admin/linux
1
0
Fork 0
mirror of https://github.com/torvalds/linux.git synced 2025-12-07 20:06:24 +00:00
Code Issues Packages Projects Releases Wiki Activity

lib/crypto: x86/blake2s: Use local labels for data

Browse Source 
Following the usual practice, prefix the names of the data labels with
".L" so that the assembler treats them as truly local.  This more
clearly expresses the intent and is less error-prone.

Reviewed-by: Ard Biesheuvel <ardb@kernel.org>
Link: https://lore.kernel.org/r/20251102234209.62133-4-ebiggers@kernel.org
Signed-off-by: Eric Biggers <ebiggers@kernel.org>
This commit is contained in:
Eric Biggers
2025-11-02 15:42:06 -08:00
parent c19bdf24cc
commit 83c1a867c9
1 changed files with 26 additions and 19 deletions
Download Patch File Download Diff File Expand all files Collapse all files

45
lib/crypto/x86/blake2s-core.S
View File

@@ -6,19 +6,25 @@
#include <linux/linkage.h> #include <linux/linkage.h>
.section .rodata.cst32.BLAKE2S_IV, "aM", @progbits, 32 .section .rodata.cst32.iv, "aM", @progbits, 32
.align 32 .align 32
IV: .octa 0xA54FF53A3C6EF372BB67AE856A09E667 .Liv:
.octa 0xA54FF53A3C6EF372BB67AE856A09E667
.octa 0x5BE0CD191F83D9AB9B05688C510E527F .octa 0x5BE0CD191F83D9AB9B05688C510E527F
.section .rodata.cst16.ROT16, "aM", @progbits, 16
.section .rodata.cst16.ror16, "aM", @progbits, 16
.align 16 .align 16
ROT16: .octa 0x0D0C0F0E09080B0A0504070601000302 .Lror16:
.section .rodata.cst16.ROR328, "aM", @progbits, 16 .octa 0x0D0C0F0E09080B0A0504070601000302
.section .rodata.cst16.ror8, "aM", @progbits, 16
.align 16 .align 16
ROR328: .octa 0x0C0F0E0D080B0A090407060500030201 .Lror8:
.section .rodata.cst64.BLAKE2S_SIGMA, "aM", @progbits, 160 .octa 0x0C0F0E0D080B0A090407060500030201
.section .rodata.cst64.sigma, "aM", @progbits, 160
.align 64 .align 64
SIGMA: .Lsigma:
.byte 0, 2, 4, 6, 1, 3, 5, 7, 14, 8, 10, 12, 15, 9, 11, 13 .byte 0, 2, 4, 6, 1, 3, 5, 7, 14, 8, 10, 12, 15, 9, 11, 13
.byte 14, 4, 9, 13, 10, 8, 15, 6, 5, 1, 0, 11, 3, 12, 2, 7 .byte 14, 4, 9, 13, 10, 8, 15, 6, 5, 1, 0, 11, 3, 12, 2, 7
.byte 11, 12, 5, 15, 8, 0, 2, 13, 9, 10, 3, 7, 4, 14, 6, 1 .byte 11, 12, 5, 15, 8, 0, 2, 13, 9, 10, 3, 7, 4, 14, 6, 1
@@ -29,9 +35,10 @@ SIGMA:
.byte 13, 7, 12, 3, 11, 14, 1, 9, 2, 5, 15, 8, 10, 0, 4, 6 .byte 13, 7, 12, 3, 11, 14, 1, 9, 2, 5, 15, 8, 10, 0, 4, 6
.byte 6, 14, 11, 0, 15, 9, 3, 8, 10, 12, 13, 1, 5, 2, 7, 4 .byte 6, 14, 11, 0, 15, 9, 3, 8, 10, 12, 13, 1, 5, 2, 7, 4
