arm64: 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.

Note that this drops the CONFIG_KERNEL_MODE_NEON dependency, as that is
always set for arm64.

Link: https://lkml.kernel.org/r/20260327061704.3707577-14-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>

3 files changed, 386 insertions, 0 deletions

diff --git a/lib/raid/xor/Makefile b/lib/raid/xor/Makefile
index fb760edae54b..4ab0e7411ff7 100644
--- a/lib/raid/xor/Makefile
+++ b/lib/raid/xor/Makefile
@@ -13,7 +13,11 @@ xor-$(CONFIG_ARM)		+= arm/xor.o
 ifeq ($(CONFIG_ARM),y)
 xor-$(CONFIG_KERNEL_MODE_NEON)	+= arm/xor-neon.o arm/xor-neon-glue.o
 endif
+xor-$(CONFIG_ARM64)		+= arm64/xor-neon.o arm64/xor-neon-glue.o
 
 
 CFLAGS_arm/xor-neon.o		+= $(CC_FLAGS_FPU)
 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)
diff --git a/lib/raid/xor/arm64/xor-neon-glue.c b/lib/raid/xor/arm64/xor-neon-glue.c
new file mode 100644
index 000000000000..067a2095659a
--- /dev/null
+++ b/lib/raid/xor/arm64/xor-neon-glue.c
@@ -0,0 +1,57 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Authors: Jackie Liu <liuyun01@kylinos.cn>
+ * Copyright (C) 2018,Tianjin KYLIN Information Technology Co., Ltd.
+ */
+
+#include <linux/raid/xor_impl.h>
+#include <asm/simd.h>
+#include <asm/xor.h>
+
+extern struct xor_block_template const xor_block_inner_neon;
+
+static void
+xor_neon_2(unsigned long bytes, unsigned long * __restrict p1,
+	   const unsigned long * __restrict p2)
+{
+	scoped_ksimd()
+		xor_block_inner_neon.do_2(bytes, p1, p2);
+}
+
+static void
+xor_neon_3(unsigned long bytes, unsigned long * __restrict p1,
+	   const unsigned long * __restrict p2,
+	   const unsigned long * __restrict p3)
+{
+	scoped_ksimd()
+		xor_block_inner_neon.do_3(bytes, p1, p2, p3);
+}
+
+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)
+{
+	scoped_ksimd()
+		xor_block_inner_neon.do_4(bytes, p1, p2, p3, p4);
+}
+
+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)
+{
+	scoped_ksimd()
+		xor_block_inner_neon.do_5(bytes, p1, p2, p3, p4, p5);
+}
+
+struct xor_block_template xor_block_arm64 = {
+	.name   = "arm64_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/arm64/xor-neon.c b/lib/raid/xor/arm64/xor-neon.c
new file mode 100644
index 000000000000..8d2d185090db
--- /dev/null
+++ b/lib/raid/xor/arm64/xor-neon.c
@@ -0,0 +1,325 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Authors: Jackie Liu <liuyun01@kylinos.cn>
+ * 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>
+
+static void xor_arm64_neon_2(unsigned long bytes, unsigned long * __restrict p1,
+	const unsigned long * __restrict p2)
+{
+	uint64_t *dp1 = (uint64_t *)p1;
+	uint64_t *dp2 = (uint64_t *)p2;
+
+	register uint64x2_t v0, v1, v2, v3;
+	long lines = bytes / (sizeof(uint64x2_t) * 4);
