Message-ID: <20080815120846.24722.46227.stgit@dev.haskins.net>
Date:	Fri, 15 Aug 2008 08:08:47 -0400
From:	Gregory Haskins <ghaskins@...ell.com>
To:	mingo@...e.hu, paulmck@...ux.vnet.ibm.com, peterz@...radead.org,
	tglx@...utronix.de, rostedt@...dmis.org
Cc:	linux-kernel@...r.kernel.org, linux-rt-users@...r.kernel.org,
	gregory.haskins@...il.com, David.Holmes@....com
Subject: [PATCH RT RFC v2 7/8] rtmutex: convert rtmutexes to fully use the PI
	library

We have previously only laid some of the groundwork to use the PI
library, but left the existing infrastructure in place in the
rtmutex code.  This patch converts the rtmutex PI code to officially
use the PI library.

Signed-off-by: Gregory Haskins <ghaskins@...ell.com>
---

 include/linux/rt_lock.h   |    2 
 include/linux/rtmutex.h   |   15 -
 include/linux/sched.h     |   21 -
 kernel/fork.c             |    2 
 kernel/rcupreempt-boost.c |    2 
 kernel/rtmutex-debug.c    |    4 
 kernel/rtmutex-tester.c   |    4 
 kernel/rtmutex.c          |  944 ++++++++++++++-------------------------------
 kernel/rtmutex_common.h   |   18 -
 kernel/rwlock_torture.c   |   32 --
 kernel/sched.c            |   12 -
 11 files changed, 321 insertions(+), 735 deletions(-)

diff --git a/include/linux/rt_lock.h b/include/linux/rt_lock.h
index c00cfb3..d0ef0f1 100644
--- a/include/linux/rt_lock.h
+++ b/include/linux/rt_lock.h
@@ -14,6 +14,7 @@
 #include <asm/atomic.h>
 #include <linux/spinlock_types.h>
 #include <linux/sched_prio.h>
+#include <linux/pi.h>
 
 #ifdef CONFIG_PREEMPT_RT
 /*
@@ -67,6 +68,7 @@ struct rw_mutex {
 	atomic_t		count;	/* number of times held for read */
 	atomic_t		owners; /* number of owners as readers */
 	struct list_head	readers;
+	struct pi_sink          pi_snk;
 	int prio;
 };
 
diff --git a/include/linux/rtmutex.h b/include/linux/rtmutex.h
index 14774ce..d984244 100644
--- a/include/linux/rtmutex.h
+++ b/include/linux/rtmutex.h
@@ -15,6 +15,7 @@
 #include <linux/linkage.h>
 #include <linux/plist.h>
 #include <linux/spinlock_types.h>
+#include <linux/pi.h>
 
 /**
  * The rt_mutex structure
@@ -27,6 +28,12 @@ struct rt_mutex {
 	raw_spinlock_t		wait_lock;
 	struct plist_head	wait_list;
 	struct task_struct	*owner;
+	struct {
+		struct pi_source src;
+		struct pi_node   node;
+		struct pi_sink   snk;
+		int              prio;
+	} pi;
 #ifdef CONFIG_DEBUG_RT_MUTEXES
 	int			save_state;
 	const char 		*name, *file;
@@ -96,12 +103,4 @@ extern int rt_mutex_trylock(struct rt_mutex *lock);
 
 extern void rt_mutex_unlock(struct rt_mutex *lock);
 
-#ifdef CONFIG_RT_MUTEXES
-# define INIT_RT_MUTEXES(tsk)						\
-	.pi_waiters = PLIST_HEAD_INIT(tsk.pi_waiters, &tsk.pi_lock),	\
-	INIT_RT_MUTEX_DEBUG(tsk)
-#else
-# define INIT_RT_MUTEXES(tsk)
-#endif
-
 #endif
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 9132b42..d59c804 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1106,6 +1106,7 @@ struct reader_lock_struct {
 	struct rw_mutex *lock;
 	struct list_head list;
 	struct task_struct *task;
+	struct pi_source pi_src;
 	int count;
 };
 
@@ -1309,15 +1310,6 @@ struct task_struct {
 
 	} pi;
 
-#ifdef CONFIG_RT_MUTEXES
-	/* PI waiters blocked on a rt_mutex held by this task */
-	struct plist_head pi_waiters;
-	/* Deadlock detection and priority inheritance handling */
-	struct rt_mutex_waiter *pi_blocked_on;
-	int rtmutex_prio;
-	struct pi_source rtmutex_prio_src;
-#endif
-
 #ifdef CONFIG_DEBUG_MUTEXES
 	/* mutex deadlock detection */
 	struct mutex_waiter *blocked_on;
@@ -1806,17 +1798,6 @@ int sched_rt_handler(struct ctl_table *table, int write,
 
 extern unsigned int sysctl_sched_compat_yield;
 
-#ifdef CONFIG_RT_MUTEXES
-extern int rt_mutex_getprio(struct task_struct *p);
-extern void rt_mutex_adjust_pi(struct task_struct *p);
-#else
-static inline int rt_mutex_getprio(struct task_struct *p)
-{
-	return p->normal_prio;
-}
-# define rt_mutex_adjust_pi(p)		do { } while (0)
-#endif
-
 extern void set_user_nice(struct task_struct *p, long nice);
 extern int task_prio(const struct task_struct *p);
 extern int task_nice(const struct task_struct *p);
diff --git a/kernel/fork.c b/kernel/fork.c
index 399a0a9..759c6de 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -885,8 +885,6 @@ static void rt_mutex_init_task(struct task_struct *p)
 {
 	spin_lock_init(&p->pi_lock);
 #ifdef CONFIG_RT_MUTEXES
-	plist_head_init(&p->pi_waiters, &p->pi_lock);
-	p->pi_blocked_on = NULL;
 # ifdef CONFIG_DEBUG_RT_MUTEXES
 	p->last_kernel_lock = NULL;
 # endif
diff --git a/kernel/rcupreempt-boost.c b/kernel/rcupreempt-boost.c
index e8d9d76..85b3c2b 100644
--- a/kernel/rcupreempt-boost.c
+++ b/kernel/rcupreempt-boost.c
@@ -424,7 +424,7 @@ void rcu_boost_readers(void)
 
 	spin_lock_irqsave(&rcu_boost_wake_lock, flags);
 
-	prio = rt_mutex_getprio(curr);
+	prio = get_rcu_prio(curr);
 
 	rcu_trace_boost_try_boost_readers(RCU_BOOST_ME);
 
diff --git a/kernel/rtmutex-debug.c b/kernel/rtmutex-debug.c
index 0d9cb54..2034ce1 100644
--- a/kernel/rtmutex-debug.c
+++ b/kernel/rtmutex-debug.c
@@ -57,8 +57,6 @@ static void printk_lock(struct rt_mutex *lock, int print_owner)
 
 void rt_mutex_debug_task_free(struct task_struct *task)
 {
-	DEBUG_LOCKS_WARN_ON(!plist_head_empty(&task->pi_waiters));
-	DEBUG_LOCKS_WARN_ON(task->pi_blocked_on);
 #ifdef CONFIG_PREEMPT_RT
 	WARN_ON(task->reader_lock_count);
 #endif
@@ -156,7 +154,6 @@ void debug_rt_mutex_init_waiter(struct rt_mutex_waiter *waiter)
 {
 	memset(waiter, 0x11, sizeof(*waiter));
 	plist_node_init(&waiter->list_entry, MAX_PRIO);
-	plist_node_init(&waiter->pi_list_entry, MAX_PRIO);
 	waiter->deadlock_task_pid = NULL;
 }
 
@@ -164,7 +161,6 @@ void debug_rt_mutex_free_waiter(struct rt_mutex_waiter *waiter)
 {
 	put_pid(waiter->deadlock_task_pid);
 	DEBUG_LOCKS_WARN_ON(!plist_node_empty(&waiter->list_entry));
-	DEBUG_LOCKS_WARN_ON(!plist_node_empty(&waiter->pi_list_entry));
 	DEBUG_LOCKS_WARN_ON(waiter->task);
 	memset(waiter, 0x22, sizeof(*waiter));
 }
diff --git a/kernel/rtmutex-tester.c b/kernel/rtmutex-tester.c
index 092e4c6..dff8781 100644
--- a/kernel/rtmutex-tester.c
+++ b/kernel/rtmutex-tester.c
@@ -373,11 +373,11 @@ static ssize_t sysfs_test_status(struct sys_device *dev, char *buf)
 	spin_lock(&rttest_lock);
 
 	curr += sprintf(curr,
-		"O: %4d, E:%8d, S: 0x%08lx, P: %4d, N: %4d, B: %p, K: %d, M:",
+		"O: %4d, E:%8d, S: 0x%08lx, P: %4d, N: %4d, K: %d M:",
 		td->opcode, td->event, tsk->state,
 			(MAX_RT_PRIO - 1) - tsk->prio,
 			(MAX_RT_PRIO - 1) - tsk->normal_prio,
-		tsk->pi_blocked_on, td->bkl);
+			td->bkl);
 
 	for (i = MAX_RT_TEST_MUTEXES - 1; i >=0 ; i--)
 		curr += sprintf(curr, "%d", td->mutexes[i]);
diff --git a/kernel/rtmutex.c b/kernel/rtmutex.c
index 62fdc3d..0f64298 100644
--- a/kernel/rtmutex.c
+++ b/kernel/rtmutex.c
@@ -58,14 +58,32 @@
  * state.
  */
 
+static inline void
+rtmutex_pi_owner(struct rt_mutex *lock, struct task_struct *p, int add)
+{
+	if (!p || p == RT_RW_READER)
+		return;
+
+	if (add)
+		task_pi_boost(p, &lock->pi.src, PI_FLAG_DEFER_UPDATE);
+	else
+		task_pi_deboost(p, &lock->pi.src, PI_FLAG_DEFER_UPDATE);
+}
+
 static void
 rt_mutex_set_owner(struct rt_mutex *lock, struct task_struct *owner,
 		   unsigned long mask)
 {
 	unsigned long val = (unsigned long)owner | mask;
 
-	if (rt_mutex_has_waiters(lock))
+	if (rt_mutex_has_waiters(lock)) {
+		struct task_struct *prev_owner = rt_mutex_owner(lock);
+
+		rtmutex_pi_owner(lock, prev_owner, 0);
+		rtmutex_pi_owner(lock, owner, 1);
+
 		val |= RT_MUTEX_HAS_WAITERS;
+	}
 
 	lock->owner = (struct task_struct *)val;
 }
@@ -134,245 +152,88 @@ static inline int task_is_reader(struct task_struct *task) { return 0; }
 #endif
 
 int pi_initialized;
-
-/*
- * we initialize the wait_list runtime. (Could be done build-time and/or
- * boot-time.)
- */
-static inline void init_lists(struct rt_mutex *lock)
+static inline int rtmutex_pi_boost(struct pi_sink *snk,
+				  struct pi_source *src,
+				  unsigned int flags)
 {
-	if (unlikely(!lock->wait_list.prio_list.prev)) {
-		plist_head_init(&lock->wait_list, &lock->wait_lock);
-#ifdef CONFIG_DEBUG_RT_MUTEXES
-		pi_initialized++;
-#endif
-	}
-}
-
-static int rt_mutex_get_readers_prio(struct task_struct *task, int prio);
-
-/*
- * Calculate task priority from the waiter list priority
- *
- * Return task->normal_prio when the waiter list is empty or when
- * the waiter is not allowed to do priority boosting
- */
-int rt_mutex_getprio(struct task_struct *task)
-{
-	int prio = min(task->normal_prio, get_rcu_prio(task));
-
-	prio = rt_mutex_get_readers_prio(task, prio);
-
-	if (likely(!task_has_pi_waiters(task)))
-		return prio;
-
-	return min(task_top_pi_waiter(task)->pi_list_entry.prio, prio);
-}
+	struct rt_mutex *lock = container_of(snk, struct rt_mutex, pi.snk);
 
-/*
- * Adjust the priority of a task, after its pi_waiters got modified.
- *
- * This can be both boosting and unboosting. task->pi_lock must be held.
- */
-static void __rt_mutex_adjust_prio(struct task_struct *task)
-{
-	int prio = rt_mutex_getprio(task);
-
-	if (task->rtmutex_prio != prio) {
-		task->rtmutex_prio = prio;
-		task_pi_boost(task, &task->rtmutex_prio_src, 0);
-	}
-}
-
-/*
- * Adjust task priority (undo boosting). Called from the exit path of
- * rt_mutex_slowunlock() and rt_mutex_slowlock().
- *
- * (Note: We do this outside of the protection of lock->wait_lock to
- * allow the lock to be taken while or before we readjust the priority
- * of task. We do not use the spin_xx_mutex() variants here as we are
- * outside of the debug path.)
- */
-static void rt_mutex_adjust_prio(struct task_struct *task)
-{
-	unsigned long flags;
+	/*
+	 * We dont need to take any locks here because the
+	 * lock->pi.node interlock is already guaranteeing mutual
+	 * exclusion.
+	 */
+	lock->pi.prio = *src->prio;
 
-	spin_lock_irqsave(&task->pi_lock, flags);
-	__rt_mutex_adjust_prio(task);
-	spin_unlock_irqrestore(&task->pi_lock, flags);
+	return 0;
 }
 
-/*
- * Max number of times we'll walk the boosting chain:
- */
-int max_lock_depth = 1024;
-
-static int rt_mutex_adjust_readers(struct rt_mutex *orig_lock,
-				   struct rt_mutex_waiter *orig_waiter,
-				   struct task_struct *top_task,
-				   struct rt_mutex *lock,
-				   int recursion_depth);
-/*
- * Adjust the priority chain. Also used for deadlock detection.
- * Decreases task's usage by one - may thus free the task.
- * Returns 0 or -EDEADLK.
- */
-static int rt_mutex_adjust_prio_chain(struct task_struct *task,
-				      int deadlock_detect,
-				      struct rt_mutex *orig_lock,
-				      struct rt_mutex_waiter *orig_waiter,
-				      struct task_struct *top_task,
-				      int recursion_depth)
+static inline int rtmutex_pi_update(struct pi_sink *snk,
+				    unsigned int flags)
 {
-	struct rt_mutex *lock;
-	struct rt_mutex_waiter *waiter, *top_waiter = orig_waiter;
-	int detect_deadlock, ret = 0, depth = 0;
-	unsigned long flags;
+	struct rt_mutex *lock = container_of(snk, struct rt_mutex, pi.snk);
+	struct task_struct *owner = NULL;
+	unsigned long iflags;
 
-	detect_deadlock = debug_rt_mutex_detect_deadlock(orig_waiter,
-							 deadlock_detect);
+	spin_lock_irqsave(&lock->wait_lock, iflags);
 
-	/*
-	 * The (de)boosting is a step by step approach with a lot of
-	 * pitfalls. We want this to be preemptible and we want hold a
-	 * maximum of two locks per step. So we have to check
-	 * carefully whether things change under us.
-	 */
- again:
-	if (++depth > max_lock_depth) {
-		static int prev_max;
+	if (rt_mutex_has_waiters(lock)) {
+		owner = rt_mutex_owner(lock);
 
-		/*
-		 * Print this only once. If the admin changes the limit,
-		 * print a new message when reaching the limit again.
-		 */
-		if (prev_max != max_lock_depth) {
-			prev_max = max_lock_depth;
-			printk(KERN_WARNING "Maximum lock depth %d reached "
-			       "task: %s (%d)\n", max_lock_depth,
-			       top_task->comm, task_pid_nr(top_task));
+		if (owner && owner != RT_RW_READER) {
+			rtmutex_pi_owner(lock, owner, 1);
+			get_task_struct(owner);
 		}
-		put_task_struct(task);
-
-		return deadlock_detect ? -EDEADLK : 0;
 	}
-  retry:
-	/*
-	 * Task can not go away as we did a get_task() before !
-	 */
-	spin_lock_irqsave(&task->pi_lock, flags);
 
