[RFC PATCH v5 21/23] vhost: Make possible to check for device exclusive vq group

["Eugenio Pérez" <eperezma@redhat.com>]

CVQ needs to be in its own group, not shared with any data vq. Enable
the checking of it here, before introducing address space id concepts.

Signed-off-by: Eugenio Pérez <eperezma@redhat.com>
---
 include/hw/virtio/vhost.h |  2 +
 hw/net/vhost_net.c        |  4 +-
 hw/virtio/vhost-vdpa.c    | 79 ++++++++++++++++++++++++++++++++++++++-
 hw/virtio/trace-events    |  1 +
 4 files changed, 84 insertions(+), 2 deletions(-)

diff --git a/include/hw/virtio/vhost.h b/include/hw/virtio/vhost.h
index 58a73e7b7a..034868fa9e 100644
--- a/include/hw/virtio/vhost.h
+++ b/include/hw/virtio/vhost.h
@@ -78,6 +78,8 @@ struct vhost_dev {
     int vq_index_end;
     /* if non-zero, minimum required value for max_queues */
     int num_queues;
+    /* Must be a vq group different than any other vhost dev */
+    bool independent_vq_group;
     uint64_t features;
     uint64_t acked_features;
     uint64_t backend_features;
diff --git a/hw/net/vhost_net.c b/hw/net/vhost_net.c
index 44a105ec29..10480e19e5 100644
--- a/hw/net/vhost_net.c
+++ b/hw/net/vhost_net.c
@@ -343,14 +343,16 @@ int vhost_net_start(VirtIODevice *dev, NetClientState *ncs,
     }
 
     for (i = 0; i < nvhosts; i++) {
+        bool cvq_idx = i >= data_queue_pairs;
 
-        if (i < data_queue_pairs) {
+        if (!cvq_idx) {
             peer = qemu_get_peer(ncs, i);
         } else { /* Control Virtqueue */
             peer = qemu_get_peer(ncs, n->max_queue_pairs);
         }
 
         net = get_vhost_net(peer);
+        net->dev.independent_vq_group = !!cvq_idx;
         vhost_net_set_vq_index(net, i * 2, index_end);
 
         /* Suppress the masking guest notifiers on vhost user
diff --git a/hw/virtio/vhost-vdpa.c b/hw/virtio/vhost-vdpa.c
index d09e06d212..dfff94d46f 100644
--- a/hw/virtio/vhost-vdpa.c
+++ b/hw/virtio/vhost-vdpa.c
@@ -677,7 +677,8 @@ static int vhost_vdpa_set_backend_cap(struct vhost_dev *dev)
 {
     uint64_t features;
     uint64_t f = 0x1ULL << VHOST_BACKEND_F_IOTLB_MSG_V2 |
-        0x1ULL << VHOST_BACKEND_F_IOTLB_BATCH;
+        0x1ULL << VHOST_BACKEND_F_IOTLB_BATCH |
+        0x1ULL << VHOST_BACKEND_F_IOTLB_ASID;
     int r;
 
     if (vhost_vdpa_call(dev, VHOST_GET_BACKEND_FEATURES, &features)) {
@@ -1097,6 +1098,78 @@ static bool vhost_vdpa_svqs_stop(struct vhost_dev *dev)
     return true;
 }
 
