From: Andi Kleen <andi@firstfloor.org>
To: Thomas Gleixner <tglx@linutronix.de>
Cc: Andi Kleen <andi@firstfloor.org>,
Mathieu Desnoyers <mathieu.desnoyers@efficios.com>,
Peter Zijlstra <peterz@infradead.org>,
"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>,
Ingo Molnar <mingo@redhat.com>, "H. Peter Anvin" <hpa@zytor.com>,
Andrew Hunter <ahh@google.com>, 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>
Subject: Re: [RFC PATCH v3 for 4.15 08/24] Provide cpu_opv system call
Date: Fri, 17 Nov 2017 11:15:47 -0800 [thread overview]
Message-ID: <20171117191547.GI2482@two.firstfloor.org> (raw)
In-Reply-To: <alpine.DEB.2.20.1711171922420.2186@nanos>
> The most straight forward is to have a mechanism which forces everything
> into the slow path in case of debugging, lack of progress, etc. The slow
That's the abort address, right?
For the generic case the fall back path would require disabling preemption
unfortunately, for which we don't have a mechanism in user space.
I think that is what Mathieu tried to implement here with this call.
There may be some special cases where it's possible without preemption
control, e.g. a malloc could just not use the per cpu cache. But I doubt
that is possible in all cases that Mathieu envisions.
But again would be a different code path, and I question the need for it when
we can just let the operator of the debugger deal with it.
-Andi
next prev parent reply other threads:[~2017-11-17 19:15 UTC|newest]
Thread overview: 80+ messages / expand[flat|nested] mbox.gz Atom feed top
2017-11-14 20:03 [RFC PATCH for 4.15 00/24] Restartable sequences and CPU op vector v11 Mathieu Desnoyers
2017-11-14 20:03 ` [RFC PATCH v11 for 4.15 01/24] Restartable sequences system call Mathieu Desnoyers
2017-11-14 20:39 ` Ben Maurer
2017-11-14 20:52 ` Mathieu Desnoyers
2017-11-14 21:48 ` Ben Maurer
[not found] ` <CY4PR15MB168884529B3C0F8E6CC06257CF280@CY4PR15MB1688.namprd15.prod.outlook.com>
2017-11-14 20:49 ` Ben Maurer
2017-11-14 21:03 ` Mathieu Desnoyers
2017-11-16 16:18 ` Peter Zijlstra
2017-11-16 16:27 ` Mathieu Desnoyers
2017-11-16 16:32 ` Peter Zijlstra
2017-11-16 17:09 ` Mathieu Desnoyers
2017-11-16 18:43 ` Peter Zijlstra
2017-11-16 18:49 ` Mathieu Desnoyers
2017-11-16 19:06 ` Thomas Gleixner
2017-11-16 20:06 ` Mathieu Desnoyers
2017-11-16 19:14 ` Peter Zijlstra
2017-11-16 20:37 ` Mathieu Desnoyers
2017-11-16 20:46 ` Peter Zijlstra
2017-11-16 21:08 ` Thomas Gleixner
2017-11-19 17:24 ` Mathieu Desnoyers
2017-11-14 20:03 ` [RFC PATCH for 4.15 02/24] Restartable sequences: ARM 32 architecture support Mathieu Desnoyers
2017-11-14 20:03 ` [RFC PATCH for 4.15 03/24] Restartable sequences: wire up ARM 32 system call Mathieu Desnoyers
2017-11-14 20:03 ` [RFC PATCH for 4.15 04/24] Restartable sequences: x86 32/64 architecture support Mathieu Desnoyers
2017-11-16 21:14 ` Thomas Gleixner
2017-11-19 17:41 ` Mathieu Desnoyers
2017-11-20 8:38 ` Thomas Gleixner
2017-11-14 20:03 ` [RFC PATCH for 4.15 05/24] Restartable sequences: wire up x86 32/64 system call Mathieu Desnoyers
2017-11-14 20:03 ` [RFC PATCH for 4.15 06/24] Restartable sequences: powerpc architecture support Mathieu Desnoyers
2017-11-14 20:03 ` [RFC PATCH for 4.15 07/24] Restartable sequences: Wire up powerpc system call Mathieu Desnoyers
2017-11-14 20:03 ` [RFC PATCH v3 for 4.15 08/24] Provide cpu_opv " Mathieu Desnoyers
2017-11-15 1:34 ` Mathieu Desnoyers
2017-11-15 7:44 ` Michael Kerrisk (man-pages)
2017-11-15 14:30 ` Mathieu Desnoyers
