All of lore.kernel.org
 help / color / mirror / Atom feed
From: Oleg Nesterov <oleg@redhat.com>
To: Andy Lutomirski <luto@amacapital.net>
Cc: "H. Peter Anvin" <hpa@zytor.com>,
	linux-arch <linux-arch@vger.kernel.org>, X86 ML <x86@kernel.org>,
	Frederic Weisbecker <fweisbec@gmail.com>,
	LSM List <linux-security-module@vger.kernel.org>,
	Linux MIPS Mailing List <linux-mips@linux-mips.org>,
	"linux-arm-kernel@lists.infradead.org" 
	<linux-arm-kernel@lists.infradead.org>,
	Alexei Starovoitov <ast@plumgrid.com>,
	Will Drewry <wad@chromium.org>, Kees Cook <keescook@chromium.org>,
	"linux-kernel@vger.kernel.org" <linux-kernel@vger.kernel.org>
Subject: Re: [PATCH v4 0/5] x86: two-phase syscall tracing and seccomp fastpath
Date: Wed, 30 Jul 2014 17:32:59 +0200	[thread overview]
Message-ID: <20140730153259.GA25478@redhat.com> (raw)
In-Reply-To: <CALCETrXHF5YzPQDvnJs=mFNm2Ff_FekGu_Y8-JyMaWh2hctR7A@mail.gmail.com>

On 07/29, Andy Lutomirski wrote:
>
> > SAVE_REST is 6 movq instructions and a subq.  FIXUP_TOP_OF_STACK is 7
> > movqs (and 8 if I ever get my way).  RESTORE_TOP_OF_STACK is 4.
> > RESTORE_REST is 6 movqs and an adsq.  So we're talking about avoiding
> > 21 movqs, and addq, and a subq.  That may be significant.  (And I
> > suspect that the difference is much larger on platforms like arm64,
> > but that's a separate issue.)

OK, thanks. We could probably simplify the logic in phase1 + phase2 if
it was a single function though.

> To put some more options on the table: there's an argument to be made
> that the whole fast-path/slow-path split isn't worth it.  We could
> unconditionally set up a full frame for all syscalls.  This means:

Or, at least, can't we allocate the full frame and avoid "add/sub %rsp"?

> This means:
...
> On the
> other hand, there's zero chance that this would be ready for 3.17.
>
> I'd tend to advocate for keeping the approach in my patches for now.

Yes, sure, I didn't try to convince you to change this code. Thanks.

Oleg.


WARNING: multiple messages have this Message-ID (diff)
From: oleg@redhat.com (Oleg Nesterov)
To: linux-arm-kernel@lists.infradead.org
Subject: [PATCH v4 0/5] x86: two-phase syscall tracing and seccomp fastpath
Date: Wed, 30 Jul 2014 17:32:59 +0200	[thread overview]
Message-ID: <20140730153259.GA25478@redhat.com> (raw)
In-Reply-To: <CALCETrXHF5YzPQDvnJs=mFNm2Ff_FekGu_Y8-JyMaWh2hctR7A@mail.gmail.com>

On 07/29, Andy Lutomirski wrote:
>
> > SAVE_REST is 6 movq instructions and a subq.  FIXUP_TOP_OF_STACK is 7
> > movqs (and 8 if I ever get my way).  RESTORE_TOP_OF_STACK is 4.
> > RESTORE_REST is 6 movqs and an adsq.  So we're talking about avoiding
> > 21 movqs, and addq, and a subq.  That may be significant.  (And I
> > suspect that the difference is much larger on platforms like arm64,
> > but that's a separate issue.)

OK, thanks. We could probably simplify the logic in phase1 + phase2 if
it was a single function though.

> To put some more options on the table: there's an argument to be made
> that the whole fast-path/slow-path split isn't worth it.  We could
> unconditionally set up a full frame for all syscalls.  This means:

Or, at least, can't we allocate the full frame and avoid "add/sub %rsp"?

> This means:
...
> On the
> other hand, there's zero chance that this would be ready for 3.17.
>
> I'd tend to advocate for keeping the approach in my patches for now.

Yes, sure, I didn't try to convince you to change this code. Thanks.

