md/raid6 algorithms: xor_syndrome() for SSE2

The second and (last) optimized XOR syndrome calculation. This version
supports right and left side optimization. All CPUs with architecture
older than Haswell will benefit from it.

It should be noted that SSE2 movntdq kills performance for memory areas
that are read and written simultaneously in chunks smaller than cache
line size. So use movdqa instead for P/Q writes in sse21 and sse22 XOR
functions.

Signed-off-by: Markus Stockhausen <stockhausen@collogia.de>
Signed-off-by: NeilBrown <neilb@suse.de>
This commit is contained in:
Markus Stockhausen 2014-12-15 12:57:05 +11:00 committed by NeilBrown
parent 9a5ce91d05
commit a582564b24
1 changed files with 227 additions and 3 deletions

View File

@ -88,9 +88,58 @@ static void raid6_sse21_gen_syndrome(int disks, size_t bytes, void **ptrs)
kernel_fpu_end();
}
static void raid6_sse21_xor_syndrome(int disks, int start, int stop,
size_t bytes, void **ptrs)
{
u8 **dptr = (u8 **)ptrs;
u8 *p, *q;
int d, z, z0;
z0 = stop; /* P/Q right side optimization */
p = dptr[disks-2]; /* XOR parity */
q = dptr[disks-1]; /* RS syndrome */
kernel_fpu_begin();
asm volatile("movdqa %0,%%xmm0" : : "m" (raid6_sse_constants.x1d[0]));
for ( d = 0 ; d < bytes ; d += 16 ) {
asm volatile("movdqa %0,%%xmm4" :: "m" (dptr[z0][d]));
asm volatile("movdqa %0,%%xmm2" : : "m" (p[d]));
asm volatile("pxor %xmm4,%xmm2");
/* P/Q data pages */
for ( z = z0-1 ; z >= start ; z-- ) {
asm volatile("pxor %xmm5,%xmm5");
asm volatile("pcmpgtb %xmm4,%xmm5");
asm volatile("paddb %xmm4,%xmm4");
asm volatile("pand %xmm0,%xmm5");
asm volatile("pxor %xmm5,%xmm4");
asm volatile("movdqa %0,%%xmm5" :: "m" (dptr[z][d]));
asm volatile("pxor %xmm5,%xmm2");
asm volatile("pxor %xmm5,%xmm4");
}
/* P/Q left side optimization */
for ( z = start-1 ; z >= 0 ; z-- ) {
asm volatile("pxor %xmm5,%xmm5");
asm volatile("pcmpgtb %xmm4,%xmm5");
asm volatile("paddb %xmm4,%xmm4");
asm volatile("pand %xmm0,%xmm5");
asm volatile("pxor %xmm5,%xmm4");
}
asm volatile("pxor %0,%%xmm4" : : "m" (q[d]));
/* Don't use movntdq for r/w memory area < cache line */
asm volatile("movdqa %%xmm4,%0" : "=m" (q[d]));
asm volatile("movdqa %%xmm2,%0" : "=m" (p[d]));
}
asm volatile("sfence" : : : "memory");
kernel_fpu_end();
}
const struct raid6_calls raid6_sse2x1 = {
raid6_sse21_gen_syndrome,
NULL, /* XOR not yet implemented */
raid6_sse21_xor_syndrome,
raid6_have_sse2,
"sse2x1",
1 /* Has cache hints */
@ -151,9 +200,76 @@ static void raid6_sse22_gen_syndrome(int disks, size_t bytes, void **ptrs)
kernel_fpu_end();
}
static void raid6_sse22_xor_syndrome(int disks, int start, int stop,
size_t bytes, void **ptrs)
{
u8 **dptr = (u8 **)ptrs;
u8 *p, *q;
int d, z, z0;
z0 = stop; /* P/Q right side optimization */
p = dptr[disks-2]; /* XOR parity */
q = dptr[disks-1]; /* RS syndrome */
kernel_fpu_begin();
asm volatile("movdqa %0,%%xmm0" : : "m" (raid6_sse_constants.x1d[0]));
for ( d = 0 ; d < bytes ; d += 32 ) {
asm volatile("movdqa %0,%%xmm4" :: "m" (dptr[z0][d]));
asm volatile("movdqa %0,%%xmm6" :: "m" (dptr[z0][d+16]));
