Files
linux/lib/raid/xor/xor_impl.h
Christoph Hellwig 80dcf0a783 xor: pass the entire operation to the low-level ops
Currently the high-level xor code chunks up all operations into small
units for only up to 1 + 4 vectors, and passes it to four different
methods.  This means the FPU/vector context is entered and left a lot for
wide stripes, and a lot of indirect expensive indirect calls are
performed.  Switch to passing the entire gen_xor request to the low-level
ops, and provide a macro to dispatch it to the existing helper.

This reduce the number of indirect calls and FPU/vector context switches
by a factor approaching nr_stripes / 4, and also reduces source and binary
code size.

Link: https://lkml.kernel.org/r/20260327061704.3707577-27-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>
2026-04-02 23:36:21 -07:00

57 lines
1.6 KiB
C

/* SPDX-License-Identifier: GPL-2.0 */
#ifndef _XOR_IMPL_H
#define _XOR_IMPL_H
#include <linux/init.h>
#include <linux/minmax.h>
struct xor_block_template {
struct xor_block_template *next;
const char *name;
int speed;
void (*xor_gen)(void *dest, void **srcs, unsigned int src_cnt,
unsigned int bytes);
};
#define __DO_XOR_BLOCKS(_name, _handle1, _handle2, _handle3, _handle4) \
void \
xor_gen_##_name(void *dest, void **srcs, unsigned int src_cnt, \
unsigned int bytes) \
{ \
unsigned int src_off = 0; \
\
while (src_cnt > 0) { \
unsigned int this_cnt = min(src_cnt, 4); \
\
if (this_cnt == 1) \
_handle1(bytes, dest, srcs[src_off]); \
else if (this_cnt == 2) \
_handle2(bytes, dest, srcs[src_off], \
srcs[src_off + 1]); \
else if (this_cnt == 3) \
_handle3(bytes, dest, srcs[src_off], \
srcs[src_off + 1], srcs[src_off + 2]); \
else \
_handle4(bytes, dest, srcs[src_off], \
srcs[src_off + 1], srcs[src_off + 2], \
srcs[src_off + 3]); \
\
src_cnt -= this_cnt; \
src_off += this_cnt; \
} \
}
#define DO_XOR_BLOCKS(_name, _handle1, _handle2, _handle3, _handle4) \
static __DO_XOR_BLOCKS(_name, _handle1, _handle2, _handle3, _handle4)
/* generic implementations */
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;
void __init xor_register(struct xor_block_template *tmpl);
void __init xor_force(struct xor_block_template *tmpl);
#endif /* _XOR_IMPL_H */