summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
-rw-r--r--Documentation/locking/locktypes.rst215
-rw-r--r--drivers/block/zram/zcomp.c44
-rw-r--r--drivers/block/zram/zcomp.h5
-rw-r--r--drivers/connector/cn_proc.c21
-rw-r--r--fs/squashfs/decompressor_multi_percpu.c21
-rw-r--r--include/linux/idr.h2
-rw-r--r--include/linux/local_lock.h54
-rw-r--r--include/linux/local_lock_internal.h90
-rw-r--r--include/linux/radix-tree.h11
-rw-r--r--include/linux/swap.h1
-rw-r--r--kernel/locking/lockdep.c2
-rw-r--r--kernel/locking/rtmutex.c2
-rw-r--r--lib/radix-tree.c20
-rw-r--r--mm/compaction.c6
-rw-r--r--mm/swap.c118
15 files changed, 502 insertions, 110 deletions
diff --git a/Documentation/locking/locktypes.rst b/Documentation/locking/locktypes.rst
index 09f45ce38d26..1b577a8bf982 100644
--- a/Documentation/locking/locktypes.rst
+++ b/Documentation/locking/locktypes.rst
@@ -13,6 +13,7 @@ The kernel provides a variety of locking primitives which can be divided
into two categories:
- Sleeping locks
+ - CPU local locks
- Spinning locks
This document conceptually describes these lock types and provides rules
@@ -44,9 +45,23 @@ Sleeping lock types:
On PREEMPT_RT kernels, these lock types are converted to sleeping locks:
+ - local_lock
- spinlock_t
- rwlock_t
+
+CPU local locks
+---------------
+
+ - local_lock
+
+On non-PREEMPT_RT kernels, local_lock functions are wrappers around
+preemption and interrupt disabling primitives. Contrary to other locking
+mechanisms, disabling preemption or interrupts are pure CPU local
+concurrency control mechanisms and not suited for inter-CPU concurrency
+control.
+
+
Spinning locks
--------------
@@ -67,6 +82,7 @@ can have suffixes which apply further protections:
_irqsave/restore() Save and disable / restore interrupt disabled state
=================== ====================================================
+
Owner semantics
===============
@@ -139,6 +155,56 @@ implementation, thus changing the fairness:
writer from starving readers.
+local_lock
+==========
+
+local_lock provides a named scope to critical sections which are protected
+by disabling preemption or interrupts.
+
+On non-PREEMPT_RT kernels local_lock operations map to the preemption and
+interrupt disabling and enabling primitives:
+
+ =========================== ======================
+ local_lock(&llock) preempt_disable()
+ local_unlock(&llock) preempt_enable()
+ local_lock_irq(&llock) local_irq_disable()
+ local_unlock_irq(&llock) local_irq_enable()
+ local_lock_save(&llock) local_irq_save()
+ local_lock_restore(&llock) local_irq_save()
+ =========================== ======================
+
+The named scope of local_lock has two advantages over the regular
+primitives:
+
+ - The lock name allows static analysis and is also a clear documentation
+ of the protection scope while the regular primitives are scopeless and
+ opaque.
+
+ - If lockdep is enabled the local_lock gains a lockmap which allows to
+ validate the correctness of the protection. This can detect cases where
+ e.g. a function using preempt_disable() as protection mechanism is
+ invoked from interrupt or soft-interrupt context. Aside of that
+ lockdep_assert_held(&llock) works as with any other locking primitive.
+
+local_lock and PREEMPT_RT
+-------------------------
+
+PREEMPT_RT kernels map local_lock to a per-CPU spinlock_t, thus changing
+semantics:
+
+ - All spinlock_t changes also apply to local_lock.
+
+local_lock usage
+----------------
+
+local_lock should be used in situations where disabling preemption or
+interrupts is the appropriate form of concurrency control to protect
+per-CPU data structures on a non PREEMPT_RT kernel.
+
+local_lock is not suitable to protect against preemption or interrupts on a
+PREEMPT_RT kernel due to the PREEMPT_RT specific spinlock_t semantics.
