[PATCH v6 7/9] vhost: annotate IOTLB lock

[David Marchand <david.marchand@redhat.com>]

The starting point for this is __vhost_iova_to_vva() which requires the
lock to be taken. Annotate all the code leading to a call to it.

vdpa and vhost_crypto code are annotated but they end up not taking
a IOTLB lock and have been marked with a FIXME at the top level.

Signed-off-by: David Marchand <david.marchand@redhat.com>
Acked-by: Morten Brørup <mb@smartsharesystems.com>
Reviewed-by: Maxime Coquelin <maxime.coquelin@redhat.com>
---
Changes since v5:
- rebased after packed support was added to async code,

Changes since RFC v3:
- rebased,
- moved unconditionnal lock acquire in separate patch,
- fixed annotations,

---
 lib/vhost/iotlb.h        |  4 ++++
 lib/vhost/vdpa.c         |  1 +
 lib/vhost/vhost.c        |  8 +++-----
 lib/vhost/vhost.h        | 22 ++++++++++++++------
 lib/vhost/vhost_crypto.c |  8 ++++++++
 lib/vhost/virtio_net.c   | 43 ++++++++++++++++++++++++++++++++++++++++
 6 files changed, 75 insertions(+), 11 deletions(-)

diff --git a/lib/vhost/iotlb.h b/lib/vhost/iotlb.h
index e27ebebcf5..be079a8aa7 100644
--- a/lib/vhost/iotlb.h
+++ b/lib/vhost/iotlb.h
@@ -11,24 +11,28 @@
 
 static __rte_always_inline void
 vhost_user_iotlb_rd_lock(struct vhost_virtqueue *vq)
+	__rte_shared_lock_function(&vq->iotlb_lock)
 {
 	rte_rwlock_read_lock(&vq->iotlb_lock);
 }
 
 static __rte_always_inline void
 vhost_user_iotlb_rd_unlock(struct vhost_virtqueue *vq)
+	__rte_unlock_function(&vq->iotlb_lock)
 {
 	rte_rwlock_read_unlock(&vq->iotlb_lock);
 }
 
 static __rte_always_inline void
 vhost_user_iotlb_wr_lock(struct vhost_virtqueue *vq)
+	__rte_exclusive_lock_function(&vq->iotlb_lock)
 {
 	rte_rwlock_write_lock(&vq->iotlb_lock);
 }
 
 static __rte_always_inline void
 vhost_user_iotlb_wr_unlock(struct vhost_virtqueue *vq)
+	__rte_unlock_function(&vq->iotlb_lock)
 {
 	rte_rwlock_write_unlock(&vq->iotlb_lock);
 }
diff --git a/lib/vhost/vdpa.c b/lib/vhost/vdpa.c
index 577cb00a43..a430a66970 100644
--- a/lib/vhost/vdpa.c
+++ b/lib/vhost/vdpa.c
@@ -146,6 +146,7 @@ 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;
diff --git a/lib/vhost/vhost.c b/lib/vhost/vhost.c
index 1e0c30791e..c36dc06a0a 100644
--- a/lib/vhost/vhost.c
+++ b/lib/vhost/vhost.c
@@ -52,7 +52,6 @@ static const struct vhost_vq_stats_name_off vhost_vq_stat_strings[] = {
 
 #define VHOST_NB_VQ_STATS RTE_DIM(vhost_vq_stat_strings)
 
-/* Called with iotlb_lock read-locked */
 uint64_t
 __vhost_iova_to_vva(struct virtio_net *dev, struct vhost_virtqueue *vq,
 		    uint64_t iova, uint64_t *size, uint8_t perm)
@@ -419,6 +418,7 @@ free_device(struct virtio_net *dev)
 
 static __rte_always_inline int
 log_translate(struct virtio_net *dev, struct vhost_virtqueue *vq)
+	__rte_shared_locks_required(&vq->iotlb_lock)
 {
 	if (likely(!(vq->ring_addrs.flags & (1 << VHOST_VRING_F_LOG))))
 		return 0;
@@ -435,8 +435,6 @@ log_translate(struct virtio_net *dev, struct vhost_virtqueue *vq)
  * Converts vring log address to GPA
  * If IOMMU is enabled, the log address is IOVA
  * If IOMMU not enabled, the log address is already GPA
- *
- * Caller should have iotlb_lock read-locked
  */
 uint64_t
 translate_log_addr(struct virtio_net *dev, struct vhost_virtqueue *vq,
@@ -467,9 +465,9 @@ translate_log_addr(struct virtio_net *dev, struct vhost_virtqueue *vq,
 		return log_addr;
 }
 
