virtio,pci,pc: features,fixes

pci: Initial support for SPDM Responders
 cxl: Add support for scan media, feature commands, device patrol scrub
     control, DDR5 ECS control, firmware updates
 virtio: in-order support
 virtio-net: support for SR-IOV emulation (note: known issues on s390,
                                           might get reverted if not fixed)
 smbios: memory device size is now configurable per Machine
 cpu: architecture agnostic code to support vCPU Hotplug
 
 Fixes, cleanups all over the place.
 
 Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
 -----BEGIN PGP SIGNATURE-----
 
 iQFDBAABCAAtFiEEXQn9CHHI+FuUyooNKB8NuNKNVGkFAmae9l8PHG1zdEByZWRo
 YXQuY29tAAoJECgfDbjSjVRp8fYH/impBH9nViO/WK48io4mLSkl0EUL8Y/xrMvH
 zKFCKaXq8D96VTt1Z4EGKYgwG0voBKZaCEKYU/0ARGnSlSwxINQ8ROCnBWMfn2sx
 yQt08EXVMznNLtXjc6U5zCoCi6SaV85GH40No3MUFXBQt29ZSlFqO/fuHGZHYBwS
 wuVKvTjjNF4EsGt3rS4Qsv6BwZWMM+dE6yXpKWk68kR8IGp+6QGxkMbWt9uEX2Md
 VuemKVnFYw0XGCGy5K+ZkvoA2DGpEw0QxVSOMs8CI55Oc9SkTKz5fUSzXXGo1if+
 M1CTjOPJu6pMym6gy6XpFa8/QioDA/jE2vBQvfJ64TwhJDV159s=
 =k8e9
 -----END PGP SIGNATURE-----

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

virtio,pci,pc: features,fixes

pci: Initial support for SPDM Responders
cxl: Add support for scan media, feature commands, device patrol scrub
    control, DDR5 ECS control, firmware updates
virtio: in-order support
virtio-net: support for SR-IOV emulation (note: known issues on s390,
                                          might get reverted if not fixed)
smbios: memory device size is now configurable per Machine
cpu: architecture agnostic code to support vCPU Hotplug

Fixes, cleanups all over the place.

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

# -----BEGIN PGP SIGNATURE-----
#
# iQFDBAABCAAtFiEEXQn9CHHI+FuUyooNKB8NuNKNVGkFAmae9l8PHG1zdEByZWRo
# YXQuY29tAAoJECgfDbjSjVRp8fYH/impBH9nViO/WK48io4mLSkl0EUL8Y/xrMvH
# zKFCKaXq8D96VTt1Z4EGKYgwG0voBKZaCEKYU/0ARGnSlSwxINQ8ROCnBWMfn2sx
# yQt08EXVMznNLtXjc6U5zCoCi6SaV85GH40No3MUFXBQt29ZSlFqO/fuHGZHYBwS
# wuVKvTjjNF4EsGt3rS4Qsv6BwZWMM+dE6yXpKWk68kR8IGp+6QGxkMbWt9uEX2Md
# VuemKVnFYw0XGCGy5K+ZkvoA2DGpEw0QxVSOMs8CI55Oc9SkTKz5fUSzXXGo1if+
# M1CTjOPJu6pMym6gy6XpFa8/QioDA/jE2vBQvfJ64TwhJDV159s=
# =k8e9
# -----END PGP SIGNATURE-----
# gpg: Signature made Tue 23 Jul 2024 10:16:31 AM AEST
# 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: The key's User ID 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: (61 commits)
  hw/nvme: Add SPDM over DOE support
  backends: Initial support for SPDM socket support
  hw/pci: Add all Data Object Types defined in PCIe r6.0
  tests/acpi: Add expected ACPI AML files for RISC-V
  tests/qtest/bios-tables-test.c: Enable basic testing for RISC-V
  tests/acpi: Add empty ACPI data files for RISC-V
  tests/qtest/bios-tables-test.c: Remove the fall back path
  tests/acpi: update expected DSDT blob for aarch64 and microvm
  acpi/gpex: Create PCI link devices outside PCI root bridge
  tests/acpi: Allow DSDT acpi table changes for aarch64
  hw/riscv/virt-acpi-build.c: Update the HID of RISC-V UART
  hw/riscv/virt-acpi-build.c: Add namespace devices for PLIC and APLIC
  virtio-iommu: Add trace point on virtio_iommu_detach_endpoint_from_domain
  hw/vfio/common: Add vfio_listener_region_del_iommu trace event
  virtio-iommu: Remove the end point on detach
  virtio-iommu: Free [host_]resv_ranges on unset_iommu_devices
  virtio-iommu: Remove probe_done
  Revert "virtio-iommu: Clear IOMMUDevice when VFIO device is unplugged"
  gdbstub: Add helper function to unregister GDB register space
  physmem: Add helper function to destroy CPU AddressSpace
  ...

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

MAINTAINERS

@@ -2009,6 +2009,7 @@ F: hw/pci-bridge/*
 F: qapi/pci.json
 F: docs/pci*
 F: docs/specs/*pci*
+F: docs/system/sriov.rst
 
 PCIE DOE
 M: Huai-Cheng Kuo <hchkuo@avery-design.com.tw>
@@ -2208,6 +2209,7 @@ F: docs/devel/vfio-iommufd.rst
 
 vhost
 M: Michael S. Tsirkin <mst@redhat.com>
+R: Stefano Garzarella <sgarzare@redhat.com>
 S: Supported
 F: hw/*/*vhost*
 F: docs/interop/vhost-user.json
@@ -3398,6 +3400,12 @@ F: tests/qtest/*tpm*
 F: docs/specs/tpm.rst
 T: git https://github.com/stefanberger/qemu-tpm.git tpm-next
 
+SPDM
+M: Alistair Francis <alistair.francis@wdc.com>
+S: Maintained
+F: backends/spdm-socket.c
+F: include/sysemu/spdm-socket.h
+
 Checkpatch
 S: Odd Fixes
 F: scripts/checkpatch.pl
@@ -3657,6 +3665,7 @@ F: tests/uefi-test-tools/
 VT-d Emulation
 M: Michael S. Tsirkin <mst@redhat.com>
 R: Jason Wang <jasowang@redhat.com>
+R: Yi Liu <yi.l.liu@intel.com>
 S: Supported
 F: hw/i386/intel_iommu.c
 F: hw/i386/intel_iommu_internal.h

accel/kvm/kvm-all.c

@@ -340,14 +340,71 @@ err:
     return ret;
 }
 
+void kvm_park_vcpu(CPUState *cpu)
+{
+    struct KVMParkedVcpu *vcpu;
+
+    trace_kvm_park_vcpu(cpu->cpu_index, kvm_arch_vcpu_id(cpu));
+
+    vcpu = g_malloc0(sizeof(*vcpu));
+    vcpu->vcpu_id = kvm_arch_vcpu_id(cpu);
+    vcpu->kvm_fd = cpu->kvm_fd;
+    QLIST_INSERT_HEAD(&kvm_state->kvm_parked_vcpus, vcpu, node);
+}
+
+int kvm_unpark_vcpu(KVMState *s, unsigned long vcpu_id)
+{
+    struct KVMParkedVcpu *cpu;
+    int kvm_fd = -ENOENT;
+
+    QLIST_FOREACH(cpu, &s->kvm_parked_vcpus, node) {
+        if (cpu->vcpu_id == vcpu_id) {
+            QLIST_REMOVE(cpu, node);
+            kvm_fd = cpu->kvm_fd;
+            g_free(cpu);
+        }
+    }
+
+    trace_kvm_unpark_vcpu(vcpu_id, kvm_fd > 0 ? "unparked" : "!found parked");
+
+    return kvm_fd;
+}
+
+int kvm_create_vcpu(CPUState *cpu)
+{
+    unsigned long vcpu_id = kvm_arch_vcpu_id(cpu);
+    KVMState *s = kvm_state;
+    int kvm_fd;
+
+    /* check if the KVM vCPU already exist but is parked */
+    kvm_fd = kvm_unpark_vcpu(s, vcpu_id);
+    if (kvm_fd < 0) {
+        /* vCPU not parked: create a new KVM vCPU */
+        kvm_fd = kvm_vm_ioctl(s, KVM_CREATE_VCPU, vcpu_id);
+        if (kvm_fd < 0) {
+            error_report("KVM_CREATE_VCPU IOCTL failed for vCPU %lu", vcpu_id);
+            return kvm_fd;
+        }
+    }
+
+    cpu->kvm_fd = kvm_fd;
+    cpu->kvm_state = s;
+    cpu->vcpu_dirty = true;
+    cpu->dirty_pages = 0;
+    cpu->throttle_us_per_full = 0;
+
+    trace_kvm_create_vcpu(cpu->cpu_index, vcpu_id, kvm_fd);
+
+    return 0;
+}
+
 static int do_kvm_destroy_vcpu(CPUState *cpu)
 {
     KVMState *s = kvm_state;
     long mmap_size;
-    struct KVMParkedVcpu *vcpu = NULL;
     int ret = 0;
 
