summaryrefslogtreecommitdiffstats
path: root/kernel
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2017-02-20 13:23:30 -0800
committerLinus Torvalds <torvalds@linux-foundation.org>2017-02-20 13:23:30 -0800
commit42e1b14b6e1455ece2ccbe474c25388d0230a590 (patch)
tree7f62d95f795a2ac5c183248dce39e75340ccfb76 /kernel
parent828cad8ea05d194d8a9452e0793261c2024c23a2 (diff)
parent95cb64c1fe61e70685a95f6260c8e9cd219fe08c (diff)
downloadlinux-42e1b14b6e1455ece2ccbe474c25388d0230a590.tar.bz2
Merge branch 'locking-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull locking updates from Ingo Molnar: "The main changes in this cycle were: - Implement wraparound-safe refcount_t and kref_t types based on generic atomic primitives (Peter Zijlstra) - Improve and fix the ww_mutex code (Nicolai Hähnle) - Add self-tests to the ww_mutex code (Chris Wilson) - Optimize percpu-rwsems with the 'rcuwait' mechanism (Davidlohr Bueso) - Micro-optimize the current-task logic all around the core kernel (Davidlohr Bueso) - Tidy up after recent optimizations: remove stale code and APIs, clean up the code (Waiman Long) - ... plus misc fixes, updates and cleanups" * 'locking-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (50 commits) fork: Fix task_struct alignment locking/spinlock/debug: Remove spinlock lockup detection code lockdep: Fix incorrect condition to print bug msgs for MAX_LOCKDEP_CHAIN_HLOCKS lkdtm: Convert to refcount_t testing kref: Implement 'struct kref' using refcount_t refcount_t: Introduce a special purpose refcount type sched/wake_q: Clarify queue reinit comment sched/wait, rcuwait: Fix typo in comment locking/mutex: Fix lockdep_assert_held() fail locking/rtmutex: Flip unlikely() branch to likely() in __rt_mutex_slowlock() locking/rwsem: Reinit wake_q after use locking/rwsem: Remove unnecessary atomic_long_t casts jump_labels: Move header guard #endif down where it belongs locking/atomic, kref: Implement kref_put_lock() locking/ww_mutex: Turn off __must_check for now locking/atomic, kref: Avoid more abuse locking/atomic, kref: Use kref_get_unless_zero() more locking/atomic, kref: Kill kref_sub() locking/atomic, kref: Add kref_read() locking/atomic, kref: Add KREF_INIT() ...
Diffstat (limited to 'kernel')
-rw-r--r--kernel/exit.c52
-rw-r--r--kernel/fork.c6
-rw-r--r--kernel/locking/Makefile1
-rw-r--r--kernel/locking/lockdep.c2
-rw-r--r--kernel/locking/locktorture.c73
-rw-r--r--kernel/locking/mutex-debug.h17
-rw-r--r--kernel/locking/mutex.c516
-rw-r--r--kernel/locking/mutex.h4
-rw-r--r--kernel/locking/percpu-rwsem.c7
-rw-r--r--kernel/locking/qspinlock_paravirt.h2
-rw-r--r--kernel/locking/rtmutex.c2
-rw-r--r--kernel/locking/rwsem-spinlock.c18
-rw-r--r--kernel/locking/rwsem-xadd.c14
-rw-r--r--kernel/locking/semaphore.c7
-rw-r--r--kernel/locking/spinlock.c8
-rw-r--r--kernel/locking/spinlock_debug.c86
-rw-r--r--kernel/locking/test-ww_mutex.c646
-rw-r--r--kernel/pid.c4
18 files changed, 1127 insertions, 338 deletions
diff --git a/kernel/exit.c b/kernel/exit.c
index 8e5e21338b3a..b67c57faa705 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -55,6 +55,7 @@
#include <linux/shm.h>
#include <linux/kcov.h>
#include <linux/random.h>
+#include <linux/rcuwait.h>
#include <linux/uaccess.h>
#include <asm/unistd.h>
@@ -282,6 +283,35 @@ retry:
return task;
}
+void rcuwait_wake_up(struct rcuwait *w)
+{
+ struct task_struct *task;
+
+ rcu_read_lock();
+
+ /*
+ * Order condition vs @task, such that everything prior to the load
+ * of @task is visible. This is the condition as to why the user called
+ * rcuwait_trywake() in the first place. Pairs with set_current_state()
+ * barrier (A) in rcuwait_wait_event().
+ *
+ * WAIT WAKE
+ * [S] tsk = current [S] cond = true
+ * MB (A) MB (B)
+ * [L] cond [L] tsk
+ */
+ smp_rmb(); /* (B) */
+
+ /*
+ * Avoid using task_rcu_dereference() magic as long as we are careful,
+ * see comment in rcuwait_wait_event() regarding ->exit_state.
+ */
+ task = rcu_dereference(w->task);
+ if (task)
+ wake_up_process(task);
+ rcu_read_unlock();
+}
+
struct task_struct *try_get_task_struct(struct task_struct **ptask)
{
struct task_struct *task;
@@ -468,12 +498,12 @@ assign_new_owner:
* Turn us into a lazy TLB process if we
* aren't already..
*/
-static void exit_mm(struct task_struct *tsk)
+static void exit_mm(void)
{
- struct mm_struct *mm = tsk->mm;
+ struct mm_struct *mm = current->mm;
struct core_state *core_state;
- mm_release(tsk, mm);
+ mm_release(current, mm);
if (!mm)
return;
sync_mm_rss(mm);
@@ -491,7 +521,7 @@ static void exit_mm(struct task_struct *tsk)
up_read(&mm->mmap_sem);
- self.task = tsk;
+ self.task = current;
self.next = xchg(&core_state->dumper.next, &self);
/*
* Implies mb(), the result of xchg() must be visible
@@ -501,22 +531,22 @@ static void exit_mm(struct task_struct *tsk)
complete(&core_state->startup);
for (;;) {
- set_task_state(tsk, TASK_UNINTERRUPTIBLE);
+ set_current_state(TASK_UNINTERRUPTIBLE);
if (!self.task) /* see coredump_finish() */
break;
freezable_schedule();
}
- __set_task_state(tsk, TASK_RUNNING);
+ __set_current_state(TASK_RUNNING);
down_read(&mm->mmap_sem);
}
atomic_inc(&mm->mm_count);
- BUG_ON(mm != tsk->active_mm);
+ BUG_ON(mm != current->active_mm);
/* more a memory barrier than a real lock */
- task_lock(tsk);
- tsk->mm = NULL;
+ task_lock(current);
+ current->mm = NULL;
up_read(&mm->mmap_sem);
enter_lazy_tlb(mm, current);
- task_unlock(tsk);
+ task_unlock(current);
mm_update_next_owner(mm);
mmput(mm);
if (test_thread_flag(TIF_MEMDIE))
@@ -823,7 +853,7 @@ void __noreturn do_exit(long code)
tsk->exit_code = code;
taskstats_exit(tsk, group_dead);
- exit_mm(tsk);
+ exit_mm();
if (group_dead)
acct_process();
diff --git a/kernel/fork.c b/kernel/fork.c
index f6995cdfe714..ff82e24573b6 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -432,11 +432,13 @@ void __init fork_init(void)
int i;
#ifndef CONFIG_ARCH_TASK_STRUCT_ALLOCATOR
#ifndef ARCH_MIN_TASKALIGN
-#define ARCH_MIN_TASKALIGN L1_CACHE_BYTES
+#define ARCH_MIN_TASKALIGN 0
#endif
+ int align = max_t(int, L1_CACHE_BYTES, ARCH_MIN_TASKALIGN);
+
/* create a slab on which task_structs can be allocated */
task_struct_cachep = kmem_cache_create("task_struct",
- arch_task_struct_size, ARCH_MIN_TASKALIGN,
+ arch_task_struct_size, align,
SLAB_PANIC|SLAB_NOTRACK|SLAB_ACCOUNT, NULL);
#endif
diff --git a/kernel/locking/Makefile b/kernel/locking/Makefile
index 6f88e352cd4f..760158d9d98d 100644
--- a/kernel/locking/Makefile
+++ b/kernel/locking/Makefile
@@ -28,3 +28,4 @@ obj-$(CONFIG_RWSEM_GENERIC_SPINLOCK) += rwsem-spinlock.o
obj-$(CONFIG_RWSEM_XCHGADD_ALGORITHM) += rwsem-xadd.o
obj-$(CONFIG_QUEUED_RWLOCKS) += qrwlock.o
obj-$(CONFIG_LOCK_TORTURE_TEST) += locktorture.o
+obj-$(CONFIG_WW_MUTEX_SELFTEST) += test-ww_mutex.o
diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c
index d9a698e8458f..9812e5dd409e 100644
--- a/kernel/locking/lockdep.c
+++ b/kernel/locking/lockdep.c
@@ -2203,7 +2203,7 @@ cache_hit:
* Important for check_no_collision().
*/
if (unlikely(nr_chain_hlocks > MAX_LOCKDEP_CHAIN_HLOCKS)) {
- if (debug_locks_off_graph_unlock())
+ if (!debug_locks_off_graph_unlock())
return 0;
print_lockdep_off("BUG: MAX_LOCKDEP_CHAIN_HLOCKS too low!");
diff --git a/kernel/locking/locktorture.c b/kernel/locking/locktorture.c
index d3de04b12f8c..28350dc8ecbb 100644
--- a/kernel/locking/locktorture.c
+++ b/kernel/locking/locktorture.c
@@ -372,6 +372,78 @@ static struct lock_torture_ops mutex_lock_ops = {
.name = "mutex_lock"
};
+#include <linux/ww_mutex.h>
+static DEFINE_WW_CLASS(torture_ww_class);
+static DEFINE_WW_MUTEX(torture_ww_mutex_0, &torture_ww_class);
+static DEFINE_WW_MUTEX(torture_ww_mutex_1, &torture_ww_class);
+static DEFINE_WW_MUTEX(torture_ww_mutex_2, &torture_ww_class);
+
+static int torture_ww_mutex_lock(void)
+__acquires(torture_ww_mutex_0)
+__acquires(torture_ww_mutex_1)
+__acquires(torture_ww_mutex_2)
+{
+ LIST_HEAD(list);
+ struct reorder_lock {
+ struct list_head link;
+ struct ww_mutex *lock;
+ } locks[3], *ll, *ln;
+ struct ww_acquire_ctx ctx;
+
+ locks[0].lock = &torture_ww_mutex_0;
+ list_add(&locks[0].link, &list);
+
+ locks[1].lock = &torture_ww_mutex_1;
+ list_add(&locks[1].link, &list);
+
+ locks[2].lock = &torture_ww_mutex_2;
+ list_add(&locks[2].link, &list);
+
+ ww_acquire_init(&ctx, &torture_ww_class);
+
+ list_for_each_entry(ll, &list, link) {
+ int err;
+
+ err = ww_mutex_lock(ll->lock, &ctx);
+ if (!err)
+ continue;
+
+ ln = ll;
+ list_for_each_entry_continue_reverse(ln, &list, link)
+ ww_mutex_unlock(ln->lock);
+
+ if (err != -EDEADLK)
+ return err;
+
+ ww_mutex_lock_slow(ll->lock, &ctx);
+ list_move(&ll->link, &list);
+ }
+
+ ww_acquire_fini(&ctx);
+ return 0;
+}
+
+static void torture_ww_mutex_unlock(void)
+__releases(torture_ww_mutex_0)
+__releases(torture_ww_mutex_1)
+__releases(torture_ww_mutex_2)
+{
+ ww_mutex_unlock(&torture_ww_mutex_0);
+ ww_mutex_unlock(&torture_ww_mutex_1);
+ ww_mutex_unlock(&torture_ww_mutex_2);
+}
+
+static struct lock_torture_ops ww_mutex_lock_ops = {
+ .writelock = torture_ww_mutex_lock,
+ .write_delay = torture_mutex_delay,
+ .task_boost = torture_boost_dummy,
+ .writeunlock = torture_ww_mutex_unlock,
+ .readlock = NULL,
+ .read_delay = NULL,
+ .readunlock = NULL,
+ .name = "ww_mutex_lock"
+};
+
#ifdef CONFIG_RT_MUTEXES
static DEFINE_RT_MUTEX(torture_rtmutex);
@@ -797,6 +869,7 @@ static int __init lock_torture_init(void)
&spin_lock_ops, &spin_lock_irq_ops,
&rw_lock_ops, &rw_lock_irq_ops,
&mutex_lock_ops,
+ &ww_mutex_lock_ops,
#ifdef CONFIG_RT_MUTEXES
&rtmutex_lock_ops,
#endif
diff --git a/kernel/locking/mutex-debug.h b/kernel/locking/mutex-debug.h
index a459faa48987..4174417d5309 100644
--- a/kernel/locking/mutex-debug.h
+++ b/kernel/locking/mutex-debug.h
@@ -26,20 +26,3 @@ extern void mutex_remove_waiter(struct mutex *lock, struct mutex_waiter *waiter,
extern void debug_mutex_unlock(struct mutex *lock);
extern void debug_mutex_init(struct mutex *lock, const char *name,
struct lock_class_key *key);
-
-#define spin_lock_mutex(lock, flags) \
- do { \
- struct mutex *l = container_of(lock, struct mutex, wait_lock); \
- \
- DEBUG_LOCKS_WARN_ON(in_interrupt()); \
- local_irq_save(flags); \
- arch_spin_lock(&(lock)->rlock.raw_lock);\
- DEBUG_LOCKS_WARN_ON(l->magic != l); \
- } while (0)
-
-#define spin_unlock_mutex(lock, flags) \
- do { \
- arch_spin_unlock(&(lock)->rlock.raw_lock); \
- local_irq_restore(flags); \
- preempt_check_resched(); \
- } while (0)
diff --git a/kernel/locking/mutex.c b/kernel/locking/mutex.c
index 8464a5cbab97..ad2d9e22697b 100644
--- a/kernel/locking/mutex.c
+++ b/kernel/locking/mutex.c
@@ -50,16 +50,17 @@ EXPORT_SYMBOL(__mutex_init);
/*
* @owner: contains: 'struct task_struct *' to the current lock owner,
* NULL means not owned. Since task_struct pointers are aligned at
- * ARCH_MIN_TASKALIGN (which is at least sizeof(void *)), we have low
- * bits to store extra state.
+ * at least L1_CACHE_BYTES, we have low bits to store extra state.
*
* Bit0 indicates a non-empty waiter list; unlock must issue a wakeup.
* Bit1 indicates unlock needs to hand the lock to the top-waiter
+ * Bit2 indicates handoff has been done and we're waiting for pickup.
*/
#define MUTEX_FLAG_WAITERS 0x01
#define MUTEX_FLAG_HANDOFF 0x02
+#define MUTEX_FLAG_PICKUP 0x04
-#define MUTEX_FLAGS 0x03
+#define MUTEX_FLAGS 0x07
static inline struct task_struct *__owner_task(unsigned long owner)
{
@@ -72,38 +73,29 @@ static inline unsigned long __owner_flags(unsigned long owner)
}
/*
- * Actual trylock that will work on any unlocked state.
- *
- * When setting the owner field, we must preserve the low flag bits.
- *
- * Be careful with @handoff, only set that in a wait-loop (where you set
- * HANDOFF) to avoid recursive lock attempts.
+ * Trylock variant that retuns the owning task on failure.
*/
-static inline bool __mutex_trylock(struct mutex *lock, const bool handoff)
+static inline struct task_struct *__mutex_trylock_or_owner(struct mutex *lock)
{
unsigned long owner, curr = (unsigned long)current;
owner = atomic_long_read(&lock->owner);
for (;;) { /* must loop, can race against a flag */
unsigned long old, flags = __owner_flags(owner);
+ unsigned long task = owner & ~MUTEX_FLAGS;
- if (__owner_task(owner)) {
- if (handoff && unlikely(__owner_task(owner) == current)) {
- /*
- * Provide ACQUIRE semantics for the lock-handoff.
- *
- * We cannot easily use load-acquire here, since
- * the actual load is a failed cmpxchg, which
- * doesn't imply any barriers.
- *
- * Also, this is a fairly unlikely scenario, and
- * this contains the cost.
- */
- smp_mb(); /* ACQUIRE */
- return true;
- }
+ if (task) {
+ if (likely(task != curr))
+ break;
- return false;
+ if (likely(!(flags & MUTEX_FLAG_PICKUP)))
+ break;
+
+ flags &= ~MUTEX_FLAG_PICKUP;
+ } else {
+#ifdef CONFIG_DEBUG_MUTEXES
+ DEBUG_LOCKS_WARN_ON(flags & MUTEX_FLAG_PICKUP);
+#endif
}
/*
@@ -111,15 +103,24 @@ static inline bool __mutex_trylock(struct mutex *lock, const bool handoff)
* past the point where we acquire it. This would be possible
* if we (accidentally) set the bit on an unlocked mutex.
*/
- if (handoff)
- flags &= ~MUTEX_FLAG_HANDOFF;
+ flags &= ~MUTEX_FLAG_HANDOFF;
old = atomic_long_cmpxchg_acquire(&lock->owner, owner, curr | flags);
if (old == owner)
- return true;
+ return NULL;
owner = old;
}
+
+ return __owner_task(owner);
+}
+
+/*
+ * Actual trylock that will work on any unlocked state.
+ */
+static inline bool __mutex_trylock(struct mutex *lock)
+{
+ return !__mutex_trylock_or_owner(lock);
}
#ifndef CONFIG_DEBUG_LOCK_ALLOC
@@ -171,9 +172,9 @@ static inline bool __mutex_waiter_is_first(struct mutex *lock, struct mutex_wait
/*
* Give up ownership to a specific task, when @task = NULL, this is equivalent
- * to a regular unlock. Clears HANDOFF, preserves WAITERS. Provides RELEASE
- * semantics like a regular unlock, the __mutex_trylock() provides matching
- * ACQUIRE semantics for the handoff.
+ * to a regular unlock. Sets PICKUP on a handoff, clears HANDOF, preserves
+ * WAITERS. Provides RELEASE semantics like a regular unlock, the
+ * __mutex_trylock() provides a matching ACQUIRE semantics for the handoff.
*/
static void __mutex_handoff(struct mutex *lock, struct task_struct *task)
{
@@ -184,10 +185,13 @@ static void __mutex_handoff(struct mutex *lock, struct task_struct *task)
#ifdef CONFIG_DEBUG_MUTEXES
DEBUG_LOCKS_WARN_ON(__owner_task(owner) != current);
+ DEBUG_LOCKS_WARN_ON(owner & MUTEX_FLAG_PICKUP);
#endif
new = (owner & MUTEX_FLAG_WAITERS);
new |= (unsigned long)task;
+ if (task)
+ new |= MUTEX_FLAG_PICKUP;
old = atomic_long_cmpxchg_release(&lock->owner, owner, new);
if (old == owner)
@@ -237,8 +241,8 @@ void __sched mutex_lock(struct mutex *lock)
EXPORT_SYMBOL(mutex_lock);
#endif
-static __always_inline void ww_mutex_lock_acquired(struct ww_mutex *ww,
- struct ww_acquire_ctx *ww_ctx)
+static __always_inline void
+ww_mutex_lock_acquired(struct ww_mutex *ww, struct ww_acquire_ctx *ww_ctx)
{
#ifdef CONFIG_DEBUG_MUTEXES
/*
@@ -277,17 +281,50 @@ static __always_inline void ww_mutex_lock_acquired(struct ww_mutex *ww,
ww_ctx->acquired++;
}
+static inline bool __sched
+__ww_ctx_stamp_after(struct ww_acquire_ctx *a, struct ww_acquire_ctx *b)
+{
+ return a->stamp - b->stamp <= LONG_MAX &&
+ (a->stamp != b->stamp || a > b);
+}
+
+/*
+ * Wake up any waiters that may have to back off when the lock is held by the
+ * given context.
+ *
+ * Due to the invariants on the wait list, this can only affect the first
+ * waiter with a context.
+ *
+ * The current task must not be on the wait list.
