locking: contended_release tracepoint instrumentation

index 8e89baa3775f..da978f2afb45 100644
@@ -5,7 +5,6 @@
 #if !defined(_TRACE_LOCK_H) || defined(TRACE_HEADER_MULTI_READ)
 #define _TRACE_LOCK_H
 
-#include <linux/sched.h>
 #include <linux/tracepoint.h>
 
 /* flags for lock:contention_begin */

index c8cb010d655e..39d5bf8e6562 100644
@@ -107,6 +107,8 @@ static inline bool percpu_down_read_trylock(struct percpu_rw_semaphore *sem)
 	return ret;
 }
 
+extern void __percpu_up_read(struct percpu_rw_semaphore *sem);
+
 static inline void percpu_up_read(struct percpu_rw_semaphore *sem)
 {
 	rwsem_release(&sem->dep_map, _RET_IP_);

@@ -118,18 +120,7 @@ static inline void percpu_up_read(struct percpu_rw_semaphore *sem)
 	if (likely(rcu_sync_is_idle(&sem->rss))) {
 		this_cpu_dec(*sem->read_count);
 	} else {
-		/*
-		 * slowpath; reader will only ever wake a single blocked
-		 * writer.
-		 */
-		smp_mb(); /* B matches C */
-		/*
-		 * In other words, if they see our decrement (presumably to
-		 * aggregate zero, as that is the only time it matters) they
-		 * will also see our critical section.
-		 */
-		this_cpu_dec(*sem->read_count);
-		rcuwait_wake_up(&sem->writer);
+		__percpu_up_read(sem);
 	}
 	preempt_enable();
 }

index ef234469baac..f3ee7a0d6047 100644
@@ -288,3 +288,21 @@ void percpu_up_write(struct percpu_rw_semaphore *sem)
 	rcu_sync_exit(&sem->rss);
 }
 EXPORT_SYMBOL_GPL(percpu_up_write);
+
+void __percpu_up_read(struct percpu_rw_semaphore *sem)
+{
+	lockdep_assert_preemption_disabled();
+	/*
+	 * slowpath; reader will only ever wake a single blocked
+	 * writer.
+	 */
+	smp_mb(); /* B matches C */
+	/*
+	 * In other words, if they see our decrement (presumably to
+	 * aggregate zero, as that is the only time it matters) they
+	 * will also see our critical section.
+	 */
+	this_cpu_dec(*sem->read_count);
+	rcuwait_wake_up(&sem->writer);
+}
+EXPORT_SYMBOL_GPL(__percpu_up_read);

index da978f2afb45..1ded869cd619 100644
@@ -137,6 +137,23 @@ 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 */

index 427187ff02db..6c2c9312eb8f 100644
@@ -997,6 +997,9 @@ static noinline void __sched __mutex_unlock_slowpath(struct mutex *lock, unsigne
 		wake_q_add(&wake_q, next);
 	}
 
+	if (trace_contended_release_enabled() && waiter)
+		trace_contended_release(lock);
+
 	if (owner & MUTEX_FLAG_HANDOFF)
 		__mutex_handoff(lock, next);
 

@@ -1194,6 +1197,7 @@ EXPORT_SYMBOL(ww_mutex_lock_interruptible);
 
 EXPORT_TRACEPOINT_SYMBOL_GPL(contention_begin);
 EXPORT_TRACEPOINT_SYMBOL_GPL(contention_end);
+EXPORT_TRACEPOINT_SYMBOL_GPL(contended_release);
 
 /**
  * atomic_dec_and_mutex_lock - return holding mutex if we dec to 0

index f3ee7a0d6047..46b5903989b8 100644
@@ -263,6 +263,9 @@ void percpu_up_write(struct percpu_rw_semaphore *sem)
 {
 	rwsem_release(&sem->dep_map, _RET_IP_);
 
