Linux kernel mirror (for testing)
git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git
kernel
os
linux
lib/crypto: x86/blake2s: Reduce size of BLAKE2S_SIGMA2
Save 480 bytes of .rodata by replacing the .long constants with .bytes,
and using the vpmovzxbd instruction to expand them.
Also update the code to do the loads before incrementing %rax rather
than after. This avoids the need for the first load to use an offset.
Reviewed-by: Ard Biesheuvel <ardb@kernel.org>
Link: https://lore.kernel.org/r/20250827151131.27733-8-ebiggers@kernel.org
Signed-off-by: Eric Biggers <ebiggers@kernel.org>
+14
-14
+14
-14
lib/crypto/x86/blake2s-core.S
+14
-14
lib/crypto/x86/blake2s-core.S
···
29
29
.byte 13, 7, 12, 3, 11, 14, 1, 9, 2, 5, 15, 8, 10, 0, 4, 6
30
30
.byte 6, 14, 11, 0, 15, 9, 3, 8, 10, 12, 13, 1, 5, 2, 7, 4
31
31
.byte 10, 8, 7, 1, 2, 4, 6, 5, 13, 15, 9, 3, 0, 11, 14, 12
32
-
.section .rodata.cst64.BLAKE2S_SIGMA2, "aM", @progbits, 640
32
+
.section .rodata.cst64.BLAKE2S_SIGMA2, "aM", @progbits, 160
33
33
.align 64
34
34
SIGMA2:
35
-
.long 0, 2, 4, 6, 1, 3, 5, 7, 14, 8, 10, 12, 15, 9, 11, 13
36
-
.long 8, 2, 13, 15, 10, 9, 12, 3, 6, 4, 0, 14, 5, 11, 1, 7
37
-
.long 11, 13, 8, 6, 5, 10, 14, 3, 2, 4, 12, 15, 1, 0, 7, 9
38
-
.long 11, 10, 7, 0, 8, 15, 1, 13, 3, 6, 2, 12, 4, 14, 9, 5
39
-
.long 4, 10, 9, 14, 15, 0, 11, 8, 1, 7, 3, 13, 2, 5, 6, 12
40
-
.long 2, 11, 4, 15, 14, 3, 10, 8, 13, 6, 5, 7, 0, 12, 1, 9
41
-
.long 4, 8, 15, 9, 14, 11, 13, 5, 3, 2, 1, 12, 6, 10, 7, 0
42
-
.long 6, 13, 0, 14, 12, 2, 1, 11, 15, 4, 5, 8, 7, 9, 3, 10
43
-
.long 15, 5, 4, 13, 10, 7, 3, 11, 12, 2, 0, 6, 9, 8, 1, 14
44
-
.long 8, 7, 14, 11, 13, 15, 0, 12, 10, 4, 5, 6, 3, 2, 1, 9
35
+
.byte 0, 2, 4, 6, 1, 3, 5, 7, 14, 8, 10, 12, 15, 9, 11, 13
36
+
.byte 8, 2, 13, 15, 10, 9, 12, 3, 6, 4, 0, 14, 5, 11, 1, 7
37
+
.byte 11, 13, 8, 6, 5, 10, 14, 3, 2, 4, 12, 15, 1, 0, 7, 9
38
+
.byte 11, 10, 7, 0, 8, 15, 1, 13, 3, 6, 2, 12, 4, 14, 9, 5
39
+
.byte 4, 10, 9, 14, 15, 0, 11, 8, 1, 7, 3, 13, 2, 5, 6, 12
40
+
.byte 2, 11, 4, 15, 14, 3, 10, 8, 13, 6, 5, 7, 0, 12, 1, 9
41
+
.byte 4, 8, 15, 9, 14, 11, 13, 5, 3, 2, 1, 12, 6, 10, 7, 0
42
+
.byte 6, 13, 0, 14, 12, 2, 1, 11, 15, 4, 5, 8, 7, 9, 3, 10
43
+
.byte 15, 5, 4, 13, 10, 7, 3, 11, 12, 2, 0, 6, 9, 8, 1, 14
44
+
.byte 8, 7, 14, 11, 13, 15, 0, 12, 10, 4, 5, 6, 3, 2, 1, 9
45
45
46
46
.text
47
47
SYM_FUNC_START(blake2s_compress_ssse3)
···
193
193
leaq SIGMA2(%rip),%rax
194
194
movb $0xa,%cl
195
195
.Lblake2s_compress_avx512_roundloop:
196
-
addq $0x40,%rax
197
-
vmovdqa -0x40(%rax),%ymm8
198
-
vmovdqa -0x20(%rax),%ymm9
196
+
vpmovzxbd (%rax),%ymm8
197
+
vpmovzxbd 0x8(%rax),%ymm9
198
+
addq $0x10,%rax
199
199
vpermi2d %ymm7,%ymm6,%ymm8
200
200
vpermi2d %ymm7,%ymm6,%ymm9
201
201
vmovdqa %ymm8,%ymm6