+
+
raw_spinlock_t and spinlock_t
=============================
@@ -258,10 +324,82 @@ implementation, thus changing semantics:
PREEMPT_RT caveats
==================
+local_lock on RT
+----------------
+
+The mapping of local_lock to spinlock_t on PREEMPT_RT kernels has a few
+implications. For example, on a non-PREEMPT_RT kernel the following code
+sequence works as expected::
+
+ local_lock_irq(&local_lock);
+ raw_spin_lock(&lock);
+
+and is fully equivalent to::
+
+ raw_spin_lock_irq(&lock);
+
+On a PREEMPT_RT kernel this code sequence breaks because local_lock_irq()
+is mapped to a per-CPU spinlock_t which neither disables interrupts nor
+preemption. The following code sequence works perfectly correct on both
+PREEMPT_RT and non-PREEMPT_RT kernels::
+
+ local_lock_irq(&local_lock);
+ spin_lock(&lock);
+
+Another caveat with local locks is that each local_lock has a specific
+protection scope. So the following substitution is wrong::
+
+ func1()
+ {
+ local_irq_save(flags); -> local_lock_irqsave(&local_lock_1, flags);
+ func3();
+ local_irq_restore(flags); -> local_lock_irqrestore(&local_lock_1, flags);
+ }
+
+ func2()
+ {
+ local_irq_save(flags); -> local_lock_irqsave(&local_lock_2, flags);
+ func3();
+ local_irq_restore(flags); -> local_lock_irqrestore(&local_lock_2, flags);
+ }
+
+ func3()
+ {
+ lockdep_assert_irqs_disabled();
+ access_protected_data();
+ }
+
+On a non-PREEMPT_RT kernel this works correctly, but on a PREEMPT_RT kernel
+local_lock_1 and local_lock_2 are distinct and cannot serialize the callers
+of func3(). Also the lockdep assert will trigger on a PREEMPT_RT kernel
+because local_lock_irqsave() does not disable interrupts due to the
+PREEMPT_RT-specific semantics of spinlock_t. The correct substitution is::
+
+ func1()
+ {
+ local_irq_save(flags); -> local_lock_irqsave(&local_lock, flags);
+ func3();
+ local_irq_restore(flags); -> local_lock_irqrestore(&local_lock, flags);
+ }
+
+ func2()
+ {
+ local_irq_save(flags); -> local_lock_irqsave(&local_lock, flags);
+ func3();
+ local_irq_restore(flags); -> local_lock_irqrestore(&local_lock, flags);
+ }
+
+ func3()
+ {
+ lockdep_assert_held(&local_lock);
+ access_protected_data();
+ }
+
+
spinlock_t and rwlock_t
-----------------------
-These changes in spinlock_t and rwlock_t semantics on PREEMPT_RT kernels
+The changes in spinlock_t and rwlock_t semantics on PREEMPT_RT kernels
have a few implications. For example, on a non-PREEMPT_RT kernel the
following code sequence works as expected::
@@ -282,9 +420,61 @@ local_lock mechanism. Acquiring the local_lock pins the task to a CPU,
allowing things like per-CPU interrupt disabled locks to be acquired.
However, this approach should be used only where absolutely necessary.
+A typical scenario is protection of per-CPU variables in thread context::
-raw_spinlock_t
---------------
+ struct foo *p = get_cpu_ptr(&var1);
+
+ spin_lock(&p->lock);
+ p->count += this_cpu_read(var2);
+
+This is correct code on a non-PREEMPT_RT kernel, but on a PREEMPT_RT kernel
+this breaks. The PREEMPT_RT-specific change of spinlock_t semantics does
+not allow to acquire p->lock because get_cpu_ptr() implicitly disables
+preemption. The following substitution works on both kernels::
+
+ struct foo *p;
+
+ migrate_disable();
+ p = this_cpu_ptr(&var1);
+ spin_lock(&p->lock);
+ p->count += this_cpu_read(var2);
+
+On a non-PREEMPT_RT kernel migrate_disable() maps to preempt_disable()
+which makes the above code fully equivalent. On a PREEMPT_RT kernel
+migrate_disable() ensures that the task is pinned on the current CPU which
+in turn guarantees that the per-CPU access to var1 and var2 are staying on
+the same CPU.
+
+The migrate_disable() substitution is not valid for the following
+scenario::
+
+ func()
+ {
+ struct foo *p;
+
+ migrate_disable();
+ p = this_cpu_ptr(&var1);
+ p->val = func2();
+
+While correct on a non-PREEMPT_RT kernel, this breaks on PREEMPT_RT because
+here migrate_disable() does not protect against reentrancy from a
+preempting task. A correct substitution for this case is::
+
+ func()
+ {
+ struct foo *p;
+
+ local_lock(&foo_lock);
+ p = this_cpu_ptr(&var1);
+ p->val = func2();
+
+On a non-PREEMPT_RT kernel this protects against reentrancy by disabling
+preemption. On a PREEMPT_RT kernel this is achieved by acquiring the
+underlying per-CPU spinlock.
+
+
+raw_spinlock_t on RT
+--------------------
Acquiring a raw_spinlock_t disables preemption and possibly also
interrupts, so the critical section must avoid acquiring a regular
@@ -325,22 +515,25 @@ Lock type nesting rules
The most basic rules are:
- - Lock types of the same lock category (sleeping, spinning) can nest
- arbitrarily as long as they respect the general lock ordering rules to
- prevent deadlocks.
+ - Lock types of the same lock category (sleeping, CPU local, spinning)
+ can nest arbitrarily as long as they respect the general lock ordering
+ rules to prevent deadlocks.
+
+ - Sleeping lock types cannot nest inside CPU local and spinning lock types.
- - Sleeping lock types cannot nest inside spinning lock types.
+ - CPU local and spinning lock types can nest inside sleeping lock types.
- - Spinning lock types can nest inside sleeping lock types.
+ - Spinning lock types can nest inside all lock types
These constraints apply both in PREEMPT_RT and otherwise.
The fact that PREEMPT_RT changes the lock category of spinlock_t and
-rwlock_t from spinning to sleeping means that they cannot be acquired while
-holding a raw spinlock. This results in the following nesting ordering:
+rwlock_t from spinning to sleeping and substitutes local_lock with a
+per-CPU spinlock_t means that they cannot be acquired while holding a raw
+spinlock. This results in the following nesting ordering:
1) Sleeping locks
- 2) spinlock_t and rwlock_t
+ 2) spinlock_t, rwlock_t, local_lock
3) raw_spinlock_t and bit spinlocks
Lockdep will complain if these constraints are violated, both in
diff --git a/drivers/block/zram/zcomp.c b/drivers/block/zram/zcomp.c
index 1a8564a79d8d..5ee8e3fae551 100644
--- a/drivers/block/zram/zcomp.c
+++ b/drivers/block/zram/zcomp.c
@@ -37,19 +37,16 @@ static void zcomp_strm_free(struct zcomp_strm *zstrm)
if (!IS_ERR_OR_NULL(zstrm->tfm))
crypto_free_comp(zstrm->tfm);
free_pages((unsigned long)zstrm->buffer, 1);
- kfree(zstrm);
+ zstrm->tfm = NULL;
+ zstrm->buffer = NULL;
}
/*
- * allocate new zcomp_strm structure with ->tfm initialized by
- * backend, return NULL on error
+ * Initialize zcomp_strm structure with ->tfm initialized by backend, and
+ * ->buffer. Return a negative value on error.
