Merge remote-tracking branch 'remotes/mst/tags/for_upstream' into staging

pci, pc, virtio: features, fixes

reconnect for vhost blk
tests for UEFI
misc other stuff

Signed-off-by: Michael S. Tsirkin <mst@redhat.com>

# gpg: Signature made Tue 21 May 2019 14:41:32 BST
# gpg:                using RSA key 281F0DB8D28D5469
# gpg: Good signature from "Michael S. Tsirkin <mst@kernel.org>" [full]
# gpg:                 aka "Michael S. Tsirkin <mst@redhat.com>" [full]
# Primary key fingerprint: 0270 606B 6F3C DF3D 0B17  0970 C350 3912 AFBE 8E67
#      Subkey fingerprint: 5D09 FD08 71C8 F85B 94CA  8A0D 281F 0DB8 D28D 5469

* remotes/mst/tags/for_upstream: (34 commits)
  tests: acpi: print error unable to dump ACPI table during rebuild
  tests: acpi: refactor rebuild-expected-aml.sh to dump ACPI tables for a specified list of targets
  tests: acpi: allow to override default accelerator
  tests: acpi: ignore SMBIOS tests when UEFI firmware is used
  tests: acpi: add a way to start tests with UEFI firmware
  tests: acpi: add acpi_find_rsdp_address_uefi() helper
  tests: acpi: move boot_sector_init() into x86 tests branch
  tests: acpi: skip FACS table if board uses hw reduced ACPI profile
  tests: acpi: fetch X_DSDT if pointer to DSDT is 0
  tests: acpi: make pointer to RSDP 64bit
  tests: acpi: make RSDT test routine handle XSDT
  tests: acpi: make acpi_fetch_table() take size of fetched table pointer
  tests: acpi: rename acpi_parse_rsdp_table() into acpi_fetch_rsdp_table()
  pci: Simplify pci_bus_is_root()
  pcie: Remove redundant test in pcie_mmcfg_data_{read,write}()
  libvhost-user: fix bad vu_log_write
  hw/arm/virt-acpi-build: pass AcpiMcfgInfo to build_mcfg()
  i386, acpi: remove mcfg_ prefix in AcpiMcfgInfo members
  hw/arm/virt-acpi-build: remove unnecessary variable mcfg_start
  do not call vhost_net_cleanup() on running net from char user event
  ...

Signed-off-by: Peter Maydell <peter.maydell@linaro.org>

17 files changed, 326 insertions, 146 deletions

diff --git a/hw/acpi/pcihp.c b/hw/acpi/pcihp.c
index 88e4ae1..613406d 100644
--- a/hw/acpi/pcihp.c
+++ b/hw/acpi/pcihp.c
@@ -37,14 +37,7 @@
 #include "hw/pci/pci_bus.h"
 #include "qapi/error.h"
 #include "qom/qom-qobject.h"
-
-//#define DEBUG
-
-#ifdef DEBUG
-# define ACPI_PCIHP_DPRINTF(format, ...)     printf(format, ## __VA_ARGS__)
-#else
-# define ACPI_PCIHP_DPRINTF(format, ...)     do { } while (0)
-#endif
+#include "trace.h"
 
 #define ACPI_PCIHP_ADDR 0xae00
 #define ACPI_PCIHP_SIZE 0x0014
@@ -159,6 +152,8 @@ static void acpi_pcihp_eject_slot(AcpiPciHpState *s, unsigned bsel, unsigned slo
     int slot = ctz32(slots);
     PCIBus *bus = acpi_pcihp_find_hotplug_bus(s, bsel);
 
+    trace_acpi_pci_eject_slot(bsel, slot);
+
     if (!bus) {
         return;
     }
@@ -270,6 +265,8 @@ void acpi_pcihp_device_plug_cb(HotplugHandler *hotplug_dev, AcpiPciHpState *s,
 void acpi_pcihp_device_unplug_cb(HotplugHandler *hotplug_dev, AcpiPciHpState *s,
                                  DeviceState *dev, Error **errp)
 {
+    trace_acpi_pci_unplug(PCI_SLOT(PCI_DEVICE(dev)->devfn),
+                          acpi_pcihp_get_bsel(pci_get_bus(PCI_DEVICE(dev))));
     object_property_set_bool(OBJECT(dev), false, "realized", NULL);
 }
 
@@ -280,6 +277,9 @@ void acpi_pcihp_device_unplug_request_cb(HotplugHandler *hotplug_dev,
     PCIDevice *pdev = PCI_DEVICE(dev);
     int slot = PCI_SLOT(pdev->devfn);
     int bsel = acpi_pcihp_get_bsel(pci_get_bus(pdev));
+
+    trace_acpi_pci_unplug_request(bsel, slot);
+
     if (bsel < 0) {
         error_setg(errp, "Unsupported bus. Bus doesn't have property '"
                    ACPI_PCIHP_PROP_BSEL "' set");
@@ -306,23 +306,23 @@ static uint64_t pci_read(void *opaque, hwaddr addr, unsigned int size)
         if (!s->legacy_piix) {
             s->acpi_pcihp_pci_status[bsel].up = 0;
         }
-        ACPI_PCIHP_DPRINTF("pci_up_read %" PRIu32 "\n", val);
+        trace_acpi_pci_up_read(val);
         break;
     case PCI_DOWN_BASE:
         val = s->acpi_pcihp_pci_status[bsel].down;
-        ACPI_PCIHP_DPRINTF("pci_down_read %" PRIu32 "\n", val);
+        trace_acpi_pci_down_read(val);
         break;
     case PCI_EJ_BASE:
         /* No feature defined yet */
-        ACPI_PCIHP_DPRINTF("pci_features_read %" PRIu32 "\n", val);
+        trace_acpi_pci_features_read(val);
         break;
     case PCI_RMV_BASE:
         val = s->acpi_pcihp_pci_status[bsel].hotplug_enable;
-        ACPI_PCIHP_DPRINTF("pci_rmv_read %" PRIu32 "\n", val);
+        trace_acpi_pci_rmv_read(val);
         break;
     case PCI_SEL_BASE:
         val = s->hotplug_select;
-        ACPI_PCIHP_DPRINTF("pci_sel_read %" PRIu32 "\n", val);
+        trace_acpi_pci_sel_read(val);
     default:
         break;
     }
@@ -340,13 +340,11 @@ static void pci_write(void *opaque, hwaddr addr, uint64_t data,
             break;
         }
         acpi_pcihp_eject_slot(s, s->hotplug_select, data);
-        ACPI_PCIHP_DPRINTF("pciej write %" HWADDR_PRIx " <== %" PRIu64 "\n",
-                      addr, data);
+        trace_acpi_pci_ej_write(addr, data);
         break;
     case PCI_SEL_BASE:
         s->hotplug_select = s->legacy_piix ? ACPI_PCIHP_BSEL_DEFAULT : data;
-        ACPI_PCIHP_DPRINTF("pcisel write %" HWADDR_PRIx " <== %" PRIu64 "\n",
-                      addr, data);
+        trace_acpi_pci_sel_write(addr, data);
     default:
         break;
     }
diff --git a/hw/acpi/piix4.c b/hw/acpi/piix4.c
index c903e65..ec4e186 100644
--- a/hw/acpi/piix4.c
+++ b/hw/acpi/piix4.c
@@ -39,14 +39,7 @@
 #include "hw/acpi/acpi_dev_interface.h"
 #include "hw/xen/xen.h"
 #include "qom/cpu.h"
-
-//#define DEBUG
-
-#ifdef DEBUG
-# define PIIX4_DPRINTF(format, ...)     printf(format, ## __VA_ARGS__)
-#else
-# define PIIX4_DPRINTF(format, ...)     do { } while (0)
-#endif
+#include "trace.h"
 