-	waiter = task->pi_blocked_on;
-	/*
-	 * Check whether the end of the boosting chain has been
-	 * reached or the state of the chain has changed while we
-	 * dropped the locks.
-	 */
-	if (!waiter || !waiter->task)
-		goto out_unlock_pi;
-
-	/*
-	 * Check the orig_waiter state. After we dropped the locks,
-	 * the previous owner of the lock might have released the lock
-	 * and made us the pending owner:
-	 */
-	if (orig_waiter && !orig_waiter->task)
-		goto out_unlock_pi;
-
-	/*
-	 * Drop out, when the task has no waiters. Note,
-	 * top_waiter can be NULL, when we are in the deboosting
-	 * mode!
-	 */
-	if (top_waiter && (!task_has_pi_waiters(task) ||
-			   top_waiter != task_top_pi_waiter(task)))
-		goto out_unlock_pi;
-
-	/*
-	 * When deadlock detection is off then we check, if further
-	 * priority adjustment is necessary.
-	 */
-	if (!detect_deadlock && waiter->list_entry.prio == task->prio)
-		goto out_unlock_pi;
+	spin_unlock_irqrestore(&lock->wait_lock, iflags);
 
-	lock = waiter->lock;
-	if (!spin_trylock(&lock->wait_lock)) {
-		spin_unlock_irqrestore(&task->pi_lock, flags);
-		cpu_relax();
-		goto retry;
+	if (owner && owner != RT_RW_READER) {
+		task_pi_update(owner, 0);
+		put_task_struct(owner);
 	}
 
-	/* Deadlock detection */
-	if (lock == orig_lock || rt_mutex_owner(lock) == top_task) {
-		debug_rt_mutex_deadlock(deadlock_detect, orig_waiter, lock);
-		spin_unlock(&lock->wait_lock);
-		ret = deadlock_detect ? -EDEADLK : 0;
-		goto out_unlock_pi;
-	}
+	return 0;
+}
 
-	top_waiter = rt_mutex_top_waiter(lock);
+static struct pi_sink rtmutex_pi_snk = {
+    .boost = rtmutex_pi_boost,
+    .update = rtmutex_pi_update,
+};
 
-	/* Requeue the waiter */
-	plist_del(&waiter->list_entry, &lock->wait_list);
-	waiter->list_entry.prio = task->prio;
-	plist_add(&waiter->list_entry, &lock->wait_list);
-
-	/* Release the task */
-	spin_unlock(&task->pi_lock);
-	put_task_struct(task);
+static void init_pi(struct rt_mutex *lock)
+{
+	pi_node_init(&lock->pi.node);
 
-	/* Grab the next task */
-	task = rt_mutex_owner(lock);
+	lock->pi.prio = MAX_PRIO;
+	pi_source_init(&lock->pi.src, &lock->pi.prio);
+	lock->pi.snk = rtmutex_pi_snk;
 
-	/*
-	 * Readers are special. We may need to boost more than one owner.
-	 */
-	if (task_is_reader(task)) {
-		ret = rt_mutex_adjust_readers(orig_lock, orig_waiter,
-					      top_task, lock,
-					      recursion_depth);
-		spin_unlock_irqrestore(&lock->wait_lock, flags);
-		goto out;
-	}
+	pi_add_sink(&lock->pi.node, &lock->pi.snk,
+		    PI_FLAG_DEFER_UPDATE | PI_FLAG_ALREADY_BOOSTED);
+}
 
-	get_task_struct(task);
-	spin_lock(&task->pi_lock);
-
-	if (waiter == rt_mutex_top_waiter(lock)) {
-		/* Boost the owner */
-		plist_del(&top_waiter->pi_list_entry, &task->pi_waiters);
-		waiter->pi_list_entry.prio = waiter->list_entry.prio;
-		plist_add(&waiter->pi_list_entry, &task->pi_waiters);
-		__rt_mutex_adjust_prio(task);
-
-	} else if (top_waiter == waiter) {
-		/* Deboost the owner */
-		plist_del(&waiter->pi_list_entry, &task->pi_waiters);
-		waiter = rt_mutex_top_waiter(lock);
-		waiter->pi_list_entry.prio = waiter->list_entry.prio;
-		plist_add(&waiter->pi_list_entry, &task->pi_waiters);
-		__rt_mutex_adjust_prio(task);
+/*
+ * we initialize the wait_list runtime. (Could be done build-time and/or
+ * boot-time.)
+ */
+static inline void init_lists(struct rt_mutex *lock)
+{
+	if (unlikely(!lock->wait_list.prio_list.prev)) {
+		plist_head_init(&lock->wait_list, &lock->wait_lock);
+		init_pi(lock);
+#ifdef CONFIG_DEBUG_RT_MUTEXES
+		pi_initialized++;
+#endif
 	}
-
-	spin_unlock(&task->pi_lock);
-
-	top_waiter = rt_mutex_top_waiter(lock);
-	spin_unlock_irqrestore(&lock->wait_lock, flags);
-
-	if (!detect_deadlock && waiter != top_waiter)
-		goto out_put_task;
-
-	goto again;
-
- out_unlock_pi:
-	spin_unlock_irqrestore(&task->pi_lock, flags);
- out_put_task:
-	put_task_struct(task);
- out:
-	return ret;
 }
 
 /*
+ * Max number of times we'll walk the boosting chain:
+ */
+int max_lock_depth = 1024;
+
+/*
  * Optimization: check if we can steal the lock from the
  * assigned pending owner [which might not have taken the
  * lock yet]:
@@ -380,7 +241,6 @@ static int rt_mutex_adjust_prio_chain(struct task_struct *task,
 static inline int try_to_steal_lock(struct rt_mutex *lock, int mode)
 {
 	struct task_struct *pendowner = rt_mutex_owner(lock);
-	struct rt_mutex_waiter *next;
 
 	if (!rt_mutex_owner_pending(lock))
 		return 0;
@@ -390,49 +250,7 @@ static inline int try_to_steal_lock(struct rt_mutex *lock, int mode)
 
 	WARN_ON(task_is_reader(rt_mutex_owner(lock)));
 
-	spin_lock(&pendowner->pi_lock);
-	if (!lock_is_stealable(pendowner, mode)) {
-		spin_unlock(&pendowner->pi_lock);
-		return 0;
-	}
-
-	/*
-	 * Check if a waiter is enqueued on the pending owners
-	 * pi_waiters list. Remove it and readjust pending owners
-	 * priority.
-	 */
-	if (likely(!rt_mutex_has_waiters(lock))) {
-		spin_unlock(&pendowner->pi_lock);
-		return 1;
-	}
-
-	/* No chain handling, pending owner is not blocked on anything: */
-	next = rt_mutex_top_waiter(lock);
-	plist_del(&next->pi_list_entry, &pendowner->pi_waiters);
-	__rt_mutex_adjust_prio(pendowner);
-	spin_unlock(&pendowner->pi_lock);
-
-	/*
-	 * We are going to steal the lock and a waiter was
-	 * enqueued on the pending owners pi_waiters queue. So
-	 * we have to enqueue this waiter into
-	 * current->pi_waiters list. This covers the case,
-	 * where current is boosted because it holds another
-	 * lock and gets unboosted because the booster is
-	 * interrupted, so we would delay a waiter with higher
-	 * priority as current->normal_prio.
-	 *
-	 * Note: in the rare case of a SCHED_OTHER task changing
-	 * its priority and thus stealing the lock, next->task
-	 * might be current:
-	 */
-	if (likely(next->task != current)) {
-		spin_lock(&current->pi_lock);
-		plist_add(&next->pi_list_entry, &current->pi_waiters);
-		__rt_mutex_adjust_prio(current);
-		spin_unlock(&current->pi_lock);
-	}
-	return 1;
+	return lock_is_stealable(pendowner, mode);
 }
 
 /*
@@ -486,74 +304,145 @@ static inline int try_to_take_rt_mutex(struct rt_mutex *lock)
 }
 
