crypto/aesni_mb: fix possible crypto job leak
authorPablo de Lara <pablo.de.lara.guarch@intel.com>
Thu, 13 Jul 2017 03:35:12 +0000 (04:35 +0100)
committerPablo de Lara <pablo.de.lara.guarch@intel.com>
Wed, 19 Jul 2017 11:10:41 +0000 (14:10 +0300)
commit7c95d47c1ead28b7ffa0fc77e33d76b014c9511e
treecc48d921f96cf11554af38c303c0141ed97af907
parent8dfb8d05f11405f339b5db5c8eac3153ae5efb1b
crypto/aesni_mb: fix possible crypto job leak

When dequeueing operations from an AESNI-MB device,
crypto jobs are dequeued from the internal scheduler
in the Multi-buffer library.

If the number of jobs available to retrieve
are higher than the number of crypto operations
that are required, then an extra job is retrieved
(due to an incorrect conditional), but not used.
This leads to a job leak and the operation associated
to that job will not be ever dequeued.

Fixes: 0f548b50a160 ("crypto/aesni_mb: process crypto op on dequeue")
Cc: stable@dpdk.org
Signed-off-by: Pablo de Lara <pablo.de.lara.guarch@intel.com>
Acked-by: Declan Doherty <declan.doherty@intel.com>
drivers/crypto/aesni_mb/rte_aesni_mb_pmd.c