[RFC PATCH 5/5] vhost: annotate IOTLB locks

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

The IOTLB code uses r/w locks.

Introduce a wrapper around this type of locks and annotate iotlb_lock
and iotlb_pending_lock.

clang does not support conditionally held locks, so always take iotlb
locks regardless of VIRTIO_F_IOMMU_PLATFORM feature.

vdpa and vhost_crypto code are annotated though they end up not taking
a IOTLB lock and have been marked with a FIXME.

Signed-off-by: David Marchand <david.marchand@redhat.com>
---
 lib/vhost/iotlb.c        | 36 +++++++--------
 lib/vhost/iotlb.h        | 24 ----------
 lib/vhost/vdpa.c         |  1 +
 lib/vhost/vhost.c        | 16 +++----
 lib/vhost/vhost.h        | 94 +++++++++++++++++++++++++++++++++++-----
 lib/vhost/vhost_crypto.c |  7 +++
 lib/vhost/vhost_user.c   | 16 +++++--
 lib/vhost/virtio_net.c   | 49 ++++++++++++++++-----
 8 files changed, 164 insertions(+), 79 deletions(-)

diff --git a/lib/vhost/iotlb.c b/lib/vhost/iotlb.c
index 5a5ba8b82a..e5367d3af9 100644
--- a/lib/vhost/iotlb.c
+++ b/lib/vhost/iotlb.c
@@ -30,14 +30,14 @@ vhost_user_iotlb_pending_remove_all(struct vhost_virtqueue *vq)
 {
 	struct vhost_iotlb_entry *node, *temp_node;
 
-	rte_rwlock_write_lock(&vq->iotlb_pending_lock);
+	vhost_rwlock_write_lock(&vq->iotlb_pending_lock);
 
 	RTE_TAILQ_FOREACH_SAFE(node, &vq->iotlb_pending_list, next, temp_node) {
 		TAILQ_REMOVE(&vq->iotlb_pending_list, node, next);
 		rte_mempool_put(vq->iotlb_pool, node);
 	}
 
-	rte_rwlock_write_unlock(&vq->iotlb_pending_lock);
+	vhost_rwlock_write_unlock(&vq->iotlb_pending_lock);
 }
 
 bool
@@ -47,7 +47,7 @@ vhost_user_iotlb_pending_miss(struct vhost_virtqueue *vq, uint64_t iova,
 	struct vhost_iotlb_entry *node;
 	bool found = false;
 
-	rte_rwlock_read_lock(&vq->iotlb_pending_lock);
+	vhost_rwlock_read_lock(&vq->iotlb_pending_lock);
 
 	TAILQ_FOREACH(node, &vq->iotlb_pending_list, next) {
 		if ((node->iova == iova) && (node->perm == perm)) {
@@ -56,7 +56,7 @@ vhost_user_iotlb_pending_miss(struct vhost_virtqueue *vq, uint64_t iova,
 		}
 	}
 
-	rte_rwlock_read_unlock(&vq->iotlb_pending_lock);
+	vhost_rwlock_read_unlock(&vq->iotlb_pending_lock);
 
 	return found;
 }
@@ -89,11 +89,11 @@ vhost_user_iotlb_pending_insert(struct virtio_net *dev, struct vhost_virtqueue *
 	node->iova = iova;
 	node->perm = perm;
 
-	rte_rwlock_write_lock(&vq->iotlb_pending_lock);
+	vhost_rwlock_write_lock(&vq->iotlb_pending_lock);
 
 	TAILQ_INSERT_TAIL(&vq->iotlb_pending_list, node, next);
 
-	rte_rwlock_write_unlock(&vq->iotlb_pending_lock);
+	vhost_rwlock_write_unlock(&vq->iotlb_pending_lock);
 }
 
 void
@@ -102,7 +102,7 @@ vhost_user_iotlb_pending_remove(struct vhost_virtqueue *vq,
 {
 	struct vhost_iotlb_entry *node, *temp_node;
 
-	rte_rwlock_write_lock(&vq->iotlb_pending_lock);
+	vhost_rwlock_write_lock(&vq->iotlb_pending_lock);
 
 	RTE_TAILQ_FOREACH_SAFE(node, &vq->iotlb_pending_list, next,
 				temp_node) {
@@ -116,7 +116,7 @@ vhost_user_iotlb_pending_remove(struct vhost_virtqueue *vq,
 		rte_mempool_put(vq->iotlb_pool, node);
 	}
 
-	rte_rwlock_write_unlock(&vq->iotlb_pending_lock);
+	vhost_rwlock_write_unlock(&vq->iotlb_pending_lock);
 }
 
 static void
@@ -124,7 +124,7 @@ vhost_user_iotlb_cache_remove_all(struct vhost_virtqueue *vq)
 {
 	struct vhost_iotlb_entry *node, *temp_node;
 
-	rte_rwlock_write_lock(&vq->iotlb_lock);
+	vhost_rwlock_write_lock(&vq->iotlb_lock);
 
 	RTE_TAILQ_FOREACH_SAFE(node, &vq->iotlb_list, next, temp_node) {
 		TAILQ_REMOVE(&vq->iotlb_list, node, next);
@@ -133,7 +133,7 @@ vhost_user_iotlb_cache_remove_all(struct vhost_virtqueue *vq)
 
 	vq->iotlb_cache_nr = 0;
 
-	rte_rwlock_write_unlock(&vq->iotlb_lock);
+	vhost_rwlock_write_unlock(&vq->iotlb_lock);
 }
 
 static void
@@ -142,7 +142,7 @@ vhost_user_iotlb_cache_random_evict(struct vhost_virtqueue *vq)
 	struct vhost_iotlb_entry *node, *temp_node;
 	int entry_idx;
 
-	rte_rwlock_write_lock(&vq->iotlb_lock);
+	vhost_rwlock_write_lock(&vq->iotlb_lock);
 
 	entry_idx = rte_rand() % vq->iotlb_cache_nr;
 
@@ -156,7 +156,7 @@ vhost_user_iotlb_cache_random_evict(struct vhost_virtqueue *vq)
 		entry_idx--;
 	}
 
-	rte_rwlock_write_unlock(&vq->iotlb_lock);
+	vhost_rwlock_write_unlock(&vq->iotlb_lock);
 }
 
 void
@@ -190,7 +190,7 @@ vhost_user_iotlb_cache_insert(struct virtio_net *dev, struct vhost_virtqueue *vq
 	new_node->size = size;
 	new_node->perm = perm;
 
-	rte_rwlock_write_lock(&vq->iotlb_lock);
+	vhost_rwlock_write_lock(&vq->iotlb_lock);
 
 	TAILQ_FOREACH(node, &vq->iotlb_list, next) {
 		/*
@@ -213,7 +213,7 @@ vhost_user_iotlb_cache_insert(struct virtio_net *dev, struct vhost_virtqueue *vq
 unlock:
 	vhost_user_iotlb_pending_remove(vq, iova, size, perm);
 
-	rte_rwlock_write_unlock(&vq->iotlb_lock);
+	vhost_rwlock_write_unlock(&vq->iotlb_lock);
 
 }
 
@@ -226,7 +226,7 @@ vhost_user_iotlb_cache_remove(struct vhost_virtqueue *vq,
 	if (unlikely(!size))
 		return;
 
-	rte_rwlock_write_lock(&vq->iotlb_lock);
+	vhost_rwlock_write_lock(&vq->iotlb_lock);
 
 	RTE_TAILQ_FOREACH_SAFE(node, &vq->iotlb_list, next, temp_node) {
 		/* Sorted list */
@@ -240,7 +240,7 @@ vhost_user_iotlb_cache_remove(struct vhost_virtqueue *vq,
 		}
 	}
 
-	rte_rwlock_write_unlock(&vq->iotlb_lock);
+	vhost_rwlock_write_unlock(&vq->iotlb_lock);
 }
 
 uint64_t
@@ -312,8 +312,8 @@ vhost_user_iotlb_init(struct virtio_net *dev, int vq_index)
 		socket = 0;
 #endif
 
-	rte_rwlock_init(&vq->iotlb_lock);
-	rte_rwlock_init(&vq->iotlb_pending_lock);
+	vhost_rwlock_init(&vq->iotlb_lock);
+	vhost_rwlock_init(&vq->iotlb_pending_lock);
 
 	TAILQ_INIT(&vq->iotlb_list);
 	TAILQ_INIT(&vq->iotlb_pending_list);
diff --git a/lib/vhost/iotlb.h b/lib/vhost/iotlb.h
index 8d0ff7473b..96ec4d608f 100644
--- a/lib/vhost/iotlb.h
+++ b/lib/vhost/iotlb.h
@@ -9,30 +9,6 @@
 
 #include "vhost.h"
 
-static __rte_always_inline void
-vhost_user_iotlb_rd_lock(struct vhost_virtqueue *vq)
-{
-	rte_rwlock_read_lock(&vq->iotlb_lock);
-}
-
-static __rte_always_inline void
-vhost_user_iotlb_rd_unlock(struct vhost_virtqueue *vq)
-{
-	rte_rwlock_read_unlock(&vq->iotlb_lock);
-}
-
-static __rte_always_inline void
-vhost_user_iotlb_wr_lock(struct vhost_virtqueue *vq)
-{
-	rte_rwlock_write_lock(&vq->iotlb_lock);
-}
-
-static __rte_always_inline void
-vhost_user_iotlb_wr_unlock(struct vhost_virtqueue *vq)
-{
-	rte_rwlock_write_unlock(&vq->iotlb_lock);
-}
-
 void vhost_user_iotlb_cache_insert(struct virtio_net *dev, struct vhost_virtqueue *vq,
 					uint64_t iova, uint64_t uaddr,
 					uint64_t size, uint8_t perm);
diff --git a/lib/vhost/vdpa.c b/lib/vhost/vdpa.c
index 8fa2153023..406f13288b 100644
--- a/lib/vhost/vdpa.c
+++ b/lib/vhost/vdpa.c
@@ -130,6 +130,7 @@ rte_vdpa_unregister_device(struct rte_vdpa_device *dev)
 
 int
 rte_vdpa_relay_vring_used(int vid, uint16_t qid, void *vring_m)
+	VHOST_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 ea28323367..466a24dabe 100644
--- a/lib/vhost/vhost.c
+++ b/lib/vhost/vhost.c
@@ -50,7 +50,7 @@ __vhost_iova_to_vva(struct virtio_net *dev, struct vhost_virtqueue *vq,
 		 * which could cause a deadlock with QEMU if an IOTLB update
 		 * is being handled. We can safely unlock here to avoid it.
 		 */
-		vhost_user_iotlb_rd_unlock(vq);
+		vhost_rwlock_read_unlock(&vq->iotlb_lock);
 
 		vhost_user_iotlb_pending_insert(dev, vq, iova, perm);
 		if (vhost_user_iotlb_miss(dev, iova, perm)) {
@@ -59,7 +59,7 @@ __vhost_iova_to_vva(struct virtio_net *dev, struct vhost_virtqueue *vq,
 			vhost_user_iotlb_pending_remove(vq, iova, 1, perm);
 		}
 
-		vhost_user_iotlb_rd_lock(vq);
+		vhost_rwlock_read_lock(&vq->iotlb_lock);
 	}
 
 	return 0;
@@ -383,6 +383,7 @@ free_device(struct virtio_net *dev)
 
 static __rte_always_inline int
 log_translate(struct virtio_net *dev, struct vhost_virtqueue *vq)
+	VHOST_RDLOCK_REQUIRES(vq->iotlb_lock)
 {
 	if (likely(!(vq->ring_addrs.flags & (1 << VHOST_VRING_F_LOG))))
 		return 0;
@@ -434,6 +435,7 @@ translate_log_addr(struct virtio_net *dev, struct vhost_virtqueue *vq,
 /* Caller should have iotlb_lock read-locked */
 static int
 vring_translate_split(struct virtio_net *dev, struct vhost_virtqueue *vq)
+	VHOST_RDLOCK_REQUIRES(vq->iotlb_lock)
 {
 	uint64_t req_size, size;
 
@@ -473,6 +475,7 @@ vring_translate_split(struct virtio_net *dev, struct vhost_virtqueue *vq)
 /* Caller should have iotlb_lock read-locked */
 static int
 vring_translate_packed(struct virtio_net *dev, struct vhost_virtqueue *vq)
+	VHOST_RDLOCK_REQUIRES(vq->iotlb_lock)
 {
 	uint64_t req_size, size;
 
@@ -506,7 +509,6 @@ vring_translate_packed(struct virtio_net *dev, struct vhost_virtqueue *vq)
 int
 vring_translate(struct virtio_net *dev, struct vhost_virtqueue *vq)
 {
-
 	if (!(dev->features & (1ULL << VIRTIO_F_IOMMU_PLATFORM)))
 		return -1;
 
@@ -527,19 +529,13 @@ vring_translate(struct virtio_net *dev, struct vhost_virtqueue *vq)
 }
 
 void
-vring_invalidate(struct virtio_net *dev, struct vhost_virtqueue *vq)
+vring_invalidate(struct virtio_net *dev __rte_unused, struct vhost_virtqueue *vq)
 {
-	if (dev->features & (1ULL << VIRTIO_F_IOMMU_PLATFORM))
-		vhost_user_iotlb_wr_lock(vq);
-
 	vq->access_ok = false;
 	vq->desc = NULL;
 	vq->avail = NULL;
 	vq->used = NULL;
 	vq->log_guest_addr = 0;
-
-	if (dev->features & (1ULL << VIRTIO_F_IOMMU_PLATFORM))
-		vhost_user_iotlb_wr_unlock(vq);
 }
 
 static void
diff --git a/lib/vhost/vhost.h b/lib/vhost/vhost.h
index 4b301ec152..08ace9994a 100644
--- a/lib/vhost/vhost.h
+++ b/lib/vhost/vhost.h
@@ -108,6 +108,19 @@
 #define VHOST_SPINLOCK_RELEASES(...) \
 	__attribute__((unlock_function(__VA_ARGS__)))
 
+#define VHOST_RDLOCK_REQUIRES(...) \
+	__attribute__((shared_locks_required(__VA_ARGS__)))
+#define VHOST_RDLOCK_ACQUIRES(...) \
+	__attribute__((shared_lock_function(__VA_ARGS__)))
+#define VHOST_RDLOCK_RELEASES(...) \
+	__attribute__((unlock_function(__VA_ARGS__)))
+#define VHOST_WRLOCK_REQUIRES(...) \
+	__attribute__((exclusive_locks_required(__VA_ARGS__)))
+#define VHOST_WRLOCK_ACQUIRES(...) \
+	__attribute__((exclusive_lock_function(__VA_ARGS__)))
+#define VHOST_WRLOCK_RELEASES(...) \
+	__attribute__((unlock_function(__VA_ARGS__)))
+
 #else
 #define VHOST_NO_THREAD_SAFETY_ANALYSIS
 #define VHOST_LOCKABLE
@@ -117,6 +130,13 @@
 #define VHOST_SPINLOCK_ACQUIRES(...)
 #define VHOST_SPINLOCK_TRYLOCK(...)
 #define VHOST_SPINLOCK_RELEASES(...)
+
+#define VHOST_RDLOCK_ACQUIRES(...)
+#define VHOST_RDLOCK_REQUIRES(...)
+#define VHOST_RDLOCK_RELEASES(...)
+#define VHOST_WRLOCK_REQUIRES(...)
+#define VHOST_WRLOCK_ACQUIRES(...)
+#define VHOST_WRLOCK_RELEASES(...)
 #endif
 
 typedef struct VHOST_LOCKABLE {
@@ -153,6 +173,48 @@ vhost_spinlock_unlock(vhost_spinlock_t *l)
 	rte_spinlock_unlock(&l->l);
 }
 
