From: Ard Biesheuvel <ardb+git@google.com>
To: linux-raid@vger.kernel.org
Cc: linux-arm-kernel@lists.infradead.org,
linux-crypto@vger.kernel.org, Ard Biesheuvel <ardb@kernel.org>,
Christoph Hellwig <hch@lst.de>,
Russell King <linux@armlinux.org.uk>,
Arnd Bergmann <arnd@arndb.de>,
Eric Biggers <ebiggers@kernel.org>
Subject: [PATCH v2 4/5] xor/arm64: Use shared NEON intrinsics implementation from 32-bit ARM
Date: Tue, 31 Mar 2026 09:49:44 +0200 [thread overview]
Message-ID: <20260331074940.55502-11-ardb+git@google.com> (raw)
In-Reply-To: <20260331074940.55502-7-ardb+git@google.com>
From: Ard Biesheuvel <ardb@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@kernel.org>
---
lib/raid/xor/Makefile | 3 +-
lib/raid/xor/arm/xor-neon.c | 4 +
lib/raid/xor/arm64/xor-neon.c | 172 +-------------------
3 files changed, 9 insertions(+), 170 deletions(-)
diff --git a/lib/raid/xor/Makefile b/lib/raid/xor/Makefile
index 4d633dfd5b90..b27bf5156784 100644
--- a/lib/raid/xor/Makefile
+++ b/lib/raid/xor/Makefile
@@ -19,7 +19,8 @@ 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
+xor-$(CONFIG_ARM64) += arm/xor-neon.o arm64/xor-neon.o \
+ arm64/xor-neon-glue.o
xor-$(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
diff --git a/lib/raid/xor/arm/xor-neon.c b/lib/raid/xor/arm/xor-neon.c
index a3e2b4af8d36..c7c3cf634e23 100644
--- a/lib/raid/xor/arm/xor-neon.c
+++ b/lib/raid/xor/arm/xor-neon.c
@@ -173,3 +173,7 @@ static void __xor_neon_5(unsigned long bytes, unsigned long * __restrict p1,
__DO_XOR_BLOCKS(neon_inner, __xor_neon_2, __xor_neon_3, __xor_neon_4,
__xor_neon_5);
+
+#ifdef CONFIG_ARM64
+extern typeof(__xor_neon_2) __xor_eor3_2 __alias(__xor_neon_2);
+#endif
diff --git a/lib/raid/xor/arm64/xor-neon.c b/lib/raid/xor/arm64/xor-neon.c
index 97ef3cb92496..e44016c363f1 100644
--- a/lib/raid/xor/arm64/xor-neon.c
+++ b/lib/raid/xor/arm64/xor-neon.c
@@ -1,8 +1,4 @@
// SPDX-License-Identifier: GPL-2.0-only
-/*
- * Authors: Jackie Liu <liuyun01@kylinos.cn>
- * Copyright (C) 2018,Tianjin KYLIN Information Technology Co., Ltd.
- */
#include <linux/cache.h>
#include <asm/neon-intrinsics.h>
@@ -10,170 +6,8 @@
#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);
+extern void __xor_eor3_2(unsigned long bytes, unsigned long * __restrict p1,
+ const unsigned long * __restrict p2);
static inline uint64x2_t eor3(uint64x2_t p, uint64x2_t q, uint64x2_t r)
{
@@ -308,5 +142,5 @@ static void __xor_eor3_5(unsigned long bytes, unsigned long * __restrict p1,
} while (--lines > 0);
}
-__DO_XOR_BLOCKS(eor3_inner, __xor_neon_2, __xor_eor3_3, __xor_eor3_4,
+__DO_XOR_BLOCKS(eor3_inner, __xor_eor3_2, __xor_eor3_3, __xor_eor3_4,
__xor_eor3_5);
--
2.53.0.1018.g2bb0e51243-goog
next prev parent reply other threads:[~2026-03-31 7:50 UTC|newest]
Thread overview: 9+ messages / expand[flat|nested] mbox.gz Atom feed top
2026-03-31 7:49 [PATCH v2 0/5] xor/arm: Replace vectorized version with intrinsics Ard Biesheuvel
2026-03-31 7:49 ` [PATCH v2 1/5] ARM: Add a neon-intrinsics.h header like on arm64 Ard Biesheuvel
2026-03-31 7:49 ` [PATCH v2 2/5] crypto: aegis128 - Use neon-intrinsics.h on ARM too Ard Biesheuvel
2026-03-31 7:49 ` [PATCH v2 3/5] xor/arm: Replace vectorized implementation with arm64's intrinsics Ard Biesheuvel
2026-03-31 7:49 ` Ard Biesheuvel [this message]
2026-03-31 7:49 ` [PATCH v2 5/5] ARM: Remove hacked-up asm/types.h header Ard Biesheuvel
2026-03-31 15:16 ` [PATCH v2 0/5] xor/arm: Replace vectorized version with intrinsics Christoph Hellwig
2026-03-31 15:26 ` Ard Biesheuvel
2026-03-31 15:28 ` Christoph Hellwig
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20260331074940.55502-11-ardb+git@google.com \
--to=ardb+git@google.com \
--cc=ardb@kernel.org \
--cc=arnd@arndb.de \
--cc=ebiggers@kernel.org \
--cc=hch@lst.de \
--cc=linux-arm-kernel@lists.infradead.org \
--cc=linux-crypto@vger.kernel.org \
--cc=linux-raid@vger.kernel.org \
--cc=linux@armlinux.org.uk \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.