md/raid6: implement recovery using ARM NEON intrinsics
Provide a NEON accelerated implementation of the recovery algorithm,
which supersedes the default byte-by-byte one.
Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
diff --git a/lib/raid6/Makefile b/lib/raid6/Makefile
index 3057011..a93adf6 100644
--- a/lib/raid6/Makefile
+++ b/lib/raid6/Makefile
@@ -5,7 +5,7 @@
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-$(CONFIG_KERNEL_MODE_NEON) += neon.o neon1.o neon2.o neon4.o neon8.o
+raid6_pq-$(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
@@ -26,7 +26,9 @@
ifeq ($(ARCH),arm)
NEON_FLAGS += -mfloat-abi=softfp -mfpu=neon
endif
+CFLAGS_recov_neon_inner.o += $(NEON_FLAGS)
ifeq ($(ARCH),arm64)
+CFLAGS_REMOVE_recov_neon_inner.o += -mgeneral-regs-only
CFLAGS_REMOVE_neon1.o += -mgeneral-regs-only
CFLAGS_REMOVE_neon2.o += -mgeneral-regs-only
CFLAGS_REMOVE_neon4.o += -mgeneral-regs-only