From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1753583AbbBXS2Y (ORCPT ); Tue, 24 Feb 2015 13:28:24 -0500 Received: from e23smtp08.au.ibm.com ([202.81.31.141]:53846 "EHLO e23smtp08.au.ibm.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1753095AbbBXS2W (ORCPT ); Tue, 24 Feb 2015 13:28:22 -0500 Message-ID: <54ECC2F1.4040704@linux.vnet.ibm.com> Date: Tue, 24 Feb 2015 23:59:05 +0530 From: Raghavendra K T Organization: IBM User-Agent: Mozilla/5.0 (X11; Linux x86_64; rv:17.0) Gecko/20130625 Thunderbird/17.0.7 MIME-Version: 1.0 To: Greg KH CC: Ingo Molnar , tglx@linutronix.de, mingo@redhat.com, hpa@zytor.com, torvalds@linux-foundation.org, konrad.wilk@oracle.com, pbonzini@redhat.com, peterz@infradead.org, paulmck@linux.vnet.ibm.com, waiman.long@hp.com, davej@redhat.com, oleg@redhat.com, x86@kernel.org, jeremy@goop.org, paul.gortmaker@windriver.com, ak@linux.intel.com, jasowang@redhat.com, linux-kernel@vger.kernel.org, kvm@vger.kernel.org, virtualization@lists.linux-foundation.org, xen-devel@lists.xenproject.org, riel@redhat.com, borntraeger@de.ibm.com, akpm@linux-foundation.org, a.ryabinin@samsung.com, sasha.levin@oracle.com, dave@stgolabs.net, stable@vger.kernel.org Subject: Re: [PATCH for stable] x86/spinlocks/paravirt: Fix memory corruption on unlock References: <1424769899-14158-1-git-send-email-raghavendra.kt@linux.vnet.ibm.com> <20150224141731.GA16033@kroah.com> <20150224144737.GA26074@gmail.com> <20150224152013.GC18122@kroah.com> In-Reply-To: <20150224152013.GC18122@kroah.com> Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit X-TM-AS-MML: disable X-Content-Scanned: Fidelis XPS MAILER x-cbid: 15022418-0029-0000-0000-000001294C70 Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On 02/24/2015 08:50 PM, Greg KH wrote: > On Tue, Feb 24, 2015 at 03:47:37PM +0100, Ingo Molnar wrote: >> >> * Greg KH wrote: >> >>> On Tue, Feb 24, 2015 at 02:54:59PM +0530, Raghavendra K T wrote: >>>> Paravirt spinlock clears slowpath flag after doing unlock. >>>> As explained by Linus currently it does: >>>> prev = *lock; >>>> add_smp(&lock->tickets.head, TICKET_LOCK_INC); >>>> >>>> /* add_smp() is a full mb() */ >>>> >>>> if (unlikely(lock->tickets.tail & TICKET_SLOWPATH_FLAG)) >>>> __ticket_unlock_slowpath(lock, prev); >>>> >>>> which is *exactly* the kind of things you cannot do with spinlocks, >>>> because after you've done the "add_smp()" and released the spinlock >>>> for the fast-path, you can't access the spinlock any more. Exactly >>>> because a fast-path lock might come in, and release the whole data >>>> structure. >>>> >>>> Linus suggested that we should not do any writes to lock after unlock(), >>>> and we can move slowpath clearing to fastpath lock. >>>> >>>> So this patch implements the fix with: >>>> 1. Moving slowpath flag to head (Oleg): >>>> Unlocked locks don't care about the slowpath flag; therefore we can keep >>>> it set after the last unlock, and clear it again on the first (try)lock. >>>> -- this removes the write after unlock. note that keeping slowpath flag would >>>> result in unnecessary kicks. >>>> By moving the slowpath flag from the tail to the head ticket we also avoid >>>> the need to access both the head and tail tickets on unlock. >>>> >>>> 2. use xadd to avoid read/write after unlock that checks the need for >>>> unlock_kick (Linus): >>>> We further avoid the need for a read-after-release by using xadd; >>>> the prev head value will include the slowpath flag and indicate if we >>>> need to do PV kicking of suspended spinners -- on modern chips xadd >>>> isn't (much) more expensive than an add + load. >>>> >>>> Result: >>>> setup: 16core (32 cpu +ht sandy bridge 8GB 16vcpu guest) >>>> benchmark overcommit %improve >>>> kernbench 1x -0.13 >>>> kernbench 2x 0.02 >>>> dbench 1x -1.77 >>>> dbench 2x -0.63 >>>> >>>> [Jeremy: hinted missing TICKET_LOCK_INC for kick] >>>> [Oleg: Moving slowpath flag to head, ticket_equals idea] >>>> [PeterZ: Detailed changelog] >>>> >>>> Reported-by: Sasha Levin >>>> Suggested-by: Linus Torvalds >>>> Signed-off-by: Raghavendra K T >>>> Reviewed-by: Oleg Nesterov >>>> Acked-by: David Vrabel >>>> --- >>>> arch/x86/include/asm/spinlock.h | 94 ++++++++++++++++++++--------------------- >>>> arch/x86/kernel/kvm.c | 7 ++- >>>> arch/x86/xen/spinlock.c | 7 ++- >>>> 3 files changed, 58 insertions(+), 50 deletions(-) >>>> >>>> Changes for stable: >>>> - Don't replace the ACCESS_ONCE to READ_ONCE which would cause horraneous >>>> Compiler warnings (Linus, David Vbriel, PeterZ, Ingo) >>> >>> What is the git commit id of this in Linus's tree? What >>> stable tree(s) do you want this applied to? >> >> It's: >> >> d6abfdb20223 x86/spinlocks/paravirt: Fix memory corruption on unlock >> >> You'll also need this fix from Linus to avoid (harmless) >> build warnings: >> >> dd36929720f4 kernel: make READ_ONCE() valid on const arguments > > Great. But what stable kernel trees should it be backported to? Just > 3.19? Or anything older? My patch was intended only for 3.19. Though paravirt changes have gone in 3.12, the problem manifested clearly after some of the completion related changes. but I leave that decision to experts here. (I 'll send necessary changes if patch is needed for older versions because it may not apply cleanly).