-/* Caller should have iotlb_lock read-locked */
 static int
 vring_translate_split(struct virtio_net *dev, struct vhost_virtqueue *vq)
+	__rte_shared_locks_required(&vq->iotlb_lock)
 {
 	uint64_t req_size, size;
 
@@ -506,9 +504,9 @@ vring_translate_split(struct virtio_net *dev, struct vhost_virtqueue *vq)
 	return 0;
 }
 
-/* Caller should have iotlb_lock read-locked */
 static int
 vring_translate_packed(struct virtio_net *dev, struct vhost_virtqueue *vq)
+	__rte_shared_locks_required(&vq->iotlb_lock)
 {
 	uint64_t req_size, size;
 
diff --git a/lib/vhost/vhost.h b/lib/vhost/vhost.h
index c05313cf37..5750f0c005 100644
--- a/lib/vhost/vhost.h
+++ b/lib/vhost/vhost.h
@@ -563,12 +563,15 @@ void __vhost_log_cache_write(struct virtio_net *dev,
 		uint64_t addr, uint64_t len);
 void __vhost_log_cache_write_iova(struct virtio_net *dev,
 		struct vhost_virtqueue *vq,
-		uint64_t iova, uint64_t len);
+		uint64_t iova, uint64_t len)
+	__rte_shared_locks_required(&vq->iotlb_lock);
 void __vhost_log_cache_sync(struct virtio_net *dev,
 		struct vhost_virtqueue *vq);
+
 void __vhost_log_write(struct virtio_net *dev, uint64_t addr, uint64_t len);
 void __vhost_log_write_iova(struct virtio_net *dev, struct vhost_virtqueue *vq,
-			    uint64_t iova, uint64_t len);
+			    uint64_t iova, uint64_t len)
+	__rte_shared_locks_required(&vq->iotlb_lock);
 
 static __rte_always_inline void
 vhost_log_write(struct virtio_net *dev, uint64_t addr, uint64_t len)
@@ -618,6 +621,7 @@ vhost_log_used_vring(struct virtio_net *dev, struct vhost_virtqueue *vq,
 static __rte_always_inline void
 vhost_log_cache_write_iova(struct virtio_net *dev, struct vhost_virtqueue *vq,
 			   uint64_t iova, uint64_t len)
+	__rte_shared_locks_required(&vq->iotlb_lock)
 {
 	if (likely(!(dev->features & (1ULL << VHOST_F_LOG_ALL))))
 		return;
@@ -631,6 +635,7 @@ vhost_log_cache_write_iova(struct virtio_net *dev, struct vhost_virtqueue *vq,
 static __rte_always_inline void
 vhost_log_write_iova(struct virtio_net *dev, struct vhost_virtqueue *vq,
 			   uint64_t iova, uint64_t len)
+	__rte_shared_locks_required(&vq->iotlb_lock)
 {
 	if (likely(!(dev->features & (1ULL << VHOST_F_LOG_ALL))))
 		return;
@@ -834,18 +839,23 @@ struct rte_vhost_device_ops const *vhost_driver_callback_get(const char *path);
 void vhost_backend_cleanup(struct virtio_net *dev);
 
 uint64_t __vhost_iova_to_vva(struct virtio_net *dev, struct vhost_virtqueue *vq,
-			uint64_t iova, uint64_t *len, uint8_t perm);
+			uint64_t iova, uint64_t *len, uint8_t perm)
+	__rte_shared_locks_required(&vq->iotlb_lock);
 void *vhost_alloc_copy_ind_table(struct virtio_net *dev,
 			struct vhost_virtqueue *vq,
-			uint64_t desc_addr, uint64_t desc_len);
-int vring_translate(struct virtio_net *dev, struct vhost_virtqueue *vq);
+			uint64_t desc_addr, uint64_t desc_len)
+	__rte_shared_locks_required(&vq->iotlb_lock);
+int vring_translate(struct virtio_net *dev, struct vhost_virtqueue *vq)
+	__rte_shared_locks_required(&vq->iotlb_lock);
 uint64_t translate_log_addr(struct virtio_net *dev, struct vhost_virtqueue *vq,
-		uint64_t log_addr);
+		uint64_t log_addr)
+	__rte_shared_locks_required(&vq->iotlb_lock);
 void vring_invalidate(struct virtio_net *dev, struct vhost_virtqueue *vq);
 
