diff options
author | Ard Biesheuvel <ardb@kernel.org> | 2022-02-05 16:23:45 +0100 |
---|---|---|
committer | Herbert Xu <herbert@gondor.apana.org.au> | 2022-02-11 20:39:39 +1100 |
commit | 297565aa22cfa80ab0f88c3569693aea0b6afb6d (patch) | |
tree | 86c452349612ec00b52d83c78900bcf45b6bbd8d /arch/arm64/include | |
parent | e8bf24bd439da1ee7f37c2b03f44c6ad37c0c8c0 (diff) | |
download | linux-297565aa22cfa80ab0f88c3569693aea0b6afb6d.tar.bz2 |
lib/xor: make xor prototypes more friendly to compiler vectorization
Modern compilers are perfectly capable of extracting parallelism from
the XOR routines, provided that the prototypes reflect the nature of the
input accurately, in particular, the fact that the input vectors are
expected not to overlap. This is not documented explicitly, but is
implied by the interchangeability of the various C routines, some of
which use temporary variables while others don't: this means that these
routines only behave identically for non-overlapping inputs.
So let's decorate these input vectors with the __restrict modifier,
which informs the compiler that there is no overlap. While at it, make
the input-only vectors pointer-to-const as well.
Tested-by: Nathan Chancellor <nathan@kernel.org>
Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
Reviewed-by: Nick Desaulniers <ndesaulniers@google.com>
Link: https://github.com/ClangBuiltLinux/linux/issues/563
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Diffstat (limited to 'arch/arm64/include')
-rw-r--r-- | arch/arm64/include/asm/xor.h | 21 |
1 files changed, 14 insertions, 7 deletions
diff --git a/arch/arm64/include/asm/xor.h b/arch/arm64/include/asm/xor.h index 947f6a4f1aa0..befcd8a7abc9 100644 --- a/arch/arm64/include/asm/xor.h +++ b/arch/arm64/include/asm/xor.h @@ -16,7 +16,8 @@ extern struct xor_block_template const xor_block_inner_neon; static void -xor_neon_2(unsigned long bytes, unsigned long *p1, unsigned long *p2) +xor_neon_2(unsigned long bytes, unsigned long * __restrict p1, + const unsigned long * __restrict p2) { kernel_neon_begin(); xor_block_inner_neon.do_2(bytes, p1, p2); @@ -24,8 +25,9 @@ xor_neon_2(unsigned long bytes, unsigned long *p1, unsigned long *p2) } static void -xor_neon_3(unsigned long bytes, unsigned long *p1, unsigned long *p2, - unsigned long *p3) +xor_neon_3(unsigned long bytes, unsigned long * __restrict p1, + const unsigned long * __restrict p2, + const unsigned long * __restrict p3) { kernel_neon_begin(); xor_block_inner_neon.do_3(bytes, p1, p2, p3); @@ -33,8 +35,10 @@ xor_neon_3(unsigned long bytes, unsigned long *p1, unsigned long *p2, } static void -xor_neon_4(unsigned long bytes, unsigned long *p1, unsigned long *p2, - unsigned long *p3, unsigned long *p4) +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) { kernel_neon_begin(); xor_block_inner_neon.do_4(bytes, p1, p2, p3, p4); @@ -42,8 +46,11 @@ xor_neon_4(unsigned long bytes, unsigned long *p1, unsigned long *p2, } static void -xor_neon_5(unsigned long bytes, unsigned long *p1, unsigned long *p2, - unsigned long *p3, unsigned long *p4, unsigned long *p5) +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, + const unsigned long * __restrict p5) { kernel_neon_begin(); xor_block_inner_neon.do_5(bytes, p1, p2, p3, p4, p5); |