diff mbox series

[v2,3/8] crypto: x86/aes-xts - use .irp when useful

Message ID 20241212212845.40333-4-ebiggers@kernel.org
State New
Headers show
Series crypto: x86 - minor optimizations and cleanup to VAES code | expand

Commit Message

Eric Biggers Dec. 12, 2024, 9:28 p.m. UTC 
From: Eric Biggers <ebiggers@google.com>

Use .irp instead of repeating code.

No change in the generated code.

Signed-off-by: Eric Biggers <ebiggers@google.com>
---
 arch/x86/crypto/aes-xts-avx-x86_64.S | 74 ++++++----------------------
 1 file changed, 15 insertions(+), 59 deletions(-)
diff mbox series

Patch

diff --git a/arch/x86/crypto/aes-xts-avx-x86_64.S b/arch/x86/crypto/aes-xts-avx-x86_64.S
index 48f97b79f7a9..580e73396052 100644
--- a/arch/x86/crypto/aes-xts-avx-x86_64.S
+++ b/arch/x86/crypto/aes-xts-avx-x86_64.S
@@ -110,43 +110,17 @@ 
 
 .macro _define_aliases
 	// Define register aliases V0-V15, or V0-V31 if all 32 SIMD registers
 	// are available, that map to the xmm, ymm, or zmm registers according
 	// to the selected Vector Length (VL).
-	_define_Vi	0
-	_define_Vi	1
-	_define_Vi	2
-	_define_Vi	3
-	_define_Vi	4
-	_define_Vi	5
-	_define_Vi	6
-	_define_Vi	7
-	_define_Vi	8
-	_define_Vi	9
-	_define_Vi	10
-	_define_Vi	11
-	_define_Vi	12
-	_define_Vi	13
-	_define_Vi	14
-	_define_Vi	15
+.irp i, 0,1,2,3,4,5,6,7,8,9,10,11,12,13,14,15
+	_define_Vi	\i
+.endr
 .if USE_AVX10
-	_define_Vi	16
-	_define_Vi	17
-	_define_Vi	18
-	_define_Vi	19
-	_define_Vi	20
-	_define_Vi	21
-	_define_Vi	22
-	_define_Vi	23
-	_define_Vi	24
-	_define_Vi	25
-	_define_Vi	26
-	_define_Vi	27
-	_define_Vi	28
-	_define_Vi	29
-	_define_Vi	30
-	_define_Vi	31
+.irp i, 16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31
+	_define_Vi	\i
+.endr
 .endif
 
 	// V0-V3 hold the data blocks during the main loop, or temporary values
 	// otherwise.  V4-V5 hold temporary values.
 
@@ -543,19 +517,13 @@ 
 	_vaes_1x	\enc, 0, 2, \xmm_suffix, \data
 .Laes192\@:
 	_vaes_1x	\enc, 0, 3, \xmm_suffix, \data
 	_vaes_1x	\enc, 0, 4, \xmm_suffix, \data
 .Laes128\@:
-	_vaes_1x	\enc, 0, 5, \xmm_suffix, \data
-	_vaes_1x	\enc, 0, 6, \xmm_suffix, \data
-	_vaes_1x	\enc, 0, 7, \xmm_suffix, \data
-	_vaes_1x	\enc, 0, 8, \xmm_suffix, \data
-	_vaes_1x	\enc, 0, 9, \xmm_suffix, \data
-	_vaes_1x	\enc, 0, 10, \xmm_suffix, \data
-	_vaes_1x	\enc, 0, 11, \xmm_suffix, \data
-	_vaes_1x	\enc, 0, 12, \xmm_suffix, \data
-	_vaes_1x	\enc, 0, 13, \xmm_suffix, \data
+.irp i, 5,6,7,8,9,10,11,12,13
+	_vaes_1x	\enc, 0, \i, \xmm_suffix, \data
+.endr
 	_vaes_1x	\enc, 1, 14, \xmm_suffix, \data
 	_vpxor		\tweak, \data, \data
 .endm
 
 .macro	_aes_xts_crypt	enc
@@ -616,19 +584,13 @@ 
 	_vaes_4x	\enc, 0, 2
 .Laes192\@:
 	_vaes_4x	\enc, 0, 3
 	_vaes_4x	\enc, 0, 4
 .Laes128\@:
-	_vaes_4x	\enc, 0, 5
-	_vaes_4x	\enc, 0, 6
-	_vaes_4x	\enc, 0, 7
-	_vaes_4x	\enc, 0, 8
-	_vaes_4x	\enc, 0, 9
-	_vaes_4x	\enc, 0, 10
-	_vaes_4x	\enc, 0, 11
-	_vaes_4x	\enc, 0, 12
-	_vaes_4x	\enc, 0, 13
+.irp i, 5,6,7,8,9,10,11,12,13
+	_vaes_4x	\enc, 0, \i
+.endr
 	_vaes_4x	\enc, 1, 14
 
 	// XOR in the tweaks again.
 	_vpxor		TWEAK0, V0, V0
 	_vpxor		TWEAK1, V1, V1
@@ -777,19 +739,13 @@  SYM_TYPED_FUNC_START(aes_xts_encrypt_iv)
 	vaesenc		-5*16(%rdi), %xmm0, %xmm0
 .Lencrypt_iv_aes192:
 	vaesenc		-4*16(%rdi), %xmm0, %xmm0
 	vaesenc		-3*16(%rdi), %xmm0, %xmm0
 .Lencrypt_iv_aes128:
-	vaesenc		-2*16(%rdi), %xmm0, %xmm0
-	vaesenc		-1*16(%rdi), %xmm0, %xmm0
-	vaesenc		0*16(%rdi), %xmm0, %xmm0
-	vaesenc		1*16(%rdi), %xmm0, %xmm0
-	vaesenc		2*16(%rdi), %xmm0, %xmm0
-	vaesenc		3*16(%rdi), %xmm0, %xmm0
-	vaesenc		4*16(%rdi), %xmm0, %xmm0
-	vaesenc		5*16(%rdi), %xmm0, %xmm0
-	vaesenc		6*16(%rdi), %xmm0, %xmm0
+.irp i, -2,-1,0,1,2,3,4,5,6
+	vaesenc		\i*16(%rdi), %xmm0, %xmm0
+.endr
 	vaesenclast	7*16(%rdi), %xmm0, %xmm0
 	vmovdqu		%xmm0, (%rsi)
 	RET
 SYM_FUNC_END(aes_xts_encrypt_iv)