virtio-mem: Paravirtualized memory hot(un)plug

index f104b42961..5fff79523a 100644
@@ -40,7 +40,8 @@ static int balloon_inhibit_count;
 
 bool qemu_balloon_is_inhibited(void)
 {
-    return atomic_read(&balloon_inhibit_count) > 0;
+    return atomic_read(&balloon_inhibit_count) > 0 ||
+           ram_block_discard_is_disabled();
 }
 
 void qemu_balloon_inhibit(bool state)

56 lines not on this page · raw message

47 lines not on this page · raw message

index 95564c17ed..d0b1bc7581 100644
@@ -105,12 +105,12 @@ static void vfio_ap_realize(DeviceState *dev, Error **errp)
     vapdev->vdev.dev = dev;
 
     /*
-     * vfio-ap devices operate in a way compatible with
-     * memory ballooning, as no pages are pinned in the host.
-     * This needs to be set before vfio_get_device() for vfio common to
-     * handle the balloon inhibitor.
+     * vfio-ap devices operate in a way compatible discarding of memory in
+     * RAM blocks, as no pages are pinned in the host. This needs to be
+     * set before vfio_get_device() for vfio common to handle
+     * ram_block_discard_disable().
      */
-    vapdev->vdev.balloon_allowed = true;
+    vapdev->vdev.ram_block_discard_allowed = true;
 
     ret = vfio_get_device(vfio_group, mdevid, &vapdev->vdev, errp);
     if (ret) {

index c8624943c1..12dd44da52 100644
@@ -425,12 +425,13 @@ static void vfio_ccw_get_device(VFIOGroup *group, VFIOCCWDevice *vcdev,
 
     /*
      * All vfio-ccw devices are believed to operate in a way compatible with
-     * memory ballooning, ie. pages pinned in the host are in the current
-     * working set of the guest driver and therefore never overlap with pages
-     * available to the guest balloon driver.  This needs to be set before
-     * vfio_get_device() for vfio common to handle the balloon inhibitor.
+     * discarding of memory in RAM blocks, ie. pages pinned in the host are
+     * in the current working set of the guest driver and therefore never
+     * overlap e.g., with pages available to the guest balloon driver.  This
+     * needs to be set before vfio_get_device() for vfio common to handle
+     * ram_block_discard_disable().
      */
-    vcdev->vdev.balloon_allowed = true;
+    vcdev->vdev.ram_block_discard_allowed = true;
 
     if (vfio_get_device(group, vcdev->cdev.mdevid, &vcdev->vdev, errp)) {
         goto out_err;

104 lines not on this page · raw message

index 342dd6b912..c33c11b7e4 100644
@@ -2796,7 +2796,7 @@ static void vfio_realize(PCIDevice *pdev, Error **errp)
     }
 
     /*
-     * Mediated devices *might* operate compatibly with memory ballooning, but
+     * Mediated devices *might* operate compatibly with discarding of RAM, but
      * we cannot know for certain, it depends on whether the mdev vendor driver
      * stays in sync with the active working set of the guest driver.  Prevent
      * the x-balloon-allowed option unless this is minimally an mdev device.

@@ -2809,7 +2809,7 @@ static void vfio_realize(PCIDevice *pdev, Error **errp)
 
     trace_vfio_mdev(vdev->vbasedev.name, is_mdev);
 
-    if (vdev->vbasedev.balloon_allowed && !is_mdev) {
+    if (vdev->vbasedev.ram_block_discard_allowed && !is_mdev) {
         error_setg(errp, "x-balloon-allowed only potentially compatible "
                    "with mdev devices");
         vfio_put_group(group);

@@ -3163,7 +3163,7 @@ static Property vfio_pci_dev_properties[] = {
                     VFIO_FEATURE_ENABLE_IGD_OPREGION_BIT, false),
     DEFINE_PROP_BOOL("x-no-mmap", VFIOPCIDevice, vbasedev.no_mmap, false),
     DEFINE_PROP_BOOL("x-balloon-allowed", VFIOPCIDevice,
-                     vbasedev.balloon_allowed, false),
+                     vbasedev.ram_block_discard_allowed, false),
     DEFINE_PROP_BOOL("x-no-kvm-intx", VFIOPCIDevice, no_kvm_intx, false),
     DEFINE_PROP_BOOL("x-no-kvm-msi", VFIOPCIDevice, no_kvm_msi, false),
     DEFINE_PROP_BOOL("x-no-kvm-msix", VFIOPCIDevice, no_kvm_msix, false),

index fd564209ac..c78f3ff559 100644
@@ -108,7 +108,7 @@ typedef struct VFIODevice {
     bool reset_works;
     bool needs_reset;
     bool no_mmap;
-    bool balloon_allowed;
+    bool ram_block_discard_allowed;
     VFIODeviceOps *ops;
     unsigned int num_irqs;
     unsigned int num_regions;

@@ -128,7 +128,7 @@ typedef struct VFIOGroup {
     QLIST_HEAD(, VFIODevice) device_list;
     QLIST_ENTRY(VFIOGroup) next;
     QLIST_ENTRY(VFIOGroup) container_next;
-    bool balloon_allowed;
+    bool ram_block_discard_allowed;
 } VFIOGroup;
 
 typedef struct VFIODMABuf {

index d06cc04079..fa18b2caae 100644
@@ -40,7 +40,6 @@
 #include "trace.h"
 #include "hw/irq.h"
 #include "sysemu/sev.h"
-#include "sysemu/balloon.h"
 #include "qapi/visitor.h"
 #include "qapi/qapi-types-common.h"
 #include "qapi/qapi-visit-common.h"

