locking, sched: The PREEMPT-RT locking infrastructure

index ded90b0..3f02b81 100644
@@ -14,29 +14,14 @@ typedef struct {
 } local_lock_t;
 
 #ifdef CONFIG_DEBUG_LOCK_ALLOC
-# define LL_DEP_MAP_INIT(lockname)			\
+# define LOCAL_LOCK_DEBUG_INIT(lockname)		\
 	.dep_map = {					\
 		.name = #lockname,			\
 		.wait_type_inner = LD_WAIT_CONFIG,	\
-		.lock_type = LD_LOCK_PERCPU,			\
-	}
-#else
-# define LL_DEP_MAP_INIT(lockname)
-#endif
-
-#define INIT_LOCAL_LOCK(lockname)	{ LL_DEP_MAP_INIT(lockname) }
-
-#define __local_lock_init(lock)					\
-do {								\
-	static struct lock_class_key __key;			\
-								\
-	debug_check_no_locks_freed((void *)lock, sizeof(*lock));\
-	lockdep_init_map_type(&(lock)->dep_map, #lock, &__key, 0, \
-			      LD_WAIT_CONFIG, LD_WAIT_INV,	\
-			      LD_LOCK_PERCPU);			\
-} while (0)
+		.lock_type = LD_LOCK_PERCPU,		\
+	},						\
+	.owner = NULL,
 
-#ifdef CONFIG_DEBUG_LOCK_ALLOC
 static inline void local_lock_acquire(local_lock_t *l)
 {
 	lock_map_acquire(&l->dep_map);

@@ -51,11 +36,30 @@ static inline void local_lock_release(local_lock_t *l)
 	lock_map_release(&l->dep_map);
 }
 
+static inline void local_lock_debug_init(local_lock_t *l)
+{
+	l->owner = NULL;
+}
 #else /* CONFIG_DEBUG_LOCK_ALLOC */
+# define LOCAL_LOCK_DEBUG_INIT(lockname)
 static inline void local_lock_acquire(local_lock_t *l) { }
 static inline void local_lock_release(local_lock_t *l) { }
+static inline void local_lock_debug_init(local_lock_t *l) { }
 #endif /* !CONFIG_DEBUG_LOCK_ALLOC */
 
+#define INIT_LOCAL_LOCK(lockname)	{ LOCAL_LOCK_DEBUG_INIT(lockname) }
+
+#define __local_lock_init(lock)					\
+do {								\
+	static struct lock_class_key __key;			\
+								\
+	debug_check_no_locks_freed((void *)lock, sizeof(*lock));\
+	lockdep_init_map_type(&(lock)->dep_map, #lock, &__key,  \
+			      0, LD_WAIT_CONFIG, LD_WAIT_INV,	\
+			      LD_LOCK_PERCPU);			\
+	local_lock_debug_init(lock);				\
+} while (0)
+
 #define __local_lock(lock)					\
 	do {							\
 		preempt_disable();				\

index d1672de..87b325a 100644
@@ -52,17 +52,22 @@ do { \
 } while (0)
 
 #ifdef CONFIG_DEBUG_LOCK_ALLOC
-#define __DEP_MAP_RT_MUTEX_INITIALIZER(mutexname) \
-	, .dep_map = { .name = #mutexname }
+#define __DEP_MAP_RT_MUTEX_INITIALIZER(mutexname)	\
+	.dep_map = {					\
+		.name = #mutexname,			\
+		.wait_type_inner = LD_WAIT_SLEEP,	\
+	}
 #else
 #define __DEP_MAP_RT_MUTEX_INITIALIZER(mutexname)
 #endif
 
-#define __RT_MUTEX_INITIALIZER(mutexname) \
-	{ .wait_lock = __RAW_SPIN_LOCK_UNLOCKED(mutexname.wait_lock) \
-	, .waiters = RB_ROOT_CACHED \
-	, .owner = NULL \
-	__DEP_MAP_RT_MUTEX_INITIALIZER(mutexname)}
+#define __RT_MUTEX_INITIALIZER(mutexname)				\
+{									\
+	.wait_lock = __RAW_SPIN_LOCK_UNLOCKED(mutexname.wait_lock),	\
+	.waiters = RB_ROOT_CACHED,					\
+	.owner = NULL,							\
+	__DEP_MAP_RT_MUTEX_INITIALIZER(mutexname)			\
+}
 
 #define DEFINE_RT_MUTEX(mutexname) \
 	struct rt_mutex mutexname = __RT_MUTEX_INITIALIZER(mutexname)

index ad0db32..1a7e3f8 100644
@@ -1556,7 +1556,7 @@ void __sched __rt_mutex_init(struct rt_mutex *lock, const char *name,
 		     struct lock_class_key *key)
 {
 	debug_check_no_locks_freed((void *)lock, sizeof(*lock));
-	lockdep_init_map(&lock->dep_map, name, key, 0);
+	lockdep_init_map_wait(&lock->dep_map, name, key, 0, LD_WAIT_SLEEP);
 
 	__rt_mutex_basic_init(lock);
 }

index 20ffcc0..961991e 100644
@@ -3562,6 +3562,22 @@ static void ttwu_queue(struct task_struct *p, int cpu, int wake_flags)
 }
 
 /*
+ * Invoked from try_to_wake_up() to check whether the task can be woken up.
+ *
+ * The caller holds p::pi_lock if p != current or has preemption
+ * disabled when p == current.
+ */
+static __always_inline
+bool ttwu_state_match(struct task_struct *p, unsigned int state, int *success)
+{
+	if (READ_ONCE(p->__state) & state) {
+		*success = 1;
+		return true;
+	}
+	return false;
+}
+
+/*
  * Notes on Program-Order guarantees on SMP systems.
  *
  *  MIGRATION

@@ -3700,10 +3716,9 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags)
 		 *  - we're serialized against set_special_state() by virtue of
 		 *    it disabling IRQs (this allows not taking ->pi_lock).
 		 */
-		if (!(READ_ONCE(p->__state) & state))
+		if (!ttwu_state_match(p, state, &success))
 			goto out;
 
-		success = 1;
 		trace_sched_waking(p);
 		WRITE_ONCE(p->__state, TASK_RUNNING);
 		trace_sched_wakeup(p);

@@ -3718,14 +3733,11 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags)
 	 */
 	raw_spin_lock_irqsave(&p->pi_lock, flags);
 	smp_mb__after_spinlock();
-	if (!(READ_ONCE(p->__state) & state))
+	if (!ttwu_state_match(p, state, &success))
 		goto unlock;
 
 	trace_sched_waking(p);
 
