Gh0st
/
linux
mirror of https://github.com/torvalds/linux.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

lib/crc: Switch ARM and arm64 to 'ksimd' scoped guard API 

Before modifying the prototypes of kernel_neon_begin() and
kernel_neon_end() to accommodate kernel mode FP/SIMD state buffers
allocated on the stack, move arm64 to the new 'ksimd' scoped guard API,
which encapsulates the calls to those functions.

For symmetry, do the same for 32-bit ARM too.

Reviewed-by: Eric Biggers <ebiggers@kernel.org>
Reviewed-by: Jonathan Cameron <jonathan.cameron@huawei.com>
Acked-by: Catalin Marinas <catalin.marinas@arm.com>
Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
This commit is contained in:
Ard Biesheuvel 2025-10-01 13:27:08 +02:00
parent f53d18a4e6
commit 4fb623074e
4 changed files with 22 additions and 43 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

19
lib/crc/arm/crc-t10dif.h
View File

@ -5,7 +5,6 @@
* Copyright (C) 2016 Linaro Ltd <ard.biesheuvel@linaro.org>
*/
#include <asm/neon.h>
#include <asm/simd.h>
static __ro_after_init DEFINE_STATIC_KEY_FALSE(have_neon);
@ -19,22 +18,16 @@ asmlinkage void crc_t10dif_pmull8(u16 init_crc, const u8 *buf, size_t len,
static inline u16 crc_t10dif_arch(u16 crc, const u8 *data, size_t length)
{
if (length >= CRC_T10DIF_PMULL_CHUNK_SIZE) {
if (length >= CRC_T10DIF_PMULL_CHUNK_SIZE && likely(may_use_simd())) {
if (static_branch_likely(&have_pmull)) {
if (likely(may_use_simd())) {
kernel_neon_begin();
crc = crc_t10dif_pmull64(crc, data, length);
kernel_neon_end();
return crc;
}
scoped_ksimd()
return crc_t10dif_pmull64(crc, data, length);
} else if (length > CRC_T10DIF_PMULL_CHUNK_SIZE &&
static_branch_likely(&have_neon) &&
likely(may_use_simd())) {
static_branch_likely(&have_neon)) {
u8 buf[16] __aligned(16);
kernel_neon_begin();
crc_t10dif_pmull8(crc, data, length, buf);
kernel_neon_end();
scoped_ksimd()
crc_t10dif_pmull8(crc, data, length, buf);
return crc_t10dif_generic(0, buf, sizeof(buf));
}

11
lib/crc/arm/crc32.h
View File

@ -8,7 +8,6 @@
#include <linux/cpufeature.h>
#include <asm/hwcap.h>
#include <asm/neon.h>
#include <asm/simd.h>
static __ro_after_init DEFINE_STATIC_KEY_FALSE(have_crc32);
@ -42,9 +41,8 @@ static inline u32 crc32_le_arch(u32 crc, const u8 *p, size_t len)
len -= n;
}
n = round_down(len, 16);
kernel_neon_begin();
crc = crc32_pmull_le(p, n, crc);
kernel_neon_end();
scoped_ksimd()
crc = crc32_pmull_le(p, n, crc);
p += n;
len -= n;
}
@ -71,9 +69,8 @@ static inline u32 crc32c_arch(u32 crc, const u8 *p, size_t len)
len -= n;
}
n = round_down(len, 16);
kernel_neon_begin();
crc = crc32c_pmull_le(p, n, crc);
kernel_neon_end();
scoped_ksimd()
crc = crc32c_pmull_le(p, n, crc);
p += n;
len -= n;
}

19
lib/crc/arm64/crc-t10dif.h
View File

@ -7,7 +7,6 @@
#include <linux/cpufeature.h>
#include <asm/neon.h>
#include <asm/simd.h>
static __ro_after_init DEFINE_STATIC_KEY_FALSE(have_asimd);
@ -21,22 +20,16 @@ asmlinkage u16 crc_t10dif_pmull_p64(u16 init_crc, const u8 *buf, size_t len);
static inline u16 crc_t10dif_arch(u16 crc, const u8 *data, size_t length)
{
if (length >= CRC_T10DIF_PMULL_CHUNK_SIZE) {
if (length >= CRC_T10DIF_PMULL_CHUNK_SIZE && likely(may_use_simd())) {
if (static_branch_likely(&have_pmull)) {
if (likely(may_use_simd())) {
kernel_neon_begin();
crc = crc_t10dif_pmull_p64(crc, data, length);
kernel_neon_end();
return crc;
}
scoped_ksimd()
return crc_t10dif_pmull_p64(crc, data, length);
} else if (length > CRC_T10DIF_PMULL_CHUNK_SIZE &&
static_branch_likely(&have_asimd) &&
likely(may_use_simd())) {
static_branch_likely(&have_asimd)) {
u8 buf[16];
kernel_neon_begin();
crc_t10dif_pmull_p8(crc, data, length, buf);
kernel_neon_end();
scoped_ksimd()
crc_t10dif_pmull_p8(crc, data, length, buf);
return crc_t10dif_generic(0, buf, sizeof(buf));
}

16
lib/crc/arm64/crc32.h
View File

@ -2,7 +2,6 @@
#include <asm/alternative.h>
#include <asm/cpufeature.h>
#include <asm/neon.h>
#include <asm/simd.h>
// The minimum input length to consider the 4-way interleaved code path
@ -23,9 +22,8 @@ static inline u32 crc32_le_arch(u32 crc, const u8 *p, size_t len)
if (len >= min_len && cpu_have_named_feature(PMULL) &&
likely(may_use_simd())) {
kernel_neon_begin();
crc = crc32_le_arm64_4way(crc, p, len);
kernel_neon_end();
scoped_ksimd()
crc = crc32_le_arm64_4way(crc, p, len);
p += round_down(len, 64);
len %= 64;
@ -44,9 +42,8 @@ static inline u32 crc32c_arch(u32 crc, const u8 *p, size_t len)
if (len >= min_len && cpu_have_named_feature(PMULL) &&
likely(may_use_simd())) {
kernel_neon_begin();
crc = crc32c_le_arm64_4way(crc, p, len);
kernel_neon_end();
scoped_ksimd()
crc = crc32c_le_arm64_4way(crc, p, len);
p += round_down(len, 64);
len %= 64;
@ -65,9 +62,8 @@ static inline u32 crc32_be_arch(u32 crc, const u8 *p, size_t len)
if (len >= min_len && cpu_have_named_feature(PMULL) &&
likely(may_use_simd())) {
kernel_neon_begin();
crc = crc32_be_arm64_4way(crc, p, len);
kernel_neon_end();
scoped_ksimd()
crc = crc32_be_arm64_4way(crc, p, len);
p += round_down(len, 64);
len %= 64;