Skip to contentSkip to conversation

NIC vhost-vdpa state restore via Shadow CVQ

PATCH Superseded Eugenio Pérez 2 participants 14 messages Aug 19, 2022 – Aug 23, 2022 Networking

v9 of 10 Superseded Latest is v10 →

lore
Share & tools
lore
#0 lore raw

v9 cover NIC vhost-vdpa state restore via Shadow CVQ

CVQ of net vhost-vdpa devices can be intercepted since the addition of x-svq. 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.

Depending on the device, this series may need fixes with message id [1] to achieve full live migration.

[1] <[email protected]>

v9:
- Use guest acked features instead of device's.
- Minors: fix typos and patch messages, constify vhost_vdpa and VirtIONet vars, delete unneeded increment of cursor.

v8:
- Rename NetClientInfo load to start, so is symmetrical with stop()
- Delete copy of device's in buffer at vhost_vdpa_net_load

v7:
- Remove accidental double free.

v6:
- Move map and unmap of the buffers to the start and stop of the device. This implies more callbacks on NetClientInfo, but simplifies the SVQ CVQ code.
- Not assume that in buffer is sizeof(virtio_net_ctrl_ack) in vhost_vdpa_net_cvq_add
- Reduce the number of changes from previous versions
- Delete unused memory barrier

v5:
- Rename s/start/load/
- Use independent NetClientInfo to only add load callback on cvq.
- Accept out sg instead of dev_buffers[] at vhost_vdpa_net_cvq_map_elem
- Use only out size instead of iovec dev_buffers to know if the descriptor is effectively available, allowing to delete artificial !NULL VirtQueueElement on vhost_svq_add call.

v4:
- Actually use NetClientInfo callback.

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 (12):
vhost: stop transfer elem ownership in vhost_handle_guest_kick
vhost: use SVQ element ndescs instead of opaque data for desc
validation
vhost: Delete useless read memory barrier
vhost: Do not depend on !NULL VirtQueueElement on vhost_svq_flush
vhost_net: Add NetClientInfo start callback
vhost_net: Add NetClientInfo stop callback
vdpa: add net_vhost_vdpa_cvq_info NetClientInfo
vdpa: Move command buffers map to start of net device
vdpa: extract vhost_vdpa_net_cvq_add from
vhost_vdpa_net_handle_ctrl_avail
vhost_net: add NetClientState->load() 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                  |   6 +
 hw/net/vhost_net.c                 |  17 +++
 hw/virtio/vhost-shadow-virtqueue.c |  27 ++--
 hw/virtio/vhost-vdpa.c             |  15 --
 net/vhost-vdpa.c                   | 224 ++++++++++++++++++-----------
 6 files changed, 177 insertions(+), 113 deletions(-)
Signature · 1 line
2.31.1
#1 lore raw

PATCH v9 1/12 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 82a784d250..a1261d4a0f 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 v9 2/12 vhost: use SVQ element ndescs instead of opaque data for desc validation

In reply to Eugenio Pérez

Since we're going to allow SVQ to add elements without the guest's knowledge and without its own VirtQueueElement, it's easier to check if an element is a valid head checking a different thing than the VirtQueueElement.

---
 hw/virtio/vhost-shadow-virtqueue.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)
hw/virtio/vhost-shadow-virtqueue.c +2 -1
index a1261d4a0f..b35aeef4bd 100644
@@ -414,7 +414,7 @@ static VirtQueueElement *vhost_svq_get_buf(VhostShadowVirtqueue *svq,
         return NULL;
     }
 
-    if (unlikely(!svq->desc_state[used_elem.id].elem)) {
+    if (unlikely(!svq->desc_state[used_elem.id].ndescs)) {
         qemu_log_mask(LOG_GUEST_ERROR,
             "Device %s says index %u is used, but it was not available",
             svq->vdev->name, used_elem.id);
@@ -422,6 +422,7 @@ static VirtQueueElement *vhost_svq_get_buf(VhostShadowVirtqueue *svq,
     }
 
     num = svq->desc_state[used_elem.id].ndescs;
+    svq->desc_state[used_elem.id].ndescs = 0;
     last_used_chain = vhost_svq_last_desc_of_chain(svq, num, used_elem.id);
     svq->desc_next[last_used_chain] = svq->free_head;
     svq->free_head = used_elem.id;
Signature · 1 line
2.31.1
#3 lore raw

PATCH v9 3/12 vhost: Delete useless read memory barrier

In reply to Eugenio Pérez

As discussed in previous series [1], this memory barrier is useless with the atomic read of used idx at vhost_svq_more_used. Deleting it.

[1] https://lists.nongnu.org/archive/html/qemu-devel/2022-07/msg02616.html

---
 hw/virtio/vhost-shadow-virtqueue.c | 3 ---
 1 file changed, 3 deletions(-)
hw/virtio/vhost-shadow-virtqueue.c +0 -3
index b35aeef4bd..8df5296f24 100644
@@ -509,9 +509,6 @@ size_t vhost_svq_poll(VhostShadowVirtqueue *svq)
         if (unlikely(g_get_monotonic_time() - start_us > 10e6)) {
             return 0;
         }
-
-        /* Make sure we read new used_idx */
-        smp_rmb();
     } while (true);
 }
 
Signature · 1 line
2.31.1
#4 lore raw

PATCH v9 4/12 vhost: Do not depend on !NULL VirtQueueElement on vhost_svq_flush

In reply to Eugenio Pérez

Since QEMU will be able to inject new elements on CVQ to restore the state, we need not to depend on a VirtQueueElement to know if a new element has been used by the device or not. Instead of check that, check if there are new elements only using used idx on vhost_svq_flush.

---
v6: Change less from the previous function

---
 hw/virtio/vhost-shadow-virtqueue.c | 11 +++++++----
 1 file changed, 7 insertions(+), 4 deletions(-)
hw/virtio/vhost-shadow-virtqueue.c +7 -4
index 8df5296f24..e8e5bbc368 100644
@@ -499,17 +499,20 @@ static void vhost_svq_flush(VhostShadowVirtqueue *svq,
 size_t vhost_svq_poll(VhostShadowVirtqueue *svq)
 {
     int64_t start_us = g_get_monotonic_time();
+    uint32_t len;
+
     do {
-        uint32_t len;
-        VirtQueueElement *elem = vhost_svq_get_buf(svq, &len);
-        if (elem) {
-            return len;
+        if (vhost_svq_more_used(svq)) {
+            break;
         }
 
         if (unlikely(g_get_monotonic_time() - start_us > 10e6)) {
             return 0;
         }
     } while (true);
+
+    vhost_svq_get_buf(svq, &len);
+    return len;
 }
 
 /**
Signature · 1 line
2.31.1
#5 lore raw

PATCH v9 5/12 vhost_net: Add NetClientInfo start callback

In reply to Eugenio Pérez

This is used by the backend to perform actions before the device is started.

In particular, vdpa net use it to map CVQ buffers to the device, so it can send control commands using them.

---
v9: Rename also in patch message
v8: Rename NetClientInfo prepare callback to start, so it aligns with
future "stop"

---
 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..2e0baeba26 100644
@@ -244,6 +244,13 @@ static int vhost_net_start_one(struct vhost_net *net,
     struct vhost_vring_file file = { };
     int r;
 
+    if (net->nc->info->start) {
+        r = net->nc->info->start(net->nc);
+        if (r < 0) {
+            return r;
+        }
+    }
+
     r = vhost_dev_enable_notifiers(&net->dev, dev);
     if (r < 0) {
         goto fail_notifiers;
Signature · 1 line
2.31.1
#6 lore raw

PATCH v9 6/12 vhost_net: Add NetClientInfo stop callback

In reply to Eugenio Pérez

Used by the backend to perform actions after the device is stopped.

In particular, vdpa net use it to unmap CVQ buffers to the device, cleaning the actions performed in prepare().

---
v9: Replace performend by performed in patch message

---
 include/net/net.h  | 2 ++
 hw/net/vhost_net.c | 3 +++
 2 files changed, 5 insertions(+)
include/net/net.h +2 -0
index ad9e80083a..476ad45b9a 100644
@@ -45,6 +45,7 @@ typedef struct NICConf {
 typedef void (NetPoll)(NetClientState *, bool enable);
 typedef bool (NetCanReceive)(NetClientState *);
 typedef int (NetStart)(NetClientState *);
+typedef void (NetStop)(NetClientState *);
 typedef ssize_t (NetReceive)(NetClientState *, const uint8_t *, size_t);
 typedef ssize_t (NetReceiveIOV)(NetClientState *, const struct iovec *, int);
 typedef void (NetCleanup) (NetClientState *);
@@ -73,6 +74,7 @@ typedef struct NetClientInfo {
     NetReceiveIOV *receive_iov;
     NetCanReceive *can_receive;
     NetStart *start;
+    NetStop *stop;
     NetCleanup *cleanup;
     LinkStatusChanged *link_status_changed;
     QueryRxFilter *query_rx_filter;
hw/net/vhost_net.c +3 -0
index 2e0baeba26..9d4b334453 100644
@@ -320,6 +320,9 @@ static void vhost_net_stop_one(struct vhost_net *net,
         net->nc->info->poll(net->nc, true);
     }
     vhost_dev_stop(&net->dev, dev);
+    if (net->nc->info->stop) {
+        net->nc->info->stop(net->nc);
+    }
     vhost_dev_disable_notifiers(&net->dev, dev);
 }
 
Signature · 1 line
2.31.1
#7 lore raw

PATCH v9 7/12 vdpa: add net_vhost_vdpa_cvq_info NetClientInfo

In reply to Eugenio Pérez

Next patches will add a new info callback to restore NIC status through CVQ. Since only the CVQ vhost device is needed, create it with a new NetClientInfo.

---
v5: Create a new NetClientInfo instead of reusing the dataplane one.

---
 net/vhost-vdpa.c | 12 +++++++++++-
 1 file changed, 11 insertions(+), 1 deletion(-)
net/vhost-vdpa.c +11 -1
index 303447a68e..2cc1e64daf 100644
@@ -334,6 +334,16 @@ static bool vhost_vdpa_net_cvq_map_elem(VhostVDPAState *s,
     return true;
 }
 
+static NetClientInfo net_vhost_vdpa_cvq_info = {
+    .type = NET_CLIENT_DRIVER_VHOST_VDPA,
+    .size = sizeof(VhostVDPAState),
+    .receive = vhost_vdpa_receive,
+    .cleanup = vhost_vdpa_cleanup,
+    .has_vnet_hdr = vhost_vdpa_has_vnet_hdr,
+    .has_ufo = vhost_vdpa_has_ufo,
+    .check_peer_type = vhost_vdpa_check_peer_type,
+};
+
 /**
  * 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.
@@ -475,7 +485,7 @@ static NetClientState *net_vhost_vdpa_init(NetClientState *peer,
         nc = qemu_new_net_client(&net_vhost_vdpa_info, peer, device,
                                  name);
     } else {
-        nc = qemu_new_net_control_client(&net_vhost_vdpa_info, peer,
+        nc = qemu_new_net_control_client(&net_vhost_vdpa_cvq_info, peer,
                                          device, name);
     }
     snprintf(nc->info_str, sizeof(nc->info_str), TYPE_VHOST_VDPA);
Signature · 1 line
2.31.1
#8 lore raw

PATCH v9 8/12 vdpa: Move command buffers map to start of net device

In reply to Eugenio Pérez

As this series will reuse them to restore the device state at the end of a migration (or a device start), let's allocate only once at the device start so we don't duplicate their map and unmap.

---
 net/vhost-vdpa.c | 123 ++++++++++++++++++++++-------------------------
 1 file changed, 58 insertions(+), 65 deletions(-)
net/vhost-vdpa.c +58 -65
index 2cc1e64daf..9ca065dff6 100644
@@ -263,29 +263,20 @@ static size_t vhost_vdpa_net_cvq_cmd_page_len(void)
     return ROUND_UP(vhost_vdpa_net_cvq_cmd_len(), qemu_real_host_page_size());
 }
 
-/** Copy and map a guest buffer. */
-static bool vhost_vdpa_cvq_map_buf(struct vhost_vdpa *v,
-                                   const struct iovec *out_data,
-                                   size_t out_num, size_t data_len, void *buf,
-                                   size_t *written, bool write)
+/** Map CVQ buffer. */
+static int vhost_vdpa_cvq_map_buf(struct vhost_vdpa *v, void *buf, size_t size,
+                                  bool write)
 {
     DMAMap map = {};
     int r;
 
-    if (unlikely(!data_len)) {
-        qemu_log_mask(LOG_GUEST_ERROR, "%s: invalid legnth of %s buffer\n",
-                      __func__, write ? "in" : "out");
-        return false;
-    }
-
-    *written = iov_to_buf(out_data, out_num, 0, buf, data_len);
     map.translated_addr = (hwaddr)(uintptr_t)buf;
-    map.size = vhost_vdpa_net_cvq_cmd_page_len() - 1;
+    map.size = size - 1;
     map.perm = write ? IOMMU_RW : IOMMU_RO,
     r = vhost_iova_tree_map_alloc(v->iova_tree, &map);
     if (unlikely(r != IOVA_OK)) {
         error_report("Cannot map injected element");
-        return false;
+        return r;
     }
 
     r = vhost_vdpa_dma_map(v, map.iova, vhost_vdpa_net_cvq_cmd_page_len(), buf,
@@ -294,50 +285,58 @@ static bool vhost_vdpa_cvq_map_buf(struct vhost_vdpa *v,
         goto dma_map_err;
     }
 
-    return true;
+    return 0;
 
 dma_map_err:
     vhost_iova_tree_remove(v->iova_tree, &map);
-    return false;
+    return r;
 }
 
-/**
- * Copy the guest element into a dedicated buffer suitable to be sent to NIC
- *
- * @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 int vhost_vdpa_net_cvq_start(NetClientState *nc)
 {
-    size_t in_copied;
-    bool ok;
+    VhostVDPAState *s;
+    int r;
 
-    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);
-    if (unlikely(!ok)) {
-        return false;
+    assert(nc->info->type == NET_CLIENT_DRIVER_VHOST_VDPA);
+
+    s = DO_UPCAST(VhostVDPAState, nc, nc);
+    if (!s->vhost_vdpa.shadow_vqs_enabled) {
+        return 0;
     }
 
-    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);
-    if (unlikely(!ok)) {
+    r = vhost_vdpa_cvq_map_buf(&s->vhost_vdpa, s->cvq_cmd_out_buffer,
+                               vhost_vdpa_net_cvq_cmd_page_len(), false);
+    if (unlikely(r < 0)) {
+        return r;
+    }
+
+    r = vhost_vdpa_cvq_map_buf(&s->vhost_vdpa, s->cvq_cmd_in_buffer,
+                               vhost_vdpa_net_cvq_cmd_page_len(), true);
+    if (unlikely(r < 0)) {
         vhost_vdpa_cvq_unmap_buf(&s->vhost_vdpa, s->cvq_cmd_out_buffer);
-        return false;
     }
 
-    iov[1].iov_len = sizeof(virtio_net_ctrl_ack);
-    return true;
+    return r;
+}
+
+static void vhost_vdpa_net_cvq_stop(NetClientState *nc)
+{
+    VhostVDPAState *s = DO_UPCAST(VhostVDPAState, nc, nc);
+
+    assert(nc->info->type == NET_CLIENT_DRIVER_VHOST_VDPA);
+
+    if (s->vhost_vdpa.shadow_vqs_enabled) {
+        vhost_vdpa_cvq_unmap_buf(&s->vhost_vdpa, s->cvq_cmd_out_buffer);
+        vhost_vdpa_cvq_unmap_buf(&s->vhost_vdpa, s->cvq_cmd_in_buffer);
+    }
 }
 
 static NetClientInfo net_vhost_vdpa_cvq_info = {
     .type = NET_CLIENT_DRIVER_VHOST_VDPA,
     .size = sizeof(VhostVDPAState),
     .receive = vhost_vdpa_receive,
+    .start = vhost_vdpa_net_cvq_start,
+    .stop = vhost_vdpa_net_cvq_stop,
     .cleanup = vhost_vdpa_cleanup,
     .has_vnet_hdr = vhost_vdpa_has_vnet_hdr,
     .has_ufo = vhost_vdpa_has_ufo,
@@ -348,19 +347,17 @@ static NetClientInfo net_vhost_vdpa_cvq_info = {
  * 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.
  */
-static bool vhost_vdpa_net_cvq_validate_cmd(const struct iovec *out,
-                                            size_t out_num)
+static bool vhost_vdpa_net_cvq_validate_cmd(const void *out_buf, size_t len)
 {
     struct virtio_net_ctrl_hdr ctrl;
-    size_t n;
 
-    n = iov_to_buf(out, out_num, 0, &ctrl, sizeof(ctrl));
-    if (unlikely(n < sizeof(ctrl))) {
+    if (unlikely(len < sizeof(ctrl))) {
         qemu_log_mask(LOG_GUEST_ERROR,
-                      "%s: invalid legnth of out buffer %zu\n", __func__, n);
+                      "%s: invalid legnth of out buffer %zu\n", __func__, len);
         return false;
     }
 
+    memcpy(&ctrl, out_buf, sizeof(ctrl));
     switch (ctrl.class) {
     case VIRTIO_NET_CTRL_MAC:
         switch (ctrl.cmd) {
@@ -392,10 +389,14 @@ static int vhost_vdpa_net_handle_ctrl_avail(VhostShadowVirtqueue *svq,
     VhostVDPAState *s = opaque;
     size_t in_len, dev_written;
     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 },
+    /* Out buffer sent to both the vdpa device and the device model */
+    struct iovec out = {
+        .iov_base = s->cvq_cmd_out_buffer,
+    };
+    /* In buffer sent to the device */
+    const struct iovec dev_in = {
+        .iov_base = s->cvq_cmd_in_buffer,
+        .iov_len = sizeof(virtio_net_ctrl_ack),
     };
     /* in buffer used for device model */
     const struct iovec in = {
@@ -405,17 +406,15 @@ static int vhost_vdpa_net_handle_ctrl_avail(VhostShadowVirtqueue *svq,
     int r = -EINVAL;
     bool ok;
 
-    ok = vhost_vdpa_net_cvq_map_elem(s, elem, dev_buffers);
-    if (unlikely(!ok)) {
-        goto out;
-    }
-
-    ok = vhost_vdpa_net_cvq_validate_cmd(&dev_buffers[0], 1);
+    out.iov_len = iov_to_buf(elem->out_sg, elem->out_num, 0,
+                             s->cvq_cmd_out_buffer,
+                             vhost_vdpa_net_cvq_cmd_len());
+    ok = vhost_vdpa_net_cvq_validate_cmd(s->cvq_cmd_out_buffer, out.iov_len);
     if (unlikely(!ok)) {
         goto out;
     }
 
-    r = vhost_svq_add(svq, &dev_buffers[0], 1, &dev_buffers[1], 1, elem);
+    r = vhost_svq_add(svq, &out, 1, &dev_in, 1, elem);
     if (unlikely(r != 0)) {
         if (unlikely(r == -ENOSPC)) {
             qemu_log_mask(LOG_GUEST_ERROR, "%s: No space on device queue\n",
@@ -435,13 +434,13 @@ static int vhost_vdpa_net_handle_ctrl_avail(VhostShadowVirtqueue *svq,
         goto out;
     }
 
-    memcpy(&status, dev_buffers[1].iov_base, sizeof(status));
+    memcpy(&status, s->cvq_cmd_in_buffer, sizeof(status));
     if (status != VIRTIO_NET_OK) {
         goto out;
     }
 
     status = VIRTIO_NET_ERR;
-    virtio_net_handle_ctrl_iov(svq->vdev, &in, 1, dev_buffers, 1);
+    virtio_net_handle_ctrl_iov(svq->vdev, &in, 1, &out, 1);
     if (status != VIRTIO_NET_OK) {
         error_report("Bad CVQ processing in model");
     }
@@ -454,12 +453,6 @@ out:
     }
     vhost_svq_push_elem(svq, elem, MIN(in_len, sizeof(status)));
     g_free(elem);
-    if (dev_buffers[0].iov_base) {
-        vhost_vdpa_cvq_unmap_buf(&s->vhost_vdpa, dev_buffers[0].iov_base);
-    }
-    if (dev_buffers[1].iov_base) {
-        vhost_vdpa_cvq_unmap_buf(&s->vhost_vdpa, dev_buffers[1].iov_base);
-    }
     return r;
 }
 
Signature · 1 line
2.31.1
#9 lore raw

PATCH v9 9/12 vdpa: extract vhost_vdpa_net_cvq_add from vhost_vdpa_net_handle_ctrl_avail

In reply to Eugenio Pérez

So we can reuse it to inject state messages.

--
v7:
* Remove double free error

v6:
* Do not assume in buffer sent to the device is sizeof(virtio_net_ctrl_ack)

v5:
* Do not use an artificial !NULL VirtQueueElement
* Use only out size instead of iovec dev_buffers for these functions.

