mutex: Add support for wound/wait style locks

Wound/wait mutexes are used when other multiple lock
acquisitions of a similar type can be done in an arbitrary
order. The deadlock handling used here is called wait/wound in
the RDBMS literature: The older tasks waits until it can acquire
the contended lock. The younger tasks needs to back off and drop
all the locks it is currently holding, i.e. the younger task is
wounded.

For full documentation please read Documentation/ww-mutex-design.txt.

References: https://lwn.net/Articles/548909/
Signed-off-by: Maarten Lankhorst <maarten.lankhorst@canonical.com>
Acked-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Acked-by: Rob Clark <robdclark@gmail.com>
Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: dri-devel@lists.freedesktop.org
Cc: linaro-mm-sig@lists.linaro.org
Cc: rostedt@goodmis.org
Cc: daniel@ffwll.ch
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/51C8038C.9000106@canonical.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>

1 files changed, 302 insertions, 16 deletions

diff --git a/kernel/mutex.c b/kernel/mutex.c
index 42f8dda2467b..fc801aafe8fd 100644
--- a/kernel/mutex.c
+++ b/kernel/mutex.c
@@ -254,16 +254,165 @@ void __sched mutex_unlock(struct mutex *lock)
 
 EXPORT_SYMBOL(mutex_unlock);
 
