Move the optimized XOR into lib/raid and include it it in the main xor.ko instead of building a separate module for it.
Signed-off-by: Christoph Hellwig <[email protected]> --- arch/arm/include/asm/xor.h | 190 +----------------- arch/arm/lib/Makefile | 5 - lib/raid/xor/Makefile | 8 + lib/raid/xor/arm/xor-neon-glue.c | 58 ++++++ {arch/arm/lib => lib/raid/xor/arm}/xor-neon.c | 10 +- lib/raid/xor/arm/xor.c | 136 +++++++++++++ 6 files changed, 205 insertions(+), 202 deletions(-) create mode 100644 lib/raid/xor/arm/xor-neon-glue.c rename {arch/arm/lib => lib/raid/xor/arm}/xor-neon.c (74%) create mode 100644 lib/raid/xor/arm/xor.c diff --git a/arch/arm/include/asm/xor.h b/arch/arm/include/asm/xor.h index b2dcd49186e2..989c55872ef6 100644 --- a/arch/arm/include/asm/xor.h +++ b/arch/arm/include/asm/xor.h @@ -1,198 +1,12 @@ /* SPDX-License-Identifier: GPL-2.0-only */ /* - * arch/arm/include/asm/xor.h - * * Copyright (C) 2001 Russell King */ #include <asm-generic/xor.h> -#include <asm/hwcap.h> #include <asm/neon.h> -#define __XOR(a1, a2) a1 ^= a2 - -#define GET_BLOCK_2(dst) \ - __asm__("ldmia %0, {%1, %2}" \ - : "=r" (dst), "=r" (a1), "=r" (a2) \ - : "0" (dst)) - -#define GET_BLOCK_4(dst) \ - __asm__("ldmia %0, {%1, %2, %3, %4}" \ - : "=r" (dst), "=r" (a1), "=r" (a2), "=r" (a3), "=r" (a4) \ - : "0" (dst)) - -#define XOR_BLOCK_2(src) \ - __asm__("ldmia %0!, {%1, %2}" \ - : "=r" (src), "=r" (b1), "=r" (b2) \ - : "0" (src)); \ - __XOR(a1, b1); __XOR(a2, b2); - -#define XOR_BLOCK_4(src) \ - __asm__("ldmia %0!, {%1, %2, %3, %4}" \ - : "=r" (src), "=r" (b1), "=r" (b2), "=r" (b3), "=r" (b4) \ - : "0" (src)); \ - __XOR(a1, b1); __XOR(a2, b2); __XOR(a3, b3); __XOR(a4, b4) - -#define PUT_BLOCK_2(dst) \ - __asm__ __volatile__("stmia %0!, {%2, %3}" \ - : "=r" (dst) \ - : "0" (dst), "r" (a1), "r" (a2)) - -#define PUT_BLOCK_4(dst) \ - __asm__ __volatile__("stmia %0!, {%2, %3, %4, %5}" \ - : "=r" (dst) \ - : "0" (dst), "r" (a1), "r" (a2), "r" (a3), "r" (a4)) - -static void -xor_arm4regs_2(unsigned long bytes, unsigned long * __restrict p1, - const unsigned long * __restrict p2) -{ - unsigned int lines = bytes / sizeof(unsigned long) / 4; - register unsigned int a1 __asm__("r4"); - register unsigned int a2 __asm__("r5"); - register unsigned int a3 __asm__("r6"); - register unsigned int a4 __asm__("r10"); - register unsigned int b1 __asm__("r8"); - register unsigned int b2 __asm__("r9"); - register unsigned int b3 __asm__("ip"); - register unsigned int b4 __asm__("lr"); - - do { - GET_BLOCK_4(p1); - XOR_BLOCK_4(p2); - PUT_BLOCK_4(p1); - } while (--lines); -} - -static void -xor_arm4regs_3(unsigned long bytes, unsigned long * __restrict p1, - const unsigned long * __restrict p2, - const unsigned long * __restrict p3) -{ - unsigned int lines = bytes / sizeof(unsigned long) / 4; - register unsigned int a1 __asm__("r4"); - register unsigned int a2 __asm__("r5"); - register unsigned int a3 __asm__("r6"); - register unsigned int a4 __asm__("r10"); - register unsigned int b1 __asm__("r8"); - register unsigned int b2 __asm__("r9"); - register unsigned int b3 __asm__("ip"); - register unsigned int b4 __asm__("lr"); - - do { - GET_BLOCK_4(p1); - XOR_BLOCK_4(p2); - XOR_BLOCK_4(p3); - PUT_BLOCK_4(p1); - } while (--lines); -} - -static void -xor_arm4regs_4(unsigned long bytes, unsigned long * __restrict p1, - const unsigned long * __restrict p2, - const unsigned long * __restrict p3, - const unsigned long * __restrict p4) -{ - unsigned int lines = bytes / sizeof(unsigned long) / 2; - register unsigned int a1 __asm__("r8"); - register unsigned int a2 __asm__("r9"); - register unsigned int b1 __asm__("ip"); - register unsigned int b2 __asm__("lr"); - - do { - GET_BLOCK_2(p1); - XOR_BLOCK_2(p2); - XOR_BLOCK_2(p3); - XOR_BLOCK_2(p4); - PUT_BLOCK_2(p1); - } while (--lines); -} - -static void -xor_arm4regs_5(unsigned long bytes, unsigned long * __restrict p1, - const unsigned long * __restrict p2, - const unsigned long * __restrict p3, - const unsigned long * __restrict p4, - const unsigned long * __restrict p5) -{ - unsigned int lines = bytes / sizeof(unsigned long) / 2; - register unsigned int a1 __asm__("r8"); - register unsigned int a2 __asm__("r9"); - register unsigned int b1 __asm__("ip"); - register unsigned int b2 __asm__("lr"); - - do { - GET_BLOCK_2(p1); - XOR_BLOCK_2(p2); - XOR_BLOCK_2(p3); - XOR_BLOCK_2(p4); - XOR_BLOCK_2(p5); - PUT_BLOCK_2(p1); - } while (--lines); -} - -static struct xor_block_template xor_block_arm4regs = { - .name = "arm4regs", - .do_2 = xor_arm4regs_2, - .do_3 = xor_arm4regs_3, - .do_4 = xor_arm4regs_4, - .do_5 = xor_arm4regs_5, -}; - -#ifdef CONFIG_KERNEL_MODE_NEON - -extern struct xor_block_template const xor_block_neon_inner; - -static void -xor_neon_2(unsigned long bytes, unsigned long * __restrict p1, - const unsigned long * __restrict p2) -{ - kernel_neon_begin(); - xor_block_neon_inner.do_2(bytes, p1, p2); - kernel_neon_end(); -} - -static void -xor_neon_3(unsigned long bytes, unsigned long * __restrict p1, - const unsigned long * __restrict p2, - const unsigned long * __restrict p3) -{ - kernel_neon_begin(); - xor_block_neon_inner.do_3(bytes, p1, p2, p3); - kernel_neon_end(); -} - -static void -xor_neon_4(unsigned long bytes, unsigned long * __restrict p1, - const unsigned long * __restrict p2, - const unsigned long * __restrict p3, - const unsigned long * __restrict p4) -{ - kernel_neon_begin(); - xor_block_neon_inner.do_4(bytes, p1, p2, p3, p4); - kernel_neon_end(); -} - -static void -xor_neon_5(unsigned long bytes, unsigned long * __restrict p1, - const unsigned long * __restrict p2, - const unsigned long * __restrict p3, - const unsigned long * __restrict p4, - const unsigned long * __restrict p5) -{ - kernel_neon_begin(); - xor_block_neon_inner.do_5(bytes, p1, p2, p3, p4, p5); - kernel_neon_end(); -} - -static struct xor_block_template xor_block_neon = { - .name = "neon", - .do_2 = xor_neon_2, - .do_3 = xor_neon_3, - .do_4 = xor_neon_4, - .do_5 = xor_neon_5 -}; - -#endif /* CONFIG_KERNEL_MODE_NEON */ +extern struct xor_block_template xor_block_arm4regs; +extern struct xor_block_template xor_block_neon; #define arch_xor_init arch_xor_init static __always_inline void __init arch_xor_init(void) diff --git a/arch/arm/lib/Makefile b/arch/arm/lib/Makefile index 0ca5aae1bcc3..9295055cdfc9 100644 --- a/arch/arm/lib/Makefile +++ b/arch/arm/lib/Makefile @@ -39,9 +39,4 @@ endif $(obj)/csumpartialcopy.o: $(obj)/csumpartialcopygeneric.S $(obj)/csumpartialcopyuser.o: $(obj)/csumpartialcopygeneric.S -ifeq ($(CONFIG_KERNEL_MODE_NEON),y) - CFLAGS_xor-neon.o += $(CC_FLAGS_FPU) - obj-$(CONFIG_XOR_BLOCKS) += xor-neon.o -endif - obj-$(CONFIG_FUNCTION_ERROR_INJECTION) += error-inject.o diff --git a/lib/raid/xor/Makefile b/lib/raid/xor/Makefile index 6d03c27c37c7..fb760edae54b 100644 --- a/lib/raid/xor/Makefile +++ b/lib/raid/xor/Makefile @@ -9,3 +9,11 @@ xor-y += xor-8regs-prefetch.o xor-y += xor-32regs-prefetch.o