*/
-static struct zcomp_strm *zcomp_strm_alloc(struct zcomp *comp)
+static int zcomp_strm_init(struct zcomp_strm *zstrm, struct zcomp *comp)
{
- struct zcomp_strm *zstrm = kmalloc(sizeof(*zstrm), GFP_KERNEL);
- if (!zstrm)
- return NULL;
-
zstrm->tfm = crypto_alloc_comp(comp->name, 0, 0);
/*
* allocate 2 pages. 1 for compressed data, plus 1 extra for the
@@ -58,9 +55,9 @@ static struct zcomp_strm *zcomp_strm_alloc(struct zcomp *comp)
zstrm->buffer = (void *)__get_free_pages(GFP_KERNEL | __GFP_ZERO, 1);
if (IS_ERR_OR_NULL(zstrm->tfm) || !zstrm->buffer) {
zcomp_strm_free(zstrm);
- zstrm = NULL;
+ return -ENOMEM;
}
- return zstrm;
+ return 0;
}
bool zcomp_available_algorithm(const char *comp)
@@ -113,12 +110,13 @@ ssize_t zcomp_available_show(const char *comp, char *buf)
struct zcomp_strm *zcomp_stream_get(struct zcomp *comp)
{
- return *get_cpu_ptr(comp->stream);
+ local_lock(&comp->stream->lock);
+ return this_cpu_ptr(comp->stream);
}
void zcomp_stream_put(struct zcomp *comp)
{
- put_cpu_ptr(comp->stream);
+ local_unlock(&comp->stream->lock);
}
int zcomp_compress(struct zcomp_strm *zstrm,
@@ -159,17 +157,15 @@ int zcomp_cpu_up_prepare(unsigned int cpu, struct hlist_node *node)
{
struct zcomp *comp = hlist_entry(node, struct zcomp, node);
struct zcomp_strm *zstrm;
+ int ret;
- if (WARN_ON(*per_cpu_ptr(comp->stream, cpu)))
- return 0;
+ zstrm = per_cpu_ptr(comp->stream, cpu);
+ local_lock_init(&zstrm->lock);
- zstrm = zcomp_strm_alloc(comp);
- if (IS_ERR_OR_NULL(zstrm)) {
+ ret = zcomp_strm_init(zstrm, comp);
+ if (ret)
pr_err("Can't allocate a compression stream\n");
- return -ENOMEM;
- }
- *per_cpu_ptr(comp->stream, cpu) = zstrm;
- return 0;
+ return ret;
}
int zcomp_cpu_dead(unsigned int cpu, struct hlist_node *node)
@@ -177,10 +173,8 @@ int zcomp_cpu_dead(unsigned int cpu, struct hlist_node *node)
struct zcomp *comp = hlist_entry(node, struct zcomp, node);
struct zcomp_strm *zstrm;
- zstrm = *per_cpu_ptr(comp->stream, cpu);
- if (!IS_ERR_OR_NULL(zstrm))
- zcomp_strm_free(zstrm);
- *per_cpu_ptr(comp->stream, cpu) = NULL;
+ zstrm = per_cpu_ptr(comp->stream, cpu);
+ zcomp_strm_free(zstrm);
return 0;
}
@@ -188,7 +182,7 @@ static int zcomp_init(struct zcomp *comp)
{
int ret;
- comp->stream = alloc_percpu(struct zcomp_strm *);
+ comp->stream = alloc_percpu(struct zcomp_strm);
if (!comp->stream)
return -ENOMEM;
diff --git a/drivers/block/zram/zcomp.h b/drivers/block/zram/zcomp.h
index 1806475b919d..40f6420f4b2e 100644
--- a/drivers/block/zram/zcomp.h
+++ b/drivers/block/zram/zcomp.h
@@ -5,8 +5,11 @@
#ifndef _ZCOMP_H_
#define _ZCOMP_H_
+#include <linux/local_lock.h>
struct zcomp_strm {
+ /* The members ->buffer and ->tfm are protected by ->lock. */
+ local_lock_t lock;
/* compression/decompression buffer */
void *buffer;
struct crypto_comp *tfm;
@@ -14,7 +17,7 @@ struct zcomp_strm {
/* dynamic per-device compression frontend */
struct zcomp {
- struct zcomp_strm * __percpu *stream;
+ struct zcomp_strm __percpu *stream;
const char *name;
struct hlist_node node;
};
diff --git a/drivers/connector/cn_proc.c b/drivers/connector/cn_proc.c
index d58ce664da84..646ad385e490 100644
--- a/drivers/connector/cn_proc.c
+++ b/drivers/connector/cn_proc.c
@@ -18,6 +18,7 @@
#include <linux/pid_namespace.h>
#include <linux/cn_proc.h>
+#include <linux/local_lock.h>
/*
* Size of a cn_msg followed by a proc_event structure. Since the
@@ -38,25 +39,31 @@ static inline struct cn_msg *buffer_to_cn_msg(__u8 *buffer)
static atomic_t proc_event_num_listeners = ATOMIC_INIT(0);
static struct cb_id cn_proc_event_id = { CN_IDX_PROC, CN_VAL_PROC };
-/* proc_event_counts is used as the sequence number of the netlink message */
-static DEFINE_PER_CPU(__u32, proc_event_counts) = { 0 };
+/* local_event.count is used as the sequence number of the netlink message */
+struct local_event {
+ local_lock_t lock;
+ __u32 count;
+};
+static DEFINE_PER_CPU(struct local_event, local_event) = {
+ .lock = INIT_LOCAL_LOCK(lock),
+};
static inline void send_msg(struct cn_msg *msg)
{
- preempt_disable();
+ local_lock(&local_event.lock);
- msg->seq = __this_cpu_inc_return(proc_event_counts) - 1;
+ msg->seq = __this_cpu_inc_return(local_event.count) - 1;
((struct proc_event *)msg->data)->cpu = smp_processor_id();
/*
- * Preemption remains disabled during send to ensure the messages are
- * ordered according to their sequence numbers.
