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/arm/crypto/aes-neonbs-core.S | 8 +++-----
1 file changed, 3 insertions(+), 5 deletions(-)
diff --git a/arch/arm/crypto/aes-neonbs-core.S b/arch/arm/crypto/aes-neonbs-core.S
index d3eab76b6e1b..bb75918e4984 100644
--- a/arch/arm/crypto/aes-neonbs-core.S
+++ b/arch/arm/crypto/aes-neonbs-core.S
@@ -887,10 +887,6 @@ ENDPROC(aesbs_ctr_encrypt)
veor \out, \out, \tmp
.endm
- .align 4
-.Lxts_mul_x:
- .quad 1, 0x87
-
/*
* aesbs_xts_encrypt(u8 out[], u8 const in[], u8 const rk[], int rounds,
* int blocks, u8 iv[])
@@ -899,7 +895,9 @@ ENDPROC(aesbs_ctr_encrypt)
*/
__xts_prepare8:
vld1.8 {q14}, [r7] // load iv
- __ldr q15, .Lxts_mul_x // load tweak mask
+ vmov.i32 d30, #0x87 // compose tweak mask vector
+ vmovl.u32 q15, d30
+ vshr.u64 d30, d31, #7
vmov q12, q14
__adr ip, 0f
--
2.17.1