 #define GPE_BASE 0xafe0
 #define GPE_LEN 4
@@ -583,7 +576,7 @@ static uint64_t gpe_readb(void *opaque, hwaddr addr, unsigned width)
     PIIX4PMState *s = opaque;
     uint32_t val = acpi_gpe_ioport_readb(&s->ar, addr);
 
-    PIIX4_DPRINTF("gpe read %" HWADDR_PRIx " == %" PRIu32 "\n", addr, val);
+    trace_piix4_gpe_readb(addr, width, val);
     return val;
 }
 
@@ -592,10 +585,9 @@ static void gpe_writeb(void *opaque, hwaddr addr, uint64_t val,
 {
     PIIX4PMState *s = opaque;
 
+    trace_piix4_gpe_writeb(addr, width, val);
     acpi_gpe_ioport_writeb(&s->ar, addr, val);
     acpi_update_sci(&s->ar, s->irq);
-
-    PIIX4_DPRINTF("gpe write %" HWADDR_PRIx " <== %" PRIu64 "\n", addr, val);
 }
 
 static const MemoryRegionOps piix4_gpe_ops = {
diff --git a/hw/acpi/trace-events b/hw/acpi/trace-events
index 6272d8a..96b8273 100644
--- a/hw/acpi/trace-events
+++ b/hw/acpi/trace-events
@@ -31,6 +31,22 @@ cpuhp_acpi_ejecting_cpu(uint32_t idx) "0x%"PRIx32
 cpuhp_acpi_write_ost_ev(uint32_t slot, uint32_t ev) "idx[0x%"PRIx32"] OST EVENT: 0x%"PRIx32
 cpuhp_acpi_write_ost_status(uint32_t slot, uint32_t st) "idx[0x%"PRIx32"] OST STATUS: 0x%"PRIx32
 
+# pcihp.c
+acpi_pci_eject_slot(unsigned bsel, unsigned slot) "bsel: %u slot: %u"
+acpi_pci_unplug(int bsel, int slot) "bsel: %d slot: %d"
+acpi_pci_unplug_request(int bsel, int slot) "bsel: %d slot: %d"
+acpi_pci_up_read(uint32_t val) "%" PRIu32
+acpi_pci_down_read(uint32_t val) "%" PRIu32
+acpi_pci_features_read(uint32_t val) "%" PRIu32
+acpi_pci_rmv_read(uint32_t val) "%" PRIu32
+acpi_pci_sel_read(uint32_t val) "%" PRIu32
+acpi_pci_ej_write(uint64_t addr, uint64_t data) "0x%" PRIx64 " <== %" PRIu64
+acpi_pci_sel_write(uint64_t addr, uint64_t data) "0x%" PRIx64 " <== %" PRIu64
+
+# piix4.c
+piix4_gpe_readb(uint64_t addr, unsigned width, uint64_t val) "addr: 0x%" PRIx64 " width: %d ==> 0x%" PRIx64
+piix4_gpe_writeb(uint64_t addr, unsigned width, uint64_t val) "addr: 0x%" PRIx64 " width: %d <== 0x%" PRIx64
+
 # tco.c
 tco_timer_reload(int ticks, int msec) "ticks=%d (%d ms)"
 tco_timer_expired(int timeouts_no, bool strap, bool no_reboot) "timeouts_no=%d no_reboot=%d/%d"
diff --git a/hw/arm/virt-acpi-build.c b/hw/arm/virt-acpi-build.c
index bf9c0bc..e7c96d6 100644
--- a/hw/arm/virt-acpi-build.c
+++ b/hw/arm/virt-acpi-build.c
@@ -40,6 +40,7 @@
 #include "hw/loader.h"
 #include "hw/hw.h"
 #include "hw/acpi/aml-build.h"
+#include "hw/acpi/pci.h"
 #include "hw/pci/pcie_host.h"
 #include "hw/pci/pci.h"
 #include "hw/arm/virt.h"
@@ -546,25 +547,20 @@ build_srat(GArray *table_data, BIOSLinker *linker, VirtMachineState *vms)
 }
 
 static void
-build_mcfg(GArray *table_data, BIOSLinker *linker, VirtMachineState *vms)
+build_mcfg(GArray *table_data, BIOSLinker *linker, AcpiMcfgInfo *info)
 {
     AcpiTableMcfg *mcfg;
-    const MemMapEntry *memmap = vms->memmap;
-    int ecam_id = VIRT_ECAM_ID(vms->highmem_ecam);
     int len = sizeof(*mcfg) + sizeof(mcfg->allocation[0]);
-    int mcfg_start = table_data->len;
 
     mcfg = acpi_data_push(table_data, len);
-    mcfg->allocation[0].address = cpu_to_le64(memmap[ecam_id].base);
+    mcfg->allocation[0].address = cpu_to_le64(info->base);
 
     /* Only a single allocation so no need to play with segments */
     mcfg->allocation[0].pci_segment = cpu_to_le16(0);
     mcfg->allocation[0].start_bus_number = 0;
-    mcfg->allocation[0].end_bus_number =
-        PCIE_MMCFG_BUS(memmap[ecam_id].size - 1);
+    mcfg->allocation[0].end_bus_number = PCIE_MMCFG_BUS(info->size - 1);
 
-    build_header(linker, table_data, (void *)(table_data->data + mcfg_start),
-                 "MCFG", table_data->len - mcfg_start, 1, NULL, NULL);
+    build_header(linker, table_data, (void *)mcfg, "MCFG", len, 1, NULL, NULL);
 }
 
 /* GTDT */
@@ -803,7 +799,13 @@ void virt_acpi_build(VirtMachineState *vms, AcpiBuildTables *tables)
     build_gtdt(tables_blob, tables->linker, vms);
 
     acpi_add_table(table_offsets, tables_blob);
-    build_mcfg(tables_blob, tables->linker, vms);
+    {
+        AcpiMcfgInfo mcfg = {
+           .base = vms->memmap[VIRT_ECAM_ID(vms->highmem_ecam)].base,
+           .size = vms->memmap[VIRT_ECAM_ID(vms->highmem_ecam)].size,
+        };
+        build_mcfg(tables_blob, tables->linker, &mcfg);
+    }
 
     acpi_add_table(table_offsets, tables_blob);
     build_spcr(tables_blob, tables->linker, vms);
diff --git a/hw/block/vhost-user-blk.c b/hw/block/vhost-user-blk.c
index 28b8136..9cb6133 100644
--- a/hw/block/vhost-user-blk.c
+++ b/hw/block/vhost-user-blk.c
@@ -103,7 +103,7 @@ const VhostDevConfigOps blk_ops = {
     .vhost_dev_config_notifier = vhost_user_blk_handle_config_change,
 };
 
-static void vhost_user_blk_start(VirtIODevice *vdev)
+static int vhost_user_blk_start(VirtIODevice *vdev)
 {
     VHostUserBlk *s = VHOST_USER_BLK(vdev);
     BusState *qbus = BUS(qdev_get_parent_bus(DEVICE(vdev)));
@@ -112,13 +112,13 @@ static void vhost_user_blk_start(VirtIODevice *vdev)
 
     if (!k->set_guest_notifiers) {
         error_report("binding does not support guest notifiers");
-        return;
+        return -ENOSYS;
     }
 
     ret = vhost_dev_enable_notifiers(&s->dev, vdev);
     if (ret < 0) {
         error_report("Error enabling host notifiers: %d", -ret);
-        return;
+        return ret;
     }
 
     ret = k->set_guest_notifiers(qbus->parent, s->dev.nvqs, true);
@@ -157,12 +157,13 @@ static void vhost_user_blk_start(VirtIODevice *vdev)
         vhost_virtqueue_mask(&s->dev, vdev, i, false);
     }
 
-    return;
+    return ret;
 
 err_guest_notifiers:
     k->set_guest_notifiers(qbus->parent, s->dev.nvqs, false);
 err_host_notifiers:
     vhost_dev_disable_notifiers(&s->dev, vdev);
+    return ret;
 }
 
 static void vhost_user_blk_stop(VirtIODevice *vdev)
@@ -190,18 +191,28 @@ static void vhost_user_blk_stop(VirtIODevice *vdev)
 static void vhost_user_blk_set_status(VirtIODevice *vdev, uint8_t status)
 {
     VHostUserBlk *s = VHOST_USER_BLK(vdev);
-    bool should_start = status & VIRTIO_CONFIG_S_DRIVER_OK;
+    bool should_start = vdev->started;
+    int ret;
 
     if (!vdev->vm_running) {
         should_start = false;
     }
 
+    if (!s->connected) {
+        return;
+    }
+
     if (s->dev.started == should_start) {
         return;
     }
 
     if (should_start) {
-        vhost_user_blk_start(vdev);
+        ret = vhost_user_blk_start(vdev);
+        if (ret < 0) {
+            error_report("vhost-user-blk: vhost start failed: %s",
+                         strerror(-ret));
+            qemu_chr_fe_disconnect(&s->chardev);
+        }
     } else {
         vhost_user_blk_stop(vdev);
     }
@@ -237,10 +248,13 @@ static uint64_t vhost_user_blk_get_features(VirtIODevice *vdev,
 static void vhost_user_blk_handle_output(VirtIODevice *vdev, VirtQueue *vq)
 {
     VHostUserBlk *s = VHOST_USER_BLK(vdev);
-    int i;
+    int i, ret;
 
-    if (!(virtio_host_has_feature(vdev, VIRTIO_F_VERSION_1) &&
-        !virtio_vdev_has_feature(vdev, VIRTIO_F_VERSION_1))) {
+    if (!vdev->start_on_kick) {
+        return;
+    }
+
+    if (!s->connected) {
         return;
     }
 
@@ -251,7 +265,13 @@ static void vhost_user_blk_handle_output(VirtIODevice *vdev, VirtQueue *vq)
     /* Some guests kick before setting VIRTIO_CONFIG_S_DRIVER_OK so start
      * vhost here instead of waiting for .set_status().
      */
-    vhost_user_blk_start(vdev);
+    ret = vhost_user_blk_start(vdev);
+    if (ret < 0) {
+        error_report("vhost-user-blk: vhost start failed: %s",
+                     strerror(-ret));
+        qemu_chr_fe_disconnect(&s->chardev);
+        return;
+    }
 
