Merge branch 'core-locking-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull core locking changes from Ingo Molnar:
 - futex performance increases: larger hashes, smarter wakeups
 - mutex debugging improvements
 - lots of SMP ordering documentation updates
 - introduce the smp_load_acquire(), smp_store_release() primitives.
   (There are WIP patches that make use of them - not yet merged)
 - lockdep micro-optimizations
 - lockdep improvement: better cover IRQ contexts
 - liblockdep at last. We'll continue to monitor how useful this is

* 'core-locking-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (34 commits)
  futexes: Fix futex_hashsize initialization
  arch: Re-sort some Kbuild files to hopefully help avoid some conflicts
  futexes: Avoid taking the hb->lock if there's nothing to wake up
  futexes: Document multiprocessor ordering guarantees
  futexes: Increase hash table size for better performance
  futexes: Clean up various details
  arch: Introduce smp_load_acquire(), smp_store_release()
  arch: Clean up asm/barrier.h implementations using asm-generic/barrier.h
  arch: Move smp_mb__{before,after}_atomic_{inc,dec}.h into asm/atomic.h
  locking/doc: Rename LOCK/UNLOCK to ACQUIRE/RELEASE
  mutexes: Give more informative mutex warning in the !lock->owner case
  powerpc: Full barrier for smp_mb__after_unlock_lock()
  rcu: Apply smp_mb__after_unlock_lock() to preserve grace periods
  Documentation/memory-barriers.txt: Downgrade UNLOCK+BLOCK
  locking: Add an smp_mb__after_unlock_lock() for UNLOCK+BLOCK barrier
  Documentation/memory-barriers.txt: Document ACCESS_ONCE()
  Documentation/memory-barriers.txt: Prohibit speculative writes
  Documentation/memory-barriers.txt: Add long atomic examples to memory-barriers.txt
  Documentation/memory-barriers.txt: Add needed ACCESS_ONCE() calls to memory-barriers.txt
  Revert "smp/cpumask: Make CONFIG_CPUMASK_OFFSTACK=y usable without debug dependency"
  ...

6 files changed, 242 insertions, 50 deletions

diff --git a/kernel/futex.c b/kernel/futex.c
index f6ff0191ecf7..1ddc4498f1e1 100644
--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -63,14 +63,101 @@
 #include <linux/sched/rt.h>
 #include <linux/hugetlb.h>
 #include <linux/freezer.h>
+#include <linux/bootmem.h>
 
 #include <asm/futex.h>
 
 #include "locking/rtmutex_common.h"
 
-int __read_mostly futex_cmpxchg_enabled;
+/*
+ * Basic futex operation and ordering guarantees:
+ *
+ * The waiter reads the futex value in user space and calls
+ * futex_wait(). This function computes the hash bucket and acquires
+ * the hash bucket lock. After that it reads the futex user space value
+ * again and verifies that the data has not changed. If it has not changed
+ * it enqueues itself into the hash bucket, releases the hash bucket lock
+ * and schedules.
+ *
+ * The waker side modifies the user space value of the futex and calls
+ * futex_wake(). This function computes the hash bucket and acquires the
+ * hash bucket lock. Then it looks for waiters on that futex in the hash
+ * bucket and wakes them.
+ *
+ * In futex wake up scenarios where no tasks are blocked on a futex, taking
+ * the hb spinlock can be avoided and simply return. In order for this
+ * optimization to work, ordering guarantees must exist so that the waiter
+ * being added to the list is acknowledged when the list is concurrently being
+ * checked by the waker, avoiding scenarios like the following:
+ *
+ * CPU 0                               CPU 1
+ * val = *futex;
+ * sys_futex(WAIT, futex, val);
+ *   futex_wait(futex, val);
+ *   uval = *futex;
+ *                                     *futex = newval;
+ *                                     sys_futex(WAKE, futex);
+ *                                       futex_wake(futex);
+ *                                       if (queue_empty())
+ *                                         return;
+ *   if (uval == val)
+ *      lock(hash_bucket(futex));
+ *      queue();
+ *     unlock(hash_bucket(futex));
+ *     schedule();
+ *
+ * This would cause the waiter on CPU 0 to wait forever because it
+ * missed the transition of the user space value from val to newval
+ * and the waker did not find the waiter in the hash bucket queue.
+ *
+ * The correct serialization ensures that a waiter either observes
+ * the changed user space value before blocking or is woken by a
+ * concurrent waker:
+ *
+ * CPU 0                                 CPU 1
+ * val = *futex;
+ * sys_futex(WAIT, futex, val);
+ *   futex_wait(futex, val);
+ *
+ *   waiters++;
+ *   mb(); (A) <-- paired with -.
+ *                              |
+ *   lock(hash_bucket(futex));  |
+ *                              |
+ *   uval = *futex;             |
+ *                              |        *futex = newval;
+ *                              |        sys_futex(WAKE, futex);
+ *                              |          futex_wake(futex);
+ *                              |
+ *                              `------->  mb(); (B)
+ *   if (uval == val)
+ *     queue();
+ *     unlock(hash_bucket(futex));
+ *     schedule();                         if (waiters)
+ *                                           lock(hash_bucket(futex));
+ *                                           wake_waiters(futex);
+ *                                           unlock(hash_bucket(futex));
+ *
+ * Where (A) orders the waiters increment and the futex value read -- this
+ * is guaranteed by the head counter in the hb spinlock; and where (B)
+ * orders the write to futex and the waiters read -- this is done by the
+ * barriers in get_futex_key_refs(), through either ihold or atomic_inc,
+ * depending on the futex type.
+ *
+ * This yields the following case (where X:=waiters, Y:=futex):
+ *
+ *	X = Y = 0
+ *
+ *	w[X]=1		w[Y]=1
+ *	MB		MB
+ *	r[Y]=y		r[X]=x
+ *
+ * Which guarantees that x==0 && y==0 is impossible; which translates back into
+ * the guarantee that we cannot both miss the futex variable change and the
+ * enqueue.
+ */
 
