diff options
author | Suresh Siddha <suresh.b.siddha@intel.com> | 2012-08-24 23:13:00 +0200 |
---|---|---|
committer | H. Peter Anvin <hpa@linux.intel.com> | 2012-09-19 00:52:08 +0200 |
commit | 841e3604d35aa70d399146abdc526d8c89a2c2f5 (patch) | |
tree | 80d2266c21e5ae0b5f4097db3ee71888fc92bec1 /arch/x86/include/asm/xor_32.h | |
parent | x86, kvm: use kernel_fpu_begin/end() in kvm_load/put_guest_fpu() (diff) | |
download | linux-841e3604d35aa70d399146abdc526d8c89a2c2f5.tar.xz linux-841e3604d35aa70d399146abdc526d8c89a2c2f5.zip |
x86, fpu: always use kernel_fpu_begin/end() for in-kernel FPU usage
use kernel_fpu_begin/end() instead of unconditionally accessing cr0 and
saving/restoring just the few used xmm/ymm registers.
This has some advantages like:
* If the task's FPU state is already active, then kernel_fpu_begin()
will just save the user-state and avoiding the read/write of cr0.
In general, cr0 accesses are much slower.
* Manual save/restore of xmm/ymm registers will affect the 'modified' and
the 'init' optimizations brought in the by xsaveopt/xrstor
infrastructure.
* Foward compatibility with future vector register extensions will be a
problem if the xmm/ymm registers are manually saved and restored
(corrupting the extended state of those vector registers).
With this patch, there was no significant difference in the xor throughput
using AVX, measured during boot.
Signed-off-by: Suresh Siddha <suresh.b.siddha@intel.com>
Link: http://lkml.kernel.org/r/1345842782-24175-5-git-send-email-suresh.b.siddha@intel.com
Cc: Jim Kukunas <james.t.kukunas@linux.intel.com>
Cc: NeilBrown <neilb@suse.de>
Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
Diffstat (limited to 'arch/x86/include/asm/xor_32.h')
-rw-r--r-- | arch/x86/include/asm/xor_32.h | 56 |
1 files changed, 8 insertions, 48 deletions
diff --git a/arch/x86/include/asm/xor_32.h b/arch/x86/include/asm/xor_32.h index 454570891bdc..aabd5850bdb9 100644 --- a/arch/x86/include/asm/xor_32.h +++ b/arch/x86/include/asm/xor_32.h @@ -534,38 +534,6 @@ static struct xor_block_template xor_block_p5_mmx = { * Copyright (C) 1999 Zach Brown (with obvious credit due Ingo) */ -#define XMMS_SAVE \ -do { \ - preempt_disable(); \ - cr0 = read_cr0(); \ - clts(); \ - asm volatile( \ - "movups %%xmm0,(%0) ;\n\t" \ - "movups %%xmm1,0x10(%0) ;\n\t" \ - "movups %%xmm2,0x20(%0) ;\n\t" \ - "movups %%xmm3,0x30(%0) ;\n\t" \ - : \ - : "r" (xmm_save) \ - : "memory"); \ -} while (0) - -#define XMMS_RESTORE \ -do { \ - asm volatile( \ - "sfence ;\n\t" \ - "movups (%0),%%xmm0 ;\n\t" \ - "movups 0x10(%0),%%xmm1 ;\n\t" \ - "movups 0x20(%0),%%xmm2 ;\n\t" \ - "movups 0x30(%0),%%xmm3 ;\n\t" \ - : \ - : "r" (xmm_save) \ - : "memory"); \ - write_cr0(cr0); \ - preempt_enable(); \ -} while (0) - -#define ALIGN16 __attribute__((aligned(16))) - #define OFFS(x) "16*("#x")" #define PF_OFFS(x) "256+16*("#x")" #define PF0(x) " prefetchnta "PF_OFFS(x)"(%1) ;\n" @@ -587,10 +555,8 @@ static void xor_sse_2(unsigned long bytes, unsigned long *p1, unsigned long *p2) { unsigned long lines = bytes >> 8; - char xmm_save[16*4] ALIGN16; - int cr0; - XMMS_SAVE; + kernel_fpu_begin(); asm volatile( #undef BLOCK @@ -633,7 +599,7 @@ xor_sse_2(unsigned long bytes, unsigned long *p1, unsigned long *p2) : : "memory"); - XMMS_RESTORE; + kernel_fpu_end(); } static void @@ -641,10 +607,8 @@ xor_sse_3(unsigned long bytes, unsigned long *p1, unsigned long *p2, unsigned long *p3) { unsigned long lines = bytes >> 8; - char xmm_save[16*4] ALIGN16; - int cr0; - XMMS_SAVE; + kernel_fpu_begin(); asm volatile( #undef BLOCK @@ -694,7 +658,7 @@ xor_sse_3(unsigned long bytes, unsigned long *p1, unsigned long *p2, : : "memory" ); - XMMS_RESTORE; + kernel_fpu_end(); } static void @@ -702,10 +666,8 @@ xor_sse_4(unsigned long bytes, unsigned long *p1, unsigned long *p2, unsigned long *p3, unsigned long *p4) { unsigned long lines = bytes >> 8; - char xmm_save[16*4] ALIGN16; - int cr0; - XMMS_SAVE; + kernel_fpu_begin(); asm volatile( #undef BLOCK @@ -762,7 +724,7 @@ xor_sse_4(unsigned long bytes, unsigned long *p1, unsigned long *p2, : : "memory" ); - XMMS_RESTORE; + kernel_fpu_end(); } static void @@ -770,10 +732,8 @@ xor_sse_5(unsigned long bytes, unsigned long *p1, unsigned long *p2, unsigned long *p3, unsigned long *p4, unsigned long *p5) { unsigned long lines = bytes >> 8; - char xmm_save[16*4] ALIGN16; - int cr0; - XMMS_SAVE; + kernel_fpu_begin(); /* Make sure GCC forgets anything it knows about p4 or p5, such that it won't pass to the asm volatile below a @@ -850,7 +810,7 @@ xor_sse_5(unsigned long bytes, unsigned long *p1, unsigned long *p2, like assuming they have some legal value. */ asm("" : "=r" (p4), "=r" (p5)); - XMMS_RESTORE; + kernel_fpu_end(); } static struct xor_block_template xor_block_pIII_sse = { |