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 10:39:39 +0100 |
| commit | 297565aa22cfa80ab0f88c3569693aea0b6afb6d (patch) | |
| tree | 86c452349612ec00b52d83c78900bcf45b6bbd8d /arch/s390/lib | |
| parent | crypto: atmel-tdes - Add support for the TDES IP available on sama7g5 SoC (diff) | |
| download | linux-297565aa22cfa80ab0f88c3569693aea0b6afb6d.tar.xz linux-297565aa22cfa80ab0f88c3569693aea0b6afb6d.zip | |
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/s390/lib')
| -rw-r--r-- | arch/s390/lib/xor.c | 21 |
1 files changed, 14 insertions, 7 deletions
diff --git a/arch/s390/lib/xor.c b/arch/s390/lib/xor.c index a963c3d8ad0d..fb924a8041dc 100644 --- a/arch/s390/lib/xor.c +++ b/arch/s390/lib/xor.c @@ -11,7 +11,8 @@ #include <linux/raid/xor.h> #include <asm/xor.h> -static void xor_xc_2(unsigned long bytes, unsigned long *p1, unsigned long *p2) +static void xor_xc_2(unsigned long bytes, unsigned long * __restrict p1, + const unsigned long * __restrict p2) { asm volatile( " larl 1,2f\n" @@ -32,8 +33,9 @@ static void xor_xc_2(unsigned long bytes, unsigned long *p1, unsigned long *p2) : "0", "1", "cc", "memory"); } -static void xor_xc_3(unsigned long bytes, unsigned long *p1, unsigned long *p2, - unsigned long *p3) +static void xor_xc_3(unsigned long bytes, unsigned long * __restrict p1, + const unsigned long * __restrict p2, + const unsigned long * __restrict p3) { asm volatile( " larl 1,2f\n" @@ -58,8 +60,10 @@ static void xor_xc_3(unsigned long bytes, unsigned long *p1, unsigned long *p2, : : "0", "1", "cc", "memory"); } -static void xor_xc_4(unsigned long bytes, unsigned long *p1, unsigned long *p2, - unsigned long *p3, unsigned long *p4) +static void xor_xc_4(unsigned long bytes, unsigned long * __restrict p1, + const unsigned long * __restrict p2, + const unsigned long * __restrict p3, + const unsigned long * __restrict p4) { asm volatile( " larl 1,2f\n" @@ -88,8 +92,11 @@ static void xor_xc_4(unsigned long bytes, unsigned long *p1, unsigned long *p2, : : "0", "1", "cc", "memory"); } -static void xor_xc_5(unsigned long bytes, unsigned long *p1, unsigned long *p2, - unsigned long *p3, unsigned long *p4, unsigned long *p5) +static void xor_xc_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) { asm volatile( " larl 1,2f\n" |