-	/* We're going to change ->state: */
-	success = 1;
-
 	/*
 	 * Ensure we load p->on_rq _after_ p->state, otherwise it would
 	 * be possible to, falsely, observe p->on_rq == 0 and get stuck

index ec8d07d..9a9f606 100644
@@ -95,7 +95,9 @@ struct task_group;
 #define TASK_WAKING			0x0200
 #define TASK_NOLOAD			0x0400
 #define TASK_NEW			0x0800
-#define TASK_STATE_MAX			0x1000
+/* RT specific auxilliary flag to mark RT lock waiters */
+#define TASK_RTLOCK_WAIT		0x1000
+#define TASK_STATE_MAX			0x2000
 
 /* Convenience macros for the sake of set_current_state: */
 #define TASK_KILLABLE			(TASK_WAKEKILL | TASK_UNINTERRUPTIBLE)

index 9a9f606..4c72cf6 100644
@@ -123,8 +123,6 @@ struct task_group;
 
 #define task_is_stopped_or_traced(task)	((READ_ONCE(task->__state) & (__TASK_STOPPED | __TASK_TRACED)) != 0)
 
-#ifdef CONFIG_DEBUG_ATOMIC_SLEEP
-
 /*
  * Special states are those that do not use the normal wait-loop pattern. See
  * the comment with set_special_state().

@@ -132,30 +130,24 @@ struct task_group;
 #define is_special_task_state(state)				\
 	((state) & (__TASK_STOPPED | __TASK_TRACED | TASK_PARKED | TASK_DEAD))
 
-#define __set_current_state(state_value)			\
-	do {							\
-		WARN_ON_ONCE(is_special_task_state(state_value));\
-		current->task_state_change = _THIS_IP_;		\
-		WRITE_ONCE(current->__state, (state_value));	\
-	} while (0)
-
-#define set_current_state(state_value)				\
-	do {							\
-		WARN_ON_ONCE(is_special_task_state(state_value));\
-		current->task_state_change = _THIS_IP_;		\
-		smp_store_mb(current->__state, (state_value));	\
+#ifdef CONFIG_DEBUG_ATOMIC_SLEEP
+# define debug_normal_state_change(state_value)				\
+	do {								\
+		WARN_ON_ONCE(is_special_task_state(state_value));	\
+		current->task_state_change = _THIS_IP_;			\
 	} while (0)
 
-#define set_special_state(state_value)					\
+# define debug_special_state_change(state_value)			\
 	do {								\
-		unsigned long flags; /* may shadow */			\
 		WARN_ON_ONCE(!is_special_task_state(state_value));	\
-		raw_spin_lock_irqsave(&current->pi_lock, flags);	\
 		current->task_state_change = _THIS_IP_;			\
-		WRITE_ONCE(current->__state, (state_value));		\
-		raw_spin_unlock_irqrestore(&current->pi_lock, flags);	\
 	} while (0)
+
 #else
+# define debug_normal_state_change(cond)	do { } while (0)
+# define debug_special_state_change(cond)	do { } while (0)
+#endif
+
 /*
  * set_current_state() includes a barrier so that the write of current->state
  * is correctly serialised wrt the caller's subsequent test of whether to

@@ -194,27 +186,33 @@ struct task_group;
  * Also see the comments of try_to_wake_up().
  */
 #define __set_current_state(state_value)				\
-	WRITE_ONCE(current->__state, (state_value))
+	do {								\
+		debug_normal_state_change((state_value));		\
+		WRITE_ONCE(current->__state, (state_value));		\
+	} while (0)
 
 #define set_current_state(state_value)					\
-	smp_store_mb(current->__state, (state_value))
+	do {								\
+		debug_normal_state_change((state_value));		\
+		smp_store_mb(current->__state, (state_value));		\
+	} while (0)
 
 /*
  * set_special_state() should be used for those states when the blocking task
  * can not use the regular condition based wait-loop. In that case we must
- * serialize against wakeups such that any possible in-flight TASK_RUNNING stores
- * will not collide with our state change.
+ * serialize against wakeups such that any possible in-flight TASK_RUNNING
+ * stores will not collide with our state change.
  */
 #define set_special_state(state_value)					\
 	do {								\
 		unsigned long flags; /* may shadow */			\
+									\
 		raw_spin_lock_irqsave(&current->pi_lock, flags);	\
+		debug_special_state_change((state_value));		\
 		WRITE_ONCE(current->__state, (state_value));		\
 		raw_spin_unlock_irqrestore(&current->pi_lock, flags);	\
 	} while (0)
 
-#endif
-
 #define get_current_state()	READ_ONCE(current->__state)
 
 /* Task command name length: */

index 4c72cf6..02714b9 100644
@@ -143,9 +143,22 @@ struct task_group;
 		current->task_state_change = _THIS_IP_;			\
 	} while (0)
 
+# define debug_rtlock_wait_set_state()					\
+	do {								 \
+		current->saved_state_change = current->task_state_change;\
+		current->task_state_change = _THIS_IP_;			 \
+	} while (0)
+
+# define debug_rtlock_wait_restore_state()				\
+	do {								 \
+		current->task_state_change = current->saved_state_change;\
+	} while (0)
+
 #else
 # define debug_normal_state_change(cond)	do { } while (0)
 # define debug_special_state_change(cond)	do { } while (0)
+# define debug_rtlock_wait_set_state()		do { } while (0)
+# define debug_rtlock_wait_restore_state()	do { } while (0)
 #endif
 
 /*

@@ -213,6 +226,51 @@ struct task_group;
 		raw_spin_unlock_irqrestore(&current->pi_lock, flags);	\
 	} while (0)
 
+/*
+ * PREEMPT_RT specific variants for "sleeping" spin/rwlocks
+ *
+ * RT's spin/rwlock substitutions are state preserving. The state of the
+ * task when blocking on the lock is saved in task_struct::saved_state and
+ * restored after the lock has been acquired.  These operations are
+ * serialized by task_struct::pi_lock against try_to_wake_up(). Any non RT
+ * lock related wakeups while the task is blocked on the lock are
+ * redirected to operate on task_struct::saved_state to ensure that these
+ * are not dropped. On restore task_struct::saved_state is set to
+ * TASK_RUNNING so any wakeup attempt redirected to saved_state will fail.
+ *
+ * The lock operation looks like this:
+ *
+ *	current_save_and_set_rtlock_wait_state();
+ *	for (;;) {
+ *		if (try_lock())
+ *			break;
+ *		raw_spin_unlock_irq(&lock->wait_lock);
+ *		schedule_rtlock();
+ *		raw_spin_lock_irq(&lock->wait_lock);
+ *		set_current_state(TASK_RTLOCK_WAIT);
+ *	}
+ *	current_restore_rtlock_saved_state();
+ */
+#define current_save_and_set_rtlock_wait_state()			\
+	do {								\
+		lockdep_assert_irqs_disabled();				\
+		raw_spin_lock(&current->pi_lock);			\
+		current->saved_state = current->__state;		\
+		debug_rtlock_wait_set_state();				\
+		WRITE_ONCE(current->__state, TASK_RTLOCK_WAIT);		\
+		raw_spin_unlock(&current->pi_lock);			\
+	} while (0);
+
+#define current_restore_rtlock_saved_state()				\
+	do {								\
+		lockdep_assert_irqs_disabled();				\
+		raw_spin_lock(&current->pi_lock);			\
+		debug_rtlock_wait_restore_state();			\
+		WRITE_ONCE(current->__state, current->saved_state);	\
+		current->saved_state = TASK_RUNNING;			\
+		raw_spin_unlock(&current->pi_lock);			\
+	} while (0);
+
 #define get_current_state()	READ_ONCE(current->__state)
 
