All of lore.kernel.org
 help / color / mirror / Atom feed
From: Peter Zijlstra <peterz@infradead.org>
To: tglx@linutronix.de
Cc: mingo@kernel.org, juri.lelli@arm.com, rostedt@goodmis.org,
	xlpang@redhat.com, bigeasy@linutronix.de,
	linux-kernel@vger.kernel.org, mathieu.desnoyers@efficios.com,
	jdesfossez@efficios.com, bristot@redhat.com,
	dvhart@infradead.org, peterz@infradead.org
Subject: [PATCH -v4 09/10] futex: Remove inconsistent hb/rt_mutex state magic
Date: Tue, 13 Dec 2016 09:36:47 +0100	[thread overview]
Message-ID: <20161213085730.629728043@infradead.org> (raw)
In-Reply-To: 20161213083638.938898295@infradead.org

[-- Attachment #1: peterz-futex-pi-unlock-6.patch --]
[-- Type: text/plain, Size: 2139 bytes --]

Now that we guarantee hb queue and rt_mutex waiter state match up, we
no longer need to deal with the fallout of when they don't.

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
---
 kernel/futex.c |   38 +-------------------------------------
 1 file changed, 1 insertion(+), 37 deletions(-)

--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -1396,13 +1396,7 @@ static int wake_futex_pi(u32 __user *uad
 	raw_spin_lock_irq(&pi_state->pi_mutex.wait_lock);
 	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.
-	 */
-	if (!new_owner)
-		new_owner = top_waiter->task;
+	BUG_ON(!new_owner);
 
 	/*
 	 * We pass it to the next owner. The WAITERS bit is always
@@ -2324,7 +2318,6 @@ static long futex_wait_restart(struct re
  */
 static int fixup_owner(u32 __user *uaddr, struct futex_q *q, int locked)
 {
-	struct task_struct *owner;
 	int ret = 0;
 
 	if (locked) {
@@ -2337,35 +2330,6 @@ static int fixup_owner(u32 __user *uaddr
 		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.

  parent reply	other threads:[~2016-12-13  9:02 UTC|newest]

Thread overview: 28+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2016-12-13  8:36 [PATCH -v4 00/10] FUTEX_UNLOCK_PI wobbles Peter Zijlstra
2016-12-13  8:36 ` [PATCH -v4 01/10] futex: Fix potential use-after-free in FUTEX_REQUEUE_PI Peter Zijlstra
2016-12-16 23:58   ` Darren Hart
2016-12-13  8:36 ` [PATCH -v4 02/10] futex: Add missing error handling to FUTEX_REQUEUE_PI Peter Zijlstra
2016-12-17  0:06   ` Darren Hart
2016-12-17 13:54     ` Peter Zijlstra
2016-12-18 23:31       ` Darren Hart
2016-12-13  8:36 ` [PATCH -v4 03/10] futex: Cleanup variable names for futex_top_waiter() Peter Zijlstra
2016-12-17  0:13   ` Darren Hart
2017-02-22 14:07     ` Peter Zijlstra
2016-12-13  8:36 ` [PATCH -v4 04/10] futex: Use smp_store_release() in mark_wake_futex() Peter Zijlstra
2016-12-17  0:50   ` Darren Hart
2017-02-22 14:03     ` Peter Zijlstra
2017-03-17  0:35       ` Darren Hart
2016-12-13  8:36 ` [PATCH -v4 05/10] futex: Remove rt_mutex_deadlock_account_*() Peter Zijlstra
2016-12-13  8:36 ` [PATCH -v4 06/10] futex,rt_mutex: Provide futex specific rt_mutex API Peter Zijlstra
2016-12-13  8:36 ` [PATCH -v4 07/10] futex: Change locking Peter Zijlstra
2016-12-13  8:36 ` [PATCH -v4 08/10] futex: Rework futex_lock_pi() vs rt_mutex_timed_futex_lock() Peter Zijlstra
2016-12-13  8:36 ` Peter Zijlstra [this message]
2016-12-13  8:36 ` [PATCH -v4 10/10] futex: Pull rt_mutex_futex_unlock() out from under hb->lock Peter Zijlstra
2016-12-13 16:07 ` [PATCH -v4 00/10] FUTEX_UNLOCK_PI wobbles Peter Zijlstra
2017-02-22 11:02   ` Peter Zijlstra
2017-02-22 15:36     ` Peter Zijlstra
2017-03-01  9:05       ` Thomas Gleixner
2017-03-03  9:35         ` Peter Zijlstra
2016-12-16 23:31 ` Darren Hart
2016-12-17 13:52   ` Peter Zijlstra
2016-12-18 22:39     ` Darren Hart

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20161213085730.629728043@infradead.org \
    --to=peterz@infradead.org \
    --cc=bigeasy@linutronix.de \
    --cc=bristot@redhat.com \
    --cc=dvhart@infradead.org \
    --cc=jdesfossez@efficios.com \
    --cc=juri.lelli@arm.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mathieu.desnoyers@efficios.com \
    --cc=mingo@kernel.org \
    --cc=rostedt@goodmis.org \
    --cc=tglx@linutronix.de \
    --cc=xlpang@redhat.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.