-#define FUTEX_HASHBITS (CONFIG_BASE_SMALL ? 4 : 8)
+int __read_mostly futex_cmpxchg_enabled;
 
 /*
  * Futex flags used to encode options to functions and preserve them across
@@ -149,9 +236,41 @@ static const struct futex_q futex_q_init = {
 struct futex_hash_bucket {
 	spinlock_t lock;
 	struct plist_head chain;
-};
+} ____cacheline_aligned_in_smp;
 
-static struct futex_hash_bucket futex_queues[1<<FUTEX_HASHBITS];
+static unsigned long __read_mostly futex_hashsize;
+
+static struct futex_hash_bucket *futex_queues;
+
+static inline void futex_get_mm(union futex_key *key)
+{
+	atomic_inc(&key->private.mm->mm_count);
+	/*
+	 * Ensure futex_get_mm() implies a full barrier such that
+	 * get_futex_key() implies a full barrier. This is relied upon
+	 * as full barrier (B), see the ordering comment above.
+	 */
+	smp_mb__after_atomic_inc();
+}
+
+static inline bool hb_waiters_pending(struct futex_hash_bucket *hb)
+{
+#ifdef CONFIG_SMP
+	/*
+	 * Tasks trying to enter the critical region are most likely
+	 * potential waiters that will be added to the plist. Ensure
+	 * that wakers won't miss to-be-slept tasks in the window between
+	 * the wait call and the actual plist_add.
+	 */
+	if (spin_is_locked(&hb->lock))
+		return true;
+	smp_rmb(); /* Make sure we check the lock state first */
+
+	return !plist_head_empty(&hb->chain);
+#else
+	return true;
+#endif
+}
 
 /*
  * We hash on the keys returned from get_futex_key (see below).
@@ -161,7 +280,7 @@ static struct futex_hash_bucket *hash_futex(union futex_key *key)
 	u32 hash = jhash2((u32*)&key->both.word,
 			  (sizeof(key->both.word)+sizeof(key->both.ptr))/4,
 			  key->both.offset);
-	return &futex_queues[hash & ((1 << FUTEX_HASHBITS)-1)];
+	return &futex_queues[hash & (futex_hashsize - 1)];
 }
 
 /*
@@ -187,10 +306,10 @@ static void get_futex_key_refs(union futex_key *key)
 
 	switch (key->both.offset & (FUT_OFF_INODE|FUT_OFF_MMSHARED)) {
 	case FUT_OFF_INODE:
-		ihold(key->shared.inode);
+		ihold(key->shared.inode); /* implies MB (B) */
 		break;
 	case FUT_OFF_MMSHARED:
-		atomic_inc(&key->private.mm->mm_count);
+		futex_get_mm(key); /* implies MB (B) */
 		break;
 	}
 }
@@ -264,7 +383,7 @@ get_futex_key(u32 __user *uaddr, int fshared, union futex_key *key, int rw)
 	if (!fshared) {
 		key->private.mm = mm;
 		key->private.address = address;
-		get_futex_key_refs(key);
+		get_futex_key_refs(key);  /* implies MB (B) */
 		return 0;
 	}
 
