public inbox for linux-raid@vger.kernel.org
 help / color / mirror / Atom feed
From: Christoph Hellwig <hch@lst.de>
To: Andrew Morton <akpm@linux-foundation.org>
Cc: Richard Henderson <richard.henderson@linaro.org>,
	Matt Turner <mattst88@gmail.com>,
	Magnus Lindholm <linmag7@gmail.com>,
	Russell King <linux@armlinux.org.uk>,
	Catalin Marinas <catalin.marinas@arm.com>,
	Will Deacon <will@kernel.org>,
	Huacai Chen <chenhuacai@kernel.org>,
	WANG Xuerui <kernel@xen0n.name>,
	Madhavan Srinivasan <maddy@linux.ibm.com>,
	Michael Ellerman <mpe@ellerman.id.au>,
	Nicholas Piggin <npiggin@gmail.com>,
	"Christophe Leroy (CS GROUP)" <chleroy@kernel.org>,
	Paul Walmsley <pjw@kernel.org>,
	Palmer Dabbelt <palmer@dabbelt.com>,
	Albert Ou <aou@eecs.berkeley.edu>,
	Alexandre Ghiti <alex@ghiti.fr>,
	Heiko Carstens <hca@linux.ibm.com>,
	Vasily Gorbik <gor@linux.ibm.com>,
	Alexander Gordeev <agordeev@linux.ibm.com>,
	Christian Borntraeger <borntraeger@linux.ibm.com>,
	Sven Schnelle <svens@linux.ibm.com>,
	"David S. Miller" <davem@davemloft.net>,
	Andreas Larsson <andreas@gaisler.com>,
	Richard Weinberger <richard@nod.at>,
	Anton Ivanov <anton.ivanov@cambridgegreys.com>,
	Johannes Berg <johannes@sipsolutions.net>,
	Thomas Gleixner <tglx@kernel.org>, Ingo Molnar <mingo@redhat.com>,
	Borislav Petkov <bp@alien8.de>,
	Dave Hansen <dave.hansen@linux.intel.com>,
	x86@kernel.org, "H. Peter Anvin" <hpa@zytor.com>,
	Herbert Xu <herbert@gondor.apana.org.au>,
	Dan Williams <dan.j.williams@intel.com>, Chris Mason <clm@fb.com>,
	David Sterba <dsterba@suse.com>, Arnd Bergmann <arnd@arndb.de>,
	Song Liu <song@kernel.org>, Yu Kuai <yukuai@fnnas.com>,
	Li Nan <linan122@huawei.com>, "Theodore Ts'o" <tytso@mit.edu>,
	"Jason A. Donenfeld" <Jason@zx2c4.com>,
	linux-alpha@vger.kernel.org, linux-kernel@vger.kernel.org,
	linux-arm-kernel@lists.infradead.org, loongarch@lists.linux.dev,
	linuxppc-dev@lists.ozlabs.org, linux-riscv@lists.infradead.org,
	linux-s390@vger.kernel.org, sparclinux@vger.kernel.org,
	linux-um@lists.infradead.org, linux-crypto@vger.kernel.org,
	linux-btrfs@vger.kernel.org, linux-arch@vger.kernel.org,
	linux-raid@vger.kernel.org
Subject: [PATCH 09/27] xor: move generic implementations out of asm-generic/xor.h
Date: Wed, 11 Mar 2026 08:03:41 +0100	[thread overview]
Message-ID: <20260311070416.972667-10-hch@lst.de> (raw)
In-Reply-To: <20260311070416.972667-1-hch@lst.de>

Move the generic implementations from asm-generic/xor.h to
per-implementaion .c files in lib/raid.  This will build them
unconditionally even when an architecture forces a specific
implementation, but as we'll need at least one generic version
for the static_call optimization later on we'll pay that price.

Note that this would cause the second xor_block_8regs instance created by
arch/arm/lib/xor-neon.c to be generated instead of discarded as dead
code, so add a NO_TEMPLATE symbol to disable it for this case.

Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 arch/arm/lib/xor-neon.c            |   4 +-
 include/asm-generic/xor.h          | 727 +----------------------------
 lib/raid/xor/Makefile              |   4 +
 lib/raid/xor/xor-32regs-prefetch.c | 268 +++++++++++
 lib/raid/xor/xor-32regs.c          | 219 +++++++++
 lib/raid/xor/xor-8regs-prefetch.c  | 146 ++++++
 lib/raid/xor/xor-8regs.c           | 105 +++++
 7 files changed, 748 insertions(+), 725 deletions(-)
 create mode 100644 lib/raid/xor/xor-32regs-prefetch.c
 create mode 100644 lib/raid/xor/xor-32regs.c
 create mode 100644 lib/raid/xor/xor-8regs-prefetch.c
 create mode 100644 lib/raid/xor/xor-8regs.c

diff --git a/arch/arm/lib/xor-neon.c b/arch/arm/lib/xor-neon.c
index 282980b9bf2a..b5be50567991 100644
--- a/arch/arm/lib/xor-neon.c
+++ b/arch/arm/lib/xor-neon.c
@@ -26,8 +26,8 @@ MODULE_LICENSE("GPL");
 #pragma GCC optimize "tree-vectorize"
 #endif
 
-#pragma GCC diagnostic ignored "-Wunused-variable"
-#include <asm-generic/xor.h>
+#define NO_TEMPLATE
+#include "../../../lib/raid/xor/xor-8regs.c"
 
 struct xor_block_template const xor_block_neon_inner = {
 	.name	= "__inner_neon__",
diff --git a/include/asm-generic/xor.h b/include/asm-generic/xor.h
index 79c0096aa9d9..fc151fdc45ab 100644
--- a/include/asm-generic/xor.h
+++ b/include/asm-generic/xor.h
@@ -5,726 +5,7 @@
  * Generic optimized RAID-5 checksumming functions.
