All of lore.kernel.org
 help / color / mirror / Atom feed
From: Jens Freimann <jfreimann@redhat.com>
To: qemu-devel@nongnu.org
Cc: parav@mellanox.com, mst@redhat.com, aadam@redhat.com,
	dgilbert@redhat.com, alex.williamson@redhat.com,
	laine@redhat.com, ailan@redhat.com, ehabkost@redhat.com
Subject: [PATCH v3 09/10] net/virtio: add failover support
Date: Fri, 11 Oct 2019 13:20:14 +0200	[thread overview]
Message-ID: <20191011112015.11785-10-jfreimann@redhat.com> (raw)
In-Reply-To: <20191011112015.11785-1-jfreimann@redhat.com>

This patch adds support to handle failover device pairs of a virtio-net
device and a vfio-pci device, where the virtio-net acts as the standby
device and the vfio-pci device as the primary.

The general idea is that we have a pair of devices, a vfio-pci and a
emulated (virtio-net) device. Before migration the vfio device is
unplugged and data flows to the emulated device, on the target side
another vfio-pci device is plugged in to take over the data-path. In the
guest the net_failover module will pair net devices with the same MAC
address.

To achieve this we need:

1. Provide a callback function for the should_be_hidden DeviceListener.
   It is called when the primary device is plugged in. Evaluate the QOpt
   passed in to check if it is the matching primary device. It returns
   two values:
     - one to signal if the device to be added is the matching
       primary device
     - another one to signal to qdev if it should actually
       continue with adding the device or skip it.

   In the latter case it stores the device options in the VirtioNet
   struct and the device is added once the VIRTIO_NET_F_STANDBY feature is
   negotiated during virtio feature negotiation.

   If the virtio-net devices are not realized at the time the vfio-pci
   devices are realized, we need to connect the devices later. This way
   we make sure primary and standby devices can be specified in any
   order.

2. Register a callback for migration status notifier. When called it
   will unplug its primary device before the migration happens.

3. Register a callback for the migration code that checks if a device
   needs to be unplugged from the guest.

Signed-off-by: Jens Freimann <jfreimann@redhat.com>
---
 hw/net/virtio-net.c            | 267 +++++++++++++++++++++++++++++++++
 include/hw/virtio/virtio-net.h |  12 ++
 include/hw/virtio/virtio.h     |   1 +
 3 files changed, 280 insertions(+)

diff --git a/hw/net/virtio-net.c b/hw/net/virtio-net.c
index 9f11422337..fb62e18b65 100644
--- a/hw/net/virtio-net.c
+++ b/hw/net/virtio-net.c
@@ -12,6 +12,7 @@
  */
 
 #include "qemu/osdep.h"
+#include "qemu/atomic.h"
 #include "qemu/iov.h"
 #include "qemu/main-loop.h"
 #include "qemu/module.h"
@@ -21,6 +22,10 @@
 #include "net/tap.h"
 #include "qemu/error-report.h"
 #include "qemu/timer.h"
+#include "qemu/option.h"
+#include "qemu/option_int.h"
+#include "qemu/config-file.h"
+#include "qapi/qmp/qdict.h"
 #include "hw/virtio/virtio-net.h"
 #include "net/vhost_net.h"
 #include "net/announce.h"
@@ -28,11 +33,15 @@
 #include "qapi/error.h"
 #include "qapi/qapi-events-net.h"
 #include "hw/qdev-properties.h"
+#include "qapi/qapi-types-migration.h"
+#include "qapi/qapi-events-migration.h"
 #include "hw/virtio/virtio-access.h"
 #include "migration/misc.h"
 #include "standard-headers/linux/ethtool.h"
 #include "sysemu/sysemu.h"
 #include "trace.h"
+#include "monitor/qdev.h"
+#include "hw/pci/pci.h"
 
 #define VIRTIO_NET_VM_VERSION    11
 
@@ -746,9 +755,85 @@ static inline uint64_t virtio_net_supported_guest_offloads(VirtIONet *n)
     return virtio_net_guest_offloads_by_features(vdev->guest_features);
 }
 
+static void failover_add_primary(VirtIONet *n)
+{
+    Error *err = NULL;
+
+    n->primary_device_opts = qemu_opts_find(qemu_find_opts("device"),
+            n->primary_device_id);
+    if (n->primary_device_opts) {
+        n->primary_dev = qdev_device_add(n->primary_device_opts, &err);
+        if (err) {
+            qemu_opts_del(n->primary_device_opts);
+        }
+        if (n->primary_dev) {
+            n->primary_bus = n->primary_dev->parent_bus;
+            if (err) {
+                qdev_unplug(n->primary_dev, &err);
+                qdev_set_id(n->primary_dev, "");
+
+            }
+        }
+    }
+    if (err) {
+        error_report_err(err);
+    }
+}
+
+static int is_my_primary(void *opaque, QemuOpts *opts, Error **errp)
+{
+    VirtIONet *n = opaque;
+    int ret = 0;
+
+    const char *standby_id = qemu_opt_get(opts, "net_failover_pair_id");
+
+    if (standby_id != NULL && (g_strcmp0(standby_id, n->netclient_name) == 0)) {
+        n->primary_device_id = g_strdup(opts->id);
+        ret = 1;
+    }
+
+    return ret;
+}
+
+static DeviceState *virtio_net_find_primary(VirtIONet *n, Error *err)
+{
+    DeviceState *dev = NULL;
+
+    if (qemu_opts_foreach(qemu_find_opts("device"),
+                         is_my_primary, n, &err)) {
+        if (n->primary_device_id) {
+            dev = qdev_find_recursive(sysbus_get_default(),
+                    n->primary_device_id);
+        } else {
+            return NULL;
+        }
+    }
+    return dev;
+}
+
+
+
+static DeviceState *virtio_connect_failover_devices(VirtIONet *n,
+                                                    DeviceState *dev,
+                                                    Error **errp)
+{
+    DeviceState *prim_dev = NULL;
+
+    prim_dev = virtio_net_find_primary(n, *errp);
+    if (prim_dev) {
+        n->primary_device_id = g_strdup(prim_dev->id);
+        n->primary_device_opts = prim_dev->opts;
+    } else {
+        error_setg(errp, "connect: virtio_net: Could not find primary device");
+    }
+
+    return prim_dev;
+}
+
 static void virtio_net_set_features(VirtIODevice *vdev, uint64_t features)
 {
     VirtIONet *n = VIRTIO_NET(vdev);
+    Error *err = NULL;
     int i;
 
     if (n->mtu_bypass_backend &&
@@ -790,6 +875,22 @@ static void virtio_net_set_features(VirtIODevice *vdev, uint64_t features)
     } else {
         memset(n->vlans, 0xff, MAX_VLAN >> 3);
     }
+
+    if (virtio_has_feature(features, VIRTIO_NET_F_STANDBY)) {
+        atomic_set(&n->primary_should_be_hidden, false);
+        failover_add_primary(n);
+        if (!n->primary_dev) {
+            n->primary_dev = virtio_connect_failover_devices(n, n->qdev, &err);
+            if (!n->primary_dev) {
+                failover_add_primary(n);
+                n->primary_dev = virtio_connect_failover_devices(n, n->qdev,
+                                                                 &err);
+            }
+        }
+    }
+    if (err) {
+        error_report_err(err);
+    }
 }
 
 static int virtio_net_handle_rx_mode(VirtIONet *n, uint8_t cmd,
@@ -2630,6 +2731,135 @@ void virtio_net_set_netclient_name(VirtIONet *n, const char *name,
     n->netclient_type = g_strdup(type);
 }
 
