staging: ccree: fix leak of import() after init()

crypto_ahash_import() may be called either after
crypto_ahash_init() or without such call. Right now
we always internally call init() as part of
import(), thus leaking memory and mappings if the
user has already called init() herself.

Fix this by only calling init() internally if the
state is not already initialized.

Fixes: commit 454527d0d94f ("staging: ccree: fix hash import/export")
Cc: stable <stable@vger.kernel.org>
Signed-off-by: Gilad Ben-Yossef <gilad@benyossef.com>
Reviewed-by: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

diff --git a/drivers/staging/ccree/ssi_hash.c b/drivers/staging/ccree/ssi_hash.c
index d79090ed7f9c71ee5bcbed31e27a05a5da47bb83..1799d3f26a9e29858e1a4362fe4fc491609750dd 100644 (file)
--- a/drivers/staging/ccree/ssi_hash.c
+++ b/drivers/staging/ccree/ssi_hash.c
@@ -1778,9 +1778,12 @@ static int ssi_ahash_import(struct ahash_request *req, const void *in)
        }
        in += sizeof(u32);
 
-       rc = ssi_hash_init(state, ctx);
-       if (rc)
-               goto out;
+       /* call init() to allocate bufs if the user hasn't */
+       if (!state->digest_buff) {
+               rc = ssi_hash_init(state, ctx);
+               if (rc)
+                       goto out;
+       }
 
        dma_sync_single_for_cpu(dev, state->digest_buff_dma_addr,
                                ctx->inter_digestsize, DMA_BIDIRECTIONAL);