  */
 
-#include <linux/prefetch.h>
-
-static void
-xor_8regs_2(unsigned long bytes, unsigned long * __restrict p1,
-	    const unsigned long * __restrict p2)
-{
-	long lines = bytes / (sizeof (long)) / 8;
-
-	do {
-		p1[0] ^= p2[0];
-		p1[1] ^= p2[1];
-		p1[2] ^= p2[2];
-		p1[3] ^= p2[3];
-		p1[4] ^= p2[4];
-		p1[5] ^= p2[5];
-		p1[6] ^= p2[6];
-		p1[7] ^= p2[7];
-		p1 += 8;
-		p2 += 8;
-	} while (--lines > 0);
-}
-
-static void
-xor_8regs_3(unsigned long bytes, unsigned long * __restrict p1,
-	    const unsigned long * __restrict p2,
-	    const unsigned long * __restrict p3)
-{
-	long lines = bytes / (sizeof (long)) / 8;
-
-	do {
-		p1[0] ^= p2[0] ^ p3[0];
-		p1[1] ^= p2[1] ^ p3[1];
-		p1[2] ^= p2[2] ^ p3[2];
-		p1[3] ^= p2[3] ^ p3[3];
-		p1[4] ^= p2[4] ^ p3[4];
-		p1[5] ^= p2[5] ^ p3[5];
-		p1[6] ^= p2[6] ^ p3[6];
-		p1[7] ^= p2[7] ^ p3[7];
-		p1 += 8;
-		p2 += 8;
-		p3 += 8;
-	} while (--lines > 0);
-}
-
-static void
-xor_8regs_4(unsigned long bytes, unsigned long * __restrict p1,
-	    const unsigned long * __restrict p2,
-	    const unsigned long * __restrict p3,
-	    const unsigned long * __restrict p4)
-{
-	long lines = bytes / (sizeof (long)) / 8;
-
-	do {
-		p1[0] ^= p2[0] ^ p3[0] ^ p4[0];
-		p1[1] ^= p2[1] ^ p3[1] ^ p4[1];
-		p1[2] ^= p2[2] ^ p3[2] ^ p4[2];
-		p1[3] ^= p2[3] ^ p3[3] ^ p4[3];
-		p1[4] ^= p2[4] ^ p3[4] ^ p4[4];
-		p1[5] ^= p2[5] ^ p3[5] ^ p4[5];
-		p1[6] ^= p2[6] ^ p3[6] ^ p4[6];
-		p1[7] ^= p2[7] ^ p3[7] ^ p4[7];
-		p1 += 8;
-		p2 += 8;
-		p3 += 8;
-		p4 += 8;
-	} while (--lines > 0);
-}
-
-static void
-xor_8regs_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)
-{
-	long lines = bytes / (sizeof (long)) / 8;
-
-	do {
-		p1[0] ^= p2[0] ^ p3[0] ^ p4[0] ^ p5[0];
-		p1[1] ^= p2[1] ^ p3[1] ^ p4[1] ^ p5[1];
-		p1[2] ^= p2[2] ^ p3[2] ^ p4[2] ^ p5[2];
-		p1[3] ^= p2[3] ^ p3[3] ^ p4[3] ^ p5[3];
-		p1[4] ^= p2[4] ^ p3[4] ^ p4[4] ^ p5[4];
-		p1[5] ^= p2[5] ^ p3[5] ^ p4[5] ^ p5[5];
-		p1[6] ^= p2[6] ^ p3[6] ^ p4[6] ^ p5[6];
-		p1[7] ^= p2[7] ^ p3[7] ^ p4[7] ^ p5[7];
-		p1 += 8;
-		p2 += 8;
-		p3 += 8;
-		p4 += 8;
-		p5 += 8;
-	} while (--lines > 0);
-}
-
-static void
-xor_32regs_2(unsigned long bytes, unsigned long * __restrict p1,
-	     const unsigned long * __restrict p2)
-{
-	long lines = bytes / (sizeof (long)) / 8;
-
-	do {
-		register long d0, d1, d2, d3, d4, d5, d6, d7;
-		d0 = p1[0];	/* Pull the stuff into registers	*/
-		d1 = p1[1];	/*  ... in bursts, if possible.		*/
-		d2 = p1[2];
-		d3 = p1[3];
-		d4 = p1[4];
-		d5 = p1[5];
-		d6 = p1[6];
-		d7 = p1[7];
-		d0 ^= p2[0];
-		d1 ^= p2[1];
-		d2 ^= p2[2];
-		d3 ^= p2[3];
-		d4 ^= p2[4];
-		d5 ^= p2[5];
-		d6 ^= p2[6];
-		d7 ^= p2[7];
-		p1[0] = d0;	/* Store the result (in bursts)		*/
-		p1[1] = d1;
-		p1[2] = d2;
-		p1[3] = d3;
-		p1[4] = d4;
-		p1[5] = d5;
-		p1[6] = d6;
-		p1[7] = d7;
-		p1 += 8;
-		p2 += 8;
-	} while (--lines > 0);
-}
-
-static void
-xor_32regs_3(unsigned long bytes, unsigned long * __restrict p1,
-	     const unsigned long * __restrict p2,
-	     const unsigned long * __restrict p3)
-{
-	long lines = bytes / (sizeof (long)) / 8;
-
-	do {
-		register long d0, d1, d2, d3, d4, d5, d6, d7;
-		d0 = p1[0];	/* Pull the stuff into registers	*/
-		d1 = p1[1];	/*  ... in bursts, if possible.		*/
-		d2 = p1[2];
-		d3 = p1[3];
-		d4 = p1[4];
-		d5 = p1[5];
-		d6 = p1[6];
-		d7 = p1[7];
-		d0 ^= p2[0];
-		d1 ^= p2[1];
-		d2 ^= p2[2];
-		d3 ^= p2[3];
-		d4 ^= p2[4];
-		d5 ^= p2[5];
-		d6 ^= p2[6];
-		d7 ^= p2[7];
-		d0 ^= p3[0];
-		d1 ^= p3[1];
-		d2 ^= p3[2];
-		d3 ^= p3[3];
-		d4 ^= p3[4];
-		d5 ^= p3[5];
-		d6 ^= p3[6];
-		d7 ^= p3[7];
-		p1[0] = d0;	/* Store the result (in bursts)		*/
-		p1[1] = d1;
-		p1[2] = d2;
-		p1[3] = d3;
-		p1[4] = d4;
-		p1[5] = d5;
-		p1[6] = d6;
-		p1[7] = d7;
-		p1 += 8;
-		p2 += 8;
-		p3 += 8;
-	} while (--lines > 0);
-}
-
-static void
-xor_32regs_4(unsigned long bytes, unsigned long * __restrict p1,
-	     const unsigned long * __restrict p2,
-	     const unsigned long * __restrict p3,
-	     const unsigned long * __restrict p4)
-{
-	long lines = bytes / (sizeof (long)) / 8;
-
-	do {
-		register long d0, d1, d2, d3, d4, d5, d6, d7;
-		d0 = p1[0];	/* Pull the stuff into registers	*/
-		d1 = p1[1];	/*  ... in bursts, if possible.		*/
-		d2 = p1[2];
-		d3 = p1[3];
-		d4 = p1[4];
-		d5 = p1[5];
-		d6 = p1[6];
-		d7 = p1[7];
-		d0 ^= p2[0];
-		d1 ^= p2[1];
-		d2 ^= p2[2];
-		d3 ^= p2[3];
-		d4 ^= p2[4];
-		d5 ^= p2[5];
-		d6 ^= p2[6];
-		d7 ^= p2[7];
-		d0 ^= p3[0];
-		d1 ^= p3[1];
-		d2 ^= p3[2];
-		d3 ^= p3[3];
-		d4 ^= p3[4];
-		d5 ^= p3[5];
-		d6 ^= p3[6];
-		d7 ^= p3[7];
-		d0 ^= p4[0];
-		d1 ^= p4[1];
-		d2 ^= p4[2];
-		d3 ^= p4[3];
-		d4 ^= p4[4];
-		d5 ^= p4[5];
-		d6 ^= p4[6];
-		d7 ^= p4[7];
-		p1[0] = d0;	/* Store the result (in bursts)		*/
-		p1[1] = d1;
-		p1[2] = d2;
-		p1[3] = d3;
-		p1[4] = d4;
-		p1[5] = d5;
-		p1[6] = d6;
-		p1[7] = d7;
-		p1 += 8;
-		p2 += 8;
-		p3 += 8;
-		p4 += 8;
-	} while (--lines > 0);
-}
-
-static void
-xor_32regs_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)
-{
-	long lines = bytes / (sizeof (long)) / 8;
-
-	do {
-		register long d0, d1, d2, d3, d4, d5, d6, d7;
-		d0 = p1[0];	/* Pull the stuff into registers	*/
-		d1 = p1[1];	/*  ... in bursts, if possible.		*/
-		d2 = p1[2];
-		d3 = p1[3];
-		d4 = p1[4];
-		d5 = p1[5];
-		d6 = p1[6];
-		d7 = p1[7];
-		d0 ^= p2[0];
-		d1 ^= p2[1];
-		d2 ^= p2[2];
-		d3 ^= p2[3];
-		d4 ^= p2[4];
-		d5 ^= p2[5];
-		d6 ^= p2[6];
-		d7 ^= p2[7];
-		d0 ^= p3[0];
-		d1 ^= p3[1];
-		d2 ^= p3[2];
-		d3 ^= p3[3];
-		d4 ^= p3[4];
-		d5 ^= p3[5];
-		d6 ^= p3[6];
-		d7 ^= p3[7];
-		d0 ^= p4[0];
-		d1 ^= p4[1];
-		d2 ^= p4[2];
-		d3 ^= p4[3];
-		d4 ^= p4[4];
-		d5 ^= p4[5];
-		d6 ^= p4[6];
-		d7 ^= p4[7];
-		d0 ^= p5[0];
-		d1 ^= p5[1];
-		d2 ^= p5[2];
-		d3 ^= p5[3];
-		d4 ^= p5[4];
-		d5 ^= p5[5];
-		d6 ^= p5[6];
-		d7 ^= p5[7];
-		p1[0] = d0;	/* Store the result (in bursts)		*/
-		p1[1] = d1;
-		p1[2] = d2;
-		p1[3] = d3;
-		p1[4] = d4;
-		p1[5] = d5;
-		p1[6] = d6;
-		p1[7] = d7;
-		p1 += 8;
-		p2 += 8;
-		p3 += 8;
-		p4 += 8;
-		p5 += 8;
-	} while (--lines > 0);
-}
-
-static void
-xor_8regs_p_2(unsigned long bytes, unsigned long * __restrict p1,
-	      const unsigned long * __restrict p2)
-{
-	long lines = bytes / (sizeof (long)) / 8 - 1;
-	prefetchw(p1);
-	prefetch(p2);
-
-	do {
-		prefetchw(p1+8);
-		prefetch(p2+8);
- once_more:
-		p1[0] ^= p2[0];
-		p1[1] ^= p2[1];
-		p1[2] ^= p2[2];
-		p1[3] ^= p2[3];
-		p1[4] ^= p2[4];
-		p1[5] ^= p2[5];
-		p1[6] ^= p2[6];
-		p1[7] ^= p2[7];
-		p1 += 8;
-		p2 += 8;
-	} while (--lines > 0);
-	if (lines == 0)
-		goto once_more;
-}
-
-static void
-xor_8regs_p_3(unsigned long bytes, unsigned long * __restrict p1,
-	      const unsigned long * __restrict p2,
-	      const unsigned long * __restrict p3)
-{
-	long lines = bytes / (sizeof (long)) / 8 - 1;
-	prefetchw(p1);
-	prefetch(p2);
-	prefetch(p3);
-
-	do {
-		prefetchw(p1+8);
-		prefetch(p2+8);
-		prefetch(p3+8);
- once_more:
-		p1[0] ^= p2[0] ^ p3[0];
-		p1[1] ^= p2[1] ^ p3[1];
-		p1[2] ^= p2[2] ^ p3[2];
-		p1[3] ^= p2[3] ^ p3[3];
-		p1[4] ^= p2[4] ^ p3[4];
-		p1[5] ^= p2[5] ^ p3[5];
-		p1[6] ^= p2[6] ^ p3[6];
-		p1[7] ^= p2[7] ^ p3[7];
-		p1 += 8;
-		p2 += 8;
-		p3 += 8;
-	} while (--lines > 0);
-	if (lines == 0)
-		goto once_more;
-}
-
-static void
-xor_8regs_p_4(unsigned long bytes, unsigned long * __restrict p1,
-	      const unsigned long * __restrict p2,
-	      const unsigned long * __restrict p3,
-	      const unsigned long * __restrict p4)
-{
-	long lines = bytes / (sizeof (long)) / 8 - 1;
-
-	prefetchw(p1);
-	prefetch(p2);
-	prefetch(p3);
-	prefetch(p4);
-
-	do {
-		prefetchw(p1+8);
-		prefetch(p2+8);
-		prefetch(p3+8);
-		prefetch(p4+8);
- once_more:
-		p1[0] ^= p2[0] ^ p3[0] ^ p4[0];
-		p1[1] ^= p2[1] ^ p3[1] ^ p4[1];
-		p1[2] ^= p2[2] ^ p3[2] ^ p4[2];
-		p1[3] ^= p2[3] ^ p3[3] ^ p4[3];
-		p1[4] ^= p2[4] ^ p3[4] ^ p4[4];
-		p1[5] ^= p2[5] ^ p3[5] ^ p4[5];
-		p1[6] ^= p2[6] ^ p3[6] ^ p4[6];
-		p1[7] ^= p2[7] ^ p3[7] ^ p4[7];
-		p1 += 8;
-		p2 += 8;
-		p3 += 8;
-		p4 += 8;
-	} while (--lines > 0);
-	if (lines == 0)
-		goto once_more;
-}
-
-static void
-xor_8regs_p_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)
-{
-	long lines = bytes / (sizeof (long)) / 8 - 1;
-
-	prefetchw(p1);
-	prefetch(p2);
-	prefetch(p3);
-	prefetch(p4);
-	prefetch(p5);
-
-	do {
-		prefetchw(p1+8);
-		prefetch(p2+8);
-		prefetch(p3+8);
-		prefetch(p4+8);
-		prefetch(p5+8);
- once_more:
-		p1[0] ^= p2[0] ^ p3[0] ^ p4[0] ^ p5[0];
-		p1[1] ^= p2[1] ^ p3[1] ^ p4[1] ^ p5[1];
-		p1[2] ^= p2[2] ^ p3[2] ^ p4[2] ^ p5[2];
-		p1[3] ^= p2[3] ^ p3[3] ^ p4[3] ^ p5[3];
-		p1[4] ^= p2[4] ^ p3[4] ^ p4[4] ^ p5[4];
-		p1[5] ^= p2[5] ^ p3[5] ^ p4[5] ^ p5[5];
-		p1[6] ^= p2[6] ^ p3[6] ^ p4[6] ^ p5[6];
-		p1[7] ^= p2[7] ^ p3[7] ^ p4[7] ^ p5[7];
-		p1 += 8;
-		p2 += 8;
-		p3 += 8;
-		p4 += 8;
-		p5 += 8;
-	} while (--lines > 0);
-	if (lines == 0)
-		goto once_more;
-}
-
-static void
-xor_32regs_p_2(unsigned long bytes, unsigned long * __restrict p1,
-	       const unsigned long * __restrict p2)
-{
-	long lines = bytes / (sizeof (long)) / 8 - 1;
-
-	prefetchw(p1);
-	prefetch(p2);
-
-	do {
-		register long d0, d1, d2, d3, d4, d5, d6, d7;
-
-		prefetchw(p1+8);
-		prefetch(p2+8);
- once_more:
-		d0 = p1[0];	/* Pull the stuff into registers	*/
-		d1 = p1[1];	/*  ... in bursts, if possible.		*/
-		d2 = p1[2];
-		d3 = p1[3];
-		d4 = p1[4];
-		d5 = p1[5];
-		d6 = p1[6];
-		d7 = p1[7];
-		d0 ^= p2[0];
-		d1 ^= p2[1];
-		d2 ^= p2[2];
-		d3 ^= p2[3];
-		d4 ^= p2[4];
-		d5 ^= p2[5];
-		d6 ^= p2[6];
-		d7 ^= p2[7];
-		p1[0] = d0;	/* Store the result (in bursts)		*/
-		p1[1] = d1;
-		p1[2] = d2;
-		p1[3] = d3;
-		p1[4] = d4;
-		p1[5] = d5;
-		p1[6] = d6;
-		p1[7] = d7;
-		p1 += 8;
-		p2 += 8;
-	} while (--lines > 0);
-	if (lines == 0)
-		goto once_more;
-}
-
-static void
-xor_32regs_p_3(unsigned long bytes, unsigned long * __restrict p1,
-	       const unsigned long * __restrict p2,
-	       const unsigned long * __restrict p3)
-{
-	long lines = bytes / (sizeof (long)) / 8 - 1;
-
-	prefetchw(p1);
-	prefetch(p2);
