Merge branch 'next' into for-linus

Prepare input updates for 5.11 merge window.

10 files changed, 234 insertions, 130 deletions

diff --git a/kernel/locking/Makefile b/kernel/locking/Makefile
index 45452facff3b..6d11cfb9b41f 100644
--- a/kernel/locking/Makefile
+++ b/kernel/locking/Makefile
@@ -5,6 +5,9 @@ KCOV_INSTRUMENT		:= n
 
 obj-y += mutex.o semaphore.o rwsem.o percpu-rwsem.o
 
+# Avoid recursion lockdep -> KCSAN -> ... -> lockdep.
+KCSAN_SANITIZE_lockdep.o := n
+
 ifdef CONFIG_FUNCTION_TRACER
 CFLAGS_REMOVE_lockdep.o = $(CC_FLAGS_FTRACE)
 CFLAGS_REMOVE_lockdep_proc.o = $(CC_FLAGS_FTRACE)
diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c
index ac10db66cc63..2facbbd146ec 100644
--- a/kernel/locking/lockdep.c
+++ b/kernel/locking/lockdep.c
@@ -393,28 +393,9 @@ void lockdep_init_task(struct task_struct *task)
 	task->lockdep_recursion = 0;
 }
 
-/*
- * Split the recrursion counter in two to readily detect 'off' vs recursion.
- */
-#define LOCKDEP_RECURSION_BITS	16
-#define LOCKDEP_OFF		(1U << LOCKDEP_RECURSION_BITS)
-#define LOCKDEP_RECURSION_MASK	(LOCKDEP_OFF - 1)
-
-void lockdep_off(void)
-{
-	current->lockdep_recursion += LOCKDEP_OFF;
-}
-EXPORT_SYMBOL(lockdep_off);
-
-void lockdep_on(void)
-{
-	current->lockdep_recursion -= LOCKDEP_OFF;
-}
-EXPORT_SYMBOL(lockdep_on);
-
-static inline void lockdep_recursion_finish(void)
+static __always_inline void lockdep_recursion_finish(void)
 {
-	if (WARN_ON_ONCE(--current->lockdep_recursion))
+	if (WARN_ON_ONCE((--current->lockdep_recursion) & LOCKDEP_RECURSION_MASK))
 		current->lockdep_recursion = 0;
 }
 
@@ -489,7 +470,7 @@ struct lock_trace {
 	struct hlist_node	hash_entry;
 	u32			hash;
 	u32			nr_entries;
-	unsigned long		entries[0] __aligned(sizeof(unsigned long));
+	unsigned long		entries[] __aligned(sizeof(unsigned long));
 };
 #define LOCK_TRACE_SIZE_IN_LONGS				\
 	(sizeof(struct lock_trace) / sizeof(unsigned long))
@@ -820,7 +801,7 @@ static int count_matching_names(struct lock_class *new_class)
 }
 
 /* used from NMI context -- must be lockless */
-static inline struct lock_class *
+static __always_inline struct lock_class *
 look_up_lock_class(const struct lockdep_map *lock, unsigned int subclass)
 {
 	struct lockdep_subclass_key *key;
@@ -1742,7 +1723,7 @@ static int noop_count(struct lock_list *entry, void *data)
 static unsigned long __lockdep_count_forward_deps(struct lock_list *this)
 {
 	unsigned long  count = 0;
-	struct lock_list *uninitialized_var(target_entry);
+	struct lock_list *target_entry;
 
 	__bfs_forwards(this, (void *)&count, noop_count, &target_entry);
 
@@ -1768,7 +1749,7 @@ unsigned long lockdep_count_forward_deps(struct lock_class *class)
 static unsigned long __lockdep_count_backward_deps(struct lock_list *this)
 {
 	unsigned long  count = 0;
-	struct lock_list *uninitialized_var(target_entry);
+	struct lock_list *target_entry;
 
 	__bfs_backwards(this, (void *)&count, noop_count, &target_entry);
 
@@ -1823,7 +1804,7 @@ check_noncircular(struct held_lock *src, struct held_lock *target,
 		  struct lock_trace **const trace)
 {
 	int ret;
-	struct lock_list *uninitialized_var(target_entry);
+	struct lock_list *target_entry;
 	struct lock_list src_entry = {
 		.class = hlock_class(src),
 		.parent = NULL,
@@ -1861,7 +1842,7 @@ static noinline int
 check_redundant(struct held_lock *src, struct held_lock *target)
 {
 	int ret;
-	struct lock_list *uninitialized_var(target_entry);
+	struct lock_list *target_entry;
 	struct lock_list src_entry = {
 		.class = hlock_class(src),
 		.parent = NULL,
@@ -2081,9 +2062,9 @@ print_bad_irq_dependency(struct task_struct *curr,
 	pr_warn("-----------------------------------------------------\n");
 	pr_warn("%s/%d [HC%u[%lu]:SC%u[%lu]:HE%u:SE%u] is trying to acquire:\n",
 		curr->comm, task_pid_nr(curr),
-		curr->hardirq_context, hardirq_count() >> HARDIRQ_SHIFT,
+		lockdep_hardirq_context(), hardirq_count() >> HARDIRQ_SHIFT,
 		curr->softirq_context, softirq_count() >> SOFTIRQ_SHIFT,
-		curr->hardirqs_enabled,
+		lockdep_hardirqs_enabled(),
 		curr->softirqs_enabled);
 	print_lock(next);
 
