[PATCH v2 2/2] locking: Add contended_release tracepoint

[Dmitry Ilvokhin <d@ilvokhin.com>]

Add the contended_release trace event. This tracepoint fires on the
holder side when a contended lock is released, complementing the
existing contention_begin/contention_end tracepoints which fire on the
waiter side.

This enables correlating lock hold time under contention with waiter
events by lock address.

Add trace_contended_release() calls to the slowpath unlock paths of
sleepable locks: mutex, rtmutex, semaphore, rwsem, percpu-rwsem, and
RT-specific rwbase locks. Each call site fires only when there are
blocked waiters being woken, except percpu_up_write() which always wakes
via __wake_up().

Signed-off-by: Dmitry Ilvokhin <d@ilvokhin.com>
---
 include/trace/events/lock.h   | 17 +++++++++++++++++
 kernel/locking/mutex.c        |  1 +
 kernel/locking/percpu-rwsem.c |  3 +++
 kernel/locking/rtmutex.c      |  1 +
 kernel/locking/rwbase_rt.c    |  8 +++++++-
 kernel/locking/rwsem.c        |  9 +++++++--
 kernel/locking/semaphore.c    |  4 +++-
 7 files changed, 39 insertions(+), 4 deletions(-)

diff --git a/include/trace/events/lock.h b/include/trace/events/lock.h
index 8e89baa3775f..4f28e41977ec 100644
--- a/include/trace/events/lock.h
+++ b/include/trace/events/lock.h
@@ -138,6 +138,23 @@ TRACE_EVENT(contention_end,
 	TP_printk("%p (ret=%d)", __entry->lock_addr, __entry->ret)
 );
 
+TRACE_EVENT(contended_release,
+
+	TP_PROTO(void *lock),
+
+	TP_ARGS(lock),
+
+	TP_STRUCT__entry(
+		__field(void *, lock_addr)
+	),
+
+	TP_fast_assign(
+		__entry->lock_addr = lock;
+	),
+
+	TP_printk("%p", __entry->lock_addr)
+);
+
 #endif /* _TRACE_LOCK_H */
 
 /* This part must be outside protection */
diff --git a/kernel/locking/mutex.c b/kernel/locking/mutex.c
index 427187ff02db..ff9d07f3e900 100644
--- a/kernel/locking/mutex.c
+++ b/kernel/locking/mutex.c
@@ -992,6 +992,7 @@ static noinline void __sched __mutex_unlock_slowpath(struct mutex *lock, unsigne
 	if (waiter) {
 		next = waiter->task;
 
+		trace_contended_release(lock);
 		debug_mutex_wake_waiter(lock, waiter);
 		__clear_task_blocked_on(next, lock);
 		wake_q_add(&wake_q, next);
diff --git a/kernel/locking/percpu-rwsem.c b/kernel/locking/percpu-rwsem.c
index f3ee7a0d6047..1eee51766aaf 100644
--- a/kernel/locking/percpu-rwsem.c
+++ b/kernel/locking/percpu-rwsem.c
@@ -263,6 +263,8 @@ void percpu_up_write(struct percpu_rw_semaphore *sem)
 {
 	rwsem_release(&sem->dep_map, _RET_IP_);
 
+	trace_contended_release(sem);
+
 	/*
 	 * Signal the writer is done, no fast path yet.
 	 *
@@ -297,6 +299,7 @@ void __percpu_up_read(struct percpu_rw_semaphore *sem)
 	 * writer.
 	 */
 	smp_mb(); /* B matches C */
+	trace_contended_release(sem);
 	/*
 	 * In other words, if they see our decrement (presumably to
 	 * aggregate zero, as that is the only time it matters) they
diff --git a/kernel/locking/rtmutex.c b/kernel/locking/rtmutex.c
index ccaba6148b61..3db8a840b4e8 100644
--- a/kernel/locking/rtmutex.c
+++ b/kernel/locking/rtmutex.c
@@ -1466,6 +1466,7 @@ static void __sched rt_mutex_slowunlock(struct rt_mutex_base *lock)
 		raw_spin_lock_irqsave(&lock->wait_lock, flags);
 	}
 
