futex: Rework inconsistent rt_mutex/futex_q state

There is a weird state in the futex_unlock_pi() path when it interleaves
with a concurrent futex_lock_pi() at the point where it drops hb->lock.

In this case, it can happen that the rt_mutex wait_list and the futex_q
disagree on pending waiters, in particular rt_mutex will find no pending
waiters where futex_q thinks there are. In this case the rt_mutex unlock
code cannot assign an owner.

The futex side fixup code has to cleanup the inconsistencies with quite a
bunch of interesting corner cases.

Simplify all this by changing wake_futex_pi() to return -EAGAIN when this
situation occurs. This then gives the futex_lock_pi() code the opportunity
to continue and the retried futex_unlock_pi() will now observe a coherent
state.

The only problem is that this breaks RT timeliness guarantees. That
is, consider the following scenario:

  T1 and T2 are both pinned to CPU0. prio(T2) > prio(T1)

    CPU0

    T1
      lock_pi()
      queue_me()  <- Waiter is visible

    preemption

    T2
      unlock_pi()
	loops with -EAGAIN forever

Which is undesirable for PI primitives. Future patches will rectify
this.

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/20170322104151.850383690@infradead.org
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>

diff --git a/kernel/futex.c b/kernel/futex.c
index 3b6dbeecd91be431eea601ed9d458f00b2d4a68b..51a248af1db939971514021f9f7d66c2803d541d 100644 (file)
--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -1404,12 +1404,19 @@ static int wake_futex_pi(u32 __user *uaddr, u32 uval, struct futex_q *top_waiter
        new_owner = rt_mutex_next_owner(&pi_state->pi_mutex);
 
        /*
-        * It is possible that the next waiter (the one that brought
-        * top_waiter owner to the kernel) timed out and is no longer
-        * waiting on the lock.
+        * When we interleave with futex_lock_pi() where it does
+        * rt_mutex_timed_futex_lock(), we might observe @this futex_q waiter,
+        * but the rt_mutex's wait_list can be empty (either still, or again,
+        * depending on which side we land).
+        *
+        * When this happens, give up our locks and try again, giving the
+        * futex_lock_pi() instance time to complete, either by waiting on the
+        * rtmutex or removing itself from the futex queue.
         */
-       if (!new_owner)
-               new_owner = top_waiter->task;
+       if (!new_owner) {
+               raw_spin_unlock_irq(&pi_state->pi_mutex.wait_lock);
+               return -EAGAIN;
+       }
 
        /*
         * We pass it to the next owner. The WAITERS bit is always
@@ -2332,7 +2339,6 @@ static long futex_wait_restart(struct restart_block *restart);
  */
 static int fixup_owner(u32 __user *uaddr, struct futex_q *q, int locked)
 {
-       struct task_struct *owner;
        int ret = 0;
 
        if (locked) {
@@ -2345,44 +2351,16 @@ static int fixup_owner(u32 __user *uaddr, struct futex_q *q, int locked)
                goto out;
        }
 
-       /*
-        * Catch the rare case, where the lock was released when we were on the
-        * way back before we locked the hash bucket.
-        */
-       if (q->pi_state->owner == current) {
-               /*
-                * Try to get the rt_mutex now. This might fail as some other
-                * task acquired the rt_mutex after we removed ourself from the
-                * rt_mutex waiters list.
-                */
-               if (rt_mutex_futex_trylock(&q->pi_state->pi_mutex)) {
-                       locked = 1;
-                       goto out;
-               }
-
-               /*
-                * pi_state is incorrect, some other task did a lock steal and
-                * we returned due to timeout or signal without taking the
-                * rt_mutex. Too late.
-                */
-               raw_spin_lock_irq(&q->pi_state->pi_mutex.wait_lock);
-               owner = rt_mutex_owner(&q->pi_state->pi_mutex);
-               if (!owner)
-                       owner = rt_mutex_next_owner(&q->pi_state->pi_mutex);
-               raw_spin_unlock_irq(&q->pi_state->pi_mutex.wait_lock);
-               ret = fixup_pi_state_owner(uaddr, q, owner);
-               goto out;
-       }
-
        /*
         * Paranoia check. If we did not take the lock, then we should not be
         * the owner of the rt_mutex.
         */
-       if (rt_mutex_owner(&q->pi_state->pi_mutex) == current)
+       if (rt_mutex_owner(&q->pi_state->pi_mutex) == current) {
                printk(KERN_ERR "fixup_owner: ret = %d pi-mutex: %p "
                                "pi-state %p\n", ret,
                                q->pi_state->pi_mutex.owner,
                                q->pi_state->owner);
+       }
 
 out:
        return ret ? ret : locked;