Merge branch 'futexes-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip

* 'futexes-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip:
  futex: fix restart in wait_requeue_pi
  futex: fix restart for early wakeup in futex_wait_requeue_pi()
  futex: cleanup error exit
  futex: remove the wait queue
  futex: add requeue-pi documentation
  futex: remove FUTEX_REQUEUE_PI (non CMP)
  futex: fix futex_wait_setup key handling
  sparc64: extend TI_RESTART_BLOCK space by 8 bytes
  futex: fixup unlocked requeue pi case
  futex: add requeue_pi functionality
  futex: split out futex value validation code
  futex: distangle futex_requeue()
  futex: add FUTEX_HAS_TIMEOUT flag to restart.futex.flags
  rt_mutex: add proxy lock routines
  futex: split out fixup owner logic from futex_lock_pi()
  futex: split out atomic logic from futex_lock_pi()
  futex: add helper to find the top prio waiter of a futex
  futex: separate futex_wait_queue_me() logic from futex_wait()

7 files changed, 1225 insertions, 355 deletions

diff --git a/Documentation/futex-requeue-pi.txt b/Documentation/futex-requeue-pi.txt
new file mode 100644
index 00000000000..9dc1ff4fd53
--- /dev/null
+++ b/Documentation/futex-requeue-pi.txt
@@ -0,0 +1,131 @@
+Futex Requeue PI
+----------------
+
+Requeueing of tasks from a non-PI futex to a PI futex requires
+special handling in order to ensure the underlying rt_mutex is never
+left without an owner if it has waiters; doing so would break the PI
+boosting logic [see rt-mutex-desgin.txt] For the purposes of
+brevity, this action will be referred to as "requeue_pi" throughout
+this document.  Priority inheritance is abbreviated throughout as
+"PI".
+
+Motivation
+----------
+
+Without requeue_pi, the glibc implementation of
+pthread_cond_broadcast() must resort to waking all the tasks waiting
+on a pthread_condvar and letting them try to sort out which task
+gets to run first in classic thundering-herd formation.  An ideal
+implementation would wake the highest-priority waiter, and leave the
+rest to the natural wakeup inherent in unlocking the mutex
+associated with the condvar.
+
+Consider the simplified glibc calls:
+
+/* caller must lock mutex */
+pthread_cond_wait(cond, mutex)
+{
+	lock(cond->__data.__lock);
+	unlock(mutex);
+	do {
+	   unlock(cond->__data.__lock);
+	   futex_wait(cond->__data.__futex);
+	   lock(cond->__data.__lock);
+	} while(...)
+	unlock(cond->__data.__lock);
+	lock(mutex);
+}
+
+pthread_cond_broadcast(cond)
+{
+	lock(cond->__data.__lock);
+	unlock(cond->__data.__lock);
+	futex_requeue(cond->data.__futex, cond->mutex);
+}
+
+Once pthread_cond_broadcast() requeues the tasks, the cond->mutex
+has waiters. Note that pthread_cond_wait() attempts to lock the
+mutex only after it has returned to user space.  This will leave the
+underlying rt_mutex with waiters, and no owner, breaking the
+previously mentioned PI-boosting algorithms.
+
+In order to support PI-aware pthread_condvar's, the kernel needs to
+be able to requeue tasks to PI futexes.  This support implies that
+upon a successful futex_wait system call, the caller would return to
+user space already holding the PI futex.  The glibc implementation
+would be modified as follows:
+
+
+/* caller must lock mutex */
+pthread_cond_wait_pi(cond, mutex)
+{
+	lock(cond->__data.__lock);
+	unlock(mutex);
+	do {
+	   unlock(cond->__data.__lock);
+	   futex_wait_requeue_pi(cond->__data.__futex);
+	   lock(cond->__data.__lock);
+	} while(...)
+	unlock(cond->__data.__lock);
+        /* the kernel acquired the the mutex for us */
+}
+
+pthread_cond_broadcast_pi(cond)
+{
+	lock(cond->__data.__lock);
+	unlock(cond->__data.__lock);
+	futex_requeue_pi(cond->data.__futex, cond->mutex);
+}
+
+The actual glibc implementation will likely test for PI and make the
+necessary changes inside the existing calls rather than creating new
+calls for the PI cases.  Similar changes are needed for
+pthread_cond_timedwait() and pthread_cond_signal().
+
+Implementation
+--------------
+
+In order to ensure the rt_mutex has an owner if it has waiters, it
+is necessary for both the requeue code, as well as the waiting code,
+to be able to acquire the rt_mutex before returning to user space.
+The requeue code cannot simply wake the waiter and leave it to
+acquire the rt_mutex as it would open a race window between the
+requeue call returning to user space and the waiter waking and
+starting to run.  This is especially true in the uncontended case.
+
+The solution involves two new rt_mutex helper routines,
+rt_mutex_start_proxy_lock() and rt_mutex_finish_proxy_lock(), which
+allow the requeue code to acquire an uncontended rt_mutex on behalf
+of the waiter and to enqueue the waiter on a contended rt_mutex.
+Two new system calls provide the kernel<->user interface to
+requeue_pi: FUTEX_WAIT_REQUEUE_PI and FUTEX_REQUEUE_CMP_PI.
+
+FUTEX_WAIT_REQUEUE_PI is called by the waiter (pthread_cond_wait()
+and pthread_cond_timedwait()) to block on the initial futex and wait
+to be requeued to a PI-aware futex.  The implementation is the
+result of a high-speed collision between futex_wait() and
+futex_lock_pi(), with some extra logic to check for the additional
+wake-up scenarios.
+
+FUTEX_REQUEUE_CMP_PI is called by the waker
+(pthread_cond_broadcast() and pthread_cond_signal()) to requeue and
+possibly wake the waiting tasks. Internally, this system call is
+still handled by futex_requeue (by passing requeue_pi=1).  Before
+requeueing, futex_requeue() attempts to acquire the requeue target
+PI futex on behalf of the top waiter.  If it can, this waiter is
+woken.  futex_requeue() then proceeds to requeue the remaining
+nr_wake+nr_requeue tasks to the PI futex, calling
+rt_mutex_start_proxy_lock() prior to each requeue to prepare the
+task as a waiter on the underlying rt_mutex.  It is possible that
+the lock can be acquired at this stage as well, if so, the next
+waiter is woken to finish the acquisition of the lock.
+
+FUTEX_REQUEUE_PI accepts nr_wake and nr_requeue as arguments, but
+their sum is all that really matters.  futex_requeue() will wake or
+requeue up to nr_wake + nr_requeue tasks.  It will wake only as many
+tasks as it can acquire the lock for, which in the majority of cases
+should be 0 as good programming practice dictates that the caller of
+either pthread_cond_broadcast() or pthread_cond_signal() acquire the
+mutex prior to making the call. FUTEX_REQUEUE_PI requires that
+nr_wake=1.  nr_requeue should be INT_MAX for broadcast and 0 for
+signal.
diff --git a/arch/sparc/include/asm/thread_info_64.h b/arch/sparc/include/asm/thread_info_64.h
index 639ac805448..65865726b28 100644
--- a/arch/sparc/include/asm/thread_info_64.h
+++ b/arch/sparc/include/asm/thread_info_64.h
@@ -102,8 +102,8 @@ struct thread_info {
 #define TI_KERN_CNTD1	0x00000488
 #define TI_PCR		0x00000490
 #define TI_RESTART_BLOCK 0x00000498
-#define TI_KUNA_REGS	0x000004c0
-#define TI_KUNA_INSN	0x000004c8
+#define TI_KUNA_REGS	0x000004c8
+#define TI_KUNA_INSN	0x000004d0
 #define TI_FPREGS	0x00000500
 