+ * local_lock() disables preemption during send to ensure the messages
+ * are ordered according to their sequence numbers.
*
* If cn_netlink_send() fails, the data is not sent.
*/
cn_netlink_send(msg, 0, CN_IDX_PROC, GFP_NOWAIT);
- preempt_enable();
+ local_unlock(&local_event.lock);
}
void proc_fork_connector(struct task_struct *task)
diff --git a/fs/squashfs/decompressor_multi_percpu.c b/fs/squashfs/decompressor_multi_percpu.c
index 2a2a2d106440..e206ebfe003c 100644
--- a/fs/squashfs/decompressor_multi_percpu.c
+++ b/fs/squashfs/decompressor_multi_percpu.c
@@ -8,6 +8,7 @@
#include <linux/slab.h>
#include <linux/percpu.h>
#include <linux/buffer_head.h>
+#include <linux/local_lock.h>
#include "squashfs_fs.h"
#include "squashfs_fs_sb.h"
@@ -20,7 +21,8 @@
*/
struct squashfs_stream {
- void *stream;
+ void *stream;
+ local_lock_t lock;
};
void *squashfs_decompressor_create(struct squashfs_sb_info *msblk,
@@ -41,6 +43,7 @@ void *squashfs_decompressor_create(struct squashfs_sb_info *msblk,
err = PTR_ERR(stream->stream);
goto out;
}
+ local_lock_init(&stream->lock);
}
kfree(comp_opts);
@@ -75,12 +78,16 @@ void squashfs_decompressor_destroy(struct squashfs_sb_info *msblk)
int squashfs_decompress(struct squashfs_sb_info *msblk, struct buffer_head **bh,
int b, int offset, int length, struct squashfs_page_actor *output)
{
- struct squashfs_stream __percpu *percpu =
- (struct squashfs_stream __percpu *) msblk->stream;
- struct squashfs_stream *stream = get_cpu_ptr(percpu);
- int res = msblk->decompressor->decompress(msblk, stream->stream, bh, b,
- offset, length, output);
- put_cpu_ptr(stream);
+ struct squashfs_stream *stream;
+ int res;
+
+ local_lock(&msblk->stream->lock);
+ stream = this_cpu_ptr(msblk->stream);
+
+ res = msblk->decompressor->decompress(msblk, stream->stream, bh, b,
+ offset, length, output);
+
+ local_unlock(&msblk->stream->lock);
if (res < 0)
ERROR("%s decompression failed, data probably corrupt\n",
diff --git a/include/linux/idr.h b/include/linux/idr.h
index ac6e946b6767..3ade03e5c7af 100644
--- a/include/linux/idr.h
+++ b/include/linux/idr.h
@@ -171,7 +171,7 @@ static inline bool idr_is_empty(const struct idr *idr)
*/
static inline void idr_preload_end(void)
{
- preempt_enable();
+ local_unlock(&radix_tree_preloads.lock);
}
/**
diff --git a/include/linux/local_lock.h b/include/linux/local_lock.h
new file mode 100644
index 000000000000..e55010fa7329
--- /dev/null
+++ b/include/linux/local_lock.h
@@ -0,0 +1,54 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _LINUX_LOCAL_LOCK_H
+#define _LINUX_LOCAL_LOCK_H
+
+#include <linux/local_lock_internal.h>
+
+/**
+ * local_lock_init - Runtime initialize a lock instance
+ */
+#define local_lock_init(lock) __local_lock_init(lock)
+
+/**
+ * local_lock - Acquire a per CPU local lock
+ * @lock: The lock variable
+ */
+#define local_lock(lock) __local_lock(lock)
+
+/**
+ * local_lock_irq - Acquire a per CPU local lock and disable interrupts
+ * @lock: The lock variable
+ */
+#define local_lock_irq(lock) __local_lock_irq(lock)
+
+/**
+ * local_lock_irqsave - Acquire a per CPU local lock, save and disable
+ * interrupts
+ * @lock: The lock variable
+ * @flags: Storage for interrupt flags
+ */
+#define local_lock_irqsave(lock, flags) \
+ __local_lock_irqsave(lock, flags)
+
+/**
+ * local_unlock - Release a per CPU local lock
+ * @lock: The lock variable
+ */
+#define local_unlock(lock) __local_unlock(lock)
+
+/**
+ * local_unlock_irq - Release a per CPU local lock and enable interrupts
+ * @lock: The lock variable
+ */
+#define local_unlock_irq(lock) __local_unlock_irq(lock)
+
+/**
+ * local_unlock_irqrestore - Release a per CPU local lock and restore
+ * interrupt flags
+ * @lock: The lock variable
+ * @flags: Interrupt flags to restore
+ */
+#define local_unlock_irqrestore(lock, flags) \
+ __local_unlock_irqrestore(lock, flags)
+
+#endif
diff --git a/include/linux/local_lock_internal.h b/include/linux/local_lock_internal.h
new file mode 100644
index 000000000000..4a8795b21d77
--- /dev/null
+++ b/include/linux/local_lock_internal.h
@@ -0,0 +1,90 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _LINUX_LOCAL_LOCK_H
+# error "Do not include directly, include linux/local_lock.h"
+#endif
+
+#include <linux/percpu-defs.h>
+#include <linux/lockdep.h>
+