-	prefetch(p3);
-
-	do {
-		register long d0, d1, d2, d3, d4, d5, d6, d7;
-
-		prefetchw(p1+8);
-		prefetch(p2+8);
-		prefetch(p3+8);
- once_more:
-		d0 = p1[0];	/* Pull the stuff into registers	*/
-		d1 = p1[1];	/*  ... in bursts, if possible.		*/
-		d2 = p1[2];
-		d3 = p1[3];
-		d4 = p1[4];
-		d5 = p1[5];
-		d6 = p1[6];
-		d7 = p1[7];
-		d0 ^= p2[0];
-		d1 ^= p2[1];
-		d2 ^= p2[2];
-		d3 ^= p2[3];
-		d4 ^= p2[4];
-		d5 ^= p2[5];
-		d6 ^= p2[6];
-		d7 ^= p2[7];
-		d0 ^= p3[0];
-		d1 ^= p3[1];
-		d2 ^= p3[2];
-		d3 ^= p3[3];
-		d4 ^= p3[4];
-		d5 ^= p3[5];
-		d6 ^= p3[6];
-		d7 ^= p3[7];
-		p1[0] = d0;	/* Store the result (in bursts)		*/
-		p1[1] = d1;
-		p1[2] = d2;
-		p1[3] = d3;
-		p1[4] = d4;
-		p1[5] = d5;
-		p1[6] = d6;
-		p1[7] = d7;
-		p1 += 8;
-		p2 += 8;
-		p3 += 8;
-	} while (--lines > 0);
-	if (lines == 0)
-		goto once_more;
-}
-
-static void
-xor_32regs_p_4(unsigned long bytes, unsigned long * __restrict p1,
-	       const unsigned long * __restrict p2,
-	       const unsigned long * __restrict p3,
-	       const unsigned long * __restrict p4)
-{
-	long lines = bytes / (sizeof (long)) / 8 - 1;
-
-	prefetchw(p1);
-	prefetch(p2);
-	prefetch(p3);
-	prefetch(p4);
-
-	do {
-		register long d0, d1, d2, d3, d4, d5, d6, d7;
-
-		prefetchw(p1+8);
-		prefetch(p2+8);
-		prefetch(p3+8);
-		prefetch(p4+8);
- once_more:
-		d0 = p1[0];	/* Pull the stuff into registers	*/
-		d1 = p1[1];	/*  ... in bursts, if possible.		*/
-		d2 = p1[2];
-		d3 = p1[3];
-		d4 = p1[4];
-		d5 = p1[5];
-		d6 = p1[6];
-		d7 = p1[7];
-		d0 ^= p2[0];
-		d1 ^= p2[1];
-		d2 ^= p2[2];
-		d3 ^= p2[3];
-		d4 ^= p2[4];
-		d5 ^= p2[5];
-		d6 ^= p2[6];
-		d7 ^= p2[7];
-		d0 ^= p3[0];
-		d1 ^= p3[1];
-		d2 ^= p3[2];
-		d3 ^= p3[3];
-		d4 ^= p3[4];
-		d5 ^= p3[5];
-		d6 ^= p3[6];
-		d7 ^= p3[7];
-		d0 ^= p4[0];
-		d1 ^= p4[1];
-		d2 ^= p4[2];
-		d3 ^= p4[3];
-		d4 ^= p4[4];
-		d5 ^= p4[5];
-		d6 ^= p4[6];
-		d7 ^= p4[7];
-		p1[0] = d0;	/* Store the result (in bursts)		*/
-		p1[1] = d1;
-		p1[2] = d2;
-		p1[3] = d3;
-		p1[4] = d4;
-		p1[5] = d5;
-		p1[6] = d6;
-		p1[7] = d7;
-		p1 += 8;
-		p2 += 8;
-		p3 += 8;
-		p4 += 8;
-	} while (--lines > 0);
-	if (lines == 0)
-		goto once_more;
-}
-
-static void
-xor_32regs_p_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)
-{
-	long lines = bytes / (sizeof (long)) / 8 - 1;
-
-	prefetchw(p1);
-	prefetch(p2);
-	prefetch(p3);
-	prefetch(p4);
-	prefetch(p5);
-
-	do {
-		register long d0, d1, d2, d3, d4, d5, d6, d7;
-
-		prefetchw(p1+8);
-		prefetch(p2+8);
-		prefetch(p3+8);
-		prefetch(p4+8);
-		prefetch(p5+8);
- once_more:
-		d0 = p1[0];	/* Pull the stuff into registers	*/
-		d1 = p1[1];	/*  ... in bursts, if possible.		*/
-		d2 = p1[2];
-		d3 = p1[3];
-		d4 = p1[4];
-		d5 = p1[5];
-		d6 = p1[6];
-		d7 = p1[7];
-		d0 ^= p2[0];
-		d1 ^= p2[1];
-		d2 ^= p2[2];
-		d3 ^= p2[3];
-		d4 ^= p2[4];
-		d5 ^= p2[5];
-		d6 ^= p2[6];
-		d7 ^= p2[7];
-		d0 ^= p3[0];
-		d1 ^= p3[1];
-		d2 ^= p3[2];
-		d3 ^= p3[3];
-		d4 ^= p3[4];
-		d5 ^= p3[5];
-		d6 ^= p3[6];
-		d7 ^= p3[7];
-		d0 ^= p4[0];
-		d1 ^= p4[1];
-		d2 ^= p4[2];
-		d3 ^= p4[3];
-		d4 ^= p4[4];
-		d5 ^= p4[5];
-		d6 ^= p4[6];
-		d7 ^= p4[7];
-		d0 ^= p5[0];
-		d1 ^= p5[1];
-		d2 ^= p5[2];
-		d3 ^= p5[3];
-		d4 ^= p5[4];
-		d5 ^= p5[5];
-		d6 ^= p5[6];
-		d7 ^= p5[7];
-		p1[0] = d0;	/* Store the result (in bursts)		*/
-		p1[1] = d1;
-		p1[2] = d2;
-		p1[3] = d3;
-		p1[4] = d4;
-		p1[5] = d5;
-		p1[6] = d6;
-		p1[7] = d7;
-		p1 += 8;
-		p2 += 8;
-		p3 += 8;
-		p4 += 8;
-		p5 += 8;
-	} while (--lines > 0);
-	if (lines == 0)
-		goto once_more;
-}
-
-static struct xor_block_template xor_block_8regs = {
-	.name = "8regs",
-	.do_2 = xor_8regs_2,
-	.do_3 = xor_8regs_3,
-	.do_4 = xor_8regs_4,
-	.do_5 = xor_8regs_5,
-};
-
-static struct xor_block_template xor_block_32regs = {
-	.name = "32regs",
-	.do_2 = xor_32regs_2,
-	.do_3 = xor_32regs_3,
-	.do_4 = xor_32regs_4,
-	.do_5 = xor_32regs_5,
-};
-
-static struct xor_block_template xor_block_8regs_p __maybe_unused = {
-	.name = "8regs_prefetch",
-	.do_2 = xor_8regs_p_2,
-	.do_3 = xor_8regs_p_3,
-	.do_4 = xor_8regs_p_4,
-	.do_5 = xor_8regs_p_5,
-};
-
-static struct xor_block_template xor_block_32regs_p __maybe_unused = {
-	.name = "32regs_prefetch",
-	.do_2 = xor_32regs_p_2,
-	.do_3 = xor_32regs_p_3,
-	.do_4 = xor_32regs_p_4,
-	.do_5 = xor_32regs_p_5,
-};
+extern struct xor_block_template xor_block_8regs;
+extern struct xor_block_template xor_block_32regs;
+extern struct xor_block_template xor_block_8regs_p;
+extern struct xor_block_template xor_block_32regs_p;
diff --git a/lib/raid/xor/Makefile b/lib/raid/xor/Makefile
index 7bca0ce8e90a..89a944c9f990 100644
--- a/lib/raid/xor/Makefile
+++ b/lib/raid/xor/Makefile
@@ -3,3 +3,7 @@
 obj-$(CONFIG_XOR_BLOCKS)	+= xor.o
 
 xor-y				+= xor-core.o
+xor-y				+= xor-8regs.o
+xor-y				+= xor-32regs.o
+xor-y				+= xor-8regs-prefetch.o
+xor-y				+= xor-32regs-prefetch.o
diff --git a/lib/raid/xor/xor-32regs-prefetch.c b/lib/raid/xor/xor-32regs-prefetch.c
new file mode 100644
index 000000000000..8666c287f777
