From: Peter Zijlstra <peterz@infradead.org>
To: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Cc: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>,
Boqun Feng <boqun.feng@gmail.com>,
Andy Lutomirski <luto@amacapital.net>,
Dave Watson <davejwatson@fb.com>,
linux-kernel <linux-kernel@vger.kernel.org>,
linux-api <linux-api@vger.kernel.org>,
Paul Turner <pjt@google.com>,
Andrew Morton <akpm@linux-foundation.org>,
Russell King <linux@arm.linux.org.uk>,
Thomas Gleixner <tglx@linutronix.de>,
Ingo Molnar <mingo@redhat.com>, "H. Peter Anvin" <hpa@zytor.com>,
Andrew Hunter <ahh@google.com>, Andi Kleen <andi@firstfloor.org>,
Chris Lameter <cl@linux.com>, Ben Maurer <bmaurer@fb.com>,
rostedt <rostedt@goodmis.org>,
Josh Triplett <josh@joshtriplett.org>,
Linus Torvalds <torvalds@linux-foundation.org>,
Catalin Marinas <catalin.marinas@arm.com>, Will Deacon <will>
Subject: Re: [RFC PATCH for 4.17 02/21] rseq: Introduce restartable sequences system call (v12)
Date: Wed, 28 Mar 2018 17:28:14 +0200 [thread overview]
Message-ID: <20180328152814.GI4082@hirez.programming.kicks-ass.net> (raw)
In-Reply-To: <265889560.1.1522250045589.JavaMail.zimbra@efficios.com>
On Wed, Mar 28, 2018 at 11:14:05AM -0400, Mathieu Desnoyers wrote:
> > If at all possible I would make it SIGSEGV when issueing SYSCALL()s from
> > within an RSEQ.
>
> What's the goal there ? rseq critical sections can technically do system calls
> if they wish. Why prevent this ?
This all started as a way to do 'small' _fast_ per-cpu ops, System calls
do NOT fit in that pattern. If you're willing to do a system calls the
cost of atomics is not a problem.
> How would you handle signal handlers that issue system calls while nested
> on top of a rseq critical section in the userspace thread ? SIGSEGV on
> SYSCALLs will break this case.
Have the rseq thing aborted prior to delivering the signal ?
WARNING: multiple messages have this Message-ID (diff)
From: Peter Zijlstra <peterz@infradead.org>
To: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Cc: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>,
Boqun Feng <boqun.feng@gmail.com>,
Andy Lutomirski <luto@amacapital.net>,
Dave Watson <davejwatson@fb.com>,
linux-kernel <linux-kernel@vger.kernel.org>,
linux-api <linux-api@vger.kernel.org>,
Paul Turner <pjt@google.com>,
Andrew Morton <akpm@linux-foundation.org>,
Russell King <linux@arm.linux.org.uk>,
Thomas Gleixner <tglx@linutronix.de>,
Ingo Molnar <mingo@redhat.com>, "H. Peter Anvin" <hpa@zytor.com>,
Andrew Hunter <ahh@google.com>, Andi Kleen <andi@firstfloor.org>,
Chris Lameter <cl@linux.com>, Ben Maurer <bmaurer@fb.com>,
rostedt <rostedt@goodmis.org>,
Josh Triplett <josh@joshtriplett.org>,
Linus Torvalds <torvalds@linux-foundation.org>,
Catalin Marinas <catalin.marinas@arm.com>,
Will Deacon <will.deacon@arm.com>,
Michael Kerrisk <mtk.manpages@gmail.com>,
Alexander Viro <viro@zeniv.linux.org.uk>
Subject: Re: [RFC PATCH for 4.17 02/21] rseq: Introduce restartable sequences system call (v12)
Date: Wed, 28 Mar 2018 17:28:14 +0200 [thread overview]
Message-ID: <20180328152814.GI4082@hirez.programming.kicks-ass.net> (raw)
In-Reply-To: <265889560.1.1522250045589.JavaMail.zimbra@efficios.com>
On Wed, Mar 28, 2018 at 11:14:05AM -0400, Mathieu Desnoyers wrote:
> > If at all possible I would make it SIGSEGV when issueing SYSCALL()s from
> > within an RSEQ.
>
> What's the goal there ? rseq critical sections can technically do system calls
> if they wish. Why prevent this ?
This all started as a way to do 'small' _fast_ per-cpu ops, System calls
do NOT fit in that pattern. If you're willing to do a system calls the
cost of atomics is not a problem.
> How would you handle signal handlers that issue system calls while nested
> on top of a rseq critical section in the userspace thread ? SIGSEGV on
> SYSCALLs will break this case.
