RAID/s390: provide raid6 recovery optimization

The XC instruction can be used to improve the speed of the raid6
recovery. The loops now operate on blocks of 256 bytes.

Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
This commit is contained in:
Martin Schwidefsky 2016-08-31 09:27:35 +02:00
parent 7bac4f5b8e
commit f5b55fa1f8
4 changed files with 121 additions and 1 deletions

View File

@ -116,6 +116,7 @@ struct raid6_recov_calls {
extern const struct raid6_recov_calls raid6_recov_intx1;
extern const struct raid6_recov_calls raid6_recov_ssse3;
extern const struct raid6_recov_calls raid6_recov_avx2;
extern const struct raid6_recov_calls raid6_recov_s390xc;
extern const struct raid6_calls raid6_neonx1;
extern const struct raid6_calls raid6_neonx2;

View File

@ -7,7 +7,7 @@ raid6_pq-$(CONFIG_X86) += recov_ssse3.o recov_avx2.o mmx.o sse1.o sse2.o avx2.o
raid6_pq-$(CONFIG_ALTIVEC) += altivec1.o altivec2.o altivec4.o altivec8.o
raid6_pq-$(CONFIG_KERNEL_MODE_NEON) += neon.o neon1.o neon2.o neon4.o neon8.o
raid6_pq-$(CONFIG_TILEGX) += tilegx8.o
raid6_pq-$(CONFIG_S390) += s390vx8.o
raid6_pq-$(CONFIG_S390) += s390vx8.o recov_s390xc.o
hostprogs-y += mktables

View File

@ -97,6 +97,9 @@ const struct raid6_recov_calls *const raid6_recov_algos[] = {
#endif
#ifdef CONFIG_AS_SSSE3
&raid6_recov_ssse3,
#endif
#ifdef CONFIG_S390
&raid6_recov_s390xc,
#endif
&raid6_recov_intx1,
NULL

116
lib/raid6/recov_s390xc.c Normal file
View File

@ -0,0 +1,116 @@
/*
* RAID-6 data recovery in dual failure mode based on the XC instruction.
*
* Copyright IBM Corp. 2016
* Author(s): Martin Schwidefsky <schwidefsky@de.ibm.com>
*/
#include <linux/export.h>
#include <linux/raid/pq.h>
static inline void xor_block(u8 *p1, u8 *p2)
{
typedef struct { u8 _[256]; } addrtype;
asm volatile(
" xc 0(256,%[p1]),0(%[p2])\n"
: "+m" (*(addrtype *) p1) : "m" (*(addrtype *) p2),
[p1] "a" (p1), [p2] "a" (p2) : "cc");
}
/* Recover two failed data blocks. */
static void raid6_2data_recov_s390xc(int disks, size_t bytes, int faila,
int failb, void **ptrs)
{
u8 *p, *q, *dp, *dq;
const u8 *pbmul; /* P multiplier table for B data */
const u8 *qmul; /* Q multiplier table (for both) */
int i;
p = (u8 *)ptrs[disks-2];
q = (u8 *)ptrs[disks-1];
/* Compute syndrome with zero for the missing data pages
Use the dead data pages as temporary storage for
delta p and delta q */
dp = (u8 *)ptrs[faila];
ptrs[faila] = (void *)raid6_empty_zero_page;
ptrs[disks-2] = dp;
dq = (u8 *)ptrs[failb];
ptrs[failb] = (void *)raid6_empty_zero_page;
ptrs[disks-1] = dq;
raid6_call.gen_syndrome(disks, bytes, ptrs);
/* Restore pointer table */
ptrs[faila] = dp;
ptrs[failb] = dq;
ptrs[disks-2] = p;
ptrs[disks-1] = q;
/* Now, pick the proper data tables */
pbmul = raid6_gfmul[raid6_gfexi[failb-faila]];
qmul = raid6_gfmul[raid6_gfinv[raid6_gfexp[faila]^raid6_gfexp[failb]]];
/* Now do it... */
while (bytes) {
xor_block(dp, p);
xor_block(dq, q);
for (i = 0; i < 256; i++)
dq[i] = pbmul[dp[i]] ^ qmul[dq[i]];
xor_block(dp, dq);
p += 256;
q += 256;
dp += 256;
dq += 256;
bytes -= 256;
}
}
/* Recover failure of one data block plus the P block */
static void raid6_datap_recov_s390xc(int disks, size_t bytes, int faila,
void **ptrs)
{
u8 *p, *q, *dq;
const u8 *qmul; /* Q multiplier table */
int i;
p = (u8 *)ptrs[disks-2];
q = (u8 *)ptrs[disks-1];
/* Compute syndrome with zero for the missing data page
Use the dead data page as temporary storage for delta q */
dq = (u8 *)ptrs[faila];
ptrs[faila] = (void *)raid6_empty_zero_page;
ptrs[disks-1] = dq;
raid6_call.gen_syndrome(disks, bytes, ptrs);
/* Restore pointer table */
ptrs[faila] = dq;
ptrs[disks-1] = q;
/* Now, pick the proper data tables */
qmul = raid6_gfmul[raid6_gfinv[raid6_gfexp[faila]]];
/* Now do it... */
while (bytes) {
xor_block(dq, q);
for (i = 0; i < 256; i++)
dq[i] = qmul[dq[i]];
xor_block(p, dq);
p += 256;
q += 256;
dq += 256;
bytes -= 256;
}
}
const struct raid6_recov_calls raid6_recov_s390xc = {
.data2 = raid6_2data_recov_s390xc,
.datap = raid6_datap_recov_s390xc,
.valid = NULL,
.name = "s390xc",
.priority = 1,
};