     /* Kick right away to begin processing requests already in vring */
     for (i = 0; i < s->dev.nvqs; i++) {
@@ -271,11 +291,103 @@ static void vhost_user_blk_reset(VirtIODevice *vdev)
     vhost_dev_free_inflight(s->inflight);
 }
 
+static int vhost_user_blk_connect(DeviceState *dev)
+{
+    VirtIODevice *vdev = VIRTIO_DEVICE(dev);
+    VHostUserBlk *s = VHOST_USER_BLK(vdev);
+    int ret = 0;
+
+    if (s->connected) {
+        return 0;
+    }
+    s->connected = true;
+
+    s->dev.nvqs = s->num_queues;
+    s->dev.vqs = s->vqs;
+    s->dev.vq_index = 0;
+    s->dev.backend_features = 0;
+
+    vhost_dev_set_config_notifier(&s->dev, &blk_ops);
+
+    ret = vhost_dev_init(&s->dev, &s->vhost_user, VHOST_BACKEND_TYPE_USER, 0);
+    if (ret < 0) {
+        error_report("vhost-user-blk: vhost initialization failed: %s",
+                     strerror(-ret));
+        return ret;
+    }
+
+    /* restore vhost state */
+    if (vdev->started) {
+        ret = vhost_user_blk_start(vdev);
+        if (ret < 0) {
+            error_report("vhost-user-blk: vhost start failed: %s",
+                         strerror(-ret));
+            return ret;
+        }
+    }
+
+    return 0;
+}
+
+static void vhost_user_blk_disconnect(DeviceState *dev)
+{
+    VirtIODevice *vdev = VIRTIO_DEVICE(dev);
+    VHostUserBlk *s = VHOST_USER_BLK(vdev);
+
+    if (!s->connected) {
+        return;
+    }
+    s->connected = false;
+
+    if (s->dev.started) {
+        vhost_user_blk_stop(vdev);
+    }
+
+    vhost_dev_cleanup(&s->dev);
+}
+
+static gboolean vhost_user_blk_watch(GIOChannel *chan, GIOCondition cond,
+                                     void *opaque)
+{
+    DeviceState *dev = opaque;
+    VirtIODevice *vdev = VIRTIO_DEVICE(dev);
+    VHostUserBlk *s = VHOST_USER_BLK(vdev);
+
+    qemu_chr_fe_disconnect(&s->chardev);
+
+    return true;
+}
+
+static void vhost_user_blk_event(void *opaque, int event)
+{
+    DeviceState *dev = opaque;
+    VirtIODevice *vdev = VIRTIO_DEVICE(dev);
+    VHostUserBlk *s = VHOST_USER_BLK(vdev);
+
+    switch (event) {
+    case CHR_EVENT_OPENED:
+        if (vhost_user_blk_connect(dev) < 0) {
+            qemu_chr_fe_disconnect(&s->chardev);
+            return;
+        }
+        s->watch = qemu_chr_fe_add_watch(&s->chardev, G_IO_HUP,
+                                         vhost_user_blk_watch, dev);
+        break;
+    case CHR_EVENT_CLOSED:
+        vhost_user_blk_disconnect(dev);
+        if (s->watch) {
+            g_source_remove(s->watch);
+            s->watch = 0;
+        }
+        break;
+    }
+}
+
 static void vhost_user_blk_device_realize(DeviceState *dev, Error **errp)
 {
     VirtIODevice *vdev = VIRTIO_DEVICE(dev);
     VHostUserBlk *s = VHOST_USER_BLK(vdev);
-    struct vhost_virtqueue *vqs = NULL;
+    Error *err = NULL;
     int i, ret;
 
     if (!s->chardev.chr) {
@@ -306,27 +418,29 @@ static void vhost_user_blk_device_realize(DeviceState *dev, Error **errp)
     }
 
     s->inflight = g_new0(struct vhost_inflight, 1);
+    s->vqs = g_new(struct vhost_virtqueue, s->num_queues);
+    s->watch = 0;
+    s->connected = false;
 
-    s->dev.nvqs = s->num_queues;
-    s->dev.vqs = g_new(struct vhost_virtqueue, s->dev.nvqs);
-    s->dev.vq_index = 0;
-    s->dev.backend_features = 0;
-    vqs = s->dev.vqs;
-
-    vhost_dev_set_config_notifier(&s->dev, &blk_ops);
+    qemu_chr_fe_set_handlers(&s->chardev,  NULL, NULL, vhost_user_blk_event,
+                             NULL, (void *)dev, NULL, true);
 
-    ret = vhost_dev_init(&s->dev, &s->vhost_user, VHOST_BACKEND_TYPE_USER, 0);
-    if (ret < 0) {
-        error_setg(errp, "vhost-user-blk: vhost initialization failed: %s",
-                   strerror(-ret));
+reconnect:
+    if (qemu_chr_fe_wait_connected(&s->chardev, &err) < 0) {
+        error_report_err(err);
         goto virtio_err;
     }
 
+    /* check whether vhost_user_blk_connect() failed or not */
+    if (!s->connected) {
+        goto reconnect;
+    }
+
     ret = vhost_dev_get_config(&s->dev, (uint8_t *)&s->blkcfg,
-                              sizeof(struct virtio_blk_config));
+                               sizeof(struct virtio_blk_config));
     if (ret < 0) {
-        error_setg(errp, "vhost-user-blk: get block config failed");
-        goto vhost_err;
+        error_report("vhost-user-blk: get block config failed");
+        goto reconnect;
     }
 
     if (s->blkcfg.num_queues != s->num_queues) {
@@ -335,10 +449,8 @@ static void vhost_user_blk_device_realize(DeviceState *dev, Error **errp)
 
     return;
 
-vhost_err:
-    vhost_dev_cleanup(&s->dev);
 virtio_err:
-    g_free(vqs);
+    g_free(s->vqs);
     g_free(s->inflight);
     virtio_cleanup(vdev);
     vhost_user_cleanup(&s->vhost_user);
@@ -348,12 +460,13 @@ static void vhost_user_blk_device_unrealize(DeviceState *dev, Error **errp)
 {
     VirtIODevice *vdev = VIRTIO_DEVICE(dev);
     VHostUserBlk *s = VHOST_USER_BLK(dev);
-    struct vhost_virtqueue *vqs = s->dev.vqs;
 
-    vhost_user_blk_set_status(vdev, 0);
+    virtio_set_status(vdev, 0);
+    qemu_chr_fe_set_handlers(&s->chardev,  NULL, NULL, NULL,
+                             NULL, NULL, NULL, false);
     vhost_dev_cleanup(&s->dev);
     vhost_dev_free_inflight(s->inflight);
-    g_free(vqs);
+    g_free(s->vqs);
     g_free(s->inflight);
     virtio_cleanup(vdev);
     vhost_user_cleanup(&s->vhost_user);
diff --git a/hw/core/machine.c b/hw/core/machine.c
index 5d046a4..934c1bc 100644
--- a/hw/core/machine.c
+++ b/hw/core/machine.c
@@ -102,9 +102,26 @@ const size_t hw_compat_2_7_len = G_N_ELEMENTS(hw_compat_2_7);
 
 GlobalProperty hw_compat_2_6[] = {
     { "virtio-mmio", "format_transport_address", "off" },
-    /* Optional because not all virtio-pci devices support legacy mode */
-    { "virtio-pci", "disable-modern", "on",  .optional = true },
-    { "virtio-pci", "disable-legacy", "off", .optional = true },
+    /*
+     * don't include devices which are modern-only
+     * ie keyboard, mouse, tablet, gpu, vga & crypto
+     */
+    { "virtio-9p-pci", "disable-modern", "on" },
+    { "virtio-9p-pci", "disable-legacy", "off" },
+    { "virtio-balloon-pci", "disable-modern", "on" },
+    { "virtio-balloon-pci", "disable-legacy", "off" },
+    { "virtio-blk-pci", "disable-modern", "on" },
+    { "virtio-blk-pci", "disable-legacy", "off" },
+    { "virtio-input-host-pci", "disable-modern", "on" },
+    { "virtio-input-host-pci", "disable-legacy", "off" },
+    { "virtio-net-pci", "disable-modern", "on" },
+    { "virtio-net-pci", "disable-legacy", "off" },
+    { "virtio-rng-pci", "disable-modern", "on" },
+    { "virtio-rng-pci", "disable-legacy", "off" },
+    { "virtio-scsi-pci", "disable-modern", "on" },
+    { "virtio-scsi-pci", "disable-legacy", "off" },
+    { "virtio-serial-pci", "disable-modern", "on" },
+    { "virtio-serial-pci", "disable-legacy", "off" },
 };
 const size_t hw_compat_2_6_len = G_N_ELEMENTS(hw_compat_2_6);
 
diff --git a/hw/display/virtio-gpu-pci.c b/hw/display/virtio-gpu-pci.c
index bdcd33c..0bc4d9d 100644
--- a/hw/display/virtio-gpu-pci.c
+++ b/hw/display/virtio-gpu-pci.c
@@ -47,7 +47,9 @@ static void virtio_gpu_pci_realize(VirtIOPCIProxy *vpci_dev, Error **errp)
     Error *local_error = NULL;
 
     qdev_set_parent_bus(vdev, BUS(&vpci_dev->bus));
-    virtio_pci_force_virtio_1(vpci_dev);
+    if (!virtio_pci_force_virtio_1(vpci_dev, errp)) {
+        return;
+    }
     object_property_set_bool(OBJECT(vdev), true, "realized", &local_error);
 
     if (local_error) {
diff --git a/hw/display/virtio-vga.c b/hw/display/virtio-vga.c
index a2b803b..5d57bf5 100644
--- a/hw/display/virtio-vga.c
+++ b/hw/display/virtio-vga.c
@@ -154,7 +154,9 @@ static void virtio_vga_realize(VirtIOPCIProxy *vpci_dev, Error **errp)
 
     /* init virtio bits */
     qdev_set_parent_bus(DEVICE(g), BUS(&vpci_dev->bus));
-    virtio_pci_force_virtio_1(vpci_dev);
+    if (!virtio_pci_force_virtio_1(vpci_dev, errp)) {
+        return;
+    }
     object_property_set_bool(OBJECT(g), true, "realized", &err);
     if (err) {
         error_propagate(errp, err);
diff --git a/hw/i386/acpi-build.c b/hw/i386/acpi-build.c
index b4ec14e..0d78d73 100644
--- a/hw/i386/acpi-build.c
+++ b/hw/i386/acpi-build.c
@@ -59,6 +59,7 @@
 #include "hw/i386/x86-iommu.h"
 
 #include "hw/acpi/aml-build.h"
+#include "hw/acpi/pci.h"
 
 #include "qom/qom-qobject.h"
 #include "hw/i386/amd_iommu.h"
@@ -87,11 +88,6 @@
 /* Default IOAPIC ID */
 #define ACPI_BUILD_IOAPIC_ID 0x0
 
-typedef struct AcpiMcfgInfo {
-    uint64_t mcfg_base;
-    uint32_t mcfg_size;
-} AcpiMcfgInfo;
-
 typedef struct AcpiPmInfo {
     bool s3_disabled;
     bool s4_disabled;
@@ -2413,29 +2409,16 @@ static void
 build_mcfg_q35(GArray *table_data, BIOSLinker *linker, AcpiMcfgInfo *info)
 {
     AcpiTableMcfg *mcfg;
-    const char *sig;
     int len = sizeof(*mcfg) + 1 * sizeof(mcfg->allocation[0]);
 
     mcfg = acpi_data_push(table_data, len);
-    mcfg->allocation[0].address = cpu_to_le64(info->mcfg_base);
+    mcfg->allocation[0].address = cpu_to_le64(info->base);
     /* Only a single allocation so no need to play with segments */
     mcfg->allocation[0].pci_segment = cpu_to_le16(0);
     mcfg->allocation[0].start_bus_number = 0;
-    mcfg->allocation[0].end_bus_number = PCIE_MMCFG_BUS(info->mcfg_size - 1);
+    mcfg->allocation[0].end_bus_number = PCIE_MMCFG_BUS(info->size - 1);
 
-    /* MCFG is used for ECAM which can be enabled or disabled by guest.
-     * To avoid table size changes (which create migration issues),
-     * always create the table even if there are no allocations,
-     * but set the signature to a reserved value in this case.
-     * ACPI spec requires OSPMs to ignore such tables.
-     */
-    if (info->mcfg_base == PCIE_BASE_ADDR_UNMAPPED) {
-        /* Reserved signature: ignored by OSPM */
-        sig = "QEMU";
-    } else {
-        sig = "MCFG";
-    }
-    build_header(linker, table_data, (void *)mcfg, sig, len, 1, NULL, NULL);
+    build_header(linker, table_data, (void *)mcfg, "MCFG", len, 1, NULL, NULL);
 }
 
 /*
@@ -2602,12 +2585,15 @@ static bool acpi_get_mcfg(AcpiMcfgInfo *mcfg)
     if (!o) {
         return false;
     }
-    mcfg->mcfg_base = qnum_get_uint(qobject_to(QNum, o));
+    mcfg->base = qnum_get_uint(qobject_to(QNum, o));
     qobject_unref(o);
+    if (mcfg->base == PCIE_BASE_ADDR_UNMAPPED) {
+        return false;
+    }
 
     o = object_property_get_qobject(pci_host, PCIE_HOST_MCFG_SIZE, NULL);
     assert(o);
-    mcfg->mcfg_size = qnum_get_uint(qobject_to(QNum, o));
+    mcfg->size = qnum_get_uint(qobject_to(QNum, o));
     qobject_unref(o);
     return true;
 }
diff --git a/hw/pci-bridge/pci_expander_bridge.c b/hw/pci-bridge/pci_expander_bridge.c
index e62de42..ca66bc7 100644
--- a/hw/pci-bridge/pci_expander_bridge.c
+++ b/hw/pci-bridge/pci_expander_bridge.c
@@ -66,11 +66,6 @@ static int pxb_bus_num(PCIBus *bus)
     return pxb->bus_nr;
 }
 
-static bool pxb_is_root(PCIBus *bus)
-{
-    return true; /* by definition */
-}
-
 static uint16_t pxb_bus_numa_node(PCIBus *bus)
 {
     PXBDev *pxb = convert_to_pxb(bus->parent_dev);
@@ -83,7 +78,6 @@ static void pxb_bus_class_init(ObjectClass *class, void *data)
     PCIBusClass *pbc = PCI_BUS_CLASS(class);
 
     pbc->bus_num = pxb_bus_num;
-    pbc->is_root = pxb_is_root;
     pbc->numa_node = pxb_bus_numa_node;
 }
 
diff --git a/hw/pci/pci.c b/hw/pci/pci.c
index a78023f..b386777 100644
--- a/hw/pci/pci.c
+++ b/hw/pci/pci.c
@@ -129,14 +129,9 @@ static void pci_bus_unrealize(BusState *qbus, Error **errp)
     vmstate_unregister(NULL, &vmstate_pcibus, bus);
 }
 
-static bool pcibus_is_root(PCIBus *bus)
-{
-    return !bus->parent_dev;
-}
-
 static int pcibus_num(PCIBus *bus)
 {
-    if (pcibus_is_root(bus)) {
+    if (pci_bus_is_root(bus)) {
         return 0; /* pci host bridge */
     }
     return bus->parent_dev->config[PCI_SECONDARY_BUS];
@@ -164,7 +159,6 @@ static void pci_bus_class_init(ObjectClass *klass, void *data)
     k->unrealize = pci_bus_unrealize;
     k->reset = pcibus_reset;
 
-    pbc->is_root = pcibus_is_root;
     pbc->bus_num = pcibus_num;
     pbc->numa_node = pcibus_numa_node;
     pbc->allows_extended_config_space = pcibus_allows_extended_config_space;
@@ -398,6 +392,7 @@ static void pci_root_bus_init(PCIBus *bus, DeviceState *parent,
     bus->slot_reserved_mask = 0x0;
     bus->address_space_mem = address_space_mem;
     bus->address_space_io = address_space_io;
+    bus->flags |= PCI_BUS_IS_ROOT;
 
     /* host bridge */
     QLIST_INIT(&bus->child);
@@ -415,11 +410,6 @@ bool pci_bus_is_express(PCIBus *bus)
     return object_dynamic_cast(OBJECT(bus), TYPE_PCIE_BUS);
 }
 
-bool pci_bus_is_root(PCIBus *bus)
-{
-    return PCI_BUS_GET_CLASS(bus)->is_root(bus);
-}
-
 bool pci_bus_allows_extended_config_space(PCIBus *bus)
 {
     return PCI_BUS_GET_CLASS(bus)->allows_extended_config_space(bus);
diff --git a/hw/pci/pcie_host.c b/hw/pci/pcie_host.c
index 553db56..1ee4945 100644
--- a/hw/pci/pcie_host.c
+++ b/hw/pci/pcie_host.c
@@ -47,11 +47,6 @@ static void pcie_mmcfg_data_write(void *opaque, hwaddr mmcfg_addr,
     }
     addr = PCIE_MMCFG_CONFOFFSET(mmcfg_addr);
     limit = pci_config_size(pci_dev);
-    if (limit <= addr) {
-        /* conventional pci device can be behind pcie-to-pci bridge.
-           256 <= addr < 4K has no effects. */
-        return;
-    }
     pci_host_config_write_common(pci_dev, addr, limit, val, len);
 }
 
