[dpdk-dev] [DPDK] [PATCH 1/3] qat: remove atomics

[Anatoly Burakov <anatoly.burakov@intel.com>]

From: "Burakov, Anatoly" <anatoly.burakov@intel.com>

Replacing atomics in the qat driver with simple 16-bit integers for
number of inflight packets.

This adds a new limitation to the QAT driver: each queue pair is
now explicitly single-threaded.

Signed-off-by: Burakov, Anatoly <anatoly.burakov@intel.com>
---
 doc/guides/cryptodevs/qat.rst          |  1 +
 doc/guides/rel_notes/release_17_11.rst |  6 ++++++
 drivers/crypto/qat/qat_crypto.c        | 12 +++++-------
 drivers/crypto/qat/qat_crypto.h        |  2 +-
 drivers/crypto/qat/qat_qp.c            |  4 ++--
 5 files changed, 15 insertions(+), 10 deletions(-)

diff --git a/doc/guides/cryptodevs/qat.rst b/doc/guides/cryptodevs/qat.rst
index a3fce7b..cb17b6b 100644
--- a/doc/guides/cryptodevs/qat.rst
+++ b/doc/guides/cryptodevs/qat.rst
@@ -90,6 +90,7 @@ Limitations
 * No BSD support as BSD QAT kernel driver not available.
 * ZUC EEA3/EIA3 is not supported by dh895xcc devices
 * Maximum additional authenticated data (AAD) for GCM is 240 bytes long.
+* Queue pairs are not thread-safe (that is, within a single queue pair, RX and TX from different lcores is not supported).
 
 
 Installation
diff --git a/doc/guides/rel_notes/release_17_11.rst b/doc/guides/rel_notes/release_17_11.rst
index 170f4f9..67b6f68 100644
--- a/doc/guides/rel_notes/release_17_11.rst
+++ b/doc/guides/rel_notes/release_17_11.rst
@@ -41,6 +41,12 @@ New Features
      Also, make sure to start the actual text at the margin.
      =========================================================
 
+* **Updated qat crypto PMD.**
+
+  Performance enhancements:
+
+  * Removed atomics from the internal queue pair structure.
+
 
 Resolved Issues
 ---------------
diff --git a/drivers/crypto/qat/qat_crypto.c b/drivers/crypto/qat/qat_crypto.c
index 1f52cab..2ee5866 100644
--- a/drivers/crypto/qat/qat_crypto.c
+++ b/drivers/crypto/qat/qat_crypto.c
@@ -52,7 +52,6 @@
 #include <rte_eal.h>
 #include <rte_per_lcore.h>
 #include <rte_lcore.h>
-#include <rte_atomic.h>
 #include <rte_branch_prediction.h>
 #include <rte_mempool.h>
 #include <rte_mbuf.h>
@@ -946,10 +945,10 @@ qat_pmd_enqueue_op_burst(void *qp, struct rte_crypto_op **ops,
 	tail = queue->tail;
 
 	/* Find how many can actually fit on the ring */
-	overflow = rte_atomic16_add_return(&tmp_qp->inflights16, nb_ops)
-				- queue->max_inflights;
+	tmp_qp->inflights16 += nb_ops;
+	overflow = tmp_qp->inflights16 - queue->max_inflights;
 	if (overflow > 0) {
-		rte_atomic16_sub(&tmp_qp->inflights16, overflow);
+		tmp_qp->inflights16 -= overflow;
 		nb_ops_possible = nb_ops - overflow;
 		if (nb_ops_possible == 0)
 			return 0;
@@ -964,8 +963,7 @@ qat_pmd_enqueue_op_burst(void *qp, struct rte_crypto_op **ops,
 			 * This message cannot be enqueued,
 			 * decrease number of ops that wasn't sent
 			 */
-			rte_atomic16_sub(&tmp_qp->inflights16,
-					nb_ops_possible - nb_ops_sent);
+			tmp_qp->inflights16 -= nb_ops_possible - nb_ops_sent;
 			if (nb_ops_sent == 0)
 				return 0;
 			goto kick_tail;
@@ -1037,7 +1035,7 @@ qat_pmd_dequeue_op_burst(void *qp, struct rte_crypto_op **ops,
 		WRITE_CSR_RING_HEAD(tmp_qp->mmap_bar_addr,
 					queue->hw_bundle_number,
 					queue->hw_queue_number, queue->head);
-		rte_atomic16_sub(&tmp_qp->inflights16, msg_counter);
+		tmp_qp->inflights16 -= msg_counter;
 		tmp_qp->stats.dequeued_count += msg_counter;
 	}
 	return msg_counter;
diff --git a/drivers/crypto/qat/qat_crypto.h b/drivers/crypto/qat/qat_crypto.h
index 3f35a00..7773b57 100644
--- a/drivers/crypto/qat/qat_crypto.h
+++ b/drivers/crypto/qat/qat_crypto.h
@@ -77,7 +77,7 @@ struct qat_queue {
 
 struct qat_qp {
 	void			*mmap_bar_addr;
-	rte_atomic16_t		inflights16;
+	uint16_t		inflights16;
 	struct	qat_queue	tx_q;
 	struct	qat_queue	rx_q;
 	struct	rte_cryptodev_stats stats;
diff --git a/drivers/crypto/qat/qat_qp.c b/drivers/crypto/qat/qat_qp.c
index 5048d21..e98bffe 100644
--- a/drivers/crypto/qat/qat_qp.c
+++ b/drivers/crypto/qat/qat_qp.c
@@ -186,7 +186,7 @@ int qat_crypto_sym_qp_setup(struct rte_cryptodev *dev, uint16_t queue_pair_id,
 			RTE_CACHE_LINE_SIZE);
 
 	qp->mmap_bar_addr = pci_dev->mem_resource[0].addr;
-	rte_atomic16_init(&qp->inflights16);
+	qp->inflights16 = 0;
 
 	if (qat_tx_queue_create(dev, &(qp->tx_q),
 		queue_pair_id, qp_conf->nb_descriptors, socket_id) != 0) {
@@ -269,7 +269,7 @@ int qat_crypto_sym_qp_release(struct rte_cryptodev *dev, uint16_t queue_pair_id)
 	}
 
 	/* Don't free memory if there are still responses to be processed */
-	if (rte_atomic16_read(&(qp->inflights16)) == 0) {
+	if (qp->inflights16 == 0) {
 		qat_queue_delete(&(qp->tx_q));
 		qat_queue_delete(&(qp->rx_q));
 	} else {
-- 
2.7.4