bybrooklyn/linux
1
0
Fork 0
mirror of https://github.com/torvalds/linux.git synced 2026-04-18 06:44:00 -04:00
Code Issues Packages Projects Releases Wiki Activity

xor: pass the entire operation to the low-level ops

Browse Source 
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>
This commit is contained in:
Christoph Hellwig
2026-03-27 07:16:58 +01:00
committed by Andrew Morton
parent 0f629e7283
commit 80dcf0a783
26 changed files with 224 additions and 505 deletions
Download Patch File Download Diff File Expand all files Collapse all files

20
lib/raid/xor/arm64/xor-neon.c
View File

@@ -10,7 +10,7 @@
#include "xor_arch.h"
#include "xor-neon.h"
void __xor_neon_2(unsigned long bytes, unsigned long * __restrict p1,
static void __xor_neon_2(unsigned long bytes, unsigned long * __restrict p1,
const unsigned long * __restrict p2)
{
uint64_t *dp1 = (uint64_t *)p1;
@@ -37,7 +37,7 @@ void __xor_neon_2(unsigned long bytes, unsigned long * __restrict p1,
} while (--lines > 0);
}
void __xor_neon_3(unsigned long bytes, unsigned long * __restrict p1,
static void __xor_neon_3(unsigned long bytes, unsigned long * __restrict p1,
const unsigned long * __restrict p2,
const unsigned long * __restrict p3)
{
@@ -73,7 +73,7 @@ void __xor_neon_3(unsigned long bytes, unsigned long * __restrict p1,
} while (--lines > 0);
}
void __xor_neon_4(unsigned long bytes, unsigned long * __restrict p1,
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)
@@ -118,7 +118,7 @@ void __xor_neon_4(unsigned long bytes, unsigned long * __restrict p1,
} while (--lines > 0);
}
void __xor_neon_5(unsigned long bytes, unsigned long * __restrict p1,
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,
@@ -172,6 +172,9 @@ void __xor_neon_5(unsigned long bytes, unsigned long * __restrict p1,
} while (--lines > 0);
}
__DO_XOR_BLOCKS(neon_inner, __xor_neon_2, __xor_neon_3, __xor_neon_4,
__xor_neon_5);
static inline uint64x2_t eor3(uint64x2_t p, uint64x2_t q, uint64x2_t r)
{
uint64x2_t res;
@@ -182,7 +185,7 @@ static inline uint64x2_t eor3(uint64x2_t p, uint64x2_t q, uint64x2_t r)
return res;
}
void __xor_eor3_3(unsigned long bytes, unsigned long * __restrict p1,
static void __xor_eor3_3(unsigned long bytes, unsigned long * __restrict p1,
const unsigned long * __restrict p2,
const unsigned long * __restrict p3)
{
@@ -216,7 +219,7 @@ void __xor_eor3_3(unsigned long bytes, unsigned long * __restrict p1,
} while (--lines > 0);
}
void __xor_eor3_4(unsigned long bytes, unsigned long * __restrict p1,
static void __xor_eor3_4(unsigned long bytes, unsigned long * __restrict p1,
const unsigned long * __restrict p2,
const unsigned long * __restrict p3,
const unsigned long * __restrict p4)
@@ -259,7 +262,7 @@ void __xor_eor3_4(unsigned long bytes, unsigned long * __restrict p1,
} while (--lines > 0);
}
void __xor_eor3_5(unsigned long bytes, unsigned long * __restrict p1,
static void __xor_eor3_5(unsigned long bytes, unsigned long * __restrict p1,
const unsigned long * __restrict p2,
const unsigned long * __restrict p3,
const unsigned long * __restrict p4,
@@ -304,3 +307,6 @@ void __xor_eor3_5(unsigned long bytes, unsigned long * __restrict p1,
dp5 += 8;
} while (--lines > 0);
}
__DO_XOR_BLOCKS(eor3_inner, __xor_neon_2, __xor_eor3_3, __xor_eor3_4,
__xor_eor3_5);