lib/raid6: add ARM-NEON accelerated syndrome calculation

Rebased/reworked a patch contributed by Rob Herring that uses
NEON intrinsics to perform the RAID-6 syndrome calculations.
It uses the existing unroll.awk code to generate several
unrolled versions of which the best performing one is selected
at boot time.

Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Acked-by: Nicolas Pitre <nico@linaro.org>
Cc: hpa@linux.intel.com

1 files changed, 40 insertions, 0 deletions

diff --git a/lib/raid6/Makefile b/lib/raid6/Makefile
index 9f7c184725d7..b4625787c7ee 100644
--- a/lib/raid6/Makefile
+++ b/lib/raid6/Makefile
@@ -5,6 +5,7 @@ raid6_pq-y	+= algos.o recov.o tables.o int1.o int2.o int4.o \
 
 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
 
 hostprogs-y	+= mktables
 
@@ -16,6 +17,21 @@ ifeq ($(CONFIG_ALTIVEC),y)
 altivec_flags := -maltivec -mabi=altivec
 endif
 
+# The GCC option -ffreestanding is required in order to compile code containing
+# ARM/NEON intrinsics in a non C99-compliant environment (such as the kernel)
+ifeq ($(CONFIG_KERNEL_MODE_NEON),y)
+NEON_FLAGS := -ffreestanding
+ifeq ($(ARCH),arm)
+NEON_FLAGS += -mfloat-abi=softfp -mfpu=neon
+endif
+ifeq ($(ARCH),arm64)
+CFLAGS_REMOVE_neon1.o += -mgeneral-regs-only
+CFLAGS_REMOVE_neon2.o += -mgeneral-regs-only
+CFLAGS_REMOVE_neon4.o += -mgeneral-regs-only
+CFLAGS_REMOVE_neon8.o += -mgeneral-regs-only
+endif
+endif
+
 targets += int1.c
 $(obj)/int1.c:   UNROLL := 1
 $(obj)/int1.c:   $(src)/int.uc $(src)/unroll.awk FORCE
@@ -70,6 +86,30 @@ $(obj)/altivec8.c:   UNROLL := 8
 $(obj)/altivec8.c:   $(src)/altivec.uc $(src)/unroll.awk FORCE
 	$(call if_changed,unroll)
 
+CFLAGS_neon1.o += $(NEON_FLAGS)
+targets += neon1.c
+$(obj)/neon1.c:   UNROLL := 1
+$(obj)/neon1.c:   $(src)/neon.uc $(src)/unroll.awk FORCE
+	$(call if_changed,unroll)
+
+CFLAGS_neon2.o += $(NEON_FLAGS)
+targets += neon2.c
+$(obj)/neon2.c:   UNROLL := 2
+$(obj)/neon2.c:   $(src)/neon.uc $(src)/unroll.awk FORCE
+	$(call if_changed,unroll)
+
+CFLAGS_neon4.o += $(NEON_FLAGS)
+targets += neon4.c
+$(obj)/neon4.c:   UNROLL := 4
+$(obj)/neon4.c:   $(src)/neon.uc $(src)/unroll.awk FORCE
+	$(call if_changed,unroll)
+
+CFLAGS_neon8.o += $(NEON_FLAGS)
+targets += neon8.c
+$(obj)/neon8.c:   UNROLL := 8
+$(obj)/neon8.c:   $(src)/neon.uc $(src)/unroll.awk FORCE
+	$(call if_changed,unroll)
+
 quiet_cmd_mktable = TABLE   $@
       cmd_mktable = $(obj)/mktables > $@ || ( rm -f $@ && exit 1 )