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

Pull locking fixes from Thomas Gleixner:
 "The locking department delivers:

   - A rather large and intrusive bundle of fixes to address serious
     performance regressions introduced by the new rwsem / mcs
     technology.  Simpler solutions have been discussed, but they would
     have been ugly bandaids with more risk than doing the right thing.

   - Make the rwsem spin on owner technology opt-in for architectures
     and enable it only on the known to work ones.

   - A few fixes to the lockdep userspace library"

* 'locking-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  locking/rwsem: Add CONFIG_RWSEM_SPIN_ON_OWNER
  locking/mutex: Disable optimistic spinning on some architectures
  locking/rwsem: Reduce the size of struct rw_semaphore
  locking/rwsem: Rename 'activity' to 'count'
  locking/spinlocks/mcs: Micro-optimize osq_unlock()
  locking/spinlocks/mcs: Introduce and use init macro and function for osq locks
  locking/spinlocks/mcs: Convert osq lock to atomic_t to reduce overhead
  locking/spinlocks/mcs: Rename optimistic_spin_queue() to optimistic_spin_node()
  locking/rwsem: Allow conservative optimistic spinning when readers have lock
  tools/liblockdep: Account for bitfield changes in lockdeps lock_acquire
  tools/liblockdep: Remove debug print left over from development
  tools/liblockdep: Fix comparison of a boolean value with a value of 2

7 files changed, 85 insertions, 45 deletions

diff --git a/kernel/Kconfig.locks b/kernel/Kconfig.locks
index 35536d9c0964..76768ee812b2 100644
--- a/kernel/Kconfig.locks
+++ b/kernel/Kconfig.locks
@@ -220,9 +220,16 @@ config INLINE_WRITE_UNLOCK_IRQRESTORE
 
 endif
 
+config ARCH_SUPPORTS_ATOMIC_RMW
+        bool
+
 config MUTEX_SPIN_ON_OWNER
         def_bool y
-        depends on SMP && !DEBUG_MUTEXES
+        depends on SMP && !DEBUG_MUTEXES && ARCH_SUPPORTS_ATOMIC_RMW
+
+config RWSEM_SPIN_ON_OWNER
+       def_bool y
+       depends on SMP && RWSEM_XCHGADD_ALGORITHM && ARCH_SUPPORTS_ATOMIC_RMW
 
 config ARCH_USE_QUEUE_RWLOCK
         bool
diff --git a/kernel/locking/mcs_spinlock.c b/kernel/locking/mcs_spinlock.c
index 838dc9e00669..be9ee1559fca 100644
--- a/kernel/locking/mcs_spinlock.c
+++ b/kernel/locking/mcs_spinlock.c
@@ -14,21 +14,47 @@
  * called from interrupt context and we have preemption disabled while
  * spinning.
  */
-static DEFINE_PER_CPU_SHARED_ALIGNED(struct optimistic_spin_queue, osq_node);
+static DEFINE_PER_CPU_SHARED_ALIGNED(struct optimistic_spin_node, osq_node);
+
+/*
+ * We use the value 0 to represent "no CPU", thus the encoded value
+ * will be the CPU number incremented by 1.
+ */
+static inline int encode_cpu(int cpu_nr)
+{
+        return cpu_nr + 1;
+}
+
+static inline struct optimistic_spin_node *decode_cpu(int encoded_cpu_val)
+{
+        int cpu_nr = encoded_cpu_val - 1;
+
+        return per_cpu_ptr(&osq_node, cpu_nr);
+}
 