-    trace_kvm_destroy_vcpu();
+    trace_kvm_destroy_vcpu(cpu->cpu_index, kvm_arch_vcpu_id(cpu));
 
     ret = kvm_arch_destroy_vcpu(cpu);
     if (ret < 0) {
@@ -373,10 +430,7 @@ static int do_kvm_destroy_vcpu(CPUState *cpu)
         }
     }
 
-    vcpu = g_malloc0(sizeof(*vcpu));
-    vcpu->vcpu_id = kvm_arch_vcpu_id(cpu);
-    vcpu->kvm_fd = cpu->kvm_fd;
-    QLIST_INSERT_HEAD(&kvm_state->kvm_parked_vcpus, vcpu, node);
+    kvm_park_vcpu(cpu);
 err:
     return ret;
 }
@@ -389,24 +443,6 @@ void kvm_destroy_vcpu(CPUState *cpu)
     }
 }
 
-static int kvm_get_vcpu(KVMState *s, unsigned long vcpu_id)
-{
-    struct KVMParkedVcpu *cpu;
-
-    QLIST_FOREACH(cpu, &s->kvm_parked_vcpus, node) {
-        if (cpu->vcpu_id == vcpu_id) {
-            int kvm_fd;
-
-            QLIST_REMOVE(cpu, node);
-            kvm_fd = cpu->kvm_fd;
-            g_free(cpu);
-            return kvm_fd;
-        }
-    }
-
-    return kvm_vm_ioctl(s, KVM_CREATE_VCPU, (void *)vcpu_id);
-}
-
 int kvm_init_vcpu(CPUState *cpu, Error **errp)
 {
     KVMState *s = kvm_state;
@@ -415,19 +451,14 @@ int kvm_init_vcpu(CPUState *cpu, Error **errp)
 
     trace_kvm_init_vcpu(cpu->cpu_index, kvm_arch_vcpu_id(cpu));
 
-    ret = kvm_get_vcpu(s, kvm_arch_vcpu_id(cpu));
+    ret = kvm_create_vcpu(cpu);
     if (ret < 0) {
-        error_setg_errno(errp, -ret, "kvm_init_vcpu: kvm_get_vcpu failed (%lu)",
+        error_setg_errno(errp, -ret,
+                         "kvm_init_vcpu: kvm_create_vcpu failed (%lu)",
                          kvm_arch_vcpu_id(cpu));
         goto err;
     }
 
-    cpu->kvm_fd = ret;
-    cpu->kvm_state = s;
-    cpu->vcpu_dirty = true;
-    cpu->dirty_pages = 0;
-    cpu->throttle_us_per_full = 0;
-
     mmap_size = kvm_ioctl(s, KVM_GET_VCPU_MMAP_SIZE, 0);
     if (mmap_size < 0) {
         ret = mmap_size;

accel/kvm/kvm-cpus.h

@@ -22,5 +22,4 @@ bool kvm_supports_guest_debug(void);
 int kvm_insert_breakpoint(CPUState *cpu, int type, vaddr addr, vaddr len);
 int kvm_remove_breakpoint(CPUState *cpu, int type, vaddr addr, vaddr len);
 void kvm_remove_all_breakpoints(CPUState *cpu);
-
 #endif /* KVM_CPUS_H */

accel/kvm/trace-events

@@ -9,6 +9,10 @@ kvm_device_ioctl(int fd, int type, void *arg) "dev fd %d, type 0x%x, arg %p"
 kvm_failed_reg_get(uint64_t id, const char *msg) "Warning: Unable to retrieve ONEREG %" PRIu64 " from KVM: %s"
 kvm_failed_reg_set(uint64_t id, const char *msg) "Warning: Unable to set ONEREG %" PRIu64 " to KVM: %s"
 kvm_init_vcpu(int cpu_index, unsigned long arch_cpu_id) "index: %d id: %lu"
+kvm_create_vcpu(int cpu_index, unsigned long arch_cpu_id, int kvm_fd) "index: %d, id: %lu, kvm fd: %d"
+kvm_destroy_vcpu(int cpu_index, unsigned long arch_cpu_id) "index: %d id: %lu"
+kvm_park_vcpu(int cpu_index, unsigned long arch_cpu_id) "index: %d id: %lu"
+kvm_unpark_vcpu(unsigned long arch_cpu_id, const char *msg) "id: %lu %s"
 kvm_irqchip_commit_routes(void) ""
 kvm_irqchip_add_msi_route(char *name, int vector, int virq) "dev %s vector %d virq %d"
 kvm_irqchip_update_msi_route(int virq) "Updating MSI route virq=%d"
@@ -25,7 +29,6 @@ kvm_dirty_ring_reaper(const char *s) "%s"
 kvm_dirty_ring_reap(uint64_t count, int64_t t) "reaped %"PRIu64" pages (took %"PRIi64" us)"
 kvm_dirty_ring_reaper_kick(const char *reason) "%s"
 kvm_dirty_ring_flush(int finished) "%d"
-kvm_destroy_vcpu(void) ""
 kvm_failed_get_vcpu_mmap_size(void) ""
 kvm_cpu_exec(void) ""
 kvm_interrupt_exit_request(void) ""

backends/Kconfig

@@ -3,3 +3,7 @@ source tpm/Kconfig
 config IOMMUFD
     bool
     depends on VFIO
+
+config SPDM_SOCKET
+    bool
+    default y

backends/meson.build

@@ -33,4 +33,6 @@ endif
 system_ss.add(when: gio, if_true: files('dbus-vmstate.c'))
 system_ss.add(when: 'CONFIG_SGX', if_true: files('hostmem-epc.c'))
 
+system_ss.add(when: 'CONFIG_SPDM_SOCKET', if_true: files('spdm-socket.c'))
+
 subdir('tpm')