@@ -371,7 +490,7 @@ again:
 		key->shared.pgoff = basepage_index(page);
 	}
 
-	get_futex_key_refs(key);
+	get_futex_key_refs(key); /* implies MB (B) */
 
 out:
 	unlock_page(page_head);
@@ -598,13 +717,10 @@ lookup_pi_state(u32 uval, struct futex_hash_bucket *hb,
 {
 	struct futex_pi_state *pi_state = NULL;
 	struct futex_q *this, *next;
-	struct plist_head *head;
 	struct task_struct *p;
 	pid_t pid = uval & FUTEX_TID_MASK;
 
-	head = &hb->chain;
-
-	plist_for_each_entry_safe(this, next, head, list) {
+	plist_for_each_entry_safe(this, next, &hb->chain, list) {
 		if (match_futex(&this->key, key)) {
 			/*
 			 * Another waiter already exists - bump up
@@ -986,7 +1102,6 @@ futex_wake(u32 __user *uaddr, unsigned int flags, int nr_wake, u32 bitset)
 {
 	struct futex_hash_bucket *hb;
 	struct futex_q *this, *next;
-	struct plist_head *head;
 	union futex_key key = FUTEX_KEY_INIT;
 	int ret;
 
@@ -998,10 +1113,14 @@ futex_wake(u32 __user *uaddr, unsigned int flags, int nr_wake, u32 bitset)
 		goto out;
 
 	hb = hash_futex(&key);
+
+	/* Make sure we really have tasks to wakeup */
+	if (!hb_waiters_pending(hb))
+		goto out_put_key;
+
 	spin_lock(&hb->lock);
-	head = &hb->chain;
 
-	plist_for_each_entry_safe(this, next, head, list) {
+	plist_for_each_entry_safe(this, next, &hb->chain, list) {
 		if (match_futex (&this->key, &key)) {
 			if (this->pi_state || this->rt_waiter) {
 				ret = -EINVAL;
@@ -1019,6 +1138,7 @@ futex_wake(u32 __user *uaddr, unsigned int flags, int nr_wake, u32 bitset)
 	}
 
 	spin_unlock(&hb->lock);
+out_put_key:
 	put_futex_key(&key);
 out:
 	return ret;
@@ -1034,7 +1154,6 @@ futex_wake_op(u32 __user *uaddr1, unsigned int flags, u32 __user *uaddr2,
 {
 	union futex_key key1 = FUTEX_KEY_INIT, key2 = FUTEX_KEY_INIT;
 	struct futex_hash_bucket *hb1, *hb2;
-	struct plist_head *head;
 	struct futex_q *this, *next;
 	int ret, op_ret;
 
@@ -1082,9 +1201,7 @@ retry_private:
 		goto retry;
 	}
 
-	head = &hb1->chain;
-
-	plist_for_each_entry_safe(this, next, head, list) {
+	plist_for_each_entry_safe(this, next, &hb1->chain, list) {
 		if (match_futex (&this->key, &key1)) {
 			if (this->pi_state || this->rt_waiter) {
 				ret = -EINVAL;
@@ -1097,10 +1214,8 @@ retry_private:
 	}
 
 	if (op_ret > 0) {
-		head = &hb2->chain;
-
 		op_ret = 0;
-		plist_for_each_entry_safe(this, next, head, list) {
+		plist_for_each_entry_safe(this, next, &hb2->chain, list) {
 			if (match_futex (&this->key, &key2)) {
 				if (this->pi_state || this->rt_waiter) {
 					ret = -EINVAL;
@@ -1270,7 +1385,6 @@ static int futex_requeue(u32 __user *uaddr1, unsigned int flags,
 	int drop_count = 0, task_count = 0, ret;
 	struct futex_pi_state *pi_state = NULL;
 	struct futex_hash_bucket *hb1, *hb2;
-	struct plist_head *head1;
 	struct futex_q *this, *next;
 	u32 curval2;
 
@@ -1393,8 +1507,7 @@ retry_private:
 		}
 	}
 
-	head1 = &hb1->chain;
-	plist_for_each_entry_safe(this, next, head1, list) {
+	plist_for_each_entry_safe(this, next, &hb1->chain, list) {
 		if (task_count - nr_wake >= nr_requeue)
 			break;
 
@@ -1489,12 +1602,12 @@ static inline struct futex_hash_bucket *queue_lock(struct futex_q *q)
 	hb = hash_futex(&q->key);
 	q->lock_ptr = &hb->lock;
 