@@ -2263,8 +2244,8 @@ static int check_irq_usage(struct task_struct *curr, struct held_lock *prev,
 {
 	unsigned long usage_mask = 0, forward_mask, backward_mask;
 	enum lock_usage_bit forward_bit = 0, backward_bit = 0;
-	struct lock_list *uninitialized_var(target_entry1);
-	struct lock_list *uninitialized_var(target_entry);
+	struct lock_list *target_entry1;
+	struct lock_list *target_entry;
 	struct lock_list this, that;
 	int ret;
 
@@ -3350,9 +3331,9 @@ print_usage_bug(struct task_struct *curr, struct held_lock *this,
 
 	pr_warn("%s/%d [HC%u[%lu]:SC%u[%lu]:HE%u:SE%u] takes:\n",
 		curr->comm, task_pid_nr(curr),
-		lockdep_hardirq_context(curr), hardirq_count() >> HARDIRQ_SHIFT,
+		lockdep_hardirq_context(), hardirq_count() >> HARDIRQ_SHIFT,
 		lockdep_softirq_context(curr), softirq_count() >> SOFTIRQ_SHIFT,
-		lockdep_hardirqs_enabled(curr),
+		lockdep_hardirqs_enabled(),
 		lockdep_softirqs_enabled(curr));
 	print_lock(this);
 
@@ -3457,7 +3438,7 @@ check_usage_forwards(struct task_struct *curr, struct held_lock *this,
 {
 	int ret;
 	struct lock_list root;
-	struct lock_list *uninitialized_var(target_entry);
+	struct lock_list *target_entry;
 
 	root.parent = NULL;
 	root.class = hlock_class(this);
@@ -3484,7 +3465,7 @@ check_usage_backwards(struct task_struct *curr, struct held_lock *this,
 {
 	int ret;
 	struct lock_list root;
-	struct lock_list *uninitialized_var(target_entry);
+	struct lock_list *target_entry;
 
 	root.parent = NULL;
 	root.class = hlock_class(this);
@@ -3503,19 +3484,21 @@ check_usage_backwards(struct task_struct *curr, struct held_lock *this,
 
 void print_irqtrace_events(struct task_struct *curr)
 {
-	printk("irq event stamp: %u\n", curr->irq_events);
+	const struct irqtrace_events *trace = &curr->irqtrace;
+
+	printk("irq event stamp: %u\n", trace->irq_events);
 	printk("hardirqs last  enabled at (%u): [<%px>] %pS\n",
-		curr->hardirq_enable_event, (void *)curr->hardirq_enable_ip,
-		(void *)curr->hardirq_enable_ip);
+		trace->hardirq_enable_event, (void *)trace->hardirq_enable_ip,
+		(void *)trace->hardirq_enable_ip);
 	printk("hardirqs last disabled at (%u): [<%px>] %pS\n",
-		curr->hardirq_disable_event, (void *)curr->hardirq_disable_ip,
-		(void *)curr->hardirq_disable_ip);
+		trace->hardirq_disable_event, (void *)trace->hardirq_disable_ip,
+		(void *)trace->hardirq_disable_ip);
 	printk("softirqs last  enabled at (%u): [<%px>] %pS\n",
-		curr->softirq_enable_event, (void *)curr->softirq_enable_ip,
-		(void *)curr->softirq_enable_ip);
+		trace->softirq_enable_event, (void *)trace->softirq_enable_ip,
+		(void *)trace->softirq_enable_ip);
 	printk("softirqs last disabled at (%u): [<%px>] %pS\n",
-		curr->softirq_disable_event, (void *)curr->softirq_disable_ip,
-		(void *)curr->softirq_disable_ip);
+		trace->softirq_disable_event, (void *)trace->softirq_disable_ip,
+		(void *)trace->softirq_disable_ip);
 }
 
 static int HARDIRQ_verbose(struct lock_class *class)
@@ -3635,13 +3618,10 @@ mark_held_locks(struct task_struct *curr, enum lock_usage_bit base_bit)
 /*
  * Hardirqs will be enabled:
  */
-static void __trace_hardirqs_on_caller(unsigned long ip)
+static void __trace_hardirqs_on_caller(void)
 {
 	struct task_struct *curr = current;
 
-	/* we'll do an OFF -> ON transition: */
-	curr->hardirqs_enabled = 1;
-
 	/*
 	 * We are going to turn hardirqs on, so set the
 	 * usage bit for all held locks:
@@ -3654,20 +3634,33 @@ static void __trace_hardirqs_on_caller(unsigned long ip)
 	 * this bit from being set before)
 	 */
 	if (curr->softirqs_enabled)
-		if (!mark_held_locks(curr, LOCK_ENABLED_SOFTIRQ))
-			return;
-
-	curr->hardirq_enable_ip = ip;
-	curr->hardirq_enable_event = ++curr->irq_events;
-	debug_atomic_inc(hardirqs_on_events);
+		mark_held_locks(curr, LOCK_ENABLED_SOFTIRQ);
 }
 