 /* We embed this in the uppermost byte of thread_info->flags */
diff --git a/include/linux/futex.h b/include/linux/futex.h
index 3bf5bb5a34f..34956c8fdeb 100644
--- a/include/linux/futex.h
+++ b/include/linux/futex.h
@@ -23,6 +23,8 @@ union ktime;
 #define FUTEX_TRYLOCK_PI	8
 #define FUTEX_WAIT_BITSET	9
 #define FUTEX_WAKE_BITSET	10
+#define FUTEX_WAIT_REQUEUE_PI	11
+#define FUTEX_CMP_REQUEUE_PI	12
 
 #define FUTEX_PRIVATE_FLAG	128
 #define FUTEX_CLOCK_REALTIME	256
@@ -38,6 +40,10 @@ union ktime;
 #define FUTEX_TRYLOCK_PI_PRIVATE (FUTEX_TRYLOCK_PI | FUTEX_PRIVATE_FLAG)
 #define FUTEX_WAIT_BITSET_PRIVATE	(FUTEX_WAIT_BITS | FUTEX_PRIVATE_FLAG)
 #define FUTEX_WAKE_BITSET_PRIVATE	(FUTEX_WAKE_BITS | FUTEX_PRIVATE_FLAG)
+#define FUTEX_WAIT_REQUEUE_PI_PRIVATE	(FUTEX_WAIT_REQUEUE_PI | \
+					 FUTEX_PRIVATE_FLAG)
+#define FUTEX_CMP_REQUEUE_PI_PRIVATE	(FUTEX_CMP_REQUEUE_PI | \
+					 FUTEX_PRIVATE_FLAG)
 