+typedef struct {
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+ struct lockdep_map dep_map;
+ struct task_struct *owner;
+#endif
+} local_lock_t;
+
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+# define LL_DEP_MAP_INIT(lockname) \
+ .dep_map = { \
+ .name = #lockname, \
+ .wait_type_inner = LD_WAIT_CONFIG, \
+ }
+#else
+# define LL_DEP_MAP_INIT(lockname)
+#endif
+
+#define INIT_LOCAL_LOCK(lockname) { LL_DEP_MAP_INIT(lockname) }
+
+#define __local_lock_init(lock) \
+do { \
+ static struct lock_class_key __key; \
+ \
+ debug_check_no_locks_freed((void *)lock, sizeof(*lock));\
+ lockdep_init_map_wait(&(lock)->dep_map, #lock, &__key, 0, LD_WAIT_CONFIG);\
+} while (0)
+
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+static inline void local_lock_acquire(local_lock_t *l)
+{
+ lock_map_acquire(&l->dep_map);
+ DEBUG_LOCKS_WARN_ON(l->owner);
+ l->owner = current;
+}
+
+static inline void local_lock_release(local_lock_t *l)
+{
+ DEBUG_LOCKS_WARN_ON(l->owner != current);
+ l->owner = NULL;
+ lock_map_release(&l->dep_map);
+}
+
+#else /* CONFIG_DEBUG_LOCK_ALLOC */
+static inline void local_lock_acquire(local_lock_t *l) { }
+static inline void local_lock_release(local_lock_t *l) { }
+#endif /* !CONFIG_DEBUG_LOCK_ALLOC */
+
+#define __local_lock(lock) \
+ do { \
+ preempt_disable(); \
+ local_lock_acquire(this_cpu_ptr(lock)); \
+ } while (0)
+
+#define __local_lock_irq(lock) \
+ do { \
+ local_irq_disable(); \
+ local_lock_acquire(this_cpu_ptr(lock)); \
+ } while (0)
+
+#define __local_lock_irqsave(lock, flags) \
+ do { \
+ local_irq_save(flags); \
+ local_lock_acquire(this_cpu_ptr(lock)); \
+ } while (0)
+
+#define __local_unlock(lock) \
+ do { \
+ local_lock_release(this_cpu_ptr(lock)); \
+ preempt_enable(); \
+ } while (0)
+
+#define __local_unlock_irq(lock) \
+ do { \
+ local_lock_release(this_cpu_ptr(lock)); \
+ local_irq_enable(); \
+ } while (0)
+
+#define __local_unlock_irqrestore(lock, flags) \
+ do { \
+ local_lock_release(this_cpu_ptr(lock)); \
+ local_irq_restore(flags); \
+ } while (0)
diff --git a/include/linux/radix-tree.h b/include/linux/radix-tree.h
index 63e62372443a..c2a9f7c90727 100644
--- a/include/linux/radix-tree.h
+++ b/include/linux/radix-tree.h
@@ -16,11 +16,20 @@
#include <linux/spinlock.h>
#include <linux/types.h>
#include <linux/xarray.h>
+#include <linux/local_lock.h>
/* Keep unconverted code working */
#define radix_tree_root xarray
#define radix_tree_node xa_node
+struct radix_tree_preload {
+ local_lock_t lock;
+ unsigned nr;
+ /* nodes->parent points to next preallocated node */
+ struct radix_tree_node *nodes;
+};
+DECLARE_PER_CPU(struct radix_tree_preload, radix_tree_preloads);
+
/*
* The bottom two bits of the slot determine how the remaining bits in the
* slot are interpreted:
@@ -245,7 +254,7 @@ int radix_tree_tagged(const struct radix_tree_root *, unsigned int tag);
static inline void radix_tree_preload_end(void)
{
- preempt_enable();
+ local_unlock(&radix_tree_preloads.lock);
}
void __rcu **idr_get_free(struct radix_tree_root *root,
diff --git a/include/linux/swap.h b/include/linux/swap.h
index e1bbf7a16b27..25181d2dd0b9 100644
--- a/include/linux/swap.h
+++ b/include/linux/swap.h
@@ -337,6 +337,7 @@ extern void activate_page(struct page *);
extern void mark_page_accessed(struct page *);
extern void lru_add_drain(void);
extern void lru_add_drain_cpu(int cpu);
+extern void lru_add_drain_cpu_zone(struct zone *zone);
extern void lru_add_drain_all(void);
extern void rotate_reclaimable_page(struct page *page);
extern void deactivate_file_page(struct page *page);
diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c
index 6f1c8cba09c6..dd3cc0854c32 100644
--- a/kernel/locking/lockdep.c
+++ b/kernel/locking/lockdep.c
@@ -470,7 +470,7 @@ struct lock_trace {
struct hlist_node hash_entry;
u32 hash;
u32 nr_entries;
- unsigned long entries[0] __aligned(sizeof(unsigned long));
+ unsigned long entries[] __aligned(sizeof(unsigned long));
};
#define LOCK_TRACE_SIZE_IN_LONGS \
(sizeof(struct lock_trace) / sizeof(unsigned long))
diff --git a/kernel/locking/rtmutex.c b/kernel/locking/rtmutex.c
index c9f090d64f00..cfdd5b93264d 100644
--- a/kernel/locking/rtmutex.c
+++ b/kernel/locking/rtmutex.c
@@ -141,7 +141,6 @@ static void fixup_rt_mutex_waiters(struct rt_mutex *lock)
* set up.
