From f3456b9fd269c6d0c973b136c5449d46b2510f4b Mon Sep 17 00:00:00 2001 From: Ard Biesheuvel Date: Thu, 26 Nov 2020 08:49:07 +0100 Subject: [PATCH] crypto: arm/aes-ce - work around Cortex-A57/A72 silion errata ARM Cortex-A57 and Cortex-A72 cores running in 32-bit mode are affected by silicon errata #1742098 and #1655431, respectively, where the second instruction of a AES instruction pair may execute twice if an interrupt is taken right after the first instruction consumes an input register of which a single 32-bit lane has been updated the last time it was modified. This is not such a rare occurrence as it may seem: in counter mode, only the least significant 32-bit word is incremented in the absence of a carry, which makes our counter mode implementation susceptible to these errata. So let's shuffle the counter assignments around a bit so that the most recent updates when the AES instruction pair executes are 128-bit wide. [0] ARM-EPM-049219 v23 Cortex-A57 MPCore Software Developers Errata Notice [1] ARM-EPM-012079 v11.0 Cortex-A72 MPCore Software Developers Errata Notice Cc: # v5.4+ Signed-off-by: Ard Biesheuvel Signed-off-by: Herbert Xu --- arch/arm/crypto/aes-ce-core.S | 32 ++++++++++++++++++++++---------- 1 file 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]!