vhost: fix deadlock during vDPA SW live migration

In a nested virtualization environment, running dpdk-vdpa
in QEMU-L1 for software live migration will result in a
deadlock between dpdk-vdpa and QEMU-L2 processes.
'rte_vdpa_relay_vring_used'->
'__vhost_iova_to_vva'->
'vhost_user_iotlb_rd_unlock(vq)'->
'vhost_user_iotlb_miss'-> send vhost message
'VHOST_USER_SLAVE_IOTLB_MSG' to QEMU-L2's vdpa socket, then
call 'vhost_user_iotlb_rd_lock(vq)' to hold the read lock
`iotlb_lock`.

But there is no place to release this read lock.

QEMU-L2 get the 'VHOST_USER_SLAVE_IOTLB_MSG', then call
'vhost_user_send_device_iotlb_msg' to send
'VHOST_USER_IOTLB_MSG' messages to dpdk-vdpa.

dpdk-vdpa will call vhost_user_iotlb_cache_insert and will
obtain the write lock `iotlb_lock`, but the read lock
`iotlb_lock` has not been released and will block here.

This patch add lock and unlock function to fix the deadlock.

Fixes: b13ad2d ("vhost: provide helpers for virtio ring relay")
Cc: stable@dpdk.org

Signed-off-by: Hao Chen <chenh@yusur.tech>
Reviewed-by: Maxime Coquelin <maxime.coquelin@redhat.com>

lib/vhost/vdpa.c

@@ -19,6 +19,7 @@
 #include "rte_vdpa.h"
 #include "vdpa_driver.h"
 #include "vhost.h"
+#include "iotlb.h"
 
 /** Double linked list of vDPA devices. */
 TAILQ_HEAD(vdpa_device_list, rte_vdpa_device);
@@ -147,7 +148,6 @@ rte_vdpa_unregister_device(struct rte_vdpa_device *dev)
 
 int
 rte_vdpa_relay_vring_used(int vid, uint16_t qid, void *vring_m)
-	__rte_no_thread_safety_analysis /* FIXME: requires iotlb_lock? */
 {
 	struct virtio_net *dev = get_device(vid);
 	uint16_t idx, idx_m, desc_id;
@@ -193,17 +193,21 @@ rte_vdpa_relay_vring_used(int vid, uint16_t qid, void *vring_m)
 			if (unlikely(nr_descs > vq->size))
 				return -1;
 
+			vhost_user_iotlb_rd_lock(vq);
 			desc_ring = (struct vring_desc *)(uintptr_t)
 				vhost_iova_to_vva(dev, vq,
 						vq->desc[desc_id].addr, &dlen,
 						VHOST_ACCESS_RO);
+			vhost_user_iotlb_rd_unlock(vq);
 			if (unlikely(!desc_ring))
 				return -1;
 
 			if (unlikely(dlen < vq->desc[desc_id].len)) {
+				vhost_user_iotlb_rd_lock(vq);
 				idesc = vhost_alloc_copy_ind_table(dev, vq,
 						vq->desc[desc_id].addr,
 						vq->desc[desc_id].len);
+				vhost_user_iotlb_rd_unlock(vq);
 				if (unlikely(!idesc))
 					return -1;
 
@@ -220,9 +224,12 @@ rte_vdpa_relay_vring_used(int vid, uint16_t qid, void *vring_m)
 			if (unlikely(nr_descs-- == 0))
 				goto fail;
 			desc = desc_ring[desc_id];
-			if (desc.flags & VRING_DESC_F_WRITE)
+			if (desc.flags & VRING_DESC_F_WRITE) {
+				vhost_user_iotlb_rd_lock(vq);
 				vhost_log_write_iova(dev, vq, desc.addr,
 						     desc.len);
+				vhost_user_iotlb_rd_unlock(vq);
+			}
 			desc_id = desc.next;
 		} while (desc.flags & VRING_DESC_F_NEXT);