X-Git-Url: http://git.droids-corp.org/?a=blobdiff_plain;f=drivers%2Fnet%2Ftap%2Frte_eth_tap.c;h=6567bba75b475d51ee15afb8508f0b596d4496d6;hb=191447ce23765dc22a21b5cfe02c7d1a7a776258;hp=61e5ffcdd06035439c0e597bd1c03925355b262a;hpb=0781f5762cfe0a7bbada05da4380f2efecfe79ff;p=dpdk.git

diff --git a/drivers/net/tap/rte_eth_tap.c b/drivers/net/tap/rte_eth_tap.c
index 61e5ffcdd0..6567bba75b 100644
--- a/drivers/net/tap/rte_eth_tap.c
+++ b/drivers/net/tap/rte_eth_tap.c
@@ -61,6 +61,7 @@
 
 #include <rte_eth_tap.h>
 #include <tap_flow.h>
+#include <tap_netlink.h>
 #include <tap_tcmsgs.h>
 
 /* Linux based path to the TUN device */
@@ -69,6 +70,7 @@
 
 #define ETH_TAP_IFACE_ARG       "iface"
 #define ETH_TAP_SPEED_ARG       "speed"
+#define ETH_TAP_REMOTE_ARG      "remote"
 
 #ifdef IFF_MULTI_QUEUE
 #define RTE_PMD_TAP_MAX_QUEUES	16
@@ -84,6 +86,7 @@ static struct rte_vdev_driver pmd_tap_drv;
 static const char *valid_arguments[] = {
 	ETH_TAP_IFACE_ARG,
 	ETH_TAP_SPEED_ARG,
+	ETH_TAP_REMOTE_ARG,
 	NULL
 };
 
@@ -109,6 +112,8 @@ static int
 tap_ioctl(struct pmd_internals *pmd, unsigned long request,
 	  struct ifreq *ifr, int set);
 
+static int tap_intr_handle_set(struct rte_eth_dev *dev, int set);
+
 /* Tun/Tap allocation routine
  *
  * name is the number of the interface to use, unless NULL to take the host
@@ -243,10 +248,43 @@ tun_alloc(struct pmd_internals *pmd, uint16_t qid)
 				pmd->name);
 			return fd;
 		}
+		if (pmd->remote_if_index) {
+			/*
+			 * Flush usually returns negative value because it tries
+			 * to delete every QDISC (and on a running device, one
+			 * QDISC at least is needed). Ignore negative return
+			 * value.
+			 */
+			qdisc_flush(pmd->nlsk_fd, pmd->remote_if_index);
+			if (qdisc_create_ingress(pmd->nlsk_fd,
+						 pmd->remote_if_index) < 0)
+				goto remote_fail;
+			LIST_INIT(&pmd->implicit_flows);
+			if (tap_flow_implicit_create(
+				    pmd, TAP_REMOTE_LOCAL_MAC) < 0)
+				goto remote_fail;
+			if (tap_flow_implicit_create(
+				    pmd, TAP_REMOTE_BROADCAST) < 0)
+				goto remote_fail;
+			if (tap_flow_implicit_create(
+				    pmd, TAP_REMOTE_BROADCASTV6) < 0)
+				goto remote_fail;
+			if (tap_flow_implicit_create(
+				    pmd, TAP_REMOTE_TX) < 0)
+				goto remote_fail;
+		}
 	}
 
 	return fd;
 
+remote_fail:
+	RTE_LOG(ERR, PMD,
+		"Could not set up remote flow rules for %s: remote disabled.\n",
+		pmd->name);
+	pmd->remote_if_index = 0;
+	tap_flow_implicit_flush(pmd, NULL);
+	return fd;
+
 error:
 	if (fd > 0)
 		close(fd);
@@ -402,8 +440,25 @@ tap_ioctl(struct pmd_internals *pmd, unsigned long request,
 	  struct ifreq *ifr, int set)
 {
 	short req_flags = ifr->ifr_flags;
+	int remote = !!pmd->remote_if_index;
 
-	snprintf(ifr->ifr_name, IFNAMSIZ, "%s", pmd->name);
+	/*
+	 * If there is a remote netdevice, apply ioctl on it, then apply it on
+	 * the tap netdevice.
+	 */
+	if (request == SIOCGIFFLAGS && !set) {
+		/*
+		 * Special case for getting flags. If set is given,
+		 * then return the flags from the remote netdevice only.
+		 * Otherwise return the flags from the tap netdevice.
+		 */
+		remote = 0;
+	}
+apply:
+	if (remote)
+		snprintf(ifr->ifr_name, IFNAMSIZ, "%s", pmd->remote_iface);
+	else
+		snprintf(ifr->ifr_name, IFNAMSIZ, "%s", pmd->name);
 	switch (request) {
 	case SIOCSIFFLAGS:
 		/* fetch current flags to leave other flags untouched */
@@ -414,7 +469,17 @@ tap_ioctl(struct pmd_internals *pmd, unsigned long request,
 		else
 			ifr->ifr_flags &= ~req_flags;
 		break;
+	case SIOCGIFFLAGS:
+		if (remote && set)
+			remote = 0; /* don't loop */
+		break;
 	case SIOCGIFHWADDR:
+		/* Set remote MAC on the tap netdevice */
+		if (!remote && pmd->remote_if_index) {
+			request = SIOCSIFHWADDR;
+			goto apply;
+		}
+		break;
 	case SIOCSIFHWADDR:
 	case SIOCSIFMTU:
 		break;
@@ -425,6 +490,8 @@ tap_ioctl(struct pmd_internals *pmd, unsigned long request,
 	}
 	if (ioctl(pmd->ioctl_sock, request, ifr) < 0)
 		goto error;
+	if (remote--)
+		goto apply;
 	return 0;
 
 error:
@@ -456,6 +523,11 @@ tap_link_set_up(struct rte_eth_dev *dev)
 static int
 tap_dev_start(struct rte_eth_dev *dev)
 {
+	int err;
+
+	err = tap_intr_handle_set(dev, 1);
+	if (err)
+		return err;
 	return tap_link_set_up(dev);
 }
 
@@ -464,6 +536,7 @@ tap_dev_start(struct rte_eth_dev *dev)
 static void
 tap_dev_stop(struct rte_eth_dev *dev)
 {
+	tap_intr_handle_set(dev, 0);
 	tap_link_set_down(dev);
 }
 
@@ -585,6 +658,7 @@ tap_dev_close(struct rte_eth_dev *dev __rte_unused)
 
 	tap_link_set_down(dev);
 	tap_flow_flush(dev, NULL);
+	tap_flow_implicit_flush(internals, NULL);
 
 	for (i = 0; i < internals->nb_queues; i++) {
 		if (internals->rxq[i].fd != -1)
@@ -621,9 +695,25 @@ tap_tx_queue_release(void *queue)
 }
 
 static int
-tap_link_update(struct rte_eth_dev *dev __rte_unused,
-		int wait_to_complete __rte_unused)
+tap_link_update(struct rte_eth_dev *dev, int wait_to_complete __rte_unused)
 {
+	struct rte_eth_link *dev_link = &dev->data->dev_link;
+	struct pmd_internals *pmd = dev->data->dev_private;
+	struct ifreq ifr = { .ifr_flags = 0 };
+
+	if (pmd->remote_if_index) {
+		tap_ioctl(pmd, SIOCGIFFLAGS, &ifr, 1);
+		if (!(ifr.ifr_flags & IFF_UP) ||
+		    !(ifr.ifr_flags & IFF_RUNNING)) {
+			dev_link->link_status = ETH_LINK_DOWN;
+			return 0;
+		}
+	}
+	tap_ioctl(pmd, SIOCGIFFLAGS, &ifr, 0);
+	dev_link->link_status =
+		((ifr.ifr_flags & IFF_UP) && (ifr.ifr_flags & IFF_RUNNING) ?
+		 ETH_LINK_UP :
+		 ETH_LINK_DOWN);
 	return 0;
 }
 