xor-$(CONFIG_ALPHA) += alpha/xor.o +xor-$(CONFIG_ARM) += arm/xor.o +ifeq ($(CONFIG_ARM),y) +xor-$(CONFIG_KERNEL_MODE_NEON) += arm/xor-neon.o arm/xor-neon-glue.o +endif + + +CFLAGS_arm/xor-neon.o += $(CC_FLAGS_FPU) +CFLAGS_REMOVE_arm/xor-neon.o += $(CC_FLAGS_NO_FPU) diff --git a/lib/raid/xor/arm/xor-neon-glue.c b/lib/raid/xor/arm/xor-neon-glue.c new file mode 100644 index 000000000000..c7b162b383a2 --- /dev/null +++ b/lib/raid/xor/arm/xor-neon-glue.c @@ -0,0 +1,58 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (C) 2001 Russell King + */ +#include <linux/raid/xor_impl.h> +#include <asm/xor.h> + +extern struct xor_block_template const xor_block_neon_inner; + +static void +xor_neon_2(unsigned long bytes, unsigned long * __restrict p1, + const unsigned long * __restrict p2) +{ + kernel_neon_begin(); + xor_block_neon_inner.do_2(bytes, p1, p2); + kernel_neon_end(); +} + +static void +xor_neon_3(unsigned long bytes, unsigned long * __restrict p1, + const unsigned long * __restrict p2, + const unsigned long * __restrict p3) +{ + kernel_neon_begin(); + xor_block_neon_inner.do_3(bytes, p1, p2, p3); + kernel_neon_end(); +} + +static void +xor_neon_4(unsigned long bytes, unsigned long * __restrict p1, + const unsigned long * __restrict p2, + const unsigned long * __restrict p3, + const unsigned long * __restrict p4) +{ + kernel_neon_begin(); + xor_block_neon_inner.do_4(bytes, p1, p2, p3, p4); + kernel_neon_end(); +} + +static void +xor_neon_5(unsigned long bytes, unsigned long * __restrict p1, + const unsigned long * __restrict p2, + const unsigned long * __restrict p3, + const unsigned long * __restrict p4, + const unsigned long * __restrict p5) +{ + kernel_neon_begin(); + xor_block_neon_inner.do_5(bytes, p1, p2, p3, p4, p5); + kernel_neon_end(); +} + +struct xor_block_template xor_block_neon = { + .name = "neon", + .do_2 = xor_neon_2, + .do_3 = xor_neon_3, + .do_4 = xor_neon_4, + .do_5 = xor_neon_5 +}; diff --git a/arch/arm/lib/xor-neon.c b/lib/raid/xor/arm/xor-neon.c similarity index 74% rename from arch/arm/lib/xor-neon.c rename to lib/raid/xor/arm/xor-neon.c index b5be50567991..c9d4378b0f0e 100644 --- a/arch/arm/lib/xor-neon.c +++ b/lib/raid/xor/arm/xor-neon.c @@ -1,16 +1,9 @@ // SPDX-License-Identifier: GPL-2.0-only /* - * linux/arch/arm/lib/xor-neon.c - * * Copyright (C) 2013 Linaro Ltd <[email protected]> */ -#include <linux/raid/xor.h> #include <linux/raid/xor_impl.h> -#include <linux/module.h> - -MODULE_DESCRIPTION("NEON accelerated XOR implementation"); -MODULE_LICENSE("GPL"); #ifndef __ARM_NEON__ #error You should compile this file with '-march=armv7-a -mfloat-abi=softfp -mfpu=neon' @@ -27,7 +20,7 @@ MODULE_LICENSE("GPL"); #endif #define NO_TEMPLATE -#include "../../../lib/raid/xor/xor-8regs.c" +#include "../xor-8regs.c" struct xor_block_template const xor_block_neon_inner = { .name = "__inner_neon__", @@ -36,4 +29,3 @@ struct xor_block_template const xor_block_neon_inner = { .do_4 = xor_8regs_4, .do_5 = xor_8regs_5, }; -EXPORT_SYMBOL(xor_block_neon_inner); diff --git a/lib/raid/xor/arm/xor.c b/lib/raid/xor/arm/xor.c new file mode 100644 index 000000000000..2263341dbbcd --- /dev/null +++ b/lib/raid/xor/arm/xor.c @@ -0,0 +1,136 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (C) 2001 Russell King + */ +#include <linux/raid/xor_impl.h> +#include <asm/xor.h> + +#define __XOR(a1, a2) a1 ^= a2 + +#define GET_BLOCK_2(dst) \ + __asm__("ldmia %0, {%1, %2}" \ + : "=r" (dst), "=r" (a1), "=r" (a2) \ + : "0" (dst)) + +#define GET_BLOCK_4(dst) \ + __asm__("ldmia %0, {%1, %2, %3, %4}" \ + : "=r" (dst), "=r" (a1), "=r" (a2), "=r" (a3), "=r" (a4) \ + : "0" (dst)) + +#define XOR_BLOCK_2(src) \ + __asm__("ldmia %0!, {%1, %2}" \ + : "=r" (src), "=r" (b1), "=r" (b2) \ + : "0" (src)); \ + __XOR(a1, b1); __XOR(a2, b2); + +#define XOR_BLOCK_4(src) \ + __asm__("ldmia %0!, {%1, %2, %3, %4}" \ + : "=r" (src), "=r" (b1), "=r" (b2), "=r" (b3), "=r" (b4) \ + : "0" (src)); \ + __XOR(a1, b1); __XOR(a2, b2); __XOR(a3, b3); __XOR(a4, b4) + +#define PUT_BLOCK_2(dst) \ + __asm__ __volatile__("stmia %0!, {%2, %3}" \ + : "=r" (dst) \ + : "0" (dst), "r" (a1), "r" (a2)) + +#define PUT_BLOCK_4(dst) \ + __asm__ __volatile__("stmia %0!, {%2, %3, %4, %5}" \ + : "=r" (dst) \ + : "0" (dst), "r" (a1), "r" (a2), "r" (a3), "r" (a4)) + +static void +xor_arm4regs_2(unsigned long bytes, unsigned long * __restrict p1, + const unsigned long * __restrict p2) +{ + unsigned int lines = bytes / sizeof(unsigned long) / 4; + register unsigned int a1 __asm__("r4"); + register unsigned int a2 __asm__("r5"); + register unsigned int a3 __asm__("r6"); + register unsigned int a4 __asm__("r10"); + register unsigned int b1 __asm__("r8"); + register unsigned int b2 __asm__("r9"); + register unsigned int b3 __asm__("ip"); + register unsigned int b4 __asm__("lr"); + + do { + GET_BLOCK_4(p1); + XOR_BLOCK_4(p2); + PUT_BLOCK_4(p1); + } while (--lines); +} + +static void +xor_arm4regs_3(unsigned long bytes, unsigned long * __restrict p1, + const unsigned long * __restrict p2, + const unsigned long * __restrict p3) +{ + unsigned int lines = bytes / sizeof(unsigned long) / 4; + register unsigned int a1 __asm__("r4"); + register unsigned int a2 __asm__("r5"); + register unsigned int a3 __asm__("r6"); + register unsigned int a4 __asm__("r10"); + register unsigned int b1 __asm__("r8"); + register unsigned int b2 __asm__("r9"); + register unsigned int b3 __asm__("ip"); + register unsigned int b4 __asm__("lr"); + + do { + GET_BLOCK_4(p1); + XOR_BLOCK_4(p2); + XOR_BLOCK_4(p3); + PUT_BLOCK_4(p1); + } while (--lines); +} + +static void +xor_arm4regs_4(unsigned long bytes, unsigned long * __restrict p1, + const unsigned long * __restrict p2, + const unsigned long * __restrict p3, + const unsigned long * __restrict p4) +{ + unsigned int lines = bytes / sizeof(unsigned long) / 2; + register unsigned int a1 __asm__("r8"); + register unsigned int a2 __asm__("r9"); + register unsigned int b1 __asm__("ip"); + register unsigned int b2 __asm__("lr"); + + do { + GET_BLOCK_2(p1); + XOR_BLOCK_2(p2); + XOR_BLOCK_2(p3); + XOR_BLOCK_2(p4); + PUT_BLOCK_2(p1); + } while (--lines); +} + +static void +xor_arm4regs_5(unsigned long bytes, unsigned long * __restrict p1, + const unsigned long * __restrict p2, + const unsigned long * __restrict p3, + const unsigned long * __restrict p4, + const unsigned long * __restrict p5) +{ + unsigned int lines = bytes / sizeof(unsigned long) / 2; + register unsigned int a1 __asm__("r8"); + register unsigned int a2 __asm__("r9"); + register unsigned int b1 __asm__("ip"); + register unsigned int b2 __asm__("lr"); + + do { + GET_BLOCK_2(p1); + XOR_BLOCK_2(p2); + XOR_BLOCK_2(p3); + XOR_BLOCK_2(p4); + XOR_BLOCK_2(p5); + PUT_BLOCK_2(p1); + } while (--lines); +} + +struct xor_block_template xor_block_arm4regs = { + .name = "arm4regs", + .do_2 = xor_arm4regs_2, + .do_3 = xor_arm4regs_3, + .do_4 = xor_arm4regs_4, + .do_5 = xor_arm4regs_5, +}; -- 2.47.3