---
 net/vhost-vdpa.c | 59 +++++++++++++++++++++++++++++++-----------------
 1 file changed, 38 insertions(+), 21 deletions(-)
net/vhost-vdpa.c +38 -21
index 9ca065dff6..ebf76d1034 100644
@@ -331,6 +331,38 @@ static void vhost_vdpa_net_cvq_stop(NetClientState *nc)
     }
 }
 
+static ssize_t vhost_vdpa_net_cvq_add(VhostVDPAState *s, size_t out_len,
+                                      size_t in_len)
+{
+    /* Buffers for the device */
+    const struct iovec out = {
+        .iov_base = s->cvq_cmd_out_buffer,
+        .iov_len = out_len,
+    };
+    const struct iovec in = {
+        .iov_base = s->cvq_cmd_in_buffer,
+        .iov_len = sizeof(virtio_net_ctrl_ack),
+    };
+    VhostShadowVirtqueue *svq = g_ptr_array_index(s->vhost_vdpa.shadow_vqs, 0);
+    int r;
+
+    r = vhost_svq_add(svq, &out, 1, &in, 1, NULL);
+    if (unlikely(r != 0)) {
+        if (unlikely(r == -ENOSPC)) {
+            qemu_log_mask(LOG_GUEST_ERROR, "%s: No space on device queue\n",
+                          __func__);
+        }
+        return r;
+    }
+
+    /*
+     * 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
+     */
+    return vhost_svq_poll(svq);
+}
+
 static NetClientInfo net_vhost_vdpa_cvq_info = {
     .type = NET_CLIENT_DRIVER_VHOST_VDPA,
     .size = sizeof(VhostVDPAState),
@@ -387,23 +419,18 @@ 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 buffer sent to both the vdpa device and the device model */
     struct iovec out = {
         .iov_base = s->cvq_cmd_out_buffer,
     };
-    /* In buffer sent to the device */
-    const struct iovec dev_in = {
-        .iov_base = s->cvq_cmd_in_buffer,
-        .iov_len = sizeof(virtio_net_ctrl_ack),
-    };
     /* in buffer used for device model */
     const struct iovec in = {
         .iov_base = &status,
         .iov_len = sizeof(status),
     };
-    int r = -EINVAL;
+    ssize_t dev_written = -EINVAL;
     bool ok;
 
     out.iov_len = iov_to_buf(elem->out_sg, elem->out_num, 0,
@@ -414,21 +441,11 @@ static int vhost_vdpa_net_handle_ctrl_avail(VhostShadowVirtqueue *svq,
         goto out;
     }
 
-    r = vhost_svq_add(svq, &out, 1, &dev_in, 1, elem);
-    if (unlikely(r != 0)) {
-        if (unlikely(r == -ENOSPC)) {
-            qemu_log_mask(LOG_GUEST_ERROR, "%s: No space on device queue\n",
-                          __func__);
-        }
+    dev_written = vhost_vdpa_net_cvq_add(s, out.iov_len, sizeof(status));
+    if (unlikely(dev_written < 0)) {
         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;
@@ -436,7 +453,7 @@ static int vhost_vdpa_net_handle_ctrl_avail(VhostShadowVirtqueue *svq,
 
     memcpy(&status, s->cvq_cmd_in_buffer, sizeof(status));
     if (status != VIRTIO_NET_OK) {
-        goto out;
+        return VIRTIO_NET_ERR;
     }
 
     status = VIRTIO_NET_ERR;
@@ -453,7 +470,7 @@ out:
     }
     vhost_svq_push_elem(svq, elem, MIN(in_len, sizeof(status)));
     g_free(elem);
-    return r;
+    return dev_written < 0 ? dev_written : 0;
 }
 
 static const VhostShadowVirtqueueOps vhost_vdpa_net_svq_ops = {
Signature · 1 line
2.31.1
#10 lore raw

PATCH v9 10/12 vhost_net: add NetClientState->load() callback

In reply to Eugenio Pérez

It allows per-net client operations right after device's successful start. In particular, to load the device status.

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

---
v5: Rename start / load, naming it more specifically.