@@ -635,6 +725,8 @@ tap_promisc_enable(struct rte_eth_dev *dev)
 
 	dev->data->promiscuous = 1;
 	tap_ioctl(pmd, SIOCSIFFLAGS, &ifr, 1);
+	if (pmd->remote_if_index)
+		tap_flow_implicit_create(pmd, TAP_REMOTE_PROMISC);
 }
 
 static void
@@ -645,6 +737,8 @@ tap_promisc_disable(struct rte_eth_dev *dev)
 
 	dev->data->promiscuous = 0;
 	tap_ioctl(pmd, SIOCSIFFLAGS, &ifr, 0);
+	if (pmd->remote_if_index)
+		tap_flow_implicit_destroy(pmd, TAP_REMOTE_PROMISC);
 }
 
 static void
@@ -655,6 +749,8 @@ tap_allmulti_enable(struct rte_eth_dev *dev)
 
 	dev->data->all_multicast = 1;
 	tap_ioctl(pmd, SIOCSIFFLAGS, &ifr, 1);
+	if (pmd->remote_if_index)
+		tap_flow_implicit_create(pmd, TAP_REMOTE_ALLMULTI);
 }
 
 static void
@@ -665,6 +761,8 @@ tap_allmulti_disable(struct rte_eth_dev *dev)
 
 	dev->data->all_multicast = 0;
 	tap_ioctl(pmd, SIOCSIFFLAGS, &ifr, 0);
+	if (pmd->remote_if_index)
+		tap_flow_implicit_destroy(pmd, TAP_REMOTE_ALLMULTI);
 }
 
 
@@ -887,6 +985,55 @@ tap_set_mc_addr_list(struct rte_eth_dev *dev __rte_unused,
 	return 0;
 }
 
+static int
+tap_nl_msg_handler(struct nlmsghdr *nh, void *arg)
+{
+	struct rte_eth_dev *dev = arg;
+	struct pmd_internals *pmd = dev->data->dev_private;
+	struct ifinfomsg *info = NLMSG_DATA(nh);
+
+	if (nh->nlmsg_type != RTM_NEWLINK ||
+	    (info->ifi_index != pmd->if_index &&
+	     info->ifi_index != pmd->remote_if_index))
+		return 0;
+	return tap_link_update(dev, 0);
+}
+
+static void
+tap_dev_intr_handler(struct rte_intr_handle *intr_handle __rte_unused,
+		     void *cb_arg)
+{
+	struct rte_eth_dev *dev = cb_arg;
+	struct pmd_internals *pmd = dev->data->dev_private;
+
+	nl_recv(pmd->intr_handle.fd, tap_nl_msg_handler, dev);
+}
+
+static int
+tap_intr_handle_set(struct rte_eth_dev *dev, int set)
+{
+	struct pmd_internals *pmd = dev->data->dev_private;
+
+	/* In any case, disable interrupt if the conf is no longer there. */
+	if (!dev->data->dev_conf.intr_conf.lsc) {
+		if (pmd->intr_handle.fd != -1)
+			nl_final(pmd->intr_handle.fd);
+		rte_intr_callback_unregister(
+			&pmd->intr_handle, tap_dev_intr_handler, dev);
+		return 0;
+	}
+	if (set) {
+		pmd->intr_handle.fd = nl_init(RTMGRP_LINK);
+		if (unlikely(pmd->intr_handle.fd == -1))
+			return -EBADF;
+		return rte_intr_callback_register(
+			&pmd->intr_handle, tap_dev_intr_handler, dev);
+	}
+	nl_final(pmd->intr_handle.fd);
+	return rte_intr_callback_unregister(&pmd->intr_handle,
+					    tap_dev_intr_handler, dev);
+}
+
 static const uint32_t*
 tap_dev_supported_ptypes_get(struct rte_eth_dev *dev __rte_unused)
 {
@@ -982,7 +1129,7 @@ tap_kernel_support(struct pmd_internals *pmd)
 }
 
 static int
-eth_dev_tap_create(const char *name, char *tap_name)
+eth_dev_tap_create(const char *name, char *tap_name, char *remote_iface)
 {
 	int numa_node = rte_socket_id();
 	struct rte_eth_dev *dev = NULL;
@@ -1028,7 +1175,7 @@ eth_dev_tap_create(const char *name, char *tap_name)
 	data->dev_private = pmd;
 	data->port_id = dev->data->port_id;
 	data->mtu = dev->data->mtu;
-	data->dev_flags = RTE_ETH_DEV_DETACHABLE;
+	data->dev_flags = RTE_ETH_DEV_DETACHABLE | RTE_ETH_DEV_INTR_LSC;
 	data->kdrv = RTE_KDRV_NONE;
 	data->drv_name = pmd_tap_drv.driver.name;
 	data->numa_node = numa_node;
@@ -1044,6 +1191,9 @@ eth_dev_tap_create(const char *name, char *tap_name)
 	dev->rx_pkt_burst = pmd_rx_burst;
 	dev->tx_pkt_burst = pmd_tx_burst;
 
+	pmd->intr_handle.type = RTE_INTR_HANDLE_EXT;
+	pmd->intr_handle.fd = -1;
+
 	/* Presetup the fds to -1 as being not valid */
 	for (i = 0; i < RTE_PMD_TAP_MAX_QUEUES; i++) {
 		pmd->rxq[i].fd = -1;
@@ -1058,7 +1208,16 @@ eth_dev_tap_create(const char *name, char *tap_name)
 	 * If no netlink socket can be created, then it will fail when
 	 * creating/destroying flow rules.
 	 */
-	pmd->nlsk_fd = nl_init();
+	pmd->nlsk_fd = nl_init(0);
+	if (strlen(remote_iface)) {
+		pmd->remote_if_index = if_nametoindex(remote_iface);
+		snprintf(pmd->remote_iface, RTE_ETH_NAME_MAX_LEN,
+			 "%s", remote_iface);
+		if (!pmd->remote_if_index)
+			RTE_LOG(ERR, PMD, "Could not find %s ifindex: "
+				"remote interface will remain unconfigured\n",
+				remote_iface);
+	}
 
 	return 0;
 
@@ -1099,6 +1258,19 @@ set_interface_speed(const char *key __rte_unused,
 	return 0;
 }
 
+static int
+set_remote_iface(const char *key __rte_unused,
+		 const char *value,
+		 void *extra_args)
+{
+	char *name = (char *)extra_args;
+
+	if (value)
+		snprintf(name, RTE_ETH_NAME_MAX_LEN, "%s", value);
+
+	return 0;
+}
+
 /* Open a TAP interface device.
  */
 static int
@@ -1108,10 +1280,12 @@ rte_pmd_tap_probe(const char *name, const char *params)
 	struct rte_kvargs *kvlist = NULL;
 	int speed;
 	char tap_name[RTE_ETH_NAME_MAX_LEN];
+	char remote_iface[RTE_ETH_NAME_MAX_LEN];
 
 	speed = ETH_SPEED_NUM_10G;
 	snprintf(tap_name, sizeof(tap_name), "%s%d",
 		 DEFAULT_TAP_NAME, tap_unit++);
+	memset(remote_iface, 0, RTE_ETH_NAME_MAX_LEN);
 
 	if (params && (params[0] != '\0')) {
 		RTE_LOG(DEBUG, PMD, "paramaters (%s)\n", params);
@@ -1135,6 +1309,15 @@ rte_pmd_tap_probe(const char *name, const char *params)
 				if (ret == -1)
 					goto leave;
 			}
+
+			if (rte_kvargs_count(kvlist, ETH_TAP_REMOTE_ARG) == 1) {
+				ret = rte_kvargs_process(kvlist,
+							 ETH_TAP_REMOTE_ARG,
+							 &set_remote_iface,
+							 remote_iface);
+				if (ret == -1)
+					goto leave;
+			}
 		}
 	}
 	pmd_link.link_speed = speed;
@@ -1142,7 +1325,7 @@ rte_pmd_tap_probe(const char *name, const char *params)
 	RTE_LOG(NOTICE, PMD, "Initializing pmd_tap for %s as %s\n",
 		name, tap_name);
 
-	ret = eth_dev_tap_create(name, tap_name);
+	ret = eth_dev_tap_create(name, tap_name, remote_iface);
 
 leave:
 	if (ret == -1) {
@@ -1175,6 +1358,7 @@ rte_pmd_tap_remove(const char *name)
 	internals = eth_dev->data->dev_private;
 	if (internals->flower_support && internals->nlsk_fd) {
 		tap_flow_flush(eth_dev, NULL);
+		tap_flow_implicit_flush(internals, NULL);
 		nl_final(internals->nlsk_fd);
 	}
 	for (i = 0; i < internals->nb_queues; i++)