virtio: features,fixes

A bunch of improvements:
 - vhost dirty log is now only scanned once, not once per device
 - virtio and vhost now support VIRTIO_F_NOTIFICATION_DATA
 - cxl gained DCD emulation support
 - pvpanic gained shutdown support
 - beginning of patchset for Generic Port Affinity Structure
 - s3 support
 - friendlier error messages when boot fails on some illegal configs
 - for vhost-user, VHOST_USER_SET_LOG_BASE is now only sent once
 - part of vhost-user support for any POSIX system -
   not yet enabled due to qtest failures
 - sr-iov VF setup code has been reworked significantly
 - new tests, particularly for risc-v ACPI
 - bugfixes
 
 Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
 -----BEGIN PGP SIGNATURE-----
 
 iQFDBAABCAAtFiEEXQn9CHHI+FuUyooNKB8NuNKNVGkFAmaF068PHG1zdEByZWRo
 YXQuY29tAAoJECgfDbjSjVRp+DMIAMC//mBXIZlPprfhb5cuZklxYi31Acgu5TUr
 njqjCkN+mFhXXZuc3B67xmrQ066IEPtsbzCjSnzuU41YK4tjvO1g+LgYJBv41G16
 va2k8vFM5pdvRA+UC9li1CCIPxiEcszxOdzZemj3szWLVLLUmwsc5OZLWWeFA5m8
 vXrrT9miODUz3z8/Xn/TVpxnmD6glKYIRK/IJRzzC4Qqqwb5H3ji/BJV27cDUtdC
 w6ns5RYIj5j4uAiG8wQNDggA1bMsTxFxThRDUwxlxaIwAcexrf1oRnxGRePA7PVG
 BXrt5yodrZYR2sR6svmOOIF3wPMUDKdlAItTcEgYyxaVo5rAdpc=
 =p9h4
 -----END PGP SIGNATURE-----

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

virtio: features,fixes

A bunch of improvements:
- vhost dirty log is now only scanned once, not once per device
- virtio and vhost now support VIRTIO_F_NOTIFICATION_DATA
- cxl gained DCD emulation support
- pvpanic gained shutdown support
- beginning of patchset for Generic Port Affinity Structure
- s3 support
- friendlier error messages when boot fails on some illegal configs
- for vhost-user, VHOST_USER_SET_LOG_BASE is now only sent once
- part of vhost-user support for any POSIX system -
  not yet enabled due to qtest failures
- sr-iov VF setup code has been reworked significantly
- new tests, particularly for risc-v ACPI
- bugfixes

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

# -----BEGIN PGP SIGNATURE-----
#
# iQFDBAABCAAtFiEEXQn9CHHI+FuUyooNKB8NuNKNVGkFAmaF068PHG1zdEByZWRo
# YXQuY29tAAoJECgfDbjSjVRp+DMIAMC//mBXIZlPprfhb5cuZklxYi31Acgu5TUr
# njqjCkN+mFhXXZuc3B67xmrQ066IEPtsbzCjSnzuU41YK4tjvO1g+LgYJBv41G16
# va2k8vFM5pdvRA+UC9li1CCIPxiEcszxOdzZemj3szWLVLLUmwsc5OZLWWeFA5m8
# vXrrT9miODUz3z8/Xn/TVpxnmD6glKYIRK/IJRzzC4Qqqwb5H3ji/BJV27cDUtdC
# w6ns5RYIj5j4uAiG8wQNDggA1bMsTxFxThRDUwxlxaIwAcexrf1oRnxGRePA7PVG
# BXrt5yodrZYR2sR6svmOOIF3wPMUDKdlAItTcEgYyxaVo5rAdpc=
# =p9h4
# -----END PGP SIGNATURE-----
# gpg: Signature made Wed 03 Jul 2024 03:41:51 PM PDT
# gpg:                using RSA key 5D09FD0871C8F85B94CA8A0D281F0DB8D28D5469
# gpg:                issuer "mst@redhat.com"
# gpg: Good signature from "Michael S. Tsirkin <mst@kernel.org>" [undefined]
# gpg:                 aka "Michael S. Tsirkin <mst@redhat.com>" [undefined]
# gpg: WARNING: This key is not certified with a trusted signature!
# gpg:          There is no indication that the signature belongs to the owner.
# 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: (85 commits)
  hw/pci: Replace -1 with UINT32_MAX for romsize
  pcie_sriov: Register VFs after migration
  pcie_sriov: Remove num_vfs from PCIESriovPF
  pcie_sriov: Release VFs failed to realize
  pcie_sriov: Reuse SR-IOV VF device instances
  pcie_sriov: Ensure VF function number does not overflow
  pcie_sriov: Do not manually unrealize
  hw/ppc/spapr_pci: Do not reject VFs created after a PF
  hw/ppc/spapr_pci: Do not create DT for disabled PCI device
  hw/pci: Rename has_power to enabled
  virtio-iommu: Clear IOMMUDevice when VFIO device is unplugged
  virtio: remove virtio_tswap16s() call in vring_packed_event_read()
  hw/cxl/events: Mark cxl-add-dynamic-capacity and cxl-release-dynamic-capcity unstable
  hw/cxl/events: Improve QMP interfaces and documentation for add/release dynamic capacity.
  tests/data/acpi/rebuild-expected-aml.sh: Add RISC-V
  pc-bios/meson.build: Add support for RISC-V in unpack_edk2_blobs
  meson.build: Add RISC-V to the edk2-target list
  tests/data/acpi/virt: Move ARM64 ACPI tables under aarch64/${machine} path
  tests/data/acpi: Move x86 ACPI tables under x86/${machine} path
  tests/qtest/bios-tables-test.c: Set "arch" for x86 tests
  ...

Signed-off-by: Richard Henderson <richard.henderson@linaro.org>

backends/hostmem-shm.c

@@ -0,0 +1,123 @@
+/*
+ * QEMU host POSIX shared memory object backend
+ *
+ * Copyright (C) 2024 Red Hat Inc
+ *
+ * Authors:
+ *   Stefano Garzarella <sgarzare@redhat.com>
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2 or later.
+ * See the COPYING file in the top-level directory.
+ */
+
+#include "qemu/osdep.h"
+#include "sysemu/hostmem.h"
+#include "qapi/error.h"
+
+#define TYPE_MEMORY_BACKEND_SHM "memory-backend-shm"
+
+OBJECT_DECLARE_SIMPLE_TYPE(HostMemoryBackendShm, MEMORY_BACKEND_SHM)
+
+struct HostMemoryBackendShm {
+    HostMemoryBackend parent_obj;
+};
+
+static bool
+shm_backend_memory_alloc(HostMemoryBackend *backend, Error **errp)
+{
+    g_autoptr(GString) shm_name = g_string_new(NULL);
+    g_autofree char *backend_name = NULL;
+    uint32_t ram_flags;
+    int fd, oflag;
+    mode_t mode;
+
+    if (!backend->size) {
+        error_setg(errp, "can't create shm backend with size 0");
+        return false;
+    }
+
+    if (!backend->share) {
+        error_setg(errp, "can't create shm backend with `share=off`");
+        return false;
+    }
+
+    /*
+     * Let's use `mode = 0` because we don't want other processes to open our
+     * memory unless we share the file descriptor with them.
+     */
+    mode = 0;
+    oflag = O_RDWR | O_CREAT | O_EXCL;
+    backend_name = host_memory_backend_get_name(backend);
+
+    /*
+     * Some operating systems allow creating anonymous POSIX shared memory
+     * objects (e.g. FreeBSD provides the SHM_ANON constant), but this is not
+     * defined by POSIX, so let's create a unique name.
+     *
+     * From Linux's shm_open(3) man-page:
+     *   For  portable  use,  a shared  memory  object should be identified
+     *   by a name of the form /somename;"
+     */
+    g_string_printf(shm_name, "/qemu-" FMT_pid "-shm-%s", getpid(),
+                    backend_name);
+
+    fd = shm_open(shm_name->str, oflag, mode);
+    if (fd < 0) {
+        error_setg_errno(errp, errno,
+                         "failed to create POSIX shared memory");
+        return false;
+    }
+
+    /*
+     * We have the file descriptor, so we no longer need to expose the
+     * POSIX shared memory object. However it will remain allocated as long as
+     * there are file descriptors pointing to it.
+     */
+    shm_unlink(shm_name->str);
+
+    if (ftruncate(fd, backend->size) == -1) {
+        error_setg_errno(errp, errno,
+                         "failed to resize POSIX shared memory to %" PRIu64,
+                         backend->size);
+        close(fd);
+        return false;
+    }
+
+    ram_flags = RAM_SHARED;
+    ram_flags |= backend->reserve ? 0 : RAM_NORESERVE;
+
+    return memory_region_init_ram_from_fd(&backend->mr, OBJECT(backend),
+                                              backend_name, backend->size,
+                                              ram_flags, fd, 0, errp);
+}
+
+static void
+shm_backend_instance_init(Object *obj)
+{
+    HostMemoryBackendShm *m = MEMORY_BACKEND_SHM(obj);
+
+    MEMORY_BACKEND(m)->share = true;
+}
+
+static void
+shm_backend_class_init(ObjectClass *oc, void *data)
+{
+    HostMemoryBackendClass *bc = MEMORY_BACKEND_CLASS(oc);
+
+    bc->alloc = shm_backend_memory_alloc;
+}
+
+static const TypeInfo shm_backend_info = {
+    .name = TYPE_MEMORY_BACKEND_SHM,
+    .parent = TYPE_MEMORY_BACKEND,
+    .instance_init = shm_backend_instance_init,
+    .class_init = shm_backend_class_init,
+    .instance_size = sizeof(HostMemoryBackendShm),
+};
+
+static void register_types(void)
+{
+    type_register_static(&shm_backend_info);
+}
+
+type_init(register_types);

backends/meson.build

@@ -13,6 +13,7 @@ system_ss.add([files(
 if host_os != 'windows'
   system_ss.add(files('rng-random.c'))
   system_ss.add(files('hostmem-file.c'))
+  system_ss.add([files('hostmem-shm.c'), rt])
 endif
 if host_os == 'linux'
   system_ss.add(files('hostmem-memfd.c'))

contrib/vhost-user-blk/vhost-user-blk.c

@@ -16,6 +16,7 @@
  */
 
 #include "qemu/osdep.h"
+#include "qemu/bswap.h"
 #include "standard-headers/linux/virtio_blk.h"
 #include "libvhost-user-glib.h"
 
@@ -194,8 +195,8 @@ vub_discard_write_zeroes(VubReq *req, struct iovec *iov, uint32_t iovcnt,
     #if defined(__linux__) && defined(BLKDISCARD) && defined(BLKZEROOUT)
     VubDev *vdev_blk = req->vdev_blk;
     desc = buf;
-    uint64_t range[2] = { le64toh(desc->sector) << 9,
+    uint64_t range[2] = { le64_to_cpu(desc->sector) << 9,
-                          le32toh(desc->num_sectors) << 9 };
+                          le32_to_cpu(desc->num_sectors) << 9 };
     if (type == VIRTIO_BLK_T_DISCARD) {
         if (ioctl(vdev_blk->blk_fd, BLKDISCARD, range) == 0) {
             g_free(buf);
@@ -267,13 +268,13 @@ static int vub_virtio_process_req(VubDev *vdev_blk,
     req->in = (struct virtio_blk_inhdr *)elem->in_sg[in_num - 1].iov_base;
     in_num--;
 
-    type = le32toh(req->out->type);
+    type = le32_to_cpu(req->out->type);
     switch (type & ~VIRTIO_BLK_T_BARRIER) {
     case VIRTIO_BLK_T_IN:
     case VIRTIO_BLK_T_OUT: {
         ssize_t ret = 0;
         bool is_write = type & VIRTIO_BLK_T_OUT;
-        req->sector_num = le64toh(req->out->sector);
+        req->sector_num = le64_to_cpu(req->out->sector);
         if (is_write) {
             ret  = vub_writev(req, &elem->out_sg[1], out_num);
         } else {
@@ -469,7 +470,6 @@ static int unix_sock_new(char *unix_fn)
 {
     int sock;
     struct sockaddr_un un;
-    size_t len;
 
     assert(unix_fn);
 
@@ -481,10 +481,9 @@ static int unix_sock_new(char *unix_fn)
 
     un.sun_family = AF_UNIX;
     (void)snprintf(un.sun_path, sizeof(un.sun_path), "%s", unix_fn);
-    len = sizeof(un.sun_family) + strlen(un.sun_path);
 
     (void)unlink(unix_fn);
-    if (bind(sock, (struct sockaddr *)&un, len) < 0) {
+    if (bind(sock, (struct sockaddr *)&un, sizeof(un)) < 0) {
         perror("bind");
         goto fail;
     }

contrib/vhost-user-input/main.c

@@ -51,8 +51,8 @@ static void vi_input_send(VuInput *vi, struct virtio_input_event *event)
     vi->queue[vi->qindex++].event = *event;
 
     /* ... until we see a report sync ... */
-    if (event->type != htole16(EV_SYN) ||
+    if (event->type != cpu_to_le16(EV_SYN) ||
-        event->code != htole16(SYN_REPORT)) {
+        event->code != cpu_to_le16(SYN_REPORT)) {
         return;
     }
 
@@ -103,9 +103,9 @@ vi_evdev_watch(VuDev *dev, int condition, void *data)
 
         g_debug("input %d %d %d", evdev.type, evdev.code, evdev.value);
 
-        virtio.type  = htole16(evdev.type);
+        virtio.type  = cpu_to_le16(evdev.type);
-        virtio.code  = htole16(evdev.code);
+        virtio.code  = cpu_to_le16(evdev.code);
-        virtio.value = htole32(evdev.value);
+        virtio.value = cpu_to_le32(evdev.value);
         vi_input_send(vi, &virtio);
     }
 }
@@ -124,9 +124,9 @@ static void vi_handle_status(VuInput *vi, virtio_input_event *event)
 
     evdev.input_event_sec = tval.tv_sec;
     evdev.input_event_usec = tval.tv_usec;
-    evdev.type = le16toh(event->type);
+    evdev.type = le16_to_cpu(event->type);
-    evdev.code = le16toh(event->code);
+    evdev.code = le16_to_cpu(event->code);
-    evdev.value = le32toh(event->value);
+    evdev.value = le32_to_cpu(event->value);
 
     rc = write(vi->evdevfd, &evdev, sizeof(evdev));
     if (rc == -1) {

docs/pcie_sriov.txt

@@ -52,9 +52,11 @@ setting up a BAR for a VF.
       ...
 
       /* Add and initialize the SR/IOV capability */
-      pcie_sriov_pf_init(d, 0x200, "your_virtual_dev",
+      if (!pcie_sriov_pf_init(d, 0x200, "your_virtual_dev",
-                       vf_devid, initial_vfs, total_vfs,
+                              vf_devid, initial_vfs, total_vfs,
-                       fun_offset, stride);
+                              fun_offset, stride, errp)) {
+         return;
+      }
 
       /* Set up individual VF BARs (parameters as for normal BARs) */
       pcie_sriov_pf_init_vf_bar( ... )

docs/specs/pvpanic.rst

@@ -29,7 +29,7 @@ bit 1
   a guest panic has happened and will be handled by the guest;
   the host should record it or report it, but should not affect
   the execution of the guest.
-bit 2 (to be implemented)
+bit 2
   a regular guest shutdown has happened and should be processed by the host
 
 PCI Interface

docs/system/devices/vhost-user.rst

@@ -98,8 +98,9 @@ Shared memory object
 
 In order for the daemon to access the VirtIO queues to process the
 requests it needs access to the guest's address space. This is
-achieved via the ``memory-backend-file`` or ``memory-backend-memfd``
+achieved via the ``memory-backend-file``, ``memory-backend-memfd``, or
-objects. A reference to a file-descriptor which can access this object
+``memory-backend-shm`` objects.
+A reference to a file-descriptor which can access this object
 will be passed via the socket as part of the protocol negotiation.
 
 Currently the shared memory object needs to match the size of the main

hw/arm/virt-acpi-build.c

@@ -209,12 +209,19 @@ static void acpi_dsdt_add_tpm(Aml *scope, VirtMachineState *vms)
 #define ROOT_COMPLEX_ENTRY_SIZE 36
 #define IORT_NODE_OFFSET 48
 
+/*
+ * Append an ID mapping entry as described by "Table 4 ID mapping format" in
+ * "IO Remapping Table System Software on ARM Platforms", Chapter 3.
+ * Document number: ARM DEN 0049E.f, Apr 2024
+ *
+ * Note that @id_count gets internally subtracted by one, following the spec.
+ */
 static void build_iort_id_mapping(GArray *table_data, uint32_t input_base,
                                   uint32_t id_count, uint32_t out_ref)
 {
-    /* Table 4 ID mapping format */
     build_append_int_noprefix(table_data, input_base, 4); /* Input base */
-    build_append_int_noprefix(table_data, id_count, 4); /* Number of IDs */
+    /* Number of IDs - The number of IDs in the range minus one */
+    build_append_int_noprefix(table_data, id_count - 1, 4);
     build_append_int_noprefix(table_data, input_base, 4); /* Output base */
     build_append_int_noprefix(table_data, out_ref, 4); /* Output Reference */
     /* Flags */
@@ -269,7 +276,6 @@ static void
 build_iort(GArray *table_data, BIOSLinker *linker, VirtMachineState *vms)
 {
     int i, nb_nodes, rc_mapping_count;
-    const uint32_t iort_node_offset = IORT_NODE_OFFSET;
     size_t node_size, smmu_offset = 0;
     AcpiIortIdMapping *idmap;
     uint32_t id = 0;
@@ -306,8 +312,8 @@ build_iort(GArray *table_data, BIOSLinker *linker, VirtMachineState *vms)
         }
 
         /* Append the last RC -> ITS ID mapping */
-        if (next_range.input_base < 0xFFFF) {
+        if (next_range.input_base < 0x10000) {
-            next_range.id_count = 0xFFFF - next_range.input_base;
+            next_range.id_count = 0x10000 - next_range.input_base;
             g_array_append_val(its_idmaps, next_range);
         }
 
@@ -366,7 +372,7 @@ build_iort(GArray *table_data, BIOSLinker *linker, VirtMachineState *vms)
         build_append_int_noprefix(table_data, 0, 4);
 
         /* output IORT node is the ITS group node (the first node) */
-        build_iort_id_mapping(table_data, 0, 0xFFFF, IORT_NODE_OFFSET);
+        build_iort_id_mapping(table_data, 0, 0x10000, IORT_NODE_OFFSET);
     }
 
     /* Table 17 Root Complex Node */
@@ -415,11 +421,11 @@ build_iort(GArray *table_data, BIOSLinker *linker, VirtMachineState *vms)
             range = &g_array_index(its_idmaps, AcpiIortIdMapping, i);
             /* output IORT node is the ITS group node (the first node) */
             build_iort_id_mapping(table_data, range->input_base,
-                                  range->id_count, iort_node_offset);
+                                  range->id_count, IORT_NODE_OFFSET);
         }
     } else {
         /* output IORT node is the ITS group node (the first node) */
-        build_iort_id_mapping(table_data, 0, 0xFFFF, IORT_NODE_OFFSET);
+        build_iort_id_mapping(table_data, 0, 0x10000, IORT_NODE_OFFSET);
     }
 
     acpi_table_end(linker, &table);

hw/block/vhost-user-blk.c

@@ -51,6 +51,7 @@ static const int user_feature_bits[] = {
     VIRTIO_F_RING_PACKED,
     VIRTIO_F_IOMMU_PLATFORM,
     VIRTIO_F_RING_RESET,
+    VIRTIO_F_NOTIFICATION_DATA,
     VHOST_INVALID_FEATURE_BIT
 };
 
@@ -353,7 +354,7 @@ static void vhost_user_blk_disconnect(DeviceState *dev)
     VHostUserBlk *s = VHOST_USER_BLK(vdev);
 
     if (!s->connected) {
-        return;
+        goto done;
     }
     s->connected = false;
 
@@ -361,6 +362,7 @@ static void vhost_user_blk_disconnect(DeviceState *dev)
 
     vhost_dev_cleanup(&s->dev);
 
+done:
     /* Re-instate the event handler for new connections */
     qemu_chr_fe_set_handlers(&s->chardev, NULL, NULL, vhost_user_blk_event,
                              NULL, dev, NULL, true);
@@ -384,7 +386,7 @@ static void vhost_user_blk_event(void *opaque, QEMUChrEvent event)
     case CHR_EVENT_CLOSED:
         /* defer close until later to avoid circular close */
         vhost_user_async_close(dev, &s->chardev, &s->dev,
-                               vhost_user_blk_disconnect, vhost_user_blk_event);
+                               vhost_user_blk_disconnect);
         break;
     case CHR_EVENT_BREAK:
     case CHR_EVENT_MUX_IN:

hw/core/machine.c

@@ -38,6 +38,7 @@ GlobalProperty hw_compat_9_0[] = {
     {"arm-cpu", "backcompat-cntfrq", "true" },
     {"scsi-disk-base", "migrate-emulated-scsi-request", "false" },
     {"vfio-pci", "skip-vsc-check", "false" },
+    { "virtio-pci", "x-pcie-pm-no-soft-reset", "off" },
 };
 const size_t hw_compat_9_0_len = G_N_ELEMENTS(hw_compat_9_0);
 

hw/cxl/cxl-mailbox-utils.c

@@ -19,8 +19,12 @@
 #include "qemu/units.h"
 #include "qemu/uuid.h"
 #include "sysemu/hostmem.h"
+#include "qemu/range.h"
 
 #define CXL_CAPACITY_MULTIPLIER   (256 * MiB)
+#define CXL_DC_EVENT_LOG_SIZE 8
+#define CXL_NUM_EXTENTS_SUPPORTED 512
+#define CXL_NUM_TAGS_SUPPORTED 0
 
 /*
  * How to add a new command, example. The command set FOO, with cmd BAR.
@@ -79,6 +83,11 @@ enum {
         #define GET_POISON_LIST        0x0
         #define INJECT_POISON          0x1
         #define CLEAR_POISON           0x2
+    DCD_CONFIG  = 0x48,
+        #define GET_DC_CONFIG          0x0
+        #define GET_DYN_CAP_EXT_LIST   0x1
+        #define ADD_DYN_CAP_RSP        0x2
+        #define RELEASE_DYN_CAP        0x3
     PHYSICAL_SWITCH = 0x51,
         #define IDENTIFY_SWITCH_DEVICE      0x0
         #define GET_PHYSICAL_PORT_STATE     0x1
@@ -617,7 +626,8 @@ static CXLRetCode cmd_firmware_update_get_info(const struct cxl_cmd *cmd,
                                                size_t *len_out,
                                                CXLCCI *cci)
 {
-    CXLDeviceState *cxl_dstate = &CXL_TYPE3(cci->d)->cxl_dstate;
+    CXLType3Dev *ct3d = CXL_TYPE3(cci->d);
+    CXLDeviceState *cxl_dstate = &ct3d->cxl_dstate;
     struct {
         uint8_t slots_supported;
         uint8_t slot_info;
@@ -631,7 +641,8 @@ static CXLRetCode cmd_firmware_update_get_info(const struct cxl_cmd *cmd,
     QEMU_BUILD_BUG_ON(sizeof(*fw_info) != 0x50);
 
     if ((cxl_dstate->vmem_size < CXL_CAPACITY_MULTIPLIER) ||
-        (cxl_dstate->pmem_size < CXL_CAPACITY_MULTIPLIER)) {
+        (cxl_dstate->pmem_size < CXL_CAPACITY_MULTIPLIER) ||
+        (ct3d->dc.total_capacity < CXL_CAPACITY_MULTIPLIER)) {
         return CXL_MBOX_INTERNAL_ERROR;
     }
 
@@ -780,14 +791,16 @@ static CXLRetCode cmd_identify_memory_device(const struct cxl_cmd *cmd,
         uint16_t inject_poison_limit;
         uint8_t poison_caps;
         uint8_t qos_telemetry_caps;
+        uint16_t dc_event_log_size;
     } QEMU_PACKED *id;
-    QEMU_BUILD_BUG_ON(sizeof(*id) != 0x43);
+    QEMU_BUILD_BUG_ON(sizeof(*id) != 0x45);
     CXLType3Dev *ct3d = CXL_TYPE3(cci->d);
     CXLType3Class *cvc = CXL_TYPE3_GET_CLASS(ct3d);
     CXLDeviceState *cxl_dstate = &ct3d->cxl_dstate;
 
     if ((!QEMU_IS_ALIGNED(cxl_dstate->vmem_size, CXL_CAPACITY_MULTIPLIER)) ||
-        (!QEMU_IS_ALIGNED(cxl_dstate->pmem_size, CXL_CAPACITY_MULTIPLIER))) {
+        (!QEMU_IS_ALIGNED(cxl_dstate->pmem_size, CXL_CAPACITY_MULTIPLIER)) ||
+        (!QEMU_IS_ALIGNED(ct3d->dc.total_capacity, CXL_CAPACITY_MULTIPLIER))) {
         return CXL_MBOX_INTERNAL_ERROR;
     }
 
@@ -797,7 +810,7 @@ static CXLRetCode cmd_identify_memory_device(const struct cxl_cmd *cmd,
     snprintf(id->fw_revision, 0x10, "BWFW VERSION %02d", 0);
 
     stq_le_p(&id->total_capacity,
-             cxl_dstate->mem_size / CXL_CAPACITY_MULTIPLIER);
+             cxl_dstate->static_mem_size / CXL_CAPACITY_MULTIPLIER);
     stq_le_p(&id->persistent_capacity,
              cxl_dstate->pmem_size / CXL_CAPACITY_MULTIPLIER);
     stq_le_p(&id->volatile_capacity,
@@ -807,6 +820,7 @@ static CXLRetCode cmd_identify_memory_device(const struct cxl_cmd *cmd,
     st24_le_p(id->poison_list_max_mer, 256);
     /* No limit - so limited by main poison record limit */
     stw_le_p(&id->inject_poison_limit, 0);
+    stw_le_p(&id->dc_event_log_size, CXL_DC_EVENT_LOG_SIZE);
 
