[PATCH 4/5] xor/arm64: Use shared NEON intrinsics implementation from 32-bit ARM

Ard Biesheuvel ardb+git at google.com
Fri Mar 27 04:30:52 PDT 2026


From: Ard Biesheuvel <ardb at kernel.org>

Tweak the arm64 code so that the pure NEON intrinsics implementation of
XOR is shared between arm64 and ARM.

Signed-off-by: Ard Biesheuvel <ardb at kernel.org>
---
 lib/raid/xor/arm64/xor-neon.c | 170 +-------------------
 lib/raid/xor/arm64/xor-neon.h |   3 +
 lib/raid/xor/arm64/xor_arch.h |   4 +-
 3 files changed, 5 insertions(+), 172 deletions(-)

diff --git a/lib/raid/xor/arm64/xor-neon.c b/lib/raid/xor/arm64/xor-neon.c
index 97ef3cb92496..43fa5236fd41 100644
--- a/lib/raid/xor/arm64/xor-neon.c
+++ b/lib/raid/xor/arm64/xor-neon.c
@@ -1,179 +1,11 @@
 // SPDX-License-Identifier: GPL-2.0-only
-/*
- * Authors: Jackie Liu <liuyun01 at kylinos.cn>
- * Copyright (C) 2018,Tianjin KYLIN Information Technology Co., Ltd.
- */
 
 #include <linux/cache.h>
 #include <asm/neon-intrinsics.h>
 #include "xor_impl.h"
-#include "xor_arch.h"
 #include "xor-neon.h"
 
-static void __xor_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_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_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_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);
-}
-
-__DO_XOR_BLOCKS(neon_inner, __xor_neon_2, __xor_neon_3, __xor_neon_4,
-		__xor_neon_5);
+#include "../arm/xor-neon.c"
 
 static inline uint64x2_t eor3(uint64x2_t p, uint64x2_t q, uint64x2_t r)
 {
diff --git a/lib/raid/xor/arm64/xor-neon.h b/lib/raid/xor/arm64/xor-neon.h
index 514699ba8f5f..d49e7a7f0e14 100644
--- a/lib/raid/xor/arm64/xor-neon.h
+++ b/lib/raid/xor/arm64/xor-neon.h
@@ -1,5 +1,8 @@
 /* SPDX-License-Identifier: GPL-2.0-only */
 
+extern struct xor_block_template xor_block_neon;
+extern struct xor_block_template xor_block_eor3;
+
 void xor_gen_neon_inner(void *dest, void **srcs, unsigned int src_cnt,
 		unsigned int bytes);
 void xor_gen_eor3_inner(void *dest, void **srcs, unsigned int src_cnt,
diff --git a/lib/raid/xor/arm64/xor_arch.h b/lib/raid/xor/arm64/xor_arch.h
index 5dbb40319501..7c9d16324c33 100644
--- a/lib/raid/xor/arm64/xor_arch.h
+++ b/lib/raid/xor/arm64/xor_arch.h
@@ -4,9 +4,7 @@
  * Copyright (C) 2018,Tianjin KYLIN Information Technology Co., Ltd.
  */
 #include <asm/simd.h>
-
-extern struct xor_block_template xor_block_neon;
-extern struct xor_block_template xor_block_eor3;
+#include "xor-neon.h"
 
 static __always_inline void __init arch_xor_init(void)
 {
-- 
2.53.0.1018.g2bb0e51243-goog




More information about the linux-arm-kernel mailing list