+static bool failover_unplug_primary(VirtIONet *n)
+{
+    HotplugHandler *hotplug_ctrl;
+    PCIDevice *pci_dev;
+    Error *err = NULL;
+
+    hotplug_ctrl = qdev_get_hotplug_handler(n->primary_dev);
+    if (hotplug_ctrl) {
+        pci_dev = PCI_DEVICE(n->primary_dev);
+        pci_dev->partially_hotplugged = true;
+        hotplug_handler_unplug_request(hotplug_ctrl, n->primary_dev, &err);
+        if (err) {
+            error_report_err(err);
+            return false;
+        }
+    } else {
+        return false;
+    }
+    return true;
+}
+
+static bool failover_replug_primary(VirtIONet *n, Error **errp)
+{
+    HotplugHandler *hotplug_ctrl;
+    PCIDevice *pdev = PCI_DEVICE(n->primary_dev);
+
+    if (!pdev->partially_hotplugged) {
+        return true;
+    }
+    if (!n->primary_device_opts) {
+        n->primary_device_opts = qemu_opts_from_qdict(
+                qemu_find_opts("device"),
+                n->primary_device_dict, errp);
+    }
+    if (n->primary_device_opts) {
+        qdev_set_parent_bus(n->primary_dev, n->primary_bus);
+        n->primary_should_be_hidden = false;
+        qemu_opt_set_bool(n->primary_device_opts,
+                "partially_hotplugged", true, errp);
+        hotplug_ctrl = qdev_get_hotplug_handler(n->primary_dev);
+        if (hotplug_ctrl) {
+            hotplug_handler_pre_plug(hotplug_ctrl, n->primary_dev, errp);
+            hotplug_handler_plug(hotplug_ctrl, n->primary_dev, errp);
+        }
+        if (!n->primary_dev) {
+            error_setg(errp, "virtio_net: couldn't find primary device");
+        }
+    }
+    return *errp != NULL;
+}
+
+static void virtio_net_handle_migration_primary(VirtIONet *n,
+                                                MigrationState *s)
+{
+    bool should_be_hidden;
+    Error *err = NULL;
+
+    should_be_hidden = atomic_read(&n->primary_should_be_hidden);
+
+    if (!n->primary_dev) {
+        n->primary_dev = virtio_connect_failover_devices(n, n->qdev, &err);
+        if (!n->primary_dev) {
+            return;
+        }
+    }
+
+    if (migration_in_setup(s) && !should_be_hidden &&
+        n->primary_dev) {
+        if (failover_unplug_primary(n)) {
+            vmstate_unregister(n->primary_dev, qdev_get_vmsd(n->primary_dev),
+                    n->primary_dev);
+            qapi_event_send_unplug_primary(n->primary_device_id);
+            atomic_set(&n->primary_should_be_hidden, true);
+        } else {
+            warn_report("virtio_net: Couldn't unplug primary device");
+        }
+    } else if (migration_has_failed(s)) {
+        /* We already unplugged the device let's plugged it back */
+        if (!failover_replug_primary(n, &err)) {
+            if (err) {
+                error_report_err(err);
+            }
+        }
+    }
+}
+
+static void virtio_net_migration_state_notifier(Notifier *notifier, void *data)
+{
+    MigrationState *s = data;
+    VirtIONet *n = container_of(notifier, VirtIONet, migration_state);
+    virtio_net_handle_migration_primary(n, s);
+}
+
+static void virtio_net_primary_should_be_hidden(DeviceListener *listener,
+            QemuOpts *device_opts, bool *match_found, bool *hide)
+{
+    VirtIONet *n = container_of(listener, VirtIONet, primary_listener);
+
+    n->primary_device_dict = qemu_opts_to_qdict(device_opts,
+            n->primary_device_dict);
+    if (n->primary_device_dict) {
+        g_free(n->standby_id);
+        n->standby_id = g_strdup(qdict_get_try_str(n->primary_device_dict,
+                    "net_failover_pair_id"));
+    }
+    if (device_opts && g_strcmp0(n->standby_id, n->netclient_name) == 0) {
+        *match_found = true;
+    } else {
+        *match_found = false;
+        *hide = false;
+        g_free(n->standby_id);
+        n->primary_device_dict = NULL;
+        return;
+    }
+
+    n->primary_device_opts = device_opts;
+
+    /* primary_should_be_hidden is set during feature negotiation */
+    *hide = atomic_read(&n->primary_should_be_hidden);
+
+    if (n->primary_device_dict) {
+        g_free(n->primary_device_id);
+        n->primary_device_id = g_strdup(qdict_get_try_str(
+                    n->primary_device_dict, "id"));
+        if (!n->primary_device_id) {
+            warn_report("primary_device_id NULL");
+        }
+    }
+}
 static void virtio_net_device_realize(DeviceState *dev, Error **errp)
 {
     VirtIODevice *vdev = VIRTIO_DEVICE(dev);
@@ -2660,6 +2890,16 @@ static void virtio_net_device_realize(DeviceState *dev, Error **errp)
         n->host_features |= (1ULL << VIRTIO_NET_F_SPEED_DUPLEX);
     }
 
