[PATCH 4.14 68/75] staging: ccree: fix leak of import() after init()

[Greg Kroah-Hartman]

4.14-stable review patch.  If anyone has any objections, please let me know.

------------------

From: Gilad Ben-Yossef <gilad@xxxxxxxxxxxxx>

commit c5f39d07860c35e5e4c63188139465af790f86ce upstream.

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")
Signed-off-by: Gilad Ben-Yossef <gilad@xxxxxxxxxxxxx>
Reviewed-by: Dan Carpenter <dan.carpenter@xxxxxxxxxx>
Signed-off-by: Greg Kroah-Hartman <gregkh@xxxxxxxxxxxxxxxxxxx>

---
 drivers/staging/ccree/ssi_hash.c |    9 ++++++---
 1 file changed, 6 insertions(+), 3 deletions(-)

--- a/drivers/staging/ccree/ssi_hash.c
+++ b/drivers/staging/ccree/ssi_hash.c
@@ -1790,9 +1790,12 @@ static int ssi_ahash_import(struct ahash
 	}
 	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);