From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1753309Ab3J2VXu (ORCPT ); Tue, 29 Oct 2013 17:23:50 -0400 Received: from ozlabs.org ([203.10.76.45]:36478 "EHLO ozlabs.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751044Ab3J2VXt (ORCPT ); Tue, 29 Oct 2013 17:23:49 -0400 From: Michael Neuling To: Peter Zijlstra cc: Victor Kaplansky , Oleg Nesterov , Anton Blanchard , Benjamin Herrenschmidt , Frederic Weisbecker , LKML , Linux PPC dev , Mathieu Desnoyers , Michael Ellerman , "Paul E. McKenney" Subject: Re: perf events ring buffer memory barrier on powerpc In-reply-to: <20131029103057.GN2490@laptop.programming.kicks-ass.net> References: <12083.1382486094@ale.ozlabs.ibm.com> <20131023141948.GB3566@localhost.localdomain> <20131025173749.GG19466@laptop.lan> <20131028132634.GO19466@laptop.lan> <20131028163418.GD4126@linux.vnet.ibm.com> <20131028201735.GA15629@redhat.com> <20131029102131.GA16117@laptop.programming.kicks-ass.net> <20131029103057.GN2490@laptop.programming.kicks-ass.net> Comments: In-reply-to Peter Zijlstra message dated "Tue, 29 Oct 2013 11:30:57 +0100." X-Mailer: MH-E 8.2; nmh 1.5; GNU Emacs 23.4.1 Date: Wed, 30 Oct 2013 08:23:48 +1100 Message-ID: <12631.1383081828@ale.ozlabs.ibm.com> Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Peter Zijlstra wrote: > On Tue, Oct 29, 2013 at 11:21:31AM +0100, Peter Zijlstra wrote: > > On Mon, Oct 28, 2013 at 10:58:58PM +0200, Victor Kaplansky wrote: > > > Oleg Nesterov wrote on 10/28/2013 10:17:35 PM: > > > > > > > mb(); // XXXXXXXX: do we really need it? I think yes. > > > > > > Oh, it is hard to argue with feelings. Also, it is easy to be on > > > conservative side and put the barrier here just in case. > > > > I'll make it a full mb for now and too am curious to see the end of this > > discussion explaining things ;-) > > That is, I've now got this queued: Can we also CC stable@kernel.org? This has been around for a while. Mikey > > --- > Subject: perf: Fix perf ring buffer memory ordering > From: Peter Zijlstra > Date: Mon Oct 28 13:55:29 CET 2013 > > The PPC64 people noticed a missing memory barrier and crufty old > comments in the perf ring buffer code. So update all the comments and > add the missing barrier. > > When the architecture implements local_t using atomic_long_t there > will be double barriers issued; but short of introducing more > conditional barrier primitives this is the best we can do. > > Cc: Mathieu Desnoyers > Cc: michael@ellerman.id.au > Cc: Paul McKenney > Cc: Michael Neuling > Cc: Frederic Weisbecker > Cc: anton@samba.org > Cc: benh@kernel.crashing.org > Reported-by: Victor Kaplansky > Tested-by: Victor Kaplansky > Signed-off-by: Peter Zijlstra > Link: http://lkml.kernel.org/r/20131025173749.GG19466@laptop.lan > --- > include/uapi/linux/perf_event.h | 12 +++++++----- > kernel/events/ring_buffer.c | 31 +++++++++++++++++++++++++++---- > 2 files changed, 34 insertions(+), 9 deletions(-) > > Index: linux-2.6/include/uapi/linux/perf_event.h > =================================================================== > --- linux-2.6.orig/include/uapi/linux/perf_event.h > +++ linux-2.6/include/uapi/linux/perf_event.h > @@ -479,13 +479,15 @@ struct perf_event_mmap_page { > /* > * Control data for the mmap() data buffer. > * > - * User-space reading the @data_head value should issue an rmb(), on > - * SMP capable platforms, after reading this value -- see > - * perf_event_wakeup(). > + * User-space reading the @data_head value should issue an smp_rmb(), > + * after reading this value. > * > * When the mapping is PROT_WRITE the @data_tail value should be > - * written by userspace to reflect the last read data. In this case > - * the kernel will not over-write unread data. > + * written by userspace to reflect the last read data, after issueing > + * an smp_mb() to