futex,rt_mutex: Provide futex specific rt_mutex API

Part of what makes futex_unlock_pi() intricate is that
rt_mutex_futex_unlock() -> rt_mutex_slowunlock() can drop
rt_mutex::wait_lock.

This means it cannot rely on the atomicy of wait_lock, which would be
preferred in order to not rely on hb->lock so much.

The reason rt_mutex_slowunlock() needs to drop wait_lock is because it can
race with the rt_mutex fastpath, however futexes have their own fast path.

Since futexes already have a bunch of separate rt_mutex accessors, complete
that set and implement a rt_mutex variant without fastpath for them.

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: juri.lelli@arm.com
Cc: bigeasy@linutronix.de
Cc: xlpang@redhat.com
Cc: rostedt@goodmis.org
Cc: mathieu.desnoyers@efficios.com
Cc: jdesfossez@efficios.com
Cc: dvhart@infradead.org
Cc: bristot@redhat.com
Link: http://lkml.kernel.org/r/20170322104151.702962446@infradead.org
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>

1 files changed, 14 insertions, 16 deletions

diff --git a/kernel/futex.c b/kernel/futex.c
index cc1034038285..af022919933a 100644
--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -916,7 +916,7 @@ void exit_pi_state_list(struct task_struct *curr)
                 pi_state->owner = NULL;
                 raw_spin_unlock_irq(&curr->pi_lock);
 
-                rt_mutex_unlock(&pi_state->pi_mutex);
+                rt_mutex_futex_unlock(&pi_state->pi_mutex);
 
                 spin_unlock(&hb->lock);
 
@@ -1364,20 +1364,18 @@ static int wake_futex_pi(u32 __user *uaddr, u32 uval, struct futex_q *top_waiter
         pi_state->owner = new_owner;
         raw_spin_unlock(&new_owner->pi_lock);
 
-        raw_spin_unlock_irq(&pi_state->pi_mutex.wait_lock);
-
-        deboost = rt_mutex_futex_unlock(&pi_state->pi_mutex, &wake_q);
-
         /*
-         * First unlock HB so the waiter does not spin on it once he got woken
-         * up. Second wake up the waiter before the priority is adjusted. If we
-         * deboost first (and lose our higher priority), then the task might get
-         * scheduled away before the wake up can take place.
+         * We've updated the uservalue, this unlock cannot fail.
          */
+        deboost = __rt_mutex_futex_unlock(&pi_state->pi_mutex, &wake_q);
+
+        raw_spin_unlock_irq(&pi_state->pi_mutex.wait_lock);
         spin_unlock(&hb->lock);
-        wake_up_q(&wake_q);
-        if (deboost)
+
+        if (deboost) {
+                wake_up_q(&wake_q);
                 rt_mutex_adjust_prio(current);
+        }
 
         return 0;
 }
@@ -2253,7 +2251,7 @@ static int fixup_owner(u32 __user *uaddr, struct futex_q *q, int locked)
                  * task acquired the rt_mutex after we removed ourself from the
                  * rt_mutex waiters list.
                  */
-                if (rt_mutex_trylock(&q->pi_state->pi_mutex)) {
+                if (rt_mutex_futex_trylock(&q->pi_state->pi_mutex)) {
                         locked = 1;
                         goto out;
                 }
@@ -2568,7 +2566,7 @@ retry_private:
         if (!trylock) {
                 ret = rt_mutex_timed_futex_lock(&q.pi_state->pi_mutex, to);
         } else {
-                ret = rt_mutex_trylock(&q.pi_state->pi_mutex);
+                ret = rt_mutex_futex_trylock(&q.pi_state->pi_mutex);
                 /* Fixup the trylock return value: */
                 ret = ret ? 0 : -EWOULDBLOCK;
         }
@@ -2591,7 +2589,7 @@ retry_private:
          * it and return the fault to userspace.
          */
         if (ret && (rt_mutex_owner(&q.pi_state->pi_mutex) == current))
-                rt_mutex_unlock(&q.pi_state->pi_mutex);
+                rt_mutex_futex_unlock(&q.pi_state->pi_mutex);
 
         /* Unqueue and drop the lock */
         unqueue_me_pi(&q);
@@ -2898,7 +2896,7 @@ static int futex_wait_requeue_pi(u32 __user *uaddr, unsigned int flags,
                         spin_lock(q.lock_ptr);
                         ret = fixup_pi_state_owner(uaddr2, &q, current);
                         if (ret && rt_mutex_owner(&q.pi_state->pi_mutex) == current)
-                                rt_mutex_unlock(&q.pi_state->pi_mutex);
+                                rt_mutex_futex_unlock(&q.pi_state->pi_mutex);
                         /*
                          * Drop the reference to the pi state which
                          * the requeue_pi() code acquired for us.
@@ -2938,7 +2936,7 @@ static int futex_wait_requeue_pi(u32 __user *uaddr, unsigned int flags,
                  * userspace.
                  */
                 if (ret && rt_mutex_owner(pi_mutex) == current)
-                        rt_mutex_unlock(pi_mutex);
+                        rt_mutex_futex_unlock(pi_mutex);
 
                 /* Unqueue and drop the lock. */
                 unqueue_me_pi(&q);