Have the rseq thing aborted prior to delivering the signal ?
next prev parent reply other threads:[~2018-03-28 15:28 UTC|newest]
Thread overview: 123+ messages / expand[flat|nested] mbox.gz Atom feed top
2018-03-27 16:05 [RFC PATCH for 4.17 00/21] Restartable sequences and CPU op vector Mathieu Desnoyers
2018-03-27 16:05 ` [RFC PATCH for 4.17 01/21] uapi headers: Provide types_32_64.h Mathieu Desnoyers
2018-03-27 16:05 ` [RFC PATCH for 4.17 02/21] rseq: Introduce restartable sequences system call (v12) Mathieu Desnoyers
2018-03-28 6:47 ` Boqun Feng
2018-03-28 6:47 ` Boqun Feng
2018-03-28 14:06 ` Mathieu Desnoyers
2018-03-28 14:06 ` Mathieu Desnoyers
2018-03-28 14:31 ` Mathieu Desnoyers
2018-03-28 14:31 ` Mathieu Desnoyers
2018-03-28 11:19 ` Peter Zijlstra
2018-03-28 11:19 ` Peter Zijlstra
2018-03-28 14:19 ` Mathieu Desnoyers
2018-03-28 14:19 ` Mathieu Desnoyers
2018-03-28 11:22 ` Peter Zijlstra
2018-03-28 11:22 ` Peter Zijlstra
2018-03-28 14:26 ` Mathieu Desnoyers
2018-03-28 14:26 ` Mathieu Desnoyers
2018-03-28 12:29 ` Peter Zijlstra
2018-03-28 12:29 ` Peter Zijlstra
2018-03-28 12:52 ` Peter Zijlstra
2018-03-28 12:52 ` Peter Zijlstra
2018-03-28 15:03 ` Mathieu Desnoyers
2018-03-28 15:03 ` Mathieu Desnoyers
2018-03-28 16:19 ` Mathieu Desnoyers
2018-03-28 16:19 ` Mathieu Desnoyers
2018-03-28 12:50 ` Peter Zijlstra
2018-03-28 12:50 ` Peter Zijlstra
2018-03-28 14:47 ` Mathieu Desnoyers
2018-03-28 14:47 ` Mathieu Desnoyers
2018-03-28 14:59 ` Peter Zijlstra
2018-03-28 14:59 ` Peter Zijlstra
2018-03-28 15:14 ` Mathieu Desnoyers
2018-03-28 15:14 ` Mathieu Desnoyers
2018-03-28 15:28 ` Peter Zijlstra [this message]
2018-03-28 15:28 ` Peter Zijlstra
2018-03-28 15:37 ` Mathieu Desnoyers
2018-03-28 15:37 ` Mathieu Desnoyers
2018-03-28 17:49 ` Peter Zijlstra
2018-03-28 17:49 ` Peter Zijlstra
2018-03-28 20:19 ` Mathieu Desnoyers
2018-03-28 20:19 ` Mathieu Desnoyers
2018-03-28 21:25 ` Thomas Gleixner
2018-03-28 21:25 ` Thomas Gleixner
2018-03-29 13:54 ` Mathieu Desnoyers
2018-03-29 13:54 ` Mathieu Desnoyers
2018-03-29 14:23 ` Peter Zijlstra
2018-03-29 14:23 ` Peter Zijlstra
2018-03-29 15:39 ` Mathieu Desnoyers
2018-03-29 15:39 ` Mathieu Desnoyers
2018-03-29 16:24 ` Steven Rostedt
2018-03-29 16:24 ` Steven Rostedt
2018-03-29 18:02 ` Mathieu Desnoyers
2018-03-29 18:02 ` Mathieu Desnoyers
2018-03-29 18:07 ` Steven Rostedt
2018-03-29 18:07 ` Steven Rostedt
2018-03-29 18:35 ` Mathieu Desnoyers
2018-03-29 18:35 ` Mathieu Desnoyers
2018-03-29 18:46 ` Steven Rostedt
2018-03-29 18:46 ` Steven Rostedt
2018-03-29 18:47 ` Steven Rostedt
2018-03-29 18:47 ` Steven Rostedt
2018-04-01 16:13 ` Alan Cox
2018-04-01 16:13 ` Alan Cox
2018-04-02 15:03 ` Christopher Lameter
2018-04-02 15:03 ` Christopher Lameter
2018-04-02 15:27 ` Paul E. McKenney
2018-04-02 15:27 ` Paul E. McKenney
2018-04-02 15:33 ` Mathieu Desnoyers
2018-04-02 15:33 ` Mathieu Desnoyers
2018-04-03 16:36 ` Mathieu Desnoyers
2018-04-03 16:36 ` Mathieu Desnoyers
2018-04-03 20:32 ` Mathieu Desnoyers
2018-04-03 20:32 ` Mathieu Desnoyers
2018-03-27 16:05 ` [RFC PATCH for 4.17 03/21] arm: Add restartable sequences support Mathieu Desnoyers
2018-03-27 16:05 ` [RFC PATCH for 4.17 04/21] arm: Wire up restartable sequences system call Mathieu Desnoyers
2018-03-27 16:05 ` [RFC PATCH for 4.17 05/21] x86: Add support for restartable sequences Mathieu Desnoyers
2018-03-27 16:05 ` [RFC PATCH for 4.17 06/21] x86: Wire up restartable sequence system call Mathieu Desnoyers
