Merge drm/drm-next into drm-intel-next-queued

We need a backmerge to get DP_DPCD_REV_14 before we push other
i915 changes to dinq that could break compilation.

Signed-off-by: Rodrigo Vivi <[email protected]>

12 files changed, 489 insertions, 392 deletions

diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c
index 023386338269..5fa4d3138bf1 100644
--- a/kernel/locking/lockdep.c
+++ b/kernel/locking/lockdep.c
@@ -561,20 +561,24 @@ static void print_lock(struct held_lock *hlock)
 	printk(KERN_CONT ", at: %pS\n", (void *)hlock->acquire_ip);
 }
 
-static void lockdep_print_held_locks(struct task_struct *curr)
+static void lockdep_print_held_locks(struct task_struct *p)
 {
-	int i, depth = curr->lockdep_depth;
+	int i, depth = READ_ONCE(p->lockdep_depth);
 
-	if (!depth) {
-		printk("no locks held by %s/%d.\n", curr->comm, task_pid_nr(curr));
+	if (!depth)
+		printk("no locks held by %s/%d.\n", p->comm, task_pid_nr(p));
+	else
+		printk("%d lock%s held by %s/%d:\n", depth,
+		       depth > 1 ? "s" : "", p->comm, task_pid_nr(p));
+	/*
+	 * It's not reliable to print a task's held locks if it's not sleeping
+	 * and it's not the current task.
+	 */
+	if (p->state == TASK_RUNNING && p != current)
 		return;
-	}
-	printk("%d lock%s held by %s/%d:\n",
-		depth, depth > 1 ? "s" : "", curr->comm, task_pid_nr(curr));
-
 	for (i = 0; i < depth; i++) {
 		printk(" #%d: ", i);
-		print_lock(curr->held_locks + i);
+		print_lock(p->held_locks + i);
 	}
 }
 
@@ -1261,11 +1265,11 @@ unsigned long lockdep_count_forward_deps(struct lock_class *class)
 	this.parent = NULL;
 	this.class = class;
 
-	local_irq_save(flags);
+	raw_local_irq_save(flags);
 	arch_spin_lock(&lockdep_lock);
 	ret = __lockdep_count_forward_deps(&this);
 	arch_spin_unlock(&lockdep_lock);
-	local_irq_restore(flags);
+	raw_local_irq_restore(flags);
 
 	return ret;
 }
@@ -1288,11 +1292,11 @@ unsigned long lockdep_count_backward_deps(struct lock_class *class)
 	this.parent = NULL;
 	this.class = class;
 
-	local_irq_save(flags);
+	raw_local_irq_save(flags);
 	arch_spin_lock(&lockdep_lock);
 	ret = __lockdep_count_backward_deps(&this);
 	arch_spin_unlock(&lockdep_lock);
-	local_irq_restore(flags);
+	raw_local_irq_restore(flags);
 
 	return ret;
 }
@@ -4407,7 +4411,7 @@ void debug_check_no_locks_freed(const void *mem_from, unsigned long mem_len)
 	if (unlikely(!debug_locks))
 		return;
 
-	local_irq_save(flags);
+	raw_local_irq_save(flags);
 	for (i = 0; i < curr->lockdep_depth; i++) {
 		hlock = curr->held_locks + i;
 
@@ -4418,7 +4422,7 @@ void debug_check_no_locks_freed(const void *mem_from, unsigned long mem_len)
 		print_freed_lock_bug(curr, mem_from, mem_from + mem_len, hlock);
 		break;
 	}
-	local_irq_restore(flags);
+	raw_local_irq_restore(flags);
 }
 EXPORT_SYMBOL_GPL(debug_check_no_locks_freed);
 
@@ -4451,8 +4455,6 @@ EXPORT_SYMBOL_GPL(debug_check_no_locks_held);
 void debug_show_all_locks(void)
 {
 	struct task_struct *g, *p;
-	int count = 10;
-	int unlock = 1;
 
 	if (unlikely(!debug_locks)) {
 		pr_warn("INFO: lockdep is turned off.\n");
@@ -4460,50 +4462,18 @@ void debug_show_all_locks(void)
 	}
 	pr_warn("\nShowing all locks held in the system:\n");
 
-	/*
-	 * Here we try to get the tasklist_lock as hard as possible,
-	 * if not successful after 2 seconds we ignore it (but keep
-	 * trying). This is to enable a debug printout even if a
-	 * tasklist_lock-holding task deadlocks or crashes.
-	 */
-retry:
-	if (!read_trylock(&tasklist_lock)) {
-		if (count == 10)
-			pr_warn("hm, tasklist_lock locked, retrying... ");
-		if (count) {
-			count--;
-			pr_cont(" #%d", 10-count);
-			mdelay(200);
-			goto retry;
-		}
-		pr_cont(" ignoring it.\n");
-		unlock = 0;
-	} else {
-		if (count != 10)
-			pr_cont(" locked it.\n");
-	}
-
-	do_each_thread(g, p) {
-		/*
-		 * It's not reliable to print a task's held locks
-		 * if it's not sleeping (or if it's not the current
-		 * task):
-		 */
-		if (p->state == TASK_RUNNING && p != current)
+	rcu_read_lock();
+	for_each_process_thread(g, p) {
+		if (!p->lockdep_depth)
 			continue;
-		if (p->lockdep_depth)
-			lockdep_print_held_locks(p);
-		if (!unlock)
-			if (read_trylock(&tasklist_lock))
-				unlock = 1;
+		lockdep_print_held_locks(p);
 		touch_nmi_watchdog();
-	} while_each_thread(g, p);
+		touch_all_softlockup_watchdogs();
+	}
+	rcu_read_unlock();
 
 	pr_warn("\n");
 	pr_warn("=============================================\n\n");
-
-	if (unlock)
-		read_unlock(&tasklist_lock);
 }
 EXPORT_SYMBOL_GPL(debug_show_all_locks);
 #endif
diff --git a/kernel/locking/lockdep_proc.c b/kernel/locking/lockdep_proc.c
index ad69bbc9bd28..3dd980dfba2d 100644
--- a/kernel/locking/lockdep_proc.c
+++ b/kernel/locking/lockdep_proc.c
@@ -101,18 +101,6 @@ static const struct seq_operations lockdep_ops = {
 	.show	= l_show,
 };
 
-static int lockdep_open(struct inode *inode, struct file *file)
-{
-	return seq_open(file, &lockdep_ops);
-}
-
-static const struct file_operations proc_lockdep_operations = {
-	.open		= lockdep_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= seq_release,
-};
-
 #ifdef CONFIG_PROVE_LOCKING
 static void *lc_start(struct seq_file *m, loff_t *pos)
 {
@@ -170,18 +158,6 @@ static const struct seq_operations lockdep_chains_ops = {
 	.stop	= lc_stop,
 	.show	= lc_show,
 };
-
-static int lockdep_chains_open(struct inode *inode, struct file *file)
-{
-	return seq_open(file, &lockdep_chains_ops);
-}
-
-static const struct file_operations proc_lockdep_chains_operations = {
-	.open		= lockdep_chains_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= seq_release,
-};
 #endif /* CONFIG_PROVE_LOCKING */
 
 static void lockdep_stats_debug_show(struct seq_file *m)
@@ -355,18 +331,6 @@ static int lockdep_stats_show(struct seq_file *m, void *v)
 	return 0;
 }
 
-static int lockdep_stats_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, lockdep_stats_show, NULL);
-}
-
-static const struct file_operations proc_lockdep_stats_operations = {
-	.open		= lockdep_stats_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-};
-
 #ifdef CONFIG_LOCK_STAT
 
 struct lock_stat_data {
@@ -682,14 +646,11 @@ static const struct file_operations proc_lock_stat_operations = {
 
 static int __init lockdep_proc_init(void)
 {
-	proc_create("lockdep", S_IRUSR, NULL, &proc_lockdep_operations);
+	proc_create_seq("lockdep", S_IRUSR, NULL, &lockdep_ops);
 #ifdef CONFIG_PROVE_LOCKING
-	proc_create("lockdep_chains", S_IRUSR, NULL,
-		    &proc_lockdep_chains_operations);
+	proc_create_seq("lockdep_chains", S_IRUSR, NULL, &lockdep_chains_ops);
 #endif
-	proc_create("lockdep_stats", S_IRUSR, NULL,
-		    &proc_lockdep_stats_operations);
-
+	proc_create_single("lockdep_stats", S_IRUSR, NULL, lockdep_stats_show);
 #ifdef CONFIG_LOCK_STAT
 	proc_create("lock_stat", S_IRUSR | S_IWUSR, NULL,
 		    &proc_lock_stat_operations);
diff --git a/kernel/locking/locktorture.c b/kernel/locking/locktorture.c
index 6850ffd69125..c28224347d69 100644
--- a/kernel/locking/locktorture.c
+++ b/kernel/locking/locktorture.c
@@ -365,7 +365,7 @@ static struct lock_torture_ops mutex_lock_ops = {
 };
 
 #include <linux/ww_mutex.h>
-static DEFINE_WW_CLASS(torture_ww_class);
+static DEFINE_WD_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);
@@ -913,7 +913,9 @@ static int __init lock_torture_init(void)
 	/* Initialize the statistics so that each run gets its own numbers. */
 	if (nwriters_stress) {
 		lock_is_write_held = 0;
-		cxt.lwsa = kmalloc(sizeof(*cxt.lwsa) * cxt.nrealwriters_stress, GFP_KERNEL);
+		cxt.lwsa = kmalloc_array(cxt.nrealwriters_stress,
+					 sizeof(*cxt.lwsa),
+					 GFP_KERNEL);
 		if (cxt.lwsa == NULL) {
 			VERBOSE_TOROUT_STRING("cxt.lwsa: Out of memory");
 			firsterr = -ENOMEM;
@@ -942,7 +944,9 @@ static int __init lock_torture_init(void)
 
 		if (nreaders_stress) {
 			lock_is_read_held = 0;
-			cxt.lrsa = kmalloc(sizeof(*cxt.lrsa) * cxt.nrealreaders_stress, GFP_KERNEL);
+			cxt.lrsa = kmalloc_array(cxt.nrealreaders_stress,
+						 sizeof(*cxt.lrsa),
+						 GFP_KERNEL);
 			if (cxt.lrsa == NULL) {
 				VERBOSE_TOROUT_STRING("cxt.lrsa: Out of memory");
 				firsterr = -ENOMEM;
@@ -985,7 +989,8 @@ static int __init lock_torture_init(void)
 	}
 
 	if (nwriters_stress) {
-		writer_tasks = kzalloc(cxt.nrealwriters_stress * sizeof(writer_tasks[0]),
+		writer_tasks = kcalloc(cxt.nrealwriters_stress,
+				       sizeof(writer_tasks[0]),
 				       GFP_KERNEL);
 		if (writer_tasks == NULL) {
 			VERBOSE_TOROUT_ERRSTRING("writer_tasks: Out of memory");
@@ -995,7 +1000,8 @@ static int __init lock_torture_init(void)
 	}
 
 	if (cxt.cur_ops->readlock) {
-		reader_tasks = kzalloc(cxt.nrealreaders_stress * sizeof(reader_tasks[0]),
+		reader_tasks = kcalloc(cxt.nrealreaders_stress,
+				       sizeof(reader_tasks[0]),
 				       GFP_KERNEL);
 		if (reader_tasks == NULL) {
 			VERBOSE_TOROUT_ERRSTRING("reader_tasks: Out of memory");
diff --git a/kernel/locking/mcs_spinlock.h b/kernel/locking/mcs_spinlock.h
index f046b7ce9dd6..5e10153b4d3c 100644
--- a/kernel/locking/mcs_spinlock.h
+++ b/kernel/locking/mcs_spinlock.h
@@ -23,13 +23,15 @@ struct mcs_spinlock {
 
 #ifndef arch_mcs_spin_lock_contended
 /*
- * Using smp_load_acquire() provides a memory barrier that ensures
- * subsequent operations happen after the lock is acquired.
+ * Using smp_cond_load_acquire() provides the acquire semantics
+ * required so that subsequent operations happen after the
+ * lock is acquired. Additionally, some architectures such as
+ * ARM64 would like to do spin-waiting instead of purely
+ * spinning, and smp_cond_load_acquire() provides that behavior.
  */
 #define arch_mcs_spin_lock_contended(l)					\
 do {									\
-	while (!(smp_load_acquire(l)))					\
-		cpu_relax();						\
+	smp_cond_load_acquire(l, VAL);					\
 } while (0)
 #endif
 
diff --git a/kernel/locking/mutex.c b/kernel/locking/mutex.c
index 2048359f33d2..1a81a1257b3f 100644
--- a/kernel/locking/mutex.c
+++ b/kernel/locking/mutex.c
@@ -139,8 +139,9 @@ static inline bool __mutex_trylock(struct mutex *lock)
 static __always_inline bool __mutex_trylock_fast(struct mutex *lock)
 {
 	unsigned long curr = (unsigned long)current;
+	unsigned long zero = 0UL;
 
-	if (!atomic_long_cmpxchg_acquire(&lock->owner, 0UL, curr))
+	if (atomic_long_try_cmpxchg_acquire(&lock->owner, &zero, curr))
 		return true;
 
 	return false;
@@ -173,6 +174,21 @@ static inline bool __mutex_waiter_is_first(struct mutex *lock, struct mutex_wait
 }
 
 /*
+ * Add @waiter to a given location in the lock wait_list and set the
+ * FLAG_WAITERS flag if it's the first waiter.
+ */
+static void __sched
+__mutex_add_waiter(struct mutex *lock, struct mutex_waiter *waiter,
+		   struct list_head *list)
+{
+	debug_mutex_add_waiter(lock, waiter, current);
+
+	list_add_tail(&waiter->list, list);
+	if (__mutex_waiter_is_first(lock, waiter))
+		__mutex_set_flag(lock, MUTEX_FLAG_WAITERS);
+}
+
+/*
  * Give up ownership to a specific task, when @task = NULL, this is equivalent
  * to a regular unlock. Sets PICKUP on a handoff, clears HANDOF, preserves
  * WAITERS. Provides RELEASE semantics like a regular unlock, the
@@ -243,6 +259,22 @@ 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.
+ *
+ * Wound-Wait:
+ *   The newer transactions are wounded when:
+ *     An older transaction makes a request for a lock being held by
+ *     the newer 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)
 {
@@ -281,26 +313,108 @@ 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 (!ww_ctx->is_wait_die)
+		return false;
+
+	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;
+}
+
+/*
+ * Wound-Wait; wound a younger @hold_ctx if it holds the lock.
+ *
+ * Wound the lock holder if there are waiters with older transactions than
+ * the lock holders. Even if multiple waiters may wound the lock holder,
+ * it's sufficient that only one does.
+ */
+static bool __ww_mutex_wound(struct mutex *lock,
+			     struct ww_acquire_ctx *ww_ctx,
+			     struct ww_acquire_ctx *hold_ctx)
+{
+	struct task_struct *owner = __mutex_owner(lock);
+
+	lockdep_assert_held(&lock->wait_lock);
+
+	/*
+	 * Possible through __ww_mutex_add_waiter() when we race with
+	 * ww_mutex_set_context_fastpath(). In that case we'll get here again
+	 * through __ww_mutex_check_waiters().
+	 */
+	if (!hold_ctx)
+		return false;
+
+	/*
+	 * Can have !owner because of __mutex_unlock_slowpath(), but if owner,
+	 * it cannot go away because we'll have FLAG_WAITERS set and hold
+	 * wait_lock.
+	 */
+	if (!owner)
+		return false;
+
+	if (ww_ctx->acquired > 0 && __ww_ctx_stamp_after(hold_ctx, ww_ctx)) {
+		hold_ctx->wounded = 1;
+
+		/*
+		 * wake_up_process() paired with set_current_state()
+		 * inserts sufficient barriers to make sure @owner either sees
+		 * it's wounded in __ww_mutex_lock_check_stamp() or has a
+		 * wakeup pending to re-read the wounded state.
+		 */
+		if (owner != current)
+			wake_up_process(owner);
+
+		return true;
+	}
+
+	return false;
 }
 
 /*
- * 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, or wound us.
  *
- * 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.
+ *
+ * This relies on never mixing wait-die/wound-wait on the same wait-list;
+ * which is currently ensured by that being a ww_class property.
  *
  * 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;
 
@@ -310,66 +424,51 @@ __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) ||
+		    __ww_mutex_wound(lock, cur->ww_ctx, 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.
 	 */
-	smp_mb(); /* ^^^ */
+	smp_mb(); /* See comments above and below. */
 
 	/*
-	 * Check if lock is contended, if not there is nobody to wake up
+	 * [W] ww->ctx = ctx	    [W] MUTEX_FLAG_WAITERS
+	 *     MB		        MB
+	 * [R] MUTEX_FLAG_WAITERS   [R] ww->ctx
+	 *
+	 * The memory barrier above pairs with the memory barrier in
+	 * __ww_mutex_add_waiter() and makes sure we either observe ww->ctx
+	 * and/or !empty list.
 	 */
 	if (likely(!(atomic_long_read(&lock->base.owner) & MUTEX_FLAG_WAITERS)))
 		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 or wound us.
 	 */
 	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
@@ -645,37 +744,83 @@ 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 the wound condition for the current lock acquire.
+ *
+ * Wound-Wait: If we're wounded, kill ourself.
+ *
+ * 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 (!ctx->is_wait_die) {
+		if (ctx->wounded)
+			return __ww_mutex_kill(lock, ctx);
+
+		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 and for
+ * Wound-Wait ensure we wound the owning context when it is younger.
+ */
 static inline int __sched
 __ww_mutex_add_waiter(struct mutex_waiter *waiter,
 		      struct mutex *lock,
@@ -683,16 +828,21 @@ __ww_mutex_add_waiter(struct mutex_waiter *waiter,
 {
 	struct mutex_waiter *cur;
 	struct list_head *pos;
+	bool is_wait_die;
 
 	if (!ww_ctx) {
-		list_add_tail(&waiter->list, &lock->wait_list);
+		__mutex_add_waiter(lock, waiter, &lock->wait_list);
 		return 0;
 	}
 
+	is_wait_die = ww_ctx->is_wait_die;
+
 	/*
 	 * 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. Wound-Wait waiters
+	 * never die here, but they are sorted in stamp order and
+	 * may wound the lock holder.
 	 */
 	pos = &lock->wait_list;
 	list_for_each_entry_reverse(cur, &lock->wait_list, list) {
@@ -700,16 +850,16 @@ __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;
-
-				ww = container_of(lock, struct ww_mutex, base);
-				DEBUG_LOCKS_WARN_ON(ww_ctx->contending_lock);
-				ww_ctx->contending_lock = ww;
-#endif
-				return -EDEADLK;
+			/*
+			 * 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.
+			 */
+			if (is_wait_die) {
+				int ret = __ww_mutex_kill(lock, ww_ctx);
+
+				if (ret)
+					return ret;
 			}
 
 			break;
@@ -717,17 +867,28 @@ __ww_mutex_add_waiter(struct mutex_waiter *waiter,
 
 		pos = &cur->list;
 
+		/* Wait-Die: ensure younger waiters die. */
+		__ww_mutex_die(lock, cur, ww_ctx);
+	}
+
+	__mutex_add_waiter(lock, waiter, pos);
+
+	/*
+	 * Wound-Wait: if we're blocking on a mutex owned by a younger context,
+	 * wound that such that we might proceed.
+	 */
+	if (!is_wait_die) {
+		struct ww_mutex *ww = container_of(lock, struct ww_mutex, base);
+
 		/*
-		 * Wake up the waiter so that it gets a chance to back
-		 * off.
+		 * See ww_mutex_set_context_fastpath(). Orders setting
+		 * MUTEX_FLAG_WAITERS vs the ww->ctx load,
+		 * such that either we or the fastpath will wound @ww->ctx.
 		 */
-		if (cur->ww_ctx->acquired > 0) {
-			debug_mutex_wake_waiter(lock, cur);
-			wake_up_process(cur->task);
-		}
+		smp_mb();
+		__ww_mutex_wound(lock, ww_ctx, ww->ctx);
 	}
 
-	list_add_tail(&waiter->list, pos);
 	return 0;
 }
 
@@ -750,6 +911,14 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass,
 	if (use_ww_ctx && ww_ctx) {
 		if (unlikely(ww_ctx == READ_ONCE(ww->ctx)))
 			return -EALREADY;
+
+		/*
+		 * Reset the wounded flag after a kill. No other process can
+		 * race and wound us here since they can't have a valid owner
+		 * pointer if we don't have any locks held.
+		 */
+		if (ww_ctx->acquired == 0)
+			ww_ctx->wounded = 0;
 	}
 
 	preempt_disable();
@@ -771,7 +940,7 @@ __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;
 	}
@@ -783,25 +952,26 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass,
 
 	if (!use_ww_ctx) {
 		/* add waiting tasks to the end of the waitqueue (FIFO): */
-		list_add_tail(&waiter.list, &lock->wait_list);
+		__mutex_add_waiter(lock, &waiter, &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. */
+		/*
+		 * 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;
 	}
 
 	waiter.task = current;
 
