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

include/linux/raid/pq.h

@@ -114,6 +114,11 @@ 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_calls raid6_neonx1;
+extern const struct raid6_calls raid6_neonx2;
+extern const struct raid6_calls raid6_neonx4;
+extern const struct raid6_calls raid6_neonx8;
+
 /* Algorithm list */
 extern const struct raid6_calls * const raid6_algos[];
 extern const struct raid6_recov_calls *const raid6_recov_algos[];

lib/raid6/.gitignore

@@ -2,3 +2,4 @@ mktables
 altivec*.c
 int*.c
 tables.c
+neon?.c

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 )
 

lib/raid6/algos.c

@@ -70,6 +70,12 @@ const struct raid6_calls * const raid6_algos[] = {
 	&raid6_intx2,
 	&raid6_intx4,
 	&raid6_intx8,
+#ifdef CONFIG_KERNEL_MODE_NEON
+	&raid6_neonx1,
+	&raid6_neonx2,
+	&raid6_neonx4,
+	&raid6_neonx8,
+#endif
 	NULL
 };
 

lib/raid6/neon.c

+/*
+ * linux/lib/raid6/neon.c - RAID6 syndrome calculation using ARM NEON intrinsics
+ *
+ * Copyright (C) 2013 Linaro Ltd <ard.biesheuvel@linaro.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/raid/pq.h>
+
+#ifdef __KERNEL__
+#include <asm/neon.h>
+#else
+#define kernel_neon_begin()
+#define kernel_neon_end()
+#define cpu_has_neon()		(1)
+#endif
+
+/*
+ * There are 2 reasons these wrappers are kept in a separate compilation unit
+ * from the actual implementations in neonN.c (generated from neon.uc by
+ * unroll.awk):
+ * - the actual implementations use NEON intrinsics, and the GCC support header
+ *   (arm_neon.h) is not fully compatible (type wise) with the kernel;
+ * - the neonN.c files are compiled with -mfpu=neon and optimization enabled,
+ *   and we have to make sure that we never use *any* NEON/VFP instructions
+ *   outside a kernel_neon_begin()/kernel_neon_end() pair.
+ */
+
+#define RAID6_NEON_WRAPPER(_n)						\
+	static void raid6_neon ## _n ## _gen_syndrome(int disks,	\
+					size_t bytes, void **ptrs)	\
+	{								\
+		void raid6_neon ## _n  ## _gen_syndrome_real(int,	\
+						unsigned long, void**);	\
+		kernel_neon_begin();					\
+		raid6_neon ## _n ## _gen_syndrome_real(disks,		\
+					(unsigned long)bytes, ptrs);	\
+		kernel_neon_end();					\
+	}								\
+	struct raid6_calls const raid6_neonx ## _n = {			\
+		raid6_neon ## _n ## _gen_syndrome,			\
+		raid6_have_neon,					\
+		"neonx" #_n,						\
+		0							\
+	}
+
+static int raid6_have_neon(void)
+{
+	return cpu_has_neon();
+}
+
+RAID6_NEON_WRAPPER(1);
+RAID6_NEON_WRAPPER(2);
+RAID6_NEON_WRAPPER(4);
+RAID6_NEON_WRAPPER(8);

