DPDK patches and discussions
 help / color / mirror / Atom feed
From: Xiaolong Ye <xiaolong.ye@intel.com>
To: Xiaolong Ye <xiaolong.ye@intel.com>, Qi Zhang <qi.z.zhang@intel.com>
Cc: Karlsson Magnus <magnus.karlsson@intel.com>,
	Topel Bjorn <bjorn.topel@intel.com>,
	yuan.peng@intel.com, dev@dpdk.org
Subject: [dpdk-dev] [PATCH v1] net/af_xdp: support need wakeup feature
Date: Mon, 17 Jun 2019 22:23:03 +0800	[thread overview]
Message-ID: <20190617142303.85240-1-xiaolong.ye@intel.com> (raw)

This patch adds a new devarg to support the 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 are executing on the same core.

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

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.

kernel side patchset can be found at netdev mailing list.
https://lore.kernel.org/netdev/CAJ8uoz2szX=+JXXAMyuVmvSsMXZuDqp6a8rjDQpTioxbZwxFmQ@mail.gmail.com/T/#t

It is targeted for v5.3

 drivers/net/af_xdp/rte_eth_af_xdp.c | 51 ++++++++++++++++++++---------
 1 file changed, 36 insertions(+), 15 deletions(-)

diff --git a/drivers/net/af_xdp/rte_eth_af_xdp.c b/drivers/net/af_xdp/rte_eth_af_xdp.c
index c638d9227..198b00147 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;
 };
 
@@ -117,6 +119,7 @@ struct pmd_internals {
 	int combined_queue_cnt;
 
 	int pmd_zc;
+	int need_wakeup;
 	struct rte_ether_addr eth_addr;
 
 	struct pkt_rx_queue *rx_queues;
@@ -127,12 +130,14 @@ struct pmd_internals {
 #define ETH_AF_XDP_START_QUEUE_ARG		"start_queue"
 #define ETH_AF_XDP_QUEUE_COUNT_ARG		"queue_count"
 #define ETH_AF_XDP_PMD_ZC_ARG			"pmd_zero_copy"
+#define ETH_AF_XDP_NEED_WAKEUP_ARG		"need_wakeup"
 
 static const char * const valid_arguments[] = {
 	ETH_AF_XDP_IFACE_ARG,
 	ETH_AF_XDP_START_QUEUE_ARG,
 	ETH_AF_XDP_QUEUE_COUNT_ARG,
 	ETH_AF_XDP_PMD_ZC_ARG,
+	ETH_AF_XDP_NEED_WAKEUP_ARG,
 	NULL
 };
 
@@ -206,8 +211,12 @@ 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 (xsk_ring_prod__needs_wakeup(fq))
+			(void)poll(rxq->fds, 1, 1000);
+
 		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 +288,17 @@ 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;
+	if (xsk_ring_prod__needs_wakeup(&txq->tx))
+		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 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);
 }
 
@@ -621,7 +631,7 @@ xsk_configure(struct pmd_internals *internals, struct pkt_rx_queue *rxq,
 	cfg.tx_size = ring_size;
 	cfg.libbpf_flags = 0;
 	cfg.xdp_flags = XDP_FLAGS_UPDATE_IF_NOEXIST;
-	cfg.bind_flags = 0;
+	cfg.bind_flags = internals->need_wakeup ? XDP_USE_NEED_WAKEUP : 0;
 	ret = xsk_socket__create(&rxq->xsk, internals->if_name,
 			rxq->xsk_queue_idx, rxq->umem->umem, &rxq->rx,
 			&txq->tx, &cfg);
@@ -683,6 +693,9 @@ 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;
@@ -856,7 +869,7 @@ xdp_get_channels_info(const char *if_name, int *max_queues,
 
 static int
 parse_parameters(struct rte_kvargs *kvlist, char *if_name, int *start_queue,
-			int *queue_cnt, int *pmd_zc)
+		 int *queue_cnt, int *pmd_zc, int *need_wakeup)
 {
 	int ret;
 
@@ -882,6 +895,9 @@ parse_parameters(struct rte_kvargs *kvlist, char *if_name, int *start_queue,
 	if (ret < 0)
 		goto free_kvlist;
 
