Move the optimized XOR into lib/raid and include it it in xor.ko instead of always building it into the main kernel image.
Signed-off-by: Christoph Hellwig <[email protected]> --- arch/powerpc/include/asm/xor.h | 17 +---- arch/powerpc/include/asm/xor_altivec.h | 22 ------ arch/powerpc/lib/Makefile | 5 -- arch/powerpc/lib/xor_vmx_glue.c | 63 ----------------- lib/raid/xor/Makefile | 5 ++ .../lib => lib/raid/xor/powerpc}/xor_vmx.c | 0 .../lib => lib/raid/xor/powerpc}/xor_vmx.h | 0 lib/raid/xor/powerpc/xor_vmx_glue.c | 67 +++++++++++++++++++ 8 files changed, 74 insertions(+), 105 deletions(-) delete mode 100644 arch/powerpc/include/asm/xor_altivec.h delete mode 100644 arch/powerpc/lib/xor_vmx_glue.c rename {arch/powerpc/lib => lib/raid/xor/powerpc}/xor_vmx.c (100%) rename {arch/powerpc/lib => lib/raid/xor/powerpc}/xor_vmx.h (100%) create mode 100644 lib/raid/xor/powerpc/xor_vmx_glue.c diff --git a/arch/powerpc/include/asm/xor.h b/arch/powerpc/include/asm/xor.h index 30224c5279c4..3293ac87181c 100644 --- a/arch/powerpc/include/asm/xor.h +++ b/arch/powerpc/include/asm/xor.h @@ -8,24 +8,11 @@ #ifndef _ASM_POWERPC_XOR_H #define _ASM_POWERPC_XOR_H -#ifdef CONFIG_ALTIVEC - -#include <asm/cputable.h> #include <asm/cpu_has_feature.h> -#include <asm/xor_altivec.h> - -static struct xor_block_template xor_block_altivec = { - .name = "altivec", - .do_2 = xor_altivec_2, - .do_3 = xor_altivec_3, - .do_4 = xor_altivec_4, - .do_5 = xor_altivec_5, -}; -#endif /* CONFIG_ALTIVEC */ - -/* Also try the generic routines. */ #include <asm-generic/xor.h> +extern struct xor_block_template xor_block_altivec; + #define arch_xor_init arch_xor_init static __always_inline void __init arch_xor_init(void) { diff --git a/arch/powerpc/include/asm/xor_altivec.h b/arch/powerpc/include/asm/xor_altivec.h deleted file mode 100644 index 294620a25f80..000000000000 --- a/arch/powerpc/include/asm/xor_altivec.h +++ /dev/null @@ -1,22 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef _ASM_POWERPC_XOR_ALTIVEC_H -#define _ASM_POWERPC_XOR_ALTIVEC_H - -#ifdef CONFIG_ALTIVEC -void xor_altivec_2(unsigned long bytes, unsigned long * __restrict p1, - const unsigned long * __restrict p2); -void xor_altivec_3(unsigned long bytes, unsigned long * __restrict p1, - const unsigned long * __restrict p2, - const unsigned long * __restrict p3); -void xor_altivec_4(unsigned long bytes, unsigned long * __restrict p1, - const unsigned long * __restrict p2, - const unsigned long * __restrict p3, - const unsigned long * __restrict p4); -void xor_altivec_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); - -#endif -#endif /* _ASM_POWERPC_XOR_ALTIVEC_H */ diff --git a/arch/powerpc/lib/Makefile b/arch/powerpc/lib/Makefile index f14ecab674a3..002edc3f01d5 100644 --- a/arch/powerpc/lib/Makefile +++ b/arch/powerpc/lib/Makefile @@ -73,9 +73,4 @@ obj-$(CONFIG_PPC_LIB_RHEAP) += rheap.o obj-$(CONFIG_FTR_FIXUP_SELFTEST) += feature-fixups-test.o -obj-$(CONFIG_ALTIVEC) += xor_vmx.o xor_vmx_glue.o -CFLAGS_xor_vmx.o += -mhard-float -maltivec $(call cc-option,-mabi=altivec) -# Enable <altivec.h> -CFLAGS_xor_vmx.o += -isystem $(shell $(CC) -print-file-name=include) - obj-$(CONFIG_PPC64) += $(obj64-y) diff --git a/arch/powerpc/lib/xor_vmx_glue.c b/arch/powerpc/lib/xor_vmx_glue.c deleted file mode 100644 index 35d917ece4d1..000000000000 --- a/arch/powerpc/lib/xor_vmx_glue.c +++ /dev/null @@ -1,63 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-or-later -/* - * Altivec XOR operations - * - * Copyright 2017 IBM Corp. - */ - -#include <linux/preempt.h> -#include <linux/export.h> -#include <linux/sched.h> -#include <asm/switch_to.h> -#include <asm/xor_altivec.h> -#include "xor_vmx.h" - -void xor_altivec_2(unsigned long bytes, unsigned long * __restrict p1, - const unsigned long * __restrict p2) -{ - preempt_disable(); - enable_kernel_altivec(); - __xor_altivec_2(bytes, p1, p2); - disable_kernel_altivec(); - preempt_enable(); -} -EXPORT_SYMBOL(xor_altivec_2); - -void