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>

diff --git a/drivers/crypto/aesni_mb/rte_aesni_mb_pmd.c b/drivers/crypto/aesni_mb/rte_aesni_mb_pmd.c
index 3aaa070..13cffaf 100644 (file)
--- a/drivers/crypto/aesni_mb/rte_aesni_mb_pmd.c
+++ b/drivers/crypto/aesni_mb/rte_aesni_mb_pmd.c
@@ -587,7 +587,7 @@ handle_completed_jobs(struct aesni_mb_qp *qp, JOB_AES_HMAC *job,
        struct rte_crypto_op *op = NULL;
        unsigned processed_jobs = 0;
 
-       while (job != NULL && processed_jobs < nb_ops) {
+       while (job != NULL) {
                op = post_process_mb_job(qp, job);
 
                if (op) {
@@ -597,6 +597,8 @@ handle_completed_jobs(struct aesni_mb_qp *qp, JOB_AES_HMAC *job,
                        qp->stats.dequeue_err_count++;
                        break;
                }
+               if (processed_jobs == nb_ops)
+                       break;
 
                job = (*qp->op_fns->job.get_completed_job)(&qp->mb_mgr);
        }