2017-11-16 23:26 ` Thomas Gleixner
2017-11-17 0:14 ` Andi Kleen
2017-11-17 10:09 ` Thomas Gleixner
2017-11-17 17:14 ` Mathieu Desnoyers
2017-11-17 18:18 ` Andi Kleen
2017-11-17 18:59 ` Thomas Gleixner
2017-11-17 19:15 ` Andi Kleen [this message]
2017-11-17 20:07 ` Thomas Gleixner
2017-11-18 21:09 ` Andy Lutomirski
2017-11-17 20:22 ` Thomas Gleixner
2017-11-20 17:13 ` Mathieu Desnoyers
2017-11-20 16:13 ` Mathieu Desnoyers
2017-11-20 17:48 ` Thomas Gleixner
2017-11-20 18:03 ` Thomas Gleixner
2017-11-20 18:42 ` Mathieu Desnoyers
2017-11-20 18:39 ` Mathieu Desnoyers
2017-11-20 18:49 ` Andi Kleen
2017-11-20 22:46 ` Mathieu Desnoyers
2017-11-20 19:44 ` Thomas Gleixner
2017-11-21 11:25 ` Mathieu Desnoyers
2017-11-14 20:03 ` [RFC PATCH for 4.15 09/24] cpu_opv: Wire up x86 32/64 " Mathieu Desnoyers
2017-11-14 20:04 ` [RFC PATCH for 4.15 10/24] cpu_opv: Wire up powerpc " Mathieu Desnoyers
2017-11-14 20:04 ` [RFC PATCH for 4.15 11/24] cpu_opv: Wire up ARM32 " Mathieu Desnoyers
2017-11-14 20:04 ` [RFC PATCH v2 for 4.15 12/24] cpu_opv: Implement selftests Mathieu Desnoyers
2017-11-14 20:04 ` [RFC PATCH v2 for 4.15 13/24] Restartable sequences: Provide self-tests Mathieu Desnoyers
2017-11-14 20:04 ` [RFC PATCH for 4.15 14/24] Restartable sequences selftests: arm: workaround gcc asm size guess Mathieu Desnoyers
2017-11-14 20:04 ` [RFC PATCH v2 for 4.15 15/24] membarrier: selftest: Test private expedited cmd Mathieu Desnoyers
2017-11-14 20:04 ` [RFC PATCH v7 for 4.15 16/24] membarrier: powerpc: Skip memory barrier in switch_mm() Mathieu Desnoyers
2017-11-14 20:04 ` [RFC PATCH v5 for 4.15 17/24] membarrier: Document scheduler barrier requirements Mathieu Desnoyers
2017-11-14 20:04 ` [RFC PATCH for 4.15 18/24] membarrier: provide SHARED_EXPEDITED command Mathieu Desnoyers
2017-11-15 1:36 ` Mathieu Desnoyers
2017-11-14 20:04 ` [RFC PATCH for 4.15 19/24] membarrier: selftest: Test shared expedited cmd Mathieu Desnoyers
2017-11-17 15:07 ` Shuah Khan
2017-11-14 20:04 ` [RFC PATCH for 4.15 20/24] membarrier: Provide core serializing command Mathieu Desnoyers
2017-11-14 20:04 ` [RFC PATCH v2 for 4.15 21/24] x86: Introduce sync_core_before_usermode Mathieu Desnoyers
2017-11-14 20:04 ` [RFC PATCH v2 for 4.15 22/24] membarrier: x86: Provide core serializing command Mathieu Desnoyers
2017-11-14 20:04 ` [RFC PATCH for 4.15 23/24] membarrier: selftest: Test private expedited sync core cmd Mathieu Desnoyers
2017-11-17 15:09 ` Shuah Khan
2017-11-17 16:17 ` Mathieu Desnoyers
2017-11-14 20:04 ` [RFC PATCH for 4.15 24/24] membarrier: arm64: Provide core serializing command Mathieu Desnoyers
2017-11-14 21:08 ` [RFC PATCH for 4.15 00/24] Restartable sequences and CPU op vector v11 Linus Torvalds
2017-11-14 21:15 ` Andy Lutomirski
2017-11-14 21:32 ` Paul Turner
2018-03-27 18:15 ` Mathieu Desnoyers
2017-11-14 21:32 ` Mathieu Desnoyers
2017-11-15 4:12 ` Andy Lutomirski
2017-11-15 6:34 ` Mathieu Desnoyers
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=20171117191547.GI2482@two.firstfloor.org \
--to=andi@firstfloor.org \
--cc=ahh@google.com \
--cc=akpm@linux-foundation.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=mtk.manpages@gmail.com \
--cc=paulmck@linux.vnet.ibm.com \
--cc=peterz@infradead.org \
--cc=pjt@google.com \
--cc=rostedt@goodmis.org \
--cc=tglx@linutronix.de \
--cc=torvalds@linux-foundation.org \
--cc=will.deacon@arm.com \
/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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox