virtio,acpi: features, fixes, cleanups.

index d54a8701d8..ab36fbfa0c 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"

@@ -2229,7 +2228,8 @@ 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 dc3490c9fa..21ea5ba1d2 100644
@@ -1211,7 +1211,7 @@ static void test_migrate_auto_converge(void)
      * without throttling.
      */
     migrate_set_parameter_int(from, "downtime-limit", 1);
-    migrate_set_parameter_int(from, "max-bandwidth", 1000000); /* ~1Mb/s */
+    migrate_set_parameter_int(from, "max-bandwidth", 100000000); /* ~100Mb/s */
 
     /* To check remaining size after precopy */
     migrate_set_capability(from, "pause-before-switchover", true);

index 10507b2a43..8a84718490 100644
@@ -628,8 +628,13 @@ static void virtio_balloon_free_page_done(VirtIOBalloon *s)
 {
     VirtIODevice *vdev = VIRTIO_DEVICE(s);
 
-    s->free_page_report_status = FREE_PAGE_REPORT_S_DONE;
-    virtio_notify_config(vdev);
+    if (s->free_page_report_status != FREE_PAGE_REPORT_S_DONE) {
+        /* See virtio_balloon_free_page_stop() */
+        qemu_mutex_lock(&s->free_page_lock);
+        s->free_page_report_status = FREE_PAGE_REPORT_S_DONE;
+        qemu_mutex_unlock(&s->free_page_lock);
+        virtio_notify_config(vdev);
+    }
 }
 
 static int

@@ -653,17 +658,26 @@ virtio_balloon_free_page_report_notify(NotifierWithReturn *n, void *data)
     case PRECOPY_NOTIFY_SETUP:
         precopy_enable_free_page_optimization();
         break;
-    case PRECOPY_NOTIFY_COMPLETE:
-    case PRECOPY_NOTIFY_CLEANUP:
     case PRECOPY_NOTIFY_BEFORE_BITMAP_SYNC:
         virtio_balloon_free_page_stop(dev);
         break;
     case PRECOPY_NOTIFY_AFTER_BITMAP_SYNC:
         if (vdev->vm_running) {
             virtio_balloon_free_page_start(dev);
-        } else {
-            virtio_balloon_free_page_done(dev);
+            break;
         }
+        /*
+         * Set S_DONE before migrating the vmstate, so the guest will reuse
+         * all hinted pages once running on the destination. Fall through.
+         */
+    case PRECOPY_NOTIFY_CLEANUP:
+        /*
+         * Especially, if something goes wrong during precopy or if migration
+         * is canceled, we have to properly communicate S_DONE to the VM.
+         */
+        virtio_balloon_free_page_done(dev);
+        break;
+    case PRECOPY_NOTIFY_COMPLETE:
         break;
     default:
         virtio_error(vdev, "%s: %d reason unknown", __func__, pnd->reason);

index 4af9679d03..58b1425c17 100644
@@ -1643,13 +1643,13 @@ static void pc_virtio_pmem_pci_pre_plug(HotplugHandler *hotplug_dev,
     HotplugHandler *hotplug_dev2 = qdev_get_bus_hotplug_handler(dev);
     Error *local_err = NULL;
 
-    if (!hotplug_dev2) {
+    if (!hotplug_dev2 && dev->hotplugged) {
         /*
          * Without a bus hotplug handler, we cannot control the plug/unplug
-         * order. This should never be the case on x86, however better add
-         * a safety net.
+         * order. We should never reach this point when hotplugging on x86,
+         * however, better add a safety net.
          */
-        error_setg(errp, "virtio-pmem-pci not supported on this bus.");
+        error_setg(errp, "virtio-pmem-pci hotplug not supported on this bus.");
         return;
     }
     /*

@@ -1658,7 +1658,7 @@ static void pc_virtio_pmem_pci_pre_plug(HotplugHandler *hotplug_dev,
      */
     memory_device_pre_plug(MEMORY_DEVICE(dev), MACHINE(hotplug_dev), NULL,
                            &local_err);
-    if (!local_err) {
+    if (!local_err && hotplug_dev2) {
         hotplug_handler_pre_plug(hotplug_dev2, dev, &local_err);
     }
     error_propagate(errp, local_err);

@@ -1676,9 +1676,11 @@ static void pc_virtio_pmem_pci_plug(HotplugHandler *hotplug_dev,
      * device bits.
      */
     memory_device_plug(MEMORY_DEVICE(dev), MACHINE(hotplug_dev));
-    hotplug_handler_plug(hotplug_dev2, dev, &local_err);
-    if (local_err) {
-        memory_device_unplug(MEMORY_DEVICE(dev), MACHINE(hotplug_dev));
+    if (hotplug_dev2) {
+        hotplug_handler_plug(hotplug_dev2, dev, &local_err);
+        if (local_err) {
+            memory_device_unplug(MEMORY_DEVICE(dev), MACHINE(hotplug_dev));
+        }
     }
     error_propagate(errp, local_err);
 }

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 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 95564c17ed..b9330a8e6f 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.
+     * vfio-ap devices operate in a way compatible with 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 the balloon inhibitor.
+     * 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 06e69d7066..ff7f369779 100644
@@ -574,12 +574,13 @@ 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 6838bcc4b3..d020ea9f82 100644
@@ -2789,7 +2789,7 @@ 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.

@@ -2802,7 +2802,7 @@ 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);

@@ -3156,7 +3156,7 @@ 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 7207025bd4..38ec38b9a8 100644
@@ -2472,6 +2472,47 @@ static inline MemOp devend_memop(enum device_endian end)
 }
 #endif
 
+/*
+ * Inhibit technologies that require discarding of pages in RAM blocks, e.g.,
+ * to manage the actual amount of memory consumed by the VM (then, the memory
+ * provided by RAM blocks might be bigger than the desired memory consumption).
+ * This *must* be set if:
+ * - Discarding parts of a RAM blocks does not result in the change being
+ *   reflected in the VM and the pages getting freed.
+ * - All memory in RAM blocks is pinned or duplicated, invaldiating any previous
+ *   discards blindly.
+ * - Discarding parts of a RAM blocks will result in integrity issues (e.g.,
+ *   encrypted VMs).
+ * Technologies that only temporarily pin the current working set of a
+ * driver are fine, because we don't expect such pages to be discarded
+ * (esp. based on guest action like balloon inflation).
+ *
+ * This is *not* to be used to protect from concurrent discards (esp.,
+ * postcopy).
+ *
+ * Returns 0 if successful. Returns -EBUSY if a technology that relies on
+ * discards to work reliably is active.
+ */
+int ram_block_discard_disable(bool state);
+
+/*
+ * Inhibit technologies that disable discarding of pages in RAM blocks.
+ *
+ * Returns 0 if successful. Returns -EBUSY if discards are already set to
+ * broken.
+ */
+int ram_block_discard_require(bool state);
+
+/*
+ * Test if discarding of memory in ram blocks is disabled.
+ */
+bool ram_block_discard_is_disabled(void);
+
+/*
+ * Test if discarding of memory in ram blocks is required to work reliably.
+ */
+bool ram_block_discard_is_required(void);
+
 #endif
 
 #endif

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

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 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 8a84718490..ae31f0817a 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)

@@ -336,7 +342,7 @@ static void virtio_balloon_handle_report(VirtIODevice *vdev, VirtQueue *vq)
          * accessible by another device or process, or if the guest is
          * expecting it to retain a non-zero value.
          */
-        if (qemu_balloon_is_inhibited() || dev->poison_val) {
+        if (virtio_balloon_inhibited() || dev->poison_val) {
             goto skip_element;
         }
 

@@ -421,7 +427,7 @@ 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 481a590f72..d365d82209 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 b111406d56..023fd25f2b 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 2725886d06..e9aec69afd 100644
@@ -824,6 +824,7 @@ 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;

@@ -844,6 +845,11 @@ 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();
             }

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 a4e9c33416..c1bf7d5356 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

129 lines not on this page · raw message

index d273174ad3..f100a53231 100644
@@ -680,6 +680,12 @@ 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 = lookup_sev_guest_info(id);
     if (!sev) {
         error_report("%s: '%s' is not a valid '%s' object",

@@ -751,6 +757,7 @@ sev_guest_init(const char *id)
     return sev;
 err:
     sev_guest = NULL;
+    ram_block_discard_disable(false);
     return NULL;
 }
 

index 2b0b58a336..2ec13e4cc3 100644
@@ -1821,6 +1821,7 @@ 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;
 

@@ -1855,6 +1856,21 @@ 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 58b1425c17..576f2502f9 100644
@@ -88,6 +88,7 @@
 #include "hw/net/ne2000-isa.h"
 #include "standard-headers/asm-x86/bootparam.h"
 #include "hw/virtio/virtio-pmem-pci.h"
+#include "hw/virtio/virtio-mem-pci.h"
 #include "hw/mem/memory-device.h"
 #include "sysemu/replay.h"
 #include "qapi/qmp/qerror.h"

@@ -1637,8 +1638,8 @@ static void pc_cpu_pre_plug(HotplugHandler *hotplug_dev,
     numa_cpu_pre_plug(cpu_slot, dev, errp);
 }
 
-static void pc_virtio_pmem_pci_pre_plug(HotplugHandler *hotplug_dev,
-                                        DeviceState *dev, Error **errp)
+static void pc_virtio_md_pci_pre_plug(HotplugHandler *hotplug_dev,
+                                      DeviceState *dev, Error **errp)
 {
     HotplugHandler *hotplug_dev2 = qdev_get_bus_hotplug_handler(dev);
     Error *local_err = NULL;

@@ -1649,7 +1650,8 @@ static void pc_virtio_pmem_pci_pre_plug(HotplugHandler *hotplug_dev,
          * order. We should never reach this point when hotplugging on x86,
          * however, better add a safety net.
          */
-        error_setg(errp, "virtio-pmem-pci hotplug not supported on this bus.");
+        error_setg(errp, "hotplug of virtio based memory devices not supported"
+                   " on this bus.");
         return;
     }
     /*

@@ -1664,8 +1666,8 @@ static void pc_virtio_pmem_pci_pre_plug(HotplugHandler *hotplug_dev,
     error_propagate(errp, local_err);
 }
 
-static void pc_virtio_pmem_pci_plug(HotplugHandler *hotplug_dev,
-                                    DeviceState *dev, Error **errp)
+static void pc_virtio_md_pci_plug(HotplugHandler *hotplug_dev,
+                                  DeviceState *dev, Error **errp)
 {
     HotplugHandler *hotplug_dev2 = qdev_get_bus_hotplug_handler(dev);
     Error *local_err = NULL;

@@ -1685,17 +1687,17 @@ static void pc_virtio_pmem_pci_plug(HotplugHandler *hotplug_dev,
     error_propagate(errp, local_err);
 }
 
-static void pc_virtio_pmem_pci_unplug_request(HotplugHandler *hotplug_dev,
-                                              DeviceState *dev, Error **errp)
+static void pc_virtio_md_pci_unplug_request(HotplugHandler *hotplug_dev,
+                                            DeviceState *dev, Error **errp)
 {
-    /* We don't support virtio pmem hot unplug */
-    error_setg(errp, "virtio pmem device unplug not supported.");
+    /* We don't support hot unplug of virtio based memory devices */
+    error_setg(errp, "virtio based memory devices cannot be unplugged.");
 }
 
-static void pc_virtio_pmem_pci_unplug(HotplugHandler *hotplug_dev,
-                                      DeviceState *dev, Error **errp)
+static void pc_virtio_md_pci_unplug(HotplugHandler *hotplug_dev,
+                                    DeviceState *dev, Error **errp)
 {
-    /* We don't support virtio pmem hot unplug */
+    /* We don't support hot unplug of virtio based memory devices */
 }
 
 static void pc_machine_device_pre_plug_cb(HotplugHandler *hotplug_dev,

@@ -1705,8 +1707,9 @@ static void pc_machine_device_pre_plug_cb(HotplugHandler *hotplug_dev,
         pc_memory_pre_plug(hotplug_dev, dev, errp);
     } else if (object_dynamic_cast(OBJECT(dev), TYPE_CPU)) {
         pc_cpu_pre_plug(hotplug_dev, dev, errp);
-    } else if (object_dynamic_cast(OBJECT(dev), TYPE_VIRTIO_PMEM_PCI)) {
-        pc_virtio_pmem_pci_pre_plug(hotplug_dev, dev, errp);
+    } else if (object_dynamic_cast(OBJECT(dev), TYPE_VIRTIO_PMEM_PCI) ||
+               object_dynamic_cast(OBJECT(dev), TYPE_VIRTIO_MEM_PCI)) {
+        pc_virtio_md_pci_pre_plug(hotplug_dev, dev, errp);
     }
 }
 

@@ -1717,8 +1720,9 @@ static void pc_machine_device_plug_cb(HotplugHandler *hotplug_dev,
         pc_memory_plug(hotplug_dev, dev, errp);
     } else if (object_dynamic_cast(OBJECT(dev), TYPE_CPU)) {
         pc_cpu_plug(hotplug_dev, dev, errp);
-    } else if (object_dynamic_cast(OBJECT(dev), TYPE_VIRTIO_PMEM_PCI)) {
-        pc_virtio_pmem_pci_plug(hotplug_dev, dev, errp);
+    } else if (object_dynamic_cast(OBJECT(dev), TYPE_VIRTIO_PMEM_PCI) ||
+               object_dynamic_cast(OBJECT(dev), TYPE_VIRTIO_MEM_PCI)) {
+        pc_virtio_md_pci_plug(hotplug_dev, dev, errp);
     }
 }
 

@@ -1729,8 +1733,9 @@ static void pc_machine_device_unplug_request_cb(HotplugHandler *hotplug_dev,
         pc_memory_unplug_request(hotplug_dev, dev, errp);
     } else if (object_dynamic_cast(OBJECT(dev), TYPE_CPU)) {
         pc_cpu_unplug_request_cb(hotplug_dev, dev, errp);
-    } else if (object_dynamic_cast(OBJECT(dev), TYPE_VIRTIO_PMEM_PCI)) {
-        pc_virtio_pmem_pci_unplug_request(hotplug_dev, dev, errp);
+    } else if (object_dynamic_cast(OBJECT(dev), TYPE_VIRTIO_PMEM_PCI) ||
+               object_dynamic_cast(OBJECT(dev), TYPE_VIRTIO_MEM_PCI)) {
+        pc_virtio_md_pci_unplug_request(hotplug_dev, dev, errp);
     } else {
         error_setg(errp, "acpi: device unplug request for not supported device"
                    " type: %s", object_get_typename(OBJECT(dev)));

@@ -1744,8 +1749,9 @@ static void pc_machine_device_unplug_cb(HotplugHandler *hotplug_dev,
         pc_memory_unplug(hotplug_dev, dev, errp);
     } else if (object_dynamic_cast(OBJECT(dev), TYPE_CPU)) {
         pc_cpu_unplug_cb(hotplug_dev, dev, errp);
-    } else if (object_dynamic_cast(OBJECT(dev), TYPE_VIRTIO_PMEM_PCI)) {
-        pc_virtio_pmem_pci_unplug(hotplug_dev, dev, errp);
+    } else if (object_dynamic_cast(OBJECT(dev), TYPE_VIRTIO_PMEM_PCI) ||
+               object_dynamic_cast(OBJECT(dev), TYPE_VIRTIO_MEM_PCI)) {
+        pc_virtio_md_pci_unplug(hotplug_dev, dev, errp);
     } else {
         error_setg(errp, "acpi: device unplug for not supported device"
                    " type: %s", object_get_typename(OBJECT(dev)));

@@ -1757,7 +1763,8 @@ static HotplugHandler *pc_get_hotplug_handler(MachineState *machine,
 {
     if (object_dynamic_cast(OBJECT(dev), TYPE_PC_DIMM) ||
         object_dynamic_cast(OBJECT(dev), TYPE_CPU) ||
-        object_dynamic_cast(OBJECT(dev), TYPE_VIRTIO_PMEM_PCI)) {
+        object_dynamic_cast(OBJECT(dev), TYPE_VIRTIO_PMEM_PCI) ||
+        object_dynamic_cast(OBJECT(dev), TYPE_VIRTIO_MEM_PCI)) {
         return HOTPLUG_HANDLER(machine);
     }
 

78 lines not on this page · raw message

724 lines not on this page · raw message

index 8992f1f12b..dfb8523c8b 100644
@@ -1,19 +1 @@
 /* List of comma-separated changed AML files to ignore */
-"tests/data/acpi/pc/DSDT",
-"tests/data/acpi/pc/DSDT.acpihmat",
-"tests/data/acpi/pc/DSDT.bridge",
-"tests/data/acpi/pc/DSDT.cphp",
-"tests/data/acpi/pc/DSDT.dimmpxm",
-"tests/data/acpi/pc/DSDT.ipmikcs",
-"tests/data/acpi/pc/DSDT.memhp",
-"tests/data/acpi/pc/DSDT.numamem",
-"tests/data/acpi/q35/DSDT",
-"tests/data/acpi/q35/DSDT.acpihmat",
-"tests/data/acpi/q35/DSDT.bridge",
-"tests/data/acpi/q35/DSDT.cphp",
-"tests/data/acpi/q35/DSDT.dimmpxm",
-"tests/data/acpi/q35/DSDT.ipmibt",
-"tests/data/acpi/q35/DSDT.memhp",
-"tests/data/acpi/q35/DSDT.mmio64",
-"tests/data/acpi/q35/DSDT.numamem",
-"tests/data/acpi/q35/DSDT.tis",

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 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 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 b74c77cd42..0778224964 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 {

85 lines not on this page · raw message

index 2df33f9125..6ed5409669 100644
@@ -519,12 +519,82 @@ 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;
+    uint64_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("Property '%s' size changed from 0x%" PRIx64 " to 0x%"
+                     PRIx64, VIRTIO_MEM_MEMDEV_PROP, tmp->region_size,
+                     new_region_size);
+        return -EINVAL;
+    }
+    if (tmp->block_size != vmem->block_size) {
+        error_report("Property '%s' changed from 0x%" PRIx64 " to 0x%" PRIx64,
+                     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_UINT64(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 18815d9be2..426ce5f625 100644
@@ -207,6 +207,7 @@ struct MachineClass {
     const char **valid_cpu_types;
     strList *allowed_dynamic_sysbus_devices;
     bool auto_enable_numa_with_memhp;
+    bool auto_enable_numa_with_memdev;
     void (*numa_auto_assign_ram)(MachineClass *mc, NodeInfo *nodes,
                                  int nb_nodes, ram_addr_t size);
     bool ignore_boot_device_suffixes;

index cd0834ce7f..f97be80a86 100644
@@ -2373,6 +2373,7 @@ static void virt_machine_class_init(ObjectClass *oc, void *data)
     hc->unplug = virt_machine_device_unplug_cb;
     mc->nvdimm_supported = true;
     mc->auto_enable_numa_with_memhp = true;
+    mc->auto_enable_numa_with_memdev = true;
     mc->default_ram_id = "mach-virt.ram";
 
     object_class_property_add(oc, "acpi", "OnOffAuto",

@@ -2485,6 +2486,7 @@ static void virt_machine_5_0_options(MachineClass *mc)
     virt_machine_5_1_options(mc);
     compat_props_add(mc->compat_props, hw_compat_5_0, hw_compat_5_0_len);
     mc->numa_mem_supported = true;
+    mc->auto_enable_numa_with_memdev = false;
 }
 DEFINE_VIRT_MACHINE(5, 0)
 

index e9aec69afd..6a20ce7cf1 100644
@@ -688,8 +688,9 @@ void numa_complete_configuration(MachineState *ms)
     NodeInfo *numa_info = ms->numa_state->nodes;
 
     /*
-     * If memory hotplug is enabled (slots > 0) but without '-numa'
-     * options explicitly on CLI, guestes will break.
+     * If memory hotplug is enabled (slot > 0) or memory devices are enabled
+     * (ms->maxram_size > ram_size) but without '-numa' options explicitly on
+     * CLI, guests will break.
      *
      *   Windows: won't enable memory hotplug without SRAT table at all
      *

@@ -704,9 +705,9 @@ void numa_complete_configuration(MachineState *ms)
      * assume there is just one node with whole RAM.
      */
     if (ms->numa_state->num_nodes == 0 &&
-        ((ms->ram_slots > 0 &&
-        mc->auto_enable_numa_with_memhp) ||
-        mc->auto_enable_numa)) {
+        ((ms->ram_slots && mc->auto_enable_numa_with_memhp) ||
+         (ms->maxram_size > ms->ram_size && mc->auto_enable_numa_with_memdev) ||
+         mc->auto_enable_numa)) {
             NumaNodeOptions node = { };
             parse_numa_node(ms, &node, &error_abort);
             numa_info[0].node_mem = ram_size;

index 5e931975a0..81d0888930 100644
@@ -464,6 +464,7 @@ static void microvm_class_init(ObjectClass *oc, void *data)
     mc->max_cpus = 288;
     mc->has_hotpluggable_cpus = false;
     mc->auto_enable_numa_with_memhp = false;
+    mc->auto_enable_numa_with_memdev = false;
     mc->default_cpu_type = TARGET_DEFAULT_CPU_TYPE;
     mc->nvdimm_supported = false;
     mc->default_ram_id = "microvm.ram";

index 576f2502f9..61acc9e530 100644
@@ -1975,6 +1975,7 @@ static void pc_machine_class_init(ObjectClass *oc, void *data)
     mc->get_default_cpu_node_id = x86_get_default_cpu_node_id;
     mc->possible_cpu_arch_ids = x86_possible_cpu_arch_ids;
     mc->auto_enable_numa_with_memhp = true;
+    mc->auto_enable_numa_with_memdev = true;
     mc->has_hotpluggable_cpus = true;
     mc->default_boot_order = "cad";
     mc->hot_add_cpu = pc_hot_add_cpu;

index 1d832b2878..fae487f57d 100644
@@ -444,6 +444,7 @@ static void pc_i440fx_5_0_machine_options(MachineClass *m)
     m->numa_mem_supported = true;
     compat_props_add(m->compat_props, hw_compat_5_0, hw_compat_5_0_len);
     compat_props_add(m->compat_props, pc_compat_5_0, pc_compat_5_0_len);
+    m->auto_enable_numa_with_memdev = false;
 }
 
 DEFINE_I440FX_MACHINE(v5_0, "pc-i440fx-5.0", NULL,

index 047ea8db28..acd6d405f0 100644
@@ -372,6 +372,7 @@ static void pc_q35_5_0_machine_options(MachineClass *m)
     m->numa_mem_supported = true;
     compat_props_add(m->compat_props, hw_compat_5_0, hw_compat_5_0_len);
     compat_props_add(m->compat_props, pc_compat_5_0, pc_compat_5_0_len);
+    m->auto_enable_numa_with_memhp = false;
 }
 
 DEFINE_Q35_MACHINE(v5_0, "pc-q35-5.0", NULL,

index 38c9399cd4..0f6f215925 100644
@@ -83,6 +83,10 @@ typedef struct VirtioBusClass {
      */
     int (*ioeventfd_assign)(DeviceState *d, EventNotifier *notifier,
                             int n, bool assign);
+    /*
+     * Whether queue number n is enabled.
+     */
+    bool (*queue_enabled)(DeviceState *d, int n);
     /*
      * Does the transport have variable vring alignment?
      * (ie can it ever call virtio_queue_set_align()?)

index cc9c9dc162..5bd2a2f621 100644
@@ -3286,6 +3286,12 @@ hwaddr virtio_queue_get_desc_addr(VirtIODevice *vdev, int n)
 
 bool virtio_queue_enabled(VirtIODevice *vdev, int n)
 {
+    BusState *qbus = qdev_get_parent_bus(DEVICE(vdev));
+    VirtioBusClass *k = VIRTIO_BUS_GET_CLASS(qbus);
+
+    if (k->queue_enabled) {
+        return k->queue_enabled(qbus->parent, n);
+    }
     return virtio_queue_get_desc_addr(vdev, n) != 0;
 }
 

index 6ed5409669..fdd4dbb42c 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 6b82803fa7..4096d64aaf 100644
@@ -306,7 +306,9 @@ int vhost_net_start(VirtIODevice *dev, NetClientState *ncs,
     BusState *qbus = BUS(qdev_get_parent_bus(DEVICE(dev)));
     VirtioBusState *vbus = VIRTIO_BUS(qbus);
     VirtioBusClass *k = VIRTIO_BUS_GET_CLASS(vbus);
+    struct vhost_net *net;
     int r, e, i;
+    NetClientState *peer;
 
     if (!k->set_guest_notifiers) {
         error_report("binding does not support guest notifiers");

@@ -314,9 +316,9 @@ int vhost_net_start(VirtIODevice *dev, NetClientState *ncs,
     }
 
     for (i = 0; i < total_queues; i++) {
-        struct vhost_net *net;
 
-        net = get_vhost_net(ncs[i].peer);
+        peer = qemu_get_peer(ncs, i);
+        net = get_vhost_net(peer);
         vhost_net_set_vq_index(net, i * 2);
 
         /* Suppress the masking guest notifiers on vhost user

@@ -335,15 +337,16 @@ int vhost_net_start(VirtIODevice *dev, NetClientState *ncs,
     }
 
     for (i = 0; i < total_queues; i++) {
-        r = vhost_net_start_one(get_vhost_net(ncs[i].peer), dev);
+        peer = qemu_get_peer(ncs, i);
+        r = vhost_net_start_one(get_vhost_net(peer), dev);
 
         if (r < 0) {
             goto err_start;
         }
 
-        if (ncs[i].peer->vring_enable) {
+        if (peer->vring_enable) {
             /* restore vring enable state */
-            r = vhost_set_vring_enable(ncs[i].peer, ncs[i].peer->vring_enable);
+            r = vhost_set_vring_enable(peer, peer->vring_enable);
 
             if (r < 0) {
                 goto err_start;

@@ -355,7 +358,8 @@ int vhost_net_start(VirtIODevice *dev, NetClientState *ncs,
 
 err_start:
     while (--i >= 0) {
-        vhost_net_stop_one(get_vhost_net(ncs[i].peer), dev);
+        peer = qemu_get_peer(ncs , i);
+        vhost_net_stop_one(get_vhost_net(peer), dev);
     }
     e = k->set_guest_notifiers(qbus->parent, total_queues * 2, false);
     if (e < 0) {

index 39085d9444..e7ef42d62b 100644
@@ -176,6 +176,7 @@ void hmp_info_network(Monitor *mon, const QDict *qdict);
 void net_socket_rs_init(SocketReadState *rs,
                         SocketReadStateFinalize *finalize,
                         bool vnet_hdr);
+NetClientState *qemu_get_peer(NetClientState *nc, int queue_index);
 
 /* NIC info */
 

index d1130296e1..9099a327dd 100644
@@ -325,6 +325,13 @@ void *qemu_get_nic_opaque(NetClientState *nc)
     return nic->opaque;
 }
 
+NetClientState *qemu_get_peer(NetClientState *nc, int queue_index)
+{
+    assert(nc != NULL);
+    NetClientState *ncs = nc + queue_index;
+    return ncs->peer;
+}
+
 static void qemu_cleanup_net_client(NetClientState *nc)
 {
     QTAILQ_REMOVE(&net_clients, nc, next);

index 5fd25fe520..10304b583e 100644
@@ -1686,8 +1686,9 @@ int vhost_dev_start(struct vhost_dev *hdev, VirtIODevice *vdev)
         }
     }
 
-    if (vhost_dev_has_iommu(hdev)) {
-        hdev->vhost_ops->vhost_set_iotlb_callback(hdev, true);
+    if (vhost_dev_has_iommu(hdev) &&
+        hdev->vhost_ops->vhost_set_iotlb_callback) {
+            hdev->vhost_ops->vhost_set_iotlb_callback(hdev, true);
 
         /* Update used ring information for IOTLB to work correctly,
          * vhost-kernel code requires for this.*/

@@ -1730,7 +1731,9 @@ void vhost_dev_stop(struct vhost_dev *hdev, VirtIODevice *vdev)
     }
 
     if (vhost_dev_has_iommu(hdev)) {
-        hdev->vhost_ops->vhost_set_iotlb_callback(hdev, false);
+        if (hdev->vhost_ops->vhost_set_iotlb_callback) {
+            hdev->vhost_ops->vhost_set_iotlb_callback(hdev, false);
+        }
         memory_listener_unregister(&hdev->iommu_listener);
     }
     vhost_log_put(hdev, true);

index 10304b583e..32809e54b5 100644
@@ -1685,7 +1685,12 @@ int vhost_dev_start(struct vhost_dev *hdev, VirtIODevice *vdev)
             goto fail_log;
         }
     }
-
+    if (hdev->vhost_ops->vhost_dev_start) {
+        r = hdev->vhost_ops->vhost_dev_start(hdev, true);
+        if (r) {
+            goto fail_log;
+        }
+    }
     if (vhost_dev_has_iommu(hdev) &&
         hdev->vhost_ops->vhost_set_iotlb_callback) {
             hdev->vhost_ops->vhost_set_iotlb_callback(hdev, true);

@@ -1723,6 +1728,9 @@ void vhost_dev_stop(struct vhost_dev *hdev, VirtIODevice *vdev)
     /* should only be called after backend is connected */
     assert(hdev->vhost_ops);
 
+    if (hdev->vhost_ops->vhost_dev_start) {
+        hdev->vhost_ops->vhost_dev_start(hdev, false);
+    }
     for (i = 0; i < hdev->nvqs; ++i) {
         vhost_virtqueue_stop(hdev,
                              vdev,

index 7bc8c1c056..8554cf2a03 100644
@@ -1107,6 +1107,18 @@ static AddressSpace *virtio_pci_get_dma_as(DeviceState *d)
     return pci_get_address_space(dev);
 }
 
+static bool virtio_pci_queue_enabled(DeviceState *d, int n)
+{
+    VirtIOPCIProxy *proxy = VIRTIO_PCI(d);
+    VirtIODevice *vdev = virtio_bus_get_device(&proxy->bus);
+
+    if (virtio_vdev_has_feature(vdev, VIRTIO_F_VERSION_1)) {
+        return proxy->vqs[vdev->queue_sel].enabled;
+    }
+
+    return virtio_queue_enabled(vdev, n);
+}
+
 static int virtio_pci_add_mem_cap(VirtIOPCIProxy *proxy,
                                    struct virtio_pci_cap *cap)
 {

@@ -2064,6 +2076,7 @@ static void virtio_pci_bus_class_init(ObjectClass *klass, void *data)
     k->ioeventfd_enabled = virtio_pci_ioeventfd_enabled;
     k->ioeventfd_assign = virtio_pci_ioeventfd_assign;
     k->get_dma_as = virtio_pci_get_dma_as;
+    k->queue_enabled = virtio_pci_queue_enabled;
 }
 
 static const TypeInfo virtio_pci_bus_info = {

index 6f6670783f..b80f344cd6 100644
@@ -112,6 +112,7 @@ typedef int (*vhost_get_inflight_fd_op)(struct vhost_dev *dev,
 typedef int (*vhost_set_inflight_fd_op)(struct vhost_dev *dev,
                                         struct vhost_inflight *inflight);
 
+typedef int (*vhost_dev_start_op)(struct vhost_dev *dev, bool started);
 typedef struct VhostOps {
     VhostBackendType backend_type;
     vhost_backend_init vhost_backend_init;