+typedef struct VHOST_LOCKABLE {
+	rte_rwlock_t l;
+} vhost_rwlock_t;
+
+static __rte_always_inline void
+vhost_rwlock_init(vhost_rwlock_t *l)
+{
+	rte_rwlock_init(&l->l);
+}
+
+static __rte_always_inline void
+vhost_rwlock_read_lock(vhost_rwlock_t *l)
+	VHOST_RDLOCK_ACQUIRES(l)
+	VHOST_NO_THREAD_SAFETY_ANALYSIS
+{
+	rte_rwlock_read_lock(&l->l);
+}
+
+static __rte_always_inline void
+vhost_rwlock_read_unlock(vhost_rwlock_t *l)
+	VHOST_RDLOCK_RELEASES(l)
+	VHOST_NO_THREAD_SAFETY_ANALYSIS
+{
+	rte_rwlock_read_unlock(&l->l);
+}
+
+static __rte_always_inline void
+vhost_rwlock_write_lock(vhost_rwlock_t *l)
+	VHOST_WRLOCK_ACQUIRES(l)
+	VHOST_NO_THREAD_SAFETY_ANALYSIS
+{
+	rte_rwlock_write_lock(&l->l);
+}
+
+static __rte_always_inline void
+vhost_rwlock_write_unlock(vhost_rwlock_t *l)
+	VHOST_WRLOCK_RELEASES(l)
+	VHOST_NO_THREAD_SAFETY_ANALYSIS
+{
+	rte_rwlock_write_unlock(&l->l);
+}
+
 /**
  * Structure contains buffer address, length and descriptor index
  * from vring to do scatter RX.
@@ -346,8 +408,8 @@ struct vhost_virtqueue {
 	uint64_t		log_guest_addr;
 	struct log_cache_entry	*log_cache;
 
-	rte_rwlock_t	iotlb_lock;
-	rte_rwlock_t	iotlb_pending_lock;
+	vhost_rwlock_t	iotlb_lock;
+	vhost_rwlock_t	iotlb_pending_lock;
 	struct rte_mempool *iotlb_pool;
 	TAILQ_HEAD(, vhost_iotlb_entry) iotlb_list;
 	TAILQ_HEAD(, vhost_iotlb_entry) iotlb_pending_list;
@@ -592,12 +654,15 @@ 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)
+	VHOST_RDLOCK_REQUIRES(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)
+	VHOST_RDLOCK_REQUIRES(vq->iotlb_lock);
 
 static __rte_always_inline void
 vhost_log_write(struct virtio_net *dev, uint64_t addr, uint64_t len)
@@ -647,6 +712,7 @@ 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)
+	VHOST_RDLOCK_REQUIRES(vq->iotlb_lock)
 {
 	if (likely(!(dev->features & (1ULL << VHOST_F_LOG_ALL))))
 		return;
@@ -660,6 +726,7 @@ 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)
+	VHOST_RDLOCK_REQUIRES(vq->iotlb_lock)
 {
 	if (likely(!(dev->features & (1ULL << VHOST_F_LOG_ALL))))
 		return;
@@ -863,18 +930,23 @@ 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);
-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 iova, uint64_t *len, uint8_t perm)
+	VHOST_RDLOCK_REQUIRES(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)
+	VHOST_RDLOCK_REQUIRES(vq->iotlb_lock);
+int vring_translate(struct virtio_net *dev, struct vhost_virtqueue *vq)
+	VHOST_RDLOCK_REQUIRES(vq->iotlb_lock);
 uint64_t translate_log_addr(struct virtio_net *dev, struct vhost_virtqueue *vq,
-		uint64_t log_addr);
-void vring_invalidate(struct virtio_net *dev, struct vhost_virtqueue *vq);
+		uint64_t log_addr)
+	VHOST_RDLOCK_REQUIRES(vq->iotlb_lock);
+void vring_invalidate(struct virtio_net *dev, struct vhost_virtqueue *vq)
+	VHOST_WRLOCK_REQUIRES(vq->iotlb_lock);
 