 /* Task command name length: */

@@ -668,6 +726,11 @@ struct task_struct {
 #endif
 	unsigned int			__state;
 
+#ifdef CONFIG_PREEMPT_RT
+	/* saved state for "spinlock sleepers" */
+	unsigned int			saved_state;
+#endif
+
 	/*
 	 * This begins the randomizable portion of task_struct. Only
 	 * scheduling-critical items should be added above here.

@@ -1357,6 +1420,9 @@ struct task_struct {
 	struct kmap_ctrl		kmap_ctrl;
 #ifdef CONFIG_DEBUG_ATOMIC_SLEEP
 	unsigned long			task_state_change;
+# ifdef CONFIG_PREEMPT_RT
+	unsigned long			saved_state_change;
+# endif
 #endif
 	int				pagefault_disabled;
 #ifdef CONFIG_MMU

index 961991e..e407c6a 100644
@@ -3566,14 +3566,47 @@ static void ttwu_queue(struct task_struct *p, int cpu, int wake_flags)
  *
  * The caller holds p::pi_lock if p != current or has preemption
  * disabled when p == current.
+ *
+ * The rules of PREEMPT_RT saved_state:
+ *
+ *   The related locking code always holds p::pi_lock when updating
+ *   p::saved_state, which means the code is fully serialized in both cases.
+ *
+ *   The lock wait and lock wakeups happen via TASK_RTLOCK_WAIT. No other
+ *   bits set. This allows to distinguish all wakeup scenarios.
  */
 static __always_inline
 bool ttwu_state_match(struct task_struct *p, unsigned int state, int *success)
 {
+	if (IS_ENABLED(CONFIG_DEBUG_PREEMPT)) {
+		WARN_ON_ONCE((state & TASK_RTLOCK_WAIT) &&
+			     state != TASK_RTLOCK_WAIT);
+	}
+
 	if (READ_ONCE(p->__state) & state) {
 		*success = 1;
 		return true;
 	}
+
+#ifdef CONFIG_PREEMPT_RT
+	/*
+	 * Saved state preserves the task state across blocking on
+	 * an RT lock.  If the state matches, set p::saved_state to
+	 * TASK_RUNNING, but do not wake the task because it waits
+	 * for a lock wakeup. Also indicate success because from
+	 * the regular waker's point of view this has succeeded.
+	 *
+	 * After acquiring the lock the task will restore p::__state
+	 * from p::saved_state which ensures that the regular
+	 * wakeup is not lost. The restore will also set
+	 * p::saved_state to TASK_RUNNING so any further tests will
+	 * not result in false positives vs. @success
+	 */
+	if (p->saved_state & state) {
+		p->saved_state = TASK_RUNNING;
+		*success = 1;
+	}
+#endif
 	return false;
 }
 

index e407c6a..ebc24e1 100644
@@ -5820,6 +5820,18 @@ pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
 #endif /* CONFIG_SCHED_CORE */
 
 /*
+ * Constants for the sched_mode argument of __schedule().
+ *
+ * The mode argument allows RT enabled kernels to differentiate a
+ * preemption from blocking on an 'sleeping' spin/rwlock. Note that
+ * SM_MASK_PREEMPT for !RT has all bits set, which allows the compiler to
+ * optimize the AND operation out and just check for zero.
+ */
+#define SM_NONE			0x0
+#define SM_PREEMPT		0x1
+#define SM_MASK_PREEMPT		(~0U)
+
+/*
  * __schedule() is the main scheduler function.
  *
  * The main means of driving the scheduler and thus entering this function are:

@@ -5858,7 +5870,7 @@ pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
  *
  * WARNING: must be called with preemption disabled!
  */
-static void __sched notrace __schedule(bool preempt)
+static void __sched notrace __schedule(unsigned int sched_mode)
 {
 	struct task_struct *prev, *next;
 	unsigned long *switch_count;

@@ -5871,13 +5883,13 @@ static void __sched notrace __schedule(bool preempt)
 	rq = cpu_rq(cpu);
 	prev = rq->curr;
 
-	schedule_debug(prev, preempt);
+	schedule_debug(prev, !!sched_mode);
 
 	if (sched_feat(HRTICK) || sched_feat(HRTICK_DL))
 		hrtick_clear(rq);
 
 	local_irq_disable();
-	rcu_note_context_switch(preempt);
+	rcu_note_context_switch(!!sched_mode);
 
 	/*
 	 * Make sure that signal_pending_state()->signal_pending() below

@@ -5911,7 +5923,7 @@ static void __sched notrace __schedule(bool preempt)
 	 *  - ptrace_{,un}freeze_traced() can change ->state underneath us.
 	 */
 	prev_state = READ_ONCE(prev->__state);
-	if (!preempt && prev_state) {
+	if (!(sched_mode & SM_MASK_PREEMPT) && prev_state) {
 		if (signal_pending_state(prev_state, prev)) {
 			WRITE_ONCE(prev->__state, TASK_RUNNING);
 		} else {

@@ -5977,7 +5989,7 @@ static void __sched notrace __schedule(bool preempt)
 		migrate_disable_switch(rq, prev);
 		psi_sched_switch(prev, next, !task_on_rq_queued(prev));
 
-		trace_sched_switch(preempt, prev, next);
+		trace_sched_switch(sched_mode & SM_MASK_PREEMPT, prev, next);
 
 		/* Also unlocks the rq: */
 		rq = context_switch(rq, prev, next, &rf);

@@ -5998,7 +6010,7 @@ void __noreturn do_task_dead(void)
 	/* Tell freezer to ignore us: */
 	current->flags |= PF_NOFREEZE;
 
-	__schedule(false);
+	__schedule(SM_NONE);
 	BUG();
 
 	/* Avoid "noreturn function does return" - but don't continue if BUG() is a NOP: */

@@ -6059,7 +6071,7 @@ asmlinkage __visible void __sched schedule(void)
 	sched_submit_work(tsk);
 	do {
 		preempt_disable();
-		__schedule(false);
+		__schedule(SM_NONE);
 		sched_preempt_enable_no_resched();
 	} while (need_resched());
 	sched_update_worker(tsk);