+    if (n->failover) {
+        n->primary_listener.should_be_hidden =
+            virtio_net_primary_should_be_hidden;
+        atomic_set(&n->primary_should_be_hidden, true);
+        device_listener_register(&n->primary_listener);
+        n->migration_state.notify = virtio_net_migration_state_notifier;
+        add_migration_state_change_notifier(&n->migration_state);
+        n->host_features |= (1ULL << VIRTIO_NET_F_STANDBY);
+    }
+
     virtio_net_set_config_size(n, n->host_features);
     virtio_init(vdev, "virtio-net", VIRTIO_ID_NET, n->config_size);
 
@@ -2782,6 +3022,13 @@ static void virtio_net_device_unrealize(DeviceState *dev, Error **errp)
     g_free(n->mac_table.macs);
     g_free(n->vlans);
 
+    if (n->failover) {
+        g_free(n->primary_device_id);
+        g_free(n->standby_id);
+        qobject_unref(n->primary_device_dict);
+        n->primary_device_dict = NULL;
+    }
+
     max_queues = n->multiqueue ? n->max_queues : 1;
     for (i = 0; i < max_queues; i++) {
         virtio_net_del_queue(n, i);
@@ -2819,6 +3066,23 @@ static int virtio_net_pre_save(void *opaque)
     return 0;
 }
 
+static bool primary_unplug_pending(void *opaque)
+{
+    DeviceState *dev = opaque;
+    VirtIODevice *vdev = VIRTIO_DEVICE(dev);
+    VirtIONet *n = VIRTIO_NET(vdev);
+
+    return n->primary_dev ? n->primary_dev->pending_deleted_event : false;
+}
+
+static bool dev_unplug_pending(void *opaque)
+{
+    DeviceState *dev = opaque;
+    VirtioDeviceClass *vdc = VIRTIO_DEVICE_GET_CLASS(dev);
+
+    return vdc->primary_unplug_pending(dev);
+}
+
 static const VMStateDescription vmstate_virtio_net = {
     .name = "virtio-net",
     .minimum_version_id = VIRTIO_NET_VM_VERSION,
@@ -2828,6 +3092,7 @@ static const VMStateDescription vmstate_virtio_net = {
         VMSTATE_END_OF_LIST()
     },
     .pre_save = virtio_net_pre_save,
+    .dev_unplug_pending = dev_unplug_pending,
 };
 
 static Property virtio_net_properties[] = {
@@ -2889,6 +3154,7 @@ static Property virtio_net_properties[] = {
                      true),
     DEFINE_PROP_INT32("speed", VirtIONet, net_conf.speed, SPEED_UNKNOWN),
     DEFINE_PROP_STRING("duplex", VirtIONet, net_conf.duplex_str),
+    DEFINE_PROP_BOOL("failover", VirtIONet, failover, false),
     DEFINE_PROP_END_OF_LIST(),
 };
 
@@ -2913,6 +3179,7 @@ static void virtio_net_class_init(ObjectClass *klass, void *data)
     vdc->guest_notifier_pending = virtio_net_guest_notifier_pending;
     vdc->legacy_features |= (0x1 << VIRTIO_NET_F_GSO);
     vdc->vmsd = &vmstate_virtio_net_device;
+    vdc->primary_unplug_pending = primary_unplug_pending;
 }
 
 static const TypeInfo virtio_net_info = {
diff --git a/include/hw/virtio/virtio-net.h b/include/hw/virtio/virtio-net.h
index b96f0c643f..3da4ca382a 100644
--- a/include/hw/virtio/virtio-net.h
+++ b/include/hw/virtio/virtio-net.h
@@ -18,6 +18,7 @@
 #include "standard-headers/linux/virtio_net.h"
 #include "hw/virtio/virtio.h"
 #include "net/announce.h"
+#include "qemu/option_int.h"
 
 #define TYPE_VIRTIO_NET "virtio-net-device"
 #define VIRTIO_NET(obj) \
@@ -43,6 +44,7 @@ typedef struct virtio_net_conf
     int32_t speed;
     char *duplex_str;
     uint8_t duplex;
+    char *primary_id_str;
 } virtio_net_conf;
 