-	if (__mutex_waiter_is_first(lock, &waiter))
-		__mutex_set_flag(lock, MUTEX_FLAG_WAITERS);
-
 	set_current_state(state);
 	for (;;) {
 		/*
@@ -814,7 +984,7 @@ __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.
 		 */
@@ -823,8 +993,8 @@ __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;
 		}
@@ -858,6 +1028,16 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass,
 acquired:
 	__set_current_state(TASK_RUNNING);
 
+	if (use_ww_ctx && ww_ctx) {
+		/*
+		 * Wound-Wait; we stole the lock (!first_waiter), check the
+		 * waiters as anyone might want to wound us.
+		 */
+		if (!ww_ctx->is_wait_die &&
+		    !__mutex_waiter_is_first(lock, &waiter))
+			__ww_mutex_check_waiters(lock, ww_ctx);
+	}
+
 	mutex_remove_waiter(lock, &waiter, current);
 	if (likely(list_empty(&lock->wait_list)))
 		__mutex_clear_flag(lock, MUTEX_FLAGS);
@@ -869,7 +1049,7 @@ 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();
@@ -878,7 +1058,7 @@ 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);
diff --git a/kernel/locking/qspinlock.c b/kernel/locking/qspinlock.c
index d880296245c5..bfaeb05123ff 100644
--- a/kernel/locking/qspinlock.c
+++ b/kernel/locking/qspinlock.c
@@ -12,11 +12,11 @@
  * GNU General Public License for more details.
  *
  * (C) Copyright 2013-2015 Hewlett-Packard Development Company, L.P.
- * (C) Copyright 2013-2014 Red Hat, Inc.
+ * (C) Copyright 2013-2014,2018 Red Hat, Inc.
  * (C) Copyright 2015 Intel Corp.
  * (C) Copyright 2015 Hewlett-Packard Enterprise Development LP
  *
- * Authors: Waiman Long <[email protected]>
+ * Authors: Waiman Long <[email protected]>
  *          Peter Zijlstra <[email protected]>
  */
 
@@ -33,6 +33,11 @@
 #include <asm/qspinlock.h>
 
 /*
+ * Include queued spinlock statistics code
+ */
+#include "qspinlock_stat.h"
+
+/*
  * The basic principle of a queue-based spinlock can best be understood
  * by studying a classic queue-based spinlock implementation called the
  * MCS lock. The paper below provides a good description for this kind
@@ -77,6 +82,18 @@
 #endif
 
 /*
+ * The pending bit spinning loop count.
+ * This heuristic is used to limit the number of lockword accesses
+ * made by atomic_cond_read_relaxed when waiting for the lock to
+ * transition out of the "== _Q_PENDING_VAL" state. We don't spin
+ * indefinitely because there's no guarantee that we'll make forward
+ * progress.
+ */
+#ifndef _Q_PENDING_LOOPS
+#define _Q_PENDING_LOOPS	1
+#endif
+
+/*
  * Per-CPU queue node structures; we can never have more than 4 nested
  * contexts: task, softirq, hardirq, nmi.
  *
@@ -114,41 +131,18 @@ static inline __pure struct mcs_spinlock *decode_tail(u32 tail)
 
 #define _Q_LOCKED_PENDING_MASK (_Q_LOCKED_MASK | _Q_PENDING_MASK)
 
-/*
- * By using the whole 2nd least significant byte for the pending bit, we
- * can allow better optimization of the lock acquisition for the pending
- * bit holder.
+#if _Q_PENDING_BITS == 8
+/**
+ * clear_pending - clear the pending bit.
+ * @lock: Pointer to queued spinlock structure
  *
- * This internal structure is also used by the set_locked function which
- * is not restricted to _Q_PENDING_BITS == 8.
+ * *,1,* -> *,0,*
  */
-struct __qspinlock {
-	union {
-		atomic_t val;
-#ifdef __LITTLE_ENDIAN
-		struct {
-			u8	locked;
-			u8	pending;
-		};
-		struct {
-			u16	locked_pending;
-			u16	tail;
-		};
-#else
-		struct {
-			u16	tail;
-			u16	locked_pending;
-		};
-		struct {
-			u8	reserved[2];
-			u8	pending;
-			u8	locked;
-		};
-#endif
-	};
-};
+static __always_inline void clear_pending(struct qspinlock *lock)
+{
+	WRITE_ONCE(lock->pending, 0);
+}
 
-#if _Q_PENDING_BITS == 8
 /**
  * clear_pending_set_locked - take ownership and clear the pending bit.
  * @lock: Pointer to queued spinlock structure
@@ -159,9 +153,7 @@ struct __qspinlock {
  */
 static __always_inline void clear_pending_set_locked(struct qspinlock *lock)
 {
-	struct __qspinlock *l = (void *)lock;
-
-	WRITE_ONCE(l->locked_pending, _Q_LOCKED_VAL);
+	WRITE_ONCE(lock->locked_pending, _Q_LOCKED_VAL);
 }
 
 /*
@@ -176,19 +168,28 @@ static __always_inline void clear_pending_set_locked(struct qspinlock *lock)
  */
 static __always_inline u32 xchg_tail(struct qspinlock *lock, u32 tail)
 {
-	struct __qspinlock *l = (void *)lock;
-
 	/*
-	 * Use release semantics to make sure that the MCS node is properly
-	 * initialized before changing the tail code.
+	 * We can use relaxed semantics since the caller ensures that the
+	 * MCS node is properly initialized before updating the tail.
 	 */
-	return (u32)xchg_release(&l->tail,
+	return (u32)xchg_relaxed(&lock->tail,
 				 tail >> _Q_TAIL_OFFSET) << _Q_TAIL_OFFSET;
 }
 
 #else /* _Q_PENDING_BITS == 8 */
 
 /**
+ * clear_pending - clear the pending bit.
+ * @lock: Pointer to queued spinlock structure
+ *
+ * *,1,* -> *,0,*
+ */
+static __always_inline void clear_pending(struct qspinlock *lock)
+{
+	atomic_andnot(_Q_PENDING_VAL, &lock->val);
+}
+
+/**
  * clear_pending_set_locked - take ownership and clear the pending bit.
  * @lock: Pointer to queued spinlock structure
  *
@@ -216,10 +217,11 @@ static __always_inline u32 xchg_tail(struct qspinlock *lock, u32 tail)
 	for (;;) {
 		new = (val & _Q_LOCKED_PENDING_MASK) | tail;
 		/*
-		 * Use release semantics to make sure that the MCS node is
-		 * properly initialized before changing the tail code.
+		 * We can use relaxed semantics since the caller ensures that
+		 * the MCS node is properly initialized before updating the
+		 * tail.
 		 */
-		old = atomic_cmpxchg_release(&lock->val, val, new);
+		old = atomic_cmpxchg_relaxed(&lock->val, val, new);
 		if (old == val)
 			break;
 