 static __rte_always_inline uint64_t
 vhost_iova_to_vva(struct virtio_net *dev, struct vhost_virtqueue *vq,
 			uint64_t iova, uint64_t *len, uint8_t perm)
+	__rte_shared_locks_required(&vq->iotlb_lock)
 {
 	if (!(dev->features & (1ULL << VIRTIO_F_IOMMU_PLATFORM)))
 		return rte_vhost_va_from_guest_pa(dev->mem, iova, len);
diff --git a/lib/vhost/vhost_crypto.c b/lib/vhost/vhost_crypto.c
index b448b6685d..f02bf865c3 100644
--- a/lib/vhost/vhost_crypto.c
+++ b/lib/vhost/vhost_crypto.c
@@ -490,6 +490,7 @@ static __rte_always_inline struct virtio_crypto_inhdr *
 reach_inhdr(struct vhost_crypto_data_req *vc_req,
 		struct vhost_crypto_desc *head,
 		uint32_t max_n_descs)
+	__rte_shared_locks_required(&vc_req->vq->iotlb_lock)
 {
 	struct virtio_crypto_inhdr *inhdr;
 	struct vhost_crypto_desc *last = head + (max_n_descs - 1);
@@ -536,6 +537,7 @@ static __rte_always_inline void *
 get_data_ptr(struct vhost_crypto_data_req *vc_req,
 		struct vhost_crypto_desc *cur_desc,
 		uint8_t perm)
+	__rte_shared_locks_required(&vc_req->vq->iotlb_lock)
 {
 	void *data;
 	uint64_t dlen = cur_desc->len;
@@ -552,6 +554,7 @@ get_data_ptr(struct vhost_crypto_data_req *vc_req,
 static __rte_always_inline uint32_t
 copy_data_from_desc(void *dst, struct vhost_crypto_data_req *vc_req,
 	struct vhost_crypto_desc *desc, uint32_t size)
+	__rte_shared_locks_required(&vc_req->vq->iotlb_lock)
 {
 	uint64_t remain;
 	uint64_t addr;
@@ -582,6 +585,7 @@ static __rte_always_inline int
 copy_data(void *data, struct vhost_crypto_data_req *vc_req,
 	struct vhost_crypto_desc *head, struct vhost_crypto_desc **cur_desc,
 	uint32_t size, uint32_t max_n_descs)
+	__rte_shared_locks_required(&vc_req->vq->iotlb_lock)
 {
 	struct vhost_crypto_desc *desc = *cur_desc;
 	uint32_t left = size;
@@ -665,6 +669,7 @@ prepare_write_back_data(struct vhost_crypto_data_req *vc_req,
 		uint32_t offset,
 		uint64_t write_back_len,
 		uint32_t max_n_descs)
+	__rte_shared_locks_required(&vc_req->vq->iotlb_lock)
 {
 	struct vhost_crypto_writeback_data *wb_data, *head;
 	struct vhost_crypto_desc *desc = *cur_desc;
@@ -785,6 +790,7 @@ prepare_sym_cipher_op(struct vhost_crypto *vcrypto, struct rte_crypto_op *op,
 		struct virtio_crypto_cipher_data_req *cipher,
 		struct vhost_crypto_desc *head,
 		uint32_t max_n_descs)
+	__rte_shared_locks_required(&vc_req->vq->iotlb_lock)
 {
 	struct vhost_crypto_desc *desc = head;
 	struct vhost_crypto_writeback_data *ewb = NULL;
@@ -938,6 +944,7 @@ prepare_sym_chain_op(struct vhost_crypto *vcrypto, struct rte_crypto_op *op,
 		struct virtio_crypto_alg_chain_data_req *chain,
 		struct vhost_crypto_desc *head,
 		uint32_t max_n_descs)
+	__rte_shared_locks_required(&vc_req->vq->iotlb_lock)
 {
 	struct vhost_crypto_desc *desc = head, *digest_desc;
 	struct vhost_crypto_writeback_data *ewb = NULL, *ewb2 = NULL;
@@ -1123,6 +1130,7 @@ vhost_crypto_process_one_req(struct vhost_crypto *vcrypto,
 		struct vhost_virtqueue *vq, struct rte_crypto_op *op,
 		struct vring_desc *head, struct vhost_crypto_desc *descs,
 		uint16_t desc_idx)
+	__rte_no_thread_safety_analysis /* FIXME: requires iotlb_lock? */
 {
 	struct vhost_crypto_data_req *vc_req = rte_mbuf_to_priv(op->sym->m_src);
 	struct rte_cryptodev_sym_session *session;
diff --git a/lib/vhost/virtio_net.c b/lib/vhost/virtio_net.c
index 49fc46e127..51dc3c96d3 100644
--- a/lib/vhost/virtio_net.c
+++ b/lib/vhost/virtio_net.c
@@ -233,6 +233,7 @@ vhost_async_dma_check_completed(struct virtio_net *dev, int16_t dma_id, uint16_t
 