-	spin_lock(&hb->lock);
+	spin_lock(&hb->lock); /* implies MB (A) */
 	return hb;
 }
 
 static inline void
-queue_unlock(struct futex_q *q, struct futex_hash_bucket *hb)
+queue_unlock(struct futex_hash_bucket *hb)
 	__releases(&hb->lock)
 {
 	spin_unlock(&hb->lock);
@@ -1867,7 +1980,7 @@ retry_private:
 	ret = get_futex_value_locked(&uval, uaddr);
 
 	if (ret) {
-		queue_unlock(q, *hb);
+		queue_unlock(*hb);
 
 		ret = get_user(uval, uaddr);
 		if (ret)
@@ -1881,7 +1994,7 @@ retry_private:
 	}
 
 	if (uval != val) {
-		queue_unlock(q, *hb);
+		queue_unlock(*hb);
 		ret = -EWOULDBLOCK;
 	}
 
@@ -2029,7 +2142,7 @@ retry_private:
 			 * Task is exiting and we just wait for the
 			 * exit to complete.
 			 */
-			queue_unlock(&q, hb);
+			queue_unlock(hb);
 			put_futex_key(&q.key);
 			cond_resched();
 			goto retry;
@@ -2081,7 +2194,7 @@ retry_private:
 	goto out_put_key;
 
 out_unlock_put_key:
-	queue_unlock(&q, hb);
+	queue_unlock(hb);
 
 out_put_key:
 	put_futex_key(&q.key);
@@ -2091,7 +2204,7 @@ out:
 	return ret != -EINTR ? ret : -ERESTARTNOINTR;
 
 uaddr_faulted:
-	queue_unlock(&q, hb);
+	queue_unlock(hb);
 
 	ret = fault_in_user_writeable(uaddr);
 	if (ret)
@@ -2113,7 +2226,6 @@ static int futex_unlock_pi(u32 __user *uaddr, unsigned int flags)
 {
 	struct futex_hash_bucket *hb;
 	struct futex_q *this, *next;
-	struct plist_head *head;
 	union futex_key key = FUTEX_KEY_INIT;
 	u32 uval, vpid = task_pid_vnr(current);
 	int ret;
@@ -2153,9 +2265,7 @@ retry:
 	 * Ok, other tasks may need to be woken up - check waiters
 	 * and do the wakeup if necessary:
 	 */
-	head = &hb->chain;
-
-	plist_for_each_entry_safe(this, next, head, list) {
+	plist_for_each_entry_safe(this, next, &hb->chain, list) {
 		if (!match_futex (&this->key, &key))
 			continue;
 		ret = wake_futex_pi(uaddr, uval, this);
@@ -2734,8 +2844,21 @@ SYSCALL_DEFINE6(futex, u32 __user *, uaddr, int, op, u32, val,
 static int __init futex_init(void)
 {
 	u32 curval;
-	int i;
+	unsigned int futex_shift;
+	unsigned long i;
+
+#if CONFIG_BASE_SMALL
+	futex_hashsize = 16;
+#else
+	futex_hashsize = roundup_pow_of_two(256 * num_possible_cpus());
+#endif
 
+	futex_queues = alloc_large_system_hash("futex", sizeof(*futex_queues),
+					       futex_hashsize, 0,
+					       futex_hashsize < 256 ? HASH_SMALL : 0,
+					       &futex_shift, NULL,
+					       futex_hashsize, futex_hashsize);
+	futex_hashsize = 1UL << futex_shift;
 	/*
 	 * This will fail and we want it. Some arch implementations do
 	 * runtime detection of the futex_atomic_cmpxchg_inatomic()
@@ -2749,7 +2872,7 @@ static int __init futex_init(void)
 	if (cmpxchg_futex_value_locked(&curval, NULL, 0, 0) == -EFAULT)
 		futex_cmpxchg_enabled = 1;
 
-	for (i = 0; i < ARRAY_SIZE(futex_queues); i++) {
+	for (i = 0; i < futex_hashsize; i++) {
 		plist_head_init(&futex_queues[i].chain);
 		spin_lock_init(&futex_queues[i].lock);
 	}
diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c
index 576ba756a32d..eb8a54783fa0 100644
--- a/kernel/locking/lockdep.c
+++ b/kernel/locking/lockdep.c
@@ -590,6 +590,7 @@ static int very_verbose(struct lock_class *class)
 /*
  * Is this the address of a static object:
  */
+#ifdef __KERNEL__
 static int static_obj(void *obj)
 {
 	unsigned long start = (unsigned long) &_stext,
@@ -616,6 +617,7 @@ static int static_obj(void *obj)
 	 */
 	return is_module_address(addr) || is_module_percpu_address(addr);
 }
+#endif
 