@@ -6087,7 +6099,7 @@ void __sched schedule_idle(void)
 	 */
 	WARN_ON_ONCE(current->__state);
 	do {
-		__schedule(false);
+		__schedule(SM_NONE);
 	} while (need_resched());
 }
 

@@ -6140,7 +6152,7 @@ static void __sched notrace preempt_schedule_common(void)
 		 */
 		preempt_disable_notrace();
 		preempt_latency_start(1);
-		__schedule(true);
+		__schedule(SM_PREEMPT);
 		preempt_latency_stop(1);
 		preempt_enable_no_resched_notrace();
 

@@ -6219,7 +6231,7 @@ asmlinkage __visible void __sched notrace preempt_schedule_notrace(void)
 		 * an infinite recursion.
 		 */
 		prev_ctx = exception_enter();
-		__schedule(true);
+		__schedule(SM_PREEMPT);
 		exception_exit(prev_ctx);
 
 		preempt_latency_stop(1);

@@ -6368,7 +6380,7 @@ asmlinkage __visible void __sched preempt_schedule_irq(void)
 	do {
 		preempt_disable();
 		local_irq_enable();
-		__schedule(true);
+		__schedule(SM_PREEMPT);
 		local_irq_disable();
 		sched_preempt_enable_no_resched();
 	} while (need_resched());

index 02714b9..746dfc0 100644
@@ -288,6 +288,9 @@ extern long schedule_timeout_idle(long timeout);
 asmlinkage void schedule(void);
 extern void schedule_preempt_disabled(void);
 asmlinkage void preempt_schedule_irq(void);
+#ifdef CONFIG_PREEMPT_RT
+ extern void schedule_rtlock(void);
+#endif
 
 extern int __must_check io_schedule_prepare(void);
 extern void io_schedule_finish(int token);

index ebc24e1..c89c1d4 100644
@@ -5829,7 +5829,13 @@ pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
  */
 #define SM_NONE			0x0
 #define SM_PREEMPT		0x1
-#define SM_MASK_PREEMPT		(~0U)
+#define SM_RTLOCK_WAIT		0x2
+
+#ifndef CONFIG_PREEMPT_RT
+# define SM_MASK_PREEMPT	(~0U)
+#else
+# define SM_MASK_PREEMPT	SM_PREEMPT
+#endif
 
 /*
  * __schedule() is the main scheduler function.

@@ -6134,6 +6140,18 @@ void __sched schedule_preempt_disabled(void)
 	preempt_disable();
 }
 
+#ifdef CONFIG_PREEMPT_RT
+void __sched notrace schedule_rtlock(void)
+{
+	do {
+		preempt_disable();
+		__schedule(SM_RTLOCK_WAIT);
+		sched_preempt_enable_no_resched();
+	} while (need_resched());
+}
+NOKPROBE_SYMBOL(schedule_rtlock);
+#endif
+
 static void __sched notrace preempt_schedule_common(void)
 {
 	do {

index 26a2013..06cd8fb 100644
@@ -42,8 +42,11 @@ struct wake_q_head {
 
 #define WAKE_Q_TAIL ((struct wake_q_node *) 0x01)
 
-#define DEFINE_WAKE_Q(name)				\
-	struct wake_q_head name = { WAKE_Q_TAIL, &name.first }
+#define WAKE_Q_HEAD_INITIALIZER(name)				\
+	{ WAKE_Q_TAIL, &name.first }
+
+#define DEFINE_WAKE_Q(name)					\
+	struct wake_q_head name = WAKE_Q_HEAD_INITIALIZER(name)
 
 static inline void wake_q_init(struct wake_q_head *head)
 {

index 6f5fe50..c8a6256 100644
@@ -1904,8 +1904,8 @@ int __atomisp_streamoff(struct file *file, void *fh, enum v4l2_buf_type type)
 	dev_dbg(isp->dev, "Stop stream on pad %d for asd%d\n",
 		atomisp_subdev_source_pad(vdev), asd->index);
 
-	BUG_ON(!rt_mutex_is_locked(&isp->mutex));
-	BUG_ON(!mutex_is_locked(&isp->streamoff_mutex));
+	lockdep_assert_held(&isp->mutex);
+	lockdep_assert_held(&isp->streamoff_mutex);
 
 	if (type != V4L2_BUF_TYPE_VIDEO_CAPTURE) {
 		dev_dbg(isp->dev, "unsupported v4l2 buf type\n");

index 87b325a..cb0f441 100644
@@ -72,17 +72,6 @@ do { \
 #define DEFINE_RT_MUTEX(mutexname) \
 	struct rt_mutex mutexname = __RT_MUTEX_INITIALIZER(mutexname)
 
-/**
- * rt_mutex_is_locked - is the mutex locked
- * @lock: the mutex to be queried
- *
- * Returns 1 if the mutex is locked, 0 if unlocked.
- */
-static inline int rt_mutex_is_locked(struct rt_mutex *lock)
-{
-	return lock->owner != NULL;
-}
-
 extern void __rt_mutex_init(struct rt_mutex *lock, const char *name, struct lock_class_key *key);
 
 #ifdef CONFIG_DEBUG_LOCK_ALLOC

index 1a7e3f8..5187add 100644
@@ -141,8 +141,19 @@ static __always_inline void fixup_rt_mutex_waiters(struct rt_mutex *lock)
  * set up.
  */
 #ifndef CONFIG_DEBUG_RT_MUTEXES
-# define rt_mutex_cmpxchg_acquire(l,c,n) (cmpxchg_acquire(&l->owner, c, n) == c)
-# define rt_mutex_cmpxchg_release(l,c,n) (cmpxchg_release(&l->owner, c, n) == c)
+static __always_inline bool rt_mutex_cmpxchg_acquire(struct rt_mutex *lock,
+						     struct task_struct *old,
+						     struct task_struct *new)
+{
+	return cmpxchg_acquire(&lock->owner, old, new) == old;
+}
+
+static __always_inline bool rt_mutex_cmpxchg_release(struct rt_mutex *lock,
+						     struct task_struct *old,
+						     struct task_struct *new)
+{
+	return cmpxchg_release(&lock->owner, old, new) == old;
+}
 
 /*
  * Callers must hold the ->wait_lock -- which is the whole purpose as we force

@@ -201,8 +212,20 @@ static __always_inline bool unlock_rt_mutex_safe(struct rt_mutex *lock,
 }
 
