diff options
| author | Andi Kleen <ak@suse.de> | 2006-09-26 10:52:38 +0200 |
|---|---|---|
| committer | Andi Kleen <andi@basil.nowhere.org> | 2006-09-26 10:52:38 +0200 |
| commit | 53ee11ae0d73f28029a5f0d991bc4dcd7c817e7a (patch) | |
| tree | c0a025cc592d516674bb1d8a0046bf281b6d1724 /arch/x86_64/kernel/setup64.c | |
| parent | [PATCH] x86: Remove incorrect comment about ACPI e820 entries (diff) | |
| download | linux-53ee11ae0d73f28029a5f0d991bc4dcd7c817e7a.tar.xz linux-53ee11ae0d73f28029a5f0d991bc4dcd7c817e7a.zip | |
[PATCH] Optimize PDA accesses slightly
Based on a idea by Jeremy Fitzhardinge:
Replace the volatiles and memory clobbers in the PDA access with
telling gcc about access to a proxy PDA structure that doesn't
actually exist. But the dummy accesses give a defined ordering for
read/write accesses.
Also add some memory barriers to the early GS initialization to
make sure no PDA access is moved before it.
Advantage is some .text savings (probably most from better
code for accessing "current"):
text data bss dec hex filename
4845647 1223688 615864 6685199 66020f vmlinux
4837780 1223688 615864 6677332 65e354 vmlinux-pda
1.2% smaller code
Cc: Jeremy Fitzhardinge <jeremy@goop.org>
Signed-off-by: Andi Kleen <ak@suse.de>
Diffstat (limited to 'arch/x86_64/kernel/setup64.c')
| -rw-r--r-- | arch/x86_64/kernel/setup64.c | 3 |
1 files changed, 3 insertions, 0 deletions
diff --git a/arch/x86_64/kernel/setup64.c b/arch/x86_64/kernel/setup64.c index e85cfbb49b63..491361752c70 100644 --- a/arch/x86_64/kernel/setup64.c +++ b/arch/x86_64/kernel/setup64.c @@ -121,7 +121,10 @@ void pda_init(int cpu) /* Setup up data that may be needed in __get_free_pages early */ asm volatile("movl %0,%%fs ; movl %0,%%gs" :: "r" (0)); + /* Memory clobbers used to order PDA accessed */ + mb(); wrmsrl(MSR_GS_BASE, pda); + mb(); pda->cpunumber = cpu; pda->irqcount = -1; |