+/**
+ * ww_mutex_unlock - release the w/w mutex
+ * @lock: the mutex to be released
+ *
+ * Unlock a mutex that has been locked by this task previously with any of the
+ * ww_mutex_lock* functions (with or without an acquire context). It is
+ * forbidden to release the locks after releasing the acquire context.
+ *
+ * This function must not be used in interrupt context. Unlocking
+ * of a unlocked mutex is not allowed.
+ */
+void __sched ww_mutex_unlock(struct ww_mutex *lock)
+{
+        /*
+         * The unlocking fastpath is the 0->1 transition from 'locked'
+         * into 'unlocked' state:
+         */
+        if (lock->ctx) {
+#ifdef CONFIG_DEBUG_MUTEXES
+                DEBUG_LOCKS_WARN_ON(!lock->ctx->acquired);
+#endif
+                if (lock->ctx->acquired > 0)
+                        lock->ctx->acquired--;
+                lock->ctx = NULL;
+        }
+
+#ifndef CONFIG_DEBUG_MUTEXES
+        /*
+         * When debugging is enabled we must not clear the owner before time,
+         * the slow path will always be taken, and that clears the owner field
+         * after verifying that it was indeed current.
+         */
+        mutex_clear_owner(&lock->base);
+#endif
+        __mutex_fastpath_unlock(&lock->base.count, __mutex_unlock_slowpath);
+}
+EXPORT_SYMBOL(ww_mutex_unlock);
+
+static inline int __sched
+__mutex_lock_check_stamp(struct mutex *lock, struct ww_acquire_ctx *ctx)
+{
+        struct ww_mutex *ww = container_of(lock, struct ww_mutex, base);
+        struct ww_acquire_ctx *hold_ctx = ACCESS_ONCE(ww->ctx);
+
+        if (!hold_ctx)
+                return 0;
+
+        if (unlikely(ctx == hold_ctx))
+                return -EALREADY;
+
+        if (ctx->stamp - hold_ctx->stamp <= LONG_MAX &&
+            (ctx->stamp != hold_ctx->stamp || ctx > hold_ctx)) {
+#ifdef CONFIG_DEBUG_MUTEXES
+                DEBUG_LOCKS_WARN_ON(ctx->contending_lock);
+                ctx->contending_lock = ww;
+#endif
+                return -EDEADLK;
+        }
+
+        return 0;
+}
+
+static __always_inline void ww_mutex_lock_acquired(struct ww_mutex *ww,
+                                                   struct ww_acquire_ctx *ww_ctx)
+{
+#ifdef CONFIG_DEBUG_MUTEXES
+        /*
+         * If this WARN_ON triggers, you used ww_mutex_lock to acquire,
+         * but released with a normal mutex_unlock in this call.
+         *
+         * This should never happen, always use ww_mutex_unlock.
+         */
+        DEBUG_LOCKS_WARN_ON(ww->ctx);
+
+        /*
+         * Not quite done after calling ww_acquire_done() ?
+         */
+        DEBUG_LOCKS_WARN_ON(ww_ctx->done_acquire);
+
+        if (ww_ctx->contending_lock) {
+                /*
+                 * After -EDEADLK you tried to
+                 * acquire a different ww_mutex? Bad!
+                 */
+                DEBUG_LOCKS_WARN_ON(ww_ctx->contending_lock != ww);
+
+                /*
+                 * You called ww_mutex_lock after receiving -EDEADLK,
+                 * but 'forgot' to unlock everything else first?
+                 */
+                DEBUG_LOCKS_WARN_ON(ww_ctx->acquired > 0);
+                ww_ctx->contending_lock = NULL;
+        }
+
+        /*
+         * Naughty, using a different class will lead to undefined behavior!
+         */
+        DEBUG_LOCKS_WARN_ON(ww_ctx->ww_class != ww->ww_class);
+#endif
+        ww_ctx->acquired++;
+}
+
+/*
+ * after acquiring lock with fastpath or when we lost out in contested
+ * slowpath, set ctx and wake up any waiters so they can recheck.
+ *
+ * This function is never called when CONFIG_DEBUG_LOCK_ALLOC is set,
+ * as the fastpath and opportunistic spinning are disabled in that case.
+ */
+static __always_inline void
+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;
+
+        /*
+         * The lock->ctx update should be visible on all cores before
+         * the atomic read is done, otherwise contended waiters might be
+         * missed. The contended waiters will either see ww_ctx == NULL
+         * and keep spinning, or it will acquire wait_lock, add itself
+         * to waiter list and sleep.
+         */
+        smp_mb(); /* ^^^ */
+
+        /*
+         * Check if lock is contended, if not there is nobody to wake up
+         */
+        if (likely(atomic_read(&lock->base.count) == 0))
+                return;
+
+        /*
+         * 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);
+}
+
 /*
  * Lock a mutex (possibly interruptible), slowpath:
  */
-static inline int __sched
+static __always_inline int __sched
 __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass,
-                    struct lockdep_map *nest_lock, unsigned long ip)
+                    struct lockdep_map *nest_lock, unsigned long ip,
+                    struct ww_acquire_ctx *ww_ctx)
 {
         struct task_struct *task = current;
         struct mutex_waiter waiter;
         unsigned long flags;
+        int ret;
 
         preempt_disable();
         mutex_acquire_nest(&lock->dep_map, subclass, 0, nest_lock, ip);
@@ -298,6 +447,22 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass,
                 struct task_struct *owner;
                 struct mspin_node  node;
 
+                if (!__builtin_constant_p(ww_ctx == NULL) && 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 (ACCESS_ONCE(ww->ctx))
+                                break;
+                }
+
                 /*
                  * If there's an owner, wait for it to either
                  * release the lock or go to sleep.
@@ -312,6 +477,13 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass,
                 if ((atomic_read(&lock->count) == 1) &&
                     (atomic_cmpxchg(&lock->count, 1, 0) == 1)) {
                         lock_acquired(&lock->dep_map, ip);
+                        if (!__builtin_constant_p(ww_ctx == NULL)) {
+                                struct ww_mutex *ww;
+                                ww = container_of(lock, struct ww_mutex, base);
+
+                                ww_mutex_set_context_fastpath(ww, ww_ctx);
+                        }
+
                         mutex_set_owner(lock);
                         mspin_unlock(MLOCK(lock), &node);
                         preempt_enable();
@@ -371,15 +543,16 @@ slowpath:
                  * TASK_UNINTERRUPTIBLE case.)
                  */
                 if (unlikely(signal_pending_state(state, task))) {
-                        mutex_remove_waiter(lock, &waiter,
-                                            task_thread_info(task));
-                        mutex_release(&lock->dep_map, 1, ip);
-                        spin_unlock_mutex(&lock->wait_lock, flags);
+                        ret = -EINTR;
+                        goto err;
+                }
 