@@ -2143,7 +2142,8 @@ static int kvm_init(MachineState *ms)
 
     s->sync_mmu = !!kvm_vm_check_extension(kvm_state, KVM_CAP_SYNC_MMU);
     if (!s->sync_mmu) {
-        qemu_balloon_inhibit(true);
+        ret = ram_block_discard_disable(true);
+        assert(!ret);
     }
 
     return 0;

index 67ae2e02ff..e82129e874 100644
@@ -43,7 +43,6 @@
 #include "hw/qdev-properties.h"
 #include "hw/s390x/tod.h"
 #include "sysemu/sysemu.h"
-#include "sysemu/balloon.h"
 #include "hw/s390x/pv.h"
 #include "migration/blocker.h"
 

@@ -329,7 +328,7 @@ static void s390_machine_unprotect(S390CcwMachineState *ms)
     ms->pv = false;
     migrate_del_blocker(pv_mig_blocker);
     error_free_or_abort(&pv_mig_blocker);
-    qemu_balloon_inhibit(false);
+    ram_block_discard_disable(false);
 }
 
 static int s390_machine_protect(S390CcwMachineState *ms)

@@ -338,17 +337,22 @@ static int s390_machine_protect(S390CcwMachineState *ms)
     int rc;
 
    /*
-    * Ballooning on protected VMs needs support in the guest for
-    * sharing and unsharing balloon pages. Block ballooning for
-    * now, until we have a solution to make at least Linux guests
-    * either support it or fail gracefully.
+    * Discarding of memory in RAM blocks does not work as expected with
+    * protected VMs. Sharing and unsharing pages would be required. Disable
+    * it for now, until until we have a solution to make at least Linux
+    * guests either support it (e.g., virtio-balloon) or fail gracefully.
     */
-    qemu_balloon_inhibit(true);
+    rc = ram_block_discard_disable(true);
+    if (rc) {
+        error_report("protected VMs: cannot disable RAM discard");
+        return rc;
+    }
+
     error_setg(&pv_mig_blocker,
                "protected VMs are currently not migrateable.");
     rc = migrate_add_blocker(pv_mig_blocker, &local_err);
     if (rc) {
-        qemu_balloon_inhibit(false);
+        ram_block_discard_disable(false);
         error_report_err(local_err);
         error_free_or_abort(&pv_mig_blocker);
         return rc;

@@ -357,7 +361,7 @@ static int s390_machine_protect(S390CcwMachineState *ms)
     /* Create SE VM */
     rc = s390_pv_vm_enable();
     if (rc) {
-        qemu_balloon_inhibit(false);
+        ram_block_discard_disable(false);
         migrate_del_blocker(pv_mig_blocker);
         error_free_or_abort(&pv_mig_blocker);
         return rc;

index 5fff79523a..354408c6ea 100644
@@ -36,24 +36,6 @@
 static QEMUBalloonEvent *balloon_event_fn;
 static QEMUBalloonStatus *balloon_stat_fn;
 static void *balloon_opaque;
-static int balloon_inhibit_count;
-
-bool qemu_balloon_is_inhibited(void)
-{
-    return atomic_read(&balloon_inhibit_count) > 0 ||
-           ram_block_discard_is_disabled();
-}
-
-void qemu_balloon_inhibit(bool state)
-{
-    if (state) {
-        atomic_inc(&balloon_inhibit_count);
-    } else {
-        atomic_dec(&balloon_inhibit_count);
-    }
-
-    assert(atomic_read(&balloon_inhibit_count) >= 0);
-}
 
 static bool have_balloon(Error **errp)
 {

index 065cd450f1..5ce2f956df 100644
@@ -63,6 +63,12 @@ static bool virtio_balloon_pbp_matches(PartiallyBalloonedPage *pbp,
     return pbp->base_gpa == base_gpa;
 }
 
+static bool virtio_balloon_inhibited(void)
+{
+    /* Postcopy cannot deal with concurrent discards, so it's special. */
+    return ram_block_discard_is_disabled() || migration_in_incoming_postcopy();
+}
+
 static void balloon_inflate_page(VirtIOBalloon *balloon,
                                  MemoryRegion *mr, hwaddr mr_offset,
                                  PartiallyBalloonedPage *pbp)

@@ -360,7 +366,7 @@ static void virtio_balloon_handle_output(VirtIODevice *vdev, VirtQueue *vq)
 
             trace_virtio_balloon_handle_output(memory_region_name(section.mr),
                                                pa);
-            if (!qemu_balloon_is_inhibited()) {
+            if (!virtio_balloon_inhibited()) {
                 if (vq == s->ivq) {
                     balloon_inflate_page(s, section.mr,
                                          section.offset_within_region, &pbp);

index d2762257aa..34e7d75713 100644
@@ -69,6 +69,8 @@ bool migration_has_failed(MigrationState *);
 /* ...and after the device transmission */
 bool migration_in_postcopy_after_devices(MigrationState *);
 void migration_global_dump(Monitor *mon);
+/* True if incomming migration entered POSTCOPY_INCOMING_DISCARD */
+bool migration_in_incoming_postcopy(void);
 
 /* migration/block-dirty-bitmap.c */
 void dirty_bitmap_mig_init(void);

index aea0c44985..20a2defe3a 100644
@@ -23,7 +23,5 @@ typedef void (QEMUBalloonStatus)(void *opaque, BalloonInfo *info);
 int qemu_add_balloon_handler(QEMUBalloonEvent *event_func,
                              QEMUBalloonStatus *stat_func, void *opaque);
 void qemu_remove_balloon_handler(void *opaque);
-bool qemu_balloon_is_inhibited(void);
-void qemu_balloon_inhibit(bool state);
 
 #endif

index b63ad91d34..14856cc930 100644
@@ -1772,6 +1772,13 @@ bool migration_in_postcopy_after_devices(MigrationState *s)
     return migration_in_postcopy() && s->postcopy_after_devices;
 }
 
+bool migration_in_incoming_postcopy(void)
+{
+    PostcopyState ps = postcopy_state_get();
+
+    return ps >= POSTCOPY_INCOMING_DISCARD && ps < POSTCOPY_INCOMING_END;
+}
+
 bool migration_is_idle(void)
 {
     MigrationState *s = current_migration;

index a36402722b..b41a9fe2fd 100644
@@ -27,7 +27,6 @@
 #include "qemu/notify.h"
 #include "qemu/rcu.h"
 #include "sysemu/sysemu.h"
-#include "sysemu/balloon.h"
 #include "qemu/error-report.h"
 #include "trace.h"
 #include "hw/boards.h"

@@ -520,20 +519,6 @@ int postcopy_ram_incoming_init(MigrationIncomingState *mis)
     return 0;
 }
 
-/*
- * Manage a single vote to the QEMU balloon inhibitor for all postcopy usage,
- * last caller wins.
- */
-static void postcopy_balloon_inhibit(bool state)
-{
-    static bool cur_state = false;
-
-    if (state != cur_state) {
-        qemu_balloon_inhibit(state);
-        cur_state = state;
-    }
-}
-
 /*
  * At the end of a migration where postcopy_ram_incoming_init was called.
  */

@@ -565,8 +550,6 @@ int postcopy_ram_incoming_cleanup(MigrationIncomingState *mis)
         mis->have_fault_thread = false;
     }
 
-    postcopy_balloon_inhibit(false);
-
     if (enable_mlock) {
         if (os_mlock() < 0) {
             error_report("mlock: %s", strerror(errno));

@@ -1160,12 +1143,6 @@ int postcopy_ram_incoming_setup(MigrationIncomingState *mis)
     }
     memset(mis->postcopy_tmp_zero_page, '\0', mis->largest_page_size);
 
-    /*
-     * Ballooning can mark pages as absent while we're postcopying
-     * that would cause false userfaults.
-     */
-    postcopy_balloon_inhibit(true);
-
     trace_postcopy_ram_enable_notify();
 
     return 0;

index 51cdbe5496..4a4863db28 100644
@@ -649,6 +649,12 @@ sev_guest_init(const char *id)
     uint32_t host_cbitpos;
     struct sev_user_data_status status = {};
 
+    ret = ram_block_discard_disable(true);
+    if (ret) {
+        error_report("%s: cannot disable RAM discard", __func__);
+        return NULL;
+    }
+
     sev_state = s = g_new0(SEVState, 1);
     s->sev_info = lookup_sev_guest_info(id);
     if (!s->sev_info) {

@@ -724,6 +730,7 @@ sev_guest_init(const char *id)
 err:
     g_free(sev_state);
     sev_state = NULL;
+    ram_block_discard_disable(false);
     return NULL;
 }
 

index ec45d33ba3..bbe6f36627 100644
@@ -29,6 +29,7 @@
 #include "qemu/sockets.h"
 #include "qemu/bitmap.h"
 #include "qemu/coroutine.h"
+#include "exec/memory.h"
 #include <sys/socket.h>
 #include <netdb.h>
 #include <arpa/inet.h>

@@ -4017,8 +4018,14 @@ void rdma_start_incoming_migration(const char *host_port, Error **errp)
     Error *local_err = NULL;
 
     trace_rdma_start_incoming_migration();
-    rdma = qemu_rdma_data_init(host_port, &local_err);
 
+    /* Avoid ram_block_discard_disable(), cannot change during migration. */
+    if (ram_block_discard_is_required()) {
+        error_setg(errp, "RDMA: cannot disable RAM discard");
+        return;
+    }
+
+    rdma = qemu_rdma_data_init(host_port, &local_err);
     if (rdma == NULL) {
         goto err;
     }

@@ -4067,10 +4074,17 @@ void rdma_start_outgoing_migration(void *opaque,
                             const char *host_port, Error **errp)
 {
     MigrationState *s = opaque;
-    RDMAContext *rdma = qemu_rdma_data_init(host_port, errp);
     RDMAContext *rdma_return_path = NULL;
+    RDMAContext *rdma;
     int ret = 0;
 
+    /* Avoid ram_block_discard_disable(), cannot change during migration. */
+    if (ram_block_discard_is_required()) {
+        error_setg(errp, "RDMA: cannot disable RAM discard");
+        return;
+    }
+
+    rdma = qemu_rdma_data_init(host_port, errp);
     if (rdma == NULL) {
         goto err;
     }

index 1636e6f907..768e1f04c3 100644
@@ -25,7 +25,7 @@ void migrate_start_colo_process(MigrationState *s);
 bool migration_in_colo_state(void);
 
