From: Eric Dumazet <edumazet@google.com>
To: David Laight <David.Laight@aculab.com>
Cc: Arjun Roy <arjunroy@google.com>,
Mathieu Desnoyers <mathieu.desnoyers@efficios.com>,
Eric Dumazet <eric.dumazet@gmail.com>,
Ingo Molnar <mingo@kernel.org>,
Peter Zijlstra <peterz@infradead.org>,
paulmck <paulmck@kernel.org>, Boqun Feng <boqun.feng@gmail.com>,
linux-kernel <linux-kernel@vger.kernel.org>
Subject: Re: [PATCH v2 3/3] rseq: optimise rseq_get_rseq_cs() and clear_rseq_cs()
Date: Wed, 14 Apr 2021 18:00:28 +0200 [thread overview]
Message-ID: <CANn89iJj9254GORTsabwv6ZBPWzebR4iYAj9VYxuOZSrF99fNg@mail.gmail.com> (raw)
In-Reply-To: <2c6885b0241d4127b8cb7e38abbbe1e5@AcuMS.aculab.com>
On Wed, Apr 14, 2021 at 9:55 AM David Laight <David.Laight@aculab.com> wrote:
>
> From: Arjun Roy
> > Sent: 13 April 2021 23:04
> >
> > On Tue, Apr 13, 2021 at 2:19 PM David Laight <David.Laight@aculab.com> wrote:
> > >
> > > > If we're special-casing 64-bit architectures anyways - unrolling the
> > > > 32B copy_from_user() for struct rseq_cs appears to be roughly 5-10%
> > > > savings on x86-64 when I measured it (well, in a microbenchmark, not
> > > > in rseq_get_rseq_cs() directly). Perhaps that could be an additional
> > > > avenue for improvement here.
> > >
> > > The killer is usually 'user copy hardening'.
> > > It significantly slows down sendmsg() and recvmsg().
> > > I've got measurable performance improvements by
> > > using __copy_from_user() when the buffer since has
> > > already been checked - but isn't a compile-time constant.
> > >
> > > There is also scope for using _get_user() when reading
> > > iovec[] (instead of copy_from_user()) and doing all the
> > > bound checks (etc) in the loop.
> > > That gives a measurable improvement for writev("/dev/null").
> > > I must sort those patches out again.
> > >
> > > David
> > >
> >
> > In this case I mean replacing copy_from_user(rseq_cs, urseq_cs,
> > sizeof(*rseq_cs)) with 4 (x8B=32 total) unsafe_get_user() (wrapped in
> > user_read_access_begin/end()) which I think would just bypass user
> > copy hardening (as far as I can tell).
>
> Yes that is one advantage over any of the get_user() calls.
> You also lose all the 'how shall we optimise this' checks
> in copy_from_user().
>
> Repeated unsafe_get_user() calls are crying out for an optimisation.
> You get something like:
> failed = 0;
> copy();
> if (failed) goto error;
> copy();
> if (failed) goto error;
> Where 'failed' is set by the fault handler.
>
> This could be optimised to:
> failed = 0;
> copy();
> copy();
> if (failed) goto error;
> Even if it faults on every invalid address it probably
> doesn't matter - no one cares about that path.
On which arch are you looking at ?
On x86_64 at least, code generation is just perfect.
Not even a conditional jmp, it is all handled by exceptions (if any)
stac
copy();
copy();
clac
<out_of_line>
efault_end: do error recovery.
>
> I've not really looked at how it could be achieved though.
>
> It might be that the 'asm goto with outputs' variant
> manages to avoid the compare and jump.
>
> David
>
> -
> Registered Address Lakeside, Bramley Road, Mount Farm, Milton Keynes, MK1 1PT, UK
> Registration No: 1397386 (Wales)
next prev parent reply other threads:[~2021-04-14 16:00 UTC|newest]
Thread overview: 26+ messages / expand[flat|nested] mbox.gz Atom feed top
2021-04-13 16:22 [PATCH v2 0/3] rseq: minor optimizations Eric Dumazet
2021-04-13 16:22 ` [PATCH v2 1/3] rseq: optimize rseq_update_cpu_id() Eric Dumazet
2021-04-13 16:22 ` [PATCH v2 2/3] rseq: remove redundant access_ok() Eric Dumazet
2021-04-13 16:22 ` [PATCH v2 3/3] rseq: optimise rseq_get_rseq_cs() and clear_rseq_cs() Eric Dumazet
2021-04-13 16:54 ` Mathieu Desnoyers
2021-04-13 16:57 ` Eric Dumazet
2021-04-13 17:01 ` Eric Dumazet
2021-04-13 17:07 ` Eric Dumazet
2021-04-13 17:20 ` Mathieu Desnoyers
2021-04-13 17:33 ` Eric Dumazet
2021-04-13 18:00 ` Mathieu Desnoyers
2021-04-13 18:22 ` Eric Dumazet
2021-04-13 18:35 ` Arjun Roy
2021-04-13 21:19 ` David Laight
2021-04-13 22:03 ` Arjun Roy
2021-04-14 7:55 ` David Laight
2021-04-14 16:00 ` Eric Dumazet [this message]
2021-04-14 16:08 ` David Laight
2021-04-14 16:10 ` Eric Dumazet
2021-04-14 17:15 ` Arjun Roy
2021-04-14 17:35 ` Eric Dumazet
2021-04-14 20:15 ` Arjun Roy
2021-04-14 20:25 ` Eric Dumazet
2021-04-14 20:35 ` Arjun Roy
2021-04-13 19:13 ` Mathieu Desnoyers
2021-04-13 17:06 ` 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=CANn89iJj9254GORTsabwv6ZBPWzebR4iYAj9VYxuOZSrF99fNg@mail.gmail.com \
--to=edumazet@google.com \
--cc=David.Laight@aculab.com \
--cc=arjunroy@google.com \
--cc=boqun.feng@gmail.com \
--cc=eric.dumazet@gmail.com \
--cc=linux-kernel@vger.kernel.org \
--cc=mathieu.desnoyers@efficios.com \
--cc=mingo@kernel.org \
--cc=paulmck@kernel.org \
--cc=peterz@infradead.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.