1 files changed, 105 insertions, 71 deletions

diff --git a/kernel/locking/rwsem.c b/kernel/locking/rwsem.c
index 44873594de03..24df4d98f7d2 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 <linux/hung_task.h>
 #include <trace/events/lock.h>
 
 #ifndef CONFIG_PREEMPT_RT
@@ -35,7 +36,7 @@
 /*
  * The least significant 2 bits of the owner value has the following
  * meanings when set.
- *  - Bit 0: RWSEM_READER_OWNED - The rwsem is owned by readers
+ *  - Bit 0: RWSEM_READER_OWNED - rwsem may be owned by readers (just a hint)
  *  - Bit 1: RWSEM_NONSPINNABLE - Cannot spin on a reader-owned lock
  *
  * When the rwsem is reader-owned and a spinning writer has timed out,
@@ -181,12 +182,21 @@ static inline void rwsem_set_reader_owned(struct rw_semaphore *sem)
 	__rwsem_set_reader_owned(sem, current);
 }
 
+#if defined(CONFIG_DEBUG_RWSEMS) || defined(CONFIG_DETECT_HUNG_TASK_BLOCKER)
+/*
+ * Return just the real task structure pointer of the owner
+ */
+struct task_struct *rwsem_owner(struct rw_semaphore *sem)
+{
+	return (struct task_struct *)
+		(atomic_long_read(&sem->owner) & ~RWSEM_OWNER_FLAGS_MASK);
+}
+
 /*
  * Return true if the rwsem is owned by a reader.
  */
-static inline bool is_rwsem_reader_owned(struct rw_semaphore *sem)
+bool is_rwsem_reader_owned(struct rw_semaphore *sem)
 {
-#ifdef CONFIG_DEBUG_RWSEMS
 	/*
 	 * Check the count to see if it is write-locked.
 	 */
@@ -194,16 +204,14 @@ static inline bool is_rwsem_reader_owned(struct rw_semaphore *sem)
 
 	if (count & RWSEM_WRITER_MASK)
 		return false;
-#endif
 	return rwsem_test_oflags(sem, RWSEM_READER_OWNED);
 }
 
-#ifdef CONFIG_DEBUG_RWSEMS
 /*
- * With CONFIG_DEBUG_RWSEMS configured, it will make sure that if there
- * is a task pointer in owner of a reader-owned rwsem, it will be the
- * real owner or one of the real owners. The only exception is when the
- * unlock is done by up_read_non_owner().
+ * With CONFIG_DEBUG_RWSEMS or CONFIG_DETECT_HUNG_TASK_BLOCKER configured,
+ * it will make sure that the owner field of a reader-owned rwsem either
+ * points to a real reader-owner(s) or gets cleared. The only exception is
+ * when the unlock is done by up_read_non_owner().
  */
 static inline void rwsem_clear_reader_owned(struct rw_semaphore *sem)
 {
@@ -256,25 +264,13 @@ 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);
-		ret = true;
+		return true;
 	}
 
-	preempt_enable();
-	return ret;
-}
-
-/*
- * Return just the real task structure pointer of the owner
- */
-static inline struct task_struct *rwsem_owner(struct rw_semaphore *sem)
-{
-	return (struct task_struct *)
-		(atomic_long_read(&sem->owner) & ~RWSEM_OWNER_FLAGS_MASK);
+	return false;
 }
 
 /*
@@ -624,19 +620,17 @@ static inline bool rwsem_try_write_lock(struct rw_semaphore *sem,
 			 */
 			if (first->handoff_set && (waiter != first))
 				return false;
-
-			/*
-			 * 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;
 
 		if (count & RWSEM_LOCK_MASK) {
-			if (has_handoff || (!rt_task(waiter->task) &&
+			/*
+			 * A waiter (first or not) can set the handoff bit
+			 * if it is an RT task or wait in the wait queue
+			 * for too long.
+			 */
+			if (has_handoff || (!rt_or_dl_task(waiter->task) &&
 					    !time_after(jiffies, waiter->timeout)))
 				return false;
 
@@ -651,11 +645,12 @@ static inline bool rwsem_try_write_lock(struct rw_semaphore *sem,
 	} while (!atomic_long_try_cmpxchg_acquire(&sem->count, &count, new));
 