---
 include/net/net.h  | 2 ++
 hw/net/vhost_net.c | 7 +++++++
 2 files changed, 9 insertions(+)
include/net/net.h +2 -0
index 476ad45b9a..81d0b21def 100644
@@ -45,6 +45,7 @@ typedef struct NICConf {
 typedef void (NetPoll)(NetClientState *, bool enable);
 typedef bool (NetCanReceive)(NetClientState *);
 typedef int (NetStart)(NetClientState *);
+typedef int (NetLoad)(NetClientState *);
 typedef void (NetStop)(NetClientState *);
 typedef ssize_t (NetReceive)(NetClientState *, const uint8_t *, size_t);
 typedef ssize_t (NetReceiveIOV)(NetClientState *, const struct iovec *, int);
@@ -74,6 +75,7 @@ typedef struct NetClientInfo {
     NetReceiveIOV *receive_iov;
     NetCanReceive *can_receive;
     NetStart *start;
+    NetLoad *load;
     NetStop *stop;
     NetCleanup *cleanup;
     LinkStatusChanged *link_status_changed;
hw/net/vhost_net.c +7 -0
index 9d4b334453..d28f8b974b 100644
@@ -281,6 +281,13 @@ static int vhost_net_start_one(struct vhost_net *net,
             }
         }
     }
+
+    if (net->nc->info->load) {
+        r = net->nc->info->load(net->nc);
+        if (r < 0) {
+            goto fail;
+        }
+    }
     return 0;
 fail:
     file.fd = -1;
Signature · 1 line
2.31.1
#11 lore raw

PATCH v9 11/12 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.

---
v9:
* Use guest acked features instead of device's.
* Constify vhost_vdpa and VirtIONet variables.
* Delete unneeded increment of cursor.

v8:
* Delete unneeded copy from device's in buffer.

v6:
* Map and unmap command buffers at the start and end of device usage.

v5:
* Rename s/start/load/
* Use independent NetClientInfo to only add load callback on cvq.

---
 net/vhost-vdpa.c | 40 ++++++++++++++++++++++++++++++++++++++++
 1 file changed, 40 insertions(+)
net/vhost-vdpa.c +40 -0
index ebf76d1034..8fad31a5fd 100644
@@ -363,11 +363,51 @@ static ssize_t vhost_vdpa_net_cvq_add(VhostVDPAState *s, size_t out_len,
     return vhost_svq_poll(svq);
 }
 
+static int vhost_vdpa_net_load(NetClientState *nc)
+{
+    VhostVDPAState *s = DO_UPCAST(VhostVDPAState, nc, nc);
+    const struct vhost_vdpa *v = &s->vhost_vdpa;
+    const VirtIONet *n;
+    uint64_t features;
+
+    assert(nc->info->type == NET_CLIENT_DRIVER_VHOST_VDPA);
+
+    if (!v->shadow_vqs_enabled) {
+        return 0;
+    }
+
+    n = VIRTIO_NET(v->dev->vdev);
+    features = n->parent_obj.guest_features;
+    if (features & BIT_ULL(VIRTIO_NET_F_CTRL_MAC_ADDR)) {
+        const struct virtio_net_ctrl_hdr ctrl = {
+            .class = VIRTIO_NET_CTRL_MAC,
+            .cmd = VIRTIO_NET_CTRL_MAC_ADDR_SET,
+        };
+        char *cursor = s->cvq_cmd_out_buffer;
+        ssize_t dev_written;
+
+        memcpy(cursor, &ctrl, sizeof(ctrl));
+        cursor += sizeof(ctrl);
+        memcpy(cursor, n->mac, sizeof(n->mac));
+
+        dev_written = vhost_vdpa_net_cvq_add(s, sizeof(ctrl) + sizeof(n->mac),
+                                             sizeof(virtio_net_ctrl_ack));
+        if (unlikely(dev_written < 0)) {
+            return dev_written;
+        }
+
+        return *((virtio_net_ctrl_ack *)s->cvq_cmd_in_buffer) != VIRTIO_NET_OK;
+    }
+
+    return 0;
+}
+
 static NetClientInfo net_vhost_vdpa_cvq_info = {
     .type = NET_CLIENT_DRIVER_VHOST_VDPA,
     .size = sizeof(VhostVDPAState),
     .receive = vhost_vdpa_receive,
     .start = vhost_vdpa_net_cvq_start,
+    .load = vhost_vdpa_net_load,
     .stop = vhost_vdpa_net_cvq_stop,
     .cleanup = vhost_vdpa_cleanup,
     .has_vnet_hdr = vhost_vdpa_has_vnet_hdr,
Signature · 1 line
2.31.1
Acked-by on v9 11/12
#12 lore raw

Re: [PATCH v9 11/12] vdpa: Add virtio-net mac address via CVQ at start

Quoted 4 lines · Eugenio Pérez

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

Quoted 75 lines

---
v9:
* Use guest acked features instead of device's.
* Constify vhost_vdpa and VirtIONet variables.
* Delete unneeded increment of cursor.

v8:
* Delete unneeded copy from device's in buffer.

v6:
* Map and unmap command buffers at the start and end of device usage.

v5:
* Rename s/start/load/
* Use independent NetClientInfo to only add load callback on cvq.

