1 files changed, 112 insertions, 64 deletions

diff --git a/kernel/locking/rwsem.c b/kernel/locking/rwsem.c
index 69aba4abe104..44873594de03 100644
--- a/kernel/locking/rwsem.c
+++ b/kernel/locking/rwsem.c
@@ -27,6 +27,7 @@
 #include <linux/export.h>
 #include <linux/rwsem.h>
 #include <linux/atomic.h>
+#include <trace/events/lock.h>
 
 #ifndef CONFIG_PREEMPT_RT
 #include "lock_events.h"
@@ -132,14 +133,19 @@
  * the owner value concurrently without lock. Read from owner, however,
  * may not need READ_ONCE() as long as the pointer value is only used
  * for comparison and isn't being dereferenced.
+ *
+ * Both rwsem_{set,clear}_owner() functions should be in the same
+ * preempt disable section as the atomic op that changes sem->count.
  */
 static inline void rwsem_set_owner(struct rw_semaphore *sem)
 {
+	lockdep_assert_preemption_disabled();
 	atomic_long_set(&sem->owner, (long)current);
 }
 
 static inline void rwsem_clear_owner(struct rw_semaphore *sem)
 {
+	lockdep_assert_preemption_disabled();
 	atomic_long_set(&sem->owner, 0);
 }
 
@@ -250,13 +256,16 @@ static inline bool rwsem_read_trylock(struct rw_semaphore *sem, long *cntp)
 static inline bool rwsem_write_trylock(struct rw_semaphore *sem)
 {
 	long tmp = RWSEM_UNLOCKED_VALUE;
+	bool ret = false;
 
+	preempt_disable();
 	if (atomic_long_try_cmpxchg_acquire(&sem->count, &tmp, RWSEM_WRITER_LOCKED)) {
 		rwsem_set_owner(sem);
-		return true;
+		ret = true;
 	}
 
-	return false;
+	preempt_enable();
+	return ret;
 }
 
 /*
@@ -334,8 +343,6 @@ struct rwsem_waiter {
 	struct task_struct *task;
 	enum rwsem_waiter_type type;
 	unsigned long timeout;
-
-	/* Writer only, not initialized in reader */
 	bool handoff_set;
 };
 #define rwsem_first_waiter(sem) \
@@ -375,16 +382,19 @@ rwsem_add_waiter(struct rw_semaphore *sem, struct rwsem_waiter *waiter)
  *
  * Both rwsem_mark_wake() and rwsem_try_write_lock() contain a full 'copy' of
  * this function. Modify with care.
+ *
+ * Return: true if wait_list isn't empty and false otherwise
  */
-static inline void
+static inline bool
 rwsem_del_waiter(struct rw_semaphore *sem, struct rwsem_waiter *waiter)
 {
 	lockdep_assert_held(&sem->wait_lock);
 	list_del(&waiter->list);
 	if (likely(!list_empty(&sem->wait_list)))
-		return;
+		return true;
 
 	atomic_long_andnot(RWSEM_FLAG_HANDOFF | RWSEM_FLAG_WAITERS, &sem->count);
+	return false;
 }
 
 /*
@@ -455,10 +465,12 @@ static void rwsem_mark_wake(struct rw_semaphore *sem,
 			 * to give up the lock), request a HANDOFF to
 			 * force the issue.
 			 */
-			if (!(oldcount & RWSEM_FLAG_HANDOFF) &&
-			    time_after(jiffies, waiter->timeout)) {
-				adjustment -= RWSEM_FLAG_HANDOFF;
-				lockevent_inc(rwsem_rlock_handoff);
+			if (time_after(jiffies, waiter->timeout)) {
+				if (!(oldcount & RWSEM_FLAG_HANDOFF)) {
+					adjustment -= RWSEM_FLAG_HANDOFF;
+					lockevent_inc(rwsem_rlock_handoff);
+				}
+				waiter->handoff_set = true;
 			}
 
 			atomic_long_add(-adjustment, &sem->count);
@@ -559,6 +571,33 @@ static void rwsem_mark_wake(struct rw_semaphore *sem,
 }
 