+	if (trace_contended_release_enabled() && wq_has_sleeper(&sem->waiters))
+		trace_contended_release(sem);
+
 	/*
 	 * Signal the writer is done, no fast path yet.
 	 *

@@ -292,6 +295,14 @@ EXPORT_SYMBOL_GPL(percpu_up_write);
 void __percpu_up_read(struct percpu_rw_semaphore *sem)
 {
 	lockdep_assert_preemption_disabled();
+	/*
+	 * After percpu_up_write() completes, rcu_sync_is_idle() can still
+	 * return false during the grace period, forcing readers into this
+	 * slowpath. Only trace when a writer is actually waiting for
+	 * readers to drain.
+	 */
+	if (trace_contended_release_enabled() && rcuwait_active(&sem->writer))
+		trace_contended_release(sem);
 	/*
 	 * slowpath; reader will only ever wake a single blocked
 	 * writer.

index ccaba6148b61..3db8a840b4e8 100644
@@ -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.

index 82e078c0665a..74da5601018f 100644
@@ -174,6 +174,8 @@ static void __sched __rwbase_read_unlock(struct rwbase_rt *rwb,
 static __always_inline void rwbase_read_unlock(struct rwbase_rt *rwb,
 					       unsigned int state)
 {
+	if (trace_contended_release_enabled() && rt_mutex_owner(&rwb->rtmutex))
+		trace_contended_release(rwb);
 	/*
 	 * rwb->readers can only hit 0 when a writer is waiting for the
 	 * active readers to leave the critical section.

@@ -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);
 }

index bf647097369c..602d5fd3c91a 100644
@@ -1387,6 +1387,8 @@ static inline void __up_read(struct rw_semaphore *sem)
 	rwsem_clear_reader_owned(sem);
 	tmp = atomic_long_add_return_release(-RWSEM_READER_BIAS, &sem->count);
 	DEBUG_RWSEMS_WARN_ON(tmp < 0, sem);
+	if (trace_contended_release_enabled() && (tmp & RWSEM_FLAG_WAITERS))
+		trace_contended_release(sem);
 	if (unlikely((tmp & (RWSEM_LOCK_MASK|RWSEM_FLAG_WAITERS)) ==
 		      RWSEM_FLAG_WAITERS)) {
 		clear_nonspinnable(sem);

@@ -1413,8 +1415,10 @@ 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 +1441,10 @@ 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();
 }
 

index 74d41433ba13..35ac3498dca5 100644
@@ -230,6 +230,10 @@ void __sched up(struct semaphore *sem)
 		sem->count++;
 	else
 		__up(sem, &wake_q);
+
+	if (trace_contended_release_enabled() && !wake_q_empty(&wake_q))
+		trace_contended_release(sem);
+
 	raw_spin_unlock_irqrestore(&sem->lock, flags);
 	if (!wake_q_empty(&wake_q))
 		wake_up_q(&wake_q);

index 6ce2117e49f6..c349162f15eb 100644
@@ -13,12 +13,12 @@
 
 #include <asm-generic/qspinlock_types.h>
 
-#define	queued_spin_unlock queued_spin_unlock
+#define	queued_spin_release queued_spin_release
 /**
- * queued_spin_unlock - release a queued spinlock
+ * queued_spin_release - release a queued spinlock
  * @lock : Pointer to queued spinlock structure
  */
-static inline void queued_spin_unlock(struct qspinlock *lock)
+static inline void queued_spin_release(struct qspinlock *lock)
 {
 	/* This could be optimised with ARCH_HAS_MMIOWB */
 	mmiowb();

index 7beffcb08ed6..ac75e0736198 100644
@@ -49,9 +49,9 @@ static __always_inline bool pv_vcpu_is_preempted(long cpu)
 				ALT_NOT(X86_FEATURE_VCPUPREEMPT));
 }
 
-#define queued_spin_unlock queued_spin_unlock
+#define queued_spin_release queued_spin_release
 /**
- * queued_spin_unlock - release a queued spinlock
+ * queued_spin_release - release a queued spinlock
  * @lock : Pointer to queued spinlock structure
  *
  * A smp_store_release() on the least-significant byte.

@@ -66,7 +66,7 @@ static inline void queued_spin_lock_slowpath(struct qspinlock *lock, u32 val)
 	pv_queued_spin_lock_slowpath(lock, val);
 }
 
-static inline void queued_spin_unlock(struct qspinlock *lock)
+static inline void queued_spin_release(struct qspinlock *lock)
 {
 	kcsan_release();
 	pv_queued_spin_unlock(lock);

index bf47cca2c375..df76f34645a0 100644
@@ -115,12 +115,12 @@ static __always_inline void queued_spin_lock(struct qspinlock *lock)
 }
 #endif
 
-#ifndef queued_spin_unlock
+#ifndef queued_spin_release
 /**
- * queued_spin_unlock - release a queued spinlock
+ * queued_spin_release - release a queued spinlock
  * @lock : Pointer to queued spinlock structure
  */
-static __always_inline void queued_spin_unlock(struct qspinlock *lock)
+static __always_inline void queued_spin_release(struct qspinlock *lock)
 {
 	/*
 	 * unlock() needs release semantics:

@@ -129,6 +129,15 @@ static __always_inline void queued_spin_unlock(struct qspinlock *lock)
 }
 #endif
 
+/**
+ * queued_spin_unlock - unlock a queued spinlock
+ * @lock : Pointer to queued spinlock structure
+ */
+static __always_inline void queued_spin_unlock(struct qspinlock *lock)
+{
+	queued_spin_release(lock);
+}
+
 #ifndef virt_spin_lock
 static __always_inline bool virt_spin_lock(struct qspinlock *lock)
 {

index df76f34645a0..915a4c2777f6 100644
@@ -41,6 +41,7 @@
 
 #include <asm-generic/qspinlock_types.h>
 #include <linux/atomic.h>
+#include <linux/tracepoint-defs.h>
 
 #ifndef queued_spin_is_locked
 /**

@@ -129,12 +130,29 @@ static __always_inline void queued_spin_release(struct qspinlock *lock)
 }
 #endif
 
+DECLARE_TRACEPOINT(contended_release);
+
+extern void queued_spin_release_traced(struct qspinlock *lock);
+
 /**
  * queued_spin_unlock - unlock a queued spinlock
  * @lock : Pointer to queued spinlock structure
+ *
+ * Generic tracing wrapper around the arch-overridable
+ * queued_spin_release().
  */
 static __always_inline void queued_spin_unlock(struct qspinlock *lock)
 {
+	/*
+	 * Trace and release are combined in queued_spin_release_traced() so
+	 * the compiler does not need to preserve the lock pointer across the
+	 * function call, avoiding callee-saved register save/restore on the
+	 * hot path.
+	 */
+	if (tracepoint_enabled(contended_release)) {
+		queued_spin_release_traced(lock);
+		return;
+	}
 	queued_spin_release(lock);
 }
 

index af8d122bb649..c72610980ec7 100644
@@ -104,6 +104,14 @@ static __always_inline u32  __pv_wait_head_or_lock(struct qspinlock *lock,
 #define queued_spin_lock_slowpath	native_queued_spin_lock_slowpath
 #endif
 
+void __lockfunc queued_spin_release_traced(struct qspinlock *lock)
+{
+	if (queued_spin_is_contended(lock))
+		trace_contended_release(lock);
+	queued_spin_release(lock);
+}
+EXPORT_SYMBOL(queued_spin_release_traced);
+
 #endif /* _GEN_PV_LOCK_SLOWPATH */
 
 /**

index 75b8f4601b28..4b627bafba8b 100644
@@ -101,16 +101,26 @@ static inline void queued_write_lock(struct qrwlock *lock)
 	queued_write_lock_slowpath(lock);
 }
 
+static __always_inline void __queued_read_unlock(struct qrwlock *lock)
+{
+	/*
+	 * Atomically decrement the reader count
+	 */
+	(void)atomic_sub_return_release(_QR_BIAS, &lock->cnts);
+}
+
 /**
  * queued_read_unlock - release read lock of a queued rwlock
  * @lock : Pointer to queued rwlock structure
  */
 static inline void queued_read_unlock(struct qrwlock *lock)
 {
-	/*
-	 * Atomically decrement the reader count
-	 */
-	(void)atomic_sub_return_release(_QR_BIAS, &lock->cnts);
+	__queued_read_unlock(lock);
+}
+
+static __always_inline void __queued_write_unlock(struct qrwlock *lock)
+{
+	smp_store_release(&lock->wlocked, 0);
 }
 
 /**

@@ -119,7 +129,7 @@ static inline void queued_read_unlock(struct qrwlock *lock)
  */
 static inline void queued_write_unlock(struct qrwlock *lock)
 {
-	smp_store_release(&lock->wlocked, 0);
+	__queued_write_unlock(lock);
 }
 
 /**

index 4b627bafba8b..274c19006125 100644
@@ -14,6 +14,7 @@
 #define __ASM_GENERIC_QRWLOCK_H
 
 #include <linux/atomic.h>
+#include <linux/tracepoint-defs.h>
 #include <asm/barrier.h>
 #include <asm/processor.h>
 

@@ -35,6 +36,10 @@
  */
 extern void queued_read_lock_slowpath(struct qrwlock *lock);
 extern void queued_write_lock_slowpath(struct qrwlock *lock);
+extern void queued_read_unlock_traced(struct qrwlock *lock);
+extern void queued_write_unlock_traced(struct qrwlock *lock);
+
+DECLARE_TRACEPOINT(contended_release);
 
 /**
  * queued_read_trylock - try to acquire read lock of a queued rwlock

@@ -115,6 +120,17 @@ static __always_inline void __queued_read_unlock(struct qrwlock *lock)
  */
 static inline void queued_read_unlock(struct qrwlock *lock)
 {
+	/*
+	 * Trace and unlock are combined in the traced unlock variant so
+	 * the compiler does not need to preserve the lock pointer across
+	 * the function call, avoiding callee-saved register save/restore
+	 * on the hot path.
+	 */
+	if (tracepoint_enabled(contended_release)) {
+		queued_read_unlock_traced(lock);
+		return;
+	}
+
 	__queued_read_unlock(lock);
 }
 

@@ -129,6 +145,12 @@ static __always_inline void __queued_write_unlock(struct qrwlock *lock)
  */
 static inline void queued_write_unlock(struct qrwlock *lock)
 {
+	/* See comment in queued_read_unlock(). */
+	if (tracepoint_enabled(contended_release)) {
+		queued_write_unlock_traced(lock);
+		return;
+	}
+
 	__queued_write_unlock(lock);
 }
 

index d2ef312a8611..5f7a0fc2b27a 100644
@@ -90,3 +90,19 @@ void __lockfunc queued_write_lock_slowpath(struct qrwlock *lock)
 	trace_contention_end(lock, 0);
 }
 EXPORT_SYMBOL(queued_write_lock_slowpath);
+
+void __lockfunc queued_read_unlock_traced(struct qrwlock *lock)
+{
+	if (queued_rwlock_is_contended(lock))
+		trace_contended_release(lock);
+	__queued_read_unlock(lock);
+}
+EXPORT_SYMBOL(queued_read_unlock_traced);
+
+void __lockfunc queued_write_unlock_traced(struct qrwlock *lock)
+{
+	if (queued_rwlock_is_contended(lock))
+		trace_contended_release(lock);
+	__queued_write_unlock(lock);
+}
+EXPORT_SYMBOL(queued_write_unlock_traced);