mirrors/linux
1
0
Fork 0
mirror of https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git synced 2026-05-01 01:14:19 -04:00
Code Issues Packages Projects Releases Wiki Activity

crypto: x86/aes-xts - eliminate a few more instructions

Browse Source 
- For conditionally subtracting 16 from LEN when decrypting a message
  whose length isn't a multiple of 16, use the cmovnz instruction.

- Fold the addition of 4*VL to LEN into the sub of VL or 16 from LEN.

- Remove an unnecessary test instruction.

This results in slightly shorter code, both source and binary.

Signed-off-by: Eric Biggers <ebiggers@google.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
This commit is contained in:
Eric Biggers
2024-04-12 20:17:27 -07:00
committed by Herbert Xu
parent 2717e01fc3
commit e619723a85
1 changed files with 13 additions and 26 deletions
Download Patch File Download Diff File Expand all files Collapse all files

39
arch/x86/crypto/aes-xts-avx-x86_64.S
View File

@@ -559,20 +559,20 @@
.macro _aes_xts_crypt enc
_define_aliases
// Load the AES key length: 16 (AES-128), 24 (AES-192), or 32 (AES-256).
movl 480(KEY), KEYLEN
.if !\enc
// When decrypting a message whose length isn't a multiple of the AES
// block length, exclude the last full block from the main loop by
// subtracting 16 from LEN. This is needed because ciphertext stealing
// decryption uses the last two tweaks in reverse order. We'll handle
// the last full block and the partial block specially at the end.
lea -16(LEN), %rax
test $15, LEN
jnz .Lneed_cts_dec\@
.Lxts_init\@:
cmovnz %rax, LEN
.endif
// Load the AES key length: 16 (AES-128), 24 (AES-192), or 32 (AES-256).
movl 480(KEY), KEYLEN
// Setup the pointer to the round keys and cache as many as possible.
_setup_round_keys \enc
@@ -661,11 +661,10 @@
RET
.Lhandle_remainder\@:
add $4*VL, LEN // Undo the extra sub from earlier.
// En/decrypt any remaining full blocks, one vector at a time.
.if VL > 16
sub $VL, LEN
add $3*VL, LEN // Undo extra sub of 4*VL, then sub VL.
jl .Lvec_at_a_time_done\@
.Lvec_at_a_time\@:
_vmovdqu (SRC), V0
@@ -677,9 +676,9 @@
sub $VL, LEN
jge .Lvec_at_a_time\@
.Lvec_at_a_time_done\@:
add $VL-16, LEN // Undo the extra sub from earlier.
add $VL-16, LEN // Undo extra sub of VL, then sub 16.
.else
sub $16, LEN
add $4*VL-16, LEN // Undo extra sub of 4*VL, then sub 16.
.endif
// En/decrypt any remaining full blocks, one at a time.
@@ -694,24 +693,12 @@
sub $16, LEN
jge .Lblock_at_a_time\@
.Lblock_at_a_time_done\@:
add $16, LEN // Undo the extra sub from earlier.
add $16, LEN // Undo the extra sub of 16.
// Now 0 <= LEN <= 15. If LEN is zero, we're done.
jz .Ldone\@
.Lfull_blocks_done\@:
// Now 0 <= LEN <= 15. If LEN is nonzero, do ciphertext stealing to
// process the last 16 + LEN bytes. If LEN is zero, we're done.
test LEN, LEN
jnz .Lcts\@
jmp .Ldone\@
.if !\enc
.Lneed_cts_dec\@:
sub $16, LEN
jmp .Lxts_init\@
.endif
.Lcts\@:
// Do ciphertext stealing (CTS) to en/decrypt the last full block and
// the partial block. TWEAK0_XMM contains the next tweak.
// Otherwise 1 <= LEN <= 15, but the real remaining length is 16 + LEN.
// Do ciphertext stealing to process the last 16 + LEN bytes.
.if \enc
// If encrypting, the main loop already encrypted the last full block to