 /*
  * Support for robust futexes: the kernel cleans up held futexes at
diff --git a/include/linux/thread_info.h b/include/linux/thread_info.h
index e6b820f8b56..a8cc4e13434 100644
--- a/include/linux/thread_info.h
+++ b/include/linux/thread_info.h
@@ -21,13 +21,14 @@ struct restart_block {
 		struct {
 			unsigned long arg0, arg1, arg2, arg3;
 		};
-		/* For futex_wait */
+		/* For futex_wait and futex_wait_requeue_pi */
 		struct {
 			u32 *uaddr;
 			u32 val;
 			u32 flags;
 			u32 bitset;
 			u64 time;
+			u32 *uaddr2;
 		} futex;
 		/* For nanosleep */
 		struct {
diff --git a/kernel/futex.c b/kernel/futex.c
index d546b2d53a6..80b5ce71659 100644
--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -19,6 +19,10 @@
  *  PRIVATE futexes by Eric Dumazet
  *  Copyright (C) 2007 Eric Dumazet <dada1@cosmosbay.com>
  *
+ *  Requeue-PI support by Darren Hart <dvhltc@us.ibm.com>
+ *  Copyright (C) IBM Corporation, 2009
+ *  Thanks to Thomas Gleixner for conceptual design and careful reviews.
+ *
  *  Thanks to Ben LaHaise for yelling "hashed waitqueues" loudly
  *  enough at me, Linus for the original (flawed) idea, Matthew
  *  Kirkwood for proof-of-concept implementation.
@@ -96,8 +100,8 @@ struct futex_pi_state {
  */
 struct futex_q {
 	struct plist_node list;
-	/* There can only be a single waiter */
-	wait_queue_head_t waiter;
+	/* Waiter reference */
+	struct task_struct *task;
 
 	/* Which hash list lock to use: */
 	spinlock_t *lock_ptr;
@@ -107,7 +111,9 @@ struct futex_q {
 
 	/* Optional priority inheritance state: */
 	struct futex_pi_state *pi_state;
-	struct task_struct *task;
+
+	/* rt_waiter storage for requeue_pi: */
+	struct rt_mutex_waiter *rt_waiter;
 
 	/* Bitset for the optional bitmasked wakeup */
 	u32 bitset;
@@ -278,6 +284,25 @@ void put_futex_key(int fshared, union futex_key *key)
 	drop_futex_key_refs(key);
 }
 
+/**
+ * futex_top_waiter() - Return the highest priority waiter on a futex
+ * @hb:     the hash bucket the futex_q's reside in
+ * @key:    the futex key (to distinguish it from other futex futex_q's)
+ *
+ * Must be called with the hb lock held.
+ */
+static struct futex_q *futex_top_waiter(struct futex_hash_bucket *hb,
+					union futex_key *key)
+{
+	struct futex_q *this;
+
+	plist_for_each_entry(this, &hb->chain, list) {
+		if (match_futex(&this->key, key))
+			return this;
+	}
+	return NULL;
+}
+
 static u32 cmpxchg_futex_value_locked(u32 __user *uaddr, u32 uval, u32 newval)
 {
 	u32 curval;
@@ -539,28 +564,160 @@ lookup_pi_state(u32 uval, struct futex_hash_bucket *hb,
 	return 0;
 }
 
