diff mbox series

[7/7] crypto: x86/aes-xts - more code size optimizations

Message ID 20241210235834.40862-8-ebiggers@kernel.org
State Superseded
Headers show
Series crypto: x86 - minor optimizations and cleanup to VAES code | expand

Commit Message

Eric Biggers Dec. 10, 2024, 11:58 p.m. UTC 
From: Eric Biggers <ebiggers@google.com>

Prefer immediates of -128 to 128, since the former fits in a signed
byte, saving 3 bytes per instruction.  Also prefer VEX-coded
instructions to EVEX where this is easy to do.

Signed-off-by: Eric Biggers <ebiggers@google.com>
---
 arch/x86/crypto/aes-xts-avx-x86_64.S | 24 +++++++++++++-----------
 1 file changed, 13 insertions(+), 11 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 bb3d0dfeca575..a49637f0a729d 100644
--- a/arch/x86/crypto/aes-xts-avx-x86_64.S
+++ b/arch/x86/crypto/aes-xts-avx-x86_64.S
@@ -186,10 +186,11 @@ 
 .endif
 	// V30-V31 are currently unused.
 .endm
 
 // Move a vector between memory and a register.
+// The register operand must be in the first 16 vector registers.
 .macro	_vmovdqu	src, dst
 .if VL < 64
 	vmovdqu		\src, \dst
 .else
 	vmovdqu8	\src, \dst
@@ -206,15 +207,16 @@ 
 	vbroadcasti32x4	\src, \dst
 .endif
 .endm
 
 // XOR two vectors together.
+// Any register operands must be in the first 16 vector registers.
 .macro	_vpxor	src1, src2, dst
-.if USE_AVX10
-	vpxord		\src1, \src2, \dst
-.else
+.if VL < 64
 	vpxor		\src1, \src2, \dst
+.else
+	vpxord		\src1, \src2, \dst
 .endif
 .endm
 
 // XOR three vectors together.
 .macro	_xor3	src1, src2, src3_and_dst
@@ -559,22 +561,22 @@ 
 	_setup_round_keys	\enc
 
 	// Compute the first set of tweaks TWEAK[0-3].
 	_compute_first_set_of_tweaks
 
-	sub		$4*VL, LEN
+	add		$-4*VL, LEN  // shorter than 'sub 4*VL' when VL=32
 	jl		.Lhandle_remainder\@
 
 .Lmain_loop\@:
 	// This is the main loop, en/decrypting 4*VL bytes per iteration.
 
 	// XOR each source block with its tweak and the zero-th round key.
 .if USE_AVX10
-	vmovdqu8	0*VL(SRC), V0
-	vmovdqu8	1*VL(SRC), V1
-	vmovdqu8	2*VL(SRC), V2
-	vmovdqu8	3*VL(SRC), V3
+	_vmovdqu	0*VL(SRC), V0
+	_vmovdqu	1*VL(SRC), V1
+	_vmovdqu	2*VL(SRC), V2
+	_vmovdqu	3*VL(SRC), V3
 	vpternlogd	$0x96, TWEAK0, KEY0, V0
 	vpternlogd	$0x96, TWEAK1, KEY0, V1
 	vpternlogd	$0x96, TWEAK2, KEY0, V2
 	vpternlogd	$0x96, TWEAK3, KEY0, V3
 .else
@@ -616,13 +618,13 @@ 
 	_vmovdqu	V3, 3*VL(DST)
 
 	// Finish computing the next set of tweaks.
 	_tweak_step	1000
 
-	add		$4*VL, SRC
-	add		$4*VL, DST
-	sub		$4*VL, LEN
+	sub		$-4*VL, SRC  // shorter than 'add 4*VL' when VL=32
+	sub		$-4*VL, DST
+	add		$-4*VL, LEN
 	jge		.Lmain_loop\@
 
 	// Check for the uncommon case where the data length isn't a multiple of
 	// 4*VL.  Handle it out-of-line in order to optimize for the common
 	// case.  In the common case, just fall through to the ret.