vhost: provide helpers for virtio ring relay

This patch provides two helpers for vdpa device driver to perform a
relay between the guest virtio ring and a mediated virtio ring.

The available ring relay will synchronize the available entries, and
help to do desc validity checking.

The used ring relay will synchronize the used entries from mediated ring
to guest ring, and help to do dirty page logging for live migration.

The later patch will leverage these two helpers.

Signed-off-by: Xiao Wang <xiao.w.wang@intel.com>
Reviewed-by: Maxime Coquelin <maxime.coquelin@redhat.com>

lib/librte_vhost/rte_vdpa.h

@@ -173,4 +173,43 @@ rte_vdpa_get_device_num(void);
  */
 int __rte_experimental
 rte_vhost_host_notifier_ctrl(int vid, bool enable);
+
+/**
+ * @warning
+ * @b EXPERIMENTAL: this API may change without prior notice
+ *
+ * Synchronize the available ring from guest to mediated ring, help to
+ * check desc validity to protect against malicious guest driver.
+ *
+ * @param vid
+ *  vhost device id
+ * @param qid
+ *  vhost queue id
+ * @param vring_m
+ *  mediated virtio ring pointer
+ * @return
+ *  number of synced available entries on success, -1 on failure
+ */
+int __rte_experimental
+rte_vdpa_relay_vring_avail(int vid, uint16_t qid, void *vring_m);
+
+/**
+ * @warning
+ * @b EXPERIMENTAL: this API may change without prior notice
+ *
+ * Synchronize the used ring from mediated ring to guest, log dirty
+ * page for each writeable buffer, caller should handle the used
+ * ring logging before device stop.
+ *
+ * @param vid
+ *  vhost device id
+ * @param qid
+ *  vhost queue id
+ * @param vring_m
+ *  mediated virtio ring pointer
+ * @return
+ *  number of synced used entries on success, -1 on failure
+ */
+int __rte_experimental
+rte_vdpa_relay_vring_used(int vid, uint16_t qid, void *vring_m);
 #endif /* _RTE_VDPA_H_ */

lib/librte_vhost/rte_vhost_version.map

@@ -84,4 +84,6 @@ EXPERIMENTAL {
 	rte_vhost_crypto_set_zero_copy;
 	rte_vhost_va_from_guest_pa;
 	rte_vhost_host_notifier_ctrl;
+	rte_vdpa_relay_vring_avail;
+	rte_vdpa_relay_vring_used;
 };

lib/librte_vhost/vdpa.c

@@ -122,3 +122,197 @@ rte_vdpa_get_device_num(void)
 {
 	return vdpa_device_num;
 }
+
+static bool
+invalid_desc_check(struct virtio_net *dev, struct vhost_virtqueue *vq,
+		uint64_t desc_iova, uint64_t desc_len, uint8_t perm)
+{
+	uint64_t desc_addr, desc_chunck_len;
+
+	while (desc_len) {
+		desc_chunck_len = desc_len;
+		desc_addr = vhost_iova_to_vva(dev, vq,
+				desc_iova,
+				&desc_chunck_len,
+				perm);
+
+		if (!desc_addr)
+			return true;
+
+		desc_len -= desc_chunck_len;
+		desc_iova += desc_chunck_len;
+	}
+
+	return false;
+}
+
+int __rte_experimental
+rte_vdpa_relay_vring_avail(int vid, uint16_t qid, void *vring_m)
+{
+	struct virtio_net *dev = get_device(vid);
+	uint16_t idx, idx_m, desc_id;
+	struct vring_desc desc;
+	struct vhost_virtqueue *vq;
+	struct vring_desc *desc_ring;
+	struct vring_desc *idesc = NULL;
+	struct vring *s_vring;
+	uint64_t dlen;
+	int ret;
+	uint8_t perm;
+
+	if (!dev || !vring_m)
+		return -1;
+
+	if (qid >= dev->nr_vring)
+		return -1;
+
+	if (vq_is_packed(dev))
+		return -1;
+
+	s_vring = (struct vring *)vring_m;
+	vq = dev->virtqueue[qid];
+	idx = vq->avail->idx;
+	idx_m = s_vring->avail->idx;
+	ret = (uint16_t)(idx - idx_m);
+
+	while (idx_m != idx) {
+		/* avail entry copy */
+		desc_id = vq->avail->ring[idx_m & (vq->size - 1)];
+		s_vring->avail->ring[idx_m & (vq->size - 1)] = desc_id;
+		desc_ring = vq->desc;
+
+		if (vq->desc[desc_id].flags & VRING_DESC_F_INDIRECT) {
+			dlen = vq->desc[desc_id].len;
+			desc_ring = (struct vring_desc *)(uintptr_t)
+				vhost_iova_to_vva(dev, vq,
+						vq->desc[desc_id].addr, &dlen,
+						VHOST_ACCESS_RO);
+			if (unlikely(!desc_ring))
+				return -1;
+
+			if (unlikely(dlen < vq->desc[idx].len)) {
+				idesc = alloc_copy_ind_table(dev, vq,
+						vq->desc[idx].addr,
+						vq->desc[idx].len);
+				if (unlikely(!idesc))
+					return -1;
+
+				desc_ring = idesc;
+			}
+
+			desc_id = 0;
+		}
+
+		/* check if the buf addr is within the guest memory */
+		do {
+			desc = desc_ring[desc_id];
+			perm = desc.flags & VRING_DESC_F_WRITE ?
+				VHOST_ACCESS_WO : VHOST_ACCESS_RO;
+			if (invalid_desc_check(dev, vq, desc.addr, desc.len,
+						perm)) {
+				if (unlikely(idesc))
+					free_ind_table(idesc);
+				return -1;
+			}
+			desc_id = desc.next;
+		} while (desc.flags & VRING_DESC_F_NEXT);
+
+		if (unlikely(idesc)) {
+			free_ind_table(idesc);
+			idesc = NULL;
+		}
+
+		idx_m++;
+	}
+
+	rte_smp_wmb();
+	s_vring->avail->idx = idx;
+
+	if (dev->features & (1ULL << VIRTIO_RING_F_EVENT_IDX))
+		vhost_avail_event(vq) = idx;
+
+	return ret;
+}
+
+int __rte_experimental
+rte_vdpa_relay_vring_used(int vid, uint16_t qid, void *vring_m)
+{
+	struct virtio_net *dev = get_device(vid);
+	uint16_t idx, idx_m, desc_id;
+	struct vhost_virtqueue *vq;
+	struct vring_desc desc;
+	struct vring_desc *desc_ring;
+	struct vring_desc *idesc = NULL;
+	struct vring *s_vring;
+	uint64_t dlen;
+	int ret;
+
+	if (!dev || !vring_m)
+		return -1;
+
+	if (qid >= dev->nr_vring)
+		return -1;
+
+	if (vq_is_packed(dev))
+		return -1;
+
+	s_vring = (struct vring *)vring_m;
+	vq = dev->virtqueue[qid];
+	idx = vq->used->idx;
+	idx_m = s_vring->used->idx;
+	ret = (uint16_t)(idx_m - idx);
+
+	while (idx != idx_m) {
+		/* copy used entry, used ring logging is not covered here */
+		vq->used->ring[idx & (vq->size - 1)] =
+			s_vring->used->ring[idx & (vq->size - 1)];
+
+		desc_id = vq->used->ring[idx & (vq->size - 1)].id;
+		desc_ring = vq->desc;
+
+		if (vq->desc[desc_id].flags & VRING_DESC_F_INDIRECT) {
+			dlen = vq->desc[desc_id].len;
+			desc_ring = (struct vring_desc *)(uintptr_t)
+				vhost_iova_to_vva(dev, vq,
+						vq->desc[desc_id].addr, &dlen,
+						VHOST_ACCESS_RO);
+			if (unlikely(!desc_ring))
+				return -1;
+
+			if (unlikely(dlen < vq->desc[idx].len)) {
+				idesc = alloc_copy_ind_table(dev, vq,
+						vq->desc[idx].addr,
+						vq->desc[idx].len);
+				if (unlikely(!idesc))
+					return -1;
+
+				desc_ring = idesc;
+			}
+
+			desc_id = 0;
+		}
+
+		/* dirty page logging for DMA writeable buffer */
+		do {
+			desc = desc_ring[desc_id];
+			if (desc.flags & VRING_DESC_F_WRITE)
+				vhost_log_write(dev, desc.addr, desc.len);
+			desc_id = desc.next;
+		} while (desc.flags & VRING_DESC_F_NEXT);
+
+		if (unlikely(idesc)) {
+			free_ind_table(idesc);
+			idesc = NULL;
+		}
+
+		idx++;
+	}
+
+	rte_smp_wmb();
+	vq->used->idx = idx_m;
+
+	if (dev->features & (1ULL << VIRTIO_RING_F_EVENT_IDX))
+		vring_used_event(s_vring) = idx_m;
+
+	return ret;
+}

