From: Eric Biggers <ebiggers@xxxxxxxxxx> My patches to make testmgr fuzz algorithms against their generic implementation detected that the arm64 implementations of "cbcmac(aes)" handle empty messages differently from the cbcmac template. Namely, the arm64 implementations return the encrypted initial value, but the cbcmac template returns the initial value directly. This isn't actually a meaningful case because any user of cbcmac needs to prepend the message length, as CCM does; otherwise it's insecure. However, we should keep the behavior consistent; at the very least this makes testing easier. Do it the easy way, which is to change the arm64 implementations to have the same behavior as the cbcmac template. For what it's worth, ghash does things essentially the same way: it returns its initial value when given an empty message, even though in practice ghash is never passed an empty message. Signed-off-by: Eric Biggers <ebiggers@xxxxxxxxxx> --- arch/arm64/crypto/aes-glue.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm64/crypto/aes-glue.c b/arch/arm64/crypto/aes-glue.c index 692cb75f2ca2f..f0ceb545bd1ee 100644 --- a/arch/arm64/crypto/aes-glue.c +++ b/arch/arm64/crypto/aes-glue.c @@ -707,7 +707,7 @@ static int cbcmac_final(struct shash_desc *desc, u8 *out) struct mac_tfm_ctx *tctx = crypto_shash_ctx(desc->tfm); struct mac_desc_ctx *ctx = shash_desc_ctx(desc); - mac_do_update(&tctx->key, NULL, 0, ctx->dg, 1, 0); + mac_do_update(&tctx->key, NULL, 0, ctx->dg, (ctx->len != 0), 0); memcpy(out, ctx->dg, AES_BLOCK_SIZE); -- 2.21.0