 /*
+ * Remove a waiter and try to wake up other waiters in the wait queue
+ * This function is called from the out_nolock path of both the reader and
+ * writer slowpaths with wait_lock held. It releases the wait_lock and
+ * optionally wake up waiters before it returns.
+ */
+static inline void
+rwsem_del_wake_waiter(struct rw_semaphore *sem, struct rwsem_waiter *waiter,
+		      struct wake_q_head *wake_q)
+		      __releases(&sem->wait_lock)
+{
+	bool first = rwsem_first_waiter(sem) == waiter;
+
+	wake_q_init(wake_q);
+
+	/*
+	 * If the wait_list isn't empty and the waiter to be deleted is
+	 * the first waiter, we wake up the remaining waiters as they may
+	 * be eligible to acquire or spin on the lock.
+	 */
+	if (rwsem_del_waiter(sem, waiter) && first)
+		rwsem_mark_wake(sem, RWSEM_WAKE_ANY, wake_q);
+	raw_spin_unlock_irq(&sem->wait_lock);
+	if (!wake_q_empty(wake_q))
+		wake_up_q(wake_q);
+}
+
+/*
  * This function must be called with the sem->wait_lock held to prevent
  * race conditions between checking the rwsem wait list and setting the
  * sem->count accordingly.
@@ -568,7 +607,7 @@ static void rwsem_mark_wake(struct rw_semaphore *sem,
 static inline bool rwsem_try_write_lock(struct rw_semaphore *sem,
 					struct rwsem_waiter *waiter)
 {
-	bool first = rwsem_first_waiter(sem) == waiter;
+	struct rwsem_waiter *first = rwsem_first_waiter(sem);
 	long count, new;
 
 	lockdep_assert_held(&sem->wait_lock);
@@ -578,11 +617,20 @@ static inline bool rwsem_try_write_lock(struct rw_semaphore *sem,
 		bool has_handoff = !!(count & RWSEM_FLAG_HANDOFF);
 
 		if (has_handoff) {
-			if (!first)
+			/*
+			 * Honor handoff bit and yield only when the first
+			 * waiter is the one that set it. Otherwisee, we
+			 * still try to acquire the rwsem.
+			 */
+			if (first->handoff_set && (waiter != first))
 				return false;
 
-			/* First waiter inherits a previously set handoff bit */
-			waiter->handoff_set = true;
+			/*
+			 * First waiter can inherit a previously set handoff
+			 * bit and spin on rwsem if lock acquisition fails.
+			 */
+			if (waiter == first)
+				waiter->handoff_set = true;
 		}
 
 		new = count;
@@ -901,7 +949,7 @@ done:
  */
 static inline void clear_nonspinnable(struct rw_semaphore *sem)
 {
-	if (rwsem_test_oflags(sem, RWSEM_NONSPINNABLE))
+	if (unlikely(rwsem_test_oflags(sem, RWSEM_NONSPINNABLE)))
 		atomic_long_andnot(RWSEM_NONSPINNABLE, &sem->owner);
 }
 