 static inline void
 do_data_copy_enqueue(struct virtio_net *dev, struct vhost_virtqueue *vq)
+	__rte_shared_locks_required(&vq->iotlb_lock)
 {
 	struct batch_copy_elem *elem = vq->batch_copy_elems;
 	uint16_t count = vq->batch_copy_nb_elems;
@@ -637,6 +638,7 @@ vhost_shadow_enqueue_single_packed(struct virtio_net *dev,
 				   uint16_t *id,
 				   uint16_t *count,
 				   uint16_t num_buffers)
+	__rte_shared_locks_required(&vq->iotlb_lock)
 {
 	vhost_shadow_enqueue_packed(vq, len, id, count, num_buffers);
 
@@ -728,6 +730,7 @@ static __rte_always_inline int
 map_one_desc(struct virtio_net *dev, struct vhost_virtqueue *vq,
 		struct buf_vector *buf_vec, uint16_t *vec_idx,
 		uint64_t desc_iova, uint64_t desc_len, uint8_t perm)
+	__rte_shared_locks_required(&vq->iotlb_lock)
 {
 	uint16_t vec_id = *vec_idx;
 
@@ -765,6 +768,7 @@ fill_vec_buf_split(struct virtio_net *dev, struct vhost_virtqueue *vq,
 			 uint32_t avail_idx, uint16_t *vec_idx,
 			 struct buf_vector *buf_vec, uint16_t *desc_chain_head,
 			 uint32_t *desc_chain_len, uint8_t perm)
+	__rte_shared_locks_required(&vq->iotlb_lock)
 {
 	uint16_t idx = vq->avail->ring[avail_idx & (vq->size - 1)];
 	uint16_t vec_id = *vec_idx;
@@ -848,6 +852,7 @@ reserve_avail_buf_split(struct virtio_net *dev, struct vhost_virtqueue *vq,
 				uint64_t size, struct buf_vector *buf_vec,
 				uint16_t *num_buffers, uint16_t avail_head,
 				uint16_t *nr_vec)
+	__rte_shared_locks_required(&vq->iotlb_lock)
 {
 	uint16_t cur_idx;
 	uint16_t vec_idx = 0;
@@ -898,6 +903,7 @@ fill_vec_buf_packed_indirect(struct virtio_net *dev,
 			struct vhost_virtqueue *vq,
 			struct vring_packed_desc *desc, uint16_t *vec_idx,
 			struct buf_vector *buf_vec, uint32_t *len, uint8_t perm)
+	__rte_shared_locks_required(&vq->iotlb_lock)
 {
 	uint16_t i;
 	uint32_t nr_descs;
@@ -956,6 +962,7 @@ fill_vec_buf_packed(struct virtio_net *dev, struct vhost_virtqueue *vq,
 				uint16_t avail_idx, uint16_t *desc_count,
 				struct buf_vector *buf_vec, uint16_t *vec_idx,
 				uint16_t *buf_id, uint32_t *len, uint8_t perm)
+	__rte_shared_locks_required(&vq->iotlb_lock)
 {
 	bool wrap_counter = vq->avail_wrap_counter;
 	struct vring_packed_desc *descs = vq->desc_packed;
@@ -1021,6 +1028,7 @@ static __rte_noinline void
 copy_vnet_hdr_to_desc(struct virtio_net *dev, struct vhost_virtqueue *vq,
 		struct buf_vector *buf_vec,
 		struct virtio_net_hdr_mrg_rxbuf *hdr)
+	__rte_shared_locks_required(&vq->iotlb_lock)
 {
 	uint64_t len;
 	uint64_t remain = dev->vhost_hlen;
@@ -1124,6 +1132,7 @@ async_fill_seg(struct virtio_net *dev, struct vhost_virtqueue *vq,
 		struct rte_mbuf *m, uint32_t mbuf_offset,
 		uint64_t buf_iova, uint32_t cpy_len, bool to_desc)
 	__rte_exclusive_locks_required(&vq->access_lock)
+	__rte_shared_locks_required(&vq->iotlb_lock)
 {
 	struct vhost_async *async = vq->async;
 	uint64_t mapped_len;
@@ -1164,6 +1173,7 @@ static __rte_always_inline void
 sync_fill_seg(struct virtio_net *dev, struct vhost_virtqueue *vq,
 		struct rte_mbuf *m, uint32_t mbuf_offset,
 		uint64_t buf_addr, uint64_t buf_iova, uint32_t cpy_len, bool to_desc)
+	__rte_shared_locks_required(&vq->iotlb_lock)
 {
 	struct batch_copy_elem *batch_copy = vq->batch_copy_elems;
 