+static int vhost_vdpa_get_vring_group(struct vhost_dev *dev,
+                                      struct vhost_vring_state *state)
+{
+    int ret = vhost_vdpa_call(dev, VHOST_VDPA_GET_VRING_GROUP, state);
+    trace_vhost_vdpa_get_vring_group(dev, state->index, state->num);
+    return ret;
+}
+
+static bool vhost_dev_is_independent_group(struct vhost_dev *dev)
+{
+    struct vhost_vdpa *v = dev->opaque;
+    struct vhost_vring_state this_vq_group = {
+        .index = dev->vq_index,
+    };
+    int ret;
+
+    if (!(dev->backend_cap & VHOST_BACKEND_F_IOTLB_ASID)) {
+        return true;
+    }
+
+    if (!v->shadow_vqs_enabled) {
+        return true;
+    }
+
+    ret = vhost_vdpa_get_vring_group(dev, &this_vq_group);
+    if (unlikely(ret)) {
+        goto call_err;
+    }
+
+    for (int i = 1; i < dev->nvqs; ++i) {
+        struct vhost_vring_state vq_group = {
+            .index = dev->vq_index + i,
+        };
+
+        ret = vhost_vdpa_get_vring_group(dev, &vq_group);
+        if (unlikely(ret)) {
+            goto call_err;
+        }
+        if (unlikely(vq_group.num != this_vq_group.num)) {
+            error_report("VQ %d group is different than VQ %d one",
+                         this_vq_group.index, vq_group.index);
+            return false;
+        }
+    }
+
+    for (int i = 0; i < dev->vq_index_end; ++i) {
+        struct vhost_vring_state vq_group = {
+            .index = i,
+        };
+
+        if (dev->vq_index <= i && i < dev->vq_index + dev->nvqs) {
+            continue;
+        }
+
+        ret = vhost_vdpa_get_vring_group(dev, &vq_group);
+        if (unlikely(ret)) {
+            goto call_err;
+        }
+        if (unlikely(vq_group.num == this_vq_group.num)) {
+            error_report("VQ %d group is the same as VQ %d one",
+                         this_vq_group.index, vq_group.index);
+            return false;
+        }
+    }
+
+    return true;
+
+call_err:
+    error_report("Can't read vq group, errno=%d (%s)", ret, g_strerror(-ret));
+    return false;
+}
+
 static int vhost_vdpa_dev_start(struct vhost_dev *dev, bool started)
 {
     struct vhost_vdpa *v = dev->opaque;
@@ -1105,6 +1178,10 @@ static int vhost_vdpa_dev_start(struct vhost_dev *dev, bool started)
 
     if (started) {
         vhost_vdpa_host_notifiers_init(dev);
+        if (dev->independent_vq_group &&
+            !vhost_dev_is_independent_group(dev)) {
+            return -1;
+        }
         ok = vhost_vdpa_svqs_start(dev);
         if (unlikely(!ok)) {
             return -1;
diff --git a/hw/virtio/trace-events b/hw/virtio/trace-events
index 333348d9d5..e6fdc03514 100644
--- a/hw/virtio/trace-events
+++ b/hw/virtio/trace-events
@@ -43,6 +43,7 @@ vhost_vdpa_set_vring_ready(void *dev) "dev: %p"
 vhost_vdpa_dump_config(void *dev, const char *line) "dev: %p %s"
 vhost_vdpa_set_config(void *dev, uint32_t offset, uint32_t size, uint32_t flags) "dev: %p offset: %"PRIu32" size: %"PRIu32" flags: 0x%"PRIx32
 vhost_vdpa_get_config(void *dev, void *config, uint32_t config_len) "dev: %p config: %p config_len: %"PRIu32
+vhost_vdpa_get_vring_group(void *dev, unsigned int index, unsigned int num) "dev: %p index: %u num: %u"
 vhost_vdpa_dev_start(void *dev, bool started) "dev: %p started: %d"
 vhost_vdpa_set_log_base(void *dev, uint64_t base, unsigned long long size, int refcnt, int fd, void *log) "dev: %p base: 0x%"PRIx64" size: %llu refcnt: %d fd: %d log: %p"
 vhost_vdpa_set_vring_addr(void *dev, unsigned int index, unsigned int flags, uint64_t desc_user_addr, uint64_t used_user_addr, uint64_t avail_user_addr, uint64_t log_guest_addr) "dev: %p index: %u flags: 0x%x desc_user_addr: 0x%"PRIx64" used_user_addr: 0x%"PRIx64" avail_user_addr: 0x%"PRIx64" log_guest_addr: 0x%"PRIx64
-- 
2.27.0