@@ -1,8 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _ASM_UM_XOR_H
-#define _ASM_UM_XOR_H
-
-#include <asm/cpufeature.h>
-#include <../../x86/include/asm/xor.h>
-
-#endif

@@ -65,4 +65,3 @@ mandatory-y += vermagic.h
 mandatory-y += vga.h
 mandatory-y += video.h
 mandatory-y += word-at-a-time.h
-mandatory-y += xor.h

@@ -1,11 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-or-later */
-/*
- * include/asm-generic/xor.h
- *
- * Generic optimized RAID-5 checksumming functions.
- */
-
-extern struct xor_block_template xor_block_8regs;
-extern struct xor_block_template xor_block_32regs;
-extern struct xor_block_template xor_block_8regs_p;
-extern struct xor_block_template xor_block_32regs_p;

@@ -2,3 +2,18 @@
 
 config XOR_BLOCKS
 	tristate
+
+# selected by architectures that provide an optimized XOR implementation
+config XOR_BLOCKS_ARCH
+	depends on XOR_BLOCKS
+	default y if ALPHA
+	default y if ARM && KERNEL_MODE_NEON
+	default y if ARM64
+	default y if CPU_HAS_LSX		# loongarch
+	default y if ALTIVEC			# powerpc
+	default y if RISCV_ISA_V
+	default y if SPARC
+	default y if S390
+	default y if X86_32
+	default y if X86_64
+	bool

@@ -1,5 +1,7 @@
 # SPDX-License-Identifier: GPL-2.0
 
+ccflags-y			+= -I $(src)
+
 obj-$(CONFIG_XOR_BLOCKS)	+= xor.o
 
 xor-y				+= xor-core.o

@@ -8,6 +10,10 @@ xor-y				+= xor-32regs.o
 xor-y				+= xor-8regs-prefetch.o
 xor-y				+= xor-32regs-prefetch.o
 
+ifeq ($(CONFIG_XOR_BLOCKS_ARCH),y)
+CFLAGS_xor-core.o		+= -I$(src)/$(SRCARCH)
+endif
+
 xor-$(CONFIG_ALPHA)		+= alpha/xor.o
 xor-$(CONFIG_ARM)		+= arm/xor.o
 ifeq ($(CONFIG_ARM),y)

@@ -2,8 +2,8 @@
 /*
  * Optimized XOR parity functions for alpha EV5 and EV6
  */
-#include <linux/raid/xor_impl.h>
-#include <asm/xor.h>
+#include "xor_impl.h"
+#include "xor_arch.h"
 
 extern void
 xor_alpha_2(unsigned long bytes, unsigned long * __restrict p1,

@@ -1,7 +1,6 @@
 /* SPDX-License-Identifier: GPL-2.0-or-later */
 
 #include <asm/special_insns.h>
-#include <asm-generic/xor.h>
 
 extern struct xor_block_template xor_block_alpha;
 extern struct xor_block_template xor_block_alpha_prefetch;

@@ -10,7 +9,6 @@ extern struct xor_block_template xor_block_alpha_prefetch;
  * Force the use of alpha_prefetch if EV6, as it is significantly faster in the
  * cold cache case.
  */
-#define arch_xor_init arch_xor_init
 static __always_inline void __init arch_xor_init(void)
 {
 	if (implver() == IMPLVER_EV6) {

@@ -2,8 +2,8 @@
 /*
  *  Copyright (C) 2001 Russell King
  */
-#include <linux/raid/xor_impl.h>
-#include <asm/xor.h>
+#include "xor_impl.h"
+#include "xor_arch.h"
 
 extern struct xor_block_template const xor_block_neon_inner;
 

@@ -3,7 +3,7 @@
  * Copyright (C) 2013 Linaro Ltd <ard.biesheuvel@linaro.org>
  */
 
-#include <linux/raid/xor_impl.h>
+#include "xor_impl.h"
 
 #ifndef __ARM_NEON__
 #error You should compile this file with '-march=armv7-a -mfloat-abi=softfp -mfpu=neon'

@@ -2,8 +2,8 @@
 /*
  *  Copyright (C) 2001 Russell King
  */
-#include <linux/raid/xor_impl.h>
-#include <asm/xor.h>
+#include "xor_impl.h"
+#include "xor_arch.h"
 
 #define __XOR(a1, a2) a1 ^= a2
 

@@ -2,13 +2,11 @@
 /*
  *  Copyright (C) 2001 Russell King
  */
-#include <asm-generic/xor.h>
 #include <asm/neon.h>
 