backends/spdm-socket.c

@@ -0,0 +1,216 @@
+/* SPDX-License-Identifier: BSD-3-Clause */
+/*
+ * QEMU SPDM socket support
+ *
+ * This is based on:
+ * https://github.com/DMTF/spdm-emu/blob/07c0a838bcc1c6207c656ac75885c0603e344b6f/spdm_emu/spdm_emu_common/command.c
+ * but has been re-written to match QEMU style
+ *
+ * Copyright (c) 2021, DMTF. All rights reserved.
+ * Copyright (c) 2023. Western Digital Corporation or its affiliates.
+ */
+
+#include "qemu/osdep.h"
+#include "sysemu/spdm-socket.h"
+#include "qapi/error.h"
+
+static bool read_bytes(const int socket, uint8_t *buffer,
+                       size_t number_of_bytes)
+{
+    ssize_t number_received = 0;
+    ssize_t result;
+
+    while (number_received < number_of_bytes) {
+        result = recv(socket, buffer + number_received,
+                      number_of_bytes - number_received, 0);
+        if (result <= 0) {
+            return false;
+        }
+        number_received += result;
+    }
+    return true;
+}
+
+static bool read_data32(const int socket, uint32_t *data)
+{
+    bool result;
+
+    result = read_bytes(socket, (uint8_t *)data, sizeof(uint32_t));
+    if (!result) {
+        return result;
+    }
+    *data = ntohl(*data);
+    return true;
+}
+
+static bool read_multiple_bytes(const int socket, uint8_t *buffer,
+                                uint32_t *bytes_received,
+                                uint32_t max_buffer_length)
+{
+    uint32_t length;
+    bool result;
+
+    result = read_data32(socket, &length);
+    if (!result) {
+        return result;
+    }
+
+    if (length > max_buffer_length) {
+        return false;
+    }
+
+    if (bytes_received) {
+        *bytes_received = length;
+    }
+
+    if (length == 0) {
+        return true;
+    }
+
+    return read_bytes(socket, buffer, length);
+}
+
+static bool receive_platform_data(const int socket,
+                                  uint32_t transport_type,
+                                  uint32_t *command,
+                                  uint8_t *receive_buffer,
+                                  uint32_t *bytes_to_receive)
+{
+    bool result;
+    uint32_t response;
+    uint32_t bytes_received;
+
+    result = read_data32(socket, &response);
+    if (!result) {
+        return result;
+    }
+    *command = response;
+
+    result = read_data32(socket, &transport_type);
+    if (!result) {
+        return result;
+    }
+
+    bytes_received = 0;
+    result = read_multiple_bytes(socket, receive_buffer, &bytes_received,
+                                 *bytes_to_receive);
+    if (!result) {
+        return result;
+    }
+    *bytes_to_receive = bytes_received;
+
+    return result;
+}
+
+static bool write_bytes(const int socket, const uint8_t *buffer,
+                        uint32_t number_of_bytes)
+{
+    ssize_t number_sent = 0;
+    ssize_t result;
+
+    while (number_sent < number_of_bytes) {
+        result = send(socket, buffer + number_sent,
+                      number_of_bytes - number_sent, 0);
+        if (result == -1) {
+            return false;
+        }
+        number_sent += result;
+    }
+    return true;
+}
+
+static bool write_data32(const int socket, uint32_t data)
+{
+    data = htonl(data);
+    return write_bytes(socket, (uint8_t *)&data, sizeof(uint32_t));
+}
+
+static bool write_multiple_bytes(const int socket, const uint8_t *buffer,
+                                 uint32_t bytes_to_send)
+{
+    bool result;
+
+    result = write_data32(socket, bytes_to_send);
+    if (!result) {
+        return result;
+    }
+
+    return write_bytes(socket, buffer, bytes_to_send);
+}
+
+static bool send_platform_data(const int socket,
+                               uint32_t transport_type, uint32_t command,
+                               const uint8_t *send_buffer, size_t bytes_to_send)
+{
+    bool result;
+
+    result = write_data32(socket, command);
+    if (!result) {
+        return result;
+    }
+
+    result = write_data32(socket, transport_type);
+    if (!result) {
+        return result;
+    }
+
+    return write_multiple_bytes(socket, send_buffer, bytes_to_send);
+}
+
+int spdm_socket_connect(uint16_t port, Error **errp)
+{
+    int client_socket;
+    struct sockaddr_in server_addr;
+
+    client_socket = socket(AF_INET, SOCK_STREAM, IPPROTO_TCP);
+    if (client_socket < 0) {
+        error_setg(errp, "cannot create socket: %s", strerror(errno));
+        return -1;
+    }
+
+    memset((char *)&server_addr, 0, sizeof(server_addr));
+    server_addr.sin_family = AF_INET;
+    server_addr.sin_addr.s_addr = htonl(INADDR_LOOPBACK);
+    server_addr.sin_port = htons(port);
+
+
+    if (connect(client_socket, (struct sockaddr *)&server_addr,
+                sizeof(server_addr)) < 0) {
+        error_setg(errp, "cannot connect: %s", strerror(errno));
+        close(client_socket);
+        return -1;
+    }
+
+    return client_socket;
+}
+
+uint32_t spdm_socket_rsp(const int socket, uint32_t transport_type,
+                         void *req, uint32_t req_len,
+                         void *rsp, uint32_t rsp_len)
+{
+    uint32_t command;
+    bool result;
+
+    result = send_platform_data(socket, transport_type,
+                                SPDM_SOCKET_COMMAND_NORMAL,
+                                req, req_len);
+    if (!result) {
+        return 0;
+    }
+
+    result = receive_platform_data(socket, transport_type, &command,
+                                   (uint8_t *)rsp, &rsp_len);
+    if (!result) {
+        return 0;
+    }
+
+    assert(command != 0);
+
+    return rsp_len;
+}
+
+void spdm_socket_close(const int socket, uint32_t transport_type)
+{
+    send_platform_data(socket, transport_type,
+                       SPDM_SOCKET_COMMAND_SHUTDOWN, NULL, 0);
+}

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

@@ -196,7 +196,7 @@ vub_discard_write_zeroes(VubReq *req, struct iovec *iov, uint32_t iovcnt,
     VubDev *vdev_blk = req->vdev_blk;
     desc = buf;
     uint64_t range[2] = { le64_to_cpu(desc->sector) << 9,
-                          le32_to_cpu(desc->num_sectors) << 9 };
+                          (uint64_t)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);

docs/specs/acpi_hw_reduced_hotplug.rst

@@ -64,7 +64,8 @@ GED IO interface (4 byte access)
        0: Memory hotplug event
        1: System power down event
        2: NVDIMM hotplug event
-    3-31: Reserved
+       3: CPU hotplug event
+    4-31: Reserved
 
 **write_access:**
 

docs/specs/index.rst

@@ -29,6 +29,7 @@ guest hardware that is specific to QEMU.
    edu
    ivshmem-spec
    pvpanic
+   spdm
    standard-vga
    virt-ctlr
    vmcoreinfo

docs/specs/spdm.rst

@@ -0,0 +1,134 @@
+======================================================
+QEMU Security Protocols and Data Models (SPDM) Support
+======================================================
+
+SPDM enables authentication, attestation and key exchange to assist in
+providing infrastructure security enablement. It's a standard published
+by the `DMTF`_.
+
+QEMU supports connecting to a SPDM responder implementation. This allows an
+external application to emulate the SPDM responder logic for an SPDM device.
+
+Setting up a SPDM server
+========================
+
+When using QEMU with SPDM devices QEMU will connect to a server which
+implements the SPDM functionality.
+
+SPDM-Utils
+----------
+
+You can use `SPDM Utils`_ to emulate a responder. This is the simplest method.
+
+SPDM-Utils is a Linux applications to manage, test and develop devices
+supporting DMTF Security Protocol and Data Model (SPDM). It is written in Rust
+and utilises libspdm.
+
+To use SPDM-Utils you will need to do the following steps. Details are included
+in the SPDM-Utils README.
+
+ 1. `Build libspdm`_
+ 2. `Build SPDM Utils`_
+ 3. `Run it as a server`_
+
+spdm-emu
+--------
+
+You can use `spdm emu`_ to model the
+SPDM responder.
+
+.. code-block:: shell
+
+    $ cd spdm-emu
+    $ git submodule init; git submodule update --recursive
+    $ mkdir build; cd build
+    $ cmake -DARCH=x64 -DTOOLCHAIN=GCC -DTARGET=Debug -DCRYPTO=openssl ..
+    $ make -j32
+    $ make copy_sample_key # Build certificates, required for SPDM authentication.
+
+It is worth noting that the certificates should be in compliance with
+PCIe r6.1 sec 6.31.3. This means you will need to add the following to
+openssl.cnf
+
+.. code-block::
+
+    subjectAltName = otherName:2.23.147;UTF8:Vendor=1b36:Device=0010:CC=010802:REV=02:SSVID=1af4:SSID=1100
+    2.23.147 = ASN1:OID:2.23.147
+
+and then manually regenerate some certificates with:
+
+.. code-block:: shell
+
+    $ openssl req -nodes -newkey ec:param.pem -keyout end_responder.key \
+        -out end_responder.req -sha384 -batch \
+        -subj "/CN=DMTF libspdm ECP384 responder cert"
+
+    $ openssl x509 -req -in end_responder.req -out end_responder.cert \
+        -CA inter.cert -CAkey inter.key -sha384 -days 3650 -set_serial 3 \
+        -extensions v3_end -extfile ../openssl.cnf
+
+    $ openssl asn1parse -in end_responder.cert -out end_responder.cert.der
+
+    $ cat ca.cert.der inter.cert.der end_responder.cert.der > bundle_responder.certchain.der
+
+You can use SPDM-Utils instead as it will generate the correct certificates
+automatically.
+
+The responder can then be launched with
+
+.. code-block:: shell
+
+    $ cd bin
+    $ ./spdm_responder_emu --trans PCI_DOE
+
+Connecting an SPDM NVMe device
+==============================
+
+Once a SPDM server is running we can start QEMU and connect to the server.
+
+For an NVMe device first let's setup a block we can use
+
+.. code-block:: shell
+
+    $ cd qemu-spdm/linux/image
+    $ dd if=/dev/zero of=blknvme bs=1M count=2096 # 2GB NNMe Drive
+
+Then you can add this to your QEMU command line:
+
+.. code-block:: shell
+
+    -drive file=blknvme,if=none,id=mynvme,format=raw \
+        -device nvme,drive=mynvme,serial=deadbeef,spdm_port=2323
+
+At which point QEMU will try to connect to the SPDM server.
+
+Note that if using x64-64 you will want to use the q35 machine instead
+of the default. So the entire QEMU command might look like this
+
+.. code-block:: shell
+
+    qemu-system-x86_64 -M q35 \
+        --kernel bzImage \
+        -drive file=rootfs.ext2,if=virtio,format=raw \
+        -append "root=/dev/vda console=ttyS0" \
+        -net none -nographic \
+        -drive file=blknvme,if=none,id=mynvme,format=raw \
+        -device nvme,drive=mynvme,serial=deadbeef,spdm_port=2323
+
+.. _DMTF:
+   https://www.dmtf.org/standards/SPDM
+
+.. _SPDM Utils:
+   https://github.com/westerndigitalcorporation/spdm-utils
+
+.. _spdm emu:
+   https://github.com/dmtf/spdm-emu
+
+.. _Build libspdm:
+   https://github.com/westerndigitalcorporation/spdm-utils?tab=readme-ov-file#build-libspdm
+
+.. _Build SPDM Utils:
+   https://github.com/westerndigitalcorporation/spdm-utils?tab=readme-ov-file#build-the-binary
+
+.. _Run it as a server:
+   https://github.com/westerndigitalcorporation/spdm-utils#qemu-spdm-device-emulation

docs/system/index.rst

@@ -39,3 +39,4 @@ or Hypervisor.Framework.
    multi-process
    confidential-guest-support
    vm-templating
+   sriov

docs/system/sriov.rst

@@ -0,0 +1,36 @@
+.. SPDX-License-Identifier: GPL-2.0-or-later
+
+Compsable SR-IOV device
+=======================
+
+SR-IOV (Single Root I/O Virtualization) is an optional extended capability of a
+PCI Express device. It allows a single physical function (PF) to appear as
+multiple virtual functions (VFs) for the main purpose of eliminating software
+overhead in I/O from virtual machines.
+
+There are devices with predefined SR-IOV configurations, but it is also possible
+to compose an SR-IOV device yourself. Composing an SR-IOV device is currently
+only supported by virtio-net-pci.
+
+Users can configure an SR-IOV-capable virtio-net device by adding
+virtio-net-pci functions to a bus. Below is a command line example:
+
+.. code-block:: shell
+
+    -netdev user,id=n -netdev user,id=o
+    -netdev user,id=p -netdev user,id=q
+    -device pcie-root-port,id=b
+    -device virtio-net-pci,bus=b,addr=0x0.0x3,netdev=q,sriov-pf=f
+    -device virtio-net-pci,bus=b,addr=0x0.0x2,netdev=p,sriov-pf=f
+    -device virtio-net-pci,bus=b,addr=0x0.0x1,netdev=o,sriov-pf=f
+    -device virtio-net-pci,bus=b,addr=0x0.0x0,netdev=n,id=f
+
+The VFs specify the paired PF with ``sriov-pf`` property. The PF must be
+added after all VFs. It is the user's responsibility to ensure that VFs have
+function numbers larger than one of the PF, and that the function numbers
+have a consistent stride.
+
+You may also need to perform additional steps to activate the SR-IOV feature on
+your guest. For Linux, refer to [1]_.
+
+.. [1] https://docs.kernel.org/PCI/pci-iov-howto.html

gdbstub/gdbstub.c

@@ -618,6 +618,19 @@ void gdb_register_coprocessor(CPUState *cpu,
     }
 }
 
+void gdb_unregister_coprocessor_all(CPUState *cpu)
+{
+    /*
+     * Safe to nuke everything. GDBRegisterState::xml is static const char so
+     * it won't be freed
+     */
+    g_array_free(cpu->gdb_regs, true);
+
+    cpu->gdb_regs = NULL;
+    cpu->gdb_num_regs = 0;
+    cpu->gdb_num_g_regs = 0;
+}
+
 static void gdb_process_breakpoint_remove_all(GDBProcess *p)
 {
     CPUState *cpu = gdb_get_first_cpu_in_process(p);

hw/acpi/acpi-cpu-hotplug-stub.c

@@ -19,6 +19,12 @@ void legacy_acpi_cpu_hotplug_init(MemoryRegion *parent, Object *owner,
     return;
 }
 
+void cpu_hotplug_hw_init(MemoryRegion *as, Object *owner,
+                         CPUHotplugState *state, hwaddr base_addr)
+{
+    return;
+}
+
 void acpi_cpu_ospm_status(CPUHotplugState *cpu_st, ACPIOSTInfoList ***list)
 {
     return;

hw/acpi/cpu.c

@@ -7,7 +7,6 @@
 #include "trace.h"
 #include "sysemu/numa.h"
 
-#define ACPI_CPU_HOTPLUG_REG_LEN 12
 #define ACPI_CPU_SELECTOR_OFFSET_WR 0
 #define ACPI_CPU_FLAGS_OFFSET_RW 4
 #define ACPI_CPU_CMD_OFFSET_WR 5
@@ -339,9 +338,10 @@ const VMStateDescription vmstate_cpu_hotplug = {
 #define CPU_FW_EJECT_EVENT "CEJF"
 
 void build_cpus_aml(Aml *table, MachineState *machine, CPUHotplugFeatures opts,
-                    build_madt_cpu_fn build_madt_cpu, hwaddr io_base,
+                    build_madt_cpu_fn build_madt_cpu, hwaddr base_addr,
                     const char *res_root,
-                    const char *event_handler_method)
+                    const char *event_handler_method,
+                    AmlRegionSpace rs)
 {
     Aml *ifctx;
     Aml *field;
@@ -365,14 +365,22 @@ void build_cpus_aml(Aml *table, MachineState *machine, CPUHotplugFeatures opts,
             aml_name_decl("_UID", aml_string("CPU Hotplug resources")));
         aml_append(cpu_ctrl_dev, aml_mutex(CPU_LOCK, 0));
 
+        assert((rs == AML_SYSTEM_IO) || (rs == AML_SYSTEM_MEMORY));
+
         crs = aml_resource_template();
-        aml_append(crs, aml_io(AML_DECODE16, io_base, io_base, 1,
+        if (rs == AML_SYSTEM_IO) {
+            aml_append(crs, aml_io(AML_DECODE16, base_addr, base_addr, 1,
                                ACPI_CPU_HOTPLUG_REG_LEN));
+        } else if (rs == AML_SYSTEM_MEMORY) {
+            aml_append(crs, aml_memory32_fixed(base_addr,
+                               ACPI_CPU_HOTPLUG_REG_LEN, AML_READ_WRITE));
+        }
+
         aml_append(cpu_ctrl_dev, aml_name_decl("_CRS", crs));
 
         /* declare CPU hotplug MMIO region with related access fields */
         aml_append(cpu_ctrl_dev,
-            aml_operation_region("PRST", AML_SYSTEM_IO, aml_int(io_base),
+            aml_operation_region("PRST", rs, aml_int(base_addr),
                                  ACPI_CPU_HOTPLUG_REG_LEN));
 
         field = aml_field("PRST", AML_BYTE_ACC, AML_NOLOCK,

hw/acpi/generic_event_device.c

@@ -25,6 +25,7 @@ static const uint32_t ged_supported_events[] = {
     ACPI_GED_MEM_HOTPLUG_EVT,
     ACPI_GED_PWR_DOWN_EVT,
     ACPI_GED_NVDIMM_HOTPLUG_EVT,
+    ACPI_GED_CPU_HOTPLUG_EVT,
 };
 
 /*
@@ -107,6 +108,9 @@ void build_ged_aml(Aml *table, const char *name, HotplugHandler *hotplug_dev,
                 aml_append(if_ctx, aml_call0(MEMORY_DEVICES_CONTAINER "."
                                              MEMORY_SLOT_SCAN_METHOD));
                 break;
+            case ACPI_GED_CPU_HOTPLUG_EVT:
+                aml_append(if_ctx, aml_call0(AML_GED_EVT_CPU_SCAN_METHOD));
+                break;
             case ACPI_GED_PWR_DOWN_EVT:
                 aml_append(if_ctx,
                            aml_notify(aml_name(ACPI_POWER_BUTTON_DEVICE),
@@ -234,6 +238,8 @@ static void acpi_ged_device_plug_cb(HotplugHandler *hotplug_dev,
         } else {
             acpi_memory_plug_cb(hotplug_dev, &s->memhp_state, dev, errp);
         }
+    } else if (object_dynamic_cast(OBJECT(dev), TYPE_CPU)) {
+        acpi_cpu_plug_cb(hotplug_dev, &s->cpuhp_state, dev, errp);
     } else {
         error_setg(errp, "virt: device plug request for unsupported device"
                    " type: %s", object_get_typename(OBJECT(dev)));
@@ -248,6 +254,8 @@ static void acpi_ged_unplug_request_cb(HotplugHandler *hotplug_dev,
     if ((object_dynamic_cast(OBJECT(dev), TYPE_PC_DIMM) &&
                        !(object_dynamic_cast(OBJECT(dev), TYPE_NVDIMM)))) {
         acpi_memory_unplug_request_cb(hotplug_dev, &s->memhp_state, dev, errp);
+    } else if (object_dynamic_cast(OBJECT(dev), TYPE_CPU)) {
+        acpi_cpu_unplug_request_cb(hotplug_dev, &s->cpuhp_state, dev, errp);
     } else {
         error_setg(errp, "acpi: device unplug request for unsupported device"
                    " type: %s", object_get_typename(OBJECT(dev)));
@@ -261,6 +269,8 @@ static void acpi_ged_unplug_cb(HotplugHandler *hotplug_dev,
 
     if (object_dynamic_cast(OBJECT(dev), TYPE_PC_DIMM)) {
         acpi_memory_unplug_cb(&s->memhp_state, dev, errp);
+    } else if (object_dynamic_cast(OBJECT(dev), TYPE_CPU)) {
+        acpi_cpu_unplug_cb(&s->cpuhp_state, dev, errp);
     } else {
         error_setg(errp, "acpi: device unplug for unsupported device"
                    " type: %s", object_get_typename(OBJECT(dev)));
@@ -272,6 +282,7 @@ static void acpi_ged_ospm_status(AcpiDeviceIf *adev, ACPIOSTInfoList ***list)
     AcpiGedState *s = ACPI_GED(adev);
 
     acpi_memory_ospm_status(&s->memhp_state, list);
+    acpi_cpu_ospm_status(&s->cpuhp_state, list);
 }
 
 static void acpi_ged_send_event(AcpiDeviceIf *adev, AcpiEventStatusBits ev)
@@ -286,6 +297,8 @@ static void acpi_ged_send_event(AcpiDeviceIf *adev, AcpiEventStatusBits ev)
         sel = ACPI_GED_PWR_DOWN_EVT;
     } else if (ev & ACPI_NVDIMM_HOTPLUG_STATUS) {
         sel = ACPI_GED_NVDIMM_HOTPLUG_EVT;
+    } else if (ev & ACPI_CPU_HOTPLUG_STATUS) {
+        sel = ACPI_GED_CPU_HOTPLUG_EVT;
     } else {
         /* Unknown event. Return without generating interrupt. */
         warn_report("GED: Unsupported event %d. No irq injected", ev);
@@ -371,6 +384,42 @@ static const VMStateDescription vmstate_acpi_ged = {
     }
 };
 
+static void acpi_ged_realize(DeviceState *dev, Error **errp)
+{
+    SysBusDevice *sbd = SYS_BUS_DEVICE(dev);
+    AcpiGedState *s = ACPI_GED(dev);
+    uint32_t ged_events;
+    int i;
+
+    ged_events = ctpop32(s->ged_event_bitmap);
+
+    for (i = 0; i < ARRAY_SIZE(ged_supported_events) && ged_events; i++) {
+        uint32_t event = s->ged_event_bitmap & ged_supported_events[i];
+
+        if (!event) {
+            continue;
+        }
+
+        switch (event) {
+        case ACPI_GED_CPU_HOTPLUG_EVT:
+            /* initialize CPU Hotplug related regions */
+            memory_region_init(&s->container_cpuhp, OBJECT(dev),
+                                "cpuhp container",
+                                ACPI_CPU_HOTPLUG_REG_LEN);
+            sysbus_init_mmio(sbd, &s->container_cpuhp);
+            cpu_hotplug_hw_init(&s->container_cpuhp, OBJECT(dev),
+                                &s->cpuhp_state, 0);
+            break;
+        }
+        ged_events--;
+    }
+
+    if (ged_events) {
+        error_report("Unsupported events specified");
+        abort();
+    }
+}
+
 static void acpi_ged_initfn(Object *obj)
 {
     DeviceState *dev = DEVICE(obj);
@@ -411,6 +460,7 @@ static void acpi_ged_class_init(ObjectClass *class, void *data)
     dc->desc = "ACPI Generic Event Device";
     device_class_set_props(dc, acpi_ged_properties);
     dc->vmsd = &vmstate_acpi_ged;
+    dc->realize = acpi_ged_realize;
 
     hc->plug = acpi_ged_device_plug_cb;
     hc->unplug_request = acpi_ged_unplug_request_cb;

hw/arm/virt.c

@@ -3308,6 +3308,7 @@ DEFINE_VIRT_MACHINE_AS_LATEST(9, 1)
 static void virt_machine_9_0_options(MachineClass *mc)
 {
     virt_machine_9_1_options(mc);
+    mc->smbios_memory_device_size = 16 * GiB;
     compat_props_add(mc->compat_props, hw_compat_9_0, hw_compat_9_0_len);
 }
 DEFINE_VIRT_MACHINE(9, 0)

hw/audio/virtio-snd.c

@@ -282,11 +282,13 @@ uint32_t virtio_snd_set_pcm_params(VirtIOSound *s,
         error_report("Number of channels is not supported.");
         return cpu_to_le32(VIRTIO_SND_S_NOT_SUPP);
     }
-    if (!(supported_formats & BIT(params->format))) {
+    if (BIT(params->format) > sizeof(supported_formats) ||
+        !(supported_formats & BIT(params->format))) {
         error_report("Stream format is not supported.");
         return cpu_to_le32(VIRTIO_SND_S_NOT_SUPP);
     }
-    if (!(supported_rates & BIT(params->rate))) {
+    if (BIT(params->rate) > sizeof(supported_rates) ||
+        !(supported_rates & BIT(params->rate))) {
         error_report("Stream rate is not supported.");
         return cpu_to_le32(VIRTIO_SND_S_NOT_SUPP);
     }
@@ -1261,7 +1263,7 @@ static void virtio_snd_pcm_in_cb(void *data, int available)
 {
     VirtIOSoundPCMStream *stream = data;
     VirtIOSoundPCMBuffer *buffer;
-    size_t size;
+    size_t size, max_size;
 
     WITH_QEMU_LOCK_GUARD(&stream->queue_mutex) {
         while (!QSIMPLEQ_EMPTY(&stream->queue)) {
@@ -1275,7 +1277,12 @@ static void virtio_snd_pcm_in_cb(void *data, int available)
                 continue;
             }
 
+            max_size = iov_size(buffer->elem->in_sg, buffer->elem->in_num);
             for (;;) {
+                if (buffer->size >= max_size) {
+                    return_rx_buffer(stream, buffer);
+                    break;
+                }
                 size = AUD_read(stream->voice.in,
                         buffer->data + buffer->size,
                         MIN(available, (stream->params.period_bytes -

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_IN_ORDER,
     VIRTIO_F_NOTIFICATION_DATA,
     VHOST_INVALID_FEATURE_BIT
 };

hw/core/cpu-common.c

@@ -282,7 +282,10 @@ static void cpu_common_finalize(Object *obj)
     }
 #endif
     free_queued_cpu_work(cpu);
-    g_array_free(cpu->gdb_regs, TRUE);
+    /* If cleanup didn't happen in context to gdb_unregister_coprocessor_all */
+    if (cpu->gdb_regs) {
+        g_array_free(cpu->gdb_regs, TRUE);
+    }
     qemu_lockcnt_destroy(&cpu->in_ioctl_lock);
     qemu_mutex_destroy(&cpu->work_mutex);
     qemu_cond_destroy(cpu->halt_cond);

hw/core/machine.c

@@ -1005,6 +1005,12 @@ static void machine_class_init(ObjectClass *oc, void *data)
     /* Default 128 MB as guest ram size */
     mc->default_ram_size = 128 * MiB;
     mc->rom_file_has_mr = true;
+    /*
+     * SMBIOS 3.1.0 7.18.5 Memory Device — Extended Size
+     * use max possible value that could be encoded into
+     * 'Extended Size' field (2047Tb).
+     */
+    mc->smbios_memory_device_size = 2047 * TiB;
 
     /* numa node memory size aligned on 8MB by default.
      * On Linux, each node's border has to be 8MB aligned

hw/cxl/cxl-events.c

@@ -139,6 +139,19 @@ bool cxl_event_insert(CXLDeviceState *cxlds, CXLEventLogType log_type,
     return cxl_event_count(log) == 1;
 }
 
+void cxl_discard_all_event_records(CXLDeviceState *cxlds)
+{
+    CXLEventLogType log_type;
+    CXLEventLog *log;
+
+    for (log_type = 0; log_type < CXL_EVENT_TYPE_MAX; log_type++) {
+        log = &cxlds->event_logs[log_type];
+        while (!cxl_event_empty(log)) {
+            cxl_event_delete_head(cxlds, log_type, log);
+        }
+    }
+}
+
 CXLRetCode cxl_event_get_records(CXLDeviceState *cxlds, CXLGetEventPayload *pl,
                                  uint8_t log_type, int max_recs,
                                  size_t *len)

hw/cxl/cxl-host.c

@@ -315,7 +315,8 @@ static void machine_set_cxl(Object *obj, Visitor *v, const char *name,
 static void machine_get_cfmw(Object *obj, Visitor *v, const char *name,
                              void *opaque, Error **errp)
 {
-    CXLFixedMemoryWindowOptionsList **list = opaque;
+    CXLState *state = opaque;
+    CXLFixedMemoryWindowOptionsList **list = &state->cfmw_list;
 
     visit_type_CXLFixedMemoryWindowOptionsList(v, name, list, errp);
 }

hw/i386/acpi-build.c

@@ -1536,7 +1536,8 @@ build_dsdt(GArray *table_data, BIOSLinker *linker,
             .fw_unplugs_cpu = pm->smi_on_cpu_unplug,
         };
         build_cpus_aml(dsdt, machine, opts, pc_madt_cpu_entry,
-                       pm->cpu_hp_io_base, "\\_SB.PCI0", "\\_GPE._E02");
+                       pm->cpu_hp_io_base, "\\_SB.PCI0", "\\_GPE._E02",
+                       AML_SYSTEM_IO);
     }
 
     if (pcms->memhp_io_base && nr_mem) {

hw/i386/intel_iommu.c

@@ -358,7 +358,7 @@ static VTDIOTLBEntry *vtd_lookup_iotlb(IntelIOMMUState *s, uint16_t source_id,
 {
     struct vtd_iotlb_key key;
     VTDIOTLBEntry *entry;
-    int level;
+    unsigned level;
 
     for (level = VTD_SL_PT_LEVEL; level < VTD_SL_PML4_LEVEL; level++) {
         key.gfn = vtd_get_iotlb_gfn(addr, level);

hw/i386/intel_iommu_internal.h

@@ -264,10 +264,10 @@
 #define VTD_FRCD_FR(val)        (((val) & 0xffULL) << 32)
 #define VTD_FRCD_SID_MASK       0xffffULL
 #define VTD_FRCD_SID(val)       ((val) & VTD_FRCD_SID_MASK)
+#define VTD_FRCD_PV(val)        (((val) & 0xffffULL) << 40)
+#define VTD_FRCD_PP(val)        (((val) & 0x1ULL) << 31)
 /* For the low 64-bit of 128-bit */
 #define VTD_FRCD_FI(val)        ((val) & ~0xfffULL)
-#define VTD_FRCD_PV(val)        (((val) & 0xffffULL) << 40)
-#define VTD_FRCD_PP(val)        (((val) & 0x1) << 31)
 #define VTD_FRCD_IR_IDX(val)    (((val) & 0xffffULL) << 48)
 
 /* DMA Remapping Fault Conditions */
@@ -436,7 +436,7 @@ struct VTDIOTLBPageInvInfo {
     uint16_t domain_id;
     uint32_t pasid;
     uint64_t addr;
-    uint8_t mask;
+    uint64_t mask;
 };
 typedef struct VTDIOTLBPageInvInfo VTDIOTLBPageInvInfo;
 

hw/i386/pc_piix.c

@@ -495,6 +495,7 @@ static void pc_i440fx_machine_9_0_options(MachineClass *m)
     pc_i440fx_machine_9_1_options(m);
     m->alias = NULL;
     m->is_default = false;
+    m->smbios_memory_device_size = 16 * GiB;
 
     compat_props_add(m->compat_props, hw_compat_9_0, hw_compat_9_0_len);
     compat_props_add(m->compat_props, pc_compat_9_0, pc_compat_9_0_len);

hw/i386/pc_q35.c

@@ -374,6 +374,7 @@ static void pc_q35_machine_9_0_options(MachineClass *m)
     PCMachineClass *pcmc = PC_MACHINE_CLASS(m);
     pc_q35_machine_9_1_options(m);
     m->alias = NULL;
+    m->smbios_memory_device_size = 16 * GiB;
     compat_props_add(m->compat_props, hw_compat_9_0, hw_compat_9_0_len);
     compat_props_add(m->compat_props, pc_compat_9_0, pc_compat_9_0_len);
     pcmc->isa_bios_alias = false;

hw/mem/cxl_type3.c

@@ -737,6 +737,11 @@ static bool cxl_setup_memory(CXLType3Dev *ct3d, Error **errp)
             error_setg(errp, "volatile memdev must have backing device");
             return false;
         }
+        if (host_memory_backend_is_mapped(ct3d->hostvmem)) {
+            error_setg(errp, "memory backend %s can't be used multiple times.",
+               object_get_canonical_path_component(OBJECT(ct3d->hostvmem)));
+            return false;
+        }
         memory_region_set_nonvolatile(vmr, false);
         memory_region_set_enabled(vmr, true);
         host_memory_backend_set_mapped(ct3d->hostvmem, true);
@@ -760,6 +765,11 @@ static bool cxl_setup_memory(CXLType3Dev *ct3d, Error **errp)
             error_setg(errp, "persistent memdev must have backing device");
             return false;
         }
+        if (host_memory_backend_is_mapped(ct3d->hostpmem)) {
+            error_setg(errp, "memory backend %s can't be used multiple times.",
+               object_get_canonical_path_component(OBJECT(ct3d->hostpmem)));
+            return false;
+        }
         memory_region_set_nonvolatile(pmr, true);
         memory_region_set_enabled(pmr, true);
         host_memory_backend_set_mapped(ct3d->hostpmem, true);
@@ -790,6 +800,11 @@ static bool cxl_setup_memory(CXLType3Dev *ct3d, Error **errp)
             return false;
         }
 
+        if (host_memory_backend_is_mapped(ct3d->dc.host_dc)) {
+            error_setg(errp, "memory backend %s can't be used multiple times.",
+               object_get_canonical_path_component(OBJECT(ct3d->dc.host_dc)));
+            return false;
+        }
         /*
          * Set DC regions as volatile for now, non-volatile support can
          * be added in the future if needed.
@@ -829,6 +844,7 @@ static void ct3_realize(PCIDevice *pci_dev, Error **errp)
     uint8_t *pci_conf = pci_dev->config;
     unsigned short msix_num = 6;
     int i, rc;
+    uint16_t count;
 
     QTAILQ_INIT(&ct3d->error_list);
 
@@ -893,6 +909,28 @@ static void ct3_realize(PCIDevice *pci_dev, Error **errp)
     }
     cxl_event_init(&ct3d->cxl_dstate, 2);
 
+    /* Set default value for patrol scrub attributes */
+    ct3d->patrol_scrub_attrs.scrub_cycle_cap =
+                           CXL_MEMDEV_PS_SCRUB_CYCLE_CHANGE_CAP_DEFAULT |
+                           CXL_MEMDEV_PS_SCRUB_REALTIME_REPORT_CAP_DEFAULT;
+    ct3d->patrol_scrub_attrs.scrub_cycle =
+                           CXL_MEMDEV_PS_CUR_SCRUB_CYCLE_DEFAULT |
+                           (CXL_MEMDEV_PS_MIN_SCRUB_CYCLE_DEFAULT << 8);
+    ct3d->patrol_scrub_attrs.scrub_flags = CXL_MEMDEV_PS_ENABLE_DEFAULT;
+
+    /* Set default value for DDR5 ECS read attributes */
+    for (count = 0; count < CXL_ECS_NUM_MEDIA_FRUS; count++) {
+        ct3d->ecs_attrs[count].ecs_log_cap =
+                            CXL_ECS_LOG_ENTRY_TYPE_DEFAULT;
+        ct3d->ecs_attrs[count].ecs_cap =
+                            CXL_ECS_REALTIME_REPORT_CAP_DEFAULT;
+        ct3d->ecs_attrs[count].ecs_config =
+                            CXL_ECS_THRESHOLD_COUNT_DEFAULT |
+                            (CXL_ECS_MODE_DEFAULT << 3);
+        /* Reserved */
+        ct3d->ecs_attrs[count].ecs_flags = 0;
+    }
+
     return;
 
 err_release_cdat:
@@ -1127,7 +1165,7 @@ MemTxResult cxl_type3_read(PCIDevice *d, hwaddr host_addr, uint64_t *data,
         return MEMTX_ERROR;
     }
 
-    if (sanitize_running(&ct3d->cci)) {
+    if (cxl_dev_media_disabled(&ct3d->cxl_dstate)) {
         qemu_guest_getrandom_nofail(data, size);
         return MEMTX_OK;
     }
@@ -1149,7 +1187,7 @@ MemTxResult cxl_type3_write(PCIDevice *d, hwaddr host_addr, uint64_t data,
         return MEMTX_ERROR;
     }
 
-    if (sanitize_running(&ct3d->cci)) {
+    if (cxl_dev_media_disabled(&ct3d->cxl_dstate)) {
         return MEMTX_OK;
     }
 
@@ -1304,6 +1342,12 @@ void cxl_set_poison_list_overflowed(CXLType3Dev *ct3d)
             cxl_device_get_timestamp(&ct3d->cxl_dstate);
 }
 
+void cxl_clear_poison_list_overflowed(CXLType3Dev *ct3d)
+{
+    ct3d->poison_list_overflowed = false;
+    ct3d->poison_list_overflow_ts = 0;
+}
+
 void qmp_cxl_inject_poison(const char *path, uint64_t start, uint64_t length,
                            Error **errp)
 {
@@ -1340,19 +1384,21 @@ void qmp_cxl_inject_poison(const char *path, uint64_t start, uint64_t length,
         }
     }
 
-    if (ct3d->poison_list_cnt == CXL_POISON_LIST_LIMIT) {
-        cxl_set_poison_list_overflowed(ct3d);
-        return;
-    }
-
     p = g_new0(CXLPoison, 1);
     p->length = length;
     p->start = start;
     /* Different from injected via the mbox */
     p->type = CXL_POISON_TYPE_INTERNAL;
 
-    QLIST_INSERT_HEAD(&ct3d->poison_list, p, node);
-    ct3d->poison_list_cnt++;
+    if (ct3d->poison_list_cnt < CXL_POISON_LIST_LIMIT) {
+        QLIST_INSERT_HEAD(&ct3d->poison_list, p, node);
+        ct3d->poison_list_cnt++;
+    } else {
+        if (!ct3d->poison_list_overflowed) {
+            cxl_set_poison_list_overflowed(ct3d);
+        }
+        QLIST_INSERT_HEAD(&ct3d->poison_list_bkp, p, node);
+    }
 }
 
 /* For uncorrectable errors include support for multiple header recording */

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_IN_ORDER,
     VIRTIO_F_NOTIFICATION_DATA,
     VIRTIO_NET_F_HASH_REPORT,
     VHOST_INVALID_FEATURE_BIT
@@ -78,6 +79,7 @@ static const int user_feature_bits[] = {
     VIRTIO_F_IOMMU_PLATFORM,
     VIRTIO_F_RING_PACKED,
     VIRTIO_F_RING_RESET,
+    VIRTIO_F_IN_ORDER,
     VIRTIO_NET_F_RSS,
     VIRTIO_NET_F_HASH_REPORT,
     VIRTIO_NET_F_GUEST_USO4,

hw/nvme/ctrl.c

@@ -203,6 +203,7 @@
 #include "sysemu/hostmem.h"
 #include "hw/pci/msix.h"
 #include "hw/pci/pcie_sriov.h"
+#include "sysemu/spdm-socket.h"
 #include "migration/vmstate.h"
 
 #include "nvme.h"
@@ -8315,6 +8316,27 @@ static int nvme_add_pm_capability(PCIDevice *pci_dev, uint8_t offset)
     return 0;
 }
 
+static bool pcie_doe_spdm_rsp(DOECap *doe_cap)
+{
+    void *req = pcie_doe_get_write_mbox_ptr(doe_cap);
+    uint32_t req_len = pcie_doe_get_obj_len(req) * 4;
+    void *rsp = doe_cap->read_mbox;
+    uint32_t rsp_len = SPDM_SOCKET_MAX_MESSAGE_BUFFER_SIZE;
+
+    uint32_t recvd = spdm_socket_rsp(doe_cap->spdm_socket,
+                             SPDM_SOCKET_TRANSPORT_TYPE_PCI_DOE,
+                             req, req_len, rsp, rsp_len);
+    doe_cap->read_mbox_len += DIV_ROUND_UP(recvd, 4);
+
+    return recvd != 0;
+}
+
+static DOEProtocol doe_spdm_prot[] = {
+    { PCI_VENDOR_ID_PCI_SIG, PCI_SIG_DOE_CMA, pcie_doe_spdm_rsp },
+    { PCI_VENDOR_ID_PCI_SIG, PCI_SIG_DOE_SECURED_CMA, pcie_doe_spdm_rsp },
+    { }
+};
+
 static bool nvme_init_pci(NvmeCtrl *n, PCIDevice *pci_dev, Error **errp)
 {
     ERRP_GUARD();
@@ -8402,6 +8424,25 @@ static bool nvme_init_pci(NvmeCtrl *n, PCIDevice *pci_dev, Error **errp)
 
     nvme_update_msixcap_ts(pci_dev, n->conf_msix_qsize);
 
+    pcie_cap_deverr_init(pci_dev);
+
+    /* DOE Initialisation */
+    if (pci_dev->spdm_port) {
+        uint16_t doe_offset = n->params.sriov_max_vfs ?
+                                  PCI_CONFIG_SPACE_SIZE + PCI_ARI_SIZEOF
+                                  : PCI_CONFIG_SPACE_SIZE;
+
+        pcie_doe_init(pci_dev, &pci_dev->doe_spdm, doe_offset,
+                      doe_spdm_prot, true, 0);
+
+        pci_dev->doe_spdm.spdm_socket = spdm_socket_connect(pci_dev->spdm_port,
+                                                            errp);
+
+        if (pci_dev->doe_spdm.spdm_socket < 0) {
+            return false;
+        }
+    }
+
     if (n->params.cmb_size_mb) {
         nvme_init_cmb(n, pci_dev);
     }
@@ -8650,6 +8691,11 @@ static void nvme_exit(PCIDevice *pci_dev)
         g_free(n->cmb.buf);
     }
 
