futex_requeue_pi optimization

This patch provides the futex_requeue_pi functionality, which allows some
threads waiting on a normal futex to be requeued on the wait-queue of a
PI-futex.

This provides an optimization, already used for (normal) futexes, to be used
with the PI-futexes.

This optimization is currently used by the glibc in pthread_broadcast, when
using "normal" mutexes.  With futex_requeue_pi, it can be used with
PRIO_INHERIT mutexes too.
Signed-off-by: Pierre Peiffer <pierre.peiffer@bull.net>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Ulrich Drepper <drepper@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

include/linux/futex.h

@@ -17,6 +17,7 @@ union ktime;
 #define FUTEX_LOCK_PI		6
 #define FUTEX_UNLOCK_PI		7
 #define FUTEX_TRYLOCK_PI	8
+#define FUTEX_CMP_REQUEUE_PI	9
 
 /*
  * Support for robust futexes: the kernel cleans up held futexes at
@@ -84,10 +85,15 @@ struct robust_list_head {
  */
 #define FUTEX_OWNER_DIED	0x40000000
 
+/*
+ * Some processes have been requeued on this PI-futex
+ */
+#define FUTEX_WAITER_REQUEUED	0x20000000
+
 /*
  * The rest of the robust-futex field is for the TID:
  */
-#define FUTEX_TID_MASK		0x3fffffff
+#define FUTEX_TID_MASK		0x0fffffff
 
 /*
  * This limit protects against a deliberately circular list.
@@ -111,6 +117,7 @@ handle_futex_death(u32 __user *uaddr, struct task_struct *curr, int pi);
  * We set bit 0 to indicate if it's an inode-based key.
  */
 union futex_key {
+	u32 __user *uaddr;
 	struct {
 		unsigned long pgoff;
 		struct inode *inode;

kernel/futex_compat.c

@@ -156,7 +156,8 @@ asmlinkage long compat_sys_futex(u32 __user *uaddr, int op, u32 val,
 			t = ktime_add(ktime_get(), t);
 		tp = &t;
 	}
-	if (op == FUTEX_REQUEUE || op == FUTEX_CMP_REQUEUE)
+	if (op == FUTEX_REQUEUE || op == FUTEX_CMP_REQUEUE
+	    || op == FUTEX_CMP_REQUEUE_PI)
 		val2 = (int) (unsigned long) utime;
 
 	return do_futex(uaddr, op, val, tp, uaddr2, val2, val3);

kernel/rtmutex.c

@@ -56,7 +56,7 @@
  * state.
  */
 
-static void
+void
 rt_mutex_set_owner(struct rt_mutex *lock, struct task_struct *owner,
 		   unsigned long mask)
 {
@@ -80,29 +80,6 @@ static void fixup_rt_mutex_waiters(struct rt_mutex *lock)
 		clear_rt_mutex_waiters(lock);
 }
 
-/*
- * We can speed up the acquire/release, if the architecture
- * supports cmpxchg and if there's no debugging state to be set up
- */
-#if defined(__HAVE_ARCH_CMPXCHG) && !defined(CONFIG_DEBUG_RT_MUTEXES)
-# define rt_mutex_cmpxchg(l,c,n)	(cmpxchg(&l->owner, c, n) == c)
-static inline void mark_rt_mutex_waiters(struct rt_mutex *lock)
-{
-	unsigned long owner, *p = (unsigned long *) &lock->owner;
-
-	do {
-		owner = *p;
-	} while (cmpxchg(p, owner, owner | RT_MUTEX_HAS_WAITERS) != owner);
-}
-#else
-# define rt_mutex_cmpxchg(l,c,n)	(0)
-static inline void mark_rt_mutex_waiters(struct rt_mutex *lock)
-{
-	lock->owner = (struct task_struct *)
-			((unsigned long)lock->owner | RT_MUTEX_HAS_WAITERS);
-}
-#endif
-
 /*
  * Calculate task priority from the waiter list priority
  *
@@ -123,7 +100,7 @@ int rt_mutex_getprio(struct task_struct *task)
  *
  * This can be both boosting and unboosting. task->pi_lock must be held.
  */
-static void __rt_mutex_adjust_prio(struct task_struct *task)
+void __rt_mutex_adjust_prio(struct task_struct *task)
 {
 	int prio = rt_mutex_getprio(task);
 
@@ -159,11 +136,11 @@ int max_lock_depth = 1024;
  * 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 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)
 {
 	struct rt_mutex *lock;
 	struct rt_mutex_waiter *waiter, *top_waiter = orig_waiter;
@@ -524,8 +501,8 @@ static void wakeup_next_waiter(struct rt_mutex *lock)
  *
  * Must be called with lock->wait_lock held
  */
-static void remove_waiter(struct rt_mutex *lock,
-			  struct rt_mutex_waiter *waiter)
+void remove_waiter(struct rt_mutex *lock,
+		   struct rt_mutex_waiter *waiter)
 {
 	int first = (waiter == rt_mutex_top_waiter(lock));
 	struct task_struct *owner = rt_mutex_owner(lock);

kernel/rtmutex_common.h

@@ -112,6 +112,29 @@ static inline unsigned long rt_mutex_owner_pending(struct rt_mutex *lock)
 	return (unsigned long)lock->owner & RT_MUTEX_OWNER_PENDING;
 }
 
+/*
+ * We can speed up the acquire/release, if the architecture
+ * supports cmpxchg and if there's no debugging state to be set up
+ */
+#if defined(__HAVE_ARCH_CMPXCHG) && !defined(CONFIG_DEBUG_RT_MUTEXES)
+# define rt_mutex_cmpxchg(l,c,n)	(cmpxchg(&l->owner, c, n) == c)
+static inline void mark_rt_mutex_waiters(struct rt_mutex *lock)
+{
+	unsigned long owner, *p = (unsigned long *) &lock->owner;
+
+	do {
+		owner = *p;
+	} while (cmpxchg(p, owner, owner | RT_MUTEX_HAS_WAITERS) != owner);
+}
+#else
+# define rt_mutex_cmpxchg(l,c,n)	(0)
+static inline void mark_rt_mutex_waiters(struct rt_mutex *lock)
+{
+	lock->owner = (struct task_struct *)
+			((unsigned long)lock->owner | RT_MUTEX_HAS_WAITERS);
+}
+#endif
+
 /*
  * PI-futex support (proxy locking functions, etc.):
  */
@@ -120,4 +143,15 @@ 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 void rt_mutex_set_owner(struct rt_mutex *lock, struct task_struct *owner,
+			       unsigned long mask);
+extern void __rt_mutex_adjust_prio(struct task_struct *task);
+extern 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);
+extern void remove_waiter(struct rt_mutex *lock,
+			  struct rt_mutex_waiter *waiter);
 #endif