---
  net/vhost-vdpa.c | 40 ++++++++++++++++++++++++++++++++++++++++
  1 file changed, 40 insertions(+)
net/vhost-vdpa.c +40 -0
index ebf76d1034..8fad31a5fd 100644
@@ -363,11 +363,51 @@ static ssize_t vhost_vdpa_net_cvq_add(VhostVDPAState *s, size_t out_len,
      return vhost_svq_poll(svq);
  }
 
+static int vhost_vdpa_net_load(NetClientState *nc)
+{
+    VhostVDPAState *s = DO_UPCAST(VhostVDPAState, nc, nc);
+    const struct vhost_vdpa *v = &s->vhost_vdpa;
+    const VirtIONet *n;
+    uint64_t features;
+
+    assert(nc->info->type == NET_CLIENT_DRIVER_VHOST_VDPA);
+
+    if (!v->shadow_vqs_enabled) {
+        return 0;
+    }
+
+    n = VIRTIO_NET(v->dev->vdev);
+    features = n->parent_obj.guest_features;
+    if (features & BIT_ULL(VIRTIO_NET_F_CTRL_MAC_ADDR)) {
+        const struct virtio_net_ctrl_hdr ctrl = {
+            .class = VIRTIO_NET_CTRL_MAC,
+            .cmd = VIRTIO_NET_CTRL_MAC_ADDR_SET,
+        };
+        char *cursor = s->cvq_cmd_out_buffer;
+        ssize_t dev_written;
+
+        memcpy(cursor, &ctrl, sizeof(ctrl));
+        cursor += sizeof(ctrl);
+        memcpy(cursor, n->mac, sizeof(n->mac));
+
+        dev_written = vhost_vdpa_net_cvq_add(s, sizeof(ctrl) + sizeof(n->mac),
+                                             sizeof(virtio_net_ctrl_ack));
+        if (unlikely(dev_written < 0)) {
+            return dev_written;
+        }
+
+        return *((virtio_net_ctrl_ack *)s->cvq_cmd_in_buffer) != VIRTIO_NET_OK;
+    }
+
+    return 0;
+}
+
  static NetClientInfo net_vhost_vdpa_cvq_info = {
      .type = NET_CLIENT_DRIVER_VHOST_VDPA,
      .size = sizeof(VhostVDPAState),
      .receive = vhost_vdpa_receive,
      .start = vhost_vdpa_net_cvq_start,
+    .load = vhost_vdpa_net_load,
      .stop = vhost_vdpa_net_cvq_stop,
      .cleanup = vhost_vdpa_cleanup,
      .has_vnet_hdr = vhost_vdpa_has_vnet_hdr,
#13 lore raw

PATCH v9 12/12 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         | 15 ---------------
 net/vhost-vdpa.c               |  2 --
 3 files changed, 18 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 -15
index 45d6e86b45..15cb87223e 100644
@@ -1032,13 +1032,6 @@ 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);
@@ -1081,10 +1074,6 @@ err:
         vhost_svq_stop(svq);
     }
 
-    if (v->migration_blocker) {
-        migrate_del_blocker(v->migration_blocker);
-    }
-
     return false;
 }
 
@@ -1100,10 +1089,6 @@ static void vhost_vdpa_svqs_stop(struct vhost_dev *dev)
         VhostShadowVirtqueue *svq = g_ptr_array_index(v->shadow_vqs, i);
         vhost_vdpa_svq_unmap_rings(dev, svq);
     }
-
-    if (v->migration_blocker) {
-        migrate_del_blocker(v->migration_blocker);
-    }
 }
 
 static int vhost_vdpa_dev_start(struct vhost_dev *dev, bool started)
net/vhost-vdpa.c +0 -2
index 8fad31a5fd..97b658f412 100644
@@ -555,8 +555,6 @@ 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