-void lockdep_hardirqs_on(unsigned long ip)
+/**
+ * lockdep_hardirqs_on_prepare - Prepare for enabling interrupts
+ * @ip:		Caller address
+ *
+ * Invoked before a possible transition to RCU idle from exit to user or
+ * guest mode. This ensures that all RCU operations are done before RCU
+ * stops watching. After the RCU transition lockdep_hardirqs_on() has to be
+ * invoked to set the final state.
+ */
+void lockdep_hardirqs_on_prepare(unsigned long ip)
 {
-	if (unlikely(!debug_locks || current->lockdep_recursion))
+	if (unlikely(!debug_locks))
 		return;
 
-	if (unlikely(current->hardirqs_enabled)) {
+	/*
+	 * NMIs do not (and cannot) track lock dependencies, nothing to do.
+	 */
+	if (unlikely(in_nmi()))
+		return;
+
+	if (unlikely(current->lockdep_recursion & LOCKDEP_RECURSION_MASK))
+		return;
+
+	if (unlikely(lockdep_hardirqs_enabled())) {
 		/*
 		 * Neither irq nor preemption are disabled here
 		 * so this is racy by nature but losing one hit
@@ -3695,23 +3688,98 @@ void lockdep_hardirqs_on(unsigned long ip)
 	 * Can't allow enabling interrupts while in an interrupt handler,
 	 * that's general bad form and such. Recursion, limited stack etc..
 	 */
-	if (DEBUG_LOCKS_WARN_ON(current->hardirq_context))
+	if (DEBUG_LOCKS_WARN_ON(lockdep_hardirq_context()))
 		return;
 
+	current->hardirq_chain_key = current->curr_chain_key;
+
 	current->lockdep_recursion++;
-	__trace_hardirqs_on_caller(ip);
+	__trace_hardirqs_on_caller();
 	lockdep_recursion_finish();
 }
-NOKPROBE_SYMBOL(lockdep_hardirqs_on);
+EXPORT_SYMBOL_GPL(lockdep_hardirqs_on_prepare);
+
+void noinstr lockdep_hardirqs_on(unsigned long ip)
+{
+	struct irqtrace_events *trace = &current->irqtrace;
+
+	if (unlikely(!debug_locks))
+		return;
+
+	/*
+	 * NMIs can happen in the middle of local_irq_{en,dis}able() where the
+	 * tracking state and hardware state are out of sync.
+	 *
+	 * NMIs must save lockdep_hardirqs_enabled() to restore IRQ state from,
+	 * and not rely on hardware state like normal interrupts.
+	 */
+	if (unlikely(in_nmi())) {
+		if (!IS_ENABLED(CONFIG_TRACE_IRQFLAGS_NMI))
+			return;
+
+		/*
+		 * Skip:
+		 *  - recursion check, because NMI can hit lockdep;
+		 *  - hardware state check, because above;
+		 *  - chain_key check, see lockdep_hardirqs_on_prepare().
+		 */
+		goto skip_checks;
+	}
+
+	if (unlikely(current->lockdep_recursion & LOCKDEP_RECURSION_MASK))
+		return;
+
+	if (lockdep_hardirqs_enabled()) {
+		/*
+		 * Neither irq nor preemption are disabled here
+		 * so this is racy by nature but losing one hit
+		 * in a stat is not a big deal.
+		 */
+		__debug_atomic_inc(redundant_hardirqs_on);
+		return;
+	}
+
+	/*
+	 * We're enabling irqs and according to our state above irqs weren't
+	 * already enabled, yet we find the hardware thinks they are in fact
+	 * enabled.. someone messed up their IRQ state tracing.
+	 */
+	if (DEBUG_LOCKS_WARN_ON(!irqs_disabled()))
+		return;
+
+	/*
+	 * Ensure the lock stack remained unchanged between
+	 * lockdep_hardirqs_on_prepare() and lockdep_hardirqs_on().
+	 */
+	DEBUG_LOCKS_WARN_ON(current->hardirq_chain_key !=
+			    current->curr_chain_key);
+
+skip_checks:
+	/* we'll do an OFF -> ON transition: */
+	__this_cpu_write(hardirqs_enabled, 1);
+	trace->hardirq_enable_ip = ip;
+	trace->hardirq_enable_event = ++trace->irq_events;
+	debug_atomic_inc(hardirqs_on_events);
+}
+EXPORT_SYMBOL_GPL(lockdep_hardirqs_on);
 
 /*
  * Hardirqs were disabled:
  */
-void lockdep_hardirqs_off(unsigned long ip)
+void noinstr lockdep_hardirqs_off(unsigned long ip)
 {
-	struct task_struct *curr = current;
+	if (unlikely(!debug_locks))
+		return;
 