-                        debug_mutex_free_waiter(&waiter);
-                        preempt_enable();
-                        return -EINTR;
+                if (!__builtin_constant_p(ww_ctx == NULL) && ww_ctx->acquired > 0) {
+                        ret = __mutex_lock_check_stamp(lock, ww_ctx);
+                        if (ret)
+                                goto err;
                 }
+
                 __set_task_state(task, state);
 
                 /* didn't get the lock, go to sleep: */
@@ -394,6 +567,30 @@ done:
         mutex_remove_waiter(lock, &waiter, current_thread_info());
         mutex_set_owner(lock);
 
+        if (!__builtin_constant_p(ww_ctx == NULL)) {
+                struct ww_mutex *ww = container_of(lock,
+                                                      struct ww_mutex,
+                                                      base);
+                struct mutex_waiter *cur;
+
+                /*
+                 * This branch gets optimized out for the common case,
+                 * and is only important for ww_mutex_lock.
+                 */
+
+                ww_mutex_lock_acquired(ww, ww_ctx);
+                ww->ctx = ww_ctx;
+
+                /*
+                 * Give any possible sleeping processes the chance to wake up,
+                 * so they can recheck if they have to back off.
+                 */
+                list_for_each_entry(cur, &lock->wait_list, list) {
+                        debug_mutex_wake_waiter(lock, cur);
+                        wake_up_process(cur->task);
+                }
+        }
+
         /* set it to 0 if there are no waiters left: */
         if (likely(list_empty(&lock->wait_list)))
                 atomic_set(&lock->count, 0);
@@ -404,6 +601,14 @@ done:
         preempt_enable();
 
         return 0;
+
+err:
+        mutex_remove_waiter(lock, &waiter, task_thread_info(task));
+        spin_unlock_mutex(&lock->wait_lock, flags);
+        debug_mutex_free_waiter(&waiter);
+        mutex_release(&lock->dep_map, 1, ip);
+        preempt_enable();
+        return ret;
 }
 
 #ifdef CONFIG_DEBUG_LOCK_ALLOC
@@ -411,7 +616,8 @@ void __sched
 mutex_lock_nested(struct mutex *lock, unsigned int subclass)
 {
         might_sleep();
-        __mutex_lock_common(lock, TASK_UNINTERRUPTIBLE, subclass, NULL, _RET_IP_);
+        __mutex_lock_common(lock, TASK_UNINTERRUPTIBLE,
+                            subclass, NULL, _RET_IP_, NULL);
 }
 
 EXPORT_SYMBOL_GPL(mutex_lock_nested);
@@ -420,7 +626,8 @@ 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_);
+        __mutex_lock_common(lock, TASK_UNINTERRUPTIBLE,
+                            0, nest, _RET_IP_, NULL);
 }
 
 EXPORT_SYMBOL_GPL(_mutex_lock_nest_lock);
@@ -429,7 +636,8 @@ 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_);
+        return __mutex_lock_common(lock, TASK_KILLABLE,
+                                   subclass, NULL, _RET_IP_, NULL);
 }
 EXPORT_SYMBOL_GPL(mutex_lock_killable_nested);
 
@@ -438,10 +646,30 @@ mutex_lock_interruptible_nested(struct mutex *lock, unsigned int subclass)
 {
         might_sleep();
         return __mutex_lock_common(lock, TASK_INTERRUPTIBLE,
-                                   subclass, NULL, _RET_IP_);
+                                   subclass, NULL, _RET_IP_, NULL);
 }
 
