From 352ebd066b625a5058bd988e5b32e6992f4d5b88 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 27 Mar 2026 07:16:52 +0100 Subject: xor: avoid indirect calls for arm64-optimized ops Remove the inner xor_block_templates, and instead have two separate actual template that call into the neon-enabled compilation unit. Link: https://lkml.kernel.org/r/20260327061704.3707577-21-hch@lst.de Signed-off-by: Christoph Hellwig Reviewed-by: Eric Biggers Tested-by: Eric Biggers Cc: Albert Ou Cc: Alexander Gordeev Cc: Alexandre Ghiti Cc: Andreas Larsson Cc: Anton Ivanov Cc: Ard Biesheuvel Cc: Arnd Bergmann Cc: "Borislav Petkov (AMD)" Cc: Catalin Marinas Cc: Chris Mason Cc: Christian Borntraeger Cc: Dan Williams Cc: David S. Miller Cc: David Sterba Cc: Heiko Carstens Cc: Herbert Xu Cc: "H. Peter Anvin" Cc: Huacai Chen Cc: Ingo Molnar Cc: Jason A. Donenfeld Cc: Johannes Berg Cc: Li Nan Cc: Madhavan Srinivasan Cc: Magnus Lindholm Cc: Matt Turner Cc: Michael Ellerman Cc: Nicholas Piggin Cc: Palmer Dabbelt Cc: Richard Henderson Cc: Richard Weinberger Cc: Russell King Cc: Song Liu Cc: Sven Schnelle Cc: Ted Ts'o Cc: Vasily Gorbik Cc: WANG Xuerui Cc: Will Deacon Signed-off-by: Andrew Morton --- lib/raid/xor/arm64/xor-neon-glue.c | 95 ++++++++++++++++++++------------------ lib/raid/xor/arm64/xor-neon.c | 73 +++++++++++------------------ lib/raid/xor/arm64/xor-neon.h | 30 ++++++++++++ 3 files changed, 106 insertions(+), 92 deletions(-) create mode 100644 lib/raid/xor/arm64/xor-neon.h (limited to 'lib/raid') diff --git a/lib/raid/xor/arm64/xor-neon-glue.c b/lib/raid/xor/arm64/xor-neon-glue.c index 067a2095659a..08c3e3573388 100644 --- a/lib/raid/xor/arm64/xor-neon-glue.c +++ b/lib/raid/xor/arm64/xor-neon-glue.c @@ -7,51 +7,54 @@ #include #include #include +#include "xor-neon.h" -extern struct xor_block_template const xor_block_inner_neon; - -static void -xor_neon_2(unsigned long bytes, unsigned long * __restrict p1, - const unsigned long * __restrict p2) -{ - scoped_ksimd() - xor_block_inner_neon.do_2(bytes, p1, p2); -} - -static void -xor_neon_3(unsigned long bytes, unsigned long * __restrict p1, - const unsigned long * __restrict p2, - const unsigned long * __restrict p3) -{ - scoped_ksimd() - xor_block_inner_neon.do_3(bytes, p1, p2, p3); -} - -static void -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) -{ - scoped_ksimd() - xor_block_inner_neon.do_4(bytes, p1, p2, p3, p4); -} - -static void -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) -{ - scoped_ksimd() - xor_block_inner_neon.do_5(bytes, p1, p2, p3, p4, p5); -} - -struct xor_block_template xor_block_arm64 = { - .name = "arm64_neon", - .do_2 = xor_neon_2, - .do_3 = xor_neon_3, - .do_4 = xor_neon_4, - .do_5 = xor_neon_5 +#define XOR_TEMPLATE(_name) \ +static void \ +xor_##_name##_2(unsigned long bytes, unsigned long * __restrict p1, \ + const unsigned long * __restrict p2) \ +{ \ + scoped_ksimd() \ + __xor_##_name##_2(bytes, p1, p2); \ +} \ + \ +static void \ +xor_##_name##_3(unsigned long bytes, unsigned long * __restrict p1, \ + const unsigned long * __restrict p2, \ + const unsigned long * __restrict p3) \ +{ \ + scoped_ksimd() \ + __xor_##_name##_3(bytes, p1, p2, p3); \ +} \ + \ +static void \ +xor_##_name##_4(unsigned long bytes, unsigned long * __restrict p1, \ + const unsigned long * __restrict p2, \ + const unsigned long * __restrict p3, \ + const unsigned long * __restrict p4) \ +{ \ + scoped_ksimd() \ + __xor_##_name##_4(bytes, p1, p2, p3, p4); \ +} \ + \ +static void \ +xor_##_name##_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) \ +{ \ + scoped_ksimd() \ + __xor_##_name##_5(bytes, p1, p2, p3, p4, p5); \ +} \ + \ +struct xor_block_template xor_block_##_name = { \ + .name = __stringify(_name), \ + .do_2 = xor_##_name##_2, \ + .do_3 = xor_##_name##_3, \ + .do_4 = xor_##_name##_4, \ + .do_5 = xor_##_name##_5 \ }; + +XOR_TEMPLATE(neon); +XOR_TEMPLATE(eor3); diff --git a/lib/raid/xor/arm64/xor-neon.c