq_info *slotinfo = NULL; struct irq_info *info; for (info = rt->slots; entries--; info++) - if (info->bus == dev->bus->number && - PCI_SLOT(info->devfn) == PCI_SLOT(dev->devfn)) - return info; - return NULL; + if (info->bus == dev->bus->number) { + if (info->devfn == dev->devfn) + return info; + if (!slotinfo && + PCI_SLOT(info->devfn) == PCI_SLOT(dev->devfn)) + slotinfo = info; + } + return slotinfo; +} + +/* + * Buses behind bridges are typically not listed in the PIRQ routing table. + * Do the usual dance then and walk the tree of bridges up adjusting the + * pin number accordingly on the way until the originating root bus device + * has been reached and then use its routing information. + */ +static struct irq_info *pirq_get_info(struct pci_dev *dev, u8 *pin) +{ + struct pci_dev *temp_dev = dev; + struct irq_info *info; + u8 temp_pin = *pin; + u8 dpin = temp_pin; + + info = pirq_get_dev_info(dev); + while (!info && temp_dev->bus->parent) { + struct pci_dev *bridge = temp_dev->bus->self; + + temp_pin = pci_swizzle_interrupt_pin(temp_dev, temp_pin); + info = pirq_get_dev_info(bridge); + if (info) + dev_warn(&dev->dev, + "using bridge %s INT %c to get INT %c\n", + pci_name(bridge), + 'A' + temp_pin - 1, 'A' + dpin - 1); + + temp_dev = bridge; + } + *pin = temp_pin; + return info; } static int pcibios_lookup_irq(struct pci_dev *dev, int assign) { - u8 pin; struct irq_info *info; int i, pirq, newirq; + u8 dpin, pin; int irq = 0; u32 mask; struct irq_router *r = &pirq_router; @@ -1157,8 +1403,8 @@ static int pcibios_lookup_irq(struct pci_dev *dev, int assign) char *msg = NULL; /* Find IRQ pin */ - pci_read_config_byte(dev, PCI_INTERRUPT_PIN, &pin); - if (!pin) { + pci_read_config_byte(dev, PCI_INTERRUPT_PIN, &dpin); + if (!dpin) { dev_dbg(&dev->dev, "no interrupt pin\n"); return 0; } @@ -1171,20 +1417,21 @@ static int pcibios_lookup_irq(struct pci_dev *dev, int assign) if (!pirq_table) return 0; - info = pirq_get_info(dev); + pin = dpin; + info = pirq_get_info(dev, &pin); if (!info) { dev_dbg(&dev->dev, "PCI INT %c not found in routing table\n", - 'A' + pin - 1); + 'A' + dpin - 1); return 0; } pirq = info->irq[pin - 1].link; mask = info->irq[pin - 1].bitmap; if (!pirq) { - dev_dbg(&dev->dev, "PCI INT %c not routed\n", 'A' + pin - 1); + dev_dbg(&dev->dev, "PCI INT %c not routed\n", 'A' + dpin - 1); return 0; } dev_dbg(&dev->dev, "PCI INT %c -> PIRQ %02x, mask %04x, excl %04x", - 'A' + pin - 1, pirq, mask, pirq_table->exclusive_irqs); + 'A' + dpin - 1, pirq, mask, pirq_table->exclusive_irqs); mask &= pcibios_irq_mask; /* Work around broken HP Pavilion Notebooks which assign USB to @@ -1226,7 +1473,7 @@ static int pcibios_lookup_irq(struct pci_dev *dev, int assign) newirq = i; } } - dev_dbg(&dev->dev, "PCI INT %c -> newirq %d", 'A' + pin - 1, newirq); + dev_dbg(&dev->dev, "PCI INT %c -> newirq %d", 'A' + dpin - 1, newirq); /* Check if it is hardcoded */ if ((pirq & 0xf0) == 0xf0) { @@ -1260,15 +1507,17 @@ static int pcibios_lookup_irq(struct pci_dev *dev, int assign) return 0; } } - dev_info(&dev->dev, "%s PCI INT %c -> IRQ %d\n", msg, 'A' + pin - 1, irq); + dev_info(&dev->dev, "%s PCI INT %c -> IRQ %d\n", + msg, 'A' + dpin - 1, irq); /* Update IRQ for all devices with the same pirq value */ for_each_pci_dev(dev2) { - pci_read_config_byte(dev2, PCI_INTERRUPT_PIN, &pin); - if (!pin) + pci_read_config_byte(dev2, PCI_INTERRUPT_PIN, &dpin); + if (!dpin) continue; - info = pirq_get_info(dev2); + pin = dpin; + info = pirq_get_info(dev2, &pin); if (!info) continue; if (info->irq[pin - 1].link == pirq) { diff --git a/arch/x86/platform/efi/efi.c b/arch/x86/platform/efi/efi.c index 147c30a81f15..1591d67e0bcd 100644 --- a/arch/x86/platform/efi/efi.c +++ b/arch/x86/platform/efi/efi.c @@ -93,6 +93,9 @@ static const unsigned long * const efi_tables[] = { #ifdef CONFIG_LOAD_UEFI_KEYS &efi.mokvar_table, #endif +#ifdef CONFIG_EFI_COCO_SECRET + &efi.coco_secret, +#endif }; u64 efi_setup; /* efi setup_data physical address */ diff --git a/arch/x86/platform/uv/uv_nmi.c b/arch/x86/platform/uv/uv_nmi.c index 1e9ff28bc2e0..a60af0230e27 100644 --- a/arch/x86/platform/uv/uv_nmi.c +++ b/arch/x86/platform/uv/uv_nmi.c @@ -244,8 +244,10 @@ static inline bool uv_nmi_action_is(const char *action) /* Setup which NMI support is present in system */ static void uv_nmi_setup_mmrs(void) { + bool new_nmi_method_only = false; + /* First determine arch specific MMRs to handshake with BIOS */ - if (UVH_EVENT_OCCURRED0_EXTIO_INT0_MASK) { + if (UVH_EVENT_OCCURRED0_EXTIO_INT0_MASK) { /* UV2,3,4 setup */ uvh_nmi_mmrx = UVH_EVENT_OCCURRED0; uvh_nmi_mmrx_clear = UVH_EVENT_OCCURRED0_ALIAS; uvh_nmi_mmrx_shift = UVH_EVENT_OCCURRED0_EXTIO_INT0_SHFT; @@ -255,26 +257,25 @@ static void uv_nmi_setup_mmrs(void) uvh_nmi_mmrx_req = UVH_BIOS_KERNEL_MMR_ALIAS_2; uvh_nmi_mmrx_req_shift = 62; - } else if (UVH_EVENT_OCCURRED1_EXTIO_INT0_MASK) { + } else if (UVH_EVENT_OCCURRED1_EXTIO_INT0_MASK) { /* UV5+ setup */ uvh_nmi_mmrx = UVH_EVENT_OCCURRED1; uvh_nmi_mmrx_clear = UVH_EVENT_OCCURRED1_ALIAS; uvh_nmi_mmrx_shift = UVH_EVENT_OCCURRED1_EXTIO_INT0_SHFT; uvh_nmi_mmrx_type = "OCRD1-EXTIO_INT0"; - uvh_nmi_mmrx_supported = UVH_EXTIO_INT0_BROADCAST; - uvh_nmi_mmrx_req = UVH_BIOS_KERNEL_MMR_ALIAS_2; - uvh_nmi_mmrx_req_shift = 62; + new_nmi_method_only = true; /* Newer nmi always valid on UV5+ */ + uvh_nmi_mmrx_req = 0; /* no request bit to clear */ } else { - pr_err("UV:%s:cannot find EVENT_OCCURRED*_EXTIO_INT0\n", - __func__); + pr_err("UV:%s:NMI support not available on this system\n", __func__); return; } /* Then find out if new NMI is supported */ - if (likely(uv_read_local_mmr(uvh_nmi_mmrx_supported))) { - uv_write_local_mmr(uvh_nmi_mmrx_req, - 1UL << uvh_nmi_mmrx_req_shift); + if (new_nmi_method_only || uv_read_local_mmr(uvh_nmi_mmrx_supported)) { + if (uvh_nmi_mmrx_req) + uv_write_local_mmr(uvh_nmi_mmrx_req, + 1UL << uvh_nmi_mmrx_req_shift); nmi_mmr = uvh_nmi_mmrx; nmi_mmr_clear = uvh_nmi_mmrx_clear; nmi_mmr_pending = 1UL << uvh_nmi_mmrx_shift; @@ -985,7 +986,7 @@ static int uv_handle_nmi(unsigned int reason, struct pt_regs *regs) /* Clear global flags */ if (master) { - if (cpumask_weight(uv_nmi_cpu_mask)) + if (!cpumask_empty(uv_nmi_cpu_mask)) uv_nmi_cleanup_mask(); atomic_set(&uv_nmi_cpus_in_nmi, -1); atomic_set(&uv_nmi_cpu, -1); diff --git a/arch/x86/realmode/init.c b/arch/x86/realmode/init.c index c5e29db02a46..41d7669a97ad 100644 --- a/arch/x86/realmode/init.c +++ b/arch/x86/realmode/init.c @@ -67,7 +67,7 @@ void __init reserve_real_mode(void) memblock_reserve(0, SZ_1M); } -static void sme_sev_setup_real_mode(struct trampoline_header *th) +static void __init sme_sev_setup_real_mode(struct trampoline_header *th) { #ifdef CONFIG_AMD_MEM_ENCRYPT if (cc_platform_has(CC_ATTR_HOST_MEM_ENCRYPT)) diff --git a/arch/x86/realmode/rm/header.S b/arch/x86/realmode/rm/header.S index 8c1db5bf5d78..2eb62be6d256 100644 --- a/arch/x86/realmode/rm/header.S +++ b/arch/x86/realmode/rm/header.S @@ -24,6 +24,7 @@ SYM_DATA_START(real_mode_header) .long pa_sev_es_trampoline_start #endif #ifdef CONFIG_X86_64 + .long pa_trampoline_start64 .long pa_trampoline_pgd; #endif /* ACPI S3 wakeup */ diff --git a/arch/x86/realmode/rm/trampoline_64.S b/arch/x86/realmode/rm/trampoline_64.S index cc8391f86cdb..e38d61d6562e 100644 --- a/arch/x86/realmode/rm/trampoline_64.S +++ b/arch/x86/realmode/rm/trampoline_64.S @@ -70,7 +70,7 @@ SYM_CODE_START(trampoline_start) movw $__KERNEL_DS, %dx # Data segment descriptor # Enable protected mode - movl $X86_CR0_PE, %eax # protected mode (PE) bit + movl $(CR0_STATE & ~X86_CR0_PG), %eax movl %eax, %cr0 # into protected mode # flush prefetch and jump to startup_32 @@ -143,13 +143,24 @@ SYM_CODE_START(startup_32) movl %eax, %cr3 # Set up EFER + movl $MSR_EFER, %ecx + rdmsr + /* + * Skip writing to EFER if the register already has desired + * value (to avoid #VE for the TDX guest). + */ + cmp pa_tr_efer, %eax + jne .Lwrite_efer + cmp pa_tr_efer + 4, %edx + je .Ldone_efer +.Lwrite_efer: movl pa_tr_efer, %eax movl pa_tr_efer + 4, %edx - movl $MSR_EFER, %ecx wrmsr - # Enable paging and in turn activate Long Mode - movl $(X86_CR0_PG | X86_CR0_WP | X86_CR0_PE), %eax +.Ldone_efer: + # Enable paging and in turn activate Long Mode. + movl $CR0_STATE, %eax movl %eax, %cr0 /* @@ -161,6 +172,19 @@ SYM_CODE_START(startup_32) ljmpl $__KERNEL_CS, $pa_startup_64 SYM_CODE_END(startup_32) +SYM_CODE_START(pa_trampoline_compat) + /* + * In compatibility mode. Prep ESP and DX for startup_32, then disable + * paging and complete the switch to legacy 32-bit mode. + */ + movl $rm_stack_end, %esp + movw $__KERNEL_DS, %dx + + movl $(CR0_STATE & ~X86_CR0_PG), %eax + movl %eax, %cr0 + ljmpl $__KERNEL32_CS, $pa_startup_32 +SYM_CODE_END(pa_trampoline_compat) + .section ".text64","ax" .code64 .balign 4 @@ -169,6 +193,20 @@ SYM_CODE_START(startup_64) jmpq *tr_start(%rip) SYM_CODE_END(startup_64) +SYM_CODE_START(trampoline_start64) + /* + * APs start here on a direct transfer from 64-bit BIOS with identity + * mapped page tables. Load the kernel's GDT in order to gear down to + * 32-bit mode (to handle 4-level vs. 5-level paging), and to (re)load + * segment registers. Load the zero IDT so any fault triggers a + * shutdown instead of jumping back into BIOS. + */ + lidt tr_idt(%rip) + lgdt tr_gdt64(%rip) + + ljmpl *tr_compat(%rip) +SYM_CODE_END(trampoline_start64) + .section ".rodata","a" # Duplicate the global descriptor table # so the kernel can live anywhere @@ -182,6 +220,17 @@ SYM_DATA_START(tr_gdt) .quad 0x00cf93000000ffff # __KERNEL_DS SYM_DATA_END_LABEL(tr_gdt, SYM_L_LOCAL, tr_gdt_end) +SYM_DATA_START(tr_gdt64) + .short tr_gdt_end - tr_gdt - 1 # gdt limit + .long pa_tr_gdt + .long 0 +SYM_DATA_END(tr_gdt64) + +SYM_DATA_START(tr_compat) + .long pa_trampoline_compat + .short __KERNEL32_CS +SYM_DATA_END(tr_compat) + .bss .balign PAGE_SIZE SYM_DATA(trampoline_pgd, .space PAGE_SIZE) diff --git a/arch/x86/realmode/rm/trampoline_common.S b/arch/x86/realmode/rm/trampoline_common.S index 5033e640f957..4331c32c47f8 100644 --- a/arch/x86/realmode/rm/trampoline_common.S +++ b/arch/x86/realmode/rm/trampoline_common.S @@ -1,4 +1,14 @@ /* SPDX-License-Identifier: GPL-2.0 */ .section ".rodata","a" .balign 16 -SYM_DATA_LOCAL(tr_idt, .fill 1, 6, 0) + +/* + * When a bootloader hands off to the kernel in 32-bit mode an + * IDT with a 2-byte limit and 4-byte base is needed. When a boot + * loader hands off to a kernel 64-bit mode the base address + * extends to 8-bytes. Reserve enough space for either scenario. + */ +SYM_DATA_START_LOCAL(tr_idt) + .short 0 + .quad 0 +SYM_DATA_END(tr_idt) diff --git a/arch/x86/realmode/rm/wakemain.c b/arch/x86/realmode/rm/wakemain.c index 1d6437e6d2ba..a6f4d8388ad8 100644 --- a/arch/x86/realmode/rm/wakemain.c +++ b/arch/x86/realmode/rm/wakemain.c @@ -62,8 +62,12 @@ static void send_morse(const char *pattern) } } +struct port_io_ops pio_ops; + void main(void) { + init_default_io_ops(); + /* Kill machine if structures are wrong */ if (wakeup_header.real_magic != 0x12345678) while (1) diff --git a/arch/x86/virt/vmx/tdx/tdxcall.S b/arch/x86/virt/vmx/tdx/tdxcall.S new file mode 100644 index 000000000000..49a54356ae99 --- /dev/null +++ b/arch/x86/virt/vmx/tdx/tdxcall.S @@ -0,0 +1,96 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#include <asm/asm-offsets.h> +#include <asm/tdx.h> + +/* + * TDCALL and SEAMCALL are supported in Binutils >= 2.36. + */ +#define tdcall .byte 0x66,0x0f,0x01,0xcc +#define seamcall .byte 0x66,0x0f,0x01,0xcf + +/* + * TDX_MODULE_CALL - common helper macro for both + * TDCALL and SEAMCALL instructions. + * + * TDCALL - used by TDX guests to make requests to the + * TDX module and hypercalls to the VMM. + * SEAMCALL - used by TDX hosts to make requests to the + * TDX module. + */ +.macro TDX_MODULE_CALL host:req + /* + * R12 will be used as temporary storage for struct tdx_module_output + * pointer. Since R12-R15 registers are not used by TDCALL/SEAMCALL + * services supported by this function, it can be reused. + */ + + /* Callee saved, so preserve it */ + push %r12 + + /* + * Push output pointer to stack. + * After the operation, it will be fetched into R12 register. + */ + push %r9 + + /* Mangle function call ABI into TDCALL/SEAMCALL ABI: */ + /* Move Leaf ID to RAX */ + mov %rdi, %rax + /* Move input 4 to R9 */ + mov %r8, %r9 + /* Move input 3 to R8 */ + mov %rcx, %r8 + /* Move input 1 to RCX */ + mov %rsi, %rcx + /* Leave input param 2 in RDX */ + + .if \host + seamcall + /* + * SEAMCALL instruction is essentially a VMExit from VMX root + * mode to SEAM VMX root mode. VMfailInvalid (CF=1) indicates + * that the targeted SEAM firmware is not loaded or disabled, + * or P-SEAMLDR is busy with another SEAMCALL. %rax is not + * changed in this case. + * + * Set %rax to TDX_SEAMCALL_VMFAILINVALID for VMfailInvalid. + * This value will never be used as actual SEAMCALL error code as + * it is from the Reserved status code class. + */ + jnc .Lno_vmfailinvalid + mov $TDX_SEAMCALL_VMFAILINVALID, %rax +.Lno_vmfailinvalid: + + .else + tdcall + .endif + + /* + * Fetch output pointer from stack to R12 (It is used + * as temporary storage) + */ + pop %r12 + + /* + * Since this macro can be invoked with NULL as an output pointer, + * check if caller provided an output struct before storing output + * registers. + * + * Update output registers, even if the call failed (RAX != 0). + * Other registers may contain details of the failure. + */ + test %r12, %r12 + jz .Lno_output_struct + + /* Copy result registers to output struct: */ + movq %rcx, TDX_MODULE_rcx(%r12) + movq %rdx, TDX_MODULE_rdx(%r12) + movq %r8, TDX_MODULE_r8(%r12) + movq %r9, TDX_MODULE_r9(%r12) + movq %r10, TDX_MODULE_r10(%r12) + movq %r11, TDX_MODULE_r11(%r12) + +.Lno_output_struct: + /* Restore the state of R12 register */ + pop %r12 +.endm diff --git a/arch/x86/xen/smp_pv.c b/arch/x86/xen/smp_pv.c index 688aa8b6ae29..ba7af2eca755 100644 --- a/arch/x86/xen/smp_pv.c +++ b/arch/x86/xen/smp_pv.c @@ -260,8 +260,11 @@ cpu_initialize_context(unsigned int cpu, struct task_struct *idle) return 0; ctxt = kzalloc(sizeof(*ctxt), GFP_KERNEL); - if (ctxt == NULL) + if (ctxt == NULL) { + cpumask_clear_cpu(cpu, xen_cpu_initialized_map); + cpumask_clear_cpu(cpu, cpu_callout_mask); return -ENOMEM; + } gdt = get_cpu_gdt_rw(cpu); diff --git a/block/Makefile b/block/Makefile index 3950ecbc5c26..4e01bb71ad6e 100644 --- a/block/Makefile +++ b/block/Makefile @@ -16,6 +16,7 @@ obj-$(CONFIG_BLK_DEV_BSG_COMMON) += bsg.o obj-$(CONFIG_BLK_DEV_BSGLIB) += bsg-lib.o obj-$(CONFIG_BLK_CGROUP) += blk-cgroup.o obj-$(CONFIG_BLK_CGROUP_RWSTAT) += blk-cgroup-rwstat.o +obj-$(CONFIG_BLK_CGROUP_FC_APPID) += blk-cgroup-fc-appid.o obj-$(CONFIG_BLK_DEV_THROTTLING) += blk-throttle.o obj-$(CONFIG_BLK_CGROUP_IOPRIO) += blk-ioprio.o obj-$(CONFIG_BLK_CGROUP_IOLATENCY) += blk-iolatency.o diff --git a/block/badblocks.c b/block/badblocks.c index d39056630d9c..3afb550c0f7b 100644 --- a/block/badblocks.c +++ b/block/badblocks.c @@ -65,7 +65,6 @@ int badblocks_check(struct badblocks *bb, sector_t s, int sectors, s >>= bb->shift; target += (1<<bb->shift) - 1; target >>= bb->shift; - sectors = target - s; } /* 'target' is now the first block after the bad range */ @@ -345,7 +344,6 @@ int badblocks_clear(struct badblocks *bb, sector_t s, int sectors) s += (1<<bb->shift) - 1; s >>= bb->shift; target >>= bb->shift; - sectors = target - s; } write_seqlock_irq(&bb->lock); diff --git a/block/bdev.c b/block/bdev.c index 13de871fa816..7bf88e591aaf 100644 --- a/block/bdev.c +++ b/block/bdev.c @@ -673,17 +673,17 @@ static int blkdev_get_whole(struct block_device *bdev, fmode_t mode) } } - if (!bdev->bd_openers) + if (!atomic_read(&bdev->bd_openers)) set_init_blocksize(bdev); if (test_bit(GD_NEED_PART_SCAN, &disk->state)) bdev_disk_changed(disk, false); - bdev->bd_openers++; + atomic_inc(&bdev->bd_openers); return 0; } static void blkdev_put_whole(struct block_device *bdev, fmode_t mode) { - if (!--bdev->bd_openers) + if (atomic_dec_and_test(&bdev->bd_openers)) blkdev_flush_mapping(bdev); if (bdev->bd_disk->fops->release) bdev->bd_disk->fops->release(bdev->bd_disk, mode); @@ -694,7 +694,7 @@ static int blkdev_get_part(struct block_device *part, fmode_t mode) struct gendisk *disk = part->bd_disk; int ret; - if (part->bd_openers) + if (atomic_read(&part->bd_openers)) goto done; ret = blkdev_get_whole(bdev_whole(part), mode); @@ -708,7 +708,7 @@ static int blkdev_get_part(struct block_device *part, fmode_t mode) disk->open_partitions++; set_init_blocksize(part); done: - part->bd_openers++; + atomic_inc(&part->bd_openers); return 0; out_blkdev_put: @@ -720,7 +720,7 @@ static void blkdev_put_part(struct block_device *part, fmode_t mode) { struct block_device *whole = bdev_whole(part); - if (--part->bd_openers) + if (!atomic_dec_and_test(&part->bd_openers)) return; blkdev_flush_mapping(part); whole->bd_disk->open_partitions--; @@ -899,7 +899,7 @@ void blkdev_put(struct block_device *bdev, fmode_t mode) * of the world and we want to avoid long (could be several minute) * syncs while holding the mutex. */ - if (bdev->bd_openers == 1) + if (atomic_read(&bdev->bd_openers) == 1) sync_blockdev(bdev); mutex_lock(&disk->open_mutex); @@ -1044,7 +1044,7 @@ void sync_bdevs(bool wait) bdev = I_BDEV(inode); mutex_lock(&bdev->bd_disk->open_mutex); - if (!bdev->bd_openers) { + if (!atomic_read(&bdev->bd_openers)) { ; /* skip */ } else if (wait) { /* diff --git a/block/bfq-cgroup.c b/block/bfq-cgroup.c index 420eda2589c0..09574af83566 100644 --- a/block/bfq-cgroup.c +++ b/block/bfq-cgroup.c @@ -557,6 +557,7 @@ static void bfq_pd_init(struct blkg_policy_data *pd) */ bfqg->bfqd = bfqd; bfqg->active_entities = 0; + bfqg->online = true; bfqg->rq_pos_tree = RB_ROOT; } @@ -585,28 +586,11 @@ static void bfq_group_set_parent(struct bfq_group *bfqg, entity->sched_data = &parent->sched_data; } -static struct bfq_group *bfq_lookup_bfqg(struct bfq_data *bfqd, - struct blkcg *blkcg) +static void bfq_link_bfqg(struct bfq_data *bfqd, struct bfq_group *bfqg) { - struct blkcg_gq *blkg; - - blkg = blkg_lookup(blkcg, bfqd->queue); - if (likely(blkg)) - return blkg_to_bfqg(blkg); - return NULL; -} - -struct bfq_group *bfq_find_set_group(struct bfq_data *bfqd, - struct blkcg *blkcg) -{ - struct bfq_group *bfqg, *parent; + struct bfq_group *parent; struct bfq_entity *entity; - bfqg = bfq_lookup_bfqg(bfqd, blkcg); - - if (unlikely(!bfqg)) - return NULL; - /* * Update chain of bfq_groups as we might be handling a leaf group * which, along with some of its relatives, has not been hooked yet @@ -623,8 +607,24 @@ struct bfq_group *bfq_find_set_group(struct bfq_data *bfqd, bfq_group_set_parent(curr_bfqg, parent); } } +} - return bfqg; +struct bfq_group *bfq_bio_bfqg(struct bfq_data *bfqd, struct bio *bio) +{ + struct blkcg_gq *blkg = bio->bi_blkg; + struct bfq_group *bfqg; + + while (blkg) { + bfqg = blkg_to_bfqg(blkg); + if (bfqg->online) { + bio_associate_blkg_from_css(bio, &blkg->blkcg->css); + return bfqg; + } + blkg = blkg->parent; + } + bio_associate_blkg_from_css(bio, + &bfqg_to_blkg(bfqd->root_group)->blkcg->css); + return bfqd->root_group; } /** @@ -714,25 +714,15 @@ void bfq_bfqq_move(struct bfq_data *bfqd, struct bfq_queue *bfqq, * Move bic to blkcg, assuming that bfqd->lock is held; which makes * sure that the reference to cgroup is valid across the call (see * comments in bfq_bic_update_cgroup on this issue) - * - * NOTE: an alternative approach might have been to store the current - * cgroup in bfqq and getting a reference to it, reducing the lookup - * time here, at the price of slightly more complex code. */ -static struct bfq_group *__bfq_bic_change_cgroup(struct bfq_data *bfqd, - struct bfq_io_cq *bic, - struct blkcg *blkcg) +static void *__bfq_bic_change_cgroup(struct bfq_data *bfqd, + struct bfq_io_cq *bic, + struct bfq_group *bfqg) { struct bfq_queue *async_bfqq = bic_to_bfqq(bic, 0); struct bfq_queue *sync_bfqq = bic_to_bfqq(bic, 1); - struct bfq_group *bfqg; struct bfq_entity *entity; - bfqg = bfq_find_set_group(bfqd, blkcg); - - if (unlikely(!bfqg)) - bfqg = bfqd->root_group; - if (async_bfqq) { entity = &async_bfqq->entity; @@ -743,9 +733,39 @@ static struct bfq_group *__bfq_bic_change_cgroup(struct bfq_data *bfqd, } if (sync_bfqq) { - entity = &sync_bfqq->entity; - if (entity->sched_data != &bfqg->sched_data) - bfq_bfqq_move(bfqd, sync_bfqq, bfqg); + if (!sync_bfqq->new_bfqq && !bfq_bfqq_coop(sync_bfqq)) { + /* We are the only user of this bfqq, just move it */ + if (sync_bfqq->entity.sched_data != &bfqg->sched_data) + bfq_bfqq_move(bfqd, sync_bfqq, bfqg); + } else { + struct bfq_queue *bfqq; + + /* + * The queue was merged to a different queue. Check + * that the merge chain still belongs to the same + * cgroup. + */ + for (bfqq = sync_bfqq; bfqq; bfqq = bfqq->new_bfqq) + if (bfqq->entity.sched_data != + &bfqg->sched_data) + break; + if (bfqq) { + /* + * Some queue changed cgroup so the merge is + * not valid anymore. We cannot easily just + * cancel the merge (by clearing new_bfqq) as + * there may be other processes using this + * queue and holding refs to all queues below + * sync_bfqq->new_bfqq. Similarly if the merge + * already happened, we need to detach from + * bfqq now so that we cannot merge bio to a + * request from the old cgroup. + */ + bfq_put_cooperator(sync_bfqq); + bfq_release_process_ref(bfqd, sync_bfqq); + bic_set_bfqq(bic, NULL, 1); + } + } } return bfqg; @@ -754,20 +774,24 @@ static struct bfq_group *__bfq_bic_change_cgroup(struct bfq_data *bfqd, void bfq_bic_update_cgroup(struct bfq_io_cq *bic, struct bio *bio) { struct bfq_data *bfqd = bic_to_bfqd(bic); - struct bfq_group *bfqg = NULL; + struct bfq_group *bfqg = bfq_bio_bfqg(bfqd, bio); uint64_t serial_nr; - rcu_read_lock(); - serial_nr = __bio_blkcg(bio)->css.serial_nr; + serial_nr = bfqg_to_blkg(bfqg)->blkcg->css.serial_nr; /* * Check whether blkcg has changed. The condition may trigger * spuriously on a newly created cic but there's no harm. */ if (unlikely(!bfqd) || likely(bic->blkcg_serial_nr == serial_nr)) - goto out; + return; - bfqg = __bfq_bic_change_cgroup(bfqd, bic, __bio_blkcg(bio)); + /* + * New cgroup for this process. Make sure it is linked to bfq internal + * cgroup hierarchy. + */ + bfq_link_bfqg(bfqd, bfqg); + __bfq_bic_change_cgroup(bfqd, bic, bfqg); /* * Update blkg_path for bfq_log_* functions. We cache this * path, and update it here, for the following @@ -820,8 +844,6 @@ void bfq_bic_update_cgroup(struct bfq_io_cq *bic, struct bio *bio) */ blkg_path(bfqg_to_blkg(bfqg), bfqg->blkg_path, sizeof(bfqg->blkg_path)); bic->blkcg_serial_nr = serial_nr; -out: - rcu_read_unlock(); } /** @@ -949,6 +971,7 @@ static void bfq_pd_offline(struct blkg_policy_data *pd) put_async_queues: bfq_put_async_queues(bfqd, bfqg); + bfqg->online = false; spin_unlock_irqrestore(&bfqd->lock, flags); /* @@ -1438,7 +1461,7 @@ void bfq_end_wr_async(struct bfq_data *bfqd) bfq_end_wr_async_queues(bfqd, bfqd->root_group); } -struct bfq_group *bfq_find_set_group(struct bfq_data *bfqd, struct blkcg *blkcg) +struct bfq_group *bfq_bio_bfqg(struct bfq_data *bfqd, struct bio *bio) { return bfqd->root_group; } diff --git a/block/bfq-iosched.c b/block/bfq-iosched.c index 1f62dbdc521f..0d46cb728bbf 100644 --- a/block/bfq-iosched.c +++ b/block/bfq-iosched.c @@ -374,7 +374,7 @@ static const unsigned long bfq_activation_stable_merging = 600; */ static const unsigned long bfq_late_stable_merging = 600; -#define RQ_BIC(rq) icq_to_bic((rq)->elv.priv[0]) +#define RQ_BIC(rq) ((struct bfq_io_cq *)((rq)->elv.priv[0])) #define RQ_BFQQ(rq) ((rq)->elv.priv[1]) struct bfq_queue *bic_to_bfqq(struct bfq_io_cq *bic, bool is_sync) @@ -456,6 +456,8 @@ static struct bfq_io_cq *bfq_bic_lookup(struct request_queue *q) */ void bfq_schedule_dispatch(struct bfq_data *bfqd) { + lockdep_assert_held(&bfqd->lock); + if (bfqd->queued != 0) { bfq_log(bfqd, "schedule dispatch"); blk_mq_run_hw_queues(bfqd->queue, true); @@ -2133,9 +2135,7 @@ static void bfq_check_waker(struct bfq_data *bfqd, struct bfq_queue *bfqq, if (!bfqd->last_completed_rq_bfqq || bfqd->last_completed_rq_bfqq == bfqq || bfq_bfqq_has_short_ttime(bfqq) || - bfqq->dispatched > 0 || - now_ns - bfqd->last_completion >= 4 * NSEC_PER_MSEC || - bfqd->last_completed_rq_bfqq == bfqq->waker_bfqq) + now_ns - bfqd->last_completion >= 4 * NSEC_PER_MSEC) return; /* @@ -2208,9 +2208,13 @@ static void bfq_add_request(struct request *rq) bfq_log_bfqq(bfqd, bfqq, "add_request %d", rq_is_sync(rq)); bfqq->queued[rq_is_sync(rq)]++; - bfqd->queued++; + /* + * Updating of 'bfqd->queued' is protected by 'bfqd->lock', however, it + * may be read without holding the lock in bfq_has_work(). + */ + WRITE_ONCE(bfqd->queued, bfqd->queued + 1); - if (RB_EMPTY_ROOT(&bfqq->sort_list) && bfq_bfqq_sync(bfqq)) { + if (bfq_bfqq_sync(bfqq) && RQ_BIC(rq)->requests <= 1) { bfq_check_waker(bfqd, bfqq, now_ns); /* @@ -2400,7 +2404,11 @@ static void bfq_remove_request(struct request_queue *q, if (rq->queuelist.prev != &rq->queuelist) list_del_init(&rq->queuelist); bfqq->queued[sync]--; - bfqd->queued--; + /* + * Updating of 'bfqd->queued' is protected by 'bfqd->lock', however, it + * may be read without holding the lock in bfq_has_work(). + */ + WRITE_ONCE(bfqd->queued, bfqd->queued - 1); elv_rb_del(&bfqq->sort_list, rq); elv_rqhash_del(q, rq); @@ -2463,10 +2471,17 @@ static bool bfq_bio_merge(struct request_queue *q, struct bio *bio, spin_lock_irq(&bfqd->lock); - if (bic) + if (bic) { + /* + * Make sure cgroup info is uptodate for current process before + * considering the merge. + */ + bfq_bic_update_cgroup(bic, bio); + bfqd->bio_bfqq = bic_to_bfqq(bic, op_is_sync(bio->bi_opf)); - else + } else { bfqd->bio_bfqq = NULL; + } bfqd->bio_bic = bic; ret = blk_mq_sched_try_merge(q, bio, nr_segs, &free); @@ -2496,8 +2511,6 @@ static int bfq_request_merge(struct request_queue *q, struct request **req, return ELEVATOR_NO_MERGE; } -static struct bfq_queue *bfq_init_rq(struct request *rq); - static void bfq_request_merged(struct request_queue *q, struct request *req, enum elv_merge type) { @@ -2506,7 +2519,7 @@ static void bfq_request_merged(struct request_queue *q, struct request *req, blk_rq_pos(req) < blk_rq_pos(container_of(rb_prev(&req->rb_node), struct request, rb_node))) { - struct bfq_queue *bfqq = bfq_init_rq(req); + struct bfq_queue *bfqq = RQ_BFQQ(req); struct bfq_data *bfqd; struct request *prev, *next_rq; @@ -2558,8 +2571,8 @@ static void bfq_request_merged(struct request_queue *q, struct request *req, static void bfq_requests_merged(struct request_queue *q, struct request *rq, struct request *next) { - struct bfq_queue *bfqq = bfq_init_rq(rq), - *next_bfqq = bfq_init_rq(next); + struct bfq_queue *bfqq = RQ_BFQQ(rq), + *next_bfqq = RQ_BFQQ(next); if (!bfqq) goto remove; @@ -2764,6 +2777,14 @@ bfq_setup_merge(struct bfq_queue *bfqq, struct bfq_queue *new_bfqq) if (process_refs == 0 || new_process_refs == 0) return NULL; + /* + * Make sure merged queues belong to the same parent. Parents could + * have changed since the time we decided the two queues are suitable + * for merging. + */ + if (new_bfqq->entity.parent != bfqq->entity.parent) + return NULL; + bfq_log_bfqq(bfqq->bfqd, bfqq, "scheduling merge with queue %d", new_bfqq->pid); @@ -2901,9 +2922,12 @@ bfq_setup_cooperator(struct bfq_data *bfqd, struct bfq_queue *bfqq, struct bfq_queue *new_bfqq = bfq_setup_merge(bfqq, stable_merge_bfqq); - bic->stably_merged = true; - if (new_bfqq && new_bfqq->bic) - new_bfqq->bic->stably_merged = true; + if (new_bfqq) { + bic->stably_merged = true; + if (new_bfqq->bic) + new_bfqq->bic->stably_merged = + true; + } return new_bfqq; } else return NULL; @@ -5045,11 +5069,11 @@ static bool bfq_has_work(struct blk_mq_hw_ctx *hctx) struct bfq_data *bfqd = hctx->queue->elevator->elevator_data; /* - * Avoiding lock: a race on bfqd->busy_queues should cause at + * Avoiding lock: a race on bfqd->queued should cause at * most a call to dispatch for nothing */ return !list_empty_careful(&bfqd->dispatch) || - bfq_tot_busy_queues(bfqd) > 0; + READ_ONCE(bfqd->queued); } static struct request *__bfq_dispatch_request(struct blk_mq_hw_ctx *hctx) @@ -5310,7 +5334,7 @@ static void bfq_put_stable_ref(struct bfq_queue *bfqq) bfq_put_queue(bfqq); } -static void bfq_put_cooperator(struct bfq_queue *bfqq) +void bfq_put_cooperator(struct bfq_queue *bfqq) { struct bfq_queue *__bfqq, *next; @@ -5716,14 +5740,7 @@ static struct bfq_queue *bfq_get_queue(struct bfq_data *bfqd, struct bfq_queue *bfqq; struct bfq_group *bfqg; - rcu_read_lock(); - - bfqg = bfq_find_set_group(bfqd, __bio_blkcg(bio)); - if (!bfqg) { - bfqq = &bfqd->oom_bfqq; - goto out; - } - + bfqg = bfq_bio_bfqg(bfqd, bio); if (!is_sync) { async_bfqq = bfq_async_queue_prio(bfqd, bfqg, ioprio_class, ioprio); @@ -5769,8 +5786,6 @@ out: if (bfqq != &bfqd->oom_bfqq && is_sync && !respawn) bfqq = bfq_do_or_sched_stable_merge(bfqd, bfqq, bic); - - rcu_read_unlock(); return bfqq; } @@ -6117,6 +6132,8 @@ static inline void bfq_update_insert_stats(struct request_queue *q, unsigned int cmd_flags) {} #endif /* CONFIG_BFQ_CGROUP_DEBUG */ +static struct bfq_queue *bfq_init_rq(struct request *rq); + static void bfq_insert_request(struct blk_mq_hw_ctx *hctx, struct request *rq, bool at_head) { @@ -6132,18 +6149,15 @@ static void bfq_insert_request(struct blk_mq_hw_ctx *hctx, struct request *rq, bfqg_stats_update_legacy_io(q, rq); #endif spin_lock_irq(&bfqd->lock); + bfqq = bfq_init_rq(rq); if (blk_mq_sched_try_insert_merge(q, rq, &free)) { spin_unlock_irq(&bfqd->lock); blk_mq_free_requests(&free); return; } - spin_unlock_irq(&bfqd->lock); - trace_block_rq_insert(rq); - spin_lock_irq(&bfqd->lock); - bfqq = bfq_init_rq(rq); if (!bfqq || at_head) { if (at_head) list_add(&rq->queuelist, &bfqd->dispatch); @@ -6360,12 +6374,6 @@ static void bfq_completed_request(struct bfq_queue *bfqq, struct bfq_data *bfqd) bfq_schedule_dispatch(bfqd); } -static void bfq_finish_requeue_request_body(struct bfq_queue *bfqq) -{ - bfqq_request_freed(bfqq); - bfq_put_queue(bfqq); -} - /* * The processes associated with bfqq may happen to generate their * cumulative I/O at a lower rate than the rate at which the device @@ -6562,7 +6570,9 @@ static void bfq_finish_requeue_request(struct request *rq) bfq_completed_request(bfqq, bfqd); } - bfq_finish_requeue_request_body(bfqq); + bfqq_request_freed(bfqq); + bfq_put_queue(bfqq); + RQ_BIC(rq)->requests--; spin_unlock_irqrestore(&bfqd->lock, flags); /* @@ -6796,6 +6806,7 @@ static struct bfq_queue *bfq_init_rq(struct request *rq) bfqq_request_allocated(bfqq); bfqq->ref++; + bic->requests++; bfq_log_bfqq(bfqd, bfqq, "get_request %p: bfqq %p, %d", rq, bfqq, bfqq->ref); @@ -6892,8 +6903,8 @@ bfq_idle_slice_timer_body(struct bfq_data *bfqd, struct bfq_queue *bfqq) bfq_bfqq_expire(bfqd, bfqq, true, reason); schedule_dispatch: - spin_unlock_irqrestore(&bfqd->lock, flags); bfq_schedule_dispatch(bfqd); + spin_unlock_irqrestore(&bfqd->lock, flags); } /* diff --git a/block/bfq-iosched.h b/block/bfq-iosched.h index 3b83e3d1c2e5..ca8177d7bf7c 100644 --- a/block/bfq-iosched.h +++ b/block/bfq-iosched.h @@ -468,6 +468,7 @@ struct bfq_io_cq { struct bfq_queue *stable_merge_bfqq; bool stably_merged; /* non splittable if true */ + unsigned int requests; /* Number of requests this process has in flight */ }; /** @@ -928,6 +929,8 @@ struct bfq_group { /* reference counter (see comments in bfq_bic_update_cgroup) */ int ref; + /* Is bfq_group still online? */ + bool online; struct bfq_entity entity; struct bfq_sched_data sched_data; @@ -979,6 +982,7 @@ void bfq_weights_tree_remove(struct bfq_data *bfqd, void bfq_bfqq_expire(struct bfq_data *bfqd, struct bfq_queue *bfqq, bool compensate, enum bfqq_expiration reason); void bfq_put_queue(struct bfq_queue *bfqq); +void bfq_put_cooperator(struct bfq_queue *bfqq); void bfq_end_wr_async_queues(struct bfq_data *bfqd, struct bfq_group *bfqg); void bfq_release_process_ref(struct bfq_data *bfqd, struct bfq_queue *bfqq); void bfq_schedule_dispatch(struct bfq_data *bfqd); @@ -1006,8 +1010,7 @@ void bfq_bfqq_move(struct bfq_data *bfqd, struct bfq_queue *bfqq, void bfq_init_entity(struct bfq_entity *entity, struct bfq_group *bfqg); void bfq_bic_update_cgroup(struct bfq_io_cq *bic, struct bio *bio); void bfq_end_wr_async(struct bfq_data *bfqd); -struct bfq_group *bfq_find_set_group(struct bfq_data *bfqd, - struct blkcg *blkcg); +struct bfq_group *bfq_bio_bfqg(struct bfq_data *bfqd, struct bio *bio); struct blkcg_gq *bfqg_to_blkg(struct bfq_group *bfqg); struct bfq_group *bfqq_group(struct bfq_queue *bfqq); struct bfq_group *bfq_create_group_hierarchy(struct bfq_data *bfqd, int node); @@ -1100,13 +1103,13 @@ struct bfq_group *bfqq_group(struct bfq_queue *bfqq); break; \ bfq_bfqq_name((bfqq), pid_str, MAX_BFQQ_NAME_LENGTH); \ blk_add_cgroup_trace_msg((bfqd)->queue, \ - bfqg_to_blkg(bfqq_group(bfqq))->blkcg, \ + &bfqg_to_blkg(bfqq_group(bfqq))->blkcg->css, \ "%s " fmt, pid_str, ##args); \ } while (0) #define bfq_log_bfqg(bfqd, bfqg, fmt, args...) do { \ blk_add_cgroup_trace_msg((bfqd)->queue, \ - bfqg_to_blkg(bfqg)->blkcg, fmt, ##args); \ + &bfqg_to_blkg(bfqg)->blkcg->css, fmt, ##args); \ } while (0) #else /* CONFIG_BFQ_GROUP_IOSCHED */ diff --git a/block/bio.c b/block/bio.c index 4259125e16ab..a3893d80dccc 100644 --- a/block/bio.c +++ b/block/bio.c @@ -224,24 +224,13 @@ EXPORT_SYMBOL(bio_uninit); static void bio_free(struct bio *bio) { struct bio_set *bs = bio->bi_pool; - void *p; - - bio_uninit(bio); + void *p = bio; - if (bs) { - bvec_free(&bs->bvec_pool, bio->bi_io_vec, bio->bi_max_vecs); + WARN_ON_ONCE(!bs); - /* - * If we have front padding, adjust the bio pointer before freeing - */ - p = bio; - p -= bs->front_pad; - - mempool_free(p, &bs->bio_pool); - } else { - /* Bio was allocated by bio_kmalloc() */ - kfree(bio); - } + bio_uninit(bio); + bvec_free(&bs->bvec_pool, bio->bi_io_vec, bio->bi_max_vecs); + mempool_free(p - bs->front_pad, &bs->bio_pool); } /* @@ -419,6 +408,28 @@ static void punt_bios_to_rescuer(struct bio_set *bs) queue_work(bs->rescue_workqueue, &bs->rescue_work); } +static struct bio *bio_alloc_percpu_cache(struct block_device *bdev, + unsigned short nr_vecs, unsigned int opf, gfp_t gfp, + struct bio_set *bs) +{ + struct bio_alloc_cache *cache; + struct bio *bio; + + cache = per_cpu_ptr(bs->cache, get_cpu()); + if (!cache->free_list) { + put_cpu(); + return NULL; + } + bio = cache->free_list; + cache->free_list = bio->bi_next; + cache->nr--; + put_cpu(); + + bio_init(bio, bdev, nr_vecs ? bio->bi_inline_vecs : NULL, nr_vecs, opf); + bio->bi_pool = bs; + return bio; +} + /** * bio_alloc_bioset - allocate a bio for I/O * @bdev: block device to allocate the bio for (can be %NULL) @@ -451,6 +462,9 @@ static void punt_bios_to_rescuer(struct bio_set *bs) * submit_bio_noacct() should be avoided - instead, use bio_set's front_pad * for per bio allocations. * + * If REQ_ALLOC_CACHE is set, the final put of the bio MUST be done from process + * context, not hard/soft IRQ. + * * Returns: Pointer to new bio on success, NULL on failure. */ struct bio *bio_alloc_bioset(struct block_device *bdev, unsigned short nr_vecs, @@ -465,6 +479,21 @@ struct bio *bio_alloc_bioset(struct block_device *bdev, unsigned short nr_vecs, if (WARN_ON_ONCE(!mempool_initialized(&bs->bvec_pool) && nr_vecs > 0)) return NULL; + if (opf & REQ_ALLOC_CACHE) { + if (bs->cache && nr_vecs <= BIO_INLINE_VECS) { + bio = bio_alloc_percpu_cache(bdev, nr_vecs, opf, + gfp_mask, bs); + if (bio) + return bio; + /* + * No cached bio available, bio returned below marked with + * REQ_ALLOC_CACHE to particpate in per-cpu alloc cache. + */ + } else { + opf &= ~REQ_ALLOC_CACHE; + } + } + /* * submit_bio_noacct() converts recursion to iteration; this means if * we're running beneath it, any bios we allocate and submit will not be @@ -528,28 +557,28 @@ err_free: EXPORT_SYMBOL(bio_alloc_bioset); /** - * bio_kmalloc - kmalloc a bio for I/O + * bio_kmalloc - kmalloc a bio + * @nr_vecs: number of bio_vecs to allocate * @gfp_mask: the GFP_* mask given to the slab allocator - * @nr_iovecs: number of iovecs to pre-allocate * - * Use kmalloc to allocate and initialize a bio. + * Use kmalloc to allocate a bio (including bvecs). The bio must be initialized + * using bio_init() before use. To free a bio returned from this function use + * kfree() after calling bio_uninit(). A bio returned from this function can + * be reused by calling bio_uninit() before calling bio_init() again. + * + * Note that unlike bio_alloc() or bio_alloc_bioset() allocations from this + * function are not backed by a mempool can can fail. Do not use this function + * for allocations in the file system I/O path. * * Returns: Pointer to new bio on success, NULL on failure. */ -struct bio *bio_kmalloc(gfp_t gfp_mask, unsigned short nr_iovecs) +struct bio *bio_kmalloc(unsigned short nr_vecs, gfp_t gfp_mask) { struct bio *bio; - if (nr_iovecs > UIO_MAXIOV) - return NULL; - - bio = kmalloc(struct_size(bio, bi_inline_vecs, nr_iovecs), gfp_mask); - if (unlikely(!bio)) + if (nr_vecs > UIO_MAXIOV) return NULL; - bio_init(bio, NULL, nr_iovecs ? bio->bi_inline_vecs : NULL, nr_iovecs, - 0); - bio->bi_pool = NULL; - return bio; + return kmalloc(struct_size(bio, bi_inline_vecs, nr_vecs), gfp_mask); } EXPORT_SYMBOL(bio_kmalloc); @@ -711,7 +740,7 @@ void bio_put(struct bio *bio) return; } - if (bio_flagged(bio, BIO_PERCPU_CACHE)) { + if (bio->bi_opf & REQ_ALLOC_CACHE) { struct bio_alloc_cache *cache; bio_uninit(bio); @@ -732,14 +761,15 @@ static int __bio_clone(struct bio *bio, struct bio *bio_src, gfp_t gfp) bio_set_flag(bio, BIO_CLONED); if (bio_flagged(bio_src, BIO_THROTTLED)) bio_set_flag(bio, BIO_THROTTLED); - if (bio->bi_bdev == bio_src->bi_bdev && - bio_flagged(bio_src, BIO_REMAPPED)) - bio_set_flag(bio, BIO_REMAPPED); bio->bi_ioprio = bio_src->bi_ioprio; bio->bi_iter = bio_src->bi_iter; - bio_clone_blkg_association(bio, bio_src); - blkcg_bio_issue_init(bio); + if (bio->bi_bdev) { + if (bio->bi_bdev == bio_src->bi_bdev && + bio_flagged(bio_src, BIO_REMAPPED)) + bio_set_flag(bio, BIO_REMAPPED); + bio_clone_blkg_association(bio, bio_src); + } if (bio_crypt_clone(bio, bio_src, gfp) < 0) return -ENOMEM; @@ -1727,55 +1757,13 @@ int bioset_init_from_src(struct bio_set *bs, struct bio_set *src) flags |= BIOSET_NEED_BVECS; if (src->rescue_workqueue) flags |= BIOSET_NEED_RESCUER; + if (src->cache) + flags |= BIOSET_PERCPU_CACHE; return bioset_init(bs, src->bio_pool.min_nr, src->front_pad, flags); } EXPORT_SYMBOL(bioset_init_from_src); -/** - * bio_alloc_kiocb - Allocate a bio from bio_set based on kiocb - * @kiocb: kiocb describing the IO - * @bdev: block device to allocate the bio for (can be %NULL) - * @nr_vecs: number of iovecs to pre-allocate - * @opf: operation and flags for bio - * @bs: bio_set to allocate from - * - * Description: - * Like @bio_alloc_bioset, but pass in the kiocb. The kiocb is only - * used to check if we should dip into the per-cpu bio_set allocation - * cache. The allocation uses GFP_KERNEL internally. On return, the - * bio is marked BIO_PERCPU_CACHEABLE, and the final put of the bio - * MUST be done from process context, not hard/soft IRQ. - * - */ -struct bio *bio_alloc_kiocb(struct kiocb *kiocb, struct block_device *bdev, - unsigned short nr_vecs, unsigned int opf, struct bio_set *bs) -{ - struct bio_alloc_cache *cache; - struct bio *bio; - - if (!(kiocb->ki_flags & IOCB_ALLOC_CACHE) || nr_vecs > BIO_INLINE_VECS) - return bio_alloc_bioset(bdev, nr_vecs, opf, GFP_KERNEL, bs); - - cache = per_cpu_ptr(bs->cache, get_cpu()); - if (cache->free_list) { - bio = cache->free_list; - cache->free_list = bio->bi_next; - cache->nr--; - put_cpu(); - bio_init(bio, bdev, nr_vecs ? bio->bi_inline_vecs : NULL, - nr_vecs, opf); - bio->bi_pool = bs; - bio_set_flag(bio, BIO_PERCPU_CACHE); - return bio; - } - put_cpu(); - bio = bio_alloc_bioset(bdev, nr_vecs, opf, GFP_KERNEL, bs); - bio_set_flag(bio, BIO_PERCPU_CACHE); - return bio; -} -EXPORT_SYMBOL_GPL(bio_alloc_kiocb); - static int __init init_bio(void) { int i; diff --git a/block/blk-cgroup-fc-appid.c b/block/blk-cgroup-fc-appid.c new file mode 100644 index 000000000000..760a2e1878dd --- /dev/null +++ b/block/blk-cgroup-fc-appid.c @@ -0,0 +1,57 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include "blk-cgroup.h" + +/** + * blkcg_set_fc_appid - set the fc_app_id field associted to blkcg + * @app_id: application identifier + * @cgrp_id: cgroup id + * @app_id_len: size of application identifier + */ +int blkcg_set_fc_appid(char *app_id, u64 cgrp_id, size_t app_id_len) +{ + struct cgroup *cgrp; + struct cgroup_subsys_state *css; + struct blkcg *blkcg; + int ret = 0; + + if (app_id_len > FC_APPID_LEN) + return -EINVAL; + + cgrp = cgroup_get_from_id(cgrp_id); + if (!cgrp) + return -ENOENT; + css = cgroup_get_e_css(cgrp, &io_cgrp_subsys); + if (!css) { + ret = -ENOENT; + goto out_cgrp_put; + } + blkcg = css_to_blkcg(css); + /* + * There is a slight race condition on setting the appid. + * Worst case an I/O may not find the right id. + * This is no different from the I/O we let pass while obtaining + * the vmid from the fabric. + * Adding the overhead of a lock is not necessary. + */ + strlcpy(blkcg->fc_app_id, app_id, app_id_len); + css_put(css); +out_cgrp_put: + cgroup_put(cgrp); + return ret; +} +EXPORT_SYMBOL_GPL(blkcg_set_fc_appid); + +/** + * blkcg_get_fc_appid - get the fc app identifier associated with a bio + * @bio: target bio + * + * On success return the fc_app_id, on failure return NULL + */ +char *blkcg_get_fc_appid(struct bio *bio) +{ + if (!bio->bi_blkg || bio->bi_blkg->blkcg->fc_app_id[0] == '\0') + return NULL; + return bio->bi_blkg->blkcg->fc_app_id; +} +EXPORT_SYMBOL_GPL(blkcg_get_fc_appid); diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c index 8dfe62786cd5..40161a3f68d0 100644 --- a/block/blk-cgroup.c +++ b/block/blk-cgroup.c @@ -59,6 +59,23 @@ static struct workqueue_struct *blkcg_punt_bio_wq; #define BLKG_DESTROY_BATCH_SIZE 64 +/** + * blkcg_css - find the current css + * + * Find the css associated with either the kthread or the current task. + * This may return a dying css, so it is up to the caller to use tryget logic + * to confirm it is alive and well. + */ +static struct cgroup_subsys_state *blkcg_css(void) +{ + struct cgroup_subsys_state *css; + + css = kthread_blkcg(); + if (css) + return css; + return task_css(current, io_cgrp_id); +} + static bool blkcg_policy_enabled(struct request_queue *q, const struct blkcg_policy *pol) { @@ -156,6 +173,33 @@ static void blkg_async_bio_workfn(struct work_struct *work) } /** + * bio_blkcg_css - return the blkcg CSS associated with a bio + * @bio: target bio + * + * This returns the CSS for the blkcg associated with a bio, or %NULL if not + * associated. Callers are expected to either handle %NULL or know association + * has been done prior to calling this. + */ +struct cgroup_subsys_state *bio_blkcg_css(struct bio *bio) +{ + if (!bio || !bio->bi_blkg) + return NULL; + return &bio->bi_blkg->blkcg->css; +} +EXPORT_SYMBOL_GPL(bio_blkcg_css); + +/** + * blkcg_parent - get the parent of a blkcg + * @blkcg: blkcg of interest + * + * Return the parent blkcg of @blkcg. Can be called anytime. + */ +static inline struct blkcg *blkcg_parent(struct blkcg *blkcg) +{ + return css_to_blkcg(blkcg->css.parent); +} + +/** * blkg_alloc - allocate a blkg * @blkcg: block cgroup the new blkg is associated with * @q: request_queue the new blkg is associated with @@ -254,7 +298,6 @@ static struct blkcg_gq *blkg_create(struct blkcg *blkcg, struct blkcg_gq *blkg; int i, ret; - WARN_ON_ONCE(!rcu_read_lock_held()); lockdep_assert_held(&q->queue_lock); /* request_queue is dying, do not create/recreate a blkg */ @@ -905,7 +948,6 @@ static void blkcg_print_one_stat(struct blkcg_gq *blkg, struct seq_file *s) { struct blkg_iostat_set *bis = &blkg->iostat; u64 rbytes, wbytes, rios, wios, dbytes, dios; - bool has_stats = false; const char *dname; unsigned seq; int i; @@ -931,14 +973,12 @@ static void blkcg_print_one_stat(struct blkcg_gq *blkg, struct seq_file *s) } while (u64_stats_fetch_retry(&bis->sync, seq)); if (rbytes || wbytes || rios || wios) { - has_stats = true; seq_printf(s, "rbytes=%llu wbytes=%llu rios=%llu wios=%llu dbytes=%llu dios=%llu", rbytes, wbytes, rios, wios, dbytes, dios); } if (blkcg_debug_stats && atomic_read(&blkg->use_delay)) { - has_stats = true; seq_printf(s, " use_delay=%d delay_nsec=%llu", atomic_read(&blkg->use_delay), atomic64_read(&blkg->delay_nsec)); @@ -950,12 +990,10 @@ static void blkcg_print_one_stat(struct blkcg_gq *blkg, struct seq_file *s) if (!blkg->pd[i] || !pol->pd_stat_fn) continue; - if (pol->pd_stat_fn(blkg->pd[i], s)) - has_stats = true; + pol->pd_stat_fn(blkg->pd[i], s); } - if (has_stats) - seq_printf(s, "\n"); + seq_puts(s, "\n"); } static int blkcg_print_stat(struct seq_file *sf, void *v) @@ -994,6 +1032,13 @@ static struct cftype blkcg_legacy_files[] = { { } /* terminate */ }; +#ifdef CONFIG_CGROUP_WRITEBACK +struct list_head *blkcg_get_cgwb_list(struct cgroup_subsys_state *css) +{ + return &css_to_blkcg(css)->cgwb_list; +} +#endif + /* * blkcg destruction is a three-stage process. * @@ -1016,25 +1061,6 @@ static struct cftype blkcg_legacy_files[] = { */ /** - * blkcg_css_offline - cgroup css_offline callback - * @css: css of interest - * - * This function is called when @css is about to go away. Here the cgwbs are - * offlined first and only once writeback associated with the blkcg has - * finished do we start step 2 (see above). - */ -static void blkcg_css_offline(struct cgroup_subsys_state *css) -{ - struct blkcg *blkcg = css_to_blkcg(css); - - /* this prevents anyone from attaching or migrating to this blkcg */ - wb_blkcg_offline(blkcg); - - /* put the base online pin allowing step 2 to be triggered */ - blkcg_unpin_online(blkcg); -} - -/** * blkcg_destroy_blkgs - responsible for shooting down blkgs * @blkcg: blkcg of interest * @@ -1045,7 +1071,7 @@ static void blkcg_css_offline(struct cgroup_subsys_state *css) * * This is the blkcg counterpart of ioc_release_fn(). */ -void blkcg_destroy_blkgs(struct blkcg *blkcg) +static void blkcg_destroy_blkgs(struct blkcg *blkcg) { might_sleep(); @@ -1075,6 +1101,57 @@ void blkcg_destroy_blkgs(struct blkcg *blkcg) spin_unlock_irq(&blkcg->lock); } +/** + * blkcg_pin_online - pin online state + * @blkcg_css: blkcg of interest + * + * While pinned, a blkcg is kept online. This is primarily used to + * impedance-match blkg and cgwb lifetimes so that blkg doesn't go offline + * while an associated cgwb is still active. + */ +void blkcg_pin_online(struct cgroup_subsys_state *blkcg_css) +{ + refcount_inc(&css_to_blkcg(blkcg_css)->online_pin); +} + +/** + * blkcg_unpin_online - unpin online state + * @blkcg_css: blkcg of interest + * + * This is primarily used to impedance-match blkg and cgwb lifetimes so + * that blkg doesn't go offline while an associated cgwb is still active. + * When this count goes to zero, all active cgwbs have finished so the + * blkcg can continue destruction by calling blkcg_destroy_blkgs(). + */ +void blkcg_unpin_online(struct cgroup_subsys_state *blkcg_css) +{ + struct blkcg *blkcg = css_to_blkcg(blkcg_css); + + do { + if (!refcount_dec_and_test(&blkcg->online_pin)) + break; + blkcg_destroy_blkgs(blkcg); + blkcg = blkcg_parent(blkcg); + } while (blkcg); +} + +/** + * blkcg_css_offline - cgroup css_offline callback + * @css: css of interest + * + * This function is called when @css is about to go away. Here the cgwbs are + * offlined first and only once writeback associated with the blkcg has + * finished do we start step 2 (see above). + */ +static void blkcg_css_offline(struct cgroup_subsys_state *css) +{ + /* this prevents anyone from attaching or migrating to this blkcg */ + wb_blkcg_offline(css); + + /* put the base online pin allowing step 2 to be triggered */ + blkcg_unpin_online(css); +} + static void blkcg_css_free(struct cgroup_subsys_state *css) { struct blkcg *blkcg = css_to_blkcg(css); @@ -1163,8 +1240,7 @@ unlock: static int blkcg_css_online(struct cgroup_subsys_state *css) { - struct blkcg *blkcg = css_to_blkcg(css); - struct blkcg *parent = blkcg_parent(blkcg); + struct blkcg *parent = blkcg_parent(css_to_blkcg(css)); /* * blkcg_pin_online() is used to delay blkcg offline so that blkgs @@ -1172,7 +1248,7 @@ static int blkcg_css_online(struct cgroup_subsys_state *css) * parent so that offline always happens towards the root. */ if (parent) - blkcg_pin_online(parent); + blkcg_pin_online(css); return 0; } @@ -1201,14 +1277,13 @@ int blkcg_init_queue(struct request_queue *q) preloaded = !radix_tree_preload(GFP_KERNEL); /* Make sure the root blkg exists. */ - rcu_read_lock(); + /* spin_lock_irq can serve as RCU read-side critical section. */ spin_lock_irq(&q->queue_lock); blkg = blkg_create(&blkcg_root, q, new_blkg); if (IS_ERR(blkg)) goto err_unlock; q->root_blkg = blkg; spin_unlock_irq(&q->queue_lock); - rcu_read_unlock(); if (preloaded) radix_tree_preload_end(); @@ -1234,7 +1309,6 @@ err_destroy_all: return ret; err_unlock: spin_unlock_irq(&q->queue_lock); - rcu_read_unlock(); if (preloaded) radix_tree_preload_end(); return PTR_ERR(blkg); @@ -1726,7 +1800,6 @@ static void blkcg_maybe_throttle_blkg(struct blkcg_gq *blkg, bool use_memdelay) void blkcg_maybe_throttle_current(void) { struct request_queue *q = current->throttle_queue; - struct cgroup_subsys_state *css; struct blkcg *blkcg; struct blkcg_gq *blkg; bool use_memdelay = current->use_memdelay; @@ -1738,12 +1811,7 @@ void blkcg_maybe_throttle_current(void) current->use_memdelay = false; rcu_read_lock(); - css = kthread_blkcg(); - if (css) - blkcg = css_to_blkcg(css); - else - blkcg = css_to_blkcg(task_css(current, io_cgrp_id)); - + blkcg = css_to_blkcg(blkcg_css()); if (!blkcg) goto out; blkg = blkg_lookup(blkcg, q); @@ -1889,7 +1957,7 @@ void bio_associate_blkg(struct bio *bio) rcu_read_lock(); if (bio->bi_blkg) - css = &bio_blkcg(bio)->css; + css = bio_blkcg_css(bio); else css = blkcg_css(); @@ -1950,6 +2018,22 @@ void blk_cgroup_bio_start(struct bio *bio) put_cpu(); } +bool blk_cgroup_congested(void) +{ + struct cgroup_subsys_state *css; + bool ret = false; + + rcu_read_lock(); + for (css = blkcg_css(); css; css = css->parent) { + if (atomic_read(&css->cgroup->congestion_count)) { + ret = true; + break; + } + } + rcu_read_unlock(); + return ret; +} + static int __init blkcg_init(void) { blkcg_punt_bio_wq = alloc_workqueue("blkcg_punt_bio", diff --git a/block/blk-cgroup.h b/block/blk-cgroup.h index 47e1e38390c9..d4de0a35e066 100644 --- a/block/blk-cgroup.h +++ b/block/blk-cgroup.h @@ -15,13 +15,101 @@ */ #include <linux/blk-cgroup.h> +#include <linux/cgroup.h> +#include <linux/kthread.h> #include <linux/blk-mq.h> +struct blkcg_gq; +struct blkg_policy_data; + + /* percpu_counter batch for blkg_[rw]stats, per-cpu drift doesn't matter */ #define BLKG_STAT_CPU_BATCH (INT_MAX / 2) #ifdef CONFIG_BLK_CGROUP +enum blkg_iostat_type { + BLKG_IOSTAT_READ, + BLKG_IOSTAT_WRITE, + BLKG_IOSTAT_DISCARD, + + BLKG_IOSTAT_NR, +}; + +struct blkg_iostat { + u64 bytes[BLKG_IOSTAT_NR]; + u64 ios[BLKG_IOSTAT_NR]; +}; + +struct blkg_iostat_set { + struct u64_stats_sync sync; + struct blkg_iostat cur; + struct blkg_iostat last; +}; + +/* association between a blk cgroup and a request queue */ +struct blkcg_gq { + /* Pointer to the associated request_queue */ + struct request_queue *q; + struct list_head q_node; + struct hlist_node blkcg_node; + struct blkcg *blkcg; + + /* all non-root blkcg_gq's are guaranteed to have access to parent */ + struct blkcg_gq *parent; + + /* reference count */ + struct percpu_ref refcnt; + + /* is this blkg online? protected by both blkcg and q locks */ + bool online; + + struct blkg_iostat_set __percpu *iostat_cpu; + struct blkg_iostat_set iostat; + + struct blkg_policy_data *pd[BLKCG_MAX_POLS]; + + spinlock_t async_bio_lock; + struct bio_list async_bios; + union { + struct work_struct async_bio_work; + struct work_struct free_work; + }; + + atomic_t use_delay; + atomic64_t delay_nsec; + atomic64_t delay_start; + u64 last_delay; + int last_use; + + struct rcu_head rcu_head; +}; + +struct blkcg { + struct cgroup_subsys_state css; + spinlock_t lock; + refcount_t online_pin; + + struct radix_tree_root blkg_tree; + struct blkcg_gq __rcu *blkg_hint; + struct hlist_head blkg_list; + + struct blkcg_policy_data *cpd[BLKCG_MAX_POLS]; + + struct list_head all_blkcgs_node; +#ifdef CONFIG_BLK_CGROUP_FC_APPID + char fc_app_id[FC_APPID_LEN]; +#endif +#ifdef CONFIG_CGROUP_WRITEBACK + struct list_head cgwb_list; +#endif +}; + +static inline struct blkcg *css_to_blkcg(struct cgroup_subsys_state *css) +{ + return css ? container_of(css, struct blkcg, css) : NULL; +} + /* * A blkcg_gq (blkg) is association between a block cgroup (blkcg) and a * request_queue (q). This is used by blkcg policies which need to track @@ -63,7 +151,7 @@ typedef void (blkcg_pol_online_pd_fn)(struct blkg_policy_data *pd); typedef void (blkcg_pol_offline_pd_fn)(struct blkg_policy_data *pd); typedef void (blkcg_pol_free_pd_fn)(struct blkg_policy_data *pd); typedef void (blkcg_pol_reset_pd_stats_fn)(struct blkg_policy_data *pd); -typedef bool (blkcg_pol_stat_pd_fn)(struct blkg_policy_data *pd, +typedef void (blkcg_pol_stat_pd_fn)(struct blkg_policy_data *pd, struct seq_file *s); struct blkcg_policy { @@ -123,52 +211,14 @@ int blkg_conf_prep(struct blkcg *blkcg, const struct blkcg_policy *pol, void blkg_conf_finish(struct blkg_conf_ctx *ctx); /** - * blkcg_css - find the current css - * - * Find the css associated with either the kthread or the current task. - * This may return a dying css, so it is up to the caller to use tryget logic - * to confirm it is alive and well. - */ -static inline struct cgroup_subsys_state *blkcg_css(void) -{ - struct cgroup_subsys_state *css; - - css = kthread_blkcg(); - if (css) - return css; - return task_css(current, io_cgrp_id); -} - -/** - * __bio_blkcg - internal, inconsistent version to get blkcg - * - * DO NOT USE. - * This function is inconsistent and consequently is dangerous to use. The - * first part of the function returns a blkcg where a reference is owned by the - * bio. This means it does not need to be rcu protected as it cannot go away - * with the bio owning a reference to it. However, the latter potentially gets - * it from task_css(). This can race against task migration and the cgroup - * dying. It is also semantically different as it must be called rcu protected - * and is susceptible to failure when trying to get a reference to it. - * Therefore, it is not ok to assume that *_get() will always succeed on the - * blkcg returned here. - */ -static inline struct blkcg *__bio_blkcg(struct bio *bio) -{ - if (bio && bio->bi_blkg) - return bio->bi_blkg->blkcg; - return css_to_blkcg(blkcg_css()); -} - -/** * bio_issue_as_root_blkg - see if this bio needs to be issued as root blkg * @return: true if this bio needs to be submitted with the root blkg context. * * In order to avoid priority inversions we sometimes need to issue a bio as if * it were attached to the root blkg, and then backcharge to the actual owning - * blkg. The idea is we do bio_blkcg() to look up the actual context for the - * bio and attach the appropriate blkg to the bio. Then we call this helper and - * if it is true run with the root blkg for that queue and then do any + * blkg. The idea is we do bio_blkcg_css() to look up the actual context for + * the bio and attach the appropriate blkg to the bio. Then we call this helper + * and if it is true run with the root blkg for that queue and then do any * backcharging to the originating cgroup once the io is complete. */ static inline bool bio_issue_as_root_blkg(struct bio *bio) @@ -457,7 +507,8 @@ struct blkcg_policy_data { struct blkcg_policy { }; -#ifdef CONFIG_BLOCK +struct blkcg { +}; static inline struct blkcg_gq *blkg_lookup(struct blkcg *blkcg, void *key) { return NULL; } static inline struct blkcg_gq *blk_queue_root_blkg(struct request_queue *q) @@ -471,8 +522,6 @@ static inline int blkcg_activate_policy(struct request_queue *q, static inline void blkcg_deactivate_policy(struct request_queue *q, const struct blkcg_policy *pol) { } -static inline struct blkcg *__bio_blkcg(struct bio *bio) { return NULL; } - static inline struct blkg_policy_data *blkg_to_pd(struct blkcg_gq *blkg, struct blkcg_policy *pol) { return NULL; } static inline struct blkcg_gq *pd_to_blkg(struct blkg_policy_data *pd) { return NULL; } @@ -488,7 +537,6 @@ static inline bool blk_cgroup_mergeable(struct request *rq, struct bio *bio) { r #define blk_queue_for_each_rl(rl, q) \ for ((rl) = &(q)->root_rl; (rl); (rl) = NULL) -#endif /* CONFIG_BLOCK */ #endif /* CONFIG_BLK_CGROUP */ #endif /* _BLK_CGROUP_PRIVATE_H */ diff --git a/block/blk-core.c b/block/blk-core.c index bc0506772152..80fa73c419a9 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -588,10 +588,9 @@ static inline int bio_check_eod(struct bio *bio) (nr_sectors > maxsector || bio->bi_iter.bi_sector > maxsector - nr_sectors)) { pr_info_ratelimited("%s: attempt to access beyond end of device\n" - "%pg: rw=%d, want=%llu, limit=%llu\n", - current->comm, - bio->bi_bdev, bio->bi_opf, - bio_end_sector(bio), maxsector); + "%pg: rw=%d, sector=%llu, nr_sectors = %u limit=%llu\n", + current->comm, bio->bi_bdev, bio->bi_opf, + bio->bi_iter.bi_sector, nr_sectors, maxsector); return -EIO; } return 0; @@ -816,11 +815,11 @@ void submit_bio_noacct(struct bio *bio) switch (bio_op(bio)) { case REQ_OP_DISCARD: - if (!blk_queue_discard(q)) + if (!bdev_max_discard_sectors(bdev)) goto not_supported; break; case REQ_OP_SECURE_ERASE: - if (!blk_queue_secure_erase(q)) + if (!bdev_max_secure_erase_sectors(bdev)) goto not_supported; break; case REQ_OP_ZONE_APPEND: @@ -889,19 +888,11 @@ void submit_bio(struct bio *bio) if (blkcg_punt_bio_submit(bio)) return; - /* - * If it's a regular read/write or a barrier with data attached, - * go through the normal accounting stuff before submission. - */ - if (bio_has_data(bio)) { - unsigned int count = bio_sectors(bio); - - if (op_is_write(bio_op(bio))) { - count_vm_events(PGPGOUT, count); - } else { - task_io_account_read(bio->bi_iter.bi_size); - count_vm_events(PGPGIN, count); - } + if (bio_op(bio) == REQ_OP_READ) { + task_io_account_read(bio->bi_iter.bi_size); + count_vm_events(PGPGIN, bio_sectors(bio)); + } else if (bio_op(bio) == REQ_OP_WRITE) { + count_vm_events(PGPGOUT, bio_sectors(bio)); } /* @@ -1018,21 +1009,22 @@ again: } } -static unsigned long __part_start_io_acct(struct block_device *part, - unsigned int sectors, unsigned int op, - unsigned long start_time) +unsigned long bdev_start_io_acct(struct block_device *bdev, + unsigned int sectors, unsigned int op, + unsigned long start_time) { const int sgrp = op_stat_group(op); part_stat_lock(); - update_io_ticks(part, start_time, false); - part_stat_inc(part, ios[sgrp]); - part_stat_add(part, sectors[sgrp], sectors); - part_stat_local_inc(part, in_flight[op_is_write(op)]); + update_io_ticks(bdev, start_time, false); + part_stat_inc(bdev, ios[sgrp]); + part_stat_add(bdev, sectors[sgrp], sectors); + part_stat_local_inc(bdev, in_flight[op_is_write(op)]); part_stat_unlock(); return start_time; } +EXPORT_SYMBOL(bdev_start_io_acct); /** * bio_start_io_acct_time - start I/O accounting for bio based drivers @@ -1041,8 +1033,8 @@ static unsigned long __part_start_io_acct(struct block_device *part, */ void bio_start_io_acct_time(struct bio *bio, unsigned long start_time) { - __part_start_io_acct(bio->bi_bdev, bio_sectors(bio), - bio_op(bio), start_time); + bdev_start_io_acct(bio->bi_bdev, bio_sectors(bio), + bio_op(bio), start_time); } EXPORT_SYMBOL_GPL(bio_start_io_acct_time); @@ -1054,46 +1046,33 @@ EXPORT_SYMBOL_GPL(bio_start_io_acct_time); */ unsigned long bio_start_io_acct(struct bio *bio) { - return __part_start_io_acct(bio->bi_bdev, bio_sectors(bio), - bio_op(bio), jiffies); + return bdev_start_io_acct(bio->bi_bdev, bio_sectors(bio), + bio_op(bio), jiffies); } EXPORT_SYMBOL_GPL(bio_start_io_acct); -unsigned long disk_start_io_acct(struct gendisk *disk, unsigned int sectors, - unsigned int op) -{ - return __part_start_io_acct(disk->part0, sectors, op, jiffies); -} -EXPORT_SYMBOL(disk_start_io_acct); - -static void __part_end_io_acct(struct block_device *part, unsigned int op, - unsigned long start_time) +void bdev_end_io_acct(struct block_device *bdev, unsigned int op, + unsigned long start_time) { const int sgrp = op_stat_group(op); unsigned long now = READ_ONCE(jiffies); unsigned long duration = now - start_time; part_stat_lock(); - update_io_ticks(part, now, true); - part_stat_add(part, nsecs[sgrp], jiffies_to_nsecs(duration)); - part_stat_local_dec(part, in_flight[op_is_write(op)]); + update_io_ticks(bdev, now, true); + part_stat_add(bdev, nsecs[sgrp], jiffies_to_nsecs(duration)); + part_stat_local_dec(bdev, in_flight[op_is_write(op)]); part_stat_unlock(); } +EXPORT_SYMBOL(bdev_end_io_acct); void bio_end_io_acct_remapped(struct bio *bio, unsigned long start_time, - struct block_device *orig_bdev) + struct block_device *orig_bdev) { - __part_end_io_acct(orig_bdev, bio_op(bio), start_time); + bdev_end_io_acct(orig_bdev, bio_op(bio), start_time); } EXPORT_SYMBOL_GPL(bio_end_io_acct_remapped); -void disk_end_io_acct(struct gendisk *disk, unsigned int op, - unsigned long start_time) -{ - __part_end_io_acct(disk->part0, op, start_time); -} -EXPORT_SYMBOL(disk_end_io_acct); - /** * blk_lld_busy - Check if underlying low-level drivers of a device are busy * @q : the queue of the device being checked diff --git a/block/blk-crypto-fallback.c b/block/blk-crypto-fallback.c index 7c854584b52b..621abd1b0e4d 100644 --- a/block/blk-crypto-fallback.c +++ b/block/blk-crypto-fallback.c @@ -152,23 +152,25 @@ static void blk_crypto_fallback_encrypt_endio(struct bio *enc_bio) src_bio->bi_status = enc_bio->bi_status; - bio_put(enc_bio); + bio_uninit(enc_bio); + kfree(enc_bio); bio_endio(src_bio); } static struct bio *blk_crypto_fallback_clone_bio(struct bio *bio_src) { + unsigned int nr_segs = bio_segments(bio_src); struct bvec_iter iter; struct bio_vec bv; struct bio *bio; - bio = bio_kmalloc(GFP_NOIO, bio_segments(bio_src)); + bio = bio_kmalloc(nr_segs, GFP_NOIO); if (!bio) return NULL; - bio->bi_bdev = bio_src->bi_bdev; + bio_init(bio, bio_src->bi_bdev, bio->bi_inline_vecs, nr_segs, + bio_src->bi_opf); if (bio_flagged(bio_src, BIO_REMAPPED)) bio_set_flag(bio, BIO_REMAPPED); - bio->bi_opf = bio_src->bi_opf; bio->bi_ioprio = bio_src->bi_ioprio; bio->bi_iter.bi_sector = bio_src->bi_iter.bi_sector; bio->bi_iter.bi_size = bio_src->bi_iter.bi_size; @@ -177,7 +179,6 @@ static struct bio *blk_crypto_fallback_clone_bio(struct bio *bio_src) bio->bi_io_vec[bio->bi_vcnt++] = bv; bio_clone_blkg_association(bio, bio_src); - blkcg_bio_issue_init(bio); return bio; } @@ -363,8 +364,8 @@ out_release_keyslot: blk_crypto_put_keyslot(slot); out_put_enc_bio: if (enc_bio) - bio_put(enc_bio); - + bio_uninit(enc_bio); + kfree(enc_bio); return ret; } diff --git a/block/blk-iocost.c b/block/blk-iocost.c index 9bd670999d0a..33a11ba971ea 100644 --- a/block/blk-iocost.c +++ b/block/blk-iocost.c @@ -533,8 +533,7 @@ struct ioc_gq { /* statistics */ struct iocg_pcpu_stat __percpu *pcpu_stat; - struct iocg_stat local_stat; - struct iocg_stat desc_stat; + struct iocg_stat stat; struct iocg_stat last_stat; u64 last_stat_abs_vusage; u64 usage_delta_us; @@ -1371,7 +1370,7 @@ static bool iocg_kick_delay(struct ioc_gq *iocg, struct ioc_now *now) return true; } else { if (iocg->indelay_since) { - iocg->local_stat.indelay_us += now->now - iocg->indelay_since; + iocg->stat.indelay_us += now->now - iocg->indelay_since; iocg->indelay_since = 0; } iocg->delay = 0; @@ -1419,7 +1418,7 @@ static void iocg_pay_debt(struct ioc_gq *iocg, u64 abs_vpay, /* if debt is paid in full, restore inuse */ if (!iocg->abs_vdebt) { - iocg->local_stat.indebt_us += now->now - iocg->indebt_since; + iocg->stat.indebt_us += now->now - iocg->indebt_since; iocg->indebt_since = 0; propagate_weights(iocg, iocg->active, iocg->last_inuse, @@ -1513,7 +1512,7 @@ static void iocg_kick_waitq(struct ioc_gq *iocg, bool pay_debt, if (!waitqueue_active(&iocg->waitq)) { if (iocg->wait_since) { - iocg->local_stat.wait_us += now->now - iocg->wait_since; + iocg->stat.wait_us += now->now - iocg->wait_since; iocg->wait_since = 0; } return; @@ -1641,11 +1640,30 @@ static void iocg_build_inner_walk(struct ioc_gq *iocg, } } +/* propagate the deltas to the parent */ +static void iocg_flush_stat_upward(struct ioc_gq *iocg) +{ + if (iocg->level > 0) { + struct iocg_stat *parent_stat = + &iocg->ancestors[iocg->level - 1]->stat; + + parent_stat->usage_us += + iocg->stat.usage_us - iocg->last_stat.usage_us; + parent_stat->wait_us += + iocg->stat.wait_us - iocg->last_stat.wait_us; + parent_stat->indebt_us += + iocg->stat.indebt_us - iocg->last_stat.indebt_us; + parent_stat->indelay_us += + iocg->stat.indelay_us - iocg->last_stat.indelay_us; + } + + iocg->last_stat = iocg->stat; +} + /* collect per-cpu counters and propagate the deltas to the parent */ -static void iocg_flush_stat_one(struct ioc_gq *iocg, struct ioc_now *now) +static void iocg_flush_stat_leaf(struct ioc_gq *iocg, struct ioc_now *now) { struct ioc *ioc = iocg->ioc; - struct iocg_stat new_stat; u64 abs_vusage = 0; u64 vusage_delta; int cpu; @@ -1661,34 +1679,9 @@ static void iocg_flush_stat_one(struct ioc_gq *iocg, struct ioc_now *now) iocg->last_stat_abs_vusage = abs_vusage; iocg->usage_delta_us = div64_u64(vusage_delta, ioc->vtime_base_rate); - iocg->local_stat.usage_us += iocg->usage_delta_us; - - /* propagate upwards */ - new_stat.usage_us = - iocg->local_stat.usage_us + iocg->desc_stat.usage_us; - new_stat.wait_us = - iocg->local_stat.wait_us + iocg->desc_stat.wait_us; - new_stat.indebt_us = - iocg->local_stat.indebt_us + iocg->desc_stat.indebt_us; - new_stat.indelay_us = - iocg->local_stat.indelay_us + iocg->desc_stat.indelay_us; - - /* propagate the deltas to the parent */ - if (iocg->level > 0) { - struct iocg_stat *parent_stat = - &iocg->ancestors[iocg->level - 1]->desc_stat; + iocg->stat.usage_us += iocg->usage_delta_us; - parent_stat->usage_us += - new_stat.usage_us - iocg->last_stat.usage_us; - parent_stat->wait_us += - new_stat.wait_us - iocg->last_stat.wait_us; - parent_stat->indebt_us += - new_stat.indebt_us - iocg->last_stat.indebt_us; - parent_stat->indelay_us += - new_stat.indelay_us - iocg->last_stat.indelay_us; - } - - iocg->last_stat = new_stat; + iocg_flush_stat_upward(iocg); } /* get stat counters ready for reading on all active iocgs */ @@ -1699,13 +1692,13 @@ static void iocg_flush_stat(struct list_head *target_iocgs, struct ioc_now *now) /* flush leaves and build inner node walk list */ list_for_each_entry(iocg, target_iocgs, active_list) { - iocg_flush_stat_one(iocg, now); + iocg_flush_stat_leaf(iocg, now); iocg_build_inner_walk(iocg, &inner_walk); } /* keep flushing upwards by walking the inner list backwards */ list_for_each_entry_safe_reverse(iocg, tiocg, &inner_walk, walk_list) { - iocg_flush_stat_one(iocg, now); + iocg_flush_stat_upward(iocg); list_del_init(&iocg->walk_list); } } @@ -2152,16 +2145,16 @@ static int ioc_check_iocgs(struct ioc *ioc, struct ioc_now *now) /* flush wait and indebt stat deltas */ if (iocg->wait_since) { - iocg->local_stat.wait_us += now->now - iocg->wait_since; + iocg->stat.wait_us += now->now - iocg->wait_since; iocg->wait_since = now->now; } if (iocg->indebt_since) { - iocg->local_stat.indebt_us += + iocg->stat.indebt_us += now->now - iocg->indebt_since; iocg->indebt_since = now->now; } if (iocg->indelay_since) { - iocg->local_stat.indelay_us += + iocg->stat.indelay_us += now->now - iocg->indelay_since; iocg->indelay_since = now->now; } @@ -3005,13 +2998,13 @@ static void ioc_pd_free(struct blkg_policy_data *pd) kfree(iocg); } -static bool ioc_pd_stat(struct blkg_policy_data *pd, struct seq_file *s) +static void ioc_pd_stat(struct blkg_policy_data *pd, struct seq_file *s) { struct ioc_gq *iocg = pd_to_iocg(pd); struct ioc *ioc = iocg->ioc; if (!ioc->enabled) - return false; + return; if (iocg->level == 0) { unsigned vp10k = DIV64_U64_ROUND_CLOSEST( @@ -3027,7 +3020,6 @@ static bool ioc_pd_stat(struct blkg_policy_data *pd, struct seq_file *s) iocg->last_stat.wait_us, iocg->last_stat.indebt_us, iocg->last_stat.indelay_us); - return true; } static u64 ioc_weight_prfill(struct seq_file *sf, struct blkg_policy_data *pd, diff --git a/block/blk-iolatency.c b/block/blk-iolatency.c index 2f33932e72e3..5b676c7cf2b6 100644 --- a/block/blk-iolatency.c +++ b/block/blk-iolatency.c @@ -891,7 +891,7 @@ static int iolatency_print_limit(struct seq_file *sf, void *v) return 0; } -static bool iolatency_ssd_stat(struct iolatency_grp *iolat, struct seq_file *s) +static void iolatency_ssd_stat(struct iolatency_grp *iolat, struct seq_file *s) { struct latency_stat stat; int cpu; @@ -914,17 +914,16 @@ static bool iolatency_ssd_stat(struct iolatency_grp *iolat, struct seq_file *s) (unsigned long long)stat.ps.missed, (unsigned long long)stat.ps.total, iolat->rq_depth.max_depth); - return true; } -static bool iolatency_pd_stat(struct blkg_policy_data *pd, struct seq_file *s) +static void iolatency_pd_stat(struct blkg_policy_data *pd, struct seq_file *s) { struct iolatency_grp *iolat = pd_to_lat(pd); unsigned long long avg_lat; unsigned long long cur_win; if (!blkcg_debug_stats) - return false; + return; if (iolat->ssd) return iolatency_ssd_stat(iolat, s); @@ -937,7 +936,6 @@ static bool iolatency_pd_stat(struct blkg_policy_data *pd, struct seq_file *s) else seq_printf(s, " depth=%u avg_lat=%llu win=%llu", iolat->rq_depth.max_depth, avg_lat, cur_win); - return true; } static struct blkg_policy_data *iolatency_pd_alloc(gfp_t gfp, diff --git a/block/blk-lib.c b/block/blk-lib.c index 237d60d8b585..09b7e1200c0f 100644 --- a/block/blk-lib.c +++ b/block/blk-lib.c @@ -10,30 +10,44 @@ #include "blk.h" +static sector_t bio_discard_limit(struct block_device *bdev, sector_t sector) +{ + unsigned int discard_granularity = bdev_discard_granularity(bdev); + sector_t granularity_aligned_sector; + + if (bdev_is_partition(bdev)) + sector += bdev->bd_start_sect; + + granularity_aligned_sector = + round_up(sector, discard_granularity >> SECTOR_SHIFT); + + /* + * Make sure subsequent bios start aligned to the discard granularity if + * it needs to be split. + */ + if (granularity_aligned_sector != sector) + return granularity_aligned_sector - sector; + + /* + * Align the bio size to the discard granularity to make splitting the bio + * at discard granularity boundaries easier in the driver if needed. + */ + return round_down(UINT_MAX, discard_granularity) >> SECTOR_SHIFT; +} + int __blkdev_issue_discard(struct block_device *bdev, sector_t sector, - sector_t nr_sects, gfp_t gfp_mask, int flags, - struct bio **biop) + sector_t nr_sects, gfp_t gfp_mask, struct bio **biop) { - struct request_queue *q = bdev_get_queue(bdev); struct bio *bio = *biop; - unsigned int op; - sector_t bs_mask, part_offset = 0; + sector_t bs_mask; if (bdev_read_only(bdev)) return -EPERM; - - if (flags & BLKDEV_DISCARD_SECURE) { - if (!blk_queue_secure_erase(q)) - return -EOPNOTSUPP; - op = REQ_OP_SECURE_ERASE; - } else { - if (!blk_queue_discard(q)) - return -EOPNOTSUPP; - op = REQ_OP_DISCARD; - } + if (!bdev_max_discard_sectors(bdev)) + return -EOPNOTSUPP; /* In case the discard granularity isn't set by buggy device driver */ - if (WARN_ON_ONCE(!q->limits.discard_granularity)) { + if (WARN_ON_ONCE(!bdev_discard_granularity(bdev))) { char dev_name[BDEVNAME_SIZE]; bdevname(bdev, dev_name); @@ -48,38 +62,11 @@ int __blkdev_issue_discard(struct block_device *bdev, sector_t sector, if (!nr_sects) return -EINVAL; - /* In case the discard request is in a partition */ - if (bdev_is_partition(bdev)) - part_offset = bdev->bd_start_sect; - while (nr_sects) { - sector_t granularity_aligned_lba, req_sects; - sector_t sector_mapped = sector + part_offset; - - granularity_aligned_lba = round_up(sector_mapped, - q->limits.discard_granularity >> SECTOR_SHIFT); - - /* - * Check whether the discard bio starts at a discard_granularity - * aligned LBA, - * - If no: set (granularity_aligned_lba - sector_mapped) to - * bi_size of the first split bio, then the second bio will - * start at a discard_granularity aligned LBA on the device. - * - If yes: use bio_aligned_discard_max_sectors() as the max - * possible bi_size of the first split bio. Then when this bio - * is split in device drive, the split ones are very probably - * to be aligned to discard_granularity of the device's queue. - */ - if (granularity_aligned_lba == sector_mapped) - req_sects = min_t(sector_t, nr_sects, - bio_aligned_discard_max_sectors(q)); - else - req_sects = min_t(sector_t, nr_sects, - granularity_aligned_lba - sector_mapped); - - WARN_ON_ONCE((req_sects << 9) > UINT_MAX); + sector_t req_sects = + min(nr_sects, bio_discard_limit(bdev, sector)); - bio = blk_next_bio(bio, bdev, 0, op, gfp_mask); + bio = blk_next_bio(bio, bdev, 0, REQ_OP_DISCARD, gfp_mask); bio->bi_iter.bi_sector = sector; bio->bi_iter.bi_size = req_sects << 9; sector += req_sects; @@ -105,21 +92,19 @@ EXPORT_SYMBOL(__blkdev_issue_discard); * @sector: start sector * @nr_sects: number of sectors to discard * @gfp_mask: memory allocation flags (for bio_alloc) - * @flags: BLKDEV_DISCARD_* flags to control behaviour * * Description: * Issue a discard request for the sectors in question. */ int blkdev_issue_discard(struct block_device *bdev, sector_t sector, - sector_t nr_sects, gfp_t gfp_mask, unsigned long flags) + sector_t nr_sects, gfp_t gfp_mask) { struct bio *bio = NULL; struct blk_plug plug; int ret; blk_start_plug(&plug); - ret = __blkdev_issue_discard(bdev, sector, nr_sects, gfp_mask, flags, - &bio); + ret = __blkdev_issue_discard(bdev, sector, nr_sects, gfp_mask, &bio); if (!ret && bio) { ret = submit_bio_wait(bio); if (ret == -EOPNOTSUPP) @@ -316,3 +301,42 @@ retry: return ret; } EXPORT_SYMBOL(blkdev_issue_zeroout); + +int blkdev_issue_secure_erase(struct block_device *bdev, sector_t sector, + sector_t nr_sects, gfp_t gfp) +{ + sector_t bs_mask = (bdev_logical_block_size(bdev) >> 9) - 1; + unsigned int max_sectors = bdev_max_secure_erase_sectors(bdev); + struct bio *bio = NULL; + struct blk_plug plug; + int ret = 0; + + if (max_sectors == 0) + return -EOPNOTSUPP; + if ((sector | nr_sects) & bs_mask) + return -EINVAL; + if (bdev_read_only(bdev)) + return -EPERM; + + blk_start_plug(&plug); + for (;;) { + unsigned int len = min_t(sector_t, nr_sects, max_sectors); + + bio = blk_next_bio(bio, bdev, 0, REQ_OP_SECURE_ERASE, gfp); + bio->bi_iter.bi_sector = sector; + bio->bi_iter.bi_size = len; + + sector += len << SECTOR_SHIFT; + nr_sects -= len << SECTOR_SHIFT; + if (!nr_sects) { + ret = submit_bio_wait(bio); + bio_put(bio); + break; + } + cond_resched(); + } + blk_finish_plug(&plug); + + return ret; +} +EXPORT_SYMBOL(blkdev_issue_secure_erase); diff --git a/block/blk-map.c b/block/blk-map.c index c7f71d83eff1..df8b066cd548 100644 --- a/block/blk-map.c +++ b/block/blk-map.c @@ -152,10 +152,10 @@ static int bio_copy_user_iov(struct request *rq, struct rq_map_data *map_data, nr_pages = bio_max_segs(DIV_ROUND_UP(offset + len, PAGE_SIZE)); ret = -ENOMEM; - bio = bio_kmalloc(gfp_mask, nr_pages); + bio = bio_kmalloc(nr_pages, gfp_mask); if (!bio) goto out_bmd; - bio->bi_opf |= req_op(rq); + bio_init(bio, NULL, bio->bi_inline_vecs, nr_pages, req_op(rq)); if (map_data) { nr_pages = 1 << map_data->page_order; @@ -224,7 +224,8 @@ static int bio_copy_user_iov(struct request *rq, struct rq_map_data *map_data, cleanup: if (!map_data) bio_free_pages(bio); - bio_put(bio); + bio_uninit(bio); + kfree(bio); out_bmd: kfree(bmd); return ret; @@ -234,6 +235,7 @@ static int bio_map_user_iov(struct request *rq, struct iov_iter *iter, gfp_t gfp_mask) { unsigned int max_sectors = queue_max_hw_sectors(rq->q); + unsigned int nr_vecs = iov_iter_npages(iter, BIO_MAX_VECS); struct bio *bio; int ret; int j; @@ -241,10 +243,10 @@ static int bio_map_user_iov(struct request *rq, struct iov_iter *iter, if (!iov_iter_count(iter)) return -EINVAL; - bio = bio_kmalloc(gfp_mask, iov_iter_npages(iter, BIO_MAX_VECS)); + bio = bio_kmalloc(nr_vecs, gfp_mask); if (!bio) return -ENOMEM; - bio->bi_opf |= req_op(rq); + bio_init(bio, NULL, bio->bi_inline_vecs, nr_vecs, req_op(rq)); while (iov_iter_count(iter)) { struct page **pages; @@ -260,10 +262,9 @@ static int bio_map_user_iov(struct request *rq, struct iov_iter *iter, npages = DIV_ROUND_UP(offs + bytes, PAGE_SIZE); - if (unlikely(offs & queue_dma_alignment(rq->q))) { - ret = -EINVAL; + if (unlikely(offs & queue_dma_alignment(rq->q))) j = 0; - } else { + else { for (j = 0; j < npages; j++) { struct page *page = pages[j]; unsigned int n = PAGE_SIZE - offs; @@ -303,7 +304,8 @@ static int bio_map_user_iov(struct request *rq, struct iov_iter *iter, out_unmap: bio_release_pages(bio, false); - bio_put(bio); + bio_uninit(bio); + kfree(bio); return ret; } @@ -323,7 +325,8 @@ static void bio_invalidate_vmalloc_pages(struct bio *bio) static void bio_map_kern_endio(struct bio *bio) { bio_invalidate_vmalloc_pages(bio); - bio_put(bio); + bio_uninit(bio); + kfree(bio); } /** @@ -348,9 +351,10 @@ static struct bio *bio_map_kern(struct request_queue *q, void *data, int offset, i; struct bio *bio; - bio = bio_kmalloc(gfp_mask, nr_pages); + bio = bio_kmalloc(nr_pages, gfp_mask); if (!bio) return ERR_PTR(-ENOMEM); + bio_init(bio, NULL, bio->bi_inline_vecs, nr_pages, 0); if (is_vmalloc) { flush_kernel_vmap_range(data, len); @@ -374,7 +378,8 @@ static struct bio *bio_map_kern(struct request_queue *q, void *data, if (bio_add_pc_page(q, bio, page, bytes, offset) < bytes) { /* we don't support partial mappings */ - bio_put(bio); + bio_uninit(bio); + kfree(bio); return ERR_PTR(-EINVAL); } @@ -390,7 +395,8 @@ static struct bio *bio_map_kern(struct request_queue *q, void *data, static void bio_copy_kern_endio(struct bio *bio) { bio_free_pages(bio); - bio_put(bio); + bio_uninit(bio); + kfree(bio); } static void bio_copy_kern_endio_read(struct bio *bio) @@ -435,9 +441,10 @@ static struct bio *bio_copy_kern(struct request_queue *q, void *data, return ERR_PTR(-EINVAL); nr_pages = end - start; - bio = bio_kmalloc(gfp_mask, nr_pages); + bio = bio_kmalloc(nr_pages, gfp_mask); if (!bio) return ERR_PTR(-ENOMEM); + bio_init(bio, NULL, bio->bi_inline_vecs, nr_pages, 0); while (len) { struct page *page; @@ -471,7 +478,8 @@ static struct bio *bio_copy_kern(struct request_queue *q, void *data, cleanup: bio_free_pages(bio); - bio_put(bio); + bio_uninit(bio); + kfree(bio); return ERR_PTR(-ENOMEM); } @@ -602,7 +610,8 @@ int blk_rq_unmap_user(struct bio *bio) next_bio = bio; bio = bio->bi_next; - bio_put(next_bio); + bio_uninit(next_bio); + kfree(next_bio); } return ret; @@ -648,8 +657,10 @@ int blk_rq_map_kern(struct request_queue *q, struct request *rq, void *kbuf, bio->bi_opf |= req_op(rq); ret = blk_rq_append_bio(rq, bio); - if (unlikely(ret)) - bio_put(bio); + if (unlikely(ret)) { + bio_uninit(bio); + kfree(bio); + } return ret; } EXPORT_SYMBOL(blk_rq_map_kern); diff --git a/block/blk-mq-debugfs.c b/block/blk-mq-debugfs.c index aa0349e9f083..7e4136a60e1c 100644 --- a/block/blk-mq-debugfs.c +++ b/block/blk-mq-debugfs.c @@ -113,10 +113,8 @@ static const char *const blk_queue_flag_name[] = { QUEUE_FLAG_NAME(FAIL_IO), QUEUE_FLAG_NAME(NONROT), QUEUE_FLAG_NAME(IO_STAT), - QUEUE_FLAG_NAME(DISCARD), QUEUE_FLAG_NAME(NOXMERGES), QUEUE_FLAG_NAME(ADD_RANDOM), - QUEUE_FLAG_NAME(SECERASE), QUEUE_FLAG_NAME(SAME_FORCE), QUEUE_FLAG_NAME(DEAD), QUEUE_FLAG_NAME(INIT_DONE), diff --git a/block/blk-mq.c b/block/blk-mq.c index 84d749511f55..ae116b755648 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -1083,7 +1083,7 @@ bool blk_mq_complete_request_remote(struct request *rq) WRITE_ONCE(rq->state, MQ_RQ_COMPLETE); /* - * For a polled request, always complete locallly, it's pointless + * For a polled request, always complete locally, it's pointless * to redirect the completion. */ if (rq->cmd_flags & REQ_POLLED) @@ -1169,6 +1169,62 @@ static void blk_end_sync_rq(struct request *rq, blk_status_t error) complete(waiting); } +/* + * Allow 2x BLK_MAX_REQUEST_COUNT requests on plug queue for multiple + * queues. This is important for md arrays to benefit from merging + * requests. + */ +static inline unsigned short blk_plug_max_rq_count(struct blk_plug *plug) +{ + if (plug->multiple_queues) + return BLK_MAX_REQUEST_COUNT * 2; + return BLK_MAX_REQUEST_COUNT; +} + +static void blk_add_rq_to_plug(struct blk_plug *plug, struct request *rq) +{ + struct request *last = rq_list_peek(&plug->mq_list); + + if (!plug->rq_count) { + trace_block_plug(rq->q); + } else if (plug->rq_count >= blk_plug_max_rq_count(plug) || + (!blk_queue_nomerges(rq->q) && + blk_rq_bytes(last) >= BLK_PLUG_FLUSH_SIZE)) { + blk_mq_flush_plug_list(plug, false); + trace_block_plug(rq->q); + } + + if (!plug->multiple_queues && last && last->q != rq->q) + plug->multiple_queues = true; + if (!plug->has_elevator && (rq->rq_flags & RQF_ELV)) + plug->has_elevator = true; + rq->rq_next = NULL; + rq_list_add(&plug->mq_list, rq); + plug->rq_count++; +} + +static void __blk_execute_rq_nowait(struct request *rq, bool at_head, + rq_end_io_fn *done, bool use_plug) +{ + WARN_ON(irqs_disabled()); + WARN_ON(!blk_rq_is_passthrough(rq)); + + rq->end_io = done; + + blk_account_io_start(rq); + + if (use_plug && current->plug) { + blk_add_rq_to_plug(current->plug, rq); + return; + } + /* + * don't check dying flag for MQ because the request won't + * be reused after dying flag is set + */ + blk_mq_sched_insert_request(rq, at_head, true, false); +} + + /** * blk_execute_rq_nowait - insert a request to I/O scheduler for execution * @rq: request to insert @@ -1184,18 +1240,8 @@ static void blk_end_sync_rq(struct request *rq, blk_status_t error) */ void blk_execute_rq_nowait(struct request *rq, bool at_head, rq_end_io_fn *done) { - WARN_ON(irqs_disabled()); - WARN_ON(!blk_rq_is_passthrough(rq)); + __blk_execute_rq_nowait(rq, at_head, done, true); - rq->end_io = done; - - blk_account_io_start(rq); - - /* - * don't check dying flag for MQ because the request won't - * be reused after dying flag is set - */ - blk_mq_sched_insert_request(rq, at_head, true, false); } EXPORT_SYMBOL_GPL(blk_execute_rq_nowait); @@ -1233,8 +1279,13 @@ blk_status_t blk_execute_rq(struct request *rq, bool at_head) DECLARE_COMPLETION_ONSTACK(wait); unsigned long hang_check; + /* + * iopoll requires request to be submitted to driver, so can't + * use plug + */ rq->end_io_data = &wait; - blk_execute_rq_nowait(rq, at_head, blk_end_sync_rq); + __blk_execute_rq_nowait(rq, at_head, blk_end_sync_rq, + !blk_rq_is_poll(rq)); /* Prevent hang_check timer from firing at us during very long I/O */ hang_check = sysctl_hung_task_timeout_secs; @@ -2676,40 +2727,6 @@ void blk_mq_try_issue_list_directly(struct blk_mq_hw_ctx *hctx, hctx->queue->mq_ops->commit_rqs(hctx); } -/* - * Allow 2x BLK_MAX_REQUEST_COUNT requests on plug queue for multiple - * queues. This is important for md arrays to benefit from merging - * requests. - */ -static inline unsigned short blk_plug_max_rq_count(struct blk_plug *plug) -{ - if (plug->multiple_queues) - return BLK_MAX_REQUEST_COUNT * 2; - return BLK_MAX_REQUEST_COUNT; -} - -static void blk_add_rq_to_plug(struct blk_plug *plug, struct request *rq) -{ - struct request *last = rq_list_peek(&plug->mq_list); - - if (!plug->rq_count) { - trace_block_plug(rq->q); - } else if (plug->rq_count >= blk_plug_max_rq_count(plug) || - (!blk_queue_nomerges(rq->q) && - blk_rq_bytes(last) >= BLK_PLUG_FLUSH_SIZE)) { - blk_mq_flush_plug_list(plug, false); - trace_block_plug(rq->q); - } - - if (!plug->multiple_queues && last && last->q != rq->q) - plug->multiple_queues = true; - if (!plug->has_elevator && (rq->rq_flags & RQF_ELV)) - plug->has_elevator = true; - rq->rq_next = NULL; - rq_list_add(&plug->mq_list, rq); - plug->rq_count++; -} - static bool blk_mq_attempt_bio_merge(struct request_queue *q, struct bio *bio, unsigned int nr_segs) { diff --git a/block/blk-settings.c b/block/blk-settings.c index b83df3d2eebc..6ccceb421ed2 100644 --- a/block/blk-settings.c +++ b/block/blk-settings.c @@ -46,6 +46,7 @@ void blk_set_default_limits(struct queue_limits *lim) lim->max_zone_append_sectors = 0; lim->max_discard_sectors = 0; lim->max_hw_discard_sectors = 0; + lim->max_secure_erase_sectors = 0; lim->discard_granularity = 0; lim->discard_alignment = 0; lim->discard_misaligned = 0; @@ -177,6 +178,18 @@ void blk_queue_max_discard_sectors(struct request_queue *q, EXPORT_SYMBOL(blk_queue_max_discard_sectors); /** + * blk_queue_max_secure_erase_sectors - set max sectors for a secure erase + * @q: the request queue for the device + * @max_sectors: maximum number of sectors to secure_erase + **/ +void blk_queue_max_secure_erase_sectors(struct request_queue *q, + unsigned int max_sectors) +{ + q->limits.max_secure_erase_sectors = max_sectors; +} +EXPORT_SYMBOL(blk_queue_max_secure_erase_sectors); + +/** * blk_queue_max_write_zeroes_sectors - set max sectors for a single * write zeroes * @q: the request queue for the device @@ -468,6 +481,40 @@ void blk_queue_io_opt(struct request_queue *q, unsigned int opt) } EXPORT_SYMBOL(blk_queue_io_opt); +static int queue_limit_alignment_offset(struct queue_limits *lim, + sector_t sector) +{ + unsigned int granularity = max(lim->physical_block_size, lim->io_min); + unsigned int alignment = sector_div(sector, granularity >> SECTOR_SHIFT) + << SECTOR_SHIFT; + + return (granularity + lim->alignment_offset - alignment) % granularity; +} + +static unsigned int queue_limit_discard_alignment(struct queue_limits *lim, + sector_t sector) +{ + unsigned int alignment, granularity, offset; + + if (!lim->max_discard_sectors) + return 0; + + /* Why are these in bytes, not sectors? */ + alignment = lim->discard_alignment >> SECTOR_SHIFT; + granularity = lim->discard_granularity >> SECTOR_SHIFT; + if (!granularity) + return 0; + + /* Offset of the partition start in 'granularity' sectors */ + offset = sector_div(sector, granularity); + + /* And why do we do this modulus *again* in blkdev_issue_discard()? */ + offset = (granularity + alignment - offset) % granularity; + + /* Turn it back into bytes, gaah */ + return offset << SECTOR_SHIFT; +} + static unsigned int blk_round_down_sectors(unsigned int sectors, unsigned int lbs) { sectors = round_down(sectors, lbs >> SECTOR_SHIFT); @@ -627,7 +674,8 @@ int blk_stack_limits(struct queue_limits *t, struct queue_limits *b, t->discard_alignment = lcm_not_zero(t->discard_alignment, alignment) % t->discard_granularity; } - + t->max_secure_erase_sectors = min_not_zero(t->max_secure_erase_sectors, + b->max_secure_erase_sectors); t->zone_write_granularity = max(t->zone_write_granularity, b->zone_write_granularity); t->zoned = max(t->zoned, b->zoned); @@ -901,3 +949,27 @@ void blk_queue_set_zoned(struct gendisk *disk, enum blk_zoned_model model) } } EXPORT_SYMBOL_GPL(blk_queue_set_zoned); + +int bdev_alignment_offset(struct block_device *bdev) +{ + struct request_queue *q = bdev_get_queue(bdev); + + if (q->limits.misaligned) + return -1; + if (bdev_is_partition(bdev)) + return queue_limit_alignment_offset(&q->limits, + bdev->bd_start_sect); + return q->limits.alignment_offset; +} +EXPORT_SYMBOL_GPL(bdev_alignment_offset); + +unsigned int bdev_discard_alignment(struct block_device *bdev) +{ + struct request_queue *q = bdev_get_queue(bdev); + + if (bdev_is_partition(bdev)) + return queue_limit_discard_alignment(&q->limits, + bdev->bd_start_sect); + return q->limits.discard_alignment; +} +EXPORT_SYMBOL_GPL(bdev_discard_alignment); diff --git a/block/blk-throttle.c b/block/blk-throttle.c index 469c483719be..139b2d7a99e2 100644 --- a/block/blk-throttle.c +++ b/block/blk-throttle.c @@ -227,7 +227,7 @@ static unsigned int tg_iops_limit(struct throtl_grp *tg, int rw) break; \ if ((__tg)) { \ blk_add_cgroup_trace_msg(__td->queue, \ - tg_to_blkg(__tg)->blkcg, "throtl " fmt, ##args);\ + &tg_to_blkg(__tg)->blkcg->css, "throtl " fmt, ##args);\ } else { \ blk_add_trace_msg(__td->queue, "throtl " fmt, ##args); \ } \ @@ -2189,13 +2189,14 @@ again: } out_unlock: - spin_unlock_irq(&q->queue_lock); bio_set_flag(bio, BIO_THROTTLED); #ifdef CONFIG_BLK_DEV_THROTTLING_LOW if (throttled || !td->track_bio_latency) bio->bi_issue.value |= BIO_ISSUE_THROTL_SKIP_LATENCY; #endif + spin_unlock_irq(&q->queue_lock); + rcu_read_unlock(); return throttled; } diff --git a/block/blk.h b/block/blk.h index 8ccbc6e07636..434017701403 100644 --- a/block/blk.h +++ b/block/blk.h @@ -347,20 +347,6 @@ static inline unsigned int bio_allowed_max_sectors(struct request_queue *q) } /* - * The max bio size which is aligned to q->limits.discard_granularity. This - * is a hint to split large discard bio in generic block layer, then if device - * driver needs to split the discard bio into smaller ones, their bi_size can - * be very probably and easily aligned to discard_granularity of the device's - * queue. - */ -static inline unsigned int bio_aligned_discard_max_sectors( - struct request_queue *q) -{ - return round_down(UINT_MAX, q->limits.discard_granularity) >> - SECTOR_SHIFT; -} - -/* * Internal io_context interface */ struct io_cq *ioc_find_get_icq(struct request_queue *q); @@ -450,13 +436,6 @@ extern struct device_attribute dev_attr_events; extern struct device_attribute dev_attr_events_async; extern struct device_attribute dev_attr_events_poll_msecs; -static inline void bio_clear_polled(struct bio *bio) -{ - /* can't support alloc cache if we turn off polling */ - bio_clear_flag(bio, BIO_PERCPU_CACHE); - bio->bi_opf &= ~REQ_POLLED; -} - long blkdev_ioctl(struct file *file, unsigned cmd, unsigned long arg); long compat_blkdev_ioctl(struct file *file, unsigned cmd, unsigned long arg); diff --git a/block/bounce.c b/block/bounce.c index 467be46d0e65..8f7b6fe3b4db 100644 --- a/block/bounce.c +++ b/block/bounce.c @@ -191,7 +191,6 @@ static struct bio *bounce_clone_bio(struct bio *bio_src) goto err_put; bio_clone_blkg_association(bio, bio_src); - blkcg_bio_issue_init(bio); return bio; diff --git a/block/fops.c b/block/fops.c index 9f2ecec406b0..b9b83030e0df 100644 --- a/block/fops.c +++ b/block/fops.c @@ -44,14 +44,6 @@ static unsigned int dio_bio_write_op(struct kiocb *iocb) #define DIO_INLINE_BIO_VECS 4 -static void blkdev_bio_end_io_simple(struct bio *bio) -{ - struct task_struct *waiter = bio->bi_private; - - WRITE_ONCE(bio->bi_private, NULL); - blk_wake_io_task(waiter); -} - static ssize_t __blkdev_direct_IO_simple(struct kiocb *iocb, struct iov_iter *iter, unsigned int nr_pages) { @@ -83,8 +75,6 @@ static ssize_t __blkdev_direct_IO_simple(struct kiocb *iocb, bio_init(&bio, bdev, vecs, nr_pages, dio_bio_write_op(iocb)); } bio.bi_iter.bi_sector = pos >> SECTOR_SHIFT; - bio.bi_private = current; - bio.bi_end_io = blkdev_bio_end_io_simple; bio.bi_ioprio = iocb->ki_ioprio; ret = bio_iov_iter_get_pages(&bio, iter); @@ -97,18 +87,8 @@ static ssize_t __blkdev_direct_IO_simple(struct kiocb *iocb, if (iocb->ki_flags & IOCB_NOWAIT) bio.bi_opf |= REQ_NOWAIT; - if (iocb->ki_flags & IOCB_HIPRI) - bio_set_polled(&bio, iocb); - submit_bio(&bio); - for (;;) { - set_current_state(TASK_UNINTERRUPTIBLE); - if (!READ_ONCE(bio.bi_private)) - break; - if (!(iocb->ki_flags & IOCB_HIPRI) || !bio_poll(&bio, NULL, 0)) - blk_io_schedule(); - } - __set_current_state(TASK_RUNNING); + submit_bio_wait(&bio); bio_release_pages(&bio, should_dirty); if (unlikely(bio.bi_status)) @@ -197,8 +177,10 @@ static ssize_t __blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter, (bdev_logical_block_size(bdev) - 1)) return -EINVAL; - bio = bio_alloc_kiocb(iocb, bdev, nr_pages, opf, &blkdev_dio_pool); - + if (iocb->ki_flags & IOCB_ALLOC_CACHE) + opf |= REQ_ALLOC_CACHE; + bio = bio_alloc_bioset(bdev, nr_pages, opf, GFP_KERNEL, + &blkdev_dio_pool); dio = container_of(bio, struct blkdev_dio, bio); atomic_set(&dio->ref, 1); /* @@ -320,7 +302,10 @@ static ssize_t __blkdev_direct_IO_async(struct kiocb *iocb, (bdev_logical_block_size(bdev) - 1)) return -EINVAL; - bio = bio_alloc_kiocb(iocb, bdev, nr_pages, opf, &blkdev_dio_pool); + if (iocb->ki_flags & IOCB_ALLOC_CACHE) + opf |= REQ_ALLOC_CACHE; + bio = bio_alloc_bioset(bdev, nr_pages, opf, GFP_KERNEL, + &blkdev_dio_pool); dio = container_of(bio, struct blkdev_dio, bio); dio->flags = 0; dio->iocb = iocb; @@ -672,7 +657,7 @@ static long blkdev_fallocate(struct file *file, int mode, loff_t start, break; case FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE | FALLOC_FL_NO_HIDE_STALE: error = blkdev_issue_discard(bdev, start >> SECTOR_SHIFT, - len >> SECTOR_SHIFT, GFP_KERNEL, 0); + len >> SECTOR_SHIFT, GFP_KERNEL); break; default: error = -EOPNOTSUPP; diff --git a/block/genhd.c b/block/genhd.c index b8b6759d670f..36532b931841 100644 --- a/block/genhd.c +++ b/block/genhd.c @@ -1010,7 +1010,7 @@ static ssize_t disk_alignment_offset_show(struct device *dev, { struct gendisk *disk = dev_to_disk(dev); - return sprintf(buf, "%d\n", queue_alignment_offset(disk->queue)); + return sprintf(buf, "%d\n", bdev_alignment_offset(disk->part0)); } static ssize_t disk_discard_alignment_show(struct device *dev, @@ -1019,7 +1019,7 @@ static ssize_t disk_discard_alignment_show(struct device *dev, { struct gendisk *disk = dev_to_disk(dev); - return sprintf(buf, "%d\n", queue_discard_alignment(disk->queue)); + return sprintf(buf, "%d\n", bdev_alignment_offset(disk->part0)); } static ssize_t diskseq_show(struct device *dev, diff --git a/block/ioctl.c b/block/ioctl.c index f8703db99c73..46949f1b0dba 100644 --- a/block/ioctl.c +++ b/block/ioctl.c @@ -83,18 +83,17 @@ static int compat_blkpg_ioctl(struct block_device *bdev, #endif static int blk_ioctl_discard(struct block_device *bdev, fmode_t mode, - unsigned long arg, unsigned long flags) + unsigned long arg) { uint64_t range[2]; uint64_t start, len; - struct request_queue *q = bdev_get_queue(bdev); struct inode *inode = bdev->bd_inode; int err; if (!(mode & FMODE_WRITE)) return -EBADF; - if (!blk_queue_discard(q)) + if (!bdev_max_discard_sectors(bdev)) return -EOPNOTSUPP; if (copy_from_user(range, (void __user *)arg, sizeof(range))) @@ -115,15 +114,43 @@ static int blk_ioctl_discard(struct block_device *bdev, fmode_t mode, err = truncate_bdev_range(bdev, mode, start, start + len - 1); if (err) goto fail; - - err = blkdev_issue_discard(bdev, start >> 9, len >> 9, - GFP_KERNEL, flags); - + err = blkdev_issue_discard(bdev, start >> 9, len >> 9, GFP_KERNEL); fail: filemap_invalidate_unlock(inode->i_mapping); return err; } +static int blk_ioctl_secure_erase(struct block_device *bdev, fmode_t mode, + void __user *argp) +{ + uint64_t start, len; + uint64_t range[2]; + int err; + + if (!(mode & FMODE_WRITE)) + return -EBADF; + if (!bdev_max_secure_erase_sectors(bdev)) + return -EOPNOTSUPP; + if (copy_from_user(range, argp, sizeof(range))) + return -EFAULT; + + start = range[0]; + len = range[1]; + if ((start & 511) || (len & 511)) + return -EINVAL; + if (start + len > bdev_nr_bytes(bdev)) + return -EINVAL; + + filemap_invalidate_lock(bdev->bd_inode->i_mapping); + err = truncate_bdev_range(bdev, mode, start, start + len - 1); + if (!err) + err = blkdev_issue_secure_erase(bdev, start >> 9, len >> 9, + GFP_KERNEL); + filemap_invalidate_unlock(bdev->bd_inode->i_mapping); + return err; +} + + static int blk_ioctl_zeroout(struct block_device *bdev, fmode_t mode, unsigned long arg) { @@ -451,10 +478,9 @@ static int blkdev_common_ioctl(struct block_device *bdev, fmode_t mode, case BLKROSET: return blkdev_roset(bdev, mode, cmd, arg); case BLKDISCARD: - return blk_ioctl_discard(bdev, mode, arg, 0); + return blk_ioctl_discard(bdev, mode, arg); case BLKSECDISCARD: - return blk_ioctl_discard(bdev, mode, arg, - BLKDEV_DISCARD_SECURE); + return blk_ioctl_secure_erase(bdev, mode, argp); case BLKZEROOUT: return blk_ioctl_zeroout(bdev, mode, arg); case BLKGETDISKSEQ: @@ -489,7 +515,7 @@ static int blkdev_common_ioctl(struct block_device *bdev, fmode_t mode, queue_max_sectors(bdev_get_queue(bdev))); return put_ushort(argp, max_sectors); case BLKROTATIONAL: - return put_ushort(argp, !blk_queue_nonrot(bdev_get_queue(bdev))); + return put_ushort(argp, !bdev_nonrot(bdev)); case BLKRASET: case BLKFRASET: if(!capable(CAP_SYS_ADMIN)) diff --git a/block/mq-deadline.c b/block/mq-deadline.c index 3ed5eaf3446a..6ed602b2f80a 100644 --- a/block/mq-deadline.c +++ b/block/mq-deadline.c @@ -742,6 +742,7 @@ static void dd_insert_request(struct blk_mq_hw_ctx *hctx, struct request *rq, if (at_head) { list_add(&rq->queuelist, &per_prio->dispatch); + rq->fifo_time = jiffies; } else { deadline_add_rq_rb(per_prio, rq); diff --git a/block/partitions/acorn.c b/block/partitions/acorn.c index 2c381c694c57..d2fc122d7426 100644 --- a/block/partitions/acorn.c +++ b/block/partitions/acorn.c @@ -282,13 +282,13 @@ int adfspart_check_ADFS(struct parsed_partitions *state) #ifdef CONFIG_ACORN_PARTITION_RISCIX case PARTITION_RISCIX_SCSI: case PARTITION_RISCIX_MFM: - slot = riscix_partition(state, start_sect, slot, + riscix_partition(state, start_sect, slot, nr_sects); break; #endif case PARTITION_LINUX: - slot = linux_partition(state, start_sect, slot, + linux_partition(state, start_sect, slot, nr_sects); break; } diff --git a/block/partitions/atari.c b/block/partitions/atari.c index da5994175416..9655c728262a 100644 --- a/block/partitions/atari.c +++ b/block/partitions/atari.c @@ -140,7 +140,6 @@ int atari_partition(struct parsed_partitions *state) /* accept only GEM,BGM,RAW,LNX,SWP partitions */ if (!((pi->flg & 1) && OK_id(pi->id))) continue; - part_fmt = 2; put_partition (state, slot, be32_to_cpu(pi->st), be32_to_cpu(pi->siz)); diff --git a/block/partitions/core.c b/block/partitions/core.c index 2ef8dfa1e5c8..8a0ec929023b 100644 --- a/block/partitions/core.c +++ b/block/partitions/core.c @@ -200,21 +200,13 @@ static ssize_t part_ro_show(struct device *dev, static ssize_t part_alignment_offset_show(struct device *dev, struct device_attribute *attr, char *buf) { - struct block_device *bdev = dev_to_bdev(dev); - - return sprintf(buf, "%u\n", - queue_limit_alignment_offset(&bdev_get_queue(bdev)->limits, - bdev->bd_start_sect)); + return sprintf(buf, "%u\n", bdev_alignment_offset(dev_to_bdev(dev))); } static ssize_t part_discard_alignment_show(struct device *dev, struct device_attribute *attr, char *buf) { - struct block_device *bdev = dev_to_bdev(dev); - - return sprintf(buf, "%u\n", - queue_limit_discard_alignment(&bdev_get_queue(bdev)->limits, - bdev->bd_start_sect)); + return sprintf(buf, "%u\n", bdev_discard_alignment(dev_to_bdev(dev))); } static DEVICE_ATTR(partition, 0444, part_partition_show, NULL); @@ -486,7 +478,7 @@ int bdev_del_partition(struct gendisk *disk, int partno) goto out_unlock; ret = -EBUSY; - if (part->bd_openers) + if (atomic_read(&part->bd_openers)) goto out_unlock; delete_partition(part); diff --git a/block/partitions/ldm.c b/block/partitions/ldm.c index 27f6c7d9c776..38e58960ae03 100644 --- a/block/partitions/ldm.c +++ b/block/partitions/ldm.c @@ -736,7 +736,6 @@ static bool ldm_parse_cmp3 (const u8 *buffer, int buflen, struct vblk *vb) len = r_cols; } else { r_stripe = 0; - r_cols = 0; len = r_parent; } if (len < 0) @@ -783,11 +782,8 @@ static int ldm_parse_dgr3 (const u8 *buffer, int buflen, struct vblk *vb) r_id1 = ldm_relative (buffer, buflen, 0x24, r_diskid); r_id2 = ldm_relative (buffer, buflen, 0x24, r_id1); len = r_id2; - } else { - r_id1 = 0; - r_id2 = 0; + } else len = r_diskid; - } if (len < 0) return false; @@ -826,11 +822,8 @@ static bool ldm_parse_dgr4 (const u8 *buffer, int buflen, struct vblk *vb) r_id1 = ldm_relative (buffer, buflen, 0x44, r_name); r_id2 = ldm_relative (buffer, buflen, 0x44, r_id1); len = r_id2; - } else { - r_id1 = 0; - r_id2 = 0; + } else len = r_name; - } if (len < 0) return false; @@ -963,10 +956,8 @@ static bool ldm_parse_prt3(const u8 *buffer, int buflen, struct vblk *vb) return false; } len = r_index; - } else { - r_index = 0; + } else len = r_diskid; - } if (len < 0) { ldm_error("len %d < 0", len); return false; diff --git a/drivers/ata/ahci.c b/drivers/ata/ahci.c index 397dfd27c90d..c1eca72b4575 100644 --- a/drivers/ata/ahci.c +++ b/drivers/ata/ahci.c @@ -324,7 +324,6 @@ static const struct pci_device_id ahci_pci_tbl[] = { { PCI_VDEVICE(INTEL, 0x1d02), board_ahci }, /* PBG AHCI */ { PCI_VDEVICE(INTEL, 0x1d04), board_ahci }, /* PBG RAID */ { PCI_VDEVICE(INTEL, 0x1d06), board_ahci }, /* PBG RAID */ - { PCI_VDEVICE(INTEL, 0x2826), board_ahci }, /* PBG/Lewisburg RAID*/ { PCI_VDEVICE(INTEL, 0x2323), board_ahci }, /* DH89xxCC AHCI */ { PCI_VDEVICE(INTEL, 0x1e02), board_ahci }, /* Panther Point AHCI */ { PCI_VDEVICE(INTEL, 0x1e03), board_ahci_low_power }, /* Panther M AHCI */ @@ -367,7 +366,9 @@ static const struct pci_device_id ahci_pci_tbl[] = { { PCI_VDEVICE(INTEL, 0x1f3e), board_ahci_avn }, /* Avoton RAID */ { PCI_VDEVICE(INTEL, 0x1f3f), board_ahci_avn }, /* Avoton RAID */ { PCI_VDEVICE(INTEL, 0x2823), board_ahci }, /* Wellsburg/Lewisburg AHCI*/ - { PCI_VDEVICE(INTEL, 0x2827), board_ahci }, /* Wellsburg/Lewisburg RAID*/ + { PCI_VDEVICE(INTEL, 0x2826), board_ahci }, /* *burg SATA0 'RAID' */ + { PCI_VDEVICE(INTEL, 0x2827), board_ahci }, /* *burg SATA1 'RAID' */ + { PCI_VDEVICE(INTEL, 0x282f), board_ahci }, /* *burg SATA2 'RAID' */ { PCI_VDEVICE(INTEL, 0x43d4), board_ahci }, /* Rocket Lake PCH-H RAID */ { PCI_VDEVICE(INTEL, 0x43d5), board_ahci }, /* Rocket Lake PCH-H RAID */ { PCI_VDEVICE(INTEL, 0x43d6), board_ahci }, /* Rocket Lake PCH-H RAID */ diff --git a/drivers/ata/ahci_brcm.c b/drivers/ata/ahci_brcm.c index ab8552b1ff2a..f61795c546cf 100644 --- a/drivers/ata/ahci_brcm.c +++ b/drivers/ata/ahci_brcm.c @@ -549,15 +549,10 @@ static int brcm_ahci_remove(struct platform_device *pdev) struct ata_host *host = dev_get_drvdata(&pdev->dev); struct ahci_host_priv *hpriv = host->private_data; struct brcm_ahci_priv *priv = hpriv->plat_data; - int ret; brcm_sata_phys_disable(priv); - ret = ata_platform_remove_one(pdev); - if (ret) - return ret; - - return 0; + return ata_platform_remove_one(pdev); } static void brcm_ahci_shutdown(struct platform_device *pdev) diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c index ca64837641be..40e816419f48 100644 --- a/drivers/ata/libata-core.c +++ b/drivers/ata/libata-core.c @@ -96,7 +96,8 @@ struct ata_force_param { unsigned long xfer_mask; unsigned int horkage_on; unsigned int horkage_off; - u16 lflags; + u16 lflags_on; + u16 lflags_off; }; struct ata_force_ent { @@ -386,11 +387,17 @@ static void ata_force_link_limits(struct ata_link *link) } /* let lflags stack */ - if (fe->param.lflags) { - link->flags |= fe->param.lflags; + if (fe->param.lflags_on) { + link->flags |= fe->param.lflags_on; ata_link_notice(link, "FORCE: link flag 0x%x forced -> 0x%x\n", - fe->param.lflags, link->flags); + fe->param.lflags_on, link->flags); + } + if (fe->param.lflags_off) { + link->flags &= ~fe->param.lflags_off; + ata_link_notice(link, + "FORCE: link flag 0x%x cleared -> 0x%x\n", + fe->param.lflags_off, link->flags); } } } @@ -898,7 +905,7 @@ EXPORT_SYMBOL_GPL(ata_xfer_mode2mask); * RETURNS: * Matching xfer_shift, -1 if no match found. */ -int ata_xfer_mode2shift(unsigned long xfer_mode) +int ata_xfer_mode2shift(u8 xfer_mode) { const struct ata_xfer_ent *ent; @@ -1398,7 +1405,7 @@ unsigned long ata_id_xfermask(const u16 *id) /* But wait.. there's more. Design your standards by * committee and you too can get a free iordy field to - * process. However its the speeds not the modes that + * process. However it is the speeds not the modes that * are supported... Note drivers using the timing API * will get this right anyway */ @@ -3898,7 +3905,7 @@ static const struct ata_blacklist_entry ata_device_blacklist [] = { /* Devices where NCQ should be avoided */ /* NCQ is slow */ { "WDC WD740ADFD-00", NULL, ATA_HORKAGE_NONCQ }, - { "WDC WD740ADFD-00NLR1", NULL, ATA_HORKAGE_NONCQ, }, + { "WDC WD740ADFD-00NLR1", NULL, ATA_HORKAGE_NONCQ }, /* http://thread.gmane.org/gmane.linux.ide/14907 */ { "FUJITSU MHT2060BH", NULL, ATA_HORKAGE_NONCQ }, /* NCQ is broken */ @@ -3924,23 +3931,23 @@ static const struct ata_blacklist_entry ata_device_blacklist [] = { /* drives which fail FPDMA_AA activation (some may freeze afterwards) the ST disks also have LPM issues */ { "ST1000LM024 HN-M101MBB", NULL, ATA_HORKAGE_BROKEN_FPDMA_AA | - ATA_HORKAGE_NOLPM, }, + ATA_HORKAGE_NOLPM }, { "VB0250EAVER", "HPG7", ATA_HORKAGE_BROKEN_FPDMA_AA }, /* Blacklist entries taken from Silicon Image 3124/3132 Windows driver .inf file - also several Linux problem reports */ - { "HTS541060G9SA00", "MB3OC60D", ATA_HORKAGE_NONCQ, }, - { "HTS541080G9SA00", "MB4OC60D", ATA_HORKAGE_NONCQ, }, - { "HTS541010G9SA00", "MBZOC60D", ATA_HORKAGE_NONCQ, }, + { "HTS541060G9SA00", "MB3OC60D", ATA_HORKAGE_NONCQ }, + { "HTS541080G9SA00", "MB4OC60D", ATA_HORKAGE_NONCQ }, + { "HTS541010G9SA00", "MBZOC60D", ATA_HORKAGE_NONCQ }, /* https://bugzilla.kernel.org/show_bug.cgi?id=15573 */ - { "C300-CTFDDAC128MAG", "0001", ATA_HORKAGE_NONCQ, }, + { "C300-CTFDDAC128MAG", "0001", ATA_HORKAGE_NONCQ }, /* Sandisk SD7/8/9s lock up hard on large trims */ - { "SanDisk SD[789]*", NULL, ATA_HORKAGE_MAX_TRIM_128M, }, + { "SanDisk SD[789]*", NULL, ATA_HORKAGE_MAX_TRIM_128M }, /* devices which puke on READ_NATIVE_MAX */ - { "HDS724040KLSA80", "KFAOA20N", ATA_HORKAGE_BROKEN_HPA, }, + { "HDS724040KLSA80", "KFAOA20N", ATA_HORKAGE_BROKEN_HPA }, { "WDC WD3200JD-00KLB0", "WD-WCAMR1130137", ATA_HORKAGE_BROKEN_HPA }, { "WDC WD2500JD-00HBB0", "WD-WMAL71490727", ATA_HORKAGE_BROKEN_HPA }, { "MAXTOR 6L080L4", "A93.0500", ATA_HORKAGE_BROKEN_HPA }, @@ -3949,22 +3956,22 @@ static const struct ata_blacklist_entry ata_device_blacklist [] = { { "OCZ-VERTEX", "1.30", ATA_HORKAGE_BROKEN_HPA }, /* Devices which report 1 sector over size HPA */ - { "ST340823A", NULL, ATA_HORKAGE_HPA_SIZE, }, - { "ST320413A", NULL, ATA_HORKAGE_HPA_SIZE, }, - { "ST310211A", NULL, ATA_HORKAGE_HPA_SIZE, }, + { "ST340823A", NULL, ATA_HORKAGE_HPA_SIZE }, + { "ST320413A", NULL, ATA_HORKAGE_HPA_SIZE }, + { "ST310211A", NULL, ATA_HORKAGE_HPA_SIZE }, /* Devices which get the IVB wrong */ - { "QUANTUM FIREBALLlct10 05", "A03.0900", ATA_HORKAGE_IVB, }, + { "QUANTUM FIREBALLlct10 05", "A03.0900", ATA_HORKAGE_IVB }, /* Maybe we should just blacklist TSSTcorp... */ - { "TSSTcorp CDDVDW SH-S202[HJN]", "SB0[01]", ATA_HORKAGE_IVB, }, + { "TSSTcorp CDDVDW SH-S202[HJN]", "SB0[01]", ATA_HORKAGE_IVB }, /* Devices that do not need bridging limits applied */ - { "MTRON MSP-SATA*", NULL, ATA_HORKAGE_BRIDGE_OK, }, - { "BUFFALO HD-QSU2/R5", NULL, ATA_HORKAGE_BRIDGE_OK, }, + { "MTRON MSP-SATA*", NULL, ATA_HORKAGE_BRIDGE_OK }, + { "BUFFALO HD-QSU2/R5", NULL, ATA_HORKAGE_BRIDGE_OK }, /* Devices which aren't very happy with higher link speeds */ - { "WD My Book", NULL, ATA_HORKAGE_1_5_GBPS, }, - { "Seagate FreeAgent GoFlex", NULL, ATA_HORKAGE_1_5_GBPS, }, + { "WD My Book", NULL, ATA_HORKAGE_1_5_GBPS }, + { "Seagate FreeAgent GoFlex", NULL, ATA_HORKAGE_1_5_GBPS }, /* * Devices which choke on SETXFER. Applies only if both the @@ -3982,57 +3989,57 @@ static const struct ata_blacklist_entry ata_device_blacklist [] = { /* 512GB MX100 with MU01 firmware has both queued TRIM and LPM issues */ { "Crucial_CT512MX100*", "MU01", ATA_HORKAGE_NO_NCQ_TRIM | ATA_HORKAGE_ZERO_AFTER_TRIM | - ATA_HORKAGE_NOLPM, }, + ATA_HORKAGE_NOLPM }, /* 512GB MX100 with newer firmware has only LPM issues */ { "Crucial_CT512MX100*", NULL, ATA_HORKAGE_ZERO_AFTER_TRIM | - ATA_HORKAGE_NOLPM, }, + ATA_HORKAGE_NOLPM }, /* 480GB+ M500 SSDs have both queued TRIM and LPM issues */ { "Crucial_CT480M500*", NULL, ATA_HORKAGE_NO_NCQ_TRIM | ATA_HORKAGE_ZERO_AFTER_TRIM | - ATA_HORKAGE_NOLPM, }, + ATA_HORKAGE_NOLPM }, { "Crucial_CT960M500*", NULL, ATA_HORKAGE_NO_NCQ_TRIM | ATA_HORKAGE_ZERO_AFTER_TRIM | - ATA_HORKAGE_NOLPM, }, + ATA_HORKAGE_NOLPM }, /* These specific Samsung models/firmware-revs do not handle LPM well */ - { "SAMSUNG MZMPC128HBFU-000MV", "CXM14M1Q", ATA_HORKAGE_NOLPM, }, - { "SAMSUNG SSD PM830 mSATA *", "CXM13D1Q", ATA_HORKAGE_NOLPM, }, - { "SAMSUNG MZ7TD256HAFV-000L9", NULL, ATA_HORKAGE_NOLPM, }, - { "SAMSUNG MZ7TE512HMHP-000L1", "EXT06L0Q", ATA_HORKAGE_NOLPM, }, + { "SAMSUNG MZMPC128HBFU-000MV", "CXM14M1Q", ATA_HORKAGE_NOLPM }, + { "SAMSUNG SSD PM830 mSATA *", "CXM13D1Q", ATA_HORKAGE_NOLPM }, + { "SAMSUNG MZ7TD256HAFV-000L9", NULL, ATA_HORKAGE_NOLPM }, + { "SAMSUNG MZ7TE512HMHP-000L1", "EXT06L0Q", ATA_HORKAGE_NOLPM }, /* devices that don't properly handle queued TRIM commands */ { "Micron_M500IT_*", "MU01", ATA_HORKAGE_NO_NCQ_TRIM | - ATA_HORKAGE_ZERO_AFTER_TRIM, }, + ATA_HORKAGE_ZERO_AFTER_TRIM }, { "Micron_M500_*", NULL, ATA_HORKAGE_NO_NCQ_TRIM | - ATA_HORKAGE_ZERO_AFTER_TRIM, }, + ATA_HORKAGE_ZERO_AFTER_TRIM }, { "Crucial_CT*M500*", NULL, ATA_HORKAGE_NO_NCQ_TRIM | - ATA_HORKAGE_ZERO_AFTER_TRIM, }, + ATA_HORKAGE_ZERO_AFTER_TRIM }, { "Micron_M5[15]0_*", "MU01", ATA_HORKAGE_NO_NCQ_TRIM | - ATA_HORKAGE_ZERO_AFTER_TRIM, }, + ATA_HORKAGE_ZERO_AFTER_TRIM }, { "Crucial_CT*M550*", "MU01", ATA_HORKAGE_NO_NCQ_TRIM | - ATA_HORKAGE_ZERO_AFTER_TRIM, }, + ATA_HORKAGE_ZERO_AFTER_TRIM }, { "Crucial_CT*MX100*", "MU01", ATA_HORKAGE_NO_NCQ_TRIM | - ATA_HORKAGE_ZERO_AFTER_TRIM, }, + ATA_HORKAGE_ZERO_AFTER_TRIM }, { "Samsung SSD 840 EVO*", NULL, ATA_HORKAGE_NO_NCQ_TRIM | ATA_HORKAGE_NO_DMA_LOG | - ATA_HORKAGE_ZERO_AFTER_TRIM, }, + ATA_HORKAGE_ZERO_AFTER_TRIM }, { "Samsung SSD 840*", NULL, ATA_HORKAGE_NO_NCQ_TRIM | - ATA_HORKAGE_ZERO_AFTER_TRIM, }, + ATA_HORKAGE_ZERO_AFTER_TRIM }, { "Samsung SSD 850*", NULL, ATA_HORKAGE_NO_NCQ_TRIM | - ATA_HORKAGE_ZERO_AFTER_TRIM, }, + ATA_HORKAGE_ZERO_AFTER_TRIM }, { "Samsung SSD 860*", NULL, ATA_HORKAGE_NO_NCQ_TRIM | ATA_HORKAGE_ZERO_AFTER_TRIM | - ATA_HORKAGE_NO_NCQ_ON_ATI, }, + ATA_HORKAGE_NO_NCQ_ON_ATI }, { "Samsung SSD 870*", NULL, ATA_HORKAGE_NO_NCQ_TRIM | ATA_HORKAGE_ZERO_AFTER_TRIM | - ATA_HORKAGE_NO_NCQ_ON_ATI, }, + ATA_HORKAGE_NO_NCQ_ON_ATI }, { "FCCT*M500*", NULL, ATA_HORKAGE_NO_NCQ_TRIM | - ATA_HORKAGE_ZERO_AFTER_TRIM, }, + ATA_HORKAGE_ZERO_AFTER_TRIM }, /* devices that don't properly handle TRIM commands */ - { "SuperSSpeed S238*", NULL, ATA_HORKAGE_NOTRIM, }, - { "M88V29*", NULL, ATA_HORKAGE_NOTRIM, }, + { "SuperSSpeed S238*", NULL, ATA_HORKAGE_NOTRIM }, + { "M88V29*", NULL, ATA_HORKAGE_NOTRIM }, /* * As defined, the DRAT (Deterministic Read After Trim) and RZAT @@ -4050,16 +4057,16 @@ static const struct ata_blacklist_entry ata_device_blacklist [] = { * The intel 510 drive has buggy DRAT/RZAT. Explicitly exclude * that model before whitelisting all other intel SSDs. */ - { "INTEL*SSDSC2MH*", NULL, 0, }, + { "INTEL*SSDSC2MH*", NULL, 0 }, - { "Micron*", NULL, ATA_HORKAGE_ZERO_AFTER_TRIM, }, - { "Crucial*", NULL, ATA_HORKAGE_ZERO_AFTER_TRIM, }, - { "INTEL*SSD*", NULL, ATA_HORKAGE_ZERO_AFTER_TRIM, }, - { "SSD*INTEL*", NULL, ATA_HORKAGE_ZERO_AFTER_TRIM, }, - { "Samsung*SSD*", NULL, ATA_HORKAGE_ZERO_AFTER_TRIM, }, - { "SAMSUNG*SSD*", NULL, ATA_HORKAGE_ZERO_AFTER_TRIM, }, - { "SAMSUNG*MZ7KM*", NULL, ATA_HORKAGE_ZERO_AFTER_TRIM, }, - { "ST[1248][0248]0[FH]*", NULL, ATA_HORKAGE_ZERO_AFTER_TRIM, }, + { "Micron*", NULL, ATA_HORKAGE_ZERO_AFTER_TRIM }, + { "Crucial*", NULL, ATA_HORKAGE_ZERO_AFTER_TRIM }, + { "INTEL*SSD*", NULL, ATA_HORKAGE_ZERO_AFTER_TRIM }, + { "SSD*INTEL*", NULL, ATA_HORKAGE_ZERO_AFTER_TRIM }, + { "Samsung*SSD*", NULL, ATA_HORKAGE_ZERO_AFTER_TRIM }, + { "SAMSUNG*SSD*", NULL, ATA_HORKAGE_ZERO_AFTER_TRIM }, + { "SAMSUNG*MZ7KM*", NULL, ATA_HORKAGE_ZERO_AFTER_TRIM }, + { "ST[1248][0248]0[FH]*", NULL, ATA_HORKAGE_ZERO_AFTER_TRIM }, /* * Some WD SATA-I drives spin up and down erratically when the link @@ -4567,42 +4574,6 @@ void swap_buf_le16(u16 *buf, unsigned int buf_words) } /** - * ata_qc_new_init - Request an available ATA command, and initialize it - * @dev: Device from whom we request an available command structure - * @tag: tag - * - * LOCKING: - * None. - */ - -struct ata_queued_cmd *ata_qc_new_init(struct ata_device *dev, int tag) -{ - struct ata_port *ap = dev->link->ap; - struct ata_queued_cmd *qc; - - /* no command while frozen */ - if (unlikely(ap->pflags & ATA_PFLAG_FROZEN)) - return NULL; - - /* libsas case */ - if (ap->flags & ATA_FLAG_SAS_HOST) { - tag = ata_sas_allocate_tag(ap); - if (tag < 0) - return NULL; - } - - qc = __ata_qc_from_tag(ap, tag); - qc->tag = qc->hw_tag = tag; - qc->scsicmd = NULL; - qc->ap = ap; - qc->dev = dev; - - ata_qc_reinit(qc); - - return qc; -} - -/** * ata_qc_free - free unused ata_queued_cmd * @qc: Command to complete * @@ -4614,19 +4585,9 @@ struct ata_queued_cmd *ata_qc_new_init(struct ata_device *dev, int tag) */ void ata_qc_free(struct ata_queued_cmd *qc) { - struct ata_port *ap; - unsigned int tag; - - WARN_ON_ONCE(qc == NULL); /* ata_qc_from_tag _might_ return NULL */ - ap = qc->ap; - qc->flags = 0; - tag = qc->tag; - if (ata_tag_valid(tag)) { + if (ata_tag_valid(qc->tag)) qc->tag = ATA_TAG_POISON; - if (ap->flags & ATA_FLAG_SAS_HOST) - ata_sas_free_tag(tag, ap); - } } void __ata_qc_complete(struct ata_queued_cmd *qc) @@ -5605,7 +5566,7 @@ static void ata_finalize_port_ops(struct ata_port_operations *ops) * Start and then freeze ports of @host. Started status is * recorded in host->flags, so this function can be called * multiple times. Ports are guaranteed to get started only - * once. If host->ops isn't initialized yet, its set to the + * once. If host->ops is not initialized yet, it is set to the * first non-dummy port ops. * * LOCKING: @@ -6146,67 +6107,113 @@ int ata_platform_remove_one(struct platform_device *pdev) EXPORT_SYMBOL_GPL(ata_platform_remove_one); #ifdef CONFIG_ATA_FORCE + +#define force_cbl(name, flag) \ + { #name, .cbl = (flag) } + +#define force_spd_limit(spd, val) \ + { #spd, .spd_limit = (val) } + +#define force_xfer(mode, shift) \ + { #mode, .xfer_mask = (1UL << (shift)) } + +#define force_lflag_on(name, flags) \ + { #name, .lflags_on = (flags) } + +#define force_lflag_onoff(name, flags) \ + { "no" #name, .lflags_on = (flags) }, \ + { #name, .lflags_off = (flags) } + +#define force_horkage_on(name, flag) \ + { #name, .horkage_on = (flag) } + +#define force_horkage_onoff(name, flag) \ + { "no" #name, .horkage_on = (flag) }, \ + { #name, .horkage_off = (flag) } + +static const struct ata_force_param force_tbl[] __initconst = { + force_cbl(40c, ATA_CBL_PATA40), + force_cbl(80c, ATA_CBL_PATA80), + force_cbl(short40c, ATA_CBL_PATA40_SHORT), + force_cbl(unk, ATA_CBL_PATA_UNK), + force_cbl(ign, ATA_CBL_PATA_IGN), + force_cbl(sata, ATA_CBL_SATA), + + force_spd_limit(1.5Gbps, 1), + force_spd_limit(3.0Gbps, 2), + + force_xfer(pio0, ATA_SHIFT_PIO + 0), + force_xfer(pio1, ATA_SHIFT_PIO + 1), + force_xfer(pio2, ATA_SHIFT_PIO + 2), + force_xfer(pio3, ATA_SHIFT_PIO + 3), + force_xfer(pio4, ATA_SHIFT_PIO + 4), + force_xfer(pio5, ATA_SHIFT_PIO + 5), + force_xfer(pio6, ATA_SHIFT_PIO + 6), + force_xfer(mwdma0, ATA_SHIFT_MWDMA + 0), + force_xfer(mwdma1, ATA_SHIFT_MWDMA + 1), + force_xfer(mwdma2, ATA_SHIFT_MWDMA + 2), + force_xfer(mwdma3, ATA_SHIFT_MWDMA + 3), + force_xfer(mwdma4, ATA_SHIFT_MWDMA + 4), + force_xfer(udma0, ATA_SHIFT_UDMA + 0), + force_xfer(udma16, ATA_SHIFT_UDMA + 0), + force_xfer(udma/16, ATA_SHIFT_UDMA + 0), + force_xfer(udma1, ATA_SHIFT_UDMA + 1), + force_xfer(udma25, ATA_SHIFT_UDMA + 1), + force_xfer(udma/25, ATA_SHIFT_UDMA + 1), + force_xfer(udma2, ATA_SHIFT_UDMA + 2), + force_xfer(udma33, ATA_SHIFT_UDMA + 2), + force_xfer(udma/33, ATA_SHIFT_UDMA + 2), + force_xfer(udma3, ATA_SHIFT_UDMA + 3), + force_xfer(udma44, ATA_SHIFT_UDMA + 3), + force_xfer(udma/44, ATA_SHIFT_UDMA + 3), + force_xfer(udma4, ATA_SHIFT_UDMA + 4), + force_xfer(udma66, ATA_SHIFT_UDMA + 4), + force_xfer(udma/66, ATA_SHIFT_UDMA + 4), + force_xfer(udma5, ATA_SHIFT_UDMA + 5), + force_xfer(udma100, ATA_SHIFT_UDMA + 5), + force_xfer(udma/100, ATA_SHIFT_UDMA + 5), + force_xfer(udma6, ATA_SHIFT_UDMA + 6), + force_xfer(udma133, ATA_SHIFT_UDMA + 6), + force_xfer(udma/133, ATA_SHIFT_UDMA + 6), + force_xfer(udma7, ATA_SHIFT_UDMA + 7), + + force_lflag_on(nohrst, ATA_LFLAG_NO_HRST), + force_lflag_on(nosrst, ATA_LFLAG_NO_SRST), + force_lflag_on(norst, ATA_LFLAG_NO_HRST | ATA_LFLAG_NO_SRST), + force_lflag_on(rstonce, ATA_LFLAG_RST_ONCE), + force_lflag_onoff(dbdelay, ATA_LFLAG_NO_DEBOUNCE_DELAY), + + force_horkage_onoff(ncq, ATA_HORKAGE_NONCQ), + force_horkage_onoff(ncqtrim, ATA_HORKAGE_NO_NCQ_TRIM), + force_horkage_onoff(ncqati, ATA_HORKAGE_NO_NCQ_ON_ATI), + + force_horkage_onoff(trim, ATA_HORKAGE_NOTRIM), + force_horkage_on(trim_zero, ATA_HORKAGE_ZERO_AFTER_TRIM), + force_horkage_on(max_trim_128m, ATA_HORKAGE_MAX_TRIM_128M), + + force_horkage_onoff(dma, ATA_HORKAGE_NODMA), + force_horkage_on(atapi_dmadir, ATA_HORKAGE_ATAPI_DMADIR), + force_horkage_on(atapi_mod16_dma, ATA_HORKAGE_ATAPI_MOD16_DMA), + + force_horkage_onoff(dmalog, ATA_HORKAGE_NO_DMA_LOG), + force_horkage_onoff(iddevlog, ATA_HORKAGE_NO_ID_DEV_LOG), + force_horkage_onoff(logdir, ATA_HORKAGE_NO_LOG_DIR), + + force_horkage_on(max_sec_128, ATA_HORKAGE_MAX_SEC_128), + force_horkage_on(max_sec_1024, ATA_HORKAGE_MAX_SEC_1024), + force_horkage_on(max_sec_lba48, ATA_HORKAGE_MAX_SEC_LBA48), + + force_horkage_onoff(lpm, ATA_HORKAGE_NOLPM), + force_horkage_onoff(setxfer, ATA_HORKAGE_NOSETXFER), + force_horkage_on(dump_id, ATA_HORKAGE_DUMP_ID), + + force_horkage_on(disable, ATA_HORKAGE_DISABLE), +}; + static int __init ata_parse_force_one(char **cur, struct ata_force_ent *force_ent, const char **reason) { - static const struct ata_force_param force_tbl[] __initconst = { - { "40c", .cbl = ATA_CBL_PATA40 }, - { "80c", .cbl = ATA_CBL_PATA80 }, - { "short40c", .cbl = ATA_CBL_PATA40_SHORT }, - { "unk", .cbl = ATA_CBL_PATA_UNK }, - { "ign", .cbl = ATA_CBL_PATA_IGN }, - { "sata", .cbl = ATA_CBL_SATA }, - { "1.5Gbps", .spd_limit = 1 }, - { "3.0Gbps", .spd_limit = 2 }, - { "noncq", .horkage_on = ATA_HORKAGE_NONCQ }, - { "ncq", .horkage_off = ATA_HORKAGE_NONCQ }, - { "noncqtrim", .horkage_on = ATA_HORKAGE_NO_NCQ_TRIM }, - { "ncqtrim", .horkage_off = ATA_HORKAGE_NO_NCQ_TRIM }, - { "noncqati", .horkage_on = ATA_HORKAGE_NO_NCQ_ON_ATI }, - { "ncqati", .horkage_off = ATA_HORKAGE_NO_NCQ_ON_ATI }, - { "dump_id", .horkage_on = ATA_HORKAGE_DUMP_ID }, - { "pio0", .xfer_mask = 1 << (ATA_SHIFT_PIO + 0) }, - { "pio1", .xfer_mask = 1 << (ATA_SHIFT_PIO + 1) }, - { "pio2", .xfer_mask = 1 << (ATA_SHIFT_PIO + 2) }, - { "pio3", .xfer_mask = 1 << (ATA_SHIFT_PIO + 3) }, - { "pio4", .xfer_mask = 1 << (ATA_SHIFT_PIO + 4) }, - { "pio5", .xfer_mask = 1 << (ATA_SHIFT_PIO + 5) }, - { "pio6", .xfer_mask = 1 << (ATA_SHIFT_PIO + 6) }, - { "mwdma0", .xfer_mask = 1 << (ATA_SHIFT_MWDMA + 0) }, - { "mwdma1", .xfer_mask = 1 << (ATA_SHIFT_MWDMA + 1) }, - { "mwdma2", .xfer_mask = 1 << (ATA_SHIFT_MWDMA + 2) }, - { "mwdma3", .xfer_mask = 1 << (ATA_SHIFT_MWDMA + 3) }, - { "mwdma4", .xfer_mask = 1 << (ATA_SHIFT_MWDMA + 4) }, - { "udma0", .xfer_mask = 1 << (ATA_SHIFT_UDMA + 0) }, - { "udma16", .xfer_mask = 1 << (ATA_SHIFT_UDMA + 0) }, - { "udma/16", .xfer_mask = 1 << (ATA_SHIFT_UDMA + 0) }, - { "udma1", .xfer_mask = 1 << (ATA_SHIFT_UDMA + 1) }, - { "udma25", .xfer_mask = 1 << (ATA_SHIFT_UDMA + 1) }, - { "udma/25", .xfer_mask = 1 << (ATA_SHIFT_UDMA + 1) }, - { "udma2", .xfer_mask = 1 << (ATA_SHIFT_UDMA + 2) }, - { "udma33", .xfer_mask = 1 << (ATA_SHIFT_UDMA + 2) }, - { "udma/33", .xfer_mask = 1 << (ATA_SHIFT_UDMA + 2) }, - { "udma3", .xfer_mask = 1 << (ATA_SHIFT_UDMA + 3) }, - { "udma44", .xfer_mask = 1 << (ATA_SHIFT_UDMA + 3) }, - { "udma/44", .xfer_mask = 1 << (ATA_SHIFT_UDMA + 3) }, - { "udma4", .xfer_mask = 1 << (ATA_SHIFT_UDMA + 4) }, - { "udma66", .xfer_mask = 1 << (ATA_SHIFT_UDMA + 4) }, - { "udma/66", .xfer_mask = 1 << (ATA_SHIFT_UDMA + 4) }, - { "udma5", .xfer_mask = 1 << (ATA_SHIFT_UDMA + 5) }, - { "udma100", .xfer_mask = 1 << (ATA_SHIFT_UDMA + 5) }, - { "udma/100", .xfer_mask = 1 << (ATA_SHIFT_UDMA + 5) }, - { "udma6", .xfer_mask = 1 << (ATA_SHIFT_UDMA + 6) }, - { "udma133", .xfer_mask = 1 << (ATA_SHIFT_UDMA + 6) }, - { "udma/133", .xfer_mask = 1 << (ATA_SHIFT_UDMA + 6) }, - { "udma7", .xfer_mask = 1 << (ATA_SHIFT_UDMA + 7) }, - { "nohrst", .lflags = ATA_LFLAG_NO_HRST }, - { "nosrst", .lflags = ATA_LFLAG_NO_SRST }, - { "norst", .lflags = ATA_LFLAG_NO_HRST | ATA_LFLAG_NO_SRST }, - { "rstonce", .lflags = ATA_LFLAG_RST_ONCE }, - { "atapi_dmadir", .horkage_on = ATA_HORKAGE_ATAPI_DMADIR }, - { "disable", .horkage_on = ATA_HORKAGE_DISABLE }, - }; char *start = *cur, *p = *cur; char *id, *val, *endp; const struct ata_force_param *match_fp = NULL; @@ -6288,7 +6295,7 @@ static void __init ata_parse_force_param(void) int last_port = -1, last_device = -1; char *p, *cur, *next; - /* calculate maximum number of params and allocate force_tbl */ + /* Calculate maximum number of params and allocate ata_force_tbl */ for (p = ata_force_param_buf; *p; p++) if (*p == ',') size++; diff --git a/drivers/ata/libata-sata.c b/drivers/ata/libata-sata.c index 044a16daa2d4..7a5fe41aa5ae 100644 --- a/drivers/ata/libata-sata.c +++ b/drivers/ata/libata-sata.c @@ -1268,31 +1268,6 @@ int ata_sas_queuecmd(struct scsi_cmnd *cmd, struct ata_port *ap) } EXPORT_SYMBOL_GPL(ata_sas_queuecmd); -int ata_sas_allocate_tag(struct ata_port *ap) -{ - unsigned int max_queue = ap->host->n_tags; - unsigned int i, tag; - - for (i = 0, tag = ap->sas_last_tag + 1; i < max_queue; i++, tag++) { - tag = tag < max_queue ? tag : 0; - - /* the last tag is reserved for internal command. */ - if (ata_tag_internal(tag)) - continue; - - if (!test_and_set_bit(tag, &ap->sas_tag_allocated)) { - ap->sas_last_tag = tag; - return tag; - } - } - return -1; -} - -void ata_sas_free_tag(unsigned int tag, struct ata_port *ap) -{ - clear_bit(tag, &ap->sas_tag_allocated); -} - /** * sata_async_notification - SATA async notification handler * @ap: ATA port where async notification is received diff --git a/drivers/ata/libata-scsi.c b/drivers/ata/libata-scsi.c index 06c9d90238d9..42cecf95a4e5 100644 --- a/drivers/ata/libata-scsi.c +++ b/drivers/ata/libata-scsi.c @@ -638,24 +638,48 @@ EXPORT_SYMBOL_GPL(ata_scsi_ioctl); static struct ata_queued_cmd *ata_scsi_qc_new(struct ata_device *dev, struct scsi_cmnd *cmd) { + struct ata_port *ap = dev->link->ap; struct ata_queued_cmd *qc; + int tag; - qc = ata_qc_new_init(dev, scsi_cmd_to_rq(cmd)->tag); - if (qc) { - qc->scsicmd = cmd; - qc->scsidone = scsi_done; - - qc->sg = scsi_sglist(cmd); - qc->n_elem = scsi_sg_count(cmd); + if (unlikely(ap->pflags & ATA_PFLAG_FROZEN)) + goto fail; - if (scsi_cmd_to_rq(cmd)->rq_flags & RQF_QUIET) - qc->flags |= ATA_QCFLAG_QUIET; + if (ap->flags & ATA_FLAG_SAS_HOST) { + /* + * SAS hosts may queue > ATA_MAX_QUEUE commands so use + * unique per-device budget token as a tag. + */ + if (WARN_ON_ONCE(cmd->budget_token >= ATA_MAX_QUEUE)) + goto fail; + tag = cmd->budget_token; } else { - cmd->result = (DID_OK << 16) | SAM_STAT_TASK_SET_FULL; - scsi_done(cmd); + tag = scsi_cmd_to_rq(cmd)->tag; } + qc = __ata_qc_from_tag(ap, tag); + qc->tag = qc->hw_tag = tag; + qc->ap = ap; + qc->dev = dev; + + ata_qc_reinit(qc); + + qc->scsicmd = cmd; + qc->scsidone = scsi_done; + + qc->sg = scsi_sglist(cmd); + qc->n_elem = scsi_sg_count(cmd); + + if (scsi_cmd_to_rq(cmd)->rq_flags & RQF_QUIET) + qc->flags |= ATA_QCFLAG_QUIET; + return qc; + +fail: + set_host_byte(cmd, DID_OK); + set_status_byte(cmd, SAM_STAT_TASK_SET_FULL); + scsi_done(cmd); + return NULL; } static void ata_qc_set_pc_nbytes(struct ata_queued_cmd *qc) diff --git a/drivers/ata/libata.h b/drivers/ata/libata.h index c9c2496d91ea..926a7f41303d 100644 --- a/drivers/ata/libata.h +++ b/drivers/ata/libata.h @@ -44,7 +44,6 @@ static inline void ata_force_cbl(struct ata_port *ap) { } #endif extern u64 ata_tf_to_lba(const struct ata_taskfile *tf); extern u64 ata_tf_to_lba48(const struct ata_taskfile *tf); -extern struct ata_queued_cmd *ata_qc_new_init(struct ata_device *dev, int tag); extern int ata_build_rw_tf(struct ata_taskfile *tf, struct ata_device *dev, u64 block, u32 n_block, unsigned int tf_flags, unsigned int tag, int class); @@ -91,18 +90,6 @@ extern unsigned int ata_read_log_page(struct ata_device *dev, u8 log, #define to_ata_port(d) container_of(d, struct ata_port, tdev) -/* libata-sata.c */ -#ifdef CONFIG_SATA_HOST -int ata_sas_allocate_tag(struct ata_port *ap); -void ata_sas_free_tag(unsigned int tag, struct ata_port *ap); -#else -static inline int ata_sas_allocate_tag(struct ata_port *ap) -{ - return -EOPNOTSUPP; -} -static inline void ata_sas_free_tag(unsigned int tag, struct ata_port *ap) { } -#endif - /* libata-acpi.c */ #ifdef CONFIG_ATA_ACPI extern unsigned int ata_acpi_gtf_filter; diff --git a/drivers/ata/pata_ftide010.c b/drivers/ata/pata_ftide010.c index 2e35505b683c..0117df0fe3c5 100644 --- a/drivers/ata/pata_ftide010.c +++ b/drivers/ata/pata_ftide010.c @@ -536,8 +536,8 @@ static int pata_ftide010_probe(struct platform_device *pdev) return 0; err_dis_clk: - if (!IS_ERR(ftide->pclk)) - clk_disable_unprepare(ftide->pclk); + clk_disable_unprepare(ftide->pclk); + return ret; } @@ -547,8 +547,7 @@ static int pata_ftide010_remove(struct platform_device *pdev) struct ftide010 *ftide = host->private_data; ata_host_detach(ftide->host); - if (!IS_ERR(ftide->pclk)) - clk_disable_unprepare(ftide->pclk); + clk_disable_unprepare(ftide->pclk); return 0; } diff --git a/drivers/ata/pata_mpc52xx.c b/drivers/ata/pata_mpc52xx.c index 3250ef317df6..03b6ae37a578 100644 --- a/drivers/ata/pata_mpc52xx.c +++ b/drivers/ata/pata_mpc52xx.c @@ -19,11 +19,12 @@ #include <linux/gfp.h> #include <linux/delay.h> #include <linux/libata.h> +#include <linux/of_address.h> +#include <linux/of_irq.h> #include <linux/of_platform.h> #include <linux/types.h> #include <asm/cacheflush.h> -#include <asm/prom.h> #include <asm/mpc52xx.h> #include <linux/fsl/bestcomm/bestcomm.h> diff --git a/drivers/ata/pata_sil680.c b/drivers/ata/pata_sil680.c index 0da58ce20d82..67ef2e26d7df 100644 --- a/drivers/ata/pata_sil680.c +++ b/drivers/ata/pata_sil680.c @@ -47,11 +47,9 @@ * criticial. */ -static unsigned long sil680_selreg(struct ata_port *ap, int r) +static int sil680_selreg(struct ata_port *ap, int r) { - unsigned long base = 0xA0 + r; - base += (ap->port_no << 4); - return base; + return 0xA0 + (ap->port_no << 4) + r; } /** @@ -65,12 +63,9 @@ static unsigned long sil680_selreg(struct ata_port *ap, int r) * the unit shift. */ -static unsigned long sil680_seldev(struct ata_port *ap, struct ata_device *adev, int r) +static int sil680_seldev(struct ata_port *ap, struct ata_device *adev, int r) { - unsigned long base = 0xA0 + r; - base += (ap->port_no << 4); - base |= adev->devno ? 2 : 0; - return base; + return 0xA0 + (ap->port_no << 4) + r + (adev->devno << 1); } @@ -85,8 +80,9 @@ static unsigned long sil680_seldev(struct ata_port *ap, struct ata_device *adev, static int sil680_cable_detect(struct ata_port *ap) { struct pci_dev *pdev = to_pci_dev(ap->host->dev); - unsigned long addr = sil680_selreg(ap, 0); + int addr = sil680_selreg(ap, 0); u8 ata66; + pci_read_config_byte(pdev, addr, &ata66); if (ata66 & 1) return ATA_CBL_PATA80; @@ -113,9 +109,9 @@ static void sil680_set_piomode(struct ata_port *ap, struct ata_device *adev) 0x328A, 0x2283, 0x1281, 0x10C3, 0x10C1 }; - unsigned long tfaddr = sil680_selreg(ap, 0x02); - unsigned long addr = sil680_seldev(ap, adev, 0x04); - unsigned long addr_mask = 0x80 + 4 * ap->port_no; + int tfaddr = sil680_selreg(ap, 0x02); + int addr = sil680_seldev(ap, adev, 0x04); + int addr_mask = 0x80 + 4 * ap->port_no; struct pci_dev *pdev = to_pci_dev(ap->host->dev); int pio = adev->pio_mode - XFER_PIO_0; int lowest_pio = pio; @@ -165,9 +161,9 @@ static void sil680_set_dmamode(struct ata_port *ap, struct ata_device *adev) static const u16 dma_table[3] = { 0x2208, 0x10C2, 0x10C1 }; struct pci_dev *pdev = to_pci_dev(ap->host->dev); - unsigned long ma = sil680_seldev(ap, adev, 0x08); - unsigned long ua = sil680_seldev(ap, adev, 0x0C); - unsigned long addr_mask = 0x80 + 4 * ap->port_no; + int ma = sil680_seldev(ap, adev, 0x08); + int ua = sil680_seldev(ap, adev, 0x0C); + int addr_mask = 0x80 + 4 * ap->port_no; int port_shift = adev->devno * 4; u8 scsc, mode; u16 multi, ultra; @@ -219,7 +215,7 @@ static void sil680_sff_exec_command(struct ata_port *ap, static bool sil680_sff_irq_check(struct ata_port *ap) { struct pci_dev *pdev = to_pci_dev(ap->host->dev); - unsigned long addr = sil680_selreg(ap, 1); + int addr = sil680_selreg(ap, 1); u8 val; pci_read_config_byte(pdev, addr, &val); diff --git a/drivers/ata/pata_via.c b/drivers/ata/pata_via.c index 439ca882f73c..215c02d4056a 100644 --- a/drivers/ata/pata_via.c +++ b/drivers/ata/pata_via.c @@ -248,9 +248,9 @@ static void via_do_set_mode(struct ata_port *ap, struct ata_device *adev, struct pci_dev *pdev = to_pci_dev(ap->host->dev); struct ata_device *peer = ata_dev_pair(adev); struct ata_timing t, p; - static int via_clock = 33333; /* Bus clock in kHZ */ - unsigned long T = 1000000000 / via_clock; - unsigned long UT = T; + const int via_clock = 33333; /* Bus clock in kHz */ + const int T = 1000000000 / via_clock; + int UT = T; int ut; int offset = 3 - (2*ap->port_no) - adev->devno; diff --git a/drivers/ata/sata_gemini.c b/drivers/ata/sata_gemini.c index 00e1c7941d0e..b729e9919bb0 100644 --- a/drivers/ata/sata_gemini.c +++ b/drivers/ata/sata_gemini.c @@ -318,7 +318,6 @@ static int gemini_sata_probe(struct platform_device *pdev) struct device_node *np = dev->of_node; struct sata_gemini *sg; struct regmap *map; - struct resource *res; enum gemini_muxmode muxmode; u32 gmode; u32 gmask; @@ -329,11 +328,7 @@ static int gemini_sata_probe(struct platform_device *pdev) return -ENOMEM; sg->dev = dev; - res = platform_get_resource(pdev, IORESOURCE_MEM, 0); - if (!res) - return -ENODEV; - - sg->base = devm_ioremap_resource(dev, res); + sg->base = devm_platform_ioremap_resource(pdev, 0); if (IS_ERR(sg->base)) return PTR_ERR(sg->base); diff --git a/drivers/base/firmware_loader/main.c b/drivers/base/firmware_loader/main.c index 94d1789a233e..406a907a4cae 100644 --- a/drivers/base/firmware_loader/main.c +++ b/drivers/base/firmware_loader/main.c @@ -735,6 +735,8 @@ _request_firmware(const struct firmware **firmware_p, const char *name, size_t offset, u32 opt_flags) { struct firmware *fw = NULL; + struct cred *kern_cred = NULL; + const struct cred *old_cred; bool nondirect = false; int ret; @@ -751,6 +753,18 @@ _request_firmware(const struct firmware **firmware_p, const char *name, if (ret <= 0) /* error or already assigned */ goto out; + /* + * We are about to try to access the firmware file. Because we may have been + * called by a driver when serving an unrelated request from userland, we use + * the kernel credentials to read the file. + */ + kern_cred = prepare_kernel_cred(NULL); + if (!kern_cred) { + ret = -ENOMEM; + goto out; + } + old_cred = override_creds(kern_cred); + ret = fw_get_filesystem_firmware(device, fw->priv, "", NULL); /* Only full reads can support decompression, platform, and sysfs. */ @@ -776,6 +790,9 @@ _request_firmware(const struct firmware **firmware_p, const char *name, } else ret = assign_fw(fw, device); + revert_creds(old_cred); + put_cred(kern_cred); + out: if (ret < 0) { fw_abort_batch_reqs(fw); diff --git a/drivers/block/aoe/aoe.h b/drivers/block/aoe/aoe.h index 84d0fcebd6af..749ae1246f4c 100644 --- a/drivers/block/aoe/aoe.h +++ b/drivers/block/aoe/aoe.h @@ -244,3 +244,5 @@ void aoenet_exit(void); void aoenet_xmit(struct sk_buff_head *); int is_aoe_netif(struct net_device *ifp); int set_aoe_iflist(const char __user *str, size_t size); + +extern struct workqueue_struct *aoe_wq; diff --git a/drivers/block/aoe/aoeblk.c b/drivers/block/aoe/aoeblk.c index 8a91fcac6f82..348adf335217 100644 --- a/drivers/block/aoe/aoeblk.c +++ b/drivers/block/aoe/aoeblk.c @@ -435,7 +435,7 @@ err_mempool: err: spin_lock_irqsave(&d->lock, flags); d->flags &= ~DEVFL_GD_NOW; - schedule_work(&d->work); + queue_work(aoe_wq, &d->work); spin_unlock_irqrestore(&d->lock, flags); } diff --git a/drivers/block/aoe/aoecmd.c b/drivers/block/aoe/aoecmd.c index 384073ef2323..d7317425be51 100644 --- a/drivers/block/aoe/aoecmd.c +++ b/drivers/block/aoe/aoecmd.c @@ -968,7 +968,7 @@ ataid_complete(struct aoedev *d, struct aoetgt *t, unsigned char *id) d->flags |= DEVFL_NEWSIZE; else d->flags |= DEVFL_GDALLOC; - schedule_work(&d->work); + queue_work(aoe_wq, &d->work); } static void diff --git a/drivers/block/aoe/aoedev.c b/drivers/block/aoe/aoedev.c index c5753c6bfe80..b381d1c3ef32 100644 --- a/drivers/block/aoe/aoedev.c +++ b/drivers/block/aoe/aoedev.c @@ -321,7 +321,7 @@ flush(const char __user *str, size_t cnt, int exiting) specified = 1; } - flush_scheduled_work(); + flush_workqueue(aoe_wq); /* pass one: do aoedev_downdev, which might sleep */ restart1: spin_lock_irqsave(&devlist_lock, flags); @@ -520,7 +520,7 @@ freetgt(struct aoedev *d, struct aoetgt *t) void aoedev_exit(void) { - flush_scheduled_work(); + flush_workqueue(aoe_wq); flush(NULL, 0, EXITING); } diff --git a/drivers/block/aoe/aoemain.c b/drivers/block/aoe/aoemain.c index 1e4e2971171c..6238c4c87cfc 100644 --- a/drivers/block/aoe/aoemain.c +++ b/drivers/block/aoe/aoemain.c @@ -16,6 +16,7 @@ MODULE_DESCRIPTION("AoE block/char driver for 2.6.2 and newer 2.6 kernels"); MODULE_VERSION(VERSION); static struct timer_list timer; +struct workqueue_struct *aoe_wq; static void discover_timer(struct timer_list *t) { @@ -35,6 +36,7 @@ aoe_exit(void) aoechr_exit(); aoedev_exit(); aoeblk_exit(); /* free cache after de-allocating bufs */ + destroy_workqueue(aoe_wq); } static int __init @@ -42,9 +44,13 @@ aoe_init(void) { int ret; + aoe_wq = alloc_workqueue("aoe_wq", 0, 0); + if (!aoe_wq) + return -ENOMEM; + ret = aoedev_init(); if (ret) - return ret; + goto dev_fail; ret = aoechr_init(); if (ret) goto chr_fail; @@ -77,6 +83,8 @@ aoe_init(void) aoechr_exit(); chr_fail: aoedev_exit(); + dev_fail: + destroy_workqueue(aoe_wq); printk(KERN_INFO "aoe: initialisation failure.\n"); return ret; diff --git a/drivers/block/drbd/drbd_bitmap.c b/drivers/block/drbd/drbd_bitmap.c index df25eecf80af..9e060e49b3f8 100644 --- a/drivers/block/drbd/drbd_bitmap.c +++ b/drivers/block/drbd/drbd_bitmap.c @@ -683,7 +683,7 @@ int drbd_bm_resize(struct drbd_device *device, sector_t capacity, int set_new_bi } } - want = ALIGN(words*sizeof(long), PAGE_SIZE) >> PAGE_SHIFT; + want = PFN_UP(words*sizeof(long)); have = b->bm_number_of_pages; if (want == have) { D_ASSERT(device, b->bm_pages != NULL); diff --git a/drivers/block/drbd/drbd_main.c b/drivers/block/drbd/drbd_main.c index 4b0b25cc916e..2887350ae010 100644 --- a/drivers/block/drbd/drbd_main.c +++ b/drivers/block/drbd/drbd_main.c @@ -903,31 +903,6 @@ void drbd_gen_and_send_sync_uuid(struct drbd_peer_device *peer_device) } } -/* communicated if (agreed_features & DRBD_FF_WSAME) */ -static void -assign_p_sizes_qlim(struct drbd_device *device, struct p_sizes *p, - struct request_queue *q) -{ - if (q) { - p->qlim->physical_block_size = cpu_to_be32(queue_physical_block_size(q)); - p->qlim->logical_block_size = cpu_to_be32(queue_logical_block_size(q)); - p->qlim->alignment_offset = cpu_to_be32(queue_alignment_offset(q)); - p->qlim->io_min = cpu_to_be32(queue_io_min(q)); - p->qlim->io_opt = cpu_to_be32(queue_io_opt(q)); - p->qlim->discard_enabled = blk_queue_discard(q); - p->qlim->write_same_capable = 0; - } else { - q = device->rq_queue; - p->qlim->physical_block_size = cpu_to_be32(queue_physical_block_size(q)); - p->qlim->logical_block_size = cpu_to_be32(queue_logical_block_size(q)); - p->qlim->alignment_offset = 0; - p->qlim->io_min = cpu_to_be32(queue_io_min(q)); - p->qlim->io_opt = cpu_to_be32(queue_io_opt(q)); - p->qlim->discard_enabled = 0; - p->qlim->write_same_capable = 0; - } -} - int drbd_send_sizes(struct drbd_peer_device *peer_device, int trigger_reply, enum dds_flags flags) { struct drbd_device *device = peer_device->device; @@ -949,7 +924,9 @@ int drbd_send_sizes(struct drbd_peer_device *peer_device, int trigger_reply, enu memset(p, 0, packet_size); if (get_ldev_if_state(device, D_NEGOTIATING)) { - struct request_queue *q = bdev_get_queue(device->ldev->backing_bdev); + struct block_device *bdev = device->ldev->backing_bdev; + struct request_queue *q = bdev_get_queue(bdev); + d_size = drbd_get_max_capacity(device->ldev); rcu_read_lock(); u_size = rcu_dereference(device->ldev->disk_conf)->disk_size; @@ -957,14 +934,32 @@ int drbd_send_sizes(struct drbd_peer_device *peer_device, int trigger_reply, enu q_order_type = drbd_queue_order_type(device); max_bio_size = queue_max_hw_sectors(q) << 9; max_bio_size = min(max_bio_size, DRBD_MAX_BIO_SIZE); - assign_p_sizes_qlim(device, p, q); + p->qlim->physical_block_size = + cpu_to_be32(bdev_physical_block_size(bdev)); + p->qlim->logical_block_size = + cpu_to_be32(bdev_logical_block_size(bdev)); + p->qlim->alignment_offset = + cpu_to_be32(bdev_alignment_offset(bdev)); + p->qlim->io_min = cpu_to_be32(bdev_io_min(bdev)); + p->qlim->io_opt = cpu_to_be32(bdev_io_opt(bdev)); + p->qlim->discard_enabled = !!bdev_max_discard_sectors(bdev); put_ldev(device); } else { + struct request_queue *q = device->rq_queue; + + p->qlim->physical_block_size = + cpu_to_be32(queue_physical_block_size(q)); + p->qlim->logical_block_size = + cpu_to_be32(queue_logical_block_size(q)); + p->qlim->alignment_offset = 0; + p->qlim->io_min = cpu_to_be32(queue_io_min(q)); + p->qlim->io_opt = cpu_to_be32(queue_io_opt(q)); + p->qlim->discard_enabled = 0; + d_size = 0; u_size = 0; q_order_type = QUEUE_ORDERED_NONE; max_bio_size = DRBD_MAX_BIO_SIZE; /* ... multiple BIOs per peer_request */ - assign_p_sizes_qlim(device, p, NULL); } if (peer_device->connection->agreed_pro_version <= 94) @@ -3586,9 +3581,8 @@ const char *cmdname(enum drbd_packet cmd) * when we want to support more than * one PRO_VERSION */ static const char *cmdnames[] = { + [P_DATA] = "Data", - [P_WSAME] = "WriteSame", - [P_TRIM] = "Trim", [P_DATA_REPLY] = "DataReply", [P_RS_DATA_REPLY] = "RSDataReply", [P_BARRIER] = "Barrier", @@ -3599,7 +3593,6 @@ const char *cmdname(enum drbd_packet cmd) [P_DATA_REQUEST] = "DataRequest", [P_RS_DATA_REQUEST] = "RSDataRequest", [P_SYNC_PARAM] = "SyncParam", - [P_SYNC_PARAM89] = "SyncParam89", [P_PROTOCOL] = "ReportProtocol", [P_UUIDS] = "ReportUUIDs", [P_SIZES] = "ReportSizes", @@ -3607,6 +3600,7 @@ const char *cmdname(enum drbd_packet cmd) [P_SYNC_UUID] = "ReportSyncUUID", [P_AUTH_CHALLENGE] = "AuthChallenge", [P_AUTH_RESPONSE] = "AuthResponse", + [P_STATE_CHG_REQ] = "StateChgRequest", [P_PING] = "Ping", [P_PING_ACK] = "PingAck", [P_RECV_ACK] = "RecvAck", @@ -3617,23 +3611,25 @@ const char *cmdname(enum drbd_packet cmd) [P_NEG_DREPLY] = "NegDReply", [P_NEG_RS_DREPLY] = "NegRSDReply", [P_BARRIER_ACK] = "BarrierAck", - [P_STATE_CHG_REQ] = "StateChgRequest", [P_STATE_CHG_REPLY] = "StateChgReply", [P_OV_REQUEST] = "OVRequest", [P_OV_REPLY] = "OVReply", [P_OV_RESULT] = "OVResult", [P_CSUM_RS_REQUEST] = "CsumRSRequest", [P_RS_IS_IN_SYNC] = "CsumRSIsInSync", + [P_SYNC_PARAM89] = "SyncParam89", [P_COMPRESSED_BITMAP] = "CBitmap", [P_DELAY_PROBE] = "DelayProbe", [P_OUT_OF_SYNC] = "OutOfSync", - [P_RETRY_WRITE] = "RetryWrite", [P_RS_CANCEL] = "RSCancel", [P_CONN_ST_CHG_REQ] = "conn_st_chg_req", [P_CONN_ST_CHG_REPLY] = "conn_st_chg_reply", [P_PROTOCOL_UPDATE] = "protocol_update", + [P_TRIM] = "Trim", [P_RS_THIN_REQ] = "rs_thin_req", [P_RS_DEALLOCATED] = "rs_deallocated", + [P_WSAME] = "WriteSame", + [P_ZEROES] = "Zeroes", /* enum drbd_packet, but not commands - obsoleted flags: * P_MAY_IGNORE diff --git a/drivers/block/drbd/drbd_nl.c b/drivers/block/drbd/drbd_nl.c index b7216c186ba4..013d355a2033 100644 --- a/drivers/block/drbd/drbd_nl.c +++ b/drivers/block/drbd/drbd_nl.c @@ -770,6 +770,7 @@ int drbd_adm_set_role(struct sk_buff *skb, struct genl_info *info) struct set_role_parms parms; int err; enum drbd_ret_code retcode; + enum drbd_state_rv rv; retcode = drbd_adm_prepare(&adm_ctx, skb, info, DRBD_ADM_NEED_MINOR); if (!adm_ctx.reply_skb) @@ -790,14 +791,14 @@ int drbd_adm_set_role(struct sk_buff *skb, struct genl_info *info) mutex_lock(&adm_ctx.resource->adm_mutex); if (info->genlhdr->cmd == DRBD_ADM_PRIMARY) - retcode = (enum drbd_ret_code)drbd_set_role(adm_ctx.device, - R_PRIMARY, parms.assume_uptodate); + rv = drbd_set_role(adm_ctx.device, R_PRIMARY, parms.assume_uptodate); else - retcode = (enum drbd_ret_code)drbd_set_role(adm_ctx.device, - R_SECONDARY, 0); + rv = drbd_set_role(adm_ctx.device, R_SECONDARY, 0); mutex_unlock(&adm_ctx.resource->adm_mutex); genl_lock(); + drbd_adm_finish(&adm_ctx, info, rv); + return 0; out: drbd_adm_finish(&adm_ctx, info, retcode); return 0; @@ -1204,50 +1205,40 @@ static unsigned int drbd_max_discard_sectors(struct drbd_connection *connection) } static void decide_on_discard_support(struct drbd_device *device, - struct request_queue *q, - struct request_queue *b, - bool discard_zeroes_if_aligned) + struct drbd_backing_dev *bdev) { - /* q = drbd device queue (device->rq_queue) - * b = backing device queue (device->ldev->backing_bdev->bd_disk->queue), - * or NULL if diskless - */ - struct drbd_connection *connection = first_peer_device(device)->connection; - bool can_do = b ? blk_queue_discard(b) : true; - - if (can_do && connection->cstate >= C_CONNECTED && !(connection->agreed_features & DRBD_FF_TRIM)) { - can_do = false; - drbd_info(connection, "peer DRBD too old, does not support TRIM: disabling discards\n"); - } - if (can_do) { - /* We don't care for the granularity, really. - * Stacking limits below should fix it for the local - * device. Whether or not it is a suitable granularity - * on the remote device is not our problem, really. If - * you care, you need to use devices with similar - * topology on all peers. */ - blk_queue_discard_granularity(q, 512); - q->limits.max_discard_sectors = drbd_max_discard_sectors(connection); - blk_queue_flag_set(QUEUE_FLAG_DISCARD, q); - q->limits.max_write_zeroes_sectors = drbd_max_discard_sectors(connection); - } else { - blk_queue_flag_clear(QUEUE_FLAG_DISCARD, q); - blk_queue_discard_granularity(q, 0); - q->limits.max_discard_sectors = 0; - q->limits.max_write_zeroes_sectors = 0; - } -} + struct drbd_connection *connection = + first_peer_device(device)->connection; + struct request_queue *q = device->rq_queue; -static void fixup_discard_if_not_supported(struct request_queue *q) -{ - /* To avoid confusion, if this queue does not support discard, clear - * max_discard_sectors, which is what lsblk -D reports to the user. - * Older kernels got this wrong in "stack limits". - * */ - if (!blk_queue_discard(q)) { - blk_queue_max_discard_sectors(q, 0); - blk_queue_discard_granularity(q, 0); + if (bdev && !bdev_max_discard_sectors(bdev->backing_bdev)) + goto not_supported; + + if (connection->cstate >= C_CONNECTED && + !(connection->agreed_features & DRBD_FF_TRIM)) { + drbd_info(connection, + "peer DRBD too old, does not support TRIM: disabling discards\n"); + goto not_supported; } + + /* + * We don't care for the granularity, really. + * + * Stacking limits below should fix it for the local device. Whether or + * not it is a suitable granularity on the remote device is not our + * problem, really. If you care, you need to use devices with similar + * topology on all peers. + */ + blk_queue_discard_granularity(q, 512); + q->limits.max_discard_sectors = drbd_max_discard_sectors(connection); + q->limits.max_write_zeroes_sectors = + drbd_max_discard_sectors(connection); + return; + +not_supported: + blk_queue_discard_granularity(q, 0); + q->limits.max_discard_sectors = 0; + q->limits.max_write_zeroes_sectors = 0; } static void fixup_write_zeroes(struct drbd_device *device, struct request_queue *q) @@ -1273,7 +1264,6 @@ static void drbd_setup_queue_param(struct drbd_device *device, struct drbd_backi unsigned int max_segments = 0; struct request_queue *b = NULL; struct disk_conf *dc; - bool discard_zeroes_if_aligned = true; if (bdev) { b = bdev->backing_bdev->bd_disk->queue; @@ -1282,7 +1272,6 @@ static void drbd_setup_queue_param(struct drbd_device *device, struct drbd_backi rcu_read_lock(); dc = rcu_dereference(device->ldev->disk_conf); max_segments = dc->max_bio_bvecs; - discard_zeroes_if_aligned = dc->discard_zeroes_if_aligned; rcu_read_unlock(); blk_set_stacking_limits(&q->limits); @@ -1292,13 +1281,12 @@ static void drbd_setup_queue_param(struct drbd_device *device, struct drbd_backi /* This is the workaround for "bio would need to, but cannot, be split" */ blk_queue_max_segments(q, max_segments ? max_segments : BLK_MAX_SEGMENTS); blk_queue_segment_boundary(q, PAGE_SIZE-1); - decide_on_discard_support(device, q, b, discard_zeroes_if_aligned); + decide_on_discard_support(device, bdev); if (b) { blk_stack_limits(&q->limits, &b->limits, 0); disk_update_readahead(device->vdisk); } - fixup_discard_if_not_supported(q); fixup_write_zeroes(device, q); } @@ -1437,14 +1425,14 @@ static bool write_ordering_changed(struct disk_conf *a, struct disk_conf *b) static void sanitize_disk_conf(struct drbd_device *device, struct disk_conf *disk_conf, struct drbd_backing_dev *nbc) { - struct request_queue * const q = nbc->backing_bdev->bd_disk->queue; + struct block_device *bdev = nbc->backing_bdev; if (disk_conf->al_extents < DRBD_AL_EXTENTS_MIN) disk_conf->al_extents = DRBD_AL_EXTENTS_MIN; if (disk_conf->al_extents > drbd_al_extents_max(nbc)) disk_conf->al_extents = drbd_al_extents_max(nbc); - if (!blk_queue_discard(q)) { + if (!bdev_max_discard_sectors(bdev)) { if (disk_conf->rs_discard_granularity) { disk_conf->rs_discard_granularity = 0; /* disable feature */ drbd_info(device, "rs_discard_granularity feature disabled\n"); @@ -1453,16 +1441,19 @@ static void sanitize_disk_conf(struct drbd_device *device, struct disk_conf *dis if (disk_conf->rs_discard_granularity) { int orig_value = disk_conf->rs_discard_granularity; + sector_t discard_size = bdev_max_discard_sectors(bdev) << 9; + unsigned int discard_granularity = bdev_discard_granularity(bdev); int remainder; - if (q->limits.discard_granularity > disk_conf->rs_discard_granularity) - disk_conf->rs_discard_granularity = q->limits.discard_granularity; + if (discard_granularity > disk_conf->rs_discard_granularity) + disk_conf->rs_discard_granularity = discard_granularity; - remainder = disk_conf->rs_discard_granularity % q->limits.discard_granularity; + remainder = disk_conf->rs_discard_granularity % + discard_granularity; disk_conf->rs_discard_granularity += remainder; - if (disk_conf->rs_discard_granularity > q->limits.max_discard_sectors << 9) - disk_conf->rs_discard_granularity = q->limits.max_discard_sectors << 9; + if (disk_conf->rs_discard_granularity > discard_size) + disk_conf->rs_discard_granularity = discard_size; if (disk_conf->rs_discard_granularity != orig_value) drbd_info(device, "rs_discard_granularity changed to %d\n", @@ -1611,8 +1602,7 @@ int drbd_adm_disk_opts(struct sk_buff *skb, struct genl_info *info) drbd_send_sync_param(peer_device); } - synchronize_rcu(); - kfree(old_disk_conf); + kvfree_rcu(old_disk_conf); kfree(old_plan); mod_timer(&device->request_timer, jiffies + HZ); goto success; @@ -2443,8 +2433,7 @@ int drbd_adm_net_opts(struct sk_buff *skb, struct genl_info *info) mutex_unlock(&connection->resource->conf_update); mutex_unlock(&connection->data.mutex); - synchronize_rcu(); - kfree(old_net_conf); + kvfree_rcu(old_net_conf); if (connection->cstate >= C_WF_REPORT_PARAMS) { struct drbd_peer_device *peer_device; @@ -2502,6 +2491,7 @@ int drbd_adm_connect(struct sk_buff *skb, struct genl_info *info) struct drbd_resource *resource; struct drbd_connection *connection; enum drbd_ret_code retcode; + enum drbd_state_rv rv; int i; int err; @@ -2621,12 +2611,11 @@ int drbd_adm_connect(struct sk_buff *skb, struct genl_info *info) } rcu_read_unlock(); - retcode = (enum drbd_ret_code)conn_request_state(connection, - NS(conn, C_UNCONNECTED), CS_VERBOSE); + rv = conn_request_state(connection, NS(conn, C_UNCONNECTED), CS_VERBOSE); conn_reconfig_done(connection); mutex_unlock(&adm_ctx.resource->adm_mutex); - drbd_adm_finish(&adm_ctx, info, retcode); + drbd_adm_finish(&adm_ctx, info, rv); return 0; fail: @@ -2734,11 +2723,12 @@ int drbd_adm_disconnect(struct sk_buff *skb, struct genl_info *info) mutex_lock(&adm_ctx.resource->adm_mutex); rv = conn_try_disconnect(connection, parms.force_disconnect); - if (rv < SS_SUCCESS) - retcode = (enum drbd_ret_code)rv; - else - retcode = NO_ERROR; mutex_unlock(&adm_ctx.resource->adm_mutex); + if (rv < SS_SUCCESS) { + drbd_adm_finish(&adm_ctx, info, rv); + return 0; + } + retcode = NO_ERROR; fail: drbd_adm_finish(&adm_ctx, info, retcode); return 0; @@ -2857,8 +2847,7 @@ int drbd_adm_resize(struct sk_buff *skb, struct genl_info *info) new_disk_conf->disk_size = (sector_t)rs.resize_size; rcu_assign_pointer(device->ldev->disk_conf, new_disk_conf); mutex_unlock(&device->resource->conf_update); - synchronize_rcu(); - kfree(old_disk_conf); + kvfree_rcu(old_disk_conf); new_disk_conf = NULL; } diff --git a/drivers/block/drbd/drbd_receiver.c b/drivers/block/drbd/drbd_receiver.c index 08da922f81d1..6762be53f409 100644 --- a/drivers/block/drbd/drbd_receiver.c +++ b/drivers/block/drbd/drbd_receiver.c @@ -364,7 +364,7 @@ drbd_alloc_peer_req(struct drbd_peer_device *peer_device, u64 id, sector_t secto struct drbd_device *device = peer_device->device; struct drbd_peer_request *peer_req; struct page *page = NULL; - unsigned nr_pages = (payload_size + PAGE_SIZE -1) >> PAGE_SHIFT; + unsigned int nr_pages = PFN_UP(payload_size); if (drbd_insert_fault(device, DRBD_FAULT_AL_EE)) return NULL; @@ -1511,7 +1511,6 @@ void drbd_bump_write_ordering(struct drbd_resource *resource, struct drbd_backin int drbd_issue_discard_or_zero_out(struct drbd_device *device, sector_t start, unsigned int nr_sectors, int flags) { struct block_device *bdev = device->ldev->backing_bdev; - struct request_queue *q = bdev_get_queue(bdev); sector_t tmp, nr; unsigned int max_discard_sectors, granularity; int alignment; @@ -1521,10 +1520,10 @@ int drbd_issue_discard_or_zero_out(struct drbd_device *device, sector_t start, u goto zero_out; /* Zero-sector (unknown) and one-sector granularities are the same. */ - granularity = max(q->limits.discard_granularity >> 9, 1U); + granularity = max(bdev_discard_granularity(bdev) >> 9, 1U); alignment = (bdev_discard_alignment(bdev) >> 9) % granularity; - max_discard_sectors = min(q->limits.max_discard_sectors, (1U << 22)); + max_discard_sectors = min(bdev_max_discard_sectors(bdev), (1U << 22)); max_discard_sectors -= max_discard_sectors % granularity; if (unlikely(!max_discard_sectors)) goto zero_out; @@ -1548,7 +1547,8 @@ int drbd_issue_discard_or_zero_out(struct drbd_device *device, sector_t start, u start = tmp; } while (nr_sectors >= max_discard_sectors) { - err |= blkdev_issue_discard(bdev, start, max_discard_sectors, GFP_NOIO, 0); + err |= blkdev_issue_discard(bdev, start, max_discard_sectors, + GFP_NOIO); nr_sectors -= max_discard_sectors; start += max_discard_sectors; } @@ -1560,7 +1560,7 @@ int drbd_issue_discard_or_zero_out(struct drbd_device *device, sector_t start, u nr = nr_sectors; nr -= (unsigned int)nr % granularity; if (nr) { - err |= blkdev_issue_discard(bdev, start, nr, GFP_NOIO, 0); + err |= blkdev_issue_discard(bdev, start, nr, GFP_NOIO); nr_sectors -= nr; start += nr; } @@ -1575,11 +1575,10 @@ int drbd_issue_discard_or_zero_out(struct drbd_device *device, sector_t start, u static bool can_do_reliable_discards(struct drbd_device *device) { - struct request_queue *q = bdev_get_queue(device->ldev->backing_bdev); struct disk_conf *dc; bool can_do; - if (!blk_queue_discard(q)) + if (!bdev_max_discard_sectors(device->ldev->backing_bdev)) return false; rcu_read_lock(); @@ -1629,9 +1628,9 @@ int drbd_submit_peer_request(struct drbd_device *device, struct bio *bio; struct page *page = peer_req->pages; sector_t sector = peer_req->i.sector; - unsigned data_size = peer_req->i.size; - unsigned n_bios = 0; - unsigned nr_pages = (data_size + PAGE_SIZE -1) >> PAGE_SHIFT; + unsigned int data_size = peer_req->i.size; + unsigned int n_bios = 0; + unsigned int nr_pages = PFN_UP(data_size); /* TRIM/DISCARD: for now, always use the helper function * blkdev_issue_zeroout(..., discard=true). @@ -3751,8 +3750,7 @@ static int receive_protocol(struct drbd_connection *connection, struct packet_in drbd_info(connection, "peer data-integrity-alg: %s\n", integrity_alg[0] ? integrity_alg : "(none)"); - synchronize_rcu(); - kfree(old_net_conf); + kvfree_rcu(old_net_conf); return 0; disconnect_rcu_unlock: @@ -3903,7 +3901,6 @@ static int receive_SyncParam(struct drbd_connection *connection, struct packet_i drbd_err(device, "verify-alg of wrong size, " "peer wants %u, accepting only up to %u byte\n", data_size, SHARED_SECRET_MAX); - err = -EIO; goto reconnect; } @@ -4121,8 +4118,7 @@ static int receive_sizes(struct drbd_connection *connection, struct packet_info rcu_assign_pointer(device->ldev->disk_conf, new_disk_conf); mutex_unlock(&connection->resource->conf_update); - synchronize_rcu(); - kfree(old_disk_conf); + kvfree_rcu(old_disk_conf); drbd_info(device, "Peer sets u_size to %lu sectors (old: %lu)\n", (unsigned long)p_usize, (unsigned long)my_usize); diff --git a/drivers/block/drbd/drbd_req.c b/drivers/block/drbd/drbd_req.c index 75be0e16770a..e64bcfba30ef 100644 --- a/drivers/block/drbd/drbd_req.c +++ b/drivers/block/drbd/drbd_req.c @@ -922,7 +922,7 @@ static bool remote_due_to_read_balancing(struct drbd_device *device, sector_t se switch (rbm) { case RB_CONGESTED_REMOTE: - return 0; + return false; case RB_LEAST_PENDING: return atomic_read(&device->local_cnt) > atomic_read(&device->ap_pending_cnt) + atomic_read(&device->rs_pending_cnt); diff --git a/drivers/block/drbd/drbd_state.c b/drivers/block/drbd/drbd_state.c index 4ee11aef6672..3f7bf9f2d874 100644 --- a/drivers/block/drbd/drbd_state.c +++ b/drivers/block/drbd/drbd_state.c @@ -2071,8 +2071,7 @@ static int w_after_conn_state_ch(struct drbd_work *w, int unused) conn_free_crypto(connection); mutex_unlock(&connection->resource->conf_update); - synchronize_rcu(); - kfree(old_conf); + kvfree_rcu(old_conf); } if (ns_max.susp_fen) { diff --git a/drivers/block/drbd/drbd_worker.c b/drivers/block/drbd/drbd_worker.c index 0f9956f4e9c4..af3051dd8912 100644 --- a/drivers/block/drbd/drbd_worker.c +++ b/drivers/block/drbd/drbd_worker.c @@ -1030,7 +1030,7 @@ static void move_to_net_ee_or_free(struct drbd_device *device, struct drbd_peer_ { if (drbd_peer_req_has_active_page(peer_req)) { /* This might happen if sendpage() has not finished */ - int i = (peer_req->i.size + PAGE_SIZE -1) >> PAGE_SHIFT; + int i = PFN_UP(peer_req->i.size); atomic_add(i, &device->pp_in_use_by_net); atomic_sub(i, &device->pp_in_use); spin_lock_irq(&device->resource->req_lock); diff --git a/drivers/block/loop.c b/drivers/block/loop.c index a58595f5ee2c..e2cb51810e89 100644 --- a/drivers/block/loop.c +++ b/drivers/block/loop.c @@ -1,54 +1,7 @@ +// SPDX-License-Identifier: GPL-2.0-only /* - * linux/drivers/block/loop.c - * - * Written by Theodore Ts'o, 3/29/93 - * - * Copyright 1993 by Theodore Ts'o. Redistribution of this file is - * permitted under the GNU General Public License. - * - * DES encryption plus some minor changes by Werner Almesberger, 30-MAY-1993 - * more DES encryption plus IDEA encryption by Nicholas J. Leon, June 20, 1996 - * - * Modularized and updated for 1.1.16 kernel - Mitch Dsouza 28th May 1994 - * Adapted for 1.3.59 kernel - Andries Brouwer, 1 Feb 1996 - * - * Fixed do_loop_request() re-entrancy - Vincent.Renardias@waw.com Mar 20, 1997 - * - * Added devfs support - Richard Gooch <rgooch@atnf.csiro.au> 16-Jan-1998 - * - * Handle sparse backing files correctly - Kenn Humborg, Jun 28, 1998 - * - * Loadable modules and other fixes by AK, 1998 - * - * Make real block number available to downstream transfer functions, enables - * CBC (and relatives) mode encryption requiring unique IVs per data block. - * Reed H. Petty, rhp@draper.net - * - * Maximum number of loop devices now dynamic via max_loop module parameter. - * Russell Kroll <rkroll@exploits.org> 19990701 - * - * Maximum number of loop devices when compiled-in now selectable by passing - * max_loop=<1-255> to the kernel on boot. - * Erik I. Bolsø, <eriki@himolde.no>, Oct 31, 1999 - * - * Completely rewrite request handling to be make_request_fn style and - * non blocking, pushing work to a helper thread. Lots of fixes from - * Al Viro too. - * Jens Axboe <axboe@suse.de>, Nov 2000 - * - * Support up to 256 loop devices - * Heinz Mauelshagen <mge@sistina.com>, Feb 2002 - * - * Support for falling back on the write file operation when the address space - * operations write_begin is not available on the backing filesystem. - * Anton Altaparmakov, 16 Feb 2005 - * - * Still To Fix: - * - Advisory locking is ignored here. - * - Should use an own CAP_* category instead of CAP_SYS_ADMIN - * + * Copyright 1993 by Theodore Ts'o. */ - #include <linux/module.h> #include <linux/moduleparam.h> #include <linux/sched.h> @@ -59,7 +12,6 @@ #include <linux/errno.h> #include <linux/major.h> #include <linux/wait.h> -#include <linux/blkdev.h> #include <linux/blkpg.h> #include <linux/init.h> #include <linux/swap.h> @@ -80,10 +32,62 @@ #include <linux/blk-cgroup.h> #include <linux/sched/mm.h> #include <linux/statfs.h> +#include <linux/uaccess.h> +#include <linux/blk-mq.h> +#include <linux/spinlock.h> +#include <uapi/linux/loop.h> + +/* Possible states of device */ +enum { + Lo_unbound, + Lo_bound, + Lo_rundown, + Lo_deleting, +}; -#include "loop.h" +struct loop_func_table; + +struct loop_device { + int lo_number; + loff_t lo_offset; + loff_t lo_sizelimit; + int lo_flags; + char lo_file_name[LO_NAME_SIZE]; + + struct file * lo_backing_file; + struct block_device *lo_device; + + gfp_t old_gfp_mask; + + spinlock_t lo_lock; + int lo_state; + spinlock_t lo_work_lock; + struct workqueue_struct *workqueue; + struct work_struct rootcg_work; + struct list_head rootcg_cmd_list; + struct list_head idle_worker_list; + struct rb_root worker_tree; + struct timer_list timer; + bool use_dio; + bool sysfs_inited; + + struct request_queue *lo_queue; + struct blk_mq_tag_set tag_set; + struct gendisk *lo_disk; + struct mutex lo_mutex; + bool idr_visible; +}; -#include <linux/uaccess.h> +struct loop_cmd { + struct list_head list_entry; + bool use_aio; /* use AIO interface to handle I/O */ + atomic_t ref; /* only for aio */ + long ret; + struct kiocb iocb; + struct bio_vec *bvec; + struct cgroup_subsys_state *blkcg_css; + struct cgroup_subsys_state *memcg_css; +}; #define LOOP_IDLE_WORKER_TIMEOUT (60 * HZ) #define LOOP_DEFAULT_HW_Q_DEPTH (128) @@ -314,15 +318,12 @@ static int lo_fallocate(struct loop_device *lo, struct request *rq, loff_t pos, mode |= FALLOC_FL_KEEP_SIZE; - if (!blk_queue_discard(lo->lo_queue)) { - ret = -EOPNOTSUPP; - goto out; - } + if (!bdev_max_discard_sectors(lo->lo_device)) + return -EOPNOTSUPP; ret = file->f_op->fallocate(file, mode, pos, blk_rq_bytes(rq)); if (unlikely(ret && ret != -EINVAL && ret != -EOPNOTSUPP)) - ret = -EIO; - out: + return -EIO; return ret; } @@ -572,6 +573,10 @@ static int loop_change_fd(struct loop_device *lo, struct block_device *bdev, if (!file) return -EBADF; + + /* suppress uevents while reconfiguring the device */ + dev_set_uevent_suppress(disk_to_dev(lo->lo_disk), 1); + is_loop = is_loop_device(file); error = loop_global_lock_killable(lo, is_loop); if (error) @@ -626,13 +631,18 @@ static int loop_change_fd(struct loop_device *lo, struct block_device *bdev, fput(old_file); if (partscan) loop_reread_partitions(lo); - return 0; + + error = 0; +done: + /* enable and uncork uevent now that we are done */ + dev_set_uevent_suppress(disk_to_dev(lo->lo_disk), 0); + return error; out_err: loop_global_unlock(lo, is_loop); out_putf: fput(file); - return error; + goto done; } /* loop sysfs attributes */ @@ -762,7 +772,7 @@ static void loop_config_discard(struct loop_device *lo) struct request_queue *backingq = bdev_get_queue(I_BDEV(inode)); max_discard_sectors = backingq->limits.max_write_zeroes_sectors; - granularity = backingq->limits.discard_granularity ?: + granularity = bdev_discard_granularity(I_BDEV(inode)) ?: queue_physical_block_size(backingq); /* @@ -787,14 +797,11 @@ static void loop_config_discard(struct loop_device *lo) q->limits.discard_granularity = granularity; blk_queue_max_discard_sectors(q, max_discard_sectors); blk_queue_max_write_zeroes_sectors(q, max_discard_sectors); - blk_queue_flag_set(QUEUE_FLAG_DISCARD, q); } else { q->limits.discard_granularity = 0; blk_queue_max_discard_sectors(q, 0); blk_queue_max_write_zeroes_sectors(q, 0); - blk_queue_flag_clear(QUEUE_FLAG_DISCARD, q); } - q->limits.discard_alignment = 0; } struct loop_worker { @@ -808,8 +815,6 @@ struct loop_worker { }; static void loop_workfn(struct work_struct *work); -static void loop_rootcg_workfn(struct work_struct *work); -static void loop_free_idle_workers(struct timer_list *timer); #ifdef CONFIG_BLK_CGROUP static inline int queue_on_root_worker(struct cgroup_subsys_state *css) @@ -893,6 +898,39 @@ queue_work: spin_unlock_irq(&lo->lo_work_lock); } +static void loop_set_timer(struct loop_device *lo) +{ + timer_reduce(&lo->timer, jiffies + LOOP_IDLE_WORKER_TIMEOUT); +} + +static void loop_free_idle_workers(struct loop_device *lo, bool delete_all) +{ + struct loop_worker *pos, *worker; + + spin_lock_irq(&lo->lo_work_lock); + list_for_each_entry_safe(worker, pos, &lo->idle_worker_list, + idle_list) { + if (!delete_all && + time_is_after_jiffies(worker->last_ran_at + + LOOP_IDLE_WORKER_TIMEOUT)) + break; + list_del(&worker->idle_list); + rb_erase(&worker->rb_node, &lo->worker_tree); + css_put(worker->blkcg_css); + kfree(worker); + } + if (!list_empty(&lo->idle_worker_list)) + loop_set_timer(lo); + spin_unlock_irq(&lo->lo_work_lock); +} + +static void loop_free_idle_workers_timer(struct timer_list *timer) +{ + struct loop_device *lo = container_of(timer, struct loop_device, timer); + + return loop_free_idle_workers(lo, false); +} + static void loop_update_rotational(struct loop_device *lo) { struct file *file = lo->lo_backing_file; @@ -903,7 +941,7 @@ static void loop_update_rotational(struct loop_device *lo) /* not all filesystems (e.g. tmpfs) have a sb->s_bdev */ if (file_bdev) - nonrot = blk_queue_nonrot(bdev_get_queue(file_bdev)); + nonrot = bdev_nonrot(file_bdev); if (nonrot) blk_queue_flag_set(QUEUE_FLAG_NONROT, q); @@ -967,6 +1005,9 @@ static int loop_configure(struct loop_device *lo, fmode_t mode, /* This is safe, since we have a reference from open(). */ __module_get(THIS_MODULE); + /* suppress uevents while reconfiguring the device */ + dev_set_uevent_suppress(disk_to_dev(lo->lo_disk), 1); + /* * If we don't hold exclusive handle for the device, upgrade to it * here to avoid changing device under exclusive owner. @@ -1011,24 +1052,19 @@ static int loop_configure(struct loop_device *lo, fmode_t mode, !file->f_op->write_iter) lo->lo_flags |= LO_FLAGS_READ_ONLY; - lo->workqueue = alloc_workqueue("loop%d", - WQ_UNBOUND | WQ_FREEZABLE, - 0, - lo->lo_number); if (!lo->workqueue) { - error = -ENOMEM; - goto out_unlock; + lo->workqueue = alloc_workqueue("loop%d", + WQ_UNBOUND | WQ_FREEZABLE, + 0, lo->lo_number); + if (!lo->workqueue) { + error = -ENOMEM; + goto out_unlock; + } } disk_force_media_change(lo->lo_disk, DISK_EVENT_MEDIA_CHANGE); set_disk_ro(lo->lo_disk, (lo->lo_flags & LO_FLAGS_READ_ONLY) != 0); - INIT_WORK(&lo->rootcg_work, loop_rootcg_workfn); - INIT_LIST_HEAD(&lo->rootcg_cmd_list); - INIT_LIST_HEAD(&lo->idle_worker_list); - lo->worker_tree = RB_ROOT; - timer_setup(&lo->timer, loop_free_idle_workers, - TIMER_DEFERRABLE); lo->use_dio = lo->lo_flags & LO_FLAGS_DIRECT_IO; lo->lo_device = bdev; lo->lo_backing_file = file; @@ -1073,7 +1109,12 @@ static int loop_configure(struct loop_device *lo, fmode_t mode, loop_reread_partitions(lo); if (!