 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)
 {
 	xor_register(&xor_block_arm4regs);

@@ -4,9 +4,9 @@
  * Copyright (C) 2018,Tianjin KYLIN Information Technology Co., Ltd.
  */
 
-#include <linux/raid/xor_impl.h>
 #include <asm/simd.h>
-#include <asm/xor.h>
+#include "xor_impl.h"
+#include "xor_arch.h"
 #include "xor-neon.h"
 
 #define XOR_TEMPLATE(_name)						\

@@ -4,10 +4,10 @@
  * Copyright (C) 2018,Tianjin KYLIN Information Technology Co., Ltd.
  */
 
-#include <linux/raid/xor_impl.h>
 #include <linux/cache.h>
 #include <asm/neon-intrinsics.h>
-#include <asm/xor.h>
+#include "xor_impl.h"
+#include "xor_arch.h"
 #include "xor-neon.h"
 
 void __xor_neon_2(unsigned long bytes, unsigned long * __restrict p1,

@@ -3,14 +3,11 @@
  * Authors: Jackie Liu <liuyun01@kylinos.cn>
  * Copyright (C) 2018,Tianjin KYLIN Information Technology Co., Ltd.
  */
-
-#include <asm-generic/xor.h>
 #include <asm/simd.h>
 
 extern struct xor_block_template xor_block_neon;
 extern struct xor_block_template xor_block_eor3;
 
-#define arch_xor_init arch_xor_init
 static __always_inline void __init arch_xor_init(void)
 {
 	xor_register(&xor_block_8regs);

@@ -2,9 +2,6 @@
 /*
  * Copyright (C) 2023 WANG Xuerui <git@xen0n.name>
  */
-#ifndef _ASM_LOONGARCH_XOR_H
-#define _ASM_LOONGARCH_XOR_H
-
 #include <asm/cpu-features.h>
 
 /*

@@ -15,12 +12,10 @@
  * the scalar ones, maybe for errata or micro-op reasons. It may be
  * appropriate to revisit this after one or two more uarch generations.
  */
-#include <asm-generic/xor.h>
 
 extern struct xor_block_template xor_block_lsx;
 extern struct xor_block_template xor_block_lasx;
 
-#define arch_xor_init arch_xor_init
 static __always_inline void __init arch_xor_init(void)
 {
 	xor_register(&xor_block_8regs);

@@ -36,5 +31,3 @@ static __always_inline void __init arch_xor_init(void)
 		xor_register(&xor_block_lasx);
 #endif
 }
-
-#endif /* _ASM_LOONGARCH_XOR_H */

@@ -6,9 +6,9 @@
  */
 
 #include <linux/sched.h>
-#include <linux/raid/xor_impl.h>
 #include <asm/fpu.h>
-#include <asm/xor.h>
+#include "xor_impl.h"
+#include "xor_arch.h"
 #include "xor_simd.h"
 
 #define MAKE_XOR_GLUE_2(flavor)							\

@@ -5,15 +5,10 @@
  *
  * Author: Anton Blanchard <anton@au.ibm.com>
  */
-#ifndef _ASM_POWERPC_XOR_H
-#define _ASM_POWERPC_XOR_H
-
 #include <asm/cpu_has_feature.h>
-#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)
 {
 	xor_register(&xor_block_8regs);

@@ -25,5 +20,3 @@ static __always_inline void __init arch_xor_init(void)
 		xor_register(&xor_block_altivec);
 #endif
 }
-
-#endif /* _ASM_POWERPC_XOR_H */

@@ -7,9 +7,9 @@
 
 #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_impl.h"
+#include "xor_arch.h"
 #include "xor_vmx.h"
 
 static void xor_altivec_2(unsigned long bytes, unsigned long * __restrict p1,

@@ -3,11 +3,11 @@
  * Copyright (C) 2021 SiFive
  */
 
-#include <linux/raid/xor_impl.h>
 #include <asm/vector.h>
 #include <asm/switch_to.h>
 #include <asm/asm-prototypes.h>
-#include <asm/xor.h>
+#include "xor_impl.h"
+#include "xor_arch.h"
 
 static void xor_vector_2(unsigned long bytes, unsigned long *__restrict p1,
 			 const unsigned long *__restrict p2)