@@ -152,6 +153,7 @@ typedef struct VhostOps {
     vhost_backend_mem_section_filter_op vhost_backend_mem_section_filter;
     vhost_get_inflight_fd_op vhost_get_inflight_fd;
     vhost_set_inflight_fd_op vhost_set_inflight_fd;
+    vhost_dev_start_op vhost_dev_start;
 } VhostOps;
 
 extern const VhostOps user_ops;

index fa84abac97..bfc24207e2 100644
@@ -118,6 +118,9 @@ typedef int (*vhost_dev_start_op)(struct vhost_dev *dev, bool started);
 typedef int (*vhost_vq_get_addr_op)(struct vhost_dev *dev,
                     struct vhost_vring_addr *addr,
                     struct vhost_virtqueue *vq);
+
+typedef int (*vhost_get_device_id_op)(struct vhost_dev *dev, uint32_t *dev_id);
+
 typedef struct VhostOps {
     VhostBackendType backend_type;
     vhost_backend_init vhost_backend_init;

@@ -160,6 +163,7 @@ typedef struct VhostOps {
     vhost_set_inflight_fd_op vhost_set_inflight_fd;
     vhost_dev_start_op vhost_dev_start;
     vhost_vq_get_addr_op  vhost_vq_get_addr;
+    vhost_get_device_id_op vhost_get_device_id;
 } VhostOps;
 
 extern const VhostOps user_ops;

index 32809e54b5..1e083a8976 100644
@@ -773,15 +773,25 @@ static int vhost_virtqueue_set_addr(struct vhost_dev *dev,
                                     struct vhost_virtqueue *vq,
                                     unsigned idx, bool enable_log)
 {
-    struct vhost_vring_addr addr = {
-        .index = idx,
-        .desc_user_addr = (uint64_t)(unsigned long)vq->desc,
-        .avail_user_addr = (uint64_t)(unsigned long)vq->avail,
-        .used_user_addr = (uint64_t)(unsigned long)vq->used,
-        .log_guest_addr = vq->used_phys,
-        .flags = enable_log ? (1 << VHOST_VRING_F_LOG) : 0,
-    };
-    int r = dev->vhost_ops->vhost_set_vring_addr(dev, &addr);
+    struct vhost_vring_addr addr;
+    int r;
+    memset(&addr, 0, sizeof(struct vhost_vring_addr));
+
+    if (dev->vhost_ops->vhost_vq_get_addr) {
+        r = dev->vhost_ops->vhost_vq_get_addr(dev, &addr, vq);
+        if (r < 0) {
+            VHOST_OPS_DEBUG("vhost_vq_get_addr failed");
+            return -errno;
+        }
+    } else {
+        addr.desc_user_addr = (uint64_t)(unsigned long)vq->desc;
+        addr.avail_user_addr = (uint64_t)(unsigned long)vq->avail;
+        addr.used_user_addr = (uint64_t)(unsigned long)vq->used;
+    }
+    addr.index = idx;
+    addr.log_guest_addr = vq->used_phys;
+    addr.flags = enable_log ? (1 << VHOST_VRING_F_LOG) : 0;
+    r = dev->vhost_ops->vhost_set_vring_addr(dev, &addr);
     if (r < 0) {
         VHOST_OPS_DEBUG("vhost_set_vring_addr failed");
         return -errno;

index b80f344cd6..fa84abac97 100644
@@ -34,6 +34,7 @@ struct vhost_vring_state;
 struct vhost_vring_addr;
 struct vhost_scsi_target;
 struct vhost_iotlb_msg;
+struct vhost_virtqueue;
 
 typedef int (*vhost_backend_init)(struct vhost_dev *dev, void *opaque);
 typedef int (*vhost_backend_cleanup)(struct vhost_dev *dev);

@@ -113,6 +114,10 @@ typedef int (*vhost_set_inflight_fd_op)(struct vhost_dev *dev,
                                         struct vhost_inflight *inflight);
 
 typedef int (*vhost_dev_start_op)(struct vhost_dev *dev, bool started);
+
+typedef int (*vhost_vq_get_addr_op)(struct vhost_dev *dev,
+                    struct vhost_vring_addr *addr,
+                    struct vhost_virtqueue *vq);
 typedef struct VhostOps {
     VhostBackendType backend_type;
     vhost_backend_init vhost_backend_init;

@@ -154,6 +159,7 @@ typedef struct VhostOps {
     vhost_get_inflight_fd_op vhost_get_inflight_fd;
     vhost_set_inflight_fd_op vhost_set_inflight_fd;
     vhost_dev_start_op vhost_dev_start;
+    vhost_vq_get_addr_op  vhost_vq_get_addr;
 } VhostOps;
 
 extern const VhostOps user_ops;