     *len_out = sizeof(*id);
     return CXL_MBOX_SUCCESS;
@@ -828,9 +842,11 @@ static CXLRetCode cmd_ccls_get_partition_info(const struct cxl_cmd *cmd,
         uint64_t next_pmem;
     } QEMU_PACKED *part_info = (void *)payload_out;
     QEMU_BUILD_BUG_ON(sizeof(*part_info) != 0x20);
+    CXLType3Dev *ct3d = container_of(cxl_dstate, CXLType3Dev, cxl_dstate);
 
     if ((!QEMU_IS_ALIGNED(cxl_dstate->vmem_size, CXL_CAPACITY_MULTIPLIER)) ||
-        (!QEMU_IS_ALIGNED(cxl_dstate->pmem_size, CXL_CAPACITY_MULTIPLIER))) {
+        (!QEMU_IS_ALIGNED(cxl_dstate->pmem_size, CXL_CAPACITY_MULTIPLIER)) ||
+        (!QEMU_IS_ALIGNED(ct3d->dc.total_capacity, CXL_CAPACITY_MULTIPLIER))) {
         return CXL_MBOX_INTERNAL_ERROR;
     }
 
@@ -1172,7 +1188,8 @@ static CXLRetCode cmd_media_clear_poison(const struct cxl_cmd *cmd,
     struct clear_poison_pl *in = (void *)payload_in;
 
     dpa = ldq_le_p(&in->dpa);
-    if (dpa + CXL_CACHE_LINE_SIZE > cxl_dstate->mem_size) {
+    if (dpa + CXL_CACHE_LINE_SIZE > cxl_dstate->static_mem_size +
+        ct3d->dc.total_capacity) {
         return CXL_MBOX_INVALID_PA;
     }
 
@@ -1235,6 +1252,576 @@ static CXLRetCode cmd_media_clear_poison(const struct cxl_cmd *cmd,
     return CXL_MBOX_SUCCESS;
 }
 
+/*
+ * CXL r3.1 section 8.2.9.9.9.1: Get Dynamic Capacity Configuration
+ * (Opcode: 4800h)
+ */
+static CXLRetCode cmd_dcd_get_dyn_cap_config(const struct cxl_cmd *cmd,
+                                             uint8_t *payload_in,
+                                             size_t len_in,
+                                             uint8_t *payload_out,
+                                             size_t *len_out,
+                                             CXLCCI *cci)
+{
+    CXLType3Dev *ct3d = CXL_TYPE3(cci->d);
+    struct {
+        uint8_t region_cnt;
+        uint8_t start_rid;
+    } QEMU_PACKED *in = (void *)payload_in;
+    struct {
+        uint8_t num_regions;
+        uint8_t regions_returned;
+        uint8_t rsvd1[6];
+        struct {
+            uint64_t base;
+            uint64_t decode_len;
+            uint64_t region_len;
+            uint64_t block_size;
+            uint32_t dsmadhandle;
+            uint8_t flags;
+            uint8_t rsvd2[3];
+        } QEMU_PACKED records[];
+    } QEMU_PACKED *out = (void *)payload_out;
+    struct {
+        uint32_t num_extents_supported;
+        uint32_t num_extents_available;
+        uint32_t num_tags_supported;
+        uint32_t num_tags_available;
+    } QEMU_PACKED *extra_out;
+    uint16_t record_count;
+    uint16_t i;
+    uint16_t out_pl_len;
+    uint8_t start_rid;
+
+    start_rid = in->start_rid;
+    if (start_rid >= ct3d->dc.num_regions) {
+        return CXL_MBOX_INVALID_INPUT;
+    }
+
+    record_count = MIN(ct3d->dc.num_regions - in->start_rid, in->region_cnt);
+
+    out_pl_len = sizeof(*out) + record_count * sizeof(out->records[0]);
+    extra_out = (void *)(payload_out + out_pl_len);
+    out_pl_len += sizeof(*extra_out);
+    assert(out_pl_len <= CXL_MAILBOX_MAX_PAYLOAD_SIZE);
+
+    out->num_regions = ct3d->dc.num_regions;
+    out->regions_returned = record_count;
+    for (i = 0; i < record_count; i++) {
+        stq_le_p(&out->records[i].base,
+                 ct3d->dc.regions[start_rid + i].base);
+        stq_le_p(&out->records[i].decode_len,
+                 ct3d->dc.regions[start_rid + i].decode_len /
+                 CXL_CAPACITY_MULTIPLIER);
+        stq_le_p(&out->records[i].region_len,
+                 ct3d->dc.regions[start_rid + i].len);
+        stq_le_p(&out->records[i].block_size,
+                 ct3d->dc.regions[start_rid + i].block_size);
+        stl_le_p(&out->records[i].dsmadhandle,
+                 ct3d->dc.regions[start_rid + i].dsmadhandle);
+        out->records[i].flags = ct3d->dc.regions[start_rid + i].flags;
+    }
+    /*
+     * TODO: Assign values once extents and tags are introduced
+     * to use.
+     */
+    stl_le_p(&extra_out->num_extents_supported, CXL_NUM_EXTENTS_SUPPORTED);
+    stl_le_p(&extra_out->num_extents_available, CXL_NUM_EXTENTS_SUPPORTED -
+             ct3d->dc.total_extent_count);
+    stl_le_p(&extra_out->num_tags_supported, CXL_NUM_TAGS_SUPPORTED);
+    stl_le_p(&extra_out->num_tags_available, CXL_NUM_TAGS_SUPPORTED);
+
+    *len_out = out_pl_len;
+    return CXL_MBOX_SUCCESS;
+}
+
+/*
+ * CXL r3.1 section 8.2.9.9.9.2:
+ * Get Dynamic Capacity Extent List (Opcode 4801h)
+ */
+static CXLRetCode cmd_dcd_get_dyn_cap_ext_list(const struct cxl_cmd *cmd,
+                                               uint8_t *payload_in,
+                                               size_t len_in,
+                                               uint8_t *payload_out,
+                                               size_t *len_out,
+                                               CXLCCI *cci)
+{
+    CXLType3Dev *ct3d = CXL_TYPE3(cci->d);
+    struct {
+        uint32_t extent_cnt;
+        uint32_t start_extent_id;
+    } QEMU_PACKED *in = (void *)payload_in;
+    struct {
+        uint32_t count;
+        uint32_t total_extents;
+        uint32_t generation_num;
+        uint8_t rsvd[4];
+        CXLDCExtentRaw records[];
+    } QEMU_PACKED *out = (void *)payload_out;
+    uint32_t start_extent_id = in->start_extent_id;
+    CXLDCExtentList *extent_list = &ct3d->dc.extents;
+    uint16_t record_count = 0, i = 0, record_done = 0;
+    uint16_t out_pl_len, size;
+    CXLDCExtent *ent;
+
+    if (start_extent_id > ct3d->dc.total_extent_count) {
+        return CXL_MBOX_INVALID_INPUT;
+    }
+
+    record_count = MIN(in->extent_cnt,
+                       ct3d->dc.total_extent_count - start_extent_id);
+    size = CXL_MAILBOX_MAX_PAYLOAD_SIZE - sizeof(*out);
+    record_count = MIN(record_count, size / sizeof(out->records[0]));
+    out_pl_len = sizeof(*out) + record_count * sizeof(out->records[0]);
+
+    stl_le_p(&out->count, record_count);
+    stl_le_p(&out->total_extents, ct3d->dc.total_extent_count);
+    stl_le_p(&out->generation_num, ct3d->dc.ext_list_gen_seq);
+
+    if (record_count > 0) {
+        CXLDCExtentRaw *out_rec = &out->records[record_done];
+
+        QTAILQ_FOREACH(ent, extent_list, node) {
+            if (i++ < start_extent_id) {
+                continue;
+            }
+            stq_le_p(&out_rec->start_dpa, ent->start_dpa);
+            stq_le_p(&out_rec->len, ent->len);
+            memcpy(&out_rec->tag, ent->tag, 0x10);
+            stw_le_p(&out_rec->shared_seq, ent->shared_seq);
+
+            record_done++;
+            if (record_done == record_count) {
+                break;
+            }
+        }
+    }
+
+    *len_out = out_pl_len;
+    return CXL_MBOX_SUCCESS;
+}
+
+/*
+ * Check whether any bit between addr[nr, nr+size) is set,
+ * return true if any bit is set, otherwise return false
+ */
+bool test_any_bits_set(const unsigned long *addr, unsigned long nr,
+                              unsigned long size)
+{
+    unsigned long res = find_next_bit(addr, size + nr, nr);
+
+    return res < nr + size;
+}
+
+CXLDCRegion *cxl_find_dc_region(CXLType3Dev *ct3d, uint64_t dpa, uint64_t len)
+{
+    int i;
+    CXLDCRegion *region = &ct3d->dc.regions[0];
+
+    if (dpa < region->base ||
+        dpa >= region->base + ct3d->dc.total_capacity) {
+        return NULL;
+    }
+
+    /*
+     * CXL r3.1 section 9.13.3: Dynamic Capacity Device (DCD)
+     *
+     * Regions are used in increasing-DPA order, with Region 0 being used for
+     * the lowest DPA of Dynamic Capacity and Region 7 for the highest DPA.
+     * So check from the last region to find where the dpa belongs. Extents that
+     * cross multiple regions are not allowed.
+     */
+    for (i = ct3d->dc.num_regions - 1; i >= 0; i--) {
+        region = &ct3d->dc.regions[i];
+        if (dpa >= region->base) {
+            if (dpa + len > region->base + region->len) {
+                return NULL;
+            }
+            return region;
+        }
+    }
+
+    return NULL;
+}
+
+void cxl_insert_extent_to_extent_list(CXLDCExtentList *list,
+                                             uint64_t dpa,
+                                             uint64_t len,
+                                             uint8_t *tag,
+                                             uint16_t shared_seq)
+{
+    CXLDCExtent *extent;
+
+    extent = g_new0(CXLDCExtent, 1);
+    extent->start_dpa = dpa;
+    extent->len = len;
+    if (tag) {
+        memcpy(extent->tag, tag, 0x10);
+    }
+    extent->shared_seq = shared_seq;
+
+    QTAILQ_INSERT_TAIL(list, extent, node);
+}
+
+void cxl_remove_extent_from_extent_list(CXLDCExtentList *list,
+                                        CXLDCExtent *extent)
+{
+    QTAILQ_REMOVE(list, extent, node);
+    g_free(extent);
+}
+
+/*
+ * Add a new extent to the extent "group" if group exists;
+ * otherwise, create a new group
+ * Return value: the extent group where the extent is inserted.
+ */
+CXLDCExtentGroup *cxl_insert_extent_to_extent_group(CXLDCExtentGroup *group,
+                                                    uint64_t dpa,
+                                                    uint64_t len,
+                                                    uint8_t *tag,
+                                                    uint16_t shared_seq)
+{
+    if (!group) {
+        group = g_new0(CXLDCExtentGroup, 1);
+        QTAILQ_INIT(&group->list);
+    }
+    cxl_insert_extent_to_extent_list(&group->list, dpa, len,
+                                     tag, shared_seq);
+    return group;
+}
+
+void cxl_extent_group_list_insert_tail(CXLDCExtentGroupList *list,
+                                       CXLDCExtentGroup *group)
+{
+    QTAILQ_INSERT_TAIL(list, group, node);
+}
+
+void cxl_extent_group_list_delete_front(CXLDCExtentGroupList *list)
+{
+    CXLDCExtent *ent, *ent_next;
+    CXLDCExtentGroup *group = QTAILQ_FIRST(list);
+
+    QTAILQ_REMOVE(list, group, node);
+    QTAILQ_FOREACH_SAFE(ent, &group->list, node, ent_next) {
+        cxl_remove_extent_from_extent_list(&group->list, ent);
+    }
+    g_free(group);
+}
+
+/*
+ * CXL r3.1 Table 8-168: Add Dynamic Capacity Response Input Payload
+ * CXL r3.1 Table 8-170: Release Dynamic Capacity Input Payload
+ */
+typedef struct CXLUpdateDCExtentListInPl {
+    uint32_t num_entries_updated;
+    uint8_t flags;
+    uint8_t rsvd[3];
+    /* CXL r3.1 Table 8-169: Updated Extent */
+    struct {
+        uint64_t start_dpa;
+        uint64_t len;
+        uint8_t rsvd[8];
+    } QEMU_PACKED updated_entries[];
+} QEMU_PACKED CXLUpdateDCExtentListInPl;
+
+/*
+ * For the extents in the extent list to operate, check whether they are valid
+ * 1. The extent should be in the range of a valid DC region;
+ * 2. The extent should not cross multiple regions;
+ * 3. The start DPA and the length of the extent should align with the block
+ * size of the region;
+ * 4. The address range of multiple extents in the list should not overlap.
+ */
+static CXLRetCode cxl_detect_malformed_extent_list(CXLType3Dev *ct3d,
+        const CXLUpdateDCExtentListInPl *in)
+{
+    uint64_t min_block_size = UINT64_MAX;
+    CXLDCRegion *region;
+    CXLDCRegion *lastregion = &ct3d->dc.regions[ct3d->dc.num_regions - 1];
+    g_autofree unsigned long *blk_bitmap = NULL;
+    uint64_t dpa, len;
+    uint32_t i;
+
+    for (i = 0; i < ct3d->dc.num_regions; i++) {
+        region = &ct3d->dc.regions[i];
+        min_block_size = MIN(min_block_size, region->block_size);
+    }
+
+    blk_bitmap = bitmap_new((lastregion->base + lastregion->len -
+                             ct3d->dc.regions[0].base) / min_block_size);
+
+    for (i = 0; i < in->num_entries_updated; i++) {
+        dpa = in->updated_entries[i].start_dpa;
+        len = in->updated_entries[i].len;
+
+        region = cxl_find_dc_region(ct3d, dpa, len);
+        if (!region) {
+            return CXL_MBOX_INVALID_PA;
+        }
+
+        dpa -= ct3d->dc.regions[0].base;
+        if (dpa % region->block_size || len % region->block_size) {
+            return CXL_MBOX_INVALID_EXTENT_LIST;
+        }
+        /* the dpa range already covered by some other extents in the list */
+        if (test_any_bits_set(blk_bitmap, dpa / min_block_size,
+            len / min_block_size)) {
+            return CXL_MBOX_INVALID_EXTENT_LIST;
+        }
+        bitmap_set(blk_bitmap, dpa / min_block_size, len / min_block_size);
+   }
+
+    return CXL_MBOX_SUCCESS;
+}
+
+static CXLRetCode cxl_dcd_add_dyn_cap_rsp_dry_run(CXLType3Dev *ct3d,
+        const CXLUpdateDCExtentListInPl *in)
+{
+    uint32_t i;
+    CXLDCExtent *ent;
+    CXLDCExtentGroup *ext_group;
+    uint64_t dpa, len;
+    Range range1, range2;
+
+    for (i = 0; i < in->num_entries_updated; i++) {
+        dpa = in->updated_entries[i].start_dpa;
+        len = in->updated_entries[i].len;
+
+        range_init_nofail(&range1, dpa, len);
+
+        /*
+         * The host-accepted DPA range must be contained by the first extent
+         * group in the pending list
+         */
+        ext_group = QTAILQ_FIRST(&ct3d->dc.extents_pending);
+        if (!cxl_extents_contains_dpa_range(&ext_group->list, dpa, len)) {
+            return CXL_MBOX_INVALID_PA;
+        }
+
+        /* to-be-added range should not overlap with range already accepted */
+        QTAILQ_FOREACH(ent, &ct3d->dc.extents, node) {
+            range_init_nofail(&range2, ent->start_dpa, ent->len);
+            if (range_overlaps_range(&range1, &range2)) {
+                return CXL_MBOX_INVALID_PA;
+            }
+        }
+    }
+    return CXL_MBOX_SUCCESS;
+}
+
+/*
+ * CXL r3.1 section 8.2.9.9.9.3: Add Dynamic Capacity Response (Opcode 4802h)
+ * An extent is added to the extent list and becomes usable only after the
+ * response is processed successfully.
+ */
+static CXLRetCode cmd_dcd_add_dyn_cap_rsp(const struct cxl_cmd *cmd,
+                                          uint8_t *payload_in,
+                                          size_t len_in,
+                                          uint8_t *payload_out,
+                                          size_t *len_out,
+                                          CXLCCI *cci)
+{
+    CXLUpdateDCExtentListInPl *in = (void *)payload_in;
+    CXLType3Dev *ct3d = CXL_TYPE3(cci->d);
+    CXLDCExtentList *extent_list = &ct3d->dc.extents;
+    uint32_t i;
+    uint64_t dpa, len;
+    CXLRetCode ret;
+
+    if (in->num_entries_updated == 0) {
+        cxl_extent_group_list_delete_front(&ct3d->dc.extents_pending);
+        return CXL_MBOX_SUCCESS;
+    }
+
+    /* Adding extents causes exceeding device's extent tracking ability. */
+    if (in->num_entries_updated + ct3d->dc.total_extent_count >
+        CXL_NUM_EXTENTS_SUPPORTED) {
+        return CXL_MBOX_RESOURCES_EXHAUSTED;
+    }
+
+    ret = cxl_detect_malformed_extent_list(ct3d, in);
+    if (ret != CXL_MBOX_SUCCESS) {
+        return ret;
+    }
+
+    ret = cxl_dcd_add_dyn_cap_rsp_dry_run(ct3d, in);
+    if (ret != CXL_MBOX_SUCCESS) {
+        return ret;
+    }
+
+    for (i = 0; i < in->num_entries_updated; i++) {
+        dpa = in->updated_entries[i].start_dpa;
+        len = in->updated_entries[i].len;
+
+        cxl_insert_extent_to_extent_list(extent_list, dpa, len, NULL, 0);
+        ct3d->dc.total_extent_count += 1;
+        ct3_set_region_block_backed(ct3d, dpa, len);
+    }
+    /* Remove the first extent group in the pending list */
+    cxl_extent_group_list_delete_front(&ct3d->dc.extents_pending);
+
+    return CXL_MBOX_SUCCESS;
+}
+
+/*
+ * Copy extent list from src to dst
+ * Return value: number of extents copied
+ */
+static uint32_t copy_extent_list(CXLDCExtentList *dst,
+                                 const CXLDCExtentList *src)
+{
+    uint32_t cnt = 0;
+    CXLDCExtent *ent;
+
+    if (!dst || !src) {
+        return 0;
+    }
+
+    QTAILQ_FOREACH(ent, src, node) {
+        cxl_insert_extent_to_extent_list(dst, ent->start_dpa, ent->len,
+                                         ent->tag, ent->shared_seq);
+        cnt++;
+    }
+    return cnt;
+}
+
+static CXLRetCode cxl_dc_extent_release_dry_run(CXLType3Dev *ct3d,
+        const CXLUpdateDCExtentListInPl *in, CXLDCExtentList *updated_list,
+        uint32_t *updated_list_size)
+{
+    CXLDCExtent *ent, *ent_next;
+    uint64_t dpa, len;
+    uint32_t i;
+    int cnt_delta = 0;
+    CXLRetCode ret = CXL_MBOX_SUCCESS;
+
+    QTAILQ_INIT(updated_list);
+    copy_extent_list(updated_list, &ct3d->dc.extents);
+
+    for (i = 0; i < in->num_entries_updated; i++) {
+        Range range;
+
+        dpa = in->updated_entries[i].start_dpa;
+        len = in->updated_entries[i].len;
+
+        /* Check if the DPA range is not fully backed with valid extents */
+        if (!ct3_test_region_block_backed(ct3d, dpa, len)) {
+            ret = CXL_MBOX_INVALID_PA;
+            goto free_and_exit;
+        }
+
+        /* After this point, extent overflow is the only error can happen */
+        while (len > 0) {
+            QTAILQ_FOREACH(ent, updated_list, node) {
+                range_init_nofail(&range, ent->start_dpa, ent->len);
+
+                if (range_contains(&range, dpa)) {
+                    uint64_t len1, len2 = 0, len_done = 0;
+                    uint64_t ent_start_dpa = ent->start_dpa;
+                    uint64_t ent_len = ent->len;
+
+                    len1 = dpa - ent->start_dpa;
+                    /* Found the extent or the subset of an existing extent */
+                    if (range_contains(&range, dpa + len - 1)) {
+                        len2 = ent_start_dpa + ent_len - dpa - len;
+                    } else {
+                        dpa = ent_start_dpa + ent_len;
+                    }
+                    len_done = ent_len - len1 - len2;
+
+                    cxl_remove_extent_from_extent_list(updated_list, ent);
+                    cnt_delta--;
+
+                    if (len1) {
+                        cxl_insert_extent_to_extent_list(updated_list,
+                                                         ent_start_dpa,
+                                                         len1, NULL, 0);
+                        cnt_delta++;
+                    }
+                    if (len2) {
+                        cxl_insert_extent_to_extent_list(updated_list,
+                                                         dpa + len,
+                                                         len2, NULL, 0);
+                        cnt_delta++;
+                    }
+
+                    if (cnt_delta + ct3d->dc.total_extent_count >
+                            CXL_NUM_EXTENTS_SUPPORTED) {
+                        ret = CXL_MBOX_RESOURCES_EXHAUSTED;
+                        goto free_and_exit;
+                    }
+
+                    len -= len_done;
+                    break;
+                }
+            }
+        }
+    }
+free_and_exit:
+    if (ret != CXL_MBOX_SUCCESS) {
+        QTAILQ_FOREACH_SAFE(ent, updated_list, node, ent_next) {
+            cxl_remove_extent_from_extent_list(updated_list, ent);
+        }
+        *updated_list_size = 0;
+    } else {
+        *updated_list_size = ct3d->dc.total_extent_count + cnt_delta;
+    }
+
+    return ret;
+}
+
+/*
+ * CXL r3.1 section 8.2.9.9.9.4: Release Dynamic Capacity (Opcode 4803h)
+ */
+static CXLRetCode cmd_dcd_release_dyn_cap(const struct cxl_cmd *cmd,
+                                          uint8_t *payload_in,
+                                          size_t len_in,
+                                          uint8_t *payload_out,
+                                          size_t *len_out,
+                                          CXLCCI *cci)
+{
+    CXLUpdateDCExtentListInPl *in = (void *)payload_in;
+    CXLType3Dev *ct3d = CXL_TYPE3(cci->d);
+    CXLDCExtentList updated_list;
+    CXLDCExtent *ent, *ent_next;
+    uint32_t updated_list_size;
+    CXLRetCode ret;
+
+    if (in->num_entries_updated == 0) {
+        return CXL_MBOX_INVALID_INPUT;
+    }
+
+    ret = cxl_detect_malformed_extent_list(ct3d, in);
+    if (ret != CXL_MBOX_SUCCESS) {
+        return ret;
+    }
+
+    ret = cxl_dc_extent_release_dry_run(ct3d, in, &updated_list,
+                                        &updated_list_size);
+    if (ret != CXL_MBOX_SUCCESS) {
+        return ret;
+    }
+
+    /*
+     * If the dry run release passes, the returned updated_list will
+     * be the updated extent list and we just need to clear the extents
+     * in the accepted list and copy extents in the updated_list to accepted
+     * list and update the extent count;
+     */
+    QTAILQ_FOREACH_SAFE(ent, &ct3d->dc.extents, node, ent_next) {
+        ct3_clear_region_block_backed(ct3d, ent->start_dpa, ent->len);
+        cxl_remove_extent_from_extent_list(&ct3d->dc.extents, ent);
+    }
+    copy_extent_list(&ct3d->dc.extents, &updated_list);
+    QTAILQ_FOREACH_SAFE(ent, &updated_list, node, ent_next) {
+        ct3_set_region_block_backed(ct3d, ent->start_dpa, ent->len);
+        cxl_remove_extent_from_extent_list(&updated_list, ent);
+    }
+    ct3d->dc.total_extent_count = updated_list_size;
+
+    return CXL_MBOX_SUCCESS;
+}
+
 #define IMMEDIATE_CONFIG_CHANGE (1 << 1)
 #define IMMEDIATE_DATA_CHANGE (1 << 2)
 #define IMMEDIATE_POLICY_CHANGE (1 << 3)
@@ -1279,6 +1866,20 @@ static const struct cxl_cmd cxl_cmd_set[256][256] = {
         cmd_media_clear_poison, 72, 0 },
 };
 
+static const struct cxl_cmd cxl_cmd_set_dcd[256][256] = {
+    [DCD_CONFIG][GET_DC_CONFIG] = { "DCD_GET_DC_CONFIG",
+        cmd_dcd_get_dyn_cap_config, 2, 0 },
+    [DCD_CONFIG][GET_DYN_CAP_EXT_LIST] = {
+        "DCD_GET_DYNAMIC_CAPACITY_EXTENT_LIST", cmd_dcd_get_dyn_cap_ext_list,
+        8, 0 },
+    [DCD_CONFIG][ADD_DYN_CAP_RSP] = {
+        "DCD_ADD_DYNAMIC_CAPACITY_RESPONSE", cmd_dcd_add_dyn_cap_rsp,
+        ~0, IMMEDIATE_DATA_CHANGE },
+    [DCD_CONFIG][RELEASE_DYN_CAP] = {
+        "DCD_RELEASE_DYNAMIC_CAPACITY", cmd_dcd_release_dyn_cap,
+        ~0, IMMEDIATE_DATA_CHANGE },
+};
+
 static const struct cxl_cmd cxl_cmd_set_sw[256][256] = {
     [INFOSTAT][IS_IDENTIFY] = { "IDENTIFY", cmd_infostat_identify, 0, 0 },
     [INFOSTAT][BACKGROUND_OPERATION_STATUS] = { "BACKGROUND_OPERATION_STATUS",
@@ -1424,9 +2025,9 @@ static void bg_timercb(void *opaque)
     }
 }
 