*/
#ifndef CONFIG_DEBUG_RT_MUTEXES
-# define rt_mutex_cmpxchg_relaxed(l,c,n) (cmpxchg_relaxed(&l->owner, c, n) == c)
# define rt_mutex_cmpxchg_acquire(l,c,n) (cmpxchg_acquire(&l->owner, c, n) == c)
# define rt_mutex_cmpxchg_release(l,c,n) (cmpxchg_release(&l->owner, c, n) == c)
@@ -202,7 +201,6 @@ static inline bool unlock_rt_mutex_safe(struct rt_mutex *lock,
}
#else
-# define rt_mutex_cmpxchg_relaxed(l,c,n) (0)
# define rt_mutex_cmpxchg_acquire(l,c,n) (0)
# define rt_mutex_cmpxchg_release(l,c,n) (0)
diff --git a/lib/radix-tree.c b/lib/radix-tree.c
index 2ee6ae3b0ade..34e406fe561f 100644
--- a/lib/radix-tree.c
+++ b/lib/radix-tree.c
@@ -20,6 +20,7 @@
#include <linux/kernel.h>
#include <linux/kmemleak.h>
#include <linux/percpu.h>
+#include <linux/local_lock.h>
#include <linux/preempt.h> /* in_interrupt() */
#include <linux/radix-tree.h>
#include <linux/rcupdate.h>
@@ -27,7 +28,6 @@
#include <linux/string.h>
#include <linux/xarray.h>
-
/*
* Radix tree node cache.
*/
@@ -58,12 +58,10 @@ struct kmem_cache *radix_tree_node_cachep;
/*
* Per-cpu pool of preloaded nodes
*/
-struct radix_tree_preload {
- unsigned nr;
- /* nodes->parent points to next preallocated node */
- struct radix_tree_node *nodes;
+DEFINE_PER_CPU(struct radix_tree_preload, radix_tree_preloads) = {
+ .lock = INIT_LOCAL_LOCK(lock),
};
-static DEFINE_PER_CPU(struct radix_tree_preload, radix_tree_preloads) = { 0, };
+EXPORT_PER_CPU_SYMBOL_GPL(radix_tree_preloads);
static inline struct radix_tree_node *entry_to_node(void *ptr)
{
@@ -332,14 +330,14 @@ static __must_check int __radix_tree_preload(gfp_t gfp_mask, unsigned nr)
*/
gfp_mask &= ~__GFP_ACCOUNT;
- preempt_disable();
+ local_lock(&radix_tree_preloads.lock);
rtp = this_cpu_ptr(&radix_tree_preloads);
while (rtp->nr < nr) {
- preempt_enable();
+ local_unlock(&radix_tree_preloads.lock);
node = kmem_cache_alloc(radix_tree_node_cachep, gfp_mask);
if (node == NULL)
goto out;
- preempt_disable();
+ local_lock(&radix_tree_preloads.lock);
rtp = this_cpu_ptr(&radix_tree_preloads);
if (rtp->nr < nr) {
node->parent = rtp->nodes;
@@ -381,7 +379,7 @@ int radix_tree_maybe_preload(gfp_t gfp_mask)
if (gfpflags_allow_blocking(gfp_mask))
return __radix_tree_preload(gfp_mask, RADIX_TREE_PRELOAD_SIZE);
/* Preloading doesn't help anything with this gfp mask, skip it */
- preempt_disable();
+ local_lock(&radix_tree_preloads.lock);
return 0;
}
EXPORT_SYMBOL(radix_tree_maybe_preload);
@@ -1470,7 +1468,7 @@ EXPORT_SYMBOL(radix_tree_tagged);
void idr_preload(gfp_t gfp_mask)
{
if (__radix_tree_preload(gfp_mask, IDR_PRELOAD_SIZE))
- preempt_disable();
+ local_lock(&radix_tree_preloads.lock);
}
EXPORT_SYMBOL(idr_preload);
diff --git a/mm/compaction.c b/mm/compaction.c
index 46f0fcc93081..c9d659e6a02c 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -2243,15 +2243,11 @@ check_drain:
* would succeed.
*/
if (cc->order > 0 && last_migrated_pfn) {
- int cpu;
unsigned long current_block_start =
block_start_pfn(cc->migrate_pfn, cc->order);
if (last_migrated_pfn < current_block_start) {
- cpu = get_cpu();
- lru_add_drain_cpu(cpu);
- drain_local_pages(cc->zone);
- put_cpu();
+ lru_add_drain_cpu_zone(cc->zone);
/* No more flushing until we migrate again */
last_migrated_pfn = 0;
}
diff --git a/mm/swap.c b/mm/swap.c
index bf9a79fed62d..0ac463d44cff 100644
--- a/mm/swap.c
+++ b/mm/swap.c
@@ -35,6 +35,7 @@
#include <linux/uio.h>
#include <linux/hugetlb.h>
#include <linux/page_idle.h>
+#include <linux/local_lock.h>
#include "internal.h"
@@ -44,14 +45,32 @@
/* How many pages do we try to swap or page in/out together? */
int page_cluster;
-static DEFINE_PER_CPU(struct pagevec, lru_add_pvec);
-static DEFINE_PER_CPU(struct pagevec, lru_rotate_pvecs);
-static DEFINE_PER_CPU(struct pagevec, lru_deactivate_file_pvecs);
-static DEFINE_PER_CPU(struct pagevec, lru_deactivate_pvecs);
-static DEFINE_PER_CPU(struct pagevec, lru_lazyfree_pvecs);
+/* Protecting only lru_rotate.pvec which requires disabling interrupts */
+struct lru_rotate {
+ local_lock_t lock;
+ struct pagevec pvec;
+};
+static DEFINE_PER_CPU(struct lru_rotate, lru_rotate) = {
+ .lock = INIT_LOCAL_LOCK(lock),
+};
+
+/*
+ * The following struct pagevec are grouped together because they are protected
+ * by disabling preemption (and interrupts remain enabled).
+ */
+struct lru_pvecs {
+ local_lock_t lock;
+ struct pagevec lru_add;
+ struct pagevec lru_deactivate_file;
+ struct pagevec lru_deactivate;
+ struct pagevec lru_lazyfree;
#ifdef CONFIG_SMP
-static DEFINE_PER_CPU(struct pagevec, activate_page_pvecs);
+ struct pagevec activate_page;
#endif
+};
+static DEFINE_PER_CPU(struct lru_pvecs, lru_pvecs) = {
+ .lock = INIT_LOCAL_LOCK(lock),
+};
/*
* This path almost never happens for VM activity - pages are normally
@@ -254,11 +273,11 @@ void rotate_reclaimable_page(struct page *page)
unsigned long flags;
get_page(page);
- local_irq_save(flags);
- pvec = this_cpu_ptr(&lru_rotate_pvecs);
+ local_lock_irqsave(&lru_rotate.lock, flags);
+ pvec = this_cpu_ptr(&lru_rotate.pvec);
if (!pagevec_add(pvec, page) || PageCompound(page))
pagevec_move_tail(pvec);
- local_irq_restore(flags);
+ local_unlock_irqrestore(&lru_rotate.lock, flags);
}
}
@@ -293,7 +312,7 @@ static void __activate_page(struct page *page, struct lruvec *lruvec,
#ifdef CONFIG_SMP
static void activate_page_drain(int cpu)
{
- struct pagevec *pvec = &per_cpu(activate_page_pvecs, cpu);
+ struct pagevec *pvec = &per_cpu(lru_pvecs.activate_page, cpu);
if (pagevec_count(pvec))
pagevec_lru_move_fn(pvec, __activate_page, NULL);
@@ -301,19 +320,21 @@ static void activate_page_drain(int cpu)
static bool need_activate_page_drain(int cpu)
{
- return pagevec_count(&per_cpu(activate_page_pvecs, cpu)) != 0;
+ return pagevec_count(&per_cpu(lru_pvecs.activate_page, cpu)) != 0;
}
void activate_page(struct page *page)
{
page = compound_head(page);
if (PageLRU(page) && !PageActive(page) && !PageUnevictable(page)) {
- struct pagevec *pvec = &get_cpu_var(activate_page_pvecs);
+ struct pagevec *pvec;
+ local_lock(&lru_pvecs.lock);
+ pvec = this_cpu_ptr(&lru_pvecs.activate_page);
get_page(page);
if (!pagevec_add(pvec, page) || PageCompound(page))
pagevec_lru_move_fn(pvec, __activate_page, NULL);
- put_cpu_var(activate_page_pvecs);
+ local_unlock(&lru_pvecs.lock);
}
}
@@ -335,9 +356,12 @@ void activate_page(struct page *page)
static void __lru_cache_activate_page(struct page *page)
{
- struct pagevec *pvec = &get_cpu_var(lru_add_pvec);
+ struct pagevec *pvec;
int i;
+ local_lock(&lru_pvecs.lock);
+ pvec = this_cpu_ptr(&lru_pvecs.lru_add);
+
/*
* Search backwards on the optimistic assumption that the page being
* activated has just been added to this pagevec. Note that only
@@ -357,7 +381,7 @@ static void __lru_cache_activate_page(struct page *page)
}
}
- put_cpu_var(lru_add_pvec);
+ local_unlock(&lru_pvecs.lock);
}
/*
@@ -385,7 +409,7 @@ void mark_page_accessed(struct page *page)
} else if (!PageActive(page)) {
/*
* If the page is on the LRU, queue it for activation via
- * activate_page_pvecs. Otherwise, assume the page is on a
+ * lru_pvecs.activate_page. Otherwise, assume the page is on a
* pagevec, mark it active and it'll be moved to the active
* LRU on the next drain.