 /*
  * To make lock name printouts unique, we calculate a unique
@@ -4115,6 +4117,7 @@ void debug_check_no_locks_held(void)
 }
 EXPORT_SYMBOL_GPL(debug_check_no_locks_held);
 
+#ifdef __KERNEL__
 void debug_show_all_locks(void)
 {
 	struct task_struct *g, *p;
@@ -4172,6 +4175,7 @@ retry:
 		read_unlock(&tasklist_lock);
 }
 EXPORT_SYMBOL_GPL(debug_show_all_locks);
+#endif
 
 /*
  * Careful: only use this function if you are sure that
diff --git a/kernel/locking/mutex-debug.c b/kernel/locking/mutex-debug.c
index 7e3443fe1f48..faf6f5b53e77 100644
--- a/kernel/locking/mutex-debug.c
+++ b/kernel/locking/mutex-debug.c
@@ -75,7 +75,12 @@ void debug_mutex_unlock(struct mutex *lock)
 		return;
 
 	DEBUG_LOCKS_WARN_ON(lock->magic != lock);
-	DEBUG_LOCKS_WARN_ON(lock->owner != current);
+
+	if (!lock->owner)
+		DEBUG_LOCKS_WARN_ON(!lock->owner);
+	else
+		DEBUG_LOCKS_WARN_ON(lock->owner != current);
+
 	DEBUG_LOCKS_WARN_ON(!lock->wait_list.prev && !lock->wait_list.next);
 	mutex_clear_owner(lock);
 }
diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index dd081987a8ec..a6205a05b5e4 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -1133,8 +1133,10 @@ rcu_start_future_gp(struct rcu_node *rnp, struct rcu_data *rdp)
 	 * hold it, acquire the root rcu_node structure's lock in order to
 	 * start one (if needed).
 	 */
-	if (rnp != rnp_root)
+	if (rnp != rnp_root) {
 		raw_spin_lock(&rnp_root->lock);
+		smp_mb__after_unlock_lock();
+	}
 
 	/*
 	 * Get a new grace-period number.  If there really is no grace
@@ -1354,6 +1356,7 @@ static void note_gp_changes(struct rcu_state *rsp, struct rcu_data *rdp)
 		local_irq_restore(flags);
 		return;
 	}
+	smp_mb__after_unlock_lock();
 	__note_gp_changes(rsp, rnp, rdp);
 	raw_spin_unlock_irqrestore(&rnp->lock, flags);
 }
@@ -1368,6 +1371,7 @@ static int rcu_gp_init(struct rcu_state *rsp)
 
 	rcu_bind_gp_kthread();
 	raw_spin_lock_irq(&rnp->lock);
+	smp_mb__after_unlock_lock();
 	if (rsp->gp_flags == 0) {
 		/* Spurious wakeup, tell caller to go back to sleep.  */
 		raw_spin_unlock_irq(&rnp->lock);
@@ -1409,6 +1413,7 @@ static int rcu_gp_init(struct rcu_state *rsp)
 	 */
 	rcu_for_each_node_breadth_first(rsp, rnp) {
 		raw_spin_lock_irq(&rnp->lock);
+		smp_mb__after_unlock_lock();
 		rdp = this_cpu_ptr(rsp->rda);
 		rcu_preempt_check_blocked_tasks(rnp);
 		rnp->qsmask = rnp->qsmaskinit;
@@ -1463,6 +1468,7 @@ static int rcu_gp_fqs(struct rcu_state *rsp, int fqs_state_in)
 	/* Clear flag to prevent immediate re-entry. */
 	if (ACCESS_ONCE(rsp->gp_flags) & RCU_GP_FLAG_FQS) {
 		raw_spin_lock_irq(&rnp->lock);
+		smp_mb__after_unlock_lock();
 		rsp->gp_flags &= ~RCU_GP_FLAG_FQS;
 		raw_spin_unlock_irq(&rnp->lock);
 	}
@@ -1480,6 +1486,7 @@ static void rcu_gp_cleanup(struct rcu_state *rsp)
 	struct rcu_node *rnp = rcu_get_root(rsp);
 
