Replace the vector load from memory sequence with a simple instruction
sequence to compose the tweak vector directly.
Signed-off-by: Ard Biesheuvel <ard.biesheuvel@xxxxxxxxxx>
---
arch/arm64/crypto/aes-neonbs-core.S | 9 +++------
1 file changed, 3 insertions(+), 6 deletions(-)
diff --git a/arch/arm64/crypto/aes-neonbs-core.S b/arch/arm64/crypto/aes-neonbs-core.S
index cf10ff8878a3..65982039fa36 100644
--- a/arch/arm64/crypto/aes-neonbs-core.S
+++ b/arch/arm64/crypto/aes-neonbs-core.S
@@ -730,11 +730,6 @@ ENDPROC(aesbs_cbc_decrypt)
eor \out\().16b, \out\().16b, \tmp\().16b
.endm
- .align 4
-.Lxts_mul_x:
-CPU_LE( .quad 1, 0x87 )
-CPU_BE( .quad 0x87, 1 )
-
/*
* aesbs_xts_encrypt(u8 out[], u8 const in[], u8 const rk[], int rounds,
* int blocks, u8 iv[])
@@ -806,7 +801,9 @@ ENDPROC(__xts_crypt8)
mov x23, x4
mov x24, x5
-0: ldr q30, .Lxts_mul_x
+0: movi v30.2s, #0x1
+ movi v25.2s, #0x87
+ uzp1 v30.4s, v30.4s, v25.4s
ld1 {v25.16b}, [x24]
99: adr x7, \do8
--
2.17.1
