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()

Documentation/futex-requeue-pi.txt

+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.

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 */

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

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 {

kernel/rtmutex_common.h

@@ -120,6 +120,14 @@ extern void rt_mutex_init_proxy_locked(struct rt_mutex *lock,
 				       struct task_struct *proxy_owner);
 extern void rt_mutex_proxy_unlock(struct rt_mutex *lock,
 				  struct task_struct *proxy_owner);
+extern int rt_mutex_start_proxy_lock(struct rt_mutex *lock,
+				     struct rt_mutex_waiter *waiter,
+				     struct task_struct *task,
+				     int detect_deadlock);
+extern int rt_mutex_finish_proxy_lock(struct rt_mutex *lock,
+				      struct hrtimer_sleeper *to,
+				      struct rt_mutex_waiter *waiter,
+				      int detect_deadlock);
 
 #ifdef CONFIG_DEBUG_RT_MUTEXES
 # include "rtmutex-debug.h"