From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S932847AbdBVPg1 (ORCPT ); Wed, 22 Feb 2017 10:36:27 -0500 Received: from bombadil.infradead.org ([65.50.211.133]:51329 "EHLO bombadil.infradead.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S932526AbdBVPgT (ORCPT ); Wed, 22 Feb 2017 10:36:19 -0500 Date: Wed, 22 Feb 2017 16:36:12 +0100 From: Peter Zijlstra 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 Subject: Re: [PATCH -v4 00/10] FUTEX_UNLOCK_PI wobbles Message-ID: <20170222153612.GT6536@twins.programming.kicks-ass.net> References: <20161213083638.938898295@infradead.org> <20161213160714.GF3061@worktop.programming.kicks-ass.net> <20170222110244.GP6536@twins.programming.kicks-ass.net> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <20170222110244.GP6536@twins.programming.kicks-ass.net> User-Agent: Mutt/1.5.23.1 (2014-03-12) Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On Wed, Feb 22, 2017 at 12:02:44PM +0100, Peter Zijlstra wrote: > OK, so after having not thought about this, and then spend the last two > days trying to cram all this nonsense back into my head, I think I have > a slightly simpler option. > > In any case, I'll go respin the patch-set and repost. That is; what is wrong with the below patch against mainline? --- kernel/futex.c | 48 +++++++++++++----------------------------------- 1 file changed, 13 insertions(+), 35 deletions(-) diff --git a/kernel/futex.c b/kernel/futex.c index c591a2a..fafa25a 100644 --- a/kernel/futex.c +++ b/kernel/futex.c @@ -1318,12 +1318,18 @@ static int wake_futex_pi(u32 __user *uaddr, u32 uval, struct futex_q *this, new_owner = rt_mutex_next_owner(&pi_state->pi_mutex); /* - * It is possible that the next waiter (the one that brought - * this 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 and unqueue_me(). */ - if (!new_owner) - new_owner = this->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 @@ -2245,43 +2251,15 @@ static int fixup_owner(u32 __user *uaddr, struct futex_q *q, int locked) } /* - * 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_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;