Oleg.

  reply	other threads:[~2014-07-30 15:35 UTC|newest]

Thread overview: 62+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2014-07-29  3:38 [PATCH v4 0/5] x86: two-phase syscall tracing and seccomp fastpath Andy Lutomirski
2014-07-29  3:38 ` Andy Lutomirski
2014-07-29  3:38 ` [PATCH v4 1/5] x86,x32,audit: Fix x32's AUDIT_ARCH wrt audit Andy Lutomirski
2014-07-29  3:38   ` Andy Lutomirski
2014-07-29  3:38 ` [PATCH v4 2/5] x86,entry: Only call user_exit if TIF_NOHZ Andy Lutomirski
2014-07-29  3:38   ` Andy Lutomirski
2014-07-29 19:32   ` Oleg Nesterov
2014-07-29 19:32     ` Oleg Nesterov
2014-07-30 16:43     ` Frederic Weisbecker
2014-07-30 16:43       ` Frederic Weisbecker
2014-07-30 17:23       ` Andy Lutomirski
2014-07-30 17:23         ` Andy Lutomirski
2014-07-30 17:23         ` Andy Lutomirski
2014-07-31 15:16         ` Frederic Weisbecker
2014-07-31 15:16           ` Frederic Weisbecker
2014-07-31 15:16           ` Frederic Weisbecker
2014-07-31 16:42           ` Oleg Nesterov
2014-07-31 16:42             ` Oleg Nesterov
2014-07-31 16:42             ` Oleg Nesterov
2014-07-31 16:49             ` Frederic Weisbecker
2014-07-31 16:49               ` Frederic Weisbecker
2014-07-31 16:49               ` Frederic Weisbecker
2014-07-31 16:54               ` Oleg Nesterov
2014-07-31 16:54                 ` Oleg Nesterov
2014-07-31 16:54                 ` Oleg Nesterov
2014-07-31 16:58                 ` Oleg Nesterov
2014-07-31 16:58                   ` Oleg Nesterov
2014-07-31 16:58                   ` Oleg Nesterov
2014-07-31 17:17                 ` Frederic Weisbecker
2014-07-31 17:17                   ` Frederic Weisbecker
2014-07-31 17:17                   ` Frederic Weisbecker
2014-07-29  3:38 ` [PATCH v4 3/5] x86: Split syscall_trace_enter into two phases Andy Lutomirski
2014-07-29  3:38   ` Andy Lutomirski
2014-07-29 19:25   ` Oleg Nesterov
2014-07-29 19:25     ` Oleg Nesterov
2014-07-29  3:38 ` [PATCH v4 4/5] x86_64,entry: Treat regs->ax the same in fastpath and slowpath syscalls Andy Lutomirski
2014-07-29  3:38   ` [PATCH v4 4/5] x86_64, entry: " Andy Lutomirski
2014-07-29  3:38 ` [PATCH v4 5/5] x86_64,entry: Use split-phase syscall_trace_enter for 64-bit syscalls Andy Lutomirski
2014-07-29  3:38   ` [PATCH v4 5/5] x86_64, entry: " Andy Lutomirski
2014-07-29 19:20 ` [PATCH v4 0/5] x86: two-phase syscall tracing and seccomp fastpath Oleg Nesterov
2014-07-29 19:20   ` Oleg Nesterov
2014-07-29 20:54   ` Andy Lutomirski
2014-07-29 20:54     ` Andy Lutomirski
2014-07-29 20:54     ` Andy Lutomirski
2014-07-29 23:30     ` Andy Lutomirski
2014-07-29 23:30       ` Andy Lutomirski
2014-07-29 23:30       ` Andy Lutomirski
2014-07-30 15:32       ` Oleg Nesterov [this message]
2014-07-30 15:32         ` Oleg Nesterov
2014-07-30 15:32         ` Oleg Nesterov
2014-07-30 16:59       ` Frederic Weisbecker
2014-07-30 16:59         ` Frederic Weisbecker
2014-07-30 16:59         ` Frederic Weisbecker
2014-07-30 17:25         ` Andy Lutomirski
2014-07-30 17:25           ` Andy Lutomirski
2014-07-30 17:25           ` Andy Lutomirski
2014-07-31 16:56           ` H. Peter Anvin
2014-07-31 16:56             ` H. Peter Anvin
2014-07-31 16:56             ` H. Peter Anvin
2014-07-31 17:20             ` Frederic Weisbecker
2014-07-31 17:20               ` Frederic Weisbecker
2014-07-31 17:20               ` Frederic Weisbecker

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=20140730153259.GA25478@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=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.