linux-kernel.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Brian Gerst <brgerst@gmail.com>
To: Andy Lutomirski <luto@kernel.org>
Cc: X86 ML <x86@kernel.org>, Borislav Petkov <bpetkov@suse.de>,
	"linux-kernel@vger.kernel.org" <linux-kernel@vger.kernel.org>,
	Dave Hansen <dave.hansen@intel.com>,
	Linus Torvalds <torvalds@linux-foundation.org>
Subject: Re: [PATCH 07/18] x86/asm/64: Merge the fast and slow SYSRET paths
Date: Wed, 1 Nov 2017 13:25:22 -0400	[thread overview]
Message-ID: <CAMzpN2hw6q5G7A-2vb7mHqECf4-Vd8D7XEVGXg7U-Mi06qY_4w@mail.gmail.com> (raw)
In-Reply-To: <998a8c2c39546115f93e4c6e2ad7f918626f6145.1509006199.git.luto@kernel.org>

On Thu, Oct 26, 2017 at 4:26 AM, Andy Lutomirski <luto@kernel.org> wrote:
> They did almost the same thing.  Remove a bunch of pointless
> instructions (mostly hidden in macros) and reduce cognitive load by
> merging them.
>
> Signed-off-by: Andy Lutomirski <luto@kernel.org>
> ---
>  arch/x86/entry/entry_64.S | 6 +++---
>  1 file changed, 3 insertions(+), 3 deletions(-)
>
> diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S
> index 9dafafa3e0ec..c855ee91a3a5 100644
> --- a/arch/x86/entry/entry_64.S
> +++ b/arch/x86/entry/entry_64.S
> @@ -220,10 +220,9 @@ entry_SYSCALL_64_fastpath:
>         TRACE_IRQS_ON           /* user mode is traced as IRQs on */
>         movq    RIP(%rsp), %rcx
>         movq    EFLAGS(%rsp), %r11
> -       RESTORE_C_REGS_EXCEPT_RCX_R11
> -       movq    RSP(%rsp), %rsp
> +       addq    $6*8, %rsp      /* skip extra regs -- they were preserved */
>         UNWIND_HINT_EMPTY
> -       USERGS_SYSRET64
> +       jmp     .Lpop_c_regs_except_rcx_r11_and_sysret
>
>  1:
>         /*
> @@ -315,6 +314,7 @@ syscall_return_via_sysret:
>         /* rcx and r11 are already restored (see code above) */
>         UNWIND_HINT_EMPTY
>         POP_EXTRA_REGS
> +.Lpop_c_regs_except_rcx_r11_and_sysret:
>         popq    %rsi    /* skip r11 */
>         popq    %r10
>         popq    %r9

Wouldn't it be more logical to keep the SYSRET path at the end of the
fast path (reverse of what you are doing here)?  That way the fast
path falls through without jumping.

--
Brian Gerst

  parent reply	other threads:[~2017-11-01 17:25 UTC|newest]