 	/*
-	 * We have either acquired the lock with handoff bit cleared or
-	 * set the handoff bit.
+	 * We have either acquired the lock with handoff bit cleared or set
+	 * the handoff bit. Only the first waiter can have its handoff_set
+	 * set here to enable optimistic spinning in slowpath loop.
 	 */
 	if (new & RWSEM_FLAG_HANDOFF) {
-		waiter->handoff_set = true;
+		first->handoff_set = true;
 		lockevent_inc(rwsem_wlock_handoff);
 		return false;
 	}
@@ -717,7 +712,6 @@ static inline bool rwsem_can_spin_on_owner(struct rw_semaphore *sem)
 		return false;
 	}
 
-	preempt_disable();
 	/*
 	 * Disable preemption is equal to the RCU read-side crital section,
 	 * thus the task_strcut structure won't go away.
@@ -729,14 +723,11 @@ static inline bool rwsem_can_spin_on_owner(struct rw_semaphore *sem)
 	if ((flags & RWSEM_NONSPINNABLE) ||
 	    (owner && !(flags & RWSEM_READER_OWNED) && !owner_on_cpu(owner)))
 		ret = false;
-	preempt_enable();
 
 	lockevent_cond_inc(rwsem_opt_fail, !ret);
 	return ret;
 }
 
-#define OWNER_SPINNABLE		(OWNER_NULL | OWNER_WRITER | OWNER_READER)
-
 static inline enum owner_state
 rwsem_owner_state(struct task_struct *owner, unsigned long flags)
 {
@@ -829,8 +820,6 @@ static bool rwsem_optimistic_spin(struct rw_semaphore *sem)
 	int loop = 0;
 	u64 rspin_threshold = 0;
 
-	preempt_disable();
-
 	/* sem->wait_lock should not be held when doing optimistic spinning */
 	if (!osq_lock(&sem->osq))
 		goto done;
@@ -845,7 +834,7 @@ static bool rwsem_optimistic_spin(struct rw_semaphore *sem)
 		enum owner_state owner_state;
 
 		owner_state = rwsem_spin_on_owner(sem);
-		if (!(owner_state & OWNER_SPINNABLE))
+		if (owner_state == OWNER_NONSPINNABLE)
 			break;
 
 		/*
@@ -922,7 +911,7 @@ static bool rwsem_optimistic_spin(struct rw_semaphore *sem)
 		if (owner_state != OWNER_WRITER) {
 			if (need_resched())
 				break;
-			if (rt_task(current) &&
+			if (rt_or_dl_task(current) &&
 			   (prev_owner_state != OWNER_WRITER))
 				break;
 		}
@@ -938,7 +927,6 @@ static bool rwsem_optimistic_spin(struct rw_semaphore *sem)
 	}
 	osq_unlock(&sem->osq);
 done:
-	preempt_enable();
 	lockevent_cond_inc(rwsem_opt_fail, !taken);
 	return taken;
 }
@@ -1011,8 +999,8 @@ rwsem_down_read_slowpath(struct rw_semaphore *sem, long count, unsigned int stat
 
 	/*
 	 * To prevent a constant stream of readers from starving a sleeping
-	 * waiter, don't attempt optimistic lock stealing if the lock is
-	 * currently owned by readers.
+	 * writer, don't attempt optimistic lock stealing if the lock is
+	 * very likely owned by readers.
 	 */
 	if ((atomic_long_read(&sem->owner) & RWSEM_READER_OWNED) &&
 	    (rcnt > 1) && !(count & RWSEM_WRITER_LOCKED))
@@ -1076,10 +1064,13 @@ queue:
 		wake_up_q(&wake_q);
 
 	trace_contention_begin(sem, LCB_F_READ);
+	set_current_state(state);
+
+	if (state == TASK_UNINTERRUPTIBLE)
+		hung_task_set_blocker(sem, BLOCKER_TYPE_RWSEM_READER);
 
 	/* wait to be given the lock */
 	for (;;) {
-		set_current_state(state);
 		if (!smp_load_acquire(&waiter.task)) {
 			/* Matches rwsem_mark_wake()'s smp_store_release(). */
 			break;
@@ -1092,10 +1083,14 @@ queue:
 			/* Ordered by sem->wait_lock against rwsem_mark_wake(). */
 			break;
 		}
-		schedule();
+		schedule_preempt_disabled();
 		lockevent_inc(rwsem_sleep_reader);
+		set_current_state(state);
 	}
 