 /*
- * Task blocks on lock.
- *
- * Prepare waiter and propagate pi chain
- *
- * This must be called with lock->wait_lock held.
+ * These callbacks are invoked whenever a waiter has changed priority.
+ * So we should requeue it within the lock->wait_list
  */
-static int task_blocks_on_rt_mutex(struct rt_mutex *lock,
-				   struct rt_mutex_waiter *waiter,
-				   int detect_deadlock, unsigned long flags)
+
+static inline int rtmutex_waiter_pi_boost(struct pi_sink *snk,
+					  struct pi_source *src,
+					  unsigned int flags)
 {
-	struct task_struct *owner = rt_mutex_owner(lock);
-	struct rt_mutex_waiter *top_waiter = waiter;
-	int chain_walk = 0, res;
+	struct rt_mutex_waiter *waiter;
 
-	spin_lock(&current->pi_lock);
-	__rt_mutex_adjust_prio(current);
-	waiter->task = current;
-	waiter->lock = lock;
-	plist_node_init(&waiter->list_entry, current->prio);
-	plist_node_init(&waiter->pi_list_entry, current->prio);
+	waiter = container_of(snk, struct rt_mutex_waiter, pi.snk);
 
-	/* Get the top priority waiter on the lock */
-	if (rt_mutex_has_waiters(lock))
-		top_waiter = rt_mutex_top_waiter(lock);
-	plist_add(&waiter->list_entry, &lock->wait_list);
+	/*
+	 * We dont need to take any locks here because the
+	 * waiter->pi.node interlock is already guaranteeing mutual
+	 * exclusion.
+	 */
+	waiter->pi.prio = *src->prio;
 
-	current->pi_blocked_on = waiter;
+	return 0;
+}
 
-	spin_unlock(&current->pi_lock);
+static inline int rtmutex_waiter_pi_update(struct pi_sink *snk,
+					   unsigned int flags)
+{
+	struct rt_mutex *lock;
+	struct rt_mutex_waiter *waiter;
+	unsigned long iflags;
 
-	if (waiter == rt_mutex_top_waiter(lock)) {
-		/* readers are handled differently */
-		if (task_is_reader(owner)) {
-			res = rt_mutex_adjust_readers(lock, waiter,
-						      current, lock, 0);
-			return res;
-		}
+	waiter = container_of(snk, struct rt_mutex_waiter, pi.snk);
+	lock = waiter->lock;
 
-		spin_lock(&owner->pi_lock);
-		plist_del(&top_waiter->pi_list_entry, &owner->pi_waiters);
-		plist_add(&waiter->pi_list_entry, &owner->pi_waiters);
+	spin_lock_irqsave(&lock->wait_lock, iflags);
 
-		__rt_mutex_adjust_prio(owner);
-		if (owner->pi_blocked_on)
-			chain_walk = 1;
-		spin_unlock(&owner->pi_lock);
+	/*
+	 * If waiter->task is non-NULL, it means we are still valid in the
+	 * pi list.  Therefore, if waiter->pi.prio has changed since we
+	 * queued ourselves, requeue it.
+	 */
+	if (waiter->task && waiter->list_entry.prio != waiter->pi.prio) {
+		plist_del(&waiter->list_entry, &lock->wait_list);
+		plist_node_init(&waiter->list_entry, waiter->pi.prio);
+		plist_add(&waiter->list_entry, &lock->wait_list);
 	}
-	else if (debug_rt_mutex_detect_deadlock(waiter, detect_deadlock))
-		chain_walk = 1;
 
-	if (!chain_walk || task_is_reader(owner))
-		return 0;
+	spin_unlock_irqrestore(&lock->wait_lock, iflags);
+
+	return 0;
+}
+
+static struct pi_sink rtmutex_waiter_pi_snk = {
+    .boost = rtmutex_waiter_pi_boost,
+    .update = rtmutex_waiter_pi_update,
+};
+
+/*
+ * This must be called with lock->wait_lock held.
+ */
+static int add_waiter(struct rt_mutex *lock,
+		      struct rt_mutex_waiter *waiter,
+		      unsigned long *flags)
+{
+	int has_waiters = rt_mutex_has_waiters(lock);
+
+	waiter->task = current;
+	waiter->lock = lock;
+	waiter->pi.prio = current->prio;
+	plist_node_init(&waiter->list_entry, waiter->pi.prio);
+	plist_add(&waiter->list_entry, &lock->wait_list);
+	waiter->pi.snk = rtmutex_waiter_pi_snk;
 
 	/*
-	 * The owner can't disappear while holding a lock,
-	 * so the owner struct is protected by wait_lock.
-	 * Gets dropped in rt_mutex_adjust_prio_chain()!
+	 * Link the waiter object to the task so that we can adjust our
+	 * position on the prio list if the priority is changed. Note
+	 * that if the priority races between the time we recorded it
+	 * above and the time it is set here, we will correct the race
+	 * when we task_pi_update(current) below.  Otherwise the the
+	 * update is a no-op
 	 */
-	get_task_struct(owner);
+	pi_add_sink(&current->pi.node, &waiter->pi.snk,
+		    PI_FLAG_DEFER_UPDATE);
 
-	spin_unlock_irqrestore(&lock->wait_lock, flags);
+	/*
+	 * Link the lock object to the waiter so that we can form a chain
+	 * to the owner
+	 */
+	pi_add_sink(&current->pi.node, &lock->pi.node.snk,
+		    PI_FLAG_DEFER_UPDATE);
 
-	res = rt_mutex_adjust_prio_chain(owner, detect_deadlock, lock, waiter,
-					 current, 0);
+	/*
+	 * If we previously had no waiters, we are transitioning to
+	 * a mode where we need to boost the owner
+	 */
+	if (!has_waiters) {
+		struct task_struct *owner = rt_mutex_owner(lock);
+		rtmutex_pi_owner(lock, owner, 1);
+	}
 
-	spin_lock_irq(&lock->wait_lock);
+	spin_unlock_irqrestore(&lock->wait_lock, *flags);
+	task_pi_update(current, 0);
+	spin_lock_irqsave(&lock->wait_lock, *flags);
+
+	return 0;
+}
+
+/*
+ * Remove a waiter from a lock
+ *
+ * Must be called with lock->wait_lock held
+ */
+static void remove_waiter(struct rt_mutex *lock,
+			  struct rt_mutex_waiter *waiter)
+{
+	struct task_struct *p = waiter->task;
+
+	plist_del(&waiter->list_entry, &lock->wait_list);
+	waiter->task = NULL;
+
+	/*
+	 * We can stop boosting the owner if there are no more waiters
+	 */
+	if (!rt_mutex_has_waiters(lock)) {
+		struct task_struct *owner = rt_mutex_owner(lock);
+		rtmutex_pi_owner(lock, owner, 0);
+	}
 
-	return res;
+	/*
+	 * Unlink the lock object from the waiter
+	 */
+	pi_del_sink(&p->pi.node, &lock->pi.node.snk, PI_FLAG_DEFER_UPDATE);
+
+	/*
+	 * Unlink the waiter object from the task.  Note that we
+	 * technically do not need an update for "p" because the
+	 * .deboost will be processed synchronous to this call
+	 * since there is no .deboost handler registered for
+	 * the waiter sink
+	 */
+	pi_del_sink(&p->pi.node, &waiter->pi.snk, PI_FLAG_DEFER_UPDATE);
 }
 
 /*
@@ -566,24 +455,10 @@ static int task_blocks_on_rt_mutex(struct rt_mutex *lock,
  */
 static void wakeup_next_waiter(struct rt_mutex *lock, int savestate)
 {
-	struct rt_mutex_waiter *waiter;
-	struct task_struct *pendowner;
-	struct rt_mutex_waiter *next;
-
-	spin_lock(&current->pi_lock);
+	struct rt_mutex_waiter *waiter = rt_mutex_top_waiter(lock);
+	struct task_struct *pendowner = waiter->task;
 
-	waiter = rt_mutex_top_waiter(lock);
-	plist_del(&waiter->list_entry, &lock->wait_list);
-
-	/*
-	 * Remove it from current->pi_waiters. We do not adjust a
-	 * possible priority boost right now. We execute wakeup in the
-	 * boosted mode and go back to normal after releasing
-	 * lock->wait_lock.
-	 */
-	plist_del(&waiter->pi_list_entry, &current->pi_waiters);
-	pendowner = waiter->task;
-	waiter->task = NULL;
+	remove_waiter(lock, waiter);
 