+/**
+ * futex_lock_pi_atomic() - atomic work required to acquire a pi aware futex
+ * @uaddr:		the pi futex user address
+ * @hb:			the pi futex hash bucket
+ * @key:		the futex key associated with uaddr and hb
+ * @ps:			the pi_state pointer where we store the result of the
+ *			lookup
+ * @task:		the task to perform the atomic lock work for.  This will
+ *			be "current" except in the case of requeue pi.
+ * @set_waiters:	force setting the FUTEX_WAITERS bit (1) or not (0)
+ *
+ * Returns:
+ *  0 - ready to wait
+ *  1 - acquired the lock
+ * <0 - error
+ *
+ * The hb->lock and futex_key refs shall be held by the caller.
+ */
+static int futex_lock_pi_atomic(u32 __user *uaddr, struct futex_hash_bucket *hb,
+				union futex_key *key,
+				struct futex_pi_state **ps,
+				struct task_struct *task, int set_waiters)
+{
+	int lock_taken, ret, ownerdied = 0;
+	u32 uval, newval, curval;
+
+retry:
+	ret = lock_taken = 0;
+
+	/*
+	 * To avoid races, we attempt to take the lock here again
+	 * (by doing a 0 -> TID atomic cmpxchg), while holding all
+	 * the locks. It will most likely not succeed.
+	 */
+	newval = task_pid_vnr(task);
+	if (set_waiters)
+		newval |= FUTEX_WAITERS;
+
+	curval = cmpxchg_futex_value_locked(uaddr, 0, newval);
+
+	if (unlikely(curval == -EFAULT))
+		return -EFAULT;
+
+	/*
+	 * Detect deadlocks.
+	 */
+	if ((unlikely((curval & FUTEX_TID_MASK) == task_pid_vnr(task))))
+		return -EDEADLK;
+
+	/*
+	 * Surprise - we got the lock. Just return to userspace:
+	 */
+	if (unlikely(!curval))
+		return 1;
+
+	uval = curval;
+
+	/*
+	 * Set the FUTEX_WAITERS flag, so the owner will know it has someone
+	 * to wake at the next unlock.
+	 */
+	newval = curval | FUTEX_WAITERS;
+
+	/*
+	 * There are two cases, where a futex might have no owner (the
+	 * owner TID is 0): OWNER_DIED. We take over the futex in this
+	 * case. We also do an unconditional take over, when the owner
+	 * of the futex died.
+	 *
+	 * This is safe as we are protected by the hash bucket lock !
+	 */
+	if (unlikely(ownerdied || !(curval & FUTEX_TID_MASK))) {
+		/* Keep the OWNER_DIED bit */
+		newval = (curval & ~FUTEX_TID_MASK) | task_pid_vnr(task);
+		ownerdied = 0;
+		lock_taken = 1;
+	}
+
+	curval = cmpxchg_futex_value_locked(uaddr, uval, newval);
+
+	if (unlikely(curval == -EFAULT))
+		return -EFAULT;
+	if (unlikely(curval != uval))
+		goto retry;
+
+	/*
+	 * We took the lock due to owner died take over.
+	 */
+	if (unlikely(lock_taken))
+		return 1;
+
+	/*
+	 * We dont have the lock. Look up the PI state (or create it if
+	 * we are the first waiter):
+	 */
+	ret = lookup_pi_state(uval, hb, key, ps);
+
+	if (unlikely(ret)) {
+		switch (ret) {
+		case -ESRCH:
+			/*
+			 * No owner found for this futex. Check if the
+			 * OWNER_DIED bit is set to figure out whether
+			 * this is a robust futex or not.
+			 */
+			if (get_futex_value_locked(&curval, uaddr))
+				return -EFAULT;
+
+			/*
+			 * We simply start over in case of a robust
+			 * futex. The code above will take the futex
+			 * and return happy.
+			 */
+			if (curval & FUTEX_OWNER_DIED) {
+				ownerdied = 1;
+				goto retry;
+			}
+		default:
+			break;
+		}
+	}
+
+	return ret;
+}
+
 /*
  * The hash bucket lock must be held when this is called.
  * Afterwards, the futex_q must not be accessed.
  */
 static void wake_futex(struct futex_q *q)
 {
-	plist_del(&q->list, &q->list.plist);
+	struct task_struct *p = q->task;
+
 	/*
-	 * The lock in wake_up_all() is a crucial memory barrier after the
-	 * plist_del() and also before assigning to q->lock_ptr.
+	 * We set q->lock_ptr = NULL _before_ we wake up the task. If
+	 * a non futex wake up happens on another CPU then the task
+	 * might exit and p would dereference a non existing task
+	 * struct. Prevent this by holding a reference on p across the
+	 * wake up.
 	 */
-	wake_up(&q->waiter);
+	get_task_struct(p);
+
+	plist_del(&q->list, &q->list.plist);
 	/*
-	 * The waiting task can free the futex_q as soon as this is written,
-	 * without taking any locks.  This must come last.
-	 *
-	 * A memory barrier is required here to prevent the following store to
-	 * lock_ptr from getting ahead of the wakeup. Clearing the lock at the
-	 * end of wake_up() does not prevent this store from moving.
+	 * The waiting task can free the futex_q as soon as
+	 * q->lock_ptr = NULL is written, without taking any locks. A
+	 * memory barrier is required here to prevent the following
+	 * store to lock_ptr from getting ahead of the plist_del.
 	 */
 	smp_wmb();
 	q->lock_ptr = NULL;
+
+	wake_up_state(p, TASK_NORMAL);
+	put_task_struct(p);
 }
 
 static int wake_futex_pi(u32 __user *uaddr, u32 uval, struct futex_q *this)
@@ -689,7 +846,7 @@ static int futex_wake(u32 __user *uaddr, int fshared, int nr_wake, u32 bitset)
 
 	plist_for_each_entry_safe(this, next, head, list) {
 		if (match_futex (&this->key, &key)) {
-			if (this->pi_state) {
+			if (this->pi_state || this->rt_waiter) {
 				ret = -EINVAL;
 				break;
 			}
@@ -802,24 +959,185 @@ out:
 	return ret;
 }
 