-	if (unlikely(!debug_locks || current->lockdep_recursion))
+	/*
+	 * Matching lockdep_hardirqs_on(), allow NMIs in the middle of lockdep;
+	 * they will restore the software state. This ensures the software
+	 * state is consistent inside NMIs as well.
+	 */
+	if (in_nmi()) {
+		if (!IS_ENABLED(CONFIG_TRACE_IRQFLAGS_NMI))
+			return;
+	} else if (current->lockdep_recursion & LOCKDEP_RECURSION_MASK)
 		return;
 
 	/*
@@ -3721,25 +3789,28 @@ void lockdep_hardirqs_off(unsigned long ip)
 	if (DEBUG_LOCKS_WARN_ON(!irqs_disabled()))
 		return;
 
-	if (curr->hardirqs_enabled) {
+	if (lockdep_hardirqs_enabled()) {
+		struct irqtrace_events *trace = &current->irqtrace;
+
 		/*
 		 * We have done an ON -> OFF transition:
 		 */
-		curr->hardirqs_enabled = 0;
-		curr->hardirq_disable_ip = ip;
-		curr->hardirq_disable_event = ++curr->irq_events;
+		__this_cpu_write(hardirqs_enabled, 0);
+		trace->hardirq_disable_ip = ip;
+		trace->hardirq_disable_event = ++trace->irq_events;
 		debug_atomic_inc(hardirqs_off_events);
-	} else
+	} else {
 		debug_atomic_inc(redundant_hardirqs_off);
+	}
 }
-NOKPROBE_SYMBOL(lockdep_hardirqs_off);
+EXPORT_SYMBOL_GPL(lockdep_hardirqs_off);
 
 /*
  * Softirqs will be enabled:
  */
 void lockdep_softirqs_on(unsigned long ip)
 {
-	struct task_struct *curr = current;
+	struct irqtrace_events *trace = &current->irqtrace;
 
 	if (unlikely(!debug_locks || current->lockdep_recursion))
 		return;
@@ -3751,7 +3822,7 @@ void lockdep_softirqs_on(unsigned long ip)
 	if (DEBUG_LOCKS_WARN_ON(!irqs_disabled()))
 		return;
 
-	if (curr->softirqs_enabled) {
+	if (current->softirqs_enabled) {
 		debug_atomic_inc(redundant_softirqs_on);
 		return;
 	}
@@ -3760,17 +3831,17 @@ void lockdep_softirqs_on(unsigned long ip)
 	/*
 	 * We'll do an OFF -> ON transition:
 	 */
-	curr->softirqs_enabled = 1;
-	curr->softirq_enable_ip = ip;
-	curr->softirq_enable_event = ++curr->irq_events;
+	current->softirqs_enabled = 1;
+	trace->softirq_enable_ip = ip;
+	trace->softirq_enable_event = ++trace->irq_events;
 	debug_atomic_inc(softirqs_on_events);
 	/*
 	 * We are going to turn softirqs on, so set the
 	 * usage bit for all held locks, if hardirqs are
 	 * enabled too:
 	 */
-	if (curr->hardirqs_enabled)
-		mark_held_locks(curr, LOCK_ENABLED_SOFTIRQ);
+	if (lockdep_hardirqs_enabled())
+		mark_held_locks(current, LOCK_ENABLED_SOFTIRQ);
 	lockdep_recursion_finish();
 }
 
@@ -3779,8 +3850,6 @@ void lockdep_softirqs_on(unsigned long ip)
  */
 void lockdep_softirqs_off(unsigned long ip)
 {
-	struct task_struct *curr = current;
-
 	if (unlikely(!debug_locks || current->lockdep_recursion))
 		return;
 
@@ -3790,13 +3859,15 @@ void lockdep_softirqs_off(unsigned long ip)
 	if (DEBUG_LOCKS_WARN_ON(!irqs_disabled()))
 		return;
 
-	if (curr->softirqs_enabled) {
+	if (current->softirqs_enabled) {
+		struct irqtrace_events *trace = &current->irqtrace;
+
 		/*
 		 * We have done an ON -> OFF transition:
 		 */
-		curr->softirqs_enabled = 0;
-		curr->softirq_disable_ip = ip;
-		curr->softirq_disable_event = ++curr->irq_events;
+		current->softirqs_enabled = 0;
+		trace->softirq_disable_ip = ip;
+		trace->softirq_disable_event = ++trace->irq_events;
 		debug_atomic_inc(softirqs_off_events);
 		/*
 		 * Whoops, we wanted softirqs off, so why aren't they?
@@ -3818,7 +3889,7 @@ mark_usage(struct task_struct *curr, struct held_lock *hlock, int check)
 	 */
 	if (!hlock->trylock) {
 		if (hlock->read) {
-			if (curr->hardirq_context)
+			if (lockdep_hardirq_context())
 				if (!mark_lock(curr, hlock,
 						LOCK_USED_IN_HARDIRQ_READ))
 					return 0;
@@ -3827,7 +3898,7 @@ mark_usage(struct task_struct *curr, struct held_lock *hlock, int check)
 						LOCK_USED_IN_SOFTIRQ_READ))
 					return 0;
 		} else {
-			if (curr->hardirq_context)
+			if (lockdep_hardirq_context())
 				if (!mark_lock(curr, hlock, LOCK_USED_IN_HARDIRQ))
 					return 0;
 			if (curr->softirq_context)
@@ -3865,7 +3936,7 @@ lock_used:
 