 #else
-# define rt_mutex_cmpxchg_acquire(l,c,n)	(0)
-# define rt_mutex_cmpxchg_release(l,c,n)	(0)
+static __always_inline bool rt_mutex_cmpxchg_acquire(struct rt_mutex *lock,
+						     struct task_struct *old,
+						     struct task_struct *new)
+{
+	return false;
+
+}
+
+static __always_inline bool rt_mutex_cmpxchg_release(struct rt_mutex *lock,
+						     struct task_struct *old,
+						     struct task_struct *new)
+{
+	return false;
+}
 
 static __always_inline void mark_rt_mutex_waiters(struct rt_mutex *lock)
 {

index 5187add..98f06c5 100644
@@ -145,14 +145,14 @@ static __always_inline bool rt_mutex_cmpxchg_acquire(struct rt_mutex *lock,
 						     struct task_struct *old,
 						     struct task_struct *new)
 {
-	return cmpxchg_acquire(&lock->owner, old, new) == old;
+	return try_cmpxchg_acquire(&lock->owner, &old, new);
 }
 
 static __always_inline bool rt_mutex_cmpxchg_release(struct rt_mutex *lock,
 						     struct task_struct *old,
 						     struct task_struct *new)
 {
-	return cmpxchg_release(&lock->owner, old, new) == old;
+	return try_cmpxchg_release(&lock->owner, &old, new);
 }
 
 /*

527 lines not on this page · raw message

453 lines not on this page · raw message

100 lines not on this page · raw message

index cb0f441..8527402 100644
@@ -19,6 +19,21 @@
 
 extern int max_lock_depth; /* for sysctl */
 
+struct rt_mutex_base {
+	raw_spinlock_t		wait_lock;
+	struct rb_root_cached   waiters;
+	struct task_struct	*owner;
+};
+
+#define __RT_MUTEX_BASE_INITIALIZER(rtbasename)				\
+{									\
+	.wait_lock = __RAW_SPIN_LOCK_UNLOCKED(rtbasename.wait_lock),	\
+	.waiters = RB_ROOT_CACHED,					\
+	.owner = NULL							\
+}
+
+extern void rt_mutex_base_init(struct rt_mutex_base *rtb);
+
 /**
  * The rt_mutex structure
  *

@@ -28,9 +43,7 @@ extern int max_lock_depth; /* for sysctl */
  * @owner:	the mutex owner
  */
 struct rt_mutex {
-	raw_spinlock_t		wait_lock;
-	struct rb_root_cached   waiters;
-	struct task_struct	*owner;
+	struct rt_mutex_base	rtmutex;
 #ifdef CONFIG_DEBUG_LOCK_ALLOC
 	struct lockdep_map	dep_map;
 #endif

@@ -63,9 +76,7 @@ do { \
 
 #define __RT_MUTEX_INITIALIZER(mutexname)				\
 {									\
-	.wait_lock = __RAW_SPIN_LOCK_UNLOCKED(mutexname.wait_lock),	\
-	.waiters = RB_ROOT_CACHED,					\
-	.owner = NULL,							\
+	.rtmutex = __RT_MUTEX_BASE_INITIALIZER(mutexname.rtmutex),	\
 	__DEP_MAP_RT_MUTEX_INITIALIZER(mutexname)			\
 }
 

index 2ecb075..6eab247 100644
@@ -179,7 +179,7 @@ struct futex_pi_state {
 	/*
 	 * The PI object:
 	 */
-	struct rt_mutex pi_mutex;
+	struct rt_mutex_base pi_mutex;
 
 	struct task_struct *owner;
 	refcount_t refcount;

@@ -3254,7 +3254,7 @@ static int futex_wait_requeue_pi(u32 __user *uaddr, unsigned int flags,
 			ret = ret < 0 ? ret : 0;
 		}
 	} else {
-		struct rt_mutex *pi_mutex;
+		struct rt_mutex_base *pi_mutex;
 
 		/*
 		 * We have been woken up by futex_unlock_pi(), a timeout, or a

240 lines not on this page · raw message

139 lines not on this page · raw message

index 0f314a2..548285a 100644
@@ -32,7 +32,7 @@ struct rt_mutex_waiter {
 	struct rb_node		tree_entry;
 	struct rb_node		pi_tree_entry;
 	struct task_struct	*task;
-	struct rt_mutex		*lock;
+	struct rt_mutex_base	*lock;
 	int			prio;
 	u64			deadline;
 };

@@ -40,26 +40,26 @@ struct rt_mutex_waiter {
 /*
  * PI-futex support (proxy locking functions, etc.):
  */
-extern void rt_mutex_init_proxy_locked(struct rt_mutex *lock,
+extern void rt_mutex_init_proxy_locked(struct rt_mutex_base *lock,
 				       struct task_struct *proxy_owner);
-extern void rt_mutex_proxy_unlock(struct rt_mutex *lock);
-extern int __rt_mutex_start_proxy_lock(struct rt_mutex *lock,
+extern void rt_mutex_proxy_unlock(struct rt_mutex_base *lock);
+extern int __rt_mutex_start_proxy_lock(struct rt_mutex_base *lock,
 				     struct rt_mutex_waiter *waiter,
 				     struct task_struct *task);
-extern int rt_mutex_start_proxy_lock(struct rt_mutex *lock,
+extern int rt_mutex_start_proxy_lock(struct rt_mutex_base *lock,
 				     struct rt_mutex_waiter *waiter,
 				     struct task_struct *task);
-extern int rt_mutex_wait_proxy_lock(struct rt_mutex *lock,
+extern int rt_mutex_wait_proxy_lock(struct rt_mutex_base *lock,
 			       struct hrtimer_sleeper *to,
 			       struct rt_mutex_waiter *waiter);
-extern bool rt_mutex_cleanup_proxy_lock(struct rt_mutex *lock,
+extern bool rt_mutex_cleanup_proxy_lock(struct rt_mutex_base *lock,
 				 struct rt_mutex_waiter *waiter);
 
-extern int rt_mutex_futex_trylock(struct rt_mutex *l);
-extern int __rt_mutex_futex_trylock(struct rt_mutex *l);
+extern int rt_mutex_futex_trylock(struct rt_mutex_base *l);
+extern int __rt_mutex_futex_trylock(struct rt_mutex_base *l);
 
-extern void rt_mutex_futex_unlock(struct rt_mutex *lock);
-extern bool __rt_mutex_futex_unlock(struct rt_mutex *lock,
+extern void rt_mutex_futex_unlock(struct rt_mutex_base *lock);
+extern bool __rt_mutex_futex_unlock(struct rt_mutex_base *lock,
 				struct wake_q_head *wake_q);
 
 extern void rt_mutex_postunlock(struct wake_q_head *wake_q);

@@ -69,12 +69,12 @@ extern void rt_mutex_postunlock(struct wake_q_head *wake_q);
  * unconditionally.
  */
 #ifdef CONFIG_RT_MUTEXES
-static inline int rt_mutex_has_waiters(struct rt_mutex *lock)
+static inline int rt_mutex_has_waiters(struct rt_mutex_base *lock)
 {
 	return !RB_EMPTY_ROOT(&lock->waiters.rb_root);
 }
 
-static inline struct rt_mutex_waiter *rt_mutex_top_waiter(struct rt_mutex *lock)
+static inline struct rt_mutex_waiter *rt_mutex_top_waiter(struct rt_mutex_base *lock)
 {
 	struct rb_node *leftmost = rb_first_cached(&lock->waiters);
 	struct rt_mutex_waiter *w = NULL;

@@ -99,7 +99,7 @@ static inline struct rt_mutex_waiter *task_top_pi_waiter(struct task_struct *p)
 
 #define RT_MUTEX_HAS_WAITERS	1UL
 
-static inline struct task_struct *rt_mutex_owner(struct rt_mutex *lock)
+static inline struct task_struct *rt_mutex_owner(struct rt_mutex_base *lock)
 {
 	unsigned long owner = (unsigned long) READ_ONCE(lock->owner);
 

@@ -121,21 +121,21 @@ enum rtmutex_chainwalk {
 	RT_MUTEX_FULL_CHAINWALK,
 };
 
-static inline void __rt_mutex_basic_init(struct rt_mutex *lock)
+static inline void __rt_mutex_base_init(struct rt_mutex_base *lock)
 {
-	lock->owner = NULL;
 	raw_spin_lock_init(&lock->wait_lock);
 	lock->waiters = RB_ROOT_CACHED;
+	lock->owner = NULL;
 }
 
 /* Debug functions */
-static inline void debug_rt_mutex_unlock(struct rt_mutex *lock)
+static inline void debug_rt_mutex_unlock(struct rt_mutex_base *lock)
 {
 	if (IS_ENABLED(CONFIG_DEBUG_RT_MUTEXES))
 		DEBUG_LOCKS_WARN_ON(rt_mutex_owner(lock) != current);
 }
 
-static inline void debug_rt_mutex_proxy_unlock(struct rt_mutex *lock)
+static inline void debug_rt_mutex_proxy_unlock(struct rt_mutex_base *lock)
 {
 	if (IS_ENABLED(CONFIG_DEBUG_RT_MUTEXES))
 		DEBUG_LOCKS_WARN_ON(!rt_mutex_owner(lock));

@@ -163,7 +163,7 @@ static inline void rt_mutex_init_waiter(struct rt_mutex_waiter *waiter)
 
 #else /* CONFIG_RT_MUTEXES */
 /* Used in rcu/tree_plugin.h */
-static inline struct task_struct *rt_mutex_owner(struct rt_mutex *lock)
+static inline struct task_struct *rt_mutex_owner(struct rt_mutex_base *lock)
 {
 	return NULL;
 }

index de1dc3b..0ff5e4f 100644
@@ -559,7 +559,7 @@ rcu_preempt_deferred_qs_irqrestore(struct task_struct *t, unsigned long flags)
 			WRITE_ONCE(rnp->exp_tasks, np);
 		if (IS_ENABLED(CONFIG_RCU_BOOST)) {
 			/* Snapshot ->boost_mtx ownership w/rnp->lock held. */
-			drop_boost_mutex = rt_mutex_owner(&rnp->boost_mtx) == t;
+			drop_boost_mutex = rt_mutex_owner(&rnp->boost_mtx.rtmutex) == t;
 			if (&t->rcu_node_entry == rnp->boost_tasks)
 				WRITE_ONCE(rnp->boost_tasks, np);
 		}

@@ -586,7 +586,7 @@ rcu_preempt_deferred_qs_irqrestore(struct task_struct *t, unsigned long flags)
 
 		/* Unboost if we were boosted. */
 		if (IS_ENABLED(CONFIG_RCU_BOOST) && drop_boost_mutex)
-			rt_mutex_futex_unlock(&rnp->boost_mtx);
+			rt_mutex_futex_unlock(&rnp->boost_mtx.rtmutex);
 
 		/*
 		 * If this was the last task on the expedited lists,

@@ -1083,7 +1083,7 @@ static int rcu_boost(struct rcu_node *rnp)
 	 * section.
 	 */
 	t = container_of(tb, struct task_struct, rcu_node_entry);
-	rt_mutex_init_proxy_locked(&rnp->boost_mtx, t);
+	rt_mutex_init_proxy_locked(&rnp->boost_mtx.rtmutex, t);
 	raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
 	/* Lock only for side effect: boosts task t's priority. */
 	rt_mutex_lock(&rnp->boost_mtx);

index b31f6cb..3d0b29c 100644
@@ -1106,7 +1106,7 @@ static void __sched remove_waiter(struct rt_mutex_base *lock,
 }
 
 /**
- * __rt_mutex_slowlock() - Perform the wait-wake-try-to-take loop
+ * rt_mutex_slowlock_block() - Perform the wait-wake-try-to-take loop
  * @lock:		 the rt_mutex to take
  * @state:		 the state the task should block in (TASK_INTERRUPTIBLE
  *			 or TASK_UNINTERRUPTIBLE)

@@ -1115,10 +1115,10 @@ static void __sched remove_waiter(struct rt_mutex_base *lock,
  *
  * Must be called with lock->wait_lock held and interrupts disabled
  */
-static int __sched __rt_mutex_slowlock(struct rt_mutex_base *lock,
-				       unsigned int state,
-				       struct hrtimer_sleeper *timeout,
-				       struct rt_mutex_waiter *waiter)
+static int __sched rt_mutex_slowlock_block(struct rt_mutex_base *lock,
+					   unsigned int state,
+					   struct hrtimer_sleeper *timeout,
+					   struct rt_mutex_waiter *waiter)
 {
 	int ret = 0;
 

@@ -1168,52 +1168,37 @@ static void __sched rt_mutex_handle_deadlock(int res, int detect_deadlock,
 	}
 }
 
-/*
- * Slow path lock function:
+/**
+ * __rt_mutex_slowlock - Locking slowpath invoked with lock::wait_lock held
+ * @lock:	The rtmutex to block lock
+ * @state:	The task state for sleeping
+ * @chwalk:	Indicator whether full or partial chainwalk is requested
+ * @waiter:	Initializer waiter for blocking
  */
-static int __sched rt_mutex_slowlock(struct rt_mutex_base *lock,
-				     unsigned int state,
-				     struct hrtimer_sleeper *timeout,
-				     enum rtmutex_chainwalk chwalk)
+static int __sched __rt_mutex_slowlock(struct rt_mutex_base *lock,
+				       unsigned int state,
+				       enum rtmutex_chainwalk chwalk,
+				       struct rt_mutex_waiter *waiter)
 {
-	struct rt_mutex_waiter waiter;
-	unsigned long flags;
-	int ret = 0;
-
-	rt_mutex_init_waiter(&waiter);
+	int ret;
 