+ */
+static void __sched
+__ww_mutex_wakeup_for_backoff(struct mutex *lock, struct ww_acquire_ctx *ww_ctx)
+{
+ struct mutex_waiter *cur;
+
+ lockdep_assert_held(&lock->wait_lock);
+
+ list_for_each_entry(cur, &lock->wait_list, list) {
+ if (!cur->ww_ctx)
+ continue;
+
+ if (cur->ww_ctx->acquired > 0 &&
+ __ww_ctx_stamp_after(cur->ww_ctx, ww_ctx)) {
+ debug_mutex_wake_waiter(lock, cur);
+ wake_up_process(cur->task);
+ }
+
+ break;
+ }
+}
+
/*
* After acquiring lock with fastpath or when we lost out in contested
* slowpath, set ctx and wake up any waiters so they can recheck.
*/
static __always_inline void
-ww_mutex_set_context_fastpath(struct ww_mutex *lock,
- struct ww_acquire_ctx *ctx)
+ww_mutex_set_context_fastpath(struct ww_mutex *lock, struct ww_acquire_ctx *ctx)
{
- unsigned long flags;
- struct mutex_waiter *cur;
-
ww_mutex_lock_acquired(lock, ctx);
lock->ctx = ctx;
@@ -311,46 +348,79 @@ ww_mutex_set_context_fastpath(struct ww_mutex *lock,
* Uh oh, we raced in fastpath, wake up everyone in this case,
* so they can see the new lock->ctx.
*/
- spin_lock_mutex(&lock->base.wait_lock, flags);
- list_for_each_entry(cur, &lock->base.wait_list, list) {
- debug_mutex_wake_waiter(&lock->base, cur);
- wake_up_process(cur->task);
- }
- spin_unlock_mutex(&lock->base.wait_lock, flags);
+ spin_lock(&lock->base.wait_lock);
+ __ww_mutex_wakeup_for_backoff(&lock->base, ctx);
+ spin_unlock(&lock->base.wait_lock);
}
/*
- * After acquiring lock in the slowpath set ctx and wake up any
- * waiters so they can recheck.
+ * After acquiring lock in the slowpath set ctx.
+ *
+ * Unlike for the fast path, the caller ensures that waiters are woken up where
+ * necessary.
*
* Callers must hold the mutex wait_lock.
*/
static __always_inline void
-ww_mutex_set_context_slowpath(struct ww_mutex *lock,
- struct ww_acquire_ctx *ctx)
+ww_mutex_set_context_slowpath(struct ww_mutex *lock, struct ww_acquire_ctx *ctx)
{
- struct mutex_waiter *cur;
-
ww_mutex_lock_acquired(lock, ctx);
lock->ctx = ctx;
+}
+
+#ifdef CONFIG_MUTEX_SPIN_ON_OWNER
+
+static inline
+bool ww_mutex_spin_on_owner(struct mutex *lock, struct ww_acquire_ctx *ww_ctx,
+ struct mutex_waiter *waiter)
+{
+ struct ww_mutex *ww;
+
+ ww = container_of(lock, struct ww_mutex, base);
/*
- * Give any possible sleeping processes the chance to wake up,
- * so they can recheck if they have to back off.
+ * If ww->ctx is set the contents are undefined, only
+ * by acquiring wait_lock there is a guarantee that
+ * they are not invalid when reading.
+ *
+ * As such, when deadlock detection needs to be
+ * performed the optimistic spinning cannot be done.
+ *
+ * Check this in every inner iteration because we may
+ * be racing against another thread's ww_mutex_lock.
*/
- list_for_each_entry(cur, &lock->base.wait_list, list) {
- debug_mutex_wake_waiter(&lock->base, cur);
- wake_up_process(cur->task);
- }
+ if (ww_ctx->acquired > 0 && READ_ONCE(ww->ctx))
+ return false;
+
+ /*
+ * If we aren't on the wait list yet, cancel the spin
+ * if there are waiters. We want to avoid stealing the
+ * lock from a waiter with an earlier stamp, since the
+ * other thread may already own a lock that we also
+ * need.
+ */
+ if (!waiter && (atomic_long_read(&lock->owner) & MUTEX_FLAG_WAITERS))
+ return false;
+
+ /*
+ * Similarly, stop spinning if we are no longer the
+ * first waiter.
+ */
+ if (waiter && !__mutex_waiter_is_first(lock, waiter))
+ return false;
+
+ return true;
}
-#ifdef CONFIG_MUTEX_SPIN_ON_OWNER
/*
- * Look out! "owner" is an entirely speculative pointer
- * access and not reliable.
+ * Look out! "owner" is an entirely speculative pointer access and not
+ * reliable.
+ *
+ * "noinline" so that this function shows up on perf profiles.
*/
static noinline
-bool mutex_spin_on_owner(struct mutex *lock, struct task_struct *owner)
+bool mutex_spin_on_owner(struct mutex *lock, struct task_struct *owner,
+ struct ww_acquire_ctx *ww_ctx, struct mutex_waiter *waiter)
{
bool ret = true;
@@ -373,6 +443,11 @@ bool mutex_spin_on_owner(struct mutex *lock, struct task_struct *owner)
break;
}
+ if (ww_ctx && !ww_mutex_spin_on_owner(lock, ww_ctx, waiter)) {
+ ret = false;
+ break;
+ }
+
cpu_relax();
}
rcu_read_unlock();
@@ -431,12 +506,10 @@ static inline int mutex_can_spin_on_owner(struct mutex *lock)
* with the spinner at the head of the OSQ, if present, until the owner is
* changed to itself.
*/
-static bool mutex_optimistic_spin(struct mutex *lock,
- struct ww_acquire_ctx *ww_ctx,
- const bool use_ww_ctx, const bool waiter)
+static __always_inline bool
+mutex_optimistic_spin(struct mutex *lock, struct ww_acquire_ctx *ww_ctx,
+ const bool use_ww_ctx, struct mutex_waiter *waiter)
{
- struct task_struct *task = current;
-
if (!waiter) {
/*
* The purpose of the mutex_can_spin_on_owner() function is
@@ -460,40 +533,17 @@ static bool mutex_optimistic_spin(struct mutex *lock,
for (;;) {
struct task_struct *owner;
- if (use_ww_ctx && ww_ctx->acquired > 0) {
- struct ww_mutex *ww;
-
- ww = container_of(lock, struct ww_mutex, base);
- /*
- * If ww->ctx is set the contents are undefined, only
- * by acquiring wait_lock there is a guarantee that
- * they are not invalid when reading.
- *
- * As such, when deadlock detection needs to be
- * performed the optimistic spinning cannot be done.
- */
- if (READ_ONCE(ww->ctx))
- goto fail_unlock;
- }
+ /* Try to acquire the mutex... */
+ owner = __mutex_trylock_or_owner(lock);
+ if (!owner)
+ break;
/*
- * If there's an owner, wait for it to either
+ * There's an owner, wait for it to either
* release the lock or go to sleep.
*/
- owner = __mutex_owner(lock);
- if (owner) {
- if (waiter && owner == task) {
- smp_mb(); /* ACQUIRE */
- break;
- }
-
- if (!mutex_spin_on_owner(lock, owner))
- goto fail_unlock;
- }
-
- /* Try to acquire the mutex if it is unlocked. */
- if (__mutex_trylock(lock, waiter))
- break;
+ if (!mutex_spin_on_owner(lock, owner, ww_ctx, waiter))
+ goto fail_unlock;
/*
* The cpu_relax() call is a compiler barrier which forces
@@ -532,9 +582,9 @@ fail:
return false;
}
#else
-static bool mutex_optimistic_spin(struct mutex *lock,
- struct ww_acquire_ctx *ww_ctx,
- const bool use_ww_ctx, const bool waiter)
+static __always_inline bool
+mutex_optimistic_spin(struct mutex *lock, struct ww_acquire_ctx *ww_ctx,
+ const bool use_ww_ctx, struct mutex_waiter *waiter)
{
return false;
}
@@ -594,23 +644,88 @@ void __sched ww_mutex_unlock(struct ww_mutex *lock)
EXPORT_SYMBOL(ww_mutex_unlock);
static inline int __sched
-__ww_mutex_lock_check_stamp(struct mutex *lock, struct ww_acquire_ctx *ctx)
+__ww_mutex_lock_check_stamp(struct mutex *lock, struct mutex_waiter *waiter,
+ struct ww_acquire_ctx *ctx)
{
struct ww_mutex *ww = container_of(lock, struct ww_mutex, base);
struct ww_acquire_ctx *hold_ctx = READ_ONCE(ww->ctx);
+ struct mutex_waiter *cur;
+
+ if (hold_ctx && __ww_ctx_stamp_after(ctx, hold_ctx))
+ goto deadlock;
- if (!hold_ctx)
+ /*
+ * If there is a waiter in front of us that has a context, then its
+ * stamp is earlier than ours and we must back off.
+ */
+ cur = waiter;
+ list_for_each_entry_continue_reverse(cur, &lock->wait_list, list) {
+ if (cur->ww_ctx)
+ goto deadlock;
+ }
+
+ return 0;
+
+deadlock:
+#ifdef CONFIG_DEBUG_MUTEXES
+ DEBUG_LOCKS_WARN_ON(ctx->contending_lock);
+ ctx->contending_lock = ww;
+#endif
+ return -EDEADLK;
+}
+
+static inline int __sched
+__ww_mutex_add_waiter(struct mutex_waiter *waiter,
+ struct mutex *lock,
+ struct ww_acquire_ctx *ww_ctx)
+{
+ struct mutex_waiter *cur;
+ struct list_head *pos;
+
+ if (!ww_ctx) {
+ list_add_tail(&waiter->list, &lock->wait_list);
return 0;
+ }
- if (ctx->stamp - hold_ctx->stamp <= LONG_MAX &&
- (ctx->stamp != hold_ctx->stamp || ctx > hold_ctx)) {
+ /*
+ * Add the waiter before the first waiter with a higher stamp.
+ * Waiters without a context are skipped to avoid starving
+ * them.
+ */
+ pos = &lock->wait_list;
+ list_for_each_entry_reverse(cur, &lock->wait_list, list) {
+ if (!cur->ww_ctx)
+ continue;
+
+ if (__ww_ctx_stamp_after(ww_ctx, cur->ww_ctx)) {
+ /* Back off immediately if necessary. */
+ if (ww_ctx->acquired > 0) {
#ifdef CONFIG_DEBUG_MUTEXES
- DEBUG_LOCKS_WARN_ON(ctx->contending_lock);
- ctx->contending_lock = ww;
+ struct ww_mutex *ww;
+
+ ww = container_of(lock, struct ww_mutex, base);
+ DEBUG_LOCKS_WARN_ON(ww_ctx->contending_lock);
+ ww_ctx->contending_lock = ww;
#endif
- return -EDEADLK;
+ return -EDEADLK;
+ }
+
+ break;
+ }
+
+ pos = &cur->list;
+
+ /*
+ * Wake up the waiter so that it gets a chance to back
+ * off.