+
+	do {
+		/* p1 ^= p2 */
+		v0 = veorq_u64(vld1q_u64(dp1 +  0), vld1q_u64(dp2 +  0));
+		v1 = veorq_u64(vld1q_u64(dp1 +  2), vld1q_u64(dp2 +  2));
+		v2 = veorq_u64(vld1q_u64(dp1 +  4), vld1q_u64(dp2 +  4));
+		v3 = veorq_u64(vld1q_u64(dp1 +  6), vld1q_u64(dp2 +  6));
+
+		/* store */
+		vst1q_u64(dp1 +  0, v0);
+		vst1q_u64(dp1 +  2, v1);
+		vst1q_u64(dp1 +  4, v2);
+		vst1q_u64(dp1 +  6, v3);
+
+		dp1 += 8;
+		dp2 += 8;
+	} while (--lines > 0);
+}
+
+static void xor_arm64_neon_3(unsigned long bytes, unsigned long * __restrict p1,
+	const unsigned long * __restrict p2,
+	const unsigned long * __restrict p3)
+{
+	uint64_t *dp1 = (uint64_t *)p1;
+	uint64_t *dp2 = (uint64_t *)p2;
+	uint64_t *dp3 = (uint64_t *)p3;
+
+	register uint64x2_t v0, v1, v2, v3;
+	long lines = bytes / (sizeof(uint64x2_t) * 4);
+
+	do {
+		/* p1 ^= p2 */
+		v0 = veorq_u64(vld1q_u64(dp1 +  0), vld1q_u64(dp2 +  0));
+		v1 = veorq_u64(vld1q_u64(dp1 +  2), vld1q_u64(dp2 +  2));
+		v2 = veorq_u64(vld1q_u64(dp1 +  4), vld1q_u64(dp2 +  4));
+		v3 = veorq_u64(vld1q_u64(dp1 +  6), vld1q_u64(dp2 +  6));
+
+		/* p1 ^= p3 */
+		v0 = veorq_u64(v0, vld1q_u64(dp3 +  0));
+		v1 = veorq_u64(v1, vld1q_u64(dp3 +  2));
+		v2 = veorq_u64(v2, vld1q_u64(dp3 +  4));
+		v3 = veorq_u64(v3, vld1q_u64(dp3 +  6));
+
+		/* store */
+		vst1q_u64(dp1 +  0, v0);
+		vst1q_u64(dp1 +  2, v1);
+		vst1q_u64(dp1 +  4, v2);
+		vst1q_u64(dp1 +  6, v3);
+
+		dp1 += 8;
+		dp2 += 8;
+		dp3 += 8;
+	} while (--lines > 0);
+}
+
+static void xor_arm64_neon_4(unsigned long bytes, unsigned long * __restrict p1,
+	const unsigned long * __restrict p2,
+	const unsigned long * __restrict p3,
+	const unsigned long * __restrict p4)
+{
+	uint64_t *dp1 = (uint64_t *)p1;
+	uint64_t *dp2 = (uint64_t *)p2;
+	uint64_t *dp3 = (uint64_t *)p3;
+	uint64_t *dp4 = (uint64_t *)p4;
+
+	register uint64x2_t v0, v1, v2, v3;
+	long lines = bytes / (sizeof(uint64x2_t) * 4);
+
+	do {
+		/* p1 ^= p2 */
+		v0 = veorq_u64(vld1q_u64(dp1 +  0), vld1q_u64(dp2 +  0));
+		v1 = veorq_u64(vld1q_u64(dp1 +  2), vld1q_u64(dp2 +  2));
+		v2 = veorq_u64(vld1q_u64(dp1 +  4), vld1q_u64(dp2 +  4));
+		v3 = veorq_u64(vld1q_u64(dp1 +  6), vld1q_u64(dp2 +  6));
+
+		/* p1 ^= p3 */
+		v0 = veorq_u64(v0, vld1q_u64(dp3 +  0));
+		v1 = veorq_u64(v1, vld1q_u64(dp3 +  2));
+		v2 = veorq_u64(v2, vld1q_u64(dp3 +  4));
+		v3 = veorq_u64(v3, vld1q_u64(dp3 +  6));
+
+		/* p1 ^= p4 */
+		v0 = veorq_u64(v0, vld1q_u64(dp4 +  0));
+		v1 = veorq_u64(v1, vld1q_u64(dp4 +  2));
+		v2 = veorq_u64(v2, vld1q_u64(dp4 +  4));
+		v3 = veorq_u64(v3, vld1q_u64(dp4 +  6));
+
+		/* store */
+		vst1q_u64(dp1 +  0, v0);
+		vst1q_u64(dp1 +  2, v1);
+		vst1q_u64(dp1 +  4, v2);
+		vst1q_u64(dp1 +  6, v3);
+
+		dp1 += 8;
