net/vhost: fix crash when creating vdev dynamically

[dpdk.git] / drivers / net / vhost / rte_eth_vhost.c

diff --git a/drivers/net/vhost/rte_eth_vhost.c b/drivers/net/vhost/rte_eth_vhost.c
index 04179b4..11b6076 100644 (file)
--- a/drivers/net/vhost/rte_eth_vhost.c
+++ b/drivers/net/vhost/rte_eth_vhost.c
@@ -35,11 +35,11 @@
 #include <stdbool.h>
 
 #include <rte_mbuf.h>
-#include <rte_ethdev.h>
+#include <rte_ethdev_driver.h>
 #include <rte_ethdev_vdev.h>
 #include <rte_malloc.h>
 #include <rte_memcpy.h>
-#include <rte_vdev.h>
+#include <rte_bus_vdev.h>
 #include <rte_kvargs.h>
 #include <rte_vhost.h>
 #include <rte_spinlock.h>
@@ -52,6 +52,7 @@ enum {VIRTIO_RXQ, VIRTIO_TXQ, VIRTIO_QNUM};
 #define ETH_VHOST_QUEUES_ARG           "queues"
 #define ETH_VHOST_CLIENT_ARG           "client"
 #define ETH_VHOST_DEQUEUE_ZERO_COPY    "dequeue-zero-copy"
+#define ETH_VHOST_IOMMU_SUPPORT                "iommu-support"
 #define VHOST_MAX_PKT_BURST 32
 
 static const char *valid_arguments[] = {
@@ -59,6 +60,7 @@ static const char *valid_arguments[] = {
        ETH_VHOST_QUEUES_ARG,
        ETH_VHOST_CLIENT_ARG,
        ETH_VHOST_DEQUEUE_ZERO_COPY,
+       ETH_VHOST_IOMMU_SUPPORT,
        NULL
 };
 
@@ -115,6 +117,7 @@ struct pmd_internal {
        char *dev_name;
        char *iface_name;
        uint16_t max_queues;
+       uint16_t vid;
        rte_atomic32_t started;
 };
 
@@ -525,8 +528,10 @@ update_queuing_status(struct rte_eth_dev *dev)
        unsigned int i;
        int allow_queuing = 1;
 
-       if (rte_atomic32_read(&internal->started) == 0 ||
-           rte_atomic32_read(&internal->dev_attached) == 0)
+       if (rte_atomic32_read(&internal->dev_attached) == 0)
+               return;
+
+       if (rte_atomic32_read(&internal->started) == 0)
                allow_queuing = 0;
 
        /* Wait until rx/tx_pkt_burst stops accessing vhost device */
@@ -549,13 +554,36 @@ update_queuing_status(struct rte_eth_dev *dev)
        }
 }
 
+static void
+queue_setup(struct rte_eth_dev *eth_dev, struct pmd_internal *internal)
+{
+       struct vhost_queue *vq;
+       int i;
+
+       for (i = 0; i < eth_dev->data->nb_rx_queues; i++) {
+               vq = eth_dev->data->rx_queues[i];
+               if (!vq)
+                       continue;
+               vq->vid = internal->vid;
+               vq->internal = internal;
+               vq->port = eth_dev->data->port_id;
+       }
+       for (i = 0; i < eth_dev->data->nb_tx_queues; i++) {
+               vq = eth_dev->data->tx_queues[i];
+               if (!vq)
+                       continue;
+               vq->vid = internal->vid;
+               vq->internal = internal;
+               vq->port = eth_dev->data->port_id;
+       }
+}
+
 static int
 new_device(int vid)
 {
        struct rte_eth_dev *eth_dev;
        struct internal_list *list;
        struct pmd_internal *internal;
-       struct vhost_queue *vq;
        unsigned i;
        char ifname[PATH_MAX];
 #ifdef RTE_LIBRTE_VHOST_NUMA
@@ -578,21 +606,13 @@ new_device(int vid)
                eth_dev->data->numa_node = newnode;
 #endif
 
-       for (i = 0; i < eth_dev->data->nb_rx_queues; i++) {
-               vq = eth_dev->data->rx_queues[i];
-               if (vq == NULL)
-                       continue;
-               vq->vid = vid;
-               vq->internal = internal;
-               vq->port = eth_dev->data->port_id;
-       }
-       for (i = 0; i < eth_dev->data->nb_tx_queues; i++) {
-               vq = eth_dev->data->tx_queues[i];
-               if (vq == NULL)
-                       continue;
-               vq->vid = vid;
-               vq->internal = internal;
-               vq->port = eth_dev->data->port_id;
+       internal->vid = vid;
+       if (eth_dev->data->rx_queues && eth_dev->data->tx_queues) {
+               queue_setup(eth_dev, internal);
+               rte_atomic32_set(&internal->dev_attached, 1);
+       } else {
+               RTE_LOG(INFO, PMD, "RX/TX queues have not setup yet\n");
+               rte_atomic32_set(&internal->dev_attached, 0);
        }
 
        for (i = 0; i < rte_vhost_get_vring_num(vid); i++)
@@ -602,13 +622,11 @@ new_device(int vid)
 
        eth_dev->data->dev_link.link_status = ETH_LINK_UP;
 
-       rte_atomic32_set(&internal->dev_attached, 1);
        update_queuing_status(eth_dev);
 
-       RTE_LOG(INFO, PMD, "New connection established\n");
+       RTE_LOG(INFO, PMD, "Vhost device %d created\n", vid);
 
-       _rte_eth_dev_callback_process(eth_dev, RTE_ETH_EVENT_INTR_LSC,
-                                     NULL, NULL);
+       _rte_eth_dev_callback_process(eth_dev, RTE_ETH_EVENT_INTR_LSC, NULL);
 
        return 0;
 }
@@ -633,8 +651,9 @@ destroy_device(int vid)
        eth_dev = list->eth_dev;
        internal = eth_dev->data->dev_private;
 
-       rte_atomic32_set(&internal->dev_attached, 0);
+       rte_atomic32_set(&internal->started, 0);
        update_queuing_status(eth_dev);
+       rte_atomic32_set(&internal->dev_attached, 0);
 
        eth_dev->data->dev_link.link_status = ETH_LINK_DOWN;
 
@@ -660,10 +679,9 @@ destroy_device(int vid)
        state->max_vring = 0;
        rte_spinlock_unlock(&state->lock);
 
-       RTE_LOG(INFO, PMD, "Connection closed\n");
+       RTE_LOG(INFO, PMD, "Vhost device %d destroyed\n", vid);
 
-       _rte_eth_dev_callback_process(eth_dev, RTE_ETH_EVENT_INTR_LSC,
-                                     NULL, NULL);
+       _rte_eth_dev_callback_process(eth_dev, RTE_ETH_EVENT_INTR_LSC, NULL);
 }
 
 static int
@@ -692,8 +710,7 @@ vring_state_changed(int vid, uint16_t vring, int enable)
        RTE_LOG(INFO, PMD, "vring%u is %s\n",
                        vring, enable ? "enabled" : "disabled");
 
-       _rte_eth_dev_callback_process(eth_dev, RTE_ETH_EVENT_QUEUE_STATE,
-                                     NULL, NULL);
+       _rte_eth_dev_callback_process(eth_dev, RTE_ETH_EVENT_QUEUE_STATE, NULL);
 
        return 0;
 }
@@ -771,12 +788,17 @@ rte_eth_vhost_get_vid_from_port_id(uint16_t port_id)
 }
 
 static int
-eth_dev_start(struct rte_eth_dev *dev)
+eth_dev_start(struct rte_eth_dev *eth_dev)
 {
-       struct pmd_internal *internal = dev->data->dev_private;
+       struct pmd_internal *internal = eth_dev->data->dev_private;
+
+       if (unlikely(rte_atomic32_read(&internal->dev_attached) == 0)) {
+               queue_setup(eth_dev, internal);
+               rte_atomic32_set(&internal->dev_attached, 1);
+       }
 
        rte_atomic32_set(&internal->started, 1);
-       update_queuing_status(dev);
+       update_queuing_status(eth_dev);
 
        return 0;
 }
@@ -890,7 +912,7 @@ eth_dev_info(struct rte_eth_dev *dev,
        dev_info->min_rx_bufsize = 0;
 }
 
-static void
+static int
 eth_stats_get(struct rte_eth_dev *dev, struct rte_eth_stats *stats)
 {
        unsigned i;
@@ -928,6 +950,8 @@ eth_stats_get(struct rte_eth_dev *dev, struct rte_eth_stats *stats)
        stats->oerrors = tx_missed_total;
        stats->ibytes = rx_total_bytes;
        stats->obytes = tx_total_bytes;
+
+       return 0;
 }
 
 static void
@@ -1084,8 +1108,7 @@ eth_dev_vhost_create(struct rte_vdev_device *dev, char *iface_name,
        internal->max_queues = queues;
        data->dev_link = pmd_link;
        data->mac_addrs = eth_addr;
-       data->dev_flags =
-               RTE_ETH_DEV_DETACHABLE | RTE_ETH_DEV_INTR_LSC;
+       data->dev_flags = RTE_ETH_DEV_INTR_LSC;
 
        eth_dev->dev_ops = &ops;
 
@@ -1163,6 +1186,7 @@ rte_pmd_vhost_probe(struct rte_vdev_device *dev)
        uint64_t flags = 0;
        int client_mode = 0;
        int dequeue_zero_copy = 0;
+       int iommu_support = 0;
 
        RTE_LOG(INFO, PMD, "Initializing pmd_vhost for %s\n",
                rte_vdev_device_name(dev));
@@ -1210,6 +1234,16 @@ rte_pmd_vhost_probe(struct rte_vdev_device *dev)
                        flags |= RTE_VHOST_USER_DEQUEUE_ZERO_COPY;
        }
 
+       if (rte_kvargs_count(kvlist, ETH_VHOST_IOMMU_SUPPORT) == 1) {
+               ret = rte_kvargs_process(kvlist, ETH_VHOST_IOMMU_SUPPORT,
+                                        &open_int, &iommu_support);
+               if (ret < 0)
+                       goto out_free;
+
+               if (iommu_support)
+                       flags |= RTE_VHOST_USER_IOMMU_SUPPORT;
+       }
+
        if (dev->device.numa_node == SOCKET_ID_ANY)
                dev->device.numa_node = rte_socket_id();