b/lib/raid/xor/arm64/xor-neon.c index 8d2d185090db..61194c292917 100644 --- a/lib/raid/xor/arm64/xor-neon.c +++ b/lib/raid/xor/arm64/xor-neon.c @@ -8,9 +8,10 @@ #include #include #include +#include "xor-neon.h" -static void xor_arm64_neon_2(unsigned long bytes, unsigned long * __restrict p1, - const unsigned long * __restrict p2) +void __xor_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; @@ -36,9 +37,9 @@ static void xor_arm64_neon_2(unsigned long bytes, unsigned long * __restrict p1, } while (--lines > 0); } -static void xor_arm64_neon_3(unsigned long bytes, unsigned long * __restrict p1, - const unsigned long * __restrict p2, - const unsigned long * __restrict p3) +void __xor_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; @@ -72,10 +73,10 @@ static void xor_arm64_neon_3(unsigned long bytes, unsigned long * __restrict p1, } while (--lines > 0); } -static 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) +void __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) { uint64_t *dp1 = (uint64_t *)p1; uint64_t *dp2 = (uint64_t *)p2; @@ -117,11 +118,11 @@ static void xor_arm64_neon_4(unsigned long bytes, unsigned long * __restrict p1, } while (--lines > 0); } -static 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) +void __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) { uint64_t *dp1 = (uint64_t *)p1; uint64_t *dp2 = (uint64_t *)p2; @@ -171,14 +172,6 @@ static void xor_arm64_neon_5(unsigned long bytes, unsigned long * __restrict p1, } while (--lines > 0); } -struct xor_block_template xor_block_inner_neon __ro_after_init = { - .name = "__inner_neon__", - .do_2 = xor_arm64_neon_2, - .do_3 = xor_arm64_neon_3, - .do_4 = xor_arm64_neon_4, - .do_5 = xor_arm64_neon_5, -}; - static inline uint64x2_t eor3(uint64x2_t p, uint64x2_t q, uint64x2_t r) { uint64x2_t res; @@ -189,10 +182,9 @@ 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 * __restrict p1, - const unsigned long * __restrict p2, - const unsigned long * __restrict p3) +void __xor_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; @@ -224,11 +216,10 @@ static void xor_arm64_eor3_3(unsigned long bytes, } while (--lines > 0); } -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) +void __xor_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; @@ -268,12 +259,11 @@ static void xor_arm64_eor3_4(unsigned long bytes, } while (--lines > 0); } -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) +void __xor_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; @@ -314,12 +304,3 @@ static void xor_arm64_eor3_5(unsigned long bytes, dp5 += 8; } while (--lines > 0); } - -void __init xor_neon_init(void) -{ - if (cpu_have_named_feature(SHA3)) { - xor_block_inner_neon.do_3 = xor_arm64_eor3_3; - xor_block_inner_neon.do_4 = xor_arm64_eor3_4; - xor_block_inner_neon.do_5 = xor_arm64_eor3_5; - } -} diff --git a/lib/raid/xor/arm64/xor-neon.h b/lib/raid/xor/arm64/xor-neon.h new file mode 100644 index 000000000000..cec0ac846fea --- /dev/null +++ b/lib/raid/xor/arm64/xor-neon.h @@ -0,0 +1,30 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ + +void __xor_neon_2(unsigned long bytes, unsigned long * __restrict p1, + const unsigned long * __restrict p2); +void __xor_neon_3(unsigned long bytes, unsigned long * __restrict p1, + const unsigned long * __restrict p2, + const unsigned long * __restrict p3); +void __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); +void __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); + +#define __xor_eor3_2 __xor_neon_2 +void __xor_eor3_3(unsigned long bytes, unsigned long * __restrict p1, + const unsigned long * __restrict p2, + const unsigned long * __restrict p3); +void __xor_eor3_4(unsigned long bytes, unsigned long * __restrict p1, + const unsigned long * __restrict p2, + const unsigned long * __restrict p3, + const unsigned long * __restrict p4); +void __xor_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); -- cgit v1.2.3