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 3/5] xor/arm: Replace vectorized implementation with arm64's intrinsics
Date: Fri, 27 Mar 2026 12:30:51 +0100 [thread overview]
Message-ID: <20260327113047.4043492-10-ardb+git@google.com> (raw)
In-Reply-To: <20260327113047.4043492-7-ardb+git@google.com>
From: Ard Biesheuvel <ardb@kernel.org>
Drop the XOR implementation generated by the vectorizer: this has always
been a bit of a hack, and now that arm64 has an intrinsics version that
works on ARM too, let's use that instead.
So copy the part of the arm64 code that can be shared (so not the EOR3
version). The arm64 code will be updated in a subsequent patch to share
this implementation.
Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
---
lib/raid/xor/arm/xor-neon.c | 183 ++++++++++++++++++--
lib/raid/xor/arm/xor-neon.h | 7 +
lib/raid/xor/arm/xor_arch.h | 7 +-
lib/raid/xor/xor-8regs.c | 2 -
4 files changed, 174 insertions(+), 25 deletions(-)
diff --git a/lib/raid/xor/arm/xor-neon.c b/lib/raid/xor/arm/xor-neon.c
index 23147e3a7904..a3e2b4af8d36 100644
--- a/lib/raid/xor/arm/xor-neon.c
+++ b/lib/raid/xor/arm/xor-neon.c
@@ -1,26 +1,175 @@
// SPDX-License-Identifier: GPL-2.0-only
/*
- * Copyright (C) 2013 Linaro Ltd <ard.biesheuvel@linaro.org>
+ * Authors: Jackie Liu <liuyun01@kylinos.cn>
+ * Copyright (C) 2018,Tianjin KYLIN Information Technology Co., Ltd.
*/
#include "xor_impl.h"
-#include "xor_arch.h"
+#include "xor-neon.h"
-#ifndef __ARM_NEON__
-#error You should compile this file with '-march=armv7-a -mfloat-abi=softfp -mfpu=neon'
-#endif
+#include <asm/neon-intrinsics.h>
-/*
- * 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
+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);
-#define NO_TEMPLATE
-#include "../xor-8regs.c"
+ dp1 += 8;
+ dp2 += 8;
+ dp3 += 8;
+ dp4 += 8;
+ dp5 += 8;
+ } while (--lines > 0);
+}
-__DO_XOR_BLOCKS(neon_inner, xor_8regs_2, xor_8regs_3, xor_8regs_4, xor_8regs_5);
+__DO_XOR_BLOCKS(neon_inner, __xor_neon_2, __xor_neon_3, __xor_neon_4,
+ __xor_neon_5);
diff --git a/lib/raid/xor/arm/xor-neon.h b/lib/raid/xor/arm/xor-neon.h
new file mode 100644
index 000000000000..406e0356f05b
--- /dev/null
+++ b/lib/raid/xor/arm/xor-neon.h
@@ -0,0 +1,7 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+
+extern struct xor_block_template xor_block_arm4regs;
+extern struct xor_block_template xor_block_neon;
+
+void xor_gen_neon_inner(void *dest, void **srcs, unsigned int src_cnt,
+ unsigned int bytes);
diff --git a/lib/raid/xor/arm/xor_arch.h b/lib/raid/xor/arm/xor_arch.h
index 775ff835df65..f1ddb64fe62a 100644
--- a/lib/raid/xor/arm/xor_arch.h
+++ b/lib/raid/xor/arm/xor_arch.h
@@ -3,12 +3,7 @@
* Copyright (C) 2001 Russell King
*/
#include <asm/neon.h>
-
-extern struct xor_block_template xor_block_arm4regs;
-extern struct xor_block_template xor_block_neon;
-
-void xor_gen_neon_inner(void *dest, void **srcs, unsigned int src_cnt,
- unsigned int bytes);
+#include "xor-neon.h"
static __always_inline void __init arch_xor_init(void)
{
diff --git a/lib/raid/xor/xor-8regs.c b/lib/raid/xor/xor-8regs.c
index 1edaed8acffe..46b3c8bdc27f 100644
--- a/lib/raid/xor/xor-8regs.c
+++ b/lib/raid/xor/xor-8regs.c
@@ -93,11 +93,9 @@ xor_8regs_5(unsigned long bytes, unsigned long * __restrict p1,
} while (--lines > 0);
}
-#ifndef NO_TEMPLATE
DO_XOR_BLOCKS(8regs, xor_8regs_2, xor_8regs_3, xor_8regs_4, xor_8regs_5);
struct xor_block_template xor_block_8regs = {
.name = "8regs",
.xor_gen = xor_gen_8regs,
};
-#endif /* NO_TEMPLATE */
--
2.53.0.1018.g2bb0e51243-goog
next prev parent reply other threads:[~2026-03-27 11:31 UTC|newest]
Thread overview: 8+ messages / expand[flat|nested] mbox.gz Atom feed top
2026-03-27 11:30 [PATCH 0/5] xor/arm: Replace vectorized version with intrinsics Ard Biesheuvel
2026-03-27 11:30 ` [PATCH 1/5] ARM: Add a neon-intrinsics.h header like on arm64 Ard Biesheuvel
2026-03-27 11:30 ` [PATCH 2/5] crypto: aegis128 - Use neon-intrinsics.h on ARM too Ard Biesheuvel
2026-03-27 11:30 ` Ard Biesheuvel [this message]
2026-03-27 11:30 ` [PATCH 4/5] xor/arm64: Use shared NEON intrinsics implementation from 32-bit ARM Ard Biesheuvel
2026-03-27 13:50 ` Christoph Hellwig
2026-03-27 14:45 ` Ard Biesheuvel
2026-03-27 11:30 ` [PATCH 5/5] ARM: Remove hacked-up asm/types.h header Ard Biesheuvel
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=20260327113047.4043492-10-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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox