[dpdk-dev] [PATCH v2 2/9] vhost: provide helpers for virtio ring relay

[Xiao Wang]

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

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

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

The next patch will leverage these two helpers.

Signed-off-by: Xiao Wang <xiao.w.wang at intel.com>
---
v2:
* Make the vring relay API parameter as "void *" to accomodate the future
  potential new ring layout, e.g. packed ring.
* Add parameter check for the new API.
* Add memory barrier for ring idx update.
* Remove the used ring logging in the relay.
* Some comment fix and code cleaning according to Tiwei's comment.
---
 lib/librte_vhost/rte_vdpa.h            |  38 +++++++
 lib/librte_vhost/rte_vhost_version.map |   2 +
 lib/librte_vhost/vdpa.c                | 187 +++++++++++++++++++++++++++++++++
 lib/librte_vhost/vhost.h               |  40 +++++++
 lib/librte_vhost/virtio_net.c          |  39 -------
 5 files changed, 267 insertions(+), 39 deletions(-)

diff --git a/lib/librte_vhost/rte_vdpa.h b/lib/librte_vhost/rte_vdpa.h
index fff657391..265250939 100644
--- a/lib/librte_vhost/rte_vdpa.h
+++ b/lib/librte_vhost/rte_vdpa.h
@@ -173,4 +173,42 @@ 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 mediate ring, help to
+ * check desc validity to protect against malicious guest driver.
+ *
+ * @param vid
+ *  vhost device id
+ * @param qid
+ *  vhost queue id
+ * @param m_vring
+ *  mediate virtio ring pointer
+ * @return
+ *  number of synced available entries on success, -1 on failure
+ */
+int __rte_experimental
+rte_vdpa_relay_avail_ring(int vid, uint16_t qid, void *m_vring);
+
+/**
+ * @warning
+ * @b EXPERIMENTAL: this API may change without prior notice
+ *
+ * Synchronize the used ring from mediate ring to guest, log dirty
+ * page for each Rx buffer used.
+ *
+ * @param vid
+ *  vhost device id
+ * @param qid
+ *  vhost queue id
+ * @param m_vring
+ *  mediate virtio ring pointer
+ * @return
+ *  number of synced used entries on success, -1 on failure
+ */
+int __rte_experimental
+rte_vdpa_relay_used_ring(int vid, uint16_t qid, void *m_vring);
 #endif /* _RTE_VDPA_H_ */
diff --git a/lib/librte_vhost/rte_vhost_version.map b/lib/librte_vhost/rte_vhost_version.map
index 22302e972..0ad0fbea2 100644
--- a/lib/librte_vhost/rte_vhost_version.map
+++ b/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_avail_ring;
+	rte_vdpa_relay_used_ring;
 };
diff --git a/lib/librte_vhost/vdpa.c b/lib/librte_vhost/vdpa.c
index e7d849ee0..16193cfc0 100644
--- a/lib/librte_vhost/vdpa.c
+++ b/lib/librte_vhost/vdpa.c
@@ -122,3 +122,190 @@ 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_vdpa_relay_avail_ring(int vid, uint16_t qid, void *m_vring)
+{
+	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;
+
+	if (!dev || !m_vring)
+		return -1;
+
+	if (qid >= dev->nr_vring)
+		return -1;
+
+	if (vq_is_packed(dev))
+		return -1;
+
+	s_vring = (struct vring *)m_vring;
+	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];
+			if (invalid_desc_check(dev, vq, desc.addr, desc.len,
+						VHOST_ACCESS_RW)) {
+				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_vdpa_relay_used_ring(int vid, uint16_t qid, void *m_vring)
+{
+	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 || !m_vring)
+		return -1;
+
+	if (qid >= dev->nr_vring)
+		return -1;
+
+	if (vq_is_packed(dev))
+		return -1;
+
+	s_vring = (struct vring *)m_vring;
+	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;
+}
diff --git a/lib/librte_vhost/vhost.h b/lib/librte_vhost/vhost.h
index 5218f1b12..2164cd6d9 100644
--- a/lib/librte_vhost/vhost.h
+++ b/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"
@@ -753,4 +754,43 @@ 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_ */
diff --git a/lib/librte_vhost/virtio_net.c b/lib/librte_vhost/virtio_net.c
index 5e1a1a727..8c657a101 100644
--- a/lib/librte_vhost/virtio_net.c
+++ b/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,
-- 
2.15.1