Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 23.128.96.18 as permitted sender) client-ip=23.128.96.18;
MIME-Version: 1.0
References: <20210413162240.3131033-1-eric.dumazet@gmail.com>
 <20210413162240.3131033-4-eric.dumazet@gmail.com> <567941475.72456.1618332885342.JavaMail.zimbra@efficios.com>
 <CANn89iJi=RY5HE6+TDvNv0HPEuedtsYHkEZSoEb45EO=tQM2tw@mail.gmail.com>
 <CANn89iKChc2Xf7fnJN0A7OfA7v=S0f6KruB91dKmEPVRhxQyPg@mail.gmail.com>
 <CANn89iKnQ7KeCo0os0c67GMgEkmrRqhmGhug-xL-Mx5BhR+BkQ@mail.gmail.com>
 <989543379.72506.1618334454075.JavaMail.zimbra@efficios.com>
 <CANn89iLXE6V2gpbJeE6KVU+YiNkmYZKjpRxKv8b69k1ECsyE9g@mail.gmail.com>
 <1347243835.72576.1618336812739.JavaMail.zimbra@efficios.com>
 <CANn89iKhKrHgTduwUtZ6QhxE6xFcK=ijadwACg9aSEJ7QQx4Mg@mail.gmail.com>
 <CAOFY-A1=2MzHvmqBEo=WBT6gWc=KnmtCWogjLdwZVDTp-zDjBQ@mail.gmail.com>
 <feed2c13dbe34279a03929a588c46c67@AcuMS.aculab.com> <CAOFY-A21tjC5dWwM0W0aXHij40kKj2JNo5Nq4X8mBZZdKwr+AA@mail.gmail.com>
 <2c6885b0241d4127b8cb7e38abbbe1e5@AcuMS.aculab.com> <CANn89iJj9254GORTsabwv6ZBPWzebR4iYAj9VYxuOZSrF99fNg@mail.gmail.com>
 <1e5576a1a5b24cb0b1d53b9bb22d528e@AcuMS.aculab.com> <CANn89iKmUJRf3FNuk6BhC06Qt-C_RuYfxPUm-1Ho0ztL0KJsLg@mail.gmail.com>
In-Reply-To: <CANn89iKmUJRf3FNuk6BhC06Qt-C_RuYfxPUm-1Ho0ztL0KJsLg@mail.gmail.com>
From:   Arjun Roy <arjunroy@google.com>
Date:   Wed, 14 Apr 2021 10:15:07 -0700
Message-ID: <CAOFY-A1Nff_99-V+W-xyhq3g4kvqXPzM3eWAQV2WpzrxPfjeFw@mail.gmail.com>
Subject: Re: [PATCH v2 3/3] rseq: optimise rseq_get_rseq_cs() and clear_rseq_cs()
To:     Eric Dumazet <edumazet@google.com>
Cc:     David Laight <David.Laight@aculab.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>
Content-Type: text/plain; charset="UTF-8"
Precedence: bulk

On Wed, Apr 14, 2021 at 9:10 AM Eric Dumazet <edumazet@google.com> wrote:
>
> On Wed, Apr 14, 2021 at 6:08 PM David Laight <David.Laight@aculab.com> wrote:
> >
> > From: Eric Dumazet
> > > Sent: 14 April 2021 17:00
> > ...
> > > > 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.
> >
> > It will be x86_64.
> > I'm definitely seeing repeated tests of (IIRC) %rdx.
> >
> > It may well be because the compiler isn't very new.
> > Will be an Ubuntu build of 9.3.0.
> > Does that support 'asm goto with outputs' - which
> > may be the difference.
> >
>
> Yep, probably. I am using some recent clang version.
>

On x86-64 I can confirm, for me it (4 x unsafe_get_user()) compiles
down to stac + lfence + 8 x mov + clac as straight line code. And
results in roughly a 5%-10% speedup over copy_from_user().

-Arjun


> >         David
> >
> > -
> > Registered Address Lakeside, Bramley Road, Mount Farm, Milton Keynes, MK1 1PT, UK
> > Registration No: 1397386 (Wales)