@@ -3,11 +3,9 @@
  * Copyright (C) 2021 SiFive
  */
 #include <asm/vector.h>
-#include <asm-generic/xor.h>
 
 extern struct xor_block_template xor_block_rvv;
 
-#define arch_xor_init arch_xor_init
 static __always_inline void __init arch_xor_init(void)
 {
 	xor_register(&xor_block_8regs);

@@ -7,8 +7,8 @@
  */
 
 #include <linux/types.h>
-#include <linux/raid/xor_impl.h>
-#include <asm/xor.h>
+#include "xor_impl.h"
+#include "xor_arch.h"
 
 static void xor_xc_2(unsigned long bytes, unsigned long * __restrict p1,
 		     const unsigned long * __restrict p2)

@@ -5,15 +5,9 @@
  * Copyright IBM Corp. 2016
  * Author(s): Martin Schwidefsky <schwidefsky@de.ibm.com>
  */
-#ifndef _ASM_S390_XOR_H
-#define _ASM_S390_XOR_H
-
 extern struct xor_block_template xor_block_xc;
 
-#define arch_xor_init arch_xor_init
 static __always_inline void __init arch_xor_init(void)
 {
 	xor_force(&xor_block_xc);
 }
-
-#endif /* _ASM_S390_XOR_H */

@@ -5,8 +5,8 @@
  *
  * Copyright (C) 1999 Jakub Jelinek (jj@ultra.linux.cz)
  */
-#include <linux/raid/xor_impl.h>
-#include <asm/xor.h>
+#include "xor_impl.h"
+#include "xor_arch.h"
 
 static void
 sparc_2(unsigned long bytes, unsigned long * __restrict p1,

@@ -8,8 +8,8 @@
  * Copyright (C) 2006 David S. Miller <davem@davemloft.net>
  */
 
-#include <linux/raid/xor_impl.h>
-#include <asm/xor.h>
+#include "xor_impl.h"
+#include "xor_arch.h"
 
 void xor_vis_2(unsigned long bytes, unsigned long * __restrict p1,
 	       const unsigned long * __restrict p2);

@@ -3,16 +3,12 @@
  * Copyright (C) 1997, 1999 Jakub Jelinek (jj@ultra.linux.cz)
  * Copyright (C) 2006 David S. Miller <davem@davemloft.net>
  */
-#ifndef ___ASM_SPARC_XOR_H
-#define ___ASM_SPARC_XOR_H
-
 #if defined(__sparc__) && defined(__arch64__)
 #include <asm/spitfire.h>
 
 extern struct xor_block_template xor_block_VIS;
 extern struct xor_block_template xor_block_niagara;
 
-#define arch_xor_init arch_xor_init
 static __always_inline void __init arch_xor_init(void)
 {
 	/* Force VIS for everything except Niagara.  */

@@ -28,12 +24,8 @@ static __always_inline void __init arch_xor_init(void)
 }
 #else /* sparc64 */
 
-/* For grins, also test the generic routines.  */
-#include <asm-generic/xor.h>
-
 extern struct xor_block_template xor_block_SPARC;
 
-#define arch_xor_init arch_xor_init
 static __always_inline void __init arch_xor_init(void)
 {
 	xor_register(&xor_block_8regs);

@@ -41,4 +33,3 @@ static __always_inline void __init arch_xor_init(void)
 	xor_register(&xor_block_SPARC);
 }
 #endif /* !sparc64 */
-#endif /* ___ASM_SPARC_XOR_H */

@@ -0,0 +1,2 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#include <../x86/xor_arch.h>

@@ -8,9 +8,9 @@
  * Based on Ingo Molnar and Zach Brown's respective MMX and SSE routines
  */
 #include <linux/compiler.h>
-#include <linux/raid/xor_impl.h>
 #include <asm/fpu/api.h>
-#include <asm/xor.h>
+#include "xor_impl.h"
+#include "xor_arch.h"
 
 #define BLOCK4(i) \
 		BLOCK(32 * i, 0) \

@@ -4,9 +4,9 @@
  *
  * Copyright (C) 1998 Ingo Molnar.
  */
-#include <linux/raid/xor_impl.h>
 #include <asm/fpu/api.h>
-#include <asm/xor.h>
+#include "xor_impl.h"
+#include "xor_arch.h"
 
 #define LD(x, y)	"       movq   8*("#x")(%1), %%mm"#y"   ;\n"
 #define ST(x, y)	"       movq %%mm"#y",   8*("#x")(%1)   ;\n"