--- /dev/null
+++ b/lib/raid/xor/xor-32regs-prefetch.c
@@ -0,0 +1,268 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+#include <linux/prefetch.h>
+#include <linux/raid/xor_impl.h>
+#include <asm-generic/xor.h>
+
+static void
+xor_32regs_p_2(unsigned long bytes, unsigned long * __restrict p1,
+	       const unsigned long * __restrict p2)
+{
+	long lines = bytes / (sizeof (long)) / 8 - 1;
+
+	prefetchw(p1);
+	prefetch(p2);
+
+	do {
+		register long d0, d1, d2, d3, d4, d5, d6, d7;
+
+		prefetchw(p1+8);
+		prefetch(p2+8);
+ once_more:
+		d0 = p1[0];	/* Pull the stuff into registers	*/
+		d1 = p1[1];	/*  ... in bursts, if possible.		*/
+		d2 = p1[2];
+		d3 = p1[3];
+		d4 = p1[4];
+		d5 = p1[5];
+		d6 = p1[6];
+		d7 = p1[7];
+		d0 ^= p2[0];
+		d1 ^= p2[1];
+		d2 ^= p2[2];
+		d3 ^= p2[3];
+		d4 ^= p2[4];
+		d5 ^= p2[5];
+		d6 ^= p2[6];
+		d7 ^= p2[7];
+		p1[0] = d0;	/* Store the result (in bursts)		*/
+		p1[1] = d1;
+		p1[2] = d2;
+		p1[3] = d3;
+		p1[4] = d4;
+		p1[5] = d5;
+		p1[6] = d6;
+		p1[7] = d7;
+		p1 += 8;
+		p2 += 8;
+	} while (--lines > 0);
+	if (lines == 0)
+		goto once_more;
+}
+
+static void
+xor_32regs_p_3(unsigned long bytes, unsigned long * __restrict p1,
+	       const unsigned long * __restrict p2,
+	       const unsigned long * __restrict p3)
+{
+	long lines = bytes / (sizeof (long)) / 8 - 1;
+
+	prefetchw(p1);
+	prefetch(p2);
+	prefetch(p3);
+
+	do {
+		register long d0, d1, d2, d3, d4, d5, d6, d7;
+
+		prefetchw(p1+8);
+		prefetch(p2+8);
+		prefetch(p3+8);
+ once_more:
+		d0 = p1[0];	/* Pull the stuff into registers	*/
+		d1 = p1[1];	/*  ... in bursts, if possible.		*/
+		d2 = p1[2];
+		d3 = p1[3];
+		d4 = p1[4];
+		d5 = p1[5];
+		d6 = p1[6];
+		d7 = p1[7];
+		d0 ^= p2[0];
+		d1 ^= p2[1];
+		d2 ^= p2[2];
+		d3 ^= p2[3];
+		d4 ^= p2[4];
+		d5 ^= p2[5];
+		d6 ^= p2[6];
+		d7 ^= p2[7];
+		d0 ^= p3[0];
+		d1 ^= p3[1];
+		d2 ^= p3[2];
+		d3 ^= p3[3];
+		d4 ^= p3[4];
+		d5 ^= p3[5];
+		d6 ^= p3[6];
+		d7 ^= p3[7];
+		p1[0] = d0;	/* Store the result (in bursts)		*/
+		p1[1] = d1;
+		p1[2] = d2;
+		p1[3] = d3;
+		p1[4] = d4;
+		p1[5] = d5;
+		p1[6] = d6;
+		p1[7] = d7;
+		p1 += 8;
+		p2 += 8;
+		p3 += 8;
+	} while (--lines > 0);
+	if (lines == 0)
+		goto once_more;
+}
+
+static void
+xor_32regs_p_4(unsigned long bytes, unsigned long * __restrict p1,
+	       const unsigned long * __restrict p2,
+	       const unsigned long * __restrict p3,
+	       const unsigned long * __restrict p4)
+{
+	long lines = bytes / (sizeof (long)) / 8 - 1;
+
+	prefetchw(p1);
+	prefetch(p2);
+	prefetch(p3);
+	prefetch(p4);
+
+	do {
+		register long d0, d1, d2, d3, d4, d5, d6, d7;
+
+		prefetchw(p1+8);
+		prefetch(p2+8);
+		prefetch(p3+8);
+		prefetch(p4+8);
+ once_more:
+		d0 = p1[0];	/* Pull the stuff into registers	*/
+		d1 = p1[1];	/*  ... in bursts, if possible.		*/
+		d2 = p1[2];
+		d3 = p1[3];
+		d4 = p1[4];
+		d5 = p1[5];
+		d6 = p1[6];
+		d7 = p1[7];
+		d0 ^= p2[0];
+		d1 ^= p2[1];
+		d2 ^= p2[2];
+		d3 ^= p2[3];
+		d4 ^= p2[4];
+		d5 ^= p2[5];
+		d6 ^= p2[6];
+		d7 ^= p2[7];
+		d0 ^= p3[0];
+		d1 ^= p3[1];
+		d2 ^= p3[2];
+		d3 ^= p3[3];
+		d4 ^= p3[4];
+		d5 ^= p3[5];
+		d6 ^= p3[6];
+		d7 ^= p3[7];
+		d0 ^= p4[0];
+		d1 ^= p4[1];
+		d2 ^= p4[2];
+		d3 ^= p4[3];
+		d4 ^= p4[4];
+		d5 ^= p4[5];
+		d6 ^= p4[6];
+		d7 ^= p4[7];
+		p1[0] = d0;	/* Store the result (in bursts)		*/
+		p1[1] = d1;
+		p1[2] = d2;
+		p1[3] = d3;
+		p1[4] = d4;
+		p1[5] = d5;
+		p1[6] = d6;
+		p1[7] = d7;
+		p1 += 8;
+		p2 += 8;
+		p3 += 8;
+		p4 += 8;
+	} while (--lines > 0);
+	if (lines == 0)
+		goto once_more;
+}
+
+static void
+xor_32regs_p_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)
+{
+	long lines = bytes / (sizeof (long)) / 8 - 1;
+
+	prefetchw(p1);
+	prefetch(p2);
+	prefetch(p3);
+	prefetch(p4);
+	prefetch(p5);
+
+	do {
+		register long d0, d1, d2, d3, d4, d5, d6, d7;
+
+		prefetchw(p1+8);
+		prefetch(p2+8);
+		prefetch(p3+8);
+		prefetch(p4+8);
+		prefetch(p5+8);
+ once_more:
+		d0 = p1[0];	/* Pull the stuff into registers	*/
+		d1 = p1[1];	/*  ... in bursts, if possible.		*/
+		d2 = p1[2];
+		d3 = p1[3];
+		d4 = p1[4];
+		d5 = p1[5];
+		d6 = p1[6];
+		d7 = p1[7];
+		d0 ^= p2[0];
+		d1 ^= p2[1];
+		d2 ^= p2[2];
+		d3 ^= p2[3];
+		d4 ^= p2[4];
+		d5 ^= p2[5];
+		d6 ^= p2[6];
+		d7 ^= p2[7];
+		d0 ^= p3[0];
+		d1 ^= p3[1];
+		d2 ^= p3[2];
+		d3 ^= p3[3];
+		d4 ^= p3[4];
+		d5 ^= p3[5];
+		d6 ^= p3[6];
+		d7 ^= p3[7];
+		d0 ^= p4[0];
+		d1 ^= p4[1];
+		d2 ^= p4[2];
+		d3 ^= p4[3];
+		d4 ^= p4[4];
+		d5 ^= p4[5];
+		d6 ^= p4[6];
+		d7 ^= p4[7];
+		d0 ^= p5[0];
+		d1 ^= p5[1];
+		d2 ^= p5[2];
+		d3 ^= p5[3];
+		d4 ^= p5[4];
+		d5 ^= p5[5];
+		d6 ^= p5[6];
+		d7 ^= p5[7];
+		p1[0] = d0;	/* Store the result (in bursts)		*/
+		p1[1] = d1;
+		p1[2] = d2;
+		p1[3] = d3;
+		p1[4] = d4;
+		p1[5] = d5;
+		p1[6] = d6;
+		p1[7] = d7;
+		p1 += 8;
+		p2 += 8;
+		p3 += 8;
+		p4 += 8;
+		p5 += 8;
+	} while (--lines > 0);
+	if (lines == 0)
+		goto once_more;
+}
+
+struct xor_block_template xor_block_32regs_p = {
+	.name = "32regs_prefetch",
+	.do_2 = xor_32regs_p_2,
+	.do_3 = xor_32regs_p_3,
+	.do_4 = xor_32regs_p_4,
+	.do_5 = xor_32regs_p_5,
+};
diff --git a/lib/raid/xor/xor-32regs.c b/lib/raid/xor/xor-32regs.c
new file mode 100644
index 000000000000..58d4fac43eb4
--- /dev/null
+++ b/lib/raid/xor/xor-32regs.c
@@ -0,0 +1,219 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+#include <linux/raid/xor_impl.h>
+#include <asm-generic/xor.h>
+
+static void
+xor_32regs_2(unsigned long bytes, unsigned long * __restrict p1,
+	     const unsigned long * __restrict p2)
+{
+	long lines = bytes / (sizeof (long)) / 8;
+
+	do {
+		register long d0, d1, d2, d3, d4, d5, d6, d7;
+		d0 = p1[0];	/* Pull the stuff into registers	*/
+		d1 = p1[1];	/*  ... in bursts, if possible.		*/
+		d2 = p1[2];
+		d3 = p1[3];
+		d4 = p1[4];
+		d5 = p1[5];
+		d6 = p1[6];
+		d7 = p1[7];
+		d0 ^= p2[0];
+		d1 ^= p2[1];
+		d2 ^= p2[2];
+		d3 ^= p2[3];
+		d4 ^= p2[4];
+		d5 ^= p2[5];
+		d6 ^= p2[6];
+		d7 ^= p2[7];
+		p1[0] = d0;	/* Store the result (in bursts)		*/
+		p1[1] = d1;
+		p1[2] = d2;
+		p1[3] = d3;
+		p1[4] = d4;
+		p1[5] = d5;
+		p1[6] = d6;
+		p1[7] = d7;
+		p1 += 8;
+		p2 += 8;
+	} while (--lines > 0);
+}
+
+static void
+xor_32regs_3(unsigned long bytes, unsigned long * __restrict p1,
+	     const unsigned long * __restrict p2,
+	     const unsigned long * __restrict p3)
+{
+	long lines = bytes / (sizeof (long)) / 8;
+
+	do {
+		register long d0, d1, d2, d3, d4, d5, d6, d7;
+		d0 = p1[0];	/* Pull the stuff into registers	*/
+		d1 = p1[1];	/*  ... in bursts, if possible.		*/
+		d2 = p1[2];
+		d3 = p1[3];
+		d4 = p1[4];
+		d5 = p1[5];
+		d6 = p1[6];
+		d7 = p1[7];
+		d0 ^= p2[0];
+		d1 ^= p2[1];
+		d2 ^= p2[2];
+		d3 ^= p2[3];
+		d4 ^= p2[4];
+		d5 ^= p2[5];
+		d6 ^= p2[6];
+		d7 ^= p2[7];
+		d0 ^= p3[0];
+		d1 ^= p3[1];
+		d2 ^= p3[2];
+		d3 ^= p3[3];
+		d4 ^= p3[4];
+		d5 ^= p3[5];
+		d6 ^= p3[6];
+		d7 ^= p3[7];
+		p1[0] = d0;	/* Store the result (in bursts)		*/
+		p1[1] = d1;
+		p1[2] = d2;
+		p1[3] = d3;
+		p1[4] = d4;
+		p1[5] = d5;
+		p1[6] = d6;
+		p1[7] = d7;
+		p1 += 8;
+		p2 += 8;
+		p3 += 8;
+	} while (--lines > 0);
+}
+
+static void
+xor_32regs_4(unsigned long bytes, unsigned long * __restrict p1,
+	     const unsigned long * __restrict p2,
+	     const unsigned long * __restrict p3,
+	     const unsigned long * __restrict p4)
+{
+	long lines = bytes / (sizeof (long)) / 8;
+
+	do {
+		register long d0, d1, d2, d3, d4, d5, d6, d7;
+		d0 = p1[0];	/* Pull the stuff into registers	*/
+		d1 = p1[1];	/*  ... in bursts, if possible.		*/
+		d2 = p1[2];
+		d3 = p1[3];
+		d4 = p1[4];
+		d5 = p1[5];
+		d6 = p1[6];
+		d7 = p1[7];
+		d0 ^= p2[0];
+		d1 ^= p2[1];
+		d2 ^= p2[2];
+		d3 ^= p2[3];
+		d4 ^= p2[4];
+		d5 ^= p2[5];
+		d6 ^= p2[6];
+		d7 ^= p2[7];
+		d0 ^= p3[0];
+		d1 ^= p3[1];
+		d2 ^= p3[2];
+		d3 ^= p3[3];
+		d4 ^= p3[4];
+		d5 ^= p3[5];
+		d6 ^= p3[6];
+		d7 ^= p3[7];
+		d0 ^= p4[0];
+		d1 ^= p4[1];
+		d2 ^= p4[2];
+		d3 ^= p4[3];
+		d4 ^= p4[4];
+		d5 ^= p4[5];
+		d6 ^= p4[6];
+		d7 ^= p4[7];
+		p1[0] = d0;	/* Store the result (in bursts)		*/
+		p1[1] = d1;
+		p1[2] = d2;
+		p1[3] = d3;
+		p1[4] = d4;
+		p1[5] = d5;
+		p1[6] = d6;
+		p1[7] = d7;
+		p1 += 8;
+		p2 += 8;
+		p3 += 8;
+		p4 += 8;
+	} while (--lines > 0);
+}
+
+static void
+xor_32regs_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)
+{
+	long lines = bytes / (sizeof (long)) / 8;
+
+	do {
+		register long d0, d1, d2, d3, d4, d5, d6, d7;
+		d0 = p1[0];	/* Pull the stuff into registers	*/
+		d1 = p1[1];	/*  ... in bursts, if possible.		*/
+		d2 = p1[2];
+		d3 = p1[3];
+		d4 = p1[4];
+		d5 = p1[5];
+		d6 = p1[6];
+		d7 = p1[7];
+		d0 ^= p2[0];
+		d1 ^= p2[1];
+		d2 ^= p2[2];
+		d3 ^= p2[3];
+		d4 ^= p2[4];
+		d5 ^= p2[5];
+		d6 ^= p2[6];
+		d7 ^= p2[7];
+		d0 ^= p3[0];
+		d1 ^= p3[1];
+		d2 ^= p3[2];
+		d3 ^= p3[3];
+		d4 ^= p3[4];
+		d5 ^= p3[5];
+		d6 ^= p3[6];
+		d7 ^= p3[7];
+		d0 ^= p4[0];
+		d1 ^= p4[1];
+		d2 ^= p4[2];
+		d3 ^= p4[3];
+		d4 ^= p4[4];
+		d5 ^= p4[5];
+		d6 ^= p4[6];
+		d7 ^= p4[7];
+		d0 ^= p5[0];
+		d1 ^= p5[1];
+		d2 ^= p5[2];
+		d3 ^= p5[3];
+		d4 ^= p5[4];
+		d5 ^= p5[5];
+		d6 ^= p5[6];
+		d7 ^= p5[7];
+		p1[0] = d0;	/* Store the result (in bursts)		*/
+		p1[1] = d1;
+		p1[2] = d2;
+		p1[3] = d3;
+		p1[4] = d4;
+		p1[5] = d5;
+		p1[6] = d6;
+		p1[7] = d7;
+		p1 += 8;
+		p2 += 8;
+		p3 += 8;
+		p4 += 8;
+		p5 += 8;
+	} while (--lines > 0);
+}
+
+struct xor_block_template xor_block_32regs = {
+	.name = "32regs",
+	.do_2 = xor_32regs_2,
+	.do_3 = xor_32regs_3,
+	.do_4 = xor_32regs_4,
+	.do_5 = xor_32regs_5,
+};
diff --git a/lib/raid/xor/xor-8regs-prefetch.c b/lib/raid/xor/xor-8regs-prefetch.c
new file mode 100644
index 000000000000..67061e35a0a6
--- /dev/null
+++ b/lib/raid/xor/xor-8regs-prefetch.c
@@ -0,0 +1,146 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+#include <linux/prefetch.h>
+#include <linux/raid/xor_impl.h>
+#include <asm-generic/xor.h>
+
+static void
+xor_8regs_p_2(unsigned long bytes, unsigned long * __restrict p1,
+	      const unsigned long * __restrict p2)
+{