+	if (state == TASK_UNINTERRUPTIBLE)
+		hung_task_clear_blocker();
+
 	__set_current_state(TASK_RUNNING);
 	lockevent_inc(rwsem_rlock);
 	trace_contention_end(sem, 0);
@@ -1157,6 +1152,9 @@ rwsem_down_write_slowpath(struct rw_semaphore *sem, int state)
 	set_current_state(state);
 	trace_contention_begin(sem, LCB_F_WRITE);
 
+	if (state == TASK_UNINTERRUPTIBLE)
+		hung_task_set_blocker(sem, BLOCKER_TYPE_RWSEM_WRITER);
+
 	for (;;) {
 		if (rwsem_try_write_lock(sem, &waiter)) {
 			/* rwsem_try_write_lock() implies ACQUIRE on success */
@@ -1179,20 +1177,21 @@ rwsem_down_write_slowpath(struct rw_semaphore *sem, int state)
 		if (waiter.handoff_set) {
 			enum owner_state owner_state;
 
-			preempt_disable();
 			owner_state = rwsem_spin_on_owner(sem);
-			preempt_enable();
-
 			if (owner_state == OWNER_NULL)
 				goto trylock_again;
 		}
 
-		schedule();
+		schedule_preempt_disabled();
 		lockevent_inc(rwsem_sleep_writer);
 		set_current_state(state);
 trylock_again:
 		raw_spin_lock_irq(&sem->wait_lock);
 	}
+
+	if (state == TASK_UNINTERRUPTIBLE)
+		hung_task_clear_blocker();
+
 	__set_current_state(TASK_RUNNING);
 	raw_spin_unlock_irq(&sem->wait_lock);
 	lockevent_inc(rwsem_wlock);
@@ -1252,77 +1251,96 @@ static struct rw_semaphore *rwsem_downgrade_wake(struct rw_semaphore *sem)
 /*
  * lock for reading
  */
-static inline int __down_read_common(struct rw_semaphore *sem, int state)
+static __always_inline int __down_read_common(struct rw_semaphore *sem, int state)
 {
+	int ret = 0;
 	long count;
 
+	preempt_disable();
 	if (!rwsem_read_trylock(sem, &count)) {
-		if (IS_ERR(rwsem_down_read_slowpath(sem, count, state)))
-			return -EINTR;
+		if (IS_ERR(rwsem_down_read_slowpath(sem, count, state))) {
+			ret = -EINTR;
+			goto out;
+		}
 		DEBUG_RWSEMS_WARN_ON(!is_rwsem_reader_owned(sem), sem);
 	}
-	return 0;
+out:
+	preempt_enable();
+	return ret;
 }
 
-static inline void __down_read(struct rw_semaphore *sem)
+static __always_inline void __down_read(struct rw_semaphore *sem)
 {
 	__down_read_common(sem, TASK_UNINTERRUPTIBLE);
 }
 
-static inline int __down_read_interruptible(struct rw_semaphore *sem)
+static __always_inline int __down_read_interruptible(struct rw_semaphore *sem)
 {
 	return __down_read_common(sem, TASK_INTERRUPTIBLE);
 }
 
-static inline int __down_read_killable(struct rw_semaphore *sem)
+static __always_inline int __down_read_killable(struct rw_semaphore *sem)
 {
 	return __down_read_common(sem, TASK_KILLABLE);
 }
 
 static inline int __down_read_trylock(struct rw_semaphore *sem)
 {
+	int ret = 0;
 	long tmp;
 
 	DEBUG_RWSEMS_WARN_ON(sem->magic != sem, sem);
 
+	preempt_disable();
 	tmp = atomic_long_read(&sem->count);
 	while (!(tmp & RWSEM_READ_FAILED_MASK)) {
 		if (atomic_long_try_cmpxchg_acquire(&sem->count, &tmp,
 						    tmp + RWSEM_READER_BIAS)) {
 			rwsem_set_reader_owned(sem);
-			return 1;
+			ret = 1;
+			break;
 		}
 	}
-	return 0;
+	preempt_enable();
+	return ret;
 }
 
 /*
  * lock for writing
  */
-static inline int __down_write_common(struct rw_semaphore *sem, int state)
+static __always_inline int __down_write_common(struct rw_semaphore *sem, int state)
 {
+	int ret = 0;
+
+	preempt_disable();
 	if (unlikely(!rwsem_write_trylock(sem))) {
 		if (IS_ERR(rwsem_down_write_slowpath(sem, state)))
-			return -EINTR;
+			ret = -EINTR;
 	}
-
-	return 0;
+	preempt_enable();
+	return ret;
 }
 