@@ -926,6 +974,31 @@ rwsem_spin_on_owner(struct rw_semaphore *sem)
 #endif
 
 /*
+ * Prepare to wake up waiter(s) in the wait queue by putting them into the
+ * given wake_q if the rwsem lock owner isn't a writer. If rwsem is likely
+ * reader-owned, wake up read lock waiters in queue front or wake up any
+ * front waiter otherwise.
+
+ * This is being called from both reader and writer slow paths.
+ */
+static inline void rwsem_cond_wake_waiter(struct rw_semaphore *sem, long count,
+					  struct wake_q_head *wake_q)
+{
+	enum rwsem_wake_type wake_type;
+
+	if (count & RWSEM_WRITER_MASK)
+		return;
+
+	if (count & RWSEM_READER_MASK) {
+		wake_type = RWSEM_WAKE_READERS;
+	} else {
+		wake_type = RWSEM_WAKE_ANY;
+		clear_nonspinnable(sem);
+	}
+	rwsem_mark_wake(sem, wake_type, wake_q);
+}
+
+/*
  * Wait for the read lock to be granted
  */
 static struct rw_semaphore __sched *
@@ -935,7 +1008,6 @@ rwsem_down_read_slowpath(struct rw_semaphore *sem, long count, unsigned int stat
 	long rcnt = (count >> RWSEM_READER_SHIFT);
 	struct rwsem_waiter waiter;
 	DEFINE_WAKE_Q(wake_q);
-	bool wake = false;
 
 	/*
 	 * To prevent a constant stream of readers from starving a sleeping
@@ -972,17 +1044,17 @@ queue:
 	waiter.task = current;
 	waiter.type = RWSEM_WAITING_FOR_READ;
 	waiter.timeout = jiffies + RWSEM_WAIT_TIMEOUT;
+	waiter.handoff_set = false;
 
 	raw_spin_lock_irq(&sem->wait_lock);
 	if (list_empty(&sem->wait_list)) {
 		/*
 		 * In case the wait queue is empty and the lock isn't owned
-		 * by a writer or has the handoff bit set, this reader can
-		 * exit the slowpath and return immediately as its
-		 * RWSEM_READER_BIAS has already been set in the count.
+		 * by a writer, this reader can exit the slowpath and return
+		 * immediately as its RWSEM_READER_BIAS has already been set
+		 * in the count.
 		 */
-		if (!(atomic_long_read(&sem->count) &
-		     (RWSEM_WRITER_MASK | RWSEM_FLAG_HANDOFF))) {
+		if (!(atomic_long_read(&sem->count) & RWSEM_WRITER_MASK)) {
 			/* Provide lock ACQUIRE */
 			smp_acquire__after_ctrl_dep();
 			raw_spin_unlock_irq(&sem->wait_lock);
@@ -997,22 +1069,13 @@ queue:
 	/* we're now waiting on the lock, but no longer actively locking */
 	count = atomic_long_add_return(adjustment, &sem->count);
 
-	/*
-	 * If there are no active locks, wake the front queued process(es).
-	 *
-	 * If there are no writers and we are first in the queue,
-	 * wake our own waiter to join the existing active readers !
-	 */
-	if (!(count & RWSEM_LOCK_MASK)) {
-		clear_nonspinnable(sem);
-		wake = true;
-	}
-	if (wake || (!(count & RWSEM_WRITER_MASK) &&
-		    (adjustment & RWSEM_FLAG_WAITERS)))
-		rwsem_mark_wake(sem, RWSEM_WAKE_ANY, &wake_q);
-
+	rwsem_cond_wake_waiter(sem, count, &wake_q);
 	raw_spin_unlock_irq(&sem->wait_lock);
-	wake_up_q(&wake_q);
+
+	if (!wake_q_empty(&wake_q))
+		wake_up_q(&wake_q);
+
+	trace_contention_begin(sem, LCB_F_READ);
 
 	/* wait to be given the lock */
 	for (;;) {
@@ -1035,23 +1098,23 @@ queue:
 
 	__set_current_state(TASK_RUNNING);
 	lockevent_inc(rwsem_rlock);
+	trace_contention_end(sem, 0);
 	return sem;
 
 out_nolock:
-	rwsem_del_waiter(sem, &waiter);
-	raw_spin_unlock_irq(&sem->wait_lock);
+	rwsem_del_wake_waiter(sem, &waiter, &wake_q);
 	__set_current_state(TASK_RUNNING);
 	lockevent_inc(rwsem_rlock_fail);
+	trace_contention_end(sem, -EINTR);
 	return ERR_PTR(-EINTR);
 }
 