-void cxl_init_cci(CXLCCI *cci, size_t payload_max)
+static void cxl_rebuild_cel(CXLCCI *cci)
 {
-    cci->payload_max = payload_max;
+    cci->cel_size = 0; /* Reset for a fresh build */
     for (int set = 0; set < 256; set++) {
         for (int cmd = 0; cmd < 256; cmd++) {
             if (cci->cxl_cmd_set[set][cmd].handler) {
@@ -1440,6 +2041,13 @@ void cxl_init_cci(CXLCCI *cci, size_t payload_max)
             }
         }
     }
+}
+
+void cxl_init_cci(CXLCCI *cci, size_t payload_max)
+{
+    cci->payload_max = payload_max;
+    cxl_rebuild_cel(cci);
+
     cci->bg.complete_pct = 0;
     cci->bg.starttime = 0;
     cci->bg.runtime = 0;
@@ -1447,10 +2055,29 @@ void cxl_init_cci(CXLCCI *cci, size_t payload_max)
                                  bg_timercb, cci);
 }
 
+static void cxl_copy_cci_commands(CXLCCI *cci, const struct cxl_cmd (*cxl_cmds)[256])
+{
+    for (int set = 0; set < 256; set++) {
+        for (int cmd = 0; cmd < 256; cmd++) {
+            if (cxl_cmds[set][cmd].handler) {
+                cci->cxl_cmd_set[set][cmd] = cxl_cmds[set][cmd];
+            }
+        }
+    }
+}
+
+void cxl_add_cci_commands(CXLCCI *cci, const struct cxl_cmd (*cxl_cmd_set)[256],
+                                 size_t payload_max)
+{
+    cci->payload_max = MAX(payload_max, cci->payload_max);
+    cxl_copy_cci_commands(cci, cxl_cmd_set);
+    cxl_rebuild_cel(cci);
+}
+
 void cxl_initialize_mailbox_swcci(CXLCCI *cci, DeviceState *intf,
                                   DeviceState *d, size_t payload_max)
 {
-    cci->cxl_cmd_set = cxl_cmd_set_sw;
+    cxl_copy_cci_commands(cci, cxl_cmd_set_sw);
     cci->d = d;
     cci->intf = intf;
     cxl_init_cci(cci, payload_max);
@@ -1458,7 +2085,12 @@ void cxl_initialize_mailbox_swcci(CXLCCI *cci, DeviceState *intf,
 
 void cxl_initialize_mailbox_t3(CXLCCI *cci, DeviceState *d, size_t payload_max)
 {
-    cci->cxl_cmd_set = cxl_cmd_set;
+    CXLType3Dev *ct3d = CXL_TYPE3(d);
+
+    cxl_copy_cci_commands(cci, cxl_cmd_set);
+    if (ct3d->dc.num_regions) {
+        cxl_copy_cci_commands(cci, cxl_cmd_set_dcd);
+    }
     cci->d = d;
 
     /* No separation for PCI MB as protocol handled in PCI device */
@@ -1476,7 +2108,7 @@ static const struct cxl_cmd cxl_cmd_set_t3_ld[256][256] = {
 void cxl_initialize_t3_ld_cci(CXLCCI *cci, DeviceState *d, DeviceState *intf,
                                size_t payload_max)
 {
-    cci->cxl_cmd_set = cxl_cmd_set_t3_ld;
+    cxl_copy_cci_commands(cci, cxl_cmd_set_t3_ld);
     cci->d = d;
     cci->intf = intf;
     cxl_init_cci(cci, payload_max);
@@ -1496,7 +2128,7 @@ void cxl_initialize_t3_fm_owned_ld_mctpcci(CXLCCI *cci, DeviceState *d,
                                            DeviceState *intf,
                                            size_t payload_max)
 {
-    cci->cxl_cmd_set = cxl_cmd_set_t3_fm_owned_ld_mctp;
+    cxl_copy_cci_commands(cci, cxl_cmd_set_t3_fm_owned_ld_mctp);
     cci->d = d;
     cci->intf = intf;
     cxl_init_cci(cci, payload_max);

hw/display/vhost-user-gpu.c

@@ -281,8 +281,9 @@ vhost_user_gpu_handle_display(VhostUserGPU *g, VhostUserGpuMsg *msg)
             modifier = m2->modifier;
         }
 
-        dmabuf = qemu_dmabuf_new(m->fd_width, m->fd_height,
+        dmabuf = qemu_dmabuf_new(m->width, m->height,
-                                 m->fd_stride, 0, 0, 0, 0,
+                                 m->fd_stride, 0, 0,
+                                 m->fd_width, m->fd_height,
                                  m->fd_drm_fourcc, modifier,
                                  fd, false, m->fd_flags &
                                  VIRTIO_GPU_RESOURCE_FLAG_Y_0_TOP);

hw/i386/e820_memory_layout.c

@@ -11,22 +11,29 @@
 #include "e820_memory_layout.h"
 
 static size_t e820_entries;
-struct e820_entry *e820_table;
+static struct e820_entry *e820_table;
+static gboolean e820_done;
 
-int e820_add_entry(uint64_t address, uint64_t length, uint32_t type)
+void e820_add_entry(uint64_t address, uint64_t length, uint32_t type)
 {
+    assert(!e820_done);
+
     /* new "etc/e820" file -- include ram and reserved entries */
     e820_table = g_renew(struct e820_entry, e820_table, e820_entries + 1);
     e820_table[e820_entries].address = cpu_to_le64(address);
     e820_table[e820_entries].length = cpu_to_le64(length);
     e820_table[e820_entries].type = cpu_to_le32(type);
     e820_entries++;
-
-    return e820_entries;
 }
 
-int e820_get_num_entries(void)
+int e820_get_table(struct e820_entry **table)
 {
+    e820_done = true;
+
+    if (table) {
+        *table = e820_table;
+    }
+
     return e820_entries;
 }
 

hw/i386/e820_memory_layout.h

@@ -22,13 +22,9 @@ struct e820_entry {
     uint32_t type;
 } QEMU_PACKED __attribute((__aligned__(4)));
 
-extern struct e820_entry *e820_table;
+void e820_add_entry(uint64_t address, uint64_t length, uint32_t type);
-
-int e820_add_entry(uint64_t address, uint64_t length, uint32_t type);
-int e820_get_num_entries(void);
 bool e820_get_entry(int index, uint32_t type,
                     uint64_t *address, uint64_t *length);
-
+int e820_get_table(struct e820_entry **table);
-
 
 #endif

hw/i386/fw_cfg.c

@@ -48,6 +48,15 @@ const char *fw_cfg_arch_key_name(uint16_t key)
     return NULL;
 }
 
+/* Add etc/e820 late, once all regions should be present */
+void fw_cfg_add_e820(FWCfgState *fw_cfg)
+{
+    struct e820_entry *table;
+    int nr_e820 = e820_get_table(&table);
+
+    fw_cfg_add_file(fw_cfg, "etc/e820", table, nr_e820 * sizeof(*table));
+}
+
 void fw_cfg_build_smbios(PCMachineState *pcms, FWCfgState *fw_cfg,
                          SmbiosEntryPointType ep_type)
 {
@@ -60,6 +69,7 @@ void fw_cfg_build_smbios(PCMachineState *pcms, FWCfgState *fw_cfg,
     PCMachineClass *pcmc = PC_MACHINE_GET_CLASS(pcms);
     MachineClass *mc = MACHINE_GET_CLASS(pcms);
     X86CPU *cpu = X86_CPU(ms->possible_cpus->cpus[0].cpu);
+    int nr_e820;
 
     if (pcmc->smbios_defaults) {
         /* These values are guest ABI, do not change */
@@ -78,8 +88,9 @@ void fw_cfg_build_smbios(PCMachineState *pcms, FWCfgState *fw_cfg,
     }
 
     /* build the array of physical mem area from e820 table */
-    mem_array = g_malloc0(sizeof(*mem_array) * e820_get_num_entries());
+    nr_e820 = e820_get_table(NULL);
-    for (i = 0, array_count = 0; i < e820_get_num_entries(); i++) {
+    mem_array = g_malloc0(sizeof(*mem_array) * nr_e820);
+    for (i = 0, array_count = 0; i < nr_e820; i++) {
         uint64_t addr, len;
 
         if (e820_get_entry(i, E820_RAM, &addr, &len)) {
@@ -138,9 +149,6 @@ FWCfgState *fw_cfg_arch_create(MachineState *ms,
 #endif
     fw_cfg_add_i32(fw_cfg, FW_CFG_IRQ0_OVERRIDE, 1);
 
-    fw_cfg_add_file(fw_cfg, "etc/e820", e820_table,
-                    sizeof(struct e820_entry) * e820_get_num_entries());
-
     fw_cfg_add_bytes(fw_cfg, FW_CFG_HPET, &hpet_cfg, sizeof(hpet_cfg));
     /* allocate memory for the NUMA channel: one (64bit) word for the number
      * of nodes, one word for each VCPU->node and one word for each node to

hw/i386/fw_cfg.h

@@ -27,5 +27,6 @@ void fw_cfg_build_smbios(PCMachineState *pcms, FWCfgState *fw_cfg,
                          SmbiosEntryPointType ep_type);
 void fw_cfg_build_feature_control(MachineState *ms, FWCfgState *fw_cfg);
 void fw_cfg_add_acpi_dsdt(Aml *scope, FWCfgState *fw_cfg);
+void fw_cfg_add_e820(FWCfgState *fw_cfg);
 
 #endif

hw/i386/microvm.c

@@ -324,8 +324,6 @@ static void microvm_memory_init(MicrovmMachineState *mms)
     fw_cfg_add_i16(fw_cfg, FW_CFG_MAX_CPUS, machine->smp.max_cpus);
     fw_cfg_add_i64(fw_cfg, FW_CFG_RAM_SIZE, (uint64_t)machine->ram_size);
     fw_cfg_add_i32(fw_cfg, FW_CFG_IRQ0_OVERRIDE, 1);
-    fw_cfg_add_file(fw_cfg, "etc/e820", e820_table,
-                    sizeof(struct e820_entry) * e820_get_num_entries());
 
     rom_set_fw(fw_cfg);
 
@@ -586,9 +584,11 @@ static void microvm_machine_done(Notifier *notifier, void *data)
 {
     MicrovmMachineState *mms = container_of(notifier, MicrovmMachineState,
                                             machine_done);
+    X86MachineState *x86ms = X86_MACHINE(mms);
 
     acpi_setup_microvm(mms);
     dt_setup_microvm(mms);
+    fw_cfg_add_e820(x86ms->fw_cfg);
 }
 
 static void microvm_powerdown_req(Notifier *notifier, void *data)

hw/i386/pc.c

@@ -625,6 +625,7 @@ void pc_machine_done(Notifier *notifier, void *data)
     acpi_setup();
     if (x86ms->fw_cfg) {
         fw_cfg_build_smbios(pcms, x86ms->fw_cfg, pcms->smbios_entry_point_type);
+        fw_cfg_add_e820(x86ms->fw_cfg);
         fw_cfg_build_feature_control(MACHINE(pcms), x86ms->fw_cfg);
         /* update FW_CFG_NB_CPUS to account for -device added CPUs */
         fw_cfg_modify_i16(x86ms->fw_cfg, FW_CFG_NB_CPUS, x86ms->boot_cpus);

hw/intc/apic_common.c

@@ -433,6 +433,7 @@ static void apic_common_set_id(Object *obj, Visitor *v, const char *name,
     APICCommonState *s = APIC_COMMON(obj);
     DeviceState *dev = DEVICE(obj);
     uint32_t value;
+    Error *local_err = NULL;
 
     if (dev->realized) {
         qdev_prop_set_after_realize(dev, name, errp);
@@ -444,7 +445,11 @@ static void apic_common_set_id(Object *obj, Visitor *v, const char *name,
     }
 
     if (value >= 255 && !cpu_has_x2apic_feature(&s->cpu->env)) {
-        error_setg(errp, "APIC ID %d requires x2APIC feature in CPU", value);
+        error_setg(&local_err,
+                   "APIC ID %d requires x2APIC feature in CPU",
+                   value);
+        error_append_hint(&local_err, "Try x2apic=on in -cpu.\n");
+        error_propagate(errp, local_err);
         return;
     }
 

hw/mem/cxl_type3.c

@@ -30,6 +30,7 @@
 #include "hw/pci/msix.h"
 
 #define DWORD_BYTE 4
+#define CXL_CAPACITY_MULTIPLIER   (256 * MiB)
 
 /* Default CDAT entries for a memory region */
 enum {
@@ -43,8 +44,9 @@ enum {
 };
 
 static void ct3_build_cdat_entries_for_mr(CDATSubHeader **cdat_table,
-                                          int dsmad_handle, MemoryRegion *mr,
+                                          int dsmad_handle, uint64_t size,
-                                          bool is_pmem, uint64_t dpa_base)
+                                          bool is_pmem, bool is_dynamic,
+                                          uint64_t dpa_base)
 {
     CDATDsmas *dsmas;
     CDATDslbis *dslbis0;
@@ -60,9 +62,10 @@ static void ct3_build_cdat_entries_for_mr(CDATSubHeader **cdat_table,
             .length = sizeof(*dsmas),
         },
         .DSMADhandle = dsmad_handle,
-        .flags = is_pmem ? CDAT_DSMAS_FLAG_NV : 0,
+        .flags = (is_pmem ? CDAT_DSMAS_FLAG_NV : 0) |
+                 (is_dynamic ? CDAT_DSMAS_FLAG_DYNAMIC_CAP : 0),
         .DPA_base = dpa_base,
-        .DPA_length = memory_region_size(mr),
+        .DPA_length = size,
     };
 
     /* For now, no memory side cache, plausiblish numbers */
@@ -131,7 +134,7 @@ static void ct3_build_cdat_entries_for_mr(CDATSubHeader **cdat_table,
          */
         .EFI_memory_type_attr = is_pmem ? 2 : 1,
         .DPA_offset = 0,
-        .DPA_length = memory_region_size(mr),
+        .DPA_length = size,
     };
 
     /* Header always at start of structure */
@@ -148,11 +151,13 @@ static int ct3_build_cdat_table(CDATSubHeader ***cdat_table, void *priv)
     g_autofree CDATSubHeader **table = NULL;
     CXLType3Dev *ct3d = priv;
     MemoryRegion *volatile_mr = NULL, *nonvolatile_mr = NULL;
+    MemoryRegion *dc_mr = NULL;
+    uint64_t vmr_size = 0, pmr_size = 0;
     int dsmad_handle = 0;
     int cur_ent = 0;
     int len = 0;
 
-    if (!ct3d->hostpmem && !ct3d->hostvmem) {
+    if (!ct3d->hostpmem && !ct3d->hostvmem && !ct3d->dc.num_regions) {
         return 0;
     }
 
@@ -162,6 +167,7 @@ static int ct3_build_cdat_table(CDATSubHeader ***cdat_table, void *priv)
             return -EINVAL;
         }
         len += CT3_CDAT_NUM_ENTRIES;
+        vmr_size = memory_region_size(volatile_mr);
     }
 
     if (ct3d->hostpmem) {
@@ -170,23 +176,57 @@ static int ct3_build_cdat_table(CDATSubHeader ***cdat_table, void *priv)
             return -EINVAL;
         }
         len += CT3_CDAT_NUM_ENTRIES;
+        pmr_size = memory_region_size(nonvolatile_mr);
+    }
+
+    if (ct3d->dc.num_regions) {
+        if (!ct3d->dc.host_dc) {
+            return -EINVAL;
+        }
+        dc_mr = host_memory_backend_get_memory(ct3d->dc.host_dc);
+        if (!dc_mr) {
+            return -EINVAL;
+        }
+        len += CT3_CDAT_NUM_ENTRIES * ct3d->dc.num_regions;
     }
 
     table = g_malloc0(len * sizeof(*table));
 
     /* Now fill them in */
     if (volatile_mr) {
-        ct3_build_cdat_entries_for_mr(table, dsmad_handle++, volatile_mr,
+        ct3_build_cdat_entries_for_mr(table, dsmad_handle++, vmr_size,
-                                      false, 0);
+                                      false, false, 0);
         cur_ent = CT3_CDAT_NUM_ENTRIES;
     }
 
     if (nonvolatile_mr) {
-        uint64_t base = volatile_mr ? memory_region_size(volatile_mr) : 0;
+        uint64_t base = vmr_size;
         ct3_build_cdat_entries_for_mr(&(table[cur_ent]), dsmad_handle++,
-                                      nonvolatile_mr, true, base);
+                                      pmr_size, true, false, base);
         cur_ent += CT3_CDAT_NUM_ENTRIES;
     }
+
+    if (dc_mr) {
+        int i;
+        uint64_t region_base = vmr_size + pmr_size;
+
+        /*
+         * We assume the dynamic capacity to be volatile for now.
+         * Non-volatile dynamic capacity will be added if needed in the
+         * future.
+         */
+        for (i = 0; i < ct3d->dc.num_regions; i++) {
+            ct3_build_cdat_entries_for_mr(&(table[cur_ent]),
+                                          dsmad_handle++,
+                                          ct3d->dc.regions[i].len,
+                                          false, true, region_base);
+            ct3d->dc.regions[i].dsmadhandle = dsmad_handle - 1;
+
+            cur_ent += CT3_CDAT_NUM_ENTRIES;
+            region_base += ct3d->dc.regions[i].len;
+        }
+    }
+
     assert(len == cur_ent);
 
     *cdat_table = g_steal_pointer(&table);
@@ -297,10 +337,17 @@ static void build_dvsecs(CXLType3Dev *ct3d)
             range2_size_lo = (2 << 5) | (2 << 2) | 0x3 |
                              (ct3d->hostpmem->size & 0xF0000000);
         }
-    } else {
+    } else if (ct3d->hostpmem) {
         range1_size_hi = ct3d->hostpmem->size >> 32;
         range1_size_lo = (2 << 5) | (2 << 2) | 0x3 |
                          (ct3d->hostpmem->size & 0xF0000000);
+    } else {
+        /*
+         * For DCD with no static memory, set memory active, memory class bits.
+         * No range is set.
+         */
+        range1_size_hi = 0;
+        range1_size_lo = (2 << 5) | (2 << 2) | 0x3;
     }
 
     dvsec = (uint8_t *)&(CXLDVSECDevice){
@@ -567,11 +614,103 @@ static void ct3d_reg_write(void *opaque, hwaddr offset, uint64_t value,
     }
 }
 
+/*
+ * TODO: dc region configuration will be updated once host backend and address
+ * space support is added for DCD.
+ */
+static bool cxl_create_dc_regions(CXLType3Dev *ct3d, Error **errp)
+{
+    int i;
+    uint64_t region_base = 0;
+    uint64_t region_len;
+    uint64_t decode_len;
+    uint64_t blk_size = 2 * MiB;
+    CXLDCRegion *region;
+    MemoryRegion *mr;
+    uint64_t dc_size;
+
+    mr = host_memory_backend_get_memory(ct3d->dc.host_dc);
+    dc_size = memory_region_size(mr);
+    region_len = DIV_ROUND_UP(dc_size, ct3d->dc.num_regions);
+
+    if (dc_size % (ct3d->dc.num_regions * CXL_CAPACITY_MULTIPLIER) != 0) {
+        error_setg(errp,
+                   "backend size is not multiple of region len: 0x%" PRIx64,
+                   region_len);
+        return false;
+    }
+    if (region_len % CXL_CAPACITY_MULTIPLIER != 0) {
+        error_setg(errp, "DC region size is unaligned to 0x%" PRIx64,
+                   CXL_CAPACITY_MULTIPLIER);
+        return false;
+    }
+    decode_len = region_len;
+
+    if (ct3d->hostvmem) {
+        mr = host_memory_backend_get_memory(ct3d->hostvmem);
+        region_base += memory_region_size(mr);
+    }
+    if (ct3d->hostpmem) {
+        mr = host_memory_backend_get_memory(ct3d->hostpmem);
+        region_base += memory_region_size(mr);
+    }
+    if (region_base % CXL_CAPACITY_MULTIPLIER != 0) {
+        error_setg(errp, "DC region base not aligned to 0x%" PRIx64,
+                   CXL_CAPACITY_MULTIPLIER);
+        return false;
+    }
+
+    for (i = 0, region = &ct3d->dc.regions[0];
+         i < ct3d->dc.num_regions;
+         i++, region++, region_base += region_len) {
+        *region = (CXLDCRegion) {
+            .base = region_base,
+            .decode_len = decode_len,
+            .len = region_len,
+            .block_size = blk_size,
+            /* dsmad_handle set when creating CDAT table entries */
+            .flags = 0,
+        };
+        ct3d->dc.total_capacity += region->len;
+        region->blk_bitmap = bitmap_new(region->len / region->block_size);
+    }
+    QTAILQ_INIT(&ct3d->dc.extents);
+    QTAILQ_INIT(&ct3d->dc.extents_pending);
+
+    return true;
+}
+
+static void cxl_destroy_dc_regions(CXLType3Dev *ct3d)
+{
+    CXLDCExtent *ent, *ent_next;
+    CXLDCExtentGroup *group, *group_next;
+    int i;
+    CXLDCRegion *region;
+
+    QTAILQ_FOREACH_SAFE(ent, &ct3d->dc.extents, node, ent_next) {
+        cxl_remove_extent_from_extent_list(&ct3d->dc.extents, ent);
+    }
+
+    QTAILQ_FOREACH_SAFE(group, &ct3d->dc.extents_pending, node, group_next) {
+        QTAILQ_REMOVE(&ct3d->dc.extents_pending, group, node);
+        QTAILQ_FOREACH_SAFE(ent, &group->list, node, ent_next) {
+            cxl_remove_extent_from_extent_list(&group->list, ent);
+        }
+        g_free(group);
+    }
+
+    for (i = 0; i < ct3d->dc.num_regions; i++) {
+        region = &ct3d->dc.regions[i];
+        g_free(region->blk_bitmap);
+    }
+}
+
 static bool cxl_setup_memory(CXLType3Dev *ct3d, Error **errp)
 {
     DeviceState *ds = DEVICE(ct3d);
 
-    if (!ct3d->hostmem && !ct3d->hostvmem && !ct3d->hostpmem) {
+    if (!ct3d->hostmem && !ct3d->hostvmem && !ct3d->hostpmem
+        && !ct3d->dc.num_regions) {
         error_setg(errp, "at least one memdev property must be set");
         return false;
     } else if (ct3d->hostmem && ct3d->hostpmem) {
@@ -608,7 +747,7 @@ static bool cxl_setup_memory(CXLType3Dev *ct3d, Error **errp)
         }
         address_space_init(&ct3d->hostvmem_as, vmr, v_name);
         ct3d->cxl_dstate.vmem_size = memory_region_size(vmr);
-        ct3d->cxl_dstate.mem_size += memory_region_size(vmr);
+        ct3d->cxl_dstate.static_mem_size += memory_region_size(vmr);
         g_free(v_name);
     }
 
@@ -631,10 +770,47 @@ static bool cxl_setup_memory(CXLType3Dev *ct3d, Error **errp)
         }
         address_space_init(&ct3d->hostpmem_as, pmr, p_name);
         ct3d->cxl_dstate.pmem_size = memory_region_size(pmr);
-        ct3d->cxl_dstate.mem_size += memory_region_size(pmr);
+        ct3d->cxl_dstate.static_mem_size += memory_region_size(pmr);
         g_free(p_name);
     }
 
+    ct3d->dc.total_capacity = 0;
+    if (ct3d->dc.num_regions > 0) {
+        MemoryRegion *dc_mr;
+        char *dc_name;
+
+        if (!ct3d->dc.host_dc) {
+            error_setg(errp, "dynamic capacity must have a backing device");
+            return false;
+        }
+
+        dc_mr = host_memory_backend_get_memory(ct3d->dc.host_dc);
+        if (!dc_mr) {
+            error_setg(errp, "dynamic capacity must have a backing device");
+            return false;
+        }
+
+        /*
+         * Set DC regions as volatile for now, non-volatile support can
+         * be added in the future if needed.
+         */
+        memory_region_set_nonvolatile(dc_mr, false);
+        memory_region_set_enabled(dc_mr, true);
+        host_memory_backend_set_mapped(ct3d->dc.host_dc, true);
+        if (ds->id) {
+            dc_name = g_strdup_printf("cxl-dcd-dpa-dc-space:%s", ds->id);
+        } else {
+            dc_name = g_strdup("cxl-dcd-dpa-dc-space");
+        }
+        address_space_init(&ct3d->dc.host_dc_as, dc_mr, dc_name);
+        g_free(dc_name);
+
+        if (!cxl_create_dc_regions(ct3d, errp)) {
+            error_append_hint(errp, "setup DC regions failed");
+            return false;
+        }
+    }
+
     return true;
 }
 