-	/*
-	 * Technically we could use raw_spin_[un]lock_irq() here, but this can
-	 * be called in early boot if the cmpxchg() fast path is disabled
-	 * (debug, no architecture support). In this case we will acquire the
-	 * rtmutex with lock->wait_lock held. But we cannot unconditionally
-	 * enable interrupts in that early boot case. So we need to use the
-	 * irqsave/restore variants.
-	 */
-	raw_spin_lock_irqsave(&lock->wait_lock, flags);
+	lockdep_assert_held(&lock->wait_lock);
 
 	/* Try to acquire the lock again: */
-	if (try_to_take_rt_mutex(lock, current, NULL)) {
-		raw_spin_unlock_irqrestore(&lock->wait_lock, flags);
+	if (try_to_take_rt_mutex(lock, current, NULL))
 		return 0;
-	}
 
 	set_current_state(state);
 
-	/* Setup the timer, when timeout != NULL */
-	if (unlikely(timeout))
-		hrtimer_start_expires(&timeout->timer, HRTIMER_MODE_ABS);
-
-	ret = task_blocks_on_rt_mutex(lock, &waiter, current, chwalk);
+	ret = task_blocks_on_rt_mutex(lock, waiter, current, chwalk);
 
 	if (likely(!ret))
-		/* sleep on the mutex */
-		ret = __rt_mutex_slowlock(lock, state, timeout, &waiter);
+		ret = rt_mutex_slowlock_block(lock, state, NULL, waiter);
 
 	if (unlikely(ret)) {
 		__set_current_state(TASK_RUNNING);
-		remove_waiter(lock, &waiter);
-		rt_mutex_handle_deadlock(ret, chwalk, &waiter);
+		remove_waiter(lock, waiter);
+		rt_mutex_handle_deadlock(ret, chwalk, waiter);
 	}
 
 	/*

@@ -1221,14 +1206,45 @@ static int __sched rt_mutex_slowlock(struct rt_mutex_base *lock,
 	 * unconditionally. We might have to fix that up.
 	 */
 	fixup_rt_mutex_waiters(lock);
+	return ret;
+}
 
-	raw_spin_unlock_irqrestore(&lock->wait_lock, flags);
+static inline int __rt_mutex_slowlock_locked(struct rt_mutex_base *lock,
+					     unsigned int state)
+{
+	struct rt_mutex_waiter waiter;
+	int ret;
+
+	rt_mutex_init_waiter(&waiter);
 
-	/* Remove pending timer: */
-	if (unlikely(timeout))
-		hrtimer_cancel(&timeout->timer);
+	ret = __rt_mutex_slowlock(lock, state, RT_MUTEX_MIN_CHAINWALK, &waiter);
 
 	debug_rt_mutex_free_waiter(&waiter);
+	return ret;
+}
+
+/*
+ * rt_mutex_slowlock - Locking slowpath invoked when fast path fails
+ * @lock:	The rtmutex to block lock
+ * @state:	The task state for sleeping
+ */
+static int __sched rt_mutex_slowlock(struct rt_mutex_base *lock,
+				     unsigned int state)
+{
+	unsigned long flags;
+	int ret;
+
+	/*
+	 * Technically we could use raw_spin_[un]lock_irq() here, but this can
+	 * be called in early boot if the cmpxchg() fast path is disabled
+	 * (debug, no architecture support). In this case we will acquire the
+	 * rtmutex with lock->wait_lock held. But we cannot unconditionally
+	 * enable interrupts in that early boot case. So we need to use the
+	 * irqsave/restore variants.
+	 */
+	raw_spin_lock_irqsave(&lock->wait_lock, flags);
+	ret = __rt_mutex_slowlock_locked(lock, state);
+	raw_spin_unlock_irqrestore(&lock->wait_lock, flags);
 
 	return ret;
 }

@@ -1239,7 +1255,7 @@ static __always_inline int __rt_mutex_lock(struct rt_mutex_base *lock,
 	if (likely(rt_mutex_cmpxchg_acquire(lock, NULL, current)))
 		return 0;
 
-	return rt_mutex_slowlock(lock, state, NULL, RT_MUTEX_MIN_CHAINWALK);
+	return rt_mutex_slowlock(lock, state);
 }
 
 static int __sched __rt_mutex_slowtrylock(struct rt_mutex_base *lock)

index 38de4b1..c5136f4 100644
@@ -342,7 +342,7 @@ int __sched rt_mutex_wait_proxy_lock(struct rt_mutex_base *lock,
 	raw_spin_lock_irq(&lock->wait_lock);
 	/* sleep on the mutex */
 	set_current_state(TASK_INTERRUPTIBLE);
-	ret = __rt_mutex_slowlock(lock, TASK_INTERRUPTIBLE, to, waiter);
+	ret = rt_mutex_slowlock_block(lock, TASK_INTERRUPTIBLE, to, waiter);
 	/*
 	 * try_to_take_rt_mutex() sets the waiter bit unconditionally. We might
 	 * have to fix that up.

index 8527402..174419e 100644
@@ -13,6 +13,7 @@
 #ifndef __LINUX_RT_MUTEX_H
 #define __LINUX_RT_MUTEX_H
 
+#include <linux/compiler.h>
 #include <linux/linkage.h>
 #include <linux/rbtree.h>
 #include <linux/spinlock_types.h>

@@ -32,6 +33,17 @@ struct rt_mutex_base {
 	.owner = NULL							\
 }
 
+/**
+ * rt_mutex_base_is_locked - is the rtmutex locked
+ * @lock: the mutex to be queried
+ *
+ * Returns true if the mutex is locked, false if unlocked.
+ */
+static inline bool rt_mutex_base_is_locked(struct rt_mutex_base *lock)
+{
+	return READ_ONCE(lock->owner) != NULL;
+}
+
 extern void rt_mutex_base_init(struct rt_mutex_base *rtb);
 
 /**

new file mode 100644
index 0000000..1d264dd
@@ -0,0 +1,39 @@
+// SPDX-License-Identifier: GPL-2.0-only
+#ifndef _LINUX_RWBASE_RT_H
+#define _LINUX_RWBASE_RT_H
+
+#include <linux/rtmutex.h>
+#include <linux/atomic.h>
+
+#define READER_BIAS		(1U << 31)
+#define WRITER_BIAS		(1U << 30)
+
+struct rwbase_rt {
+	atomic_t		readers;
+	struct rt_mutex_base	rtmutex;
+};
+
+#define __RWBASE_INITIALIZER(name)				\
+{								\
+	.readers = ATOMIC_INIT(READER_BIAS),			\
+	.rtmutex = __RT_MUTEX_BASE_INITIALIZER(name.rtmutex),	\
+}
+
+#define init_rwbase_rt(rwbase)					\
+	do {							\
+		rt_mutex_base_init(&(rwbase)->rtmutex);		\
+		atomic_set(&(rwbase)->readers, READER_BIAS);	\
+	} while (0)
+
+
+static __always_inline bool rw_base_is_locked(struct rwbase_rt *rwb)
+{
+	return atomic_read(&rwb->readers) != READER_BIAS;
+}
+
+static __always_inline bool rw_base_is_contended(struct rwbase_rt *rwb)
+{
+	return atomic_read(&rwb->readers) > 0;
+}
+
+#endif /* _LINUX_RWBASE_RT_H */