 /* loadvm */
-void migration_incoming_enable_colo(void);
+int migration_incoming_enable_colo(void);
 void migration_incoming_disable_colo(void);
 bool migration_incoming_colo_enabled(void);
 void *colo_process_incoming_thread(void *opaque);

index 14856cc930..0f6799f5d2 100644
@@ -338,12 +338,18 @@ bool migration_incoming_colo_enabled(void)
 
 void migration_incoming_disable_colo(void)
 {
+    ram_block_discard_disable(false);
     migration_colo_enabled = false;
 }
 
-void migration_incoming_enable_colo(void)
+int migration_incoming_enable_colo(void)
 {
+    if (ram_block_discard_disable(true)) {
+        error_report("COLO: cannot disable RAM discard");
+        return -EBUSY;
+    }
     migration_colo_enabled = true;
+    return 0;
 }
 
 void migrate_add_address(SocketAddress *address)

index c00a6807d9..19b4f9600d 100644
@@ -2111,8 +2111,15 @@ static int loadvm_handle_recv_bitmap(MigrationIncomingState *mis,
 
 static int loadvm_process_enable_colo(MigrationIncomingState *mis)
 {
-    migration_incoming_enable_colo();
-    return colo_init_ram_cache();
+    int ret = migration_incoming_enable_colo();
+
+    if (!ret) {
+        ret = colo_init_ram_cache();
+        if (ret) {
+            migration_incoming_disable_colo();
+        }
+    }
+    return ret;
 }
 
 /*

index ecc27a1740..b052355ac7 100644
@@ -44,6 +44,7 @@
 #define VIRTIO_ID_VSOCK        19 /* virtio vsock transport */
 #define VIRTIO_ID_CRYPTO       20 /* virtio crypto */
 #define VIRTIO_ID_IOMMU        23 /* virtio IOMMU */
+#define VIRTIO_ID_MEM          24 /* virtio mem */
 #define VIRTIO_ID_FS           26 /* virtio filesystem */
 #define VIRTIO_ID_PMEM         27 /* virtio pmem */
 #define VIRTIO_ID_MAC80211_HWSIM 29 /* virtio mac80211-hwsim */

211 lines not on this page · raw message

728 lines not on this page · raw message

78 lines not on this page · raw message

129 lines not on this page · raw message

new file mode 100644
index 0000000000..8820cd6628
@@ -0,0 +1,33 @@
+/*
+ * Virtio MEM PCI device
+ *
+ * Copyright (C) 2020 Red Hat, Inc.
+ *
+ * Authors:
+ *  David Hildenbrand <[email protected]>
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2.
+ * See the COPYING file in the top-level directory.
+ */
+
+#ifndef QEMU_VIRTIO_MEM_PCI_H
+#define QEMU_VIRTIO_MEM_PCI_H
+
+#include "hw/virtio/virtio-pci.h"
+#include "hw/virtio/virtio-mem.h"
+
+typedef struct VirtIOMEMPCI VirtIOMEMPCI;
+
+/*
+ * virtio-mem-pci: This extends VirtioPCIProxy.
+ */
+#define TYPE_VIRTIO_MEM_PCI "virtio-mem-pci-base"
+#define VIRTIO_MEM_PCI(obj) \
+        OBJECT_CHECK(VirtIOMEMPCI, (obj), TYPE_VIRTIO_MEM_PCI)
+
+struct VirtIOMEMPCI {
+    VirtIOPCIProxy parent_obj;
+    VirtIOMEM vdev;
+};
+
+#endif /* QEMU_VIRTIO_MEM_PCI_H */

index cfedf5a995..fec72d5a31 100644
@@ -87,6 +87,7 @@ extern bool pci_available;
 #define PCI_DEVICE_ID_VIRTIO_VSOCK       0x1012
 #define PCI_DEVICE_ID_VIRTIO_PMEM        0x1013
 #define PCI_DEVICE_ID_VIRTIO_IOMMU       0x1014
+#define PCI_DEVICE_ID_VIRTIO_MEM         0x1015
 
 #define PCI_VENDOR_ID_REDHAT             0x1b36
 #define PCI_DEVICE_ID_REDHAT_BRIDGE      0x0001

index 9c61e769ca..afc9a28069 100644
@@ -1818,6 +1818,7 @@ void hmp_info_memory_devices(Monitor *mon, const QDict *qdict)
     MemoryDeviceInfoList *info_list = qmp_query_memory_devices(&err);
     MemoryDeviceInfoList *info;
     VirtioPMEMDeviceInfo *vpi;
+    VirtioMEMDeviceInfo *vmi;
     MemoryDeviceInfo *value;
     PCDIMMDeviceInfo *di;
 

