Message ID | 1510218980-3549-2-git-send-email-gilad@benyossef.com |
---|---|
State | Accepted |
Commit | c5f39d07860c35e5e4c63188139465af790f86ce |
Headers | show |
Series | [v2,01/10] staging: ccree: fix leak of import() after init() | expand |
diff --git a/drivers/staging/ccree/ssi_hash.c b/drivers/staging/ccree/ssi_hash.c index d79090e..1799d3f 100644 --- 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);
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> --- drivers/staging/ccree/ssi_hash.c | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) -- 2.7.4