@@ -1202,6 +1212,7 @@ mbuf_to_desc(struct virtio_net *dev, struct vhost_virtqueue *vq,
 		struct rte_mbuf *m, struct buf_vector *buf_vec,
 		uint16_t nr_vec, uint16_t num_buffers, bool is_async)
 	__rte_exclusive_locks_required(&vq->access_lock)
+	__rte_shared_locks_required(&vq->iotlb_lock)
 {
 	uint32_t vec_idx = 0;
 	uint32_t mbuf_offset, mbuf_avail;
@@ -1331,6 +1342,7 @@ vhost_enqueue_single_packed(struct virtio_net *dev,
 			    struct buf_vector *buf_vec,
 			    uint16_t *nr_descs)
 	__rte_exclusive_locks_required(&vq->access_lock)
+	__rte_shared_locks_required(&vq->iotlb_lock)
 {
 	uint16_t nr_vec = 0;
 	uint16_t avail_idx = vq->last_avail_idx;
@@ -1392,6 +1404,7 @@ static __rte_noinline uint32_t
 virtio_dev_rx_split(struct virtio_net *dev, struct vhost_virtqueue *vq,
 	struct rte_mbuf **pkts, uint32_t count)
 	__rte_exclusive_locks_required(&vq->access_lock)
+	__rte_shared_locks_required(&vq->iotlb_lock)
 {
 	uint32_t pkt_idx = 0;
 	uint16_t num_buffers;
@@ -1448,6 +1461,7 @@ virtio_dev_rx_sync_batch_check(struct virtio_net *dev,
 			   struct rte_mbuf **pkts,
 			   uint64_t *desc_addrs,
 			   uint64_t *lens)
+	__rte_shared_locks_required(&vq->iotlb_lock)
 {
 	bool wrap_counter = vq->avail_wrap_counter;
 	struct vring_packed_desc *descs = vq->desc_packed;
@@ -1551,6 +1565,7 @@ virtio_dev_rx_batch_packed_copy(struct virtio_net *dev,
 			   struct rte_mbuf **pkts,
 			   uint64_t *desc_addrs,
 			   uint64_t *lens)
+	__rte_shared_locks_required(&vq->iotlb_lock)
 {
 	uint32_t buf_offset = sizeof(struct virtio_net_hdr_mrg_rxbuf);
 	struct virtio_net_hdr_mrg_rxbuf *hdrs[PACKED_BATCH_SIZE];
@@ -1598,6 +1613,7 @@ static __rte_always_inline int
 virtio_dev_rx_sync_batch_packed(struct virtio_net *dev,
 			   struct vhost_virtqueue *vq,
 			   struct rte_mbuf **pkts)
+	__rte_shared_locks_required(&vq->iotlb_lock)
 {
 	uint64_t desc_addrs[PACKED_BATCH_SIZE];
 	uint64_t lens[PACKED_BATCH_SIZE];
@@ -1620,6 +1636,7 @@ virtio_dev_rx_single_packed(struct virtio_net *dev,
 			    struct vhost_virtqueue *vq,
 			    struct rte_mbuf *pkt)
 	__rte_exclusive_locks_required(&vq->access_lock)
+	__rte_shared_locks_required(&vq->iotlb_lock)
 {
 	struct buf_vector buf_vec[BUF_VECTOR_MAX];
 	uint16_t nr_descs = 0;
@@ -1645,6 +1662,7 @@ virtio_dev_rx_packed(struct virtio_net *dev,
 		     struct rte_mbuf **__rte_restrict pkts,
 		     uint32_t count)
 	__rte_exclusive_locks_required(&vq->access_lock)
+	__rte_shared_locks_required(&vq->iotlb_lock)
 {
 	uint32_t pkt_idx = 0;
 