 	raw_spin_lock_irq(&rnp->lock);
+	smp_mb__after_unlock_lock();
 	gp_duration = jiffies - rsp->gp_start;
 	if (gp_duration > rsp->gp_max)
 		rsp->gp_max = gp_duration;
@@ -1505,6 +1512,7 @@ static void rcu_gp_cleanup(struct rcu_state *rsp)
 	 */
 	rcu_for_each_node_breadth_first(rsp, rnp) {
 		raw_spin_lock_irq(&rnp->lock);
+		smp_mb__after_unlock_lock();
 		ACCESS_ONCE(rnp->completed) = rsp->gpnum;
 		rdp = this_cpu_ptr(rsp->rda);
 		if (rnp == rdp->mynode)
@@ -1515,6 +1523,7 @@ static void rcu_gp_cleanup(struct rcu_state *rsp)
 	}
 	rnp = rcu_get_root(rsp);
 	raw_spin_lock_irq(&rnp->lock);
+	smp_mb__after_unlock_lock();
 	rcu_nocb_gp_set(rnp, nocb);
 
 	rsp->completed = rsp->gpnum; /* Declare grace period done. */
@@ -1749,6 +1758,7 @@ rcu_report_qs_rnp(unsigned long mask, struct rcu_state *rsp,
 		rnp_c = rnp;
 		rnp = rnp->parent;
 		raw_spin_lock_irqsave(&rnp->lock, flags);
+		smp_mb__after_unlock_lock();
 		WARN_ON_ONCE(rnp_c->qsmask);
 	}
 
@@ -1778,6 +1788,7 @@ rcu_report_qs_rdp(int cpu, struct rcu_state *rsp, struct rcu_data *rdp)
 
 	rnp = rdp->mynode;
 	raw_spin_lock_irqsave(&rnp->lock, flags);
+	smp_mb__after_unlock_lock();
 	if (rdp->passed_quiesce == 0 || rdp->gpnum != rnp->gpnum ||
 	    rnp->completed == rnp->gpnum) {
 
@@ -1992,6 +2003,7 @@ static void rcu_cleanup_dead_cpu(int cpu, struct rcu_state *rsp)
 	mask = rdp->grpmask;	/* rnp->grplo is constant. */
 	do {
 		raw_spin_lock(&rnp->lock);	/* irqs already disabled. */
+		smp_mb__after_unlock_lock();
 		rnp->qsmaskinit &= ~mask;
 		if (rnp->qsmaskinit != 0) {
 			if (rnp != rdp->mynode)
@@ -2202,6 +2214,7 @@ static void force_qs_rnp(struct rcu_state *rsp,
 		cond_resched();
 		mask = 0;
 		raw_spin_lock_irqsave(&rnp->lock, flags);
+		smp_mb__after_unlock_lock();
 		if (!rcu_gp_in_progress(rsp)) {
 			raw_spin_unlock_irqrestore(&rnp->lock, flags);
 			return;
@@ -2231,6 +2244,7 @@ static void force_qs_rnp(struct rcu_state *rsp,
 	rnp = rcu_get_root(rsp);
 	if (rnp->qsmask == 0) {
 		raw_spin_lock_irqsave(&rnp->lock, flags);
+		smp_mb__after_unlock_lock();
 		rcu_initiate_boost(rnp, flags); /* releases rnp->lock. */
 	}
 }
@@ -2263,6 +2277,7 @@ static void force_quiescent_state(struct rcu_state *rsp)
 
 	/* Reached the root of the rcu_node tree, acquire lock. */
 	raw_spin_lock_irqsave(&rnp_old->lock, flags);
+	smp_mb__after_unlock_lock();
 	raw_spin_unlock(&rnp_old->fqslock);
 	if (ACCESS_ONCE(rsp->gp_flags) & RCU_GP_FLAG_FQS) {
 		rsp->n_force_qs_lh++;
@@ -2378,6 +2393,7 @@ static void __call_rcu_core(struct rcu_state *rsp, struct rcu_data *rdp,
 			struct rcu_node *rnp_root = rcu_get_root(rsp);
 
 			raw_spin_lock(&rnp_root->lock);
+			smp_mb__after_unlock_lock();
 			rcu_start_gp(rsp);
 			raw_spin_unlock(&rnp_root->lock);
 		} else {
diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h
index 08a765232432..506a7a97a2e2 100644
--- a/kernel/rcu/tree_plugin.h
+++ b/kernel/rcu/tree_plugin.h
@@ -204,6 +204,7 @@ static void rcu_preempt_note_context_switch(int cpu)
 		rdp = per_cpu_ptr(rcu_preempt_state.rda, cpu);
 		rnp = rdp->mynode;
 		raw_spin_lock_irqsave(&rnp->lock, flags);
+		smp_mb__after_unlock_lock();
 		t->rcu_read_unlock_special |= RCU_READ_UNLOCK_BLOCKED;
 		t->rcu_blocked_node = rnp;
 
