Skip to contentSkip to conversation

NIC vhost-vdpa state restore via Shadow CVQ

PATCH Superseded Eugenio Pérez 1 participant 7 messages Jul 22, 2022 Networking

v3 of 10 Superseded Latest is v10 →

lore
Share & tools
lore
#0 lore raw

v3 cover NIC vhost-vdpa state restore via Shadow CVQ

CVQ of net vhost-vdpa devices can be intercepted since the work of [1]. The virtio-net device model is updated. The migration was blocked because although the state can be megrated between VMM it was not possible to restore on the destination NIC.

This series add support for SVQ to inject external messages without the guest's knowledge, so before the guest is resumed all the guest visible state is restored. It is done using standard CVQ messages, so the vhost-vdpa device does not need to learn how to restore it: As long as they have the feature, they know how to handle it.

This series needs fixes [1] and [2] to be applied to achieve full live migration.

Thanks!

[1] https://lists.nongnu.org/archive/html/qemu-devel/2022-07/msg02984.html
[2] https://lists.nongnu.org/archive/html/qemu-devel/2022-07/msg03993.html

v3:
- Route vhost-vdpa start code through NetClientInfo callback.
- Delete extra vhost_net_stop_one() call.

v2:
- Fix SIGSEGV dereferencing SVQ when not in svq mode

v1 from RFC:
- Do not reorder DRIVER_OK & enable patches.
- Delete leftovers

Eugenio Pérez (6):
vhost: stop transfer elem ownership in vhost_handle_guest_kick
vdpa: Extract vhost_vdpa_net_cvq_add from
vhost_vdpa_net_handle_ctrl_avail
vdpa: Make vhost_vdpa_net_cvq_map_elem accept any out sg
vdpa: add NetClientState->start() callback
vdpa: Add virtio-net mac address via CVQ at start
vdpa: Delete CVQ migration blocker

 include/hw/virtio/vhost-vdpa.h     |   1 -
 include/net/net.h                  |   2 +
 include/net/vhost-vdpa.h           |   1 +
 hw/net/vhost_net.c                 |   7 ++
 hw/virtio/vhost-shadow-virtqueue.c |  10 +-
 hw/virtio/vhost-vdpa.c             |  14 ---
 net/vhost-vdpa.c                   | 162 +++++++++++++++++++++--------
 7 files changed, 133 insertions(+), 64 deletions(-)
Signature · 1 line
2.31.1
#1 lore raw

PATCH v3 1/6 vhost: stop transfer elem ownership in vhost_handle_guest_kick

It was easier to allow vhost_svq_add to handle the memory. Now that we will allow qemu to add elements to a SVQ without the guest's knowledge, it's better to handle it in the caller.

---
 hw/virtio/vhost-shadow-virtqueue.c | 10 ++++------
 1 file changed, 4 insertions(+), 6 deletions(-)
hw/virtio/vhost-shadow-virtqueue.c +4 -6
index e4956728dd..ffd2b2c972 100644
@@ -233,9 +233,6 @@ static void vhost_svq_kick(VhostShadowVirtqueue *svq)
 /**
  * Add an element to a SVQ.
  *
- * The caller must check that there is enough slots for the new element. It
- * takes ownership of the element: In case of failure not ENOSPC, it is free.
- *
  * Return -EINVAL if element is invalid, -ENOSPC if dev queue is full
  */
 int vhost_svq_add(VhostShadowVirtqueue *svq, const struct iovec *out_sg,
@@ -252,7 +249,6 @@ int vhost_svq_add(VhostShadowVirtqueue *svq, const struct iovec *out_sg,
 
     ok = vhost_svq_add_split(svq, out_sg, out_num, in_sg, in_num, &qemu_head);
     if (unlikely(!ok)) {
-        g_free(elem);
         return -EINVAL;
     }
 
@@ -293,7 +289,7 @@ static void vhost_handle_guest_kick(VhostShadowVirtqueue *svq)
         virtio_queue_set_notification(svq->vq, false);
 
         while (true) {
-            VirtQueueElement *elem;
+            g_autofree VirtQueueElement *elem;
             int r;
 
             if (svq->next_guest_avail_elem) {
@@ -324,12 +320,14 @@ static void vhost_handle_guest_kick(VhostShadowVirtqueue *svq)
                      * queue the current guest descriptor and ignore kicks
                      * until some elements are used.
                      */
-                    svq->next_guest_avail_elem = elem;
+                    svq->next_guest_avail_elem = g_steal_pointer(&elem);
                 }
 
                 /* VQ is full or broken, just return and ignore kicks */
                 return;
             }
+            /* elem belongs to SVQ or external caller now */
+            elem = NULL;
         }
 
         virtio_queue_set_notification(svq->vq, true);
Signature · 1 line
2.31.1
#2 lore raw

PATCH v3 2/6 vdpa: Extract vhost_vdpa_net_cvq_add from vhost_vdpa_net_handle_ctrl_avail

In reply to Eugenio Pérez

So we can reuse to inject state messages.