+ */
+ if (cur->ww_ctx->acquired > 0) {
+ debug_mutex_wake_waiter(lock, cur);
+ wake_up_process(cur->task);
+ }
}
+ list_add_tail(&waiter->list, pos);
return 0;
}
@@ -622,15 +737,15 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass,
struct lockdep_map *nest_lock, unsigned long ip,
struct ww_acquire_ctx *ww_ctx, const bool use_ww_ctx)
{
- struct task_struct *task = current;
struct mutex_waiter waiter;
- unsigned long flags;
bool first = false;
struct ww_mutex *ww;
int ret;
- if (use_ww_ctx) {
- ww = container_of(lock, struct ww_mutex, base);
+ might_sleep();
+
+ ww = container_of(lock, struct ww_mutex, base);
+ if (use_ww_ctx && ww_ctx) {
if (unlikely(ww_ctx == READ_ONCE(ww->ctx)))
return -EALREADY;
}
@@ -638,36 +753,54 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass,
preempt_disable();
mutex_acquire_nest(&lock->dep_map, subclass, 0, nest_lock, ip);
- if (__mutex_trylock(lock, false) ||
- mutex_optimistic_spin(lock, ww_ctx, use_ww_ctx, false)) {
+ if (__mutex_trylock(lock) ||
+ mutex_optimistic_spin(lock, ww_ctx, use_ww_ctx, NULL)) {
/* got the lock, yay! */
lock_acquired(&lock->dep_map, ip);
- if (use_ww_ctx)
+ if (use_ww_ctx && ww_ctx)
ww_mutex_set_context_fastpath(ww, ww_ctx);
preempt_enable();
return 0;
}
- spin_lock_mutex(&lock->wait_lock, flags);
+ spin_lock(&lock->wait_lock);
/*
* After waiting to acquire the wait_lock, try again.
*/
- if (__mutex_trylock(lock, false))
+ if (__mutex_trylock(lock)) {
+ if (use_ww_ctx && ww_ctx)
+ __ww_mutex_wakeup_for_backoff(lock, ww_ctx);
+
goto skip_wait;
+ }
debug_mutex_lock_common(lock, &waiter);
- debug_mutex_add_waiter(lock, &waiter, task);
+ debug_mutex_add_waiter(lock, &waiter, current);
- /* add waiting tasks to the end of the waitqueue (FIFO): */
- list_add_tail(&waiter.list, &lock->wait_list);
- waiter.task = task;
+ lock_contended(&lock->dep_map, ip);
+
+ if (!use_ww_ctx) {
+ /* add waiting tasks to the end of the waitqueue (FIFO): */
+ list_add_tail(&waiter.list, &lock->wait_list);
+
+#ifdef CONFIG_DEBUG_MUTEXES
+ waiter.ww_ctx = MUTEX_POISON_WW_CTX;
+#endif
+ } else {
+ /* Add in stamp order, waking up waiters that must back off. */
+ ret = __ww_mutex_add_waiter(&waiter, lock, ww_ctx);
+ if (ret)
+ goto err_early_backoff;
+
+ waiter.ww_ctx = ww_ctx;
+ }
+
+ waiter.task = current;
if (__mutex_waiter_is_first(lock, &waiter))
__mutex_set_flag(lock, MUTEX_FLAG_WAITERS);
- lock_contended(&lock->dep_map, ip);
-
- set_task_state(task, state);
+ set_current_state(state);
for (;;) {
/*
* Once we hold wait_lock, we're serialized against
@@ -675,7 +808,7 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass,
* before testing the error conditions to make sure we pick up
* the handoff.
*/
- if (__mutex_trylock(lock, first))
+ if (__mutex_trylock(lock))
goto acquired;
/*
@@ -683,42 +816,47 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass,
* wait_lock. This ensures the lock cancellation is ordered
* against mutex_unlock() and wake-ups do not go missing.
*/
- if (unlikely(signal_pending_state(state, task))) {
+ if (unlikely(signal_pending_state(state, current))) {
ret = -EINTR;
goto err;
}
- if (use_ww_ctx && ww_ctx->acquired > 0) {
- ret = __ww_mutex_lock_check_stamp(lock, ww_ctx);
+ if (use_ww_ctx && ww_ctx && ww_ctx->acquired > 0) {
+ ret = __ww_mutex_lock_check_stamp(lock, &waiter, ww_ctx);
if (ret)
goto err;
}
- spin_unlock_mutex(&lock->wait_lock, flags);
+ spin_unlock(&lock->wait_lock);
schedule_preempt_disabled();
- if (!first && __mutex_waiter_is_first(lock, &waiter)) {
- first = true;
- __mutex_set_flag(lock, MUTEX_FLAG_HANDOFF);
+ /*
+ * ww_mutex needs to always recheck its position since its waiter
+ * list is not FIFO ordered.
+ */
+ if ((use_ww_ctx && ww_ctx) || !first) {
+ first = __mutex_waiter_is_first(lock, &waiter);
+ if (first)
+ __mutex_set_flag(lock, MUTEX_FLAG_HANDOFF);
}
- set_task_state(task, state);
+ set_current_state(state);
/*
* Here we order against unlock; we must either see it change
* state back to RUNNING and fall through the next schedule(),
* or we must see its unlock and acquire.
*/
- if ((first && mutex_optimistic_spin(lock, ww_ctx, use_ww_ctx, true)) ||
- __mutex_trylock(lock, first))
+ if (__mutex_trylock(lock) ||
+ (first && mutex_optimistic_spin(lock, ww_ctx, use_ww_ctx, &waiter)))
break;
- spin_lock_mutex(&lock->wait_lock, flags);
+ spin_lock(&lock->wait_lock);
}
- spin_lock_mutex(&lock->wait_lock, flags);
+ spin_lock(&lock->wait_lock);
acquired:
- __set_task_state(task, TASK_RUNNING);
+ __set_current_state(TASK_RUNNING);
- mutex_remove_waiter(lock, &waiter, task);
+ mutex_remove_waiter(lock, &waiter, current);
if (likely(list_empty(&lock->wait_list)))
__mutex_clear_flag(lock, MUTEX_FLAGS);
@@ -728,30 +866,44 @@ skip_wait:
/* got the lock - cleanup and rejoice! */
lock_acquired(&lock->dep_map, ip);
- if (use_ww_ctx)
+ if (use_ww_ctx && ww_ctx)
ww_mutex_set_context_slowpath(ww, ww_ctx);
- spin_unlock_mutex(&lock->wait_lock, flags);
+ spin_unlock(&lock->wait_lock);
preempt_enable();
return 0;
err:
- __set_task_state(task, TASK_RUNNING);
- mutex_remove_waiter(lock, &waiter, task);
- spin_unlock_mutex(&lock->wait_lock, flags);
+ __set_current_state(TASK_RUNNING);
+ mutex_remove_waiter(lock, &waiter, current);
+err_early_backoff:
+ spin_unlock(&lock->wait_lock);
debug_mutex_free_waiter(&waiter);
mutex_release(&lock->dep_map, 1, ip);
preempt_enable();
return ret;
}
+static int __sched
+__mutex_lock(struct mutex *lock, long state, unsigned int subclass,
+ struct lockdep_map *nest_lock, unsigned long ip)
+{
+ return __mutex_lock_common(lock, state, subclass, nest_lock, ip, NULL, false);
+}
+
+static int __sched
+__ww_mutex_lock(struct mutex *lock, long state, unsigned int subclass,
+ struct lockdep_map *nest_lock, unsigned long ip,
+ struct ww_acquire_ctx *ww_ctx)
+{
+ return __mutex_lock_common(lock, state, subclass, nest_lock, ip, ww_ctx, true);
+}
+
#ifdef CONFIG_DEBUG_LOCK_ALLOC
void __sched
mutex_lock_nested(struct mutex *lock, unsigned int subclass)
{
- might_sleep();
- __mutex_lock_common(lock, TASK_UNINTERRUPTIBLE,
- subclass, NULL, _RET_IP_, NULL, 0);
+ __mutex_lock(lock, TASK_UNINTERRUPTIBLE, subclass, NULL, _RET_IP_);
}
EXPORT_SYMBOL_GPL(mutex_lock_nested);
@@ -759,27 +911,21 @@ EXPORT_SYMBOL_GPL(mutex_lock_nested);
void __sched
_mutex_lock_nest_lock(struct mutex *lock, struct lockdep_map *nest)
{
- might_sleep();
- __mutex_lock_common(lock, TASK_UNINTERRUPTIBLE,
- 0, nest, _RET_IP_, NULL, 0);
+ __mutex_lock(lock, TASK_UNINTERRUPTIBLE, 0, nest, _RET_IP_);
}
EXPORT_SYMBOL_GPL(_mutex_lock_nest_lock);
int __sched
mutex_lock_killable_nested(struct mutex *lock, unsigned int subclass)
{
- might_sleep();
- return __mutex_lock_common(lock, TASK_KILLABLE,
- subclass, NULL, _RET_IP_, NULL, 0);
+ return __mutex_lock(lock, TASK_KILLABLE, subclass, NULL, _RET_IP_);
}
EXPORT_SYMBOL_GPL(mutex_lock_killable_nested);
int __sched
mutex_lock_interruptible_nested(struct mutex *lock, unsigned int subclass)
{
- might_sleep();
- return __mutex_lock_common(lock, TASK_INTERRUPTIBLE,
- subclass, NULL, _RET_IP_, NULL, 0);
+ return __mutex_lock(lock, TASK_INTERRUPTIBLE, subclass, NULL, _RET_IP_);
}
EXPORT_SYMBOL_GPL(mutex_lock_interruptible_nested);
@@ -824,35 +970,37 @@ ww_mutex_deadlock_injection(struct ww_mutex *lock, struct ww_acquire_ctx *ctx)
}
int __sched
-__ww_mutex_lock(struct ww_mutex *lock, struct ww_acquire_ctx *ctx)
+ww_mutex_lock(struct ww_mutex *lock, struct ww_acquire_ctx *ctx)
{
int ret;