 /*
  * Get a stable @node->next pointer, either for unlock() or unqueue() purposes.
  * Can return NULL in case we were the last queued and we updated @lock instead.
  */
-static inline struct optimistic_spin_queue *
-osq_wait_next(struct optimistic_spin_queue **lock,
-              struct optimistic_spin_queue *node,
-              struct optimistic_spin_queue *prev)
+static inline struct optimistic_spin_node *
+osq_wait_next(struct optimistic_spin_queue *lock,
+              struct optimistic_spin_node *node,
+              struct optimistic_spin_node *prev)
 {
-        struct optimistic_spin_queue *next = NULL;
+        struct optimistic_spin_node *next = NULL;
+        int curr = encode_cpu(smp_processor_id());
+        int old;
+
+        /*
+         * If there is a prev node in queue, then the 'old' value will be
+         * the prev node's CPU #, else it's set to OSQ_UNLOCKED_VAL since if
+         * we're currently last in queue, then the queue will then become empty.
+         */
+        old = prev ? prev->cpu : OSQ_UNLOCKED_VAL;
 
         for (;;) {
-                if (*lock == node && cmpxchg(lock, node, prev) == node) {
+                if (atomic_read(&lock->tail) == curr &&
+                    atomic_cmpxchg(&lock->tail, curr, old) == curr) {
                         /*
                          * We were the last queued, we moved @lock back. @prev
                          * will now observe @lock and will complete its
@@ -59,18 +85,23 @@ osq_wait_next(struct optimistic_spin_queue **lock,
         return next;
 }
 
-bool osq_lock(struct optimistic_spin_queue **lock)
+bool osq_lock(struct optimistic_spin_queue *lock)
 {
-        struct optimistic_spin_queue *node = this_cpu_ptr(&osq_node);
-        struct optimistic_spin_queue *prev, *next;
+        struct optimistic_spin_node *node = this_cpu_ptr(&osq_node);
+        struct optimistic_spin_node *prev, *next;
+        int curr = encode_cpu(smp_processor_id());
+        int old;
 
         node->locked = 0;
         node->next = NULL;
+        node->cpu = curr;
 
-        node->prev = prev = xchg(lock, node);
-        if (likely(prev == NULL))
+        old = atomic_xchg(&lock->tail, curr);
+        if (old == OSQ_UNLOCKED_VAL)
                 return true;
 
+        prev = decode_cpu(old);
+        node->prev = prev;
         ACCESS_ONCE(prev->next) = node;
 
         /*
@@ -149,20 +180,21 @@ unqueue:
         return false;
 }
 
-void osq_unlock(struct optimistic_spin_queue **lock)
+void osq_unlock(struct optimistic_spin_queue *lock)
 {
-        struct optimistic_spin_queue *node = this_cpu_ptr(&osq_node);
-        struct optimistic_spin_queue *next;
+        struct optimistic_spin_node *node, *next;
+        int curr = encode_cpu(smp_processor_id());
 
         /*
          * Fast path for the uncontended case.
          */
-        if (likely(cmpxchg(lock, node, NULL) == node))
+        if (likely(atomic_cmpxchg(&lock->tail, curr, OSQ_UNLOCKED_VAL) == curr))
                 return;
 
         /*
          * Second most likely case.
          */
+        node = this_cpu_ptr(&osq_node);
         next = xchg(&node->next, NULL);
         if (next) {
                 ACCESS_ONCE(next->locked) = 1;
diff --git a/kernel/locking/mcs_spinlock.h b/kernel/locking/mcs_spinlock.h
index a2dbac4aca6b..74356dc0ce29 100644
--- a/kernel/locking/mcs_spinlock.h
+++ b/kernel/locking/mcs_spinlock.h
@@ -118,12 +118,13 @@ void mcs_spin_unlock(struct mcs_spinlock **lock, struct mcs_spinlock *node)
  * mutex_lock()/rwsem_down_{read,write}() etc.
  */
 
-struct optimistic_spin_queue {
-        struct optimistic_spin_queue *next, *prev;
+struct optimistic_spin_node {
+        struct optimistic_spin_node *next, *prev;
         int locked; /* 1 if lock acquired */
+        int cpu; /* encoded CPU # value */
 };
 
-extern bool osq_lock(struct optimistic_spin_queue **lock);
-extern void osq_unlock(struct optimistic_spin_queue **lock);
+extern bool osq_lock(struct optimistic_spin_queue *lock);
+extern void osq_unlock(struct optimistic_spin_queue *lock);
 