---
 net/vhost-vdpa.c | 74 ++++++++++++++++++++++++++++++------------------
 1 file changed, 47 insertions(+), 27 deletions(-)
net/vhost-vdpa.c +47 -27
index 6abad276a6..1b82ac2e07 100644
@@ -334,6 +334,46 @@ static bool vhost_vdpa_net_cvq_map_elem(VhostVDPAState *s,
     return true;
 }
 
+static virtio_net_ctrl_ack vhost_vdpa_net_cvq_add(VhostShadowVirtqueue *svq,
+                                               const struct iovec *dev_buffers)
+{
+    /* in buffer used for device model */
+    virtio_net_ctrl_ack status;
+    size_t dev_written;
+    int r;
+
+    /*
+     * Add a fake non-NULL VirtQueueElement since we'll remove before SVQ
+     * event loop can get it.
+     */
+    r = vhost_svq_add(svq, &dev_buffers[0], 1, &dev_buffers[1], 1, (void *)1);
+    if (unlikely(r != 0)) {
+        if (unlikely(r == -ENOSPC)) {
+            qemu_log_mask(LOG_GUEST_ERROR, "%s: No space on device queue\n",
+                          __func__);
+        }
+        return VIRTIO_NET_ERR;
+    }
+
+    /*
+     * We can poll here since we've had BQL from the time we sent the
+     * descriptor. Also, we need to take the answer before SVQ pulls by itself,
+     * when BQL is released
+     */
+    dev_written = vhost_svq_poll(svq);
+    if (unlikely(dev_written < sizeof(status))) {
+        error_report("Insufficient written data (%zu)", dev_written);
+        return VIRTIO_NET_ERR;
+    }
+
+    memcpy(&status, dev_buffers[1].iov_base, sizeof(status));
+    if (status != VIRTIO_NET_OK) {
+        return VIRTIO_NET_ERR;
+    }
+
+    return VIRTIO_NET_OK;
+}
+
 /**
  * Do not forward commands not supported by SVQ. Otherwise, the device could
  * accept it and qemu would not know how to update the device model.
@@ -380,19 +420,18 @@ static int vhost_vdpa_net_handle_ctrl_avail(VhostShadowVirtqueue *svq,
                                             void *opaque)
 {
     VhostVDPAState *s = opaque;
-    size_t in_len, dev_written;
+    size_t in_len;
     virtio_net_ctrl_ack status = VIRTIO_NET_ERR;
     /* out and in buffers sent to the device */
     struct iovec dev_buffers[2] = {
         { .iov_base = s->cvq_cmd_out_buffer },
         { .iov_base = s->cvq_cmd_in_buffer },
     };
-    /* in buffer used for device model */
+    /* in buffer seen by virtio-net device model */
     const struct iovec in = {
         .iov_base = &status,
         .iov_len = sizeof(status),
     };
-    int r = -EINVAL;
     bool ok;
 
     ok = vhost_vdpa_net_cvq_map_elem(s, elem, dev_buffers);
@@ -405,35 +444,16 @@ static int vhost_vdpa_net_handle_ctrl_avail(VhostShadowVirtqueue *svq,
         goto out;
     }
 
-    r = vhost_svq_add(svq, &dev_buffers[0], 1, &dev_buffers[1], 1, elem);
-    if (unlikely(r != 0)) {
-        if (unlikely(r == -ENOSPC)) {
-            qemu_log_mask(LOG_GUEST_ERROR, "%s: No space on device queue\n",
-                          __func__);
-        }
-        goto out;
-    }
-
-    /*
-     * We can poll here since we've had BQL from the time we sent the
-     * descriptor. Also, we need to take the answer before SVQ pulls by itself,
-     * when BQL is released
-     */
-    dev_written = vhost_svq_poll(svq);
-    if (unlikely(dev_written < sizeof(status))) {
-        error_report("Insufficient written data (%zu)", dev_written);
-        goto out;
-    }
-
-    memcpy(&status, dev_buffers[1].iov_base, sizeof(status));
+    status = vhost_vdpa_net_cvq_add(svq, dev_buffers);
     if (status != VIRTIO_NET_OK) {
         goto out;
     }
 
     status = VIRTIO_NET_ERR;
-    virtio_net_handle_ctrl_iov(svq->vdev, &in, 1, dev_buffers, 1);
-    if (status != VIRTIO_NET_OK) {
+    in_len = virtio_net_handle_ctrl_iov(svq->vdev, &in, 1, dev_buffers, 1);
+    if (in_len != sizeof(status) || status != VIRTIO_NET_OK) {
         error_report("Bad CVQ processing in model");
+        return VIRTIO_NET_ERR;
     }
 
 out:
@@ -450,7 +470,7 @@ out:
     if (dev_buffers[1].iov_base) {
         vhost_vdpa_cvq_unmap_buf(&s->vhost_vdpa, dev_buffers[1].iov_base);
     }
-    return r;
+    return status == VIRTIO_NET_OK ? 0 : 1;
 }
 
 static const VhostShadowVirtqueueOps vhost_vdpa_net_svq_ops = {
Signature · 1 line
2.31.1
#3 lore raw