lib/raid6/neon.uc

+/* -----------------------------------------------------------------------
+ *
+ *   neon.uc - RAID-6 syndrome calculation using ARM NEON instructions
+ *
+ *   Copyright (C) 2012 Rob Herring
+ *
+ *   Based on altivec.uc:
+ *     Copyright 2002-2004 H. Peter Anvin - All Rights Reserved
+ *
+ *   This program is free software; you can redistribute it and/or modify
+ *   it under the terms of the GNU General Public License as published by
+ *   the Free Software Foundation, Inc., 53 Temple Place Ste 330,
+ *   Boston MA 02111-1307, USA; either version 2 of the License, or
+ *   (at your option) any later version; incorporated herein by reference.
+ *
+ * ----------------------------------------------------------------------- */
+
+/*
+ * neon$#.c
+ *
+ * $#-way unrolled NEON intrinsics math RAID-6 instruction set
+ *
+ * This file is postprocessed using unroll.awk
+ */
+
+#include <arm_neon.h>
+
+typedef uint8x16_t unative_t;
+
+#define NBYTES(x) ((unative_t){x,x,x,x, x,x,x,x, x,x,x,x, x,x,x,x})
+#define NSIZE	sizeof(unative_t)
+
+/*
+ * The SHLBYTE() operation shifts each byte left by 1, *not*
+ * rolling over into the next byte
+ */
+static inline unative_t SHLBYTE(unative_t v)
+{
+	return vshlq_n_u8(v, 1);
+}
+
+/*
+ * The MASK() operation returns 0xFF in any byte for which the high
+ * bit is 1, 0x00 for any byte for which the high bit is 0.
+ */
+static inline unative_t MASK(unative_t v)
+{
+	const uint8x16_t temp = NBYTES(0);
+	return (unative_t)vcltq_s8((int8x16_t)v, (int8x16_t)temp);
+}
+
+void raid6_neon$#_gen_syndrome_real(int disks, unsigned long bytes, void **ptrs)
+{
+	uint8_t **dptr = (uint8_t **)ptrs;
+	uint8_t *p, *q;
+	int d, z, z0;
+
+	register unative_t wd$$, wq$$, wp$$, w1$$, w2$$;
+	const unative_t x1d = NBYTES(0x1d);
+
+	z0 = disks - 3;		/* Highest data disk */
+	p = dptr[z0+1];		/* XOR parity */
+	q = dptr[z0+2];		/* RS syndrome */
+
+	for ( d = 0 ; d < bytes ; d += NSIZE*$# ) {
+		wq$$ = wp$$ = vld1q_u8(&dptr[z0][d+$$*NSIZE]);
+		for ( z = z0-1 ; z >= 0 ; z-- ) {
+			wd$$ = vld1q_u8(&dptr[z][d+$$*NSIZE]);
+			wp$$ = veorq_u8(wp$$, wd$$);
+			w2$$ = MASK(wq$$);
+			w1$$ = SHLBYTE(wq$$);
+
+			w2$$ = vandq_u8(w2$$, x1d);
+			w1$$ = veorq_u8(w1$$, w2$$);
+			wq$$ = veorq_u8(w1$$, wd$$);
+		}
+		vst1q_u8(&p[d+NSIZE*$$], wp$$);
+		vst1q_u8(&q[d+NSIZE*$$], wq$$);
+	}
+}

lib/raid6/test/Makefile

@@ -22,11 +22,23 @@ ifeq ($(ARCH),x86_64)
         IS_X86 = yes
 endif
 
+ifeq ($(ARCH),arm)
+        CFLAGS += -I../../../arch/arm/include -mfpu=neon
+        HAS_NEON = yes
+endif
+ifeq ($(ARCH),arm64)
+        CFLAGS += -I../../../arch/arm64/include
+        HAS_NEON = yes
+endif
+
 ifeq ($(IS_X86),yes)
         OBJS   += mmx.o sse1.o sse2.o avx2.o recov_ssse3.o recov_avx2.o
         CFLAGS += $(shell echo "vpbroadcastb %xmm0, %ymm1" |	\
                     gcc -c -x assembler - >&/dev/null &&	\
                     rm ./-.o && echo -DCONFIG_AS_AVX2=1)
+else ifeq ($(HAS_NEON),yes)
+        OBJS   += neon.o neon1.o neon2.o neon4.o neon8.o
+        CFLAGS += -DCONFIG_KERNEL_MODE_NEON=1
 else
         HAS_ALTIVEC := $(shell echo -e '\#include <altivec.h>\nvector int a;' |\
                          gcc -c -x c - >&/dev/null && \
@@ -55,6 +67,18 @@ raid6.a: $(OBJS)
 raid6test: test.c raid6.a
 	$(CC) $(CFLAGS) -o raid6test $^
 
+neon1.c: neon.uc ../unroll.awk
+	$(AWK) ../unroll.awk -vN=1 < neon.uc > $@
+
+neon2.c: neon.uc ../unroll.awk
+	$(AWK) ../unroll.awk -vN=2 < neon.uc > $@
+
+neon4.c: neon.uc ../unroll.awk
+	$(AWK) ../unroll.awk -vN=4 < neon.uc > $@
+
+neon8.c: neon.uc ../unroll.awk
+	$(AWK) ../unroll.awk -vN=8 < neon.uc > $@
+
 altivec1.c: altivec.uc ../unroll.awk
 	$(AWK) ../unroll.awk -vN=1 < altivec.uc > $@
 
@@ -89,7 +113,7 @@ tables.c: mktables
 	./mktables > tables.c
 
 clean:
-	rm -f *.o *.a mktables mktables.c *.uc int*.c altivec*.c tables.c raid6test
+	rm -f *.o *.a mktables mktables.c *.uc int*.c altivec*.c neon*.c tables.c raid6test
 
 spotless: clean
 	rm -f *~