separate the data read from the ->data_tail store. > + * In this case the kernel will not over-write unread data. > + * > + * See perf_output_put_handle() for the data ordering. > */ > __u64 data_head; /* head in the data section */ > __u64 data_tail; /* user-space written tail */ > Index: linux-2.6/kernel/events/ring_buffer.c > =================================================================== > --- linux-2.6.orig/kernel/events/ring_buffer.c > +++ linux-2.6/kernel/events/ring_buffer.c > @@ -87,10 +87,31 @@ static void perf_output_put_handle(struc > goto out; > > /* > - * Publish the known good head. Rely on the full barrier implied > - * by atomic_dec_and_test() order the rb->head read and this > - * write. > + * Since the mmap() consumer (userspace) can run on a different CPU: > + * > + * kernel user > + * > + * READ ->data_tail READ ->data_head > + * smp_mb() (A) smp_rmb() (C) > + * WRITE $data READ $data > + * smp_wmb() (B) smp_mb() (D) > + * STORE ->data_head WRITE ->data_tail > + * > + * Where A pairs with D, and B pairs with C. > + * > + * I don't think A needs to be a full barrier because we won't in fact > + * write data until we see the store from userspace. So we simply don't > + * issue the data WRITE until we observe it. Be conservative for now. > + * > + * OTOH, D needs to be a full barrier since it separates the data READ > + * from the tail WRITE. > + * > + * For B a WMB is sufficient since it separates two WRITEs, and for C > + * an RMB is sufficient since it separates two READs. > + * > + * See perf_output_begin(). > */ > + smp_wmb(); > rb->user_page->data_head = head; > > /* > @@ -154,9 +175,11 @@ int perf_output_begin(struct perf_output > * Userspace could choose to issue a mb() before updating the > * tail pointer. So that all reads will be completed before the > * write is issued. > + * > + * See perf_output_put_handle(). > */ > tail = ACCESS_ONCE(rb->user_page->data_tail); > - smp_rmb(); > + smp_mb(); > offset = head = local_read(&rb->head); > head += size; > if (unlikely(!perf_output_space(rb, tail, offset, head))) > From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: From: Michael Neuling To: Peter Zijlstra Subject: Re: perf events ring buffer memory barrier on powerpc In-reply-to: <20131029103057.GN2490@laptop.programming.kicks-ass.net> References: <12083.1382486094@ale.ozlabs.ibm.com> <20131023141948.GB3566@localhost.localdomain> <20131025173749.GG19466@laptop.lan> <20131028132634.GO19466@laptop.lan> <20131028163418.GD4126@linux.vnet.ibm.com> <20131028201735.GA15629@redhat.com> <20131029102131.GA16117@laptop.programming.kicks-ass.net> <20131029103057.GN2490@laptop.programming.kicks-ass.net> Date: Wed, 30 Oct 2013 08:23:48 +1100 Message-ID: <12631.1383081828@ale.ozlabs.ibm.com> Cc: Mathieu Desnoyers , Oleg Nesterov , LKML , Linux PPC dev , Anton Blanchard , Frederic Weisbecker , Victor Kaplansky , "Paul E. McKenney" List-Id: Linux on PowerPC Developers Mail List List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Peter Zijlstra wrote: > On Tue, Oct 29, 2013 at 11:21:31AM +0100, Peter Zijlstra wrote: > > On Mon, Oct 28, 2013 at 10:58:58PM +0200, Victor Kaplansky wrote: > > > Oleg Nesterov wrote on 10/28/2013 10:17:35 PM: > > > > > > > mb(); // XXXXXXXX: do we really need it? I think yes. > > > > > > Oh, it is hard to argue with feelings. Also, it is easy to be on > > > conservative side and put the barrier here just in case. > > > > I'll make it a full mb for now and too am curious to see the end of this > > discussion explaining things ;-) > > That is, I've now got this queued: Can we also CC stable@kernel.org? This has been around for a while. Mikey > > --- > Subject: perf: Fix perf ring buffer memory ordering > From: Peter Zijlstra > Date: Mon Oct 28 13:55:29 CET 2013 > > The PPC64 people noticed