Merge tag 'for_upstream' of https://git.kernel.org/pub/scm/virt/kvm/mst/qemu into staging

virtio,pc,pci: features, cleanups, fixes

more memslots support in libvhost-user
support PCIe Gen5/Gen6 link speeds in pcie
more traces in vdpa
network simulation devices support in vdpa
SMBIOS type 9 descriptor implementation
Bump max_cpus to 4096 vcpus in q35
aw-bits and granule options in VIRTIO-IOMMU
Support report NUMA nodes for device memory using GI in acpi
Beginning of shutdown event support in pvpanic

fixes, cleanups all over the place.

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

# -----BEGIN PGP SIGNATURE-----
#
# iQFDBAABCAAtFiEEXQn9CHHI+FuUyooNKB8NuNKNVGkFAmXw0TMPHG1zdEByZWRo
# YXQuY29tAAoJECgfDbjSjVRp8x4H+gLMoGwaGAX7gDGPgn2Ix4j/3kO77ZJ9X9k/
# 1KqZu/9eMS1j2Ei+vZqf05w7qRjxxhwDq3ilEXF/+UFqgAehLqpRRB8j5inqvzYt
# +jv0DbL11PBp/oFjWcytm5CbiVsvq8KlqCF29VNzc162XdtcduUOWagL96y8lJfZ
# uPrOoyeR7SMH9lp3LLLHWgu+9W4nOS03RroZ6Umj40y5B7yR0Rrppz8lMw5AoQtr
# 0gMRnFhYXeiW6CXdz+Tzcr7XfvkkYDi/j7ibiNSURLBfOpZa6Y8+kJGKxz5H1K1G
# 6ZY4PBcOpQzl+NMrktPHogczgJgOK10t+1i/R3bGZYw2Qn/93Eg=
# =C0UU
# -----END PGP SIGNATURE-----
# gpg: Signature made Tue 12 Mar 2024 22:03:31 GMT
# gpg:                using RSA key 5D09FD0871C8F85B94CA8A0D281F0DB8D28D5469
# gpg:                issuer "mst@redhat.com"
# 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

* tag 'for_upstream' of https://git.kernel.org/pub/scm/virt/kvm/mst/qemu: (68 commits)
  docs/specs/pvpanic: document shutdown event
  hw/cxl: Fix missing reserved data in CXL Device DVSEC
  hmat acpi: Fix out of bounds access due to missing use of indirection
  hmat acpi: Do not add Memory Proximity Domain Attributes Structure targetting non existent memory.
  qemu-options.hx: Document the virtio-iommu-pci aw-bits option
  hw/arm/virt: Set virtio-iommu aw-bits default value to 48
  hw/i386/q35: Set virtio-iommu aw-bits default value to 39
  virtio-iommu: Add an option to define the input range width
  virtio-iommu: Trace domain range limits as unsigned int
  qemu-options.hx: Document the virtio-iommu-pci granule option
  virtio-iommu: Change the default granule to the host page size
  virtio-iommu: Add a granule property
  hw/i386/acpi-build: Add support for SRAT Generic Initiator structures
  hw/acpi: Implement the SRAT GI affinity structure
  qom: new object to associate device to NUMA node
  hw/i386/pc: Inline pc_cmos_init() into pc_cmos_init_late() and remove it
  hw/i386/pc: Set "normal" boot device order in pc_basic_device_init()
  hw/i386/pc: Avoid one use of the current_machine global
  hw/i386/pc: Remove "rtc_state" link again
  Revert "hw/i386/pc: Confine system flash handling to pc_sysfw"
  ...

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

# Conflicts:
#	hw/core/machine.c

6 files changed, 313 insertions, 23 deletions

diff --git a/hw/virtio/trace-events b/hw/virtio/trace-events
index 77905d1994..13b6991179 100644
--- a/hw/virtio/trace-events
+++ b/hw/virtio/trace-events
@@ -30,6 +30,7 @@ vhost_user_write(uint32_t req, uint32_t flags) "req:%d flags:0x%"PRIx32""
 vhost_user_create_notifier(int idx, void *n) "idx:%d n:%p"
 
 # vhost-vdpa.c
+vhost_vdpa_skipped_memory_section(int is_ram, int is_iommu, int is_protected, int is_ram_device, uint64_t first, uint64_t last, int page_mask) "is_ram=%d, is_iommu=%d, is_protected=%d, is_ram_device=%d iova_min=0x%"PRIx64" iova_last=0x%"PRIx64" page_mask=0x%x"
 vhost_vdpa_dma_map(void *vdpa, int fd, uint32_t msg_type, uint32_t asid, uint64_t iova, uint64_t size, uint64_t uaddr, uint8_t perm, uint8_t type) "vdpa_shared:%p fd: %d msg_type: %"PRIu32" asid: %"PRIu32" iova: 0x%"PRIx64" size: 0x%"PRIx64" uaddr: 0x%"PRIx64" perm: 0x%"PRIx8" type: %"PRIu8
 vhost_vdpa_dma_unmap(void *vdpa, int fd, uint32_t msg_type, uint32_t asid, uint64_t iova, uint64_t size, uint8_t type) "vdpa_shared:%p fd: %d msg_type: %"PRIu32" asid: %"PRIu32" iova: 0x%"PRIx64" size: 0x%"PRIx64" type: %"PRIu8
 vhost_vdpa_listener_begin_batch(void *v, int fd, uint32_t msg_type, uint8_t type)  "vdpa_shared:%p fd: %d msg_type: %"PRIu32" type: %"PRIu8
@@ -57,8 +58,8 @@ vhost_vdpa_dev_start(void *dev, bool started) "dev: %p started: %d"
 vhost_vdpa_set_log_base(void *dev, uint64_t base, unsigned long long size, int refcnt, int fd, void *log) "dev: %p base: 0x%"PRIx64" size: %llu refcnt: %d fd: %d log: %p"
 vhost_vdpa_set_vring_addr(void *dev, unsigned int index, unsigned int flags, uint64_t desc_user_addr, uint64_t used_user_addr, uint64_t avail_user_addr, uint64_t log_guest_addr) "dev: %p index: %u flags: 0x%x desc_user_addr: 0x%"PRIx64" used_user_addr: 0x%"PRIx64" avail_user_addr: 0x%"PRIx64" log_guest_addr: 0x%"PRIx64
 vhost_vdpa_set_vring_num(void *dev, unsigned int index, unsigned int num) "dev: %p index: %u num: %u"
-vhost_vdpa_set_vring_base(void *dev, unsigned int index, unsigned int num) "dev: %p index: %u num: %u"
-vhost_vdpa_get_vring_base(void *dev, unsigned int index, unsigned int num) "dev: %p index: %u num: %u"
+vhost_vdpa_set_dev_vring_base(void *dev, unsigned int index, unsigned int num, bool svq) "dev: %p index: %u num: %u svq: %d"
+vhost_vdpa_get_vring_base(void *dev, unsigned int index, unsigned int num, bool svq) "dev: %p index: %u num: %u svq: %d"
 vhost_vdpa_set_vring_kick(void *dev, unsigned int index, int fd) "dev: %p index: %u fd: %d"
 vhost_vdpa_set_vring_call(void *dev, unsigned int index, int fd) "dev: %p index: %u fd: %d"
 vhost_vdpa_get_features(void *dev, uint64_t features) "dev: %p features: 0x%"PRIx64
@@ -111,7 +112,7 @@ virtio_iommu_device_reset(void) "reset!"
 virtio_iommu_system_reset(void) "system reset!"
 virtio_iommu_get_features(uint64_t features) "device supports features=0x%"PRIx64
 virtio_iommu_device_status(uint8_t status) "driver status = %d"
-virtio_iommu_get_config(uint64_t page_size_mask, uint64_t start, uint64_t end, uint32_t domain_start, uint32_t domain_end, uint32_t probe_size, uint8_t bypass) "page_size_mask=0x%"PRIx64" input range start=0x%"PRIx64" input range end=0x%"PRIx64" domain range start=%d domain range end=%d probe_size=0x%x bypass=0x%x"
+virtio_iommu_get_config(uint64_t page_size_mask, uint64_t start, uint64_t end, uint32_t domain_start, uint32_t domain_end, uint32_t probe_size, uint8_t bypass) "page_size_mask=0x%"PRIx64" input range start=0x%"PRIx64" input range end=0x%"PRIx64" domain range start=%u domain range end=%u probe_size=0x%x bypass=0x%x"
 virtio_iommu_set_config(uint8_t bypass) "bypass=0x%x"
 virtio_iommu_attach(uint32_t domain_id, uint32_t ep_id) "domain=%d endpoint=%d"
 virtio_iommu_detach(uint32_t domain_id, uint32_t ep_id) "domain=%d endpoint=%d"
diff --git a/hw/virtio/vhost-user.c b/hw/virtio/vhost-user.c
index 1af8621481..cdf9af4a4b 100644
--- a/hw/virtio/vhost-user.c
+++ b/hw/virtio/vhost-user.c
@@ -1610,11 +1610,27 @@ vhost_user_backend_handle_shared_object_add(struct vhost_dev *dev,
 }
 
 static int
-vhost_user_backend_handle_shared_object_remove(VhostUserShared *object)
+vhost_user_backend_handle_shared_object_remove(struct vhost_dev *dev,
+                                               VhostUserShared *object)
 {
     QemuUUID uuid;
 
     memcpy(uuid.data, object->uuid, sizeof(object->uuid));
+    switch (virtio_object_type(&uuid)) {
+    case TYPE_VHOST_DEV:
+    {
+        struct vhost_dev *owner = virtio_lookup_vhost_device(&uuid);
+        if (dev != owner) {
+            /* Not allowed to remove non-owned entries */
+            return 0;
+        }
+        break;
+    }
+    default:
+        /* Not allowed to remove non-owned entries */
+        return 0;
+    }
+
     return virtio_remove_resource(&uuid);
 }
 
@@ -1793,7 +1809,8 @@ static gboolean backend_read(QIOChannel *ioc, GIOCondition condition,
         ret = vhost_user_backend_handle_shared_object_add(dev, &payload.object);
         break;
     case VHOST_USER_BACKEND_SHARED_OBJECT_REMOVE:
-        ret = vhost_user_backend_handle_shared_object_remove(&payload.object);
+        ret = vhost_user_backend_handle_shared_object_remove(dev,
+                                                             &payload.object);
         break;
     case VHOST_USER_BACKEND_SHARED_OBJECT_LOOKUP:
         ret = vhost_user_backend_handle_shared_object_lookup(dev->opaque, ioc,
diff --git a/hw/virtio/vhost-vdpa.c b/hw/virtio/vhost-vdpa.c
index ddae494ca8..3bcd05cc22 100644
--- a/hw/virtio/vhost-vdpa.c
+++ b/hw/virtio/vhost-vdpa.c
@@ -47,12 +47,17 @@ static bool vhost_vdpa_listener_skipped_section(MemoryRegionSection *section,
                                                 int page_mask)
 {
     Int128 llend;
+    bool is_ram = memory_region_is_ram(section->mr);
+    bool is_iommu = memory_region_is_iommu(section->mr);
+    bool is_protected = memory_region_is_protected(section->mr);
 
-    if ((!memory_region_is_ram(section->mr) &&
-         !memory_region_is_iommu(section->mr)) ||
-        memory_region_is_protected(section->mr) ||
-        /* vhost-vDPA doesn't allow MMIO to be mapped  */
-        memory_region_is_ram_device(section->mr)) {
+    /* vhost-vDPA doesn't allow MMIO to be mapped  */
+    bool is_ram_device = memory_region_is_ram_device(section->mr);
+
+    if ((!is_ram && !is_iommu) || is_protected || is_ram_device) {
+        trace_vhost_vdpa_skipped_memory_section(is_ram, is_iommu, is_protected,
+                                                is_ram_device, iova_min,
+                                                iova_max, page_mask);
         return true;
     }
 
@@ -69,7 +74,7 @@ static bool vhost_vdpa_listener_skipped_section(MemoryRegionSection *section,
      * size that maps to the kernel
      */
 
-    if (!memory_region_is_iommu(section->mr)) {
+    if (!is_iommu) {
         llend = vhost_vdpa_section_end(section, page_mask);
         if (int128_gt(llend, int128_make64(iova_max))) {
             error_report("RAM section out of device range (max=0x%" PRIx64
@@ -555,6 +560,11 @@ static bool vhost_vdpa_first_dev(struct vhost_dev *dev)
     return v->index == 0;
 }
 
+static bool vhost_vdpa_last_dev(struct vhost_dev *dev)
+{
+    return dev->vq_index + dev->nvqs == dev->vq_index_end;
+}
+
 static int vhost_vdpa_get_dev_features(struct vhost_dev *dev,
                                        uint64_t *features)
 {
@@ -965,7 +975,10 @@ static int vhost_vdpa_get_config(struct vhost_dev *dev, uint8_t *config,
 static int vhost_vdpa_set_dev_vring_base(struct vhost_dev *dev,
                                          struct vhost_vring_state *ring)
 {
-    trace_vhost_vdpa_set_vring_base(dev, ring->index, ring->num);
+    struct vhost_vdpa *v = dev->opaque;
+
+    trace_vhost_vdpa_set_dev_vring_base(dev, ring->index, ring->num,
+                                        v->shadow_vqs_enabled);
     return vhost_vdpa_call(dev, VHOST_SET_VRING_BASE, ring);
 }
 
@@ -1315,7 +1328,7 @@ static int vhost_vdpa_dev_start(struct vhost_dev *dev, bool started)
         vhost_vdpa_host_notifiers_uninit(dev, dev->nvqs);
     }
 
-    if (dev->vq_index + dev->nvqs != dev->vq_index_end) {
+    if (!vhost_vdpa_last_dev(dev)) {
         return 0;
     }
 
@@ -1337,7 +1350,7 @@ static void vhost_vdpa_reset_status(struct vhost_dev *dev)
 {
     struct vhost_vdpa *v = dev->opaque;
 
-    if (dev->vq_index + dev->nvqs != dev->vq_index_end) {
+    if (!vhost_vdpa_last_dev(dev)) {
         return;
     }
 
@@ -1407,6 +1420,7 @@ static int vhost_vdpa_get_vring_base(struct vhost_dev *dev,
 
     if (v->shadow_vqs_enabled) {
         ring->num = virtio_queue_get_last_avail_idx(dev->vdev, ring->index);
+        trace_vhost_vdpa_get_vring_base(dev, ring->index, ring->num, true);
         return 0;
     }
 
@@ -1419,7 +1433,7 @@ static int vhost_vdpa_get_vring_base(struct vhost_dev *dev,
     }
 
     ret = vhost_vdpa_call(dev, VHOST_GET_VRING_BASE, ring);
-    trace_vhost_vdpa_get_vring_base(dev, ring->index, ring->num);
+    trace_vhost_vdpa_get_vring_base(dev, ring->index, ring->num, false);
     return ret;
 }
 
@@ -1447,7 +1461,15 @@ static int vhost_vdpa_set_vring_call(struct vhost_dev *dev,
 
     /* Remember last call fd because we can switch to SVQ anytime. */
     vhost_svq_set_svq_call_fd(svq, file->fd);
-    if (v->shadow_vqs_enabled) {
+    /*
+     * When SVQ is transitioning to off, shadow_vqs_enabled has
+     * not been set back to false yet, but the underlying call fd
+     * will have to switch back to the guest notifier to signal the
+     * passthrough virtqueues. In other situations, SVQ's own call
+     * fd shall be used to signal the device model.
+     */
+    if (v->shadow_vqs_enabled &&
+        v->shared->svq_switching != SVQ_TSTATE_DISABLING) {
         return 0;
     }
 
diff --git a/hw/virtio/virtio-iommu.c b/hw/virtio/virtio-iommu.c
index 86623d55a5..1326c6ec41 100644
--- a/hw/virtio/virtio-iommu.c
+++ b/hw/virtio/virtio-iommu.c
@@ -29,6 +29,7 @@
 #include "sysemu/reset.h"
 #include "sysemu/sysemu.h"
 #include "qemu/reserved-region.h"
+#include "qemu/units.h"
 #include "qapi/error.h"
 #include "qemu/error-report.h"
 #include "trace.h"
@@ -1115,8 +1116,8 @@ static int virtio_iommu_notify_flag_changed(IOMMUMemoryRegion *iommu_mr,
 }
 
 /*
- * The default mask (TARGET_PAGE_MASK) is the smallest supported guest granule,
- * for example 0xfffffffffffff000. When an assigned device has page size
+ * The default mask depends on the "granule" property. For example, with
+ * 4k granule, it is -(4 * KiB). When an assigned device has page size
  * restrictions due to the hardware IOMMU configuration, apply this restriction
  * to the mask.
  */
@@ -1313,8 +1314,32 @@ static void virtio_iommu_device_realize(DeviceState *dev, Error **errp)
      * in vfio realize
      */
     s->config.bypass = s->boot_bypass;
-    s->config.page_size_mask = qemu_target_page_mask();
-    s->config.input_range.end = UINT64_MAX;
+    if (s->aw_bits < 32 || s->aw_bits > 64) {
+        error_setg(errp, "aw-bits must be within [32,64]");
+        return;
+    }
+    s->config.input_range.end =
+        s->aw_bits == 64 ? UINT64_MAX : BIT_ULL(s->aw_bits) - 1;
+
+    switch (s->granule_mode) {
+    case GRANULE_MODE_4K:
+        s->config.page_size_mask = -(4 * KiB);
+        break;
+    case GRANULE_MODE_8K:
+        s->config.page_size_mask = -(8 * KiB);
+        break;
+    case GRANULE_MODE_16K:
+        s->config.page_size_mask = -(16 * KiB);
+        break;
+    case GRANULE_MODE_64K:
+        s->config.page_size_mask = -(64 * KiB);
+        break;
+    case GRANULE_MODE_HOST:
+        s->config.page_size_mask = qemu_real_host_page_mask();
+        break;
+    default:
+        error_setg(errp, "Unsupported granule mode");
+    }
     s->config.domain_range.end = UINT32_MAX;
     s->config.probe_size = VIOMMU_PROBE_SIZE;
 
@@ -1522,6 +1547,9 @@ static Property virtio_iommu_properties[] = {
     DEFINE_PROP_LINK("primary-bus", VirtIOIOMMU, primary_bus,
                      TYPE_PCI_BUS, PCIBus *),
     DEFINE_PROP_BOOL("boot-bypass", VirtIOIOMMU, boot_bypass, true),
+    DEFINE_PROP_GRANULE_MODE("granule", VirtIOIOMMU, granule_mode,
+                             GRANULE_MODE_HOST),
+    DEFINE_PROP_UINT8("aw-bits", VirtIOIOMMU, aw_bits, 64),
     DEFINE_PROP_END_OF_LIST(),
 };
 
diff --git a/hw/virtio/virtio-pci.c b/hw/virtio/virtio-pci.c
index cb6940fc0e..eaaf86402c 100644
--- a/hw/virtio/virtio-pci.c
+++ b/hw/virtio/virtio-pci.c
@@ -1442,6 +1442,155 @@ int virtio_pci_add_shm_cap(VirtIOPCIProxy *proxy,
     return virtio_pci_add_mem_cap(proxy, &cap.cap);
 }
 
+/* Called within call_rcu().  */
+static void bitmap_free_region_cache(BitmapMemoryRegionCaches *caches)
+{
+    assert(caches != NULL);
+    address_space_cache_destroy(&caches->bitmap);
+    g_free(caches);
+}
+
+static void lm_disable(VirtIODevice *vdev)
+{
+    BitmapMemoryRegionCaches *caches;
+    caches = qatomic_read(&vdev->caches);
+    qatomic_rcu_set(&vdev->caches, NULL);
+    if (caches) {
+        call_rcu(caches, bitmap_free_region_cache, rcu);
+    }
+}
+
+static void lm_enable(VirtIODevice *vdev)
+{
+    BitmapMemoryRegionCaches *old = vdev->caches;
+    BitmapMemoryRegionCaches *new = NULL;
+    hwaddr addr, end, size;
+    int64_t len;
+
+    addr = vdev->lm_base_addr_low | ((hwaddr)(vdev->lm_base_addr_high) << 32);
+    end = vdev->lm_end_addr_low | ((hwaddr)(vdev->lm_end_addr_high) << 32);
+    size = end - addr;
+    if (size <= 0) {
+        error_report("Invalid lm size.");
+        return;
+    }
+
+    new = g_new0(BitmapMemoryRegionCaches, 1);
+    len = address_space_cache_init(&new->bitmap, vdev->dma_as, addr, size,
+                                   true);
+    if (len < size) {
+        virtio_error(vdev, "Cannot map bitmap");
+        goto err_bitmap;
+    }
+    qatomic_rcu_set(&vdev->caches, new);
+
+    if (old) {
+        call_rcu(old, bitmap_free_region_cache, rcu);
+    }
+
+    return;
+
+err_bitmap:
+    address_space_cache_destroy(&new->bitmap);
+    g_free(new);
+}
+
+static uint64_t virtio_pci_lm_read(void *opaque, hwaddr addr,
+                                       unsigned size)
+{
+    VirtIOPCIProxy *proxy = opaque;
+    VirtIODevice *vdev = virtio_bus_get_device(&proxy->bus);
+    hwaddr offset_end = LM_VRING_STATE_OFFSET +
+                        virtio_pci_queue_mem_mult(proxy) * VIRTIO_QUEUE_MAX;
+    uint32_t val;
+    int qid;
+
+    if (vdev == NULL) {
+        return UINT64_MAX;
+    }
+    switch (addr) {
+    case LM_LOGGING_CTRL:
+        val = vdev->lm_logging_ctrl;
+        break;
+    case LM_BASE_ADDR_LOW:
+        val = vdev->lm_base_addr_low;
+        break;
+    case LM_BASE_ADDR_HIGH:
+        val = vdev->lm_base_addr_high;
+        break;
+    case LM_END_ADDR_LOW:
+        val = vdev->lm_end_addr_low;
+        break;
+    case LM_END_ADDR_HIGH:
+        val = vdev->lm_end_addr_high;
+        break;
+    default:
+        if (addr >= LM_VRING_STATE_OFFSET && addr <= offset_end) {
+            qid = (addr - LM_VRING_STATE_OFFSET) /
+                  virtio_pci_queue_mem_mult(proxy);
+            val = virtio_queue_get_vring_states(vdev, qid);
+        } else
+            val = 0;
+
+        break;
+    }
+
+    return val;
+}
+
+static void virtio_pci_lm_write(void *opaque, hwaddr addr,
+                                    uint64_t val, unsigned size)
+{
+    VirtIOPCIProxy *proxy = opaque;
+    VirtIODevice *vdev = virtio_bus_get_device(&proxy->bus);
+    hwaddr offset_end = LM_VRING_STATE_OFFSET +
+                        virtio_pci_queue_mem_mult(proxy) * VIRTIO_QUEUE_MAX;
+    int qid;
+
+    if (vdev == NULL) {
+        return;
+    }
+
+    switch (addr) {
+    case LM_LOGGING_CTRL:
+        vdev->lm_logging_ctrl = val;
+        switch (val) {
+        case LM_DISABLE:
+            lm_disable(vdev);
+            break;
+        case LM_ENABLE:
+            lm_enable(vdev);
+            break;
+        default:
+            virtio_error(vdev, "Unsupport LM_LOGGING_CTRL value: %"PRIx64,
+                         val);
+                break;
+        };
+
+        break;
+    case LM_BASE_ADDR_LOW:
+        vdev->lm_base_addr_low = val;
+        break;
+    case LM_BASE_ADDR_HIGH:
+        vdev->lm_base_addr_high = val;
+        break;
+    case LM_END_ADDR_LOW:
+        vdev->lm_end_addr_low = val;
+        break;
+    case LM_END_ADDR_HIGH:
+        vdev->lm_end_addr_high = val;
+        break;
+    default:
+        if (addr >= LM_VRING_STATE_OFFSET && addr <= offset_end) {
+            qid = (addr - LM_VRING_STATE_OFFSET) /
+                  virtio_pci_queue_mem_mult(proxy);
+            virtio_queue_set_vring_states(vdev, qid, val);
+        } else
+            virtio_error(vdev, "Unsupport addr: %"PRIx64, addr);
+        break;
+    }
+}
+
 static uint64_t virtio_pci_common_read(void *opaque, hwaddr addr,
                                        unsigned size)
 {
@@ -1823,6 +1972,15 @@ static void virtio_pci_modern_regions_init(VirtIOPCIProxy *proxy,
         },
         .endianness = DEVICE_LITTLE_ENDIAN,
     };
+    static const MemoryRegionOps lm_ops = {
+        .read = virtio_pci_lm_read,
+        .write = virtio_pci_lm_write,
+        .impl = {
+            .min_access_size = 1,
+            .max_access_size = 4,
+        },
+        .endianness = DEVICE_LITTLE_ENDIAN,
+    };
     g_autoptr(GString) name = g_string_new(NULL);
 
     g_string_printf(name, "virtio-pci-common-%s", vdev_name);
@@ -1859,6 +2017,14 @@ static void virtio_pci_modern_regions_init(VirtIOPCIProxy *proxy,
                           proxy,
                           name->str,
                           proxy->notify_pio.size);
+    if (proxy->flags & VIRTIO_PCI_FLAG_VDPA) {
+        g_string_printf(name, "virtio-pci-lm-%s", vdev_name);
+        memory_region_init_io(&proxy->lm.mr, OBJECT(proxy),
+                          &lm_ops,
+                          proxy,
+                          name->str,
+                          proxy->lm.size);
+    }
 }
 
 static void virtio_pci_modern_region_map(VirtIOPCIProxy *proxy,
@@ -2021,6 +2187,10 @@ static void virtio_pci_device_plugged(DeviceState *d, Error **errp)
         virtio_pci_modern_mem_region_map(proxy, &proxy->isr, &cap);
         virtio_pci_modern_mem_region_map(proxy, &proxy->device, &cap);
         virtio_pci_modern_mem_region_map(proxy, &proxy->notify, &notify.cap);
+        if (proxy->flags & VIRTIO_PCI_FLAG_VDPA) {
+            memory_region_add_subregion(&proxy->modern_bar,
+                                        proxy->lm.offset, &proxy->lm.mr);
+        }
 
         if (modern_pio) {
             memory_region_init(&proxy->io_bar, OBJECT(proxy),
@@ -2090,6 +2260,9 @@ static void virtio_pci_device_unplugged(DeviceState *d)
         virtio_pci_modern_mem_region_unmap(proxy, &proxy->isr);
         virtio_pci_modern_mem_region_unmap(proxy, &proxy->device);
         virtio_pci_modern_mem_region_unmap(proxy, &proxy->notify);
+        if (proxy->flags & VIRTIO_PCI_FLAG_VDPA) {
+            memory_region_del_subregion(&proxy->modern_bar, &proxy->lm.mr);
+        }
         if (modern_pio) {
             virtio_pci_modern_io_region_unmap(proxy, &proxy->notify_pio);
         }
@@ -2144,9 +2317,17 @@ static void virtio_pci_realize(PCIDevice *pci_dev, Error **errp)
     proxy->notify_pio.type = VIRTIO_PCI_CAP_NOTIFY_CFG;
 