-static inline void __down_write(struct rw_semaphore *sem)
+static __always_inline void __down_write(struct rw_semaphore *sem)
 {
 	__down_write_common(sem, TASK_UNINTERRUPTIBLE);
 }
 
-static inline int __down_write_killable(struct rw_semaphore *sem)
+static __always_inline int __down_write_killable(struct rw_semaphore *sem)
 {
 	return __down_write_common(sem, TASK_KILLABLE);
 }
 
 static inline int __down_write_trylock(struct rw_semaphore *sem)
 {
+	int ret;
+
+	preempt_disable();
 	DEBUG_RWSEMS_WARN_ON(sem->magic != sem, sem);
-	return rwsem_write_trylock(sem);
+	ret = rwsem_write_trylock(sem);
+	preempt_enable();
+
+	return ret;
 }
 
 /*
@@ -1335,6 +1353,7 @@ static inline void __up_read(struct rw_semaphore *sem)
 	DEBUG_RWSEMS_WARN_ON(sem->magic != sem, sem);
 	DEBUG_RWSEMS_WARN_ON(!is_rwsem_reader_owned(sem), sem);
 
+	preempt_disable();
 	rwsem_clear_reader_owned(sem);
 	tmp = atomic_long_add_return_release(-RWSEM_READER_BIAS, &sem->count);
 	DEBUG_RWSEMS_WARN_ON(tmp < 0, sem);
@@ -1343,6 +1362,7 @@ static inline void __up_read(struct rw_semaphore *sem)
 		clear_nonspinnable(sem);
 		rwsem_wake(sem);
 	}
+	preempt_enable();
 }
 
 /*
@@ -1363,9 +1383,9 @@ static inline void __up_write(struct rw_semaphore *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);
+	preempt_enable();
 }
 
 /*
@@ -1383,11 +1403,13 @@ static inline void __downgrade_write(struct rw_semaphore *sem)
 	 * write side. As such, rely on RELEASE semantics.
 	 */
 	DEBUG_RWSEMS_WARN_ON(rwsem_owner(sem) != current, sem);
+	preempt_disable();
 	tmp = atomic_long_fetch_add_release(
 		-RWSEM_WRITER_LOCKED+RWSEM_READER_BIAS, &sem->count);
 	rwsem_set_reader_owned(sem);
 	if (tmp & RWSEM_FLAG_WAITERS)
 		rwsem_downgrade_wake(sem);
+	preempt_enable();
 }
 
 #else /* !CONFIG_PREEMPT_RT */
@@ -1404,8 +1426,8 @@ static inline void __downgrade_write(struct rw_semaphore *sem)
 #define rwbase_rtmutex_lock_state(rtm, state)		\
 	__rt_mutex_lock(rtm, state)
 
-#define rwbase_rtmutex_slowlock_locked(rtm, state)	\
-	__rt_mutex_slowlock_locked(rtm, NULL, state)
+#define rwbase_rtmutex_slowlock_locked(rtm, state, wq)	\
+	__rt_mutex_slowlock_locked(rtm, NULL, state, wq)
 
 #define rwbase_rtmutex_unlock(rtm)			\
 	__rt_mutex_unlock(rtm)
@@ -1416,8 +1438,14 @@ static inline void __downgrade_write(struct rw_semaphore *sem)
 #define rwbase_signal_pending_state(state, current)	\
 	signal_pending_state(state, current)
 
+#define rwbase_pre_schedule()				\
+	rt_mutex_pre_schedule()
+
 #define rwbase_schedule()				\
-	schedule()
+	rt_mutex_schedule()
+
+#define rwbase_post_schedule()				\
+	rt_mutex_post_schedule()
 
 #include "rwbase_rt.c"
 
@@ -1662,6 +1690,12 @@ void down_read_non_owner(struct rw_semaphore *sem)
 {
 	might_sleep();
 	__down_read(sem);
+	/*
+	 * The owner value for a reader-owned lock is mostly for debugging
+	 * purpose only and is not critical to the correct functioning of
+	 * rwsem. So it is perfectly fine to set it in a preempt-enabled
+	 * context here.
+	 */
 	__rwsem_set_reader_owned(sem, NULL);
 }
 EXPORT_SYMBOL(down_read_non_owner);