@@ -237,9 +239,7 @@ static __always_inline u32 xchg_tail(struct qspinlock *lock, u32 tail)
  */
 static __always_inline void set_locked(struct qspinlock *lock)
 {
-	struct __qspinlock *l = (void *)lock;
-
-	WRITE_ONCE(l->locked, _Q_LOCKED_VAL);
+	WRITE_ONCE(lock->locked, _Q_LOCKED_VAL);
 }
 
 
@@ -294,86 +294,83 @@ static __always_inline u32  __pv_wait_head_or_lock(struct qspinlock *lock,
 void queued_spin_lock_slowpath(struct qspinlock *lock, u32 val)
 {
 	struct mcs_spinlock *prev, *next, *node;
-	u32 new, old, tail;
+	u32 old, tail;
 	int idx;
 
 	BUILD_BUG_ON(CONFIG_NR_CPUS >= (1U << _Q_TAIL_CPU_BITS));
 
 	if (pv_enabled())
-		goto queue;
+		goto pv_queue;
 
 	if (virt_spin_lock(lock))
 		return;
 
 	/*
-	 * wait for in-progress pending->locked hand-overs
+	 * Wait for in-progress pending->locked hand-overs with a bounded
+	 * number of spins so that we guarantee forward progress.
 	 *
 	 * 0,1,0 -> 0,0,1
 	 */
 	if (val == _Q_PENDING_VAL) {
-		while ((val = atomic_read(&lock->val)) == _Q_PENDING_VAL)
-			cpu_relax();
+		int cnt = _Q_PENDING_LOOPS;
+		val = atomic_cond_read_relaxed(&lock->val,
+					       (VAL != _Q_PENDING_VAL) || !cnt--);
 	}
 
 	/*
+	 * If we observe any contention; queue.
+	 */
+	if (val & ~_Q_LOCKED_MASK)
+		goto queue;
+
+	/*
 	 * trylock || pending
 	 *
 	 * 0,0,0 -> 0,0,1 ; trylock
 	 * 0,0,1 -> 0,1,1 ; pending
 	 */
-	for (;;) {
+	val = atomic_fetch_or_acquire(_Q_PENDING_VAL, &lock->val);
+	if (!(val & ~_Q_LOCKED_MASK)) {
 		/*
-		 * If we observe any contention; queue.
+		 * We're pending, wait for the owner to go away.
+		 *
+		 * *,1,1 -> *,1,0
+		 *
+		 * this wait loop must be a load-acquire such that we match the
+		 * store-release that clears the locked bit and create lock
+		 * sequentiality; this is because not all
+		 * clear_pending_set_locked() implementations imply full
+		 * barriers.
 		 */
-		if (val & ~_Q_LOCKED_MASK)
-			goto queue;
-
-		new = _Q_LOCKED_VAL;
-		if (val == new)
-			new |= _Q_PENDING_VAL;
+		if (val & _Q_LOCKED_MASK) {
+			atomic_cond_read_acquire(&lock->val,
+						 !(VAL & _Q_LOCKED_MASK));
+		}
 
 		/*
-		 * Acquire semantic is required here as the function may
-		 * return immediately if the lock was free.
+		 * take ownership and clear the pending bit.
+		 *
+		 * *,1,0 -> *,0,1
 		 */
-		old = atomic_cmpxchg_acquire(&lock->val, val, new);
-		if (old == val)
-			break;
-
-		val = old;
-	}
-
-	/*
-	 * we won the trylock
-	 */
-	if (new == _Q_LOCKED_VAL)
+		clear_pending_set_locked(lock);
+		qstat_inc(qstat_lock_pending, true);
 		return;
+	}
 
 	/*
-	 * we're pending, wait for the owner to go away.
-	 *
-	 * *,1,1 -> *,1,0
-	 *
-	 * this wait loop must be a load-acquire such that we match the
-	 * store-release that clears the locked bit and create lock
-	 * sequentiality; this is because not all clear_pending_set_locked()
-	 * implementations imply full barriers.
-	 */
-	smp_cond_load_acquire(&lock->val.counter, !(VAL & _Q_LOCKED_MASK));
-
-	/*
-	 * take ownership and clear the pending bit.
-	 *
-	 * *,1,0 -> *,0,1
+	 * If pending was clear but there are waiters in the queue, then
+	 * we need to undo our setting of pending before we queue ourselves.
 	 */
-	clear_pending_set_locked(lock);
-	return;
+	if (!(val & _Q_PENDING_MASK))
+		clear_pending(lock);
 
 	/*
 	 * End of pending bit optimistic spinning and beginning of MCS
 	 * queuing.
 	 */
 queue:
+	qstat_inc(qstat_lock_slowpath, true);
+pv_queue:
 	node = this_cpu_ptr(&mcs_nodes[0]);
 	idx = node->count++;
 	tail = encode_tail(smp_processor_id(), idx);
@@ -400,12 +397,18 @@ queue:
 		goto release;
 
 	/*
+	 * Ensure that the initialisation of @node is complete before we
+	 * publish the updated tail via xchg_tail() and potentially link
+	 * @node into the waitqueue via WRITE_ONCE(prev->next, node) below.
+	 */
+	smp_wmb();
+
+	/*
+	 * Publish the updated tail.
 	 * We have already touched the queueing cacheline; don't bother with
 	 * pending stuff.
 	 *
 	 * p,*,* -> n,*,*
-	 *
-	 * RELEASE, such that the stores to @node must be complete.
 	 */
 	old = xchg_tail(lock, tail);
 	next = NULL;
@@ -417,14 +420,8 @@ queue:
 	if (old & _Q_TAIL_MASK) {
 		prev = decode_tail(old);
 
-		/*
-		 * We must ensure that the stores to @node are observed before
-		 * the write to prev->next. The address dependency from
-		 * xchg_tail is not sufficient to ensure this because the read
-		 * component of xchg_tail is unordered with respect to the
-		 * initialisation of @node.
-		 */
-		smp_store_release(&prev->next, node);
+		/* Link @node into the waitqueue. */
+		WRITE_ONCE(prev->next, node);
 
 		pv_wait_node(node, prev);
 		arch_mcs_spin_lock_contended(&node->locked);
@@ -453,8 +450,8 @@ queue:
 	 *
 	 * The PV pv_wait_head_or_lock function, if active, will acquire
 	 * the lock and return a non-zero value. So we have to skip the
-	 * smp_cond_load_acquire() call. As the next PV queue head hasn't been
-	 * designated yet, there is no way for the locked value to become
+	 * atomic_cond_read_acquire() call. As the next PV queue head hasn't
+	 * been designated yet, there is no way for the locked value to become
 	 * _Q_SLOW_VAL. So both the set_locked() and the
 	 * atomic_cmpxchg_relaxed() calls will be safe.
 	 *
@@ -464,44 +461,38 @@ queue:
 	if ((val = pv_wait_head_or_lock(lock, node)))
 		goto locked;
 
