[dpdk-dev] [PATCH v3] net/tap: add queues when attaching from secondary process

[Thomas Monjalon]

From: Raslan Darawsheh <rasland at mellanox.com>

In the case the device is created by the primary process,
the secondary must request some file descriptors to attach the queues.
The file descriptors are shared via IPC Unix socket.

Thanks to the IPC synchronization, the secondary process
is now able to do Rx/Tx on a TAP created by the primary process.

Signed-off-by: Raslan Darawsheh <rasland at mellanox.com>
Signed-off-by: Thomas Monjalon <thomas at monjalon.net>
---
Note: there is a bug in EAL IPC regarding fd translation.
A fix will be sent later for EAL.

v3:
   - split some long lines
v2:
   - translate file descriptors via IPC API
   - add documentation
---
 doc/guides/nics/tap.rst                |  16 +++
 doc/guides/rel_notes/release_18_08.rst |   5 +
 drivers/net/tap/Makefile               |   1 +
 drivers/net/tap/rte_eth_tap.c          | 131 ++++++++++++++++++++++++-
 4 files changed, 152 insertions(+), 1 deletion(-)

diff --git a/doc/guides/nics/tap.rst b/doc/guides/nics/tap.rst
index 27148681c..d1f3e1c24 100644
--- a/doc/guides/nics/tap.rst
+++ b/doc/guides/nics/tap.rst
@@ -152,6 +152,22 @@ Distribute IPv4 TCP packets using RSS to a given MAC address over queues 0-3::
    testpmd> flow create 0 priority 4 ingress pattern eth dst is 0a:0b:0c:0d:0e:0f \
             / ipv4 / tcp / end actions rss queues 0 1 2 3 end / end
 
+Multi-process sharing
+---------------------
+
+It is possible to attach an existing TAP device in a secondary process,
+by declaring it as a vdev with the same name as in the primary process,
+and without any parameter.
+
+The port attached in a secondary process will give access to the
+statistics and the queues.
+Therefore it can be used for monitoring or Rx/Tx processing.
+
+The IPC synchronization of Rx/Tx queues is currently limited:
+
+  - Only 8 queues
+  - Synchronized on probing, but not on later port update
+
 Example
 -------
 
diff --git a/doc/guides/rel_notes/release_18_08.rst b/doc/guides/rel_notes/release_18_08.rst
index dd611b571..ec6a81236 100644
--- a/doc/guides/rel_notes/release_18_08.rst
+++ b/doc/guides/rel_notes/release_18_08.rst
@@ -74,6 +74,11 @@ New Features
   * Add handlers to add/delete VxLAN port number.
   * Add devarg to specify ingress VLAN rewrite mode.
 
+* **Added TAP Rx/Tx queues sharing with a secondary process.**
+
+  A secondary process can attach a TAP device created in the primary process,
+  probe the queues, and process Rx/Tx in a secondary process.
+
 
 API Changes
 -----------
diff --git a/drivers/net/tap/Makefile b/drivers/net/tap/Makefile
index 324336535..3dcf05a72 100644
--- a/drivers/net/tap/Makefile
+++ b/drivers/net/tap/Makefile
@@ -27,6 +27,7 @@ LDLIBS += -lrte_ethdev -lrte_net -lrte_kvargs -lrte_hash
 LDLIBS += -lrte_bus_vdev -lrte_gso
 
 CFLAGS += -DTAP_MAX_QUEUES=$(TAP_MAX_QUEUES)
+CFLAGS += -DALLOW_EXPERIMENTAL_API
 
 #
 # all source are stored in SRCS-y
diff --git a/drivers/net/tap/rte_eth_tap.c b/drivers/net/tap/rte_eth_tap.c
index 4493507ed..98cbdf614 100644
--- a/drivers/net/tap/rte_eth_tap.c
+++ b/drivers/net/tap/rte_eth_tap.c
@@ -16,6 +16,8 @@
 #include <rte_debug.h>
 #include <rte_ip.h>
 #include <rte_string_fns.h>
+#include <rte_ethdev.h>
+#include <rte_errno.h>
 
 #include <assert.h>
 #include <sys/types.h>
@@ -62,6 +64,9 @@
 #define TAP_GSO_MBUFS_NUM \
 	(TAP_GSO_MBUFS_PER_CORE * TAP_GSO_MBUF_CACHE_SIZE)
 
+/* IPC key for queue fds sync */
+#define TAP_MP_KEY "tap_mp_sync_queues"
+
 static struct rte_vdev_driver pmd_tap_drv;
 static struct rte_vdev_driver pmd_tun_drv;
 
@@ -100,6 +105,17 @@ enum ioctl_mode {
 	REMOTE_ONLY,
 };
 
+/* Message header to synchronize queues via IPC */
+struct ipc_queues {
+	char port_name[RTE_DEV_NAME_MAX_LEN];
+	int rxq_count;
+	int txq_count;
+	/*
+	 * The file descriptors are in the dedicated part
+	 * of the Unix message to be translated by the kernel.
+	 */
+};
+
 static int tap_intr_handle_set(struct rte_eth_dev *dev, int set);
 
 /**
@@ -1920,6 +1936,100 @@ rte_pmd_tun_probe(struct rte_vdev_device *dev)
 	return ret;
 }
 