 /* Coalesced packets type & status */
@@ -185,6 +187,16 @@ struct VirtIONet {
     AnnounceTimer announce_timer;
     bool needs_vnet_hdr_swap;
     bool mtu_bypass_backend;
+    QemuOpts *primary_device_opts;
+    QDict *primary_device_dict;
+    DeviceState *primary_dev;
+    BusState *primary_bus;
+    char *primary_device_id;
+    char *standby_id;
+    bool primary_should_be_hidden;
+    bool failover;
+    DeviceListener primary_listener;
+    Notifier migration_state;
 };
 
 void virtio_net_set_netclient_name(VirtIONet *n, const char *name,
diff --git a/include/hw/virtio/virtio.h b/include/hw/virtio/virtio.h
index 48e8d04ff6..0c857ecf1a 100644
--- a/include/hw/virtio/virtio.h
+++ b/include/hw/virtio/virtio.h
@@ -159,6 +159,7 @@ typedef struct VirtioDeviceClass {
     void (*save)(VirtIODevice *vdev, QEMUFile *f);
     int (*load)(VirtIODevice *vdev, QEMUFile *f, int version_id);
     const VMStateDescription *vmsd;
+    bool (*primary_unplug_pending)(void *opaque);
 } VirtioDeviceClass;
 
 void virtio_instance_init_common(Object *proxy_obj, void *data,
-- 
2.21.0



  parent reply	other threads:[~2019-10-11 11:25 UTC|newest]

Thread overview: 35+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2019-10-11 11:20 [PATCH v3 0/10] add failover feature for assigned network devices Jens Freimann
2019-10-11 11:20 ` [PATCH v3 01/10] qdev/qbus: add hidden device support Jens Freimann
2019-10-14  9:46   ` Cornelia Huck
2019-10-14 12:02     ` Jens Freimann
2019-10-15 19:19   ` Alex Williamson
2019-10-16  7:04     ` Jens Freimann
2019-10-11 11:20 ` [PATCH v3 02/10] pci: mark devices partially unplugged Jens Freimann
2019-10-16  1:53   ` Alex Williamson
2019-10-11 11:20 ` [PATCH v3 03/10] pci: mark device having guest unplug request pending Jens Freimann
2019-10-11 11:20 ` [PATCH v3 04/10] qapi: add unplug primary event Jens Freimann
2019-10-11 11:20 ` [PATCH v3 05/10] qapi: add failover negotiated event Jens Freimann
2019-10-11 11:20 ` [PATCH v3 06/10] migration: allow unplug during migration for failover devices Jens Freimann
2019-10-11 11:20 ` [PATCH v3 07/10] migration: add new migration state wait-unplug Jens Freimann
2019-10-11 12:57   ` Michael S. Tsirkin
2019-10-11 14:22     ` Jens Freimann
2019-10-11 16:49   ` Dr. David Alan Gilbert
2019-10-11 17:11   ` Dr. David Alan Gilbert
2019-10-15  9:45     ` Jens Freimann
2019-10-15 10:50       ` Dr. David Alan Gilbert
2019-10-16  7:07         ` Jens Freimann
2019-10-11 11:20 ` [PATCH v3 08/10] libqos: tolerate wait-unplug migration state Jens Freimann
2019-10-11 11:20 ` Jens Freimann [this message]
2019-10-11 11:20 ` [PATCH v3 10/10] vfio: unplug failover primary device before migration Jens Freimann
2019-10-14 10:05   ` Cornelia Huck
2019-10-16  1:52   ` Alex Williamson
2019-10-16 20:18     ` Jens Freimann
2019-10-17  0:39       ` Alex Williamson
2019-10-17  7:45         ` Jens Freimann
2019-10-11 14:28 ` [PATCH v3 0/10] add failover feature for assigned network devices Michael S. Tsirkin
2019-10-11 16:04 ` no-reply
2019-10-15 19:03 ` Alex Williamson
2019-10-15 21:17   ` Michael S. Tsirkin
2019-10-17 10:33   ` Jens Freimann
2019-10-17 12:51     ` Alex Williamson
2019-10-17 14:04       ` Jens Freimann

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20191011112015.11785-10-jfreimann@redhat.com \
    --to=jfreimann@redhat.com \
    --cc=aadam@redhat.com \
    --cc=ailan@redhat.com \
    --cc=alex.williamson@redhat.com \
    --cc=dgilbert@redhat.com \
    --cc=ehabkost@redhat.com \
    --cc=laine@redhat.com \
    --cc=mst@redhat.com \
    --cc=parav@mellanox.com \
    --cc=qemu-devel@nongnu.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.