 static inline unsigned int task_irq_context(struct task_struct *task)
 {
-	return LOCK_CHAIN_HARDIRQ_CONTEXT * !!task->hardirq_context +
+	return LOCK_CHAIN_HARDIRQ_CONTEXT * !!lockdep_hardirq_context() +
 	       LOCK_CHAIN_SOFTIRQ_CONTEXT * !!task->softirq_context;
 }
 
@@ -3898,13 +3969,18 @@ static int separate_irq_context(struct task_struct *curr,
 static int mark_lock(struct task_struct *curr, struct held_lock *this,
 			     enum lock_usage_bit new_bit)
 {
-	unsigned int new_mask = 1 << new_bit, ret = 1;
+	unsigned int old_mask, new_mask, ret = 1;
 
 	if (new_bit >= LOCK_USAGE_STATES) {
 		DEBUG_LOCKS_WARN_ON(1);
 		return 0;
 	}
 
+	if (new_bit == LOCK_USED && this->read)
+		new_bit = LOCK_USED_READ;
+
+	new_mask = 1 << new_bit;
+
 	/*
 	 * If already set then do not dirty the cacheline,
 	 * nor do any checks:
@@ -3917,13 +3993,22 @@ static int mark_lock(struct task_struct *curr, struct held_lock *this,
 	/*
 	 * Make sure we didn't race:
 	 */
-	if (unlikely(hlock_class(this)->usage_mask & new_mask)) {
-		graph_unlock();
-		return 1;
-	}
+	if (unlikely(hlock_class(this)->usage_mask & new_mask))
+		goto unlock;
 
+	old_mask = hlock_class(this)->usage_mask;
 	hlock_class(this)->usage_mask |= new_mask;
 
+	/*
+	 * Save one usage_traces[] entry and map both LOCK_USED and
+	 * LOCK_USED_READ onto the same entry.
+	 */
+	if (new_bit == LOCK_USED || new_bit == LOCK_USED_READ) {
+		if (old_mask & (LOCKF_USED | LOCKF_USED_READ))
+			goto unlock;
+		new_bit = LOCK_USED;
+	}
+
 	if (!(hlock_class(this)->usage_traces[new_bit] = save_trace()))
 		return 0;
 
@@ -3937,6 +4022,7 @@ static int mark_lock(struct task_struct *curr, struct held_lock *this,
 			return 0;
 	}
 
+unlock:
 	graph_unlock();
 
 	/*
@@ -3958,7 +4044,7 @@ static inline short task_wait_context(struct task_struct *curr)
 	 * Set appropriate wait type for the context; for IRQs we have to take
 	 * into account force_irqthread as that is implied by PREEMPT_RT.
 	 */
-	if (curr->hardirq_context) {
+	if (lockdep_hardirq_context()) {
 		/*
 		 * Check if force_irqthreads will run us threaded.
 		 */
@@ -4399,7 +4485,7 @@ static void print_unlock_imbalance_bug(struct task_struct *curr,
 		curr->comm, task_pid_nr(curr));
 	print_lockdep_cache(lock);
 	pr_cont(") at:\n");
-	print_ip_sym(ip);
+	print_ip_sym(KERN_WARNING, ip);
 	pr_warn("but there are no more locks to release!\n");
 	pr_warn("\nother info that might help us debug this:\n");
 	lockdep_print_held_locks(curr);
@@ -4408,8 +4494,8 @@ static void print_unlock_imbalance_bug(struct task_struct *curr,
 	dump_stack();
 }
 
-static int match_held_lock(const struct held_lock *hlock,
-					const struct lockdep_map *lock)
+static noinstr int match_held_lock(const struct held_lock *hlock,
+				   const struct lockdep_map *lock)
 {
 	if (hlock->instance == lock)
 		return 1;
@@ -4696,7 +4782,7 @@ __lock_release(struct lockdep_map *lock, unsigned long ip)
 	return 0;
 }
 
-static nokprobe_inline
+static __always_inline
 int __lock_is_held(const struct lockdep_map *lock, int read)
 {
 	struct task_struct *curr = current;
@@ -4801,11 +4887,11 @@ static void check_flags(unsigned long flags)
 		return;
 
 	if (irqs_disabled_flags(flags)) {
-		if (DEBUG_LOCKS_WARN_ON(current->hardirqs_enabled)) {
+		if (DEBUG_LOCKS_WARN_ON(lockdep_hardirqs_enabled())) {
 			printk("possible reason: unannotated irqs-off.\n");
 		}
 	} else {
-		if (DEBUG_LOCKS_WARN_ON(!current->hardirqs_enabled)) {
+		if (DEBUG_LOCKS_WARN_ON(!lockdep_hardirqs_enabled())) {
 			printk("possible reason: unannotated irqs-on.\n");
 		}
 	}
@@ -4871,12 +4957,20 @@ static void verify_lock_unused(struct lockdep_map *lock, struct held_lock *hlock
 {
 #ifdef CONFIG_PROVE_LOCKING
 	struct lock_class *class = look_up_lock_class(lock, subclass);
+	unsigned long mask = LOCKF_USED;
 