@@ -312,6 +313,7 @@ static void rcu_report_unblock_qs_rnp(struct rcu_node *rnp, unsigned long flags)
 	mask = rnp->grpmask;
 	raw_spin_unlock(&rnp->lock);	/* irqs remain disabled. */
 	raw_spin_lock(&rnp_p->lock);	/* irqs already disabled. */
+	smp_mb__after_unlock_lock();
 	rcu_report_qs_rnp(mask, &rcu_preempt_state, rnp_p, flags);
 }
 
@@ -381,6 +383,7 @@ void rcu_read_unlock_special(struct task_struct *t)
 		for (;;) {
 			rnp = t->rcu_blocked_node;
 			raw_spin_lock(&rnp->lock);  /* irqs already disabled. */
+			smp_mb__after_unlock_lock();
 			if (rnp == t->rcu_blocked_node)
 				break;
 			raw_spin_unlock(&rnp->lock); /* irqs remain disabled. */
@@ -605,6 +608,7 @@ static int rcu_preempt_offline_tasks(struct rcu_state *rsp,
 	while (!list_empty(lp)) {
 		t = list_entry(lp->next, typeof(*t), rcu_node_entry);
 		raw_spin_lock(&rnp_root->lock); /* irqs already disabled */
+		smp_mb__after_unlock_lock();
 		list_del(&t->rcu_node_entry);
 		t->rcu_blocked_node = rnp_root;
 		list_add(&t->rcu_node_entry, lp_root);
@@ -629,6 +633,7 @@ static int rcu_preempt_offline_tasks(struct rcu_state *rsp,
 	 * in this case.
 	 */
 	raw_spin_lock(&rnp_root->lock); /* irqs already disabled */
+	smp_mb__after_unlock_lock();
 	if (rnp_root->boost_tasks != NULL &&
 	    rnp_root->boost_tasks != rnp_root->gp_tasks &&
 	    rnp_root->boost_tasks != rnp_root->exp_tasks)
@@ -772,6 +777,7 @@ static void rcu_report_exp_rnp(struct rcu_state *rsp, struct rcu_node *rnp,
 	unsigned long mask;
 
 	raw_spin_lock_irqsave(&rnp->lock, flags);
+	smp_mb__after_unlock_lock();
 	for (;;) {
 		if (!sync_rcu_preempt_exp_done(rnp)) {
 			raw_spin_unlock_irqrestore(&rnp->lock, flags);
@@ -787,6 +793,7 @@ static void rcu_report_exp_rnp(struct rcu_state *rsp, struct rcu_node *rnp,
 		raw_spin_unlock(&rnp->lock); /* irqs remain disabled */
 		rnp = rnp->parent;
 		raw_spin_lock(&rnp->lock); /* irqs already disabled */
+		smp_mb__after_unlock_lock();
 		rnp->expmask &= ~mask;
 	}
 }
@@ -806,6 +813,7 @@ sync_rcu_preempt_exp_init(struct rcu_state *rsp, struct rcu_node *rnp)
 	int must_wait = 0;
 
 	raw_spin_lock_irqsave(&rnp->lock, flags);
+	smp_mb__after_unlock_lock();
 	if (list_empty(&rnp->blkd_tasks)) {
 		raw_spin_unlock_irqrestore(&rnp->lock, flags);
 	} else {
@@ -886,6 +894,7 @@ void synchronize_rcu_expedited(void)
 	/* Initialize ->expmask for all non-leaf rcu_node structures. */
 	rcu_for_each_nonleaf_node_breadth_first(rsp, rnp) {
 		raw_spin_lock_irqsave(&rnp->lock, flags);
+		smp_mb__after_unlock_lock();
 		rnp->expmask = rnp->qsmaskinit;
 		raw_spin_unlock_irqrestore(&rnp->lock, flags);
 	}
@@ -1191,6 +1200,7 @@ static int rcu_boost(struct rcu_node *rnp)
 		return 0;  /* Nothing left to boost. */
 
 	raw_spin_lock_irqsave(&rnp->lock, flags);
+	smp_mb__after_unlock_lock();
 
 	/*
 	 * Recheck under the lock: all tasks in need of boosting
@@ -1377,6 +1387,7 @@ static int rcu_spawn_one_boost_kthread(struct rcu_state *rsp,
 	if (IS_ERR(t))
 		return PTR_ERR(t);
 	raw_spin_lock_irqsave(&rnp->lock, flags);
+	smp_mb__after_unlock_lock();
 	rnp->boost_kthread_task = t;
 	raw_spin_unlock_irqrestore(&rnp->lock, flags);
 	sp.sched_priority = RCU_BOOST_PRIO;
@@ -1769,6 +1780,7 @@ static void rcu_prepare_for_idle(int cpu)
 			continue;
 		rnp = rdp->mynode;
 		raw_spin_lock(&rnp->lock); /* irqs already disabled. */
+		smp_mb__after_unlock_lock();
 		rcu_accelerate_cbs(rsp, rnp, rdp);
 		raw_spin_unlock(&rnp->lock); /* irqs remain disabled. */
 	}
@@ -2209,6 +2221,7 @@ static void rcu_nocb_wait_gp(struct rcu_data *rdp)
 	struct rcu_node *rnp = rdp->mynode;
 
 	raw_spin_lock_irqsave(&rnp->lock, flags);
+	smp_mb__after_unlock_lock();
 	c = rcu_start_future_gp(rnp, rdp);
 	raw_spin_unlock_irqrestore(&rnp->lock, flags);
 
diff --git a/kernel/softirq.c b/kernel/softirq.c
index 11025ccc06dd..9a4500e4c189 100644
--- a/kernel/softirq.c
+++ b/kernel/softirq.c
@@ -211,14 +211,48 @@ EXPORT_SYMBOL(local_bh_enable_ip);
 #define MAX_SOFTIRQ_TIME  msecs_to_jiffies(2)
 #define MAX_SOFTIRQ_RESTART 10
 
+#ifdef CONFIG_TRACE_IRQFLAGS
+/*
+ * When we run softirqs from irq_exit() and thus on the hardirq stack we need
+ * to keep the lockdep irq context tracking as tight as possible in order to
+ * not miss-qualify lock contexts and miss possible deadlocks.
+ */
+
+static inline bool lockdep_softirq_start(void)
+{
+	bool in_hardirq = false;
+
+	if (trace_hardirq_context(current)) {
+		in_hardirq = true;
+		trace_hardirq_exit();
+	}
+
+	lockdep_softirq_enter();
+
+	return in_hardirq;
+}
+
+static inline void lockdep_softirq_end(bool in_hardirq)
+{
+	lockdep_softirq_exit();
+
+	if (in_hardirq)
+		trace_hardirq_enter();
+}
+#else
+static inline bool lockdep_softirq_start(void) { return false; }
+static inline void lockdep_softirq_end(bool in_hardirq) { }
+#endif
+
 asmlinkage void __do_softirq(void)
 {
-	struct softirq_action *h;
-	__u32 pending;
 	unsigned long end = jiffies + MAX_SOFTIRQ_TIME;
-	int cpu;
 	unsigned long old_flags = current->flags;
 	int max_restart = MAX_SOFTIRQ_RESTART;
+	struct softirq_action *h;
+	bool in_hardirq;
+	__u32 pending;
+	int cpu;
 
 	/*
 	 * Mask out PF_MEMALLOC s current task context is borrowed for the
@@ -231,7 +265,7 @@ asmlinkage void __do_softirq(void)
 	account_irq_enter_time(current);
 
 	__local_bh_disable(_RET_IP_, SOFTIRQ_OFFSET);
-	lockdep_softirq_enter();
+	in_hardirq = lockdep_softirq_start();
 
 	cpu = smp_processor_id();
 restart:
@@ -278,16 +312,13 @@ restart:
 		wakeup_softirqd();
 	}
 
-	lockdep_softirq_exit();
-
+	lockdep_softirq_end(in_hardirq);
 	account_irq_exit_time(current);
 	__local_bh_enable(SOFTIRQ_OFFSET);
 	WARN_ON_ONCE(in_interrupt());
 	tsk_restore_flags(current, old_flags, PF_MEMALLOC);
 }
 
-
-
 asmlinkage void do_softirq(void)
 {
 	__u32 pending;
@@ -375,13 +406,13 @@ void irq_exit(void)
 #endif
 
 	account_irq_exit_time(current);
-	trace_hardirq_exit();
 	preempt_count_sub(HARDIRQ_OFFSET);
 	if (!in_interrupt() && local_softirq_pending())
 		invoke_softirq();
 
 	tick_irq_exit();
 	rcu_irq_exit();
+	trace_hardirq_exit(); /* must be last! */
 }
 
 /*