Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 23.128.96.34 as permitted sender) client-ip=23.128.96.34;
MIME-Version: 1.0
References: <20230721161018.50214-1-brgerst@gmail.com> <ZR5yTecBhCFsVOtQ@gmail.com>
 <CAMzpN2j7qddPEUdD+ZX3dtyQkPq6e4gzwcu5szkZ2esh_8zm9g@mail.gmail.com>
 <ZR8an4+JbkLS8/Ol@gmail.com> <5def7e28-3949-9685-7ddf-19b550847ef0@zytor.com>
In-Reply-To: <5def7e28-3949-9685-7ddf-19b550847ef0@zytor.com>
From:   Uros Bizjak <ubizjak@gmail.com>
Date:   Sat, 7 Oct 2023 11:56:58 +0200
Message-ID: <CAFULd4byZBKAUrJ2+5EoEaTHTXpk+0FFeFvze9r+Y1dTezG7YQ@mail.gmail.com>
Subject: Re: [PATCH v2 0/6] x86: Clean up fast syscall return validation
To:     "H. Peter Anvin" <hpa@zytor.com>
Cc:     Ingo Molnar <mingo@kernel.org>, Brian Gerst <brgerst@gmail.com>,
        linux-kernel@vger.kernel.org, x86@kernel.org,
        Thomas Gleixner <tglx@linutronix.de>,
        Borislav Petkov <bp@alien8.de>,
        Andy Lutomirski <luto@kernel.org>,
        =?UTF-8?Q?Mika_Penttil=C3=A4?= <mpenttil@redhat.com>,
        Linus Torvalds <torvalds@linux-foundation.org>,
        Denys Vlasenko <dvlasenk@redhat.com>,
        Peter Zijlstra <peterz@infradead.org>,
        Josh Poimboeuf <jpoimboe@redhat.com>
Content-Type: text/plain; charset="UTF-8"
Content-Transfer-Encoding: quoted-printable
Precedence: bulk

On Fri, Oct 6, 2023 at 8:59=E2=80=AFPM H. Peter Anvin <hpa@zytor.com> wrote=
:
>
> On 10/5/23 13:20, Ingo Molnar wrote:
> >
> > * Brian Gerst <brgerst@gmail.com> wrote:
> >
> >> Looking at the compiled output, the only suboptimal code appears to be
> >> the canonical address test, where the C code uses the CL register for
> >> the shifts instead of immediates.
> >>
> >>   180:   e9 00 00 00 00          jmp    185 <do_syscall_64+0x85>
> >>                          181: R_X86_64_PC32      .altinstr_aux-0x4
> >>   185:   b9 07 00 00 00          mov    $0x7,%ecx
> >>   18a:   eb 05                   jmp    191 <do_syscall_64+0x91>
> >>   18c:   b9 10 00 00 00          mov    $0x10,%ecx
> >>   191:   48 89 c2                mov    %rax,%rdx
> >>   194:   48 d3 e2                shl    %cl,%rdx
> >>   197:   48 d3 fa                sar    %cl,%rdx
> >>   19a:   48 39 d0                cmp    %rdx,%rax
> >>   19d:   75 39                   jne    1d8 <do_syscall_64+0xd8>
> >
> > Yeah, it didn't look equivalent - so I guess we want a C equivalent for=
:
> >
> > -       ALTERNATIVE "shl $(64 - 48), %rcx; sar $(64 - 48), %rcx", \
> > -               "shl $(64 - 57), %rcx; sar $(64 - 57), %rcx", X86_FEATU=
RE_LA57
> >
> > instead of the pgtable_l5_enabled() runtime test that
> > __is_canonical_address() uses?
> >
>
> I don't think such a thing (without simply duplicate the above as an
> alternative asm, which is obviously easy enough, and still allows the
> compiler to pick the register used) would be possible without immediate
> patching support[*].
>
> Incidentally, this is a question for Uros: is there a reason this is a
> mov to %ecx and not just %cl, which would save 3 bytes?

The compiler uses 32-bit mode to move values between registers, even
when they are less than 32-bit wide. To avoid partial register stalls,
it uses 32-bit mode as much as possible (e.g. zero-extends from memory
to load 8-bit value, load of 32-bit constant, etc). Since the kernel
is compiled with -O2, the compiler does not care that much for the
size of instructions, and it uses full 32-bit width to initialize
register with a constant.

Please note that 8-bit movb instruction in fact represents insert into
word-mode register. The compiler does not know how this word-mode
register will be used, so to avoid partial register stalls, it takes a
cautious approach and (with -O2) moves constant to a register with a
word-width instruction.

Also, the compiler is quite eager to CSE constants. When there are two
or more uses of the same constant, it will move a constant into the
register first.

Uros.