-/*
- * Requeue all waiters hashed on one physical page to another
- * physical page.
+/**
+ * requeue_futex() - Requeue a futex_q from one hb to another
+ * @q:		the futex_q to requeue
+ * @hb1:	the source hash_bucket
+ * @hb2:	the target hash_bucket
+ * @key2:	the new key for the requeued futex_q
+ */
+static inline
+void requeue_futex(struct futex_q *q, struct futex_hash_bucket *hb1,
+		   struct futex_hash_bucket *hb2, union futex_key *key2)
+{
+
+	/*
+	 * If key1 and key2 hash to the same bucket, no need to
+	 * requeue.
+	 */
+	if (likely(&hb1->chain != &hb2->chain)) {
+		plist_del(&q->list, &hb1->chain);
+		plist_add(&q->list, &hb2->chain);
+		q->lock_ptr = &hb2->lock;
+#ifdef CONFIG_DEBUG_PI_LIST
+		q->list.plist.lock = &hb2->lock;
+#endif
+	}
+	get_futex_key_refs(key2);
+	q->key = *key2;
+}
+
+/**
+ * requeue_pi_wake_futex() - Wake a task that acquired the lock during requeue
+ * q:	the futex_q
+ * key:	the key of the requeue target futex
+ *
+ * During futex_requeue, with requeue_pi=1, it is possible to acquire the
+ * target futex if it is uncontended or via a lock steal.  Set the futex_q key
+ * to the requeue target futex so the waiter can detect the wakeup on the right
+ * futex, but remove it from the hb and NULL the rt_waiter so it can detect
+ * atomic lock acquisition.  Must be called with the q->lock_ptr held.
+ */
+static inline
+void requeue_pi_wake_futex(struct futex_q *q, union futex_key *key)
+{
+	drop_futex_key_refs(&q->key);
+	get_futex_key_refs(key);
+	q->key = *key;
+
+	WARN_ON(plist_node_empty(&q->list));
+	plist_del(&q->list, &q->list.plist);
+
+	WARN_ON(!q->rt_waiter);
+	q->rt_waiter = NULL;
+
+	wake_up_state(q->task, TASK_NORMAL);
+}
+
+/**
+ * futex_proxy_trylock_atomic() - Attempt an atomic lock for the top waiter
+ * @pifutex:		the user address of the to futex
+ * @hb1:		the from futex hash bucket, must be locked by the caller
+ * @hb2:		the to futex hash bucket, must be locked by the caller
+ * @key1:		the from futex key
+ * @key2:		the to futex key
+ * @ps:			address to store the pi_state pointer
+ * @set_waiters:	force setting the FUTEX_WAITERS bit (1) or not (0)
+ *
+ * Try and get the lock on behalf of the top waiter if we can do it atomically.
+ * Wake the top waiter if we succeed.  If the caller specified set_waiters,
+ * then direct futex_lock_pi_atomic() to force setting the FUTEX_WAITERS bit.
+ * hb1 and hb2 must be held by the caller.
+ *
+ * Returns:
+ *  0 - failed to acquire the lock atomicly
+ *  1 - acquired the lock
+ * <0 - error
+ */
+static int futex_proxy_trylock_atomic(u32 __user *pifutex,
+				 struct futex_hash_bucket *hb1,
+				 struct futex_hash_bucket *hb2,
+				 union futex_key *key1, union futex_key *key2,
+				 struct futex_pi_state **ps, int set_waiters)
+{
+	struct futex_q *top_waiter = NULL;
+	u32 curval;
+	int ret;
+
+	if (get_futex_value_locked(&curval, pifutex))
+		return -EFAULT;
+
+	/*
+	 * Find the top_waiter and determine if there are additional waiters.
+	 * If the caller intends to requeue more than 1 waiter to pifutex,
+	 * force futex_lock_pi_atomic() to set the FUTEX_WAITERS bit now,
+	 * as we have means to handle the possible fault.  If not, don't set
+	 * the bit unecessarily as it will force the subsequent unlock to enter
+	 * the kernel.
+	 */
+	top_waiter = futex_top_waiter(hb1, key1);
+
+	/* There are no waiters, nothing for us to do. */
+	if (!top_waiter)
+		return 0;
+
+	/*
+	 * Try to take the lock for top_waiter.  Set the FUTEX_WAITERS bit in
+	 * the contended case or if set_waiters is 1.  The pi_state is returned
+	 * in ps in contended cases.
+	 */
+	ret = futex_lock_pi_atomic(pifutex, hb2, key2, ps, top_waiter->task,
+				   set_waiters);
+	if (ret == 1)
+		requeue_pi_wake_futex(top_waiter, key2);
+
+	return ret;
+}
+
+/**
+ * futex_requeue() - Requeue waiters from uaddr1 to uaddr2
+ * uaddr1:	source futex user address
+ * uaddr2:	target futex user address
+ * nr_wake:	number of waiters to wake (must be 1 for requeue_pi)
+ * nr_requeue:	number of waiters to requeue (0-INT_MAX)
+ * requeue_pi:	if we are attempting to requeue from a non-pi futex to a
+ * 		pi futex (pi to pi requeue is not supported)
+ *
+ * Requeue waiters on uaddr1 to uaddr2. In the requeue_pi case, try to acquire
+ * uaddr2 atomically on behalf of the top waiter.
+ *
+ * Returns:
+ * >=0 - on success, the number of tasks requeued or woken
+ *  <0 - on error
  */
 static int futex_requeue(u32 __user *uaddr1, int fshared, u32 __user *uaddr2,
-			 int nr_wake, int nr_requeue, u32 *cmpval)
+			 int nr_wake, int nr_requeue, u32 *cmpval,
+			 int requeue_pi)
 {
 	union futex_key key1 = FUTEX_KEY_INIT, key2 = FUTEX_KEY_INIT;
+	int drop_count = 0, task_count = 0, ret;
+	struct futex_pi_state *pi_state = NULL;
 	struct futex_hash_bucket *hb1, *hb2;
 	struct plist_head *head1;
 	struct futex_q *this, *next;
-	int ret, drop_count = 0;
+	u32 curval2;
+
+	if (requeue_pi) {
+		/*
+		 * requeue_pi requires a pi_state, try to allocate it now
+		 * without any locks in case it fails.
+		 */
+		if (refill_pi_state_cache())
+			return -ENOMEM;
+		/*
+		 * requeue_pi must wake as many tasks as it can, up to nr_wake
+		 * + nr_requeue, since it acquires the rt_mutex prior to
+		 * returning to userspace, so as to not leave the rt_mutex with
+		 * waiters and no owner.  However, second and third wake-ups
+		 * cannot be predicted as they involve race conditions with the
+		 * first wake and a fault while looking up the pi_state.  Both
+		 * pthread_cond_signal() and pthread_cond_broadcast() should
+		 * use nr_wake=1.
+		 */
+		if (nr_wake != 1)
+			return -EINVAL;
+	}
 