 	/* if it doesn't have a class (yet), it certainly hasn't been used yet */
 	if (!class)
 		return;
 
-	if (!(class->usage_mask & LOCK_USED))
+	/*
+	 * READ locks only conflict with USED, such that if we only ever use
+	 * READ locks, there is no deadlock possible -- RCU.
+	 */
+	if (!hlock->read)
+		mask |= LOCKF_USED_READ;
+
+	if (!(class->usage_mask & mask))
 		return;
 
 	hlock->class_idx = class - lock_classes;
@@ -4906,6 +5000,8 @@ void lock_acquire(struct lockdep_map *lock, unsigned int subclass,
 {
 	unsigned long flags;
 
+	trace_lock_acquire(lock, subclass, trylock, read, check, nest_lock, ip);
+
 	if (unlikely(current->lockdep_recursion)) {
 		/* XXX allow trylock from NMI ?!? */
 		if (lockdep_nmi() && !trylock) {
@@ -4930,7 +5026,6 @@ void lock_acquire(struct lockdep_map *lock, unsigned int subclass,
 	check_flags(flags);
 
 	current->lockdep_recursion++;
-	trace_lock_acquire(lock, subclass, trylock, read, check, nest_lock, ip);
 	__lock_acquire(lock, subclass, trylock, read, check,
 		       irqs_disabled_flags(flags), nest_lock, ip, 0, 0);
 	lockdep_recursion_finish();
@@ -4942,13 +5037,15 @@ void lock_release(struct lockdep_map *lock, unsigned long ip)
 {
 	unsigned long flags;
 
+	trace_lock_release(lock, ip);
+
 	if (unlikely(current->lockdep_recursion))
 		return;
 
 	raw_local_irq_save(flags);
 	check_flags(flags);
+
 	current->lockdep_recursion++;
-	trace_lock_release(lock, ip);
 	if (__lock_release(lock, ip))
 		check_chain_key(current);
 	lockdep_recursion_finish();
@@ -4956,7 +5053,7 @@ void lock_release(struct lockdep_map *lock, unsigned long ip)
 }
 EXPORT_SYMBOL_GPL(lock_release);
 
-int lock_is_held_type(const struct lockdep_map *lock, int read)
+noinstr int lock_is_held_type(const struct lockdep_map *lock, int read)
 {
 	unsigned long flags;
 	int ret = 0;
@@ -5050,7 +5147,7 @@ static void print_lock_contention_bug(struct task_struct *curr,
 		curr->comm, task_pid_nr(curr));
 	print_lockdep_cache(lock);
 	pr_cont(") at:\n");
-	print_ip_sym(ip);
+	print_ip_sym(KERN_WARNING, ip);
 	pr_warn("but there are no locks held!\n");
 	pr_warn("\nother info that might help us debug this:\n");
 	lockdep_print_held_locks(curr);
@@ -5134,8 +5231,6 @@ __lock_acquired(struct lockdep_map *lock, unsigned long ip)
 		hlock->holdtime_stamp = now;
 	}
 
-	trace_lock_acquired(lock, ip);
-
 	stats = get_lock_stats(hlock_class(hlock));
 	if (waittime) {
 		if (hlock->read)
@@ -5154,6 +5249,8 @@ void lock_contended(struct lockdep_map *lock, unsigned long ip)
 {
 	unsigned long flags;
 
+	trace_lock_acquired(lock, ip);
+
 	if (unlikely(!lock_stat || !debug_locks))
 		return;
 
@@ -5163,7 +5260,6 @@ void lock_contended(struct lockdep_map *lock, unsigned long ip)
 	raw_local_irq_save(flags);
 	check_flags(flags);
 	current->lockdep_recursion++;
-	trace_lock_contended(lock, ip);
 	__lock_contended(lock, ip);
 	lockdep_recursion_finish();
 	raw_local_irq_restore(flags);
@@ -5174,6 +5270,8 @@ void lock_acquired(struct lockdep_map *lock, unsigned long ip)
 {
 	unsigned long flags;
 
+	trace_lock_contended(lock, ip);
+
 	if (unlikely(!lock_stat || !debug_locks))
 		return;
 
@@ -5826,9 +5924,7 @@ void lockdep_rcu_suspicious(const char *file, const int line, const char *s)
 	pr_warn("\n%srcu_scheduler_active = %d, debug_locks = %d\n",
 	       !rcu_lockdep_current_cpu_online()
 			? "RCU used illegally from offline CPU!\n"
-			: !rcu_is_watching()
-				? "RCU used illegally from idle CPU!\n"
-				: "",
+			: "",
 	       rcu_scheduler_active, debug_locks);
 
 	/*
diff --git a/kernel/locking/lockdep_internals.h b/kernel/locking/lockdep_internals.h
index baca699b94e9..b0be1560ed17 100644
--- a/kernel/locking/lockdep_internals.h
+++ b/kernel/locking/lockdep_internals.h
@@ -19,6 +19,7 @@ enum lock_usage_bit {
 #include "lockdep_states.h"
 #undef LOCKDEP_STATE
 	LOCK_USED,
+	LOCK_USED_READ,
 	LOCK_USAGE_STATES
 };
 
@@ -40,6 +41,7 @@ enum {
 #include "lockdep_states.h"
 #undef LOCKDEP_STATE
 	__LOCKF(USED)
+	__LOCKF(USED_READ)
 };
 
 #define LOCKDEP_STATE(__STATE)	LOCKF_ENABLED_##__STATE |
diff --git a/kernel/locking/lockdep_proc.c b/kernel/locking/lockdep_proc.c
index 5525cd3ba0c8..02ef87f50df2 100644
--- a/kernel/locking/lockdep_proc.c
+++ b/kernel/locking/lockdep_proc.c
@@ -423,7 +423,7 @@ static void seq_lock_time(struct seq_file *m, struct lock_time *lt)
 	seq_time(m, lt->min);
 	seq_time(m, lt->max);
 	seq_time(m, lt->total);
-	seq_time(m, lt->nr ? div_s64(lt->total, lt->nr) : 0);
+	seq_time(m, lt->nr ? div64_u64(lt->total, lt->nr) : 0);
 }
 
 static void seq_stats(struct seq_file *m, struct lock_stat_data *data)
diff --git a/kernel/locking/locktorture.c b/kernel/locking/locktorture.c
index 5efbfc68ce99..9cfa5e89cff7 100644
--- a/kernel/locking/locktorture.c
+++ b/kernel/locking/locktorture.c
@@ -436,8 +436,6 @@ static int torture_rtmutex_lock(void) __acquires(torture_rtmutex)
 
 static void torture_rtmutex_boost(struct torture_random_state *trsp)
 {
-	int policy;
-	struct sched_param param;
 	const unsigned int factor = 50000; /* yes, quite arbitrary */
 
 	if (!rt_task(current)) {
@@ -448,8 +446,7 @@ static void torture_rtmutex_boost(struct torture_random_state *trsp)
 		 */
 		if (trsp && !(torture_random(trsp) %
 			      (cxt.nrealwriters_stress * factor))) {
-			policy = SCHED_FIFO;
-			param.sched_priority = MAX_RT_PRIO - 1;
+			sched_set_fifo(current);
 		} else /* common case, do nothing */
 			return;
 	} else {
@@ -462,13 +459,10 @@ static void torture_rtmutex_boost(struct torture_random_state *trsp)
 		 */
 		if (!trsp || !(torture_random(trsp) %
 			       (cxt.nrealwriters_stress * factor * 2))) {
-			policy = SCHED_NORMAL;
-			param.sched_priority = 0;
+			sched_set_normal(current, 0);
 		} else /* common case, do nothing */
 			return;
 	}
-
-	sched_setscheduler_nocheck(current, policy, &param);
 }
 
 static void torture_rtmutex_delay(struct torture_random_state *trsp)
@@ -631,13 +625,13 @@ static int lock_torture_writer(void *arg)
 		cxt.cur_ops->writelock();
 		if (WARN_ON_ONCE(lock_is_write_held))
 			lwsp->n_lock_fail++;
-		lock_is_write_held = 1;
+		lock_is_write_held = true;
 		if (WARN_ON_ONCE(lock_is_read_held))
 			lwsp->n_lock_fail++; /* rare, but... */
 
 		lwsp->n_lock_acquired++;
 		cxt.cur_ops->write_delay(&rand);
-		lock_is_write_held = 0;
+		lock_is_write_held = false;
 		cxt.cur_ops->writeunlock();
 
 		stutter_wait("lock_torture_writer");
@@ -665,13 +659,13 @@ static int lock_torture_reader(void *arg)
 			schedule_timeout_uninterruptible(1);
 
 		cxt.cur_ops->readlock();
-		lock_is_read_held = 1;
+		lock_is_read_held = true;
 		if (WARN_ON_ONCE(lock_is_write_held))
 			lrsp->n_lock_fail++; /* rare, but... */
 
 		lrsp->n_lock_acquired++;
 		cxt.cur_ops->read_delay(&rand);
-		lock_is_read_held = 0;
+		lock_is_read_held = false;
 		cxt.cur_ops->readunlock();
 
 		stutter_wait("lock_torture_reader");
@@ -686,7 +680,7 @@ static int lock_torture_reader(void *arg)
 static void __torture_print_stats(char *page,
 				  struct lock_stress_stats *statp, bool write)
 {
-	bool fail = 0;
+	bool fail = false;
 	int i, n_stress;
 	long max = 0, min = statp ? statp[0].n_lock_acquired : 0;
 	long long sum = 0;
@@ -904,7 +898,7 @@ 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;
+		lock_is_write_held = false;
 		cxt.lwsa = kmalloc_array(cxt.nrealwriters_stress,
 					 sizeof(*cxt.lwsa),
 					 GFP_KERNEL);
@@ -935,7 +929,7 @@ static int __init lock_torture_init(void)
 		}
 