+	long lines = bytes / (sizeof (long)) / 8 - 1;
+	prefetchw(p1);
+	prefetch(p2);
+
+	do {
+		prefetchw(p1+8);
+		prefetch(p2+8);
+ once_more:
+		p1[0] ^= p2[0];
+		p1[1] ^= p2[1];
+		p1[2] ^= p2[2];
+		p1[3] ^= p2[3];
+		p1[4] ^= p2[4];
+		p1[5] ^= p2[5];
+		p1[6] ^= p2[6];
+		p1[7] ^= p2[7];
+		p1 += 8;
+		p2 += 8;
+	} while (--lines > 0);
+	if (lines == 0)
+		goto once_more;
+}
+
+static void
+xor_8regs_p_3(unsigned long bytes, unsigned long * __restrict p1,
+	      const unsigned long * __restrict p2,
+	      const unsigned long * __restrict p3)
+{
+	long lines = bytes / (sizeof (long)) / 8 - 1;
+	prefetchw(p1);
+	prefetch(p2);
+	prefetch(p3);
+
+	do {
+		prefetchw(p1+8);
+		prefetch(p2+8);
+		prefetch(p3+8);
+ once_more:
+		p1[0] ^= p2[0] ^ p3[0];
+		p1[1] ^= p2[1] ^ p3[1];
+		p1[2] ^= p2[2] ^ p3[2];
+		p1[3] ^= p2[3] ^ p3[3];
+		p1[4] ^= p2[4] ^ p3[4];
+		p1[5] ^= p2[5] ^ p3[5];
+		p1[6] ^= p2[6] ^ p3[6];
+		p1[7] ^= p2[7] ^ p3[7];
+		p1 += 8;
+		p2 += 8;
+		p3 += 8;
+	} while (--lines > 0);
+	if (lines == 0)
+		goto once_more;
+}
+
+static void
+xor_8regs_p_4(unsigned long bytes, unsigned long * __restrict p1,
+	      const unsigned long * __restrict p2,
+	      const unsigned long * __restrict p3,
+	      const unsigned long * __restrict p4)
+{
+	long lines = bytes / (sizeof (long)) / 8 - 1;
+
+	prefetchw(p1);
+	prefetch(p2);
+	prefetch(p3);
+	prefetch(p4);
+
+	do {
+		prefetchw(p1+8);
+		prefetch(p2+8);
+		prefetch(p3+8);
+		prefetch(p4+8);
+ once_more:
+		p1[0] ^= p2[0] ^ p3[0] ^ p4[0];
+		p1[1] ^= p2[1] ^ p3[1] ^ p4[1];
+		p1[2] ^= p2[2] ^ p3[2] ^ p4[2];
+		p1[3] ^= p2[3] ^ p3[3] ^ p4[3];
+		p1[4] ^= p2[4] ^ p3[4] ^ p4[4];
+		p1[5] ^= p2[5] ^ p3[5] ^ p4[5];
+		p1[6] ^= p2[6] ^ p3[6] ^ p4[6];
+		p1[7] ^= p2[7] ^ p3[7] ^ p4[7];
+		p1 += 8;
+		p2 += 8;
+		p3 += 8;
+		p4 += 8;
+	} while (--lines > 0);
+	if (lines == 0)
+		goto once_more;
+}
+
+static void
+xor_8regs_p_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)
+{
+	long lines = bytes / (sizeof (long)) / 8 - 1;
+
+	prefetchw(p1);
+	prefetch(p2);
+	prefetch(p3);
+	prefetch(p4);
+	prefetch(p5);
+
+	do {
+		prefetchw(p1+8);
+		prefetch(p2+8);
+		prefetch(p3+8);
+		prefetch(p4+8);
+		prefetch(p5+8);
+ once_more:
+		p1[0] ^= p2[0] ^ p3[0] ^ p4[0] ^ p5[0];
+		p1[1] ^= p2[1] ^ p3[1] ^ p4[1] ^ p5[1];
+		p1[2] ^= p2[2] ^ p3[2] ^ p4[2] ^ p5[2];
+		p1[3] ^= p2[3] ^ p3[3] ^ p4[3] ^ p5[3];
+		p1[4] ^= p2[4] ^ p3[4] ^ p4[4] ^ p5[4];
+		p1[5] ^= p2[5] ^ p3[5] ^ p4[5] ^ p5[5];
+		p1[6] ^= p2[6] ^ p3[6] ^ p4[6] ^ p5[6];
+		p1[7] ^= p2[7] ^ p3[7] ^ p4[7] ^ p5[7];
+		p1 += 8;
+		p2 += 8;
+		p3 += 8;
+		p4 += 8;
+		p5 += 8;
+	} while (--lines > 0);
+	if (lines == 0)
+		goto once_more;
+}
+
+struct xor_block_template xor_block_8regs_p = {
+	.name = "8regs_prefetch",
+	.do_2 = xor_8regs_p_2,
+	.do_3 = xor_8regs_p_3,
+	.do_4 = xor_8regs_p_4,
+	.do_5 = xor_8regs_p_5,
+};
diff --git a/lib/raid/xor/xor-8regs.c b/lib/raid/xor/xor-8regs.c
new file mode 100644
index 000000000000..769f796ab2cf
--- /dev/null
+++ b/lib/raid/xor/xor-8regs.c
@@ -0,0 +1,105 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+#include <linux/raid/xor_impl.h>
+#include <asm-generic/xor.h>
+
+static void
+xor_8regs_2(unsigned long bytes, unsigned long * __restrict p1,
+	    const unsigned long * __restrict p2)
+{
+	long lines = bytes / (sizeof (long)) / 8;
+
+	do {
+		p1[0] ^= p2[0];
+		p1[1] ^= p2[1];
+		p1[2] ^= p2[2];
+		p1[3] ^= p2[3];
+		p1[4] ^= p2[4];
+		p1[5] ^= p2[5];
+		p1[6] ^= p2[6];
+		p1[7] ^= p2[7];
+		p1 += 8;
+		p2 += 8;
+	} while (--lines > 0);
+}
+
+static void
+xor_8regs_3(unsigned long bytes, unsigned long * __restrict p1,
+	    const unsigned long * __restrict p2,
+	    const unsigned long * __restrict p3)
+{
+	long lines = bytes / (sizeof (long)) / 8;
+
+	do {
+		p1[0] ^= p2[0] ^ p3[0];
+		p1[1] ^= p2[1] ^ p3[1];
+		p1[2] ^= p2[2] ^ p3[2];
+		p1[3] ^= p2[3] ^ p3[3];
+		p1[4] ^= p2[4] ^ p3[4];
+		p1[5] ^= p2[5] ^ p3[5];
+		p1[6] ^= p2[6] ^ p3[6];
+		p1[7] ^= p2[7] ^ p3[7];
+		p1 += 8;
+		p2 += 8;
+		p3 += 8;
+	} while (--lines > 0);
+}
+
+static void
+xor_8regs_4(unsigned long bytes, unsigned long * __restrict p1,
+	    const unsigned long * __restrict p2,
+	    const unsigned long * __restrict p3,
+	    const unsigned long * __restrict p4)
+{
+	long lines = bytes / (sizeof (long)) / 8;
+
+	do {
+		p1[0] ^= p2[0] ^ p3[0] ^ p4[0];
+		p1[1] ^= p2[1] ^ p3[1] ^ p4[1];
+		p1[2] ^= p2[2] ^ p3[2] ^ p4[2];
+		p1[3] ^= p2[3] ^ p3[3] ^ p4[3];
+		p1[4] ^= p2[4] ^ p3[4] ^ p4[4];
+		p1[5] ^= p2[5] ^ p3[5] ^ p4[5];
+		p1[6] ^= p2[6] ^ p3[6] ^ p4[6];
+		p1[7] ^= p2[7] ^ p3[7] ^ p4[7];
+		p1 += 8;
+		p2 += 8;
+		p3 += 8;
+		p4 += 8;
+	} while (--lines > 0);
+}
+
+static void
+xor_8regs_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)
+{
+	long lines = bytes / (sizeof (long)) / 8;
+
+	do {
+		p1[0] ^= p2[0] ^ p3[0] ^ p4[0] ^ p5[0];
+		p1[1] ^= p2[1] ^ p3[1] ^ p4[1] ^ p5[1];
+		p1[2] ^= p2[2] ^ p3[2] ^ p4[2] ^ p5[2];
+		p1[3] ^= p2[3] ^ p3[3] ^ p4[3] ^ p5[3];
+		p1[4] ^= p2[4] ^ p3[4] ^ p4[4] ^ p5[4];
+		p1[5] ^= p2[5] ^ p3[5] ^ p4[5] ^ p5[5];