 retry:
+	if (pi_state != NULL) {
+		/*
+		 * We will have to lookup the pi_state again, so free this one
+		 * to keep the accounting correct.
+		 */
+		free_pi_state(pi_state);
+		pi_state = NULL;
+	}
+
 	ret = get_futex_key(uaddr1, fshared, &key1, VERIFY_READ);
 	if (unlikely(ret != 0))
 		goto out;
-	ret = get_futex_key(uaddr2, fshared, &key2, VERIFY_READ);
+	ret = get_futex_key(uaddr2, fshared, &key2,
+			    requeue_pi ? VERIFY_WRITE : VERIFY_READ);
 	if (unlikely(ret != 0))
 		goto out_put_key1;
 
@@ -854,32 +1172,99 @@ retry_private:
 		}
 	}
 
+	if (requeue_pi && (task_count - nr_wake < nr_requeue)) {
+		/*
+		 * Attempt to acquire uaddr2 and wake the top waiter. If we
+		 * intend to requeue waiters, force setting the FUTEX_WAITERS
+		 * bit.  We force this here where we are able to easily handle
+		 * faults rather in the requeue loop below.
+		 */
+		ret = futex_proxy_trylock_atomic(uaddr2, hb1, hb2, &key1,
+						 &key2, &pi_state, nr_requeue);
+
+		/*
+		 * At this point the top_waiter has either taken uaddr2 or is
+		 * waiting on it.  If the former, then the pi_state will not
+		 * exist yet, look it up one more time to ensure we have a
+		 * reference to it.
+		 */
+		if (ret == 1) {
+			WARN_ON(pi_state);
+			task_count++;
+			ret = get_futex_value_locked(&curval2, uaddr2);
+			if (!ret)
+				ret = lookup_pi_state(curval2, hb2, &key2,
+						      &pi_state);
+		}
+
+		switch (ret) {
+		case 0:
+			break;
+		case -EFAULT:
+			double_unlock_hb(hb1, hb2);
+			put_futex_key(fshared, &key2);
+			put_futex_key(fshared, &key1);
+			ret = get_user(curval2, uaddr2);
+			if (!ret)
+				goto retry;
+			goto out;
+		case -EAGAIN:
+			/* The owner was exiting, try again. */
+			double_unlock_hb(hb1, hb2);
+			put_futex_key(fshared, &key2);
+			put_futex_key(fshared, &key1);
+			cond_resched();
+			goto retry;
+		default:
+			goto out_unlock;
+		}
+	}
+
 	head1 = &hb1->chain;
 	plist_for_each_entry_safe(this, next, head1, list) {
-		if (!match_futex (&this->key, &key1))
+		if (task_count - nr_wake >= nr_requeue)
+			break;
+
+		if (!match_futex(&this->key, &key1))
 			continue;
-		if (++ret <= nr_wake) {
+
+		WARN_ON(!requeue_pi && this->rt_waiter);
+		WARN_ON(requeue_pi && !this->rt_waiter);
+
+		/*
+		 * Wake nr_wake waiters.  For requeue_pi, if we acquired the
+		 * lock, we already woke the top_waiter.  If not, it will be
+		 * woken by futex_unlock_pi().
+		 */
+		if (++task_count <= nr_wake && !requeue_pi) {
 			wake_futex(this);
-		} else {
-			/*
-			 * If key1 and key2 hash to the same bucket, no need to
-			 * requeue.
-			 */
-			if (likely(head1 != &hb2->chain)) {
-				plist_del(&this->list, &hb1->chain);
-				plist_add(&this->list, &hb2->chain);
-				this->lock_ptr = &hb2->lock;
-#ifdef CONFIG_DEBUG_PI_LIST
-				this->list.plist.lock = &hb2->lock;
-#endif
-			}
-			this->key = key2;
-			get_futex_key_refs(&key2);
-			drop_count++;
+			continue;
+		}
 
-			if (ret - nr_wake >= nr_requeue)
-				break;
+		/*
+		 * Requeue nr_requeue waiters and possibly one more in the case
+		 * of requeue_pi if we couldn't acquire the lock atomically.
+		 */
+		if (requeue_pi) {
+			/* Prepare the waiter to take the rt_mutex. */
+			atomic_inc(&pi_state->refcount);
+			this->pi_state = pi_state;
+			ret = rt_mutex_start_proxy_lock(&pi_state->pi_mutex,
+							this->rt_waiter,
+							this->task, 1);
+			if (ret == 1) {
+				/* We got the lock. */
+				requeue_pi_wake_futex(this, &key2);
+				continue;
+			} else if (ret) {
+				/* -EDEADLK */
+				this->pi_state = NULL;
+				free_pi_state(pi_state);
+				goto out_unlock;
+			}
 		}
+		requeue_futex(this, hb1, hb2, &key2);
+		drop_count++;
 	}
 
 out_unlock:
@@ -899,7 +1284,9 @@ out_put_keys:
 out_put_key1:
 	put_futex_key(fshared, &key1);
 out:
-	return ret;
+	if (pi_state != NULL)
+		free_pi_state(pi_state);
+	return ret ? ret : task_count;
 }
 
