All of lore.kernel.org
 help / color / mirror / Atom feed
From: Oleg Nesterov <oleg@redhat.com>
To: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Andy Lutomirski <luto@amacapital.net>,
	"Paul E. McKenney" <paulmck@linux.vnet.ibm.com>,
	LKML <linux-kernel@vger.kernel.org>,
	Kees Cook <keescook@chromium.org>, Will Drewry <wad@chromium.org>,
	the arch/x86 maintainers <x86@kernel.org>,
	"<linux-arm-kernel@lists.infradead.org>"
	<linux-arm-kernel@lists.infradead.org>,
	Linux MIPS Mailing List <linux-mips@linux-mips.org>,
	"linux-arch@vger.kernel.org" <linux-arch@vger.kernel.org>,
	LSM List <linux-security-module@vger.kernel.org>,
	Alexei Starovoitov <ast@plumgrid.com>,
	"H. Peter Anvin" <hpa@zytor.com>
Subject: Re: TIF_NOHZ can escape nonhz mask? (Was: [PATCH v3 6/8] x86: Split syscall_trace_enter into two phases)
Date: Thu, 31 Jul 2014 21:05:18 +0200	[thread overview]
Message-ID: <20140731190518.GA21938@redhat.com> (raw)
In-Reply-To: <CAFTL4hyHh3Bw0eeJe9q50HVrt=B-zgmyu6C_hy+RoW21kQEJtg@mail.gmail.com>

On 07/31, Frederic Weisbecker wrote:
>
> 2014-07-31 20:47 GMT+02:00 Frederic Weisbecker <fweisbec@gmail.com>:
> > On Thu, Jul 31, 2014 at 08:12:30PM +0200, Oleg Nesterov wrote:
> >> On 07/31, Frederic Weisbecker wrote:
> > No, because preempt_schedule_irq() does the ctx_state save and restore with
> > exception_enter/exception_exit.
>
> Similar thing happens with schedule_user().
>
> preempt_schedule_irq() handles kernel preemption and schedule_user()
> the user preemption. On both cases we save and restore the context
> tracking state.
>
> This might be the missing piece you were missing :)

YYYYYEEEEESSSS, thanks!!

And in fact I was going to suggest to add this logic into preempt schedule
paths to improve the situation if we can't make TIF_NOHZ per-cpu.

But Frederic, perhaps I'll return here tomorrow with another question, it
is too late for me now ;)

Thanks!

Oleg.

WARNING: multiple messages have this Message-ID (diff)
From: oleg@redhat.com (Oleg Nesterov)
To: linux-arm-kernel@lists.infradead.org
Subject: TIF_NOHZ can escape nonhz mask? (Was: [PATCH v3 6/8] x86: Split syscall_trace_enter into two phases)
Date: Thu, 31 Jul 2014 21:05:18 +0200	[thread overview]
Message-ID: <20140731190518.GA21938@redhat.com> (raw)
In-Reply-To: <CAFTL4hyHh3Bw0eeJe9q50HVrt=B-zgmyu6C_hy+RoW21kQEJtg@mail.gmail.com>

On 07/31, Frederic Weisbecker wrote:
>
> 2014-07-31 20:47 GMT+02:00 Frederic Weisbecker <fweisbec@gmail.com>:
> > On Thu, Jul 31, 2014 at 08:12:30PM +0200, Oleg Nesterov wrote:
> >> On 07/31, Frederic Weisbecker wrote:
> > No, because preempt_schedule_irq() does the ctx_state save and restore with
> > exception_enter/exception_exit.
>
> Similar thing happens with schedule_user().
>
> preempt_schedule_irq() handles kernel preemption and schedule_user()
> the user preemption. On both cases we save and restore the context
> tracking state.
>
> This might be the missing piece you were missing :)

YYYYYEEEEESSSS, thanks!!

And in fact I was going to suggest to add this logic into preempt schedule
paths to improve the situation if we can't make TIF_NOHZ per-cpu.

But Frederic, perhaps I'll return here tomorrow with another question, it
is too late for me now ;)

Thanks!

Oleg.

  reply	other threads:[~2014-07-31 19:05 UTC|newest]