+/* Request queue file descriptors from secondary to primary. */
+static int
+tap_mp_attach_queues(const char *port_name, struct rte_eth_dev *dev)
+{
+	int ret;
+	struct pmd_internals *devpriv;
+	struct timespec timeout = {.tv_sec = 1, .tv_nsec = 0};
+	struct rte_mp_msg request, *reply;
+	struct rte_mp_reply replies;
+	struct ipc_queues *request_param = (struct ipc_queues *)request.param;
+	struct ipc_queues *reply_param;
+	int queue, fd_iterator;
+
+	/* Prepare the request */
+	strcpy(request.name, TAP_MP_KEY);
+	strcpy(request_param->port_name, port_name);
+	request.len_param = sizeof(*request_param);
+
+	/* Send request and receive reply */
+	ret = rte_mp_request_sync(&request, &replies, &timeout);
+	if (ret < 0) {
+		TAP_LOG(ERR, "Failed to request queues from primary: %d",
+			rte_errno);
+		return -1;
+	}
+	/* FIXME: handle replies.nb_received > 1 */
+	reply = &replies.msgs[0];
+	reply_param = (struct ipc_queues *)reply->param;
+	TAP_LOG(DEBUG, "Received IPC reply for %s", reply_param->port_name);
+
+	/* Attach the queues from received file descriptors */
+	devpriv = dev->data->dev_private;
+	fd_iterator = 0;
+	for (queue = 0; queue < reply_param->rxq_count; queue++)
+		devpriv->rxq[queue].fd = reply->fds[fd_iterator++];
+	for (queue = 0; queue < reply_param->txq_count; queue++)
+		devpriv->txq[queue].fd = reply->fds[fd_iterator++];
+
+	return 0;
+}
+
+/* Send the queue file descriptors from the primary process to secondary. */
+static int
+tap_mp_sync_queues(const struct rte_mp_msg *request, const void *peer)
+{
+	struct rte_eth_dev *dev;
+	struct pmd_internals *devpriv;
+	struct rte_mp_msg reply;
+	const struct ipc_queues *request_param =
+		(const struct ipc_queues *)request->param;
+	struct ipc_queues *reply_param =
+		(struct ipc_queues *)reply.param;
+	uint16_t port_id;
+	int queue;
+	int ret;
+
+	/* Get requested port */
+	TAP_LOG(DEBUG, "Received IPC request for %s", request_param->port_name);
+	ret = rte_eth_dev_get_port_by_name(request_param->port_name, &port_id);
+	if (ret) {
+		TAP_LOG(ERR, "Failed to get port id for %s",
+			request_param->port_name);
+		return -1;
+	}
+	dev = &rte_eth_devices[port_id];
+	devpriv = dev->data->dev_private;
+
+	/* Fill file descriptors for all queues */
+	reply.num_fds = 0;
+	reply_param->rxq_count = 0;
+	for (queue = 0; queue < dev->data->nb_rx_queues; queue++) {
+		reply.fds[reply.num_fds++] = devpriv->rxq[queue].fd;
+		reply_param->rxq_count++;
+	}
+	reply_param->txq_count = 0;
+	for (queue = 0; queue < dev->data->nb_tx_queues; queue++) {
+		reply.fds[reply.num_fds++] = devpriv->txq[queue].fd;
+		reply_param->txq_count++;
+	}
+	/* FIXME: split message if more queues than RTE_MP_MAX_FD_NUM */
+	RTE_ASSERT(reply.num_fds <= RTE_MP_MAX_FD_NUM);
+
+	/* Send reply */
+	strcpy(reply.name, request->name);
+	strcpy(reply_param->port_name, request_param->port_name);
+	reply.len_param = sizeof(*reply_param);
+	if (rte_mp_reply(&reply, peer) < 0) {
+		TAP_LOG(ERR, "Failed to reply an IPC request to sync queues");
+		return -1;
+	}
+
+	return 0;
+}
+
 /* Open a TAP interface device.
  */
 static int
@@ -1946,8 +2056,18 @@ rte_pmd_tap_probe(struct rte_vdev_device *dev)
 			TAP_LOG(ERR, "Failed to probe %s", name);
 			return -1;
 		}
-		/* TODO: request info from primary to set up Rx and Tx */
 		eth_dev->dev_ops = &ops;
+		eth_dev->rx_pkt_burst = pmd_rx_burst;
+		eth_dev->tx_pkt_burst = pmd_tx_burst;
+
+		if (!rte_eal_primary_proc_alive(NULL)) {
+			TAP_LOG(ERR, "Primary process is missing");
+			return -1;
+		}
+		ret = tap_mp_attach_queues(name, eth_dev);
+		if (ret != 0)
+			return -1;
+
 		rte_eth_dev_probing_finish(eth_dev);
 		return 0;
 	}
@@ -1998,10 +2118,19 @@ rte_pmd_tap_probe(struct rte_vdev_device *dev)
 	ret = eth_dev_tap_create(dev, tap_name, remote_iface, &user_mac,
 		ETH_TUNTAP_TYPE_TAP);
 
+	/* Register IPC feed callback */
+	ret = rte_mp_action_register(TAP_MP_KEY, tap_mp_sync_queues);
+	if (ret < 0 && rte_errno != EEXIST) {
+		TAP_LOG(ERR, "%s: Failed to register IPC callback: %s",
+			tuntap_name, strerror(rte_errno));
+		goto leave;
+	}
+
 leave:
 	if (ret == -1) {
 		TAP_LOG(ERR, "Failed to create pmd for %s as %s",
 			name, tap_name);
+		rte_mp_action_unregister(TAP_MP_KEY);
 		tap_unit--;		/* Restore the unit number */
 	}
 	rte_kvargs_free(kvlist);
-- 
2.17.1