-	val = smp_cond_load_acquire(&lock->val.counter, !(VAL & _Q_LOCKED_PENDING_MASK));
+	val = atomic_cond_read_acquire(&lock->val, !(VAL & _Q_LOCKED_PENDING_MASK));
 
 locked:
 	/*
 	 * claim the lock:
 	 *
 	 * n,0,0 -> 0,0,1 : lock, uncontended
-	 * *,0,0 -> *,0,1 : lock, contended
+	 * *,*,0 -> *,*,1 : lock, contended
 	 *
-	 * If the queue head is the only one in the queue (lock value == tail),
-	 * clear the tail code and grab the lock. Otherwise, we only need
-	 * to grab the lock.
+	 * If the queue head is the only one in the queue (lock value == tail)
+	 * and nobody is pending, clear the tail code and grab the lock.
+	 * Otherwise, we only need to grab the lock.
 	 */
-	for (;;) {
-		/* In the PV case we might already have _Q_LOCKED_VAL set */
-		if ((val & _Q_TAIL_MASK) != tail) {
-			set_locked(lock);
-			break;
-		}
-		/*
-		 * The smp_cond_load_acquire() call above has provided the
-		 * necessary acquire semantics required for locking. At most
-		 * two iterations of this loop may be ran.
-		 */
-		old = atomic_cmpxchg_relaxed(&lock->val, val, _Q_LOCKED_VAL);
-		if (old == val)
-			goto release;	/* No contention */
 
-		val = old;
-	}
+	/*
+	 * In the PV case we might already have _Q_LOCKED_VAL set.
+	 *
+	 * The atomic_cond_read_acquire() call above has provided the
+	 * necessary acquire semantics required for locking.
+	 */
+	if (((val & _Q_TAIL_MASK) == tail) &&
+	    atomic_try_cmpxchg_relaxed(&lock->val, &val, _Q_LOCKED_VAL))
+		goto release; /* No contention */
+
+	/* Either somebody is queued behind us or _Q_PENDING_VAL is set */
+	set_locked(lock);
 
 	/*
 	 * contended path; wait for next if not observed yet, release.
 	 */
-	if (!next) {
-		while (!(next = READ_ONCE(node->next)))
-			cpu_relax();
-	}
+	if (!next)
+		next = smp_cond_load_relaxed(&node->next, (VAL));
 
 	arch_mcs_spin_unlock_contended(&next->locked);
 	pv_kick_node(lock, next);
diff --git a/kernel/locking/qspinlock_paravirt.h b/kernel/locking/qspinlock_paravirt.h
index 6ee477765e6c..5a0cf5f9008c 100644
--- a/kernel/locking/qspinlock_paravirt.h
+++ b/kernel/locking/qspinlock_paravirt.h
@@ -56,11 +56,6 @@ struct pv_node {
 };
 
 /*
- * Include queued spinlock statistics code
- */
-#include "qspinlock_stat.h"
-
-/*
  * Hybrid PV queued/unfair lock
  *
  * By replacing the regular queued_spin_trylock() with the function below,
@@ -87,8 +82,6 @@ struct pv_node {
 #define queued_spin_trylock(l)	pv_hybrid_queued_unfair_trylock(l)
 static inline bool pv_hybrid_queued_unfair_trylock(struct qspinlock *lock)
 {
-	struct __qspinlock *l = (void *)lock;
-
 	/*
 	 * Stay in unfair lock mode as long as queued mode waiters are
 	 * present in the MCS wait queue but the pending bit isn't set.
@@ -97,7 +90,7 @@ static inline bool pv_hybrid_queued_unfair_trylock(struct qspinlock *lock)
 		int val = atomic_read(&lock->val);
 
 		if (!(val & _Q_LOCKED_PENDING_MASK) &&
-		   (cmpxchg_acquire(&l->locked, 0, _Q_LOCKED_VAL) == 0)) {
+		   (cmpxchg_acquire(&lock->locked, 0, _Q_LOCKED_VAL) == 0)) {
 			qstat_inc(qstat_pv_lock_stealing, true);
 			return true;
 		}
@@ -117,16 +110,7 @@ static inline bool pv_hybrid_queued_unfair_trylock(struct qspinlock *lock)
 #if _Q_PENDING_BITS == 8
 static __always_inline void set_pending(struct qspinlock *lock)
 {
-	struct __qspinlock *l = (void *)lock;
-
-	WRITE_ONCE(l->pending, 1);
-}
-
-static __always_inline void clear_pending(struct qspinlock *lock)
-{
-	struct __qspinlock *l = (void *)lock;
-
-	WRITE_ONCE(l->pending, 0);
+	WRITE_ONCE(lock->pending, 1);
 }
 
 /*
@@ -136,10 +120,8 @@ static __always_inline void clear_pending(struct qspinlock *lock)
  */
 static __always_inline int trylock_clear_pending(struct qspinlock *lock)
 {
-	struct __qspinlock *l = (void *)lock;
-
-	return !READ_ONCE(l->locked) &&
-	       (cmpxchg_acquire(&l->locked_pending, _Q_PENDING_VAL,
+	return !READ_ONCE(lock->locked) &&
+	       (cmpxchg_acquire(&lock->locked_pending, _Q_PENDING_VAL,
 				_Q_LOCKED_VAL) == _Q_PENDING_VAL);
 }
 #else /* _Q_PENDING_BITS == 8 */
@@ -148,11 +130,6 @@ static __always_inline void set_pending(struct qspinlock *lock)
 	atomic_or(_Q_PENDING_VAL, &lock->val);
 }
 
-static __always_inline void clear_pending(struct qspinlock *lock)
-{
-	atomic_andnot(_Q_PENDING_VAL, &lock->val);
-}
-
 static __always_inline int trylock_clear_pending(struct qspinlock *lock)
 {
 	int val = atomic_read(&lock->val);
@@ -384,7 +361,6 @@ static void pv_wait_node(struct mcs_spinlock *node, struct mcs_spinlock *prev)
 static void pv_kick_node(struct qspinlock *lock, struct mcs_spinlock *node)
 {
 	struct pv_node *pn = (struct pv_node *)node;
-	struct __qspinlock *l = (void *)lock;
 
 	/*
 	 * If the vCPU is indeed halted, advance its state to match that of
@@ -413,7 +389,7 @@ static void pv_kick_node(struct qspinlock *lock, struct mcs_spinlock *node)
 	 * the hash table later on at unlock time, no atomic instruction is
 	 * needed.
 	 */
-	WRITE_ONCE(l->locked, _Q_SLOW_VAL);
+	WRITE_ONCE(lock->locked, _Q_SLOW_VAL);
 	(void)pv_hash(lock, pn);
 }
 
