summaryrefslogtreecommitdiff
path: root/arch/x86/include/asm/xor_32.h
diff options
context:
space:
mode:
authorJan Beulich <JBeulich@suse.com>2012-11-02 18:19:18 +0400
committerIngo Molnar <mingo@kernel.org>2013-01-25 12:23:50 +0400
commite8f6e3f8a14bae98197c6d9f280cd23d22eb1a33 (patch)
treeaefda4da8f27c865d858147864df8f0cd92b0efb /arch/x86/include/asm/xor_32.h
parente3e81aca8d51a50e19d6c67fafc4c9c4f0404bf1 (diff)
downloadlinux-e8f6e3f8a14bae98197c6d9f280cd23d22eb1a33.tar.xz
x86/xor: Unify SSE-base xor-block routines
Besides folding duplicate code, this has the advantage of fixing x86-64's failure to use proper (para-virtualizable) accessors for dealing with CR0.TS. Signed-off-by: Jan Beulich <jbeulich@suse.com> Acked-by: H. Peter Anvin <hpa@zytor.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Link: http://lkml.kernel.org/r/5093E47602000078000A615B@nat28.tlf.novell.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
Diffstat (limited to 'arch/x86/include/asm/xor_32.h')
-rw-r--r--arch/x86/include/asm/xor_32.h286
1 files changed, 1 insertions, 285 deletions
diff --git a/arch/x86/include/asm/xor_32.h b/arch/x86/include/asm/xor_32.h
index f79cb7ec0e06..b85dc87f3cc7 100644
--- a/arch/x86/include/asm/xor_32.h
+++ b/arch/x86/include/asm/xor_32.h
@@ -2,7 +2,7 @@
#define _ASM_X86_XOR_32_H
/*
- * Optimized RAID-5 checksumming functions for MMX and SSE.
+ * Optimized RAID-5 checksumming functions for MMX.
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
@@ -529,290 +529,6 @@ static struct xor_block_template xor_block_p5_mmx = {
.do_5 = xor_p5_mmx_5,
};
-/*
- * Cache avoiding checksumming functions utilizing KNI instructions
- * Copyright (C) 1999 Zach Brown (with obvious credit due Ingo)
- */
-
-#define OFFS(x) "16*("#x")"
-#define PF_OFFS(x) "256+16*("#x")"
-#define PF0(x) " prefetchnta "PF_OFFS(x)"(%1) ;\n"
-#define LD(x, y) " movaps "OFFS(x)"(%1), %%xmm"#y" ;\n"
-#define ST(x, y) " movaps %%xmm"#y", "OFFS(x)"(%1) ;\n"
-#define PF1(x) " prefetchnta "PF_OFFS(x)"(%2) ;\n"
-#define PF2(x) " prefetchnta "PF_OFFS(x)"(%3) ;\n"
-#define PF3(x) " prefetchnta "PF_OFFS(x)"(%4) ;\n"
-#define PF4(x) " prefetchnta "PF_OFFS(x)"(%5) ;\n"
-#define PF5(x) " prefetchnta "PF_OFFS(x)"(%6) ;\n"
-#define XO1(x, y) " xorps "OFFS(x)"(%2), %%xmm"#y" ;\n"
-#define XO2(x, y) " xorps "OFFS(x)"(%3), %%xmm"#y" ;\n"
-#define XO3(x, y) " xorps "OFFS(x)"(%4), %%xmm"#y" ;\n"
-#define XO4(x, y) " xorps "OFFS(x)"(%5), %%xmm"#y" ;\n"
-#define XO5(x, y) " xorps "OFFS(x)"(%6), %%xmm"#y" ;\n"
-
-
-static void
-xor_sse_2(unsigned long bytes, unsigned long *p1, unsigned long *p2)
-{
- unsigned long lines = bytes >> 8;
-
- kernel_fpu_begin();
-
- asm volatile(
-#undef BLOCK
-#define BLOCK(i) \
- LD(i, 0) \
- LD(i + 1, 1) \
- PF1(i) \
- PF1(i + 2) \
- LD(i + 2, 2) \
- LD(i + 3, 3) \
- PF0(i + 4) \
- PF0(i + 6) \
- XO1(i, 0) \
- XO1(i + 1, 1) \
- XO1(i + 2, 2) \
- XO1(i + 3, 3) \
- ST(i, 0) \
- ST(i + 1, 1) \
- ST(i + 2, 2) \
- ST(i + 3, 3) \
-
-
- PF0(0)
- PF0(2)
-
- " .align 32 ;\n"
- " 1: ;\n"
-
- BLOCK(0)
- BLOCK(4)
- BLOCK(8)
- BLOCK(12)
-
- " addl $256, %1 ;\n"
- " addl $256, %2 ;\n"
- " decl %0 ;\n"
- " jnz 1b ;\n"
- : "+r" (lines),
- "+r" (p1), "+r" (p2)
- :
- : "memory");
-
- kernel_fpu_end();
-}
-
-static void
-xor_sse_3(unsigned long bytes, unsigned long *p1, unsigned long *p2,
- unsigned long *p3)
-{
- unsigned long lines = bytes >> 8;