 	/*
 	 * Do the wakeup before the ownership change to give any spinning
@@ -621,113 +496,6 @@ static void wakeup_next_waiter(struct rt_mutex *lock, int savestate)
 	}
 
 	rt_mutex_set_owner(lock, pendowner, RT_MUTEX_OWNER_PENDING);
-
-	spin_unlock(&current->pi_lock);
-
-	/*
-	 * Clear the pi_blocked_on variable and enqueue a possible
-	 * waiter into the pi_waiters list of the pending owner. This
-	 * prevents that in case the pending owner gets unboosted a
-	 * waiter with higher priority than pending-owner->normal_prio
-	 * is blocked on the unboosted (pending) owner.
-	 */
-
-	if (rt_mutex_has_waiters(lock))
-		next = rt_mutex_top_waiter(lock);
-	else
-		next = NULL;
-
-	spin_lock(&pendowner->pi_lock);
-
-	WARN_ON(!pendowner->pi_blocked_on);
-	WARN_ON(pendowner->pi_blocked_on != waiter);
-	WARN_ON(pendowner->pi_blocked_on->lock != lock);
-
-	pendowner->pi_blocked_on = NULL;
-
-	if (next)
-		plist_add(&next->pi_list_entry, &pendowner->pi_waiters);
-
-	spin_unlock(&pendowner->pi_lock);
-}
-
-/*
- * Remove a waiter from a lock
- *
- * Must be called with lock->wait_lock held
- */
-static void remove_waiter(struct rt_mutex *lock,
-			  struct rt_mutex_waiter *waiter,
-			  unsigned long flags)
-{
-	int first = (waiter == rt_mutex_top_waiter(lock));
-	struct task_struct *owner = rt_mutex_owner(lock);
-	int chain_walk = 0;
-
-	spin_lock(&current->pi_lock);
-	plist_del(&waiter->list_entry, &lock->wait_list);
-	waiter->task = NULL;
-	current->pi_blocked_on = NULL;
-	spin_unlock(&current->pi_lock);
-
-	if (first && owner != current && !task_is_reader(owner)) {
-
-		spin_lock(&owner->pi_lock);
-
-		plist_del(&waiter->pi_list_entry, &owner->pi_waiters);
-
-		if (rt_mutex_has_waiters(lock)) {
-			struct rt_mutex_waiter *next;
-
-			next = rt_mutex_top_waiter(lock);
-			plist_add(&next->pi_list_entry, &owner->pi_waiters);
-		}
-		__rt_mutex_adjust_prio(owner);
-
-		if (owner->pi_blocked_on)
-			chain_walk = 1;
-
-		spin_unlock(&owner->pi_lock);
-	}
-
-	WARN_ON(!plist_node_empty(&waiter->pi_list_entry));
-
-	if (!chain_walk)
-		return;
-
-	/* gets dropped in rt_mutex_adjust_prio_chain()! */
-	get_task_struct(owner);
-
-	spin_unlock_irqrestore(&lock->wait_lock, flags);
-
-	rt_mutex_adjust_prio_chain(owner, 0, lock, NULL, current, 0);
-
-	spin_lock_irq(&lock->wait_lock);
-}
-
-/*
- * Recheck the pi chain, in case we got a priority setting
- *
- * Called from sched_setscheduler
- */
-void rt_mutex_adjust_pi(struct task_struct *task)
-{
-	struct rt_mutex_waiter *waiter;
-	unsigned long flags;
-
-	spin_lock_irqsave(&task->pi_lock, flags);
-
-	waiter = task->pi_blocked_on;
-	if (!waiter || waiter->list_entry.prio == task->prio) {
-		spin_unlock_irqrestore(&task->pi_lock, flags);
-		return;
-	}
-
-	/* gets dropped in rt_mutex_adjust_prio_chain()! */
-	get_task_struct(task);
-	spin_unlock_irqrestore(&task->pi_lock, flags);
-
-	rt_mutex_adjust_prio_chain(task, 0, NULL, NULL, task, 0);
 }
 
 /*
@@ -869,7 +637,7 @@ rt_spin_lock_slowlock(struct rt_mutex *lock)
 		 * but the lock got stolen by an higher prio task.
 		 */
 		if (!waiter.task) {
-			task_blocks_on_rt_mutex(lock, &waiter, 0, flags);
+			add_waiter(lock, &waiter, &flags);
 			/* Wakeup during boost ? */
 			if (unlikely(!waiter.task))
 				continue;
@@ -917,7 +685,7 @@ rt_spin_lock_slowlock(struct rt_mutex *lock)
 	 * can end up with a non-NULL waiter.task:
 	 */
 	if (unlikely(waiter.task))
-		remove_waiter(lock, &waiter, flags);
+		remove_waiter(lock, &waiter);
 	/*
 	 * try_to_take_rt_mutex() sets the waiter bit
 	 * unconditionally. We might have to fix that up:
@@ -927,6 +695,9 @@ rt_spin_lock_slowlock(struct rt_mutex *lock)
  unlock:
 	spin_unlock_irqrestore(&lock->wait_lock, flags);
 
+	/* Undo any pi boosting, if necessary */
+	task_pi_update(current, 0);
+
 	debug_rt_mutex_free_waiter(&waiter);
 }
 
@@ -954,8 +725,8 @@ rt_spin_lock_slowunlock(struct rt_mutex *lock)
 
 	spin_unlock_irqrestore(&lock->wait_lock, flags);
 
-	/* Undo pi boosting.when necessary */
-	rt_mutex_adjust_prio(current);
+	/* Undo pi boosting when necessary */
+	task_pi_update(current, 0);
 }
 
 void __lockfunc rt_spin_lock(spinlock_t *lock)
@@ -1126,6 +897,9 @@ static inline void
 rt_rwlock_add_reader(struct reader_lock_struct *rls, struct rw_mutex *rwm)
 {
 	list_add(&rls->list, &rwm->readers);
+
+	pi_source_init(&rls->pi_src, &rwm->prio);
+	task_pi_boost(rls->task, &rls->pi_src, PI_FLAG_DEFER_UPDATE);
 }
 
 /*
@@ -1249,21 +1023,7 @@ static int try_to_take_rw_read(struct rw_mutex *rwm, int mtx)
 				waiter = rt_mutex_top_waiter(mutex);
 				if (!lock_is_stealable(waiter->task, mode))
 					return 0;
-				/*
-				 * The pending reader has PI waiters,
-				 * but we are taking the lock.
-				 * Remove the waiters from the pending owner.
-				 */
-				spin_lock(&mtxowner->pi_lock);
-				plist_del(&waiter->pi_list_entry, &mtxowner->pi_waiters);
-				spin_unlock(&mtxowner->pi_lock);
 			}
-		} else if (rt_mutex_has_waiters(mutex)) {
-			/* Readers do things differently with respect to PI */
-			waiter = rt_mutex_top_waiter(mutex);
-			spin_lock(&current->pi_lock);
-			plist_del(&waiter->pi_list_entry, &current->pi_waiters);
-			spin_unlock(&current->pi_lock);
 		}
 		/* Readers never own the mutex */
 		rt_mutex_set_owner(mutex, RT_RW_READER, 0);
@@ -1275,7 +1035,7 @@ static int try_to_take_rw_read(struct rw_mutex *rwm, int mtx)
 	if (incr) {
 		atomic_inc(&rwm->owners);
 		rw_check_held(rwm);
-		spin_lock(&current->pi_lock);
+		preempt_disable();
 		reader_count = current->reader_lock_count++;
 		if (likely(reader_count < MAX_RWLOCK_DEPTH)) {
 			rls = &current->owned_read_locks[reader_count];
@@ -1285,10 +1045,11 @@ static int try_to_take_rw_read(struct rw_mutex *rwm, int mtx)
 			rt_rwlock_add_reader(rls, rwm);
 		} else
 			WARN_ON_ONCE(1);
-		spin_unlock(&current->pi_lock);
+		preempt_enable();
 	}
 	rt_mutex_deadlock_account_lock(mutex, current);
 	atomic_inc(&rwm->count);
+
 	return 1;
 }
 
