[PATCH] pi-futex: futex_lock_pi/futex_unlock_pi support

This adds the actual pi-futex implementation, based on rt-mutexes.

[dino@in.ibm.com: fix an oops-causing race]
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Arjan van de Ven <arjan@linux.intel.com>
Signed-off-by: Dinakar Guniguntala <dino@in.ibm.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>

include/linux/futex.h

@@ -12,6 +12,9 @@
 #define FUTEX_REQUEUE		3
 #define FUTEX_CMP_REQUEUE	4
 #define FUTEX_WAKE_OP		5
+#define FUTEX_LOCK_PI		6
+#define FUTEX_UNLOCK_PI		7
+#define FUTEX_TRYLOCK_PI	8
 
 /*
  * Support for robust futexes: the kernel cleans up held futexes at
@@ -97,10 +100,14 @@ extern int handle_futex_death(u32 __user *uaddr, struct task_struct *curr);
 
 #ifdef CONFIG_FUTEX
 extern void exit_robust_list(struct task_struct *curr);
+extern void exit_pi_state_list(struct task_struct *curr);
 #else
 static inline void exit_robust_list(struct task_struct *curr)
 {
 }
+static inline void exit_pi_state_list(struct task_struct *curr)
+{
+}
 #endif
 
 #define FUTEX_OP_SET		0	/* *(int *)UADDR2 = OPARG; */

include/linux/sched.h

@@ -84,6 +84,7 @@ struct sched_param {
 #include <asm/processor.h>
 
 struct exec_domain;
+struct futex_pi_state;
 
 /*
  * List of flags we want to share for kernel threads,
@@ -915,6 +916,8 @@ struct task_struct {
 #ifdef CONFIG_COMPAT
 	struct compat_robust_list_head __user *compat_robust_list;
 #endif
+	struct list_head pi_state_list;
+	struct futex_pi_state *pi_state_cache;
 
 	atomic_t fs_excl;	/* holding fs exclusive resources */
 	struct rcu_head rcu;

kernel/exit.c

@@ -925,6 +925,14 @@ fastcall NORET_TYPE void do_exit(long code)
 	mpol_free(tsk->mempolicy);
 	tsk->mempolicy = NULL;
 #endif
+	/*
+	 * This must happen late, after the PID is not
+	 * hashed anymore:
+	 */
+	if (unlikely(!list_empty(&tsk->pi_state_list)))
+		exit_pi_state_list(tsk);
+	if (unlikely(current->pi_state_cache))
+		kfree(current->pi_state_cache);
 	/*
 	 * If DEBUG_MUTEXES is on, make sure we are holding no locks:
 	 */

kernel/fork.c

@@ -1092,6 +1092,9 @@ static task_t *copy_process(unsigned long clone_flags,
 #ifdef CONFIG_COMPAT
 	p->compat_robust_list = NULL;
 #endif
+	INIT_LIST_HEAD(&p->pi_state_list);
+	p->pi_state_cache = NULL;
+
 	/*
 	 * sigaltstack should be cleared when sharing the same VM
 	 */

kernel/futex_compat.c

@@ -129,14 +129,19 @@ asmlinkage long compat_sys_futex(u32 __user *uaddr, int op, u32 val,
 	unsigned long timeout = MAX_SCHEDULE_TIMEOUT;
 	int val2 = 0;
 
-	if (utime && (op == FUTEX_WAIT)) {
+	if (utime && (op == FUTEX_WAIT || op == FUTEX_LOCK_PI)) {
 		if (get_compat_timespec(&t, utime))
 			return -EFAULT;
 		if (!timespec_valid(&t))
 			return -EINVAL;
-		timeout = timespec_to_jiffies(&t) + 1;
+		if (op == FUTEX_WAIT)
+			timeout = timespec_to_jiffies(&t) + 1;
+		else {
+			timeout = t.tv_sec;
+			val2 = t.tv_nsec;
+		}
 	}
-	if (op >= FUTEX_REQUEUE)
+	if (op == FUTEX_REQUEUE || op == FUTEX_CMP_REQUEUE)
 		val2 = (int) (unsigned long) utime;
 
 	return do_futex(uaddr, op, val, timeout, uaddr2, val2, val3);

kernel/rtmutex_common.h

@@ -112,4 +112,12 @@ static inline unsigned long rt_mutex_owner_pending(struct rt_mutex *lock)
 	return (unsigned long)lock->owner & RT_MUTEX_OWNER_PENDING;
 }
 
+/*
+ * PI-futex support (proxy locking functions, etc.):
+ */
+extern struct task_struct *rt_mutex_next_owner(struct rt_mutex *lock);
+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);
 #endif