dpdk/0437-net-af_xdp-re-enable-secondary-process-support.patch

From 9876cf8316b3ef31dea2381024cf92a5af945616 Mon Sep 17 00:00:00 2001
From: Ciara Loftus <ciara.loftus@intel.com>
Date: Wed, 9 Feb 2022 09:48:08 +0000
Subject: [PATCH] net/af_xdp: re-enable secondary process support

[ upstream commit 9876cf8316b3ef31dea2381024cf92a5af945616 ]

Secondary process support had been disabled for the AF_XDP PMD because
there was no logic in place to share the AF_XDP socket file descriptors
between the processes. This commit introduces this logic using the IPC
APIs.

Rx and Tx are disabled in the secondary process due to memory mapping of
the AF_XDP rings being assigned by the kernel in the primary process only.
However other operations including retrieval of stats are permitted.

Signed-off-by: Ciara Loftus <ciara.loftus@intel.com>
Acked-by: Stephen Hemminger <stephen@networkplumber.org>
---
 doc/guides/nics/af_xdp.rst             |   9 ++
 doc/guides/nics/features/af_xdp.ini    |   1 +
 drivers/net/af_xdp/rte_eth_af_xdp.c    | 215 +++++++++++++++++++++++--
 3 files changed, 211 insertions(+), 15 deletions(-)

diff --git a/doc/guides/nics/af_xdp.rst b/doc/guides/nics/af_xdp.rst
index db02ea1984..3d8b70e3f8 100644
--- a/doc/guides/nics/af_xdp.rst
+++ b/doc/guides/nics/af_xdp.rst
@@ -141,4 +141,13 @@ Limitations
   NAPI context from a watchdog timer instead of from softirqs. More information
   on this feature can be found at [1].

+- **Secondary Processes**
+
+  Rx and Tx are not supported for secondary processes due to memory mapping of
+  the AF_XDP rings being assigned by the kernel in the primary process only.
+  However other operations including statistics retrieval are permitted.
+  The maximum number of queues permitted for PMDs operating in this model is 8
+  as this is the maximum number of fds that can be sent through the IPC APIs as
+  defined by RTE_MP_MAX_FD_NUM.
+
   [1] https://lwn.net/Articles/837010/
diff --git a/doc/guides/nics/features/af_xdp.ini b/doc/guides/nics/features/af_xdp.ini
index 54b738e616..8e7e075aaf 100644
--- a/doc/guides/nics/features/af_xdp.ini
+++ b/doc/guides/nics/features/af_xdp.ini
@@ -9,4 +9,5 @@ Power mgmt address monitor = Y
 MTU update           = Y
 Promiscuous mode     = Y
 Stats per queue      = Y
+Multiprocess aware   = Y
 x86-64               = Y

diff --git a/drivers/net/af_xdp/rte_eth_af_xdp.c b/drivers/net/af_xdp/rte_eth_af_xdp.c
index 802f912cb7..4a37c11960 100644
--- a/drivers/net/af_xdp/rte_eth_af_xdp.c
+++ b/drivers/net/af_xdp/rte_eth_af_xdp.c
@@ -80,6 +80,18 @@ RTE_LOG_REGISTER_DEFAULT(af_xdp_logtype, NOTICE);

 #define ETH_AF_XDP_ETH_OVERHEAD		(RTE_ETHER_HDR_LEN + RTE_ETHER_CRC_LEN)

+#define ETH_AF_XDP_MP_KEY "afxdp_mp_send_fds"
+
+static int afxdp_dev_count;
+
+/* Message header to synchronize fds via IPC */
+struct ipc_hdr {
+	char port_name[RTE_DEV_NAME_MAX_LEN];
+	/* The file descriptors are in the dedicated part
+	 * of the Unix message to be translated by the kernel.
+	 */
+};
+
 struct xsk_umem_info {
 	struct xsk_umem *umem;
 	struct rte_ring *buf_ring;
@@ -147,6 +159,10 @@ struct pmd_internals {
 	struct pkt_tx_queue *tx_queues;
 };

+struct pmd_process_private {
+	int rxq_xsk_fds[RTE_MAX_QUEUES_PER_PORT];
+};
+
 #define ETH_AF_XDP_IFACE_ARG			"iface"
 #define ETH_AF_XDP_START_QUEUE_ARG		"start_queue"
 #define ETH_AF_XDP_QUEUE_COUNT_ARG		"queue_count"
@@ -795,11 +811,12 @@ static int
 eth_stats_get(struct rte_eth_dev *dev, struct rte_eth_stats *stats)
 {
 	struct pmd_internals *internals = dev->data->dev_private;
+	struct pmd_process_private *process_private = dev->process_private;
 	struct xdp_statistics xdp_stats;
 	struct pkt_rx_queue *rxq;
 	struct pkt_tx_queue *txq;
 	socklen_t optlen;
-	int i, ret;
+	int i, ret, fd;

 	for (i = 0; i < dev->data->nb_rx_queues; i++) {
 		optlen = sizeof(struct xdp_statistics);
@@ -815,8 +832,9 @@ eth_stats_get(struct rte_eth_dev *dev, struct rte_eth_stats *stats)
 		stats->ibytes += stats->q_ibytes[i];
 		stats->imissed += rxq->stats.rx_dropped;
 		stats->oerrors += txq->stats.tx_dropped;
-		ret = getsockopt(xsk_socket__fd(rxq->xsk), SOL_XDP,
-				XDP_STATISTICS, &xdp_stats, &optlen);
+		fd = process_private->rxq_xsk_fds[i];
+		ret = fd >= 0 ? getsockopt(fd, SOL_XDP, XDP_STATISTICS,
+					   &xdp_stats, &optlen) : -1;
 		if (ret != 0) {
 			AF_XDP_LOG(ERR, "getsockopt() failed for XDP_STATISTICS.\n");
 			return -1;
@@ -884,7 +902,7 @@ eth_dev_close(struct rte_eth_dev *dev)
 	int i;

 	if (rte_eal_process_type() != RTE_PROC_PRIMARY)
-		return 0;
+		goto out;

 	AF_XDP_LOG(INFO, "Closing AF_XDP ethdev on numa socket %u\n",
 		rte_socket_id());
@@ -927,6 +945,9 @@ eth_dev_close(struct rte_eth_dev *dev)
 		}
 	}

+out:
+	rte_free(dev->process_private);
+
 	return 0;
 }

@@ -1355,6 +1376,7 @@ eth_rx_queue_setup(struct rte_eth_dev *dev,
 		   struct rte_mempool *mb_pool)
 {
 	struct pmd_internals *internals = dev->data->dev_private;
+	struct pmd_process_private *process_private = dev->process_private;
 	struct pkt_rx_queue *rxq;
 	int ret;

@@ -1393,6 +1415,8 @@ eth_rx_queue_setup(struct rte_eth_dev *dev,
 	rxq->fds[0].fd = xsk_socket__fd(rxq->xsk);
 	rxq->fds[0].events = POLLIN;

+	process_private->rxq_xsk_fds[rx_queue_id] = rxq->fds[0].fd;
+
 	dev->data->rx_queues[rx_queue_id] = rxq;
 	return 0;

@@ -1694,6 +1718,7 @@ init_internals(struct rte_vdev_device *dev, const char *if_name,
 {
 	const char *name = rte_vdev_device_name(dev);
 	const unsigned int numa_node = dev->device.numa_node;
+	struct pmd_process_private *process_private;
 	struct pmd_internals *internals;
 	struct rte_eth_dev *eth_dev;
 	int ret;
@@ -1759,9 +1784,17 @@ init_internals(struct rte_vdev_device *dev, const char *if_name,
 	if (ret)
 		goto err_free_tx;

+	process_private = (struct pmd_process_private *)
+		rte_zmalloc_socket(name, sizeof(struct pmd_process_private),
+				   RTE_CACHE_LINE_SIZE, numa_node);
+	if (process_private == NULL) {
+		AF_XDP_LOG(ERR, "Failed to alloc memory for process private\n");
+		goto err_free_tx;
+	}
+
 	eth_dev = rte_eth_vdev_allocate(dev, 0);
 	if (eth_dev == NULL)
-		goto err_free_tx;
+		goto err_free_pp;

 	eth_dev->data->dev_private = internals;
 	eth_dev->data->dev_link = pmd_link;
@@ -1770,6 +1803,10 @@ init_internals(struct rte_vdev_device *dev, const char *if_name,
 	eth_dev->dev_ops = &ops;
 	eth_dev->rx_pkt_burst = eth_af_xdp_rx;
 	eth_dev->tx_pkt_burst = eth_af_xdp_tx;
+	eth_dev->process_private = process_private;
+
+	for (i = 0; i < queue_cnt; i++)
+		process_private->rxq_xsk_fds[i] = -1;

 #if defined(XDP_UMEM_UNALIGNED_CHUNK_FLAG)
 	AF_XDP_LOG(INFO, "Zero copy between umem and mbuf enabled.\n");
@@ -1777,6 +1814,8 @@ init_internals(struct rte_vdev_device *dev, const char *if_name,

 	return eth_dev;

+err_free_pp:
+	rte_free(process_private);
 err_free_tx:
 	rte_free(internals->tx_queues);
 err_free_rx:
@@ -1786,6 +1825,119 @@ init_internals(struct rte_vdev_device *dev, const char *if_name,
 	return NULL;
 }

+/* Secondary process requests rxq fds from primary. */
+static int
+afxdp_mp_request_fds(const char *name, struct rte_eth_dev *dev)
+{
+	struct pmd_process_private *process_private = dev->process_private;
+	struct timespec timeout = {.tv_sec = 1, .tv_nsec = 0};
+	struct rte_mp_msg request, *reply;
+	struct rte_mp_reply replies;
+	struct ipc_hdr *request_param = (struct ipc_hdr *)request.param;
+	int i, ret;
+
+	/* Prepare the request */
+	memset(&request, 0, sizeof(request));
+	strlcpy(request.name, ETH_AF_XDP_MP_KEY, sizeof(request.name));
+	strlcpy(request_param->port_name, name,
+		sizeof(request_param->port_name));
+	request.len_param = sizeof(*request_param);
+
+	/* Send the request and receive the reply */
+	AF_XDP_LOG(DEBUG, "Sending multi-process IPC request for %s\n", name);
+	ret = rte_mp_request_sync(&request, &replies, &timeout);
+	if (ret < 0 || replies.nb_received != 1) {
+		AF_XDP_LOG(ERR, "Failed to request fds from primary: %d",
+			   rte_errno);
+		return -1;
+	}
+	reply = replies.msgs;
+	AF_XDP_LOG(DEBUG, "Received multi-process IPC reply for %s\n", name);
+	if (dev->data->nb_rx_queues != reply->num_fds) {
+		AF_XDP_LOG(ERR, "Incorrect number of fds received: %d != %d\n",
+			   reply->num_fds, dev->data->nb_rx_queues);
+		return -EINVAL;
+	}
+
+	for (i = 0; i < reply->num_fds; i++)
+		process_private->rxq_xsk_fds[i] = reply->fds[i];
+
+	free(reply);
+	return 0;
+}
+
+/* Primary process sends rxq fds to secondary. */
+static int
+afxdp_mp_send_fds(const struct rte_mp_msg *request, const void *peer)
+{
+	struct rte_eth_dev *dev;
+	struct pmd_process_private *process_private;
+	struct rte_mp_msg reply;
+	const struct ipc_hdr *request_param =
+		(const struct ipc_hdr *)request->param;
+	struct ipc_hdr *reply_param =
+		(struct ipc_hdr *)reply.param;
+	const char *request_name = request_param->port_name;
+	int i;
+
+	AF_XDP_LOG(DEBUG, "Received multi-process IPC request for %s\n",
+		   request_name);
+
+	/* Find the requested port */
+	dev = rte_eth_dev_get_by_name(request_name);
+	if (!dev) {
+		AF_XDP_LOG(ERR, "Failed to get port id for %s\n", request_name);
+		return -1;
+	}
+	process_private = dev->process_private;
+
+	/* Populate the reply with the xsk fd for each queue */
+	reply.num_fds = 0;
+	if (dev->data->nb_rx_queues > RTE_MP_MAX_FD_NUM) {
+		AF_XDP_LOG(ERR, "Number of rx queues (%d) exceeds max number of fds (%d)\n",
+			   dev->data->nb_rx_queues, RTE_MP_MAX_FD_NUM);
+		return -EINVAL;
+	}
+
+	for (i = 0; i < dev->data->nb_rx_queues; i++)
+		reply.fds[reply.num_fds++] = process_private->rxq_xsk_fds[i];
+
+	/* Send the reply */
+	strlcpy(reply.name, request->name, sizeof(reply.name));
+	strlcpy(reply_param->port_name, request_name,
+		sizeof(reply_param->port_name));
+	reply.len_param = sizeof(*reply_param);
+	AF_XDP_LOG(DEBUG, "Sending multi-process IPC reply for %s\n",
+		   reply_param->port_name);
+	if (rte_mp_reply(&reply, peer) < 0) {
+		AF_XDP_LOG(ERR, "Failed to reply to multi-process IPC request\n");
+		return -1;
+	}
+	return 0;
+}
+
+/* Secondary process rx function. RX is disabled because memory mapping of the
+ * rings being assigned by the kernel in the primary process only.
+ */
+static uint16_t
+eth_af_xdp_rx_noop(void *queue __rte_unused,
+		struct rte_mbuf **bufs __rte_unused,
+		uint16_t nb_pkts __rte_unused)
+{
+	return 0;
+}
+
+/* Secondary process tx function. TX is disabled because memory mapping of the
+ * rings being assigned by the kernel in the primary process only.
+ */
+static uint16_t
+eth_af_xdp_tx_noop(void *queue __rte_unused,
+			struct rte_mbuf **bufs __rte_unused,
+			uint16_t nb_pkts __rte_unused)
+{
+	return 0;
+}
+
 static int
 rte_pmd_af_xdp_probe(struct rte_vdev_device *dev)
 {
@@ -1795,19 +1947,39 @@ rte_pmd_af_xdp_probe(struct rte_vdev_device *dev)
 	int xsk_queue_cnt = ETH_AF_XDP_DFLT_QUEUE_COUNT;
 	int shared_umem = 0;
 	char prog_path[PATH_MAX] = {'\0'};
-	int busy_budget = -1;
+	int busy_budget = -1, ret;
 	struct rte_eth_dev *eth_dev = NULL;
-	const char *name;
+	const char *name = rte_vdev_device_name(dev);

-	AF_XDP_LOG(INFO, "Initializing pmd_af_xdp for %s\n",
-		rte_vdev_device_name(dev));
+	AF_XDP_LOG(INFO, "Initializing pmd_af_xdp for %s\n", name);

-	name = rte_vdev_device_name(dev);
 	if (rte_eal_process_type() == RTE_PROC_SECONDARY) {
-		AF_XDP_LOG(ERR, "Failed to probe %s. "
-				"AF_XDP PMD does not support secondary processes.\n",
-				name);
-		return -ENOTSUP;
+		eth_dev = rte_eth_dev_attach_secondary(name);
+		if (eth_dev == NULL) {
+			AF_XDP_LOG(ERR, "Failed to probe %s\n", name);
+			return -EINVAL;
+		}
+		eth_dev->dev_ops = &ops;
+		eth_dev->device = &dev->device;
+		eth_dev->rx_pkt_burst = eth_af_xdp_rx_noop;
+		eth_dev->tx_pkt_burst = eth_af_xdp_tx_noop;
+		eth_dev->process_private = (struct pmd_process_private *)
+			rte_zmalloc_socket(name,
+					   sizeof(struct pmd_process_private),
+					   RTE_CACHE_LINE_SIZE,
+					   eth_dev->device->numa_node);
+		if (eth_dev->process_private == NULL) {
+			AF_XDP_LOG(ERR,
+				"Failed to alloc memory for process private\n");
+			return -ENOMEM;
+		}
+
+		/* Obtain the xsk fds from the primary process. */
+		if (afxdp_mp_request_fds(name, eth_dev))
+			return -1;
+
+		rte_eth_dev_probing_finish(eth_dev);
+		return 0;
 	}

 	kvlist = rte_kvargs_parse(rte_vdev_device_args(dev), valid_arguments);
@@ -1842,6 +2014,17 @@ rte_pmd_af_xdp_probe(struct rte_vdev_device *dev)
 		return -1;
 	}

+	/* Register IPC callback which shares xsk fds from primary to secondary */
+	if (!afxdp_dev_count) {
+		ret = rte_mp_action_register(ETH_AF_XDP_MP_KEY, afxdp_mp_send_fds);
+		if (ret < 0) {
+			AF_XDP_LOG(ERR, "%s: Failed to register multi-process IPC callback: %s",
+				   name, strerror(rte_errno));
+			return -1;
+		}
+	}
+	afxdp_dev_count++;
+
 	rte_eth_dev_probing_finish(eth_dev);

 	return 0;
@@ -1864,9 +2047,11 @@ rte_pmd_af_xdp_remove(struct rte_vdev_device *dev)
 		return 0;

 	eth_dev_close(eth_dev);
+	if (afxdp_dev_count == 1)
+		rte_mp_action_unregister(ETH_AF_XDP_MP_KEY);
+	afxdp_dev_count--;
 	rte_eth_dev_release_port(eth_dev);

-
 	return 0;
 }

--
2.33.0