*/
@@ -404,12 +428,14 @@ EXPORT_SYMBOL(mark_page_accessed);
static void __lru_cache_add(struct page *page)
{
- struct pagevec *pvec = &get_cpu_var(lru_add_pvec);
+ struct pagevec *pvec;
+ local_lock(&lru_pvecs.lock);
+ pvec = this_cpu_ptr(&lru_pvecs.lru_add);
get_page(page);
if (!pagevec_add(pvec, page) || PageCompound(page))
__pagevec_lru_add(pvec);
- put_cpu_var(lru_add_pvec);
+ local_unlock(&lru_pvecs.lock);
}
/**
@@ -593,30 +619,30 @@ static void lru_lazyfree_fn(struct page *page, struct lruvec *lruvec,
*/
void lru_add_drain_cpu(int cpu)
{
- struct pagevec *pvec = &per_cpu(lru_add_pvec, cpu);
+ struct pagevec *pvec = &per_cpu(lru_pvecs.lru_add, cpu);
if (pagevec_count(pvec))
__pagevec_lru_add(pvec);
- pvec = &per_cpu(lru_rotate_pvecs, cpu);
+ pvec = &per_cpu(lru_rotate.pvec, cpu);
if (pagevec_count(pvec)) {
unsigned long flags;
/* No harm done if a racing interrupt already did this */
- local_irq_save(flags);
+ local_lock_irqsave(&lru_rotate.lock, flags);
pagevec_move_tail(pvec);
- local_irq_restore(flags);
+ local_unlock_irqrestore(&lru_rotate.lock, flags);
}
- pvec = &per_cpu(lru_deactivate_file_pvecs, cpu);
+ pvec = &per_cpu(lru_pvecs.lru_deactivate_file, cpu);
if (pagevec_count(pvec))
pagevec_lru_move_fn(pvec, lru_deactivate_file_fn, NULL);
- pvec = &per_cpu(lru_deactivate_pvecs, cpu);
+ pvec = &per_cpu(lru_pvecs.lru_deactivate, cpu);
if (pagevec_count(pvec))
pagevec_lru_move_fn(pvec, lru_deactivate_fn, NULL);
- pvec = &per_cpu(lru_lazyfree_pvecs, cpu);
+ pvec = &per_cpu(lru_pvecs.lru_lazyfree, cpu);
if (pagevec_count(pvec))
pagevec_lru_move_fn(pvec, lru_lazyfree_fn, NULL);
@@ -641,11 +667,14 @@ void deactivate_file_page(struct page *page)
return;
if (likely(get_page_unless_zero(page))) {
- struct pagevec *pvec = &get_cpu_var(lru_deactivate_file_pvecs);
+ struct pagevec *pvec;
+
+ local_lock(&lru_pvecs.lock);
+ pvec = this_cpu_ptr(&lru_pvecs.lru_deactivate_file);
if (!pagevec_add(pvec, page) || PageCompound(page))
pagevec_lru_move_fn(pvec, lru_deactivate_file_fn, NULL);
- put_cpu_var(lru_deactivate_file_pvecs);
+ local_unlock(&lru_pvecs.lock);
}
}
@@ -660,12 +689,14 @@ void deactivate_file_page(struct page *page)
void deactivate_page(struct page *page)
{
if (PageLRU(page) && PageActive(page) && !PageUnevictable(page)) {
- struct pagevec *pvec = &get_cpu_var(lru_deactivate_pvecs);
+ struct pagevec *pvec;
+ local_lock(&lru_pvecs.lock);
+ pvec = this_cpu_ptr(&lru_pvecs.lru_deactivate);
get_page(page);
if (!pagevec_add(pvec, page) || PageCompound(page))
pagevec_lru_move_fn(pvec, lru_deactivate_fn, NULL);
- put_cpu_var(lru_deactivate_pvecs);
+ local_unlock(&lru_pvecs.lock);
}
}
@@ -680,19 +711,30 @@ void mark_page_lazyfree(struct page *page)
{
if (PageLRU(page) && PageAnon(page) && PageSwapBacked(page) &&
!PageSwapCache(page) && !PageUnevictable(page)) {
- struct pagevec *pvec = &get_cpu_var(lru_lazyfree_pvecs);
+ struct pagevec *pvec;
+ local_lock(&lru_pvecs.lock);
+ pvec = this_cpu_ptr(&lru_pvecs.lru_lazyfree);
get_page(page);
if (!pagevec_add(pvec, page) || PageCompound(page))
pagevec_lru_move_fn(pvec, lru_lazyfree_fn, NULL);
- put_cpu_var(lru_lazyfree_pvecs);
+ local_unlock(&lru_pvecs.lock);
}
}
void lru_add_drain(void)
{
- lru_add_drain_cpu(get_cpu());
- put_cpu();
+ local_lock(&lru_pvecs.lock);
+ lru_add_drain_cpu(smp_processor_id());
+ local_unlock(&lru_pvecs.lock);
+}
+
+void lru_add_drain_cpu_zone(struct zone *zone)
+{
+ local_lock(&lru_pvecs.lock);
+ lru_add_drain_cpu(smp_processor_id());
+ drain_local_pages(zone);
+ local_unlock(&lru_pvecs.lock);
}
#ifdef CONFIG_SMP
@@ -743,11 +785,11 @@ void lru_add_drain_all(void)
for_each_online_cpu(cpu) {
struct work_struct *work = &per_cpu(lru_add_drain_work, cpu);
- if (pagevec_count(&per_cpu(lru_add_pvec, cpu)) ||
- pagevec_count(&per_cpu(lru_rotate_pvecs, cpu)) ||
- pagevec_count(&per_cpu(lru_deactivate_file_pvecs, cpu)) ||
- pagevec_count(&per_cpu(lru_deactivate_pvecs, cpu)) ||
- pagevec_count(&per_cpu(lru_lazyfree_pvecs, cpu)) ||
+ if (pagevec_count(&per_cpu(lru_pvecs.lru_add, cpu)) ||
+ pagevec_count(&per_cpu(lru_rotate.pvec, cpu)) ||
+ pagevec_count(&per_cpu(lru_pvecs.lru_deactivate_file, cpu)) ||
+ pagevec_count(&per_cpu(lru_pvecs.lru_deactivate, cpu)) ||
+ pagevec_count(&per_cpu(lru_pvecs.lru_lazyfree, cpu)) ||
need_activate_page_drain(cpu)) {
INIT_WORK(work, lru_add_drain_per_cpu);
queue_work_on(cpu, mm_percpu_wq, work);