 /* The key must be already stored in q->key. */
@@ -907,8 +1294,6 @@ static inline struct futex_hash_bucket *queue_lock(struct futex_q *q)
 {
 	struct futex_hash_bucket *hb;
 
-	init_waitqueue_head(&q->waiter);
-
 	get_futex_key_refs(&q->key);
 	hb = hash_futex(&q->key);
 	q->lock_ptr = &hb->lock;
@@ -1119,35 +1504,149 @@ handle_fault:
  */
 #define FLAGS_SHARED		0x01
 #define FLAGS_CLOCKRT		0x02
+#define FLAGS_HAS_TIMEOUT	0x04
 
 static long futex_wait_restart(struct restart_block *restart);
 
-static int futex_wait(u32 __user *uaddr, int fshared,
-		      u32 val, ktime_t *abs_time, u32 bitset, int clockrt)
+/**
+ * fixup_owner() - Post lock pi_state and corner case management
+ * @uaddr:	user address of the futex
+ * @fshared:	whether the futex is shared (1) or not (0)
+ * @q:		futex_q (contains pi_state and access to the rt_mutex)
+ * @locked:	if the attempt to take the rt_mutex succeeded (1) or not (0)
+ *
+ * After attempting to lock an rt_mutex, this function is called to cleanup
+ * the pi_state owner as well as handle race conditions that may allow us to
+ * acquire the lock. Must be called with the hb lock held.
+ *
+ * Returns:
+ *  1 - success, lock taken
+ *  0 - success, lock not taken
+ * <0 - on error (-EFAULT)
+ */
+static int fixup_owner(u32 __user *uaddr, int fshared, struct futex_q *q,
+		       int locked)
 {
-	struct task_struct *curr = current;
-	struct restart_block *restart;
-	DECLARE_WAITQUEUE(wait, curr);
-	struct futex_hash_bucket *hb;
-	struct futex_q q;
-	u32 uval;
-	int ret;
-	struct hrtimer_sleeper t;
-	int rem = 0;
+	struct task_struct *owner;
+	int ret = 0;
 
-	if (!bitset)
-		return -EINVAL;
+	if (locked) {
+		/*
+		 * Got the lock. We might not be the anticipated owner if we
+		 * did a lock-steal - fix up the PI-state in that case:
+		 */
+		if (q->pi_state->owner != current)
+			ret = fixup_pi_state_owner(uaddr, q, current, fshared);
+		goto out;
+	}
 
-	q.pi_state = NULL;
-	q.bitset = bitset;
-retry:
-	q.key = FUTEX_KEY_INIT;
-	ret = get_futex_key(uaddr, fshared, &q.key, VERIFY_READ);
-	if (unlikely(ret != 0))
+	/*
+	 * Catch the rare case, where the lock was released when we were on the
+	 * way back before we locked the hash bucket.
+	 */
+	if (q->pi_state->owner == current) {
+		/*
+		 * Try to get the rt_mutex now. This might fail as some other
+		 * task acquired the rt_mutex after we removed ourself from the
+		 * rt_mutex waiters list.
+		 */
+		if (rt_mutex_trylock(&q->pi_state->pi_mutex)) {
+			locked = 1;
+			goto out;
+		}
+
+		/*
+		 * pi_state is incorrect, some other task did a lock steal and
+		 * we returned due to timeout or signal without taking the
+		 * rt_mutex. Too late. We can access the rt_mutex_owner without
+		 * locking, as the other task is now blocked on the hash bucket
+		 * lock. Fix the state up.
+		 */
+		owner = rt_mutex_owner(&q->pi_state->pi_mutex);
+		ret = fixup_pi_state_owner(uaddr, q, owner, fshared);
 		goto out;
+	}
 