-
- kernel_fpu_begin();
-
- asm volatile(
-#undef BLOCK
-#define BLOCK(i) \
- PF1(i) \
- PF1(i + 2) \
- LD(i,0) \
- LD(i + 1, 1) \
- LD(i + 2, 2) \
- LD(i + 3, 3) \
- PF2(i) \
- PF2(i + 2) \
- PF0(i + 4) \
- PF0(i + 6) \
- XO1(i,0) \
- XO1(i + 1, 1) \
- XO1(i + 2, 2) \
- XO1(i + 3, 3) \
- XO2(i,0) \
- XO2(i + 1, 1) \
- XO2(i + 2, 2) \
- XO2(i + 3, 3) \
- ST(i,0) \
- ST(i + 1, 1) \
- ST(i + 2, 2) \
- ST(i + 3, 3) \
-
-
- PF0(0)
- PF0(2)
-
- " .align 32 ;\n"
- " 1: ;\n"
-
- BLOCK(0)
- BLOCK(4)
- BLOCK(8)
- BLOCK(12)
-
- " addl $256, %1 ;\n"
- " addl $256, %2 ;\n"
- " addl $256, %3 ;\n"
- " decl %0 ;\n"
- " jnz 1b ;\n"
- : "+r" (lines),
- "+r" (p1), "+r"(p2), "+r"(p3)
- :
- : "memory" );
-
- kernel_fpu_end();
-}
-
-static void
-xor_sse_4(unsigned long bytes, unsigned long *p1, unsigned long *p2,
- unsigned long *p3, unsigned long *p4)
-{
- unsigned long lines = bytes >> 8;
-
- kernel_fpu_begin();
-
- asm volatile(
-#undef BLOCK
-#define BLOCK(i) \
- PF1(i) \
- PF1(i + 2) \
- LD(i,0) \
- LD(i + 1, 1) \
- LD(i + 2, 2) \
- LD(i + 3, 3) \
- PF2(i) \
- PF2(i + 2) \
- XO1(i,0) \
- XO1(i + 1, 1) \
- XO1(i + 2, 2) \
- XO1(i + 3, 3) \
- PF3(i) \
- PF3(i + 2) \
- PF0(i + 4) \
- PF0(i + 6) \
- XO2(i,0) \
- XO2(i + 1, 1) \
- XO2(i + 2, 2) \
- XO2(i + 3, 3) \
- XO3(i,0) \
- XO3(i + 1, 1) \
- XO3(i + 2, 2) \
- XO3(i + 3, 3) \
- ST(i,0) \
- ST(i + 1, 1) \
- ST(i + 2, 2) \
- ST(i + 3, 3) \
-
-
- PF0(0)
- PF0(2)
-
- " .align 32 ;\n"
- " 1: ;\n"
-
- BLOCK(0)
- BLOCK(4)
- BLOCK(8)
- BLOCK(12)
-
- " addl $256, %1 ;\n"
- " addl $256, %2 ;\n"
- " addl $256, %3 ;\n"
- " addl $256, %4 ;\n"
- " decl %0 ;\n"
- " jnz 1b ;\n"
- : "+r" (lines),
- "+r" (p1), "+r" (p2), "+r" (p3), "+r" (p4)
- :
- : "memory" );
-
- kernel_fpu_end();
-}
-
-static void
-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;
-
- 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
- register that is shared with any other variable. That's
- because we modify p4 and p5 there, but we can't mark them
- as read/write, otherwise we'd overflow the 10-asm-operands
- limit of GCC < 3.1. */
- asm("" : "+r" (p4), "+r" (p5));
-
- asm volatile(
-#undef BLOCK
-#define BLOCK(i) \
- PF1(i) \
- PF1(i + 2) \
- LD(i,0) \
- LD(i + 1, 1) \
- LD(i + 2, 2) \
- LD(i + 3, 3) \
- PF2(i) \
- PF2(i + 2) \
- XO1(i,0) \
- XO1(i + 1, 1) \
- XO1(i + 2, 2) \
- XO1(i + 3, 3) \
- PF3(i) \
- PF3(i + 2) \
- XO2(i,0) \
- XO2(i + 1, 1) \
- XO2(i + 2, 2) \
- XO2(i + 3, 3) \
- PF4(i) \
- PF4(i + 2) \
- PF0(i + 4) \
- PF0(i + 6) \
- XO3(i,0) \
- XO3(i + 1, 1) \
- XO3(i + 2, 2) \
- XO3(i + 3, 3) \
- XO4(i,0) \
- XO4(i + 1, 1) \
- XO4(i + 2, 2) \
- XO4(i + 3, 3) \
- ST(i,0) \
- ST(i + 1, 1) \
- ST(i + 2, 2) \
- ST(i + 3, 3) \
-
-
- PF0(0)
- PF0(2)
-
- " .align 32 ;\n"
- " 1: ;\n"
-
- BLOCK(0)
- BLOCK(4)
- BLOCK(8)
- BLOCK(12)
-
- " addl $256, %1 ;\n"
- " addl $256, %2 ;\n"
- " addl $256, %3 ;\n"
- " addl $256, %4 ;\n"
- " addl $256, %5 ;\n"
- " decl %0 ;\n"
- " jnz 1b ;\n"
- : "+r" (lines),
- "+r" (p1), "+r" (p2), "+r" (p3)
- : "r" (p4), "r" (p5)
- : "memory");
-
- /* p4 and p5 were modified, and now the variables are dead.
- Clobber them just to be sure nobody does something stupid
- like assuming they have some legal value. */
- asm("" : "=r" (p4), "=r" (p5));
-
- kernel_fpu_end();
-}
-
static struct xor_block_template xor_block_pIII_sse = {
.name = "pIII_sse",
.do_2 = xor_sse_2,