(mode & FMODE_EXCL)) bd_abort_claiming(bdev, loop_configure); - return 0; + + error = 0; +done: + /* enable and uncork uevent now that we are done */ + dev_set_uevent_suppress(disk_to_dev(lo->lo_disk), 0); + return error; out_unlock: loop_global_unlock(lo, is_loop); @@ -1084,53 +1125,24 @@ out_putf: fput(file); /* This is safe: open() is still holding a reference. */ module_put(THIS_MODULE); - return error; + goto done; } static void __loop_clr_fd(struct loop_device *lo, bool release) { struct file *filp; gfp_t gfp = lo->old_gfp_mask; - struct loop_worker *pos, *worker; - - /* - * Flush loop_configure() and loop_change_fd(). It is acceptable for - * loop_validate_file() to succeed, for actual clear operation has not - * started yet. - */ - mutex_lock(&loop_validate_mutex); - mutex_unlock(&loop_validate_mutex); - /* - * loop_validate_file() now fails because l->lo_state != Lo_bound - * became visible. - */ - - /* - * Since this function is called upon "ioctl(LOOP_CLR_FD)" xor "close() - * after ioctl(LOOP_CLR_FD)", it is a sign of something going wrong if - * lo->lo_state has changed while waiting for lo->lo_mutex. - */ - mutex_lock(&lo->lo_mutex); - BUG_ON(lo->lo_state != Lo_rundown); - mutex_unlock(&lo->lo_mutex); if (test_bit(QUEUE_FLAG_WC, &lo->lo_queue->queue_flags)) blk_queue_write_cache(lo->lo_queue, false, false); - /* freeze request queue during the transition */ - blk_mq_freeze_queue(lo->lo_queue); - - destroy_workqueue(lo->workqueue); - spin_lock_irq(&lo->lo_work_lock); - list_for_each_entry_safe(worker, pos, &lo->idle_worker_list, - idle_list) { - list_del(&worker->idle_list); - rb_erase(&worker->rb_node, &lo->worker_tree); - css_put(worker->blkcg_css); - kfree(worker); - } - spin_unlock_irq(&lo->lo_work_lock); - del_timer_sync(&lo->timer); + /* + * Freeze the request queue when unbinding on a live file descriptor and + * thus an open device. When called from ->release we are guaranteed + * that there is no I/O in progress already. + */ + if (!release) + blk_mq_freeze_queue(lo->lo_queue); spin_lock_irq(&lo->lo_lock); filp = lo->lo_backing_file; @@ -1151,7 +1163,8 @@ static void __loop_clr_fd(struct loop_device *lo, bool release) mapping_set_gfp_mask(filp->f_mapping, gfp); /* This is safe: open() is still holding a reference. */ module_put(THIS_MODULE); - blk_mq_unfreeze_queue(lo->lo_queue); + if (!release) + blk_mq_unfreeze_queue(lo->lo_queue); disk_force_media_change(lo->lo_disk, DISK_EVENT_MEDIA_CHANGE); @@ -1202,11 +1215,20 @@ static int loop_clr_fd(struct loop_device *lo) { int err; - err = mutex_lock_killable(&lo->lo_mutex); + /* + * Since lo_ioctl() is called without locks held, it is possible that + * loop_configure()/loop_change_fd() and loop_clr_fd() run in parallel. + * + * Therefore, use global lock when setting Lo_rundown state in order to + * make sure that loop_validate_file() will fail if the "struct file" + * which loop_configure()/loop_change_fd() found via fget() was this + * loop device. + */ + err = loop_global_lock_killable(lo, true); if (err) return err; if (lo->lo_state != Lo_bound) { - mutex_unlock(&lo->lo_mutex); + loop_global_unlock(lo, true); return -ENXIO; } /* @@ -1219,13 +1241,13 @@ static int loop_clr_fd(struct loop_device *lo) * <dev>/do something like mkfs/losetup -d <dev> causing the losetup -d * command to fail with EBUSY. */ - if (atomic_read(&lo->lo_refcnt) > 1) { + if (disk_openers(lo->lo_disk) > 1) { lo->lo_flags |= LO_FLAGS_AUTOCLEAR; - mutex_unlock(&lo->lo_mutex); + loop_global_unlock(lo, true); return 0; } lo->lo_state = Lo_rundown; - mutex_unlock(&lo->lo_mutex); + loop_global_unlock(lo, true); __loop_clr_fd(lo, false); return 0; @@ -1257,15 +1279,6 @@ loop_set_status(struct loop_device *lo, const struct loop_info64 *info) /* I/O need to be drained during transfer transition */ blk_mq_freeze_queue(lo->lo_queue); - if (size_changed && lo->lo_device->bd_inode->i_mapping->nrpages) { - /* If any pages were dirtied after invalidate_bdev(), try again */ - err = -EAGAIN; - pr_warn("%s: loop%d (%s) still has dirty pages (nrpages=%lu)\n", - __func__, lo->lo_number, lo->lo_file_name, - lo->lo_device->bd_inode->i_mapping->nrpages); - goto out_unfreeze; - } - prev_lo_flags = lo->lo_flags; err = loop_set_status_from_info(lo, info); @@ -1476,21 +1489,10 @@ static int loop_set_block_size(struct loop_device *lo, unsigned long arg) invalidate_bdev(lo->lo_device); blk_mq_freeze_queue(lo->lo_queue); - - /* invalidate_bdev should have truncated all the pages */ - if (lo->lo_device->bd_inode->i_mapping->nrpages) { - err = -EAGAIN; - pr_warn("%s: loop%d (%s) still has dirty pages (nrpages=%lu)\n", - __func__, lo->lo_number, lo->lo_file_name, - lo->lo_device->bd_inode->i_mapping->nrpages); - goto out_unfreeze; - } - blk_queue_logical_block_size(lo->lo_queue, arg); blk_queue_physical_block_size(lo->lo_queue, arg); blk_queue_io_min(lo->lo_queue, arg); loop_update_dio(lo); -out_unfreeze: blk_mq_unfreeze_queue(lo->lo_queue); return err; @@ -1720,33 +1722,15 @@ static int lo_compat_ioctl(struct block_device *bdev, fmode_t mode, } #endif -static int lo_open(struct block_device *bdev, fmode_t mode) -{ - struct loop_device *lo = bdev->bd_disk->private_data; - int err; - - err = mutex_lock_killable(&lo->lo_mutex); - if (err) - return err; - if (lo->lo_state == Lo_deleting) - err = -ENXIO; - else - atomic_inc(&lo->lo_refcnt); - mutex_unlock(&lo->lo_mutex); - return err; -} - static void lo_release(struct gendisk *disk, fmode_t mode) { struct loop_device *lo = disk->private_data; - mutex_lock(&lo->lo_mutex); - if (atomic_dec_return(&lo->lo_refcnt)) - goto out_unlock; + if (disk_openers(disk) > 0) + return; - if (lo->lo_flags & LO_FLAGS_AUTOCLEAR) { - if (lo->lo_state != Lo_bound) - goto out_unlock; + mutex_lock(&lo->lo_mutex); + if (lo->lo_state == Lo_bound && (lo->lo_flags & LO_FLAGS_AUTOCLEAR)) { lo->lo_state = Lo_rundown; mutex_unlock(&lo->lo_mutex); /* @@ -1755,27 +1739,30 @@ static void lo_release(struct gendisk *disk, fmode_t mode) */ __loop_clr_fd(lo, true); return; - } else if (lo->lo_state == Lo_bound) { - /* - * Otherwise keep thread (if running) and config, - * but flush possible ongoing bios in thread. - */ - blk_mq_freeze_queue(lo->lo_queue); - blk_mq_unfreeze_queue(lo->lo_queue); } - -out_unlock: mutex_unlock(&lo->lo_mutex); } +static void lo_free_disk(struct gendisk *disk) +{ + struct loop_device *lo = disk->private_data; + + if (lo->workqueue) + destroy_workqueue(lo->workqueue); + loop_free_idle_workers(lo, true); + del_timer_sync(&lo->timer); + mutex_destroy(&lo->lo_mutex); + kfree(lo); +} + static const struct block_device_operations lo_fops = { .owner = THIS_MODULE, - .open = lo_open, .release = lo_release, .ioctl = lo_ioctl, #ifdef CONFIG_COMPAT .compat_ioctl = lo_compat_ioctl, #endif + .free_disk = lo_free_disk, }; /* @@ -1834,12 +1821,14 @@ static blk_status_t loop_queue_rq(struct blk_mq_hw_ctx *hctx, cmd->blkcg_css = NULL; cmd->memcg_css = NULL; #ifdef CONFIG_BLK_CGROUP - if (rq->bio && rq->bio->bi_blkg) { - cmd->blkcg_css = &bio_blkcg(rq->bio)->css; + if (rq->bio) { + cmd->blkcg_css = bio_blkcg_css(rq->bio); #ifdef CONFIG_MEMCG - cmd->memcg_css = - cgroup_get_e_css(cmd->blkcg_css->cgroup, - &memory_cgrp_subsys); + if (cmd->blkcg_css) { + cmd->memcg_css = + cgroup_get_e_css(cmd->blkcg_css->cgroup, + &memory_cgrp_subsys); + } #endif } #endif @@ -1888,11 +1877,6 @@ static void loop_handle_cmd(struct loop_cmd *cmd) } } -static void loop_set_timer(struct loop_device *lo) -{ - timer_reduce(&lo->timer, jiffies + LOOP_IDLE_WORKER_TIMEOUT); -} - static void loop_process_work(struct loop_worker *worker, struct list_head *cmd_list, struct loop_device *lo) { @@ -1941,27 +1925,6 @@ static void loop_rootcg_workfn(struct work_struct *work) loop_process_work(NULL, &lo->rootcg_cmd_list, lo); } -static void loop_free_idle_workers(struct timer_list *timer) -{ - struct loop_device *lo = container_of(timer, struct loop_device, timer); - struct loop_worker *pos, *worker; - - spin_lock_irq(&lo->lo_work_lock); - list_for_each_entry_safe(worker, pos, &lo->idle_worker_list, - idle_list) { - if (time_is_after_jiffies(worker->last_ran_at + - LOOP_IDLE_WORKER_TIMEOUT)) - break; - list_del(&worker->idle_list); - rb_erase(&worker->rb_node, &lo->worker_tree); - css_put(worker->blkcg_css); - kfree(worker); - } - if (!list_empty(&lo->idle_worker_list)) - loop_set_timer(lo); - spin_unlock_irq(&lo->lo_work_lock); -} - static const struct blk_mq_ops loop_mq_ops = { .queue_rq = loop_queue_rq, .complete = lo_complete_rq, @@ -1977,6 +1940,9 @@ static int loop_add(int i) lo = kzalloc(sizeof(*lo), GFP_KERNEL); if (!lo) goto out; + lo->worker_tree = RB_ROOT; + INIT_LIST_HEAD(&lo->idle_worker_list); + timer_setup(&lo->timer, loop_free_idle_workers_timer, TIMER_DEFERRABLE); lo->lo_state = Lo_unbound; err = mutex_lock_killable(&loop_ctl_mutex); @@ -2046,11 +2012,12 @@ static int loop_add(int i) */ if (!part_shift) disk->flags |= GENHD_FL_NO_PART; - atomic_set(&lo->lo_refcnt, 0); mutex_init(&lo->lo_mutex); lo->lo_number = i; spin_lock_init(&lo->lo_lock); spin_lock_init(&lo->lo_work_lock); + INIT_WORK(&lo->rootcg_work, loop_rootcg_workfn); + INIT_LIST_HEAD(&lo->rootcg_cmd_list); disk->major = LOOP_MAJOR; disk->first_minor = i << part_shift; disk->minors = 1 << part_shift; @@ -2090,15 +2057,14 @@ static void loop_remove(struct loop_device *lo) { /* Make this loop device unreachable from pathname. */ del_gendisk(lo->lo_disk); - blk_cleanup_disk(lo->lo_disk); + blk_cleanup_queue(lo->lo_disk->queue); blk_mq_free_tag_set(&lo->tag_set); mutex_lock(&loop_ctl_mutex); idr_remove(&loop_index_idr, lo->lo_number); mutex_unlock(&loop_ctl_mutex); - /* There is no route which can find this loop device. */ - mutex_destroy(&lo->lo_mutex); - kfree(lo); + + put_disk(lo->lo_disk); } static void loop_probe(dev_t dev) @@ -2137,13 +2103,12 @@ static int loop_control_remove(int idx) ret = mutex_lock_killable(&lo->lo_mutex); if (ret) goto mark_visible; - if (lo->lo_state != Lo_unbound || - atomic_read(&lo->lo_refcnt) > 0) { + if (lo->lo_state != Lo_unbound || disk_openers(lo->lo_disk) > 0) { mutex_unlock(&lo->lo_mutex); ret = -EBUSY; goto mark_visible; } - /* Mark this loop device no longer open()-able. */ + /* Mark this loop device as no more bound, but not quite unbound yet */ lo->lo_state = Lo_deleting; mutex_unlock(&lo->lo_mutex); diff --git a/drivers/block/loop.h b/drivers/block/loop.h deleted file mode 100644 index 082d4b6bfc6a..000000000000 --- a/drivers/block/loop.h +++ /dev/null @@ -1,72 +0,0 @@ -/* - * loop.h - * - * Written by Theodore Ts'o, 3/29/93. - * - * Copyright 1993 by Theodore Ts'o. Redistribution of this file is - * permitted under the GNU General Public License. - */ -#ifndef _LINUX_LOOP_H -#define _LINUX_LOOP_H - -#include <linux/bio.h> -#include <linux/blkdev.h> -#include <linux/blk-mq.h> -#include <linux/spinlock.h> -#include <linux/mutex.h> -#include <uapi/linux/loop.h> - -/* Possible states of device */ -enum { - Lo_unbound, - Lo_bound, - Lo_rundown, - Lo_deleting, -}; - -struct loop_func_table; - -struct loop_device { - int lo_number; - atomic_t lo_refcnt; - loff_t lo_offset; - loff_t lo_sizelimit; - int lo_flags; - char lo_file_name[LO_NAME_SIZE]; - - struct file * lo_backing_file; - struct block_device *lo_device; - - gfp_t old_gfp_mask; - - spinlock_t lo_lock; - int lo_state; - spinlock_t lo_work_lock; - struct workqueue_struct *workqueue; - struct work_struct rootcg_work; - struct list_head rootcg_cmd_list; - struct list_head idle_worker_list; - struct rb_root worker_tree; - struct timer_list timer; - bool use_dio; - bool sysfs_inited; - - struct request_queue *lo_queue; - struct blk_mq_tag_set tag_set; - struct gendisk *lo_disk; - struct mutex lo_mutex; - bool idr_visible; -}; - -struct loop_cmd { - struct list_head list_entry; - bool use_aio; /* use AIO interface to handle I/O */ - atomic_t ref; /* only for aio */ - long ret; - struct kiocb iocb; - struct bio_vec *bvec; - struct cgroup_subsys_state *blkcg_css; - struct cgroup_subsys_state *memcg_css; -}; - -#endif diff --git a/drivers/block/mtip32xx/mtip32xx.c b/drivers/block/mtip32xx/mtip32xx.c index 4fbaf0b4958b..27386a572ba4 100644 --- a/drivers/block/mtip32xx/mtip32xx.c +++ b/drivers/block/mtip32xx/mtip32xx.c @@ -2729,7 +2729,7 @@ static int mtip_dma_alloc(struct driver_data *dd) { struct mtip_port *port = dd->port; - /* Allocate dma memory for RX Fis, Identify, and Sector Bufffer */ + /* Allocate dma memory for RX Fis, Identify, and Sector Buffer */ port->block1 = dma_alloc_coherent(&dd->pdev->dev, BLOCK_DMA_ALLOC_SZ, &port->block1_dma, GFP_KERNEL); diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c index 5a1f98494ddd..ac8b045c777c 100644 --- a/drivers/block/nbd.c +++ b/drivers/block/nbd.c @@ -333,7 +333,6 @@ static int nbd_set_size(struct nbd_device *nbd, loff_t bytesize, if (nbd->config->flags & NBD_FLAG_SEND_TRIM) { nbd->disk->queue->limits.discard_granularity = blksize; - nbd->disk->queue->limits.discard_alignment = blksize; blk_queue_max_discard_sectors(nbd->disk->queue, UINT_MAX); } blk_queue_logical_block_size(nbd->disk->queue, blksize); @@ -947,11 +946,15 @@ static int wait_for_reconnect(struct nbd_device *nbd) struct nbd_config *config = nbd->config; if (!config->dead_conn_timeout) return 0; - if (test_bit(NBD_RT_DISCONNECTED, &config->runtime_flags)) + + if (!wait_event_timeout(config->conn_wait, + test_bit(NBD_RT_DISCONNECTED, + &config->runtime_flags) || + atomic_read(&config->live_connections) > 0, + config->dead_conn_timeout)) return 0; - return wait_event_timeout(config->conn_wait, - atomic_read(&config->live_connections) > 0, - config->dead_conn_timeout) > 0; + + return !test_bit(NBD_RT_DISCONNECTED, &config->runtime_flags); } static int nbd_handle_cmd(struct nbd_cmd *cmd, int index) @@ -1217,11 +1220,11 @@ static int nbd_reconnect_socket(struct nbd_device *nbd, unsigned long arg) return -ENOSPC; } -static void nbd_bdev_reset(struct block_device *bdev) +static void nbd_bdev_reset(struct nbd_device *nbd) { - if (bdev->bd_openers > 1) + if (disk_openers(nbd->disk) > 1) return; - set_capacity(bdev->bd_disk, 0); + set_capacity(nbd->disk, 0); } static void nbd_parse_flags(struct nbd_device *nbd) @@ -1231,8 +1234,6 @@ static void nbd_parse_flags(struct nbd_device *nbd) set_disk_ro(nbd->disk, true); else set_disk_ro(nbd->disk, false); - if (config->flags & NBD_FLAG_SEND_TRIM) - blk_queue_flag_set(QUEUE_FLAG_DISCARD, nbd->disk->queue); if (config->flags & NBD_FLAG_SEND_FLUSH) { if (config->flags & NBD_FLAG_SEND_FUA) blk_queue_write_cache(nbd->disk->queue, true, true); @@ -1318,9 +1319,7 @@ static void nbd_config_put(struct nbd_device *nbd) nbd->tag_set.timeout = 0; nbd->disk->queue->limits.discard_granularity = 0; - nbd->disk->queue->limits.discard_alignment = 0; - blk_queue_max_discard_sectors(nbd->disk->queue, UINT_MAX); - blk_queue_flag_clear(QUEUE_FLAG_DISCARD, nbd->disk->queue); + blk_queue_max_discard_sectors(nbd->disk->queue, 0); mutex_unlock(&nbd->config_lock); nbd_put(nbd); @@ -1389,7 +1388,7 @@ static int nbd_start_device(struct nbd_device *nbd) return nbd_set_size(nbd, config->bytesize, nbd_blksize(config)); } -static int nbd_start_device_ioctl(struct nbd_device *nbd, struct block_device *bdev) +static int nbd_start_device_ioctl(struct nbd_device *nbd) { struct nbd_config *config = nbd->config; int ret; @@ -1408,7 +1407,7 @@ static int nbd_start_device_ioctl(struct nbd_device *nbd, struct block_device *b flush_workqueue(nbd->recv_workq); mutex_lock(&nbd->config_lock); - nbd_bdev_reset(bdev); + nbd_bdev_reset(nbd); /* user requested, ignore socket errors */ if (test_bit(NBD_RT_DISCONNECT_REQUESTED, &config->runtime_flags)) ret = 0; @@ -1422,7 +1421,7 @@ static void nbd_clear_sock_ioctl(struct nbd_device *nbd, { sock_shutdown(nbd); __invalidate_device(bdev, true); - nbd_bdev_reset(bdev); + nbd_bdev_reset(nbd); if (test_and_clear_bit(NBD_RT_HAS_CONFIG_REF, &nbd->config->runtime_flags)) nbd_config_put(nbd); @@ -1468,7 +1467,7 @@ static int __nbd_ioctl(struct block_device *bdev, struct nbd_device *nbd, config->flags = arg; return 0; case NBD_DO_IT: - return nbd_start_device_ioctl(nbd, bdev); + return nbd_start_device_ioctl(nbd); case NBD_CLEAR_QUE: /* * This is for compatibility only. The queue is always cleared @@ -1579,7 +1578,7 @@ static void nbd_release(struct gendisk *disk, fmode_t mode) struct nbd_device *nbd = disk->private_data; if (test_bit(NBD_RT_DISCONNECT_ON_CLOSE, &nbd->config->runtime_flags) && - disk->part0->bd_openers == 0) + disk_openers(disk) == 0) nbd_disconnect_and_put(nbd); nbd_config_put(nbd); @@ -1784,7 +1783,6 @@ static struct nbd_device *nbd_dev_add(int index, unsigned int refs) blk_queue_flag_set(QUEUE_FLAG_NONROT, disk->queue); blk_queue_flag_clear(QUEUE_FLAG_ADD_RANDOM, disk->queue); disk->queue->limits.discard_granularity = 0; - disk->queue->limits.discard_alignment = 0; blk_queue_max_discard_sectors(disk->queue, 0); blk_queue_max_segment_size(disk->queue, UINT_MAX); blk_queue_max_segments(disk->queue, USHRT_MAX); @@ -2082,6 +2080,7 @@ static void nbd_disconnect_and_put(struct nbd_device *nbd) mutex_lock(&nbd->config_lock); nbd_disconnect(nbd); sock_shutdown(nbd); + wake_up(&nbd->config->conn_wait); /* * Make sure recv thread has finished, we can safely call nbd_clear_que() * to cancel the inflight I/Os. diff --git a/drivers/block/null_blk/main.c b/drivers/block/null_blk/main.c index c441a4972064..539cfeac263d 100644 --- a/drivers/block/null_blk/main.c +++ b/drivers/block/null_blk/main.c @@ -11,6 +11,9 @@ #include <linux/init.h> #include "null_blk.h" +#undef pr_fmt +#define pr_fmt(fmt) "null_blk: " fmt + #define FREE_BATCH 16 #define TICKS_PER_SEC 50ULL @@ -232,6 +235,7 @@ static struct nullb_device *null_alloc_dev(void); static void null_free_dev(struct nullb_device *dev); static void null_del_dev(struct nullb *nullb); static int null_add_dev(struct nullb_device *dev); +static struct nullb *null_find_dev_by_name(const char *name); static void null_free_device_storage(struct nullb_device *dev, bool is_cache); static inline struct nullb_device *to_nullb_device(struct config_item *item) @@ -560,6 +564,9 @@ config_item *nullb_group_make_item(struct config_group *group, const char *name) { struct nullb_device *dev; + if (null_find_dev_by_name(name)) + return ERR_PTR(-EEXIST); + dev = null_alloc_dev(); if (!dev) return ERR_PTR(-ENOMEM); @@ -1765,9 +1772,7 @@ static void null_config_discard(struct nullb *nullb) } nullb->q->limits.discard_granularity = nullb->dev->blocksize; - nullb->q->limits.discard_alignment = nullb->dev->blocksize; blk_queue_max_discard_sectors(nullb->q, UINT_MAX >> 9); - blk_queue_flag_set(QUEUE_FLAG_DISCARD, nullb->q); } static const struct block_device_operations null_bio_ops = { @@ -2061,7 +2066,13 @@ static int null_add_dev(struct nullb_device *dev) null_config_discard(nullb); - sprintf(nullb->disk_name, "nullb%d", nullb->index); + if (config_item_name(&dev->item)) { + /* Use configfs dir name as the device name */ + snprintf(nullb->disk_name, sizeof(nullb->disk_name), + "%s", config_item_name(&dev->item)); + } else { + sprintf(nullb->disk_name, "nullb%d", nullb->index); + } rv = null_gendisk_register(nullb); if (rv) @@ -2071,6 +2082,8 @@ static int null_add_dev(struct nullb_device *dev) list_add_tail(&nullb->list, &nullb_list); mutex_unlock(&lock); + pr_info("disk %s created\n", nullb->disk_name); + return 0; out_cleanup_zone: null_free_zoned_dev(dev); @@ -2088,12 +2101,53 @@ out: return rv; } +static struct nullb *null_find_dev_by_name(const char *name) +{ + struct nullb *nullb = NULL, *nb; + + mutex_lock(&lock); + list_for_each_entry(nb, &nullb_list, list) { + if (strcmp(nb->disk_name, name) == 0) { + nullb = nb; + break; + } + } + mutex_unlock(&lock); + + return nullb; +} + +static int null_create_dev(void) +{ + struct nullb_device *dev; + int ret; + + dev = null_alloc_dev(); + if (!dev) + return -ENOMEM; + + ret = null_add_dev(dev); + if (ret) { + null_free_dev(dev); + return ret; + } + + return 0; +} + +static void null_destroy_dev(struct nullb *nullb) +{ + struct nullb_device *dev = nullb->dev; + + null_del_dev(nullb); + null_free_dev(dev); +} + static int __init null_init(void) { int ret = 0; unsigned int i; struct nullb *nullb; - struct nullb_device *dev; if (g_bs > PAGE_SIZE) { pr_warn("invalid block size\n"); @@ -2113,19 +2167,21 @@ static int __init null_init(void) } if (g_queue_mode == NULL_Q_RQ) { - pr_err("legacy IO path no longer available\n"); + pr_err("legacy IO path is no longer available\n"); return -EINVAL; } + if (g_queue_mode == NULL_Q_MQ && g_use_per_node_hctx) { if (g_submit_queues != nr_online_nodes) { pr_warn("submit_queues param is set to %u.\n", - nr_online_nodes); + nr_online_nodes); g_submit_queues = nr_online_nodes; } - } else if (g_submit_queues > nr_cpu_ids) + } else if (g_submit_queues > nr_cpu_ids) { g_submit_queues = nr_cpu_ids; - else if (g_submit_queues <= 0) + } else if (g_submit_queues <= 0) { g_submit_queues = 1; + } if (g_queue_mode == NULL_Q_MQ && shared_tags) { ret = null_init_tag_set(NULL, &tag_set); @@ -2149,16 +2205,9 @@ static int __init null_init(void) } for (i = 0; i < nr_devices; i++) { - dev = null_alloc_dev(); - if (!dev) { - ret = -ENOMEM; - goto err_dev; - } - ret = null_add_dev(dev); - if (ret) { - null_free_dev(dev); + ret = null_create_dev(); + if (ret) goto err_dev; - } } pr_info("module loaded\n"); @@ -2167,9 +2216,7 @@ static int __init null_init(void) err_dev: while (!list_empty(&nullb_list)) { nullb = list_entry(nullb_list.next, struct nullb, list); - dev = nullb->dev; - null_del_dev(nullb); - null_free_dev(dev); + null_destroy_dev(nullb); } unregister_blkdev(null_major, "nullb"); err_conf: @@ -2190,12 +2237,8 @@ static void __exit null_exit(void) mutex_lock(&lock); while (!list_empty(&nullb_list)) { - struct nullb_device *dev; - nullb = list_entry(nullb_list.next, struct nullb, list); - dev = nullb->dev; - null_del_dev(nullb); - null_free_dev(dev); + null_destroy_dev(nullb); } mutex_unlock(&lock); diff --git a/drivers/block/null_blk/null_blk.h b/drivers/block/null_blk/null_blk.h index 78eb56b0ca55..4525a65e1b23 100644 --- a/drivers/block/null_blk/null_blk.h +++ b/drivers/block/null_blk/null_blk.h @@ -16,13 +16,15 @@ #include <linux/mutex.h> struct nullb_cmd { - struct request *rq; - struct bio *bio; + union { + struct request *rq; + struct bio *bio; + }; unsigned int tag; blk_status_t error; + bool fake_timeout; struct nullb_queue *nq; struct hrtimer timer; - bool fake_timeout; }; struct nullb_queue { diff --git a/drivers/block/null_blk/zoned.c b/drivers/block/null_blk/zoned.c index dae54dd1aeac..ed158ea4fdd1 100644 --- a/drivers/block/null_blk/zoned.c +++ b/drivers/block/null_blk/zoned.c @@ -6,6 +6,9 @@ #define CREATE_TRACE_POINTS #include "trace.h" +#undef pr_fmt +#define pr_fmt(fmt) "null_blk: " fmt + static inline sector_t mb_to_sects(unsigned long mb) { return ((sector_t)mb * SZ_1M) >> SECTOR_SHIFT; @@ -75,8 +78,8 @@ int null_init_zoned_dev(struct nullb_device *dev, struct request_queue *q) dev->zone_capacity = dev->zone_size; if (dev->zone_capacity > dev->zone_size) { - pr_err("null_blk: zone capacity (%lu MB) larger than zone size (%lu MB)\n", - dev->zone_capacity, dev->zone_size); + pr_err("zone capacity (%lu MB) larger than zone size (%lu MB)\n", + dev->zone_capacity, dev->zone_size); return -EINVAL; } diff --git a/drivers/block/pktcdvd.c b/drivers/block/pktcdvd.c index 86c8794ede41..789093375344 100644 --- a/drivers/block/pktcdvd.c +++ b/drivers/block/pktcdvd.c @@ -12,7 +12,7 @@ * Theory of operation: * * At the lowest level, there is the standard driver for the CD/DVD device, - * typically ide-cd.c or sr.c. This driver can handle read and write requests, + * such as drivers/scsi/sr.c. This driver can handle read and write requests, * but it doesn't know anything about the special restrictions that apply to * packet writing. One restriction is that write requests must be aligned to * packet boundaries on the physical media, and the size of a write request @@ -522,7 +522,7 @@ static struct packet_data *pkt_alloc_packet_data(int frames) goto no_pkt; pkt->frames = frames; - pkt->w_bio = bio_kmalloc(GFP_KERNEL, frames); + pkt->w_bio = bio_kmalloc(frames, GFP_KERNEL); if (!pkt->w_bio) goto no_bio; @@ -536,27 +536,21 @@ static struct packet_data *pkt_alloc_packet_data(int frames) bio_list_init(&pkt->orig_bios); for (i = 0; i < frames; i++) { - struct bio *bio = bio_kmalloc(GFP_KERNEL, 1); - if (!bio) + pkt->r_bios[i] = bio_kmalloc(1, GFP_KERNEL); + if (!pkt->r_bios[i]) goto no_rd_bio; - - pkt->r_bios[i] = bio; } return pkt; no_rd_bio: - for (i = 0; i < frames; i++) { - struct bio *bio = pkt->r_bios[i]; - if (bio) - bio_put(bio); - } - + for (i = 0; i < frames; i++) + kfree(pkt->r_bios[i]); no_page: for (i = 0; i < frames / FRAMES_PER_PAGE; i++) if (pkt->pages[i]) __free_page(pkt->pages[i]); - bio_put(pkt->w_bio); + kfree(pkt->w_bio); no_bio: kfree(pkt); no_pkt: @@ -570,14 +564,11 @@ static void pkt_free_packet_data(struct packet_data *pkt) { int i; - for (i = 0; i < pkt->frames; i++) { - struct bio *bio = pkt->r_bios[i]; - if (bio) - bio_put(bio); - } + for (i = 0; i < pkt->frames; i++) + kfree(pkt->r_bios[i]); for (i = 0; i < pkt->frames / FRAMES_PER_PAGE; i++) __free_page(pkt->pages[i]); - bio_put(pkt->w_bio); + kfree(pkt->w_bio); kfree(pkt); } @@ -951,6 +942,7 @@ static void pkt_end_io_read(struct bio *bio) if (bio->bi_status) atomic_inc(&pkt->io_errors); + bio_uninit(bio); if (atomic_dec_and_test(&pkt->io_wait)) { atomic_inc(&pkt->run_sm); wake_up(&pd->wqueue); @@ -968,6 +960,7 @@ static void pkt_end_io_packet_write(struct bio *bio) pd->stats.pkt_ended++; + bio_uninit(bio); pkt_bio_finished(pd); atomic_dec(&pkt->io_wait); atomic_inc(&pkt->run_sm); @@ -1022,7 +1015,7 @@ static void pkt_gather_data(struct pktcdvd_device *pd, struct packet_data *pkt) continue; bio = pkt->r_bios[f]; - bio_reset(bio, pd->bdev, REQ_OP_READ); + bio_init(bio, pd->bdev, bio->bi_inline_vecs, 1, REQ_OP_READ); bio->bi_iter.bi_sector = pkt->sector + f * (CD_FRAMESIZE >> 9); bio->bi_end_io = pkt_end_io_read; bio->bi_private = pkt; @@ -1235,7 +1228,8 @@ static void pkt_start_write(struct pktcdvd_device *pd, struct packet_data *pkt) { int f; - bio_reset(pkt->w_bio, pd->bdev, REQ_OP_WRITE); + bio_init(pkt->w_bio, pd->bdev, pkt->w_bio->bi_inline_vecs, pkt->frames, + REQ_OP_WRITE); pkt->w_bio->bi_iter.bi_sector = pkt->sector; pkt->w_bio->bi_end_io = pkt_end_io_packet_write; pkt->w_bio->bi_private = pkt; diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c index b844432bad20..2b21f717cce1 100644 --- a/drivers/block/rbd.c +++ b/drivers/block/rbd.c @@ -4942,7 +4942,6 @@ static int rbd_init_disk(struct rbd_device *rbd_dev) blk_queue_io_opt(q, rbd_dev->opts->alloc_size); if (rbd_dev->opts->trim) { - blk_queue_flag_set(QUEUE_FLAG_DISCARD, q); q->limits.discard_granularity = rbd_dev->opts->alloc_size; blk_queue_max_discard_sectors(q, objset_bytes >> SECTOR_SHIFT); blk_queue_max_write_zeroes_sectors(q, objset_bytes >> SECTOR_SHIFT); diff --git a/drivers/block/rnbd/rnbd-clt.c b/drivers/block/rnbd/rnbd-clt.c index b66e8840b94b..409c76b81aed 100644 --- a/drivers/block/rnbd/rnbd-clt.c +++ b/drivers/block/rnbd/rnbd-clt.c @@ -25,6 +25,7 @@ static int rnbd_client_major; static DEFINE_IDA(index_ida); static DEFINE_MUTEX(sess_lock); static LIST_HEAD(sess_list); +static struct workqueue_struct *rnbd_clt_wq; /* * Maximum number of partitions an instance can have. @@ -1364,11 +1365,9 @@ static void setup_request_queue(struct rnbd_clt_dev *dev) blk_queue_max_discard_sectors(dev->queue, dev->max_discard_sectors); dev->queue->limits.discard_granularity = dev->discard_granularity; dev->queue->limits.discard_alignment = dev->discard_alignment; - if (dev->max_discard_sectors) - blk_queue_flag_set(QUEUE_FLAG_DISCARD, dev->queue); if (dev->secure_discard) - blk_queue_flag_set(QUEUE_FLAG_SECERASE, dev->queue); - + blk_queue_max_secure_erase_sectors(dev->queue, + dev->max_discard_sectors); blk_queue_flag_set(QUEUE_FLAG_SAME_COMP, dev->queue); blk_queue_flag_set(QUEUE_FLAG_SAME_FORCE, dev->queue); blk_queue_max_segments(dev->queue, dev->max_segments); @@ -1761,12 +1760,12 @@ static void rnbd_destroy_sessions(void) * procedure takes minutes. */ INIT_WORK(&dev->unmap_on_rmmod_work, unmap_device_work); - queue_work(system_long_wq, &dev->unmap_on_rmmod_work); + queue_work(rnbd_clt_wq, &dev->unmap_on_rmmod_work); } rnbd_clt_put_sess(sess); } /* Wait for all scheduled unmap works */ - flush_workqueue(system_long_wq); + flush_workqueue(rnbd_clt_wq); WARN_ON(!list_empty(&sess_list)); } @@ -1791,6 +1790,14 @@ static int __init rnbd_client_init(void) pr_err("Failed to load module, creating sysfs device files failed, err: %d\n", err); unregister_blkdev(rnbd_client_major, "rnbd"); + return err; + } + rnbd_clt_wq = alloc_workqueue("rnbd_clt_wq", 0, 0); + if (!rnbd_clt_wq) { + pr_err("Failed to load module, alloc_workqueue failed.\n"); + rnbd_clt_destroy_sysfs_files(); + unregister_blkdev(rnbd_client_major, "rnbd"); + err = -ENOMEM; } return err; @@ -1801,6 +1808,7 @@ static void __exit rnbd_client_exit(void) rnbd_destroy_sessions(); unregister_blkdev(rnbd_client_major, "rnbd"); ida_destroy(&index_ida); + destroy_workqueue(rnbd_clt_wq); } module_init(rnbd_client_init); diff --git a/drivers/block/rnbd/rnbd-srv-dev.h b/drivers/block/rnbd/rnbd-srv-dev.h index 2c3df02b5e8e..4309e5252469 100644 --- a/drivers/block/rnbd/rnbd-srv-dev.h +++ b/drivers/block/rnbd/rnbd-srv-dev.h @@ -44,16 +44,12 @@ static inline int rnbd_dev_get_max_hw_sects(const struct rnbd_dev *dev) static inline int rnbd_dev_get_secure_discard(const struct rnbd_dev *dev) { - return blk_queue_secure_erase(bdev_get_queue(dev->bdev)); + return bdev_max_secure_erase_sectors(dev->bdev); } static inline int rnbd_dev_get_max_discard_sects(const struct rnbd_dev *dev) { - if (!blk_queue_discard(bdev_get_queue(dev->bdev))) - return 0; - - return blk_queue_get_max_sectors(bdev_get_queue(dev->bdev), - REQ_OP_DISCARD); + return bdev_max_discard_sectors(dev->bdev); } static inline int rnbd_dev_get_discard_granularity(const struct rnbd_dev *dev) @@ -63,7 +59,7 @@ static inline int rnbd_dev_get_discard_granularity(const struct rnbd_dev *dev) static inline int rnbd_dev_get_discard_alignment(const struct rnbd_dev *dev) { - return bdev_get_queue(dev->bdev)->limits.discard_alignment; + return bdev_discard_alignment(dev->bdev); } #endif /* RNBD_SRV_DEV_H */ diff --git a/drivers/block/rnbd/rnbd-srv.c b/drivers/block/rnbd/rnbd-srv.c index f04df6294650..beaef43a67b9 100644 --- a/drivers/block/rnbd/rnbd-srv.c +++ b/drivers/block/rnbd/rnbd-srv.c @@ -533,7 +533,6 @@ static void rnbd_srv_fill_msg_open_rsp(struct rnbd_msg_open_rsp *rsp, struct rnbd_srv_sess_dev *sess_dev) { struct rnbd_dev *rnbd_dev = sess_dev->rnbd_dev; - struct request_queue *q = bdev_get_queue(rnbd_dev->bdev); rsp->hdr.type = cpu_to_le16(RNBD_MSG_OPEN_RSP); rsp->device_id = @@ -558,9 +557,9 @@ static void rnbd_srv_fill_msg_open_rsp(struct rnbd_msg_open_rsp *rsp, rsp->secure_discard = cpu_to_le16(rnbd_dev_get_secure_discard(rnbd_dev)); rsp->cache_policy = 0; - if (test_bit(QUEUE_FLAG_WC, &q->queue_flags)) + if (bdev_write_cache(rnbd_dev->bdev)) rsp->cache_policy |= RNBD_WRITEBACK; - if (blk_queue_fua(q)) + if (bdev_fua(rnbd_dev->bdev)) rsp->cache_policy |= RNBD_FUA; } diff --git a/drivers/block/virtio_blk.c b/drivers/block/virtio_blk.c index a8bcf3f664af..d624cc8eddc3 100644 --- a/drivers/block/virtio_blk.c +++ b/drivers/block/virtio_blk.c @@ -867,11 +867,12 @@ static int virtblk_probe(struct virtio_device *vdev) blk_queue_io_opt(q, blk_size * opt_io_size); if (virtio_has_feature(vdev, VIRTIO_BLK_F_DISCARD)) { - q->limits.discard_granularity = blk_size; - virtio_cread(vdev, struct virtio_blk_config, discard_sector_alignment, &v); - q->limits.discard_alignment = v ? v << SECTOR_SHIFT : 0; + if (v) + q->limits.discard_granularity = v << SECTOR_SHIFT; + else + q->limits.discard_granularity = blk_size; virtio_cread(vdev, struct virtio_blk_config, max_discard_sectors, &v); @@ -888,8 +889,6 @@ static int virtblk_probe(struct virtio_device *vdev) v = sg_elems; blk_queue_max_discard_segments(q, min(v, MAX_DISCARD_SEGMENTS)); - - blk_queue_flag_set(QUEUE_FLAG_DISCARD, q); } if (virtio_has_feature(vdev, VIRTIO_BLK_F_WRITE_ZEROES)) { diff --git a/drivers/block/xen-blkback/blkback.c b/drivers/block/xen-blkback/blkback.c index de42458195bc..a97f2bf5b01b 100644 --- a/drivers/block/xen-blkback/blkback.c +++ b/drivers/block/xen-blkback/blkback.c @@ -970,7 +970,6 @@ static int dispatch_discard_io(struct xen_blkif_ring *ring, int status = BLKIF_RSP_OKAY; struct xen_blkif *blkif = ring->blkif; struct block_device *bdev = blkif->vbd.bdev; - unsigned long secure; struct phys_req preq; xen_blkif_get(blkif); @@ -987,13 +986,15 @@ static int dispatch_discard_io(struct xen_blkif_ring *ring, } ring->st_ds_req++; - secure = (blkif->vbd.discard_secure && - (req->u.discard.flag & BLKIF_DISCARD_SECURE)) ? - BLKDEV_DISCARD_SECURE : 0; + if (blkif->vbd.discard_secure && + (req->u.discard.flag & BLKIF_DISCARD_SECURE)) + err = blkdev_issue_secure_erase(bdev, + req->u.discard.sector_number, + req->u.discard.nr_sectors, GFP_KERNEL); + else + err = blkdev_issue_discard(bdev, req->u.discard.sector_number, + req->u.discard.nr_sectors, GFP_KERNEL); - err = blkdev_issue_discard(bdev, req->u.discard.sector_number, - req->u.discard.nr_sectors, - GFP_KERNEL, secure); fail_response: if (err == -EOPNOTSUPP) { pr_debug("discard op failed, not supported\n"); diff --git a/drivers/block/xen-blkback/xenbus.c b/drivers/block/xen-blkback/xenbus.c index f09040435e2e..97de13b14175 100644 --- a/drivers/block/xen-blkback/xenbus.c +++ b/drivers/block/xen-blkback/xenbus.c @@ -484,7 +484,6 @@ static int xen_vbd_create(struct xen_blkif *blkif, blkif_vdev_t handle, { struct xen_vbd *vbd; struct block_device *bdev; - struct request_queue *q; vbd = &blkif->vbd; vbd->handle = handle; @@ -516,11 +515,9 @@ static int xen_vbd_create(struct xen_blkif *blkif, blkif_vdev_t handle, if (vbd->bdev->bd_disk->flags & GENHD_FL_REMOVABLE) vbd->type |= VDISK_REMOVABLE; - q = bdev_get_queue(bdev); - if (q && test_bit(QUEUE_FLAG_WC, &q->queue_flags)) + if (bdev_write_cache(bdev)) vbd->flush_support = true; - - if (q && blk_queue_secure_erase(q)) + if (bdev_max_secure_erase_sectors(bdev)) vbd->discard_secure = true; vbd->feature_gnt_persistent = feature_persistent; @@ -578,22 +575,21 @@ static void xen_blkbk_discard(struct xenbus_transaction xbt, struct backend_info int err; int state = 0; struct block_device *bdev = be->blkif->vbd.bdev; - struct request_queue *q = bdev_get_queue(bdev); if (!xenbus_read_unsigned(dev->nodename, "discard-enable", 1)) return; - if (blk_queue_discard(q)) { + if (bdev_max_discard_sectors(bdev)) { err = xenbus_printf(xbt, dev->nodename, "discard-granularity", "%u", - q->limits.discard_granularity); + bdev_discard_granularity(bdev)); if (err) { dev_warn(&dev->dev, "writing discard-granularity (%d)", err); return; } err = xenbus_printf(xbt, dev->nodename, "discard-alignment", "%u", - q->limits.discard_alignment); + bdev_discard_alignment(bdev)); if (err) { dev_warn(&dev->dev, "writing discard-alignment (%d)", err); return; diff --git a/drivers/block/xen-blkfront.c b/drivers/block/xen-blkfront.c index 003056d4f7f5..0f3f5238f7bc 100644 --- a/drivers/block/xen-blkfront.c +++ b/drivers/block/xen-blkfront.c @@ -944,13 +944,13 @@ static void blkif_set_queue_limits(struct blkfront_info *info) blk_queue_flag_set(QUEUE_FLAG_VIRT, rq); if (info->feature_discard) { - blk_queue_flag_set(QUEUE_FLAG_DISCARD, rq); blk_queue_max_discard_sectors(rq, get_capacity(gd)); rq->limits.discard_granularity = info->discard_granularity ?: info->physical_sector_size; rq->limits.discard_alignment = info->discard_alignment; if (info->feature_secdiscard) - blk_queue_flag_set(QUEUE_FLAG_SECERASE, rq); + blk_queue_max_secure_erase_sectors(rq, + get_capacity(gd)); } /* Hard sector size and max sectors impersonate the equiv. hardware. */ @@ -1606,8 +1606,8 @@ static irqreturn_t blkif_interrupt(int irq, void *dev_id) blkif_req(req)->error = BLK_STS_NOTSUPP; info->feature_discard = 0; info->feature_secdiscard = 0; - blk_queue_flag_clear(QUEUE_FLAG_DISCARD, rq); - blk_queue_flag_clear(QUEUE_FLAG_SECERASE, rq); + blk_queue_max_discard_sectors(rq, 0); + blk_queue_max_secure_erase_sectors(rq, 0); } break; case BLKIF_OP_FLUSH_DISKCACHE: diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c index e9474b02012d..6853dd3c7d3a 100644 --- a/drivers/block/zram/zram_drv.c +++ b/drivers/block/zram/zram_drv.c @@ -1675,9 +1675,10 @@ static int zram_rw_page(struct block_device *bdev, sector_t sector, bv.bv_len = PAGE_SIZE; bv.bv_offset = 0; - start_time = disk_start_io_acct(bdev->bd_disk, SECTORS_PER_PAGE, op); + start_time = bdev_start_io_acct(bdev->bd_disk->part0, + SECTORS_PER_PAGE, op, jiffies); ret = zram_bvec_rw(zram, &bv, index, offset, op, NULL); - disk_end_io_acct(bdev->bd_disk, op, start_time); + bdev_end_io_acct(bdev->bd_disk->part0, op, start_time); out: /* * If I/O fails, just return error(ie, non-zero) without @@ -1786,7 +1787,7 @@ static ssize_t reset_store(struct device *dev, int ret; unsigned short do_reset; struct zram *zram; - struct block_device *bdev; + struct gendisk *disk; ret = kstrtou16(buf, 10, &do_reset); if (ret) @@ -1796,26 +1797,26 @@ static ssize_t reset_store(struct device *dev, return -EINVAL; zram = dev_to_zram(dev); - bdev = zram->disk->part0; + disk = zram->disk; - mutex_lock(&bdev->bd_disk->open_mutex); + mutex_lock(&disk->open_mutex); /* Do not reset an active device or claimed device */ - if (bdev->bd_openers || zram->claim) { - mutex_unlock(&bdev->bd_disk->open_mutex); + if (disk_openers(disk) || zram->claim) { + mutex_unlock(&disk->open_mutex); return -EBUSY; } /* From now on, anyone can't open /dev/zram[0-9] */ zram->claim = true; - mutex_unlock(&bdev->bd_disk->open_mutex); + mutex_unlock(&disk->open_mutex); /* Make sure all the pending I/O are finished */ - sync_blockdev(bdev); + sync_blockdev(disk->part0); zram_reset_device(zram); - mutex_lock(&bdev->bd_disk->open_mutex); + mutex_lock(&disk->open_mutex); zram->claim = false; - mutex_unlock(&bdev->bd_disk->open_mutex); + mutex_unlock(&disk->open_mutex); return len; } @@ -1952,7 +1953,6 @@ static int zram_add(void) blk_queue_io_opt(zram->disk->queue, PAGE_SIZE); zram->disk->queue->limits.discard_granularity = PAGE_SIZE; blk_queue_max_discard_sectors(zram->disk->queue, UINT_MAX); - blk_queue_flag_set(QUEUE_FLAG_DISCARD, zram->disk->queue); /* * zram_bio_discard() will clear all logical blocks if logical block @@ -1987,19 +1987,18 @@ out_free_dev: static int zram_remove(struct zram *zram) { - struct block_device *bdev = zram->disk->part0; bool claimed; - mutex_lock(&bdev->bd_disk->open_mutex); - if (bdev->bd_openers) { - mutex_unlock(&bdev->bd_disk->open_mutex); + mutex_lock(&zram->disk->open_mutex); + if (disk_openers(zram->disk)) { + mutex_unlock(&zram->disk->open_mutex); return -EBUSY; } claimed = zram->claim; if (!claimed) zram->claim = true; - mutex_unlock(&bdev->bd_disk->open_mutex); + mutex_unlock(&zram->disk->open_mutex); zram_debugfs_unregister(zram); @@ -2011,7 +2010,7 @@ static int zram_remove(struct zram *zram) ; } else { /* Make sure all the pending I/O are finished */ - sync_blockdev(bdev); + sync_blockdev(zram->disk->part0); zram_reset_device(zram); } diff --git a/drivers/cdrom/cdrom.c b/drivers/cdrom/cdrom.c index 2dc9da683a13..416f723a2dbb 100644 --- a/drivers/cdrom/cdrom.c +++ b/drivers/cdrom/cdrom.c @@ -14,15 +14,6 @@ actually talk to the hardware. Suggestions are welcome. Patches that work are more welcome though. ;-) - To Do List: - ---------------------------------- - - -- Modify sysctl/proc interface. I plan on having one directory per - drive, with entries for outputing general drive information, and sysctl - based tunable parameters such as whether the tray should auto-close for - that drive. Suggestions (or patches) for this welcome! - - Revision History ---------------------------------- 1.00 Date Unknown -- David van Leeuwen <david@tm.tno.nl> @@ -648,6 +639,7 @@ int register_cdrom(struct gendisk *disk, struct cdrom_device_info *cdi) mutex_unlock(&cdrom_mutex); return 0; } +EXPORT_SYMBOL(register_cdrom); #undef ENSURE void unregister_cdrom(struct cdrom_device_info *cdi) @@ -663,6 +655,7 @@ void unregister_cdrom(struct cdrom_device_info *cdi) cd_dbg(CD_REG_UNREG, "drive \"/dev/%s\" unregistered\n", cdi->name); } +EXPORT_SYMBOL(unregister_cdrom); int cdrom_get_media_event(struct cdrom_device_info *cdi, struct media_event_desc *med) @@ -690,6 +683,7 @@ int cdrom_get_media_event(struct cdrom_device_info *cdi, memcpy(med, &buffer[sizeof(*eh)], sizeof(*med)); return 0; } +EXPORT_SYMBOL(cdrom_get_media_event); static int cdrom_get_random_writable(struct cdrom_device_info *cdi, struct rwrt_feature_desc *rfd) @@ -1206,6 +1200,7 @@ err: cdi->use_count--; return ret; } +EXPORT_SYMBOL(cdrom_open); /* This code is similar to that in open_for_data. The routine is called whenever an audio play operation is requested. @@ -1301,6 +1296,7 @@ void cdrom_release(struct cdrom_device_info *cdi, fmode_t mode) cdo->tray_move(cdi, 1); } } +EXPORT_SYMBOL(cdrom_release); static int cdrom_read_mech_status(struct cdrom_device_info *cdi, struct cdrom_changer_info *buf) @@ -1382,6 +1378,7 @@ int cdrom_number_of_slots(struct cdrom_device_info *cdi) kfree(info); return nslots; } +EXPORT_SYMBOL(cdrom_number_of_slots); /* If SLOT < 0, unload the current slot. Otherwise, try to load SLOT. */ @@ -1581,6 +1578,7 @@ void init_cdrom_command(struct packet_command *cgc, void *buf, int len, cgc->data_direction = type; cgc->timeout = CDROM_DEF_TIMEOUT; } +EXPORT_SYMBOL(init_cdrom_command); /* DVD handling */ @@ -1999,6 +1997,7 @@ int cdrom_mode_sense(struct cdrom_device_info *cdi, cgc->data_direction = CGC_DATA_READ; return cdo->generic_packet(cdi, cgc); } +EXPORT_SYMBOL(cdrom_mode_sense); int cdrom_mode_select(struct cdrom_device_info *cdi, struct packet_command *cgc) @@ -2014,6 +2013,7 @@ int cdrom_mode_select(struct cdrom_device_info *cdi, cgc->data_direction = CGC_DATA_WRITE; return cdo->generic_packet(cdi, cgc); } +EXPORT_SYMBOL(cdrom_mode_select); static int cdrom_read_subchannel(struct cdrom_device_info *cdi, struct cdrom_subchnl *subchnl, int mcn) @@ -2443,14 +2443,6 @@ static int cdrom_ioctl_select_disc(struct cdrom_device_info *cdi, return -EINVAL; } - /* - * ->select_disc is a hook to allow a driver-specific way of - * seleting disc. However, since there is no equivalent hook for - * cdrom_slot_status this may not actually be useful... - */ - if (cdi->ops->select_disc) - return cdi->ops->select_disc(cdi, arg); - cd_dbg(CD_CHANGER, "Using generic cdrom_select_disc()\n"); return cdrom_select_disc(cdi, arg); } @@ -2892,6 +2884,7 @@ use_toc: *last_written = toc.cdte_addr.lba; return 0; } +EXPORT_SYMBOL(cdrom_get_last_written); /* return the next writable block. also for udf file system. */ static int cdrom_get_next_writable(struct cdrom_device_info *cdi, @@ -3429,18 +3422,7 @@ int cdrom_ioctl(struct cdrom_device_info *cdi, struct block_device *bdev, return -ENOSYS; } - -EXPORT_SYMBOL(cdrom_get_last_written); -EXPORT_SYMBOL(register_cdrom); -EXPORT_SYMBOL(unregister_cdrom); -EXPORT_SYMBOL(cdrom_open); -EXPORT_SYMBOL(cdrom_release); EXPORT_SYMBOL(cdrom_ioctl); -EXPORT_SYMBOL(cdrom_number_of_slots); -EXPORT_SYMBOL(cdrom_mode_select); -EXPORT_SYMBOL(cdrom_mode_sense); -EXPORT_SYMBOL(init_cdrom_command); -EXPORT_SYMBOL(cdrom_get_media_event); #ifdef CONFIG_SYSCTL diff --git a/drivers/char/agp/amd64-agp.c b/drivers/char/agp/amd64-agp.c index dc78a4fb879e..84a4aa9312cf 100644 --- a/drivers/char/agp/amd64-agp.c +++ b/drivers/char/agp/amd64-agp.c @@ -327,7 +327,7 @@ static int cache_nbs(struct pci_dev *pdev, u32 cap_ptr) { int i; - if (amd_cache_northbridges() < 0) + if (!amd_nb_num()) return -ENODEV; if (!amd_nb_has_feature(AMD_NB_GART)) diff --git a/drivers/clk/at91/clk-generated.c b/drivers/clk/at91/clk-generated.c index 23cc8297ec4c..d429ba52a719 100644 --- a/drivers/clk/at91/clk-generated.c +++ b/drivers/clk/at91/clk-generated.c @@ -117,6 +117,10 @@ static void clk_generated_best_diff(struct clk_rate_request *req, tmp_rate = parent_rate; else tmp_rate = parent_rate / div; + + if (tmp_rate < req->min_rate || tmp_rate > req->max_rate) + return; + tmp_diff = abs(req->rate - tmp_rate); if (*best_diff < 0 || *best_diff >= tmp_diff) { diff --git a/drivers/clk/bcm/clk-bcm2835.c b/drivers/clk/bcm/clk-bcm2835.c index 3ad20e75fd23..48a1eb9f2d55 100644 --- a/drivers/clk/bcm/clk-bcm2835.c +++ b/drivers/clk/bcm/clk-bcm2835.c @@ -941,6 +941,7 @@ static u32 bcm2835_clock_choose_div(struct clk_hw *hw, u64 temp = (u64)parent_rate << CM_DIV_FRAC_BITS; u32 div, mindiv, maxdiv; + do_div(temp, rate); div = temp; div &= ~unused_frac_mask; diff --git a/drivers/clk/sunxi-ng/ccu-sun6i-rtc.c b/drivers/clk/sunxi-ng/ccu-sun6i-rtc.c index 2f3ddc908ebd..d65398497d5f 100644 --- a/drivers/clk/sunxi-ng/ccu-sun6i-rtc.c +++ b/drivers/clk/sunxi-ng/ccu-sun6i-rtc.c @@ -298,10 +298,6 @@ static const struct sunxi_ccu_desc sun6i_rtc_ccu_desc = { .hw_clks = &sun6i_rtc_ccu_hw_clks, }; -static const struct clk_parent_data sun50i_h6_osc32k_fanout_parents[] = { - { .hw = &osc32k_clk.common.hw }, -}; - static const struct clk_parent_data sun50i_h616_osc32k_fanout_parents[] = { { .hw = &osc32k_clk.common.hw }, { .fw_name = "pll-32k" }, @@ -314,13 +310,6 @@ static const struct clk_parent_data sun50i_r329_osc32k_fanout_parents[] = { { .hw = &osc24M_32k_clk.common.hw } }; -static const struct sun6i_rtc_match_data sun50i_h6_rtc_ccu_data = { - .have_ext_osc32k = true, - .have_iosc_calibration = true, - .osc32k_fanout_parents = sun50i_h6_osc32k_fanout_parents, - .osc32k_fanout_nparents = ARRAY_SIZE(sun50i_h6_osc32k_fanout_parents), -}; - static const struct sun6i_rtc_match_data sun50i_h616_rtc_ccu_data = { .have_iosc_calibration = true, .rtc_32k_single_parent = true, @@ -336,10 +325,6 @@ static const struct sun6i_rtc_match_data sun50i_r329_rtc_ccu_data = { static const struct of_device_id sun6i_rtc_ccu_match[] = { { - .compatible = "allwinner,sun50i-h6-rtc", - .data = &sun50i_h6_rtc_ccu_data, - }, - { .compatible = "allwinner,sun50i-h616-rtc", .data = &sun50i_h616_rtc_ccu_data, }, diff --git a/drivers/crypto/qcom-rng.c b/drivers/crypto/qcom-rng.c index 11f30fd48c14..031b5f701a0a 100644 --- a/drivers/crypto/qcom-rng.c +++ b/drivers/crypto/qcom-rng.c @@ -65,6 +65,7 @@ static int qcom_rng_read(struct qcom_rng *rng, u8 *data, unsigned int max) } else { /* copy only remaining bytes */ memcpy(data, &val, max - currsize); + break; } } while (currsize < max); diff --git a/drivers/dma-buf/dma-buf.c b/drivers/dma-buf/dma-buf.c index df23239b04fc..53297a0d9c57 100644 --- a/drivers/dma-buf/dma-buf.c +++ b/drivers/dma-buf/dma-buf.c @@ -407,6 +407,7 @@ static inline int is_dma_buf_file(struct file *file) static struct file *dma_buf_getfile(struct dma_buf *dmabuf, int flags) { + static atomic64_t dmabuf_inode = ATOMIC64_INIT(0); struct file *file; struct inode *inode = alloc_anon_inode(dma_buf_mnt->mnt_sb); @@ -416,6 +417,13 @@ static struct file *dma_buf_getfile(struct dma_buf *dmabuf, int flags) inode->i_size = dmabuf->size; inode_set_bytes(inode, dmabuf->size); + /* + * The ->i_ino acquired from get_next_ino() is not unique thus + * not suitable for using it as dentry name by dmabuf stats. + * Override ->i_ino with the unique and dmabuffs specific + * value. + */ + inode->i_ino = atomic64_add_return(1, &dmabuf_inode); file = alloc_file_pseudo(inode, dma_buf_mnt, "dmabuf", flags, &dma_buf_fops); if (IS_ERR(file)) @@ -543,10 +551,6 @@ struct dma_buf *dma_buf_export(const struct dma_buf_export_info *exp_info) file->f_mode |= FMODE_LSEEK; dmabuf->file = file; - ret = dma_buf_stats_setup(dmabuf); - if (ret) - goto err_sysfs; - mutex_init(&dmabuf->lock); INIT_LIST_HEAD(&dmabuf->attachments); @@ -554,6 +558,10 @@ struct dma_buf *dma_buf_export(const struct dma_buf_export_info *exp_info) list_add(&dmabuf->list_node, &db_list.head); mutex_unlock(&db_list.lock); + ret = dma_buf_stats_setup(dmabuf); + if (ret) + goto err_sysfs; + return dmabuf; err_sysfs: diff --git a/drivers/edac/Kconfig b/drivers/edac/Kconfig index 58ab63642e72..d3e2477948c8 100644 --- a/drivers/edac/Kconfig +++ b/drivers/edac/Kconfig @@ -55,6 +55,7 @@ config EDAC_DECODE_MCE config EDAC_GHES bool "Output ACPI APEI/GHES BIOS detected errors via EDAC" depends on ACPI_APEI_GHES && (EDAC=y) + select UEFI_CPER help Not all machines support hardware-driven error report. Some of those provide a BIOS-driven error report mechanism via ACPI, using the @@ -484,7 +485,7 @@ config EDAC_ARMADA_XP config EDAC_SYNOPSYS tristate "Synopsys DDR Memory Controller" - depends on ARCH_ZYNQ || ARCH_ZYNQMP || ARCH_INTEL_SOCFPGA + depends on ARCH_ZYNQ || ARCH_ZYNQMP || ARCH_INTEL_SOCFPGA || ARCH_MXC help Support for error detection and correction on the Synopsys DDR memory controller. diff --git a/drivers/edac/amd64_edac.c b/drivers/edac/amd64_edac.c index 812baa48b290..2f854feeeb23 100644 --- a/drivers/edac/amd64_edac.c +++ b/drivers/edac/amd64_edac.c @@ -4336,7 +4336,7 @@ static int __init amd64_edac_init(void) if (!x86_match_cpu(amd64_cpuids)) return -ENODEV; - if (amd_cache_northbridges() < 0) + if (!amd_nb_num()) return -ENODEV; opstate_init(); diff --git a/drivers/edac/armada_xp_edac.c b/drivers/edac/armada_xp_edac.c index b1f46a974b9e..038abbb83f4b 100644 --- a/drivers/edac/armada_xp_edac.c +++ b/drivers/edac/armada_xp_edac.c @@ -286,17 +286,10 @@ static int axp_mc_probe(struct platform_device *pdev) struct edac_mc_layer layers[1]; const struct of_device_id *id; struct mem_ctl_info *mci; - struct resource *r; void __iomem *base; uint32_t config; - r = platform_get_resource(pdev, IORESOURCE_MEM, 0); - if (!r) { - dev_err(&pdev->dev, "Unable to get mem resource\n"); - return -ENODEV; - } - - base = devm_ioremap_resource(&pdev->dev, r); + base = devm_platform_ioremap_resource(pdev, 0); if (IS_ERR(base)) { dev_err(&pdev->dev, "Unable to map regs\n"); return PTR_ERR(base); @@ -516,15 +509,8 @@ static int aurora_l2_probe(struct platform_device *pdev) const struct of_device_id *id; uint32_t l2x0_aux_ctrl; void __iomem *base; - struct resource *r; - - r = platform_get_resource(pdev, IORESOURCE_MEM, 0); - if (!r) { - dev_err(&pdev->dev, "Unable to get mem resource\n"); - return -ENODEV; - } - base = devm_ioremap_resource(&pdev->dev, r); + base = devm_platform_ioremap_resource(pdev, 0); if (IS_ERR(base)) { dev_err(&pdev->dev, "Unable to map regs\n"); return PTR_ERR(base); diff --git a/drivers/edac/dmc520_edac.c b/drivers/edac/dmc520_edac.c index b8a7d9594afd..1fa5ca57e9ec 100644 --- a/drivers/edac/dmc520_edac.c +++ b/drivers/edac/dmc520_edac.c @@ -489,7 +489,7 @@ static int dmc520_edac_probe(struct platform_device *pdev) dev = &pdev->dev; for (idx = 0; idx < NUMBER_OF_IRQS; idx++) { - irq = platform_get_irq_byname(pdev, dmc520_irq_configs[idx].name); + irq = platform_get_irq_byname_optional(pdev, dmc520_irq_configs[idx].name); irqs[idx] = irq; masks[idx] = dmc520_irq_configs[idx].mask; if (irq >= 0) { diff --git a/drivers/edac/edac_device.c b/drivers/edac/edac_device.c index 8c4d947fb848..19522c568aa5 100644 --- a/drivers/edac/edac_device.c +++ b/drivers/edac/edac_device.c @@ -47,99 +47,67 @@ static void edac_device_dump_device(struct edac_device_ctl_info *edac_dev) } #endif /* CONFIG_EDAC_DEBUG */ -struct edac_device_ctl_info *edac_device_alloc_ctl_info( - unsigned sz_private, - char *edac_device_name, unsigned nr_instances, - char *edac_block_name, unsigned nr_blocks, - unsigned offset_value, /* zero, 1, or other based offset */ - struct edac_dev_sysfs_block_attribute *attrib_spec, unsigned nr_attrib, - int device_index) +/* + * @off_val: zero, 1, or other based offset + */ +struct edac_device_ctl_info * +edac_device_alloc_ctl_info(unsigned pvt_sz, char *dev_name, unsigned nr_instances, + char *blk_name, unsigned nr_blocks, unsigned off_val, + struct edac_dev_sysfs_block_attribute *attrib_spec, + unsigned nr_attrib, int device_index) { - struct edac_device_ctl_info *dev_ctl; - struct edac_device_instance *dev_inst, *inst; - struct edac_device_block *dev_blk, *blk_p, *blk; struct edac_dev_sysfs_block_attribute *dev_attrib, *attrib_p, *attrib; - unsigned total_size; - unsigned count; + struct edac_device_block *dev_blk, *blk_p, *blk; + struct edac_device_instance *dev_inst, *inst; + struct edac_device_ctl_info *dev_ctl; unsigned instance, block, attr; - void *pvt, *p; + void *pvt; int err; edac_dbg(4, "instances=%d blocks=%d\n", nr_instances, nr_blocks); - /* Calculate the size of memory we need to allocate AND - * determine the offsets of the various item arrays - * (instance,block,attrib) from the start of an allocated structure. - * We want the alignment of each item (instance,block,attrib) - * to be at least as stringent as what the compiler would - * provide if we could simply hardcode everything into a single struct. - */ - p = NULL; - dev_ctl = edac_align_ptr(&p, sizeof(*dev_ctl), 1); + dev_ctl = kzalloc(sizeof(struct edac_device_ctl_info), GFP_KERNEL); + if (!dev_ctl) + return NULL; - /* Calc the 'end' offset past end of ONE ctl_info structure - * which will become the start of the 'instance' array - */ - dev_inst = edac_align_ptr(&p, sizeof(*dev_inst), nr_instances); + dev_inst = kcalloc(nr_instances, sizeof(struct edac_device_instance), GFP_KERNEL); + if (!dev_inst) + goto free; - /* Calc the 'end' offset past the instance array within the ctl_info - * which will become the start of the block array - */ - count = nr_instances * nr_blocks; - dev_blk = edac_align_ptr(&p, sizeof(*dev_blk), count); + dev_ctl->instances = dev_inst; - /* Calc the 'end' offset past the dev_blk array - * which will become the start of the attrib array, if any. - */ - /* calc how many nr_attrib we need */ - if (nr_attrib > 0) - count *= nr_attrib; - dev_attrib = edac_align_ptr(&p, sizeof(*dev_attrib), count); + dev_blk = kcalloc(nr_instances * nr_blocks, sizeof(struct edac_device_block), GFP_KERNEL); + if (!dev_blk) + goto free; - /* Calc the 'end' offset past the attributes array */ - pvt = edac_align_ptr(&p, sz_private, 1); + dev_ctl->blocks = dev_blk; - /* 'pvt' now points to where the private data area is. - * At this point 'pvt' (like dev_inst,dev_blk and dev_attrib) - * is baselined at ZERO - */ - total_size = ((unsigned long)pvt) + sz_private; + if (nr_attrib) { + dev_attrib = kcalloc(nr_attrib, sizeof(struct edac_dev_sysfs_block_attribute), + GFP_KERNEL); + if (!dev_attrib) + goto free; - /* Allocate the amount of memory for the set of control structures */ - dev_ctl = kzalloc(total_size, GFP_KERNEL); - if (dev_ctl == NULL) - return NULL; + dev_ctl->attribs = dev_attrib; + } - /* Adjust pointers so they point within the actual memory we - * just allocated rather than an imaginary chunk of memory - * located at address 0. - * 'dev_ctl' points to REAL memory, while the others are - * ZERO based and thus need to be adjusted to point within - * the allocated memory. - */ - dev_inst = (struct edac_device_instance *) - (((char *)dev_ctl) + ((unsigned long)dev_inst)); - dev_blk = (struct edac_device_block *) - (((char *)dev_ctl) + ((unsigned long)dev_blk)); - dev_attrib = (struct edac_dev_sysfs_block_attribute *) - (((char *)dev_ctl) + ((unsigned long)dev_attrib)); - pvt = sz_private ? (((char *)dev_ctl) + ((unsigned long)pvt)) : NULL; - - /* Begin storing the information into the control info structure */ - dev_ctl->dev_idx = device_index; - dev_ctl->nr_instances = nr_instances; - dev_ctl->instances = dev_inst; - dev_ctl->pvt_info = pvt; + if (pvt_sz) { + pvt = kzalloc(pvt_sz, GFP_KERNEL); + if (!pvt) + goto free; + + dev_ctl->pvt_info = pvt; + } + + dev_ctl->dev_idx = device_index; + dev_ctl->nr_instances = nr_instances; /* Default logging of CEs and UEs */ dev_ctl->log_ce = 1; dev_ctl->log_ue = 1; /* Name of this edac device */ - snprintf(dev_ctl->name,sizeof(dev_ctl->name),"%s",edac_device_name); - - edac_dbg(4, "edac_dev=%p next after end=%p\n", - dev_ctl, pvt + sz_private); + snprintf(dev_ctl->name, sizeof(dev_ctl->name),"%s", dev_name); /* Initialize every Instance */ for (instance = 0; instance < nr_instances; instance++) { @@ -150,15 +118,14 @@ struct edac_device_ctl_info *edac_device_alloc_ctl_info( inst->blocks = blk_p; /* name of this instance */ - snprintf(inst->name, sizeof(inst->name), - "%s%u", edac_device_name, instance); + snprintf(inst->name, sizeof(inst->name), "%s%u", dev_name, instance); /* Initialize every block in each instance */ for (block = 0; block < nr_blocks; block++) { blk = &blk_p[block]; blk->instance = inst; snprintf(blk->name, sizeof(blk->name), - "%s%d", edac_block_name, block+offset_value); + "%s%d", blk_name, block + off_val); edac_dbg(4, "instance=%d inst_p=%p block=#%d block_p=%p name='%s'\n", instance, inst, block, blk, blk->name); @@ -210,10 +177,8 @@ struct edac_device_ctl_info *edac_device_alloc_ctl_info( * Initialize the 'root' kobj for the edac_device controller */ err = edac_device_register_sysfs_main_kobj(dev_ctl); - if (err) { - kfree(dev_ctl); - return NULL; - } + if (err) + goto free; /* at this point, the root kobj is valid, and in order to * 'free' the object, then the function: @@ -223,6 +188,11 @@ struct edac_device_ctl_info *edac_device_alloc_ctl_info( */ return dev_ctl; + +free: + __edac_device_free_ctl_info(dev_ctl); + + return NULL; } EXPORT_SYMBOL_GPL(edac_device_alloc_ctl_info); diff --git a/drivers/edac/edac_device.h b/drivers/edac/edac_device.h index fc2d2c218064..3f44e6b9d387 100644 --- a/drivers/edac/edac_device.h +++ b/drivers/edac/edac_device.h @@ -216,6 +216,8 @@ struct edac_device_ctl_info { */ u32 nr_instances; struct edac_device_instance *instances; + struct edac_device_block *blocks; + struct edac_dev_sysfs_block_attribute *attribs; /* Event counters for the this whole EDAC Device */ struct edac_device_counter counters; @@ -348,4 +350,16 @@ edac_device_handle_ue(struct edac_device_ctl_info *edac_dev, int inst_nr, */ extern int edac_device_alloc_index(void); extern const char *edac_layer_name[]; + +/* Free the actual struct */ +static inline void __edac_device_free_ctl_info(struct edac_device_ctl_info *ci) +{ + if (ci) { + kfree(ci->pvt_info); + kfree(ci->attribs); + kfree(ci->blocks); + kfree(ci->instances); + kfree(ci); + } +} #endif diff --git a/drivers/edac/edac_device_sysfs.c b/drivers/edac/edac_device_sysfs.c index 9a61d92bdf42..ac678b4a21fc 100644 --- a/drivers/edac/edac_device_sysfs.c +++ b/drivers/edac/edac_device_sysfs.c @@ -208,10 +208,7 @@ static void edac_device_ctrl_master_release(struct kobject *kobj) /* decrement the EDAC CORE module ref count */ module_put(edac_dev->owner); - /* free the control struct containing the 'main' kobj - * passed in to this routine - */ - kfree(edac_dev); + __edac_device_free_ctl_info(edac_dev); } /* ktype for the main (master) kobject */ diff --git a/drivers/edac/edac_mc.c b/drivers/edac/edac_mc.c index d2715774af6f..eb58644bb019 100644 --- a/drivers/edac/edac_mc.c +++ b/drivers/edac/edac_mc.c @@ -170,61 +170,6 @@ const char * const edac_mem_types[] = { }; EXPORT_SYMBOL_GPL(edac_mem_types); -/** - * edac_align_ptr - Prepares the pointer offsets for a single-shot allocation - * @p: pointer to a pointer with the memory offset to be used. At - * return, this will be incremented to point to the next offset - * @size: Size of the data structure to be reserved - * @n_elems: Number of elements that should be reserved - * - * If 'size' is a constant, the compiler will optimize this whole function - * down to either a no-op or the addition of a constant to the value of '*p'. - * - * The 'p' pointer is absolutely needed to keep the proper advancing - * further in memory to the proper offsets when allocating the struct along - * with its embedded structs, as edac_device_alloc_ctl_info() does it - * above, for example. - * - * At return, the pointer 'p' will be incremented to be used on a next call - * to this function. - */ -void *edac_align_ptr(void **p, unsigned int size, int n_elems) -{ - unsigned int align, r; - void *ptr = *p; - - *p += size * n_elems; - - /* - * 'p' can possibly be an unaligned item X such that sizeof(X) is - * 'size'. Adjust 'p' so that its alignment is at least as - * stringent as what the compiler would provide for X and return - * the aligned result. - * Here we assume that the alignment of a "long long" is the most - * stringent alignment that the compiler will ever provide by default. - * As far as I know, this is a reasonable assumption. - */ - if (size > sizeof(long)) - align = sizeof(long long); - else if (size > sizeof(int)) - align = sizeof(long); - else if (size > sizeof(short)) - align = sizeof(int); - else if (size > sizeof(char)) - align = sizeof(short); - else - return ptr; - - r = (unsigned long)ptr % align; - - if (r == 0) - return ptr; - - *p += align - r; - - return (void *)(((unsigned long)ptr) + align - r); -} - static void _edac_mc_free(struct mem_ctl_info *mci) { put_device(&mci->dev); @@ -257,6 +202,8 @@ static void mci_release(struct device *dev) } kfree(mci->csrows); } + kfree(mci->pvt_info); + kfree(mci->layers); kfree(mci); } @@ -392,9 +339,8 @@ struct mem_ctl_info *edac_mc_alloc(unsigned int mc_num, { struct mem_ctl_info *mci; struct edac_mc_layer *layer; - unsigned int idx, size, tot_dimms = 1; + unsigned int idx, tot_dimms = 1; unsigned int tot_csrows = 1, tot_channels = 1; - void *pvt, *ptr = NULL; bool per_rank = false; if (WARN_ON(n_layers > EDAC_MAX_LAYERS || n_layers == 0)) @@ -416,41 +362,25 @@ struct mem_ctl_info *edac_mc_alloc(unsigned int mc_num, per_rank = true; } - /* Figure out the offsets of the various items from the start of an mc - * structure. We want the alignment of each item to be at least as - * stringent as what the compiler would provide if we could simply - * hardcode everything into a single struct. - */ - mci = edac_align_ptr(&ptr, sizeof(*mci), 1); - layer = edac_align_ptr(&ptr, sizeof(*layer), n_layers); - pvt = edac_align_ptr(&ptr, sz_pvt, 1); - size = ((unsigned long)pvt) + sz_pvt; - - edac_dbg(1, "allocating %u bytes for mci data (%d %s, %d csrows/channels)\n", - size, - tot_dimms, - per_rank ? "ranks" : "dimms", - tot_csrows * tot_channels); - - mci = kzalloc(size, GFP_KERNEL); - if (mci == NULL) + mci = kzalloc(sizeof(struct mem_ctl_info), GFP_KERNEL); + if (!mci) return NULL; + mci->layers = kcalloc(n_layers, sizeof(struct edac_mc_layer), GFP_KERNEL); + if (!mci->layers) + goto error; + + mci->pvt_info = kzalloc(sz_pvt, GFP_KERNEL); + if (!mci->pvt_info) + goto error; + mci->dev.release = mci_release; device_initialize(&mci->dev); - /* Adjust pointers so they point within the memory we just allocated - * rather than an imaginary chunk of memory located at address 0. - */ - layer = (struct edac_mc_layer *)(((char *)mci) + ((unsigned long)layer)); - pvt = sz_pvt ? (((char *)mci) + ((unsigned long)pvt)) : NULL; - /* setup index and various internal pointers */ mci->mc_idx = mc_num; mci->tot_dimms = tot_dimms; - mci->pvt_info = pvt; mci->n_layers = n_layers; - mci->layers = layer; memcpy(mci->layers, layers, sizeof(*layer) * n_layers); mci->nr_csrows = tot_csrows; mci->num_cschannel = tot_channels; diff --git a/drivers/edac/edac_module.h b/drivers/edac/edac_module.h index aa1f91688eb8..96f6de0c8ff6 100644 --- a/drivers/edac/edac_module.h +++ b/drivers/edac/edac_module.h @@ -59,8 +59,6 @@ extern void edac_device_reset_delay_period(struct edac_device_ctl_info *edac_dev, unsigned long value); extern void edac_mc_reset_delay_period(unsigned long value); -extern void *edac_align_ptr(void **p, unsigned size, int n_elems); - /* * EDAC debugfs functions */ diff --git a/drivers/edac/edac_pci.c b/drivers/edac/edac_pci.c index 48c844a72a27..2205d7e731db 100644 --- a/drivers/edac/edac_pci.c +++ b/drivers/edac/edac_pci.c @@ -29,32 +29,31 @@ static LIST_HEAD(edac_pci_list); static atomic_t pci_indexes = ATOMIC_INIT(0); struct edac_pci_ctl_info *edac_pci_alloc_ctl_info(unsigned int sz_pvt, - const char *edac_pci_name) + const char *edac_pci_name) { struct edac_pci_ctl_info *pci; - void *p = NULL, *pvt; - unsigned int size; edac_dbg(1, "\n"); - pci = edac_align_ptr(&p, sizeof(*pci), 1); - pvt = edac_align_ptr(&p, 1, sz_pvt); - size = ((unsigned long)pvt) + sz_pvt; - - /* Alloc the needed control struct memory */ - pci = kzalloc(size, GFP_KERNEL); - if (pci == NULL) + pci = kzalloc(sizeof(struct edac_pci_ctl_info), GFP_KERNEL); + if (!pci) return NULL; - /* Now much private space */ - pvt = sz_pvt ? ((char *)pci) + ((unsigned long)pvt) : NULL; + if (sz_pvt) { + pci->pvt_info = kzalloc(sz_pvt, GFP_KERNEL); + if (!pci->pvt_info) + goto free; + } - pci->pvt_info = pvt; pci->op_state = OP_ALLOC; snprintf(pci->name, strlen(edac_pci_name) + 1, "%s", edac_pci_name); return pci; + +free: + kfree(pci); + return NULL; } EXPORT_SYMBOL_GPL(edac_pci_alloc_ctl_info); diff --git a/drivers/edac/ghes_edac.c b/drivers/edac/ghes_edac.c index 6d1ddecbf0da..59b0bedc9c24 100644 --- a/drivers/edac/ghes_edac.c +++ b/drivers/edac/ghes_edac.c @@ -15,11 +15,13 @@ #include "edac_module.h" #include <ras/ras_event.h> +#define OTHER_DETAIL_LEN 400 + struct ghes_pvt { struct mem_ctl_info *mci; /* Buffers for the error handling routine */ - char other_detail[400]; + char other_detail[OTHER_DETAIL_LEN]; char msg[80]; }; @@ -36,7 +38,7 @@ static struct ghes_pvt *ghes_pvt; * This driver's representation of the system hardware, as collected * from DMI. */ -struct ghes_hw_desc { +static struct ghes_hw_desc { int num_dimms; struct dimm_info *dimms; } ghes_hw; @@ -235,8 +237,34 @@ static void ghes_scan_system(void) system_scanned = true; } +static int print_mem_error_other_detail(const struct cper_sec_mem_err *mem, char *msg, + const char *location, unsigned int len) +{ + u32 n; + + if (!msg) + return 0; + + n = 0; + len -= 1; + + n += scnprintf(msg + n, len - n, "APEI location: %s ", location); + + if (!(mem->validation_bits & CPER_MEM_VALID_ERROR_STATUS)) + goto out; + + n += scnprintf(msg + n, len - n, "status(0x%016llx): ", mem->error_status); + n += scnprintf(msg + n, len - n, "%s ", cper_mem_err_status_str(mem->error_status)); + +out: + msg[n] = '\0'; + + return n; +} + void ghes_edac_report_mem_error(int sev, struct cper_sec_mem_err *mem_err) { + struct cper_mem_err_compact cmem; struct edac_raw_error_desc *e; struct mem_ctl_info *mci; struct ghes_pvt *pvt; @@ -292,60 +320,10 @@ void ghes_edac_report_mem_error(int sev, struct cper_sec_mem_err *mem_err) /* Error type, mapped on e->msg */ if (mem_err->validation_bits & CPER_MEM_VALID_ERROR_TYPE) { + u8 etype = mem_err->error_type; + p = pvt->msg; - switch (mem_err->error_type) { - case 0: - p += sprintf(p, "Unknown"); - break; - case 1: - p += sprintf(p, "No error"); - break; - case 2: - p += sprintf(p, "Single-bit ECC"); - break; - case 3: - p += sprintf(p, "Multi-bit ECC"); - break; - case 4: - p += sprintf(p, "Single-symbol ChipKill ECC"); - break; - case 5: - p += sprintf(p, "Multi-symbol ChipKill ECC"); - break; - case 6: - p += sprintf(p, "Master abort"); - break; - case 7: - p += sprintf(p, "Target abort"); - break; - case 8: - p += sprintf(p, "Parity Error"); - break; - case 9: - p += sprintf(p, "Watchdog timeout"); - break; - case 10: - p += sprintf(p, "Invalid address"); - break; - case 11: - p += sprintf(p, "Mirror Broken"); - break; - case 12: - p += sprintf(p, "Memory Sparing"); - break; - case 13: - p += sprintf(p, "Scrub corrected error"); - break; - case 14: - p += sprintf(p, "Scrub uncorrected error"); - break; - case 15: - p += sprintf(p, "Physical Memory Map-out event"); - break; - default: - p += sprintf(p, "reserved error (%d)", - mem_err->error_type); - } + p += snprintf(p, sizeof(pvt->msg), "%s", cper_mem_err_type_str(etype)); } else { strcpy(pvt->msg, "unknown error"); } @@ -362,52 +340,19 @@ void ghes_edac_report_mem_error(int sev, struct cper_sec_mem_err *mem_err) /* Memory error location, mapped on e->location */ p = e->location; - if (mem_err->validation_bits & CPER_MEM_VALID_NODE) - p += sprintf(p, "node:%d ", mem_err->node); - if (mem_err->validation_bits & CPER_MEM_VALID_CARD) - p += sprintf(p, "card:%d ", mem_err->card); - if (mem_err->validation_bits & CPER_MEM_VALID_MODULE) - p += sprintf(p, "module:%d ", mem_err->module); - if (mem_err->validation_bits & CPER_MEM_VALID_RANK_NUMBER) - p += sprintf(p, "rank:%d ", mem_err->rank); - if (mem_err->validation_bits & CPER_MEM_VALID_BANK) - p += sprintf(p, "bank:%d ", mem_err->bank); - if (mem_err->validation_bits & CPER_MEM_VALID_BANK_GROUP) - p += sprintf(p, "bank_group:%d ", - mem_err->bank >> CPER_MEM_BANK_GROUP_SHIFT); - if (mem_err->validation_bits & CPER_MEM_VALID_BANK_ADDRESS) - p += sprintf(p, "bank_address:%d ", - mem_err->bank & CPER_MEM_BANK_ADDRESS_MASK); - if (mem_err->validation_bits & (CPER_MEM_VALID_ROW | CPER_MEM_VALID_ROW_EXT)) { - u32 row = mem_err->row; - - row |= cper_get_mem_extension(mem_err->validation_bits, mem_err->extended); - p += sprintf(p, "row:%d ", row); - } - if (mem_err->validation_bits & CPER_MEM_VALID_COLUMN) - p += sprintf(p, "col:%d ", mem_err->column); - if (mem_err->validation_bits & CPER_MEM_VALID_BIT_POSITION) - p += sprintf(p, "bit_pos:%d ", mem_err->bit_pos); + cper_mem_err_pack(mem_err, &cmem); + p += cper_mem_err_location(&cmem, p); + if (mem_err->validation_bits & CPER_MEM_VALID_MODULE_HANDLE) { - const char *bank = NULL, *device = NULL; struct dimm_info *dimm; - dmi_memdev_name(mem_err->mem_dev_handle, &bank, &device); - if (bank != NULL && device != NULL) - p += sprintf(p, "DIMM location:%s %s ", bank, device); - else - p += sprintf(p, "DIMM DMI handle: 0x%.4x ", - mem_err->mem_dev_handle); - + p += cper_dimm_err_location(&cmem, p); dimm = find_dimm_by_handle(mci, mem_err->mem_dev_handle); if (dimm) { e->top_layer = dimm->idx; strcpy(e->label, dimm->label); } } - if (mem_err->validation_bits & CPER_MEM_VALID_CHIP_ID) - p += sprintf(p, "chipID: %d ", - mem_err->extended >> CPER_MEM_CHIP_ID_SHIFT); if (p > e->location) *(p - 1) = '\0'; @@ -416,78 +361,7 @@ void ghes_edac_report_mem_error(int sev, struct cper_sec_mem_err *mem_err) /* All other fields are mapped on e->other_detail */ p = pvt->other_detail; - p += snprintf(p, sizeof(pvt->other_detail), - "APEI location: %s ", e->location); - if (mem_err->validation_bits & CPER_MEM_VALID_ERROR_STATUS) { - u64 status = mem_err->error_status; - - p += sprintf(p, "status(0x%016llx): ", (long long)status); - switch ((status >> 8) & 0xff) { - case 1: - p += sprintf(p, "Error detected internal to the component "); - break; - case 16: - p += sprintf(p, "Error detected in the bus "); - break; - case 4: - p += sprintf(p, "Storage error in DRAM memory "); - break; - case 5: - p += sprintf(p, "Storage error in TLB "); - break; - case 6: - p += sprintf(p, "Storage error in cache "); - break; - case 7: - p += sprintf(p, "Error in one or more functional units "); - break; - case 8: - p += sprintf(p, "component failed self test "); - break; - case 9: - p += sprintf(p, "Overflow or undervalue of internal queue "); - break; - case 17: - p += sprintf(p, "Virtual address not found on IO-TLB or IO-PDIR "); - break; - case 18: - p += sprintf(p, "Improper access error "); - break; - case 19: - p += sprintf(p, "Access to a memory address which is not mapped to any component "); - break; - case 20: - p += sprintf(p, "Loss of Lockstep "); - break; - case 21: - p += sprintf(p, "Response not associated with a request "); - break; - case 22: - p += sprintf(p, "Bus parity error - must also set the A, C, or D Bits "); - break; - case 23: - p += sprintf(p, "Detection of a PATH_ERROR "); - break; - case 25: - p += sprintf(p, "Bus operation timeout "); - break; - case 26: - p += sprintf(p, "A read was issued to data that has been poisoned "); - break; - default: - p += sprintf(p, "reserved "); - break; - } - } - if (mem_err->validation_bits & CPER_MEM_VALID_REQUESTOR_ID) - p += sprintf(p, "requestorID: 0x%016llx ", - (long long)mem_err->requestor_id); - if (mem_err->validation_bits & CPER_MEM_VALID_RESPONDER_ID) - p += sprintf(p, "responderID: 0x%016llx ", - (long long)mem_err->responder_id); - if (mem_err->validation_bits & CPER_MEM_VALID_TARGET_ID) - p += sprintf(p, "targetID: 0x%016llx ", - (long long)mem_err->responder_id); + p += print_mem_error_other_detail(mem_err, p, e->location, OTHER_DETAIL_LEN); if (p > pvt->other_detail) *(p - 1) = '\0'; diff --git a/drivers/edac/i5100_edac.c b/drivers/edac/i5100_edac.c index 324a46b8479b..f5d82518c15e 100644 --- a/drivers/edac/i5100_edac.c +++ b/drivers/edac/i5100_edac.c @@ -244,11 +244,6 @@ static inline u32 i5100_nrecmema_rank(u32 a) return a >> 8 & ((1 << 3) - 1); } -static inline u32 i5100_nrecmema_dm_buf_id(u32 a) -{ - return a & ((1 << 8) - 1); -} - static inline u32 i5100_nrecmemb_cas(u32 a) { return a >> 16 & ((1 << 13) - 1); diff --git a/drivers/edac/mpc85xx_edac.c b/drivers/edac/mpc85xx_edac.c index 67f7bc3fe5b3..5bf92298554d 100644 --- a/drivers/edac/mpc85xx_edac.c +++ b/drivers/edac/mpc85xx_edac.c @@ -609,13 +609,6 @@ static int mpc85xx_l2_err_remove(struct platform_device *op) } static const struct of_device_id mpc85xx_l2_err_of_match[] = { -/* deprecate the fsl,85.. forms in the future, 2.6.30? */ - { .compatible = "fsl,8540-l2-cache-controller", }, - { .compatible = "fsl,8541-l2-cache-controller", }, - { .compatible = "fsl,8544-l2-cache-controller", }, - { .compatible = "fsl,8548-l2-cache-controller", }, - { .compatible = "fsl,8555-l2-cache-controller", }, - { .compatible = "fsl,8568-l2-cache-controller", }, { .compatible = "fsl,mpc8536-l2-cache-controller", }, { .compatible = "fsl,mpc8540-l2-cache-controller", }, { .compatible = "fsl,mpc8541-l2-cache-controller", }, @@ -644,13 +637,6 @@ static struct platform_driver mpc85xx_l2_err_driver = { }; static const struct of_device_id mpc85xx_mc_err_of_match[] = { -/* deprecate the fsl,85.. forms in the future, 2.6.30? */ - { .compatible = "fsl,8540-memory-controller", }, - { .compatible = "fsl,8541-memory-controller", }, - { .compatible = "fsl,8544-memory-controller", }, - { .compatible = "fsl,8548-memory-controller", }, - { .compatible = "fsl,8555-memory-controller", }, - { .compatible = "fsl,8568-memory-controller", }, { .compatible = "fsl,mpc8536-memory-controller", }, { .compatible = "fsl,mpc8540-memory-controller", }, { .compatible = "fsl,mpc8541-memory-controller", }, diff --git a/drivers/edac/synopsys_edac.c b/drivers/edac/synopsys_edac.c index 40b1abeca856..1cee64b80a7e 100644 --- a/drivers/edac/synopsys_edac.c +++ b/drivers/edac/synopsys_edac.c @@ -1,22 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * Synopsys DDR ECC Driver * This driver is based on ppc4xx_edac.c drivers * * Copyright (C) 2012 - 2014 Xilinx, Inc. - * - * This program 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, either version 2 of the License, or - * (at your option) any later version. - * - * This program 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. - * - * This file is subject to the terms and conditions of the GNU General Public - * License. See the file "COPYING" in the main directory of this archive - * for more details */ #include <linux/edac.h> diff --git a/drivers/edac/xgene_edac.c b/drivers/edac/xgene_edac.c index 7197f9fa0245..54081403db4f 100644 --- a/drivers/edac/xgene_edac.c +++ b/drivers/edac/xgene_edac.c @@ -501,7 +501,7 @@ static int xgene_edac_mc_remove(struct xgene_edac_mc_ctx *mcu) #define MEMERR_L2C_L2ESRA_PAGE_OFFSET 0x0804 /* - * Processor Module Domain (PMD) context - Context for a pair of processsors. + * Processor Module Domain (PMD) context - Context for a pair of processors. * Each PMD consists of 2 CPUs and a shared L2 cache. Each CPU consists of * its own L1 cache. */ diff --git a/drivers/firmware/efi/Kconfig b/drivers/firmware/efi/Kconfig index 2c3dac5ecb36..4720ba98cec3 100644 --- a/drivers/firmware/efi/Kconfig +++ b/drivers/firmware/efi/Kconfig @@ -91,6 +91,18 @@ config EFI_SOFT_RESERVE If unsure, say Y. +config EFI_DXE_MEM_ATTRIBUTES + bool "Adjust memory attributes in EFISTUB" + depends on EFI && EFI_STUB && X86 + default y + help + UEFI specification does not guarantee all memory to be + accessible for both write and execute as the kernel expects + it to be. + Use DXE services to check and alter memory protection + attributes during boot via EFISTUB to ensure that memory + ranges used by the kernel are writable and executable. + config EFI_PARAMS_FROM_FDT bool help @@ -284,3 +296,34 @@ config EFI_CUSTOM_SSDT_OVERLAYS See Documentation/admin-guide/acpi/ssdt-overlays.rst for more information. + +config EFI_DISABLE_RUNTIME + bool "Disable EFI runtime services support by default" + default y if PREEMPT_RT + help + Allow to disable the EFI runtime services support by default. This can + already be achieved by using the efi=noruntime option, but it could be + useful to have this default without any kernel command line parameter. + + The EFI runtime services are disabled by default when PREEMPT_RT is + enabled, because measurements have shown that some EFI functions calls + might take too much time to complete, causing large latencies which is + an issue for Real-Time kernels. + + This default can be overridden by using the efi=runtime option. + +config EFI_COCO_SECRET + bool "EFI Confidential Computing Secret Area Support" + depends on EFI + help + Confidential Computing platforms (such as AMD SEV) allow the + Guest Owner to securely inject secrets during guest VM launch. + The secrets are placed in a designated EFI reserved memory area. + + In order to use the secrets in the kernel, the location of the secret + area (as published in the EFI config table) must be kept. + + If you say Y here, the address of the EFI secret area will be kept + for usage inside the kernel. This will allow the + virt/coco/efi_secret module to access the secrets, which in turn + allows userspace programs to access the injected secrets. diff --git a/drivers/firmware/efi/cper.c b/drivers/firmware/efi/cper.c index 6ec8edec6329..e4e5ea7ce910 100644 --- a/drivers/firmware/efi/cper.c +++ b/drivers/firmware/efi/cper.c @@ -211,7 +211,33 @@ const char *cper_mem_err_type_str(unsigned int etype) } EXPORT_SYMBOL_GPL(cper_mem_err_type_str); -static int cper_mem_err_location(struct cper_mem_err_compact *mem, char *msg) +const char *cper_mem_err_status_str(u64 status) +{ + switch ((status >> 8) & 0xff) { + case 1: return "Error detected internal to the component"; + case 4: return "Storage error in DRAM memory"; + case 5: return "Storage error in TLB"; + case 6: return "Storage error in cache"; + case 7: return "Error in one or more functional units"; + case 8: return "Component failed self test"; + case 9: return "Overflow or undervalue of internal queue"; + case 16: return "Error detected in the bus"; + case 17: return "Virtual address not found on IO-TLB or IO-PDIR"; + case 18: return "Improper access error"; + case 19: return "Access to a memory address which is not mapped to any component"; + case 20: return "Loss of Lockstep"; + case 21: return "Response not associated with a request"; + case 22: return "Bus parity error - must also set the A, C, or D Bits"; + case 23: return "Detection of a protocol error"; + case 24: return "Detection of a PATH_ERROR"; + case 25: return "Bus operation timeout"; + case 26: return "A read was issued to data that has been poisoned"; + default: return "Reserved"; + } +} +EXPORT_SYMBOL_GPL(cper_mem_err_status_str); + +int cper_mem_err_location(struct cper_mem_err_compact *mem, char *msg) { u32 len, n; @@ -221,51 +247,51 @@ static int cper_mem_err_location(struct cper_mem_err_compact *mem, char *msg) n = 0; len = CPER_REC_LEN; if (mem->validation_bits & CPER_MEM_VALID_NODE) - n += scnprintf(msg + n, len - n, "node: %d ", mem->node); + n += scnprintf(msg + n, len - n, "node:%d ", mem->node); if (mem->validation_bits & CPER_MEM_VALID_CARD) - n += scnprintf(msg + n, len - n, "card: %d ", mem->card); + n += scnprintf(msg + n, len - n, "card:%d ", mem->card); if (mem->validation_bits & CPER_MEM_VALID_MODULE) - n += scnprintf(msg + n, len - n, "module: %d ", mem->module); + n += scnprintf(msg + n, len - n, "module:%d ", mem->module); if (mem->validation_bits & CPER_MEM_VALID_RANK_NUMBER) - n += scnprintf(msg + n, len - n, "rank: %d ", mem->rank); + n += scnprintf(msg + n, len - n, "rank:%d ", mem->rank); if (mem->validation_bits & CPER_MEM_VALID_BANK) - n += scnprintf(msg + n, len - n, "bank: %d ", mem->bank); + n += scnprintf(msg + n, len - n, "bank:%d ", mem->bank); if (mem->validation_bits & CPER_MEM_VALID_BANK_GROUP) - n += scnprintf(msg + n, len - n, "bank_group: %d ", + n += scnprintf(msg + n, len - n, "bank_group:%d ", mem->bank >> CPER_MEM_BANK_GROUP_SHIFT); if (mem->validation_bits & CPER_MEM_VALID_BANK_ADDRESS) - n += scnprintf(msg + n, len - n, "bank_address: %d ", + n += scnprintf(msg + n, len - n, "bank_address:%d ", mem->bank & CPER_MEM_BANK_ADDRESS_MASK); if (mem->validation_bits & CPER_MEM_VALID_DEVICE) - n += scnprintf(msg + n, len - n, "device: %d ", mem->device); + n += scnprintf(msg + n, len - n, "device:%d ", mem->device); if (mem->validation_bits & (CPER_MEM_VALID_ROW | CPER_MEM_VALID_ROW_EXT)) { u32 row = mem->row; row |= cper_get_mem_extension(mem->validation_bits, mem->extended); - n += scnprintf(msg + n, len - n, "row: %d ", row); + n += scnprintf(msg + n, len - n, "row:%d ", row); } if (mem->validation_bits & CPER_MEM_VALID_COLUMN) - n += scnprintf(msg + n, len - n, "column: %d ", mem->column); + n += scnprintf(msg + n, len - n, "column:%d ", mem->column); if (mem->validation_bits & CPER_MEM_VALID_BIT_POSITION) - n += scnprintf(msg + n, len - n, "bit_position: %d ", + n += scnprintf(msg + n, len - n, "bit_position:%d ", mem->bit_pos); if (mem->validation_bits & CPER_MEM_VALID_REQUESTOR_ID) - n += scnprintf(msg + n, len - n, "requestor_id: 0x%016llx ", + n += scnprintf(msg + n, len - n, "requestor_id:0x%016llx ", mem->requestor_id); if (mem->validation_bits & CPER_MEM_VALID_RESPONDER_ID) - n += scnprintf(msg + n, len - n, "responder_id: 0x%016llx ", + n += scnprintf(msg + n, len - n, "responder_id:0x%016llx ", mem->responder_id); if (mem->validation_bits & CPER_MEM_VALID_TARGET_ID) - n += scnprintf(msg + n, len - n, "target_id: 0x%016llx ", + n += scnprintf(msg + n, len - n, "target_id:0x%016llx ", mem->target_id); if (mem->validation_bits & CPER_MEM_VALID_CHIP_ID) - n += scnprintf(msg + n, len - n, "chip_id: %d ", + n += scnprintf(msg + n, len - n, "chip_id:%d ", mem->extended >> CPER_MEM_CHIP_ID_SHIFT); return n; } -static int cper_dimm_err_location(struct cper_mem_err_compact *mem, char *msg) +int cper_dimm_err_location(struct cper_mem_err_compact *mem, char *msg) { u32 len, n; const char *bank = NULL, *device = NULL; @@ -334,7 +360,9 @@ static void cper_print_mem(const char *pfx, const struct cper_sec_mem_err *mem, return; } if (mem->validation_bits & CPER_MEM_VALID_ERROR_STATUS) - printk("%s""error_status: 0x%016llx\n", pfx, mem->error_status); + printk("%s error_status: %s (0x%016llx)\n", + pfx, cper_mem_err_status_str(mem->error_status), + mem->error_status); if (mem->validation_bits & CPER_MEM_VALID_PA) printk("%s""physical_address: 0x%016llx\n", pfx, mem->physical_addr); diff --git a/drivers/firmware/efi/efi.c b/drivers/firmware/efi/efi.c index 5502e176d51b..860534bcfdac 100644 --- a/drivers/firmware/efi/efi.c +++ b/drivers/firmware/efi/efi.c @@ -46,6 +46,9 @@ struct efi __read_mostly efi = { #ifdef CONFIG_LOAD_UEFI_KEYS .mokvar_table = EFI_INVALID_TABLE_ADDR, #endif +#ifdef CONFIG_EFI_COCO_SECRET + .coco_secret = EFI_INVALID_TABLE_ADDR, +#endif }; EXPORT_SYMBOL(efi); @@ -66,7 +69,7 @@ struct mm_struct efi_mm = { struct workqueue_struct *efi_rts_wq; -static bool disable_runtime = IS_ENABLED(CONFIG_PREEMPT_RT); +static bool disable_runtime = IS_ENABLED(CONFIG_EFI_DISABLE_RUNTIME); static int __init setup_noefi(char *arg) { disable_runtime = true; @@ -422,6 +425,11 @@ static int __init efisubsys_init(void) if (efi_enabled(EFI_DBG) && efi_enabled(EFI_PRESERVE_BS_REGIONS)) efi_debugfs_init(); +#ifdef CONFIG_EFI_COCO_SECRET + if (efi.coco_secret != EFI_INVALID_TABLE_ADDR) + platform_device_register_simple("efi_secret", 0, NULL, 0); +#endif + return 0; err_remove_group: @@ -529,6 +537,9 @@ static const efi_config_table_type_t common_tables[] __initconst = { #ifdef CONFIG_LOAD_UEFI_KEYS {LINUX_EFI_MOK_VARIABLE_TABLE_GUID, &efi.mokvar_table, "MOKvar" }, #endif +#ifdef CONFIG_EFI_COCO_SECRET + {LINUX_EFI_COCO_SECRET_AREA_GUID, &efi.coco_secret, "CocoSecret" }, +#endif {}, }; diff --git a/drivers/firmware/efi/libstub/arm32-stub.c b/drivers/firmware/efi/libstub/arm32-stub.c index 4b5b2403b3a0..0131e3aaa605 100644 --- a/drivers/firmware/efi/libstub/arm32-stub.c +++ b/drivers/firmware/efi/libstub/arm32-stub.c @@ -117,7 +117,8 @@ efi_status_t handle_kernel_image(unsigned long *image_addr, unsigned long *image_size, unsigned long *reserve_addr, unsigned long *reserve_size, - efi_loaded_image_t *image) + efi_loaded_image_t *image, + efi_handle_t image_handle) { const int slack = TEXT_OFFSET - 5 * PAGE_SIZE; int alloc_size = MAX_UNCOMP_KERNEL_SIZE + EFI_PHYS_ALIGN; diff --git a/drivers/firmware/efi/libstub/arm64-stub.c b/drivers/firmware/efi/libstub/arm64-stub.c index 9cc556013d08..577173ee1f83 100644 --- a/drivers/firmware/efi/libstub/arm64-stub.c +++ b/drivers/firmware/efi/libstub/arm64-stub.c @@ -83,7 +83,8 @@ efi_status_t handle_kernel_image(unsigned long *image_addr, unsigned long *image_size, unsigned long *reserve_addr, unsigned long *reserve_size, - efi_loaded_image_t *image) + efi_loaded_image_t *image, + efi_handle_t image_handle) { efi_status_t status; unsigned long kernel_size, kernel_memsize = 0; @@ -100,7 +101,15 @@ efi_status_t handle_kernel_image(unsigned long *image_addr, u64 min_kimg_align = efi_nokaslr ? MIN_KIMG_ALIGN : EFI_KIMG_ALIGN; if (IS_ENABLED(CONFIG_RANDOMIZE_BASE)) { - if (!efi_nokaslr) { + efi_guid_t li_fixed_proto = LINUX_EFI_LOADED_IMAGE_FIXED_GUID; + void *p; + + if (efi_nokaslr) { + efi_info("KASLR disabled on kernel command line\n"); + } else if (efi_bs_call(handle_protocol, image_handle, + &li_fixed_proto, &p) == EFI_SUCCESS) { + efi_info("Image placement fixed by loader\n"); + } else { status = efi_get_random_bytes(sizeof(phys_seed), (u8 *)&phys_seed); if (status == EFI_NOT_FOUND) { @@ -111,8 +120,6 @@ efi_status_t handle_kernel_image(unsigned long *image_addr, status); efi_nokaslr = true; } - } else { - efi_info("KASLR disabled on kernel command line\n"); } } diff --git a/drivers/firmware/efi/libstub/efi-stub.c b/drivers/firmware/efi/libstub/efi-stub.c index da93864d7abc..f515394cce6e 100644 --- a/drivers/firmware/efi/libstub/efi-stub.c +++ b/drivers/firmware/efi/libstub/efi-stub.c @@ -198,7 +198,7 @@ efi_status_t __efiapi efi_pe_entry(efi_handle_t handle, status = handle_kernel_image(&image_addr, &image_size, &reserve_addr, &reserve_size, - image); + image, handle); if (status != EFI_SUCCESS) { efi_err("Failed to relocate kernel\n"); goto fail_free_screeninfo; diff --git a/drivers/firmware/efi/libstub/efistub.h b/drivers/firmware/efi/libstub/efistub.h index edb77b0621ea..b0ae0a454404 100644 --- a/drivers/firmware/efi/libstub/efistub.h +++ b/drivers/firmware/efi/libstub/efistub.h @@ -36,6 +36,9 @@ extern bool efi_novamap; extern const efi_system_table_t *efi_system_table; +typedef union efi_dxe_services_table efi_dxe_services_table_t; +extern const efi_dxe_services_table_t *efi_dxe_table; + efi_status_t __efiapi efi_pe_entry(efi_handle_t handle, efi_system_table_t *sys_table_arg); @@ -44,6 +47,7 @@ efi_status_t __efiapi efi_pe_entry(efi_handle_t handle, #define efi_is_native() (true) #define efi_bs_call(func, ...) efi_system_table->boottime->func(__VA_ARGS__) #define efi_rt_call(func, ...) efi_system_table->runtime->func(__VA_ARGS__) +#define efi_dxe_call(func, ...) efi_dxe_table->func(__VA_ARGS__) #define efi_table_attr(inst, attr) (inst->attr) #define efi_call_proto(inst, func, ...) inst->func(inst, ##__VA_ARGS__) @@ -329,6 +333,76 @@ union efi_boot_services { } mixed_mode; }; +typedef enum { + EfiGcdMemoryTypeNonExistent, + EfiGcdMemoryTypeReserved, + EfiGcdMemoryTypeSystemMemory, + EfiGcdMemoryTypeMemoryMappedIo, + EfiGcdMemoryTypePersistent, + EfiGcdMemoryTypeMoreReliable, + EfiGcdMemoryTypeMaximum +} efi_gcd_memory_type_t; + +typedef struct { + efi_physical_addr_t base_address; + u64 length; + u64 capabilities; + u64 attributes; + efi_gcd_memory_type_t gcd_memory_type; + void *image_handle; + void *device_handle; +} efi_gcd_memory_space_desc_t; + +/* + * EFI DXE Services table + */ +union efi_dxe_services_table { + struct { + efi_table_hdr_t hdr; + void *add_memory_space; + void *allocate_memory_space; + void *free_memory_space; + void *remove_memory_space; + efi_status_t (__efiapi *get_memory_space_descriptor)(efi_physical_addr_t, + efi_gcd_memory_space_desc_t *); + efi_status_t (__efiapi *set_memory_space_attributes)(efi_physical_addr_t, + u64, u64); + void *get_memory_space_map; + void *add_io_space; + void *allocate_io_space; + void *free_io_space; + void *remove_io_space; + void *get_io_space_descriptor; + void *get_io_space_map; + void *dispatch; + void *schedule; + void *trust; + void *process_firmware_volume; + void *set_memory_space_capabilities; + }; + struct { + efi_table_hdr_t hdr; + u32 add_memory_space; + u32 allocate_memory_space; + u32 free_memory_space; + u32 remove_memory_space; + u32 get_memory_space_descriptor; + u32 set_memory_space_attributes; + u32 get_memory_space_map; + u32 add_io_space; + u32 allocate_io_space; + u32 free_io_space; + u32 remove_io_space; + u32 get_io_space_descriptor; + u32 get_io_space_map; + u32 dispatch; + u32 schedule; + u32 trust; + u32 process_firmware_volume; + u32 set_memory_space_capabilities; + } mixed_mode; +}; + typedef union efi_uga_draw_protocol efi_uga_draw_protocol_t; union efi_uga_draw_protocol { @@ -720,6 +794,13 @@ union efi_tcg2_protocol { } mixed_mode; }; +struct riscv_efi_boot_protocol { + u64 revision; + + efi_status_t (__efiapi *get_boot_hartid)(struct riscv_efi_boot_protocol *, + unsigned long *boot_hartid); +}; + typedef union efi_load_file_protocol efi_load_file_protocol_t; typedef union efi_load_file_protocol efi_load_file2_protocol_t; @@ -865,7 +946,8 @@ efi_status_t handle_kernel_image(unsigned long *image_addr, unsigned long *image_size, unsigned long *reserve_addr, unsigned long *reserve_size, - efi_loaded_image_t *image); + efi_loaded_image_t *image, + efi_handle_t image_handle); asmlinkage void __noreturn efi_enter_kernel(unsigned long entrypoint, unsigned long fdt_addr, diff --git a/drivers/firmware/efi/libstub/randomalloc.c b/drivers/firmware/efi/libstub/randomalloc.c index 724155b9e10d..715f37479154 100644 --- a/drivers/firmware/efi/libstub/randomalloc.c +++ b/drivers/firmware/efi/libstub/randomalloc.c @@ -56,6 +56,7 @@ efi_status_t efi_random_alloc(unsigned long size, unsigned long random_seed) { unsigned long map_size, desc_size, total_slots = 0, target_slot; + unsigned long total_mirrored_slots = 0; unsigned long buff_size; efi_status_t status; efi_memory_desc_t *memory_map; @@ -86,8 +87,14 @@ efi_status_t efi_random_alloc(unsigned long size, slots = get_entry_num_slots(md, size, ilog2(align)); MD_NUM_SLOTS(md) = slots; total_slots += slots; + if (md->attribute & EFI_MEMORY_MORE_RELIABLE) + total_mirrored_slots += slots; } + /* consider only mirrored slots for randomization if any exist */ + if (total_mirrored_slots > 0) + total_slots = total_mirrored_slots; + /* find a random number between 0 and total_slots */ target_slot = (total_slots * (u64)(random_seed & U32_MAX)) >> 32; @@ -107,6 +114,10 @@ efi_status_t efi_random_alloc(unsigned long size, efi_physical_addr_t target; unsigned long pages; + if (total_mirrored_slots > 0 && + !(md->attribute & EFI_MEMORY_MORE_RELIABLE)) + continue; + if (target_slot >= MD_NUM_SLOTS(md)) { target_slot -= MD_NUM_SLOTS(md); continue; diff --git a/drivers/firmware/efi/libstub/riscv-stub.c b/drivers/firmware/efi/libstub/riscv-stub.c index 9c460843442f..9e85e58d1f27 100644 --- a/drivers/firmware/efi/libstub/riscv-stub.c +++ b/drivers/firmware/efi/libstub/riscv-stub.c @@ -21,9 +21,9 @@ #define MIN_KIMG_ALIGN SZ_4M #endif -typedef void __noreturn (*jump_kernel_func)(unsigned int, unsigned long); +typedef void __noreturn (*jump_kernel_func)(unsigned long, unsigned long); -static u32 hartid; +static unsigned long hartid; static int get_boot_hartid_from_fdt(void) { @@ -47,14 +47,31 @@ static int get_boot_hartid_from_fdt(void) return 0; } +static efi_status_t get_boot_hartid_from_efi(void) +{ + efi_guid_t boot_protocol_guid = RISCV_EFI_BOOT_PROTOCOL_GUID; + struct riscv_efi_boot_protocol *boot_protocol; + efi_status_t status; + + status = efi_bs_call(locate_protocol, &boot_protocol_guid, NULL, + (void **)&boot_protocol); + if (status != EFI_SUCCESS) + return status; + return efi_call_proto(boot_protocol, get_boot_hartid, &hartid); +} + efi_status_t check_platform_features(void) { + efi_status_t status; int ret; - ret = get_boot_hartid_from_fdt(); - if (ret) { - efi_err("/chosen/boot-hartid missing or invalid!\n"); - return EFI_UNSUPPORTED; + status = get_boot_hartid_from_efi(); + if (status != EFI_SUCCESS) { + ret = get_boot_hartid_from_fdt(); + if (ret) { + efi_err("Failed to get boot hartid!\n"); + return EFI_UNSUPPORTED; + } } return EFI_SUCCESS; } @@ -80,7 +97,8 @@ efi_status_t handle_kernel_image(unsigned long *image_addr, unsigned long *image_size, unsigned long *reserve_addr, unsigned long *reserve_size, - efi_loaded_image_t *image) + efi_loaded_image_t *image, + efi_handle_t image_handle) { unsigned long kernel_size = 0; unsigned long preferred_addr; diff --git a/drivers/firmware/efi/libstub/x86-stub.c b/drivers/firmware/efi/libstub/x86-stub.c index 01ddd4502e28..b14e88ccefca 100644 --- a/drivers/firmware/efi/libstub/x86-stub.c +++ b/drivers/firmware/efi/libstub/x86-stub.c @@ -22,6 +22,7 @@ #define MAXMEM_X86_64_4LEVEL (1ull << 46) const efi_system_table_t *efi_system_table; +const efi_dxe_services_table_t *efi_dxe_table; extern u32 image_offset; static efi_loaded_image_t *image = NULL; @@ -211,9 +212,110 @@ static void retrieve_apple_device_properties(struct boot_params *boot_params) } } +static void +adjust_memory_range_protection(unsigned long start, unsigned long size) +{ + efi_status_t status; + efi_gcd_memory_space_desc_t desc; + unsigned long end, next; + unsigned long rounded_start, rounded_end; + unsigned long unprotect_start, unprotect_size; + int has_system_memory = 0; + + if (efi_dxe_table == NULL) + return; + + rounded_start = rounddown(start, EFI_PAGE_SIZE); + rounded_end = roundup(start + size, EFI_PAGE_SIZE); + + /* + * Don't modify memory region attributes, they are + * already suitable, to lower the possibility to + * encounter firmware bugs. + */ + + for (end = start + size; start < end; start = next) { + + status = efi_dxe_call(get_memory_space_descriptor, start, &desc); + + if (status != EFI_SUCCESS) + return; + + next = desc.base_address + desc.length; + + /* + * Only system memory is suitable for trampoline/kernel image placement, + * so only this type of memory needs its attributes to be modified. + */ + + if (desc.gcd_memory_type != EfiGcdMemoryTypeSystemMemory || + (desc.attributes & (EFI_MEMORY_RO | EFI_MEMORY_XP)) == 0) + continue; + + unprotect_start = max(rounded_start, (unsigned long)desc.base_address); + unprotect_size = min(rounded_end, next) - unprotect_start; + + status = efi_dxe_call(set_memory_space_attributes, + unprotect_start, unprotect_size, + EFI_MEMORY_WB); + + if (status != EFI_SUCCESS) { + efi_warn("Unable to unprotect memory range [%08lx,%08lx]: %d\n", + unprotect_start, + unprotect_start + unprotect_size, + (int)status); + } + } +} + +/* + * Trampoline takes 2 pages and can be loaded in first megabyte of memory + * with its end placed between 128k and 640k where BIOS might start. + * (see arch/x86/boot/compressed/pgtable_64.c) + * + * We cannot find exact trampoline placement since memory map + * can be modified by UEFI, and it can alter the computed address. + */ + +#define TRAMPOLINE_PLACEMENT_BASE ((128 - 8)*1024) +#define TRAMPOLINE_PLACEMENT_SIZE (640*1024 - (128 - 8)*1024) + +void startup_32(struct boot_params *boot_params); + +static void +setup_memory_protection(unsigned long image_base, unsigned long image_size) +{ + /* + * Allow execution of possible trampoline used + * for switching between 4- and 5-level page tables + * and relocated kernel image. + */ + + adjust_memory_range_protection(TRAMPOLINE_PLACEMENT_BASE, + TRAMPOLINE_PLACEMENT_SIZE); + +#ifdef CONFIG_64BIT + if (image_base != (unsigned long)startup_32) + adjust_memory_range_protection(image_base, image_size); +#else + /* + * Clear protection flags on a whole range of possible + * addresses used for KASLR. We don't need to do that + * on x86_64, since KASLR/extraction is performed after + * dedicated identity page tables are built and we only + * need to remove possible protection on relocated image + * itself disregarding further relocations. + */ + adjust_memory_range_protection(LOAD_PHYSICAL_ADDR, + KERNEL_IMAGE_SIZE - LOAD_PHYSICAL_ADDR); +#endif +} + static const efi_char16_t apple[] = L"Apple"; -static void setup_quirks(struct boot_params *boot_params) +static void setup_quirks(struct boot_params *boot_params, + unsigned long image_base, + unsigned long image_size) { efi_char16_t *fw_vendor = (efi_char16_t *)(unsigned long) efi_table_attr(efi_system_table, fw_vendor); @@ -222,6 +324,9 @@ static void setup_quirks(struct boot_params *boot_params) if (IS_ENABLED(CONFIG_APPLE_PROPERTIES)) retrieve_apple_device_properties(boot_params); } + + if (IS_ENABLED(CONFIG_EFI_DXE_MEM_ATTRIBUTES)) + setup_memory_protection(image_base, image_size); } /* @@ -341,8 +446,6 @@ static void __noreturn efi_exit(efi_handle_t handle, efi_status_t status) asm("hlt"); } -void startup_32(struct boot_params *boot_params); - void __noreturn efi_stub_entry(efi_handle_t handle, efi_system_table_t *sys_table_arg, struct boot_params *boot_params); @@ -677,11 +780,17 @@ unsigned long efi_main(efi_handle_t handle, efi_status_t status; efi_system_table = sys_table_arg; - /* Check if we were booted by the EFI firmware */ if (efi_system_table->hdr.signature != EFI_SYSTEM_TABLE_SIGNATURE) efi_exit(handle, EFI_INVALID_PARAMETER); + efi_dxe_table = get_efi_config_table(EFI_DXE_SERVICES_TABLE_GUID); + if (efi_dxe_table && + efi_dxe_table->hdr.signature != EFI_DXE_SERVICES_TABLE_SIGNATURE) { + efi_warn("Ignoring DXE services table: invalid signature\n"); + efi_dxe_table = NULL; + } + /* * If the kernel isn't already loaded at a suitable address, * relocate it. @@ -791,7 +900,7 @@ unsigned long efi_main(efi_handle_t handle, setup_efi_pci(boot_params); - setup_quirks(boot_params); + setup_quirks(boot_params, bzimage_addr, buffer_end - buffer_start); status = exit_boot(boot_params, handle); if (status != EFI_SUCCESS) { diff --git a/drivers/gpio/TODO b/drivers/gpio/TODO index b8b1473a5b1e..f87ff3fa8a53 100644 --- a/drivers/gpio/TODO +++ b/drivers/gpio/TODO @@ -178,3 +178,22 @@ discussed but the idea is to provide a low-level access point for debugging and hacking and to expose all lines without the need of any exporting. Also provide ample ammunition to shoot oneself in the foot, because this is debugfs after all. + + +Moving over to immutable irq_chip structures + +Most of the gpio chips implementing interrupt support rely on gpiolib +intercepting some of the irq_chip callbacks, preventing the structures +from being made read-only and forcing duplication of structures that +should otherwise be unique. + +The solution is to call into the gpiolib code when needed (resource +management, enable/disable or unmask/mask callbacks), and to let the +core code know about that by exposing a flag (IRQCHIP_IMMUTABLE) in +the irq_chip structure. The irq_chip structure can then be made unique +and const. + +A small number of drivers have been converted (pl061, tegra186, msm, +amd, apple), and can be used as examples of how to proceed with this +conversion. Note that drivers using the generic irqchip framework +cannot be converted yet, but watch this space! diff --git a/drivers/gpio/gpio-mvebu.c b/drivers/gpio/gpio-mvebu.c index a2c8dd329b31..2db19cd640a4 100644 --- a/drivers/gpio/gpio-mvebu.c +++ b/drivers/gpio/gpio-mvebu.c @@ -707,6 +707,9 @@ static int mvebu_pwm_apply(struct pwm_chip *chip, struct pwm_device *pwm, unsigned long flags; unsigned int on, off; + if (state->polarity != PWM_POLARITY_NORMAL) + return -EINVAL; + val = (unsigned long long) mvpwm->clk_rate * state->duty_cycle; do_div(val, NSEC_PER_SEC); if (val > UINT_MAX + 1ULL) diff --git a/drivers/gpio/gpio-pl061.c b/drivers/gpio/gpio-pl061.c index 4ecab700f23f..6464056cb6ae 100644 --- a/drivers/gpio/gpio-pl061.c +++ b/drivers/gpio/gpio-pl061.c @@ -52,7 +52,6 @@ struct pl061 { void __iomem *base; struct gpio_chip gc; - struct irq_chip irq_chip; int parent_irq; #ifdef CONFIG_PM @@ -241,6 +240,8 @@ static void pl061_irq_mask(struct irq_data *d) gpioie = readb(pl061->base + GPIOIE) & ~mask; writeb(gpioie, pl061->base + GPIOIE); raw_spin_unlock(&pl061->lock); + + gpiochip_disable_irq(gc, d->hwirq); } static void pl061_irq_unmask(struct irq_data *d) @@ -250,6 +251,8 @@ static void pl061_irq_unmask(struct irq_data *d) u8 mask = BIT(irqd_to_hwirq(d) % PL061_GPIO_NR); u8 gpioie; + gpiochip_enable_irq(gc, d->hwirq); + raw_spin_lock(&pl061->lock); gpioie = readb(pl061->base + GPIOIE) | mask; writeb(gpioie, pl061->base + GPIOIE); @@ -283,6 +286,24 @@ static int pl061_irq_set_wake(struct irq_data *d, unsigned int state) return irq_set_irq_wake(pl061->parent_irq, state); } +static void pl061_irq_print_chip(struct irq_data *data, struct seq_file *p) +{ + struct gpio_chip *gc = irq_data_get_irq_chip_data(data); + + seq_printf(p, dev_name(gc->parent)); +} + +static const struct irq_chip pl061_irq_chip = { + .irq_ack = pl061_irq_ack, + .irq_mask = pl061_irq_mask, + .irq_unmask = pl061_irq_unmask, + .irq_set_type = pl061_irq_type, + .irq_set_wake = pl061_irq_set_wake, + .irq_print_chip = pl061_irq_print_chip, + .flags = IRQCHIP_IMMUTABLE, + GPIOCHIP_IRQ_RESOURCE_HELPERS, +}; + static int pl061_probe(struct amba_device *adev, const struct amba_id *id) { struct device *dev = &adev->dev; @@ -315,13 +336,6 @@ static int pl061_probe(struct amba_device *adev, const struct amba_id *id) /* * irq_chip support */ - pl061->irq_chip.name = dev_name(dev); - pl061->irq_chip.irq_ack = pl061_irq_ack; - pl061->irq_chip.irq_mask = pl061_irq_mask; - pl061->irq_chip.irq_unmask = pl061_irq_unmask; - pl061->irq_chip.irq_set_type = pl061_irq_type; - pl061->irq_chip.irq_set_wake = pl061_irq_set_wake; - writeb(0, pl061->base + GPIOIE); /* disable irqs */ irq = adev->irq[0]; if (!irq) @@ -329,7 +343,7 @@ static int pl061_probe(struct amba_device *adev, const struct amba_id *id) pl061->parent_irq = irq; girq = &pl061->gc.irq; - girq->chip = &pl061->irq_chip; + gpio_irq_chip_set_chip(girq, &pl061_irq_chip); girq->parent_handler = pl061_irq_handler; girq->num_parents = 1; girq->parents = devm_kcalloc(dev, 1, sizeof(*girq->parents), diff --git a/drivers/gpio/gpio-tegra186.c b/drivers/gpio/gpio-tegra186.c index 031fe105b58e..84c4f1e9fb0c 100644 --- a/drivers/gpio/gpio-tegra186.c +++ b/drivers/gpio/gpio-tegra186.c @@ -80,7 +80,6 @@ struct tegra_gpio_soc { struct tegra_gpio { struct gpio_chip gpio; - struct irq_chip intc; unsigned int num_irq; unsigned int *irq; @@ -372,6 +371,8 @@ static void tegra186_irq_mask(struct irq_data *data) value = readl(base + TEGRA186_GPIO_ENABLE_CONFIG); value &= ~TEGRA186_GPIO_ENABLE_CONFIG_INTERRUPT; writel(value, base + TEGRA186_GPIO_ENABLE_CONFIG); + + gpiochip_disable_irq(&gpio->gpio, data->hwirq); } static void tegra186_irq_unmask(struct irq_data *data) @@ -385,6 +386,8 @@ static void tegra186_irq_unmask(struct irq_data *data) if (WARN_ON(base == NULL)) return; + gpiochip_enable_irq(&gpio->gpio, data->hwirq); + value = readl(base + TEGRA186_GPIO_ENABLE_CONFIG); value |= TEGRA186_GPIO_ENABLE_CONFIG_INTERRUPT; writel(value, base + TEGRA186_GPIO_ENABLE_CONFIG); @@ -456,6 +459,24 @@ static int tegra186_irq_set_wake(struct irq_data *data, unsigned int on) return 0; } +static void tegra186_irq_print_chip(struct irq_data *data, struct seq_file *p) +{ + struct gpio_chip *gc = irq_data_get_irq_chip_data(data); + + seq_printf(p, dev_name(gc->parent)); +} + +static const struct irq_chip tegra186_gpio_irq_chip = { + .irq_ack = tegra186_irq_ack, + .irq_mask = tegra186_irq_mask, + .irq_unmask = tegra186_irq_unmask, + .irq_set_type = tegra186_irq_set_type, + .irq_set_wake = tegra186_irq_set_wake, + .irq_print_chip = tegra186_irq_print_chip, + .flags = IRQCHIP_IMMUTABLE, + GPIOCHIP_IRQ_RESOURCE_HELPERS, +}; + static void tegra186_gpio_irq(struct irq_desc *desc) { struct tegra_gpio *gpio = irq_desc_get_handler_data(desc); @@ -760,15 +781,8 @@ static int tegra186_gpio_probe(struct platform_device *pdev) gpio->gpio.of_xlate = tegra186_gpio_of_xlate; #endif /* CONFIG_OF_GPIO */ - gpio->intc.name = dev_name(&pdev->dev); - gpio->intc.irq_ack = tegra186_irq_ack; - gpio->intc.irq_mask = tegra186_irq_mask; - gpio->intc.irq_unmask = tegra186_irq_unmask; - gpio->intc.irq_set_type = tegra186_irq_set_type; - gpio->intc.irq_set_wake = tegra186_irq_set_wake; - irq = &gpio->gpio.irq; - irq->chip = &gpio->intc; + gpio_irq_chip_set_chip(irq, &tegra186_gpio_irq_chip); irq->fwnode = of_node_to_fwnode(pdev->dev.of_node); irq->child_to_parent_hwirq = tegra186_gpio_child_to_parent_hwirq; irq->populate_parent_alloc_arg = tegra186_gpio_populate_parent_fwspec; diff --git a/drivers/gpio/gpio-vf610.c b/drivers/gpio/gpio-vf610.c index 20780c35da1b..23cddb265a0d 100644 --- a/drivers/gpio/gpio-vf610.c +++ b/drivers/gpio/gpio-vf610.c @@ -125,9 +125,13 @@ static int vf610_gpio_direction_output(struct gpio_chip *chip, unsigned gpio, { struct vf610_gpio_port *port = gpiochip_get_data(chip); unsigned long mask = BIT(gpio); + u32 val; - if (port->sdata && port->sdata->have_paddr) - vf610_gpio_writel(mask, port->gpio_base + GPIO_PDDR); + if (port->sdata && port->sdata->have_paddr) { + val = vf610_gpio_readl(port->gpio_base + GPIO_PDDR); + val |= mask; + vf610_gpio_writel(val, port->gpio_base + GPIO_PDDR); + } vf610_gpio_set(chip, gpio, value); diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c index b7694171655c..690035124faa 100644 --- a/drivers/gpio/gpiolib.c +++ b/drivers/gpio/gpiolib.c @@ -1433,19 +1433,21 @@ static int gpiochip_to_irq(struct gpio_chip *gc, unsigned int offset) return irq_create_mapping(domain, offset); } -static int gpiochip_irq_reqres(struct irq_data *d) +int gpiochip_irq_reqres(struct irq_data *d) { struct gpio_chip *gc = irq_data_get_irq_chip_data(d); return gpiochip_reqres_irq(gc, d->hwirq); } +EXPORT_SYMBOL(gpiochip_irq_reqres); -static void gpiochip_irq_relres(struct irq_data *d) +void gpiochip_irq_relres(struct irq_data *d) { struct gpio_chip *gc = irq_data_get_irq_chip_data(d); gpiochip_relres_irq(gc, d->hwirq); } +EXPORT_SYMBOL(gpiochip_irq_relres); static void gpiochip_irq_mask(struct irq_data *d) { @@ -1485,6 +1487,11 @@ static void gpiochip_set_irq_hooks(struct gpio_chip *gc) { struct irq_chip *irqchip = gc->irq.chip; + if (irqchip->flags & IRQCHIP_IMMUTABLE) + return; + + chip_warn(gc, "not an immutable chip, please consider fixing it!\n"); + if (!irqchip->irq_request_resources && !irqchip->irq_release_resources) { irqchip->irq_request_resources = gpiochip_irq_reqres; @@ -1652,7 +1659,7 @@ static void gpiochip_irqchip_remove(struct gpio_chip *gc) irq_domain_remove(gc->irq.domain); } - if (irqchip) { + if (irqchip && !(irqchip->flags & IRQCHIP_IMMUTABLE)) { if (irqchip->irq_request_resources == gpiochip_irq_reqres) { irqchip->irq_request_resources = NULL; irqchip->irq_release_resources = NULL; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h index cdf0818088b3..7606e3b6361e 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h @@ -1342,9 +1342,11 @@ static inline int amdgpu_acpi_smart_shift_update(struct drm_device *dev, #if defined(CONFIG_ACPI) && defined(CONFIG_SUSPEND) bool amdgpu_acpi_is_s3_active(struct amdgpu_device *adev); +bool amdgpu_acpi_should_gpu_reset(struct amdgpu_device *adev); bool amdgpu_acpi_is_s0ix_active(struct amdgpu_device *adev); #else static inline bool amdgpu_acpi_is_s0ix_active(struct amdgpu_device *adev) { return false; } +static inline bool amdgpu_acpi_should_gpu_reset(struct amdgpu_device *adev) { return false; } static inline bool amdgpu_acpi_is_s3_active(struct amdgpu_device *adev) { return false; } #endif diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c index 0e12315fa0cb..98ac53ee6bb5 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c @@ -1046,6 +1046,20 @@ bool amdgpu_acpi_is_s3_active(struct amdgpu_device *adev) } /** + * amdgpu_acpi_should_gpu_reset + * + * @adev: amdgpu_device_pointer + * + * returns true if should reset GPU, false if not + */ +bool amdgpu_acpi_should_gpu_reset(struct amdgpu_device *adev) +{ + if (adev->flags & AMD_IS_APU) + return false; + return pm_suspend_target_state != PM_SUSPEND_TO_IDLE; +} + +/** * amdgpu_acpi_is_s0ix_active * * @adev: amdgpu_device_pointer diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c index 8f0e6d93bb9c..c317078d1afd 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c @@ -296,6 +296,7 @@ static int amdgpu_ctx_set_stable_pstate(struct amdgpu_ctx *ctx, { struct amdgpu_device *adev = ctx->adev; enum amd_dpm_forced_level level; + u32 current_stable_pstate; int r; mutex_lock(&adev->pm.stable_pstate_ctx_lock); @@ -304,6 +305,10 @@ static int amdgpu_ctx_set_stable_pstate(struct amdgpu_ctx *ctx, goto done; } + r = amdgpu_ctx_get_stable_pstate(ctx, ¤t_stable_pstate); + if (r || (stable_pstate == current_stable_pstate)) + goto done; + switch (stable_pstate) { case AMDGPU_CTX_STABLE_PSTATE_NONE: level = AMD_DPM_FORCED_LEVEL_AUTO; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c index 7fd0277b2805..46ef57b07c15 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c @@ -2336,7 +2336,7 @@ static int amdgpu_pmops_suspend_noirq(struct device *dev) struct drm_device *drm_dev = dev_get_drvdata(dev); struct amdgpu_device *adev = drm_to_adev(drm_dev); - if (!adev->in_s0ix) + if (amdgpu_acpi_should_gpu_reset(adev)) return amdgpu_asic_reset(adev); return 0; diff --git a/drivers/gpu/drm/amd/amdgpu/vi.c b/drivers/gpu/drm/amd/amdgpu/vi.c index 039b90cdc3bc..45f0188c4273 100644 --- a/drivers/gpu/drm/amd/amdgpu/vi.c +++ b/drivers/gpu/drm/amd/amdgpu/vi.c @@ -81,6 +81,10 @@ #include "mxgpu_vi.h" #include "amdgpu_dm.h" +#if IS_ENABLED(CONFIG_X86) +#include <asm/intel-family.h> +#endif + #define ixPCIE_LC_L1_PM_SUBSTATE 0x100100C6 #define PCIE_LC_L1_PM_SUBSTATE__LC_L1_SUBSTATES_OVERRIDE_EN_MASK 0x00000001L #define PCIE_LC_L1_PM_SUBSTATE__LC_PCI_PM_L1_2_OVERRIDE_MASK 0x00000002L @@ -1134,13 +1138,24 @@ static void vi_enable_aspm(struct amdgpu_device *adev) WREG32_PCIE(ixPCIE_LC_CNTL, data); } +static bool aspm_support_quirk_check(void) +{ +#if IS_ENABLED(CONFIG_X86) + struct cpuinfo_x86 *c = &cpu_data(0); + + return !(c->x86 == 6 && c->x86_model == INTEL_FAM6_ALDERLAKE); +#else + return true; +#endif +} + static void vi_program_aspm(struct amdgpu_device *adev) { u32 data, data1, orig; bool bL1SS = false; bool bClkReqSupport = true; - if (!amdgpu_device_should_use_aspm(adev)) + if (!amdgpu_device_should_use_aspm(adev) || !aspm_support_quirk_check()) return; if (adev->flags & AMD_IS_APU || diff --git a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_init.c b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_init.c index d7559e5a99ce..e708f07fe75a 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_init.c +++ b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_init.c @@ -153,9 +153,4 @@ void dcn31_hw_sequencer_construct(struct dc *dc) dc->hwss.init_hw = dcn20_fpga_init_hw; dc->hwseq->funcs.init_pipes = NULL; } - if (dc->debug.disable_z10) { - /*hw not support z10 or sw disable it*/ - dc->hwss.z10_restore = NULL; - dc->hwss.z10_save_init = NULL; - } } diff --git a/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c b/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c index f1544755d8b4..f10a0256413e 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c +++ b/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c @@ -1351,14 +1351,8 @@ static int smu_disable_dpms(struct smu_context *smu) { struct amdgpu_device *adev = smu->adev; int ret = 0; - /* - * TODO: (adev->in_suspend && !adev->in_s0ix) is added to pair - * the workaround which always reset the asic in suspend. - * It's likely that workaround will be dropped in the future. - * Then the change here should be dropped together. - */ bool use_baco = !smu->is_apu && - (((amdgpu_in_reset(adev) || (adev->in_suspend && !adev->in_s0ix)) && + ((amdgpu_in_reset(adev) && (amdgpu_asic_reset_method(adev) == AMD_RESET_METHOD_BACO)) || ((adev->in_runpm || adev->in_s4) && amdgpu_asic_supports_baco(adev))); diff --git a/drivers/gpu/drm/dp/drm_dp_mst_topology.c b/drivers/gpu/drm/dp/drm_dp_mst_topology.c index 11300b53d24f..7a7cc44686f9 100644 --- a/drivers/gpu/drm/dp/drm_dp_mst_topology.c +++ b/drivers/gpu/drm/dp/drm_dp_mst_topology.c @@ -4852,6 +4852,7 @@ static void fetch_monitor_name(struct drm_dp_mst_topology_mgr *mgr, mst_edid = drm_dp_mst_get_edid(port->connector, mgr, port); drm_edid_get_monitor_name(mst_edid, name, namelen); + kfree(mst_edid); } /** diff --git a/drivers/gpu/drm/i915/display/intel_dmc.c b/drivers/gpu/drm/i915/display/intel_dmc.c index 7616a3906b9e..1b774dcfb281 100644 --- a/drivers/gpu/drm/i915/display/intel_dmc.c +++ b/drivers/gpu/drm/i915/display/intel_dmc.c @@ -367,6 +367,44 @@ static void dmc_set_fw_offset(struct intel_dmc *dmc, } } +static bool dmc_mmio_addr_sanity_check(struct intel_dmc *dmc, + const u32 *mmioaddr, u32 mmio_count, + int header_ver, u8 dmc_id) +{ + struct drm_i915_private *i915 = container_of(dmc, typeof(*i915), dmc); + u32 start_range, end_range; + int i; + + if (dmc_id >= DMC_FW_MAX) { + drm_warn(&i915->drm, "Unsupported firmware id %u\n", dmc_id); + return false; + } + + if (header_ver == 1) { + start_range = DMC_MMIO_START_RANGE; + end_range = DMC_MMIO_END_RANGE; + } else if (dmc_id == DMC_FW_MAIN) { + start_range = TGL_MAIN_MMIO_START; + end_range = TGL_MAIN_MMIO_END; + } else if (DISPLAY_VER(i915) >= 13) { + start_range = ADLP_PIPE_MMIO_START; + end_range = ADLP_PIPE_MMIO_END; + } else if (DISPLAY_VER(i915) >= 12) { + start_range = TGL_PIPE_MMIO_START(dmc_id); + end_range = TGL_PIPE_MMIO_END(dmc_id); + } else { + drm_warn(&i915->drm, "Unknown mmio range for sanity check"); + return false; + } + + for (i = 0; i < mmio_count; i++) { + if (mmioaddr[i] < start_range || mmioaddr[i] > end_range) + return false; + } + + return true; +} + static u32 parse_dmc_fw_header(struct intel_dmc *dmc, const struct intel_dmc_header_base *dmc_header, size_t rem_size, u8 dmc_id) @@ -436,6 +474,12 @@ static u32 parse_dmc_fw_header(struct intel_dmc *dmc, return 0; } + if (!dmc_mmio_addr_sanity_check(dmc, mmioaddr, mmio_count, + dmc_header->header_ver, dmc_id)) { + drm_err(&i915->drm, "DMC firmware has Wrong MMIO Addresses\n"); + return 0; + } + for (i = 0; i < mmio_count; i++) { dmc_info->mmioaddr[i] = _MMIO(mmioaddr[i]); dmc_info->mmiodata[i] = mmiodata[i]; diff --git a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c index d42f437149c9..6ca8929cf6e1 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c @@ -1252,14 +1252,12 @@ static void *reloc_iomap(struct i915_vma *batch, * Only attempt to pin the batch buffer to ggtt if the current batch * is not inside ggtt, or the batch buffer is not misplaced. */ - if (!i915_is_ggtt(batch->vm)) { + if (!i915_is_ggtt(batch->vm) || + !i915_vma_misplaced(batch, 0, 0, PIN_MAPPABLE)) { vma = i915_gem_object_ggtt_pin_ww(obj, &eb->ww, NULL, 0, 0, PIN_MAPPABLE | PIN_NONBLOCK /* NOWARN */ | PIN_NOEVICT); - } else if (i915_vma_is_map_and_fenceable(batch)) { - __i915_vma_pin(batch); - vma = batch; } if (vma == ERR_PTR(-EDEADLK)) diff --git a/drivers/gpu/drm/i915/gt/intel_reset.c b/drivers/gpu/drm/i915/gt/intel_reset.c index 82713264b96c..b7c6d4462ec5 100644 --- a/drivers/gpu/drm/i915/gt/intel_reset.c +++ b/drivers/gpu/drm/i915/gt/intel_reset.c @@ -806,7 +806,7 @@ static int gt_reset(struct intel_gt *gt, intel_engine_mask_t stalled_mask) __intel_engine_reset(engine, stalled_mask & engine->mask); local_bh_enable(); - intel_uc_reset(>->uc, true); + intel_uc_reset(>->uc, ALL_ENGINES); intel_ggtt_restore_fences(gt->ggtt); diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc.h b/drivers/gpu/drm/i915/gt/uc/intel_guc.h index bf7079480d47..2488d1197f3e 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_guc.h +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc.h @@ -438,7 +438,7 @@ int intel_guc_global_policies_update(struct intel_guc *guc); void intel_guc_context_ban(struct intel_context *ce, struct i915_request *rq); void intel_guc_submission_reset_prepare(struct intel_guc *guc); -void intel_guc_submission_reset(struct intel_guc *guc, bool stalled); +void intel_guc_submission_reset(struct intel_guc *guc, intel_engine_mask_t stalled); void intel_guc_submission_reset_finish(struct intel_guc *guc); void intel_guc_submission_cancel_requests(struct intel_guc *guc); diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c index 1ce7e04aa837..28f9aac0201d 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c @@ -1590,9 +1590,9 @@ __unwind_incomplete_requests(struct intel_context *ce) spin_unlock_irqrestore(&sched_engine->lock, flags); } -static void __guc_reset_context(struct intel_context *ce, bool stalled) +static void __guc_reset_context(struct intel_context *ce, intel_engine_mask_t stalled) { - bool local_stalled; + bool guilty; struct i915_request *rq; unsigned long flags; u32 head; @@ -1620,7 +1620,7 @@ static void __guc_reset_context(struct intel_context *ce, bool stalled) if (!intel_context_is_pinned(ce)) goto next_context; - local_stalled = false; + guilty = false; rq = intel_context_find_active_request(ce); if (!rq) { head = ce->ring->tail; @@ -1628,14 +1628,14 @@ static void __guc_reset_context(struct intel_context *ce, bool stalled) } if (i915_request_started(rq)) - local_stalled = true; + guilty = stalled & ce->engine->mask; GEM_BUG_ON(i915_active_is_idle(&ce->active)); head = intel_ring_wrap(ce->ring, rq->head); - __i915_request_reset(rq, local_stalled && stalled); + __i915_request_reset(rq, guilty); out_replay: - guc_reset_state(ce, head, local_stalled && stalled); + guc_reset_state(ce, head, guilty); next_context: if (i != number_children) ce = list_next_entry(ce, parallel.child_link); @@ -1645,7 +1645,7 @@ next_context: intel_context_put(parent); } -void intel_guc_submission_reset(struct intel_guc *guc, bool stalled) +void intel_guc_submission_reset(struct intel_guc *guc, intel_engine_mask_t stalled) { struct intel_context *ce; unsigned long index; @@ -4013,7 +4013,7 @@ static void guc_context_replay(struct intel_context *ce) { struct i915_sched_engine *sched_engine = ce->engine->sched_engine; - __guc_reset_context(ce, true); + __guc_reset_context(ce, ce->engine->mask); tasklet_hi_schedule(&sched_engine->tasklet); } diff --git a/drivers/gpu/drm/i915/gt/uc/intel_uc.c b/drivers/gpu/drm/i915/gt/uc/intel_uc.c index da199aa6989f..8eb34de2f20c 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_uc.c +++ b/drivers/gpu/drm/i915/gt/uc/intel_uc.c @@ -593,7 +593,7 @@ sanitize: __uc_sanitize(uc); } -void intel_uc_reset(struct intel_uc *uc, bool stalled) +void intel_uc_reset(struct intel_uc *uc, intel_engine_mask_t stalled) { struct intel_guc *guc = &uc->guc; diff --git a/drivers/gpu/drm/i915/gt/uc/intel_uc.h b/drivers/gpu/drm/i915/gt/uc/intel_uc.h index 866b462821c0..a8f38c2c60e2 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_uc.h +++ b/drivers/gpu/drm/i915/gt/uc/intel_uc.h @@ -42,7 +42,7 @@ void intel_uc_driver_late_release(struct intel_uc *uc); void intel_uc_driver_remove(struct intel_uc *uc); void intel_uc_init_mmio(struct intel_uc *uc); void intel_uc_reset_prepare(struct intel_uc *uc); -void intel_uc_reset(struct intel_uc *uc, bool stalled); +void intel_uc_reset(struct intel_uc *uc, intel_engine_mask_t stalled); void intel_uc_reset_finish(struct intel_uc *uc); void intel_uc_cancel_requests(struct intel_uc *uc); void intel_uc_suspend(struct intel_uc *uc); diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h index a9354f8f110d..fe960c204362 100644 --- a/drivers/gpu/drm/i915/i915_reg.h +++ b/drivers/gpu/drm/i915/i915_reg.h @@ -5501,6 +5501,22 @@ /* MMIO address range for DMC program (0x80000 - 0x82FFF) */ #define DMC_MMIO_START_RANGE 0x80000 #define DMC_MMIO_END_RANGE 0x8FFFF +#define DMC_V1_MMIO_START_RANGE 0x80000 +#define TGL_MAIN_MMIO_START 0x8F000 +#define TGL_MAIN_MMIO_END 0x8FFFF +#define _TGL_PIPEA_MMIO_START 0x92000 +#define _TGL_PIPEA_MMIO_END 0x93FFF +#define _TGL_PIPEB_MMIO_START 0x96000 +#define _TGL_PIPEB_MMIO_END 0x97FFF +#define ADLP_PIPE_MMIO_START 0x5F000 +#define ADLP_PIPE_MMIO_END 0x5FFFF + +#define TGL_PIPE_MMIO_START(dmc_id) _PICK_EVEN(((dmc_id) - 1), _TGL_PIPEA_MMIO_START,\ + _TGL_PIPEB_MMIO_START) + +#define TGL_PIPE_MMIO_END(dmc_id) _PICK_EVEN(((dmc_id) - 1), _TGL_PIPEA_MMIO_END,\ + _TGL_PIPEB_MMIO_END) + #define SKL_DMC_DC3_DC5_COUNT _MMIO(0x80030) #define SKL_DMC_DC5_DC6_COUNT _MMIO(0x8002C) #define BXT_DMC_DC3_DC5_COUNT _MMIO(0x80038) diff --git a/drivers/gpu/drm/i915/i915_vma.c b/drivers/gpu/drm/i915/i915_vma.c index 94fcdb7bd21d..eeaa8d0d0407 100644 --- a/drivers/gpu/drm/i915/i915_vma.c +++ b/drivers/gpu/drm/i915/i915_vma.c @@ -1605,17 +1605,17 @@ void i915_vma_close(struct i915_vma *vma) static void __i915_vma_remove_closed(struct i915_vma *vma) { - struct intel_gt *gt = vma->vm->gt; - - spin_lock_irq(>->closed_lock); list_del_init(&vma->closed_link); - spin_unlock_irq(>->closed_lock); } void i915_vma_reopen(struct i915_vma *vma) { + struct intel_gt *gt = vma->vm->gt; + + spin_lock_irq(>->closed_lock); if (i915_vma_is_closed(vma)) __i915_vma_remove_closed(vma); + spin_unlock_irq(>->closed_lock); } void i915_vma_release(struct kref *ref) @@ -1641,6 +1641,7 @@ static void force_unbind(struct i915_vma *vma) static void release_references(struct i915_vma *vma) { struct drm_i915_gem_object *obj = vma->obj; + struct intel_gt *gt = vma->vm->gt; GEM_BUG_ON(i915_vma_is_active(vma)); @@ -1650,7 +1651,9 @@ static void release_references(struct i915_vma *vma) rb_erase(&vma->obj_node, &obj->vma.tree); spin_unlock(&obj->vma.lock); + spin_lock_irq(>->closed_lock); __i915_vma_remove_closed(vma); + spin_unlock_irq(>->closed_lock); __i915_vma_put(vma); } diff --git a/drivers/gpu/drm/nouveau/nouveau_backlight.c b/drivers/gpu/drm/nouveau/nouveau_backlight.c index daf9f87477ba..a2141d3d9b1d 100644 --- a/drivers/gpu/drm/nouveau/nouveau_backlight.c +++ b/drivers/gpu/drm/nouveau/nouveau_backlight.c @@ -46,8 +46,9 @@ static bool nouveau_get_backlight_name(char backlight_name[BL_NAME_SIZE], struct nouveau_backlight *bl) { - const int nb = ida_simple_get(&bl_ida, 0, 0, GFP_KERNEL); - if (nb < 0 || nb >= 100) + const int nb = ida_alloc_max(&bl_ida, 99, GFP_KERNEL); + + if (nb < 0) return false; if (nb > 0) snprintf(backlight_name, BL_NAME_SIZE, "nv_backlight%d", nb); @@ -414,7 +415,7 @@ nouveau_backlight_init(struct drm_connector *connector) nv_encoder, ops, &props); if (IS_ERR(bl->dev)) { if (bl->id >= 0) - ida_simple_remove(&bl_ida, bl->id); + ida_free(&bl_ida, bl->id); ret = PTR_ERR(bl->dev); goto fail_alloc; } @@ -442,7 +443,7 @@ nouveau_backlight_fini(struct drm_connector *connector) return; if (bl->id >= 0) - ida_simple_remove(&bl_ida, bl->id); + ida_free(&bl_ida, bl->id); backlight_device_unregister(bl->dev); nv_conn->backlight = NULL; diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/device/tegra.c b/drivers/gpu/drm/nouveau/nvkm/engine/device/tegra.c index 992cc285f2fe..2ed528c065fa 100644 --- a/drivers/gpu/drm/nouveau/nvkm/engine/device/tegra.c +++ b/drivers/gpu/drm/nouveau/nvkm/engine/device/tegra.c @@ -123,7 +123,7 @@ nvkm_device_tegra_probe_iommu(struct nvkm_device_tegra *tdev) mutex_init(&tdev->iommu.mutex); - if (iommu_present(&platform_bus_type)) { + if (device_iommu_mapped(dev)) { tdev->iommu.domain = iommu_domain_alloc(&platform_bus_type); if (!tdev->iommu.domain) goto error; diff --git a/drivers/gpu/drm/vc4/vc4_hdmi.c b/drivers/gpu/drm/vc4/vc4_hdmi.c index 6c58b0fd13fb..98b78ec6b37d 100644 --- a/drivers/gpu/drm/vc4/vc4_hdmi.c +++ b/drivers/gpu/drm/vc4/vc4_hdmi.c @@ -38,6 +38,7 @@ #include <drm/drm_scdc_helper.h> #include <linux/clk.h> #include <linux/component.h> +#include <linux/gpio/consumer.h> #include <linux/i2c.h> #include <linux/of_address.h> #include <linux/of_gpio.h> diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_cmd.c b/drivers/gpu/drm/vmwgfx/vmwgfx_cmd.c index a3bfbb6c3e14..162dfeb1cc5a 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_cmd.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_cmd.c @@ -528,7 +528,7 @@ int vmw_cmd_send_fence(struct vmw_private *dev_priv, uint32_t *seqno) *seqno = atomic_add_return(1, &dev_priv->marker_seq); } while (*seqno == 0); - if (!(vmw_fifo_caps(dev_priv) & SVGA_FIFO_CAP_FENCE)) { + if (!vmw_has_fences(dev_priv)) { /* * Don't request hardware to send a fence. The @@ -675,11 +675,14 @@ int vmw_cmd_emit_dummy_query(struct vmw_private *dev_priv, */ bool vmw_cmd_supported(struct vmw_private *vmw) { - if ((vmw->capabilities & (SVGA_CAP_COMMAND_BUFFERS | - SVGA_CAP_CMD_BUFFERS_2)) != 0) - return true; + bool has_cmdbufs = + (vmw->capabilities & (SVGA_CAP_COMMAND_BUFFERS | + SVGA_CAP_CMD_BUFFERS_2)) != 0; + if (vmw_is_svga_v3(vmw)) + return (has_cmdbufs && + (vmw->capabilities & SVGA_CAP_GBOBJECTS) != 0); /* * We have FIFO cmd's */ - return vmw->fifo_mem != NULL; + return has_cmdbufs || vmw->fifo_mem != NULL; } diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h index ea3ecdda561d..6de0b9ef5c77 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h @@ -1679,4 +1679,12 @@ static inline void vmw_irq_status_write(struct vmw_private *vmw, outl(status, vmw->io_start + SVGA_IRQSTATUS_PORT); } +static inline bool vmw_has_fences(struct vmw_private *vmw) +{ + if ((vmw->capabilities & (SVGA_CAP_COMMAND_BUFFERS | + SVGA_CAP_CMD_BUFFERS_2)) != 0) + return true; + return (vmw_fifo_caps(vmw) & SVGA_FIFO_CAP_FENCE) != 0; +} + #endif diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_fb.c b/drivers/gpu/drm/vmwgfx/vmwgfx_fb.c index 8ee34576c7d0..adf17c740656 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_fb.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_fb.c @@ -483,7 +483,7 @@ static int vmw_fb_kms_detach(struct vmw_fb_par *par, static int vmw_fb_kms_framebuffer(struct fb_info *info) { - struct drm_mode_fb_cmd2 mode_cmd; + struct drm_mode_fb_cmd2 mode_cmd = {0}; struct vmw_fb_par *par = info->par; struct fb_var_screeninfo *var = &info->var; struct drm_framebuffer *cur_fb; diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_fence.c b/drivers/gpu/drm/vmwgfx/vmwgfx_fence.c index 59d6a2dd4c2e..66cc35dc223e 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_fence.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_fence.c @@ -82,6 +82,22 @@ fman_from_fence(struct vmw_fence_obj *fence) return container_of(fence->base.lock, struct vmw_fence_manager, lock); } +static u32 vmw_fence_goal_read(struct vmw_private *vmw) +{ + if ((vmw->capabilities2 & SVGA_CAP2_EXTRA_REGS) != 0) + return vmw_read(vmw, SVGA_REG_FENCE_GOAL); + else + return vmw_fifo_mem_read(vmw, SVGA_FIFO_FENCE_GOAL); +} + +static void vmw_fence_goal_write(struct vmw_private *vmw, u32 value) +{ + if ((vmw->capabilities2 & SVGA_CAP2_EXTRA_REGS) != 0) + vmw_write(vmw, SVGA_REG_FENCE_GOAL, value); + else + vmw_fifo_mem_write(vmw, SVGA_FIFO_FENCE_GOAL, value); +} + /* * Note on fencing subsystem usage of irqs: * Typically the vmw_fences_update function is called @@ -392,7 +408,7 @@ static bool vmw_fence_goal_new_locked(struct vmw_fence_manager *fman, if (likely(!fman->seqno_valid)) return false; - goal_seqno = vmw_fifo_mem_read(fman->dev_priv, SVGA_FIFO_FENCE_GOAL); + goal_seqno = vmw_fence_goal_read(fman->dev_priv); if (likely(passed_seqno - goal_seqno >= VMW_FENCE_WRAP)) return false; @@ -400,9 +416,8 @@ static bool vmw_fence_goal_new_locked(struct vmw_fence_manager *fman, list_for_each_entry(fence, &fman->fence_list, head) { if (!list_empty(&fence->seq_passed_actions)) { fman->seqno_valid = true; - vmw_fifo_mem_write(fman->dev_priv, - SVGA_FIFO_FENCE_GOAL, - fence->base.seqno); + vmw_fence_goal_write(fman->dev_priv, + fence->base.seqno); break; } } @@ -434,13 +449,12 @@ static bool vmw_fence_goal_check_locked(struct vmw_fence_obj *fence) if (dma_fence_is_signaled_locked(&fence->base)) return false; - goal_seqno = vmw_fifo_mem_read(fman->dev_priv, SVGA_FIFO_FENCE_GOAL); + goal_seqno = vmw_fence_goal_read(fman->dev_priv); if (likely(fman->seqno_valid && goal_seqno - fence->base.seqno < VMW_FENCE_WRAP)) return false; - vmw_fifo_mem_write(fman->dev_priv, SVGA_FIFO_FENCE_GOAL, - fence->base.seqno); + vmw_fence_goal_write(fman->dev_priv, fence->base.seqno); fman->seqno_valid = true; return true; diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_irq.c b/drivers/gpu/drm/vmwgfx/vmwgfx_irq.c index c5191de365ca..fe4732bf2c9d 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_irq.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_irq.c @@ -32,6 +32,14 @@ #define VMW_FENCE_WRAP (1 << 24) +static u32 vmw_irqflag_fence_goal(struct vmw_private *vmw) +{ + if ((vmw->capabilities2 & SVGA_CAP2_EXTRA_REGS) != 0) + return SVGA_IRQFLAG_REG_FENCE_GOAL; + else + return SVGA_IRQFLAG_FENCE_GOAL; +} + /** * vmw_thread_fn - Deferred (process context) irq handler * @@ -96,7 +104,7 @@ static irqreturn_t vmw_irq_handler(int irq, void *arg) wake_up_all(&dev_priv->fifo_queue); if ((masked_status & (SVGA_IRQFLAG_ANY_FENCE | - SVGA_IRQFLAG_FENCE_GOAL)) && + vmw_irqflag_fence_goal(dev_priv))) && !test_and_set_bit(VMW_IRQTHREAD_FENCE, dev_priv->irqthread_pending)) ret = IRQ_WAKE_THREAD; @@ -137,8 +145,7 @@ bool vmw_seqno_passed(struct vmw_private *dev_priv, if (likely(dev_priv->last_read_seqno - seqno < VMW_FENCE_WRAP)) return true; - if (!(vmw_fifo_caps(dev_priv) & SVGA_FIFO_CAP_FENCE) && - vmw_fifo_idle(dev_priv, seqno)) + if (!vmw_has_fences(dev_priv) && vmw_fifo_idle(dev_priv, seqno)) return true; /** @@ -160,6 +167,7 @@ int vmw_fallback_wait(struct vmw_private *dev_priv, unsigned long timeout) { struct vmw_fifo_state *fifo_state = dev_priv->fifo; + bool fifo_down = false; uint32_t count = 0; uint32_t signal_seq; @@ -176,12 +184,14 @@ int vmw_fallback_wait(struct vmw_private *dev_priv, */ if (fifo_idle) { - down_read(&fifo_state->rwsem); if (dev_priv->cman) { ret = vmw_cmdbuf_idle(dev_priv->cman, interruptible, 10*HZ); if (ret) goto out_err; + } else if (fifo_state) { + down_read(&fifo_state->rwsem); + fifo_down = true; } } @@ -218,12 +228,12 @@ int vmw_fallback_wait(struct vmw_private *dev_priv, } } finish_wait(&dev_priv->fence_queue, &__wait); - if (ret == 0 && fifo_idle) + if (ret == 0 && fifo_idle && fifo_state) vmw_fence_write(dev_priv, signal_seq); wake_up_all(&dev_priv->fence_queue); out_err: - if (fifo_idle) + if (fifo_down) up_read(&fifo_state->rwsem); return ret; @@ -266,13 +276,13 @@ void vmw_seqno_waiter_remove(struct vmw_private *dev_priv) void vmw_goal_waiter_add(struct vmw_private *dev_priv) { - vmw_generic_waiter_add(dev_priv, SVGA_IRQFLAG_FENCE_GOAL, + vmw_generic_waiter_add(dev_priv, vmw_irqflag_fence_goal(dev_priv), &dev_priv->goal_queue_waiters); } void vmw_goal_waiter_remove(struct vmw_private *dev_priv) { - vmw_generic_waiter_remove(dev_priv, SVGA_IRQFLAG_FENCE_GOAL, + vmw_generic_waiter_remove(dev_priv, vmw_irqflag_fence_goal(dev_priv), &dev_priv->goal_queue_waiters); } diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c index bbd2f4ec08ec..93431e8f6606 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c @@ -1344,7 +1344,6 @@ vmw_kms_new_framebuffer(struct vmw_private *dev_priv, ret = vmw_kms_new_framebuffer_surface(dev_priv, surface, &vfb, mode_cmd, is_bo_proxy); - /* * vmw_create_bo_proxy() adds a reference that is no longer * needed @@ -1385,13 +1384,16 @@ static struct drm_framebuffer *vmw_kms_fb_create(struct drm_device *dev, ret = vmw_user_lookup_handle(dev_priv, file_priv, mode_cmd->handles[0], &surface, &bo); - if (ret) + if (ret) { + DRM_ERROR("Invalid buffer object handle %u (0x%x).\n", + mode_cmd->handles[0], mode_cmd->handles[0]); goto err_out; + } if (!bo && !vmw_kms_srf_ok(dev_priv, mode_cmd->width, mode_cmd->height)) { - DRM_ERROR("Surface size cannot exceed %dx%d", + DRM_ERROR("Surface size cannot exceed %dx%d\n", dev_priv->texture_max_width, dev_priv->texture_max_height); goto err_out; diff --git a/drivers/hwmon/Kconfig b/drivers/hwmon/Kconfig index 68a8a27ab3b7..f2b038fa3b84 100644 --- a/drivers/hwmon/Kconfig +++ b/drivers/hwmon/Kconfig @@ -960,7 +960,7 @@ config SENSORS_LTC4261 config SENSORS_LTQ_CPUTEMP bool "Lantiq cpu temperature sensor driver" - depends on LANTIQ + depends on SOC_XWAY help If you say yes here you get support for the temperature sensor inside your CPU. diff --git a/drivers/hwmon/tmp401.c b/drivers/hwmon/tmp401.c index b86d9df7105d..52c9e7d3f2ae 100644 --- a/drivers/hwmon/tmp401.c +++ b/drivers/hwmon/tmp401.c @@ -708,10 +708,21 @@ static int tmp401_probe(struct i2c_client *client) return 0; } +static const struct of_device_id __maybe_unused tmp4xx_of_match[] = { + { .compatible = "ti,tmp401", }, + { .compatible = "ti,tmp411", }, + { .compatible = "ti,tmp431", }, + { .compatible = "ti,tmp432", }, + { .compatible = "ti,tmp435", }, + { }, +}; +MODULE_DEVICE_TABLE(of, tmp4xx_of_match); + static struct i2c_driver tmp401_driver = { .class = I2C_CLASS_HWMON, .driver = { .name = "tmp401", + .of_match_table = of_match_ptr(tmp4xx_of_match), }, .probe_new = tmp401_probe, .id_table = tmp401_id, diff --git a/drivers/i2c/busses/i2c-ismt.c b/drivers/i2c/busses/i2c-ismt.c index c0364314877e..c16157ee8c52 100644 --- a/drivers/i2c/busses/i2c-ismt.c +++ b/drivers/i2c/busses/i2c-ismt.c @@ -82,6 +82,7 @@ #define ISMT_DESC_ENTRIES 2 /* number of descriptor entries */ #define ISMT_MAX_RETRIES 3 /* number of SMBus retries to attempt */ +#define ISMT_LOG_ENTRIES 3 /* number of interrupt cause log entries */ /* Hardware Descriptor Constants - Control Field */ #define ISMT_DESC_CWRL 0x01 /* Command/Write Length */ @@ -175,6 +176,8 @@ struct ismt_priv { u8 head; /* ring buffer head pointer */ struct completion cmp; /* interrupt completion */ u8 buffer[I2C_SMBUS_BLOCK_MAX + 16]; /* temp R/W data buffer */ + dma_addr_t log_dma; + u32 *log; }; static const struct pci_device_id ismt_ids[] = { @@ -411,6 +414,9 @@ static int ismt_access(struct i2c_adapter *adap, u16 addr, memset(desc, 0, sizeof(struct ismt_desc)); desc->tgtaddr_rw = ISMT_DESC_ADDR_RW(addr, read_write); + /* Always clear the log entries */ + memset(priv->log, 0, ISMT_LOG_ENTRIES * sizeof(u32)); + /* Initialize common control bits */ if (likely(pci_dev_msi_enabled(priv->pci_dev))) desc->control = ISMT_DESC_INT | ISMT_DESC_FAIR; @@ -708,6 +714,8 @@ static void ismt_hw_init(struct ismt_priv *priv) /* initialize the Master Descriptor Base Address (MDBA) */ writeq(priv->io_rng_dma, priv->smba + ISMT_MSTR_MDBA); + writeq(priv->log_dma, priv->smba + ISMT_GR_SMTICL); + /* initialize the Master Control Register (MCTRL) */ writel(ISMT_MCTRL_MEIE, priv->smba + ISMT_MSTR_MCTRL); @@ -795,6 +803,12 @@ static int ismt_dev_init(struct ismt_priv *priv) priv->head = 0; init_completion(&priv->cmp); + priv->log = dmam_alloc_coherent(&priv->pci_dev->dev, + ISMT_LOG_ENTRIES * sizeof(u32), + &priv->log_dma, GFP_KERNEL); + if (!priv->log) + return -ENOMEM; + return 0; } diff --git a/drivers/i2c/busses/i2c-mt7621.c b/drivers/i2c/busses/i2c-mt7621.c index 45fe4a7fe0c0..901f0fb04fee 100644 --- a/drivers/i2c/busses/i2c-mt7621.c +++ b/drivers/i2c/busses/i2c-mt7621.c @@ -304,7 +304,8 @@ static int mtk_i2c_probe(struct platform_device *pdev) if (i2c->bus_freq == 0) { dev_warn(i2c->dev, "clock-frequency 0 not supported\n"); - return -EINVAL; + ret = -EINVAL; + goto err_disable_clk; } adap = &i2c->adap; @@ -322,10 +323,15 @@ static int mtk_i2c_probe(struct platform_device *pdev) ret = i2c_add_adapter(adap); if (ret < 0) - return ret; + goto err_disable_clk; dev_info(&pdev->dev, "clock %u kHz\n", i2c->bus_freq / 1000); + return 0; + +err_disable_clk: + clk_disable_unprepare(i2c->clk); + return ret; } diff --git a/drivers/i2c/busses/i2c-thunderx-pcidrv.c b/drivers/i2c/busses/i2c-thunderx-pcidrv.c index 12c90aa0900e..a77cd86fe75e 100644 --- a/drivers/i2c/busses/i2c-thunderx-pcidrv.c +++ b/drivers/i2c/busses/i2c-thunderx-pcidrv.c @@ -213,6 +213,7 @@ static int thunder_i2c_probe_pci(struct pci_dev *pdev, i2c->adap.bus_recovery_info = &octeon_i2c_recovery_info; i2c->adap.dev.parent = dev; i2c->adap.dev.of_node = pdev->dev.of_node; + i2c->adap.dev.fwnode = dev->fwnode; snprintf(i2c->adap.name, sizeof(i2c->adap.name), "Cavium ThunderX i2c adapter at %s", dev_name(dev)); i2c_set_adapdata(&i2c->adap, i2c); diff --git a/drivers/input/touchscreen/ili210x.c b/drivers/input/touchscreen/ili210x.c index 2bd407d86bae..e9bd36adbe47 100644 --- a/drivers/input/touchscreen/ili210x.c +++ b/drivers/input/touchscreen/ili210x.c @@ -756,15 +756,12 @@ static int ili251x_firmware_reset(struct i2c_client *client) return ili251x_firmware_busy(client); } -static void ili251x_hardware_reset(struct device *dev) +static void ili210x_hardware_reset(struct gpio_desc *reset_gpio) { - struct i2c_client *client = to_i2c_client(dev); - struct ili210x *priv = i2c_get_clientdata(client); - /* Reset the controller */ - gpiod_set_value_cansleep(priv->reset_gpio, 1); - usleep_range(10000, 15000); - gpiod_set_value_cansleep(priv->reset_gpio, 0); + gpiod_set_value_cansleep(reset_gpio, 1); + usleep_range(12000, 15000); + gpiod_set_value_cansleep(reset_gpio, 0); msleep(300); } @@ -773,6 +770,7 @@ static ssize_t ili210x_firmware_update_store(struct device *dev, const char *buf, size_t count) { struct i2c_client *client = to_i2c_client(dev); + struct ili210x *priv = i2c_get_clientdata(client); const char *fwname = ILI251X_FW_FILENAME; const struct firmware *fw; u16 ac_end, df_end; @@ -803,7 +801,7 @@ static ssize_t ili210x_firmware_update_store(struct device *dev, dev_dbg(dev, "Firmware update started, firmware=%s\n", fwname); - ili251x_hardware_reset(dev); + ili210x_hardware_reset(priv->reset_gpio); error = ili251x_firmware_reset(client); if (error) @@ -858,7 +856,7 @@ static ssize_t ili210x_firmware_update_store(struct device *dev, error = count; exit: - ili251x_hardware_reset(dev); + ili210x_hardware_reset(priv->reset_gpio); dev_dbg(dev, "Firmware update ended, error=%i\n", error); enable_irq(client->irq); kfree(fwbuf); @@ -951,9 +949,7 @@ static int ili210x_i2c_probe(struct i2c_client *client, if (error) return error; - usleep_range(50, 100); - gpiod_set_value_cansleep(reset_gpio, 0); - msleep(100); + ili210x_hardware_reset(reset_gpio); } priv = devm_kzalloc(dev, sizeof(*priv), GFP_KERNEL); diff --git a/drivers/interconnect/core.c b/drivers/interconnect/core.c index 9050ca1f4285..808f6e7a8048 100644 --- a/drivers/interconnect/core.c +++ b/drivers/interconnect/core.c @@ -1087,9 +1087,15 @@ static int of_count_icc_providers(struct device_node *np) { struct device_node *child; int count = 0; + const struct of_device_id __maybe_unused ignore_list[] = { + { .compatible = "qcom,sc7180-ipa-virt" }, + { .compatible = "qcom,sdx55-ipa-virt" }, + {} + }; for_each_available_child_of_node(np, child) { - if (of_property_read_bool(child, "#interconnect-cells")) + if (of_property_read_bool(child, "#interconnect-cells") && + likely(!of_match_node(ignore_list, child))) count++; count += of_count_icc_providers(child); } diff --git a/drivers/irqchip/Kconfig b/drivers/irqchip/Kconfig index 15edb9a6fcae..135c156673a7 100644 --- a/drivers/irqchip/Kconfig +++ b/drivers/irqchip/Kconfig @@ -257,6 +257,18 @@ config ST_IRQCHIP help Enables SysCfg Controlled IRQs on STi based platforms. +config SUN4I_INTC + bool + +config SUN6I_R_INTC + bool + select IRQ_DOMAIN_HIERARCHY + select IRQ_FASTEOI_HIERARCHY_HANDLERS + +config SUNXI_NMI_INTC + bool + select GENERIC_IRQ_CHIP + config TB10X_IRQC bool select IRQ_DOMAIN diff --git a/drivers/irqchip/Makefile b/drivers/irqchip/Makefile index 160a1d8ceaa9..9b1ffb0f98cc 100644 --- a/drivers/irqchip/Makefile +++ b/drivers/irqchip/Makefile @@ -23,9 +23,9 @@ obj-$(CONFIG_OMPIC) += irq-ompic.o obj-$(CONFIG_OR1K_PIC) += irq-or1k-pic.o obj-$(CONFIG_ORION_IRQCHIP) += irq-orion.o obj-$(CONFIG_OMAP_IRQCHIP) += irq-omap-intc.o -obj-$(CONFIG_ARCH_SUNXI) += irq-sun4i.o -obj-$(CONFIG_ARCH_SUNXI) += irq-sun6i-r.o -obj-$(CONFIG_ARCH_SUNXI) += irq-sunxi-nmi.o +obj-$(CONFIG_SUN4I_INTC) += irq-sun4i.o +obj-$(CONFIG_SUN6I_R_INTC) += irq-sun6i-r.o +obj-$(CONFIG_SUNXI_NMI_INTC) += irq-sunxi-nmi.o obj-$(CONFIG_ARCH_SPEAR3XX) += spear-shirq.o obj-$(CONFIG_ARM_GIC) += irq-gic.o irq-gic-common.o obj-$(CONFIG_ARM_GIC_PM) += irq-gic-pm.o diff --git a/drivers/irqchip/irq-armada-370-xp.c b/drivers/irqchip/irq-armada-370-xp.c index 5b8d571c041d..ee18eb3e72b7 100644 --- a/drivers/irqchip/irq-armada-370-xp.c +++ b/drivers/irqchip/irq-armada-370-xp.c @@ -209,15 +209,29 @@ static struct msi_domain_info armada_370_xp_msi_domain_info = { static void armada_370_xp_compose_msi_msg(struct irq_data *data, struct msi_msg *msg) { + unsigned int cpu = cpumask_first(irq_data_get_effective_affinity_mask(data)); + msg->address_lo = lower_32_bits(msi_doorbell_addr); msg->address_hi = upper_32_bits(msi_doorbell_addr); - msg->data = 0xf00 | (data->hwirq + PCI_MSI_DOORBELL_START); + msg->data = BIT(cpu + 8) | (data->hwirq + PCI_MSI_DOORBELL_START); } static int armada_370_xp_msi_set_affinity(struct irq_data *irq_data, const struct cpumask *mask, bool force) { - return -EINVAL; + unsigned int cpu; + + if (!force) + cpu = cpumask_any_and(mask, cpu_online_mask); + else + cpu = cpumask_first(mask); + + if (cpu >= nr_cpu_ids) + return -EINVAL; + + irq_data_update_effective_affinity(irq_data, cpumask_of(cpu)); + + return IRQ_SET_MASK_OK; } static struct irq_chip armada_370_xp_msi_bottom_irq_chip = { @@ -264,11 +278,21 @@ static const struct irq_domain_ops armada_370_xp_msi_domain_ops = { .free = armada_370_xp_msi_free, }; -static int armada_370_xp_msi_init(struct device_node *node, - phys_addr_t main_int_phys_base) +static void armada_370_xp_msi_reenable_percpu(void) { u32 reg; + /* Enable MSI doorbell mask and combined cpu local interrupt */ + reg = readl(per_cpu_int_base + ARMADA_370_XP_IN_DRBEL_MSK_OFFS) + | PCI_MSI_DOORBELL_MASK; + writel(reg, per_cpu_int_base + ARMADA_370_XP_IN_DRBEL_MSK_OFFS); + /* Unmask local doorbell interrupt */ + writel(1, per_cpu_int_base + ARMADA_370_XP_INT_CLEAR_MASK_OFFS); +} + +static int armada_370_xp_msi_init(struct device_node *node, + phys_addr_t main_int_phys_base) +{ msi_doorbell_addr = main_int_phys_base + ARMADA_370_XP_SW_TRIG_INT_OFFS; @@ -287,18 +311,13 @@ static int armada_370_xp_msi_init(struct device_node *node, return -ENOMEM; } - reg = readl(per_cpu_int_base + ARMADA_370_XP_IN_DRBEL_MSK_OFFS) - | PCI_MSI_DOORBELL_MASK; - - writel(reg, per_cpu_int_base + - ARMADA_370_XP_IN_DRBEL_MSK_OFFS); - - /* Unmask IPI interrupt */ - writel(1, per_cpu_int_base + ARMADA_370_XP_INT_CLEAR_MASK_OFFS); + armada_370_xp_msi_reenable_percpu(); return 0; } #else +static void armada_370_xp_msi_reenable_percpu(void) {} + static inline int armada_370_xp_msi_init(struct device_node *node, phys_addr_t main_int_phys_base) { @@ -308,7 +327,16 @@ static inline int armada_370_xp_msi_init(struct device_node *node, static void armada_xp_mpic_perf_init(void) { - unsigned long cpuid = cpu_logical_map(smp_processor_id()); + unsigned long cpuid; + + /* + * This Performance Counter Overflow interrupt is specific for + * Armada 370 and XP. It is not available on Armada 375, 38x and 39x. + */ + if (!of_machine_is_compatible("marvell,armada-370-xp")) + return; + + cpuid = cpu_logical_map(smp_processor_id()); /* Enable Performance Counter Overflow interrupts */ writel(ARMADA_370_XP_INT_CAUSE_PERF(cpuid), @@ -501,6 +529,8 @@ static void armada_xp_mpic_reenable_percpu(void) } ipi_resume(); + + armada_370_xp_msi_reenable_percpu(); } static int armada_xp_mpic_starting_cpu(unsigned int cpu) diff --git a/drivers/irqchip/irq-aspeed-i2c-ic.c b/drivers/irqchip/irq-aspeed-i2c-ic.c index a47db16ff960..9c9fc3e2967e 100644 --- a/drivers/irqchip/irq-aspeed-i2c-ic.c +++ b/drivers/irqchip/irq-aspeed-i2c-ic.c @@ -77,8 +77,8 @@ static int __init aspeed_i2c_ic_of_init(struct device_node *node, } i2c_ic->parent_irq = irq_of_parse_and_map(node, 0); - if (i2c_ic->parent_irq < 0) { - ret = i2c_ic->parent_irq; + if (!i2c_ic->parent_irq) { + ret = -EINVAL; goto err_iounmap; } diff --git a/drivers/irqchip/irq-aspeed-scu-ic.c b/drivers/irqchip/irq-aspeed-scu-ic.c index 18b77c3e6db4..279e92cf0b16 100644 --- a/drivers/irqchip/irq-aspeed-scu-ic.c +++ b/drivers/irqchip/irq-aspeed-scu-ic.c @@ -157,8 +157,8 @@ static int aspeed_scu_ic_of_init_common(struct aspeed_scu_ic *scu_ic, } irq = irq_of_parse_and_map(node, 0); - if (irq < 0) { - rc = irq; + if (!irq) { + rc = -EINVAL; goto err; } diff --git a/drivers/irqchip/irq-bcm6345-l1.c b/drivers/irqchip/irq-bcm6345-l1.c index fd079215c17f..142a7431745f 100644 --- a/drivers/irqchip/irq-bcm6345-l1.c +++ b/drivers/irqchip/irq-bcm6345-l1.c @@ -315,7 +315,7 @@ static int __init bcm6345_l1_of_init(struct device_node *dn, cpumask_set_cpu(idx, &intc->cpumask); } - if (!cpumask_weight(&intc->cpumask)) { + if (cpumask_empty(&intc->cpumask)) { ret = -ENODEV; goto out_free; } diff --git a/drivers/irqchip/irq-csky-apb-intc.c b/drivers/irqchip/irq-csky-apb-intc.c index d36f536506ba..42d8a2438ebc 100644 --- a/drivers/irqchip/irq-csky-apb-intc.c +++ b/drivers/irqchip/irq-csky-apb-intc.c @@ -136,11 +136,11 @@ static inline bool handle_irq_perbit(struct pt_regs *regs, u32 hwirq, u32 irq_base) { if (hwirq == 0) - return 0; + return false; generic_handle_domain_irq(root_domain, irq_base + __fls(hwirq)); - return 1; + return true; } /* gx6605s 64 irqs interrupt controller */ diff --git a/drivers/irqchip/irq-gic-v3-its.c b/drivers/irqchip/irq-gic-v3-its.c index a0fc764ec9dc..5ff09de6c48f 100644 --- a/drivers/irqchip/irq-gic-v3-its.c +++ b/drivers/irqchip/irq-gic-v3-its.c @@ -1624,7 +1624,7 @@ static int its_select_cpu(struct irq_data *d, cpu = cpumask_pick_least_loaded(d, tmpmask); } else { - cpumask_and(tmpmask, irq_data_get_affinity_mask(d), cpu_online_mask); + cpumask_copy(tmpmask, aff_mask); /* If we cannot cross sockets, limit the search to that node */ if ((its_dev->its->flags & ITS_FLAGS_WORKAROUND_CAVIUM_23144) && diff --git a/drivers/irqchip/irq-gic-v3.c b/drivers/irqchip/irq-gic-v3.c index b252d5534547..2be8dea6b6b0 100644 --- a/drivers/irqchip/irq-gic-v3.c +++ b/drivers/irqchip/irq-gic-v3.c @@ -352,28 +352,27 @@ static int gic_peek_irq(struct irq_data *d, u32 offset) static void gic_poke_irq(struct irq_data *d, u32 offset) { - void (*rwp_wait)(void); void __iomem *base; u32 index, mask; offset = convert_offset_index(d, offset, &index); mask = 1 << (index % 32); - if (gic_irq_in_rdist(d)) { + if (gic_irq_in_rdist(d)) base = gic_data_rdist_sgi_base(); - rwp_wait = gic_redist_wait_for_rwp; - } else { + else base = gic_data.dist_base; - rwp_wait = gic_dist_wait_for_rwp; - } writel_relaxed(mask, base + offset + (index / 32) * 4); - rwp_wait(); } static void gic_mask_irq(struct irq_data *d) { gic_poke_irq(d, GICD_ICENABLER); + if (gic_irq_in_rdist(d)) + gic_redist_wait_for_rwp(); + else + gic_dist_wait_for_rwp(); } static void gic_eoimode1_mask_irq(struct irq_data *d) @@ -420,7 +419,11 @@ static int gic_irq_set_irqchip_state(struct irq_data *d, break; case IRQCHIP_STATE_MASKED: - reg = val ? GICD_ICENABLER : GICD_ISENABLER; + if (val) { + gic_mask_irq(d); + return 0; + } + reg = GICD_ISENABLER; break; default: @@ -556,7 +559,8 @@ static void gic_irq_nmi_teardown(struct irq_data *d) static void gic_eoi_irq(struct irq_data *d) { - gic_write_eoir(gic_irq(d)); + write_gicreg(gic_irq(d), ICC_EOIR1_EL1); + isb(); } static void gic_eoimode1_eoi_irq(struct irq_data *d) @@ -574,7 +578,6 @@ static int gic_set_type(struct irq_data *d, unsigned int type) { enum gic_intid_range range; unsigned int irq = gic_irq(d); - void (*rwp_wait)(void); void __iomem *base; u32 offset, index; int ret; @@ -590,17 +593,14 @@ static int gic_set_type(struct irq_data *d, unsigned int type) type != IRQ_TYPE_LEVEL_HIGH && type != IRQ_TYPE_EDGE_RISING) return -EINVAL; - if (gic_irq_in_rdist(d)) { + if (gic_irq_in_rdist(d)) base = gic_data_rdist_sgi_base(); - rwp_wait = gic_redist_wait_for_rwp; - } else { + else base = gic_data.dist_base; - rwp_wait = gic_dist_wait_for_rwp; - } offset = convert_offset_index(d, GICD_ICFGR, &index); - ret = gic_configure_irq(index, type, base + offset, rwp_wait); + ret = gic_configure_irq(index, type, base + offset, NULL); if (ret && (range == PPI_RANGE || range == EPPI_RANGE)) { /* Misconfigured PPIs are usually not fatal */ pr_warn("GIC: PPI INTID%d is secure or misconfigured\n", irq); @@ -640,82 +640,101 @@ static void gic_deactivate_unhandled(u32 irqnr) if (irqnr < 8192) gic_write_dir(irqnr); } else { - gic_write_eoir(irqnr); + write_gicreg(irqnr, ICC_EOIR1_EL1); + isb(); } } -static inline void gic_handle_nmi(u32 irqnr, struct pt_regs *regs) +/* + * Follow a read of the IAR with any HW maintenance that needs to happen prior + * to invoking the relevant IRQ handler. We must do two things: + * + * (1) Ensure instruction ordering between a read of IAR and subsequent + * instructions in the IRQ handler using an ISB. + * + * It is possible for the IAR to report an IRQ which was signalled *after* + * the CPU took an IRQ exception as multiple interrupts can race to be + * recognized by the GIC, earlier interrupts could be withdrawn, and/or + * later interrupts could be prioritized by the GIC. + * + * For devices which are tightly coupled to the CPU, such as PMUs, a + * context synchronization event is necessary to ensure that system + * register state is not stale, as these may have been indirectly written + * *after* exception entry. + * + * (2) Deactivate the interrupt when EOI mode 1 is in use. + */ +static inline void gic_complete_ack(u32 irqnr) { - bool irqs_enabled = interrupts_enabled(regs); - int err; - - if (irqs_enabled) - nmi_enter(); - if (static_branch_likely(&supports_deactivate_key)) - gic_write_eoir(irqnr); - /* - * Leave the PSR.I bit set to prevent other NMIs to be - * received while handling this one. - * PSR.I will be restored when we ERET to the - * interrupted context. - */ - err = generic_handle_domain_nmi(gic_data.domain, irqnr); - if (err) - gic_deactivate_unhandled(irqnr); + write_gicreg(irqnr, ICC_EOIR1_EL1); - if (irqs_enabled) - nmi_exit(); + isb(); } -static u32 do_read_iar(struct pt_regs *regs) +static bool gic_rpr_is_nmi_prio(void) { - u32 iar; + if (!gic_supports_nmi()) + return false; - if (gic_supports_nmi() && unlikely(!interrupts_enabled(regs))) { - u64 pmr; + return unlikely(gic_read_rpr() == GICD_INT_RPR_PRI(GICD_INT_NMI_PRI)); +} - /* - * We were in a context with IRQs disabled. However, the - * entry code has set PMR to a value that allows any - * interrupt to be acknowledged, and not just NMIs. This can - * lead to surprising effects if the NMI has been retired in - * the meantime, and that there is an IRQ pending. The IRQ - * would then be taken in NMI context, something that nobody - * wants to debug twice. - * - * Until we sort this, drop PMR again to a level that will - * actually only allow NMIs before reading IAR, and then - * restore it to what it was. - */ - pmr = gic_read_pmr(); - gic_pmr_mask_irqs(); - isb(); +static bool gic_irqnr_is_special(u32 irqnr) +{ + return irqnr >= 1020 && irqnr <= 1023; +} - iar = gic_read_iar(); +static void __gic_handle_irq(u32 irqnr, struct pt_regs *regs) +{ + if (gic_irqnr_is_special(irqnr)) + return; - gic_write_pmr(pmr); - } else { - iar = gic_read_iar(); + gic_complete_ack(irqnr); + + if (generic_handle_domain_irq(gic_data.domain, irqnr)) { + WARN_ONCE(true, "Unexpected interrupt (irqnr %u)\n", irqnr); + gic_deactivate_unhandled(irqnr); } +} + +static void __gic_handle_nmi(u32 irqnr, struct pt_regs *regs) +{ + if (gic_irqnr_is_special(irqnr)) + return; + + gic_complete_ack(irqnr); - return iar; + if (generic_handle_domain_nmi(gic_data.domain, irqnr)) { + WARN_ONCE(true, "Unexpected pseudo-NMI (irqnr %u)\n", irqnr); + gic_deactivate_unhandled(irqnr); + } } -static asmlinkage void __exception_irq_entry gic_handle_irq(struct pt_regs *regs) +/* + * An exception has been taken from a context with IRQs enabled, and this could + * be an IRQ or an NMI. + * + * The entry code called us with DAIF.IF set to keep NMIs masked. We must clear + * DAIF.IF (and update ICC_PMR_EL1 to mask regular IRQs) prior to returning, + * after handling any NMI but before handling any IRQ. + * + * The entry code has performed IRQ entry, and if an NMI is detected we must + * perform NMI entry/exit around invoking the handler. + */ +static void __gic_handle_irq_from_irqson(struct pt_regs *regs) { + bool is_nmi; u32 irqnr; - irqnr = do_read_iar(regs); + irqnr = gic_read_iar(); - /* Check for special IDs first */ - if ((irqnr >= 1020 && irqnr <= 1023)) - return; + is_nmi = gic_rpr_is_nmi_prio(); - if (gic_supports_nmi() && - unlikely(gic_read_rpr() == GICD_INT_RPR_PRI(GICD_INT_NMI_PRI))) { - gic_handle_nmi(irqnr, regs); - return; + if (is_nmi) { + nmi_enter(); + __gic_handle_nmi(irqnr, regs); + nmi_exit(); } if (gic_prio_masking_enabled()) { @@ -723,15 +742,52 @@ static asmlinkage void __exception_irq_entry gic_handle_irq(struct pt_regs *regs gic_arch_enable_irqs(); } - if (static_branch_likely(&supports_deactivate_key)) - gic_write_eoir(irqnr); - else - isb(); + if (!is_nmi) + __gic_handle_irq(irqnr, regs); +} - if (generic_handle_domain_irq(gic_data.domain, irqnr)) { - WARN_ONCE(true, "Unexpected interrupt received!\n"); - gic_deactivate_unhandled(irqnr); - } +/* + * An exception has been taken from a context with IRQs disabled, which can only + * be an NMI. + * + * The entry code called us with DAIF.IF set to keep NMIs masked. We must leave + * DAIF.IF (and ICC_PMR_EL1) unchanged. + * + * The entry code has performed NMI entry. + */ +static void __gic_handle_irq_from_irqsoff(struct pt_regs *regs) +{ + u64 pmr; + u32 irqnr; + + /* + * We were in a context with IRQs disabled. However, the + * entry code has set PMR to a value that allows any + * interrupt to be acknowledged, and not just NMIs. This can + * lead to surprising effects if the NMI has been retired in + * the meantime, and that there is an IRQ pending. The IRQ + * would then be taken in NMI context, something that nobody + * wants to debug twice. + * + * Until we sort this, drop PMR again to a level that will + * actually only allow NMIs before reading IAR, and then + * restore it to what it was. + */ + pmr = gic_read_pmr(); + gic_pmr_mask_irqs(); + isb(); + irqnr = gic_read_iar(); + gic_write_pmr(pmr); + + __gic_handle_nmi(irqnr, regs); +} + +static asmlinkage void __exception_irq_entry gic_handle_irq(struct pt_regs *regs) +{ + if (unlikely(gic_supports_nmi() && !interrupts_enabled(regs))) + __gic_handle_irq_from_irqsoff(regs); + else + __gic_handle_irq_from_irqson(regs); } static u32 gic_get_pribits(void) @@ -807,8 +863,8 @@ static void __init gic_dist_init(void) for (i = 0; i < GIC_ESPI_NR; i += 4) writel_relaxed(GICD_INT_DEF_PRI_X4, base + GICD_IPRIORITYRnE + i); - /* Now do the common stuff, and wait for the distributor to drain */ - gic_dist_config(base, GIC_LINE_NR, gic_dist_wait_for_rwp); + /* Now do the common stuff */ + gic_dist_config(base, GIC_LINE_NR, NULL); val = GICD_CTLR_ARE_NS | GICD_CTLR_ENABLE_G1A | GICD_CTLR_ENABLE_G1; if (gic_data.rdists.gicd_typer2 & GICD_TYPER2_nASSGIcap) { @@ -816,8 +872,9 @@ static void __init gic_dist_init(void) val |= GICD_CTLR_nASSGIreq; } - /* Enable distributor with ARE, Group1 */ + /* Enable distributor with ARE, Group1, and wait for it to drain */ writel_relaxed(val, base + GICD_CTLR); + gic_dist_wait_for_rwp(); /* * Set all global interrupts to the boot CPU only. ARE must be @@ -919,6 +976,7 @@ static int __gic_update_rdist_properties(struct redist_region *region, void __iomem *ptr) { u64 typer = gic_read_typer(ptr + GICR_TYPER); + u32 ctlr = readl_relaxed(ptr + GICR_CTLR); /* Boot-time cleanip */ if ((typer & GICR_TYPER_VLPIS) && (typer & GICR_TYPER_RVPEID)) { @@ -938,9 +996,18 @@ static int __gic_update_rdist_properties(struct redist_region *region, gic_data.rdists.has_vlpis &= !!(typer & GICR_TYPER_VLPIS); - /* RVPEID implies some form of DirectLPI, no matter what the doc says... :-/ */ + /* + * TYPER.RVPEID implies some form of DirectLPI, no matter what the + * doc says... :-/ And CTLR.IR implies another subset of DirectLPI + * that the ITS driver can make use of for LPIs (and not VLPIs). + * + * These are 3 different ways to express the same thing, depending + * on the revision of the architecture and its relaxations over + * time. Just group them under the 'direct_lpi' banner. + */ gic_data.rdists.has_rvpeid &= !!(typer & GICR_TYPER_RVPEID); gic_data.rdists.has_direct_lpi &= (!!(typer & GICR_TYPER_DirectLPIS) | + !!(ctlr & GICR_CTLR_IR) | gic_data.rdists.has_rvpeid); gic_data.rdists.has_vpend_valid_dirty &= !!(typer & GICR_TYPER_DIRTY); @@ -962,7 +1029,11 @@ static void gic_update_rdist_properties(void) gic_iterate_rdists(__gic_update_rdist_properties); if (WARN_ON(gic_data.ppi_nr == UINT_MAX)) gic_data.ppi_nr = 0; - pr_info("%d PPIs implemented\n", gic_data.ppi_nr); + pr_info("GICv3 features: %d PPIs%s%s\n", + gic_data.ppi_nr, + gic_data.has_rss ? ", RSS" : "", + gic_data.rdists.has_direct_lpi ? ", DirectLPI" : ""); + if (gic_data.rdists.has_vlpis) pr_info("GICv4 features: %s%s%s\n", gic_data.rdists.has_direct_lpi ? "DirectLPI " : "", @@ -1284,8 +1355,6 @@ static int gic_set_affinity(struct irq_data *d, const struct cpumask *mask_val, */ if (enabled) gic_unmask_irq(d); - else - gic_dist_wait_for_rwp(); irq_data_update_effective_affinity(d, cpumask_of(cpu)); @@ -1803,8 +1872,6 @@ static int __init gic_init_bases(void __iomem *dist_base, irq_domain_update_bus_token(gic_data.domain, DOMAIN_BUS_WIRED); gic_data.has_rss = !!(typer & GICD_TYPER_RSS); - pr_info("Distributor has %sRange Selector support\n", - gic_data.has_rss ? "" : "no "); if (typer & GICD_TYPER_MBIS) { err = mbi_init(handle, gic_data.domain); @@ -1980,10 +2047,10 @@ static int __init gic_of_init(struct device_node *node, struct device_node *pare u32 nr_redist_regions; int err, i; - dist_base = of_iomap(node, 0); - if (!dist_base) { + dist_base = of_io_request_and_map(node, 0, "GICD"); + if (IS_ERR(dist_base)) { pr_err("%pOF: unable to map gic dist registers\n", node); - return -ENXIO; + return PTR_ERR(dist_base); } err = gic_validate_dist_version(dist_base); @@ -2007,8 +2074,8 @@ static int __init gic_of_init(struct device_node *node, struct device_node *pare int ret; ret = of_address_to_resource(node, 1 + i, &res); - rdist_regs[i].redist_base = of_iomap(node, 1 + i); - if (ret || !rdist_regs[i].redist_base) { + rdist_regs[i].redist_base = of_io_request_and_map(node, 1 + i, "GICR"); + if (ret || IS_ERR(rdist_regs[i].redist_base)) { pr_err("%pOF: couldn't map region %d\n", node, i); err = -ENODEV; goto out_unmap_rdist; @@ -2034,7 +2101,7 @@ static int __init gic_of_init(struct device_node *node, struct device_node *pare out_unmap_rdist: for (i = 0; i < nr_redist_regions; i++) - if (rdist_regs[i].redist_base) + if (rdist_regs[i].redist_base && !IS_ERR(rdist_regs[i].redist_base)) iounmap(rdist_regs[i].redist_base); kfree(rdist_regs); out_unmap_dist: @@ -2081,6 +2148,7 @@ gic_acpi_parse_madt_redist(union acpi_subtable_headers *header, pr_err("Couldn't map GICR region @%llx\n", redist->base_address); return -ENOMEM; } + request_mem_region(redist->base_address, redist->length, "GICR"); gic_acpi_register_redist(redist->base_address, redist_base); return 0; @@ -2103,6 +2171,7 @@ gic_acpi_parse_madt_gicc(union acpi_subtable_headers *header, redist_base = ioremap(gicc->gicr_base_address, size); if (!redist_base) return -ENOMEM; + request_mem_region(gicc->gicr_base_address, size, "GICR"); gic_acpi_register_redist(gicc->gicr_base_address, redist_base); return 0; @@ -2304,6 +2373,7 @@ gic_acpi_init(union acpi_subtable_headers *header, const unsigned long end) pr_err("Unable to map GICD registers\n"); return -ENOMEM; } + request_mem_region(dist->base_address, ACPI_GICV3_DIST_MEM_SIZE, "GICD"); err = gic_validate_dist_version(acpi_data.dist_base); if (err) { diff --git a/drivers/irqchip/irq-gic.c b/drivers/irqchip/irq-gic.c index 09c710ecc387..820404cb56bc 100644 --- a/drivers/irqchip/irq-gic.c +++ b/drivers/irqchip/irq-gic.c @@ -1115,7 +1115,8 @@ static int gic_irq_domain_translate(struct irq_domain *d, *type = fwspec->param[2] & IRQ_TYPE_SENSE_MASK; /* Make it clear that broken DTs are... broken */ - WARN_ON(*type == IRQ_TYPE_NONE); + WARN(*type == IRQ_TYPE_NONE, + "HW irq %ld has invalid type\n", *hwirq); return 0; } @@ -1132,7 +1133,8 @@ static int gic_irq_domain_translate(struct irq_domain *d, *hwirq = fwspec->param[0]; *type = fwspec->param[1]; - WARN_ON(*type == IRQ_TYPE_NONE); + WARN(*type == IRQ_TYPE_NONE, + "HW irq %ld has invalid type\n", *hwirq); return 0; } diff --git a/drivers/irqchip/irq-imx-irqsteer.c b/drivers/irqchip/irq-imx-irqsteer.c index 8d91a02593fc..96230a04ec23 100644 --- a/drivers/irqchip/irq-imx-irqsteer.c +++ b/drivers/irqchip/irq-imx-irqsteer.c @@ -12,6 +12,7 @@ #include <linux/kernel.h> #include <linux/of_irq.h> #include <linux/of_platform.h> +#include <linux/pm_runtime.h> #include <linux/spinlock.h> #define CTRL_STRIDE_OFF(_t, _r) (_t * 4 * _r) @@ -70,7 +71,7 @@ static void imx_irqsteer_irq_mask(struct irq_data *d) raw_spin_unlock_irqrestore(&data->lock, flags); } -static struct irq_chip imx_irqsteer_irq_chip = { +static const struct irq_chip imx_irqsteer_irq_chip = { .name = "irqsteer", .irq_mask = imx_irqsteer_irq_mask, .irq_unmask = imx_irqsteer_irq_unmask, @@ -175,7 +176,7 @@ static int imx_irqsteer_probe(struct platform_device *pdev) data->irq_count = DIV_ROUND_UP(irqs_num, 64); data->reg_num = irqs_num / 32; - if (IS_ENABLED(CONFIG_PM_SLEEP)) { + if (IS_ENABLED(CONFIG_PM)) { data->saved_reg = devm_kzalloc(&pdev->dev, sizeof(u32) * data->reg_num, GFP_KERNEL); @@ -199,6 +200,7 @@ static int imx_irqsteer_probe(struct platform_device *pdev) ret = -ENOMEM; goto out; } + irq_domain_set_pm_device(data->domain, &pdev->dev); if (!data->irq_count || data->irq_count > CHAN_MAX_OUTPUT_INT) { ret = -EINVAL; @@ -219,6 +221,9 @@ static int imx_irqsteer_probe(struct platform_device *pdev) platform_set_drvdata(pdev, data); + pm_runtime_set_active(&pdev->dev); + pm_runtime_enable(&pdev->dev); + return 0; out: clk_disable_unprepare(data->ipg_clk); @@ -241,7 +246,7 @@ static int imx_irqsteer_remove(struct platform_device *pdev) return 0; } -#ifdef CONFIG_PM_SLEEP +#ifdef CONFIG_PM static void imx_irqsteer_save_regs(struct irqsteer_data *data) { int i; @@ -288,7 +293,10 @@ static int imx_irqsteer_resume(struct device *dev) #endif static const struct dev_pm_ops imx_irqsteer_pm_ops = { - SET_NOIRQ_SYSTEM_SLEEP_PM_OPS(imx_irqsteer_suspend, imx_irqsteer_resume) + SET_NOIRQ_SYSTEM_SLEEP_PM_OPS(pm_runtime_force_suspend, + pm_runtime_force_resume) + SET_RUNTIME_PM_OPS(imx_irqsteer_suspend, + imx_irqsteer_resume, NULL) }; static const struct of_device_id imx_irqsteer_dt_ids[] = { diff --git a/drivers/irqchip/irq-sni-exiu.c b/drivers/irqchip/irq-sni-exiu.c index abd011fcecf4..c7db617e1a2f 100644 --- a/drivers/irqchip/irq-sni-exiu.c +++ b/drivers/irqchip/irq-sni-exiu.c @@ -37,11 +37,26 @@ struct exiu_irq_data { u32 spi_base; }; -static void exiu_irq_eoi(struct irq_data *d) +static void exiu_irq_ack(struct irq_data *d) { struct exiu_irq_data *data = irq_data_get_irq_chip_data(d); writel(BIT(d->hwirq), data->base + EIREQCLR); +} + +static void exiu_irq_eoi(struct irq_data *d) +{ + struct exiu_irq_data *data = irq_data_get_irq_chip_data(d); + + /* + * Level triggered interrupts are latched and must be cleared during + * EOI or the interrupt will be jammed on. Of course if a level + * triggered interrupt is still asserted then the write will not clear + * the interrupt. + */ + if (irqd_is_level_type(d)) + writel(BIT(d->hwirq), data->base + EIREQCLR); + irq_chip_eoi_parent(d); } @@ -91,10 +106,13 @@ static int exiu_irq_set_type(struct irq_data *d, unsigned int type) writel_relaxed(val, data->base + EILVL); val = readl_relaxed(data->base + EIEDG); - if (type == IRQ_TYPE_LEVEL_LOW || type == IRQ_TYPE_LEVEL_HIGH) + if (type == IRQ_TYPE_LEVEL_LOW || type == IRQ_TYPE_LEVEL_HIGH) { val &= ~BIT(d->hwirq); - else + irq_set_handler_locked(d, handle_fasteoi_irq); + } else { val |= BIT(d->hwirq); + irq_set_handler_locked(d, handle_fasteoi_ack_irq); + } writel_relaxed(val, data->base + EIEDG); writel_relaxed(BIT(d->hwirq), data->base + EIREQCLR); @@ -104,6 +122,7 @@ static int exiu_irq_set_type(struct irq_data *d, unsigned int type) static struct irq_chip exiu_irq_chip = { .name = "EXIU", + .irq_ack = exiu_irq_ack, .irq_eoi = exiu_irq_eoi, .irq_enable = exiu_irq_enable, .irq_mask = exiu_irq_mask, diff --git a/drivers/irqchip/irq-sun6i-r.c b/drivers/irqchip/irq-sun6i-r.c index 4cd3e533740b..a01e44049415 100644 --- a/drivers/irqchip/irq-sun6i-r.c +++ b/drivers/irqchip/irq-sun6i-r.c @@ -249,11 +249,13 @@ static int sun6i_r_intc_domain_alloc(struct irq_domain *domain, for (i = 0; i < nr_irqs; ++i, ++hwirq, ++virq) { if (hwirq == nmi_hwirq) { irq_domain_set_hwirq_and_chip(domain, virq, hwirq, - &sun6i_r_intc_nmi_chip, 0); + &sun6i_r_intc_nmi_chip, + NULL); irq_set_handler(virq, handle_fasteoi_ack_irq); } else { irq_domain_set_hwirq_and_chip(domain, virq, hwirq, - &sun6i_r_intc_wakeup_chip, 0); + &sun6i_r_intc_wakeup_chip, + NULL); } } diff --git a/drivers/irqchip/irq-xtensa-mx.c b/drivers/irqchip/irq-xtensa-mx.c index 27933338f7b3..8c581c985aa7 100644 --- a/drivers/irqchip/irq-xtensa-mx.c +++ b/drivers/irqchip/irq-xtensa-mx.c @@ -151,14 +151,25 @@ static struct irq_chip xtensa_mx_irq_chip = { .irq_set_affinity = xtensa_mx_irq_set_affinity, }; +static void __init xtensa_mx_init_common(struct irq_domain *root_domain) +{ + unsigned int i; + + irq_set_default_host(root_domain); + secondary_init_irq(); + + /* Initialize default IRQ routing to CPU 0 */ + for (i = 0; i < XCHAL_NUM_EXTINTERRUPTS; ++i) + set_er(1, MIROUT(i)); +} + int __init xtensa_mx_init_legacy(struct device_node *interrupt_parent) { struct irq_domain *root_domain = irq_domain_add_legacy(NULL, NR_IRQS - 1, 1, 0, &xtensa_mx_irq_domain_ops, &xtensa_mx_irq_chip); - irq_set_default_host(root_domain); - secondary_init_irq(); + xtensa_mx_init_common(root_domain); return 0; } @@ -168,8 +179,7 @@ static int __init xtensa_mx_init(struct device_node *np, struct irq_domain *root_domain = irq_domain_add_linear(np, NR_IRQS, &xtensa_mx_irq_domain_ops, &xtensa_mx_irq_chip); - irq_set_default_host(root_domain); - secondary_init_irq(); + xtensa_mx_init_common(root_domain); return 0; } IRQCHIP_DECLARE(xtensa_mx_irq_chip, "cdns,xtensa-mx", xtensa_mx_init); diff --git a/drivers/md/bcache/alloc.c b/drivers/md/bcache/alloc.c index 097577ae3c47..ce13c272c387 100644 --- a/drivers/md/bcache/alloc.c +++ b/drivers/md/bcache/alloc.c @@ -336,7 +336,7 @@ static int bch_allocator_thread(void *arg) mutex_unlock(&ca->set->bucket_lock); blkdev_issue_discard(ca->bdev, bucket_to_sector(ca->set, bucket), - ca->sb.bucket_size, GFP_KERNEL, 0); + ca->sb.bucket_size, GFP_KERNEL); mutex_lock(&ca->set->bucket_lock); } diff --git a/drivers/md/bcache/debug.c b/drivers/md/bcache/debug.c index 6230dfdd9286..7510d1c983a5 100644 --- a/drivers/md/bcache/debug.c +++ b/drivers/md/bcache/debug.c @@ -107,15 +107,16 @@ void bch_btree_verify(struct btree *b) void bch_data_verify(struct cached_dev *dc, struct bio *bio) { + unsigned int nr_segs = bio_segments(bio); struct bio *check; struct bio_vec bv, cbv; struct bvec_iter iter, citer = { 0 }; - check = bio_kmalloc(GFP_NOIO, bio_segments(bio)); + check = bio_kmalloc(nr_segs, GFP_NOIO); if (!check) return; - bio_set_dev(check, bio->bi_bdev); - check->bi_opf = REQ_OP_READ; + bio_init(check, bio->bi_bdev, check->bi_inline_vecs, nr_segs, + REQ_OP_READ); check->bi_iter.bi_sector = bio->bi_iter.bi_sector; check->bi_iter.bi_size = bio->bi_iter.bi_size; @@ -146,7 +147,8 @@ void bch_data_verify(struct cached_dev *dc, struct bio *bio) bio_free_pages(check); out_put: - bio_put(check); + bio_uninit(check); + kfree(check); } #endif diff --git a/drivers/md/bcache/request.c b/drivers/md/bcache/request.c index 320fcdfef48e..9c5dde73da88 100644 --- a/drivers/md/bcache/request.c +++ b/drivers/md/bcache/request.c @@ -1005,7 +1005,7 @@ static void cached_dev_write(struct cached_dev *dc, struct search *s) bio_get(s->iop.bio); if (bio_op(bio) == REQ_OP_DISCARD && - !blk_queue_discard(bdev_get_queue(dc->bdev))) + !bdev_max_discard_sectors(dc->bdev)) goto insert_data; /* I/O request sent to backing device */ @@ -1115,7 +1115,7 @@ static void detached_dev_do_request(struct bcache_device *d, struct bio *bio, bio->bi_private = ddip; if ((bio_op(bio) == REQ_OP_DISCARD) && - !blk_queue_discard(bdev_get_queue(dc->bdev))) + !bdev_max_discard_sectors(dc->bdev)) bio->bi_end_io(bio); else submit_bio_noacct(bio); diff --git a/drivers/md/bcache/super.c b/drivers/md/bcache/super.c index bf3de149d3c9..2f49e31142f6 100644 --- a/drivers/md/bcache/super.c +++ b/drivers/md/bcache/super.c @@ -973,7 +973,6 @@ static int bcache_device_init(struct bcache_device *d, unsigned int block_size, blk_queue_flag_set(QUEUE_FLAG_NONROT, d->disk->queue); blk_queue_flag_clear(QUEUE_FLAG_ADD_RANDOM, d->disk->queue); - blk_queue_flag_set(QUEUE_FLAG_DISCARD, d->disk->queue); blk_queue_write_cache(q, true, true); @@ -2350,7 +2349,7 @@ static int register_cache(struct cache_sb *sb, struct cache_sb_disk *sb_disk, ca->bdev->bd_holder = ca; ca->sb_disk = sb_disk; - if (blk_queue_discard(bdev_get_queue(bdev))) + if (bdev_max_discard_sectors((bdev))) ca->discard = CACHE_DISCARD(&ca->sb); ret = cache_alloc(ca); diff --git a/drivers/md/bcache/sysfs.c b/drivers/md/bcache/sysfs.c index d1029d71ff3b..c6f677059214 100644 --- a/drivers/md/bcache/sysfs.c +++ b/drivers/md/bcache/sysfs.c @@ -1151,7 +1151,7 @@ STORE(__bch_cache) if (attr == &sysfs_discard) { bool v = strtoul_or_return(buf); - if (blk_queue_discard(bdev_get_queue(ca->bdev))) + if (bdev_max_discard_sectors(ca->bdev)) ca->discard = v; if (v != CACHE_DISCARD(&ca->sb)) { diff --git a/drivers/md/dm-bufio.c b/drivers/md/dm-bufio.c index e9cbc70d5a0e..5ffa1dcf84cf 100644 --- a/drivers/md/dm-bufio.c +++ b/drivers/md/dm-bufio.c @@ -611,7 +611,8 @@ static void bio_complete(struct bio *bio) { struct dm_buffer *b = bio->bi_private; blk_status_t status = bio->bi_status; - bio_put(bio); + bio_uninit(bio); + kfree(bio); b->end_io(b, status); } @@ -626,16 +627,14 @@ static void use_bio(struct dm_buffer *b, int rw, sector_t sector, if (unlikely(b->c->sectors_per_block_bits < PAGE_SHIFT - SECTOR_SHIFT)) vec_size += 2; - bio = bio_kmalloc(GFP_NOWAIT | __GFP_NORETRY | __GFP_NOWARN, vec_size); + bio = bio_kmalloc(vec_size, GFP_NOWAIT | __GFP_NORETRY | __GFP_NOWARN); if (!bio) { dmio: use_dmio(b, rw, sector, n_sectors, offset); return; } - + bio_init(bio, b->c->bdev, bio->bi_inline_vecs, vec_size, rw); bio->bi_iter.bi_sector = sector; - bio_set_dev(bio, b->c->bdev); - bio_set_op_attrs(bio, rw, 0); bio->bi_end_io = bio_complete; bio->bi_private = b; diff --git a/drivers/md/dm-cache-target.c b/drivers/md/dm-cache-target.c index 780a61bc6cc0..28c5de8eca4a 100644 --- a/drivers/md/dm-cache-target.c +++ b/drivers/md/dm-cache-target.c @@ -3329,13 +3329,6 @@ static int cache_iterate_devices(struct dm_target *ti, return r; } -static bool origin_dev_supports_discard(struct block_device *origin_bdev) -{ - struct request_queue *q = bdev_get_queue(origin_bdev); - - return blk_queue_discard(q); -} - /* * If discard_passdown was enabled verify that the origin device * supports discards. Disable discard_passdown if not. @@ -3349,7 +3342,7 @@ static void disable_passdown_if_not_supported(struct cache *cache) if (!cache->features.discard_passdown) return; - if (!origin_dev_supports_discard(origin_bdev)) + if (!bdev_max_discard_sectors(origin_bdev)) reason = "discard unsupported"; else if (origin_limits->max_discard_sectors < cache->sectors_per_block) diff --git a/drivers/md/dm-clone-target.c b/drivers/md/dm-clone-target.c index 128316a73d01..811b0a5379d0 100644 --- a/drivers/md/dm-clone-target.c +++ b/drivers/md/dm-clone-target.c @@ -2016,13 +2016,6 @@ static void clone_resume(struct dm_target *ti) do_waker(&clone->waker.work); } -static bool bdev_supports_discards(struct block_device *bdev) -{ - struct request_queue *q = bdev_get_queue(bdev); - - return (q && blk_queue_discard(q)); -} - /* * If discard_passdown was enabled verify that the destination device supports * discards. Disable discard_passdown if not. @@ -2036,7 +2029,7 @@ static void disable_passdown_if_not_supported(struct clone *clone) if (!test_bit(DM_CLONE_DISCARD_PASSDOWN, &clone->flags)) return; - if (!bdev_supports_discards(dest_dev)) + if (!bdev_max_discard_sectors(dest_dev)) reason = "discard unsupported"; else if (dest_limits->max_discard_sectors < clone->region_size) reason = "max discard sectors smaller than a region"; diff --git a/drivers/md/dm-io.c b/drivers/md/dm-io.c index 5762366333a2..e4b95eaeec8c 100644 --- a/drivers/md/dm-io.c +++ b/drivers/md/dm-io.c @@ -311,7 +311,7 @@ static void do_region(int op, int op_flags, unsigned region, * Reject unsupported discard and write same requests. */ if (op == REQ_OP_DISCARD) - special_cmd_max_sectors = q->limits.max_discard_sectors; + special_cmd_max_sectors = bdev_max_discard_sectors(where->bdev); else if (op == REQ_OP_WRITE_ZEROES) special_cmd_max_sectors = q->limits.max_write_zeroes_sectors; if ((op == REQ_OP_DISCARD || op == REQ_OP_WRITE_ZEROES) && diff --git a/drivers/md/dm-log-writes.c b/drivers/md/dm-log-writes.c index c9d036d6bb2e..e194226c89e5 100644 --- a/drivers/md/dm-log-writes.c +++ b/drivers/md/dm-log-writes.c @@ -866,9 +866,8 @@ static int log_writes_message(struct dm_target *ti, unsigned argc, char **argv, static void log_writes_io_hints(struct dm_target *ti, struct queue_limits *limits) { struct log_writes_c *lc = ti->private; - struct request_queue *q = bdev_get_queue(lc->dev->bdev); - if (!q || !blk_queue_discard(q)) { + if (!bdev_max_discard_sectors(lc->dev->bdev)) { lc->device_supports_discard = false; limits->discard_granularity = lc->sectorsize; limits->max_discard_sectors = (UINT_MAX >> SECTOR_SHIFT); diff --git a/drivers/md/dm-raid.c b/drivers/md/dm-raid.c index 2b26435a6946..9526ccbedafb 100644 --- a/drivers/md/dm-raid.c +++ b/drivers/md/dm-raid.c @@ -2963,13 +2963,8 @@ static void configure_discard_support(struct raid_set *rs) raid456 = rs_is_raid456(rs); for (i = 0; i < rs->raid_disks; i++) { - struct request_queue *q; - - if (!rs->dev[i].rdev.bdev) - continue; - - q = bdev_get_queue(rs->dev[i].rdev.bdev); - if (!q || !blk_queue_discard(q)) + if (!rs->dev[i].rdev.bdev || + !bdev_max_discard_sectors(rs->dev[i].rdev.bdev)) return; if (raid456) { diff --git a/drivers/md/dm-table.c b/drivers/md/dm-table.c index 03541cfc2317..e7d42f6335a2 100644 --- a/drivers/md/dm-table.c +++ b/drivers/md/dm-table.c @@ -1820,9 +1820,7 @@ static int device_dax_write_cache_enabled(struct dm_target *ti, static int device_is_rotational(struct dm_target *ti, struct dm_dev *dev, sector_t start, sector_t len, void *data) { - struct request_queue *q = bdev_get_queue(dev->bdev); - - return !blk_queue_nonrot(q); + return !bdev_nonrot(dev->bdev); } static int device_is_not_random(struct dm_target *ti, struct dm_dev *dev, @@ -1890,9 +1888,7 @@ static bool dm_table_supports_nowait(struct dm_table *t) static int device_not_discard_capable(struct dm_target *ti, struct dm_dev *dev, sector_t start, sector_t len, void *data) { - struct request_queue *q = bdev_get_queue(dev->bdev); - - return !blk_queue_discard(q); + return !bdev_max_discard_sectors(dev->bdev); } static bool dm_table_supports_discards(struct dm_table *t) @@ -1924,9 +1920,7 @@ static int device_not_secure_erase_capable(struct dm_target *ti, struct dm_dev *dev, sector_t start, sector_t len, void *data) { - struct request_queue *q = bdev_get_queue(dev->bdev); - - return !blk_queue_secure_erase(q); + return !bdev_max_secure_erase_sectors(dev->bdev); } static bool dm_table_supports_secure_erase(struct dm_table *t) @@ -1952,9 +1946,7 @@ static int device_requires_stable_pages(struct dm_target *ti, struct dm_dev *dev, sector_t start, sector_t len, void *data) { - struct request_queue *q = bdev_get_queue(dev->bdev); - - return blk_queue_stable_writes(q); + return bdev_stable_writes(dev->bdev); } int dm_table_set_restrictions(struct dm_table *t, struct request_queue *q, @@ -1974,18 +1966,15 @@ int dm_table_set_restrictions(struct dm_table *t, struct request_queue *q, blk_queue_flag_clear(QUEUE_FLAG_NOWAIT, q); if (!dm_table_supports_discards(t)) { - blk_queue_flag_clear(QUEUE_FLAG_DISCARD, q); - /* Must also clear discard limits... */ q->limits.max_discard_sectors = 0; q->limits.max_hw_discard_sectors = 0; q->limits.discard_granularity = 0; q->limits.discard_alignment = 0; q->limits.discard_misaligned = 0; - } else - blk_queue_flag_set(QUEUE_FLAG_DISCARD, q); + } - if (dm_table_supports_secure_erase(t)) - blk_queue_flag_set(QUEUE_FLAG_SECERASE, q); + if (!dm_table_supports_secure_erase(t)) + q->limits.max_secure_erase_sectors = 0; if (dm_table_supports_flush(t, (1UL << QUEUE_FLAG_WC))) { wc = true; diff --git a/drivers/md/dm-thin.c b/drivers/md/dm-thin.c index 4d25d0e27031..84c083f76673 100644 --- a/drivers/md/dm-thin.c +++ b/drivers/md/dm-thin.c @@ -398,8 +398,8 @@ static int issue_discard(struct discard_op *op, dm_block_t data_b, dm_block_t da sector_t s = block_to_sectors(tc->pool, data_b); sector_t len = block_to_sectors(tc->pool, data_e - data_b); - return __blkdev_issue_discard(tc->pool_dev->bdev, s, len, - GFP_NOWAIT, 0, &op->bio); + return __blkdev_issue_discard(tc->pool_dev->bdev, s, len, GFP_NOWAIT, + &op->bio); } static void end_discard(struct discard_op *op, int r) @@ -2802,13 +2802,6 @@ static void requeue_bios(struct pool *pool) /*---------------------------------------------------------------- * Binding of control targets to a pool object *--------------------------------------------------------------*/ -static bool data_dev_supports_discard(struct pool_c *pt) -{ - struct request_queue *q = bdev_get_queue(pt->data_dev->bdev); - - return blk_queue_discard(q); -} - static bool is_factor(sector_t block_size, uint32_t n) { return !sector_div(block_size, n); @@ -2828,7 +2821,7 @@ static void disable_passdown_if_not_supported(struct pool_c *pt) if (!pt->adjusted_pf.discard_passdown) return; - if (!data_dev_supports_discard(pt)) + if (!bdev_max_discard_sectors(pt->data_dev->bdev)) reason = "discard unsupported"; else if (data_limits->max_discard_sectors < pool->sectors_per_block) @@ -4057,8 +4050,6 @@ static void pool_io_hints(struct dm_target *ti, struct queue_limits *limits) /* * Must explicitly disallow stacking discard limits otherwise the * block layer will stack them if pool's data device has support. - * QUEUE_FLAG_DISCARD wouldn't be set but there is no way for the - * user to see that, so make sure to set all discard limits to 0. */ limits->discard_granularity = 0; return; diff --git a/drivers/md/dm-zoned-target.c b/drivers/md/dm-zoned-target.c index cac295cc8840..0ec5d8b9b1a4 100644 --- a/drivers/md/dm-zoned-target.c +++ b/drivers/md/dm-zoned-target.c @@ -1001,7 +1001,7 @@ static void dmz_io_hints(struct dm_target *ti, struct queue_limits *limits) blk_limits_io_min(limits, DMZ_BLOCK_SIZE); blk_limits_io_opt(limits, DMZ_BLOCK_SIZE); - limits->discard_alignment = DMZ_BLOCK_SIZE; + limits->discard_alignment = 0; limits->discard_granularity = DMZ_BLOCK_SIZE; limits->max_discard_sectors = chunk_sectors; limits->max_hw_discard_sectors = chunk_sectors; diff --git a/drivers/md/dm.c b/drivers/md/dm.c index 82957bd460e8..39081338ca61 100644 --- a/drivers/md/dm.c +++ b/drivers/md/dm.c @@ -955,7 +955,6 @@ void disable_discard(struct mapped_device *md) /* device doesn't really support DISCARD, disable it */ limits->max_discard_sectors = 0; - blk_queue_flag_clear(QUEUE_FLAG_DISCARD, md->queue); } void disable_write_zeroes(struct mapped_device *md) @@ -982,7 +981,7 @@ static void clone_endio(struct bio *bio) if (unlikely(error == BLK_STS_TARGET)) { if (bio_op(bio) == REQ_OP_DISCARD && - !q->limits.max_discard_sectors) + !bdev_max_discard_sectors(bio->bi_bdev)) disable_discard(md); else if (bio_op(bio) == REQ_OP_WRITE_ZEROES && !q->limits.max_write_zeroes_sectors) diff --git a/drivers/md/md-bitmap.c b/drivers/md/md-bitmap.c index bfd6026d7809..d87f674ab762 100644 --- a/drivers/md/md-bitmap.c +++ b/drivers/md/md-bitmap.c @@ -639,14 +639,6 @@ re_read: daemon_sleep = le32_to_cpu(sb->daemon_sleep) * HZ; write_behind = le32_to_cpu(sb->write_behind); sectors_reserved = le32_to_cpu(sb->sectors_reserved); - /* Setup nodes/clustername only if bitmap version is - * cluster-compatible - */ - if (sb->version == cpu_to_le32(BITMAP_MAJOR_CLUSTERED)) { - nodes = le32_to_cpu(sb->nodes); - strlcpy(bitmap->mddev->bitmap_info.cluster_name, - sb->cluster_name, 64); - } /* verify that the bitmap-specific fields are valid */ if (sb->magic != cpu_to_le32(BITMAP_MAGIC)) @@ -668,6 +660,16 @@ re_read: goto out; } + /* + * Setup nodes/clustername only if bitmap version is + * cluster-compatible + */ + if (sb->version == cpu_to_le32(BITMAP_MAJOR_CLUSTERED)) { + nodes = le32_to_cpu(sb->nodes); + strscpy(bitmap->mddev->bitmap_info.cluster_name, + sb->cluster_name, 64); + } + /* keep the array size field of the bitmap superblock up to date */ sb->sync_size = cpu_to_le64(bitmap->mddev->resync_max_sectors); @@ -695,14 +697,13 @@ re_read: if (le32_to_cpu(sb->version) == BITMAP_MAJOR_HOSTENDIAN) set_bit(BITMAP_HOSTENDIAN, &bitmap->flags); bitmap->events_cleared = le64_to_cpu(sb->events_cleared); - strlcpy(bitmap->mddev->bitmap_info.cluster_name, sb->cluster_name, 64); err = 0; out: kunmap_atomic(sb); - /* Assigning chunksize is required for "re_read" */ - bitmap->mddev->bitmap_info.chunksize = chunksize; if (err == 0 && nodes && (bitmap->cluster_slot < 0)) { + /* Assigning chunksize is required for "re_read" */ + bitmap->mddev->bitmap_info.chunksize = chunksize; err = md_setup_cluster(bitmap->mddev, nodes); if (err) { pr_warn("%s: Could not setup cluster service (%d)\n", @@ -713,18 +714,18 @@ out: goto re_read; } - out_no_sb: - if (test_bit(BITMAP_STALE, &bitmap->flags)) - bitmap->events_cleared = bitmap->mddev->events; - bitmap->mddev->bitmap_info.chunksize = chunksize; - bitmap->mddev->bitmap_info.daemon_sleep = daemon_sleep; - bitmap->mddev->bitmap_info.max_write_behind = write_behind; - bitmap->mddev->bitmap_info.nodes = nodes; - if (bitmap->mddev->bitmap_info.space == 0 || - bitmap->mddev->bitmap_info.space > sectors_reserved) - bitmap->mddev->bitmap_info.space = sectors_reserved; - if (err) { + if (err == 0) { + if (test_bit(BITMAP_STALE, &bitmap->flags)) + bitmap->events_cleared = bitmap->mddev->events; + bitmap->mddev->bitmap_info.chunksize = chunksize; + bitmap->mddev->bitmap_info.daemon_sleep = daemon_sleep; + bitmap->mddev->bitmap_info.max_write_behind = write_behind; + bitmap->mddev->bitmap_info.nodes = nodes; + if (bitmap->mddev->bitmap_info.space == 0 || + bitmap->mddev->bitmap_info.space > sectors_reserved) + bitmap->mddev->bitmap_info.space = sectors_reserved; + } else { md_bitmap_print_sb(bitmap); if (bitmap->cluster_slot < 0) md_cluster_stop(bitmap->mddev); diff --git a/drivers/md/md-cluster.c b/drivers/md/md-cluster.c index 1c8a06b77c85..37cbcce3cc66 100644 --- a/drivers/md/md-cluster.c +++ b/drivers/md/md-cluster.c @@ -201,7 +201,7 @@ static struct dlm_lock_resource *lockres_init(struct mddev *mddev, pr_err("md-cluster: Unable to allocate resource name for resource %s\n", name); goto out_err; } - strlcpy(res->name, name, namelen + 1); + strscpy(res->name, name, namelen + 1); if (with_lvb) { res->lksb.sb_lvbptr = kzalloc(LVB_SIZE, GFP_KERNEL); if (!res->lksb.sb_lvbptr) { diff --git a/drivers/md/md-linear.c b/drivers/md/md-linear.c index 0f55b079371b..138a3b25c5c8 100644 --- a/drivers/md/md-linear.c +++ b/drivers/md/md-linear.c @@ -64,7 +64,6 @@ static struct linear_conf *linear_conf(struct mddev *mddev, int raid_disks) struct linear_conf *conf; struct md_rdev *rdev; int i, cnt; - bool discard_supported = false; conf = kzalloc(struct_size(conf, disks, raid_disks), GFP_KERNEL); if (!conf) @@ -96,9 +95,6 @@ static struct linear_conf *linear_conf(struct mddev *mddev, int raid_disks) conf->array_sectors += rdev->sectors; cnt++; - - if (blk_queue_discard(bdev_get_queue(rdev->bdev))) - discard_supported = true; } if (cnt != raid_disks) { pr_warn("md/linear:%s: not enough drives present. Aborting!