 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)
+	VHOST_RDLOCK_REQUIRES(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 b1c0eb6a0f..2d0a1250fb 100644
--- a/lib/vhost/vhost_crypto.c
+++ b/lib/vhost/vhost_crypto.c
@@ -506,6 +506,7 @@ 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)
+	VHOST_RDLOCK_REQUIRES(vc_req->vq->iotlb_lock)
 {
 	struct virtio_crypto_inhdr *inhdr;
 	struct vhost_crypto_desc *last = head + (max_n_descs - 1);
@@ -552,6 +553,7 @@ static __rte_always_inline void *
 get_data_ptr(struct vhost_crypto_data_req *vc_req,
 		struct vhost_crypto_desc *cur_desc,
 		uint8_t perm)
+	VHOST_RDLOCK_REQUIRES(vc_req->vq->iotlb_lock)
 {
 	void *data;
 	uint64_t dlen = cur_desc->len;
@@ -570,6 +572,7 @@ copy_data(void *dst_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)
+	VHOST_RDLOCK_REQUIRES(vc_req->vq->iotlb_lock)
 {
 	struct vhost_crypto_desc *desc = *cur_desc;
 	uint64_t remain, addr, dlen, len;
@@ -718,6 +721,7 @@ prepare_write_back_data(struct vhost_crypto_data_req *vc_req,
 		uint32_t offset,
 		uint64_t write_back_len,
 		uint32_t max_n_descs)
+	VHOST_RDLOCK_REQUIRES(vc_req->vq->iotlb_lock)
 {
 	struct vhost_crypto_writeback_data *wb_data, *head;
 	struct vhost_crypto_desc *desc = *cur_desc;
@@ -838,6 +842,7 @@ 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)
+	VHOST_RDLOCK_REQUIRES(vc_req->vq->iotlb_lock)
 {
 	struct vhost_crypto_desc *desc = head;
 	struct vhost_crypto_writeback_data *ewb = NULL;
@@ -990,6 +995,7 @@ 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)
+	VHOST_RDLOCK_REQUIRES(vc_req->vq->iotlb_lock)
 {
 	struct vhost_crypto_desc *desc = head, *digest_desc;
 	struct vhost_crypto_writeback_data *ewb = NULL, *ewb2 = NULL;
@@ -1172,6 +1178,7 @@ 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)
+	VHOST_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/vhost_user.c b/lib/vhost/vhost_user.c
index 35f1e23995..0482c00801 100644
--- a/lib/vhost/vhost_user.c
+++ b/lib/vhost/vhost_user.c
@@ -754,10 +754,10 @@ ring_addr_to_vva(struct virtio_net *dev, struct vhost_virtqueue *vq,
 	if (dev->features & (1ULL << VIRTIO_F_IOMMU_PLATFORM)) {
 		uint64_t vva;
 
-		vhost_user_iotlb_rd_lock(vq);
+		vhost_rwlock_read_lock(&vq->iotlb_lock);
 		vva = vhost_iova_to_vva(dev, vq, ra,
 					size, VHOST_ACCESS_RW);
-		vhost_user_iotlb_rd_unlock(vq);
+		vhost_rwlock_read_unlock(&vq->iotlb_lock);
 
 		return vva;
 	}
@@ -770,9 +770,9 @@ log_addr_to_gpa(struct virtio_net *dev, struct vhost_virtqueue *vq)
 {
 	uint64_t log_gpa;
 
-	vhost_user_iotlb_rd_lock(vq);
+	vhost_rwlock_read_lock(&vq->iotlb_lock);
 	log_gpa = translate_log_addr(dev, vq, vq->ring_addrs.log_guest_addr);
-	vhost_user_iotlb_rd_unlock(vq);
+	vhost_rwlock_read_unlock(&vq->iotlb_lock);
 
 	return log_gpa;
 }
@@ -927,7 +927,9 @@ vhost_user_set_vring_addr(struct virtio_net **pdev,
 	 */
 	memcpy(&vq->ring_addrs, addr, sizeof(*addr));
 
+	vhost_rwlock_write_lock(&vq->iotlb_lock);
 	vring_invalidate(dev, vq);
+	vhost_rwlock_write_unlock(&vq->iotlb_lock);
 
 	if ((vq->enabled && (dev->features &
 				(1ULL << VHOST_USER_F_PROTOCOL_FEATURES))) ||
@@ -1437,7 +1439,9 @@ vhost_user_set_mem_table(struct virtio_net **pdev,
 			 * need to be translated again as virtual addresses have
 			 * changed.
 			 */
+			vhost_rwlock_write_lock(&vq->iotlb_lock);
 			vring_invalidate(dev, vq);
+			vhost_rwlock_write_unlock(&vq->iotlb_lock);
 
 			dev = translate_ring_addresses(dev, i);
 			if (!dev) {
@@ -2186,7 +2190,9 @@ vhost_user_get_vring_base(struct virtio_net **pdev,
 
 	vhost_user_iotlb_flush_all(vq);
 