@@ -1378,7 +1139,7 @@ rt_read_slowlock(struct rw_mutex *rwm, int mtx)
 		 * but the lock got stolen by a higher prio task.
 		 */
 		if (!waiter.task) {
-			task_blocks_on_rt_mutex(mutex, &waiter, 0, flags);
+			add_waiter(mutex, &waiter, &flags);
 			/* Wakeup during boost ? */
 			if (unlikely(!waiter.task))
 				continue;
@@ -1417,7 +1178,7 @@ rt_read_slowlock(struct rw_mutex *rwm, int mtx)
 	}
 
 	if (unlikely(waiter.task))
-		remove_waiter(mutex, &waiter, flags);
+		remove_waiter(mutex, &waiter);
 
 	WARN_ON(rt_mutex_owner(mutex) &&
 		rt_mutex_owner(mutex) != current &&
@@ -1430,6 +1191,9 @@ rt_read_slowlock(struct rw_mutex *rwm, int mtx)
 	if (mtx && unlikely(saved_lock_depth >= 0))
 		rt_reacquire_bkl(saved_lock_depth);
 
+	/* Undo any pi boosting, if necessary */
+	task_pi_update(current, 0);
+
 	debug_rt_mutex_free_waiter(&waiter);
 }
 
@@ -1457,13 +1221,13 @@ __rt_read_fasttrylock(struct rw_mutex *rwm)
 		atomic_inc(&rwm->owners);
 		rw_check_held(rwm);
 		local_irq_save(flags);
-		spin_lock(&current->pi_lock);
 		reader_count = current->reader_lock_count++;
 		if (likely(reader_count < MAX_RWLOCK_DEPTH)) {
 			current->owned_read_locks[reader_count].lock = rwm;
 			current->owned_read_locks[reader_count].count = 1;
 		} else
 			WARN_ON_ONCE(1);
+
 		/*
 		 * If this task is no longer the sole owner of the lock
 		 * or someone is blocking, then we need to add the task
@@ -1473,16 +1237,12 @@ __rt_read_fasttrylock(struct rw_mutex *rwm)
 			struct rt_mutex *mutex = &rwm->mutex;
 			struct reader_lock_struct *rls;
 
-			/* preserve lock order, we only need wait_lock now */
-			spin_unlock(&current->pi_lock);
-
 			spin_lock(&mutex->wait_lock);
 			rls = &current->owned_read_locks[reader_count];
 			if (!rls->list.prev || list_empty(&rls->list))
-				rt_rwlock_add_reader(rlw, rwm);
+				rt_rwlock_add_reader(rls, rwm);
 			spin_unlock(&mutex->wait_lock);
-		} else
-			spin_unlock(&current->pi_lock);
+		}
 		local_irq_restore(flags);
 		return 1;
 	}
@@ -1591,7 +1351,7 @@ rt_write_slowlock(struct rw_mutex *rwm, int mtx)
 		 * but the lock got stolen by a higher prio task.
 		 */
 		if (!waiter.task) {
-			task_blocks_on_rt_mutex(mutex, &waiter, 0, flags);
+			add_waiter(mutex, &waiter, &flags);
 			/* Wakeup during boost ? */
 			if (unlikely(!waiter.task))
 				continue;
@@ -1630,7 +1390,7 @@ rt_write_slowlock(struct rw_mutex *rwm, int mtx)
 	}
 
 	if (unlikely(waiter.task))
-		remove_waiter(mutex, &waiter, flags);
+		remove_waiter(mutex, &waiter);
 
 	/* check on unlock if we have any waiters. */
 	if (rt_mutex_has_waiters(mutex))
@@ -1642,6 +1402,9 @@ rt_write_slowlock(struct rw_mutex *rwm, int mtx)
 	if (mtx && unlikely(saved_lock_depth >= 0))
 		rt_reacquire_bkl(saved_lock_depth);
 
+	/* Undo any pi boosting, if necessary */
+	task_pi_update(current, 0);
+
 	debug_rt_mutex_free_waiter(&waiter);
 
 }
@@ -1733,7 +1496,7 @@ rt_read_slowunlock(struct rw_mutex *rwm, int mtx)
 
 	for (i = current->reader_lock_count - 1; i >= 0; i--) {
 		if (current->owned_read_locks[i].lock == rwm) {
-			spin_lock(&current->pi_lock);
+			preempt_disable();
 			current->owned_read_locks[i].count--;
 			if (!current->owned_read_locks[i].count) {
 				current->reader_lock_count--;
@@ -1743,9 +1506,11 @@ rt_read_slowunlock(struct rw_mutex *rwm, int mtx)
 				WARN_ON(!rls->list.prev || list_empty(&rls->list));
 				list_del_init(&rls->list);
 				rls->lock = NULL;
+				task_pi_deboost(current, &rls->pi_src,
+						PI_FLAG_DEFER_UPDATE);
 				rw_check_held(rwm);
 			}
-			spin_unlock(&current->pi_lock);
+			preempt_enable();
 			break;
 		}
 	}
@@ -1776,7 +1541,6 @@ rt_read_slowunlock(struct rw_mutex *rwm, int mtx)
 
 	/* If no one is blocked, then clear all ownership */
 	if (!rt_mutex_has_waiters(mutex)) {
-		rwm->prio = MAX_PRIO;
 		/*
 		 * If count is not zero, we are under the limit with
 		 * no other readers.
@@ -1835,28 +1599,11 @@ rt_read_slowunlock(struct rw_mutex *rwm, int mtx)
 		rt_mutex_set_owner(mutex, RT_RW_READER, 0);
 	}
 
-	if (rt_mutex_has_waiters(mutex)) {
-		waiter = rt_mutex_top_waiter(mutex);
-		rwm->prio = waiter->task->prio;
-		/*
-		 * If readers still own this lock, then we need
-		 * to update the pi_list too. Readers have a separate
-		 * path in the PI chain.
-		 */
-		if (reader_count) {
-			spin_lock(&pendowner->pi_lock);
-			plist_del(&waiter->pi_list_entry,
-				  &pendowner->pi_waiters);
-			spin_unlock(&pendowner->pi_lock);
-		}
-	} else
-		rwm->prio = MAX_PRIO;
-
  out:
 	spin_unlock_irqrestore(&mutex->wait_lock, flags);
 
-	/* Undo pi boosting.when necessary */
-	rt_mutex_adjust_prio(current);
+	/* Undo pi boosting when necessary */
+	task_pi_update(current, 0);
 }
 
 static inline void
@@ -1874,9 +1621,9 @@ rt_read_fastunlock(struct rw_mutex *rwm,
 		int reader_count;
 		int owners;
 
-		spin_lock_irqsave(&current->pi_lock, flags);
+		local_irq_save(flags);
 		reader_count = --current->reader_lock_count;
-		spin_unlock_irqrestore(&current->pi_lock, flags);
+		local_irq_restore(flags);
 
 		rt_mutex_deadlock_account_unlock(current);
 		if (unlikely(reader_count < 0)) {
@@ -1972,17 +1719,7 @@ rt_write_slowunlock(struct rw_mutex *rwm, int mtx)
 	while (waiter && !waiter->write_lock) {
 		struct task_struct *reader = waiter->task;
 
-		spin_lock(&pendowner->pi_lock);
-		plist_del(&waiter->list_entry, &mutex->wait_list);
-
-		/* nop if not on a list */
-		plist_del(&waiter->pi_list_entry, &pendowner->pi_waiters);
-		spin_unlock(&pendowner->pi_lock);
-
-		spin_lock(&reader->pi_lock);
-		waiter->task = NULL;
-		reader->pi_blocked_on = NULL;
-		spin_unlock(&reader->pi_lock);
+		remove_waiter(mutex, waiter);
 
 		if (savestate)
 			wake_up_process_mutex(reader);
@@ -1995,32 +1732,12 @@ rt_write_slowunlock(struct rw_mutex *rwm, int mtx)
 			waiter = NULL;
 	}
 