@@ -1772,6 +1790,7 @@ static __rte_noinline uint32_t
 virtio_dev_rx_async_submit_split(struct virtio_net *dev, struct vhost_virtqueue *vq,
 	struct rte_mbuf **pkts, uint32_t count, int16_t dma_id, uint16_t vchan_id)
 	__rte_exclusive_locks_required(&vq->access_lock)
+	__rte_shared_locks_required(&vq->iotlb_lock)
 {
 	struct buf_vector buf_vec[BUF_VECTOR_MAX];
 	uint32_t pkt_idx = 0;
@@ -1879,6 +1898,7 @@ vhost_enqueue_async_packed(struct virtio_net *dev,
 			    uint16_t *nr_descs,
 			    uint16_t *nr_buffers)
 	__rte_exclusive_locks_required(&vq->access_lock)
+	__rte_shared_locks_required(&vq->iotlb_lock)
 {
 	uint16_t nr_vec = 0;
 	uint16_t avail_idx = vq->last_avail_idx;
@@ -1938,6 +1958,7 @@ static __rte_always_inline int16_t
 virtio_dev_rx_async_packed(struct virtio_net *dev, struct vhost_virtqueue *vq,
 			    struct rte_mbuf *pkt, uint16_t *nr_descs, uint16_t *nr_buffers)
 	__rte_exclusive_locks_required(&vq->access_lock)
+	__rte_shared_locks_required(&vq->iotlb_lock)
 {
 	struct buf_vector buf_vec[BUF_VECTOR_MAX];
 