 #endif /* __LINUX_MCS_SPINLOCK_H */
diff --git a/kernel/locking/mutex.c b/kernel/locking/mutex.c
index bc73d33c6760..acca2c1a3c5e 100644
--- a/kernel/locking/mutex.c
+++ b/kernel/locking/mutex.c
@@ -60,7 +60,7 @@ __mutex_init(struct mutex *lock, const char *name, struct lock_class_key *key)
         INIT_LIST_HEAD(&lock->wait_list);
         mutex_clear_owner(lock);
 #ifdef CONFIG_MUTEX_SPIN_ON_OWNER
-        lock->osq = NULL;
+        osq_lock_init(&lock->osq);
 #endif
 
         debug_mutex_init(lock, name, key);
diff --git a/kernel/locking/rwsem-spinlock.c b/kernel/locking/rwsem-spinlock.c
index 9be8a9144978..2c93571162cb 100644
--- a/kernel/locking/rwsem-spinlock.c
+++ b/kernel/locking/rwsem-spinlock.c
@@ -26,7 +26,7 @@ int rwsem_is_locked(struct rw_semaphore *sem)
         unsigned long flags;
 
         if (raw_spin_trylock_irqsave(&sem->wait_lock, flags)) {
-                ret = (sem->activity != 0);
+                ret = (sem->count != 0);
                 raw_spin_unlock_irqrestore(&sem->wait_lock, flags);
         }
         return ret;
@@ -46,7 +46,7 @@ void __init_rwsem(struct rw_semaphore *sem, const char *name,
         debug_check_no_locks_freed((void *)sem, sizeof(*sem));
         lockdep_init_map(&sem->dep_map, name, key, 0);
 #endif
-        sem->activity = 0;
+        sem->count = 0;
         raw_spin_lock_init(&sem->wait_lock);
         INIT_LIST_HEAD(&sem->wait_list);
 }
@@ -95,7 +95,7 @@ __rwsem_do_wake(struct rw_semaphore *sem, int wakewrite)
                 waiter = list_entry(next, struct rwsem_waiter, list);
         } while (waiter->type != RWSEM_WAITING_FOR_WRITE);
 
-        sem->activity += woken;
+        sem->count += woken;
 
  out:
         return sem;
@@ -126,9 +126,9 @@ void __sched __down_read(struct rw_semaphore *sem)
 
         raw_spin_lock_irqsave(&sem->wait_lock, flags);
 
-        if (sem->activity >= 0 && list_empty(&sem->wait_list)) {
+        if (sem->count >= 0 && list_empty(&sem->wait_list)) {
                 /* granted */
-                sem->activity++;
+                sem->count++;
                 raw_spin_unlock_irqrestore(&sem->wait_lock, flags);
                 goto out;
         }
@@ -170,9 +170,9 @@ int __down_read_trylock(struct rw_semaphore *sem)
 
         raw_spin_lock_irqsave(&sem->wait_lock, flags);
 
-        if (sem->activity >= 0 && list_empty(&sem->wait_list)) {
+        if (sem->count >= 0 && list_empty(&sem->wait_list)) {
                 /* granted */
-                sem->activity++;
+                sem->count++;
                 ret = 1;
         }
 
@@ -206,7 +206,7 @@ void __sched __down_write_nested(struct rw_semaphore *sem, int subclass)
                  * itself into sleep and waiting for system woke it or someone
                  * else in the head of the wait list up.
                  */
-                if (sem->activity == 0)
+                if (sem->count == 0)
                         break;
                 set_task_state(tsk, TASK_UNINTERRUPTIBLE);
                 raw_spin_unlock_irqrestore(&sem->wait_lock, flags);
@@ -214,7 +214,7 @@ void __sched __down_write_nested(struct rw_semaphore *sem, int subclass)
                 raw_spin_lock_irqsave(&sem->wait_lock, flags);
         }
         /* got the lock */
-        sem->activity = -1;
+        sem->count = -1;
         list_del(&waiter.list);
 
         raw_spin_unlock_irqrestore(&sem->wait_lock, flags);
@@ -235,9 +235,9 @@ int __down_write_trylock(struct rw_semaphore *sem)
 
         raw_spin_lock_irqsave(&sem->wait_lock, flags);
 