asm volatile("movdqa %0,%%xmm2" : : "m" (p[d]));
asm volatile("movdqa %0,%%xmm3" : : "m" (p[d+16]));
asm volatile("pxor %xmm4,%xmm2");
asm volatile("pxor %xmm6,%xmm3");
/* P/Q data pages */
for ( z = z0-1 ; z >= start ; z-- ) {
asm volatile("pxor %xmm5,%xmm5");
asm volatile("pxor %xmm7,%xmm7");
asm volatile("pcmpgtb %xmm4,%xmm5");
asm volatile("pcmpgtb %xmm6,%xmm7");
asm volatile("paddb %xmm4,%xmm4");
asm volatile("paddb %xmm6,%xmm6");
asm volatile("pand %xmm0,%xmm5");
asm volatile("pand %xmm0,%xmm7");
asm volatile("pxor %xmm5,%xmm4");
asm volatile("pxor %xmm7,%xmm6");
asm volatile("movdqa %0,%%xmm5" :: "m" (dptr[z][d]));
asm volatile("movdqa %0,%%xmm7" :: "m" (dptr[z][d+16]));
asm volatile("pxor %xmm5,%xmm2");
asm volatile("pxor %xmm7,%xmm3");
asm volatile("pxor %xmm5,%xmm4");
asm volatile("pxor %xmm7,%xmm6");
}
/* P/Q left side optimization */
for ( z = start-1 ; z >= 0 ; z-- ) {
asm volatile("pxor %xmm5,%xmm5");
asm volatile("pxor %xmm7,%xmm7");
asm volatile("pcmpgtb %xmm4,%xmm5");
asm volatile("pcmpgtb %xmm6,%xmm7");
asm volatile("paddb %xmm4,%xmm4");
asm volatile("paddb %xmm6,%xmm6");
asm volatile("pand %xmm0,%xmm5");
asm volatile("pand %xmm0,%xmm7");
asm volatile("pxor %xmm5,%xmm4");
asm volatile("pxor %xmm7,%xmm6");
}
asm volatile("pxor %0,%%xmm4" : : "m" (q[d]));
asm volatile("pxor %0,%%xmm6" : : "m" (q[d+16]));
/* Don't use movntdq for r/w memory area < cache line */
asm volatile("movdqa %%xmm4,%0" : "=m" (q[d]));
asm volatile("movdqa %%xmm6,%0" : "=m" (q[d+16]));
asm volatile("movdqa %%xmm2,%0" : "=m" (p[d]));
asm volatile("movdqa %%xmm3,%0" : "=m" (p[d+16]));
}
asm volatile("sfence" : : : "memory");
kernel_fpu_end();
}
const struct raid6_calls raid6_sse2x2 = {
raid6_sse22_gen_syndrome,
NULL, /* XOR not yet implemented */
raid6_sse22_xor_syndrome,
raid6_have_sse2,
"sse2x2",
1 /* Has cache hints */
@ -250,9 +366,117 @@ static void raid6_sse24_gen_syndrome(int disks, size_t bytes, void **ptrs)
kernel_fpu_end();
}
static void raid6_sse24_xor_syndrome(int disks, int start, int stop,
size_t bytes, void **ptrs)
{
u8 **dptr = (u8 **)ptrs;
u8 *p, *q;
int d, z, z0;
z0 = stop; /* P/Q right side optimization */
p = dptr[disks-2]; /* XOR parity */
q = dptr[disks-1]; /* RS syndrome */
kernel_fpu_begin();
asm volatile("movdqa %0,%%xmm0" :: "m" (raid6_sse_constants.x1d[0]));
for ( d = 0 ; d < bytes ; d += 64 ) {
asm volatile("movdqa %0,%%xmm4" :: "m" (dptr[z0][d]));
asm volatile("movdqa %0,%%xmm6" :: "m" (dptr[z0][d+16]));
asm volatile("movdqa %0,%%xmm12" :: "m" (dptr[z0][d+32]));
asm volatile("movdqa %0,%%xmm14" :: "m" (dptr[z0][d+48]));
asm volatile("movdqa %0,%%xmm2" : : "m" (p[d]));
asm volatile("movdqa %0,%%xmm3" : : "m" (p[d+16]));
asm volatile("movdqa %0,%%xmm10" : : "m" (p[d+32]));
asm volatile("movdqa %0,%%xmm11" : : "m" (p[d+48]));
asm volatile("pxor %xmm4,%xmm2");
asm volatile("pxor %xmm6,%xmm3");
asm volatile("pxor %xmm12,%xmm10");
asm volatile("pxor %xmm14,%xmm11");
/* P/Q data pages */
for ( z = z0-1 ; z >= start ; z-- ) {