might_sleep();
- ret = __mutex_lock_common(&lock->base, TASK_UNINTERRUPTIBLE,
- 0, &ctx->dep_map, _RET_IP_, ctx, 1);
- if (!ret && ctx->acquired > 1)
+ ret = __ww_mutex_lock(&lock->base, TASK_UNINTERRUPTIBLE,
+ 0, ctx ? &ctx->dep_map : NULL, _RET_IP_,
+ ctx);
+ if (!ret && ctx && ctx->acquired > 1)
return ww_mutex_deadlock_injection(lock, ctx);
return ret;
}
-EXPORT_SYMBOL_GPL(__ww_mutex_lock);
+EXPORT_SYMBOL_GPL(ww_mutex_lock);
int __sched
-__ww_mutex_lock_interruptible(struct ww_mutex *lock, struct ww_acquire_ctx *ctx)
+ww_mutex_lock_interruptible(struct ww_mutex *lock, struct ww_acquire_ctx *ctx)
{
int ret;
might_sleep();
- ret = __mutex_lock_common(&lock->base, TASK_INTERRUPTIBLE,
- 0, &ctx->dep_map, _RET_IP_, ctx, 1);
+ ret = __ww_mutex_lock(&lock->base, TASK_INTERRUPTIBLE,
+ 0, ctx ? &ctx->dep_map : NULL, _RET_IP_,
+ ctx);
- if (!ret && ctx->acquired > 1)
+ if (!ret && ctx && ctx->acquired > 1)
return ww_mutex_deadlock_injection(lock, ctx);
return ret;
}
-EXPORT_SYMBOL_GPL(__ww_mutex_lock_interruptible);
+EXPORT_SYMBOL_GPL(ww_mutex_lock_interruptible);
#endif
@@ -862,8 +1010,8 @@ EXPORT_SYMBOL_GPL(__ww_mutex_lock_interruptible);
static noinline void __sched __mutex_unlock_slowpath(struct mutex *lock, unsigned long ip)
{
struct task_struct *next = NULL;
- unsigned long owner, flags;
DEFINE_WAKE_Q(wake_q);
+ unsigned long owner;
mutex_release(&lock->dep_map, 1, ip);
@@ -880,6 +1028,7 @@ static noinline void __sched __mutex_unlock_slowpath(struct mutex *lock, unsigne
#ifdef CONFIG_DEBUG_MUTEXES
DEBUG_LOCKS_WARN_ON(__owner_task(owner) != current);
+ DEBUG_LOCKS_WARN_ON(owner & MUTEX_FLAG_PICKUP);
#endif
if (owner & MUTEX_FLAG_HANDOFF)
@@ -897,7 +1046,7 @@ static noinline void __sched __mutex_unlock_slowpath(struct mutex *lock, unsigne
owner = old;
}
- spin_lock_mutex(&lock->wait_lock, flags);
+ spin_lock(&lock->wait_lock);
debug_mutex_unlock(lock);
if (!list_empty(&lock->wait_list)) {
/* get the first entry from the wait-list: */
@@ -914,7 +1063,7 @@ static noinline void __sched __mutex_unlock_slowpath(struct mutex *lock, unsigne
if (owner & MUTEX_FLAG_HANDOFF)
__mutex_handoff(lock, next);
- spin_unlock_mutex(&lock->wait_lock, flags);
+ spin_unlock(&lock->wait_lock);
wake_up_q(&wake_q);
}
@@ -977,37 +1126,34 @@ EXPORT_SYMBOL_GPL(mutex_lock_io);
static noinline void __sched
__mutex_lock_slowpath(struct mutex *lock)
{
- __mutex_lock_common(lock, TASK_UNINTERRUPTIBLE, 0,
- NULL, _RET_IP_, NULL, 0);
+ __mutex_lock(lock, TASK_UNINTERRUPTIBLE, 0, NULL, _RET_IP_);
}
static noinline int __sched
__mutex_lock_killable_slowpath(struct mutex *lock)
{
- return __mutex_lock_common(lock, TASK_KILLABLE, 0,
- NULL, _RET_IP_, NULL, 0);
+ return __mutex_lock(lock, TASK_KILLABLE, 0, NULL, _RET_IP_);
}
static noinline int __sched
__mutex_lock_interruptible_slowpath(struct mutex *lock)
{
- return __mutex_lock_common(lock, TASK_INTERRUPTIBLE, 0,
- NULL, _RET_IP_, NULL, 0);
+ return __mutex_lock(lock, TASK_INTERRUPTIBLE, 0, NULL, _RET_IP_);
}
static noinline int __sched
__ww_mutex_lock_slowpath(struct ww_mutex *lock, struct ww_acquire_ctx *ctx)
{
- return __mutex_lock_common(&lock->base, TASK_UNINTERRUPTIBLE, 0,
- NULL, _RET_IP_, ctx, 1);
+ return __ww_mutex_lock(&lock->base, TASK_UNINTERRUPTIBLE, 0, NULL,
+ _RET_IP_, ctx);
}
static noinline int __sched
__ww_mutex_lock_interruptible_slowpath(struct ww_mutex *lock,
struct ww_acquire_ctx *ctx)
{
- return __mutex_lock_common(&lock->base, TASK_INTERRUPTIBLE, 0,
- NULL, _RET_IP_, ctx, 1);
+ return __ww_mutex_lock(&lock->base, TASK_INTERRUPTIBLE, 0, NULL,
+ _RET_IP_, ctx);
}
#endif
@@ -1028,7 +1174,7 @@ __ww_mutex_lock_interruptible_slowpath(struct ww_mutex *lock,
*/
int __sched mutex_trylock(struct mutex *lock)
{
- bool locked = __mutex_trylock(lock, false);
+ bool locked = __mutex_trylock(lock);
if (locked)
mutex_acquire(&lock->dep_map, 0, 1, _RET_IP_);
@@ -1039,32 +1185,34 @@ EXPORT_SYMBOL(mutex_trylock);
#ifndef CONFIG_DEBUG_LOCK_ALLOC
int __sched
-__ww_mutex_lock(struct ww_mutex *lock, struct ww_acquire_ctx *ctx)
+ww_mutex_lock(struct ww_mutex *lock, struct ww_acquire_ctx *ctx)
{
might_sleep();
if (__mutex_trylock_fast(&lock->base)) {
- ww_mutex_set_context_fastpath(lock, ctx);
+ if (ctx)
+ ww_mutex_set_context_fastpath(lock, ctx);
return 0;
}
return __ww_mutex_lock_slowpath(lock, ctx);
}
-EXPORT_SYMBOL(__ww_mutex_lock);
+EXPORT_SYMBOL(ww_mutex_lock);
int __sched
-__ww_mutex_lock_interruptible(struct ww_mutex *lock, struct ww_acquire_ctx *ctx)
+ww_mutex_lock_interruptible(struct ww_mutex *lock, struct ww_acquire_ctx *ctx)
{
might_sleep();
if (__mutex_trylock_fast(&lock->base)) {
- ww_mutex_set_context_fastpath(lock, ctx);
+ if (ctx)
+ ww_mutex_set_context_fastpath(lock, ctx);
return 0;
}
return __ww_mutex_lock_interruptible_slowpath(lock, ctx);
}
-EXPORT_SYMBOL(__ww_mutex_lock_interruptible);
+EXPORT_SYMBOL(ww_mutex_lock_interruptible);
#endif
diff --git a/kernel/locking/mutex.h b/kernel/locking/mutex.h
index 4410a4af42a3..6ebc1902f779 100644
--- a/kernel/locking/mutex.h
+++ b/kernel/locking/mutex.h
@@ -9,10 +9,6 @@
* !CONFIG_DEBUG_MUTEXES case. Most of them are NOPs:
*/
-#define spin_lock_mutex(lock, flags) \
- do { spin_lock(lock); (void)(flags); } while (0)
-#define spin_unlock_mutex(lock, flags) \
- do { spin_unlock(lock); (void)(flags); } while (0)
#define mutex_remove_waiter(lock, waiter, task) \
__list_del((waiter)->list.prev, (waiter)->list.next)
diff --git a/kernel/locking/percpu-rwsem.c b/kernel/locking/percpu-rwsem.c
index ce182599cf2e..883cf1b92d90 100644
--- a/kernel/locking/percpu-rwsem.c
+++ b/kernel/locking/percpu-rwsem.c
@@ -1,7 +1,6 @@
#include <linux/atomic.h>
#include <linux/rwsem.h>
#include <linux/percpu.h>
-#include <linux/wait.h>
#include <linux/lockdep.h>
#include <linux/percpu-rwsem.h>
#include <linux/rcupdate.h>
@@ -18,7 +17,7 @@ int __percpu_init_rwsem(struct percpu_rw_semaphore *sem,
/* ->rw_sem represents the whole percpu_rw_semaphore for lockdep */
rcu_sync_init(&sem->rss, RCU_SCHED_SYNC);
__init_rwsem(&sem->rw_sem, name, rwsem_key);
- init_waitqueue_head(&sem->writer);
+ rcuwait_init(&sem->writer);
sem->readers_block = 0;
return 0;
}
@@ -103,7 +102,7 @@ void __percpu_up_read(struct percpu_rw_semaphore *sem)
__this_cpu_dec(*sem->read_count);
/* Prod writer to recheck readers_active */
- wake_up(&sem->writer);
+ rcuwait_wake_up(&sem->writer);
}
EXPORT_SYMBOL_GPL(__percpu_up_read);
@@ -160,7 +159,7 @@ void percpu_down_write(struct percpu_rw_semaphore *sem)
*/
/* Wait for all now active readers to complete. */
- wait_event(sem->writer, readers_active_check(sem));
+ rcuwait_wait_event(&sem->writer, readers_active_check(sem));
}
EXPORT_SYMBOL_GPL(percpu_down_write);
diff --git a/kernel/locking/qspinlock_paravirt.h b/kernel/locking/qspinlock_paravirt.h
index e3b5520005db..e6b2f7ad3e51 100644
--- a/kernel/locking/qspinlock_paravirt.h
+++ b/kernel/locking/qspinlock_paravirt.h
@@ -263,7 +263,7 @@ pv_wait_early(struct pv_node *prev, int loop)
if ((loop & PV_PREV_CHECK_MASK) != 0)
return false;
- return READ_ONCE(prev->state) != vcpu_running;
+ return READ_ONCE(prev->state) != vcpu_running || vcpu_is_preempted(prev->cpu);
}
/*
diff --git a/kernel/locking/rtmutex.c b/kernel/locking/rtmutex.c
index 2f443ed2320a..d340be3a488f 100644
--- a/kernel/locking/rtmutex.c
+++ b/kernel/locking/rtmutex.c
@@ -1179,7 +1179,7 @@ __rt_mutex_slowlock(struct rt_mutex *lock, int state,
* TASK_INTERRUPTIBLE checks for signals and
* timeout. Ignored otherwise.
*/
- if (unlikely(state == TASK_INTERRUPTIBLE)) {
+ if (likely(state == TASK_INTERRUPTIBLE)) {
/* Signal pending? */
if (signal_pending(current))
ret = -EINTR;
diff --git a/kernel/locking/rwsem-spinlock.c b/kernel/locking/rwsem-spinlock.c
index 1591f6b3539f..5eacab880f67 100644
--- a/kernel/locking/rwsem-spinlock.c
+++ b/kernel/locking/rwsem-spinlock.c
@@ -128,7 +128,6 @@ __rwsem_wake_one_writer(struct rw_semaphore *sem)
void __sched __down_read(struct rw_semaphore *sem)
{
struct rwsem_waiter waiter;
- struct task_struct *tsk;
unsigned long flags;
raw_spin_lock_irqsave(&sem->wait_lock, flags);
@@ -140,13 +139,12 @@ void __sched __down_read(struct rw_semaphore *sem)
goto out;
}
- tsk = current;
- set_task_state(tsk, TASK_UNINTERRUPTIBLE);
+ set_current_state(TASK_UNINTERRUPTIBLE);
/* set up my own style of waitqueue */
- waiter.task = tsk;
+ waiter.task = current;
waiter.type = RWSEM_WAITING_FOR_READ;
- get_task_struct(tsk);
+ get_task_struct(current);
list_add_tail(&waiter.list, &sem->wait_list);
@@ -158,10 +156,10 @@ void __sched __down_read(struct rw_semaphore *sem)
if (!waiter.task)
break;
schedule();
- set_task_state(tsk, TASK_UNINTERRUPTIBLE);
+ set_current_state(TASK_UNINTERRUPTIBLE);
}
- __set_task_state(tsk, TASK_RUNNING);
+ __set_current_state(TASK_RUNNING);
out:
;
}
@@ -194,15 +192,13 @@ int __down_read_trylock(struct rw_semaphore *sem)
int __sched __down_write_common(struct rw_semaphore *sem, int state)
{
struct rwsem_waiter waiter;
- struct task_struct *tsk;
unsigned long flags;
int ret = 0;
raw_spin_lock_irqsave(&sem->wait_lock, flags);
/* set up my own style of waitqueue */
- tsk = current;
- waiter.task = tsk;
+ waiter.task = current;
waiter.type = RWSEM_WAITING_FOR_WRITE;
list_add_tail(&waiter.list, &sem->wait_list);
@@ -220,7 +216,7 @@ int __sched __down_write_common(struct rw_semaphore *sem, int state)
ret = -EINTR;
goto out;
}
- set_task_state(tsk, state);
+ set_current_state(state);
raw_spin_unlock_irqrestore(&sem->wait_lock, flags);
schedule();
raw_spin_lock_irqsave(&sem->wait_lock, flags);
diff --git a/kernel/locking/rwsem-xadd.c b/kernel/locking/rwsem-xadd.c
index 631506004f9e..2ad8d8dc3bb1 100644
--- a/kernel/locking/rwsem-xadd.c
+++ b/kernel/locking/rwsem-xadd.c
@@ -224,10 +224,9 @@ struct rw_semaphore __sched *rwsem_down_read_failed(struct rw_semaphore *sem)
{
long count, adjustment = -RWSEM_ACTIVE_READ_BIAS;
struct rwsem_waiter waiter;
- struct task_struct *tsk = current;
DEFINE_WAKE_Q(wake_q);
- waiter.task = tsk;
+ waiter.task = current;
waiter.type = RWSEM_WAITING_FOR_READ;
raw_spin_lock_irq(&sem->wait_lock);
@@ -254,13 +253,13 @@ struct rw_semaphore __sched *rwsem_down_read_failed(struct rw_semaphore *sem)
/* wait to be given the lock */
while (true) {
- set_task_state(tsk, TASK_UNINTERRUPTIBLE);
+ set_current_state(TASK_UNINTERRUPTIBLE);
if (!waiter.task)
break;
schedule();
}
- __set_task_state(tsk, TASK_RUNNING);
+ __set_current_state(TASK_RUNNING);
return sem;
}
EXPORT_SYMBOL(rwsem_down_read_failed);
@@ -503,8 +502,6 @@ __rwsem_down_write_failed_common(struct rw_semaphore *sem, int state)
* wake any read locks that were queued ahead of us.
*/
if (count > RWSEM_WAITING_BIAS) {
- DEFINE_WAKE_Q(wake_q);
-
__rwsem_mark_wake(sem, RWSEM_WAKE_READERS, &wake_q);
/*
* The wakeup is normally called _after_ the wait_lock
@@ -514,6 +511,11 @@ __rwsem_down_write_failed_common(struct rw_semaphore *sem, int state)
* for attempting rwsem_try_write_lock().
*/
wake_up_q(&wake_q);
+
+ /*
+ * Reinitialize wake_q after use.
+ */
+ wake_q_init(&wake_q);
}
} else
diff --git a/kernel/locking/semaphore.c b/kernel/locking/semaphore.c
index b8120abe594b..9512e37637dc 100644
--- a/kernel/locking/semaphore.c
+++ b/kernel/locking/semaphore.c
@@ -204,19 +204,18 @@ struct semaphore_waiter {
static inline int __sched __down_common(struct semaphore *sem, long state,
long timeout)
{
- struct task_struct *task = current;
struct semaphore_waiter waiter;
list_add_tail(&waiter.list, &sem->wait_list);
- waiter.task = task;
+ waiter.task = current;
waiter.up = false;
for (;;) {
- if (signal_pending_state(state, task))
+ if (signal_pending_state(state, current))
goto interrupted;
if (unlikely(timeout <= 0))
goto timed_out;
- __set_task_state(task, state);
+ __set_current_state(state);
raw_spin_unlock_irq(&sem->lock);
timeout = schedule_timeout(timeout);
raw_spin_lock_irq(&sem->lock);
diff --git a/kernel/locking/spinlock.c b/kernel/locking/spinlock.c
index db3ccb1dd614..4b082b5cac9e 100644
--- a/kernel/locking/spinlock.c
+++ b/kernel/locking/spinlock.c
@@ -363,14 +363,6 @@ void __lockfunc _raw_spin_lock_nested(raw_spinlock_t *lock, int subclass)
}
EXPORT_SYMBOL(_raw_spin_lock_nested);
-void __lockfunc _raw_spin_lock_bh_nested(raw_spinlock_t *lock, int subclass)
-{
- __local_bh_disable_ip(_RET_IP_, SOFTIRQ_LOCK_OFFSET);
- spin_acquire(&lock->dep_map, subclass, 0, _RET_IP_);
- LOCK_CONTENDED(lock, do_raw_spin_trylock, do_raw_spin_lock);
-}
-EXPORT_SYMBOL(_raw_spin_lock_bh_nested);
-
unsigned long __lockfunc _raw_spin_lock_irqsave_nested(raw_spinlock_t *lock,
int subclass)
{
diff --git a/kernel/locking/spinlock_debug.c b/kernel/locking/spinlock_debug.c
index 0374a596cffa..9aa0fccd5d43 100644
--- a/kernel/locking/spinlock_debug.c
+++ b/kernel/locking/spinlock_debug.c
@@ -103,38 +103,14 @@ static inline void debug_spin_unlock(raw_spinlock_t *lock)
lock->owner_cpu = -1;
}
-static void __spin_lock_debug(raw_spinlock_t *lock)
-{
- u64 i;
- u64 loops = loops_per_jiffy * HZ;
-
- for (i = 0; i < loops; i++) {
- if (arch_spin_trylock(&lock->raw_lock))
- return;
- __delay(1);
- }
- /* lockup suspected: */
- spin_dump(lock, "lockup suspected");
-#ifdef CONFIG_SMP
- trigger_all_cpu_backtrace();
-#endif
-
- /*
- * The trylock above was causing a livelock. Give the lower level arch
- * specific lock code a chance to acquire the lock. We have already
- * printed a warning/backtrace at this point. The non-debug arch
- * specific code might actually succeed in acquiring the lock. If it is
- * not successful, the end-result is the same - there is no forward
- * progress.
- */
- arch_spin_lock(&lock->raw_lock);
-}
-
+/*
+ * We are now relying on the NMI watchdog to detect lockup instead of doing
+ * the detection here with an unfair lock which can cause problem of its own.
+ */
void do_raw_spin_lock(raw_spinlock_t *lock)
{
debug_spin_lock_before(lock);
- if (unlikely(!arch_spin_trylock(&lock->raw_lock)))
- __spin_lock_debug(lock);
+ arch_spin_lock(&lock->raw_lock);
debug_spin_lock_after(lock);
}
@@ -172,32 +148,6 @@ static void rwlock_bug(rwlock_t *lock, const char *msg)
#define RWLOCK_BUG_ON(cond, lock, msg) if (unlikely(cond)) rwlock_bug(lock, msg)
-#if 0 /* __write_lock_debug() can lock up - maybe this can too? */
-static void __read_lock_debug(rwlock_t *lock)
-{
- u64 i;
- u64 loops = loops_per_jiffy * HZ;
- int print_once = 1;
-
- for (;;) {
- for (i = 0; i < loops; i++) {
- if (arch_read_trylock(&lock->raw_lock))
- return;
- __delay(1);
- }
- /* lockup suspected: */
- if (print_once) {
- print_once = 0;
- printk(KERN_EMERG "BUG: read-lock lockup on CPU#%d, "
- "%s/%d, %p\n",
- raw_smp_processor_id(), current->comm,
- current->pid, lock);
- dump_stack();
- }
- }
-}
-#endif
-
void do_raw_read_lock(rwlock_t *lock)
{
RWLOCK_BUG_ON(lock->magic != RWLOCK_MAGIC, lock, "bad magic");
@@ -247,32 +197,6 @@ static inline void debug_write_unlock(rwlock_t *lock)
lock->owner_cpu = -1;
}
-#if 0 /* This can cause lockups */
-static void __write_lock_debug(rwlock_t *lock)
-{
- u64 i;
- u64 loops = loops_per_jiffy * HZ;
- int print_once = 1;
-
- for (;;) {
- for (i = 0; i < loops; i++) {
- if (arch_write_trylock(&lock->raw_lock))
- return;
- __delay(1);
- }
- /* lockup suspected: */
- if (print_once) {
- print_once = 0;
- printk(KERN_EMERG "BUG: write-lock lockup on CPU#%d, "
- "%s/%d, %p\n",
- raw_smp_processor_id(), current->comm,
- current->pid, lock);
- dump_stack();
- }
- }
-}
-#endif
-
void do_raw_write_lock(rwlock_t *lock)
{
debug_write_lock_before(lock);
diff --git a/kernel/locking/test-ww_mutex.c b/kernel/locking/test-ww_mutex.c
new file mode 100644
index 000000000000..da6c9a34f62f
--- /dev/null
+++ b/kernel/locking/test-ww_mutex.c
@@ -0,0 +1,646 @@
+/*
+ * Module-based API test facility for ww_mutexes
+ *
+ * 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.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, you can access it online at
+ * http://www.gnu.org/licenses/gpl-2.0.html.
+ */
+
+#include <linux/kernel.h>
+
+#include <linux/completion.h>
+#include <linux/delay.h>
+#include <linux/kthread.h>
+#include <linux/module.h>
+#include <linux/random.h>
+#include <linux/slab.h>
+#include <linux/ww_mutex.h>
+
+static DEFINE_WW_CLASS(ww_class);
+struct workqueue_struct *wq;
+
+struct test_mutex {
+ struct work_struct work;
+ struct ww_mutex mutex;
+ struct completion ready, go, done;
+ unsigned int flags;
+};
+
+#define TEST_MTX_SPIN BIT(0)
+#define TEST_MTX_TRY BIT(1)
+#define TEST_MTX_CTX BIT(2)
+#define __TEST_MTX_LAST BIT(3)
+
+static void test_mutex_work(struct work_struct *work)
+{
+ struct test_mutex *mtx = container_of(work, typeof(*mtx), work);
+
+ complete(&mtx->ready);
+ wait_for_completion(&mtx->go);
+
+ if (mtx->flags & TEST_MTX_TRY) {
+ while (!ww_mutex_trylock(&mtx->mutex))
+ cpu_relax();
+ } else {
+ ww_mutex_lock(&mtx->mutex, NULL);
+ }
+ complete(&mtx->done);
+ ww_mutex_unlock(&mtx->mutex);
+}
+
+static int __test_mutex(unsigned int flags)
+{
+#define TIMEOUT (HZ / 16)
+ struct test_mutex mtx;
+ struct ww_acquire_ctx ctx;
+ int ret;
+
+ ww_mutex_init(&mtx.mutex, &ww_class);
+ ww_acquire_init(&ctx, &ww_class);
+
+ INIT_WORK_ONSTACK(&mtx.work, test_mutex_work);
+ init_completion(&mtx.ready);
+ init_completion(&mtx.go);
+ init_completion(&mtx.done);
+ mtx.flags = flags;
+
+ schedule_work(&mtx.work);
+
+ wait_for_completion(&mtx.ready);
+ ww_mutex_lock(&mtx.mutex, (flags & TEST_MTX_CTX) ? &ctx : NULL);
+ complete(&mtx.go);
+ if (flags & TEST_MTX_SPIN) {
+ unsigned long timeout = jiffies + TIMEOUT;
+
+ ret = 0;
+ do {
+ if (completion_done(&mtx.done)) {
+ ret = -EINVAL;
+ break;
+ }
+ cpu_relax();
+ } while (time_before(jiffies, timeout));
+ } else {
+ ret = wait_for_completion_timeout(&mtx.done, TIMEOUT);
+ }
+ ww_mutex_unlock(&mtx.mutex);
+ ww_acquire_fini(&ctx);
+
+ if (ret) {
+ pr_err("%s(flags=%x): mutual exclusion failure\n",
+ __func__, flags);
+ ret = -EINVAL;
+ }
+
+ flush_work(&mtx.work);
+ destroy_work_on_stack(&mtx.work);
+ return ret;
+#undef TIMEOUT
+}
+
+static int test_mutex(void)
+{
+ int ret;
+ int i;
+
+ for (i = 0; i < __TEST_MTX_LAST; i++) {
+ ret = __test_mutex(i);
+ if (ret)
+ return ret;
+ }
+
+ return 0;
+}
+
+static int test_aa(void)
+{
+ struct ww_mutex mutex;
+ struct ww_acquire_ctx ctx;
+ int ret;
+
+ ww_mutex_init(&mutex, &ww_class);
+ ww_acquire_init(&ctx, &ww_class);
+
+ ww_mutex_lock(&mutex, &ctx);
+
+ if (ww_mutex_trylock(&mutex)) {
+ pr_err("%s: trylocked itself!\n", __func__);
+ ww_mutex_unlock(&mutex);
+ ret = -EINVAL;
+ goto out;
+ }
+
+ ret = ww_mutex_lock(&mutex, &ctx);
+ if (ret != -EALREADY) {
+ pr_err("%s: missed deadlock for recursing, ret=%d\n",
+ __func__, ret);
+ if (!ret)
+ ww_mutex_unlock(&mutex);
+ ret = -EINVAL;
+ goto out;
+ }
+
+ ret = 0;
+out:
+ ww_mutex_unlock(&mutex);
+ ww_acquire_fini(&ctx);
+ return ret;
+}
+
+struct test_abba {
+ struct work_struct work;
+ struct ww_mutex a_mutex;
+ struct ww_mutex b_mutex;
+ struct completion a_ready;
+ struct completion b_ready;
+ bool resolve;
+ int result;
+};
+
+static void test_abba_work(struct work_struct *work)
+{
+ struct test_abba *abba = container_of(work, typeof(*abba), work);
+ struct ww_acquire_ctx ctx;
+ int err;
+
+ ww_acquire_init(&ctx, &ww_class);
+ ww_mutex_lock(&abba->b_mutex, &ctx);
+
+ complete(&abba->b_ready);
+ wait_for_completion(&abba->a_ready);
+
+ err = ww_mutex_lock(&abba->a_mutex, &ctx);
+ if (abba->resolve && err == -EDEADLK) {
+ ww_mutex_unlock(&abba->b_mutex);
+ ww_mutex_lock_slow(&abba->a_mutex, &ctx);
+ err = ww_mutex_lock(&abba->b_mutex, &ctx);
+ }
+
+ if (!err)
+ ww_mutex_unlock(&abba->a_mutex);
+ ww_mutex_unlock(&abba->b_mutex);
+ ww_acquire_fini(&ctx);
+
+ abba->result = err;
+}
+
+static int test_abba(bool resolve)
+{
+ struct test_abba abba;
+ struct ww_acquire_ctx ctx;
+ int err, ret;
+
+ ww_mutex_init(&abba.a_mutex, &ww_class);
+ ww_mutex_init(&abba.b_mutex, &ww_class);
+ INIT_WORK_ONSTACK(&abba.work, test_abba_work);
+ init_completion(&abba.a_ready);
+ init_completion(&abba.b_ready);
+ abba.resolve = resolve;
+
+ schedule_work(&abba.work);
+
+ ww_acquire_init(&ctx, &ww_class);
+ ww_mutex_lock(&abba.a_mutex, &ctx);
+
+ complete(&abba.a_ready);
+ wait_for_completion(&abba.b_ready);
+
+ err = ww_mutex_lock(&abba.b_mutex, &ctx);
+ if (resolve && err == -EDEADLK) {
+ ww_mutex_unlock(&abba.a_mutex);
+ ww_mutex_lock_slow(&abba.b_mutex, &ctx);
+ err = ww_mutex_lock(&abba.a_mutex, &ctx);
+ }
+
+ if (!err)
+ ww_mutex_unlock(&abba.b_mutex);
+ ww_mutex_unlock(&abba.a_mutex);
+ ww_acquire_fini(&ctx);
+
+ flush_work(&abba.work);
+ destroy_work_on_stack(&abba.work);
+
+ ret = 0;
+ if (resolve) {
+ if (err || abba.result) {
+ pr_err("%s: failed to resolve ABBA deadlock, A err=%d, B err=%d\n",
+ __func__, err, abba.result);
+ ret = -EINVAL;
+ }
+ } else {
+ if (err != -EDEADLK && abba.result != -EDEADLK) {
+ pr_err("%s: missed ABBA deadlock, A err=%d, B err=%d\n",
+ __func__, err, abba.result);
+ ret = -EINVAL;
+ }
+ }
+ return ret;
+}
+
+struct test_cycle {
+ struct work_struct work;
+ struct ww_mutex a_mutex;
+ struct ww_mutex *b_mutex;
+ struct completion *a_signal;
+ struct completion b_signal;
+ int result;
+};
+
+static void test_cycle_work(struct work_struct *work)
+{
+ struct test_cycle *cycle = container_of(work, typeof(*cycle), work);
+ struct ww_acquire_ctx ctx;
+ int err;
+
+ ww_acquire_init(&ctx, &ww_class);
+ ww_mutex_lock(&cycle->a_mutex, &ctx);
+
+ complete(cycle->a_signal);
+ wait_for_completion(&cycle->b_signal);
+
+ err = ww_mutex_lock(cycle->b_mutex, &ctx);
+ if (err == -EDEADLK) {
+ ww_mutex_unlock(&cycle->a_mutex);
+ ww_mutex_lock_slow(cycle->b_mutex, &ctx);
+ err = ww_mutex_lock(&cycle->a_mutex, &ctx);
+ }
+
+ if (!err)
+ ww_mutex_unlock(cycle->b_mutex);
+ ww_mutex_unlock(&cycle->a_mutex);
+ ww_acquire_fini(&ctx);
+
+ cycle->result = err;
+}
+
+static int __test_cycle(unsigned int nthreads)
+{
+ struct test_cycle *cycles;
+ unsigned int n, last = nthreads - 1;
+ int ret;
+
+ cycles = kmalloc_array(nthreads, sizeof(*cycles), GFP_KERNEL);
+ if (!cycles)
+ return -ENOMEM;
+
+ for (n = 0; n < nthreads; n++) {
+ struct test_cycle *cycle = &cycles[n];
+
+ ww_mutex_init(&cycle->a_mutex, &ww_class);
+ if (n == last)
+ cycle->b_mutex = &cycles[0].a_mutex;
+ else
+ cycle->b_mutex = &cycles[n + 1].a_mutex;
+
+ if (n == 0)
+ cycle->a_signal = &cycles[last].b_signal;
+ else
+ cycle->a_signal = &cycles[n - 1].b_signal;
+ init_completion(&cycle->b_signal);
+
+ INIT_WORK(&cycle->work, test_cycle_work);
+ cycle->result = 0;
+ }
+
+ for (n = 0; n < nthreads; n++)
+ queue_work(wq, &cycles[n].work);
+
+ flush_workqueue(wq);
+
+ ret = 0;
+ for (n = 0; n < nthreads; n++) {
+ struct test_cycle *cycle = &cycles[n];
+
+ if (!cycle->result)
+ continue;
+
+ pr_err("cylic deadlock not resolved, ret[%d/%d] = %d\n",
+ n, nthreads, cycle->result);
+ ret = -EINVAL;
+ break;
+ }
+
+ for (n = 0; n < nthreads; n++)
+ ww_mutex_destroy(&cycles[n].a_mutex);
+ kfree(cycles);
+ return ret;
+}
+
+static int test_cycle(unsigned int ncpus)
+{
+ unsigned int n;
+ int ret;
+
+ for (n = 2; n <= ncpus + 1; n++) {
+ ret = __test_cycle(n);
+ if (ret)
+ return ret;
+ }
+
+ return 0;
+}
+
+struct stress {
+ struct work_struct work;
+ struct ww_mutex *locks;
+ int nlocks;
+ int nloops;
+};
+
+static int *get_random_order(int count)
+{
+ int *order;
+ int n, r, tmp;
+
+ order = kmalloc_array(count, sizeof(*order), GFP_TEMPORARY);
+ if (!order)
+ return order;
+
+ for (n = 0; n < count; n++)
+ order[n] = n;
+
+ for (n = count - 1; n > 1; n--) {
+ r = get_random_int() % (n + 1);
+ if (r != n) {
+ tmp = order[n];
+ order[n] = order[r];
+ order[r] = tmp;
+ }
+ }
+
+ return order;
+}
+
+static void dummy_load(struct stress *stress)
+{
+ usleep_range(1000, 2000);
+}
+
+static void stress_inorder_work(struct work_struct *work)
+{
+ struct stress *stress = container_of(work, typeof(*stress), work);
+ const int nlocks = stress->nlocks;
+ struct ww_mutex *locks = stress->locks;
+ struct ww_acquire_ctx ctx;
+ int *order;
+
+ order = get_random_order(nlocks);
+ if (!order)
+ return;
+
+ ww_acquire_init(&ctx, &ww_class);
+
+ do {
+ int contended = -1;
+ int n, err;
+
+retry:
+ err = 0;
+ for (n = 0; n < nlocks; n++) {
+ if (n == contended)
+ continue;
+
+ err = ww_mutex_lock(&locks[order[n]], &ctx);
+ if (err < 0)
+ break;
+ }
+ if (!err)
+ dummy_load(stress);
+
+ if (contended > n)
+ ww_mutex_unlock(&locks[order[contended]]);
+ contended = n;
+ while (n--)
+ ww_mutex_unlock(&locks[order[n]]);
+
+ if (err == -EDEADLK) {
+ ww_mutex_lock_slow(&locks[order[contended]], &ctx);
+ goto retry;
+ }
+
+ if (err) {
+ pr_err_once("stress (%s) failed with %d\n",
+ __func__, err);
+ break;
+ }
+ } while (--stress->nloops);
+
+ ww_acquire_fini(&ctx);
+
+ kfree(order);
+ kfree(stress);
+}
+
+struct reorder_lock {
+ struct list_head link;
+ struct ww_mutex *lock;
+};
+
+static void stress_reorder_work(struct work_struct *work)
+{
+ struct stress *stress = container_of(work, typeof(*stress), work);
+ LIST_HEAD(locks);
+ struct ww_acquire_ctx ctx;
+ struct reorder_lock *ll, *ln;
+ int *order;
+ int n, err;
+
+ order = get_random_order(stress->nlocks);
+ if (!order)
+ return;
+
+ for (n = 0; n < stress->nlocks; n++) {
+ ll = kmalloc(sizeof(*ll), GFP_KERNEL);
+ if (!ll)
+ goto out;
+
+ ll->lock = &stress->locks[order[n]];
+ list_add(&ll->link, &locks);
+ }
+ kfree(order);
+ order = NULL;
+
+ ww_acquire_init(&ctx, &ww_class);
+
+ do {
+ list_for_each_entry(ll, &locks, link) {
+ err = ww_mutex_lock(ll->lock, &ctx);
+ if (!err)
+ continue;
+
+ ln = ll;
+ list_for_each_entry_continue_reverse(ln, &locks, link)
+ ww_mutex_unlock(ln->lock);
+
+ if (err != -EDEADLK) {
+ pr_err_once("stress (%s) failed with %d\n",
+ __func__, err);
+ break;
+ }
+
+ ww_mutex_lock_slow(ll->lock, &ctx);
+ list_move(&ll->link, &locks); /* restarts iteration */
+ }
+
+ dummy_load(stress);
+ list_for_each_entry(ll, &locks, link)
+ ww_mutex_unlock(ll->lock);
+ } while (--stress->nloops);
+
+ ww_acquire_fini(&ctx);
+
+out:
+ list_for_each_entry_safe(ll, ln, &locks, link)
+ kfree(ll);
+ kfree(order);
+ kfree(stress);
+}
+
+static void stress_one_work(struct work_struct *work)
+{
+ struct stress *stress = container_of(work, typeof(*stress), work);
+ const int nlocks = stress->nlocks;
+ struct ww_mutex *lock = stress->locks + (get_random_int() % nlocks);
+ int err;
+
+ do {
+ err = ww_mutex_lock(lock, NULL);
+ if (!err) {
+ dummy_load(stress);
+ ww_mutex_unlock(lock);
+ } else {
+ pr_err_once("stress (%s) failed with %d\n",
+ __func__, err);
+ break;
+ }
+ } while (--stress->nloops);
+
+ kfree(stress);
+}
+
+#define STRESS_INORDER BIT(0)
+#define STRESS_REORDER BIT(1)
+#define STRESS_ONE BIT(2)
+#define STRESS_ALL (STRESS_INORDER | STRESS_REORDER | STRESS_ONE)
+
+static int stress(int nlocks, int nthreads, int nloops, unsigned int flags)
+{
+ struct ww_mutex *locks;
+ int n;
+
+ locks = kmalloc_array(nlocks, sizeof(*locks), GFP_KERNEL);
+ if (!locks)
+ return -ENOMEM;
+
+ for (n = 0; n < nlocks; n++)
+ ww_mutex_init(&locks[n], &ww_class);
+
+ for (n = 0; nthreads; n++) {
+ struct stress *stress;
+ void (*fn)(struct work_struct *work);
+
+ fn = NULL;
+ switch (n & 3) {
+ case 0:
+ if (flags & STRESS_INORDER)
+ fn = stress_inorder_work;
+ break;
+ case 1:
+ if (flags & STRESS_REORDER)
+ fn = stress_reorder_work;
+ break;
+ case 2:
+ if (flags & STRESS_ONE)
+ fn = stress_one_work;
+ break;
+ }
+
+ if (!fn)
+ continue;
+
+ stress = kmalloc(sizeof(*stress), GFP_KERNEL);
+ if (!stress)
+ break;
+
+ INIT_WORK(&stress->work, fn);
+ stress->locks = locks;
+ stress->nlocks = nlocks;
+ stress->nloops = nloops;
+
+ queue_work(wq, &stress->work);
+ nthreads--;
+ }
+
+ flush_workqueue(wq);
+
+ for (n = 0; n < nlocks; n++)
+ ww_mutex_destroy(&locks[n]);
+ kfree(locks);
+
+ return 0;
+}
+
+static int __init test_ww_mutex_init(void)
+{
+ int ncpus = num_online_cpus();
+ int ret;
+
+ wq = alloc_workqueue("test-ww_mutex", WQ_UNBOUND, 0);
+ if (!wq)
+ return -ENOMEM;
+
+ ret = test_mutex();
+ if (ret)
+ return ret;
+
+ ret = test_aa();
+ if (ret)
+ return ret;
+
+ ret = test_abba(false);
+ if (ret)
+ return ret;
+
+ ret = test_abba(true);
+ if (ret)
+ return ret;
+
+ ret = test_cycle(ncpus);
+ if (ret)
+ return ret;
+
+ ret = stress(16, 2*ncpus, 1<<10, STRESS_INORDER);
+ if (ret)
+ return ret;
+
+ ret = stress(16, 2*ncpus, 1<<10, STRESS_REORDER);
+ if (ret)
+ return ret;
+
+ ret = stress(4096, hweight32(STRESS_ALL)*ncpus, 1<<12, STRESS_ALL);
+ if (ret)
+ return ret;
+
+ return 0;
+}
+
+static void __exit test_ww_mutex_exit(void)
+{
+ destroy_workqueue(wq);
+}
+
+module_init(test_ww_mutex_init);
+module_exit(test_ww_mutex_exit);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Intel Corporation");
diff --git a/kernel/pid.c b/kernel/pid.c
index f66162f2359b..0291804151b5 100644
--- a/kernel/pid.c
+++ b/kernel/pid.c
@@ -68,9 +68,7 @@ static inline int mk_pid(struct pid_namespace *pid_ns,
* the scheme scales to up to 4 million PIDs, runtime.
*/
struct pid_namespace init_pid_ns = {
- .kref = {
- .refcount = ATOMIC_INIT(2),
- },
+ .kref = KREF_INIT(2),
.pidmap = {
[ 0 ... PIDMAP_ENTRIES-1] = { ATOMIC_INIT(BITS_PER_PAGE), NULL }
},