vhost-vdpa: add support for svq asid

Signed-off-by: Si-Wei Liu <si-wei.liu@oracle.com>

hw/virtio/vhost-shadow-virtqueue.c

@@ -136,7 +136,7 @@ static bool vhost_svq_translate_addr(const VhostShadowVirtqueue *svq,
  * Return true if success, false otherwise and print error.
  */
 static bool vhost_svq_vring_write_descs(VhostShadowVirtqueue *svq, hwaddr *sg,
-                                        const struct iovec *iovec, size_t num,
+                                        const struct iovec *iovec, hwaddr *addr, size_t num,
                                         bool more_descs, bool write)
 {
     uint16_t i = svq->free_head, last = svq->free_head;
@@ -149,8 +149,15 @@ static bool vhost_svq_vring_write_descs(VhostShadowVirtqueue *svq, hwaddr *sg,
         return true;
     }
 
-    ok = vhost_svq_translate_addr(svq, sg, iovec, num);
-    if (unlikely(!ok)) {
+    if (svq->iova_tree) {
+        ok = vhost_svq_translate_addr(svq, sg, iovec, num);
+        if (unlikely(!ok)) {
+            return false;
+        }
+    } else if (!addr) {
+        qemu_log_mask(LOG_GUEST_ERROR,
+                      "No translation found for vaddr 0x%p\n",
+                      iovec[0].iov_base);
         return false;
     }
 
@@ -161,7 +168,7 @@ static bool vhost_svq_vring_write_descs(VhostShadowVirtqueue *svq, hwaddr *sg,
         } else {
             descs[i].flags = flags;
         }
-        descs[i].addr = cpu_to_le64(sg[n]);
+        descs[i].addr = cpu_to_le64(svq->iova_tree ? sg[n] : addr[n]);
         descs[i].len = cpu_to_le32(iovec[n].iov_len);
 
         last = i;
@@ -173,8 +180,8 @@ static bool vhost_svq_vring_write_descs(VhostShadowVirtqueue *svq, hwaddr *sg,
 }
 
 static bool vhost_svq_add_split(VhostShadowVirtqueue *svq,
-                                const struct iovec *out_sg, size_t out_num,
-                                const struct iovec *in_sg, size_t in_num,
+                                const struct iovec *out_sg, hwaddr *out_addr, size_t out_num,
+                                const struct iovec *in_sg, hwaddr *in_addr, size_t in_num,
                                 unsigned *head)
 {
     unsigned avail_idx;
@@ -191,13 +198,13 @@ static bool vhost_svq_add_split(VhostShadowVirtqueue *svq,
         return false;
     }
 
-    ok = vhost_svq_vring_write_descs(svq, sgs, out_sg, out_num, in_num > 0,
+    ok = vhost_svq_vring_write_descs(svq, sgs, out_sg, out_addr, out_num, in_num > 0,
                                      false);
     if (unlikely(!ok)) {
         return false;
     }
 
-    ok = vhost_svq_vring_write_descs(svq, sgs, in_sg, in_num, false, true);
+    ok = vhost_svq_vring_write_descs(svq, sgs, in_sg, in_addr, in_num, false, true);
     if (unlikely(!ok)) {
         return false;
     }
@@ -258,7 +265,8 @@ int vhost_svq_add(VhostShadowVirtqueue *svq, const struct iovec *out_sg,
         return -ENOSPC;
     }
 
-    ok = vhost_svq_add_split(svq, out_sg, out_num, in_sg, in_num, &qemu_head);
+    ok = vhost_svq_add_split(svq, out_sg, elem ? elem->out_addr : NULL, out_num,
+                             in_sg, elem ? elem->in_addr : NULL, in_num, &qemu_head);
     if (unlikely(!ok)) {
         return -EINVAL;
     }

hw/virtio/vhost-vdpa.c

@@ -1210,7 +1210,8 @@ static bool vhost_vdpa_svqs_start(struct vhost_dev *dev)
             goto err;
         }
 
-        vhost_svq_start(svq, dev->vdev, vq, v->iova_tree);
+        vhost_svq_start(svq, dev->vdev, vq,
+                        v->desc_group >= 0 && v->address_space_id ? NULL : v->iova_tree);
         ok = vhost_vdpa_svq_map_rings(dev, svq, &addr, &err);
         if (unlikely(!ok)) {
             goto err_map;

include/hw/virtio/vhost-vdpa.h

@@ -49,6 +49,7 @@ typedef struct vhost_vdpa {
     GPtrArray *shadow_vqs;
     const VhostShadowVirtqueueOps *shadow_vq_ops;
     void *shadow_vq_ops_opaque;
+    int64_t desc_group;
     struct vhost_dev *dev;
     Error *migration_blocker;
     VhostVDPAHostNotifier notifier[VIRTIO_QUEUE_MAX];

include/standard-headers/linux/vhost_types.h

@@ -181,5 +181,10 @@ struct vhost_vdpa_iova_range {
 #define VHOST_BACKEND_F_SUSPEND  0x4
 /* Device can be resumed */
 #define VHOST_BACKEND_F_RESUME  0x5
+/* Device may expose the descriptor table, avail and used ring in a
+ * different group for ASID binding than the buffers it contains.
+ * Requires VHOST_BACKEND_F_IOTLB_ASID.
+ */
+#define VHOST_BACKEND_F_DESC_ASID    0x6
 
 #endif

linux-headers/linux/vhost.h

@@ -219,4 +219,13 @@
  */
 #define VHOST_VDPA_RESUME		_IO(VHOST_VIRTIO, 0x7E)
 
+/* Get the dedicated group for the descriptor table of a virtqueue:
+ * read index, write group in num.
+ * The virtqueue index is stored in the index field of vhost_vring_state.
+ * The group id for the descriptor table of this specific virtqueue
+ * is returned via num field of vhost_vring_state.
+ */
+#define VHOST_VDPA_GET_VRING_DESC_GROUP	_IOWR(VHOST_VIRTIO, 0x7F,	\
+					      struct vhost_vring_state)
+
 #endif

net/trace-events

@@ -23,3 +23,6 @@ colo_compare_tcp_info(const char *pkt, uint32_t seq, uint32_t ack, int hdlen, in
 # filter-rewriter.c
 colo_filter_rewriter_pkt_info(const char *func, const char *src, const char *dst, uint32_t seq, uint32_t ack, uint32_t flag) "%s: src/dst: %s/%s p: seq/ack=%u/%u  flags=0x%x"
 colo_filter_rewriter_conn_offset(uint32_t offset) ": offset=%u"
+
+# vhost-vdpa.c
+vhost_vdpa_set_address_space_id(void *v, unsigned vq_group, unsigned asid_num) "vhost_vdpa: %p vq_group: %u asid: %u"