@@ -724,6 +900,10 @@ err_release_cdat:
 err_free_special_ops:
     g_free(regs->special_ops);
 err_address_space_free:
+    if (ct3d->dc.host_dc) {
+        cxl_destroy_dc_regions(ct3d);
+        address_space_destroy(&ct3d->dc.host_dc_as);
+    }
     if (ct3d->hostpmem) {
         address_space_destroy(&ct3d->hostpmem_as);
     }
@@ -742,6 +922,10 @@ static void ct3_exit(PCIDevice *pci_dev)
     pcie_aer_exit(pci_dev);
     cxl_doe_cdat_release(cxl_cstate);
     g_free(regs->special_ops);
+    if (ct3d->dc.host_dc) {
+        cxl_destroy_dc_regions(ct3d);
+        address_space_destroy(&ct3d->dc.host_dc_as);
+    }
     if (ct3d->hostpmem) {
         address_space_destroy(&ct3d->hostpmem_as);
     }
@@ -750,6 +934,70 @@ static void ct3_exit(PCIDevice *pci_dev)
     }
 }
 
+/*
+ * Mark the DPA range [dpa, dap + len - 1] to be backed and accessible. This
+ * happens when a DC extent is added and accepted by the host.
+ */
+void ct3_set_region_block_backed(CXLType3Dev *ct3d, uint64_t dpa,
+                                 uint64_t len)
+{
+    CXLDCRegion *region;
+
+    region = cxl_find_dc_region(ct3d, dpa, len);
+    if (!region) {
+        return;
+    }
+
+    bitmap_set(region->blk_bitmap, (dpa - region->base) / region->block_size,
+               len / region->block_size);
+}
+
+/*
+ * Check whether the DPA range [dpa, dpa + len - 1] is backed with DC extents.
+ * Used when validating read/write to dc regions
+ */
+bool ct3_test_region_block_backed(CXLType3Dev *ct3d, uint64_t dpa,
+                                  uint64_t len)
+{
+    CXLDCRegion *region;
+    uint64_t nbits;
+    long nr;
+
+    region = cxl_find_dc_region(ct3d, dpa, len);
+    if (!region) {
+        return false;
+    }
+
+    nr = (dpa - region->base) / region->block_size;
+    nbits = DIV_ROUND_UP(len, region->block_size);
+    /*
+     * if bits between [dpa, dpa + len) are all 1s, meaning the DPA range is
+     * backed with DC extents, return true; else return false.
+     */
+    return find_next_zero_bit(region->blk_bitmap, nr + nbits, nr) == nr + nbits;
+}
+
+/*
+ * Mark the DPA range [dpa, dap + len - 1] to be unbacked and inaccessible.
+ * This happens when a dc extent is released by the host.
+ */
+void ct3_clear_region_block_backed(CXLType3Dev *ct3d, uint64_t dpa,
+                                   uint64_t len)
+{
+    CXLDCRegion *region;
+    uint64_t nbits;
+    long nr;
+
+    region = cxl_find_dc_region(ct3d, dpa, len);
+    if (!region) {
+        return;
+    }
+
+    nr = (dpa - region->base) / region->block_size;
+    nbits = len / region->block_size;
+    bitmap_clear(region->blk_bitmap, nr, nbits);
+}
+
 static bool cxl_type3_dpa(CXLType3Dev *ct3d, hwaddr host_addr, uint64_t *dpa)
 {
     int hdm_inc = R_CXL_HDM_DECODER1_BASE_LO - R_CXL_HDM_DECODER0_BASE_LO;
@@ -820,16 +1068,23 @@ static int cxl_type3_hpa_to_as_and_dpa(CXLType3Dev *ct3d,
                                        AddressSpace **as,
                                        uint64_t *dpa_offset)
 {
-    MemoryRegion *vmr = NULL, *pmr = NULL;
+    MemoryRegion *vmr = NULL, *pmr = NULL, *dc_mr = NULL;
+    uint64_t vmr_size = 0, pmr_size = 0, dc_size = 0;
 
     if (ct3d->hostvmem) {
         vmr = host_memory_backend_get_memory(ct3d->hostvmem);
+        vmr_size = memory_region_size(vmr);
     }
     if (ct3d->hostpmem) {
         pmr = host_memory_backend_get_memory(ct3d->hostpmem);
+        pmr_size = memory_region_size(pmr);
+    }
+    if (ct3d->dc.host_dc) {
+        dc_mr = host_memory_backend_get_memory(ct3d->dc.host_dc);
+        dc_size = memory_region_size(dc_mr);
     }
 
-    if (!vmr && !pmr) {
+    if (!vmr && !pmr && !dc_mr) {
         return -ENODEV;
     }
 
@@ -837,19 +1092,22 @@ static int cxl_type3_hpa_to_as_and_dpa(CXLType3Dev *ct3d,
         return -EINVAL;
     }
 
-    if (*dpa_offset > ct3d->cxl_dstate.mem_size) {
+    if (*dpa_offset >= vmr_size + pmr_size + dc_size) {
         return -EINVAL;
     }
 
-    if (vmr) {
+    if (*dpa_offset < vmr_size) {
-        if (*dpa_offset < memory_region_size(vmr)) {
+        *as = &ct3d->hostvmem_as;
-            *as = &ct3d->hostvmem_as;
+    } else if (*dpa_offset < vmr_size + pmr_size) {
-        } else {
-            *as = &ct3d->hostpmem_as;
-            *dpa_offset -= memory_region_size(vmr);
-        }
-    } else {
         *as = &ct3d->hostpmem_as;
+        *dpa_offset -= vmr_size;
+    } else {
+        if (!ct3_test_region_block_backed(ct3d, *dpa_offset, size)) {
+            return -ENODEV;
+        }
+
+        *as = &ct3d->dc.host_dc_as;
+        *dpa_offset -= (vmr_size + pmr_size);
     }
 
     return 0;
@@ -930,6 +1188,9 @@ static Property ct3_props[] = {
                      HostMemoryBackend *),
     DEFINE_PROP_UINT64("sn", CXLType3Dev, sn, UI64_NULL),
     DEFINE_PROP_STRING("cdat", CXLType3Dev, cxl_cstate.cdat.filename),
+    DEFINE_PROP_UINT8("num-dc-regions", CXLType3Dev, dc.num_regions, 0),
+    DEFINE_PROP_LINK("volatile-dc-memdev", CXLType3Dev, dc.host_dc,
+                     TYPE_MEMORY_BACKEND, HostMemoryBackend *),
     DEFINE_PROP_END_OF_LIST(),
 };
 
@@ -996,36 +1257,42 @@ static void set_lsa(CXLType3Dev *ct3d, const void *buf, uint64_t size,
 
 static bool set_cacheline(CXLType3Dev *ct3d, uint64_t dpa_offset, uint8_t *data)
 {
-    MemoryRegion *vmr = NULL, *pmr = NULL;
+    MemoryRegion *vmr = NULL, *pmr = NULL, *dc_mr = NULL;
     AddressSpace *as;
+    uint64_t vmr_size = 0, pmr_size = 0, dc_size = 0;
 
     if (ct3d->hostvmem) {
         vmr = host_memory_backend_get_memory(ct3d->hostvmem);
+        vmr_size = memory_region_size(vmr);
     }
     if (ct3d->hostpmem) {
         pmr = host_memory_backend_get_memory(ct3d->hostpmem);
+        pmr_size = memory_region_size(pmr);
     }
+    if (ct3d->dc.host_dc) {
+        dc_mr = host_memory_backend_get_memory(ct3d->dc.host_dc);
+        dc_size = memory_region_size(dc_mr);
+     }
 
-    if (!vmr && !pmr) {
+    if (!vmr && !pmr && !dc_mr) {
         return false;
     }
 
-    if (dpa_offset + CXL_CACHE_LINE_SIZE > ct3d->cxl_dstate.mem_size) {
+    if (dpa_offset + CXL_CACHE_LINE_SIZE > vmr_size + pmr_size + dc_size) {
         return false;
     }
 
-    if (vmr) {
+    if (dpa_offset < vmr_size) {
-        if (dpa_offset < memory_region_size(vmr)) {
+        as = &ct3d->hostvmem_as;
-            as = &ct3d->hostvmem_as;
+    } else if (dpa_offset < vmr_size + pmr_size) {
-        } else {
-            as = &ct3d->hostpmem_as;
-            dpa_offset -= memory_region_size(vmr);
-        }
-    } else {
         as = &ct3d->hostpmem_as;
+        dpa_offset -= vmr_size;
+    } else {
+        as = &ct3d->dc.host_dc_as;
+        dpa_offset -= (vmr_size + pmr_size);
     }
 
-    address_space_write(as, dpa_offset, MEMTXATTRS_UNSPECIFIED, &data,
+    address_space_write(as, dpa_offset, MEMTXATTRS_UNSPECIFIED, data,
                         CXL_CACHE_LINE_SIZE);
     return true;
 }
@@ -1268,7 +1535,6 @@ static int ct3d_qmp_cxl_event_log_enc(CxlEventLog log)
         return CXL_EVENT_TYPE_FAIL;
     case CXL_EVENT_LOG_FATAL:
         return CXL_EVENT_TYPE_FATAL;
-/* DCD not yet supported */
     default:
         return -EINVAL;
     }
@@ -1519,6 +1785,301 @@ void qmp_cxl_inject_memory_module_event(const char *path, CxlEventLog log,
     }
 }
 
+/* CXL r3.1 Table 8-50: Dynamic Capacity Event Record */
+static const QemuUUID dynamic_capacity_uuid = {
+    .data = UUID(0xca95afa7, 0xf183, 0x4018, 0x8c, 0x2f,
+                 0x95, 0x26, 0x8e, 0x10, 0x1a, 0x2a),
+};
+
+typedef enum CXLDCEventType {
+    DC_EVENT_ADD_CAPACITY = 0x0,
+    DC_EVENT_RELEASE_CAPACITY = 0x1,
+    DC_EVENT_FORCED_RELEASE_CAPACITY = 0x2,
+    DC_EVENT_REGION_CONFIG_UPDATED = 0x3,
+    DC_EVENT_ADD_CAPACITY_RSP = 0x4,
+    DC_EVENT_CAPACITY_RELEASED = 0x5,
+} CXLDCEventType;
+
+/*
+ * Check whether the range [dpa, dpa + len - 1] has overlaps with extents in
+ * the list.
+ * Return value: return true if has overlaps; otherwise, return false
+ */
+static bool cxl_extents_overlaps_dpa_range(CXLDCExtentList *list,
+                                           uint64_t dpa, uint64_t len)
+{
+    CXLDCExtent *ent;
+    Range range1, range2;
+
+    if (!list) {
+        return false;
+    }
+
+    range_init_nofail(&range1, dpa, len);
+    QTAILQ_FOREACH(ent, list, node) {
+        range_init_nofail(&range2, ent->start_dpa, ent->len);
+        if (range_overlaps_range(&range1, &range2)) {
+            return true;
+        }
+    }
+    return false;
+}
+
+/*
+ * Check whether the range [dpa, dpa + len - 1] is contained by extents in
+ * the list.
+ * Will check multiple extents containment once superset release is added.
+ * Return value: return true if range is contained; otherwise, return false
+ */
+bool cxl_extents_contains_dpa_range(CXLDCExtentList *list,
+                                    uint64_t dpa, uint64_t len)
+{
+    CXLDCExtent *ent;
+    Range range1, range2;
+
+    if (!list) {
+        return false;
+    }
+
+    range_init_nofail(&range1, dpa, len);
+    QTAILQ_FOREACH(ent, list, node) {
+        range_init_nofail(&range2, ent->start_dpa, ent->len);
+        if (range_contains_range(&range2, &range1)) {
+            return true;
+        }
+    }
+    return false;
+}
+
+static bool cxl_extent_groups_overlaps_dpa_range(CXLDCExtentGroupList *list,
+                                                 uint64_t dpa, uint64_t len)
+{
+    CXLDCExtentGroup *group;
+
+    if (!list) {
+        return false;
+    }
+
+    QTAILQ_FOREACH(group, list, node) {
+        if (cxl_extents_overlaps_dpa_range(&group->list, dpa, len)) {
+            return true;
+        }
+    }
+    return false;
+}
+
+/*
+ * The main function to process dynamic capacity event with extent list.
+ * Currently DC extents add/release requests are processed.
+ */
+static void qmp_cxl_process_dynamic_capacity_prescriptive(const char *path,
+        uint16_t hid, CXLDCEventType type, uint8_t rid,
+        CxlDynamicCapacityExtentList *records, Error **errp)
+{
+    Object *obj;
+    CXLEventDynamicCapacity dCap = {};
+    CXLEventRecordHdr *hdr = &dCap.hdr;
+    CXLType3Dev *dcd;
+    uint8_t flags = 1 << CXL_EVENT_TYPE_INFO;
+    uint32_t num_extents = 0;
+    CxlDynamicCapacityExtentList *list;
+    CXLDCExtentGroup *group = NULL;
+    g_autofree CXLDCExtentRaw *extents = NULL;
+    uint8_t enc_log = CXL_EVENT_TYPE_DYNAMIC_CAP;
+    uint64_t dpa, offset, len, block_size;
+    g_autofree unsigned long *blk_bitmap = NULL;
+    int i;
+
+    obj = object_resolve_path_type(path, TYPE_CXL_TYPE3, NULL);
+    if (!obj) {
+        error_setg(errp, "Unable to resolve CXL type 3 device");
+        return;
+    }
+
+    dcd = CXL_TYPE3(obj);
+    if (!dcd->dc.num_regions) {
+        error_setg(errp, "No dynamic capacity support from the device");
+        return;
+    }
+
+
+    if (rid >= dcd->dc.num_regions) {
+        error_setg(errp, "region id is too large");
+        return;
+    }
+    block_size = dcd->dc.regions[rid].block_size;
+    blk_bitmap = bitmap_new(dcd->dc.regions[rid].len / block_size);
+
+    /* Sanity check and count the extents */
+    list = records;
+    while (list) {
+        offset = list->value->offset;
+        len = list->value->len;
+        dpa = offset + dcd->dc.regions[rid].base;
+
+        if (len == 0) {
+            error_setg(errp, "extent with 0 length is not allowed");
+            return;
+        }
+
+        if (offset % block_size || len % block_size) {
+            error_setg(errp, "dpa or len is not aligned to region block size");
+            return;
+        }
+
+        if (offset + len > dcd->dc.regions[rid].len) {
+            error_setg(errp, "extent range is beyond the region end");
+            return;
+        }
+
+        /* No duplicate or overlapped extents are allowed */
+        if (test_any_bits_set(blk_bitmap, offset / block_size,
+                              len / block_size)) {
+            error_setg(errp, "duplicate or overlapped extents are detected");
+            return;
+        }
+        bitmap_set(blk_bitmap, offset / block_size, len / block_size);
+
+        if (type == DC_EVENT_RELEASE_CAPACITY) {
+            if (cxl_extent_groups_overlaps_dpa_range(&dcd->dc.extents_pending,
+                                                     dpa, len)) {
+                error_setg(errp,
+                           "cannot release extent with pending DPA range");
+                return;
+            }
+            if (!ct3_test_region_block_backed(dcd, dpa, len)) {
+                error_setg(errp,
+                           "cannot release extent with non-existing DPA range");
+                return;
+            }
+        } else if (type == DC_EVENT_ADD_CAPACITY) {
+            if (cxl_extents_overlaps_dpa_range(&dcd->dc.extents, dpa, len)) {
+                error_setg(errp,
+                           "cannot add DPA already accessible to the same LD");
+                return;
+            }
+            if (cxl_extent_groups_overlaps_dpa_range(&dcd->dc.extents_pending,
+                                                     dpa, len)) {
+                error_setg(errp,
+                           "cannot add DPA again while still pending");
+                return;
+            }
+        }
+        list = list->next;
+        num_extents++;
+    }
+
+    /* Create extent list for event being passed to host */
+    i = 0;
+    list = records;
+    extents = g_new0(CXLDCExtentRaw, num_extents);
+    while (list) {
+        offset = list->value->offset;
+        len = list->value->len;
+        dpa = dcd->dc.regions[rid].base + offset;
+
+        extents[i].start_dpa = dpa;
+        extents[i].len = len;
+        memset(extents[i].tag, 0, 0x10);
+        extents[i].shared_seq = 0;
+        if (type == DC_EVENT_ADD_CAPACITY) {
+            group = cxl_insert_extent_to_extent_group(group,
+                                                      extents[i].start_dpa,
+                                                      extents[i].len,
+                                                      extents[i].tag,
+                                                      extents[i].shared_seq);
+        }
+
+        list = list->next;
+        i++;
+    }
+    if (group) {
+        cxl_extent_group_list_insert_tail(&dcd->dc.extents_pending, group);
+    }
+
+    /*
+     * CXL r3.1 section 8.2.9.2.1.6: Dynamic Capacity Event Record
+     *
+     * All Dynamic Capacity event records shall set the Event Record Severity
+     * field in the Common Event Record Format to Informational Event. All
+     * Dynamic Capacity related events shall be logged in the Dynamic Capacity
+     * Event Log.
+     */
+    cxl_assign_event_header(hdr, &dynamic_capacity_uuid, flags, sizeof(dCap),
+                            cxl_device_get_timestamp(&dcd->cxl_dstate));
+
+    dCap.type = type;
+    /* FIXME: for now, validity flag is cleared */
+    dCap.validity_flags = 0;
+    stw_le_p(&dCap.host_id, hid);
+    /* only valid for DC_REGION_CONFIG_UPDATED event */
+    dCap.updated_region_id = 0;
+    dCap.flags = 0;
+    for (i = 0; i < num_extents; i++) {
+        memcpy(&dCap.dynamic_capacity_extent, &extents[i],
+               sizeof(CXLDCExtentRaw));
+
+        if (i < num_extents - 1) {
+            /* Set "More" flag */
+            dCap.flags |= BIT(0);
+        }
+
+        if (cxl_event_insert(&dcd->cxl_dstate, enc_log,
+                             (CXLEventRecordRaw *)&dCap)) {
+            cxl_event_irq_assert(dcd);
+        }
+    }
+}
+
+void qmp_cxl_add_dynamic_capacity(const char *path, uint16_t host_id,
+                                  CxlExtentSelectionPolicy sel_policy,
+                                  uint8_t region, const char *tag,
+                                  CxlDynamicCapacityExtentList  *extents,
+                                  Error **errp)
+{
+    switch (sel_policy) {
+    case CXL_EXTENT_SELECTION_POLICY_PRESCRIPTIVE:
+        qmp_cxl_process_dynamic_capacity_prescriptive(path, host_id,
+                                                      DC_EVENT_ADD_CAPACITY,
+                                                      region, extents, errp);
+        return;
+    default:
+        error_setg(errp, "Selection policy not supported");
+        return;
+    }
+}
+
+void qmp_cxl_release_dynamic_capacity(const char *path, uint16_t host_id,
+                                      CxlExtentRemovalPolicy removal_policy,
+                                      bool has_forced_removal,
+                                      bool forced_removal,
+                                      bool has_sanitize_on_release,
+                                      bool sanitize_on_release,
+                                      uint8_t region,
+                                      const char *tag,
+                                      CxlDynamicCapacityExtentList  *extents,
+                                      Error **errp)
+{
+    CXLDCEventType type = DC_EVENT_RELEASE_CAPACITY;
+
+    if (has_forced_removal && forced_removal) {
+        /* TODO: enable forced removal in the future */
+        type = DC_EVENT_FORCED_RELEASE_CAPACITY;
+        error_setg(errp, "Forced removal not supported yet");
+        return;
+    }
+
+    switch (removal_policy) {
+    case CXL_EXTENT_REMOVAL_POLICY_PRESCRIPTIVE:
+        qmp_cxl_process_dynamic_capacity_prescriptive(path, host_id, type,
+                                                      region, extents, errp);
+        return;
+    default:
+        error_setg(errp, "Removal policy not supported");
+        return;
+    }
+}
+
 static void ct3_class_init(ObjectClass *oc, void *data)
 {
     DeviceClass *dc = DEVICE_CLASS(oc);

hw/mem/cxl_type3_stubs.c

@@ -67,3 +67,28 @@ void qmp_cxl_inject_correctable_error(const char *path, CxlCorErrorType type,
 {
     error_setg(errp, "CXL Type 3 support is not compiled in");
 }
+
+void qmp_cxl_add_dynamic_capacity(const char *path,
+                                  uint16_t host_id,
+                                  CxlExtentSelectionPolicy sel_policy,
+                                  uint8_t region,
+                                  const char *tag,
+                                  CxlDynamicCapacityExtentList *extents,
+                                  Error **errp)
+{
+    error_setg(errp, "CXL Type 3 support is not compiled in");
+}
+
+void qmp_cxl_release_dynamic_capacity(const char *path, uint16_t host_id,
+                                      CxlExtentRemovalPolicy removal_policy,
+                                      bool has_forced_removal,
+                                      bool forced_removal,
+                                      bool has_sanitize_on_release,
+                                      bool sanitize_on_release,
+                                      uint8_t region,
+                                      const char *tag,
+                                      CxlDynamicCapacityExtentList *extents,
+                                      Error **errp)
+{
+    error_setg(errp, "CXL Type 3 support is not compiled in");
+}

hw/misc/pvpanic-isa.c

@@ -21,7 +21,6 @@
 #include "hw/misc/pvpanic.h"
 #include "qom/object.h"
 #include "hw/isa/isa.h"
-#include "standard-headers/misc/pvpanic.h"
 #include "hw/acpi/acpi_aml_interface.h"
 
 OBJECT_DECLARE_SIMPLE_TYPE(PVPanicISAState, PVPANIC_ISA_DEVICE)
@@ -102,7 +101,7 @@ static void build_pvpanic_isa_aml(AcpiDevAmlIf *adev, Aml *scope)
 static Property pvpanic_isa_properties[] = {
     DEFINE_PROP_UINT16(PVPANIC_IOPORT_PROP, PVPanicISAState, ioport, 0x505),
     DEFINE_PROP_UINT8("events", PVPanicISAState, pvpanic.events,
-                      PVPANIC_PANICKED | PVPANIC_CRASH_LOADED),
+                      PVPANIC_EVENTS),
     DEFINE_PROP_END_OF_LIST(),
 };
 

hw/misc/pvpanic-pci.c

@@ -55,7 +55,7 @@ static void pvpanic_pci_realizefn(PCIDevice *dev, Error **errp)
 
 static Property pvpanic_pci_properties[] = {
     DEFINE_PROP_UINT8("events", PVPanicPCIState, pvpanic.events,
-                      PVPANIC_PANICKED | PVPANIC_CRASH_LOADED),
+                      PVPANIC_EVENTS),
     DEFINE_PROP_END_OF_LIST(),
 };
 

hw/misc/pvpanic.c

@@ -27,7 +27,7 @@ static void handle_event(int event)
 {
     static bool logged;
 
-    if (event & ~(PVPANIC_PANICKED | PVPANIC_CRASH_LOADED) && !logged) {
+    if (event & ~PVPANIC_EVENTS && !logged) {
         qemu_log_mask(LOG_GUEST_ERROR, "pvpanic: unknown event %#x.\n", event);
         logged = true;
     }
@@ -41,6 +41,11 @@ static void handle_event(int event)
         qemu_system_guest_crashloaded(NULL);
         return;
     }
+
+    if (event & PVPANIC_SHUTDOWN) {
+        qemu_system_guest_pvshutdown();
+        return;
+    }
 }
 
 /* return supported events on read */

hw/net/igb.c

@@ -446,9 +446,16 @@ static void igb_pci_realize(PCIDevice *pci_dev, Error **errp)
 
     pcie_ari_init(pci_dev, 0x150);
 
-    pcie_sriov_pf_init(pci_dev, IGB_CAP_SRIOV_OFFSET, TYPE_IGBVF,
+    if (!pcie_sriov_pf_init(pci_dev, IGB_CAP_SRIOV_OFFSET,
-        IGB_82576_VF_DEV_ID, IGB_MAX_VF_FUNCTIONS, IGB_MAX_VF_FUNCTIONS,
+                            TYPE_IGBVF, IGB_82576_VF_DEV_ID,
-        IGB_VF_OFFSET, IGB_VF_STRIDE);
+                            IGB_MAX_VF_FUNCTIONS, IGB_MAX_VF_FUNCTIONS,
+                            IGB_VF_OFFSET, IGB_VF_STRIDE,
+                            errp)) {
+        pcie_cap_exit(pci_dev);
+        igb_cleanup_msix(s);
+        msi_uninit(pci_dev);
+        return;
+    }
 
     pcie_sriov_pf_init_vf_bar(pci_dev, IGBVF_MMIO_BAR_IDX,
         PCI_BASE_ADDRESS_MEM_TYPE_64 | PCI_BASE_ADDRESS_MEM_PREFETCH,

hw/net/vhost_net.c

@@ -48,6 +48,7 @@ static const int kernel_feature_bits[] = {
     VIRTIO_F_IOMMU_PLATFORM,
     VIRTIO_F_RING_PACKED,
     VIRTIO_F_RING_RESET,
+    VIRTIO_F_NOTIFICATION_DATA,
     VIRTIO_NET_F_HASH_REPORT,
     VHOST_INVALID_FEATURE_BIT
 };
@@ -55,6 +56,7 @@ static const int kernel_feature_bits[] = {
 /* Features supported by others. */
 static const int user_feature_bits[] = {
     VIRTIO_F_NOTIFY_ON_EMPTY,
+    VIRTIO_F_NOTIFICATION_DATA,
     VIRTIO_RING_F_INDIRECT_DESC,
     VIRTIO_RING_F_EVENT_IDX,
 

hw/net/virtio-net.c

@@ -2735,6 +2735,10 @@ static int32_t virtio_net_flush_tx(VirtIONetQueue *q)
          */
         assert(n->host_hdr_len <= n->guest_hdr_len);
         if (n->host_hdr_len != n->guest_hdr_len) {
+            if (iov_size(out_sg, out_num) < n->guest_hdr_len) {
+                virtio_error(vdev, "virtio-net header is invalid");
+                goto detach;
+            }
             unsigned sg_num = iov_copy(sg, ARRAY_SIZE(sg),
                                        out_sg, out_num,
                                        0, n->host_hdr_len);

hw/nvme/ctrl.c

@@ -8048,7 +8048,8 @@ out:
     return pow2ceil(bar_size);
 }
 
-static void nvme_init_sriov(NvmeCtrl *n, PCIDevice *pci_dev, uint16_t offset)
+static bool nvme_init_sriov(NvmeCtrl *n, PCIDevice *pci_dev, uint16_t offset,
+                            Error **errp)
 {
     uint16_t vf_dev_id = n->params.use_intel_id ?
                          PCI_DEVICE_ID_INTEL_NVME : PCI_DEVICE_ID_REDHAT_NVME;
@@ -8057,12 +8058,17 @@ static void nvme_init_sriov(NvmeCtrl *n, PCIDevice *pci_dev, uint16_t offset)
                                       le16_to_cpu(cap->vifrsm),
                                       NULL, NULL);
 