+	trace_contended_release(lock);
 	/*
 	 * The wakeup next waiter path does not suffer from the above
 	 * race. See the comments there.
diff --git a/kernel/locking/rwbase_rt.c b/kernel/locking/rwbase_rt.c
index 82e078c0665a..081778934b13 100644
--- a/kernel/locking/rwbase_rt.c
+++ b/kernel/locking/rwbase_rt.c
@@ -162,8 +162,10 @@ static void __sched __rwbase_read_unlock(struct rwbase_rt *rwb,
 	 * worst case which can happen is a spurious wakeup.
 	 */
 	owner = rt_mutex_owner(rtm);
-	if (owner)
+	if (owner) {
+		trace_contended_release(rwb);
 		rt_mutex_wake_q_add_task(&wqh, owner, state);
+	}
 
 	/* Pairs with the preempt_enable in rt_mutex_wake_up_q() */
 	preempt_disable();
@@ -205,6 +207,8 @@ static inline void rwbase_write_unlock(struct rwbase_rt *rwb)
 	unsigned long flags;
 
 	raw_spin_lock_irqsave(&rtm->wait_lock, flags);
+	if (trace_contended_release_enabled() && rt_mutex_has_waiters(rtm))
+		trace_contended_release(rwb);
 	__rwbase_write_unlock(rwb, WRITER_BIAS, flags);
 }
 
@@ -214,6 +218,8 @@ static inline void rwbase_write_downgrade(struct rwbase_rt *rwb)
 	unsigned long flags;
 
 	raw_spin_lock_irqsave(&rtm->wait_lock, flags);
+	if (trace_contended_release_enabled() && rt_mutex_has_waiters(rtm))
+		trace_contended_release(rwb);
 	/* Release it and account current as reader */
 	__rwbase_write_unlock(rwb, WRITER_BIAS - 1, flags);
 }
diff --git a/kernel/locking/rwsem.c b/kernel/locking/rwsem.c
index ba4cb74de064..cf7d8e75ad7b 100644
--- a/kernel/locking/rwsem.c
+++ b/kernel/locking/rwsem.c
@@ -1390,6 +1390,7 @@ static inline void __up_read(struct rw_semaphore *sem)
 	if (unlikely((tmp & (RWSEM_LOCK_MASK|RWSEM_FLAG_WAITERS)) ==
 		      RWSEM_FLAG_WAITERS)) {
 		clear_nonspinnable(sem);
+		trace_contended_release(sem);
 		rwsem_wake(sem);
 	}
 	preempt_enable();
@@ -1413,8 +1414,10 @@ 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);
-	if (unlikely(tmp & RWSEM_FLAG_WAITERS))
+	if (unlikely(tmp & RWSEM_FLAG_WAITERS)) {
+		trace_contended_release(sem);
 		rwsem_wake(sem);
+	}
 	preempt_enable();
 }
 
@@ -1437,8 +1440,10 @@ static inline void __downgrade_write(struct rw_semaphore *sem)
 	tmp = atomic_long_fetch_add_release(
 		-RWSEM_WRITER_LOCKED+RWSEM_READER_BIAS, &sem->count);
 	rwsem_set_reader_owned(sem);
-	if (tmp & RWSEM_FLAG_WAITERS)
+	if (tmp & RWSEM_FLAG_WAITERS) {
+		trace_contended_release(sem);
 		rwsem_downgrade_wake(sem);
+	}
 	preempt_enable();
 }
 
diff --git a/kernel/locking/semaphore.c b/kernel/locking/semaphore.c
index 74d41433ba13..d46415095dd6 100644
--- a/kernel/locking/semaphore.c
+++ b/kernel/locking/semaphore.c
@@ -231,8 +231,10 @@ void __sched up(struct semaphore *sem)
 	else
 		__up(sem, &wake_q);
 	raw_spin_unlock_irqrestore(&sem->lock, flags);
-	if (!wake_q_empty(&wake_q))
+	if (!wake_q_empty(&wake_q)) {
+		trace_contended_release(sem);
 		wake_up_q(&wake_q);
+	}
 }
 EXPORT_SYMBOL(up);
 
-- 
2.52.0