diff options
Diffstat (limited to 'arch/arm/crypto/aes-ce-core.S')
| -rw-r--r-- | arch/arm/crypto/aes-ce-core.S | 32 |
1 files changed, 22 insertions, 10 deletions
diff --git a/arch/arm/crypto/aes-ce-core.S b/arch/arm/crypto/aes-ce-core.S index 4d1707388d94..312428d83eed 100644 --- a/arch/arm/crypto/aes-ce-core.S +++ b/arch/arm/crypto/aes-ce-core.S @@ -386,20 +386,32 @@ ENTRY(ce_aes_ctr_encrypt) .Lctrloop4x: subs r4, r4, #4 bmi .Lctr1x - add r6, r6, #1 + + /* + * NOTE: the sequence below has been carefully tweaked to avoid + * a silicon erratum that exists in Cortex-A57 (#1742098) and + * Cortex-A72 (#1655431) cores, where AESE/AESMC instruction pairs + * may produce an incorrect result if they take their input from a + * register of which a single 32-bit lane has been updated the last + * time it was modified. To work around this, the lanes of registers + * q0-q3 below are not manipulated individually, and the different + * counter values are prepared by successive manipulations of q7. + */ + add ip, r6, #1 vmov q0, q7 + rev ip, ip + add lr, r6, #2 + vmov s31, ip @ set lane 3 of q1 via q7 + add ip, r6, #3 + rev lr, lr vmov q1, q7 - rev ip, r6 - add r6, r6, #1 + vmov s31, lr @ set lane 3 of q2 via q7 + rev ip, ip vmov q2, q7 - vmov s7, ip - rev ip, r6 - add r6, r6, #1 + vmov s31, ip @ set lane 3 of q3 via q7 + add r6, r6, #4 vmov q3, q7 - vmov s11, ip - rev ip, r6 - add r6, r6, #1 - vmov s15, ip + vld1.8 {q4-q5}, [r1]! vld1.8 {q6}, [r1]! vld1.8 {q15}, [r1]! |