-    pcie_sriov_pf_init(pci_dev, offset, "nvme", vf_dev_id,
+    if (!pcie_sriov_pf_init(pci_dev, offset, "nvme", vf_dev_id,
-                       n->params.sriov_max_vfs, n->params.sriov_max_vfs,
+                            n->params.sriov_max_vfs, n->params.sriov_max_vfs,
-                       NVME_VF_OFFSET, NVME_VF_STRIDE);
+                            NVME_VF_OFFSET, NVME_VF_STRIDE,
+                            errp)) {
+        return false;
+    }
 
     pcie_sriov_pf_init_vf_bar(pci_dev, 0, PCI_BASE_ADDRESS_SPACE_MEMORY |
                               PCI_BASE_ADDRESS_MEM_TYPE_64, bar_size);
+
+    return true;
 }
 
 static int nvme_add_pm_capability(PCIDevice *pci_dev, uint8_t offset)
@@ -8155,6 +8161,12 @@ static bool nvme_init_pci(NvmeCtrl *n, PCIDevice *pci_dev, Error **errp)
         return false;
     }
 
+    if (!pci_is_vf(pci_dev) && n->params.sriov_max_vfs &&
+        !nvme_init_sriov(n, pci_dev, 0x120, errp)) {
+        msix_uninit(pci_dev, &n->bar0, &n->bar0);
+        return false;
+    }
+
     nvme_update_msixcap_ts(pci_dev, n->conf_msix_qsize);
 
     if (n->params.cmb_size_mb) {
@@ -8165,10 +8177,6 @@ static bool nvme_init_pci(NvmeCtrl *n, PCIDevice *pci_dev, Error **errp)
         nvme_init_pmr(n, pci_dev);
     }
 
-    if (!pci_is_vf(pci_dev) && n->params.sriov_max_vfs) {
-        nvme_init_sriov(n, pci_dev, 0x120);
-    }
-
     return true;
 }
 

hw/pci/pci.c

@@ -70,7 +70,7 @@ static bool pcie_has_upstream_port(PCIDevice *dev);
 static Property pci_props[] = {
     DEFINE_PROP_PCI_DEVFN("addr", PCIDevice, devfn, -1),
     DEFINE_PROP_STRING("romfile", PCIDevice, romfile),
-    DEFINE_PROP_UINT32("romsize", PCIDevice, romsize, -1),
+    DEFINE_PROP_UINT32("romsize", PCIDevice, romsize, UINT32_MAX),
     DEFINE_PROP_UINT32("rombar",  PCIDevice, rom_bar, 1),
     DEFINE_PROP_BIT("multifunction", PCIDevice, cap_present,
                     QEMU_PCI_CAP_MULTIFUNCTION_BITNR, false),
@@ -733,10 +733,17 @@ static bool migrate_is_not_pcie(void *opaque, int version_id)
     return !pci_is_express((PCIDevice *)opaque);
 }
 
+static int pci_post_load(void *opaque, int version_id)
+{
+    pcie_sriov_pf_post_load(opaque);
+    return 0;
+}
+
 const VMStateDescription vmstate_pci_device = {
     .name = "PCIDevice",
     .version_id = 2,
     .minimum_version_id = 1,
+    .post_load = pci_post_load,
     .fields = (const VMStateField[]) {
         VMSTATE_INT32_POSITIVE_LE(version_id, PCIDevice),
         VMSTATE_BUFFER_UNSAFE_INFO_TEST(config, PCIDevice,
@@ -1525,7 +1532,7 @@ static void pci_update_mappings(PCIDevice *d)
             continue;
 
         new_addr = pci_bar_address(d, i, r->type, r->size);
-        if (!d->has_power) {
+        if (!d->enabled) {
             new_addr = PCI_BAR_UNMAPPED;
         }
 
@@ -1613,7 +1620,7 @@ void pci_default_write_config(PCIDevice *d, uint32_t addr, uint32_t val_in, int
         pci_update_irq_disabled(d, was_irq_disabled);
         memory_region_set_enabled(&d->bus_master_enable_region,
                                   (pci_get_word(d->config + PCI_COMMAND)
-                                   & PCI_COMMAND_MASTER) && d->has_power);
+                                   & PCI_COMMAND_MASTER) && d->enabled);
     }
 
     msi_write_config(d, addr, val_in, l);
@@ -2066,7 +2073,7 @@ static void pci_qdev_realize(DeviceState *qdev, Error **errp)
                                  g_cmp_uint32, NULL);
     }
 
-    if (pci_dev->romsize != -1 && !is_power_of_2(pci_dev->romsize)) {
+    if (pci_dev->romsize != UINT32_MAX && !is_power_of_2(pci_dev->romsize)) {
         error_setg(errp, "ROM size %u is not a power of two", pci_dev->romsize);
         return;
     }
@@ -2352,7 +2359,7 @@ static void pci_add_option_rom(PCIDevice *pdev, bool is_default_rom,
         return;
     }
 
-    if (load_file || pdev->romsize == -1) {
+    if (load_file || pdev->romsize == UINT32_MAX) {
         path = qemu_find_file(QEMU_FILE_TYPE_BIOS, pdev->romfile);
         if (path == NULL) {
             path = g_strdup(pdev->romfile);
@@ -2371,7 +2378,7 @@ static void pci_add_option_rom(PCIDevice *pdev, bool is_default_rom,
                        pdev->romfile);
             return;
         }
-        if (pdev->romsize != -1) {
+        if (pdev->romsize != UINT_MAX) {
             if (size > pdev->romsize) {
                 error_setg(errp, "romfile \"%s\" (%u bytes) "
                            "is too large for ROM size %u",
@@ -2884,18 +2891,18 @@ MSIMessage pci_get_msi_message(PCIDevice *dev, int vector)
     return msg;
 }
 
-void pci_set_power(PCIDevice *d, bool state)
+void pci_set_enabled(PCIDevice *d, bool state)
 {
-    if (d->has_power == state) {
+    if (d->enabled == state) {
         return;
     }
 
-    d->has_power = state;
+    d->enabled = state;
     pci_update_mappings(d);
     memory_region_set_enabled(&d->bus_master_enable_region,
                               (pci_get_word(d->config + PCI_COMMAND)
-                               & PCI_COMMAND_MASTER) && d->has_power);
+                               & PCI_COMMAND_MASTER) && d->enabled);
-    if (!d->has_power) {
+    if (d->qdev.realized) {
         pci_device_reset(d);
     }
 }

hw/pci/pci_host.c

@@ -86,7 +86,7 @@ void pci_host_config_write_common(PCIDevice *pci_dev, uint32_t addr,
      * allowing direct removal of unexposed functions.
      */
     if ((pci_dev->qdev.hotplugged && !pci_get_function_0(pci_dev)) ||
-        !pci_dev->has_power || is_pci_dev_ejected(pci_dev)) {
+        !pci_dev->enabled || is_pci_dev_ejected(pci_dev)) {
         return;
     }
 
@@ -111,7 +111,7 @@ uint32_t pci_host_config_read_common(PCIDevice *pci_dev, uint32_t addr,
      * allowing direct removal of unexposed functions.
      */
     if ((pci_dev->qdev.hotplugged && !pci_get_function_0(pci_dev)) ||
-        !pci_dev->has_power || is_pci_dev_ejected(pci_dev)) {
+        !pci_dev->enabled || is_pci_dev_ejected(pci_dev)) {
         return ~0x0;
     }
 

hw/pci/pcie_sriov.c

@@ -20,23 +20,43 @@
 #include "qapi/error.h"
 #include "trace.h"
 
-static PCIDevice *register_vf(PCIDevice *pf, int devfn,
+static void unparent_vfs(PCIDevice *dev, uint16_t total_vfs)
-                              const char *name, uint16_t vf_num);
+{
-static void unregister_vfs(PCIDevice *dev);
+    for (uint16_t i = 0; i < total_vfs; i++) {
+        PCIDevice *vf = dev->exp.sriov_pf.vf[i];
+        object_unparent(OBJECT(vf));
+        object_unref(OBJECT(vf));
+    }
+    g_free(dev->exp.sriov_pf.vf);
+    dev->exp.sriov_pf.vf = NULL;
+}
 
-void pcie_sriov_pf_init(PCIDevice *dev, uint16_t offset,
+bool pcie_sriov_pf_init(PCIDevice *dev, uint16_t offset,
                         const char *vfname, uint16_t vf_dev_id,
                         uint16_t init_vfs, uint16_t total_vfs,
-                        uint16_t vf_offset, uint16_t vf_stride)
+                        uint16_t vf_offset, uint16_t vf_stride,
+                        Error **errp)
 {
+    BusState *bus = qdev_get_parent_bus(&dev->qdev);
+    int32_t devfn = dev->devfn + vf_offset;
     uint8_t *cfg = dev->config + offset;
     uint8_t *wmask;
 
+    if (total_vfs) {
+        uint16_t ari_cap = pcie_find_capability(dev, PCI_EXT_CAP_ID_ARI);
+        uint16_t first_vf_devfn = dev->devfn + vf_offset;
+        uint16_t last_vf_devfn = first_vf_devfn + vf_stride * (total_vfs - 1);
+
+        if ((!ari_cap && PCI_SLOT(dev->devfn) != PCI_SLOT(last_vf_devfn)) ||
+            last_vf_devfn >= PCI_DEVFN_MAX) {
+            error_setg(errp, "VF function number overflows");
+            return false;
+        }
+    }
+
     pcie_add_capability(dev, PCI_EXT_CAP_ID_SRIOV, 1,
                         offset, PCI_EXT_CAP_SRIOV_SIZEOF);
     dev->exp.sriov_cap = offset;
-    dev->exp.sriov_pf.num_vfs = 0;
-    dev->exp.sriov_pf.vfname = g_strdup(vfname);
     dev->exp.sriov_pf.vf = NULL;
 
     pci_set_word(cfg + PCI_SRIOV_VF_OFFSET, vf_offset);
@@ -69,13 +89,37 @@ void pcie_sriov_pf_init(PCIDevice *dev, uint16_t offset,
     pci_set_word(wmask + PCI_SRIOV_SYS_PGSIZE, 0x553);
 
     qdev_prop_set_bit(&dev->qdev, "multifunction", true);
+
+    dev->exp.sriov_pf.vf = g_new(PCIDevice *, total_vfs);
+
+    for (uint16_t i = 0; i < total_vfs; i++) {
+        PCIDevice *vf = pci_new(devfn, vfname);
+        vf->exp.sriov_vf.pf = dev;
+        vf->exp.sriov_vf.vf_number = i;
+
+        if (!qdev_realize(&vf->qdev, bus, errp)) {
+            object_unparent(OBJECT(vf));
+            object_unref(vf);
+            unparent_vfs(dev, i);
+            return false;
+        }
+
+        /* set vid/did according to sr/iov spec - they are not used */
+        pci_config_set_vendor_id(vf->config, 0xffff);
+        pci_config_set_device_id(vf->config, 0xffff);
+
+        dev->exp.sriov_pf.vf[i] = vf;
+        devfn += vf_stride;
+    }
+
+    return true;
 }
 
 void pcie_sriov_pf_exit(PCIDevice *dev)
 {
-    unregister_vfs(dev);
+    uint8_t *cfg = dev->config + dev->exp.sriov_cap;
-    g_free((char *)dev->exp.sriov_pf.vfname);
+
-    dev->exp.sriov_pf.vfname = NULL;
+    unparent_vfs(dev, pci_get_word(cfg + PCI_SRIOV_TOTAL_VF));
 }
 
 void pcie_sriov_pf_init_vf_bar(PCIDevice *dev, int region_num,
@@ -141,26 +185,10 @@ void pcie_sriov_vf_register_bar(PCIDevice *dev, int region_num,
     }
 }
 
-static PCIDevice *register_vf(PCIDevice *pf, int devfn, const char *name,
+static void clear_ctrl_vfe(PCIDevice *dev)
-                              uint16_t vf_num)
 {
-    PCIDevice *dev = pci_new(devfn, name);
+    uint8_t *ctrl = dev->config + dev->exp.sriov_cap + PCI_SRIOV_CTRL;
-    dev->exp.sriov_vf.pf = pf;
+    pci_set_word(ctrl, pci_get_word(ctrl) & ~PCI_SRIOV_CTRL_VFE);
-    dev->exp.sriov_vf.vf_number = vf_num;
-    PCIBus *bus = pci_get_bus(pf);
-    Error *local_err = NULL;
-
-    qdev_realize(&dev->qdev, &bus->qbus, &local_err);
-    if (local_err) {
-        error_report_err(local_err);
-        return NULL;
-    }
-
-    /* set vid/did according to sr/iov spec - they are not used */
-    pci_config_set_vendor_id(dev->config, 0xffff);
-    pci_config_set_device_id(dev->config, 0xffff);
-
-    return dev;
 }
 
 static void register_vfs(PCIDevice *dev)
@@ -168,53 +196,31 @@ static void register_vfs(PCIDevice *dev)
     uint16_t num_vfs;
     uint16_t i;
     uint16_t sriov_cap = dev->exp.sriov_cap;
-    uint16_t vf_offset =
-        pci_get_word(dev->config + sriov_cap + PCI_SRIOV_VF_OFFSET);
-    uint16_t vf_stride =
-        pci_get_word(dev->config + sriov_cap + PCI_SRIOV_VF_STRIDE);
-    int32_t devfn = dev->devfn + vf_offset;
 
     assert(sriov_cap > 0);
     num_vfs = pci_get_word(dev->config + sriov_cap + PCI_SRIOV_NUM_VF);
     if (num_vfs > pci_get_word(dev->config + sriov_cap + PCI_SRIOV_TOTAL_VF)) {
+        clear_ctrl_vfe(dev);
         return;
     }
 
-    dev->exp.sriov_pf.vf = g_new(PCIDevice *, num_vfs);
-
     trace_sriov_register_vfs(dev->name, PCI_SLOT(dev->devfn),
                              PCI_FUNC(dev->devfn), num_vfs);
     for (i = 0; i < num_vfs; i++) {
-        dev->exp.sriov_pf.vf[i] = register_vf(dev, devfn,
+        pci_set_enabled(dev->exp.sriov_pf.vf[i], true);
-                                              dev->exp.sriov_pf.vfname, i);
-        if (!dev->exp.sriov_pf.vf[i]) {
-            num_vfs = i;
-            break;
-        }
-        devfn += vf_stride;
     }
-    dev->exp.sriov_pf.num_vfs = num_vfs;
 }
 
 static void unregister_vfs(PCIDevice *dev)
 {
-    uint16_t num_vfs = dev->exp.sriov_pf.num_vfs;
     uint16_t i;
+    uint8_t *cfg = dev->config + dev->exp.sriov_cap;
 
     trace_sriov_unregister_vfs(dev->name, PCI_SLOT(dev->devfn),
-                               PCI_FUNC(dev->devfn), num_vfs);
+                               PCI_FUNC(dev->devfn));
-    for (i = 0; i < num_vfs; i++) {
+    for (i = 0; i < pci_get_word(cfg + PCI_SRIOV_TOTAL_VF); i++) {
-        Error *err = NULL;
+        pci_set_enabled(dev->exp.sriov_pf.vf[i], false);
-        PCIDevice *vf = dev->exp.sriov_pf.vf[i];
-        if (!object_property_set_bool(OBJECT(vf), "realized", false, &err)) {
-            error_reportf_err(err, "Failed to unplug: ");
-        }
-        object_unparent(OBJECT(vf));
-        object_unref(OBJECT(vf));
     }
-    g_free(dev->exp.sriov_pf.vf);
-    dev->exp.sriov_pf.vf = NULL;
-    dev->exp.sriov_pf.num_vfs = 0;
 }
 
 void pcie_sriov_config_write(PCIDevice *dev, uint32_t address,
@@ -235,15 +241,21 @@ void pcie_sriov_config_write(PCIDevice *dev, uint32_t address,
                              PCI_FUNC(dev->devfn), off, val, len);
 
     if (range_covers_byte(off, len, PCI_SRIOV_CTRL)) {
-        if (dev->exp.sriov_pf.num_vfs) {
+        if (val & PCI_SRIOV_CTRL_VFE) {
-            if (!(val & PCI_SRIOV_CTRL_VFE)) {
+            register_vfs(dev);
-                unregister_vfs(dev);
-            }
         } else {
-            if (val & PCI_SRIOV_CTRL_VFE) {
+            unregister_vfs(dev);
-                register_vfs(dev);
-            }
         }
+    } else if (range_covers_byte(off, len, PCI_SRIOV_NUM_VF)) {
+        clear_ctrl_vfe(dev);
+        unregister_vfs(dev);
+    }
+}
+
+void pcie_sriov_pf_post_load(PCIDevice *dev)
+{
+    if (dev->exp.sriov_cap) {
+        register_vfs(dev);
     }
 }
 
@@ -306,7 +318,7 @@ PCIDevice *pcie_sriov_get_pf(PCIDevice *dev)
 PCIDevice *pcie_sriov_get_vf_at_index(PCIDevice *dev, int n)
 {
     assert(!pci_is_vf(dev));
-    if (n < dev->exp.sriov_pf.num_vfs) {
+    if (n < pcie_sriov_num_vfs(dev)) {
         return dev->exp.sriov_pf.vf[n];
     }
     return NULL;
@@ -314,5 +326,10 @@ PCIDevice *pcie_sriov_get_vf_at_index(PCIDevice *dev, int n)
 
 uint16_t pcie_sriov_num_vfs(PCIDevice *dev)
 {
-    return dev->exp.sriov_pf.num_vfs;
+    uint16_t sriov_cap = dev->exp.sriov_cap;
+    uint8_t *cfg = dev->config + sriov_cap;
+
+    return sriov_cap &&
+           (pci_get_word(cfg + PCI_SRIOV_CTRL) & PCI_SRIOV_CTRL_VFE) ?
+           pci_get_word(cfg + PCI_SRIOV_NUM_VF) : 0;
 }

hw/pci/trace-events

@@ -14,7 +14,7 @@ msix_write_config(char *name, bool enabled, bool masked) "dev %s enabled %d mask
 
 # hw/pci/pcie_sriov.c
 sriov_register_vfs(const char *name, int slot, int function, int num_vfs) "%s %02x:%x: creating %d vf devs"
-sriov_unregister_vfs(const char *name, int slot, int function, int num_vfs) "%s %02x:%x: Unregistering %d vf devs"
+sriov_unregister_vfs(const char *name, int slot, int function) "%s %02x:%x: Unregistering vf devs"
 sriov_config_write(const char *name, int slot, int fun, uint32_t offset, uint32_t val, uint32_t len) "%s %02x:%x: sriov offset 0x%x val 0x%x len %d"
 
 # pcie.c

hw/ppc/spapr_pci.c

@@ -1296,6 +1296,10 @@ static void spapr_dt_pci_device_cb(PCIBus *bus, PCIDevice *pdev,
         return;
     }
 
+    if (!pdev->enabled) {
+        return;
+    }
+
     err = spapr_dt_pci_device(p->sphb, pdev, p->fdt, p->offset);
     if (err < 0) {
         p->err = err;
@@ -1569,7 +1573,9 @@ static void spapr_pci_pre_plug(HotplugHandler *plug_handler,
      * hotplug, we do not allow functions to be hotplugged to a
      * slot that already has function 0 present
      */
-    if (plugged_dev->hotplugged && bus->devices[PCI_DEVFN(slotnr, 0)] &&
+    if (plugged_dev->hotplugged &&
+        !pci_is_vf(pdev) &&
+        bus->devices[PCI_DEVFN(slotnr, 0)] &&
         PCI_FUNC(pdev->devfn) != 0) {
         error_setg(errp, "PCI: slot %d function 0 already occupied by %s,"
                    " additional functions can no longer be exposed to guest.",

hw/s390x/s390-virtio-ccw.c

@@ -127,9 +127,11 @@ static void subsystem_reset(void)
 static int virtio_ccw_hcall_notify(const uint64_t *args)
 {
     uint64_t subch_id = args[0];
-    uint64_t queue = args[1];
+    uint64_t data = args[1];
     SubchDev *sch;
+    VirtIODevice *vdev;
     int cssid, ssid, schid, m;
+    uint16_t vq_idx = data;
 
     if (ioinst_disassemble_sch_ident(subch_id, &m, &cssid, &ssid, &schid)) {
         return -EINVAL;
@@ -138,12 +140,19 @@ static int virtio_ccw_hcall_notify(const uint64_t *args)
     if (!sch || !css_subch_visible(sch)) {
         return -EINVAL;
     }
-    if (queue >= VIRTIO_QUEUE_MAX) {
+
+    vdev = virtio_ccw_get_vdev(sch);
+    if (vq_idx >= VIRTIO_QUEUE_MAX || !virtio_queue_get_num(vdev, vq_idx)) {
         return -EINVAL;
     }
-    virtio_queue_notify(virtio_ccw_get_vdev(sch), queue);
-    return 0;
 
+    if (virtio_vdev_has_feature(vdev, VIRTIO_F_NOTIFICATION_DATA)) {
+        virtio_queue_set_shadow_avail_idx(virtio_get_queue(vdev, vq_idx),
+                                          (data >> 16) & 0xFFFF);
+    }
+
+    virtio_queue_notify(vdev, vq_idx);
+    return 0;
 }
 
 static int virtio_ccw_hcall_early_printk(const uint64_t *args)

hw/scsi/vhost-scsi.c

@@ -38,6 +38,7 @@ static const int kernel_feature_bits[] = {
     VIRTIO_RING_F_EVENT_IDX,
     VIRTIO_SCSI_F_HOTPLUG,
     VIRTIO_F_RING_RESET,
+    VIRTIO_F_NOTIFICATION_DATA,
     VHOST_INVALID_FEATURE_BIT
 };
 

hw/scsi/vhost-user-scsi.c

@@ -36,6 +36,7 @@ static const int user_feature_bits[] = {
     VIRTIO_RING_F_EVENT_IDX,
     VIRTIO_SCSI_F_HOTPLUG,
     VIRTIO_F_RING_RESET,
+    VIRTIO_F_NOTIFICATION_DATA,
     VHOST_INVALID_FEATURE_BIT
 };
 
@@ -181,7 +182,7 @@ static void vhost_user_scsi_disconnect(DeviceState *dev)
     VirtIOSCSICommon *vs = VIRTIO_SCSI_COMMON(dev);
 
     if (!s->connected) {
-        return;
+        goto done;
     }
     s->connected = false;
 
@@ -189,6 +190,7 @@ static void vhost_user_scsi_disconnect(DeviceState *dev)
 
     vhost_dev_cleanup(&vsc->dev);
 
+done:
     /* Re-instate the event handler for new connections */
     qemu_chr_fe_set_handlers(&vs->conf.chardev, NULL, NULL,
                              vhost_user_scsi_event, NULL, dev, NULL, true);
@@ -214,8 +216,7 @@ static void vhost_user_scsi_event(void *opaque, QEMUChrEvent event)
     case CHR_EVENT_CLOSED:
         /* defer close until later to avoid circular close */
         vhost_user_async_close(dev, &vs->conf.chardev, &vsc->dev,
-                               vhost_user_scsi_disconnect,
+                               vhost_user_scsi_disconnect);
-                               vhost_user_scsi_event);
         break;
     case CHR_EVENT_BREAK:
     case CHR_EVENT_MUX_IN:

hw/virtio/vhost-user-base.c

@@ -223,15 +223,18 @@ static void vub_disconnect(DeviceState *dev)
 {
     VirtIODevice *vdev = VIRTIO_DEVICE(dev);
     VHostUserBase *vub = VHOST_USER_BASE(vdev);
+    struct vhost_virtqueue *vhost_vqs = vub->vhost_dev.vqs;
 
     if (!vub->connected) {
-        return;
+        goto done;
     }
     vub->connected = false;
 
     vub_stop(vdev);
     vhost_dev_cleanup(&vub->vhost_dev);
+    g_free(vhost_vqs);
 
+done:
     /* Re-instate the event handler for new connections */
     qemu_chr_fe_set_handlers(&vub->chardev,
                              NULL, NULL, vub_event,
@@ -254,7 +257,7 @@ static void vub_event(void *opaque, QEMUChrEvent event)
     case CHR_EVENT_CLOSED:
         /* defer close until later to avoid circular close */
         vhost_user_async_close(dev, &vub->chardev, &vub->vhost_dev,
-                               vub_disconnect, vub_event);
+                               vub_disconnect);
         break;
     case CHR_EVENT_BREAK:
     case CHR_EVENT_MUX_IN:

hw/virtio/vhost-user-fs.c

@@ -33,7 +33,7 @@ static const int user_feature_bits[] = {
     VIRTIO_F_RING_PACKED,
     VIRTIO_F_IOMMU_PLATFORM,
     VIRTIO_F_RING_RESET,
-
+    VIRTIO_F_NOTIFICATION_DATA,
     VHOST_INVALID_FEATURE_BIT
 };
 

hw/virtio/vhost-user-vsock.c

@@ -21,6 +21,7 @@ static const int user_feature_bits[] = {
     VIRTIO_RING_F_INDIRECT_DESC,
     VIRTIO_RING_F_EVENT_IDX,
     VIRTIO_F_NOTIFY_ON_EMPTY,
+    VIRTIO_F_NOTIFICATION_DATA,
     VHOST_INVALID_FEATURE_BIT
 };
 

hw/virtio/vhost-user.c

@@ -371,6 +371,7 @@ static bool vhost_user_per_device_request(VhostUserRequest request)
     case VHOST_USER_RESET_DEVICE:
     case VHOST_USER_ADD_MEM_REG:
     case VHOST_USER_REM_MEM_REG:
+    case VHOST_USER_SET_LOG_BASE:
         return true;
     default:
         return false;
@@ -2776,25 +2777,13 @@ typedef struct {
     DeviceState *dev;
     CharBackend *cd;
     struct vhost_dev *vhost;
-    IOEventHandler *event_cb;
 } VhostAsyncCallback;
 
 static void vhost_user_async_close_bh(void *opaque)
 {
     VhostAsyncCallback *data = opaque;
-    struct vhost_dev *vhost = data->vhost;
 
-    /*
+    data->cb(data->dev);
-     * If the vhost_dev has been cleared in the meantime there is
-     * nothing left to do as some other path has completed the
-     * cleanup.
-     */
-    if (vhost->vdev) {
-        data->cb(data->dev);
-    } else if (data->event_cb) {
-        qemu_chr_fe_set_handlers(data->cd, NULL, NULL, data->event_cb,
-                                 NULL, data->dev, NULL, true);
-   }
 
     g_free(data);
 }
@@ -2806,8 +2795,7 @@ static void vhost_user_async_close_bh(void *opaque)
  */
 void vhost_user_async_close(DeviceState *d,
                             CharBackend *chardev, struct vhost_dev *vhost,
-                            vu_async_close_fn cb,
+                            vu_async_close_fn cb)
-                            IOEventHandler *event_cb)
 {
     if (!runstate_check(RUN_STATE_SHUTDOWN)) {
         /*
@@ -2823,7 +2811,6 @@ void vhost_user_async_close(DeviceState *d,
         data->dev = d;
         data->cd = chardev;
         data->vhost = vhost;
-        data->event_cb = event_cb;
 
         /* Disable any further notifications on the chardev */
         qemu_chr_fe_set_handlers(chardev,

hw/virtio/vhost-vsock-common.c

@@ -22,6 +22,7 @@
 const int feature_bits[] = {
     VIRTIO_VSOCK_F_SEQPACKET,
     VIRTIO_F_RING_RESET,
+    VIRTIO_F_RING_PACKED,
     VHOST_INVALID_FEATURE_BIT
 };
 

hw/virtio/vhost.c

@@ -43,8 +43,9 @@
     do { } while (0)
 #endif
 
-static struct vhost_log *vhost_log;
+static struct vhost_log *vhost_log[VHOST_BACKEND_TYPE_MAX];
-static struct vhost_log *vhost_log_shm;
+static struct vhost_log *vhost_log_shm[VHOST_BACKEND_TYPE_MAX];
+static QLIST_HEAD(, vhost_dev) vhost_log_devs[VHOST_BACKEND_TYPE_MAX];
 
 /* Memslots used by backends that support private memslots (without an fd). */
 static unsigned int used_memslots;
@@ -149,6 +150,47 @@ bool vhost_dev_has_iommu(struct vhost_dev *dev)
     }
 }
 
+static inline bool vhost_dev_should_log(struct vhost_dev *dev)
+{
+    assert(dev->vhost_ops);
+    assert(dev->vhost_ops->backend_type > VHOST_BACKEND_TYPE_NONE);
+    assert(dev->vhost_ops->backend_type < VHOST_BACKEND_TYPE_MAX);
+
+    return dev == QLIST_FIRST(&vhost_log_devs[dev->vhost_ops->backend_type]);
+}
+
+static inline void vhost_dev_elect_mem_logger(struct vhost_dev *hdev, bool add)
+{
+    VhostBackendType backend_type;
+
+    assert(hdev->vhost_ops);
+
+    backend_type = hdev->vhost_ops->backend_type;
+    assert(backend_type > VHOST_BACKEND_TYPE_NONE);
+    assert(backend_type < VHOST_BACKEND_TYPE_MAX);
+
+    if (add && !QLIST_IS_INSERTED(hdev, logdev_entry)) {
+        if (QLIST_EMPTY(&vhost_log_devs[backend_type])) {
+            QLIST_INSERT_HEAD(&vhost_log_devs[backend_type],
+                              hdev, logdev_entry);
+        } else {
+            /*
+             * The first vhost_device in the list is selected as the shared
+             * logger to scan memory sections. Put new entry next to the head
+             * to avoid inadvertent change to the underlying logger device.
+             * This is done in order to get better cache locality and to avoid
+             * performance churn on the hot path for log scanning. Even when
+             * new devices come and go quickly, it wouldn't end up changing
+             * the active leading logger device at all.
+             */
+            QLIST_INSERT_AFTER(QLIST_FIRST(&vhost_log_devs[backend_type]),
+                               hdev, logdev_entry);
+        }
+    } else if (!add && QLIST_IS_INSERTED(hdev, logdev_entry)) {
+        QLIST_REMOVE(hdev, logdev_entry);
+    }
+}
+
 static int vhost_sync_dirty_bitmap(struct vhost_dev *dev,
                                    MemoryRegionSection *section,
                                    hwaddr first,
@@ -166,12 +208,14 @@ static int vhost_sync_dirty_bitmap(struct vhost_dev *dev,
     start_addr = MAX(first, start_addr);
     end_addr = MIN(last, end_addr);
 
-    for (i = 0; i < dev->mem->nregions; ++i) {
+    if (vhost_dev_should_log(dev)) {
-        struct vhost_memory_region *reg = dev->mem->regions + i;
+        for (i = 0; i < dev->mem->nregions; ++i) {
-        vhost_dev_sync_region(dev, section, start_addr, end_addr,
+            struct vhost_memory_region *reg = dev->mem->regions + i;
-                              reg->guest_phys_addr,
+            vhost_dev_sync_region(dev, section, start_addr, end_addr,
-                              range_get_last(reg->guest_phys_addr,
+                                  reg->guest_phys_addr,
-                                             reg->memory_size));
+                                  range_get_last(reg->guest_phys_addr,
+                                                 reg->memory_size));
+        }
     }
     for (i = 0; i < dev->nvqs; ++i) {
         struct vhost_virtqueue *vq = dev->vqs + i;
@@ -287,6 +331,10 @@ static int vhost_set_backend_type(struct vhost_dev *dev,
         r = -1;
     }
 
+    if (r == 0) {
+        assert(dev->vhost_ops->backend_type == backend_type);
+    }
+
     return r;
 }
 
@@ -319,16 +367,22 @@ static struct vhost_log *vhost_log_alloc(uint64_t size, bool share)
     return log;
 }
 
-static struct vhost_log *vhost_log_get(uint64_t size, bool share)
+static struct vhost_log *vhost_log_get(VhostBackendType backend_type,
+                                       uint64_t size, bool share)
 {
-    struct vhost_log *log = share ? vhost_log_shm : vhost_log;
+    struct vhost_log *log;
+
+    assert(backend_type > VHOST_BACKEND_TYPE_NONE);
+    assert(backend_type < VHOST_BACKEND_TYPE_MAX);
+
+    log = share ? vhost_log_shm[backend_type] : vhost_log[backend_type];
 
     if (!log || log->size != size) {
         log = vhost_log_alloc(size, share);
         if (share) {
-            vhost_log_shm = log;
+            vhost_log_shm[backend_type] = log;
         } else {
-            vhost_log = log;
+            vhost_log[backend_type] = log;
         }
     } else {
         ++log->refcnt;
@@ -340,11 +394,20 @@ static struct vhost_log *vhost_log_get(uint64_t size, bool share)
 static void vhost_log_put(struct vhost_dev *dev, bool sync)
 {
     struct vhost_log *log = dev->log;
+    VhostBackendType backend_type;
 
     if (!log) {
         return;
     }
 
+    assert(dev->vhost_ops);
+    backend_type = dev->vhost_ops->backend_type;
+
+    if (backend_type == VHOST_BACKEND_TYPE_NONE ||
+        backend_type >= VHOST_BACKEND_TYPE_MAX) {
+        return;
+    }
+
     --log->refcnt;
     if (log->refcnt == 0) {
         /* Sync only the range covered by the old log */
@@ -352,18 +415,19 @@ static void vhost_log_put(struct vhost_dev *dev, bool sync)
             vhost_log_sync_range(dev, 0, dev->log_size * VHOST_LOG_CHUNK - 1);
         }
 
-        if (vhost_log == log) {
+        if (vhost_log[backend_type] == log) {
             g_free(log->log);
-            vhost_log = NULL;
+            vhost_log[backend_type] = NULL;
-        } else if (vhost_log_shm == log) {
+        } else if (vhost_log_shm[backend_type] == log) {
             qemu_memfd_free(log->log, log->size * sizeof(*(log->log)),
                             log->fd);
-            vhost_log_shm = NULL;
+            vhost_log_shm[backend_type] = NULL;
         }
 
         g_free(log);
     }
 
+    vhost_dev_elect_mem_logger(dev, false);
     dev->log = NULL;
     dev->log_size = 0;
 }
@@ -376,7 +440,8 @@ static bool vhost_dev_log_is_shared(struct vhost_dev *dev)
 
 static inline void vhost_dev_log_resize(struct vhost_dev *dev, uint64_t size)
 {
-    struct vhost_log *log = vhost_log_get(size, vhost_dev_log_is_shared(dev));
+    struct vhost_log *log = vhost_log_get(dev->vhost_ops->backend_type,
+                                          size, vhost_dev_log_is_shared(dev));
     uint64_t log_base = (uintptr_t)log->log;
     int r;
 
@@ -978,6 +1043,15 @@ static int vhost_dev_set_log(struct vhost_dev *dev, bool enable_log)
             goto err_vq;
         }
     }
+
+    /*
+     * At log start we select our vhost_device logger that will scan the
+     * memory sections and skip for the others. This is possible because
+     * the log is shared amongst all vhost devices for a given type of
+     * backend.
+     */
+    vhost_dev_elect_mem_logger(dev, enable_log);
+
     return 0;
 err_vq:
     for (; i >= 0; --i) {
@@ -2044,7 +2118,8 @@ int vhost_dev_start(struct vhost_dev *hdev, VirtIODevice *vdev, bool vrings)
         uint64_t log_base;
 
         hdev->log_size = vhost_get_log_size(hdev);
-        hdev->log = vhost_log_get(hdev->log_size,
+        hdev->log = vhost_log_get(hdev->vhost_ops->backend_type,
+                                  hdev->log_size,
                                   vhost_dev_log_is_shared(hdev));
         log_base = (uintptr_t)hdev->log->log;
         r = hdev->vhost_ops->vhost_set_log_base(hdev,
@@ -2054,6 +2129,7 @@ int vhost_dev_start(struct vhost_dev *hdev, VirtIODevice *vdev, bool vrings)
             VHOST_OPS_DEBUG(r, "vhost_set_log_base failed");
             goto fail_log;
         }
+        vhost_dev_elect_mem_logger(hdev, true);
     }
     if (vrings) {
         r = vhost_dev_set_vring_enable(hdev, true);

hw/virtio/virtio-iommu.c

@@ -467,6 +467,26 @@ static AddressSpace *virtio_iommu_find_add_as(PCIBus *bus, void *opaque,
     return &sdev->as;
 }
 
+static void virtio_iommu_device_clear(VirtIOIOMMU *s, PCIBus *bus, int devfn)
+{
+    IOMMUPciBus *sbus = g_hash_table_lookup(s->as_by_busptr, bus);
+    IOMMUDevice *sdev;
+
+    if (!sbus) {
+        return;
+    }
+
+    sdev = sbus->pbdev[devfn];
+    if (!sdev) {
+        return;
+    }
+
+    g_list_free_full(sdev->resv_regions, g_free);
+    sdev->resv_regions = NULL;
+    g_free(sdev);
+    sbus->pbdev[devfn] = NULL;
+}
+
 static gboolean hiod_equal(gconstpointer v1, gconstpointer v2)
 {
     const struct hiod_key *key1 = v1;
@@ -650,6 +670,7 @@ virtio_iommu_unset_iommu_device(PCIBus *bus, void *opaque, int devfn)
     }
 
     g_hash_table_remove(viommu->host_iommu_devices, &key);
+    virtio_iommu_device_clear(viommu, bus, devfn);
 }
 
 static const PCIIOMMUOps virtio_iommu_ops = {
@@ -974,6 +995,9 @@ static void virtio_iommu_handle_command(VirtIODevice *vdev, VirtQueue *vq)
         iov = elem->out_sg;
         sz = iov_to_buf(iov, iov_cnt, 0, &head, sizeof(head));
         if (unlikely(sz != sizeof(head))) {
+            qemu_log_mask(LOG_GUEST_ERROR,
+                          "%s: read %zu bytes from command head"
+                          "but expected %zu\n", __func__, sz, sizeof(head));
             tail.status = VIRTIO_IOMMU_S_DEVERR;
             goto out;
         }
@@ -1010,6 +1034,25 @@ static void virtio_iommu_handle_command(VirtIODevice *vdev, VirtQueue *vq)
 out:
         sz = iov_from_buf(elem->in_sg, elem->in_num, 0,
                           buf ? buf : &tail, output_size);
+        if (unlikely(sz != output_size)) {
+            qemu_log_mask(LOG_GUEST_ERROR,
+                          "%s: wrote %zu bytes to command response"
+                          "but response size is %zu\n",
+                          __func__, sz, output_size);
+            tail.status = VIRTIO_IOMMU_S_DEVERR;
+            /*
+             * We checked that sizeof(tail) can fit to elem->in_sg at the
+             * beginning of the loop
+             */
+            output_size = sizeof(tail);
+            g_free(buf);
+            buf = NULL;
+            sz = iov_from_buf(elem->in_sg,
+                              elem->in_num,
+                              0,
+                              &tail,
+                              output_size);
+        }
         assert(sz == output_size);
 
         virtqueue_push(vq, elem, sz);

hw/virtio/virtio-mmio.c

@@ -248,6 +248,7 @@ static void virtio_mmio_write(void *opaque, hwaddr offset, uint64_t value,
 {
     VirtIOMMIOProxy *proxy = (VirtIOMMIOProxy *)opaque;
     VirtIODevice *vdev = virtio_bus_get_device(&proxy->bus);
+    uint16_t vq_idx;
 
     trace_virtio_mmio_write_offset(offset, value);
 
@@ -407,8 +408,14 @@ static void virtio_mmio_write(void *opaque, hwaddr offset, uint64_t value,
         }
         break;
     case VIRTIO_MMIO_QUEUE_NOTIFY:
-        if (value < VIRTIO_QUEUE_MAX) {
+        vq_idx = value;
-            virtio_queue_notify(vdev, value);
+        if (vq_idx < VIRTIO_QUEUE_MAX && virtio_queue_get_num(vdev, vq_idx)) {
+            if (virtio_vdev_has_feature(vdev, VIRTIO_F_NOTIFICATION_DATA)) {
+                VirtQueue *vq = virtio_get_queue(vdev, vq_idx);
+
+                virtio_queue_set_shadow_avail_idx(vq, (value >> 16) & 0xFFFF);
+            }
+            virtio_queue_notify(vdev, vq_idx);
         }
         break;
     case VIRTIO_MMIO_INTERRUPT_ACK:

hw/virtio/virtio-pci.c

@@ -384,7 +384,7 @@ static void virtio_ioport_write(void *opaque, uint32_t addr, uint32_t val)
 {
     VirtIOPCIProxy *proxy = opaque;
     VirtIODevice *vdev = virtio_bus_get_device(&proxy->bus);
-    uint16_t vector;
+    uint16_t vector, vq_idx;
     hwaddr pa;
 
     switch (addr) {
@@ -408,8 +408,14 @@ static void virtio_ioport_write(void *opaque, uint32_t addr, uint32_t val)
             vdev->queue_sel = val;
         break;
     case VIRTIO_PCI_QUEUE_NOTIFY:
-        if (val < VIRTIO_QUEUE_MAX) {
+        vq_idx = val;
-            virtio_queue_notify(vdev, val);
+        if (vq_idx < VIRTIO_QUEUE_MAX && virtio_queue_get_num(vdev, vq_idx)) {
+            if (virtio_vdev_has_feature(vdev, VIRTIO_F_NOTIFICATION_DATA)) {
+                VirtQueue *vq = virtio_get_queue(vdev, vq_idx);
+
+                virtio_queue_set_shadow_avail_idx(vq, val >> 16);
+            }
+            virtio_queue_notify(vdev, vq_idx);
         }
         break;
     case VIRTIO_PCI_STATUS:
@@ -892,7 +898,7 @@ static int kvm_virtio_pci_vector_use_one(VirtIOPCIProxy *proxy, int queue_no)
     }
     ret = kvm_virtio_pci_vq_vector_use(proxy, vector);
     if (ret < 0) {
-        goto undo;
+        return ret;
     }
     /*
      * If guest supports masking, set up irqfd now.
@@ -902,25 +908,11 @@ static int kvm_virtio_pci_vector_use_one(VirtIOPCIProxy *proxy, int queue_no)
         ret = kvm_virtio_pci_irqfd_use(proxy, n, vector);
         if (ret < 0) {
             kvm_virtio_pci_vq_vector_release(proxy, vector);
-            goto undo;
+            return ret;
         }
     }
 
     return 0;
-undo:
-
-    vector = virtio_queue_vector(vdev, queue_no);
-    if (vector >= msix_nr_vectors_allocated(dev)) {
-        return ret;
-    }
-    if (vdev->use_guest_notifier_mask && k->guest_notifier_mask) {
-        ret = virtio_pci_get_notifier(proxy, queue_no, &n, &vector);
-        if (ret < 0) {
-            return ret;
-        }
-        kvm_virtio_pci_irqfd_release(proxy, n, vector);
-    }
-    return ret;
 }
 static int kvm_virtio_pci_vector_vq_use(VirtIOPCIProxy *proxy, int nvqs)
 {
@@ -2230,6 +2222,11 @@ static void virtio_pci_realize(PCIDevice *pci_dev, Error **errp)
             pcie_cap_lnkctl_init(pci_dev);
         }
 
+        if (proxy->flags & VIRTIO_PCI_FLAG_PM_NO_SOFT_RESET) {
+            pci_set_word(pci_dev->config + pos + PCI_PM_CTRL,
+                         PCI_PM_CTRL_NO_SOFT_RESET);
+        }
+
         if (proxy->flags & VIRTIO_PCI_FLAG_INIT_PM) {
             /* Init Power Management Control Register */
             pci_set_word(pci_dev->wmask + pos + PCI_PM_CTRL,
@@ -2292,18 +2289,46 @@ static void virtio_pci_reset(DeviceState *qdev)
     }
 }
 
+static bool virtio_pci_no_soft_reset(PCIDevice *dev)
+{
+    uint16_t pmcsr;
+
+    if (!pci_is_express(dev) || !dev->exp.pm_cap) {
+        return false;
+    }
+
+    pmcsr = pci_get_word(dev->config + dev->exp.pm_cap + PCI_PM_CTRL);
+
+    /*
+     * When No_Soft_Reset bit is set and the device
+     * is in D3hot state, don't reset device
+     */
+    return (pmcsr & PCI_PM_CTRL_NO_SOFT_RESET) &&
+           (pmcsr & PCI_PM_CTRL_STATE_MASK) == 3;
+}
+
 static void virtio_pci_bus_reset_hold(Object *obj, ResetType type)
 {
     PCIDevice *dev = PCI_DEVICE(obj);
     DeviceState *qdev = DEVICE(obj);
 
+    if (virtio_pci_no_soft_reset(dev)) {
+        return;
+    }
+
     virtio_pci_reset(qdev);
 
     if (pci_is_express(dev)) {
+        VirtIOPCIProxy *proxy = VIRTIO_PCI(dev);
+
         pcie_cap_deverr_reset(dev);
         pcie_cap_lnkctl_reset(dev);
 
-        pci_set_word(dev->config + dev->exp.pm_cap + PCI_PM_CTRL, 0);
+        if (proxy->flags & VIRTIO_PCI_FLAG_INIT_PM) {
+            pci_word_test_and_clear_mask(
+                dev->config + dev->exp.pm_cap + PCI_PM_CTRL,
+                PCI_PM_CTRL_STATE_MASK);
+        }
     }
 }
 
@@ -2330,6 +2355,8 @@ static Property virtio_pci_properties[] = {
                     VIRTIO_PCI_FLAG_INIT_LNKCTL_BIT, true),
     DEFINE_PROP_BIT("x-pcie-pm-init", VirtIOPCIProxy, flags,
                     VIRTIO_PCI_FLAG_INIT_PM_BIT, true),
+    DEFINE_PROP_BIT("x-pcie-pm-no-soft-reset", VirtIOPCIProxy, flags,
+                    VIRTIO_PCI_FLAG_PM_NO_SOFT_RESET_BIT, false),
     DEFINE_PROP_BIT("x-pcie-flr-init", VirtIOPCIProxy, flags,
                     VIRTIO_PCI_FLAG_INIT_FLR_BIT, true),
     DEFINE_PROP_BIT("aer", VirtIOPCIProxy, flags,

hw/virtio/virtio.c

@@ -323,7 +323,6 @@ static void vring_packed_event_read(VirtIODevice *vdev,
     /* Make sure flags is seen before off_wrap */
     smp_rmb();
     e->off_wrap = virtio_lduw_phys_cached(vdev, cache, off_off);
-    virtio_tswap16s(vdev, &e->flags);
 }
 
 static void vring_packed_off_wrap_write(VirtIODevice *vdev,
@@ -1745,6 +1744,11 @@ static void *virtqueue_packed_pop(VirtQueue *vq, size_t sz)
                                              &indirect_desc_cache);
     } while (rc == VIRTQUEUE_READ_DESC_MORE);
 
+    if (desc_cache != &indirect_desc_cache) {
+        /* Buffer ID is included in the last descriptor in the list. */
+        id = desc.id;
+    }
+
     /* Now copy what we have collected and mapped */
     elem = virtqueue_alloc_element(sz, out_num, in_num);
     for (i = 0; i < out_num; i++) {
@@ -2264,6 +2268,24 @@ void virtio_queue_set_align(VirtIODevice *vdev, int n, int align)
     }
 }
 
+void virtio_queue_set_shadow_avail_idx(VirtQueue *vq, uint16_t shadow_avail_idx)
+{
+    if (!vq->vring.desc) {
+        return;
+    }
+
+    /*
+     * 16-bit data for packed VQs include 1-bit wrap counter and
+     * 15-bit shadow_avail_idx.
+     */
+    if (virtio_vdev_has_feature(vq->vdev, VIRTIO_F_RING_PACKED)) {
+        vq->shadow_avail_wrap_counter = (shadow_avail_idx >> 15) & 0x1;
+        vq->shadow_avail_idx = shadow_avail_idx & 0x7FFF;
+    } else {
+        vq->shadow_avail_idx = shadow_avail_idx;
+    }
+}
+
 static void virtio_queue_notify_vq(VirtQueue *vq)
 {
     if (vq->vring.desc && vq->handle_output) {
@@ -2962,6 +2984,20 @@ int virtio_set_features(VirtIODevice *vdev, uint64_t val)
     return ret;
 }
 
+static void virtio_device_check_notification_compatibility(VirtIODevice *vdev,
+                                                           Error **errp)
+{
+    VirtioBusState *bus = VIRTIO_BUS(qdev_get_parent_bus(DEVICE(vdev)));
+    VirtioBusClass *k = VIRTIO_BUS_GET_CLASS(bus);
+    DeviceState *proxy = DEVICE(BUS(bus)->parent);
+
+    if (virtio_host_has_feature(vdev, VIRTIO_F_NOTIFICATION_DATA) &&
+        k->ioeventfd_enabled(proxy)) {
+        error_setg(errp,
+                   "notification_data=on without ioeventfd=off is not supported");
+    }
+}
+
 size_t virtio_get_config_size(const VirtIOConfigSizeParams *params,
                               uint64_t host_features)
 {
@@ -3722,6 +3758,14 @@ static void virtio_device_realize(DeviceState *dev, Error **errp)
         }
     }
 
+    /* Devices should not use both ioeventfd and notification data feature */
+    virtio_device_check_notification_compatibility(vdev, &err);
+    if (err != NULL) {
+        error_propagate(errp, err);
+        vdc->unrealize(dev);
+        return;
+    }
+
     virtio_bus_device_plugged(vdev, &err);
     if (err != NULL) {
         error_propagate(errp, err);

hw/xen/xen_pt_load_rom.c

@@ -53,7 +53,7 @@ void *pci_assign_dev_load_option_rom(PCIDevice *dev,
     }
     fseek(fp, 0, SEEK_SET);
 
-    if (dev->romsize != -1) {
+    if (dev->romsize != UINT_MAX) {
         if (st.st_size > dev->romsize) {
             error_report("ROM BAR \"%s\" (%ld bytes) is too large for ROM size %u",
                          rom_file, (long) st.st_size, dev->romsize);

include/hw/cxl/cxl_device.h

@@ -164,7 +164,7 @@ typedef struct CXLEventLog {
 } CXLEventLog;
 
 typedef struct CXLCCI {
-    const struct cxl_cmd (*cxl_cmd_set)[256];
+    struct cxl_cmd cxl_cmd_set[256][256];
     struct cel_log {
         uint16_t opcode;
         uint16_t effect;
@@ -234,7 +234,7 @@ typedef struct cxl_device_state {
     } timestamp;
 