Thread overview: 57+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2017-10-26  8:26 [PATCH 00/18] Pile o' entry/exit/sp0 changes Andy Lutomirski
2017-10-26  8:26 ` [PATCH 01/18] x86/asm/64: Remove the restore_c_regs_and_iret label Andy Lutomirski
2017-10-26 15:07   ` Borislav Petkov
2017-11-10  6:08   ` [01/18] " kemi
2017-10-26  8:26 ` [PATCH 02/18] x86/asm/64: Split the iret-to-user and iret-to-kernel paths Andy Lutomirski
2017-10-27 18:05   ` Dave Hansen
2017-11-01 11:34     ` Andy Lutomirski
2017-10-27 20:04   ` Borislav Petkov
2017-11-01 11:32     ` Andy Lutomirski
2017-10-26  8:26 ` [PATCH 03/18] x86/asm/64: Move SWAPGS into the common iret-to-usermode path Andy Lutomirski
2017-10-26 13:52   ` Brian Gerst
2017-10-26 14:13     ` Dave Hansen
2017-10-26 14:28       ` Borislav Petkov
2017-10-27 15:44         ` Andy Lutomirski
2017-10-27 18:08   ` Dave Hansen
2017-10-26  8:26 ` [PATCH 04/18] x86/asm/64: Simplify reg restore code in the standard IRET paths Andy Lutomirski
2017-10-26  8:26 ` [PATCH 05/18] x86/asm/64: Shrink paranoid_exit_restore and make labels local Andy Lutomirski
2017-10-27 20:07   ` Borislav Petkov
2017-10-26  8:26 ` [PATCH 06/18] x86/asm/64: Use pop instead of movq in syscall_return_via_sysret Andy Lutomirski
2017-10-27 20:11   ` Borislav Petkov
2017-10-26  8:26 ` [PATCH 07/18] x86/asm/64: Merge the fast and slow SYSRET paths Andy Lutomirski
2017-10-27 20:11   ` Borislav Petkov
2017-11-01 11:29     ` Andy Lutomirski
2017-11-01 12:35       ` Borislav Petkov
2017-11-01 17:26         ` Thomas Gleixner
2017-11-01 17:25   ` Brian Gerst [this message]
2017-11-01 20:35     ` Andy Lutomirski
2017-10-26  8:26 ` [PATCH 08/18] xen: add xen nmi trap entry Andy Lutomirski
2017-10-26  8:26 ` [PATCH 09/18] x86/asm/64: De-Xen-ify our NMI code Andy Lutomirski
2017-10-26  8:41   ` Juergen Gross
2017-10-27 20:11   ` Borislav Petkov
2017-10-26  8:26 ` [PATCH 10/18] x86/asm/32: Pull MSR_IA32_SYSENTER_CS update code out of native_load_sp0() Andy Lutomirski
2017-10-26 18:00   ` Brian Gerst
2017-10-27 13:51   ` Thomas Gleixner
2017-10-27 15:50     ` Andy Lutomirski
2017-10-27 20:11   ` Borislav Petkov
2017-10-26  8:26 ` [PATCH 11/18] x86/asm/64: Pass sp0 directly to load_sp0() Andy Lutomirski
2017-10-27 20:12   ` Borislav Petkov
2017-10-26  8:26 ` [PATCH 12/18] x86/asm: Add task_top_of_stack() to find the top of a task's stack Andy Lutomirski
2017-10-26  8:26 ` [PATCH 13/18] x86/xen/64: Clean up SP code in cpu_initialize_context() Andy Lutomirski
2017-10-26  8:43   ` Juergen Gross
2017-10-26  8:26 ` [PATCH 14/18] x86/boot/64: Stop initializing TSS.sp0 at boot Andy Lutomirski
2017-10-27 18:21   ` Dave Hansen
2017-10-28  8:10     ` Andy Lutomirski
2017-10-26  8:26 ` [PATCH 15/18] x86/asm/64: Remove all remaining direct thread_struct::sp0 reads Andy Lutomirski
2017-11-01 10:08   ` Borislav Petkov
2017-10-26  8:26 ` [PATCH 16/18] x86/boot/32: Fix cpu_current_top_of_stack initialization at boot Andy Lutomirski
2017-11-01 10:18   ` Borislav Petkov
2017-10-26  8:26 ` [PATCH 17/18] x86/asm/64: Remove thread_struct::sp0 Andy Lutomirski
2017-10-28  0:52   ` Brian Gerst
2017-11-01 10:23   ` Borislav Petkov
2017-11-01 10:40     ` Andy Lutomirski
2017-10-26  8:26 ` [PATCH 18/18] x86/traps: Use a new on_thread_stack() helper to clean up an assertion Andy Lutomirski
2017-11-01 10:31   ` Borislav Petkov
2017-11-01 10:45     ` Andy Lutomirski
2017-10-26 15:55 ` [PATCH 00/18] Pile o' entry/exit/sp0 changes Linus Torvalds
2017-10-28  7:31   ` Andy Lutomirski

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=CAMzpN2hw6q5G7A-2vb7mHqECf4-Vd8D7XEVGXg7U-Mi06qY_4w@mail.gmail.com \
    --to=brgerst@gmail.com \
    --cc=bpetkov@suse.de \
    --cc=dave.hansen@intel.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=luto@kernel.org \
    --cc=torvalds@linux-foundation.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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).