locking: WW mutex cleanup

Make the WW mutex code more readable by adding comments, splitting up
functions and pointing out that we're actually using the Wait-Die
algorithm.

Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Gustavo Padovan <gustavo@padovan.org>
Cc: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Cc: Sean Paul <seanpaul@chromium.org>
Cc: David Airlie <airlied@linux.ie>
Cc: Davidlohr Bueso <dave@stgolabs.net>
Cc: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Cc: Josh Triplett <josh@joshtriplett.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Kate Stewart <kstewart@linuxfoundation.org>
Cc: Philippe Ombredanne <pombredanne@nexb.com>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: linux-doc@vger.kernel.org
Cc: linux-media@vger.kernel.org
Cc: linaro-mm-sig@lists.linaro.org
Co-authored-by: Thomas Hellstrom <thellstrom@vmware.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Thomas Hellstrom <thellstrom@vmware.com>
Acked-by: Ingo Molnar <mingo@kernel.org>

1 files changed, 125 insertions, 77 deletions

diff --git a/kernel/locking/mutex.c b/kernel/locking/mutex.c
index f44f658ae629..cfe48419b7d0 100644
--- a/kernel/locking/mutex.c
+++ b/kernel/locking/mutex.c
@@ -244,6 +244,17 @@ void __sched mutex_lock(struct mutex *lock)
 EXPORT_SYMBOL(mutex_lock);
 #endif
 
+/*
+ * Wait-Die:
+ *   The newer transactions are killed when:
+ *     It (the new transaction) makes a request for a lock being held
+ *     by an older transaction.
+ */
+
+/*
+ * Associate the ww_mutex @ww with the context @ww_ctx under which we acquired
+ * it.
+ */
 static __always_inline void
 ww_mutex_lock_acquired(struct ww_mutex *ww, struct ww_acquire_ctx *ww_ctx)
 {
@@ -282,26 +293,53 @@ ww_mutex_lock_acquired(struct ww_mutex *ww, struct ww_acquire_ctx *ww_ctx)
 	DEBUG_LOCKS_WARN_ON(ww_ctx->ww_class != ww->ww_class);
 #endif
 	ww_ctx->acquired++;
+	ww->ctx = ww_ctx;
 }
 
+/*
+ * Determine if context @a is 'after' context @b. IOW, @a is a younger
+ * transaction than @b and depending on algorithm either needs to wait for
+ * @b or die.
+ */
 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);
+
+	return (signed long)(a->stamp - b->stamp) > 0;
+}
+
+/*
+ * Wait-Die; wake a younger waiter context (when locks held) such that it can
+ * die.
+ *
+ * Among waiters with context, only the first one can have other locks acquired
+ * already (ctx->acquired > 0), because __ww_mutex_add_waiter() and
+ * __ww_mutex_check_kill() wake any but the earliest context.
+ */
+static bool __sched
+__ww_mutex_die(struct mutex *lock, struct mutex_waiter *waiter,
+	       struct ww_acquire_ctx *ww_ctx)
+{
+	if (waiter->ww_ctx->acquired > 0 &&
+			__ww_ctx_stamp_after(waiter->ww_ctx, ww_ctx)) {
+		debug_mutex_wake_waiter(lock, waiter);
+		wake_up_process(waiter->task);
+	}
+
+	return true;
 }
 
 /*
- * Wake up any waiters that may have to back off when the lock is held by the
- * given context.
+ * We just acquired @lock under @ww_ctx, if there are later contexts waiting
+ * behind us on the wait-list, check if they need to die.
  *
- * Due to the invariants on the wait list, this can only affect the first
- * waiter with a context.
+ * See __ww_mutex_add_waiter() for the list-order construction; basically the
+ * list is ordered by stamp, smallest (oldest) first.
  *
  * 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)
+__ww_mutex_check_waiters(struct mutex *lock, struct ww_acquire_ctx *ww_ctx)
 {
 	struct mutex_waiter *cur;
 
@@ -311,30 +349,23 @@ __ww_mutex_wakeup_for_backoff(struct mutex *lock, struct ww_acquire_ctx *ww_ctx)
 		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;
+		if (__ww_mutex_die(lock, cur, ww_ctx))
+			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.
+ * After acquiring lock with fastpath, where we do not hold wait_lock, 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_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
+	 * the WAITERS check 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.
@@ -348,29 +379,14 @@ ww_mutex_set_context_fastpath(struct ww_mutex *lock, struct ww_acquire_ctx *ctx)
 		return;
 
 	/*
-	 * Uh oh, we raced in fastpath, wake up everyone in this case,
-	 * so they can see the new lock->ctx.
+	 * Uh oh, we raced in fastpath, check if any of the waiters need to
+	 * die.
 	 */
 	spin_lock(&lock->base.wait_lock);
-	__ww_mutex_wakeup_for_backoff(&lock->base, ctx);
+	__ww_mutex_check_waiters(&lock->base, ctx);
 	spin_unlock(&lock->base.wait_lock);
 }
 
-/*
- * 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_lock_acquired(lock, ctx);
-	lock->ctx = ctx;
-}
-
 #ifdef CONFIG_MUTEX_SPIN_ON_OWNER
 
 static inline
@@ -646,37 +662,73 @@ void __sched ww_mutex_unlock(struct ww_mutex *lock)
 }
 EXPORT_SYMBOL(ww_mutex_unlock);
 