-retry_private:
-	hb = queue_lock(&q);
+	/*
+	 * Paranoia check. If we did not take the lock, then we should not be
+	 * the owner, nor the pending owner, of the rt_mutex.
+	 */
+	if (rt_mutex_owner(&q->pi_state->pi_mutex) == current)
+		printk(KERN_ERR "fixup_owner: ret = %d pi-mutex: %p "
+				"pi-state %p\n", ret,
+				q->pi_state->pi_mutex.owner,
+				q->pi_state->owner);
+
+out:
+	return ret ? ret : locked;
+}
+
+/**
+ * futex_wait_queue_me() - queue_me() and wait for wakeup, timeout, or signal
+ * @hb:		the futex hash bucket, must be locked by the caller
+ * @q:		the futex_q to queue up on
+ * @timeout:	the prepared hrtimer_sleeper, or null for no timeout
+ */
+static void futex_wait_queue_me(struct futex_hash_bucket *hb, struct futex_q *q,
+				struct hrtimer_sleeper *timeout)
+{
+	queue_me(q, hb);
+
+	/*
+	 * There might have been scheduling since the queue_me(), as we
+	 * cannot hold a spinlock across the get_user() in case it
+	 * faults, and we cannot just set TASK_INTERRUPTIBLE state when
+	 * queueing ourselves into the futex hash. This code thus has to
+	 * rely on the futex_wake() code removing us from hash when it
+	 * wakes us up.
+	 */
+	set_current_state(TASK_INTERRUPTIBLE);
+
+	/* Arm the timer */
+	if (timeout) {
+		hrtimer_start_expires(&timeout->timer, HRTIMER_MODE_ABS);
+		if (!hrtimer_active(&timeout->timer))
+			timeout->task = NULL;
+	}
+
+	/*
+	 * !plist_node_empty() is safe here without any lock.
+	 * q.lock_ptr != 0 is not safe, because of ordering against wakeup.
+	 */
+	if (likely(!plist_node_empty(&q->list))) {
+		/*
+		 * If the timer has already expired, current will already be
+		 * flagged for rescheduling. Only call schedule if there
+		 * is no timeout, or if it has yet to expire.
+		 */
+		if (!timeout || timeout->task)
+			schedule();
+	}
+	__set_current_state(TASK_RUNNING);
+}
+
+/**
+ * futex_wait_setup() - Prepare to wait on a futex
+ * @uaddr:	the futex userspace address
+ * @val:	the expected value
+ * @fshared:	whether the futex is shared (1) or not (0)
+ * @q:		the associated futex_q
+ * @hb:		storage for hash_bucket pointer to be returned to caller
+ *
+ * Setup the futex_q and locate the hash_bucket.  Get the futex value and
+ * compare it with the expected value.  Handle atomic faults internally.
+ * Return with the hb lock held and a q.key reference on success, and unlocked
+ * with no q.key reference on failure.
+ *
+ * Returns:
+ *  0 - uaddr contains val and hb has been locked
+ * <1 - -EFAULT or -EWOULDBLOCK (uaddr does not contain val) and hb is unlcoked
+ */
+static int futex_wait_setup(u32 __user *uaddr, u32 val, int fshared,
+			   struct futex_q *q, struct futex_hash_bucket **hb)
+{
+	u32 uval;
+	int ret;
 
 	/*
 	 * Access the page AFTER the hash-bucket is locked.
@@ -1165,95 +1664,83 @@ retry_private:
 	 * A consequence is that futex_wait() can return zero and absorb
 	 * a wakeup when *uaddr != val on entry to the syscall.  This is
 	 * rare, but normal.
-	 *
-	 * For shared futexes, we hold the mmap semaphore, so the mapping
-	 * cannot have changed since we looked it up in get_futex_key.
 	 */
+retry:
+	q->key = FUTEX_KEY_INIT;
+	ret = get_futex_key(uaddr, fshared, &q->key, VERIFY_READ);
+	if (unlikely(ret != 0))
+		return ret;
+
+retry_private:
+	*hb = queue_lock(q);
+
 	ret = get_futex_value_locked(&uval, uaddr);
 
-	if (unlikely(ret)) {
-		queue_unlock(&q, hb);
+	if (ret) {
+		queue_unlock(q, *hb);
 
 		ret = get_user(uval, uaddr);
 		if (ret)
-			goto out_put_key;
+			goto out;
 
 		if (!fshared)
 			goto retry_private;
 
-		put_futex_key(fshared, &q.key);
+		put_futex_key(fshared, &q->key);
 		goto retry;
 	}
-	ret = -EWOULDBLOCK;
-	if (unlikely(uval != val)) {
-		queue_unlock(&q, hb);
-		goto out_put_key;
-	}
 
-	/* Only actually queue if *uaddr contained val.  */
-	queue_me(&q, hb);
+	if (uval != val) {
+		queue_unlock(q, *hb);
+		ret = -EWOULDBLOCK;
+	}
 
-	/*
-	 * There might have been scheduling since the queue_me(), as we
-	 * cannot hold a spinlock across the get_user() in case it
-	 * faults, and we cannot just set TASK_INTERRUPTIBLE state when
-	 * queueing ourselves into the futex hash.  This code thus has to
-	 * rely on the futex_wake() code removing us from hash when it
-	 * wakes us up.
-	 */
+out:
+	if (ret)
+		put_futex_key(fshared, &q->key);
+	return ret;
+}
 
-	/* add_wait_queue is the barrier after __set_current_state. */
-	__set_current_state(TASK_INTERRUPTIBLE);
-	add_wait_queue(&q.waiter, &wait);
-	/*
-	 * !plist_node_empty() is safe here without any lock.
-	 * q.lock_ptr != 0 is not safe, because of ordering against wakeup.
-	 */
-	if (likely(!plist_node_empty(&q.list))) {
-		if (!abs_time)
-			schedule();
-		else {
-			hrtimer_init_on_stack(&t.timer,
-					      clockrt ? CLOCK_REALTIME :
-					      CLOCK_MONOTONIC,
-					      HRTIMER_MODE_ABS);
-			hrtimer_init_sleeper(&t, current);
-			hrtimer_set_expires_range_ns(&t.timer, *abs_time,
-						     current->timer_slack_ns);
-