2018-03-27 16:05 ` [RFC PATCH for 4.17 07/21] powerpc: Add support for restartable sequences Mathieu Desnoyers
2018-03-27 16:05 ` Mathieu Desnoyers
2018-03-27 16:05 ` [RFC PATCH for 4.17 08/21] powerpc: Wire up restartable sequences system call Mathieu Desnoyers
2018-03-27 16:05 ` Mathieu Desnoyers
2018-03-27 16:05 ` [RFC PATCH for 4.17 09/21] sched: Implement push_task_to_cpu (v2) Mathieu Desnoyers
2018-03-27 16:05 ` [RFC PATCH for 4.17 10/21] cpu_opv: Provide cpu_opv system call (v6) Mathieu Desnoyers
2018-03-28 15:22 ` Peter Zijlstra
2018-03-28 15:22 ` Peter Zijlstra
2018-03-28 17:54 ` Mathieu Desnoyers
2018-03-28 17:54 ` Mathieu Desnoyers
2018-03-27 16:05 ` [RFC PATCH for 4.17 11/21] x86: Wire up cpu_opv system call Mathieu Desnoyers
2018-03-27 16:05 ` [RFC PATCH for 4.17 12/21] powerpc: " Mathieu Desnoyers
2018-03-27 16:05 ` Mathieu Desnoyers
2018-03-27 16:05 ` [RFC PATCH for 4.17 13/21] arm: " Mathieu Desnoyers
2018-03-27 16:05 ` [RFC PATCH for 4.17 14/21] selftests: lib.mk: Introduce OVERRIDE_TARGETS Mathieu Desnoyers
2018-03-27 16:05 ` Mathieu Desnoyers
2018-03-27 16:05 ` mathieu.desnoyers
2018-03-27 16:05 ` [RFC PATCH for 4.17 15/21] cpu_opv: selftests: Implement selftests (v7) Mathieu Desnoyers
2018-03-27 16:05 ` Mathieu Desnoyers
2018-03-27 16:05 ` mathieu.desnoyers
2018-03-27 16:05 ` [RFC PATCH for 4.17 16/21] rseq: selftests: Provide rseq library (v5) Mathieu Desnoyers
2018-03-27 16:05 ` Mathieu Desnoyers
2018-03-27 16:05 ` Mathieu Desnoyers
2018-03-27 16:05 ` mathieu.desnoyers
2018-03-27 16:05 ` [RFC PATCH for 4.17 17/21] rseq: selftests: Provide percpu_op API Mathieu Desnoyers
2018-03-27 16:05 ` Mathieu Desnoyers
2018-03-27 16:05 ` Mathieu Desnoyers
2018-03-27 16:05 ` mathieu.desnoyers
2018-03-27 16:05 ` [RFC PATCH for 4.17 18/21] rseq: selftests: Provide basic test Mathieu Desnoyers
2018-03-27 16:05 ` Mathieu Desnoyers
2018-03-27 16:05 ` Mathieu Desnoyers
2018-03-27 16:05 ` mathieu.desnoyers
2018-03-27 16:05 ` [RFC PATCH for 4.17 19/21] rseq: selftests: Provide basic percpu ops test Mathieu Desnoyers
2018-03-27 16:05 ` Mathieu Desnoyers
2018-03-27 16:05 ` Mathieu Desnoyers
2018-03-27 16:05 ` mathieu.desnoyers
2018-03-27 16:05 ` [RFC PATCH for 4.17 20/21] rseq: selftests: Provide parametrized tests Mathieu Desnoyers
2018-03-27 16:05 ` Mathieu Desnoyers
2018-03-27 16:05 ` Mathieu Desnoyers
2018-03-27 16:05 ` mathieu.desnoyers
2018-03-27 16:05 ` [RFC PATCH for 4.17 21/21] rseq: selftests: Provide Makefile, scripts, gitignore Mathieu Desnoyers
2018-03-27 16:05 ` Mathieu Desnoyers
2018-03-27 16:05 ` Mathieu Desnoyers
2018-03-27 16:05 ` mathieu.desnoyers
2018-03-27 19:09 ` [RFC PATCH for 4.17 00/21] Restartable sequences and CPU op vector Peter Zijlstra
2018-03-27 19:09 ` Peter Zijlstra
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20180328152814.GI4082@hirez.programming.kicks-ass.net \
--to=peterz@infradead.org \
--cc=ahh@google.com \
--cc=akpm@linux-foundation.org \
--cc=andi@firstfloor.org \
--cc=bmaurer@fb.com \
--cc=boqun.feng@gmail.com \
--cc=catalin.marinas@arm.com \
--cc=cl@linux.com \
--cc=davejwatson@fb.com \
--cc=hpa@zytor.com \
--cc=josh@joshtriplett.org \
--cc=linux-api@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux@arm.linux.org.uk \
--cc=luto@amacapital.net \
--cc=mathieu.desnoyers@efficios.com \
--cc=mingo@redhat.com \
--cc=paulmck@linux.vnet.ibm.com \
--cc=pjt@google.com \
--cc=rostedt@goodmis.org \
--cc=tglx@linutronix.de \
--cc=torvalds@linux-foundation.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.