[dpdk-dev] [PATCH v3] net/af_xdp: support need wakeup feature

[Xiaolong Ye <xiaolong.ye@intel.com>]

This patch enables need_wakeup flag for Tx and fill rings, when this flag
is set by the driver, it means that the userspace application has to
explicitly wake up the kernel Rx or kernel Tx processing by issuing a
syscall. Poll() can wake up both and sendto() or its alternatives will wake
up Tx processing only.

This feature is to provide efficient support for case that application and
driver executing on the same core.

Signed-off-by: Xiaolong Ye <xiaolong.ye@intel.com>
---
v3 changes:

1. add introduction in 19.08 release note

v2 changes:

1. remove need_wakeup devarg to make need_wakeup feature enabled
   unconditionally.
2. add conditional compilation directive to avoid breaking build with
   kernel which doesn't support need_wakeup feature yet.

Note:

Original busy poll feature has morphed into need_wakeup flag in
kernel side, the main purpose is the same, that is to support both
application and driver executing on the same core efficiently.
 doc/guides/rel_notes/release_19_08.rst |  2 ++
 drivers/net/af_xdp/rte_eth_af_xdp.c    | 41 +++++++++++++++++++-------
 2 files changed, 32 insertions(+), 11 deletions(-)

diff --git a/doc/guides/rel_notes/release_19_08.rst b/doc/guides/rel_notes/release_19_08.rst
index 8c3932d06..49656c3cc 100644
--- a/doc/guides/rel_notes/release_19_08.rst
+++ b/doc/guides/rel_notes/release_19_08.rst
@@ -87,6 +87,8 @@ New Features
     high performance
   * Added multi-queue support to allow one af_xdp vdev with multiple netdev
     queues
+  * Enabled need_wakeup feature which can provide efficient support for case
+    that application and driver executing on the same core.
 
 
 Removed Items
diff --git a/drivers/net/af_xdp/rte_eth_af_xdp.c b/drivers/net/af_xdp/rte_eth_af_xdp.c
index c638d9227..5ce90a760 100644
--- a/drivers/net/af_xdp/rte_eth_af_xdp.c
+++ b/drivers/net/af_xdp/rte_eth_af_xdp.c
@@ -5,6 +5,7 @@
 #include <errno.h>
 #include <stdlib.h>
 #include <string.h>
+#include <poll.h>
 #include <netinet/in.h>
 #include <net/if.h>
 #include <sys/socket.h>
@@ -90,6 +91,7 @@ struct pkt_rx_queue {
 	struct rx_stats stats;
 
 	struct pkt_tx_queue *pair;
+	struct pollfd fds[1];
 	int xsk_queue_idx;
 };
 
@@ -206,8 +208,14 @@ eth_af_xdp_rx(void *queue, struct rte_mbuf **bufs, uint16_t nb_pkts)
 		return 0;
 
 	rcvd = xsk_ring_cons__peek(rx, nb_pkts, &idx_rx);
-	if (rcvd == 0)
+	if (rcvd == 0) {
+#if defined(XDP_USE_NEED_WAKEUP)
+		if (xsk_ring_prod__needs_wakeup(fq))
+			(void)poll(rxq->fds, 1, 1000);
+#endif
+
 		goto out;
+	}
 
 	if (xsk_prod_nb_free(fq, free_thresh) >= free_thresh)
 		(void)reserve_fill_queue(umem, ETH_AF_XDP_RX_BATCH_SIZE);
@@ -279,16 +287,19 @@ kick_tx(struct pkt_tx_queue *txq)
 {
 	struct xsk_umem_info *umem = txq->pair->umem;
 
-	while (send(xsk_socket__fd(txq->pair->xsk), NULL,
-		      0, MSG_DONTWAIT) < 0) {
-		/* some thing unexpected */
-		if (errno != EBUSY && errno != EAGAIN && errno != EINTR)
-			break;
-
-		/* pull from completion queue to leave more space */
-		if (errno == EAGAIN)
-			pull_umem_cq(umem, ETH_AF_XDP_TX_BATCH_SIZE);
-	}
+#if defined(XDP_USE_NEED_WAKEUP)
+	if (xsk_ring_prod__needs_wakeup(&txq->tx))
+#endif
+		while (send(xsk_socket__fd(txq->pair->xsk), NULL,
+			    0, MSG_DONTWAIT) < 0) {
+			/* some thing unexpected */
+			if (errno != EBUSY && errno != EAGAIN && errno != EINTR)
+				break;
+
+			/* pull from completion queue to leave more space */
+			if (errno == EAGAIN)
+				pull_umem_cq(umem, ETH_AF_XDP_TX_BATCH_SIZE);
+		}
 	pull_umem_cq(umem, ETH_AF_XDP_TX_BATCH_SIZE);
 }
 
@@ -622,6 +633,11 @@ xsk_configure(struct pmd_internals *internals, struct pkt_rx_queue *rxq,
 	cfg.libbpf_flags = 0;
 	cfg.xdp_flags = XDP_FLAGS_UPDATE_IF_NOEXIST;
 	cfg.bind_flags = 0;
+
+#if defined(XDP_USE_NEED_WAKEUP)
+	cfg.bind_flags |= XDP_USE_NEED_WAKEUP;
+#endif
+
 	ret = xsk_socket__create(&rxq->xsk, internals->if_name,
 			rxq->xsk_queue_idx, rxq->umem->umem, &rxq->rx,
 			&txq->tx, &cfg);
@@ -683,6 +699,9 @@ eth_rx_queue_setup(struct rte_eth_dev *dev,
 		goto err;
 	}
 
+	rxq->fds[0].fd = xsk_socket__fd(rxq->xsk);
+	rxq->fds[0].events = POLLIN;
+
 	rxq->umem->pmd_zc = internals->pmd_zc;
 
 	dev->data->rx_queues[rx_queue_id] = rxq;
-- 
2.17.1