@@ -12,9 +12,9 @@
  * x86-64 changes / gcc fixes from Andi Kleen.
  * Copyright 2002 Andi Kleen, SuSE Labs.
  */
-#include <linux/raid/xor_impl.h>
 #include <asm/fpu/api.h>
-#include <asm/xor.h>
+#include "xor_impl.h"
+#include "xor_arch.h"
 
 #ifdef CONFIG_X86_32
 /* reduce register pressure */

@@ -1,9 +1,5 @@
 /* SPDX-License-Identifier: GPL-2.0-or-later */
-#ifndef _ASM_X86_XOR_H
-#define _ASM_X86_XOR_H
-
 #include <asm/cpufeature.h>
-#include <asm-generic/xor.h>
 
 extern struct xor_block_template xor_block_pII_mmx;
 extern struct xor_block_template xor_block_p5_mmx;

@@ -20,7 +16,6 @@ extern struct xor_block_template xor_block_avx;
  *
  * 32-bit without MMX can fall back to the generic routines.
  */
-#define arch_xor_init arch_xor_init
 static __always_inline void __init arch_xor_init(void)
 {
 	if (boot_cpu_has(X86_FEATURE_AVX) &&

@@ -39,5 +34,3 @@ static __always_inline void __init arch_xor_init(void)
 		xor_register(&xor_block_32regs_p);
 	}
 }
-
-#endif /* _ASM_X86_XOR_H */

@@ -1,7 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0-or-later
 #include <linux/prefetch.h>
-#include <linux/raid/xor_impl.h>
-#include <asm-generic/xor.h>
+#include "xor_impl.h"
 
 static void
 xor_32regs_p_2(unsigned long bytes, unsigned long * __restrict p1,

@@ -1,6 +1,5 @@
 // SPDX-License-Identifier: GPL-2.0-or-later
-#include <linux/raid/xor_impl.h>
-#include <asm-generic/xor.h>
+#include "xor_impl.h"
 
 static void
 xor_32regs_2(unsigned long bytes, unsigned long * __restrict p1,

@@ -1,7 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0-or-later
 #include <linux/prefetch.h>
-#include <linux/raid/xor_impl.h>
-#include <asm-generic/xor.h>
+#include "xor_impl.h"
 
 static void
 xor_8regs_p_2(unsigned long bytes, unsigned long * __restrict p1,

@@ -1,6 +1,5 @@
 // SPDX-License-Identifier: GPL-2.0-or-later
-#include <linux/raid/xor_impl.h>
-#include <asm-generic/xor.h>
+#include "xor_impl.h"
 
 static void
 xor_8regs_2(unsigned long bytes, unsigned long * __restrict p1,

@@ -9,10 +9,9 @@
 #include <linux/module.h>
 #include <linux/gfp.h>
 #include <linux/raid/xor.h>
-#include <linux/raid/xor_impl.h>
 #include <linux/jiffies.h>
 #include <linux/preempt.h>
-#include <asm/xor.h>
+#include "xor_impl.h"
 
 /* The xor routines to use.  */
 static struct xor_block_template *active_template;

@@ -141,16 +140,21 @@ static int __init calibrate_xor_blocks(void)
 	return 0;
 }
 
-static int __init xor_init(void)
-{
-#ifdef arch_xor_init
-	arch_xor_init();
+#ifdef CONFIG_XOR_BLOCKS_ARCH
+#include "xor_arch.h" /* $SRCARCH/xor_arch.h */
 #else
+static void __init arch_xor_init(void)
+{
 	xor_register(&xor_block_8regs);
 	xor_register(&xor_block_8regs_p);
 	xor_register(&xor_block_32regs);
 	xor_register(&xor_block_32regs_p);
-#endif
+}
+#endif /* CONFIG_XOR_BLOCKS_ARCH */
+
+static int __init xor_init(void)
+{
+	arch_xor_init();
 
 	/*
 	 * If this arch/cpu has a short-circuited selection, don't loop through

@@ -24,6 +24,12 @@ struct xor_block_template {
 		     const unsigned long * __restrict);
 };
 
+/* generic implementations */
+extern struct xor_block_template xor_block_8regs;
+extern struct xor_block_template xor_block_32regs;
+extern struct xor_block_template xor_block_8regs_p;
+extern struct xor_block_template xor_block_32regs_p;
+
 void __init xor_register(struct xor_block_template *tmpl);
 void __init xor_force(struct xor_block_template *tmpl);