-	/* If a writer is still pending, then update its plist. */
-	if (rt_mutex_has_waiters(mutex)) {
-		struct rt_mutex_waiter *next;
-
-		next = rt_mutex_top_waiter(mutex);
-
-		spin_lock(&pendowner->pi_lock);
-		/* delete incase we didn't go through the loop */
-		plist_del(&next->pi_list_entry, &pendowner->pi_waiters);
-
-		/* This could also be a reader (if reader_limit is set) */
-		if (next->write_lock)
-			/* add back in as top waiter */
-			plist_add(&next->pi_list_entry, &pendowner->pi_waiters);
-		spin_unlock(&pendowner->pi_lock);
-
-		rwm->prio = next->task->prio;
-	} else
-		rwm->prio = MAX_PRIO;
-
  out:
 
 	spin_unlock_irqrestore(&mutex->wait_lock, flags);
 
-	/* Undo pi boosting.when necessary */
-	rt_mutex_adjust_prio(current);
+	/* Undo pi boosting when necessary */
+	task_pi_update(current, 0);
 }
 
 static inline void
@@ -2068,7 +1785,7 @@ rt_mutex_downgrade_write(struct rw_mutex *rwm)
 	atomic_inc(&rwm->owners);
 	rw_check_held(rwm);
 
-	spin_lock(&current->pi_lock);
+	preempt_disable();
 	reader_count = current->reader_lock_count++;
 	rls = &current->owned_read_locks[reader_count];
 	if (likely(reader_count < MAX_RWLOCK_DEPTH)) {
@@ -2076,12 +1793,11 @@ rt_mutex_downgrade_write(struct rw_mutex *rwm)
 		rls->count = 1;
 	} else
 		WARN_ON_ONCE(1);
-	spin_unlock(&current->pi_lock);
+	preempt_enable();
 
 	if (!rt_mutex_has_waiters(mutex)) {
 		/* We are sole owner, we are done */
 		rwm->owner = current;
-		rwm->prio = MAX_PRIO;
 		mutex->owner = NULL;
 		spin_unlock_irqrestore(&mutex->wait_lock, flags);
 		return;
@@ -2102,17 +1818,8 @@ rt_mutex_downgrade_write(struct rw_mutex *rwm)
 	while (waiter && !waiter->write_lock) {
 		struct task_struct *reader = waiter->task;
 
-		spin_lock(&current->pi_lock);
 		plist_del(&waiter->list_entry, &mutex->wait_list);
-
-		/* nop if not on a list */
-		plist_del(&waiter->pi_list_entry, &current->pi_waiters);
-		spin_unlock(&current->pi_lock);
-
-		spin_lock(&reader->pi_lock);
 		waiter->task = NULL;
-		reader->pi_blocked_on = NULL;
-		spin_unlock(&reader->pi_lock);
 
 		/* downgrade is only for mutexes */
 		wake_up_process(reader);
@@ -2123,124 +1830,81 @@ rt_mutex_downgrade_write(struct rw_mutex *rwm)
 			waiter = NULL;
 	}
 
-	/* If a writer is still pending, then update its plist. */
-	if (rt_mutex_has_waiters(mutex)) {
-		struct rt_mutex_waiter *next;
-
-		next = rt_mutex_top_waiter(mutex);
-
-		/* setup this mutex prio for read */
-		rwm->prio = next->task->prio;
-
-		spin_lock(&current->pi_lock);
-		/* delete incase we didn't go through the loop */
-		plist_del(&next->pi_list_entry, &current->pi_waiters);
-		spin_unlock(&current->pi_lock);
-		/* No need to add back since readers don't have PI waiters */
-	} else
-		rwm->prio = MAX_PRIO;
-
 	rt_mutex_set_owner(mutex, RT_RW_READER, 0);
 
 	spin_unlock_irqrestore(&mutex->wait_lock, flags);
-
-	/*
-	 * Undo pi boosting when necessary.
-	 * If one of the awoken readers boosted us, we don't want to keep
-	 * that priority.
-	 */
-	rt_mutex_adjust_prio(current);
-}
-
-void rt_mutex_rwsem_init(struct rw_mutex *rwm, const char *name)
-{
-	struct rt_mutex *mutex = &rwm->mutex;
-
-	rwm->owner = NULL;
-	atomic_set(&rwm->count, 0);
-	atomic_set(&rwm->owners, 0);
-	rwm->prio = MAX_PRIO;
-	INIT_LIST_HEAD(&rwm->readers);
-
-	__rt_mutex_init(mutex, name);
 }
 
-static int rt_mutex_get_readers_prio(struct task_struct *task, int prio)
+/*
+ * These callbacks are invoked whenever a rwlock has changed priority.
+ * Since rwlocks maintain their own lists of reader dependencies, we
+ * may need to reboost any readers manually
+ */
+static inline int rt_rwlock_pi_boost(struct pi_sink *snk,
+				     struct pi_source *src,
+				     unsigned int flags)
 {
-	struct reader_lock_struct *rls;
 	struct rw_mutex *rwm;
-	int lock_prio;
-	int i;
 
-	for (i = 0; i < task->reader_lock_count; i++) {
-		rls = &task->owned_read_locks[i];
-		rwm = rls->lock;
-		if (rwm) {
-			lock_prio = rwm->prio;
-			if (prio > lock_prio)
-				prio = lock_prio;
-		}
-	}
+	rwm = container_of(snk, struct rw_mutex, pi_snk);
 
-	return prio;
+	/*
+	 * We dont need to take any locks here because the
+	 * lock->pi.node interlock is already guaranteeing mutual
+	 * exclusion.
+	 */
+	rwm->prio = *src->prio;
+
+	return 0;
 }
 
-static int rt_mutex_adjust_readers(struct rt_mutex *orig_lock,
-				   struct rt_mutex_waiter *orig_waiter,
-				   struct task_struct *top_task,
-				   struct rt_mutex *lock,
-				   int recursion_depth)
+static inline int rt_rwlock_pi_update(struct pi_sink *snk,
+				     unsigned int flags)
 {
+	struct rw_mutex *rwm;
+	struct rt_mutex *mutex;
 	struct reader_lock_struct *rls;
-	struct rt_mutex_waiter *waiter;
-	struct task_struct *task;
-	struct rw_mutex *rwm = container_of(lock, struct rw_mutex, mutex);
+	unsigned long iflags;
 
-	if (rt_mutex_has_waiters(lock)) {
-		waiter = rt_mutex_top_waiter(lock);
-		/*
-		 * Do we need to grab the task->pi_lock?
-		 * Really, we are only reading it. If it
-		 * changes, then that should follow this chain
-		 * too.
-		 */
-		rwm->prio = waiter->task->prio;
-	} else
-		rwm->prio = MAX_PRIO;
+	rwm = container_of(snk, struct rw_mutex, pi_snk);
+	mutex = &rwm->mutex;
 
-	if (recursion_depth >= MAX_RWLOCK_DEPTH) {
-		WARN_ON(1);
-		return 1;
-	}
+	spin_lock_irqsave(&mutex->wait_lock, iflags);
 
-	list_for_each_entry(rls, &rwm->readers, list) {
-		task = rls->task;
-		get_task_struct(task);
-		/*
-		 * rt_mutex_adjust_prio_chain will do
-		 * the put_task_struct
-		 */
-		rt_mutex_adjust_prio_chain(task, 0, orig_lock,
-					   orig_waiter, top_task,
-					   recursion_depth+1);
-	}
+	list_for_each_entry(rls, &rwm->readers, list)
+		task_pi_boost(rls->task, &rls->pi_src, 0);
+
+	spin_unlock_irqrestore(&mutex->wait_lock, iflags);
 
 	return 0;
 }
-#else
-static int rt_mutex_adjust_readers(struct rt_mutex *orig_lock,
-				   struct rt_mutex_waiter *orig_waiter,
-				   struct task_struct *top_task,
-				   struct rt_mutex *lock,
-				   int recursion_depth)
-{
-	return 0;
-}
 