+		p1[6] ^= p2[6] ^ p3[6] ^ p4[6] ^ p5[6];
+		p1[7] ^= p2[7] ^ p3[7] ^ p4[7] ^ p5[7];
+		p1 += 8;
+		p2 += 8;
+		p3 += 8;
+		p4 += 8;
+		p5 += 8;
+	} while (--lines > 0);
+}
+
+#ifndef NO_TEMPLATE
+struct xor_block_template xor_block_8regs = {
+	.name = "8regs",
+	.do_2 = xor_8regs_2,
+	.do_3 = xor_8regs_3,
+	.do_4 = xor_8regs_4,
+	.do_5 = xor_8regs_5,
+};
+#endif /* NO_TEMPLATE */
-- 
2.47.3


  parent reply	other threads:[~2026-03-11  7:06 UTC|newest]

Thread overview: 36+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2026-03-11  7:03 cleanup the RAID5 XOR library v2 Christoph Hellwig
2026-03-11  7:03 ` [PATCH 01/27] xor: assert that xor_blocks is not from preemptible user context Christoph Hellwig
2026-03-11  7:03 ` [PATCH 02/27] arm/xor: remove in_interrupt() handling Christoph Hellwig
2026-03-11  7:03 ` [PATCH 03/27] um/xor: cleanup xor.h Christoph Hellwig
2026-03-11  8:45   ` Richard Weinberger
2026-03-11  7:03 ` [PATCH 04/27] xor: move to lib/raid/ Christoph Hellwig
2026-03-11  7:03 ` [PATCH 05/27] xor: small cleanups Christoph Hellwig
2026-03-11  7:03 ` [PATCH 06/27] xor: cleanup registration and probing Christoph Hellwig
2026-03-11  7:03 ` [PATCH 07/27] xor: split xor.h Christoph Hellwig
2026-03-11  7:03 ` [PATCH 08/27] xor: remove macro abuse for XOR implementation registrations Christoph Hellwig
2026-03-11  7:03 ` Christoph Hellwig [this message]
2026-03-11  7:03 ` [PATCH 10/27] alpha: move the XOR code to lib/raid/ Christoph Hellwig
2026-03-16 22:12   ` Magnus Lindholm
2026-03-11  7:03 ` [PATCH 11/27] arm: " Christoph Hellwig
2026-03-11  7:03 ` [PATCH 12/27] arm64: " Christoph Hellwig
2026-03-11  7:03 ` [PATCH 13/27] loongarch: " Christoph Hellwig
2026-03-11  7:03 ` [PATCH 14/27] powerpc: " Christoph Hellwig
2026-03-11  7:03 ` [PATCH 15/27] riscv: " Christoph Hellwig
2026-03-11  7:03 ` [PATCH 16/27] sparc: " Christoph Hellwig
2026-03-11  7:03 ` [PATCH 17/27] s390: " Christoph Hellwig
2026-03-11  7:03 ` [PATCH 18/27] x86: " Christoph Hellwig
2026-03-11  7:03 ` [PATCH 19/27] xor: avoid indirect calls for arm64-optimized ops Christoph Hellwig
2026-03-11  7:03 ` [PATCH 20/27] xor: make xor.ko self-contained in lib/raid/ Christoph Hellwig
2026-03-11  7:03 ` [PATCH 21/27] xor: add a better public API Christoph Hellwig
2026-03-11  7:03 ` [PATCH 22/27] async_xor: use xor_gen Christoph Hellwig
2026-03-11  7:03 ` [PATCH 23/27] btrfs: " Christoph Hellwig
2026-03-12  6:14   ` David Sterba
2026-03-11  7:03 ` [PATCH 24/27] xor: pass the entire operation to the low-level ops Christoph Hellwig
2026-03-11  7:03 ` [PATCH 25/27] xor: use static_call for xor_gen Christoph Hellwig
2026-03-11  7:03 ` [PATCH 26/27] random: factor out a __limit_random_u32_below helper Christoph Hellwig
2026-03-11 22:29   ` Eric Biggers
2026-03-12  8:38     ` David Laight
2026-03-12 13:46   ` Jason A. Donenfeld
2026-03-11  7:03 ` [PATCH 27/27] xor: add a kunit test case Christoph Hellwig
2026-03-12  0:54   ` Eric Biggers
2026-03-11 18:57 ` cleanup the RAID5 XOR library v2 Andrew Morton

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=20260311070416.972667-10-hch@lst.de \
    --to=hch@lst.de \
    --cc=Jason@zx2c4.com \
    --cc=agordeev@linux.ibm.com \
    --cc=akpm@linux-foundation.org \
    --cc=alex@ghiti.fr \
    --cc=andreas@gaisler.com \
    --cc=anton.ivanov@cambridgegreys.com \
    --cc=aou@eecs.berkeley.edu \
    --cc=arnd@arndb.de \
    --cc=borntraeger@linux.ibm.com \
    --cc=bp@alien8.de \
    --cc=catalin.marinas@arm.com \
    --cc=chenhuacai@kernel.org \
    --cc=chleroy@kernel.org \
    --cc=clm@fb.com \
    --cc=dan.j.williams@intel.com \
    --cc=dave.hansen@linux.intel.com \
    --cc=davem@davemloft.net \
    --cc=dsterba@suse.com \
    --cc=gor@linux.ibm.com \
    --cc=hca@linux.ibm.com \
    --cc=herbert@gondor.apana.org.au \
    --cc=hpa@zytor.com \
    --cc=johannes@sipsolutions.net \
    --cc=kernel@xen0n.name \
    --cc=linan122@huawei.com \
    --cc=linmag7@gmail.com \
    --cc=linux-alpha@vger.kernel.org \
    --cc=linux-arch@vger.kernel.org \
    --cc=linux-arm-kernel@lists.infradead.org \
    --cc=linux-btrfs@vger.kernel.org \
    --cc=linux-crypto@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-raid@vger.kernel.org \
    --cc=linux-riscv@lists.infradead.org \
    --cc=linux-s390@vger.kernel.org \
    --cc=linux-um@lists.infradead.org \
    --cc=linux@armlinux.org.uk \
    --cc=linuxppc-dev@lists.ozlabs.org \
    --cc=loongarch@lists.linux.dev \
    --cc=maddy@linux.ibm.com \
    --cc=mattst88@gmail.com \
    --cc=mingo@redhat.com \
    --cc=mpe@ellerman.id.au \
    --cc=npiggin@gmail.com \
    --cc=palmer@dabbelt.com \
    --cc=pjw@kernel.org \
    --cc=richard.henderson@linaro.org \
    --cc=richard@nod.at \
    --cc=song@kernel.org \
    --cc=sparclinux@vger.kernel.org \
    --cc=svens@linux.ibm.com \
    --cc=tglx@kernel.org \
    --cc=tytso@mit.edu \
    --cc=will@kernel.org \
    --cc=x86@kernel.org \
    --cc=yukuai@fnnas.com \
    /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