vdpa: move iova tree to the shared struct

Next patches will register the vhost_vdpa memory listener while the VM
is migrating at the destination, so we can map the memory to the device
before stopping the VM at the source.  The main goal is to reduce the
downtime.

However, the destination QEMU is unaware of which vhost_vdpa device will
register its memory_listener.  If the source guest has CVQ enabled, it
will be the CVQ device.  Otherwise, it  will be the first one.

Move the iova tree to VhostVDPAShared so all vhost_vdpa can use it,
rather than always in the first or last vhost_vdpa.

Signed-off-by: Eugenio Pérez <eperezma@redhat.com>
Acked-by: Jason Wang <jasowang@redhat.com>
Message-Id: <20231221174322.3130442-3-eperezma@redhat.com>
Tested-by: Lei Yang <leiyang@redhat.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>

diff --git a/hw/virtio/vhost-vdpa.c b/hw/virtio/vhost-vdpa.c
index 401dfa96fd2c4228a2fe41eedcc913dfee08bdf8..95a179a0829368c23643295c6a9d3a5dd350f778 100644 (file)
--- a/hw/virtio/vhost-vdpa.c
+++ b/hw/virtio/vhost-vdpa.c
@@ -358,7 +358,7 @@ static void vhost_vdpa_listener_region_add(MemoryListener *listener,
         mem_region.size = int128_get64(llsize) - 1,
         mem_region.perm = IOMMU_ACCESS_FLAG(true, section->readonly),
 
-        r = vhost_iova_tree_map_alloc(v->iova_tree, &mem_region);
+        r = vhost_iova_tree_map_alloc(v->shared->iova_tree, &mem_region);
         if (unlikely(r != IOVA_OK)) {
             error_report("Can't allocate a mapping (%d)", r);
             goto fail;
@@ -379,7 +379,7 @@ static void vhost_vdpa_listener_region_add(MemoryListener *listener,
 
 fail_map:
     if (v->shadow_data) {
-        vhost_iova_tree_remove(v->iova_tree, mem_region);
+        vhost_iova_tree_remove(v->shared->iova_tree, mem_region);
     }
 
 fail:
@@ -441,13 +441,13 @@ static void vhost_vdpa_listener_region_del(MemoryListener *listener,
             .size = int128_get64(llsize) - 1,
         };
 
-        result = vhost_iova_tree_find_iova(v->iova_tree, &mem_region);
+        result = vhost_iova_tree_find_iova(v->shared->iova_tree, &mem_region);
         if (!result) {
             /* The memory listener map wasn't mapped */
             return;
         }
         iova = result->iova;
-        vhost_iova_tree_remove(v->iova_tree, *result);
+        vhost_iova_tree_remove(v->shared->iova_tree, *result);
     }
     vhost_vdpa_iotlb_batch_begin_once(v);
     /*
@@ -1063,7 +1063,8 @@ static void vhost_vdpa_svq_unmap_ring(struct vhost_vdpa *v, hwaddr addr)
     const DMAMap needle = {
         .translated_addr = addr,
     };
-    const DMAMap *result = vhost_iova_tree_find_iova(v->iova_tree, &needle);
+    const DMAMap *result = vhost_iova_tree_find_iova(v->shared->iova_tree,
+                                                     &needle);
     hwaddr size;
     int r;
 
@@ -1079,7 +1080,7 @@ static void vhost_vdpa_svq_unmap_ring(struct vhost_vdpa *v, hwaddr addr)
         return;
     }
 
-    vhost_iova_tree_remove(v->iova_tree, *result);
+    vhost_iova_tree_remove(v->shared->iova_tree, *result);
 }
 
 static void vhost_vdpa_svq_unmap_rings(struct vhost_dev *dev,
@@ -1107,7 +1108,7 @@ static bool vhost_vdpa_svq_map_ring(struct vhost_vdpa *v, DMAMap *needle,
 {
     int r;
 
-    r = vhost_iova_tree_map_alloc(v->iova_tree, needle);
+    r = vhost_iova_tree_map_alloc(v->shared->iova_tree, needle);
     if (unlikely(r != IOVA_OK)) {
         error_setg(errp, "Cannot allocate iova (%d)", r);
         return false;
@@ -1119,7 +1120,7 @@ static bool vhost_vdpa_svq_map_ring(struct vhost_vdpa *v, DMAMap *needle,
                            needle->perm == IOMMU_RO);
     if (unlikely(r != 0)) {
         error_setg_errno(errp, -r, "Cannot map region to device");
-        vhost_iova_tree_remove(v->iova_tree, *needle);
+        vhost_iova_tree_remove(v->shared->iova_tree, *needle);
     }
 
     return r == 0;
@@ -1220,7 +1221,7 @@ 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->shared->iova_tree);
         ok = vhost_vdpa_svq_map_rings(dev, svq, &addr, &err);
         if (unlikely(!ok)) {
             goto err_map;

diff --git a/include/hw/virtio/vhost-vdpa.h b/include/hw/virtio/vhost-vdpa.h
index eb1a56d75a7c0abfe1fb95986ca54d084ddffad0..ac036055d356cc013b3325d132ab1da348a87d60 100644 (file)
--- a/include/hw/virtio/vhost-vdpa.h
+++ b/include/hw/virtio/vhost-vdpa.h
@@ -32,6 +32,8 @@ typedef struct VhostVDPAHostNotifier {
 
 /* Info shared by all vhost_vdpa device models */
 typedef struct vhost_vdpa_shared {
+    /* IOVA mapping used by the Shadow Virtqueue */
+    VhostIOVATree *iova_tree;
 } VhostVDPAShared;
 
 typedef struct vhost_vdpa {
@@ -48,8 +50,6 @@ typedef struct vhost_vdpa {
     bool shadow_data;
     /* Device suspended successfully */
     bool suspended;
-    /* IOVA mapping used by the Shadow Virtqueue */
-    VhostIOVATree *iova_tree;
     VhostVDPAShared *shared;
     GPtrArray *shadow_vqs;
     const VhostShadowVirtqueueOps *shadow_vq_ops;

diff --git a/net/vhost-vdpa.c b/net/vhost-vdpa.c
index 8b661b9e6d9e728defd65dcc0943e4d185b33a40..10703e5833b5b76ef303c9b2aff7ca74d90d2860 100644 (file)
--- a/net/vhost-vdpa.c
+++ b/net/vhost-vdpa.c
@@ -354,8 +354,8 @@ static void vhost_vdpa_net_data_start_first(VhostVDPAState *s)
     migration_add_notifier(&s->migration_state,
                            vdpa_net_migration_state_notifier);
     if (v->shadow_vqs_enabled) {
-        v->iova_tree = vhost_iova_tree_new(v->iova_range.first,
-                                           v->iova_range.last);
+        v->shared->iova_tree = vhost_iova_tree_new(v->iova_range.first,
+                                                   v->iova_range.last);
     }
 }
 
@@ -380,11 +380,6 @@ static int vhost_vdpa_net_data_start(NetClientState *nc)
         return 0;
     }
 
-    if (v->shadow_vqs_enabled) {
-        VhostVDPAState *s0 = vhost_vdpa_net_first_nc_vdpa(s);
-        v->iova_tree = s0->vhost_vdpa.iova_tree;
-    }
-
     return 0;
 }
 
@@ -417,9 +412,8 @@ static void vhost_vdpa_net_client_stop(NetClientState *nc)
 
     dev = s->vhost_vdpa.dev;
     if (dev->vq_index + dev->nvqs == dev->vq_index_end) {
-        g_clear_pointer(&s->vhost_vdpa.iova_tree, vhost_iova_tree_delete);
-    } else {
-        s->vhost_vdpa.iova_tree = NULL;
+        g_clear_pointer(&s->vhost_vdpa.shared->iova_tree,
+                        vhost_iova_tree_delete);
     }
 }
 
@@ -474,7 +468,7 @@ static int vhost_vdpa_set_address_space_id(struct vhost_vdpa *v,
 
 static void vhost_vdpa_cvq_unmap_buf(struct vhost_vdpa *v, void *addr)
 {
-    VhostIOVATree *tree = v->iova_tree;
+    VhostIOVATree *tree = v->shared->iova_tree;
     DMAMap needle = {
         /*
          * No need to specify size or to look for more translations since
@@ -508,7 +502,7 @@ static int vhost_vdpa_cvq_map_buf(struct vhost_vdpa *v, void *buf, size_t size,
     map.translated_addr = (hwaddr)(uintptr_t)buf;
     map.size = size - 1;
     map.perm = write ? IOMMU_RW : IOMMU_RO,
-    r = vhost_iova_tree_map_alloc(v->iova_tree, &map);
+    r = vhost_iova_tree_map_alloc(v->shared->iova_tree, &map);
     if (unlikely(r != IOVA_OK)) {
         error_report("Cannot map injected element");
         return r;
@@ -523,7 +517,7 @@ static int vhost_vdpa_cvq_map_buf(struct vhost_vdpa *v, void *buf, size_t size,
     return 0;
 
 dma_map_err:
-    vhost_iova_tree_remove(v->iova_tree, map);
+    vhost_iova_tree_remove(v->shared->iova_tree, map);
     return r;
 }
 
@@ -583,24 +577,22 @@ out:
         return 0;
     }
 
-    if (s0->vhost_vdpa.iova_tree) {
-        /*
-         * SVQ is already configured for all virtqueues.  Reuse IOVA tree for
-         * simplicity, whether CVQ shares ASID with guest or not, because:
-         * - Memory listener need access to guest's memory addresses allocated
-         *   in the IOVA tree.
-         * - There should be plenty of IOVA address space for both ASID not to
-         *   worry about collisions between them.  Guest's translations are
-         *   still validated with virtio virtqueue_pop so there is no risk for
-         *   the guest to access memory that it shouldn't.
-         *
-         * To allocate a iova tree per ASID is doable but it complicates the
-         * code and it is not worth it for the moment.
-         */
-        v->iova_tree = s0->vhost_vdpa.iova_tree;
-    } else {
-        v->iova_tree = vhost_iova_tree_new(v->iova_range.first,
-                                           v->iova_range.last);
+    /*
+     * If other vhost_vdpa already have an iova_tree, reuse it for simplicity,
+     * whether CVQ shares ASID with guest or not, because:
+     * - Memory listener need access to guest's memory addresses allocated in
+     *   the IOVA tree.
+     * - There should be plenty of IOVA address space for both ASID not to
+     *   worry about collisions between them.  Guest's translations are still
+     *   validated with virtio virtqueue_pop so there is no risk for the guest
+     *   to access memory that it shouldn't.
+     *
+     * To allocate a iova tree per ASID is doable but it complicates the code
+     * and it is not worth it for the moment.
+     */
+    if (!v->shared->iova_tree) {
+        v->shared->iova_tree = vhost_iova_tree_new(v->iova_range.first,
+                                                   v->iova_range.last);
     }
 
     r = vhost_vdpa_cvq_map_buf(&s->vhost_vdpa, s->cvq_cmd_out_buffer,