PATCH v3 3/6 vdpa: Make vhost_vdpa_net_cvq_map_elem accept any out sg

In reply to Eugenio Pérez

So its generic enough to accept any out sg buffer and we can inject NIC state messages.

---
 net/vhost-vdpa.c | 29 +++++++++++++++--------------
 1 file changed, 15 insertions(+), 14 deletions(-)
net/vhost-vdpa.c +15 -14
index 1b82ac2e07..bbe1830824 100644
@@ -302,35 +302,36 @@ dma_map_err:
 }
 
 /**
- * Copy the guest element into a dedicated buffer suitable to be sent to NIC
+ * Maps out sg and in buffer into dedicated buffers suitable to be sent to NIC
  *
- * @iov: [0] is the out buffer, [1] is the in one
+ * @dev_iov: [0] is the out buffer, [1] is the in one
  */
-static bool vhost_vdpa_net_cvq_map_elem(VhostVDPAState *s,
-                                        VirtQueueElement *elem,
-                                        struct iovec *iov)
+static bool vhost_vdpa_net_cvq_map_sg(VhostVDPAState *s,
+                                      const struct iovec *out, size_t out_num,
+                                      struct iovec *dev_iov)
 {
     size_t in_copied;
     bool ok;
 
-    iov[0].iov_base = s->cvq_cmd_out_buffer;
-    ok = vhost_vdpa_cvq_map_buf(&s->vhost_vdpa, elem->out_sg, elem->out_num,
-                                vhost_vdpa_net_cvq_cmd_len(), iov[0].iov_base,
-                                &iov[0].iov_len, false);
+    dev_iov[0].iov_base = s->cvq_cmd_out_buffer;
+    ok = vhost_vdpa_cvq_map_buf(&s->vhost_vdpa, out, out_num,
+                                vhost_vdpa_net_cvq_cmd_len(),
+                                dev_iov[0].iov_base, &dev_iov[0].iov_len,
+                                false);
     if (unlikely(!ok)) {
         return false;
     }
 
-    iov[1].iov_base = s->cvq_cmd_in_buffer;
+    dev_iov[1].iov_base = s->cvq_cmd_in_buffer;
     ok = vhost_vdpa_cvq_map_buf(&s->vhost_vdpa, NULL, 0,
-                                sizeof(virtio_net_ctrl_ack), iov[1].iov_base,
-                                &in_copied, true);
+                                sizeof(virtio_net_ctrl_ack),
+                                dev_iov[1].iov_base, &in_copied, true);
     if (unlikely(!ok)) {
         vhost_vdpa_cvq_unmap_buf(&s->vhost_vdpa, s->cvq_cmd_out_buffer);
         return false;
     }
 
-    iov[1].iov_len = sizeof(virtio_net_ctrl_ack);
+    dev_iov[1].iov_len = sizeof(virtio_net_ctrl_ack);
     return true;
 }
 
@@ -434,7 +435,7 @@ static int vhost_vdpa_net_handle_ctrl_avail(VhostShadowVirtqueue *svq,
     };
     bool ok;
 
-    ok = vhost_vdpa_net_cvq_map_elem(s, elem, dev_buffers);
+    ok = vhost_vdpa_net_cvq_map_sg(s, elem->out_sg, elem->out_num, dev_buffers);
     if (unlikely(!ok)) {
         goto out;
     }
Signature · 1 line
2.31.1
#4 lore raw

PATCH v3 4/6 vdpa: add NetClientState->start() callback

In reply to Eugenio Pérez

It allows per-net client operations right after device's successful start.

Vhost-vdpa net will use it to add the CVQ buffers to restore the device status.