Thread overview: 82+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2014-07-22  1:49 [PATCH v3 0/8] Two-phase seccomp and x86 tracing changes Andy Lutomirski
2014-07-22  1:49 ` Andy Lutomirski
2014-07-22  1:49 ` [PATCH v3 1/8] seccomp,x86,arm,mips,s390: Remove nr parameter from secure_computing Andy Lutomirski
2014-07-22  1:49   ` [PATCH v3 1/8] seccomp, x86, arm, mips, s390: " Andy Lutomirski
2014-07-22  1:49 ` [PATCH v3 2/8] seccomp: Refactor the filter callback and the API Andy Lutomirski
2014-07-22  1:49   ` Andy Lutomirski
2014-07-22  1:49 ` [PATCH v3 3/8] seccomp: Allow arch code to provide seccomp_data Andy Lutomirski
2014-07-22  1:49   ` Andy Lutomirski
2014-07-22  1:49 ` [PATCH v3 4/8] seccomp: Document two-phase seccomp and arch-provided seccomp_data Andy Lutomirski
2014-07-22  1:49   ` Andy Lutomirski
2014-07-22  1:49   ` Andy Lutomirski
2014-07-22  1:53 ` [PATCH v3 5/8] x86,x32,audit: Fix x32's AUDIT_ARCH wrt audit Andy Lutomirski
2014-07-22  1:53   ` Andy Lutomirski
2014-07-22  1:53 ` [PATCH v3 6/8] x86: Split syscall_trace_enter into two phases Andy Lutomirski
2014-07-22  1:53   ` Andy Lutomirski
2014-07-28 17:37   ` Oleg Nesterov
2014-07-28 17:37     ` Oleg Nesterov
2014-07-28 18:58     ` TIF_NOHZ can escape nonhz mask? (Was: [PATCH v3 6/8] x86: Split syscall_trace_enter into two phases) Oleg Nesterov
2014-07-28 18:58       ` Oleg Nesterov
2014-07-28 19:22       ` Frederic Weisbecker
2014-07-28 19:22         ` Frederic Weisbecker
2014-07-29 17:54         ` Oleg Nesterov
2014-07-29 17:54           ` Oleg Nesterov
2014-07-30 16:35           ` Frederic Weisbecker
2014-07-30 16:35             ` Frederic Weisbecker
2014-07-30 17:46             ` Oleg Nesterov
2014-07-30 17:46               ` Oleg Nesterov
2014-07-31  0:30               ` Frederic Weisbecker
2014-07-31  0:30                 ` Frederic Weisbecker
2014-07-31 16:03                 ` Oleg Nesterov
2014-07-31 16:03                   ` Oleg Nesterov
2014-07-31 17:13                   ` Frederic Weisbecker
2014-07-31 17:13                     ` Frederic Weisbecker
2014-07-31 18:12                     ` Oleg Nesterov
2014-07-31 18:12                       ` Oleg Nesterov
2014-07-31 18:47                       ` Frederic Weisbecker
2014-07-31 18:47                         ` Frederic Weisbecker
2014-07-31 18:50                         ` Frederic Weisbecker
2014-07-31 18:50                           ` Frederic Weisbecker
2014-07-31 19:05                           ` Oleg Nesterov [this message]
2014-07-31 19:05                             ` Oleg Nesterov
2014-08-02 17:30                         ` Oleg Nesterov
2014-08-02 17:30                           ` Oleg Nesterov
2014-08-04 12:02                           ` Paul E. McKenney
2014-08-04 12:02                             ` Paul E. McKenney
2014-08-04 12:02                             ` Paul E. McKenney
2014-07-28 20:23     ` [PATCH v3 6/8] x86: Split syscall_trace_enter into two phases Andy Lutomirski
2014-07-28 20:23       ` Andy Lutomirski
2014-07-29 16:54       ` Oleg Nesterov
2014-07-29 16:54         ` Oleg Nesterov
2014-07-29 17:01         ` Andy Lutomirski
2014-07-29 17:01           ` Andy Lutomirski
2014-07-29 17:31           ` Oleg Nesterov
2014-07-29 17:31             ` Oleg Nesterov
2014-07-29 17:55             ` Andy Lutomirski
2014-07-29 17:55               ` Andy Lutomirski
2014-07-29 18:16               ` Oleg Nesterov
2014-07-29 18:16                 ` Oleg Nesterov
2014-07-29 18:22                 ` Andy Lutomirski
2014-07-29 18:22                   ` Andy Lutomirski
2014-07-29 18:44                   ` Oleg Nesterov
2014-07-29 18:44                     ` Oleg Nesterov
2014-07-22  1:53 ` [PATCH v3 7/8] x86_64,entry: Treat regs->ax the same in fastpath and slowpath syscalls Andy Lutomirski
2014-07-22  1:53   ` [PATCH v3 7/8] x86_64, entry: " Andy Lutomirski
2014-07-22  1:53 ` [PATCH v3 8/8] x86_64,entry: Use split-phase syscall_trace_enter for 64-bit syscalls Andy Lutomirski
2014-07-22  1:53   ` [PATCH v3 8/8] x86_64, entry: " Andy Lutomirski
2014-07-22 19:37 ` [PATCH v3 0/8] Two-phase seccomp and x86 tracing changes Kees Cook
2014-07-22 19:37   ` Kees Cook
2014-07-23 19:20   ` Andy Lutomirski
2014-07-23 19:20     ` Andy Lutomirski
2014-07-28 17:59     ` H. Peter Anvin
2014-07-28 17:59       ` H. Peter Anvin
2014-07-28 23:29       ` Kees Cook
2014-07-28 23:29         ` Kees Cook
2014-07-28 23:34         ` H. Peter Anvin
2014-07-28 23:34           ` H. Peter Anvin
2014-07-28 23:42           ` Kees Cook
2014-07-28 23:42             ` Kees Cook
2014-07-28 23:45             ` H. Peter Anvin
2014-07-28 23:45               ` H. Peter Anvin
2014-07-28 23:54               ` Kees Cook
2014-07-28 23:54                 ` Kees Cook

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=20140731190518.GA21938@redhat.com \
    --to=oleg@redhat.com \
    --cc=ast@plumgrid.com \
    --cc=fweisbec@gmail.com \
    --cc=hpa@zytor.com \
    --cc=keescook@chromium.org \
    --cc=linux-arch@vger.kernel.org \
    --cc=linux-arm-kernel@lists.infradead.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mips@linux-mips.org \
    --cc=linux-security-module@vger.kernel.org \
    --cc=luto@amacapital.net \
    --cc=paulmck@linux.vnet.ibm.com \
    --cc=wad@chromium.org \
    --cc=x86@kernel.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.