     /* memory region size, HDM */
-    uint64_t mem_size;
+    uint64_t static_mem_size;
     uint64_t pmem_size;
     uint64_t vmem_size;
 
@@ -301,6 +301,8 @@ void cxl_initialize_mailbox_t3(CXLCCI *cci, DeviceState *d, size_t payload_max);
 void cxl_initialize_mailbox_swcci(CXLCCI *cci, DeviceState *intf,
                                   DeviceState *d, size_t payload_max);
 void cxl_init_cci(CXLCCI *cci, size_t payload_max);
+void cxl_add_cci_commands(CXLCCI *cci, const struct cxl_cmd (*cxl_cmd_set)[256],
+                          size_t payload_max);
 int cxl_process_cci_message(CXLCCI *cci, uint8_t set, uint8_t cmd,
                             size_t len_in, uint8_t *pl_in,
                             size_t *len_out, uint8_t *pl_out,
@@ -420,6 +422,43 @@ typedef struct CXLPoison {
 typedef QLIST_HEAD(, CXLPoison) CXLPoisonList;
 #define CXL_POISON_LIST_LIMIT 256
 
+#define DCD_MAX_NUM_REGION 8
+
+typedef struct CXLDCExtentRaw {
+    uint64_t start_dpa;
+    uint64_t len;
+    uint8_t tag[0x10];
+    uint16_t shared_seq;
+    uint8_t rsvd[0x6];
+} QEMU_PACKED CXLDCExtentRaw;
+
+typedef struct CXLDCExtent {
+    uint64_t start_dpa;
+    uint64_t len;
+    uint8_t tag[0x10];
+    uint16_t shared_seq;
+    uint8_t rsvd[0x6];
+
+    QTAILQ_ENTRY(CXLDCExtent) node;
+} CXLDCExtent;
+typedef QTAILQ_HEAD(, CXLDCExtent) CXLDCExtentList;
+
+typedef struct CXLDCExtentGroup {
+    CXLDCExtentList list;
+    QTAILQ_ENTRY(CXLDCExtentGroup) node;
+} CXLDCExtentGroup;
+typedef QTAILQ_HEAD(, CXLDCExtentGroup) CXLDCExtentGroupList;
+
+typedef struct CXLDCRegion {
+    uint64_t base;       /* aligned to 256*MiB */
+    uint64_t decode_len; /* aligned to 256*MiB */
+    uint64_t len;
+    uint64_t block_size;
+    uint32_t dsmadhandle;
+    uint8_t flags;
+    unsigned long *blk_bitmap;
+} CXLDCRegion;
+
 struct CXLType3Dev {
     /* Private */
     PCIDevice parent_obj;
@@ -452,6 +491,23 @@ struct CXLType3Dev {
     unsigned int poison_list_cnt;
     bool poison_list_overflowed;
     uint64_t poison_list_overflow_ts;
+
+    struct dynamic_capacity {
+        HostMemoryBackend *host_dc;
+        AddressSpace host_dc_as;
+        /*
+         * total_capacity is equivalent to the dynamic capability
+         * memory region size.
+         */
+        uint64_t total_capacity; /* 256M aligned */
+        CXLDCExtentList extents;
+        CXLDCExtentGroupList extents_pending;
+        uint32_t total_extent_count;
+        uint32_t ext_list_gen_seq;
+
+        uint8_t num_regions; /* 0-8 regions */
+        CXLDCRegion regions[DCD_MAX_NUM_REGION];
+    } dc;
 };
 
 #define TYPE_CXL_TYPE3 "cxl-type3"
@@ -503,4 +559,29 @@ void cxl_event_irq_assert(CXLType3Dev *ct3d);
 
 void cxl_set_poison_list_overflowed(CXLType3Dev *ct3d);
 
+CXLDCRegion *cxl_find_dc_region(CXLType3Dev *ct3d, uint64_t dpa, uint64_t len);
+
+void cxl_remove_extent_from_extent_list(CXLDCExtentList *list,
+                                        CXLDCExtent *extent);
+void cxl_insert_extent_to_extent_list(CXLDCExtentList *list, uint64_t dpa,
+                                      uint64_t len, uint8_t *tag,
+                                      uint16_t shared_seq);
+bool test_any_bits_set(const unsigned long *addr, unsigned long nr,
+                       unsigned long size);
+bool cxl_extents_contains_dpa_range(CXLDCExtentList *list,
+                                    uint64_t dpa, uint64_t len);
+CXLDCExtentGroup *cxl_insert_extent_to_extent_group(CXLDCExtentGroup *group,
+                                                    uint64_t dpa,
+                                                    uint64_t len,
+                                                    uint8_t *tag,
+                                                    uint16_t shared_seq);
+void cxl_extent_group_list_insert_tail(CXLDCExtentGroupList *list,
+                                       CXLDCExtentGroup *group);
+void cxl_extent_group_list_delete_front(CXLDCExtentGroupList *list);
+void ct3_set_region_block_backed(CXLType3Dev *ct3d, uint64_t dpa,
+                                 uint64_t len);
+void ct3_clear_region_block_backed(CXLType3Dev *ct3d, uint64_t dpa,
+                                   uint64_t len);
+bool ct3_test_region_block_backed(CXLType3Dev *ct3d, uint64_t dpa,
+                                  uint64_t len);
 #endif

include/hw/cxl/cxl_events.h

@@ -166,4 +166,22 @@ typedef struct CXLEventMemoryModule {
     uint8_t reserved[0x3d];
 } QEMU_PACKED CXLEventMemoryModule;
 
+/*
+ * CXL r3.1 section Table 8-50: Dynamic Capacity Event Record
+ * All fields little endian.
+ */
+typedef struct CXLEventDynamicCapacity {
+    CXLEventRecordHdr hdr;
+    uint8_t type;
+    uint8_t validity_flags;
+    uint16_t host_id;
+    uint8_t updated_region_id;
+    uint8_t flags;
+    uint8_t reserved2[2];
+    uint8_t dynamic_capacity_extent[0x28]; /* defined in cxl_device.h */
+    uint8_t reserved[0x18];
+    uint32_t extents_avail;
+    uint32_t tags_avail;
+} QEMU_PACKED CXLEventDynamicCapacity;
+
 #endif /* CXL_EVENTS_H */

include/hw/misc/pvpanic.h

@@ -18,6 +18,12 @@
 #include "exec/memory.h"
 #include "qom/object.h"
 
+#include "standard-headers/misc/pvpanic.h"
+
+#define PVPANIC_EVENTS (PVPANIC_PANICKED | \
+                        PVPANIC_CRASH_LOADED | \
+                        PVPANIC_SHUTDOWN)
+
 #define TYPE_PVPANIC_ISA_DEVICE "pvpanic"
 #define TYPE_PVPANIC_PCI_DEVICE "pvpanic-pci"
 

include/hw/pci/pci.h

@@ -678,6 +678,6 @@ static inline void pci_irq_pulse(PCIDevice *pci_dev)
 }
 
 MSIMessage pci_get_msi_message(PCIDevice *dev, int vector);
-void pci_set_power(PCIDevice *pci_dev, bool state);
+void pci_set_enabled(PCIDevice *pci_dev, bool state);
 
 #endif

include/hw/pci/pci_device.h

@@ -56,7 +56,7 @@ typedef struct PCIReqIDCache PCIReqIDCache;
 struct PCIDevice {
     DeviceState qdev;
     bool partially_hotplugged;
-    bool has_power;
+    bool enabled;
 
     /* PCI config space */
     uint8_t *config;
@@ -205,6 +205,21 @@ static inline uint16_t pci_get_bdf(PCIDevice *dev)
     return PCI_BUILD_BDF(pci_bus_num(pci_get_bus(dev)), dev->devfn);
 }
 
+static inline void pci_set_power(PCIDevice *pci_dev, bool state)
+{
+    /*
+     * Don't change the enabled state of VFs when powering on/off the device.
+     *
+     * When powering on, VFs must not be enabled immediately but they must
+     * wait until the guest configures SR-IOV.
+     * When powering off, their corresponding PFs will be reset and disable
+     * VFs.
+     */
+    if (!pci_is_vf(pci_dev)) {
+        pci_set_enabled(pci_dev, state);
+    }
+}
+
 uint16_t pci_requester_id(PCIDevice *dev);
 
 /* DMA access functions */

include/hw/pci/pcie_sriov.h

@@ -16,9 +16,7 @@
 #include "hw/pci/pci.h"
 
 typedef struct PCIESriovPF {
-    uint16_t num_vfs;   /* Number of virtual functions created */
     uint8_t vf_bar_type[PCI_NUM_REGIONS];   /* Store type for each VF bar */
-    const char *vfname; /* Reference to the device type used for the VFs */
     PCIDevice **vf;     /* Pointer to an array of num_vfs VF devices */
 } PCIESriovPF;
 
@@ -27,10 +25,11 @@ typedef struct PCIESriovVF {
     uint16_t vf_number; /* Logical VF number of this function */
 } PCIESriovVF;
 
-void pcie_sriov_pf_init(PCIDevice *dev, uint16_t offset,
+bool pcie_sriov_pf_init(PCIDevice *dev, uint16_t offset,
                         const char *vfname, uint16_t vf_dev_id,
                         uint16_t init_vfs, uint16_t total_vfs,
-                        uint16_t vf_offset, uint16_t vf_stride);
+                        uint16_t vf_offset, uint16_t vf_stride,
+                        Error **errp);
 void pcie_sriov_pf_exit(PCIDevice *dev);
 
 /* Set up a VF bar in the SR/IOV bar area */
@@ -58,6 +57,8 @@ void pcie_sriov_pf_add_sup_pgsize(PCIDevice *dev, uint16_t opt_sup_pgsize);
 void pcie_sriov_config_write(PCIDevice *dev, uint32_t address,
                              uint32_t val, int len);
 
+void pcie_sriov_pf_post_load(PCIDevice *dev);
+
 /* Reset SR/IOV */
 void pcie_sriov_pf_reset(PCIDevice *dev);
 

include/hw/virtio/vhost-user.h

@@ -108,7 +108,6 @@ typedef void (*vu_async_close_fn)(DeviceState *cb);
 
 void vhost_user_async_close(DeviceState *d,
                             CharBackend *chardev, struct vhost_dev *vhost,
-                            vu_async_close_fn cb,
+                            vu_async_close_fn cb);
-                            IOEventHandler *event_cb);
 
 #endif

include/hw/virtio/vhost.h

@@ -129,6 +129,7 @@ struct vhost_dev {
     void *opaque;
     struct vhost_log *log;
     QLIST_ENTRY(vhost_dev) entry;
+    QLIST_ENTRY(vhost_dev) logdev_entry;
     QLIST_HEAD(, vhost_iommu) iommu_list;
     IOMMUNotifier n;
     const VhostDevConfigOps *config_ops;

include/hw/virtio/virtio-pci.h

@@ -43,6 +43,7 @@ enum {
     VIRTIO_PCI_FLAG_INIT_FLR_BIT,
     VIRTIO_PCI_FLAG_AER_BIT,
     VIRTIO_PCI_FLAG_ATS_PAGE_ALIGNED_BIT,
+    VIRTIO_PCI_FLAG_PM_NO_SOFT_RESET_BIT,
 };
 
 /* Need to activate work-arounds for buggy guests at vmstate load. */
@@ -79,6 +80,10 @@ enum {
 /* Init Power Management */
 #define VIRTIO_PCI_FLAG_INIT_PM (1 << VIRTIO_PCI_FLAG_INIT_PM_BIT)
 
+/* Init The No_Soft_Reset bit of Power Management */
+#define VIRTIO_PCI_FLAG_PM_NO_SOFT_RESET \
+  (1 << VIRTIO_PCI_FLAG_PM_NO_SOFT_RESET_BIT)
+
 /* Init Function Level Reset capability */
 #define VIRTIO_PCI_FLAG_INIT_FLR (1 << VIRTIO_PCI_FLAG_INIT_FLR_BIT)
 

include/hw/virtio/virtio.h

@@ -307,6 +307,8 @@ int virtio_queue_ready(VirtQueue *vq);
 
 int virtio_queue_empty(VirtQueue *vq);
 
+void virtio_queue_set_shadow_avail_idx(VirtQueue *vq, uint16_t idx);
+
 /* Host binding interface.  */
 
 uint32_t virtio_config_readb(VirtIODevice *vdev, uint32_t addr);
@@ -470,9 +472,9 @@ static inline bool virtio_device_started(VirtIODevice *vdev, uint8_t status)
  * @vdev - the VirtIO device
  * @status - the devices status bits
  *
- * This is similar to virtio_device_started() but also encapsulates a
+ * This is similar to virtio_device_started() but ignores vdev->started
- * check on the VM status which would prevent a device starting
+ * and also encapsulates a check on the VM status which would prevent a
- * anyway.
+ * device from starting anyway.
  */
 static inline bool virtio_device_should_start(VirtIODevice *vdev, uint8_t status)
 {
@@ -480,7 +482,7 @@ static inline bool virtio_device_should_start(VirtIODevice *vdev, uint8_t status
         return false;
     }
 
-    return virtio_device_started(vdev, status);
+    return status & VIRTIO_CONFIG_S_DRIVER_OK;
 }
 
 static inline void virtio_set_started(VirtIODevice *vdev, bool started)

include/standard-headers/linux/ethtool.h

@@ -752,6 +752,61 @@ enum ethtool_module_power_mode {
 	ETHTOOL_MODULE_POWER_MODE_HIGH,
 };
 
+/**
+ * enum ethtool_pse_types - Types of PSE controller.
+ * @ETHTOOL_PSE_UNKNOWN: Type of PSE controller is unknown
+ * @ETHTOOL_PSE_PODL: PSE controller which support PoDL
+ * @ETHTOOL_PSE_C33: PSE controller which support Clause 33 (PoE)
+ */
+enum ethtool_pse_types {
+	ETHTOOL_PSE_UNKNOWN =	1 << 0,
+	ETHTOOL_PSE_PODL =	1 << 1,
+	ETHTOOL_PSE_C33 =	1 << 2,
+};
+
+/**
+ * enum ethtool_c33_pse_admin_state - operational state of the PoDL PSE
+ *	functions. IEEE 802.3-2022 30.9.1.1.2 aPSEAdminState
+ * @ETHTOOL_C33_PSE_ADMIN_STATE_UNKNOWN: state of PSE functions is unknown
+ * @ETHTOOL_C33_PSE_ADMIN_STATE_DISABLED: PSE functions are disabled
+ * @ETHTOOL_C33_PSE_ADMIN_STATE_ENABLED: PSE functions are enabled
+ */
+enum ethtool_c33_pse_admin_state {
+	ETHTOOL_C33_PSE_ADMIN_STATE_UNKNOWN = 1,
+	ETHTOOL_C33_PSE_ADMIN_STATE_DISABLED,
+	ETHTOOL_C33_PSE_ADMIN_STATE_ENABLED,
+};
+
+/**
+ * enum ethtool_c33_pse_pw_d_status - power detection status of the PSE.
+ *	IEEE 802.3-2022 30.9.1.1.3 aPoDLPSEPowerDetectionStatus:
+ * @ETHTOOL_C33_PSE_PW_D_STATUS_UNKNOWN: PSE status is unknown
+ * @ETHTOOL_C33_PSE_PW_D_STATUS_DISABLED: The enumeration "disabled"
+ *	indicates that the PSE State diagram is in the state DISABLED.
+ * @ETHTOOL_C33_PSE_PW_D_STATUS_SEARCHING: The enumeration "searching"
+ *	indicates the PSE State diagram is in a state other than those
+ *	listed.
+ * @ETHTOOL_C33_PSE_PW_D_STATUS_DELIVERING: The enumeration
+ *	"deliveringPower" indicates that the PSE State diagram is in the
+ *	state POWER_ON.
+ * @ETHTOOL_C33_PSE_PW_D_STATUS_TEST: The enumeration "test" indicates that
+ *	the PSE State diagram is in the state TEST_MODE.
+ * @ETHTOOL_C33_PSE_PW_D_STATUS_FAULT: The enumeration "fault" indicates that
+ *	the PSE State diagram is in the state TEST_ERROR.
+ * @ETHTOOL_C33_PSE_PW_D_STATUS_OTHERFAULT: The enumeration "otherFault"
+ *	indicates that the PSE State diagram is in the state IDLE due to
+ *	the variable error_condition = true.
+ */
+enum ethtool_c33_pse_pw_d_status {
+	ETHTOOL_C33_PSE_PW_D_STATUS_UNKNOWN = 1,
+	ETHTOOL_C33_PSE_PW_D_STATUS_DISABLED,
+	ETHTOOL_C33_PSE_PW_D_STATUS_SEARCHING,
+	ETHTOOL_C33_PSE_PW_D_STATUS_DELIVERING,
+	ETHTOOL_C33_PSE_PW_D_STATUS_TEST,
+	ETHTOOL_C33_PSE_PW_D_STATUS_FAULT,
+	ETHTOOL_C33_PSE_PW_D_STATUS_OTHERFAULT,
+};
+
 /**
  * enum ethtool_podl_pse_admin_state - operational state of the PoDL PSE
  *	functions. IEEE 802.3-2018 30.15.1.1.2 aPoDLPSEAdminState

include/standard-headers/linux/pci_regs.h

@@ -1144,8 +1144,14 @@
 #define PCI_DOE_DATA_OBJECT_HEADER_2_LENGTH		0x0003ffff
 
 #define PCI_DOE_DATA_OBJECT_DISC_REQ_3_INDEX		0x000000ff
+#define PCI_DOE_DATA_OBJECT_DISC_REQ_3_VER		0x0000ff00
 #define PCI_DOE_DATA_OBJECT_DISC_RSP_3_VID		0x0000ffff
 #define PCI_DOE_DATA_OBJECT_DISC_RSP_3_PROTOCOL		0x00ff0000
 #define PCI_DOE_DATA_OBJECT_DISC_RSP_3_NEXT_INDEX	0xff000000
 
+/* Compute Express Link (CXL r3.1, sec 8.1.5) */
+#define PCI_DVSEC_CXL_PORT				3
+#define PCI_DVSEC_CXL_PORT_CTL				0x0c
+#define PCI_DVSEC_CXL_PORT_CTL_UNMASK_SBR		0x00000001
+
 #endif /* LINUX_PCI_REGS_H */

include/standard-headers/linux/virtio_bt.h

@@ -13,7 +13,6 @@
 
 enum virtio_bt_config_type {
 	VIRTIO_BT_CONFIG_TYPE_PRIMARY	= 0,
-	VIRTIO_BT_CONFIG_TYPE_AMP	= 1,
 };
 
 enum virtio_bt_config_vendor {

include/standard-headers/linux/virtio_mem.h

@@ -90,6 +90,8 @@
 #define VIRTIO_MEM_F_ACPI_PXM		0
 /* unplugged memory must not be accessed */
 #define VIRTIO_MEM_F_UNPLUGGED_INACCESSIBLE	1
+/* plugged memory will remain plugged when suspending+resuming */
+#define VIRTIO_MEM_F_PERSISTENT_SUSPEND		2
 
 
 /* --- virtio-mem: guest -> host requests --- */

include/standard-headers/linux/virtio_net.h

@@ -56,6 +56,7 @@
 #define VIRTIO_NET_F_MQ	22	/* Device supports Receive Flow
 					 * Steering */
 #define VIRTIO_NET_F_CTRL_MAC_ADDR 23	/* Set MAC address */
+#define VIRTIO_NET_F_DEVICE_STATS 50	/* Device can provide device-level statistics. */
 #define VIRTIO_NET_F_VQ_NOTF_COAL 52	/* Device supports virtqueue notification coalescing */
 #define VIRTIO_NET_F_NOTF_COAL	53	/* Device supports notifications coalescing */
 #define VIRTIO_NET_F_GUEST_USO4	54	/* Guest can handle USOv4 in. */
@@ -406,4 +407,146 @@ struct  virtio_net_ctrl_coal_vq {
 	struct virtio_net_ctrl_coal coal;
 };
 
+/*
+ * Device Statistics
+ */
+#define VIRTIO_NET_CTRL_STATS         8
+#define VIRTIO_NET_CTRL_STATS_QUERY   0
+#define VIRTIO_NET_CTRL_STATS_GET     1
+
+struct virtio_net_stats_capabilities {
+
+#define VIRTIO_NET_STATS_TYPE_CVQ       (1ULL << 32)
+
+#define VIRTIO_NET_STATS_TYPE_RX_BASIC  (1ULL << 0)
+#define VIRTIO_NET_STATS_TYPE_RX_CSUM   (1ULL << 1)
+#define VIRTIO_NET_STATS_TYPE_RX_GSO    (1ULL << 2)
+#define VIRTIO_NET_STATS_TYPE_RX_SPEED  (1ULL << 3)
+
+#define VIRTIO_NET_STATS_TYPE_TX_BASIC  (1ULL << 16)
+#define VIRTIO_NET_STATS_TYPE_TX_CSUM   (1ULL << 17)
+#define VIRTIO_NET_STATS_TYPE_TX_GSO    (1ULL << 18)
+#define VIRTIO_NET_STATS_TYPE_TX_SPEED  (1ULL << 19)
+
+	uint64_t supported_stats_types[1];
+};
+
+struct virtio_net_ctrl_queue_stats {
+	struct {
+		uint16_t vq_index;
+		uint16_t reserved[3];
+		uint64_t types_bitmap[1];
+	} stats[1];
+};
+
+struct virtio_net_stats_reply_hdr {
+#define VIRTIO_NET_STATS_TYPE_REPLY_CVQ       32
+
+#define VIRTIO_NET_STATS_TYPE_REPLY_RX_BASIC  0
+#define VIRTIO_NET_STATS_TYPE_REPLY_RX_CSUM   1
+#define VIRTIO_NET_STATS_TYPE_REPLY_RX_GSO    2
+#define VIRTIO_NET_STATS_TYPE_REPLY_RX_SPEED  3
+
+#define VIRTIO_NET_STATS_TYPE_REPLY_TX_BASIC  16
+#define VIRTIO_NET_STATS_TYPE_REPLY_TX_CSUM   17
+#define VIRTIO_NET_STATS_TYPE_REPLY_TX_GSO    18
+#define VIRTIO_NET_STATS_TYPE_REPLY_TX_SPEED  19
+	uint8_t type;
+	uint8_t reserved;
+	uint16_t vq_index;
+	uint16_t reserved1;
+	uint16_t size;
+};
+
+struct virtio_net_stats_cvq {
+	struct virtio_net_stats_reply_hdr hdr;
+
+	uint64_t command_num;
+	uint64_t ok_num;
+};
+
+struct virtio_net_stats_rx_basic {
+	struct virtio_net_stats_reply_hdr hdr;
+
+	uint64_t rx_notifications;
+
+	uint64_t rx_packets;
+	uint64_t rx_bytes;
+
+	uint64_t rx_interrupts;
+
+	uint64_t rx_drops;
+	uint64_t rx_drop_overruns;
+};
+
+struct virtio_net_stats_tx_basic {
+	struct virtio_net_stats_reply_hdr hdr;
+
+	uint64_t tx_notifications;
+
+	uint64_t tx_packets;
+	uint64_t tx_bytes;
+
+	uint64_t tx_interrupts;
+
+	uint64_t tx_drops;
+	uint64_t tx_drop_malformed;
+};
+
+struct virtio_net_stats_rx_csum {
+	struct virtio_net_stats_reply_hdr hdr;
+
+	uint64_t rx_csum_valid;
+	uint64_t rx_needs_csum;
+	uint64_t rx_csum_none;
+	uint64_t rx_csum_bad;
+};
+
+struct virtio_net_stats_tx_csum {
+	struct virtio_net_stats_reply_hdr hdr;
+
+	uint64_t tx_csum_none;
+	uint64_t tx_needs_csum;
+};
+
+struct virtio_net_stats_rx_gso {
+	struct virtio_net_stats_reply_hdr hdr;
+
+	uint64_t rx_gso_packets;
+	uint64_t rx_gso_bytes;
+	uint64_t rx_gso_packets_coalesced;
+	uint64_t rx_gso_bytes_coalesced;
+};
+
+struct virtio_net_stats_tx_gso {
+	struct virtio_net_stats_reply_hdr hdr;
+
+	uint64_t tx_gso_packets;
+	uint64_t tx_gso_bytes;
+	uint64_t tx_gso_segments;
+	uint64_t tx_gso_segments_bytes;
+	uint64_t tx_gso_packets_noseg;
+	uint64_t tx_gso_bytes_noseg;
+};
+
+struct virtio_net_stats_rx_speed {
+	struct virtio_net_stats_reply_hdr hdr;
+
+	/* rx_{packets,bytes}_allowance_exceeded are too long. So rename to
+	 * short name.
+	 */
+	uint64_t rx_ratelimit_packets;
+	uint64_t rx_ratelimit_bytes;
+};
+
+struct virtio_net_stats_tx_speed {
+	struct virtio_net_stats_reply_hdr hdr;
+
+	/* tx_{packets,bytes}_allowance_exceeded are too long. So rename to
+	 * short name.
+	 */
+	uint64_t tx_ratelimit_packets;
+	uint64_t tx_ratelimit_bytes;
+};
+
 #endif /* _LINUX_VIRTIO_NET_H */

include/standard-headers/misc/pvpanic.h

@@ -3,7 +3,10 @@
 #ifndef __PVPANIC_H__
 #define __PVPANIC_H__
 
-#define PVPANIC_PANICKED	(1 << 0)
+#include "standard-headers/linux/const.h"
-#define PVPANIC_CRASH_LOADED	(1 << 1)
+
+#define PVPANIC_PANICKED	_BITUL(0)
+#define PVPANIC_CRASH_LOADED	_BITUL(1)
+#define PVPANIC_SHUTDOWN	_BITUL(2)
 