\n", @@ -106,11 +102,6 @@ static struct linear_conf *linear_conf(struct mddev *mddev, int raid_disks) goto out; } - if (!discard_supported) - blk_queue_flag_clear(QUEUE_FLAG_DISCARD, mddev->queue); - else - blk_queue_flag_set(QUEUE_FLAG_DISCARD, mddev->queue); - /* * Here we calculate the device offsets. */ @@ -252,7 +243,7 @@ static bool linear_make_request(struct mddev *mddev, struct bio *bio) start_sector + data_offset; if (unlikely((bio_op(bio) == REQ_OP_DISCARD) && - !blk_queue_discard(bio->bi_bdev->bd_disk->queue))) { + !bdev_max_discard_sectors(bio->bi_bdev))) { /* Just ignore it */ bio_endio(bio); } else { diff --git a/drivers/md/md.c b/drivers/md/md.c index 309b3af906ad..707e802d0082 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -2627,14 +2627,16 @@ static void sync_sbs(struct mddev *mddev, int nospares) static bool does_sb_need_changing(struct mddev *mddev) { - struct md_rdev *rdev; + struct md_rdev *rdev = NULL, *iter; struct mdp_superblock_1 *sb; int role; /* Find a good rdev */ - rdev_for_each(rdev, mddev) - if ((rdev->raid_disk >= 0) && !test_bit(Faulty, &rdev->flags)) + rdev_for_each(iter, mddev) + if ((iter->raid_disk >= 0) && !test_bit(Faulty, &iter->flags)) { + rdev = iter; break; + } /* No good device found. */ if (!rdev) @@ -2645,11 +2647,11 @@ static bool does_sb_need_changing(struct mddev *mddev) rdev_for_each(rdev, mddev) { role = le16_to_cpu(sb->dev_roles[rdev->desc_nr]); /* Device activated? */ - if (role == 0xffff && rdev->raid_disk >=0 && + if (role == MD_DISK_ROLE_SPARE && rdev->raid_disk >= 0 && !test_bit(Faulty, &rdev->flags)) return true; /* Device turned faulty? */ - if (test_bit(Faulty, &rdev->flags) && (role < 0xfffd)) + if (test_bit(Faulty, &rdev->flags) && (role < MD_DISK_ROLE_MAX)) return true; } @@ -2984,10 +2986,11 @@ state_store(struct md_rdev *rdev, const char *buf, size_t len) if (cmd_match(buf, "faulty") && rdev->mddev->pers) { md_error(rdev->mddev, rdev); - if (test_bit(Faulty, &rdev->flags)) - err = 0; - else + + if (test_bit(MD_BROKEN, &rdev->mddev->flags)) err = -EBUSY; + else + err = 0; } else if (cmd_match(buf, "remove")) { if (rdev->mddev->pers) { clear_bit(Blocked, &rdev->flags); @@ -4028,7 +4031,7 @@ level_store(struct mddev *mddev, const char *buf, size_t len) oldpriv = mddev->private; mddev->pers = pers; mddev->private = priv; - strlcpy(mddev->clevel, pers->name, sizeof(mddev->clevel)); + strscpy(mddev->clevel, pers->name, sizeof(mddev->clevel)); mddev->level = mddev->new_level; mddev->layout = mddev->new_layout; mddev->chunk_sectors = mddev->new_chunk_sectors; @@ -4353,10 +4356,9 @@ __ATTR_PREALLOC(resync_start, S_IRUGO|S_IWUSR, * like active, but no writes have been seen for a while (100msec). * * broken - * RAID0/LINEAR-only: same as clean, but array is missing a member. - * It's useful because RAID0/LINEAR mounted-arrays aren't stopped - * when a member is gone, so this state will at least alert the - * user that something is wrong. +* Array is failed. It's useful because mounted-arrays aren't stopped +* when array is failed, so this state will at least alert the user that +* something is wrong. */ enum array_state { clear, inactive, suspended, readonly, read_auto, clean, active, write_pending, active_idle, broken, bad_word}; @@ -5763,7 +5765,7 @@ static int add_named_array(const char *val, const struct kernel_param *kp) len--; if (len >= DISK_NAME_LEN) return -E2BIG; - strlcpy(buf, val, len+1); + strscpy(buf, val, len+1); if (strncmp(buf, "md_", 3) == 0) return md_alloc(0, buf); if (strncmp(buf, "md", 2) == 0 && @@ -5896,7 +5898,7 @@ int md_run(struct mddev *mddev) mddev->level = pers->level; mddev->new_level = pers->level; } - strlcpy(mddev->clevel, pers->name, sizeof(mddev->clevel)); + strscpy(mddev->clevel, pers->name, sizeof(mddev->clevel)); if (mddev->reshape_position != MaxSector && pers->start_reshape == NULL) { @@ -5991,8 +5993,7 @@ int md_run(struct mddev *mddev) bool nonrot = true; rdev_for_each(rdev, mddev) { - if (rdev->raid_disk >= 0 && - !blk_queue_nonrot(bdev_get_queue(rdev->bdev))) { + if (rdev->raid_disk >= 0 && !bdev_nonrot(rdev->bdev)) { nonrot = false; break; } @@ -7444,7 +7445,7 @@ static int set_disk_faulty(struct mddev *mddev, dev_t dev) err = -ENODEV; else { md_error(mddev, rdev); - if (!test_bit(Faulty, &rdev->flags)) + if (test_bit(MD_BROKEN, &mddev->flags)) err = -EBUSY; } rcu_read_unlock(); @@ -7985,13 +7986,16 @@ void md_error(struct mddev *mddev, struct md_rdev *rdev) if (!mddev->pers || !mddev->pers->error_handler) return; - mddev->pers->error_handler(mddev,rdev); - if (mddev->degraded) + mddev->pers->error_handler(mddev, rdev); + + if (mddev->degraded && !test_bit(MD_BROKEN, &mddev->flags)) set_bit(MD_RECOVERY_RECOVER, &mddev->recovery); sysfs_notify_dirent_safe(rdev->sysfs_state); set_bit(MD_RECOVERY_INTR, &mddev->recovery); - set_bit(MD_RECOVERY_NEEDED, &mddev->recovery); - md_wakeup_thread(mddev->thread); + if (!test_bit(MD_BROKEN, &mddev->flags)) { + set_bit(MD_RECOVERY_NEEDED, &mddev->recovery); + md_wakeup_thread(mddev->thread); + } if (mddev->event_work.func) queue_work(md_misc_wq, &mddev->event_work); md_new_event(); @@ -8585,7 +8589,7 @@ void md_submit_discard_bio(struct mddev *mddev, struct md_rdev *rdev, { struct bio *discard_bio = NULL; - if (__blkdev_issue_discard(rdev->bdev, start, size, GFP_NOIO, 0, + if (__blkdev_issue_discard(rdev->bdev, start, size, GFP_NOIO, &discard_bio) || !discard_bio) return; @@ -9671,7 +9675,7 @@ static void check_sb_changes(struct mddev *mddev, struct md_rdev *rdev) role = le16_to_cpu(sb->dev_roles[rdev2->desc_nr]); if (test_bit(Candidate, &rdev2->flags)) { - if (role == 0xfffe) { + if (role == MD_DISK_ROLE_FAULTY) { pr_info("md: Removing Candidate device %s because add failed\n", bdevname(rdev2->bdev,b)); md_kick_rdev_from_array(rdev2); continue; @@ -9684,7 +9688,7 @@ static void check_sb_changes(struct mddev *mddev, struct md_rdev *rdev) /* * got activated except reshape is happening. */ - if (rdev2->raid_disk == -1 && role != 0xffff && + if (rdev2->raid_disk == -1 && role != MD_DISK_ROLE_SPARE && !(le32_to_cpu(sb->feature_map) & MD_FEATURE_RESHAPE_ACTIVE)) { rdev2->saved_raid_disk = role; @@ -9701,7 +9705,8 @@ static void check_sb_changes(struct mddev *mddev, struct md_rdev *rdev) * as faulty. The recovery is performed by the * one who initiated the error. */ - if ((role == 0xfffe) || (role == 0xfffd)) { + if (role == MD_DISK_ROLE_FAULTY || + role == MD_DISK_ROLE_JOURNAL) { md_error(mddev, rdev2); clear_bit(Blocked, &rdev2->flags); } @@ -9791,16 +9796,18 @@ static int read_rdev(struct mddev *mddev, struct md_rdev *rdev) void md_reload_sb(struct mddev *mddev, int nr) { - struct md_rdev *rdev; + struct md_rdev *rdev = NULL, *iter; int err; /* Find the rdev */ - rdev_for_each_rcu(rdev, mddev) { - if (rdev->desc_nr == nr) + rdev_for_each_rcu(iter, mddev) { + if (iter->desc_nr == nr) { + rdev = iter; break; + } } - if (!rdev || rdev->desc_nr != nr) { + if (!rdev) { pr_warn("%s: %d Could not find rdev with nr %d\n", __func__, __LINE__, nr); return; } diff --git a/drivers/md/md.h b/drivers/md/md.h index 6ac283864533..cf2cbb17acbd 100644 --- a/drivers/md/md.h +++ b/drivers/md/md.h @@ -234,34 +234,42 @@ extern int rdev_clear_badblocks(struct md_rdev *rdev, sector_t s, int sectors, int is_new); struct md_cluster_info; -/* change UNSUPPORTED_MDDEV_FLAGS for each array type if new flag is added */ +/** + * enum mddev_flags - md device flags. + * @MD_ARRAY_FIRST_USE: First use of array, needs initialization. + * @MD_CLOSING: If set, we are closing the array, do not open it then. + * @MD_JOURNAL_CLEAN: A raid with journal is already clean. + * @MD_HAS_JOURNAL: The raid array has journal feature set. + * @MD_CLUSTER_RESYNC_LOCKED: cluster raid only, which means node, already took + * resync lock, need to release the lock. + * @MD_FAILFAST_SUPPORTED: Using MD_FAILFAST on metadata writes is supported as + * calls to md_error() will never cause the array to + * become failed. + * @MD_HAS_PPL: The raid array has PPL feature set. + * @MD_HAS_MULTIPLE_PPLS: The raid array has multiple PPLs feature set. + * @MD_ALLOW_SB_UPDATE: md_check_recovery is allowed to update the metadata + * without taking reconfig_mutex. + * @MD_UPDATING_SB: md_check_recovery is updating the metadata without + * explicitly holding reconfig_mutex. + * @MD_NOT_READY: do_md_run() is active, so 'array_state', ust not report that + * array is ready yet. + * @MD_BROKEN: This is used to stop writes and mark array as failed. + * + * change UNSUPPORTED_MDDEV_FLAGS for each array type if new flag is added + */ enum mddev_flags { - MD_ARRAY_FIRST_USE, /* First use of array, needs initialization */ - MD_CLOSING, /* If set, we are closing the array, do not open - * it then */ - MD_JOURNAL_CLEAN, /* A raid with journal is already clean */ - MD_HAS_JOURNAL, /* The raid array has journal feature set */ - MD_CLUSTER_RESYNC_LOCKED, /* cluster raid only, which means node - * already took resync lock, need to - * release the lock */ - MD_FAILFAST_SUPPORTED, /* Using MD_FAILFAST on metadata writes is - * supported as calls to md_error() will - * never cause the array to become failed. - */ - MD_HAS_PPL, /* The raid array has PPL feature set */ - MD_HAS_MULTIPLE_PPLS, /* The raid array has multiple PPLs feature set */ - MD_ALLOW_SB_UPDATE, /* md_check_recovery is allowed to update - * the metadata without taking reconfig_mutex. - */ - MD_UPDATING_SB, /* md_check_recovery is updating the metadata - * without explicitly holding reconfig_mutex. - */ - MD_NOT_READY, /* do_md_run() is active, so 'array_state' - * must not report that array is ready yet - */ - MD_BROKEN, /* This is used in RAID-0/LINEAR only, to stop - * I/O in case an array member is gone/failed. - */ + MD_ARRAY_FIRST_USE, + MD_CLOSING, + MD_JOURNAL_CLEAN, + MD_HAS_JOURNAL, + MD_CLUSTER_RESYNC_LOCKED, + MD_FAILFAST_SUPPORTED, + MD_HAS_PPL, + MD_HAS_MULTIPLE_PPLS, + MD_ALLOW_SB_UPDATE, + MD_UPDATING_SB, + MD_NOT_READY, + MD_BROKEN, }; enum mddev_sb_flags { diff --git a/drivers/md/raid0.c b/drivers/md/raid0.c index b21e101183f4..e11701e394ca 100644 --- a/drivers/md/raid0.c +++ b/drivers/md/raid0.c @@ -128,21 +128,6 @@ static int create_strip_zones(struct mddev *mddev, struct r0conf **private_conf) pr_debug("md/raid0:%s: FINAL %d zones\n", mdname(mddev), conf->nr_strip_zones); - if (conf->nr_strip_zones == 1) { - conf->layout = RAID0_ORIG_LAYOUT; - } else if (mddev->layout == RAID0_ORIG_LAYOUT || - mddev->layout == RAID0_ALT_MULTIZONE_LAYOUT) { - conf->layout = mddev->layout; - } else if (default_layout == RAID0_ORIG_LAYOUT || - default_layout == RAID0_ALT_MULTIZONE_LAYOUT) { - conf->layout = default_layout; - } else { - pr_err("md/raid0:%s: cannot assemble multi-zone RAID0 with default_layout setting\n", - mdname(mddev)); - pr_err("md/raid0: please set raid0.default_layout to 1 or 2\n"); - err = -ENOTSUPP; - goto abort; - } /* * now since we have the hard sector sizes, we can make sure * chunk size is a multiple of that sector size @@ -273,6 +258,22 @@ static int create_strip_zones(struct mddev *mddev, struct r0conf **private_conf) (unsigned long long)smallest->sectors); } + if (conf->nr_strip_zones == 1 || conf->strip_zone[1].nb_dev == 1) { + conf->layout = RAID0_ORIG_LAYOUT; + } else if (mddev->layout == RAID0_ORIG_LAYOUT || + mddev->layout == RAID0_ALT_MULTIZONE_LAYOUT) { + conf->layout = mddev->layout; + } else if (default_layout == RAID0_ORIG_LAYOUT || + default_layout == RAID0_ALT_MULTIZONE_LAYOUT) { + conf->layout = default_layout; + } else { + pr_err("md/raid0:%s: cannot assemble multi-zone RAID0 with default_layout setting\n", + mdname(mddev)); + pr_err("md/raid0: please set raid0.default_layout to 1 or 2\n"); + err = -EOPNOTSUPP; + goto abort; + } + pr_debug("md/raid0:%s: done.\n", mdname(mddev)); *private_conf = conf; @@ -399,7 +400,6 @@ static int raid0_run(struct mddev *mddev) conf = mddev->private; if (mddev->queue) { struct md_rdev *rdev; - bool discard_supported = false; blk_queue_max_hw_sectors(mddev->queue, mddev->chunk_sectors); blk_queue_max_write_zeroes_sectors(mddev->queue, mddev->chunk_sectors); @@ -412,13 +412,7 @@ static int raid0_run(struct mddev *mddev) rdev_for_each(rdev, mddev) { disk_stack_limits(mddev->gendisk, rdev->bdev, rdev->data_offset << 9); - if (blk_queue_discard(bdev_get_queue(rdev->bdev))) - discard_supported = true; } - if (!discard_supported) - blk_queue_flag_clear(QUEUE_FLAG_DISCARD, mddev->queue); - else - blk_queue_flag_set(QUEUE_FLAG_DISCARD, mddev->queue); } /* calculate array device size */ diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c index 99d5464a51f8..99d5af1362d7 100644 --- a/drivers/md/raid1.c +++ b/drivers/md/raid1.c @@ -165,9 +165,10 @@ static void * r1buf_pool_alloc(gfp_t gfp_flags, void *data) * Allocate bios : 1 for reading, n-1 for writing */ for (j = pi->raid_disks ; j-- ; ) { - bio = bio_kmalloc(gfp_flags, RESYNC_PAGES); + bio = bio_kmalloc(RESYNC_PAGES, gfp_flags); if (!bio) goto out_free_bio; + bio_init(bio, NULL, bio->bi_inline_vecs, RESYNC_PAGES, 0); r1_bio->bios[j] = bio; } /* @@ -206,8 +207,10 @@ out_free_pages: resync_free_pages(&rps[j]); out_free_bio: - while (++j < pi->raid_disks) - bio_put(r1_bio->bios[j]); + while (++j < pi->raid_disks) { + bio_uninit(r1_bio->bios[j]); + kfree(r1_bio->bios[j]); + } kfree(rps); out_free_r1bio: @@ -225,7 +228,8 @@ static void r1buf_pool_free(void *__r1_bio, void *data) for (i = pi->raid_disks; i--; ) { rp = get_resync_pages(r1bio->bios[i]); resync_free_pages(rp); - bio_put(r1bio->bios[i]); + bio_uninit(r1bio->bios[i]); + kfree(r1bio->bios[i]); } /* resync pages array stored in the 1st bio's .bi_private */ @@ -704,7 +708,7 @@ static int read_balance(struct r1conf *conf, struct r1bio *r1_bio, int *max_sect /* At least two disks to choose from so failfast is OK */ set_bit(R1BIO_FailFast, &r1_bio->state); - nonrot = blk_queue_nonrot(bdev_get_queue(rdev->bdev)); + nonrot = bdev_nonrot(rdev->bdev); has_nonrot_disk |= nonrot; pending = atomic_read(&rdev->nr_pending); dist = abs(this_sector - conf->mirrors[disk].head_position); @@ -802,7 +806,7 @@ static void flush_bio_list(struct r1conf *conf, struct bio *bio) if (test_bit(Faulty, &rdev->flags)) { bio_io_error(bio); } else if (unlikely((bio_op(bio) == REQ_OP_DISCARD) && - !blk_queue_discard(bio->bi_bdev->bd_disk->queue))) + !bdev_max_discard_sectors(bio->bi_bdev))) /* Just ignore it */ bio_endio(bio); else @@ -1637,30 +1641,39 @@ static void raid1_status(struct seq_file *seq, struct mddev *mddev) seq_printf(seq, "]"); } +/** + * raid1_error() - RAID1 error handler. + * @mddev: affected md device. + * @rdev: member device to fail. + * + * The routine acknowledges &rdev failure and determines new @mddev state. + * If it failed, then: + * - &MD_BROKEN flag is set in &mddev->flags. + * - recovery is disabled. + * Otherwise, it must be degraded: + * - recovery is interrupted. + * - &mddev->degraded is bumped. + * + * @rdev is marked as &Faulty excluding case when array is failed and + * &mddev->fail_last_dev is off. + */ static void raid1_error(struct mddev *mddev, struct md_rdev *rdev) { char b[BDEVNAME_SIZE]; struct r1conf *conf = mddev->private; unsigned long flags; - /* - * If it is not operational, then we have already marked it as dead - * else if it is the last working disks with "fail_last_dev == false", - * ignore the error, let the next level up know. - * else mark the drive as failed - */ spin_lock_irqsave(&conf->device_lock, flags); - if (test_bit(In_sync, &rdev->flags) && !mddev->fail_last_dev - && (conf->raid_disks - mddev->degraded) == 1) { - /* - * Don't fail the drive, act as though we were just a - * normal single drive. - * However don't try a recovery from this drive as - * it is very likely to fail. - */ - conf->recovery_disabled = mddev->recovery_disabled; - spin_unlock_irqrestore(&conf->device_lock, flags); - return; + + if (test_bit(In_sync, &rdev->flags) && + (conf->raid_disks - mddev->degraded) == 1) { + set_bit(MD_BROKEN, &mddev->flags); + + if (!mddev->fail_last_dev) { + conf->recovery_disabled = mddev->recovery_disabled; + spin_unlock_irqrestore(&conf->device_lock, flags); + return; + } } set_bit(Blocked, &rdev->flags); if (test_and_clear_bit(In_sync, &rdev->flags)) @@ -1826,8 +1839,6 @@ static int raid1_add_disk(struct mddev *mddev, struct md_rdev *rdev) break; } } - if (mddev->queue && blk_queue_discard(bdev_get_queue(rdev->bdev))) - blk_queue_flag_set(QUEUE_FLAG_DISCARD, mddev->queue); print_conf(conf); return err; } @@ -3106,7 +3117,6 @@ static int raid1_run(struct mddev *mddev) int i; struct md_rdev *rdev; int ret; - bool discard_supported = false; if (mddev->level != 1) { pr_warn("md/raid1:%s: raid level not set to mirroring (%d)\n", @@ -3141,8 +3151,6 @@ static int raid1_run(struct mddev *mddev) continue; disk_stack_limits(mddev->gendisk, rdev->bdev, rdev->data_offset << 9); - if (blk_queue_discard(bdev_get_queue(rdev->bdev))) - discard_supported = true; } mddev->degraded = 0; @@ -3179,15 +3187,6 @@ static int raid1_run(struct mddev *mddev) md_set_array_sectors(mddev, raid1_size(mddev, 0, 0)); - if (mddev->queue) { - if (discard_supported) - blk_queue_flag_set(QUEUE_FLAG_DISCARD, - mddev->queue); - else - blk_queue_flag_clear(QUEUE_FLAG_DISCARD, - mddev->queue); - } - ret = md_integrity_register(mddev); if (ret) { md_unregister_thread(&mddev->thread); diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c index dfe7d62d3fbd..dfa576cdf11c 100644 --- a/drivers/md/raid10.c +++ b/drivers/md/raid10.c @@ -145,15 +145,17 @@ static void * r10buf_pool_alloc(gfp_t gfp_flags, void *data) * Allocate bios. */ for (j = nalloc ; j-- ; ) { - bio = bio_kmalloc(gfp_flags, RESYNC_PAGES); + bio = bio_kmalloc(RESYNC_PAGES, gfp_flags); if (!bio) goto out_free_bio; + bio_init(bio, NULL, bio->bi_inline_vecs, RESYNC_PAGES, 0); r10_bio->devs[j].bio = bio; if (!conf->have_replacement) continue; - bio = bio_kmalloc(gfp_flags, RESYNC_PAGES); + bio = bio_kmalloc(RESYNC_PAGES, gfp_flags); if (!bio) goto out_free_bio; + bio_init(bio, NULL, bio->bi_inline_vecs, RESYNC_PAGES, 0); r10_bio->devs[j].repl_bio = bio; } /* @@ -197,9 +199,11 @@ out_free_pages: out_free_bio: for ( ; j < nalloc; j++) { if (r10_bio->devs[j].bio) - bio_put(r10_bio->devs[j].bio); + bio_uninit(r10_bio->devs[j].bio); + kfree(r10_bio->devs[j].bio); if (r10_bio->devs[j].repl_bio) - bio_put(r10_bio->devs[j].repl_bio); + bio_uninit(r10_bio->devs[j].repl_bio); + kfree(r10_bio->devs[j].repl_bio); } kfree(rps); out_free_r10bio: @@ -220,12 +224,15 @@ static void r10buf_pool_free(void *__r10_bio, void *data) if (bio) { rp = get_resync_pages(bio); resync_free_pages(rp); - bio_put(bio); + bio_uninit(bio); + kfree(bio); } bio = r10bio->devs[j].repl_bio; - if (bio) - bio_put(bio); + if (bio) { + bio_uninit(bio); + kfree(bio); + } } /* resync pages array stored in the 1st bio's .bi_private */ @@ -796,7 +803,7 @@ static struct md_rdev *read_balance(struct r10conf *conf, if (!do_balance) break; - nonrot = blk_queue_nonrot(bdev_get_queue(rdev->bdev)); + nonrot = bdev_nonrot(rdev->bdev); has_nonrot_disk |= nonrot; pending = atomic_read(&rdev->nr_pending); if (min_pending > pending && nonrot) { @@ -888,7 +895,7 @@ static void flush_pending_writes(struct r10conf *conf) if (test_bit(Faulty, &rdev->flags)) { bio_io_error(bio); } else if (unlikely((bio_op(bio) == REQ_OP_DISCARD) && - !blk_queue_discard(bio->bi_bdev->bd_disk->queue))) + !bdev_max_discard_sectors(bio->bi_bdev))) /* Just ignore it */ bio_endio(bio); else @@ -1083,7 +1090,7 @@ static void raid10_unplug(struct blk_plug_cb *cb, bool from_schedule) if (test_bit(Faulty, &rdev->flags)) { bio_io_error(bio); } else if (unlikely((bio_op(bio) == REQ_OP_DISCARD) && - !blk_queue_discard(bio->bi_bdev->bd_disk->queue))) + !bdev_max_discard_sectors(bio->bi_bdev))) /* Just ignore it */ bio_endio(bio); else @@ -1963,32 +1970,40 @@ static int enough(struct r10conf *conf, int ignore) _enough(conf, 1, ignore); } +/** + * raid10_error() - RAID10 error handler. + * @mddev: affected md device. + * @rdev: member device to fail. + * + * The routine acknowledges &rdev failure and determines new @mddev state. + * If it failed, then: + * - &MD_BROKEN flag is set in &mddev->flags. + * Otherwise, it must be degraded: + * - recovery is interrupted. + * - &mddev->degraded is bumped. + + * @rdev is marked as &Faulty excluding case when array is failed and + * &mddev->fail_last_dev is off. + */ static void raid10_error(struct mddev *mddev, struct md_rdev *rdev) { char b[BDEVNAME_SIZE]; struct r10conf *conf = mddev->private; unsigned long flags; - /* - * If it is not operational, then we have already marked it as dead - * else if it is the last working disks with "fail_last_dev == false", - * ignore the error, let the next level up know. - * else mark the drive as failed - */ spin_lock_irqsave(&conf->device_lock, flags); - if (test_bit(In_sync, &rdev->flags) && !mddev->fail_last_dev - && !enough(conf, rdev->raid_disk)) { - /* - * Don't fail the drive, just return an IO error. - */ - spin_unlock_irqrestore(&conf->device_lock, flags); - return; + + if (test_bit(In_sync, &rdev->flags) && !enough(conf, rdev->raid_disk)) { + set_bit(MD_BROKEN, &mddev->flags); + + if (!mddev->fail_last_dev) { + spin_unlock_irqrestore(&conf->device_lock, flags); + return; + } } if (test_and_clear_bit(In_sync, &rdev->flags)) mddev->degraded++; - /* - * If recovery is running, make sure it aborts. - */ + set_bit(MD_RECOVERY_INTR, &mddev->recovery); set_bit(Blocked, &rdev->flags); set_bit(Faulty, &rdev->flags); @@ -2144,8 +2159,6 @@ static int raid10_add_disk(struct mddev *mddev, struct md_rdev *rdev) rcu_assign_pointer(p->rdev, rdev); break; } - if (mddev->queue && blk_queue_discard(bdev_get_queue(rdev->bdev))) - blk_queue_flag_set(QUEUE_FLAG_DISCARD, mddev->queue); print_conf(conf); return err; @@ -4069,7 +4082,6 @@ static int raid10_run(struct mddev *mddev) sector_t size; sector_t min_offset_diff = 0; int first = 1; - bool discard_supported = false; if (mddev_init_writes_pending(mddev) < 0) return -ENOMEM; @@ -4140,20 +4152,9 @@ static int raid10_run(struct mddev *mddev) rdev->data_offset << 9); disk->head_position = 0; - - if (blk_queue_discard(bdev_get_queue(rdev->bdev))) - discard_supported = true; first = 0; } - if (mddev->queue) { - if (discard_supported) - blk_queue_flag_set(QUEUE_FLAG_DISCARD, - mddev->queue); - else - blk_queue_flag_clear(QUEUE_FLAG_DISCARD, - mddev->queue); - } /* need to check that every block has at least one working mirror */ if (!enough(conf, -1)) { pr_err("md/raid10:%s: not enough operational mirrors.\n", diff --git a/drivers/md/raid5-cache.c b/drivers/md/raid5-cache.c index a7d50ff9020a..094a4042589e 100644 --- a/drivers/md/raid5-cache.c +++ b/drivers/md/raid5-cache.c @@ -1318,7 +1318,7 @@ static void r5l_write_super_and_discard_space(struct r5l_log *log, r5l_write_super(log, end); - if (!blk_queue_discard(bdev_get_queue(bdev))) + if (!bdev_max_discard_sectors(bdev)) return; mddev = log->rdev->mddev; @@ -1344,14 +1344,14 @@ static void r5l_write_super_and_discard_space(struct r5l_log *log, if (log->last_checkpoint < end) { blkdev_issue_discard(bdev, log->last_checkpoint + log->rdev->data_offset, - end - log->last_checkpoint, GFP_NOIO, 0); + end - log->last_checkpoint, GFP_NOIO); } else { blkdev_issue_discard(bdev, log->last_checkpoint + log->rdev->data_offset, log->device_size - log->last_checkpoint, - GFP_NOIO, 0); + GFP_NOIO); blkdev_issue_discard(bdev, log->rdev->data_offset, end, - GFP_NOIO, 0); + GFP_NOIO); } } diff --git a/drivers/md/raid5-ppl.c b/drivers/md/raid5-ppl.c index d3962d92df18..55d065a87b89 100644 --- a/drivers/md/raid5-ppl.c +++ b/drivers/md/raid5-ppl.c @@ -883,7 +883,9 @@ static int ppl_recover_entry(struct ppl_log *log, struct ppl_header_entry *e, (unsigned long long)r_sector, dd_idx, (unsigned long long)sector); - rdev = conf->disks[dd_idx].rdev; + /* Array has not started so rcu dereference is safe */ + rdev = rcu_dereference_protected( + conf->disks[dd_idx].rdev, 1); if (!rdev || (!test_bit(In_sync, &rdev->flags) && sector >= rdev->recovery_offset)) { pr_debug("%s:%*s data member disk %d missing\n", @@ -934,7 +936,10 @@ static int ppl_recover_entry(struct ppl_log *log, struct ppl_header_entry *e, parity_sector = raid5_compute_sector(conf, r_sector_first + i, 0, &disk, &sh); BUG_ON(sh.pd_idx != le32_to_cpu(e->parity_disk)); - parity_rdev = conf->disks[sh.pd_idx].rdev; + + /* Array has not started so rcu dereference is safe */ + parity_rdev = rcu_dereference_protected( + conf->disks[sh.pd_idx].rdev, 1); BUG_ON(parity_rdev->bdev->bd_dev != log->rdev->bdev->bd_dev); pr_debug("%s:%*s write parity at sector %llu, disk %s\n", @@ -1404,7 +1409,9 @@ int ppl_init_log(struct r5conf *conf) for (i = 0; i < ppl_conf->count; i++) { struct ppl_log *log = &ppl_conf->child_logs[i]; - struct md_rdev *rdev = conf->disks[i].rdev; + /* Array has not started so rcu dereference is safe */ + struct md_rdev *rdev = + rcu_dereference_protected(conf->disks[i].rdev, 1); mutex_init(&log->io_mutex); spin_lock_init(&log->io_list_lock); diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c index 351d341a1ffa..39038fa8b1c8 100644 --- a/drivers/md/raid5.c +++ b/drivers/md/raid5.c @@ -79,18 +79,21 @@ static inline int stripe_hash_locks_hash(struct r5conf *conf, sector_t sect) } static inline void lock_device_hash_lock(struct r5conf *conf, int hash) + __acquires(&conf->device_lock) { spin_lock_irq(conf->hash_locks + hash); spin_lock(&conf->device_lock); } static inline void unlock_device_hash_lock(struct r5conf *conf, int hash) + __releases(&conf->device_lock) { spin_unlock(&conf->device_lock); spin_unlock_irq(conf->hash_locks + hash); } static inline void lock_all_device_hash_locks_irq(struct r5conf *conf) + __acquires(&conf->device_lock) { int i; spin_lock_irq(conf->hash_locks); @@ -100,6 +103,7 @@ static inline void lock_all_device_hash_locks_irq(struct r5conf *conf) } static inline void unlock_all_device_hash_locks_irq(struct r5conf *conf) + __releases(&conf->device_lock) { int i; spin_unlock(&conf->device_lock); @@ -164,6 +168,7 @@ static bool stripe_is_lowprio(struct stripe_head *sh) } static void raid5_wakeup_stripe_thread(struct stripe_head *sh) + __must_hold(&sh->raid_conf->device_lock) { struct r5conf *conf = sh->raid_conf; struct r5worker_group *group; @@ -211,6 +216,7 @@ static void raid5_wakeup_stripe_thread(struct stripe_head *sh) static void do_release_stripe(struct r5conf *conf, struct stripe_head *sh, struct list_head *temp_inactive_list) + __must_hold(&conf->device_lock) { int i; int injournal = 0; /* number of date pages with R5_InJournal */ @@ -296,6 +302,7 @@ static void do_release_stripe(struct r5conf *conf, struct stripe_head *sh, static void __release_stripe(struct r5conf *conf, struct stripe_head *sh, struct list_head *temp_inactive_list) + __must_hold(&conf->device_lock) { if (atomic_dec_and_test(&sh->count)) do_release_stripe(conf, sh, temp_inactive_list); @@ -350,9 +357,9 @@ static void release_inactive_stripe_list(struct r5conf *conf, } } -/* should hold conf->device_lock already */ static int release_stripe_list(struct r5conf *conf, struct list_head *temp_inactive_list) + __must_hold(&conf->device_lock) { struct stripe_head *sh, *t; int count = 0; @@ -629,6 +636,10 @@ static struct stripe_head *__find_stripe(struct r5conf *conf, sector_t sector, * This is because some failed devices may only affect one * of the two sections, and some non-in_sync devices may * be insync in the section most affected by failed devices. + * + * Most calls to this function hold &conf->device_lock. Calls + * in raid5_run() do not require the lock as no other threads + * have been started yet. */ int raid5_calc_degraded(struct r5conf *conf) { @@ -686,17 +697,17 @@ int raid5_calc_degraded(struct r5conf *conf) return degraded; } -static int has_failed(struct r5conf *conf) +static bool has_failed(struct r5conf *conf) { - int degraded; + int degraded = conf->mddev->degraded; - if (conf->mddev->reshape_position == MaxSector) - return conf->mddev->degraded > conf->max_degraded; + if (test_bit(MD_BROKEN, &conf->mddev->flags)) + return true; - degraded = raid5_calc_degraded(conf); - if (degraded > conf->max_degraded) - return 1; - return 0; + if (conf->mddev->reshape_position != MaxSector) + degraded = raid5_calc_degraded(conf); + + return degraded > conf->max_degraded; } struct stripe_head * @@ -2648,6 +2659,28 @@ static void shrink_stripes(struct r5conf *conf) conf->slab_cache = NULL; } +/* + * This helper wraps rcu_dereference_protected() and can be used when + * it is known that the nr_pending of the rdev is elevated. + */ +static struct md_rdev *rdev_pend_deref(struct md_rdev __rcu *rdev) +{ + return rcu_dereference_protected(rdev, + atomic_read(&rcu_access_pointer(rdev)->nr_pending)); +} + +/* + * This helper wraps rcu_dereference_protected() and should be used + * when it is known that the mddev_lock() is held. This is safe + * seeing raid5_remove_disk() has the same lock held. + */ +static struct md_rdev *rdev_mdlock_deref(struct mddev *mddev, + struct md_rdev __rcu *rdev) +{ + return rcu_dereference_protected(rdev, + lockdep_is_held(&mddev->reconfig_mutex)); +} + static void raid5_end_read_request(struct bio * bi) { struct stripe_head *sh = bi->bi_private; @@ -2674,9 +2707,9 @@ static void raid5_end_read_request(struct bio * bi) * In that case it moved down to 'rdev'. * rdev is not removed until all requests are finished. */ - rdev = conf->disks[i].replacement; + rdev = rdev_pend_deref(conf->disks[i].replacement); if (!rdev) - rdev = conf->disks[i].rdev; + rdev = rdev_pend_deref(conf->disks[i].rdev); if (use_new_offset(conf, sh)) s = sh->sector + rdev->new_data_offset; @@ -2790,11 +2823,11 @@ static void raid5_end_write_request(struct bio *bi) for (i = 0 ; i < disks; i++) { if (bi == &sh->dev[i].req) { - rdev = conf->disks[i].rdev; + rdev = rdev_pend_deref(conf->disks[i].rdev); break; } if (bi == &sh->dev[i].rreq) { - rdev = conf->disks[i].replacement; + rdev = rdev_pend_deref(conf->disks[i].replacement); if (rdev) replacement = 1; else @@ -2802,7 +2835,7 @@ static void raid5_end_write_request(struct bio *bi) * replaced it. rdev is not removed * until all requests are finished. */ - rdev = conf->disks[i].rdev; + rdev = rdev_pend_deref(conf->disks[i].rdev); break; } } @@ -2863,34 +2896,31 @@ static void raid5_error(struct mddev *mddev, struct md_rdev *rdev) unsigned long flags; pr_debug("raid456: error called\n"); + pr_crit("md/raid:%s: Disk failure on %s, disabling device.\n", + mdname(mddev), bdevname(rdev->bdev, b)); + spin_lock_irqsave(&conf->device_lock, flags); + set_bit(Faulty, &rdev->flags); + clear_bit(In_sync, &rdev->flags); + mddev->degraded = raid5_calc_degraded(conf); - if (test_bit(In_sync, &rdev->flags) && - mddev->degraded == conf->max_degraded) { - /* - * Don't allow to achieve failed state - * Don't try to recover this device - */ + if (has_failed(conf)) { + set_bit(MD_BROKEN, &conf->mddev->flags); conf->recovery_disabled = mddev->recovery_disabled; - spin_unlock_irqrestore(&conf->device_lock, flags); - return; + + pr_crit("md/raid:%s: Cannot continue operation (%d/%d failed).\n", + mdname(mddev), mddev->degraded, conf->raid_disks); + } else { + pr_crit("md/raid:%s: Operation continuing on %d devices.\n", + mdname(mddev), conf->raid_disks - mddev->degraded); } - set_bit(Faulty, &rdev->flags); - clear_bit(In_sync, &rdev->flags); - mddev->degraded = raid5_calc_degraded(conf); spin_unlock_irqrestore(&conf->device_lock, flags); set_bit(MD_RECOVERY_INTR, &mddev->recovery); set_bit(Blocked, &rdev->flags); set_mask_bits(&mddev->sb_flags, 0, BIT(MD_SB_CHANGE_DEVS) | BIT(MD_SB_CHANGE_PENDING)); - pr_crit("md/raid:%s: Disk failure on %s, disabling device.\n" - "md/raid:%s: Operation continuing on %d devices.\n", - mdname(mddev), - bdevname(rdev->bdev, b), - mdname(mddev), - conf->raid_disks - mddev->degraded); r5c_update_on_rdev_error(mddev, rdev); } @@ -5213,23 +5243,23 @@ finish: struct r5dev *dev = &sh->dev[i]; if (test_and_clear_bit(R5_WriteError, &dev->flags)) { /* We own a safe reference to the rdev */ - rdev = conf->disks[i].rdev; + rdev = rdev_pend_deref(conf->disks[i].rdev); if (!rdev_set_badblocks(rdev, sh->sector, RAID5_STRIPE_SECTORS(conf), 0)) md_error(conf->mddev, rdev); rdev_dec_pending(rdev, conf->mddev); } if (test_and_clear_bit(R5_MadeGood, &dev->flags)) { - rdev = conf->disks[i].rdev; + rdev = rdev_pend_deref(conf->disks[i].rdev); rdev_clear_badblocks(rdev, sh->sector, RAID5_STRIPE_SECTORS(conf), 0); rdev_dec_pending(rdev, conf->mddev); } if (test_and_clear_bit(R5_MadeGoodRepl, &dev->flags)) { - rdev = conf->disks[i].replacement; + rdev = rdev_pend_deref(conf->disks[i].replacement); if (!rdev) /* rdev have been moved down */ - rdev = conf->disks[i].rdev; + rdev = rdev_pend_deref(conf->disks[i].rdev); rdev_clear_badblocks(rdev, sh->sector, RAID5_STRIPE_SECTORS(conf), 0); rdev_dec_pending(rdev, conf->mddev); @@ -5256,6 +5286,7 @@ finish: } static void raid5_activate_delayed(struct r5conf *conf) + __must_hold(&conf->device_lock) { if (atomic_read(&conf->preread_active_stripes) < IO_THRESHOLD) { while (!list_empty(&conf->delayed_list)) { @@ -5273,9 +5304,9 @@ static void raid5_activate_delayed(struct r5conf *conf) } static void activate_bit_delay(struct r5conf *conf, - struct list_head *temp_inactive_list) + struct list_head *temp_inactive_list) + __must_hold(&conf->device_lock) { - /* device_lock is held */ struct list_head head; list_add(&head, &conf->bitmap_list); list_del_init(&conf->bitmap_list); @@ -5500,6 +5531,7 @@ static struct bio *chunk_aligned_read(struct mddev *mddev, struct bio *raid_bio) * handle_list. */ static struct stripe_head *__get_priority_stripe(struct r5conf *conf, int group) + __must_hold(&conf->device_lock) { struct stripe_head *sh, *tmp; struct list_head *handle_list = NULL; @@ -6288,7 +6320,7 @@ static inline sector_t raid5_sync_request(struct mddev *mddev, sector_t sector_n */ rcu_read_lock(); for (i = 0; i < conf->raid_disks; i++) { - struct md_rdev *rdev = READ_ONCE(conf->disks[i].rdev); + struct md_rdev *rdev = rcu_dereference(conf->disks[i].rdev); if (rdev == NULL || test_bit(Faulty, &rdev->flags)) still_degraded = 1; @@ -6371,8 +6403,7 @@ static int retry_aligned_read(struct r5conf *conf, struct bio *raid_bio, static int handle_active_stripes(struct r5conf *conf, int group, struct r5worker *worker, struct list_head *temp_inactive_list) - __releases(&conf->device_lock) - __acquires(&conf->device_lock) + __must_hold(&conf->device_lock) { struct stripe_head *batch[MAX_STRIPE_BATCH], *sh; int i, batch_size = 0, hash; @@ -7166,7 +7197,7 @@ static struct r5conf *setup_conf(struct mddev *mddev) int i; int group_cnt; struct r5worker_group *new_group; - int ret; + int ret = -ENOMEM; if (mddev->new_level != 5 && mddev->new_level != 4 @@ -7225,6 +7256,7 @@ static struct r5conf *setup_conf(struct mddev *mddev) spin_lock_init(&conf->device_lock); seqcount_spinlock_init(&conf->gen_lock, &conf->device_lock); mutex_init(&conf->cache_size_mutex); + init_waitqueue_head(&conf->wait_for_quiescent); init_waitqueue_head(&conf->wait_for_stripe); init_waitqueue_head(&conf->wait_for_overlap); @@ -7242,7 +7274,7 @@ static struct r5conf *setup_conf(struct mddev *mddev) rdev_for_each(rdev, mddev) { if (test_bit(Journal, &rdev->flags)) continue; - if (blk_queue_nonrot(bdev_get_queue(rdev->bdev))) { + if (bdev_nonrot(rdev->bdev)) { conf->batch_bio_dispatch = false; break; } @@ -7302,11 +7334,13 @@ static struct r5conf *setup_conf(struct mddev *mddev) conf->level = mddev->new_level; conf->chunk_sectors = mddev->new_chunk_sectors; - if (raid5_alloc_percpu(conf) != 0) + ret = raid5_alloc_percpu(conf); + if (ret) goto abort; pr_debug("raid456: run(%s) called.\n", mdname(mddev)); + ret = -EIO; rdev_for_each(rdev, mddev) { raid_disk = rdev->raid_disk; if (raid_disk >= max_disks @@ -7317,11 +7351,11 @@ static struct r5conf *setup_conf(struct mddev *mddev) if (test_bit(Replacement, &rdev->flags)) { if (disk->replacement) goto abort; - disk->replacement = rdev; + RCU_INIT_POINTER(disk->replacement, rdev); } else { if (disk->rdev) goto abort; - disk->rdev = rdev; + RCU_INIT_POINTER(disk->rdev, rdev); } if (test_bit(In_sync, &rdev->flags)) { @@ -7370,6 +7404,7 @@ static struct r5conf *setup_conf(struct mddev *mddev) if (grow_stripes(conf, conf->min_nr_stripes)) { pr_warn("md/raid:%s: couldn't allocate %dkB for buffers\n", mdname(mddev), memory); + ret = -ENOMEM; goto abort; } else pr_debug("md/raid:%s: allocated %dkB\n", mdname(mddev), memory); @@ -7383,7 +7418,8 @@ static struct r5conf *setup_conf(struct mddev *mddev) conf->shrinker.count_objects = raid5_cache_count; conf->shrinker.batch = 128; conf->shrinker.flags = 0; - if (register_shrinker(&conf->shrinker)) { + ret = register_shrinker(&conf->shrinker); + if (ret) { pr_warn("md/raid:%s: couldn't register shrinker.\n", mdname(mddev)); goto abort; @@ -7394,17 +7430,16 @@ static struct r5conf *setup_conf(struct mddev *mddev) if (!conf->thread) { pr_warn("md/raid:%s: couldn't allocate thread.\n", mdname(mddev)); + ret = -ENOMEM; goto abort; } return conf; abort: - if (conf) { + if (conf) free_conf(conf); - return ERR_PTR(-EIO); - } else - return ERR_PTR(-ENOMEM); + return ERR_PTR(ret); } static int only_parity(int raid_disk, int algo, int raid_disks, int max_degraded) @@ -7621,17 +7656,18 @@ static int raid5_run(struct mddev *mddev) for (i = 0; i < conf->raid_disks && conf->previous_raid_disks; i++) { - rdev = conf->disks[i].rdev; + rdev = rdev_mdlock_deref(mddev, conf->disks[i].rdev); if (!rdev && conf->disks[i].replacement) { /* The replacement is all we have yet */ - rdev = conf->disks[i].replacement; + rdev = rdev_mdlock_deref(mddev, + conf->disks[i].replacement); conf->disks[i].replacement = NULL; clear_bit(Replacement, &rdev->flags); - conf->disks[i].rdev = rdev; + rcu_assign_pointer(conf->disks[i].rdev, rdev); } if (!rdev) continue; - if (conf->disks[i].replacement && + if (rcu_access_pointer(conf->disks[i].replacement) && conf->reshape_progress != MaxSector) { /* replacements and reshape simply do not mix. */ pr_warn("md: cannot handle concurrent replacement and reshape.\n"); @@ -7749,7 +7785,6 @@ static int raid5_run(struct mddev *mddev) */ stripe = stripe * PAGE_SIZE; stripe = roundup_pow_of_two(stripe); - mddev->queue->limits.discard_alignment = stripe; mddev->queue->limits.discard_granularity = stripe; blk_queue_max_write_zeroes_sectors(mddev->queue, 0); @@ -7776,14 +7811,10 @@ static int raid5_run(struct mddev *mddev) * A better idea might be to turn DISCARD into WRITE_ZEROES * requests, as that is required to be safe. */ - if (devices_handle_discard_safely && - mddev->queue->limits.max_discard_sectors >= (stripe >> 9) && - mddev->queue->limits.discard_granularity >= stripe) - blk_queue_flag_set(QUEUE_FLAG_DISCARD, - mddev->queue); - else - blk_queue_flag_clear(QUEUE_FLAG_DISCARD, - mddev->queue); + if (!devices_handle_discard_safely || + mddev->queue->limits.max_discard_sectors < (stripe >> 9) || + mddev->queue->limits.discard_granularity < stripe) + blk_queue_max_discard_sectors(mddev->queue, 0); blk_queue_max_hw_sectors(mddev->queue, UINT_MAX); } @@ -7832,8 +7863,8 @@ static void raid5_status(struct seq_file *seq, struct mddev *mddev) static void print_raid5_conf (struct r5conf *conf) { + struct md_rdev *rdev; int i; - struct disk_info *tmp; pr_debug("RAID conf printout:\n"); if (!conf) { @@ -7844,50 +7875,54 @@ static void print_raid5_conf (struct r5conf *conf) conf->raid_disks, conf->raid_disks - conf->mddev->degraded); + rcu_read_lock(); for (i = 0; i < conf->raid_disks; i++) { char b[BDEVNAME_SIZE]; - tmp = conf->disks + i; - if (tmp->rdev) + rdev = rcu_dereference(conf->disks[i].rdev); + if (rdev) pr_debug(" disk %d, o:%d, dev:%s\n", - i, !test_bit(Faulty, &tmp->rdev->flags), - bdevname(tmp->rdev->bdev, b)); + i, !test_bit(Faulty, &rdev->flags), + bdevname(rdev->bdev, b)); } + rcu_read_unlock(); } static int raid5_spare_active(struct mddev *mddev) { int i; struct r5conf *conf = mddev->private; - struct disk_info *tmp; + struct md_rdev *rdev, *replacement; int count = 0; unsigned long flags; for (i = 0; i < conf->raid_disks; i++) { - tmp = conf->disks + i; - if (tmp->replacement - && tmp->replacement->recovery_offset == MaxSector - && !test_bit(Faulty, &tmp->replacement->flags) - && !test_and_set_bit(In_sync, &tmp->replacement->flags)) { + rdev = rdev_mdlock_deref(mddev, conf->disks[i].rdev); + replacement = rdev_mdlock_deref(mddev, + conf->disks[i].replacement); + if (replacement + && replacement->recovery_offset == MaxSector + && !test_bit(Faulty, &replacement->flags) + && !test_and_set_bit(In_sync, &replacement->flags)) { /* Replacement has just become active. */ - if (!tmp->rdev - || !test_and_clear_bit(In_sync, &tmp->rdev->flags)) + if (!rdev + || !test_and_clear_bit(In_sync, &rdev->flags)) count++; - if (tmp->rdev) { + if (rdev) { /* Replaced device not technically faulty, * but we need to be sure it gets removed * and never re-added. */ - set_bit(Faulty, &tmp->rdev->flags); + set_bit(Faulty, &rdev->flags); sysfs_notify_dirent_safe( - tmp->rdev->sysfs_state); + rdev->sysfs_state); } - sysfs_notify_dirent_safe(tmp->replacement->sysfs_state); - } else if (tmp->rdev - && tmp->rdev->recovery_offset == MaxSector - && !test_bit(Faulty, &tmp->rdev->flags) - && !test_and_set_bit(In_sync, &tmp->rdev->flags)) { + sysfs_notify_dirent_safe(replacement->sysfs_state); + } else if (rdev + && rdev->recovery_offset == MaxSector + && !test_bit(Faulty, &rdev->flags) + && !test_and_set_bit(In_sync, &rdev->flags)) { count++; - sysfs_notify_dirent_safe(tmp->rdev->sysfs_state); + sysfs_notify_dirent_safe(rdev->sysfs_state); } } spin_lock_irqsave(&conf->device_lock, flags); @@ -7902,8 +7937,9 @@ static int raid5_remove_disk(struct mddev *mddev, struct md_rdev *rdev) struct r5conf *conf = mddev->private; int err = 0; int number = rdev->raid_disk; - struct md_rdev **rdevp; + struct md_rdev __rcu **rdevp; struct disk_info *p = conf->disks + number; + struct md_rdev *tmp; print_raid5_conf(conf); if (test_bit(Journal, &rdev->flags) && conf->log) { @@ -7921,9 +7957,9 @@ static int raid5_remove_disk(struct mddev *mddev, struct md_rdev *rdev) log_exit(conf); return 0; } - if (rdev == p->rdev) + if (rdev == rcu_access_pointer(p->rdev)) rdevp = &p->rdev; - else if (rdev == p->replacement) + else if (rdev == rcu_access_pointer(p->replacement)) rdevp = &p->replacement; else return 0; @@ -7943,18 +7979,20 @@ static int raid5_remove_disk(struct mddev *mddev, struct md_rdev *rdev) if (!test_bit(Faulty, &rdev->flags) && mddev->recovery_disabled != conf->recovery_disabled && !has_failed(conf) && - (!p->replacement || p->replacement == rdev) && + (!rcu_access_pointer(p->replacement) || + rcu_access_pointer(p->replacement) == rdev) && number < conf->raid_disks) { err = -EBUSY; goto abort; } *rdevp = NULL; if (!test_bit(RemoveSynchronized, &rdev->flags)) { + lockdep_assert_held(&mddev->reconfig_mutex); synchronize_rcu(); if (atomic_read(&rdev->nr_pending)) { /* lost the race, try later */ err = -EBUSY; - *rdevp = rdev; + rcu_assign_pointer(*rdevp, rdev); } } if (!err) { @@ -7962,17 +8000,19 @@ static int raid5_remove_disk(struct mddev *mddev, struct md_rdev *rdev) if (err) goto abort; } - if (p->replacement) { + + tmp = rcu_access_pointer(p->replacement); + if (tmp) { /* We must have just cleared 'rdev' */ - p->rdev = p->replacement; - clear_bit(Replacement, &p->replacement->flags); + rcu_assign_pointer(p->rdev, tmp); + clear_bit(Replacement, &tmp->flags); smp_mb(); /* Make sure other CPUs may see both as identical * but will never see neither - if they are careful */ - p->replacement = NULL; + rcu_assign_pointer(p->replacement, NULL); if (!err) - err = log_modify(conf, p->rdev, true); + err = log_modify(conf, tmp, true); } clear_bit(WantReplacement, &rdev->flags); @@ -7988,6 +8028,7 @@ static int raid5_add_disk(struct mddev *mddev, struct md_rdev *rdev) int ret, err = -EEXIST; int disk; struct disk_info *p; + struct md_rdev *tmp; int first = 0; int last = conf->raid_disks - 1; @@ -8045,7 +8086,8 @@ static int raid5_add_disk(struct mddev *mddev, struct md_rdev *rdev) } for (disk = first; disk <= last; disk++) { p = conf->disks + disk; - if (test_bit(WantReplacement, &p->rdev->flags) && + tmp = rdev_mdlock_deref(mddev, p->rdev); + if (test_bit(WantReplacement, &tmp->flags) && p->replacement == NULL) { clear_bit(In_sync, &rdev->flags); set_bit(Replacement, &rdev->flags); @@ -8336,6 +8378,7 @@ static void end_reshape(struct r5conf *conf) static void raid5_finish_reshape(struct mddev *mddev) { struct r5conf *conf = mddev->private; + struct md_rdev *rdev; if (!test_bit(MD_RECOVERY_INTR, &mddev->recovery)) { @@ -8347,10 +8390,12 @@ static void raid5_finish_reshape(struct mddev *mddev) for (d = conf->raid_disks ; d < conf->raid_disks - mddev->delta_disks; d++) { - struct md_rdev *rdev = conf->disks[d].rdev; + rdev = rdev_mdlock_deref(mddev, + conf->disks[d].rdev); if (rdev) clear_bit(In_sync, &rdev->flags); - rdev = conf->disks[d].replacement; + rdev = rdev_mdlock_deref(mddev, + conf->disks[d].replacement); if (rdev) clear_bit(In_sync, &rdev->flags); } diff --git a/drivers/md/raid5.h b/drivers/md/raid5.h index 9e8486a9e445..638d29863503 100644 --- a/drivers/md/raid5.h +++ b/drivers/md/raid5.h @@ -473,7 +473,8 @@ enum { */ struct disk_info { - struct md_rdev *rdev, *replacement; + struct md_rdev __rcu *rdev; + struct md_rdev __rcu *replacement; struct page *extra_page; /* extra page to use in prexor */ }; @@ -560,6 +561,16 @@ struct r5pending_data { struct bio_list bios; }; +struct raid5_percpu { + struct page *spare_page; /* Used when checking P/Q in raid6 */ + void *scribble; /* space for constructing buffer + * lists and performing address + * conversions + */ + int scribble_obj_size; + local_lock_t lock; +}; + struct r5conf { struct hlist_head *stripe_hashtbl; /* only protect corresponding hash list and inactive_list */ @@ -635,15 +646,7 @@ struct r5conf { */ int recovery_disabled; /* per cpu variables */ - struct raid5_percpu { - struct page *spare_page; /* Used when checking P/Q in raid6 */ - void *scribble; /* space for constructing buffer - * lists and performing address - * conversions - */ - int scribble_obj_size; - local_lock_t lock; - } __percpu *percpu; + struct raid5_percpu __percpu *percpu; int scribble_disks; int scribble_sectors; struct hlist_node node; diff --git a/drivers/mmc/core/mmc_ops.c b/drivers/mmc/core/mmc_ops.c index 180d7e9d3400..81c55bfd6e0c 100644 --- a/drivers/mmc/core/mmc_ops.c +++ b/drivers/mmc/core/mmc_ops.c @@ -21,7 +21,7 @@ #define MMC_BKOPS_TIMEOUT_MS (120 * 1000) /* 120s */ #define MMC_SANITIZE_TIMEOUT_MS (240 * 1000) /* 240s */ -#define MMC_OP_COND_PERIOD_US (1 * 1000) /* 1ms */ +#define MMC_OP_COND_PERIOD_US (4 * 1000) /* 4ms */ #define MMC_OP_COND_TIMEOUT_MS 1000 /* 1s */ static const u8 tuning_blk_pattern_4bit[] = { diff --git a/drivers/mmc/core/queue.c b/drivers/mmc/core/queue.c index c69b2d9df6f1..a3d446005571 100644 --- a/drivers/mmc/core/queue.c +++ b/drivers/mmc/core/queue.c @@ -183,14 +183,13 @@ static void mmc_queue_setup_discard(struct request_queue *q, if (!max_discard) return; - blk_queue_flag_set(QUEUE_FLAG_DISCARD, q); blk_queue_max_discard_sectors(q, max_discard); q->limits.discard_granularity = card->pref_erase << 9; /* granularity must not be greater than max. discard */ if (card->pref_erase > max_discard) q->limits.discard_granularity = SECTOR_SIZE; if (mmc_can_secure_erase_trim(card)) - blk_queue_flag_set(QUEUE_FLAG_SECERASE, q); + blk_queue_max_secure_erase_sectors(q, max_discard); } static unsigned short mmc_get_max_segments(struct mmc_host *host) diff --git a/drivers/mtd/mtd_blkdevs.c b/drivers/mtd/mtd_blkdevs.c index 64d2b093f114..f73172111465 100644 --- a/drivers/mtd/mtd_blkdevs.c +++ b/drivers/mtd/mtd_blkdevs.c @@ -377,7 +377,6 @@ int add_mtd_blktrans_dev(struct mtd_blktrans_dev *new) blk_queue_flag_clear(QUEUE_FLAG_ADD_RANDOM, new->rq); if (tr->discard) { - blk_queue_flag_set(QUEUE_FLAG_DISCARD, new->rq); blk_queue_max_discard_sectors(new->rq, UINT_MAX); new->rq->limits.discard_granularity = tr->blksize; } diff --git a/drivers/net/can/m_can/m_can.c b/drivers/net/can/m_can/m_can.c index b3b5bc1c803b..088bb1bcf1ef 100644 --- a/drivers/net/can/m_can/m_can.c +++ b/drivers/net/can/m_can/m_can.c @@ -1495,34 +1495,22 @@ static int m_can_dev_setup(struct m_can_classdev *cdev) err = can_set_static_ctrlmode(dev, CAN_CTRLMODE_FD_NON_ISO); if (err) return err; - cdev->can.bittiming_const = cdev->bit_timing ? - cdev->bit_timing : &m_can_bittiming_const_30X; - - cdev->can.data_bittiming_const = cdev->data_timing ? - cdev->data_timing : - &m_can_data_bittiming_const_30X; + cdev->can.bittiming_const = &m_can_bittiming_const_30X; + cdev->can.data_bittiming_const = &m_can_data_bittiming_const_30X; break; case 31: /* CAN_CTRLMODE_FD_NON_ISO is fixed with M_CAN IP v3.1.x */ err = can_set_static_ctrlmode(dev, CAN_CTRLMODE_FD_NON_ISO); if (err) return err; - cdev->can.bittiming_const = cdev->bit_timing ? - cdev->bit_timing : &m_can_bittiming_const_31X; - - cdev->can.data_bittiming_const = cdev->data_timing ? - cdev->data_timing : - &m_can_data_bittiming_const_31X; + cdev->can.bittiming_const = &m_can_bittiming_const_31X; + cdev->can.data_bittiming_const = &m_can_data_bittiming_const_31X; break; case 32: case 33: /* Support both MCAN version v3.2.x and v3.3.0 */ - cdev->can.bittiming_const = cdev->bit_timing ? - cdev->bit_timing : &m_can_bittiming_const_31X; - - cdev->can.data_bittiming_const = cdev->data_timing ? - cdev->data_timing : - &m_can_data_bittiming_const_31X; + cdev->can.bittiming_const = &m_can_bittiming_const_31X; + cdev->can.data_bittiming_const = &m_can_data_bittiming_const_31X; cdev->can.ctrlmode_supported |= (m_can_niso_supported(cdev) ? diff --git a/drivers/net/can/m_can/m_can.h b/drivers/net/can/m_can/m_can.h index 2c5d40997168..d18b515e6ccc 100644 --- a/drivers/net/can/m_can/m_can.h +++ b/drivers/net/can/m_can/m_can.h @@ -85,9 +85,6 @@ struct m_can_classdev { struct sk_buff *tx_skb; struct phy *transceiver; - const struct can_bittiming_const *bit_timing; - const struct can_bittiming_const *data_timing; - struct m_can_ops *ops; int version; diff --git a/drivers/net/can/m_can/m_can_pci.c b/drivers/net/can/m_can/m_can_pci.c index b56a54d6c5a9..8f184a852a0a 100644 --- a/drivers/net/can/m_can/m_can_pci.c +++ b/drivers/net/can/m_can/m_can_pci.c @@ -18,14 +18,9 @@ #define M_CAN_PCI_MMIO_BAR 0 +#define M_CAN_CLOCK_FREQ_EHL 200000000 #define CTL_CSR_INT_CTL_OFFSET 0x508 -struct m_can_pci_config { - const struct can_bittiming_const *bit_timing; - const struct can_bittiming_const *data_timing; - unsigned int clock_freq; -}; - struct m_can_pci_priv { struct m_can_classdev cdev; @@ -89,40 +84,9 @@ static struct m_can_ops m_can_pci_ops = { .read_fifo = iomap_read_fifo, }; -static const struct can_bittiming_const m_can_bittiming_const_ehl = { - .name = KBUILD_MODNAME, - .tseg1_min = 2, /* Time segment 1 = prop_seg + phase_seg1 */ - .tseg1_max = 64, - .tseg2_min = 1, /* Time segment 2 = phase_seg2 */ - .tseg2_max = 128, - .sjw_max = 128, - .brp_min = 1, - .brp_max = 512, - .brp_inc = 1, -}; - -static const struct can_bittiming_const m_can_data_bittiming_const_ehl = { - .name = KBUILD_MODNAME, - .tseg1_min = 2, /* Time segment 1 = prop_seg + phase_seg1 */ - .tseg1_max = 16, - .tseg2_min = 1, /* Time segment 2 = phase_seg2 */ - .tseg2_max = 8, - .sjw_max = 4, - .brp_min = 1, - .brp_max = 32, - .brp_inc = 1, -}; - -static const struct m_can_pci_config m_can_pci_ehl = { - .bit_timing = &m_can_bittiming_const_ehl, - .data_timing = &m_can_data_bittiming_const_ehl, - .clock_freq = 200000000, -}; - static int m_can_pci_probe(struct pci_dev *pci, const struct pci_device_id *id) { struct device *dev = &pci->dev; - const struct m_can_pci_config *cfg; struct m_can_classdev *mcan_class; struct m_can_pci_priv *priv; void __iomem *base; @@ -150,8 +114,6 @@ static int m_can_pci_probe(struct pci_dev *pci, const struct pci_device_id *id) if (!mcan_class) return -ENOMEM; - cfg = (const struct m_can_pci_config *)id->driver_data; - priv = cdev_to_priv(mcan_class); priv->base = base; @@ -163,9 +125,7 @@ static int m_can_pci_probe(struct pci_dev *pci, const struct pci_device_id *id) mcan_class->dev = &pci->dev; mcan_class->net->irq = pci_irq_vector(pci, 0); mcan_class->pm_clock_support = 1; - mcan_class->bit_timing = cfg->bit_timing; - mcan_class->data_timing = cfg->data_timing; - mcan_class->can.clock.freq = cfg->clock_freq; + mcan_class->can.clock.freq = id->driver_data; mcan_class->ops = &m_can_pci_ops; pci_set_drvdata(pci, mcan_class); @@ -218,8 +178,8 @@ static SIMPLE_DEV_PM_OPS(m_can_pci_pm_ops, m_can_pci_suspend, m_can_pci_resume); static const struct pci_device_id m_can_pci_id_table[] = { - { PCI_VDEVICE(INTEL, 0x4bc1), (kernel_ulong_t)&m_can_pci_ehl, }, - { PCI_VDEVICE(INTEL, 0x4bc2), (kernel_ulong_t)&m_can_pci_ehl, }, + { PCI_VDEVICE(INTEL, 0x4bc1), M_CAN_CLOCK_FREQ_EHL, }, + { PCI_VDEVICE(INTEL, 0x4bc2), M_CAN_CLOCK_FREQ_EHL, }, { } /* Terminating Entry */ }; MODULE_DEVICE_TABLE(pci, m_can_pci_id_table); diff --git a/drivers/net/dsa/bcm_sf2.c b/drivers/net/dsa/bcm_sf2.c index cf82b1fa9725..87e81c636339 100644 --- a/drivers/net/dsa/bcm_sf2.c +++ b/drivers/net/dsa/bcm_sf2.c @@ -809,6 +809,9 @@ static void bcm_sf2_sw_mac_link_down(struct dsa_switch *ds, int port, struct bcm_sf2_priv *priv = bcm_sf2_to_priv(ds); u32 reg, offset; + if (priv->wol_ports_mask & BIT(port)) + return; + if (port != core_readl(priv, CORE_IMP0_PRT_ID)) { if (priv->type == BCM4908_DEVICE_ID || priv->type == BCM7445_DEVICE_ID) diff --git a/drivers/net/dsa/ocelot/felix.c b/drivers/net/dsa/ocelot/felix.c index 9e28219b223d..faccfb3f0158 100644 --- a/drivers/net/dsa/ocelot/felix.c +++ b/drivers/net/dsa/ocelot/felix.c @@ -403,6 +403,7 @@ static int felix_update_trapping_destinations(struct dsa_switch *ds, { struct ocelot *ocelot = ds->priv; struct felix *felix = ocelot_to_felix(ocelot); + struct ocelot_vcap_block *block_vcap_is2; struct ocelot_vcap_filter *trap; enum ocelot_mask_mode mask_mode; unsigned long port_mask; @@ -422,9 +423,13 @@ static int felix_update_trapping_destinations(struct dsa_switch *ds, /* We are sure that "cpu" was found, otherwise * dsa_tree_setup_default_cpu() would have failed earlier. */ + block_vcap_is2 = &ocelot->block[VCAP_IS2]; /* Make sure all traps are set up for that destination */ - list_for_each_entry(trap, &ocelot->traps, trap_list) { + list_for_each_entry(trap, &block_vcap_is2->rules, list) { + if (!trap->is_trap) + continue; + /* Figure out the current trapping destination */ if (using_tag_8021q) { /* Redirect to the tag_8021q CPU port. If timestamps diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_pci_func.c b/drivers/net/ethernet/aquantia/atlantic/aq_pci_func.c index 3a529ee8c834..831833911a52 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_pci_func.c +++ b/drivers/net/ethernet/aquantia/atlantic/aq_pci_func.c @@ -449,7 +449,7 @@ static int aq_pm_freeze(struct device *dev) static int aq_pm_suspend_poweroff(struct device *dev) { - return aq_suspend_common(dev, false); + return aq_suspend_common(dev, true); } static int aq_pm_thaw(struct device *dev) @@ -459,7 +459,7 @@ static int aq_pm_thaw(struct device *dev) static int aq_pm_resume_restore(struct device *dev) { - return atl_resume_common(dev, false); + return atl_resume_common(dev, true); } static const struct dev_pm_ops aq_pm_ops = { diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_ring.c b/drivers/net/ethernet/aquantia/atlantic/aq_ring.c index 77e76c9efd32..8201ce7adb77 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_ring.c +++ b/drivers/net/ethernet/aquantia/atlantic/aq_ring.c @@ -346,7 +346,6 @@ int aq_ring_rx_clean(struct aq_ring_s *self, int budget) { struct net_device *ndev = aq_nic_get_ndev(self->aq_nic); - bool is_rsc_completed = true; int err = 0; for (; (self->sw_head != self->hw_head) && budget; @@ -364,12 +363,17 @@ int aq_ring_rx_clean(struct aq_ring_s *self, continue; if (!buff->is_eop) { + unsigned int frag_cnt = 0U; buff_ = buff; do { + bool is_rsc_completed = true; + if (buff_->next >= self->size) { err = -EIO; goto err_exit; } + + frag_cnt++; next_ = buff_->next, buff_ = &self->buff_ring[next_]; is_rsc_completed = @@ -377,18 +381,17 @@ int aq_ring_rx_clean(struct aq_ring_s *self, next_, self->hw_head); - if (unlikely(!is_rsc_completed)) - break; + if (unlikely(!is_rsc_completed) || + frag_cnt > MAX_SKB_FRAGS) { + err = 0; + goto err_exit; + } buff->is_error |= buff_->is_error; buff->is_cso_err |= buff_->is_cso_err; } while (!buff_->is_eop); - if (!is_rsc_completed) { - err = 0; - goto err_exit; - } if (buff->is_error || (buff->is_lro && buff->is_cso_err)) { buff_ = buff; @@ -446,7 +449,7 @@ int aq_ring_rx_clean(struct aq_ring_s *self, ALIGN(hdr_len, sizeof(long))); if (buff->len - hdr_len > 0) { - skb_add_rx_frag(skb, 0, buff->rxdata.page, + skb_add_rx_frag(skb, i++, buff->rxdata.page, buff->rxdata.pg_off + hdr_len, buff->len - hdr_len, AQ_CFG_RX_FRAME_MAX); @@ -455,7 +458,6 @@ int aq_ring_rx_clean(struct aq_ring_s *self, if (!buff->is_eop) { buff_ = buff; - i = 1U; do { next_ = buff_->next; buff_ = &self->buff_ring[next_]; diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c index d875ce3ec759..15ede7285fb5 100644 --- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c +++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c @@ -889,6 +889,13 @@ int hw_atl_b0_hw_ring_tx_head_update(struct aq_hw_s *self, err = -ENXIO; goto err_exit; } + + /* Validate that the new hw_head_ is reasonable. */ + if (hw_head_ >= ring->size) { + err = -ENXIO; + goto err_exit; + } + ring->hw_head = hw_head_; err = aq_hw_err_from_flags(self); diff --git a/drivers/net/ethernet/broadcom/bcmsysport.c b/drivers/net/ethernet/broadcom/bcmsysport.c index 60dde29974bf..df51be3cbe06 100644 --- a/drivers/net/ethernet/broadcom/bcmsysport.c +++ b/drivers/net/ethernet/broadcom/bcmsysport.c @@ -2585,8 +2585,10 @@ static int bcm_sysport_probe(struct platform_device *pdev) device_set_wakeup_capable(&pdev->dev, 1); priv->wol_clk = devm_clk_get_optional(&pdev->dev, "sw_sysportwol"); - if (IS_ERR(priv->wol_clk)) - return PTR_ERR(priv->wol_clk); + if (IS_ERR(priv->wol_clk)) { + ret = PTR_ERR(priv->wol_clk); + goto err_deregister_fixed_link; + } /* Set the needed headroom once and for all */ BUILD_BUG_ON(sizeof(struct bcm_tsb) != 8); diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.c b/drivers/net/ethernet/broadcom/genet/bcmgenet.c index bf1ec8fdc2ad..e87e46c47387 100644 --- a/drivers/net/ethernet/broadcom/genet/bcmgenet.c +++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.c @@ -3999,6 +3999,10 @@ static int bcmgenet_probe(struct platform_device *pdev) goto err; } priv->wol_irq = platform_get_irq_optional(pdev, 2); + if (priv->wol_irq == -EPROBE_DEFER) { + err = priv->wol_irq; + goto err; + } priv->base = devm_platform_ioremap_resource(pdev, 0); if (IS_ERR(priv->base)) { diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c index e475be29845c..61284baa0496 100644 --- a/drivers/net/ethernet/cadence/macb_main.c +++ b/drivers/net/ethernet/cadence/macb_main.c @@ -1219,7 +1219,6 @@ static void gem_rx_refill(struct macb_queue *queue) /* Make hw descriptor updates visible to CPU */ rmb(); - queue->rx_prepared_head++; desc = macb_rx_desc(queue, entry); if (!queue->rx_skbuff[entry]) { @@ -1258,6 +1257,7 @@ static void gem_rx_refill(struct macb_queue *queue) dma_wmb(); desc->addr &= ~MACB_BIT(RX_USED); } + queue->rx_prepared_head++; } /* Make descriptor updates visible to hardware */ diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c index e7b4e3ed056c..8d719f82854a 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c +++ b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c @@ -2793,14 +2793,14 @@ int t4_get_raw_vpd_params(struct adapter *adapter, struct vpd_params *p) goto out; na = ret; - memcpy(p->id, vpd + id, min_t(int, id_len, ID_LEN)); + memcpy(p->id, vpd + id, min_t(unsigned int, id_len, ID_LEN)); strim(p->id); - memcpy(p->sn, vpd + sn, min_t(int, sn_len, SERNUM_LEN)); + memcpy(p->sn, vpd + sn, min_t(unsigned int, sn_len, SERNUM_LEN)); strim(p->sn); - memcpy(p->pn, vpd + pn, min_t(int, pn_len, PN_LEN)); + memcpy(p->pn, vpd + pn, min_t(unsigned int, pn_len, PN_LEN)); strim(p->pn); - memcpy(p->na, vpd + na, min_t(int, na_len, MACADDR_LEN)); - strim((char *)p->na); + memcpy(p->na, vpd + na, min_t(unsigned int, na_len, MACADDR_LEN)); + strim(p->na); out: vfree(vpd); diff --git a/drivers/net/ethernet/dec/tulip/tulip_core.c b/drivers/net/ethernet/dec/tulip/tulip_core.c index 79df5a72877b..0040dcaab945 100644 --- a/drivers/net/ethernet/dec/tulip/tulip_core.c +++ b/drivers/net/ethernet/dec/tulip/tulip_core.c @@ -1399,8 +1399,10 @@ static int tulip_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) /* alloc_etherdev ensures aligned and zeroed private structures */ dev = alloc_etherdev (sizeof (*tp)); - if (!dev) + if (!dev) { + pci_disable_device(pdev); return -ENOMEM; + } SET_NETDEV_DEV(dev, &pdev->dev); if (pci_resource_len (pdev, 0) < tulip_tbl[chip_idx].io_size) { @@ -1785,6 +1787,7 @@ err_out_free_res: err_out_free_netdev: free_netdev (dev); + pci_disable_device(pdev); return -ENODEV; } diff --git a/drivers/net/ethernet/faraday/ftgmac100.c b/drivers/net/ethernet/faraday/ftgmac100.c index caf48023f8ea..5231818943c6 100644 --- a/drivers/net/ethernet/faraday/ftgmac100.c +++ b/drivers/net/ethernet/faraday/ftgmac100.c @@ -1928,6 +1928,11 @@ static int ftgmac100_probe(struct platform_device *pdev) /* AST2400 doesn't have working HW checksum generation */ if (np && (of_device_is_compatible(np, "aspeed,ast2400-mac"))) netdev->hw_features &= ~NETIF_F_HW_CSUM; + + /* AST2600 tx checksum with NCSI is broken */ + if (priv->use_ncsi && of_device_is_compatible(np, "aspeed,ast2600-mac")) + netdev->hw_features &= ~NETIF_F_HW_CSUM; + if (np && of_get_property(np, "no-hw-checksum", NULL)) netdev->hw_features &= ~(NETIF_F_HW_CSUM | NETIF_F_RXCSUM); netdev->features |= netdev->hw_features; diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index 6778df2177a1..98871f014994 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -7549,42 +7549,43 @@ static void i40e_free_macvlan_channels(struct i40e_vsi *vsi) static int i40e_fwd_ring_up(struct i40e_vsi *vsi, struct net_device *vdev, struct i40e_fwd_adapter *fwd) { + struct i40e_channel *ch = NULL, *ch_tmp, *iter; int ret = 0, num_tc = 1, i, aq_err; - struct i40e_channel *ch, *ch_tmp; struct i40e_pf *pf = vsi->back; struct i40e_hw *hw = &pf->hw; - if (list_empty(&vsi->macvlan_list)) - return -EINVAL; - /* Go through the list and find an available channel */ - list_for_each_entry_safe(ch, ch_tmp, &vsi->macvlan_list, list) { - if (!i40e_is_channel_macvlan(ch)) { - ch->fwd = fwd; + list_for_each_entry_safe(iter, ch_tmp, &vsi->macvlan_list, list) { + if (!i40e_is_channel_macvlan(iter)) { + iter->fwd = fwd; /* record configuration for macvlan interface in vdev */ for (i = 0; i < num_tc; i++) netdev_bind_sb_channel_queue(vsi->netdev, vdev, i, - ch->num_queue_pairs, - ch->base_queue); - for (i = 0; i < ch->num_queue_pairs; i++) { + iter->num_queue_pairs, + iter->base_queue); + for (i = 0; i < iter->num_queue_pairs; i++) { struct i40e_ring *tx_ring, *rx_ring; u16 pf_q; - pf_q = ch->base_queue + i; + pf_q = iter->base_queue + i; /* Get to TX ring ptr */ tx_ring = vsi->tx_rings[pf_q]; - tx_ring->ch = ch; + tx_ring->ch = iter; /* Get the RX ring ptr */ rx_ring = vsi->rx_rings[pf_q]; - rx_ring->ch = ch; + rx_ring->ch = iter; } + ch = iter; break; } } + if (!ch) + return -EINVAL; + /* Guarantee all rings are updated before we update the * MAC address filter. */ diff --git a/drivers/net/ethernet/intel/ice/ice.h b/drivers/net/ethernet/intel/ice/ice.h index 8ed3c9ab7ff7..a895e3a8e988 100644 --- a/drivers/net/ethernet/intel/ice/ice.h +++ b/drivers/net/ethernet/intel/ice/ice.h @@ -540,6 +540,7 @@ struct ice_pf { struct mutex avail_q_mutex; /* protects access to avail_[rx|tx]qs */ struct mutex sw_mutex; /* lock for protecting VSI alloc flow */ struct mutex tc_mutex; /* lock to protect TC changes */ + struct mutex adev_mutex; /* lock to protect aux device access */ u32 msg_enable; struct ice_ptp ptp; struct tty_driver *ice_gnss_tty_driver; diff --git a/drivers/net/ethernet/intel/ice/ice_idc.c b/drivers/net/ethernet/intel/ice/ice_idc.c index 25a436d342c2..3e3b2ed4cd5d 100644 --- a/drivers/net/ethernet/intel/ice/ice_idc.c +++ b/drivers/net/ethernet/intel/ice/ice_idc.c @@ -37,14 +37,17 @@ void ice_send_event_to_aux(struct ice_pf *pf, struct iidc_event *event) if (WARN_ON_ONCE(!in_task())) return; + mutex_lock(&pf->adev_mutex); if (!pf->adev) - return; + goto finish; device_lock(&pf->adev->dev); iadrv = ice_get_auxiliary_drv(pf); if (iadrv && iadrv->event_handler) iadrv->event_handler(pf, event); device_unlock(&pf->adev->dev); +finish: + mutex_unlock(&pf->adev_mutex); } /** @@ -290,7 +293,6 @@ int ice_plug_aux_dev(struct ice_pf *pf) return -ENOMEM; adev = &iadev->adev; - pf->adev = adev; iadev->pf = pf; adev->id = pf->aux_idx; @@ -300,18 +302,20 @@ int ice_plug_aux_dev(struct ice_pf *pf) ret = auxiliary_device_init(adev); if (ret) { - pf->adev = NULL; kfree(iadev); return ret; } ret = auxiliary_device_add(adev); if (ret) { - pf->adev = NULL; auxiliary_device_uninit(adev); return ret; } + mutex_lock(&pf->adev_mutex); + pf->adev = adev; + mutex_unlock(&pf->adev_mutex); + return 0; } @@ -320,12 +324,17 @@ int ice_plug_aux_dev(struct ice_pf *pf) */ void ice_unplug_aux_dev(struct ice_pf *pf) { - if (!pf->adev) - return; + struct auxiliary_device *adev; - auxiliary_device_delete(pf->adev); - auxiliary_device_uninit(pf->adev); + mutex_lock(&pf->adev_mutex); + adev = pf->adev; pf->adev = NULL; + mutex_unlock(&pf->adev_mutex); + + if (adev) { + auxiliary_device_delete(adev); + auxiliary_device_uninit(adev); + } } /** diff --git a/drivers/net/ethernet/intel/ice/ice_lib.c b/drivers/net/ethernet/intel/ice/ice_lib.c index 6d19c58ccacd..454e01ae09b9 100644 --- a/drivers/net/ethernet/intel/ice/ice_lib.c +++ b/drivers/net/ethernet/intel/ice/ice_lib.c @@ -3043,8 +3043,8 @@ ice_vsi_rebuild_get_coalesce(struct ice_vsi *vsi, ice_for_each_q_vector(vsi, i) { struct ice_q_vector *q_vector = vsi->q_vectors[i]; - coalesce[i].itr_tx = q_vector->tx.itr_setting; - coalesce[i].itr_rx = q_vector->rx.itr_setting; + coalesce[i].itr_tx = q_vector->tx.itr_settings; + coalesce[i].itr_rx = q_vector->rx.itr_settings; coalesce[i].intrl = q_vector->intrl; if (i < vsi->num_txq) @@ -3100,21 +3100,21 @@ ice_vsi_rebuild_set_coalesce(struct ice_vsi *vsi, */ if (i < vsi->alloc_rxq && coalesce[i].rx_valid) { rc = &vsi->q_vectors[i]->rx; - rc->itr_setting = coalesce[i].itr_rx; + rc->itr_settings = coalesce[i].itr_rx; ice_write_itr(rc, rc->itr_setting); } else if (i < vsi->alloc_rxq) { rc = &vsi->q_vectors[i]->rx; - rc->itr_setting = coalesce[0].itr_rx; + rc->itr_settings = coalesce[0].itr_rx; ice_write_itr(rc, rc->itr_setting); } if (i < vsi->alloc_txq && coalesce[i].tx_valid) { rc = &vsi->q_vectors[i]->tx; - rc->itr_setting = coalesce[i].itr_tx; + rc->itr_settings = coalesce[i].itr_tx; ice_write_itr(rc, rc->itr_setting); } else if (i < vsi->alloc_txq) { rc = &vsi->q_vectors[i]->tx; - rc->itr_setting = coalesce[0].itr_tx; + rc->itr_settings = coalesce[0].itr_tx; ice_write_itr(rc, rc->itr_setting); } @@ -3128,12 +3128,12 @@ ice_vsi_rebuild_set_coalesce(struct ice_vsi *vsi, for (; i < vsi->num_q_vectors; i++) { /* transmit */ rc = &vsi->q_vectors[i]->tx; - rc->itr_setting = coalesce[0].itr_tx; + rc->itr_settings = coalesce[0].itr_tx; ice_write_itr(rc, rc->itr_setting); /* receive */ rc = &vsi->q_vectors[i]->rx; - rc->itr_setting = coalesce[0].itr_rx; + rc->itr_settings = coalesce[0].itr_rx; ice_write_itr(rc, rc->itr_setting); vsi->q_vectors[i]->intrl = coalesce[0].intrl; diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c index 9a0a358a15c2..963a5f40e071 100644 --- a/drivers/net/ethernet/intel/ice/ice_main.c +++ b/drivers/net/ethernet/intel/ice/ice_main.c @@ -3769,6 +3769,7 @@ u16 ice_get_avail_rxq_count(struct ice_pf *pf) static void ice_deinit_pf(struct ice_pf *pf) { ice_service_task_stop(pf); + mutex_destroy(&pf->adev_mutex); mutex_destroy(&pf->sw_mutex); mutex_destroy(&pf->tc_mutex); mutex_destroy(&pf->avail_q_mutex); @@ -3847,6 +3848,7 @@ static int ice_init_pf(struct ice_pf *pf) mutex_init(&pf->sw_mutex); mutex_init(&pf->tc_mutex); + mutex_init(&pf->adev_mutex); INIT_HLIST_HEAD(&pf->aq_wait_list); spin_lock_init(&pf->aq_wait_lock); @@ -6170,9 +6172,10 @@ static int ice_up_complete(struct ice_vsi *vsi) ice_ptp_link_change(pf, pf->hw.pf_id, true); } - /* clear this now, and the first stats read will be used as baseline */ - vsi->stat_offsets_loaded = false; - + /* Perform an initial read of the statistics registers now to + * set the baseline so counters are ready when interface is up + */ + ice_update_eth_stats(vsi); ice_service_task_schedule(pf); return 0; diff --git a/drivers/net/ethernet/intel/ice/ice_ptp.c b/drivers/net/ethernet/intel/ice/ice_ptp.c index a1cd33273ca4..662947c882e8 100644 --- a/drivers/net/ethernet/intel/ice/ice_ptp.c +++ b/drivers/net/ethernet/intel/ice/ice_ptp.c @@ -500,12 +500,19 @@ ice_ptp_read_src_clk_reg(struct ice_pf *pf, struct ptp_system_timestamp *sts) * This function must be called periodically to ensure that the cached value * is never more than 2 seconds old. It must also be called whenever the PHC * time has been changed. + * + * Return: + * * 0 - OK, successfully updated + * * -EAGAIN - PF was busy, need to reschedule the update */ -static void ice_ptp_update_cached_phctime(struct ice_pf *pf) +static int ice_ptp_update_cached_phctime(struct ice_pf *pf) { u64 systime; int i; + if (test_and_set_bit(ICE_CFG_BUSY, pf->state)) + return -EAGAIN; + /* Read the current PHC time */ systime = ice_ptp_read_src_clk_reg(pf, NULL); @@ -528,6 +535,9 @@ static void ice_ptp_update_cached_phctime(struct ice_pf *pf) WRITE_ONCE(vsi->rx_rings[j]->cached_phctime, systime); } } + clear_bit(ICE_CFG_BUSY, pf->state); + + return 0; } /** @@ -2287,6 +2297,7 @@ ice_ptp_init_tx_e810(struct ice_pf *pf, struct ice_ptp_tx *tx) /** * ice_ptp_tx_tstamp_cleanup - Cleanup old timestamp requests that got dropped + * @hw: pointer to the hw struct * @tx: PTP Tx tracker to clean up * * Loop through the Tx timestamp requests and see if any of them have been @@ -2295,7 +2306,7 @@ ice_ptp_init_tx_e810(struct ice_pf *pf, struct ice_ptp_tx *tx) * timestamp will never be captured. This might happen if the packet gets * discarded before it reaches the PHY timestamping block. */ -static void ice_ptp_tx_tstamp_cleanup(struct ice_ptp_tx *tx) +static void ice_ptp_tx_tstamp_cleanup(struct ice_hw *hw, struct ice_ptp_tx *tx) { u8 idx; @@ -2304,11 +2315,16 @@ static void ice_ptp_tx_tstamp_cleanup(struct ice_ptp_tx *tx) for_each_set_bit(idx, tx->in_use, tx->len) { struct sk_buff *skb; + u64 raw_tstamp; /* Check if this SKB has been waiting for too long */ if (time_is_after_jiffies(tx->tstamps[idx].start + 2 * HZ)) continue; + /* Read tstamp to be able to use this register again */ + ice_read_phy_tstamp(hw, tx->quad, idx + tx->quad_offset, + &raw_tstamp); + spin_lock(&tx->lock); skb = tx->tstamps[idx].skb; tx->tstamps[idx].skb = NULL; @@ -2324,17 +2340,18 @@ static void ice_ptp_periodic_work(struct kthread_work *work) { struct ice_ptp *ptp = container_of(work, struct ice_ptp, work.work); struct ice_pf *pf = container_of(ptp, struct ice_pf, ptp); + int err; if (!test_bit(ICE_FLAG_PTP, pf->flags)) return; - ice_ptp_update_cached_phctime(pf); + err = ice_ptp_update_cached_phctime(pf); - ice_ptp_tx_tstamp_cleanup(&pf->ptp.port.tx); + ice_ptp_tx_tstamp_cleanup(&pf->hw, &pf->ptp.port.tx); - /* Run twice a second */ + /* Run twice a second or reschedule if phc update failed */ kthread_queue_delayed_work(ptp->kworker, &ptp->work, - msecs_to_jiffies(500)); + msecs_to_jiffies(err ? 10 : 500)); } /** diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.h b/drivers/net/ethernet/intel/ice/ice_txrx.h index cead3eb149bd..ffb3f6a589da 100644 --- a/drivers/net/ethernet/intel/ice/ice_txrx.h +++ b/drivers/net/ethernet/intel/ice/ice_txrx.h @@ -384,9 +384,14 @@ struct ice_ring_container { /* this matches the maximum number of ITR bits, but in usec * values, so it is shifted left one bit (bit zero is ignored) */ - u16 itr_setting:13; - u16 itr_reserved:2; - u16 itr_mode:1; + union { + struct { + u16 itr_setting:13; + u16 itr_reserved:2; + u16 itr_mode:1; + }; + u16 itr_settings; + }; enum ice_container_type type; }; diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl.c b/drivers/net/ethernet/intel/ice/ice_virtchnl.c index b72606c9e6d0..2889e050a4c9 100644 --- a/drivers/net/ethernet/intel/ice/ice_virtchnl.c +++ b/drivers/net/ethernet/intel/ice/ice_virtchnl.c @@ -1308,12 +1308,51 @@ error_param: } /** + * ice_vf_vsi_dis_single_txq - disable a single Tx queue + * @vf: VF to disable queue for + * @vsi: VSI for the VF + * @q_id: VF relative (0-based) queue ID + * + * Attempt to disable the Tx queue passed in. If the Tx queue was successfully + * disabled then clear q_id bit in the enabled queues bitmap and return + * success. Otherwise return error. + */ +static int +ice_vf_vsi_dis_single_txq(struct ice_vf *vf, struct ice_vsi *vsi, u16 q_id) +{ + struct ice_txq_meta txq_meta = { 0 }; + struct ice_tx_ring *ring; + int err; + + if (!test_bit(q_id, vf->txq_ena)) + dev_dbg(ice_pf_to_dev(vsi->back), "Queue %u on VSI %u is not enabled, but stopping it anyway\n", + q_id, vsi->vsi_num); + + ring = vsi->tx_rings[q_id]; + if (!ring) + return -EINVAL; + + ice_fill_txq_meta(vsi, ring, &txq_meta); + + err = ice_vsi_stop_tx_ring(vsi, ICE_NO_RESET, vf->vf_id, ring, &txq_meta); + if (err) { + dev_err(ice_pf_to_dev(vsi->back), "Failed to stop Tx ring %d on VSI %d\n", + q_id, vsi->vsi_num); + return err; + } + + /* Clear enabled queues flag */ + clear_bit(q_id, vf->txq_ena); + + return 0; +} + +/** * ice_vc_dis_qs_msg * @vf: pointer to the VF info * @msg: pointer to the msg buffer * - * called from the VF to disable all or specific - * queue(s) + * called from the VF to disable all or specific queue(s) */ static int ice_vc_dis_qs_msg(struct ice_vf *vf, u8 *msg) { @@ -1350,30 +1389,15 @@ static int ice_vc_dis_qs_msg(struct ice_vf *vf, u8 *msg) q_map = vqs->tx_queues; for_each_set_bit(vf_q_id, &q_map, ICE_MAX_RSS_QS_PER_VF) { - struct ice_tx_ring *ring = vsi->tx_rings[vf_q_id]; - struct ice_txq_meta txq_meta = { 0 }; - if (!ice_vc_isvalid_q_id(vf, vqs->vsi_id, vf_q_id)) { v_ret = VIRTCHNL_STATUS_ERR_PARAM; goto error_param; } - if (!test_bit(vf_q_id, vf->txq_ena)) - dev_dbg(ice_pf_to_dev(vsi->back), "Queue %u on VSI %u is not enabled, but stopping it anyway\n", - vf_q_id, vsi->vsi_num); - - ice_fill_txq_meta(vsi, ring, &txq_meta); - - if (ice_vsi_stop_tx_ring(vsi, ICE_NO_RESET, vf->vf_id, - ring, &txq_meta)) { - dev_err(ice_pf_to_dev(vsi->back), "Failed to stop Tx ring %d on VSI %d\n", - vf_q_id, vsi->vsi_num); + if (ice_vf_vsi_dis_single_txq(vf, vsi, vf_q_id)) { v_ret = VIRTCHNL_STATUS_ERR_PARAM; goto error_param; } - - /* Clear enabled queues flag */ - clear_bit(vf_q_id, vf->txq_ena); } } @@ -1622,6 +1646,14 @@ static int ice_vc_cfg_qs_msg(struct ice_vf *vf, u8 *msg) if (qpi->txq.ring_len > 0) { vsi->tx_rings[i]->dma = qpi->txq.dma_ring_addr; vsi->tx_rings[i]->count = qpi->txq.ring_len; + + /* Disable any existing queue first */ + if (ice_vf_vsi_dis_single_txq(vf, vsi, q_idx)) { + v_ret = VIRTCHNL_STATUS_ERR_PARAM; + goto error_param; + } + + /* Configure a queue with the requested settings */ if (ice_vsi_cfg_single_txq(vsi, vsi->tx_rings, q_idx)) { v_ret = VIRTCHNL_STATUS_ERR_PARAM; goto error_param; diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c index 34b33b21e0dc..68be2976f539 100644 --- a/drivers/net/ethernet/intel/igb/igb_main.c +++ b/drivers/net/ethernet/intel/igb/igb_main.c @@ -5505,7 +5505,8 @@ static void igb_watchdog_task(struct work_struct *work) break; } - if (adapter->link_speed != SPEED_1000) + if (adapter->link_speed != SPEED_1000 || + !hw->phy.ops.read_reg) goto no_wait; /* wait for Remote receiver status OK */ diff --git a/drivers/net/ethernet/mediatek/mtk_ppe.c b/drivers/net/ethernet/mediatek/mtk_ppe.c index 3ad10c793308..66298e2235c9 100644 --- a/drivers/net/ethernet/mediatek/mtk_ppe.c +++ b/drivers/net/ethernet/mediatek/mtk_ppe.c @@ -395,7 +395,7 @@ static void mtk_ppe_init_foe_table(struct mtk_ppe *ppe) static const u8 skip[] = { 12, 25, 38, 51, 76, 89, 102 }; int i, k; - memset(ppe->foe_table, 0, MTK_PPE_ENTRIES * sizeof(ppe->foe_table)); + memset(ppe->foe_table, 0, MTK_PPE_ENTRIES * sizeof(*ppe->foe_table)); if (!IS_ENABLED(CONFIG_SOC_MT7621)) return; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/ct_fs_smfs.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/ct_fs_smfs.c index 59988e24b704..bec9ed0103a9 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/ct_fs_smfs.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/ct_fs_smfs.c @@ -23,7 +23,7 @@ struct mlx5_ct_fs_smfs_matcher { }; struct mlx5_ct_fs_smfs_matchers { - struct mlx5_ct_fs_smfs_matcher smfs_matchers[4]; + struct mlx5_ct_fs_smfs_matcher smfs_matchers[6]; struct list_head used; }; @@ -44,7 +44,8 @@ struct mlx5_ct_fs_smfs_rule { }; static inline void -mlx5_ct_fs_smfs_fill_mask(struct mlx5_ct_fs *fs, struct mlx5_flow_spec *spec, bool ipv4, bool tcp) +mlx5_ct_fs_smfs_fill_mask(struct mlx5_ct_fs *fs, struct mlx5_flow_spec *spec, bool ipv4, bool tcp, + bool gre) { void *headers_c = MLX5_ADDR_OF(fte_match_param, spec->match_criteria, outer_headers); @@ -77,7 +78,7 @@ mlx5_ct_fs_smfs_fill_mask(struct mlx5_ct_fs *fs, struct mlx5_flow_spec *spec, bo MLX5_SET_TO_ONES(fte_match_set_lyr_2_4, headers_c, tcp_dport); MLX5_SET(fte_match_set_lyr_2_4, headers_c, tcp_flags, ntohs(MLX5_CT_TCP_FLAGS_MASK)); - } else { + } else if (!gre) { MLX5_SET_TO_ONES(fte_match_set_lyr_2_4, headers_c, udp_sport); MLX5_SET_TO_ONES(fte_match_set_lyr_2_4, headers_c, udp_dport); } @@ -87,7 +88,7 @@ mlx5_ct_fs_smfs_fill_mask(struct mlx5_ct_fs *fs, struct mlx5_flow_spec *spec, bo static struct mlx5dr_matcher * mlx5_ct_fs_smfs_matcher_create(struct mlx5_ct_fs *fs, struct mlx5dr_table *tbl, bool ipv4, - bool tcp, u32 priority) + bool tcp, bool gre, u32 priority) { struct mlx5dr_matcher *dr_matcher; struct mlx5_flow_spec *spec; @@ -96,7 +97,7 @@ mlx5_ct_fs_smfs_matcher_create(struct mlx5_ct_fs *fs, struct mlx5dr_table *tbl, if (!spec) return ERR_PTR(-ENOMEM); - mlx5_ct_fs_smfs_fill_mask(fs, spec, ipv4, tcp); + mlx5_ct_fs_smfs_fill_mask(fs, spec, ipv4, tcp, gre); spec->match_criteria_enable = MLX5_MATCH_MISC_PARAMETERS_2 | MLX5_MATCH_OUTER_HEADERS; dr_matcher = mlx5_smfs_matcher_create(tbl, priority, spec); @@ -108,7 +109,7 @@ mlx5_ct_fs_smfs_matcher_create(struct mlx5_ct_fs *fs, struct mlx5dr_table *tbl, } static struct mlx5_ct_fs_smfs_matcher * -mlx5_ct_fs_smfs_matcher_get(struct mlx5_ct_fs *fs, bool nat, bool ipv4, bool tcp) +mlx5_ct_fs_smfs_matcher_get(struct mlx5_ct_fs *fs, bool nat, bool ipv4, bool tcp, bool gre) { struct mlx5_ct_fs_smfs *fs_smfs = mlx5_ct_fs_priv(fs); struct mlx5_ct_fs_smfs_matcher *m, *smfs_matcher; @@ -119,7 +120,7 @@ mlx5_ct_fs_smfs_matcher_get(struct mlx5_ct_fs *fs, bool nat, bool ipv4, bool tcp int prio; matchers = nat ? &fs_smfs->matchers_nat : &fs_smfs->matchers; - smfs_matcher = &matchers->smfs_matchers[ipv4 * 2 + tcp]; + smfs_matcher = &matchers->smfs_matchers[ipv4 * 3 + tcp * 2 + gre]; if (refcount_inc_not_zero(&smfs_matcher->ref)) return smfs_matcher; @@ -145,11 +146,11 @@ mlx5_ct_fs_smfs_matcher_get(struct mlx5_ct_fs *fs, bool nat, bool ipv4, bool tcp } tbl = nat ? fs_smfs->ct_nat_tbl : fs_smfs->ct_tbl; - dr_matcher = mlx5_ct_fs_smfs_matcher_create(fs, tbl, ipv4, tcp, prio); + dr_matcher = mlx5_ct_fs_smfs_matcher_create(fs, tbl, ipv4, tcp, gre, prio); if (IS_ERR(dr_matcher)) { netdev_warn(fs->netdev, - "ct_fs_smfs: failed to create matcher (nat %d, ipv4 %d, tcp %d), err: %ld\n", - nat, ipv4, tcp, PTR_ERR(dr_matcher)); + "ct_fs_smfs: failed to create matcher (nat %d, ipv4 %d, tcp %d, gre %d), err: %ld\n", + nat, ipv4, tcp, gre, PTR_ERR(dr_matcher)); smfs_matcher = ERR_CAST(dr_matcher); goto out_unlock; @@ -222,16 +223,17 @@ mlx5_ct_fs_smfs_destroy(struct mlx5_ct_fs *fs) static inline bool mlx5_tc_ct_valid_used_dissector_keys(const u32 used_keys) { -#define DISSECTOR_BIT(name) BIT(FLOW_DISSECTOR_KEY_ ## name) - const u32 basic_keys = DISSECTOR_BIT(BASIC) | DISSECTOR_BIT(CONTROL) | - DISSECTOR_BIT(PORTS) | DISSECTOR_BIT(META); - const u32 ipv4_tcp = basic_keys | DISSECTOR_BIT(IPV4_ADDRS) | DISSECTOR_BIT(TCP); - const u32 ipv4_udp = basic_keys | DISSECTOR_BIT(IPV4_ADDRS); - const u32 ipv6_tcp = basic_keys | DISSECTOR_BIT(IPV6_ADDRS) | DISSECTOR_BIT(TCP); - const u32 ipv6_udp = basic_keys | DISSECTOR_BIT(IPV6_ADDRS); +#define DISS_BIT(name) BIT(FLOW_DISSECTOR_KEY_ ## name) + const u32 basic_keys = DISS_BIT(BASIC) | DISS_BIT(CONTROL) | DISS_BIT(META); + const u32 ipv4_tcp = basic_keys | DISS_BIT(IPV4_ADDRS) | DISS_BIT(PORTS) | DISS_BIT(TCP); + const u32 ipv6_tcp = basic_keys | DISS_BIT(IPV6_ADDRS) | DISS_BIT(PORTS) | DISS_BIT(TCP); + const u32 ipv4_udp = basic_keys | DISS_BIT(IPV4_ADDRS) | DISS_BIT(PORTS); + const u32 ipv6_udp = basic_keys | DISS_BIT(IPV6_ADDRS) | DISS_BIT(PORTS); + const u32 ipv4_gre = basic_keys | DISS_BIT(IPV4_ADDRS); + const u32 ipv6_gre = basic_keys | DISS_BIT(IPV6_ADDRS); return (used_keys == ipv4_tcp || used_keys == ipv4_udp || used_keys == ipv6_tcp || - used_keys == ipv6_udp); + used_keys == ipv6_udp || used_keys == ipv4_gre || used_keys == ipv6_gre); } static bool @@ -254,20 +256,24 @@ mlx5_ct_fs_smfs_ct_validate_flow_rule(struct mlx5_ct_fs *fs, struct flow_rule *f flow_rule_match_control(flow_rule, &control); flow_rule_match_ipv4_addrs(flow_rule, &ipv4_addrs); flow_rule_match_ipv6_addrs(flow_rule, &ipv6_addrs); - flow_rule_match_ports(flow_rule, &ports); - flow_rule_match_tcp(flow_rule, &tcp); + if (basic.key->ip_proto != IPPROTO_GRE) + flow_rule_match_ports(flow_rule, &ports); + if (basic.key->ip_proto == IPPROTO_TCP) + flow_rule_match_tcp(flow_rule, &tcp); if (basic.mask->n_proto != htons(0xFFFF) || (basic.key->n_proto != htons(ETH_P_IP) && basic.key->n_proto != htons(ETH_P_IPV6)) || basic.mask->ip_proto != 0xFF || - (basic.key->ip_proto != IPPROTO_UDP && basic.key->ip_proto != IPPROTO_TCP)) { + (basic.key->ip_proto != IPPROTO_UDP && basic.key->ip_proto != IPPROTO_TCP && + basic.key->ip_proto != IPPROTO_GRE)) { ct_dbg("rule uses unexpected basic match (n_proto 0x%04x/0x%04x, ip_proto 0x%02x/0x%02x)", ntohs(basic.key->n_proto), ntohs(basic.mask->n_proto), basic.key->ip_proto, basic.mask->ip_proto); return false; } - if (ports.mask->src != htons(0xFFFF) || ports.mask->dst != htons(0xFFFF)) { + if (basic.key->ip_proto != IPPROTO_GRE && + (ports.mask->src != htons(0xFFFF) || ports.mask->dst != htons(0xFFFF))) { ct_dbg("rule uses ports match (src 0x%04x, dst 0x%04x)", ports.mask->src, ports.mask->dst); return false; @@ -291,7 +297,7 @@ mlx5_ct_fs_smfs_ct_rule_add(struct mlx5_ct_fs *fs, struct mlx5_flow_spec *spec, struct mlx5dr_action *actions[5]; struct mlx5dr_rule *rule; int num_actions = 0, err; - bool nat, tcp, ipv4; + bool nat, tcp, ipv4, gre; if (!mlx5_ct_fs_smfs_ct_validate_flow_rule(fs, flow_rule)) return ERR_PTR(-EOPNOTSUPP); @@ -314,15 +320,17 @@ mlx5_ct_fs_smfs_ct_rule_add(struct mlx5_ct_fs *fs, struct mlx5_flow_spec *spec, ipv4 = mlx5e_tc_get_ip_version(spec, true) == 4; tcp = MLX5_GET(fte_match_param, spec->match_value, outer_headers.ip_protocol) == IPPROTO_TCP; + gre = MLX5_GET(fte_match_param, spec->match_value, + outer_headers.ip_protocol) == IPPROTO_GRE; - smfs_matcher = mlx5_ct_fs_smfs_matcher_get(fs, nat, ipv4, tcp); + smfs_matcher = mlx5_ct_fs_smfs_matcher_get(fs, nat, ipv4, tcp, gre); if (IS_ERR(smfs_matcher)) { err = PTR_ERR(smfs_matcher); goto err_matcher; } rule = mlx5_smfs_rule_create(smfs_matcher->dr_matcher, spec, num_actions, actions, - MLX5_FLOW_CONTEXT_FLOW_SOURCE_ANY_VPORT); + spec->flow_context.flow_source); if (!rule) { err = -EINVAL; goto err_create; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/trap.c b/drivers/net/ethernet/mellanox/mlx5/core/en/trap.c index a55b066746cb..857840ab1e91 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/trap.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/trap.c @@ -14,19 +14,26 @@ static int mlx5e_trap_napi_poll(struct napi_struct *napi, int budget) bool busy = false; int work_done = 0; + rcu_read_lock(); + ch_stats->poll++; work_done = mlx5e_poll_rx_cq(&rq->cq, budget); busy |= work_done == budget; busy |= rq->post_wqes(rq); - if (busy) - return budget; + if (busy) { + work_done = budget; + goto out; + } if (unlikely(!napi_complete_done(napi, work_done))) - return work_done; + goto out; mlx5e_cq_arm(&rq->cq); + +out: + rcu_read_unlock(); return work_done; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index 2f1dedc721d1..fa229998606c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -3864,6 +3864,10 @@ static netdev_features_t mlx5e_fix_uplink_rep_features(struct net_device *netdev if (netdev->features & NETIF_F_NTUPLE) netdev_warn(netdev, "Disabling ntuple, not supported in switchdev mode\n"); + features &= ~NETIF_F_GRO_HW; + if (netdev->features & NETIF_F_GRO_HW) + netdev_warn(netdev, "Disabling HW_GRO, not supported in switchdev mode\n"); + return features; } @@ -3896,6 +3900,25 @@ static netdev_features_t mlx5e_fix_features(struct net_device *netdev, } } + if (params->xdp_prog) { + if (features & NETIF_F_LRO) { + netdev_warn(netdev, "LRO is incompatible with XDP\n"); + features &= ~NETIF_F_LRO; + } + if (features & NETIF_F_GRO_HW) { + netdev_warn(netdev, "HW GRO is incompatible with XDP\n"); + features &= ~NETIF_F_GRO_HW; + } + } + + if (priv->xsk.refcnt) { + if (features & NETIF_F_GRO_HW) { + netdev_warn(netdev, "HW GRO is incompatible with AF_XDP (%u XSKs are active)\n", + priv->xsk.refcnt); + features &= ~NETIF_F_GRO_HW; + } + } + if (MLX5E_GET_PFLAG(params, MLX5E_PFLAG_RX_CQE_COMPRESS)) { features &= ~NETIF_F_RXHASH; if (netdev->features & NETIF_F_RXHASH) @@ -4850,10 +4873,6 @@ static void mlx5e_build_nic_netdev(struct net_device *netdev) netdev->hw_features |= NETIF_F_HW_VLAN_CTAG_FILTER; netdev->hw_features |= NETIF_F_HW_VLAN_STAG_TX; - if (!!MLX5_CAP_GEN(mdev, shampo) && - mlx5e_check_fragmented_striding_rq_cap(mdev)) - netdev->hw_features |= NETIF_F_GRO_HW; - if (mlx5e_tunnel_any_tx_proto_supported(mdev)) { netdev->hw_enc_features |= NETIF_F_HW_CSUM; netdev->hw_enc_features |= NETIF_F_TSO; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c index 816d991f7621..3ad67e6b5586 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c @@ -2663,28 +2663,6 @@ static void cleanup_root_ns(struct mlx5_flow_root_namespace *root_ns) clean_tree(&root_ns->ns.node); } -void mlx5_cleanup_fs(struct mlx5_core_dev *dev) -{ - struct mlx5_flow_steering *steering = dev->priv.steering; - - cleanup_root_ns(steering->root_ns); - cleanup_root_ns(steering->fdb_root_ns); - steering->fdb_root_ns = NULL; - kfree(steering->fdb_sub_ns); - steering->fdb_sub_ns = NULL; - cleanup_root_ns(steering->port_sel_root_ns); - cleanup_root_ns(steering->sniffer_rx_root_ns); - cleanup_root_ns(steering->sniffer_tx_root_ns); - cleanup_root_ns(steering->rdma_rx_root_ns); - cleanup_root_ns(steering->rdma_tx_root_ns); - cleanup_root_ns(steering->egress_root_ns); - mlx5_cleanup_fc_stats(dev); - kmem_cache_destroy(steering->ftes_cache); - kmem_cache_destroy(steering->fgs_cache); - mlx5_ft_pool_destroy(dev); - kfree(steering); -} - static int init_sniffer_tx_root_ns(struct mlx5_flow_steering *steering) { struct fs_prio *prio; @@ -3086,42 +3064,27 @@ cleanup: return err; } -int mlx5_init_fs(struct mlx5_core_dev *dev) +void mlx5_fs_core_cleanup(struct mlx5_core_dev *dev) { - struct mlx5_flow_steering *steering; - int err = 0; - - err = mlx5_init_fc_stats(dev); - if (err) - return err; - - err = mlx5_ft_pool_init(dev); - if (err) - return err; - - steering = kzalloc(sizeof(*steering), GFP_KERNEL); - if (!steering) { - err = -ENOMEM; - goto err; - } - - steering->dev = dev; - dev->priv.steering = steering; + struct mlx5_flow_steering *steering = dev->priv.steering; - if (mlx5_fs_dr_is_supported(dev)) - steering->mode = MLX5_FLOW_STEERING_MODE_SMFS; - else - steering->mode = MLX5_FLOW_STEERING_MODE_DMFS; + cleanup_root_ns(steering->root_ns); + cleanup_root_ns(steering->fdb_root_ns); + steering->fdb_root_ns = NULL; + kfree(steering->fdb_sub_ns); + steering->fdb_sub_ns = NULL; + cleanup_root_ns(steering->port_sel_root_ns); + cleanup_root_ns(steering->sniffer_rx_root_ns); + cleanup_root_ns(steering->sniffer_tx_root_ns); + cleanup_root_ns(steering->rdma_rx_root_ns); + cleanup_root_ns(steering->rdma_tx_root_ns); + cleanup_root_ns(steering->egress_root_ns); +} - steering->fgs_cache = kmem_cache_create("mlx5_fs_fgs", - sizeof(struct mlx5_flow_group), 0, - 0, NULL); - steering->ftes_cache = kmem_cache_create("mlx5_fs_ftes", sizeof(struct fs_fte), 0, - 0, NULL); - if (!steering->ftes_cache || !steering->fgs_cache) { - err = -ENOMEM; - goto err; - } +int mlx5_fs_core_init(struct mlx5_core_dev *dev) +{ + struct mlx5_flow_steering *steering = dev->priv.steering; + int err = 0; if ((((MLX5_CAP_GEN(dev, port_type) == MLX5_CAP_PORT_TYPE_ETH) && (MLX5_CAP_GEN(dev, nic_flow_table))) || @@ -3180,8 +3143,64 @@ int mlx5_init_fs(struct mlx5_core_dev *dev) } return 0; + +err: + mlx5_fs_core_cleanup(dev); + return err; +} + +void mlx5_fs_core_free(struct mlx5_core_dev *dev) +{ + struct mlx5_flow_steering *steering = dev->priv.steering; + + kmem_cache_destroy(steering->ftes_cache); + kmem_cache_destroy(steering->fgs_cache); + kfree(steering); + mlx5_ft_pool_destroy(dev); + mlx5_cleanup_fc_stats(dev); +} + +int mlx5_fs_core_alloc(struct mlx5_core_dev *dev) +{ + struct mlx5_flow_steering *steering; + int err = 0; + + err = mlx5_init_fc_stats(dev); + if (err) + return err; + + err = mlx5_ft_pool_init(dev); + if (err) + goto err; + + steering = kzalloc(sizeof(*steering), GFP_KERNEL); + if (!steering) { + err = -ENOMEM; + goto err; + } + + steering->dev = dev; + dev->priv.steering = steering; + + if (mlx5_fs_dr_is_supported(dev)) + steering->mode = MLX5_FLOW_STEERING_MODE_SMFS; + else + steering->mode = MLX5_FLOW_STEERING_MODE_DMFS; + + steering->fgs_cache = kmem_cache_create("mlx5_fs_fgs", + sizeof(struct mlx5_flow_group), 0, + 0, NULL); + steering->ftes_cache = kmem_cache_create("mlx5_fs_ftes", sizeof(struct fs_fte), 0, + 0, NULL); + if (!steering->ftes_cache || !steering->fgs_cache) { + err = -ENOMEM; + goto err; + } + + return 0; + err: - mlx5_cleanup_fs(dev); + mlx5_fs_core_free(dev); return err; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h index c488a7c5b07e..3f20523e514f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h @@ -298,8 +298,10 @@ int mlx5_flow_namespace_set_peer(struct mlx5_flow_root_namespace *ns, int mlx5_flow_namespace_set_mode(struct mlx5_flow_namespace *ns, enum mlx5_flow_steering_mode mode); -int mlx5_init_fs(struct mlx5_core_dev *dev); -void mlx5_cleanup_fs(struct mlx5_core_dev *dev); +int mlx5_fs_core_alloc(struct mlx5_core_dev *dev); +void mlx5_fs_core_free(struct mlx5_core_dev *dev); +int mlx5_fs_core_init(struct mlx5_core_dev *dev); +void mlx5_fs_core_cleanup(struct mlx5_core_dev *dev); int mlx5_fs_egress_acls_init(struct mlx5_core_dev *dev, int total_vports); void mlx5_fs_egress_acls_cleanup(struct mlx5_core_dev *dev); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c b/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c index ca1aba845dd6..81eb67fb95b0 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c @@ -8,7 +8,8 @@ enum { MLX5_FW_RESET_FLAGS_RESET_REQUESTED, MLX5_FW_RESET_FLAGS_NACK_RESET_REQUEST, - MLX5_FW_RESET_FLAGS_PENDING_COMP + MLX5_FW_RESET_FLAGS_PENDING_COMP, + MLX5_FW_RESET_FLAGS_DROP_NEW_REQUESTS }; struct mlx5_fw_reset { @@ -208,7 +209,10 @@ static void poll_sync_reset(struct timer_list *t) if (fatal_error) { mlx5_core_warn(dev, "Got Device Reset\n"); - queue_work(fw_reset->wq, &fw_reset->reset_reload_work); + if (!test_bit(MLX5_FW_RESET_FLAGS_DROP_NEW_REQUESTS, &fw_reset->reset_flags)) + queue_work(fw_reset->wq, &fw_reset->reset_reload_work); + else + mlx5_core_err(dev, "Device is being removed, Drop new reset work\n"); return; } @@ -433,9 +437,12 @@ static int fw_reset_event_notifier(struct notifier_block *nb, unsigned long acti struct mlx5_fw_reset *fw_reset = mlx5_nb_cof(nb, struct mlx5_fw_reset, nb); struct mlx5_eqe *eqe = data; + if (test_bit(MLX5_FW_RESET_FLAGS_DROP_NEW_REQUESTS, &fw_reset->reset_flags)) + return NOTIFY_DONE; + switch (eqe->sub_type) { case MLX5_GENERAL_SUBTYPE_FW_LIVE_PATCH_EVENT: - queue_work(fw_reset->wq, &fw_reset->fw_live_patch_work); + queue_work(fw_reset->wq, &fw_reset->fw_live_patch_work); break; case MLX5_GENERAL_SUBTYPE_PCI_SYNC_FOR_FW_UPDATE_EVENT: mlx5_sync_reset_events_handle(fw_reset, eqe); @@ -479,6 +486,18 @@ void mlx5_fw_reset_events_stop(struct mlx5_core_dev *dev) mlx5_eq_notifier_unregister(dev, &dev->priv.fw_reset->nb); } +void mlx5_drain_fw_reset(struct mlx5_core_dev *dev) +{ + struct mlx5_fw_reset *fw_reset = dev->priv.fw_reset; + + set_bit(MLX5_FW_RESET_FLAGS_DROP_NEW_REQUESTS, &fw_reset->reset_flags); + cancel_work_sync(&fw_reset->fw_live_patch_work); + cancel_work_sync(&fw_reset->reset_request_work); + cancel_work_sync(&fw_reset->reset_reload_work); + cancel_work_sync(&fw_reset->reset_now_work); + cancel_work_sync(&fw_reset->reset_abort_work); +} + int mlx5_fw_reset_init(struct mlx5_core_dev *dev) { struct mlx5_fw_reset *fw_reset = kzalloc(sizeof(*fw_reset), GFP_KERNEL); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.h b/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.h index 694fc7cb2684..dc141c7e641a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.h @@ -16,6 +16,7 @@ int mlx5_fw_reset_set_live_patch(struct mlx5_core_dev *dev); int mlx5_fw_reset_wait_reset_done(struct mlx5_core_dev *dev); void mlx5_fw_reset_events_start(struct mlx5_core_dev *dev); void mlx5_fw_reset_events_stop(struct mlx5_core_dev *dev); +void mlx5_drain_fw_reset(struct mlx5_core_dev *dev); int mlx5_fw_reset_init(struct mlx5_core_dev *dev); void mlx5_fw_reset_cleanup(struct mlx5_core_dev *dev); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c index 2589e39eb9c7..ef196cb764e2 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c @@ -938,6 +938,12 @@ static int mlx5_init_once(struct mlx5_core_dev *dev) goto err_sf_table_cleanup; } + err = mlx5_fs_core_alloc(dev); + if (err) { + mlx5_core_err(dev, "Failed to alloc flow steering\n"); + goto err_fs; + } + dev->dm = mlx5_dm_create(dev); if (IS_ERR(dev->dm)) mlx5_core_warn(dev, "Failed to init device memory%d\n", err); @@ -948,6 +954,8 @@ static int mlx5_init_once(struct mlx5_core_dev *dev) return 0; +err_fs: + mlx5_sf_table_cleanup(dev); err_sf_table_cleanup: mlx5_sf_hw_table_cleanup(dev); err_sf_hw_table_cleanup: @@ -985,6 +993,7 @@ static void mlx5_cleanup_once(struct mlx5_core_dev *dev) mlx5_hv_vhca_destroy(dev->hv_vhca); mlx5_fw_tracer_destroy(dev->tracer); mlx5_dm_cleanup(dev); + mlx5_fs_core_free(dev); mlx5_sf_table_cleanup(dev); mlx5_sf_hw_table_cleanup(dev); mlx5_vhca_event_cleanup(dev); @@ -1191,7 +1200,7 @@ static int mlx5_load(struct mlx5_core_dev *dev) goto err_tls_start; } - err = mlx5_init_fs(dev); + err = mlx5_fs_core_init(dev); if (err) { mlx5_core_err(dev, "Failed to init flow steering\n"); goto err_fs; @@ -1236,7 +1245,7 @@ err_ec: err_vhca: mlx5_vhca_event_stop(dev); err_set_hca: - mlx5_cleanup_fs(dev); + mlx5_fs_core_cleanup(dev); err_fs: mlx5_accel_tls_cleanup(dev); err_tls_start: @@ -1265,7 +1274,7 @@ static void mlx5_unload(struct mlx5_core_dev *dev) mlx5_ec_cleanup(dev); mlx5_sf_hw_table_destroy(dev); mlx5_vhca_event_stop(dev); - mlx5_cleanup_fs(dev); + mlx5_fs_core_cleanup(dev); mlx5_accel_ipsec_cleanup(dev); mlx5_accel_tls_cleanup(dev); mlx5_fpga_device_stop(dev); @@ -1618,6 +1627,10 @@ static void remove_one(struct pci_dev *pdev) struct mlx5_core_dev *dev = pci_get_drvdata(pdev); struct devlink *devlink = priv_to_devlink(dev); + /* mlx5_drain_fw_reset() is using devlink APIs. Hence, we must drain + * fw_reset before unregistering the devlink. + */ + mlx5_drain_fw_reset(dev); devlink_unregister(devlink); mlx5_sriov_disable(pdev); mlx5_crdump_disable(dev); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_action.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_action.c index 850937cd8bf9..1383550f44c1 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_action.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_action.c @@ -530,6 +530,37 @@ static int dr_action_handle_cs_recalc(struct mlx5dr_domain *dmn, return 0; } +static void dr_action_modify_ttl_adjust(struct mlx5dr_domain *dmn, + struct mlx5dr_ste_actions_attr *attr, + bool rx_rule, + bool *recalc_cs_required) +{ + *recalc_cs_required = false; + + /* if device supports csum recalculation - no adjustment needed */ + if (mlx5dr_ste_supp_ttl_cs_recalc(&dmn->info.caps)) + return; + + /* no adjustment needed on TX rules */ + if (!rx_rule) + return; + + if (!MLX5_CAP_ESW_FLOWTABLE(dmn->mdev, fdb_ipv4_ttl_modify)) { + /* Ignore the modify TTL action. + * It is always kept as last HW action. + */ + attr->modify_actions--; + return; + } + + if (dmn->type == MLX5DR_DOMAIN_TYPE_FDB) + /* Due to a HW bug on some devices, modifying TTL on RX flows + * will cause an incorrect checksum calculation. In such cases + * we will use a FW table to recalculate the checksum. + */ + *recalc_cs_required = true; +} + static void dr_action_print_sequence(struct mlx5dr_domain *dmn, struct mlx5dr_action *actions[], int last_idx) @@ -650,8 +681,9 @@ int mlx5dr_actions_build_ste_arr(struct mlx5dr_matcher *matcher, case DR_ACTION_TYP_MODIFY_HDR: attr.modify_index = action->rewrite->index; attr.modify_actions = action->rewrite->num_of_actions; - recalc_cs_required = action->rewrite->modify_ttl && - !mlx5dr_ste_supp_ttl_cs_recalc(&dmn->info.caps); + if (action->rewrite->modify_ttl) + dr_action_modify_ttl_adjust(dmn, &attr, rx_rule, + &recalc_cs_required); break; case DR_ACTION_TYP_L2_TO_TNL_L2: case DR_ACTION_TYP_L2_TO_TNL_L3: @@ -732,12 +764,7 @@ int mlx5dr_actions_build_ste_arr(struct mlx5dr_matcher *matcher, *new_hw_ste_arr_sz = nic_matcher->num_of_builders; last_ste = ste_arr + DR_STE_SIZE * (nic_matcher->num_of_builders - 1); - /* Due to a HW bug in some devices, modifying TTL on RX flows will - * cause an incorrect checksum calculation. In this case we will - * use a FW table to recalculate. - */ - if (dmn->type == MLX5DR_DOMAIN_TYPE_FDB && - rx_rule && recalc_cs_required && dest_action) { + if (recalc_cs_required && dest_action) { ret = dr_action_handle_cs_recalc(dmn, dest_action, &attr.final_icm_addr); if (ret) { mlx5dr_err(dmn, @@ -842,7 +869,8 @@ struct mlx5dr_action * mlx5dr_action_create_mult_dest_tbl(struct mlx5dr_domain *dmn, struct mlx5dr_action_dest *dests, u32 num_of_dests, - bool ignore_flow_level) + bool ignore_flow_level, + u32 flow_source) { struct mlx5dr_cmd_flow_destination_hw_info *hw_dests; struct mlx5dr_action **ref_actions; @@ -914,7 +942,8 @@ mlx5dr_action_create_mult_dest_tbl(struct mlx5dr_domain *dmn, reformat_req, &action->dest_tbl->fw_tbl.id, &action->dest_tbl->fw_tbl.group_id, - ignore_flow_level); + ignore_flow_level, + flow_source); if (ret) goto free_action; @@ -1556,12 +1585,6 @@ dr_action_modify_check_is_ttl_modify(const void *sw_action) return sw_field == MLX5_ACTION_IN_FIELD_OUT_IP_TTL; } -static bool dr_action_modify_ttl_ignore(struct mlx5dr_domain *dmn) -{ - return !mlx5dr_ste_supp_ttl_cs_recalc(&dmn->info.caps) && - !MLX5_CAP_ESW_FLOWTABLE(dmn->mdev, fdb_ipv4_ttl_modify); -} - static int dr_actions_convert_modify_header(struct mlx5dr_action *action, u32 max_hw_actions, u32 num_sw_actions, @@ -1573,6 +1596,7 @@ static int dr_actions_convert_modify_header(struct mlx5dr_action *action, const struct mlx5dr_ste_action_modify_field *hw_dst_action_info; const struct mlx5dr_ste_action_modify_field *hw_src_action_info; struct mlx5dr_domain *dmn = action->rewrite->dmn; + __be64 *modify_ttl_sw_action = NULL; int ret, i, hw_idx = 0; __be64 *sw_action; __be64 hw_action; @@ -1585,8 +1609,14 @@ static int dr_actions_convert_modify_header(struct mlx5dr_action *action, action->rewrite->allow_rx = 1; action->rewrite->allow_tx = 1; - for (i = 0; i < num_sw_actions; i++) { - sw_action = &sw_actions[i]; + for (i = 0; i < num_sw_actions || modify_ttl_sw_action; i++) { + /* modify TTL is handled separately, as a last action */ + if (i == num_sw_actions) { + sw_action = modify_ttl_sw_action; + modify_ttl_sw_action = NULL; + } else { + sw_action = &sw_actions[i]; + } ret = dr_action_modify_check_field_limitation(action, sw_action); @@ -1595,10 +1625,9 @@ static int dr_actions_convert_modify_header(struct mlx5dr_action *action, if (!(*modify_ttl) && dr_action_modify_check_is_ttl_modify(sw_action)) { - if (dr_action_modify_ttl_ignore(dmn)) - continue; - + modify_ttl_sw_action = sw_action; *modify_ttl = true; + continue; } /* Convert SW action to HW action */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_fw.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_fw.c index 68a4c32d5f34..f05ef0cd54ba 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_fw.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_fw.c @@ -104,7 +104,8 @@ int mlx5dr_fw_create_md_tbl(struct mlx5dr_domain *dmn, bool reformat_req, u32 *tbl_id, u32 *group_id, - bool ignore_flow_level) + bool ignore_flow_level, + u32 flow_source) { struct mlx5dr_cmd_create_flow_table_attr ft_attr = {}; struct mlx5dr_cmd_fte_info fte_info = {}; @@ -139,6 +140,7 @@ int mlx5dr_fw_create_md_tbl(struct mlx5dr_domain *dmn, fte_info.val = val; fte_info.dest_arr = dest; fte_info.ignore_flow_level = ignore_flow_level; + fte_info.flow_context.flow_source = flow_source; ret = mlx5dr_cmd_set_fte(dmn->mdev, 0, 0, &ft_info, *group_id, &fte_info); if (ret) { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste_v0.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste_v0.c index 5a322335f204..2010d4ac6519 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste_v0.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste_v0.c @@ -420,7 +420,7 @@ dr_ste_v0_set_actions_tx(struct mlx5dr_domain *dmn, * encapsulation. The reason for that is that we support * modify headers for outer headers only */ - if (action_type_set[DR_ACTION_TYP_MODIFY_HDR]) { + if (action_type_set[DR_ACTION_TYP_MODIFY_HDR] && attr->modify_actions) { dr_ste_v0_set_entry_type(last_ste, DR_STE_TYPE_MODIFY_PKT); dr_ste_v0_set_rewrite_actions(last_ste, attr->modify_actions, @@ -513,7 +513,7 @@ dr_ste_v0_set_actions_rx(struct mlx5dr_domain *dmn, } } - if (action_type_set[DR_ACTION_TYP_MODIFY_HDR]) { + if (action_type_set[DR_ACTION_TYP_MODIFY_HDR] && attr->modify_actions) { if (dr_ste_v0_get_entry_type(last_ste) == DR_STE_TYPE_MODIFY_PKT) dr_ste_v0_arr_init_next(&last_ste, added_stes, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_types.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_types.h index 46866a5fc5ca..98320e3945ad 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_types.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_types.h @@ -1461,7 +1461,8 @@ int mlx5dr_fw_create_md_tbl(struct mlx5dr_domain *dmn, bool reformat_req, u32 *tbl_id, u32 *group_id, - bool ignore_flow_level); + bool ignore_flow_level, + u32 flow_source); void mlx5dr_fw_destroy_md_tbl(struct mlx5dr_domain *dmn, u32 tbl_id, u32 group_id); #endif /* _DR_TYPES_H_ */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/fs_dr.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/fs_dr.c index 045b0cf90063..728f81882589 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/fs_dr.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/fs_dr.c @@ -520,6 +520,7 @@ static int mlx5_cmd_dr_create_fte(struct mlx5_flow_root_namespace *ns, } else if (num_term_actions > 1) { bool ignore_flow_level = !!(fte->action.flags & FLOW_ACT_IGNORE_FLOW_LEVEL); + u32 flow_source = fte->flow_context.flow_source; if (num_actions == MLX5_FLOW_CONTEXT_ACTION_MAX || fs_dr_num_actions == MLX5_FLOW_CONTEXT_ACTION_MAX) { @@ -529,7 +530,8 @@ static int mlx5_cmd_dr_create_fte(struct mlx5_flow_root_namespace *ns, tmp_action = mlx5dr_action_create_mult_dest_tbl(domain, term_actions, num_term_actions, - ignore_flow_level); + ignore_flow_level, + flow_source); if (!tmp_action) { err = -EOPNOTSUPP; goto free_actions; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/mlx5dr.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/mlx5dr.h index ec5cbec0d455..7626c85643b1 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/mlx5dr.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/mlx5dr.h @@ -99,7 +99,8 @@ struct mlx5dr_action * mlx5dr_action_create_mult_dest_tbl(struct mlx5dr_domain *dmn, struct mlx5dr_action_dest *dests, u32 num_of_dests, - bool ignore_flow_level); + bool ignore_flow_level, + u32 flow_source); struct mlx5dr_action *mlx5dr_action_create_drop(void); diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_ipip.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_ipip.c index 01cf5a6a26bd..a2ee695a3f17 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_ipip.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_ipip.c @@ -568,10 +568,8 @@ static int mlxsw_sp2_ipip_rem_addr_set_gre6(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_ipip_entry *ipip_entry) { - struct __ip6_tnl_parm parms6; - - parms6 = mlxsw_sp_ipip_netdev_parms6(ipip_entry->ol_dev); - return mlxsw_sp_ipv6_addr_kvdl_index_get(mlxsw_sp, &parms6.raddr, + return mlxsw_sp_ipv6_addr_kvdl_index_get(mlxsw_sp, + &ipip_entry->parms.daddr.addr6, &ipip_entry->dip_kvdl_index); } @@ -579,10 +577,7 @@ static void mlxsw_sp2_ipip_rem_addr_unset_gre6(struct mlxsw_sp *mlxsw_sp, const struct mlxsw_sp_ipip_entry *ipip_entry) { - struct __ip6_tnl_parm parms6; - - parms6 = mlxsw_sp_ipip_netdev_parms6(ipip_entry->ol_dev); - mlxsw_sp_ipv6_addr_put(mlxsw_sp, &parms6.raddr); + mlxsw_sp_ipv6_addr_put(mlxsw_sp, &ipip_entry->parms.daddr.addr6); } static const struct mlxsw_sp_ipip_ops mlxsw_sp2_ipip_gre6_ops = { diff --git a/drivers/net/ethernet/microchip/lan966x/lan966x_main.c b/drivers/net/ethernet/microchip/lan966x/lan966x_main.c index 95830e3e2b1f..05f6dcc9dfd5 100644 --- a/drivers/net/ethernet/microchip/lan966x/lan966x_main.c +++ b/drivers/net/ethernet/microchip/lan966x/lan966x_main.c @@ -103,6 +103,24 @@ static int lan966x_create_targets(struct platform_device *pdev, return 0; } +static bool lan966x_port_unique_address(struct net_device *dev) +{ + struct lan966x_port *port = netdev_priv(dev); + struct lan966x *lan966x = port->lan966x; + int p; + + for (p = 0; p < lan966x->num_phys_ports; ++p) { + port = lan966x->ports[p]; + if (!port || port->dev == dev) + continue; + + if (ether_addr_equal(dev->dev_addr, port->dev->dev_addr)) + return false; + } + + return true; +} + static int lan966x_port_set_mac_address(struct net_device *dev, void *p) { struct lan966x_port *port = netdev_priv(dev); @@ -110,16 +128,26 @@ static int lan966x_port_set_mac_address(struct net_device *dev, void *p) const struct sockaddr *addr = p; int ret; + if (ether_addr_equal(addr->sa_data, dev->dev_addr)) + return 0; + /* Learn the new net device MAC address in the mac table. */ ret = lan966x_mac_cpu_learn(lan966x, addr->sa_data, HOST_PVID); if (ret) return ret; + /* If there is another port with the same address as the dev, then don't + * delete it from the MAC table + */ + if (!lan966x_port_unique_address(dev)) + goto out; + /* Then forget the previous one. */ ret = lan966x_mac_cpu_forget(lan966x, dev->dev_addr, HOST_PVID); if (ret) return ret; +out: eth_hw_addr_set(dev, addr->sa_data); return ret; } diff --git a/drivers/net/ethernet/mscc/ocelot.c b/drivers/net/ethernet/mscc/ocelot.c index ca71b62a44dc..20ceac81a2c2 100644 --- a/drivers/net/ethernet/mscc/ocelot.c +++ b/drivers/net/ethernet/mscc/ocelot.c @@ -1622,7 +1622,7 @@ int ocelot_trap_add(struct ocelot *ocelot, int port, trap->action.mask_mode = OCELOT_MASK_MODE_PERMIT_DENY; trap->action.port_mask = 0; trap->take_ts = take_ts; - list_add_tail(&trap->trap_list, &ocelot->traps); + trap->is_trap = true; new = true; } @@ -1634,10 +1634,8 @@ int ocelot_trap_add(struct ocelot *ocelot, int port, err = ocelot_vcap_filter_replace(ocelot, trap); if (err) { trap->ingress_port_mask &= ~BIT(port); - if (!trap->ingress_port_mask) { - list_del(&trap->trap_list); + if (!trap->ingress_port_mask) kfree(trap); - } return err; } @@ -1657,11 +1655,8 @@ int ocelot_trap_del(struct ocelot *ocelot, int port, unsigned long cookie) return 0; trap->ingress_port_mask &= ~BIT(port); - if (!trap->ingress_port_mask) { - list_del(&trap->trap_list); - + if (!trap->ingress_port_mask) return ocelot_vcap_filter_del(ocelot, trap); - } return ocelot_vcap_filter_replace(ocelot, trap); } diff --git a/drivers/net/ethernet/mscc/ocelot_flower.c b/drivers/net/ethernet/mscc/ocelot_flower.c index 03b5e59d033e..51cf241ff7d0 100644 --- a/drivers/net/ethernet/mscc/ocelot_flower.c +++ b/drivers/net/ethernet/mscc/ocelot_flower.c @@ -280,9 +280,10 @@ static int ocelot_flower_parse_action(struct ocelot *ocelot, int port, filter->type = OCELOT_VCAP_FILTER_OFFLOAD; break; case FLOW_ACTION_TRAP: - if (filter->block_id != VCAP_IS2) { + if (filter->block_id != VCAP_IS2 || + filter->lookup != 0) { NL_SET_ERR_MSG_MOD(extack, - "Trap action can only be offloaded to VCAP IS2"); + "Trap action can only be offloaded to VCAP IS2 lookup 0"); return -EOPNOTSUPP; } if (filter->goto_target != -1) { @@ -295,7 +296,7 @@ static int ocelot_flower_parse_action(struct ocelot *ocelot, int port, filter->action.cpu_copy_ena = true; filter->action.cpu_qu_num = 0; filter->type = OCELOT_VCAP_FILTER_OFFLOAD; - list_add_tail(&filter->trap_list, &ocelot->traps); + filter->is_trap = true; break; case FLOW_ACTION_POLICE: if (filter->block_id == PSFP_BLOCK_ID) { @@ -878,8 +879,6 @@ int ocelot_cls_flower_replace(struct ocelot *ocelot, int port, ret = ocelot_flower_parse(ocelot, port, ingress, f, filter); if (ret) { - if (!list_empty(&filter->trap_list)) - list_del(&filter->trap_list); kfree(filter); return ret; } diff --git a/drivers/net/ethernet/mscc/ocelot_vcap.c b/drivers/net/ethernet/mscc/ocelot_vcap.c index c8701ac955a8..eeb4cc07dd16 100644 --- a/drivers/net/ethernet/mscc/ocelot_vcap.c +++ b/drivers/net/ethernet/mscc/ocelot_vcap.c @@ -374,7 +374,6 @@ static void is2_entry_set(struct ocelot *ocelot, int ix, OCELOT_VCAP_BIT_0); vcap_key_set(vcap, &data, VCAP_IS2_HK_IGR_PORT_MASK, 0, ~filter->ingress_port_mask); - vcap_key_bit_set(vcap, &data, VCAP_IS2_HK_FIRST, OCELOT_VCAP_BIT_ANY); vcap_key_bit_set(vcap, &data, VCAP_IS2_HK_HOST_MATCH, OCELOT_VCAP_BIT_ANY); vcap_key_bit_set(vcap, &data, VCAP_IS2_HK_L2_MC, filter->dmac_mc); @@ -1217,6 +1216,8 @@ int ocelot_vcap_filter_add(struct ocelot *ocelot, struct ocelot_vcap_filter *tmp; tmp = ocelot_vcap_block_find_filter_by_index(block, i); + /* Read back the filter's counters before moving it */ + vcap_entry_get(ocelot, i - 1, tmp); vcap_entry_set(ocelot, i, tmp); } @@ -1250,7 +1251,11 @@ int ocelot_vcap_filter_del(struct ocelot *ocelot, struct ocelot_vcap_filter del_filter; int i, index; + /* Need to inherit the block_id so that vcap_entry_set() + * does not get confused and knows where to install it. + */ memset(&del_filter, 0, sizeof(del_filter)); + del_filter.block_id = filter->block_id; /* Gets index of the filter */ index = ocelot_vcap_block_get_filter_index(block, filter); @@ -1265,6 +1270,8 @@ int ocelot_vcap_filter_del(struct ocelot *ocelot, struct ocelot_vcap_filter *tmp; tmp = ocelot_vcap_block_find_filter_by_index(block, i); + /* Read back the filter's counters before moving it */ + vcap_entry_get(ocelot, i + 1, tmp); vcap_entry_set(ocelot, i, tmp); } diff --git a/drivers/net/ethernet/pensando/ionic/ionic_bus_pci.c b/drivers/net/ethernet/pensando/ionic/ionic_bus_pci.c index 6ffc62c41165..0a7a757494bc 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_bus_pci.c +++ b/drivers/net/ethernet/pensando/ionic/ionic_bus_pci.c @@ -256,7 +256,7 @@ static int ionic_probe(struct pci_dev *pdev, const struct pci_device_id *ent) err = ionic_map_bars(ionic); if (err) - goto err_out_pci_disable_device; + goto err_out_pci_release_regions; /* Configure the device */ err = ionic_setup(ionic); @@ -360,6 +360,7 @@ err_out_teardown: err_out_unmap_bars: ionic_unmap_bars(ionic); +err_out_pci_release_regions: pci_release_regions(pdev); err_out_pci_disable_device: pci_disable_device(pdev); diff --git a/drivers/net/ethernet/qlogic/qla3xxx.c b/drivers/net/ethernet/qlogic/qla3xxx.c index b30589a135c2..06f4d9a9e938 100644 --- a/drivers/net/ethernet/qlogic/qla3xxx.c +++ b/drivers/net/ethernet/qlogic/qla3xxx.c @@ -3614,7 +3614,8 @@ static void ql_reset_work(struct work_struct *work) qdev->mem_map_registers; unsigned long hw_flags; - if (test_bit((QL_RESET_PER_SCSI | QL_RESET_START), &qdev->flags)) { + if (test_bit(QL_RESET_PER_SCSI, &qdev->flags) || + test_bit(QL_RESET_START, &qdev->flags)) { clear_bit(QL_LINK_MASTER, &qdev->flags); /* diff --git a/drivers/net/ethernet/sfc/ef10.c b/drivers/net/ethernet/sfc/ef10.c index 50d535981a35..f8edb3f1b73a 100644 --- a/drivers/net/ethernet/sfc/ef10.c +++ b/drivers/net/ethernet/sfc/ef10.c @@ -3579,6 +3579,11 @@ static int efx_ef10_mtd_probe(struct efx_nic *efx) n_parts++; } + if (!n_parts) { + kfree(parts); + return 0; + } + rc = efx_mtd_add(efx, &parts[0].common, n_parts, sizeof(*parts)); fail: if (rc) diff --git a/drivers/net/ethernet/sfc/efx_channels.c b/drivers/net/ethernet/sfc/efx_channels.c index 377df8b7f015..40df910aa140 100644 --- a/drivers/net/ethernet/sfc/efx_channels.c +++ b/drivers/net/ethernet/sfc/efx_channels.c @@ -867,7 +867,9 @@ static void efx_set_xdp_channels(struct efx_nic *efx) int efx_realloc_channels(struct efx_nic *efx, u32 rxq_entries, u32 txq_entries) { - struct efx_channel *other_channel[EFX_MAX_CHANNELS], *channel; + struct efx_channel *other_channel[EFX_MAX_CHANNELS], *channel, + *ptp_channel = efx_ptp_channel(efx); + struct efx_ptp_data *ptp_data = efx->ptp_data; unsigned int i, next_buffer_table = 0; u32 old_rxq_entries, old_txq_entries; int rc, rc2; @@ -938,6 +940,7 @@ int efx_realloc_channels(struct efx_nic *efx, u32 rxq_entries, u32 txq_entries) efx_set_xdp_channels(efx); out: + efx->ptp_data = NULL; /* Destroy unused channel structures */ for (i = 0; i < efx->n_channels; i++) { channel = other_channel[i]; @@ -948,6 +951,7 @@ out: } } + efx->ptp_data = ptp_data; rc2 = efx_soft_enable_interrupts(efx); if (rc2) { rc = rc ? rc : rc2; @@ -966,6 +970,7 @@ rollback: efx->txq_entries = old_txq_entries; for (i = 0; i < efx->n_channels; i++) swap(efx->channel[i], other_channel[i]); + efx_ptp_update_channel(efx, ptp_channel); goto out; } diff --git a/drivers/net/ethernet/sfc/ptp.c b/drivers/net/ethernet/sfc/ptp.c index f0ef515e2ade..4625f85acab2 100644 --- a/drivers/net/ethernet/sfc/ptp.c +++ b/drivers/net/ethernet/sfc/ptp.c @@ -45,6 +45,7 @@ #include "farch_regs.h" #include "tx.h" #include "nic.h" /* indirectly includes ptp.h */ +#include "efx_channels.h" /* Maximum number of events expected to make up a PTP event */ #define MAX_EVENT_FRAGS 3 @@ -541,6 +542,12 @@ struct efx_channel *efx_ptp_channel(struct efx_nic *efx) return efx->ptp_data ? efx->ptp_data->channel : NULL; } +void efx_ptp_update_channel(struct efx_nic *efx, struct efx_channel *channel) +{ + if (efx->ptp_data) + efx->ptp_data->channel = channel; +} + static u32 last_sync_timestamp_major(struct efx_nic *efx) { struct efx_channel *channel = efx_ptp_channel(efx); @@ -1443,6 +1450,11 @@ int efx_ptp_probe(struct efx_nic *efx, struct efx_channel *channel) int rc = 0; unsigned int pos; + if (efx->ptp_data) { + efx->ptp_data->channel = channel; + return 0; + } + ptp = kzalloc(sizeof(struct efx_ptp_data), GFP_KERNEL); efx->ptp_data = ptp; if (!efx->ptp_data) @@ -2176,7 +2188,7 @@ static const struct efx_channel_type efx_ptp_channel_type = { .pre_probe = efx_ptp_probe_channel, .post_remove = efx_ptp_remove_channel, .get_name = efx_ptp_get_channel_name, - /* no copy operation; there is no need to reallocate this channel */ + .copy = efx_copy_channel, .receive_skb = efx_ptp_rx, .want_txqs = efx_ptp_want_txqs, .keep_eventq = false, diff --git a/drivers/net/ethernet/sfc/ptp.h b/drivers/net/ethernet/sfc/ptp.h index 9855e8c9e544..7b1ef7002b3f 100644 --- a/drivers/net/ethernet/sfc/ptp.h +++ b/drivers/net/ethernet/sfc/ptp.h @@ -16,6 +16,7 @@ struct ethtool_ts_info; int efx_ptp_probe(struct efx_nic *efx, struct efx_channel *channel); void efx_ptp_defer_probe_with_channel(struct efx_nic *efx); struct efx_channel *efx_ptp_channel(struct efx_nic *efx); +void efx_ptp_update_channel(struct efx_nic *efx, struct efx_channel *channel); void efx_ptp_remove(struct efx_nic *efx); int efx_ptp_set_ts_config(struct efx_nic *efx, struct ifreq *ifr); int efx_ptp_get_ts_config(struct efx_nic *efx, struct ifreq *ifr); diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c index fcf17d8a0494..644bb54f5f02 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c @@ -181,7 +181,7 @@ static int stmmac_pci_probe(struct pci_dev *pdev, return -ENOMEM; /* Enable pci device */ - ret = pci_enable_device(pdev); + ret = pcim_enable_device(pdev); if (ret) { dev_err(&pdev->dev, "%s: ERROR: failed to enable device\n", __func__); @@ -241,8 +241,6 @@ static void stmmac_pci_remove(struct pci_dev *pdev) pcim_iounmap_regions(pdev, BIT(i)); break; } - - pci_disable_device(pdev); } static int __maybe_unused stmmac_pci_suspend(struct device *dev) diff --git a/drivers/net/ipa/gsi.c b/drivers/net/ipa/gsi.c index bc981043cc80..a701178a1d13 100644 --- a/drivers/net/ipa/gsi.c +++ b/drivers/net/ipa/gsi.c @@ -1367,9 +1367,10 @@ static void gsi_evt_ring_rx_update(struct gsi_evt_ring *evt_ring, u32 index) struct gsi_event *event_done; struct gsi_event *event; struct gsi_trans *trans; + u32 trans_count = 0; u32 byte_count = 0; - u32 old_index; u32 event_avail; + u32 old_index; trans_info = &channel->trans_info; @@ -1390,6 +1391,7 @@ static void gsi_evt_ring_rx_update(struct gsi_evt_ring *evt_ring, u32 index) do { trans->len = __le16_to_cpu(event->len); byte_count += trans->len; + trans_count++; /* Move on to the next event and transaction */ if (--event_avail) @@ -1401,7 +1403,7 @@ static void gsi_evt_ring_rx_update(struct gsi_evt_ring *evt_ring, u32 index) /* We record RX bytes when they are received */ channel->byte_count += byte_count; - channel->trans_count++; + channel->trans_count += trans_count; } /* Initialize a ring, including allocating DMA memory for its entries */ diff --git a/drivers/net/ipa/ipa_endpoint.c b/drivers/net/ipa/ipa_endpoint.c index 888e94278a84..cea7b2e2ce96 100644 --- a/drivers/net/ipa/ipa_endpoint.c +++ b/drivers/net/ipa/ipa_endpoint.c @@ -1150,13 +1150,12 @@ static void ipa_endpoint_skb_copy(struct ipa_endpoint *endpoint, return; skb = __dev_alloc_skb(len, GFP_ATOMIC); - if (!skb) - return; - - /* Copy the data into the socket buffer and receive it */ - skb_put(skb, len); - memcpy(skb->data, data, len); - skb->truesize += extra; + if (skb) { + /* Copy the data into the socket buffer and receive it */ + skb_put(skb, len); + memcpy(skb->data, data, len); + skb->truesize += extra; + } ipa_modem_skb_rx(endpoint->netdev, skb); } diff --git a/drivers/net/ipa/ipa_qmi.c b/drivers/net/ipa/ipa_qmi.c index 90f3aec55b36..ec010cf2e816 100644 --- a/drivers/net/ipa/ipa_qmi.c +++ b/drivers/net/ipa/ipa_qmi.c @@ -125,7 +125,7 @@ static void ipa_qmi_indication(struct ipa_qmi *ipa_qmi) */ static void ipa_qmi_ready(struct ipa_qmi *ipa_qmi) { - struct ipa *ipa = container_of(ipa_qmi, struct ipa, qmi); + struct ipa *ipa; int ret; /* We aren't ready until the modem and microcontroller are */ diff --git a/drivers/net/phy/micrel.c b/drivers/net/phy/micrel.c index fc53b71dc872..cd9aa353b653 100644 --- a/drivers/net/phy/micrel.c +++ b/drivers/net/phy/micrel.c @@ -1743,7 +1743,7 @@ static int ksz886x_cable_test_get_status(struct phy_device *phydev, static int lanphy_read_page_reg(struct phy_device *phydev, int page, u32 addr) { - u32 data; + int data; phy_lock_mdio_bus(phydev); __phy_write(phydev, LAN_EXT_PAGE_ACCESS_CONTROL, page); @@ -2444,8 +2444,7 @@ static int lan8804_config_init(struct phy_device *phydev) static irqreturn_t lan8814_handle_interrupt(struct phy_device *phydev) { - u16 tsu_irq_status; - int irq_status; + int irq_status, tsu_irq_status; irq_status = phy_read(phydev, LAN8814_INTS); if (irq_status > 0 && (irq_status & LAN8814_INT_LINK)) @@ -2657,6 +2656,7 @@ static struct phy_driver ksphy_driver[] = { .name = "Micrel KS8737", /* PHY_BASIC_FEATURES */ .driver_data = &ks8737_type, + .probe = kszphy_probe, .config_init = kszphy_config_init, .config_intr = kszphy_config_intr, .handle_interrupt = kszphy_handle_interrupt, @@ -2782,8 +2782,8 @@ static struct phy_driver ksphy_driver[] = { .config_init = ksz8061_config_init, .config_intr = kszphy_config_intr, .handle_interrupt = kszphy_handle_interrupt, - .suspend = kszphy_suspend, - .resume = kszphy_resume, + .suspend = genphy_suspend, + .resume = genphy_resume, }, { .phy_id = PHY_ID_KSZ9021, .phy_id_mask = 0x000ffffe, diff --git a/drivers/net/phy/phy.c b/drivers/net/phy/phy.c index beb2b66da132..f122026c4682 100644 --- a/drivers/net/phy/phy.c +++ b/drivers/net/phy/phy.c @@ -970,8 +970,13 @@ static irqreturn_t phy_interrupt(int irq, void *phy_dat) { struct phy_device *phydev = phy_dat; struct phy_driver *drv = phydev->drv; + irqreturn_t ret; - return drv->handle_interrupt(phydev); + mutex_lock(&phydev->lock); + ret = drv->handle_interrupt(phydev); + mutex_unlock(&phydev->lock); + + return ret; } /** diff --git a/drivers/net/ppp/pppoe.c b/drivers/net/ppp/pppoe.c index 3619520340b7..e172743948ed 100644 --- a/drivers/net/ppp/pppoe.c +++ b/drivers/net/ppp/pppoe.c @@ -988,6 +988,7 @@ static int pppoe_fill_forward_path(struct net_device_path_ctx *ctx, path->encap.proto = htons(ETH_P_PPP_SES); path->encap.id = be16_to_cpu(po->num); memcpy(path->encap.h_dest, po->pppoe_pa.remote, ETH_ALEN); + memcpy(ctx->daddr, po->pppoe_pa.remote, ETH_ALEN); path->dev = ctx->dev; ctx->dev = dev; diff --git a/drivers/net/vmxnet3/vmxnet3_drv.c b/drivers/net/vmxnet3/vmxnet3_drv.c index d9d90baac72a..93e8d119d45f 100644 --- a/drivers/net/vmxnet3/vmxnet3_drv.c +++ b/drivers/net/vmxnet3/vmxnet3_drv.c @@ -589,6 +589,7 @@ vmxnet3_rq_alloc_rx_buf(struct vmxnet3_rx_queue *rq, u32 ring_idx, if (dma_mapping_error(&adapter->pdev->dev, rbi->dma_addr)) { dev_kfree_skb_any(rbi->skb); + rbi->skb = NULL; rq->stats.rx_buf_alloc_failure++; break; } @@ -613,6 +614,7 @@ vmxnet3_rq_alloc_rx_buf(struct vmxnet3_rx_queue *rq, u32 ring_idx, if (dma_mapping_error(&adapter->pdev->dev, rbi->dma_addr)) { put_page(rbi->page); + rbi->page = NULL; rq->stats.rx_buf_alloc_failure++; break; } @@ -1666,6 +1668,10 @@ vmxnet3_rq_cleanup(struct vmxnet3_rx_queue *rq, u32 i, ring_idx; struct Vmxnet3_RxDesc *rxd; + /* ring has already been cleaned up */ + if (!rq->rx_ring[0].base) + return; + for (ring_idx = 0; ring_idx < 2; ring_idx++) { for (i = 0; i < rq->rx_ring[ring_idx].size; i++) { #ifdef __BIG_ENDIAN_BITFIELD diff --git a/drivers/net/wireless/ath/ath11k/core.c b/drivers/net/wireless/ath/ath11k/core.c index 71eb7d04c3bf..90a5df1fbdbd 100644 --- a/drivers/net/wireless/ath/ath11k/core.c +++ b/drivers/net/wireless/ath/ath11k/core.c @@ -1288,6 +1288,7 @@ static void ath11k_core_restart(struct work_struct *work) ieee80211_stop_queues(ar->hw); ath11k_mac_drain_tx(ar); + complete(&ar->completed_11d_scan); complete(&ar->scan.started); complete(&ar->scan.completed); complete(&ar->peer_assoc_done); diff --git a/drivers/net/wireless/ath/ath11k/core.h b/drivers/net/wireless/ath/ath11k/core.h index c0228e91a596..b8634eddf49a 100644 --- a/drivers/net/wireless/ath/ath11k/core.h +++ b/drivers/net/wireless/ath/ath11k/core.h @@ -38,6 +38,8 @@ extern unsigned int ath11k_frame_mode; +#define ATH11K_SCAN_TIMEOUT_HZ (20 * HZ) + #define ATH11K_MON_TIMER_INTERVAL 10 enum ath11k_supported_bw { @@ -189,6 +191,12 @@ enum ath11k_scan_state { ATH11K_SCAN_ABORTING, }; +enum ath11k_11d_state { + ATH11K_11D_IDLE, + ATH11K_11D_PREPARING, + ATH11K_11D_RUNNING, +}; + enum ath11k_dev_flags { ATH11K_CAC_RUNNING, ATH11K_FLAG_CORE_REGISTERED, @@ -607,9 +615,8 @@ struct ath11k { bool dfs_block_radar_events; struct ath11k_thermal thermal; u32 vdev_id_11d_scan; - struct completion finish_11d_scan; - struct completion finish_11d_ch_list; - bool pending_11d; + struct completion completed_11d_scan; + enum ath11k_11d_state state_11d; bool regdom_set_by_user; int hw_rate_code; u8 twt_enabled; diff --git a/drivers/net/wireless/ath/ath11k/mac.c b/drivers/net/wireless/ath/ath11k/mac.c index e6b34b0d61bd..58ff761393db 100644 --- a/drivers/net/wireless/ath/ath11k/mac.c +++ b/drivers/net/wireless/ath/ath11k/mac.c @@ -3601,26 +3601,6 @@ static int ath11k_mac_op_hw_scan(struct ieee80211_hw *hw, if (ret) goto exit; - /* Currently the pending_11d=true only happened 1 time while - * wlan interface up in ath11k_mac_11d_scan_start(), it is called by - * ath11k_mac_op_add_interface(), after wlan interface up, - * pending_11d=false always. - * If remove below wait, it always happened scan fail and lead connect - * fail while wlan interface up, because it has a 11d scan which is running - * in firmware, and lead this scan failed. - */ - if (ar->pending_11d) { - long time_left; - unsigned long timeout = 5 * HZ; - - if (ar->supports_6ghz) - timeout += 5 * HZ; - - time_left = wait_for_completion_timeout(&ar->finish_11d_ch_list, timeout); - ath11k_dbg(ar->ab, ATH11K_DBG_MAC, - "mac wait 11d channel list time left %ld\n", time_left); - } - memset(&arg, 0, sizeof(arg)); ath11k_wmi_start_scan_init(ar, &arg); arg.vdev_id = arvif->vdev_id; @@ -3686,6 +3666,10 @@ exit: kfree(arg.extraie.ptr); mutex_unlock(&ar->conf_mutex); + + if (ar->state_11d == ATH11K_11D_PREPARING) + ath11k_mac_11d_scan_start(ar, arvif->vdev_id); + return ret; } @@ -5814,7 +5798,7 @@ static int ath11k_mac_op_start(struct ieee80211_hw *hw) /* TODO: Do we need to enable ANI? */ - ath11k_reg_update_chan_list(ar); + ath11k_reg_update_chan_list(ar, false); ar->num_started_vdevs = 0; ar->num_created_vdevs = 0; @@ -5881,6 +5865,11 @@ static void ath11k_mac_op_stop(struct ieee80211_hw *hw) cancel_work_sync(&ar->ab->update_11d_work); cancel_work_sync(&ar->ab->rfkill_work); + if (ar->state_11d == ATH11K_11D_PREPARING) { + ar->state_11d = ATH11K_11D_IDLE; + complete(&ar->completed_11d_scan); + } + spin_lock_bh(&ar->data_lock); list_for_each_entry_safe(ppdu_stats, tmp, &ar->ppdu_stats_info, list) { list_del(&ppdu_stats->list); @@ -6051,7 +6040,7 @@ static bool ath11k_mac_vif_ap_active_any(struct ath11k_base *ab) return false; } -void ath11k_mac_11d_scan_start(struct ath11k *ar, u32 vdev_id, bool wait) +void ath11k_mac_11d_scan_start(struct ath11k *ar, u32 vdev_id) { struct wmi_11d_scan_start_params param; int ret; @@ -6079,28 +6068,22 @@ void ath11k_mac_11d_scan_start(struct ath11k *ar, u32 vdev_id, bool wait) ath11k_dbg(ar->ab, ATH11K_DBG_MAC, "mac start 11d scan\n"); - if (wait) - reinit_completion(&ar->finish_11d_scan); - ret = ath11k_wmi_send_11d_scan_start_cmd(ar, ¶m); if (ret) { ath11k_warn(ar->ab, "failed to start 11d scan vdev %d ret: %d\n", vdev_id, ret); } else { ar->vdev_id_11d_scan = vdev_id; - if (wait) { - ar->pending_11d = true; - ret = wait_for_completion_timeout(&ar->finish_11d_scan, - 5 * HZ); - ath11k_dbg(ar->ab, ATH11K_DBG_MAC, - "mac 11d scan left time %d\n", ret); - - if (!ret) - ar->pending_11d = false; - } + if (ar->state_11d == ATH11K_11D_PREPARING) + ar->state_11d = ATH11K_11D_RUNNING; } fin: + if (ar->state_11d == ATH11K_11D_PREPARING) { + ar->state_11d = ATH11K_11D_IDLE; + complete(&ar->completed_11d_scan); + } + mutex_unlock(&ar->ab->vdev_id_11d_lock); } @@ -6123,12 +6106,15 @@ void ath11k_mac_11d_scan_stop(struct ath11k *ar) vdev_id = ar->vdev_id_11d_scan; ret = ath11k_wmi_send_11d_scan_stop_cmd(ar, vdev_id); - if (ret) + if (ret) { ath11k_warn(ar->ab, "failed to stopt 11d scan vdev %d ret: %d\n", vdev_id, ret); - else + } else { ar->vdev_id_11d_scan = ATH11K_11D_INVALID_VDEV_ID; + ar->state_11d = ATH11K_11D_IDLE; + complete(&ar->completed_11d_scan); + } } mutex_unlock(&ar->ab->vdev_id_11d_lock); } @@ -6324,8 +6310,10 @@ static int ath11k_mac_op_add_interface(struct ieee80211_hw *hw, goto err_peer_del; } - ath11k_mac_11d_scan_start(ar, arvif->vdev_id, true); - + if (test_bit(WMI_TLV_SERVICE_11D_OFFLOAD, ab->wmi_ab.svc_map)) { + reinit_completion(&ar->completed_11d_scan); + ar->state_11d = ATH11K_11D_PREPARING; + } break; case WMI_VDEV_TYPE_MONITOR: set_bit(ATH11K_FLAG_MONITOR_VDEV_CREATED, &ar->monitor_flags); @@ -7190,7 +7178,7 @@ ath11k_mac_op_unassign_vif_chanctx(struct ieee80211_hw *hw, } if (arvif->vdev_type == WMI_VDEV_TYPE_STA) - ath11k_mac_11d_scan_start(ar, arvif->vdev_id, false); + ath11k_mac_11d_scan_start(ar, arvif->vdev_id); mutex_unlock(&ar->conf_mutex); } @@ -8671,8 +8659,7 @@ int ath11k_mac_allocate(struct ath11k_base *ab) ar->monitor_vdev_id = -1; clear_bit(ATH11K_FLAG_MONITOR_VDEV_CREATED, &ar->monitor_flags); ar->vdev_id_11d_scan = ATH11K_11D_INVALID_VDEV_ID; - init_completion(&ar->finish_11d_scan); - init_completion(&ar->finish_11d_ch_list); + init_completion(&ar->completed_11d_scan); } return 0; diff --git a/drivers/net/wireless/ath/ath11k/mac.h b/drivers/net/wireless/ath/ath11k/mac.h index 0e6c870b09c8..29b523af66dd 100644 --- a/drivers/net/wireless/ath/ath11k/mac.h +++ b/drivers/net/wireless/ath/ath11k/mac.h @@ -130,7 +130,7 @@ extern const struct htt_rx_ring_tlv_filter ath11k_mac_mon_status_filter_default; #define ATH11K_SCAN_11D_INTERVAL 600000 #define ATH11K_11D_INVALID_VDEV_ID 0xFFFF -void ath11k_mac_11d_scan_start(struct ath11k *ar, u32 vdev_id, bool wait); +void ath11k_mac_11d_scan_start(struct ath11k *ar, u32 vdev_id); void ath11k_mac_11d_scan_stop(struct ath11k *ar); void ath11k_mac_11d_scan_stop_all(struct ath11k_base *ab); diff --git a/drivers/net/wireless/ath/ath11k/reg.c b/drivers/net/wireless/ath/ath11k/reg.c index 81e11cde31d7..80a697771393 100644 --- a/drivers/net/wireless/ath/ath11k/reg.c +++ b/drivers/net/wireless/ath/ath11k/reg.c @@ -102,7 +102,7 @@ ath11k_reg_notifier(struct wiphy *wiphy, struct regulatory_request *request) ar->regdom_set_by_user = true; } -int ath11k_reg_update_chan_list(struct ath11k *ar) +int ath11k_reg_update_chan_list(struct ath11k *ar, bool wait) { struct ieee80211_supported_band **bands; struct scan_chan_list_params *params; @@ -111,7 +111,32 @@ int ath11k_reg_update_chan_list(struct ath11k *ar) struct channel_param *ch; enum nl80211_band band; int num_channels = 0; - int i, ret; + int i, ret, left; + + if (wait && ar->state_11d != ATH11K_11D_IDLE) { + left = wait_for_completion_timeout(&ar->completed_11d_scan, + ATH11K_SCAN_TIMEOUT_HZ); + if (!left) { + ath11k_dbg(ar->ab, ATH11K_DBG_REG, + "failed to receive 11d scan complete: timed out\n"); + ar->state_11d = ATH11K_11D_IDLE; + } + ath11k_dbg(ar->ab, ATH11K_DBG_REG, + "reg 11d scan wait left time %d\n", left); + } + + if (wait && + (ar->scan.state == ATH11K_SCAN_STARTING || + ar->scan.state == ATH11K_SCAN_RUNNING)) { + left = wait_for_completion_timeout(&ar->scan.completed, + ATH11K_SCAN_TIMEOUT_HZ); + if (!left) + ath11k_dbg(ar->ab, ATH11K_DBG_REG, + "failed to receive hw scan complete: timed out\n"); + + ath11k_dbg(ar->ab, ATH11K_DBG_REG, + "reg hw scan wait left time %d\n", left); + } bands = hw->wiphy->bands; for (band = 0; band < NUM_NL80211_BANDS; band++) { @@ -193,11 +218,6 @@ int ath11k_reg_update_chan_list(struct ath11k *ar) ret = ath11k_wmi_send_scan_chan_list_cmd(ar, params); kfree(params); - if (ar->pending_11d) { - complete(&ar->finish_11d_ch_list); - ar->pending_11d = false; - } - return ret; } @@ -263,15 +283,8 @@ int ath11k_regd_update(struct ath11k *ar) goto err; } - if (ar->pending_11d) - complete(&ar->finish_11d_scan); - rtnl_lock(); wiphy_lock(ar->hw->wiphy); - - if (ar->pending_11d) - reinit_completion(&ar->finish_11d_ch_list); - ret = regulatory_set_wiphy_regd_sync(ar->hw->wiphy, regd_copy); wiphy_unlock(ar->hw->wiphy); rtnl_unlock(); @@ -282,7 +295,7 @@ int ath11k_regd_update(struct ath11k *ar) goto err; if (ar->state == ATH11K_STATE_ON) { - ret = ath11k_reg_update_chan_list(ar); + ret = ath11k_reg_update_chan_list(ar, true); if (ret) goto err; } diff --git a/drivers/net/wireless/ath/ath11k/reg.h b/drivers/net/wireless/ath/ath11k/reg.h index 5fb9dc03a74e..2f284f26378d 100644 --- a/drivers/net/wireless/ath/ath11k/reg.h +++ b/drivers/net/wireless/ath/ath11k/reg.h @@ -32,5 +32,5 @@ struct ieee80211_regdomain * ath11k_reg_build_regd(struct ath11k_base *ab, struct cur_regulatory_info *reg_info, bool intersect); int ath11k_regd_update(struct ath11k *ar); -int ath11k_reg_update_chan_list(struct ath11k *ar); +int ath11k_reg_update_chan_list(struct ath11k *ar, bool wait); #endif diff --git a/drivers/net/wireless/ath/ath11k/wmi.c b/drivers/net/wireless/ath/ath11k/wmi.c index b4f86c45d81f..2751fe8814df 100644 --- a/drivers/net/wireless/ath/ath11k/wmi.c +++ b/drivers/net/wireless/ath/ath11k/wmi.c @@ -2015,7 +2015,10 @@ void ath11k_wmi_start_scan_init(struct ath11k *ar, { /* setup commonly used values */ arg->scan_req_id = 1; - arg->scan_priority = WMI_SCAN_PRIORITY_LOW; + if (ar->state_11d == ATH11K_11D_PREPARING) + arg->scan_priority = WMI_SCAN_PRIORITY_MEDIUM; + else + arg->scan_priority = WMI_SCAN_PRIORITY_LOW; arg->dwell_time_active = 50; arg->dwell_time_active_2g = 0; arg->dwell_time_passive = 150; @@ -6350,8 +6353,10 @@ static void ath11k_wmi_op_ep_tx_credits(struct ath11k_base *ab) static int ath11k_reg_11d_new_cc_event(struct ath11k_base *ab, struct sk_buff *skb) { const struct wmi_11d_new_cc_ev *ev; + struct ath11k *ar; + struct ath11k_pdev *pdev; const void **tb; - int ret; + int ret, i; tb = ath11k_wmi_tlv_parse_alloc(ab, skb->data, skb->len, GFP_ATOMIC); if (IS_ERR(tb)) { @@ -6377,6 +6382,13 @@ static int ath11k_reg_11d_new_cc_event(struct ath11k_base *ab, struct sk_buff *s kfree(tb); + for (i = 0; i < ab->num_radios; i++) { + pdev = &ab->pdevs[i]; + ar = pdev->ar; + ar->state_11d = ATH11K_11D_IDLE; + complete(&ar->completed_11d_scan); + } + queue_work(ab->workqueue, &ab->update_11d_work); return 0; diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-dbg-tlv.c b/drivers/net/wireless/intel/iwlwifi/iwl-dbg-tlv.c index 866a33f49915..3237d4b528b5 100644 --- a/drivers/net/wireless/intel/iwlwifi/iwl-dbg-tlv.c +++ b/drivers/net/wireless/intel/iwlwifi/iwl-dbg-tlv.c @@ -371,7 +371,7 @@ void iwl_dbg_tlv_del_timers(struct iwl_trans *trans) struct iwl_dbg_tlv_timer_node *node, *tmp; list_for_each_entry_safe(node, tmp, timer_list, list) { - del_timer(&node->timer); + del_timer_sync(&node->timer); list_del(&node->list); kfree(node); } diff --git a/drivers/net/wireless/mac80211_hwsim.c b/drivers/net/wireless/mac80211_hwsim.c index 28bfa7b7b73c..e9ec63e0e395 100644 --- a/drivers/net/wireless/mac80211_hwsim.c +++ b/drivers/net/wireless/mac80211_hwsim.c @@ -2202,11 +2202,14 @@ mac80211_hwsim_sta_rc_update(struct ieee80211_hw *hw, if (!data->use_chanctx) { confbw = data->bw; } else { - struct ieee80211_chanctx_conf *chanctx_conf = - rcu_dereference(vif->chanctx_conf); + struct ieee80211_chanctx_conf *chanctx_conf; + + rcu_read_lock(); + chanctx_conf = rcu_dereference(vif->chanctx_conf); if (!WARN_ON(!chanctx_conf)) confbw = chanctx_conf->def.width; + rcu_read_unlock(); } WARN(bw > hwsim_get_chanwidth(confbw), @@ -2475,11 +2478,13 @@ static void hw_scan_work(struct work_struct *work) if (req->ie_len) skb_put_data(probe, req->ie, req->ie_len); + rcu_read_lock(); if (!ieee80211_tx_prepare_skb(hwsim->hw, hwsim->hw_scan_vif, probe, hwsim->tmp_chan->band, NULL)) { + rcu_read_unlock(); kfree_skb(probe); continue; } @@ -2487,6 +2492,7 @@ static void hw_scan_work(struct work_struct *work) local_bh_disable(); mac80211_hwsim_tx_frame(hwsim->hw, probe, hwsim->tmp_chan); + rcu_read_unlock(); local_bh_enable(); } } diff --git a/drivers/nfc/pn533/pn533.c b/drivers/nfc/pn533/pn533.c index a491db46e3bd..d9f6367b9993 100644 --- a/drivers/nfc/pn533/pn533.c +++ b/drivers/nfc/pn533/pn533.c @@ -2787,13 +2787,14 @@ void pn53x_common_clean(struct pn533 *priv) { struct pn533_cmd *cmd, *n; + /* delete the timer before cleanup the worker */ + del_timer_sync(&priv->listen_timer); + flush_delayed_work(&priv->poll_work); destroy_workqueue(priv->wq); skb_queue_purge(&priv->resp_q); - del_timer(&priv->listen_timer); - list_for_each_entry_safe(cmd, n, &priv->cmd_queue, queue) { list_del(&cmd->queue); kfree(cmd); diff --git a/drivers/nvme/host/constants.c b/drivers/nvme/host/constants.c index 7d49eb34b348..4910543f00ff 100644 --- a/drivers/nvme/host/constants.c +++ b/drivers/nvme/host/constants.c @@ -4,7 +4,6 @@ * Copyright (c) 2022, Oracle and/or its affiliates */ -#include <linux/blkdev.h> #include "nvme.h" #ifdef CONFIG_NVME_VERBOSE_ERRORS @@ -92,6 +91,7 @@ static const char * const nvme_statuses[] = { [NVME_SC_NS_WRITE_PROTECTED] = "Namespace is Write Protected", [NVME_SC_CMD_INTERRUPTED] = "Command Interrupted", [NVME_SC_TRANSIENT_TR_ERR] = "Transient Transport Error", + [NVME_SC_ADMIN_COMMAND_MEDIA_NOT_READY] = "Admin Command Media Not Ready", [NVME_SC_INVALID_IO_CMD_SET] = "Invalid IO Command Set", [NVME_SC_LBA_RANGE] = "LBA Out of Range", [NVME_SC_CAP_EXCEEDED] = "Capacity Exceeded", @@ -155,10 +155,13 @@ static const char * const nvme_statuses[] = { [NVME_SC_COMPARE_FAILED] = "Compare Failure", [NVME_SC_ACCESS_DENIED] = "Access Denied", [NVME_SC_UNWRITTEN_BLOCK] = "Deallocated or Unwritten Logical Block", + [NVME_SC_INTERNAL_PATH_ERROR] = "Internal Pathing Error", [NVME_SC_ANA_PERSISTENT_LOSS] = "Asymmetric Access Persistent Loss", [NVME_SC_ANA_INACCESSIBLE] = "Asymmetric Access Inaccessible", [NVME_SC_ANA_TRANSITION] = "Asymmetric Access Transition", + [NVME_SC_CTRL_PATH_ERROR] = "Controller Pathing Error", [NVME_SC_HOST_PATH_ERROR] = "Host Pathing Error", + [NVME_SC_HOST_ABORTED_CMD] = "Host Aborted Command", }; const unsigned char *nvme_get_error_status_str(u16 status) diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index e1846d04817f..72f7c955c707 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -1207,6 +1207,7 @@ static void nvme_keep_alive_work(struct work_struct *work) rq->timeout = ctrl->kato * HZ; rq->end_io_data = ctrl; + rq->rq_flags |= RQF_QUIET; blk_execute_rq_nowait(rq, false, nvme_keep_alive_end_io); } @@ -1426,6 +1427,32 @@ out_free_id: return error; } +static int nvme_identify_ns_cs_indep(struct nvme_ctrl *ctrl, unsigned nsid, + struct nvme_id_ns_cs_indep **id) +{ + struct nvme_command c = { + .identify.opcode = nvme_admin_identify, + .identify.nsid = cpu_to_le32(nsid), + .identify.cns = NVME_ID_CNS_NS_CS_INDEP, + }; + int ret; + + *id = kmalloc(sizeof(**id), GFP_KERNEL); + if (!*id) + return -ENOMEM; + + ret = nvme_submit_sync_cmd(ctrl->admin_q, &c, *id, sizeof(**id)); + if (ret) { + dev_warn(ctrl->device, + "Identify namespace (CS independent) failed (%d)\n", + ret); + kfree(*id); + return ret; + } + + return 0; +} + static int nvme_features(struct nvme_ctrl *dev, u8 op, unsigned int fid, unsigned int dword11, void *buffer, size_t buflen, u32 *result) { @@ -1621,20 +1648,22 @@ static void nvme_config_discard(struct gendisk *disk, struct nvme_ns *ns) u32 size = queue_logical_block_size(queue); if (ctrl->max_discard_sectors == 0) { - blk_queue_flag_clear(QUEUE_FLAG_DISCARD, queue); + blk_queue_max_discard_sectors(queue, 0); return; } BUILD_BUG_ON(PAGE_SIZE / sizeof(struct nvme_dsm_range) < NVME_DSM_MAX_RANGES); - queue->limits.discard_alignment = 0; queue->limits.discard_granularity = size; /* If discard is already enabled, don't reset queue limits */ - if (blk_queue_flag_test_and_set(QUEUE_FLAG_DISCARD, queue)) + if (queue->limits.max_discard_sectors) return; + if (ctrl->dmrsl && ctrl->dmrsl <= nvme_sect_to_lba(ns, UINT_MAX)) + ctrl->max_discard_sectors = nvme_lba_to_sect(ns, ctrl->dmrsl); + blk_queue_max_discard_sectors(queue, ctrl->max_discard_sectors); blk_queue_max_discard_segments(queue, ctrl->max_discard_segments); @@ -1771,7 +1800,7 @@ static void nvme_set_queue_limits(struct nvme_ctrl *ctrl, blk_queue_max_segments(q, min_t(u32, max_segments, USHRT_MAX)); } blk_queue_virt_boundary(q, NVME_CTRL_PAGE_SIZE - 1); - blk_queue_dma_alignment(q, 7); + blk_queue_dma_alignment(q, 3); blk_queue_write_cache(q, vwc, vwc); } @@ -2100,10 +2129,9 @@ static const struct block_device_operations nvme_bdev_ops = { .pr_ops = &nvme_pr_ops, }; -static int nvme_wait_ready(struct nvme_ctrl *ctrl, u64 cap, bool enabled) +static int nvme_wait_ready(struct nvme_ctrl *ctrl, u32 timeout, bool enabled) { - unsigned long timeout = - ((NVME_CAP_TIMEOUT(cap) + 1) * HZ / 2) + jiffies; + unsigned long timeout_jiffies = ((timeout + 1) * HZ / 2) + jiffies; u32 csts, bit = enabled ? NVME_CSTS_RDY : 0; int ret; @@ -2116,7 +2144,7 @@ static int nvme_wait_ready(struct nvme_ctrl *ctrl, u64 cap, bool enabled) usleep_range(1000, 2000); if (fatal_signal_pending(current)) return -EINTR; - if (time_after(jiffies, timeout)) { + if (time_after(jiffies, timeout_jiffies)) { dev_err(ctrl->device, "Device not ready; aborting %s, CSTS=0x%x\n", enabled ? "initialisation" : "reset", csts); @@ -2147,13 +2175,14 @@ int nvme_disable_ctrl(struct nvme_ctrl *ctrl) if (ctrl->quirks & NVME_QUIRK_DELAY_BEFORE_CHK_RDY) msleep(NVME_QUIRK_DELAY_AMOUNT); - return nvme_wait_ready(ctrl, ctrl->cap, false); + return nvme_wait_ready(ctrl, NVME_CAP_TIMEOUT(ctrl->cap), false); } EXPORT_SYMBOL_GPL(nvme_disable_ctrl); int nvme_enable_ctrl(struct nvme_ctrl *ctrl) { unsigned dev_page_min; + u32 timeout; int ret; ret = ctrl->ops->reg_read64(ctrl, NVME_REG_CAP, &ctrl->cap); @@ -2174,6 +2203,27 @@ int nvme_enable_ctrl(struct nvme_ctrl *ctrl) ctrl->ctrl_config = NVME_CC_CSS_CSI; else ctrl->ctrl_config = NVME_CC_CSS_NVM; + + if (ctrl->cap & NVME_CAP_CRMS_CRWMS) { + u32 crto; + + ret = ctrl->ops->reg_read32(ctrl, NVME_REG_CRTO, &crto); + if (ret) { + dev_err(ctrl->device, "Reading CRTO failed (%d)\n", + ret); + return ret; + } + + if (ctrl->cap & NVME_CAP_CRMS_CRIMS) { + ctrl->ctrl_config |= NVME_CC_CRIME; + timeout = NVME_CRTO_CRIMT(crto); + } else { + timeout = NVME_CRTO_CRWMT(crto); + } + } else { + timeout = NVME_CAP_TIMEOUT(ctrl->cap); + } + ctrl->ctrl_config |= (NVME_CTRL_PAGE_SHIFT - 12) << NVME_CC_MPS_SHIFT; ctrl->ctrl_config |= NVME_CC_AMS_RR | NVME_CC_SHN_NONE; ctrl->ctrl_config |= NVME_CC_IOSQES | NVME_CC_IOCQES; @@ -2182,7 +2232,7 @@ int nvme_enable_ctrl(struct nvme_ctrl *ctrl) ret = ctrl->ops->reg_write32(ctrl, NVME_REG_CC, ctrl->ctrl_config); if (ret) return ret; - return nvme_wait_ready(ctrl, ctrl->cap, true); + return nvme_wait_ready(ctrl, timeout, true); } EXPORT_SYMBOL_GPL(nvme_enable_ctrl); @@ -2894,8 +2944,7 @@ static int nvme_init_non_mdts_limits(struct nvme_ctrl *ctrl) if (id->dmrl) ctrl->max_discard_segments = id->dmrl; - if (id->dmrsl) - ctrl->max_discard_sectors = le32_to_cpu(id->dmrsl); + ctrl->dmrsl = le32_to_cpu(id->dmrsl); if (id->wzsl) ctrl->max_zeroes_sectors = nvme_mps_to_sectors(ctrl, id->wzsl); @@ -3080,10 +3129,6 @@ int nvme_init_ctrl_finish(struct nvme_ctrl *ctrl) if (ret) return ret; - ret = nvme_init_non_mdts_limits(ctrl); - if (ret < 0) - return ret; - ret = nvme_configure_apst(ctrl); if (ret < 0) return ret; @@ -3146,6 +3191,7 @@ static const struct file_operations nvme_dev_fops = { .release = nvme_dev_release, .unlocked_ioctl = nvme_dev_ioctl, .compat_ioctl = compat_ptr_ioctl, + .uring_cmd = nvme_dev_uring_cmd, }; static ssize_t nvme_sysfs_reset(struct device *dev, @@ -3699,6 +3745,7 @@ static const struct file_operations nvme_ns_chr_fops = { .release = nvme_ns_chr_release, .unlocked_ioctl = nvme_ns_chr_ioctl, .compat_ioctl = compat_ptr_ioctl, + .uring_cmd = nvme_ns_chr_uring_cmd, }; static int nvme_add_ns_cdev(struct nvme_ns *ns) @@ -4090,11 +4137,26 @@ out: static void nvme_validate_or_alloc_ns(struct nvme_ctrl *ctrl, unsigned nsid) { struct nvme_ns_ids ids = { }; + struct nvme_id_ns_cs_indep *id; struct nvme_ns *ns; + bool ready = true; if (nvme_identify_ns_descs(ctrl, nsid, &ids)) return; + /* + * Check if the namespace is ready. If not ignore it, we will get an + * AEN once it becomes ready and restart the scan. + */ + if ((ctrl->cap & NVME_CAP_CRMS_CRIMS) && + !nvme_identify_ns_cs_indep(ctrl, nsid, &id)) { + ready = id->nstat & NVME_NSTAT_NRDY; + kfree(id); + } + + if (!ready) + return; + ns = nvme_find_get_ns(ctrl, nsid); if (ns) { nvme_validate_ns(ns, &ids); @@ -4237,11 +4299,26 @@ static void nvme_scan_work(struct work_struct *work) { struct nvme_ctrl *ctrl = container_of(work, struct nvme_ctrl, scan_work); + int ret; /* No tagset on a live ctrl means IO queues could not created */ if (ctrl->state != NVME_CTRL_LIVE || !ctrl->tagset) return; + /* + * Identify controller limits can change at controller reset due to + * new firmware download, even though it is not common we cannot ignore + * such scenario. Controller's non-mdts limits are reported in the unit + * of logical blocks that is dependent on the format of attached + * namespace. Hence re-read the limits at the time of ns allocation. + */ + ret = nvme_init_non_mdts_limits(ctrl); + if (ret < 0) { + dev_warn(ctrl->device, + "reading non-mdts-limits failed: %d\n", ret); + return; + } + if (test_and_clear_bit(NVME_AER_NOTICE_NS_CHANGED, &ctrl->events)) { dev_info(ctrl->device, "rescanning namespaces.\n"); nvme_clear_changed_ns_log(ctrl); @@ -4839,6 +4916,8 @@ static inline void _nvme_check_size(void) BUILD_BUG_ON(sizeof(struct nvme_command) != 64); BUILD_BUG_ON(sizeof(struct nvme_id_ctrl) != NVME_IDENTIFY_DATA_SIZE); BUILD_BUG_ON(sizeof(struct nvme_id_ns) != NVME_IDENTIFY_DATA_SIZE); + BUILD_BUG_ON(sizeof(struct nvme_id_ns_cs_indep) != + NVME_IDENTIFY_DATA_SIZE); BUILD_BUG_ON(sizeof(struct nvme_id_ns_zns) != NVME_IDENTIFY_DATA_SIZE); BUILD_BUG_ON(sizeof(struct nvme_id_ns_nvm) != NVME_IDENTIFY_DATA_SIZE); BUILD_BUG_ON(sizeof(struct nvme_id_ctrl_zns) != NVME_IDENTIFY_DATA_SIZE); diff --git a/drivers/nvme/host/fabrics.h b/drivers/nvme/host/fabrics.h index 1e3a09cad961..46d6e194ac2b 100644 --- a/drivers/nvme/host/fabrics.h +++ b/drivers/nvme/host/fabrics.h @@ -187,6 +187,14 @@ static inline char *nvmf_ctrl_subsysnqn(struct nvme_ctrl *ctrl) return ctrl->subsys->subnqn; } +static inline void nvmf_complete_timed_out_request(struct request *rq) +{ + if (blk_mq_request_started(rq) && !blk_mq_request_completed(rq)) { + nvme_req(rq)->status = NVME_SC_HOST_ABORTED_CMD; + blk_mq_complete_request(rq); + } +} + int nvmf_reg_read32(struct nvme_ctrl *ctrl, u32 off, u32 *val); int nvmf_reg_read64(struct nvme_ctrl *ctrl, u32 off, u64 *val); int nvmf_reg_write32(struct nvme_ctrl *ctrl, u32 off, u32 val); diff --git a/drivers/nvme/host/fc.c b/drivers/nvme/host/fc.c index 080f85f4105f..7ae72c7a211b 100644 --- a/drivers/nvme/host/fc.c +++ b/drivers/nvme/host/fc.c @@ -3831,6 +3831,9 @@ process_local_list: return count; } +static DEVICE_ATTR(nvme_discovery, 0200, NULL, nvme_fc_nvme_discovery_store); + +#ifdef CONFIG_BLK_CGROUP_FC_APPID /* Parse the cgroup id from a buf and return the length of cgrpid */ static int fc_parse_cgrpid(const char *buf, u64 *id) { @@ -3854,12 +3857,10 @@ static int fc_parse_cgrpid(const char *buf, u64 *id) } /* - * fc_update_appid: Parse and update the appid in the blkcg associated with - * cgroupid. - * @buf: buf contains both cgrpid and appid info - * @count: size of the buffer + * Parse and update the appid in the blkcg associated with the cgroupid. */ -static int fc_update_appid(const char *buf, size_t count) +static ssize_t fc_appid_store(struct device *dev, + struct device_attribute *attr, const char *buf, size_t count) { u64 cgrp_id; int appid_len = 0; @@ -3887,23 +3888,14 @@ static int fc_update_appid(const char *buf, size_t count) return ret; return count; } - -static ssize_t fc_appid_store(struct device *dev, - struct device_attribute *attr, const char *buf, size_t count) -{ - int ret = 0; - - ret = fc_update_appid(buf, count); - if (ret < 0) - return -EINVAL; - return count; -} -static DEVICE_ATTR(nvme_discovery, 0200, NULL, nvme_fc_nvme_discovery_store); static DEVICE_ATTR(appid_store, 0200, NULL, fc_appid_store); +#endif /* CONFIG_BLK_CGROUP_FC_APPID */ static struct attribute *nvme_fc_attrs[] = { &dev_attr_nvme_discovery.attr, +#ifdef CONFIG_BLK_CGROUP_FC_APPID &dev_attr_appid_store.attr, +#endif NULL }; diff --git a/drivers/nvme/host/ioctl.c b/drivers/nvme/host/ioctl.c index 554566371ffa..096b1b47d750 100644 --- a/drivers/nvme/host/ioctl.c +++ b/drivers/nvme/host/ioctl.c @@ -5,6 +5,7 @@ */ #include <linux/ptrace.h> /* for force_successful_syscall_return */ #include <linux/nvme_ioctl.h> +#include <linux/io_uring.h> #include "nvme.h" /* @@ -53,10 +54,21 @@ out: return ERR_PTR(ret); } -static int nvme_submit_user_cmd(struct request_queue *q, +static int nvme_finish_user_metadata(struct request *req, void __user *ubuf, + void *meta, unsigned len, int ret) +{ + if (!ret && req_op(req) == REQ_OP_DRV_IN && + copy_to_user(ubuf, meta, len)) + ret = -EFAULT; + kfree(meta); + return ret; +} + +static struct request *nvme_alloc_user_request(struct request_queue *q, struct nvme_command *cmd, void __user *ubuffer, unsigned bufflen, void __user *meta_buffer, unsigned meta_len, - u32 meta_seed, u64 *result, unsigned timeout, bool vec) + u32 meta_seed, void **metap, unsigned timeout, bool vec, + unsigned int rq_flags, blk_mq_req_flags_t blk_flags) { bool write = nvme_is_write(cmd); struct nvme_ns *ns = q->queuedata; @@ -66,9 +78,9 @@ static int nvme_submit_user_cmd(struct request_queue *q, void *meta = NULL; int ret; - req = blk_mq_alloc_request(q, nvme_req_op(cmd), 0); + req = blk_mq_alloc_request(q, nvme_req_op(cmd) | rq_flags, blk_flags); if (IS_ERR(req)) - return PTR_ERR(req); + return req; nvme_init_request(req, cmd); if (timeout) @@ -105,26 +117,50 @@ static int nvme_submit_user_cmd(struct request_queue *q, goto out_unmap; } req->cmd_flags |= REQ_INTEGRITY; + *metap = meta; } } + return req; + +out_unmap: + if (bio) + blk_rq_unmap_user(bio); +out: + blk_mq_free_request(req); + return ERR_PTR(ret); +} + +static int nvme_submit_user_cmd(struct request_queue *q, + struct nvme_command *cmd, void __user *ubuffer, + unsigned bufflen, void __user *meta_buffer, unsigned meta_len, + u32 meta_seed, u64 *result, unsigned timeout, bool vec) +{ + struct request *req; + void *meta = NULL; + struct bio *bio; + int ret; + + req = nvme_alloc_user_request(q, cmd, ubuffer, bufflen, meta_buffer, + meta_len, meta_seed, &meta, timeout, vec, 0, 0); + if (IS_ERR(req)) + return PTR_ERR(req); + + bio = req->bio; + ret = nvme_execute_passthru_rq(req); + if (result) *result = le64_to_cpu(nvme_req(req)->result.u64); - if (meta && !ret && !write) { - if (copy_to_user(meta_buffer, meta, meta_len)) - ret = -EFAULT; - } - kfree(meta); - out_unmap: + if (meta) + ret = nvme_finish_user_metadata(req, meta_buffer, meta, + meta_len, ret); if (bio) blk_rq_unmap_user(bio); - out: blk_mq_free_request(req); return ret; } - static int nvme_submit_io(struct nvme_ns *ns, struct nvme_user_io __user *uio) { struct nvme_user_io io; @@ -296,6 +332,139 @@ static int nvme_user_cmd64(struct nvme_ctrl *ctrl, struct nvme_ns *ns, return status; } +struct nvme_uring_data { + __u64 metadata; + __u64 addr; + __u32 data_len; + __u32 metadata_len; + __u32 timeout_ms; +}; + +/* + * This overlays struct io_uring_cmd pdu. + * Expect build errors if this grows larger than that. + */ +struct nvme_uring_cmd_pdu { + union { + struct bio *bio; + struct request *req; + }; + void *meta; /* kernel-resident buffer */ + void __user *meta_buffer; + u32 meta_len; +}; + +static inline struct nvme_uring_cmd_pdu *nvme_uring_cmd_pdu( + struct io_uring_cmd *ioucmd) +{ + return (struct nvme_uring_cmd_pdu *)&ioucmd->pdu; +} + +static void nvme_uring_task_cb(struct io_uring_cmd *ioucmd) +{ + struct nvme_uring_cmd_pdu *pdu = nvme_uring_cmd_pdu(ioucmd); + struct request *req = pdu->req; + struct bio *bio = req->bio; + int status; + u64 result; + + if (nvme_req(req)->flags & NVME_REQ_CANCELLED) + status = -EINTR; + else + status = nvme_req(req)->status; + + result = le64_to_cpu(nvme_req(req)->result.u64); + + if (pdu->meta) + status = nvme_finish_user_metadata(req, pdu->meta_buffer, + pdu->meta, pdu->meta_len, status); + if (bio) + blk_rq_unmap_user(bio); + blk_mq_free_request(req); + + io_uring_cmd_done(ioucmd, status, result); +} + +static void nvme_uring_cmd_end_io(struct request *req, blk_status_t err) +{ + struct io_uring_cmd *ioucmd = req->end_io_data; + struct nvme_uring_cmd_pdu *pdu = nvme_uring_cmd_pdu(ioucmd); + /* extract bio before reusing the same field for request */ + struct bio *bio = pdu->bio; + + pdu->req = req; + req->bio = bio; + /* this takes care of moving rest of completion-work to task context */ + io_uring_cmd_complete_in_task(ioucmd, nvme_uring_task_cb); +} + +static int nvme_uring_cmd_io(struct nvme_ctrl *ctrl, struct nvme_ns *ns, + struct io_uring_cmd *ioucmd, unsigned int issue_flags, bool vec) +{ + struct nvme_uring_cmd_pdu *pdu = nvme_uring_cmd_pdu(ioucmd); + const struct nvme_uring_cmd *cmd = ioucmd->cmd; + struct request_queue *q = ns ? ns->queue : ctrl->admin_q; + struct nvme_uring_data d; + struct nvme_command c; + struct request *req; + unsigned int rq_flags = 0; + blk_mq_req_flags_t blk_flags = 0; + void *meta = NULL; + + if (!capable(CAP_SYS_ADMIN)) + return -EACCES; + + c.common.opcode = READ_ONCE(cmd->opcode); + c.common.flags = READ_ONCE(cmd->flags); + if (c.common.flags) + return -EINVAL; + + c.common.command_id = 0; + c.common.nsid = cpu_to_le32(cmd->nsid); + if (!nvme_validate_passthru_nsid(ctrl, ns, le32_to_cpu(c.common.nsid))) + return -EINVAL; + + c.common.cdw2[0] = cpu_to_le32(READ_ONCE(cmd->cdw2)); + c.common.cdw2[1] = cpu_to_le32(READ_ONCE(cmd->cdw3)); + c.common.metadata = 0; + c.common.dptr.prp1 = c.common.dptr.prp2 = 0; + c.common.cdw10 = cpu_to_le32(READ_ONCE(cmd->cdw10)); + c.common.cdw11 = cpu_to_le32(READ_ONCE(cmd->cdw11)); + c.common.cdw12 = cpu_to_le32(READ_ONCE(cmd->cdw12)); + c.common.cdw13 = cpu_to_le32(READ_ONCE(cmd->cdw13)); + c.common.cdw14 = cpu_to_le32(READ_ONCE(cmd->cdw14)); + c.common.cdw15 = cpu_to_le32(READ_ONCE(cmd->cdw15)); + + d.metadata = READ_ONCE(cmd->metadata); + d.addr = READ_ONCE(cmd->addr); + d.data_len = READ_ONCE(cmd->data_len); + d.metadata_len = READ_ONCE(cmd->metadata_len); + d.timeout_ms = READ_ONCE(cmd->timeout_ms); + + if (issue_flags & IO_URING_F_NONBLOCK) { + rq_flags = REQ_NOWAIT; + blk_flags = BLK_MQ_REQ_NOWAIT; + } + + req = nvme_alloc_user_request(q, &c, nvme_to_user_ptr(d.addr), + d.data_len, nvme_to_user_ptr(d.metadata), + d.metadata_len, 0, &meta, d.timeout_ms ? + msecs_to_jiffies(d.timeout_ms) : 0, vec, rq_flags, + blk_flags); + if (IS_ERR(req)) + return PTR_ERR(req); + req->end_io_data = ioucmd; + + /* to free bio on completion, as req->bio will be null at that time */ + pdu->bio = req->bio; + pdu->meta = meta; + pdu->meta_buffer = nvme_to_user_ptr(d.metadata); + pdu->meta_len = d.metadata_len; + + blk_execute_rq_nowait(req, 0, nvme_uring_cmd_end_io); + return -EIOCBQUEUED; +} + static bool is_ctrl_ioctl(unsigned int cmd) { if (cmd == NVME_IOCTL_ADMIN_CMD || cmd == NVME_IOCTL_ADMIN64_CMD) @@ -387,6 +556,53 @@ long nvme_ns_chr_ioctl(struct file *file, unsigned int cmd, unsigned long arg) return __nvme_ioctl(ns, cmd, (void __user *)arg); } +static int nvme_uring_cmd_checks(unsigned int issue_flags) +{ + /* IOPOLL not supported yet */ + if (issue_flags & IO_URING_F_IOPOLL) + return -EOPNOTSUPP; + + /* NVMe passthrough requires big SQE/CQE support */ + if ((issue_flags & (IO_URING_F_SQE128|IO_URING_F_CQE32)) != + (IO_URING_F_SQE128|IO_URING_F_CQE32)) + return -EOPNOTSUPP; + return 0; +} + +static int nvme_ns_uring_cmd(struct nvme_ns *ns, struct io_uring_cmd *ioucmd, + unsigned int issue_flags) +{ + struct nvme_ctrl *ctrl = ns->ctrl; + int ret; + + BUILD_BUG_ON(sizeof(struct nvme_uring_cmd_pdu) > sizeof(ioucmd->pdu)); + + ret = nvme_uring_cmd_checks(issue_flags); + if (ret) + return ret; + + switch (ioucmd->cmd_op) { + case NVME_URING_CMD_IO: + ret = nvme_uring_cmd_io(ctrl, ns, ioucmd, issue_flags, false); + break; + case NVME_URING_CMD_IO_VEC: + ret = nvme_uring_cmd_io(ctrl, ns, ioucmd, issue_flags, true); + break; + default: + ret = -ENOTTY; + } + + return ret; +} + +int nvme_ns_chr_uring_cmd(struct io_uring_cmd *ioucmd, unsigned int issue_flags) +{ + struct nvme_ns *ns = container_of(file_inode(ioucmd->file)->i_cdev, + struct nvme_ns, cdev); + + return nvme_ns_uring_cmd(ns, ioucmd, issue_flags); +} + #ifdef CONFIG_NVME_MULTIPATH static int nvme_ns_head_ctrl_ioctl(struct nvme_ns *ns, unsigned int cmd, void __user *argp, struct nvme_ns_head *head, int srcu_idx) @@ -453,8 +669,46 @@ out_unlock: srcu_read_unlock(&head->srcu, srcu_idx); return ret; } + +int nvme_ns_head_chr_uring_cmd(struct io_uring_cmd *ioucmd, + unsigned int issue_flags) +{ + struct cdev *cdev = file_inode(ioucmd->file)->i_cdev; + struct nvme_ns_head *head = container_of(cdev, struct nvme_ns_head, cdev); + int srcu_idx = srcu_read_lock(&head->srcu); + struct nvme_ns *ns = nvme_find_path(head); + int ret = -EINVAL; + + if (ns) + ret = nvme_ns_uring_cmd(ns, ioucmd, issue_flags); + srcu_read_unlock(&head->srcu, srcu_idx); + return ret; +} #endif /* CONFIG_NVME_MULTIPATH */ +int nvme_dev_uring_cmd(struct io_uring_cmd *ioucmd, unsigned int issue_flags) +{ + struct nvme_ctrl *ctrl = ioucmd->file->private_data; + int ret; + + ret = nvme_uring_cmd_checks(issue_flags); + if (ret) + return ret; + + switch (ioucmd->cmd_op) { + case NVME_URING_CMD_ADMIN: + ret = nvme_uring_cmd_io(ctrl, NULL, ioucmd, issue_flags, false); + break; + case NVME_URING_CMD_ADMIN_VEC: + ret = nvme_uring_cmd_io(ctrl, NULL, ioucmd, issue_flags, true); + break; + default: + ret = -ENOTTY; + } + + return ret; +} + static int nvme_dev_user_cmd(struct nvme_ctrl *ctrl, void __user *argp) { struct nvme_ns *ns; diff --git a/drivers/nvme/host/multipath.c b/drivers/nvme/host/multipath.c index d464fdf978fb..d3e2440d8abb 100644 --- a/drivers/nvme/host/multipath.c +++ b/drivers/nvme/host/multipath.c @@ -437,6 +437,7 @@ static const struct file_operations nvme_ns_head_chr_fops = { .release = nvme_ns_head_chr_release, .unlocked_ioctl = nvme_ns_head_chr_ioctl, .compat_ioctl = compat_ptr_ioctl, + .uring_cmd = nvme_ns_head_chr_uring_cmd, }; static int nvme_add_ns_head_cdev(struct nvme_ns_head *head) diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h index a2b53ca63335..9b72b6ecf33c 100644 --- a/drivers/nvme/host/nvme.h +++ b/drivers/nvme/host/nvme.h @@ -284,6 +284,7 @@ struct nvme_ctrl { #endif u16 crdt[3]; u16 oncs; + u32 dmrsl; u16 oacs; u16 sqsize; u32 max_namespaces; @@ -782,7 +783,12 @@ long nvme_ns_head_chr_ioctl(struct file *file, unsigned int cmd, unsigned long arg); long nvme_dev_ioctl(struct file *file, unsigned int cmd, unsigned long arg); +int nvme_ns_chr_uring_cmd(struct io_uring_cmd *ioucmd, + unsigned int issue_flags); +int nvme_ns_head_chr_uring_cmd(struct io_uring_cmd *ioucmd, + unsigned int issue_flags); int nvme_getgeo(struct block_device *bdev, struct hd_geometry *geo); +int nvme_dev_uring_cmd(struct io_uring_cmd *ioucmd, unsigned int issue_flags); extern const struct attribute_group *nvme_ns_id_attr_groups[]; extern const struct pr_ops nvme_pr_ops; diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index 3aacf1c0d5a5..5a98a7de0964 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -1439,6 +1439,7 @@ static enum blk_eh_timer_return nvme_timeout(struct request *req, bool reserved) nvme_init_request(abort_req, &cmd); abort_req->end_io_data = NULL; + abort_req->rq_flags |= RQF_QUIET; blk_execute_rq_nowait(abort_req, false, abort_endio); /* @@ -1775,6 +1776,7 @@ static int nvme_alloc_admin_tags(struct nvme_dev *dev) dev->ctrl.admin_q = blk_mq_init_queue(&dev->admin_tagset); if (IS_ERR(dev->ctrl.admin_q)) { blk_mq_free_tag_set(&dev->admin_tagset); + dev->ctrl.admin_q = NULL; return -ENOMEM; } if (!blk_get_queue(dev->ctrl.admin_q)) { @@ -2486,6 +2488,7 @@ static int nvme_delete_queue(struct nvme_queue *nvmeq, u8 opcode) req->end_io_data = nvmeq; init_completion(&nvmeq->delete_done); + req->rq_flags |= RQF_QUIET; blk_execute_rq_nowait(req, false, opcode == nvme_admin_delete_cq ? nvme_del_cq_end : nvme_del_queue_end); return 0; @@ -2675,7 +2678,7 @@ static void nvme_dev_disable(struct nvme_dev *dev, bool shutdown) struct pci_dev *pdev = to_pci_dev(dev->dev); mutex_lock(&dev->shutdown_lock); - if (pci_is_enabled(pdev)) { + if (pci_device_is_present(pdev) && pci_is_enabled(pdev)) { u32 csts = readl(dev->bar + NVME_REG_CSTS); if (dev->ctrl.state == NVME_CTRL_LIVE || diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c index d9f19d901313..b87c8ae41d9b 100644 --- a/drivers/nvme/host/rdma.c +++ b/drivers/nvme/host/rdma.c @@ -2010,10 +2010,7 @@ static void nvme_rdma_complete_timed_out(struct request *rq) struct nvme_rdma_queue *queue = req->queue; nvme_rdma_stop_queue(queue); - if (blk_mq_request_started(rq) && !blk_mq_request_completed(rq)) { - nvme_req(rq)->status = NVME_SC_HOST_ABORTED_CMD; - blk_mq_complete_request(rq); - } + nvmf_complete_timed_out_request(rq); } static enum blk_eh_timer_return diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c index ad3a2bf2f1e9..bb67538d241b 100644 --- a/drivers/nvme/host/tcp.c +++ b/drivers/nvme/host/tcp.c @@ -2318,10 +2318,7 @@ static void nvme_tcp_complete_timed_out(struct request *rq) struct nvme_ctrl *ctrl = &req->queue->ctrl->ctrl; nvme_tcp_stop_queue(ctrl, nvme_tcp_queue_id(req->queue)); - if (blk_mq_request_started(rq) && !blk_mq_request_completed(rq)) { - nvme_req(rq)->status = NVME_SC_HOST_ABORTED_CMD; - blk_mq_complete_request(rq); - } + nvmf_complete_timed_out_request(rq); } static enum blk_eh_timer_return diff --git a/drivers/nvme/target/io-cmd-bdev.c b/drivers/nvme/target/io-cmd-bdev.c index d886c2c59554..27a72504d31c 100644 --- a/drivers/nvme/target/io-cmd-bdev.c +++ b/drivers/nvme/target/io-cmd-bdev.c @@ -360,7 +360,7 @@ static u16 nvmet_bdev_discard_range(struct nvmet_req *req, ret = __blkdev_issue_discard(ns->bdev, nvmet_lba_to_sect(ns, range->slba), le32_to_cpu(range->nlb) << (ns->blksize_shift - 9), - GFP_KERNEL, 0, bio); + GFP_KERNEL, bio); if (ret && ret != -EOPNOTSUPP) { req->error_slba = le64_to_cpu(range->slba); return errno_to_nvme_status(req, ret); diff --git a/drivers/nvme/target/zns.c b/drivers/nvme/target/zns.c index e34718b09550..82b61acf7a72 100644 --- a/drivers/nvme/target/zns.c +++ b/drivers/nvme/target/zns.c @@ -34,8 +34,7 @@ static int validate_conv_zones_cb(struct blk_zone *z, bool nvmet_bdev_zns_enable(struct nvmet_ns *ns) { - struct request_queue *q = ns->bdev->bd_disk->queue; - u8 zasl = nvmet_zasl(queue_max_zone_append_sectors(q)); + u8 zasl = nvmet_zasl(bdev_max_zone_append_sectors(ns->bdev)); struct gendisk *bd_disk = ns->bdev->bd_disk; int ret; diff --git a/drivers/pci/controller/dwc/pcie-qcom.c b/drivers/pci/controller/dwc/pcie-qcom.c index 6ab90891801d..816028c0f6ed 100644 --- a/drivers/pci/controller/dwc/pcie-qcom.c +++ b/drivers/pci/controller/dwc/pcie-qcom.c @@ -1550,6 +1550,11 @@ static const struct qcom_pcie_cfg sc7280_cfg = { .pipe_clk_need_muxing = true, }; +static const struct qcom_pcie_cfg sc8180x_cfg = { + .ops = &ops_1_9_0, + .has_tbu_clk = true, +}; + static const struct dw_pcie_ops dw_pcie_ops = { .link_up = qcom_pcie_link_up, .start_link = qcom_pcie_start_link, @@ -1656,7 +1661,7 @@ static const struct of_device_id qcom_pcie_match[] = { { .compatible = "qcom,pcie-qcs404", .data = &ipq4019_cfg }, { .compatible = "qcom,pcie-sdm845", .data = &sdm845_cfg }, { .compatible = "qcom,pcie-sm8250", .data = &sm8250_cfg }, - { .compatible = "qcom,pcie-sc8180x", .data = &sm8250_cfg }, + { .compatible = "qcom,pcie-sc8180x", .data = &sc8180x_cfg }, { .compatible = "qcom,pcie-sm8450-pcie0", .data = &sm8450_pcie0_cfg }, { .compatible = "qcom,pcie-sm8450-pcie1", .data = &sm8450_pcie1_cfg }, { .compatible = "qcom,pcie-sc7280", .data = &sc7280_cfg }, diff --git a/drivers/pci/controller/pci-aardvark.c b/drivers/pci/controller/pci-aardvark.c index 09d9bf465d72..ffec82c8a523 100644 --- a/drivers/pci/controller/pci-aardvark.c +++ b/drivers/pci/controller/pci-aardvark.c @@ -272,7 +272,6 @@ struct advk_pcie { u32 actions; } wins[OB_WIN_COUNT]; u8 wins_count; - int irq; struct irq_domain *rp_irq_domain; struct irq_domain *irq_domain; struct irq_chip irq_chip; @@ -1570,26 +1569,21 @@ static void advk_pcie_handle_int(struct advk_pcie *pcie) } } -static void advk_pcie_irq_handler(struct irq_desc *desc) +static irqreturn_t advk_pcie_irq_handler(int irq, void *arg) { - struct advk_pcie *pcie = irq_desc_get_handler_data(desc); - struct irq_chip *chip = irq_desc_get_chip(desc); - u32 val, mask, status; + struct advk_pcie *pcie = arg; + u32 status; - chained_irq_enter(chip, desc); + status = advk_readl(pcie, HOST_CTRL_INT_STATUS_REG); + if (!(status & PCIE_IRQ_CORE_INT)) + return IRQ_NONE; - val = advk_readl(pcie, HOST_CTRL_INT_STATUS_REG); - mask = advk_readl(pcie, HOST_CTRL_INT_MASK_REG); - status = val & ((~mask) & PCIE_IRQ_ALL_MASK); + advk_pcie_handle_int(pcie); - if (status & PCIE_IRQ_CORE_INT) { - advk_pcie_handle_int(pcie); + /* Clear interrupt */ + advk_writel(pcie, PCIE_IRQ_CORE_INT, HOST_CTRL_INT_STATUS_REG); - /* Clear interrupt */ - advk_writel(pcie, PCIE_IRQ_CORE_INT, HOST_CTRL_INT_STATUS_REG); - } - - chained_irq_exit(chip, desc); + return IRQ_HANDLED; } static int advk_pcie_map_irq(const struct pci_dev *dev, u8 slot, u8 pin) @@ -1669,7 +1663,7 @@ static int advk_pcie_probe(struct platform_device *pdev) struct advk_pcie *pcie; struct pci_host_bridge *bridge; struct resource_entry *entry; - int ret; + int ret, irq; bridge = devm_pci_alloc_host_bridge(dev, sizeof(struct advk_pcie)); if (!bridge) @@ -1755,9 +1749,17 @@ static int advk_pcie_probe(struct platform_device *pdev) if (IS_ERR(pcie->base)) return PTR_ERR(pcie->base); - pcie->irq = platform_get_irq(pdev, 0); - if (pcie->irq < 0) - return pcie->irq; + irq = platform_get_irq(pdev, 0); + if (irq < 0) + return irq; + + ret = devm_request_irq(dev, irq, advk_pcie_irq_handler, + IRQF_SHARED | IRQF_NO_THREAD, "advk-pcie", + pcie); + if (ret) { + dev_err(dev, "Failed to register interrupt\n"); + return ret; + } pcie->reset_gpio = devm_gpiod_get_from_of_node(dev, dev->of_node, "reset-gpios", 0, @@ -1814,15 +1816,12 @@ static int advk_pcie_probe(struct platform_device *pdev) return ret; } - irq_set_chained_handler_and_data(pcie->irq, advk_pcie_irq_handler, pcie); - bridge->sysdata = pcie; bridge->ops = &advk_pcie_ops; bridge->map_irq = advk_pcie_map_irq; ret = pci_host_probe(bridge); if (ret < 0) { - irq_set_chained_handler_and_data(pcie->irq, NULL, NULL); advk_pcie_remove_rp_irq_domain(pcie); advk_pcie_remove_msi_irq_domain(pcie); advk_pcie_remove_irq_domain(pcie); @@ -1871,9 +1870,6 @@ static int advk_pcie_remove(struct platform_device *pdev) advk_writel(pcie, PCIE_ISR1_ALL_MASK, PCIE_ISR1_REG); advk_writel(pcie, PCIE_IRQ_ALL_MASK, HOST_CTRL_INT_STATUS_REG); - /* Remove IRQ handler */ - irq_set_chained_handler_and_data(pcie->irq, NULL, NULL); - /* Remove IRQ domains */ advk_pcie_remove_rp_irq_domain(pcie); advk_pcie_remove_msi_irq_domain(pcie); diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c index 9ecce435fb3f..d25122fbe98a 100644 --- a/drivers/pci/pci.c +++ b/drivers/pci/pci.c @@ -2920,6 +2920,16 @@ static const struct dmi_system_id bridge_d3_blacklist[] = { DMI_MATCH(DMI_BOARD_VENDOR, "Gigabyte Technology Co., Ltd."), DMI_MATCH(DMI_BOARD_NAME, "X299 DESIGNARE EX-CF"), }, + /* + * Downstream device is not accessible after putting a root port + * into D3cold and back into D0 on Elo i2. + */ + .ident = "Elo i2", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Elo Touch Solutions"), + DMI_MATCH(DMI_PRODUCT_NAME, "Elo i2"), + DMI_MATCH(DMI_PRODUCT_VERSION, "RevB"), + }, }, #endif { } diff --git a/drivers/pinctrl/aspeed/pinctrl-aspeed-g6.c b/drivers/pinctrl/aspeed/pinctrl-aspeed-g6.c index a3fa03bcd9a3..80838dc54b3a 100644 --- a/drivers/pinctrl/aspeed/pinctrl-aspeed-g6.c +++ b/drivers/pinctrl/aspeed/pinctrl-aspeed-g6.c @@ -1236,18 +1236,17 @@ FUNC_GROUP_DECL(SALT8, AA12); FUNC_GROUP_DECL(WDTRST4, AA12); #define AE12 196 -SIG_EXPR_LIST_DECL_SEMG(AE12, FWSPIDQ2, FWQSPID, FWSPID, - SIG_DESC_SET(SCU438, 4)); +SIG_EXPR_LIST_DECL_SESG(AE12, FWSPIQ2, FWQSPI, SIG_DESC_SET(SCU438, 4)); SIG_EXPR_LIST_DECL_SESG(AE12, GPIOY4, GPIOY4); -PIN_DECL_(AE12, SIG_EXPR_LIST_PTR(AE12, FWSPIDQ2), +PIN_DECL_(AE12, SIG_EXPR_LIST_PTR(AE12, FWSPIQ2), SIG_EXPR_LIST_PTR(AE12, GPIOY4)); #define AF12 197 -SIG_EXPR_LIST_DECL_SEMG(AF12, FWSPIDQ3, FWQSPID, FWSPID, - SIG_DESC_SET(SCU438, 5)); +SIG_EXPR_LIST_DECL_SESG(AF12, FWSPIQ3, FWQSPI, SIG_DESC_SET(SCU438, 5)); SIG_EXPR_LIST_DECL_SESG(AF12, GPIOY5, GPIOY5); -PIN_DECL_(AF12, SIG_EXPR_LIST_PTR(AF12, FWSPIDQ3), +PIN_DECL_(AF12, SIG_EXPR_LIST_PTR(AF12, FWSPIQ3), SIG_EXPR_LIST_PTR(AF12, GPIOY5)); +FUNC_GROUP_DECL(FWQSPI, AE12, AF12); #define AC12 198 SSSF_PIN_DECL(AC12, GPIOY6, FWSPIABR, SIG_DESC_SET(SCU438, 6)); @@ -1520,9 +1519,8 @@ SIG_EXPR_LIST_DECL_SEMG(Y4, EMMCDAT7, EMMCG8, EMMC, SIG_DESC_SET(SCU404, 3)); PIN_DECL_3(Y4, GPIO18E3, FWSPIDMISO, VBMISO, EMMCDAT7); GROUP_DECL(FWSPID, Y1, Y2, Y3, Y4); -GROUP_DECL(FWQSPID, Y1, Y2, Y3, Y4, AE12, AF12); GROUP_DECL(EMMCG8, AB4, AA4, AC4, AA5, Y5, AB5, AB6, AC5, Y1, Y2, Y3, Y4); -FUNC_DECL_2(FWSPID, FWSPID, FWQSPID); +FUNC_DECL_1(FWSPID, FWSPID); FUNC_GROUP_DECL(VB, Y1, Y2, Y3, Y4); FUNC_DECL_3(EMMC, EMMCG1, EMMCG4, EMMCG8); /* @@ -1918,7 +1916,7 @@ static const struct aspeed_pin_group aspeed_g6_groups[] = { ASPEED_PINCTRL_GROUP(FSI2), ASPEED_PINCTRL_GROUP(FWSPIABR), ASPEED_PINCTRL_GROUP(FWSPID), - ASPEED_PINCTRL_GROUP(FWQSPID), + ASPEED_PINCTRL_GROUP(FWQSPI), ASPEED_PINCTRL_GROUP(FWSPIWP), ASPEED_PINCTRL_GROUP(GPIT0), ASPEED_PINCTRL_GROUP(GPIT1), @@ -2160,6 +2158,7 @@ static const struct aspeed_pin_function aspeed_g6_functions[] = { ASPEED_PINCTRL_FUNC(FSI2), ASPEED_PINCTRL_FUNC(FWSPIABR), ASPEED_PINCTRL_FUNC(FWSPID), + ASPEED_PINCTRL_FUNC(FWQSPI), ASPEED_PINCTRL_FUNC(FWSPIWP), ASPEED_PINCTRL_FUNC(GPIT0), ASPEED_PINCTRL_FUNC(GPIT1), diff --git a/drivers/pinctrl/mediatek/pinctrl-mt8365.c b/drivers/pinctrl/mediatek/pinctrl-mt8365.c index 727c65221aef..57f37a294063 100644 --- a/drivers/pinctrl/mediatek/pinctrl-mt8365.c +++ b/drivers/pinctrl/mediatek/pinctrl-mt8365.c @@ -259,7 +259,7 @@ static const struct mtk_pin_ies_smt_set mt8365_ies_set[] = { MTK_PIN_IES_SMT_SPEC(104, 104, 0x420, 13), MTK_PIN_IES_SMT_SPEC(105, 109, 0x420, 14), MTK_PIN_IES_SMT_SPEC(110, 113, 0x420, 15), - MTK_PIN_IES_SMT_SPEC(114, 112, 0x420, 16), + MTK_PIN_IES_SMT_SPEC(114, 116, 0x420, 16), MTK_PIN_IES_SMT_SPEC(117, 119, 0x420, 17), MTK_PIN_IES_SMT_SPEC(120, 122, 0x420, 18), MTK_PIN_IES_SMT_SPEC(123, 125, 0x420, 19), diff --git a/drivers/pinctrl/pinctrl-amd.c b/drivers/pinctrl/pinctrl-amd.c index 1a7d686494ff..0645c2c24f50 100644 --- a/drivers/pinctrl/pinctrl-amd.c +++ b/drivers/pinctrl/pinctrl-amd.c @@ -387,6 +387,8 @@ static void amd_gpio_irq_enable(struct irq_data *d) struct gpio_chip *gc = irq_data_get_irq_chip_data(d); struct amd_gpio *gpio_dev = gpiochip_get_data(gc); + gpiochip_enable_irq(gc, d->hwirq); + raw_spin_lock_irqsave(&gpio_dev->lock, flags); pin_reg = readl(gpio_dev->base + (d->hwirq)*4); pin_reg |= BIT(INTERRUPT_ENABLE_OFF); @@ -408,6 +410,8 @@ static void amd_gpio_irq_disable(struct irq_data *d) pin_reg &= ~BIT(INTERRUPT_MASK_OFF); writel(pin_reg, gpio_dev->base + (d->hwirq)*4); raw_spin_unlock_irqrestore(&gpio_dev->lock, flags); + + gpiochip_disable_irq(gc, d->hwirq); } static void amd_gpio_irq_mask(struct irq_data *d) @@ -577,7 +581,7 @@ static void amd_irq_ack(struct irq_data *d) */ } -static struct irq_chip amd_gpio_irqchip = { +static const struct irq_chip amd_gpio_irqchip = { .name = "amd_gpio", .irq_ack = amd_irq_ack, .irq_enable = amd_gpio_irq_enable, @@ -593,7 +597,8 @@ static struct irq_chip amd_gpio_irqchip = { * the wake event. Otherwise the wake event will never clear and * prevent the system from suspending. */ - .flags = IRQCHIP_ENABLE_WAKEUP_ON_SUSPEND, + .flags = IRQCHIP_ENABLE_WAKEUP_ON_SUSPEND | IRQCHIP_IMMUTABLE, + GPIOCHIP_IRQ_RESOURCE_HELPERS, }; #define PIN_IRQ_PENDING (BIT(INTERRUPT_STS_OFF) | BIT(WAKE_STS_OFF)) @@ -1026,7 +1031,7 @@ static int amd_gpio_probe(struct platform_device *pdev) amd_gpio_irq_init(gpio_dev); girq = &gpio_dev->gc.irq; - girq->chip = &amd_gpio_irqchip; + gpio_irq_chip_set_chip(girq, &amd_gpio_irqchip); /* This will let us handle the parent IRQ in the driver */ girq->parent_handler = NULL; girq->num_parents = 0; diff --git a/drivers/pinctrl/pinctrl-apple-gpio.c b/drivers/pinctrl/pinctrl-apple-gpio.c index 72f4dd2466e1..5e610849dfc3 100644 --- a/drivers/pinctrl/pinctrl-apple-gpio.c +++ b/drivers/pinctrl/pinctrl-apple-gpio.c @@ -36,7 +36,6 @@ struct apple_gpio_pinctrl { struct pinctrl_desc pinctrl_desc; struct gpio_chip gpio_chip; - struct irq_chip irq_chip; u8 irqgrps[]; }; @@ -275,17 +274,21 @@ static unsigned int apple_gpio_irq_type(unsigned int type) static void apple_gpio_irq_mask(struct irq_data *data) { - struct apple_gpio_pinctrl *pctl = gpiochip_get_data(irq_data_get_irq_chip_data(data)); + struct gpio_chip *gc = irq_data_get_irq_chip_data(data); + struct apple_gpio_pinctrl *pctl = gpiochip_get_data(gc); apple_gpio_set_reg(pctl, data->hwirq, REG_GPIOx_MODE, FIELD_PREP(REG_GPIOx_MODE, REG_GPIOx_IN_IRQ_OFF)); + gpiochip_disable_irq(gc, data->hwirq); } static void apple_gpio_irq_unmask(struct irq_data *data) { - struct apple_gpio_pinctrl *pctl = gpiochip_get_data(irq_data_get_irq_chip_data(data)); + struct gpio_chip *gc = irq_data_get_irq_chip_data(data); + struct apple_gpio_pinctrl *pctl = gpiochip_get_data(gc); unsigned int irqtype = apple_gpio_irq_type(irqd_get_trigger_type(data)); + gpiochip_enable_irq(gc, data->hwirq); apple_gpio_set_reg(pctl, data->hwirq, REG_GPIOx_MODE, FIELD_PREP(REG_GPIOx_MODE, irqtype)); } @@ -343,13 +346,15 @@ static void apple_gpio_irq_handler(struct irq_desc *desc) chained_irq_exit(chip, desc); } -static struct irq_chip apple_gpio_irqchip = { - .name = "Apple-GPIO", - .irq_startup = apple_gpio_irq_startup, - .irq_ack = apple_gpio_irq_ack, - .irq_mask = apple_gpio_irq_mask, - .irq_unmask = apple_gpio_irq_unmask, - .irq_set_type = apple_gpio_irq_set_type, +static const struct irq_chip apple_gpio_irqchip = { + .name = "Apple-GPIO", + .irq_startup = apple_gpio_irq_startup, + .irq_ack = apple_gpio_irq_ack, + .irq_mask = apple_gpio_irq_mask, + .irq_unmask = apple_gpio_irq_unmask, + .irq_set_type = apple_gpio_irq_set_type, + .flags = IRQCHIP_IMMUTABLE, + GPIOCHIP_IRQ_RESOURCE_HELPERS, }; /* Probe & register */ @@ -360,8 +365,6 @@ static int apple_gpio_register(struct apple_gpio_pinctrl *pctl) void **irq_data = NULL; int ret; - pctl->irq_chip = apple_gpio_irqchip; - pctl->gpio_chip.label = dev_name(pctl->dev); pctl->gpio_chip.request = gpiochip_generic_request; pctl->gpio_chip.free = gpiochip_generic_free; @@ -377,7 +380,7 @@ static int apple_gpio_register(struct apple_gpio_pinctrl *pctl) if (girq->num_parents) { int i; - girq->chip = &pctl->irq_chip; + gpio_irq_chip_set_chip(girq, &apple_gpio_irqchip); girq->parent_handler = apple_gpio_irq_handler; girq->parents = kmalloc_array(girq->num_parents, diff --git a/drivers/pinctrl/pinctrl-ocelot.c b/drivers/pinctrl/pinctrl-ocelot.c index 003fb0e34153..6a956ee94494 100644 --- a/drivers/pinctrl/pinctrl-ocelot.c +++ b/drivers/pinctrl/pinctrl-ocelot.c @@ -129,6 +129,7 @@ enum { FUNC_PTP1, FUNC_PTP2, FUNC_PTP3, + FUNC_PTPSYNC_0, FUNC_PTPSYNC_1, FUNC_PTPSYNC_2, FUNC_PTPSYNC_3, @@ -252,6 +253,7 @@ static const char *const ocelot_function_names[] = { [FUNC_PTP1] = "ptp1", [FUNC_PTP2] = "ptp2", [FUNC_PTP3] = "ptp3", + [FUNC_PTPSYNC_0] = "ptpsync_0", [FUNC_PTPSYNC_1] = "ptpsync_1", [FUNC_PTPSYNC_2] = "ptpsync_2", [FUNC_PTPSYNC_3] = "ptpsync_3", @@ -983,7 +985,7 @@ LAN966X_P(31, GPIO, FC3_c, CAN1, NONE, OB_TRG, RECO_b, NON LAN966X_P(32, GPIO, FC3_c, NONE, SGPIO_a, NONE, MIIM_Sa, NONE, R); LAN966X_P(33, GPIO, FC1_b, NONE, SGPIO_a, NONE, MIIM_Sa, MIIM_b, R); LAN966X_P(34, GPIO, FC1_b, NONE, SGPIO_a, NONE, MIIM_Sa, MIIM_b, R); -LAN966X_P(35, GPIO, FC1_b, NONE, SGPIO_a, CAN0_b, NONE, NONE, R); +LAN966X_P(35, GPIO, FC1_b, PTPSYNC_0, SGPIO_a, CAN0_b, NONE, NONE, R); LAN966X_P(36, GPIO, NONE, PTPSYNC_1, NONE, CAN0_b, NONE, NONE, R); LAN966X_P(37, GPIO, FC_SHRD0, PTPSYNC_2, TWI_SLC_GATE_AD, NONE, NONE, NONE, R); LAN966X_P(38, GPIO, NONE, PTPSYNC_3, NONE, NONE, NONE, NONE, R); diff --git a/drivers/pinctrl/qcom/pinctrl-msm.c b/drivers/pinctrl/qcom/pinctrl-msm.c index 966ea6622ff3..a2abfe987ab1 100644 --- a/drivers/pinctrl/qcom/pinctrl-msm.c +++ b/drivers/pinctrl/qcom/pinctrl-msm.c @@ -42,7 +42,6 @@ * @chip: gpiochip handle. * @desc: pin controller descriptor * @restart_nb: restart notifier block. - * @irq_chip: irq chip information * @irq: parent irq for the TLMM irq_chip. * @intr_target_use_scm: route irq to application cpu using scm calls * @lock: Spinlock to protect register resources as well @@ -63,7 +62,6 @@ struct msm_pinctrl { struct pinctrl_desc desc; struct notifier_block restart_nb; - struct irq_chip irq_chip; int irq; bool intr_target_use_scm; @@ -868,6 +866,8 @@ static void msm_gpio_irq_enable(struct irq_data *d) struct gpio_chip *gc = irq_data_get_irq_chip_data(d); struct msm_pinctrl *pctrl = gpiochip_get_data(gc); + gpiochip_enable_irq(gc, d->hwirq); + if (d->parent_data) irq_chip_enable_parent(d); @@ -885,6 +885,8 @@ static void msm_gpio_irq_disable(struct irq_data *d) if (!test_bit(d->hwirq, pctrl->skip_wake_irqs)) msm_gpio_irq_mask(d); + + gpiochip_disable_irq(gc, d->hwirq); } /** @@ -958,6 +960,14 @@ static void msm_gpio_irq_ack(struct irq_data *d) raw_spin_unlock_irqrestore(&pctrl->lock, flags); } +static void msm_gpio_irq_eoi(struct irq_data *d) +{ + d = d->parent_data; + + if (d) + d->chip->irq_eoi(d); +} + static bool msm_gpio_needs_dual_edge_parent_workaround(struct irq_data *d, unsigned int type) { @@ -1255,6 +1265,26 @@ static bool msm_gpio_needs_valid_mask(struct msm_pinctrl *pctrl) return device_property_count_u16(pctrl->dev, "gpios") > 0; } +static const struct irq_chip msm_gpio_irq_chip = { + .name = "msmgpio", + .irq_enable = msm_gpio_irq_enable, + .irq_disable = msm_gpio_irq_disable, + .irq_mask = msm_gpio_irq_mask, + .irq_unmask = msm_gpio_irq_unmask, + .irq_ack = msm_gpio_irq_ack, + .irq_eoi = msm_gpio_irq_eoi, + .irq_set_type = msm_gpio_irq_set_type, + .irq_set_wake = msm_gpio_irq_set_wake, + .irq_request_resources = msm_gpio_irq_reqres, + .irq_release_resources = msm_gpio_irq_relres, + .irq_set_affinity = msm_gpio_irq_set_affinity, + .irq_set_vcpu_affinity = msm_gpio_irq_set_vcpu_affinity, + .flags = (IRQCHIP_MASK_ON_SUSPEND | + IRQCHIP_SET_TYPE_MASKED | + IRQCHIP_ENABLE_WAKEUP_ON_SUSPEND | + IRQCHIP_IMMUTABLE), +}; + static int msm_gpio_init(struct msm_pinctrl *pctrl) { struct gpio_chip *chip; @@ -1276,22 +1306,6 @@ static int msm_gpio_init(struct msm_pinctrl *pctrl) if (msm_gpio_needs_valid_mask(pctrl)) chip->init_valid_mask = msm_gpio_init_valid_mask; - pctrl->irq_chip.name = "msmgpio"; - pctrl->irq_chip.irq_enable = msm_gpio_irq_enable; - pctrl->irq_chip.irq_disable = msm_gpio_irq_disable; - pctrl->irq_chip.irq_mask = msm_gpio_irq_mask; - pctrl->irq_chip.irq_unmask = msm_gpio_irq_unmask; - pctrl->irq_chip.irq_ack = msm_gpio_irq_ack; - pctrl->irq_chip.irq_set_type = msm_gpio_irq_set_type; - pctrl->irq_chip.irq_set_wake = msm_gpio_irq_set_wake; - pctrl->irq_chip.irq_request_resources = msm_gpio_irq_reqres; - pctrl->irq_chip.irq_release_resources = msm_gpio_irq_relres; - pctrl->irq_chip.irq_set_affinity = msm_gpio_irq_set_affinity; - pctrl->irq_chip.irq_set_vcpu_affinity = msm_gpio_irq_set_vcpu_affinity; - pctrl->irq_chip.flags = IRQCHIP_MASK_ON_SUSPEND | - IRQCHIP_SET_TYPE_MASKED | - IRQCHIP_ENABLE_WAKEUP_ON_SUSPEND; - np = of_parse_phandle(pctrl->dev->of_node, "wakeup-parent", 0); if (np) { chip->irq.parent_domain = irq_find_matching_host(np, @@ -1300,7 +1314,6 @@ static int msm_gpio_init(struct msm_pinctrl *pctrl) if (!chip->irq.parent_domain) return -EPROBE_DEFER; chip->irq.child_to_parent_hwirq = msm_gpio_wakeirq; - pctrl->irq_chip.irq_eoi = irq_chip_eoi_parent; /* * Let's skip handling the GPIOs, if the parent irqchip * is handling the direct connect IRQ of the GPIO. @@ -1313,7 +1326,7 @@ static int msm_gpio_init(struct msm_pinctrl *pctrl) } girq = &chip->irq; - girq->chip = &pctrl->irq_chip; + gpio_irq_chip_set_chip(girq, &msm_gpio_irq_chip); girq->parent_handler = msm_gpio_irq_handler; girq->fwnode = pctrl->dev->fwnode; girq->num_parents = 1; diff --git a/drivers/pinctrl/sunxi/pinctrl-suniv-f1c100s.c b/drivers/pinctrl/sunxi/pinctrl-suniv-f1c100s.c index 2801ca706273..b8fc88a23cf4 100644 --- a/drivers/pinctrl/sunxi/pinctrl-suniv-f1c100s.c +++ b/drivers/pinctrl/sunxi/pinctrl-suniv-f1c100s.c @@ -51,7 +51,7 @@ static const struct sunxi_desc_pin suniv_f1c100s_pins[] = { SUNXI_FUNCTION(0x3, "pwm0"), /* PWM0 */ SUNXI_FUNCTION(0x4, "i2s"), /* IN */ SUNXI_FUNCTION(0x5, "uart1"), /* RX */ - SUNXI_FUNCTION(0x6, "spi1")), /* MOSI */ + SUNXI_FUNCTION(0x6, "spi1")), /* CLK */ SUNXI_PIN(SUNXI_PINCTRL_PIN(A, 3), SUNXI_FUNCTION(0x0, "gpio_in"), SUNXI_FUNCTION(0x1, "gpio_out"), @@ -204,7 +204,7 @@ static const struct sunxi_desc_pin suniv_f1c100s_pins[] = { SUNXI_FUNCTION(0x0, "gpio_in"), SUNXI_FUNCTION(0x1, "gpio_out"), SUNXI_FUNCTION(0x2, "lcd"), /* D20 */ - SUNXI_FUNCTION(0x3, "lvds1"), /* RX */ + SUNXI_FUNCTION(0x3, "uart2"), /* RX */ SUNXI_FUNCTION_IRQ_BANK(0x6, 0, 14)), SUNXI_PIN(SUNXI_PINCTRL_PIN(D, 15), SUNXI_FUNCTION(0x0, "gpio_in"), diff --git a/drivers/platform/surface/aggregator/core.c b/drivers/platform/surface/aggregator/core.c index d384d36098c2..a62c5dfe42d6 100644 --- a/drivers/platform/surface/aggregator/core.c +++ b/drivers/platform/surface/aggregator/core.c @@ -817,7 +817,7 @@ err_cpkg: err_bus: return status; } -module_init(ssam_core_init); +subsys_initcall(ssam_core_init); static void __exit ssam_core_exit(void) { diff --git a/drivers/platform/surface/surface_gpe.c b/drivers/platform/surface/surface_gpe.c index c1775db29efb..ec66fde28e75 100644 --- a/drivers/platform/surface/surface_gpe.c +++ b/drivers/platform/surface/surface_gpe.c @@ -100,6 +100,14 @@ static const struct dmi_system_id dmi_lid_device_table[] = { .driver_data = (void *)lid_device_props_l4D, }, { + .ident = "Surface Pro 8", + .matches = { + DMI_EXACT_MATCH(DMI_SYS_VENDOR, "Microsoft Corporation"), + DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "Surface Pro 8"), + }, + .driver_data = (void *)lid_device_props_l4B, + }, + { .ident = "Surface Book 1", .matches = { DMI_EXACT_MATCH(DMI_SYS_VENDOR, "Microsoft Corporation"), diff --git a/drivers/platform/x86/intel/pmt/telemetry.c b/drivers/platform/x86/intel/pmt/telemetry.c index 6b6f3e2a617a..f73ecfd4a309 100644 --- a/drivers/platform/x86/intel/pmt/telemetry.c +++ b/drivers/platform/x86/intel/pmt/telemetry.c @@ -103,7 +103,7 @@ static int pmt_telem_probe(struct auxiliary_device *auxdev, const struct auxilia auxiliary_set_drvdata(auxdev, priv); for (i = 0; i < intel_vsec_dev->num_resources; i++) { - struct intel_pmt_entry *entry = &priv->entry[i]; + struct intel_pmt_entry *entry = &priv->entry[priv->num_entries]; ret = intel_pmt_dev_create(entry, &pmt_telem_ns, intel_vsec_dev, i); if (ret < 0) diff --git a/drivers/platform/x86/thinkpad_acpi.c b/drivers/platform/x86/thinkpad_acpi.c index c568fae56db2..e6cb4a14cdd4 100644 --- a/drivers/platform/x86/thinkpad_acpi.c +++ b/drivers/platform/x86/thinkpad_acpi.c @@ -309,6 +309,20 @@ struct ibm_init_struct { struct ibm_struct *data; }; +/* DMI Quirks */ +struct quirk_entry { + bool btusb_bug; + u32 s2idle_bug_mmio; +}; + +static struct quirk_entry quirk_btusb_bug = { + .btusb_bug = true, +}; + +static struct quirk_entry quirk_s2idle_bug = { + .s2idle_bug_mmio = 0xfed80380, +}; + static struct { u32 bluetooth:1; u32 hotkey:1; @@ -338,6 +352,7 @@ static struct { u32 hotkey_poll_active:1; u32 has_adaptive_kbd:1; u32 kbd_lang:1; + struct quirk_entry *quirks; } tp_features; static struct { @@ -4359,9 +4374,10 @@ static void bluetooth_exit(void) bluetooth_shutdown(); } -static const struct dmi_system_id bt_fwbug_list[] __initconst = { +static const struct dmi_system_id fwbug_list[] __initconst = { { .ident = "ThinkPad E485", + .driver_data = &quirk_btusb_bug, .matches = { DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"), DMI_MATCH(DMI_BOARD_NAME, "20KU"), @@ -4369,6 +4385,7 @@ static const struct dmi_system_id bt_fwbug_list[] __initconst = { }, { .ident = "ThinkPad E585", + .driver_data = &quirk_btusb_bug, .matches = { DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"), DMI_MATCH(DMI_BOARD_NAME, "20KV"), @@ -4376,6 +4393,7 @@ static const struct dmi_system_id bt_fwbug_list[] __initconst = { }, { .ident = "ThinkPad A285 - 20MW", + .driver_data = &quirk_btusb_bug, .matches = { DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"), DMI_MATCH(DMI_BOARD_NAME, "20MW"), @@ -4383,6 +4401,7 @@ static const struct dmi_system_id bt_fwbug_list[] __initconst = { }, { .ident = "ThinkPad A285 - 20MX", + .driver_data = &quirk_btusb_bug, .matches = { DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"), DMI_MATCH(DMI_BOARD_NAME, "20MX"), @@ -4390,6 +4409,7 @@ static const struct dmi_system_id bt_fwbug_list[] __initconst = { }, { .ident = "ThinkPad A485 - 20MU", + .driver_data = &quirk_btusb_bug, .matches = { DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"), DMI_MATCH(DMI_BOARD_NAME, "20MU"), @@ -4397,14 +4417,125 @@ static const struct dmi_system_id bt_fwbug_list[] __initconst = { }, { .ident = "ThinkPad A485 - 20MV", + .driver_data = &quirk_btusb_bug, .matches = { DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"), DMI_MATCH(DMI_BOARD_NAME, "20MV"), }, }, + { + .ident = "L14 Gen2 AMD", + .driver_data = &quirk_s2idle_bug, + .matches = { + DMI_MATCH(DMI_BOARD_VENDOR, "LENOVO"), + DMI_MATCH(DMI_PRODUCT_NAME, "20X5"), + } + }, + { + .ident = "T14s Gen2 AMD", + .driver_data = &quirk_s2idle_bug, + .matches = { + DMI_MATCH(DMI_BOARD_VENDOR, "LENOVO"), + DMI_MATCH(DMI_PRODUCT_NAME, "20XF"), + } + }, + { + .ident = "X13 Gen2 AMD", + .driver_data = &quirk_s2idle_bug, + .matches = { + DMI_MATCH(DMI_BOARD_VENDOR, "LENOVO"), + DMI_MATCH(DMI_PRODUCT_NAME, "20XH"), + } + }, + { + .ident = "T14 Gen2 AMD", + .driver_data = &quirk_s2idle_bug, + .matches = { + DMI_MATCH(DMI_BOARD_VENDOR, "LENOVO"), + DMI_MATCH(DMI_PRODUCT_NAME, "20XK"), + } + }, + { + .ident = "T14 Gen1 AMD", + .driver_data = &quirk_s2idle_bug, + .matches = { + DMI_MATCH(DMI_BOARD_VENDOR, "LENOVO"), + DMI_MATCH(DMI_PRODUCT_NAME, "20UD"), + } + }, + { + .ident = "T14 Gen1 AMD", + .driver_data = &quirk_s2idle_bug, + .matches = { + DMI_MATCH(DMI_BOARD_VENDOR, "LENOVO"), + DMI_MATCH(DMI_PRODUCT_NAME, "20UE"), + } + }, + { + .ident = "T14s Gen1 AMD", + .driver_data = &quirk_s2idle_bug, + .matches = { + DMI_MATCH(DMI_BOARD_VENDOR, "LENOVO"), + DMI_MATCH(DMI_PRODUCT_NAME, "20UH"), + } + }, + { + .ident = "P14s Gen1 AMD", + .driver_data = &quirk_s2idle_bug, + .matches = { + DMI_MATCH(DMI_BOARD_VENDOR, "LENOVO"), + DMI_MATCH(DMI_PRODUCT_NAME, "20Y1"), + } + }, + { + .ident = "P14s Gen2 AMD", + .driver_data = &quirk_s2idle_bug, + .matches = { + DMI_MATCH(DMI_BOARD_VENDOR, "LENOVO"), + DMI_MATCH(DMI_PRODUCT_NAME, "21A0"), + } + }, {} }; +#ifdef CONFIG_SUSPEND +/* + * Lenovo laptops from a variety of generations run a SMI handler during the D3->D0 + * transition that occurs specifically when exiting suspend to idle which can cause + * large delays during resume when the IOMMU translation layer is enabled (the default + * behavior) for NVME devices: + * + * To avoid this firmware problem, skip the SMI handler on these machines before the + * D0 transition occurs. + */ +static void thinkpad_acpi_amd_s2idle_restore(void) +{ + struct resource *res; + void __iomem *addr; + u8 val; + + res = request_mem_region_muxed(tp_features.quirks->s2idle_bug_mmio, 1, + "thinkpad_acpi_pm80"); + if (!res) + return; + + addr = ioremap(tp_features.quirks->s2idle_bug_mmio, 1); + if (!addr) + goto cleanup_resource; + + val = ioread8(addr); + iowrite8(val & ~BIT(0), addr); + + iounmap(addr); +cleanup_resource: + release_resource(res); +} + +static struct acpi_s2idle_dev_ops thinkpad_acpi_s2idle_dev_ops = { + .restore = thinkpad_acpi_amd_s2idle_restore, +}; +#endif + static const struct pci_device_id fwbug_cards_ids[] __initconst = { { PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x24F3) }, { PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x24FD) }, @@ -4419,7 +4550,8 @@ static int __init have_bt_fwbug(void) * Some AMD based ThinkPads have a firmware bug that calling * "GBDC" will cause bluetooth on Intel wireless cards blocked */ - if (dmi_check_system(bt_fwbug_list) && pci_dev_present(fwbug_cards_ids)) { + if (tp_features.quirks && tp_features.quirks->btusb_bug && + pci_dev_present(fwbug_cards_ids)) { vdbg_printk(TPACPI_DBG_INIT | TPACPI_DBG_RFKILL, FW_BUG "disable bluetooth subdriver for Intel cards\n"); return 1; @@ -8748,24 +8880,27 @@ static int __init fan_init(struct ibm_init_struct *iibm) fan_status_access_mode = TPACPI_FAN_RD_TPEC; if (quirks & TPACPI_FAN_Q1) fan_quirk1_setup(); - if (quirks & TPACPI_FAN_2FAN) { - tp_features.second_fan = 1; - pr_info("secondary fan support enabled\n"); - } - if (quirks & TPACPI_FAN_2CTL) { - tp_features.second_fan = 1; - tp_features.second_fan_ctl = 1; - pr_info("secondary fan control enabled\n"); - } /* Try and probe the 2nd fan */ + tp_features.second_fan = 1; /* needed for get_speed to work */ res = fan2_get_speed(&speed); if (res >= 0) { /* It responded - so let's assume it's there */ tp_features.second_fan = 1; tp_features.second_fan_ctl = 1; pr_info("secondary fan control detected & enabled\n"); + } else { + /* Fan not auto-detected */ + tp_features.second_fan = 0; + if (quirks & TPACPI_FAN_2FAN) { + tp_features.second_fan = 1; + pr_info("secondary fan support enabled\n"); + } + if (quirks & TPACPI_FAN_2CTL) { + tp_features.second_fan = 1; + tp_features.second_fan_ctl = 1; + pr_info("secondary fan control enabled\n"); + } } - } else { pr_err("ThinkPad ACPI EC access misbehaving, fan status and control unavailable\n"); return -ENODEV; @@ -11455,6 +11590,10 @@ static void thinkpad_acpi_module_exit(void) tpacpi_lifecycle = TPACPI_LIFE_EXITING; +#ifdef CONFIG_SUSPEND + if (tp_features.quirks && tp_features.quirks->s2idle_bug_mmio) + acpi_unregister_lps0_dev(&thinkpad_acpi_s2idle_dev_ops); +#endif if (tpacpi_hwmon) hwmon_device_unregister(tpacpi_hwmon); if (tp_features.sensors_pdrv_registered) @@ -11496,6 +11635,7 @@ static void thinkpad_acpi_module_exit(void) static int __init thinkpad_acpi_module_init(void) { + const struct dmi_system_id *dmi_id; int ret, i; tpacpi_lifecycle = TPACPI_LIFE_INIT; @@ -11535,6 +11675,10 @@ static int __init thinkpad_acpi_module_init(void) return -ENODEV; } + dmi_id = dmi_first_match(fwbug_list); + if (dmi_id) + tp_features.quirks = dmi_id->driver_data; + /* Device initialization */ tpacpi_pdev = platform_device_register_simple(TPACPI_DRVR_NAME, -1, NULL, 0); @@ -11623,6 +11767,13 @@ static int __init thinkpad_acpi_module_init(void) tp_features.input_device_registered = 1; } +#ifdef CONFIG_SUSPEND + if (tp_features.quirks && tp_features.quirks->s2idle_bug_mmio) { + if (!acpi_register_lps0_dev(&thinkpad_acpi_s2idle_dev_ops)) + pr_info("Using s2idle quirk to avoid %s platform firmware bug\n", + (dmi_id && dmi_id->ident) ? dmi_id->ident : ""); + } +#endif return 0; } diff --git a/drivers/ptp/ptp_ocp.c b/drivers/ptp/ptp_ocp.c index 0feaa4b45317..860672d6a03c 100644 --- a/drivers/ptp/ptp_ocp.c +++ b/drivers/ptp/ptp_ocp.c @@ -300,7 +300,7 @@ struct ptp_ocp { struct platform_device *spi_flash; struct clk_hw *i2c_clk; struct timer_list watchdog; - const struct ocp_attr_group *attr_tbl; + const struct attribute_group **attr_group; const struct ptp_ocp_eeprom_map *eeprom_map; struct dentry *debug_root; time64_t gnss_lost; @@ -841,7 +841,7 @@ __ptp_ocp_adjtime_locked(struct ptp_ocp *bp, u32 adj_val) } static void -ptp_ocp_adjtime_coarse(struct ptp_ocp *bp, u64 delta_ns) +ptp_ocp_adjtime_coarse(struct ptp_ocp *bp, s64 delta_ns) { struct timespec64 ts; unsigned long flags; @@ -850,7 +850,8 @@ ptp_ocp_adjtime_coarse(struct ptp_ocp *bp, u64 delta_ns) spin_lock_irqsave(&bp->lock, flags); err = __ptp_ocp_gettime_locked(bp, &ts, NULL); if (likely(!err)) { - timespec64_add_ns(&ts, delta_ns); + set_normalized_timespec64(&ts, ts.tv_sec, + ts.tv_nsec + delta_ns); __ptp_ocp_settime_locked(bp, &ts); } spin_unlock_irqrestore(&bp->lock, flags); @@ -1557,7 +1558,7 @@ ptp_ocp_signal_set(struct ptp_ocp *bp, int gen, struct ptp_ocp_signal *s) start_ns = ktime_set(ts.tv_sec, ts.tv_nsec) + NSEC_PER_MSEC; if (!s->start) { /* roundup() does not work on 32-bit systems */ - s->start = DIV_ROUND_UP_ULL(start_ns, s->period); + s->start = DIV64_U64_ROUND_UP(start_ns, s->period); s->start = ktime_add(s->start, s->phase); } @@ -1836,6 +1837,42 @@ ptp_ocp_signal_init(struct ptp_ocp *bp) } static void +ptp_ocp_attr_group_del(struct ptp_ocp *bp) +{ + sysfs_remove_groups(&bp->dev.kobj, bp->attr_group); + kfree(bp->attr_group); +} + +static int +ptp_ocp_attr_group_add(struct ptp_ocp *bp, + const struct ocp_attr_group *attr_tbl) +{ + int count, i; + int err; + + count = 0; + for (i = 0; attr_tbl[i].cap; i++) + if (attr_tbl[i].cap & bp->fw_cap) + count++; + + bp->attr_group = kcalloc(count + 1, sizeof(struct attribute_group *), + GFP_KERNEL); + if (!bp->attr_group) + return -ENOMEM; + + count = 0; + for (i = 0; attr_tbl[i].cap; i++) + if (attr_tbl[i].cap & bp->fw_cap) + bp->attr_group[count++] = attr_tbl[i].group; + + err = sysfs_create_groups(&bp->dev.kobj, bp->attr_group); + if (err) + bp->attr_group[0] = NULL; + + return err; +} + +static void ptp_ocp_sma_init(struct ptp_ocp *bp) { u32 reg; @@ -1904,7 +1941,6 @@ ptp_ocp_fb_board_init(struct ptp_ocp *bp, struct ocp_resource *r) bp->flash_start = 1024 * 4096; bp->eeprom_map = fb_eeprom_map; bp->fw_version = ioread32(&bp->image->version); - bp->attr_tbl = fb_timecard_groups; bp->fw_cap = OCP_CAP_BASIC; ver = bp->fw_version & 0xffff; @@ -1918,6 +1954,10 @@ ptp_ocp_fb_board_init(struct ptp_ocp *bp, struct ocp_resource *r) ptp_ocp_sma_init(bp); ptp_ocp_signal_init(bp); + err = ptp_ocp_attr_group_add(bp, fb_timecard_groups); + if (err) + return err; + err = ptp_ocp_fb_set_pins(bp); if (err) return err; @@ -3388,7 +3428,6 @@ ptp_ocp_complete(struct ptp_ocp *bp) { struct pps_device *pps; char buf[32]; - int i, err; if (bp->gnss_port != -1) { sprintf(buf, "ttyS%d", bp->gnss_port); @@ -3413,14 +3452,6 @@ ptp_ocp_complete(struct ptp_ocp *bp) if (pps) ptp_ocp_symlink(bp, pps->dev, "pps"); - for (i = 0; bp->attr_tbl[i].cap; i++) { - if (!(bp->attr_tbl[i].cap & bp->fw_cap)) - continue; - err = sysfs_create_group(&bp->dev.kobj, bp->attr_tbl[i].group); - if (err) - return err; - } - ptp_ocp_debugfs_add_device(bp); return 0; @@ -3492,15 +3523,11 @@ static void ptp_ocp_detach_sysfs(struct ptp_ocp *bp) { struct device *dev = &bp->dev; - int i; sysfs_remove_link(&dev->kobj, "ttyGNSS"); sysfs_remove_link(&dev->kobj, "ttyMAC"); sysfs_remove_link(&dev->kobj, "ptp"); sysfs_remove_link(&dev->kobj, "pps"); - if (bp->attr_tbl) - for (i = 0; bp->attr_tbl[i].cap; i++) - sysfs_remove_group(&dev->kobj, bp->attr_tbl[i].group); } static void @@ -3510,6 +3537,7 @@ ptp_ocp_detach(struct ptp_ocp *bp) ptp_ocp_debugfs_remove_device(bp); ptp_ocp_detach_sysfs(bp); + ptp_ocp_attr_group_del(bp); if (timer_pending(&bp->watchdog)) del_timer_sync(&bp->watchdog); if (bp->ts0) diff --git a/drivers/rtc/rtc-sun6i.c b/drivers/rtc/rtc-sun6i.c index 5b3e4da63406..5252ce4cbda4 100644 --- a/drivers/rtc/rtc-sun6i.c +++ b/drivers/rtc/rtc-sun6i.c @@ -370,6 +370,23 @@ CLK_OF_DECLARE_DRIVER(sun8i_h3_rtc_clk, "allwinner,sun8i-h3-rtc", CLK_OF_DECLARE_DRIVER(sun50i_h5_rtc_clk, "allwinner,sun50i-h5-rtc", sun8i_h3_rtc_clk_init); +static const struct sun6i_rtc_clk_data sun50i_h6_rtc_data = { + .rc_osc_rate = 16000000, + .fixed_prescaler = 32, + .has_prescaler = 1, + .has_out_clk = 1, + .export_iosc = 1, + .has_losc_en = 1, + .has_auto_swt = 1, +}; + +static void __init sun50i_h6_rtc_clk_init(struct device_node *node) +{ + sun6i_rtc_clk_init(node, &sun50i_h6_rtc_data); +} +CLK_OF_DECLARE_DRIVER(sun50i_h6_rtc_clk, "allwinner,sun50i-h6-rtc", + sun50i_h6_rtc_clk_init); + /* * The R40 user manual is self-conflicting on whether the prescaler is * fixed or configurable. The clock diagram shows it as fixed, but there diff --git a/drivers/s390/block/dasd_fba.c b/drivers/s390/block/dasd_fba.c index e084f4dedddd..60be7f7bf2d1 100644 --- a/drivers/s390/block/dasd_fba.c +++ b/drivers/s390/block/dasd_fba.c @@ -782,7 +782,6 @@ static void dasd_fba_setup_blk_queue(struct dasd_block *block) blk_queue_segment_boundary(q, PAGE_SIZE - 1); q->limits.discard_granularity = logical_block_size; - q->limits.discard_alignment = PAGE_SIZE; /* Calculate max_discard_sectors and make it PAGE aligned */ max_bytes = USHRT_MAX * logical_block_size; @@ -791,7 +790,6 @@ static void dasd_fba_setup_blk_queue(struct dasd_block *block) blk_queue_max_discard_sectors(q, max_discard_sectors); blk_queue_max_write_zeroes_sectors(q, max_discard_sectors); - blk_queue_flag_set(QUEUE_FLAG_DISCARD, q); } static int dasd_fba_pe_handler(struct dasd_device *device, diff --git a/drivers/s390/net/ctcm_mpc.c b/drivers/s390/net/ctcm_mpc.c index 88abfb5e8045..8ac213a55141 100644 --- a/drivers/s390/net/ctcm_mpc.c +++ b/drivers/s390/net/ctcm_mpc.c @@ -626,8 +626,6 @@ static void mpc_rcvd_sweep_resp(struct mpcg_info *mpcginfo) ctcm_clear_busy_do(dev); } - kfree(mpcginfo); - return; } @@ -1192,10 +1190,10 @@ static void ctcmpc_unpack_skb(struct channel *ch, struct sk_buff *pskb) CTCM_FUNTAIL, dev->name); priv->stats.rx_dropped++; /* mpcginfo only used for non-data transfers */ - kfree(mpcginfo); if (do_debug_data) ctcmpc_dump_skb(pskb, -8); } + kfree(mpcginfo); } done: @@ -1977,7 +1975,6 @@ static void mpc_action_rcvd_xid0(fsm_instance *fsm, int event, void *arg) } break; } - kfree(mpcginfo); CTCM_PR_DEBUG("ctcmpc:%s() %s xid2:%i xid7:%i xidt_p2:%i \n", __func__, ch->id, grp->outstanding_xid2, @@ -2038,7 +2035,6 @@ static void mpc_action_rcvd_xid7(fsm_instance *fsm, int event, void *arg) mpc_validate_xid(mpcginfo); break; } - kfree(mpcginfo); return; } diff --git a/drivers/s390/net/ctcm_sysfs.c b/drivers/s390/net/ctcm_sysfs.c index ded1930a00b2..e3813a7aa5e6 100644 --- a/drivers/s390/net/ctcm_sysfs.c +++ b/drivers/s390/net/ctcm_sysfs.c @@ -39,11 +39,12 @@ static ssize_t ctcm_buffer_write(struct device *dev, struct ctcm_priv *priv = dev_get_drvdata(dev); int rc; - ndev = priv->channel[CTCM_READ]->netdev; - if (!(priv && priv->channel[CTCM_READ] && ndev)) { + if (!(priv && priv->channel[CTCM_READ] && + priv->channel[CTCM_READ]->netdev)) { CTCM_DBF_TEXT(SETUP, CTC_DBF_ERROR, "bfnondev"); return -ENODEV; } + ndev = priv->channel[CTCM_READ]->netdev; rc = kstrtouint(buf, 0, &bs1); if (rc) diff --git a/drivers/s390/net/lcs.c b/drivers/s390/net/lcs.c index bab9b34926c6..84c8981317b4 100644 --- a/drivers/s390/net/lcs.c +++ b/drivers/s390/net/lcs.c @@ -1736,10 +1736,11 @@ lcs_get_control(struct lcs_card *card, struct lcs_cmd *cmd) lcs_schedule_recovery(card); break; case LCS_CMD_STOPLAN: - pr_warn("Stoplan for %s initiated by LGW\n", - card->dev->name); - if (card->dev) + if (card->dev) { + pr_warn("Stoplan for %s initiated by LGW\n", + card->dev->name); netif_carrier_off(card->dev); + } break; default: LCS_DBF_TEXT(5, trace, "noLGWcmd"); diff --git a/drivers/scsi/device_handler/scsi_dh_alua.c b/drivers/scsi/device_handler/scsi_dh_alua.c index 37d06f993b76..1d9be771f3ee 100644 --- a/drivers/scsi/device_handler/scsi_dh_alua.c +++ b/drivers/scsi/device_handler/scsi_dh_alua.c @@ -1172,9 +1172,8 @@ static blk_status_t alua_prep_fn(struct scsi_device *sdev, struct request *req) case SCSI_ACCESS_STATE_OPTIMAL: case SCSI_ACCESS_STATE_ACTIVE: case SCSI_ACCESS_STATE_LBA: - return BLK_STS_OK; case SCSI_ACCESS_STATE_TRANSITIONING: - return BLK_STS_AGAIN; + return BLK_STS_OK; default: req->rq_flags |= RQF_QUIET; return BLK_STS_IOERR; diff --git a/drivers/scsi/lpfc/lpfc_els.c b/drivers/scsi/lpfc/lpfc_els.c index ef6e8cd8c26a..872a26376ccb 100644 --- a/drivers/scsi/lpfc/lpfc_els.c +++ b/drivers/scsi/lpfc/lpfc_els.c @@ -1330,7 +1330,7 @@ lpfc_issue_els_flogi(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp, if (bf_get(lpfc_sli_intf_if_type, &phba->sli4_hba.sli_intf) == LPFC_SLI_INTF_IF_TYPE_0) { /* FLOGI needs to be 3 for WQE FCFI */ - ct = ((SLI4_CT_FCFI >> 1) & 1) | (SLI4_CT_FCFI & 1); + ct = SLI4_CT_FCFI; bf_set(wqe_ct, &wqe->els_req.wqe_com, ct); /* Set the fcfi to the fcfi we registered with */ diff --git a/drivers/scsi/lpfc/lpfc_scsi.c b/drivers/scsi/lpfc/lpfc_scsi.c index ba9dbb51b75f..f6b83853f7ee 100644 --- a/drivers/scsi/lpfc/lpfc_scsi.c +++ b/drivers/scsi/lpfc/lpfc_scsi.c @@ -5528,7 +5528,9 @@ static char *lpfc_is_command_vm_io(struct scsi_cmnd *cmd) { struct bio *bio = scsi_cmd_to_rq(cmd)->bio; - return bio ? blkcg_get_fc_appid(bio) : NULL; + if (!IS_ENABLED(CONFIG_BLK_CGROUP_FC_APPID) || !bio) + return NULL; + return blkcg_get_fc_appid(bio); } /** diff --git a/drivers/scsi/lpfc/lpfc_sli.c b/drivers/scsi/lpfc/lpfc_sli.c index bda2a7ba4e77..6adaf79e67cc 100644 --- a/drivers/scsi/lpfc/lpfc_sli.c +++ b/drivers/scsi/lpfc/lpfc_sli.c @@ -10720,10 +10720,10 @@ __lpfc_sli_prep_gen_req_s4(struct lpfc_iocbq *cmdiocbq, struct lpfc_dmabuf *bmp, /* Words 0 - 2 */ bde = (struct ulp_bde64_le *)&cmdwqe->generic.bde; - bde->addr_low = cpu_to_le32(putPaddrLow(bmp->phys)); - bde->addr_high = cpu_to_le32(putPaddrHigh(bmp->phys)); + bde->addr_low = bpl->addr_low; + bde->addr_high = bpl->addr_high; bde->type_size = cpu_to_le32(xmit_len); - bde->type_size |= cpu_to_le32(ULP_BDE64_TYPE_BLP_64); + bde->type_size |= cpu_to_le32(ULP_BDE64_TYPE_BDE_64); /* Word 3 */ cmdwqe->gen_req.request_payload_len = xmit_len; diff --git a/drivers/scsi/qla2xxx/qla_target.c b/drivers/scsi/qla2xxx/qla_target.c index 85dbf81f3204..6dfcfd8e7337 100644 --- a/drivers/scsi/qla2xxx/qla_target.c +++ b/drivers/scsi/qla2xxx/qla_target.c @@ -3826,6 +3826,9 @@ int qlt_abort_cmd(struct qla_tgt_cmd *cmd) spin_lock_irqsave(&cmd->cmd_lock, flags); if (cmd->aborted) { + if (cmd->sg_mapped) + qlt_unmap_sg(vha, cmd); + spin_unlock_irqrestore(&cmd->cmd_lock, flags); /* * It's normal to see 2 calls in this path: diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c index dc6e55761fd1..9694e2cfaf9a 100644 --- a/drivers/scsi/sd.c +++ b/drivers/scsi/sd.c @@ -797,7 +797,6 @@ static void sd_config_discard(struct scsi_disk *sdkp, unsigned int mode) case SD_LBP_FULL: case SD_LBP_DISABLE: blk_queue_max_discard_sectors(q, 0); - blk_queue_flag_clear(QUEUE_FLAG_DISCARD, q); return; case SD_LBP_UNMAP: @@ -830,7 +829,6 @@ static void sd_config_discard(struct scsi_disk *sdkp, unsigned int mode) } blk_queue_max_discard_sectors(q, max_blocks * (logical_block_size >> 9)); - blk_queue_flag_set(QUEUE_FLAG_DISCARD, q); } static blk_status_t sd_setup_unmap_cmnd(struct scsi_cmnd *cmd) diff --git a/drivers/scsi/ufs/ufshpb.c b/drivers/scsi/ufs/ufshpb.c index 81099b68bbfb..588c0329b80c 100644 --- a/drivers/scsi/ufs/ufshpb.c +++ b/drivers/scsi/ufs/ufshpb.c @@ -1254,6 +1254,13 @@ void ufshpb_rsp_upiu(struct ufs_hba *hba, struct ufshcd_lrb *lrbp) struct utp_hpb_rsp *rsp_field = &lrbp->ucd_rsp_ptr->hr; int data_seg_len; + data_seg_len = be32_to_cpu(lrbp->ucd_rsp_ptr->header.dword_2) + & MASK_RSP_UPIU_DATA_SEG_LEN; + + /* If data segment length is zero, rsp_field is not valid */ + if (!data_seg_len) + return; + if (unlikely(lrbp->lun != rsp_field->lun)) { struct scsi_device *sdev; bool found = false; @@ -1288,18 +1295,6 @@ void ufshpb_rsp_upiu(struct ufs_hba *hba, struct ufshcd_lrb *lrbp) return; } - data_seg_len = be32_to_cpu(lrbp->ucd_rsp_ptr->header.dword_2) - & MASK_RSP_UPIU_DATA_SEG_LEN; - - /* To flush remained rsp_list, we queue the map_work task */ - if (!data_seg_len) { - if (!ufshpb_is_general_lun(hpb->lun)) - return; - - ufshpb_kick_map_work(hpb); - return; - } - BUILD_BUG_ON(sizeof(struct utp_hpb_rsp) != UTP_HPB_RSP_SIZE); if (!ufshpb_is_hpb_rsp_valid(hba, lrbp, rsp_field)) diff --git a/drivers/slimbus/qcom-ctrl.c b/drivers/slimbus/qcom-ctrl.c index f04b961b96cd..ec58091fc948 100644 --- a/drivers/slimbus/qcom-ctrl.c +++ b/drivers/slimbus/qcom-ctrl.c @@ -510,9 +510,9 @@ static int qcom_slim_probe(struct platform_device *pdev) } ctrl->irq = platform_get_irq(pdev, 0); - if (!ctrl->irq) { + if (ctrl->irq < 0) { dev_err(&pdev->dev, "no slimbus IRQ\n"); - return -ENODEV; + return ctrl->irq; } sctrl = &ctrl->ctrl; diff --git a/drivers/target/iscsi/iscsi_target.c b/drivers/target/iscsi/iscsi_target.c index 6fe6a6bab3f4..ddf6c2a7212b 100644 --- a/drivers/target/iscsi/iscsi_target.c +++ b/drivers/target/iscsi/iscsi_target.c @@ -3596,10 +3596,7 @@ static int iscsit_send_reject( void iscsit_thread_get_cpumask(struct iscsi_conn *conn) { int ord, cpu; - cpumask_t conn_allowed_cpumask; - - cpumask_and(&conn_allowed_cpumask, iscsit_global->allowed_cpumask, - cpu_online_mask); + cpumask_var_t conn_allowed_cpumask; /* * bitmap_id is assigned from iscsit_global->ts_bitmap from @@ -3609,13 +3606,28 @@ void iscsit_thread_get_cpumask(struct iscsi_conn *conn) * iSCSI connection's RX/TX threads will be scheduled to * execute upon. */ - cpumask_clear(conn->conn_cpumask); - ord = conn->bitmap_id % cpumask_weight(&conn_allowed_cpumask); - for_each_cpu(cpu, &conn_allowed_cpumask) { - if (ord-- == 0) { - cpumask_set_cpu(cpu, conn->conn_cpumask); - return; + if (!zalloc_cpumask_var(&conn_allowed_cpumask, GFP_KERNEL)) { + ord = conn->bitmap_id % cpumask_weight(cpu_online_mask); + for_each_online_cpu(cpu) { + if (ord-- == 0) { + cpumask_set_cpu(cpu, conn->conn_cpumask); + return; + } + } + } else { + cpumask_and(conn_allowed_cpumask, iscsit_global->allowed_cpumask, + cpu_online_mask); + + cpumask_clear(conn->conn_cpumask); + ord = conn->bitmap_id % cpumask_weight(conn_allowed_cpumask); + for_each_cpu(cpu, conn_allowed_cpumask) { + if (ord-- == 0) { + cpumask_set_cpu(cpu, conn->conn_cpumask); + free_cpumask_var(conn_allowed_cpumask); + return; + } } + free_cpumask_var(conn_allowed_cpumask); } /* * This should never be reached.. diff --git a/drivers/target/iscsi/iscsi_target_configfs.c b/drivers/target/iscsi/iscsi_target_configfs.c index 0cedcfe207b5..57b4fd56d92a 100644 --- a/drivers/target/iscsi/iscsi_target_configfs.c +++ b/drivers/target/iscsi/iscsi_target_configfs.c @@ -1137,23 +1137,27 @@ static ssize_t lio_target_wwn_cpus_allowed_list_show( static ssize_t lio_target_wwn_cpus_allowed_list_store( struct config_item *item, const char *page, size_t count) { - int ret; + int ret = -ENOMEM; char *orig; - cpumask_t new_allowed_cpumask; + cpumask_var_t new_allowed_cpumask; + + if (!zalloc_cpumask_var(&new_allowed_cpumask, GFP_KERNEL)) + goto out; orig = kstrdup(page, GFP_KERNEL); if (!orig) - return -ENOMEM; + goto out_free_cpumask; - cpumask_clear(&new_allowed_cpumask); - ret = cpulist_parse(orig, &new_allowed_cpumask); + ret = cpulist_parse(orig, new_allowed_cpumask); + if (!ret) + cpumask_copy(iscsit_global->allowed_cpumask, + new_allowed_cpumask); kfree(orig); - if (ret != 0) - return ret; - - cpumask_copy(iscsit_global->allowed_cpumask, &new_allowed_cpumask); - return count; +out_free_cpumask: + free_cpumask_var(new_allowed_cpumask); +out: + return ret ? ret : count; } CONFIGFS_ATTR(lio_target_wwn_, cpus_allowed_list); diff --git a/drivers/target/target_core_device.c b/drivers/target/target_core_device.c index 44bb380e7390..25f33eb25337 100644 --- a/drivers/target/target_core_device.c +++ b/drivers/target/target_core_device.c @@ -829,28 +829,26 @@ struct se_device *target_alloc_device(struct se_hba *hba, const char *name) } /* - * Check if the underlying struct block_device request_queue supports - * the QUEUE_FLAG_DISCARD bit for UNMAP/WRITE_SAME in SCSI + TRIM - * in ATA and we need to set TPE=1 + * Check if the underlying struct block_device supports discard and if yes + * configure the UNMAP parameters. */ bool target_configure_unmap_from_queue(struct se_dev_attrib *attrib, - struct request_queue *q) + struct block_device *bdev) { - int block_size = queue_logical_block_size(q); + int block_size = bdev_logical_block_size(bdev); - if (!blk_queue_discard(q)) + if (!bdev_max_discard_sectors(bdev)) return false; attrib->max_unmap_lba_count = - q->limits.max_discard_sectors >> (ilog2(block_size) - 9); + bdev_max_discard_sectors(bdev) >> (ilog2(block_size) - 9); /* * Currently hardcoded to 1 in Linux/SCSI code.. */ attrib->max_unmap_block_desc_count = 1; - attrib->unmap_granularity = q->limits.discard_granularity / block_size; - attrib->unmap_granularity_alignment = q->limits.discard_alignment / - block_size; - attrib->unmap_zeroes_data = !!(q->limits.max_write_zeroes_sectors); + attrib->unmap_granularity = bdev_discard_granularity(bdev) / block_size; + attrib->unmap_granularity_alignment = + bdev_discard_alignment(bdev) / block_size; return true; } EXPORT_SYMBOL(target_configure_unmap_from_queue); diff --git a/drivers/target/target_core_file.c b/drivers/target/target_core_file.c index 8190b840065f..e68f1cc8ef98 100644 --- a/drivers/target/target_core_file.c +++ b/drivers/target/target_core_file.c @@ -134,10 +134,10 @@ static int fd_configure_device(struct se_device *dev) */ inode = file->f_mapping->host; if (S_ISBLK(inode->i_mode)) { - struct request_queue *q = bdev_get_queue(I_BDEV(inode)); + struct block_device *bdev = I_BDEV(inode); unsigned long long dev_size; - fd_dev->fd_block_size = bdev_logical_block_size(I_BDEV(inode)); + fd_dev->fd_block_size = bdev_logical_block_size(bdev); /* * Determine the number of bytes from i_size_read() minus * one (1) logical sector from underlying struct block_device @@ -150,7 +150,7 @@ static int fd_configure_device(struct se_device *dev) dev_size, div_u64(dev_size, fd_dev->fd_block_size), fd_dev->fd_block_size); - if (target_configure_unmap_from_queue(&dev->dev_attrib, q)) + if (target_configure_unmap_from_queue(&dev->dev_attrib, bdev)) pr_debug("IFILE: BLOCK Discard support available," " disabled by default\n"); /* @@ -159,7 +159,7 @@ static int fd_configure_device(struct se_device *dev) */ dev->dev_attrib.max_write_same_len = 0xFFFF; - if (blk_queue_nonrot(q)) + if (bdev_nonrot(bdev)) dev->dev_attrib.is_nonrot = 1; } else { if (!(fd_dev->fbd_flags & FBDF_HAS_SIZE)) { @@ -558,7 +558,7 @@ fd_execute_unmap(struct se_cmd *cmd, sector_t lba, sector_t nolb) ret = blkdev_issue_discard(bdev, target_to_linux_sector(dev, lba), target_to_linux_sector(dev, nolb), - GFP_KERNEL, 0); + GFP_KERNEL); if (ret < 0) { pr_warn("FILEIO: blkdev_issue_discard() failed: %d\n", ret); diff --git a/drivers/target/target_core_iblock.c b/drivers/target/target_core_iblock.c index 87ede165ddba..378c80313a0f 100644 --- a/drivers/target/target_core_iblock.c +++ b/drivers/target/target_core_iblock.c @@ -119,7 +119,7 @@ static int iblock_configure_device(struct se_device *dev) dev->dev_attrib.hw_max_sectors = queue_max_hw_sectors(q); dev->dev_attrib.hw_queue_depth = q->nr_requests; - if (target_configure_unmap_from_queue(&dev->dev_attrib, q)) + if (target_configure_unmap_from_queue(&dev->dev_attrib, bd)) pr_debug("IBLOCK: BLOCK Discard support available," " disabled by default\n"); @@ -133,7 +133,7 @@ static int iblock_configure_device(struct se_device *dev) else dev->dev_attrib.max_write_same_len = 0xFFFF; - if (blk_queue_nonrot(q)) + if (bdev_nonrot(bd)) dev->dev_attrib.is_nonrot = 1; bi = bdev_get_integrity(bd); @@ -434,7 +434,7 @@ iblock_execute_unmap(struct se_cmd *cmd, sector_t lba, sector_t nolb) ret = blkdev_issue_discard(bdev, target_to_linux_sector(dev, lba), target_to_linux_sector(dev, nolb), - GFP_KERNEL, 0); + GFP_KERNEL); if (ret < 0) { pr_err("blkdev_issue_discard() failed: %d\n", ret); return TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE; @@ -727,17 +727,16 @@ iblock_execute_rw(struct se_cmd *cmd, struct scatterlist *sgl, u32 sgl_nents, if (data_direction == DMA_TO_DEVICE) { struct iblock_dev *ib_dev = IBLOCK_DEV(dev); - struct request_queue *q = bdev_get_queue(ib_dev->ibd_bd); /* * Force writethrough using REQ_FUA if a volatile write cache * is not enabled, or if initiator set the Force Unit Access bit. */ opf = REQ_OP_WRITE; miter_dir = SG_MITER_TO_SG; - if (test_bit(QUEUE_FLAG_FUA, &q->queue_flags)) { + if (bdev_fua(ib_dev->ibd_bd)) { if (cmd->se_cmd_flags & SCF_FUA) opf |= REQ_FUA; - else if (!test_bit(QUEUE_FLAG_WC, &q->queue_flags)) + else if (!bdev_write_cache(ib_dev->ibd_bd)) opf |= REQ_FUA; } } else { @@ -886,11 +885,7 @@ iblock_parse_cdb(struct se_cmd *cmd) static bool iblock_get_write_cache(struct se_device *dev) { - struct iblock_dev *ib_dev = IBLOCK_DEV(dev); - struct block_device *bd = ib_dev->ibd_bd; - struct request_queue *q = bdev_get_queue(bd); - - return test_bit(QUEUE_FLAG_WC, &q->queue_flags); + return bdev_write_cache(IBLOCK_DEV(dev)->ibd_bd); } static const struct target_backend_ops iblock_ops = { diff --git a/drivers/target/target_core_pscsi.c b/drivers/target/target_core_pscsi.c index 60dafe4c581b..bb3fb18b2316 100644 --- a/drivers/target/target_core_pscsi.c +++ b/drivers/target/target_core_pscsi.c @@ -818,24 +818,8 @@ static ssize_t pscsi_show_configfs_dev_params(struct se_device *dev, char *b) static void pscsi_bi_endio(struct bio *bio) { - bio_put(bio); -} - -static inline struct bio *pscsi_get_bio(int nr_vecs) -{ - struct bio *bio; - /* - * Use bio_malloc() following the comment in for bio -> struct request - * in block/blk-core.c:blk_make_request() - */ - bio = bio_kmalloc(GFP_KERNEL, nr_vecs); - if (!bio) { - pr_err("PSCSI: bio_kmalloc() failed\n"); - return NULL; - } - bio->bi_end_io = pscsi_bi_endio; - - return bio; + bio_uninit(bio); + kfree(bio); } static sense_reason_t @@ -878,15 +862,12 @@ pscsi_map_sg(struct se_cmd *cmd, struct scatterlist *sgl, u32 sgl_nents, if (!bio) { new_bio: nr_vecs = bio_max_segs(nr_pages); - /* - * Calls bio_kmalloc() and sets bio->bi_end_io() - */ - bio = pscsi_get_bio(nr_vecs); + bio = bio_kmalloc(nr_vecs, GFP_KERNEL); if (!bio) goto fail; - - if (rw) - bio_set_op_attrs(bio, REQ_OP_WRITE, 0); + bio_init(bio, NULL, bio->bi_inline_vecs, nr_vecs, + rw ? REQ_OP_WRITE : REQ_OP_READ); + bio->bi_end_io = pscsi_bi_endio; pr_debug("PSCSI: Allocated bio: %p," " dir: %s nr_vecs: %d\n", bio, @@ -912,11 +893,6 @@ new_bio: goto fail; } - /* - * Clear the pointer so that another bio will - * be allocated with pscsi_get_bio() above. - */ - bio = NULL; goto new_bio; } diff --git a/drivers/thermal/intel/int340x_thermal/int3400_thermal.c b/drivers/thermal/intel/int340x_thermal/int3400_thermal.c index d97f496bab9b..79931ddc582a 100644 --- a/drivers/thermal/intel/int340x_thermal/int3400_thermal.c +++ b/drivers/thermal/intel/int340x_thermal/int3400_thermal.c @@ -194,12 +194,31 @@ static int int3400_thermal_run_osc(acpi_handle handle, char *uuid_str, int *enab return result; } +static int set_os_uuid_mask(struct int3400_thermal_priv *priv, u32 mask) +{ + int cap = 0; + + /* + * Capability bits: + * Bit 0: set to 1 to indicate DPTF is active + * Bi1 1: set to 1 to active cooling is supported by user space daemon + * Bit 2: set to 1 to passive cooling is supported by user space daemon + * Bit 3: set to 1 to critical trip is handled by user space daemon + */ + if (mask) + cap = (priv->os_uuid_mask << 1) | 0x01; + + return int3400_thermal_run_osc(priv->adev->handle, + "b23ba85d-c8b7-3542-88de-8de2ffcfd698", + &cap); +} + static ssize_t current_uuid_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { struct int3400_thermal_priv *priv = dev_get_drvdata(dev); - int i; + int ret, i; for (i = 0; i < INT3400_THERMAL_MAXIMUM_UUID; ++i) { if (!strncmp(buf, int3400_thermal_uuids[i], @@ -231,19 +250,7 @@ static ssize_t current_uuid_store(struct device *dev, } if (priv->os_uuid_mask) { - int cap, ret; - - /* - * Capability bits: - * Bit 0: set to 1 to indicate DPTF is active - * Bi1 1: set to 1 to active cooling is supported by user space daemon - * Bit 2: set to 1 to passive cooling is supported by user space daemon - * Bit 3: set to 1 to critical trip is handled by user space daemon - */ - cap = ((priv->os_uuid_mask << 1) | 0x01); - ret = int3400_thermal_run_osc(priv->adev->handle, - "b23ba85d-c8b7-3542-88de-8de2ffcfd698", - &cap); + ret = set_os_uuid_mask(priv, priv->os_uuid_mask); if (ret) return ret; } @@ -469,17 +476,26 @@ static int int3400_thermal_change_mode(struct thermal_zone_device *thermal, if (mode != thermal->mode) { int enabled; + enabled = mode == THERMAL_DEVICE_ENABLED; + + if (priv->os_uuid_mask) { + if (!enabled) { + priv->os_uuid_mask = 0; + result = set_os_uuid_mask(priv, priv->os_uuid_mask); + } + goto eval_odvp; + } + if (priv->current_uuid_index < 0 || priv->current_uuid_index >= INT3400_THERMAL_MAXIMUM_UUID) return -EINVAL; - enabled = (mode == THERMAL_DEVICE_ENABLED); result = int3400_thermal_run_osc(priv->adev->handle, int3400_thermal_uuids[priv->current_uuid_index], &enabled); } - +eval_odvp: evaluate_odvp(priv); return result; diff --git a/drivers/tty/n_gsm.c b/drivers/tty/n_gsm.c index a38b922bcbc1..fd8b86dde525 100644 --- a/drivers/tty/n_gsm.c +++ b/drivers/tty/n_gsm.c @@ -137,6 +137,7 @@ struct gsm_dlci { int retries; /* Uplink tty if active */ struct tty_port port; /* The tty bound to this DLCI if there is one */ +#define TX_SIZE 4096 /* Must be power of 2. */ struct kfifo fifo; /* Queue fifo for the DLCI */ int adaption; /* Adaption layer in use */ int prev_adaption; @@ -1658,6 +1659,7 @@ static void gsm_dlci_data(struct gsm_dlci *dlci, const u8 *data, int clen) if (len == 0) return; } + len--; slen++; tty = tty_port_tty_get(port); if (tty) { @@ -1730,7 +1732,7 @@ static struct gsm_dlci *gsm_dlci_alloc(struct gsm_mux *gsm, int addr) return NULL; spin_lock_init(&dlci->lock); mutex_init(&dlci->mutex); - if (kfifo_alloc(&dlci->fifo, 4096, GFP_KERNEL) < 0) { + if (kfifo_alloc(&dlci->fifo, TX_SIZE, GFP_KERNEL) < 0) { kfree(dlci); return NULL; } @@ -2351,6 +2353,7 @@ static void gsm_copy_config_values(struct gsm_mux *gsm, static int gsm_config(struct gsm_mux *gsm, struct gsm_config *c) { + int ret = 0; int need_close = 0; int need_restart = 0; @@ -2418,10 +2421,13 @@ static int gsm_config(struct gsm_mux *gsm, struct gsm_config *c) * FIXME: We need to separate activation/deactivation from adding * and removing from the mux array */ - if (need_restart) - gsm_activate_mux(gsm); - if (gsm->initiator && need_close) - gsm_dlci_begin_open(gsm->dlci[0]); + if (gsm->dead) { + ret = gsm_activate_mux(gsm); + if (ret) + return ret; + if (gsm->initiator) + gsm_dlci_begin_open(gsm->dlci[0]); + } return 0; } @@ -2971,8 +2977,6 @@ static struct tty_ldisc_ops tty_ldisc_packet = { * Virtual tty side */ -#define TX_SIZE 512 - /** * gsm_modem_upd_via_data - send modem bits via convergence layer * @dlci: channel @@ -3212,7 +3216,7 @@ static unsigned int gsmtty_write_room(struct tty_struct *tty) struct gsm_dlci *dlci = tty->driver_data; if (dlci->state == DLCI_CLOSED) return 0; - return TX_SIZE - kfifo_len(&dlci->fifo); + return kfifo_avail(&dlci->fifo); } static unsigned int gsmtty_chars_in_buffer(struct tty_struct *tty) diff --git a/drivers/tty/serial/8250/8250_mtk.c b/drivers/tty/serial/8250/8250_mtk.c index f4a0caa56f84..21053db93ff1 100644 --- a/drivers/tty/serial/8250/8250_mtk.c +++ b/drivers/tty/serial/8250/8250_mtk.c @@ -37,6 +37,7 @@ #define MTK_UART_IER_RTSI 0x40 /* Enable RTS Modem status interrupt */ #define MTK_UART_IER_CTSI 0x80 /* Enable CTS Modem status interrupt */ +#define MTK_UART_EFR 38 /* I/O: Extended Features Register */ #define MTK_UART_EFR_EN 0x10 /* Enable enhancement feature */ #define MTK_UART_EFR_RTS 0x40 /* Enable hardware rx flow control */ #define MTK_UART_EFR_CTS 0x80 /* Enable hardware tx flow control */ @@ -53,6 +54,12 @@ #define MTK_UART_TX_TRIGGER 1 #define MTK_UART_RX_TRIGGER MTK_UART_RX_SIZE +#define MTK_UART_FEATURE_SEL 39 /* Feature Selection register */ +#define MTK_UART_FEAT_NEWRMAP BIT(0) /* Use new register map */ + +#define MTK_UART_XON1 40 /* I/O: Xon character 1 */ +#define MTK_UART_XOFF1 42 /* I/O: Xoff character 1 */ + #ifdef CONFIG_SERIAL_8250_DMA enum dma_rx_status { DMA_RX_START = 0, @@ -169,7 +176,7 @@ static void mtk8250_dma_enable(struct uart_8250_port *up) MTK_UART_DMA_EN_RX | MTK_UART_DMA_EN_TX); serial_out(up, UART_LCR, UART_LCR_CONF_MODE_B); - serial_out(up, UART_EFR, UART_EFR_ECB); + serial_out(up, MTK_UART_EFR, UART_EFR_ECB); serial_out(up, UART_LCR, lcr); if (dmaengine_slave_config(dma->rxchan, &dma->rxconf) != 0) @@ -232,7 +239,7 @@ static void mtk8250_set_flow_ctrl(struct uart_8250_port *up, int mode) int lcr = serial_in(up, UART_LCR); serial_out(up, UART_LCR, UART_LCR_CONF_MODE_B); - serial_out(up, UART_EFR, UART_EFR_ECB); + serial_out(up, MTK_UART_EFR, UART_EFR_ECB); serial_out(up, UART_LCR, lcr); lcr = serial_in(up, UART_LCR); @@ -241,7 +248,7 @@ static void mtk8250_set_flow_ctrl(struct uart_8250_port *up, int mode) serial_out(up, MTK_UART_ESCAPE_DAT, MTK_UART_ESCAPE_CHAR); serial_out(up, MTK_UART_ESCAPE_EN, 0x00); serial_out(up, UART_LCR, UART_LCR_CONF_MODE_B); - serial_out(up, UART_EFR, serial_in(up, UART_EFR) & + serial_out(up, MTK_UART_EFR, serial_in(up, MTK_UART_EFR) & (~(MTK_UART_EFR_HW_FC | MTK_UART_EFR_SW_FC_MASK))); serial_out(up, UART_LCR, lcr); mtk8250_disable_intrs(up, MTK_UART_IER_XOFFI | @@ -255,8 +262,8 @@ static void mtk8250_set_flow_ctrl(struct uart_8250_port *up, int mode) serial_out(up, UART_LCR, UART_LCR_CONF_MODE_B); /*enable hw flow control*/ - serial_out(up, UART_EFR, MTK_UART_EFR_HW_FC | - (serial_in(up, UART_EFR) & + serial_out(up, MTK_UART_EFR, MTK_UART_EFR_HW_FC | + (serial_in(up, MTK_UART_EFR) & (~(MTK_UART_EFR_HW_FC | MTK_UART_EFR_SW_FC_MASK)))); serial_out(up, UART_LCR, lcr); @@ -270,12 +277,12 @@ static void mtk8250_set_flow_ctrl(struct uart_8250_port *up, int mode) serial_out(up, UART_LCR, UART_LCR_CONF_MODE_B); /*enable sw flow control */ - serial_out(up, UART_EFR, MTK_UART_EFR_XON1_XOFF1 | - (serial_in(up, UART_EFR) & + serial_out(up, MTK_UART_EFR, MTK_UART_EFR_XON1_XOFF1 | + (serial_in(up, MTK_UART_EFR) & (~(MTK_UART_EFR_HW_FC | MTK_UART_EFR_SW_FC_MASK)))); - serial_out(up, UART_XON1, START_CHAR(port->state->port.tty)); - serial_out(up, UART_XOFF1, STOP_CHAR(port->state->port.tty)); + serial_out(up, MTK_UART_XON1, START_CHAR(port->state->port.tty)); + serial_out(up, MTK_UART_XOFF1, STOP_CHAR(port->state->port.tty)); serial_out(up, UART_LCR, lcr); mtk8250_disable_intrs(up, MTK_UART_IER_CTSI|MTK_UART_IER_RTSI); mtk8250_enable_intrs(up, MTK_UART_IER_XOFFI); @@ -568,6 +575,10 @@ static int mtk8250_probe(struct platform_device *pdev) uart.dma = data->dma; #endif + /* Set AP UART new register map */ + writel(MTK_UART_FEAT_NEWRMAP, uart.port.membase + + (MTK_UART_FEATURE_SEL << uart.port.regshift)); + /* Disable Rate Fix function */ writel(0x0, uart.port.membase + (MTK_UART_RATE_FIX << uart.port.regshift)); diff --git a/drivers/tty/serial/digicolor-usart.c b/drivers/tty/serial/digicolor-usart.c index 6d70fea76bb3..e37a917b9dbb 100644 --- a/drivers/tty/serial/digicolor-usart.c +++ b/drivers/tty/serial/digicolor-usart.c @@ -471,11 +471,10 @@ static int digicolor_uart_probe(struct platform_device *pdev) if (IS_ERR(uart_clk)) return PTR_ERR(uart_clk); - res = platform_get_resource(pdev, IORESOURCE_MEM, 0); - dp->port.mapbase = res->start; - dp->port.membase = devm_ioremap_resource(&pdev->dev, res); + dp->port.membase = devm_platform_get_and_ioremap_resource(pdev, 0, &res); if (IS_ERR(dp->port.membase)) return PTR_ERR(dp->port.membase); + dp->port.mapbase = res->start; irq = platform_get_irq(pdev, 0); if (irq < 0) diff --git a/drivers/tty/serial/fsl_lpuart.c b/drivers/tty/serial/fsl_lpuart.c index 87789872f400..be12fee94db5 100644 --- a/drivers/tty/serial/fsl_lpuart.c +++ b/drivers/tty/serial/fsl_lpuart.c @@ -2664,6 +2664,7 @@ static int lpuart_probe(struct platform_device *pdev) struct device_node *np = pdev->dev.of_node; struct lpuart_port *sport; struct resource *res; + irq_handler_t handler; int ret; sport = devm_kzalloc(&pdev->dev, sizeof(*sport), GFP_KERNEL); @@ -2741,17 +2742,11 @@ static int lpuart_probe(struct platform_device *pdev) if (lpuart_is_32(sport)) { lpuart_reg.cons = LPUART32_CONSOLE; - ret = devm_request_irq(&pdev->dev, sport->port.irq, lpuart32_int, 0, - DRIVER_NAME, sport); + handler = lpuart32_int; } else { lpuart_reg.cons = LPUART_CONSOLE; - ret = devm_request_irq(&pdev->dev, sport->port.irq, lpuart_int, 0, - DRIVER_NAME, sport); + handler = lpuart_int; } - - if (ret) - goto failed_irq_request; - ret = uart_add_one_port(&lpuart_reg, &sport->port); if (ret) goto failed_attach_port; @@ -2773,13 +2768,18 @@ static int lpuart_probe(struct platform_device *pdev) sport->port.rs485_config(&sport->port, &sport->port.rs485); + ret = devm_request_irq(&pdev->dev, sport->port.irq, handler, 0, + DRIVER_NAME, sport); + if (ret) + goto failed_irq_request; + return 0; +failed_irq_request: failed_get_rs485: failed_reset: uart_remove_one_port(&lpuart_reg, &sport->port); failed_attach_port: -failed_irq_request: lpuart_disable_clks(sport); failed_clock_enable: failed_out_of_range: diff --git a/drivers/usb/class/cdc-wdm.c b/drivers/usb/class/cdc-wdm.c index 7f2c83f299d3..eebe782380fb 100644 --- a/drivers/usb/class/cdc-wdm.c +++ b/drivers/usb/class/cdc-wdm.c @@ -774,6 +774,7 @@ static int wdm_release(struct inode *inode, struct file *file) poison_urbs(desc); spin_lock_irq(&desc->iuspin); desc->resp_count = 0; + clear_bit(WDM_RESPONDING, &desc->flags); spin_unlock_irq(&desc->iuspin); desc->manage_power(desc->intf, 0); unpoison_urbs(desc); diff --git a/drivers/usb/gadget/function/f_uvc.c b/drivers/usb/gadget/function/f_uvc.c index 71bb5e477dba..d37965867b23 100644 --- a/drivers/usb/gadget/function/f_uvc.c +++ b/drivers/usb/gadget/function/f_uvc.c @@ -890,13 +890,37 @@ static void uvc_function_unbind(struct usb_configuration *c, { struct usb_composite_dev *cdev = c->cdev; struct uvc_device *uvc = to_uvc(f); + long wait_ret = 1; uvcg_info(f, "%s()\n", __func__); + /* If we know we're connected via v4l2, then there should be a cleanup + * of the device from userspace either via UVC_EVENT_DISCONNECT or + * though the video device removal uevent. Allow some time for the + * application to close out before things get deleted. + */ + if (uvc->func_connected) { + uvcg_dbg(f, "waiting for clean disconnect\n"); + wait_ret = wait_event_interruptible_timeout(uvc->func_connected_queue, + uvc->func_connected == false, msecs_to_jiffies(500)); + uvcg_dbg(f, "done waiting with ret: %ld\n", wait_ret); + } + device_remove_file(&uvc->vdev.dev, &dev_attr_function_name); video_unregister_device(&uvc->vdev); v4l2_device_unregister(&uvc->v4l2_dev); + if (uvc->func_connected) { + /* Wait for the release to occur to ensure there are no longer any + * pending operations that may cause panics when resources are cleaned + * up. + */ + uvcg_warn(f, "%s no clean disconnect, wait for release\n", __func__); + wait_ret = wait_event_interruptible_timeout(uvc->func_connected_queue, + uvc->func_connected == false, msecs_to_jiffies(1000)); + uvcg_dbg(f, "done waiting for release with ret: %ld\n", wait_ret); + } + usb_ep_free_request(cdev->gadget->ep0, uvc->control_req); kfree(uvc->control_buf); @@ -915,6 +939,7 @@ static struct usb_function *uvc_alloc(struct usb_function_instance *fi) mutex_init(&uvc->video.mutex); uvc->state = UVC_STATE_DISCONNECTED; + init_waitqueue_head(&uvc->func_connected_queue); opts = fi_to_f_uvc_opts(fi); mutex_lock(&opts->lock); diff --git a/drivers/usb/gadget/function/uvc.h b/drivers/usb/gadget/function/uvc.h index c3607a32b986..886103a1fe9b 100644 --- a/drivers/usb/gadget/function/uvc.h +++ b/drivers/usb/gadget/function/uvc.h @@ -14,6 +14,7 @@ #include <linux/spinlock.h> #include <linux/usb/composite.h> #include <linux/videodev2.h> +#include <linux/wait.h> #include <media/v4l2-device.h> #include <media/v4l2-dev.h> @@ -129,6 +130,7 @@ struct uvc_device { struct usb_function func; struct uvc_video video; bool func_connected; + wait_queue_head_t func_connected_queue; /* Descriptors */ struct { diff --git a/drivers/usb/gadget/function/uvc_v4l2.c b/drivers/usb/gadget/function/uvc_v4l2.c index a2c78690c5c2..fd8f73bb726d 100644 --- a/drivers/usb/gadget/function/uvc_v4l2.c +++ b/drivers/usb/gadget/function/uvc_v4l2.c @@ -253,10 +253,11 @@ uvc_v4l2_subscribe_event(struct v4l2_fh *fh, static void uvc_v4l2_disable(struct uvc_device *uvc) { - uvc->func_connected = false; uvc_function_disconnect(uvc); uvcg_video_enable(&uvc->video, 0); uvcg_free_buffers(&uvc->video.queue); + uvc->func_connected = false; + wake_up_interruptible(&uvc->func_connected_queue); } static int diff --git a/drivers/usb/gadget/legacy/raw_gadget.c b/drivers/usb/gadget/legacy/raw_gadget.c index 8d40a1f2ec57..e9440f7bf019 100644 --- a/drivers/usb/gadget/legacy/raw_gadget.c +++ b/drivers/usb/gadget/legacy/raw_gadget.c @@ -145,6 +145,7 @@ enum dev_state { STATE_DEV_INVALID = 0, STATE_DEV_OPENED, STATE_DEV_INITIALIZED, + STATE_DEV_REGISTERING, STATE_DEV_RUNNING, STATE_DEV_CLOSED, STATE_DEV_FAILED @@ -508,6 +509,7 @@ static int raw_ioctl_run(struct raw_dev *dev, unsigned long value) ret = -EINVAL; goto out_unlock; } + dev->state = STATE_DEV_REGISTERING; spin_unlock_irqrestore(&dev->lock, flags); ret = usb_gadget_probe_driver(&dev->driver); diff --git a/drivers/usb/host/xhci-mtk-sch.c b/drivers/usb/host/xhci-mtk-sch.c index f3139ce7b0a9..06a6b19acaae 100644 --- a/drivers/usb/host/xhci-mtk-sch.c +++ b/drivers/usb/host/xhci-mtk-sch.c @@ -19,11 +19,6 @@ #define HS_BW_BOUNDARY 6144 /* usb2 spec section11.18.1: at most 188 FS bytes per microframe */ #define FS_PAYLOAD_MAX 188 -/* - * max number of microframes for split transfer, - * for fs isoc in : 1 ss + 1 idle + 7 cs - */ -#define TT_MICROFRAMES_MAX 9 #define DBG_BUF_EN 64 @@ -242,28 +237,17 @@ static void drop_tt(struct usb_device *udev) static struct mu3h_sch_ep_info * create_sch_ep(struct xhci_hcd_mtk *mtk, struct usb_device *udev, - struct usb_host_endpoint *ep, struct xhci_ep_ctx *ep_ctx) + struct usb_host_endpoint *ep) { struct mu3h_sch_ep_info *sch_ep; struct mu3h_sch_bw_info *bw_info; struct mu3h_sch_tt *tt = NULL; - u32 len_bw_budget_table; bw_info = get_bw_info(mtk, udev, ep); if (!bw_info) return ERR_PTR(-ENODEV); - if (is_fs_or_ls(udev->speed)) - len_bw_budget_table = TT_MICROFRAMES_MAX; - else if ((udev->speed >= USB_SPEED_SUPER) - && usb_endpoint_xfer_isoc(&ep->desc)) - len_bw_budget_table = get_esit(ep_ctx); - else - len_bw_budget_table = 1; - - sch_ep = kzalloc(struct_size(sch_ep, bw_budget_table, - len_bw_budget_table), - GFP_KERNEL); + sch_ep = kzalloc(sizeof(*sch_ep), GFP_KERNEL); if (!sch_ep) return ERR_PTR(-ENOMEM); @@ -295,8 +279,6 @@ static void setup_sch_info(struct xhci_ep_ctx *ep_ctx, u32 mult; u32 esit_pkts; u32 max_esit_payload; - u32 *bwb_table = sch_ep->bw_budget_table; - int i; ep_type = CTX_TO_EP_TYPE(le32_to_cpu(ep_ctx->ep_info2)); maxpkt = MAX_PACKET_DECODED(le32_to_cpu(ep_ctx->ep_info2)); @@ -332,7 +314,6 @@ static void setup_sch_info(struct xhci_ep_ctx *ep_ctx, */ sch_ep->pkts = max_burst + 1; sch_ep->bw_cost_per_microframe = maxpkt * sch_ep->pkts; - bwb_table[0] = sch_ep->bw_cost_per_microframe; } else if (sch_ep->speed >= USB_SPEED_SUPER) { /* usb3_r1 spec section4.4.7 & 4.4.8 */ sch_ep->cs_count = 0; @@ -349,7 +330,6 @@ static void setup_sch_info(struct xhci_ep_ctx *ep_ctx, if (ep_type == INT_IN_EP || ep_type == INT_OUT_EP) { sch_ep->pkts = esit_pkts; sch_ep->num_budget_microframes = 1; - bwb_table[0] = maxpkt * sch_ep->pkts; } if (ep_type == ISOC_IN_EP || ep_type == ISOC_OUT_EP) { @@ -366,15 +346,8 @@ static void setup_sch_info(struct xhci_ep_ctx *ep_ctx, DIV_ROUND_UP(esit_pkts, sch_ep->pkts); sch_ep->repeat = !!(sch_ep->num_budget_microframes > 1); - sch_ep->bw_cost_per_microframe = maxpkt * sch_ep->pkts; - - for (i = 0; i < sch_ep->num_budget_microframes - 1; i++) - bwb_table[i] = sch_ep->bw_cost_per_microframe; - - /* last one <= bw_cost_per_microframe */ - bwb_table[i] = maxpkt * esit_pkts - - i * sch_ep->bw_cost_per_microframe; } + sch_ep->bw_cost_per_microframe = maxpkt * sch_ep->pkts; } else if (is_fs_or_ls(sch_ep->speed)) { sch_ep->pkts = 1; /* at most one packet for each microframe */ @@ -384,28 +357,7 @@ static void setup_sch_info(struct xhci_ep_ctx *ep_ctx, */ sch_ep->cs_count = DIV_ROUND_UP(maxpkt, FS_PAYLOAD_MAX); sch_ep->num_budget_microframes = sch_ep->cs_count; - sch_ep->bw_cost_per_microframe = - (maxpkt < FS_PAYLOAD_MAX) ? maxpkt : FS_PAYLOAD_MAX; - - /* init budget table */ - if (ep_type == ISOC_OUT_EP) { - for (i = 0; i < sch_ep->num_budget_microframes; i++) - bwb_table[i] = sch_ep->bw_cost_per_microframe; - } else if (ep_type == INT_OUT_EP) { - /* only first one consumes bandwidth, others as zero */ - bwb_table[0] = sch_ep->bw_cost_per_microframe; - } else { /* INT_IN_EP or ISOC_IN_EP */ - bwb_table[0] = 0; /* start split */ - bwb_table[1] = 0; /* idle */ - /* - * due to cs_count will be updated according to cs - * position, assign all remainder budget array - * elements as @bw_cost_per_microframe, but only first - * @num_budget_microframes elements will be used later - */ - for (i = 2; i < TT_MICROFRAMES_MAX; i++) - bwb_table[i] = sch_ep->bw_cost_per_microframe; - } + sch_ep->bw_cost_per_microframe = min_t(u32, maxpkt, FS_PAYLOAD_MAX); } } @@ -422,7 +374,7 @@ static u32 get_max_bw(struct mu3h_sch_bw_info *sch_bw, for (j = 0; j < sch_ep->num_budget_microframes; j++) { k = XHCI_MTK_BW_INDEX(base + j); - bw = sch_bw->bus_bw[k] + sch_ep->bw_budget_table[j]; + bw = sch_bw->bus_bw[k] + sch_ep->bw_cost_per_microframe; if (bw > max_bw) max_bw = bw; } @@ -433,18 +385,16 @@ static u32 get_max_bw(struct mu3h_sch_bw_info *sch_bw, static void update_bus_bw(struct mu3h_sch_bw_info *sch_bw, struct mu3h_sch_ep_info *sch_ep, bool used) { + int bw_updated; u32 base; - int i, j, k; + int i, j; + + bw_updated = sch_ep->bw_cost_per_microframe * (used ? 1 : -1); for (i = 0; i < sch_ep->num_esit; i++) { base = sch_ep->offset + i * sch_ep->esit; - for (j = 0; j < sch_ep->num_budget_microframes; j++) { - k = XHCI_MTK_BW_INDEX(base + j); - if (used) - sch_bw->bus_bw[k] += sch_ep->bw_budget_table[j]; - else - sch_bw->bus_bw[k] -= sch_ep->bw_budget_table[j]; - } + for (j = 0; j < sch_ep->num_budget_microframes; j++) + sch_bw->bus_bw[XHCI_MTK_BW_INDEX(base + j)] += bw_updated; } } @@ -464,7 +414,7 @@ static int check_fs_bus_bw(struct mu3h_sch_ep_info *sch_ep, int offset) */ for (j = 0; j < sch_ep->num_budget_microframes; j++) { k = XHCI_MTK_BW_INDEX(base + j); - tmp = tt->fs_bus_bw[k] + sch_ep->bw_budget_table[j]; + tmp = tt->fs_bus_bw[k] + sch_ep->bw_cost_per_microframe; if (tmp > FS_PAYLOAD_MAX) return -ESCH_BW_OVERFLOW; } @@ -538,19 +488,17 @@ static int check_sch_tt(struct mu3h_sch_ep_info *sch_ep, u32 offset) static void update_sch_tt(struct mu3h_sch_ep_info *sch_ep, bool used) { struct mu3h_sch_tt *tt = sch_ep->sch_tt; + int bw_updated; u32 base; - int i, j, k; + int i, j; + + bw_updated = sch_ep->bw_cost_per_microframe * (used ? 1 : -1); for (i = 0; i < sch_ep->num_esit; i++) { base = sch_ep->offset + i * sch_ep->esit; - for (j = 0; j < sch_ep->num_budget_microframes; j++) { - k = XHCI_MTK_BW_INDEX(base + j); - if (used) - tt->fs_bus_bw[k] += sch_ep->bw_budget_table[j]; - else - tt->fs_bus_bw[k] -= sch_ep->bw_budget_table[j]; - } + for (j = 0; j < sch_ep->num_budget_microframes; j++) + tt->fs_bus_bw[XHCI_MTK_BW_INDEX(base + j)] += bw_updated; } if (used) @@ -710,7 +658,7 @@ static int add_ep_quirk(struct usb_hcd *hcd, struct usb_device *udev, xhci_dbg(xhci, "%s %s\n", __func__, decode_ep(ep, udev->speed)); - sch_ep = create_sch_ep(mtk, udev, ep, ep_ctx); + sch_ep = create_sch_ep(mtk, udev, ep); if (IS_ERR_OR_NULL(sch_ep)) return -ENOMEM; diff --git a/drivers/usb/host/xhci-mtk.h b/drivers/usb/host/xhci-mtk.h index ffd4b493b4ba..1174a510dd38 100644 --- a/drivers/usb/host/xhci-mtk.h +++ b/drivers/usb/host/xhci-mtk.h @@ -83,7 +83,6 @@ struct mu3h_sch_bw_info { * times; 1: distribute the (bMaxBurst+1)*(Mult+1) packets * according to @pkts and @repeat. normal mode is used by * default - * @bw_budget_table: table to record bandwidth budget per microframe */ struct mu3h_sch_ep_info { u32 esit; @@ -109,7 +108,6 @@ struct mu3h_sch_ep_info { u32 pkts; u32 cs_count; u32 burst_mode; - u32 bw_budget_table[]; }; #define MU3C_U3_PORT_MAX 4 diff --git a/drivers/usb/serial/option.c b/drivers/usb/serial/option.c index 1364ce7f0abf..152ad882657d 100644 --- a/drivers/usb/serial/option.c +++ b/drivers/usb/serial/option.c @@ -2123,10 +2123,14 @@ static const struct usb_device_id option_ids[] = { .driver_info = RSVD(3) }, { USB_DEVICE(0x1508, 0x1001), /* Fibocom NL668 (IOT version) */ .driver_info = RSVD(4) | RSVD(5) | RSVD(6) }, + { USB_DEVICE(0x1782, 0x4d10) }, /* Fibocom L610 (AT mode) */ + { USB_DEVICE_INTERFACE_CLASS(0x1782, 0x4d11, 0xff) }, /* Fibocom L610 (ECM/RNDIS mode) */ { USB_DEVICE(0x2cb7, 0x0104), /* Fibocom NL678 series */ .driver_info = RSVD(4) | RSVD(5) }, { USB_DEVICE_INTERFACE_CLASS(0x2cb7, 0x0105, 0xff), /* Fibocom NL678 series */ .driver_info = RSVD(6) }, + { USB_DEVICE_INTERFACE_CLASS(0x2cb7, 0x0106, 0xff) }, /* Fibocom MA510 (ECM mode w/ diag intf.) */ + { USB_DEVICE_INTERFACE_CLASS(0x2cb7, 0x010a, 0xff) }, /* Fibocom MA510 (ECM mode) */ { USB_DEVICE_AND_INTERFACE_INFO(0x2cb7, 0x010b, 0xff, 0xff, 0x30) }, /* Fibocom FG150 Diag */ { USB_DEVICE_AND_INTERFACE_INFO(0x2cb7, 0x010b, 0xff, 0, 0) }, /* Fibocom FG150 AT */ { USB_DEVICE_INTERFACE_CLASS(0x2cb7, 0x01a0, 0xff) }, /* Fibocom NL668-AM/NL652-EU (laptop MBIM) */ diff --git a/drivers/usb/serial/pl2303.c b/drivers/usb/serial/pl2303.c index 88b284d61681..1d878d05a658 100644 --- a/drivers/usb/serial/pl2303.c +++ b/drivers/usb/serial/pl2303.c @@ -106,6 +106,7 @@ static const struct usb_device_id id_table[] = { { USB_DEVICE(HP_VENDOR_ID, HP_LCM220_PRODUCT_ID) }, { USB_DEVICE(HP_VENDOR_ID, HP_LCM960_PRODUCT_ID) }, { USB_DEVICE(HP_VENDOR_ID, HP_LM920_PRODUCT_ID) }, + { USB_DEVICE(HP_VENDOR_ID, HP_LM930_PRODUCT_ID) }, { USB_DEVICE(HP_VENDOR_ID, HP_LM940_PRODUCT_ID) }, { USB_DEVICE(HP_VENDOR_ID, HP_TD620_PRODUCT_ID) }, { USB_DEVICE(CRESSI_VENDOR_ID, CRESSI_EDY_PRODUCT_ID) }, diff --git a/drivers/usb/serial/pl2303.h b/drivers/usb/serial/pl2303.h index c5406452b774..732f9b13ad5d 100644 --- a/drivers/usb/serial/pl2303.h +++ b/drivers/usb/serial/pl2303.h @@ -135,6 +135,7 @@ #define HP_TD620_PRODUCT_ID 0x0956 #define HP_LD960_PRODUCT_ID 0x0b39 #define HP_LD381_PRODUCT_ID 0x0f7f +#define HP_LM930_PRODUCT_ID 0x0f9b #define HP_LCM220_PRODUCT_ID 0x3139 #define HP_LCM960_PRODUCT_ID 0x3239 #define HP_LD220_PRODUCT_ID 0x3524 diff --git a/drivers/usb/serial/qcserial.c b/drivers/usb/serial/qcserial.c index c18bf8164bc2..586ef5551e76 100644 --- a/drivers/usb/serial/qcserial.c +++ b/drivers/usb/serial/qcserial.c @@ -166,6 +166,8 @@ static const struct usb_device_id id_table[] = { {DEVICE_SWI(0x1199, 0x9090)}, /* Sierra Wireless EM7565 QDL */ {DEVICE_SWI(0x1199, 0x9091)}, /* Sierra Wireless EM7565 */ {DEVICE_SWI(0x1199, 0x90d2)}, /* Sierra Wireless EM9191 QDL */ + {DEVICE_SWI(0x1199, 0xc080)}, /* Sierra Wireless EM7590 QDL */ + {DEVICE_SWI(0x1199, 0xc081)}, /* Sierra Wireless EM7590 */ {DEVICE_SWI(0x413c, 0x81a2)}, /* Dell Wireless 5806 Gobi(TM) 4G LTE Mobile Broadband Card */ {DEVICE_SWI(0x413c, 0x81a3)}, /* Dell Wireless 5570 HSPA+ (42Mbps) Mobile Broadband Card */ {DEVICE_SWI(0x413c, 0x81a4)}, /* Dell Wireless 5570e HSPA+ (42Mbps) Mobile Broadband Card */ diff --git a/drivers/usb/typec/tcpm/tcpci.c b/drivers/usb/typec/tcpm/tcpci.c index e07d26a3cd8e..f33e08eb7670 100644 --- a/drivers/usb/typec/tcpm/tcpci.c +++ b/drivers/usb/typec/tcpm/tcpci.c @@ -877,7 +877,7 @@ static int tcpci_remove(struct i2c_client *client) /* Disable chip interrupts before unregistering port */ err = tcpci_write16(chip->tcpci, TCPC_ALERT_MASK, 0); if (err < 0) - return err; + dev_warn(&client->dev, "Failed to disable irqs (%pe)\n", ERR_PTR(err)); tcpci_unregister_port(chip->tcpci); diff --git a/drivers/usb/typec/tcpm/tcpci_mt6360.c b/drivers/usb/typec/tcpm/tcpci_mt6360.c index f1bd9e09bc87..8a952eaf9016 100644 --- a/drivers/usb/typec/tcpm/tcpci_mt6360.c +++ b/drivers/usb/typec/tcpm/tcpci_mt6360.c @@ -15,6 +15,9 @@ #include "tcpci.h" +#define MT6360_REG_PHYCTRL1 0x80 +#define MT6360_REG_PHYCTRL3 0x82 +#define MT6360_REG_PHYCTRL7 0x86 #define MT6360_REG_VCONNCTRL1 0x8C #define MT6360_REG_MODECTRL2 0x8F #define MT6360_REG_SWRESET 0xA0 @@ -22,6 +25,8 @@ #define MT6360_REG_DRPCTRL1 0xA2 #define MT6360_REG_DRPCTRL2 0xA3 #define MT6360_REG_I2CTORST 0xBF +#define MT6360_REG_PHYCTRL11 0xCA +#define MT6360_REG_RXCTRL1 0xCE #define MT6360_REG_RXCTRL2 0xCF #define MT6360_REG_CTDCTRL2 0xEC @@ -106,6 +111,27 @@ static int mt6360_tcpc_init(struct tcpci *tcpci, struct tcpci_data *tdata) if (ret) return ret; + /* BMC PHY */ + ret = mt6360_tcpc_write16(regmap, MT6360_REG_PHYCTRL1, 0x3A70); + if (ret) + return ret; + + ret = regmap_write(regmap, MT6360_REG_PHYCTRL3, 0x82); + if (ret) + return ret; + + ret = regmap_write(regmap, MT6360_REG_PHYCTRL7, 0x36); + if (ret) + return ret; + + ret = mt6360_tcpc_write16(regmap, MT6360_REG_PHYCTRL11, 0x3C60); + if (ret) + return ret; + + ret = regmap_write(regmap, MT6360_REG_RXCTRL1, 0xE8); + if (ret) + return ret; + /* Set shipping mode off, AUTOIDLE on */ return regmap_write(regmap, MT6360_REG_MODECTRL2, 0x7A); } diff --git a/drivers/vdpa/mlx5/net/mlx5_vnet.c b/drivers/vdpa/mlx5/net/mlx5_vnet.c index 79001301b383..e0de44000d92 100644 --- a/drivers/vdpa/mlx5/net/mlx5_vnet.c +++ b/drivers/vdpa/mlx5/net/mlx5_vnet.c @@ -161,6 +161,7 @@ struct mlx5_vdpa_net { struct mlx5_flow_handle *rx_rule_mcast; bool setup; u32 cur_num_vqs; + u32 rqt_size; struct notifier_block nb; struct vdpa_callback config_cb; struct mlx5_vdpa_wq_ent cvq_ent; @@ -204,17 +205,12 @@ static __virtio16 cpu_to_mlx5vdpa16(struct mlx5_vdpa_dev *mvdev, u16 val) return __cpu_to_virtio16(mlx5_vdpa_is_little_endian(mvdev), val); } -static inline u32 mlx5_vdpa_max_qps(int max_vqs) -{ - return max_vqs / 2; -} - static u16 ctrl_vq_idx(struct mlx5_vdpa_dev *mvdev) { if (!(mvdev->actual_features & BIT_ULL(VIRTIO_NET_F_MQ))) return 2; - return 2 * mlx5_vdpa_max_qps(mvdev->max_vqs); + return mvdev->max_vqs; } static bool is_ctrl_vq_idx(struct mlx5_vdpa_dev *mvdev, u16 idx) @@ -1236,25 +1232,13 @@ static void teardown_vq(struct mlx5_vdpa_net *ndev, struct mlx5_vdpa_virtqueue * static int create_rqt(struct mlx5_vdpa_net *ndev) { __be32 *list; - int max_rqt; void *rqtc; int inlen; void *in; int i, j; int err; - int num; - - if (!(ndev->mvdev.actual_features & BIT_ULL(VIRTIO_NET_F_MQ))) - num = 1; - else - num = ndev->cur_num_vqs / 2; - max_rqt = min_t(int, roundup_pow_of_two(num), - 1 << MLX5_CAP_GEN(ndev->mvdev.mdev, log_max_rqt_size)); - if (max_rqt < 1) - return -EOPNOTSUPP; - - inlen = MLX5_ST_SZ_BYTES(create_rqt_in) + max_rqt * MLX5_ST_SZ_BYTES(rq_num); + inlen = MLX5_ST_SZ_BYTES(create_rqt_in) + ndev->rqt_size * MLX5_ST_SZ_BYTES(rq_num); in = kzalloc(inlen, GFP_KERNEL); if (!in) return -ENOMEM; @@ -1263,12 +1247,12 @@ static int create_rqt(struct mlx5_vdpa_net *ndev) rqtc = MLX5_ADDR_OF(create_rqt_in, in, rqt_context); MLX5_SET(rqtc, rqtc, list_q_type, MLX5_RQTC_LIST_Q_TYPE_VIRTIO_NET_Q); - MLX5_SET(rqtc, rqtc, rqt_max_size, max_rqt); + MLX5_SET(rqtc, rqtc, rqt_max_size, ndev->rqt_size); list = MLX5_ADDR_OF(rqtc, rqtc, rq_num[0]); - for (i = 0, j = 0; i < max_rqt; i++, j += 2) - list[i] = cpu_to_be32(ndev->vqs[j % (2 * num)].virtq_id); + for (i = 0, j = 0; i < ndev->rqt_size; i++, j += 2) + list[i] = cpu_to_be32(ndev->vqs[j % ndev->cur_num_vqs].virtq_id); - MLX5_SET(rqtc, rqtc, rqt_actual_size, max_rqt); + MLX5_SET(rqtc, rqtc, rqt_actual_size, ndev->rqt_size); err = mlx5_vdpa_create_rqt(&ndev->mvdev, in, inlen, &ndev->res.rqtn); kfree(in); if (err) @@ -1282,19 +1266,13 @@ static int create_rqt(struct mlx5_vdpa_net *ndev) static int modify_rqt(struct mlx5_vdpa_net *ndev, int num) { __be32 *list; - int max_rqt; void *rqtc; int inlen; void *in; int i, j; int err; - max_rqt = min_t(int, roundup_pow_of_two(ndev->cur_num_vqs / 2), - 1 << MLX5_CAP_GEN(ndev->mvdev.mdev, log_max_rqt_size)); - if (max_rqt < 1) - return -EOPNOTSUPP; - - inlen = MLX5_ST_SZ_BYTES(modify_rqt_in) + max_rqt * MLX5_ST_SZ_BYTES(rq_num); + inlen = MLX5_ST_SZ_BYTES(modify_rqt_in) + ndev->rqt_size * MLX5_ST_SZ_BYTES(rq_num); in = kzalloc(inlen, GFP_KERNEL); if (!in) return -ENOMEM; @@ -1305,10 +1283,10 @@ static int modify_rqt(struct mlx5_vdpa_net *ndev, int num) MLX5_SET(rqtc, rqtc, list_q_type, MLX5_RQTC_LIST_Q_TYPE_VIRTIO_NET_Q); list = MLX5_ADDR_OF(rqtc, rqtc, rq_num[0]); - for (i = 0, j = 0; i < max_rqt; i++, j += 2) + for (i = 0, j = 0; i < ndev->rqt_size; i++, j += 2) list[i] = cpu_to_be32(ndev->vqs[j % num].virtq_id); - MLX5_SET(rqtc, rqtc, rqt_actual_size, max_rqt); + MLX5_SET(rqtc, rqtc, rqt_actual_size, ndev->rqt_size); err = mlx5_vdpa_modify_rqt(&ndev->mvdev, in, inlen, ndev->res.rqtn); kfree(in); if (err) @@ -1625,7 +1603,7 @@ static virtio_net_ctrl_ack handle_ctrl_mq(struct mlx5_vdpa_dev *mvdev, u8 cmd) newqps = mlx5vdpa16_to_cpu(mvdev, mq.virtqueue_pairs); if (newqps < VIRTIO_NET_CTRL_MQ_VQ_PAIRS_MIN || - newqps > mlx5_vdpa_max_qps(mvdev->max_vqs)) + newqps > ndev->rqt_size) break; if (ndev->cur_num_vqs == 2 * newqps) { @@ -1989,7 +1967,7 @@ static int setup_virtqueues(struct mlx5_vdpa_dev *mvdev) int err; int i; - for (i = 0; i < 2 * mlx5_vdpa_max_qps(mvdev->max_vqs); i++) { + for (i = 0; i < mvdev->max_vqs; i++) { err = setup_vq(ndev, &ndev->vqs[i]); if (err) goto err_vq; @@ -2060,9 +2038,11 @@ static int mlx5_vdpa_set_driver_features(struct vdpa_device *vdev, u64 features) ndev->mvdev.actual_features = features & ndev->mvdev.mlx_features; if (ndev->mvdev.actual_features & BIT_ULL(VIRTIO_NET_F_MQ)) - ndev->cur_num_vqs = 2 * mlx5vdpa16_to_cpu(mvdev, ndev->config.max_virtqueue_pairs); + ndev->rqt_size = mlx5vdpa16_to_cpu(mvdev, ndev->config.max_virtqueue_pairs); else - ndev->cur_num_vqs = 2; + ndev->rqt_size = 1; + + ndev->cur_num_vqs = 2 * ndev->rqt_size; update_cvq_info(mvdev); return err; @@ -2529,7 +2509,7 @@ static void init_mvqs(struct mlx5_vdpa_net *ndev) struct mlx5_vdpa_virtqueue *mvq; int i; - for (i = 0; i < 2 * mlx5_vdpa_max_qps(ndev->mvdev.max_vqs); ++i) { + for (i = 0; i < ndev->mvdev.max_vqs; ++i) { mvq = &ndev->vqs[i]; memset(mvq, 0, offsetof(struct mlx5_vdpa_virtqueue, ri)); mvq->index = i; @@ -2671,7 +2651,8 @@ static int mlx5_vdpa_dev_add(struct vdpa_mgmt_dev *v_mdev, const char *name, return -EOPNOTSUPP; } - max_vqs = MLX5_CAP_DEV_VDPA_EMULATION(mdev, max_num_virtio_queues); + max_vqs = min_t(int, MLX5_CAP_DEV_VDPA_EMULATION(mdev, max_num_virtio_queues), + 1 << MLX5_CAP_GEN(mdev, log_max_rqt_size)); if (max_vqs < 2) { dev_warn(mdev->device, "%d virtqueues are supported. At least 2 are required\n", @@ -2742,7 +2723,7 @@ static int mlx5_vdpa_dev_add(struct vdpa_mgmt_dev *v_mdev, const char *name, ndev->mvdev.mlx_features |= BIT_ULL(VIRTIO_NET_F_MAC); } - config->max_virtqueue_pairs = cpu_to_mlx5vdpa16(mvdev, mlx5_vdpa_max_qps(max_vqs)); + config->max_virtqueue_pairs = cpu_to_mlx5vdpa16(mvdev, max_vqs / 2); mvdev->vdev.dma_dev = &mdev->pdev->dev; err = mlx5_vdpa_alloc_resources(&ndev->mvdev); if (err) @@ -2769,7 +2750,7 @@ static int mlx5_vdpa_dev_add(struct vdpa_mgmt_dev *v_mdev, const char *name, ndev->nb.notifier_call = event_handler; mlx5_notifier_register(mdev, &ndev->nb); mvdev->vdev.mdev = &mgtdev->mgtdev; - err = _vdpa_register_device(&mvdev->vdev, 2 * mlx5_vdpa_max_qps(max_vqs) + 1); + err = _vdpa_register_device(&mvdev->vdev, max_vqs + 1); if (err) goto err_reg; diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c index 792ab5f23647..297b5db47454 100644 --- a/drivers/vhost/net.c +++ b/drivers/vhost/net.c @@ -1450,13 +1450,9 @@ err: return ERR_PTR(r); } -static struct ptr_ring *get_tap_ptr_ring(int fd) +static struct ptr_ring *get_tap_ptr_ring(struct file *file) { struct ptr_ring *ring; - struct file *file = fget(fd); - - if (!file) - return NULL; ring = tun_get_tx_ring(file); if (!IS_ERR(ring)) goto out; @@ -1465,7 +1461,6 @@ static struct ptr_ring *get_tap_ptr_ring(int fd) goto out; ring = NULL; out: - fput(file); return ring; } @@ -1552,8 +1547,12 @@ static long vhost_net_set_backend(struct vhost_net *n, unsigned index, int fd) r = vhost_net_enable_vq(n, vq); if (r) goto err_used; - if (index == VHOST_NET_VQ_RX) - nvq->rx_ring = get_tap_ptr_ring(fd); + if (index == VHOST_NET_VQ_RX) { + if (sock) + nvq->rx_ring = get_tap_ptr_ring(sock->file); + else + nvq->rx_ring = NULL; + } oldubufs = nvq->ubufs; nvq->ubufs = ubufs; diff --git a/drivers/video/fbdev/core/fbmem.c b/drivers/video/fbdev/core/fbmem.c index 97eb0dee411c..a6bb0e438216 100644 --- a/drivers/video/fbdev/core/fbmem.c +++ b/drivers/video/fbdev/core/fbmem.c @@ -1434,10 +1434,7 @@ fb_release(struct inode *inode, struct file *file) __acquires(&info->lock) __releases(&info->lock) { - struct fb_info * const info = file_fb_info(file); - - if (!info) - return -ENODEV; + struct fb_info * const info = file->private_data; lock_fb_info(info); if (info->fbops->fb_release) diff --git a/drivers/video/fbdev/core/fbsysfs.c b/drivers/video/fbdev/core/fbsysfs.c index 26892940c213..82e31a2d845e 100644 --- a/drivers/video/fbdev/core/fbsysfs.c +++ b/drivers/video/fbdev/core/fbsysfs.c @@ -80,6 +80,10 @@ void framebuffer_release(struct fb_info *info) { if (!info) return; + + if (WARN_ON(refcount_read(&info->count))) + return; + kfree(info->apertures); kfree(info); } diff --git a/drivers/video/fbdev/efifb.c b/drivers/video/fbdev/efifb.c index ea42ba6445b2..b3d5f884c544 100644 --- a/drivers/video/fbdev/efifb.c +++ b/drivers/video/fbdev/efifb.c @@ -243,6 +243,10 @@ error: static inline void efifb_show_boot_graphics(struct fb_info *info) {} #endif +/* + * fb_ops.fb_destroy is called by the last put_fb_info() call at the end + * of unregister_framebuffer() or fb_release(). Do any cleanup here. + */ static void efifb_destroy(struct fb_info *info) { if (efifb_pci_dev) @@ -254,10 +258,13 @@ static void efifb_destroy(struct fb_info *info) else memunmap(info->screen_base); } + if (request_mem_succeeded) release_mem_region(info->apertures->ranges[0].base, info->apertures->ranges[0].size); fb_dealloc_cmap(&info->cmap); + + framebuffer_release(info); } static const struct fb_ops efifb_ops = { @@ -620,9 +627,9 @@ static int efifb_remove(struct platform_device *pdev) { struct fb_info *info = platform_get_drvdata(pdev); + /* efifb_destroy takes care of info cleanup */ unregister_framebuffer(info); sysfs_remove_groups(&pdev->dev.kobj, efifb_groups); - framebuffer_release(info); return 0; } diff --git a/drivers/video/fbdev/simplefb.c b/drivers/video/fbdev/simplefb.c index 94fc9c6d0411..2c198561c338 100644 --- a/drivers/video/fbdev/simplefb.c +++ b/drivers/video/fbdev/simplefb.c @@ -84,6 +84,10 @@ struct simplefb_par { static void simplefb_clocks_destroy(struct simplefb_par *par); static void simplefb_regulators_destroy(struct simplefb_par *par); +/* + * fb_ops.fb_destroy is called by the last put_fb_info() call at the end + * of unregister_framebuffer() or fb_release(). Do any cleanup here. + */ static void simplefb_destroy(struct fb_info *info) { struct simplefb_par *par = info->par; @@ -94,6 +98,8 @@ static void simplefb_destroy(struct fb_info *info) if (info->screen_base) iounmap(info->screen_base); + framebuffer_release(info); + if (mem) release_mem_region(mem->start, resource_size(mem)); } @@ -545,8 +551,8 @@ static int simplefb_remove(struct platform_device *pdev) { struct fb_info *info = platform_get_drvdata(pdev); + /* simplefb_destroy takes care of info cleanup */ unregister_framebuffer(info); - framebuffer_release(info); return 0; } diff --git a/drivers/video/fbdev/vesafb.c b/drivers/video/fbdev/vesafb.c index df6de5a9dd4c..e25e8de5ff67 100644 --- a/drivers/video/fbdev/vesafb.c +++ b/drivers/video/fbdev/vesafb.c @@ -179,6 +179,10 @@ static int vesafb_setcolreg(unsigned regno, unsigned red, unsigned green, return err; } +/* + * fb_ops.fb_destroy is called by the last put_fb_info() call at the end + * of unregister_framebuffer() or fb_release(). Do any cleanup here. + */ static void vesafb_destroy(struct fb_info *info) { struct vesafb_par *par = info->par; @@ -188,6 +192,8 @@ static void vesafb_destroy(struct fb_info *info) if (info->screen_base) iounmap(info->screen_base); release_mem_region(info->apertures->ranges[0].base, info->apertures->ranges[0].size); + + framebuffer_release(info); } static struct fb_ops vesafb_ops = { @@ -484,10 +490,10 @@ static int vesafb_remove(struct platform_device *pdev) { struct fb_info *info = platform_get_drvdata(pdev); + /* vesafb_destroy takes care of info cleanup */ unregister_framebuffer(info); if (((struct vesafb_par *)(info->par))->region) release_region(0x3c0, 32); - framebuffer_release(info); return 0; } diff --git a/drivers/virt/Kconfig b/drivers/virt/Kconfig index 121b9293c737..87ef258cec64 100644 --- a/drivers/virt/Kconfig +++ b/drivers/virt/Kconfig @@ -47,4 +47,9 @@ source "drivers/virt/vboxguest/Kconfig" source "drivers/virt/nitro_enclaves/Kconfig" source "drivers/virt/acrn/Kconfig" + +source "drivers/virt/coco/efi_secret/Kconfig" + +source "drivers/virt/coco/sev-guest/Kconfig" + endif diff --git a/drivers/virt/Makefile b/drivers/virt/Makefile index 108d0ffcc9aa..093674e05c40 100644 --- a/drivers/virt/Makefile +++ b/drivers/virt/Makefile @@ -9,3 +9,5 @@ obj-y += vboxguest/ obj-$(CONFIG_NITRO_ENCLAVES) += nitro_enclaves/ obj-$(CONFIG_ACRN_HSM) += acrn/ +obj-$(CONFIG_EFI_SECRET) += coco/efi_secret/ +obj-$(CONFIG_SEV_GUEST) += coco/sev-guest/ diff --git a/drivers/virt/coco/efi_secret/Kconfig b/drivers/virt/coco/efi_secret/Kconfig new file mode 100644 index 000000000000..4404d198f3b2 --- /dev/null +++ b/drivers/virt/coco/efi_secret/Kconfig @@ -0,0 +1,16 @@ +# SPDX-License-Identifier: GPL-2.0-only +config EFI_SECRET + tristate "EFI secret area securityfs support" + depends on EFI && X86_64 + select EFI_COCO_SECRET + select SECURITYFS + help + This is a driver for accessing the EFI secret area via securityfs. + The EFI secret area is a memory area designated by the firmware for + confidential computing secret injection (for example for AMD SEV + guests). The driver exposes the secrets as files in + <securityfs>/secrets/coco. Files can be read and deleted (deleting + a file wipes the secret from memory). + + To compile this driver as a module, choose M here. + The module will be called efi_secret. diff --git a/drivers/virt/coco/efi_secret/Makefile b/drivers/virt/coco/efi_secret/Makefile new file mode 100644 index 000000000000..c7047ce804f7 --- /dev/null +++ b/drivers/virt/coco/efi_secret/Makefile @@ -0,0 +1,2 @@ +# SPDX-License-Identifier: GPL-2.0-only +obj-$(CONFIG_EFI_SECRET) += efi_secret.o diff --git a/drivers/virt/coco/efi_secret/efi_secret.c b/drivers/virt/coco/efi_secret/efi_secret.c new file mode 100644 index 000000000000..e700a5ef7043 --- /dev/null +++ b/drivers/virt/coco/efi_secret/efi_secret.c @@ -0,0 +1,349 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * efi_secret module + * + * Copyright (C) 2022 IBM Corporation + * Author: Dov Murik <dovmurik@linux.ibm.com> + */ + +/** + * DOC: efi_secret: Allow reading EFI confidential computing (coco) secret area + * via securityfs interface. + * + * When the module is loaded (and securityfs is mounted, typically under + * /sys/kernel/security), a "secrets/coco" directory is created in securityfs. + * In it, a file is created for each secret entry. The name of each such file + * is the GUID of the secret entry, and its content is the secret data. + */ + +#include <linux/platform_device.h> +#include <linux/seq_file.h> +#include <linux/fs.h> +#include <linux/kernel.h> +#include <linux/init.h> +#include <linux/module.h> +#include <linux/io.h> +#include <linux/security.h> +#include <linux/efi.h> +#include <linux/cacheflush.h> + +#define EFI_SECRET_NUM_FILES 64 + +struct efi_secret { + struct dentry *secrets_dir; + struct dentry *fs_dir; + struct dentry *fs_files[EFI_SECRET_NUM_FILES]; + void __iomem *secret_data; + u64 secret_data_len; +}; + +/* + * Structure of the EFI secret area + * + * Offset Length + * (bytes) (bytes) Usage + * ------- ------- ----- + * 0 16 Secret table header GUID (must be 1e74f542-71dd-4d66-963e-ef4287ff173b) + * 16 4 Length of bytes of the entire secret area + * + * 20 16 First secret entry's GUID + * 36 4 First secret entry's length in bytes (= 16 + 4 + x) + * 40 x First secret entry's data + * + * 40+x 16 Second secret entry's GUID + * 56+x 4 Second secret entry's length in bytes (= 16 + 4 + y) + * 60+x y Second secret entry's data + * + * (... and so on for additional entries) + * + * The GUID of each secret entry designates the usage of the secret data. + */ + +/** + * struct secret_header - Header of entire secret area; this should be followed + * by instances of struct secret_entry. + * @guid: Must be EFI_SECRET_TABLE_HEADER_GUID + * @len: Length in bytes of entire secret area, including header + */ +struct secret_header { + efi_guid_t guid; + u32 len; +} __attribute((packed)); + +/** + * struct secret_entry - Holds one secret entry + * @guid: Secret-specific GUID (or NULL_GUID if this secret entry was deleted) + * @len: Length of secret entry, including its guid and len fields + * @data: The secret data (full of zeros if this secret entry was deleted) + */ +struct secret_entry { + efi_guid_t guid; + u32 len; + u8 data[]; +} __attribute((packed)); + +static size_t secret_entry_data_len(struct secret_entry *e) +{ + return e->len - sizeof(*e); +} + +static struct efi_secret the_efi_secret; + +static inline struct efi_secret *efi_secret_get(void) +{ + return &the_efi_secret; +} + +static int efi_secret_bin_file_show(struct seq_file *file, void *data) +{ + struct secret_entry *e = file->private; + + if (e) + seq_write(file, e->data, secret_entry_data_len(e)); + + return 0; +} +DEFINE_SHOW_ATTRIBUTE(efi_secret_bin_file); + +/* + * Overwrite memory content with zeroes, and ensure that dirty cache lines are + * actually written back to memory, to clear out the secret. + */ +static void wipe_memory(void *addr, size_t size) +{ + memzero_explicit(addr, size); +#ifdef CONFIG_X86 + clflush_cache_range(addr, size); +#endif +} + +static int efi_secret_unlink(struct inode *dir, struct dentry *dentry) +{ + struct efi_secret *s = efi_secret_get(); + struct inode *inode = d_inode(dentry); + struct secret_entry *e = (struct secret_entry *)inode->i_private; + int i; + + if (e) { + /* Zero out the secret data */ + wipe_memory(e->data, secret_entry_data_len(e)); + e->guid = NULL_GUID; + } + + inode->i_private = NULL; + + for (i = 0; i < EFI_SECRET_NUM_FILES; i++) + if (s->fs_files[i] == dentry) + s->fs_files[i] = NULL; + + /* + * securityfs_remove tries to lock the directory's inode, but we reach + * the unlink callback when it's already locked + */ + inode_unlock(dir); + securityfs_remove(dentry); + inode_lock(dir); + + return 0; +} + +static const struct inode_operations efi_secret_dir_inode_operations = { + .lookup = simple_lookup, + .unlink = efi_secret_unlink, +}; + +static int efi_secret_map_area(struct platform_device *dev) +{ + int ret; + struct efi_secret *s = efi_secret_get(); + struct linux_efi_coco_secret_area *secret_area; + + if (efi.coco_secret == EFI_INVALID_TABLE_ADDR) { + dev_err(&dev->dev, "Secret area address is not available\n"); + return -EINVAL; + } + + secret_area = memremap(efi.coco_secret, sizeof(*secret_area), MEMREMAP_WB); + if (secret_area == NULL) { + dev_err(&dev->dev, "Could not map secret area EFI config entry\n"); + return -ENOMEM; + } + if (!secret_area->base_pa || secret_area->size < sizeof(struct secret_header)) { + dev_err(&dev->dev, + "Invalid secret area memory location (base_pa=0x%llx size=0x%llx)\n", + secret_area->base_pa, secret_area->size); + ret = -EINVAL; + goto unmap; + } + + s->secret_data = ioremap_encrypted(secret_area->base_pa, secret_area->size); + if (s->secret_data == NULL) { + dev_err(&dev->dev, "Could not map secret area\n"); + ret = -ENOMEM; + goto unmap; + } + + s->secret_data_len = secret_area->size; + ret = 0; + +unmap: + memunmap(secret_area); + return ret; +} + +static void efi_secret_securityfs_teardown(struct platform_device *dev) +{ + struct efi_secret *s = efi_secret_get(); + int i; + + for (i = (EFI_SECRET_NUM_FILES - 1); i >= 0; i--) { + securityfs_remove(s->fs_files[i]); + s->fs_files[i] = NULL; + } + + securityfs_remove(s->fs_dir); + s->fs_dir = NULL; + + securityfs_remove(s->secrets_dir); + s->secrets_dir = NULL; + + dev_dbg(&dev->dev, "Removed securityfs entries\n"); +} + +static int efi_secret_securityfs_setup(struct platform_device *dev) +{ + struct efi_secret *s = efi_secret_get(); + int ret = 0, i = 0, bytes_left; + unsigned char *ptr; + struct secret_header *h; + struct secret_entry *e; + struct dentry *dent; + char guid_str[EFI_VARIABLE_GUID_LEN + 1]; + + ptr = (void __force *)s->secret_data; + h = (struct secret_header *)ptr; + if (efi_guidcmp(h->guid, EFI_SECRET_TABLE_HEADER_GUID)) { + /* + * This is not an error: it just means that EFI defines secret + * area but it was not populated by the Guest Owner. + */ + dev_dbg(&dev->dev, "EFI secret area does not start with correct GUID\n"); + return -ENODEV; + } + if (h->len < sizeof(*h)) { + dev_err(&dev->dev, "EFI secret area reported length is too small\n"); + return -EINVAL; + } + if (h->len > s->secret_data_len) { + dev_err(&dev->dev, "EFI secret area reported length is too big\n"); + return -EINVAL; + } + + s->secrets_dir = NULL; + s->fs_dir = NULL; + memset(s->fs_files, 0, sizeof(s->fs_files)); + + dent = securityfs_create_dir("secrets", NULL); + if (IS_ERR(dent)) { + dev_err(&dev->dev, "Error creating secrets securityfs directory entry err=%ld\n", + PTR_ERR(dent)); + return PTR_ERR(dent); + } + s->secrets_dir = dent; + + dent = securityfs_create_dir("coco", s->secrets_dir); + if (IS_ERR(dent)) { + dev_err(&dev->dev, "Error creating coco securityfs directory entry err=%ld\n", + PTR_ERR(dent)); + return PTR_ERR(dent); + } + d_inode(dent)->i_op = &efi_secret_dir_inode_operations; + s->fs_dir = dent; + + bytes_left = h->len - sizeof(*h); + ptr += sizeof(*h); + while (bytes_left >= (int)sizeof(*e) && i < EFI_SECRET_NUM_FILES) { + e = (struct secret_entry *)ptr; + if (e->len < sizeof(*e) || e->len > (unsigned int)bytes_left) { + dev_err(&dev->dev, "EFI secret area is corrupted\n"); + ret = -EINVAL; + goto err_cleanup; + } + + /* Skip deleted entries (which will have NULL_GUID) */ + if (efi_guidcmp(e->guid, NULL_GUID)) { + efi_guid_to_str(&e->guid, guid_str); + + dent = securityfs_create_file(guid_str, 0440, s->fs_dir, (void *)e, + &efi_secret_bin_file_fops); + if (IS_ERR(dent)) { + dev_err(&dev->dev, "Error creating efi_secret securityfs entry\n"); + ret = PTR_ERR(dent); + goto err_cleanup; + } + + s->fs_files[i++] = dent; + } + ptr += e->len; + bytes_left -= e->len; + } + + dev_info(&dev->dev, "Created %d entries in securityfs secrets/coco\n", i); + return 0; + +err_cleanup: + efi_secret_securityfs_teardown(dev); + return ret; +} + +static void efi_secret_unmap_area(void) +{ + struct efi_secret *s = efi_secret_get(); + + if (s->secret_data) { + iounmap(s->secret_data); + s->secret_data = NULL; + s->secret_data_len = 0; + } +} + +static int efi_secret_probe(struct platform_device *dev) +{ + int ret; + + ret = efi_secret_map_area(dev); + if (ret) + return ret; + + ret = efi_secret_securityfs_setup(dev); + if (ret) + goto err_unmap; + + return ret; + +err_unmap: + efi_secret_unmap_area(); + return ret; +} + +static int efi_secret_remove(struct platform_device *dev) +{ + efi_secret_securityfs_teardown(dev); + efi_secret_unmap_area(); + return 0; +} + +static struct platform_driver efi_secret_driver = { + .probe = efi_secret_probe, + .remove = efi_secret_remove, + .driver = { + .name = "efi_secret", + }, +}; + +module_platform_driver(efi_secret_driver); + +MODULE_DESCRIPTION("Confidential computing EFI secret area access"); +MODULE_AUTHOR("IBM"); +MODULE_LICENSE("GPL"); +MODULE_ALIAS("platform:efi_secret"); diff --git a/drivers/virt/coco/sev-guest/Kconfig b/drivers/virt/coco/sev-guest/Kconfig new file mode 100644 index 000000000000..f9db0799ae67 --- /dev/null +++ b/drivers/virt/coco/sev-guest/Kconfig @@ -0,0 +1,14 @@ +config SEV_GUEST + tristate "AMD SEV Guest driver" + default m + depends on AMD_MEM_ENCRYPT + select CRYPTO_AEAD2 + select CRYPTO_GCM + help + SEV-SNP firmware provides the guest a mechanism to communicate with + the PSP without risk from a malicious hypervisor who wishes to read, + alter, drop or replay the messages sent. The driver provides + userspace interface to communicate with the PSP to request the + attestation report and more. + + If you choose 'M' here, this module will be called sev-guest. diff --git a/drivers/virt/coco/sev-guest/Makefile b/drivers/virt/coco/sev-guest/Makefile new file mode 100644 index 000000000000..63d67c27723a --- /dev/null +++ b/drivers/virt/coco/sev-guest/Makefile @@ -0,0 +1,2 @@ +# SPDX-License-Identifier: GPL-2.0-only +obj-$(CONFIG_SEV_GUEST) += sev-guest.o diff --git a/drivers/virt/coco/sev-guest/sev-guest.c b/drivers/virt/coco/sev-guest/sev-guest.c new file mode 100644 index 000000000000..90ce16b6e05f --- /dev/null +++ b/drivers/virt/coco/sev-guest/sev-guest.c @@ -0,0 +1,743 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * AMD Secure Encrypted Virtualization (SEV) guest driver interface + * + * Copyright (C) 2021 Advanced Micro Devices, Inc. + * + * Author: Brijesh Singh <brijesh.singh@amd.com> + */ + +#include <linux/module.h> +#include <linux/kernel.h> +#include <linux/types.h> +#include <linux/mutex.h> +#include <linux/io.h> +#include <linux/platform_device.h> +#include <linux/miscdevice.h> +#include <linux/set_memory.h> +#include <linux/fs.h> +#include <crypto/aead.h> +#include <linux/scatterlist.h> +#include <linux/psp-sev.h> +#include <uapi/linux/sev-guest.h> +#include <uapi/linux/psp-sev.h> + +#include <asm/svm.h> +#include <asm/sev.h> + +#include "sev-guest.h" + +#define DEVICE_NAME "sev-guest" +#define AAD_LEN 48 +#define MSG_HDR_VER 1 + +struct snp_guest_crypto { + struct crypto_aead *tfm; + u8 *iv, *authtag; + int iv_len, a_len; +}; + +struct snp_guest_dev { + struct device *dev; + struct miscdevice misc; + + void *certs_data; + struct snp_guest_crypto *crypto; + struct snp_guest_msg *request, *response; + struct snp_secrets_page_layout *layout; + struct snp_req_data input; + u32 *os_area_msg_seqno; + u8 *vmpck; +}; + +static u32 vmpck_id; +module_param(vmpck_id, uint, 0444); +MODULE_PARM_DESC(vmpck_id, "The VMPCK ID to use when communicating with the PSP."); + +/* Mutex to serialize the shared buffer access and command handling. */ +static DEFINE_MUTEX(snp_cmd_mutex); + +static bool is_vmpck_empty(struct snp_guest_dev *snp_dev) +{ + char zero_key[VMPCK_KEY_LEN] = {0}; + + if (snp_dev->vmpck) + return !memcmp(snp_dev->vmpck, zero_key, VMPCK_KEY_LEN); + + return true; +} + +static void snp_disable_vmpck(struct snp_guest_dev *snp_dev) +{ + memzero_explicit(snp_dev->vmpck, VMPCK_KEY_LEN); + snp_dev->vmpck = NULL; +} + +static inline u64 __snp_get_msg_seqno(struct snp_guest_dev *snp_dev) +{ + u64 count; + + lockdep_assert_held(&snp_cmd_mutex); + + /* Read the current message sequence counter from secrets pages */ + count = *snp_dev->os_area_msg_seqno; + + return count + 1; +} + +/* Return a non-zero on success */ +static u64 snp_get_msg_seqno(struct snp_guest_dev *snp_dev) +{ + u64 count = __snp_get_msg_seqno(snp_dev); + + /* + * The message sequence counter for the SNP guest request is a 64-bit + * value but the version 2 of GHCB specification defines a 32-bit storage + * for it. If the counter exceeds the 32-bit value then return zero. + * The caller should check the return value, but if the caller happens to + * not check the value and use it, then the firmware treats zero as an + * invalid number and will fail the message request. + */ + if (count >= UINT_MAX) { + dev_err(snp_dev->dev, "request message sequence counter overflow\n"); + return 0; + } + + return count; +} + +static void snp_inc_msg_seqno(struct snp_guest_dev *snp_dev) +{ + /* + * The counter is also incremented by the PSP, so increment it by 2 + * and save in secrets page. + */ + *snp_dev->os_area_msg_seqno += 2; +} + +static inline struct snp_guest_dev *to_snp_dev(struct file *file) +{ + struct miscdevice *dev = file->private_data; + + return container_of(dev, struct snp_guest_dev, misc); +} + +static struct snp_guest_crypto *init_crypto(struct snp_guest_dev *snp_dev, u8 *key, size_t keylen) +{ + struct snp_guest_crypto *crypto; + + crypto = kzalloc(sizeof(*crypto), GFP_KERNEL_ACCOUNT); + if (!crypto) + return NULL; + + crypto->tfm = crypto_alloc_aead("gcm(aes)", 0, 0); + if (IS_ERR(crypto->tfm)) + goto e_free; + + if (crypto_aead_setkey(crypto->tfm, key, keylen)) + goto e_free_crypto; + + crypto->iv_len = crypto_aead_ivsize(crypto->tfm); + crypto->iv = kmalloc(crypto->iv_len, GFP_KERNEL_ACCOUNT); + if (!crypto->iv) + goto e_free_crypto; + + if (crypto_aead_authsize(crypto->tfm) > MAX_AUTHTAG_LEN) { + if (crypto_aead_setauthsize(crypto->tfm, MAX_AUTHTAG_LEN)) { + dev_err(snp_dev->dev, "failed to set authsize to %d\n", MAX_AUTHTAG_LEN); + goto e_free_iv; + } + } + + crypto->a_len = crypto_aead_authsize(crypto->tfm); + crypto->authtag = kmalloc(crypto->a_len, GFP_KERNEL_ACCOUNT); + if (!crypto->authtag) + goto e_free_auth; + + return crypto; + +e_free_auth: + kfree(crypto->authtag); +e_free_iv: + kfree(crypto->iv); +e_free_crypto: + crypto_free_aead(crypto->tfm); +e_free: + kfree(crypto); + + return NULL; +} + +static void deinit_crypto(struct snp_guest_crypto *crypto) +{ + crypto_free_aead(crypto->tfm); + kfree(crypto->iv); + kfree(crypto->authtag); + kfree(crypto); +} + +static int enc_dec_message(struct snp_guest_crypto *crypto, struct snp_guest_msg *msg, + u8 *src_buf, u8 *dst_buf, size_t len, bool enc) +{ + struct snp_guest_msg_hdr *hdr = &msg->hdr; + struct scatterlist src[3], dst[3]; + DECLARE_CRYPTO_WAIT(wait); + struct aead_request *req; + int ret; + + req = aead_request_alloc(crypto->tfm, GFP_KERNEL); + if (!req) + return -ENOMEM; + + /* + * AEAD memory operations: + * +------ AAD -------+------- DATA -----+---- AUTHTAG----+ + * | msg header | plaintext | hdr->authtag | + * | bytes 30h - 5Fh | or | | + * | | cipher | | + * +------------------+------------------+----------------+ + */ + sg_init_table(src, 3); + sg_set_buf(&src[0], &hdr->algo, AAD_LEN); + sg_set_buf(&src[1], src_buf, hdr->msg_sz); + sg_set_buf(&src[2], hdr->authtag, crypto->a_len); + + sg_init_table(dst, 3); + sg_set_buf(&dst[0], &hdr->algo, AAD_LEN); + sg_set_buf(&dst[1], dst_buf, hdr->msg_sz); + sg_set_buf(&dst[2], hdr->authtag, crypto->a_len); + + aead_request_set_ad(req, AAD_LEN); + aead_request_set_tfm(req, crypto->tfm); + aead_request_set_callback(req, 0, crypto_req_done, &wait); + + aead_request_set_crypt(req, src, dst, len, crypto->iv); + ret = crypto_wait_req(enc ? crypto_aead_encrypt(req) : crypto_aead_decrypt(req), &wait); + + aead_request_free(req); + return ret; +} + +static int __enc_payload(struct snp_guest_dev *snp_dev, struct snp_guest_msg *msg, + void *plaintext, size_t len) +{ + struct snp_guest_crypto *crypto = snp_dev->crypto; + struct snp_guest_msg_hdr *hdr = &msg->hdr; + + memset(crypto->iv, 0, crypto->iv_len); + memcpy(crypto->iv, &hdr->msg_seqno, sizeof(hdr->msg_seqno)); + + return enc_dec_message(crypto, msg, plaintext, msg->payload, len, true); +} + +static int dec_payload(struct snp_guest_dev *snp_dev, struct snp_guest_msg *msg, + void *plaintext, size_t len) +{ + struct snp_guest_crypto *crypto = snp_dev->crypto; + struct snp_guest_msg_hdr *hdr = &msg->hdr; + + /* Build IV with response buffer sequence number */ + memset(crypto->iv, 0, crypto->iv_len); + memcpy(crypto->iv, &hdr->msg_seqno, sizeof(hdr->msg_seqno)); + + return enc_dec_message(crypto, msg, msg->payload, plaintext, len, false); +} + +static int verify_and_dec_payload(struct snp_guest_dev *snp_dev, void *payload, u32 sz) +{ + struct snp_guest_crypto *crypto = snp_dev->crypto; + struct snp_guest_msg *resp = snp_dev->response; + struct snp_guest_msg *req = snp_dev->request; + struct snp_guest_msg_hdr *req_hdr = &req->hdr; + struct snp_guest_msg_hdr *resp_hdr = &resp->hdr; + + dev_dbg(snp_dev->dev, "response [seqno %lld type %d version %d sz %d]\n", + resp_hdr->msg_seqno, resp_hdr->msg_type, resp_hdr->msg_version, resp_hdr->msg_sz); + + /* Verify that the sequence counter is incremented by 1 */ + if (unlikely(resp_hdr->msg_seqno != (req_hdr->msg_seqno + 1))) + return -EBADMSG; + + /* Verify response message type and version number. */ + if (resp_hdr->msg_type != (req_hdr->msg_type + 1) || + resp_hdr->msg_version != req_hdr->msg_version) + return -EBADMSG; + + /* + * If the message size is greater than our buffer length then return + * an error. + */ + if (unlikely((resp_hdr->msg_sz + crypto->a_len) > sz)) + return -EBADMSG; + + /* Decrypt the payload */ + return dec_payload(snp_dev, resp, payload, resp_hdr->msg_sz + crypto->a_len); +} + +static int enc_payload(struct snp_guest_dev *snp_dev, u64 seqno, int version, u8 type, + void *payload, size_t sz) +{ + struct snp_guest_msg *req = snp_dev->request; + struct snp_guest_msg_hdr *hdr = &req->hdr; + + memset(req, 0, sizeof(*req)); + + hdr->algo = SNP_AEAD_AES_256_GCM; + hdr->hdr_version = MSG_HDR_VER; + hdr->hdr_sz = sizeof(*hdr); + hdr->msg_type = type; + hdr->msg_version = version; + hdr->msg_seqno = seqno; + hdr->msg_vmpck = vmpck_id; + hdr->msg_sz = sz; + + /* Verify the sequence number is non-zero */ + if (!hdr->msg_seqno) + return -ENOSR; + + dev_dbg(snp_dev->dev, "request [seqno %lld type %d version %d sz %d]\n", + hdr->msg_seqno, hdr->msg_type, hdr->msg_version, hdr->msg_sz); + + return __enc_payload(snp_dev, req, payload, sz); +} + +static int handle_guest_request(struct snp_guest_dev *snp_dev, u64 exit_code, int msg_ver, + u8 type, void *req_buf, size_t req_sz, void *resp_buf, + u32 resp_sz, __u64 *fw_err) +{ + unsigned long err; + u64 seqno; + int rc; + + /* Get message sequence and verify that its a non-zero */ + seqno = snp_get_msg_seqno(snp_dev); + if (!seqno) + return -EIO; + + memset(snp_dev->response, 0, sizeof(struct snp_guest_msg)); + + /* Encrypt the userspace provided payload */ + rc = enc_payload(snp_dev, seqno, msg_ver, type, req_buf, req_sz); + if (rc) + return rc; + + /* Call firmware to process the request */ + rc = snp_issue_guest_request(exit_code, &snp_dev->input, &err); + if (fw_err) + *fw_err = err; + + if (rc) + return rc; + + /* + * The verify_and_dec_payload() will fail only if the hypervisor is + * actively modifying the message header or corrupting the encrypted payload. + * This hints that hypervisor is acting in a bad faith. Disable the VMPCK so that + * the key cannot be used for any communication. The key is disabled to ensure + * that AES-GCM does not use the same IV while encrypting the request payload. + */ + rc = verify_and_dec_payload(snp_dev, resp_buf, resp_sz); + if (rc) { + dev_alert(snp_dev->dev, + "Detected unexpected decode failure, disabling the vmpck_id %d\n", + vmpck_id); + snp_disable_vmpck(snp_dev); + return rc; + } + + /* Increment to new message sequence after payload decryption was successful. */ + snp_inc_msg_seqno(snp_dev); + + return 0; +} + +static int get_report(struct snp_guest_dev *snp_dev, struct snp_guest_request_ioctl *arg) +{ + struct snp_guest_crypto *crypto = snp_dev->crypto; + struct snp_report_resp *resp; + struct snp_report_req req; + int rc, resp_len; + + lockdep_assert_held(&snp_cmd_mutex); + + if (!arg->req_data || !arg->resp_data) + return -EINVAL; + + if (copy_from_user(&req, (void __user *)arg->req_data, sizeof(req))) + return -EFAULT; + + /* + * The intermediate response buffer is used while decrypting the + * response payload. Make sure that it has enough space to cover the + * authtag. + */ + resp_len = sizeof(resp->data) + crypto->a_len; + resp = kzalloc(resp_len, GFP_KERNEL_ACCOUNT); + if (!resp) + return -ENOMEM; + + rc = handle_guest_request(snp_dev, SVM_VMGEXIT_GUEST_REQUEST, arg->msg_version, + SNP_MSG_REPORT_REQ, &req, sizeof(req), resp->data, + resp_len, &arg->fw_err); + if (rc) + goto e_free; + + if (copy_to_user((void __user *)arg->resp_data, resp, sizeof(*resp))) + rc = -EFAULT; + +e_free: + kfree(resp); + return rc; +} + +static int get_derived_key(struct snp_guest_dev *snp_dev, struct snp_guest_request_ioctl *arg) +{ + struct snp_guest_crypto *crypto = snp_dev->crypto; + struct snp_derived_key_resp resp = {0}; + struct snp_derived_key_req req; + int rc, resp_len; + /* Response data is 64 bytes and max authsize for GCM is 16 bytes. */ + u8 buf[64 + 16]; + + lockdep_assert_held(&snp_cmd_mutex); + + if (!arg->req_data || !arg->resp_data) + return -EINVAL; + + /* + * The intermediate response buffer is used while decrypting the + * response payload. Make sure that it has enough space to cover the + * authtag. + */ + resp_len = sizeof(resp.data) + crypto->a_len; + if (sizeof(buf) < resp_len) + return -ENOMEM; + + if (copy_from_user(&req, (void __user *)arg->req_data, sizeof(req))) + return -EFAULT; + + rc = handle_guest_request(snp_dev, SVM_VMGEXIT_GUEST_REQUEST, arg->msg_version, + SNP_MSG_KEY_REQ, &req, sizeof(req), buf, resp_len, + &arg->fw_err); + if (rc) + return rc; + + memcpy(resp.data, buf, sizeof(resp.data)); + if (copy_to_user((void __user *)arg->resp_data, &resp, sizeof(resp))) + rc = -EFAULT; + + /* The response buffer contains the sensitive data, explicitly clear it. */ + memzero_explicit(buf, sizeof(buf)); + memzero_explicit(&resp, sizeof(resp)); + return rc; +} + +static int get_ext_report(struct snp_guest_dev *snp_dev, struct snp_guest_request_ioctl *arg) +{ + struct snp_guest_crypto *crypto = snp_dev->crypto; + struct snp_ext_report_req req; + struct snp_report_resp *resp; + int ret, npages = 0, resp_len; + + lockdep_assert_held(&snp_cmd_mutex); + + if (!arg->req_data || !arg->resp_data) + return -EINVAL; + + if (copy_from_user(&req, (void __user *)arg->req_data, sizeof(req))) + return -EFAULT; + + /* userspace does not want certificate data */ + if (!req.certs_len || !req.certs_address) + goto cmd; + + if (req.certs_len > SEV_FW_BLOB_MAX_SIZE || + !IS_ALIGNED(req.certs_len, PAGE_SIZE)) + return -EINVAL; + + if (!access_ok((const void __user *)req.certs_address, req.certs_len)) + return -EFAULT; + + /* + * Initialize the intermediate buffer with all zeros. This buffer + * is used in the guest request message to get the certs blob from + * the host. If host does not supply any certs in it, then copy + * zeros to indicate that certificate data was not provided. + */ + memset(snp_dev->certs_data, 0, req.certs_len); + npages = req.certs_len >> PAGE_SHIFT; +cmd: + /* + * The intermediate response buffer is used while decrypting the + * response payload. Make sure that it has enough space to cover the + * authtag. + */ + resp_len = sizeof(resp->data) + crypto->a_len; + resp = kzalloc(resp_len, GFP_KERNEL_ACCOUNT); + if (!resp) + return -ENOMEM; + + snp_dev->input.data_npages = npages; + ret = handle_guest_request(snp_dev, SVM_VMGEXIT_EXT_GUEST_REQUEST, arg->msg_version, + SNP_MSG_REPORT_REQ, &req.data, + sizeof(req.data), resp->data, resp_len, &arg->fw_err); + + /* If certs length is invalid then copy the returned length */ + if (arg->fw_err == SNP_GUEST_REQ_INVALID_LEN) { + req.certs_len = snp_dev->input.data_npages << PAGE_SHIFT; + + if (copy_to_user((void __user *)arg->req_data, &req, sizeof(req))) + ret = -EFAULT; + } + + if (ret) + goto e_free; + + if (npages && + copy_to_user((void __user *)req.certs_address, snp_dev->certs_data, + req.certs_len)) { + ret = -EFAULT; + goto e_free; + } + + if (copy_to_user((void __user *)arg->resp_data, resp, sizeof(*resp))) + ret = -EFAULT; + +e_free: + kfree(resp); + return ret; +} + +static long snp_guest_ioctl(struct file *file, unsigned int ioctl, unsigned long arg) +{ + struct snp_guest_dev *snp_dev = to_snp_dev(file); + void __user *argp = (void __user *)arg; + struct snp_guest_request_ioctl input; + int ret = -ENOTTY; + + if (copy_from_user(&input, argp, sizeof(input))) + return -EFAULT; + + input.fw_err = 0xff; + + /* Message version must be non-zero */ + if (!input.msg_version) + return -EINVAL; + + mutex_lock(&snp_cmd_mutex); + + /* Check if the VMPCK is not empty */ + if (is_vmpck_empty(snp_dev)) { + dev_err_ratelimited(snp_dev->dev, "VMPCK is disabled\n"); + mutex_unlock(&snp_cmd_mutex); + return -ENOTTY; + } + + switch (ioctl) { + case SNP_GET_REPORT: + ret = get_report(snp_dev, &input); + break; + case SNP_GET_DERIVED_KEY: + ret = get_derived_key(snp_dev, &input); + break; + case SNP_GET_EXT_REPORT: + ret = get_ext_report(snp_dev, &input); + break; + default: + break; + } + + mutex_unlock(&snp_cmd_mutex); + + if (input.fw_err && copy_to_user(argp, &input, sizeof(input))) + return -EFAULT; + + return ret; +} + +static void free_shared_pages(void *buf, size_t sz) +{ + unsigned int npages = PAGE_ALIGN(sz) >> PAGE_SHIFT; + int ret; + + if (!buf) + return; + + ret = set_memory_encrypted((unsigned long)buf, npages); + if (ret) { + WARN_ONCE(ret, "failed to restore encryption mask (leak it)\n"); + return; + } + + __free_pages(virt_to_page(buf), get_order(sz)); +} + +static void *alloc_shared_pages(struct device *dev, size_t sz) +{ + unsigned int npages = PAGE_ALIGN(sz) >> PAGE_SHIFT; + struct page *page; + int ret; + + page = alloc_pages(GFP_KERNEL_ACCOUNT, get_order(sz)); + if (!page) + return NULL; + + ret = set_memory_decrypted((unsigned long)page_address(page), npages); + if (ret) { + dev_err(dev, "failed to mark page shared, ret=%d\n", ret); + __free_pages(page, get_order(sz)); + return NULL; + } + + return page_address(page); +} + +static const struct file_operations snp_guest_fops = { + .owner = THIS_MODULE, + .unlocked_ioctl = snp_guest_ioctl, +}; + +static u8 *get_vmpck(int id, struct snp_secrets_page_layout *layout, u32 **seqno) +{ + u8 *key = NULL; + + switch (id) { + case 0: + *seqno = &layout->os_area.msg_seqno_0; + key = layout->vmpck0; + break; + case 1: + *seqno = &layout->os_area.msg_seqno_1; + key = layout->vmpck1; + break; + case 2: + *seqno = &layout->os_area.msg_seqno_2; + key = layout->vmpck2; + break; + case 3: + *seqno = &layout->os_area.msg_seqno_3; + key = layout->vmpck3; + break; + default: + break; + } + + return key; +} + +static int __init sev_guest_probe(struct platform_device *pdev) +{ + struct snp_secrets_page_layout *layout; + struct sev_guest_platform_data *data; + struct device *dev = &pdev->dev; + struct snp_guest_dev *snp_dev; + struct miscdevice *misc; + int ret; + + if (!dev->platform_data) + return -ENODEV; + + data = (struct sev_guest_platform_data *)dev->platform_data; + layout = (__force void *)ioremap_encrypted(data->secrets_gpa, PAGE_SIZE); + if (!layout) + return -ENODEV; + + ret = -ENOMEM; + snp_dev = devm_kzalloc(&pdev->dev, sizeof(struct snp_guest_dev), GFP_KERNEL); + if (!snp_dev) + goto e_unmap; + + ret = -EINVAL; + snp_dev->vmpck = get_vmpck(vmpck_id, layout, &snp_dev->os_area_msg_seqno); + if (!snp_dev->vmpck) { + dev_err(dev, "invalid vmpck id %d\n", vmpck_id); + goto e_unmap; + } + + /* Verify that VMPCK is not zero. */ + if (is_vmpck_empty(snp_dev)) { + dev_err(dev, "vmpck id %d is null\n", vmpck_id); + goto e_unmap; + } + + platform_set_drvdata(pdev, snp_dev); + snp_dev->dev = dev; + snp_dev->layout = layout; + + /* Allocate the shared page used for the request and response message. */ + snp_dev->request = alloc_shared_pages(dev, sizeof(struct snp_guest_msg)); + if (!snp_dev->request) + goto e_unmap; + + snp_dev->response = alloc_shared_pages(dev, sizeof(struct snp_guest_msg)); + if (!snp_dev->response) + goto e_free_request; + + snp_dev->certs_data = alloc_shared_pages(dev, SEV_FW_BLOB_MAX_SIZE); + if (!snp_dev->certs_data) + goto e_free_response; + + ret = -EIO; + snp_dev->crypto = init_crypto(snp_dev, snp_dev->vmpck, VMPCK_KEY_LEN); + if (!snp_dev->crypto) + goto e_free_cert_data; + + misc = &snp_dev->misc; + misc->minor = MISC_DYNAMIC_MINOR; + misc->name = DEVICE_NAME; + misc->fops = &snp_guest_fops; + + /* initial the input address for guest request */ + snp_dev->input.req_gpa = __pa(snp_dev->request); + snp_dev->input.resp_gpa = __pa(snp_dev->response); + snp_dev->input.data_gpa = __pa(snp_dev->certs_data); + + ret = misc_register(misc); + if (ret) + goto e_free_cert_data; + + dev_info(dev, "Initialized SEV guest driver (using vmpck_id %d)\n", vmpck_id); + return 0; + +e_free_cert_data: + free_shared_pages(snp_dev->certs_data, SEV_FW_BLOB_MAX_SIZE); +e_free_response: + free_shared_pages(snp_dev->response, sizeof(struct snp_guest_msg)); +e_free_request: + free_shared_pages(snp_dev->request, sizeof(struct snp_guest_msg)); +e_unmap: + iounmap(layout); + return ret; +} + +static int __exit sev_guest_remove(struct platform_device *pdev) +{ + struct snp_guest_dev *snp_dev = platform_get_drvdata(pdev); + + free_shared_pages(snp_dev->certs_data, SEV_FW_BLOB_MAX_SIZE); + free_shared_pages(snp_dev->response, sizeof(struct snp_guest_msg)); + free_shared_pages(snp_dev->request, sizeof(struct snp_guest_msg)); + deinit_crypto(snp_dev->crypto); + misc_deregister(&snp_dev->misc); + + return 0; +} + +/* + * This driver is meant to be a common SEV guest interface driver and to + * support any SEV guest API. As such, even though it has been introduced + * with the SEV-SNP support, it is named "sev-guest". + */ +static struct platform_driver sev_guest_driver = { + .remove = __exit_p(sev_guest_remove), + .driver = { + .name = "sev-guest", + }, +}; + +module_platform_driver_probe(sev_guest_driver, sev_guest_probe); + +MODULE_AUTHOR("Brijesh Singh <brijesh.singh@amd.com>"); +MODULE_LICENSE("GPL"); +MODULE_VERSION("1.0.0"); +MODULE_DESCRIPTION("AMD SEV Guest Driver"); diff --git a/drivers/virt/coco/sev-guest/sev-guest.h b/drivers/virt/coco/sev-guest/sev-guest.h new file mode 100644 index 000000000000..21bda26fdb95 --- /dev/null +++ b/drivers/virt/coco/sev-guest/sev-guest.h @@ -0,0 +1,63 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (C) 2021 Advanced Micro Devices, Inc. + * + * Author: Brijesh Singh <brijesh.singh@amd.com> + * + * SEV-SNP API spec is available at https://developer.amd.com/sev + */ + +#ifndef __VIRT_SEVGUEST_H__ +#define __VIRT_SEVGUEST_H__ + +#include <linux/types.h> + +#define MAX_AUTHTAG_LEN 32 + +/* See SNP spec SNP_GUEST_REQUEST section for the structure */ +enum msg_type { + SNP_MSG_TYPE_INVALID = 0, + SNP_MSG_CPUID_REQ, + SNP_MSG_CPUID_RSP, + SNP_MSG_KEY_REQ, + SNP_MSG_KEY_RSP, + SNP_MSG_REPORT_REQ, + SNP_MSG_REPORT_RSP, + SNP_MSG_EXPORT_REQ, + SNP_MSG_EXPORT_RSP, + SNP_MSG_IMPORT_REQ, + SNP_MSG_IMPORT_RSP, + SNP_MSG_ABSORB_REQ, + SNP_MSG_ABSORB_RSP, + SNP_MSG_VMRK_REQ, + SNP_MSG_VMRK_RSP, + + SNP_MSG_TYPE_MAX +}; + +enum aead_algo { + SNP_AEAD_INVALID, + SNP_AEAD_AES_256_GCM, +}; + +struct snp_guest_msg_hdr { + u8 authtag[MAX_AUTHTAG_LEN]; + u64 msg_seqno; + u8 rsvd1[8]; + u8 algo; + u8 hdr_version; + u16 hdr_sz; + u8 msg_type; + u8 msg_version; + u16 msg_sz; + u32 rsvd2; + u8 msg_vmpck; + u8 rsvd3[35]; +} __packed; + +struct snp_guest_msg { + struct snp_guest_msg_hdr hdr; + u8 payload[4000]; +} __packed; + +#endif /* __VIRT_SEVGUEST_H__ */ diff --git a/fs/afs/inode.c b/fs/afs/inode.c index 2fe402483ad5..30b066299d39 100644 --- a/fs/afs/inode.c +++ b/fs/afs/inode.c @@ -740,10 +740,22 @@ int afs_getattr(struct user_namespace *mnt_userns, const struct path *path, { struct inode *inode = d_inode(path->dentry); struct afs_vnode *vnode = AFS_FS_I(inode); - int seq = 0; + struct key *key; + int ret, seq = 0; _enter("{ ino=%lu v=%u }", inode->i_ino, inode->i_generation); + if (!(query_flags & AT_STATX_DONT_SYNC) && + !test_bit(AFS_VNODE_CB_PROMISED, &vnode->flags)) { + key = afs_request_key(vnode->volume->cell); + if (IS_ERR(key)) + return PTR_ERR(key); + ret = afs_validate(vnode, key); + key_put(key); + if (ret < 0) + return ret; + } + do { read_seqbegin_or_lock(&vnode->cb_lock, &seq); generic_fillattr(&init_user_ns, inode, stat); diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 31c3f592e587..84795d831282 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -4238,6 +4238,7 @@ static int wait_dev_supers(struct btrfs_device *device, int max_mirrors) */ static void btrfs_end_empty_barrier(struct bio *bio) { + bio_uninit(bio); complete(bio->bi_private); } @@ -4247,7 +4248,7 @@ static void btrfs_end_empty_barrier(struct bio *bio) */ static void write_dev_flush(struct btrfs_device *device) { - struct bio *bio = device->flush_bio; + struct bio *bio = &device->flush_bio; #ifndef CONFIG_BTRFS_FS_CHECK_INTEGRITY /* @@ -4260,12 +4261,12 @@ static void write_dev_flush(struct btrfs_device *device) * of simplicity, since this is a debug tool and not meant for use in * non-debug builds. */ - struct request_queue *q = bdev_get_queue(device->bdev); - if (!test_bit(QUEUE_FLAG_WC, &q->queue_flags)) + if (!bdev_write_cache(device->bdev)) return; #endif - bio_reset(bio, device->bdev, REQ_OP_WRITE | REQ_SYNC | REQ_PREFLUSH); + bio_init(bio, device->bdev, NULL, 0, + REQ_OP_WRITE | REQ_SYNC | REQ_PREFLUSH); bio->bi_end_io = btrfs_end_empty_barrier; init_completion(&device->flush_wait); bio->bi_private = &device->flush_wait; @@ -4279,7 +4280,7 @@ static void write_dev_flush(struct btrfs_device *device) */ static blk_status_t wait_dev_flush(struct btrfs_device *device) { - struct bio *bio = device->flush_bio; + struct bio *bio = &device->flush_bio; if (!test_bit(BTRFS_DEV_STATE_FLUSH_SENT, &device->dev_state)) return BLK_STS_OK; diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index 6aa92f84f465..6260784e74b5 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -1239,7 +1239,7 @@ static int btrfs_issue_discard(struct block_device *bdev, u64 start, u64 len, if (size) { ret = blkdev_issue_discard(bdev, start >> 9, size >> 9, - GFP_NOFS, 0); + GFP_NOFS); if (!ret) *discarded_bytes += size; else if (ret != -EOPNOTSUPP) @@ -1256,7 +1256,7 @@ static int btrfs_issue_discard(struct block_device *bdev, u64 start, u64 len, if (bytes_left) { ret = blkdev_issue_discard(bdev, start >> 9, bytes_left >> 9, - GFP_NOFS, 0); + GFP_NOFS); if (!ret) *discarded_bytes += bytes_left; } @@ -1291,7 +1291,7 @@ static int do_discard_extent(struct btrfs_io_stripe *stripe, u64 *bytes) ret = btrfs_reset_device_zone(dev_replace->tgtdev, phys, len, &discarded); discarded += src_disc; - } else if (blk_queue_discard(bdev_get_queue(stripe->dev->bdev))) { + } else if (bdev_max_discard_sectors(stripe->dev->bdev)) { ret = btrfs_issue_discard(dev->bdev, phys, len, &discarded); } else { ret = 0; @@ -5987,7 +5987,7 @@ static int btrfs_trim_free_extents(struct btrfs_device *device, u64 *trimmed) *trimmed = 0; /* Discard not supported = nothing to do. */ - if (!blk_queue_discard(bdev_get_queue(device->bdev))) + if (!bdev_max_discard_sectors(device->bdev)) return 0; /* Not writable = nothing to do. */ diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index be6c24577dbe..4b28aaea2702 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -468,7 +468,6 @@ static noinline int btrfs_ioctl_fitrim(struct btrfs_fs_info *fs_info, void __user *arg) { struct btrfs_device *device; - struct request_queue *q; struct fstrim_range range; u64 minlen = ULLONG_MAX; u64 num_devices = 0; @@ -498,14 +497,11 @@ static noinline int btrfs_ioctl_fitrim(struct btrfs_fs_info *fs_info, rcu_read_lock(); list_for_each_entry_rcu(device, &fs_info->fs_devices->devices, dev_list) { - if (!device->bdev) + if (!device->bdev || !bdev_max_discard_sectors(device->bdev)) continue; - q = bdev_get_queue(device->bdev); - if (blk_queue_discard(q)) { - num_devices++; - minlen = min_t(u64, q->limits.discard_granularity, - minlen); - } + num_devices++; + minlen = min_t(u64, bdev_discard_granularity(device->bdev), + minlen); } rcu_read_unlock(); diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index a8cc736731fd..b6b00338037c 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -405,7 +405,6 @@ void btrfs_free_device(struct btrfs_device *device) WARN_ON(!list_empty(&device->post_commit_list)); rcu_string_free(device->name); extent_io_tree_release(&device->alloc_state); - bio_put(device->flush_bio); btrfs_destroy_dev_zone_info(device); kfree(device); } @@ -643,7 +642,7 @@ static int btrfs_open_one_device(struct btrfs_fs_devices *fs_devices, set_bit(BTRFS_DEV_STATE_WRITEABLE, &device->dev_state); } - if (!blk_queue_nonrot(bdev_get_queue(bdev))) + if (!bdev_nonrot(bdev)) fs_devices->rotating = true; device->bdev = bdev; @@ -2706,7 +2705,7 @@ int btrfs_init_new_device(struct btrfs_fs_info *fs_info, const char *device_path atomic64_add(device->total_bytes, &fs_info->free_chunk_space); - if (!blk_queue_nonrot(bdev_get_queue(bdev))) + if (!bdev_nonrot(bdev)) fs_devices->rotating = true; orig_super_total_bytes = btrfs_super_total_bytes(fs_info->super_copy); @@ -6949,16 +6948,6 @@ struct btrfs_device *btrfs_alloc_device(struct btrfs_fs_info *fs_info, if (!dev) return ERR_PTR(-ENOMEM); - /* - * Preallocate a bio that's always going to be used for flushing device - * barriers and matches the device lifespan - */ - dev->flush_bio = bio_kmalloc(GFP_KERNEL, 0); - if (!dev->flush_bio) { - kfree(dev); - return ERR_PTR(-ENOMEM); - } - INIT_LIST_HEAD(&dev->dev_list); INIT_LIST_HEAD(&dev->dev_alloc_list); INIT_LIST_HEAD(&dev->post_commit_list); diff --git a/fs/btrfs/volumes.h b/fs/btrfs/volumes.h index f3e28f11cfb6..b11c563d2025 100644 --- a/fs/btrfs/volumes.h +++ b/fs/btrfs/volumes.h @@ -121,8 +121,8 @@ struct btrfs_device { /* bytes used on the current transaction */ u64 commit_bytes_used; - /* for sending down flush barriers */ - struct bio *flush_bio; + /* Bio used for flushing device barriers */ + struct bio flush_bio; struct completion flush_wait; /* per-device scrub information */ diff --git a/fs/btrfs/zoned.c b/fs/btrfs/zoned.c index d31b0eda210f..29b54fd9c128 100644 --- a/fs/btrfs/zoned.c +++ b/fs/btrfs/zoned.c @@ -350,7 +350,6 @@ int btrfs_get_dev_zone_info(struct btrfs_device *device, bool populate_cache) struct btrfs_fs_info *fs_info = device->fs_info; struct btrfs_zoned_device_info *zone_info = NULL; struct block_device *bdev = device->bdev; - struct request_queue *queue = bdev_get_queue(bdev); unsigned int max_active_zones; unsigned int nactive; sector_t nr_sectors; @@ -410,7 +409,7 @@ int btrfs_get_dev_zone_info(struct btrfs_device *device, bool populate_cache) if (!IS_ALIGNED(nr_sectors, zone_sectors)) zone_info->nr_zones++; - max_active_zones = queue_max_active_zones(queue); + max_active_zones = bdev_max_active_zones(bdev); if (max_active_zones && max_active_zones < BTRFS_MIN_ACTIVE_ZONES) { btrfs_err_in_rcu(fs_info, "zoned: %s: max active zones %u is too small, need at least %u active zones", diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c index aa25bffd4823..b6edcf89a429 100644 --- a/fs/ceph/addr.c +++ b/fs/ceph/addr.c @@ -85,7 +85,7 @@ static bool ceph_dirty_folio(struct address_space *mapping, struct folio *folio) if (folio_test_dirty(folio)) { dout("%p dirty_folio %p idx %lu -- already dirty\n", mapping->host, folio, folio->index); - BUG_ON(!folio_get_private(folio)); + VM_BUG_ON_FOLIO(!folio_test_private(folio), folio); return false; } @@ -122,7 +122,7 @@ static bool ceph_dirty_folio(struct address_space *mapping, struct folio *folio) * Reference snap context in folio->private. Also set * PagePrivate so that we get invalidate_folio callback. */ - BUG_ON(folio_get_private(folio)); + VM_BUG_ON_FOLIO(folio_test_private(folio), folio); folio_attach_private(folio, snapc); return ceph_fscache_dirty_folio(mapping, folio); @@ -150,7 +150,7 @@ static void ceph_invalidate_folio(struct folio *folio, size_t offset, } WARN_ON(!folio_test_locked(folio)); - if (folio_get_private(folio)) { + if (folio_test_private(folio)) { dout("%p invalidate_folio idx %lu full dirty page\n", inode, folio->index); @@ -729,8 +729,11 @@ static void writepages_finish(struct ceph_osd_request *req) /* clean all pages */ for (i = 0; i < req->r_num_ops; i++) { - if (req->r_ops[i].op != CEPH_OSD_OP_WRITE) + if (req->r_ops[i].op != CEPH_OSD_OP_WRITE) { + pr_warn("%s incorrect op %d req %p index %d tid %llu\n", + __func__, req->r_ops[i].op, req, i, req->r_tid); break; + } osd_data = osd_req_op_extent_osd_data(req, i); BUG_ON(osd_data->type != CEPH_OSD_DATA_TYPE_PAGES); diff --git a/fs/ceph/file.c b/fs/ceph/file.c index 6c9e837aa1d3..8c8226c0feac 100644 --- a/fs/ceph/file.c +++ b/fs/ceph/file.c @@ -629,9 +629,15 @@ static int ceph_finish_async_create(struct inode *dir, struct dentry *dentry, iinfo.change_attr = 1; ceph_encode_timespec64(&iinfo.btime, &now); - iinfo.xattr_len = ARRAY_SIZE(xattr_buf); - iinfo.xattr_data = xattr_buf; - memset(iinfo.xattr_data, 0, iinfo.xattr_len); + if (req->r_pagelist) { + iinfo.xattr_len = req->r_pagelist->length; + iinfo.xattr_data = req->r_pagelist->mapped_tail; + } else { + /* fake it */ + iinfo.xattr_len = ARRAY_SIZE(xattr_buf); + iinfo.xattr_data = xattr_buf; + memset(iinfo.xattr_data, 0, iinfo.xattr_len); + } in.ino = cpu_to_le64(vino.ino); in.snapid = cpu_to_le64(CEPH_NOSNAP); @@ -743,6 +749,10 @@ int ceph_atomic_open(struct inode *dir, struct dentry *dentry, err = ceph_security_init_secctx(dentry, mode, &as_ctx); if (err < 0) goto out_ctx; + /* Async create can't handle more than a page of xattrs */ + if (as_ctx.pagelist && + !list_is_singular(&as_ctx.pagelist->head)) + try_async = false; } else if (!d_in_lookup(dentry)) { /* If it's not being looked up, it's negative */ return -ENOENT; diff --git a/fs/direct-io.c b/fs/direct-io.c index aef06e607b40..840752006f60 100644 --- a/fs/direct-io.c +++ b/fs/direct-io.c @@ -1115,11 +1115,10 @@ static inline int drop_refcount(struct dio *dio) * individual fields and will generate much worse code. This is important * for the whole file. */ -static inline ssize_t -do_blockdev_direct_IO(struct kiocb *iocb, struct inode *inode, - struct block_device *bdev, struct iov_iter *iter, - get_block_t get_block, dio_iodone_t end_io, - dio_submit_t submit_io, int flags) +ssize_t __blockdev_direct_IO(struct kiocb *iocb, struct inode *inode, + struct block_device *bdev, struct iov_iter *iter, + get_block_t get_block, dio_iodone_t end_io, + dio_submit_t submit_io, int flags) { unsigned i_blkbits = READ_ONCE(inode->i_blkbits); unsigned blkbits = i_blkbits; @@ -1334,29 +1333,6 @@ fail_dio: kmem_cache_free(dio_cache, dio); return retval; } - -ssize_t __blockdev_direct_IO(struct kiocb *iocb, struct inode *inode, - struct block_device *bdev, struct iov_iter *iter, - get_block_t get_block, - dio_iodone_t end_io, dio_submit_t submit_io, - int flags) -{ - /* - * The block device state is needed in the end to finally - * submit everything. Since it's likely to be cache cold - * prefetch it here as first thing to hide some of the - * latency. - * - * Attempt to prefetch the pieces we likely need later. - */ - prefetch(&bdev->bd_disk->part_tbl); - prefetch(bdev->bd_disk->queue); - prefetch((char *)bdev->bd_disk->queue + SMP_CACHE_BYTES); - - return do_blockdev_direct_IO(iocb, inode, bdev, iter, get_block, - end_io, submit_io, flags); -} - EXPORT_SYMBOL(__blockdev_direct_IO); static __init int dio_init(void) diff --git a/fs/exfat/file.c b/fs/exfat/file.c index 2f5130059236..20d4e47f57ab 100644 --- a/fs/exfat/file.c +++ b/fs/exfat/file.c @@ -351,21 +351,20 @@ out: static int exfat_ioctl_fitrim(struct inode *inode, unsigned long arg) { - struct request_queue *q = bdev_get_queue(inode->i_sb->s_bdev); struct fstrim_range range; int ret = 0; if (!capable(CAP_SYS_ADMIN)) return -EPERM; - if (!blk_queue_discard(q)) + if (!bdev_max_discard_sectors(inode->i_sb->s_bdev)) return -EOPNOTSUPP; if (copy_from_user(&range, (struct fstrim_range __user *)arg, sizeof(range))) return -EFAULT; range.minlen = max_t(unsigned int, range.minlen, - q->limits.discard_granularity); + bdev_discard_granularity(inode->i_sb->s_bdev)); ret = exfat_trim_fs(inode, &range); if (ret < 0) diff --git a/fs/exfat/super.c b/fs/exfat/super.c index 8ca21e7917d1..be0788ecaf20 100644 --- a/fs/exfat/super.c +++ b/fs/exfat/super.c @@ -627,13 +627,9 @@ static int exfat_fill_super(struct super_block *sb, struct fs_context *fc) if (opts->allow_utime == (unsigned short)-1) opts->allow_utime = ~opts->fs_dmask & 0022; - if (opts->discard) { - struct request_queue *q = bdev_get_queue(sb->s_bdev); - - if (!blk_queue_discard(q)) { - exfat_warn(sb, "mounting with \"discard\" option, but the device does not support discard"); - opts->discard = 0; - } + if (opts->discard && !bdev_max_discard_sectors(sb->s_bdev)) { + exfat_warn(sb, "mounting with \"discard\" option, but the device does not support discard"); + opts->discard = 0; } sb->s_flags |= SB_NODIRATIME; diff --git a/fs/ext4/ioctl.c b/fs/ext4/ioctl.c index ba44fa1be70a..4d1d2326eee9 100644 --- a/fs/ext4/ioctl.c +++ b/fs/ext4/ioctl.c @@ -1044,7 +1044,6 @@ static int ext4_ioctl_checkpoint(struct file *filp, unsigned long arg) __u32 flags = 0; unsigned int flush_flags = 0; struct super_block *sb = file_inode(filp)->i_sb; - struct request_queue *q; if (copy_from_user(&flags, (__u32 __user *)arg, sizeof(__u32))) @@ -1065,10 +1064,8 @@ static int ext4_ioctl_checkpoint(struct file *filp, unsigned long arg) if (flags & ~EXT4_IOC_CHECKPOINT_FLAG_VALID) return -EINVAL; - q = bdev_get_queue(EXT4_SB(sb)->s_journal->j_dev); - if (!q) - return -ENXIO; - if ((flags & JBD2_JOURNAL_FLUSH_DISCARD) && !blk_queue_discard(q)) + if ((flags & JBD2_JOURNAL_FLUSH_DISCARD) && + !bdev_max_discard_sectors(EXT4_SB(sb)->s_journal->j_dev)) return -EOPNOTSUPP; if (flags & EXT4_IOC_CHECKPOINT_FLAG_DRY_RUN) @@ -1393,14 +1390,13 @@ resizefs_out: case FITRIM: { - struct request_queue *q = bdev_get_queue(sb->s_bdev); struct fstrim_range range; int ret = 0; if (!capable(CAP_SYS_ADMIN)) return -EPERM; - if (!blk_queue_discard(q)) + if (!bdev_max_discard_sectors(sb->s_bdev)) return -EOPNOTSUPP; /* diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c index 252c168454c7..ea653d19f9ec 100644 --- a/fs/ext4/mballoc.c +++ b/fs/ext4/mballoc.c @@ -3498,7 +3498,7 @@ int ext4_mb_init(struct super_block *sb) spin_lock_init(&lg->lg_prealloc_lock); } - if (blk_queue_nonrot(bdev_get_queue(sb->s_bdev))) + if (bdev_nonrot(sb->s_bdev)) sbi->s_mb_max_linear_groups = 0; else sbi->s_mb_max_linear_groups = MB_DEFAULT_LINEAR_LIMIT; @@ -3629,7 +3629,7 @@ static inline int ext4_issue_discard(struct super_block *sb, return __blkdev_issue_discard(sb->s_bdev, (sector_t)discard_block << (sb->s_blocksize_bits - 9), (sector_t)count << (sb->s_blocksize_bits - 9), - GFP_NOFS, 0, biop); + GFP_NOFS, biop); } else return sb_issue_discard(sb, discard_block, count, GFP_NOFS, 0); } @@ -6455,7 +6455,7 @@ ext4_trim_all_free(struct super_block *sb, ext4_group_t group, */ int ext4_trim_fs(struct super_block *sb, struct fstrim_range *range) { - struct request_queue *q = bdev_get_queue(sb->s_bdev); + unsigned int discard_granularity = bdev_discard_granularity(sb->s_bdev); struct ext4_group_info *grp; ext4_group_t group, first_group, last_group; ext4_grpblk_t cnt = 0, first_cluster, last_cluster; @@ -6475,9 +6475,9 @@ int ext4_trim_fs(struct super_block *sb, struct fstrim_range *range) range->len < sb->s_blocksize) return -EINVAL; /* No point to try to trim less than discard granularity */ - if (range->minlen < q->limits.discard_granularity) { + if (range->minlen < discard_granularity) { minlen = EXT4_NUM_B2C(EXT4_SB(sb), - q->limits.discard_granularity >> sb->s_blocksize_bits); + discard_granularity >> sb->s_blocksize_bits); if (minlen > EXT4_CLUSTERS_PER_GROUP(sb)) goto out; } diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 1466fbdbc8e3..6900da973ce2 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -5474,13 +5474,9 @@ no_journal: goto failed_mount9; } - if (test_opt(sb, DISCARD)) { - struct request_queue *q = bdev_get_queue(sb->s_bdev); - if (!blk_queue_discard(q)) - ext4_msg(sb, KERN_WARNING, - "mounting with \"discard\" option, but " - "the device does not support discard"); - } + if (test_opt(sb, DISCARD) && !bdev_max_discard_sectors(sb->s_bdev)) + ext4_msg(sb, KERN_WARNING, + "mounting with \"discard\" option, but the device does not support discard"); if (es->s_error_count) mod_timer(&sbi->s_err_report, jiffies + 300*HZ); /* 5 minutes */ diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h index 8c570de21ed5..2b2b3c87e45e 100644 --- a/fs/f2fs/f2fs.h +++ b/fs/f2fs/f2fs.h @@ -4372,8 +4372,7 @@ static inline bool f2fs_hw_should_discard(struct f2fs_sb_info *sbi) static inline bool f2fs_bdev_support_discard(struct block_device *bdev) { - return blk_queue_discard(bdev_get_queue(bdev)) || - bdev_is_zoned(bdev); + return bdev_max_discard_sectors(bdev) || bdev_is_zoned(bdev); } static inline bool f2fs_hw_support_discard(struct f2fs_sb_info *sbi) diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c index 5b89af0f27f0..35b6c720c2bc 100644 --- a/fs/f2fs/file.c +++ b/fs/f2fs/file.c @@ -2285,7 +2285,6 @@ static int f2fs_ioc_fitrim(struct file *filp, unsigned long arg) { struct inode *inode = file_inode(filp); struct super_block *sb = inode->i_sb; - struct request_queue *q = bdev_get_queue(sb->s_bdev); struct fstrim_range range; int ret; @@ -2304,7 +2303,7 @@ static int f2fs_ioc_fitrim(struct file *filp, unsigned long arg) return ret; range.minlen = max((unsigned int)range.minlen, - q->limits.discard_granularity); + bdev_discard_granularity(sb->s_bdev)); ret = f2fs_trim_fs(F2FS_SB(sb), &range); mnt_drop_write_file(filp); if (ret < 0) @@ -3686,18 +3685,18 @@ out: static int f2fs_secure_erase(struct block_device *bdev, struct inode *inode, pgoff_t off, block_t block, block_t len, u32 flags) { - struct request_queue *q = bdev_get_queue(bdev); sector_t sector = SECTOR_FROM_BLOCK(block); sector_t nr_sects = SECTOR_FROM_BLOCK(len); int ret = 0; - if (!q) - return -ENXIO; - - if (flags & F2FS_TRIM_FILE_DISCARD) - ret = blkdev_issue_discard(bdev, sector, nr_sects, GFP_NOFS, - blk_queue_secure_erase(q) ? - BLKDEV_DISCARD_SECURE : 0); + if (flags & F2FS_TRIM_FILE_DISCARD) { + if (bdev_max_secure_erase_sectors(bdev)) + ret = blkdev_issue_secure_erase(bdev, sector, nr_sects, + GFP_NOFS); + else + ret = blkdev_issue_discard(bdev, sector, nr_sects, + GFP_NOFS); + } if (!ret && (flags & F2FS_TRIM_FILE_ZEROOUT)) { if (IS_ENCRYPTED(inode)) diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c index bd9731cdec56..7225ce09f3ab 100644 --- a/fs/f2fs/segment.c +++ b/fs/f2fs/segment.c @@ -1196,9 +1196,8 @@ static int __submit_discard_cmd(struct f2fs_sb_info *sbi, unsigned int *issued) { struct block_device *bdev = dc->bdev; - struct request_queue *q = bdev_get_queue(bdev); unsigned int max_discard_blocks = - SECTOR_TO_BLOCK(q->limits.max_discard_sectors); + SECTOR_TO_BLOCK(bdev_max_discard_sectors(bdev)); struct discard_cmd_control *dcc = SM_I(sbi)->dcc_info; struct list_head *wait_list = (dpolicy->type == DPOLICY_FSTRIM) ? &(dcc->fstrim_list) : &(dcc->wait_list); @@ -1245,7 +1244,7 @@ static int __submit_discard_cmd(struct f2fs_sb_info *sbi, err = __blkdev_issue_discard(bdev, SECTOR_FROM_BLOCK(start), SECTOR_FROM_BLOCK(len), - GFP_NOFS, 0, &bio); + GFP_NOFS, &bio); submit: if (err) { spin_lock_irqsave(&dc->lock, flags); @@ -1375,9 +1374,8 @@ static void __update_discard_tree_range(struct f2fs_sb_info *sbi, struct discard_cmd *dc; struct discard_info di = {0}; struct rb_node **insert_p = NULL, *insert_parent = NULL; - struct request_queue *q = bdev_get_queue(bdev); unsigned int max_discard_blocks = - SECTOR_TO_BLOCK(q->limits.max_discard_sectors); + SECTOR_TO_BLOCK(bdev_max_discard_sectors(bdev)); block_t end = lstart + len; dc = (struct discard_cmd *)f2fs_lookup_rb_tree_ret(&dcc->root, diff --git a/fs/fat/file.c b/fs/fat/file.c index a5a309fcc7fa..bf91f977debe 100644 --- a/fs/fat/file.c +++ b/fs/fat/file.c @@ -127,13 +127,12 @@ static int fat_ioctl_fitrim(struct inode *inode, unsigned long arg) struct super_block *sb = inode->i_sb; struct fstrim_range __user *user_range; struct fstrim_range range; - struct request_queue *q = bdev_get_queue(sb->s_bdev); int err; if (!capable(CAP_SYS_ADMIN)) return -EPERM; - if (!blk_queue_discard(q)) + if (!bdev_max_discard_sectors(sb->s_bdev)) return -EOPNOTSUPP; user_range = (struct fstrim_range __user *)arg; @@ -141,7 +140,7 @@ static int fat_ioctl_fitrim(struct inode *inode, unsigned long arg) return -EFAULT; range.minlen = max_t(unsigned int, range.minlen, - q->limits.discard_granularity); + bdev_discard_granularity(sb->s_bdev)); err = fat_trim_fs(inode, &range); if (err < 0) diff --git a/fs/fat/inode.c b/fs/fat/inode.c index bf6051bdf1d1..3d1afb95a925 100644 --- a/fs/fat/inode.c +++ b/fs/fat/inode.c @@ -1872,13 +1872,9 @@ int fat_fill_super(struct super_block *sb, void *data, int silent, int isvfat, goto out_fail; } - if (sbi->options.discard) { - struct request_queue *q = bdev_get_queue(sb->s_bdev); - if (!blk_queue_discard(q)) - fat_msg(sb, KERN_WARNING, - "mounting with \"discard\" option, but " - "the device does not support discard"); - } + if (sbi->options.discard && !bdev_max_discard_sectors(sb->s_bdev)) + fat_msg(sb, KERN_WARNING, + "mounting with \"discard\" option, but the device does not support discard"); fat_set_state(sb, 1, 0); return 0; diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c index 591fe9cf1659..a1074a26e784 100644 --- a/fs/fs-writeback.c +++ b/fs/fs-writeback.c @@ -1712,6 +1712,10 @@ static int writeback_single_inode(struct inode *inode, */ if (!(inode->i_state & I_DIRTY_ALL)) inode_cgwb_move_to_attached(inode, wb); + else if (!(inode->i_state & I_SYNC_QUEUED) && + (inode->i_state & I_DIRTY)) + redirty_tail_locked(inode, wb); + spin_unlock(&wb->list_lock); inode_sync_complete(inode); out: @@ -1775,11 +1779,12 @@ static long writeback_sb_inodes(struct super_block *sb, }; unsigned long start_time = jiffies; long write_chunk; - long wrote = 0; /* count both pages and inodes */ + long total_wrote = 0; /* count both pages and inodes */ while (!list_empty(&wb->b_io)) { struct inode *inode = wb_inode(wb->b_io.prev); struct bdi_writeback *tmp_wb; + long wrote; if (inode->i_sb != sb) { if (work->sb) { @@ -1855,7 +1860,9 @@ static long writeback_sb_inodes(struct super_block *sb, wbc_detach_inode(&wbc); work->nr_pages -= write_chunk - wbc.nr_to_write; - wrote += write_chunk - wbc.nr_to_write; + wrote = write_chunk - wbc.nr_to_write - wbc.pages_skipped; + wrote = wrote < 0 ? 0 : wrote; + total_wrote += wrote; if (need_resched()) { /* @@ -1877,7 +1884,7 @@ static long writeback_sb_inodes(struct super_block *sb, tmp_wb = inode_to_wb_and_lock_list(inode); spin_lock(&inode->i_lock); if (!(inode->i_state & I_DIRTY_ALL)) - wrote++; + total_wrote++; requeue_inode(inode, tmp_wb, &wbc); inode_sync_complete(inode); spin_unlock(&inode->i_lock); @@ -1891,14 +1898,14 @@ static long writeback_sb_inodes(struct super_block *sb, * bail out to wb_writeback() often enough to check * background threshold and other termination conditions. */ - if (wrote) { + if (total_wrote) { if (time_is_before_jiffies(start_time + HZ / 10UL)) break; if (work->nr_pages <= 0) break; } } - return wrote; + return total_wrote; } static long __writeback_inodes_wb(struct bdi_writeback *wb, diff --git a/fs/gfs2/bmap.c b/fs/gfs2/bmap.c index 39080b2d6cf8..b6697333bb2b 100644 --- a/fs/gfs2/bmap.c +++ b/fs/gfs2/bmap.c @@ -1153,13 +1153,12 @@ static int gfs2_iomap_end(struct inode *inode, loff_t pos, loff_t length, if (length != written && (iomap->flags & IOMAP_F_NEW)) { /* Deallocate blocks that were just allocated. */ - loff_t blockmask = i_blocksize(inode) - 1; - loff_t end = (pos + length) & ~blockmask; + loff_t hstart = round_up(pos + written, i_blocksize(inode)); + loff_t hend = iomap->offset + iomap->length; - pos = (pos + written + blockmask) & ~blockmask; - if (pos < end) { - truncate_pagecache_range(inode, pos, end - 1); - punch_hole(ip, pos, end - pos); + if (hstart < hend) { + truncate_pagecache_range(inode, hstart, hend - 1); + punch_hole(ip, hstart, hend - hstart); } } diff --git a/fs/gfs2/file.c b/fs/gfs2/file.c index 48f01323c37c..2556ae1f92ea 100644 --- a/fs/gfs2/file.c +++ b/fs/gfs2/file.c @@ -770,30 +770,27 @@ static int gfs2_fsync(struct file *file, loff_t start, loff_t end, return ret ? ret : ret1; } -static inline bool should_fault_in_pages(ssize_t ret, struct iov_iter *i, +static inline bool should_fault_in_pages(struct iov_iter *i, + struct kiocb *iocb, size_t *prev_count, size_t *window_size) { size_t count = iov_iter_count(i); size_t size, offs; - if (likely(!count)) - return false; - if (ret <= 0 && ret != -EFAULT) + if (!count) return false; if (!iter_is_iovec(i)) return false; size = PAGE_SIZE; - offs = offset_in_page(i->iov[0].iov_base + i->iov_offset); + offs = offset_in_page(iocb->ki_pos); if (*prev_count != count || !*window_size) { size_t nr_dirtied; - size = ALIGN(offs + count, PAGE_SIZE); - size = min_t(size_t, size, SZ_1M); nr_dirtied = max(current->nr_dirtied_pause - current->nr_dirtied, 8); - size = min(size, nr_dirtied << PAGE_SHIFT); + size = min_t(size_t, SZ_1M, nr_dirtied << PAGE_SHIFT); } *prev_count = count; @@ -807,7 +804,7 @@ static ssize_t gfs2_file_direct_read(struct kiocb *iocb, struct iov_iter *to, struct file *file = iocb->ki_filp; struct gfs2_inode *ip = GFS2_I(file->f_mapping->host); size_t prev_count = 0, window_size = 0; - size_t written = 0; + size_t read = 0; ssize_t ret; /* @@ -835,35 +832,31 @@ retry: ret = gfs2_glock_nq(gh); if (ret) goto out_uninit; -retry_under_glock: pagefault_disable(); to->nofault = true; ret = iomap_dio_rw(iocb, to, &gfs2_iomap_ops, NULL, - IOMAP_DIO_PARTIAL, written); + IOMAP_DIO_PARTIAL, read); to->nofault = false; pagefault_enable(); + if (ret <= 0 && ret != -EFAULT) + goto out_unlock; if (ret > 0) - written = ret; - - if (should_fault_in_pages(ret, to, &prev_count, &window_size)) { - size_t leftover; + read = ret; - gfs2_holder_allow_demote(gh); - leftover = fault_in_iov_iter_writeable(to, window_size); - gfs2_holder_disallow_demote(gh); - if (leftover != window_size) { - if (gfs2_holder_queued(gh)) - goto retry_under_glock; + if (should_fault_in_pages(to, iocb, &prev_count, &window_size)) { + gfs2_glock_dq(gh); + window_size -= fault_in_iov_iter_writeable(to, window_size); + if (window_size) goto retry; - } } +out_unlock: if (gfs2_holder_queued(gh)) gfs2_glock_dq(gh); out_uninit: gfs2_holder_uninit(gh); if (ret < 0) return ret; - return written; + return read; } static ssize_t gfs2_file_direct_write(struct kiocb *iocb, struct iov_iter *from, @@ -873,7 +866,7 @@ static ssize_t gfs2_file_direct_write(struct kiocb *iocb, struct iov_iter *from, struct inode *inode = file->f_mapping->host; struct gfs2_inode *ip = GFS2_I(inode); size_t prev_count = 0, window_size = 0; - size_t read = 0; + size_t written = 0; ssize_t ret; /* @@ -901,39 +894,35 @@ retry: goto out_uninit; /* Silently fall back to buffered I/O when writing beyond EOF */ if (iocb->ki_pos + iov_iter_count(from) > i_size_read(&ip->i_inode)) - goto out; -retry_under_glock: + goto out_unlock; from->nofault = true; ret = iomap_dio_rw(iocb, from, &gfs2_iomap_ops, NULL, - IOMAP_DIO_PARTIAL, read); + IOMAP_DIO_PARTIAL, written); from->nofault = false; - - if (ret == -ENOTBLK) - ret = 0; + if (ret <= 0) { + if (ret == -ENOTBLK) + ret = 0; + if (ret != -EFAULT) + goto out_unlock; + } if (ret > 0) - read = ret; - - if (should_fault_in_pages(ret, from, &prev_count, &window_size)) { - size_t leftover; + written = ret; - gfs2_holder_allow_demote(gh); - leftover = fault_in_iov_iter_readable(from, window_size); - gfs2_holder_disallow_demote(gh); - if (leftover != window_size) { - if (gfs2_holder_queued(gh)) - goto retry_under_glock; + if (should_fault_in_pages(from, iocb, &prev_count, &window_size)) { + gfs2_glock_dq(gh); + window_size -= fault_in_iov_iter_readable(from, window_size); + if (window_size) goto retry; - } } -out: +out_unlock: if (gfs2_holder_queued(gh)) gfs2_glock_dq(gh); out_uninit: gfs2_holder_uninit(gh); if (ret < 0) return ret; - return read; + return written; } static ssize_t gfs2_file_read_iter(struct kiocb *iocb, struct iov_iter *to) @@ -941,7 +930,7 @@ static ssize_t gfs2_file_read_iter(struct kiocb *iocb, struct iov_iter *to) struct gfs2_inode *ip; struct gfs2_holder gh; size_t prev_count = 0, window_size = 0; - size_t written = 0; + size_t read = 0; ssize_t ret; /* @@ -962,7 +951,7 @@ static ssize_t gfs2_file_read_iter(struct kiocb *iocb, struct iov_iter *to) if (ret >= 0) { if (!iov_iter_count(to)) return ret; - written = ret; + read = ret; } else if (ret != -EFAULT) { if (ret != -EAGAIN) return ret; @@ -975,30 +964,26 @@ retry: ret = gfs2_glock_nq(&gh); if (ret) goto out_uninit; -retry_under_glock: pagefault_disable(); ret = generic_file_read_iter(iocb, to); pagefault_enable(); + if (ret <= 0 && ret != -EFAULT) + goto out_unlock; if (ret > 0) - written += ret; - - if (should_fault_in_pages(ret, to, &prev_count, &window_size)) { - size_t leftover; + read += ret; - gfs2_holder_allow_demote(&gh); - leftover = fault_in_iov_iter_writeable(to, window_size); - gfs2_holder_disallow_demote(&gh); - if (leftover != window_size) { - if (gfs2_holder_queued(&gh)) - goto retry_under_glock; + if (should_fault_in_pages(to, iocb, &prev_count, &window_size)) { + gfs2_glock_dq(&gh); + window_size -= fault_in_iov_iter_writeable(to, window_size); + if (window_size) goto retry; - } } +out_unlock: if (gfs2_holder_queued(&gh)) gfs2_glock_dq(&gh); out_uninit: gfs2_holder_uninit(&gh); - return written ? written : ret; + return read ? read : ret; } static ssize_t gfs2_file_buffered_write(struct kiocb *iocb, @@ -1012,7 +997,7 @@ static ssize_t gfs2_file_buffered_write(struct kiocb *iocb, struct gfs2_holder *statfs_gh = NULL; size_t prev_count = 0, window_size = 0; size_t orig_count = iov_iter_count(from); - size_t read = 0; + size_t written = 0; ssize_t ret; /* @@ -1030,10 +1015,18 @@ static ssize_t gfs2_file_buffered_write(struct kiocb *iocb, gfs2_holder_init(ip->i_gl, LM_ST_EXCLUSIVE, 0, gh); retry: + if (should_fault_in_pages(from, iocb, &prev_count, &window_size)) { + window_size -= fault_in_iov_iter_readable(from, window_size); + if (!window_size) { + ret = -EFAULT; + goto out_uninit; + } + from->count = min(from->count, window_size); + } ret = gfs2_glock_nq(gh); if (ret) goto out_uninit; -retry_under_glock: + if (inode == sdp->sd_rindex) { struct gfs2_inode *m_ip = GFS2_I(sdp->sd_statfs_inode); @@ -1050,25 +1043,19 @@ retry_under_glock: current->backing_dev_info = NULL; if (ret > 0) { iocb->ki_pos += ret; - read += ret; + written += ret; } if (inode == sdp->sd_rindex) gfs2_glock_dq_uninit(statfs_gh); - from->count = orig_count - read; - if (should_fault_in_pages(ret, from, &prev_count, &window_size)) { - size_t leftover; - - gfs2_holder_allow_demote(gh); - leftover = fault_in_iov_iter_readable(from, window_size); - gfs2_holder_disallow_demote(gh); - if (leftover != window_size) { - from->count = min(from->count, window_size - leftover); - if (gfs2_holder_queued(gh)) - goto retry_under_glock; - goto retry; - } + if (ret <= 0 && ret != -EFAULT) + goto out_unlock; + + from->count = orig_count - written; + if (should_fault_in_pages(from, iocb, &prev_count, &window_size)) { + gfs2_glock_dq(gh); + goto retry; } out_unlock: if (gfs2_holder_queued(gh)) @@ -1077,8 +1064,8 @@ out_uninit: gfs2_holder_uninit(gh); if (statfs_gh) kfree(statfs_gh); - from->count = orig_count - read; - return read ? read : ret; + from->count = orig_count - written; + return written ? written : ret; } /** diff --git a/fs/gfs2/rgrp.c b/fs/gfs2/rgrp.c index 801ad9f4f2be..6d26bb525484 100644 --- a/fs/gfs2/rgrp.c +++ b/fs/gfs2/rgrp.c @@ -1386,7 +1386,7 @@ int gfs2_fitrim(struct file *filp, void __user *argp) { struct inode *inode = file_inode(filp); struct gfs2_sbd *sdp = GFS2_SB(inode); - struct request_queue *q = bdev_get_queue(sdp->sd_vfs->s_bdev); + struct block_device *bdev = sdp->sd_vfs->s_bdev; struct buffer_head *bh; struct gfs2_rgrpd *rgd; struct gfs2_rgrpd *rgd_end; @@ -1405,7 +1405,7 @@ int gfs2_fitrim(struct file *filp, void __user *argp) if (!test_bit(SDF_JOURNAL_LIVE, &sdp->sd_flags)) return -EROFS; - if (!blk_queue_discard(q)) + if (!bdev_max_discard_sectors(bdev)) return -EOPNOTSUPP; if (copy_from_user(&r, argp, sizeof(r))) @@ -1418,8 +1418,7 @@ int gfs2_fitrim(struct file *filp, void __user *argp) start = r.start >> bs_shift; end = start + (r.len >> bs_shift); minlen = max_t(u64, r.minlen, sdp->sd_sb.sb_bsize); - minlen = max_t(u64, minlen, - q->limits.discard_granularity) >> bs_shift; + minlen = max_t(u64, minlen, bdev_discard_granularity(bdev)) >> bs_shift; if (end <= start || minlen > sdp->sd_max_rg_data) return -EINVAL; diff --git a/fs/internal.h b/fs/internal.h index 08503dc68d2b..9a6c233ee7f1 100644 --- a/fs/internal.h +++ b/fs/internal.h @@ -191,3 +191,32 @@ long splice_file_to_pipe(struct file *in, struct pipe_inode_info *opipe, loff_t *offset, size_t len, unsigned int flags); + +/* + * fs/xattr.c: + */ +struct xattr_name { + char name[XATTR_NAME_MAX + 1]; +}; + +struct xattr_ctx { + /* Value of attribute */ + union { + const void __user *cvalue; + void __user *value; + }; + void *kvalue; + size_t size; + /* Attribute name */ + struct xattr_name *kname; + unsigned int flags; +}; + + +ssize_t do_getxattr(struct user_namespace *mnt_userns, + struct dentry *d, + struct xattr_ctx *ctx); + +int setxattr_copy(const char __user *name, struct xattr_ctx *ctx); +int do_setxattr(struct user_namespace *mnt_userns, struct dentry *dentry, + struct xattr_ctx *ctx); diff --git a/fs/io-wq.c b/fs/io-wq.c index 32aeb2c581c5..824623bcf1a5 100644 --- a/fs/io-wq.c +++ b/fs/io-wq.c @@ -871,7 +871,7 @@ static bool io_wq_for_each_worker(struct io_wqe *wqe, static bool io_wq_worker_wake(struct io_worker *worker, void *data) { - set_notify_signal(worker->task); + __set_notify_signal(worker->task); wake_up_process(worker->task); return false; } @@ -991,7 +991,7 @@ static bool __io_wq_worker_cancel(struct io_worker *worker, { if (work && match->fn(work, match->data)) { work->flags |= IO_WQ_WORK_CANCEL; - set_notify_signal(worker->task); + __set_notify_signal(worker->task); return true; } diff --git a/fs/io-wq.h b/fs/io-wq.h index dbecd27656c7..ba6eee76d028 100644 --- a/fs/io-wq.h +++ b/fs/io-wq.h @@ -155,6 +155,7 @@ struct io_wq_work_node *wq_stack_extract(struct io_wq_work_node *stack) struct io_wq_work { struct io_wq_work_node list; unsigned flags; + int cancel_seq; }; static inline struct io_wq_work *wq_next_work(struct io_wq_work *work) diff --git a/fs/io_uring.c b/fs/io_uring.c index 91de361ea9ab..9f1c682d7caf 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -80,6 +80,7 @@ #include <linux/io_uring.h> #include <linux/audit.h> #include <linux/security.h> +#include <linux/xattr.h> #define CREATE_TRACE_POINTS #include <trace/events/io_uring.h> @@ -94,7 +95,7 @@ #define IORING_SQPOLL_CAP_ENTRIES_VALUE 8 /* only define max */ -#define IORING_MAX_FIXED_FILES (1U << 15) +#define IORING_MAX_FIXED_FILES (1U << 20) #define IORING_MAX_RESTRICTIONS (IORING_RESTRICTION_LAST + \ IORING_REGISTER_LAST + IORING_OP_LAST) @@ -113,6 +114,11 @@ #define IO_REQ_CLEAN_FLAGS (REQ_F_BUFFER_SELECTED | REQ_F_NEED_CLEANUP | \ REQ_F_POLLED | REQ_F_CREDS | REQ_F_ASYNC_DATA) +#define IO_REQ_CLEAN_SLOW_FLAGS (REQ_F_REFCOUNT | REQ_F_LINK | REQ_F_HARDLINK |\ + IO_REQ_CLEAN_FLAGS) + +#define IO_APOLL_MULTI_POLLED (REQ_F_APOLL_MULTISHOT | REQ_F_POLLED) + #define IO_TCTX_REFS_CACHE_NR (1U << 10) struct io_uring { @@ -166,7 +172,7 @@ struct io_rings { * The application needs a full memory barrier before checking * for IORING_SQ_NEED_WAKEUP after updating the sq tail. */ - u32 sq_flags; + atomic_t sq_flags; /* * Runtime CQ flags * @@ -198,13 +204,6 @@ struct io_rings { struct io_uring_cqe cqes[] ____cacheline_aligned_in_smp; }; -enum io_uring_cmd_flags { - IO_URING_F_COMPLETE_DEFER = 1, - IO_URING_F_UNLOCKED = 2, - /* int's last bit, sign checks are usually faster than a bit test */ - IO_URING_F_NONBLOCK = INT_MIN, -}; - struct io_mapped_ubuf { u64 ubuf; u64 ubuf_end; @@ -216,10 +215,27 @@ struct io_mapped_ubuf { struct io_ring_ctx; struct io_overflow_cqe { - struct io_uring_cqe cqe; struct list_head list; + struct io_uring_cqe cqe; }; +/* + * FFS_SCM is only available on 64-bit archs, for 32-bit we just define it as 0 + * and define IO_URING_SCM_ALL. For this case, we use SCM for all files as we + * can't safely always dereference the file when the task has exited and ring + * cleanup is done. If a file is tracked and part of SCM, then unix gc on + * process exit may reap it before __io_sqe_files_unregister() is run. + */ +#define FFS_NOWAIT 0x1UL +#define FFS_ISREG 0x2UL +#if defined(CONFIG_64BIT) +#define FFS_SCM 0x4UL +#else +#define IO_URING_SCM_ALL +#define FFS_SCM 0x0UL +#endif +#define FFS_MASK ~(FFS_NOWAIT|FFS_ISREG|FFS_SCM) + struct io_fixed_file { /* file * with additional FFS_* flags */ unsigned long file_ptr; @@ -237,6 +253,8 @@ struct io_rsrc_put { struct io_file_table { struct io_fixed_file *files; + unsigned long *bitmap; + unsigned int alloc_hint; }; struct io_rsrc_node { @@ -261,10 +279,26 @@ struct io_rsrc_data { bool quiesce; }; +#define IO_BUFFER_LIST_BUF_PER_PAGE (PAGE_SIZE / sizeof(struct io_uring_buf)) struct io_buffer_list { - struct list_head list; - struct list_head buf_list; + /* + * If ->buf_nr_pages is set, then buf_pages/buf_ring are used. If not, + * then these are classic provided buffers and ->buf_list is used. + */ + union { + struct list_head buf_list; + struct { + struct page **buf_pages; + struct io_uring_buf_ring *buf_ring; + }; + }; __u16 bgid; + + /* below is for ring provided buffers */ + __u16 buf_nr_pages; + __u16 nr_entries; + __u32 head; + __u32 mask; }; struct io_buffer { @@ -337,7 +371,7 @@ struct io_ev_fd { struct rcu_head rcu; }; -#define IO_BUFFERS_HASH_BITS 5 +#define BGID_ARRAY 64 struct io_ring_ctx { /* const or read-mostly hot data */ @@ -346,6 +380,7 @@ struct io_ring_ctx { struct io_rings *rings; unsigned int flags; + enum task_work_notify_mode notify_method; unsigned int compat: 1; unsigned int drain_next: 1; unsigned int restricted: 1; @@ -353,6 +388,7 @@ struct io_ring_ctx { unsigned int drain_active: 1; unsigned int drain_disabled: 1; unsigned int has_evfd: 1; + unsigned int syscall_iopoll: 1; } ____cacheline_aligned_in_smp; /* submission data */ @@ -382,17 +418,21 @@ struct io_ring_ctx { */ struct io_rsrc_node *rsrc_node; int rsrc_cached_refs; + atomic_t cancel_seq; struct io_file_table file_table; unsigned nr_user_files; unsigned nr_user_bufs; struct io_mapped_ubuf **user_bufs; struct io_submit_state submit_state; + + struct io_buffer_list *io_bl; + struct xarray io_bl_xa; + struct list_head io_buffers_cache; + struct list_head timeout_list; struct list_head ltimeout_list; struct list_head cq_overflow_list; - struct list_head *io_buffers; - struct list_head io_buffers_cache; struct list_head apoll_cache; struct xarray personalities; u32 pers_next; @@ -409,9 +449,16 @@ struct io_ring_ctx { struct wait_queue_head sqo_sq_wait; struct list_head sqd_list; - unsigned long check_cq_overflow; + unsigned long check_cq; struct { + /* + * We cache a range of free CQEs we can use, once exhausted it + * should go through a slower range setup, see __io_get_cqe() + */ + struct io_uring_cqe *cqe_cached; + struct io_uring_cqe *cqe_sentinel; + unsigned cached_cq_tail; unsigned cq_entries; struct io_ev_fd __rcu *io_ev_fd; @@ -497,7 +544,7 @@ struct io_uring_task { spinlock_t task_lock; struct io_wq_work_list task_list; - struct io_wq_work_list prior_task_list; + struct io_wq_work_list prio_task_list; struct callback_head task_work; struct file **registered_rings; bool task_running; @@ -546,6 +593,16 @@ struct io_accept { unsigned long nofile; }; +struct io_socket { + struct file *file; + int domain; + int type; + int protocol; + int flags; + u32 file_slot; + unsigned long nofile; +}; + struct io_sync { struct file *file; loff_t len; @@ -557,6 +614,8 @@ struct io_sync { struct io_cancel { struct file *file; u64 addr; + u32 flags; + s32 fd; }; struct io_timeout { @@ -585,7 +644,7 @@ struct io_rw { struct kiocb kiocb; u64 addr; u32 len; - u32 flags; + rwf_t flags; }; struct io_connect { @@ -602,9 +661,9 @@ struct io_sr_msg { void __user *buf; }; int msg_flags; - int bgid; size_t len; size_t done_io; + unsigned int flags; }; struct io_open { @@ -722,6 +781,12 @@ struct io_msg { u32 len; }; +struct io_nop { + struct file *file; + u64 extra1; + u64 extra2; +}; + struct io_async_connect { struct sockaddr_storage address; }; @@ -748,6 +813,12 @@ struct io_async_rw { struct wait_page_queue wpq; }; +struct io_xattr { + struct file *file; + struct xattr_ctx ctx; + struct filename *filename; +}; + enum { REQ_F_FIXED_FILE_BIT = IOSQE_FIXED_FILE_BIT, REQ_F_IO_DRAIN_BIT = IOSQE_IO_DRAIN_BIT, @@ -766,6 +837,7 @@ enum { REQ_F_NEED_CLEANUP_BIT, REQ_F_POLLED_BIT, REQ_F_BUFFER_SELECTED_BIT, + REQ_F_BUFFER_RING_BIT, REQ_F_COMPLETE_INLINE_BIT, REQ_F_REISSUE_BIT, REQ_F_CREDS_BIT, @@ -776,6 +848,7 @@ enum { REQ_F_SINGLE_POLL_BIT, REQ_F_DOUBLE_POLL_BIT, REQ_F_PARTIAL_IO_BIT, + REQ_F_APOLL_MULTISHOT_BIT, /* keep async read/write and isreg together and in order */ REQ_F_SUPPORT_NOWAIT_BIT, REQ_F_ISREG_BIT, @@ -816,6 +889,8 @@ enum { REQ_F_POLLED = BIT(REQ_F_POLLED_BIT), /* buffer already selected */ REQ_F_BUFFER_SELECTED = BIT(REQ_F_BUFFER_SELECTED_BIT), + /* buffer selected from ring, needs commit */ + REQ_F_BUFFER_RING = BIT(REQ_F_BUFFER_RING_BIT), /* completion is deferred through io_comp_state */ REQ_F_COMPLETE_INLINE = BIT(REQ_F_COMPLETE_INLINE_BIT), /* caller should reissue async */ @@ -840,6 +915,8 @@ enum { REQ_F_DOUBLE_POLL = BIT(REQ_F_DOUBLE_POLL_BIT), /* request has already done partial IO */ REQ_F_PARTIAL_IO = BIT(REQ_F_PARTIAL_IO_BIT), + /* fast poll multishot mode */ + REQ_F_APOLL_MULTISHOT = BIT(REQ_F_APOLL_MULTISHOT_BIT), }; struct async_poll { @@ -862,6 +939,21 @@ enum { IORING_RSRC_BUFFER = 1, }; +struct io_cqe { + __u64 user_data; + __s32 res; + /* fd initially, then cflags for completion */ + union { + __u32 flags; + int fd; + }; +}; + +enum { + IO_CHECK_CQ_OVERFLOW_BIT, + IO_CHECK_CQ_DROPPED_BIT, +}; + /* * NOTE! Each of the iocb union members has the file pointer * as the first entry in their struct definition. So you can @@ -897,46 +989,65 @@ struct io_kiocb { struct io_symlink symlink; struct io_hardlink hardlink; struct io_msg msg; + struct io_xattr xattr; + struct io_socket sock; + struct io_nop nop; + struct io_uring_cmd uring_cmd; }; u8 opcode; /* polled IO has completed */ u8 iopoll_completed; + /* + * Can be either a fixed buffer index, or used with provided buffers. + * For the latter, before issue it points to the buffer group ID, + * and after selection it points to the buffer ID itself. + */ u16 buf_index; unsigned int flags; - u64 user_data; - u32 result; - /* fd initially, then cflags for completion */ - union { - u32 cflags; - int fd; - }; + struct io_cqe cqe; struct io_ring_ctx *ctx; struct task_struct *task; - struct percpu_ref *fixed_rsrc_refs; - /* store used ubuf, so we can prevent reloading */ - struct io_mapped_ubuf *imu; + struct io_rsrc_node *rsrc_node; + + union { + /* store used ubuf, so we can prevent reloading */ + struct io_mapped_ubuf *imu; + + /* stores selected buf, valid IFF REQ_F_BUFFER_SELECTED is set */ + struct io_buffer *kbuf; + + /* + * stores buffer ID for ring provided buffers, valid IFF + * REQ_F_BUFFER_RING is set. + */ + struct io_buffer_list *buf_list; + }; union { /* used by request caches, completion batching and iopoll */ struct io_wq_work_node comp_list; /* cache ->apoll->events */ - int apoll_events; + __poll_t apoll_events; }; atomic_t refs; atomic_t poll_refs; struct io_task_work io_task_work; /* for polled requests, i.e. IORING_OP_POLL_ADD and async armed poll */ - struct hlist_node hash_node; + union { + struct hlist_node hash_node; + struct { + u64 extra1; + u64 extra2; + }; + }; /* internal polling, see IORING_FEAT_FAST_POLL */ struct async_poll *apoll; /* opcode allocated if it needs to store data for async defer */ void *async_data; - /* stores selected buf, valid IFF REQ_F_BUFFER_SELECTED is set */ - struct io_buffer *kbuf; /* linked requests, IFF REQ_F_HARDLINK or REQ_F_LINK are set */ struct io_kiocb *link; /* custom credentials, valid IFF REQ_F_CREDS is set */ @@ -956,6 +1067,24 @@ struct io_defer_entry { u32 seq; }; +struct io_cancel_data { + struct io_ring_ctx *ctx; + union { + u64 data; + struct file *file; + }; + u32 flags; + int seq; +}; + +/* + * The URING_CMD payload starts at 'cmd' in the first sqe, and continues into + * the following sqe if SQE128 is used. + */ +#define uring_cmd_pdu_size(is_sqe128) \ + ((1 + !!(is_sqe128)) * sizeof(struct io_uring_sqe) - \ + offsetof(struct io_uring_sqe, cmd)) + struct io_op_def { /* needs req->file assigned */ unsigned needs_file : 1; @@ -977,12 +1106,20 @@ struct io_op_def { unsigned not_supported : 1; /* skip auditing */ unsigned audit_skip : 1; + /* supports ioprio */ + unsigned ioprio : 1; + /* supports iopoll */ + unsigned iopoll : 1; /* size of async data needed, if any */ unsigned short async_size; }; static const struct io_op_def io_op_defs[] = { - [IORING_OP_NOP] = {}, + [IORING_OP_NOP] = { + .audit_skip = 1, + .iopoll = 1, + .buffer_select = 1, + }, [IORING_OP_READV] = { .needs_file = 1, .unbound_nonreg_file = 1, @@ -991,6 +1128,8 @@ static const struct io_op_def io_op_defs[] = { .needs_async_setup = 1, .plug = 1, .audit_skip = 1, + .ioprio = 1, + .iopoll = 1, .async_size = sizeof(struct io_async_rw), }, [IORING_OP_WRITEV] = { @@ -1001,6 +1140,8 @@ static const struct io_op_def io_op_defs[] = { .needs_async_setup = 1, .plug = 1, .audit_skip = 1, + .ioprio = 1, + .iopoll = 1, .async_size = sizeof(struct io_async_rw), }, [IORING_OP_FSYNC] = { @@ -1013,6 +1154,8 @@ static const struct io_op_def io_op_defs[] = { .pollin = 1, .plug = 1, .audit_skip = 1, + .ioprio = 1, + .iopoll = 1, .async_size = sizeof(struct io_async_rw), }, [IORING_OP_WRITE_FIXED] = { @@ -1022,6 +1165,8 @@ static const struct io_op_def io_op_defs[] = { .pollout = 1, .plug = 1, .audit_skip = 1, + .ioprio = 1, + .iopoll = 1, .async_size = sizeof(struct io_async_rw), }, [IORING_OP_POLL_ADD] = { @@ -1064,6 +1209,7 @@ static const struct io_op_def io_op_defs[] = { .unbound_nonreg_file = 1, .pollin = 1, .poll_exclusive = 1, + .ioprio = 1, /* used for flags */ }, [IORING_OP_ASYNC_CANCEL] = { .audit_skip = 1, @@ -1086,6 +1232,7 @@ static const struct io_op_def io_op_defs[] = { [IORING_OP_CLOSE] = {}, [IORING_OP_FILES_UPDATE] = { .audit_skip = 1, + .iopoll = 1, }, [IORING_OP_STATX] = { .audit_skip = 1, @@ -1097,6 +1244,8 @@ static const struct io_op_def io_op_defs[] = { .buffer_select = 1, .plug = 1, .audit_skip = 1, + .ioprio = 1, + .iopoll = 1, .async_size = sizeof(struct io_async_rw), }, [IORING_OP_WRITE] = { @@ -1106,6 +1255,8 @@ static const struct io_op_def io_op_defs[] = { .pollout = 1, .plug = 1, .audit_skip = 1, + .ioprio = 1, + .iopoll = 1, .async_size = sizeof(struct io_async_rw), }, [IORING_OP_FADVISE] = { @@ -1140,9 +1291,11 @@ static const struct io_op_def io_op_defs[] = { }, [IORING_OP_PROVIDE_BUFFERS] = { .audit_skip = 1, + .iopoll = 1, }, [IORING_OP_REMOVE_BUFFERS] = { .audit_skip = 1, + .iopoll = 1, }, [IORING_OP_TEE] = { .needs_file = 1, @@ -1160,11 +1313,30 @@ static const struct io_op_def io_op_defs[] = { [IORING_OP_LINKAT] = {}, [IORING_OP_MSG_RING] = { .needs_file = 1, + .iopoll = 1, + }, + [IORING_OP_FSETXATTR] = { + .needs_file = 1 + }, + [IORING_OP_SETXATTR] = {}, + [IORING_OP_FGETXATTR] = { + .needs_file = 1 + }, + [IORING_OP_GETXATTR] = {}, + [IORING_OP_SOCKET] = { + .audit_skip = 1, + }, + [IORING_OP_URING_CMD] = { + .needs_file = 1, + .plug = 1, + .needs_async_setup = 1, + .async_size = uring_cmd_pdu_size(1), }, }; /* requests with any of those set should undergo io_disarm_next() */ #define IO_DISARM_MASK (REQ_F_ARM_LTIMEOUT | REQ_F_LINK_TIMEOUT | REQ_F_FAIL) +#define IO_REQ_LINK_FLAGS (REQ_F_LINK | REQ_F_HARDLINK) static bool io_disarm_next(struct io_kiocb *req); static void io_uring_del_tctx_node(unsigned long index); @@ -1173,10 +1345,7 @@ static void io_uring_try_cancel_requests(struct io_ring_ctx *ctx, bool cancel_all); static void io_uring_cancel_generic(bool cancel_all, struct io_sq_data *sqd); -static void io_fill_cqe_req(struct io_kiocb *req, s32 res, u32 cflags); - -static void io_put_req(struct io_kiocb *req); -static void io_put_req_deferred(struct io_kiocb *req); +static void __io_req_complete_post(struct io_kiocb *req, s32 res, u32 cflags); static void io_dismantle_req(struct io_kiocb *req); static void io_queue_linked_timeout(struct io_kiocb *req); static int __io_register_rsrc_update(struct io_ring_ctx *ctx, unsigned type, @@ -1185,10 +1354,10 @@ static int __io_register_rsrc_update(struct io_ring_ctx *ctx, unsigned type, static void io_clean_op(struct io_kiocb *req); static inline struct file *io_file_get_fixed(struct io_kiocb *req, int fd, unsigned issue_flags); -static inline struct file *io_file_get_normal(struct io_kiocb *req, int fd); +static struct file *io_file_get_normal(struct io_kiocb *req, int fd); static void io_drop_inflight_file(struct io_kiocb *req); static bool io_assign_file(struct io_kiocb *req, unsigned int issue_flags); -static void __io_queue_sqe(struct io_kiocb *req); +static void io_queue_sqe(struct io_kiocb *req); static void io_rsrc_put_work(struct work_struct *work); static void io_req_task_queue(struct io_kiocb *req); @@ -1201,11 +1370,115 @@ static int io_close_fixed(struct io_kiocb *req, unsigned int issue_flags); static enum hrtimer_restart io_link_timeout_fn(struct hrtimer *timer); static void io_eventfd_signal(struct io_ring_ctx *ctx); +static void io_req_tw_post_queue(struct io_kiocb *req, s32 res, u32 cflags); static struct kmem_cache *req_cachep; static const struct file_operations io_uring_fops; +const char *io_uring_get_opcode(u8 opcode) +{ + switch ((enum io_uring_op)opcode) { + case IORING_OP_NOP: + return "NOP"; + case IORING_OP_READV: + return "READV"; + case IORING_OP_WRITEV: + return "WRITEV"; + case IORING_OP_FSYNC: + return "FSYNC"; + case IORING_OP_READ_FIXED: + return "READ_FIXED"; + case IORING_OP_WRITE_FIXED: + return "WRITE_FIXED"; + case IORING_OP_POLL_ADD: + return "POLL_ADD"; + case IORING_OP_POLL_REMOVE: + return "POLL_REMOVE"; + case IORING_OP_SYNC_FILE_RANGE: + return "SYNC_FILE_RANGE"; + case IORING_OP_SENDMSG: + return "SENDMSG"; + case IORING_OP_RECVMSG: + return "RECVMSG"; + case IORING_OP_TIMEOUT: + return "TIMEOUT"; + case IORING_OP_TIMEOUT_REMOVE: + return "TIMEOUT_REMOVE"; + case IORING_OP_ACCEPT: + return "ACCEPT"; + case IORING_OP_ASYNC_CANCEL: + return "ASYNC_CANCEL"; + case IORING_OP_LINK_TIMEOUT: + return "LINK_TIMEOUT"; + case IORING_OP_CONNECT: + return "CONNECT"; + case IORING_OP_FALLOCATE: + return "FALLOCATE"; + case IORING_OP_OPENAT: + return "OPENAT"; + case IORING_OP_CLOSE: + return "CLOSE"; + case IORING_OP_FILES_UPDATE: + return "FILES_UPDATE"; + case IORING_OP_STATX: + return "STATX"; + case IORING_OP_READ: + return "READ"; + case IORING_OP_WRITE: + return "WRITE"; + case IORING_OP_FADVISE: + return "FADVISE"; + case IORING_OP_MADVISE: + return "MADVISE"; + case IORING_OP_SEND: + return "SEND"; + case IORING_OP_RECV: + return "RECV"; + case IORING_OP_OPENAT2: + return "OPENAT2"; + case IORING_OP_EPOLL_CTL: + return "EPOLL_CTL"; + case IORING_OP_SPLICE: + return "SPLICE"; + case IORING_OP_PROVIDE_BUFFERS: + return "PROVIDE_BUFFERS"; + case IORING_OP_REMOVE_BUFFERS: + return "REMOVE_BUFFERS"; + case IORING_OP_TEE: + return "TEE"; + case IORING_OP_SHUTDOWN: + return "SHUTDOWN"; + case IORING_OP_RENAMEAT: + return "RENAMEAT"; + case IORING_OP_UNLINKAT: + return "UNLINKAT"; + case IORING_OP_MKDIRAT: + return "MKDIRAT"; + case IORING_OP_SYMLINKAT: + return "SYMLINKAT"; + case IORING_OP_LINKAT: + return "LINKAT"; + case IORING_OP_MSG_RING: + return "MSG_RING"; + case IORING_OP_FSETXATTR: + return "FSETXATTR"; + case IORING_OP_SETXATTR: + return "SETXATTR"; + case IORING_OP_FGETXATTR: + return "FGETXATTR"; + case IORING_OP_GETXATTR: + return "GETXATTR"; + case IORING_OP_SOCKET: + return "SOCKET"; + case IORING_OP_URING_CMD: + return "URING_CMD"; + case IORING_OP_LAST: + return "INVALID"; + } + return "INVALID"; +} + struct sock *io_uring_get_socket(struct file *file) { #if defined(CONFIG_UNIX) @@ -1219,6 +1492,42 @@ struct sock *io_uring_get_socket(struct file *file) } EXPORT_SYMBOL(io_uring_get_socket); +#if defined(CONFIG_UNIX) +static inline bool io_file_need_scm(struct file *filp) +{ +#if defined(IO_URING_SCM_ALL) + return true; +#else + return !!unix_get_socket(filp); +#endif +} +#else +static inline bool io_file_need_scm(struct file *filp) +{ + return false; +} +#endif + +static void io_ring_submit_unlock(struct io_ring_ctx *ctx, unsigned issue_flags) +{ + lockdep_assert_held(&ctx->uring_lock); + if (issue_flags & IO_URING_F_UNLOCKED) + mutex_unlock(&ctx->uring_lock); +} + +static void io_ring_submit_lock(struct io_ring_ctx *ctx, unsigned issue_flags) +{ + /* + * "Normal" inline submissions always hold the uring_lock, since we + * grab it from the system call. Same is true for the SQPOLL offload. + * The only exception is when we've detached the request and issue it + * from an async worker thread, grab the lock for that case. + */ + if (issue_flags & IO_URING_F_UNLOCKED) + mutex_lock(&ctx->uring_lock); + lockdep_assert_held(&ctx->uring_lock); +} + static inline void io_tw_lock(struct io_ring_ctx *ctx, bool *locked) { if (!*locked) { @@ -1280,31 +1589,36 @@ static inline void io_req_set_refcount(struct io_kiocb *req) #define IO_RSRC_REF_BATCH 100 +static void io_rsrc_put_node(struct io_rsrc_node *node, int nr) +{ + percpu_ref_put_many(&node->refs, nr); +} + static inline void io_req_put_rsrc_locked(struct io_kiocb *req, struct io_ring_ctx *ctx) __must_hold(&ctx->uring_lock) { - struct percpu_ref *ref = req->fixed_rsrc_refs; + struct io_rsrc_node *node = req->rsrc_node; - if (ref) { - if (ref == &ctx->rsrc_node->refs) + if (node) { + if (node == ctx->rsrc_node) ctx->rsrc_cached_refs++; else - percpu_ref_put(ref); + io_rsrc_put_node(node, 1); } } -static inline void io_req_put_rsrc(struct io_kiocb *req, struct io_ring_ctx *ctx) +static inline void io_req_put_rsrc(struct io_kiocb *req) { - if (req->fixed_rsrc_refs) - percpu_ref_put(req->fixed_rsrc_refs); + if (req->rsrc_node) + io_rsrc_put_node(req->rsrc_node, 1); } static __cold void io_rsrc_refs_drop(struct io_ring_ctx *ctx) __must_hold(&ctx->uring_lock) { if (ctx->rsrc_cached_refs) { - percpu_ref_put_many(&ctx->rsrc_node->refs, ctx->rsrc_cached_refs); + io_rsrc_put_node(ctx->rsrc_node, ctx->rsrc_cached_refs); ctx->rsrc_cached_refs = 0; } } @@ -1320,8 +1634,8 @@ static inline void io_req_set_rsrc_node(struct io_kiocb *req, struct io_ring_ctx *ctx, unsigned int issue_flags) { - if (!req->fixed_rsrc_refs) { - req->fixed_rsrc_refs = &ctx->rsrc_node->refs; + if (!req->rsrc_node) { + req->rsrc_node = ctx->rsrc_node; if (!(issue_flags & IO_URING_F_UNLOCKED)) { lockdep_assert_held(&ctx->uring_lock); @@ -1329,28 +1643,30 @@ static inline void io_req_set_rsrc_node(struct io_kiocb *req, if (unlikely(ctx->rsrc_cached_refs < 0)) io_rsrc_refs_refill(ctx); } else { - percpu_ref_get(req->fixed_rsrc_refs); + percpu_ref_get(&req->rsrc_node->refs); } } } static unsigned int __io_put_kbuf(struct io_kiocb *req, struct list_head *list) { - struct io_buffer *kbuf = req->kbuf; - unsigned int cflags; + if (req->flags & REQ_F_BUFFER_RING) { + if (req->buf_list) + req->buf_list->head++; + req->flags &= ~REQ_F_BUFFER_RING; + } else { + list_add(&req->kbuf->list, list); + req->flags &= ~REQ_F_BUFFER_SELECTED; + } - cflags = IORING_CQE_F_BUFFER | (kbuf->bid << IORING_CQE_BUFFER_SHIFT); - req->flags &= ~REQ_F_BUFFER_SELECTED; - list_add(&kbuf->list, list); - req->kbuf = NULL; - return cflags; + return IORING_CQE_F_BUFFER | (req->buf_index << IORING_CQE_BUFFER_SHIFT); } static inline unsigned int io_put_kbuf_comp(struct io_kiocb *req) { lockdep_assert_held(&req->ctx->completion_lock); - if (likely(!(req->flags & REQ_F_BUFFER_SELECTED))) + if (!(req->flags & (REQ_F_BUFFER_SELECTED|REQ_F_BUFFER_RING))) return 0; return __io_put_kbuf(req, &req->ctx->io_buffers_comp); } @@ -1360,7 +1676,7 @@ static inline unsigned int io_put_kbuf(struct io_kiocb *req, { unsigned int cflags; - if (likely(!(req->flags & REQ_F_BUFFER_SELECTED))) + if (!(req->flags & (REQ_F_BUFFER_SELECTED|REQ_F_BUFFER_RING))) return 0; /* @@ -1375,7 +1691,10 @@ static inline unsigned int io_put_kbuf(struct io_kiocb *req, * We migrate buffers from the comp_list to the issue cache list * when we need one. */ - if (issue_flags & IO_URING_F_UNLOCKED) { + if (req->flags & REQ_F_BUFFER_RING) { + /* no buffers to recycle for this case */ + cflags = __io_put_kbuf(req, NULL); + } else if (issue_flags & IO_URING_F_UNLOCKED) { struct io_ring_ctx *ctx = req->ctx; spin_lock(&ctx->completion_lock); @@ -1393,15 +1712,10 @@ static inline unsigned int io_put_kbuf(struct io_kiocb *req, static struct io_buffer_list *io_buffer_get_list(struct io_ring_ctx *ctx, unsigned int bgid) { - struct list_head *hash_list; - struct io_buffer_list *bl; - - hash_list = &ctx->io_buffers[hash_32(bgid, IO_BUFFERS_HASH_BITS)]; - list_for_each_entry(bl, hash_list, list) - if (bl->bgid == bgid || bgid == -1U) - return bl; + if (ctx->io_bl && bgid < BGID_ARRAY) + return &ctx->io_bl[bgid]; - return NULL; + return xa_load(&ctx->io_bl_xa, bgid); } static void io_kbuf_recycle(struct io_kiocb *req, unsigned issue_flags) @@ -1410,25 +1724,33 @@ static void io_kbuf_recycle(struct io_kiocb *req, unsigned issue_flags) struct io_buffer_list *bl; struct io_buffer *buf; - if (likely(!(req->flags & REQ_F_BUFFER_SELECTED))) + if (!(req->flags & (REQ_F_BUFFER_SELECTED|REQ_F_BUFFER_RING))) return; /* don't recycle if we already did IO to this buffer */ if (req->flags & REQ_F_PARTIAL_IO) return; + /* + * We don't need to recycle for REQ_F_BUFFER_RING, we can just clear + * the flag and hence ensure that bl->head doesn't get incremented. + * If the tail has already been incremented, hang on to it. + */ + if (req->flags & REQ_F_BUFFER_RING) { + if (req->buf_list) { + req->buf_index = req->buf_list->bgid; + req->flags &= ~REQ_F_BUFFER_RING; + } + return; + } - if (issue_flags & IO_URING_F_UNLOCKED) - mutex_lock(&ctx->uring_lock); - - lockdep_assert_held(&ctx->uring_lock); + io_ring_submit_lock(ctx, issue_flags); buf = req->kbuf; bl = io_buffer_get_list(ctx, buf->bgid); list_add(&buf->list, &bl->buf_list); req->flags &= ~REQ_F_BUFFER_SELECTED; - req->kbuf = NULL; + req->buf_index = buf->bgid; - if (issue_flags & IO_URING_F_UNLOCKED) - mutex_unlock(&ctx->uring_lock); + io_ring_submit_unlock(ctx, issue_flags); } static bool io_match_task(struct io_kiocb *head, struct task_struct *task, @@ -1469,7 +1791,12 @@ static inline void req_set_fail(struct io_kiocb *req) static inline void req_fail_link_node(struct io_kiocb *req, int res) { req_set_fail(req); - req->result = res; + req->cqe.res = res; +} + +static inline void io_req_add_to_cache(struct io_kiocb *req, struct io_ring_ctx *ctx) +{ + wq_stack_add_head(&req->comp_list, &ctx->submit_state.free_list); } static __cold void io_ring_ctx_ref_free(struct percpu_ref *ref) @@ -1506,12 +1833,14 @@ static __cold void io_fallback_req_func(struct work_struct *work) static __cold struct io_ring_ctx *io_ring_ctx_alloc(struct io_uring_params *p) { struct io_ring_ctx *ctx; - int i, hash_bits; + int hash_bits; ctx = kzalloc(sizeof(*ctx), GFP_KERNEL); if (!ctx) return NULL; + xa_init(&ctx->io_bl_xa); + /* * Use 5 bits less than the max cq entries, that should give us around * 32 entries per hash list if totally full and uniformly spread. @@ -1533,13 +1862,6 @@ static __cold struct io_ring_ctx *io_ring_ctx_alloc(struct io_uring_params *p) /* set invalid range, so io_import_fixed() fails meeting it */ ctx->dummy_ubuf->ubuf = -1UL; - ctx->io_buffers = kcalloc(1U << IO_BUFFERS_HASH_BITS, - sizeof(struct list_head), GFP_KERNEL); - if (!ctx->io_buffers) - goto err; - for (i = 0; i < (1U << IO_BUFFERS_HASH_BITS); i++) - INIT_LIST_HEAD(&ctx->io_buffers[i]); - if (percpu_ref_init(&ctx->refs, io_ring_ctx_ref_free, PERCPU_REF_ALLOW_REINIT, GFP_KERNEL)) goto err; @@ -1575,7 +1897,8 @@ static __cold struct io_ring_ctx *io_ring_ctx_alloc(struct io_uring_params *p) err: kfree(ctx->dummy_ubuf); kfree(ctx->cancel_hash); - kfree(ctx->io_buffers); + kfree(ctx->io_bl); + xa_destroy(&ctx->io_bl_xa); kfree(ctx); return NULL; } @@ -1599,10 +1922,6 @@ static bool req_need_defer(struct io_kiocb *req, u32 seq) return false; } -#define FFS_NOWAIT 0x1UL -#define FFS_ISREG 0x2UL -#define FFS_MASK ~(FFS_NOWAIT|FFS_ISREG) - static inline bool io_req_ffs_set(struct io_kiocb *req) { return req->flags & REQ_F_FIXED_FILE; @@ -1629,6 +1948,17 @@ static inline struct io_kiocb *io_prep_linked_timeout(struct io_kiocb *req) return __io_prep_linked_timeout(req); } +static noinline void __io_arm_ltimeout(struct io_kiocb *req) +{ + io_queue_linked_timeout(__io_prep_linked_timeout(req)); +} + +static inline void io_arm_ltimeout(struct io_kiocb *req) +{ + if (unlikely(req->flags & REQ_F_ARM_LTIMEOUT)) + __io_arm_ltimeout(req); +} + static void io_prep_async_work(struct io_kiocb *req) { const struct io_op_def *def = &io_op_defs[req->opcode]; @@ -1641,6 +1971,7 @@ static void io_prep_async_work(struct io_kiocb *req) req->work.list.next = NULL; req->work.flags = 0; + req->work.cancel_seq = atomic_read(&ctx->cancel_seq); if (req->flags & REQ_F_FORCE_ASYNC) req->work.flags |= IO_WQ_WORK_CONCURRENT; @@ -1672,17 +2003,15 @@ static void io_prep_async_link(struct io_kiocb *req) static inline void io_req_add_compl_list(struct io_kiocb *req) { - struct io_ring_ctx *ctx = req->ctx; - struct io_submit_state *state = &ctx->submit_state; + struct io_submit_state *state = &req->ctx->submit_state; if (!(req->flags & REQ_F_CQE_SKIP)) - ctx->submit_state.flush_cqes = true; + state->flush_cqes = true; wq_list_add_tail(&req->comp_list, &state->compl_reqs); } -static void io_queue_async_work(struct io_kiocb *req, bool *dont_use) +static void io_queue_iowq(struct io_kiocb *req, bool *dont_use) { - struct io_ring_ctx *ctx = req->ctx; struct io_kiocb *link = io_prep_linked_timeout(req); struct io_uring_task *tctx = req->task->io_uring; @@ -1702,8 +2031,9 @@ static void io_queue_async_work(struct io_kiocb *req, bool *dont_use) if (WARN_ON_ONCE(!same_thread_group(req->task, current))) req->work.flags |= IO_WQ_WORK_CANCEL; - trace_io_uring_queue_async_work(ctx, req, req->user_data, req->opcode, req->flags, - &req->work, io_wq_is_hashed(&req->work)); + trace_io_uring_queue_async_work(req->ctx, req, req->cqe.user_data, + req->opcode, req->flags, &req->work, + io_wq_is_hashed(&req->work)); io_wq_enqueue(tctx->io_wq, &req->work); if (link) io_queue_linked_timeout(link); @@ -1721,8 +2051,7 @@ static void io_kill_timeout(struct io_kiocb *req, int status) atomic_set(&req->ctx->cq_timeouts, atomic_read(&req->ctx->cq_timeouts) + 1); list_del_init(&req->timeout.list); - io_fill_cqe_req(req, status, 0); - io_put_req_deferred(req); + io_req_tw_post_queue(req, status, 0); } } @@ -1804,21 +2133,53 @@ static inline unsigned int __io_cqring_events(struct io_ring_ctx *ctx) return ctx->cached_cq_tail - READ_ONCE(ctx->rings->cq.head); } -static inline struct io_uring_cqe *io_get_cqe(struct io_ring_ctx *ctx) +/* + * writes to the cq entry need to come after reading head; the + * control dependency is enough as we're using WRITE_ONCE to + * fill the cq entry + */ +static noinline struct io_uring_cqe *__io_get_cqe(struct io_ring_ctx *ctx) { struct io_rings *rings = ctx->rings; - unsigned tail, mask = ctx->cq_entries - 1; - - /* - * writes to the cq entry need to come after reading head; the - * control dependency is enough as we're using WRITE_ONCE to - * fill the cq entry - */ - if (__io_cqring_events(ctx) == ctx->cq_entries) + unsigned int off = ctx->cached_cq_tail & (ctx->cq_entries - 1); + unsigned int shift = 0; + unsigned int free, queued, len; + + if (ctx->flags & IORING_SETUP_CQE32) + shift = 1; + + /* userspace may cheat modifying the tail, be safe and do min */ + queued = min(__io_cqring_events(ctx), ctx->cq_entries); + free = ctx->cq_entries - queued; + /* we need a contiguous range, limit based on the current array offset */ + len = min(free, ctx->cq_entries - off); + if (!len) return NULL; - tail = ctx->cached_cq_tail++; - return &rings->cqes[tail & mask]; + ctx->cached_cq_tail++; + ctx->cqe_cached = &rings->cqes[off]; + ctx->cqe_sentinel = ctx->cqe_cached + len; + ctx->cqe_cached++; + return &rings->cqes[off << shift]; +} + +static inline struct io_uring_cqe *io_get_cqe(struct io_ring_ctx *ctx) +{ + if (likely(ctx->cqe_cached < ctx->cqe_sentinel)) { + struct io_uring_cqe *cqe = ctx->cqe_cached; + + if (ctx->flags & IORING_SETUP_CQE32) { + unsigned int off = ctx->cqe_cached - ctx->rings->cqes; + + cqe += off; + } + + ctx->cached_cq_tail++; + ctx->cqe_cached++; + return cqe; + } + + return __io_get_cqe(ctx); } static void io_eventfd_signal(struct io_ring_ctx *ctx) @@ -1889,10 +2250,14 @@ static void io_cqring_ev_posted_iopoll(struct io_ring_ctx *ctx) static bool __io_cqring_overflow_flush(struct io_ring_ctx *ctx, bool force) { bool all_flushed, posted; + size_t cqe_size = sizeof(struct io_uring_cqe); if (!force && __io_cqring_events(ctx) == ctx->cq_entries) return false; + if (ctx->flags & IORING_SETUP_CQE32) + cqe_size <<= 1; + posted = false; spin_lock(&ctx->completion_lock); while (!list_empty(&ctx->cq_overflow_list)) { @@ -1904,7 +2269,7 @@ static bool __io_cqring_overflow_flush(struct io_ring_ctx *ctx, bool force) ocqe = list_first_entry(&ctx->cq_overflow_list, struct io_overflow_cqe, list); if (cqe) - memcpy(cqe, &ocqe->cqe, sizeof(*cqe)); + memcpy(cqe, &ocqe->cqe, cqe_size); else io_account_cq_overflow(ctx); @@ -1915,13 +2280,11 @@ static bool __io_cqring_overflow_flush(struct io_ring_ctx *ctx, bool force) all_flushed = list_empty(&ctx->cq_overflow_list); if (all_flushed) { - clear_bit(0, &ctx->check_cq_overflow); - WRITE_ONCE(ctx->rings->sq_flags, - ctx->rings->sq_flags & ~IORING_SQ_CQ_OVERFLOW); + clear_bit(IO_CHECK_CQ_OVERFLOW_BIT, &ctx->check_cq); + atomic_andnot(IORING_SQ_CQ_OVERFLOW, &ctx->rings->sq_flags); } - if (posted) - io_commit_cqring(ctx); + io_commit_cqring(ctx); spin_unlock(&ctx->completion_lock); if (posted) io_cqring_ev_posted(ctx); @@ -1932,7 +2295,7 @@ static bool io_cqring_overflow_flush(struct io_ring_ctx *ctx) { bool ret = true; - if (test_bit(0, &ctx->check_cq_overflow)) { + if (test_bit(IO_CHECK_CQ_OVERFLOW_BIT, &ctx->check_cq)) { /* iopoll syncs against uring_lock, not completion_lock */ if (ctx->flags & IORING_SETUP_IOPOLL) mutex_lock(&ctx->uring_lock); @@ -1944,19 +2307,23 @@ static bool io_cqring_overflow_flush(struct io_ring_ctx *ctx) return ret; } -/* must to be called somewhat shortly after putting a request */ -static inline void io_put_task(struct task_struct *task, int nr) +static void __io_put_task(struct task_struct *task, int nr) { struct io_uring_task *tctx = task->io_uring; - if (likely(task == current)) { - tctx->cached_refs += nr; - } else { - percpu_counter_sub(&tctx->inflight, nr); - if (unlikely(atomic_read(&tctx->in_idle))) - wake_up(&tctx->wait); - put_task_struct_many(task, nr); - } + percpu_counter_sub(&tctx->inflight, nr); + if (unlikely(atomic_read(&tctx->in_idle))) + wake_up(&tctx->wait); + put_task_struct_many(task, nr); +} + +/* must to be called somewhat shortly after putting a request */ +static inline void io_put_task(struct task_struct *task, int nr) +{ + if (likely(task == current)) + task->io_uring->cached_refs += nr; + else + __io_put_task(task, nr); } static void io_task_refs_refill(struct io_uring_task *tctx) @@ -1990,11 +2357,18 @@ static __cold void io_uring_drop_tctx_refs(struct task_struct *task) } static bool io_cqring_event_overflow(struct io_ring_ctx *ctx, u64 user_data, - s32 res, u32 cflags) + s32 res, u32 cflags, u64 extra1, + u64 extra2) { struct io_overflow_cqe *ocqe; + size_t ocq_size = sizeof(struct io_overflow_cqe); + bool is_cqe32 = (ctx->flags & IORING_SETUP_CQE32); + + if (is_cqe32) + ocq_size += sizeof(struct io_uring_cqe); - ocqe = kmalloc(sizeof(*ocqe), GFP_ATOMIC | __GFP_ACCOUNT); + ocqe = kmalloc(ocq_size, GFP_ATOMIC | __GFP_ACCOUNT); + trace_io_uring_cqe_overflow(ctx, user_data, res, cflags, ocqe); if (!ocqe) { /* * If we're in ring overflow flush mode, or in task cancel mode, @@ -2002,17 +2376,21 @@ static bool io_cqring_event_overflow(struct io_ring_ctx *ctx, u64 user_data, * on the floor. */ io_account_cq_overflow(ctx); + set_bit(IO_CHECK_CQ_DROPPED_BIT, &ctx->check_cq); return false; } if (list_empty(&ctx->cq_overflow_list)) { - set_bit(0, &ctx->check_cq_overflow); - WRITE_ONCE(ctx->rings->sq_flags, - ctx->rings->sq_flags | IORING_SQ_CQ_OVERFLOW); + set_bit(IO_CHECK_CQ_OVERFLOW_BIT, &ctx->check_cq); + atomic_or(IORING_SQ_CQ_OVERFLOW, &ctx->rings->sq_flags); } ocqe->cqe.user_data = user_data; ocqe->cqe.res = res; ocqe->cqe.flags = cflags; + if (is_cqe32) { + ocqe->cqe.big_cqe[0] = extra1; + ocqe->cqe.big_cqe[1] = extra2; + } list_add_tail(&ocqe->list, &ctx->cq_overflow_list); return true; } @@ -2034,42 +2412,114 @@ static inline bool __io_fill_cqe(struct io_ring_ctx *ctx, u64 user_data, WRITE_ONCE(cqe->flags, cflags); return true; } - return io_cqring_event_overflow(ctx, user_data, res, cflags); + return io_cqring_event_overflow(ctx, user_data, res, cflags, 0, 0); +} + +static inline bool __io_fill_cqe_req_filled(struct io_ring_ctx *ctx, + struct io_kiocb *req) +{ + struct io_uring_cqe *cqe; + + trace_io_uring_complete(req->ctx, req, req->cqe.user_data, + req->cqe.res, req->cqe.flags, 0, 0); + + /* + * If we can't get a cq entry, userspace overflowed the + * submission (by quite a lot). Increment the overflow count in + * the ring. + */ + cqe = io_get_cqe(ctx); + if (likely(cqe)) { + memcpy(cqe, &req->cqe, sizeof(*cqe)); + return true; + } + return io_cqring_event_overflow(ctx, req->cqe.user_data, + req->cqe.res, req->cqe.flags, 0, 0); +} + +static inline bool __io_fill_cqe32_req_filled(struct io_ring_ctx *ctx, + struct io_kiocb *req) +{ + struct io_uring_cqe *cqe; + u64 extra1 = req->extra1; + u64 extra2 = req->extra2; + + trace_io_uring_complete(req->ctx, req, req->cqe.user_data, + req->cqe.res, req->cqe.flags, extra1, extra2); + + /* + * If we can't get a cq entry, userspace overflowed the + * submission (by quite a lot). Increment the overflow count in + * the ring. + */ + cqe = io_get_cqe(ctx); + if (likely(cqe)) { + memcpy(cqe, &req->cqe, sizeof(struct io_uring_cqe)); + cqe->big_cqe[0] = extra1; + cqe->big_cqe[1] = extra2; + return true; + } + + return io_cqring_event_overflow(ctx, req->cqe.user_data, req->cqe.res, + req->cqe.flags, extra1, extra2); } static inline bool __io_fill_cqe_req(struct io_kiocb *req, s32 res, u32 cflags) { - trace_io_uring_complete(req->ctx, req, req->user_data, res, cflags); - return __io_fill_cqe(req->ctx, req->user_data, res, cflags); + trace_io_uring_complete(req->ctx, req, req->cqe.user_data, res, cflags, 0, 0); + return __io_fill_cqe(req->ctx, req->cqe.user_data, res, cflags); } -static noinline void io_fill_cqe_req(struct io_kiocb *req, s32 res, u32 cflags) +static inline void __io_fill_cqe32_req(struct io_kiocb *req, s32 res, u32 cflags, + u64 extra1, u64 extra2) { - if (!(req->flags & REQ_F_CQE_SKIP)) - __io_fill_cqe_req(req, res, cflags); + struct io_ring_ctx *ctx = req->ctx; + struct io_uring_cqe *cqe; + + if (WARN_ON_ONCE(!(ctx->flags & IORING_SETUP_CQE32))) + return; + if (req->flags & REQ_F_CQE_SKIP) + return; + + trace_io_uring_complete(ctx, req, req->cqe.user_data, res, cflags, + extra1, extra2); + + /* + * If we can't get a cq entry, userspace overflowed the + * submission (by quite a lot). Increment the overflow count in + * the ring. + */ + cqe = io_get_cqe(ctx); + if (likely(cqe)) { + WRITE_ONCE(cqe->user_data, req->cqe.user_data); + WRITE_ONCE(cqe->res, res); + WRITE_ONCE(cqe->flags, cflags); + WRITE_ONCE(cqe->big_cqe[0], extra1); + WRITE_ONCE(cqe->big_cqe[1], extra2); + return; + } + + io_cqring_event_overflow(ctx, req->cqe.user_data, res, cflags, extra1, extra2); } static noinline bool io_fill_cqe_aux(struct io_ring_ctx *ctx, u64 user_data, s32 res, u32 cflags) { ctx->cq_extra++; - trace_io_uring_complete(ctx, NULL, user_data, res, cflags); + trace_io_uring_complete(ctx, NULL, user_data, res, cflags, 0, 0); return __io_fill_cqe(ctx, user_data, res, cflags); } -static void __io_req_complete_post(struct io_kiocb *req, s32 res, - u32 cflags) +static void __io_req_complete_put(struct io_kiocb *req) { - struct io_ring_ctx *ctx = req->ctx; - - if (!(req->flags & REQ_F_CQE_SKIP)) - __io_fill_cqe_req(req, res, cflags); /* * If we're the last reference to this request, add to our locked * free_list cache. */ if (req_ref_put_and_test(req)) { - if (req->flags & (REQ_F_LINK | REQ_F_HARDLINK)) { + struct io_ring_ctx *ctx = req->ctx; + + if (req->flags & IO_REQ_LINK_FLAGS) { if (req->flags & IO_DISARM_MASK) io_disarm_next(req); if (req->link) { @@ -2077,7 +2527,7 @@ static void __io_req_complete_post(struct io_kiocb *req, s32 res, req->link = NULL; } } - io_req_put_rsrc(req, ctx); + io_req_put_rsrc(req); /* * Selected buffer deallocation in io_clean_op() assumes that * we don't hold ->completion_lock. Clean them here to avoid @@ -2091,8 +2541,23 @@ static void __io_req_complete_post(struct io_kiocb *req, s32 res, } } -static void io_req_complete_post(struct io_kiocb *req, s32 res, - u32 cflags) +static void __io_req_complete_post(struct io_kiocb *req, s32 res, + u32 cflags) +{ + if (!(req->flags & REQ_F_CQE_SKIP)) + __io_fill_cqe_req(req, res, cflags); + __io_req_complete_put(req); +} + +static void __io_req_complete_post32(struct io_kiocb *req, s32 res, + u32 cflags, u64 extra1, u64 extra2) +{ + if (!(req->flags & REQ_F_CQE_SKIP)) + __io_fill_cqe32_req(req, res, cflags, extra1, extra2); + __io_req_complete_put(req); +} + +static void io_req_complete_post(struct io_kiocb *req, s32 res, u32 cflags) { struct io_ring_ctx *ctx = req->ctx; @@ -2103,11 +2568,23 @@ static void io_req_complete_post(struct io_kiocb *req, s32 res, io_cqring_ev_posted(ctx); } +static void io_req_complete_post32(struct io_kiocb *req, s32 res, + u32 cflags, u64 extra1, u64 extra2) +{ + struct io_ring_ctx *ctx = req->ctx; + + spin_lock(&ctx->completion_lock); + __io_req_complete_post32(req, res, cflags, extra1, extra2); + io_commit_cqring(ctx); + spin_unlock(&ctx->completion_lock); + io_cqring_ev_posted(ctx); +} + static inline void io_req_complete_state(struct io_kiocb *req, s32 res, u32 cflags) { - req->result = res; - req->cflags = cflags; + req->cqe.res = res; + req->cqe.flags = cflags; req->flags |= REQ_F_COMPLETE_INLINE; } @@ -2120,8 +2597,23 @@ static inline void __io_req_complete(struct io_kiocb *req, unsigned issue_flags, io_req_complete_post(req, res, cflags); } +static inline void __io_req_complete32(struct io_kiocb *req, + unsigned int issue_flags, s32 res, + u32 cflags, u64 extra1, u64 extra2) +{ + if (issue_flags & IO_URING_F_COMPLETE_DEFER) { + io_req_complete_state(req, res, cflags); + req->extra1 = extra1; + req->extra2 = extra2; + } else { + io_req_complete_post32(req, res, cflags, extra1, extra2); + } +} + static inline void io_req_complete(struct io_kiocb *req, s32 res) { + if (res < 0) + req_set_fail(req); __io_req_complete(req, 0, res, 0); } @@ -2131,17 +2623,6 @@ static void io_req_complete_failed(struct io_kiocb *req, s32 res) io_req_complete_post(req, res, io_put_kbuf(req, IO_URING_F_UNLOCKED)); } -static void io_req_complete_fail_submit(struct io_kiocb *req) -{ - /* - * We don't submit, fail them all, for that replace hardlinks with - * normal links. Extra REQ_F_LINK is tolerated. - */ - req->flags &= ~REQ_F_HARDLINK; - req->flags |= REQ_F_LINK; - io_req_complete_failed(req, req->result); -} - /* * Don't initialise the fields below on every allocation, but do that in * advance and keep them valid across allocations. @@ -2152,7 +2633,7 @@ static void io_preinit_req(struct io_kiocb *req, struct io_ring_ctx *ctx) req->link = NULL; req->async_data = NULL; /* not necessary, but safer to zero */ - req->result = 0; + req->cqe.res = 0; } static void io_flush_cached_locked_reqs(struct io_ring_ctx *ctx, @@ -2164,19 +2645,9 @@ static void io_flush_cached_locked_reqs(struct io_ring_ctx *ctx, spin_unlock(&ctx->completion_lock); } -/* Returns true IFF there are requests in the cache */ -static bool io_flush_cached_reqs(struct io_ring_ctx *ctx) +static inline bool io_req_cache_empty(struct io_ring_ctx *ctx) { - struct io_submit_state *state = &ctx->submit_state; - - /* - * If we have more than a batch's worth of requests in our IRQ side - * locked cache, grab the lock and move them over to our submission - * side cache. - */ - if (READ_ONCE(ctx->locked_free_nr) > IO_COMPL_BATCH) - io_flush_cached_locked_reqs(ctx, state); - return !!state->free_list.next; + return !ctx->submit_state.free_list.next; } /* @@ -2188,14 +2659,20 @@ static bool io_flush_cached_reqs(struct io_ring_ctx *ctx) static __cold bool __io_alloc_req_refill(struct io_ring_ctx *ctx) __must_hold(&ctx->uring_lock) { - struct io_submit_state *state = &ctx->submit_state; gfp_t gfp = GFP_KERNEL | __GFP_NOWARN; void *reqs[IO_REQ_ALLOC_BATCH]; - struct io_kiocb *req; int ret, i; - if (likely(state->free_list.next || io_flush_cached_reqs(ctx))) - return true; + /* + * If we have more than a batch's worth of requests in our IRQ side + * locked cache, grab the lock and move them over to our submission + * side cache. + */ + if (data_race(ctx->locked_free_nr) > IO_COMPL_BATCH) { + io_flush_cached_locked_reqs(ctx, &ctx->submit_state); + if (!io_req_cache_empty(ctx)) + return true; + } ret = kmem_cache_alloc_bulk(req_cachep, gfp, ARRAY_SIZE(reqs), reqs); @@ -2212,17 +2689,17 @@ static __cold bool __io_alloc_req_refill(struct io_ring_ctx *ctx) percpu_ref_get_many(&ctx->refs, ret); for (i = 0; i < ret; i++) { - req = reqs[i]; + struct io_kiocb *req = reqs[i]; io_preinit_req(req, ctx); - wq_stack_add_head(&req->comp_list, &state->free_list); + io_req_add_to_cache(req, ctx); } return true; } static inline bool io_alloc_req_refill(struct io_ring_ctx *ctx) { - if (unlikely(!ctx->submit_state.free_list.next)) + if (unlikely(io_req_cache_empty(ctx))) return __io_alloc_req_refill(ctx); return true; } @@ -2251,11 +2728,11 @@ static inline void io_dismantle_req(struct io_kiocb *req) io_put_file(req->file); } -static __cold void __io_free_req(struct io_kiocb *req) +static __cold void io_free_req(struct io_kiocb *req) { struct io_ring_ctx *ctx = req->ctx; - io_req_put_rsrc(req, ctx); + io_req_put_rsrc(req); io_dismantle_req(req); io_put_task(req->task, 1); @@ -2273,7 +2750,7 @@ static inline void io_remove_next_linked(struct io_kiocb *req) nxt->link = NULL; } -static bool io_kill_linked_timeout(struct io_kiocb *req) +static struct io_kiocb *io_disarm_linked_timeout(struct io_kiocb *req) __must_hold(&req->ctx->completion_lock) __must_hold(&req->ctx->timeout_lock) { @@ -2286,13 +2763,10 @@ static bool io_kill_linked_timeout(struct io_kiocb *req) link->timeout.head = NULL; if (hrtimer_try_to_cancel(&io->timer) != -1) { list_del(&link->timeout.list); - /* leave REQ_F_CQE_SKIP to io_fill_cqe_req */ - io_fill_cqe_req(link, -ECANCELED, 0); - io_put_req_deferred(link); - return true; + return link; } } - return false; + return NULL; } static void io_fail_links(struct io_kiocb *req) @@ -2306,19 +2780,19 @@ static void io_fail_links(struct io_kiocb *req) long res = -ECANCELED; if (link->flags & REQ_F_FAIL) - res = link->result; + res = link->cqe.res; nxt = link->link; link->link = NULL; - trace_io_uring_fail_link(req->ctx, req, req->user_data, + trace_io_uring_fail_link(req->ctx, req, req->cqe.user_data, req->opcode, link); - if (!ignore_cqes) { + if (ignore_cqes) + link->flags |= REQ_F_CQE_SKIP; + else link->flags &= ~REQ_F_CQE_SKIP; - io_fill_cqe_req(link, res, 0); - } - io_put_req_deferred(link); + __io_req_complete_post(link, res, 0); link = nxt; } } @@ -2326,25 +2800,27 @@ static void io_fail_links(struct io_kiocb *req) static bool io_disarm_next(struct io_kiocb *req) __must_hold(&req->ctx->completion_lock) { + struct io_kiocb *link = NULL; bool posted = false; if (req->flags & REQ_F_ARM_LTIMEOUT) { - struct io_kiocb *link = req->link; - + link = req->link; req->flags &= ~REQ_F_ARM_LTIMEOUT; if (link && link->opcode == IORING_OP_LINK_TIMEOUT) { io_remove_next_linked(req); - /* leave REQ_F_CQE_SKIP to io_fill_cqe_req */ - io_fill_cqe_req(link, -ECANCELED, 0); - io_put_req_deferred(link); + io_req_tw_post_queue(link, -ECANCELED, 0); posted = true; } } else if (req->flags & REQ_F_LINK_TIMEOUT) { struct io_ring_ctx *ctx = req->ctx; spin_lock_irq(&ctx->timeout_lock); - posted = io_kill_linked_timeout(req); + link = io_disarm_linked_timeout(req); spin_unlock_irq(&ctx->timeout_lock); + if (link) { + posted = true; + io_req_tw_post_queue(link, -ECANCELED, 0); + } } if (unlikely((req->flags & REQ_F_FAIL) && !(req->flags & REQ_F_HARDLINK))) { @@ -2361,8 +2837,7 @@ static void __io_req_find_next_prep(struct io_kiocb *req) spin_lock(&ctx->completion_lock); posted = io_disarm_next(req); - if (posted) - io_commit_cqring(ctx); + io_commit_cqring(ctx); spin_unlock(&ctx->completion_lock); if (posted) io_cqring_ev_posted(ctx); @@ -2372,8 +2847,6 @@ static inline struct io_kiocb *io_req_find_next(struct io_kiocb *req) { struct io_kiocb *nxt; - if (likely(!(req->flags & (REQ_F_LINK|REQ_F_HARDLINK)))) - return NULL; /* * If LINK is set, we have dependent requests in this chain. If we * didn't fail this request, queue the first one up, moving any other @@ -2391,6 +2864,8 @@ static void ctx_flush_and_put(struct io_ring_ctx *ctx, bool *locked) { if (!ctx) return; + if (ctx->flags & IORING_SETUP_TASKRUN_FLAG) + atomic_andnot(IORING_SQ_TASKRUN, &ctx->rings->sq_flags); if (*locked) { io_submit_flush_completions(ctx); mutex_unlock(&ctx->uring_lock); @@ -2434,7 +2909,7 @@ static void handle_prev_tw_list(struct io_wq_work_node *node, if (likely(*uring_locked)) req->io_task_work.func(req, uring_locked); else - __io_req_complete_post(req, req->result, + __io_req_complete_post(req, req->cqe.res, io_put_kbuf_comp(req)); node = next; } while (node); @@ -2475,15 +2950,11 @@ static void tctx_task_work(struct callback_head *cb) while (1) { struct io_wq_work_node *node1, *node2; - if (!tctx->task_list.first && - !tctx->prior_task_list.first && uring_locked) - io_submit_flush_completions(ctx); - spin_lock_irq(&tctx->task_lock); - node1 = tctx->prior_task_list.first; + node1 = tctx->prio_task_list.first; node2 = tctx->task_list.first; INIT_WQ_LIST(&tctx->task_list); - INIT_WQ_LIST(&tctx->prior_task_list); + INIT_WQ_LIST(&tctx->prio_task_list); if (!node2 && !node1) tctx->task_running = false; spin_unlock_irq(&tctx->task_lock); @@ -2492,10 +2963,13 @@ static void tctx_task_work(struct callback_head *cb) if (node1) handle_prev_tw_list(node1, &ctx, &uring_locked); - if (node2) handle_tw_list(node2, &ctx, &uring_locked); cond_resched(); + + if (data_race(!tctx->task_list.first) && + data_race(!tctx->prio_task_list.first) && uring_locked) + io_submit_flush_completions(ctx); } ctx_flush_and_put(ctx, &uring_locked); @@ -2505,24 +2979,19 @@ static void tctx_task_work(struct callback_head *cb) io_uring_drop_tctx_refs(current); } -static void io_req_task_work_add(struct io_kiocb *req, bool priority) +static void __io_req_task_work_add(struct io_kiocb *req, + struct io_uring_task *tctx, + struct io_wq_work_list *list) { - struct task_struct *tsk = req->task; - struct io_uring_task *tctx = tsk->io_uring; - enum task_work_notify_mode notify; + struct io_ring_ctx *ctx = req->ctx; struct io_wq_work_node *node; unsigned long flags; bool running; - WARN_ON_ONCE(!tctx); - io_drop_inflight_file(req); spin_lock_irqsave(&tctx->task_lock, flags); - if (priority) - wq_list_add_tail(&req->io_task_work.node, &tctx->prior_task_list); - else - wq_list_add_tail(&req->io_task_work.node, &tctx->task_list); + wq_list_add_tail(&req->io_task_work.node, list); running = tctx->task_running; if (!running) tctx->task_running = true; @@ -2532,22 +3001,15 @@ static void io_req_task_work_add(struct io_kiocb *req, bool priority) if (running) return; - /* - * SQPOLL kernel thread doesn't need notification, just a wakeup. For - * all other cases, use TWA_SIGNAL unconditionally to ensure we're - * processing task_work. There's no reliable way to tell if TWA_RESUME - * will do the job. - */ - notify = (req->ctx->flags & IORING_SETUP_SQPOLL) ? TWA_NONE : TWA_SIGNAL; - if (likely(!task_work_add(tsk, &tctx->task_work, notify))) { - if (notify == TWA_NONE) - wake_up_process(tsk); + if (ctx->flags & IORING_SETUP_TASKRUN_FLAG) + atomic_or(IORING_SQ_TASKRUN, &ctx->rings->sq_flags); + + if (likely(!task_work_add(req->task, &tctx->task_work, ctx->notify_method))) return; - } spin_lock_irqsave(&tctx->task_lock, flags); tctx->task_running = false; - node = wq_list_merge(&tctx->prior_task_list, &tctx->task_list); + node = wq_list_merge(&tctx->prio_task_list, &tctx->task_list); spin_unlock_irqrestore(&tctx->task_lock, flags); while (node) { @@ -2559,47 +3021,73 @@ static void io_req_task_work_add(struct io_kiocb *req, bool priority) } } -static void io_req_task_cancel(struct io_kiocb *req, bool *locked) +static void io_req_task_work_add(struct io_kiocb *req) { - struct io_ring_ctx *ctx = req->ctx; + struct io_uring_task *tctx = req->task->io_uring; + + __io_req_task_work_add(req, tctx, &tctx->task_list); +} + +static void io_req_task_prio_work_add(struct io_kiocb *req) +{ + struct io_uring_task *tctx = req->task->io_uring; + if (req->ctx->flags & IORING_SETUP_SQPOLL) + __io_req_task_work_add(req, tctx, &tctx->prio_task_list); + else + __io_req_task_work_add(req, tctx, &tctx->task_list); +} + +static void io_req_tw_post(struct io_kiocb *req, bool *locked) +{ + io_req_complete_post(req, req->cqe.res, req->cqe.flags); +} + +static void io_req_tw_post_queue(struct io_kiocb *req, s32 res, u32 cflags) +{ + req->cqe.res = res; + req->cqe.flags = cflags; + req->io_task_work.func = io_req_tw_post; + io_req_task_work_add(req); +} + +static void io_req_task_cancel(struct io_kiocb *req, bool *locked) +{ /* not needed for normal modes, but SQPOLL depends on it */ - io_tw_lock(ctx, locked); - io_req_complete_failed(req, req->result); + io_tw_lock(req->ctx, locked); + io_req_complete_failed(req, req->cqe.res); } static void io_req_task_submit(struct io_kiocb *req, bool *locked) { - struct io_ring_ctx *ctx = req->ctx; - - io_tw_lock(ctx, locked); + io_tw_lock(req->ctx, locked); /* req->task == current here, checking PF_EXITING is safe */ if (likely(!(req->task->flags & PF_EXITING))) - __io_queue_sqe(req); + io_queue_sqe(req); else io_req_complete_failed(req, -EFAULT); } static void io_req_task_queue_fail(struct io_kiocb *req, int ret) { - req->result = ret; + req->cqe.res = ret; req->io_task_work.func = io_req_task_cancel; - io_req_task_work_add(req, false); + io_req_task_work_add(req); } static void io_req_task_queue(struct io_kiocb *req) { req->io_task_work.func = io_req_task_submit; - io_req_task_work_add(req, false); + io_req_task_work_add(req); } static void io_req_task_queue_reissue(struct io_kiocb *req) { - req->io_task_work.func = io_queue_async_work; - io_req_task_work_add(req, false); + req->io_task_work.func = io_queue_iowq; + io_req_task_work_add(req); } -static inline void io_queue_next(struct io_kiocb *req) +static void io_queue_next(struct io_kiocb *req) { struct io_kiocb *nxt = io_req_find_next(req); @@ -2607,17 +3095,6 @@ static inline void io_queue_next(struct io_kiocb *req) io_req_task_queue(nxt); } -static void io_free_req(struct io_kiocb *req) -{ - io_queue_next(req); - __io_free_req(req); -} - -static void io_free_req_work(struct io_kiocb *req, bool *locked) -{ - io_free_req(req); -} - static void io_free_batch_list(struct io_ring_ctx *ctx, struct io_wq_work_node *node) __must_hold(&ctx->uring_lock) @@ -2629,15 +3106,30 @@ static void io_free_batch_list(struct io_ring_ctx *ctx, struct io_kiocb *req = container_of(node, struct io_kiocb, comp_list); - if (unlikely(req->flags & REQ_F_REFCOUNT)) { - node = req->comp_list.next; - if (!req_ref_put_and_test(req)) - continue; + if (unlikely(req->flags & IO_REQ_CLEAN_SLOW_FLAGS)) { + if (req->flags & REQ_F_REFCOUNT) { + node = req->comp_list.next; + if (!req_ref_put_and_test(req)) + continue; + } + if ((req->flags & REQ_F_POLLED) && req->apoll) { + struct async_poll *apoll = req->apoll; + + if (apoll->double_poll) + kfree(apoll->double_poll); + list_add(&apoll->poll.wait.entry, + &ctx->apoll_cache); + req->flags &= ~REQ_F_POLLED; + } + if (req->flags & IO_REQ_LINK_FLAGS) + io_queue_next(req); + if (unlikely(req->flags & IO_REQ_CLEAN_FLAGS)) + io_clean_op(req); } + if (!(req->flags & REQ_F_FIXED_FILE)) + io_put_file(req->file); io_req_put_rsrc_locked(req, ctx); - io_queue_next(req); - io_dismantle_req(req); if (req->task != task) { if (task) @@ -2647,7 +3139,7 @@ static void io_free_batch_list(struct io_ring_ctx *ctx, } task_refs++; node = req->comp_list.next; - wq_stack_add_head(&req->comp_list, &ctx->submit_state.free_list); + io_req_add_to_cache(req, ctx); } while (node); if (task) @@ -2666,16 +3158,11 @@ static void __io_submit_flush_completions(struct io_ring_ctx *ctx) struct io_kiocb *req = container_of(node, struct io_kiocb, comp_list); - if (!(req->flags & REQ_F_CQE_SKIP)) - __io_fill_cqe_req(req, req->result, req->cflags); - if ((req->flags & REQ_F_POLLED) && req->apoll) { - struct async_poll *apoll = req->apoll; - - if (apoll->double_poll) - kfree(apoll->double_poll); - list_add(&apoll->poll.wait.entry, - &ctx->apoll_cache); - req->flags &= ~REQ_F_POLLED; + if (!(req->flags & REQ_F_CQE_SKIP)) { + if (!(ctx->flags & IORING_SETUP_CQE32)) + __io_fill_cqe_req_filled(ctx, req); + else + __io_fill_cqe32_req_filled(ctx, req); } } @@ -2698,23 +3185,18 @@ static inline struct io_kiocb *io_put_req_find_next(struct io_kiocb *req) struct io_kiocb *nxt = NULL; if (req_ref_put_and_test(req)) { - nxt = io_req_find_next(req); - __io_free_req(req); + if (unlikely(req->flags & IO_REQ_LINK_FLAGS)) + nxt = io_req_find_next(req); + io_free_req(req); } return nxt; } static inline void io_put_req(struct io_kiocb *req) { - if (req_ref_put_and_test(req)) - io_free_req(req); -} - -static inline void io_put_req_deferred(struct io_kiocb *req) -{ if (req_ref_put_and_test(req)) { - req->io_task_work.func = io_free_req_work; - io_req_task_work_add(req, false); + io_queue_next(req); + io_free_req(req); } } @@ -2800,7 +3282,7 @@ static int io_do_iopoll(struct io_ring_ctx *ctx, bool force_nonspin) nr_events++; if (unlikely(req->flags & REQ_F_CQE_SKIP)) continue; - __io_fill_cqe_req(req, req->result, io_put_kbuf(req, 0)); + __io_fill_cqe_req(req, req->cqe.res, io_put_kbuf(req, 0)); } if (unlikely(!nr_events)) @@ -2846,22 +3328,26 @@ static int io_iopoll_check(struct io_ring_ctx *ctx, long min) { unsigned int nr_events = 0; int ret = 0; + unsigned long check_cq; /* - * We disallow the app entering submit/complete with polling, but we - * still need to lock the ring to prevent racing with polled issue - * that got punted to a workqueue. - */ - mutex_lock(&ctx->uring_lock); - /* * Don't enter poll loop if we already have events pending. * If we do, we can potentially be spinning for commands that * already triggered a CQE (eg in error). */ - if (test_bit(0, &ctx->check_cq_overflow)) + check_cq = READ_ONCE(ctx->check_cq); + if (check_cq & BIT(IO_CHECK_CQ_OVERFLOW_BIT)) __io_cqring_overflow_flush(ctx, false); if (io_cqring_events(ctx)) - goto out; + return 0; + + /* + * Similarly do not spin if we have not informed the user of any + * dropped CQE. + */ + if (unlikely(check_cq & BIT(IO_CHECK_CQ_DROPPED_BIT))) + return -EBADR; + do { /* * If a submit got punted to a workqueue, we can have the @@ -2891,8 +3377,7 @@ static int io_iopoll_check(struct io_ring_ctx *ctx, long min) nr_events += ret; ret = 0; } while (nr_events < min && !need_resched()); -out: - mutex_unlock(&ctx->uring_lock); + return ret; } @@ -2965,21 +3450,21 @@ static bool __io_complete_rw_common(struct io_kiocb *req, long res) } else { fsnotify_access(req->file); } - if (unlikely(res != req->result)) { + if (unlikely(res != req->cqe.res)) { if ((res == -EAGAIN || res == -EOPNOTSUPP) && io_rw_should_reissue(req)) { req->flags |= REQ_F_REISSUE; return true; } req_set_fail(req); - req->result = res; + req->cqe.res = res; } return false; } static inline void io_req_task_complete(struct io_kiocb *req, bool *locked) { - int res = req->result; + int res = req->cqe.res; if (*locked) { io_req_complete_state(req, res, io_put_kbuf(req, 0)); @@ -2995,7 +3480,7 @@ static void __io_complete_rw(struct io_kiocb *req, long res, { if (__io_complete_rw_common(req, res)) return; - __io_req_complete(req, issue_flags, req->result, + __io_req_complete(req, issue_flags, req->cqe.res, io_put_kbuf(req, issue_flags)); } @@ -3005,9 +3490,9 @@ static void io_complete_rw(struct kiocb *kiocb, long res) if (__io_complete_rw_common(req, res)) return; - req->result = res; + req->cqe.res = res; req->io_task_work.func = io_req_task_complete; - io_req_task_work_add(req, !!(req->ctx->flags & IORING_SETUP_SQPOLL)); + io_req_task_prio_work_add(req); } static void io_complete_rw_iopoll(struct kiocb *kiocb, long res) @@ -3016,12 +3501,12 @@ static void io_complete_rw_iopoll(struct kiocb *kiocb, long res) if (kiocb->ki_flags & IOCB_WRITE) kiocb_end_write(req); - if (unlikely(res != req->result)) { + if (unlikely(res != req->cqe.res)) { if (res == -EAGAIN && io_rw_should_reissue(req)) { req->flags |= REQ_F_REISSUE; return; } - req->result = res; + req->cqe.res = res; } /* order with io_iopoll_complete() checking ->iopoll_completed */ @@ -3131,6 +3616,8 @@ static unsigned int io_file_get_flags(struct file *file) res |= FFS_ISREG; if (__io_file_supports_nowait(file, mode)) res |= FFS_NOWAIT; + if (io_file_need_scm(file)) + res |= FFS_SCM; return res; } @@ -3162,6 +3649,7 @@ static int io_prep_rw(struct io_kiocb *req, const struct io_uring_sqe *sqe) req->rw.addr = READ_ONCE(sqe->addr); req->rw.len = READ_ONCE(sqe->len); req->rw.flags = READ_ONCE(sqe->rw_flags); + /* used for fixed read/write too - just read unconditionally */ req->buf_index = READ_ONCE(sqe->buf_index); return 0; } @@ -3310,77 +3798,96 @@ static int io_import_fixed(struct io_kiocb *req, int rw, struct iov_iter *iter, return __io_import_fixed(req, rw, iter, imu); } -static void io_ring_submit_unlock(struct io_ring_ctx *ctx, bool needs_lock) -{ - if (needs_lock) - mutex_unlock(&ctx->uring_lock); -} - -static void io_ring_submit_lock(struct io_ring_ctx *ctx, bool needs_lock) +static int io_buffer_add_list(struct io_ring_ctx *ctx, + struct io_buffer_list *bl, unsigned int bgid) { - /* - * "Normal" inline submissions always hold the uring_lock, since we - * grab it from the system call. Same is true for the SQPOLL offload. - * The only exception is when we've detached the request and issue it - * from an async worker thread, grab the lock for that case. - */ - if (needs_lock) - mutex_lock(&ctx->uring_lock); -} - -static void io_buffer_add_list(struct io_ring_ctx *ctx, - struct io_buffer_list *bl, unsigned int bgid) -{ - struct list_head *list; - - list = &ctx->io_buffers[hash_32(bgid, IO_BUFFERS_HASH_BITS)]; - INIT_LIST_HEAD(&bl->buf_list); bl->bgid = bgid; - list_add(&bl->list, list); + if (bgid < BGID_ARRAY) + return 0; + + return xa_err(xa_store(&ctx->io_bl_xa, bgid, bl, GFP_KERNEL)); } -static struct io_buffer *io_buffer_select(struct io_kiocb *req, size_t *len, - int bgid, unsigned int issue_flags) +static void __user *io_provided_buffer_select(struct io_kiocb *req, size_t *len, + struct io_buffer_list *bl) { - struct io_buffer *kbuf = req->kbuf; - bool needs_lock = issue_flags & IO_URING_F_UNLOCKED; - struct io_ring_ctx *ctx = req->ctx; - struct io_buffer_list *bl; - - if (req->flags & REQ_F_BUFFER_SELECTED) - return kbuf; + if (!list_empty(&bl->buf_list)) { + struct io_buffer *kbuf; - io_ring_submit_lock(ctx, needs_lock); - - lockdep_assert_held(&ctx->uring_lock); - - bl = io_buffer_get_list(ctx, bgid); - if (bl && !list_empty(&bl->buf_list)) { kbuf = list_first_entry(&bl->buf_list, struct io_buffer, list); list_del(&kbuf->list); if (*len > kbuf->len) *len = kbuf->len; req->flags |= REQ_F_BUFFER_SELECTED; req->kbuf = kbuf; + req->buf_index = kbuf->bid; + return u64_to_user_ptr(kbuf->addr); + } + return NULL; +} + +static void __user *io_ring_buffer_select(struct io_kiocb *req, size_t *len, + struct io_buffer_list *bl, + unsigned int issue_flags) +{ + struct io_uring_buf_ring *br = bl->buf_ring; + struct io_uring_buf *buf; + __u32 head = bl->head; + + if (unlikely(smp_load_acquire(&br->tail) == head)) { + io_ring_submit_unlock(req->ctx, issue_flags); + return NULL; + } + + head &= bl->mask; + if (head < IO_BUFFER_LIST_BUF_PER_PAGE) { + buf = &br->bufs[head]; } else { - kbuf = ERR_PTR(-ENOBUFS); + int off = head & (IO_BUFFER_LIST_BUF_PER_PAGE - 1); + int index = head / IO_BUFFER_LIST_BUF_PER_PAGE - 1; + buf = page_address(bl->buf_pages[index]); + buf += off; } + if (*len > buf->len) + *len = buf->len; + req->flags |= REQ_F_BUFFER_RING; + req->buf_list = bl; + req->buf_index = buf->bid; - io_ring_submit_unlock(req->ctx, needs_lock); - return kbuf; + if (issue_flags & IO_URING_F_UNLOCKED) { + /* + * If we came in unlocked, we have no choice but to consume the + * buffer here. This does mean it'll be pinned until the IO + * completes. But coming in unlocked means we're in io-wq + * context, hence there should be no further retry. For the + * locked case, the caller must ensure to call the commit when + * the transfer completes (or if we get -EAGAIN and must poll + * or retry). + */ + req->buf_list = NULL; + bl->head++; + } + return u64_to_user_ptr(buf->addr); } -static void __user *io_rw_buffer_select(struct io_kiocb *req, size_t *len, - unsigned int issue_flags) +static void __user *io_buffer_select(struct io_kiocb *req, size_t *len, + unsigned int issue_flags) { - struct io_buffer *kbuf; - u16 bgid; + struct io_ring_ctx *ctx = req->ctx; + struct io_buffer_list *bl; + void __user *ret = NULL; + + io_ring_submit_lock(req->ctx, issue_flags); - bgid = req->buf_index; - kbuf = io_buffer_select(req, len, bgid, issue_flags); - if (IS_ERR(kbuf)) - return kbuf; - return u64_to_user_ptr(kbuf->addr); + bl = io_buffer_get_list(ctx, req->buf_index); + if (likely(bl)) { + if (bl->buf_nr_pages) + ret = io_ring_buffer_select(req, len, bl, issue_flags); + else + ret = io_provided_buffer_select(req, len, bl); + } + io_ring_submit_unlock(req->ctx, issue_flags); + return ret; } #ifdef CONFIG_COMPAT @@ -3390,7 +3897,7 @@ static ssize_t io_compat_import(struct io_kiocb *req, struct iovec *iov, struct compat_iovec __user *uiov; compat_ssize_t clen; void __user *buf; - ssize_t len; + size_t len; uiov = u64_to_user_ptr(req->rw.addr); if (!access_ok(uiov, sizeof(*uiov))) @@ -3401,11 +3908,12 @@ static ssize_t io_compat_import(struct io_kiocb *req, struct iovec *iov, return -EINVAL; len = clen; - buf = io_rw_buffer_select(req, &len, issue_flags); - if (IS_ERR(buf)) - return PTR_ERR(buf); + buf = io_buffer_select(req, &len, issue_flags); + if (!buf) + return -ENOBUFS; + req->rw.addr = (unsigned long) buf; iov[0].iov_base = buf; - iov[0].iov_len = (compat_size_t) len; + req->rw.len = iov[0].iov_len = (compat_size_t) len; return 0; } #endif @@ -3423,22 +3931,21 @@ static ssize_t __io_iov_buffer_select(struct io_kiocb *req, struct iovec *iov, len = iov[0].iov_len; if (len < 0) return -EINVAL; - buf = io_rw_buffer_select(req, &len, issue_flags); - if (IS_ERR(buf)) - return PTR_ERR(buf); + buf = io_buffer_select(req, &len, issue_flags); + if (!buf) + return -ENOBUFS; + req->rw.addr = (unsigned long) buf; iov[0].iov_base = buf; - iov[0].iov_len = len; + req->rw.len = iov[0].iov_len = len; return 0; } static ssize_t io_iov_buffer_select(struct io_kiocb *req, struct iovec *iov, unsigned int issue_flags) { - if (req->flags & REQ_F_BUFFER_SELECTED) { - struct io_buffer *kbuf = req->kbuf; - - iov[0].iov_base = u64_to_user_ptr(kbuf->addr); - iov[0].iov_len = kbuf->len; + if (req->flags & (REQ_F_BUFFER_SELECTED|REQ_F_BUFFER_RING)) { + iov[0].iov_base = u64_to_user_ptr(req->rw.addr); + iov[0].iov_len = req->rw.len; return 0; } if (req->rw.len != 1) @@ -3452,6 +3959,13 @@ static ssize_t io_iov_buffer_select(struct io_kiocb *req, struct iovec *iov, return __io_iov_buffer_select(req, iov, issue_flags); } +static inline bool io_do_buffer_select(struct io_kiocb *req) +{ + if (!(req->flags & REQ_F_BUFFER_SELECT)) + return false; + return !(req->flags & (REQ_F_BUFFER_SELECTED|REQ_F_BUFFER_RING)); +} + static struct iovec *__io_import_iovec(int rw, struct io_kiocb *req, struct io_rw_state *s, unsigned int issue_flags) @@ -3470,18 +3984,15 @@ static struct iovec *__io_import_iovec(int rw, struct io_kiocb *req, return NULL; } - /* buffer index only valid with fixed read/write, or buffer select */ - if (unlikely(req->buf_index && !(req->flags & REQ_F_BUFFER_SELECT))) - return ERR_PTR(-EINVAL); - buf = u64_to_user_ptr(req->rw.addr); sqe_len = req->rw.len; if (opcode == IORING_OP_READ || opcode == IORING_OP_WRITE) { - if (req->flags & REQ_F_BUFFER_SELECT) { - buf = io_rw_buffer_select(req, &sqe_len, issue_flags); - if (IS_ERR(buf)) - return ERR_CAST(buf); + if (io_do_buffer_select(req)) { + buf = io_buffer_select(req, &sqe_len, issue_flags); + if (!buf) + return ERR_PTR(-ENOBUFS); + req->rw.addr = (unsigned long) buf; req->rw.len = sqe_len; } @@ -3836,7 +4347,7 @@ static int io_read(struct io_kiocb *req, unsigned int issue_flags) kfree(iovec); return ret; } - req->result = iov_iter_count(&s->iter); + req->cqe.res = iov_iter_count(&s->iter); if (force_nonblock) { /* If the file doesn't support async, just async punt */ @@ -3852,7 +4363,7 @@ static int io_read(struct io_kiocb *req, unsigned int issue_flags) ppos = io_kiocb_update_pos(req); - ret = rw_verify_area(READ, req->file, ppos, req->result); + ret = rw_verify_area(READ, req->file, ppos, req->cqe.res); if (unlikely(ret)) { kfree(iovec); return ret; @@ -3874,7 +4385,7 @@ static int io_read(struct io_kiocb *req, unsigned int issue_flags) ret = 0; } else if (ret == -EIOCBQUEUED) { goto out_free; - } else if (ret == req->result || ret <= 0 || !force_nonblock || + } else if (ret == req->cqe.res || ret <= 0 || !force_nonblock || (req->flags & REQ_F_NOWAIT) || !need_read_all(req)) { /* read all, failed, already did sync or don't want to retry */ goto done; @@ -3964,7 +4475,7 @@ static int io_write(struct io_kiocb *req, unsigned int issue_flags) kfree(iovec); return ret; } - req->result = iov_iter_count(&s->iter); + req->cqe.res = iov_iter_count(&s->iter); if (force_nonblock) { /* If the file doesn't support async, just async punt */ @@ -3984,7 +4495,7 @@ static int io_write(struct io_kiocb *req, unsigned int issue_flags) ppos = io_kiocb_update_pos(req); - ret = rw_verify_area(WRITE, req->file, ppos, req->result); + ret = rw_verify_area(WRITE, req->file, ppos, req->cqe.res); if (unlikely(ret)) goto out_free; @@ -4048,9 +4559,7 @@ static int io_renameat_prep(struct io_kiocb *req, struct io_rename *ren = &req->rename; const char __user *oldf, *newf; - if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL)) - return -EINVAL; - if (sqe->ioprio || sqe->buf_index || sqe->splice_fd_in) + if (sqe->buf_index || sqe->splice_fd_in) return -EINVAL; if (unlikely(req->flags & REQ_F_FIXED_FILE)) return -EBADF; @@ -4087,22 +4596,257 @@ static int io_renameat(struct io_kiocb *req, unsigned int issue_flags) ren->newpath, ren->flags); req->flags &= ~REQ_F_NEED_CLEANUP; - if (ret < 0) - req_set_fail(req); io_req_complete(req, ret); return 0; } +static inline void __io_xattr_finish(struct io_kiocb *req) +{ + struct io_xattr *ix = &req->xattr; + + if (ix->filename) + putname(ix->filename); + + kfree(ix->ctx.kname); + kvfree(ix->ctx.kvalue); +} + +static void io_xattr_finish(struct io_kiocb *req, int ret) +{ + req->flags &= ~REQ_F_NEED_CLEANUP; + + __io_xattr_finish(req); + io_req_complete(req, ret); +} + +static int __io_getxattr_prep(struct io_kiocb *req, + const struct io_uring_sqe *sqe) +{ + struct io_xattr *ix = &req->xattr; + const char __user *name; + int ret; + + if (unlikely(req->flags & REQ_F_FIXED_FILE)) + return -EBADF; + + ix->filename = NULL; + ix->ctx.kvalue = NULL; + name = u64_to_user_ptr(READ_ONCE(sqe->addr)); + ix->ctx.cvalue = u64_to_user_ptr(READ_ONCE(sqe->addr2)); + ix->ctx.size = READ_ONCE(sqe->len); + ix->ctx.flags = READ_ONCE(sqe->xattr_flags); + + if (ix->ctx.flags) + return -EINVAL; + + ix->ctx.kname = kmalloc(sizeof(*ix->ctx.kname), GFP_KERNEL); + if (!ix->ctx.kname) + return -ENOMEM; + + ret = strncpy_from_user(ix->ctx.kname->name, name, + sizeof(ix->ctx.kname->name)); + if (!ret || ret == sizeof(ix->ctx.kname->name)) + ret = -ERANGE; + if (ret < 0) { + kfree(ix->ctx.kname); + return ret; + } + + req->flags |= REQ_F_NEED_CLEANUP; + return 0; +} + +static int io_fgetxattr_prep(struct io_kiocb *req, + const struct io_uring_sqe *sqe) +{ + return __io_getxattr_prep(req, sqe); +} + +static int io_getxattr_prep(struct io_kiocb *req, + const struct io_uring_sqe *sqe) +{ + struct io_xattr *ix = &req->xattr; + const char __user *path; + int ret; + + ret = __io_getxattr_prep(req, sqe); + if (ret) + return ret; + + path = u64_to_user_ptr(READ_ONCE(sqe->addr3)); + + ix->filename = getname_flags(path, LOOKUP_FOLLOW, NULL); + if (IS_ERR(ix->filename)) { + ret = PTR_ERR(ix->filename); + ix->filename = NULL; + } + + return ret; +} + +static int io_fgetxattr(struct io_kiocb *req, unsigned int issue_flags) +{ + struct io_xattr *ix = &req->xattr; + int ret; + + if (issue_flags & IO_URING_F_NONBLOCK) + return -EAGAIN; + + ret = do_getxattr(mnt_user_ns(req->file->f_path.mnt), + req->file->f_path.dentry, + &ix->ctx); + + io_xattr_finish(req, ret); + return 0; +} + +static int io_getxattr(struct io_kiocb *req, unsigned int issue_flags) +{ + struct io_xattr *ix = &req->xattr; + unsigned int lookup_flags = LOOKUP_FOLLOW; + struct path path; + int ret; + + if (issue_flags & IO_URING_F_NONBLOCK) + return -EAGAIN; + +retry: + ret = filename_lookup(AT_FDCWD, ix->filename, lookup_flags, &path, NULL); + if (!ret) { + ret = do_getxattr(mnt_user_ns(path.mnt), + path.dentry, + &ix->ctx); + + path_put(&path); + if (retry_estale(ret, lookup_flags)) { + lookup_flags |= LOOKUP_REVAL; + goto retry; + } + } + + io_xattr_finish(req, ret); + return 0; +} + +static int __io_setxattr_prep(struct io_kiocb *req, + const struct io_uring_sqe *sqe) +{ + struct io_xattr *ix = &req->xattr; + const char __user *name; + int ret; + + if (unlikely(req->flags & REQ_F_FIXED_FILE)) + return -EBADF; + + ix->filename = NULL; + name = u64_to_user_ptr(READ_ONCE(sqe->addr)); + ix->ctx.cvalue = u64_to_user_ptr(READ_ONCE(sqe->addr2)); + ix->ctx.kvalue = NULL; + ix->ctx.size = READ_ONCE(sqe->len); + ix->ctx.flags = READ_ONCE(sqe->xattr_flags); + + ix->ctx.kname = kmalloc(sizeof(*ix->ctx.kname), GFP_KERNEL); + if (!ix->ctx.kname) + return -ENOMEM; + + ret = setxattr_copy(name, &ix->ctx); + if (ret) { + kfree(ix->ctx.kname); + return ret; + } + + req->flags |= REQ_F_NEED_CLEANUP; + return 0; +} + +static int io_setxattr_prep(struct io_kiocb *req, + const struct io_uring_sqe *sqe) +{ + struct io_xattr *ix = &req->xattr; + const char __user *path; + int ret; + + ret = __io_setxattr_prep(req, sqe); + if (ret) + return ret; + + path = u64_to_user_ptr(READ_ONCE(sqe->addr3)); + + ix->filename = getname_flags(path, LOOKUP_FOLLOW, NULL); + if (IS_ERR(ix->filename)) { + ret = PTR_ERR(ix->filename); + ix->filename = NULL; + } + + return ret; +} + +static int io_fsetxattr_prep(struct io_kiocb *req, + const struct io_uring_sqe *sqe) +{ + return __io_setxattr_prep(req, sqe); +} + +static int __io_setxattr(struct io_kiocb *req, unsigned int issue_flags, + struct path *path) +{ + struct io_xattr *ix = &req->xattr; + int ret; + + ret = mnt_want_write(path->mnt); + if (!ret) { + ret = do_setxattr(mnt_user_ns(path->mnt), path->dentry, &ix->ctx); + mnt_drop_write(path->mnt); + } + + return ret; +} + +static int io_fsetxattr(struct io_kiocb *req, unsigned int issue_flags) +{ + int ret; + + if (issue_flags & IO_URING_F_NONBLOCK) + return -EAGAIN; + + ret = __io_setxattr(req, issue_flags, &req->file->f_path); + io_xattr_finish(req, ret); + + return 0; +} + +static int io_setxattr(struct io_kiocb *req, unsigned int issue_flags) +{ + struct io_xattr *ix = &req->xattr; + unsigned int lookup_flags = LOOKUP_FOLLOW; + struct path path; + int ret; + + if (issue_flags & IO_URING_F_NONBLOCK) + return -EAGAIN; + +retry: + ret = filename_lookup(AT_FDCWD, ix->filename, lookup_flags, &path, NULL); + if (!ret) { + ret = __io_setxattr(req, issue_flags, &path); + path_put(&path); + if (retry_estale(ret, lookup_flags)) { + lookup_flags |= LOOKUP_REVAL; + goto retry; + } + } + + io_xattr_finish(req, ret); + return 0; +} + static int io_unlinkat_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) { struct io_unlink *un = &req->unlink; const char __user *fname; - if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL)) - return -EINVAL; - if (sqe->ioprio || sqe->off || sqe->len || sqe->buf_index || - sqe->splice_fd_in) + if (sqe->off || sqe->len || sqe->buf_index || sqe->splice_fd_in) return -EINVAL; if (unlikely(req->flags & REQ_F_FIXED_FILE)) return -EBADF; @@ -4136,8 +4880,6 @@ static int io_unlinkat(struct io_kiocb *req, unsigned int issue_flags) ret = do_unlinkat(un->dfd, un->filename); req->flags &= ~REQ_F_NEED_CLEANUP; - if (ret < 0) - req_set_fail(req); io_req_complete(req, ret); return 0; } @@ -4148,10 +4890,7 @@ static int io_mkdirat_prep(struct io_kiocb *req, struct io_mkdir *mkd = &req->mkdir; const char __user *fname; - if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL)) - return -EINVAL; - if (sqe->ioprio || sqe->off || sqe->rw_flags || sqe->buf_index || - sqe->splice_fd_in) + if (sqe->off || sqe->rw_flags || sqe->buf_index || sqe->splice_fd_in) return -EINVAL; if (unlikely(req->flags & REQ_F_FIXED_FILE)) return -EBADF; @@ -4179,8 +4918,6 @@ static int io_mkdirat(struct io_kiocb *req, unsigned int issue_flags) ret = do_mkdirat(mkd->dfd, mkd->filename, mkd->mode); req->flags &= ~REQ_F_NEED_CLEANUP; - if (ret < 0) - req_set_fail(req); io_req_complete(req, ret); return 0; } @@ -4191,10 +4928,7 @@ static int io_symlinkat_prep(struct io_kiocb *req, struct io_symlink *sl = &req->symlink; const char __user *oldpath, *newpath; - if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL)) - return -EINVAL; - if (sqe->ioprio || sqe->len || sqe->rw_flags || sqe->buf_index || - sqe->splice_fd_in) + if (sqe->len || sqe->rw_flags || sqe->buf_index || sqe->splice_fd_in) return -EINVAL; if (unlikely(req->flags & REQ_F_FIXED_FILE)) return -EBADF; @@ -4228,8 +4962,6 @@ static int io_symlinkat(struct io_kiocb *req, unsigned int issue_flags) ret = do_symlinkat(sl->oldpath, sl->new_dfd, sl->newpath); req->flags &= ~REQ_F_NEED_CLEANUP; - if (ret < 0) - req_set_fail(req); io_req_complete(req, ret); return 0; } @@ -4240,9 +4972,7 @@ static int io_linkat_prep(struct io_kiocb *req, struct io_hardlink *lnk = &req->hardlink; const char __user *oldf, *newf; - if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL)) - return -EINVAL; - if (sqe->ioprio || sqe->rw_flags || sqe->buf_index || sqe->splice_fd_in) + if (sqe->rw_flags || sqe->buf_index || sqe->splice_fd_in) return -EINVAL; if (unlikely(req->flags & REQ_F_FIXED_FILE)) return -EBADF; @@ -4279,9 +5009,97 @@ static int io_linkat(struct io_kiocb *req, unsigned int issue_flags) lnk->newpath, lnk->flags); req->flags &= ~REQ_F_NEED_CLEANUP; + io_req_complete(req, ret); + return 0; +} + +static void io_uring_cmd_work(struct io_kiocb *req, bool *locked) +{ + req->uring_cmd.task_work_cb(&req->uring_cmd); +} + +void io_uring_cmd_complete_in_task(struct io_uring_cmd *ioucmd, + void (*task_work_cb)(struct io_uring_cmd *)) +{ + struct io_kiocb *req = container_of(ioucmd, struct io_kiocb, uring_cmd); + + req->uring_cmd.task_work_cb = task_work_cb; + req->io_task_work.func = io_uring_cmd_work; + io_req_task_prio_work_add(req); +} +EXPORT_SYMBOL_GPL(io_uring_cmd_complete_in_task); + +/* + * Called by consumers of io_uring_cmd, if they originally returned + * -EIOCBQUEUED upon receiving the command. + */ +void io_uring_cmd_done(struct io_uring_cmd *ioucmd, ssize_t ret, ssize_t res2) +{ + struct io_kiocb *req = container_of(ioucmd, struct io_kiocb, uring_cmd); + if (ret < 0) req_set_fail(req); - io_req_complete(req, ret); + if (req->ctx->flags & IORING_SETUP_CQE32) + __io_req_complete32(req, 0, ret, 0, res2, 0); + else + io_req_complete(req, ret); +} +EXPORT_SYMBOL_GPL(io_uring_cmd_done); + +static int io_uring_cmd_prep_async(struct io_kiocb *req) +{ + size_t cmd_size; + + cmd_size = uring_cmd_pdu_size(req->ctx->flags & IORING_SETUP_SQE128); + + memcpy(req->async_data, req->uring_cmd.cmd, cmd_size); + return 0; +} + +static int io_uring_cmd_prep(struct io_kiocb *req, + const struct io_uring_sqe *sqe) +{ + struct io_uring_cmd *ioucmd = &req->uring_cmd; + + if (sqe->rw_flags) + return -EINVAL; + ioucmd->cmd = sqe->cmd; + ioucmd->cmd_op = READ_ONCE(sqe->cmd_op); + return 0; +} + +static int io_uring_cmd(struct io_kiocb *req, unsigned int issue_flags) +{ + struct io_uring_cmd *ioucmd = &req->uring_cmd; + struct io_ring_ctx *ctx = req->ctx; + struct file *file = req->file; + int ret; + + if (!req->file->f_op->uring_cmd) + return -EOPNOTSUPP; + + if (ctx->flags & IORING_SETUP_SQE128) + issue_flags |= IO_URING_F_SQE128; + if (ctx->flags & IORING_SETUP_CQE32) + issue_flags |= IO_URING_F_CQE32; + if (ctx->flags & IORING_SETUP_IOPOLL) + issue_flags |= IO_URING_F_IOPOLL; + + if (req_has_async_data(req)) + ioucmd->cmd = req->async_data; + + ret = file->f_op->uring_cmd(ioucmd, issue_flags); + if (ret == -EAGAIN) { + if (!req_has_async_data(req)) { + if (io_alloc_async_data(req)) + return -ENOMEM; + io_uring_cmd_prep_async(req); + } + return -EAGAIN; + } + + if (ret != -EIOCBQUEUED) + io_uring_cmd_done(ioucmd, ret, 0); return 0; } @@ -4289,9 +5107,7 @@ static int io_shutdown_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) { #if defined(CONFIG_NET) - if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL)) - return -EINVAL; - if (unlikely(sqe->ioprio || sqe->off || sqe->addr || sqe->rw_flags || + if (unlikely(sqe->off || sqe->addr || sqe->rw_flags || sqe->buf_index || sqe->splice_fd_in)) return -EINVAL; @@ -4316,8 +5132,6 @@ static int io_shutdown(struct io_kiocb *req, unsigned int issue_flags) return -ENOTSOCK; ret = __sys_shutdown_sock(sock, req->shutdown.how); - if (ret < 0) - req_set_fail(req); io_req_complete(req, ret); return 0; #else @@ -4331,9 +5145,6 @@ static int __io_splice_prep(struct io_kiocb *req, struct io_splice *sp = &req->splice; unsigned int valid_flags = SPLICE_F_FD_IN_FIXED | SPLICE_F_ALL; - if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL)) - return -EINVAL; - sp->len = READ_ONCE(sqe->len); sp->flags = READ_ONCE(sqe->splice_flags); if (unlikely(sp->flags & ~valid_flags)) @@ -4378,7 +5189,7 @@ static int io_tee(struct io_kiocb *req, unsigned int issue_flags) done: if (ret != sp->len) req_set_fail(req); - io_req_complete(req, ret); + __io_req_complete(req, 0, ret, 0); return 0; } @@ -4423,7 +5234,20 @@ static int io_splice(struct io_kiocb *req, unsigned int issue_flags) done: if (ret != sp->len) req_set_fail(req); - io_req_complete(req, ret); + __io_req_complete(req, 0, ret, 0); + return 0; +} + +static int io_nop_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) +{ + /* + * If the ring is setup with CQE32, relay back addr/addr + */ + if (req->ctx->flags & IORING_SETUP_CQE32) { + req->nop.extra1 = READ_ONCE(sqe->addr); + req->nop.extra2 = READ_ONCE(sqe->addr2); + } + return 0; } @@ -4432,20 +5256,31 @@ done: */ static int io_nop(struct io_kiocb *req, unsigned int issue_flags) { - struct io_ring_ctx *ctx = req->ctx; + unsigned int cflags; + void __user *buf; - if (unlikely(ctx->flags & IORING_SETUP_IOPOLL)) - return -EINVAL; + if (req->flags & REQ_F_BUFFER_SELECT) { + size_t len = 1; - __io_req_complete(req, issue_flags, 0, 0); + buf = io_buffer_select(req, &len, issue_flags); + if (!buf) + return -ENOBUFS; + } + + cflags = io_put_kbuf(req, issue_flags); + if (!(req->ctx->flags & IORING_SETUP_CQE32)) + __io_req_complete(req, issue_flags, 0, cflags); + else + __io_req_complete32(req, issue_flags, 0, cflags, + req->nop.extra1, req->nop.extra2); return 0; } static int io_msg_ring_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) { - if (unlikely(sqe->addr || sqe->ioprio || sqe->rw_flags || - sqe->splice_fd_in || sqe->buf_index || sqe->personality)) + if (unlikely(sqe->addr || sqe->rw_flags || sqe->splice_fd_in || + sqe->buf_index || sqe->personality)) return -EINVAL; req->msg.user_data = READ_ONCE(sqe->off); @@ -4481,17 +5316,15 @@ done: if (ret < 0) req_set_fail(req); __io_req_complete(req, issue_flags, ret, 0); + /* put file to avoid an attempt to IOPOLL the req */ + io_put_file(req->file); + req->file = NULL; return 0; } static int io_fsync_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) { - struct io_ring_ctx *ctx = req->ctx; - - if (unlikely(ctx->flags & IORING_SETUP_IOPOLL)) - return -EINVAL; - if (unlikely(sqe->addr || sqe->ioprio || sqe->buf_index || - sqe->splice_fd_in)) + if (unlikely(sqe->addr || sqe->buf_index || sqe->splice_fd_in)) return -EINVAL; req->sync.flags = READ_ONCE(sqe->fsync_flags); @@ -4515,8 +5348,6 @@ static int io_fsync(struct io_kiocb *req, unsigned int issue_flags) ret = vfs_fsync_range(req->file, req->sync.off, end > 0 ? end : LLONG_MAX, req->sync.flags & IORING_FSYNC_DATASYNC); - if (ret < 0) - req_set_fail(req); io_req_complete(req, ret); return 0; } @@ -4524,10 +5355,7 @@ static int io_fsync(struct io_kiocb *req, unsigned int issue_flags) static int io_fallocate_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) { - if (sqe->ioprio || sqe->buf_index || sqe->rw_flags || - sqe->splice_fd_in) - return -EINVAL; - if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL)) + if (sqe->buf_index || sqe->rw_flags || sqe->splice_fd_in) return -EINVAL; req->sync.off = READ_ONCE(sqe->off); @@ -4545,9 +5373,7 @@ static int io_fallocate(struct io_kiocb *req, unsigned int issue_flags) return -EAGAIN; ret = vfs_fallocate(req->file, req->sync.mode, req->sync.off, req->sync.len); - if (ret < 0) - req_set_fail(req); - else + if (ret >= 0) fsnotify_modify(req->file); io_req_complete(req, ret); return 0; @@ -4558,9 +5384,7 @@ static int __io_openat_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe const char __user *fname; int ret; - if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL)) - return -EINVAL; - if (unlikely(sqe->ioprio || sqe->buf_index)) + if (unlikely(sqe->buf_index)) return -EINVAL; if (unlikely(req->flags & REQ_F_FIXED_FILE)) return -EBADF; @@ -4615,6 +5439,61 @@ static int io_openat2_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) return __io_openat_prep(req, sqe); } +static int io_file_bitmap_get(struct io_ring_ctx *ctx) +{ + struct io_file_table *table = &ctx->file_table; + unsigned long nr = ctx->nr_user_files; + int ret; + + if (table->alloc_hint >= nr) + table->alloc_hint = 0; + + do { + ret = find_next_zero_bit(table->bitmap, nr, table->alloc_hint); + if (ret != nr) { + table->alloc_hint = ret + 1; + return ret; + } + if (!table->alloc_hint) + break; + + nr = table->alloc_hint; + table->alloc_hint = 0; + } while (1); + + return -ENFILE; +} + +static int io_fixed_fd_install(struct io_kiocb *req, unsigned int issue_flags, + struct file *file, unsigned int file_slot) +{ + bool alloc_slot = file_slot == IORING_FILE_INDEX_ALLOC; + struct io_ring_ctx *ctx = req->ctx; + int ret; + + if (alloc_slot) { + io_ring_submit_lock(ctx, issue_flags); + ret = io_file_bitmap_get(ctx); + if (unlikely(ret < 0)) { + io_ring_submit_unlock(ctx, issue_flags); + return ret; + } + + file_slot = ret; + } else { + file_slot--; + } + + ret = io_install_fixed_file(req, file, issue_flags, file_slot); + if (alloc_slot) { + io_ring_submit_unlock(ctx, issue_flags); + if (!ret) + return file_slot; + } + + return ret; +} + static int io_openat2(struct io_kiocb *req, unsigned int issue_flags) { struct open_flags op; @@ -4670,8 +5549,8 @@ static int io_openat2(struct io_kiocb *req, unsigned int issue_flags) if (!fixed) fd_install(ret, file); else - ret = io_install_fixed_file(req, file, issue_flags, - req->open.file_slot - 1); + ret = io_fixed_fd_install(req, issue_flags, file, + req->open.file_slot); err: putname(req->open.filename); req->flags &= ~REQ_F_NEED_CLEANUP; @@ -4692,7 +5571,7 @@ static int io_remove_buffers_prep(struct io_kiocb *req, struct io_provide_buf *p = &req->pbuf; u64 tmp; - if (sqe->ioprio || sqe->rw_flags || sqe->addr || sqe->len || sqe->off || + if (sqe->rw_flags || sqe->addr || sqe->len || sqe->off || sqe->splice_fd_in) return -EINVAL; @@ -4715,6 +5594,20 @@ static int __io_remove_buffers(struct io_ring_ctx *ctx, if (!nbufs) return 0; + if (bl->buf_nr_pages) { + int j; + + i = bl->buf_ring->tail - bl->head; + for (j = 0; j < bl->buf_nr_pages; j++) + unpin_user_page(bl->buf_pages[j]); + kvfree(bl->buf_pages); + bl->buf_pages = NULL; + bl->buf_nr_pages = 0; + /* make sure it's seen as empty */ + INIT_LIST_HEAD(&bl->buf_list); + return i; + } + /* the head kbuf is the list itself */ while (!list_empty(&bl->buf_list)) { struct io_buffer *nxt; @@ -4736,22 +5629,23 @@ static int io_remove_buffers(struct io_kiocb *req, unsigned int issue_flags) struct io_ring_ctx *ctx = req->ctx; struct io_buffer_list *bl; int ret = 0; - bool needs_lock = issue_flags & IO_URING_F_UNLOCKED; - - io_ring_submit_lock(ctx, needs_lock); - lockdep_assert_held(&ctx->uring_lock); + io_ring_submit_lock(ctx, issue_flags); ret = -ENOENT; bl = io_buffer_get_list(ctx, p->bgid); - if (bl) - ret = __io_remove_buffers(ctx, bl, p->nbufs); + if (bl) { + ret = -EINVAL; + /* can't use provide/remove buffers command on mapped buffers */ + if (!bl->buf_nr_pages) + ret = __io_remove_buffers(ctx, bl, p->nbufs); + } if (ret < 0) req_set_fail(req); /* complete before unlock, IOPOLL may need the lock */ __io_req_complete(req, issue_flags, ret, 0); - io_ring_submit_unlock(ctx, needs_lock); + io_ring_submit_unlock(ctx, issue_flags); return 0; } @@ -4762,7 +5656,7 @@ static int io_provide_buffers_prep(struct io_kiocb *req, struct io_provide_buf *p = &req->pbuf; u64 tmp; - if (sqe->ioprio || sqe->rw_flags || sqe->splice_fd_in) + if (sqe->rw_flags || sqe->splice_fd_in) return -EINVAL; tmp = READ_ONCE(sqe->fd); @@ -4859,26 +5753,56 @@ static int io_add_buffers(struct io_ring_ctx *ctx, struct io_provide_buf *pbuf, return i ? 0 : -ENOMEM; } +static __cold int io_init_bl_list(struct io_ring_ctx *ctx) +{ + int i; + + ctx->io_bl = kcalloc(BGID_ARRAY, sizeof(struct io_buffer_list), + GFP_KERNEL); + if (!ctx->io_bl) + return -ENOMEM; + + for (i = 0; i < BGID_ARRAY; i++) { + INIT_LIST_HEAD(&ctx->io_bl[i].buf_list); + ctx->io_bl[i].bgid = i; + } + + return 0; +} + static int io_provide_buffers(struct io_kiocb *req, unsigned int issue_flags) { struct io_provide_buf *p = &req->pbuf; struct io_ring_ctx *ctx = req->ctx; struct io_buffer_list *bl; int ret = 0; - bool needs_lock = issue_flags & IO_URING_F_UNLOCKED; - io_ring_submit_lock(ctx, needs_lock); + io_ring_submit_lock(ctx, issue_flags); - lockdep_assert_held(&ctx->uring_lock); + if (unlikely(p->bgid < BGID_ARRAY && !ctx->io_bl)) { + ret = io_init_bl_list(ctx); + if (ret) + goto err; + } bl = io_buffer_get_list(ctx, p->bgid); if (unlikely(!bl)) { - bl = kmalloc(sizeof(*bl), GFP_KERNEL); + bl = kzalloc(sizeof(*bl), GFP_KERNEL); if (!bl) { ret = -ENOMEM; goto err; } - io_buffer_add_list(ctx, bl, p->bgid); + INIT_LIST_HEAD(&bl->buf_list); + ret = io_buffer_add_list(ctx, bl, p->bgid); + if (ret) { + kfree(bl); + goto err; + } + } + /* can't add buffers via this command for a mapped buffer ring */ + if (bl->buf_nr_pages) { + ret = -EINVAL; + goto err; } ret = io_add_buffers(ctx, p, bl); @@ -4887,7 +5811,7 @@ err: req_set_fail(req); /* complete before unlock, IOPOLL may need the lock */ __io_req_complete(req, issue_flags, ret, 0); - io_ring_submit_unlock(ctx, needs_lock); + io_ring_submit_unlock(ctx, issue_flags); return 0; } @@ -4895,9 +5819,7 @@ static int io_epoll_ctl_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) { #if defined(CONFIG_EPOLL) - if (sqe->ioprio || sqe->buf_index || sqe->splice_fd_in) - return -EINVAL; - if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL)) + if (sqe->buf_index || sqe->splice_fd_in) return -EINVAL; req->epoll.epfd = READ_ONCE(sqe->fd); @@ -4941,9 +5863,7 @@ static int io_epoll_ctl(struct io_kiocb *req, unsigned int issue_flags) static int io_madvise_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) { #if defined(CONFIG_ADVISE_SYSCALLS) && defined(CONFIG_MMU) - if (sqe->ioprio || sqe->buf_index || sqe->off || sqe->splice_fd_in) - return -EINVAL; - if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL)) + if (sqe->buf_index || sqe->off || sqe->splice_fd_in) return -EINVAL; req->madvise.addr = READ_ONCE(sqe->addr); @@ -4965,8 +5885,6 @@ static int io_madvise(struct io_kiocb *req, unsigned int issue_flags) return -EAGAIN; ret = do_madvise(current->mm, ma->addr, ma->len, ma->advice); - if (ret < 0) - req_set_fail(req); io_req_complete(req, ret); return 0; #else @@ -4976,9 +5894,7 @@ static int io_madvise(struct io_kiocb *req, unsigned int issue_flags) static int io_fadvise_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) { - if (sqe->ioprio || sqe->buf_index || sqe->addr || sqe->splice_fd_in) - return -EINVAL; - if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL)) + if (sqe->buf_index || sqe->addr || sqe->splice_fd_in) return -EINVAL; req->fadvise.offset = READ_ONCE(sqe->off); @@ -5014,9 +5930,7 @@ static int io_statx_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) { const char __user *path; - if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL)) - return -EINVAL; - if (sqe->ioprio || sqe->buf_index || sqe->splice_fd_in) + if (sqe->buf_index || sqe->splice_fd_in) return -EINVAL; if (req->flags & REQ_F_FIXED_FILE) return -EBADF; @@ -5052,19 +5966,13 @@ static int io_statx(struct io_kiocb *req, unsigned int issue_flags) ret = do_statx(ctx->dfd, ctx->filename, ctx->flags, ctx->mask, ctx->buffer); - - if (ret < 0) - req_set_fail(req); io_req_complete(req, ret); return 0; } static int io_close_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) { - if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL)) - return -EINVAL; - if (sqe->ioprio || sqe->off || sqe->addr || sqe->len || - sqe->rw_flags || sqe->buf_index) + if (sqe->off || sqe->addr || sqe->len || sqe->rw_flags || sqe->buf_index) return -EINVAL; if (req->flags & REQ_F_FIXED_FILE) return -EBADF; @@ -5096,7 +6004,8 @@ static int io_close(struct io_kiocb *req, unsigned int issue_flags) spin_unlock(&files->file_lock); goto err; } - file = fdt->fd[close->fd]; + file = rcu_dereference_protected(fdt->fd[close->fd], + lockdep_is_held(&files->file_lock)); if (!file || file->f_op == &io_uring_fops) { spin_unlock(&files->file_lock); file = NULL; @@ -5130,12 +6039,7 @@ err: static int io_sfr_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) { - struct io_ring_ctx *ctx = req->ctx; - - if (unlikely(ctx->flags & IORING_SETUP_IOPOLL)) - return -EINVAL; - if (unlikely(sqe->addr || sqe->ioprio || sqe->buf_index || - sqe->splice_fd_in)) + if (unlikely(sqe->addr || sqe->buf_index || sqe->splice_fd_in)) return -EINVAL; req->sync.off = READ_ONCE(sqe->off); @@ -5154,13 +6058,18 @@ static int io_sync_file_range(struct io_kiocb *req, unsigned int issue_flags) ret = sync_file_range(req->file, req->sync.off, req->sync.len, req->sync.flags); - if (ret < 0) - req_set_fail(req); io_req_complete(req, ret); return 0; } #if defined(CONFIG_NET) +static bool io_net_retry(struct socket *sock, int flags) +{ + if (!(flags & MSG_WAITALL)) + return false; + return sock->type == SOCK_STREAM || sock->type == SOCK_SEQPACKET; +} + static int io_setup_async_msg(struct io_kiocb *req, struct io_async_msghdr *kmsg) { @@ -5206,13 +6115,16 @@ static int io_sendmsg_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) { struct io_sr_msg *sr = &req->sr_msg; - if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL)) + if (unlikely(sqe->file_index)) return -EINVAL; if (unlikely(sqe->addr2 || sqe->file_index)) return -EINVAL; sr->umsg = u64_to_user_ptr(READ_ONCE(sqe->addr)); sr->len = READ_ONCE(sqe->len); + sr->flags = READ_ONCE(sqe->addr2); + if (sr->flags & ~IORING_RECVSEND_POLL_FIRST) + return -EINVAL; sr->msg_flags = READ_ONCE(sqe->msg_flags) | MSG_NOSIGNAL; if (sr->msg_flags & MSG_DONTWAIT) req->flags |= REQ_F_NOWAIT; @@ -5221,12 +6133,14 @@ static int io_sendmsg_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) if (req->ctx->compat) sr->msg_flags |= MSG_CMSG_COMPAT; #endif + sr->done_io = 0; return 0; } static int io_sendmsg(struct io_kiocb *req, unsigned int issue_flags) { struct io_async_msghdr iomsg, *kmsg; + struct io_sr_msg *sr = &req->sr_msg; struct socket *sock; unsigned flags; int min_ret = 0; @@ -5245,7 +6159,11 @@ static int io_sendmsg(struct io_kiocb *req, unsigned int issue_flags) kmsg = &iomsg; } - flags = req->sr_msg.msg_flags; + if (!(req->flags & REQ_F_POLLED) && + (sr->flags & IORING_RECVSEND_POLL_FIRST)) + return io_setup_async_msg(req, kmsg); + + flags = sr->msg_flags; if (issue_flags & IO_URING_F_NONBLOCK) flags |= MSG_DONTWAIT; if (flags & MSG_WAITALL) @@ -5258,12 +6176,21 @@ static int io_sendmsg(struct io_kiocb *req, unsigned int issue_flags) return io_setup_async_msg(req, kmsg); if (ret == -ERESTARTSYS) ret = -EINTR; + if (ret > 0 && io_net_retry(sock, flags)) { + sr->done_io += ret; + req->flags |= REQ_F_PARTIAL_IO; + return io_setup_async_msg(req, kmsg); + } req_set_fail(req); } /* fast path, check for non-NULL to avoid function call */ if (kmsg->free_iov) kfree(kmsg->free_iov); req->flags &= ~REQ_F_NEED_CLEANUP; + if (ret >= 0) + ret += sr->done_io; + else if (sr->done_io) + ret = sr->done_io; __io_req_complete(req, issue_flags, ret, 0); return 0; } @@ -5278,6 +6205,10 @@ static int io_send(struct io_kiocb *req, unsigned int issue_flags) int min_ret = 0; int ret; + if (!(req->flags & REQ_F_POLLED) && + (sr->flags & IORING_RECVSEND_POLL_FIRST)) + return -EAGAIN; + sock = sock_from_file(req->file); if (unlikely(!sock)) return -ENOTSOCK; @@ -5291,7 +6222,7 @@ static int io_send(struct io_kiocb *req, unsigned int issue_flags) msg.msg_controllen = 0; msg.msg_namelen = 0; - flags = req->sr_msg.msg_flags; + flags = sr->msg_flags; if (issue_flags & IO_URING_F_NONBLOCK) flags |= MSG_DONTWAIT; if (flags & MSG_WAITALL) @@ -5304,8 +6235,19 @@ static int io_send(struct io_kiocb *req, unsigned int issue_flags) return -EAGAIN; if (ret == -ERESTARTSYS) ret = -EINTR; + if (ret > 0 && io_net_retry(sock, flags)) { + sr->len -= ret; + sr->buf += ret; + sr->done_io += ret; + req->flags |= REQ_F_PARTIAL_IO; + return -EAGAIN; + } req_set_fail(req); } + if (ret >= 0) + ret += sr->done_io; + else if (sr->done_io) + ret = sr->done_io; __io_req_complete(req, issue_flags, ret, 0); return 0; } @@ -5397,14 +6339,6 @@ static int io_recvmsg_copy_hdr(struct io_kiocb *req, return __io_recvmsg_copy_hdr(req, iomsg); } -static struct io_buffer *io_recv_buffer_select(struct io_kiocb *req, - unsigned int issue_flags) -{ - struct io_sr_msg *sr = &req->sr_msg; - - return io_buffer_select(req, &sr->len, sr->bgid, issue_flags); -} - static int io_recvmsg_prep_async(struct io_kiocb *req) { int ret; @@ -5419,14 +6353,16 @@ static int io_recvmsg_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) { struct io_sr_msg *sr = &req->sr_msg; - if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL)) + if (unlikely(sqe->file_index)) return -EINVAL; if (unlikely(sqe->addr2 || sqe->file_index)) return -EINVAL; sr->umsg = u64_to_user_ptr(READ_ONCE(sqe->addr)); sr->len = READ_ONCE(sqe->len); - sr->bgid = READ_ONCE(sqe->buf_group); + sr->flags = READ_ONCE(sqe->addr2); + if (sr->flags & ~IORING_RECVSEND_POLL_FIRST) + return -EINVAL; sr->msg_flags = READ_ONCE(sqe->msg_flags) | MSG_NOSIGNAL; if (sr->msg_flags & MSG_DONTWAIT) req->flags |= REQ_F_NOWAIT; @@ -5439,19 +6375,12 @@ static int io_recvmsg_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) return 0; } -static bool io_net_retry(struct socket *sock, int flags) -{ - if (!(flags & MSG_WAITALL)) - return false; - return sock->type == SOCK_STREAM || sock->type == SOCK_SEQPACKET; -} - static int io_recvmsg(struct io_kiocb *req, unsigned int issue_flags) { struct io_async_msghdr iomsg, *kmsg; struct io_sr_msg *sr = &req->sr_msg; struct socket *sock; - struct io_buffer *kbuf; + unsigned int cflags; unsigned flags; int ret, min_ret = 0; bool force_nonblock = issue_flags & IO_URING_F_NONBLOCK; @@ -5469,24 +6398,30 @@ static int io_recvmsg(struct io_kiocb *req, unsigned int issue_flags) kmsg = &iomsg; } - if (req->flags & REQ_F_BUFFER_SELECT) { - kbuf = io_recv_buffer_select(req, issue_flags); - if (IS_ERR(kbuf)) - return PTR_ERR(kbuf); - kmsg->fast_iov[0].iov_base = u64_to_user_ptr(kbuf->addr); - kmsg->fast_iov[0].iov_len = req->sr_msg.len; - iov_iter_init(&kmsg->msg.msg_iter, READ, kmsg->fast_iov, - 1, req->sr_msg.len); + if (!(req->flags & REQ_F_POLLED) && + (sr->flags & IORING_RECVSEND_POLL_FIRST)) + return io_setup_async_msg(req, kmsg); + + if (io_do_buffer_select(req)) { + void __user *buf; + + buf = io_buffer_select(req, &sr->len, issue_flags); + if (!buf) + return -ENOBUFS; + kmsg->fast_iov[0].iov_base = buf; + kmsg->fast_iov[0].iov_len = sr->len; + iov_iter_init(&kmsg->msg.msg_iter, READ, kmsg->fast_iov, 1, + sr->len); } - flags = req->sr_msg.msg_flags; + flags = sr->msg_flags; if (force_nonblock) flags |= MSG_DONTWAIT; if (flags & MSG_WAITALL) min_ret = iov_iter_count(&kmsg->msg.msg_iter); - ret = __sys_recvmsg_sock(sock, &kmsg->msg, req->sr_msg.umsg, - kmsg->uaddr, flags); + kmsg->msg.msg_get_inq = 1; + ret = __sys_recvmsg_sock(sock, &kmsg->msg, sr->umsg, kmsg->uaddr, flags); if (ret < min_ret) { if (ret == -EAGAIN && force_nonblock) return io_setup_async_msg(req, kmsg); @@ -5510,45 +6445,54 @@ static int io_recvmsg(struct io_kiocb *req, unsigned int issue_flags) ret += sr->done_io; else if (sr->done_io) ret = sr->done_io; - __io_req_complete(req, issue_flags, ret, io_put_kbuf(req, issue_flags)); + cflags = io_put_kbuf(req, issue_flags); + if (kmsg->msg.msg_inq) + cflags |= IORING_CQE_F_SOCK_NONEMPTY; + __io_req_complete(req, issue_flags, ret, cflags); return 0; } static int io_recv(struct io_kiocb *req, unsigned int issue_flags) { - struct io_buffer *kbuf; struct io_sr_msg *sr = &req->sr_msg; struct msghdr msg; - void __user *buf = sr->buf; struct socket *sock; struct iovec iov; + unsigned int cflags; unsigned flags; int ret, min_ret = 0; bool force_nonblock = issue_flags & IO_URING_F_NONBLOCK; + if (!(req->flags & REQ_F_POLLED) && + (sr->flags & IORING_RECVSEND_POLL_FIRST)) + return -EAGAIN; + sock = sock_from_file(req->file); if (unlikely(!sock)) return -ENOTSOCK; - if (req->flags & REQ_F_BUFFER_SELECT) { - kbuf = io_recv_buffer_select(req, issue_flags); - if (IS_ERR(kbuf)) - return PTR_ERR(kbuf); - buf = u64_to_user_ptr(kbuf->addr); + if (io_do_buffer_select(req)) { + void __user *buf; + + buf = io_buffer_select(req, &sr->len, issue_flags); + if (!buf) + return -ENOBUFS; + sr->buf = buf; } - ret = import_single_range(READ, buf, sr->len, &iov, &msg.msg_iter); + ret = import_single_range(READ, sr->buf, sr->len, &iov, &msg.msg_iter); if (unlikely(ret)) goto out_free; msg.msg_name = NULL; + msg.msg_namelen = 0; msg.msg_control = NULL; + msg.msg_get_inq = 1; + msg.msg_flags = 0; msg.msg_controllen = 0; - msg.msg_namelen = 0; msg.msg_iocb = NULL; - msg.msg_flags = 0; - flags = req->sr_msg.msg_flags; + flags = sr->msg_flags; if (force_nonblock) flags |= MSG_DONTWAIT; if (flags & MSG_WAITALL) @@ -5577,36 +6521,49 @@ out_free: ret += sr->done_io; else if (sr->done_io) ret = sr->done_io; - __io_req_complete(req, issue_flags, ret, io_put_kbuf(req, issue_flags)); + cflags = io_put_kbuf(req, issue_flags); + if (msg.msg_inq) + cflags |= IORING_CQE_F_SOCK_NONEMPTY; + __io_req_complete(req, issue_flags, ret, cflags); return 0; } static int io_accept_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) { struct io_accept *accept = &req->accept; + unsigned flags; - if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL)) - return -EINVAL; - if (sqe->ioprio || sqe->len || sqe->buf_index) + if (sqe->len || sqe->buf_index) return -EINVAL; accept->addr = u64_to_user_ptr(READ_ONCE(sqe->addr)); accept->addr_len = u64_to_user_ptr(READ_ONCE(sqe->addr2)); accept->flags = READ_ONCE(sqe->accept_flags); accept->nofile = rlimit(RLIMIT_NOFILE); + flags = READ_ONCE(sqe->ioprio); + if (flags & ~IORING_ACCEPT_MULTISHOT) + return -EINVAL; accept->file_slot = READ_ONCE(sqe->file_index); - if (accept->file_slot && (accept->flags & SOCK_CLOEXEC)) - return -EINVAL; + if (accept->file_slot) { + if (accept->flags & SOCK_CLOEXEC) + return -EINVAL; + if (flags & IORING_ACCEPT_MULTISHOT && + accept->file_slot != IORING_FILE_INDEX_ALLOC) + return -EINVAL; + } if (accept->flags & ~(SOCK_CLOEXEC | SOCK_NONBLOCK)) return -EINVAL; if (SOCK_NONBLOCK != O_NONBLOCK && (accept->flags & SOCK_NONBLOCK)) accept->flags = (accept->flags & ~SOCK_NONBLOCK) | O_NONBLOCK; + if (flags & IORING_ACCEPT_MULTISHOT) + req->flags |= REQ_F_APOLL_MULTISHOT; return 0; } static int io_accept(struct io_kiocb *req, unsigned int issue_flags) { + struct io_ring_ctx *ctx = req->ctx; struct io_accept *accept = &req->accept; bool force_nonblock = issue_flags & IO_URING_F_NONBLOCK; unsigned int file_flags = force_nonblock ? O_NONBLOCK : 0; @@ -5614,6 +6571,7 @@ static int io_accept(struct io_kiocb *req, unsigned int issue_flags) struct file *file; int ret, fd; +retry: if (!fixed) { fd = __get_unused_fd_flags(accept->flags, accept->nofile); if (unlikely(fd < 0)) @@ -5625,7 +6583,89 @@ static int io_accept(struct io_kiocb *req, unsigned int issue_flags) if (!fixed) put_unused_fd(fd); ret = PTR_ERR(file); - if (ret == -EAGAIN && force_nonblock) + if (ret == -EAGAIN && force_nonblock) { + /* + * if it's multishot and polled, we don't need to + * return EAGAIN to arm the poll infra since it + * has already been done + */ + if ((req->flags & IO_APOLL_MULTI_POLLED) == + IO_APOLL_MULTI_POLLED) + ret = 0; + return ret; + } + if (ret == -ERESTARTSYS) + ret = -EINTR; + req_set_fail(req); + } else if (!fixed) { + fd_install(fd, file); + ret = fd; + } else { + ret = io_fixed_fd_install(req, issue_flags, file, + accept->file_slot); + } + + if (!(req->flags & REQ_F_APOLL_MULTISHOT)) { + __io_req_complete(req, issue_flags, ret, 0); + return 0; + } + if (ret >= 0) { + bool filled; + + spin_lock(&ctx->completion_lock); + filled = io_fill_cqe_aux(ctx, req->cqe.user_data, ret, + IORING_CQE_F_MORE); + io_commit_cqring(ctx); + spin_unlock(&ctx->completion_lock); + if (filled) { + io_cqring_ev_posted(ctx); + goto retry; + } + ret = -ECANCELED; + } + + return ret; +} + +static int io_socket_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) +{ + struct io_socket *sock = &req->sock; + + if (sqe->addr || sqe->rw_flags || sqe->buf_index) + return -EINVAL; + + sock->domain = READ_ONCE(sqe->fd); + sock->type = READ_ONCE(sqe->off); + sock->protocol = READ_ONCE(sqe->len); + sock->file_slot = READ_ONCE(sqe->file_index); + sock->nofile = rlimit(RLIMIT_NOFILE); + + sock->flags = sock->type & ~SOCK_TYPE_MASK; + if (sock->file_slot && (sock->flags & SOCK_CLOEXEC)) + return -EINVAL; + if (sock->flags & ~(SOCK_CLOEXEC | SOCK_NONBLOCK)) + return -EINVAL; + return 0; +} + +static int io_socket(struct io_kiocb *req, unsigned int issue_flags) +{ + struct io_socket *sock = &req->sock; + bool fixed = !!sock->file_slot; + struct file *file; + int ret, fd; + + if (!fixed) { + fd = __get_unused_fd_flags(sock->flags, sock->nofile); + if (unlikely(fd < 0)) + return fd; + } + file = __sys_socket_file(sock->domain, sock->type, sock->protocol); + if (IS_ERR(file)) { + if (!fixed) + put_unused_fd(fd); + ret = PTR_ERR(file); + if (ret == -EAGAIN && (issue_flags & IO_URING_F_NONBLOCK)) return -EAGAIN; if (ret == -ERESTARTSYS) ret = -EINTR; @@ -5635,7 +6675,7 @@ static int io_accept(struct io_kiocb *req, unsigned int issue_flags) ret = fd; } else { ret = io_install_fixed_file(req, file, issue_flags, - accept->file_slot - 1); + sock->file_slot - 1); } __io_req_complete(req, issue_flags, ret, 0); return 0; @@ -5653,10 +6693,7 @@ static int io_connect_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) { struct io_connect *conn = &req->connect; - if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL)) - return -EINVAL; - if (sqe->ioprio || sqe->len || sqe->buf_index || sqe->rw_flags || - sqe->splice_fd_in) + if (sqe->len || sqe->buf_index || sqe->rw_flags || sqe->splice_fd_in) return -EINVAL; conn->addr = u64_to_user_ptr(READ_ONCE(sqe->addr)); @@ -5729,6 +6766,7 @@ IO_NETOP_PREP_ASYNC(sendmsg); IO_NETOP_PREP_ASYNC(recvmsg); IO_NETOP_PREP_ASYNC(connect); IO_NETOP_PREP(accept); +IO_NETOP_PREP(socket); IO_NETOP_FN(send); IO_NETOP_FN(recv); #endif /* CONFIG_NET */ @@ -5779,7 +6817,7 @@ static void io_poll_req_insert(struct io_kiocb *req) struct io_ring_ctx *ctx = req->ctx; struct hlist_head *list; - list = &ctx->cancel_hash[hash_long(req->user_data, ctx->cancel_hash_bits)]; + list = &ctx->cancel_hash[hash_long(req->cqe.user_data, ctx->cancel_hash_bits)]; hlist_add_head(&req->hash_node, list); } @@ -5838,22 +6876,23 @@ static void io_poll_remove_entries(struct io_kiocb *req) rcu_read_unlock(); } +static int io_issue_sqe(struct io_kiocb *req, unsigned int issue_flags); /* * All poll tw should go through this. Checks for poll events, manages * references, does rewait, etc. * * Returns a negative error on failure. >0 when no action require, which is * either spurious wakeup or multishot CQE is served. 0 when it's done with - * the request, then the mask is stored in req->result. + * the request, then the mask is stored in req->cqe.res. */ -static int io_poll_check_events(struct io_kiocb *req, bool locked) +static int io_poll_check_events(struct io_kiocb *req, bool *locked) { struct io_ring_ctx *ctx = req->ctx; - int v; + int v, ret; /* req->task == current here, checking PF_EXITING is safe */ if (unlikely(req->task->flags & PF_EXITING)) - io_poll_mark_cancelled(req); + return -ECANCELED; do { v = atomic_read(&req->poll_refs); @@ -5864,32 +6903,46 @@ static int io_poll_check_events(struct io_kiocb *req, bool locked) if (v & IO_POLL_CANCEL_FLAG) return -ECANCELED; - if (!req->result) { + if (!req->cqe.res) { struct poll_table_struct pt = { ._key = req->apoll_events }; unsigned flags = locked ? 0 : IO_URING_F_UNLOCKED; if (unlikely(!io_assign_file(req, flags))) return -EBADF; - req->result = vfs_poll(req->file, &pt) & req->apoll_events; + req->cqe.res = vfs_poll(req->file, &pt) & req->apoll_events; } - /* multishot, just fill an CQE and proceed */ - if (req->result && !(req->apoll_events & EPOLLONESHOT)) { - __poll_t mask = mangle_poll(req->result & req->apoll_events); + if ((unlikely(!req->cqe.res))) + continue; + if (req->apoll_events & EPOLLONESHOT) + return 0; + + /* multishot, just fill a CQE and proceed */ + if (!(req->flags & REQ_F_APOLL_MULTISHOT)) { + __poll_t mask = mangle_poll(req->cqe.res & + req->apoll_events); bool filled; spin_lock(&ctx->completion_lock); - filled = io_fill_cqe_aux(ctx, req->user_data, mask, - IORING_CQE_F_MORE); + filled = io_fill_cqe_aux(ctx, req->cqe.user_data, + mask, IORING_CQE_F_MORE); io_commit_cqring(ctx); spin_unlock(&ctx->completion_lock); - if (unlikely(!filled)) - return -ECANCELED; - io_cqring_ev_posted(ctx); - } else if (req->result) { - return 0; + if (filled) { + io_cqring_ev_posted(ctx); + continue; + } + return -ECANCELED; } + io_tw_lock(req->ctx, locked); + if (unlikely(req->task->flags & PF_EXITING)) + return -EFAULT; + ret = io_issue_sqe(req, + IO_URING_F_NONBLOCK|IO_URING_F_COMPLETE_DEFER); + if (ret) + return ret; + /* * Release all references, retry if someone tried to restart * task_work while we were executing it. @@ -5904,21 +6957,21 @@ static void io_poll_task_func(struct io_kiocb *req, bool *locked) struct io_ring_ctx *ctx = req->ctx; int ret; - ret = io_poll_check_events(req, *locked); + ret = io_poll_check_events(req, locked); if (ret > 0) return; if (!ret) { - req->result = mangle_poll(req->result & req->poll.events); + req->cqe.res = mangle_poll(req->cqe.res & req->poll.events); } else { - req->result = ret; + req->cqe.res = ret; req_set_fail(req); } io_poll_remove_entries(req); spin_lock(&ctx->completion_lock); hash_del(&req->hash_node); - __io_req_complete_post(req, req->result, 0); + __io_req_complete_post(req, req->cqe.res, 0); io_commit_cqring(ctx); spin_unlock(&ctx->completion_lock); io_cqring_ev_posted(ctx); @@ -5929,7 +6982,7 @@ static void io_apoll_task_func(struct io_kiocb *req, bool *locked) struct io_ring_ctx *ctx = req->ctx; int ret; - ret = io_poll_check_events(req, *locked); + ret = io_poll_check_events(req, locked); if (ret > 0) return; @@ -5944,9 +6997,9 @@ static void io_apoll_task_func(struct io_kiocb *req, bool *locked) io_req_complete_failed(req, ret); } -static void __io_poll_execute(struct io_kiocb *req, int mask, int events) +static void __io_poll_execute(struct io_kiocb *req, int mask, __poll_t events) { - req->result = mask; + req->cqe.res = mask; /* * This is useful for poll that is armed on behalf of another * request, and where the wakeup path could be on a different @@ -5959,11 +7012,12 @@ static void __io_poll_execute(struct io_kiocb *req, int mask, int events) else req->io_task_work.func = io_apoll_task_func; - trace_io_uring_task_add(req->ctx, req, req->user_data, req->opcode, mask); - io_req_task_work_add(req, false); + trace_io_uring_task_add(req->ctx, req, req->cqe.user_data, req->opcode, mask); + io_req_task_work_add(req); } -static inline void io_poll_execute(struct io_kiocb *req, int res, int events) +static inline void io_poll_execute(struct io_kiocb *req, int res, + __poll_t events) { if (io_poll_get_ownership(req)) __io_poll_execute(req, res, events); @@ -5978,6 +7032,7 @@ static void io_poll_cancel_req(struct io_kiocb *req) #define wqe_to_req(wait) ((void *)((unsigned long) (wait)->private & ~1)) #define wqe_is_double(wait) ((unsigned long) (wait)->private & 1) +#define IO_ASYNC_POLL_COMMON (EPOLLONESHOT | EPOLLPRI) static int io_poll_wake(struct wait_queue_entry *wait, unsigned mode, int sync, void *key) @@ -6012,7 +7067,7 @@ static int io_poll_wake(struct wait_queue_entry *wait, unsigned mode, int sync, } /* for instances that support it check for an event match first */ - if (mask && !(mask & poll->events)) + if (mask && !(mask & (poll->events & ~IO_ASYNC_POLL_COMMON))) return 0; if (io_poll_get_ownership(req)) { @@ -6098,6 +7153,7 @@ static int __io_arm_poll_handler(struct io_kiocb *req, int v; INIT_HLIST_NODE(&req->hash_node); + req->work.cancel_seq = atomic_read(&ctx->cancel_seq); io_init_poll_iocb(poll, mask, io_poll_wake); poll->file = req->file; @@ -6168,28 +7224,34 @@ static int io_arm_poll_handler(struct io_kiocb *req, unsigned issue_flags) struct io_ring_ctx *ctx = req->ctx; struct async_poll *apoll; struct io_poll_table ipt; - __poll_t mask = EPOLLONESHOT | POLLERR | POLLPRI; + __poll_t mask = POLLPRI | POLLERR; int ret; if (!def->pollin && !def->pollout) return IO_APOLL_ABORTED; - if (!file_can_poll(req->file) || (req->flags & REQ_F_POLLED)) + if (!file_can_poll(req->file)) return IO_APOLL_ABORTED; + if ((req->flags & (REQ_F_POLLED|REQ_F_PARTIAL_IO)) == REQ_F_POLLED) + return IO_APOLL_ABORTED; + if (!(req->flags & REQ_F_APOLL_MULTISHOT)) + mask |= EPOLLONESHOT; if (def->pollin) { - mask |= POLLIN | POLLRDNORM; + mask |= EPOLLIN | EPOLLRDNORM; /* If reading from MSG_ERRQUEUE using recvmsg, ignore POLLIN */ if ((req->opcode == IORING_OP_RECVMSG) && (req->sr_msg.msg_flags & MSG_ERRQUEUE)) - mask &= ~POLLIN; + mask &= ~EPOLLIN; } else { - mask |= POLLOUT | POLLWRNORM; + mask |= EPOLLOUT | EPOLLWRNORM; } if (def->poll_exclusive) mask |= EPOLLEXCLUSIVE; - if (!(issue_flags & IO_URING_F_UNLOCKED) && - !list_empty(&ctx->apoll_cache)) { + if (req->flags & REQ_F_POLLED) { + apoll = req->apoll; + } else if (!(issue_flags & IO_URING_F_UNLOCKED) && + !list_empty(&ctx->apoll_cache)) { apoll = list_first_entry(&ctx->apoll_cache, struct async_poll, poll.wait.entry); list_del_init(&apoll->poll.wait.entry); @@ -6209,7 +7271,7 @@ static int io_arm_poll_handler(struct io_kiocb *req, unsigned issue_flags) if (ret || ipt.error) return ret ? IO_APOLL_READY : IO_APOLL_ABORTED; - trace_io_uring_poll_arm(ctx, req, req->user_data, req->opcode, + trace_io_uring_poll_arm(ctx, req, req->cqe.user_data, req->opcode, mask, apoll->poll.events); return IO_APOLL_OK; } @@ -6242,24 +7304,53 @@ static __cold bool io_poll_remove_all(struct io_ring_ctx *ctx, return found; } -static struct io_kiocb *io_poll_find(struct io_ring_ctx *ctx, __u64 sqe_addr, - bool poll_only) +static struct io_kiocb *io_poll_find(struct io_ring_ctx *ctx, bool poll_only, + struct io_cancel_data *cd) __must_hold(&ctx->completion_lock) { struct hlist_head *list; struct io_kiocb *req; - list = &ctx->cancel_hash[hash_long(sqe_addr, ctx->cancel_hash_bits)]; + list = &ctx->cancel_hash[hash_long(cd->data, ctx->cancel_hash_bits)]; hlist_for_each_entry(req, list, hash_node) { - if (sqe_addr != req->user_data) + if (cd->data != req->cqe.user_data) continue; if (poll_only && req->opcode != IORING_OP_POLL_ADD) continue; + if (cd->flags & IORING_ASYNC_CANCEL_ALL) { + if (cd->seq == req->work.cancel_seq) + continue; + req->work.cancel_seq = cd->seq; + } return req; } return NULL; } +static struct io_kiocb *io_poll_file_find(struct io_ring_ctx *ctx, + struct io_cancel_data *cd) + __must_hold(&ctx->completion_lock) +{ + struct io_kiocb *req; + int i; + + for (i = 0; i < (1U << ctx->cancel_hash_bits); i++) { + struct hlist_head *list; + + list = &ctx->cancel_hash[i]; + hlist_for_each_entry(req, list, hash_node) { + if (!(cd->flags & IORING_ASYNC_CANCEL_ANY) && + req->file != cd->file) + continue; + if (cd->seq == req->work.cancel_seq) + continue; + req->work.cancel_seq = cd->seq; + return req; + } + } + return NULL; +} + static bool io_poll_disarm(struct io_kiocb *req) __must_hold(&ctx->completion_lock) { @@ -6270,12 +7361,15 @@ static bool io_poll_disarm(struct io_kiocb *req) return true; } -static int io_poll_cancel(struct io_ring_ctx *ctx, __u64 sqe_addr, - bool poll_only) +static int io_poll_cancel(struct io_ring_ctx *ctx, struct io_cancel_data *cd) __must_hold(&ctx->completion_lock) { - struct io_kiocb *req = io_poll_find(ctx, sqe_addr, poll_only); + struct io_kiocb *req; + if (cd->flags & (IORING_ASYNC_CANCEL_FD|IORING_ASYNC_CANCEL_ANY)) + req = io_poll_file_find(ctx, cd); + else + req = io_poll_find(ctx, false, cd); if (!req) return -ENOENT; io_poll_cancel_req(req); @@ -6302,9 +7396,7 @@ static int io_poll_update_prep(struct io_kiocb *req, struct io_poll_update *upd = &req->poll_update; u32 flags; - if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL)) - return -EINVAL; - if (sqe->ioprio || sqe->buf_index || sqe->splice_fd_in) + if (sqe->buf_index || sqe->splice_fd_in) return -EINVAL; flags = READ_ONCE(sqe->len); if (flags & ~(IORING_POLL_UPDATE_EVENTS | IORING_POLL_UPDATE_USER_DATA | @@ -6334,9 +7426,7 @@ static int io_poll_add_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe struct io_poll_iocb *poll = &req->poll; u32 flags; - if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL)) - return -EINVAL; - if (sqe->ioprio || sqe->buf_index || sqe->off || sqe->addr) + if (sqe->buf_index || sqe->off || sqe->addr) return -EINVAL; flags = READ_ONCE(sqe->len); if (flags & ~IORING_POLL_ADD_MULTI) @@ -6366,13 +7456,14 @@ static int io_poll_add(struct io_kiocb *req, unsigned int issue_flags) static int io_poll_update(struct io_kiocb *req, unsigned int issue_flags) { + struct io_cancel_data cd = { .data = req->poll_update.old_user_data, }; struct io_ring_ctx *ctx = req->ctx; struct io_kiocb *preq; int ret2, ret = 0; bool locked; spin_lock(&ctx->completion_lock); - preq = io_poll_find(ctx, req->poll_update.old_user_data, true); + preq = io_poll_find(ctx, true, &cd); if (!preq || !io_poll_disarm(preq)) { spin_unlock(&ctx->completion_lock); ret = preq ? -EALREADY : -ENOENT; @@ -6388,7 +7479,7 @@ static int io_poll_update(struct io_kiocb *req, unsigned int issue_flags) preq->poll.events |= IO_POLL_UNMASK; } if (req->poll_update.update_user_data) - preq->user_data = req->poll_update.new_user_data; + preq->cqe.user_data = req->poll_update.new_user_data; ret2 = io_poll_add(preq, issue_flags); /* successfully updated, don't complete poll request */ @@ -6397,7 +7488,7 @@ static int io_poll_update(struct io_kiocb *req, unsigned int issue_flags) } req_set_fail(preq); - preq->result = -ECANCELED; + preq->cqe.res = -ECANCELED; locked = !(issue_flags & IO_URING_F_UNLOCKED); io_req_task_complete(preq, &locked); out: @@ -6425,14 +7516,14 @@ static enum hrtimer_restart io_timeout_fn(struct hrtimer *timer) if (!(data->flags & IORING_TIMEOUT_ETIME_SUCCESS)) req_set_fail(req); - req->result = -ETIME; + req->cqe.res = -ETIME; req->io_task_work.func = io_req_task_complete; - io_req_task_work_add(req, false); + io_req_task_work_add(req); return HRTIMER_NORESTART; } static struct io_kiocb *io_timeout_extract(struct io_ring_ctx *ctx, - __u64 user_data) + struct io_cancel_data *cd) __must_hold(&ctx->timeout_lock) { struct io_timeout_data *io; @@ -6440,9 +7531,16 @@ static struct io_kiocb *io_timeout_extract(struct io_ring_ctx *ctx, bool found = false; list_for_each_entry(req, &ctx->timeout_list, timeout.list) { - found = user_data == req->user_data; - if (found) - break; + if (!(cd->flags & IORING_ASYNC_CANCEL_ANY) && + cd->data != req->cqe.user_data) + continue; + if (cd->flags & (IORING_ASYNC_CANCEL_ALL|IORING_ASYNC_CANCEL_ANY)) { + if (cd->seq == req->work.cancel_seq) + continue; + req->work.cancel_seq = cd->seq; + } + found = true; + break; } if (!found) return ERR_PTR(-ENOENT); @@ -6454,11 +7552,14 @@ static struct io_kiocb *io_timeout_extract(struct io_ring_ctx *ctx, return req; } -static int io_timeout_cancel(struct io_ring_ctx *ctx, __u64 user_data) +static int io_timeout_cancel(struct io_ring_ctx *ctx, struct io_cancel_data *cd) __must_hold(&ctx->completion_lock) - __must_hold(&ctx->timeout_lock) { - struct io_kiocb *req = io_timeout_extract(ctx, user_data); + struct io_kiocb *req; + + spin_lock_irq(&ctx->timeout_lock); + req = io_timeout_extract(ctx, cd); + spin_unlock_irq(&ctx->timeout_lock); if (IS_ERR(req)) return PTR_ERR(req); @@ -6491,7 +7592,7 @@ static int io_linked_timeout_update(struct io_ring_ctx *ctx, __u64 user_data, bool found = false; list_for_each_entry(req, &ctx->ltimeout_list, timeout.list) { - found = user_data == req->user_data; + found = user_data == req->cqe.user_data; if (found) break; } @@ -6511,7 +7612,8 @@ static int io_timeout_update(struct io_ring_ctx *ctx, __u64 user_data, struct timespec64 *ts, enum hrtimer_mode mode) __must_hold(&ctx->timeout_lock) { - struct io_kiocb *req = io_timeout_extract(ctx, user_data); + struct io_cancel_data cd = { .data = user_data, }; + struct io_kiocb *req = io_timeout_extract(ctx, &cd); struct io_timeout_data *data; if (IS_ERR(req)) @@ -6531,11 +7633,9 @@ static int io_timeout_remove_prep(struct io_kiocb *req, { struct io_timeout_rem *tr = &req->timeout_rem; - if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL)) - return -EINVAL; if (unlikely(req->flags & (REQ_F_FIXED_FILE | REQ_F_BUFFER_SELECT))) return -EINVAL; - if (sqe->ioprio || sqe->buf_index || sqe->len || sqe->splice_fd_in) + if (sqe->buf_index || sqe->len || sqe->splice_fd_in) return -EINVAL; tr->ltimeout = false; @@ -6576,10 +7676,10 @@ static int io_timeout_remove(struct io_kiocb *req, unsigned int issue_flags) int ret; if (!(req->timeout_rem.flags & IORING_TIMEOUT_UPDATE)) { + struct io_cancel_data cd = { .data = tr->addr, }; + spin_lock(&ctx->completion_lock); - spin_lock_irq(&ctx->timeout_lock); - ret = io_timeout_cancel(ctx, tr->addr); - spin_unlock_irq(&ctx->timeout_lock); + ret = io_timeout_cancel(ctx, &cd); spin_unlock(&ctx->completion_lock); } else { enum hrtimer_mode mode = io_translate_timeout_mode(tr->flags); @@ -6605,10 +7705,7 @@ static int io_timeout_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe, unsigned flags; u32 off = READ_ONCE(sqe->off); - if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL)) - return -EINVAL; - if (sqe->ioprio || sqe->buf_index || sqe->len != 1 || - sqe->splice_fd_in) + if (sqe->buf_index || sqe->len != 1 || sqe->splice_fd_in) return -EINVAL; if (off && is_timeout_link) return -EINVAL; @@ -6707,30 +7804,42 @@ add: return 0; } -struct io_cancel_data { - struct io_ring_ctx *ctx; - u64 user_data; -}; - static bool io_cancel_cb(struct io_wq_work *work, void *data) { struct io_kiocb *req = container_of(work, struct io_kiocb, work); struct io_cancel_data *cd = data; - return req->ctx == cd->ctx && req->user_data == cd->user_data; + if (req->ctx != cd->ctx) + return false; + if (cd->flags & IORING_ASYNC_CANCEL_ANY) { + ; + } else if (cd->flags & IORING_ASYNC_CANCEL_FD) { + if (req->file != cd->file) + return false; + } else { + if (req->cqe.user_data != cd->data) + return false; + } + if (cd->flags & (IORING_ASYNC_CANCEL_ALL|IORING_ASYNC_CANCEL_ANY)) { + if (cd->seq == req->work.cancel_seq) + return false; + req->work.cancel_seq = cd->seq; + } + return true; } -static int io_async_cancel_one(struct io_uring_task *tctx, u64 user_data, - struct io_ring_ctx *ctx) +static int io_async_cancel_one(struct io_uring_task *tctx, + struct io_cancel_data *cd) { - struct io_cancel_data data = { .ctx = ctx, .user_data = user_data, }; enum io_wq_cancel cancel_ret; int ret = 0; + bool all; if (!tctx || !tctx->io_wq) return -ENOENT; - cancel_ret = io_wq_cancel_cb(tctx->io_wq, io_cancel_cb, &data, false); + all = cd->flags & (IORING_ASYNC_CANCEL_ALL|IORING_ASYNC_CANCEL_ANY); + cancel_ret = io_wq_cancel_cb(tctx->io_wq, io_cancel_cb, cd, all); switch (cancel_ret) { case IO_WQ_CANCEL_OK: ret = 0; @@ -6746,14 +7855,14 @@ static int io_async_cancel_one(struct io_uring_task *tctx, u64 user_data, return ret; } -static int io_try_cancel_userdata(struct io_kiocb *req, u64 sqe_addr) +static int io_try_cancel(struct io_kiocb *req, struct io_cancel_data *cd) { struct io_ring_ctx *ctx = req->ctx; int ret; WARN_ON_ONCE(!io_wq_current_is_worker() && req->task != current); - ret = io_async_cancel_one(req->task->io_uring, sqe_addr, ctx); + ret = io_async_cancel_one(req->task->io_uring, cd); /* * Fall-through even for -EALREADY, as we may have poll armed * that need unarming. @@ -6762,56 +7871,98 @@ static int io_try_cancel_userdata(struct io_kiocb *req, u64 sqe_addr) return 0; spin_lock(&ctx->completion_lock); - ret = io_poll_cancel(ctx, sqe_addr, false); + ret = io_poll_cancel(ctx, cd); if (ret != -ENOENT) goto out; - - spin_lock_irq(&ctx->timeout_lock); - ret = io_timeout_cancel(ctx, sqe_addr); - spin_unlock_irq(&ctx->timeout_lock); + if (!(cd->flags & IORING_ASYNC_CANCEL_FD)) + ret = io_timeout_cancel(ctx, cd); out: spin_unlock(&ctx->completion_lock); return ret; } +#define CANCEL_FLAGS (IORING_ASYNC_CANCEL_ALL | IORING_ASYNC_CANCEL_FD | \ + IORING_ASYNC_CANCEL_ANY) + static int io_async_cancel_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) { - if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL)) + if (unlikely(req->flags & REQ_F_BUFFER_SELECT)) return -EINVAL; - if (unlikely(req->flags & (REQ_F_FIXED_FILE | REQ_F_BUFFER_SELECT))) - return -EINVAL; - if (sqe->ioprio || sqe->off || sqe->len || sqe->cancel_flags || - sqe->splice_fd_in) + if (sqe->off || sqe->len || sqe->splice_fd_in) return -EINVAL; req->cancel.addr = READ_ONCE(sqe->addr); + req->cancel.flags = READ_ONCE(sqe->cancel_flags); + if (req->cancel.flags & ~CANCEL_FLAGS) + return -EINVAL; + if (req->cancel.flags & IORING_ASYNC_CANCEL_FD) { + if (req->cancel.flags & IORING_ASYNC_CANCEL_ANY) + return -EINVAL; + req->cancel.fd = READ_ONCE(sqe->fd); + } + return 0; } -static int io_async_cancel(struct io_kiocb *req, unsigned int issue_flags) +static int __io_async_cancel(struct io_cancel_data *cd, struct io_kiocb *req, + unsigned int issue_flags) { - struct io_ring_ctx *ctx = req->ctx; - u64 sqe_addr = req->cancel.addr; - bool needs_lock = issue_flags & IO_URING_F_UNLOCKED; + bool all = cd->flags & (IORING_ASYNC_CANCEL_ALL|IORING_ASYNC_CANCEL_ANY); + struct io_ring_ctx *ctx = cd->ctx; struct io_tctx_node *node; - int ret; + int ret, nr = 0; - ret = io_try_cancel_userdata(req, sqe_addr); - if (ret != -ENOENT) - goto done; + do { + ret = io_try_cancel(req, cd); + if (ret == -ENOENT) + break; + if (!all) + return ret; + nr++; + } while (1); /* slow path, try all io-wq's */ - io_ring_submit_lock(ctx, needs_lock); + io_ring_submit_lock(ctx, issue_flags); ret = -ENOENT; list_for_each_entry(node, &ctx->tctx_list, ctx_node) { struct io_uring_task *tctx = node->task->io_uring; - ret = io_async_cancel_one(tctx, req->cancel.addr, ctx); - if (ret != -ENOENT) - break; + ret = io_async_cancel_one(tctx, cd); + if (ret != -ENOENT) { + if (!all) + break; + nr++; + } } - io_ring_submit_unlock(ctx, needs_lock); + io_ring_submit_unlock(ctx, issue_flags); + return all ? nr : ret; +} + +static int io_async_cancel(struct io_kiocb *req, unsigned int issue_flags) +{ + struct io_cancel_data cd = { + .ctx = req->ctx, + .data = req->cancel.addr, + .flags = req->cancel.flags, + .seq = atomic_inc_return(&req->ctx->cancel_seq), + }; + int ret; + + if (cd.flags & IORING_ASYNC_CANCEL_FD) { + if (req->flags & REQ_F_FIXED_FILE) + req->file = io_file_get_fixed(req, req->cancel.fd, + issue_flags); + else + req->file = io_file_get_normal(req, req->cancel.fd); + if (!req->file) { + ret = -EBADF; + goto done; + } + cd.file = req->file; + } + + ret = __io_async_cancel(&cd, req, issue_flags); done: if (ret < 0) req_set_fail(req); @@ -6824,7 +7975,7 @@ static int io_rsrc_update_prep(struct io_kiocb *req, { if (unlikely(req->flags & (REQ_F_FIXED_FILE | REQ_F_BUFFER_SELECT))) return -EINVAL; - if (sqe->ioprio || sqe->rw_flags || sqe->splice_fd_in) + if (sqe->rw_flags || sqe->splice_fd_in) return -EINVAL; req->rsrc_update.offset = READ_ONCE(sqe->off); @@ -6838,7 +7989,6 @@ static int io_rsrc_update_prep(struct io_kiocb *req, static int io_files_update(struct io_kiocb *req, unsigned int issue_flags) { struct io_ring_ctx *ctx = req->ctx; - bool needs_lock = issue_flags & IO_URING_F_UNLOCKED; struct io_uring_rsrc_update2 up; int ret; @@ -6849,10 +7999,10 @@ static int io_files_update(struct io_kiocb *req, unsigned int issue_flags) up.resv = 0; up.resv2 = 0; - io_ring_submit_lock(ctx, needs_lock); + io_ring_submit_lock(ctx, issue_flags); ret = __io_register_rsrc_update(ctx, IORING_RSRC_FILE, &up, req->rsrc_update.nr_args); - io_ring_submit_unlock(ctx, needs_lock); + io_ring_submit_unlock(ctx, issue_flags); if (ret < 0) req_set_fail(req); @@ -6864,7 +8014,7 @@ static int io_req_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) { switch (req->opcode) { case IORING_OP_NOP: - return 0; + return io_nop_prep(req, sqe); case IORING_OP_READV: case IORING_OP_READ_FIXED: case IORING_OP_READ: @@ -6938,6 +8088,18 @@ static int io_req_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) return io_linkat_prep(req, sqe); case IORING_OP_MSG_RING: return io_msg_ring_prep(req, sqe); + case IORING_OP_FSETXATTR: + return io_fsetxattr_prep(req, sqe); + case IORING_OP_SETXATTR: + return io_setxattr_prep(req, sqe); + case IORING_OP_FGETXATTR: + return io_fgetxattr_prep(req, sqe); + case IORING_OP_GETXATTR: + return io_getxattr_prep(req, sqe); + case IORING_OP_SOCKET: + return io_socket_prep(req, sqe); + case IORING_OP_URING_CMD: + return io_uring_cmd_prep(req, sqe); } printk_once(KERN_WARNING "io_uring: unhandled opcode %d\n", @@ -6951,7 +8113,7 @@ static int io_req_prep_async(struct io_kiocb *req) /* assign early for deferred execution for non-fixed file */ if (def->needs_file && !(req->flags & REQ_F_FIXED_FILE)) - req->file = io_file_get_normal(req, req->fd); + req->file = io_file_get_normal(req, req->cqe.fd); if (!def->needs_async_setup) return 0; if (WARN_ON_ONCE(req_has_async_data(req))) @@ -6970,6 +8132,8 @@ static int io_req_prep_async(struct io_kiocb *req) return io_recvmsg_prep_async(req); case IORING_OP_CONNECT: return io_connect_prep_async(req); + case IORING_OP_URING_CMD: + return io_uring_cmd_prep_async(req); } printk_once(KERN_WARNING "io_uring: prep_async() bad opcode %d\n", req->opcode); @@ -6979,9 +8143,10 @@ static int io_req_prep_async(struct io_kiocb *req) static u32 io_get_sequence(struct io_kiocb *req) { u32 seq = req->ctx->cached_sq_head; + struct io_kiocb *cur; /* need original cached_sq_head, but it was increased for each req */ - io_for_each_link(req, req) + io_for_each_link(cur, req) seq--; return seq; } @@ -7024,7 +8189,7 @@ fail: goto queue; } - trace_io_uring_defer(ctx, req, req->user_data, req->opcode); + trace_io_uring_defer(ctx, req, req->cqe.user_data, req->opcode); de->req = req; de->seq = seq; list_add_tail(&de->list, &ctx->defer_list); @@ -7086,6 +8251,12 @@ static void io_clean_op(struct io_kiocb *req) if (req->statx.filename) putname(req->statx.filename); break; + case IORING_OP_SETXATTR: + case IORING_OP_FSETXATTR: + case IORING_OP_GETXATTR: + case IORING_OP_FGETXATTR: + __io_xattr_finish(req); + break; } } if ((req->flags & REQ_F_POLLED) && req->apoll) { @@ -7108,15 +8279,11 @@ static bool io_assign_file(struct io_kiocb *req, unsigned int issue_flags) return true; if (req->flags & REQ_F_FIXED_FILE) - req->file = io_file_get_fixed(req, req->fd, issue_flags); + req->file = io_file_get_fixed(req, req->cqe.fd, issue_flags); else - req->file = io_file_get_normal(req, req->fd); - if (req->file) - return true; + req->file = io_file_get_normal(req, req->cqe.fd); - req_set_fail(req); - req->result = -EBADF; - return false; + return !!req->file; } static int io_issue_sqe(struct io_kiocb *req, unsigned int issue_flags) @@ -7246,6 +8413,24 @@ static int io_issue_sqe(struct io_kiocb *req, unsigned int issue_flags) case IORING_OP_MSG_RING: ret = io_msg_ring(req, issue_flags); break; + case IORING_OP_FSETXATTR: + ret = io_fsetxattr(req, issue_flags); + break; + case IORING_OP_SETXATTR: + ret = io_setxattr(req, issue_flags); + break; + case IORING_OP_FGETXATTR: + ret = io_fgetxattr(req, issue_flags); + break; + case IORING_OP_GETXATTR: + ret = io_getxattr(req, issue_flags); + break; + case IORING_OP_SOCKET: + ret = io_socket(req, issue_flags); + break; + case IORING_OP_URING_CMD: + ret = io_uring_cmd(req, issue_flags); + break; default: ret = -EINVAL; break; @@ -7279,7 +8464,6 @@ static void io_wq_submit_work(struct io_wq_work *work) const struct io_op_def *def = &io_op_defs[req->opcode]; unsigned int issue_flags = IO_URING_F_UNLOCKED; bool needs_poll = false; - struct io_kiocb *timeout; int ret = 0, err = -ECANCELED; /* one will be dropped by ->io_free_work() after returning to io-wq */ @@ -7288,10 +8472,7 @@ static void io_wq_submit_work(struct io_wq_work *work) else req_ref_get(req); - timeout = io_prep_linked_timeout(req); - if (timeout) - io_queue_linked_timeout(timeout); - + io_arm_ltimeout(req); /* either cancelled or io-wq is dying, so don't touch tctx->iowq */ if (work->flags & IO_WQ_WORK_CANCEL) { @@ -7324,6 +8505,8 @@ fail: * wait for request slots on the block side. */ if (!needs_poll) { + if (!(req->ctx->flags & IORING_SETUP_IOPOLL)) + break; cond_resched(); continue; } @@ -7369,8 +8552,7 @@ static inline struct file *io_file_get_fixed(struct io_kiocb *req, int fd, struct file *file = NULL; unsigned long file_ptr; - if (issue_flags & IO_URING_F_UNLOCKED) - mutex_lock(&ctx->uring_lock); + io_ring_submit_lock(ctx, issue_flags); if (unlikely((unsigned int)fd >= ctx->nr_user_files)) goto out; @@ -7381,9 +8563,9 @@ static inline struct file *io_file_get_fixed(struct io_kiocb *req, int fd, /* mask in overlapping REQ_F and FFS bits */ req->flags |= (file_ptr << REQ_F_SUPPORT_NOWAIT_BIT); io_req_set_rsrc_node(req, ctx, 0); + WARN_ON_ONCE(file && !test_bit(fd, ctx->file_table.bitmap)); out: - if (issue_flags & IO_URING_F_UNLOCKED) - mutex_unlock(&ctx->uring_lock); + io_ring_submit_unlock(ctx, issue_flags); return file; } @@ -7404,7 +8586,7 @@ static struct file *io_file_get_normal(struct io_kiocb *req, int fd) { struct file *file = fget(fd); - trace_io_uring_file_get(req->ctx, req, req->user_data, fd); + trace_io_uring_file_get(req->ctx, req, req->cqe.user_data, fd); /* we don't allow fixed io_uring files */ if (file && file->f_op == &io_uring_fops) @@ -7418,8 +8600,14 @@ static void io_req_task_link_timeout(struct io_kiocb *req, bool *locked) int ret = -ENOENT; if (prev) { - if (!(req->task->flags & PF_EXITING)) - ret = io_try_cancel_userdata(req, prev->user_data); + if (!(req->task->flags & PF_EXITING)) { + struct io_cancel_data cd = { + .ctx = req->ctx, + .data = prev->cqe.user_data, + }; + + ret = io_try_cancel(req, &cd); + } io_req_complete_post(req, ret ?: -ETIME, 0); io_put_req(prev); } else { @@ -7453,7 +8641,7 @@ static enum hrtimer_restart io_link_timeout_fn(struct hrtimer *timer) spin_unlock_irqrestore(&ctx->timeout_lock, flags); req->io_task_work.func = io_req_task_link_timeout; - io_req_task_work_add(req, false); + io_req_task_work_add(req); return HRTIMER_NORESTART; } @@ -7479,10 +8667,17 @@ static void io_queue_linked_timeout(struct io_kiocb *req) io_put_req(req); } -static void io_queue_sqe_arm_apoll(struct io_kiocb *req) +static void io_queue_async(struct io_kiocb *req, int ret) __must_hold(&req->ctx->uring_lock) { - struct io_kiocb *linked_timeout = io_prep_linked_timeout(req); + struct io_kiocb *linked_timeout; + + if (ret != -EAGAIN || (req->flags & REQ_F_NOWAIT)) { + io_req_complete_failed(req, ret); + return; + } + + linked_timeout = io_prep_linked_timeout(req); switch (io_arm_poll_handler(req, 0)) { case IO_APOLL_READY: @@ -7493,7 +8688,7 @@ static void io_queue_sqe_arm_apoll(struct io_kiocb *req) * Queued up for async execution, worker will release * submit reference when the iocb is actually submitted. */ - io_queue_async_work(req, NULL); + io_queue_iowq(req, NULL); break; case IO_APOLL_OK: break; @@ -7503,10 +8698,9 @@ static void io_queue_sqe_arm_apoll(struct io_kiocb *req) io_queue_linked_timeout(linked_timeout); } -static inline void __io_queue_sqe(struct io_kiocb *req) +static inline void io_queue_sqe(struct io_kiocb *req) __must_hold(&req->ctx->uring_lock) { - struct io_kiocb *linked_timeout; int ret; ret = io_issue_sqe(req, IO_URING_F_NONBLOCK|IO_URING_F_COMPLETE_DEFER); @@ -7519,22 +8713,23 @@ static inline void __io_queue_sqe(struct io_kiocb *req) * We async punt it if the file wasn't marked NOWAIT, or if the file * doesn't support non-blocking read/write attempts */ - if (likely(!ret)) { - linked_timeout = io_prep_linked_timeout(req); - if (linked_timeout) - io_queue_linked_timeout(linked_timeout); - } else if (ret == -EAGAIN && !(req->flags & REQ_F_NOWAIT)) { - io_queue_sqe_arm_apoll(req); - } else { - io_req_complete_failed(req, ret); - } + if (likely(!ret)) + io_arm_ltimeout(req); + else + io_queue_async(req, ret); } static void io_queue_sqe_fallback(struct io_kiocb *req) __must_hold(&req->ctx->uring_lock) { - if (req->flags & REQ_F_FAIL) { - io_req_complete_fail_submit(req); + if (unlikely(req->flags & REQ_F_FAIL)) { + /* + * We don't submit, fail them all, for that replace hardlinks + * with normal links. Extra REQ_F_LINK is tolerated. + */ + req->flags &= ~REQ_F_HARDLINK; + req->flags |= REQ_F_LINK; + io_req_complete_failed(req, req->cqe.res); } else if (unlikely(req->ctx->drain_active)) { io_drain_req(req); } else { @@ -7543,19 +8738,10 @@ static void io_queue_sqe_fallback(struct io_kiocb *req) if (unlikely(ret)) io_req_complete_failed(req, ret); else - io_queue_async_work(req, NULL); + io_queue_iowq(req, NULL); } } -static inline void io_queue_sqe(struct io_kiocb *req) - __must_hold(&req->ctx->uring_lock) -{ - if (likely(!(req->flags & (REQ_F_FORCE_ASYNC | REQ_F_FAIL)))) - __io_queue_sqe(req); - else - io_queue_sqe_fallback(req); -} - /* * Check SQE restrictions (opcode and flags). * @@ -7610,9 +8796,9 @@ static int io_init_req(struct io_ring_ctx *ctx, struct io_kiocb *req, req->opcode = opcode = READ_ONCE(sqe->opcode); /* same numerical values with corresponding REQ_F_*, safe to copy */ req->flags = sqe_flags = READ_ONCE(sqe->flags); - req->user_data = READ_ONCE(sqe->user_data); + req->cqe.user_data = READ_ONCE(sqe->user_data); req->file = NULL; - req->fixed_rsrc_refs = NULL; + req->rsrc_node = NULL; req->task = current; if (unlikely(opcode >= IORING_OP_LAST)) { @@ -7623,9 +8809,11 @@ static int io_init_req(struct io_ring_ctx *ctx, struct io_kiocb *req, /* enforce forwards compatibility on users */ if (sqe_flags & ~SQE_VALID_FLAGS) return -EINVAL; - if ((sqe_flags & IOSQE_BUFFER_SELECT) && - !io_op_defs[opcode].buffer_select) - return -EOPNOTSUPP; + if (sqe_flags & IOSQE_BUFFER_SELECT) { + if (!io_op_defs[opcode].buffer_select) + return -EOPNOTSUPP; + req->buf_index = READ_ONCE(sqe->buf_group); + } if (sqe_flags & IOSQE_CQE_SKIP_SUCCESS) ctx->drain_disabled = true; if (sqe_flags & IOSQE_IO_DRAIN) { @@ -7648,10 +8836,15 @@ static int io_init_req(struct io_ring_ctx *ctx, struct io_kiocb *req, } } + if (!io_op_defs[opcode].ioprio && sqe->ioprio) + return -EINVAL; + if (!io_op_defs[opcode].iopoll && (ctx->flags & IORING_SETUP_IOPOLL)) + return -EINVAL; + if (io_op_defs[opcode].needs_file) { struct io_submit_state *state = &ctx->submit_state; - req->fd = READ_ONCE(sqe->fd); + req->cqe.fd = READ_ONCE(sqe->fd); /* * Plug now if we have more than 2 IO left after this, and the @@ -7683,7 +8876,44 @@ static int io_init_req(struct io_ring_ctx *ctx, struct io_kiocb *req, return io_req_prep(req, sqe); } -static int io_submit_sqe(struct io_ring_ctx *ctx, struct io_kiocb *req, +static __cold int io_submit_fail_init(const struct io_uring_sqe *sqe, + struct io_kiocb *req, int ret) +{ + struct io_ring_ctx *ctx = req->ctx; + struct io_submit_link *link = &ctx->submit_state.link; + struct io_kiocb *head = link->head; + + trace_io_uring_req_failed(sqe, ctx, req, ret); + + /* + * Avoid breaking links in the middle as it renders links with SQPOLL + * unusable. Instead of failing eagerly, continue assembling the link if + * applicable and mark the head with REQ_F_FAIL. The link flushing code + * should find the flag and handle the rest. + */ + req_fail_link_node(req, ret); + if (head && !(head->flags & REQ_F_FAIL)) + req_fail_link_node(head, -ECANCELED); + + if (!(req->flags & IO_REQ_LINK_FLAGS)) { + if (head) { + link->last->link = req; + link->head = NULL; + req = head; + } + io_queue_sqe_fallback(req); + return ret; + } + + if (head) + link->last->link = req; + else + link->head = req; + link->last = req; + return 0; +} + +static inline int io_submit_sqe(struct io_ring_ctx *ctx, struct io_kiocb *req, const struct io_uring_sqe *sqe) __must_hold(&ctx->uring_lock) { @@ -7691,35 +8921,11 @@ static int io_submit_sqe(struct io_ring_ctx *ctx, struct io_kiocb *req, int ret; ret = io_init_req(ctx, req, sqe); - if (unlikely(ret)) { - trace_io_uring_req_failed(sqe, ctx, req, ret); - - /* fail even hard links since we don't submit */ - if (link->head) { - /* - * we can judge a link req is failed or cancelled by if - * REQ_F_FAIL is set, but the head is an exception since - * it may be set REQ_F_FAIL because of other req's failure - * so let's leverage req->result to distinguish if a head - * is set REQ_F_FAIL because of its failure or other req's - * failure so that we can set the correct ret code for it. - * init result here to avoid affecting the normal path. - */ - if (!(link->head->flags & REQ_F_FAIL)) - req_fail_link_node(link->head, -ECANCELED); - } else if (!(req->flags & (REQ_F_LINK | REQ_F_HARDLINK))) { - /* - * the current req is a normal req, we should return - * error and thus break the submittion loop. - */ - io_req_complete_failed(req, ret); - return ret; - } - req_fail_link_node(req, ret); - } + if (unlikely(ret)) + return io_submit_fail_init(sqe, req, ret); /* don't need @sqe from now on */ - trace_io_uring_submit_sqe(ctx, req, req->user_data, req->opcode, + trace_io_uring_submit_sqe(ctx, req, req->cqe.user_data, req->opcode, req->flags, true, ctx->flags & IORING_SETUP_SQPOLL); @@ -7730,29 +8936,32 @@ static int io_submit_sqe(struct io_ring_ctx *ctx, struct io_kiocb *req, * submitted sync once the chain is complete. If none of those * conditions are true (normal request), then just queue it. */ - if (link->head) { - struct io_kiocb *head = link->head; - - if (!(req->flags & REQ_F_FAIL)) { - ret = io_req_prep_async(req); - if (unlikely(ret)) { - req_fail_link_node(req, ret); - if (!(head->flags & REQ_F_FAIL)) - req_fail_link_node(head, -ECANCELED); - } - } - trace_io_uring_link(ctx, req, head); + if (unlikely(link->head)) { + ret = io_req_prep_async(req); + if (unlikely(ret)) + return io_submit_fail_init(sqe, req, ret); + + trace_io_uring_link(ctx, req, link->head); link->last->link = req; link->last = req; - if (req->flags & (REQ_F_LINK | REQ_F_HARDLINK)) + if (req->flags & IO_REQ_LINK_FLAGS) return 0; - /* last request of a link, enqueue the link */ + /* last request of the link, flush it */ + req = link->head; link->head = NULL; - req = head; - } else if (req->flags & (REQ_F_LINK | REQ_F_HARDLINK)) { - link->head = req; - link->last = req; + if (req->flags & (REQ_F_FORCE_ASYNC | REQ_F_FAIL)) + goto fallback; + + } else if (unlikely(req->flags & (IO_REQ_LINK_FLAGS | + REQ_F_FORCE_ASYNC | REQ_F_FAIL))) { + if (req->flags & IO_REQ_LINK_FLAGS) { + link->head = req; + link->last = req; + } else { +fallback: + io_queue_sqe_fallback(req); + } return 0; } @@ -7767,8 +8976,8 @@ static void io_submit_state_end(struct io_ring_ctx *ctx) { struct io_submit_state *state = &ctx->submit_state; - if (state->link.head) - io_queue_sqe(state->link.head); + if (unlikely(state->link.head)) + io_queue_sqe_fallback(state->link.head); /* flush only after queuing links as they can generate completions */ io_submit_flush_completions(ctx); if (state->plug_started) @@ -7822,8 +9031,12 @@ static const struct io_uring_sqe *io_get_sqe(struct io_ring_ctx *ctx) * though the application is the one updating it. */ head = READ_ONCE(ctx->sq_array[sq_idx]); - if (likely(head < ctx->sq_entries)) + if (likely(head < ctx->sq_entries)) { + /* double index for 128-byte SQEs, twice as long */ + if (ctx->flags & IORING_SETUP_SQE128) + head <<= 1; return &ctx->sq_sqes[head]; + } /* drop invalid entries */ ctx->cq_extra--; @@ -7836,54 +9049,52 @@ static int io_submit_sqes(struct io_ring_ctx *ctx, unsigned int nr) __must_hold(&ctx->uring_lock) { unsigned int entries = io_sqring_entries(ctx); - int submitted = 0; + unsigned int left; + int ret; if (unlikely(!entries)) return 0; /* make sure SQ entry isn't read before tail */ - nr = min3(nr, ctx->sq_entries, entries); - io_get_task_refs(nr); + ret = left = min3(nr, ctx->sq_entries, entries); + io_get_task_refs(left); + io_submit_state_start(&ctx->submit_state, left); - io_submit_state_start(&ctx->submit_state, nr); do { const struct io_uring_sqe *sqe; struct io_kiocb *req; - if (unlikely(!io_alloc_req_refill(ctx))) { - if (!submitted) - submitted = -EAGAIN; + if (unlikely(!io_alloc_req_refill(ctx))) break; - } req = io_alloc_req(ctx); sqe = io_get_sqe(ctx); if (unlikely(!sqe)) { - wq_stack_add_head(&req->comp_list, &ctx->submit_state.free_list); + io_req_add_to_cache(req, ctx); break; } - /* will complete beyond this point, count as submitted */ - submitted++; - if (io_submit_sqe(ctx, req, sqe)) { - /* - * Continue submitting even for sqe failure if the - * ring was setup with IORING_SETUP_SUBMIT_ALL - */ - if (!(ctx->flags & IORING_SETUP_SUBMIT_ALL)) - break; - } - } while (submitted < nr); - if (unlikely(submitted != nr)) { - int ref_used = (submitted == -EAGAIN) ? 0 : submitted; - int unused = nr - ref_used; + /* + * Continue submitting even for sqe failure if the + * ring was setup with IORING_SETUP_SUBMIT_ALL + */ + if (unlikely(io_submit_sqe(ctx, req, sqe)) && + !(ctx->flags & IORING_SETUP_SUBMIT_ALL)) { + left--; + break; + } + } while (--left); - current->io_uring->cached_refs += unused; + if (unlikely(left)) { + ret -= left; + /* try again if it submitted nothing and can't allocate a req */ + if (!ret && io_req_cache_empty(ctx)) + ret = -EAGAIN; + current->io_uring->cached_refs += left; } io_submit_state_end(ctx); /* Commit SQ ring head once we've consumed and submitted all SQEs */ io_commit_sqring(ctx); - - return submitted; + return ret; } static inline bool io_sqd_events_pending(struct io_sq_data *sqd) @@ -7891,23 +9102,6 @@ static inline bool io_sqd_events_pending(struct io_sq_data *sqd) return READ_ONCE(sqd->state); } -static inline void io_ring_set_wakeup_flag(struct io_ring_ctx *ctx) -{ - /* Tell userspace we may need a wakeup call */ - spin_lock(&ctx->completion_lock); - WRITE_ONCE(ctx->rings->sq_flags, - ctx->rings->sq_flags | IORING_SQ_NEED_WAKEUP); - spin_unlock(&ctx->completion_lock); -} - -static inline void io_ring_clear_wakeup_flag(struct io_ring_ctx *ctx) -{ - spin_lock(&ctx->completion_lock); - WRITE_ONCE(ctx->rings->sq_flags, - ctx->rings->sq_flags & ~IORING_SQ_NEED_WAKEUP); - spin_unlock(&ctx->completion_lock); -} - static int __io_sq_thread(struct io_ring_ctx *ctx, bool cap_entries) { unsigned int to_submit; @@ -8023,8 +9217,8 @@ static int io_sq_thread(void *data) bool needs_sched = true; list_for_each_entry(ctx, &sqd->ctx_list, sqd_list) { - io_ring_set_wakeup_flag(ctx); - + atomic_or(IORING_SQ_NEED_WAKEUP, + &ctx->rings->sq_flags); if ((ctx->flags & IORING_SETUP_IOPOLL) && !wq_list_empty(&ctx->iopoll_list)) { needs_sched = false; @@ -8035,7 +9229,7 @@ static int io_sq_thread(void *data) * Ensure the store of the wakeup flag is not * reordered with the load of the SQ tail */ - smp_mb(); + smp_mb__after_atomic(); if (io_sqring_entries(ctx)) { needs_sched = false; @@ -8049,7 +9243,8 @@ static int io_sq_thread(void *data) mutex_lock(&sqd->lock); } list_for_each_entry(ctx, &sqd->ctx_list, sqd_list) - io_ring_clear_wakeup_flag(ctx); + atomic_andnot(IORING_SQ_NEED_WAKEUP, + &ctx->rings->sq_flags); } finish_wait(&sqd->wait, &wait); @@ -8059,7 +9254,7 @@ static int io_sq_thread(void *data) io_uring_cancel_generic(true, sqd); sqd->thread = NULL; list_for_each_entry(ctx, &sqd->ctx_list, sqd_list) - io_ring_set_wakeup_flag(ctx); + atomic_or(IORING_SQ_NEED_WAKEUP, &ctx->rings->sq_flags); io_run_task_work(); mutex_unlock(&sqd->lock); @@ -8099,7 +9294,8 @@ static int io_wake_function(struct wait_queue_entry *curr, unsigned int mode, * Cannot safely flush overflowed CQEs from here, ensure we wake up * the task, and the next invocation will do it. */ - if (io_should_wake(iowq) || test_bit(0, &iowq->ctx->check_cq_overflow)) + if (io_should_wake(iowq) || + test_bit(IO_CHECK_CQ_OVERFLOW_BIT, &iowq->ctx->check_cq)) return autoremove_wake_function(curr, mode, wake_flags, key); return -1; } @@ -8121,15 +9317,18 @@ static inline int io_cqring_wait_schedule(struct io_ring_ctx *ctx, ktime_t timeout) { int ret; + unsigned long check_cq; /* make sure we run task_work before checking for signals */ ret = io_run_task_work_sig(); if (ret || io_should_wake(iowq)) return ret; + check_cq = READ_ONCE(ctx->check_cq); /* let the caller flush overflows, retry */ - if (test_bit(0, &ctx->check_cq_overflow)) + if (check_cq & BIT(IO_CHECK_CQ_OVERFLOW_BIT)) return 1; - + if (unlikely(check_cq & BIT(IO_CHECK_CQ_DROPPED_BIT))) + return -EBADR; if (!schedule_hrtimeout(&timeout, HRTIMER_MODE_ABS)) return -ETIME; return 1; @@ -8194,10 +9393,10 @@ static int io_cqring_wait(struct io_ring_ctx *ctx, int min_events, prepare_to_wait_exclusive(&ctx->cq_wait, &iowq.wq, TASK_INTERRUPTIBLE); ret = io_cqring_wait_schedule(ctx, &iowq, timeout); - finish_wait(&ctx->cq_wait, &iowq.wq); cond_resched(); } while (ret > 0); + finish_wait(&ctx->cq_wait, &iowq.wq); restore_saved_sigmask_unless(ret == -EINTR); return READ_ONCE(rings->cq.head) == READ_ONCE(rings->cq.tail) ? ret : 0; @@ -8435,17 +9634,57 @@ static bool io_alloc_file_tables(struct io_file_table *table, unsigned nr_files) { table->files = kvcalloc(nr_files, sizeof(table->files[0]), GFP_KERNEL_ACCOUNT); - return !!table->files; + if (unlikely(!table->files)) + return false; + + table->bitmap = bitmap_zalloc(nr_files, GFP_KERNEL_ACCOUNT); + if (unlikely(!table->bitmap)) { + kvfree(table->files); + return false; + } + + return true; } static void io_free_file_tables(struct io_file_table *table) { kvfree(table->files); + bitmap_free(table->bitmap); table->files = NULL; + table->bitmap = NULL; +} + +static inline void io_file_bitmap_set(struct io_file_table *table, int bit) +{ + WARN_ON_ONCE(test_bit(bit, table->bitmap)); + __set_bit(bit, table->bitmap); + if (bit == table->alloc_hint) + table->alloc_hint++; +} + +static inline void io_file_bitmap_clear(struct io_file_table *table, int bit) +{ + __clear_bit(bit, table->bitmap); + table->alloc_hint = bit; } static void __io_sqe_files_unregister(struct io_ring_ctx *ctx) { +#if !defined(IO_URING_SCM_ALL) + int i; + + for (i = 0; i < ctx->nr_user_files; i++) { + struct file *file = io_file_from_index(ctx, i); + + if (!file) + continue; + if (io_fixed_file_slot(&ctx->file_table, i)->file_ptr & FFS_SCM) + continue; + io_file_bitmap_clear(&ctx->file_table, i); + fput(file); + } +#endif + #if defined(CONFIG_UNIX) if (ctx->ring_sock) { struct sock *sock = ctx->ring_sock->sk; @@ -8454,16 +9693,6 @@ static void __io_sqe_files_unregister(struct io_ring_ctx *ctx) while ((skb = skb_dequeue(&sock->sk_receive_queue)) != NULL) kfree_skb(skb); } -#else - int i; - - for (i = 0; i < ctx->nr_user_files; i++) { - struct file *file; - - file = io_file_from_index(ctx, i); - if (file) - fput(file); - } #endif io_free_file_tables(&ctx->file_table); io_rsrc_data_free(ctx->file_data); @@ -8608,107 +9837,66 @@ static struct io_sq_data *io_get_sq_data(struct io_uring_params *p, return sqd; } -#if defined(CONFIG_UNIX) /* * Ensure the UNIX gc is aware of our file set, so we are certain that * the io_uring can be safely unregistered on process exit, even if we have - * loops in the file referencing. + * loops in the file referencing. We account only files that can hold other + * files because otherwise they can't form a loop and so are not interesting + * for GC. */ -static int __io_sqe_files_scm(struct io_ring_ctx *ctx, int nr, int offset) +static int io_scm_file_account(struct io_ring_ctx *ctx, struct file *file) { +#if defined(CONFIG_UNIX) struct sock *sk = ctx->ring_sock->sk; + struct sk_buff_head *head = &sk->sk_receive_queue; struct scm_fp_list *fpl; struct sk_buff *skb; - int i, nr_files; - fpl = kzalloc(sizeof(*fpl), GFP_KERNEL); - if (!fpl) - return -ENOMEM; - - skb = alloc_skb(0, GFP_KERNEL); - if (!skb) { - kfree(fpl); - return -ENOMEM; - } + if (likely(!io_file_need_scm(file))) + return 0; - skb->sk = sk; + /* + * See if we can merge this file into an existing skb SCM_RIGHTS + * file set. If there's no room, fall back to allocating a new skb + * and filling it in. + */ + spin_lock_irq(&head->lock); + skb = skb_peek(head); + if (skb && UNIXCB(skb).fp->count < SCM_MAX_FD) + __skb_unlink(skb, head); + else + skb = NULL; + spin_unlock_irq(&head->lock); - nr_files = 0; - fpl->user = get_uid(current_user()); - for (i = 0; i < nr; i++) { - struct file *file = io_file_from_index(ctx, i + offset); + if (!skb) { + fpl = kzalloc(sizeof(*fpl), GFP_KERNEL); + if (!fpl) + return -ENOMEM; - if (!file) - continue; - fpl->fp[nr_files] = get_file(file); - unix_inflight(fpl->user, fpl->fp[nr_files]); - nr_files++; - } + skb = alloc_skb(0, GFP_KERNEL); + if (!skb) { + kfree(fpl); + return -ENOMEM; + } - if (nr_files) { + fpl->user = get_uid(current_user()); fpl->max = SCM_MAX_FD; - fpl->count = nr_files; + fpl->count = 0; + UNIXCB(skb).fp = fpl; + skb->sk = sk; skb->destructor = unix_destruct_scm; refcount_add(skb->truesize, &sk->sk_wmem_alloc); - skb_queue_head(&sk->sk_receive_queue, skb); - - for (i = 0; i < nr; i++) { - struct file *file = io_file_from_index(ctx, i + offset); - - if (file) - fput(file); - } - } else { - kfree_skb(skb); - free_uid(fpl->user); - kfree(fpl); - } - - return 0; -} - -/* - * If UNIX sockets are enabled, fd passing can cause a reference cycle which - * causes regular reference counting to break down. We rely on the UNIX - * garbage collection to take care of this problem for us. - */ -static int io_sqe_files_scm(struct io_ring_ctx *ctx) -{ - unsigned left, total; - int ret = 0; - - total = 0; - left = ctx->nr_user_files; - while (left) { - unsigned this_files = min_t(unsigned, left, SCM_MAX_FD); - - ret = __io_sqe_files_scm(ctx, this_files, total); - if (ret) - break; - left -= this_files; - total += this_files; - } - - if (!ret) - return 0; - - while (total < ctx->nr_user_files) { - struct file *file = io_file_from_index(ctx, total); - - if (file) - fput(file); - total++; } - return ret; -} -#else -static int io_sqe_files_scm(struct io_ring_ctx *ctx) -{ + fpl = UNIXCB(skb).fp; + fpl->fp[fpl->count++] = get_file(file); + unix_inflight(fpl->user, file); + skb_queue_head(head, skb); + fput(file); +#endif return 0; } -#endif static void io_rsrc_file_put(struct io_ring_ctx *ctx, struct io_rsrc_put *prsrc) { @@ -8719,6 +9907,11 @@ static void io_rsrc_file_put(struct io_ring_ctx *ctx, struct io_rsrc_put *prsrc) struct sk_buff *skb; int i; + if (!io_file_need_scm(file)) { + fput(file); + return; + } + __skb_queue_head_init(&list); /* @@ -8783,15 +9976,17 @@ static void __io_rsrc_put_work(struct io_rsrc_node *ref_node) list_del(&prsrc->list); if (prsrc->tag) { - bool lock_ring = ctx->flags & IORING_SETUP_IOPOLL; + if (ctx->flags & IORING_SETUP_IOPOLL) + mutex_lock(&ctx->uring_lock); - io_ring_submit_lock(ctx, lock_ring); spin_lock(&ctx->completion_lock); io_fill_cqe_aux(ctx, prsrc->tag, 0, 0); io_commit_cqring(ctx); spin_unlock(&ctx->completion_lock); io_cqring_ev_posted(ctx); - io_ring_submit_unlock(ctx, lock_ring); + + if (ctx->flags & IORING_SETUP_IOPOLL) + mutex_unlock(&ctx->uring_lock); } rsrc_data->do_put(ctx, prsrc); @@ -8845,27 +10040,31 @@ static int io_sqe_files_register(struct io_ring_ctx *ctx, void __user *arg, if (ret) return ret; - ret = -ENOMEM; - if (!io_alloc_file_tables(&ctx->file_table, nr_args)) - goto out_free; + if (!io_alloc_file_tables(&ctx->file_table, nr_args)) { + io_rsrc_data_free(ctx->file_data); + ctx->file_data = NULL; + return -ENOMEM; + } for (i = 0; i < nr_args; i++, ctx->nr_user_files++) { - if (copy_from_user(&fd, &fds[i], sizeof(fd))) { + struct io_fixed_file *file_slot; + + if (fds && copy_from_user(&fd, &fds[i], sizeof(fd))) { ret = -EFAULT; - goto out_fput; + goto fail; } /* allow sparse sets */ - if (fd == -1) { + if (!fds || fd == -1) { ret = -EINVAL; if (unlikely(*io_get_tag_slot(ctx->file_data, i))) - goto out_fput; + goto fail; continue; } file = fget(fd); ret = -EBADF; if (unlikely(!file)) - goto out_fput; + goto fail; /* * Don't allow io_uring instances to be registered. If UNIX @@ -8876,74 +10075,23 @@ static int io_sqe_files_register(struct io_ring_ctx *ctx, void __user *arg, */ if (file->f_op == &io_uring_fops) { fput(file); - goto out_fput; + goto fail; } - io_fixed_file_set(io_fixed_file_slot(&ctx->file_table, i), file); - } - - ret = io_sqe_files_scm(ctx); - if (ret) { - __io_sqe_files_unregister(ctx); - return ret; - } - - io_rsrc_node_switch(ctx, NULL); - return ret; -out_fput: - for (i = 0; i < ctx->nr_user_files; i++) { - file = io_file_from_index(ctx, i); - if (file) + ret = io_scm_file_account(ctx, file); + if (ret) { fput(file); - } - io_free_file_tables(&ctx->file_table); - ctx->nr_user_files = 0; -out_free: - io_rsrc_data_free(ctx->file_data); - ctx->file_data = NULL; - return ret; -} - -static int io_sqe_file_register(struct io_ring_ctx *ctx, struct file *file, - int index) -{ -#if defined(CONFIG_UNIX) - struct sock *sock = ctx->ring_sock->sk; - struct sk_buff_head *head = &sock->sk_receive_queue; - struct sk_buff *skb; - - /* - * See if we can merge this file into an existing skb SCM_RIGHTS - * file set. If there's no room, fall back to allocating a new skb - * and filling it in. - */ - spin_lock_irq(&head->lock); - skb = skb_peek(head); - if (skb) { - struct scm_fp_list *fpl = UNIXCB(skb).fp; - - if (fpl->count < SCM_MAX_FD) { - __skb_unlink(skb, head); - spin_unlock_irq(&head->lock); - fpl->fp[fpl->count] = get_file(file); - unix_inflight(fpl->user, fpl->fp[fpl->count]); - fpl->count++; - spin_lock_irq(&head->lock); - __skb_queue_head(head, skb); - } else { - skb = NULL; + goto fail; } - } - spin_unlock_irq(&head->lock); - - if (skb) { - fput(file); - return 0; + file_slot = io_fixed_file_slot(&ctx->file_table, i); + io_fixed_file_set(file_slot, file); + io_file_bitmap_set(&ctx->file_table, i); } - return __io_sqe_files_scm(ctx, 1, index); -#else + io_rsrc_node_switch(ctx, NULL); return 0; -#endif +fail: + __io_sqe_files_unregister(ctx); + return ret; } static int io_queue_rsrc_removal(struct io_rsrc_data *data, unsigned idx, @@ -8967,12 +10115,11 @@ static int io_install_fixed_file(struct io_kiocb *req, struct file *file, unsigned int issue_flags, u32 slot_index) { struct io_ring_ctx *ctx = req->ctx; - bool needs_lock = issue_flags & IO_URING_F_UNLOCKED; bool needs_switch = false; struct io_fixed_file *file_slot; int ret = -EBADF; - io_ring_submit_lock(ctx, needs_lock); + io_ring_submit_lock(ctx, issue_flags); if (file->f_op == &io_uring_fops) goto err; ret = -ENXIO; @@ -8998,22 +10145,20 @@ static int io_install_fixed_file(struct io_kiocb *req, struct file *file, if (ret) goto err; file_slot->file_ptr = 0; + io_file_bitmap_clear(&ctx->file_table, slot_index); needs_switch = true; } - *io_get_tag_slot(ctx->file_data, slot_index) = 0; - io_fixed_file_set(file_slot, file); - ret = io_sqe_file_register(ctx, file, slot_index); - if (ret) { - file_slot->file_ptr = 0; - goto err; + ret = io_scm_file_account(ctx, file); + if (!ret) { + *io_get_tag_slot(ctx->file_data, slot_index) = 0; + io_fixed_file_set(file_slot, file); + io_file_bitmap_set(&ctx->file_table, slot_index); } - - ret = 0; err: if (needs_switch) io_rsrc_node_switch(ctx, ctx->file_data); - io_ring_submit_unlock(ctx, needs_lock); + io_ring_submit_unlock(ctx, issue_flags); if (ret) fput(file); return ret; @@ -9023,12 +10168,11 @@ static int io_close_fixed(struct io_kiocb *req, unsigned int issue_flags) { unsigned int offset = req->close.file_slot - 1; struct io_ring_ctx *ctx = req->ctx; - bool needs_lock = issue_flags & IO_URING_F_UNLOCKED; struct io_fixed_file *file_slot; struct file *file; int ret; - io_ring_submit_lock(ctx, needs_lock); + io_ring_submit_lock(ctx, issue_flags); ret = -ENXIO; if (unlikely(!ctx->file_data)) goto out; @@ -9051,10 +10195,11 @@ static int io_close_fixed(struct io_kiocb *req, unsigned int issue_flags) goto out; file_slot->file_ptr = 0; + io_file_bitmap_clear(&ctx->file_table, offset); io_rsrc_node_switch(ctx, ctx->file_data); ret = 0; out: - io_ring_submit_unlock(ctx, needs_lock); + io_ring_submit_unlock(ctx, issue_flags); return ret; } @@ -9100,6 +10245,7 @@ static int __io_sqe_files_update(struct io_ring_ctx *ctx, if (err) break; file_slot->file_ptr = 0; + io_file_bitmap_clear(&ctx->file_table, i); needs_switch = true; } if (fd != -1) { @@ -9121,14 +10267,14 @@ static int __io_sqe_files_update(struct io_ring_ctx *ctx, err = -EBADF; break; } - *io_get_tag_slot(data, i) = tag; - io_fixed_file_set(file_slot, file); - err = io_sqe_file_register(ctx, file, i); + err = io_scm_file_account(ctx, file); if (err) { - file_slot->file_ptr = 0; fput(file); break; } + *io_get_tag_slot(data, i) = tag; + io_fixed_file_set(file_slot, file); + io_file_bitmap_set(&ctx->file_table, i); } } @@ -9208,7 +10354,7 @@ static __cold int io_uring_alloc_task_context(struct task_struct *task, task->io_uring = tctx; spin_lock_init(&tctx->task_lock); INIT_WQ_LIST(&tctx->task_list); - INIT_WQ_LIST(&tctx->prior_task_list); + INIT_WQ_LIST(&tctx->prio_task_list); init_task_work(&tctx->task_work, tctx_task_work); return 0; } @@ -9386,8 +10532,8 @@ static void *io_mem_alloc(size_t size) return (void *) __get_free_pages(gfp, get_order(size)); } -static unsigned long rings_size(unsigned sq_entries, unsigned cq_entries, - size_t *sq_offset) +static unsigned long rings_size(struct io_ring_ctx *ctx, unsigned int sq_entries, + unsigned int cq_entries, size_t *sq_offset) { struct io_rings *rings; size_t off, sq_array_size; @@ -9395,6 +10541,10 @@ static unsigned long rings_size(unsigned sq_entries, unsigned cq_entries, off = struct_size(rings, cqes, cq_entries); if (off == SIZE_MAX) return SIZE_MAX; + if (ctx->flags & IORING_SETUP_CQE32) { + if (check_shl_overflow(off, 1, &off)) + return SIZE_MAX; + } #ifdef CONFIG_SMP off = ALIGN(off, SMP_CACHE_BYTES); @@ -9556,30 +10706,18 @@ static int io_buffer_account_pin(struct io_ring_ctx *ctx, struct page **pages, return ret; } -static int io_sqe_buffer_register(struct io_ring_ctx *ctx, struct iovec *iov, - struct io_mapped_ubuf **pimu, - struct page **last_hpage) +static struct page **io_pin_pages(unsigned long ubuf, unsigned long len, + int *npages) { - struct io_mapped_ubuf *imu = NULL; + unsigned long start, end, nr_pages; struct vm_area_struct **vmas = NULL; struct page **pages = NULL; - unsigned long off, start, end, ubuf; - size_t size; - int ret, pret, nr_pages, i; + int i, pret, ret = -ENOMEM; - if (!iov->iov_base) { - *pimu = ctx->dummy_ubuf; - return 0; - } - - ubuf = (unsigned long) iov->iov_base; - end = (ubuf + iov->iov_len + PAGE_SIZE - 1) >> PAGE_SHIFT; + end = (ubuf + len + PAGE_SIZE - 1) >> PAGE_SHIFT; start = ubuf >> PAGE_SHIFT; nr_pages = end - start; - *pimu = NULL; - ret = -ENOMEM; - pages = kvmalloc_array(nr_pages, sizeof(struct page *), GFP_KERNEL); if (!pages) goto done; @@ -9589,10 +10727,6 @@ static int io_sqe_buffer_register(struct io_ring_ctx *ctx, struct iovec *iov, if (!vmas) goto done; - imu = kvmalloc(struct_size(imu, bvec, nr_pages), GFP_KERNEL); - if (!imu) - goto done; - ret = 0; mmap_read_lock(current->mm); pret = pin_user_pages(ubuf, nr_pages, FOLL_WRITE | FOLL_LONGTERM, @@ -9610,6 +10744,7 @@ static int io_sqe_buffer_register(struct io_ring_ctx *ctx, struct iovec *iov, break; } } + *npages = nr_pages; } else { ret = pret < 0 ? pret : -EFAULT; } @@ -9623,14 +10758,53 @@ static int io_sqe_buffer_register(struct io_ring_ctx *ctx, struct iovec *iov, unpin_user_pages(pages, pret); goto done; } + ret = 0; +done: + kvfree(vmas); + if (ret < 0) { + kvfree(pages); + pages = ERR_PTR(ret); + } + return pages; +} + +static int io_sqe_buffer_register(struct io_ring_ctx *ctx, struct iovec *iov, + struct io_mapped_ubuf **pimu, + struct page **last_hpage) +{ + struct io_mapped_ubuf *imu = NULL; + struct page **pages = NULL; + unsigned long off; + size_t size; + int ret, nr_pages, i; + + if (!iov->iov_base) { + *pimu = ctx->dummy_ubuf; + return 0; + } - ret = io_buffer_account_pin(ctx, pages, pret, imu, last_hpage); + *pimu = NULL; + ret = -ENOMEM; + + pages = io_pin_pages((unsigned long) iov->iov_base, iov->iov_len, + &nr_pages); + if (IS_ERR(pages)) { + ret = PTR_ERR(pages); + pages = NULL; + goto done; + } + + imu = kvmalloc(struct_size(imu, bvec, nr_pages), GFP_KERNEL); + if (!imu) + goto done; + + ret = io_buffer_account_pin(ctx, pages, nr_pages, imu, last_hpage); if (ret) { - unpin_user_pages(pages, pret); + unpin_user_pages(pages, nr_pages); goto done; } - off = ubuf & ~PAGE_MASK; + off = (unsigned long) iov->iov_base & ~PAGE_MASK; size = iov->iov_len; for (i = 0; i < nr_pages; i++) { size_t vec_len; @@ -9643,8 +10817,8 @@ static int io_sqe_buffer_register(struct io_ring_ctx *ctx, struct iovec *iov, size -= vec_len; } /* store original address for later verification */ - imu->ubuf = ubuf; - imu->ubuf_end = ubuf + iov->iov_len; + imu->ubuf = (unsigned long) iov->iov_base; + imu->ubuf_end = imu->ubuf + iov->iov_len; imu->nr_bvecs = nr_pages; *pimu = imu; ret = 0; @@ -9652,7 +10826,6 @@ done: if (ret) kvfree(imu); kvfree(pages); - kvfree(vmas); return ret; } @@ -9711,12 +10884,17 @@ static int io_sqe_buffers_register(struct io_ring_ctx *ctx, void __user *arg, } for (i = 0; i < nr_args; i++, ctx->nr_user_bufs++) { - ret = io_copy_iov(ctx, &iov, arg, i); - if (ret) - break; - ret = io_buffer_validate(&iov); - if (ret) - break; + if (arg) { + ret = io_copy_iov(ctx, &iov, arg, i); + if (ret) + break; + ret = io_buffer_validate(&iov); + if (ret) + break; + } else { + memset(&iov, 0, sizeof(iov)); + } + if (!iov.iov_base && *io_get_tag_slot(data, i)) { ret = -EINVAL; break; @@ -9855,19 +11033,19 @@ static int io_eventfd_unregister(struct io_ring_ctx *ctx) static void io_destroy_buffers(struct io_ring_ctx *ctx) { + struct io_buffer_list *bl; + unsigned long index; int i; - for (i = 0; i < (1U << IO_BUFFERS_HASH_BITS); i++) { - struct list_head *list = &ctx->io_buffers[i]; - - while (!list_empty(list)) { - struct io_buffer_list *bl; + for (i = 0; i < BGID_ARRAY; i++) { + if (!ctx->io_bl) + break; + __io_remove_buffers(ctx, &ctx->io_bl[i], -1U); + } - bl = list_first_entry(list, struct io_buffer_list, list); - __io_remove_buffers(ctx, bl, -1U); - list_del(&bl->list); - kfree(bl); - } + xa_for_each(&ctx->io_bl_xa, index, bl) { + xa_erase(&ctx->io_bl_xa, bl->bgid); + __io_remove_buffers(ctx, bl, -1U); } while (!list_empty(&ctx->io_buffers_pages)) { @@ -9887,7 +11065,7 @@ static void io_req_caches_free(struct io_ring_ctx *ctx) mutex_lock(&ctx->uring_lock); io_flush_cached_locked_reqs(ctx, state); - while (state->free_list.next) { + while (!io_req_cache_empty(ctx)) { struct io_wq_work_node *node; struct io_kiocb *req; @@ -9976,7 +11154,8 @@ static __cold void io_ring_ctx_free(struct io_ring_ctx *ctx) io_wq_put_hash(ctx->hash_map); kfree(ctx->cancel_hash); kfree(ctx->dummy_ubuf); - kfree(ctx->io_buffers); + kfree(ctx->io_bl); + xa_destroy(&ctx->io_bl_xa); kfree(ctx); } @@ -10007,7 +11186,8 @@ static __poll_t io_uring_poll(struct file *file, poll_table *wait) * Users may get EPOLLIN meanwhile seeing nothing in cqring, this * pushs them to do the flush. */ - if (io_cqring_events(ctx) || test_bit(0, &ctx->check_cq_overflow)) + if (io_cqring_events(ctx) || + test_bit(IO_CHECK_CQ_OVERFLOW_BIT, &ctx->check_cq)) mask |= EPOLLIN | EPOLLRDNORM; return mask; @@ -10139,8 +11319,7 @@ static __cold bool io_kill_timeouts(struct io_ring_ctx *ctx, } } spin_unlock_irq(&ctx->timeout_lock); - if (canceled != 0) - io_commit_cqring(ctx); + io_commit_cqring(ctx); spin_unlock(&ctx->completion_lock); if (canceled != 0) io_cqring_ev_posted(ctx); @@ -10160,11 +11339,13 @@ static __cold void io_ring_ctx_wait_and_kill(struct io_ring_ctx *ctx) io_unregister_personality(ctx, index); mutex_unlock(&ctx->uring_lock); - io_kill_timeouts(ctx, NULL, true); - io_poll_remove_all(ctx, NULL, true); - - /* if we failed setting up the ctx, we might not have any rings */ - io_iopoll_try_reap_events(ctx); + /* failed during ring init, it couldn't have issued any requests */ + if (ctx->rings) { + io_kill_timeouts(ctx, NULL, true); + io_poll_remove_all(ctx, NULL, true); + /* if we failed setting up the ctx, we might not have any rings */ + io_iopoll_try_reap_events(ctx); + } INIT_WORK(&ctx->exit_work, io_ring_exit_work); /* @@ -10256,6 +11437,10 @@ static __cold void io_uring_try_cancel_requests(struct io_ring_ctx *ctx, struct io_task_cancel cancel = { .task = task, .all = cancel_all, }; struct io_uring_task *tctx = task ? task->io_uring : NULL; + /* failed during ring init, it couldn't have issued any requests */ + if (!ctx->rings) + return; + while (1) { enum io_wq_cancel cret; bool ret = false; @@ -10701,6 +11886,19 @@ static int io_sqpoll_wait_sq(struct io_ring_ctx *ctx) return 0; } +static int io_validate_ext_arg(unsigned flags, const void __user *argp, size_t argsz) +{ + if (flags & IORING_ENTER_EXT_ARG) { + struct io_uring_getevents_arg arg; + + if (argsz != sizeof(arg)) + return -EINVAL; + if (copy_from_user(&arg, argp, sizeof(arg))) + return -EFAULT; + } + return 0; +} + static int io_get_ext_arg(unsigned flags, const void __user *argp, size_t *argsz, struct __kernel_timespec __user **ts, const sigset_t __user **sig) @@ -10738,7 +11936,6 @@ SYSCALL_DEFINE6(io_uring_enter, unsigned int, fd, u32, to_submit, size_t, argsz) { struct io_ring_ctx *ctx; - int submitted = 0; struct fd f; long ret; @@ -10801,39 +11998,64 @@ SYSCALL_DEFINE6(io_uring_enter, unsigned int, fd, u32, to_submit, if (ret) goto out; } - submitted = to_submit; + ret = to_submit; } else if (to_submit) { ret = io_uring_add_tctx_node(ctx); if (unlikely(ret)) goto out; - mutex_lock(&ctx->uring_lock); - submitted = io_submit_sqes(ctx, to_submit); - mutex_unlock(&ctx->uring_lock); - if (submitted != to_submit) + mutex_lock(&ctx->uring_lock); + ret = io_submit_sqes(ctx, to_submit); + if (ret != to_submit) { + mutex_unlock(&ctx->uring_lock); goto out; + } + if ((flags & IORING_ENTER_GETEVENTS) && ctx->syscall_iopoll) + goto iopoll_locked; + mutex_unlock(&ctx->uring_lock); } if (flags & IORING_ENTER_GETEVENTS) { - const sigset_t __user *sig; - struct __kernel_timespec __user *ts; - - ret = io_get_ext_arg(flags, argp, &argsz, &ts, &sig); - if (unlikely(ret)) - goto out; + int ret2; + if (ctx->syscall_iopoll) { + /* + * We disallow the app entering submit/complete with + * polling, but we still need to lock the ring to + * prevent racing with polled issue that got punted to + * a workqueue. + */ + mutex_lock(&ctx->uring_lock); +iopoll_locked: + ret2 = io_validate_ext_arg(flags, argp, argsz); + if (likely(!ret2)) { + min_complete = min(min_complete, + ctx->cq_entries); + ret2 = io_iopoll_check(ctx, min_complete); + } + mutex_unlock(&ctx->uring_lock); + } else { + const sigset_t __user *sig; + struct __kernel_timespec __user *ts; + + ret2 = io_get_ext_arg(flags, argp, &argsz, &ts, &sig); + if (likely(!ret2)) { + min_complete = min(min_complete, + ctx->cq_entries); + ret2 = io_cqring_wait(ctx, min_complete, sig, + argsz, ts); + } + } - min_complete = min(min_complete, ctx->cq_entries); + if (!ret) { + ret = ret2; - /* - * When SETUP_IOPOLL and SETUP_SQPOLL are both enabled, user - * space applications don't need to do io completion events - * polling again, they can rely on io_sq_thread to do polling - * work, which can reduce cpu usage and uring_lock contention. - */ - if (ctx->flags & IORING_SETUP_IOPOLL && - !(ctx->flags & IORING_SETUP_SQPOLL)) { - ret = io_iopoll_check(ctx, min_complete); - } else { - ret = io_cqring_wait(ctx, min_complete, sig, argsz, ts); + /* + * EBADR indicates that one or more CQE were dropped. + * Once the user has been informed we can clear the bit + * as they are obviously ok with those drops. + */ + if (unlikely(ret2 == -EBADR)) + clear_bit(IO_CHECK_CQ_DROPPED_BIT, + &ctx->check_cq); } } @@ -10842,7 +12064,7 @@ out: out_fput: if (!(flags & IORING_ENTER_REGISTERED_RING)) fdput(f); - return submitted ? submitted : ret; + return ret; } #ifdef CONFIG_PROC_FS @@ -10889,10 +12111,15 @@ static __cold void __io_uring_show_fdinfo(struct io_ring_ctx *ctx, unsigned int sq_tail = READ_ONCE(r->sq.tail); unsigned int cq_head = READ_ONCE(r->cq.head); unsigned int cq_tail = READ_ONCE(r->cq.tail); + unsigned int cq_shift = 0; unsigned int sq_entries, cq_entries; bool has_lock; + bool is_cqe32 = (ctx->flags & IORING_SETUP_CQE32); unsigned int i; + if (is_cqe32) + cq_shift = 1; + /* * we may get imprecise sqe and cqe info if uring is actively running * since we get cached_sq_head and cached_cq_tail without uring_lock @@ -10925,11 +12152,18 @@ static __cold void __io_uring_show_fdinfo(struct io_ring_ctx *ctx, cq_entries = min(cq_tail - cq_head, ctx->cq_entries); for (i = 0; i < cq_entries; i++) { unsigned int entry = i + cq_head; - struct io_uring_cqe *cqe = &r->cqes[entry & cq_mask]; + struct io_uring_cqe *cqe = &r->cqes[(entry & cq_mask) << cq_shift]; - seq_printf(m, "%5u: user_data:%llu, res:%d, flag:%x\n", + if (!is_cqe32) { + seq_printf(m, "%5u: user_data:%llu, res:%d, flag:%x\n", entry & cq_mask, cqe->user_data, cqe->res, cqe->flags); + } else { + seq_printf(m, "%5u: user_data:%llu, res:%d, flag:%x, " + "extra1:%llu, extra2:%llu\n", + entry & cq_mask, cqe->user_data, cqe->res, + cqe->flags, cqe->big_cqe[0], cqe->big_cqe[1]); + } } /* @@ -11032,7 +12266,7 @@ static __cold int io_allocate_scq_urings(struct io_ring_ctx *ctx, ctx->sq_entries = p->sq_entries; ctx->cq_entries = p->cq_entries; - size = rings_size(p->sq_entries, p->cq_entries, &sq_array_offset); + size = rings_size(ctx, p->sq_entries, p->cq_entries, &sq_array_offset); if (size == SIZE_MAX) return -EOVERFLOW; @@ -11047,7 +12281,10 @@ static __cold int io_allocate_scq_urings(struct io_ring_ctx *ctx, rings->sq_ring_entries = p->sq_entries; rings->cq_ring_entries = p->cq_entries; - size = array_size(sizeof(struct io_uring_sqe), p->sq_entries); + if (p->flags & IORING_SETUP_SQE128) + size = array_size(2 * sizeof(struct io_uring_sqe), p->sq_entries); + else + size = array_size(sizeof(struct io_uring_sqe), p->sq_entries); if (size == SIZE_MAX) { io_mem_free(ctx->rings); ctx->rings = NULL; @@ -11159,11 +12396,41 @@ static __cold int io_uring_create(unsigned entries, struct io_uring_params *p, ctx = io_ring_ctx_alloc(p); if (!ctx) return -ENOMEM; + + /* + * When SETUP_IOPOLL and SETUP_SQPOLL are both enabled, user + * space applications don't need to do io completion events + * polling again, they can rely on io_sq_thread to do polling + * work, which can reduce cpu usage and uring_lock contention. + */ + if (ctx->flags & IORING_SETUP_IOPOLL && + !(ctx->flags & IORING_SETUP_SQPOLL)) + ctx->syscall_iopoll = 1; + ctx->compat = in_compat_syscall(); if (!capable(CAP_IPC_LOCK)) ctx->user = get_uid(current_user()); /* + * For SQPOLL, we just need a wakeup, always. For !SQPOLL, if + * COOP_TASKRUN is set, then IPIs are never needed by the app. + */ + ret = -EINVAL; + if (ctx->flags & IORING_SETUP_SQPOLL) { + /* IPI related flags don't make sense with SQPOLL */ + if (ctx->flags & (IORING_SETUP_COOP_TASKRUN | + IORING_SETUP_TASKRUN_FLAG)) + goto err; + ctx->notify_method = TWA_SIGNAL_NO_IPI; + } else if (ctx->flags & IORING_SETUP_COOP_TASKRUN) { + ctx->notify_method = TWA_SIGNAL_NO_IPI; + } else { + if (ctx->flags & IORING_SETUP_TASKRUN_FLAG) + goto err; + ctx->notify_method = TWA_SIGNAL; + } + + /* * This is just grabbed for accounting purposes. When a process exits, * the mm is exited and dropped before the files, hence we need to hang * on to this mm purely for the purposes of being able to unaccount @@ -11260,10 +12527,12 @@ static long io_uring_setup(u32 entries, struct io_uring_params __user *params) if (p.flags & ~(IORING_SETUP_IOPOLL | IORING_SETUP_SQPOLL | IORING_SETUP_SQ_AFF | IORING_SETUP_CQSIZE | IORING_SETUP_CLAMP | IORING_SETUP_ATTACH_WQ | - IORING_SETUP_R_DISABLED | IORING_SETUP_SUBMIT_ALL)) + IORING_SETUP_R_DISABLED | IORING_SETUP_SUBMIT_ALL | + IORING_SETUP_COOP_TASKRUN | IORING_SETUP_TASKRUN_FLAG | + IORING_SETUP_SQE128 | IORING_SETUP_CQE32)) return -EINVAL; - return io_uring_create(entries, &p, params); + return io_uring_create(entries, &p, params); } SYSCALL_DEFINE2(io_uring_setup, u32, entries, @@ -11476,14 +12745,20 @@ static __cold int io_register_rsrc(struct io_ring_ctx *ctx, void __user *arg, memset(&rr, 0, sizeof(rr)); if (copy_from_user(&rr, arg, size)) return -EFAULT; - if (!rr.nr || rr.resv || rr.resv2) + if (!rr.nr || rr.resv2) + return -EINVAL; + if (rr.flags & ~IORING_RSRC_REGISTER_SPARSE) return -EINVAL; switch (type) { case IORING_RSRC_FILE: + if (rr.flags & IORING_RSRC_REGISTER_SPARSE && rr.data) + break; return io_sqe_files_register(ctx, u64_to_user_ptr(rr.data), rr.nr, u64_to_user_ptr(rr.tags)); case IORING_RSRC_BUFFER: + if (rr.flags & IORING_RSRC_REGISTER_SPARSE && rr.data) + break; return io_sqe_buffers_register(ctx, u64_to_user_ptr(rr.data), rr.nr, u64_to_user_ptr(rr.tags)); } @@ -11618,6 +12893,85 @@ err: return ret; } +static int io_register_pbuf_ring(struct io_ring_ctx *ctx, void __user *arg) +{ + struct io_uring_buf_ring *br; + struct io_uring_buf_reg reg; + struct io_buffer_list *bl; + struct page **pages; + int nr_pages; + + if (copy_from_user(®, arg, sizeof(reg))) + return -EFAULT; + + if (reg.pad || reg.resv[0] || reg.resv[1] || reg.resv[2]) + return -EINVAL; + if (!reg.ring_addr) + return -EFAULT; + if (reg.ring_addr & ~PAGE_MASK) + return -EINVAL; + if (!is_power_of_2(reg.ring_entries)) + return -EINVAL; + + if (unlikely(reg.bgid < BGID_ARRAY && !ctx->io_bl)) { + int ret = io_init_bl_list(ctx); + if (ret) + return ret; + } + + bl = io_buffer_get_list(ctx, reg.bgid); + if (bl) { + /* if mapped buffer ring OR classic exists, don't allow */ + if (bl->buf_nr_pages || !list_empty(&bl->buf_list)) + return -EEXIST; + } else { + bl = kzalloc(sizeof(*bl), GFP_KERNEL); + if (!bl) + return -ENOMEM; + } + + pages = io_pin_pages(reg.ring_addr, + struct_size(br, bufs, reg.ring_entries), + &nr_pages); + if (IS_ERR(pages)) { + kfree(bl); + return PTR_ERR(pages); + } + + br = page_address(pages[0]); + bl->buf_pages = pages; + bl->buf_nr_pages = nr_pages; + bl->nr_entries = reg.ring_entries; + bl->buf_ring = br; + bl->mask = reg.ring_entries - 1; + io_buffer_add_list(ctx, bl, reg.bgid); + return 0; +} + +static int io_unregister_pbuf_ring(struct io_ring_ctx *ctx, void __user *arg) +{ + struct io_uring_buf_reg reg; + struct io_buffer_list *bl; + + if (copy_from_user(®, arg, sizeof(reg))) + return -EFAULT; + if (reg.pad || reg.resv[0] || reg.resv[1] || reg.resv[2]) + return -EINVAL; + + bl = io_buffer_get_list(ctx, reg.bgid); + if (!bl) + return -ENOENT; + if (!bl->buf_nr_pages) + return -EINVAL; + + __io_remove_buffers(ctx, bl, -1U); + if (bl->bgid >= BGID_ARRAY) { + xa_erase(&ctx->io_bl_xa, bl->bgid); + kfree(bl); + } + return 0; +} + static int __io_uring_register(struct io_ring_ctx *ctx, unsigned opcode, void __user *arg, unsigned nr_args) __releases(ctx->uring_lock) @@ -11643,6 +12997,9 @@ static int __io_uring_register(struct io_ring_ctx *ctx, unsigned opcode, switch (opcode) { case IORING_REGISTER_BUFFERS: + ret = -EFAULT; + if (!arg) + break; ret = io_sqe_buffers_register(ctx, arg, nr_args, NULL); break; case IORING_UNREGISTER_BUFFERS: @@ -11652,6 +13009,9 @@ static int __io_uring_register(struct io_ring_ctx *ctx, unsigned opcode, ret = io_sqe_buffers_unregister(ctx); break; case IORING_REGISTER_FILES: + ret = -EFAULT; + if (!arg) + break; ret = io_sqe_files_register(ctx, arg, nr_args, NULL); break; case IORING_UNREGISTER_FILES: @@ -11746,6 +13106,18 @@ static int __io_uring_register(struct io_ring_ctx *ctx, unsigned opcode, case IORING_UNREGISTER_RING_FDS: ret = io_ringfd_unregister(ctx, arg, nr_args); break; + case IORING_REGISTER_PBUF_RING: + ret = -EINVAL; + if (!arg || nr_args != 1) + break; + ret = io_register_pbuf_ring(ctx, arg); + break; + case IORING_UNREGISTER_PBUF_RING: + ret = -EINVAL; + if (!arg || nr_args != 1) + break; + ret = io_unregister_pbuf_ring(ctx, arg); + break; default: ret = -EINVAL; break; @@ -11822,6 +13194,7 @@ static int __init io_uring_init(void) BUILD_BUG_SQE_ELEM(42, __u16, personality); BUILD_BUG_SQE_ELEM(44, __s32, splice_fd_in); BUILD_BUG_SQE_ELEM(44, __u32, file_index); + BUILD_BUG_SQE_ELEM(48, __u64, addr3); BUILD_BUG_ON(sizeof(struct io_uring_files_update) != sizeof(struct io_uring_rsrc_update)); @@ -11830,6 +13203,10 @@ static int __init io_uring_init(void) /* ->buf_index is u16 */ BUILD_BUG_ON(IORING_MAX_REG_BUFFERS >= (1u << 16)); + BUILD_BUG_ON(BGID_ARRAY * sizeof(struct io_buffer_list) > PAGE_SIZE); + BUILD_BUG_ON(offsetof(struct io_uring_buf_ring, bufs) != 0); + BUILD_BUG_ON(offsetof(struct io_uring_buf, resv) != + offsetof(struct io_uring_buf_ring, tail)); /* should fit into one byte */ BUILD_BUG_ON(SQE_VALID_FLAGS >= (1 << 8)); @@ -11839,6 +13216,10 @@ static int __init io_uring_init(void) BUILD_BUG_ON(ARRAY_SIZE(io_op_defs) != IORING_OP_LAST); BUILD_BUG_ON(__REQ_F_LAST_BIT > 8 * sizeof(int)); + BUILD_BUG_ON(sizeof(atomic_t) != sizeof(u32)); + + BUILD_BUG_ON(sizeof(struct io_uring_cmd) > 64); + req_cachep = KMEM_CACHE(io_kiocb, SLAB_HWCACHE_ALIGN | SLAB_PANIC | SLAB_ACCOUNT); return 0; diff --git a/fs/iomap/direct-io.c b/fs/iomap/direct-io.c index b08f5dc31780..80f9b047aa1b 100644 --- a/fs/iomap/direct-io.c +++ b/fs/iomap/direct-io.c @@ -56,7 +56,8 @@ static void iomap_dio_submit_bio(const struct iomap_iter *iter, { atomic_inc(&dio->ref); - if (dio->iocb->ki_flags & IOCB_HIPRI) { + /* Sync dio can't be polled reliably */ + if ((dio->iocb->ki_flags & IOCB_HIPRI) && !is_sync_kiocb(dio->iocb)) { bio_set_polled(bio, dio->iocb); dio->submit.poll_bio = bio; } @@ -265,8 +266,7 @@ static loff_t iomap_dio_bio_iter(const struct iomap_iter *iter, * cache flushes on IO completion. */ if (!(iomap->flags & (IOMAP_F_SHARED|IOMAP_F_DIRTY)) && - (dio->flags & IOMAP_DIO_WRITE_FUA) && - blk_queue_fua(bdev_get_queue(iomap->bdev))) + (dio->flags & IOMAP_DIO_WRITE_FUA) && bdev_fua(iomap->bdev)) use_fua = true; } @@ -654,9 +654,7 @@ __iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter, if (!READ_ONCE(dio->submit.waiter)) break; - if (!dio->submit.poll_bio || - !bio_poll(dio->submit.poll_bio, NULL, 0)) - blk_io_schedule(); + blk_io_schedule(); } __set_current_state(TASK_RUNNING); } diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c index fcacafa4510d..c0cbeeaec2d1 100644 --- a/fs/jbd2/journal.c +++ b/fs/jbd2/journal.c @@ -1762,7 +1762,6 @@ static int __jbd2_journal_erase(journal_t *journal, unsigned int flags) unsigned long block, log_offset; /* logical */ unsigned long long phys_block, block_start, block_stop; /* physical */ loff_t byte_start, byte_stop, byte_count; - struct request_queue *q = bdev_get_queue(journal->j_dev); /* flags must be set to either discard or zeroout */ if ((flags & ~JBD2_JOURNAL_FLUSH_VALID) || !flags || @@ -1770,10 +1769,8 @@ static int __jbd2_journal_erase(journal_t *journal, unsigned int flags) (flags & JBD2_JOURNAL_FLUSH_ZEROOUT))) return -EINVAL; - if (!q) - return -ENXIO; - - if ((flags & JBD2_JOURNAL_FLUSH_DISCARD) && !blk_queue_discard(q)) + if ((flags & JBD2_JOURNAL_FLUSH_DISCARD) && + !bdev_max_discard_sectors(journal->j_dev)) return -EOPNOTSUPP; /* @@ -1828,7 +1825,7 @@ static int __jbd2_journal_erase(journal_t *journal, unsigned int flags) err = blkdev_issue_discard(journal->j_dev, byte_start >> SECTOR_SHIFT, byte_count >> SECTOR_SHIFT, - GFP_NOFS, 0); + GFP_NOFS); } else if (flags & JBD2_JOURNAL_FLUSH_ZEROOUT) { err = blkdev_issue_zeroout(journal->j_dev, byte_start >> SECTOR_SHIFT, diff --git a/fs/jfs/ioctl.c b/fs/jfs/ioctl.c index 03a845ab4f00..1e7b177ece60 100644 --- a/fs/jfs/ioctl.c +++ b/fs/jfs/ioctl.c @@ -110,14 +110,13 @@ long jfs_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) case FITRIM: { struct super_block *sb = inode->i_sb; - struct request_queue *q = bdev_get_queue(sb->s_bdev); struct fstrim_range range; s64 ret = 0; if (!capable(CAP_SYS_ADMIN)) return -EPERM; - if (!blk_queue_discard(q)) { + if (!bdev_max_discard_sectors(sb->s_bdev)) { jfs_warn("FITRIM not supported on device"); return -EOPNOTSUPP; } @@ -127,7 +126,7 @@ long jfs_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) return -EFAULT; range.minlen = max_t(unsigned int, range.minlen, - q->limits.discard_granularity); + bdev_discard_granularity(sb->s_bdev)); ret = jfs_ioc_trim(inode, &range); if (ret < 0) diff --git a/fs/jfs/super.c b/fs/jfs/super.c index f1a13a74cddf..85d4f44f2ac4 100644 --- a/fs/jfs/super.c +++ b/fs/jfs/super.c @@ -372,19 +372,16 @@ static int parse_options(char *options, struct super_block *sb, s64 *newLVSize, } case Opt_discard: - { - struct request_queue *q = bdev_get_queue(sb->s_bdev); /* if set to 1, even copying files will cause * trimming :O * -> user has more control over the online trimming */ sbi->minblks_trim = 64; - if (blk_queue_discard(q)) + if (bdev_max_discard_sectors(sb->s_bdev)) *flag |= JFS_DISCARD; else pr_err("JFS: discard option not supported on device\n"); break; - } case Opt_nodiscard: *flag &= ~JFS_DISCARD; @@ -392,10 +389,9 @@ static int parse_options(char *options, struct super_block *sb, s64 *newLVSize, case Opt_discard_minblk: { - struct request_queue *q = bdev_get_queue(sb->s_bdev); char *minblks_trim = args[0].from; int rc; - if (blk_queue_discard(q)) { + if (bdev_max_discard_sectors(sb->s_bdev)) { *flag |= JFS_DISCARD; rc = kstrtouint(minblks_trim, 0, &sbi->minblks_trim); diff --git a/fs/nfs/fs_context.c b/fs/nfs/fs_context.c index e2d59bb5e6bb..9a16897e8dc6 100644 --- a/fs/nfs/fs_context.c +++ b/fs/nfs/fs_context.c @@ -517,7 +517,7 @@ static int nfs_fs_context_parse_param(struct fs_context *fc, if (result.negated) ctx->flags &= ~NFS_MOUNT_SOFTREVAL; else - ctx->flags &= NFS_MOUNT_SOFTREVAL; + ctx->flags |= NFS_MOUNT_SOFTREVAL; break; case Opt_posix: if (result.negated) diff --git a/fs/nilfs2/ioctl.c b/fs/nilfs2/ioctl.c index fec194a666f4..87e1004b606d 100644 --- a/fs/nilfs2/ioctl.c +++ b/fs/nilfs2/ioctl.c @@ -1052,20 +1052,20 @@ out: static int nilfs_ioctl_trim_fs(struct inode *inode, void __user *argp) { struct the_nilfs *nilfs = inode->i_sb->s_fs_info; - struct request_queue *q = bdev_get_queue(nilfs->ns_bdev); struct fstrim_range range; int ret; if (!capable(CAP_SYS_ADMIN)) return -EPERM; - if (!blk_queue_discard(q)) + if (!bdev_max_discard_sectors(nilfs->ns_bdev)) return -EOPNOTSUPP; if (copy_from_user(&range, argp, sizeof(range))) return -EFAULT; - range.minlen = max_t(u64, range.minlen, q->limits.discard_granularity); + range.minlen = max_t(u64, range.minlen, + bdev_discard_granularity(nilfs->ns_bdev)); down_read(&nilfs->ns_segctor_sem); ret = nilfs_sufile_trim_fs(nilfs->ns_sufile, &range); diff --git a/fs/nilfs2/sufile.c b/fs/nilfs2/sufile.c index e385cca2004a..77ff8e95421f 100644 --- a/fs/nilfs2/sufile.c +++ b/fs/nilfs2/sufile.c @@ -1100,7 +1100,7 @@ int nilfs_sufile_trim_fs(struct inode *sufile, struct fstrim_range *range) ret = blkdev_issue_discard(nilfs->ns_bdev, start * sects_per_block, nblocks * sects_per_block, - GFP_NOFS, 0); + GFP_NOFS); if (ret < 0) { put_bh(su_bh); goto out_sem; @@ -1134,7 +1134,7 @@ int nilfs_sufile_trim_fs(struct inode *sufile, struct fstrim_range *range) ret = blkdev_issue_discard(nilfs->ns_bdev, start * sects_per_block, nblocks * sects_per_block, - GFP_NOFS, 0); + GFP_NOFS); if (!ret) ndiscarded += nblocks; } diff --git a/fs/nilfs2/the_nilfs.c b/fs/nilfs2/the_nilfs.c index dd48a8f74d57..3b4a079c9617 100644 --- a/fs/nilfs2/the_nilfs.c +++ b/fs/nilfs2/the_nilfs.c @@ -672,7 +672,7 @@ int nilfs_discard_segments(struct the_nilfs *nilfs, __u64 *segnump, ret = blkdev_issue_discard(nilfs->ns_bdev, start * sects_per_block, nblocks * sects_per_block, - GFP_NOFS, 0); + GFP_NOFS); if (ret < 0) return ret; nblocks = 0; @@ -682,7 +682,7 @@ int nilfs_discard_segments(struct the_nilfs *nilfs, __u64 *segnump, ret = blkdev_issue_discard(nilfs->ns_bdev, start * sects_per_block, nblocks * sects_per_block, - GFP_NOFS, 0); + GFP_NOFS); return ret; } diff --git a/fs/notify/fanotify/fanotify_user.c b/fs/notify/fanotify/fanotify_user.c index 9b32b76a9c30..a792e21c5309 100644 --- a/fs/notify/fanotify/fanotify_user.c +++ b/fs/notify/fanotify/fanotify_user.c @@ -1657,6 +1657,19 @@ static int do_fanotify_mark(int fanotify_fd, unsigned int flags, __u64 mask, else mnt = path.mnt; + /* + * FAN_RENAME is not allowed on non-dir (for now). + * We shouldn't have allowed setting any dirent events in mask of + * non-dir, but because we always allowed it, error only if group + * was initialized with the new flag FAN_REPORT_TARGET_FID. + */ + ret = -ENOTDIR; + if (inode && !S_ISDIR(inode->i_mode) && + ((mask & FAN_RENAME) || + ((mask & FANOTIFY_DIRENT_EVENTS) && + FAN_GROUP_FLAG(group, FAN_REPORT_TARGET_FID)))) + goto path_put_and_out; + /* Mask out FAN_EVENT_ON_CHILD flag for sb/mount/non-dir marks */ if (mnt || !S_ISDIR(inode->i_mode)) { mask &= ~FAN_EVENT_ON_CHILD; diff --git a/fs/ntfs3/file.c b/fs/ntfs3/file.c index 787b53b984ee..15806eeae217 100644 --- a/fs/ntfs3/file.c +++ b/fs/ntfs3/file.c @@ -22,20 +22,20 @@ static int ntfs_ioctl_fitrim(struct ntfs_sb_info *sbi, unsigned long arg) { struct fstrim_range __user *user_range; struct fstrim_range range; - struct request_queue *q = bdev_get_queue(sbi->sb->s_bdev); int err; if (!capable(CAP_SYS_ADMIN)) return -EPERM; - if (!blk_queue_discard(q)) + if (!bdev_max_discard_sectors(sbi->sb->s_bdev)) return -EOPNOTSUPP; user_range = (struct fstrim_range __user *)arg; if (copy_from_user(&range, user_range, sizeof(range))) return -EFAULT; - range.minlen = max_t(u32, range.minlen, q->limits.discard_granularity); + range.minlen = max_t(u32, range.minlen, + bdev_discard_granularity(sbi->sb->s_bdev)); err = ntfs_trim_fs(sbi, &range); if (err < 0) diff --git a/fs/ntfs3/super.c b/fs/ntfs3/super.c index 278dcf502410..5781b9e8e3d8 100644 --- a/fs/ntfs3/super.c +++ b/fs/ntfs3/super.c @@ -882,7 +882,6 @@ static int ntfs_fill_super(struct super_block *sb, struct fs_context *fc) int err; struct ntfs_sb_info *sbi = sb->s_fs_info; struct block_device *bdev = sb->s_bdev; - struct request_queue *rq; struct inode *inode; struct ntfs_inode *ni; size_t i, tt; @@ -912,15 +911,14 @@ static int ntfs_fill_super(struct super_block *sb, struct fs_context *fc) goto out; } - rq = bdev_get_queue(bdev); - if (blk_queue_discard(rq) && rq->limits.discard_granularity) { - sbi->discard_granularity = rq->limits.discard_granularity; + if (bdev_max_discard_sectors(bdev) && bdev_discard_granularity(bdev)) { + sbi->discard_granularity = bdev_discard_granularity(bdev); sbi->discard_granularity_mask_inv = ~(u64)(sbi->discard_granularity - 1); } /* Parse boot. */ - err = ntfs_init_from_boot(sb, rq ? queue_logical_block_size(rq) : 512, + err = ntfs_init_from_boot(sb, bdev_logical_block_size(bdev), bdev_nr_bytes(bdev)); if (err) goto out; @@ -1335,7 +1333,7 @@ int ntfs_discard(struct ntfs_sb_info *sbi, CLST lcn, CLST len) return 0; err = blkdev_issue_discard(sb->s_bdev, start >> 9, (end - start) >> 9, - GFP_NOFS, 0); + GFP_NOFS); if (err == -EOPNOTSUPP) sbi->flags |= NTFS_FLAGS_NODISCARD; diff --git a/fs/ocfs2/ioctl.c b/fs/ocfs2/ioctl.c index f59461d85da4..afd54ec66103 100644 --- a/fs/ocfs2/ioctl.c +++ b/fs/ocfs2/ioctl.c @@ -903,20 +903,19 @@ long ocfs2_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) case FITRIM: { struct super_block *sb = inode->i_sb; - struct request_queue *q = bdev_get_queue(sb->s_bdev); struct fstrim_range range; int ret = 0; if (!capable(CAP_SYS_ADMIN)) return -EPERM; - if (!blk_queue_discard(q)) + if (!bdev_max_discard_sectors(sb->s_bdev)) return -EOPNOTSUPP; if (copy_from_user(&range, argp, sizeof(range))) return -EFAULT; - range.minlen = max_t(u64, q->limits.discard_granularity, + range.minlen = max_t(u64, bdev_discard_granularity(sb->s_bdev), range.minlen); ret = ocfs2_trim_fs(sb, &range); if (ret < 0) diff --git a/fs/proc/cpuinfo.c b/fs/proc/cpuinfo.c index 419760fd77bd..f38bda5b83ec 100644 --- a/fs/proc/cpuinfo.c +++ b/fs/proc/cpuinfo.c @@ -5,14 +5,10 @@ #include <linux/proc_fs.h> #include <linux/seq_file.h> -__weak void arch_freq_prepare_all(void) -{ -} - extern const struct seq_operations cpuinfo_op; + static int cpuinfo_open(struct inode *inode, struct file *file) { - arch_freq_prepare_all(); return seq_open(file, &cpuinfo_op); } diff --git a/fs/proc/fd.c b/fs/proc/fd.c index 172c86270b31..913bef0d2a36 100644 --- a/fs/proc/fd.c +++ b/fs/proc/fd.c @@ -72,7 +72,7 @@ out: return 0; } -static int seq_fdinfo_open(struct inode *inode, struct file *file) +static int proc_fdinfo_access_allowed(struct inode *inode) { bool allowed = false; struct task_struct *task = get_proc_task(inode); @@ -86,6 +86,16 @@ static int seq_fdinfo_open(struct inode *inode, struct file *file) if (!allowed) return -EACCES; + return 0; +} + +static int seq_fdinfo_open(struct inode *inode, struct file *file) +{ + int ret = proc_fdinfo_access_allowed(inode); + + if (ret) + return ret; + return single_open(file, seq_show, inode); } @@ -348,12 +358,23 @@ static int proc_readfdinfo(struct file *file, struct dir_context *ctx) proc_fdinfo_instantiate); } +static int proc_open_fdinfo(struct inode *inode, struct file *file) +{ + int ret = proc_fdinfo_access_allowed(inode); + + if (ret) + return ret; + + return 0; +} + const struct inode_operations proc_fdinfo_inode_operations = { .lookup = proc_lookupfdinfo, .setattr = proc_setattr, }; const struct file_operations proc_fdinfo_operations = { + .open = proc_open_fdinfo, .read = generic_read_dir, .iterate_shared = proc_readfdinfo, .llseek = generic_file_llseek, diff --git a/fs/squashfs/block.c b/fs/squashfs/block.c index 622c844f6d11..8879d052f96c 100644 --- a/fs/squashfs/block.c +++ b/fs/squashfs/block.c @@ -86,17 +86,10 @@ static int squashfs_bio_read(struct super_block *sb, u64 index, int length, int error, i; struct bio *bio; - if (page_count <= BIO_MAX_VECS) { - bio = bio_alloc(sb->s_bdev, page_count, REQ_OP_READ, GFP_NOIO); - } else { - bio = bio_kmalloc(GFP_NOIO, page_count); - bio_set_dev(bio, sb->s_bdev); - bio->bi_opf = REQ_OP_READ; - } - + bio = bio_kmalloc(page_count, GFP_NOIO); if (!bio) return -ENOMEM; - + bio_init(bio, sb->s_bdev, bio->bi_inline_vecs, page_count, REQ_OP_READ); bio->bi_iter.bi_sector = block * (msblk->devblksize >> SECTOR_SHIFT); for (i = 0; i < page_count; ++i) { @@ -126,7 +119,8 @@ static int squashfs_bio_read(struct super_block *sb, u64 index, int length, out_free_bio: bio_free_pages(bio); - bio_put(bio); + bio_uninit(bio); + kfree(bio); return error; } @@ -190,7 +184,8 @@ int squashfs_read_data(struct super_block *sb, u64 index, int length, length |= data[0] << 8; } bio_free_pages(bio); - bio_put(bio); + bio_uninit(bio); + kfree(bio); compressed = SQUASHFS_COMPRESSED(length); length = SQUASHFS_COMPRESSED_SIZE(length); @@ -224,7 +219,8 @@ int squashfs_read_data(struct super_block *sb, u64 index, int length, out_free_bio: bio_free_pages(bio); - bio_put(bio); + bio_uninit(bio); + kfree(bio); out: if (res < 0) { ERROR("Failed to read block 0x%llx: %d\n", index, res); diff --git a/fs/super.c b/fs/super.c index f1d4a193602d..60f57c7bc0a6 100644 --- a/fs/super.c +++ b/fs/super.c @@ -1204,7 +1204,7 @@ static int set_bdev_super(struct super_block *s, void *data) s->s_dev = s->s_bdev->bd_dev; s->s_bdi = bdi_get(s->s_bdev->bd_disk->bdi); - if (blk_queue_stable_writes(s->s_bdev->bd_disk->queue)) + if (bdev_stable_writes(s->s_bdev)) s->s_iflags |= SB_I_STABLE_WRITES; return 0; } diff --git a/fs/udf/namei.c b/fs/udf/namei.c index 0ed4861b038f..b3d5f97f16cd 100644 --- a/fs/udf/namei.c +++ b/fs/udf/namei.c @@ -75,11 +75,11 @@ int udf_write_fi(struct inode *inode, struct fileIdentDesc *cfi, if (fileident) { if (adinicb || (offset + lfi < 0)) { - memcpy(udf_get_fi_ident(sfi), fileident, lfi); + memcpy(sfi->impUse + liu, fileident, lfi); } else if (offset >= 0) { memcpy(fibh->ebh->b_data + offset, fileident, lfi); } else { - memcpy(udf_get_fi_ident(sfi), fileident, -offset); + memcpy(sfi->impUse + liu, fileident, -offset); memcpy(fibh->ebh->b_data, fileident - offset, lfi + offset); } @@ -88,11 +88,11 @@ int udf_write_fi(struct inode *inode, struct fileIdentDesc *cfi, offset += lfi; if (adinicb || (offset + padlen < 0)) { - memset(udf_get_fi_ident(sfi) + lfi, 0x00, padlen); + memset(sfi->impUse + liu + lfi, 0x00, padlen); } else if (offset >= 0) { memset(fibh->ebh->b_data + offset, 0x00, padlen); } else { - memset(udf_get_fi_ident(sfi) + lfi, 0x00, -offset); + memset(sfi->impUse + liu + lfi, 0x00, -offset); memset(fibh->ebh->b_data, 0x00, padlen + offset); } diff --git a/fs/xattr.c b/fs/xattr.c index 998045165916..e8dd03e4561e 100644 --- a/fs/xattr.c +++ b/fs/xattr.c @@ -25,6 +25,8 @@ #include <linux/uaccess.h> +#include "internal.h" + static const char * strcmp_prefix(const char *a, const char *a_prefix) { @@ -539,44 +541,76 @@ EXPORT_SYMBOL_GPL(vfs_removexattr); /* * Extended attribute SET operations */ -static long -setxattr(struct user_namespace *mnt_userns, struct dentry *d, - const char __user *name, const void __user *value, size_t size, - int flags) + +int setxattr_copy(const char __user *name, struct xattr_ctx *ctx) { int error; - void *kvalue = NULL; - char kname[XATTR_NAME_MAX + 1]; - if (flags & ~(XATTR_CREATE|XATTR_REPLACE)) + if (ctx->flags & ~(XATTR_CREATE|XATTR_REPLACE)) return -EINVAL; - error = strncpy_from_user(kname, name, sizeof(kname)); - if (error == 0 || error == sizeof(kname)) - error = -ERANGE; + error = strncpy_from_user(ctx->kname->name, name, + sizeof(ctx->kname->name)); + if (error == 0 || error == sizeof(ctx->kname->name)) + return -ERANGE; if (error < 0) return error; - if (size) { - if (size > XATTR_SIZE_MAX) + error = 0; + if (ctx->size) { + if (ctx->size > XATTR_SIZE_MAX) return -E2BIG; - kvalue = kvmalloc(size, GFP_KERNEL); - if (!kvalue) - return -ENOMEM; - if (copy_from_user(kvalue, value, size)) { - error = -EFAULT; - goto out; + + ctx->kvalue = vmemdup_user(ctx->cvalue, ctx->size); + if (IS_ERR(ctx->kvalue)) { + error = PTR_ERR(ctx->kvalue); + ctx->kvalue = NULL; } - if ((strcmp(kname, XATTR_NAME_POSIX_ACL_ACCESS) == 0) || - (strcmp(kname, XATTR_NAME_POSIX_ACL_DEFAULT) == 0)) - posix_acl_fix_xattr_from_user(mnt_userns, d_inode(d), - kvalue, size); } - error = vfs_setxattr(mnt_userns, d, kname, kvalue, size, flags); -out: - kvfree(kvalue); + return error; +} + +static void setxattr_convert(struct user_namespace *mnt_userns, + struct dentry *d, struct xattr_ctx *ctx) +{ + if (ctx->size && + ((strcmp(ctx->kname->name, XATTR_NAME_POSIX_ACL_ACCESS) == 0) || + (strcmp(ctx->kname->name, XATTR_NAME_POSIX_ACL_DEFAULT) == 0))) + posix_acl_fix_xattr_from_user(mnt_userns, d_inode(d), + ctx->kvalue, ctx->size); +} + +int do_setxattr(struct user_namespace *mnt_userns, struct dentry *dentry, + struct xattr_ctx *ctx) +{ + setxattr_convert(mnt_userns, dentry, ctx); + return vfs_setxattr(mnt_userns, dentry, ctx->kname->name, + ctx->kvalue, ctx->size, ctx->flags); +} + +static long +setxattr(struct user_namespace *mnt_userns, struct dentry *d, + const char __user *name, const void __user *value, size_t size, + int flags) +{ + struct xattr_name kname; + struct xattr_ctx ctx = { + .cvalue = value, + .kvalue = NULL, + .size = size, + .kname = &kname, + .flags = flags, + }; + int error; + error = setxattr_copy(name, &ctx); + if (error) + return error; + + error = do_setxattr(mnt_userns, d, &ctx); + + kvfree(ctx.kvalue); return error; } @@ -642,44 +676,61 @@ SYSCALL_DEFINE5(fsetxattr, int, fd, const char __user *, name, /* * Extended attribute GET operations */ -static ssize_t -getxattr(struct user_namespace *mnt_userns, struct dentry *d, - const char __user *name, void __user *value, size_t size) +ssize_t +do_getxattr(struct user_namespace *mnt_userns, struct dentry *d, + struct xattr_ctx *ctx) { ssize_t error; - void *kvalue = NULL; - char kname[XATTR_NAME_MAX + 1]; - - error = strncpy_from_user(kname, name, sizeof(kname)); - if (error == 0 || error == sizeof(kname)) - error = -ERANGE; - if (error < 0) - return error; + char *kname = ctx->kname->name; - if (size) { - if (size > XATTR_SIZE_MAX) - size = XATTR_SIZE_MAX; - kvalue = kvzalloc(size, GFP_KERNEL); - if (!kvalue) + if (ctx->size) { + if (ctx->size > XATTR_SIZE_MAX) + ctx->size = XATTR_SIZE_MAX; + ctx->kvalue = kvzalloc(ctx->size, GFP_KERNEL); + if (!ctx->kvalue) return -ENOMEM; } - error = vfs_getxattr(mnt_userns, d, kname, kvalue, size); + error = vfs_getxattr(mnt_userns, d, kname, ctx->kvalue, ctx->size); if (error > 0) { if ((strcmp(kname, XATTR_NAME_POSIX_ACL_ACCESS) == 0) || (strcmp(kname, XATTR_NAME_POSIX_ACL_DEFAULT) == 0)) posix_acl_fix_xattr_to_user(mnt_userns, d_inode(d), - kvalue, error); - if (size && copy_to_user(value, kvalue, error)) + ctx->kvalue, error); + if (ctx->size && copy_to_user(ctx->value, ctx->kvalue, error)) error = -EFAULT; - } else if (error == -ERANGE && size >= XATTR_SIZE_MAX) { + } else if (error == -ERANGE && ctx->size >= XATTR_SIZE_MAX) { /* The file system tried to returned a value bigger than XATTR_SIZE_MAX bytes. Not possible. */ error = -E2BIG; } - kvfree(kvalue); + return error; +} + +static ssize_t +getxattr(struct user_namespace *mnt_userns, struct dentry *d, + const char __user *name, void __user *value, size_t size) +{ + ssize_t error; + struct xattr_name kname; + struct xattr_ctx ctx = { + .value = value, + .kvalue = NULL, + .size = size, + .kname = &kname, + .flags = 0, + }; + + error = strncpy_from_user(kname.name, name, sizeof(kname.name)); + if (error == 0 || error == sizeof(kname.name)) + error = -ERANGE; + if (error < 0) + return error; + + error = do_getxattr(mnt_userns, d, &ctx); + kvfree(ctx.kvalue); return error; } diff --git a/fs/xfs/xfs_discard.c b/fs/xfs/xfs_discard.c index 0191de8ce9ce..c6fe3f6ebb6b 100644 --- a/fs/xfs/xfs_discard.c +++ b/fs/xfs/xfs_discard.c @@ -114,7 +114,7 @@ xfs_trim_extents( } trace_xfs_discard_extent(mp, agno, fbno, flen); - error = blkdev_issue_discard(bdev, dbno, dlen, GFP_NOFS, 0); + error = blkdev_issue_discard(bdev, dbno, dlen, GFP_NOFS); if (error) goto out_del_cursor; *blocks_trimmed += flen; @@ -152,8 +152,8 @@ xfs_ioc_trim( struct xfs_mount *mp, struct fstrim_range __user *urange) { - struct request_queue *q = bdev_get_queue(mp->m_ddev_targp->bt_bdev); - unsigned int granularity = q->limits.discard_granularity; + unsigned int granularity = + bdev_discard_granularity(mp->m_ddev_targp->bt_bdev); struct fstrim_range range; xfs_daddr_t start, end, minlen; xfs_agnumber_t start_agno, end_agno, agno; @@ -162,7 +162,7 @@ xfs_ioc_trim( if (!capable(CAP_SYS_ADMIN)) return -EPERM; - if (!blk_queue_discard(q)) + if (!bdev_max_discard_sectors(mp->m_ddev_targp->bt_bdev)) return -EOPNOTSUPP; /* diff --git a/fs/xfs/xfs_log_cil.c b/fs/xfs/xfs_log_cil.c index ba57323bfdce..c9f55e4f0957 100644 --- a/fs/xfs/xfs_log_cil.c +++ b/fs/xfs/xfs_log_cil.c @@ -605,7 +605,7 @@ xlog_discard_busy_extents( error = __blkdev_issue_discard(mp->m_ddev_targp->bt_bdev, XFS_AGB_TO_DADDR(mp, busyp->agno, busyp->bno), XFS_FSB_TO_BB(mp, busyp->length), - GFP_NOFS, 0, &bio); + GFP_NOFS, &bio); if (error && error != -EOPNOTSUPP) { xfs_info(mp, "discard failed for extent [0x%llx,%u], error %d", diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c index 54be9d64093e..a276b8111f63 100644 --- a/fs/xfs/xfs_super.c +++ b/fs/xfs/xfs_super.c @@ -1608,14 +1608,10 @@ xfs_fs_fill_super( goto out_filestream_unmount; } - if (xfs_has_discard(mp)) { - struct request_queue *q = bdev_get_queue(sb->s_bdev); - - if (!blk_queue_discard(q)) { - xfs_warn(mp, "mounting with \"discard\" option, but " - "the device does not support discard"); - mp->m_features &= ~XFS_FEAT_DISCARD; - } + if (xfs_has_discard(mp) && !bdev_max_discard_sectors(sb->s_bdev)) { + xfs_warn(mp, + "mounting with \"discard\" option, but the device does not support discard"); + mp->m_features &= ~XFS_FEAT_DISCARD; } if (xfs_has_reflink(mp)) { diff --git a/fs/zonefs/Makefile b/fs/zonefs/Makefile index 33c1a4f1132e..9fe54f5319f2 100644 --- a/fs/zonefs/Makefile +++ b/fs/zonefs/Makefile @@ -3,4 +3,4 @@ ccflags-y += -I$(src) obj-$(CONFIG_ZONEFS_FS) += zonefs.o -zonefs-y := super.o +zonefs-y := super.o sysfs.o diff --git a/fs/zonefs/super.c b/fs/zonefs/super.c index e20e7c841489..b3b0b71fdf6c 100644 --- a/fs/zonefs/super.c +++ b/fs/zonefs/super.c @@ -27,6 +27,39 @@ #define CREATE_TRACE_POINTS #include "trace.h" +/* + * Manage the active zone count. Called with zi->i_truncate_mutex held. + */ +static void zonefs_account_active(struct inode *inode) +{ + struct zonefs_sb_info *sbi = ZONEFS_SB(inode->i_sb); + struct zonefs_inode_info *zi = ZONEFS_I(inode); + + lockdep_assert_held(&zi->i_truncate_mutex); + + if (zi->i_ztype != ZONEFS_ZTYPE_SEQ) + return; + + /* + * If the zone is active, that is, if it is explicitly open or + * partially written, check if it was already accounted as active. + */ + if ((zi->i_flags & ZONEFS_ZONE_OPEN) || + (zi->i_wpoffset > 0 && zi->i_wpoffset < zi->i_max_size)) { + if (!