+	vhost_rwlock_write_lock(&vq->iotlb_lock);
 	vring_invalidate(dev, vq);
+	vhost_rwlock_write_unlock(&vq->iotlb_lock);
 
 	return RTE_VHOST_MSG_RESULT_REPLY;
 }
@@ -2591,7 +2597,9 @@ vhost_user_iotlb_msg(struct virtio_net **pdev,
 
 			if (is_vring_iotlb(dev, vq, imsg)) {
 				vhost_spinlock_lock(&vq->access_lock);
+				vhost_rwlock_write_lock(&vq->iotlb_lock);
 				vring_invalidate(dev, vq);
+				vhost_rwlock_write_unlock(&vq->iotlb_lock);
 				vhost_spinlock_unlock(&vq->access_lock);
 			}
 		}
diff --git a/lib/vhost/virtio_net.c b/lib/vhost/virtio_net.c
index 9bdba992dd..ec342e772d 100644
--- a/lib/vhost/virtio_net.c
+++ b/lib/vhost/virtio_net.c
@@ -180,6 +180,7 @@ 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)
+	VHOST_RDLOCK_REQUIRES(vq->iotlb_lock)
 {
 	struct batch_copy_elem *elem = vq->batch_copy_elems;
 	uint16_t count = vq->batch_copy_nb_elems;
@@ -526,6 +527,7 @@ vhost_shadow_enqueue_single_packed(struct virtio_net *dev,
 				   uint16_t *id,
 				   uint16_t *count,
 				   uint16_t num_buffers)
+	VHOST_RDLOCK_REQUIRES(vq->iotlb_lock)
 {
 	vhost_shadow_enqueue_packed(vq, len, id, count, num_buffers);
 
@@ -607,6 +609,7 @@ 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)
+	VHOST_RDLOCK_REQUIRES(vq->iotlb_lock)
 {
 	uint16_t vec_id = *vec_idx;
 
@@ -644,6 +647,7 @@ 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)
+	VHOST_RDLOCK_REQUIRES(vq->iotlb_lock)
 {
 	uint16_t idx = vq->avail->ring[avail_idx & (vq->size - 1)];
 	uint16_t vec_id = *vec_idx;
@@ -727,6 +731,7 @@ reserve_avail_buf_split(struct virtio_net *dev, struct vhost_virtqueue *vq,
 				uint32_t size, struct buf_vector *buf_vec,
 				uint16_t *num_buffers, uint16_t avail_head,
 				uint16_t *nr_vec)
+	VHOST_RDLOCK_REQUIRES(vq->iotlb_lock)
 {
 	uint16_t cur_idx;
 	uint16_t vec_idx = 0;
@@ -777,6 +782,7 @@ 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)
+	VHOST_RDLOCK_REQUIRES(vq->iotlb_lock)
 {
 	uint16_t i;
 	uint32_t nr_descs;
@@ -835,6 +841,7 @@ 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)
+	VHOST_RDLOCK_REQUIRES(vq->iotlb_lock)
 {
 	bool wrap_counter = vq->avail_wrap_counter;
 	struct vring_packed_desc *descs = vq->desc_packed;
@@ -900,6 +907,7 @@ 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)
+	VHOST_RDLOCK_REQUIRES(vq->iotlb_lock)
 {
 	uint64_t len;
 	uint64_t remain = dev->vhost_hlen;
@@ -1036,6 +1044,7 @@ static __rte_always_inline void
 sync_mbuf_to_desc_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)
+	VHOST_RDLOCK_REQUIRES(vq->iotlb_lock)
 {
 	struct batch_copy_elem *batch_copy = vq->batch_copy_elems;
 
@@ -1061,6 +1070,7 @@ 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)
 	VHOST_SPINLOCK_REQUIRES(vq->access_lock)
+	VHOST_RDLOCK_REQUIRES(vq->iotlb_lock)
 {
 	uint32_t vec_idx = 0;
 	uint32_t mbuf_offset, mbuf_avail;
@@ -1191,6 +1201,7 @@ vhost_enqueue_single_packed(struct virtio_net *dev,
 			    struct buf_vector *buf_vec,
 			    uint16_t *nr_descs)
 	VHOST_SPINLOCK_REQUIRES(vq->access_lock)
+	VHOST_RDLOCK_REQUIRES(vq->iotlb_lock)
 {
 	uint16_t nr_vec = 0;
 	uint16_t avail_idx = vq->last_avail_idx;
@@ -1252,6 +1263,7 @@ static __rte_noinline uint32_t
 virtio_dev_rx_split(struct virtio_net *dev, struct vhost_virtqueue *vq,
 	struct rte_mbuf **pkts, uint32_t count)
 	VHOST_SPINLOCK_REQUIRES(vq->access_lock)
+	VHOST_RDLOCK_REQUIRES(vq->iotlb_lock)
 {
 	uint32_t pkt_idx = 0;
 	uint16_t num_buffers;
@@ -1309,6 +1321,7 @@ virtio_dev_rx_sync_batch_check(struct virtio_net *dev,
 			   struct rte_mbuf **pkts,
 			   uint64_t *desc_addrs,
 			   uint64_t *lens)
+	VHOST_RDLOCK_REQUIRES(vq->iotlb_lock)
 {
 	bool wrap_counter = vq->avail_wrap_counter;
 	struct vring_packed_desc *descs = vq->desc_packed;
@@ -1360,6 +1373,7 @@ virtio_dev_rx_batch_packed_copy(struct virtio_net *dev,
 			   struct rte_mbuf **pkts,
 			   uint64_t *desc_addrs,
 			   uint64_t *lens)
+	VHOST_RDLOCK_REQUIRES(vq->iotlb_lock)
 {
 	uint32_t buf_offset = sizeof(struct virtio_net_hdr_mrg_rxbuf);
 	struct virtio_net_hdr_mrg_rxbuf *hdrs[PACKED_BATCH_SIZE];
@@ -1401,6 +1415,7 @@ static __rte_always_inline int
 virtio_dev_rx_sync_batch_packed(struct virtio_net *dev,
 			   struct vhost_virtqueue *vq,
 			   struct rte_mbuf **pkts)
+	VHOST_RDLOCK_REQUIRES(vq->iotlb_lock)
 {
 	uint64_t desc_addrs[PACKED_BATCH_SIZE];
 	uint64_t lens[PACKED_BATCH_SIZE];
@@ -1423,6 +1438,7 @@ virtio_dev_rx_single_packed(struct virtio_net *dev,
 			    struct vhost_virtqueue *vq,
 			    struct rte_mbuf *pkt)
 	VHOST_SPINLOCK_REQUIRES(vq->access_lock)
+	VHOST_RDLOCK_REQUIRES(vq->iotlb_lock)
 {
 	struct buf_vector buf_vec[BUF_VECTOR_MAX];
 	uint16_t nr_descs = 0;
@@ -1449,6 +1465,7 @@ virtio_dev_rx_packed(struct virtio_net *dev,
 		     struct rte_mbuf **__rte_restrict pkts,
 		     uint32_t count)
 	VHOST_SPINLOCK_REQUIRES(vq->access_lock)
+	VHOST_RDLOCK_REQUIRES(vq->iotlb_lock)
 {
 	uint32_t pkt_idx = 0;
 
@@ -1501,8 +1518,7 @@ virtio_dev_rx(struct virtio_net *dev, uint16_t queue_id,
 	if (unlikely(!vq->enabled))
 		goto out_access_unlock;
 
-	if (dev->features & (1ULL << VIRTIO_F_IOMMU_PLATFORM))
-		vhost_user_iotlb_rd_lock(vq);
+	vhost_rwlock_read_lock(&vq->iotlb_lock);
 
 	if (unlikely(!vq->access_ok))
 		if (unlikely(vring_translate(dev, vq) < 0))
@@ -1518,8 +1534,7 @@ virtio_dev_rx(struct virtio_net *dev, uint16_t queue_id,
 		nb_tx = virtio_dev_rx_split(dev, vq, pkts, count);
 
 out:
-	if (dev->features & (1ULL << VIRTIO_F_IOMMU_PLATFORM))
-		vhost_user_iotlb_rd_unlock(vq);
+	vhost_rwlock_read_unlock(&vq->iotlb_lock);
 
 out_access_unlock:
 	vhost_spinlock_unlock(&vq->access_lock);
@@ -1595,6 +1610,7 @@ virtio_dev_rx_async_submit_split(struct virtio_net *dev, struct vhost_virtqueue
 		uint16_t queue_id, struct rte_mbuf **pkts, uint32_t count,
 		int16_t dma_id, uint16_t vchan_id)
 	VHOST_SPINLOCK_REQUIRES(vq->access_lock)
+	VHOST_RDLOCK_REQUIRES(vq->iotlb_lock)
 {
 	struct buf_vector buf_vec[BUF_VECTOR_MAX];
 	uint32_t pkt_idx = 0;
@@ -1700,6 +1716,7 @@ vhost_enqueue_async_packed(struct virtio_net *dev,
 			    uint16_t *nr_descs,
 			    uint16_t *nr_buffers)
 	VHOST_SPINLOCK_REQUIRES(vq->access_lock)
+	VHOST_RDLOCK_REQUIRES(vq->iotlb_lock)
 {
 	uint16_t nr_vec = 0;
 	uint16_t avail_idx = vq->last_avail_idx;
@@ -1758,6 +1775,7 @@ 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)
 	VHOST_SPINLOCK_REQUIRES(vq->access_lock)
+	VHOST_RDLOCK_REQUIRES(vq->iotlb_lock)
 {
 	struct buf_vector buf_vec[BUF_VECTOR_MAX];
 
@@ -1805,6 +1823,7 @@ virtio_dev_rx_async_submit_packed(struct virtio_net *dev, struct vhost_virtqueue
 		uint16_t queue_id, struct rte_mbuf **pkts, uint32_t count,
 		int16_t dma_id, uint16_t vchan_id)
 	VHOST_SPINLOCK_REQUIRES(vq->access_lock)
+	VHOST_RDLOCK_REQUIRES(vq->iotlb_lock)
 {
 	uint32_t pkt_idx = 0;
 	uint32_t remained = count;
@@ -2154,8 +2173,7 @@ virtio_dev_rx_async_submit(struct virtio_net *dev, uint16_t queue_id,
 	if (unlikely(!vq->enabled || !vq->async))
 		goto out_access_unlock;
 