@@ -1961,6 +1982,7 @@ virtio_dev_rx_async_packed_batch_enqueue(struct virtio_net *dev,
 			   uint64_t *desc_addrs,
 			   uint64_t *lens)
 	__rte_exclusive_locks_required(&vq->access_lock)
+	__rte_shared_locks_required(&vq->iotlb_lock)
 {
 	uint32_t buf_offset = sizeof(struct virtio_net_hdr_mrg_rxbuf);
 	struct virtio_net_hdr_mrg_rxbuf *hdrs[PACKED_BATCH_SIZE];
@@ -2022,6 +2044,7 @@ virtio_dev_rx_async_packed_batch(struct virtio_net *dev,
 			   struct rte_mbuf **pkts,
 			   int16_t dma_id, uint16_t vchan_id)
 	__rte_exclusive_locks_required(&vq->access_lock)
+	__rte_shared_locks_required(&vq->iotlb_lock)
 {
 	uint64_t desc_addrs[PACKED_BATCH_SIZE];
 	uint64_t lens[PACKED_BATCH_SIZE];
@@ -2069,6 +2092,7 @@ static __rte_noinline uint32_t
 virtio_dev_rx_async_submit_packed(struct virtio_net *dev, struct vhost_virtqueue *vq,
 	struct rte_mbuf **pkts, uint32_t count, int16_t dma_id, uint16_t vchan_id)
 	__rte_exclusive_locks_required(&vq->access_lock)
+	__rte_shared_locks_required(&vq->iotlb_lock)
 {
 	uint32_t pkt_idx = 0;
 	uint16_t n_xfer;
@@ -2843,6 +2867,7 @@ desc_to_mbuf(struct virtio_net *dev, struct vhost_virtqueue *vq,
 		  struct rte_mbuf *m, struct rte_mempool *mbuf_pool,
 		  bool legacy_ol_flags, uint16_t slot_idx, bool is_async)
 	__rte_exclusive_locks_required(&vq->access_lock)
+	__rte_shared_locks_required(&vq->iotlb_lock)
 {
 	uint32_t buf_avail, buf_offset, buf_len;
 	uint64_t buf_addr, buf_iova;
@@ -3049,6 +3074,7 @@ virtio_dev_tx_split(struct virtio_net *dev, struct vhost_virtqueue *vq,
 	struct rte_mempool *mbuf_pool, struct rte_mbuf **pkts, uint16_t count,
 	bool legacy_ol_flags)
 	__rte_exclusive_locks_required(&vq->access_lock)
+	__rte_shared_locks_required(&vq->iotlb_lock)
 {
 	uint16_t i;
 	uint16_t avail_entries;
@@ -3153,6 +3179,7 @@ virtio_dev_tx_split_legacy(struct virtio_net *dev,
 	struct vhost_virtqueue *vq, struct rte_mempool *mbuf_pool,
 	struct rte_mbuf **pkts, uint16_t count)
 	__rte_exclusive_locks_required(&vq->access_lock)
+	__rte_shared_locks_required(&vq->iotlb_lock)
 {
 	return virtio_dev_tx_split(dev, vq, mbuf_pool, pkts, count, true);
 }
@@ -3163,6 +3190,7 @@ virtio_dev_tx_split_compliant(struct virtio_net *dev,
 	struct vhost_virtqueue *vq, struct rte_mempool *mbuf_pool,
 	struct rte_mbuf **pkts, uint16_t count)
 	__rte_exclusive_locks_required(&vq->access_lock)
+	__rte_shared_locks_required(&vq->iotlb_lock)
 {
 	return virtio_dev_tx_split(dev, vq, mbuf_pool, pkts, count, false);
 }
@@ -3174,6 +3202,7 @@ vhost_reserve_avail_batch_packed(struct virtio_net *dev,
 				 uint16_t avail_idx,
 				 uintptr_t *desc_addrs,
 				 uint16_t *ids)
+	__rte_shared_locks_required(&vq->iotlb_lock)
 {
 	bool wrap = vq->avail_wrap_counter;
 	struct vring_packed_desc *descs = vq->desc_packed;
@@ -3317,6 +3346,7 @@ virtio_dev_tx_batch_packed(struct virtio_net *dev,
 			   struct vhost_virtqueue *vq,
 			   struct rte_mbuf **pkts,
 			   bool legacy_ol_flags)
+	__rte_shared_locks_required(&vq->iotlb_lock)
 {
 	uint16_t avail_idx = vq->last_avail_idx;
 	uint32_t buf_offset = sizeof(struct virtio_net_hdr_mrg_rxbuf);
@@ -3364,6 +3394,7 @@ vhost_dequeue_single_packed(struct virtio_net *dev,
 			    uint16_t *desc_count,
 			    bool legacy_ol_flags)
 	__rte_exclusive_locks_required(&vq->access_lock)
+	__rte_shared_locks_required(&vq->iotlb_lock)
 {
 	struct buf_vector buf_vec[BUF_VECTOR_MAX];
 	uint32_t buf_len;
@@ -3413,6 +3444,7 @@ virtio_dev_tx_single_packed(struct virtio_net *dev,
 			    struct rte_mbuf *pkts,
 			    bool legacy_ol_flags)
 	__rte_exclusive_locks_required(&vq->access_lock)
+	__rte_shared_locks_required(&vq->iotlb_lock)
 {
 
 	uint16_t buf_id, desc_count = 0;
@@ -3444,6 +3476,7 @@ virtio_dev_tx_packed(struct virtio_net *dev,
 		     uint32_t count,
 		     bool legacy_ol_flags)
 	__rte_exclusive_locks_required(&vq->access_lock)
+	__rte_shared_locks_required(&vq->iotlb_lock)
 {
 	uint32_t pkt_idx = 0;
 