lib/librte_vhost/vhost.h

@@ -18,6 +18,7 @@
 #include <rte_log.h>
 #include <rte_ether.h>
 #include <rte_rwlock.h>
+#include <rte_malloc.h>
 
 #include "rte_vhost.h"
 #include "rte_vdpa.h"
@@ -754,4 +755,43 @@ vhost_vring_call_packed(struct virtio_net *dev, struct vhost_virtqueue *vq)
 		eventfd_write(vq->callfd, (eventfd_t)1);
 }
 
+static __rte_always_inline void *
+alloc_copy_ind_table(struct virtio_net *dev, struct vhost_virtqueue *vq,
+		uint64_t desc_addr, uint64_t desc_len)
+{
+	void *idesc;
+	uint64_t src, dst;
+	uint64_t len, remain = desc_len;
+
+	idesc = rte_malloc(__func__, desc_len, 0);
+	if (unlikely(!idesc))
+		return 0;
+
+	dst = (uint64_t)(uintptr_t)idesc;
+
+	while (remain) {
+		len = remain;
+		src = vhost_iova_to_vva(dev, vq, desc_addr, &len,
+				VHOST_ACCESS_RO);
+		if (unlikely(!src || !len)) {
+			rte_free(idesc);
+			return 0;
+		}
+
+		rte_memcpy((void *)(uintptr_t)dst, (void *)(uintptr_t)src, len);
+
+		remain -= len;
+		dst += len;
+		desc_addr += len;
+	}
+
+	return idesc;
+}
+
+static __rte_always_inline void
+free_ind_table(void *idesc)
+{
+	rte_free(idesc);
+}
+
 #endif /* _VHOST_NET_CDEV_H_ */

lib/librte_vhost/virtio_net.c

@@ -37,45 +37,6 @@ is_valid_virt_queue_idx(uint32_t idx, int is_tx, uint32_t nr_vring)
 	return (is_tx ^ (idx & 1)) == 0 && idx < nr_vring;
 }
 
-static __rte_always_inline void *
-alloc_copy_ind_table(struct virtio_net *dev, struct vhost_virtqueue *vq,
-		uint64_t desc_addr, uint64_t desc_len)
-{
-	void *idesc;
-	uint64_t src, dst;
-	uint64_t len, remain = desc_len;
-
-	idesc = rte_malloc(__func__, desc_len, 0);
-	if (unlikely(!idesc))
-		return 0;
-
-	dst = (uint64_t)(uintptr_t)idesc;
-
-	while (remain) {
-		len = remain;
-		src = vhost_iova_to_vva(dev, vq, desc_addr, &len,
-				VHOST_ACCESS_RO);
-		if (unlikely(!src || !len)) {
-			rte_free(idesc);
-			return 0;
-		}
-
-		rte_memcpy((void *)(uintptr_t)dst, (void *)(uintptr_t)src, len);
-
-		remain -= len;
-		dst += len;
-		desc_addr += len;
-	}
-
-	return idesc;
-}
-
-static __rte_always_inline void
-free_ind_table(void *idesc)
-{
-	rte_free(idesc);
-}
-
 static __rte_always_inline void
 do_flush_shadow_used_ring_split(struct virtio_net *dev,
 			struct vhost_virtqueue *vq,