-	if (dev->features & (1ULL << VIRTIO_F_IOMMU_PLATFORM))
-		vhost_user_iotlb_rd_lock(vq);
+	vhost_rwlock_read_lock(&vq->iotlb_lock);
 
 	if (unlikely(!vq->access_ok))
 		if (unlikely(vring_translate(dev, vq) < 0))
@@ -2173,8 +2191,7 @@ virtio_dev_rx_async_submit(struct virtio_net *dev, uint16_t queue_id,
 				pkts, count, dma_id, vchan_id);
 
 out:
-	if (dev->features & (1ULL << VIRTIO_F_IOMMU_PLATFORM))
-		vhost_user_iotlb_rd_unlock(vq);
+	vhost_rwlock_read_unlock(&vq->iotlb_lock);
 
 out_access_unlock:
 	vhost_spinlock_unlock(&vq->access_lock);
@@ -2697,6 +2714,7 @@ 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)
 	VHOST_SPINLOCK_REQUIRES(vq->access_lock)
+	VHOST_RDLOCK_REQUIRES(vq->iotlb_lock)
 {
 	uint16_t i;
 	uint16_t free_entries;
@@ -2793,6 +2811,7 @@ 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)
 	VHOST_SPINLOCK_REQUIRES(vq->access_lock)
+	VHOST_RDLOCK_REQUIRES(vq->iotlb_lock)
 {
 	return virtio_dev_tx_split(dev, vq, mbuf_pool, pkts, count, true);
 }
@@ -2803,6 +2822,7 @@ 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)
 	VHOST_SPINLOCK_REQUIRES(vq->access_lock)
+	VHOST_RDLOCK_REQUIRES(vq->iotlb_lock)
 {
 	return virtio_dev_tx_split(dev, vq, mbuf_pool, pkts, count, false);
 }
@@ -2814,6 +2834,7 @@ vhost_reserve_avail_batch_packed(struct virtio_net *dev,
 				 uint16_t avail_idx,
 				 uintptr_t *desc_addrs,
 				 uint16_t *ids)
+	VHOST_RDLOCK_REQUIRES(vq->iotlb_lock)
 {
 	bool wrap = vq->avail_wrap_counter;
 	struct vring_packed_desc *descs = vq->desc_packed;
@@ -2883,6 +2904,7 @@ virtio_dev_tx_batch_packed(struct virtio_net *dev,
 			   struct vhost_virtqueue *vq,
 			   struct rte_mbuf **pkts,
 			   bool legacy_ol_flags)
+	VHOST_RDLOCK_REQUIRES(vq->iotlb_lock)
 {
 	uint16_t avail_idx = vq->last_avail_idx;
 	uint32_t buf_offset = sizeof(struct virtio_net_hdr_mrg_rxbuf);
@@ -2929,6 +2951,7 @@ vhost_dequeue_single_packed(struct virtio_net *dev,
 			    uint16_t *buf_id,
 			    uint16_t *desc_count,
 			    bool legacy_ol_flags)
+	VHOST_RDLOCK_REQUIRES(vq->iotlb_lock)
 {
 	struct buf_vector buf_vec[BUF_VECTOR_MAX];
 	uint32_t buf_len;
@@ -2972,6 +2995,7 @@ virtio_dev_tx_single_packed(struct virtio_net *dev,
 			    struct rte_mempool *mbuf_pool,
 			    struct rte_mbuf *pkts,
 			    bool legacy_ol_flags)
+	VHOST_RDLOCK_REQUIRES(vq->iotlb_lock)
 {
 
 	uint16_t buf_id, desc_count = 0;
@@ -3003,6 +3027,7 @@ virtio_dev_tx_packed(struct virtio_net *dev,
 		     uint32_t count,
 		     bool legacy_ol_flags)
 	VHOST_SPINLOCK_REQUIRES(vq->access_lock)
+	VHOST_RDLOCK_REQUIRES(vq->iotlb_lock)
 {
 	uint32_t pkt_idx = 0;
 
@@ -3047,6 +3072,7 @@ 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)
 	VHOST_SPINLOCK_REQUIRES(vq->access_lock)
+	VHOST_RDLOCK_REQUIRES(vq->iotlb_lock)
 {
 	return virtio_dev_tx_packed(dev, vq, mbuf_pool, pkts, count, true);
 }
@@ -3057,6 +3083,7 @@ 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)
 	VHOST_SPINLOCK_REQUIRES(vq->access_lock)
+	VHOST_RDLOCK_REQUIRES(vq->iotlb_lock)
 {
 	return virtio_dev_tx_packed(dev, vq, mbuf_pool, pkts, count, false);
 }
@@ -3096,8 +3123,7 @@ rte_vhost_dequeue_burst(int vid, uint16_t queue_id,
 		goto out_access_unlock;
 	}
 
-	if (dev->features & (1ULL << VIRTIO_F_IOMMU_PLATFORM))
-		vhost_user_iotlb_rd_lock(vq);
+	vhost_rwlock_read_lock(&vq->iotlb_lock);
 
 	if (unlikely(!vq->access_ok))
 		if (unlikely(vring_translate(dev, vq) < 0)) {
@@ -3153,8 +3179,7 @@ rte_vhost_dequeue_burst(int vid, uint16_t queue_id,
 	}
 
 out:
-	if (dev->features & (1ULL << VIRTIO_F_IOMMU_PLATFORM))
-		vhost_user_iotlb_rd_unlock(vq);
+	vhost_rwlock_read_unlock(&vq->iotlb_lock);
 
 out_access_unlock:
 	vhost_spinlock_unlock(&vq->access_lock);
-- 
2.23.0