@@ -428,7 +404,6 @@ static u32
 pv_wait_head_or_lock(struct qspinlock *lock, struct mcs_spinlock *node)
 {
 	struct pv_node *pn = (struct pv_node *)node;
-	struct __qspinlock *l = (void *)lock;
 	struct qspinlock **lp = NULL;
 	int waitcnt = 0;
 	int loop;
@@ -443,7 +418,7 @@ pv_wait_head_or_lock(struct qspinlock *lock, struct mcs_spinlock *node)
 	/*
 	 * Tracking # of slowpath locking operations
 	 */
-	qstat_inc(qstat_pv_lock_slowpath, true);
+	qstat_inc(qstat_lock_slowpath, true);
 
 	for (;; waitcnt++) {
 		/*
@@ -479,13 +454,13 @@ pv_wait_head_or_lock(struct qspinlock *lock, struct mcs_spinlock *node)
 			 *
 			 * Matches the smp_rmb() in __pv_queued_spin_unlock().
 			 */
-			if (xchg(&l->locked, _Q_SLOW_VAL) == 0) {
+			if (xchg(&lock->locked, _Q_SLOW_VAL) == 0) {
 				/*
 				 * The lock was free and now we own the lock.
 				 * Change the lock value back to _Q_LOCKED_VAL
 				 * and unhash the table.
 				 */
-				WRITE_ONCE(l->locked, _Q_LOCKED_VAL);
+				WRITE_ONCE(lock->locked, _Q_LOCKED_VAL);
 				WRITE_ONCE(*lp, NULL);
 				goto gotlock;
 			}
@@ -493,7 +468,7 @@ pv_wait_head_or_lock(struct qspinlock *lock, struct mcs_spinlock *node)
 		WRITE_ONCE(pn->state, vcpu_hashed);
 		qstat_inc(qstat_pv_wait_head, true);
 		qstat_inc(qstat_pv_wait_again, waitcnt);
-		pv_wait(&l->locked, _Q_SLOW_VAL);
+		pv_wait(&lock->locked, _Q_SLOW_VAL);
 
 		/*
 		 * Because of lock stealing, the queue head vCPU may not be
@@ -518,7 +493,6 @@ gotlock:
 __visible void
 __pv_queued_spin_unlock_slowpath(struct qspinlock *lock, u8 locked)
 {
-	struct __qspinlock *l = (void *)lock;
 	struct pv_node *node;
 
 	if (unlikely(locked != _Q_SLOW_VAL)) {
@@ -547,7 +521,7 @@ __pv_queued_spin_unlock_slowpath(struct qspinlock *lock, u8 locked)
 	 * Now that we have a reference to the (likely) blocked pv_node,
 	 * release the lock.
 	 */
-	smp_store_release(&l->locked, 0);
+	smp_store_release(&lock->locked, 0);
 
 	/*
 	 * At this point the memory pointed at by lock can be freed/reused,
@@ -573,7 +547,6 @@ __pv_queued_spin_unlock_slowpath(struct qspinlock *lock, u8 locked)
 #ifndef __pv_queued_spin_unlock
 __visible void __pv_queued_spin_unlock(struct qspinlock *lock)
 {
-	struct __qspinlock *l = (void *)lock;
 	u8 locked;
 
 	/*
@@ -581,7 +554,7 @@ __visible void __pv_queued_spin_unlock(struct qspinlock *lock)
 	 * unhash. Otherwise it would be possible to have multiple @lock
 	 * entries, which would be BAD.
 	 */
-	locked = cmpxchg_release(&l->locked, _Q_LOCKED_VAL, 0);
+	locked = cmpxchg_release(&lock->locked, _Q_LOCKED_VAL, 0);
 	if (likely(locked == _Q_LOCKED_VAL))
 		return;
 
diff --git a/kernel/locking/qspinlock_stat.h b/kernel/locking/qspinlock_stat.h
index 4a30ef63c607..6bd78c0740fc 100644
--- a/kernel/locking/qspinlock_stat.h
+++ b/kernel/locking/qspinlock_stat.h
@@ -22,13 +22,14 @@
  *   pv_kick_wake	- # of vCPU kicks used for computing pv_latency_wake
  *   pv_latency_kick	- average latency (ns) of vCPU kick operation
  *   pv_latency_wake	- average latency (ns) from vCPU kick to wakeup
- *   pv_lock_slowpath	- # of locking operations via the slowpath
  *   pv_lock_stealing	- # of lock stealing operations
  *   pv_spurious_wakeup	- # of spurious wakeups in non-head vCPUs
  *   pv_wait_again	- # of wait's after a queue head vCPU kick
  *   pv_wait_early	- # of early vCPU wait's
  *   pv_wait_head	- # of vCPU wait's at the queue head
  *   pv_wait_node	- # of vCPU wait's at a non-head queue node
+ *   lock_pending	- # of locking operations via pending code
+ *   lock_slowpath	- # of locking operations via MCS lock queue
  *
  * Writing to the "reset_counters" file will reset all the above counter
  * values.
@@ -46,13 +47,14 @@ enum qlock_stats {
 	qstat_pv_kick_wake,
 	qstat_pv_latency_kick,
 	qstat_pv_latency_wake,
-	qstat_pv_lock_slowpath,
 	qstat_pv_lock_stealing,
 	qstat_pv_spurious_wakeup,
 	qstat_pv_wait_again,
 	qstat_pv_wait_early,
 	qstat_pv_wait_head,
 	qstat_pv_wait_node,
+	qstat_lock_pending,
+	qstat_lock_slowpath,
 	qstat_num,	/* Total number of statistical counters */
 	qstat_reset_cnts = qstat_num,
 };
@@ -73,12 +75,13 @@ static const char * const qstat_names[qstat_num + 1] = {
 	[qstat_pv_spurious_wakeup] = "pv_spurious_wakeup",
 	[qstat_pv_latency_kick]	   = "pv_latency_kick",
 	[qstat_pv_latency_wake]    = "pv_latency_wake",
-	[qstat_pv_lock_slowpath]   = "pv_lock_slowpath",
 	[qstat_pv_lock_stealing]   = "pv_lock_stealing",
 	[qstat_pv_wait_again]      = "pv_wait_again",
 	[qstat_pv_wait_early]      = "pv_wait_early",
 	[qstat_pv_wait_head]       = "pv_wait_head",
 	[qstat_pv_wait_node]       = "pv_wait_node",
+	[qstat_lock_pending]       = "lock_pending",
+	[qstat_lock_slowpath]      = "lock_slowpath",
 	[qstat_reset_cnts]         = "reset_counters",
 };
 
diff --git a/kernel/locking/rwsem-xadd.c b/kernel/locking/rwsem-xadd.c
index e795908f3607..3064c50e181e 100644
--- a/kernel/locking/rwsem-xadd.c
+++ b/kernel/locking/rwsem-xadd.c
@@ -347,30 +347,31 @@ static inline bool rwsem_try_write_lock_unqueued(struct rw_semaphore *sem)
 	}
 }
 
+static inline bool owner_on_cpu(struct task_struct *owner)
+{
+	/*
+	 * As lock holder preemption issue, we both skip spinning if
+	 * task is not on cpu or its cpu is preempted
+	 */
+	return owner->on_cpu && !vcpu_is_preempted(task_cpu(owner));
+}
+
 static inline bool rwsem_can_spin_on_owner(struct rw_semaphore *sem)
 {
 	struct task_struct *owner;
 	bool ret = true;
 
