@@ -215,14 +215,15 @@ static int ctr_encrypt(struct skcipher_request *req)
u8 *tsrc = walk.src.virt.addr;
/*
- * Minimum alignment is 8 bytes, so if nbytes is <= 8, we need
- * to tell aes_ctr_encrypt() to only read half a block.
+ * Tell aes_ctr_encrypt() to process a tail block.
*/
- blocks = (nbytes <= 8) ? -1 : 1;
+ blocks = -1;
- aes_ctr_encrypt(tail, tsrc, (u8 *)ctx->key_enc, rounds,
+ aes_ctr_encrypt(tail, NULL, (u8 *)ctx->key_enc, rounds,
blocks, walk.iv, first);
- memcpy(tdst, tail, nbytes);
+ if (tdst != tsrc)
+ memcpy(tdst, tsrc, nbytes);
+ crypto_xor(tdst, tail, nbytes);
err = skcipher_walk_done(&walk, 0);
}
kernel_neon_end();
@@ -282,7 +283,6 @@ static struct skcipher_alg aes_algs[] = { {
.cra_flags = CRYPTO_ALG_INTERNAL,
.cra_blocksize = AES_BLOCK_SIZE,
.cra_ctxsize = sizeof(struct crypto_aes_ctx),
- .cra_alignmask = 7,
.cra_module = THIS_MODULE,
},
.min_keysize = AES_MIN_KEY_SIZE,
@@ -298,7 +298,6 @@ static struct skcipher_alg aes_algs[] = { {
.cra_flags = CRYPTO_ALG_INTERNAL,
.cra_blocksize = AES_BLOCK_SIZE,
.cra_ctxsize = sizeof(struct crypto_aes_ctx),
- .cra_alignmask = 7,
.cra_module = THIS_MODULE,
},
.min_keysize = AES_MIN_KEY_SIZE,
@@ -315,7 +314,6 @@ static struct skcipher_alg aes_algs[] = { {
.cra_flags = CRYPTO_ALG_INTERNAL,
.cra_blocksize = 1,
.cra_ctxsize = sizeof(struct crypto_aes_ctx),
- .cra_alignmask = 7,
.cra_module = THIS_MODULE,
},
.min_keysize = AES_MIN_KEY_SIZE,
@@ -332,7 +330,6 @@ static struct skcipher_alg aes_algs[] = { {
.cra_priority = PRIO - 1,
.cra_blocksize = 1,
.cra_ctxsize = sizeof(struct crypto_aes_ctx),
- .cra_alignmask = 7,
.cra_module = THIS_MODULE,
},
.min_keysize = AES_MIN_KEY_SIZE,
@@ -350,7 +347,6 @@ static struct skcipher_alg aes_algs[] = { {
.cra_flags = CRYPTO_ALG_INTERNAL,
.cra_blocksize = AES_BLOCK_SIZE,
.cra_ctxsize = sizeof(struct crypto_aes_xts_ctx),
- .cra_alignmask = 7,
.cra_module = THIS_MODULE,
},
.min_keysize = 2 * AES_MIN_KEY_SIZE,
@@ -337,7 +337,7 @@ AES_ENTRY(aes_ctr_encrypt)
.Lctrcarrydone:
subs w4, w4, #1
- bmi .Lctrhalfblock /* blocks < 0 means 1/2 block */
+ bmi .Lctrtailblock /* blocks <0 means tail block */
ld1 {v3.16b}, [x1], #16
eor v3.16b, v0.16b, v3.16b
st1 {v3.16b}, [x0], #16
@@ -348,10 +348,8 @@ AES_ENTRY(aes_ctr_encrypt)
FRAME_POP
ret
-.Lctrhalfblock:
- ld1 {v3.8b}, [x1]
- eor v3.8b, v0.8b, v3.8b
- st1 {v3.8b}, [x0]
+.Lctrtailblock:
+ st1 {v0.16b}, [x0]
FRAME_POP
ret
Remove the unnecessary alignmask: it is much more efficient to deal with the misalignment in the core algorithm than relying on the crypto API to copy the data to a suitably aligned buffer. Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org> --- NOTE: this won't apply unless 'crypto: arm64/aes-blk - honour iv_out requirement in CBC and CTR modes' is applied first, which was sent out separately as a bugfix for v3.16 - v4.9 arch/arm64/crypto/aes-glue.c | 16 ++++++---------- arch/arm64/crypto/aes-modes.S | 8 +++----- 2 files changed, 9 insertions(+), 15 deletions(-) -- 2.7.4 -- To unsubscribe from this list: send the line "unsubscribe linux-crypto" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html