.byte 10, 8, 7, 1, 2, 4, 6, 5, 13, 15, 9, 3, 0, 11, 14, 12 .byte 10, 8, 7, 1, 2, 4, 6, 5, 13, 15, 9, 3, 0, 11, 14, 12
.section .rodata.cst64.BLAKE2S_SIGMA2, "aM", @progbits, 160
.section .rodata.cst64.sigma2, "aM", @progbits, 160
.align 64 .align 64
SIGMA2: .Lsigma2:
.byte 0, 2, 4, 6, 1, 3, 5, 7, 14, 8, 10, 12, 15, 9, 11, 13 .byte 0, 2, 4, 6, 1, 3, 5, 7, 14, 8, 10, 12, 15, 9, 11, 13
.byte 8, 2, 13, 15, 10, 9, 12, 3, 6, 4, 0, 14, 5, 11, 1, 7 .byte 8, 2, 13, 15, 10, 9, 12, 3, 6, 4, 0, 14, 5, 11, 1, 7
.byte 11, 13, 8, 6, 5, 10, 14, 3, 2, 4, 12, 15, 1, 0, 7, 9 .byte 11, 13, 8, 6, 5, 10, 14, 3, 2, 4, 12, 15, 1, 0, 7, 9
@@ -47,21 +54,21 @@ SIGMA2:
SYM_FUNC_START(blake2s_compress_ssse3) SYM_FUNC_START(blake2s_compress_ssse3)
movdqu (%rdi),%xmm0 movdqu (%rdi),%xmm0
movdqu 0x10(%rdi),%xmm1 movdqu 0x10(%rdi),%xmm1
movdqa ROT16(%rip),%xmm12 movdqa .Lror16(%rip),%xmm12
movdqa ROR328(%rip),%xmm13 movdqa .Lror8(%rip),%xmm13
movdqu 0x20(%rdi),%xmm14 movdqu 0x20(%rdi),%xmm14
movd %ecx,%xmm15 movd %ecx,%xmm15
leaq SIGMA+0xa0(%rip),%r8 leaq .Lsigma+0xa0(%rip),%r8
jmp .Lbeginofloop jmp .Lbeginofloop
.align 32 .align 32
.Lbeginofloop: .Lbeginofloop:
movdqa %xmm0,%xmm10 movdqa %xmm0,%xmm10
movdqa %xmm1,%xmm11 movdqa %xmm1,%xmm11
paddq %xmm15,%xmm14 paddq %xmm15,%xmm14
movdqa IV(%rip),%xmm2 movdqa .Liv(%rip),%xmm2
movdqa %xmm14,%xmm3 movdqa %xmm14,%xmm3
pxor IV+0x10(%rip),%xmm3 pxor .Liv+0x10(%rip),%xmm3
leaq SIGMA(%rip),%rcx leaq .Lsigma(%rip),%rcx
.Lroundloop: .Lroundloop:
movzbl (%rcx),%eax movzbl (%rcx),%eax
movd (%rsi,%rax,4),%xmm4 movd (%rsi,%rax,4),%xmm4
@@ -174,8 +181,8 @@ SYM_FUNC_START(blake2s_compress_avx512)
vmovdqu 0x10(%rdi),%xmm1 vmovdqu 0x10(%rdi),%xmm1
vmovdqu 0x20(%rdi),%xmm4 vmovdqu 0x20(%rdi),%xmm4
vmovd %ecx,%xmm5 vmovd %ecx,%xmm5
vmovdqa IV(%rip),%xmm14 vmovdqa .Liv(%rip),%xmm14
vmovdqa IV+16(%rip),%xmm15 vmovdqa .Liv+16(%rip),%xmm15
jmp .Lblake2s_compress_avx512_mainloop jmp .Lblake2s_compress_avx512_mainloop
.align 32 .align 32
.Lblake2s_compress_avx512_mainloop: .Lblake2s_compress_avx512_mainloop:
@@ -187,7 +194,7 @@ SYM_FUNC_START(blake2s_compress_avx512)
vmovdqu (%rsi),%ymm6 vmovdqu (%rsi),%ymm6
vmovdqu 0x20(%rsi),%ymm7 vmovdqu 0x20(%rsi),%ymm7
addq $0x40,%rsi addq $0x40,%rsi
leaq SIGMA2(%rip),%rax leaq .Lsigma2(%rip),%rax
movb $0xa,%cl movb $0xa,%cl
.Lblake2s_compress_avx512_roundloop: .Lblake2s_compress_avx512_roundloop:
vpmovzxbd (%rax),%ymm8 vpmovzxbd (%rax),%ymm8