     /* subclasses can enforce modern, so do this unconditionally */
-    memory_region_init(&proxy->modern_bar, OBJECT(proxy), "virtio-pci",
-                       /* PCI BAR regions must be powers of 2 */
-                       pow2ceil(proxy->notify.offset + proxy->notify.size));
+    if (!(proxy->flags & VIRTIO_PCI_FLAG_VDPA)) {
+        memory_region_init(&proxy->modern_bar, OBJECT(proxy), "virtio-pci",
+                           /* PCI BAR regions must be powers of 2 */
+                           pow2ceil(proxy->notify.offset + proxy->notify.size));
+    } else {
+        proxy->lm.offset = proxy->notify.offset + proxy->notify.size;
+        proxy->lm.size = 0x20 + VIRTIO_QUEUE_MAX * 4;
+        memory_region_init(&proxy->modern_bar, OBJECT(proxy), "virtio-pci",
+                           /* PCI BAR regions must be powers of 2 */
+                           pow2ceil(proxy->lm.offset + proxy->lm.size));
+    }
 
     if (proxy->disable_legacy == ON_OFF_AUTO_AUTO) {
         proxy->disable_legacy = pcie_port ? ON_OFF_AUTO_ON : ON_OFF_AUTO_OFF;
@@ -2301,6 +2482,8 @@ static Property virtio_pci_properties[] = {
                     VIRTIO_PCI_FLAG_INIT_FLR_BIT, true),
     DEFINE_PROP_BIT("aer", VirtIOPCIProxy, flags,
                     VIRTIO_PCI_FLAG_AER_BIT, false),
+    DEFINE_PROP_BIT("vdpa", VirtIOPCIProxy, flags,
+                    VIRTIO_PCI_FLAG_VDPA_BIT, false),
     DEFINE_PROP_END_OF_LIST(),
 };
 
diff --git a/hw/virtio/virtio.c b/hw/virtio/virtio.c
index d229755eae..fb6b4ccd83 100644
--- a/hw/virtio/virtio.c
+++ b/hw/virtio/virtio.c
@@ -3368,6 +3368,18 @@ static uint16_t virtio_queue_split_get_last_avail_idx(VirtIODevice *vdev,
     return vdev->vq[n].last_avail_idx;
 }
 
+static uint32_t virtio_queue_split_get_vring_states(VirtIODevice *vdev,
+                                                      int n)
+{
+    struct VirtQueue *vq = &vdev->vq[n];
+    uint16_t avail, used;
+
+    avail = vq->last_avail_idx;
+    used = vq->used_idx;
+
+    return avail | (uint32_t)used << 16;
+}
+
 unsigned int virtio_queue_get_last_avail_idx(VirtIODevice *vdev, int n)
 {
     if (virtio_vdev_has_feature(vdev, VIRTIO_F_RING_PACKED)) {
@@ -3377,6 +3389,33 @@ unsigned int virtio_queue_get_last_avail_idx(VirtIODevice *vdev, int n)
     }
 }
 
+unsigned int virtio_queue_get_vring_states(VirtIODevice *vdev, int n)
+{
+    if (virtio_vdev_has_feature(vdev, VIRTIO_F_RING_PACKED)) {
+        return -1;
+    } else {
+        return virtio_queue_split_get_vring_states(vdev, n);
+    }
+}
+
+static void virtio_queue_split_set_vring_states(VirtIODevice *vdev,
+                                                int n, uint32_t idx)
+{
+    struct VirtQueue *vq = &vdev->vq[n];
+    vq->last_avail_idx = (uint16_t)(idx & 0xffff);
+    vq->shadow_avail_idx = (uint16_t)(idx & 0xffff);
+    vq->used_idx = (uint16_t)(idx >> 16);
+}
+
+void virtio_queue_set_vring_states(VirtIODevice *vdev, int n, uint32_t idx)
+{
+    if (virtio_vdev_has_feature(vdev, VIRTIO_F_RING_PACKED)) {
+        return;
+    } else {
+        virtio_queue_split_set_vring_states(vdev, n, idx);
+    }
+}
+
 static void virtio_queue_packed_set_last_avail_idx(VirtIODevice *vdev,
                                                    int n, unsigned int idx)
 {