+		dp2 += 8;
+		dp3 += 8;
+		dp4 += 8;
+	} while (--lines > 0);
+}
+
+static void xor_arm64_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)
+{
+	uint64_t *dp1 = (uint64_t *)p1;
+	uint64_t *dp2 = (uint64_t *)p2;
+	uint64_t *dp3 = (uint64_t *)p3;
+	uint64_t *dp4 = (uint64_t *)p4;
+	uint64_t *dp5 = (uint64_t *)p5;
+
+	register uint64x2_t v0, v1, v2, v3;
+	long lines = bytes / (sizeof(uint64x2_t) * 4);
+
+	do {
+		/* p1 ^= p2 */
+		v0 = veorq_u64(vld1q_u64(dp1 +  0), vld1q_u64(dp2 +  0));
+		v1 = veorq_u64(vld1q_u64(dp1 +  2), vld1q_u64(dp2 +  2));
+		v2 = veorq_u64(vld1q_u64(dp1 +  4), vld1q_u64(dp2 +  4));
+		v3 = veorq_u64(vld1q_u64(dp1 +  6), vld1q_u64(dp2 +  6));
+
+		/* p1 ^= p3 */
+		v0 = veorq_u64(v0, vld1q_u64(dp3 +  0));
+		v1 = veorq_u64(v1, vld1q_u64(dp3 +  2));
+		v2 = veorq_u64(v2, vld1q_u64(dp3 +  4));
+		v3 = veorq_u64(v3, vld1q_u64(dp3 +  6));
+
+		/* p1 ^= p4 */
+		v0 = veorq_u64(v0, vld1q_u64(dp4 +  0));
+		v1 = veorq_u64(v1, vld1q_u64(dp4 +  2));
+		v2 = veorq_u64(v2, vld1q_u64(dp4 +  4));
+		v3 = veorq_u64(v3, vld1q_u64(dp4 +  6));
+
+		/* p1 ^= p5 */
+		v0 = veorq_u64(v0, vld1q_u64(dp5 +  0));
+		v1 = veorq_u64(v1, vld1q_u64(dp5 +  2));
+		v2 = veorq_u64(v2, vld1q_u64(dp5 +  4));
+		v3 = veorq_u64(v3, vld1q_u64(dp5 +  6));
+
+		/* store */
+		vst1q_u64(dp1 +  0, v0);
+		vst1q_u64(dp1 +  2, v1);
+		vst1q_u64(dp1 +  4, v2);
+		vst1q_u64(dp1 +  6, v3);
+
+		dp1 += 8;
+		dp2 += 8;
+		dp3 += 8;
+		dp4 += 8;
+		dp5 += 8;
+	} while (--lines > 0);
+}
+
+struct xor_block_template xor_block_inner_neon __ro_after_init = {
+	.name	= "__inner_neon__",
+	.do_2	= xor_arm64_neon_2,
+	.do_3	= xor_arm64_neon_3,
+	.do_4	= xor_arm64_neon_4,
+	.do_5	= xor_arm64_neon_5,
+};
+
+static inline uint64x2_t eor3(uint64x2_t p, uint64x2_t q, uint64x2_t r)
+{
+	uint64x2_t res;
+
+	asm(ARM64_ASM_PREAMBLE ".arch_extension sha3\n"
+	    "eor3 %0.16b, %1.16b, %2.16b, %3.16b"
+	    : "=w"(res) : "w"(p), "w"(q), "w"(r));
+	return res;
+}
+
+static void xor_arm64_eor3_3(unsigned long bytes,
+	unsigned long * __restrict p1,
+	const unsigned long * __restrict p2,
+	const unsigned long * __restrict p3)
+{
+	uint64_t *dp1 = (uint64_t *)p1;
+	uint64_t *dp2 = (uint64_t *)p2;
+	uint64_t *dp3 = (uint64_t *)p3;
+
+	register uint64x2_t v0, v1, v2, v3;
+	long lines = bytes / (sizeof(uint64x2_t) * 4);
+
+	do {
+		/* p1 ^= p2 ^ p3 */
+		v0 = eor3(vld1q_u64(dp1 + 0), vld1q_u64(dp2 + 0),
+			  vld1q_u64(dp3 + 0));
+		v1 = eor3(vld1q_u64(dp1 + 2), vld1q_u64(dp2 + 2),
+			  vld1q_u64(dp3 + 2));
+		v2 = eor3(vld1q_u64(dp1 + 4), vld1q_u64(dp2 + 4),
+			  vld1q_u64(dp3 + 4));
+		v3 = eor3(vld1q_u64(dp1 + 6), vld1q_u64(dp2 + 6),
+			  vld1q_u64(dp3 + 6));
+
+		/* store */
+		vst1q_u64(dp1 + 0, v0);