+	ret = rte_kvargs_process(kvlist, ETH_AF_XDP_NEED_WAKEUP_ARG,
+				 &parse_integer_arg, need_wakeup);
+
 free_kvlist:
 	rte_kvargs_free(kvlist);
 	return ret;
@@ -919,7 +935,7 @@ get_iface_info(const char *if_name,
 
 static struct rte_eth_dev *
 init_internals(struct rte_vdev_device *dev, const char *if_name,
-			int start_queue_idx, int queue_cnt, int pmd_zc)
+	       int start_queue_idx, int queue_cnt, int pmd_zc, int need_wakeup)
 {
 	const char *name = rte_vdev_device_name(dev);
 	const unsigned int numa_node = dev->device.numa_node;
@@ -935,6 +951,7 @@ init_internals(struct rte_vdev_device *dev, const char *if_name,
 	internals->start_queue_idx = start_queue_idx;
 	internals->queue_cnt = queue_cnt;
 	internals->pmd_zc = pmd_zc;
+	internals->need_wakeup = !!need_wakeup;
 	strlcpy(internals->if_name, if_name, IFNAMSIZ);
 
 	if (xdp_get_channels_info(if_name, &internals->max_queue_cnt,
@@ -993,6 +1010,9 @@ init_internals(struct rte_vdev_device *dev, const char *if_name,
 	if (internals->pmd_zc)
 		AF_XDP_LOG(INFO, "Zero copy between umem and mbuf enabled.\n");
 
+	if (internals->need_wakeup)
+		AF_XDP_LOG(INFO, "need_wakeup feature is explicitly turned on.\n");
+
 	return eth_dev;
 
 err_free_tx:
@@ -1014,6 +1034,7 @@ rte_pmd_af_xdp_probe(struct rte_vdev_device *dev)
 	struct rte_eth_dev *eth_dev = NULL;
 	const char *name;
 	int pmd_zc = 0;
+	int need_wakeup = 0;
 
 	AF_XDP_LOG(INFO, "Initializing pmd_af_xdp for %s\n",
 		rte_vdev_device_name(dev));
@@ -1041,7 +1062,7 @@ rte_pmd_af_xdp_probe(struct rte_vdev_device *dev)
 		dev->device.numa_node = rte_socket_id();
 
 	if (parse_parameters(kvlist, if_name, &xsk_start_queue_idx,
-			     &xsk_queue_cnt, &pmd_zc) < 0) {
+			     &xsk_queue_cnt, &pmd_zc, &need_wakeup) < 0) {
 		AF_XDP_LOG(ERR, "Invalid kvargs value\n");
 		return -EINVAL;
 	}
@@ -1052,7 +1073,7 @@ rte_pmd_af_xdp_probe(struct rte_vdev_device *dev)
 	}
 
 	eth_dev = init_internals(dev, if_name, xsk_start_queue_idx,
-					xsk_queue_cnt, pmd_zc);
+				 xsk_queue_cnt, pmd_zc, need_wakeup);
 	if (eth_dev == NULL) {
 		AF_XDP_LOG(ERR, "Failed to init internals\n");
 		return -1;
-- 
2.17.1


             reply	other threads:[~2019-06-17  7:41 UTC|newest]

Thread overview: 12+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2019-06-17 14:23 Xiaolong Ye [this message]
2019-06-17  8:03 ` David Marchand
2019-06-17 15:27   ` Ye Xiaolong
2019-06-17  8:51     ` David Marchand
2019-06-17 10:05       ` Bruce Richardson
2019-06-17 15:39       ` Ye Xiaolong
2019-06-18  8:51 ` [dpdk-dev] [PATCH v2] " Xiaolong Ye
2019-06-21 13:19 ` [dpdk-dev] [PATCH v3] " Xiaolong Ye
2019-06-27 18:22   ` Ferruh Yigit
2019-06-28  8:35     ` Ye Xiaolong
2019-06-28 10:07 ` [dpdk-dev] [PATCH v4] " Xiaolong Ye
2019-06-28 17:58   ` Ferruh Yigit

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20190617142303.85240-1-xiaolong.ye@intel.com \
    --to=xiaolong.ye@intel.com \
    --cc=bjorn.topel@intel.com \
    --cc=dev@dpdk.org \
    --cc=magnus.karlsson@intel.com \
    --cc=qi.z.zhang@intel.com \
    --cc=yuan.peng@intel.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).