@@ -70,11 +65,6 @@ static uint64_t pcie_mmcfg_data_read(void *opaque,
     }
     addr = PCIE_MMCFG_CONFOFFSET(mmcfg_addr);
     limit = pci_config_size(pci_dev);
-    if (limit <= addr) {
-        /* conventional pci device can be behind pcie-to-pci bridge.
-           256 <= addr < 4K has no effects. */
-        return ~0x0;
-    }
     return pci_host_config_read_common(pci_dev, addr, limit, len);
 }
 
diff --git a/hw/virtio/virtio-crypto-pci.c b/hw/virtio/virtio-crypto-pci.c
index 90a6e0d..13807e5 100644
--- a/hw/virtio/virtio-crypto-pci.c
+++ b/hw/virtio/virtio-crypto-pci.c
@@ -51,7 +51,9 @@ static void virtio_crypto_pci_realize(VirtIOPCIProxy *vpci_dev, Error **errp)
     }
 
     qdev_set_parent_bus(vdev, BUS(&vpci_dev->bus));
-    virtio_pci_force_virtio_1(vpci_dev);
+    if (!virtio_pci_force_virtio_1(vpci_dev, errp)) {
+        return;
+    }
     object_property_set_bool(OBJECT(vdev), true, "realized", errp);
     object_property_set_link(OBJECT(vcrypto),
                  OBJECT(vcrypto->vdev.conf.cryptodev), "cryptodev",
diff --git a/hw/virtio/virtio-input-pci.c b/hw/virtio/virtio-input-pci.c
index 2c13978..2847772 100644
--- a/hw/virtio/virtio-input-pci.c
+++ b/hw/virtio/virtio-input-pci.c
@@ -48,7 +48,9 @@ static void virtio_input_pci_realize(VirtIOPCIProxy *vpci_dev, Error **errp)
     DeviceState *vdev = DEVICE(&vinput->vdev);
 
     qdev_set_parent_bus(vdev, BUS(&vpci_dev->bus));
-    virtio_pci_force_virtio_1(vpci_dev);
+    if (!virtio_pci_force_virtio_1(vpci_dev, errp)) {
+        return;
+    }
     object_property_set_bool(OBJECT(vdev), true, "realized", errp);
 }
 
diff --git a/hw/virtio/virtio-pci.c b/hw/virtio/virtio-pci.c
index cb44e19..9056cdf 100644
--- a/hw/virtio/virtio-pci.c
+++ b/hw/virtio/virtio-pci.c
@@ -20,6 +20,7 @@
 #include "standard-headers/linux/virtio_pci.h"
 #include "hw/virtio/virtio.h"
 #include "hw/pci/pci.h"
+#include "hw/pci/pci_bus.h"
 #include "qapi/error.h"
 #include "qemu/error-report.h"
 #include "hw/pci/msi.h"
@@ -1721,16 +1722,22 @@ static void virtio_pci_realize(PCIDevice *pci_dev, Error **errp)
                        /* PCI BAR regions must be powers of 2 */
                        pow2ceil(proxy->notify.offset + proxy->notify.size));
 
-    if (proxy->disable_legacy == ON_OFF_AUTO_AUTO) {
-        proxy->disable_legacy = pcie_port ? ON_OFF_AUTO_ON : ON_OFF_AUTO_OFF;
-    }
-
-    if (!virtio_pci_modern(proxy) && !virtio_pci_legacy(proxy)) {
-        error_setg(errp, "device cannot work as neither modern nor legacy mode"
-                   " is enabled");
-        error_append_hint(errp, "Set either disable-modern or disable-legacy"
-                          " to off\n");
-        return;
+    if ((proxy->disable_legacy == ON_OFF_AUTO_ON) ||
+        ((proxy->disable_legacy == ON_OFF_AUTO_AUTO) && pcie_port)) {
+        if (proxy->disable_modern) {
+            error_setg(errp, "device cannot work as neither modern nor "
+                       "legacy mode is enabled");
+            error_append_hint(errp, "Set either disable-modern or "
+                              "disable-legacy to off\n");
+            return;
+        }
+        proxy->mode = VIRTIO_PCI_MODE_MODERN;
+    } else {
+        if (proxy->disable_modern) {
+            proxy->mode = VIRTIO_PCI_MODE_LEGACY;
+        } else {
+            proxy->mode = VIRTIO_PCI_MODE_TRANSITIONAL;
+        }
     }
 
     if (pcie_port && pci_is_express(pci_dev)) {
diff --git a/hw/virtio/virtio-pci.h b/hw/virtio/virtio-pci.h
index 1858185..bfea289 100644
--- a/hw/virtio/virtio-pci.h
+++ b/hw/virtio/virtio-pci.h
@@ -15,6 +15,7 @@
 #ifndef QEMU_VIRTIO_PCI_H
 #define QEMU_VIRTIO_PCI_H
 
+#include "qapi/error.h"
 #include "hw/pci/msi.h"
 #include "hw/virtio/virtio-bus.h"
 
@@ -118,6 +119,12 @@ typedef struct VirtIOPCIQueue {
   uint32_t used[2];
 } VirtIOPCIQueue;
 
+typedef enum {
+    VIRTIO_PCI_MODE_LEGACY,
+    VIRTIO_PCI_MODE_TRANSITIONAL,
+    VIRTIO_PCI_MODE_MODERN,
+} VirtIOPCIMode;
+
 struct VirtIOPCIProxy {
     PCIDevice pci_dev;
     MemoryRegion bar;
@@ -142,6 +149,7 @@ struct VirtIOPCIProxy {
     bool disable_modern;
     bool ignore_backend_features;
     OnOffAuto disable_legacy;
+    VirtIOPCIMode mode;
     uint32_t class_code;
     uint32_t nvectors;
     uint32_t dfselect;
@@ -156,23 +164,34 @@ struct VirtIOPCIProxy {
 
 static inline bool virtio_pci_modern(VirtIOPCIProxy *proxy)
 {
-    return !proxy->disable_modern;
+    return proxy->mode != VIRTIO_PCI_MODE_LEGACY;
 }
 
 static inline bool virtio_pci_legacy(VirtIOPCIProxy *proxy)
 {
-    return proxy->disable_legacy == ON_OFF_AUTO_OFF;
+    return proxy->mode != VIRTIO_PCI_MODE_MODERN;
 }
 