+
+static __always_inline int __sched
+__ww_mutex_kill(struct mutex *lock, struct ww_acquire_ctx *ww_ctx)
+{
+	if (ww_ctx->acquired > 0) {
+#ifdef CONFIG_DEBUG_MUTEXES
+		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 0;
+}
+
+
+/*
+ * Check whether we need to kill the transaction for the current lock acquire.
+ *
+ * Wait-Die: If we're trying to acquire a lock already held by an older
+ *           context, kill ourselves.
+ *
+ * Since __ww_mutex_add_waiter() orders the wait-list on stamp, we only have to
+ * look at waiters before us in the wait-list.
+ */
 static inline int __sched
-__ww_mutex_lock_check_stamp(struct mutex *lock, struct mutex_waiter *waiter,
-			    struct ww_acquire_ctx *ctx)
+__ww_mutex_check_kill(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 (ctx->acquired == 0)
+		return 0;
+
 	if (hold_ctx && __ww_ctx_stamp_after(ctx, hold_ctx))
-		goto deadlock;
+		return __ww_mutex_kill(lock, 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.
+	 * stamp is earlier than ours and we must kill ourself.
 	 */
 	cur = waiter;
 	list_for_each_entry_continue_reverse(cur, &lock->wait_list, list) {
-		if (cur->ww_ctx)
-			goto deadlock;
+		if (!cur->ww_ctx)
+			continue;
+
+		return __ww_mutex_kill(lock, ctx);
 	}
 
 	return 0;
-
-deadlock:
-#ifdef CONFIG_DEBUG_MUTEXES
-	DEBUG_LOCKS_WARN_ON(ctx->contending_lock);
-	ctx->contending_lock = ww;
-#endif
-	return -EDEADLK;
 }
 
+/*
+ * Add @waiter to the wait-list, keep the wait-list ordered by stamp, smallest
+ * first. Such that older contexts are preferred to acquire the lock over
+ * younger contexts.
+ *
+ * Waiters without context are interspersed in FIFO order.
+ *
+ * Furthermore, for Wait-Die kill ourself immediately when possible (there are
+ * older contexts already waiting) to avoid unnecessary waiting.
+ */
 static inline int __sched
 __ww_mutex_add_waiter(struct mutex_waiter *waiter,
 		      struct mutex *lock,
@@ -693,7 +745,7 @@ __ww_mutex_add_waiter(struct mutex_waiter *waiter,
 	/*
 	 * Add the waiter before the first waiter with a higher stamp.
 	 * Waiters without a context are skipped to avoid starving
-	 * them.
+	 * them. Wait-Die waiters may die here.
 	 */
 	pos = &lock->wait_list;
 	list_for_each_entry_reverse(cur, &lock->wait_list, list) {
@@ -701,34 +753,27 @@ __ww_mutex_add_waiter(struct mutex_waiter *waiter,
 			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
-				struct ww_mutex *ww;
+			/*
+			 * Wait-Die: if we find an older context waiting, there
+			 * is no point in queueing behind it, as we'd have to
+			 * die the moment it would acquire the lock.
+			 */
+			int ret = __ww_mutex_kill(lock, ww_ctx);
 
-				ww = container_of(lock, struct ww_mutex, base);
-				DEBUG_LOCKS_WARN_ON(ww_ctx->contending_lock);
-				ww_ctx->contending_lock = ww;
-#endif
-				return -EDEADLK;
-			}
+			if (ret)
+				return ret;
 
 			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);
-		}
+		/* Wait-Die: ensure younger waiters die. */
+		__ww_mutex_die(lock, cur, ww_ctx);
 	}
 
 	list_add_tail(&waiter->list, pos);
+
 	return 0;
 }
 
@@ -772,7 +817,7 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass,
 	 */
 	if (__mutex_trylock(lock)) {
 		if (use_ww_ctx && ww_ctx)
-			__ww_mutex_wakeup_for_backoff(lock, ww_ctx);
+			__ww_mutex_check_waiters(lock, ww_ctx);
 
 		goto skip_wait;
 	}
@@ -790,10 +835,13 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass,
 		waiter.ww_ctx = MUTEX_POISON_WW_CTX;
 #endif
 	} else {
-		/* Add in stamp order, waking up waiters that must back off. */
+		/*
+		 * Add in stamp order, waking up waiters that must kill
+		 * themselves.
+		 */
 		ret = __ww_mutex_add_waiter(&waiter, lock, ww_ctx);
 		if (ret)
-			goto err_early_backoff;
+			goto err_early_kill;
 
 		waiter.ww_ctx = ww_ctx;
 	}
@@ -815,7 +863,7 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass,
 			goto acquired;
 
 		/*
-		 * Check for signals and wound conditions while holding
+		 * Check for signals and kill conditions while holding
 		 * wait_lock. This ensures the lock cancellation is ordered
 		 * against mutex_unlock() and wake-ups do not go missing.
 		 */
@@ -824,8 +872,8 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass,
 			goto err;
 		}
 
-		if (use_ww_ctx && ww_ctx && ww_ctx->acquired > 0) {
-			ret = __ww_mutex_lock_check_stamp(lock, &waiter, ww_ctx);
+		if (use_ww_ctx && ww_ctx) {
+			ret = __ww_mutex_check_kill(lock, &waiter, ww_ctx);
 			if (ret)
 				goto err;
 		}
@@ -870,7 +918,7 @@ skip_wait:
 	lock_acquired(&lock->dep_map, ip);
 
 	if (use_ww_ctx && ww_ctx)
-		ww_mutex_set_context_slowpath(ww, ww_ctx);
+		ww_mutex_lock_acquired(ww, ww_ctx);
 
 	spin_unlock(&lock->wait_lock);
 	preempt_enable();
@@ -879,7 +927,7 @@ skip_wait:
 err:
 	__set_current_state(TASK_RUNNING);
 	mutex_remove_waiter(lock, &waiter, current);
-err_early_backoff:
+err_early_kill:
 	spin_unlock(&lock->wait_lock);
 	debug_mutex_free_waiter(&waiter);
 	mutex_release(&lock->dep_map, 1, ip);