mirror of
https://github.com/torvalds/linux.git
synced 2026-04-18 06:44:00 -04:00
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>
137 lines
3.6 KiB
C
137 lines
3.6 KiB
C
// SPDX-License-Identifier: GPL-2.0-only
|
|
/*
|
|
* Copyright (C) 2001 Russell King
|
|
*/
|
|
#include "xor_impl.h"
|
|
#include "xor_arch.h"
|
|
|
|
#define __XOR(a1, a2) a1 ^= a2
|
|
|
|
#define GET_BLOCK_2(dst) \
|
|
__asm__("ldmia %0, {%1, %2}" \
|
|
: "=r" (dst), "=r" (a1), "=r" (a2) \
|
|
: "0" (dst))
|
|
|
|
#define GET_BLOCK_4(dst) \
|
|
__asm__("ldmia %0, {%1, %2, %3, %4}" \
|
|
: "=r" (dst), "=r" (a1), "=r" (a2), "=r" (a3), "=r" (a4) \
|
|
: "0" (dst))
|
|
|
|
#define XOR_BLOCK_2(src) \
|
|
__asm__("ldmia %0!, {%1, %2}" \
|
|
: "=r" (src), "=r" (b1), "=r" (b2) \
|
|
: "0" (src)); \
|
|
__XOR(a1, b1); __XOR(a2, b2);
|
|
|
|
#define XOR_BLOCK_4(src) \
|
|
__asm__("ldmia %0!, {%1, %2, %3, %4}" \
|
|
: "=r" (src), "=r" (b1), "=r" (b2), "=r" (b3), "=r" (b4) \
|
|
: "0" (src)); \
|
|
__XOR(a1, b1); __XOR(a2, b2); __XOR(a3, b3); __XOR(a4, b4)
|
|
|
|
#define PUT_BLOCK_2(dst) \
|
|
__asm__ __volatile__("stmia %0!, {%2, %3}" \
|
|
: "=r" (dst) \
|
|
: "0" (dst), "r" (a1), "r" (a2))
|
|
|
|
#define PUT_BLOCK_4(dst) \
|
|
__asm__ __volatile__("stmia %0!, {%2, %3, %4, %5}" \
|
|
: "=r" (dst) \
|
|
: "0" (dst), "r" (a1), "r" (a2), "r" (a3), "r" (a4))
|
|
|
|
static void
|
|
xor_arm4regs_2(unsigned long bytes, unsigned long * __restrict p1,
|
|
const unsigned long * __restrict p2)
|
|
{
|
|
unsigned int lines = bytes / sizeof(unsigned long) / 4;
|
|
register unsigned int a1 __asm__("r4");
|
|
register unsigned int a2 __asm__("r5");
|
|
register unsigned int a3 __asm__("r6");
|
|
register unsigned int a4 __asm__("r10");
|
|
register unsigned int b1 __asm__("r8");
|
|
register unsigned int b2 __asm__("r9");
|
|
register unsigned int b3 __asm__("ip");
|
|
register unsigned int b4 __asm__("lr");
|
|
|
|
do {
|
|
GET_BLOCK_4(p1);
|
|
XOR_BLOCK_4(p2);
|
|
PUT_BLOCK_4(p1);
|
|
} while (--lines);
|
|
}
|
|
|
|
static void
|
|
xor_arm4regs_3(unsigned long bytes, unsigned long * __restrict p1,
|
|
const unsigned long * __restrict p2,
|
|
const unsigned long * __restrict p3)
|
|
{
|
|
unsigned int lines = bytes / sizeof(unsigned long) / 4;
|
|
register unsigned int a1 __asm__("r4");
|
|
register unsigned int a2 __asm__("r5");
|
|
register unsigned int a3 __asm__("r6");
|
|
register unsigned int a4 __asm__("r10");
|
|
register unsigned int b1 __asm__("r8");
|
|
register unsigned int b2 __asm__("r9");
|
|
register unsigned int b3 __asm__("ip");
|
|
register unsigned int b4 __asm__("lr");
|
|
|
|
do {
|
|
GET_BLOCK_4(p1);
|
|
XOR_BLOCK_4(p2);
|
|
XOR_BLOCK_4(p3);
|
|
PUT_BLOCK_4(p1);
|
|
} while (--lines);
|
|
}
|
|
|
|
static void
|
|
xor_arm4regs_4(unsigned long bytes, unsigned long * __restrict p1,
|
|
const unsigned long * __restrict p2,
|
|
const unsigned long * __restrict p3,
|
|
const unsigned long * __restrict p4)
|
|
{
|
|
unsigned int lines = bytes / sizeof(unsigned long) / 2;
|
|
register unsigned int a1 __asm__("r8");
|
|
register unsigned int a2 __asm__("r9");
|
|
register unsigned int b1 __asm__("ip");
|
|
register unsigned int b2 __asm__("lr");
|
|
|
|
do {
|
|
GET_BLOCK_2(p1);
|
|
XOR_BLOCK_2(p2);
|
|
XOR_BLOCK_2(p3);
|
|
XOR_BLOCK_2(p4);
|
|
PUT_BLOCK_2(p1);
|
|
} while (--lines);
|
|
}
|
|
|
|
static void
|
|
xor_arm4regs_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)
|
|
{
|
|
unsigned int lines = bytes / sizeof(unsigned long) / 2;
|
|
register unsigned int a1 __asm__("r8");
|
|
register unsigned int a2 __asm__("r9");
|
|
register unsigned int b1 __asm__("ip");
|
|
register unsigned int b2 __asm__("lr");
|
|
|
|
do {
|
|
GET_BLOCK_2(p1);
|
|
XOR_BLOCK_2(p2);
|
|
XOR_BLOCK_2(p3);
|
|
XOR_BLOCK_2(p4);
|
|
XOR_BLOCK_2(p5);
|
|
PUT_BLOCK_2(p1);
|
|
} while (--lines);
|
|
}
|
|
|
|
DO_XOR_BLOCKS(arm4regs, xor_arm4regs_2, xor_arm4regs_3, xor_arm4regs_4,
|
|
xor_arm4regs_5);
|
|
|
|
struct xor_block_template xor_block_arm4regs = {
|
|
.name = "arm4regs",
|
|
.xor_gen = xor_gen_arm4regs,
|
|
};
|