(zi->i_flags & ZONEFS_ZONE_ACTIVE)) { + zi->i_flags |= ZONEFS_ZONE_ACTIVE; + atomic_inc(&sbi->s_active_seq_files); + } + return; + } + + /* The zone is not active. If it was, update the active count */ + if (zi->i_flags & ZONEFS_ZONE_ACTIVE) { + zi->i_flags &= ~ZONEFS_ZONE_ACTIVE; + atomic_dec(&sbi->s_active_seq_files); + } +} + static inline int zonefs_zone_mgmt(struct inode *inode, enum req_opf op) { @@ -68,8 +101,13 @@ static inline void zonefs_i_size_write(struct inode *inode, loff_t isize) * A full zone is no longer open/active and does not need * explicit closing. */ - if (isize >= zi->i_max_size) - zi->i_flags &= ~ZONEFS_ZONE_OPEN; + if (isize >= zi->i_max_size) { + struct zonefs_sb_info *sbi = ZONEFS_SB(inode->i_sb); + + if (zi->i_flags & ZONEFS_ZONE_ACTIVE) + atomic_dec(&sbi->s_active_seq_files); + zi->i_flags &= ~(ZONEFS_ZONE_OPEN | ZONEFS_ZONE_ACTIVE); + } } static int zonefs_iomap_begin(struct inode *inode, loff_t offset, loff_t length, @@ -397,6 +435,7 @@ static int zonefs_io_error_cb(struct blk_zone *zone, unsigned int idx, zonefs_update_stats(inode, data_size); zonefs_i_size_write(inode, data_size); zi->i_wpoffset = data_size; + zonefs_account_active(inode); return 0; } @@ -508,6 +547,7 @@ static int zonefs_file_truncate(struct inode *inode, loff_t isize) zonefs_update_stats(inode, isize); truncate_setsize(inode, isize); zi->i_wpoffset = isize; + zonefs_account_active(inode); unlock: mutex_unlock(&zi->i_truncate_mutex); @@ -689,13 +729,12 @@ static ssize_t zonefs_file_dio_append(struct kiocb *iocb, struct iov_iter *from) struct inode *inode = file_inode(iocb->ki_filp); struct zonefs_inode_info *zi = ZONEFS_I(inode); struct block_device *bdev = inode->i_sb->s_bdev; - unsigned int max; + unsigned int max = bdev_max_zone_append_sectors(bdev); struct bio *bio; ssize_t size; int nr_pages; ssize_t ret; - max = queue_max_zone_append_sectors(bdev_get_queue(bdev)); max = ALIGN_DOWN(max << SECTOR_SHIFT, inode->i_sb->s_blocksize); iov_iter_truncate(from, max); @@ -866,8 +905,15 @@ static ssize_t zonefs_file_dio_write(struct kiocb *iocb, struct iov_iter *from) (ret > 0 || ret == -EIOCBQUEUED)) { if (ret > 0) count = ret; + + /* + * Update the zone write pointer offset assuming the write + * operation succeeded. If it did not, the error recovery path + * will correct it. Also do active seq file accounting. + */ mutex_lock(&zi->i_truncate_mutex); zi->i_wpoffset += count; + zonefs_account_active(inode); mutex_unlock(&zi->i_truncate_mutex); } @@ -1009,13 +1055,13 @@ inode_unlock: return ret; } -static inline bool zonefs_file_use_exp_open(struct inode *inode, struct file *file) +/* + * Write open accounting is done only for sequential files. + */ +static inline bool zonefs_seq_file_need_wro(struct inode *inode, + struct file *file) { struct zonefs_inode_info *zi = ZONEFS_I(inode); - struct zonefs_sb_info *sbi = ZONEFS_SB(inode->i_sb); - - if (!(sbi->s_mount_opts & ZONEFS_MNTOPT_EXPLICIT_OPEN)) - return false; if (zi->i_ztype != ZONEFS_ZTYPE_SEQ) return false; @@ -1026,28 +1072,34 @@ static inline bool zonefs_file_use_exp_open(struct inode *inode, struct file *fi return true; } -static int zonefs_open_zone(struct inode *inode) +static int zonefs_seq_file_write_open(struct inode *inode) { struct zonefs_inode_info *zi = ZONEFS_I(inode); - struct zonefs_sb_info *sbi = ZONEFS_SB(inode->i_sb); int ret = 0; mutex_lock(&zi->i_truncate_mutex); if (!zi->i_wr_refcnt) { - if (atomic_inc_return(&sbi->s_open_zones) > sbi->s_max_open_zones) { - atomic_dec(&sbi->s_open_zones); - ret = -EBUSY; - goto unlock; - } + struct zonefs_sb_info *sbi = ZONEFS_SB(inode->i_sb); + unsigned int wro = atomic_inc_return(&sbi->s_wro_seq_files); - if (i_size_read(inode) < zi->i_max_size) { - ret = zonefs_zone_mgmt(inode, REQ_OP_ZONE_OPEN); - if (ret) { - atomic_dec(&sbi->s_open_zones); + if (sbi->s_mount_opts & ZONEFS_MNTOPT_EXPLICIT_OPEN) { + + if (wro > sbi->s_max_wro_seq_files) { + atomic_dec(&sbi->s_wro_seq_files); + ret = -EBUSY; goto unlock; } - zi->i_flags |= ZONEFS_ZONE_OPEN; + + if (i_size_read(inode) < zi->i_max_size) { + ret = zonefs_zone_mgmt(inode, REQ_OP_ZONE_OPEN); + if (ret) { + atomic_dec(&sbi->s_wro_seq_files); + goto unlock; + } + zi->i_flags |= ZONEFS_ZONE_OPEN; + zonefs_account_active(inode); + } } } @@ -1067,30 +1119,31 @@ static int zonefs_file_open(struct inode *inode, struct file *file) if (ret) return ret; - if (zonefs_file_use_exp_open(inode, file)) - return zonefs_open_zone(inode); + if (zonefs_seq_file_need_wro(inode, file)) + return zonefs_seq_file_write_open(inode); return 0; } -static void zonefs_close_zone(struct inode *inode) +static void zonefs_seq_file_write_close(struct inode *inode) { struct zonefs_inode_info *zi = ZONEFS_I(inode); + struct super_block *sb = inode->i_sb; + struct zonefs_sb_info *sbi = ZONEFS_SB(sb); int ret = 0; mutex_lock(&zi->i_truncate_mutex); - zi->i_wr_refcnt--; - if (!zi->i_wr_refcnt) { - struct zonefs_sb_info *sbi = ZONEFS_SB(inode->i_sb); - struct super_block *sb = inode->i_sb; - /* - * If the file zone is full, it is not open anymore and we only - * need to decrement the open count. - */ - if (!(zi->i_flags & ZONEFS_ZONE_OPEN)) - goto dec; + zi->i_wr_refcnt--; + if (zi->i_wr_refcnt) + goto unlock; + /* + * The file zone may not be open anymore (e.g. the file was truncated to + * its maximum size or it was fully written). For this case, we only + * need to decrement the write open count. + */ + if (zi->i_flags & ZONEFS_ZONE_OPEN) { ret = zonefs_zone_mgmt(inode, REQ_OP_ZONE_CLOSE); if (ret) { __zonefs_io_error(inode, false); @@ -1102,14 +1155,23 @@ static void zonefs_close_zone(struct inode *inode) */ if (zi->i_flags & ZONEFS_ZONE_OPEN && !(sb->s_flags & SB_RDONLY)) { - zonefs_warn(sb, "closing zone failed, remounting filesystem read-only\n"); + zonefs_warn(sb, + "closing zone at %llu failed %d\n", + zi->i_zsector, ret); + zonefs_warn(sb, + "remounting filesystem read-only\n"); sb->s_flags |= SB_RDONLY; } + goto unlock; } + zi->i_flags &= ~ZONEFS_ZONE_OPEN; -dec: - atomic_dec(&sbi->s_open_zones); + zonefs_account_active(inode); } + + atomic_dec(&sbi->s_wro_seq_files); + +unlock: mutex_unlock(&zi->i_truncate_mutex); } @@ -1121,8 +1183,8 @@ static int zonefs_file_release(struct inode *inode, struct file *file) * the zone has gone offline or read-only). Make sure we don't fail the * close(2) for user-space. */ - if (zonefs_file_use_exp_open(inode, file)) - zonefs_close_zone(inode); + if (zonefs_seq_file_need_wro(inode, file)) + zonefs_seq_file_write_close(inode); return 0; } @@ -1311,7 +1373,7 @@ static int zonefs_init_file_inode(struct inode *inode, struct blk_zone *zone, struct super_block *sb = inode->i_sb; struct zonefs_sb_info *sbi = ZONEFS_SB(sb); struct zonefs_inode_info *zi = ZONEFS_I(inode); - int ret = 0; + int ret; inode->i_ino = zone->start >> sbi->s_zone_sectors_shift; inode->i_mode = S_IFREG | sbi->s_perm; @@ -1337,6 +1399,8 @@ static int zonefs_init_file_inode(struct inode *inode, struct blk_zone *zone, sbi->s_blocks += zi->i_max_size >> sb->s_blocksize_bits; sbi->s_used_blocks += zi->i_wpoffset >> sb->s_blocksize_bits; + mutex_lock(&zi->i_truncate_mutex); + /* * For sequential zones, make sure that any open zone is closed first * to ensure that the initial number of open zones is 0, in sync with @@ -1346,12 +1410,17 @@ static int zonefs_init_file_inode(struct inode *inode, struct blk_zone *zone, if (type == ZONEFS_ZTYPE_SEQ && (zone->cond == BLK_ZONE_COND_IMP_OPEN || zone->cond == BLK_ZONE_COND_EXP_OPEN)) { - mutex_lock(&zi->i_truncate_mutex); ret = zonefs_zone_mgmt(inode, REQ_OP_ZONE_CLOSE); - mutex_unlock(&zi->i_truncate_mutex); + if (ret) + goto unlock; } - return ret; + zonefs_account_active(inode); + +unlock: + mutex_unlock(&zi->i_truncate_mutex); + + return 0; } static struct dentry *zonefs_create_inode(struct dentry *parent, @@ -1688,14 +1757,18 @@ static int zonefs_fill_super(struct super_block *sb, void *data, int silent) sbi->s_gid = GLOBAL_ROOT_GID; sbi->s_perm = 0640; sbi->s_mount_opts = ZONEFS_MNTOPT_ERRORS_RO; - sbi->s_max_open_zones = bdev_max_open_zones(sb->s_bdev); - atomic_set(&sbi->s_open_zones, 0); - if (!sbi->s_max_open_zones && + + atomic_set(&sbi->s_wro_seq_files, 0); + sbi->s_max_wro_seq_files = bdev_max_open_zones(sb->s_bdev); + if (!sbi->s_max_wro_seq_files && sbi->s_mount_opts & ZONEFS_MNTOPT_EXPLICIT_OPEN) { zonefs_info(sb, "No open zones limit. Ignoring explicit_open mount option\n"); sbi->s_mount_opts &= ~ZONEFS_MNTOPT_EXPLICIT_OPEN; } + atomic_set(&sbi->s_active_seq_files, 0); + sbi->s_max_active_seq_files = bdev_max_active_zones(sb->s_bdev); + ret = zonefs_read_super(sb); if (ret) return ret; @@ -1710,6 +1783,10 @@ static int zonefs_fill_super(struct super_block *sb, void *data, int silent) if (ret) goto cleanup; + ret = zonefs_sysfs_register(sb); + if (ret) + goto cleanup; + zonefs_info(sb, "Mounting %u zones", blkdev_nr_zones(sb->s_bdev->bd_disk)); @@ -1755,6 +1832,8 @@ static void zonefs_kill_super(struct super_block *sb) if (sb->s_root) d_genocide(sb->s_root); + + zonefs_sysfs_unregister(sb); kill_block_super(sb); kfree(sbi); } @@ -1802,16 +1881,26 @@ static int __init zonefs_init(void) return ret; ret = register_filesystem(&zonefs_type); - if (ret) { - zonefs_destroy_inodecache(); - return ret; - } + if (ret) + goto destroy_inodecache; + + ret = zonefs_sysfs_init(); + if (ret) + goto unregister_fs; return 0; + +unregister_fs: + unregister_filesystem(&zonefs_type); +destroy_inodecache: + zonefs_destroy_inodecache(); + + return ret; } static void __exit zonefs_exit(void) { + zonefs_sysfs_exit(); zonefs_destroy_inodecache(); unregister_filesystem(&zonefs_type); } diff --git a/fs/zonefs/sysfs.c b/fs/zonefs/sysfs.c new file mode 100644 index 000000000000..9cb6755ce39a --- /dev/null +++ b/fs/zonefs/sysfs.c @@ -0,0 +1,139 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Simple file system for zoned block devices exposing zones as files. + * + * Copyright (C) 2022 Western Digital Corporation or its affiliates. + */ +#include <linux/fs.h> +#include <linux/seq_file.h> +#include <linux/blkdev.h> + +#include "zonefs.h" + +struct zonefs_sysfs_attr { + struct attribute attr; + ssize_t (*show)(struct zonefs_sb_info *sbi, char *buf); +}; + +static inline struct zonefs_sysfs_attr *to_attr(struct attribute *attr) +{ + return container_of(attr, struct zonefs_sysfs_attr, attr); +} + +#define ZONEFS_SYSFS_ATTR_RO(name) \ +static struct zonefs_sysfs_attr zonefs_sysfs_attr_##name = __ATTR_RO(name) + +#define ATTR_LIST(name) &zonefs_sysfs_attr_##name.attr + +static ssize_t zonefs_sysfs_attr_show(struct kobject *kobj, + struct attribute *attr, char *buf) +{ + struct zonefs_sb_info *sbi = + container_of(kobj, struct zonefs_sb_info, s_kobj); + struct zonefs_sysfs_attr *zonefs_attr = + container_of(attr, struct zonefs_sysfs_attr, attr); + + if (!zonefs_attr->show) + return 0; + + return zonefs_attr->show(sbi, buf); +} + +static ssize_t max_wro_seq_files_show(struct zonefs_sb_info *sbi, char *buf) +{ + return sysfs_emit(buf, "%u\n", sbi->s_max_wro_seq_files); +} +ZONEFS_SYSFS_ATTR_RO(max_wro_seq_files); + +static ssize_t nr_wro_seq_files_show(struct zonefs_sb_info *sbi, char *buf) +{ + return sysfs_emit(buf, "%d\n", atomic_read(&sbi->s_wro_seq_files)); +} +ZONEFS_SYSFS_ATTR_RO(nr_wro_seq_files); + +static ssize_t max_active_seq_files_show(struct zonefs_sb_info *sbi, char *buf) +{ + return sysfs_emit(buf, "%u\n", sbi->s_max_active_seq_files); +} +ZONEFS_SYSFS_ATTR_RO(max_active_seq_files); + +static ssize_t nr_active_seq_files_show(struct zonefs_sb_info *sbi, char *buf) +{ + return sysfs_emit(buf, "%d\n", atomic_read(&sbi->s_active_seq_files)); +} +ZONEFS_SYSFS_ATTR_RO(nr_active_seq_files); + +static struct attribute *zonefs_sysfs_attrs[] = { + ATTR_LIST(max_wro_seq_files), + ATTR_LIST(nr_wro_seq_files), + ATTR_LIST(max_active_seq_files), + ATTR_LIST(nr_active_seq_files), + NULL, +}; +ATTRIBUTE_GROUPS(zonefs_sysfs); + +static void zonefs_sysfs_sb_release(struct kobject *kobj) +{ + struct zonefs_sb_info *sbi = + container_of(kobj, struct zonefs_sb_info, s_kobj); + + complete(&sbi->s_kobj_unregister); +} + +static const struct sysfs_ops zonefs_sysfs_attr_ops = { + .show = zonefs_sysfs_attr_show, +}; + +static struct kobj_type zonefs_sb_ktype = { + .default_groups = zonefs_sysfs_groups, + .sysfs_ops = &zonefs_sysfs_attr_ops, + .release = zonefs_sysfs_sb_release, +}; + +static struct kobject *zonefs_sysfs_root; + +int zonefs_sysfs_register(struct super_block *sb) +{ + struct zonefs_sb_info *sbi = ZONEFS_SB(sb); + int ret; + + init_completion(&sbi->s_kobj_unregister); + ret = kobject_init_and_add(&sbi->s_kobj, &zonefs_sb_ktype, + zonefs_sysfs_root, "%s", sb->s_id); + if (ret) { + kobject_put(&sbi->s_kobj); + wait_for_completion(&sbi->s_kobj_unregister); + return ret; + } + + sbi->s_sysfs_registered = true; + + return 0; +} + +void zonefs_sysfs_unregister(struct super_block *sb) +{ + struct zonefs_sb_info *sbi = ZONEFS_SB(sb); + + if (!sbi || !sbi->s_sysfs_registered) + return; + + kobject_del(&sbi->s_kobj); + kobject_put(&sbi->s_kobj); + wait_for_completion(&sbi->s_kobj_unregister); +} + +int __init zonefs_sysfs_init(void) +{ + zonefs_sysfs_root = kobject_create_and_add("zonefs", fs_kobj); + if (!zonefs_sysfs_root) + return -ENOMEM; + + return 0; +} + +void zonefs_sysfs_exit(void) +{ + kobject_put(zonefs_sysfs_root); + zonefs_sysfs_root = NULL; +} diff --git a/fs/zonefs/zonefs.h b/fs/zonefs/zonefs.h index 7b147907c328..4b3de66c3233 100644 --- a/fs/zonefs/zonefs.h +++ b/fs/zonefs/zonefs.h @@ -12,6 +12,7 @@ #include <linux/uuid.h> #include <linux/mutex.h> #include <linux/rwsem.h> +#include <linux/kobject.h> /* * Maximum length of file names: this only needs to be large enough to fit @@ -39,6 +40,7 @@ static inline enum zonefs_ztype zonefs_zone_type(struct blk_zone *zone) } #define ZONEFS_ZONE_OPEN (1 << 0) +#define ZONEFS_ZONE_ACTIVE (1 << 1) /* * In-memory inode data. @@ -182,8 +184,15 @@ struct zonefs_sb_info { loff_t s_blocks; loff_t s_used_blocks; - unsigned int s_max_open_zones; - atomic_t s_open_zones; + unsigned int s_max_wro_seq_files; + atomic_t s_wro_seq_files; + + unsigned int s_max_active_seq_files; + atomic_t s_active_seq_files; + + bool s_sysfs_registered; + struct kobject s_kobj; + struct completion s_kobj_unregister; }; static inline struct zonefs_sb_info *ZONEFS_SB(struct super_block *sb) @@ -198,4 +207,9 @@ static inline struct zonefs_sb_info *ZONEFS_SB(struct super_block *sb) #define zonefs_warn(sb, format, args...) \ pr_warn("zonefs (%s) WARNING: " format, sb->s_id, ## args) +int zonefs_sysfs_register(struct super_block *sb); +void zonefs_sysfs_unregister(struct super_block *sb); +int zonefs_sysfs_init(void); +void zonefs_sysfs_exit(void); + #endif diff --git a/include/linux/audit.h b/include/linux/audit.h index d06134ac6245..cece70231138 100644 --- a/include/linux/audit.h +++ b/include/linux/audit.h @@ -339,7 +339,7 @@ static inline void audit_uring_entry(u8 op) } static inline void audit_uring_exit(int success, long code) { - if (unlikely(!audit_dummy_context())) + if (unlikely(audit_context())) __audit_uring_exit(success, code); } static inline void audit_syscall_entry(int major, unsigned long a0, diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h index 87ce24d238f3..2bd073fa6bb5 100644 --- a/include/linux/backing-dev.h +++ b/include/linux/backing-dev.h @@ -17,8 +17,6 @@ #include <linux/backing-dev-defs.h> #include <linux/slab.h> -struct blkcg; - static inline struct backing_dev_info *bdi_get(struct backing_dev_info *bdi) { kref_get(&bdi->refcnt); @@ -154,7 +152,7 @@ struct bdi_writeback *wb_get_create(struct backing_dev_info *bdi, struct cgroup_subsys_state *memcg_css, gfp_t gfp); void wb_memcg_offline(struct mem_cgroup *memcg); -void wb_blkcg_offline(struct blkcg *blkcg); +void wb_blkcg_offline(struct cgroup_subsys_state *css); /** * inode_cgwb_enabled - test whether cgroup writeback is enabled on an inode @@ -378,7 +376,7 @@ static inline void wb_memcg_offline(struct mem_cgroup *memcg) { } -static inline void wb_blkcg_offline(struct blkcg *blkcg) +static inline void wb_blkcg_offline(struct cgroup_subsys_state *css) { } diff --git a/include/linux/bio.h b/include/linux/bio.h index 00450fd86bb4..1cf3738ef1ea 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -408,9 +408,7 @@ extern int bioset_init_from_src(struct bio_set *bs, struct bio_set *src); struct bio *bio_alloc_bioset(struct block_device *bdev, unsigned short nr_vecs, unsigned int opf, gfp_t gfp_mask, struct bio_set *bs); -struct bio *bio_alloc_kiocb(struct kiocb *kiocb, struct block_device *bdev, - unsigned short nr_vecs, unsigned int opf, struct bio_set *bs); -struct bio *bio_kmalloc(gfp_t gfp_mask, unsigned short nr_iovecs); +struct bio *bio_kmalloc(unsigned short nr_vecs, gfp_t gfp_mask); extern void bio_put(struct bio *); struct bio *bio_alloc_clone(struct block_device *bdev, struct bio *bio_src, @@ -785,6 +783,12 @@ static inline void bio_set_polled(struct bio *bio, struct kiocb *kiocb) bio->bi_opf |= REQ_NOWAIT; } +static inline void bio_clear_polled(struct bio *bio) +{ + /* can't support alloc cache if we turn off polling */ + bio->bi_opf &= ~(REQ_POLLED | REQ_ALLOC_CACHE); +} + struct bio *blk_next_bio(struct bio *bio, struct block_device *bdev, unsigned int nr_pages, unsigned int opf, gfp_t gfp); diff --git a/include/linux/blk-cgroup.h b/include/linux/blk-cgroup.h index 652cd05b0924..9f40dbc65f82 100644 --- a/include/linux/blk-cgroup.h +++ b/include/linux/blk-cgroup.h @@ -14,265 +14,39 @@ * Nauman Rafique <nauman@google.com> */ -#include <linux/cgroup.h> -#include <linux/percpu.h> -#include <linux/percpu_counter.h> -#include <linux/u64_stats_sync.h> -#include <linux/seq_file.h> -#include <linux/radix-tree.h> -#include <linux/blkdev.h> -#include <linux/atomic.h> -#include <linux/kthread.h> -#include <linux/fs.h> +#include <linux/types.h> + +struct bio; +struct cgroup_subsys_state; +struct request_queue; #define FC_APPID_LEN 129 #ifdef CONFIG_BLK_CGROUP - -enum blkg_iostat_type { - BLKG_IOSTAT_READ, - BLKG_IOSTAT_WRITE, - BLKG_IOSTAT_DISCARD, - - BLKG_IOSTAT_NR, -}; - -struct blkcg_gq; -struct blkg_policy_data; - -struct blkcg { - struct cgroup_subsys_state css; - spinlock_t lock; - refcount_t online_pin; - - struct radix_tree_root blkg_tree; - struct blkcg_gq __rcu *blkg_hint; - struct hlist_head blkg_list; - - struct blkcg_policy_data *cpd[BLKCG_MAX_POLS]; - - struct list_head all_blkcgs_node; -#ifdef CONFIG_BLK_CGROUP_FC_APPID - char fc_app_id[FC_APPID_LEN]; -#endif -#ifdef CONFIG_CGROUP_WRITEBACK - struct list_head cgwb_list; -#endif -}; - -struct blkg_iostat { - u64 bytes[BLKG_IOSTAT_NR]; - u64 ios[BLKG_IOSTAT_NR]; -}; - -struct blkg_iostat_set { - struct u64_stats_sync sync; - struct blkg_iostat cur; - struct blkg_iostat last; -}; - -/* association between a blk cgroup and a request queue */ -struct blkcg_gq { - /* Pointer to the associated request_queue */ - struct request_queue *q; - struct list_head q_node; - struct hlist_node blkcg_node; - struct blkcg *blkcg; - - /* all non-root blkcg_gq's are guaranteed to have access to parent */ - struct blkcg_gq *parent; - - /* reference count */ - struct percpu_ref refcnt; - - /* is this blkg online? protected by both blkcg and q locks */ - bool online; - - struct blkg_iostat_set __percpu *iostat_cpu; - struct blkg_iostat_set iostat; - - struct blkg_policy_data *pd[BLKCG_MAX_POLS]; - - spinlock_t async_bio_lock; - struct bio_list async_bios; - union { - struct work_struct async_bio_work; - struct work_struct free_work; - }; - - atomic_t use_delay; - atomic64_t delay_nsec; - atomic64_t delay_start; - u64 last_delay; - int last_use; - - struct rcu_head rcu_head; -}; - extern struct cgroup_subsys_state * const blkcg_root_css; -void blkcg_destroy_blkgs(struct blkcg *blkcg); void blkcg_schedule_throttle(struct request_queue *q, bool use_memdelay); void blkcg_maybe_throttle_current(void); - -static inline struct blkcg *css_to_blkcg(struct cgroup_subsys_state *css) -{ - return css ? container_of(css, struct blkcg, css) : NULL; -} - -/** - * bio_blkcg - grab the blkcg associated with a bio - * @bio: target bio - * - * This returns the blkcg associated with a bio, %NULL if not associated. - * Callers are expected to either handle %NULL or know association has been - * done prior to calling this. - */ -static inline struct blkcg *bio_blkcg(struct bio *bio) -{ - if (bio && bio->bi_blkg) - return bio->bi_blkg->blkcg; - return NULL; -} - -static inline bool blk_cgroup_congested(void) -{ - struct cgroup_subsys_state *css; - bool ret = false; - - rcu_read_lock(); - css = kthread_blkcg(); - if (!css) - css = task_css(current, io_cgrp_id); - while (css) { - if (atomic_read(&css->cgroup->congestion_count)) { - ret = true; - break; - } - css = css->parent; - } - rcu_read_unlock(); - return ret; -} - -/** - * blkcg_parent - get the parent of a blkcg - * @blkcg: blkcg of interest - * - * Return the parent blkcg of @blkcg. Can be called anytime. - */ -static inline struct blkcg *blkcg_parent(struct blkcg *blkcg) -{ - return css_to_blkcg(blkcg->css.parent); -} - -/** - * blkcg_pin_online - pin online state - * @blkcg: blkcg of interest - * - * While pinned, a blkcg is kept online. This is primarily used to - * impedance-match blkg and cgwb lifetimes so that blkg doesn't go offline - * while an associated cgwb is still active. - */ -static inline void blkcg_pin_online(struct blkcg *blkcg) -{ - refcount_inc(&blkcg->online_pin); -} - -/** - * blkcg_unpin_online - unpin online state - * @blkcg: blkcg of interest - * - * This is primarily used to impedance-match blkg and cgwb lifetimes so - * that blkg doesn't go offline while an associated cgwb is still active. - * When this count goes to zero, all active cgwbs have finished so the - * blkcg can continue destruction by calling blkcg_destroy_blkgs(). - */ -static inline void blkcg_unpin_online(struct blkcg *blkcg) -{ - do { - if (!refcount_dec_and_test(&blkcg->online_pin)) - break; - blkcg_destroy_blkgs(blkcg); - blkcg = blkcg_parent(blkcg); - } while (blkcg); -} +bool blk_cgroup_congested(void); +void blkcg_pin_online(struct cgroup_subsys_state *blkcg_css); +void blkcg_unpin_online(struct cgroup_subsys_state *blkcg_css); +struct list_head *blkcg_get_cgwb_list(struct cgroup_subsys_state *css); +struct cgroup_subsys_state *bio_blkcg_css(struct bio *bio); #else /* CONFIG_BLK_CGROUP */ -struct blkcg { -}; - -struct blkcg_gq { -}; - #define blkcg_root_css ((struct cgroup_subsys_state *)ERR_PTR(-EINVAL)) static inline void blkcg_maybe_throttle_current(void) { } static inline bool blk_cgroup_congested(void) { return false; } - -#ifdef CONFIG_BLOCK static inline void blkcg_schedule_throttle(struct request_queue *q, bool use_memdelay) { } -static inline struct blkcg *bio_blkcg(struct bio *bio) { return NULL; } -#endif /* CONFIG_BLOCK */ - -#endif /* CONFIG_BLK_CGROUP */ - -#ifdef CONFIG_BLK_CGROUP_FC_APPID -/* - * Sets the fc_app_id field associted to blkcg - * @app_id: application identifier - * @cgrp_id: cgroup id - * @app_id_len: size of application identifier - */ -static inline int blkcg_set_fc_appid(char *app_id, u64 cgrp_id, size_t app_id_len) -{ - struct cgroup *cgrp; - struct cgroup_subsys_state *css; - struct blkcg *blkcg; - int ret = 0; - - if (app_id_len > FC_APPID_LEN) - return -EINVAL; - - cgrp = cgroup_get_from_id(cgrp_id); - if (!cgrp) - return -ENOENT; - css = cgroup_get_e_css(cgrp, &io_cgrp_subsys); - if (!css) { - ret = -ENOENT; - goto out_cgrp_put; - } - blkcg = css_to_blkcg(css); - /* - * There is a slight race condition on setting the appid. - * Worst case an I/O may not find the right id. - * This is no different from the I/O we let pass while obtaining - * the vmid from the fabric. - * Adding the overhead of a lock is not necessary. - */ - strlcpy(blkcg->fc_app_id, app_id, app_id_len); - css_put(css); -out_cgrp_put: - cgroup_put(cgrp); - return ret; -} - -/** - * blkcg_get_fc_appid - get the fc app identifier associated with a bio - * @bio: target bio - * - * On success return the fc_app_id, on failure return NULL - */ -static inline char *blkcg_get_fc_appid(struct bio *bio) +static inline struct cgroup_subsys_state *bio_blkcg_css(struct bio *bio) { - if (bio && bio->bi_blkg && - (bio->bi_blkg->blkcg->fc_app_id[0] != '\0')) - return bio->bi_blkg->blkcg->fc_app_id; return NULL; } -#else -static inline int blkcg_set_fc_appid(char *buf, u64 id, size_t len) { return -EINVAL; } -static inline char *blkcg_get_fc_appid(struct bio *bio) { return NULL; } -#endif /*CONFIG_BLK_CGROUP_FC_APPID*/ +#endif /* CONFIG_BLK_CGROUP */ + +int blkcg_set_fc_appid(char *app_id, u64 cgrp_id, size_t app_id_len); +char *blkcg_get_fc_appid(struct bio *bio); + #endif /* _BLK_CGROUP_H */ diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index 1973ef9bd40f..c007d58d2703 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -44,7 +44,7 @@ struct block_device { unsigned long bd_stamp; bool bd_read_only; /* read-only policy */ dev_t bd_dev; - int bd_openers; + atomic_t bd_openers; struct inode * bd_inode; /* will die */ struct super_block * bd_super; void * bd_claiming; @@ -246,9 +246,8 @@ typedef unsigned int blk_qc_t; struct bio { struct bio *bi_next; /* request queue link */ struct block_device *bi_bdev; - unsigned int bi_opf; /* bottom bits req flags, - * top bits REQ_OP. Use - * accessors. + unsigned int bi_opf; /* bottom bits REQ_OP, top bits + * req_flags. */ unsigned short bi_flags; /* BIO_* below */ unsigned short bi_ioprio; @@ -329,7 +328,6 @@ enum { BIO_QOS_MERGED, /* but went through rq_qos merge path */ BIO_REMAPPED, BIO_ZONE_WRITE_LOCKED, /* Owns a zoned device zone write lock */ - BIO_PERCPU_CACHE, /* can participate in per-cpu alloc cache */ BIO_FLAG_LAST }; @@ -409,15 +407,17 @@ enum req_flag_bits { * work item to avoid such priority inversions. */ __REQ_CGROUP_PUNT, + __REQ_POLLED, /* caller polls for completion using bio_poll */ + __REQ_ALLOC_CACHE, /* allocate IO from cache if available */ + __REQ_SWAP, /* swap I/O */ + __REQ_DRV, /* for driver use */ - /* command specific flags for REQ_OP_WRITE_ZEROES: */ + /* + * Command specific flags, keep last: + */ + /* for REQ_OP_WRITE_ZEROES: */ __REQ_NOUNMAP, /* do not free blocks when zeroing */ - __REQ_POLLED, /* caller polls for completion using bio_poll */ - - /* for driver use */ - __REQ_DRV, - __REQ_SWAP, /* swapping request. */ __REQ_NR_BITS, /* stops here */ }; @@ -439,6 +439,7 @@ enum req_flag_bits { #define REQ_NOUNMAP (1ULL << __REQ_NOUNMAP) #define REQ_POLLED (1ULL << __REQ_POLLED) +#define REQ_ALLOC_CACHE (1ULL << __REQ_ALLOC_CACHE) #define REQ_DRV (1ULL << __REQ_DRV) #define REQ_SWAP (1ULL << __REQ_SWAP) diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 60d016138997..5bdf2ac9142c 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -176,6 +176,21 @@ static inline bool disk_live(struct gendisk *disk) return !inode_unhashed(disk->part0->bd_inode); } +/** + * disk_openers - returns how many openers are there for a disk + * @disk: disk to check + * + * This returns the number of openers for a disk. Note that this value is only + * stable if disk->open_mutex is held. + * + * Note: Due to a quirk in the block layer open code, each open partition is + * only counted once even if there are multiple openers. + */ +static inline unsigned int disk_openers(struct gendisk *disk) +{ + return atomic_read(&disk->part0->bd_openers); +} + /* * The gendisk is refcounted by the part0 block_device, and the bd_device * therein is also used for device model presentation in sysfs. @@ -248,6 +263,7 @@ struct queue_limits { unsigned int io_opt; unsigned int max_discard_sectors; unsigned int max_hw_discard_sectors; + unsigned int max_secure_erase_sectors; unsigned int max_write_zeroes_sectors; unsigned int max_zone_append_sectors; unsigned int discard_granularity; @@ -540,10 +556,8 @@ struct request_queue { #define QUEUE_FLAG_NONROT 6 /* non-rotational device (SSD) */ #define QUEUE_FLAG_VIRT QUEUE_FLAG_NONROT /* paravirt device */ #define QUEUE_FLAG_IO_STAT 7 /* do disk/partitions IO accounting */ -#define QUEUE_FLAG_DISCARD 8 /* supports DISCARD */ #define QUEUE_FLAG_NOXMERGES 9 /* No extended merges */ #define QUEUE_FLAG_ADD_RANDOM 10 /* Contributes to random pool */ -#define QUEUE_FLAG_SECERASE 11 /* supports secure erase */ #define QUEUE_FLAG_SAME_FORCE 12 /* force complete on same CPU */ #define QUEUE_FLAG_DEAD 13 /* queue tear-down finished */ #define QUEUE_FLAG_INIT_DONE 14 /* queue is initialized */ @@ -582,11 +596,8 @@ bool blk_queue_flag_test_and_set(unsigned int flag, struct request_queue *q); test_bit(QUEUE_FLAG_STABLE_WRITES, &(q)->queue_flags) #define blk_queue_io_stat(q) test_bit(QUEUE_FLAG_IO_STAT, &(q)->queue_flags) #define blk_queue_add_random(q) test_bit(QUEUE_FLAG_ADD_RANDOM, &(q)->queue_flags) -#define blk_queue_discard(q) test_bit(QUEUE_FLAG_DISCARD, &(q)->queue_flags) #define blk_queue_zone_resetall(q) \ test_bit(QUEUE_FLAG_ZONE_RESETALL, &(q)->queue_flags) -#define blk_queue_secure_erase(q) \ - (test_bit(QUEUE_FLAG_SECERASE, &(q)->queue_flags)) #define blk_queue_dax(q) test_bit(QUEUE_FLAG_DAX, &(q)->queue_flags) #define blk_queue_pci_p2pdma(q) \ test_bit(QUEUE_FLAG_PCI_P2PDMA, &(q)->queue_flags) @@ -602,7 +613,6 @@ bool blk_queue_flag_test_and_set(unsigned int flag, struct request_queue *q); REQ_FAILFAST_DRIVER)) #define blk_queue_quiesced(q) test_bit(QUEUE_FLAG_QUIESCED, &(q)->queue_flags) #define blk_queue_pm_only(q) atomic_read(&(q)->pm_only) -#define blk_queue_fua(q) test_bit(QUEUE_FLAG_FUA, &(q)->queue_flags) #define blk_queue_registered(q) test_bit(QUEUE_FLAG_REGISTERED, &(q)->queue_flags) #define blk_queue_nowait(q) test_bit(QUEUE_FLAG_NOWAIT, &(q)->queue_flags) @@ -950,6 +960,8 @@ extern void blk_queue_chunk_sectors(struct request_queue *, unsigned int); extern void blk_queue_max_segments(struct request_queue *, unsigned short); extern void blk_queue_max_discard_segments(struct request_queue *, unsigned short); +void blk_queue_max_secure_erase_sectors(struct request_queue *q, + unsigned int max_sectors); extern void blk_queue_max_segment_size(struct request_queue *, unsigned int); extern void blk_queue_max_discard_sectors(struct request_queue *q, unsigned int max_discard_sectors); @@ -1090,13 +1102,12 @@ static inline long nr_blockdev_pages(void) extern void blk_io_schedule(void); -#define BLKDEV_DISCARD_SECURE (1 << 0) /* issue a secure erase */ - -extern int blkdev_issue_discard(struct block_device *bdev, sector_t sector, - sector_t nr_sects, gfp_t gfp_mask, unsigned long flags); -extern int __blkdev_issue_discard(struct block_device *bdev, sector_t sector, - sector_t nr_sects, gfp_t gfp_mask, int flags, - struct bio **biop); +int blkdev_issue_discard(struct block_device *bdev, sector_t sector, + sector_t nr_sects, gfp_t gfp_mask); +int __blkdev_issue_discard(struct block_device *bdev, sector_t sector, + sector_t nr_sects, gfp_t gfp_mask, struct bio **biop); +int blkdev_issue_secure_erase(struct block_device *bdev, sector_t sector, + sector_t nr_sects, gfp_t gfp); #define BLKDEV_ZERO_NOUNMAP (1 << 0) /* do not free blocks */ #define BLKDEV_ZERO_NOFALLBACK (1 << 1) /* don't write explicit zeroes */ @@ -1115,7 +1126,7 @@ static inline int sb_issue_discard(struct super_block *sb, sector_t block, SECTOR_SHIFT), nr_blocks << (sb->s_blocksize_bits - SECTOR_SHIFT), - gfp_mask, flags); + gfp_mask); } static inline int sb_issue_zeroout(struct super_block *sb, sector_t block, sector_t nr_blocks, gfp_t gfp_mask) @@ -1189,6 +1200,12 @@ static inline unsigned int queue_max_zone_append_sectors(const struct request_qu return min(l->max_zone_append_sectors, l->max_sectors); } +static inline unsigned int +bdev_max_zone_append_sectors(struct block_device *bdev) +{ + return queue_max_zone_append_sectors(bdev_get_queue(bdev)); +} + static inline unsigned queue_logical_block_size(const struct request_queue *q) { int retval = 512; @@ -1246,84 +1263,54 @@ bdev_zone_write_granularity(struct block_device *bdev) return queue_zone_write_granularity(bdev_get_queue(bdev)); } -static inline int queue_alignment_offset(const struct request_queue *q) -{ - if (q->limits.misaligned) - return -1; +int bdev_alignment_offset(struct block_device *bdev); +unsigned int bdev_discard_alignment(struct block_device *bdev); - return q->limits.alignment_offset; +static inline unsigned int bdev_max_discard_sectors(struct block_device *bdev) +{ + return bdev_get_queue(bdev)->limits.max_discard_sectors; } -static inline int queue_limit_alignment_offset(struct queue_limits *lim, sector_t sector) +static inline unsigned int bdev_discard_granularity(struct block_device *bdev) { - unsigned int granularity = max(lim->physical_block_size, lim->io_min); - unsigned int alignment = sector_div(sector, granularity >> SECTOR_SHIFT) - << SECTOR_SHIFT; + return bdev_get_queue(bdev)->limits.discard_granularity; +} - return (granularity + lim->alignment_offset - alignment) % granularity; +static inline unsigned int +bdev_max_secure_erase_sectors(struct block_device *bdev) +{ + return bdev_get_queue(bdev)->limits.max_secure_erase_sectors; } -static inline int bdev_alignment_offset(struct block_device *bdev) +static inline unsigned int bdev_write_zeroes_sectors(struct block_device *bdev) { struct request_queue *q = bdev_get_queue(bdev); - if (q->limits.misaligned) - return -1; - if (bdev_is_partition(bdev)) - return queue_limit_alignment_offset(&q->limits, - bdev->bd_start_sect); - return q->limits.alignment_offset; + if (q) + return q->limits.max_write_zeroes_sectors; + + return 0; } -static inline int queue_discard_alignment(const struct request_queue *q) +static inline bool bdev_nonrot(struct block_device *bdev) { - if (q->limits.discard_misaligned) - return -1; - - return q->limits.discard_alignment; + return blk_queue_nonrot(bdev_get_queue(bdev)); } -static inline int queue_limit_discard_alignment(struct queue_limits *lim, sector_t sector) +static inline bool bdev_stable_writes(struct block_device *bdev) { - unsigned int alignment, granularity, offset; - - if (!lim->max_discard_sectors) - return 0; - - /* Why are these in bytes, not sectors? */ - alignment = lim->discard_alignment >> SECTOR_SHIFT; - granularity = lim->discard_granularity >> SECTOR_SHIFT; - if (!granularity) - return 0; - - /* Offset of the partition start in 'granularity' sectors */ - offset = sector_div(sector, granularity); - - /* And why do we do this modulus *again* in blkdev_issue_discard()? */ - offset = (granularity + alignment - offset) % granularity; - - /* Turn it back into bytes, gaah */ - return offset << SECTOR_SHIFT; + return test_bit(QUEUE_FLAG_STABLE_WRITES, + &bdev_get_queue(bdev)->queue_flags); } -static inline int bdev_discard_alignment(struct block_device *bdev) +static inline bool bdev_write_cache(struct block_device *bdev) { - struct request_queue *q = bdev_get_queue(bdev); - - if (bdev_is_partition(bdev)) - return queue_limit_discard_alignment(&q->limits, - bdev->bd_start_sect); - return q->limits.discard_alignment; + return test_bit(QUEUE_FLAG_WC, &bdev_get_queue(bdev)->queue_flags); } -static inline unsigned int bdev_write_zeroes_sectors(struct block_device *bdev) +static inline bool bdev_fua(struct block_device *bdev) { - struct request_queue *q = bdev_get_queue(bdev); - - if (q) - return q->limits.max_write_zeroes_sectors; - - return 0; + return test_bit(QUEUE_FLAG_FUA, &bdev_get_queue(bdev)->queue_flags); } static inline enum blk_zoned_model bdev_zoned_model(struct block_device *bdev) @@ -1491,9 +1478,10 @@ static inline void blk_wake_io_task(struct task_struct *waiter) wake_up_process(waiter); } -unsigned long disk_start_io_acct(struct gendisk *disk, unsigned int sectors, - unsigned int op); -void disk_end_io_acct(struct gendisk *disk, unsigned int op, +unsigned long bdev_start_io_acct(struct block_device *bdev, + unsigned int sectors, unsigned int op, + unsigned long start_time); +void bdev_end_io_acct(struct block_device *bdev, unsigned int op, unsigned long start_time); void bio_start_io_acct_time(struct bio *bio, unsigned long start_time); diff --git a/include/linux/blktrace_api.h b/include/linux/blktrace_api.h index 22501a293fa5..623e22492afa 100644 --- a/include/linux/blktrace_api.h +++ b/include/linux/blktrace_api.h @@ -27,12 +27,10 @@ struct blk_trace { atomic_t dropped; }; -struct blkcg; - extern int blk_trace_ioctl(struct block_device *, unsigned, char __user *); extern void blk_trace_shutdown(struct request_queue *); -extern __printf(3, 4) -void __trace_note_message(struct blk_trace *, struct blkcg *blkcg, const char *fmt, ...); +__printf(3, 4) void __blk_trace_note_message(struct blk_trace *bt, + struct cgroup_subsys_state *css, const char *fmt, ...); /** * blk_add_trace_msg - Add a (simple) message to the blktrace stream @@ -47,14 +45,14 @@ void __trace_note_message(struct blk_trace *, struct blkcg *blkcg, const char *f * NOTE: Can not use 'static inline' due to presence of var args... * **/ -#define blk_add_cgroup_trace_msg(q, cg, fmt, ...) \ +#define blk_add_cgroup_trace_msg(q, css, fmt, ...) \ do { \ struct blk_trace *bt; \ \ rcu_read_lock(); \ bt = rcu_dereference((q)->blk_trace); \ if (unlikely(bt)) \ - __trace_note_message(bt, cg, fmt, ##__VA_ARGS__);\ + __blk_trace_note_message(bt, css, fmt, ##__VA_ARGS__);\ rcu_read_unlock(); \ } while (0) #define blk_add_trace_msg(q, fmt, ...) \ diff --git a/include/linux/bpf.h b/include/linux/bpf.h index bdb5298735ce..ecc3d3ec41cf 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -2085,6 +2085,8 @@ void bpf_offload_dev_netdev_unregister(struct bpf_offload_dev *offdev, struct net_device *netdev); bool bpf_offload_dev_match(struct bpf_prog *prog, struct net_device *netdev); +void unpriv_ebpf_notify(int new_state); + #if defined(CONFIG_NET) && defined(CONFIG_BPF_SYSCALL) int bpf_prog_offload_init(struct bpf_prog *prog, union bpf_attr *attr); diff --git a/include/linux/cc_platform.h b/include/linux/cc_platform.h index efd8205282da..cb0d6cd1c12f 100644 --- a/include/linux/cc_platform.h +++ b/include/linux/cc_platform.h @@ -72,6 +72,24 @@ enum cc_attr { * Examples include TDX guest & SEV. */ CC_ATTR_GUEST_UNROLL_STRING_IO, + + /** + * @CC_ATTR_SEV_SNP: Guest SNP is active. + * + * The platform/OS is running as a guest/virtual machine and actively + * using AMD SEV-SNP features. + */ + CC_ATTR_GUEST_SEV_SNP, + + /** + * @CC_ATTR_HOTPLUG_DISABLED: Hotplug is not supported or disabled. + * + * The platform/OS is running as a guest/virtual machine does not + * support CPU hotplug feature. + * + * Examples include TDX Guest. + */ + CC_ATTR_HOTPLUG_DISABLED, }; #ifdef CONFIG_ARCH_HAS_CC_PLATFORM diff --git a/include/linux/cdrom.h b/include/linux/cdrom.h index 0a89f111e00e..67caa909e3e6 100644 --- a/include/linux/cdrom.h +++ b/include/linux/cdrom.h @@ -77,7 +77,6 @@ struct cdrom_device_ops { int (*tray_move) (struct cdrom_device_info *, int); int (*lock_door) (struct cdrom_device_info *, int); int (*select_speed) (struct cdrom_device_info *, int); - int (*select_disc) (struct cdrom_device_info *, int); int (*get_last_session) (struct cdrom_device_info *, struct cdrom_multisession *); int (*get_mcn) (struct cdrom_device_info *, diff --git a/include/linux/ceph/osd_client.h b/include/linux/ceph/osd_client.h index 3431011f364d..cba8a6ffc329 100644 --- a/include/linux/ceph/osd_client.h +++ b/include/linux/ceph/osd_client.h @@ -287,6 +287,9 @@ struct ceph_osd_linger_request { rados_watcherrcb_t errcb; void *data; + struct ceph_pagelist *request_pl; + struct page **notify_id_pages; + struct page ***preply_pages; size_t *preply_len; }; diff --git a/include/linux/cper.h b/include/linux/cper.h index 6a511a1078ca..eacb7dd7b3af 100644 --- a/include/linux/cper.h +++ b/include/linux/cper.h @@ -558,6 +558,7 @@ extern const char *const cper_proc_error_type_strs[4]; u64 cper_next_record_id(void); const char *cper_severity_str(unsigned int); const char *cper_mem_err_type_str(unsigned int); +const char *cper_mem_err_status_str(u64 status); void cper_print_bits(const char *prefix, unsigned int bits, const char * const strs[], unsigned int strs_size); void cper_mem_err_pack(const struct cper_sec_mem_err *, @@ -568,5 +569,7 @@ void cper_print_proc_arm(const char *pfx, const struct cper_sec_proc_arm *proc); void cper_print_proc_ia(const char *pfx, const struct cper_sec_proc_ia *proc); +int cper_mem_err_location(struct cper_mem_err_compact *mem, char *msg); +int cper_dimm_err_location(struct cper_mem_err_compact *mem, char *msg); #endif diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h index 35c7d6db4139..d5595d57f4e5 100644 --- a/include/linux/cpufreq.h +++ b/include/linux/cpufreq.h @@ -1199,7 +1199,6 @@ static inline void sched_cpufreq_governor_change(struct cpufreq_policy *policy, struct cpufreq_governor *old_gov) { } #endif -extern void arch_freq_prepare_all(void); extern unsigned int arch_freq_get_on_cpu(int cpu); #ifndef arch_set_freq_scale diff --git a/include/linux/efi.h b/include/linux/efi.h index ccd4d3f91c98..db424f3dc3f2 100644 --- a/include/linux/efi.h +++ b/include/linux/efi.h @@ -213,6 +213,8 @@ struct capsule_info { size_t page_bytes_remain; }; +int efi_capsule_setup_info(struct capsule_info *cap_info, void *kbuff, + size_t hdr_bytes); int __efi_capsule_setup_info(struct capsule_info *cap_info); /* @@ -383,6 +385,7 @@ void efi_native_runtime_setup(void); #define EFI_LOAD_FILE_PROTOCOL_GUID EFI_GUID(0x56ec3091, 0x954c, 0x11d2, 0x8e, 0x3f, 0x00, 0xa0, 0xc9, 0x69, 0x72, 0x3b) #define EFI_LOAD_FILE2_PROTOCOL_GUID EFI_GUID(0x4006c0c1, 0xfcb3, 0x403e, 0x99, 0x6d, 0x4a, 0x6c, 0x87, 0x24, 0xe0, 0x6d) #define EFI_RT_PROPERTIES_TABLE_GUID EFI_GUID(0xeb66918a, 0x7eef, 0x402a, 0x84, 0x2e, 0x93, 0x1d, 0x21, 0xc3, 0x8a, 0xe9) +#define EFI_DXE_SERVICES_TABLE_GUID EFI_GUID(0x05ad34ba, 0x6f02, 0x4214, 0x95, 0x2e, 0x4d, 0xa0, 0x39, 0x8e, 0x2b, 0xb9) #define EFI_IMAGE_SECURITY_DATABASE_GUID EFI_GUID(0xd719b2cb, 0x3d3a, 0x4596, 0xa3, 0xbc, 0xda, 0xd0, 0x0e, 0x67, 0x65, 0x6f) #define EFI_SHIM_LOCK_GUID EFI_GUID(0x605dab50, 0xe046, 0x4300, 0xab, 0xb6, 0x3d, 0xd8, 0x10, 0xdd, 0x8b, 0x23) @@ -390,6 +393,7 @@ void efi_native_runtime_setup(void); #define EFI_CERT_SHA256_GUID EFI_GUID(0xc1c41626, 0x504c, 0x4092, 0xac, 0xa9, 0x41, 0xf9, 0x36, 0x93, 0x43, 0x28) #define EFI_CERT_X509_GUID EFI_GUID(0xa5c059a1, 0x94e4, 0x4aa7, 0x87, 0xb5, 0xab, 0x15, 0x5c, 0x2b, 0xf0, 0x72) #define EFI_CERT_X509_SHA256_GUID EFI_GUID(0x3bd2a492, 0x96c0, 0x4079, 0xb4, 0x20, 0xfc, 0xf9, 0x8e, 0xf1, 0x03, 0xed) +#define EFI_CC_BLOB_GUID EFI_GUID(0x067b1f5f, 0xcf26, 0x44c5, 0x85, 0x54, 0x93, 0xd7, 0x77, 0x91, 0x2d, 0x42) /* * This GUID is used to pass to the kernel proper the struct screen_info @@ -405,6 +409,20 @@ void efi_native_runtime_setup(void); #define LINUX_EFI_MEMRESERVE_TABLE_GUID EFI_GUID(0x888eb0c6, 0x8ede, 0x4ff5, 0xa8, 0xf0, 0x9a, 0xee, 0x5c, 0xb9, 0x77, 0xc2) #define LINUX_EFI_INITRD_MEDIA_GUID EFI_GUID(0x5568e427, 0x68fc, 0x4f3d, 0xac, 0x74, 0xca, 0x55, 0x52, 0x31, 0xcc, 0x68) #define LINUX_EFI_MOK_VARIABLE_TABLE_GUID EFI_GUID(0xc451ed2b, 0x9694, 0x45d3, 0xba, 0xba, 0xed, 0x9f, 0x89, 0x88, 0xa3, 0x89) +#define LINUX_EFI_COCO_SECRET_AREA_GUID EFI_GUID(0xadf956ad, 0xe98c, 0x484c, 0xae, 0x11, 0xb5, 0x1c, 0x7d, 0x33, 0x64, 0x47) + +#define RISCV_EFI_BOOT_PROTOCOL_GUID EFI_GUID(0xccd15fec, 0x6f73, 0x4eec, 0x83, 0x95, 0x3e, 0x69, 0xe4, 0xb9, 0x40, 0xbf) + +/* + * This GUID may be installed onto the kernel image's handle as a NULL protocol + * to signal to the stub that the placement of the image should be respected, + * and moving the image in physical memory is undesirable. To ensure + * compatibility with 64k pages kernels with virtually mapped stacks, and to + * avoid defeating physical randomization, this protocol should only be + * installed if the image was placed at a randomized 128k aligned address in + * memory. + */ +#define LINUX_EFI_LOADED_IMAGE_FIXED_GUID EFI_GUID(0xf5a37b6d, 0x3344, 0x42a5, 0xb6, 0xbb, 0x97, 0x86, 0x48, 0xc1, 0x89, 0x0a) /* OEM GUIDs */ #define DELLEMC_EFI_RCI2_TABLE_GUID EFI_GUID(0x2d9f28a2, 0xa886, 0x456a, 0x97, 0xa8, 0xf1, 0x1e, 0xf2, 0x4f, 0xf4, 0x55) @@ -435,6 +453,7 @@ typedef struct { } efi_config_table_type_t; #define EFI_SYSTEM_TABLE_SIGNATURE ((u64)0x5453595320494249ULL) +#define EFI_DXE_SERVICES_TABLE_SIGNATURE ((u64)0x565245535f455844ULL) #define EFI_2_30_SYSTEM_TABLE_REVISION ((2 << 16) | (30)) #define EFI_2_20_SYSTEM_TABLE_REVISION ((2 << 16) | (20)) @@ -596,6 +615,7 @@ extern struct efi { unsigned long tpm_log; /* TPM2 Event Log table */ unsigned long tpm_final_log; /* TPM2 Final Events Log table */ unsigned long mokvar_table; /* MOK variable config table */ + unsigned long coco_secret; /* Confidential computing secret table */ efi_get_time_t *get_time; efi_set_time_t *set_time; @@ -1335,4 +1355,12 @@ extern void efifb_setup_from_dmi(struct screen_info *si, const char *opt); static inline void efifb_setup_from_dmi(struct screen_info *si, const char *opt) { } #endif +struct linux_efi_coco_secret_area { + u64 base_pa; + u64 size; +}; + +/* Header of a populated EFI secret area */ +#define EFI_SECRET_TABLE_HEADER_GUID EFI_GUID(0x1e74f542, 0x71dd, 0x4d66, 0x96, 0x3e, 0xef, 0x42, 0x87, 0xff, 0x17, 0x3b) + #endif /* _LINUX_EFI_H */ diff --git a/include/linux/elfcore.h b/include/linux/elfcore.h index f8e206e82476..346a8b56cdc8 100644 --- a/include/linux/elfcore.h +++ b/include/linux/elfcore.h @@ -84,15 +84,6 @@ static inline void elf_core_copy_regs(elf_gregset_t *elfregs, struct pt_regs *re #endif } -static inline void elf_core_copy_kernel_regs(elf_gregset_t *elfregs, struct pt_regs *regs) -{ -#ifdef ELF_CORE_COPY_KERNEL_REGS - ELF_CORE_COPY_KERNEL_REGS((*elfregs), regs); -#else - elf_core_copy_regs(elfregs, regs); -#endif -} - static inline int elf_core_copy_task_regs(struct task_struct *t, elf_gregset_t* elfregs) { #if defined (ELF_CORE_COPY_TASK_REGS) diff --git a/include/linux/fs.h b/include/linux/fs.h index bbde95387a23..87b5af1d9fbe 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1953,6 +1953,7 @@ struct dir_context { #define REMAP_FILE_ADVISORY (REMAP_FILE_CAN_SHORTEN) struct iov_iter; +struct io_uring_cmd; struct file_operations { struct module *owner; @@ -1995,6 +1996,7 @@ struct file_operations { struct file *file_out, loff_t pos_out, loff_t len, unsigned int remap_flags); int (*fadvise)(struct file *, loff_t, loff_t, int); + int (*uring_cmd)(struct io_uring_cmd *ioucmd, unsigned int issue_flags); } __randomize_layout; struct inode_operations { diff --git a/include/linux/gpio/driver.h b/include/linux/gpio/driver.h index 874aabd270c9..cb689264f3e9 100644 --- a/include/linux/gpio/driver.h +++ b/include/linux/gpio/driver.h @@ -588,6 +588,22 @@ void gpiochip_relres_irq(struct gpio_chip *gc, unsigned int offset); void gpiochip_disable_irq(struct gpio_chip *gc, unsigned int offset); void gpiochip_enable_irq(struct gpio_chip *gc, unsigned int offset); +/* irq_data versions of the above */ +int gpiochip_irq_reqres(struct irq_data *data); +void gpiochip_irq_relres(struct irq_data *data); + +/* Paste this in your irq_chip structure */ +#define GPIOCHIP_IRQ_RESOURCE_HELPERS \ + .irq_request_resources = gpiochip_irq_reqres, \ + .irq_release_resources = gpiochip_irq_relres + +static inline void gpio_irq_chip_set_chip(struct gpio_irq_chip *girq, + const struct irq_chip *chip) +{ + /* Yes, dropping const is ugly, but it isn't like we have a choice */ + girq->chip = (struct irq_chip *)chip; +} + /* Line status inquiry for drivers */ bool gpiochip_line_is_open_drain(struct gpio_chip *gc, unsigned int offset); bool gpiochip_line_is_open_source(struct gpio_chip *gc, unsigned int offset); diff --git a/include/linux/io_uring.h b/include/linux/io_uring.h index 1814e698d861..4a2f6cc5a492 100644 --- a/include/linux/io_uring.h +++ b/include/linux/io_uring.h @@ -5,11 +5,37 @@ #include <linux/sched.h> #include <linux/xarray.h> +enum io_uring_cmd_flags { + IO_URING_F_COMPLETE_DEFER = 1, + IO_URING_F_UNLOCKED = 2, + /* int's last bit, sign checks are usually faster than a bit test */ + IO_URING_F_NONBLOCK = INT_MIN, + + /* ctx state flags, for URING_CMD */ + IO_URING_F_SQE128 = 4, + IO_URING_F_CQE32 = 8, + IO_URING_F_IOPOLL = 16, +}; + +struct io_uring_cmd { + struct file *file; + const void *cmd; + /* callback to defer completions to task context */ + void (*task_work_cb)(struct io_uring_cmd *cmd); + u32 cmd_op; + u32 pad; + u8 pdu[32]; /* available inline for free use */ +}; + #if defined(CONFIG_IO_URING) +void io_uring_cmd_done(struct io_uring_cmd *cmd, ssize_t ret, ssize_t res2); +void io_uring_cmd_complete_in_task(struct io_uring_cmd *ioucmd, + void (*task_work_cb)(struct io_uring_cmd *)); struct sock *io_uring_get_socket(struct file *file); void __io_uring_cancel(bool cancel_all); void __io_uring_free(struct task_struct *tsk); void io_uring_unreg_ringfd(void); +const char *io_uring_get_opcode(u8 opcode); static inline void io_uring_files_cancel(void) { @@ -29,6 +55,14 @@ static inline void io_uring_free(struct task_struct *tsk) __io_uring_free(tsk); } #else +static inline void io_uring_cmd_done(struct io_uring_cmd *cmd, ssize_t ret, + ssize_t ret2) +{ +} +static inline void io_uring_cmd_complete_in_task(struct io_uring_cmd *ioucmd, + void (*task_work_cb)(struct io_uring_cmd *)) +{ +} static inline struct sock *io_uring_get_socket(struct file *file) { return NULL; @@ -42,6 +76,10 @@ static inline void io_uring_files_cancel(void) static inline void io_uring_free(struct task_struct *tsk) { } +static inline const char *io_uring_get_opcode(u8 opcode) +{ + return ""; +} #endif #endif diff --git a/include/linux/irq.h b/include/linux/irq.h index f92788ccdba2..505308253d23 100644 --- a/include/linux/irq.h +++ b/include/linux/irq.h @@ -569,6 +569,7 @@ struct irq_chip { * IRQCHIP_ENABLE_WAKEUP_ON_SUSPEND: Invokes __enable_irq()/__disable_irq() for wake irqs * in the suspend path if they are in disabled state * IRQCHIP_AFFINITY_PRE_STARTUP: Default affinity update before startup + * IRQCHIP_IMMUTABLE: Don't ever change anything in this chip */ enum { IRQCHIP_SET_TYPE_MASKED = (1 << 0), @@ -582,6 +583,7 @@ enum { IRQCHIP_SUPPORTS_NMI = (1 << 8), IRQCHIP_ENABLE_WAKEUP_ON_SUSPEND = (1 << 9), IRQCHIP_AFFINITY_PRE_STARTUP = (1 << 10), + IRQCHIP_IMMUTABLE = (1 << 11), }; #include <linux/irqdesc.h> diff --git a/include/linux/irqchip/arm-gic-v3.h b/include/linux/irqchip/arm-gic-v3.h index 12d91f0dedf9..728691365464 100644 --- a/include/linux/irqchip/arm-gic-v3.h +++ b/include/linux/irqchip/arm-gic-v3.h @@ -127,6 +127,8 @@ #define GICR_PIDR2 GICD_PIDR2 #define GICR_CTLR_ENABLE_LPIS (1UL << 0) +#define GICR_CTLR_CES (1UL << 1) +#define GICR_CTLR_IR (1UL << 2) #define GICR_CTLR_RWP (1UL << 3) #define GICR_TYPER_CPU_NUMBER(r) (((r) >> 8) & 0xffff) diff --git a/include/linux/kthread.h b/include/linux/kthread.h index de5d75bafd66..30e5bec81d2b 100644 --- a/include/linux/kthread.h +++ b/include/linux/kthread.h @@ -222,9 +222,5 @@ void kthread_associate_blkcg(struct cgroup_subsys_state *css); struct cgroup_subsys_state *kthread_blkcg(void); #else static inline void kthread_associate_blkcg(struct cgroup_subsys_state *css) { } -static inline struct cgroup_subsys_state *kthread_blkcg(void) -{ - return NULL; -} #endif #endif /* _LINUX_KTHREAD_H */ diff --git a/include/linux/libata.h b/include/linux/libata.h index 9b1d3d8b1252..732de9014626 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -820,7 +820,6 @@ struct ata_port { unsigned int cbl; /* cable type; ATA_CBL_xxx */ struct ata_queued_cmd qcmd[ATA_MAX_QUEUE + 1]; - unsigned long sas_tag_allocated; /* for sas tag allocation only */ u64 qc_active; int nr_active_links; /* #links with active qcs */ unsigned int sas_last_tag; /* track next tag hw expects */ @@ -1111,7 +1110,7 @@ extern void ata_unpack_xfermask(unsigned long xfer_mask, unsigned long *udma_mask); extern u8 ata_xfer_mask2mode(unsigned long xfer_mask); extern unsigned long ata_xfer_mode2mask(u8 xfer_mode); -extern int ata_xfer_mode2shift(unsigned long xfer_mode); +extern int ata_xfer_mode2shift(u8 xfer_mode); extern const char *ata_mode_string(unsigned long xfer_mask); extern unsigned long ata_id_xfermask(const u16 *id); extern int ata_std_qc_defer(struct ata_queued_cmd *qc); diff --git a/include/linux/linkage.h b/include/linux/linkage.h index acb1ad2356f1..1feab6136b5b 100644 --- a/include/linux/linkage.h +++ b/include/linux/linkage.h @@ -171,12 +171,9 @@ /* SYM_ALIAS -- use only if you have to */ #ifndef SYM_ALIAS -#define SYM_ALIAS(alias, name, sym_type, linkage) \ - linkage(alias) ASM_NL \ - .set alias, name ASM_NL \ - .type alias sym_type ASM_NL \ - .set .L__sym_size_##alias, .L__sym_size_##name ASM_NL \ - .size alias, .L__sym_size_##alias +#define SYM_ALIAS(alias, name, linkage) \ + linkage(alias) ASM_NL \ + .set alias, name ASM_NL #endif /* === code annotations === */ @@ -261,7 +258,7 @@ */ #ifndef SYM_FUNC_ALIAS #define SYM_FUNC_ALIAS(alias, name) \ - SYM_ALIAS(alias, name, SYM_T_FUNC, SYM_L_GLOBAL) + SYM_ALIAS(alias, name, SYM_L_GLOBAL) #endif /* @@ -269,7 +266,7 @@ */ #ifndef SYM_FUNC_ALIAS_LOCAL #define SYM_FUNC_ALIAS_LOCAL(alias, name) \ - SYM_ALIAS(alias, name, SYM_T_FUNC, SYM_L_LOCAL) + SYM_ALIAS(alias, name, SYM_L_LOCAL) #endif /* @@ -277,7 +274,7 @@ */ #ifndef SYM_FUNC_ALIAS_WEAK #define SYM_FUNC_ALIAS_WEAK(alias, name) \ - SYM_ALIAS(alias, name, SYM_T_FUNC, SYM_L_WEAK) + SYM_ALIAS(alias, name, SYM_L_WEAK) #endif /* SYM_CODE_START -- use for non-C (special) functions */ diff --git a/include/linux/netdev_features.h b/include/linux/netdev_features.h index 2c6b9e416225..7c2d77d75a88 100644 --- a/include/linux/netdev_features.h +++ b/include/linux/netdev_features.h @@ -169,7 +169,7 @@ enum { #define NETIF_F_HW_HSR_FWD __NETIF_F(HW_HSR_FWD) #define NETIF_F_HW_HSR_DUP __NETIF_F(HW_HSR_DUP) -/* Finds the next feature with the highest number of the range of start till 0. +/* Finds the next feature with the highest number of the range of start-1 till 0. */ static inline int find_next_netdev_feature(u64 feature, unsigned long start) { @@ -188,7 +188,7 @@ static inline int find_next_netdev_feature(u64 feature, unsigned long start) for ((bit) = find_next_netdev_feature((mask_addr), \ NETDEV_FEATURE_COUNT); \ (bit) >= 0; \ - (bit) = find_next_netdev_feature((mask_addr), (bit) - 1)) + (bit) = find_next_netdev_feature((mask_addr), (bit))) /* Features valid for ethtool to change */ /* = all defined minus driver/device-class-related */ diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index b1fbe21650bb..f736c020cde2 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -900,7 +900,7 @@ struct net_device_path_stack { struct net_device_path_ctx { const struct net_device *dev; - const u8 *daddr; + u8 daddr[ETH_ALEN]; int num_vlans; struct { diff --git a/include/linux/nvme.h b/include/linux/nvme.h index f626a445d1a8..29ec3e3481ff 100644 --- a/include/linux/nvme.h +++ b/include/linux/nvme.h @@ -137,6 +137,7 @@ enum { NVME_REG_CMBMSC = 0x0050, /* Controller Memory Buffer Memory * Space Control */ + NVME_REG_CRTO = 0x0068, /* Controller Ready Timeouts */ NVME_REG_PMRCAP = 0x0e00, /* Persistent Memory Capabilities */ NVME_REG_PMRCTL = 0x0e04, /* Persistent Memory Region Control */ NVME_REG_PMRSTS = 0x0e08, /* Persistent Memory Region Status */ @@ -161,6 +162,9 @@ enum { #define NVME_CMB_BIR(cmbloc) ((cmbloc) & 0x7) #define NVME_CMB_OFST(cmbloc) (((cmbloc) >> 12) & 0xfffff) +#define NVME_CRTO_CRIMT(crto) ((crto) >> 16) +#define NVME_CRTO_CRWMT(crto) ((crto) & 0xffff) + enum { NVME_CMBSZ_SQS = 1 << 0, NVME_CMBSZ_CQS = 1 << 1, @@ -204,8 +208,10 @@ enum { NVME_CC_SHN_MASK = 3 << NVME_CC_SHN_SHIFT, NVME_CC_IOSQES = NVME_NVM_IOSQES << NVME_CC_IOSQES_SHIFT, NVME_CC_IOCQES = NVME_NVM_IOCQES << NVME_CC_IOCQES_SHIFT, - NVME_CAP_CSS_NVM = 1 << 0, - NVME_CAP_CSS_CSI = 1 << 6, + NVME_CC_CRIME = 1 << 24, +}; + +enum { NVME_CSTS_RDY = 1 << 0, NVME_CSTS_CFS = 1 << 1, NVME_CSTS_NSSRO = 1 << 4, @@ -214,10 +220,23 @@ enum { NVME_CSTS_SHST_OCCUR = 1 << 2, NVME_CSTS_SHST_CMPLT = 2 << 2, NVME_CSTS_SHST_MASK = 3 << 2, +}; + +enum { NVME_CMBMSC_CRE = 1 << 0, NVME_CMBMSC_CMSE = 1 << 1, }; +enum { + NVME_CAP_CSS_NVM = 1 << 0, + NVME_CAP_CSS_CSI = 1 << 6, +}; + +enum { + NVME_CAP_CRMS_CRIMS = 1ULL << 59, + NVME_CAP_CRMS_CRWMS = 1ULL << 60, +}; + struct nvme_id_power_state { __le16 max_power; /* centiwatts */ __u8 rsvd2; @@ -405,6 +424,21 @@ struct nvme_id_ns { __u8 vs[3712]; }; +/* I/O Command Set Independent Identify Namespace Data Structure */ +struct nvme_id_ns_cs_indep { + __u8 nsfeat; + __u8 nmic; + __u8 rescap; + __u8 fpi; + __le32 anagrpid; + __u8 nsattr; + __u8 rsvd9; + __le16 nvmsetid; + __le16 endgid; + __u8 nstat; + __u8 rsvd15[4081]; +}; + struct nvme_zns_lbafe { __le64 zsze; __u8 zdes; @@ -469,6 +503,7 @@ enum { NVME_ID_CNS_NS_DESC_LIST = 0x03, NVME_ID_CNS_CS_NS = 0x05, NVME_ID_CNS_CS_CTRL = 0x06, + NVME_ID_CNS_NS_CS_INDEP = 0x08, NVME_ID_CNS_NS_PRESENT_LIST = 0x10, NVME_ID_CNS_NS_PRESENT = 0x11, NVME_ID_CNS_CTRL_NS_LIST = 0x12, @@ -523,6 +558,10 @@ enum { }; enum { + NVME_NSTAT_NRDY = 1 << 0, +}; + +enum { NVME_NVM_NS_16B_GUARD = 0, NVME_NVM_NS_32B_GUARD = 1, NVME_NVM_NS_64B_GUARD = 2, @@ -1583,6 +1622,7 @@ enum { NVME_SC_NS_WRITE_PROTECTED = 0x20, NVME_SC_CMD_INTERRUPTED = 0x21, NVME_SC_TRANSIENT_TR_ERR = 0x22, + NVME_SC_ADMIN_COMMAND_MEDIA_NOT_READY = 0x24, NVME_SC_INVALID_IO_CMD_SET = 0x2C, NVME_SC_LBA_RANGE = 0x80, @@ -1679,9 +1719,11 @@ enum { /* * Path-related Errors: */ + NVME_SC_INTERNAL_PATH_ERROR = 0x300, NVME_SC_ANA_PERSISTENT_LOSS = 0x301, NVME_SC_ANA_INACCESSIBLE = 0x302, NVME_SC_ANA_TRANSITION = 0x303, + NVME_SC_CTRL_PATH_ERROR = 0x360, NVME_SC_HOST_PATH_ERROR = 0x370, NVME_SC_HOST_ABORTED_CMD = 0x371, diff --git a/include/linux/objtool.h b/include/linux/objtool.h index 586d35720f13..b9c1474a571e 100644 --- a/include/linux/objtool.h +++ b/include/linux/objtool.h @@ -40,6 +40,8 @@ struct unwind_hint { #ifdef CONFIG_STACK_VALIDATION +#include <asm/asm.h> + #ifndef __ASSEMBLY__ #define UNWIND_HINT(sp_reg, sp_offset, type, end) \ @@ -137,7 +139,7 @@ struct unwind_hint { .macro STACK_FRAME_NON_STANDARD func:req .pushsection .discard.func_stack_frame_non_standard, "aw" - .long \func - . + _ASM_PTR \func .popsection .endm diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index e7c39c200e2b..1a32036c918c 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -196,6 +196,7 @@ void synchronize_rcu_tasks_rude(void); void exit_tasks_rcu_start(void); void exit_tasks_rcu_finish(void); #else /* #ifdef CONFIG_TASKS_RCU_GENERIC */ +#define rcu_tasks_classic_qs(t, preempt) do { } while (0) #define rcu_tasks_qs(t, preempt) do { } while (0) #define rcu_note_voluntary_context_switch(t) do { } while (0) #define call_rcu_tasks call_rcu diff --git a/include/linux/sched.h b/include/linux/sched.h index a8911b1f35aa..6e6174dbf6e8 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -941,6 +941,9 @@ struct task_struct { #ifdef CONFIG_IOMMU_SVA unsigned pasid_activated:1; #endif +#ifdef CONFIG_CPU_SUP_INTEL + unsigned reported_split_lock:1; +#endif unsigned long atomic_flags; /* Flags requiring atomic access. */ @@ -2118,6 +2121,47 @@ static inline void cond_resched_rcu(void) #endif } +#ifdef CONFIG_PREEMPT_DYNAMIC + +extern bool preempt_model_none(void); +extern bool preempt_model_voluntary(void); +extern bool preempt_model_full(void); + +#else + +static inline bool preempt_model_none(void) +{ + return IS_ENABLED(CONFIG_PREEMPT_NONE); +} +static inline bool preempt_model_voluntary(void) +{ + return IS_ENABLED(CONFIG_PREEMPT_VOLUNTARY); +} +static inline bool preempt_model_full(void) +{ + return IS_ENABLED(CONFIG_PREEMPT); +} + +#endif + +static inline bool preempt_model_rt(void) +{ + return IS_ENABLED(CONFIG_PREEMPT_RT); +} + +/* + * Does the preemption model allow non-cooperative preemption? + * + * For !CONFIG_PREEMPT_DYNAMIC kernels this is an exact match with + * CONFIG_PREEMPTION; for CONFIG_PREEMPT_DYNAMIC this doesn't work as the + * kernel is *built* with CONFIG_PREEMPTION=y but may run with e.g. the + * PREEMPT_NONE model. + */ +static inline bool preempt_model_preemptible(void) +{ + return preempt_model_full() || preempt_model_rt(); +} + /* * Does a critical section need to be broken due to another * task waiting?: (technically does not depend on CONFIG_PREEMPTION, diff --git a/include/linux/sched/signal.h b/include/linux/sched/signal.h index 3c8b34876744..66b689f6cfcb 100644 --- a/include/linux/sched/signal.h +++ b/include/linux/sched/signal.h @@ -356,13 +356,22 @@ static inline void clear_notify_signal(void) } /* + * Returns 'true' if kick_process() is needed to force a transition from + * user -> kernel to guarantee expedient run of TWA_SIGNAL based task_work. + */ +static inline bool __set_notify_signal(struct task_struct *task) +{ + return !test_and_set_tsk_thread_flag(task, TIF_NOTIFY_SIGNAL) && + !wake_up_state(task, TASK_INTERRUPTIBLE); +} + +/* * Called to break out of interruptible wait loops, and enter the * exit_to_user_mode_loop(). */ static inline void set_notify_signal(struct task_struct *task) { - if (!test_and_set_tsk_thread_flag(task, TIF_NOTIFY_SIGNAL) && - !wake_up_state(task, TASK_INTERRUPTIBLE)) + if (__set_notify_signal(task)) kick_process(task); } diff --git a/include/linux/socket.h b/include/linux/socket.h index 6f85f5d957ef..17311ad9f9af 100644 --- a/include/linux/socket.h +++ b/include/linux/socket.h @@ -50,6 +50,9 @@ struct linger { struct msghdr { void *msg_name; /* ptr to socket address structure */ int msg_namelen; /* size of socket address structure */ + + int msg_inq; /* output, data left in socket */ + struct iov_iter msg_iter; /* data */ /* @@ -62,8 +65,9 @@ struct msghdr { void __user *msg_control_user; }; bool msg_control_is_user : 1; - __kernel_size_t msg_controllen; /* ancillary data buffer length */ + bool msg_get_inq : 1;/* return INQ after receive */ unsigned int msg_flags; /* flags on received message */ + __kernel_size_t msg_controllen; /* ancillary data buffer length */ struct kiocb *msg_iocb; /* ptr to iocb for async requests */ }; @@ -434,6 +438,7 @@ extern struct file *do_accept(struct file *file, unsigned file_flags, extern int __sys_accept4(int fd, struct sockaddr __user *upeer_sockaddr, int __user *upeer_addrlen, int flags); extern int __sys_socket(int family, int type, int protocol); +extern struct file *__sys_socket_file(int family, int type, int protocol); extern int __sys_bind(int fd, struct sockaddr __user *umyaddr, int addrlen); extern int __sys_connect_file(struct file *file, struct sockaddr_storage *addr, int addrlen, int file_flags); diff --git a/include/linux/srcutree.h b/include/linux/srcutree.h index cb1f4351e8ba..e3014319d1ad 100644 --- a/include/linux/srcutree.h +++ b/include/linux/srcutree.h @@ -47,11 +47,9 @@ struct srcu_data { */ struct srcu_node { spinlock_t __private lock; - unsigned long srcu_have_cbs[4]; /* GP seq for children */ - /* having CBs, but only */ - /* is > ->srcu_gq_seq. */ - unsigned long srcu_data_have_cbs[4]; /* Which srcu_data structs */ - /* have CBs for given GP? */ + unsigned long srcu_have_cbs[4]; /* GP seq for children having CBs, but only */ + /* if greater than ->srcu_gq_seq. */ + unsigned long srcu_data_have_cbs[4]; /* Which srcu_data structs have CBs for given GP? */ unsigned long srcu_gp_seq_needed_exp; /* Furthest future exp GP. */ struct srcu_node *srcu_parent; /* Next up in tree. */ int grplo; /* Least CPU for node. */ @@ -62,18 +60,24 @@ struct srcu_node { * Per-SRCU-domain structure, similar in function to rcu_state. */ struct srcu_struct { - struct srcu_node node[NUM_RCU_NODES]; /* Combining tree. */ + struct srcu_node *node; /* Combining tree. */ struct srcu_node *level[RCU_NUM_LVLS + 1]; /* First node at each level. */ + int srcu_size_state; /* Small-to-big transition state. */ struct mutex srcu_cb_mutex; /* Serialize CB preparation. */ - spinlock_t __private lock; /* Protect counters */ + spinlock_t __private lock; /* Protect counters and size state. */ struct mutex srcu_gp_mutex; /* Serialize GP work. */ unsigned int srcu_idx; /* Current rdr array element. */ unsigned long srcu_gp_seq; /* Grace-period seq #. */ unsigned long srcu_gp_seq_needed; /* Latest gp_seq needed. */ unsigned long srcu_gp_seq_needed_exp; /* Furthest future exp GP. */ + unsigned long srcu_gp_start; /* Last GP start timestamp (jiffies) */ unsigned long srcu_last_gp_end; /* Last GP end timestamp (ns) */ + unsigned long srcu_size_jiffies; /* Current contention-measurement interval. */ + unsigned long srcu_n_lock_retries; /* Contention events in current interval. */ + unsigned long srcu_n_exp_nodelay; /* # expedited no-delays in current GP phase. */ struct srcu_data __percpu *sda; /* Per-CPU srcu_data array. */ + bool sda_is_static; /* May ->sda be passed to free_percpu()? */ unsigned long srcu_barrier_seq; /* srcu_barrier seq #. */ struct mutex srcu_barrier_mutex; /* Serialize barrier ops. */ struct completion srcu_barrier_completion; @@ -81,10 +85,23 @@ struct srcu_struct { atomic_t srcu_barrier_cpu_cnt; /* # CPUs not yet posting a */ /* callback for the barrier */ /* operation. */ + unsigned long reschedule_jiffies; + unsigned long reschedule_count; struct delayed_work work; struct lockdep_map dep_map; }; +/* Values for size state variable (->srcu_size_state). */ +#define SRCU_SIZE_SMALL 0 +#define SRCU_SIZE_ALLOC 1 +#define SRCU_SIZE_WAIT_BARRIER 2 +#define SRCU_SIZE_WAIT_CALL 3 +#define SRCU_SIZE_WAIT_CBS1 4 +#define SRCU_SIZE_WAIT_CBS2 5 +#define SRCU_SIZE_WAIT_CBS3 6 +#define SRCU_SIZE_WAIT_CBS4 7 +#define SRCU_SIZE_BIG 8 + /* Values for state variable (bottom bits of ->srcu_gp_seq). */ #define SRCU_STATE_IDLE 0 #define SRCU_STATE_SCAN1 1 @@ -121,6 +138,7 @@ struct srcu_struct { #ifdef MODULE # define __DEFINE_SRCU(name, is_static) \ is_static struct srcu_struct name; \ + extern struct srcu_struct * const __srcu_struct_##name; \ struct srcu_struct * const __srcu_struct_##name \ __section("___srcu_struct_ptrs") = &name #else diff --git a/include/linux/sunrpc/clnt.h b/include/linux/sunrpc/clnt.h index db5149567305..90501404fa49 100644 --- a/include/linux/sunrpc/clnt.h +++ b/include/linux/sunrpc/clnt.h @@ -160,7 +160,7 @@ struct rpc_add_xprt_test { #define RPC_CLNT_CREATE_NO_RETRANS_TIMEOUT (1UL << 9) #define RPC_CLNT_CREATE_SOFTERR (1UL << 10) #define RPC_CLNT_CREATE_REUSEPORT (1UL << 11) -#define RPC_CLNT_CREATE_IGNORE_NULL_UNAVAIL (1UL << 12) +#define RPC_CLNT_CREATE_CONNECTED (1UL << 12) struct rpc_clnt *rpc_create(struct rpc_create_args *args); struct rpc_clnt *rpc_bind_new_program(struct rpc_clnt *, diff --git a/include/linux/task_work.h b/include/linux/task_work.h index 897494b597ba..795ef5a68429 100644 --- a/include/linux/task_work.h +++ b/include/linux/task_work.h @@ -17,6 +17,7 @@ enum task_work_notify_mode { TWA_NONE, TWA_RESUME, TWA_SIGNAL, + TWA_SIGNAL_NO_IPI, }; static inline bool task_work_pending(struct task_struct *task) diff --git a/include/linux/timekeeping.h b/include/linux/timekeeping.h index 78a98bdff76d..fe1e467ba046 100644 --- a/include/linux/timekeeping.h +++ b/include/linux/timekeeping.h @@ -177,6 +177,7 @@ static inline u64 ktime_get_raw_ns(void) extern u64 ktime_get_mono_fast_ns(void); extern u64 ktime_get_raw_fast_ns(void); extern u64 ktime_get_boot_fast_ns(void); +extern u64 ktime_get_tai_fast_ns(void); extern u64 ktime_get_real_fast_ns(void); /* diff --git a/include/linux/timer.h b/include/linux/timer.h index fda13c9d1256..648f00105f58 100644 --- a/include/linux/timer.h +++ b/include/linux/timer.h @@ -196,14 +196,6 @@ extern void init_timers(void); struct hrtimer; extern enum hrtimer_restart it_real_fn(struct hrtimer *); -#if defined(CONFIG_SMP) && defined(CONFIG_NO_HZ_COMMON) -struct ctl_table; - -extern unsigned int sysctl_timer_migration; -int timer_migration_handler(struct ctl_table *table, int write, - void *buffer, size_t *lenp, loff_t *ppos); -#endif - unsigned long __round_jiffies(unsigned long j, int cpu); unsigned long __round_jiffies_relative(unsigned long j, int cpu); unsigned long round_jiffies(unsigned long j); diff --git a/include/linux/torture.h b/include/linux/torture.h index 63fa4196e51c..7038104463e4 100644 --- a/include/linux/torture.h +++ b/include/linux/torture.h @@ -118,7 +118,7 @@ void _torture_stop_kthread(char *m, struct task_struct **tp); _torture_stop_kthread("Stopping " #n " task", &(tp)) #ifdef CONFIG_PREEMPTION -#define torture_preempt_schedule() preempt_schedule() +#define torture_preempt_schedule() __preempt_schedule() #else #define torture_preempt_schedule() do { } while (0) #endif diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h index 8abd08245326..62d7b81b1cb7 100644 --- a/include/net/bluetooth/hci_core.h +++ b/include/net/bluetooth/hci_core.h @@ -36,6 +36,9 @@ /* HCI priority */ #define HCI_PRIO_MAX 7 +/* HCI maximum id value */ +#define HCI_MAX_ID 10000 + /* HCI Core structures */ struct inquiry_data { bdaddr_t bdaddr; diff --git a/include/net/inet_timewait_sock.h b/include/net/inet_timewait_sock.h index 463ae5d33eb0..5b47545f22d3 100644 --- a/include/net/inet_timewait_sock.h +++ b/include/net/inet_timewait_sock.h @@ -71,7 +71,6 @@ struct inet_timewait_sock { tw_tos : 8; u32 tw_txhash; u32 tw_priority; - u32 tw_bslot; /* bind bucket slot */ struct timer_list tw_timer; struct inet_bind_bucket *tw_tb; }; @@ -110,6 +109,8 @@ static inline void inet_twsk_reschedule(struct inet_timewait_sock *tw, int timeo void inet_twsk_deschedule_put(struct inet_timewait_sock *tw); +void inet_twsk_purge(struct inet_hashinfo *hashinfo, int family); + static inline struct net *twsk_net(const struct inet_timewait_sock *twsk) { diff --git a/include/net/ip.h b/include/net/ip.h index 3984f2c39c4b..0161137914cf 100644 --- a/include/net/ip.h +++ b/include/net/ip.h @@ -56,6 +56,7 @@ struct inet_skb_parm { #define IPSKB_DOREDIRECT BIT(5) #define IPSKB_FRAG_PMTU BIT(6) #define IPSKB_L3SLAVE BIT(7) +#define IPSKB_NOPOLICY BIT(8) u16 frag_max_size; }; diff --git a/include/net/tc_act/tc_pedit.h b/include/net/tc_act/tc_pedit.h index 748cf87a4d7e..3e02709a1df6 100644 --- a/include/net/tc_act/tc_pedit.h +++ b/include/net/tc_act/tc_pedit.h @@ -14,6 +14,7 @@ struct tcf_pedit { struct tc_action common; unsigned char tcfp_nkeys; unsigned char tcfp_flags; + u32 tcfp_off_max_hint; struct tc_pedit_key *tcfp_keys; struct tcf_pedit_key_ex *tcfp_keys_ex; }; diff --git a/include/net/xfrm.h b/include/net/xfrm.h index 6fb899ff5afc..d2efddce65d4 100644 --- a/include/net/xfrm.h +++ b/include/net/xfrm.h @@ -1093,6 +1093,18 @@ static inline bool __xfrm_check_nopolicy(struct net *net, struct sk_buff *skb, return false; } +static inline bool __xfrm_check_dev_nopolicy(struct sk_buff *skb, + int dir, unsigned short family) +{ + if (dir != XFRM_POLICY_OUT && family == AF_INET) { + /* same dst may be used for traffic originating from + * devices with different policy settings. + */ + return IPCB(skb)->flags & IPSKB_NOPOLICY; + } + return skb_dst(skb) && (skb_dst(skb)->flags & DST_NOPOLICY); +} + static inline int __xfrm_policy_check2(struct sock *sk, int dir, struct sk_buff *skb, unsigned int family, int reverse) @@ -1104,7 +1116,7 @@ static inline int __xfrm_policy_check2(struct sock *sk, int dir, return __xfrm_policy_check(sk, ndir, skb, family); return __xfrm_check_nopolicy(net, skb, dir) || - (skb_dst(skb) && (skb_dst(skb)->flags & DST_NOPOLICY)) || + __xfrm_check_dev_nopolicy(skb, dir, family) || __xfrm_policy_check(sk, ndir, skb, family); } diff --git a/include/soc/mscc/ocelot_vcap.h b/include/soc/mscc/ocelot_vcap.h index 7b2bf9b1fe69..de26c992f821 100644 --- a/include/soc/mscc/ocelot_vcap.h +++ b/include/soc/mscc/ocelot_vcap.h @@ -681,7 +681,6 @@ struct ocelot_vcap_id { struct ocelot_vcap_filter { struct list_head list; - struct list_head trap_list; enum ocelot_vcap_filter_type type; int block_id; @@ -695,6 +694,7 @@ struct ocelot_vcap_filter { struct ocelot_vcap_stats stats; /* For VCAP IS1 and IS2 */ bool take_ts; + bool is_trap; unsigned long ingress_port_mask; /* For VCAP ES0 */ struct ocelot_vcap_port ingress_port; diff --git a/include/target/target_core_backend.h b/include/target/target_core_backend.h index 675f3a1fe613..773963a1e0b5 100644 --- a/include/target/target_core_backend.h +++ b/include/target/target_core_backend.h @@ -14,7 +14,7 @@ #define TRANSPORT_FLAG_PASSTHROUGH_ALUA 0x2 #define TRANSPORT_FLAG_PASSTHROUGH_PGR 0x4 -struct request_queue; +struct block_device; struct scatterlist; struct target_backend_ops { @@ -117,7 +117,7 @@ sense_reason_t passthrough_parse_cdb(struct se_cmd *cmd, bool target_sense_desc_format(struct se_device *dev); sector_t target_to_linux_sector(struct se_device *dev, sector_t lb); bool target_configure_unmap_from_queue(struct se_dev_attrib *attrib, - struct request_queue *q); + struct block_device *bdev); static inline bool target_dev_configured(struct se_device *se_dev) { diff --git a/include/trace/events/io_uring.h b/include/trace/events/io_uring.h index cddf5b6fbeb4..66fcc5a1a5b1 100644 --- a/include/trace/events/io_uring.h +++ b/include/trace/events/io_uring.h @@ -7,6 +7,7 @@ #include <linux/tracepoint.h> #include <uapi/linux/io_uring.h> +#include <linux/io_uring.h> struct io_wq_work; @@ -147,7 +148,7 @@ TRACE_EVENT(io_uring_queue_async_work, TP_PROTO(void *ctx, void * req, unsigned long long user_data, u8 opcode, unsigned int flags, struct io_wq_work *work, int rw), - TP_ARGS(ctx, req, user_data, flags, opcode, work, rw), + TP_ARGS(ctx, req, user_data, opcode, flags, work, rw), TP_STRUCT__entry ( __field( void *, ctx ) @@ -169,8 +170,9 @@ TRACE_EVENT(io_uring_queue_async_work, __entry->rw = rw; ), - TP_printk("ring %p, request %p, user_data 0x%llx, opcode %d, flags 0x%x, %s queue, work %p", - __entry->ctx, __entry->req, __entry->user_data, __entry->opcode, + TP_printk("ring %p, request %p, user_data 0x%llx, opcode %s, flags 0x%x, %s queue, work %p", + __entry->ctx, __entry->req, __entry->user_data, + io_uring_get_opcode(__entry->opcode), __entry->flags, __entry->rw ? "hashed" : "normal", __entry->work) ); @@ -205,8 +207,9 @@ TRACE_EVENT(io_uring_defer, __entry->opcode = opcode; ), - TP_printk("ring %p, request %p, user_data 0x%llx, opcode %d", - __entry->ctx, __entry->req, __entry->data, __entry->opcode) + TP_printk("ring %p, request %p, user_data 0x%llx, opcode %s", + __entry->ctx, __entry->req, __entry->data, + io_uring_get_opcode(__entry->opcode)) ); /** @@ -305,9 +308,9 @@ TRACE_EVENT(io_uring_fail_link, __entry->link = link; ), - TP_printk("ring %p, request %p, user_data 0x%llx, opcode %d, link %p", - __entry->ctx, __entry->req, __entry->user_data, __entry->opcode, - __entry->link) + TP_printk("ring %p, request %p, user_data 0x%llx, opcode %s, link %p", + __entry->ctx, __entry->req, __entry->user_data, + io_uring_get_opcode(__entry->opcode), __entry->link) ); /** @@ -318,13 +321,16 @@ TRACE_EVENT(io_uring_fail_link, * @user_data: user data associated with the request * @res: result of the request * @cflags: completion flags + * @extra1: extra 64-bit data for CQE32 + * @extra2: extra 64-bit data for CQE32 * */ TRACE_EVENT(io_uring_complete, - TP_PROTO(void *ctx, void *req, u64 user_data, int res, unsigned cflags), + TP_PROTO(void *ctx, void *req, u64 user_data, int res, unsigned cflags, + u64 extra1, u64 extra2), - TP_ARGS(ctx, req, user_data, res, cflags), + TP_ARGS(ctx, req, user_data, res, cflags, extra1, extra2), TP_STRUCT__entry ( __field( void *, ctx ) @@ -332,6 +338,8 @@ TRACE_EVENT(io_uring_complete, __field( u64, user_data ) __field( int, res ) __field( unsigned, cflags ) + __field( u64, extra1 ) + __field( u64, extra2 ) ), TP_fast_assign( @@ -340,12 +348,17 @@ TRACE_EVENT(io_uring_complete, __entry->user_data = user_data; __entry->res = res; __entry->cflags = cflags; + __entry->extra1 = extra1; + __entry->extra2 = extra2; ), - TP_printk("ring %p, req %p, user_data 0x%llx, result %d, cflags 0x%x", + TP_printk("ring %p, req %p, user_data 0x%llx, result %d, cflags 0x%x " + "extra1 %llu extra2 %llu ", __entry->ctx, __entry->req, __entry->user_data, - __entry->res, __entry->cflags) + __entry->res, __entry->cflags, + (unsigned long long) __entry->extra1, + (unsigned long long) __entry->extra2) ); /** @@ -389,9 +402,9 @@ TRACE_EVENT(io_uring_submit_sqe, __entry->sq_thread = sq_thread; ), - TP_printk("ring %p, req %p, user_data 0x%llx, opcode %d, flags 0x%x, " + TP_printk("ring %p, req %p, user_data 0x%llx, opcode %s, flags 0x%x, " "non block %d, sq_thread %d", __entry->ctx, __entry->req, - __entry->user_data, __entry->opcode, + __entry->user_data, io_uring_get_opcode(__entry->opcode), __entry->flags, __entry->force_nonblock, __entry->sq_thread) ); @@ -433,8 +446,9 @@ TRACE_EVENT(io_uring_poll_arm, __entry->events = events; ), - TP_printk("ring %p, req %p, user_data 0x%llx, opcode %d, mask 0x%x, events 0x%x", - __entry->ctx, __entry->req, __entry->user_data, __entry->opcode, + TP_printk("ring %p, req %p, user_data 0x%llx, opcode %s, mask 0x%x, events 0x%x", + __entry->ctx, __entry->req, __entry->user_data, + io_uring_get_opcode(__entry->opcode), __entry->mask, __entry->events) ); @@ -470,8 +484,9 @@ TRACE_EVENT(io_uring_task_add, __entry->mask = mask; ), - TP_printk("ring %p, req %p, user_data 0x%llx, opcode %d, mask %x", - __entry->ctx, __entry->req, __entry->user_data, __entry->opcode, + TP_printk("ring %p, req %p, user_data 0x%llx, opcode %s, mask %x", + __entry->ctx, __entry->req, __entry->user_data, + io_uring_get_opcode(__entry->opcode), __entry->mask) ); @@ -506,7 +521,7 @@ TRACE_EVENT(io_uring_req_failed, __field( u16, personality ) __field( u32, file_index ) __field( u64, pad1 ) - __field( u64, pad2 ) + __field( u64, addr3 ) __field( int, error ) ), @@ -520,27 +535,69 @@ TRACE_EVENT(io_uring_req_failed, __entry->off = sqe->off; __entry->addr = sqe->addr; __entry->len = sqe->len; - __entry->op_flags = sqe->rw_flags; + __entry->op_flags = sqe->poll32_events; __entry->buf_index = sqe->buf_index; __entry->personality = sqe->personality; __entry->file_index = sqe->file_index; __entry->pad1 = sqe->__pad2[0]; - __entry->pad2 = sqe->__pad2[1]; + __entry->addr3 = sqe->addr3; __entry->error = error; ), TP_printk("ring %p, req %p, user_data 0x%llx, " - "op %d, flags 0x%x, prio=%d, off=%llu, addr=%llu, " + "opcode %s, flags 0x%x, prio=%d, off=%llu, addr=%llu, " "len=%u, rw_flags=0x%x, buf_index=%d, " - "personality=%d, file_index=%d, pad=0x%llx/%llx, error=%d", + "personality=%d, file_index=%d, pad=0x%llx, addr3=%llx, " + "error=%d", __entry->ctx, __entry->req, __entry->user_data, - __entry->opcode, __entry->flags, __entry->ioprio, + io_uring_get_opcode(__entry->opcode), + __entry->flags, __entry->ioprio, (unsigned long long)__entry->off, (unsigned long long) __entry->addr, __entry->len, __entry->op_flags, __entry->buf_index, __entry->personality, __entry->file_index, (unsigned long long) __entry->pad1, - (unsigned long long) __entry->pad2, __entry->error) + (unsigned long long) __entry->addr3, __entry->error) +); + + +/* + * io_uring_cqe_overflow - a CQE overflowed + * + * @ctx: pointer to a ring context structure + * @user_data: user data associated with the request + * @res: CQE result + * @cflags: CQE flags + * @ocqe: pointer to the overflow cqe (if available) + * + */ +TRACE_EVENT(io_uring_cqe_overflow, + + TP_PROTO(void *ctx, unsigned long long user_data, s32 res, u32 cflags, + void *ocqe), + + TP_ARGS(ctx, user_data, res, cflags, ocqe), + + TP_STRUCT__entry ( + __field( void *, ctx ) + __field( unsigned long long, user_data ) + __field( s32, res ) + __field( u32, cflags ) + __field( void *, ocqe ) + ), + + TP_fast_assign( + __entry->ctx = ctx; + __entry->user_data = user_data; + __entry->res = res; + __entry->cflags = cflags; + __entry->ocqe = ocqe; + ), + + TP_printk("ring %p, user_data 0x%llx, res %d, flags %x, " + "overflow_cqe %p", + __entry->ctx, __entry->user_data, __entry->res, + __entry->cflags, __entry->ocqe) ); #endif /* _TRACE_IO_URING_H */ diff --git a/include/trace/events/sched.h b/include/trace/events/sched.h index 65e786756321..fbb99a61f714 100644 --- a/include/trace/events/sched.h +++ b/include/trace/events/sched.h @@ -222,11 +222,11 @@ static inline long __trace_sched_switch_state(bool preempt, TRACE_EVENT(sched_switch, TP_PROTO(bool preempt, - unsigned int prev_state, struct task_struct *prev, - struct task_struct *next), + struct task_struct *next, + unsigned int prev_state), - TP_ARGS(preempt, prev_state, prev, next), + TP_ARGS(preempt, prev, next, prev_state), TP_STRUCT__entry( __array( char, prev_comm, TASK_COMM_LEN ) diff --git a/include/trace/events/timer.h b/include/trace/events/timer.h index 6ad031c71be7..2e713a7d9aa3 100644 --- a/include/trace/events/timer.h +++ b/include/trace/events/timer.h @@ -48,6 +48,7 @@ DEFINE_EVENT(timer_class, timer_init, * timer_start - called when the timer is started * @timer: pointer to struct timer_list * @expires: the timers expiry time + * @flags: the timers flags */ TRACE_EVENT(timer_start, @@ -84,6 +85,7 @@ TRACE_EVENT(timer_start, /** * timer_expire_entry - called immediately before the timer callback * @timer: pointer to struct timer_list + * @baseclk: value of timer_base::clk when timer expires * * Allows to determine the timer latency. */ @@ -190,7 +192,8 @@ TRACE_EVENT(hrtimer_init, /** * hrtimer_start - called when the hrtimer is started - * @hrtimer: pointer to struct hrtimer + * @hrtimer: pointer to struct hrtimer + * @mode: the hrtimers mode */ TRACE_EVENT(hrtimer_start, diff --git a/include/uapi/linux/cdrom.h b/include/uapi/linux/cdrom.h index 804ff8d98f71..011e594e4a0d 100644 --- a/include/uapi/linux/cdrom.h +++ b/include/uapi/linux/cdrom.h @@ -103,7 +103,7 @@ #define CDROMREADALL 0x5318 /* read all 2646 bytes */ /* - * These ioctls are (now) only in ide-cd.c for controlling + * These ioctls were only in (now removed) ide-cd.c for controlling * drive spindown time. They should be implemented in the * Uniform driver, via generic packet commands, GPCMD_MODE_SELECT_10, * GPCMD_MODE_SENSE_10 and the GPMODE_POWER_PAGE... diff --git a/include/uapi/linux/dma-buf.h b/include/uapi/linux/dma-buf.h index 8e4a2ca0bcbf..b1523cb8ab30 100644 --- a/include/uapi/linux/dma-buf.h +++ b/include/uapi/linux/dma-buf.h @@ -92,7 +92,7 @@ struct dma_buf_sync { * between them in actual uapi, they're just different numbers. */ #define DMA_BUF_SET_NAME _IOW(DMA_BUF_BASE, 1, const char *) -#define DMA_BUF_SET_NAME_A _IOW(DMA_BUF_BASE, 1, u32) -#define DMA_BUF_SET_NAME_B _IOW(DMA_BUF_BASE, 1, u64) +#define DMA_BUF_SET_NAME_A _IOW(DMA_BUF_BASE, 1, __u32) +#define DMA_BUF_SET_NAME_B _IOW(DMA_BUF_BASE, 1, __u64) #endif diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h index 1845cf7c80ba..53e7dae92e42 100644 --- a/include/uapi/linux/io_uring.h +++ b/include/uapi/linux/io_uring.h @@ -22,6 +22,7 @@ struct io_uring_sqe { union { __u64 off; /* offset into file */ __u64 addr2; + __u32 cmd_op; }; union { __u64 addr; /* pointer to buffer or iovecs */ @@ -45,6 +46,7 @@ struct io_uring_sqe { __u32 rename_flags; __u32 unlink_flags; __u32 hardlink_flags; + __u32 xattr_flags; }; __u64 user_data; /* data to be passed back at completion time */ /* pack this to avoid bogus arm OABI complaints */ @@ -60,9 +62,28 @@ struct io_uring_sqe { __s32 splice_fd_in; __u32 file_index; }; - __u64 __pad2[2]; + union { + struct { + __u64 addr3; + __u64 __pad2[1]; + }; + /* + * If the ring is initialized with IORING_SETUP_SQE128, then + * this field is used for 80 bytes of arbitrary command data + */ + __u8 cmd[0]; + }; }; +/* + * If sqe->file_index is set to this for opcodes that instantiate a new + * direct descriptor (like openat/openat2/accept), then io_uring will allocate + * an available direct descriptor instead of having the application pass one + * in. The picked direct descriptor will be returned in cqe->res, or -ENFILE + * if the space is full. + */ +#define IORING_FILE_INDEX_ALLOC (~0U) + enum { IOSQE_FIXED_FILE_BIT, IOSQE_IO_DRAIN_BIT, @@ -102,8 +123,25 @@ enum { #define IORING_SETUP_ATTACH_WQ (1U << 5) /* attach to existing wq */ #define IORING_SETUP_R_DISABLED (1U << 6) /* start with ring disabled */ #define IORING_SETUP_SUBMIT_ALL (1U << 7) /* continue submit on error */ +/* + * Cooperative task running. When requests complete, they often require + * forcing the submitter to transition to the kernel to complete. If this + * flag is set, work will be done when the task transitions anyway, rather + * than force an inter-processor interrupt reschedule. This avoids interrupting + * a task running in userspace, and saves an IPI. + */ +#define IORING_SETUP_COOP_TASKRUN (1U << 8) +/* + * If COOP_TASKRUN is set, get notified if task work is available for + * running and a kernel transition would be needed to run it. This sets + * IORING_SQ_TASKRUN in the sq ring flags. Not valid with COOP_TASKRUN. + */ +#define IORING_SETUP_TASKRUN_FLAG (1U << 9) -enum { +#define IORING_SETUP_SQE128 (1U << 10) /* SQEs are 128 byte */ +#define IORING_SETUP_CQE32 (1U << 11) /* CQEs are 32 byte */ + +enum io_uring_op { IORING_OP_NOP, IORING_OP_READV, IORING_OP_WRITEV, @@ -145,6 +183,12 @@ enum { IORING_OP_SYMLINKAT, IORING_OP_LINKAT, IORING_OP_MSG_RING, + IORING_OP_FSETXATTR, + IORING_OP_SETXATTR, + IORING_OP_FGETXATTR, + IORING_OP_GETXATTR, + IORING_OP_SOCKET, + IORING_OP_URING_CMD, /* this goes last, obviously */ IORING_OP_LAST, @@ -188,12 +232,45 @@ enum { #define IORING_POLL_UPDATE_USER_DATA (1U << 2) /* + * ASYNC_CANCEL flags. + * + * IORING_ASYNC_CANCEL_ALL Cancel all requests that match the given key + * IORING_ASYNC_CANCEL_FD Key off 'fd' for cancelation rather than the + * request 'user_data' + * IORING_ASYNC_CANCEL_ANY Match any request + */ +#define IORING_ASYNC_CANCEL_ALL (1U << 0) +#define IORING_ASYNC_CANCEL_FD (1U << 1) +#define IORING_ASYNC_CANCEL_ANY (1U << 2) + +/* + * send/sendmsg and recv/recvmsg flags (sqe->addr2) + * + * IORING_RECVSEND_POLL_FIRST If set, instead of first attempting to send + * or receive and arm poll if that yields an + * -EAGAIN result, arm poll upfront and skip + * the initial transfer attempt. + */ +#define IORING_RECVSEND_POLL_FIRST (1U << 0) + +/* + * accept flags stored in sqe->ioprio + */ +#define IORING_ACCEPT_MULTISHOT (1U << 0) + +/* * IO completion data structure (Completion Queue Entry) */ struct io_uring_cqe { __u64 user_data; /* sqe->data submission passed back */ __s32 res; /* result code for this event */ __u32 flags; + + /* + * If the ring is initialized with IORING_SETUP_CQE32, then this field + * contains 16-bytes of padding, doubling the size of the CQE. + */ + __u64 big_cqe[]; }; /* @@ -201,9 +278,11 @@ struct io_uring_cqe { * * IORING_CQE_F_BUFFER If set, the upper 16 bits are the buffer ID * IORING_CQE_F_MORE If set, parent SQE will generate more CQE entries + * IORING_CQE_F_SOCK_NONEMPTY If set, more data to read after socket recv */ #define IORING_CQE_F_BUFFER (1U << 0) #define IORING_CQE_F_MORE (1U << 1) +#define IORING_CQE_F_SOCK_NONEMPTY (1U << 2) enum { IORING_CQE_BUFFER_SHIFT = 16, @@ -236,6 +315,7 @@ struct io_sqring_offsets { */ #define IORING_SQ_NEED_WAKEUP (1U << 0) /* needs io_uring_enter wakeup */ #define IORING_SQ_CQ_OVERFLOW (1U << 1) /* CQ ring is overflown */ +#define IORING_SQ_TASKRUN (1U << 2) /* task should enter the kernel */ struct io_cqring_offsets { __u32 head; @@ -333,6 +413,10 @@ enum { IORING_REGISTER_RING_FDS = 20, IORING_UNREGISTER_RING_FDS = 21, + /* register ring based provide buffer group */ + IORING_REGISTER_PBUF_RING = 22, + IORING_UNREGISTER_PBUF_RING = 23, + /* this goes last */ IORING_REGISTER_LAST }; @@ -350,9 +434,15 @@ struct io_uring_files_update { __aligned_u64 /* __s32 * */ fds; }; +/* + * Register a fully sparse file space, rather than pass in an array of all + * -1 file descriptors. + */ +#define IORING_RSRC_REGISTER_SPARSE (1U << 0) + struct io_uring_rsrc_register { __u32 nr; - __u32 resv; + __u32 flags; __u64 resv2; __aligned_u64 data; __aligned_u64 tags; @@ -404,6 +494,38 @@ struct io_uring_restriction { __u32 resv2[3]; }; +struct io_uring_buf { + __u64 addr; + __u32 len; + __u16 bid; + __u16 resv; +}; + +struct io_uring_buf_ring { + union { + /* + * To avoid spilling into more pages than we need to, the + * ring tail is overlaid with the io_uring_buf->resv field. + */ + struct { + __u64 resv1; + __u32 resv2; + __u16 resv3; + __u16 tail; + }; + struct io_uring_buf bufs[0]; + }; +}; + +/* argument for IORING_(UN)REGISTER_PBUF_RING */ +struct io_uring_buf_reg { + __u64 ring_addr; + __u32 ring_entries; + __u16 bgid; + __u16 pad; + __u64 resv[3]; +}; + /* * io_uring_restriction->opcode values */ diff --git a/include/uapi/linux/loop.h b/include/uapi/linux/loop.h index 98e60801195e..6f63527dd2ed 100644 --- a/include/uapi/linux/loop.h +++ b/include/uapi/linux/loop.h @@ -1,11 +1,6 @@ /* SPDX-License-Identifier: GPL-1.0+ WITH Linux-syscall-note */ /* - * include/linux/loop.h - * - * Written by Theodore Ts'o, 3/29/93. - * - * Copyright 1993 by Theodore Ts'o. Redistribution of this file is - * permitted under the GNU General Public License. + * Copyright 1993 by Theodore Ts'o. */ #ifndef _UAPI_LINUX_LOOP_H #define _UAPI_LINUX_LOOP_H diff --git a/include/uapi/linux/nvme_ioctl.h b/include/uapi/linux/nvme_ioctl.h index b2e43185e3b5..2f76cba67166 100644 --- a/include/uapi/linux/nvme_ioctl.h +++ b/include/uapi/linux/nvme_ioctl.h @@ -70,6 +70,28 @@ struct nvme_passthru_cmd64 { __u64 result; }; +/* same as struct nvme_passthru_cmd64, minus the 8b result field */ +struct nvme_uring_cmd { + __u8 opcode; + __u8 flags; + __u16 rsvd1; + __u32 nsid; + __u32 cdw2; + __u32 cdw3; + __u64 metadata; + __u64 addr; + __u32 metadata_len; + __u32 data_len; + __u32 cdw10; + __u32 cdw11; + __u32 cdw12; + __u32 cdw13; + __u32 cdw14; + __u32 cdw15; + __u32 timeout_ms; + __u32 rsvd2; +}; + #define nvme_admin_cmd nvme_passthru_cmd #define NVME_IOCTL_ID _IO('N', 0x40) @@ -83,4 +105,10 @@ struct nvme_passthru_cmd64 { #define NVME_IOCTL_IO64_CMD _IOWR('N', 0x48, struct nvme_passthru_cmd64) #define NVME_IOCTL_IO64_CMD_VEC _IOWR('N', 0x49, struct nvme_passthru_cmd64) +/* io_uring async commands: */ +#define NVME_URING_CMD_IO _IOWR('N', 0x80, struct nvme_uring_cmd) +#define NVME_URING_CMD_IO_VEC _IOWR('N', 0x81, struct nvme_uring_cmd) +#define NVME_URING_CMD_ADMIN _IOWR('N', 0x82, struct nvme_uring_cmd) +#define NVME_URING_CMD_ADMIN_VEC _IOWR('N', 0x83, struct nvme_uring_cmd) + #endif /* _UAPI_LINUX_NVME_IOCTL_H */ diff --git a/include/uapi/linux/rfkill.h b/include/uapi/linux/rfkill.h index 283c5a7b3f2c..db6c8588c1d0 100644 --- a/include/uapi/linux/rfkill.h +++ b/include/uapi/linux/rfkill.h @@ -184,7 +184,7 @@ struct rfkill_event_ext { #define RFKILL_IOC_NOINPUT 1 #define RFKILL_IOCTL_NOINPUT _IO(RFKILL_IOC_MAGIC, RFKILL_IOC_NOINPUT) #define RFKILL_IOC_MAX_SIZE 2 -#define RFKILL_IOCTL_MAX_SIZE _IOW(RFKILL_IOC_MAGIC, RFKILL_IOC_EXT_SIZE, __u32) +#define RFKILL_IOCTL_MAX_SIZE _IOW(RFKILL_IOC_MAGIC, RFKILL_IOC_MAX_SIZE, __u32) /* and that's all userspace gets */ diff --git a/include/uapi/linux/sev-guest.h b/include/uapi/linux/sev-guest.h new file mode 100644 index 000000000000..256aaeff7e65 --- /dev/null +++ b/include/uapi/linux/sev-guest.h @@ -0,0 +1,80 @@ +/* SPDX-License-Identifier: GPL-2.0-only WITH Linux-syscall-note */ +/* + * Userspace interface for AMD SEV and SNP guest driver. + * + * Copyright (C) 2021 Advanced Micro Devices, Inc. + * + * Author: Brijesh Singh <brijesh.singh@amd.com> + * + * SEV API specification is available at: https://developer.amd.com/sev/ + */ + +#ifndef __UAPI_LINUX_SEV_GUEST_H_ +#define __UAPI_LINUX_SEV_GUEST_H_ + +#include <linux/types.h> + +struct snp_report_req { + /* user data that should be included in the report */ + __u8 user_data[64]; + + /* The vmpl level to be included in the report */ + __u32 vmpl; + + /* Must be zero filled */ + __u8 rsvd[28]; +}; + +struct snp_report_resp { + /* response data, see SEV-SNP spec for the format */ + __u8 data[4000]; +}; + +struct snp_derived_key_req { + __u32 root_key_select; + __u32 rsvd; + __u64 guest_field_select; + __u32 vmpl; + __u32 guest_svn; + __u64 tcb_version; +}; + +struct snp_derived_key_resp { + /* response data, see SEV-SNP spec for the format */ + __u8 data[64]; +}; + +struct snp_guest_request_ioctl { + /* message version number (must be non-zero) */ + __u8 msg_version; + + /* Request and response structure address */ + __u64 req_data; + __u64 resp_data; + + /* firmware error code on failure (see psp-sev.h) */ + __u64 fw_err; +}; + +struct snp_ext_report_req { + struct snp_report_req data; + + /* where to copy the certificate blob */ + __u64 certs_address; + + /* length of the certificate blob */ + __u32 certs_len; +}; + +#define SNP_GUEST_REQ_IOC_TYPE 'S' + +/* Get SNP attestation report */ +#define SNP_GET_REPORT _IOWR(SNP_GUEST_REQ_IOC_TYPE, 0x0, struct snp_guest_request_ioctl) + +/* Get a derived key from the root */ +#define SNP_GET_DERIVED_KEY _IOWR(SNP_GUEST_REQ_IOC_TYPE, 0x1, struct snp_guest_request_ioctl) + +/* Get SNP extended report as defined in the GHCB specification version 2. */ +#define SNP_GET_EXT_REPORT _IOWR(SNP_GUEST_REQ_IOC_TYPE, 0x2, struct snp_guest_request_ioctl) + +#endif /* __UAPI_LINUX_SEV_GUEST_H_ */ diff --git a/include/uapi/linux/virtio_ids.h b/include/uapi/linux/virtio_ids.h index 80d76b75bccd..7aa2eb766205 100644 --- a/include/uapi/linux/virtio_ids.h +++ b/include/uapi/linux/virtio_ids.h @@ -73,12 +73,12 @@ * Virtio Transitional IDs */ -#define VIRTIO_TRANS_ID_NET 1000 /* transitional virtio net */ -#define VIRTIO_TRANS_ID_BLOCK 1001 /* transitional virtio block */ -#define VIRTIO_TRANS_ID_BALLOON 1002 /* transitional virtio balloon */ -#define VIRTIO_TRANS_ID_CONSOLE 1003 /* transitional virtio console */ -#define VIRTIO_TRANS_ID_SCSI 1004 /* transitional virtio SCSI */ -#define VIRTIO_TRANS_ID_RNG 1005 /* transitional virtio rng */ -#define VIRTIO_TRANS_ID_9P 1009 /* transitional virtio 9p console */ +#define VIRTIO_TRANS_ID_NET 0x1000 /* transitional virtio net */ +#define VIRTIO_TRANS_ID_BLOCK 0x1001 /* transitional virtio block */ +#define VIRTIO_TRANS_ID_BALLOON 0x1002 /* transitional virtio balloon */ +#define VIRTIO_TRANS_ID_CONSOLE 0x1003 /* transitional virtio console */ +#define VIRTIO_TRANS_ID_SCSI 0x1004 /* transitional virtio SCSI */ +#define VIRTIO_TRANS_ID_RNG 0x1005 /* transitional virtio rng */ +#define VIRTIO_TRANS_ID_9P 0x1009 /* transitional virtio 9p console */ #endif /* _LINUX_VIRTIO_IDS_H */ diff --git a/kernel/auditsc.c b/kernel/auditsc.c index ea2ee1181921..f3a2abd6d1a1 100644 --- a/kernel/auditsc.c +++ b/kernel/auditsc.c @@ -1959,6 +1959,12 @@ void __audit_uring_exit(int success, long code) { struct audit_context *ctx = audit_context(); + if (ctx->dummy) { + if (ctx->context != AUDIT_CTX_URING) + return; + goto out; + } + if (ctx->context == AUDIT_CTX_SYSCALL) { /* * NOTE: See the note in __audit_uring_entry() about the case diff --git a/kernel/bpf/Kconfig b/kernel/bpf/Kconfig index d56ee177d5f8..2dfe1079f772 100644 --- a/kernel/bpf/Kconfig +++ b/kernel/bpf/Kconfig @@ -27,6 +27,7 @@ config BPF_SYSCALL bool "Enable bpf() system call" select BPF select IRQ_WORK + select TASKS_RCU if PREEMPTION select TASKS_TRACE_RCU select BINARY_PRINTF select NET_SOCK_MSG if NET diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c index 9390bfd9f1cd..71a418858a5e 100644 --- a/kernel/cgroup/cpuset.c +++ b/kernel/cgroup/cpuset.c @@ -3390,8 +3390,11 @@ static struct notifier_block cpuset_track_online_nodes_nb = { */ void __init cpuset_init_smp(void) { - cpumask_copy(top_cpuset.cpus_allowed, cpu_active_mask); - top_cpuset.mems_allowed = node_states[N_MEMORY]; + /* + * cpus_allowd/mems_allowed set to v2 values in the initial + * cpuset_bind() call will be reset to v1 values in another + * cpuset_bind() call when v1 cpuset is mounted. + */ top_cpuset.old_mems_allowed = top_cpuset.mems_allowed; cpumask_copy(top_cpuset.effective_cpus, cpu_active_mask); diff --git a/kernel/configs/x86_debug.config b/kernel/configs/x86_debug.config new file mode 100644 index 000000000000..dcd86f32f4ed --- /dev/null +++ b/kernel/configs/x86_debug.config @@ -0,0 +1,18 @@ +CONFIG_X86_DEBUG_FPU=y +CONFIG_LOCK_STAT=y +CONFIG_DEBUG_VM=y +CONFIG_DEBUG_VM_VMACACHE=y +CONFIG_DEBUG_VM_RB=y +CONFIG_DEBUG_SLAB=y +CONFIG_DEBUG_KMEMLEAK=y +CONFIG_DEBUG_PAGEALLOC=y +CONFIG_SLUB_DEBUG_ON=y +CONFIG_KMEMCHECK=y +CONFIG_DEBUG_OBJECTS=y +CONFIG_DEBUG_OBJECTS_ENABLE_DEFAULT=1 +CONFIG_GCOV_KERNEL=y +CONFIG_LOCKDEP=y +CONFIG_PROVE_LOCKING=y +CONFIG_SCHEDSTATS=y +CONFIG_VMLINUX_VALIDATION=y +CONFIG_DEBUG_INFO_DWARF_TOOLCHAIN_DEFAULT=y diff --git a/kernel/cpu.c b/kernel/cpu.c index d0a9aa0b42e8..bbad5e375d3b 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -35,6 +35,7 @@ #include <linux/percpu-rwsem.h> #include <linux/cpuset.h> #include <linux/random.h> +#include <linux/cc_platform.h> #include <trace/events/power.h> #define CREATE_TRACE_POINTS @@ -716,14 +717,6 @@ static int cpuhp_up_callbacks(unsigned int cpu, struct cpuhp_cpu_state *st, /* * The cpu hotplug threads manage the bringup and teardown of the cpus */ -static void cpuhp_create(unsigned int cpu) -{ - struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu); - - init_completion(&st->done_up); - init_completion(&st->done_down); -} - static int cpuhp_should_run(unsigned int cpu) { struct cpuhp_cpu_state *st = this_cpu_ptr(&cpuhp_state); @@ -883,15 +876,27 @@ static int cpuhp_kick_ap_work(unsigned int cpu) static struct smp_hotplug_thread cpuhp_threads = { .store = &cpuhp_state.thread, - .create = &cpuhp_create, .thread_should_run = cpuhp_should_run, .thread_fn = cpuhp_thread_fun, .thread_comm = "cpuhp/%u", .selfparking = true, }; +static __init void cpuhp_init_state(void) +{ + struct cpuhp_cpu_state *st; + int cpu; + + for_each_possible_cpu(cpu) { + st = per_cpu_ptr(&cpuhp_state, cpu); + init_completion(&st->done_up); + init_completion(&st->done_down); + } +} + void __init cpuhp_threads_init(void) { + cpuhp_init_state(); BUG_ON(smpboot_register_percpu_thread(&cpuhp_threads)); kthread_unpark(this_cpu_read(cpuhp_state.thread)); } @@ -1186,6 +1191,12 @@ out: static int cpu_down_maps_locked(unsigned int cpu, enum cpuhp_state target) { + /* + * If the platform does not support hotplug, report it explicitly to + * differentiate it from a transient offlining failure. + */ + if (cc_platform_has(CC_ATTR_HOTPLUG_DISABLED)) + return -EOPNOTSUPP; if (cpu_hotplug_disabled) return -EBUSY; return _cpu_down(cpu, 0, target); diff --git a/kernel/events/core.c b/kernel/events/core.c index 7858bafffa9d..7f1e4c5897e7 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -12217,6 +12217,9 @@ SYSCALL_DEFINE5(perf_event_open, * Do not allow to attach to a group in a different task * or CPU context. If we're moving SW events, we'll fix * this up later, so allow that. + * + * Racy, not holding group_leader->ctx->mutex, see comment with + * perf_event_ctx_lock(). */ if (!move_group && group_leader->ctx != ctx) goto err_context; @@ -12282,6 +12285,7 @@ SYSCALL_DEFINE5(perf_event_open, } else { perf_event_ctx_unlock(group_leader, gctx); move_group = 0; + goto not_move_group; } } @@ -12298,7 +12302,17 @@ SYSCALL_DEFINE5(perf_event_open, } } else { mutex_lock(&ctx->mutex); + + /* + * Now that we hold ctx->lock, (re)validate group_leader->ctx == ctx, + * see the group_leader && !move_group test earlier. + */ + if (group_leader && group_leader->ctx != ctx) { + err = -EINVAL; + goto err_locked; + } } +not_move_group: if (ctx->task == TASK_TOMBSTONE) { err = -ESRCH; diff --git a/kernel/fork.c b/kernel/fork.c index 35a3beff140b..254ab63c1106 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -1046,6 +1046,11 @@ static struct task_struct *dup_task_struct(struct task_struct *orig, int node) #ifdef CONFIG_MEMCG tsk->active_memcg = NULL; #endif + +#ifdef CONFIG_CPU_SUP_INTEL + tsk->reported_split_lock = 0; +#endif + return tsk; free_stack: diff --git a/kernel/irq/affinity.c b/kernel/irq/affinity.c index fdf170404650..d9a5c1d65a79 100644 --- a/kernel/irq/affinity.c +++ b/kernel/irq/affinity.c @@ -258,7 +258,7 @@ static int __irq_build_affinity_masks(unsigned int startvec, nodemask_t nodemsk = NODE_MASK_NONE; struct node_vectors *node_vectors; - if (!cpumask_weight(cpu_mask)) + if (cpumask_empty(cpu_mask)) return 0; nodes = get_nodes_in_cpumask(node_to_cpumask, cpu_mask, &nodemsk); diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c index 54af0deb239b..e6b8e564b37f 100644 --- a/kernel/irq/chip.c +++ b/kernel/irq/chip.c @@ -1573,17 +1573,12 @@ static struct device *irq_get_parent_device(struct irq_data *data) int irq_chip_pm_get(struct irq_data *data) { struct device *dev = irq_get_parent_device(data); - int retval; + int retval = 0; - if (IS_ENABLED(CONFIG_PM) && dev) { - retval = pm_runtime_get_sync(dev); - if (retval < 0) { - pm_runtime_put_noidle(dev); - return retval; - } - } + if (IS_ENABLED(CONFIG_PM) && dev) + retval = pm_runtime_resume_and_get(dev); - return 0; + return retval; } /** diff --git a/kernel/irq/debugfs.c b/kernel/irq/debugfs.c index 2b43f5f5033d..bc8e40cf2b65 100644 --- a/kernel/irq/debugfs.c +++ b/kernel/irq/debugfs.c @@ -58,6 +58,7 @@ static const struct irq_bit_descr irqchip_flags[] = { BIT_MASK_DESCR(IRQCHIP_SUPPORTS_LEVEL_MSI), BIT_MASK_DESCR(IRQCHIP_SUPPORTS_NMI), BIT_MASK_DESCR(IRQCHIP_ENABLE_WAKEUP_ON_SUSPEND), + BIT_MASK_DESCR(IRQCHIP_IMMUTABLE), }; static void diff --git a/kernel/irq/irq_sim.c b/kernel/irq/irq_sim.c index 0cd02efa3a74..dd76323ea3fd 100644 --- a/kernel/irq/irq_sim.c +++ b/kernel/irq/irq_sim.c @@ -181,7 +181,7 @@ struct irq_domain *irq_domain_create_sim(struct fwnode_handle *fwnode, goto err_free_bitmap; work_ctx->irq_count = num_irqs; - init_irq_work(&work_ctx->work, irq_sim_handle_irq); + work_ctx->work = IRQ_WORK_INIT_HARD(irq_sim_handle_irq); return work_ctx->domain; diff --git a/kernel/irq/irqdesc.c b/kernel/irq/irqdesc.c index 0099b87dd853..d323b180b0f3 100644 --- a/kernel/irq/irqdesc.c +++ b/kernel/irq/irqdesc.c @@ -701,7 +701,6 @@ EXPORT_SYMBOL_GPL(generic_handle_irq_safe); */ int generic_handle_domain_irq(struct irq_domain *domain, unsigned int hwirq) { - WARN_ON_ONCE(!in_hardirq()); return handle_irq_desc(irq_resolve_mapping(domain, hwirq)); } EXPORT_SYMBOL_GPL(generic_handle_domain_irq); diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c index e3e245a4fd70..8c396319d5ac 100644 --- a/kernel/irq/manage.c +++ b/kernel/irq/manage.c @@ -222,11 +222,16 @@ int irq_do_set_affinity(struct irq_data *data, const struct cpumask *mask, { struct irq_desc *desc = irq_data_to_desc(data); struct irq_chip *chip = irq_data_get_irq_chip(data); + const struct cpumask *prog_mask; int ret; + static DEFINE_RAW_SPINLOCK(tmp_mask_lock); + static struct cpumask tmp_mask; + if (!chip || !chip->irq_set_affinity) return -EINVAL; + raw_spin_lock(&tmp_mask_lock); /* * If this is a managed interrupt and housekeeping is enabled on * it check whether the requested affinity mask intersects with @@ -248,24 +253,34 @@ int irq_do_set_affinity(struct irq_data *data, const struct cpumask *mask, */ if (irqd_affinity_is_managed(data) && housekeeping_enabled(HK_TYPE_MANAGED_IRQ)) { - const struct cpumask *hk_mask, *prog_mask; - - static DEFINE_RAW_SPINLOCK(tmp_mask_lock); - static struct cpumask tmp_mask; + const struct cpumask *hk_mask; hk_mask = housekeeping_cpumask(HK_TYPE_MANAGED_IRQ); - raw_spin_lock(&tmp_mask_lock); cpumask_and(&tmp_mask, mask, hk_mask); if (!cpumask_intersects(&tmp_mask, cpu_online_mask)) prog_mask = mask; else prog_mask = &tmp_mask; - ret = chip->irq_set_affinity(data, prog_mask, force); - raw_spin_unlock(&tmp_mask_lock); } else { - ret = chip->irq_set_affinity(data, mask, force); + prog_mask = mask; } + + /* + * Make sure we only provide online CPUs to the irqchip, + * unless we are being asked to force the affinity (in which + * case we do as we are told). + */ + cpumask_and(&tmp_mask, prog_mask, cpu_online_mask); + if (!force && !cpumask_empty(&tmp_mask)) + ret = chip->irq_set_affinity(data, &tmp_mask, force); + else if (force) + ret = chip->irq_set_affinity(data, mask, force); + else + ret = -EINVAL; + + raw_spin_unlock(&tmp_mask_lock); + switch (ret) { case IRQ_SET_MASK_OK: case IRQ_SET_MASK_OK_DONE: diff --git a/kernel/irq/matrix.c b/kernel/irq/matrix.c index bbfb26489aa1..1698e77645ac 100644 --- a/kernel/irq/matrix.c +++ b/kernel/irq/matrix.c @@ -286,7 +286,7 @@ void irq_matrix_remove_managed(struct irq_matrix *m, const struct cpumask *msk) int irq_matrix_alloc_managed(struct irq_matrix *m, const struct cpumask *msk, unsigned int *mapped_cpu) { - unsigned int bit, cpu, end = m->alloc_end; + unsigned int bit, cpu, end; struct cpumap *cm; if (cpumask_empty(msk)) diff --git a/kernel/irq/msi.c b/kernel/irq/msi.c index 2bdfce5edafd..a9ee535293eb 100644 --- a/kernel/irq/msi.c +++ b/kernel/irq/msi.c @@ -818,6 +818,21 @@ static int msi_init_virq(struct irq_domain *domain, int virq, unsigned int vflag irqd_clr_can_reserve(irqd); if (vflags & VIRQ_NOMASK_QUIRK) irqd_set_msi_nomask_quirk(irqd); + + /* + * If the interrupt is managed but no CPU is available to + * service it, shut it down until better times. Note that + * we only do this on the !RESERVE path as x86 (the only + * architecture using this flag) deals with this in a + * different way by using a catch-all vector. + */ + if ((vflags & VIRQ_ACTIVATE) && + irqd_affinity_is_managed(irqd) && + !cpumask_intersects(irq_data_get_affinity_mask(irqd), + cpu_online_mask)) { + irqd_set_managed_shutdown(irqd); + return 0; + } } if (!(vflags & VIRQ_ACTIVATE)) diff --git a/kernel/kexec_core.c b/kernel/kexec_core.c index 68480f731192..be4b54c2c615 100644 --- a/kernel/kexec_core.c +++ b/kernel/kexec_core.c @@ -1078,7 +1078,7 @@ void crash_save_cpu(struct pt_regs *regs, int cpu) return; memset(&prstatus, 0, sizeof(prstatus)); prstatus.common.pr_pid = current->pid; - elf_core_copy_kernel_regs(&prstatus.pr_reg, regs); + elf_core_copy_regs(&prstatus.pr_reg, regs); buf = append_elf_note(buf, KEXEC_CORE_NOTE_NAME, NT_PRSTATUS, &prstatus, sizeof(prstatus)); final_note(buf); diff --git a/kernel/kthread.c b/kernel/kthread.c index 50265f69a135..544fd4097406 100644 --- a/kernel/kthread.c +++ b/kernel/kthread.c @@ -1522,5 +1522,4 @@ struct cgroup_subsys_state *kthread_blkcg(void) } return NULL; } -EXPORT_SYMBOL(kthread_blkcg); #endif diff --git a/kernel/rcu/Kconfig b/kernel/rcu/Kconfig index bf8e341e75b4..1c630e573548 100644 --- a/kernel/rcu/Kconfig +++ b/kernel/rcu/Kconfig @@ -77,31 +77,56 @@ config TASKS_RCU_GENERIC This option enables generic infrastructure code supporting task-based RCU implementations. Not for manual selection. +config FORCE_TASKS_RCU + bool "Force selection of TASKS_RCU" + depends on RCU_EXPERT + select TASKS_RCU + default n + help + This option force-enables a task-based RCU implementation + that uses only voluntary context switch (not preemption!), + idle, and user-mode execution as quiescent states. Not for + manual selection in most cases. + config TASKS_RCU - def_bool PREEMPTION + bool + default n + select IRQ_WORK + +config FORCE_TASKS_RUDE_RCU + bool "Force selection of Tasks Rude RCU" + depends on RCU_EXPERT + select TASKS_RUDE_RCU + default n help - This option enables a task-based RCU implementation that uses - only voluntary context switch (not preemption!), idle, and - user-mode execution as quiescent states. Not for manual selection. + This option force-enables a task-based RCU implementation + that uses only context switch (including preemption) and + user-mode execution as quiescent states. It forces IPIs and + context switches on all online CPUs, including idle ones, + so use with caution. Not for manual selection in most cases. config TASKS_RUDE_RCU - def_bool 0 + bool + default n + select IRQ_WORK + +config FORCE_TASKS_TRACE_RCU + bool "Force selection of Tasks Trace RCU" + depends on RCU_EXPERT + select TASKS_TRACE_RCU + default n help This option enables a task-based RCU implementation that uses - only context switch (including preemption) and user-mode - execution as quiescent states. It forces IPIs and context - switches on all online CPUs, including idle ones, so use - with caution. + explicit rcu_read_lock_trace() read-side markers, and allows + these readers to appear in the idle loop as well as on the + CPU hotplug code paths. It can force IPIs on online CPUs, + including idle ones, so use with caution. Not for manual + selection in most cases. config TASKS_TRACE_RCU - def_bool 0 + bool + default n select IRQ_WORK - help - This option enables a task-based RCU implementation that uses - explicit rcu_read_lock_trace() read-side markers, and allows - these readers to appear in the idle loop as well as on the CPU - hotplug code paths. It can force IPIs on online CPUs, including - idle ones, so use with caution. config RCU_STALL_COMMON def_bool TREE_RCU @@ -195,6 +220,20 @@ config RCU_BOOST_DELAY Accept the default if unsure. +config RCU_EXP_KTHREAD + bool "Perform RCU expedited work in a real-time kthread" + depends on RCU_BOOST && RCU_EXPERT + default !PREEMPT_RT && NR_CPUS <= 32 + help + Use this option to further reduce the latencies of expedited + grace periods at the expense of being more disruptive. + + This option is disabled by default on PREEMPT_RT=y kernels which + disable expedited grace periods after boot by unconditionally + setting rcupdate.rcu_normal_after_boot=1. + + Accept the default if unsure. + config RCU_NOCB_CPU bool "Offload RCU callback processing from boot-selected CPUs" depends on TREE_RCU @@ -225,7 +264,7 @@ config RCU_NOCB_CPU config TASKS_TRACE_RCU_READ_MB bool "Tasks Trace RCU readers use memory barriers in user and idle" - depends on RCU_EXPERT + depends on RCU_EXPERT && TASKS_TRACE_RCU default PREEMPT_RT || NR_CPUS < 8 help Use this option to further reduce the number of IPIs sent diff --git a/kernel/rcu/Kconfig.debug b/kernel/rcu/Kconfig.debug index 4fd64999300f..9b64e55d4f61 100644 --- a/kernel/rcu/Kconfig.debug +++ b/kernel/rcu/Kconfig.debug @@ -28,9 +28,6 @@ config RCU_SCALE_TEST depends on DEBUG_KERNEL select TORTURE_TEST select SRCU - select TASKS_RCU - select TASKS_RUDE_RCU - select TASKS_TRACE_RCU default n help This option provides a kernel module that runs performance @@ -47,9 +44,6 @@ config RCU_TORTURE_TEST depends on DEBUG_KERNEL select TORTURE_TEST select SRCU - select TASKS_RCU - select TASKS_RUDE_RCU - select TASKS_TRACE_RCU default n help This option provides a kernel module that runs torture tests @@ -66,9 +60,6 @@ config RCU_REF_SCALE_TEST depends on DEBUG_KERNEL select TORTURE_TEST select SRCU - select TASKS_RCU - select TASKS_RUDE_RCU - select TASKS_TRACE_RCU default n help This option provides a kernel module that runs performance tests @@ -91,6 +82,20 @@ config RCU_CPU_STALL_TIMEOUT RCU grace period persists, additional CPU stall warnings are printed at more widely spaced intervals. +config RCU_EXP_CPU_STALL_TIMEOUT + int "Expedited RCU CPU stall timeout in milliseconds" + depends on RCU_STALL_COMMON + range 0 21000 + default 20 if ANDROID + default 0 if !ANDROID + help + If a given expedited RCU grace period extends more than the + specified number of milliseconds, a CPU stall warning is printed. + If the RCU grace period persists, additional CPU stall warnings + are printed at more widely spaced intervals. A value of zero + says to use the RCU_CPU_STALL_TIMEOUT value converted from + seconds to milliseconds. + config RCU_TRACE bool "Enable tracing for RCU" depends on DEBUG_KERNEL diff --git a/kernel/rcu/rcu.h b/kernel/rcu/rcu.h index 24b5f2c2de87..152492d52715 100644 --- a/kernel/rcu/rcu.h +++ b/kernel/rcu/rcu.h @@ -210,7 +210,9 @@ static inline bool rcu_stall_is_suppressed_at_boot(void) extern int rcu_cpu_stall_ftrace_dump; extern int rcu_cpu_stall_suppress; extern int rcu_cpu_stall_timeout; +extern int rcu_exp_cpu_stall_timeout; int rcu_jiffies_till_stall_check(void); +int rcu_exp_jiffies_till_stall_check(void); static inline bool rcu_stall_is_suppressed(void) { @@ -523,6 +525,8 @@ static inline bool rcu_check_boost_fail(unsigned long gp_state, int *cpup) { ret static inline void show_rcu_gp_kthreads(void) { } static inline int rcu_get_gp_kthreads_prio(void) { return 0; } static inline void rcu_fwd_progress_check(unsigned long j) { } +static inline void rcu_gp_slow_register(atomic_t *rgssp) { } +static inline void rcu_gp_slow_unregister(atomic_t *rgssp) { } #else /* #ifdef CONFIG_TINY_RCU */ bool rcu_dynticks_zero_in_eqs(int cpu, int *vp); unsigned long rcu_get_gp_seq(void); @@ -534,14 +538,19 @@ int rcu_get_gp_kthreads_prio(void); void rcu_fwd_progress_check(unsigned long j); void rcu_force_quiescent_state(void); extern struct workqueue_struct *rcu_gp_wq; +#ifdef CONFIG_RCU_EXP_KTHREAD +extern struct kthread_worker *rcu_exp_gp_kworker; +extern struct kthread_worker *rcu_exp_par_gp_kworker; +#else /* !CONFIG_RCU_EXP_KTHREAD */ extern struct workqueue_struct *rcu_par_gp_wq; +#endif /* CONFIG_RCU_EXP_KTHREAD */ +void rcu_gp_slow_register(atomic_t *rgssp); +void rcu_gp_slow_unregister(atomic_t *rgssp); #endif /* #else #ifdef CONFIG_TINY_RCU */ #ifdef CONFIG_RCU_NOCB_CPU -bool rcu_is_nocb_cpu(int cpu); void rcu_bind_current_to_nocb(void); #else -static inline bool rcu_is_nocb_cpu(int cpu) { return false; } static inline void rcu_bind_current_to_nocb(void) { } #endif diff --git a/kernel/rcu/rcu_segcblist.c b/kernel/rcu/rcu_segcblist.c index 81145c3ece25..c54ea2b6a36b 100644 --- a/kernel/rcu/rcu_segcblist.c +++ b/kernel/rcu/rcu_segcblist.c @@ -505,10 +505,10 @@ void rcu_segcblist_advance(struct rcu_segcblist *rsclp, unsigned long seq) WRITE_ONCE(rsclp->tails[j], rsclp->tails[RCU_DONE_TAIL]); /* - * Callbacks moved, so clean up the misordered ->tails[] pointers - * that now point into the middle of the list of ready-to-invoke - * callbacks. The overall effect is to copy down the later pointers - * into the gap that was created by the now-ready segments. + * Callbacks moved, so there might be an empty RCU_WAIT_TAIL + * and a non-empty RCU_NEXT_READY_TAIL. If so, copy the + * RCU_NEXT_READY_TAIL segment to fill the RCU_WAIT_TAIL gap + * created by the now-ready-to-invoke segments. */ for (j = RCU_WAIT_TAIL; i < RCU_NEXT_TAIL; i++, j++) { if (rsclp->tails[j] == rsclp->tails[RCU_NEXT_TAIL]) diff --git a/kernel/rcu/rcuscale.c b/kernel/rcu/rcuscale.c index 5e4f1f83d38e..277a5bfb37d4 100644 --- a/kernel/rcu/rcuscale.c +++ b/kernel/rcu/rcuscale.c @@ -268,6 +268,8 @@ static struct rcu_scale_ops srcud_ops = { .name = "srcud" }; +#ifdef CONFIG_TASKS_RCU + /* * Definitions for RCU-tasks scalability testing. */ @@ -295,6 +297,16 @@ static struct rcu_scale_ops tasks_ops = { .name = "tasks" }; +#define TASKS_OPS &tasks_ops, + +#else // #ifdef CONFIG_TASKS_RCU + +#define TASKS_OPS + +#endif // #else // #ifdef CONFIG_TASKS_RCU + +#ifdef CONFIG_TASKS_TRACE_RCU + /* * Definitions for RCU-tasks-trace scalability testing. */ @@ -324,6 +336,14 @@ static struct rcu_scale_ops tasks_tracing_ops = { .name = "tasks-tracing" }; +#define TASKS_TRACING_OPS &tasks_tracing_ops, + +#else // #ifdef CONFIG_TASKS_TRACE_RCU + +#define TASKS_TRACING_OPS + +#endif // #else // #ifdef CONFIG_TASKS_TRACE_RCU + static unsigned long rcuscale_seq_diff(unsigned long new, unsigned long old) { if (!cur_ops->gp_diff) @@ -797,7 +817,7 @@ rcu_scale_init(void) long i; int firsterr = 0; static struct rcu_scale_ops *scale_ops[] = { - &rcu_ops, &srcu_ops, &srcud_ops, &tasks_ops, &tasks_tracing_ops + &rcu_ops, &srcu_ops, &srcud_ops, TASKS_OPS TASKS_TRACING_OPS }; if (!torture_init_begin(scale_type, verbose)) diff --git a/kernel/rcu/rcutorture.c b/kernel/rcu/rcutorture.c index 55d049c39608..7120165a9342 100644 --- a/kernel/rcu/rcutorture.c +++ b/kernel/rcu/rcutorture.c @@ -738,6 +738,50 @@ static struct rcu_torture_ops busted_srcud_ops = { }; /* + * Definitions for trivial CONFIG_PREEMPT=n-only torture testing. + * This implementation does not necessarily work well with CPU hotplug. + */ + +static void synchronize_rcu_trivial(void) +{ + int cpu; + + for_each_online_cpu(cpu) { + rcutorture_sched_setaffinity(current->pid, cpumask_of(cpu)); + WARN_ON_ONCE(raw_smp_processor_id() != cpu); + } +} + +static int rcu_torture_read_lock_trivial(void) __acquires(RCU) +{ + preempt_disable(); + return 0; +} + +static void rcu_torture_read_unlock_trivial(int idx) __releases(RCU) +{ + preempt_enable(); +} + +static struct rcu_torture_ops trivial_ops = { + .ttype = RCU_TRIVIAL_FLAVOR, + .init = rcu_sync_torture_init, + .readlock = rcu_torture_read_lock_trivial, + .read_delay = rcu_read_delay, /* just reuse rcu's version. */ + .readunlock = rcu_torture_read_unlock_trivial, + .readlock_held = torture_readlock_not_held, + .get_gp_seq = rcu_no_completed, + .sync = synchronize_rcu_trivial, + .exp_sync = synchronize_rcu_trivial, + .fqs = NULL, + .stats = NULL, + .irq_capable = 1, + .name = "trivial" +}; + +#ifdef CONFIG_TASKS_RCU + +/* * Definitions for RCU-tasks torture testing. */ @@ -780,47 +824,16 @@ static struct rcu_torture_ops tasks_ops = { .name = "tasks" }; -/* - * Definitions for trivial CONFIG_PREEMPT=n-only torture testing. - * This implementation does not necessarily work well with CPU hotplug. - */ +#define TASKS_OPS &tasks_ops, -static void synchronize_rcu_trivial(void) -{ - int cpu; +#else // #ifdef CONFIG_TASKS_RCU - for_each_online_cpu(cpu) { - rcutorture_sched_setaffinity(current->pid, cpumask_of(cpu)); - WARN_ON_ONCE(raw_smp_processor_id() != cpu); - } -} +#define TASKS_OPS -static int rcu_torture_read_lock_trivial(void) __acquires(RCU) -{ - preempt_disable(); - return 0; -} +#endif // #else #ifdef CONFIG_TASKS_RCU -static void rcu_torture_read_unlock_trivial(int idx) __releases(RCU) -{ - preempt_enable(); -} -static struct rcu_torture_ops trivial_ops = { - .ttype = RCU_TRIVIAL_FLAVOR, - .init = rcu_sync_torture_init, - .readlock = rcu_torture_read_lock_trivial, - .read_delay = rcu_read_delay, /* just reuse rcu's version. */ - .readunlock = rcu_torture_read_unlock_trivial, - .readlock_held = torture_readlock_not_held, - .get_gp_seq = rcu_no_completed, - .sync = synchronize_rcu_trivial, - .exp_sync = synchronize_rcu_trivial, - .fqs = NULL, - .stats = NULL, - .irq_capable = 1, - .name = "trivial" -}; +#ifdef CONFIG_TASKS_RUDE_RCU /* * Definitions for rude RCU-tasks torture testing. @@ -851,6 +864,17 @@ static struct rcu_torture_ops tasks_rude_ops = { .name = "tasks-rude" }; +#define TASKS_RUDE_OPS &tasks_rude_ops, + +#else // #ifdef CONFIG_TASKS_RUDE_RCU + +#define TASKS_RUDE_OPS + +#endif // #else #ifdef CONFIG_TASKS_RUDE_RCU + + +#ifdef CONFIG_TASKS_TRACE_RCU + /* * Definitions for tracing RCU-tasks torture testing. */ @@ -893,6 +917,15 @@ static struct rcu_torture_ops tasks_tracing_ops = { .name = "tasks-tracing" }; +#define TASKS_TRACING_OPS &tasks_tracing_ops, + +#else // #ifdef CONFIG_TASKS_TRACE_RCU + +#define TASKS_TRACING_OPS + +#endif // #else #ifdef CONFIG_TASKS_TRACE_RCU + + static unsigned long rcutorture_seq_diff(unsigned long new, unsigned long old) { if (!cur_ops->gp_diff) @@ -1178,7 +1211,7 @@ rcu_torture_writer(void *arg) " GP expediting controlled from boot/sysfs for %s.\n", torture_type, cur_ops->name); if (WARN_ONCE(nsynctypes == 0, - "rcu_torture_writer: No update-side primitives.\n")) { + "%s: No update-side primitives.\n", __func__)) { /* * No updates primitives, so don't try updating. * The resulting test won't be testing much, hence the @@ -1186,6 +1219,7 @@ rcu_torture_writer(void *arg) */ rcu_torture_writer_state = RTWS_STOPPING; torture_kthread_stopping("rcu_torture_writer"); + return 0; } do { @@ -1322,6 +1356,17 @@ rcu_torture_fakewriter(void *arg) VERBOSE_TOROUT_STRING("rcu_torture_fakewriter task started"); set_user_nice(current, MAX_NICE); + if (WARN_ONCE(nsynctypes == 0, + "%s: No update-side primitives.\n", __func__)) { + /* + * No updates primitives, so don't try updating. + * The resulting test won't be testing much, hence the + * above WARN_ONCE(). + */ + torture_kthread_stopping("rcu_torture_fakewriter"); + return 0; + } + do { torture_hrtimeout_jiffies(torture_random(&rand) % 10, &rand); if (cur_ops->cb_barrier != NULL && @@ -2916,10 +2961,12 @@ rcu_torture_cleanup(void) pr_info("%s: Invoking %pS().\n", __func__, cur_ops->cb_barrier); cur_ops->cb_barrier(); } + rcu_gp_slow_unregister(NULL); return; } if (!cur_ops) { torture_cleanup_end(); + rcu_gp_slow_unregister(NULL); return; } @@ -3016,6 +3063,7 @@ rcu_torture_cleanup(void) else rcu_torture_print_module_parms(cur_ops, "End of test: SUCCESS"); torture_cleanup_end(); + rcu_gp_slow_unregister(&rcu_fwd_cb_nodelay); } #ifdef CONFIG_DEBUG_OBJECTS_RCU_HEAD @@ -3096,9 +3144,9 @@ rcu_torture_init(void) int flags = 0; unsigned long gp_seq = 0; static struct rcu_torture_ops *torture_ops[] = { - &rcu_ops, &rcu_busted_ops, &srcu_ops, &srcud_ops, - &busted_srcud_ops, &tasks_ops, &tasks_rude_ops, - &tasks_tracing_ops, &trivial_ops, + &rcu_ops, &rcu_busted_ops, &srcu_ops, &srcud_ops, &busted_srcud_ops, + TASKS_OPS TASKS_RUDE_OPS TASKS_TRACING_OPS + &trivial_ops, }; if (!torture_init_begin(torture_type, verbose)) @@ -3320,6 +3368,7 @@ rcu_torture_init(void) if (object_debug) rcu_test_debug_objects(); torture_init_end(); + rcu_gp_slow_register(&rcu_fwd_cb_nodelay); return 0; unwind: diff --git a/kernel/rcu/refscale.c b/kernel/rcu/refscale.c index 5489ff7f478e..909644abee67 100644 --- a/kernel/rcu/refscale.c +++ b/kernel/rcu/refscale.c @@ -207,6 +207,8 @@ static struct ref_scale_ops srcu_ops = { .name = "srcu" }; +#ifdef CONFIG_TASKS_RCU + // Definitions for RCU Tasks ref scale testing: Empty read markers. // These definitions also work for RCU Rude readers. static void rcu_tasks_ref_scale_read_section(const int nloops) @@ -232,6 +234,16 @@ static struct ref_scale_ops rcu_tasks_ops = { .name = "rcu-tasks" }; +#define RCU_TASKS_OPS &rcu_tasks_ops, + +#else // #ifdef CONFIG_TASKS_RCU + +#define RCU_TASKS_OPS + +#endif // #else // #ifdef CONFIG_TASKS_RCU + +#ifdef CONFIG_TASKS_TRACE_RCU + // Definitions for RCU Tasks Trace ref scale testing. static void rcu_trace_ref_scale_read_section(const int nloops) { @@ -261,6 +273,14 @@ static struct ref_scale_ops rcu_trace_ops = { .name = "rcu-trace" }; +#define RCU_TRACE_OPS &rcu_trace_ops, + +#else // #ifdef CONFIG_TASKS_TRACE_RCU + +#define RCU_TRACE_OPS + +#endif // #else // #ifdef CONFIG_TASKS_TRACE_RCU + // Definitions for reference count static atomic_t refcnt; @@ -790,7 +810,7 @@ ref_scale_init(void) long i; int firsterr = 0; static struct ref_scale_ops *scale_ops[] = { - &rcu_ops, &srcu_ops, &rcu_trace_ops, &rcu_tasks_ops, &refcnt_ops, &rwlock_ops, + &rcu_ops, &srcu_ops, RCU_TRACE_OPS RCU_TASKS_OPS &refcnt_ops, &rwlock_ops, &rwsem_ops, &lock_ops, &lock_irq_ops, &acqrel_ops, &clock_ops, }; diff --git a/kernel/rcu/srcutree.c b/kernel/rcu/srcutree.c index 6833d8887181..50ba70f019de 100644 --- a/kernel/rcu/srcutree.c +++ b/kernel/rcu/srcutree.c @@ -24,6 +24,7 @@ #include <linux/smp.h> #include <linux/delay.h> #include <linux/module.h> +#include <linux/slab.h> #include <linux/srcu.h> #include "rcu.h" @@ -38,6 +39,35 @@ module_param(exp_holdoff, ulong, 0444); static ulong counter_wrap_check = (ULONG_MAX >> 2); module_param(counter_wrap_check, ulong, 0444); +/* + * Control conversion to SRCU_SIZE_BIG: + * 0: Don't convert at all. + * 1: Convert at init_srcu_struct() time. + * 2: Convert when rcutorture invokes srcu_torture_stats_print(). + * 3: Decide at boot time based on system shape (default). + * 0x1x: Convert when excessive contention encountered. + */ +#define SRCU_SIZING_NONE 0 +#define SRCU_SIZING_INIT 1 +#define SRCU_SIZING_TORTURE 2 +#define SRCU_SIZING_AUTO 3 +#define SRCU_SIZING_CONTEND 0x10 +#define SRCU_SIZING_IS(x) ((convert_to_big & ~SRCU_SIZING_CONTEND) == x) +#define SRCU_SIZING_IS_NONE() (SRCU_SIZING_IS(SRCU_SIZING_NONE)) +#define SRCU_SIZING_IS_INIT() (SRCU_SIZING_IS(SRCU_SIZING_INIT)) +#define SRCU_SIZING_IS_TORTURE() (SRCU_SIZING_IS(SRCU_SIZING_TORTURE)) +#define SRCU_SIZING_IS_CONTEND() (convert_to_big & SRCU_SIZING_CONTEND) +static int convert_to_big = SRCU_SIZING_AUTO; +module_param(convert_to_big, int, 0444); + +/* Number of CPUs to trigger init_srcu_struct()-time transition to big. */ +static int big_cpu_lim __read_mostly = 128; +module_param(big_cpu_lim, int, 0444); + +/* Contention events per jiffy to initiate transition to big. */ +static int small_contention_lim __read_mostly = 100; +module_param(small_contention_lim, int, 0444); + /* Early-boot callback-management, so early that no lock is required! */ static LIST_HEAD(srcu_boot_list); static bool __read_mostly srcu_init_done; @@ -48,39 +78,90 @@ static void process_srcu(struct work_struct *work); static void srcu_delay_timer(struct timer_list *t); /* Wrappers for lock acquisition and release, see raw_spin_lock_rcu_node(). */ -#define spin_lock_rcu_node(p) \ -do { \ - spin_lock(&ACCESS_PRIVATE(p, lock)); \ - smp_mb__after_unlock_lock(); \ +#define spin_lock_rcu_node(p) \ +do { \ + spin_lock(&ACCESS_PRIVATE(p, lock)); \ + smp_mb__after_unlock_lock(); \ } while (0) #define spin_unlock_rcu_node(p) spin_unlock(&ACCESS_PRIVATE(p, lock)) -#define spin_lock_irq_rcu_node(p) \ -do { \ - spin_lock_irq(&ACCESS_PRIVATE(p, lock)); \ - smp_mb__after_unlock_lock(); \ +#define spin_lock_irq_rcu_node(p) \ +do { \ + spin_lock_irq(&ACCESS_PRIVATE(p, lock)); \ + smp_mb__after_unlock_lock(); \ } while (0) -#define spin_unlock_irq_rcu_node(p) \ +#define spin_unlock_irq_rcu_node(p) \ spin_unlock_irq(&ACCESS_PRIVATE(p, lock)) -#define spin_lock_irqsave_rcu_node(p, flags) \ -do { \ - spin_lock_irqsave(&ACCESS_PRIVATE(p, lock), flags); \ - smp_mb__after_unlock_lock(); \ +#define spin_lock_irqsave_rcu_node(p, flags) \ +do { \ + spin_lock_irqsave(&ACCESS_PRIVATE(p, lock), flags); \ + smp_mb__after_unlock_lock(); \ } while (0) -#define spin_unlock_irqrestore_rcu_node(p, flags) \ - spin_unlock_irqrestore(&ACCESS_PRIVATE(p, lock), flags) \ +#define spin_trylock_irqsave_rcu_node(p, flags) \ +({ \ + bool ___locked = spin_trylock_irqsave(&ACCESS_PRIVATE(p, lock), flags); \ + \ + if (___locked) \ + smp_mb__after_unlock_lock(); \ + ___locked; \ +}) + +#define spin_unlock_irqrestore_rcu_node(p, flags) \ + spin_unlock_irqrestore(&ACCESS_PRIVATE(p, lock), flags) \ /* - * Initialize SRCU combining tree. Note that statically allocated + * Initialize SRCU per-CPU data. Note that statically allocated * srcu_struct structures might already have srcu_read_lock() and * srcu_read_unlock() running against them. So if the is_static parameter * is set, don't initialize ->srcu_lock_count[] and ->srcu_unlock_count[]. */ -static void init_srcu_struct_nodes(struct srcu_struct *ssp) +static void init_srcu_struct_data(struct srcu_struct *ssp) +{ + int cpu; + struct srcu_data *sdp; + + /* + * Initialize the per-CPU srcu_data array, which feeds into the + * leaves of the srcu_node tree. + */ + WARN_ON_ONCE(ARRAY_SIZE(sdp->srcu_lock_count) != + ARRAY_SIZE(sdp->srcu_unlock_count)); + for_each_possible_cpu(cpu) { + sdp = per_cpu_ptr(ssp->sda, cpu); + spin_lock_init(&ACCESS_PRIVATE(sdp, lock)); + rcu_segcblist_init(&sdp->srcu_cblist); + sdp->srcu_cblist_invoking = false; + sdp->srcu_gp_seq_needed = ssp->srcu_gp_seq; + sdp->srcu_gp_seq_needed_exp = ssp->srcu_gp_seq; + sdp->mynode = NULL; + sdp->cpu = cpu; + INIT_WORK(&sdp->work, srcu_invoke_callbacks); + timer_setup(&sdp->delay_work, srcu_delay_timer, 0); + sdp->ssp = ssp; + } +} + +/* Invalid seq state, used during snp node initialization */ +#define SRCU_SNP_INIT_SEQ 0x2 + +/* + * Check whether sequence number corresponding to snp node, + * is invalid. + */ +static inline bool srcu_invl_snp_seq(unsigned long s) +{ + return rcu_seq_state(s) == SRCU_SNP_INIT_SEQ; +} + +/* + * Allocated and initialize SRCU combining tree. Returns @true if + * allocation succeeded and @false otherwise. + */ +static bool init_srcu_struct_nodes(struct srcu_struct *ssp, gfp_t gfp_flags) { int cpu; int i; @@ -92,6 +173,9 @@ static void init_srcu_struct_nodes(struct srcu_struct *ssp) /* Initialize geometry if it has not already been initialized. */ rcu_init_geometry(); + ssp->node = kcalloc(rcu_num_nodes, sizeof(*ssp->node), gfp_flags); + if (!ssp->node) + return false; /* Work out the overall tree geometry. */ ssp->level[0] = &ssp->node[0]; @@ -105,10 +189,10 @@ static void init_srcu_struct_nodes(struct srcu_struct *ssp) WARN_ON_ONCE(ARRAY_SIZE(snp->srcu_have_cbs) != ARRAY_SIZE(snp->srcu_data_have_cbs)); for (i = 0; i < ARRAY_SIZE(snp->srcu_have_cbs); i++) { - snp->srcu_have_cbs[i] = 0; + snp->srcu_have_cbs[i] = SRCU_SNP_INIT_SEQ; snp->srcu_data_have_cbs[i] = 0; } - snp->srcu_gp_seq_needed_exp = 0; + snp->srcu_gp_seq_needed_exp = SRCU_SNP_INIT_SEQ; snp->grplo = -1; snp->grphi = -1; if (snp == &ssp->node[0]) { @@ -129,39 +213,31 @@ static void init_srcu_struct_nodes(struct srcu_struct *ssp) * Initialize the per-CPU srcu_data array, which feeds into the * leaves of the srcu_node tree. */ - WARN_ON_ONCE(ARRAY_SIZE(sdp->srcu_lock_count) != - ARRAY_SIZE(sdp->srcu_unlock_count)); level = rcu_num_lvls - 1; snp_first = ssp->level[level]; for_each_possible_cpu(cpu) { sdp = per_cpu_ptr(ssp->sda, cpu); - spin_lock_init(&ACCESS_PRIVATE(sdp, lock)); - rcu_segcblist_init(&sdp->srcu_cblist); - sdp->srcu_cblist_invoking = false; - sdp->srcu_gp_seq_needed = ssp->srcu_gp_seq; - sdp->srcu_gp_seq_needed_exp = ssp->srcu_gp_seq; sdp->mynode = &snp_first[cpu / levelspread[level]]; for (snp = sdp->mynode; snp != NULL; snp = snp->srcu_parent) { if (snp->grplo < 0) snp->grplo = cpu; snp->grphi = cpu; } - sdp->cpu = cpu; - INIT_WORK(&sdp->work, srcu_invoke_callbacks); - timer_setup(&sdp->delay_work, srcu_delay_timer, 0); - sdp->ssp = ssp; sdp->grpmask = 1 << (cpu - sdp->mynode->grplo); } + smp_store_release(&ssp->srcu_size_state, SRCU_SIZE_WAIT_BARRIER); + return true; } /* * Initialize non-compile-time initialized fields, including the - * associated srcu_node and srcu_data structures. The is_static - * parameter is passed through to init_srcu_struct_nodes(), and - * also tells us that ->sda has already been wired up to srcu_data. + * associated srcu_node and srcu_data structures. The is_static parameter + * tells us that ->sda has already been wired up to srcu_data. */ static int init_srcu_struct_fields(struct srcu_struct *ssp, bool is_static) { + ssp->srcu_size_state = SRCU_SIZE_SMALL; + ssp->node = NULL; mutex_init(&ssp->srcu_cb_mutex); mutex_init(&ssp->srcu_gp_mutex); ssp->srcu_idx = 0; @@ -170,13 +246,25 @@ static int init_srcu_struct_fields(struct srcu_struct *ssp, bool is_static) mutex_init(&ssp->srcu_barrier_mutex); atomic_set(&ssp->srcu_barrier_cpu_cnt, 0); INIT_DELAYED_WORK(&ssp->work, process_srcu); + ssp->sda_is_static = is_static; if (!is_static) ssp->sda = alloc_percpu(struct srcu_data); if (!ssp->sda) return -ENOMEM; - init_srcu_struct_nodes(ssp); + init_srcu_struct_data(ssp); ssp->srcu_gp_seq_needed_exp = 0; ssp->srcu_last_gp_end = ktime_get_mono_fast_ns(); + if (READ_ONCE(ssp->srcu_size_state) == SRCU_SIZE_SMALL && SRCU_SIZING_IS_INIT()) { + if (!init_srcu_struct_nodes(ssp, GFP_ATOMIC)) { + if (!ssp->sda_is_static) { + free_percpu(ssp->sda); + ssp->sda = NULL; + return -ENOMEM; + } + } else { + WRITE_ONCE(ssp->srcu_size_state, SRCU_SIZE_BIG); + } + } smp_store_release(&ssp->srcu_gp_seq_needed, 0); /* Init done. */ return 0; } @@ -214,6 +302,86 @@ EXPORT_SYMBOL_GPL(init_srcu_struct); #endif /* #else #ifdef CONFIG_DEBUG_LOCK_ALLOC */ /* + * Initiate a transition to SRCU_SIZE_BIG with lock held. + */ +static void __srcu_transition_to_big(struct srcu_struct *ssp) +{ + lockdep_assert_held(&ACCESS_PRIVATE(ssp, lock)); + smp_store_release(&ssp->srcu_size_state, SRCU_SIZE_ALLOC); +} + +/* + * Initiate an idempotent transition to SRCU_SIZE_BIG. + */ +static void srcu_transition_to_big(struct srcu_struct *ssp) +{ + unsigned long flags; + + /* Double-checked locking on ->srcu_size-state. */ + if (smp_load_acquire(&ssp->srcu_size_state) != SRCU_SIZE_SMALL) + return; + spin_lock_irqsave_rcu_node(ssp, flags); + if (smp_load_acquire(&ssp->srcu_size_state) != SRCU_SIZE_SMALL) { + spin_unlock_irqrestore_rcu_node(ssp, flags); + return; + } + __srcu_transition_to_big(ssp); + spin_unlock_irqrestore_rcu_node(ssp, flags); +} + +/* + * Check to see if the just-encountered contention event justifies + * a transition to SRCU_SIZE_BIG. + */ +static void spin_lock_irqsave_check_contention(struct srcu_struct *ssp) +{ + unsigned long j; + + if (!SRCU_SIZING_IS_CONTEND() || ssp->srcu_size_state) + return; + j = jiffies; + if (ssp->srcu_size_jiffies != j) { + ssp->srcu_size_jiffies = j; + ssp->srcu_n_lock_retries = 0; + } + if (++ssp->srcu_n_lock_retries <= small_contention_lim) + return; + __srcu_transition_to_big(ssp); +} + +/* + * Acquire the specified srcu_data structure's ->lock, but check for + * excessive contention, which results in initiation of a transition + * to SRCU_SIZE_BIG. But only if the srcutree.convert_to_big module + * parameter permits this. + */ +static void spin_lock_irqsave_sdp_contention(struct srcu_data *sdp, unsigned long *flags) +{ + struct srcu_struct *ssp = sdp->ssp; + + if (spin_trylock_irqsave_rcu_node(sdp, *flags)) + return; + spin_lock_irqsave_rcu_node(ssp, *flags); + spin_lock_irqsave_check_contention(ssp); + spin_unlock_irqrestore_rcu_node(ssp, *flags); + spin_lock_irqsave_rcu_node(sdp, *flags); +} + +/* + * Acquire the specified srcu_struct structure's ->lock, but check for + * excessive contention, which results in initiation of a transition + * to SRCU_SIZE_BIG. But only if the srcutree.convert_to_big module + * parameter permits this. + */ +static void spin_lock_irqsave_ssp_contention(struct srcu_struct *ssp, unsigned long *flags) +{ + if (spin_trylock_irqsave_rcu_node(ssp, *flags)) + return; + spin_lock_irqsave_rcu_node(ssp, *flags); + spin_lock_irqsave_check_contention(ssp); +} + +/* * First-use initialization of statically allocated srcu_struct * structure. Wiring up the combining tree is more than can be * done with compile-time initialization, so this check is added @@ -343,7 +511,10 @@ static bool srcu_readers_active(struct srcu_struct *ssp) return sum; } -#define SRCU_INTERVAL 1 +#define SRCU_INTERVAL 1 // Base delay if no expedited GPs pending. +#define SRCU_MAX_INTERVAL 10 // Maximum incremental delay from slow readers. +#define SRCU_MAX_NODELAY_PHASE 1 // Maximum per-GP-phase consecutive no-delay instances. +#define SRCU_MAX_NODELAY 100 // Maximum consecutive no-delay instances. /* * Return grace-period delay, zero if there are expedited grace @@ -351,10 +522,18 @@ static bool srcu_readers_active(struct srcu_struct *ssp) */ static unsigned long srcu_get_delay(struct srcu_struct *ssp) { - if (ULONG_CMP_LT(READ_ONCE(ssp->srcu_gp_seq), - READ_ONCE(ssp->srcu_gp_seq_needed_exp))) - return 0; - return SRCU_INTERVAL; + unsigned long jbase = SRCU_INTERVAL; + + if (ULONG_CMP_LT(READ_ONCE(ssp->srcu_gp_seq), READ_ONCE(ssp->srcu_gp_seq_needed_exp))) + jbase = 0; + if (rcu_seq_state(READ_ONCE(ssp->srcu_gp_seq))) + jbase += jiffies - READ_ONCE(ssp->srcu_gp_start); + if (!jbase) { + WRITE_ONCE(ssp->srcu_n_exp_nodelay, READ_ONCE(ssp->srcu_n_exp_nodelay) + 1); + if (READ_ONCE(ssp->srcu_n_exp_nodelay) > SRCU_MAX_NODELAY_PHASE) + jbase = 1; + } + return jbase > SRCU_MAX_INTERVAL ? SRCU_MAX_INTERVAL : jbase; } /** @@ -382,13 +561,20 @@ void cleanup_srcu_struct(struct srcu_struct *ssp) return; /* Forgot srcu_barrier(), so just leak it! */ } if (WARN_ON(rcu_seq_state(READ_ONCE(ssp->srcu_gp_seq)) != SRCU_STATE_IDLE) || + WARN_ON(rcu_seq_current(&ssp->srcu_gp_seq) != ssp->srcu_gp_seq_needed) || WARN_ON(srcu_readers_active(ssp))) { - pr_info("%s: Active srcu_struct %p state: %d\n", - __func__, ssp, rcu_seq_state(READ_ONCE(ssp->srcu_gp_seq))); + pr_info("%s: Active srcu_struct %p read state: %d gp state: %lu/%lu\n", + __func__, ssp, rcu_seq_state(READ_ONCE(ssp->srcu_gp_seq)), + rcu_seq_current(&ssp->srcu_gp_seq), ssp->srcu_gp_seq_needed); return; /* Caller forgot to stop doing call_srcu()? */ } - free_percpu(ssp->sda); - ssp->sda = NULL; + if (!ssp->sda_is_static) { + free_percpu(ssp->sda); + ssp->sda = NULL; + } + kfree(ssp->node); + ssp->node = NULL; + ssp->srcu_size_state = SRCU_SIZE_SMALL; } EXPORT_SYMBOL_GPL(cleanup_srcu_struct); @@ -434,9 +620,13 @@ EXPORT_SYMBOL_GPL(__srcu_read_unlock); */ static void srcu_gp_start(struct srcu_struct *ssp) { - struct srcu_data *sdp = this_cpu_ptr(ssp->sda); + struct srcu_data *sdp; int state; + if (smp_load_acquire(&ssp->srcu_size_state) < SRCU_SIZE_WAIT_BARRIER) + sdp = per_cpu_ptr(ssp->sda, 0); + else + sdp = this_cpu_ptr(ssp->sda); lockdep_assert_held(&ACCESS_PRIVATE(ssp, lock)); WARN_ON_ONCE(ULONG_CMP_GE(ssp->srcu_gp_seq, ssp->srcu_gp_seq_needed)); spin_lock_rcu_node(sdp); /* Interrupts already disabled. */ @@ -445,6 +635,8 @@ static void srcu_gp_start(struct srcu_struct *ssp) (void)rcu_segcblist_accelerate(&sdp->srcu_cblist, rcu_seq_snap(&ssp->srcu_gp_seq)); spin_unlock_rcu_node(sdp); /* Interrupts remain disabled. */ + WRITE_ONCE(ssp->srcu_gp_start, jiffies); + WRITE_ONCE(ssp->srcu_n_exp_nodelay, 0); smp_mb(); /* Order prior store to ->srcu_gp_seq_needed vs. GP start. */ rcu_seq_start(&ssp->srcu_gp_seq); state = rcu_seq_state(ssp->srcu_gp_seq); @@ -517,7 +709,9 @@ static void srcu_gp_end(struct srcu_struct *ssp) int idx; unsigned long mask; struct srcu_data *sdp; + unsigned long sgsne; struct srcu_node *snp; + int ss_state; /* Prevent more than one additional grace period. */ mutex_lock(&ssp->srcu_cb_mutex); @@ -526,7 +720,7 @@ static void srcu_gp_end(struct srcu_struct *ssp) spin_lock_irq_rcu_node(ssp); idx = rcu_seq_state(ssp->srcu_gp_seq); WARN_ON_ONCE(idx != SRCU_STATE_SCAN2); - cbdelay = srcu_get_delay(ssp); + cbdelay = !!srcu_get_delay(ssp); WRITE_ONCE(ssp->srcu_last_gp_end, ktime_get_mono_fast_ns()); rcu_seq_end(&ssp->srcu_gp_seq); gpseq = rcu_seq_current(&ssp->srcu_gp_seq); @@ -537,38 +731,45 @@ static void srcu_gp_end(struct srcu_struct *ssp) /* A new grace period can start at this point. But only one. */ /* Initiate callback invocation as needed. */ - idx = rcu_seq_ctr(gpseq) % ARRAY_SIZE(snp->srcu_have_cbs); - srcu_for_each_node_breadth_first(ssp, snp) { - spin_lock_irq_rcu_node(snp); - cbs = false; - last_lvl = snp >= ssp->level[rcu_num_lvls - 1]; - if (last_lvl) - cbs = snp->srcu_have_cbs[idx] == gpseq; - snp->srcu_have_cbs[idx] = gpseq; - rcu_seq_set_state(&snp->srcu_have_cbs[idx], 1); - if (ULONG_CMP_LT(snp->srcu_gp_seq_needed_exp, gpseq)) - WRITE_ONCE(snp->srcu_gp_seq_needed_exp, gpseq); - mask = snp->srcu_data_have_cbs[idx]; - snp->srcu_data_have_cbs[idx] = 0; - spin_unlock_irq_rcu_node(snp); - if (cbs) - srcu_schedule_cbs_snp(ssp, snp, mask, cbdelay); - - /* Occasionally prevent srcu_data counter wrap. */ - if (!(gpseq & counter_wrap_check) && last_lvl) - for (cpu = snp->grplo; cpu <= snp->grphi; cpu++) { - sdp = per_cpu_ptr(ssp->sda, cpu); - spin_lock_irqsave_rcu_node(sdp, flags); - if (ULONG_CMP_GE(gpseq, - sdp->srcu_gp_seq_needed + 100)) - sdp->srcu_gp_seq_needed = gpseq; - if (ULONG_CMP_GE(gpseq, - sdp->srcu_gp_seq_needed_exp + 100)) - sdp->srcu_gp_seq_needed_exp = gpseq; - spin_unlock_irqrestore_rcu_node(sdp, flags); - } + ss_state = smp_load_acquire(&ssp->srcu_size_state); + if (ss_state < SRCU_SIZE_WAIT_BARRIER) { + srcu_schedule_cbs_sdp(per_cpu_ptr(ssp->sda, 0), cbdelay); + } else { + idx = rcu_seq_ctr(gpseq) % ARRAY_SIZE(snp->srcu_have_cbs); + srcu_for_each_node_breadth_first(ssp, snp) { + spin_lock_irq_rcu_node(snp); + cbs = false; + last_lvl = snp >= ssp->level[rcu_num_lvls - 1]; + if (last_lvl) + cbs = ss_state < SRCU_SIZE_BIG || snp->srcu_have_cbs[idx] == gpseq; + snp->srcu_have_cbs[idx] = gpseq; + rcu_seq_set_state(&snp->srcu_have_cbs[idx], 1); + sgsne = snp->srcu_gp_seq_needed_exp; + if (srcu_invl_snp_seq(sgsne) || ULONG_CMP_LT(sgsne, gpseq)) + WRITE_ONCE(snp->srcu_gp_seq_needed_exp, gpseq); + if (ss_state < SRCU_SIZE_BIG) + mask = ~0; + else + mask = snp->srcu_data_have_cbs[idx]; + snp->srcu_data_have_cbs[idx] = 0; + spin_unlock_irq_rcu_node(snp); + if (cbs) + srcu_schedule_cbs_snp(ssp, snp, mask, cbdelay); + } } + /* Occasionally prevent srcu_data counter wrap. */ + if (!(gpseq & counter_wrap_check)) + for_each_possible_cpu(cpu) { + sdp = per_cpu_ptr(ssp->sda, cpu); + spin_lock_irqsave_rcu_node(sdp, flags); + if (ULONG_CMP_GE(gpseq, sdp->srcu_gp_seq_needed + 100)) + sdp->srcu_gp_seq_needed = gpseq; + if (ULONG_CMP_GE(gpseq, sdp->srcu_gp_seq_needed_exp + 100)) + sdp->srcu_gp_seq_needed_exp = gpseq; + spin_unlock_irqrestore_rcu_node(sdp, flags); + } + /* Callback initiation done, allow grace periods after next. */ mutex_unlock(&ssp->srcu_cb_mutex); @@ -583,6 +784,14 @@ static void srcu_gp_end(struct srcu_struct *ssp) } else { spin_unlock_irq_rcu_node(ssp); } + + /* Transition to big if needed. */ + if (ss_state != SRCU_SIZE_SMALL && ss_state != SRCU_SIZE_BIG) { + if (ss_state == SRCU_SIZE_ALLOC) + init_srcu_struct_nodes(ssp, GFP_KERNEL); + else + smp_store_release(&ssp->srcu_size_state, ss_state + 1); + } } /* @@ -596,20 +805,24 @@ static void srcu_funnel_exp_start(struct srcu_struct *ssp, struct srcu_node *snp unsigned long s) { unsigned long flags; + unsigned long sgsne; - for (; snp != NULL; snp = snp->srcu_parent) { - if (rcu_seq_done(&ssp->srcu_gp_seq, s) || - ULONG_CMP_GE(READ_ONCE(snp->srcu_gp_seq_needed_exp), s)) - return; - spin_lock_irqsave_rcu_node(snp, flags); - if (ULONG_CMP_GE(snp->srcu_gp_seq_needed_exp, s)) { + if (snp) + for (; snp != NULL; snp = snp->srcu_parent) { + sgsne = READ_ONCE(snp->srcu_gp_seq_needed_exp); + if (rcu_seq_done(&ssp->srcu_gp_seq, s) || + (!srcu_invl_snp_seq(sgsne) && ULONG_CMP_GE(sgsne, s))) + return; + spin_lock_irqsave_rcu_node(snp, flags); + sgsne = snp->srcu_gp_seq_needed_exp; + if (!srcu_invl_snp_seq(sgsne) && ULONG_CMP_GE(sgsne, s)) { + spin_unlock_irqrestore_rcu_node(snp, flags); + return; + } + WRITE_ONCE(snp->srcu_gp_seq_needed_exp, s); spin_unlock_irqrestore_rcu_node(snp, flags); - return; } - WRITE_ONCE(snp->srcu_gp_seq_needed_exp, s); - spin_unlock_irqrestore_rcu_node(snp, flags); - } - spin_lock_irqsave_rcu_node(ssp, flags); + spin_lock_irqsave_ssp_contention(ssp, &flags); if (ULONG_CMP_LT(ssp->srcu_gp_seq_needed_exp, s)) WRITE_ONCE(ssp->srcu_gp_seq_needed_exp, s); spin_unlock_irqrestore_rcu_node(ssp, flags); @@ -630,39 +843,47 @@ static void srcu_funnel_gp_start(struct srcu_struct *ssp, struct srcu_data *sdp, { unsigned long flags; int idx = rcu_seq_ctr(s) % ARRAY_SIZE(sdp->mynode->srcu_have_cbs); - struct srcu_node *snp = sdp->mynode; + unsigned long sgsne; + struct srcu_node *snp; + struct srcu_node *snp_leaf; unsigned long snp_seq; - /* Each pass through the loop does one level of the srcu_node tree. */ - for (; snp != NULL; snp = snp->srcu_parent) { - if (rcu_seq_done(&ssp->srcu_gp_seq, s) && snp != sdp->mynode) - return; /* GP already done and CBs recorded. */ - spin_lock_irqsave_rcu_node(snp, flags); - if (ULONG_CMP_GE(snp->srcu_have_cbs[idx], s)) { + /* Ensure that snp node tree is fully initialized before traversing it */ + if (smp_load_acquire(&ssp->srcu_size_state) < SRCU_SIZE_WAIT_BARRIER) + snp_leaf = NULL; + else + snp_leaf = sdp->mynode; + + if (snp_leaf) + /* Each pass through the loop does one level of the srcu_node tree. */ + for (snp = snp_leaf; snp != NULL; snp = snp->srcu_parent) { + if (rcu_seq_done(&ssp->srcu_gp_seq, s) && snp != snp_leaf) + return; /* GP already done and CBs recorded. */ + spin_lock_irqsave_rcu_node(snp, flags); snp_seq = snp->srcu_have_cbs[idx]; - if (snp == sdp->mynode && snp_seq == s) - snp->srcu_data_have_cbs[idx] |= sdp->grpmask; - spin_unlock_irqrestore_rcu_node(snp, flags); - if (snp == sdp->mynode && snp_seq != s) { - srcu_schedule_cbs_sdp(sdp, do_norm - ? SRCU_INTERVAL - : 0); + if (!srcu_invl_snp_seq(snp_seq) && ULONG_CMP_GE(snp_seq, s)) { + if (snp == snp_leaf && snp_seq == s) + snp->srcu_data_have_cbs[idx] |= sdp->grpmask; + spin_unlock_irqrestore_rcu_node(snp, flags); + if (snp == snp_leaf && snp_seq != s) { + srcu_schedule_cbs_sdp(sdp, do_norm ? SRCU_INTERVAL : 0); + return; + } + if (!do_norm) + srcu_funnel_exp_start(ssp, snp, s); return; } - if (!do_norm) - srcu_funnel_exp_start(ssp, snp, s); - return; + snp->srcu_have_cbs[idx] = s; + if (snp == snp_leaf) + snp->srcu_data_have_cbs[idx] |= sdp->grpmask; + sgsne = snp->srcu_gp_seq_needed_exp; + if (!do_norm && (srcu_invl_snp_seq(sgsne) || ULONG_CMP_LT(sgsne, s))) + WRITE_ONCE(snp->srcu_gp_seq_needed_exp, s); + spin_unlock_irqrestore_rcu_node(snp, flags); } - snp->srcu_have_cbs[idx] = s; - if (snp == sdp->mynode) - snp->srcu_data_have_cbs[idx] |= sdp->grpmask; - if (!do_norm && ULONG_CMP_LT(snp->srcu_gp_seq_needed_exp, s)) - WRITE_ONCE(snp->srcu_gp_seq_needed_exp, s); - spin_unlock_irqrestore_rcu_node(snp, flags); - } /* Top of tree, must ensure the grace period will be started. */ - spin_lock_irqsave_rcu_node(ssp, flags); + spin_lock_irqsave_ssp_contention(ssp, &flags); if (ULONG_CMP_LT(ssp->srcu_gp_seq_needed, s)) { /* * Record need for grace period s. Pair with load @@ -678,9 +899,15 @@ static void srcu_funnel_gp_start(struct srcu_struct *ssp, struct srcu_data *sdp, rcu_seq_state(ssp->srcu_gp_seq) == SRCU_STATE_IDLE) { WARN_ON_ONCE(ULONG_CMP_GE(ssp->srcu_gp_seq, ssp->srcu_gp_seq_needed)); srcu_gp_start(ssp); + + // And how can that list_add() in the "else" clause + // possibly be safe for concurrent execution? Well, + // it isn't. And it does not have to be. After all, it + // can only be executed during early boot when there is only + // the one boot CPU running with interrupts still disabled. if (likely(srcu_init_done)) queue_delayed_work(rcu_gp_wq, &ssp->work, - srcu_get_delay(ssp)); + !!srcu_get_delay(ssp)); else if (list_empty(&ssp->work.work.entry)) list_add(&ssp->work.work.entry, &srcu_boot_list); } @@ -814,11 +1041,17 @@ static unsigned long srcu_gp_start_if_needed(struct srcu_struct *ssp, bool needgp = false; unsigned long s; struct srcu_data *sdp; + struct srcu_node *sdp_mynode; + int ss_state; check_init_srcu_struct(ssp); idx = srcu_read_lock(ssp); - sdp = raw_cpu_ptr(ssp->sda); - spin_lock_irqsave_rcu_node(sdp, flags); + ss_state = smp_load_acquire(&ssp->srcu_size_state); + if (ss_state < SRCU_SIZE_WAIT_CALL) + sdp = per_cpu_ptr(ssp->sda, 0); + else + sdp = raw_cpu_ptr(ssp->sda); + spin_lock_irqsave_sdp_contention(sdp, &flags); if (rhp) rcu_segcblist_enqueue(&sdp->srcu_cblist, rhp); rcu_segcblist_advance(&sdp->srcu_cblist, @@ -834,10 +1067,17 @@ static unsigned long srcu_gp_start_if_needed(struct srcu_struct *ssp, needexp = true; } spin_unlock_irqrestore_rcu_node(sdp, flags); + + /* Ensure that snp node tree is fully initialized before traversing it */ + if (ss_state < SRCU_SIZE_WAIT_BARRIER) + sdp_mynode = NULL; + else + sdp_mynode = sdp->mynode; + if (needgp) srcu_funnel_gp_start(ssp, sdp, s, do_norm); else if (needexp) - srcu_funnel_exp_start(ssp, sdp->mynode, s); + srcu_funnel_exp_start(ssp, sdp_mynode, s); srcu_read_unlock(ssp, idx); return s; } @@ -1097,6 +1337,28 @@ static void srcu_barrier_cb(struct rcu_head *rhp) complete(&ssp->srcu_barrier_completion); } +/* + * Enqueue an srcu_barrier() callback on the specified srcu_data + * structure's ->cblist. but only if that ->cblist already has at least one + * callback enqueued. Note that if a CPU already has callbacks enqueue, + * it must have already registered the need for a future grace period, + * so all we need do is enqueue a callback that will use the same grace + * period as the last callback already in the queue. + */ +static void srcu_barrier_one_cpu(struct srcu_struct *ssp, struct srcu_data *sdp) +{ + spin_lock_irq_rcu_node(sdp); + atomic_inc(&ssp->srcu_barrier_cpu_cnt); + sdp->srcu_barrier_head.func = srcu_barrier_cb; + debug_rcu_head_queue(&sdp->srcu_barrier_head); + if (!rcu_segcblist_entrain(&sdp->srcu_cblist, + &sdp->srcu_barrier_head)) { + debug_rcu_head_unqueue(&sdp->srcu_barrier_head); + atomic_dec(&ssp->srcu_barrier_cpu_cnt); + } + spin_unlock_irq_rcu_node(sdp); +} + /** * srcu_barrier - Wait until all in-flight call_srcu() callbacks complete. * @ssp: srcu_struct on which to wait for in-flight callbacks. @@ -1104,7 +1366,7 @@ static void srcu_barrier_cb(struct rcu_head *rhp) void srcu_barrier(struct srcu_struct *ssp) { int cpu; - struct srcu_data *sdp; + int idx; unsigned long s = rcu_seq_snap(&ssp->srcu_barrier_seq); check_init_srcu_struct(ssp); @@ -1120,27 +1382,13 @@ void srcu_barrier(struct srcu_struct *ssp) /* Initial count prevents reaching zero until all CBs are posted. */ atomic_set(&ssp->srcu_barrier_cpu_cnt, 1); - /* - * Each pass through this loop enqueues a callback, but only - * on CPUs already having callbacks enqueued. Note that if - * a CPU already has callbacks enqueue, it must have already - * registered the need for a future grace period, so all we - * need do is enqueue a callback that will use the same - * grace period as the last callback already in the queue. - */ - for_each_possible_cpu(cpu) { - sdp = per_cpu_ptr(ssp->sda, cpu); - spin_lock_irq_rcu_node(sdp); - atomic_inc(&ssp->srcu_barrier_cpu_cnt); - sdp->srcu_barrier_head.func = srcu_barrier_cb; - debug_rcu_head_queue(&sdp->srcu_barrier_head); - if (!rcu_segcblist_entrain(&sdp->srcu_cblist, - &sdp->srcu_barrier_head)) { - debug_rcu_head_unqueue(&sdp->srcu_barrier_head); - atomic_dec(&ssp->srcu_barrier_cpu_cnt); - } - spin_unlock_irq_rcu_node(sdp); - } + idx = srcu_read_lock(ssp); + if (smp_load_acquire(&ssp->srcu_size_state) < SRCU_SIZE_WAIT_BARRIER) + srcu_barrier_one_cpu(ssp, per_cpu_ptr(ssp->sda, 0)); + else + for_each_possible_cpu(cpu) + srcu_barrier_one_cpu(ssp, per_cpu_ptr(ssp->sda, cpu)); + srcu_read_unlock(ssp, idx); /* Remove the initial count, at which point reaching zero can happen. */ if (atomic_dec_and_test(&ssp->srcu_barrier_cpu_cnt)) @@ -1214,6 +1462,7 @@ static void srcu_advance_state(struct srcu_struct *ssp) srcu_flip(ssp); spin_lock_irq_rcu_node(ssp); rcu_seq_set_state(&ssp->srcu_gp_seq, SRCU_STATE_SCAN2); + ssp->srcu_n_exp_nodelay = 0; spin_unlock_irq_rcu_node(ssp); } @@ -1228,6 +1477,7 @@ static void srcu_advance_state(struct srcu_struct *ssp) mutex_unlock(&ssp->srcu_gp_mutex); return; /* readers present, retry later. */ } + ssp->srcu_n_exp_nodelay = 0; srcu_gp_end(ssp); /* Releases ->srcu_gp_mutex. */ } } @@ -1318,12 +1568,28 @@ static void srcu_reschedule(struct srcu_struct *ssp, unsigned long delay) */ static void process_srcu(struct work_struct *work) { + unsigned long curdelay; + unsigned long j; struct srcu_struct *ssp; ssp = container_of(work, struct srcu_struct, work.work); srcu_advance_state(ssp); - srcu_reschedule(ssp, srcu_get_delay(ssp)); + curdelay = srcu_get_delay(ssp); + if (curdelay) { + WRITE_ONCE(ssp->reschedule_count, 0); + } else { + j = jiffies; + if (READ_ONCE(ssp->reschedule_jiffies) == j) { + WRITE_ONCE(ssp->reschedule_count, READ_ONCE(ssp->reschedule_count) + 1); + if (READ_ONCE(ssp->reschedule_count) > SRCU_MAX_NODELAY) + curdelay = 1; + } else { + WRITE_ONCE(ssp->reschedule_count, 1); + WRITE_ONCE(ssp->reschedule_jiffies, j); + } + } + srcu_reschedule(ssp, curdelay); } void srcutorture_get_gp_data(enum rcutorture_type test_type, @@ -1337,43 +1603,69 @@ void srcutorture_get_gp_data(enum rcutorture_type test_type, } EXPORT_SYMBOL_GPL(srcutorture_get_gp_data); +static const char * const srcu_size_state_name[] = { + "SRCU_SIZE_SMALL", + "SRCU_SIZE_ALLOC", + "SRCU_SIZE_WAIT_BARRIER", + "SRCU_SIZE_WAIT_CALL", + "SRCU_SIZE_WAIT_CBS1", + "SRCU_SIZE_WAIT_CBS2", + "SRCU_SIZE_WAIT_CBS3", + "SRCU_SIZE_WAIT_CBS4", + "SRCU_SIZE_BIG", + "SRCU_SIZE_???", +}; + void srcu_torture_stats_print(struct srcu_struct *ssp, char *tt, char *tf) { int cpu; int idx; unsigned long s0 = 0, s1 = 0; + int ss_state = READ_ONCE(ssp->srcu_size_state); + int ss_state_idx = ss_state; idx = ssp->srcu_idx & 0x1; - pr_alert("%s%s Tree SRCU g%ld per-CPU(idx=%d):", - tt, tf, rcu_seq_current(&ssp->srcu_gp_seq), idx); - for_each_possible_cpu(cpu) { - unsigned long l0, l1; - unsigned long u0, u1; - long c0, c1; - struct srcu_data *sdp; - - sdp = per_cpu_ptr(ssp->sda, cpu); - u0 = data_race(sdp->srcu_unlock_count[!idx]); - u1 = data_race(sdp->srcu_unlock_count[idx]); - - /* - * Make sure that a lock is always counted if the corresponding - * unlock is counted. - */ - smp_rmb(); - - l0 = data_race(sdp->srcu_lock_count[!idx]); - l1 = data_race(sdp->srcu_lock_count[idx]); - - c0 = l0 - u0; - c1 = l1 - u1; - pr_cont(" %d(%ld,%ld %c)", - cpu, c0, c1, - "C."[rcu_segcblist_empty(&sdp->srcu_cblist)]); - s0 += c0; - s1 += c1; + if (ss_state < 0 || ss_state >= ARRAY_SIZE(srcu_size_state_name)) + ss_state_idx = ARRAY_SIZE(srcu_size_state_name) - 1; + pr_alert("%s%s Tree SRCU g%ld state %d (%s)", + tt, tf, rcu_seq_current(&ssp->srcu_gp_seq), ss_state, + srcu_size_state_name[ss_state_idx]); + if (!ssp->sda) { + // Called after cleanup_srcu_struct(), perhaps. + pr_cont(" No per-CPU srcu_data structures (->sda == NULL).\n"); + } else { + pr_cont(" per-CPU(idx=%d):", idx); + for_each_possible_cpu(cpu) { + unsigned long l0, l1; + unsigned long u0, u1; + long c0, c1; + struct srcu_data *sdp; + + sdp = per_cpu_ptr(ssp->sda, cpu); + u0 = data_race(sdp->srcu_unlock_count[!idx]); + u1 = data_race(sdp->srcu_unlock_count[idx]); + + /* + * Make sure that a lock is always counted if the corresponding + * unlock is counted. + */ + smp_rmb(); + + l0 = data_race(sdp->srcu_lock_count[!idx]); + l1 = data_race(sdp->srcu_lock_count[idx]); + + c0 = l0 - u0; + c1 = l1 - u1; + pr_cont(" %d(%ld,%ld %c)", + cpu, c0, c1, + "C."[rcu_segcblist_empty(&sdp->srcu_cblist)]); + s0 += c0; + s1 += c1; + } + pr_cont(" T(%ld,%ld)\n", s0, s1); } - pr_cont(" T(%ld,%ld)\n", s0, s1); + if (SRCU_SIZING_IS_TORTURE()) + srcu_transition_to_big(ssp); } EXPORT_SYMBOL_GPL(srcu_torture_stats_print); @@ -1390,6 +1682,17 @@ void __init srcu_init(void) { struct srcu_struct *ssp; + /* Decide on srcu_struct-size strategy. */ + if (SRCU_SIZING_IS(SRCU_SIZING_AUTO)) { + if (nr_cpu_ids >= big_cpu_lim) { + convert_to_big = SRCU_SIZING_INIT; // Don't bother waiting for contention. + pr_info("%s: Setting srcu_struct sizes to big.\n", __func__); + } else { + convert_to_big = SRCU_SIZING_NONE | SRCU_SIZING_CONTEND; + pr_info("%s: Setting srcu_struct sizes based on contention.\n", __func__); + } + } + /* * Once that is set, call_srcu() can follow the normal path and * queue delayed work. This must follow RCU workqueues creation @@ -1400,6 +1703,8 @@ void __init srcu_init(void) ssp = list_first_entry(&srcu_boot_list, struct srcu_struct, work.work.entry); list_del_init(&ssp->work.work.entry); + if (SRCU_SIZING_IS(SRCU_SIZING_INIT) && ssp->srcu_size_state == SRCU_SIZE_SMALL) + ssp->srcu_size_state = SRCU_SIZE_ALLOC; queue_work(rcu_gp_wq, &ssp->work.work); } } diff --git a/kernel/rcu/sync.c b/kernel/rcu/sync.c index 33d896d85902..5cefc702158f 100644 --- a/kernel/rcu/sync.c +++ b/kernel/rcu/sync.c @@ -111,7 +111,7 @@ static void rcu_sync_func(struct rcu_head *rhp) * a slowpath during the update. After this function returns, all * subsequent calls to rcu_sync_is_idle() will return false, which * tells readers to stay off their fastpaths. A later call to - * rcu_sync_exit() re-enables reader slowpaths. + * rcu_sync_exit() re-enables reader fastpaths. * * When called in isolation, rcu_sync_enter() must wait for a grace * period, however, closely spaced calls to rcu_sync_enter() can diff --git a/kernel/rcu/tasks.h b/kernel/rcu/tasks.h index 99cf3a13954c..3925e32159b5 100644 --- a/kernel/rcu/tasks.h +++ b/kernel/rcu/tasks.h @@ -46,7 +46,7 @@ struct rcu_tasks_percpu { /** * struct rcu_tasks - Definition for a Tasks-RCU-like mechanism. - * @cbs_wq: Wait queue allowing new callback to get kthread's attention. + * @cbs_wait: RCU wait allowing a new callback to get kthread's attention. * @cbs_gbl_lock: Lock protecting callback list. * @kthread_ptr: This flavor's grace-period/callback-invocation kthread. * @gp_func: This flavor's grace-period-wait function. @@ -77,7 +77,7 @@ struct rcu_tasks_percpu { * @kname: This flavor's kthread name. */ struct rcu_tasks { - struct wait_queue_head cbs_wq; + struct rcuwait cbs_wait; raw_spinlock_t cbs_gbl_lock; int gp_state; int gp_sleep; @@ -113,11 +113,11 @@ static void call_rcu_tasks_iw_wakeup(struct irq_work *iwp); #define DEFINE_RCU_TASKS(rt_name, gp, call, n) \ static DEFINE_PER_CPU(struct rcu_tasks_percpu, rt_name ## __percpu) = { \ .lock = __RAW_SPIN_LOCK_UNLOCKED(rt_name ## __percpu.cbs_pcpu_lock), \ - .rtp_irq_work = IRQ_WORK_INIT(call_rcu_tasks_iw_wakeup), \ + .rtp_irq_work = IRQ_WORK_INIT_HARD(call_rcu_tasks_iw_wakeup), \ }; \ static struct rcu_tasks rt_name = \ { \ - .cbs_wq = __WAIT_QUEUE_HEAD_INITIALIZER(rt_name.cbs_wq), \ + .cbs_wait = __RCUWAIT_INITIALIZER(rt_name.wait), \ .cbs_gbl_lock = __RAW_SPIN_LOCK_UNLOCKED(rt_name.cbs_gbl_lock), \ .gp_func = gp, \ .call_func = call, \ @@ -143,6 +143,11 @@ module_param(rcu_task_ipi_delay, int, 0644); #define RCU_TASK_STALL_TIMEOUT (HZ * 60 * 10) static int rcu_task_stall_timeout __read_mostly = RCU_TASK_STALL_TIMEOUT; module_param(rcu_task_stall_timeout, int, 0644); +#define RCU_TASK_STALL_INFO (HZ * 10) +static int rcu_task_stall_info __read_mostly = RCU_TASK_STALL_INFO; +module_param(rcu_task_stall_info, int, 0644); +static int rcu_task_stall_info_mult __read_mostly = 3; +module_param(rcu_task_stall_info_mult, int, 0444); static int rcu_task_enqueue_lim __read_mostly = -1; module_param(rcu_task_enqueue_lim, int, 0444); @@ -261,14 +266,16 @@ static void call_rcu_tasks_iw_wakeup(struct irq_work *iwp) struct rcu_tasks_percpu *rtpcp = container_of(iwp, struct rcu_tasks_percpu, rtp_irq_work); rtp = rtpcp->rtpp; - wake_up(&rtp->cbs_wq); + rcuwait_wake_up(&rtp->cbs_wait); } // Enqueue a callback for the specified flavor of Tasks RCU. static void call_rcu_tasks_generic(struct rcu_head *rhp, rcu_callback_t func, struct rcu_tasks *rtp) { + int chosen_cpu; unsigned long flags; + int ideal_cpu; unsigned long j; bool needadjust = false; bool needwake; @@ -278,8 +285,9 @@ static void call_rcu_tasks_generic(struct rcu_head *rhp, rcu_callback_t func, rhp->func = func; local_irq_save(flags); rcu_read_lock(); - rtpcp = per_cpu_ptr(rtp->rtpcpu, - smp_processor_id() >> READ_ONCE(rtp->percpu_enqueue_shift)); + ideal_cpu = smp_processor_id() >> READ_ONCE(rtp->percpu_enqueue_shift); + chosen_cpu = cpumask_next(ideal_cpu - 1, cpu_possible_mask); + rtpcp = per_cpu_ptr(rtp->rtpcpu, chosen_cpu); if (!raw_spin_trylock_rcu_node(rtpcp)) { // irqs already disabled. raw_spin_lock_rcu_node(rtpcp); // irqs already disabled. j = jiffies; @@ -460,7 +468,7 @@ static void rcu_tasks_invoke_cbs(struct rcu_tasks *rtp, struct rcu_tasks_percpu } } - if (rcu_segcblist_empty(&rtpcp->cblist)) + if (rcu_segcblist_empty(&rtpcp->cblist) || !cpu_possible(cpu)) return; raw_spin_lock_irqsave_rcu_node(rtpcp, flags); rcu_segcblist_advance(&rtpcp->cblist, rcu_seq_current(&rtp->tasks_gp_seq)); @@ -509,7 +517,9 @@ static int __noreturn rcu_tasks_kthread(void *arg) set_tasks_gp_state(rtp, RTGS_WAIT_CBS); /* If there were none, wait a bit and start over. */ - wait_event_idle(rtp->cbs_wq, (needgpcb = rcu_tasks_need_gpcb(rtp))); + rcuwait_wait_event(&rtp->cbs_wait, + (needgpcb = rcu_tasks_need_gpcb(rtp)), + TASK_IDLE); if (needgpcb & 0x2) { // Wait for one grace period. @@ -548,8 +558,15 @@ static void __init rcu_spawn_tasks_kthread_generic(struct rcu_tasks *rtp) static void __init rcu_tasks_bootup_oddness(void) { #if defined(CONFIG_TASKS_RCU) || defined(CONFIG_TASKS_TRACE_RCU) + int rtsimc; + if (rcu_task_stall_timeout != RCU_TASK_STALL_TIMEOUT) pr_info("\tTasks-RCU CPU stall warnings timeout set to %d (rcu_task_stall_timeout).\n", rcu_task_stall_timeout); + rtsimc = clamp(rcu_task_stall_info_mult, 1, 10); + if (rtsimc != rcu_task_stall_info_mult) { + pr_info("\tTasks-RCU CPU stall info multiplier clamped to %d (rcu_task_stall_info_mult).\n", rtsimc); + rcu_task_stall_info_mult = rtsimc; + } #endif /* #ifdef CONFIG_TASKS_RCU */ #ifdef CONFIG_TASKS_RCU pr_info("\tTrampoline variant of Tasks RCU enabled.\n"); @@ -568,7 +585,17 @@ static void __init rcu_tasks_bootup_oddness(void) /* Dump out rcutorture-relevant state common to all RCU-tasks flavors. */ static void show_rcu_tasks_generic_gp_kthread(struct rcu_tasks *rtp, char *s) { - struct rcu_tasks_percpu *rtpcp = per_cpu_ptr(rtp->rtpcpu, 0); // for_each... + int cpu; + bool havecbs = false; + + for_each_possible_cpu(cpu) { + struct rcu_tasks_percpu *rtpcp = per_cpu_ptr(rtp->rtpcpu, cpu); + + if (!data_race(rcu_segcblist_empty(&rtpcp->cblist))) { + havecbs = true; + break; + } + } pr_info("%s: %s(%d) since %lu g:%lu i:%lu/%lu %c%c %s\n", rtp->kname, tasks_gp_state_getname(rtp), data_race(rtp->gp_state), @@ -576,7 +603,7 @@ static void show_rcu_tasks_generic_gp_kthread(struct rcu_tasks *rtp, char *s) data_race(rcu_seq_current(&rtp->tasks_gp_seq)), data_race(rtp->n_ipis_fails), data_race(rtp->n_ipis), ".k"[!!data_race(rtp->kthread_ptr)], - ".C"[!data_race(rcu_segcblist_empty(&rtpcp->cblist))], + ".C"[havecbs], s); } #endif // #ifndef CONFIG_TINY_RCU @@ -592,10 +619,15 @@ static void exit_tasks_rcu_finish_trace(struct task_struct *t); /* Wait for one RCU-tasks grace period. */ static void rcu_tasks_wait_gp(struct rcu_tasks *rtp) { - struct task_struct *g, *t; - unsigned long lastreport; - LIST_HEAD(holdouts); + struct task_struct *g; int fract; + LIST_HEAD(holdouts); + unsigned long j; + unsigned long lastinfo; + unsigned long lastreport; + bool reported = false; + int rtsi; + struct task_struct *t; set_tasks_gp_state(rtp, RTGS_PRE_WAIT_GP); rtp->pregp_func(); @@ -621,30 +653,50 @@ static void rcu_tasks_wait_gp(struct rcu_tasks *rtp) * is empty, we are done. */ lastreport = jiffies; + lastinfo = lastreport; + rtsi = READ_ONCE(rcu_task_stall_info); // Start off with initial wait and slowly back off to 1 HZ wait. fract = rtp->init_fract; while (!list_empty(&holdouts)) { + ktime_t exp; bool firstreport; bool needreport; int rtst; - /* Slowly back off waiting for holdouts */ + // Slowly back off waiting for holdouts set_tasks_gp_state(rtp, RTGS_WAIT_SCAN_HOLDOUTS); - schedule_timeout_idle(fract); + if (!IS_ENABLED(CONFIG_PREEMPT_RT)) { + schedule_timeout_idle(fract); + } else { + exp = jiffies_to_nsecs(fract); + __set_current_state(TASK_IDLE); + schedule_hrtimeout_range(&exp, jiffies_to_nsecs(HZ / 2), HRTIMER_MODE_REL_HARD); + } if (fract < HZ) fract++; rtst = READ_ONCE(rcu_task_stall_timeout); needreport = rtst > 0 && time_after(jiffies, lastreport + rtst); - if (needreport) + if (needreport) { lastreport = jiffies; + reported = true; + } firstreport = true; WARN_ON(signal_pending(current)); set_tasks_gp_state(rtp, RTGS_SCAN_HOLDOUTS); rtp->holdouts_func(&holdouts, needreport, &firstreport); + + // Print pre-stall informational messages if needed. + j = jiffies; + if (rtsi > 0 && !reported && time_after(j, lastinfo + rtsi)) { + lastinfo = j; + rtsi = rtsi * rcu_task_stall_info_mult; + pr_info("%s: %s grace period %lu is %lu jiffies old.\n", + __func__, rtp->kname, rtp->tasks_gp_seq, j - rtp->gp_start); + } } set_tasks_gp_state(rtp, RTGS_POST_GP); @@ -950,6 +1002,9 @@ static void rcu_tasks_be_rude(struct work_struct *work) // Wait for one rude RCU-tasks grace period. static void rcu_tasks_rude_wait_gp(struct rcu_tasks *rtp) { + if (num_online_cpus() <= 1) + return; // Fastpath for only one CPU. + rtp->n_ipis += cpumask_weight(cpu_online_mask); schedule_on_each_cpu(rcu_tasks_be_rude); } diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c index a4b8189455d5..c25ba442044a 100644 --- a/kernel/rcu/tree.c +++ b/kernel/rcu/tree.c @@ -1679,6 +1679,8 @@ static bool __note_gp_changes(struct rcu_node *rnp, struct rcu_data *rdp) rdp->gp_seq = rnp->gp_seq; /* Remember new grace-period state. */ if (ULONG_CMP_LT(rdp->gp_seq_needed, rnp->gp_seq_needed) || rdp->gpwrap) WRITE_ONCE(rdp->gp_seq_needed, rnp->gp_seq_needed); + if (IS_ENABLED(CONFIG_PROVE_RCU) && READ_ONCE(rdp->gpwrap)) + WRITE_ONCE(rdp->last_sched_clock, jiffies); WRITE_ONCE(rdp->gpwrap, false); rcu_gpnum_ovf(rnp, rdp); return ret; @@ -1705,11 +1707,37 @@ static void note_gp_changes(struct rcu_data *rdp) rcu_gp_kthread_wake(); } +static atomic_t *rcu_gp_slow_suppress; + +/* Register a counter to suppress debugging grace-period delays. */ +void rcu_gp_slow_register(atomic_t *rgssp) +{ + WARN_ON_ONCE(rcu_gp_slow_suppress); + + WRITE_ONCE(rcu_gp_slow_suppress, rgssp); +} +EXPORT_SYMBOL_GPL(rcu_gp_slow_register); + +/* Unregister a counter, with NULL for not caring which. */ +void rcu_gp_slow_unregister(atomic_t *rgssp) +{ + WARN_ON_ONCE(rgssp && rgssp != rcu_gp_slow_suppress); + + WRITE_ONCE(rcu_gp_slow_suppress, NULL); +} +EXPORT_SYMBOL_GPL(rcu_gp_slow_unregister); + +static bool rcu_gp_slow_is_suppressed(void) +{ + atomic_t *rgssp = READ_ONCE(rcu_gp_slow_suppress); + + return rgssp && atomic_read(rgssp); +} + static void rcu_gp_slow(int delay) { - if (delay > 0 && - !(rcu_seq_ctr(rcu_state.gp_seq) % - (rcu_num_nodes * PER_RCU_NODE_PERIOD * delay))) + if (!rcu_gp_slow_is_suppressed() && delay > 0 && + !(rcu_seq_ctr(rcu_state.gp_seq) % (rcu_num_nodes * PER_RCU_NODE_PERIOD * delay))) schedule_timeout_idle(delay); } @@ -2096,14 +2124,29 @@ static noinline void rcu_gp_cleanup(void) /* Advance CBs to reduce false positives below. */ offloaded = rcu_rdp_is_offloaded(rdp); if ((offloaded || !rcu_accelerate_cbs(rnp, rdp)) && needgp) { + + // We get here if a grace period was needed (“needgp”) + // and the above call to rcu_accelerate_cbs() did not set + // the RCU_GP_FLAG_INIT bit in ->gp_state (which records + // the need for another grace period). The purpose + // of the “offloaded” check is to avoid invoking + // rcu_accelerate_cbs() on an offloaded CPU because we do not + // hold the ->nocb_lock needed to safely access an offloaded + // ->cblist. We do not want to acquire that lock because + // it can be heavily contended during callback floods. + WRITE_ONCE(rcu_state.gp_flags, RCU_GP_FLAG_INIT); WRITE_ONCE(rcu_state.gp_req_activity, jiffies); - trace_rcu_grace_period(rcu_state.name, - rcu_state.gp_seq, - TPS("newreq")); + trace_rcu_grace_period(rcu_state.name, rcu_state.gp_seq, TPS("newreq")); } else { - WRITE_ONCE(rcu_state.gp_flags, - rcu_state.gp_flags & RCU_GP_FLAG_INIT); + + // We get here either if there is no need for an + // additional grace period or if rcu_accelerate_cbs() has + // already set the RCU_GP_FLAG_INIT bit in ->gp_flags. + // So all we need to do is to clear all of the other + // ->gp_flags bits. + + WRITE_ONCE(rcu_state.gp_flags, rcu_state.gp_flags & RCU_GP_FLAG_INIT); } raw_spin_unlock_irq_rcu_node(rnp); @@ -2609,6 +2652,13 @@ static void rcu_do_batch(struct rcu_data *rdp) */ void rcu_sched_clock_irq(int user) { + unsigned long j; + + if (IS_ENABLED(CONFIG_PROVE_RCU)) { + j = jiffies; + WARN_ON_ONCE(time_before(j, __this_cpu_read(rcu_data.last_sched_clock))); + __this_cpu_write(rcu_data.last_sched_clock, j); + } trace_rcu_utilization(TPS("Start scheduler-tick")); lockdep_assert_irqs_disabled(); raw_cpu_inc(rcu_data.ticks_this_gp); @@ -2624,6 +2674,8 @@ void rcu_sched_clock_irq(int user) rcu_flavor_sched_clock_irq(user); if (rcu_pending(user)) invoke_rcu_core(); + if (user) + rcu_tasks_classic_qs(current, false); lockdep_assert_irqs_disabled(); trace_rcu_utilization(TPS("End scheduler-tick")); @@ -3717,7 +3769,9 @@ static int rcu_blocking_is_gp(void) { int ret; - if (IS_ENABLED(CONFIG_PREEMPTION)) + // Invoking preempt_model_*() too early gets a splat. + if (rcu_scheduler_active == RCU_SCHEDULER_INACTIVE || + preempt_model_full() || preempt_model_rt()) return rcu_scheduler_active == RCU_SCHEDULER_INACTIVE; might_sleep(); /* Check for RCU read-side critical section. */ preempt_disable(); @@ -4179,6 +4233,7 @@ rcu_boot_init_percpu_data(int cpu) rdp->rcu_ofl_gp_flags = RCU_GP_CLEANED; rdp->rcu_onl_gp_seq = rcu_state.gp_seq; rdp->rcu_onl_gp_flags = RCU_GP_CLEANED; + rdp->last_sched_clock = jiffies; rdp->cpu = cpu; rcu_boot_init_nocb_percpu_data(rdp); } @@ -4471,6 +4526,51 @@ static int rcu_pm_notify(struct notifier_block *self, return NOTIFY_OK; } +#ifdef CONFIG_RCU_EXP_KTHREAD +struct kthread_worker *rcu_exp_gp_kworker; +struct kthread_worker *rcu_exp_par_gp_kworker; + +static void __init rcu_start_exp_gp_kworkers(void) +{ + const char *par_gp_kworker_name = "rcu_exp_par_gp_kthread_worker"; + const char *gp_kworker_name = "rcu_exp_gp_kthread_worker"; + struct sched_param param = { .sched_priority = kthread_prio }; + + rcu_exp_gp_kworker = kthread_create_worker(0, gp_kworker_name); + if (IS_ERR_OR_NULL(rcu_exp_gp_kworker)) { + pr_err("Failed to create %s!