 		if (nreaders_stress) {
-			lock_is_read_held = 0;
+			lock_is_read_held = false;
 			cxt.lrsa = kmalloc_array(cxt.nrealreaders_stress,
 						 sizeof(*cxt.lrsa),
 						 GFP_KERNEL);
diff --git a/kernel/locking/osq_lock.c b/kernel/locking/osq_lock.c
index 1f7734949ac8..1de006ed3aa8 100644
--- a/kernel/locking/osq_lock.c
+++ b/kernel/locking/osq_lock.c
@@ -154,7 +154,11 @@ bool osq_lock(struct optimistic_spin_queue *lock)
 	 */
 
 	for (;;) {
-		if (prev->next == node &&
+		/*
+		 * cpu_relax() below implies a compiler barrier which would
+		 * prevent this comparison being optimized away.
+		 */
+		if (data_race(prev->next) == node &&
 		    cmpxchg(&prev->next, node, NULL) == node)
 			break;
 
diff --git a/kernel/locking/percpu-rwsem.c b/kernel/locking/percpu-rwsem.c
index 8bbafe3e5203..70a32a576f3f 100644
--- a/kernel/locking/percpu-rwsem.c
+++ b/kernel/locking/percpu-rwsem.c
@@ -45,7 +45,7 @@ EXPORT_SYMBOL_GPL(percpu_free_rwsem);
 
 static bool __percpu_down_read_trylock(struct percpu_rw_semaphore *sem)
 {
-	__this_cpu_inc(*sem->read_count);
+	this_cpu_inc(*sem->read_count);
 
 	/*
 	 * Due to having preemption disabled the decrement happens on
@@ -71,7 +71,7 @@ static bool __percpu_down_read_trylock(struct percpu_rw_semaphore *sem)
 	if (likely(!atomic_read_acquire(&sem->block)))
 		return true;
 
-	__this_cpu_dec(*sem->read_count);
+	this_cpu_dec(*sem->read_count);
 
 	/* Prod writer to re-evaluate readers_active_check() */
 	rcuwait_wake_up(&sem->writer);
diff --git a/kernel/locking/qspinlock.c b/kernel/locking/qspinlock.c
index b9515fcc9b29..cbff6ba53d56 100644
--- a/kernel/locking/qspinlock.c
+++ b/kernel/locking/qspinlock.c
@@ -581,4 +581,11 @@ EXPORT_SYMBOL(queued_spin_lock_slowpath);
 #include "qspinlock_paravirt.h"
 #include "qspinlock.c"
 
+bool nopvspin __initdata;
+static __init int parse_nopvspin(char *arg)
+{
+	nopvspin = true;
+	return 0;
+}
+early_param("nopvspin", parse_nopvspin);
 #endif
diff --git a/kernel/locking/rtmutex-debug.c b/kernel/locking/rtmutex-debug.c
index fd4fe1f5b458..36e69100e8e0 100644
--- a/kernel/locking/rtmutex-debug.c
+++ b/kernel/locking/rtmutex-debug.c
@@ -125,7 +125,7 @@ void debug_rt_mutex_print_deadlock(struct rt_mutex_waiter *waiter)
 
 	printk("\n%s/%d's [blocked] stackdump:\n\n",
 		task->comm, task_pid_nr(task));
-	show_stack(task, NULL);
+	show_stack(task, NULL, KERN_DEFAULT);
 	printk("\n%s/%d's [current] stackdump:\n\n",
 		current->comm, task_pid_nr(current));
 	dump_stack();
diff --git a/kernel/locking/rtmutex.c b/kernel/locking/rtmutex.c
index c9f090d64f00..cfdd5b93264d 100644
--- a/kernel/locking/rtmutex.c
+++ b/kernel/locking/rtmutex.c
@@ -141,7 +141,6 @@ static void fixup_rt_mutex_waiters(struct rt_mutex *lock)
  * set up.
  */
 #ifndef CONFIG_DEBUG_RT_MUTEXES
-# define rt_mutex_cmpxchg_relaxed(l,c,n) (cmpxchg_relaxed(&l->owner, c, n) == c)
 # define rt_mutex_cmpxchg_acquire(l,c,n) (cmpxchg_acquire(&l->owner, c, n) == c)
 # define rt_mutex_cmpxchg_release(l,c,n) (cmpxchg_release(&l->owner, c, n) == c)
 
@@ -202,7 +201,6 @@ static inline bool unlock_rt_mutex_safe(struct rt_mutex *lock,
 }
 
 #else
-# define rt_mutex_cmpxchg_relaxed(l,c,n)	(0)
 # define rt_mutex_cmpxchg_acquire(l,c,n)	(0)
 # define rt_mutex_cmpxchg_release(l,c,n)	(0)