From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1753237AbaJ0TCf (ORCPT ); Mon, 27 Oct 2014 15:02:35 -0400 Received: from youngberry.canonical.com ([91.189.89.112]:52617 "EHLO youngberry.canonical.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751862AbaJ0TCb (ORCPT ); Mon, 27 Oct 2014 15:02:31 -0400 From: Kamal Mostafa To: linux-kernel@vger.kernel.org, stable@vger.kernel.org, kernel-team@lists.ubuntu.com Cc: Catalin Marinas , Darren Hart , Thomas Gleixner , Peter Zijlstra , Ingo Molnar , "Paul E. McKenney" , Linus Torvalds , Kamal Mostafa Subject: [PATCH 3.13 103/105] futex: Ensure get_futex_key_refs() always implies a barrier Date: Mon, 27 Oct 2014 11:57:18 -0700 Message-Id: <1414436240-13879-104-git-send-email-kamal@canonical.com> X-Mailer: git-send-email 1.9.1 In-Reply-To: <1414436240-13879-1-git-send-email-kamal@canonical.com> References: <1414436240-13879-1-git-send-email-kamal@canonical.com> X-Extended-Stable: 3.13 Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org 3.13.11.10 -stable review patch. If anyone has any objections, please let me know. ------------------ From: Catalin Marinas commit 76835b0ebf8a7fe85beb03c75121419a7dec52f0 upstream. Commit b0c29f79ecea (futexes: Avoid taking the hb->lock if there's nothing to wake up) changes the futex code to avoid taking a lock when there are no waiters. This code has been subsequently fixed in commit 11d4616bd07f (futex: revert back to the explicit waiter counting code). Both the original commit and the fix-up rely on get_futex_key_refs() to always imply a barrier. However, for private futexes, none of the cases in the switch statement of get_futex_key_refs() would be hit and the function completes without a memory barrier as required before checking the "waiters" in futex_wake() -> hb_waiters_pending(). The consequence is a race with a thread waiting on a futex on another CPU, allowing the waker thread to read "waiters == 0" while the waiter thread to have read "futex_val == locked" (in kernel). Without this fix, the problem (user space deadlocks) can be seen with Android bionic's mutex implementation on an arm64 multi-cluster system. Signed-off-by: Catalin Marinas Reported-by: Matteo Franchin Fixes: b0c29f79ecea (futexes: Avoid taking the hb->lock if there's nothing to wake up) Acked-by: Davidlohr Bueso Tested-by: Mike Galbraith Cc: Darren Hart Cc: Thomas Gleixner Cc: Peter Zijlstra Cc: Ingo Molnar Cc: Paul E. McKenney Signed-off-by: Linus Torvalds Signed-off-by: Kamal Mostafa --- kernel/futex.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/kernel/futex.c b/kernel/futex.c index 4741b1f..2b1583e 100644 --- a/kernel/futex.c +++ b/kernel/futex.c @@ -194,6 +194,8 @@ static void get_futex_key_refs(union futex_key *key) case FUT_OFF_MMSHARED: atomic_inc(&key->private.mm->mm_count); break; + default: + smp_mb(); /* explicit MB (B) */ } } -- 1.9.1