asm volatile("prefetchnta %0" :: "m" (dptr[z][d]));
asm volatile("prefetchnta %0" :: "m" (dptr[z][d+32]));
asm volatile("pxor %xmm5,%xmm5");
asm volatile("pxor %xmm7,%xmm7");
asm volatile("pxor %xmm13,%xmm13");
asm volatile("pxor %xmm15,%xmm15");
asm volatile("pcmpgtb %xmm4,%xmm5");
asm volatile("pcmpgtb %xmm6,%xmm7");
asm volatile("pcmpgtb %xmm12,%xmm13");
asm volatile("pcmpgtb %xmm14,%xmm15");
asm volatile("paddb %xmm4,%xmm4");
asm volatile("paddb %xmm6,%xmm6");
asm volatile("paddb %xmm12,%xmm12");
asm volatile("paddb %xmm14,%xmm14");
asm volatile("pand %xmm0,%xmm5");
asm volatile("pand %xmm0,%xmm7");
asm volatile("pand %xmm0,%xmm13");
asm volatile("pand %xmm0,%xmm15");
asm volatile("pxor %xmm5,%xmm4");
asm volatile("pxor %xmm7,%xmm6");
asm volatile("pxor %xmm13,%xmm12");
asm volatile("pxor %xmm15,%xmm14");
asm volatile("movdqa %0,%%xmm5" :: "m" (dptr[z][d]));
asm volatile("movdqa %0,%%xmm7" :: "m" (dptr[z][d+16]));
asm volatile("movdqa %0,%%xmm13" :: "m" (dptr[z][d+32]));
asm volatile("movdqa %0,%%xmm15" :: "m" (dptr[z][d+48]));
asm volatile("pxor %xmm5,%xmm2");
asm volatile("pxor %xmm7,%xmm3");
asm volatile("pxor %xmm13,%xmm10");
asm volatile("pxor %xmm15,%xmm11");
asm volatile("pxor %xmm5,%xmm4");
asm volatile("pxor %xmm7,%xmm6");
asm volatile("pxor %xmm13,%xmm12");
asm volatile("pxor %xmm15,%xmm14");
}
asm volatile("prefetchnta %0" :: "m" (q[d]));
asm volatile("prefetchnta %0" :: "m" (q[d+32]));
/* P/Q left side optimization */
for ( z = start-1 ; z >= 0 ; z-- ) {
asm volatile("pxor %xmm5,%xmm5");
asm volatile("pxor %xmm7,%xmm7");
asm volatile("pxor %xmm13,%xmm13");
asm volatile("pxor %xmm15,%xmm15");
asm volatile("pcmpgtb %xmm4,%xmm5");
asm volatile("pcmpgtb %xmm6,%xmm7");
asm volatile("pcmpgtb %xmm12,%xmm13");
asm volatile("pcmpgtb %xmm14,%xmm15");
asm volatile("paddb %xmm4,%xmm4");
asm volatile("paddb %xmm6,%xmm6");
asm volatile("paddb %xmm12,%xmm12");
asm volatile("paddb %xmm14,%xmm14");
asm volatile("pand %xmm0,%xmm5");
asm volatile("pand %xmm0,%xmm7");
asm volatile("pand %xmm0,%xmm13");
asm volatile("pand %xmm0,%xmm15");
asm volatile("pxor %xmm5,%xmm4");
asm volatile("pxor %xmm7,%xmm6");
asm volatile("pxor %xmm13,%xmm12");
asm volatile("pxor %xmm15,%xmm14");
}
asm volatile("movntdq %%xmm2,%0" : "=m" (p[d]));
asm volatile("movntdq %%xmm3,%0" : "=m" (p[d+16]));
asm volatile("movntdq %%xmm10,%0" : "=m" (p[d+32]));
asm volatile("movntdq %%xmm11,%0" : "=m" (p[d+48]));
asm volatile("pxor %0,%%xmm4" : : "m" (q[d]));
asm volatile("pxor %0,%%xmm6" : : "m" (q[d+16]));
asm volatile("pxor %0,%%xmm12" : : "m" (q[d+32]));
asm volatile("pxor %0,%%xmm14" : : "m" (q[d+48]));
asm volatile("movntdq %%xmm4,%0" : "=m" (q[d]));
asm volatile("movntdq %%xmm6,%0" : "=m" (q[d+16]));
asm volatile("movntdq %%xmm12,%0" : "=m" (q[d+32]));
asm volatile("movntdq %%xmm14,%0" : "=m" (q[d+48]));
}
asm volatile("sfence" : : : "memory");
kernel_fpu_end();
}
const struct raid6_calls raid6_sse2x4 = {
raid6_sse24_gen_syndrome,
NULL, /* XOR not yet implemented */
raid6_sse24_xor_syndrome,
raid6_have_sse2,
"sse2x4",
1 /* Has cache hints */