xor_altivec_3(unsigned long bytes, unsigned long * __restrict p1, - const unsigned long * __restrict p2, - const unsigned long * __restrict p3) -{ - preempt_disable(); - enable_kernel_altivec(); - __xor_altivec_3(bytes, p1, p2, p3); - disable_kernel_altivec(); - preempt_enable(); -} -EXPORT_SYMBOL(xor_altivec_3); - -void xor_altivec_4(unsigned long bytes, unsigned long * __restrict p1, - const unsigned long * __restrict p2, - const unsigned long * __restrict p3, - const unsigned long * __restrict p4) -{ - preempt_disable(); - enable_kernel_altivec(); - __xor_altivec_4(bytes, p1, p2, p3, p4); - disable_kernel_altivec(); - preempt_enable(); -} -EXPORT_SYMBOL(xor_altivec_4); - -void xor_altivec_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) -{ - preempt_disable(); - enable_kernel_altivec(); - __xor_altivec_5(bytes, p1, p2, p3, p4, p5); - disable_kernel_altivec(); - preempt_enable(); -} -EXPORT_SYMBOL(xor_altivec_5); diff --git a/lib/raid/xor/Makefile b/lib/raid/xor/Makefile index fafd131cef27..3df9e04a1a9b 100644 --- a/lib/raid/xor/Makefile +++ b/lib/raid/xor/Makefile @@ -17,6 +17,7 @@ xor-$(CONFIG_KERNEL_MODE_NEON) += arm64/xor-neon.o arm64/xor-neon-glue.o endif xor-$(CONFIG_CPU_HAS_LSX) += loongarch/xor_simd.o xor-$(CONFIG_CPU_HAS_LSX) += loongarch/xor_simd_glue.o +xor-$(CONFIG_ALTIVEC) += powerpc/xor_vmx.o powerpc/xor_vmx_glue.o CFLAGS_arm/xor-neon.o += $(CC_FLAGS_FPU) @@ -24,3 +25,7 @@ CFLAGS_REMOVE_arm/xor-neon.o += $(CC_FLAGS_NO_FPU) CFLAGS_arm64/xor-neon.o += $(CC_FLAGS_FPU) CFLAGS_REMOVE_arm64/xor-neon.o += $(CC_FLAGS_NO_FPU) + +CFLAGS_powerpc/xor_vmx.o += -mhard-float -maltivec \ + $(call cc-option,-mabi=altivec) \ + -isystem $(shell $(CC) -print-file-name=include) diff --git a/arch/powerpc/lib/xor_vmx.c b/lib/raid/xor/powerpc/xor_vmx.c similarity index 100% rename from arch/powerpc/lib/xor_vmx.c rename to lib/raid/xor/powerpc/xor_vmx.c diff --git a/arch/powerpc/lib/xor_vmx.h b/lib/raid/xor/powerpc/xor_vmx.h similarity index 100% rename from arch/powerpc/lib/xor_vmx.h rename to lib/raid/xor/powerpc/xor_vmx.h diff --git a/lib/raid/xor/powerpc/xor_vmx_glue.c b/lib/raid/xor/powerpc/xor_vmx_glue.c new file mode 100644 index 000000000000..c41e38340700 --- /dev/null +++ b/lib/raid/xor/powerpc/xor_vmx_glue.c @@ -0,0 +1,67 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * Altivec XOR operations + * + * Copyright 2017 IBM Corp. + */ + +#include <linux/preempt.h> +#include <linux/sched.h> +#include <linux/raid/xor_impl.h> +#include <asm/switch_to.h> +#include <asm/xor.h> +#include "xor_vmx.h" + +static void xor_altivec_2(unsigned long bytes, unsigned long * __restrict p1, + const unsigned long * __restrict p2) +{ + preempt_disable(); + enable_kernel_altivec(); + __xor_altivec_2(bytes, p1, p2); + disable_kernel_altivec(); + preempt_enable(); +} + +static void xor_altivec_3(unsigned long bytes, unsigned long * __restrict p1, + const unsigned long * __restrict p2, + const unsigned long * __restrict p3) +{ + preempt_disable(); + enable_kernel_altivec(); + __xor_altivec_3(bytes, p1, p2, p3); + disable_kernel_altivec(); + preempt_enable(); +} + +static void xor_altivec_4(unsigned long bytes, unsigned long * __restrict p1, + const unsigned long * __restrict p2, + const unsigned long * __restrict p3, + const unsigned long * __restrict p4) +{ + preempt_disable(); + enable_kernel_altivec(); + __xor_altivec_4(bytes, p1, p2, p3, p4); + disable_kernel_altivec(); + preempt_enable(); +} + +static void xor_altivec_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) +{ + preempt_disable(); + enable_kernel_altivec(); + __xor_altivec_5(bytes, p1, p2, p3, p4, p5); + disable_kernel_altivec(); + preempt_enable(); +} + +struct xor_block_template xor_block_altivec = { + .name = "altivec", + .do_2 = xor_altivec_2, + .do_3 = xor_altivec_3, + .do_4 = xor_altivec_4, + .do_5 = xor_altivec_5, +}; -- 2.47.3