a missing memory barrier and crufty old > comments in the perf ring buffer code. So update all the comments and > add the missing barrier. > > When the architecture implements local_t using atomic_long_t there > will be double barriers issued; but short of introducing more > conditional barrier primitives this is the best we can do. > > Cc: Mathieu Desnoyers > Cc: michael@ellerman.id.au > Cc: Paul McKenney > Cc: Michael Neuling > Cc: Frederic Weisbecker > Cc: anton@samba.org > Cc: benh@kernel.crashing.org > Reported-by: Victor Kaplansky > Tested-by: Victor Kaplansky > Signed-off-by: Peter Zijlstra > Link: http://lkml.kernel.org/r/20131025173749.GG19466@laptop.lan > --- > include/uapi/linux/perf_event.h | 12 +++++++----- > kernel/events/ring_buffer.c | 31 +++++++++++++++++++++++++++---- > 2 files changed, 34 insertions(+), 9 deletions(-) > > Index: linux-2.6/include/uapi/linux/perf_event.h > =================================================================== > --- linux-2.6.orig/include/uapi/linux/perf_event.h > +++ linux-2.6/include/uapi/linux/perf_event.h > @@ -479,13 +479,15 @@ struct perf_event_mmap_page { > /* > * Control data for the mmap() data buffer. > * > - * User-space reading the @data_head value should issue an rmb(), on > - * SMP capable platforms, after reading this value -- see > - * perf_event_wakeup(). > + * User-space reading the @data_head value should issue an smp_rmb(), > + * after reading this value. > * > * When the mapping is PROT_WRITE the @data_tail value should be > - * written by userspace to reflect the last read data. In this case > - * the kernel will not over-write unread data. > + * written by userspace to reflect the last read data, after issueing > + * an smp_mb() to separate the data read from the ->data_tail store. > + * In this case the kernel will not over-write unread data. > + * > + * See perf_output_put_handle() for the data ordering. > */ > __u64 data_head; /* head in the data section */ > __u64 data_tail; /* user-space written tail */ > Index: linux-2.6/kernel/events/ring_buffer.c > =================================================================== > --- linux-2.6.orig/kernel/events/ring_buffer.c > +++ linux-2.6/kernel/events/ring_buffer.c > @@ -87,10 +87,31 @@ static void perf_output_put_handle(struc > goto out; > > /* > - * Publish the known good head. Rely on the full barrier implied > - * by atomic_dec_and_test() order the rb->head read and this > - * write. > + * Since the mmap() consumer (userspace) can run on a different CPU: > + * > + * kernel user > + * > + * READ ->data_tail READ ->data_head > + * smp_mb() (A) smp_rmb() (C) > + * WRITE $data READ $data > + * smp_wmb() (B) smp_mb() (D) > + * STORE ->data_head WRITE ->data_tail > + * > + * Where A pairs with D, and B pairs with C. > + * > + * I don't think A needs to be a full barrier because we won't in fact > + * write data until we see the store from userspace. So we simply don't > + * issue the data WRITE until we observe it. Be conservative for now. > + * > + * OTOH, D needs to be a full barrier since it separates the data READ > + * from the tail WRITE. > + * > + * For B a WMB is sufficient since it separates two WRITEs, and for C > + * an RMB is sufficient since it separates two READs. > + * > + * See perf_output_begin(). > */ > + smp_wmb(); > rb->user_page->data_head = head; > > /* > @@ -154,9 +175,11 @@ int perf_output_begin(struct perf_output > * Userspace could choose to issue a mb() before updating the > * tail pointer. So that all reads will be completed before the > * write is issued. > + * > + * See perf_output_put_handle(). > */ > tail = ACCESS_ONCE(rb->user_page->data_tail); > - smp_rmb(); > + smp_mb(); > offset = head = local_read(&rb->head); > head += size; > if (unlikely(!perf_output_space(rb, tail, offset, head))) >