@@ -1852,6 +1853,21 @@ void hmp_info_memory_devices(Monitor *mon, const QDict *qdict)
                 monitor_printf(mon, "  size: %" PRIu64 "\n", vpi->size);
                 monitor_printf(mon, "  memdev: %s\n", vpi->memdev);
                 break;
+            case MEMORY_DEVICE_INFO_KIND_VIRTIO_MEM:
+                vmi = value->u.virtio_mem.data;
+                monitor_printf(mon, "Memory device [%s]: \"%s\"\n",
+                               MemoryDeviceInfoKind_str(value->type),
+                               vmi->id ? vmi->id : "");
+                monitor_printf(mon, "  memaddr: 0x%" PRIx64 "\n", vmi->memaddr);
+                monitor_printf(mon, "  node: %" PRId64 "\n", vmi->node);
+                monitor_printf(mon, "  requested-size: %" PRIu64 "\n",
+                               vmi->requested_size);
+                monitor_printf(mon, "  size: %" PRIu64 "\n", vmi->size);
+                monitor_printf(mon, "  max-size: %" PRIu64 "\n", vmi->max_size);
+                monitor_printf(mon, "  block-size: %" PRIu64 "\n",
+                               vmi->block_size);
+                monitor_printf(mon, "  memdev: %s\n", vmi->memdev);
+                break;
             default:
                 g_assert_not_reached();
             }

index 316bc50d75..06960918e7 100644
@@ -812,6 +812,7 @@ static void numa_stat_memory_devices(NumaNodeMem node_mem[])
     MemoryDeviceInfoList *info;
     PCDIMMDeviceInfo     *pcdimm_info;
     VirtioPMEMDeviceInfo *vpi;
+    VirtioMEMDeviceInfo *vmi;
 
     for (info = info_list; info; info = info->next) {
         MemoryDeviceInfo *value = info->value;

@@ -832,6 +833,11 @@ static void numa_stat_memory_devices(NumaNodeMem node_mem[])
                 node_mem[0].node_mem += vpi->size;
                 node_mem[0].node_plugged_mem += vpi->size;
                 break;
+            case MEMORY_DEVICE_INFO_KIND_VIRTIO_MEM:
+                vmi = value->u.virtio_mem.data;
+                node_mem[vmi->node].node_mem += vmi->size;
+                node_mem[vmi->node].node_plugged_mem += vmi->size;
+                break;
             default:
                 g_assert_not_reached();
             }

113 lines not on this page · raw message

index 1fdad64696..455d957e17 100644
@@ -184,6 +184,7 @@ static int virtio_mem_state_change_request(VirtIOMEM *vmem, uint64_t gpa,
     } else {
         vmem->size -= size;
     }
+    notifier_list_notify(&vmem->size_change_notifiers, &vmem->size);
     return VIRTIO_MEM_RESP_ACK;
 }
 

@@ -242,7 +243,10 @@ static int virtio_mem_unplug_all(VirtIOMEM *vmem)
         return -EBUSY;
     }
     bitmap_clear(vmem->bitmap, 0, vmem->bitmap_size);
-    vmem->size = 0;
+    if (vmem->size) {
+        vmem->size = 0;
+        notifier_list_notify(&vmem->size_change_notifiers, &vmem->size);
+    }
 
     virtio_mem_resize_usable_region(vmem, vmem->requested_size, true);
     return 0;

@@ -561,6 +565,18 @@ static MemoryRegion *virtio_mem_get_memory_region(VirtIOMEM *vmem, Error **errp)
     return &vmem->memdev->mr;
 }
 
+static void virtio_mem_add_size_change_notifier(VirtIOMEM *vmem,
+                                                Notifier *notifier)
+{
+    notifier_list_add(&vmem->size_change_notifiers, notifier);
+}
+
+static void virtio_mem_remove_size_change_notifier(VirtIOMEM *vmem,
+                                                   Notifier *notifier)
+{
+    notifier_remove(notifier);
+}
+
 static void virtio_mem_get_size(Object *obj, Visitor *v, const char *name,
                                 void *opaque, Error **errp)
 {

@@ -672,6 +688,7 @@ static void virtio_mem_instance_init(Object *obj)
     VirtIOMEM *vmem = VIRTIO_MEM(obj);
 
     vmem->block_size = VIRTIO_MEM_MIN_BLOCK_SIZE;
+    notifier_list_init(&vmem->size_change_notifiers);
 
     object_property_add(obj, VIRTIO_MEM_SIZE_PROP, "size", virtio_mem_get_size,
                         NULL, NULL, NULL);

@@ -709,6 +726,8 @@ static void virtio_mem_class_init(ObjectClass *klass, void *data)
 
     vmc->fill_device_info = virtio_mem_fill_device_info;
     vmc->get_memory_region = virtio_mem_get_memory_region;
+    vmc->add_size_change_notifier = virtio_mem_add_size_change_notifier;
+    vmc->remove_size_change_notifier = virtio_mem_remove_size_change_notifier;
 }
 
 static const TypeInfo virtio_mem_info = {

index 26b90e8f3e..408a6ede50 100644
@@ -64,6 +64,9 @@ typedef struct VirtIOMEM {
 
     /* block size and alignment */
     uint32_t block_size;
+
+    /* notifiers to notify when "size" changes */
+    NotifierList size_change_notifiers;
 } VirtIOMEM;
 
 typedef struct VirtIOMEMClass {

@@ -73,6 +76,8 @@ typedef struct VirtIOMEMClass {
     /* public */
     void (*fill_device_info)(const VirtIOMEM *vmen, VirtioMEMDeviceInfo *vi);
     MemoryRegion *(*get_memory_region)(VirtIOMEM *vmem, Error **errp);
+    void (*add_size_change_notifier)(VirtIOMEM *vmem, Notifier *notifier);
+    void (*remove_size_change_notifier)(VirtIOMEM *vmem, Notifier *notifier);
 } VirtIOMEMClass;
 
 #endif

index b325303b32..1a8e854123 100644
@@ -14,6 +14,7 @@
 #include "virtio-mem-pci.h"
 #include "hw/mem/memory-device.h"
 #include "qapi/error.h"
+#include "qapi/qapi-events-misc.h"
 
 static void virtio_mem_pci_realize(VirtIOPCIProxy *vpci_dev, Error **errp)
 {

@@ -74,6 +75,21 @@ static void virtio_mem_pci_fill_device_info(const MemoryDeviceState *md,
     info->type = MEMORY_DEVICE_INFO_KIND_VIRTIO_MEM;
 }
 
+static void virtio_mem_pci_size_change_notify(Notifier *notifier, void *data)
+{
+    VirtIOMEMPCI *pci_mem = container_of(notifier, VirtIOMEMPCI,
+                                         size_change_notifier);
+    DeviceState *dev = DEVICE(pci_mem);
+    const uint64_t * const size_p = data;
+    const char *id = NULL;
+
+    if (dev->id) {
+        id = g_strdup(dev->id);
+    }
+
+    qapi_event_send_memory_device_size_change(!!id, id, *size_p);
+}
+
 static void virtio_mem_pci_class_init(ObjectClass *klass, void *data)
 {
     DeviceClass *dc = DEVICE_CLASS(klass);

@@ -98,9 +114,21 @@ static void virtio_mem_pci_class_init(ObjectClass *klass, void *data)
 static void virtio_mem_pci_instance_init(Object *obj)
 {
     VirtIOMEMPCI *dev = VIRTIO_MEM_PCI(obj);
+    VirtIOMEMClass *vmc;
+    VirtIOMEM *vmem;
 
     virtio_instance_init_common(obj, &dev->vdev, sizeof(dev->vdev),
                                 TYPE_VIRTIO_MEM);
+
+    dev->size_change_notifier.notify = virtio_mem_pci_size_change_notify;
+    vmem = VIRTIO_MEM(&dev->vdev);
+    vmc = VIRTIO_MEM_GET_CLASS(vmem);
+    /*
+     * We never remove the notifier again, as we expect both devices to
+     * disappear at the same time.
+     */
+    vmc->add_size_change_notifier(vmem, &dev->size_change_notifier);
+
     object_property_add_alias(obj, VIRTIO_MEM_BLOCK_SIZE_PROP,
                               OBJECT(&dev->vdev), VIRTIO_MEM_BLOCK_SIZE_PROP);
     object_property_add_alias(obj, VIRTIO_MEM_SIZE_PROP, OBJECT(&dev->vdev),

index 8820cd6628..b51a28b275 100644
@@ -28,6 +28,7 @@ typedef struct VirtIOMEMPCI VirtIOMEMPCI;
 struct VirtIOMEMPCI {
     VirtIOPCIProxy parent_obj;
     VirtIOMEM vdev;
+    Notifier size_change_notifier;
 };
 
 #endif /* QEMU_VIRTIO_MEM_PCI_H */

index 125494410a..19dcb8fbe3 100644
@@ -235,6 +235,7 @@ static MonitorQAPIEventConf monitor_qapi_event_conf[QAPI_EVENT__MAX] = {
     [QAPI_EVENT_QUORUM_REPORT_BAD] = { 1000 * SCALE_MS },
     [QAPI_EVENT_QUORUM_FAILURE]    = { 1000 * SCALE_MS },
     [QAPI_EVENT_VSERPORT_CHANGE]   = { 1000 * SCALE_MS },
+    [QAPI_EVENT_MEMORY_DEVICE_SIZE_CHANGE] = { 1000 * SCALE_MS },
 };
 
 /*

index 455d957e17..158215613c 100644
@@ -519,12 +519,81 @@ static int virtio_mem_post_load(void *opaque, int version_id)
     return virtio_mem_restore_unplugged(VIRTIO_MEM(opaque));
 }
 
+typedef struct VirtIOMEMMigSanityChecks {
+    VirtIOMEM *parent;
+    uint64_t addr;
+    uint64_t region_size;
+    uint32_t block_size;
+    uint32_t node;
+} VirtIOMEMMigSanityChecks;
+
+static int virtio_mem_mig_sanity_checks_pre_save(void *opaque)
+{
+    VirtIOMEMMigSanityChecks *tmp = opaque;
+    VirtIOMEM *vmem = tmp->parent;
+
+    tmp->addr = vmem->addr;
+    tmp->region_size = memory_region_size(&vmem->memdev->mr);
+    tmp->block_size = vmem->block_size;
+    tmp->node = vmem->node;
+    return 0;
+}
+
+static int virtio_mem_mig_sanity_checks_post_load(void *opaque, int version_id)
+{
+    VirtIOMEMMigSanityChecks *tmp = opaque;
+    VirtIOMEM *vmem = tmp->parent;
+    const uint64_t new_region_size = memory_region_size(&vmem->memdev->mr);
+
+    if (tmp->addr != vmem->addr) {
+        error_report("Property '%s' changed from 0x%" PRIx64 " to 0x%" PRIx64,
+                     VIRTIO_MEM_ADDR_PROP, tmp->addr, vmem->addr);
+        return -EINVAL;
+    }
+    /*
+     * Note: Preparation for resizeable memory regions. The maximum size
+     * of the memory region must not change during migration.
+     */
+    if (tmp->region_size != new_region_size) {
+        error_report("region size changed from 0x%" PRIx64 " to 0x%" PRIx64,
+                     tmp->region_size, new_region_size);
+        return -EINVAL;
+    }
+    if (tmp->block_size != vmem->block_size) {
+        error_report("Property '%s' changed from %0x" PRIx32 " to %0x" PRIx32,
+                     VIRTIO_MEM_BLOCK_SIZE_PROP, tmp->block_size,
+                     vmem->block_size);
+        return -EINVAL;
+    }
+    if (tmp->node != vmem->node) {
+        error_report("Property '%s' changed from %" PRIu32 " to %" PRIu32,
+                     VIRTIO_MEM_NODE_PROP, tmp->node, vmem->node);
+        return -EINVAL;
+    }
+    return 0;
+}
+
+static const VMStateDescription vmstate_virtio_mem_sanity_checks = {
+    .name = "virtio-mem-device/sanity-checks",
+    .pre_save = virtio_mem_mig_sanity_checks_pre_save,
+    .post_load = virtio_mem_mig_sanity_checks_post_load,
+    .fields = (VMStateField[]) {
+        VMSTATE_UINT64(addr, VirtIOMEMMigSanityChecks),
+        VMSTATE_UINT64(region_size, VirtIOMEMMigSanityChecks),
+        VMSTATE_UINT32(block_size, VirtIOMEMMigSanityChecks),
+        VMSTATE_UINT32(node, VirtIOMEMMigSanityChecks),
+        VMSTATE_END_OF_LIST(),
+    },
+};
+
 static const VMStateDescription vmstate_virtio_mem_device = {
     .name = "virtio-mem-device",
     .minimum_version_id = 1,
     .version_id = 1,
     .post_load = virtio_mem_post_load,
     .fields = (VMStateField[]) {
+        VMSTATE_WITH_TMP(VirtIOMEM, VirtIOMEMMigSanityChecks,
+                         vmstate_virtio_mem_sanity_checks),
         VMSTATE_UINT64(usable_region_size, VirtIOMEM),
         VMSTATE_UINT64(size, VirtIOMEM),
         VMSTATE_UINT64(requested_size, VirtIOMEM),

index 158215613c..4d0a2e78c0 100644
@@ -30,6 +30,7 @@
 #include "hw/boards.h"
 #include "hw/qdev-properties.h"
 #include "config-devices.h"
+#include "trace.h"
 
 /*
  * Use QEMU_VMALLOC_ALIGN, so no THP will have to be split when unplugging

@@ -100,6 +101,7 @@ static void virtio_mem_send_response(VirtIOMEM *vmem, VirtQueueElement *elem,
     VirtIODevice *vdev = VIRTIO_DEVICE(vmem);
     VirtQueue *vq = vmem->vq;
 
+    trace_virtio_mem_send_response(le16_to_cpu(resp->type));
     iov_from_buf(elem->in_sg, elem->in_num, 0, resp, sizeof(*resp));
 
     virtqueue_push(vq, elem, sizeof(*resp));

@@ -195,6 +197,7 @@ static void virtio_mem_plug_request(VirtIOMEM *vmem, VirtQueueElement *elem,
     const uint16_t nb_blocks = le16_to_cpu(req->u.plug.nb_blocks);
     uint16_t type;
 
+    trace_virtio_mem_plug_request(gpa, nb_blocks);
     type = virtio_mem_state_change_request(vmem, gpa, nb_blocks, true);
     virtio_mem_send_response_simple(vmem, elem, type);
 }

@@ -206,6 +209,7 @@ static void virtio_mem_unplug_request(VirtIOMEM *vmem, VirtQueueElement *elem,
     const uint16_t nb_blocks = le16_to_cpu(req->u.unplug.nb_blocks);
     uint16_t type;
 
+    trace_virtio_mem_unplug_request(gpa, nb_blocks);
     type = virtio_mem_state_change_request(vmem, gpa, nb_blocks, false);
     virtio_mem_send_response_simple(vmem, elem, type);
 }

@@ -225,6 +229,7 @@ static void virtio_mem_resize_usable_region(VirtIOMEM *vmem,
         return;
     }
 
+    trace_virtio_mem_resized_usable_region(vmem->usable_region_size, newsize);
     vmem->usable_region_size = newsize;
 }
 

@@ -247,7 +252,7 @@ static int virtio_mem_unplug_all(VirtIOMEM *vmem)
         vmem->size = 0;
         notifier_list_notify(&vmem->size_change_notifiers, &vmem->size);
     }
-
+    trace_virtio_mem_unplugged_all();
     virtio_mem_resize_usable_region(vmem, vmem->requested_size, true);
     return 0;
 }

@@ -255,6 +260,7 @@ static int virtio_mem_unplug_all(VirtIOMEM *vmem)
 static void virtio_mem_unplug_all_request(VirtIOMEM *vmem,
                                           VirtQueueElement *elem)
 {
+    trace_virtio_mem_unplug_all_request();
     if (virtio_mem_unplug_all(vmem)) {
         virtio_mem_send_response_simple(vmem, elem, VIRTIO_MEM_RESP_BUSY);
     } else {

@@ -272,6 +278,7 @@ static void virtio_mem_state_request(VirtIOMEM *vmem, VirtQueueElement *elem,
         .type = cpu_to_le16(VIRTIO_MEM_RESP_ACK),
     };
 
+    trace_virtio_mem_state_request(gpa, nb_blocks);
     if (!virtio_mem_valid_range(vmem, gpa, size)) {
         virtio_mem_send_response_simple(vmem, elem, VIRTIO_MEM_RESP_ERROR);
         return;

@@ -284,6 +291,7 @@ static void virtio_mem_state_request(VirtIOMEM *vmem, VirtQueueElement *elem,
     } else {
         resp.u.state.state = cpu_to_le16(VIRTIO_MEM_STATE_MIXED);
     }
+    trace_virtio_mem_state_response(le16_to_cpu(resp.u.state.state));
     virtio_mem_send_response(vmem, elem, &resp);
 }
 

index 4d0a2e78c0..e278b213e2 100644
@@ -62,8 +62,14 @@ static bool virtio_mem_is_busy(void)
     /*
      * Postcopy cannot handle concurrent discards and we don't want to migrate
      * pages on-demand with stale content when plugging new blocks.
+     *
+     * For precopy, we don't want unplugged blocks in our migration stream, and
+     * when plugging new blocks, the page content might differ between source
+     * and destination (observable by the guest when not initializing pages
+     * after plugging them) until we're running on the destination (as we didn't
+     * migrate these blocks when they were unplugged).
      */
-    return migration_in_incoming_postcopy();
+    return migration_in_incoming_postcopy() || !migration_is_idle();
 }
 
 static bool virtio_mem_test_bitmap(VirtIOMEM *vmem, uint64_t start_gpa,

@@ -475,6 +481,7 @@ static void virtio_mem_device_realize(DeviceState *dev, Error **errp)
     host_memory_backend_set_mapped(vmem->memdev, true);
     vmstate_register_ram(&vmem->memdev->mr, DEVICE(vmem));
     qemu_register_reset(virtio_mem_system_reset, vmem);
+    precopy_add_notifier(&vmem->precopy_notifier);
 }
 
 static void virtio_mem_device_unrealize(DeviceState *dev)

@@ -482,6 +489,7 @@ static void virtio_mem_device_unrealize(DeviceState *dev)
     VirtIODevice *vdev = VIRTIO_DEVICE(dev);
     VirtIOMEM *vmem = VIRTIO_MEM(dev);
 
+    precopy_remove_notifier(&vmem->precopy_notifier);
     qemu_unregister_reset(virtio_mem_system_reset, vmem);
     vmstate_unregister_ram(&vmem->memdev->mr, DEVICE(vmem));
     host_memory_backend_set_mapped(vmem->memdev, false);

@@ -760,12 +768,56 @@ static void virtio_mem_set_block_size(Object *obj, Visitor *v, const char *name,
     vmem->block_size = value;
 }
 
+static void virtio_mem_precopy_exclude_unplugged(VirtIOMEM *vmem)
+{
+    void * const host = qemu_ram_get_host_addr(vmem->memdev->mr.ram_block);
+    unsigned long first_zero_bit, last_zero_bit;
+    uint64_t offset, length;
+
+    /*
+     * Find consecutive unplugged blocks and exclude them from migration.
+     *
+     * Note: Blocks cannot get (un)plugged during precopy, no locking needed.
+     */
+    first_zero_bit = find_first_zero_bit(vmem->bitmap, vmem->bitmap_size);
+    while (first_zero_bit < vmem->bitmap_size) {
+        offset = first_zero_bit * vmem->block_size;
+        last_zero_bit = find_next_bit(vmem->bitmap, vmem->bitmap_size,
+                                      first_zero_bit + 1) - 1;
+        length = (last_zero_bit - first_zero_bit + 1) * vmem->block_size;
+
+        qemu_guest_free_page_hint(host + offset, length);
+        first_zero_bit = find_next_zero_bit(vmem->bitmap, vmem->bitmap_size,
+                                            last_zero_bit + 2);
+    }
+}
+
+static int virtio_mem_precopy_notify(NotifierWithReturn *n, void *data)
+{
+    VirtIOMEM *vmem = container_of(n, VirtIOMEM, precopy_notifier);
+    PrecopyNotifyData *pnd = data;
+
+    switch (pnd->reason) {
+    case PRECOPY_NOTIFY_SETUP:
+        precopy_enable_free_page_optimization();
+        break;
+    case PRECOPY_NOTIFY_AFTER_BITMAP_SYNC:
+        virtio_mem_precopy_exclude_unplugged(vmem);
+        break;
+    default:
+        break;
+    }
+
+    return 0;
+}
+
 static void virtio_mem_instance_init(Object *obj)
 {
     VirtIOMEM *vmem = VIRTIO_MEM(obj);
 
     vmem->block_size = VIRTIO_MEM_MIN_BLOCK_SIZE;
     notifier_list_init(&vmem->size_change_notifiers);
+    vmem->precopy_notifier.notify = virtio_mem_precopy_notify;
 
     object_property_add(obj, VIRTIO_MEM_SIZE_PROP, "size", virtio_mem_get_size,
                         NULL, NULL, NULL);

index 408a6ede50..ddb3822375 100644
@@ -67,6 +67,9 @@ typedef struct VirtIOMEM {
 
     /* notifiers to notify when "size" changes */
     NotifierList size_change_notifiers;
+
+    /* don't migrate unplugged memory */
+    NotifierWithReturn precopy_notifier;
 } VirtIOMEM;
 
 typedef struct VirtIOMEMClass {