diff options
| -rw-r--r-- | lib/crypto/x86/blake2s-core.S | 45 |
1 files changed, 26 insertions, 19 deletions
diff --git a/lib/crypto/x86/blake2s-core.S b/lib/crypto/x86/blake2s-core.S index aee13b97cc34..14e487559c09 100644 --- a/lib/crypto/x86/blake2s-core.S +++ b/lib/crypto/x86/blake2s-core.S @@ -6,19 +6,25 @@ #include <linux/linkage.h> -.section .rodata.cst32.BLAKE2S_IV, "aM", @progbits, 32 +.section .rodata.cst32.iv, "aM", @progbits, 32 .align 32 -IV: .octa 0xA54FF53A3C6EF372BB67AE856A09E667 +.Liv: + .octa 0xA54FF53A3C6EF372BB67AE856A09E667 .octa 0x5BE0CD191F83D9AB9B05688C510E527F -.section .rodata.cst16.ROT16, "aM", @progbits, 16 + +.section .rodata.cst16.ror16, "aM", @progbits, 16 .align 16 -ROT16: .octa 0x0D0C0F0E09080B0A0504070601000302 -.section .rodata.cst16.ROR328, "aM", @progbits, 16 +.Lror16: + .octa 0x0D0C0F0E09080B0A0504070601000302 + +.section .rodata.cst16.ror8, "aM", @progbits, 16 .align 16 -ROR328: .octa 0x0C0F0E0D080B0A090407060500030201 -.section .rodata.cst64.BLAKE2S_SIGMA, "aM", @progbits, 160 +.Lror8: + .octa 0x0C0F0E0D080B0A090407060500030201 + +.section .rodata.cst64.sigma, "aM", @progbits, 160 .align 64 -SIGMA: +.Lsigma: .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 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 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 -.section .rodata.cst64.BLAKE2S_SIGMA2, "aM", @progbits, 160 + +.section .rodata.cst64.sigma2, "aM", @progbits, 160 .align 64 -SIGMA2: +.Lsigma2: .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 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) movdqu (%rdi),%xmm0 movdqu 0x10(%rdi),%xmm1 - movdqa ROT16(%rip),%xmm12 - movdqa ROR328(%rip),%xmm13 + movdqa .Lror16(%rip),%xmm12 + movdqa .Lror8(%rip),%xmm13 movdqu 0x20(%rdi),%xmm14 movd %ecx,%xmm15 - leaq SIGMA+0xa0(%rip),%r8 + leaq .Lsigma+0xa0(%rip),%r8 jmp .Lbeginofloop .align 32 .Lbeginofloop: movdqa %xmm0,%xmm10 movdqa %xmm1,%xmm11 paddq %xmm15,%xmm14 - movdqa IV(%rip),%xmm2 + movdqa .Liv(%rip),%xmm2 movdqa %xmm14,%xmm3 - pxor IV+0x10(%rip),%xmm3 - leaq SIGMA(%rip),%rcx + pxor .Liv+0x10(%rip),%xmm3 + leaq .Lsigma(%rip),%rcx .Lroundloop: movzbl (%rcx),%eax movd (%rsi,%rax,4),%xmm4 @@ -174,8 +181,8 @@ SYM_FUNC_START(blake2s_compress_avx512) vmovdqu 0x10(%rdi),%xmm1 vmovdqu 0x20(%rdi),%xmm4 vmovd %ecx,%xmm5 - vmovdqa IV(%rip),%xmm14 - vmovdqa IV+16(%rip),%xmm15 + vmovdqa .Liv(%rip),%xmm14 + vmovdqa .Liv+16(%rip),%xmm15 jmp .Lblake2s_compress_avx512_mainloop .align 32 .Lblake2s_compress_avx512_mainloop: @@ -187,7 +194,7 @@ SYM_FUNC_START(blake2s_compress_avx512) vmovdqu (%rsi),%ymm6 vmovdqu 0x20(%rsi),%ymm7 addq $0x40,%rsi - leaq SIGMA2(%rip),%rax + leaq .Lsigma2(%rip),%rax movb $0xa,%cl .Lblake2s_compress_avx512_roundloop: vpmovzxbd (%rax),%ymm8 |