diff options
| author | Ard Biesheuvel <ardb@kernel.org> | 2025-10-01 13:58:26 +0200 |
|---|---|---|
| committer | Ard Biesheuvel <ardb@kernel.org> | 2025-11-12 09:52:02 +0100 |
| commit | ab5718f06b6774b99230c71c1ee5476236496b62 (patch) | |
| tree | 4f50d3b63c73799bf25098ca95e72d98d23ed8fa | |
| parent | 03bc4768fbf1bfe72497204410b58dacf29730d2 (diff) | |
arm64/xorblocks: Switch to 'ksimd' scoped guard API
Switch to the more abstract 'scoped_ksimd()' API, which will be modified
in a future patch to transparently allocate a kernel mode FP/SIMD state
buffer on the stack, so that kernel mode FP/SIMD code remains
preemptible in principe, but without the memory overhead that adds 528
bytes to the size of struct task_struct.
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>
| -rw-r--r-- | arch/arm64/include/asm/xor.h | 22 |
1 files changed, 9 insertions, 13 deletions
diff --git a/arch/arm64/include/asm/xor.h b/arch/arm64/include/asm/xor.h index befcd8a7abc9..c38e3d017a79 100644 --- a/arch/arm64/include/asm/xor.h +++ b/arch/arm64/include/asm/xor.h @@ -9,7 +9,7 @@ #include <linux/hardirq.h> #include <asm-generic/xor.h> #include <asm/hwcap.h> -#include <asm/neon.h> +#include <asm/simd.h> #ifdef CONFIG_KERNEL_MODE_NEON @@ -19,9 +19,8 @@ static void 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); - kernel_neon_end(); + scoped_ksimd() + xor_block_inner_neon.do_2(bytes, p1, p2); } static void @@ -29,9 +28,8 @@ 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); - kernel_neon_end(); + scoped_ksimd() + xor_block_inner_neon.do_3(bytes, p1, p2, p3); } static void @@ -40,9 +38,8 @@ xor_neon_4(unsigned long bytes, unsigned long * __restrict p1, const unsigned long * __restrict p3, const unsigned long * __restrict p4) { - kernel_neon_begin(); - xor_block_inner_neon.do_4(bytes, p1, p2, p3, p4); - kernel_neon_end(); + scoped_ksimd() + xor_block_inner_neon.do_4(bytes, p1, p2, p3, p4); } static void @@ -52,9 +49,8 @@ xor_neon_5(unsigned long bytes, unsigned long * __restrict p1, 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); - kernel_neon_end(); + scoped_ksimd() + xor_block_inner_neon.do_5(bytes, p1, p2, p3, p4, p5); } static struct xor_block_template xor_block_arm64 = { |