Groups | Search | Server Info | Keyboard shortcuts | Login | Register [http] [https] [nntp] [nntps]

Groups > linux.kernel > #1346144

Re: [PATCH 02/10] x86/entry/compat: In SYSENTER, sink AC clearing below the existing FLAGS test

Show all headers | View raw

On Sun, Feb 28, 2016 at 09:28:47PM -0800, Andy Lutomirski wrote:
> CLAC is slow, and the SYSENTER code already has an unlikely path
> that runs if unusual flags are set.  Drop the CLAC and instead rely
> on the unlikely path to clear AC.
> 
> This seems to save ~24 cycles on my Skylake laptop.  (Hey, Intel,
> make this faster please!)
> 
> Signed-off-by: Andy Lutomirski <luto@kernel.org>
> ---
>  arch/x86/entry/entry_64_compat.S | 8 +++-----
>  1 file changed, 3 insertions(+), 5 deletions(-)
> 
> diff --git a/arch/x86/entry/entry_64_compat.S b/arch/x86/entry/entry_64_compat.S
> index 89bcb4979e7a..7c8e72da7654 100644
> --- a/arch/x86/entry/entry_64_compat.S
> +++ b/arch/x86/entry/entry_64_compat.S
> @@ -66,8 +66,6 @@ ENTRY(entry_SYSENTER_compat)
>  	 */
>  	pushfq				/* pt_regs->flags (except IF = 0) */
>  	orl	$X86_EFLAGS_IF, (%rsp)	/* Fix saved flags */
> -	ASM_CLAC			/* Clear AC after saving FLAGS */
> -
>  	pushq	$__USER32_CS		/* pt_regs->cs */
>  	xorq    %r8,%r8
>  	pushq	%r8			/* pt_regs->ip = 0 (placeholder) */
> @@ -90,9 +88,9 @@ ENTRY(entry_SYSENTER_compat)
>  	cld
>  
>  	/*
> -	 * Sysenter doesn't filter flags, so we need to clear NT
> +	 * Sysenter doesn't filter flags, so we need to clear NT and AC
>  	 * ourselves.  To save a few cycles, we can check whether
> -	 * NT was set instead of doing an unconditional popfq.
> +	 * either was set instead of doing an unconditional popfq.
>  	 * This needs to happen before enabling interrupts so that
>  	 * we don't get preempted with NT set.
>  	 *
> @@ -102,7 +100,7 @@ ENTRY(entry_SYSENTER_compat)
>  	 * we're keeping that code behind a branch which will predict as
>  	 * not-taken and therefore its instructions won't be fetched.
>  	 */
> -	testl	$X86_EFLAGS_NT, EFLAGS(%rsp)
> +	testl	$X86_EFLAGS_NT|X86_EFLAGS_AC, EFLAGS(%rsp)
>  	jnz	.Lsysenter_fix_flags
>  .Lsysenter_flags_fixed:

Do I see it correctly that with this change, that .Lsysenter_fix_flags:
is going to be visited each time on SMAP machines and then we can get
rid of it? The reason for it was not to pollute I$ as the comment says
but that happening now anyway...

-- 
Regards/Gruss,
    Boris.

ECO tip #101: Trim your mails when you reply.

Back to linux.kernel | Previous | Next — Previous in thread | Next in thread | Find similar | Unroll thread

Thread

[PATCH 00/10] x86: Various SYSENTER/SYSEXIT/#DB fixes and cleanups Andy Lutomirski <luto@kernel.org> - 2016-02-29 06:40 +0100
  [PATCH 06/10] x86/traps: Clear DR6 early in do_debug and improve the comment Andy Lutomirski <luto@kernel.org> - 2016-02-29 06:40 +0100
  [PATCH 08/10] x86/entry: Only allocate space for SYSENTER_stack if needed Andy Lutomirski <luto@kernel.org> - 2016-02-29 06:40 +0100
  [PATCH 02/10] x86/entry/compat: In SYSENTER, sink AC clearing below the existing FLAGS test Andy Lutomirski <luto@kernel.org> - 2016-02-29 06:40 +0100
    Re: [PATCH 02/10] x86/entry/compat: In SYSENTER, sink AC clearing  below the existing FLAGS test Borislav Petkov <bp@alien8.de> - 2016-02-29 21:40 +0100
      Re: [PATCH 02/10] x86/entry/compat: In SYSENTER, sink AC clearing  below the existing FLAGS test Andy Lutomirski <luto@amacapital.net> - 2016-02-29 21:50 +0100
        Re: [PATCH 02/10] x86/entry/compat: In SYSENTER, sink AC clearing  below the existing FLAGS test Borislav Petkov <bp@alien8.de> - 2016-02-29 23:10 +0100
          Re: [PATCH 02/10] x86/entry/compat: In SYSENTER, sink AC clearing  below the existing FLAGS test Borislav Petkov <bp@alien8.de> - 2016-02-29 23:40 +0100
          Re: [PATCH 02/10] x86/entry/compat: In SYSENTER, sink AC clearing  below the existing FLAGS test Brian Gerst <brgerst@gmail.com> - 2016-02-29 23:40 +0100
  Re: [PATCH 00/10] x86: Various SYSENTER/SYSEXIT/#DB fixes and cleanups Andy Lutomirski <luto@amacapital.net> - 2016-02-29 20:00 +0100

csiph-web