lib/raid6/altivec: Add vpermxor implementation for raid6 Q syndrome

This patch uses the vpermxor instruction to optimise the raid6 Q
syndrome. This instruction was made available with POWER8, ISA version
2.07. It allows for both vperm and vxor instructions to be done in a
single instruction. This has been tested for correctness on a ppc64le
vm with a basic RAID6 setup containing 5 drives.

The performance benchmarks are from the raid6test in the
/lib/raid6/test directory. These results are from an IBM Firestone
machine with ppc64le architecture. The benchmark results show a 35%
speed increase over the best existing algorithm for powerpc (altivec).
The raid6test has also been run on a big-endian ppc64 vm to ensure it
also works for big-endian architectures.

Performance benchmarks:
  raid6: altivecx4 gen() 18773 MB/s
  raid6: altivecx8 gen() 19438 MB/s

  raid6: vpermxor4 gen() 25112 MB/s
  raid6: vpermxor8 gen() 26279 MB/s

Signed-off-by: Matt Brown <matthew.brown.dev@gmail.com>
Reviewed-by: Daniel Axtens <dja@axtens.net>
[mpe: Add VPERMXOR macro so we can build with old binutils]
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>

1 files changed, 26 insertions, 1 deletions

diff --git a/lib/raid6/Makefile b/lib/raid6/Makefile
index 4add700ddfe3..21f59443e99e 100644
--- a/lib/raid6/Makefile
+++ b/lib/raid6/Makefile
@@ -5,7 +5,8 @@ raid6_pq-y	+= algos.o recov.o tables.o int1.o int2.o int4.o \
 		   int8.o int16.o int32.o
 
 raid6_pq-$(CONFIG_X86) += recov_ssse3.o recov_avx2.o mmx.o sse1.o sse2.o avx2.o avx512.o recov_avx512.o
-raid6_pq-$(CONFIG_ALTIVEC) += altivec1.o altivec2.o altivec4.o altivec8.o
+raid6_pq-$(CONFIG_ALTIVEC) += altivec1.o altivec2.o altivec4.o altivec8.o \
+                              vpermxor1.o vpermxor2.o vpermxor4.o vpermxor8.o
 raid6_pq-$(CONFIG_KERNEL_MODE_NEON) += neon.o neon1.o neon2.o neon4.o neon8.o recov_neon.o recov_neon_inner.o
 raid6_pq-$(CONFIG_TILEGX) += tilegx8.o
 raid6_pq-$(CONFIG_S390) += s390vx8.o recov_s390xc.o
@@ -91,6 +92,30 @@ $(obj)/altivec8.c:   UNROLL := 8
 $(obj)/altivec8.c:   $(src)/altivec.uc $(src)/unroll.awk FORCE
 	$(call if_changed,unroll)
 
+CFLAGS_vpermxor1.o += $(altivec_flags)
+targets += vpermxor1.c
+$(obj)/vpermxor1.c: UNROLL := 1
+$(obj)/vpermxor1.c: $(src)/vpermxor.uc $(src)/unroll.awk FORCE
+	$(call if_changed,unroll)
+
+CFLAGS_vpermxor2.o += $(altivec_flags)
+targets += vpermxor2.c
+$(obj)/vpermxor2.c: UNROLL := 2
+$(obj)/vpermxor2.c: $(src)/vpermxor.uc $(src)/unroll.awk FORCE
+	$(call if_changed,unroll)
+
+CFLAGS_vpermxor4.o += $(altivec_flags)
+targets += vpermxor4.c
+$(obj)/vpermxor4.c: UNROLL := 4
+$(obj)/vpermxor4.c: $(src)/vpermxor.uc $(src)/unroll.awk FORCE
+	$(call if_changed,unroll)
+
+CFLAGS_vpermxor8.o += $(altivec_flags)
+targets += vpermxor8.c
+$(obj)/vpermxor8.c: UNROLL := 8
+$(obj)/vpermxor8.c: $(src)/vpermxor.uc $(src)/unroll.awk FORCE
+	$(call if_changed,unroll)
+
 CFLAGS_neon1.o += $(NEON_FLAGS)
 targets += neon1.c
 $(obj)/neon1.c:   UNROLL := 1