-        if (sem->activity == 0) {
+        if (sem->count == 0) {
                 /* got the lock */
-                sem->activity = -1;
+                sem->count = -1;
                 ret = 1;
         }
 
@@ -255,7 +255,7 @@ void __up_read(struct rw_semaphore *sem)
 
         raw_spin_lock_irqsave(&sem->wait_lock, flags);
 
-        if (--sem->activity == 0 && !list_empty(&sem->wait_list))
+        if (--sem->count == 0 && !list_empty(&sem->wait_list))
                 sem = __rwsem_wake_one_writer(sem);
 
         raw_spin_unlock_irqrestore(&sem->wait_lock, flags);
@@ -270,7 +270,7 @@ void __up_write(struct rw_semaphore *sem)
 
         raw_spin_lock_irqsave(&sem->wait_lock, flags);
 
-        sem->activity = 0;
+        sem->count = 0;
         if (!list_empty(&sem->wait_list))
                 sem = __rwsem_do_wake(sem, 1);
 
@@ -287,7 +287,7 @@ void __downgrade_write(struct rw_semaphore *sem)
 
         raw_spin_lock_irqsave(&sem->wait_lock, flags);
 
-        sem->activity = 1;
+        sem->count = 1;
         if (!list_empty(&sem->wait_list))
                 sem = __rwsem_do_wake(sem, 0);
 
diff --git a/kernel/locking/rwsem-xadd.c b/kernel/locking/rwsem-xadd.c
index dacc32142fcc..a2391ac135c8 100644
--- a/kernel/locking/rwsem-xadd.c
+++ b/kernel/locking/rwsem-xadd.c
@@ -82,9 +82,9 @@ void __init_rwsem(struct rw_semaphore *sem, const char *name,
         sem->count = RWSEM_UNLOCKED_VALUE;
         raw_spin_lock_init(&sem->wait_lock);
         INIT_LIST_HEAD(&sem->wait_list);
-#ifdef CONFIG_SMP
+#ifdef CONFIG_RWSEM_SPIN_ON_OWNER
         sem->owner = NULL;
-        sem->osq = NULL;
+        osq_lock_init(&sem->osq);
 #endif
 }
 
@@ -262,7 +262,7 @@ static inline bool rwsem_try_write_lock(long count, struct rw_semaphore *sem)
         return false;
 }
 
-#ifdef CONFIG_SMP
+#ifdef CONFIG_RWSEM_SPIN_ON_OWNER
 /*
  * Try to acquire write lock before the writer has been put on wait queue.
  */
@@ -285,10 +285,10 @@ static inline bool rwsem_try_write_lock_unqueued(struct rw_semaphore *sem)
 static inline bool rwsem_can_spin_on_owner(struct rw_semaphore *sem)
 {
         struct task_struct *owner;
-        bool on_cpu = true;
+        bool on_cpu = false;
 
         if (need_resched())
-                return 0;
+                return false;
 
         rcu_read_lock();
         owner = ACCESS_ONCE(sem->owner);
@@ -297,9 +297,9 @@ static inline bool rwsem_can_spin_on_owner(struct rw_semaphore *sem)
         rcu_read_unlock();
 
         /*
-         * If sem->owner is not set, the rwsem owner may have
-         * just acquired it and not set the owner yet or the rwsem
-         * has been released.
+         * If sem->owner is not set, yet we have just recently entered the
+         * slowpath, then there is a possibility reader(s) may have the lock.
+         * To be safe, avoid spinning in these situations.
          */
         return on_cpu;
 }
diff --git a/kernel/locking/rwsem.c b/kernel/locking/rwsem.c
index 42f806de49d4..e2d3bc7f03b4 100644
--- a/kernel/locking/rwsem.c
+++ b/kernel/locking/rwsem.c
@@ -12,7 +12,7 @@
 
 #include <linux/atomic.h>
 
-#if defined(CONFIG_SMP) && defined(CONFIG_RWSEM_XCHGADD_ALGORITHM)
+#ifdef CONFIG_RWSEM_SPIN_ON_OWNER
 static inline void rwsem_set_owner(struct rw_semaphore *sem)
 {
         sem->owner = current;