aboutsummaryrefslogtreecommitdiff
diff options
context:
space:
mode:
-rw-r--r--include/linux/futex.h3
-rw-r--r--kernel/futex.c61
2 files changed, 37 insertions, 27 deletions
diff --git a/include/linux/futex.h b/include/linux/futex.h
index 8f627b9ae2b..3bf5bb5a34f 100644
--- a/include/linux/futex.h
+++ b/include/linux/futex.h
@@ -25,7 +25,8 @@ union ktime;
#define FUTEX_WAKE_BITSET 10
#define FUTEX_PRIVATE_FLAG 128
-#define FUTEX_CMD_MASK ~FUTEX_PRIVATE_FLAG
+#define FUTEX_CLOCK_REALTIME 256
+#define FUTEX_CMD_MASK ~(FUTEX_PRIVATE_FLAG | FUTEX_CLOCK_REALTIME)
#define FUTEX_WAIT_PRIVATE (FUTEX_WAIT | FUTEX_PRIVATE_FLAG)
#define FUTEX_WAKE_PRIVATE (FUTEX_WAKE | FUTEX_PRIVATE_FLAG)
diff --git a/kernel/futex.c b/kernel/futex.c
index e10c5c8786a..b4f87bac91c 100644
--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -92,11 +92,12 @@ struct futex_pi_state {
* A futex_q has a woken state, just like tasks have TASK_RUNNING.
* It is considered woken when plist_node_empty(&q->list) || q->lock_ptr == 0.
* The order of wakup is always to make the first condition true, then
- * wake up q->waiters, then make the second condition true.
+ * wake up q->waiter, then make the second condition true.
*/
struct futex_q {
struct plist_node list;
- wait_queue_head_t waiters;
+ /* There can only be a single waiter */
+ wait_queue_head_t waiter;
/* Which hash list lock to use: */
spinlock_t *lock_ptr;
@@ -573,7 +574,7 @@ static void wake_futex(struct futex_q *q)
* The lock in wake_up_all() is a crucial memory barrier after the
* plist_del() and also before assigning to q->lock_ptr.
*/
- wake_up_all(&q->waiters);
+ wake_up(&q->waiter);
/*
* The waiting task can free the futex_q as soon as this is written,
* without taking any locks. This must come last.
@@ -930,7 +931,7 @@ static inline struct futex_hash_bucket *queue_lock(struct futex_q *q)
{
struct futex_hash_bucket *hb;
- init_waitqueue_head(&q->waiters);
+ init_waitqueue_head(&q->waiter);
get_futex_key_refs(&q->key);
hb = hash_futex(&q->key);
@@ -1142,12 +1143,13 @@ handle_fault:
* In case we must use restart_block to restart a futex_wait,
* we encode in the 'flags' shared capability
*/
-#define FLAGS_SHARED 1
+#define FLAGS_SHARED 0x01
+#define FLAGS_CLOCKRT 0x02
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)
+ u32 val, ktime_t *abs_time, u32 bitset, int clockrt)
{
struct task_struct *curr = current;
DECLARE_WAITQUEUE(wait, curr);
@@ -1220,7 +1222,7 @@ static int futex_wait(u32 __user *uaddr, int fshared,
/* add_wait_queue is the barrier after __set_current_state. */
__set_current_state(TASK_INTERRUPTIBLE);
- add_wait_queue(&q.waiters, &wait);
+ 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.
@@ -1233,8 +1235,10 @@ static int futex_wait(u32 __user *uaddr, int fshared,
slack = current->timer_slack_ns;
if (rt_task(current))
slack = 0;
- hrtimer_init_on_stack(&t.timer, CLOCK_MONOTONIC,
- HRTIMER_MODE_ABS);
+ 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, slack);
@@ -1289,6 +1293,8 @@ static int futex_wait(u32 __user *uaddr, int fshared,
if (fshared)
restart->futex.flags |= FLAGS_SHARED;
+ if (clockrt)
+ restart->futex.flags |= FLAGS_CLOCKRT;
return -ERESTART_RESTARTBLOCK;
}
@@ -1312,7 +1318,8 @@ static long futex_wait_restart(struct restart_block *restart)
if (restart->futex.flags & FLAGS_SHARED)
fshared = 1;
return (long)futex_wait(uaddr, fshared, restart->futex.val, &t,
- restart->futex.bitset);
+ restart->futex.bitset,
+ restart->futex.flags & FLAGS_CLOCKRT);
}
@@ -1558,12 +1565,11 @@ static int futex_lock_pi(u32 __user *uaddr, int fshared,
uaddr_faulted:
/*
- * We have to r/w *(int __user *)uaddr, but we can't modify it
- * non-atomically. Therefore, if get_user below is not
- * enough, we need to handle the fault ourselves, while
- * still holding the mmap_sem.
- *
- * ... and hb->lock. :-) --ANK
+ * We have to r/w *(int __user *)uaddr, and we have to modify it
+ * atomically. Therefore, if we continue to fault after get_user()
+ * below, we need to handle the fault ourselves, while still holding
+ * the mmap_sem. This can occur if the uaddr is under contention as
+ * we have to drop the mmap_sem in order to call get_user().
*/
queue_unlock(&q, hb);
@@ -1575,7 +1581,7 @@ static int futex_lock_pi(u32 __user *uaddr, int fshared,
}
ret = get_user(uval, uaddr);
- if (!ret && (uval != -EFAULT))
+ if (!ret)
goto retry;
if (to)
@@ -1669,12 +1675,11 @@ out:
pi_faulted:
/*
- * We have to r/w *(int __user *)uaddr, but we can't modify it
- * non-atomically. Therefore, if get_user below is not
- * enough, we need to handle the fault ourselves, while
- * still holding the mmap_sem.
- *
- * ... and hb->lock. --ANK
+ * We have to r/w *(int __user *)uaddr, and we have to modify it
+ * atomically. Therefore, if we continue to fault after get_user()
+ * below, we need to handle the fault ourselves, while still holding
+ * the mmap_sem. This can occur if the uaddr is under contention as
+ * we have to drop the mmap_sem in order to call get_user().
*/
spin_unlock(&hb->lock);
@@ -1687,7 +1692,7 @@ pi_faulted:
}
ret = get_user(uval, uaddr);
- if (!ret && (uval != -EFAULT))
+ if (!ret)
goto retry;
return ret;
@@ -1905,18 +1910,22 @@ void exit_robust_list(struct task_struct *curr)
long do_futex(u32 __user *uaddr, int op, u32 val, ktime_t *timeout,
u32 __user *uaddr2, u32 val2, u32 val3)
{
- int ret = -ENOSYS;
+ int clockrt, ret = -ENOSYS;
int cmd = op & FUTEX_CMD_MASK;
int fshared = 0;
if (!(op & FUTEX_PRIVATE_FLAG))
fshared = 1;
+ clockrt = op & FUTEX_CLOCK_REALTIME;
+ if (clockrt && cmd != FUTEX_WAIT_BITSET)
+ return -ENOSYS;
+
switch (cmd) {
case FUTEX_WAIT:
val3 = FUTEX_BITSET_MATCH_ANY;
case FUTEX_WAIT_BITSET:
- ret = futex_wait(uaddr, fshared, val, timeout, val3);
+ ret = futex_wait(uaddr, fshared, val, timeout, val3, clockrt);
break;
case FUTEX_WAKE:
val3 = FUTEX_BITSET_MATCH_ANY;