From mboxrd@z Thu Jan 1 00:00:00 1970 From: Mathieu Desnoyers Subject: Re: [PATCH 08/11] membarrier: Provide core serializing command (v2) Date: Mon, 29 Jan 2018 18:36:05 +0000 (UTC) Message-ID: <485936677.11601.1517250965043.JavaMail.zimbra@efficios.com> References: <20180123155733.3404-1-mathieu.desnoyers@efficios.com> <20180123155733.3404-9-mathieu.desnoyers@efficios.com> <20180129180414.GO2249@hirez.programming.kicks-ass.net> <20180129181529.GG2295@hirez.programming.kicks-ass.net> Mime-Version: 1.0 Content-Type: text/plain; charset=utf-8 Content-Transfer-Encoding: 7bit Return-path: In-Reply-To: <20180129181529.GG2295-Nxj+rRp3nVydTX5a5knrm8zTDFooKrT+cvkQGrU6aU0@public.gmane.org> Sender: linux-api-owner-u79uwXL29TY76Z2rM5mHXA@public.gmane.org To: Peter Zijlstra Cc: Ingo Molnar , Thomas Gleixner , linux-kernel , linux-api , Andy Lutomirski , "Paul E. McKenney" , Boqun Feng , Andrew Hunter , maged michael , Avi Kivity , Benjamin Herrenschmidt , Paul Mackerras , Michael Ellerman , Dave Watson , "H. Peter Anvin" , Andrea Parri , "Russell King, ARM Linux" , Greg Hackmann , Will Deacon , David List-Id: linux-arch.vger.kernel.org ----- On Jan 29, 2018, at 1:15 PM, Peter Zijlstra peterz-wEGCiKHe2LqWVfeAwA7xHQ@public.gmane.org wrote: > On Mon, Jan 29, 2018 at 07:04:14PM +0100, Peter Zijlstra wrote: >> On Tue, Jan 23, 2018 at 10:57:30AM -0500, Mathieu Desnoyers wrote: >> > diff --git a/kernel/sched/core.c b/kernel/sched/core.c >> > index f38c4c7e256a..041893128f51 100644 >> > --- a/kernel/sched/core.c >> > +++ b/kernel/sched/core.c >> > @@ -2662,9 +2662,13 @@ static struct rq *finish_task_switch(struct task_struct >> > *prev) >> > * thread, mmdrop()'s implicit full barrier is required by the >> > * membarrier system call, because the current active_mm can >> > * become the current mm without going through switch_mm(). >> > + * membarrier also requires a core serializing instruction >> > + * before going back to user-space after storing to rq->curr. >> > */ >> > - if (mm) >> > + if (mm) { >> > + membarrier_mm_sync_core_before_usermode(mm); >> > mmdrop(mm); >> > + } >> >> *confused*, when we switch from process A to process B, context_switch() >> will not set rq->prev_mm and the above mm will be NULL and we'll not >> pass through your_function_names_are_waaay_too_long and we'll not get >> cookies. >> >> And if there's anything more complicated going on, the comment/changelog >> are not adequate. > > Aaah, its the case where we do not pass through switch_mm(), the partial > comment got to me. I only realized after reading the next patch. Indeed, if we read the entire comment, it's made clear that this case is for when switch_mm is not invoked, where the current mm is changed without going through switch_mm(), when scheduling between uthread->kthread->uthread for instance. /* * When transitioning from a kernel thread to a userspace * thread, mmdrop()'s implicit full barrier is required by the * membarrier system call, because the current active_mm can * become the current mm without going through switch_mm(). * membarrier also requires a core serializing instruction * before going back to user-space after storing to rq->curr. */ Is there something I should improve in the wording of this added sentence to make it clearer ? Thanks, Mathieu > >> > if (unlikely(prev_state == TASK_DEAD)) { >> > if (prev->sched_class->task_dead) >> > prev->sched_class->task_dead(prev); >> -- Mathieu Desnoyers EfficiOS Inc. http://www.efficios.com From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from mail.efficios.com ([167.114.142.141]:51734 "EHLO mail.efficios.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751357AbeA2Sfe (ORCPT ); Mon, 29 Jan 2018 13:35:34 -0500 Date: Mon, 29 Jan 2018 18:36:05 +0000 (UTC) From: Mathieu Desnoyers Message-ID: <485936677.11601.1517250965043.JavaMail.zimbra@efficios.com> In-Reply-To: <20180129181529.GG2295@hirez.programming.kicks-ass.net> References: <20180123155733.3404-1-mathieu.desnoyers@efficios.com> <20180123155733.3404-9-mathieu.desnoyers@efficios.com> <20180129180414.GO2249@hirez.programming.kicks-ass.net> <20180129181529.GG2295@hirez.programming.kicks-ass.net> Subject: Re: [PATCH 08/11] membarrier: Provide core serializing command (v2) MIME-Version: 1.0 Content-Type: text/plain; charset=utf-8 Content-Transfer-Encoding: 7bit Sender: linux-arch-owner@vger.kernel.org List-ID: To: Peter Zijlstra Cc: Ingo Molnar , Thomas Gleixner , linux-kernel , linux-api , Andy Lutomirski , "Paul E. McKenney" , Boqun Feng , Andrew Hunter , maged michael , Avi Kivity , Benjamin Herrenschmidt , Paul Mackerras , Michael Ellerman , Dave Watson , "H. Peter Anvin" , Andrea Parri , "Russell King, ARM Linux" , Greg Hackmann , Will Deacon , David Sehr , Linus Torvalds , x86 , linux-arch Message-ID: <20180129183605.PgKIxjCa38ZdAy-VuScxX2cSR3ch4I6MZTCzobG-GlQ@z> ----- On Jan 29, 2018, at 1:15 PM, Peter Zijlstra peterz@infradead.org wrote: > On Mon, Jan 29, 2018 at 07:04:14PM +0100, Peter Zijlstra wrote: >> On Tue, Jan 23, 2018 at 10:57:30AM -0500, Mathieu Desnoyers wrote: >> > diff --git a/kernel/sched/core.c b/kernel/sched/core.c >> > index f38c4c7e256a..041893128f51 100644 >> > --- a/kernel/sched/core.c >> > +++ b/kernel/sched/core.c >> > @@ -2662,9 +2662,13 @@ static struct rq *finish_task_switch(struct task_struct >> > *prev) >> > * thread, mmdrop()'s implicit full barrier is required by the >> > * membarrier system call, because the current active_mm can >> > * become the current mm without going through switch_mm(). >> > + * membarrier also requires a core serializing instruction >> > + * before going back to user-space after storing to rq->curr. >> > */ >> > - if (mm) >> > + if (mm) { >> > + membarrier_mm_sync_core_before_usermode(mm); >> > mmdrop(mm); >> > + } >> >> *confused*, when we switch from process A to process B, context_switch() >> will not set rq->prev_mm and the above mm will be NULL and we'll not >> pass through your_function_names_are_waaay_too_long and we'll not get >> cookies. >> >> And if there's anything more complicated going on, the comment/changelog >> are not adequate. > > Aaah, its the case where we do not pass through switch_mm(), the partial > comment got to me. I only realized after reading the next patch. Indeed, if we read the entire comment, it's made clear that this case is for when switch_mm is not invoked, where the current mm is changed without going through switch_mm(), when scheduling between uthread->kthread->uthread for instance. /* * When transitioning from a kernel thread to a userspace * thread, mmdrop()'s implicit full barrier is required by the * membarrier system call, because the current active_mm can * become the current mm without going through switch_mm(). * membarrier also requires a core serializing instruction * before going back to user-space after storing to rq->curr. */ Is there something I should improve in the wording of this added sentence to make it clearer ? Thanks, Mathieu > >> > if (unlikely(prev_state == TASK_DEAD)) { >> > if (prev->sched_class->task_dead) >> > prev->sched_class->task_dead(prev); >> -- Mathieu Desnoyers EfficiOS Inc. http://www.efficios.com