 EXPORT_SYMBOL_GPL(mutex_lock_interruptible_nested);
+
+
+int __sched
+__ww_mutex_lock(struct ww_mutex *lock, struct ww_acquire_ctx *ctx)
+{
+        might_sleep();
+        return __mutex_lock_common(&lock->base, TASK_UNINTERRUPTIBLE,
+                                   0, &ctx->dep_map, _RET_IP_, ctx);
+}
+EXPORT_SYMBOL_GPL(__ww_mutex_lock);
+
+int __sched
+__ww_mutex_lock_interruptible(struct ww_mutex *lock, struct ww_acquire_ctx *ctx)
+{
+        might_sleep();
+        return __mutex_lock_common(&lock->base, TASK_INTERRUPTIBLE,
+                                   0, &ctx->dep_map, _RET_IP_, ctx);
+}
+EXPORT_SYMBOL_GPL(__ww_mutex_lock_interruptible);
+
 #endif
 
 /*
@@ -544,20 +772,39 @@ __mutex_lock_slowpath(atomic_t *lock_count)
 {
         struct mutex *lock = container_of(lock_count, struct mutex, count);
 
-        __mutex_lock_common(lock, TASK_UNINTERRUPTIBLE, 0, NULL, _RET_IP_);
+        __mutex_lock_common(lock, TASK_UNINTERRUPTIBLE, 0,
+                            NULL, _RET_IP_, NULL);
 }
 
 static noinline int __sched
 __mutex_lock_killable_slowpath(struct mutex *lock)
 {
-        return __mutex_lock_common(lock, TASK_KILLABLE, 0, NULL, _RET_IP_);
+        return __mutex_lock_common(lock, TASK_KILLABLE, 0,
+                                   NULL, _RET_IP_, NULL);
 }
 
 static noinline int __sched
 __mutex_lock_interruptible_slowpath(struct mutex *lock)
 {
-        return __mutex_lock_common(lock, TASK_INTERRUPTIBLE, 0, NULL, _RET_IP_);
+        return __mutex_lock_common(lock, TASK_INTERRUPTIBLE, 0,
+                                   NULL, _RET_IP_, NULL);
+}
+
+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);
 }
+
+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);
+}
+
 #endif
 
 /*
@@ -613,6 +860,45 @@ int __sched mutex_trylock(struct mutex *lock)
 }
 EXPORT_SYMBOL(mutex_trylock);
 
+#ifndef CONFIG_DEBUG_LOCK_ALLOC
+int __sched
+__ww_mutex_lock(struct ww_mutex *lock, struct ww_acquire_ctx *ctx)
+{
+        int ret;
+
+        might_sleep();
+
+        ret = __mutex_fastpath_lock_retval(&lock->base.count);
+
+        if (likely(!ret)) {
+                ww_mutex_set_context_fastpath(lock, ctx);
+                mutex_set_owner(&lock->base);
+        } else
+                ret = __ww_mutex_lock_slowpath(lock, ctx);
+        return ret;
+}
+EXPORT_SYMBOL(__ww_mutex_lock);
+
+int __sched
+__ww_mutex_lock_interruptible(struct ww_mutex *lock, struct ww_acquire_ctx *ctx)
+{
+        int ret;
+
+        might_sleep();
+
+        ret = __mutex_fastpath_lock_retval(&lock->base.count);
+
+        if (likely(!ret)) {
+                ww_mutex_set_context_fastpath(lock, ctx);
+                mutex_set_owner(&lock->base);
+        } else
+                ret = __ww_mutex_lock_interruptible_slowpath(lock, ctx);
+        return ret;
+}
+EXPORT_SYMBOL(__ww_mutex_lock_interruptible);
+
+#endif
+
 /**
  * atomic_dec_and_mutex_lock - return holding mutex if we dec to 0
  * @cnt: the atomic which we are to dec