---
 include/net/net.h  | 2 ++
 hw/net/vhost_net.c | 7 +++++++
 2 files changed, 9 insertions(+)
include/net/net.h +2 -0
index 523136c7ac..ad9e80083a 100644
@@ -44,6 +44,7 @@ typedef struct NICConf {
 
 typedef void (NetPoll)(NetClientState *, bool enable);
 typedef bool (NetCanReceive)(NetClientState *);
+typedef int (NetStart)(NetClientState *);
 typedef ssize_t (NetReceive)(NetClientState *, const uint8_t *, size_t);
 typedef ssize_t (NetReceiveIOV)(NetClientState *, const struct iovec *, int);
 typedef void (NetCleanup) (NetClientState *);
@@ -71,6 +72,7 @@ typedef struct NetClientInfo {
     NetReceive *receive_raw;
     NetReceiveIOV *receive_iov;
     NetCanReceive *can_receive;
+    NetStart *start;
     NetCleanup *cleanup;
     LinkStatusChanged *link_status_changed;
     QueryRxFilter *query_rx_filter;
hw/net/vhost_net.c +7 -0
index ccac5b7a64..ddd9ee0441 100644
@@ -274,6 +274,13 @@ static int vhost_net_start_one(struct vhost_net *net,
             }
         }
     }
+
+    if (net->nc->info->start) {
+        r = net->nc->info->start(net->nc);
+        if (r < 0) {
+            goto fail;
+        }
+    }
     return 0;
 fail:
     file.fd = -1;
Signature · 1 line
2.31.1
#5 lore raw

PATCH v3 5/6 vdpa: Add virtio-net mac address via CVQ at start

In reply to Eugenio Pérez

This is needed so the destination vdpa device see the same state a the guest set in the source.

---
 include/net/vhost-vdpa.h |  1 +
 net/vhost-vdpa.c         | 57 ++++++++++++++++++++++++++++++++++++++++
 2 files changed, 58 insertions(+)
include/net/vhost-vdpa.h +1 -0
index b81f9a6f2a..38d65e845d 100644
@@ -15,6 +15,7 @@
 #define TYPE_VHOST_VDPA "vhost-vdpa"
 
 struct vhost_net *vhost_vdpa_get_vhost_net(NetClientState *nc);
+int vhost_vdpa_start(NetClientState *nc);
 
 extern const int vdpa_feature_bits[];
 
net/vhost-vdpa.c +57 -0

63 lines not on this page · raw message

Signature · 1 line
2.31.1
#6 lore raw

PATCH v3 6/6 vdpa: Delete CVQ migration blocker

In reply to Eugenio Pérez

We can restore the device state in the destination via CVQ now. Remove the migration blocker.

---
 include/hw/virtio/vhost-vdpa.h |  1 -
 hw/virtio/vhost-vdpa.c         | 14 --------------
 net/vhost-vdpa.c               |  2 --
 3 files changed, 17 deletions(-)
include/hw/virtio/vhost-vdpa.h +0 -1
index d10a89303e..1111d85643 100644
@@ -35,7 +35,6 @@ typedef struct vhost_vdpa {
     bool shadow_vqs_enabled;
     /* IOVA mapping used by the Shadow Virtqueue */
     VhostIOVATree *iova_tree;
-    Error *migration_blocker;
     GPtrArray *shadow_vqs;
     const VhostShadowVirtqueueOps *shadow_vq_ops;
     void *shadow_vq_ops_opaque;
hw/virtio/vhost-vdpa.c +0 -14
index 3ff9ce3501..9a2daef7e3 100644
@@ -1023,13 +1023,6 @@ static bool vhost_vdpa_svqs_start(struct vhost_dev *dev)
         return true;
     }
 
-    if (v->migration_blocker) {
-        int r = migrate_add_blocker(v->migration_blocker, &err);
-        if (unlikely(r < 0)) {
-            return false;
-        }
-    }
-
     for (i = 0; i < v->shadow_vqs->len; ++i) {
         VirtQueue *vq = virtio_get_queue(dev->vdev, dev->vq_index + i);
         VhostShadowVirtqueue *svq = g_ptr_array_index(v->shadow_vqs, i);
@@ -1072,10 +1065,6 @@ err:
         vhost_svq_stop(svq);
     }
 
-    if (v->migration_blocker) {
-        migrate_del_blocker(v->migration_blocker);
-    }
-
     return false;
 }
 
@@ -1095,9 +1084,6 @@ static bool vhost_vdpa_svqs_stop(struct vhost_dev *dev)
         }
     }
 
-    if (v->migration_blocker) {
-        migrate_del_blocker(v->migration_blocker);
-    }
     return true;
 }
 
net/vhost-vdpa.c +0 -2
index 84e90f067a..82c115bee4 100644
@@ -573,8 +573,6 @@ static NetClientState *net_vhost_vdpa_init(NetClientState *peer,
 
         s->vhost_vdpa.shadow_vq_ops = &vhost_vdpa_net_svq_ops;
         s->vhost_vdpa.shadow_vq_ops_opaque = s;
-        error_setg(&s->vhost_vdpa.migration_blocker,
-                   "Migration disabled: vhost-vdpa uses CVQ.");
     }
     ret = vhost_vdpa_add(nc, (void *)&s->vhost_vdpa, queue_pair_index, nvqs);
     if (ret) {
Signature · 1 line
2.31.1