Thread (74 messages) 74 messages, 7 authors, 2021-10-20

Re: [dpdk-dev] [PATCH v3 6/7] cryptodev: update fast path APIs to use new flat array

From: Ananyev, Konstantin <hidden>
Date: 2021-10-19 14:40:47


 
quoted
quoted
@@ -1832,13 +1832,18 @@ static inline uint16_t
 rte_cryptodev_dequeue_burst(uint8_t dev_id, uint16_t qp_id,
 		struct rte_crypto_op **ops, uint16_t nb_ops)
 {
-	struct rte_cryptodev *dev = &rte_cryptodevs[dev_id];
+	const struct rte_crypto_fp_ops *fp_ops;
+	void *qp;

 	rte_cryptodev_trace_dequeue_burst(dev_id, qp_id, (void **)ops,
nb_ops);
quoted
-	nb_ops = (*dev->dequeue_burst)
-			(dev->data->queue_pairs[qp_id], ops, nb_ops);
+
+	fp_ops = &rte_crypto_fp_ops[dev_id];
+	qp = fp_ops->qp.data[qp_id];
+
+	nb_ops = fp_ops->dequeue_burst(qp, ops, nb_ops);
+
 #ifdef RTE_CRYPTO_CALLBACKS
-	if (unlikely(dev->deq_cbs != NULL)) {
+	if (unlikely(fp_ops->qp.deq_cb != NULL)) {
 		struct rte_cryptodev_cb_rcu *list;
 		struct rte_cryptodev_cb *cb;
As I ca see you decided to keep call-back related data-structs as public API.
I wonder that's to avoid extra changes with CB related code?
Or performance reasons?
Or probably something else?
I just wanted to avoid extra changes and it did not look that important at this point
Compared to other patches.
I would have done the changes if I had some more time.
Understood, thanks for explanation.
Keyboard shortcuts
hback out one level
jnext message in thread
kprevious message in thread
ldrill in
Escclose help / fold thread tree
?toggle this help