-static inline void virtio_pci_force_virtio_1(VirtIOPCIProxy *proxy)
+static inline bool virtio_pci_force_virtio_1(VirtIOPCIProxy *proxy,
+                                             Error **errp)
 {
-    proxy->disable_modern = false;
-    proxy->disable_legacy = ON_OFF_AUTO_ON;
+    if (proxy->disable_legacy == ON_OFF_AUTO_OFF) {
+        error_setg(errp, "Unable to set disable-legacy=off on a virtio-1.0 "
+                   "only device");
+        return false;
+    }
+    if (proxy->disable_modern == true) {
+        error_setg(errp, "Unable to set disable-modern=on on a virtio-1.0 "
+                   "only device");
+        return false;
+    }
+    proxy->mode = VIRTIO_PCI_MODE_MODERN;
+    return true;
 }
 
 static inline void virtio_pci_disable_modern(VirtIOPCIProxy *proxy)
 {
-    proxy->disable_modern = true;
+    proxy->mode = VIRTIO_PCI_MODE_LEGACY;
 }
 
 /*
diff --git a/hw/virtio/virtio.c b/hw/virtio/virtio.c
index 28056a7..4805727 100644
--- a/hw/virtio/virtio.c
+++ b/hw/virtio/virtio.c
@@ -1162,10 +1162,16 @@ int virtio_set_status(VirtIODevice *vdev, uint8_t val)
             }
         }
     }
+    vdev->started = val & VIRTIO_CONFIG_S_DRIVER_OK;
+    if (unlikely(vdev->start_on_kick && vdev->started)) {
+        vdev->start_on_kick = false;
+    }
+
     if (k->set_status) {
         k->set_status(vdev, val);
     }
     vdev->status = val;
+
     return 0;
 }
 
@@ -1208,6 +1214,9 @@ void virtio_reset(void *opaque)
         k->reset(vdev);
     }
 
+    vdev->start_on_kick = (virtio_host_has_feature(vdev, VIRTIO_F_VERSION_1) &&
+                          !virtio_vdev_has_feature(vdev, VIRTIO_F_VERSION_1));
+    vdev->started = false;
     vdev->broken = false;
     vdev->guest_features = 0;
     vdev->queue_sel = 0;
@@ -1518,14 +1527,21 @@ void virtio_queue_set_align(VirtIODevice *vdev, int n, int align)
 
 static bool virtio_queue_notify_aio_vq(VirtQueue *vq)
 {
+    bool ret = false;
+
     if (vq->vring.desc && vq->handle_aio_output) {
         VirtIODevice *vdev = vq->vdev;
 
         trace_virtio_queue_notify(vdev, vq - vdev->vq, vq);
-        return vq->handle_aio_output(vdev, vq);
+        ret = vq->handle_aio_output(vdev, vq);
+
+        if (unlikely(vdev->start_on_kick)) {
+            vdev->started = true;
+            vdev->start_on_kick = false;
+        }
     }
 
-    return false;
+    return ret;
 }
 
 static void virtio_queue_notify_vq(VirtQueue *vq)
@@ -1539,6 +1555,11 @@ static void virtio_queue_notify_vq(VirtQueue *vq)
 
         trace_virtio_queue_notify(vdev, vq - vdev->vq, vq);
         vq->handle_output(vdev, vq);
+
+        if (unlikely(vdev->start_on_kick)) {
+            vdev->started = true;
+            vdev->start_on_kick = false;
+        }
     }
 }
 
@@ -1556,6 +1577,11 @@ void virtio_queue_notify(VirtIODevice *vdev, int n)
     } else if (vq->handle_output) {
         vq->handle_output(vdev, vq);
     }
+
+    if (unlikely(vdev->start_on_kick)) {
+        vdev->started = true;
+        vdev->start_on_kick = false;
+    }
 }
 
 uint16_t virtio_queue_vector(VirtIODevice *vdev, int n)
@@ -1770,6 +1796,13 @@ static bool virtio_broken_needed(void *opaque)
     return vdev->broken;
 }
 
+static bool virtio_started_needed(void *opaque)
+{
+    VirtIODevice *vdev = opaque;
+
+    return vdev->started;
+}
+
 static const VMStateDescription vmstate_virtqueue = {
     .name = "virtqueue_state",
     .version_id = 1,
@@ -1898,6 +1931,17 @@ static const VMStateDescription vmstate_virtio_broken = {
     }
 };
 
+static const VMStateDescription vmstate_virtio_started = {
+    .name = "virtio/started",
+    .version_id = 1,
+    .minimum_version_id = 1,
+    .needed = &virtio_started_needed,
+    .fields = (VMStateField[]) {
+        VMSTATE_BOOL(started, VirtIODevice),
+        VMSTATE_END_OF_LIST()
+    }
+};
+
 static const VMStateDescription vmstate_virtio = {
     .name = "virtio",
     .version_id = 1,
@@ -1913,6 +1957,7 @@ static const VMStateDescription vmstate_virtio = {
         &vmstate_virtio_ringsize,
         &vmstate_virtio_broken,
         &vmstate_virtio_extra_state,
+        &vmstate_virtio_started,
         NULL
     }
 };
@@ -2246,7 +2291,7 @@ static void virtio_vmstate_change(void *opaque, int running, RunState state)
     VirtIODevice *vdev = opaque;
     BusState *qbus = qdev_get_parent_bus(DEVICE(vdev));
     VirtioBusClass *k = VIRTIO_BUS_GET_CLASS(qbus);
-    bool backend_run = running && (vdev->status & VIRTIO_CONFIG_S_DRIVER_OK);
+    bool backend_run = running && vdev->started;
     vdev->vm_running = running;
 
     if (backend_run) {
@@ -2286,6 +2331,9 @@ void virtio_init(VirtIODevice *vdev, const char *name,
             g_malloc0(sizeof(*vdev->vector_queues) * nvectors);
     }
 
+    vdev->start_on_kick = (virtio_host_has_feature(vdev, VIRTIO_F_VERSION_1) &&
+                          !virtio_vdev_has_feature(vdev, VIRTIO_F_VERSION_1));
+    vdev->started = false;
     vdev->device_id = device_id;
     vdev->status = 0;
     atomic_set(&vdev->isr, 0);