futex fix

index 179b26e9c934..2650d1e52803 100644
@@ -982,8 +982,11 @@ static int handle_futex_death(u32 __user *uaddr, struct task_struct *curr,
 		return -1;
 
 	/*
-	 * Special case for regular (non PI) futexes. The unlock path in
-	 * user space has two race scenarios:
+	 * Special case for regular (non PI) futexes. Ordinarily, we do
+	 * not perform any processing here unless the current thread was
+	 * the owner of the futex (by the TID check below).
+	 *
+	 * However, the unlock path has three race scenarios:
 	 *
 	 * 1. The unlock path releases the user space futex value and
 	 *    before it can execute the futex() syscall to wake up

@@ -992,42 +995,70 @@ static int handle_futex_death(u32 __user *uaddr, struct task_struct *curr,
 	 * 2. A woken up waiter is killed before it can acquire the
 	 *    futex in user space.
 	 *
-	 * In the second case, the wake up notification could be generated
-	 * by the unlock path in user space after setting the futex value
-	 * to zero or by the kernel after setting the OWNER_DIED bit below.
+	 * 3. A woken up waiter is killed in user space after another
+	 *    thread has acquired the futex, but before it can set
+	 *    FUTEX_WAITERS.
+	 *
+	 * Note that, if userspace uses the FUTEX_ROBUST_UNLOCK flag, we
+	 * will not see case 1 here.
+	 *
+	 * In the second and third case, the wake up notification could
+	 * be generated from any of:
+	 *
+	 *    i.   An ordinary futex wakeup after unlock (with or
+	 *         without FUTEX_ROBUST_UNLOCK)
+	 *    ii.  A robust wakeup from another thread's death
+	 *    iii. A previous round through this special case
+	 *
+	 * As a result, the futex world will be in one of four states:
+	 *
+	 *    A. The futex word is 0 (unlocked)
+	 *    B. The futex word is owned by another thread
+	 *       (FUTEX_WAITERS is not set)
+	 *    C. The futex word is owned by another thread
+	 *       (FUTEX_WAITERS set)
+	 *    D. The futex's owner died and OWNER_DIED is set
+	 *       (the owner part of the word is 0)
 	 *
-	 * In both cases the TID validation below prevents a wakeup of
-	 * potential waiters which can cause these waiters to block
-	 * forever.
+	 * The key issue is that the kernel usually (at least from
+	 * sources ii. and iii. or when so requested by userspace from
+	 * source i.) only ever wakes *one* waiter at a time. If this
+	 * waiter dies before acquiring the futex (or setting the
+	 * FUTEX_WAITERS bit), the kernel *must* still wake the next
+	 * waiter down the line to uphold the futex invariants and
+	 * avoid lost wakeups. Note we do not need to handle state C,
+	 * as it does not matter to us whether *we* successfully set
+	 * the bit or a third thread did so in the meantime.
 	 *
-	 * In both cases the following conditions are met:
+	 * Therefore, in these cases we must issue an additional
+	 * futex_wake(). Note however that we *must not* set OWNER_DIED
+	 * here. Our thread is *not* the owner of the futex.
 	 *
-	 *	1) task->futex.robust_list->list_op_pending != NULL
-	 *	   @pending_op == true
-	 *	2) The owner part of user space futex value == 0
+	 * Thus to summarize, the conditions for needing the additional
+	 * futex_wake() are:
+	 *
+	 *	1) @pending_op == true (the thread has not finished the
+	 *	   mutex operation)
+	 *	2) The futex word is in one of the states A, B or D
 	 *	3) Regular futex: @pi == false
 	 *
-	 * If these conditions are met, it is safe to attempt waking up a
-	 * potential waiter without touching the user space futex value and
-	 * trying to set the OWNER_DIED bit. If the futex value is zero,
-	 * the rest of the user space mutex state is consistent, so a woken
-	 * waiter will just take over the uncontended futex. Setting the
-	 * OWNER_DIED bit would create inconsistent state and malfunction
-	 * of the user space owner died handling. Otherwise, the OWNER_DIED
-	 * bit is already set, and the woken waiter is expected to deal with
-	 * this.
+	 * Note in particular that in all of the states A-D the owner
+	 * portion of the futex word differs from our thread's TID
+	 * (unless the actual owner has the same TID in another PID
+	 * namespace, but we cannot currently distinguish that
+	 * scenario), so this can be a special-case wakeup in the bail
+	 * path of the ordinary TID check.
 	 */
 	owner = uval & FUTEX_TID_MASK;
 
-	if (pending_op && !pi && !owner) {
-		futex_wake(uaddr, FLAGS_SIZE_32 | FLAGS_SHARED, NULL, 1,
-			   FUTEX_BITSET_MATCH_ANY);
+	if (owner != task_pid_vnr(curr)) {
+		if (pending_op && !pi && (!owner || !(uval & FUTEX_WAITERS))) {
+			futex_wake(uaddr, FLAGS_SIZE_32 | FLAGS_SHARED, NULL, 1,
+				   FUTEX_BITSET_MATCH_ANY);
+		}
 		return 0;
 	}
 
-	if (owner != task_pid_vnr(curr))
-		return 0;
-
 	/*
 	 * Ok, this dying thread is truly holding a futex
 	 * of interest. Set the OWNER_DIED bit atomically