+		vst1q_u64(dp1 + 2, v1);
+		vst1q_u64(dp1 + 4, v2);
+		vst1q_u64(dp1 + 6, v3);
+
+		dp1 += 8;
+		dp2 += 8;
+		dp3 += 8;
+	} while (--lines > 0);
+}
+
+static void xor_arm64_eor3_4(unsigned long bytes,
+	unsigned long * __restrict p1,
+	const unsigned long * __restrict p2,
+	const unsigned long * __restrict p3,
+	const unsigned long * __restrict p4)
+{
+	uint64_t *dp1 = (uint64_t *)p1;
+	uint64_t *dp2 = (uint64_t *)p2;
+	uint64_t *dp3 = (uint64_t *)p3;
+	uint64_t *dp4 = (uint64_t *)p4;
+
+	register uint64x2_t v0, v1, v2, v3;
+	long lines = bytes / (sizeof(uint64x2_t) * 4);
+
+	do {
+		/* p1 ^= p2 ^ p3 */
+		v0 = eor3(vld1q_u64(dp1 + 0), vld1q_u64(dp2 + 0),
+			  vld1q_u64(dp3 + 0));
+		v1 = eor3(vld1q_u64(dp1 + 2), vld1q_u64(dp2 + 2),
+			  vld1q_u64(dp3 + 2));
+		v2 = eor3(vld1q_u64(dp1 + 4), vld1q_u64(dp2 + 4),
+			  vld1q_u64(dp3 + 4));
+		v3 = eor3(vld1q_u64(dp1 + 6), vld1q_u64(dp2 + 6),
+			  vld1q_u64(dp3 + 6));
+
+		/* p1 ^= p4 */
+		v0 = veorq_u64(v0, vld1q_u64(dp4 + 0));
+		v1 = veorq_u64(v1, vld1q_u64(dp4 + 2));
+		v2 = veorq_u64(v2, vld1q_u64(dp4 + 4));
+		v3 = veorq_u64(v3, vld1q_u64(dp4 + 6));
+
+		/* store */
+		vst1q_u64(dp1 + 0, v0);
+		vst1q_u64(dp1 + 2, v1);
+		vst1q_u64(dp1 + 4, v2);
+		vst1q_u64(dp1 + 6, v3);
+
+		dp1 += 8;
+		dp2 += 8;
+		dp3 += 8;
+		dp4 += 8;
+	} while (--lines > 0);
+}
+
+static void xor_arm64_eor3_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)
+{
+	uint64_t *dp1 = (uint64_t *)p1;
+	uint64_t *dp2 = (uint64_t *)p2;
+	uint64_t *dp3 = (uint64_t *)p3;
+	uint64_t *dp4 = (uint64_t *)p4;
+	uint64_t *dp5 = (uint64_t *)p5;
+
+	register uint64x2_t v0, v1, v2, v3;
+	long lines = bytes / (sizeof(uint64x2_t) * 4);
+
+	do {
+		/* p1 ^= p2 ^ p3 */
+		v0 = eor3(vld1q_u64(dp1 + 0), vld1q_u64(dp2 + 0),
+			  vld1q_u64(dp3 + 0));
+		v1 = eor3(vld1q_u64(dp1 + 2), vld1q_u64(dp2 + 2),
+			  vld1q_u64(dp3 + 2));
+		v2 = eor3(vld1q_u64(dp1 + 4), vld1q_u64(dp2 + 4),
+			  vld1q_u64(dp3 + 4));
+		v3 = eor3(vld1q_u64(dp1 + 6), vld1q_u64(dp2 + 6),
+			  vld1q_u64(dp3 + 6));
+
+		/* p1 ^= p4 ^ p5 */
+		v0 = eor3(v0, vld1q_u64(dp4 + 0), vld1q_u64(dp5 + 0));
+		v1 = eor3(v1, vld1q_u64(dp4 + 2), vld1q_u64(dp5 + 2));
+		v2 = eor3(v2, vld1q_u64(dp4 + 4), vld1q_u64(dp5 + 4));
+		v3 = eor3(v3, vld1q_u64(dp4 + 6), vld1q_u64(dp5 + 6));
+
+		/* store */
+		vst1q_u64(dp1 + 0, v0);
+		vst1q_u64(dp1 + 2, v1);
+		vst1q_u64(dp1 + 4, v2);
+		vst1q_u64(dp1 + 6, v3);
+
+		dp1 += 8;
+		dp2 += 8;
+		dp3 += 8;
+		dp4 += 8;
+		dp5 += 8;
+	} while (--lines > 0);
+}
+
+void __init xor_neon_init(void)
+{
+	if (cpu_have_named_feature(SHA3)) {
+		xor_block_inner_neon.do_3 = xor_arm64_eor3_3;
+		xor_block_inner_neon.do_4 = xor_arm64_eor3_4;
+		xor_block_inner_neon.do_5 = xor_arm64_eor3_5;
+	}
+}