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/lib | |
parent | e8bf24bd439da1ee7f37c2b03f44c6ad37c0c8c0 (diff) |
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/lib')
-rw-r--r-- | arch/arm64/lib/xor-neon.c | 46 |
1 files changed, 29 insertions, 17 deletions
diff --git a/arch/arm64/lib/xor-neon.c b/arch/arm64/lib/xor-neon.c index d189cf4e70ea..96b171995d19 100644 --- a/arch/arm64/lib/xor-neon.c +++ b/arch/arm64/lib/xor-neon.c @@ -10,8 +10,8 @@ #include <linux/module.h> #include <asm/neon-intrinsics.h> -void xor_arm64_neon_2(unsigned long bytes, unsigned long *p1, - unsigned long *p2) +void xor_arm64_neon_2(unsigned long bytes, unsigned long * __restrict p1, + const unsigned long * __restrict p2) { uint64_t *dp1 = (uint64_t *)p1; uint64_t *dp2 = (uint64_t *)p2; @@ -37,8 +37,9 @@ void xor_arm64_neon_2(unsigned long bytes, unsigned long *p1, } while (--lines > 0); } -void xor_arm64_neon_3(unsigned long bytes, unsigned long *p1, - unsigned long *p2, unsigned long *p3) +void xor_arm64_neon_3(unsigned long bytes, unsigned long * __restrict p1, + const unsigned long * __restrict p2, + const unsigned long * __restrict p3) { uint64_t *dp1 = (uint64_t *)p1; uint64_t *dp2 = (uint64_t *)p2; @@ -72,8 +73,10 @@ void xor_arm64_neon_3(unsigned long bytes, unsigned long *p1, } while (--lines > 0); } -void xor_arm64_neon_4(unsigned long bytes, unsigned long *p1, - unsigned long *p2, unsigned long *p3, unsigned long *p4) +void xor_arm64_neon_4(unsigned long bytes, unsigned long * __restrict p1, + const unsigned long * __restrict p2, + const unsigned long * __restrict p3, + const unsigned long * __restrict p4) { uint64_t *dp1 = (uint64_t *)p1; uint64_t *dp2 = (uint64_t *)p2; @@ -115,9 +118,11 @@ void xor_arm64_neon_4(unsigned long bytes, unsigned long *p1, } while (--lines > 0); } -void xor_arm64_neon_5(unsigned long bytes, unsigned long *p1, - unsigned long *p2, unsigned long *p3, - unsigned long *p4, unsigned long *p5) +void xor_arm64_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) { uint64_t *dp1 = (uint64_t *)p1; uint64_t *dp2 = (uint64_t *)p2; @@ -186,8 +191,10 @@ static inline uint64x2_t eor3(uint64x2_t p, uint64x2_t q, uint64x2_t r) return res; } -static void xor_arm64_eor3_3(unsigned long bytes, unsigned long *p1, - unsigned long *p2, unsigned long *p3) +static void xor_arm64_eor3_3(unsigned long bytes, + unsigned long * __restrict p1, + const unsigned long * __restrict p2, + const unsigned long * __restrict p3) { uint64_t *dp1 = (uint64_t *)p1; uint64_t *dp2 = (uint64_t *)p2; @@ -219,9 +226,11 @@ static void xor_arm64_eor3_3(unsigned long bytes, unsigned long *p1, } while (--lines > 0); } -static void xor_arm64_eor3_4(unsigned long bytes, unsigned long *p1, - unsigned long *p2, unsigned long *p3, - unsigned long *p4) +static void xor_arm64_eor3_4(unsigned long bytes, + unsigned long * __restrict p1, + const unsigned long * __restrict p2, + const unsigned long * __restrict p3, + const unsigned long * __restrict p4) { uint64_t *dp1 = (uint64_t *)p1; uint64_t *dp2 = (uint64_t *)p2; @@ -261,9 +270,12 @@ static void xor_arm64_eor3_4(unsigned long bytes, unsigned long *p1, } while (--lines > 0); } -static void xor_arm64_eor3_5(unsigned long bytes, unsigned long *p1, - unsigned long *p2, unsigned long *p3, - unsigned long *p4, unsigned long *p5) +static void xor_arm64_eor3_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) { uint64_t *dp1 = (uint64_t *)p1; uint64_t *dp2 = (uint64_t *)p2; |