\n", gp_kworker_name); + return; + } + + rcu_exp_par_gp_kworker = kthread_create_worker(0, par_gp_kworker_name); + if (IS_ERR_OR_NULL(rcu_exp_par_gp_kworker)) { + pr_err("Failed to create %s!\n", par_gp_kworker_name); + kthread_destroy_worker(rcu_exp_gp_kworker); + return; + } + + sched_setscheduler_nocheck(rcu_exp_gp_kworker->task, SCHED_FIFO, ¶m); + sched_setscheduler_nocheck(rcu_exp_par_gp_kworker->task, SCHED_FIFO, + ¶m); +} + +static inline void rcu_alloc_par_gp_wq(void) +{ +} +#else /* !CONFIG_RCU_EXP_KTHREAD */ +struct workqueue_struct *rcu_par_gp_wq; + +static void __init rcu_start_exp_gp_kworkers(void) +{ +} + +static inline void rcu_alloc_par_gp_wq(void) +{ + rcu_par_gp_wq = alloc_workqueue("rcu_par_gp", WQ_MEM_RECLAIM, 0); + WARN_ON(!rcu_par_gp_wq); +} +#endif /* CONFIG_RCU_EXP_KTHREAD */ + /* * Spawn the kthreads that handle RCU's grace periods. */ @@ -4480,6 +4580,7 @@ static int __init rcu_spawn_gp_kthread(void) struct rcu_node *rnp; struct sched_param sp; struct task_struct *t; + struct rcu_data *rdp = this_cpu_ptr(&rcu_data); rcu_scheduler_fully_active = 1; t = kthread_create(rcu_gp_kthread, NULL, "%s", rcu_state.name); @@ -4497,9 +4598,17 @@ static int __init rcu_spawn_gp_kthread(void) smp_store_release(&rcu_state.gp_kthread, t); /* ^^^ */ raw_spin_unlock_irqrestore_rcu_node(rnp, flags); wake_up_process(t); - rcu_spawn_nocb_kthreads(); - rcu_spawn_boost_kthreads(); + /* This is a pre-SMP initcall, we expect a single CPU */ + WARN_ON(num_online_cpus() > 1); + /* + * Those kthreads couldn't be created on rcu_init() -> rcutree_prepare_cpu() + * due to rcu_scheduler_fully_active. + */ + rcu_spawn_cpu_nocb_kthread(smp_processor_id()); + rcu_spawn_one_boost_kthread(rdp->mynode); rcu_spawn_core_kthreads(); + /* Create kthread worker for expedited GPs */ + rcu_start_exp_gp_kworkers(); return 0; } early_initcall(rcu_spawn_gp_kthread); @@ -4745,7 +4854,6 @@ static void __init rcu_dump_rcu_node_tree(void) } struct workqueue_struct *rcu_gp_wq; -struct workqueue_struct *rcu_par_gp_wq; static void __init kfree_rcu_batch_init(void) { @@ -4782,7 +4890,7 @@ static void __init kfree_rcu_batch_init(void) void __init rcu_init(void) { - int cpu; + int cpu = smp_processor_id(); rcu_early_boot_tests(); @@ -4802,17 +4910,15 @@ void __init rcu_init(void) * or the scheduler are operational. */ pm_notifier(rcu_pm_notify, 0); - for_each_online_cpu(cpu) { - rcutree_prepare_cpu(cpu); - rcu_cpu_starting(cpu); - rcutree_online_cpu(cpu); - } + WARN_ON(num_online_cpus() > 1); // Only one CPU this early in boot. + rcutree_prepare_cpu(cpu); + rcu_cpu_starting(cpu); + rcutree_online_cpu(cpu); /* Create workqueue for Tree SRCU and for expedited GPs. */ rcu_gp_wq = alloc_workqueue("rcu_gp", WQ_MEM_RECLAIM, 0); WARN_ON(!rcu_gp_wq); - rcu_par_gp_wq = alloc_workqueue("rcu_par_gp", WQ_MEM_RECLAIM, 0); - WARN_ON(!rcu_par_gp_wq); + rcu_alloc_par_gp_wq(); /* Fill in default value for rcutree.qovld boot parameter. */ /* -After- the rcu_node ->lock fields are initialized! */ diff --git a/kernel/rcu/tree.h b/kernel/rcu/tree.h index 926673ebe355..2ccf5845957d 100644 --- a/kernel/rcu/tree.h +++ b/kernel/rcu/tree.h @@ -10,6 +10,7 @@ */ #include <linux/cache.h> +#include <linux/kthread.h> #include <linux/spinlock.h> #include <linux/rtmutex.h> #include <linux/threads.h> @@ -23,7 +24,11 @@ /* Communicate arguments to a workqueue handler. */ struct rcu_exp_work { unsigned long rew_s; +#ifdef CONFIG_RCU_EXP_KTHREAD + struct kthread_work rew_work; +#else struct work_struct rew_work; +#endif /* CONFIG_RCU_EXP_KTHREAD */ }; /* RCU's kthread states for tracing. */ @@ -254,6 +259,7 @@ struct rcu_data { unsigned long rcu_onl_gp_seq; /* ->gp_seq at last online. */ short rcu_onl_gp_flags; /* ->gp_flags at last online. */ unsigned long last_fqs_resched; /* Time of last rcu_resched(). */ + unsigned long last_sched_clock; /* Jiffies of last rcu_sched_clock_irq(). */ int cpu; }; @@ -364,6 +370,7 @@ struct rcu_state { arch_spinlock_t ofl_lock ____cacheline_internodealigned_in_smp; /* Synchronize offline with */ /* GP pre-initialization. */ + int nocb_is_setup; /* nocb is setup from boot */ }; /* Values for rcu_state structure's gp_flags field. */ @@ -421,7 +428,6 @@ static void rcu_preempt_boost_start_gp(struct rcu_node *rnp); static bool rcu_is_callbacks_kthread(void); static void rcu_cpu_kthread_setup(unsigned int cpu); static void rcu_spawn_one_boost_kthread(struct rcu_node *rnp); -static void __init rcu_spawn_boost_kthreads(void); static bool rcu_preempt_has_tasks(struct rcu_node *rnp); static bool rcu_preempt_need_deferred_qs(struct task_struct *t); static void rcu_preempt_deferred_qs(struct task_struct *t); @@ -439,7 +445,6 @@ static int rcu_nocb_need_deferred_wakeup(struct rcu_data *rdp, int level); static bool do_nocb_deferred_wakeup(struct rcu_data *rdp); static void rcu_boot_init_nocb_percpu_data(struct rcu_data *rdp); static void rcu_spawn_cpu_nocb_kthread(int cpu); -static void __init rcu_spawn_nocb_kthreads(void); static void show_rcu_nocb_state(struct rcu_data *rdp); static void rcu_nocb_lock(struct rcu_data *rdp); static void rcu_nocb_unlock(struct rcu_data *rdp); diff --git a/kernel/rcu/tree_exp.h b/kernel/rcu/tree_exp.h index 60197ea24ceb..0f70f62039a9 100644 --- a/kernel/rcu/tree_exp.h +++ b/kernel/rcu/tree_exp.h @@ -334,15 +334,13 @@ fastpath: * Select the CPUs within the specified rcu_node that the upcoming * expedited grace period needs to wait for. */ -static void sync_rcu_exp_select_node_cpus(struct work_struct *wp) +static void __sync_rcu_exp_select_node_cpus(struct rcu_exp_work *rewp) { int cpu; unsigned long flags; unsigned long mask_ofl_test; unsigned long mask_ofl_ipi; int ret; - struct rcu_exp_work *rewp = - container_of(wp, struct rcu_exp_work, rew_work); struct rcu_node *rnp = container_of(rewp, struct rcu_node, rew); raw_spin_lock_irqsave_rcu_node(rnp, flags); @@ -417,13 +415,119 @@ retry_ipi: rcu_report_exp_cpu_mult(rnp, mask_ofl_test, false); } +static void rcu_exp_sel_wait_wake(unsigned long s); + +#ifdef CONFIG_RCU_EXP_KTHREAD +static void sync_rcu_exp_select_node_cpus(struct kthread_work *wp) +{ + struct rcu_exp_work *rewp = + container_of(wp, struct rcu_exp_work, rew_work); + + __sync_rcu_exp_select_node_cpus(rewp); +} + +static inline bool rcu_gp_par_worker_started(void) +{ + return !!READ_ONCE(rcu_exp_par_gp_kworker); +} + +static inline void sync_rcu_exp_select_cpus_queue_work(struct rcu_node *rnp) +{ + kthread_init_work(&rnp->rew.rew_work, sync_rcu_exp_select_node_cpus); + /* + * Use rcu_exp_par_gp_kworker, because flushing a work item from + * another work item on the same kthread worker can result in + * deadlock. + */ + kthread_queue_work(rcu_exp_par_gp_kworker, &rnp->rew.rew_work); +} + +static inline void sync_rcu_exp_select_cpus_flush_work(struct rcu_node *rnp) +{ + kthread_flush_work(&rnp->rew.rew_work); +} + +/* + * Work-queue handler to drive an expedited grace period forward. + */ +static void wait_rcu_exp_gp(struct kthread_work *wp) +{ + struct rcu_exp_work *rewp; + + rewp = container_of(wp, struct rcu_exp_work, rew_work); + rcu_exp_sel_wait_wake(rewp->rew_s); +} + +static inline void synchronize_rcu_expedited_queue_work(struct rcu_exp_work *rew) +{ + kthread_init_work(&rew->rew_work, wait_rcu_exp_gp); + kthread_queue_work(rcu_exp_gp_kworker, &rew->rew_work); +} + +static inline void synchronize_rcu_expedited_destroy_work(struct rcu_exp_work *rew) +{ +} +#else /* !CONFIG_RCU_EXP_KTHREAD */ +static void sync_rcu_exp_select_node_cpus(struct work_struct *wp) +{ + struct rcu_exp_work *rewp = + container_of(wp, struct rcu_exp_work, rew_work); + + __sync_rcu_exp_select_node_cpus(rewp); +} + +static inline bool rcu_gp_par_worker_started(void) +{ + return !!READ_ONCE(rcu_par_gp_wq); +} + +static inline void sync_rcu_exp_select_cpus_queue_work(struct rcu_node *rnp) +{ + int cpu = find_next_bit(&rnp->ffmask, BITS_PER_LONG, -1); + + INIT_WORK(&rnp->rew.rew_work, sync_rcu_exp_select_node_cpus); + /* If all offline, queue the work on an unbound CPU. */ + if (unlikely(cpu > rnp->grphi - rnp->grplo)) + cpu = WORK_CPU_UNBOUND; + else + cpu += rnp->grplo; + queue_work_on(cpu, rcu_par_gp_wq, &rnp->rew.rew_work); +} + +static inline void sync_rcu_exp_select_cpus_flush_work(struct rcu_node *rnp) +{ + flush_work(&rnp->rew.rew_work); +} + +/* + * Work-queue handler to drive an expedited grace period forward. + */ +static void wait_rcu_exp_gp(struct work_struct *wp) +{ + struct rcu_exp_work *rewp; + + rewp = container_of(wp, struct rcu_exp_work, rew_work); + rcu_exp_sel_wait_wake(rewp->rew_s); +} + +static inline void synchronize_rcu_expedited_queue_work(struct rcu_exp_work *rew) +{ + INIT_WORK_ONSTACK(&rew->rew_work, wait_rcu_exp_gp); + queue_work(rcu_gp_wq, &rew->rew_work); +} + +static inline void synchronize_rcu_expedited_destroy_work(struct rcu_exp_work *rew) +{ + destroy_work_on_stack(&rew->rew_work); +} +#endif /* CONFIG_RCU_EXP_KTHREAD */ + /* * Select the nodes that the upcoming expedited grace period needs * to wait for. */ static void sync_rcu_exp_select_cpus(void) { - int cpu; struct rcu_node *rnp; trace_rcu_exp_grace_period(rcu_state.name, rcu_exp_gp_seq_endval(), TPS("reset")); @@ -435,28 +539,21 @@ static void sync_rcu_exp_select_cpus(void) rnp->exp_need_flush = false; if (!READ_ONCE(rnp->expmask)) continue; /* Avoid early boot non-existent wq. */ - if (!READ_ONCE(rcu_par_gp_wq) || + if (!rcu_gp_par_worker_started() || rcu_scheduler_active != RCU_SCHEDULER_RUNNING || rcu_is_last_leaf_node(rnp)) { - /* No workqueues yet or last leaf, do direct call. */ + /* No worker started yet or last leaf, do direct call. */ sync_rcu_exp_select_node_cpus(&rnp->rew.rew_work); continue; } - INIT_WORK(&rnp->rew.rew_work, sync_rcu_exp_select_node_cpus); - cpu = find_next_bit(&rnp->ffmask, BITS_PER_LONG, -1); - /* If all offline, queue the work on an unbound CPU. */ - if (unlikely(cpu > rnp->grphi - rnp->grplo)) - cpu = WORK_CPU_UNBOUND; - else - cpu += rnp->grplo; - queue_work_on(cpu, rcu_par_gp_wq, &rnp->rew.rew_work); + sync_rcu_exp_select_cpus_queue_work(rnp); rnp->exp_need_flush = true; } - /* Wait for workqueue jobs (if any) to complete. */ + /* Wait for jobs (if any) to complete. */ rcu_for_each_leaf_node(rnp) if (rnp->exp_need_flush) - flush_work(&rnp->rew.rew_work); + sync_rcu_exp_select_cpus_flush_work(rnp); } /* @@ -496,7 +593,7 @@ static void synchronize_rcu_expedited_wait(void) struct rcu_node *rnp_root = rcu_get_root(); trace_rcu_exp_grace_period(rcu_state.name, rcu_exp_gp_seq_endval(), TPS("startwait")); - jiffies_stall = rcu_jiffies_till_stall_check(); + jiffies_stall = rcu_exp_jiffies_till_stall_check(); jiffies_start = jiffies; if (tick_nohz_full_enabled() && rcu_inkernel_boot_has_ended()) { if (synchronize_rcu_expedited_wait_once(1)) @@ -571,7 +668,7 @@ static void synchronize_rcu_expedited_wait(void) dump_cpu_task(cpu); } } - jiffies_stall = 3 * rcu_jiffies_till_stall_check() + 3; + jiffies_stall = 3 * rcu_exp_jiffies_till_stall_check() + 3; } } @@ -622,17 +719,6 @@ static void rcu_exp_sel_wait_wake(unsigned long s) rcu_exp_wait_wake(s); } -/* - * Work-queue handler to drive an expedited grace period forward. - */ -static void wait_rcu_exp_gp(struct work_struct *wp) -{ - struct rcu_exp_work *rewp; - - rewp = container_of(wp, struct rcu_exp_work, rew_work); - rcu_exp_sel_wait_wake(rewp->rew_s); -} - #ifdef CONFIG_PREEMPT_RCU /* @@ -848,20 +934,19 @@ void synchronize_rcu_expedited(void) } else { /* Marshall arguments & schedule the expedited grace period. */ rew.rew_s = s; - INIT_WORK_ONSTACK(&rew.rew_work, wait_rcu_exp_gp); - queue_work(rcu_gp_wq, &rew.rew_work); + synchronize_rcu_expedited_queue_work(&rew); } /* Wait for expedited grace period to complete. */ rnp = rcu_get_root(); wait_event(rnp->exp_wq[rcu_seq_ctr(s) & 0x3], sync_exp_work_done(s)); - smp_mb(); /* Workqueue actions happen before return. */ + smp_mb(); /* Work actions happen before return. */ /* Let the next expedited grace period start. */ mutex_unlock(&rcu_state.exp_mutex); if (likely(!boottime)) - destroy_work_on_stack(&rew.rew_work); + synchronize_rcu_expedited_destroy_work(&rew); } EXPORT_SYMBOL_GPL(synchronize_rcu_expedited); diff --git a/kernel/rcu/tree_nocb.h b/kernel/rcu/tree_nocb.h index 636d0546a4e9..46694e13398a 100644 --- a/kernel/rcu/tree_nocb.h +++ b/kernel/rcu/tree_nocb.h @@ -60,9 +60,6 @@ static inline bool rcu_current_is_nocb_kthread(struct rcu_data *rdp) * Parse the boot-time rcu_nocb_mask CPU list from the kernel parameters. * If the list is invalid, a warning is emitted and all CPUs are offloaded. */ - -static bool rcu_nocb_is_setup; - static int __init rcu_nocb_setup(char *str) { alloc_bootmem_cpumask_var(&rcu_nocb_mask); @@ -72,7 +69,7 @@ static int __init rcu_nocb_setup(char *str) cpumask_setall(rcu_nocb_mask); } } - rcu_nocb_is_setup = true; + rcu_state.nocb_is_setup = true; return 1; } __setup("rcu_nocbs", rcu_nocb_setup); @@ -215,14 +212,6 @@ static void rcu_init_one_nocb(struct rcu_node *rnp) init_swait_queue_head(&rnp->nocb_gp_wq[1]); } -/* Is the specified CPU a no-CBs CPU? */ -bool rcu_is_nocb_cpu(int cpu) -{ - if (cpumask_available(rcu_nocb_mask)) - return cpumask_test_cpu(cpu, rcu_nocb_mask); - return false; -} - static bool __wake_nocb_gp(struct rcu_data *rdp_gp, struct rcu_data *rdp, bool force, unsigned long flags) @@ -1180,10 +1169,10 @@ void __init rcu_init_nohz(void) return; } } - rcu_nocb_is_setup = true; + rcu_state.nocb_is_setup = true; } - if (!rcu_nocb_is_setup) + if (!rcu_state.nocb_is_setup) return; #if defined(CONFIG_NO_HZ_FULL) @@ -1241,7 +1230,7 @@ static void rcu_spawn_cpu_nocb_kthread(int cpu) struct task_struct *t; struct sched_param sp; - if (!rcu_scheduler_fully_active || !rcu_nocb_is_setup) + if (!rcu_scheduler_fully_active || !rcu_state.nocb_is_setup) return; /* If there already is an rcuo kthread, then nothing to do. */ @@ -1277,22 +1266,6 @@ static void rcu_spawn_cpu_nocb_kthread(int cpu) WRITE_ONCE(rdp->nocb_gp_kthread, rdp_gp->nocb_gp_kthread); } -/* - * Once the scheduler is running, spawn rcuo kthreads for all online - * no-CBs CPUs. This assumes that the early_initcall()s happen before - * non-boot CPUs come online -- if this changes, we will need to add - * some mutual exclusion. - */ -static void __init rcu_spawn_nocb_kthreads(void) -{ - int cpu; - - if (rcu_nocb_is_setup) { - for_each_online_cpu(cpu) - rcu_spawn_cpu_nocb_kthread(cpu); - } -} - /* How many CB CPU IDs per GP kthread? Default of -1 for sqrt(nr_cpu_ids). */ static int rcu_nocb_gp_stride = -1; module_param(rcu_nocb_gp_stride, int, 0444); @@ -1549,10 +1522,6 @@ static void rcu_spawn_cpu_nocb_kthread(int cpu) { } -static void __init rcu_spawn_nocb_kthreads(void) -{ -} - static void show_rcu_nocb_state(struct rcu_data *rdp) { } diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h index 8360d86db1c0..c8ba0fe17267 100644 --- a/kernel/rcu/tree_plugin.h +++ b/kernel/rcu/tree_plugin.h @@ -486,6 +486,7 @@ rcu_preempt_deferred_qs_irqrestore(struct task_struct *t, unsigned long flags) t->rcu_read_unlock_special.s = 0; if (special.b.need_qs) { if (IS_ENABLED(CONFIG_RCU_STRICT_GRACE_PERIOD)) { + rdp->cpu_no_qs.b.norm = false; rcu_report_qs_rdp(rdp); udelay(rcu_unlock_delay); } else { @@ -660,7 +661,13 @@ static void rcu_read_unlock_special(struct task_struct *t) expboost && !rdp->defer_qs_iw_pending && cpu_online(rdp->cpu)) { // Get scheduler to re-evaluate and call hooks. // If !IRQ_WORK, FQS scan will eventually IPI. - init_irq_work(&rdp->defer_qs_iw, rcu_preempt_deferred_qs_handler); + if (IS_ENABLED(CONFIG_RCU_STRICT_GRACE_PERIOD) && + IS_ENABLED(CONFIG_PREEMPT_RT)) + rdp->defer_qs_iw = IRQ_WORK_INIT_HARD( + rcu_preempt_deferred_qs_handler); + else + init_irq_work(&rdp->defer_qs_iw, + rcu_preempt_deferred_qs_handler); rdp->defer_qs_iw_pending = true; irq_work_queue_on(&rdp->defer_qs_iw, rdp->cpu); } @@ -1124,7 +1131,8 @@ static void rcu_initiate_boost(struct rcu_node *rnp, unsigned long flags) __releases(rnp->lock) { raw_lockdep_assert_held_rcu_node(rnp); - if (!rcu_preempt_blocked_readers_cgp(rnp) && rnp->exp_tasks == NULL) { + if (!rnp->boost_kthread_task || + (!rcu_preempt_blocked_readers_cgp(rnp) && !rnp->exp_tasks)) { raw_spin_unlock_irqrestore_rcu_node(rnp, flags); return; } @@ -1226,18 +1234,6 @@ static void rcu_boost_kthread_setaffinity(struct rcu_node *rnp, int outgoingcpu) free_cpumask_var(cm); } -/* - * Spawn boost kthreads -- called as soon as the scheduler is running. - */ -static void __init rcu_spawn_boost_kthreads(void) -{ - struct rcu_node *rnp; - - rcu_for_each_leaf_node(rnp) - if (rcu_rnp_online_cpus(rnp)) - rcu_spawn_one_boost_kthread(rnp); -} - #else /* #ifdef CONFIG_RCU_BOOST */ static void rcu_initiate_boost(struct rcu_node *rnp, unsigned long flags) @@ -1263,10 +1259,6 @@ static void rcu_boost_kthread_setaffinity(struct rcu_node *rnp, int outgoingcpu) { } -static void __init rcu_spawn_boost_kthreads(void) -{ -} - #endif /* #else #ifdef CONFIG_RCU_BOOST */ /* diff --git a/kernel/rcu/tree_stall.h b/kernel/rcu/tree_stall.h index 0c5d8516516a..a001e1e7a992 100644 --- a/kernel/rcu/tree_stall.h +++ b/kernel/rcu/tree_stall.h @@ -25,6 +25,34 @@ int sysctl_max_rcu_stall_to_panic __read_mostly; #define RCU_STALL_MIGHT_DIV 8 #define RCU_STALL_MIGHT_MIN (2 * HZ) +int rcu_exp_jiffies_till_stall_check(void) +{ + int cpu_stall_timeout = READ_ONCE(rcu_exp_cpu_stall_timeout); + int exp_stall_delay_delta = 0; + int till_stall_check; + + // Zero says to use rcu_cpu_stall_timeout, but in milliseconds. + if (!cpu_stall_timeout) + cpu_stall_timeout = jiffies_to_msecs(rcu_jiffies_till_stall_check()); + + // Limit check must be consistent with the Kconfig limits for + // CONFIG_RCU_EXP_CPU_STALL_TIMEOUT, so check the allowed range. + // The minimum clamped value is "2UL", because at least one full + // tick has to be guaranteed. + till_stall_check = clamp(msecs_to_jiffies(cpu_stall_timeout), 2UL, 21UL * HZ); + + if (cpu_stall_timeout && jiffies_to_msecs(till_stall_check) != cpu_stall_timeout) + WRITE_ONCE(rcu_exp_cpu_stall_timeout, jiffies_to_msecs(till_stall_check)); + +#ifdef CONFIG_PROVE_RCU + /* Add extra ~25% out of till_stall_check. */ + exp_stall_delay_delta = ((till_stall_check * 25) / 100) + 1; +#endif + + return till_stall_check + exp_stall_delay_delta; +} +EXPORT_SYMBOL_GPL(rcu_exp_jiffies_till_stall_check); + /* Limit-check stall timeouts specified at boottime and runtime. */ int rcu_jiffies_till_stall_check(void) { @@ -565,9 +593,9 @@ static void print_other_cpu_stall(unsigned long gp_seq, unsigned long gps) for_each_possible_cpu(cpu) totqlen += rcu_get_n_cbs_cpu(cpu); - pr_cont("\t(detected by %d, t=%ld jiffies, g=%ld, q=%lu)\n", + pr_cont("\t(detected by %d, t=%ld jiffies, g=%ld, q=%lu ncpus=%d)\n", smp_processor_id(), (long)(jiffies - gps), - (long)rcu_seq_current(&rcu_state.gp_seq), totqlen); + (long)rcu_seq_current(&rcu_state.gp_seq), totqlen, rcu_state.n_online_cpus); if (ndetected) { rcu_dump_cpu_stacks(); @@ -626,9 +654,9 @@ static void print_cpu_stall(unsigned long gps) raw_spin_unlock_irqrestore_rcu_node(rdp->mynode, flags); for_each_possible_cpu(cpu) totqlen += rcu_get_n_cbs_cpu(cpu); - pr_cont("\t(t=%lu jiffies g=%ld q=%lu)\n", + pr_cont("\t(t=%lu jiffies g=%ld q=%lu ncpus=%d)\n", jiffies - gps, - (long)rcu_seq_current(&rcu_state.gp_seq), totqlen); + (long)rcu_seq_current(&rcu_state.gp_seq), totqlen, rcu_state.n_online_cpus); rcu_check_gp_kthread_expired_fqs_timer(); rcu_check_gp_kthread_starvation(); diff --git a/kernel/rcu/update.c b/kernel/rcu/update.c index 180ff9c41fa8..fc7fef575606 100644 --- a/kernel/rcu/update.c +++ b/kernel/rcu/update.c @@ -506,6 +506,8 @@ EXPORT_SYMBOL_GPL(rcu_cpu_stall_suppress); module_param(rcu_cpu_stall_suppress, int, 0644); int rcu_cpu_stall_timeout __read_mostly = CONFIG_RCU_CPU_STALL_TIMEOUT; module_param(rcu_cpu_stall_timeout, int, 0644); +int rcu_exp_cpu_stall_timeout __read_mostly = CONFIG_RCU_EXP_CPU_STALL_TIMEOUT; +module_param(rcu_exp_cpu_stall_timeout, int, 0644); #endif /* #ifdef CONFIG_RCU_STALL_COMMON */ // Suppress boot-time RCU CPU stall warnings and rcutorture writer stall diff --git a/kernel/scftorture.c b/kernel/scftorture.c index dcb0410950e4..5d113aa59e77 100644 --- a/kernel/scftorture.c +++ b/kernel/scftorture.c @@ -267,9 +267,10 @@ static void scf_handler(void *scfc_in) } this_cpu_inc(scf_invoked_count); if (longwait <= 0) { - if (!(r & 0xffc0)) + if (!(r & 0xffc0)) { udelay(r & 0x3f); - goto out; + goto out; + } } if (r & 0xfff) goto out; diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 51efaabac3e4..2a05096559a2 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -6382,7 +6382,7 @@ static void __sched notrace __schedule(unsigned int sched_mode) migrate_disable_switch(rq, prev); psi_sched_switch(prev, next, !task_on_rq_queued(prev)); - trace_sched_switch(sched_mode & SM_MASK_PREEMPT, prev_state, prev, next); + trace_sched_switch(sched_mode & SM_MASK_PREEMPT, prev, next, prev_state); /* Also unlocks the rq: */ rq = context_switch(rq, prev, next, &rf); @@ -8415,6 +8415,18 @@ static void __init preempt_dynamic_init(void) } } +#define PREEMPT_MODEL_ACCESSOR(mode) \ + bool preempt_model_##mode(void) \ + { \ + WARN_ON_ONCE(preempt_dynamic_mode == preempt_dynamic_undefined); \ + return preempt_dynamic_mode == preempt_dynamic_##mode; \ + } \ + EXPORT_SYMBOL_GPL(preempt_model_##mode) + +PREEMPT_MODEL_ACCESSOR(none); +PREEMPT_MODEL_ACCESSOR(voluntary); +PREEMPT_MODEL_ACCESSOR(full); + #else /* !CONFIG_PREEMPT_DYNAMIC */ static inline void preempt_dynamic_init(void) { } diff --git a/kernel/smp.c b/kernel/smp.c index 65a630f62363..df9393aeae28 100644 --- a/kernel/smp.c +++ b/kernel/smp.c @@ -183,7 +183,9 @@ static DEFINE_PER_CPU(smp_call_func_t, cur_csd_func); static DEFINE_PER_CPU(void *, cur_csd_info); static DEFINE_PER_CPU(struct cfd_seq_local, cfd_seq_local); -#define CSD_LOCK_TIMEOUT (5ULL * NSEC_PER_SEC) +static ulong csd_lock_timeout = 5000; /* CSD lock timeout in milliseconds. */ +module_param(csd_lock_timeout, ulong, 0444); + static atomic_t csd_bug_count = ATOMIC_INIT(0); static u64 cfd_seq; @@ -329,6 +331,7 @@ static bool csd_lock_wait_toolong(struct __call_single_data *csd, u64 ts0, u64 * u64 ts2, ts_delta; call_single_data_t *cpu_cur_csd; unsigned int flags = READ_ONCE(csd->node.u_flags); + unsigned long long csd_lock_timeout_ns = csd_lock_timeout * NSEC_PER_MSEC; if (!(flags & CSD_FLAG_LOCK)) { if (!unlikely(*bug_id)) @@ -341,7 +344,7 @@ static bool csd_lock_wait_toolong(struct __call_single_data *csd, u64 ts0, u64 * ts2 = sched_clock(); ts_delta = ts2 - *ts1; - if (likely(ts_delta <= CSD_LOCK_TIMEOUT)) + if (likely(ts_delta <= csd_lock_timeout_ns || csd_lock_timeout_ns == 0)) return false; firsttime = !*bug_id; diff --git a/kernel/smpboot.c b/kernel/smpboot.c index f6bc0bc8a2aa..b9f54544e749 100644 --- a/kernel/smpboot.c +++ b/kernel/smpboot.c @@ -392,6 +392,13 @@ int cpu_check_up_prepare(int cpu) */ return -EAGAIN; + case CPU_UP_PREPARE: + /* + * Timeout while waiting for the CPU to show up. Allow to try + * again later. + */ + return 0; + default: /* Should not happen. Famous last words. */ diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 830aaf8ca08e..5b7b1a82ae6a 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -2288,17 +2288,6 @@ static struct ctl_table kern_table[] = { .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_ONE, }, -#if defined(CONFIG_SMP) && defined(CONFIG_NO_HZ_COMMON) - { - .procname = "timer_migration", - .data = &sysctl_timer_migration, - .maxlen = sizeof(unsigned int), - .mode = 0644, - .proc_handler = timer_migration_handler, - .extra1 = SYSCTL_ZERO, - .extra2 = SYSCTL_ONE, - }, -#endif #ifdef CONFIG_BPF_SYSCALL { .procname = "unprivileged_bpf_disabled", diff --git a/kernel/task_work.c b/kernel/task_work.c index c59e1a49bc40..dff75bcde151 100644 --- a/kernel/task_work.c +++ b/kernel/task_work.c @@ -12,12 +12,22 @@ static struct callback_head work_exited; /* all we need is ->next == NULL */ * @notify: how to notify the targeted task * * Queue @work for task_work_run() below and notify the @task if @notify - * is @TWA_RESUME or @TWA_SIGNAL. @TWA_SIGNAL works like signals, in that the - * it will interrupt the targeted task and run the task_work. @TWA_RESUME - * work is run only when the task exits the kernel and returns to user mode, - * or before entering guest mode. Fails if the @task is exiting/exited and thus - * it can't process this @work. Otherwise @work->func() will be called when the - * @task goes through one of the aforementioned transitions, or exits. + * is @TWA_RESUME, @TWA_SIGNAL, or @TWA_SIGNAL_NO_IPI. + * + * @TWA_SIGNAL works like signals, in that the it will interrupt the targeted + * task and run the task_work, regardless of whether the task is currently + * running in the kernel or userspace. + * @TWA_SIGNAL_NO_IPI works like @TWA_SIGNAL, except it doesn't send a + * reschedule IPI to force the targeted task to reschedule and run task_work. + * This can be advantageous if there's no strict requirement that the + * task_work be run as soon as possible, just whenever the task enters the + * kernel anyway. + * @TWA_RESUME work is run only when the task exits the kernel and returns to + * user mode, or before entering guest mode. + * + * Fails if the @task is exiting/exited and thus it can't process this @work. + * Otherwise @work->func() will be called when the @task goes through one of + * the aforementioned transitions, or exits. * * If the targeted task is exiting, then an error is returned and the work item * is not queued. It's up to the caller to arrange for an alternative mechanism @@ -53,6 +63,9 @@ int task_work_add(struct task_struct *task, struct callback_head *work, case TWA_SIGNAL: set_notify_signal(task); break; + case TWA_SIGNAL_NO_IPI: + __set_notify_signal(task); + break; default: WARN_ON_ONCE(1); break; diff --git a/kernel/time/clockevents.c b/kernel/time/clockevents.c index 003ccf338d20..5d85014d59b5 100644 --- a/kernel/time/clockevents.c +++ b/kernel/time/clockevents.c @@ -690,7 +690,7 @@ static ssize_t unbind_device_store(struct device *dev, { char name[CS_NAME_LEN]; ssize_t ret = sysfs_get_uname(buf, name, count); - struct clock_event_device *ce; + struct clock_event_device *ce = NULL, *iter; if (ret < 0) return ret; @@ -698,9 +698,10 @@ static ssize_t unbind_device_store(struct device *dev, ret = -ENODEV; mutex_lock(&clockevents_mutex); raw_spin_lock_irq(&clockevents_lock); - list_for_each_entry(ce, &clockevent_devices, list) { - if (!strcmp(ce->name, name)) { - ret = __clockevents_try_unbind(ce, dev->id); + list_for_each_entry(iter, &clockevent_devices, list) { + if (!strcmp(iter->name, name)) { + ret = __clockevents_try_unbind(iter, dev->id); + ce = iter; break; } } diff --git a/kernel/time/clocksource.c b/kernel/time/clocksource.c index 95d7ca35bdf2..cee5da1e54c4 100644 --- a/kernel/time/clocksource.c +++ b/kernel/time/clocksource.c @@ -343,7 +343,7 @@ void clocksource_verify_percpu(struct clocksource *cs) cpus_read_lock(); preempt_disable(); clocksource_verify_choose_cpus(); - if (cpumask_weight(&cpus_chosen) == 0) { + if (cpumask_empty(&cpus_chosen)) { preempt_enable(); cpus_read_unlock(); pr_warn("Not enough CPUs to check clocksource '%s'.\n", cs->name); diff --git a/kernel/time/sched_clock.c b/kernel/time/sched_clock.c index b1b9b12899f5..8464c5acc913 100644 --- a/kernel/time/sched_clock.c +++ b/kernel/time/sched_clock.c @@ -8,6 +8,7 @@ #include <linux/jiffies.h> #include <linux/ktime.h> #include <linux/kernel.h> +#include <linux/math.h> #include <linux/moduleparam.h> #include <linux/sched.h> #include <linux/sched/clock.h> @@ -199,15 +200,13 @@ sched_clock_register(u64 (*read)(void), int bits, unsigned long rate) r = rate; if (r >= 4000000) { - r /= 1000000; + r = DIV_ROUND_CLOSEST(r, 1000000); r_unit = 'M'; + } else if (r >= 4000) { + r = DIV_ROUND_CLOSEST(r, 1000); + r_unit = 'k'; } else { - if (r >= 1000) { - r /= 1000; - r_unit = 'k'; - } else { - r_unit = ' '; - } + r_unit = ' '; } /* Calculate the ns resolution of this counter */ diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c index d257721c68b8..58a11f859ac7 100644 --- a/kernel/time/tick-sched.c +++ b/kernel/time/tick-sched.c @@ -928,6 +928,8 @@ static void tick_nohz_stop_tick(struct tick_sched *ts, int cpu) if (unlikely(expires == KTIME_MAX)) { if (ts->nohz_mode == NOHZ_MODE_HIGHRES) hrtimer_cancel(&ts->sched_timer); + else + tick_program_event(KTIME_MAX, 1); return; } @@ -1364,9 +1366,15 @@ static void tick_nohz_handler(struct clock_event_device *dev) tick_sched_do_timer(ts, now); tick_sched_handle(ts, regs); - /* No need to reprogram if we are running tickless */ - if (unlikely(ts->tick_stopped)) + if (unlikely(ts->tick_stopped)) { + /* + * The clockevent device is not reprogrammed, so change the + * clock event device to ONESHOT_STOPPED to avoid spurious + * interrupts on devices which might not be truly one shot. + */ + tick_program_event(KTIME_MAX, 1); return; + } hrtimer_forward(&ts->sched_timer, now, TICK_NSEC); tick_program_event(hrtimer_get_expires(&ts->sched_timer), 1); diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c index 3b1398fbddaf..4ab9949772d5 100644 --- a/kernel/time/timekeeping.c +++ b/kernel/time/timekeeping.c @@ -429,6 +429,14 @@ static void update_fast_timekeeper(const struct tk_read_base *tkr, memcpy(base + 1, base, sizeof(*base)); } +static __always_inline u64 fast_tk_get_delta_ns(struct tk_read_base *tkr) +{ + u64 delta, cycles = tk_clock_read(tkr); + + delta = clocksource_delta(cycles, tkr->cycle_last, tkr->mask); + return timekeeping_delta_to_ns(tkr, delta); +} + static __always_inline u64 __ktime_get_fast_ns(struct tk_fast *tkf) { struct tk_read_base *tkr; @@ -439,12 +447,7 @@ static __always_inline u64 __ktime_get_fast_ns(struct tk_fast *tkf) seq = raw_read_seqcount_latch(&tkf->seq); tkr = tkf->base + (seq & 0x01); now = ktime_to_ns(tkr->base); - - now += timekeeping_delta_to_ns(tkr, - clocksource_delta( - tk_clock_read(tkr), - tkr->cycle_last, - tkr->mask)); + now += fast_tk_get_delta_ns(tkr); } while (read_seqcount_latch_retry(&tkf->seq, seq)); return now; @@ -528,10 +531,27 @@ u64 notrace ktime_get_boot_fast_ns(void) { struct timekeeper *tk = &tk_core.timekeeper; - return (ktime_get_mono_fast_ns() + ktime_to_ns(tk->offs_boot)); + return (ktime_get_mono_fast_ns() + ktime_to_ns(data_race(tk->offs_boot))); } EXPORT_SYMBOL_GPL(ktime_get_boot_fast_ns); +/** + * ktime_get_tai_fast_ns - NMI safe and fast access to tai clock. + * + * The same limitations as described for ktime_get_boot_fast_ns() apply. The + * mono time and the TAI offset are not read atomically which may yield wrong + * readouts. However, an update of the TAI offset is an rare event e.g., caused + * by settime or adjtimex with an offset. The user of this function has to deal + * with the possibility of wrong timestamps in post processing. + */ +u64 notrace ktime_get_tai_fast_ns(void) +{ + struct timekeeper *tk = &tk_core.timekeeper; + + return (ktime_get_mono_fast_ns() + ktime_to_ns(data_race(tk->offs_tai))); +} +EXPORT_SYMBOL_GPL(ktime_get_tai_fast_ns); + static __always_inline u64 __ktime_get_real_fast(struct tk_fast *tkf, u64 *mono) { struct tk_read_base *tkr; @@ -543,10 +563,7 @@ static __always_inline u64 __ktime_get_real_fast(struct tk_fast *tkf, u64 *mono) tkr = tkf->base + (seq & 0x01); basem = ktime_to_ns(tkr->base); baser = ktime_to_ns(tkr->base_real); - - delta = timekeeping_delta_to_ns(tkr, - clocksource_delta(tk_clock_read(tkr), - tkr->cycle_last, tkr->mask)); + delta = fast_tk_get_delta_ns(tkr); } while (read_seqcount_latch_retry(&tkf->seq, seq)); if (mono) diff --git a/kernel/time/timer.c b/kernel/time/timer.c index 9dd2a39cb3b0..a0666d948147 100644 --- a/kernel/time/timer.c +++ b/kernel/time/timer.c @@ -44,6 +44,7 @@ #include <linux/slab.h> #include <linux/compat.h> #include <linux/random.h> +#include <linux/sysctl.h> #include <linux/uaccess.h> #include <asm/unistd.h> @@ -223,7 +224,7 @@ static void timer_update_keys(struct work_struct *work); static DECLARE_WORK(timer_update_work, timer_update_keys); #ifdef CONFIG_SMP -unsigned int sysctl_timer_migration = 1; +static unsigned int sysctl_timer_migration = 1; DEFINE_STATIC_KEY_FALSE(timers_migration_enabled); @@ -234,7 +235,42 @@ static void timers_update_migration(void) else static_branch_disable(&timers_migration_enabled); } -#else + +#ifdef CONFIG_SYSCTL +static int timer_migration_handler(struct ctl_table *table, int write, + void *buffer, size_t *lenp, loff_t *ppos) +{ + int ret; + + mutex_lock(&timer_keys_mutex); + ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos); + if (!ret && write) + timers_update_migration(); + mutex_unlock(&timer_keys_mutex); + return ret; +} + +static struct ctl_table timer_sysctl[] = { + { + .procname = "timer_migration", + .data = &sysctl_timer_migration, + .maxlen = sizeof(unsigned int), + .mode = 0644, + .proc_handler = timer_migration_handler, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_ONE, + }, + {} +}; + +static int __init timer_sysctl_init(void) +{ + register_sysctl("kernel", timer_sysctl); + return 0; +} +device_initcall(timer_sysctl_init); +#endif /* CONFIG_SYSCTL */ +#else /* CONFIG_SMP */ static inline void timers_update_migration(void) { } #endif /* !CONFIG_SMP */ @@ -251,19 +287,6 @@ void timers_update_nohz(void) schedule_work(&timer_update_work); } -int timer_migration_handler(struct ctl_table *table, int write, - void *buffer, size_t *lenp, loff_t *ppos) -{ - int ret; - - mutex_lock(&timer_keys_mutex); - ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos); - if (!ret && write) - timers_update_migration(); - mutex_unlock(&timer_keys_mutex); - return ret; -} - static inline bool is_timers_nohz_active(void) { return static_branch_unlikely(&timers_nohz_active); @@ -502,7 +525,7 @@ static inline unsigned calc_index(unsigned long expires, unsigned lvl, * * Round up with level granularity to prevent this. */ - expires = (expires + LVL_GRAN(lvl)) >> LVL_SHIFT(lvl); + expires = (expires >> LVL_SHIFT(lvl)) + 1; *bucket_expiry = expires << LVL_SHIFT(lvl); return LVL_OFFS(lvl) + (expires & LVL_MASK); } @@ -615,9 +638,39 @@ static void internal_add_timer(struct timer_base *base, struct timer_list *timer static const struct debug_obj_descr timer_debug_descr; +struct timer_hint { + void (*function)(struct timer_list *t); + long offset; +}; + +#define TIMER_HINT(fn, container, timr, hintfn) \ + { \ + .function = fn, \ + .offset = offsetof(container, hintfn) - \ + offsetof(container, timr) \ + } + +static const struct timer_hint timer_hints[] = { + TIMER_HINT(delayed_work_timer_fn, + struct delayed_work, timer, work.func), + TIMER_HINT(kthread_delayed_work_timer_fn, + struct kthread_delayed_work, timer, work.func), +}; + static void *timer_debug_hint(void *addr) { - return ((struct timer_list *) addr)->function; + struct timer_list *timer = addr; + int i; + + for (i = 0; i < ARRAY_SIZE(timer_hints); i++) { + if (timer_hints[i].function == timer->function) { + void (**fn)(void) = addr + timer_hints[i].offset; + + return *fn; + } + } + + return timer->function; } static bool timer_is_static_object(void *addr) @@ -1953,6 +2006,7 @@ int timers_prepare_cpu(unsigned int cpu) base = per_cpu_ptr(&timer_bases[b], cpu); base->clk = jiffies; base->next_expiry = base->clk + NEXT_TIMER_MAX_DELTA; + base->next_expiry_recalc = false; base->timers_pending = false; base->is_idle = false; } diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig index 2c43e327a619..bf5da6c4e999 100644 --- a/kernel/trace/Kconfig +++ b/kernel/trace/Kconfig @@ -144,6 +144,7 @@ config TRACING select BINARY_PRINTF select EVENT_TRACING select TRACE_CLOCK + select TASKS_RCU if PREEMPTION config GENERIC_TRACER bool diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c index 4d5629196d01..10a32b0f2deb 100644 --- a/kernel/trace/blktrace.c +++ b/kernel/trace/blktrace.c @@ -145,13 +145,14 @@ static void trace_note_time(struct blk_trace *bt) local_irq_restore(flags); } -void __trace_note_message(struct blk_trace *bt, struct blkcg *blkcg, - const char *fmt, ...) +void __blk_trace_note_message(struct blk_trace *bt, + struct cgroup_subsys_state *css, const char *fmt, ...) { int n; va_list args; unsigned long flags; char *buf; + u64 cgid = 0; if (unlikely(bt->trace_state != Blktrace_running && !blk_tracer_enabled)) @@ -170,17 +171,16 @@ void __trace_note_message(struct blk_trace *bt, struct blkcg *blkcg, n = vscnprintf(buf, BLK_TN_MAX_MSG, fmt, args); va_end(args); - if (!(blk_tracer_flags.val & TRACE_BLK_OPT_CGROUP)) - blkcg = NULL; #ifdef CONFIG_BLK_CGROUP - trace_note(bt, current->pid, BLK_TN_MESSAGE, buf, n, - blkcg ? cgroup_id(blkcg->css.cgroup) : 1); -#else - trace_note(bt, current->pid, BLK_TN_MESSAGE, buf, n, 0); + if (css && (blk_tracer_flags.val & TRACE_BLK_OPT_CGROUP)) + cgid = cgroup_id(css->cgroup); + else + cgid = 1; #endif + trace_note(bt, current->pid, BLK_TN_MESSAGE, buf, n, cgid); local_irq_restore(flags); } -EXPORT_SYMBOL_GPL(__trace_note_message); +EXPORT_SYMBOL_GPL(__blk_trace_note_message); static int act_log_check(struct blk_trace *bt, u32 what, sector_t sector, pid_t pid) @@ -411,7 +411,7 @@ static ssize_t blk_msg_write(struct file *filp, const char __user *buffer, return PTR_ERR(msg); bt = filp->private_data; - __trace_note_message(bt, NULL, "%s", msg); + __blk_trace_note_message(bt, NULL, "%s", msg); kfree(msg); return count; @@ -783,6 +783,7 @@ void blk_trace_shutdown(struct request_queue *q) #ifdef CONFIG_BLK_CGROUP static u64 blk_trace_bio_get_cgid(struct request_queue *q, struct bio *bio) { + struct cgroup_subsys_state *blkcg_css; struct blk_trace *bt; /* We don't use the 'bt' value here except as an optimization... */ @@ -790,9 +791,10 @@ static u64 blk_trace_bio_get_cgid(struct request_queue *q, struct bio *bio) if (!bt || !(blk_tracer_flags.val & TRACE_BLK_OPT_CGROUP)) return 0; - if (!bio->bi_blkg) + blkcg_css = bio_blkcg_css(bio); + if (!blkcg_css) return 0; - return cgroup_id(bio_blkcg(bio)->css.cgroup); + return cgroup_id(blkcg_css->cgroup); } #else static u64 blk_trace_bio_get_cgid(struct request_queue *q, struct bio *bio) diff --git a/kernel/trace/fgraph.c b/kernel/trace/fgraph.c index 8f4fb328133a..a7e84c8543cb 100644 --- a/kernel/trace/fgraph.c +++ b/kernel/trace/fgraph.c @@ -404,9 +404,9 @@ free: static void ftrace_graph_probe_sched_switch(void *ignore, bool preempt, - unsigned int prev_state, struct task_struct *prev, - struct task_struct *next) + struct task_struct *next, + unsigned int prev_state) { unsigned long long timestamp; int index; diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index 4f1d2f5e7263..af899b058c8d 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -7420,9 +7420,9 @@ ftrace_func_t ftrace_ops_get_func(struct ftrace_ops *ops) static void ftrace_filter_pid_sched_switch_probe(void *data, bool preempt, - unsigned int prev_state, struct task_struct *prev, - struct task_struct *next) + struct task_struct *next, + unsigned int prev_state) { struct trace_array *tr = data; struct trace_pid_list *pid_list; diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c index e11e167b7809..f97de82d1342 100644 --- a/kernel/trace/trace_events.c +++ b/kernel/trace/trace_events.c @@ -773,9 +773,9 @@ void trace_event_follow_fork(struct trace_array *tr, bool enable) static void event_filter_pid_sched_switch_probe_pre(void *data, bool preempt, - unsigned int prev_state, struct task_struct *prev, - struct task_struct *next) + struct task_struct *next, + unsigned int prev_state) { struct trace_array *tr = data; struct trace_pid_list *no_pid_list; @@ -799,9 +799,9 @@ event_filter_pid_sched_switch_probe_pre(void *data, bool preempt, static void event_filter_pid_sched_switch_probe_post(void *data, bool preempt, - unsigned int prev_state, struct task_struct *prev, - struct task_struct *next) + struct task_struct *next, + unsigned int prev_state) { struct trace_array *tr = data; struct trace_pid_list *no_pid_list; diff --git a/kernel/trace/trace_osnoise.c b/kernel/trace/trace_osnoise.c index e9ae1f33a7f0..afb92e2f0aea 100644 --- a/kernel/trace/trace_osnoise.c +++ b/kernel/trace/trace_osnoise.c @@ -1168,9 +1168,9 @@ thread_exit(struct osnoise_variables *osn_var, struct task_struct *t) */ static void trace_sched_switch_callback(void *data, bool preempt, - unsigned int prev_state, struct task_struct *p, - struct task_struct *n) + struct task_struct *n, + unsigned int prev_state) { struct osnoise_variables *osn_var = this_cpu_osn_var(); diff --git a/kernel/trace/trace_sched_switch.c b/kernel/trace/trace_sched_switch.c index 45796d8bd4b2..c9ffdcfe622e 100644 --- a/kernel/trace/trace_sched_switch.c +++ b/kernel/trace/trace_sched_switch.c @@ -22,8 +22,8 @@ static DEFINE_MUTEX(sched_register_mutex); static void probe_sched_switch(void *ignore, bool preempt, - unsigned int prev_state, - struct task_struct *prev, struct task_struct *next) + struct task_struct *prev, struct task_struct *next, + unsigned int prev_state) { int flags; diff --git a/kernel/trace/trace_sched_wakeup.c b/kernel/trace/trace_sched_wakeup.c index 46429f9a96fa..330aee1c1a49 100644 --- a/kernel/trace/trace_sched_wakeup.c +++ b/kernel/trace/trace_sched_wakeup.c @@ -426,8 +426,8 @@ tracing_sched_wakeup_trace(struct trace_array *tr, static void notrace probe_wakeup_sched_switch(void *ignore, bool preempt, - unsigned int prev_state, - struct task_struct *prev, struct task_struct *next) + struct task_struct *prev, struct task_struct *next, + unsigned int prev_state) { struct trace_array_cpu *data; u64 T0, T1, delta; diff --git a/lib/bug.c b/lib/bug.c index 45a0584f6541..c223a2575b72 100644 --- a/lib/bug.c +++ b/lib/bug.c @@ -6,8 +6,7 @@ CONFIG_BUG - emit BUG traps. Nothing happens without this. CONFIG_GENERIC_BUG - enable this code. - CONFIG_GENERIC_BUG_RELATIVE_POINTERS - use 32-bit pointers relative to - the containing struct bug_entry for bug_addr and file. + CONFIG_GENERIC_BUG_RELATIVE_POINTERS - use 32-bit relative pointers for bug_addr and file CONFIG_DEBUG_BUGVERBOSE - emit full file+line information for each BUG CONFIG_BUG and CONFIG_DEBUG_BUGVERBOSE are potentially user-settable @@ -53,10 +52,10 @@ extern struct bug_entry __start___bug_table[], __stop___bug_table[]; static inline unsigned long bug_addr(const struct bug_entry *bug) { -#ifndef CONFIG_GENERIC_BUG_RELATIVE_POINTERS - return bug->bug_addr; +#ifdef CONFIG_GENERIC_BUG_RELATIVE_POINTERS + return (unsigned long)&bug->bug_addr_disp + bug->bug_addr_disp; #else - return (unsigned long)bug + bug->bug_addr_disp; + return bug->bug_addr; #endif } @@ -131,10 +130,10 @@ void bug_get_file_line(struct bug_entry *bug, const char **file, unsigned int *line) { #ifdef CONFIG_DEBUG_BUGVERBOSE -#ifndef CONFIG_GENERIC_BUG_RELATIVE_POINTERS - *file = bug->file; +#ifdef CONFIG_GENERIC_BUG_RELATIVE_POINTERS + *file = (const char *)&bug->file_disp + bug->file_disp; #else - *file = (const char *)bug + bug->file_disp; + *file = bug->file; #endif *line = bug->line; #else diff --git a/lib/debugobjects.c b/lib/debugobjects.c index 6946f8e204e3..337d797a7141 100644 --- a/lib/debugobjects.c +++ b/lib/debugobjects.c @@ -1,11 +1,8 @@ +// SPDX-License-Identifier: GPL-2.0 /* * Generic infrastructure for lifetime debugging of objects. * - * Started by Thomas Gleixner - * * Copyright (C) 2008, Thomas Gleixner <tglx@linutronix.de> - * - * For licencing details see kernel-base/COPYING */ #define pr_fmt(fmt) "ODEBUG: " fmt diff --git a/lib/dim/net_dim.c b/lib/dim/net_dim.c index 06811d866775..53f6b9c6e936 100644 --- a/lib/dim/net_dim.c +++ b/lib/dim/net_dim.c @@ -12,41 +12,41 @@ * Each profile size must be of NET_DIM_PARAMS_NUM_PROFILES */ #define NET_DIM_PARAMS_NUM_PROFILES 5 -#define NET_DIM_DEFAULT_RX_CQ_MODERATION_PKTS_FROM_EQE 256 -#define NET_DIM_DEFAULT_TX_CQ_MODERATION_PKTS_FROM_EQE 128 +#define NET_DIM_DEFAULT_RX_CQ_PKTS_FROM_EQE 256 +#define NET_DIM_DEFAULT_TX_CQ_PKTS_FROM_EQE 128 #define NET_DIM_DEF_PROFILE_CQE 1 #define NET_DIM_DEF_PROFILE_EQE 1 #define NET_DIM_RX_EQE_PROFILES { \ - {1, NET_DIM_DEFAULT_RX_CQ_MODERATION_PKTS_FROM_EQE}, \ - {8, NET_DIM_DEFAULT_RX_CQ_MODERATION_PKTS_FROM_EQE}, \ - {64, NET_DIM_DEFAULT_RX_CQ_MODERATION_PKTS_FROM_EQE}, \ - {128, NET_DIM_DEFAULT_RX_CQ_MODERATION_PKTS_FROM_EQE}, \ - {256, NET_DIM_DEFAULT_RX_CQ_MODERATION_PKTS_FROM_EQE}, \ + {.usec = 1, .pkts = NET_DIM_DEFAULT_RX_CQ_PKTS_FROM_EQE,}, \ + {.usec = 8, .pkts = NET_DIM_DEFAULT_RX_CQ_PKTS_FROM_EQE,}, \ + {.usec = 64, .pkts = NET_DIM_DEFAULT_RX_CQ_PKTS_FROM_EQE,}, \ + {.usec = 128, .pkts = NET_DIM_DEFAULT_RX_CQ_PKTS_FROM_EQE,}, \ + {.usec = 256, .pkts = NET_DIM_DEFAULT_RX_CQ_PKTS_FROM_EQE,} \ } #define NET_DIM_RX_CQE_PROFILES { \ - {2, 256}, \ - {8, 128}, \ - {16, 64}, \ - {32, 64}, \ - {64, 64} \ + {.usec = 2, .pkts = 256,}, \ + {.usec = 8, .pkts = 128,}, \ + {.usec = 16, .pkts = 64,}, \ + {.usec = 32, .pkts = 64,}, \ + {.usec = 64, .pkts = 64,} \ } #define NET_DIM_TX_EQE_PROFILES { \ - {1, NET_DIM_DEFAULT_TX_CQ_MODERATION_PKTS_FROM_EQE}, \ - {8, NET_DIM_DEFAULT_TX_CQ_MODERATION_PKTS_FROM_EQE}, \ - {32, NET_DIM_DEFAULT_TX_CQ_MODERATION_PKTS_FROM_EQE}, \ - {64, NET_DIM_DEFAULT_TX_CQ_MODERATION_PKTS_FROM_EQE}, \ - {128, NET_DIM_DEFAULT_TX_CQ_MODERATION_PKTS_FROM_EQE} \ + {.usec = 1, .pkts = NET_DIM_DEFAULT_TX_CQ_PKTS_FROM_EQE,}, \ + {.usec = 8, .pkts = NET_DIM_DEFAULT_TX_CQ_PKTS_FROM_EQE,}, \ + {.usec = 32, .pkts = NET_DIM_DEFAULT_TX_CQ_PKTS_FROM_EQE,}, \ + {.usec = 64, .pkts = NET_DIM_DEFAULT_TX_CQ_PKTS_FROM_EQE,}, \ + {.usec = 128, .pkts = NET_DIM_DEFAULT_TX_CQ_PKTS_FROM_EQE,} \ } #define NET_DIM_TX_CQE_PROFILES { \ - {5, 128}, \ - {8, 64}, \ - {16, 32}, \ - {32, 32}, \ - {64, 32} \ + {.usec = 5, .pkts = 128,}, \ + {.usec = 8, .pkts = 64,}, \ + {.usec = 16, .pkts = 32,}, \ + {.usec = 32, .pkts = 32,}, \ + {.usec = 64, .pkts = 32,} \ } static const struct dim_cq_moder diff --git a/lib/irq_poll.c b/lib/irq_poll.c index 2f17b488d58e..2d5329a42105 100644 --- a/lib/irq_poll.c +++ b/lib/irq_poll.c @@ -188,14 +188,18 @@ EXPORT_SYMBOL(irq_poll_init); static int irq_poll_cpu_dead(unsigned int cpu) { /* - * If a CPU goes away, splice its entries to the current CPU - * and trigger a run of the softirq + * If a CPU goes away, splice its entries to the current CPU and + * set the POLL softirq bit. The local_bh_disable()/enable() pair + * ensures that it is handled. Otherwise the current CPU could + * reach idle with the POLL softirq pending. */ + local_bh_disable(); local_irq_disable(); list_splice_init(&per_cpu(blk_cpu_iopoll, cpu), this_cpu_ptr(&blk_cpu_iopoll)); __raise_softirq_irqoff(IRQ_POLL_SOFTIRQ); local_irq_enable(); + local_bh_enable(); return 0; } diff --git a/lib/percpu-refcount.c b/lib/percpu-refcount.c index af9302141bcf..e5c5315da274 100644 --- a/lib/percpu-refcount.c +++ b/lib/percpu-refcount.c @@ -76,6 +76,7 @@ int percpu_ref_init(struct percpu_ref *ref, percpu_ref_func_t *release, data = kzalloc(sizeof(*ref->data), gfp); if (!data) { free_percpu((void __percpu *)ref->percpu_count_ptr); + ref->percpu_count_ptr = 0; return -ENOMEM; } diff --git a/mm/backing-dev.c b/mm/backing-dev.c index 7176af65b103..ff60bd7d74e0 100644 --- a/mm/backing-dev.c +++ b/mm/backing-dev.c @@ -1,5 +1,6 @@ // SPDX-License-Identifier: GPL-2.0-only +#include <linux/blkdev.h> #include <linux/wait.h> #include <linux/rbtree.h> #include <linux/kthread.h> @@ -390,7 +391,6 @@ static void cgwb_release_workfn(struct work_struct *work) { struct bdi_writeback *wb = container_of(work, struct bdi_writeback, release_work); - struct blkcg *blkcg = css_to_blkcg(wb->blkcg_css); struct backing_dev_info *bdi = wb->bdi; mutex_lock(&wb->bdi->cgwb_release_mutex); @@ -401,7 +401,7 @@ static void cgwb_release_workfn(struct work_struct *work) mutex_unlock(&wb->bdi->cgwb_release_mutex); /* triggers blkg destruction if no online users left */ - blkcg_unpin_online(blkcg); + blkcg_unpin_online(wb->blkcg_css); fprop_local_destroy_percpu(&wb->memcg_completions); @@ -446,7 +446,6 @@ static int cgwb_create(struct backing_dev_info *bdi, { struct mem_cgroup *memcg; struct cgroup_subsys_state *blkcg_css; - struct blkcg *blkcg; struct list_head *memcg_cgwb_list, *blkcg_cgwb_list; struct bdi_writeback *wb; unsigned long flags; @@ -454,9 +453,8 @@ static int cgwb_create(struct backing_dev_info *bdi, memcg = mem_cgroup_from_css(memcg_css); blkcg_css = cgroup_get_e_css(memcg_css->cgroup, &io_cgrp_subsys); - blkcg = css_to_blkcg(blkcg_css); memcg_cgwb_list = &memcg->cgwb_list; - blkcg_cgwb_list = &blkcg->cgwb_list; + blkcg_cgwb_list = blkcg_get_cgwb_list(blkcg_css); /* look up again under lock and discard on blkcg mismatch */ spin_lock_irqsave(&cgwb_lock, flags); @@ -511,7 +509,7 @@ static int cgwb_create(struct backing_dev_info *bdi, list_add_tail_rcu(&wb->bdi_node, &bdi->wb_list); list_add(&wb->memcg_node, memcg_cgwb_list); list_add(&wb->blkcg_node, blkcg_cgwb_list); - blkcg_pin_online(blkcg); + blkcg_pin_online(blkcg_css); css_get(memcg_css); css_get(blkcg_css); } @@ -724,18 +722,19 @@ void wb_memcg_offline(struct mem_cgroup *memcg) /** * wb_blkcg_offline - kill all wb's associated with a blkcg being offlined - * @blkcg: blkcg being offlined + * @css: blkcg being offlined * * Also prevents creation of any new wb's associated with @blkcg. */ -void wb_blkcg_offline(struct blkcg *blkcg) +void wb_blkcg_offline(struct cgroup_subsys_state *css) { struct bdi_writeback *wb, *next; + struct list_head *list = blkcg_get_cgwb_list(css); spin_lock_irq(&cgwb_lock); - list_for_each_entry_safe(wb, next, &blkcg->cgwb_list, blkcg_node) + list_for_each_entry_safe(wb, next, list, blkcg_node) cgwb_kill(wb); - blkcg->cgwb_list.next = NULL; /* prevent new wb's */ + list->next = NULL; /* prevent new wb's */ spin_unlock_irq(&cgwb_lock); } diff --git a/mm/huge_memory.c b/mm/huge_memory.c index c468fee595ff..910a138e9859 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -2495,11 +2495,16 @@ int split_huge_page_to_list(struct page *page, struct list_head *list) struct address_space *mapping = NULL; int extra_pins, ret; pgoff_t end; + bool is_hzp; - VM_BUG_ON_PAGE(is_huge_zero_page(head), head); VM_BUG_ON_PAGE(!PageLocked(head), head); VM_BUG_ON_PAGE(!PageCompound(head), head); + is_hzp = is_huge_zero_page(head); + VM_WARN_ON_ONCE_PAGE(is_hzp, head); + if (is_hzp) + return -EBUSY; + if (PageWriteback(head)) return -EBUSY; diff --git a/mm/kfence/core.c b/mm/kfence/core.c index 9b2b5f56f4ae..11a954763be9 100644 --- a/mm/kfence/core.c +++ b/mm/kfence/core.c @@ -621,6 +621,16 @@ static bool __init kfence_init_pool_early(void) * fails for the first page, and therefore expect addr==__kfence_pool in * most failure cases. */ + for (char *p = (char *)addr; p < __kfence_pool + KFENCE_POOL_SIZE; p += PAGE_SIZE) { + struct slab *slab = virt_to_slab(p); + + if (!slab) + continue; +#ifdef CONFIG_MEMCG + slab->memcg_data = 0; +#endif + __folio_clear_slab(slab_folio(slab)); + } memblock_free_late(__pa(addr), KFENCE_POOL_SIZE - (addr - (unsigned long)__kfence_pool)); __kfence_pool = NULL; return false; diff --git a/mm/memory-failure.c b/mm/memory-failure.c index 27760c19bad7..d4a4adcca01f 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -1274,7 +1274,7 @@ try_again: } out: if (ret == -EIO) - dump_page(p, "hwpoison: unhandlable page"); + pr_err("Memory failure: %#lx: unhandlable page.\n", page_to_pfn(p)); return ret; } @@ -1861,19 +1861,6 @@ try_again: if (PageTransHuge(hpage)) { /* - * Bail out before SetPageHasHWPoisoned() if hpage is - * huge_zero_page, although PG_has_hwpoisoned is not - * checked in set_huge_zero_page(). - * - * TODO: Handle memory failure of huge_zero_page thoroughly. - */ - if (is_huge_zero_page(hpage)) { - action_result(pfn, MF_MSG_UNSPLIT_THP, MF_IGNORED); - res = -EBUSY; - goto unlock_mutex; - } - - /* * The flag must be set after the refcount is bumped * otherwise it may race with THP split. * And the flag can't be set in get_hwpoison_page() since diff --git a/mm/mremap.c b/mm/mremap.c index 303d3290b938..0b93fac76851 100644 --- a/mm/mremap.c +++ b/mm/mremap.c @@ -947,7 +947,7 @@ SYSCALL_DEFINE5(mremap, unsigned long, addr, unsigned long, old_len, return -EINTR; vma = vma_lookup(mm, addr); if (!vma) { - ret = EFAULT; + ret = -EFAULT; goto out; } diff --git a/mm/page_io.c b/mm/page_io.c index 89fbf3cae30f..3fbdab6a940e 100644 --- a/mm/page_io.c +++ b/mm/page_io.c @@ -360,7 +360,6 @@ int swap_readpage(struct page *page, bool synchronous) * attempt to access it in the page fault retry time check. */ if (synchronous) { - bio->bi_opf |= REQ_POLLED; get_task_struct(current); bio->bi_private = current; } @@ -372,8 +371,7 @@ int swap_readpage(struct page *page, bool synchronous) if (!READ_ONCE(bio->bi_private)) break; - if (!bio_poll(bio, NULL, 0)) - blk_io_schedule(); + blk_io_schedule(); } __set_current_state(TASK_RUNNING); bio_put(bio); diff --git a/mm/readahead.c b/mm/readahead.c index 4a60cdb64262..26bf74a6b2fe 100644 --- a/mm/readahead.c +++ b/mm/readahead.c @@ -113,6 +113,7 @@ * ->readpage() which may be less efficient. */ +#include <linux/blkdev.h> #include <linux/kernel.h> #include <linux/dax.h> #include <linux/gfp.h> diff --git a/mm/swapfile.c b/mm/swapfile.c index 63c61f8b2611..981a6e85c88e 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -6,6 +6,7 @@ * Swap reorganised 29.12.95, Stephen Tweedie */ +#include <linux/blkdev.h> #include <linux/mm.h> #include <linux/sched/mm.h> #include <linux/sched/task.h> @@ -179,7 +180,7 @@ static int discard_swap(struct swap_info_struct *si) nr_blocks = ((sector_t)se->nr_pages - 1) << (PAGE_SHIFT - 9); if (nr_blocks) { err = blkdev_issue_discard(si->bdev, start_block, - nr_blocks, GFP_KERNEL, 0); + nr_blocks, GFP_KERNEL); if (err) return err; cond_resched(); @@ -190,7 +191,7 @@ static int discard_swap(struct swap_info_struct *si) nr_blocks = (sector_t)se->nr_pages << (PAGE_SHIFT - 9); err = blkdev_issue_discard(si->bdev, start_block, - nr_blocks, GFP_KERNEL, 0); + nr_blocks, GFP_KERNEL); if (err) break; @@ -254,7 +255,7 @@ static void discard_swap_cluster(struct swap_info_struct *si, start_block <<= PAGE_SHIFT - 9; nr_blocks <<= PAGE_SHIFT - 9; if (blkdev_issue_discard(si->bdev, start_block, - nr_blocks, GFP_NOIO, 0)) + nr_blocks, GFP_NOIO)) break; se = next_se(se); @@ -2466,7 +2467,7 @@ SYSCALL_DEFINE1(swapoff, const char __user *, specialfile) if (p->flags & SWP_CONTINUED) free_swap_count_continuations(p); - if (!p->bdev || !blk_queue_nonrot(bdev_get_queue(p->bdev))) + if (!p->bdev || !bdev_nonrot(p->bdev)) atomic_dec(&nr_rotate_swap); mutex_lock(&swapon_mutex); @@ -2761,7 +2762,7 @@ static int claim_swapfile(struct swap_info_struct *p, struct inode *inode) * write only restriction. Hence zoned block devices are not * suitable for swapping. Disallow them here. */ - if (blk_queue_is_zoned(p->bdev->bd_disk->queue)) + if (bdev_is_zoned(p->bdev)) return -EINVAL; p->flags |= SWP_BLKDEV; } else if (S_ISREG(inode->i_mode)) { @@ -2957,20 +2958,6 @@ static int setup_swap_map_and_extents(struct swap_info_struct *p, return nr_extents; } -/* - * Helper to sys_swapon determining if a given swap - * backing device queue supports DISCARD operations. - */ -static bool swap_discardable(struct swap_info_struct *si) -{ - struct request_queue *q = bdev_get_queue(si->bdev); - - if (!blk_queue_discard(q)) - return false; - - return true; -} - SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags) { struct swap_info_struct *p; @@ -3065,13 +3052,13 @@ SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags) goto bad_swap_unlock_inode; } - if (p->bdev && blk_queue_stable_writes(p->bdev->bd_disk->queue)) + if (p->bdev && bdev_stable_writes(p->bdev)) p->flags |= SWP_STABLE_WRITES; if (p->bdev && p->bdev->bd_disk->fops->rw_page) p->flags |= SWP_SYNCHRONOUS_IO; - if (p->bdev && blk_queue_nonrot(bdev_get_queue(p->bdev))) { + if (p->bdev && bdev_nonrot(p->bdev)) { int cpu; unsigned long ci, nr_cluster; @@ -3132,7 +3119,8 @@ SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags) sizeof(long), GFP_KERNEL); - if (p->bdev && (swap_flags & SWAP_FLAG_DISCARD) && swap_discardable(p)) { + if ((swap_flags & SWAP_FLAG_DISCARD) && + p->bdev && bdev_max_discard_sectors(p->bdev)) { /* * When discard is enabled for swap with no particular * policy flagged, we set all swap discard flags here in diff --git a/net/batman-adv/fragmentation.c b/net/batman-adv/fragmentation.c index 0899a729a23f..c120c7c6d25f 100644 --- a/net/batman-adv/fragmentation.c +++ b/net/batman-adv/fragmentation.c @@ -475,6 +475,17 @@ int batadv_frag_send_packet(struct sk_buff *skb, goto free_skb; } + /* GRO might have added fragments to the fragment list instead of + * frags[]. But this is not handled by skb_split and must be + * linearized to avoid incorrect length information after all + * batman-adv fragments were created and submitted to the + * hard-interface + */ + if (skb_has_frag_list(skb) && __skb_linearize(skb)) { + ret = -ENOMEM; + goto free_skb; + } + /* Create one header to be copied to all fragments */ frag_header.packet_type = BATADV_UNICAST_FRAG; frag_header.version = BATADV_COMPAT_VERSION; diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c index b4782a6c1025..45c2dd2e1590 100644 --- a/net/bluetooth/hci_core.c +++ b/net/bluetooth/hci_core.c @@ -2555,10 +2555,10 @@ int hci_register_dev(struct hci_dev *hdev) */ switch (hdev->dev_type) { case HCI_PRIMARY: - id = ida_simple_get(&hci_index_ida, 0, 0, GFP_KERNEL); + id = ida_simple_get(&hci_index_ida, 0, HCI_MAX_ID, GFP_KERNEL); break; case HCI_AMP: - id = ida_simple_get(&hci_index_ida, 1, 0, GFP_KERNEL); + id = ida_simple_get(&hci_index_ida, 1, HCI_MAX_ID, GFP_KERNEL); break; default: return -EINVAL; @@ -2567,7 +2567,7 @@ int hci_register_dev(struct hci_dev *hdev) if (id < 0) return id; - sprintf(hdev->name, "hci%d", id); + snprintf(hdev->name, sizeof(hdev->name), "hci%d", id); hdev->id = id; BT_DBG("%p name %s bus %d", hdev, hdev->name, hdev->bus); diff --git a/net/bridge/br_input.c b/net/bridge/br_input.c index 196417859c4a..68b3e850bcb9 100644 --- a/net/bridge/br_input.c +++ b/net/bridge/br_input.c @@ -39,6 +39,13 @@ static int br_pass_frame_up(struct sk_buff *skb) dev_sw_netstats_rx_add(brdev, skb->len); vg = br_vlan_group_rcu(br); + + /* Reset the offload_fwd_mark because there could be a stacked + * bridge above, and it should not think this bridge it doing + * that bridge's work forwarding out its ports. + */ + br_switchdev_frame_unmark(skb); + /* Bridge is just like any other port. Make sure the * packet is allowed except in promisc mode when someone * may be running packet capture. diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c index 83eb97c94e83..9d82bb42e958 100644 --- a/net/ceph/osd_client.c +++ b/net/ceph/osd_client.c @@ -537,43 +537,6 @@ static void request_init(struct ceph_osd_request *req) target_init(&req->r_t); } -/* - * This is ugly, but it allows us to reuse linger registration and ping - * requests, keeping the structure of the code around send_linger{_ping}() - * reasonable. Setting up a min_nr=2 mempool for each linger request - * and dealing with copying ops (this blasts req only, watch op remains - * intact) isn't any better. - */ -static void request_reinit(struct ceph_osd_request *req) -{ - struct ceph_osd_client *osdc = req->r_osdc; - bool mempool = req->r_mempool; - unsigned int num_ops = req->r_num_ops; - u64 snapid = req->r_snapid; - struct ceph_snap_context *snapc = req->r_snapc; - bool linger = req->r_linger; - struct ceph_msg *request_msg = req->r_request; - struct ceph_msg *reply_msg = req->r_reply; - - dout("%s req %p\n", __func__, req); - WARN_ON(kref_read(&req->r_kref) != 1); - request_release_checks(req); - - WARN_ON(kref_read(&request_msg->kref) != 1); - WARN_ON(kref_read(&reply_msg->kref) != 1); - target_destroy(&req->r_t); - - request_init(req); - req->r_osdc = osdc; - req->r_mempool = mempool; - req->r_num_ops = num_ops; - req->r_snapid = snapid; - req->r_snapc = snapc; - req->r_linger = linger; - req->r_request = request_msg; - req->r_reply = reply_msg; -} - struct ceph_osd_request *ceph_osdc_alloc_request(struct ceph_osd_client *osdc, struct ceph_snap_context *snapc, unsigned int num_ops, @@ -918,14 +881,30 @@ EXPORT_SYMBOL(osd_req_op_xattr_init); * @watch_opcode: CEPH_OSD_WATCH_OP_* */ static void osd_req_op_watch_init(struct ceph_osd_request *req, int which, - u64 cookie, u8 watch_opcode) + u8 watch_opcode, u64 cookie, u32 gen) { struct ceph_osd_req_op *op; op = osd_req_op_init(req, which, CEPH_OSD_OP_WATCH, 0); op->watch.cookie = cookie; op->watch.op = watch_opcode; - op->watch.gen = 0; + op->watch.gen = gen; +} + +/* + * prot_ver, timeout and notify payload (may be empty) should already be + * encoded in @request_pl + */ +static void osd_req_op_notify_init(struct ceph_osd_request *req, int which, + u64 cookie, struct ceph_pagelist *request_pl) +{ + struct ceph_osd_req_op *op; + + op = osd_req_op_init(req, which, CEPH_OSD_OP_NOTIFY, 0); + op->notify.cookie = cookie; + + ceph_osd_data_pagelist_init(&op->notify.request_data, request_pl); + op->indata_len = request_pl->length; } /* @@ -2731,10 +2710,13 @@ static void linger_release(struct kref *kref) WARN_ON(!list_empty(&lreq->pending_lworks)); WARN_ON(lreq->osd); - if (lreq->reg_req) - ceph_osdc_put_request(lreq->reg_req); - if (lreq->ping_req) - ceph_osdc_put_request(lreq->ping_req); + if (lreq->request_pl) + ceph_pagelist_release(lreq->request_pl); + if (lreq->notify_id_pages) + ceph_release_page_vector(lreq->notify_id_pages, 1); + + ceph_osdc_put_request(lreq->reg_req); + ceph_osdc_put_request(lreq->ping_req); target_destroy(&lreq->t); kfree(lreq); } @@ -3003,6 +2985,12 @@ static void linger_commit_cb(struct ceph_osd_request *req) struct ceph_osd_linger_request *lreq = req->r_priv; mutex_lock(&lreq->lock); + if (req != lreq->reg_req) { + dout("%s lreq %p linger_id %llu unknown req (%p != %p)\n", + __func__, lreq, lreq->linger_id, req, lreq->reg_req); + goto out; + } + dout("%s lreq %p linger_id %llu result %d\n", __func__, lreq, lreq->linger_id, req->r_result); linger_reg_commit_complete(lreq, req->r_result); @@ -3026,6 +3014,7 @@ static void linger_commit_cb(struct ceph_osd_request *req) } } +out: mutex_unlock(&lreq->lock); linger_put(lreq); } @@ -3048,6 +3037,12 @@ static void linger_reconnect_cb(struct ceph_osd_request *req) struct ceph_osd_linger_request *lreq = req->r_priv; mutex_lock(&lreq->lock); + if (req != lreq->reg_req) { + dout("%s lreq %p linger_id %llu unknown req (%p != %p)\n", + __func__, lreq, lreq->linger_id, req, lreq->reg_req); + goto out; + } + dout("%s lreq %p linger_id %llu result %d last_error %d\n", __func__, lreq, lreq->linger_id, req->r_result, lreq->last_error); if (req->r_result < 0) { @@ -3057,46 +3052,64 @@ static void linger_reconnect_cb(struct ceph_osd_request *req) } } +out: mutex_unlock(&lreq->lock); linger_put(lreq); } static void send_linger(struct ceph_osd_linger_request *lreq) { - struct ceph_osd_request *req = lreq->reg_req; - struct ceph_osd_req_op *op = &req->r_ops[0]; + struct ceph_osd_client *osdc = lreq->osdc; + struct ceph_osd_request *req; + int ret; - verify_osdc_wrlocked(req->r_osdc); + verify_osdc_wrlocked(osdc); + mutex_lock(&lreq->lock); dout("%s lreq %p linger_id %llu\n", __func__, lreq, lreq->linger_id); - if (req->r_osd) - cancel_linger_request(req); + if (lreq->reg_req) { + if (lreq->reg_req->r_osd) + cancel_linger_request(lreq->reg_req); + ceph_osdc_put_request(lreq->reg_req); + } + + req = ceph_osdc_alloc_request(osdc, NULL, 1, true, GFP_NOIO); + BUG_ON(!req); - request_reinit(req); target_copy(&req->r_t, &lreq->t); req->r_mtime = lreq->mtime; - mutex_lock(&lreq->lock); if (lreq->is_watch && lreq->committed) { - WARN_ON(op->op != CEPH_OSD_OP_WATCH || - op->watch.cookie != lreq->linger_id); - op->watch.op = CEPH_OSD_WATCH_OP_RECONNECT; - op->watch.gen = ++lreq->register_gen; + osd_req_op_watch_init(req, 0, CEPH_OSD_WATCH_OP_RECONNECT, + lreq->linger_id, ++lreq->register_gen); dout("lreq %p reconnect register_gen %u\n", lreq, - op->watch.gen); + req->r_ops[0].watch.gen); req->r_callback = linger_reconnect_cb; } else { - if (!lreq->is_watch) + if (lreq->is_watch) { + osd_req_op_watch_init(req, 0, CEPH_OSD_WATCH_OP_WATCH, + lreq->linger_id, 0); + } else { lreq->notify_id = 0; - else - WARN_ON(op->watch.op != CEPH_OSD_WATCH_OP_WATCH); + + refcount_inc(&lreq->request_pl->refcnt); + osd_req_op_notify_init(req, 0, lreq->linger_id, + lreq->request_pl); + ceph_osd_data_pages_init( + osd_req_op_data(req, 0, notify, response_data), + lreq->notify_id_pages, PAGE_SIZE, 0, false, false); + } dout("lreq %p register\n", lreq); req->r_callback = linger_commit_cb; } - mutex_unlock(&lreq->lock); + + ret = ceph_osdc_alloc_messages(req, GFP_NOIO); + BUG_ON(ret); req->r_priv = linger_get(lreq); req->r_linger = true; + lreq->reg_req = req; + mutex_unlock(&lreq->lock); submit_request(req, true); } @@ -3106,6 +3119,12 @@ static void linger_ping_cb(struct ceph_osd_request *req) struct ceph_osd_linger_request *lreq = req->r_priv; mutex_lock(&lreq->lock); + if (req != lreq->ping_req) { + dout("%s lreq %p linger_id %llu unknown req (%p != %p)\n", + __func__, lreq, lreq->linger_id, req, lreq->ping_req); + goto out; + } + dout("%s lreq %p linger_id %llu result %d ping_sent %lu last_error %d\n", __func__, lreq, lreq->linger_id, req->r_result, lreq->ping_sent, lreq->last_error); @@ -3121,6 +3140,7 @@ static void linger_ping_cb(struct ceph_osd_request *req) lreq->register_gen, req->r_ops[0].watch.gen); } +out: mutex_unlock(&lreq->lock); linger_put(lreq); } @@ -3128,8 +3148,8 @@ static void linger_ping_cb(struct ceph_osd_request *req) static void send_linger_ping(struct ceph_osd_linger_request *lreq) { struct ceph_osd_client *osdc = lreq->osdc; - struct ceph_osd_request *req = lreq->ping_req; - struct ceph_osd_req_op *op = &req->r_ops[0]; + struct ceph_osd_request *req; + int ret; if (ceph_osdmap_flag(osdc, CEPH_OSDMAP_PAUSERD)) { dout("%s PAUSERD\n", __func__); @@ -3141,19 +3161,26 @@ static void send_linger_ping(struct ceph_osd_linger_request *lreq) __func__, lreq, lreq->linger_id, lreq->ping_sent, lreq->register_gen); - if (req->r_osd) - cancel_linger_request(req); + if (lreq->ping_req) { + if (lreq->ping_req->r_osd) + cancel_linger_request(lreq->ping_req); + ceph_osdc_put_request(lreq->ping_req); + } - request_reinit(req); - target_copy(&req->r_t, &lreq->t); + req = ceph_osdc_alloc_request(osdc, NULL, 1, true, GFP_NOIO); + BUG_ON(!req); - WARN_ON(op->op != CEPH_OSD_OP_WATCH || - op->watch.cookie != lreq->linger_id || - op->watch.op != CEPH_OSD_WATCH_OP_PING); - op->watch.gen = lreq->register_gen; + target_copy(&req->r_t, &lreq->t); + osd_req_op_watch_init(req, 0, CEPH_OSD_WATCH_OP_PING, lreq->linger_id, + lreq->register_gen); req->r_callback = linger_ping_cb; + + ret = ceph_osdc_alloc_messages(req, GFP_NOIO); + BUG_ON(ret); + req->r_priv = linger_get(lreq); req->r_linger = true; + lreq->ping_req = req; ceph_osdc_get_request(req); account_request(req); @@ -3169,12 +3196,6 @@ static void linger_submit(struct ceph_osd_linger_request *lreq) down_write(&osdc->lock); linger_register(lreq); - if (lreq->is_watch) { - lreq->reg_req->r_ops[0].watch.cookie = lreq->linger_id; - lreq->ping_req->r_ops[0].watch.cookie = lreq->linger_id; - } else { - lreq->reg_req->r_ops[0].notify.cookie = lreq->linger_id; - } calc_target(osdc, &lreq->t, false); osd = lookup_create_osd(osdc, lreq->t.osd, true); @@ -3206,9 +3227,9 @@ static void cancel_linger_map_check(struct ceph_osd_linger_request *lreq) */ static void __linger_cancel(struct ceph_osd_linger_request *lreq) { - if (lreq->is_watch && lreq->ping_req->r_osd) + if (lreq->ping_req && lreq->ping_req->r_osd) cancel_linger_request(lreq->ping_req); - if (lreq->reg_req->r_osd) + if (lreq->reg_req && lreq->reg_req->r_osd) cancel_linger_request(lreq->reg_req); cancel_linger_map_check(lreq); unlink_linger(lreq->osd, lreq); @@ -4570,8 +4591,13 @@ int ceph_osdc_start_request(struct ceph_osd_client *osdc, EXPORT_SYMBOL(ceph_osdc_start_request); /* - * Unregister a registered request. The request is not completed: - * ->r_result isn't set and __complete_request() isn't called. + * Unregister request. If @req was registered, it isn't completed: + * r_result isn't set and __complete_request() isn't invoked. + * + * If @req wasn't registered, this call may have raced with + * handle_reply(), in which case r_result would already be set and + * __complete_request() would be getting invoked, possibly even + * concurrently with this call. */ void ceph_osdc_cancel_request(struct ceph_osd_request *req) { @@ -4657,43 +4683,6 @@ again: } EXPORT_SYMBOL(ceph_osdc_sync); -static struct ceph_osd_request * -alloc_linger_request(struct ceph_osd_linger_request *lreq) -{ - struct ceph_osd_request *req; - - req = ceph_osdc_alloc_request(lreq->osdc, NULL, 1, false, GFP_NOIO); - if (!req) - return NULL; - - ceph_oid_copy(&req->r_base_oid, &lreq->t.base_oid); - ceph_oloc_copy(&req->r_base_oloc, &lreq->t.base_oloc); - return req; -} - -static struct ceph_osd_request * -alloc_watch_request(struct ceph_osd_linger_request *lreq, u8 watch_opcode) -{ - struct ceph_osd_request *req; - - req = alloc_linger_request(lreq); - if (!req) - return NULL; - - /* - * Pass 0 for cookie because we don't know it yet, it will be - * filled in by linger_submit(). - */ - osd_req_op_watch_init(req, 0, 0, watch_opcode); - - if (ceph_osdc_alloc_messages(req, GFP_NOIO)) { - ceph_osdc_put_request(req); - return NULL; - } - - return req; -} - /* * Returns a handle, caller owns a ref. */ @@ -4723,18 +4712,6 @@ ceph_osdc_watch(struct ceph_osd_client *osdc, lreq->t.flags = CEPH_OSD_FLAG_WRITE; ktime_get_real_ts64(&lreq->mtime); - lreq->reg_req = alloc_watch_request(lreq, CEPH_OSD_WATCH_OP_WATCH); - if (!lreq->reg_req) { - ret = -ENOMEM; - goto err_put_lreq; - } - - lreq->ping_req = alloc_watch_request(lreq, CEPH_OSD_WATCH_OP_PING); - if (!lreq->ping_req) { - ret = -ENOMEM; - goto err_put_lreq; - } - linger_submit(lreq); ret = linger_reg_commit_wait(lreq); if (ret) { @@ -4772,8 +4749,8 @@ int ceph_osdc_unwatch(struct ceph_osd_client *osdc, ceph_oloc_copy(&req->r_base_oloc, &lreq->t.base_oloc); req->r_flags = CEPH_OSD_FLAG_WRITE; ktime_get_real_ts64(&req->r_mtime); - osd_req_op_watch_init(req, 0, lreq->linger_id, - CEPH_OSD_WATCH_OP_UNWATCH); + osd_req_op_watch_init(req, 0, CEPH_OSD_WATCH_OP_UNWATCH, + lreq->linger_id, 0); ret = ceph_osdc_alloc_messages(req, GFP_NOIO); if (ret) @@ -4859,35 +4836,6 @@ out_put_req: } EXPORT_SYMBOL(ceph_osdc_notify_ack); -static int osd_req_op_notify_init(struct ceph_osd_request *req, int which, - u64 cookie, u32 prot_ver, u32 timeout, - void *payload, u32 payload_len) -{ - struct ceph_osd_req_op *op; - struct ceph_pagelist *pl; - int ret; - - op = osd_req_op_init(req, which, CEPH_OSD_OP_NOTIFY, 0); - op->notify.cookie = cookie; - - pl = ceph_pagelist_alloc(GFP_NOIO); - if (!pl) - return -ENOMEM; - - ret = ceph_pagelist_encode_32(pl, 1); /* prot_ver */ - ret |= ceph_pagelist_encode_32(pl, timeout); - ret |= ceph_pagelist_encode_32(pl, payload_len); - ret |= ceph_pagelist_append(pl, payload, payload_len); - if (ret) { - ceph_pagelist_release(pl); - return -ENOMEM; - } - - ceph_osd_data_pagelist_init(&op->notify.request_data, pl); - op->indata_len = pl->length; - return 0; -} - /* * @timeout: in seconds * @@ -4906,7 +4854,6 @@ int ceph_osdc_notify(struct ceph_osd_client *osdc, size_t *preply_len) { struct ceph_osd_linger_request *lreq; - struct page **pages; int ret; WARN_ON(!timeout); @@ -4919,41 +4866,35 @@ int ceph_osdc_notify(struct ceph_osd_client *osdc, if (!lreq) return -ENOMEM; - lreq->preply_pages = preply_pages; - lreq->preply_len = preply_len; - - ceph_oid_copy(&lreq->t.base_oid, oid); - ceph_oloc_copy(&lreq->t.base_oloc, oloc); - lreq->t.flags = CEPH_OSD_FLAG_READ; - - lreq->reg_req = alloc_linger_request(lreq); - if (!lreq->reg_req) { + lreq->request_pl = ceph_pagelist_alloc(GFP_NOIO); + if (!lreq->request_pl) { ret = -ENOMEM; goto out_put_lreq; } - /* - * Pass 0 for cookie because we don't know it yet, it will be - * filled in by linger_submit(). - */ - ret = osd_req_op_notify_init(lreq->reg_req, 0, 0, 1, timeout, - payload, payload_len); - if (ret) + ret = ceph_pagelist_encode_32(lreq->request_pl, 1); /* prot_ver */ + ret |= ceph_pagelist_encode_32(lreq->request_pl, timeout); + ret |= ceph_pagelist_encode_32(lreq->request_pl, payload_len); + ret |= ceph_pagelist_append(lreq->request_pl, payload, payload_len); + if (ret) { + ret = -ENOMEM; goto out_put_lreq; + } /* for notify_id */ - pages = ceph_alloc_page_vector(1, GFP_NOIO); - if (IS_ERR(pages)) { - ret = PTR_ERR(pages); + lreq->notify_id_pages = ceph_alloc_page_vector(1, GFP_NOIO); + if (IS_ERR(lreq->notify_id_pages)) { + ret = PTR_ERR(lreq->notify_id_pages); + lreq->notify_id_pages = NULL; goto out_put_lreq; } - ceph_osd_data_pages_init(osd_req_op_data(lreq->reg_req, 0, notify, - response_data), - pages, PAGE_SIZE, 0, false, true); - ret = ceph_osdc_alloc_messages(lreq->reg_req, GFP_NOIO); - if (ret) - goto out_put_lreq; + lreq->preply_pages = preply_pages; + lreq->preply_len = preply_len; + + ceph_oid_copy(&lreq->t.base_oid, oid); + ceph_oloc_copy(&lreq->t.base_oloc, oloc); + lreq->t.flags = CEPH_OSD_FLAG_READ; linger_submit(lreq); ret = linger_reg_commit_wait(lreq); diff --git a/net/core/dev.c b/net/core/dev.c index 1461c2d9dec8..2771fd22dc6a 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -681,11 +681,11 @@ int dev_fill_forward_path(const struct net_device *dev, const u8 *daddr, const struct net_device *last_dev; struct net_device_path_ctx ctx = { .dev = dev, - .daddr = daddr, }; struct net_device_path *path; int ret = 0; + memcpy(ctx.daddr, daddr, sizeof(ctx.daddr)); stack->num_paths = 0; while (ctx.dev && ctx.dev->netdev_ops->ndo_fill_forward_path) { last_dev = ctx.dev; diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 30b523fa4ad2..c90c74de90d5 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -3897,7 +3897,7 @@ struct sk_buff *skb_segment_list(struct sk_buff *skb, unsigned int delta_len = 0; struct sk_buff *tail = NULL; struct sk_buff *nskb, *tmp; - int err; + int len_diff, err; skb_push(skb, -skb_network_offset(skb) + offset); @@ -3937,9 +3937,11 @@ struct sk_buff *skb_segment_list(struct sk_buff *skb, skb_push(nskb, -skb_network_offset(nskb) + offset); skb_release_head_state(nskb); + len_diff = skb_network_header_len(nskb) - skb_network_header_len(skb); __copy_skb_header(nskb, skb); skb_headers_offset_update(nskb, skb_headroom(nskb) - skb_headroom(skb)); + nskb->transport_header += len_diff; skb_copy_from_linear_data_offset(skb, -tnl_hlen, nskb->data - tnl_hlen, offset + tnl_hlen); diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c index ae662567a6cb..0ea29270d7e5 100644 --- a/net/dccp/ipv4.c +++ b/net/dccp/ipv4.c @@ -1030,9 +1030,15 @@ static void __net_exit dccp_v4_exit_net(struct net *net) inet_ctl_sock_destroy(pn->v4_ctl_sk); } +static void __net_exit dccp_v4_exit_batch(struct list_head *net_exit_list) +{ + inet_twsk_purge(&dccp_hashinfo, AF_INET); +} + static struct pernet_operations dccp_v4_ops = { .init = dccp_v4_init_net, .exit = dccp_v4_exit_net, + .exit_batch = dccp_v4_exit_batch, .id = &dccp_v4_pernet_id, .size = sizeof(struct dccp_v4_pernet), }; diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c index eab3bd1ee9a0..fa663518fa0e 100644 --- a/net/dccp/ipv6.c +++ b/net/dccp/ipv6.c @@ -1115,9 +1115,15 @@ static void __net_exit dccp_v6_exit_net(struct net *net) inet_ctl_sock_destroy(pn->v6_ctl_sk); } +static void __net_exit dccp_v6_exit_batch(struct list_head *net_exit_list) +{ + inet_twsk_purge(&dccp_hashinfo, AF_INET6); +} + static struct pernet_operations dccp_v6_ops = { .init = dccp_v6_init_net, .exit = dccp_v6_exit_net, + .exit_batch = dccp_v6_exit_batch, .id = &dccp_v6_pernet_id, .size = sizeof(struct dccp_v6_pernet), }; diff --git a/net/decnet/dn_dev.c b/net/decnet/dn_dev.c index 0ee7d4c0c955..a09ba642b5e7 100644 --- a/net/decnet/dn_dev.c +++ b/net/decnet/dn_dev.c @@ -854,7 +854,7 @@ static void dn_send_endnode_hello(struct net_device *dev, struct dn_ifaddr *ifa) memcpy(msg->neighbor, dn_hiord, ETH_ALEN); if (dn_db->router) { - struct dn_neigh *dn = (struct dn_neigh *)dn_db->router; + struct dn_neigh *dn = container_of(dn_db->router, struct dn_neigh, n); dn_dn2eth(msg->neighbor, dn->addr); } @@ -902,7 +902,7 @@ static void dn_send_router_hello(struct net_device *dev, struct dn_ifaddr *ifa) { int n; struct dn_dev *dn_db = rcu_dereference_raw(dev->dn_ptr); - struct dn_neigh *dn = (struct dn_neigh *)dn_db->router; + struct dn_neigh *dn = container_of(dn_db->router, struct dn_neigh, n); struct sk_buff *skb; size_t size; unsigned char *ptr; diff --git a/net/decnet/dn_neigh.c b/net/decnet/dn_neigh.c index 94b306f6d551..fbd98ac853ea 100644 --- a/net/decnet/dn_neigh.c +++ b/net/decnet/dn_neigh.c @@ -426,7 +426,8 @@ int dn_neigh_router_hello(struct net *net, struct sock *sk, struct sk_buff *skb) if (!dn_db->router) { dn_db->router = neigh_clone(neigh); } else { - if (msg->priority > ((struct dn_neigh *)dn_db->router)->priority) + if (msg->priority > container_of(dn_db->router, + struct dn_neigh, n)->priority) neigh_release(xchg(&dn_db->router, neigh_clone(neigh))); } } diff --git a/net/decnet/dn_route.c b/net/decnet/dn_route.c index 7e85f2a1ae25..d1d78a463a06 100644 --- a/net/decnet/dn_route.c +++ b/net/decnet/dn_route.c @@ -1120,7 +1120,7 @@ source_ok: /* Ok then, we assume its directly connected and move on */ select_source: if (neigh) - gateway = ((struct dn_neigh *)neigh)->addr; + gateway = container_of(neigh, struct dn_neigh, n)->addr; if (gateway == 0) gateway = fld.daddr; if (fld.saddr == 0) { @@ -1429,7 +1429,7 @@ static int dn_route_input_slow(struct sk_buff *skb) /* Use the default router if there is one */ neigh = neigh_clone(dn_db->router); if (neigh) { - gateway = ((struct dn_neigh *)neigh)->addr; + gateway = container_of(neigh, struct dn_neigh, n)->addr; goto make_route; } diff --git a/net/dsa/port.c b/net/dsa/port.c index cdc56ba11f52..bdccb613285d 100644 --- a/net/dsa/port.c +++ b/net/dsa/port.c @@ -451,6 +451,7 @@ out_rollback_unoffload: switchdev_bridge_port_unoffload(brport_dev, dp, &dsa_slave_switchdev_notifier, &dsa_slave_switchdev_blocking_notifier); + dsa_flush_workqueue(); out_rollback_unbridge: dsa_broadcast(DSA_NOTIFIER_BRIDGE_LEAVE, &info); out_rollback: diff --git a/net/ipv4/inet_timewait_sock.c b/net/ipv4/inet_timewait_sock.c index 9e0bbd026560..0ec501845cb3 100644 --- a/net/ipv4/inet_timewait_sock.c +++ b/net/ipv4/inet_timewait_sock.c @@ -52,7 +52,8 @@ static void inet_twsk_kill(struct inet_timewait_sock *tw) spin_unlock(lock); /* Disassociate with bind bucket. */ - bhead = &hashinfo->bhash[tw->tw_bslot]; + bhead = &hashinfo->bhash[inet_bhashfn(twsk_net(tw), tw->tw_num, + hashinfo->bhash_size)]; spin_lock(&bhead->lock); inet_twsk_bind_unhash(tw, hashinfo); @@ -111,12 +112,8 @@ void inet_twsk_hashdance(struct inet_timewait_sock *tw, struct sock *sk, Note, that any socket with inet->num != 0 MUST be bound in binding cache, even if it is closed. */ - /* Cache inet_bhashfn(), because 'struct net' might be no longer - * available later in inet_twsk_kill(). - */ - tw->tw_bslot = inet_bhashfn(twsk_net(tw), inet->inet_num, - hashinfo->bhash_size); - bhead = &hashinfo->bhash[tw->tw_bslot]; + bhead = &hashinfo->bhash[inet_bhashfn(twsk_net(tw), inet->inet_num, + hashinfo->bhash_size)]; spin_lock(&bhead->lock); tw->tw_tb = icsk->icsk_bind_hash; WARN_ON(!icsk->icsk_bind_hash); @@ -257,3 +254,50 @@ void __inet_twsk_schedule(struct inet_timewait_sock *tw, int timeo, bool rearm) } } EXPORT_SYMBOL_GPL(__inet_twsk_schedule); + +void inet_twsk_purge(struct inet_hashinfo *hashinfo, int family) +{ + struct inet_timewait_sock *tw; + struct sock *sk; + struct hlist_nulls_node *node; + unsigned int slot; + + for (slot = 0; slot <= hashinfo->ehash_mask; slot++) { + struct inet_ehash_bucket *head = &hashinfo->ehash[slot]; +restart_rcu: + cond_resched(); + rcu_read_lock(); +restart: + sk_nulls_for_each_rcu(sk, node, &head->chain) { + if (sk->sk_state != TCP_TIME_WAIT) + continue; + tw = inet_twsk(sk); + if ((tw->tw_family != family) || + refcount_read(&twsk_net(tw)->ns.count)) + continue; + + if (unlikely(!refcount_inc_not_zero(&tw->tw_refcnt))) + continue; + + if (unlikely((tw->tw_family != family) || + refcount_read(&twsk_net(tw)->ns.count))) { + inet_twsk_put(tw); + goto restart; + } + + rcu_read_unlock(); + local_bh_disable(); + inet_twsk_deschedule_put(tw); + local_bh_enable(); + goto restart_rcu; + } + /* If the nulls value we got at the end of this lookup is + * not the expected one, we must restart lookup. + * We probably met an item that was moved to another chain. + */ + if (get_nulls_value(node) != slot) + goto restart; + rcu_read_unlock(); + } +} +EXPORT_SYMBOL_GPL(inet_twsk_purge); diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c index 3ee947557b88..aa9a11b20d18 100644 --- a/net/ipv4/ping.c +++ b/net/ipv4/ping.c @@ -305,6 +305,7 @@ static int ping_check_bind_addr(struct sock *sk, struct inet_sock *isk, struct net *net = sock_net(sk); if (sk->sk_family == AF_INET) { struct sockaddr_in *addr = (struct sockaddr_in *) uaddr; + u32 tb_id = RT_TABLE_LOCAL; int chk_addr_ret; if (addr_len < sizeof(*addr)) @@ -318,7 +319,8 @@ static int ping_check_bind_addr(struct sock *sk, struct inet_sock *isk, pr_debug("ping_check_bind_addr(sk=%p,addr=%pI4,port=%d)\n", sk, &addr->sin_addr.s_addr, ntohs(addr->sin_port)); - chk_addr_ret = inet_addr_type(net, addr->sin_addr.s_addr); + tb_id = l3mdev_fib_table_by_index(net, sk->sk_bound_dev_if) ? : tb_id; + chk_addr_ret = inet_addr_type_table(net, addr->sin_addr.s_addr, tb_id); if (!inet_addr_valid_or_nonlocal(net, inet_sk(sk), addr->sin_addr.s_addr, @@ -355,6 +357,14 @@ static int ping_check_bind_addr(struct sock *sk, struct inet_sock *isk, return -ENODEV; } } + + if (!dev && sk->sk_bound_dev_if) { + dev = dev_get_by_index_rcu(net, sk->sk_bound_dev_if); + if (!dev) { + rcu_read_unlock(); + return -ENODEV; + } + } has_addr = pingv6_ops.ipv6_chk_addr(net, &addr->sin6_addr, dev, scoped); rcu_read_unlock(); diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 98c6f3429593..ed01063d8f30 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -1726,6 +1726,7 @@ static int ip_route_input_mc(struct sk_buff *skb, __be32 daddr, __be32 saddr, struct in_device *in_dev = __in_dev_get_rcu(dev); unsigned int flags = RTCF_MULTICAST; struct rtable *rth; + bool no_policy; u32 itag = 0; int err; @@ -1736,8 +1737,12 @@ static int ip_route_input_mc(struct sk_buff *skb, __be32 daddr, __be32 saddr, if (our) flags |= RTCF_LOCAL; + no_policy = IN_DEV_ORCONF(in_dev, NOPOLICY); + if (no_policy) + IPCB(skb)->flags |= IPSKB_NOPOLICY; + rth = rt_dst_alloc(dev_net(dev)->loopback_dev, flags, RTN_MULTICAST, - IN_DEV_ORCONF(in_dev, NOPOLICY), false); + no_policy, false); if (!rth) return -ENOBUFS; @@ -1753,6 +1758,7 @@ static int ip_route_input_mc(struct sk_buff *skb, __be32 daddr, __be32 saddr, #endif RT_CACHE_STAT_INC(in_slow_mc); + skb_dst_drop(skb); skb_dst_set(skb, &rth->dst); return 0; } @@ -1795,7 +1801,7 @@ static int __mkroute_input(struct sk_buff *skb, struct rtable *rth; int err; struct in_device *out_dev; - bool do_cache; + bool do_cache, no_policy; u32 itag = 0; /* get a working reference to the output device */ @@ -1840,6 +1846,10 @@ static int __mkroute_input(struct sk_buff *skb, } } + no_policy = IN_DEV_ORCONF(in_dev, NOPOLICY); + if (no_policy) + IPCB(skb)->flags |= IPSKB_NOPOLICY; + fnhe = find_exception(nhc, daddr); if (do_cache) { if (fnhe) @@ -1852,8 +1862,7 @@ static int __mkroute_input(struct sk_buff *skb, } } - rth = rt_dst_alloc(out_dev->dev, 0, res->type, - IN_DEV_ORCONF(in_dev, NOPOLICY), + rth = rt_dst_alloc(out_dev->dev, 0, res->type, no_policy, IN_DEV_ORCONF(out_dev, NOXFRM)); if (!rth) { err = -ENOBUFS; @@ -2228,6 +2237,7 @@ static int ip_route_input_slow(struct sk_buff *skb, __be32 daddr, __be32 saddr, struct rtable *rth; struct flowi4 fl4; bool do_cache = true; + bool no_policy; /* IP on this device is disabled. */ @@ -2346,6 +2356,10 @@ brd_input: RT_CACHE_STAT_INC(in_brd); local_input: + no_policy = IN_DEV_ORCONF(in_dev, NOPOLICY); + if (no_policy) + IPCB(skb)->flags |= IPSKB_NOPOLICY; + do_cache &= res->fi && !itag; if (do_cache) { struct fib_nh_common *nhc = FIB_RES_NHC(*res); @@ -2360,7 +2374,7 @@ local_input: rth = rt_dst_alloc(ip_rt_get_dev(net, res), flags | RTCF_LOCAL, res->type, - IN_DEV_ORCONF(in_dev, NOPOLICY), false); + no_policy, false); if (!rth) goto e_nobufs; diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index cf18fbcbf123..bb7ef45408e1 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -2335,8 +2335,10 @@ static int tcp_recvmsg_locked(struct sock *sk, struct msghdr *msg, size_t len, if (sk->sk_state == TCP_LISTEN) goto out; - if (tp->recvmsg_inq) + if (tp->recvmsg_inq) { *cmsg_flags = TCP_CMSG_INQ; + msg->msg_get_inq = 1; + } timeo = sock_rcvtimeo(sk, nonblock); /* Urgent data needs to be handled specially. */ @@ -2559,7 +2561,7 @@ recv_sndq: int tcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int nonblock, int flags, int *addr_len) { - int cmsg_flags = 0, ret, inq; + int cmsg_flags = 0, ret; struct scm_timestamping_internal tss; if (unlikely(flags & MSG_ERRQUEUE)) @@ -2576,12 +2578,14 @@ int tcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int nonblock, release_sock(sk); sk_defer_free_flush(sk); - if (cmsg_flags && ret >= 0) { + if ((cmsg_flags || msg->msg_get_inq) && ret >= 0) { if (cmsg_flags & TCP_CMSG_TS) tcp_recv_timestamp(msg, sk, &tss); - if (cmsg_flags & TCP_CMSG_INQ) { - inq = tcp_inq_hint(sk); - put_cmsg(msg, SOL_TCP, TCP_CM_INQ, sizeof(inq), &inq); + if (msg->msg_get_inq) { + msg->msg_inq = tcp_inq_hint(sk); + if (cmsg_flags & TCP_CMSG_INQ) + put_cmsg(msg, SOL_TCP, TCP_CM_INQ, + sizeof(msg->msg_inq), &msg->msg_inq); } } return ret; diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index f9cec624068d..457f5b5d5d4a 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -3173,6 +3173,8 @@ static void __net_exit tcp_sk_exit_batch(struct list_head *net_exit_list) { struct net *net; + inet_twsk_purge(&tcp_hashinfo, AF_INET); + list_for_each_entry(net, net_exit_list, exit_list) tcp_fastopen_ctx_destroy(net); } diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 13678d3908fa..faaddaf43c90 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -2207,9 +2207,15 @@ static void __net_exit tcpv6_net_exit(struct net *net) inet_ctl_sock_destroy(net->ipv6.tcp_sk); } +static void __net_exit tcpv6_net_exit_batch(struct list_head *net_exit_list) +{ + inet_twsk_purge(&tcp_hashinfo, AF_INET6); +} + static struct pernet_operations tcpv6_net_ops = { .init = tcpv6_net_init, .exit = tcpv6_net_exit, + .exit_batch = tcpv6_net_exit_batch, }; int __init tcpv6_init(void) diff --git a/net/key/af_key.c b/net/key/af_key.c index fd51db3be91c..339d95df19d3 100644 --- a/net/key/af_key.c +++ b/net/key/af_key.c @@ -2826,8 +2826,10 @@ static int pfkey_process(struct sock *sk, struct sk_buff *skb, const struct sadb void *ext_hdrs[SADB_EXT_MAX]; int err; - pfkey_broadcast(skb_clone(skb, GFP_KERNEL), GFP_KERNEL, - BROADCAST_PROMISC_ONLY, NULL, sock_net(sk)); + err = pfkey_broadcast(skb_clone(skb, GFP_KERNEL), GFP_KERNEL, + BROADCAST_PROMISC_ONLY, NULL, sock_net(sk)); + if (err) + return err; memset(ext_hdrs, 0, sizeof(ext_hdrs)); err = parse_exthdrs(skb, hdr, ext_hdrs); @@ -2898,7 +2900,7 @@ static int count_ah_combs(const struct xfrm_tmpl *t) break; if (!aalg->pfkey_supported) continue; - if (aalg_tmpl_set(t, aalg)) + if (aalg_tmpl_set(t, aalg) && aalg->available) sz += sizeof(struct sadb_comb); } return sz + sizeof(struct sadb_prop); @@ -2916,7 +2918,7 @@ static int count_esp_combs(const struct xfrm_tmpl *t) if (!ealg->pfkey_supported) continue; - if (!(ealg_tmpl_set(t, ealg))) + if (!(ealg_tmpl_set(t, ealg) && ealg->available)) continue; for (k = 1; ; k++) { @@ -2927,7 +2929,7 @@ static int count_esp_combs(const struct xfrm_tmpl *t) if (!aalg->pfkey_supported) continue; - if (aalg_tmpl_set(t, aalg)) + if (aalg_tmpl_set(t, aalg) && aalg->available) sz += sizeof(struct sadb_comb); } } diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c index 1b30c724ca8d..dc8aec1a5d3d 100644 --- a/net/mac80211/mlme.c +++ b/net/mac80211/mlme.c @@ -3657,6 +3657,12 @@ static bool ieee80211_assoc_success(struct ieee80211_sub_if_data *sdata, cbss->transmitted_bss->bssid); bss_conf->bssid_indicator = cbss->max_bssid_indicator; bss_conf->bssid_index = cbss->bssid_index; + } else { + bss_conf->nontransmitted = false; + memset(bss_conf->transmitter_bssid, 0, + sizeof(bss_conf->transmitter_bssid)); + bss_conf->bssid_indicator = 0; + bss_conf->bssid_index = 0; } /* diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c index beb6b92eb780..88d797fa82ff 100644 --- a/net/mac80211/rx.c +++ b/net/mac80211/rx.c @@ -1405,8 +1405,7 @@ static void ieee80211_rx_reorder_ampdu(struct ieee80211_rx_data *rx, goto dont_reorder; /* not part of a BA session */ - if (ack_policy != IEEE80211_QOS_CTL_ACK_POLICY_BLOCKACK && - ack_policy != IEEE80211_QOS_CTL_ACK_POLICY_NORMAL) + if (ack_policy == IEEE80211_QOS_CTL_ACK_POLICY_NOACK) goto dont_reorder; /* new, potentially un-ordered, ampdu frame - process it */ diff --git a/net/mptcp/options.c b/net/mptcp/options.c index 325383646f5c..b548cec86c9d 100644 --- a/net/mptcp/options.c +++ b/net/mptcp/options.c @@ -107,7 +107,7 @@ static void mptcp_parse_option(const struct sk_buff *skb, ptr += 2; } if (opsize == TCPOLEN_MPTCP_MPC_ACK_DATA_CSUM) { - mp_opt->csum = (__force __sum16)get_unaligned_be16(ptr); + mp_opt->csum = get_unaligned((__force __sum16 *)ptr); mp_opt->suboptions |= OPTION_MPTCP_CSUMREQD; ptr += 2; } @@ -221,7 +221,7 @@ static void mptcp_parse_option(const struct sk_buff *skb, if (opsize == expected_opsize + TCPOLEN_MPTCP_DSS_CHECKSUM) { mp_opt->suboptions |= OPTION_MPTCP_CSUMREQD; - mp_opt->csum = (__force __sum16)get_unaligned_be16(ptr); + mp_opt->csum = get_unaligned((__force __sum16 *)ptr); ptr += 2; } @@ -1240,7 +1240,7 @@ static void mptcp_set_rwin(const struct tcp_sock *tp) WRITE_ONCE(msk->rcv_wnd_sent, ack_seq); } -u16 __mptcp_make_csum(u64 data_seq, u32 subflow_seq, u16 data_len, __wsum sum) +__sum16 __mptcp_make_csum(u64 data_seq, u32 subflow_seq, u16 data_len, __wsum sum) { struct csum_pseudo_header header; __wsum csum; @@ -1256,15 +1256,25 @@ u16 __mptcp_make_csum(u64 data_seq, u32 subflow_seq, u16 data_len, __wsum sum) header.csum = 0; csum = csum_partial(&header, sizeof(header), sum); - return (__force u16)csum_fold(csum); + return csum_fold(csum); } -static u16 mptcp_make_csum(const struct mptcp_ext *mpext) +static __sum16 mptcp_make_csum(const struct mptcp_ext *mpext) { return __mptcp_make_csum(mpext->data_seq, mpext->subflow_seq, mpext->data_len, ~csum_unfold(mpext->csum)); } +static void put_len_csum(u16 len, __sum16 csum, void *data) +{ + __sum16 *sumptr = data + 2; + __be16 *ptr = data; + + put_unaligned_be16(len, ptr); + + put_unaligned(csum, sumptr); +} + void mptcp_write_options(__be32 *ptr, const struct tcp_sock *tp, struct mptcp_out_options *opts) { @@ -1340,8 +1350,9 @@ void mptcp_write_options(__be32 *ptr, const struct tcp_sock *tp, put_unaligned_be32(mpext->subflow_seq, ptr); ptr += 1; if (opts->csum_reqd) { - put_unaligned_be32(mpext->data_len << 16 | - mptcp_make_csum(mpext), ptr); + put_len_csum(mpext->data_len, + mptcp_make_csum(mpext), + ptr); } else { put_unaligned_be32(mpext->data_len << 16 | TCPOPT_NOP << 8 | TCPOPT_NOP, ptr); @@ -1392,11 +1403,12 @@ void mptcp_write_options(__be32 *ptr, const struct tcp_sock *tp, goto mp_capable_done; if (opts->csum_reqd) { - put_unaligned_be32(opts->data_len << 16 | - __mptcp_make_csum(opts->data_seq, - opts->subflow_seq, - opts->data_len, - ~csum_unfold(opts->csum)), ptr); + put_len_csum(opts->data_len, + __mptcp_make_csum(opts->data_seq, + opts->subflow_seq, + opts->data_len, + ~csum_unfold(opts->csum)), + ptr); } else { put_unaligned_be32(opts->data_len << 16 | TCPOPT_NOP << 8 | TCPOPT_NOP, ptr); diff --git a/net/mptcp/pm.c b/net/mptcp/pm.c index 01809eef29b4..aa51b100e033 100644 --- a/net/mptcp/pm.c +++ b/net/mptcp/pm.c @@ -178,14 +178,13 @@ void mptcp_pm_subflow_check_next(struct mptcp_sock *msk, const struct sock *ssk, struct mptcp_pm_data *pm = &msk->pm; bool update_subflows; - update_subflows = (ssk->sk_state == TCP_CLOSE) && - (subflow->request_join || subflow->mp_join); + update_subflows = subflow->request_join || subflow->mp_join; if (!READ_ONCE(pm->work_pending) && !update_subflows) return; spin_lock_bh(&pm->lock); if (update_subflows) - pm->subflows--; + __mptcp_pm_close_subflow(msk); /* Even if this subflow is not really established, tell the PM to try * to pick the next ones, if possible. diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h index 3c1a3036550f..5655a63aa6a8 100644 --- a/net/mptcp/protocol.h +++ b/net/mptcp/protocol.h @@ -443,7 +443,8 @@ struct mptcp_subflow_context { can_ack : 1, /* only after processing the remote a key */ disposable : 1, /* ctx can be free at ulp release time */ stale : 1, /* unable to snd/rcv data, do not use for xmit */ - local_id_valid : 1; /* local_id is correctly initialized */ + local_id_valid : 1, /* local_id is correctly initialized */ + valid_csum_seen : 1; /* at least one csum validated */ enum mptcp_data_avail data_avail; u32 remote_nonce; u64 thmac; @@ -723,7 +724,7 @@ void mptcp_token_destroy(struct mptcp_sock *msk); void mptcp_crypto_key_sha(u64 key, u32 *token, u64 *idsn); void mptcp_crypto_hmac_sha(u64 key1, u64 key2, u8 *msg, int len, void *hmac); -u16 __mptcp_make_csum(u64 data_seq, u32 subflow_seq, u16 data_len, __wsum sum); +__sum16 __mptcp_make_csum(u64 data_seq, u32 subflow_seq, u16 data_len, __wsum sum); void __init mptcp_pm_init(void); void mptcp_pm_data_init(struct mptcp_sock *msk); @@ -833,6 +834,20 @@ unsigned int mptcp_pm_get_add_addr_accept_max(const struct mptcp_sock *msk); unsigned int mptcp_pm_get_subflows_max(const struct mptcp_sock *msk); unsigned int mptcp_pm_get_local_addr_max(const struct mptcp_sock *msk); +/* called under PM lock */ +static inline void __mptcp_pm_close_subflow(struct mptcp_sock *msk) +{ + if (--msk->pm.subflows < mptcp_pm_get_subflows_max(msk)) + WRITE_ONCE(msk->pm.accept_subflow, true); +} + +static inline void mptcp_pm_close_subflow(struct mptcp_sock *msk) +{ + spin_lock_bh(&msk->pm.lock); + __mptcp_pm_close_subflow(msk); + spin_unlock_bh(&msk->pm.lock); +} + void mptcp_sockopt_sync(struct mptcp_sock *msk, struct sock *ssk); void mptcp_sockopt_sync_locked(struct mptcp_sock *msk, struct sock *ssk); diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c index aba260f547da..be76ada89d96 100644 --- a/net/mptcp/subflow.c +++ b/net/mptcp/subflow.c @@ -888,7 +888,7 @@ static enum mapping_status validate_data_csum(struct sock *ssk, struct sk_buff * { struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk); u32 offset, seq, delta; - u16 csum; + __sum16 csum; int len; if (!csum_reqd) @@ -955,11 +955,14 @@ static enum mapping_status validate_data_csum(struct sock *ssk, struct sk_buff * subflow->map_data_csum); if (unlikely(csum)) { MPTCP_INC_STATS(sock_net(ssk), MPTCP_MIB_DATACSUMERR); - subflow->send_mp_fail = 1; - MPTCP_INC_STATS(sock_net(ssk), MPTCP_MIB_MPFAILTX); + if (subflow->mp_join || subflow->valid_csum_seen) { + subflow->send_mp_fail = 1; + MPTCP_INC_STATS(sock_net(ssk), MPTCP_MIB_MPFAILTX); + } return subflow->mp_join ? MAPPING_INVALID : MAPPING_DUMMY; } + subflow->valid_csum_seen = 1; return MAPPING_OK; } @@ -1141,6 +1144,18 @@ static void subflow_sched_work_if_closed(struct mptcp_sock *msk, struct sock *ss } } +static bool subflow_can_fallback(struct mptcp_subflow_context *subflow) +{ + struct mptcp_sock *msk = mptcp_sk(subflow->conn); + + if (subflow->mp_join) + return false; + else if (READ_ONCE(msk->csum_enabled)) + return !subflow->valid_csum_seen; + else + return !subflow->fully_established; +} + static bool subflow_check_data_avail(struct sock *ssk) { struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk); @@ -1218,7 +1233,7 @@ fallback: return true; } - if (subflow->mp_join || subflow->fully_established) { + if (!subflow_can_fallback(subflow)) { /* fatal protocol error, close the socket. * subflow_error_report() will introduce the appropriate barriers */ @@ -1422,20 +1437,20 @@ int __mptcp_subflow_connect(struct sock *sk, const struct mptcp_addr_info *loc, struct sockaddr_storage addr; int remote_id = remote->id; int local_id = loc->id; + int err = -ENOTCONN; struct socket *sf; struct sock *ssk; u32 remote_token; int addrlen; int ifindex; u8 flags; - int err; if (!mptcp_is_fully_established(sk)) - return -ENOTCONN; + goto err_out; err = mptcp_subflow_create_socket(sk, &sf); if (err) - return err; + goto err_out; ssk = sf->sk; subflow = mptcp_subflow_ctx(ssk); @@ -1492,6 +1507,12 @@ failed_unlink: failed: subflow->disposable = 1; sock_release(sf); + +err_out: + /* we account subflows before the creation, and this failures will not + * be caught by sk_state_change() + */ + mptcp_pm_close_subflow(msk); return err; } diff --git a/net/netfilter/nf_flow_table_core.c b/net/netfilter/nf_flow_table_core.c index 3db256da919b..f2def06d1070 100644 --- a/net/netfilter/nf_flow_table_core.c +++ b/net/netfilter/nf_flow_table_core.c @@ -179,12 +179,11 @@ EXPORT_SYMBOL_GPL(flow_offload_route_init); static void flow_offload_fixup_tcp(struct ip_ct_tcp *tcp) { - tcp->state = TCP_CONNTRACK_ESTABLISHED; tcp->seen[0].td_maxwin = 0; tcp->seen[1].td_maxwin = 0; } -static void flow_offload_fixup_ct_timeout(struct nf_conn *ct) +static void flow_offload_fixup_ct(struct nf_conn *ct) { struct net *net = nf_ct_net(ct); int l4num = nf_ct_protonum(ct); @@ -193,7 +192,9 @@ static void flow_offload_fixup_ct_timeout(struct nf_conn *ct) if (l4num == IPPROTO_TCP) { struct nf_tcp_net *tn = nf_tcp_pernet(net); - timeout = tn->timeouts[TCP_CONNTRACK_ESTABLISHED]; + flow_offload_fixup_tcp(&ct->proto.tcp); + + timeout = tn->timeouts[ct->proto.tcp.state]; timeout -= tn->offload_timeout; } else if (l4num == IPPROTO_UDP) { struct nf_udp_net *tn = nf_udp_pernet(net); @@ -211,18 +212,6 @@ static void flow_offload_fixup_ct_timeout(struct nf_conn *ct) WRITE_ONCE(ct->timeout, nfct_time_stamp + timeout); } -static void flow_offload_fixup_ct_state(struct nf_conn *ct) -{ - if (nf_ct_protonum(ct) == IPPROTO_TCP) - flow_offload_fixup_tcp(&ct->proto.tcp); -} - -static void flow_offload_fixup_ct(struct nf_conn *ct) -{ - flow_offload_fixup_ct_state(ct); - flow_offload_fixup_ct_timeout(ct); -} - static void flow_offload_route_release(struct flow_offload *flow) { nft_flow_dst_release(flow, FLOW_OFFLOAD_DIR_ORIGINAL); @@ -335,8 +324,10 @@ void flow_offload_refresh(struct nf_flowtable *flow_table, u32 timeout; timeout = nf_flowtable_time_stamp + flow_offload_get_timeout(flow); - if (READ_ONCE(flow->timeout) != timeout) + if (timeout - READ_ONCE(flow->timeout) > HZ) WRITE_ONCE(flow->timeout, timeout); + else + return; if (likely(!nf_flowtable_hw_offload(flow_table))) return; @@ -359,22 +350,14 @@ static void flow_offload_del(struct nf_flowtable *flow_table, rhashtable_remove_fast(&flow_table->rhashtable, &flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].node, nf_flow_offload_rhash_params); - - clear_bit(IPS_OFFLOAD_BIT, &flow->ct->status); - - if (nf_flow_has_expired(flow)) - flow_offload_fixup_ct(flow->ct); - else - flow_offload_fixup_ct_timeout(flow->ct); - flow_offload_free(flow); } void flow_offload_teardown(struct flow_offload *flow) { + clear_bit(IPS_OFFLOAD_BIT, &flow->ct->status); set_bit(NF_FLOW_TEARDOWN, &flow->flags); - - flow_offload_fixup_ct_state(flow->ct); + flow_offload_fixup_ct(flow->ct); } EXPORT_SYMBOL_GPL(flow_offload_teardown); @@ -438,33 +421,12 @@ nf_flow_table_iterate(struct nf_flowtable *flow_table, return err; } -static bool flow_offload_stale_dst(struct flow_offload_tuple *tuple) -{ - struct dst_entry *dst; - - if (tuple->xmit_type == FLOW_OFFLOAD_XMIT_NEIGH || - tuple->xmit_type == FLOW_OFFLOAD_XMIT_XFRM) { - dst = tuple->dst_cache; - if (!dst_check(dst, tuple->dst_cookie)) - return true; - } - - return false; -} - -static bool nf_flow_has_stale_dst(struct flow_offload *flow) -{ - return flow_offload_stale_dst(&flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple) || - flow_offload_stale_dst(&flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].tuple); -} - static void nf_flow_offload_gc_step(struct nf_flowtable *flow_table, struct flow_offload *flow, void *data) { if (nf_flow_has_expired(flow) || - nf_ct_is_dying(flow->ct) || - nf_flow_has_stale_dst(flow)) - set_bit(NF_FLOW_TEARDOWN, &flow->flags); + nf_ct_is_dying(flow->ct)) + flow_offload_teardown(flow); if (test_bit(NF_FLOW_TEARDOWN, &flow->flags)) { if (test_bit(NF_FLOW_HW, &flow->flags)) { diff --git a/net/netfilter/nf_flow_table_ip.c b/net/netfilter/nf_flow_table_ip.c index 32c0eb1b4821..b350fe9d00b0 100644 --- a/net/netfilter/nf_flow_table_ip.c +++ b/net/netfilter/nf_flow_table_ip.c @@ -248,6 +248,15 @@ static bool nf_flow_exceeds_mtu(const struct sk_buff *skb, unsigned int mtu) return true; } +static inline bool nf_flow_dst_check(struct flow_offload_tuple *tuple) +{ + if (tuple->xmit_type != FLOW_OFFLOAD_XMIT_NEIGH && + tuple->xmit_type != FLOW_OFFLOAD_XMIT_XFRM) + return true; + + return dst_check(tuple->dst_cache, tuple->dst_cookie); +} + static unsigned int nf_flow_xmit_xfrm(struct sk_buff *skb, const struct nf_hook_state *state, struct dst_entry *dst) @@ -367,6 +376,11 @@ nf_flow_offload_ip_hook(void *priv, struct sk_buff *skb, if (nf_flow_state_check(flow, iph->protocol, skb, thoff)) return NF_ACCEPT; + if (!nf_flow_dst_check(&tuplehash->tuple)) { + flow_offload_teardown(flow); + return NF_ACCEPT; + } + if (skb_try_make_writable(skb, thoff + hdrsize)) return NF_DROP; @@ -624,6 +638,11 @@ nf_flow_offload_ipv6_hook(void *priv, struct sk_buff *skb, if (nf_flow_state_check(flow, ip6h->nexthdr, skb, thoff)) return NF_ACCEPT; + if (!nf_flow_dst_check(&tuplehash->tuple)) { + flow_offload_teardown(flow); + return NF_ACCEPT; + } + if (skb_try_make_writable(skb, thoff + hdrsize)) return NF_DROP; diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 16c3a39689f4..a096b9fbbbdf 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -8342,16 +8342,7 @@ EXPORT_SYMBOL_GPL(nf_tables_trans_destroy_flush_work); static bool nft_expr_reduce(struct nft_regs_track *track, const struct nft_expr *expr) { - if (!expr->ops->reduce) { - pr_warn_once("missing reduce for expression %s ", - expr->ops->type->name); - return false; - } - - if (nft_reduce_is_readonly(expr)) - return false; - - return expr->ops->reduce(track, expr); + return false; } static int nf_tables_commit_chain_prepare(struct net *net, struct nft_chain *chain) diff --git a/net/netfilter/nft_flow_offload.c b/net/netfilter/nft_flow_offload.c index 900d48c810a1..6f0b07fe648d 100644 --- a/net/netfilter/nft_flow_offload.c +++ b/net/netfilter/nft_flow_offload.c @@ -36,6 +36,15 @@ static void nft_default_forward_path(struct nf_flow_route *route, route->tuple[dir].xmit_type = nft_xmit_type(dst_cache); } +static bool nft_is_valid_ether_device(const struct net_device *dev) +{ + if (!dev || (dev->flags & IFF_LOOPBACK) || dev->type != ARPHRD_ETHER || + dev->addr_len != ETH_ALEN || !is_valid_ether_addr(dev->dev_addr)) + return false; + + return true; +} + static int nft_dev_fill_forward_path(const struct nf_flow_route *route, const struct dst_entry *dst_cache, const struct nf_conn *ct, @@ -47,6 +56,9 @@ static int nft_dev_fill_forward_path(const struct nf_flow_route *route, struct neighbour *n; u8 nud_state; + if (!nft_is_valid_ether_device(dev)) + goto out; + n = dst_neigh_lookup(dst_cache, daddr); if (!n) return -1; @@ -60,6 +72,7 @@ static int nft_dev_fill_forward_path(const struct nf_flow_route *route, if (!(nud_state & NUD_VALID)) return -1; +out: return dev_fill_forward_path(dev, ha, stack); } @@ -78,15 +91,6 @@ struct nft_forward_info { enum flow_offload_xmit_type xmit_type; }; -static bool nft_is_valid_ether_device(const struct net_device *dev) -{ - if (!dev || (dev->flags & IFF_LOOPBACK) || dev->type != ARPHRD_ETHER || - dev->addr_len != ETH_ALEN || !is_valid_ether_addr(dev->dev_addr)) - return false; - - return true; -} - static void nft_dev_path_info(const struct net_device_path_stack *stack, struct nft_forward_info *info, unsigned char *ha, struct nf_flowtable *flowtable) @@ -119,7 +123,8 @@ static void nft_dev_path_info(const struct net_device_path_stack *stack, info->indev = NULL; break; } - info->outdev = path->dev; + if (!info->outdev) + info->outdev = path->dev; info->encap[info->num_encaps].id = path->encap.id; info->encap[info->num_encaps].proto = path->encap.proto; info->num_encaps++; @@ -293,7 +298,8 @@ static void nft_flow_offload_eval(const struct nft_expr *expr, case IPPROTO_TCP: tcph = skb_header_pointer(pkt->skb, nft_thoff(pkt), sizeof(_tcph), &_tcph); - if (unlikely(!tcph || tcph->fin || tcph->rst)) + if (unlikely(!tcph || tcph->fin || tcph->rst || + !nf_conntrack_tcp_established(ct))) goto out; break; case IPPROTO_UDP: diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index 05a3795eac8e..73e9c0a9c187 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -1975,7 +1975,6 @@ static int netlink_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, copied = len; } - skb_reset_transport_header(data_skb); err = skb_copy_datagram_msg(data_skb, 0, msg, copied); if (msg->msg_name) { diff --git a/net/nfc/nci/data.c b/net/nfc/nci/data.c index 6055dc9a82aa..aa5e712adf07 100644 --- a/net/nfc/nci/data.c +++ b/net/nfc/nci/data.c @@ -118,7 +118,7 @@ static int nci_queue_tx_data_frags(struct nci_dev *ndev, skb_frag = nci_skb_alloc(ndev, (NCI_DATA_HDR_SIZE + frag_len), - GFP_KERNEL); + GFP_ATOMIC); if (skb_frag == NULL) { rc = -ENOMEM; goto free_exit; diff --git a/net/nfc/nci/hci.c b/net/nfc/nci/hci.c index 19703a649b5a..78c4b6addf15 100644 --- a/net/nfc/nci/hci.c +++ b/net/nfc/nci/hci.c @@ -153,7 +153,7 @@ static int nci_hci_send_data(struct nci_dev *ndev, u8 pipe, i = 0; skb = nci_skb_alloc(ndev, conn_info->max_pkt_payload_len + - NCI_DATA_HDR_SIZE, GFP_KERNEL); + NCI_DATA_HDR_SIZE, GFP_ATOMIC); if (!skb) return -ENOMEM; @@ -184,7 +184,7 @@ static int nci_hci_send_data(struct nci_dev *ndev, u8 pipe, if (i < data_len) { skb = nci_skb_alloc(ndev, conn_info->max_pkt_payload_len + - NCI_DATA_HDR_SIZE, GFP_KERNEL); + NCI_DATA_HDR_SIZE, GFP_ATOMIC); if (!skb) return -ENOMEM; diff --git a/net/rds/tcp.c b/net/rds/tcp.c index 2f638f8b7b1e..73ee2771093d 100644 --- a/net/rds/tcp.c +++ b/net/rds/tcp.c @@ -487,11 +487,11 @@ struct rds_tcp_net { /* All module specific customizations to the RDS-TCP socket should be done in * rds_tcp_tune() and applied after socket creation. */ -void rds_tcp_tune(struct socket *sock) +bool rds_tcp_tune(struct socket *sock) { struct sock *sk = sock->sk; struct net *net = sock_net(sk); - struct rds_tcp_net *rtn = net_generic(net, rds_tcp_netid); + struct rds_tcp_net *rtn; tcp_sock_set_nodelay(sock->sk); lock_sock(sk); @@ -499,10 +499,15 @@ void rds_tcp_tune(struct socket *sock) * a process which created this net namespace terminated. */ if (!sk->sk_net_refcnt) { + if (!maybe_get_net(net)) { + release_sock(sk); + return false; + } sk->sk_net_refcnt = 1; - get_net_track(net, &sk->ns_tracker, GFP_KERNEL); + netns_tracker_alloc(net, &sk->ns_tracker, GFP_KERNEL); sock_inuse_add(net, 1); } + rtn = net_generic(net, rds_tcp_netid); if (rtn->sndbuf_size > 0) { sk->sk_sndbuf = rtn->sndbuf_size; sk->sk_userlocks |= SOCK_SNDBUF_LOCK; @@ -512,6 +517,7 @@ void rds_tcp_tune(struct socket *sock) sk->sk_userlocks |= SOCK_RCVBUF_LOCK; } release_sock(sk); + return true; } static void rds_tcp_accept_worker(struct work_struct *work) diff --git a/net/rds/tcp.h b/net/rds/tcp.h index dc8d745d6857..f8b5930d7b34 100644 --- a/net/rds/tcp.h +++ b/net/rds/tcp.h @@ -49,7 +49,7 @@ struct rds_tcp_statistics { }; /* tcp.c */ -void rds_tcp_tune(struct socket *sock); +bool rds_tcp_tune(struct socket *sock); void rds_tcp_set_callbacks(struct socket *sock, struct rds_conn_path *cp); void rds_tcp_reset_callbacks(struct socket *sock, struct rds_conn_path *cp); void rds_tcp_restore_callbacks(struct socket *sock, diff --git a/net/rds/tcp_connect.c b/net/rds/tcp_connect.c index 5461d77fff4f..f0c477c5d1db 100644 --- a/net/rds/tcp_connect.c +++ b/net/rds/tcp_connect.c @@ -124,7 +124,10 @@ int rds_tcp_conn_path_connect(struct rds_conn_path *cp) if (ret < 0) goto out; - rds_tcp_tune(sock); + if (!rds_tcp_tune(sock)) { + ret = -EINVAL; + goto out; + } if (isv6) { sin6.sin6_family = AF_INET6; diff --git a/net/rds/tcp_listen.c b/net/rds/tcp_listen.c index 09cadd556d1e..7edf2e69d3fe 100644 --- a/net/rds/tcp_listen.c +++ b/net/rds/tcp_listen.c @@ -133,7 +133,10 @@ int rds_tcp_accept_one(struct socket *sock) __module_get(new_sock->ops->owner); rds_tcp_keepalive(new_sock); - rds_tcp_tune(new_sock); + if (!rds_tcp_tune(new_sock)) { + ret = -EINVAL; + goto out; + } inet = inet_sk(new_sock->sk); diff --git a/net/sched/act_pedit.c b/net/sched/act_pedit.c index 31fcd279c177..211c757bfc3c 100644 --- a/net/sched/act_pedit.c +++ b/net/sched/act_pedit.c @@ -149,7 +149,7 @@ static int tcf_pedit_init(struct net *net, struct nlattr *nla, struct nlattr *pattr; struct tcf_pedit *p; int ret = 0, err; - int ksize; + int i, ksize; u32 index; if (!nla) { @@ -228,6 +228,22 @@ static int tcf_pedit_init(struct net *net, struct nlattr *nla, p->tcfp_nkeys = parm->nkeys; } memcpy(p->tcfp_keys, parm->keys, ksize); + p->tcfp_off_max_hint = 0; + for (i = 0; i < p->tcfp_nkeys; ++i) { + u32 cur = p->tcfp_keys[i].off; + + /* sanitize the shift value for any later use */ + p->tcfp_keys[i].shift = min_t(size_t, BITS_PER_TYPE(int) - 1, + p->tcfp_keys[i].shift); + + /* The AT option can read a single byte, we can bound the actual + * value with uchar max. + */ + cur += (0xff & p->tcfp_keys[i].offmask) >> p->tcfp_keys[i].shift; + + /* Each key touches 4 bytes starting from the computed offset */ + p->tcfp_off_max_hint = max(p->tcfp_off_max_hint, cur + 4); + } p->tcfp_flags = parm->flags; goto_ch = tcf_action_set_ctrlact(*a, parm->action, goto_ch); @@ -308,13 +324,18 @@ static int tcf_pedit_act(struct sk_buff *skb, const struct tc_action *a, struct tcf_result *res) { struct tcf_pedit *p = to_pedit(a); + u32 max_offset; int i; - if (skb_unclone(skb, GFP_ATOMIC)) - return p->tcf_action; - spin_lock(&p->tcf_lock); + max_offset = (skb_transport_header_was_set(skb) ? + skb_transport_offset(skb) : + skb_network_offset(skb)) + + p->tcfp_off_max_hint; + if (skb_ensure_writable(skb, min(skb->len, max_offset))) + goto unlock; + tcf_lastuse_update(&p->tcf_tm); if (p->tcfp_nkeys > 0) { @@ -403,6 +424,7 @@ bad: p->tcf_qstats.overlimits++; done: bstats_update(&p->tcf_bstats, skb); +unlock: spin_unlock(&p->tcf_lock); return p->tcf_action; } diff --git a/net/smc/smc_rx.c b/net/smc/smc_rx.c index 51e8eb2933ff..338b9ef806e8 100644 --- a/net/smc/smc_rx.c +++ b/net/smc/smc_rx.c @@ -355,12 +355,12 @@ int smc_rx_recvmsg(struct smc_sock *smc, struct msghdr *msg, } break; } + if (!timeo) + return -EAGAIN; if (signal_pending(current)) { read_done = sock_intr_errno(timeo); break; } - if (!timeo) - return -EAGAIN; } if (!smc_rx_data_available(conn)) { diff --git a/net/socket.c b/net/socket.c index 6887840682bb..bb6a1a12fbde 100644 --- a/net/socket.c +++ b/net/socket.c @@ -504,7 +504,7 @@ static int sock_map_fd(struct socket *sock, int flags) struct socket *sock_from_file(struct file *file) { if (file->f_op == &socket_file_ops) - return file->private_data; /* set in sock_map_fd */ + return file->private_data; /* set in sock_alloc_file */ return NULL; } @@ -1538,11 +1538,10 @@ int sock_create_kern(struct net *net, int family, int type, int protocol, struct } EXPORT_SYMBOL(sock_create_kern); -int __sys_socket(int family, int type, int protocol) +static struct socket *__sys_socket_create(int family, int type, int protocol) { - int retval; struct socket *sock; - int flags; + int retval; /* Check the SOCK_* constants for consistency. */ BUILD_BUG_ON(SOCK_CLOEXEC != O_CLOEXEC); @@ -1550,17 +1549,50 @@ int __sys_socket(int family, int type, int protocol) BUILD_BUG_ON(SOCK_CLOEXEC & SOCK_TYPE_MASK); BUILD_BUG_ON(SOCK_NONBLOCK & SOCK_TYPE_MASK); - flags = type & ~SOCK_TYPE_MASK; - if (flags & ~(SOCK_CLOEXEC | SOCK_NONBLOCK)) - return -EINVAL; + if ((type & ~SOCK_TYPE_MASK) & ~(SOCK_CLOEXEC | SOCK_NONBLOCK)) + return ERR_PTR(-EINVAL); type &= SOCK_TYPE_MASK; + retval = sock_create(family, type, protocol, &sock); + if (retval < 0) + return ERR_PTR(retval); + + return sock; +} + +struct file *__sys_socket_file(int family, int type, int protocol) +{ + struct socket *sock; + struct file *file; + int flags; + + sock = __sys_socket_create(family, type, protocol); + if (IS_ERR(sock)) + return ERR_CAST(sock); + + flags = type & ~SOCK_TYPE_MASK; if (SOCK_NONBLOCK != O_NONBLOCK && (flags & SOCK_NONBLOCK)) flags = (flags & ~SOCK_NONBLOCK) | O_NONBLOCK; - retval = sock_create(family, type, protocol, &sock); - if (retval < 0) - return retval; + file = sock_alloc_file(sock, flags, NULL); + if (IS_ERR(file)) + sock_release(sock); + + return file; +} + +int __sys_socket(int family, int type, int protocol) +{ + struct socket *sock; + int flags; + + sock = __sys_socket_create(family, type, protocol); + if (IS_ERR(sock)) + return PTR_ERR(sock); + + flags = type & ~SOCK_TYPE_MASK; + if (SOCK_NONBLOCK != O_NONBLOCK && (flags & SOCK_NONBLOCK)) + flags = (flags & ~SOCK_NONBLOCK) | O_NONBLOCK; return sock_map_fd(sock, flags & (O_CLOEXEC | O_NONBLOCK)); } diff --git a/net/sunrpc/auth_gss/gss_rpc_upcall.c b/net/sunrpc/auth_gss/gss_rpc_upcall.c index 8ca1d809b78d..f549e4c05def 100644 --- a/net/sunrpc/auth_gss/gss_rpc_upcall.c +++ b/net/sunrpc/auth_gss/gss_rpc_upcall.c @@ -97,7 +97,8 @@ static int gssp_rpc_create(struct net *net, struct rpc_clnt **_clnt) * timeout, which would result in reconnections being * done without the correct namespace: */ - .flags = RPC_CLNT_CREATE_IGNORE_NULL_UNAVAIL | + .flags = RPC_CLNT_CREATE_NOPING | + RPC_CLNT_CREATE_CONNECTED | RPC_CLNT_CREATE_NO_IDLE_TIMEOUT }; struct rpc_clnt *clnt; diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c index 22c28cf43eba..e2c6eca0271b 100644 --- a/net/sunrpc/clnt.c +++ b/net/sunrpc/clnt.c @@ -76,6 +76,7 @@ static int rpc_encode_header(struct rpc_task *task, static int rpc_decode_header(struct rpc_task *task, struct xdr_stream *xdr); static int rpc_ping(struct rpc_clnt *clnt); +static int rpc_ping_noreply(struct rpc_clnt *clnt); static void rpc_check_timeout(struct rpc_task *task); static void rpc_register_client(struct rpc_clnt *clnt) @@ -479,9 +480,12 @@ static struct rpc_clnt *rpc_create_xprt(struct rpc_create_args *args, if (!(args->flags & RPC_CLNT_CREATE_NOPING)) { int err = rpc_ping(clnt); - if ((args->flags & RPC_CLNT_CREATE_IGNORE_NULL_UNAVAIL) && - err == -EOPNOTSUPP) - err = 0; + if (err != 0) { + rpc_shutdown_client(clnt); + return ERR_PTR(err); + } + } else if (args->flags & RPC_CLNT_CREATE_CONNECTED) { + int err = rpc_ping_noreply(clnt); if (err != 0) { rpc_shutdown_client(clnt); return ERR_PTR(err); @@ -2712,6 +2716,10 @@ static const struct rpc_procinfo rpcproc_null = { .p_decode = rpcproc_decode_null, }; +static const struct rpc_procinfo rpcproc_null_noreply = { + .p_encode = rpcproc_encode_null, +}; + static void rpc_null_call_prepare(struct rpc_task *task, void *data) { @@ -2765,6 +2773,28 @@ static int rpc_ping(struct rpc_clnt *clnt) return status; } +static int rpc_ping_noreply(struct rpc_clnt *clnt) +{ + struct rpc_message msg = { + .rpc_proc = &rpcproc_null_noreply, + }; + struct rpc_task_setup task_setup_data = { + .rpc_client = clnt, + .rpc_message = &msg, + .callback_ops = &rpc_null_ops, + .flags = RPC_TASK_SOFT | RPC_TASK_SOFTCONN | RPC_TASK_NULLCREDS, + }; + struct rpc_task *task; + int status; + + task = rpc_run_task(&task_setup_data); + if (IS_ERR(task)) + return PTR_ERR(task); + status = task->tk_status; + rpc_put_task(task); + return status; +} + struct rpc_cb_add_xprt_calldata { struct rpc_xprt_switch *xps; struct rpc_xprt *xprt; diff --git a/net/tls/tls_device.c b/net/tls/tls_device.c index af875ad4a822..3919fe2c58c5 100644 --- a/net/tls/tls_device.c +++ b/net/tls/tls_device.c @@ -1347,7 +1347,10 @@ static int tls_device_down(struct net_device *netdev) /* Device contexts for RX and TX will be freed in on sk_destruct * by tls_device_free_ctx. rx_conf and tx_conf stay in TLS_HW. + * Now release the ref taken above. */ + if (refcount_dec_and_test(&ctx->refcount)) + tls_device_free_ctx(ctx); } up_write(&device_offload_lock); diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 21e808fcb676..1a3551b6d18b 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -3173,6 +3173,15 @@ int nl80211_parse_chandef(struct cfg80211_registered_device *rdev, } else if (attrs[NL80211_ATTR_CHANNEL_WIDTH]) { chandef->width = nla_get_u32(attrs[NL80211_ATTR_CHANNEL_WIDTH]); + if (chandef->chan->band == NL80211_BAND_S1GHZ) { + /* User input error for channel width doesn't match channel */ + if (chandef->width != ieee80211_s1g_channel_width(chandef->chan)) { + NL_SET_ERR_MSG_ATTR(extack, + attrs[NL80211_ATTR_CHANNEL_WIDTH], + "bad channel width"); + return -EINVAL; + } + } if (attrs[NL80211_ATTR_CENTER_FREQ1]) { chandef->center_freq1 = nla_get_u32(attrs[NL80211_ATTR_CENTER_FREQ1]); @@ -11657,18 +11666,23 @@ static int nl80211_set_tx_bitrate_mask(struct sk_buff *skb, struct cfg80211_bitrate_mask mask; struct cfg80211_registered_device *rdev = info->user_ptr[0]; struct net_device *dev = info->user_ptr[1]; + struct wireless_dev *wdev = dev->ieee80211_ptr; int err; if (!rdev->ops->set_bitrate_mask) return -EOPNOTSUPP; + wdev_lock(wdev); err = nl80211_parse_tx_bitrate_mask(info, info->attrs, NL80211_ATTR_TX_RATES, &mask, dev, true); if (err) - return err; + goto out; - return rdev_set_bitrate_mask(rdev, dev, NULL, &mask); + err = rdev_set_bitrate_mask(rdev, dev, NULL, &mask); +out: + wdev_unlock(wdev); + return err; } static int nl80211_register_mgmt(struct sk_buff *skb, struct genl_info *info) diff --git a/net/wireless/scan.c b/net/wireless/scan.c index 4a6d86432910..6d82bd9eaf8c 100644 --- a/net/wireless/scan.c +++ b/net/wireless/scan.c @@ -1829,7 +1829,7 @@ int cfg80211_get_ies_channel_number(const u8 *ie, size_t ielen, if (tmp && tmp->datalen >= sizeof(struct ieee80211_s1g_oper_ie)) { struct ieee80211_s1g_oper_ie *s1gop = (void *)tmp->data; - return s1gop->primary_ch; + return s1gop->oper_ch; } } else { tmp = cfg80211_find_elem(WLAN_EID_DS_PARAMS, ie, ielen); diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index 00bd0ecff5a1..f1876ea61fdc 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -3744,7 +3744,7 @@ static int stale_bundle(struct dst_entry *dst) void xfrm_dst_ifdown(struct dst_entry *dst, struct net_device *dev) { while ((dst = xfrm_dst_child(dst)) && dst->xfrm && dst->dev == dev) { - dst->dev = dev_net(dev)->loopback_dev; + dst->dev = blackhole_netdev; dev_hold(dst->dev); dev_put(dev); } diff --git a/samples/trace_events/trace_custom_sched.h b/samples/trace_events/trace_custom_sched.h index 9fdd8e7c2a45..951388334a3f 100644 --- a/samples/trace_events/trace_custom_sched.h +++ b/samples/trace_events/trace_custom_sched.h @@ -25,11 +25,11 @@ TRACE_CUSTOM_EVENT(sched_switch, * that the custom event is using. */ TP_PROTO(bool preempt, - unsigned int prev_state, struct task_struct *prev, - struct task_struct *next), + struct task_struct *next, + unsigned int prev_state), - TP_ARGS(preempt, prev_state, prev, next), + TP_ARGS(preempt, prev, next, prev_state), /* * The next fields are where the customization happens. diff --git a/scripts/Makefile.build b/scripts/Makefile.build index 33c1ed581522..3911bfc21702 100644 --- a/scripts/Makefile.build +++ b/scripts/Makefile.build @@ -233,7 +233,7 @@ objtool_args = \ $(if $(CONFIG_FRAME_POINTER),, --no-fp) \ $(if $(CONFIG_GCOV_KERNEL), --no-unreachable) \ $(if $(CONFIG_RETPOLINE), --retpoline) \ - $(if $(CONFIG_X86_SMAP), --uaccess) \ + --uaccess \ $(if $(CONFIG_FTRACE_MCOUNT_USE_OBJTOOL), --mcount) \ $(if $(CONFIG_SLS), --sls) diff --git a/scripts/link-vmlinux.sh b/scripts/link-vmlinux.sh index 9361a1ef02c9..e036b0bbb42c 100755 --- a/scripts/link-vmlinux.sh +++ b/scripts/link-vmlinux.sh @@ -146,9 +146,9 @@ objtool_link() if is_enabled CONFIG_RETPOLINE; then objtoolopt="${objtoolopt} --retpoline" fi - if is_enabled CONFIG_X86_SMAP; then - objtoolopt="${objtoolopt} --uaccess" - fi + + objtoolopt="${objtoolopt} --uaccess" + if is_enabled CONFIG_SLS; then objtoolopt="${objtoolopt} --sls" fi diff --git a/security/selinux/ss/hashtab.c b/security/selinux/ss/hashtab.c index 0ae4e4e57a40..3fb8f9026e9b 100644 --- a/security/selinux/ss/hashtab.c +++ b/security/selinux/ss/hashtab.c @@ -179,7 +179,8 @@ int hashtab_duplicate(struct hashtab *new, struct hashtab *orig, kmem_cache_free(hashtab_node_cachep, cur); } } - kmem_cache_free(hashtab_node_cachep, new); + kfree(new->htable); + memset(new, 0, sizeof(*new)); return -ENOMEM; } diff --git a/sound/isa/wavefront/wavefront_synth.c b/sound/isa/wavefront/wavefront_synth.c index 69cbc79fbb71..2aaaa6807174 100644 --- a/sound/isa/wavefront/wavefront_synth.c +++ b/sound/isa/wavefront/wavefront_synth.c @@ -1094,7 +1094,8 @@ wavefront_send_sample (snd_wavefront_t *dev, if (dataptr < data_end) { - __get_user (sample_short, dataptr); + if (get_user(sample_short, dataptr)) + return -EFAULT; dataptr += skip; if (data_is_unsigned) { /* GUS ? */ diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index cf531c1efa13..ad292df7d805 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -937,6 +937,9 @@ static int alc_init(struct hda_codec *codec) return 0; } +#define alc_free snd_hda_gen_free + +#ifdef CONFIG_PM static inline void alc_shutup(struct hda_codec *codec) { struct alc_spec *spec = codec->spec; @@ -950,9 +953,6 @@ static inline void alc_shutup(struct hda_codec *codec) alc_shutup_pins(codec); } -#define alc_free snd_hda_gen_free - -#ifdef CONFIG_PM static void alc_power_eapd(struct hda_codec *codec) { alc_auto_setup_eapd(codec, false); @@ -966,9 +966,7 @@ static int alc_suspend(struct hda_codec *codec) spec->power_hook(codec); return 0; } -#endif -#ifdef CONFIG_PM static int alc_resume(struct hda_codec *codec) { struct alc_spec *spec = codec->spec; @@ -6780,6 +6778,41 @@ static void alc256_fixup_mic_no_presence_and_resume(struct hda_codec *codec, } } +static void alc_fixup_dell4_mic_no_presence_quiet(struct hda_codec *codec, + const struct hda_fixup *fix, + int action) +{ + struct alc_spec *spec = codec->spec; + struct hda_input_mux *imux = &spec->gen.input_mux; + int i; + + alc269_fixup_limit_int_mic_boost(codec, fix, action); + + switch (action) { + case HDA_FIXUP_ACT_PRE_PROBE: + /** + * Set the vref of pin 0x19 (Headset Mic) and pin 0x1b (Headphone Mic) + * to Hi-Z to avoid pop noises at startup and when plugging and + * unplugging headphones. + */ + snd_hda_codec_set_pin_target(codec, 0x19, PIN_VREFHIZ); + snd_hda_codec_set_pin_target(codec, 0x1b, PIN_VREFHIZ); + break; + case HDA_FIXUP_ACT_PROBE: + /** + * Make the internal mic (0x12) the default input source to + * prevent pop noises on cold boot. + */ + for (i = 0; i < imux->num_items; i++) { + if (spec->gen.imux_pins[i] == 0x12) { + spec->gen.cur_mux[0] = i; + break; + } + } + break; + } +} + enum { ALC269_FIXUP_GPIO2, ALC269_FIXUP_SONY_VAIO, @@ -6821,6 +6854,7 @@ enum { ALC269_FIXUP_DELL2_MIC_NO_PRESENCE, ALC269_FIXUP_DELL3_MIC_NO_PRESENCE, ALC269_FIXUP_DELL4_MIC_NO_PRESENCE, + ALC269_FIXUP_DELL4_MIC_NO_PRESENCE_QUIET, ALC269_FIXUP_HEADSET_MODE, ALC269_FIXUP_HEADSET_MODE_NO_HP_MIC, ALC269_FIXUP_ASPIRE_HEADSET_MIC, @@ -7012,6 +7046,7 @@ enum { ALC245_FIXUP_CS35L41_SPI_4, ALC245_FIXUP_CS35L41_SPI_4_HP_GPIO_LED, ALC285_FIXUP_HP_SPEAKERS_MICMUTE_LED, + ALC295_FIXUP_FRAMEWORK_LAPTOP_MIC_NO_PRESENCE, }; static const struct hda_fixup alc269_fixups[] = { @@ -8808,6 +8843,21 @@ static const struct hda_fixup alc269_fixups[] = { .chained = true, .chain_id = ALC285_FIXUP_HP_MUTE_LED, }, + [ALC269_FIXUP_DELL4_MIC_NO_PRESENCE_QUIET] = { + .type = HDA_FIXUP_FUNC, + .v.func = alc_fixup_dell4_mic_no_presence_quiet, + .chained = true, + .chain_id = ALC269_FIXUP_DELL4_MIC_NO_PRESENCE, + }, + [ALC295_FIXUP_FRAMEWORK_LAPTOP_MIC_NO_PRESENCE] = { + .type = HDA_FIXUP_PINS, + .v.pins = (const struct hda_pintbl[]) { + { 0x19, 0x02a1112c }, /* use as headset mic, without its own jack detect */ + { } + }, + .chained = true, + .chain_id = ALC269_FIXUP_HEADSET_MODE_NO_HP_MIC + }, }; static const struct snd_pci_quirk alc269_fixup_tbl[] = { @@ -8898,6 +8948,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x1028, 0x09bf, "Dell Precision", ALC233_FIXUP_ASUS_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1028, 0x0a2e, "Dell", ALC236_FIXUP_DELL_AIO_HEADSET_MIC), SND_PCI_QUIRK(0x1028, 0x0a30, "Dell", ALC236_FIXUP_DELL_AIO_HEADSET_MIC), + SND_PCI_QUIRK(0x1028, 0x0a38, "Dell Latitude 7520", ALC269_FIXUP_DELL4_MIC_NO_PRESENCE_QUIET), SND_PCI_QUIRK(0x1028, 0x0a58, "Dell", ALC255_FIXUP_DELL_HEADSET_MIC), SND_PCI_QUIRK(0x1028, 0x0a61, "Dell XPS 15 9510", ALC289_FIXUP_DUAL_SPK), SND_PCI_QUIRK(0x1028, 0x0a62, "Dell Precision 5560", ALC289_FIXUP_DUAL_SPK), @@ -9040,6 +9091,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x103c, 0x8995, "HP EliteBook 855 G9", ALC287_FIXUP_CS35L41_I2C_2), SND_PCI_QUIRK(0x103c, 0x89a4, "HP ProBook 440 G9", ALC236_FIXUP_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x89a6, "HP ProBook 450 G9", ALC236_FIXUP_HP_GPIO_LED), + SND_PCI_QUIRK(0x103c, 0x89aa, "HP EliteBook 630 G9", ALC236_FIXUP_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x89ac, "HP EliteBook 640 G9", ALC236_FIXUP_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x89ae, "HP EliteBook 650 G9", ALC236_FIXUP_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x89c3, "Zbook Studio G9", ALC245_FIXUP_CS35L41_SPI_4_HP_GPIO_LED), @@ -9290,6 +9342,14 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x1c06, 0x2013, "Lemote A1802", ALC269_FIXUP_LEMOTE_A1802), SND_PCI_QUIRK(0x1c06, 0x2015, "Lemote A190X", ALC269_FIXUP_LEMOTE_A190X), SND_PCI_QUIRK(0x1d05, 0x1132, "TongFang PHxTxX1", ALC256_FIXUP_SET_COEF_DEFAULTS), + SND_PCI_QUIRK(0x1d05, 0x1096, "TongFang GMxMRxx", ALC269_FIXUP_NO_SHUTUP), + SND_PCI_QUIRK(0x1d05, 0x1100, "TongFang GKxNRxx", ALC269_FIXUP_NO_SHUTUP), + SND_PCI_QUIRK(0x1d05, 0x1111, "TongFang GMxZGxx", ALC269_FIXUP_NO_SHUTUP), + SND_PCI_QUIRK(0x1d05, 0x1119, "TongFang GMxZGxx", ALC269_FIXUP_NO_SHUTUP), + SND_PCI_QUIRK(0x1d05, 0x1129, "TongFang GMxZGxx", ALC269_FIXUP_NO_SHUTUP), + SND_PCI_QUIRK(0x1d05, 0x1147, "TongFang GMxTGxx", ALC269_FIXUP_NO_SHUTUP), + SND_PCI_QUIRK(0x1d05, 0x115c, "TongFang GMxTGxx", ALC269_FIXUP_NO_SHUTUP), + SND_PCI_QUIRK(0x1d05, 0x121b, "TongFang GMxAGxx", ALC269_FIXUP_NO_SHUTUP), SND_PCI_QUIRK(0x1d72, 0x1602, "RedmiBook", ALC255_FIXUP_XIAOMI_HEADSET_MIC), SND_PCI_QUIRK(0x1d72, 0x1701, "XiaomiNotebook Pro", ALC298_FIXUP_DELL1_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1d72, 0x1901, "RedmiBook 14", ALC256_FIXUP_ASUS_HEADSET_MIC), @@ -9297,6 +9357,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x8086, 0x2074, "Intel NUC 8", ALC233_FIXUP_INTEL_NUC8_DMIC), SND_PCI_QUIRK(0x8086, 0x2080, "Intel NUC 8 Rugged", ALC256_FIXUP_INTEL_NUC8_RUGGED), SND_PCI_QUIRK(0x8086, 0x2081, "Intel NUC 10", ALC256_FIXUP_INTEL_NUC10), + SND_PCI_QUIRK(0xf111, 0x0001, "Framework Laptop", ALC295_FIXUP_FRAMEWORK_LAPTOP_MIC_NO_PRESENCE), #if 0 /* Below is a quirk table taken from the old code. diff --git a/sound/usb/quirks-table.h b/sound/usb/quirks-table.h index 0ea39565e623..40a5e3eb4ef2 100644 --- a/sound/usb/quirks-table.h +++ b/sound/usb/quirks-table.h @@ -3235,6 +3235,15 @@ YAMAHA_DEVICE(0x7010, "UB99"), } }, +/* Rane SL-1 */ +{ + USB_DEVICE(0x13e5, 0x0001), + .driver_info = (unsigned long) & (const struct snd_usb_audio_quirk) { + .ifnum = QUIRK_ANY_INTERFACE, + .type = QUIRK_AUDIO_STANDARD_INTERFACE + } +}, + /* disabled due to regression for other devices; * see https://bugzilla.kernel.org/show_bug.cgi?id=199905 */ diff --git a/sound/usb/quirks.c b/sound/usb/quirks.c index ab9f3da49941..fbbe59054c3f 100644 --- a/sound/usb/quirks.c +++ b/sound/usb/quirks.c @@ -1822,6 +1822,8 @@ static const struct usb_audio_quirk_flags_table quirk_flags_table[] = { QUIRK_FLAG_IGNORE_CTL_ERROR), DEVICE_FLG(0x06f8, 0xd002, /* Hercules DJ Console (Macintosh Edition) */ QUIRK_FLAG_IGNORE_CTL_ERROR), + DEVICE_FLG(0x0711, 0x5800, /* MCT Trigger 5 USB-to-HDMI */ + QUIRK_FLAG_GET_SAMPLE_RATE), DEVICE_FLG(0x074d, 0x3553, /* Outlaw RR2150 (Micronas UAC3553B) */ QUIRK_FLAG_GET_SAMPLE_RATE), DEVICE_FLG(0x08bb, 0x2702, /* LineX FM Transmitter */ diff --git a/tools/Makefile b/tools/Makefile index db2f7b8ebed5..724134f0e56c 100644 --- a/tools/Makefile +++ b/tools/Makefile @@ -24,6 +24,7 @@ help: @echo ' intel-speed-select - Intel Speed Select tool' @echo ' kvm_stat - top-like utility for displaying kvm statistics' @echo ' leds - LEDs tools' + @echo ' nolibc - nolibc headers testing and installation' @echo ' objtool - an ELF object analysis tool' @echo ' pci - PCI tools' @echo ' perf - Linux performance measurement and analysis tool' @@ -74,6 +75,9 @@ bpf/%: FORCE libapi: FORCE $(call descend,lib/api) +nolibc_%: FORCE + $(call descend,include/nolibc,$(patsubst nolibc_%,%,$@)) + # The perf build does not follow the descend function setup, # invoking it via it's own make rule. PERF_O = $(if $(O),$(O)/tools/perf,) diff --git a/tools/arch/x86/include/asm/disabled-features.h b/tools/arch/x86/include/asm/disabled-features.h index 1231d63f836d..1ae0fab7d902 100644 --- a/tools/arch/x86/include/asm/disabled-features.h +++ b/tools/arch/x86/include/asm/disabled-features.h @@ -10,12 +10,6 @@ * cpu_feature_enabled(). */ -#ifdef CONFIG_X86_SMAP -# define DISABLE_SMAP 0 -#else -# define DISABLE_SMAP (1<<(X86_FEATURE_SMAP & 31)) -#endif - #ifdef CONFIG_X86_UMIP # define DISABLE_UMIP 0 #else @@ -80,7 +74,7 @@ #define DISABLED_MASK6 0 #define DISABLED_MASK7 (DISABLE_PTI) #define DISABLED_MASK8 0 -#define DISABLED_MASK9 (DISABLE_SMAP|DISABLE_SGX) +#define DISABLED_MASK9 (DISABLE_SGX) #define DISABLED_MASK10 0 #define DISABLED_MASK11 0 #define DISABLED_MASK12 0 diff --git a/tools/build/Makefile.feature b/tools/build/Makefile.feature index ae61f464043a..c6a48d0ef9ff 100644 --- a/tools/build/Makefile.feature +++ b/tools/build/Makefile.feature @@ -98,6 +98,7 @@ FEATURE_TESTS_EXTRA := \ llvm-version \ clang \ libbpf \ + libbpf-btf__load_from_kernel_by_id \ libpfm4 \ libdebuginfod \ clang-bpf-co-re diff --git a/tools/build/feature/Makefile b/tools/build/feature/Makefile index de66e1cc0734..cb4a2a4fa2e4 100644 --- a/tools/build/feature/Makefile +++ b/tools/build/feature/Makefile @@ -57,6 +57,7 @@ FILES= \ test-lzma.bin \ test-bpf.bin \ test-libbpf.bin \ + test-libbpf-btf__load_from_kernel_by_id.bin \ test-get_cpuid.bin \ test-sdt.bin \ test-cxx.bin \ @@ -287,6 +288,9 @@ $(OUTPUT)test-bpf.bin: $(OUTPUT)test-libbpf.bin: $(BUILD) -lbpf +$(OUTPUT)test-libbpf-btf__load_from_kernel_by_id.bin: + $(BUILD) -lbpf + $(OUTPUT)test-sdt.bin: $(BUILD) diff --git a/tools/build/feature/test-libbpf-btf__load_from_kernel_by_id.c b/tools/build/feature/test-libbpf-btf__load_from_kernel_by_id.c new file mode 100644 index 000000000000..f7c084428735 --- /dev/null +++ b/tools/build/feature/test-libbpf-btf__load_from_kernel_by_id.c @@ -0,0 +1,7 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <bpf/libbpf.h> + +int main(void) +{ + return btf__load_from_kernel_by_id(20151128, NULL); +} diff --git a/tools/include/linux/objtool.h b/tools/include/linux/objtool.h index 586d35720f13..b9c1474a571e 100644 --- a/tools/include/linux/objtool.h +++ b/tools/include/linux/objtool.h @@ -40,6 +40,8 @@ struct unwind_hint { #ifdef CONFIG_STACK_VALIDATION +#include <asm/asm.h> + #ifndef __ASSEMBLY__ #define UNWIND_HINT(sp_reg, sp_offset, type, end) \ @@ -137,7 +139,7 @@ struct unwind_hint { .macro STACK_FRAME_NON_STANDARD func:req .pushsection .discard.func_stack_frame_non_standard, "aw" - .long \func - . + _ASM_PTR \func .popsection .endm diff --git a/tools/include/nolibc/Makefile b/tools/include/nolibc/Makefile new file mode 100644 index 000000000000..7a16d917c185 --- /dev/null +++ b/tools/include/nolibc/Makefile @@ -0,0 +1,42 @@ +# SPDX-License-Identifier: GPL-2.0 +# Makefile for nolibc installation and tests +include ../../scripts/Makefile.include + +# we're in ".../tools/include/nolibc" +ifeq ($(srctree),) +srctree := $(patsubst %/tools/include/,%,$(dir $(CURDIR))) +endif + +nolibc_arch := $(patsubst arm64,aarch64,$(ARCH)) +arch_file := arch-$(nolibc_arch).h +all_files := ctype.h errno.h nolibc.h signal.h std.h stdio.h stdlib.h string.h \ + sys.h time.h types.h unistd.h + +# install all headers needed to support a bare-metal compiler +all: + +# Note: when ARCH is "x86" we concatenate both x86_64 and i386 +headers: + $(Q)mkdir -p $(OUTPUT)sysroot + $(Q)mkdir -p $(OUTPUT)sysroot/include + $(Q)cp $(all_files) $(OUTPUT)sysroot/include/ + $(Q)if [ "$(ARCH)" = "x86" ]; then \ + sed -e \ + 's,^#ifndef _NOLIBC_ARCH_X86_64_H,#if !defined(_NOLIBC_ARCH_X86_64_H) \&\& defined(__x86_64__),' \ + arch-x86_64.h; \ + sed -e \ + 's,^#ifndef _NOLIBC_ARCH_I386_H,#if !defined(_NOLIBC_ARCH_I386_H) \&\& !defined(__x86_64__),' \ + arch-i386.h; \ + elif [ -e "$(arch_file)" ]; then \ + cat $(arch_file); \ + else \ + echo "Fatal: architecture $(ARCH) not yet supported by nolibc." >&2; \ + exit 1; \ + fi > $(OUTPUT)sysroot/include/arch.h + +headers_standalone: headers + $(Q)$(MAKE) -C $(srctree) headers + $(Q)$(MAKE) -C $(srctree) headers_install INSTALL_HDR_PATH=$(OUTPUT)/sysroot + +clean: + $(call QUIET_CLEAN, nolibc) rm -rf "$(OUTPUT)sysroot" diff --git a/tools/include/nolibc/arch-aarch64.h b/tools/include/nolibc/arch-aarch64.h new file mode 100644 index 000000000000..f68baf8f395f --- /dev/null +++ b/tools/include/nolibc/arch-aarch64.h @@ -0,0 +1,199 @@ +/* SPDX-License-Identifier: LGPL-2.1 OR MIT */ +/* + * AARCH64 specific definitions for NOLIBC + * Copyright (C) 2017-2022 Willy Tarreau <w@1wt.eu> + */ + +#ifndef _NOLIBC_ARCH_AARCH64_H +#define _NOLIBC_ARCH_AARCH64_H + +/* O_* macros for fcntl/open are architecture-specific */ +#define O_RDONLY 0 +#define O_WRONLY 1 +#define O_RDWR 2 +#define O_CREAT 0x40 +#define O_EXCL 0x80 +#define O_NOCTTY 0x100 +#define O_TRUNC 0x200 +#define O_APPEND 0x400 +#define O_NONBLOCK 0x800 +#define O_DIRECTORY 0x4000 + +/* The struct returned by the newfstatat() syscall. Differs slightly from the + * x86_64's stat one by field ordering, so be careful. + */ +struct sys_stat_struct { + unsigned long st_dev; + unsigned long st_ino; + unsigned int st_mode; + unsigned int st_nlink; + unsigned int st_uid; + unsigned int st_gid; + + unsigned long st_rdev; + unsigned long __pad1; + long st_size; + int st_blksize; + int __pad2; + + long st_blocks; + long st_atime; + unsigned long st_atime_nsec; + long st_mtime; + + unsigned long st_mtime_nsec; + long st_ctime; + unsigned long st_ctime_nsec; + unsigned int __unused[2]; +}; + +/* Syscalls for AARCH64 : + * - registers are 64-bit + * - stack is 16-byte aligned + * - syscall number is passed in x8 + * - arguments are in x0, x1, x2, x3, x4, x5 + * - the system call is performed by calling svc 0 + * - syscall return comes in x0. + * - the arguments are cast to long and assigned into the target registers + * which are then simply passed as registers to the asm code, so that we + * don't have to experience issues with register constraints. + * + * On aarch64, select() is not implemented so we have to use pselect6(). + */ +#define __ARCH_WANT_SYS_PSELECT6 + +#define my_syscall0(num) \ +({ \ + register long _num __asm__ ("x8") = (num); \ + register long _arg1 __asm__ ("x0"); \ + \ + __asm__ volatile ( \ + "svc #0\n" \ + : "=r"(_arg1) \ + : "r"(_num) \ + : "memory", "cc" \ + ); \ + _arg1; \ +}) + +#define my_syscall1(num, arg1) \ +({ \ + register long _num __asm__ ("x8") = (num); \ + register long _arg1 __asm__ ("x0") = (long)(arg1); \ + \ + __asm__ volatile ( \ + "svc #0\n" \ + : "=r"(_arg1) \ + : "r"(_arg1), \ + "r"(_num) \ + : "memory", "cc" \ + ); \ + _arg1; \ +}) + +#define my_syscall2(num, arg1, arg2) \ +({ \ + register long _num __asm__ ("x8") = (num); \ + register long _arg1 __asm__ ("x0") = (long)(arg1); \ + register long _arg2 __asm__ ("x1") = (long)(arg2); \ + \ + __asm__ volatile ( \ + "svc #0\n" \ + : "=r"(_arg1) \ + : "r"(_arg1), "r"(_arg2), \ + "r"(_num) \ + : "memory", "cc" \ + ); \ + _arg1; \ +}) + +#define my_syscall3(num, arg1, arg2, arg3) \ +({ \ + register long _num __asm__ ("x8") = (num); \ + register long _arg1 __asm__ ("x0") = (long)(arg1); \ + register long _arg2 __asm__ ("x1") = (long)(arg2); \ + register long _arg3 __asm__ ("x2") = (long)(arg3); \ + \ + __asm__ volatile ( \ + "svc #0\n" \ + : "=r"(_arg1) \ + : "r"(_arg1), "r"(_arg2), "r"(_arg3), \ + "r"(_num) \ + : "memory", "cc" \ + ); \ + _arg1; \ +}) + +#define my_syscall4(num, arg1, arg2, arg3, arg4) \ +({ \ + register long _num __asm__ ("x8") = (num); \ + register long _arg1 __asm__ ("x0") = (long)(arg1); \ + register long _arg2 __asm__ ("x1") = (long)(arg2); \ + register long _arg3 __asm__ ("x2") = (long)(arg3); \ + register long _arg4 __asm__ ("x3") = (long)(arg4); \ + \ + __asm__ volatile ( \ + "svc #0\n" \ + : "=r"(_arg1) \ + : "r"(_arg1), "r"(_arg2), "r"(_arg3), "r"(_arg4), \ + "r"(_num) \ + : "memory", "cc" \ + ); \ + _arg1; \ +}) + +#define my_syscall5(num, arg1, arg2, arg3, arg4, arg5) \ +({ \ + register long _num __asm__ ("x8") = (num); \ + register long _arg1 __asm__ ("x0") = (long)(arg1); \ + register long _arg2 __asm__ ("x1") = (long)(arg2); \ + register long _arg3 __asm__ ("x2") = (long)(arg3); \ + register long _arg4 __asm__ ("x3") = (long)(arg4); \ + register long _arg5 __asm__ ("x4") = (long)(arg5); \ + \ + __asm__ volatile ( \ + "svc #0\n" \ + : "=r" (_arg1) \ + : "r"(_arg1), "r"(_arg2), "r"(_arg3), "r"(_arg4), "r"(_arg5), \ + "r"(_num) \ + : "memory", "cc" \ + ); \ + _arg1; \ +}) + +#define my_syscall6(num, arg1, arg2, arg3, arg4, arg5, arg6) \ +({ \ + register long _num __asm__ ("x8") = (num); \ + register long _arg1 __asm__ ("x0") = (long)(arg1); \ + register long _arg2 __asm__ ("x1") = (long)(arg2); \ + register long _arg3 __asm__ ("x2") = (long)(arg3); \ + register long _arg4 __asm__ ("x3") = (long)(arg4); \ + register long _arg5 __asm__ ("x4") = (long)(arg5); \ + register long _arg6 __asm__ ("x5") = (long)(arg6); \ + \ + __asm__ volatile ( \ + "svc #0\n" \ + : "=r" (_arg1) \ + : "r"(_arg1), "r"(_arg2), "r"(_arg3), "r"(_arg4), "r"(_arg5), \ + "r"(_arg6), "r"(_num) \ + : "memory", "cc" \ + ); \ + _arg1; \ +}) + +/* startup code */ +__asm__ (".section .text\n" + ".weak _start\n" + "_start:\n" + "ldr x0, [sp]\n" // argc (x0) was in the stack + "add x1, sp, 8\n" // argv (x1) = sp + "lsl x2, x0, 3\n" // envp (x2) = 8*argc ... + "add x2, x2, 8\n" // + 8 (skip null) + "add x2, x2, x1\n" // + argv + "and sp, x1, -16\n" // sp must be 16-byte aligned in the callee + "bl main\n" // main() returns the status code, we'll exit with it. + "mov x8, 93\n" // NR_exit == 93 + "svc #0\n" + ""); + +#endif // _NOLIBC_ARCH_AARCH64_H diff --git a/tools/include/nolibc/arch-arm.h b/tools/include/nolibc/arch-arm.h new file mode 100644 index 000000000000..f31be8e967d6 --- /dev/null +++ b/tools/include/nolibc/arch-arm.h @@ -0,0 +1,204 @@ +/* SPDX-License-Identifier: LGPL-2.1 OR MIT */ +/* + * ARM specific definitions for NOLIBC + * Copyright (C) 2017-2022 Willy Tarreau <w@1wt.eu> + */ + +#ifndef _NOLIBC_ARCH_ARM_H +#define _NOLIBC_ARCH_ARM_H + +/* O_* macros for fcntl/open are architecture-specific */ +#define O_RDONLY 0 +#define O_WRONLY 1 +#define O_RDWR 2 +#define O_CREAT 0x40 +#define O_EXCL 0x80 +#define O_NOCTTY 0x100 +#define O_TRUNC 0x200 +#define O_APPEND 0x400 +#define O_NONBLOCK 0x800 +#define O_DIRECTORY 0x4000 + +/* The struct returned by the stat() syscall, 32-bit only, the syscall returns + * exactly 56 bytes (stops before the unused array). In big endian, the format + * differs as devices are returned as short only. + */ +struct sys_stat_struct { +#if defined(__ARMEB__) + unsigned short st_dev; + unsigned short __pad1; +#else + unsigned long st_dev; +#endif + unsigned long st_ino; + unsigned short st_mode; + unsigned short st_nlink; + unsigned short st_uid; + unsigned short st_gid; + +#if defined(__ARMEB__) + unsigned short st_rdev; + unsigned short __pad2; +#else + unsigned long st_rdev; +#endif + unsigned long st_size; + unsigned long st_blksize; + unsigned long st_blocks; + + unsigned long st_atime; + unsigned long st_atime_nsec; + unsigned long st_mtime; + unsigned long st_mtime_nsec; + + unsigned long st_ctime; + unsigned long st_ctime_nsec; + unsigned long __unused[2]; +}; + +/* Syscalls for ARM in ARM or Thumb modes : + * - registers are 32-bit + * - stack is 8-byte aligned + * ( http://infocenter.arm.com/help/index.jsp?topic=/com.arm.doc.faqs/ka4127.html) + * - syscall number is passed in r7 + * - arguments are in r0, r1, r2, r3, r4, r5 + * - the system call is performed by calling svc #0 + * - syscall return comes in r0. + * - only lr is clobbered. + * - the arguments are cast to long and assigned into the target registers + * which are then simply passed as registers to the asm code, so that we + * don't have to experience issues with register constraints. + * - the syscall number is always specified last in order to allow to force + * some registers before (gcc refuses a %-register at the last position). + * + * Also, ARM supports the old_select syscall if newselect is not available + */ +#define __ARCH_WANT_SYS_OLD_SELECT + +#define my_syscall0(num) \ +({ \ + register long _num __asm__ ("r7") = (num); \ + register long _arg1 __asm__ ("r0"); \ + \ + __asm__ volatile ( \ + "svc #0\n" \ + : "=r"(_arg1) \ + : "r"(_num) \ + : "memory", "cc", "lr" \ + ); \ + _arg1; \ +}) + +#define my_syscall1(num, arg1) \ +({ \ + register long _num __asm__ ("r7") = (num); \ + register long _arg1 __asm__ ("r0") = (long)(arg1); \ + \ + __asm__ volatile ( \ + "svc #0\n" \ + : "=r"(_arg1) \ + : "r"(_arg1), \ + "r"(_num) \ + : "memory", "cc", "lr" \ + ); \ + _arg1; \ +}) + +#define my_syscall2(num, arg1, arg2) \ +({ \ + register long _num __asm__ ("r7") = (num); \ + register long _arg1 __asm__ ("r0") = (long)(arg1); \ + register long _arg2 __asm__ ("r1") = (long)(arg2); \ + \ + __asm__ volatile ( \ + "svc #0\n" \ + : "=r"(_arg1) \ + : "r"(_arg1), "r"(_arg2), \ + "r"(_num) \ + : "memory", "cc", "lr" \ + ); \ + _arg1; \ +}) + +#define my_syscall3(num, arg1, arg2, arg3) \ +({ \ + register long _num __asm__ ("r7") = (num); \ + register long _arg1 __asm__ ("r0") = (long)(arg1); \ + register long _arg2 __asm__ ("r1") = (long)(arg2); \ + register long _arg3 __asm__ ("r2") = (long)(arg3); \ + \ + __asm__ volatile ( \ + "svc #0\n" \ + : "=r"(_arg1) \ + : "r"(_arg1), "r"(_arg2), "r"(_arg3), \ + "r"(_num) \ + : "memory", "cc", "lr" \ + ); \ + _arg1; \ +}) + +#define my_syscall4(num, arg1, arg2, arg3, arg4) \ +({ \ + register long _num __asm__ ("r7") = (num); \ + register long _arg1 __asm__ ("r0") = (long)(arg1); \ + register long _arg2 __asm__ ("r1") = (long)(arg2); \ + register long _arg3 __asm__ ("r2") = (long)(arg3); \ + register long _arg4 __asm__ ("r3") = (long)(arg4); \ + \ + __asm__ volatile ( \ + "svc #0\n" \ + : "=r"(_arg1) \ + : "r"(_arg1), "r"(_arg2), "r"(_arg3), "r"(_arg4), \ + "r"(_num) \ + : "memory", "cc", "lr" \ + ); \ + _arg1; \ +}) + +#define my_syscall5(num, arg1, arg2, arg3, arg4, arg5) \ +({ \ + register long _num __asm__ ("r7") = (num); \ + register long _arg1 __asm__ ("r0") = (long)(arg1); \ + register long _arg2 __asm__ ("r1") = (long)(arg2); \ + register long _arg3 __asm__ ("r2") = (long)(arg3); \ + register long _arg4 __asm__ ("r3") = (long)(arg4); \ + register long _arg5 __asm__ ("r4") = (long)(arg5); \ + \ + __asm__ volatile ( \ + "svc #0\n" \ + : "=r" (_arg1) \ + : "r"(_arg1), "r"(_arg2), "r"(_arg3), "r"(_arg4), "r"(_arg5), \ + "r"(_num) \ + : "memory", "cc", "lr" \ + ); \ + _arg1; \ +}) + +/* startup code */ +__asm__ (".section .text\n" + ".weak _start\n" + "_start:\n" +#if defined(__THUMBEB__) || defined(__THUMBEL__) + /* We enter here in 32-bit mode but if some previous functions were in + * 16-bit mode, the assembler cannot know, so we need to tell it we're in + * 32-bit now, then switch to 16-bit (is there a better way to do it than + * adding 1 by hand ?) and tell the asm we're now in 16-bit mode so that + * it generates correct instructions. Note that we do not support thumb1. + */ + ".code 32\n" + "add r0, pc, #1\n" + "bx r0\n" + ".code 16\n" +#endif + "pop {%r0}\n" // argc was in the stack + "mov %r1, %sp\n" // argv = sp + "add %r2, %r1, %r0, lsl #2\n" // envp = argv + 4*argc ... + "add %r2, %r2, $4\n" // ... + 4 + "and %r3, %r1, $-8\n" // AAPCS : sp must be 8-byte aligned in the + "mov %sp, %r3\n" // callee, an bl doesn't push (lr=pc) + "bl main\n" // main() returns the status code, we'll exit with it. + "movs r7, $1\n" // NR_exit == 1 + "svc $0x00\n" + ""); + +#endif // _NOLIBC_ARCH_ARM_H diff --git a/tools/include/nolibc/arch-i386.h b/tools/include/nolibc/arch-i386.h new file mode 100644 index 000000000000..d7e7212346e2 --- /dev/null +++ b/tools/include/nolibc/arch-i386.h @@ -0,0 +1,219 @@ +/* SPDX-License-Identifier: LGPL-2.1 OR MIT */ +/* + * i386 specific definitions for NOLIBC + * Copyright (C) 2017-2022 Willy Tarreau <w@1wt.eu> + */ + +#ifndef _NOLIBC_ARCH_I386_H +#define _NOLIBC_ARCH_I386_H + +/* O_* macros for fcntl/open are architecture-specific */ +#define O_RDONLY 0 +#define O_WRONLY 1 +#define O_RDWR 2 +#define O_CREAT 0x40 +#define O_EXCL 0x80 +#define O_NOCTTY 0x100 +#define O_TRUNC 0x200 +#define O_APPEND 0x400 +#define O_NONBLOCK 0x800 +#define O_DIRECTORY 0x10000 + +/* The struct returned by the stat() syscall, 32-bit only, the syscall returns + * exactly 56 bytes (stops before the unused array). + */ +struct sys_stat_struct { + unsigned long st_dev; + unsigned long st_ino; + unsigned short st_mode; + unsigned short st_nlink; + unsigned short st_uid; + unsigned short st_gid; + + unsigned long st_rdev; + unsigned long st_size; + unsigned long st_blksize; + unsigned long st_blocks; + + unsigned long st_atime; + unsigned long st_atime_nsec; + unsigned long st_mtime; + unsigned long st_mtime_nsec; + + unsigned long st_ctime; + unsigned long st_ctime_nsec; + unsigned long __unused[2]; +}; + +/* Syscalls for i386 : + * - mostly similar to x86_64 + * - registers are 32-bit + * - syscall number is passed in eax + * - arguments are in ebx, ecx, edx, esi, edi, ebp respectively + * - all registers are preserved (except eax of course) + * - the system call is performed by calling int $0x80 + * - syscall return comes in eax + * - the arguments are cast to long and assigned into the target registers + * which are then simply passed as registers to the asm code, so that we + * don't have to experience issues with register constraints. + * - the syscall number is always specified last in order to allow to force + * some registers before (gcc refuses a %-register at the last position). + * + * Also, i386 supports the old_select syscall if newselect is not available + */ +#define __ARCH_WANT_SYS_OLD_SELECT + +#define my_syscall0(num) \ +({ \ + long _ret; \ + register long _num __asm__ ("eax") = (num); \ + \ + __asm__ volatile ( \ + "int $0x80\n" \ + : "=a" (_ret) \ + : "0"(_num) \ + : "memory", "cc" \ + ); \ + _ret; \ +}) + +#define my_syscall1(num, arg1) \ +({ \ + long _ret; \ + register long _num __asm__ ("eax") = (num); \ + register long _arg1 __asm__ ("ebx") = (long)(arg1); \ + \ + __asm__ volatile ( \ + "int $0x80\n" \ + : "=a" (_ret) \ + : "r"(_arg1), \ + "0"(_num) \ + : "memory", "cc" \ + ); \ + _ret; \ +}) + +#define my_syscall2(num, arg1, arg2) \ +({ \ + long _ret; \ + register long _num __asm__ ("eax") = (num); \ + register long _arg1 __asm__ ("ebx") = (long)(arg1); \ + register long _arg2 __asm__ ("ecx") = (long)(arg2); \ + \ + __asm__ volatile ( \ + "int $0x80\n" \ + : "=a" (_ret) \ + : "r"(_arg1), "r"(_arg2), \ + "0"(_num) \ + : "memory", "cc" \ + ); \ + _ret; \ +}) + +#define my_syscall3(num, arg1, arg2, arg3) \ +({ \ + long _ret; \ + register long _num __asm__ ("eax") = (num); \ + register long _arg1 __asm__ ("ebx") = (long)(arg1); \ + register long _arg2 __asm__ ("ecx") = (long)(arg2); \ + register long _arg3 __asm__ ("edx") = (long)(arg3); \ + \ + __asm__ volatile ( \ + "int $0x80\n" \ + : "=a" (_ret) \ + : "r"(_arg1), "r"(_arg2), "r"(_arg3), \ + "0"(_num) \ + : "memory", "cc" \ + ); \ + _ret; \ +}) + +#define my_syscall4(num, arg1, arg2, arg3, arg4) \ +({ \ + long _ret; \ + register long _num __asm__ ("eax") = (num); \ + register long _arg1 __asm__ ("ebx") = (long)(arg1); \ + register long _arg2 __asm__ ("ecx") = (long)(arg2); \ + register long _arg3 __asm__ ("edx") = (long)(arg3); \ + register long _arg4 __asm__ ("esi") = (long)(arg4); \ + \ + __asm__ volatile ( \ + "int $0x80\n" \ + : "=a" (_ret) \ + : "r"(_arg1), "r"(_arg2), "r"(_arg3), "r"(_arg4), \ + "0"(_num) \ + : "memory", "cc" \ + ); \ + _ret; \ +}) + +#define my_syscall5(num, arg1, arg2, arg3, arg4, arg5) \ +({ \ + long _ret; \ + register long _num __asm__ ("eax") = (num); \ + register long _arg1 __asm__ ("ebx") = (long)(arg1); \ + register long _arg2 __asm__ ("ecx") = (long)(arg2); \ + register long _arg3 __asm__ ("edx") = (long)(arg3); \ + register long _arg4 __asm__ ("esi") = (long)(arg4); \ + register long _arg5 __asm__ ("edi") = (long)(arg5); \ + \ + __asm__ volatile ( \ + "int $0x80\n" \ + : "=a" (_ret) \ + : "r"(_arg1), "r"(_arg2), "r"(_arg3), "r"(_arg4), "r"(_arg5), \ + "0"(_num) \ + : "memory", "cc" \ + ); \ + _ret; \ +}) + +#define my_syscall6(num, arg1, arg2, arg3, arg4, arg5, arg6) \ +({ \ + long _eax = (long)(num); \ + long _arg6 = (long)(arg6); /* Always in memory */ \ + __asm__ volatile ( \ + "pushl %[_arg6]\n\t" \ + "pushl %%ebp\n\t" \ + "movl 4(%%esp),%%ebp\n\t" \ + "int $0x80\n\t" \ + "popl %%ebp\n\t" \ + "addl $4,%%esp\n\t" \ + : "+a"(_eax) /* %eax */ \ + : "b"(arg1), /* %ebx */ \ + "c"(arg2), /* %ecx */ \ + "d"(arg3), /* %edx */ \ + "S"(arg4), /* %esi */ \ + "D"(arg5), /* %edi */ \ + [_arg6]"m"(_arg6) /* memory */ \ + : "memory", "cc" \ + ); \ + _eax; \ +}) + +/* startup code */ +/* + * i386 System V ABI mandates: + * 1) last pushed argument must be 16-byte aligned. + * 2) The deepest stack frame should be set to zero + * + */ +__asm__ (".section .text\n" + ".weak _start\n" + "_start:\n" + "pop %eax\n" // argc (first arg, %eax) + "mov %esp, %ebx\n" // argv[] (second arg, %ebx) + "lea 4(%ebx,%eax,4),%ecx\n" // then a NULL then envp (third arg, %ecx) + "xor %ebp, %ebp\n" // zero the stack frame + "and $-16, %esp\n" // x86 ABI : esp must be 16-byte aligned before + "sub $4, %esp\n" // the call instruction (args are aligned) + "push %ecx\n" // push all registers on the stack so that we + "push %ebx\n" // support both regparm and plain stack modes + "push %eax\n" + "call main\n" // main() returns the status code in %eax + "mov %eax, %ebx\n" // retrieve exit code (32-bit int) + "movl $1, %eax\n" // NR_exit == 1 + "int $0x80\n" // exit now + "hlt\n" // ensure it does not + ""); + +#endif // _NOLIBC_ARCH_I386_H diff --git a/tools/include/nolibc/arch-mips.h b/tools/include/nolibc/arch-mips.h new file mode 100644 index 000000000000..5fc5b8029bff --- /dev/null +++ b/tools/include/nolibc/arch-mips.h @@ -0,0 +1,215 @@ +/* SPDX-License-Identifier: LGPL-2.1 OR MIT */ +/* + * MIPS specific definitions for NOLIBC + * Copyright (C) 2017-2022 Willy Tarreau <w@1wt.eu> + */ + +#ifndef _NOLIBC_ARCH_MIPS_H +#define _NOLIBC_ARCH_MIPS_H + +/* O_* macros for fcntl/open are architecture-specific */ +#define O_RDONLY 0 +#define O_WRONLY 1 +#define O_RDWR 2 +#define O_APPEND 0x0008 +#define O_NONBLOCK 0x0080 +#define O_CREAT 0x0100 +#define O_TRUNC 0x0200 +#define O_EXCL 0x0400 +#define O_NOCTTY 0x0800 +#define O_DIRECTORY 0x10000 + +/* The struct returned by the stat() syscall. 88 bytes are returned by the + * syscall. + */ +struct sys_stat_struct { + unsigned int st_dev; + long st_pad1[3]; + unsigned long st_ino; + unsigned int st_mode; + unsigned int st_nlink; + unsigned int st_uid; + unsigned int st_gid; + unsigned int st_rdev; + long st_pad2[2]; + long st_size; + long st_pad3; + + long st_atime; + long st_atime_nsec; + long st_mtime; + long st_mtime_nsec; + + long st_ctime; + long st_ctime_nsec; + long st_blksize; + long st_blocks; + long st_pad4[14]; +}; + +/* Syscalls for MIPS ABI O32 : + * - WARNING! there's always a delayed slot! + * - WARNING again, the syntax is different, registers take a '$' and numbers + * do not. + * - registers are 32-bit + * - stack is 8-byte aligned + * - syscall number is passed in v0 (starts at 0xfa0). + * - arguments are in a0, a1, a2, a3, then the stack. The caller needs to + * leave some room in the stack for the callee to save a0..a3 if needed. + * - Many registers are clobbered, in fact only a0..a2 and s0..s8 are + * preserved. See: https://www.linux-mips.org/wiki/Syscall as well as + * scall32-o32.S in the kernel sources. + * - the system call is performed by calling "syscall" + * - syscall return comes in v0, and register a3 needs to be checked to know + * if an error occurred, in which case errno is in v0. + * - the arguments are cast to long and assigned into the target registers + * which are then simply passed as registers to the asm code, so that we + * don't have to experience issues with register constraints. + */ + +#define my_syscall0(num) \ +({ \ + register long _num __asm__ ("v0") = (num); \ + register long _arg4 __asm__ ("a3"); \ + \ + __asm__ volatile ( \ + "addiu $sp, $sp, -32\n" \ + "syscall\n" \ + "addiu $sp, $sp, 32\n" \ + : "=r"(_num), "=r"(_arg4) \ + : "r"(_num) \ + : "memory", "cc", "at", "v1", "hi", "lo", \ + "t0", "t1", "t2", "t3", "t4", "t5", "t6", "t7", "t8", "t9" \ + ); \ + _arg4 ? -_num : _num; \ +}) + +#define my_syscall1(num, arg1) \ +({ \ + register long _num __asm__ ("v0") = (num); \ + register long _arg1 __asm__ ("a0") = (long)(arg1); \ + register long _arg4 __asm__ ("a3"); \ + \ + __asm__ volatile ( \ + "addiu $sp, $sp, -32\n" \ + "syscall\n" \ + "addiu $sp, $sp, 32\n" \ + : "=r"(_num), "=r"(_arg4) \ + : "0"(_num), \ + "r"(_arg1) \ + : "memory", "cc", "at", "v1", "hi", "lo", \ + "t0", "t1", "t2", "t3", "t4", "t5", "t6", "t7", "t8", "t9" \ + ); \ + _arg4 ? -_num : _num; \ +}) + +#define my_syscall2(num, arg1, arg2) \ +({ \ + register long _num __asm__ ("v0") = (num); \ + register long _arg1 __asm__ ("a0") = (long)(arg1); \ + register long _arg2 __asm__ ("a1") = (long)(arg2); \ + register long _arg4 __asm__ ("a3"); \ + \ + __asm__ volatile ( \ + "addiu $sp, $sp, -32\n" \ + "syscall\n" \ + "addiu $sp, $sp, 32\n" \ + : "=r"(_num), "=r"(_arg4) \ + : "0"(_num), \ + "r"(_arg1), "r"(_arg2) \ + : "memory", "cc", "at", "v1", "hi", "lo", \ + "t0", "t1", "t2", "t3", "t4", "t5", "t6", "t7", "t8", "t9" \ + ); \ + _arg4 ? -_num : _num; \ +}) + +#define my_syscall3(num, arg1, arg2, arg3) \ +({ \ + register long _num __asm__ ("v0") = (num); \ + register long _arg1 __asm__ ("a0") = (long)(arg1); \ + register long _arg2 __asm__ ("a1") = (long)(arg2); \ + register long _arg3 __asm__ ("a2") = (long)(arg3); \ + register long _arg4 __asm__ ("a3"); \ + \ + __asm__ volatile ( \ + "addiu $sp, $sp, -32\n" \ + "syscall\n" \ + "addiu $sp, $sp, 32\n" \ + : "=r"(_num), "=r"(_arg4) \ + : "0"(_num), \ + "r"(_arg1), "r"(_arg2), "r"(_arg3) \ + : "memory", "cc", "at", "v1", "hi", "lo", \ + "t0", "t1", "t2", "t3", "t4", "t5", "t6", "t7", "t8", "t9" \ + ); \ + _arg4 ? -_num : _num; \ +}) + +#define my_syscall4(num, arg1, arg2, arg3, arg4) \ +({ \ + register long _num __asm__ ("v0") = (num); \ + register long _arg1 __asm__ ("a0") = (long)(arg1); \ + register long _arg2 __asm__ ("a1") = (long)(arg2); \ + register long _arg3 __asm__ ("a2") = (long)(arg3); \ + register long _arg4 __asm__ ("a3") = (long)(arg4); \ + \ + __asm__ volatile ( \ + "addiu $sp, $sp, -32\n" \ + "syscall\n" \ + "addiu $sp, $sp, 32\n" \ + : "=r" (_num), "=r"(_arg4) \ + : "0"(_num), \ + "r"(_arg1), "r"(_arg2), "r"(_arg3), "r"(_arg4) \ + : "memory", "cc", "at", "v1", "hi", "lo", \ + "t0", "t1", "t2", "t3", "t4", "t5", "t6", "t7", "t8", "t9" \ + ); \ + _arg4 ? -_num : _num; \ +}) + +#define my_syscall5(num, arg1, arg2, arg3, arg4, arg5) \ +({ \ + register long _num __asm__ ("v0") = (num); \ + register long _arg1 __asm__ ("a0") = (long)(arg1); \ + register long _arg2 __asm__ ("a1") = (long)(arg2); \ + register long _arg3 __asm__ ("a2") = (long)(arg3); \ + register long _arg4 __asm__ ("a3") = (long)(arg4); \ + register long _arg5 = (long)(arg5); \ + \ + __asm__ volatile ( \ + "addiu $sp, $sp, -32\n" \ + "sw %7, 16($sp)\n" \ + "syscall\n " \ + "addiu $sp, $sp, 32\n" \ + : "=r" (_num), "=r"(_arg4) \ + : "0"(_num), \ + "r"(_arg1), "r"(_arg2), "r"(_arg3), "r"(_arg4), "r"(_arg5) \ + : "memory", "cc", "at", "v1", "hi", "lo", \ + "t0", "t1", "t2", "t3", "t4", "t5", "t6", "t7", "t8", "t9" \ + ); \ + _arg4 ? -_num : _num; \ +}) + +/* startup code, note that it's called __start on MIPS */ +__asm__ (".section .text\n" + ".weak __start\n" + ".set nomips16\n" + ".set noreorder\n" + ".option pic0\n" + ".ent __start\n" + "__start:\n" + "lw $a0,($sp)\n" // argc was in the stack + "addiu $a1, $sp, 4\n" // argv = sp + 4 + "sll $a2, $a0, 2\n" // a2 = argc * 4 + "add $a2, $a2, $a1\n" // envp = argv + 4*argc ... + "addiu $a2, $a2, 4\n" // ... + 4 + "li $t0, -8\n" + "and $sp, $sp, $t0\n" // sp must be 8-byte aligned + "addiu $sp,$sp,-16\n" // the callee expects to save a0..a3 there! + "jal main\n" // main() returns the status code, we'll exit with it. + "nop\n" // delayed slot + "move $a0, $v0\n" // retrieve 32-bit exit code from v0 + "li $v0, 4001\n" // NR_exit == 4001 + "syscall\n" + ".end __start\n" + ""); + +#endif // _NOLIBC_ARCH_MIPS_H diff --git a/tools/include/nolibc/arch-riscv.h b/tools/include/nolibc/arch-riscv.h new file mode 100644 index 000000000000..95e2b7924925 --- /dev/null +++ b/tools/include/nolibc/arch-riscv.h @@ -0,0 +1,204 @@ +/* SPDX-License-Identifier: LGPL-2.1 OR MIT */ +/* + * RISCV (32 and 64) specific definitions for NOLIBC + * Copyright (C) 2017-2022 Willy Tarreau <w@1wt.eu> + */ + +#ifndef _NOLIBC_ARCH_RISCV_H +#define _NOLIBC_ARCH_RISCV_H + +/* O_* macros for fcntl/open are architecture-specific */ +#define O_RDONLY 0 +#define O_WRONLY 1 +#define O_RDWR 2 +#define O_CREAT 0x100 +#define O_EXCL 0x200 +#define O_NOCTTY 0x400 +#define O_TRUNC 0x1000 +#define O_APPEND 0x2000 +#define O_NONBLOCK 0x4000 +#define O_DIRECTORY 0x200000 + +struct sys_stat_struct { + unsigned long st_dev; /* Device. */ + unsigned long st_ino; /* File serial number. */ + unsigned int st_mode; /* File mode. */ + unsigned int st_nlink; /* Link count. */ + unsigned int st_uid; /* User ID of the file's owner. */ + unsigned int st_gid; /* Group ID of the file's group. */ + unsigned long st_rdev; /* Device number, if device. */ + unsigned long __pad1; + long st_size; /* Size of file, in bytes. */ + int st_blksize; /* Optimal block size for I/O. */ + int __pad2; + long st_blocks; /* Number 512-byte blocks allocated. */ + long st_atime; /* Time of last access. */ + unsigned long st_atime_nsec; + long st_mtime; /* Time of last modification. */ + unsigned long st_mtime_nsec; + long st_ctime; /* Time of last status change. */ + unsigned long st_ctime_nsec; + unsigned int __unused4; + unsigned int __unused5; +}; + +#if __riscv_xlen == 64 +#define PTRLOG "3" +#define SZREG "8" +#elif __riscv_xlen == 32 +#define PTRLOG "2" +#define SZREG "4" +#endif + +/* Syscalls for RISCV : + * - stack is 16-byte aligned + * - syscall number is passed in a7 + * - arguments are in a0, a1, a2, a3, a4, a5 + * - the system call is performed by calling ecall + * - syscall return comes in a0 + * - the arguments are cast to long and assigned into the target + * registers which are then simply passed as registers to the asm code, + * so that we don't have to experience issues with register constraints. + * + * On riscv, select() is not implemented so we have to use pselect6(). + */ +#define __ARCH_WANT_SYS_PSELECT6 + +#define my_syscall0(num) \ +({ \ + register long _num __asm__ ("a7") = (num); \ + register long _arg1 __asm__ ("a0"); \ + \ + __asm__ volatile ( \ + "ecall\n\t" \ + : "=r"(_arg1) \ + : "r"(_num) \ + : "memory", "cc" \ + ); \ + _arg1; \ +}) + +#define my_syscall1(num, arg1) \ +({ \ + register long _num __asm__ ("a7") = (num); \ + register long _arg1 __asm__ ("a0") = (long)(arg1); \ + \ + __asm__ volatile ( \ + "ecall\n" \ + : "+r"(_arg1) \ + : "r"(_num) \ + : "memory", "cc" \ + ); \ + _arg1; \ +}) + +#define my_syscall2(num, arg1, arg2) \ +({ \ + register long _num __asm__ ("a7") = (num); \ + register long _arg1 __asm__ ("a0") = (long)(arg1); \ + register long _arg2 __asm__ ("a1") = (long)(arg2); \ + \ + __asm__ volatile ( \ + "ecall\n" \ + : "+r"(_arg1) \ + : "r"(_arg2), \ + "r"(_num) \ + : "memory", "cc" \ + ); \ + _arg1; \ +}) + +#define my_syscall3(num, arg1, arg2, arg3) \ +({ \ + register long _num __asm__ ("a7") = (num); \ + register long _arg1 __asm__ ("a0") = (long)(arg1); \ + register long _arg2 __asm__ ("a1") = (long)(arg2); \ + register long _arg3 __asm__ ("a2") = (long)(arg3); \ + \ + __asm__ volatile ( \ + "ecall\n\t" \ + : "+r"(_arg1) \ + : "r"(_arg2), "r"(_arg3), \ + "r"(_num) \ + : "memory", "cc" \ + ); \ + _arg1; \ +}) + +#define my_syscall4(num, arg1, arg2, arg3, arg4) \ +({ \ + register long _num __asm__ ("a7") = (num); \ + register long _arg1 __asm__ ("a0") = (long)(arg1); \ + register long _arg2 __asm__ ("a1") = (long)(arg2); \ + register long _arg3 __asm__ ("a2") = (long)(arg3); \ + register long _arg4 __asm__ ("a3") = (long)(arg4); \ + \ + __asm__ volatile ( \ + "ecall\n" \ + : "+r"(_arg1) \ + : "r"(_arg2), "r"(_arg3), "r"(_arg4), \ + "r"(_num) \ + : "memory", "cc" \ + ); \ + _arg1; \ +}) + +#define my_syscall5(num, arg1, arg2, arg3, arg4, arg5) \ +({ \ + register long _num __asm__ ("a7") = (num); \ + register long _arg1 __asm__ ("a0") = (long)(arg1); \ + register long _arg2 __asm__ ("a1") = (long)(arg2); \ + register long _arg3 __asm__ ("a2") = (long)(arg3); \ + register long _arg4 __asm__ ("a3") = (long)(arg4); \ + register long _arg5 __asm__ ("a4") = (long)(arg5); \ + \ + __asm__ volatile ( \ + "ecall\n" \ + : "+r"(_arg1) \ + : "r"(_arg2), "r"(_arg3), "r"(_arg4), "r"(_arg5), \ + "r"(_num) \ + : "memory", "cc" \ + ); \ + _arg1; \ +}) + +#define my_syscall6(num, arg1, arg2, arg3, arg4, arg5, arg6) \ +({ \ + register long _num __asm__ ("a7") = (num); \ + register long _arg1 __asm__ ("a0") = (long)(arg1); \ + register long _arg2 __asm__ ("a1") = (long)(arg2); \ + register long _arg3 __asm__ ("a2") = (long)(arg3); \ + register long _arg4 __asm__ ("a3") = (long)(arg4); \ + register long _arg5 __asm__ ("a4") = (long)(arg5); \ + register long _arg6 __asm__ ("a5") = (long)(arg6); \ + \ + __asm__ volatile ( \ + "ecall\n" \ + : "+r"(_arg1) \ + : "r"(_arg2), "r"(_arg3), "r"(_arg4), "r"(_arg5), "r"(_arg6), \ + "r"(_num) \ + : "memory", "cc" \ + ); \ + _arg1; \ +}) + +/* startup code */ +__asm__ (".section .text\n" + ".weak _start\n" + "_start:\n" + ".option push\n" + ".option norelax\n" + "lla gp, __global_pointer$\n" + ".option pop\n" + "ld a0, 0(sp)\n" // argc (a0) was in the stack + "add a1, sp, "SZREG"\n" // argv (a1) = sp + "slli a2, a0, "PTRLOG"\n" // envp (a2) = SZREG*argc ... + "add a2, a2, "SZREG"\n" // + SZREG (skip null) + "add a2,a2,a1\n" // + argv + "andi sp,a1,-16\n" // sp must be 16-byte aligned + "call main\n" // main() returns the status code, we'll exit with it. + "li a7, 93\n" // NR_exit == 93 + "ecall\n" + ""); + +#endif // _NOLIBC_ARCH_RISCV_H diff --git a/tools/include/nolibc/arch-x86_64.h b/tools/include/nolibc/arch-x86_64.h new file mode 100644 index 000000000000..0e1e9eb8545d --- /dev/null +++ b/tools/include/nolibc/arch-x86_64.h @@ -0,0 +1,215 @@ +/* SPDX-License-Identifier: LGPL-2.1 OR MIT */ +/* + * x86_64 specific definitions for NOLIBC + * Copyright (C) 2017-2022 Willy Tarreau <w@1wt.eu> + */ + +#ifndef _NOLIBC_ARCH_X86_64_H +#define _NOLIBC_ARCH_X86_64_H + +/* O_* macros for fcntl/open are architecture-specific */ +#define O_RDONLY 0 +#define O_WRONLY 1 +#define O_RDWR 2 +#define O_CREAT 0x40 +#define O_EXCL 0x80 +#define O_NOCTTY 0x100 +#define O_TRUNC 0x200 +#define O_APPEND 0x400 +#define O_NONBLOCK 0x800 +#define O_DIRECTORY 0x10000 + +/* The struct returned by the stat() syscall, equivalent to stat64(). The + * syscall returns 116 bytes and stops in the middle of __unused. + */ +struct sys_stat_struct { + unsigned long st_dev; + unsigned long st_ino; + unsigned long st_nlink; + unsigned int st_mode; + unsigned int st_uid; + + unsigned int st_gid; + unsigned int __pad0; + unsigned long st_rdev; + long st_size; + long st_blksize; + + long st_blocks; + unsigned long st_atime; + unsigned long st_atime_nsec; + unsigned long st_mtime; + + unsigned long st_mtime_nsec; + unsigned long st_ctime; + unsigned long st_ctime_nsec; + long __unused[3]; +}; + +/* Syscalls for x86_64 : + * - registers are 64-bit + * - syscall number is passed in rax + * - arguments are in rdi, rsi, rdx, r10, r8, r9 respectively + * - the system call is performed by calling the syscall instruction + * - syscall return comes in rax + * - rcx and r11 are clobbered, others are preserved. + * - the arguments are cast to long and assigned into the target registers + * which are then simply passed as registers to the asm code, so that we + * don't have to experience issues with register constraints. + * - the syscall number is always specified last in order to allow to force + * some registers before (gcc refuses a %-register at the last position). + * - see also x86-64 ABI section A.2 AMD64 Linux Kernel Conventions, A.2.1 + * Calling Conventions. + * + * Link x86-64 ABI: https://gitlab.com/x86-psABIs/x86-64-ABI/-/wikis/home + * + */ + +#define my_syscall0(num) \ +({ \ + long _ret; \ + register long _num __asm__ ("rax") = (num); \ + \ + __asm__ volatile ( \ + "syscall\n" \ + : "=a"(_ret) \ + : "0"(_num) \ + : "rcx", "r11", "memory", "cc" \ + ); \ + _ret; \ +}) + +#define my_syscall1(num, arg1) \ +({ \ + long _ret; \ + register long _num __asm__ ("rax") = (num); \ + register long _arg1 __asm__ ("rdi") = (long)(arg1); \ + \ + __asm__ volatile ( \ + "syscall\n" \ + : "=a"(_ret) \ + : "r"(_arg1), \ + "0"(_num) \ + : "rcx", "r11", "memory", "cc" \ + ); \ + _ret; \ +}) + +#define my_syscall2(num, arg1, arg2) \ +({ \ + long _ret; \ + register long _num __asm__ ("rax") = (num); \ + register long _arg1 __asm__ ("rdi") = (long)(arg1); \ + register long _arg2 __asm__ ("rsi") = (long)(arg2); \ + \ + __asm__ volatile ( \ + "syscall\n" \ + : "=a"(_ret) \ + : "r"(_arg1), "r"(_arg2), \ + "0"(_num) \ + : "rcx", "r11", "memory", "cc" \ + ); \ + _ret; \ +}) + +#define my_syscall3(num, arg1, arg2, arg3) \ +({ \ + long _ret; \ + register long _num __asm__ ("rax") = (num); \ + register long _arg1 __asm__ ("rdi") = (long)(arg1); \ + register long _arg2 __asm__ ("rsi") = (long)(arg2); \ + register long _arg3 __asm__ ("rdx") = (long)(arg3); \ + \ + __asm__ volatile ( \ + "syscall\n" \ + : "=a"(_ret) \ + : "r"(_arg1), "r"(_arg2), "r"(_arg3), \ + "0"(_num) \ + : "rcx", "r11", "memory", "cc" \ + ); \ + _ret; \ +}) + +#define my_syscall4(num, arg1, arg2, arg3, arg4) \ +({ \ + long _ret; \ + register long _num __asm__ ("rax") = (num); \ + register long _arg1 __asm__ ("rdi") = (long)(arg1); \ + register long _arg2 __asm__ ("rsi") = (long)(arg2); \ + register long _arg3 __asm__ ("rdx") = (long)(arg3); \ + register long _arg4 __asm__ ("r10") = (long)(arg4); \ + \ + __asm__ volatile ( \ + "syscall\n" \ + : "=a"(_ret) \ + : "r"(_arg1), "r"(_arg2), "r"(_arg3), "r"(_arg4), \ + "0"(_num) \ + : "rcx", "r11", "memory", "cc" \ + ); \ + _ret; \ +}) + +#define my_syscall5(num, arg1, arg2, arg3, arg4, arg5) \ +({ \ + long _ret; \ + register long _num __asm__ ("rax") = (num); \ + register long _arg1 __asm__ ("rdi") = (long)(arg1); \ + register long _arg2 __asm__ ("rsi") = (long)(arg2); \ + register long _arg3 __asm__ ("rdx") = (long)(arg3); \ + register long _arg4 __asm__ ("r10") = (long)(arg4); \ + register long _arg5 __asm__ ("r8") = (long)(arg5); \ + \ + __asm__ volatile ( \ + "syscall\n" \ + : "=a"(_ret) \ + : "r"(_arg1), "r"(_arg2), "r"(_arg3), "r"(_arg4), "r"(_arg5), \ + "0"(_num) \ + : "rcx", "r11", "memory", "cc" \ + ); \ + _ret; \ +}) + +#define my_syscall6(num, arg1, arg2, arg3, arg4, arg5, arg6) \ +({ \ + long _ret; \ + register long _num __asm__ ("rax") = (num); \ + register long _arg1 __asm__ ("rdi") = (long)(arg1); \ + register long _arg2 __asm__ ("rsi") = (long)(arg2); \ + register long _arg3 __asm__ ("rdx") = (long)(arg3); \ + register long _arg4 __asm__ ("r10") = (long)(arg4); \ + register long _arg5 __asm__ ("r8") = (long)(arg5); \ + register long _arg6 __asm__ ("r9") = (long)(arg6); \ + \ + __asm__ volatile ( \ + "syscall\n" \ + : "=a"(_ret) \ + : "r"(_arg1), "r"(_arg2), "r"(_arg3), "r"(_arg4), "r"(_arg5), \ + "r"(_arg6), "0"(_num) \ + : "rcx", "r11", "memory", "cc" \ + ); \ + _ret; \ +}) + +/* startup code */ +/* + * x86-64 System V ABI mandates: + * 1) %rsp must be 16-byte aligned right before the function call. + * 2) The deepest stack frame should be zero (the %rbp). + * + */ +__asm__ (".section .text\n" + ".weak _start\n" + "_start:\n" + "pop %rdi\n" // argc (first arg, %rdi) + "mov %rsp, %rsi\n" // argv[] (second arg, %rsi) + "lea 8(%rsi,%rdi,8),%rdx\n" // then a NULL then envp (third arg, %rdx) + "xor %ebp, %ebp\n" // zero the stack frame + "and $-16, %rsp\n" // x86 ABI : esp must be 16-byte aligned before call + "call main\n" // main() returns the status code, we'll exit with it. + "mov %eax, %edi\n" // retrieve exit code (32 bit) + "mov $60, %eax\n" // NR_exit == 60 + "syscall\n" // really exit + "hlt\n" // ensure it does not return + ""); + +#endif // _NOLIBC_ARCH_X86_64_H diff --git a/tools/include/nolibc/arch.h b/tools/include/nolibc/arch.h new file mode 100644 index 000000000000..4c6992321b0d --- /dev/null +++ b/tools/include/nolibc/arch.h @@ -0,0 +1,32 @@ +/* SPDX-License-Identifier: LGPL-2.1 OR MIT */ +/* + * Copyright (C) 2017-2022 Willy Tarreau <w@1wt.eu> + */ + +/* Below comes the architecture-specific code. For each architecture, we have + * the syscall declarations and the _start code definition. This is the only + * global part. On all architectures the kernel puts everything in the stack + * before jumping to _start just above us, without any return address (_start + * is not a function but an entry pint). So at the stack pointer we find argc. + * Then argv[] begins, and ends at the first NULL. Then we have envp which + * starts and ends with a NULL as well. So envp=argv+argc+1. + */ + +#ifndef _NOLIBC_ARCH_H +#define _NOLIBC_ARCH_H + +#if defined(__x86_64__) +#include "arch-x86_64.h" +#elif defined(__i386__) || defined(__i486__) || defined(__i586__) || defined(__i686__) +#include "arch-i386.h" +#elif defined(__ARM_EABI__) +#include "arch-arm.h" +#elif defined(__aarch64__) +#include "arch-aarch64.h" +#elif defined(__mips__) && defined(_ABIO32) +#include "arch-mips.h" +#elif defined(__riscv) +#include "arch-riscv.h" +#endif + +#endif /* _NOLIBC_ARCH_H */ diff --git a/tools/include/nolibc/ctype.h b/tools/include/nolibc/ctype.h new file mode 100644 index 000000000000..e3000b2992d7 --- /dev/null +++ b/tools/include/nolibc/ctype.h @@ -0,0 +1,99 @@ +/* SPDX-License-Identifier: LGPL-2.1 OR MIT */ +/* + * ctype function definitions for NOLIBC + * Copyright (C) 2017-2021 Willy Tarreau <w@1wt.eu> + */ + +#ifndef _NOLIBC_CTYPE_H +#define _NOLIBC_CTYPE_H + +#include "std.h" + +/* + * As much as possible, please keep functions alphabetically sorted. + */ + +static __attribute__((unused)) +int isascii(int c) +{ + /* 0x00..0x7f */ + return (unsigned int)c <= 0x7f; +} + +static __attribute__((unused)) +int isblank(int c) +{ + return c == '\t' || c == ' '; +} + +static __attribute__((unused)) +int iscntrl(int c) +{ + /* 0x00..0x1f, 0x7f */ + return (unsigned int)c < 0x20 || c == 0x7f; +} + +static __attribute__((unused)) +int isdigit(int c) +{ + return (unsigned int)(c - '0') < 10; +} + +static __attribute__((unused)) +int isgraph(int c) +{ + /* 0x21..0x7e */ + return (unsigned int)(c - 0x21) < 0x5e; +} + +static __attribute__((unused)) +int islower(int c) +{ + return (unsigned int)(c - 'a') < 26; +} + +static __attribute__((unused)) +int isprint(int c) +{ + /* 0x20..0x7e */ + return (unsigned int)(c - 0x20) < 0x5f; +} + +static __attribute__((unused)) +int isspace(int c) +{ + /* \t is 0x9, \n is 0xA, \v is 0xB, \f is 0xC, \r is 0xD */ + return ((unsigned int)c == ' ') || (unsigned int)(c - 0x09) < 5; +} + +static __attribute__((unused)) +int isupper(int c) +{ + return (unsigned int)(c - 'A') < 26; +} + +static __attribute__((unused)) +int isxdigit(int c) +{ + return isdigit(c) || (unsigned int)(c - 'A') < 6 || (unsigned int)(c - 'a') < 6; +} + +static __attribute__((unused)) +int isalpha(int c) +{ + return islower(c) || isupper(c); +} + +static __attribute__((unused)) +int isalnum(int c) +{ + return isalpha(c) || isdigit(c); +} + +static __attribute__((unused)) +int ispunct(int c) +{ + return isgraph(c) && !isalnum(c); +} + +#endif /* _NOLIBC_CTYPE_H */ diff --git a/tools/include/nolibc/errno.h b/tools/include/nolibc/errno.h new file mode 100644 index 000000000000..06893d6dfb7a --- /dev/null +++ b/tools/include/nolibc/errno.h @@ -0,0 +1,27 @@ +/* SPDX-License-Identifier: LGPL-2.1 OR MIT */ +/* + * Minimal errno definitions for NOLIBC + * Copyright (C) 2017-2022 Willy Tarreau <w@1wt.eu> + */ + +#ifndef _NOLIBC_ERRNO_H +#define _NOLIBC_ERRNO_H + +#include <asm/errno.h> + +/* this way it will be removed if unused */ +static int errno; + +#ifndef NOLIBC_IGNORE_ERRNO +#define SET_ERRNO(v) do { errno = (v); } while (0) +#else +#define SET_ERRNO(v) do { } while (0) +#endif + + +/* errno codes all ensure that they will not conflict with a valid pointer + * because they all correspond to the highest addressable memory page. + */ +#define MAX_ERRNO 4095 + +#endif /* _NOLIBC_ERRNO_H */ diff --git a/tools/include/nolibc/nolibc.h b/tools/include/nolibc/nolibc.h index c1c285fe494a..b2bc48d3cfe4 100644 --- a/tools/include/nolibc/nolibc.h +++ b/tools/include/nolibc/nolibc.h @@ -57,22 +57,32 @@ * having to specify anything. * * Finally some very common libc-level functions are provided. It is the case - * for a few functions usually found in string.h, ctype.h, or stdlib.h. Nothing - * is currently provided regarding stdio emulation. + * for a few functions usually found in string.h, ctype.h, or stdlib.h. * - * The macro NOLIBC is always defined, so that it is possible for a program to - * check this macro to know if it is being built against and decide to disable - * some features or simply not to include some standard libc files. - * - * Ideally this file should be split in multiple files for easier long term - * maintenance, but provided as a single file as it is now, it's quite - * convenient to use. Maybe some variations involving a set of includes at the - * top could work. + * The nolibc.h file is only a convenient entry point which includes all other + * files. It also defines the NOLIBC macro, so that it is possible for a + * program to check this macro to know if it is being built against and decide + * to disable some features or simply not to include some standard libc files. * * A simple static executable may be built this way : * $ gcc -fno-asynchronous-unwind-tables -fno-ident -s -Os -nostdlib \ * -static -include nolibc.h -o hello hello.c -lgcc * + * Simple programs meant to be reasonably portable to various libc and using + * only a few common includes, may also be built by simply making the include + * path point to the nolibc directory: + * $ gcc -fno-asynchronous-unwind-tables -fno-ident -s -Os -nostdlib \ + * -I../nolibc -o hello hello.c -lgcc + * + * The available standard (but limited) include files are: + * ctype.h, errno.h, signal.h, stdio.h, stdlib.h, string.h, time.h + * + * In addition, the following ones are expected to be provided by the compiler: + * float.h, stdarg.h, stddef.h + * + * The following ones which are part to the C standard are not provided: + * assert.h, locale.h, math.h, setjmp.h, limits.h + * * A very useful calling convention table may be found here : * http://man7.org/linux/man-pages/man2/syscall.2.html * @@ -80,2502 +90,22 @@ * https://w3challs.com/syscalls/ * */ +#ifndef _NOLIBC_H +#define _NOLIBC_H -#include <asm/unistd.h> -#include <asm/ioctls.h> -#include <asm/errno.h> -#include <linux/fs.h> -#include <linux/loop.h> -#include <linux/time.h> +#include "std.h" +#include "arch.h" +#include "types.h" +#include "sys.h" +#include "ctype.h" +#include "signal.h" +#include "stdio.h" +#include "stdlib.h" +#include "string.h" +#include "time.h" +#include "unistd.h" +/* Used by programs to avoid std includes */ #define NOLIBC -/* this way it will be removed if unused */ -static int errno; - -#ifndef NOLIBC_IGNORE_ERRNO -#define SET_ERRNO(v) do { errno = (v); } while (0) -#else -#define SET_ERRNO(v) do { } while (0) -#endif - -/* errno codes all ensure that they will not conflict with a valid pointer - * because they all correspond to the highest addressable memory page. - */ -#define MAX_ERRNO 4095 - -/* Declare a few quite common macros and types that usually are in stdlib.h, - * stdint.h, ctype.h, unistd.h and a few other common locations. - */ - -#define NULL ((void *)0) - -/* stdint types */ -typedef unsigned char uint8_t; -typedef signed char int8_t; -typedef unsigned short uint16_t; -typedef signed short int16_t; -typedef unsigned int uint32_t; -typedef signed int int32_t; -typedef unsigned long long uint64_t; -typedef signed long long int64_t; -typedef unsigned long size_t; -typedef signed long ssize_t; -typedef unsigned long uintptr_t; -typedef signed long intptr_t; -typedef signed long ptrdiff_t; - -/* for stat() */ -typedef unsigned int dev_t; -typedef unsigned long ino_t; -typedef unsigned int mode_t; -typedef signed int pid_t; -typedef unsigned int uid_t; -typedef unsigned int gid_t; -typedef unsigned long nlink_t; -typedef signed long off_t; -typedef signed long blksize_t; -typedef signed long blkcnt_t; -typedef signed long time_t; - -/* for poll() */ -struct pollfd { - int fd; - short int events; - short int revents; -}; - -/* for getdents64() */ -struct linux_dirent64 { - uint64_t d_ino; - int64_t d_off; - unsigned short d_reclen; - unsigned char d_type; - char d_name[]; -}; - -/* commonly an fd_set represents 256 FDs */ -#define FD_SETSIZE 256 -typedef struct { uint32_t fd32[FD_SETSIZE/32]; } fd_set; - -/* needed by wait4() */ -struct rusage { - struct timeval ru_utime; - struct timeval ru_stime; - long ru_maxrss; - long ru_ixrss; - long ru_idrss; - long ru_isrss; - long ru_minflt; - long ru_majflt; - long ru_nswap; - long ru_inblock; - long ru_oublock; - long ru_msgsnd; - long ru_msgrcv; - long ru_nsignals; - long ru_nvcsw; - long ru_nivcsw; -}; - -/* stat flags (WARNING, octal here) */ -#define S_IFDIR 0040000 -#define S_IFCHR 0020000 -#define S_IFBLK 0060000 -#define S_IFREG 0100000 -#define S_IFIFO 0010000 -#define S_IFLNK 0120000 -#define S_IFSOCK 0140000 -#define S_IFMT 0170000 - -#define S_ISDIR(mode) (((mode) & S_IFDIR) == S_IFDIR) -#define S_ISCHR(mode) (((mode) & S_IFCHR) == S_IFCHR) -#define S_ISBLK(mode) (((mode) & S_IFBLK) == S_IFBLK) -#define S_ISREG(mode) (((mode) & S_IFREG) == S_IFREG) -#define S_ISFIFO(mode) (((mode) & S_IFIFO) == S_IFIFO) -#define S_ISLNK(mode) (((mode) & S_IFLNK) == S_IFLNK) -#define S_ISSOCK(mode) (((mode) & S_IFSOCK) == S_IFSOCK) - -#define DT_UNKNOWN 0 -#define DT_FIFO 1 -#define DT_CHR 2 -#define DT_DIR 4 -#define DT_BLK 6 -#define DT_REG 8 -#define DT_LNK 10 -#define DT_SOCK 12 - -/* all the *at functions */ -#ifndef AT_FDCWD -#define AT_FDCWD -100 -#endif - -/* lseek */ -#define SEEK_SET 0 -#define SEEK_CUR 1 -#define SEEK_END 2 - -/* reboot */ -#define LINUX_REBOOT_MAGIC1 0xfee1dead -#define LINUX_REBOOT_MAGIC2 0x28121969 -#define LINUX_REBOOT_CMD_HALT 0xcdef0123 -#define LINUX_REBOOT_CMD_POWER_OFF 0x4321fedc -#define LINUX_REBOOT_CMD_RESTART 0x01234567 -#define LINUX_REBOOT_CMD_SW_SUSPEND 0xd000fce2 - - -/* The format of the struct as returned by the libc to the application, which - * significantly differs from the format returned by the stat() syscall flavours. - */ -struct stat { - dev_t st_dev; /* ID of device containing file */ - ino_t st_ino; /* inode number */ - mode_t st_mode; /* protection */ - nlink_t st_nlink; /* number of hard links */ - uid_t st_uid; /* user ID of owner */ - gid_t st_gid; /* group ID of owner */ - dev_t st_rdev; /* device ID (if special file) */ - off_t st_size; /* total size, in bytes */ - blksize_t st_blksize; /* blocksize for file system I/O */ - blkcnt_t st_blocks; /* number of 512B blocks allocated */ - time_t st_atime; /* time of last access */ - time_t st_mtime; /* time of last modification */ - time_t st_ctime; /* time of last status change */ -}; - -#define WEXITSTATUS(status) (((status) & 0xff00) >> 8) -#define WIFEXITED(status) (((status) & 0x7f) == 0) - -/* for SIGCHLD */ -#include <asm/signal.h> - -/* Below comes the architecture-specific code. For each architecture, we have - * the syscall declarations and the _start code definition. This is the only - * global part. On all architectures the kernel puts everything in the stack - * before jumping to _start just above us, without any return address (_start - * is not a function but an entry pint). So at the stack pointer we find argc. - * Then argv[] begins, and ends at the first NULL. Then we have envp which - * starts and ends with a NULL as well. So envp=argv+argc+1. - */ - -#if defined(__x86_64__) -/* Syscalls for x86_64 : - * - registers are 64-bit - * - syscall number is passed in rax - * - arguments are in rdi, rsi, rdx, r10, r8, r9 respectively - * - the system call is performed by calling the syscall instruction - * - syscall return comes in rax - * - rcx and r11 are clobbered, others are preserved. - * - the arguments are cast to long and assigned into the target registers - * which are then simply passed as registers to the asm code, so that we - * don't have to experience issues with register constraints. - * - the syscall number is always specified last in order to allow to force - * some registers before (gcc refuses a %-register at the last position). - * - see also x86-64 ABI section A.2 AMD64 Linux Kernel Conventions, A.2.1 - * Calling Conventions. - * - * Link x86-64 ABI: https://gitlab.com/x86-psABIs/x86-64-ABI/-/wikis/x86-64-psABI - * - */ - -#define my_syscall0(num) \ -({ \ - long _ret; \ - register long _num asm("rax") = (num); \ - \ - asm volatile ( \ - "syscall\n" \ - : "=a"(_ret) \ - : "0"(_num) \ - : "rcx", "r11", "memory", "cc" \ - ); \ - _ret; \ -}) - -#define my_syscall1(num, arg1) \ -({ \ - long _ret; \ - register long _num asm("rax") = (num); \ - register long _arg1 asm("rdi") = (long)(arg1); \ - \ - asm volatile ( \ - "syscall\n" \ - : "=a"(_ret) \ - : "r"(_arg1), \ - "0"(_num) \ - : "rcx", "r11", "memory", "cc" \ - ); \ - _ret; \ -}) - -#define my_syscall2(num, arg1, arg2) \ -({ \ - long _ret; \ - register long _num asm("rax") = (num); \ - register long _arg1 asm("rdi") = (long)(arg1); \ - register long _arg2 asm("rsi") = (long)(arg2); \ - \ - asm volatile ( \ - "syscall\n" \ - : "=a"(_ret) \ - : "r"(_arg1), "r"(_arg2), \ - "0"(_num) \ - : "rcx", "r11", "memory", "cc" \ - ); \ - _ret; \ -}) - -#define my_syscall3(num, arg1, arg2, arg3) \ -({ \ - long _ret; \ - register long _num asm("rax") = (num); \ - register long _arg1 asm("rdi") = (long)(arg1); \ - register long _arg2 asm("rsi") = (long)(arg2); \ - register long _arg3 asm("rdx") = (long)(arg3); \ - \ - asm volatile ( \ - "syscall\n" \ - : "=a"(_ret) \ - : "r"(_arg1), "r"(_arg2), "r"(_arg3), \ - "0"(_num) \ - : "rcx", "r11", "memory", "cc" \ - ); \ - _ret; \ -}) - -#define my_syscall4(num, arg1, arg2, arg3, arg4) \ -({ \ - long _ret; \ - register long _num asm("rax") = (num); \ - register long _arg1 asm("rdi") = (long)(arg1); \ - register long _arg2 asm("rsi") = (long)(arg2); \ - register long _arg3 asm("rdx") = (long)(arg3); \ - register long _arg4 asm("r10") = (long)(arg4); \ - \ - asm volatile ( \ - "syscall\n" \ - : "=a"(_ret) \ - : "r"(_arg1), "r"(_arg2), "r"(_arg3), "r"(_arg4), \ - "0"(_num) \ - : "rcx", "r11", "memory", "cc" \ - ); \ - _ret; \ -}) - -#define my_syscall5(num, arg1, arg2, arg3, arg4, arg5) \ -({ \ - long _ret; \ - register long _num asm("rax") = (num); \ - register long _arg1 asm("rdi") = (long)(arg1); \ - register long _arg2 asm("rsi") = (long)(arg2); \ - register long _arg3 asm("rdx") = (long)(arg3); \ - register long _arg4 asm("r10") = (long)(arg4); \ - register long _arg5 asm("r8") = (long)(arg5); \ - \ - asm volatile ( \ - "syscall\n" \ - : "=a"(_ret) \ - : "r"(_arg1), "r"(_arg2), "r"(_arg3), "r"(_arg4), "r"(_arg5), \ - "0"(_num) \ - : "rcx", "r11", "memory", "cc" \ - ); \ - _ret; \ -}) - -#define my_syscall6(num, arg1, arg2, arg3, arg4, arg5, arg6) \ -({ \ - long _ret; \ - register long _num asm("rax") = (num); \ - register long _arg1 asm("rdi") = (long)(arg1); \ - register long _arg2 asm("rsi") = (long)(arg2); \ - register long _arg3 asm("rdx") = (long)(arg3); \ - register long _arg4 asm("r10") = (long)(arg4); \ - register long _arg5 asm("r8") = (long)(arg5); \ - register long _arg6 asm("r9") = (long)(arg6); \ - \ - asm volatile ( \ - "syscall\n" \ - : "=a"(_ret) \ - : "r"(_arg1), "r"(_arg2), "r"(_arg3), "r"(_arg4), "r"(_arg5), \ - "r"(_arg6), "0"(_num) \ - : "rcx", "r11", "memory", "cc" \ - ); \ - _ret; \ -}) - -/* startup code */ -/* - * x86-64 System V ABI mandates: - * 1) %rsp must be 16-byte aligned right before the function call. - * 2) The deepest stack frame should be zero (the %rbp). - * - */ -asm(".section .text\n" - ".global _start\n" - "_start:\n" - "pop %rdi\n" // argc (first arg, %rdi) - "mov %rsp, %rsi\n" // argv[] (second arg, %rsi) - "lea 8(%rsi,%rdi,8),%rdx\n" // then a NULL then envp (third arg, %rdx) - "xor %ebp, %ebp\n" // zero the stack frame - "and $-16, %rsp\n" // x86 ABI : esp must be 16-byte aligned before call - "call main\n" // main() returns the status code, we'll exit with it. - "mov %eax, %edi\n" // retrieve exit code (32 bit) - "mov $60, %eax\n" // NR_exit == 60 - "syscall\n" // really exit - "hlt\n" // ensure it does not return - ""); - -/* fcntl / open */ -#define O_RDONLY 0 -#define O_WRONLY 1 -#define O_RDWR 2 -#define O_CREAT 0x40 -#define O_EXCL 0x80 -#define O_NOCTTY 0x100 -#define O_TRUNC 0x200 -#define O_APPEND 0x400 -#define O_NONBLOCK 0x800 -#define O_DIRECTORY 0x10000 - -/* The struct returned by the stat() syscall, equivalent to stat64(). The - * syscall returns 116 bytes and stops in the middle of __unused. - */ -struct sys_stat_struct { - unsigned long st_dev; - unsigned long st_ino; - unsigned long st_nlink; - unsigned int st_mode; - unsigned int st_uid; - - unsigned int st_gid; - unsigned int __pad0; - unsigned long st_rdev; - long st_size; - long st_blksize; - - long st_blocks; - unsigned long st_atime; - unsigned long st_atime_nsec; - unsigned long st_mtime; - - unsigned long st_mtime_nsec; - unsigned long st_ctime; - unsigned long st_ctime_nsec; - long __unused[3]; -}; - -#elif defined(__i386__) || defined(__i486__) || defined(__i586__) || defined(__i686__) -/* Syscalls for i386 : - * - mostly similar to x86_64 - * - registers are 32-bit - * - syscall number is passed in eax - * - arguments are in ebx, ecx, edx, esi, edi, ebp respectively - * - all registers are preserved (except eax of course) - * - the system call is performed by calling int $0x80 - * - syscall return comes in eax - * - the arguments are cast to long and assigned into the target registers - * which are then simply passed as registers to the asm code, so that we - * don't have to experience issues with register constraints. - * - the syscall number is always specified last in order to allow to force - * some registers before (gcc refuses a %-register at the last position). - * - * Also, i386 supports the old_select syscall if newselect is not available - */ -#define __ARCH_WANT_SYS_OLD_SELECT - -#define my_syscall0(num) \ -({ \ - long _ret; \ - register long _num asm("eax") = (num); \ - \ - asm volatile ( \ - "int $0x80\n" \ - : "=a" (_ret) \ - : "0"(_num) \ - : "memory", "cc" \ - ); \ - _ret; \ -}) - -#define my_syscall1(num, arg1) \ -({ \ - long _ret; \ - register long _num asm("eax") = (num); \ - register long _arg1 asm("ebx") = (long)(arg1); \ - \ - asm volatile ( \ - "int $0x80\n" \ - : "=a" (_ret) \ - : "r"(_arg1), \ - "0"(_num) \ - : "memory", "cc" \ - ); \ - _ret; \ -}) - -#define my_syscall2(num, arg1, arg2) \ -({ \ - long _ret; \ - register long _num asm("eax") = (num); \ - register long _arg1 asm("ebx") = (long)(arg1); \ - register long _arg2 asm("ecx") = (long)(arg2); \ - \ - asm volatile ( \ - "int $0x80\n" \ - : "=a" (_ret) \ - : "r"(_arg1), "r"(_arg2), \ - "0"(_num) \ - : "memory", "cc" \ - ); \ - _ret; \ -}) - -#define my_syscall3(num, arg1, arg2, arg3) \ -({ \ - long _ret; \ - register long _num asm("eax") = (num); \ - register long _arg1 asm("ebx") = (long)(arg1); \ - register long _arg2 asm("ecx") = (long)(arg2); \ - register long _arg3 asm("edx") = (long)(arg3); \ - \ - asm volatile ( \ - "int $0x80\n" \ - : "=a" (_ret) \ - : "r"(_arg1), "r"(_arg2), "r"(_arg3), \ - "0"(_num) \ - : "memory", "cc" \ - ); \ - _ret; \ -}) - -#define my_syscall4(num, arg1, arg2, arg3, arg4) \ -({ \ - long _ret; \ - register long _num asm("eax") = (num); \ - register long _arg1 asm("ebx") = (long)(arg1); \ - register long _arg2 asm("ecx") = (long)(arg2); \ - register long _arg3 asm("edx") = (long)(arg3); \ - register long _arg4 asm("esi") = (long)(arg4); \ - \ - asm volatile ( \ - "int $0x80\n" \ - : "=a" (_ret) \ - : "r"(_arg1), "r"(_arg2), "r"(_arg3), "r"(_arg4), \ - "0"(_num) \ - : "memory", "cc" \ - ); \ - _ret; \ -}) - -#define my_syscall5(num, arg1, arg2, arg3, arg4, arg5) \ -({ \ - long _ret; \ - register long _num asm("eax") = (num); \ - register long _arg1 asm("ebx") = (long)(arg1); \ - register long _arg2 asm("ecx") = (long)(arg2); \ - register long _arg3 asm("edx") = (long)(arg3); \ - register long _arg4 asm("esi") = (long)(arg4); \ - register long _arg5 asm("edi") = (long)(arg5); \ - \ - asm volatile ( \ - "int $0x80\n" \ - : "=a" (_ret) \ - : "r"(_arg1), "r"(_arg2), "r"(_arg3), "r"(_arg4), "r"(_arg5), \ - "0"(_num) \ - : "memory", "cc" \ - ); \ - _ret; \ -}) - -/* startup code */ -/* - * i386 System V ABI mandates: - * 1) last pushed argument must be 16-byte aligned. - * 2) The deepest stack frame should be set to zero - * - */ -asm(".section .text\n" - ".global _start\n" - "_start:\n" - "pop %eax\n" // argc (first arg, %eax) - "mov %esp, %ebx\n" // argv[] (second arg, %ebx) - "lea 4(%ebx,%eax,4),%ecx\n" // then a NULL then envp (third arg, %ecx) - "xor %ebp, %ebp\n" // zero the stack frame - "and $-16, %esp\n" // x86 ABI : esp must be 16-byte aligned before - "sub $4, %esp\n" // the call instruction (args are aligned) - "push %ecx\n" // push all registers on the stack so that we - "push %ebx\n" // support both regparm and plain stack modes - "push %eax\n" - "call main\n" // main() returns the status code in %eax - "mov %eax, %ebx\n" // retrieve exit code (32-bit int) - "movl $1, %eax\n" // NR_exit == 1 - "int $0x80\n" // exit now - "hlt\n" // ensure it does not - ""); - -/* fcntl / open */ -#define O_RDONLY 0 -#define O_WRONLY 1 -#define O_RDWR 2 -#define O_CREAT 0x40 -#define O_EXCL 0x80 -#define O_NOCTTY 0x100 -#define O_TRUNC 0x200 -#define O_APPEND 0x400 -#define O_NONBLOCK 0x800 -#define O_DIRECTORY 0x10000 - -/* The struct returned by the stat() syscall, 32-bit only, the syscall returns - * exactly 56 bytes (stops before the unused array). - */ -struct sys_stat_struct { - unsigned long st_dev; - unsigned long st_ino; - unsigned short st_mode; - unsigned short st_nlink; - unsigned short st_uid; - unsigned short st_gid; - - unsigned long st_rdev; - unsigned long st_size; - unsigned long st_blksize; - unsigned long st_blocks; - - unsigned long st_atime; - unsigned long st_atime_nsec; - unsigned long st_mtime; - unsigned long st_mtime_nsec; - - unsigned long st_ctime; - unsigned long st_ctime_nsec; - unsigned long __unused[2]; -}; - -#elif defined(__ARM_EABI__) -/* Syscalls for ARM in ARM or Thumb modes : - * - registers are 32-bit - * - stack is 8-byte aligned - * ( http://infocenter.arm.com/help/index.jsp?topic=/com.arm.doc.faqs/ka4127.html) - * - syscall number is passed in r7 - * - arguments are in r0, r1, r2, r3, r4, r5 - * - the system call is performed by calling svc #0 - * - syscall return comes in r0. - * - only lr is clobbered. - * - the arguments are cast to long and assigned into the target registers - * which are then simply passed as registers to the asm code, so that we - * don't have to experience issues with register constraints. - * - the syscall number is always specified last in order to allow to force - * some registers before (gcc refuses a %-register at the last position). - * - * Also, ARM supports the old_select syscall if newselect is not available - */ -#define __ARCH_WANT_SYS_OLD_SELECT - -#define my_syscall0(num) \ -({ \ - register long _num asm("r7") = (num); \ - register long _arg1 asm("r0"); \ - \ - asm volatile ( \ - "svc #0\n" \ - : "=r"(_arg1) \ - : "r"(_num) \ - : "memory", "cc", "lr" \ - ); \ - _arg1; \ -}) - -#define my_syscall1(num, arg1) \ -({ \ - register long _num asm("r7") = (num); \ - register long _arg1 asm("r0") = (long)(arg1); \ - \ - asm volatile ( \ - "svc #0\n" \ - : "=r"(_arg1) \ - : "r"(_arg1), \ - "r"(_num) \ - : "memory", "cc", "lr" \ - ); \ - _arg1; \ -}) - -#define my_syscall2(num, arg1, arg2) \ -({ \ - register long _num asm("r7") = (num); \ - register long _arg1 asm("r0") = (long)(arg1); \ - register long _arg2 asm("r1") = (long)(arg2); \ - \ - asm volatile ( \ - "svc #0\n" \ - : "=r"(_arg1) \ - : "r"(_arg1), "r"(_arg2), \ - "r"(_num) \ - : "memory", "cc", "lr" \ - ); \ - _arg1; \ -}) - -#define my_syscall3(num, arg1, arg2, arg3) \ -({ \ - register long _num asm("r7") = (num); \ - register long _arg1 asm("r0") = (long)(arg1); \ - register long _arg2 asm("r1") = (long)(arg2); \ - register long _arg3 asm("r2") = (long)(arg3); \ - \ - asm volatile ( \ - "svc #0\n" \ - : "=r"(_arg1) \ - : "r"(_arg1), "r"(_arg2), "r"(_arg3), \ - "r"(_num) \ - : "memory", "cc", "lr" \ - ); \ - _arg1; \ -}) - -#define my_syscall4(num, arg1, arg2, arg3, arg4) \ -({ \ - register long _num asm("r7") = (num); \ - register long _arg1 asm("r0") = (long)(arg1); \ - register long _arg2 asm("r1") = (long)(arg2); \ - register long _arg3 asm("r2") = (long)(arg3); \ - register long _arg4 asm("r3") = (long)(arg4); \ - \ - asm volatile ( \ - "svc #0\n" \ - : "=r"(_arg1) \ - : "r"(_arg1), "r"(_arg2), "r"(_arg3), "r"(_arg4), \ - "r"(_num) \ - : "memory", "cc", "lr" \ - ); \ - _arg1; \ -}) - -#define my_syscall5(num, arg1, arg2, arg3, arg4, arg5) \ -({ \ - register long _num asm("r7") = (num); \ - register long _arg1 asm("r0") = (long)(arg1); \ - register long _arg2 asm("r1") = (long)(arg2); \ - register long _arg3 asm("r2") = (long)(arg3); \ - register long _arg4 asm("r3") = (long)(arg4); \ - register long _arg5 asm("r4") = (long)(arg5); \ - \ - asm volatile ( \ - "svc #0\n" \ - : "=r" (_arg1) \ - : "r"(_arg1), "r"(_arg2), "r"(_arg3), "r"(_arg4), "r"(_arg5), \ - "r"(_num) \ - : "memory", "cc", "lr" \ - ); \ - _arg1; \ -}) - -/* startup code */ -asm(".section .text\n" - ".global _start\n" - "_start:\n" -#if defined(__THUMBEB__) || defined(__THUMBEL__) - /* We enter here in 32-bit mode but if some previous functions were in - * 16-bit mode, the assembler cannot know, so we need to tell it we're in - * 32-bit now, then switch to 16-bit (is there a better way to do it than - * adding 1 by hand ?) and tell the asm we're now in 16-bit mode so that - * it generates correct instructions. Note that we do not support thumb1. - */ - ".code 32\n" - "add r0, pc, #1\n" - "bx r0\n" - ".code 16\n" -#endif - "pop {%r0}\n" // argc was in the stack - "mov %r1, %sp\n" // argv = sp - "add %r2, %r1, %r0, lsl #2\n" // envp = argv + 4*argc ... - "add %r2, %r2, $4\n" // ... + 4 - "and %r3, %r1, $-8\n" // AAPCS : sp must be 8-byte aligned in the - "mov %sp, %r3\n" // callee, an bl doesn't push (lr=pc) - "bl main\n" // main() returns the status code, we'll exit with it. - "movs r7, $1\n" // NR_exit == 1 - "svc $0x00\n" - ""); - -/* fcntl / open */ -#define O_RDONLY 0 -#define O_WRONLY 1 -#define O_RDWR 2 -#define O_CREAT 0x40 -#define O_EXCL 0x80 -#define O_NOCTTY 0x100 -#define O_TRUNC 0x200 -#define O_APPEND 0x400 -#define O_NONBLOCK 0x800 -#define O_DIRECTORY 0x4000 - -/* The struct returned by the stat() syscall, 32-bit only, the syscall returns - * exactly 56 bytes (stops before the unused array). In big endian, the format - * differs as devices are returned as short only. - */ -struct sys_stat_struct { -#if defined(__ARMEB__) - unsigned short st_dev; - unsigned short __pad1; -#else - unsigned long st_dev; -#endif - unsigned long st_ino; - unsigned short st_mode; - unsigned short st_nlink; - unsigned short st_uid; - unsigned short st_gid; -#if defined(__ARMEB__) - unsigned short st_rdev; - unsigned short __pad2; -#else - unsigned long st_rdev; -#endif - unsigned long st_size; - unsigned long st_blksize; - unsigned long st_blocks; - unsigned long st_atime; - unsigned long st_atime_nsec; - unsigned long st_mtime; - unsigned long st_mtime_nsec; - unsigned long st_ctime; - unsigned long st_ctime_nsec; - unsigned long __unused[2]; -}; - -#elif defined(__aarch64__) -/* Syscalls for AARCH64 : - * - registers are 64-bit - * - stack is 16-byte aligned - * - syscall number is passed in x8 - * - arguments are in x0, x1, x2, x3, x4, x5 - * - the system call is performed by calling svc 0 - * - syscall return comes in x0. - * - the arguments are cast to long and assigned into the target registers - * which are then simply passed as registers to the asm code, so that we - * don't have to experience issues with register constraints. - * - * On aarch64, select() is not implemented so we have to use pselect6(). - */ -#define __ARCH_WANT_SYS_PSELECT6 - -#define my_syscall0(num) \ -({ \ - register long _num asm("x8") = (num); \ - register long _arg1 asm("x0"); \ - \ - asm volatile ( \ - "svc #0\n" \ - : "=r"(_arg1) \ - : "r"(_num) \ - : "memory", "cc" \ - ); \ - _arg1; \ -}) - -#define my_syscall1(num, arg1) \ -({ \ - register long _num asm("x8") = (num); \ - register long _arg1 asm("x0") = (long)(arg1); \ - \ - asm volatile ( \ - "svc #0\n" \ - : "=r"(_arg1) \ - : "r"(_arg1), \ - "r"(_num) \ - : "memory", "cc" \ - ); \ - _arg1; \ -}) - -#define my_syscall2(num, arg1, arg2) \ -({ \ - register long _num asm("x8") = (num); \ - register long _arg1 asm("x0") = (long)(arg1); \ - register long _arg2 asm("x1") = (long)(arg2); \ - \ - asm volatile ( \ - "svc #0\n" \ - : "=r"(_arg1) \ - : "r"(_arg1), "r"(_arg2), \ - "r"(_num) \ - : "memory", "cc" \ - ); \ - _arg1; \ -}) - -#define my_syscall3(num, arg1, arg2, arg3) \ -({ \ - register long _num asm("x8") = (num); \ - register long _arg1 asm("x0") = (long)(arg1); \ - register long _arg2 asm("x1") = (long)(arg2); \ - register long _arg3 asm("x2") = (long)(arg3); \ - \ - asm volatile ( \ - "svc #0\n" \ - : "=r"(_arg1) \ - : "r"(_arg1), "r"(_arg2), "r"(_arg3), \ - "r"(_num) \ - : "memory", "cc" \ - ); \ - _arg1; \ -}) - -#define my_syscall4(num, arg1, arg2, arg3, arg4) \ -({ \ - register long _num asm("x8") = (num); \ - register long _arg1 asm("x0") = (long)(arg1); \ - register long _arg2 asm("x1") = (long)(arg2); \ - register long _arg3 asm("x2") = (long)(arg3); \ - register long _arg4 asm("x3") = (long)(arg4); \ - \ - asm volatile ( \ - "svc #0\n" \ - : "=r"(_arg1) \ - : "r"(_arg1), "r"(_arg2), "r"(_arg3), "r"(_arg4), \ - "r"(_num) \ - : "memory", "cc" \ - ); \ - _arg1; \ -}) - -#define my_syscall5(num, arg1, arg2, arg3, arg4, arg5) \ -({ \ - register long _num asm("x8") = (num); \ - register long _arg1 asm("x0") = (long)(arg1); \ - register long _arg2 asm("x1") = (long)(arg2); \ - register long _arg3 asm("x2") = (long)(arg3); \ - register long _arg4 asm("x3") = (long)(arg4); \ - register long _arg5 asm("x4") = (long)(arg5); \ - \ - asm volatile ( \ - "svc #0\n" \ - : "=r" (_arg1) \ - : "r"(_arg1), "r"(_arg2), "r"(_arg3), "r"(_arg4), "r"(_arg5), \ - "r"(_num) \ - : "memory", "cc" \ - ); \ - _arg1; \ -}) - -#define my_syscall6(num, arg1, arg2, arg3, arg4, arg5, arg6) \ -({ \ - register long _num asm("x8") = (num); \ - register long _arg1 asm("x0") = (long)(arg1); \ - register long _arg2 asm("x1") = (long)(arg2); \ - register long _arg3 asm("x2") = (long)(arg3); \ - register long _arg4 asm("x3") = (long)(arg4); \ - register long _arg5 asm("x4") = (long)(arg5); \ - register long _arg6 asm("x5") = (long)(arg6); \ - \ - asm volatile ( \ - "svc #0\n" \ - : "=r" (_arg1) \ - : "r"(_arg1), "r"(_arg2), "r"(_arg3), "r"(_arg4), "r"(_arg5), \ - "r"(_arg6), "r"(_num) \ - : "memory", "cc" \ - ); \ - _arg1; \ -}) - -/* startup code */ -asm(".section .text\n" - ".global _start\n" - "_start:\n" - "ldr x0, [sp]\n" // argc (x0) was in the stack - "add x1, sp, 8\n" // argv (x1) = sp - "lsl x2, x0, 3\n" // envp (x2) = 8*argc ... - "add x2, x2, 8\n" // + 8 (skip null) - "add x2, x2, x1\n" // + argv - "and sp, x1, -16\n" // sp must be 16-byte aligned in the callee - "bl main\n" // main() returns the status code, we'll exit with it. - "mov x8, 93\n" // NR_exit == 93 - "svc #0\n" - ""); - -/* fcntl / open */ -#define O_RDONLY 0 -#define O_WRONLY 1 -#define O_RDWR 2 -#define O_CREAT 0x40 -#define O_EXCL 0x80 -#define O_NOCTTY 0x100 -#define O_TRUNC 0x200 -#define O_APPEND 0x400 -#define O_NONBLOCK 0x800 -#define O_DIRECTORY 0x4000 - -/* The struct returned by the newfstatat() syscall. Differs slightly from the - * x86_64's stat one by field ordering, so be careful. - */ -struct sys_stat_struct { - unsigned long st_dev; - unsigned long st_ino; - unsigned int st_mode; - unsigned int st_nlink; - unsigned int st_uid; - unsigned int st_gid; - - unsigned long st_rdev; - unsigned long __pad1; - long st_size; - int st_blksize; - int __pad2; - - long st_blocks; - long st_atime; - unsigned long st_atime_nsec; - long st_mtime; - - unsigned long st_mtime_nsec; - long st_ctime; - unsigned long st_ctime_nsec; - unsigned int __unused[2]; -}; - -#elif defined(__mips__) && defined(_ABIO32) -/* Syscalls for MIPS ABI O32 : - * - WARNING! there's always a delayed slot! - * - WARNING again, the syntax is different, registers take a '$' and numbers - * do not. - * - registers are 32-bit - * - stack is 8-byte aligned - * - syscall number is passed in v0 (starts at 0xfa0). - * - arguments are in a0, a1, a2, a3, then the stack. The caller needs to - * leave some room in the stack for the callee to save a0..a3 if needed. - * - Many registers are clobbered, in fact only a0..a2 and s0..s8 are - * preserved. See: https://www.linux-mips.org/wiki/Syscall as well as - * scall32-o32.S in the kernel sources. - * - the system call is performed by calling "syscall" - * - syscall return comes in v0, and register a3 needs to be checked to know - * if an error occurred, in which case errno is in v0. - * - the arguments are cast to long and assigned into the target registers - * which are then simply passed as registers to the asm code, so that we - * don't have to experience issues with register constraints. - */ - -#define my_syscall0(num) \ -({ \ - register long _num asm("v0") = (num); \ - register long _arg4 asm("a3"); \ - \ - asm volatile ( \ - "addiu $sp, $sp, -32\n" \ - "syscall\n" \ - "addiu $sp, $sp, 32\n" \ - : "=r"(_num), "=r"(_arg4) \ - : "r"(_num) \ - : "memory", "cc", "at", "v1", "hi", "lo", \ - "t0", "t1", "t2", "t3", "t4", "t5", "t6", "t7", "t8", "t9" \ - ); \ - _arg4 ? -_num : _num; \ -}) - -#define my_syscall1(num, arg1) \ -({ \ - register long _num asm("v0") = (num); \ - register long _arg1 asm("a0") = (long)(arg1); \ - register long _arg4 asm("a3"); \ - \ - asm volatile ( \ - "addiu $sp, $sp, -32\n" \ - "syscall\n" \ - "addiu $sp, $sp, 32\n" \ - : "=r"(_num), "=r"(_arg4) \ - : "0"(_num), \ - "r"(_arg1) \ - : "memory", "cc", "at", "v1", "hi", "lo", \ - "t0", "t1", "t2", "t3", "t4", "t5", "t6", "t7", "t8", "t9" \ - ); \ - _arg4 ? -_num : _num; \ -}) - -#define my_syscall2(num, arg1, arg2) \ -({ \ - register long _num asm("v0") = (num); \ - register long _arg1 asm("a0") = (long)(arg1); \ - register long _arg2 asm("a1") = (long)(arg2); \ - register long _arg4 asm("a3"); \ - \ - asm volatile ( \ - "addiu $sp, $sp, -32\n" \ - "syscall\n" \ - "addiu $sp, $sp, 32\n" \ - : "=r"(_num), "=r"(_arg4) \ - : "0"(_num), \ - "r"(_arg1), "r"(_arg2) \ - : "memory", "cc", "at", "v1", "hi", "lo", \ - "t0", "t1", "t2", "t3", "t4", "t5", "t6", "t7", "t8", "t9" \ - ); \ - _arg4 ? -_num : _num; \ -}) - -#define my_syscall3(num, arg1, arg2, arg3) \ -({ \ - register long _num asm("v0") = (num); \ - register long _arg1 asm("a0") = (long)(arg1); \ - register long _arg2 asm("a1") = (long)(arg2); \ - register long _arg3 asm("a2") = (long)(arg3); \ - register long _arg4 asm("a3"); \ - \ - asm volatile ( \ - "addiu $sp, $sp, -32\n" \ - "syscall\n" \ - "addiu $sp, $sp, 32\n" \ - : "=r"(_num), "=r"(_arg4) \ - : "0"(_num), \ - "r"(_arg1), "r"(_arg2), "r"(_arg3) \ - : "memory", "cc", "at", "v1", "hi", "lo", \ - "t0", "t1", "t2", "t3", "t4", "t5", "t6", "t7", "t8", "t9" \ - ); \ - _arg4 ? -_num : _num; \ -}) - -#define my_syscall4(num, arg1, arg2, arg3, arg4) \ -({ \ - register long _num asm("v0") = (num); \ - register long _arg1 asm("a0") = (long)(arg1); \ - register long _arg2 asm("a1") = (long)(arg2); \ - register long _arg3 asm("a2") = (long)(arg3); \ - register long _arg4 asm("a3") = (long)(arg4); \ - \ - asm volatile ( \ - "addiu $sp, $sp, -32\n" \ - "syscall\n" \ - "addiu $sp, $sp, 32\n" \ - : "=r" (_num), "=r"(_arg4) \ - : "0"(_num), \ - "r"(_arg1), "r"(_arg2), "r"(_arg3), "r"(_arg4) \ - : "memory", "cc", "at", "v1", "hi", "lo", \ - "t0", "t1", "t2", "t3", "t4", "t5", "t6", "t7", "t8", "t9" \ - ); \ - _arg4 ? -_num : _num; \ -}) - -#define my_syscall5(num, arg1, arg2, arg3, arg4, arg5) \ -({ \ - register long _num asm("v0") = (num); \ - register long _arg1 asm("a0") = (long)(arg1); \ - register long _arg2 asm("a1") = (long)(arg2); \ - register long _arg3 asm("a2") = (long)(arg3); \ - register long _arg4 asm("a3") = (long)(arg4); \ - register long _arg5 = (long)(arg5); \ - \ - asm volatile ( \ - "addiu $sp, $sp, -32\n" \ - "sw %7, 16($sp)\n" \ - "syscall\n " \ - "addiu $sp, $sp, 32\n" \ - : "=r" (_num), "=r"(_arg4) \ - : "0"(_num), \ - "r"(_arg1), "r"(_arg2), "r"(_arg3), "r"(_arg4), "r"(_arg5) \ - : "memory", "cc", "at", "v1", "hi", "lo", \ - "t0", "t1", "t2", "t3", "t4", "t5", "t6", "t7", "t8", "t9" \ - ); \ - _arg4 ? -_num : _num; \ -}) - -/* startup code, note that it's called __start on MIPS */ -asm(".section .text\n" - ".set nomips16\n" - ".global __start\n" - ".set noreorder\n" - ".option pic0\n" - ".ent __start\n" - "__start:\n" - "lw $a0,($sp)\n" // argc was in the stack - "addiu $a1, $sp, 4\n" // argv = sp + 4 - "sll $a2, $a0, 2\n" // a2 = argc * 4 - "add $a2, $a2, $a1\n" // envp = argv + 4*argc ... - "addiu $a2, $a2, 4\n" // ... + 4 - "li $t0, -8\n" - "and $sp, $sp, $t0\n" // sp must be 8-byte aligned - "addiu $sp,$sp,-16\n" // the callee expects to save a0..a3 there! - "jal main\n" // main() returns the status code, we'll exit with it. - "nop\n" // delayed slot - "move $a0, $v0\n" // retrieve 32-bit exit code from v0 - "li $v0, 4001\n" // NR_exit == 4001 - "syscall\n" - ".end __start\n" - ""); - -/* fcntl / open */ -#define O_RDONLY 0 -#define O_WRONLY 1 -#define O_RDWR 2 -#define O_APPEND 0x0008 -#define O_NONBLOCK 0x0080 -#define O_CREAT 0x0100 -#define O_TRUNC 0x0200 -#define O_EXCL 0x0400 -#define O_NOCTTY 0x0800 -#define O_DIRECTORY 0x10000 - -/* The struct returned by the stat() syscall. 88 bytes are returned by the - * syscall. - */ -struct sys_stat_struct { - unsigned int st_dev; - long st_pad1[3]; - unsigned long st_ino; - unsigned int st_mode; - unsigned int st_nlink; - unsigned int st_uid; - unsigned int st_gid; - unsigned int st_rdev; - long st_pad2[2]; - long st_size; - long st_pad3; - long st_atime; - long st_atime_nsec; - long st_mtime; - long st_mtime_nsec; - long st_ctime; - long st_ctime_nsec; - long st_blksize; - long st_blocks; - long st_pad4[14]; -}; - -#elif defined(__riscv) - -#if __riscv_xlen == 64 -#define PTRLOG "3" -#define SZREG "8" -#elif __riscv_xlen == 32 -#define PTRLOG "2" -#define SZREG "4" -#endif - -/* Syscalls for RISCV : - * - stack is 16-byte aligned - * - syscall number is passed in a7 - * - arguments are in a0, a1, a2, a3, a4, a5 - * - the system call is performed by calling ecall - * - syscall return comes in a0 - * - the arguments are cast to long and assigned into the target - * registers which are then simply passed as registers to the asm code, - * so that we don't have to experience issues with register constraints. - */ - -#define my_syscall0(num) \ -({ \ - register long _num asm("a7") = (num); \ - register long _arg1 asm("a0"); \ - \ - asm volatile ( \ - "ecall\n\t" \ - : "=r"(_arg1) \ - : "r"(_num) \ - : "memory", "cc" \ - ); \ - _arg1; \ -}) - -#define my_syscall1(num, arg1) \ -({ \ - register long _num asm("a7") = (num); \ - register long _arg1 asm("a0") = (long)(arg1); \ - \ - asm volatile ( \ - "ecall\n" \ - : "+r"(_arg1) \ - : "r"(_num) \ - : "memory", "cc" \ - ); \ - _arg1; \ -}) - -#define my_syscall2(num, arg1, arg2) \ -({ \ - register long _num asm("a7") = (num); \ - register long _arg1 asm("a0") = (long)(arg1); \ - register long _arg2 asm("a1") = (long)(arg2); \ - \ - asm volatile ( \ - "ecall\n" \ - : "+r"(_arg1) \ - : "r"(_arg2), \ - "r"(_num) \ - : "memory", "cc" \ - ); \ - _arg1; \ -}) - -#define my_syscall3(num, arg1, arg2, arg3) \ -({ \ - register long _num asm("a7") = (num); \ - register long _arg1 asm("a0") = (long)(arg1); \ - register long _arg2 asm("a1") = (long)(arg2); \ - register long _arg3 asm("a2") = (long)(arg3); \ - \ - asm volatile ( \ - "ecall\n\t" \ - : "+r"(_arg1) \ - : "r"(_arg2), "r"(_arg3), \ - "r"(_num) \ - : "memory", "cc" \ - ); \ - _arg1; \ -}) - -#define my_syscall4(num, arg1, arg2, arg3, arg4) \ -({ \ - register long _num asm("a7") = (num); \ - register long _arg1 asm("a0") = (long)(arg1); \ - register long _arg2 asm("a1") = (long)(arg2); \ - register long _arg3 asm("a2") = (long)(arg3); \ - register long _arg4 asm("a3") = (long)(arg4); \ - \ - asm volatile ( \ - "ecall\n" \ - : "+r"(_arg1) \ - : "r"(_arg2), "r"(_arg3), "r"(_arg4), \ - "r"(_num) \ - : "memory", "cc" \ - ); \ - _arg1; \ -}) - -#define my_syscall5(num, arg1, arg2, arg3, arg4, arg5) \ -({ \ - register long _num asm("a7") = (num); \ - register long _arg1 asm("a0") = (long)(arg1); \ - register long _arg2 asm("a1") = (long)(arg2); \ - register long _arg3 asm("a2") = (long)(arg3); \ - register long _arg4 asm("a3") = (long)(arg4); \ - register long _arg5 asm("a4") = (long)(arg5); \ - \ - asm volatile ( \ - "ecall\n" \ - : "+r"(_arg1) \ - : "r"(_arg2), "r"(_arg3), "r"(_arg4), "r"(_arg5), \ - "r"(_num) \ - : "memory", "cc" \ - ); \ - _arg1; \ -}) - -#define my_syscall6(num, arg1, arg2, arg3, arg4, arg5, arg6) \ -({ \ - register long _num asm("a7") = (num); \ - register long _arg1 asm("a0") = (long)(arg1); \ - register long _arg2 asm("a1") = (long)(arg2); \ - register long _arg3 asm("a2") = (long)(arg3); \ - register long _arg4 asm("a3") = (long)(arg4); \ - register long _arg5 asm("a4") = (long)(arg5); \ - register long _arg6 asm("a5") = (long)(arg6); \ - \ - asm volatile ( \ - "ecall\n" \ - : "+r"(_arg1) \ - : "r"(_arg2), "r"(_arg3), "r"(_arg4), "r"(_arg5), "r"(_arg6), \ - "r"(_num) \ - : "memory", "cc" \ - ); \ - _arg1; \ -}) - -/* startup code */ -asm(".section .text\n" - ".global _start\n" - "_start:\n" - ".option push\n" - ".option norelax\n" - "lla gp, __global_pointer$\n" - ".option pop\n" - "ld a0, 0(sp)\n" // argc (a0) was in the stack - "add a1, sp, "SZREG"\n" // argv (a1) = sp - "slli a2, a0, "PTRLOG"\n" // envp (a2) = SZREG*argc ... - "add a2, a2, "SZREG"\n" // + SZREG (skip null) - "add a2,a2,a1\n" // + argv - "andi sp,a1,-16\n" // sp must be 16-byte aligned - "call main\n" // main() returns the status code, we'll exit with it. - "li a7, 93\n" // NR_exit == 93 - "ecall\n" - ""); - -/* fcntl / open */ -#define O_RDONLY 0 -#define O_WRONLY 1 -#define O_RDWR 2 -#define O_CREAT 0x100 -#define O_EXCL 0x200 -#define O_NOCTTY 0x400 -#define O_TRUNC 0x1000 -#define O_APPEND 0x2000 -#define O_NONBLOCK 0x4000 -#define O_DIRECTORY 0x200000 - -struct sys_stat_struct { - unsigned long st_dev; /* Device. */ - unsigned long st_ino; /* File serial number. */ - unsigned int st_mode; /* File mode. */ - unsigned int st_nlink; /* Link count. */ - unsigned int st_uid; /* User ID of the file's owner. */ - unsigned int st_gid; /* Group ID of the file's group. */ - unsigned long st_rdev; /* Device number, if device. */ - unsigned long __pad1; - long st_size; /* Size of file, in bytes. */ - int st_blksize; /* Optimal block size for I/O. */ - int __pad2; - long st_blocks; /* Number 512-byte blocks allocated. */ - long st_atime; /* Time of last access. */ - unsigned long st_atime_nsec; - long st_mtime; /* Time of last modification. */ - unsigned long st_mtime_nsec; - long st_ctime; /* Time of last status change. */ - unsigned long st_ctime_nsec; - unsigned int __unused4; - unsigned int __unused5; -}; - -#endif - - -/* Below are the C functions used to declare the raw syscalls. They try to be - * architecture-agnostic, and return either a success or -errno. Declaring them - * static will lead to them being inlined in most cases, but it's still possible - * to reference them by a pointer if needed. - */ -static __attribute__((unused)) -void *sys_brk(void *addr) -{ - return (void *)my_syscall1(__NR_brk, addr); -} - -static __attribute__((noreturn,unused)) -void sys_exit(int status) -{ - my_syscall1(__NR_exit, status & 255); - while(1); // shut the "noreturn" warnings. -} - -static __attribute__((unused)) -int sys_chdir(const char *path) -{ - return my_syscall1(__NR_chdir, path); -} - -static __attribute__((unused)) -int sys_chmod(const char *path, mode_t mode) -{ -#ifdef __NR_fchmodat - return my_syscall4(__NR_fchmodat, AT_FDCWD, path, mode, 0); -#elif defined(__NR_chmod) - return my_syscall2(__NR_chmod, path, mode); -#else -#error Neither __NR_fchmodat nor __NR_chmod defined, cannot implement sys_chmod() -#endif -} - -static __attribute__((unused)) -int sys_chown(const char *path, uid_t owner, gid_t group) -{ -#ifdef __NR_fchownat - return my_syscall5(__NR_fchownat, AT_FDCWD, path, owner, group, 0); -#elif defined(__NR_chown) - return my_syscall3(__NR_chown, path, owner, group); -#else -#error Neither __NR_fchownat nor __NR_chown defined, cannot implement sys_chown() -#endif -} - -static __attribute__((unused)) -int sys_chroot(const char *path) -{ - return my_syscall1(__NR_chroot, path); -} - -static __attribute__((unused)) -int sys_close(int fd) -{ - return my_syscall1(__NR_close, fd); -} - -static __attribute__((unused)) -int sys_dup(int fd) -{ - return my_syscall1(__NR_dup, fd); -} - -#ifdef __NR_dup3 -static __attribute__((unused)) -int sys_dup3(int old, int new, int flags) -{ - return my_syscall3(__NR_dup3, old, new, flags); -} -#endif - -static __attribute__((unused)) -int sys_dup2(int old, int new) -{ -#ifdef __NR_dup3 - return my_syscall3(__NR_dup3, old, new, 0); -#elif defined(__NR_dup2) - return my_syscall2(__NR_dup2, old, new); -#else -#error Neither __NR_dup3 nor __NR_dup2 defined, cannot implement sys_dup2() -#endif -} - -static __attribute__((unused)) -int sys_execve(const char *filename, char *const argv[], char *const envp[]) -{ - return my_syscall3(__NR_execve, filename, argv, envp); -} - -static __attribute__((unused)) -pid_t sys_fork(void) -{ -#ifdef __NR_clone - /* note: some archs only have clone() and not fork(). Different archs - * have a different API, but most archs have the flags on first arg and - * will not use the rest with no other flag. - */ - return my_syscall5(__NR_clone, SIGCHLD, 0, 0, 0, 0); -#elif defined(__NR_fork) - return my_syscall0(__NR_fork); -#else -#error Neither __NR_clone nor __NR_fork defined, cannot implement sys_fork() -#endif -} - -static __attribute__((unused)) -int sys_fsync(int fd) -{ - return my_syscall1(__NR_fsync, fd); -} - -static __attribute__((unused)) -int sys_getdents64(int fd, struct linux_dirent64 *dirp, int count) -{ - return my_syscall3(__NR_getdents64, fd, dirp, count); -} - -static __attribute__((unused)) -pid_t sys_getpgid(pid_t pid) -{ - return my_syscall1(__NR_getpgid, pid); -} - -static __attribute__((unused)) -pid_t sys_getpgrp(void) -{ - return sys_getpgid(0); -} - -static __attribute__((unused)) -pid_t sys_getpid(void) -{ - return my_syscall0(__NR_getpid); -} - -static __attribute__((unused)) -pid_t sys_gettid(void) -{ - return my_syscall0(__NR_gettid); -} - -static __attribute__((unused)) -int sys_gettimeofday(struct timeval *tv, struct timezone *tz) -{ - return my_syscall2(__NR_gettimeofday, tv, tz); -} - -static __attribute__((unused)) -int sys_ioctl(int fd, unsigned long req, void *value) -{ - return my_syscall3(__NR_ioctl, fd, req, value); -} - -static __attribute__((unused)) -int sys_kill(pid_t pid, int signal) -{ - return my_syscall2(__NR_kill, pid, signal); -} - -static __attribute__((unused)) -int sys_link(const char *old, const char *new) -{ -#ifdef __NR_linkat - return my_syscall5(__NR_linkat, AT_FDCWD, old, AT_FDCWD, new, 0); -#elif defined(__NR_link) - return my_syscall2(__NR_link, old, new); -#else -#error Neither __NR_linkat nor __NR_link defined, cannot implement sys_link() -#endif -} - -static __attribute__((unused)) -off_t sys_lseek(int fd, off_t offset, int whence) -{ - return my_syscall3(__NR_lseek, fd, offset, whence); -} - -static __attribute__((unused)) -int sys_mkdir(const char *path, mode_t mode) -{ -#ifdef __NR_mkdirat - return my_syscall3(__NR_mkdirat, AT_FDCWD, path, mode); -#elif defined(__NR_mkdir) - return my_syscall2(__NR_mkdir, path, mode); -#else -#error Neither __NR_mkdirat nor __NR_mkdir defined, cannot implement sys_mkdir() -#endif -} - -static __attribute__((unused)) -long sys_mknod(const char *path, mode_t mode, dev_t dev) -{ -#ifdef __NR_mknodat - return my_syscall4(__NR_mknodat, AT_FDCWD, path, mode, dev); -#elif defined(__NR_mknod) - return my_syscall3(__NR_mknod, path, mode, dev); -#else -#error Neither __NR_mknodat nor __NR_mknod defined, cannot implement sys_mknod() -#endif -} - -static __attribute__((unused)) -int sys_mount(const char *src, const char *tgt, const char *fst, - unsigned long flags, const void *data) -{ - return my_syscall5(__NR_mount, src, tgt, fst, flags, data); -} - -static __attribute__((unused)) -int sys_open(const char *path, int flags, mode_t mode) -{ -#ifdef __NR_openat - return my_syscall4(__NR_openat, AT_FDCWD, path, flags, mode); -#elif defined(__NR_open) - return my_syscall3(__NR_open, path, flags, mode); -#else -#error Neither __NR_openat nor __NR_open defined, cannot implement sys_open() -#endif -} - -static __attribute__((unused)) -int sys_pivot_root(const char *new, const char *old) -{ - return my_syscall2(__NR_pivot_root, new, old); -} - -static __attribute__((unused)) -int sys_poll(struct pollfd *fds, int nfds, int timeout) -{ -#if defined(__NR_ppoll) - struct timespec t; - - if (timeout >= 0) { - t.tv_sec = timeout / 1000; - t.tv_nsec = (timeout % 1000) * 1000000; - } - return my_syscall4(__NR_ppoll, fds, nfds, (timeout >= 0) ? &t : NULL, NULL); -#elif defined(__NR_poll) - return my_syscall3(__NR_poll, fds, nfds, timeout); -#else -#error Neither __NR_ppoll nor __NR_poll defined, cannot implement sys_poll() -#endif -} - -static __attribute__((unused)) -ssize_t sys_read(int fd, void *buf, size_t count) -{ - return my_syscall3(__NR_read, fd, buf, count); -} - -static __attribute__((unused)) -ssize_t sys_reboot(int magic1, int magic2, int cmd, void *arg) -{ - return my_syscall4(__NR_reboot, magic1, magic2, cmd, arg); -} - -static __attribute__((unused)) -int sys_sched_yield(void) -{ - return my_syscall0(__NR_sched_yield); -} - -static __attribute__((unused)) -int sys_select(int nfds, fd_set *rfds, fd_set *wfds, fd_set *efds, struct timeval *timeout) -{ -#if defined(__ARCH_WANT_SYS_OLD_SELECT) && !defined(__NR__newselect) - struct sel_arg_struct { - unsigned long n; - fd_set *r, *w, *e; - struct timeval *t; - } arg = { .n = nfds, .r = rfds, .w = wfds, .e = efds, .t = timeout }; - return my_syscall1(__NR_select, &arg); -#elif defined(__ARCH_WANT_SYS_PSELECT6) && defined(__NR_pselect6) - struct timespec t; - - if (timeout) { - t.tv_sec = timeout->tv_sec; - t.tv_nsec = timeout->tv_usec * 1000; - } - return my_syscall6(__NR_pselect6, nfds, rfds, wfds, efds, timeout ? &t : NULL, NULL); -#elif defined(__NR__newselect) || defined(__NR_select) -#ifndef __NR__newselect -#define __NR__newselect __NR_select -#endif - return my_syscall5(__NR__newselect, nfds, rfds, wfds, efds, timeout); -#else -#error None of __NR_select, __NR_pselect6, nor __NR__newselect defined, cannot implement sys_select() -#endif -} - -static __attribute__((unused)) -int sys_setpgid(pid_t pid, pid_t pgid) -{ - return my_syscall2(__NR_setpgid, pid, pgid); -} - -static __attribute__((unused)) -pid_t sys_setsid(void) -{ - return my_syscall0(__NR_setsid); -} - -static __attribute__((unused)) -int sys_stat(const char *path, struct stat *buf) -{ - struct sys_stat_struct stat; - long ret; - -#ifdef __NR_newfstatat - /* only solution for arm64 */ - ret = my_syscall4(__NR_newfstatat, AT_FDCWD, path, &stat, 0); -#elif defined(__NR_stat) - ret = my_syscall2(__NR_stat, path, &stat); -#else -#error Neither __NR_newfstatat nor __NR_stat defined, cannot implement sys_stat() -#endif - buf->st_dev = stat.st_dev; - buf->st_ino = stat.st_ino; - buf->st_mode = stat.st_mode; - buf->st_nlink = stat.st_nlink; - buf->st_uid = stat.st_uid; - buf->st_gid = stat.st_gid; - buf->st_rdev = stat.st_rdev; - buf->st_size = stat.st_size; - buf->st_blksize = stat.st_blksize; - buf->st_blocks = stat.st_blocks; - buf->st_atime = stat.st_atime; - buf->st_mtime = stat.st_mtime; - buf->st_ctime = stat.st_ctime; - return ret; -} - - -static __attribute__((unused)) -int sys_symlink(const char *old, const char *new) -{ -#ifdef __NR_symlinkat - return my_syscall3(__NR_symlinkat, old, AT_FDCWD, new); -#elif defined(__NR_symlink) - return my_syscall2(__NR_symlink, old, new); -#else -#error Neither __NR_symlinkat nor __NR_symlink defined, cannot implement sys_symlink() -#endif -} - -static __attribute__((unused)) -mode_t sys_umask(mode_t mode) -{ - return my_syscall1(__NR_umask, mode); -} - -static __attribute__((unused)) -int sys_umount2(const char *path, int flags) -{ - return my_syscall2(__NR_umount2, path, flags); -} - -static __attribute__((unused)) -int sys_unlink(const char *path) -{ -#ifdef __NR_unlinkat - return my_syscall3(__NR_unlinkat, AT_FDCWD, path, 0); -#elif defined(__NR_unlink) - return my_syscall1(__NR_unlink, path); -#else -#error Neither __NR_unlinkat nor __NR_unlink defined, cannot implement sys_unlink() -#endif -} - -static __attribute__((unused)) -pid_t sys_wait4(pid_t pid, int *status, int options, struct rusage *rusage) -{ - return my_syscall4(__NR_wait4, pid, status, options, rusage); -} - -static __attribute__((unused)) -pid_t sys_waitpid(pid_t pid, int *status, int options) -{ - return sys_wait4(pid, status, options, 0); -} - -static __attribute__((unused)) -pid_t sys_wait(int *status) -{ - return sys_waitpid(-1, status, 0); -} - -static __attribute__((unused)) -ssize_t sys_write(int fd, const void *buf, size_t count) -{ - return my_syscall3(__NR_write, fd, buf, count); -} - - -/* Below are the libc-compatible syscalls which return x or -1 and set errno. - * They rely on the functions above. Similarly they're marked static so that it - * is possible to assign pointers to them if needed. - */ - -static __attribute__((unused)) -int brk(void *addr) -{ - void *ret = sys_brk(addr); - - if (!ret) { - SET_ERRNO(ENOMEM); - return -1; - } - return 0; -} - -static __attribute__((noreturn,unused)) -void exit(int status) -{ - sys_exit(status); -} - -static __attribute__((unused)) -int chdir(const char *path) -{ - int ret = sys_chdir(path); - - if (ret < 0) { - SET_ERRNO(-ret); - ret = -1; - } - return ret; -} - -static __attribute__((unused)) -int chmod(const char *path, mode_t mode) -{ - int ret = sys_chmod(path, mode); - - if (ret < 0) { - SET_ERRNO(-ret); - ret = -1; - } - return ret; -} - -static __attribute__((unused)) -int chown(const char *path, uid_t owner, gid_t group) -{ - int ret = sys_chown(path, owner, group); - - if (ret < 0) { - SET_ERRNO(-ret); - ret = -1; - } - return ret; -} - -static __attribute__((unused)) -int chroot(const char *path) -{ - int ret = sys_chroot(path); - - if (ret < 0) { - SET_ERRNO(-ret); - ret = -1; - } - return ret; -} - -static __attribute__((unused)) -int close(int fd) -{ - int ret = sys_close(fd); - - if (ret < 0) { - SET_ERRNO(-ret); - ret = -1; - } - return ret; -} - -static __attribute__((unused)) -int dup(int fd) -{ - int ret = sys_dup(fd); - - if (ret < 0) { - SET_ERRNO(-ret); - ret = -1; - } - return ret; -} - -static __attribute__((unused)) -int dup2(int old, int new) -{ - int ret = sys_dup2(old, new); - - if (ret < 0) { - SET_ERRNO(-ret); - ret = -1; - } - return ret; -} - -#ifdef __NR_dup3 -static __attribute__((unused)) -int dup3(int old, int new, int flags) -{ - int ret = sys_dup3(old, new, flags); - - if (ret < 0) { - SET_ERRNO(-ret); - ret = -1; - } - return ret; -} -#endif - -static __attribute__((unused)) -int execve(const char *filename, char *const argv[], char *const envp[]) -{ - int ret = sys_execve(filename, argv, envp); - - if (ret < 0) { - SET_ERRNO(-ret); - ret = -1; - } - return ret; -} - -static __attribute__((unused)) -pid_t fork(void) -{ - pid_t ret = sys_fork(); - - if (ret < 0) { - SET_ERRNO(-ret); - ret = -1; - } - return ret; -} - -static __attribute__((unused)) -int fsync(int fd) -{ - int ret = sys_fsync(fd); - - if (ret < 0) { - SET_ERRNO(-ret); - ret = -1; - } - return ret; -} - -static __attribute__((unused)) -int getdents64(int fd, struct linux_dirent64 *dirp, int count) -{ - int ret = sys_getdents64(fd, dirp, count); - - if (ret < 0) { - SET_ERRNO(-ret); - ret = -1; - } - return ret; -} - -static __attribute__((unused)) -pid_t getpgid(pid_t pid) -{ - pid_t ret = sys_getpgid(pid); - - if (ret < 0) { - SET_ERRNO(-ret); - ret = -1; - } - return ret; -} - -static __attribute__((unused)) -pid_t getpgrp(void) -{ - pid_t ret = sys_getpgrp(); - - if (ret < 0) { - SET_ERRNO(-ret); - ret = -1; - } - return ret; -} - -static __attribute__((unused)) -pid_t getpid(void) -{ - pid_t ret = sys_getpid(); - - if (ret < 0) { - SET_ERRNO(-ret); - ret = -1; - } - return ret; -} - -static __attribute__((unused)) -pid_t gettid(void) -{ - pid_t ret = sys_gettid(); - - if (ret < 0) { - SET_ERRNO(-ret); - ret = -1; - } - return ret; -} - -static __attribute__((unused)) -int gettimeofday(struct timeval *tv, struct timezone *tz) -{ - int ret = sys_gettimeofday(tv, tz); - - if (ret < 0) { - SET_ERRNO(-ret); - ret = -1; - } - return ret; -} - -static __attribute__((unused)) -int ioctl(int fd, unsigned long req, void *value) -{ - int ret = sys_ioctl(fd, req, value); - - if (ret < 0) { - SET_ERRNO(-ret); - ret = -1; - } - return ret; -} - -static __attribute__((unused)) -int kill(pid_t pid, int signal) -{ - int ret = sys_kill(pid, signal); - - if (ret < 0) { - SET_ERRNO(-ret); - ret = -1; - } - return ret; -} - -static __attribute__((unused)) -int link(const char *old, const char *new) -{ - int ret = sys_link(old, new); - - if (ret < 0) { - SET_ERRNO(-ret); - ret = -1; - } - return ret; -} - -static __attribute__((unused)) -off_t lseek(int fd, off_t offset, int whence) -{ - off_t ret = sys_lseek(fd, offset, whence); - - if (ret < 0) { - SET_ERRNO(-ret); - ret = -1; - } - return ret; -} - -static __attribute__((unused)) -int mkdir(const char *path, mode_t mode) -{ - int ret = sys_mkdir(path, mode); - - if (ret < 0) { - SET_ERRNO(-ret); - ret = -1; - } - return ret; -} - -static __attribute__((unused)) -int mknod(const char *path, mode_t mode, dev_t dev) -{ - int ret = sys_mknod(path, mode, dev); - - if (ret < 0) { - SET_ERRNO(-ret); - ret = -1; - } - return ret; -} - -static __attribute__((unused)) -int mount(const char *src, const char *tgt, - const char *fst, unsigned long flags, - const void *data) -{ - int ret = sys_mount(src, tgt, fst, flags, data); - - if (ret < 0) { - SET_ERRNO(-ret); - ret = -1; - } - return ret; -} - -static __attribute__((unused)) -int open(const char *path, int flags, mode_t mode) -{ - int ret = sys_open(path, flags, mode); - - if (ret < 0) { - SET_ERRNO(-ret); - ret = -1; - } - return ret; -} - -static __attribute__((unused)) -int pivot_root(const char *new, const char *old) -{ - int ret = sys_pivot_root(new, old); - - if (ret < 0) { - SET_ERRNO(-ret); - ret = -1; - } - return ret; -} - -static __attribute__((unused)) -int poll(struct pollfd *fds, int nfds, int timeout) -{ - int ret = sys_poll(fds, nfds, timeout); - - if (ret < 0) { - SET_ERRNO(-ret); - ret = -1; - } - return ret; -} - -static __attribute__((unused)) -ssize_t read(int fd, void *buf, size_t count) -{ - ssize_t ret = sys_read(fd, buf, count); - - if (ret < 0) { - SET_ERRNO(-ret); - ret = -1; - } - return ret; -} - -static __attribute__((unused)) -int reboot(int cmd) -{ - int ret = sys_reboot(LINUX_REBOOT_MAGIC1, LINUX_REBOOT_MAGIC2, cmd, 0); - - if (ret < 0) { - SET_ERRNO(-ret); - ret = -1; - } - return ret; -} - -static __attribute__((unused)) -void *sbrk(intptr_t inc) -{ - void *ret; - - /* first call to find current end */ - if ((ret = sys_brk(0)) && (sys_brk(ret + inc) == ret + inc)) - return ret + inc; - - SET_ERRNO(ENOMEM); - return (void *)-1; -} - -static __attribute__((unused)) -int sched_yield(void) -{ - int ret = sys_sched_yield(); - - if (ret < 0) { - SET_ERRNO(-ret); - ret = -1; - } - return ret; -} - -static __attribute__((unused)) -int select(int nfds, fd_set *rfds, fd_set *wfds, fd_set *efds, struct timeval *timeout) -{ - int ret = sys_select(nfds, rfds, wfds, efds, timeout); - - if (ret < 0) { - SET_ERRNO(-ret); - ret = -1; - } - return ret; -} - -static __attribute__((unused)) -int setpgid(pid_t pid, pid_t pgid) -{ - int ret = sys_setpgid(pid, pgid); - - if (ret < 0) { - SET_ERRNO(-ret); - ret = -1; - } - return ret; -} - -static __attribute__((unused)) -pid_t setsid(void) -{ - pid_t ret = sys_setsid(); - - if (ret < 0) { - SET_ERRNO(-ret); - ret = -1; - } - return ret; -} - -static __attribute__((unused)) -unsigned int sleep(unsigned int seconds) -{ - struct timeval my_timeval = { seconds, 0 }; - - if (sys_select(0, 0, 0, 0, &my_timeval) < 0) - return my_timeval.tv_sec + !!my_timeval.tv_usec; - else - return 0; -} - -static __attribute__((unused)) -int msleep(unsigned int msecs) -{ - struct timeval my_timeval = { msecs / 1000, (msecs % 1000) * 1000 }; - - if (sys_select(0, 0, 0, 0, &my_timeval) < 0) - return (my_timeval.tv_sec * 1000) + - (my_timeval.tv_usec / 1000) + - !!(my_timeval.tv_usec % 1000); - else - return 0; -} - -static __attribute__((unused)) -int stat(const char *path, struct stat *buf) -{ - int ret = sys_stat(path, buf); - - if (ret < 0) { - SET_ERRNO(-ret); - ret = -1; - } - return ret; -} - -static __attribute__((unused)) -int symlink(const char *old, const char *new) -{ - int ret = sys_symlink(old, new); - - if (ret < 0) { - SET_ERRNO(-ret); - ret = -1; - } - return ret; -} - -static __attribute__((unused)) -int tcsetpgrp(int fd, pid_t pid) -{ - return ioctl(fd, TIOCSPGRP, &pid); -} - -static __attribute__((unused)) -mode_t umask(mode_t mode) -{ - return sys_umask(mode); -} - -static __attribute__((unused)) -int umount2(const char *path, int flags) -{ - int ret = sys_umount2(path, flags); - - if (ret < 0) { - SET_ERRNO(-ret); - ret = -1; - } - return ret; -} - -static __attribute__((unused)) -int unlink(const char *path) -{ - int ret = sys_unlink(path); - - if (ret < 0) { - SET_ERRNO(-ret); - ret = -1; - } - return ret; -} - -static __attribute__((unused)) -pid_t wait4(pid_t pid, int *status, int options, struct rusage *rusage) -{ - pid_t ret = sys_wait4(pid, status, options, rusage); - - if (ret < 0) { - SET_ERRNO(-ret); - ret = -1; - } - return ret; -} - -static __attribute__((unused)) -pid_t waitpid(pid_t pid, int *status, int options) -{ - pid_t ret = sys_waitpid(pid, status, options); - - if (ret < 0) { - SET_ERRNO(-ret); - ret = -1; - } - return ret; -} - -static __attribute__((unused)) -pid_t wait(int *status) -{ - pid_t ret = sys_wait(status); - - if (ret < 0) { - SET_ERRNO(-ret); - ret = -1; - } - return ret; -} - -static __attribute__((unused)) -ssize_t write(int fd, const void *buf, size_t count) -{ - ssize_t ret = sys_write(fd, buf, count); - - if (ret < 0) { - SET_ERRNO(-ret); - ret = -1; - } - return ret; -} - -/* some size-optimized reimplementations of a few common str* and mem* - * functions. They're marked static, except memcpy() and raise() which are used - * by libgcc on ARM, so they are marked weak instead in order not to cause an - * error when building a program made of multiple files (not recommended). - */ - -static __attribute__((unused)) -void *memmove(void *dst, const void *src, size_t len) -{ - ssize_t pos = (dst <= src) ? -1 : (long)len; - void *ret = dst; - - while (len--) { - pos += (dst <= src) ? 1 : -1; - ((char *)dst)[pos] = ((char *)src)[pos]; - } - return ret; -} - -static __attribute__((unused)) -void *memset(void *dst, int b, size_t len) -{ - char *p = dst; - - while (len--) - *(p++) = b; - return dst; -} - -static __attribute__((unused)) -int memcmp(const void *s1, const void *s2, size_t n) -{ - size_t ofs = 0; - char c1 = 0; - - while (ofs < n && !(c1 = ((char *)s1)[ofs] - ((char *)s2)[ofs])) { - ofs++; - } - return c1; -} - -static __attribute__((unused)) -char *strcpy(char *dst, const char *src) -{ - char *ret = dst; - - while ((*dst++ = *src++)); - return ret; -} - -static __attribute__((unused)) -char *strchr(const char *s, int c) -{ - while (*s) { - if (*s == (char)c) - return (char *)s; - s++; - } - return NULL; -} - -static __attribute__((unused)) -char *strrchr(const char *s, int c) -{ - const char *ret = NULL; - - while (*s) { - if (*s == (char)c) - ret = s; - s++; - } - return (char *)ret; -} - -static __attribute__((unused)) -size_t nolibc_strlen(const char *str) -{ - size_t len; - - for (len = 0; str[len]; len++); - return len; -} - -#define strlen(str) ({ \ - __builtin_constant_p((str)) ? \ - __builtin_strlen((str)) : \ - nolibc_strlen((str)); \ -}) - -static __attribute__((unused)) -int isdigit(int c) -{ - return (unsigned int)(c - '0') <= 9; -} - -static __attribute__((unused)) -long atol(const char *s) -{ - unsigned long ret = 0; - unsigned long d; - int neg = 0; - - if (*s == '-') { - neg = 1; - s++; - } - - while (1) { - d = (*s++) - '0'; - if (d > 9) - break; - ret *= 10; - ret += d; - } - - return neg ? -ret : ret; -} - -static __attribute__((unused)) -int atoi(const char *s) -{ - return atol(s); -} - -static __attribute__((unused)) -const char *ltoa(long in) -{ - /* large enough for -9223372036854775808 */ - static char buffer[21]; - char *pos = buffer + sizeof(buffer) - 1; - int neg = in < 0; - unsigned long n = neg ? -in : in; - - *pos-- = '\0'; - do { - *pos-- = '0' + n % 10; - n /= 10; - if (pos < buffer) - return pos + 1; - } while (n); - - if (neg) - *pos-- = '-'; - return pos + 1; -} - -__attribute__((weak,unused)) -void *memcpy(void *dst, const void *src, size_t len) -{ - return memmove(dst, src, len); -} - -/* needed by libgcc for divide by zero */ -__attribute__((weak,unused)) -int raise(int signal) -{ - return kill(getpid(), signal); -} - -/* Here come a few helper functions */ - -static __attribute__((unused)) -void FD_ZERO(fd_set *set) -{ - memset(set, 0, sizeof(*set)); -} - -static __attribute__((unused)) -void FD_SET(int fd, fd_set *set) -{ - if (fd < 0 || fd >= FD_SETSIZE) - return; - set->fd32[fd / 32] |= 1 << (fd & 31); -} - -/* WARNING, it only deals with the 4096 first majors and 256 first minors */ -static __attribute__((unused)) -dev_t makedev(unsigned int major, unsigned int minor) -{ - return ((major & 0xfff) << 8) | (minor & 0xff); -} +#endif /* _NOLIBC_H */ diff --git a/tools/include/nolibc/signal.h b/tools/include/nolibc/signal.h new file mode 100644 index 000000000000..ef47e71e2be3 --- /dev/null +++ b/tools/include/nolibc/signal.h @@ -0,0 +1,22 @@ +/* SPDX-License-Identifier: LGPL-2.1 OR MIT */ +/* + * signal function definitions for NOLIBC + * Copyright (C) 2017-2022 Willy Tarreau <w@1wt.eu> + */ + +#ifndef _NOLIBC_SIGNAL_H +#define _NOLIBC_SIGNAL_H + +#include "std.h" +#include "arch.h" +#include "types.h" +#include "sys.h" + +/* This one is not marked static as it's needed by libgcc for divide by zero */ +__attribute__((weak,unused,section(".text.nolibc_raise"))) +int raise(int signal) +{ + return sys_kill(sys_getpid(), signal); +} + +#endif /* _NOLIBC_SIGNAL_H */ diff --git a/tools/include/nolibc/std.h b/tools/include/nolibc/std.h new file mode 100644 index 000000000000..1747ae125392 --- /dev/null +++ b/tools/include/nolibc/std.h @@ -0,0 +1,49 @@ +/* SPDX-License-Identifier: LGPL-2.1 OR MIT */ +/* + * Standard definitions and types for NOLIBC + * Copyright (C) 2017-2021 Willy Tarreau <w@1wt.eu> + */ + +#ifndef _NOLIBC_STD_H +#define _NOLIBC_STD_H + +/* Declare a few quite common macros and types that usually are in stdlib.h, + * stdint.h, ctype.h, unistd.h and a few other common locations. Please place + * integer type definitions and generic macros here, but avoid OS-specific and + * syscall-specific stuff, as this file is expected to be included very early. + */ + +/* note: may already be defined */ +#ifndef NULL +#define NULL ((void *)0) +#endif + +/* stdint types */ +typedef unsigned char uint8_t; +typedef signed char int8_t; +typedef unsigned short uint16_t; +typedef signed short int16_t; +typedef unsigned int uint32_t; +typedef signed int int32_t; +typedef unsigned long long uint64_t; +typedef signed long long int64_t; +typedef unsigned long size_t; +typedef signed long ssize_t; +typedef unsigned long uintptr_t; +typedef signed long intptr_t; +typedef signed long ptrdiff_t; + +/* those are commonly provided by sys/types.h */ +typedef unsigned int dev_t; +typedef unsigned long ino_t; +typedef unsigned int mode_t; +typedef signed int pid_t; +typedef unsigned int uid_t; +typedef unsigned int gid_t; +typedef unsigned long nlink_t; +typedef signed long off_t; +typedef signed long blksize_t; +typedef signed long blkcnt_t; +typedef signed long time_t; + +#endif /* _NOLIBC_STD_H */ diff --git a/tools/include/nolibc/stdio.h b/tools/include/nolibc/stdio.h new file mode 100644 index 000000000000..15dedf8d0902 --- /dev/null +++ b/tools/include/nolibc/stdio.h @@ -0,0 +1,306 @@ +/* SPDX-License-Identifier: LGPL-2.1 OR MIT */ +/* + * minimal stdio function definitions for NOLIBC + * Copyright (C) 2017-2021 Willy Tarreau <w@1wt.eu> + */ + +#ifndef _NOLIBC_STDIO_H +#define _NOLIBC_STDIO_H + +#include <stdarg.h> + +#include "std.h" +#include "arch.h" +#include "errno.h" +#include "types.h" +#include "sys.h" +#include "stdlib.h" +#include "string.h" + +#ifndef EOF +#define EOF (-1) +#endif + +/* just define FILE as a non-empty type */ +typedef struct FILE { + char dummy[1]; +} FILE; + +/* We define the 3 common stdio files as constant invalid pointers that + * are easily recognized. + */ +static __attribute__((unused)) FILE* const stdin = (FILE*)-3; +static __attribute__((unused)) FILE* const stdout = (FILE*)-2; +static __attribute__((unused)) FILE* const stderr = (FILE*)-1; + +/* getc(), fgetc(), getchar() */ + +#define getc(stream) fgetc(stream) + +static __attribute__((unused)) +int fgetc(FILE* stream) +{ + unsigned char ch; + int fd; + + if (stream < stdin || stream > stderr) + return EOF; + + fd = 3 + (long)stream; + + if (read(fd, &ch, 1) <= 0) + return EOF; + return ch; +} + +static __attribute__((unused)) +int getchar(void) +{ + return fgetc(stdin); +} + + +/* putc(), fputc(), putchar() */ + +#define putc(c, stream) fputc(c, stream) + +static __attribute__((unused)) +int fputc(int c, FILE* stream) +{ + unsigned char ch = c; + int fd; + + if (stream < stdin || stream > stderr) + return EOF; + + fd = 3 + (long)stream; + + if (write(fd, &ch, 1) <= 0) + return EOF; + return ch; +} + +static __attribute__((unused)) +int putchar(int c) +{ + return fputc(c, stdout); +} + + +/* fwrite(), puts(), fputs(). Note that puts() emits '\n' but not fputs(). */ + +/* internal fwrite()-like function which only takes a size and returns 0 on + * success or EOF on error. It automatically retries on short writes. + */ +static __attribute__((unused)) +int _fwrite(const void *buf, size_t size, FILE *stream) +{ + ssize_t ret; + int fd; + + if (stream < stdin || stream > stderr) + return EOF; + + fd = 3 + (long)stream; + + while (size) { + ret = write(fd, buf, size); + if (ret <= 0) + return EOF; + size -= ret; + buf += ret; + } + return 0; +} + +static __attribute__((unused)) +size_t fwrite(const void *s, size_t size, size_t nmemb, FILE *stream) +{ + size_t written; + + for (written = 0; written < nmemb; written++) { + if (_fwrite(s, size, stream) != 0) + break; + s += size; + } + return written; +} + +static __attribute__((unused)) +int fputs(const char *s, FILE *stream) +{ + return _fwrite(s, strlen(s), stream); +} + +static __attribute__((unused)) +int puts(const char *s) +{ + if (fputs(s, stdout) == EOF) + return EOF; + return putchar('\n'); +} + + +/* fgets() */ +static __attribute__((unused)) +char *fgets(char *s, int size, FILE *stream) +{ + int ofs; + int c; + + for (ofs = 0; ofs + 1 < size;) { + c = fgetc(stream); + if (c == EOF) + break; + s[ofs++] = c; + if (c == '\n') + break; + } + if (ofs < size) + s[ofs] = 0; + return ofs ? s : NULL; +} + + +/* minimal vfprintf(). It supports the following formats: + * - %[l*]{d,u,c,x,p} + * - %s + * - unknown modifiers are ignored. + */ +static __attribute__((unused)) +int vfprintf(FILE *stream, const char *fmt, va_list args) +{ + char escape, lpref, c; + unsigned long long v; + unsigned int written; + size_t len, ofs; + char tmpbuf[21]; + const char *outstr; + + written = ofs = escape = lpref = 0; + while (1) { + c = fmt[ofs++]; + + if (escape) { + /* we're in an escape sequence, ofs == 1 */ + escape = 0; + if (c == 'c' || c == 'd' || c == 'u' || c == 'x' || c == 'p') { + char *out = tmpbuf; + + if (c == 'p') + v = va_arg(args, unsigned long); + else if (lpref) { + if (lpref > 1) + v = va_arg(args, unsigned long long); + else + v = va_arg(args, unsigned long); + } else + v = va_arg(args, unsigned int); + + if (c == 'd') { + /* sign-extend the value */ + if (lpref == 0) + v = (long long)(int)v; + else if (lpref == 1) + v = (long long)(long)v; + } + + switch (c) { + case 'c': + out[0] = v; + out[1] = 0; + break; + case 'd': + i64toa_r(v, out); + break; + case 'u': + u64toa_r(v, out); + break; + case 'p': + *(out++) = '0'; + *(out++) = 'x'; + /* fall through */ + default: /* 'x' and 'p' above */ + u64toh_r(v, out); + break; + } + outstr = tmpbuf; + } + else if (c == 's') { + outstr = va_arg(args, char *); + if (!outstr) + outstr="(null)"; + } + else if (c == '%') { + /* queue it verbatim */ + continue; + } + else { + /* modifiers or final 0 */ + if (c == 'l') { + /* long format prefix, maintain the escape */ + lpref++; + } + escape = 1; + goto do_escape; + } + len = strlen(outstr); + goto flush_str; + } + + /* not an escape sequence */ + if (c == 0 || c == '%') { + /* flush pending data on escape or end */ + escape = 1; + lpref = 0; + outstr = fmt; + len = ofs - 1; + flush_str: + if (_fwrite(outstr, len, stream) != 0) + break; + + written += len; + do_escape: + if (c == 0) + break; + fmt += ofs; + ofs = 0; + continue; + } + + /* literal char, just queue it */ + } + return written; +} + +static __attribute__((unused)) +int fprintf(FILE *stream, const char *fmt, ...) +{ + va_list args; + int ret; + + va_start(args, fmt); + ret = vfprintf(stream, fmt, args); + va_end(args); + return ret; +} + +static __attribute__((unused)) +int printf(const char *fmt, ...) +{ + va_list args; + int ret; + + va_start(args, fmt); + ret = vfprintf(stdout, fmt, args); + va_end(args); + return ret; +} + +static __attribute__((unused)) +void perror(const char *msg) +{ + fprintf(stderr, "%s%serrno=%d\n", (msg && *msg) ? msg : "", (msg && *msg) ? ": " : "", errno); +} + +#endif /* _NOLIBC_STDIO_H */ diff --git a/tools/include/nolibc/stdlib.h b/tools/include/nolibc/stdlib.h new file mode 100644 index 000000000000..8fd32eaf8037 --- /dev/null +++ b/tools/include/nolibc/stdlib.h @@ -0,0 +1,423 @@ +/* SPDX-License-Identifier: LGPL-2.1 OR MIT */ +/* + * stdlib function definitions for NOLIBC + * Copyright (C) 2017-2021 Willy Tarreau <w@1wt.eu> + */ + +#ifndef _NOLIBC_STDLIB_H +#define _NOLIBC_STDLIB_H + +#include "std.h" +#include "arch.h" +#include "types.h" +#include "sys.h" +#include "string.h" + +struct nolibc_heap { + size_t len; + char user_p[] __attribute__((__aligned__)); +}; + +/* Buffer used to store int-to-ASCII conversions. Will only be implemented if + * any of the related functions is implemented. The area is large enough to + * store "18446744073709551615" or "-9223372036854775808" and the final zero. + */ +static __attribute__((unused)) char itoa_buffer[21]; + +/* + * As much as possible, please keep functions alphabetically sorted. + */ + +/* must be exported, as it's used by libgcc for various divide functions */ +__attribute__((weak,unused,noreturn,section(".text.nolibc_abort"))) +void abort(void) +{ + sys_kill(sys_getpid(), SIGABRT); + for (;;); +} + +static __attribute__((unused)) +long atol(const char *s) +{ + unsigned long ret = 0; + unsigned long d; + int neg = 0; + + if (*s == '-') { + neg = 1; + s++; + } + + while (1) { + d = (*s++) - '0'; + if (d > 9) + break; + ret *= 10; + ret += d; + } + + return neg ? -ret : ret; +} + +static __attribute__((unused)) +int atoi(const char *s) +{ + return atol(s); +} + +static __attribute__((unused)) +void free(void *ptr) +{ + struct nolibc_heap *heap; + + if (!ptr) + return; + + heap = container_of(ptr, struct nolibc_heap, user_p); + munmap(heap, heap->len); +} + +/* getenv() tries to find the environment variable named <name> in the + * environment array pointed to by global variable "environ" which must be + * declared as a char **, and must be terminated by a NULL (it is recommended + * to set this variable to the "envp" argument of main()). If the requested + * environment variable exists its value is returned otherwise NULL is + * returned. getenv() is forcefully inlined so that the reference to "environ" + * will be dropped if unused, even at -O0. + */ +static __attribute__((unused)) +char *_getenv(const char *name, char **environ) +{ + int idx, i; + + if (environ) { + for (idx = 0; environ[idx]; idx++) { + for (i = 0; name[i] && name[i] == environ[idx][i];) + i++; + if (!name[i] && environ[idx][i] == '=') + return &environ[idx][i+1]; + } + } + return NULL; +} + +static inline __attribute__((unused,always_inline)) +char *getenv(const char *name) +{ + extern char **environ; + return _getenv(name, environ); +} + +static __attribute__((unused)) +void *malloc(size_t len) +{ + struct nolibc_heap *heap; + + /* Always allocate memory with size multiple of 4096. */ + len = sizeof(*heap) + len; + len = (len + 4095UL) & -4096UL; + heap = mmap(NULL, len, PROT_READ|PROT_WRITE, MAP_ANONYMOUS|MAP_PRIVATE, + -1, 0); + if (__builtin_expect(heap == MAP_FAILED, 0)) + return NULL; + + heap->len = len; + return heap->user_p; +} + +static __attribute__((unused)) +void *calloc(size_t size, size_t nmemb) +{ + void *orig; + size_t res = 0; + + if (__builtin_expect(__builtin_mul_overflow(nmemb, size, &res), 0)) { + SET_ERRNO(ENOMEM); + return NULL; + } + + /* + * No need to zero the heap, the MAP_ANONYMOUS in malloc() + * already does it. + */ + return malloc(res); +} + +static __attribute__((unused)) +void *realloc(void *old_ptr, size_t new_size) +{ + struct nolibc_heap *heap; + size_t user_p_len; + void *ret; + + if (!old_ptr) + return malloc(new_size); + + heap = container_of(old_ptr, struct nolibc_heap, user_p); + user_p_len = heap->len - sizeof(*heap); + /* + * Don't realloc() if @user_p_len >= @new_size, this block of + * memory is still enough to handle the @new_size. Just return + * the same pointer. + */ + if (user_p_len >= new_size) + return old_ptr; + + ret = malloc(new_size); + if (__builtin_expect(!ret, 0)) + return NULL; + + memcpy(ret, heap->user_p, heap->len); + munmap(heap, heap->len); + return ret; +} + +/* Converts the unsigned long integer <in> to its hex representation into + * buffer <buffer>, which must be long enough to store the number and the + * trailing zero (17 bytes for "ffffffffffffffff" or 9 for "ffffffff"). The + * buffer is filled from the first byte, and the number of characters emitted + * (not counting the trailing zero) is returned. The function is constructed + * in a way to optimize the code size and avoid any divide that could add a + * dependency on large external functions. + */ +static __attribute__((unused)) +int utoh_r(unsigned long in, char *buffer) +{ + signed char pos = (~0UL > 0xfffffffful) ? 60 : 28; + int digits = 0; + int dig; + + do { + dig = in >> pos; + in -= (uint64_t)dig << pos; + pos -= 4; + if (dig || digits || pos < 0) { + if (dig > 9) + dig += 'a' - '0' - 10; + buffer[digits++] = '0' + dig; + } + } while (pos >= 0); + + buffer[digits] = 0; + return digits; +} + +/* converts unsigned long <in> to an hex string using the static itoa_buffer + * and returns the pointer to that string. + */ +static inline __attribute__((unused)) +char *utoh(unsigned long in) +{ + utoh_r(in, itoa_buffer); + return itoa_buffer; +} + +/* Converts the unsigned long integer <in> to its string representation into + * buffer <buffer>, which must be long enough to store the number and the + * trailing zero (21 bytes for 18446744073709551615 in 64-bit, 11 for + * 4294967295 in 32-bit). The buffer is filled from the first byte, and the + * number of characters emitted (not counting the trailing zero) is returned. + * The function is constructed in a way to optimize the code size and avoid + * any divide that could add a dependency on large external functions. + */ +static __attribute__((unused)) +int utoa_r(unsigned long in, char *buffer) +{ + unsigned long lim; + int digits = 0; + int pos = (~0UL > 0xfffffffful) ? 19 : 9; + int dig; + + do { + for (dig = 0, lim = 1; dig < pos; dig++) + lim *= 10; + + if (digits || in >= lim || !pos) { + for (dig = 0; in >= lim; dig++) + in -= lim; + buffer[digits++] = '0' + dig; + } + } while (pos--); + + buffer[digits] = 0; + return digits; +} + +/* Converts the signed long integer <in> to its string representation into + * buffer <buffer>, which must be long enough to store the number and the + * trailing zero (21 bytes for -9223372036854775808 in 64-bit, 12 for + * -2147483648 in 32-bit). The buffer is filled from the first byte, and the + * number of characters emitted (not counting the trailing zero) is returned. + */ +static __attribute__((unused)) +int itoa_r(long in, char *buffer) +{ + char *ptr = buffer; + int len = 0; + + if (in < 0) { + in = -in; + *(ptr++) = '-'; + len++; + } + len += utoa_r(in, ptr); + return len; +} + +/* for historical compatibility, same as above but returns the pointer to the + * buffer. + */ +static inline __attribute__((unused)) +char *ltoa_r(long in, char *buffer) +{ + itoa_r(in, buffer); + return buffer; +} + +/* converts long integer <in> to a string using the static itoa_buffer and + * returns the pointer to that string. + */ +static inline __attribute__((unused)) +char *itoa(long in) +{ + itoa_r(in, itoa_buffer); + return itoa_buffer; +} + +/* converts long integer <in> to a string using the static itoa_buffer and + * returns the pointer to that string. Same as above, for compatibility. + */ +static inline __attribute__((unused)) +char *ltoa(long in) +{ + itoa_r(in, itoa_buffer); + return itoa_buffer; +} + +/* converts unsigned long integer <in> to a string using the static itoa_buffer + * and returns the pointer to that string. + */ +static inline __attribute__((unused)) +char *utoa(unsigned long in) +{ + utoa_r(in, itoa_buffer); + return itoa_buffer; +} + +/* Converts the unsigned 64-bit integer <in> to its hex representation into + * buffer <buffer>, which must be long enough to store the number and the + * trailing zero (17 bytes for "ffffffffffffffff"). The buffer is filled from + * the first byte, and the number of characters emitted (not counting the + * trailing zero) is returned. The function is constructed in a way to optimize + * the code size and avoid any divide that could add a dependency on large + * external functions. + */ +static __attribute__((unused)) +int u64toh_r(uint64_t in, char *buffer) +{ + signed char pos = 60; + int digits = 0; + int dig; + + do { + if (sizeof(long) >= 8) { + dig = (in >> pos) & 0xF; + } else { + /* 32-bit platforms: avoid a 64-bit shift */ + uint32_t d = (pos >= 32) ? (in >> 32) : in; + dig = (d >> (pos & 31)) & 0xF; + } + if (dig > 9) + dig += 'a' - '0' - 10; + pos -= 4; + if (dig || digits || pos < 0) + buffer[digits++] = '0' + dig; + } while (pos >= 0); + + buffer[digits] = 0; + return digits; +} + +/* converts uint64_t <in> to an hex string using the static itoa_buffer and + * returns the pointer to that string. + */ +static inline __attribute__((unused)) +char *u64toh(uint64_t in) +{ + u64toh_r(in, itoa_buffer); + return itoa_buffer; +} + +/* Converts the unsigned 64-bit integer <in> to its string representation into + * buffer <buffer>, which must be long enough to store the number and the + * trailing zero (21 bytes for 18446744073709551615). The buffer is filled from + * the first byte, and the number of characters emitted (not counting the + * trailing zero) is returned. The function is constructed in a way to optimize + * the code size and avoid any divide that could add a dependency on large + * external functions. + */ +static __attribute__((unused)) +int u64toa_r(uint64_t in, char *buffer) +{ + unsigned long long lim; + int digits = 0; + int pos = 19; /* start with the highest possible digit */ + int dig; + + do { + for (dig = 0, lim = 1; dig < pos; dig++) + lim *= 10; + + if (digits || in >= lim || !pos) { + for (dig = 0; in >= lim; dig++) + in -= lim; + buffer[digits++] = '0' + dig; + } + } while (pos--); + + buffer[digits] = 0; + return digits; +} + +/* Converts the signed 64-bit integer <in> to its string representation into + * buffer <buffer>, which must be long enough to store the number and the + * trailing zero (21 bytes for -9223372036854775808). The buffer is filled from + * the first byte, and the number of characters emitted (not counting the + * trailing zero) is returned. + */ +static __attribute__((unused)) +int i64toa_r(int64_t in, char *buffer) +{ + char *ptr = buffer; + int len = 0; + + if (in < 0) { + in = -in; + *(ptr++) = '-'; + len++; + } + len += u64toa_r(in, ptr); + return len; +} + +/* converts int64_t <in> to a string using the static itoa_buffer and returns + * the pointer to that string. + */ +static inline __attribute__((unused)) +char *i64toa(int64_t in) +{ + i64toa_r(in, itoa_buffer); + return itoa_buffer; +} + +/* converts uint64_t <in> to a string using the static itoa_buffer and returns + * the pointer to that string. + */ +static inline __attribute__((unused)) +char *u64toa(uint64_t in) +{ + u64toa_r(in, itoa_buffer); + return itoa_buffer; +} + +#endif /* _NOLIBC_STDLIB_H */ diff --git a/tools/include/nolibc/string.h b/tools/include/nolibc/string.h new file mode 100644 index 000000000000..bef35bee9c44 --- /dev/null +++ b/tools/include/nolibc/string.h @@ -0,0 +1,285 @@ +/* SPDX-License-Identifier: LGPL-2.1 OR MIT */ +/* + * string function definitions for NOLIBC + * Copyright (C) 2017-2021 Willy Tarreau <w@1wt.eu> + */ + +#ifndef _NOLIBC_STRING_H +#define _NOLIBC_STRING_H + +#include "std.h" + +static void *malloc(size_t len); + +/* + * As much as possible, please keep functions alphabetically sorted. + */ + +static __attribute__((unused)) +int memcmp(const void *s1, const void *s2, size_t n) +{ + size_t ofs = 0; + char c1 = 0; + + while (ofs < n && !(c1 = ((char *)s1)[ofs] - ((char *)s2)[ofs])) { + ofs++; + } + return c1; +} + +static __attribute__((unused)) +void *_nolibc_memcpy_up(void *dst, const void *src, size_t len) +{ + size_t pos = 0; + + while (pos < len) { + ((char *)dst)[pos] = ((const char *)src)[pos]; + pos++; + } + return dst; +} + +static __attribute__((unused)) +void *_nolibc_memcpy_down(void *dst, const void *src, size_t len) +{ + while (len) { + len--; + ((char *)dst)[len] = ((const char *)src)[len]; + } + return dst; +} + +/* might be ignored by the compiler without -ffreestanding, then found as + * missing. + */ +__attribute__((weak,unused,section(".text.nolibc_memmove"))) +void *memmove(void *dst, const void *src, size_t len) +{ + size_t dir, pos; + + pos = len; + dir = -1; + + if (dst < src) { + pos = -1; + dir = 1; + } + + while (len) { + pos += dir; + ((char *)dst)[pos] = ((const char *)src)[pos]; + len--; + } + return dst; +} + +/* must be exported, as it's used by libgcc on ARM */ +__attribute__((weak,unused,section(".text.nolibc_memcpy"))) +void *memcpy(void *dst, const void *src, size_t len) +{ + return _nolibc_memcpy_up(dst, src, len); +} + +/* might be ignored by the compiler without -ffreestanding, then found as + * missing. + */ +__attribute__((weak,unused,section(".text.nolibc_memset"))) +void *memset(void *dst, int b, size_t len) +{ + char *p = dst; + + while (len--) + *(p++) = b; + return dst; +} + +static __attribute__((unused)) +char *strchr(const char *s, int c) +{ + while (*s) { + if (*s == (char)c) + return (char *)s; + s++; + } + return NULL; +} + +static __attribute__((unused)) +int strcmp(const char *a, const char *b) +{ + unsigned int c; + int diff; + + while (!(diff = (unsigned char)*a++ - (c = (unsigned char)*b++)) && c) + ; + return diff; +} + +static __attribute__((unused)) +char *strcpy(char *dst, const char *src) +{ + char *ret = dst; + + while ((*dst++ = *src++)); + return ret; +} + +/* this function is only used with arguments that are not constants or when + * it's not known because optimizations are disabled. + */ +static __attribute__((unused)) +size_t nolibc_strlen(const char *str) +{ + size_t len; + + for (len = 0; str[len]; len++); + return len; +} + +/* do not trust __builtin_constant_p() at -O0, as clang will emit a test and + * the two branches, then will rely on an external definition of strlen(). + */ +#if defined(__OPTIMIZE__) +#define strlen(str) ({ \ + __builtin_constant_p((str)) ? \ + __builtin_strlen((str)) : \ + nolibc_strlen((str)); \ +}) +#else +#define strlen(str) nolibc_strlen((str)) +#endif + +static __attribute__((unused)) +size_t strnlen(const char *str, size_t maxlen) +{ + size_t len; + + for (len = 0; (len < maxlen) && str[len]; len++); + return len; +} + +static __attribute__((unused)) +char *strdup(const char *str) +{ + size_t len; + char *ret; + + len = strlen(str); + ret = malloc(len + 1); + if (__builtin_expect(ret != NULL, 1)) + memcpy(ret, str, len + 1); + + return ret; +} + +static __attribute__((unused)) +char *strndup(const char *str, size_t maxlen) +{ + size_t len; + char *ret; + + len = strnlen(str, maxlen); + ret = malloc(len + 1); + if (__builtin_expect(ret != NULL, 1)) { + memcpy(ret, str, len); + ret[len] = '\0'; + } + + return ret; +} + +static __attribute__((unused)) +size_t strlcat(char *dst, const char *src, size_t size) +{ + size_t len; + char c; + + for (len = 0; dst[len]; len++) + ; + + for (;;) { + c = *src; + if (len < size) + dst[len] = c; + if (!c) + break; + len++; + src++; + } + + return len; +} + +static __attribute__((unused)) +size_t strlcpy(char *dst, const char *src, size_t size) +{ + size_t len; + char c; + + for (len = 0;;) { + c = src[len]; + if (len < size) + dst[len] = c; + if (!c) + break; + len++; + } + return len; +} + +static __attribute__((unused)) +char *strncat(char *dst, const char *src, size_t size) +{ + char *orig = dst; + + while (*dst) + dst++; + + while (size && (*dst = *src)) { + src++; + dst++; + size--; + } + + *dst = 0; + return orig; +} + +static __attribute__((unused)) +int strncmp(const char *a, const char *b, size_t size) +{ + unsigned int c; + int diff = 0; + + while (size-- && + !(diff = (unsigned char)*a++ - (c = (unsigned char)*b++)) && c) + ; + + return diff; +} + +static __attribute__((unused)) +char *strncpy(char *dst, const char *src, size_t size) +{ + size_t len; + + for (len = 0; len < size; len++) + if ((dst[len] = *src)) + src++; + return dst; +} + +static __attribute__((unused)) +char *strrchr(const char *s, int c) +{ + const char *ret = NULL; + + while (*s) { + if (*s == (char)c) + ret = s; + s++; + } + return (char *)ret; +} + +#endif /* _NOLIBC_STRING_H */ diff --git a/tools/include/nolibc/sys.h b/tools/include/nolibc/sys.h new file mode 100644 index 000000000000..08491070387b --- /dev/null +++ b/tools/include/nolibc/sys.h @@ -0,0 +1,1247 @@ +/* SPDX-License-Identifier: LGPL-2.1 OR MIT */ +/* + * Syscall definitions for NOLIBC (those in man(2)) + * Copyright (C) 2017-2021 Willy Tarreau <w@1wt.eu> + */ + +#ifndef _NOLIBC_SYS_H +#define _NOLIBC_SYS_H + +#include <stdarg.h> +#include "std.h" + +/* system includes */ +#include <asm/unistd.h> +#include <asm/signal.h> // for SIGCHLD +#include <asm/ioctls.h> +#include <asm/mman.h> +#include <linux/fs.h> +#include <linux/loop.h> +#include <linux/time.h> + +#include "arch.h" +#include "errno.h" +#include "types.h" + + +/* Functions in this file only describe syscalls. They're declared static so + * that the compiler usually decides to inline them while still being allowed + * to pass a pointer to one of their instances. Each syscall exists in two + * versions: + * - the "internal" ones, which matches the raw syscall interface at the + * kernel level, which may sometimes slightly differ from the documented + * libc-level ones. For example most of them return either a valid value + * or -errno. All of these are prefixed with "sys_". They may be called + * by non-portable applications if desired. + * + * - the "exported" ones, whose interface must closely match the one + * documented in man(2), that applications are supposed to expect. These + * ones rely on the internal ones, and set errno. + * + * Each syscall will be defined with the two functions, sorted in alphabetical + * order applied to the exported names. + * + * In case of doubt about the relevance of a function here, only those which + * set errno should be defined here. Wrappers like those appearing in man(3) + * should not be placed here. + */ + + +/* + * int brk(void *addr); + * void *sbrk(intptr_t inc) + */ + +static __attribute__((unused)) +void *sys_brk(void *addr) +{ + return (void *)my_syscall1(__NR_brk, addr); +} + +static __attribute__((unused)) +int brk(void *addr) +{ + void *ret = sys_brk(addr); + + if (!ret) { + SET_ERRNO(ENOMEM); + return -1; + } + return 0; +} + +static __attribute__((unused)) +void *sbrk(intptr_t inc) +{ + void *ret; + + /* first call to find current end */ + if ((ret = sys_brk(0)) && (sys_brk(ret + inc) == ret + inc)) + return ret + inc; + + SET_ERRNO(ENOMEM); + return (void *)-1; +} + + +/* + * int chdir(const char *path); + */ + +static __attribute__((unused)) +int sys_chdir(const char *path) +{ + return my_syscall1(__NR_chdir, path); +} + +static __attribute__((unused)) +int chdir(const char *path) +{ + int ret = sys_chdir(path); + + if (ret < 0) { + SET_ERRNO(-ret); + ret = -1; + } + return ret; +} + + +/* + * int chmod(const char *path, mode_t mode); + */ + +static __attribute__((unused)) +int sys_chmod(const char *path, mode_t mode) +{ +#ifdef __NR_fchmodat + return my_syscall4(__NR_fchmodat, AT_FDCWD, path, mode, 0); +#elif defined(__NR_chmod) + return my_syscall2(__NR_chmod, path, mode); +#else +#error Neither __NR_fchmodat nor __NR_chmod defined, cannot implement sys_chmod() +#endif +} + +static __attribute__((unused)) +int chmod(const char *path, mode_t mode) +{ + int ret = sys_chmod(path, mode); + + if (ret < 0) { + SET_ERRNO(-ret); + ret = -1; + } + return ret; +} + + +/* + * int chown(const char *path, uid_t owner, gid_t group); + */ + +static __attribute__((unused)) +int sys_chown(const char *path, uid_t owner, gid_t group) +{ +#ifdef __NR_fchownat + return my_syscall5(__NR_fchownat, AT_FDCWD, path, owner, group, 0); +#elif defined(__NR_chown) + return my_syscall3(__NR_chown, path, owner, group); +#else +#error Neither __NR_fchownat nor __NR_chown defined, cannot implement sys_chown() +#endif +} + +static __attribute__((unused)) +int chown(const char *path, uid_t owner, gid_t group) +{ + int ret = sys_chown(path, owner, group); + + if (ret < 0) { + SET_ERRNO(-ret); + ret = -1; + } + return ret; +} + + +/* + * int chroot(const char *path); + */ + +static __attribute__((unused)) +int sys_chroot(const char *path) +{ + return my_syscall1(__NR_chroot, path); +} + +static __attribute__((unused)) +int chroot(const char *path) +{ + int ret = sys_chroot(path); + + if (ret < 0) { + SET_ERRNO(-ret); + ret = -1; + } + return ret; +} + + +/* + * int close(int fd); + */ + +static __attribute__((unused)) +int sys_close(int fd) +{ + return my_syscall1(__NR_close, fd); +} + +static __attribute__((unused)) +int close(int fd) +{ + int ret = sys_close(fd); + + if (ret < 0) { + SET_ERRNO(-ret); + ret = -1; + } + return ret; +} + + +/* + * int dup(int fd); + */ + +static __attribute__((unused)) +int sys_dup(int fd) +{ + return my_syscall1(__NR_dup, fd); +} + +static __attribute__((unused)) +int dup(int fd) +{ + int ret = sys_dup(fd); + + if (ret < 0) { + SET_ERRNO(-ret); + ret = -1; + } + return ret; +} + + +/* + * int dup2(int old, int new); + */ + +static __attribute__((unused)) +int sys_dup2(int old, int new) +{ +#ifdef __NR_dup3 + return my_syscall3(__NR_dup3, old, new, 0); +#elif defined(__NR_dup2) + return my_syscall2(__NR_dup2, old, new); +#else +#error Neither __NR_dup3 nor __NR_dup2 defined, cannot implement sys_dup2() +#endif +} + +static __attribute__((unused)) +int dup2(int old, int new) +{ + int ret = sys_dup2(old, new); + + if (ret < 0) { + SET_ERRNO(-ret); + ret = -1; + } + return ret; +} + + +/* + * int dup3(int old, int new, int flags); + */ + +#ifdef __NR_dup3 +static __attribute__((unused)) +int sys_dup3(int old, int new, int flags) +{ + return my_syscall3(__NR_dup3, old, new, flags); +} + +static __attribute__((unused)) +int dup3(int old, int new, int flags) +{ + int ret = sys_dup3(old, new, flags); + + if (ret < 0) { + SET_ERRNO(-ret); + ret = -1; + } + return ret; +} +#endif + + +/* + * int execve(const char *filename, char *const argv[], char *const envp[]); + */ + +static __attribute__((unused)) +int sys_execve(const char *filename, char *const argv[], char *const envp[]) +{ + return my_syscall3(__NR_execve, filename, argv, envp); +} + +static __attribute__((unused)) +int execve(const char *filename, char *const argv[], char *const envp[]) +{ + int ret = sys_execve(filename, argv, envp); + + if (ret < 0) { + SET_ERRNO(-ret); + ret = -1; + } + return ret; +} + + +/* + * void exit(int status); + */ + +static __attribute__((noreturn,unused)) +void sys_exit(int status) +{ + my_syscall1(__NR_exit, status & 255); + while(1); // shut the "noreturn" warnings. +} + +static __attribute__((noreturn,unused)) +void exit(int status) +{ + sys_exit(status); +} + + +/* + * pid_t fork(void); + */ + +static __attribute__((unused)) +pid_t sys_fork(void) +{ +#ifdef __NR_clone + /* note: some archs only have clone() and not fork(). Different archs + * have a different API, but most archs have the flags on first arg and + * will not use the rest with no other flag. + */ + return my_syscall5(__NR_clone, SIGCHLD, 0, 0, 0, 0); +#elif defined(__NR_fork) + return my_syscall0(__NR_fork); +#else +#error Neither __NR_clone nor __NR_fork defined, cannot implement sys_fork() +#endif +} + +static __attribute__((unused)) +pid_t fork(void) +{ + pid_t ret = sys_fork(); + + if (ret < 0) { + SET_ERRNO(-ret); + ret = -1; + } + return ret; +} + + +/* + * int fsync(int fd); + */ + +static __attribute__((unused)) +int sys_fsync(int fd) +{ + return my_syscall1(__NR_fsync, fd); +} + +static __attribute__((unused)) +int fsync(int fd) +{ + int ret = sys_fsync(fd); + + if (ret < 0) { + SET_ERRNO(-ret); + ret = -1; + } + return ret; +} + + +/* + * int getdents64(int fd, struct linux_dirent64 *dirp, int count); + */ + +static __attribute__((unused)) +int sys_getdents64(int fd, struct linux_dirent64 *dirp, int count) +{ + return my_syscall3(__NR_getdents64, fd, dirp, count); +} + +static __attribute__((unused)) +int getdents64(int fd, struct linux_dirent64 *dirp, int count) +{ + int ret = sys_getdents64(fd, dirp, count); + + if (ret < 0) { + SET_ERRNO(-ret); + ret = -1; + } + return ret; +} + + +/* + * pid_t getpgid(pid_t pid); + */ + +static __attribute__((unused)) +pid_t sys_getpgid(pid_t pid) +{ + return my_syscall1(__NR_getpgid, pid); +} + +static __attribute__((unused)) +pid_t getpgid(pid_t pid) +{ + pid_t ret = sys_getpgid(pid); + + if (ret < 0) { + SET_ERRNO(-ret); + ret = -1; + } + return ret; +} + + +/* + * pid_t getpgrp(void); + */ + +static __attribute__((unused)) +pid_t sys_getpgrp(void) +{ + return sys_getpgid(0); +} + +static __attribute__((unused)) +pid_t getpgrp(void) +{ + return sys_getpgrp(); +} + + +/* + * pid_t getpid(void); + */ + +static __attribute__((unused)) +pid_t sys_getpid(void) +{ + return my_syscall0(__NR_getpid); +} + +static __attribute__((unused)) +pid_t getpid(void) +{ + return sys_getpid(); +} + + +/* + * pid_t getppid(void); + */ + +static __attribute__((unused)) +pid_t sys_getppid(void) +{ + return my_syscall0(__NR_getppid); +} + +static __attribute__((unused)) +pid_t getppid(void) +{ + return sys_getppid(); +} + + +/* + * pid_t gettid(void); + */ + +static __attribute__((unused)) +pid_t sys_gettid(void) +{ + return my_syscall0(__NR_gettid); +} + +static __attribute__((unused)) +pid_t gettid(void) +{ + return sys_gettid(); +} + + +/* + * int gettimeofday(struct timeval *tv, struct timezone *tz); + */ + +static __attribute__((unused)) +int sys_gettimeofday(struct timeval *tv, struct timezone *tz) +{ + return my_syscall2(__NR_gettimeofday, tv, tz); +} + +static __attribute__((unused)) +int gettimeofday(struct timeval *tv, struct timezone *tz) +{ + int ret = sys_gettimeofday(tv, tz); + + if (ret < 0) { + SET_ERRNO(-ret); + ret = -1; + } + return ret; +} + + +/* + * int ioctl(int fd, unsigned long req, void *value); + */ + +static __attribute__((unused)) +int sys_ioctl(int fd, unsigned long req, void *value) +{ + return my_syscall3(__NR_ioctl, fd, req, value); +} + +static __attribute__((unused)) +int ioctl(int fd, unsigned long req, void *value) +{ + int ret = sys_ioctl(fd, req, value); + + if (ret < 0) { + SET_ERRNO(-ret); + ret = -1; + } + return ret; +} + +/* + * int kill(pid_t pid, int signal); + */ + +static __attribute__((unused)) +int sys_kill(pid_t pid, int signal) +{ + return my_syscall2(__NR_kill, pid, signal); +} + +static __attribute__((unused)) +int kill(pid_t pid, int signal) +{ + int ret = sys_kill(pid, signal); + + if (ret < 0) { + SET_ERRNO(-ret); + ret = -1; + } + return ret; +} + + +/* + * int link(const char *old, const char *new); + */ + +static __attribute__((unused)) +int sys_link(const char *old, const char *new) +{ +#ifdef __NR_linkat + return my_syscall5(__NR_linkat, AT_FDCWD, old, AT_FDCWD, new, 0); +#elif defined(__NR_link) + return my_syscall2(__NR_link, old, new); +#else +#error Neither __NR_linkat nor __NR_link defined, cannot implement sys_link() +#endif +} + +static __attribute__((unused)) +int link(const char *old, const char *new) +{ + int ret = sys_link(old, new); + + if (ret < 0) { + SET_ERRNO(-ret); + ret = -1; + } + return ret; +} + + +/* + * off_t lseek(int fd, off_t offset, int whence); + */ + +static __attribute__((unused)) +off_t sys_lseek(int fd, off_t offset, int whence) +{ + return my_syscall3(__NR_lseek, fd, offset, whence); +} + +static __attribute__((unused)) +off_t lseek(int fd, off_t offset, int whence) +{ + off_t ret = sys_lseek(fd, offset, whence); + + if (ret < 0) { + SET_ERRNO(-ret); + ret = -1; + } + return ret; +} + + +/* + * int mkdir(const char *path, mode_t mode); + */ + +static __attribute__((unused)) +int sys_mkdir(const char *path, mode_t mode) +{ +#ifdef __NR_mkdirat + return my_syscall3(__NR_mkdirat, AT_FDCWD, path, mode); +#elif defined(__NR_mkdir) + return my_syscall2(__NR_mkdir, path, mode); +#else +#error Neither __NR_mkdirat nor __NR_mkdir defined, cannot implement sys_mkdir() +#endif +} + +static __attribute__((unused)) +int mkdir(const char *path, mode_t mode) +{ + int ret = sys_mkdir(path, mode); + + if (ret < 0) { + SET_ERRNO(-ret); + ret = -1; + } + return ret; +} + + +/* + * int mknod(const char *path, mode_t mode, dev_t dev); + */ + +static __attribute__((unused)) +long sys_mknod(const char *path, mode_t mode, dev_t dev) +{ +#ifdef __NR_mknodat + return my_syscall4(__NR_mknodat, AT_FDCWD, path, mode, dev); +#elif defined(__NR_mknod) + return my_syscall3(__NR_mknod, path, mode, dev); +#else +#error Neither __NR_mknodat nor __NR_mknod defined, cannot implement sys_mknod() +#endif +} + +static __attribute__((unused)) +int mknod(const char *path, mode_t mode, dev_t dev) +{ + int ret = sys_mknod(path, mode, dev); + + if (ret < 0) { + SET_ERRNO(-ret); + ret = -1; + } + return ret; +} + +#ifndef MAP_SHARED +#define MAP_SHARED 0x01 /* Share changes */ +#define MAP_PRIVATE 0x02 /* Changes are private */ +#define MAP_SHARED_VALIDATE 0x03 /* share + validate extension flags */ +#endif + +#ifndef MAP_FAILED +#define MAP_FAILED ((void *)-1) +#endif + +static __attribute__((unused)) +void *sys_mmap(void *addr, size_t length, int prot, int flags, int fd, + off_t offset) +{ +#ifndef my_syscall6 + /* Function not implemented. */ + return -ENOSYS; +#else + + int n; + +#if defined(__i386__) + n = __NR_mmap2; + offset >>= 12; +#else + n = __NR_mmap; +#endif + + return (void *)my_syscall6(n, addr, length, prot, flags, fd, offset); +#endif +} + +static __attribute__((unused)) +void *mmap(void *addr, size_t length, int prot, int flags, int fd, off_t offset) +{ + void *ret = sys_mmap(addr, length, prot, flags, fd, offset); + + if ((unsigned long)ret >= -4095UL) { + SET_ERRNO(-(long)ret); + ret = MAP_FAILED; + } + return ret; +} + +static __attribute__((unused)) +int sys_munmap(void *addr, size_t length) +{ + return my_syscall2(__NR_munmap, addr, length); +} + +static __attribute__((unused)) +int munmap(void *addr, size_t length) +{ + int ret = sys_munmap(addr, length); + + if (ret < 0) { + SET_ERRNO(-ret); + ret = -1; + } + return ret; +} + +/* + * int mount(const char *source, const char *target, + * const char *fstype, unsigned long flags, + * const void *data); + */ +static __attribute__((unused)) +int sys_mount(const char *src, const char *tgt, const char *fst, + unsigned long flags, const void *data) +{ + return my_syscall5(__NR_mount, src, tgt, fst, flags, data); +} + +static __attribute__((unused)) +int mount(const char *src, const char *tgt, + const char *fst, unsigned long flags, + const void *data) +{ + int ret = sys_mount(src, tgt, fst, flags, data); + + if (ret < 0) { + SET_ERRNO(-ret); + ret = -1; + } + return ret; +} + + +/* + * int open(const char *path, int flags[, mode_t mode]); + */ + +static __attribute__((unused)) +int sys_open(const char *path, int flags, mode_t mode) +{ +#ifdef __NR_openat + return my_syscall4(__NR_openat, AT_FDCWD, path, flags, mode); +#elif defined(__NR_open) + return my_syscall3(__NR_open, path, flags, mode); +#else +#error Neither __NR_openat nor __NR_open defined, cannot implement sys_open() +#endif +} + +static __attribute__((unused)) +int open(const char *path, int flags, ...) +{ + mode_t mode = 0; + int ret; + + if (flags & O_CREAT) { + va_list args; + + va_start(args, flags); + mode = va_arg(args, mode_t); + va_end(args); + } + + ret = sys_open(path, flags, mode); + + if (ret < 0) { + SET_ERRNO(-ret); + ret = -1; + } + return ret; +} + + +/* + * int pivot_root(const char *new, const char *old); + */ + +static __attribute__((unused)) +int sys_pivot_root(const char *new, const char *old) +{ + return my_syscall2(__NR_pivot_root, new, old); +} + +static __attribute__((unused)) +int pivot_root(const char *new, const char *old) +{ + int ret = sys_pivot_root(new, old); + + if (ret < 0) { + SET_ERRNO(-ret); + ret = -1; + } + return ret; +} + + +/* + * int poll(struct pollfd *fds, int nfds, int timeout); + */ + +static __attribute__((unused)) +int sys_poll(struct pollfd *fds, int nfds, int timeout) +{ +#if defined(__NR_ppoll) + struct timespec t; + + if (timeout >= 0) { + t.tv_sec = timeout / 1000; + t.tv_nsec = (timeout % 1000) * 1000000; + } + return my_syscall4(__NR_ppoll, fds, nfds, (timeout >= 0) ? &t : NULL, NULL); +#elif defined(__NR_poll) + return my_syscall3(__NR_poll, fds, nfds, timeout); +#else +#error Neither __NR_ppoll nor __NR_poll defined, cannot implement sys_poll() +#endif +} + +static __attribute__((unused)) +int poll(struct pollfd *fds, int nfds, int timeout) +{ + int ret = sys_poll(fds, nfds, timeout); + + if (ret < 0) { + SET_ERRNO(-ret); + ret = -1; + } + return ret; +} + + +/* + * ssize_t read(int fd, void *buf, size_t count); + */ + +static __attribute__((unused)) +ssize_t sys_read(int fd, void *buf, size_t count) +{ + return my_syscall3(__NR_read, fd, buf, count); +} + +static __attribute__((unused)) +ssize_t read(int fd, void *buf, size_t count) +{ + ssize_t ret = sys_read(fd, buf, count); + + if (ret < 0) { + SET_ERRNO(-ret); + ret = -1; + } + return ret; +} + + +/* + * int reboot(int cmd); + * <cmd> is among LINUX_REBOOT_CMD_* + */ + +static __attribute__((unused)) +ssize_t sys_reboot(int magic1, int magic2, int cmd, void *arg) +{ + return my_syscall4(__NR_reboot, magic1, magic2, cmd, arg); +} + +static __attribute__((unused)) +int reboot(int cmd) +{ + int ret = sys_reboot(LINUX_REBOOT_MAGIC1, LINUX_REBOOT_MAGIC2, cmd, 0); + + if (ret < 0) { + SET_ERRNO(-ret); + ret = -1; + } + return ret; +} + + +/* + * int sched_yield(void); + */ + +static __attribute__((unused)) +int sys_sched_yield(void) +{ + return my_syscall0(__NR_sched_yield); +} + +static __attribute__((unused)) +int sched_yield(void) +{ + int ret = sys_sched_yield(); + + if (ret < 0) { + SET_ERRNO(-ret); + ret = -1; + } + return ret; +} + + +/* + * int select(int nfds, fd_set *read_fds, fd_set *write_fds, + * fd_set *except_fds, struct timeval *timeout); + */ + +static __attribute__((unused)) +int sys_select(int nfds, fd_set *rfds, fd_set *wfds, fd_set *efds, struct timeval *timeout) +{ +#if defined(__ARCH_WANT_SYS_OLD_SELECT) && !defined(__NR__newselect) + struct sel_arg_struct { + unsigned long n; + fd_set *r, *w, *e; + struct timeval *t; + } arg = { .n = nfds, .r = rfds, .w = wfds, .e = efds, .t = timeout }; + return my_syscall1(__NR_select, &arg); +#elif defined(__ARCH_WANT_SYS_PSELECT6) && defined(__NR_pselect6) + struct timespec t; + + if (timeout) { + t.tv_sec = timeout->tv_sec; + t.tv_nsec = timeout->tv_usec * 1000; + } + return my_syscall6(__NR_pselect6, nfds, rfds, wfds, efds, timeout ? &t : NULL, NULL); +#elif defined(__NR__newselect) || defined(__NR_select) +#ifndef __NR__newselect +#define __NR__newselect __NR_select +#endif + return my_syscall5(__NR__newselect, nfds, rfds, wfds, efds, timeout); +#else +#error None of __NR_select, __NR_pselect6, nor __NR__newselect defined, cannot implement sys_select() +#endif +} + +static __attribute__((unused)) +int select(int nfds, fd_set *rfds, fd_set *wfds, fd_set *efds, struct timeval *timeout) +{ + int ret = sys_select(nfds, rfds, wfds, efds, timeout); + + if (ret < 0) { + SET_ERRNO(-ret); + ret = -1; + } + return ret; +} + + +/* + * int setpgid(pid_t pid, pid_t pgid); + */ + +static __attribute__((unused)) +int sys_setpgid(pid_t pid, pid_t pgid) +{ + return my_syscall2(__NR_setpgid, pid, pgid); +} + +static __attribute__((unused)) +int setpgid(pid_t pid, pid_t pgid) +{ + int ret = sys_setpgid(pid, pgid); + + if (ret < 0) { + SET_ERRNO(-ret); + ret = -1; + } + return ret; +} + + +/* + * pid_t setsid(void); + */ + +static __attribute__((unused)) +pid_t sys_setsid(void) +{ + return my_syscall0(__NR_setsid); +} + +static __attribute__((unused)) +pid_t setsid(void) +{ + pid_t ret = sys_setsid(); + + if (ret < 0) { + SET_ERRNO(-ret); + ret = -1; + } + return ret; +} + + +/* + * int stat(const char *path, struct stat *buf); + * Warning: the struct stat's layout is arch-dependent. + */ + +static __attribute__((unused)) +int sys_stat(const char *path, struct stat *buf) +{ + struct sys_stat_struct stat; + long ret; + +#ifdef __NR_newfstatat + /* only solution for arm64 */ + ret = my_syscall4(__NR_newfstatat, AT_FDCWD, path, &stat, 0); +#elif defined(__NR_stat) + ret = my_syscall2(__NR_stat, path, &stat); +#else +#error Neither __NR_newfstatat nor __NR_stat defined, cannot implement sys_stat() +#endif + buf->st_dev = stat.st_dev; + buf->st_ino = stat.st_ino; + buf->st_mode = stat.st_mode; + buf->st_nlink = stat.st_nlink; + buf->st_uid = stat.st_uid; + buf->st_gid = stat.st_gid; + buf->st_rdev = stat.st_rdev; + buf->st_size = stat.st_size; + buf->st_blksize = stat.st_blksize; + buf->st_blocks = stat.st_blocks; + buf->st_atime = stat.st_atime; + buf->st_mtime = stat.st_mtime; + buf->st_ctime = stat.st_ctime; + return ret; +} + +static __attribute__((unused)) +int stat(const char *path, struct stat *buf) +{ + int ret = sys_stat(path, buf); + + if (ret < 0) { + SET_ERRNO(-ret); + ret = -1; + } + return ret; +} + + +/* + * int symlink(const char *old, const char *new); + */ + +static __attribute__((unused)) +int sys_symlink(const char *old, const char *new) +{ +#ifdef __NR_symlinkat + return my_syscall3(__NR_symlinkat, old, AT_FDCWD, new); +#elif defined(__NR_symlink) + return my_syscall2(__NR_symlink, old, new); +#else +#error Neither __NR_symlinkat nor __NR_symlink defined, cannot implement sys_symlink() +#endif +} + +static __attribute__((unused)) +int symlink(const char *old, const char *new) +{ + int ret = sys_symlink(old, new); + + if (ret < 0) { + SET_ERRNO(-ret); + ret = -1; + } + return ret; +} + + +/* + * mode_t umask(mode_t mode); + */ + +static __attribute__((unused)) +mode_t sys_umask(mode_t mode) +{ + return my_syscall1(__NR_umask, mode); +} + +static __attribute__((unused)) +mode_t umask(mode_t mode) +{ + return sys_umask(mode); +} + + +/* + * int umount2(const char *path, int flags); + */ + +static __attribute__((unused)) +int sys_umount2(const char *path, int flags) +{ + return my_syscall2(__NR_umount2, path, flags); +} + +static __attribute__((unused)) +int umount2(const char *path, int flags) +{ + int ret = sys_umount2(path, flags); + + if (ret < 0) { + SET_ERRNO(-ret); + ret = -1; + } + return ret; +} + + +/* + * int unlink(const char *path); + */ + +static __attribute__((unused)) +int sys_unlink(const char *path) +{ +#ifdef __NR_unlinkat + return my_syscall3(__NR_unlinkat, AT_FDCWD, path, 0); +#elif defined(__NR_unlink) + return my_syscall1(__NR_unlink, path); +#else +#error Neither __NR_unlinkat nor __NR_unlink defined, cannot implement sys_unlink() +#endif +} + +static __attribute__((unused)) +int unlink(const char *path) +{ + int ret = sys_unlink(path); + + if (ret < 0) { + SET_ERRNO(-ret); + ret = -1; + } + return ret; +} + + +/* + * pid_t wait(int *status); + * pid_t wait4(pid_t pid, int *status, int options, struct rusage *rusage); + * pid_t waitpid(pid_t pid, int *status, int options); + */ + +static __attribute__((unused)) +pid_t sys_wait4(pid_t pid, int *status, int options, struct rusage *rusage) +{ + return my_syscall4(__NR_wait4, pid, status, options, rusage); +} + +static __attribute__((unused)) +pid_t wait(int *status) +{ + pid_t ret = sys_wait4(-1, status, 0, NULL); + + if (ret < 0) { + SET_ERRNO(-ret); + ret = -1; + } + return ret; +} + +static __attribute__((unused)) +pid_t wait4(pid_t pid, int *status, int options, struct rusage *rusage) +{ + pid_t ret = sys_wait4(pid, status, options, rusage); + + if (ret < 0) { + SET_ERRNO(-ret); + ret = -1; + } + return ret; +} + + +static __attribute__((unused)) +pid_t waitpid(pid_t pid, int *status, int options) +{ + pid_t ret = sys_wait4(pid, status, options, NULL); + + if (ret < 0) { + SET_ERRNO(-ret); + ret = -1; + } + return ret; +} + + +/* + * ssize_t write(int fd, const void *buf, size_t count); + */ + +static __attribute__((unused)) +ssize_t sys_write(int fd, const void *buf, size_t count) +{ + return my_syscall3(__NR_write, fd, buf, count); +} + +static __attribute__((unused)) +ssize_t write(int fd, const void *buf, size_t count) +{ + ssize_t ret = sys_write(fd, buf, count); + + if (ret < 0) { + SET_ERRNO(-ret); + ret = -1; + } + return ret; +} + + +#endif /* _NOLIBC_SYS_H */ diff --git a/tools/include/nolibc/time.h b/tools/include/nolibc/time.h new file mode 100644 index 000000000000..d18b7661fdd7 --- /dev/null +++ b/tools/include/nolibc/time.h @@ -0,0 +1,28 @@ +/* SPDX-License-Identifier: LGPL-2.1 OR MIT */ +/* + * time function definitions for NOLIBC + * Copyright (C) 2017-2022 Willy Tarreau <w@1wt.eu> + */ + +#ifndef _NOLIBC_TIME_H +#define _NOLIBC_TIME_H + +#include "std.h" +#include "arch.h" +#include "types.h" +#include "sys.h" + +static __attribute__((unused)) +time_t time(time_t *tptr) +{ + struct timeval tv; + + /* note, cannot fail here */ + sys_gettimeofday(&tv, NULL); + + if (tptr) + *tptr = tv.tv_sec; + return tv.tv_sec; +} + +#endif /* _NOLIBC_TIME_H */ diff --git a/tools/include/nolibc/types.h b/tools/include/nolibc/types.h new file mode 100644 index 000000000000..959997034e55 --- /dev/null +++ b/tools/include/nolibc/types.h @@ -0,0 +1,205 @@ +/* SPDX-License-Identifier: LGPL-2.1 OR MIT */ +/* + * Special types used by various syscalls for NOLIBC + * Copyright (C) 2017-2021 Willy Tarreau <w@1wt.eu> + */ + +#ifndef _NOLIBC_TYPES_H +#define _NOLIBC_TYPES_H + +#include "std.h" +#include <linux/time.h> + + +/* Only the generic macros and types may be defined here. The arch-specific + * ones such as the O_RDONLY and related macros used by fcntl() and open(), or + * the layout of sys_stat_struct must not be defined here. + */ + +/* stat flags (WARNING, octal here) */ +#define S_IFDIR 0040000 +#define S_IFCHR 0020000 +#define S_IFBLK 0060000 +#define S_IFREG 0100000 +#define S_IFIFO 0010000 +#define S_IFLNK 0120000 +#define S_IFSOCK 0140000 +#define S_IFMT 0170000 + +#define S_ISDIR(mode) (((mode) & S_IFDIR) == S_IFDIR) +#define S_ISCHR(mode) (((mode) & S_IFCHR) == S_IFCHR) +#define S_ISBLK(mode) (((mode) & S_IFBLK) == S_IFBLK) +#define S_ISREG(mode) (((mode) & S_IFREG) == S_IFREG) +#define S_ISFIFO(mode) (((mode) & S_IFIFO) == S_IFIFO) +#define S_ISLNK(mode) (((mode) & S_IFLNK) == S_IFLNK) +#define S_ISSOCK(mode) (((mode) & S_IFSOCK) == S_IFSOCK) + +/* dirent types */ +#define DT_UNKNOWN 0x0 +#define DT_FIFO 0x1 +#define DT_CHR 0x2 +#define DT_DIR 0x4 +#define DT_BLK 0x6 +#define DT_REG 0x8 +#define DT_LNK 0xa +#define DT_SOCK 0xc + +/* commonly an fd_set represents 256 FDs */ +#ifndef FD_SETSIZE +#define FD_SETSIZE 256 +#endif + +/* PATH_MAX and MAXPATHLEN are often used and found with plenty of different + * values. + */ +#ifndef PATH_MAX +#define PATH_MAX 4096 +#endif + +#ifndef MAXPATHLEN +#define MAXPATHLEN (PATH_MAX) +#endif + +/* Special FD used by all the *at functions */ +#ifndef AT_FDCWD +#define AT_FDCWD (-100) +#endif + +/* whence values for lseek() */ +#define SEEK_SET 0 +#define SEEK_CUR 1 +#define SEEK_END 2 + +/* cmd for reboot() */ +#define LINUX_REBOOT_MAGIC1 0xfee1dead +#define LINUX_REBOOT_MAGIC2 0x28121969 +#define LINUX_REBOOT_CMD_HALT 0xcdef0123 +#define LINUX_REBOOT_CMD_POWER_OFF 0x4321fedc +#define LINUX_REBOOT_CMD_RESTART 0x01234567 +#define LINUX_REBOOT_CMD_SW_SUSPEND 0xd000fce2 + +/* Macros used on waitpid()'s return status */ +#define WEXITSTATUS(status) (((status) & 0xff00) >> 8) +#define WIFEXITED(status) (((status) & 0x7f) == 0) + +/* waitpid() flags */ +#define WNOHANG 1 + +/* standard exit() codes */ +#define EXIT_SUCCESS 0 +#define EXIT_FAILURE 1 + +/* for select() */ +typedef struct { + uint32_t fd32[(FD_SETSIZE + 31) / 32]; +} fd_set; + +#define FD_CLR(fd, set) do { \ + fd_set *__set = (set); \ + int __fd = (fd); \ + if (__fd >= 0) \ + __set->fd32[__fd / 32] &= ~(1U << (__fd & 31)); \ + } while (0) + +#define FD_SET(fd, set) do { \ + fd_set *__set = (set); \ + int __fd = (fd); \ + if (__fd >= 0) \ + __set->fd32[__fd / 32] |= 1U << (__fd & 31); \ + } while (0) + +#define FD_ISSET(fd, set) ({ \ + fd_set *__set = (set); \ + int __fd = (fd); \ + int __r = 0; \ + if (__fd >= 0) \ + __r = !!(__set->fd32[__fd / 32] & 1U << (__fd & 31)); \ + __r; \ + }) + +#define FD_ZERO(set) do { \ + fd_set *__set = (set); \ + int __idx; \ + for (__idx = 0; __idx < (FD_SETSIZE+31) / 32; __idx ++) \ + __set->fd32[__idx] = 0; \ + } while (0) + +/* for poll() */ +#define POLLIN 0x0001 +#define POLLPRI 0x0002 +#define POLLOUT 0x0004 +#define POLLERR 0x0008 +#define POLLHUP 0x0010 +#define POLLNVAL 0x0020 + +struct pollfd { + int fd; + short int events; + short int revents; +}; + +/* for getdents64() */ +struct linux_dirent64 { + uint64_t d_ino; + int64_t d_off; + unsigned short d_reclen; + unsigned char d_type; + char d_name[]; +}; + +/* needed by wait4() */ +struct rusage { + struct timeval ru_utime; + struct timeval ru_stime; + long ru_maxrss; + long ru_ixrss; + long ru_idrss; + long ru_isrss; + long ru_minflt; + long ru_majflt; + long ru_nswap; + long ru_inblock; + long ru_oublock; + long ru_msgsnd; + long ru_msgrcv; + long ru_nsignals; + long ru_nvcsw; + long ru_nivcsw; +}; + +/* The format of the struct as returned by the libc to the application, which + * significantly differs from the format returned by the stat() syscall flavours. + */ +struct stat { + dev_t st_dev; /* ID of device containing file */ + ino_t st_ino; /* inode number */ + mode_t st_mode; /* protection */ + nlink_t st_nlink; /* number of hard links */ + uid_t st_uid; /* user ID of owner */ + gid_t st_gid; /* group ID of owner */ + dev_t st_rdev; /* device ID (if special file) */ + off_t st_size; /* total size, in bytes */ + blksize_t st_blksize; /* blocksize for file system I/O */ + blkcnt_t st_blocks; /* number of 512B blocks allocated */ + time_t st_atime; /* time of last access */ + time_t st_mtime; /* time of last modification */ + time_t st_ctime; /* time of last status change */ +}; + +/* WARNING, it only deals with the 4096 first majors and 256 first minors */ +#define makedev(major, minor) ((dev_t)((((major) & 0xfff) << 8) | ((minor) & 0xff))) +#define major(dev) ((unsigned int)(((dev) >> 8) & 0xfff)) +#define minor(dev) ((unsigned int)(((dev) & 0xff)) + +#ifndef offsetof +#define offsetof(TYPE, FIELD) ((size_t) &((TYPE *)0)->FIELD) +#endif + +#ifndef container_of +#define container_of(PTR, TYPE, FIELD) ({ \ + __typeof__(((TYPE *)0)->FIELD) *__FIELD_PTR = (PTR); \ + (TYPE *)((char *) __FIELD_PTR - offsetof(TYPE, FIELD)); \ +}) +#endif + +#endif /* _NOLIBC_TYPES_H */ diff --git a/tools/include/nolibc/unistd.h b/tools/include/nolibc/unistd.h new file mode 100644 index 000000000000..1c25e20ee360 --- /dev/null +++ b/tools/include/nolibc/unistd.h @@ -0,0 +1,54 @@ +/* SPDX-License-Identifier: LGPL-2.1 OR MIT */ +/* + * unistd function definitions for NOLIBC + * Copyright (C) 2017-2022 Willy Tarreau <w@1wt.eu> + */ + +#ifndef _NOLIBC_UNISTD_H +#define _NOLIBC_UNISTD_H + +#include "std.h" +#include "arch.h" +#include "types.h" +#include "sys.h" + + +static __attribute__((unused)) +int msleep(unsigned int msecs) +{ + struct timeval my_timeval = { msecs / 1000, (msecs % 1000) * 1000 }; + + if (sys_select(0, 0, 0, 0, &my_timeval) < 0) + return (my_timeval.tv_sec * 1000) + + (my_timeval.tv_usec / 1000) + + !!(my_timeval.tv_usec % 1000); + else + return 0; +} + +static __attribute__((unused)) +unsigned int sleep(unsigned int seconds) +{ + struct timeval my_timeval = { seconds, 0 }; + + if (sys_select(0, 0, 0, 0, &my_timeval) < 0) + return my_timeval.tv_sec + !!my_timeval.tv_usec; + else + return 0; +} + +static __attribute__((unused)) +int usleep(unsigned int usecs) +{ + struct timeval my_timeval = { usecs / 1000000, usecs % 1000000 }; + + return sys_select(0, 0, 0, 0, &my_timeval); +} + +static __attribute__((unused)) +int tcsetpgrp(int fd, pid_t pid) +{ + return ioctl(fd, TIOCSPGRP, &pid); +} + +#endif /* _NOLIBC_UNISTD_H */ diff --git a/tools/include/uapi/linux/kvm.h b/tools/include/uapi/linux/kvm.h index 91a6fe4e02c0..6a184d260c7f 100644 --- a/tools/include/uapi/linux/kvm.h +++ b/tools/include/uapi/linux/kvm.h @@ -445,7 +445,13 @@ struct kvm_run { #define KVM_SYSTEM_EVENT_RESET 2 #define KVM_SYSTEM_EVENT_CRASH 3 __u32 type; - __u64 flags; + __u32 ndata; + union { +#ifndef __KERNEL__ + __u64 flags; +#endif + __u64 data[16]; + }; } system_event; /* KVM_EXIT_S390_STSI */ struct { @@ -1144,6 +1150,8 @@ struct kvm_ppc_resize_hpt { #define KVM_CAP_S390_MEM_OP_EXTENSION 211 #define KVM_CAP_PMU_CAPABILITY 212 #define KVM_CAP_DISABLE_QUIRKS2 213 +/* #define KVM_CAP_VM_TSC_CONTROL 214 */ +#define KVM_CAP_SYSTEM_EVENT_DATA 215 #ifdef KVM_CAP_IRQ_ROUTING diff --git a/tools/memory-model/README b/tools/memory-model/README index 9edd402704c4..dab38904206a 100644 --- a/tools/memory-model/README +++ b/tools/memory-model/README @@ -54,7 +54,8 @@ klitmus7 Compatibility Table -- 4.14 7.48 -- 4.15 -- 4.19 7.49 -- 4.20 -- 5.5 7.54 -- - 5.6 -- 7.56 -- + 5.6 -- 5.16 7.56 -- + 5.17 -- 7.56.1 -- ============ ========== diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config index f3bf9297bcc0..1bd64e7404b9 100644 --- a/tools/perf/Makefile.config +++ b/tools/perf/Makefile.config @@ -553,9 +553,16 @@ ifndef NO_LIBELF ifeq ($(feature-libbpf), 1) EXTLIBS += -lbpf $(call detected,CONFIG_LIBBPF_DYNAMIC) + + $(call feature_check,libbpf-btf__load_from_kernel_by_id) + ifeq ($(feature-libbpf-btf__load_from_kernel_by_id), 1) + CFLAGS += -DHAVE_LIBBPF_BTF__LOAD_FROM_KERNEL_BY_ID + endif else dummy := $(error Error: No libbpf devel library found, please install libbpf-devel); endif + else + CFLAGS += -DHAVE_LIBBPF_BTF__LOAD_FROM_KERNEL_BY_ID endif endif diff --git a/tools/perf/arch/x86/util/perf_regs.c b/tools/perf/arch/x86/util/perf_regs.c index 207c56805c55..0ed177991ad0 100644 --- a/tools/perf/arch/x86/util/perf_regs.c +++ b/tools/perf/arch/x86/util/perf_regs.c @@ -9,6 +9,8 @@ #include "../../../util/perf_regs.h" #include "../../../util/debug.h" #include "../../../util/event.h" +#include "../../../util/pmu.h" +#include "../../../util/pmu-hybrid.h" const struct sample_reg sample_reg_masks[] = { SMPL_REG(AX, PERF_REG_X86_AX), @@ -284,12 +286,22 @@ uint64_t arch__intr_reg_mask(void) .disabled = 1, .exclude_kernel = 1, }; + struct perf_pmu *pmu; int fd; /* * In an unnamed union, init it here to build on older gcc versions */ attr.sample_period = 1; + if (perf_pmu__has_hybrid()) { + /* + * The same register set is supported among different hybrid PMUs. + * Only check the first available one. + */ + pmu = list_first_entry(&perf_pmu__hybrid_pmus, typeof(*pmu), hybrid_list); + attr.config |= (__u64)pmu->type << PERF_PMU_TYPE_SHIFT; + } + event_attr_init(&attr); fd = sys_perf_event_open(&attr, 0, -1, -1, 0); diff --git a/tools/perf/bench/numa.c b/tools/perf/bench/numa.c index 44e1f8a44087..20eed1e53f80 100644 --- a/tools/perf/bench/numa.c +++ b/tools/perf/bench/numa.c @@ -311,6 +311,7 @@ err_out: /* BUG_ON due to failure in allocation of orig_mask/mask */ BUG_ON(-1); + return NULL; } static cpu_set_t *bind_to_node(int target_node) @@ -364,6 +365,7 @@ err_out: /* BUG_ON due to failure in allocation of orig_mask/mask */ BUG_ON(-1); + return NULL; } static void bind_to_cpumask(cpu_set_t *mask) @@ -1738,7 +1740,7 @@ static int __bench_numa(const char *name) "GB/sec,", "total-speed", "GB/sec total speed"); if (g->p.show_details >= 2) { - char tname[14 + 2 * 10 + 1]; + char tname[14 + 2 * 11 + 1]; struct thread_data *td; for (p = 0; p < g->p.nr_proc; p++) { for (t = 0; t < g->p.nr_threads; t++) { diff --git a/tools/perf/tests/bpf.c b/tools/perf/tests/bpf.c index 57b9591f7cbb..17c023823713 100644 --- a/tools/perf/tests/bpf.c +++ b/tools/perf/tests/bpf.c @@ -222,11 +222,11 @@ static int __test__bpf(int idx) ret = test_llvm__fetch_bpf_obj(&obj_buf, &obj_buf_sz, bpf_testcase_table[idx].prog_id, - true, NULL); + false, NULL); if (ret != TEST_OK || !obj_buf || !obj_buf_sz) { pr_debug("Unable to get BPF object, %s\n", bpf_testcase_table[idx].msg_compile_fail); - if (idx == 0) + if ((idx == 0) || (ret == TEST_SKIP)) return TEST_SKIP; else return TEST_FAIL; @@ -364,9 +364,11 @@ static int test__bpf_prologue_test(struct test_suite *test __maybe_unused, static struct test_case bpf_tests[] = { #ifdef HAVE_LIBBPF_SUPPORT TEST_CASE("Basic BPF filtering", basic_bpf_test), - TEST_CASE("BPF pinning", bpf_pinning), + TEST_CASE_REASON("BPF pinning", bpf_pinning, + "clang isn't installed or environment missing BPF support"), #ifdef HAVE_BPF_PROLOGUE - TEST_CASE("BPF prologue generation", bpf_prologue_test), + TEST_CASE_REASON("BPF prologue generation", bpf_prologue_test, + "clang isn't installed or environment missing BPF support"), #else TEST_CASE_REASON("BPF prologue generation", bpf_prologue_test, "not compiled in"), #endif diff --git a/tools/perf/tests/builtin-test.c b/tools/perf/tests/builtin-test.c index fac3717d9ba1..d336cda94a11 100644 --- a/tools/perf/tests/builtin-test.c +++ b/tools/perf/tests/builtin-test.c @@ -279,6 +279,7 @@ static const char *shell_test__description(char *description, size_t size, { FILE *fp; char filename[PATH_MAX]; + int ch; path__join(filename, sizeof(filename), path, name); fp = fopen(filename, "r"); @@ -286,7 +287,9 @@ static const char *shell_test__description(char *description, size_t size, return NULL; /* Skip shebang */ - while (fgetc(fp) != '\n'); + do { + ch = fgetc(fp); + } while (ch != EOF && ch != '\n'); description = fgets(description, size, fp); fclose(fp); @@ -417,7 +420,8 @@ static int run_shell_tests(int argc, const char *argv[], int i, int width, .priv = &st, }; - if (!perf_test__matches(test_suite.desc, curr, argc, argv)) + if (test_suite.desc == NULL || + !perf_test__matches(test_suite.desc, curr, argc, argv)) continue; st.file = ent->d_name; diff --git a/tools/perf/tests/shell/stat_all_pmu.sh b/tools/perf/tests/shell/stat_all_pmu.sh index b30dba455f36..9c9ef33e0b3c 100755 --- a/tools/perf/tests/shell/stat_all_pmu.sh +++ b/tools/perf/tests/shell/stat_all_pmu.sh @@ -5,6 +5,16 @@ set -e for p in $(perf list --raw-dump pmu); do + # In powerpc, skip the events for hv_24x7 and hv_gpci. + # These events needs input values to be filled in for + # core, chip, partition id based on system. + # Example: hv_24x7/CPM_ADJUNCT_INST,domain=?,core=?/ + # hv_gpci/event,partition_id=?/ + # Hence skip these events for ppc. + if echo "$p" |grep -Eq 'hv_24x7|hv_gpci' ; then + echo "Skipping: Event '$p' in powerpc" + continue + fi echo "Testing $p" result=$(perf stat -e "$p" true 2>&1) if ! echo "$result" | grep -q "$p" && ! echo "$result" | grep -q "<not supported>" ; then diff --git a/tools/perf/tests/shell/test_arm_coresight.sh b/tools/perf/tests/shell/test_arm_coresight.sh index 6de53b7ef5ff..e4cb4f1806ff 100755 --- a/tools/perf/tests/shell/test_arm_coresight.sh +++ b/tools/perf/tests/shell/test_arm_coresight.sh @@ -29,7 +29,6 @@ cleanup_files() rm -f ${file} rm -f "${perfdata}.old" trap - exit term int - kill -2 $$ exit $glb_err } diff --git a/tools/perf/tests/topology.c b/tools/perf/tests/topology.c index ee1e3dcbc0bd..d23a9e322ff5 100644 --- a/tools/perf/tests/topology.c +++ b/tools/perf/tests/topology.c @@ -109,6 +109,17 @@ static int check_cpu_topology(char *path, struct perf_cpu_map *map) && strncmp(session->header.env.arch, "aarch64", 7)) return TEST_SKIP; + /* + * In powerpc pSeries platform, not all the topology information + * are exposed via sysfs. Due to restriction, detail like + * physical_package_id will be set to -1. Hence skip this + * test if physical_package_id returns -1 for cpu from perf_cpu_map. + */ + if (strncmp(session->header.env.arch, "powerpc", 7)) { + if (cpu__get_socket_id(perf_cpu_map__cpu(map, 0)) == -1) + return TEST_SKIP; + } + TEST_ASSERT_VAL("Session header CPU map not set", session->header.env.cpu); for (i = 0; i < session->header.env.nr_cpus_avail; i++) { diff --git a/tools/perf/util/bpf-event.c b/tools/perf/util/bpf-event.c index 94624733af7e..8271ab764eb5 100644 --- a/tools/perf/util/bpf-event.c +++ b/tools/perf/util/bpf-event.c @@ -22,7 +22,8 @@ #include "record.h" #include "util/synthetic-events.h" -struct btf * __weak btf__load_from_kernel_by_id(__u32 id) +#ifndef HAVE_LIBBPF_BTF__LOAD_FROM_KERNEL_BY_ID +struct btf *btf__load_from_kernel_by_id(__u32 id) { struct btf *btf; #pragma GCC diagnostic push @@ -32,6 +33,7 @@ struct btf * __weak btf__load_from_kernel_by_id(__u32 id) return err ? ERR_PTR(err) : btf; } +#endif int __weak bpf_prog_load(enum bpf_prog_type prog_type, const char *prog_name __maybe_unused, diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c index f9a320694b85..a7f93f5a1ac8 100644 --- a/tools/perf/util/session.c +++ b/tools/perf/util/session.c @@ -1151,9 +1151,20 @@ static void branch_stack__printf(struct perf_sample *sample, bool callstack) struct branch_entry *entries = perf_sample__branch_entries(sample); uint64_t i; - printf("%s: nr:%" PRIu64 "\n", - !callstack ? "... branch stack" : "... branch callstack", - sample->branch_stack->nr); + if (!callstack) { + printf("%s: nr:%" PRIu64 "\n", "... branch stack", sample->branch_stack->nr); + } else { + /* the reason of adding 1 to nr is because after expanding + * branch stack it generates nr + 1 callstack records. e.g., + * B()->C() + * A()->B() + * the final callstack should be: + * C() + * B() + * A() + */ + printf("%s: nr:%" PRIu64 "\n", "... branch callstack", sample->branch_stack->nr+1); + } for (i = 0; i < sample->branch_stack->nr; i++) { struct branch_entry *e = &entries[i]; @@ -1169,8 +1180,13 @@ static void branch_stack__printf(struct perf_sample *sample, bool callstack) (unsigned)e->flags.reserved, e->flags.type ? branch_type_name(e->flags.type) : ""); } else { - printf("..... %2"PRIu64": %016" PRIx64 "\n", - i, i > 0 ? e->from : e->to); + if (i == 0) { + printf("..... %2"PRIu64": %016" PRIx64 "\n" + "..... %2"PRIu64": %016" PRIx64 "\n", + i, e->to, i+1, e->from); + } else { + printf("..... %2"PRIu64": %016" PRIx64 "\n", i+1, e->from); + } } } } diff --git a/tools/perf/util/stat.c b/tools/perf/util/stat.c index 817a2de264b4..c1af37e11f98 100644 --- a/tools/perf/util/stat.c +++ b/tools/perf/util/stat.c @@ -472,9 +472,10 @@ int perf_stat_process_counter(struct perf_stat_config *config, int perf_event__process_stat_event(struct perf_session *session, union perf_event *event) { - struct perf_counts_values count; + struct perf_counts_values count, *ptr; struct perf_record_stat *st = &event->stat; struct evsel *counter; + int cpu_map_idx; count.val = st->val; count.ena = st->ena; @@ -485,8 +486,18 @@ int perf_event__process_stat_event(struct perf_session *session, pr_err("Failed to resolve counter for stat event.\n"); return -EINVAL; } - - *perf_counts(counter->counts, st->cpu, st->thread) = count; + cpu_map_idx = perf_cpu_map__idx(evsel__cpus(counter), (struct perf_cpu){.cpu = st->cpu}); + if (cpu_map_idx == -1) { + pr_err("Invalid CPU %d for event %s.\n", st->cpu, evsel__name(counter)); + return -EINVAL; + } + ptr = perf_counts(counter->counts, cpu_map_idx, st->thread); + if (ptr == NULL) { + pr_err("Failed to find perf count for CPU %d thread %d on event %s.\n", + st->cpu, st->thread, evsel__name(counter)); + return -EINVAL; + } + *ptr = count; counter->supported = true; return 0; } diff --git a/tools/testing/selftests/kvm/x86_64/pmu_event_filter_test.c b/tools/testing/selftests/kvm/x86_64/pmu_event_filter_test.c index 0d06ffa95d9d..93d77574b255 100644 --- a/tools/testing/selftests/kvm/x86_64/pmu_event_filter_test.c +++ b/tools/testing/selftests/kvm/x86_64/pmu_event_filter_test.c @@ -208,7 +208,7 @@ static bool sanity_check_pmu(struct kvm_vm *vm) return success; } -static struct kvm_pmu_event_filter *make_pmu_event_filter(uint32_t nevents) +static struct kvm_pmu_event_filter *alloc_pmu_event_filter(uint32_t nevents) { struct kvm_pmu_event_filter *f; int size = sizeof(*f) + nevents * sizeof(f->events[0]); @@ -220,19 +220,29 @@ static struct kvm_pmu_event_filter *make_pmu_event_filter(uint32_t nevents) return f; } -static struct kvm_pmu_event_filter *event_filter(uint32_t action) + +static struct kvm_pmu_event_filter * +create_pmu_event_filter(const uint64_t event_list[], + int nevents, uint32_t action) { struct kvm_pmu_event_filter *f; int i; - f = make_pmu_event_filter(ARRAY_SIZE(event_list)); + f = alloc_pmu_event_filter(nevents); f->action = action; - for (i = 0; i < ARRAY_SIZE(event_list); i++) + for (i = 0; i < nevents; i++) f->events[i] = event_list[i]; return f; } +static struct kvm_pmu_event_filter *event_filter(uint32_t action) +{ + return create_pmu_event_filter(event_list, + ARRAY_SIZE(event_list), + action); +} + /* * Remove the first occurrence of 'event' (if any) from the filter's * event list. @@ -271,6 +281,22 @@ static uint64_t test_with_filter(struct kvm_vm *vm, return run_vm_to_sync(vm); } +static void test_amd_deny_list(struct kvm_vm *vm) +{ + uint64_t event = EVENT(0x1C2, 0); + struct kvm_pmu_event_filter *f; + uint64_t count; + + f = create_pmu_event_filter(&event, 1, KVM_PMU_EVENT_DENY); + count = test_with_filter(vm, f); + + free(f); + if (count != NUM_BRANCHES) + pr_info("%s: Branch instructions retired = %lu (expected %u)\n", + __func__, count, NUM_BRANCHES); + TEST_ASSERT(count, "Allowed PMU event is not counting"); +} + static void test_member_deny_list(struct kvm_vm *vm) { struct kvm_pmu_event_filter *f = event_filter(KVM_PMU_EVENT_DENY); @@ -453,6 +479,9 @@ int main(int argc, char *argv[]) exit(KSFT_SKIP); } + if (use_amd_pmu()) + test_amd_deny_list(vm); + test_without_filter(vm); test_member_deny_list(vm); test_member_allow_list(vm); diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile index 0f2ebc38d893..e1f998defd10 100644 --- a/tools/testing/selftests/net/Makefile +++ b/tools/testing/selftests/net/Makefile @@ -25,6 +25,7 @@ TEST_PROGS += bareudp.sh TEST_PROGS += amt.sh TEST_PROGS += unicast_extensions.sh TEST_PROGS += udpgro_fwd.sh +TEST_PROGS += udpgro_frglist.sh TEST_PROGS += veth.sh TEST_PROGS += ioam6.sh TEST_PROGS += gro.sh @@ -61,6 +62,8 @@ TEST_FILES := settings KSFT_KHDR_INSTALL := 1 include ../lib.mk +include bpf/Makefile + $(OUTPUT)/reuseport_bpf_numa: LDLIBS += -lnuma $(OUTPUT)/tcp_mmap: LDLIBS += -lpthread $(OUTPUT)/tcp_inq: LDLIBS += -lpthread diff --git a/tools/testing/selftests/net/bpf/Makefile b/tools/testing/selftests/net/bpf/Makefile new file mode 100644 index 000000000000..f91bf14bbee7 --- /dev/null +++ b/tools/testing/selftests/net/bpf/Makefile @@ -0,0 +1,14 @@ +# SPDX-License-Identifier: GPL-2.0 + +CLANG ?= clang +CCINCLUDE += -I../../bpf +CCINCLUDE += -I../../../../../usr/include/ + +TEST_CUSTOM_PROGS = $(OUTPUT)/bpf/nat6to4.o +all: $(TEST_CUSTOM_PROGS) + +$(OUTPUT)/%.o: %.c + $(CLANG) -O2 -target bpf -c $< $(CCINCLUDE) -o $@ + +clean: + rm -f $(TEST_CUSTOM_PROGS) diff --git a/tools/testing/selftests/net/bpf/nat6to4.c b/tools/testing/selftests/net/bpf/nat6to4.c new file mode 100644 index 000000000000..ac54c36b25fc --- /dev/null +++ b/tools/testing/selftests/net/bpf/nat6to4.c @@ -0,0 +1,285 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * This code is taken from the Android Open Source Project and the author + * (Maciej Żenczykowski) has gave permission to relicense it under the + * GPLv2. Therefore 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 + + * The original headers, including the original license headers, are + * included below for completeness. + * + * Copyright (C) 2019 The Android Open Source Project + * + * Licensed under the Apache License, Version 2.0 (the "License"); + * you may not use this file except in compliance with the License. + * You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ +#include <linux/bpf.h> +#include <linux/if.h> +#include <linux/if_ether.h> +#include <linux/if_packet.h> +#include <linux/in.h> +#include <linux/in6.h> +#include <linux/ip.h> +#include <linux/ipv6.h> +#include <linux/pkt_cls.h> +#include <linux/swab.h> +#include <stdbool.h> +#include <stdint.h> + + +#include <linux/udp.h> + +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_endian.h> + +#define IP_DF 0x4000 // Flag: "Don't Fragment" + +SEC("schedcls/ingress6/nat_6") +int sched_cls_ingress6_nat_6_prog(struct __sk_buff *skb) +{ + const int l2_header_size = sizeof(struct ethhdr); + void *data = (void *)(long)skb->data; + const void *data_end = (void *)(long)skb->data_end; + const struct ethhdr * const eth = data; // used iff is_ethernet + const struct ipv6hdr * const ip6 = (void *)(eth + 1); + + // Require ethernet dst mac address to be our unicast address. + if (skb->pkt_type != PACKET_HOST) + return TC_ACT_OK; + + // Must be meta-ethernet IPv6 frame + if (skb->protocol != bpf_htons(ETH_P_IPV6)) + return TC_ACT_OK; + + // Must have (ethernet and) ipv6 header + if (data + l2_header_size + sizeof(*ip6) > data_end) + return TC_ACT_OK; + + // Ethertype - if present - must be IPv6 + if (eth->h_proto != bpf_htons(ETH_P_IPV6)) + return TC_ACT_OK; + + // IP version must be 6 + if (ip6->version != 6) + return TC_ACT_OK; + // Maximum IPv6 payload length that can be translated to IPv4 + if (bpf_ntohs(ip6->payload_len) > 0xFFFF - sizeof(struct iphdr)) + return TC_ACT_OK; + switch (ip6->nexthdr) { + case IPPROTO_TCP: // For TCP & UDP the checksum neutrality of the chosen IPv6 + case IPPROTO_UDP: // address means there is no need to update their checksums. + case IPPROTO_GRE: // We do not need to bother looking at GRE/ESP headers, + case IPPROTO_ESP: // since there is never a checksum to update. + break; + default: // do not know how to handle anything else + return TC_ACT_OK; + } + + struct ethhdr eth2; // used iff is_ethernet + + eth2 = *eth; // Copy over the ethernet header (src/dst mac) + eth2.h_proto = bpf_htons(ETH_P_IP); // But replace the ethertype + + struct iphdr ip = { + .version = 4, // u4 + .ihl = sizeof(struct iphdr) / sizeof(__u32), // u4 + .tos = (ip6->priority << 4) + (ip6->flow_lbl[0] >> 4), // u8 + .tot_len = bpf_htons(bpf_ntohs(ip6->payload_len) + sizeof(struct iphdr)), // u16 + .id = 0, // u16 + .frag_off = bpf_htons(IP_DF), // u16 + .ttl = ip6->hop_limit, // u8 + .protocol = ip6->nexthdr, // u8 + .check = 0, // u16 + .saddr = 0x0201a8c0, // u32 + .daddr = 0x0101a8c0, // u32 + }; + + // Calculate the IPv4 one's complement checksum of the IPv4 header. + __wsum sum4 = 0; + + for (int i = 0; i < sizeof(ip) / sizeof(__u16); ++i) + sum4 += ((__u16 *)&ip)[i]; + + // Note that sum4 is guaranteed to be non-zero by virtue of ip.version == 4 + sum4 = (sum4 & 0xFFFF) + (sum4 >> 16); // collapse u32 into range 1 .. 0x1FFFE + sum4 = (sum4 & 0xFFFF) + (sum4 >> 16); // collapse any potential carry into u16 + ip.check = (__u16)~sum4; // sum4 cannot be zero, so this is never 0xFFFF + + // Calculate the *negative* IPv6 16-bit one's complement checksum of the IPv6 header. + __wsum sum6 = 0; + // We'll end up with a non-zero sum due to ip6->version == 6 (which has '0' bits) + for (int i = 0; i < sizeof(*ip6) / sizeof(__u16); ++i) + sum6 += ~((__u16 *)ip6)[i]; // note the bitwise negation + + // Note that there is no L4 checksum update: we are relying on the checksum neutrality + // of the ipv6 address chosen by netd's ClatdController. + + // Packet mutations begin - point of no return, but if this first modification fails + // the packet is probably still pristine, so let clatd handle it. + if (bpf_skb_change_proto(skb, bpf_htons(ETH_P_IP), 0)) + return TC_ACT_OK; + bpf_csum_update(skb, sum6); + + data = (void *)(long)skb->data; + data_end = (void *)(long)skb->data_end; + if (data + l2_header_size + sizeof(struct iphdr) > data_end) + return TC_ACT_SHOT; + + struct ethhdr *new_eth = data; + + // Copy over the updated ethernet header + *new_eth = eth2; + + // Copy over the new ipv4 header. + *(struct iphdr *)(new_eth + 1) = ip; + return bpf_redirect(skb->ifindex, BPF_F_INGRESS); +} + +SEC("schedcls/egress4/snat4") +int sched_cls_egress4_snat4_prog(struct __sk_buff *skb) +{ + const int l2_header_size = sizeof(struct ethhdr); + void *data = (void *)(long)skb->data; + const void *data_end = (void *)(long)skb->data_end; + const struct ethhdr *const eth = data; // used iff is_ethernet + const struct iphdr *const ip4 = (void *)(eth + 1); + + // Must be meta-ethernet IPv4 frame + if (skb->protocol != bpf_htons(ETH_P_IP)) + return TC_ACT_OK; + + // Must have ipv4 header + if (data + l2_header_size + sizeof(struct ipv6hdr) > data_end) + return TC_ACT_OK; + + // Ethertype - if present - must be IPv4 + if (eth->h_proto != bpf_htons(ETH_P_IP)) + return TC_ACT_OK; + + // IP version must be 4 + if (ip4->version != 4) + return TC_ACT_OK; + + // We cannot handle IP options, just standard 20 byte == 5 dword minimal IPv4 header + if (ip4->ihl != 5) + return TC_ACT_OK; + + // Maximum IPv6 payload length that can be translated to IPv4 + if (bpf_htons(ip4->tot_len) > 0xFFFF - sizeof(struct ipv6hdr)) + return TC_ACT_OK; + + // Calculate the IPv4 one's complement checksum of the IPv4 header. + __wsum sum4 = 0; + + for (int i = 0; i < sizeof(*ip4) / sizeof(__u16); ++i) + sum4 += ((__u16 *)ip4)[i]; + + // Note that sum4 is guaranteed to be non-zero by virtue of ip4->version == 4 + sum4 = (sum4 & 0xFFFF) + (sum4 >> 16); // collapse u32 into range 1 .. 0x1FFFE + sum4 = (sum4 & 0xFFFF) + (sum4 >> 16); // collapse any potential carry into u16 + // for a correct checksum we should get *a* zero, but sum4 must be positive, ie 0xFFFF + if (sum4 != 0xFFFF) + return TC_ACT_OK; + + // Minimum IPv4 total length is the size of the header + if (bpf_ntohs(ip4->tot_len) < sizeof(*ip4)) + return TC_ACT_OK; + + // We are incapable of dealing with IPv4 fragments + if (ip4->frag_off & ~bpf_htons(IP_DF)) + return TC_ACT_OK; + + switch (ip4->protocol) { + case IPPROTO_TCP: // For TCP & UDP the checksum neutrality of the chosen IPv6 + case IPPROTO_GRE: // address means there is no need to update their checksums. + case IPPROTO_ESP: // We do not need to bother looking at GRE/ESP headers, + break; // since there is never a checksum to update. + + case IPPROTO_UDP: // See above comment, but must also have UDP header... + if (data + sizeof(*ip4) + sizeof(struct udphdr) > data_end) + return TC_ACT_OK; + const struct udphdr *uh = (const struct udphdr *)(ip4 + 1); + // If IPv4/UDP checksum is 0 then fallback to clatd so it can calculate the + // checksum. Otherwise the network or more likely the NAT64 gateway might + // drop the packet because in most cases IPv6/UDP packets with a zero checksum + // are invalid. See RFC 6935. TODO: calculate checksum via bpf_csum_diff() + if (!uh->check) + return TC_ACT_OK; + break; + + default: // do not know how to handle anything else + return TC_ACT_OK; + } + struct ethhdr eth2; // used iff is_ethernet + + eth2 = *eth; // Copy over the ethernet header (src/dst mac) + eth2.h_proto = bpf_htons(ETH_P_IPV6); // But replace the ethertype + + struct ipv6hdr ip6 = { + .version = 6, // __u8:4 + .priority = ip4->tos >> 4, // __u8:4 + .flow_lbl = {(ip4->tos & 0xF) << 4, 0, 0}, // __u8[3] + .payload_len = bpf_htons(bpf_ntohs(ip4->tot_len) - 20), // __be16 + .nexthdr = ip4->protocol, // __u8 + .hop_limit = ip4->ttl, // __u8 + }; + ip6.saddr.in6_u.u6_addr32[0] = bpf_htonl(0x20010db8); + ip6.saddr.in6_u.u6_addr32[1] = 0; + ip6.saddr.in6_u.u6_addr32[2] = 0; + ip6.saddr.in6_u.u6_addr32[3] = bpf_htonl(1); + ip6.daddr.in6_u.u6_addr32[0] = bpf_htonl(0x20010db8); + ip6.daddr.in6_u.u6_addr32[1] = 0; + ip6.daddr.in6_u.u6_addr32[2] = 0; + ip6.daddr.in6_u.u6_addr32[3] = bpf_htonl(2); + + // Calculate the IPv6 16-bit one's complement checksum of the IPv6 header. + __wsum sum6 = 0; + // We'll end up with a non-zero sum due to ip6.version == 6 + for (int i = 0; i < sizeof(ip6) / sizeof(__u16); ++i) + sum6 += ((__u16 *)&ip6)[i]; + + // Packet mutations begin - point of no return, but if this first modification fails + // the packet is probably still pristine, so let clatd handle it. + if (bpf_skb_change_proto(skb, bpf_htons(ETH_P_IPV6), 0)) + return TC_ACT_OK; + + // This takes care of updating the skb->csum field for a CHECKSUM_COMPLETE packet. + // In such a case, skb->csum is a 16-bit one's complement sum of the entire payload, + // thus we need to subtract out the ipv4 header's sum, and add in the ipv6 header's sum. + // However, we've already verified the ipv4 checksum is correct and thus 0. + // Thus we only need to add the ipv6 header's sum. + // + // bpf_csum_update() always succeeds if the skb is CHECKSUM_COMPLETE and returns an error + // (-ENOTSUPP) if it isn't. So we just ignore the return code (see above for more details). + bpf_csum_update(skb, sum6); + + // bpf_skb_change_proto() invalidates all pointers - reload them. + data = (void *)(long)skb->data; + data_end = (void *)(long)skb->data_end; + + // I cannot think of any valid way for this error condition to trigger, however I do + // believe the explicit check is required to keep the in kernel ebpf verifier happy. + if (data + l2_header_size + sizeof(ip6) > data_end) + return TC_ACT_SHOT; + + struct ethhdr *new_eth = data; + + // Copy over the updated ethernet header + *new_eth = eth2; + // Copy over the new ipv4 header. + *(struct ipv6hdr *)(new_eth + 1) = ip6; + return TC_ACT_OK; +} + +char _license[] SEC("license") = ("GPL"); diff --git a/tools/testing/selftests/net/fcnal-test.sh b/tools/testing/selftests/net/fcnal-test.sh index 47c4d4b4a44a..54701c8b0cd7 100755 --- a/tools/testing/selftests/net/fcnal-test.sh +++ b/tools/testing/selftests/net/fcnal-test.sh @@ -810,10 +810,16 @@ ipv4_ping() setup set_sysctl net.ipv4.raw_l3mdev_accept=1 2>/dev/null ipv4_ping_novrf + setup + set_sysctl net.ipv4.ping_group_range='0 2147483647' 2>/dev/null + ipv4_ping_novrf log_subsection "With VRF" setup "yes" ipv4_ping_vrf + setup "yes" + set_sysctl net.ipv4.ping_group_range='0 2147483647' 2>/dev/null + ipv4_ping_vrf } ################################################################################ @@ -2348,10 +2354,16 @@ ipv6_ping() log_subsection "No VRF" setup ipv6_ping_novrf + setup + set_sysctl net.ipv4.ping_group_range='0 2147483647' 2>/dev/null + ipv6_ping_novrf log_subsection "With VRF" setup "yes" ipv6_ping_vrf + setup "yes" + set_sysctl net.ipv4.ping_group_range='0 2147483647' 2>/dev/null + ipv6_ping_vrf } ################################################################################ diff --git a/tools/testing/selftests/net/forwarding/Makefile b/tools/testing/selftests/net/forwarding/Makefile index c87e674b61b1..e811090f7748 100644 --- a/tools/testing/selftests/net/forwarding/Makefile +++ b/tools/testing/selftests/net/forwarding/Makefile @@ -86,7 +86,7 @@ TEST_PROGS = bridge_igmp.sh \ vxlan_bridge_1d_port_8472.sh \ vxlan_bridge_1d.sh \ vxlan_bridge_1q_ipv6.sh \ - vxlan_bridge_1q_port_8472_ipv6.sh + vxlan_bridge_1q_port_8472_ipv6.sh \ vxlan_bridge_1q_port_8472.sh \ vxlan_bridge_1q.sh \ vxlan_symmetric_ipv6.sh \ diff --git a/tools/testing/selftests/net/mptcp/mptcp_join.sh b/tools/testing/selftests/net/mptcp/mptcp_join.sh index 7314257d248a..48ef112f42c2 100755 --- a/tools/testing/selftests/net/mptcp/mptcp_join.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh @@ -1444,6 +1444,33 @@ chk_prio_nr() [ "${dump_stats}" = 1 ] && dump_stats } +chk_subflow_nr() +{ + local need_title="$1" + local msg="$2" + local subflow_nr=$3 + local cnt1 + local cnt2 + + if [ -n "${need_title}" ]; then + printf "%03u %-36s %s" "${TEST_COUNT}" "${TEST_NAME}" "${msg}" + else + printf "%-${nr_blank}s %s" " " "${msg}" + fi + + cnt1=$(ss -N $ns1 -tOni | grep -c token) + cnt2=$(ss -N $ns2 -tOni | grep -c token) + if [ "$cnt1" != "$subflow_nr" -o "$cnt2" != "$subflow_nr" ]; then + echo "[fail] got $cnt1:$cnt2 subflows expected $subflow_nr" + fail_test + dump_stats=1 + else + echo "[ ok ]" + fi + + [ "${dump_stats}" = 1 ] && ( ss -N $ns1 -tOni ; ss -N $ns1 -tOni | grep token; ip -n $ns1 mptcp endpoint ) +} + chk_link_usage() { local ns=$1 @@ -2556,7 +2583,7 @@ fastclose_tests() fi } -implicit_tests() +endpoint_tests() { # userspace pm type prevents add_addr if reset "implicit EP"; then @@ -2578,6 +2605,23 @@ implicit_tests() $ns2 10.0.2.2 id 1 flags signal wait fi + + if reset "delete and re-add"; then + pm_nl_set_limits $ns1 1 1 + pm_nl_set_limits $ns2 1 1 + pm_nl_add_endpoint $ns2 10.0.2.2 id 2 dev ns2eth2 flags subflow + run_tests $ns1 $ns2 10.0.1.1 4 0 0 slow & + + wait_mpj $ns2 + pm_nl_del_endpoint $ns2 2 10.0.2.2 + sleep 0.5 + chk_subflow_nr needtitle "after delete" 1 + + pm_nl_add_endpoint $ns2 10.0.2.2 dev ns2eth2 flags subflow + wait_mpj $ns2 + chk_subflow_nr "" "after re-add" 2 + wait + fi } # [$1: error message] @@ -2624,7 +2668,7 @@ all_tests_sorted=( d@deny_join_id0_tests m@fullmesh_tests z@fastclose_tests - I@implicit_tests + I@endpoint_tests ) all_tests_args="" diff --git a/tools/testing/selftests/net/udpgro_frglist.sh b/tools/testing/selftests/net/udpgro_frglist.sh new file mode 100755 index 000000000000..807b74c8fd80 --- /dev/null +++ b/tools/testing/selftests/net/udpgro_frglist.sh @@ -0,0 +1,101 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 +# +# Run a series of udpgro benchmarks + +readonly PEER_NS="ns-peer-$(mktemp -u XXXXXX)" + +cleanup() { + local -r jobs="$(jobs -p)" + local -r ns="$(ip netns list|grep $PEER_NS)" + + [ -n "${jobs}" ] && kill -INT ${jobs} 2>/dev/null + [ -n "$ns" ] && ip netns del $ns 2>/dev/null +} +trap cleanup EXIT + +run_one() { + # use 'rx' as separator between sender args and receiver args + local -r all="$@" + local -r tx_args=${all%rx*} + local rx_args=${all#*rx} + + + + ip netns add "${PEER_NS}" + ip -netns "${PEER_NS}" link set lo up + ip link add type veth + ip link set dev veth0 up + ip addr add dev veth0 192.168.1.2/24 + ip addr add dev veth0 2001:db8::2/64 nodad + + ip link set dev veth1 netns "${PEER_NS}" + ip -netns "${PEER_NS}" addr add dev veth1 192.168.1.1/24 + ip -netns "${PEER_NS}" addr add dev veth1 2001:db8::1/64 nodad + ip -netns "${PEER_NS}" link set dev veth1 up + ip netns exec "${PEER_NS}" ethtool -K veth1 rx-gro-list on + + + ip -n "${PEER_NS}" link set veth1 xdp object ../bpf/xdp_dummy.o section xdp_dummy + tc -n "${PEER_NS}" qdisc add dev veth1 clsact + tc -n "${PEER_NS}" filter add dev veth1 ingress prio 4 protocol ipv6 bpf object-file ../bpf/nat6to4.o section schedcls/ingress6/nat_6 direct-action + tc -n "${PEER_NS}" filter add dev veth1 egress prio 4 protocol ip bpf object-file ../bpf/nat6to4.o section schedcls/egress4/snat4 direct-action + echo ${rx_args} + ip netns exec "${PEER_NS}" ./udpgso_bench_rx ${rx_args} -r & + + # Hack: let bg programs complete the startup + sleep 0.1 + ./udpgso_bench_tx ${tx_args} +} + +run_in_netns() { + local -r args=$@ + echo ${args} + ./in_netns.sh $0 __subprocess ${args} +} + +run_udp() { + local -r args=$@ + + echo "udp gso - over veth touching data" + run_in_netns ${args} -u -S 0 rx -4 -v + + echo "udp gso and gro - over veth touching data" + run_in_netns ${args} -S 0 rx -4 -G +} + +run_tcp() { + local -r args=$@ + + echo "tcp - over veth touching data" + run_in_netns ${args} -t rx -4 -t +} + +run_all() { + local -r core_args="-l 4" + local -r ipv4_args="${core_args} -4 -D 192.168.1.1" + local -r ipv6_args="${core_args} -6 -D 2001:db8::1" + + echo "ipv6" + run_tcp "${ipv6_args}" + run_udp "${ipv6_args}" +} + +if [ ! -f ../bpf/xdp_dummy.o ]; then + echo "Missing xdp_dummy helper. Build bpf selftest first" + exit -1 +fi + +if [ ! -f bpf/nat6to4.o ]; then + echo "Missing nat6to4 helper. Build bpfnat6to4.o selftest first" + exit -1 +fi + +if [[ $# -eq 0 ]]; then + run_all +elif [[ $1 == "__subprocess" ]]; then + shift + run_one $@ +else + run_in_netns $@ +fi diff --git a/tools/testing/selftests/rcutorture/bin/functions.sh b/tools/testing/selftests/rcutorture/bin/functions.sh index c35ba24f994c..66d0414d8e4b 100644 --- a/tools/testing/selftests/rcutorture/bin/functions.sh +++ b/tools/testing/selftests/rcutorture/bin/functions.sh @@ -301,7 +301,7 @@ specify_qemu_cpus () { echo $2 -smp $3 ;; qemu-system-ppc64) - nt="`lscpu | grep '^NUMA node0' | sed -e 's/^[^,]*,\([0-9]*\),.*$/\1/'`" + nt="`lscpu | sed -n 's/^Thread(s) per core:\s*//p'`" echo $2 -smp cores=`expr \( $3 + $nt - 1 \) / $nt`,threads=$nt ;; esac diff --git a/tools/testing/selftests/rcutorture/bin/kvm-find-errors.sh b/tools/testing/selftests/rcutorture/bin/kvm-find-errors.sh index 5f682fc892dd..88983cba7956 100755 --- a/tools/testing/selftests/rcutorture/bin/kvm-find-errors.sh +++ b/tools/testing/selftests/rcutorture/bin/kvm-find-errors.sh @@ -36,7 +36,7 @@ do then egrep "error:|warning:|^ld: .*undefined reference to" < $i > $i.diags files="$files $i.diags $i" - elif ! test -f ${scenariobasedir}/vmlinux + elif ! test -f ${scenariobasedir}/vmlinux && ! test -f "${rundir}/re-run" then echo No ${scenariobasedir}/vmlinux file > $i.diags files="$files $i.diags $i" diff --git a/tools/testing/selftests/rcutorture/bin/kvm-recheck.sh b/tools/testing/selftests/rcutorture/bin/kvm-recheck.sh index 0a5419982ab3..0789c5606d2a 100755 --- a/tools/testing/selftests/rcutorture/bin/kvm-recheck.sh +++ b/tools/testing/selftests/rcutorture/bin/kvm-recheck.sh @@ -33,7 +33,12 @@ do TORTURE_SUITE="`cat $i/../torture_suite`" configfile=`echo $i | sed -e 's,^.*/,,'` rm -f $i/console.log.*.diags - kvm-recheck-${TORTURE_SUITE}.sh $i + case "${TORTURE_SUITE}" in + X*) + ;; + *) + kvm-recheck-${TORTURE_SUITE}.sh $i + esac if test -f "$i/qemu-retval" && test "`cat $i/qemu-retval`" -ne 0 && test "`cat $i/qemu-retval`" -ne 137 then echo QEMU error, output: diff --git a/tools/testing/selftests/rcutorture/bin/kvm-remote.sh b/tools/testing/selftests/rcutorture/bin/kvm-remote.sh index 8c4c1e4792d0..0ff59bd8b640 100755 --- a/tools/testing/selftests/rcutorture/bin/kvm-remote.sh +++ b/tools/testing/selftests/rcutorture/bin/kvm-remote.sh @@ -138,14 +138,14 @@ chmod +x $T/bin/kvm-remote-*.sh # Check first to avoid the need for cleanup for system-name typos for i in $systems do - ncpus="`ssh $i getconf _NPROCESSORS_ONLN 2> /dev/null`" - echo $i: $ncpus CPUs " " `date` | tee -a "$oldrun/remote-log" + ncpus="`ssh -o BatchMode=yes $i getconf _NPROCESSORS_ONLN 2> /dev/null`" ret=$? if test "$ret" -ne 0 then echo System $i unreachable, giving up. | tee -a "$oldrun/remote-log" exit 4 fi + echo $i: $ncpus CPUs " " `date` | tee -a "$oldrun/remote-log" done # Download and expand the tarball on all systems. @@ -153,14 +153,14 @@ echo Build-products tarball: `du -h $T/binres.tgz` | tee -a "$oldrun/remote-log" for i in $systems do echo Downloading tarball to $i `date` | tee -a "$oldrun/remote-log" - cat $T/binres.tgz | ssh $i "cd /tmp; tar -xzf -" + cat $T/binres.tgz | ssh -o BatchMode=yes $i "cd /tmp; tar -xzf -" ret=$? tries=0 while test "$ret" -ne 0 do echo Unable to download $T/binres.tgz to system $i, waiting and then retrying. $tries prior retries. | tee -a "$oldrun/remote-log" sleep 60 - cat $T/binres.tgz | ssh $i "cd /tmp; tar -xzf -" + cat $T/binres.tgz | ssh -o BatchMode=yes $i "cd /tmp; tar -xzf -" ret=$? if test "$ret" -ne 0 then @@ -185,7 +185,7 @@ checkremotefile () { while : do - ssh $1 "test -f \"$2\"" + ssh -o BatchMode=yes $1 "test -f \"$2\"" ret=$? if test "$ret" -eq 255 then @@ -228,7 +228,7 @@ startbatches () { then continue # System still running last test, skip. fi - ssh "$i" "cd \"$resdir/$ds\"; touch remote.run; PATH=\"$T/bin:$PATH\" nohup kvm-remote-$curbatch.sh > kvm-remote-$curbatch.sh.out 2>&1 &" 1>&2 + ssh -o BatchMode=yes "$i" "cd \"$resdir/$ds\"; touch remote.run; PATH=\"$T/bin:$PATH\" nohup kvm-remote-$curbatch.sh > kvm-remote-$curbatch.sh.out 2>&1 &" 1>&2 ret=$? if test "$ret" -ne 0 then @@ -267,7 +267,7 @@ do sleep 30 done echo " ---" Collecting results from $i `date` | tee -a "$oldrun/remote-log" - ( cd "$oldrun"; ssh $i "cd $rundir; tar -czf - kvm-remote-*.sh.out */console.log */kvm-test-1-run*.sh.out */qemu[_-]pid */qemu-retval */qemu-affinity; rm -rf $T > /dev/null 2>&1" | tar -xzf - ) + ( cd "$oldrun"; ssh -o BatchMode=yes $i "cd $rundir; tar -czf - kvm-remote-*.sh.out */console.log */kvm-test-1-run*.sh.out */qemu[_-]pid */qemu-retval */qemu-affinity; rm -rf $T > /dev/null 2>&1" | tar -xzf - ) done ( kvm-end-run-stats.sh "$oldrun" "$starttime"; echo $? > $T/exitcode ) | tee -a "$oldrun/remote-log" diff --git a/tools/testing/selftests/rcutorture/bin/kvm.sh b/tools/testing/selftests/rcutorture/bin/kvm.sh index 55b2c1533282..263e16aeca0e 100755 --- a/tools/testing/selftests/rcutorture/bin/kvm.sh +++ b/tools/testing/selftests/rcutorture/bin/kvm.sh @@ -44,6 +44,7 @@ TORTURE_KCONFIG_KASAN_ARG="" TORTURE_KCONFIG_KCSAN_ARG="" TORTURE_KMAKE_ARG="" TORTURE_QEMU_MEM=512 +torture_qemu_mem_default=1 TORTURE_REMOTE= TORTURE_SHUTDOWN_GRACE=180 TORTURE_SUITE=rcu @@ -86,7 +87,7 @@ usage () { echo " --remote" echo " --results absolute-pathname" echo " --shutdown-grace seconds" - echo " --torture lock|rcu|rcuscale|refscale|scf" + echo " --torture lock|rcu|rcuscale|refscale|scf|X*" echo " --trust-make" exit 1 } @@ -180,6 +181,10 @@ do ;; --kasan) TORTURE_KCONFIG_KASAN_ARG="CONFIG_DEBUG_INFO=y CONFIG_KASAN=y"; export TORTURE_KCONFIG_KASAN_ARG + if test -n "$torture_qemu_mem_default" + then + TORTURE_QEMU_MEM=2G + fi ;; --kconfig|--kconfigs) checkarg --kconfig "(Kconfig options)" $# "$2" '^CONFIG_[A-Z0-9_]\+=\([ynm]\|[0-9]\+\)\( CONFIG_[A-Z0-9_]\+=\([ynm]\|[0-9]\+\)\)*$' '^error$' @@ -202,6 +207,7 @@ do --memory) checkarg --memory "(memory size)" $# "$2" '^[0-9]\+[MG]\?$' error TORTURE_QEMU_MEM=$2 + torture_qemu_mem_default= shift ;; --no-initrd) @@ -231,7 +237,7 @@ do shift ;; --torture) - checkarg --torture "(suite name)" "$#" "$2" '^\(lock\|rcu\|rcuscale\|refscale\|scf\)$' '^--' + checkarg --torture "(suite name)" "$#" "$2" '^\(lock\|rcu\|rcuscale\|refscale\|scf\|X.*\)$' '^--' TORTURE_SUITE=$2 TORTURE_MOD="`echo $TORTURE_SUITE | sed -e 's/^\(lock\|rcu\|scf\)$/\1torture/'`" shift diff --git a/tools/testing/selftests/rcutorture/bin/torture.sh b/tools/testing/selftests/rcutorture/bin/torture.sh index bfe09e2829c8..d477618e7261 100755 --- a/tools/testing/selftests/rcutorture/bin/torture.sh +++ b/tools/testing/selftests/rcutorture/bin/torture.sh @@ -54,6 +54,7 @@ do_kvfree=yes do_kasan=yes do_kcsan=no do_clocksourcewd=yes +do_rt=yes # doyesno - Helper function for yes/no arguments function doyesno () { @@ -82,6 +83,7 @@ usage () { echo " --do-rcuscale / --do-no-rcuscale" echo " --do-rcutorture / --do-no-rcutorture" echo " --do-refscale / --do-no-refscale" + echo " --do-rt / --do-no-rt" echo " --do-scftorture / --do-no-scftorture" echo " --duration [ <minutes> | <hours>h | <days>d ]" echo " --kcsan-kmake-arg kernel-make-arguments" @@ -118,6 +120,7 @@ do do_scftorture=yes do_rcuscale=yes do_refscale=yes + do_rt=yes do_kvfree=yes do_kasan=yes do_kcsan=yes @@ -148,6 +151,7 @@ do do_scftorture=no do_rcuscale=no do_refscale=no + do_rt=no do_kvfree=no do_kasan=no do_kcsan=no @@ -162,6 +166,9 @@ do --do-refscale|--do-no-refscale) do_refscale=`doyesno "$1" --do-refscale` ;; + --do-rt|--do-no-rt) + do_rt=`doyesno "$1" --do-rt` + ;; --do-scftorture|--do-no-scftorture) do_scftorture=`doyesno "$1" --do-scftorture` ;; @@ -322,6 +329,7 @@ then echo " --- make clean" > "$amcdir/Make.out" 2>&1 make -j$MAKE_ALLOTED_CPUS clean >> "$amcdir/Make.out" 2>&1 echo " --- make allmodconfig" >> "$amcdir/Make.out" 2>&1 + cp .config $amcdir make -j$MAKE_ALLOTED_CPUS allmodconfig >> "$amcdir/Make.out" 2>&1 echo " --- make " >> "$amcdir/Make.out" 2>&1 make -j$MAKE_ALLOTED_CPUS >> "$amcdir/Make.out" 2>&1 @@ -350,8 +358,19 @@ fi if test "$do_scftorture" = "yes" then - torture_bootargs="scftorture.nthreads=$HALF_ALLOTED_CPUS torture.disable_onoff_at_boot" - torture_set "scftorture" tools/testing/selftests/rcutorture/bin/kvm.sh --torture scf --allcpus --duration "$duration_scftorture" --configs "$configs_scftorture" --kconfig "CONFIG_NR_CPUS=$HALF_ALLOTED_CPUS" --memory 1G --trust-make + torture_bootargs="scftorture.nthreads=$HALF_ALLOTED_CPUS torture.disable_onoff_at_boot csdlock_debug=1" + torture_set "scftorture" tools/testing/selftests/rcutorture/bin/kvm.sh --torture scf --allcpus --duration "$duration_scftorture" --configs "$configs_scftorture" --kconfig "CONFIG_NR_CPUS=$HALF_ALLOTED_CPUS" --memory 2G --trust-make +fi + +if test "$do_rt" = "yes" +then + # With all post-boot grace periods forced to normal. + torture_bootargs="rcupdate.rcu_cpu_stall_suppress_at_boot=1 torture.disable_onoff_at_boot rcupdate.rcu_task_stall_timeout=30000 rcupdate.rcu_normal=1" + torture_set "rcurttorture" tools/testing/selftests/rcutorture/bin/kvm.sh --allcpus --duration "$duration_rcutorture" --configs "TREE03" --trust-make + + # With all post-boot grace periods forced to expedited. + torture_bootargs="rcupdate.rcu_cpu_stall_suppress_at_boot=1 torture.disable_onoff_at_boot rcupdate.rcu_task_stall_timeout=30000 rcupdate.rcu_expedited=1" + torture_set "rcurttorture-exp" tools/testing/selftests/rcutorture/bin/kvm.sh --allcpus --duration "$duration_rcutorture" --configs "TREE03" --trust-make fi if test "$do_refscale" = yes @@ -363,7 +382,7 @@ fi for prim in $primlist do torture_bootargs="refscale.scale_type="$prim" refscale.nreaders=$HALF_ALLOTED_CPUS refscale.loops=10000 refscale.holdoff=20 torture.disable_onoff_at_boot" - torture_set "refscale-$prim" tools/testing/selftests/rcutorture/bin/kvm.sh --torture refscale --allcpus --duration 5 --kconfig "CONFIG_NR_CPUS=$HALF_ALLOTED_CPUS" --bootargs "verbose_batched=$VERBOSE_BATCH_CPUS torture.verbose_sleep_frequency=8 torture.verbose_sleep_duration=$VERBOSE_BATCH_CPUS" --trust-make + torture_set "refscale-$prim" tools/testing/selftests/rcutorture/bin/kvm.sh --torture refscale --allcpus --duration 5 --kconfig "CONFIG_TASKS_TRACE_RCU=y CONFIG_NR_CPUS=$HALF_ALLOTED_CPUS" --bootargs "verbose_batched=$VERBOSE_BATCH_CPUS torture.verbose_sleep_frequency=8 torture.verbose_sleep_duration=$VERBOSE_BATCH_CPUS" --trust-make done if test "$do_rcuscale" = yes @@ -375,13 +394,13 @@ fi for prim in $primlist do torture_bootargs="rcuscale.scale_type="$prim" rcuscale.nwriters=$HALF_ALLOTED_CPUS rcuscale.holdoff=20 torture.disable_onoff_at_boot" - torture_set "rcuscale-$prim" tools/testing/selftests/rcutorture/bin/kvm.sh --torture rcuscale --allcpus --duration 5 --kconfig "CONFIG_NR_CPUS=$HALF_ALLOTED_CPUS" --trust-make + torture_set "rcuscale-$prim" tools/testing/selftests/rcutorture/bin/kvm.sh --torture rcuscale --allcpus --duration 5 --kconfig "CONFIG_TASKS_TRACE_RCU=y CONFIG_NR_CPUS=$HALF_ALLOTED_CPUS" --trust-make done if test "$do_kvfree" = "yes" then torture_bootargs="rcuscale.kfree_rcu_test=1 rcuscale.kfree_nthreads=16 rcuscale.holdoff=20 rcuscale.kfree_loops=10000 torture.disable_onoff_at_boot" - torture_set "rcuscale-kvfree" tools/testing/selftests/rcutorture/bin/kvm.sh --torture rcuscale --allcpus --duration 10 --kconfig "CONFIG_NR_CPUS=$HALF_ALLOTED_CPUS" --memory 1G --trust-make + torture_set "rcuscale-kvfree" tools/testing/selftests/rcutorture/bin/kvm.sh --torture rcuscale --allcpus --duration 10 --kconfig "CONFIG_NR_CPUS=$HALF_ALLOTED_CPUS" --memory 2G --trust-make fi if test "$do_clocksourcewd" = "yes" diff --git a/tools/testing/selftests/rcutorture/configs/rcu/RUDE01 b/tools/testing/selftests/rcutorture/configs/rcu/RUDE01 index 7093422050f6..6fd6acb94518 100644 --- a/tools/testing/selftests/rcutorture/configs/rcu/RUDE01 +++ b/tools/testing/selftests/rcutorture/configs/rcu/RUDE01 @@ -8,3 +8,5 @@ CONFIG_DEBUG_LOCK_ALLOC=y CONFIG_PROVE_LOCKING=y #CHECK#CONFIG_PROVE_RCU=y CONFIG_RCU_EXPERT=y +CONFIG_FORCE_TASKS_RUDE_RCU=y +#CHECK#CONFIG_TASKS_RUDE_RCU=y diff --git a/tools/testing/selftests/rcutorture/configs/rcu/SRCU-N b/tools/testing/selftests/rcutorture/configs/rcu/SRCU-N index 2da8b49589a0..07f5e0a70ae7 100644 --- a/tools/testing/selftests/rcutorture/configs/rcu/SRCU-N +++ b/tools/testing/selftests/rcutorture/configs/rcu/SRCU-N @@ -6,3 +6,5 @@ CONFIG_PREEMPT_NONE=y CONFIG_PREEMPT_VOLUNTARY=n CONFIG_PREEMPT=n #CHECK#CONFIG_RCU_EXPERT=n +CONFIG_KPROBES=n +CONFIG_FTRACE=n diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TASKS01 b/tools/testing/selftests/rcutorture/configs/rcu/TASKS01 index 3ca112444ce7..d84801b9a7ae 100644 --- a/tools/testing/selftests/rcutorture/configs/rcu/TASKS01 +++ b/tools/testing/selftests/rcutorture/configs/rcu/TASKS01 @@ -7,4 +7,5 @@ CONFIG_PREEMPT=y CONFIG_DEBUG_LOCK_ALLOC=y CONFIG_PROVE_LOCKING=y #CHECK#CONFIG_PROVE_RCU=y +CONFIG_TASKS_RCU=y CONFIG_RCU_EXPERT=y diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TASKS02 b/tools/testing/selftests/rcutorture/configs/rcu/TASKS02 index ad2be91e5ee7..2f9fcffff5ae 100644 --- a/tools/testing/selftests/rcutorture/configs/rcu/TASKS02 +++ b/tools/testing/selftests/rcutorture/configs/rcu/TASKS02 @@ -2,3 +2,7 @@ CONFIG_SMP=n CONFIG_PREEMPT_NONE=y CONFIG_PREEMPT_VOLUNTARY=n CONFIG_PREEMPT=n +CONFIG_PREEMPT_DYNAMIC=n +#CHECK#CONFIG_TASKS_RCU=y +CONFIG_FORCE_TASKS_RCU=y +CONFIG_RCU_EXPERT=y diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TASKS02.boot b/tools/testing/selftests/rcutorture/configs/rcu/TASKS02.boot index cd2a188eeb6d..b9b6d67cbc5f 100644 --- a/tools/testing/selftests/rcutorture/configs/rcu/TASKS02.boot +++ b/tools/testing/selftests/rcutorture/configs/rcu/TASKS02.boot @@ -1 +1,2 @@ rcutorture.torture_type=tasks +rcutorture.stat_interval=60 diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TASKS03 b/tools/testing/selftests/rcutorture/configs/rcu/TASKS03 index dc02083803ce..dea26c568678 100644 --- a/tools/testing/selftests/rcutorture/configs/rcu/TASKS03 +++ b/tools/testing/selftests/rcutorture/configs/rcu/TASKS03 @@ -7,3 +7,5 @@ CONFIG_HZ_PERIODIC=n CONFIG_NO_HZ_IDLE=n CONFIG_NO_HZ_FULL=y #CHECK#CONFIG_RCU_EXPERT=n +CONFIG_TASKS_RCU=y +CONFIG_RCU_EXPERT=y diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TRACE01 b/tools/testing/selftests/rcutorture/configs/rcu/TRACE01 index e4d74e5fc1d0..85b407467454 100644 --- a/tools/testing/selftests/rcutorture/configs/rcu/TRACE01 +++ b/tools/testing/selftests/rcutorture/configs/rcu/TRACE01 @@ -4,8 +4,11 @@ CONFIG_HOTPLUG_CPU=y CONFIG_PREEMPT_NONE=y CONFIG_PREEMPT_VOLUNTARY=n CONFIG_PREEMPT=n +CONFIG_PREEMPT_DYNAMIC=n CONFIG_DEBUG_LOCK_ALLOC=n CONFIG_PROVE_LOCKING=n #CHECK#CONFIG_PROVE_RCU=n +CONFIG_FORCE_TASKS_TRACE_RCU=y +#CHECK#CONFIG_TASKS_TRACE_RCU=y CONFIG_TASKS_TRACE_RCU_READ_MB=y CONFIG_RCU_EXPERT=y diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TRACE02 b/tools/testing/selftests/rcutorture/configs/rcu/TRACE02 index 77541eeb4e9f..093ea6e8e65c 100644 --- a/tools/testing/selftests/rcutorture/configs/rcu/TRACE02 +++ b/tools/testing/selftests/rcutorture/configs/rcu/TRACE02 @@ -7,5 +7,7 @@ CONFIG_PREEMPT=y CONFIG_DEBUG_LOCK_ALLOC=y CONFIG_PROVE_LOCKING=y #CHECK#CONFIG_PROVE_RCU=y +CONFIG_FORCE_TASKS_TRACE_RCU=y +#CHECK#CONFIG_TASKS_TRACE_RCU=y CONFIG_TASKS_TRACE_RCU_READ_MB=n CONFIG_RCU_EXPERT=y diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE04 b/tools/testing/selftests/rcutorture/configs/rcu/TREE04 index 22ad0261728d..ae395981b5e5 100644 --- a/tools/testing/selftests/rcutorture/configs/rcu/TREE04 +++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE04 @@ -1,8 +1,9 @@ CONFIG_SMP=y CONFIG_NR_CPUS=8 -CONFIG_PREEMPT_NONE=y -CONFIG_PREEMPT_VOLUNTARY=n +CONFIG_PREEMPT_NONE=n +CONFIG_PREEMPT_VOLUNTARY=y CONFIG_PREEMPT=n +CONFIG_PREEMPT_DYNAMIC=n #CHECK#CONFIG_TREE_RCU=y CONFIG_HZ_PERIODIC=n CONFIG_NO_HZ_IDLE=n diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE07 b/tools/testing/selftests/rcutorture/configs/rcu/TREE07 index 2789b47e4ecd..d30922d8c883 100644 --- a/tools/testing/selftests/rcutorture/configs/rcu/TREE07 +++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE07 @@ -3,6 +3,7 @@ CONFIG_NR_CPUS=16 CONFIG_PREEMPT_NONE=y CONFIG_PREEMPT_VOLUNTARY=n CONFIG_PREEMPT=n +CONFIG_PREEMPT_DYNAMIC=n #CHECK#CONFIG_TREE_RCU=y CONFIG_HZ_PERIODIC=n CONFIG_NO_HZ_IDLE=n diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE09 b/tools/testing/selftests/rcutorture/configs/rcu/TREE09 index 8523a7515cbf..fc45645bb5f4 100644 --- a/tools/testing/selftests/rcutorture/configs/rcu/TREE09 +++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE09 @@ -13,3 +13,5 @@ CONFIG_DEBUG_LOCK_ALLOC=n CONFIG_RCU_BOOST=n CONFIG_DEBUG_OBJECTS_RCU_HEAD=n #CHECK#CONFIG_RCU_EXPERT=n +CONFIG_KPROBES=n +CONFIG_FTRACE=n diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE10 b/tools/testing/selftests/rcutorture/configs/rcu/TREE10 index 4a00539bfdd7..a323d8948b7c 100644 --- a/tools/testing/selftests/rcutorture/configs/rcu/TREE10 +++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE10 @@ -3,6 +3,7 @@ CONFIG_NR_CPUS=56 CONFIG_PREEMPT_NONE=y CONFIG_PREEMPT_VOLUNTARY=n CONFIG_PREEMPT=n +CONFIG_PREEMPT_DYNAMIC=n #CHECK#CONFIG_TREE_RCU=y CONFIG_HZ_PERIODIC=n CONFIG_NO_HZ_IDLE=y diff --git a/tools/testing/selftests/rcutorture/configs/rcu/ver_functions.sh b/tools/testing/selftests/rcutorture/configs/rcu/ver_functions.sh index effa415f9b92..e2bc99c785e7 100644 --- a/tools/testing/selftests/rcutorture/configs/rcu/ver_functions.sh +++ b/tools/testing/selftests/rcutorture/configs/rcu/ver_functions.sh @@ -9,7 +9,7 @@ # rcutorture_param_n_barrier_cbs bootparam-string # -# Adds n_barrier_cbs rcutorture module parameter to kernels having it. +# Adds n_barrier_cbs rcutorture module parameter if not already specified. rcutorture_param_n_barrier_cbs () { if echo $1 | grep -q "rcutorture\.n_barrier_cbs" then @@ -30,13 +30,25 @@ rcutorture_param_onoff () { fi } +# rcutorture_param_stat_interval bootparam-string +# +# Adds stat_interval rcutorture module parameter if not already specified. +rcutorture_param_stat_interval () { + if echo $1 | grep -q "rcutorture\.stat_interval" + then + : + else + echo rcutorture.stat_interval=15 + fi +} + # per_version_boot_params bootparam-string config-file seconds # # Adds per-version torture-module parameters to kernels supporting them. per_version_boot_params () { echo $1 `rcutorture_param_onoff "$1" "$2"` \ `rcutorture_param_n_barrier_cbs "$1"` \ - rcutorture.stat_interval=15 \ + `rcutorture_param_stat_interval "$1"` \ rcutorture.shutdown_secs=$3 \ rcutorture.test_no_idle_hz=1 \ rcutorture.verbose=1 diff --git a/tools/testing/selftests/rcutorture/configs/rcuscale/CFcommon b/tools/testing/selftests/rcutorture/configs/rcuscale/CFcommon index 90942bb5bebc..6a00157bee5b 100644 --- a/tools/testing/selftests/rcutorture/configs/rcuscale/CFcommon +++ b/tools/testing/selftests/rcutorture/configs/rcuscale/CFcommon @@ -1,5 +1,6 @@ CONFIG_RCU_SCALE_TEST=y CONFIG_PRINTK_TIME=y -CONFIG_TASKS_RCU_GENERIC=y -CONFIG_TASKS_RCU=y -CONFIG_TASKS_TRACE_RCU=y +CONFIG_FORCE_TASKS_RCU=y +#CHECK#CONFIG_TASKS_RCU=y +CONFIG_FORCE_TASKS_TRACE_RCU=y +#CHECK#CONFIG_TASKS_TRACE_RCU=y diff --git a/tools/testing/selftests/rcutorture/configs/rcuscale/TREE b/tools/testing/selftests/rcutorture/configs/rcuscale/TREE index f110d9ffbe4c..b10706fd03a4 100644 --- a/tools/testing/selftests/rcutorture/configs/rcuscale/TREE +++ b/tools/testing/selftests/rcutorture/configs/rcuscale/TREE @@ -16,3 +16,5 @@ CONFIG_RCU_BOOST=n CONFIG_DEBUG_OBJECTS_RCU_HEAD=n CONFIG_RCU_EXPERT=y CONFIG_RCU_TRACE=y +CONFIG_KPROBES=n +CONFIG_FTRACE=n diff --git a/tools/testing/selftests/rcutorture/configs/refscale/CFcommon b/tools/testing/selftests/rcutorture/configs/refscale/CFcommon index a98b58b54bb1..fbea3b13baba 100644 --- a/tools/testing/selftests/rcutorture/configs/refscale/CFcommon +++ b/tools/testing/selftests/rcutorture/configs/refscale/CFcommon @@ -1,2 +1,6 @@ CONFIG_RCU_REF_SCALE_TEST=y CONFIG_PRINTK_TIME=y +CONFIG_FORCE_TASKS_RCU=y +#CHECK#CONFIG_TASKS_RCU=y +CONFIG_FORCE_TASKS_TRACE_RCU=y +#CHECK#CONFIG_TASKS_TRACE_RCU=y diff --git a/tools/testing/selftests/rcutorture/configs/refscale/NOPREEMPT b/tools/testing/selftests/rcutorture/configs/refscale/NOPREEMPT index 7f06838a91e6..ef2b501a6971 100644 --- a/tools/testing/selftests/rcutorture/configs/refscale/NOPREEMPT +++ b/tools/testing/selftests/rcutorture/configs/refscale/NOPREEMPT @@ -15,3 +15,5 @@ CONFIG_PROVE_LOCKING=n CONFIG_RCU_BOOST=n CONFIG_DEBUG_OBJECTS_RCU_HEAD=n CONFIG_RCU_EXPERT=y +CONFIG_KPROBES=n +CONFIG_FTRACE=n diff --git a/tools/testing/selftests/rcutorture/configs/scf/NOPREEMPT b/tools/testing/selftests/rcutorture/configs/scf/NOPREEMPT index b8429d6c6ebc..3a59346b3de7 100644 --- a/tools/testing/selftests/rcutorture/configs/scf/NOPREEMPT +++ b/tools/testing/selftests/rcutorture/configs/scf/NOPREEMPT @@ -7,3 +7,5 @@ CONFIG_NO_HZ_IDLE=n CONFIG_NO_HZ_FULL=y CONFIG_DEBUG_LOCK_ALLOC=n CONFIG_PROVE_LOCKING=n +CONFIG_KPROBES=n +CONFIG_FTRACE=n diff --git a/tools/testing/selftests/rcutorture/configs/scf/PREEMPT b/tools/testing/selftests/rcutorture/configs/scf/PREEMPT index ae4992b141b0..cb37e08037d6 100644 --- a/tools/testing/selftests/rcutorture/configs/scf/PREEMPT +++ b/tools/testing/selftests/rcutorture/configs/scf/PREEMPT @@ -7,3 +7,4 @@ CONFIG_NO_HZ_IDLE=y CONFIG_NO_HZ_FULL=n CONFIG_DEBUG_LOCK_ALLOC=y CONFIG_PROVE_LOCKING=y +CONFIG_RCU_EXPERT=y diff --git a/tools/testing/selftests/rcutorture/configs/scf/ver_functions.sh b/tools/testing/selftests/rcutorture/configs/scf/ver_functions.sh index d3d9e35d3d55..2d949e58f5a5 100644 --- a/tools/testing/selftests/rcutorture/configs/scf/ver_functions.sh +++ b/tools/testing/selftests/rcutorture/configs/scf/ver_functions.sh @@ -25,6 +25,5 @@ per_version_boot_params () { echo $1 `scftorture_param_onoff "$1" "$2"` \ scftorture.stat_interval=15 \ scftorture.shutdown_secs=$3 \ - scftorture.verbose=1 \ - scf + scftorture.verbose=1 } diff --git a/tools/testing/selftests/vm/Makefile b/tools/testing/selftests/vm/Makefile index 04a49e876a46..5b1ecd00695b 100644 --- a/tools/testing/selftests/vm/Makefile +++ b/tools/testing/selftests/vm/Makefile @@ -57,9 +57,9 @@ CAN_BUILD_I386 := $(shell ./../x86/check_cc.sh "$(CC)" ../x86/trivial_32bit_prog CAN_BUILD_X86_64 := $(shell ./../x86/check_cc.sh "$(CC)" ../x86/trivial_64bit_program.c) CAN_BUILD_WITH_NOPIE := $(shell ./../x86/check_cc.sh "$(CC)" ../x86/trivial_program.c -no-pie) -TARGETS := protection_keys -BINARIES_32 := $(TARGETS:%=%_32) -BINARIES_64 := $(TARGETS:%=%_64) +VMTARGETS := protection_keys +BINARIES_32 := $(VMTARGETS:%=%_32) +BINARIES_64 := $(VMTARGETS:%=%_64) ifeq ($(CAN_BUILD_WITH_NOPIE),1) CFLAGS += -no-pie @@ -112,7 +112,7 @@ $(BINARIES_32): CFLAGS += -m32 -mxsave $(BINARIES_32): LDLIBS += -lrt -ldl -lm $(BINARIES_32): $(OUTPUT)/%_32: %.c $(CC) $(CFLAGS) $(EXTRA_CFLAGS) $(notdir $^) $(LDLIBS) -o $@ -$(foreach t,$(TARGETS),$(eval $(call gen-target-rule-32,$(t)))) +$(foreach t,$(VMTARGETS),$(eval $(call gen-target-rule-32,$(t)))) endif ifeq ($(CAN_BUILD_X86_64),1) @@ -120,7 +120,7 @@ $(BINARIES_64): CFLAGS += -m64 -mxsave $(BINARIES_64): LDLIBS += -lrt -ldl $(BINARIES_64): $(OUTPUT)/%_64: %.c $(CC) $(CFLAGS) $(EXTRA_CFLAGS) $(notdir $^) $(LDLIBS) -o $@ -$(foreach t,$(TARGETS),$(eval $(call gen-target-rule-64,$(t)))) +$(foreach t,$(VMTARGETS),$(eval $(call gen-target-rule-64,$(t)))) endif # x86_64 users should be encouraged to install 32-bit libraries diff --git a/virt/kvm/eventfd.c b/virt/kvm/eventfd.c index 59b1dd4a549e..2a3ed401ce46 100644 --- a/virt/kvm/eventfd.c +++ b/virt/kvm/eventfd.c @@ -77,7 +77,8 @@ irqfd_resampler_ack(struct kvm_irq_ack_notifier *kian) idx = srcu_read_lock(&kvm->irq_srcu); - list_for_each_entry_rcu(irqfd, &resampler->list, resampler_link) + list_for_each_entry_srcu(irqfd, &resampler->list, resampler_link, + srcu_read_lock_held(&kvm->irq_srcu)) eventfd_signal(irqfd->resamplefd, 1); srcu_read_unlock(&kvm->irq_srcu, idx); diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 6d971fb1b08d..5ab12214e18d 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -1560,7 +1560,7 @@ static int kvm_prepare_memory_region(struct kvm *kvm, r = kvm_arch_prepare_memory_region(kvm, old, new, change); /* Free the bitmap on failure if it was allocated above. */ - if (r && new && new->dirty_bitmap && old && !old->dirty_bitmap) + if (r && new && new->dirty_bitmap && (!old || !old->dirty_bitmap)) kvm_destroy_dirty_bitmap(new); return r; |