@@ -3488,6 +3521,7 @@ virtio_dev_tx_packed_legacy(struct virtio_net *dev,
 	struct vhost_virtqueue *__rte_restrict vq, struct rte_mempool *mbuf_pool,
 	struct rte_mbuf **__rte_restrict pkts, uint32_t count)
 	__rte_exclusive_locks_required(&vq->access_lock)
+	__rte_shared_locks_required(&vq->iotlb_lock)
 {
 	return virtio_dev_tx_packed(dev, vq, mbuf_pool, pkts, count, true);
 }
@@ -3498,6 +3532,7 @@ virtio_dev_tx_packed_compliant(struct virtio_net *dev,
 	struct vhost_virtqueue *__rte_restrict vq, struct rte_mempool *mbuf_pool,
 	struct rte_mbuf **__rte_restrict pkts, uint32_t count)
 	__rte_exclusive_locks_required(&vq->access_lock)
+	__rte_shared_locks_required(&vq->iotlb_lock)
 {
 	return virtio_dev_tx_packed(dev, vq, mbuf_pool, pkts, count, false);
 }
@@ -3661,6 +3696,7 @@ virtio_dev_tx_async_split(struct virtio_net *dev, struct vhost_virtqueue *vq,
 		struct rte_mempool *mbuf_pool, struct rte_mbuf **pkts, uint16_t count,
 		int16_t dma_id, uint16_t vchan_id, bool legacy_ol_flags)
 	__rte_exclusive_locks_required(&vq->access_lock)
+	__rte_shared_locks_required(&vq->iotlb_lock)
 {
 	static bool allocerr_warned;
 	bool dropped = false;
@@ -3808,6 +3844,7 @@ virtio_dev_tx_async_split_legacy(struct virtio_net *dev,
 		struct rte_mbuf **pkts, uint16_t count,
 		int16_t dma_id, uint16_t vchan_id)
 	__rte_exclusive_locks_required(&vq->access_lock)
+	__rte_shared_locks_required(&vq->iotlb_lock)
 {
 	return virtio_dev_tx_async_split(dev, vq, mbuf_pool,
 				pkts, count, dma_id, vchan_id, true);
@@ -3820,6 +3857,7 @@ virtio_dev_tx_async_split_compliant(struct virtio_net *dev,
 		struct rte_mbuf **pkts, uint16_t count,
 		int16_t dma_id, uint16_t vchan_id)
 	__rte_exclusive_locks_required(&vq->access_lock)
+	__rte_shared_locks_required(&vq->iotlb_lock)
 {
 	return virtio_dev_tx_async_split(dev, vq, mbuf_pool,
 				pkts, count, dma_id, vchan_id, false);
@@ -3851,6 +3889,7 @@ virtio_dev_tx_async_single_packed(struct virtio_net *dev,
 			uint16_t slot_idx,
 			bool legacy_ol_flags)
 	__rte_exclusive_locks_required(&vq->access_lock)
+	__rte_shared_locks_required(&vq->iotlb_lock)
 {
 	int err;
 	uint16_t buf_id, desc_count = 0;
@@ -3903,6 +3942,7 @@ virtio_dev_tx_async_packed_batch(struct virtio_net *dev,
 			   struct rte_mbuf **pkts, uint16_t slot_idx,
 			   uint16_t dma_id, uint16_t vchan_id)
 	__rte_exclusive_locks_required(&vq->access_lock)
+	__rte_shared_locks_required(&vq->iotlb_lock)
 {
 	uint16_t avail_idx = vq->last_avail_idx;
 	uint32_t buf_offset = sizeof(struct virtio_net_hdr_mrg_rxbuf);
@@ -3960,6 +4000,7 @@ virtio_dev_tx_async_packed(struct virtio_net *dev, struct vhost_virtqueue *vq,
 		struct rte_mempool *mbuf_pool, struct rte_mbuf **pkts,
 		uint16_t count, uint16_t dma_id, uint16_t vchan_id, bool legacy_ol_flags)
 	__rte_exclusive_locks_required(&vq->access_lock)
+	__rte_shared_locks_required(&vq->iotlb_lock)
 {
 	uint32_t pkt_idx = 0;
 	uint16_t slot_idx = 0;
@@ -4070,6 +4111,7 @@ virtio_dev_tx_async_packed_legacy(struct virtio_net *dev, struct vhost_virtqueue
 		struct rte_mempool *mbuf_pool, struct rte_mbuf **pkts,
 		uint16_t count, uint16_t dma_id, uint16_t vchan_id)
 	__rte_exclusive_locks_required(&vq->access_lock)
+	__rte_shared_locks_required(&vq->iotlb_lock)
 {
 	return virtio_dev_tx_async_packed(dev, vq, mbuf_pool,
 				pkts, count, dma_id, vchan_id, true);
@@ -4081,6 +4123,7 @@ virtio_dev_tx_async_packed_compliant(struct virtio_net *dev, struct vhost_virtqu
 		struct rte_mempool *mbuf_pool, struct rte_mbuf **pkts,
 		uint16_t count, uint16_t dma_id, uint16_t vchan_id)
 	__rte_exclusive_locks_required(&vq->access_lock)
+	__rte_shared_locks_required(&vq->iotlb_lock)
 {
 	return virtio_dev_tx_async_packed(dev, vq, mbuf_pool,
 				pkts, count, dma_id, vchan_id, false);
-- 
2.39.1