-static int rt_mutex_get_readers_prio(struct task_struct *task, int prio)
+static struct pi_sink rt_rwlock_pi_snk = {
+    .boost = rt_rwlock_pi_boost,
+    .update = rt_rwlock_pi_update,
+};
+
+void rt_mutex_rwsem_init(struct rw_mutex *rwm, const char *name)
 {
-	return prio;
+	struct rt_mutex *mutex = &rwm->mutex;
+
+	rwm->owner = NULL;
+	atomic_set(&rwm->count, 0);
+	atomic_set(&rwm->owners, 0);
+	rwm->prio = MAX_PRIO;
+	INIT_LIST_HEAD(&rwm->readers);
+
+	__rt_mutex_init(mutex, name);
+
+	/*
+	 * Link the rwlock object to the mutex so we get notified
+	 * of any priority changes in the future
+	 */
+	rwm->pi_snk = rt_rwlock_pi_snk;
+	pi_add_sink(&mutex->pi.node, &rwm->pi_snk,
+		    PI_FLAG_DEFER_UPDATE | PI_FLAG_ALREADY_BOOSTED);
 }
+
 #endif /* CONFIG_PREEMPT_RT */
 
 static inline int rt_release_bkl(struct rt_mutex *lock, unsigned long flags)
@@ -2335,8 +1999,7 @@ rt_mutex_slowlock(struct rt_mutex *lock, int state,
 		 * but the lock got stolen by a higher prio task.
 		 */
 		if (!waiter.task) {
-			ret = task_blocks_on_rt_mutex(lock, &waiter,
-						      detect_deadlock, flags);
+			ret = add_waiter(lock, &waiter, &flags);
 			/*
 			 * If we got woken up by the owner then start loop
 			 * all over without going into schedule to try
@@ -2374,7 +2037,7 @@ rt_mutex_slowlock(struct rt_mutex *lock, int state,
 	set_current_state(TASK_RUNNING);
 
 	if (unlikely(waiter.task))
-		remove_waiter(lock, &waiter, flags);
+		remove_waiter(lock, &waiter);
 
 	/*
 	 * try_to_take_rt_mutex() sets the waiter bit
@@ -2388,13 +2051,8 @@ rt_mutex_slowlock(struct rt_mutex *lock, int state,
 	if (unlikely(timeout))
 		hrtimer_cancel(&timeout->timer);
 
-	/*
-	 * Readjust priority, when we did not get the lock. We might
-	 * have been the pending owner and boosted. Since we did not
-	 * take the lock, the PI boost has to go.
-	 */
-	if (unlikely(ret))
-		rt_mutex_adjust_prio(current);
+	/* Undo any pi boosting, if necessary */
+	task_pi_update(current, 0);
 
 	/* Must we reaquire the BKL? */
 	if (unlikely(saved_lock_depth >= 0))
@@ -2457,8 +2115,8 @@ rt_mutex_slowunlock(struct rt_mutex *lock)
 
 	spin_unlock_irqrestore(&lock->wait_lock, flags);
 
-	/* Undo pi boosting if necessary: */
-	rt_mutex_adjust_prio(current);
+	/* Undo pi boosting when necessary */
+	task_pi_update(current, 0);
 }
 
 /*
@@ -2654,6 +2312,8 @@ void __rt_mutex_init(struct rt_mutex *lock, const char *name)
 	spin_lock_init(&lock->wait_lock);
 	plist_head_init(&lock->wait_list, &lock->wait_lock);
 
+	init_pi(lock);
+
 	debug_rt_mutex_init(lock, name);
 }
 EXPORT_SYMBOL_GPL(__rt_mutex_init);
diff --git a/kernel/rtmutex_common.h b/kernel/rtmutex_common.h
index 70df5f5..7bf32d0 100644
--- a/kernel/rtmutex_common.h
+++ b/kernel/rtmutex_common.h
@@ -14,6 +14,7 @@
 
 #include <linux/rtmutex.h>
 #include <linux/rt_lock.h>
+#include <linux/pi.h>
 
 /*
  * The rtmutex in kernel tester is independent of rtmutex debugging. We
@@ -48,10 +49,13 @@ extern void schedule_rt_mutex_test(struct rt_mutex *lock);
  */
 struct rt_mutex_waiter {
 	struct plist_node	list_entry;
-	struct plist_node	pi_list_entry;
 	struct task_struct	*task;
 	struct rt_mutex		*lock;
 	int			write_lock;
+	struct {
+		struct pi_sink   snk;
+		int              prio;
+	} pi;
 #ifdef CONFIG_DEBUG_RT_MUTEXES
 	unsigned long		ip;
 	struct pid		*deadlock_task_pid;
@@ -79,18 +83,6 @@ rt_mutex_top_waiter(struct rt_mutex *lock)
 	return w;
 }
 
-static inline int task_has_pi_waiters(struct task_struct *p)
-{
-	return !plist_head_empty(&p->pi_waiters);
-}
-
-static inline struct rt_mutex_waiter *
-task_top_pi_waiter(struct task_struct *p)
-{
-	return plist_first_entry(&p->pi_waiters, struct rt_mutex_waiter,
-				  pi_list_entry);
-}
-
 /*
  * lock->owner state tracking:
  */
diff --git a/kernel/rwlock_torture.c b/kernel/rwlock_torture.c
index 2820815..689a0d0 100644
--- a/kernel/rwlock_torture.c
+++ b/kernel/rwlock_torture.c
@@ -682,37 +682,7 @@ static int __init mutex_stress_init(void)
 
 			print_owned_read_locks(tsks[i]);
 
-			if (tsks[i]->pi_blocked_on) {
-				w = (void *)tsks[i]->pi_blocked_on;
-				mtx = w->lock;
-				spin_unlock_irq(&tsks[i]->pi_lock);
-				spin_lock_irq(&mtx->wait_lock);
-				spin_lock(&tsks[i]->pi_lock);
-				own = (unsigned long)mtx->owner & ~3UL;
-				oops_in_progress++;
-				printk("%s:%d is blocked on ",
-				       tsks[i]->comm, tsks[i]->pid);
-				__print_symbol("%s", (unsigned long)mtx);
-				if (own == 0x100)
-					printk(" owner is READER\n");
-				else if (!(own & ~300))
-					printk(" owner is ILLEGAL!!\n");
-				else if (!own)
-					printk(" has no owner!\n");
-				else {
-					struct task_struct *owner = (void*)own;
-
-					printk(" owner is %s:%d\n",
-					       owner->comm, owner->pid);
-				}
-				oops_in_progress--;
-
-				spin_unlock(&tsks[i]->pi_lock);
-				spin_unlock_irq(&mtx->wait_lock);
-			} else {
-				print_owned_read_locks(tsks[i]);
-				spin_unlock_irq(&tsks[i]->pi_lock);
-			}
+			spin_unlock_irq(&tsks[i]->pi_lock);
 		}
 	}
 #endif
diff --git a/kernel/sched.c b/kernel/sched.c
index 729139d..a373250 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -2413,12 +2413,6 @@ task_pi_init(struct task_struct *p)
 	pi_source_init(&p->pi.src, &p->normal_prio);
 	task_pi_boost(p, &p->pi.src, PI_FLAG_DEFER_UPDATE);
 
-#ifdef CONFIG_RT_MUTEXES
-	p->rtmutex_prio = MAX_PRIO;
-	pi_source_init(&p->rtmutex_prio_src, &p->rtmutex_prio);
-	task_pi_boost(p, &p->rtmutex_prio_src, PI_FLAG_DEFER_UPDATE);
-#endif
-
 	/*
 	 * We add our own task as a dependency of ourselves so that
 	 * we get boost-notifications (via task_pi_boost_cb) whenever
@@ -5029,7 +5023,6 @@ task_pi_update_cb(struct pi_sink *snk, unsigned int flags)
 	 */
 	if (unlikely(p == rq->idle)) {
 		WARN_ON(p != rq->curr);
-		WARN_ON(p->pi_blocked_on);
 		goto out_unlock;
 	}
 
@@ -5360,7 +5353,6 @@ recheck:
 	spin_unlock_irqrestore(&p->pi_lock, flags);
 
 	task_pi_update(p, 0);
-	rt_mutex_adjust_pi(p);
 
 	return 0;
 }
@@ -8494,10 +8486,6 @@ void __init sched_init(void)
 
 	task_pi_init(&init_task);
 
-#ifdef CONFIG_RT_MUTEXES
-	plist_head_init(&init_task.pi_waiters, &init_task.pi_lock);
-#endif
-
 	/*
 	 * The boot idle thread does lazy MMU switching as well:
 	 */

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/

Powered by blists - more mailing lists