 /*
  * Wait until we successfully acquire the write lock
  */
-static struct rw_semaphore *
+static struct rw_semaphore __sched *
 rwsem_down_write_slowpath(struct rw_semaphore *sem, int state)
 {
-	long count;
 	struct rwsem_waiter waiter;
 	DEFINE_WAKE_Q(wake_q);
 
@@ -1075,23 +1138,8 @@ rwsem_down_write_slowpath(struct rw_semaphore *sem, int state)
 
 	/* we're now waiting on the lock */
 	if (rwsem_first_waiter(sem) != &waiter) {
-		count = atomic_long_read(&sem->count);
-
-		/*
-		 * If there were already threads queued before us and:
-		 *  1) there are no active locks, wake the front
-		 *     queued process(es) as the handoff bit might be set.
-		 *  2) there are no active writers and some readers, the lock
-		 *     must be read owned; so we try to wake any read lock
-		 *     waiters that were queued ahead of us.
-		 */
-		if (count & RWSEM_WRITER_MASK)
-			goto wait;
-
-		rwsem_mark_wake(sem, (count & RWSEM_READER_MASK)
-					? RWSEM_WAKE_READERS
-					: RWSEM_WAKE_ANY, &wake_q);
-
+		rwsem_cond_wake_waiter(sem, atomic_long_read(&sem->count),
+				       &wake_q);
 		if (!wake_q_empty(&wake_q)) {
 			/*
 			 * We want to minimize wait_lock hold time especially
@@ -1099,16 +1147,16 @@ rwsem_down_write_slowpath(struct rw_semaphore *sem, int state)
 			 */
 			raw_spin_unlock_irq(&sem->wait_lock);
 			wake_up_q(&wake_q);
-			wake_q_init(&wake_q);	/* Used again, reinit */
 			raw_spin_lock_irq(&sem->wait_lock);
 		}
 	} else {
 		atomic_long_or(RWSEM_FLAG_WAITERS, &sem->count);
 	}
 
-wait:
 	/* wait until we successfully acquire the lock */
 	set_current_state(state);
+	trace_contention_begin(sem, LCB_F_WRITE);
+
 	for (;;) {
 		if (rwsem_try_write_lock(sem, &waiter)) {
 			/* rwsem_try_write_lock() implies ACQUIRE on success */
@@ -1148,17 +1196,15 @@ trylock_again:
 	__set_current_state(TASK_RUNNING);
 	raw_spin_unlock_irq(&sem->wait_lock);
 	lockevent_inc(rwsem_wlock);
+	trace_contention_end(sem, 0);
 	return sem;
 
 out_nolock:
 	__set_current_state(TASK_RUNNING);
 	raw_spin_lock_irq(&sem->wait_lock);
-	rwsem_del_waiter(sem, &waiter);
-	if (!list_empty(&sem->wait_list))
-		rwsem_mark_wake(sem, RWSEM_WAKE_ANY, &wake_q);
-	raw_spin_unlock_irq(&sem->wait_lock);
-	wake_up_q(&wake_q);
+	rwsem_del_wake_waiter(sem, &waiter, &wake_q);
 	lockevent_inc(rwsem_wlock_fail);
+	trace_contention_end(sem, -EINTR);
 	return ERR_PTR(-EINTR);
 }
 
@@ -1314,8 +1360,10 @@ static inline void __up_write(struct rw_semaphore *sem)
 	DEBUG_RWSEMS_WARN_ON((rwsem_owner(sem) != current) &&
 			    !rwsem_test_oflags(sem, RWSEM_NONSPINNABLE), sem);
 
+	preempt_disable();
 	rwsem_clear_owner(sem);
 	tmp = atomic_long_fetch_add_release(-RWSEM_WRITER_LOCKED, &sem->count);
+	preempt_enable();
 	if (unlikely(tmp & RWSEM_FLAG_WAITERS))
 		rwsem_wake(sem);
 }