 #endif /* __PVPANIC_H__ */

include/sysemu/runstate.h

@@ -104,6 +104,7 @@ void qemu_system_killed(int signal, pid_t pid);
 void qemu_system_reset(ShutdownCause reason);
 void qemu_system_guest_panicked(GuestPanicInformation *info);
 void qemu_system_guest_crashloaded(GuestPanicInformation *info);
+void qemu_system_guest_pvshutdown(void);
 bool qemu_system_dump_in_progress(void);
 
 #endif

linux-headers/asm-generic/unistd.h

@@ -842,8 +842,11 @@ __SYSCALL(__NR_lsm_set_self_attr, sys_lsm_set_self_attr)
 #define __NR_lsm_list_modules 461
 __SYSCALL(__NR_lsm_list_modules, sys_lsm_list_modules)
 
+#define __NR_mseal 462
+__SYSCALL(__NR_mseal, sys_mseal)
+
 #undef __NR_syscalls
-#define __NR_syscalls 462
+#define __NR_syscalls 463
 
 /*
  * 32 bit systems traditionally used different

linux-headers/asm-mips/unistd_n32.h

@@ -390,5 +390,6 @@
 #define __NR_lsm_get_self_attr (__NR_Linux + 459)
 #define __NR_lsm_set_self_attr (__NR_Linux + 460)
 #define __NR_lsm_list_modules (__NR_Linux + 461)
+#define __NR_mseal (__NR_Linux + 462)
 
 #endif /* _ASM_UNISTD_N32_H */

linux-headers/asm-mips/unistd_n64.h

@@ -366,5 +366,6 @@
 #define __NR_lsm_get_self_attr (__NR_Linux + 459)
 #define __NR_lsm_set_self_attr (__NR_Linux + 460)
 #define __NR_lsm_list_modules (__NR_Linux + 461)
+#define __NR_mseal (__NR_Linux + 462)
 
 #endif /* _ASM_UNISTD_N64_H */

linux-headers/asm-mips/unistd_o32.h

@@ -436,5 +436,6 @@
 #define __NR_lsm_get_self_attr (__NR_Linux + 459)
 #define __NR_lsm_set_self_attr (__NR_Linux + 460)
 #define __NR_lsm_list_modules (__NR_Linux + 461)
+#define __NR_mseal (__NR_Linux + 462)
 
 #endif /* _ASM_UNISTD_O32_H */

linux-headers/asm-powerpc/unistd_32.h

@@ -443,6 +443,7 @@
 #define __NR_lsm_get_self_attr 459
 #define __NR_lsm_set_self_attr 460
 #define __NR_lsm_list_modules 461
+#define __NR_mseal 462
 
 
 #endif /* _ASM_UNISTD_32_H */

linux-headers/asm-powerpc/unistd_64.h

@@ -415,6 +415,7 @@
 #define __NR_lsm_get_self_attr 459
 #define __NR_lsm_set_self_attr 460
 #define __NR_lsm_list_modules 461
+#define __NR_mseal 462
 
 
 #endif /* _ASM_UNISTD_64_H */

linux-headers/asm-s390/unistd_32.h

@@ -434,5 +434,6 @@
 #define __NR_lsm_get_self_attr 459
 #define __NR_lsm_set_self_attr 460
 #define __NR_lsm_list_modules 461
+#define __NR_mseal 462
 
 #endif /* _ASM_S390_UNISTD_32_H */

linux-headers/asm-s390/unistd_64.h

@@ -382,5 +382,6 @@
 #define __NR_lsm_get_self_attr 459
 #define __NR_lsm_set_self_attr 460
 #define __NR_lsm_list_modules 461
+#define __NR_mseal 462
 
 #endif /* _ASM_S390_UNISTD_64_H */

linux-headers/asm-x86/unistd_32.h

@@ -452,6 +452,7 @@
 #define __NR_lsm_get_self_attr 459
 #define __NR_lsm_set_self_attr 460
 #define __NR_lsm_list_modules 461
+#define __NR_mseal 462
 
 
 #endif /* _ASM_UNISTD_32_H */

linux-headers/asm-x86/unistd_64.h

@@ -374,6 +374,7 @@
 #define __NR_lsm_get_self_attr 459
 #define __NR_lsm_set_self_attr 460
 #define __NR_lsm_list_modules 461
+#define __NR_mseal 462
 
 
 #endif /* _ASM_UNISTD_64_H */

linux-headers/asm-x86/unistd_x32.h

@@ -318,6 +318,7 @@
 #define __NR_set_mempolicy_home_node (__X32_SYSCALL_BIT + 450)
 #define __NR_cachestat (__X32_SYSCALL_BIT + 451)
 #define __NR_fchmodat2 (__X32_SYSCALL_BIT + 452)
+#define __NR_map_shadow_stack (__X32_SYSCALL_BIT + 453)
 #define __NR_futex_wake (__X32_SYSCALL_BIT + 454)
 #define __NR_futex_wait (__X32_SYSCALL_BIT + 455)
 #define __NR_futex_requeue (__X32_SYSCALL_BIT + 456)
@@ -326,6 +327,7 @@
 #define __NR_lsm_get_self_attr (__X32_SYSCALL_BIT + 459)
 #define __NR_lsm_set_self_attr (__X32_SYSCALL_BIT + 460)
 #define __NR_lsm_list_modules (__X32_SYSCALL_BIT + 461)
+#define __NR_mseal (__X32_SYSCALL_BIT + 462)
 #define __NR_rt_sigaction (__X32_SYSCALL_BIT + 512)
 #define __NR_rt_sigreturn (__X32_SYSCALL_BIT + 513)
 #define __NR_ioctl (__X32_SYSCALL_BIT + 514)

linux-headers/linux/kvm.h

@@ -1217,9 +1217,9 @@ struct kvm_vfio_spapr_tce {
 /* Available with KVM_CAP_SPAPR_RESIZE_HPT */
 #define KVM_PPC_RESIZE_HPT_PREPARE _IOR(KVMIO, 0xad, struct kvm_ppc_resize_hpt)
 #define KVM_PPC_RESIZE_HPT_COMMIT  _IOR(KVMIO, 0xae, struct kvm_ppc_resize_hpt)
-/* Available with KVM_CAP_PPC_RADIX_MMU or KVM_CAP_PPC_HASH_MMU_V3 */
+/* Available with KVM_CAP_PPC_MMU_RADIX or KVM_CAP_PPC_MMU_HASH_V3 */
 #define KVM_PPC_CONFIGURE_V3_MMU  _IOW(KVMIO,  0xaf, struct kvm_ppc_mmuv3_cfg)
-/* Available with KVM_CAP_PPC_RADIX_MMU */
+/* Available with KVM_CAP_PPC_MMU_RADIX */
 #define KVM_PPC_GET_RMMU_INFO	  _IOW(KVMIO,  0xb0, struct kvm_ppc_rmmu_info)
 /* Available with KVM_CAP_PPC_GET_CPU_CHAR */
 #define KVM_PPC_GET_CPU_CHAR	  _IOR(KVMIO,  0xb1, struct kvm_ppc_cpu_char)

linux-headers/linux/stddef.h

@@ -55,4 +55,12 @@
 #define __counted_by(m)
 #endif
 
+#ifndef __counted_by_le
+#define __counted_by_le(m)
+#endif
+
+#ifndef __counted_by_be
+#define __counted_by_be(m)
+#endif
+
 #endif /* _LINUX_STDDEF_H */

meson.build

@@ -93,7 +93,7 @@ else
   iasl = find_program(get_option('iasl'), required: true)
 endif
 
-edk2_targets = [ 'arm-softmmu', 'aarch64-softmmu', 'i386-softmmu', 'x86_64-softmmu' ]
+edk2_targets = [ 'arm-softmmu', 'aarch64-softmmu', 'i386-softmmu', 'x86_64-softmmu', 'riscv64-softmmu' ]
 unpack_edk2_blobs = false
 foreach target : edk2_targets
   if target in target_dirs

net/vhost-vdpa.c

@@ -62,6 +62,7 @@ const int vdpa_feature_bits[] = {
     VIRTIO_F_RING_PACKED,
     VIRTIO_F_RING_RESET,
     VIRTIO_F_VERSION_1,
+    VIRTIO_F_NOTIFICATION_DATA,
     VIRTIO_NET_F_CSUM,
     VIRTIO_NET_F_CTRL_GUEST_OFFLOADS,
     VIRTIO_NET_F_CTRL_MAC_ADDR,
@@ -399,7 +400,10 @@ static int vhost_vdpa_net_data_load(NetClientState *nc)
     }
 
     for (int i = 0; i < v->dev->nvqs; ++i) {
-        vhost_vdpa_set_vring_ready(v, i + v->dev->vq_index);
+        int ret = vhost_vdpa_set_vring_ready(v, i + v->dev->vq_index);
+        if (ret < 0) {
+            return ret;
+        }
     }
     return 0;
 }
@@ -1238,7 +1242,10 @@ static int vhost_vdpa_net_cvq_load(NetClientState *nc)
 
     assert(nc->info->type == NET_CLIENT_DRIVER_VHOST_VDPA);
 
-    vhost_vdpa_set_vring_ready(v, v->dev->vq_index);
+    r = vhost_vdpa_set_vring_ready(v, v->dev->vq_index);
+    if (unlikely(r < 0)) {
+        return r;
+    }
 
     if (v->shadow_vqs_enabled) {
         n = VIRTIO_NET(v->dev->vdev);
@@ -1277,7 +1284,10 @@ static int vhost_vdpa_net_cvq_load(NetClientState *nc)
     }
 
     for (int i = 0; i < v->dev->vq_index; ++i) {
-        vhost_vdpa_set_vring_ready(v, i);
+        r = vhost_vdpa_set_vring_ready(v, i);
+        if (unlikely(r < 0)) {
+            return r;
+        }
     }
 
     return 0;

pc-bios/meson.build

@@ -4,6 +4,8 @@ if unpack_edk2_blobs
     'edk2-aarch64-code.fd',
     'edk2-arm-code.fd',
     'edk2-arm-vars.fd',
+    'edk2-riscv-code.fd',
+    'edk2-riscv-vars.fd',
     'edk2-i386-code.fd',
     'edk2-i386-secure-code.fd',
     'edk2-i386-vars.fd',

qapi/cxl.json

@@ -361,3 +361,192 @@
 ##
 {'command': 'cxl-inject-correctable-error',
  'data': {'path': 'str', 'type': 'CxlCorErrorType'}}
+
+##
+# @CxlDynamicCapacityExtent:
+#
+# A single dynamic capacity extent.  This is a contiguous allocation
+# of memory by Device Physical Address within a single Dynamic
+# Capacity Region on a CXL Type 3 Device.
+#
+# @offset: The offset (in bytes) to the start of the region
+#     where the extent belongs to.
+#
+# @len: The length of the extent in bytes.
+#
+# Since: 9.1
+##
+{ 'struct': 'CxlDynamicCapacityExtent',
+  'data': {
+      'offset':'uint64',
+      'len': 'uint64'
+  }
+}
+
+##
+# @CxlExtentSelectionPolicy:
+#
+# The policy to use for selecting which extents comprise the added
+# capacity, as defined in Compute Express Link (CXL) Specification,
+# Revision 3.1, Table 7-70.
+#
+# @free: Device is responsible for allocating the requested memory
+#     capacity and is free to do this using any combination of
+#     supported extents.
+#
+# @contiguous: Device is responsible for allocating the requested
+#     memory capacity but must do so as a single contiguous
+#     extent.
+#
+# @prescriptive: The precise set of extents to be allocated is
+#     specified by the command.  Thus allocation is being managed
+#     by the issuer of the allocation command, not the device.
+#
+# @enable-shared-access: Capacity has already been allocated to a
+#     different host using free, contiguous or prescriptive policy
+#     with a known tag.  This policy then instructs the device to
+#     make the capacity with the specified tag available to an
+#     additional host.  Capacity is implicit as it matches that
+#     already associated with the tag.  Note that the extent list
+#     (and hence Device Physical Addresses) used are per host, so
+#     a device may use different representations on each host.
+#     The ordering of the extents provided to each host is indicated
+#     to the host using per extent sequence numbers generated by
+#     the device.  Has a similar meaning for temporal sharing, but
+#     in that case there may be only one host involved.
+#
+# Since: 9.1
+##
+{ 'enum': 'CxlExtentSelectionPolicy',
+  'data': ['free',
+           'contiguous',
+           'prescriptive',
+           'enable-shared-access']
+}
+
+##
+# @cxl-add-dynamic-capacity:
+#
+# Initiate adding dynamic capacity extents to a host.  This simulates
+# operations defined in Compute Express Link (CXL) Specification,
+# Revision 3.1, Section 7.6.7.6.5. Note that, currently, establishing
+# success or failure of the full Add Dynamic Capacity flow requires
+# out of band communication with the OS of the CXL host.
+#
+# @path: path to the CXL Dynamic Capacity Device in the QOM tree.
+#
+# @host-id: The "Host ID" field as defined in Compute Express Link
+#     (CXL) Specification, Revision 3.1, Table 7-70.
+#
+# @selection-policy: The "Selection Policy" bits as defined in
+#     Compute Express Link (CXL) Specification, Revision 3.1,
+#     Table 7-70.  It specifies the policy to use for selecting
+#     which extents comprise the added capacity.
+#
+# @region: The "Region Number" field as defined in Compute Express
+#     Link (CXL) Specification, Revision 3.1, Table 7-70.  Valid
+#     range is from 0-7.
+#
+# @tag: The "Tag" field as defined in Compute Express Link (CXL)
+#     Specification, Revision 3.1, Table 7-70.
+#
+# @extents: The "Extent List" field as defined in Compute Express Link
+#     (CXL) Specification, Revision 3.1, Table 7-70.
+#
+# Features:
+#
+# @unstable: For now this command is subject to change.
+#
+# Since : 9.1
+##
+{ 'command': 'cxl-add-dynamic-capacity',
+  'data': { 'path': 'str',
+            'host-id': 'uint16',
+            'selection-policy': 'CxlExtentSelectionPolicy',
+            'region': 'uint8',
+            '*tag': 'str',
+            'extents': [ 'CxlDynamicCapacityExtent' ]
+           },
+  'features': [ 'unstable' ]
+}
+
+##
+# @CxlExtentRemovalPolicy:
+#
+# The policy to use for selecting which extents comprise the released
+# capacity, defined in the "Flags" field in Compute Express Link (CXL)
+# Specification, Revision 3.1, Table 7-71.
+#
+# @tag-based: Extents are selected by the device based on tag, with
+#     no requirement for contiguous extents.
+#
+# @prescriptive: Extent list of capacity to release is included in
+#     the request payload.
+#
+# Since: 9.1
+##
+{ 'enum': 'CxlExtentRemovalPolicy',
+  'data': ['tag-based',
+           'prescriptive']
+}
+
+##
+# @cxl-release-dynamic-capacity:
+#
+# Initiate release of dynamic capacity extents from a host.  This
+# simulates operations defined in Compute Express Link (CXL)
+# Specification, Revision 3.1, Section 7.6.7.6.6. Note that,
+# currently, success or failure of the full Release Dynamic Capacity
+# flow requires out of band communication with the OS of the CXL host.
+#
+# @path: path to the CXL Dynamic Capacity Device in the QOM tree.
+#
+# @host-id: The "Host ID" field as defined in Compute Express Link
+#     (CXL) Specification, Revision 3.1, Table 7-71.
+#
+# @removal-policy: Bit[3:0] of the "Flags" field as defined in
+#     Compute Express Link (CXL) Specification, Revision 3.1,
+#     Table 7-71.
+#
+# @forced-removal: Bit[4] of the "Flags" field in Compute Express
+#     Link (CXL) Specification, Revision 3.1, Table 7-71.  When set,
+#     the device does not wait for a Release Dynamic Capacity command
+#     from the host.  Instead, the host immediately looses access to
+#     the released capacity.
+#
+# @sanitize-on-release: Bit[5] of the "Flags" field in Compute
+#     Express Link (CXL) Specification, Revision 3.1, Table 7-71.
+#     When set, the device should sanitize all released capacity as
+#     a result of this request. This ensures that all user data
+#     and metadata is made permanently unavailable by whatever
+#     means is appropriate for the media type. Note that changing
+#     encryption keys is not sufficient.
+#
+# @region: The "Region Number" field as defined in Compute Express
+#     Link Specification, Revision 3.1, Table 7-71.  Valid range
+#     is from 0-7.
+#
+# @tag: The "Tag" field as defined in Compute Express Link (CXL)
+#     Specification, Revision 3.1, Table 7-71.
+#
+# @extents: The "Extent List" field as defined in Compute Express
+#     Link (CXL) Specification, Revision 3.1, Table 7-71.
+#
+# Features:
+#
+# @unstable: For now this command is subject to change.
+#
+# Since : 9.1
+##
+{ 'command': 'cxl-release-dynamic-capacity',
+  'data': { 'path': 'str',
+            'host-id': 'uint16',
+            'removal-policy': 'CxlExtentRemovalPolicy',
+            '*forced-removal': 'bool',
+            '*sanitize-on-release': 'bool',
+            'region': 'uint8',
+            '*tag': 'str',
+            'extents': [ 'CxlDynamicCapacityExtent' ]
+           },
+  'features': [ 'unstable' ]
+}

qapi/qom.json

@@ -600,7 +600,9 @@
 #     preallocation threads (default: none) (since 7.2)
 #
 # @share: if false, the memory is private to QEMU; if true, it is
-#     shared (default: false)
+#     shared (default false for backends memory-backend-file and
+#     memory-backend-ram, true for backends memory-backend-epc,
+#     memory-backend-memfd, and memory-backend-shm)
 #
 # @reserve: if true, reserve swap space (or huge pages) if applicable
 #     (default: true) (since 6.1)
@@ -700,8 +702,6 @@
 #
 # Properties for memory-backend-memfd objects.
 #
-# The @share boolean option is true by default with memfd.
-#
 # @hugetlb: if true, the file to be created resides in the hugetlbfs
 #     filesystem (default: false)
 #
@@ -721,13 +721,26 @@
             '*hugetlbsize': 'size',
             '*seal': 'bool' } }
 
+##
+# @MemoryBackendShmProperties:
+#
+# Properties for memory-backend-shm objects.
+#
+# This memory backend supports only shared memory, which is the
+# default.
+#
+# Since: 9.1
+##
+{ 'struct': 'MemoryBackendShmProperties',
+  'base': 'MemoryBackendProperties',
+  'data': { },
+  'if': 'CONFIG_POSIX' }
+
 ##
 # @MemoryBackendEpcProperties:
 #
 # Properties for memory-backend-epc objects.
 #
-# The @share boolean option is true by default with epc
-#
 # The @merge boolean option is false by default with epc
 #
 # The @dump boolean option is false by default with epc
@@ -1051,6 +1064,8 @@
     { 'name': 'memory-backend-memfd',
       'if': 'CONFIG_LINUX' },
     'memory-backend-ram',
+    { 'name': 'memory-backend-shm',
+      'if': 'CONFIG_POSIX' },
     'pef-guest',
     { 'name': 'pr-manager-helper',
       'if': 'CONFIG_LINUX' },
@@ -1123,6 +1138,8 @@
       'memory-backend-memfd':       { 'type': 'MemoryBackendMemfdProperties',
                                       'if': 'CONFIG_LINUX' },
       'memory-backend-ram':         'MemoryBackendProperties',
+      'memory-backend-shm':         { 'type': 'MemoryBackendShmProperties',
+                                      'if': 'CONFIG_POSIX' },
       'pr-manager-helper':          { 'type': 'PrManagerHelperProperties',
                                       'if': 'CONFIG_LINUX' },
       'qtest':                      'QtestProperties',

qapi/run-state.json

@@ -462,6 +462,20 @@
 { 'event': 'GUEST_CRASHLOADED',
   'data': { 'action': 'GuestPanicAction', '*info': 'GuestPanicInformation' } }
 
+##
+# @GUEST_PVSHUTDOWN:
+#
+# Emitted when guest submits a shutdown request via pvpanic interface
+#
+# Since: 9.1
+#
+# Example:
+#
+#     <- { "event": "GUEST_PVSHUTDOWN",
+#          "timestamp": { "seconds": 1648245259, "microseconds": 893771 } }
+##
+{ 'event': 'GUEST_PVSHUTDOWN' }
+
 ##
 # @GuestPanicAction:
 #

qemu-options.hx

@@ -5240,6 +5240,22 @@ SRST
 
         The ``share`` boolean option is on by default with memfd.
 
+    ``-object memory-backend-shm,id=id,merge=on|off,dump=on|off,share=on|off,prealloc=on|off,size=size,host-nodes=host-nodes,policy=default|preferred|bind|interleave``
+        Creates a POSIX shared memory backend object, which allows
+        QEMU to share the memory with an external process (e.g. when
+        using vhost-user).
+
+        ``memory-backend-shm`` is a more portable and less featureful version
+        of ``memory-backend-memfd``. It can then be used in any POSIX system,
+        especially when memfd is not supported.
+
+        Please refer to ``memory-backend-file`` for a description of the
+        options.
+
+        The ``share`` boolean option is on by default with shm. Setting it to
+        off will cause a failure during allocation because it is not supported
+        by this backend.
+
     ``-object iommufd,id=id[,fd=fd]``
         Creates an iommufd backend which allows control of DMA mapping
         through the ``/dev/iommu`` device.

subprojects/libvhost-user/libvhost-user.c

@@ -568,7 +568,7 @@ vu_message_read_default(VuDev *dev, int conn_fd, VhostUserMsg *vmsg)
         if (cmsg->cmsg_level == SOL_SOCKET && cmsg->cmsg_type == SCM_RIGHTS) {
             fd_size = cmsg->cmsg_len - CMSG_LEN(0);
             vmsg->fd_num = fd_size / sizeof(int);
-            assert(fd_size < VHOST_MEMORY_BASELINE_NREGIONS);
+            assert(vmsg->fd_num <= VHOST_MEMORY_BASELINE_NREGIONS);
             memcpy(vmsg->fds, CMSG_DATA(cmsg), fd_size);
             break;
         }
@@ -632,12 +632,18 @@ vu_message_write(VuDev *dev, int conn_fd, VhostUserMsg *vmsg)
         memcpy(CMSG_DATA(cmsg), vmsg->fds, fdsize);
     } else {
         msg.msg_controllen = 0;
+        msg.msg_control = NULL;
     }
 
     do {
         rc = sendmsg(conn_fd, &msg, 0);
     } while (rc < 0 && (errno == EINTR || errno == EAGAIN));
 
+    if (rc <= 0) {
+        vu_panic(dev, "Error while writing: %s", strerror(errno));
+        return false;
+    }
+
     if (vmsg->size) {
         do {
             if (vmsg->data) {
@@ -1668,6 +1674,17 @@ vu_get_protocol_features_exec(VuDev *dev, VhostUserMsg *vmsg)
         features |= dev->iface->get_protocol_features(dev);
     }
 
+#ifndef MFD_ALLOW_SEALING
+    /*
+     * If MFD_ALLOW_SEALING is not defined, we are not able to handle
+     * VHOST_USER_GET_INFLIGHT_FD messages, since we can't create a memfd.
+     * Those messages are used only if VHOST_USER_PROTOCOL_F_INFLIGHT_SHMFD
+     * is negotiated. A device implementation can enable it, so let's mask
+     * it to avoid a runtime panic.
+     */
+    features &= ~(1ULL << VHOST_USER_PROTOCOL_F_INFLIGHT_SHMFD);
+#endif
+
     vmsg_set_reply_u64(vmsg, features);
     return true;
 }

system/runstate.c

@@ -584,6 +584,12 @@ void qemu_system_guest_crashloaded(GuestPanicInformation *info)
     qapi_free_GuestPanicInformation(info);
 }
 
+void qemu_system_guest_pvshutdown(void)
+{
+    qapi_event_send_guest_pvshutdown();
+    qemu_system_shutdown_request(SHUTDOWN_CAUSE_GUEST_SHUTDOWN);
+}
+
 void qemu_system_reset_request(ShutdownCause reason)
 {
     if (reboot_action == REBOOT_ACTION_SHUTDOWN &&

target/i386/kvm/kvm.c

@@ -2706,11 +2706,7 @@ int kvm_arch_init(MachineState *ms, KVMState *s)
     }
 
     /* Tell fw_cfg to notify the BIOS to reserve the range. */
-    ret = e820_add_entry(identity_base, 0x4000, E820_RESERVED);
+    e820_add_entry(identity_base, 0x4000, E820_RESERVED);
-    if (ret < 0) {
-        fprintf(stderr, "e820_add_entry() table is full\n");
-        return ret;
-    }
 
     shadow_mem = object_property_get_int(OBJECT(s), "kvm-shadow-mem", &error_abort);
     if (shadow_mem != -1) {

target/i386/kvm/xen-emu.c

@@ -176,12 +176,7 @@ int kvm_xen_init(KVMState *s, uint32_t hypercall_msr)
     s->xen_caps = xen_caps;
 
     /* Tell fw_cfg to notify the BIOS to reserve the range. */
-    ret = e820_add_entry(XEN_SPECIAL_AREA_ADDR, XEN_SPECIAL_AREA_SIZE,
+    e820_add_entry(XEN_SPECIAL_AREA_ADDR, XEN_SPECIAL_AREA_SIZE, E820_RESERVED);
-                         E820_RESERVED);
-    if (ret < 0) {
-        fprintf(stderr, "e820_add_entry() table is full\n");
-        return ret;
-    }
 
     /* The pages couldn't be overlaid until KVM was initialized */
     xen_primary_console_reset();