x86/entry/compat: In SYSENTER, sink AC clearing below the existing FLAGS test

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 <[email protected]>
Cc: Andrew Cooper <[email protected]>
Cc: Andy Lutomirski <[email protected]>
Cc: Borislav Petkov <[email protected]>
Cc: Brian Gerst <[email protected]>
Cc: Denys Vlasenko <[email protected]>
Cc: H. Peter Anvin <[email protected]>
Cc: Linus Torvalds <[email protected]>
Cc: Oleg Nesterov <[email protected]>
Cc: Peter Zijlstra <[email protected]>
Cc: Thomas Gleixner <[email protected]>
Link: http://lkml.kernel.org/r/90d6db2189f9add83bc7bddd75a0c19ebbd676b2.1457578375.git.luto@kernel.org
Signed-off-by: Ingo Molnar <[email protected]>

diff --git a/arch/x86/entry/entry_64_compat.S b/arch/x86/entry/entry_64_compat.S
index 3c990eeee40bd6e83b4d830654fdf966250bb0e1..da5c19443e0b51796ac145180f967868617ea165 100644 (file)
--- 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: