net/vhost: fix access to freed memory

This patch fixes heap-use-after-free reported by ASan.

It is possible for the rte_vhost_dequeue_burst() to access the vq
is freed when numa_realloc() gets called in the device running state.
The control plane will set the vq->access_lock to protected the vq
from the data plane. Unfortunately the lock will fail at the moment
the vq is freed, allowing the rte_vhost_dequeue_burst() to access
the fields of the vq, which will trigger a heap-use-after-free error.

In the case of multiple queues, the vhost pmd can access other queues
that are not ready when the first queue is ready, which makes no sense
and also allows numa_realloc() and rte_vhost_dequeue_burst() access to
vq to happen at the same time. By controlling vq->allow_queuing we can make
the pmd access only the queues that are ready.

Fixes: 1ce3c7fe149 ("net/vhost: emulate device start/stop behavior")

Signed-off-by: Yuan Wang <yuanx.wang@intel.com>
Tested-by: Wei Ling <weix.ling@intel.com>
Reviewed-by: Maxime Coquelin <maxime.coquelin@redhat.com>

diff --git a/drivers/net/vhost/rte_eth_vhost.c b/drivers/net/vhost/rte_eth_vhost.c
index 070f0e6..8a65955 100644 (file)
--- a/drivers/net/vhost/rte_eth_vhost.c
+++ b/drivers/net/vhost/rte_eth_vhost.c
@@ -720,6 +720,7 @@ update_queuing_status(struct rte_eth_dev *dev)
 {
        struct pmd_internal *internal = dev->data->dev_private;
        struct vhost_queue *vq;
+       struct rte_vhost_vring_state *state;
        unsigned int i;
        int allow_queuing = 1;
 
@@ -730,12 +731,17 @@ update_queuing_status(struct rte_eth_dev *dev)
            rte_atomic32_read(&internal->dev_attached) == 0)
                allow_queuing = 0;
 
+       state = vring_states[dev->data->port_id];
+
        /* Wait until rx/tx_pkt_burst stops accessing vhost device */
        for (i = 0; i < dev->data->nb_rx_queues; i++) {
                vq = dev->data->rx_queues[i];
                if (vq == NULL)
                        continue;
-               rte_atomic32_set(&vq->allow_queuing, allow_queuing);
+               if (allow_queuing && state->cur[vq->virtqueue_id])
+                       rte_atomic32_set(&vq->allow_queuing, 1);
+               else
+                       rte_atomic32_set(&vq->allow_queuing, 0);
                while (rte_atomic32_read(&vq->while_queuing))
                        rte_pause();
        }
@@ -744,7 +750,10 @@ update_queuing_status(struct rte_eth_dev *dev)
                vq = dev->data->tx_queues[i];
                if (vq == NULL)
                        continue;
-               rte_atomic32_set(&vq->allow_queuing, allow_queuing);
+               if (allow_queuing && state->cur[vq->virtqueue_id])
+                       rte_atomic32_set(&vq->allow_queuing, 1);
+               else
+                       rte_atomic32_set(&vq->allow_queuing, 0);
                while (rte_atomic32_read(&vq->while_queuing))
                        rte_pause();
        }
@@ -967,6 +976,8 @@ vring_state_changed(int vid, uint16_t vring, int enable)
        state->max_vring = RTE_MAX(vring, state->max_vring);
        rte_spinlock_unlock(&state->lock);
 
+       update_queuing_status(eth_dev);
+
        VHOST_LOG(INFO, "vring%u is %s\n",
                        vring, enable ? "enabled" : "disabled");