263 lines not on this page · raw message

index a66038d..426e98e 100644
@@ -16,6 +16,19 @@
 #include <linux/spinlock.h>
 #include <linux/atomic.h>
 #include <linux/err.h>
+
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+# define __RWSEM_DEP_MAP_INIT(lockname)			\
+	.dep_map = {					\
+		.name = #lockname,			\
+		.wait_type_inner = LD_WAIT_SLEEP,	\
+	},
+#else
+# define __RWSEM_DEP_MAP_INIT(lockname)
+#endif
+
+#ifndef CONFIG_PREEMPT_RT
+
 #ifdef CONFIG_RWSEM_SPIN_ON_OWNER
 #include <linux/osq_lock.h>
 #endif

@@ -64,16 +77,6 @@ static inline int rwsem_is_locked(struct rw_semaphore *sem)
 
 /* Common initializer macros and functions */
 
-#ifdef CONFIG_DEBUG_LOCK_ALLOC
-# define __RWSEM_DEP_MAP_INIT(lockname)			\
-	.dep_map = {					\
-		.name = #lockname,			\
-		.wait_type_inner = LD_WAIT_SLEEP,	\
-	},
-#else
-# define __RWSEM_DEP_MAP_INIT(lockname)
-#endif
-
 #ifdef CONFIG_DEBUG_RWSEMS
 # define __RWSEM_DEBUG_INIT(lockname) .magic = &lockname,
 #else

@@ -119,6 +122,61 @@ static inline int rwsem_is_contended(struct rw_semaphore *sem)
 	return !list_empty(&sem->wait_list);
 }
 
+#else /* !CONFIG_PREEMPT_RT */
+
+#include <linux/rwbase_rt.h>
+
+struct rw_semaphore {
+	struct rwbase_rt	rwbase;
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+	struct lockdep_map	dep_map;
+#endif
+};
+
+#define __RWSEM_INITIALIZER(name)				\
+	{							\
+		.rwbase = __RWBASE_INITIALIZER(name),		\
+		__RWSEM_DEP_MAP_INIT(name)			\
+	}
+
+#define DECLARE_RWSEM(lockname) \
+	struct rw_semaphore lockname = __RWSEM_INITIALIZER(lockname)
+
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+extern void  __rwsem_init(struct rw_semaphore *rwsem, const char *name,
+			  struct lock_class_key *key);
+#else
+static inline void  __rwsem_init(struct rw_semaphore *rwsem, const char *name,
+				 struct lock_class_key *key)
+{
+}
+#endif
+
+#define init_rwsem(sem)						\
+do {								\
+	static struct lock_class_key __key;			\
+								\
+	init_rwbase_rt(&(sem)->rwbase);			\
+	__rwsem_init((sem), #sem, &__key);			\
+} while (0)
+
+static __always_inline int rwsem_is_locked(struct rw_semaphore *sem)
+{
+	return rw_base_is_locked(&sem->rwbase);
+}
+
+static __always_inline int rwsem_is_contended(struct rw_semaphore *sem)
+{
+	return rw_base_is_contended(&sem->rwbase);
+}
+
+#endif /* CONFIG_PREEMPT_RT */
+
+/*
+ * The functions below are the same for all rwsem implementations including
+ * the RT specific variant.
+ */
+
 /*
  * lock for reading
  */

120 lines not on this page · raw message

index 3d0b29c..c13b9b8 100644
@@ -692,7 +692,7 @@ static int __sched rt_mutex_adjust_prio_chain(struct task_struct *task,
 		 * to get the lock.
 		 */
 		if (prerequeue_top_waiter != rt_mutex_top_waiter(lock))
-			wake_up_process(rt_mutex_top_waiter(lock)->task);
+			wake_up_state(waiter->task, waiter->wake_state);
 		raw_spin_unlock_irq(&lock->wait_lock);
 		return 0;
 	}

index 548285a..fcc55de 100644
@@ -25,6 +25,7 @@
  * @pi_tree_entry:	pi node to enqueue into the mutex owner waiters tree
  * @task:		task reference to the blocked task
  * @lock:		Pointer to the rt_mutex on which the waiter blocks
+ * @wake_state:		Wakeup state to use (TASK_NORMAL or TASK_RTLOCK_WAIT)
  * @prio:		Priority of the waiter
  * @deadline:		Deadline of the waiter if applicable
  */

@@ -33,6 +34,7 @@ struct rt_mutex_waiter {
 	struct rb_node		pi_tree_entry;
 	struct task_struct	*task;
 	struct rt_mutex_base	*lock;
+	unsigned int		wake_state;
 	int			prio;
 	u64			deadline;
 };

@@ -158,9 +160,16 @@ static inline void rt_mutex_init_waiter(struct rt_mutex_waiter *waiter)
 	debug_rt_mutex_init_waiter(waiter);
 	RB_CLEAR_NODE(&waiter->pi_tree_entry);
 	RB_CLEAR_NODE(&waiter->tree_entry);
+	waiter->wake_state = TASK_NORMAL;
 	waiter->task = NULL;
 }
 
+static inline void rtlock_init_rtmutex_waiter(struct rt_mutex_waiter *waiter)
+{
+	rt_mutex_init_waiter(waiter);
+	waiter->wake_state = TASK_RTLOCK_WAIT;
+}
+
 #else /* CONFIG_RT_MUTEXES */
 /* Used in rcu/tree_plugin.h */
 static inline struct task_struct *rt_mutex_owner(struct rt_mutex_base *lock)

index c13b9b8..35f7685 100644
@@ -347,6 +347,21 @@ static __always_inline void rt_mutex_adjust_prio(struct task_struct *p)
 	rt_mutex_setprio(p, pi_task);
 }
 
+/* RT mutex specific wake_q wrappers */
+static __always_inline void rt_mutex_wake_q_add(struct rt_wake_q_head *wqh,
+						struct rt_mutex_waiter *w)
+{
+	wake_q_add(&wqh->head, w->task);
+}
+
+static __always_inline void rt_mutex_wake_up_q(struct rt_wake_q_head *wqh)
+{
+	wake_up_q(&wqh->head);
+
+	/* Pairs with preempt_disable() in mark_wakeup_next_waiter() */
+	preempt_enable();
+}
+
 /*
  * Deadlock detection is conditional:
  *