+	BUILD_BUG_ON(!rwsem_has_anonymous_owner(RWSEM_OWNER_UNKNOWN));
+
 	if (need_resched())
 		return false;
 
 	rcu_read_lock();
 	owner = READ_ONCE(sem->owner);
-	if (!rwsem_owner_is_writer(owner)) {
-		/*
-		 * Don't spin if the rwsem is readers owned.
-		 */
-		ret = !rwsem_owner_is_reader(owner);
-		goto done;
+	if (owner) {
+		ret = is_rwsem_owner_spinnable(owner) &&
+		      owner_on_cpu(owner);
 	}
-
-	/*
-	 * As lock holder preemption issue, we both skip spinning if task is not
-	 * on cpu or its cpu is preempted
-	 */
-	ret = owner->on_cpu && !vcpu_is_preempted(task_cpu(owner));
-done:
 	rcu_read_unlock();
 	return ret;
 }
@@ -382,11 +383,11 @@ static noinline bool rwsem_spin_on_owner(struct rw_semaphore *sem)
 {
 	struct task_struct *owner = READ_ONCE(sem->owner);
 
-	if (!rwsem_owner_is_writer(owner))
-		goto out;
+	if (!is_rwsem_owner_spinnable(owner))
+		return false;
 
 	rcu_read_lock();
-	while (sem->owner == owner) {
+	while (owner && (READ_ONCE(sem->owner) == owner)) {
 		/*
 		 * Ensure we emit the owner->on_cpu, dereference _after_
 		 * checking sem->owner still matches owner, if that fails,
@@ -399,8 +400,7 @@ static noinline bool rwsem_spin_on_owner(struct rw_semaphore *sem)
 		 * abort spinning when need_resched or owner is not running or
 		 * owner's cpu is preempted.
 		 */
-		if (!owner->on_cpu || need_resched() ||
-				vcpu_is_preempted(task_cpu(owner))) {
+		if (need_resched() || !owner_on_cpu(owner)) {
 			rcu_read_unlock();
 			return false;
 		}
@@ -408,12 +408,12 @@ static noinline bool rwsem_spin_on_owner(struct rw_semaphore *sem)
 		cpu_relax();
 	}
 	rcu_read_unlock();
-out:
+
 	/*
 	 * If there is a new owner or the owner is not set, we continue
 	 * spinning.
 	 */
-	return !rwsem_owner_is_reader(READ_ONCE(sem->owner));
+	return is_rwsem_owner_spinnable(READ_ONCE(sem->owner));
 }
 
 static bool rwsem_optimistic_spin(struct rw_semaphore *sem)
diff --git a/kernel/locking/rwsem.c b/kernel/locking/rwsem.c
index 30465a2f2b6c..776308d2fa9e 100644
--- a/kernel/locking/rwsem.c
+++ b/kernel/locking/rwsem.c
@@ -181,6 +181,7 @@ void down_read_non_owner(struct rw_semaphore *sem)
 	might_sleep();
 
 	__down_read(sem);
+	rwsem_set_reader_owned(sem);
 }
 
 EXPORT_SYMBOL(down_read_non_owner);
@@ -221,5 +222,3 @@ void up_read_non_owner(struct rw_semaphore *sem)
 EXPORT_SYMBOL(up_read_non_owner);
 
 #endif
-
-
diff --git a/kernel/locking/rwsem.h b/kernel/locking/rwsem.h
index a17cba8d94bb..b9d0e72aa80f 100644
--- a/kernel/locking/rwsem.h
+++ b/kernel/locking/rwsem.h
@@ -1,20 +1,24 @@
 /* SPDX-License-Identifier: GPL-2.0 */
 /*
  * The owner field of the rw_semaphore structure will be set to
- * RWSEM_READ_OWNED when a reader grabs the lock. A writer will clear
+ * RWSEM_READER_OWNED when a reader grabs the lock. A writer will clear
  * the owner field when it unlocks. A reader, on the other hand, will
  * not touch the owner field when it unlocks.
  *
- * In essence, the owner field now has the following 3 states:
+ * In essence, the owner field now has the following 4 states:
  *  1) 0
  *     - lock is free or the owner hasn't set the field yet
  *  2) RWSEM_READER_OWNED
  *     - lock is currently or previously owned by readers (lock is free
  *       or not set by owner yet)
- *  3) Other non-zero value
- *     - a writer owns the lock
+ *  3) RWSEM_ANONYMOUSLY_OWNED bit set with some other bits set as well
+ *     - lock is owned by an anonymous writer, so spinning on the lock
+ *       owner should be disabled.
+ *  4) Other non-zero value
+ *     - a writer owns the lock and other writers can spin on the lock owner.
  */
-#define RWSEM_READER_OWNED	((struct task_struct *)1UL)
+#define RWSEM_ANONYMOUSLY_OWNED	(1UL << 0)
+#define RWSEM_READER_OWNED	((struct task_struct *)RWSEM_ANONYMOUSLY_OWNED)
 
 #ifdef CONFIG_DEBUG_RWSEMS
 # define DEBUG_RWSEMS_WARN_ON(c)	DEBUG_LOCKS_WARN_ON(c)
@@ -51,14 +55,22 @@ static inline void rwsem_set_reader_owned(struct rw_semaphore *sem)
 		WRITE_ONCE(sem->owner, RWSEM_READER_OWNED);
 }
 
-static inline bool rwsem_owner_is_writer(struct task_struct *owner)
+/*
+ * Return true if the a rwsem waiter can spin on the rwsem's owner
+ * and steal the lock, i.e. the lock is not anonymously owned.
+ * N.B. !owner is considered spinnable.
+ */
+static inline bool is_rwsem_owner_spinnable(struct task_struct *owner)
 {
-	return owner && owner != RWSEM_READER_OWNED;
+	return !((unsigned long)owner & RWSEM_ANONYMOUSLY_OWNED);
 }
 
-static inline bool rwsem_owner_is_reader(struct task_struct *owner)
+/*
+ * Return true if rwsem is owned by an anonymous writer or readers.
+ */
+static inline bool rwsem_has_anonymous_owner(struct task_struct *owner)
 {
-	return owner == RWSEM_READER_OWNED;
+	return (unsigned long)owner & RWSEM_ANONYMOUSLY_OWNED;
 }
 #else
 static inline void rwsem_set_owner(struct rw_semaphore *sem)
diff --git a/kernel/locking/test-ww_mutex.c b/kernel/locking/test-ww_mutex.c
index 0e4cd64ad2c0..5b915b370d5a 100644
--- a/kernel/locking/test-ww_mutex.c
+++ b/kernel/locking/test-ww_mutex.c
@@ -26,7 +26,7 @@
 #include <linux/slab.h>
 #include <linux/ww_mutex.h>
 
-static DEFINE_WW_CLASS(ww_class);
+static DEFINE_WD_CLASS(ww_class);
 struct workqueue_struct *wq;
 
 struct test_mutex {