arm: move the XOR code to lib/raid/

Move the optimized XOR into lib/raid and include it it in the main xor.ko
instead of building a separate module for it.

Link: https://lkml.kernel.org/r/20260327061704.3707577-13-hch@lst.de
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Eric Biggers <ebiggers@kernel.org>
Tested-by: Eric Biggers <ebiggers@kernel.org>
Cc: Albert Ou <aou@eecs.berkeley.edu>
Cc: Alexander Gordeev <agordeev@linux.ibm.com>
Cc: Alexandre Ghiti <alex@ghiti.fr>
Cc: Andreas Larsson <andreas@gaisler.com>
Cc: Anton Ivanov <anton.ivanov@cambridgegreys.com>
Cc: Ard Biesheuvel <ardb@kernel.org>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: "Borislav Petkov (AMD)" <bp@alien8.de>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Chris Mason <clm@fb.com>
Cc: Christian Borntraeger <borntraeger@linux.ibm.com>
Cc: Dan Williams <dan.j.williams@intel.com>
Cc: David S. Miller <davem@davemloft.net>
Cc: David Sterba <dsterba@suse.com>
Cc: Heiko Carstens <hca@linux.ibm.com>
Cc: Herbert Xu <herbert@gondor.apana.org.au>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Huacai Chen <chenhuacai@kernel.org>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jason A. Donenfeld <jason@zx2c4.com>
Cc: Johannes Berg <johannes@sipsolutions.net>
Cc: Li Nan <linan122@huawei.com>
Cc: Madhavan Srinivasan <maddy@linux.ibm.com>
Cc: Magnus Lindholm <linmag7@gmail.com>
Cc: Matt Turner <mattst88@gmail.com>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Nicholas Piggin <npiggin@gmail.com>
Cc: Palmer Dabbelt <palmer@dabbelt.com>
Cc: Richard Henderson <richard.henderson@linaro.org>
Cc: Richard Weinberger <richard@nod.at>
Cc: Russell King <linux@armlinux.org.uk>
Cc: Song Liu <song@kernel.org>
Cc: Sven Schnelle <svens@linux.ibm.com>
Cc: Ted Ts'o <tytso@mit.edu>
Cc: Vasily Gorbik <gor@linux.ibm.com>
Cc: WANG Xuerui <kernel@xen0n.name>
Cc: Will Deacon <will@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

4 files changed, 233 insertions, 0 deletions

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/lib/raid/xor/arm/xor-neon.c b/lib/raid/xor/arm/xor-neon.c
new file mode 100644
index 000000000000..c9d4378b0f0e
--- /dev/null
+++ b/lib/raid/xor/arm/xor-neon.c
@@ -0,0 +1,31 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2013 Linaro Ltd <ard.biesheuvel@linaro.org>
+ */
+
+#include <linux/raid/xor_impl.h>
+
+#ifndef __ARM_NEON__
+#error You should compile this file with '-march=armv7-a -mfloat-abi=softfp -mfpu=neon'
+#endif
+
+/*
+ * Pull in the reference implementations while instructing GCC (through
+ * -ftree-vectorize) to attempt to exploit implicit parallelism and emit
+ * NEON instructions. Clang does this by default at O2 so no pragma is
+ * needed.
+ */
+#ifdef CONFIG_CC_IS_GCC
+#pragma GCC optimize "tree-vectorize"
+#endif
+
+#define NO_TEMPLATE
+#include "../xor-8regs.c"
+
+struct xor_block_template const xor_block_neon_inner = {
+	.name	= "__inner_neon__",
+	.do_2	= xor_8regs_2,
+	.do_3	= xor_8regs_3,
+	.do_4	= xor_8regs_4,
+	.do_5	= xor_8regs_5,
+};
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,
+};