+    if (pci_dev->doe_spdm.spdm_socket > 0) {
+        spdm_socket_close(pci_dev->doe_spdm.spdm_socket,
+                          SPDM_SOCKET_TRANSPORT_TYPE_PCI_DOE);
+    }
+
     if (n->pmr.dev) {
         host_memory_backend_set_mapped(n->pmr.dev, false);
     }
@@ -8695,6 +8741,7 @@ static Property nvme_props[] = {
     DEFINE_PROP_BOOL("msix-exclusive-bar", NvmeCtrl, params.msix_exclusive_bar,
                      false),
     DEFINE_PROP_UINT16("mqes", NvmeCtrl, params.mqes, 0x7ff),
+    DEFINE_PROP_UINT16("spdm_port", PCIDevice, spdm_port, 0),
     DEFINE_PROP_END_OF_LIST(),
 };
 
@@ -8766,11 +8813,25 @@ static void nvme_pci_write_config(PCIDevice *dev, uint32_t address,
 {
     uint16_t old_num_vfs = pcie_sriov_num_vfs(dev);
 
+    if (pcie_find_capability(dev, PCI_EXT_CAP_ID_DOE)) {
+        pcie_doe_write_config(&dev->doe_spdm, address, val, len);
+    }
     pci_default_write_config(dev, address, val, len);
     pcie_cap_flr_write_config(dev, address, val, len);
     nvme_sriov_post_write_config(dev, old_num_vfs);
 }
 
+static uint32_t nvme_pci_read_config(PCIDevice *dev, uint32_t address, int len)
+{
+    uint32_t val;
+    if (dev->spdm_port && pcie_find_capability(dev, PCI_EXT_CAP_ID_DOE)) {
+        if (pcie_doe_read_config(&dev->doe_spdm, address, len, &val)) {
+            return val;
+        }
+    }
+    return pci_default_read_config(dev, address, len);
+}
+
 static const VMStateDescription nvme_vmstate = {
     .name = "nvme",
     .unmigratable = 1,
@@ -8783,6 +8844,7 @@ static void nvme_class_init(ObjectClass *oc, void *data)
 
     pc->realize = nvme_realize;
     pc->config_write = nvme_pci_write_config;
+    pc->config_read = nvme_pci_read_config;
     pc->exit = nvme_exit;
     pc->class_id = PCI_CLASS_STORAGE_EXPRESS;
     pc->revision = 2;

hw/pci-host/gpex-acpi.c

@@ -7,7 +7,8 @@
 #include "hw/pci/pcie_host.h"
 #include "hw/acpi/cxl.h"
 
-static void acpi_dsdt_add_pci_route_table(Aml *dev, uint32_t irq)
+static void acpi_dsdt_add_pci_route_table(Aml *dev, uint32_t irq,
+                                          Aml *scope, uint8_t bus_num)
 {
     Aml *method, *crs;
     int i, slot_no;
@@ -20,7 +21,7 @@ static void acpi_dsdt_add_pci_route_table(Aml *dev, uint32_t irq)
             Aml *pkg = aml_package(4);
             aml_append(pkg, aml_int((slot_no << 16) | 0xFFFF));
             aml_append(pkg, aml_int(i));
-            aml_append(pkg, aml_name("GSI%d", gsi));
+            aml_append(pkg, aml_name("L%.02X%X", bus_num, gsi));
             aml_append(pkg, aml_int(0));
             aml_append(rt_pkg, pkg);
         }
@@ -30,7 +31,7 @@ static void acpi_dsdt_add_pci_route_table(Aml *dev, uint32_t irq)
     /* Create GSI link device */
     for (i = 0; i < PCI_NUM_PINS; i++) {
         uint32_t irqs = irq + i;
-        Aml *dev_gsi = aml_device("GSI%d", i);
+        Aml *dev_gsi = aml_device("L%.02X%X", bus_num, i);
         aml_append(dev_gsi, aml_name_decl("_HID", aml_string("PNP0C0F")));
         aml_append(dev_gsi, aml_name_decl("_UID", aml_int(i)));
         crs = aml_resource_template();
@@ -45,7 +46,7 @@ static void acpi_dsdt_add_pci_route_table(Aml *dev, uint32_t irq)
         aml_append(dev_gsi, aml_name_decl("_CRS", crs));
         method = aml_method("_SRS", 1, AML_NOTSERIALIZED);
         aml_append(dev_gsi, method);
-        aml_append(dev, dev_gsi);
+        aml_append(scope, dev_gsi);
     }
 }
 
@@ -174,7 +175,7 @@ void acpi_dsdt_add_gpex(Aml *scope, struct GPEXConfig *cfg)
                 aml_append(dev, aml_name_decl("_PXM", aml_int(numa_node)));
             }
 
-            acpi_dsdt_add_pci_route_table(dev, cfg->irq);
+            acpi_dsdt_add_pci_route_table(dev, cfg->irq, scope, bus_num);
 
             /*
              * Resources defined for PXBs are composed of the following parts:
@@ -205,7 +206,7 @@ void acpi_dsdt_add_gpex(Aml *scope, struct GPEXConfig *cfg)
     aml_append(dev, aml_name_decl("_STR", aml_unicode("PCIe 0 Device")));
     aml_append(dev, aml_name_decl("_CCA", aml_int(1)));
 
-    acpi_dsdt_add_pci_route_table(dev, cfg->irq);
+    acpi_dsdt_add_pci_route_table(dev, cfg->irq, scope, 0);
 
     method = aml_method("_CBA", 0, AML_NOTSERIALIZED);
     aml_append(method, aml_return(aml_int(cfg->ecam.base)));

hw/pci/pci.c

@@ -85,6 +85,7 @@ static Property pci_props[] = {
                     QEMU_PCIE_ERR_UNC_MASK_BITNR, true),
     DEFINE_PROP_BIT("x-pcie-ari-nextfn-1", PCIDevice, cap_present,
                     QEMU_PCIE_ARI_NEXTFN_1_BITNR, false),
+    DEFINE_PROP_STRING("sriov-pf", PCIDevice, sriov_pf),
     DEFINE_PROP_END_OF_LIST()
 };
 
@@ -959,13 +960,8 @@ static void pci_init_multifunction(PCIBus *bus, PCIDevice *dev, Error **errp)
         dev->config[PCI_HEADER_TYPE] |= PCI_HEADER_TYPE_MULTI_FUNCTION;
     }
 
-    /*
-     * With SR/IOV and ARI, a device at function 0 need not be a multifunction
-     * device, as it may just be a VF that ended up with function 0 in
-     * the legacy PCI interpretation. Avoid failing in such cases:
-     */
-    if (pci_is_vf(dev) &&
-        dev->exp.sriov_vf.pf->cap_present & QEMU_PCI_CAP_MULTIFUNCTION) {
+    /* SR/IOV is not handled here. */
+    if (pci_is_vf(dev)) {
         return;
     }
 
@@ -998,7 +994,8 @@ static void pci_init_multifunction(PCIBus *bus, PCIDevice *dev, Error **errp)
     }
     /* function 0 indicates single function, so function > 0 must be NULL */
     for (func = 1; func < PCI_FUNC_MAX; ++func) {
-        if (bus->devices[PCI_DEVFN(slot, func)]) {
+        PCIDevice *device = bus->devices[PCI_DEVFN(slot, func)];
+        if (device && !pci_is_vf(device)) {
             error_setg(errp, "PCI: %x.0 indicates single function, "
                        "but %x.%x is already populated.",
                        slot, slot, func);
@@ -1283,6 +1280,7 @@ static void pci_qdev_unrealize(DeviceState *dev)
 
     pci_unregister_io_regions(pci_dev);
     pci_del_option_rom(pci_dev);
+    pcie_sriov_unregister_device(pci_dev);
 
     if (pc->exit) {
         pc->exit(pci_dev);
@@ -1314,7 +1312,6 @@ void pci_register_bar(PCIDevice *pci_dev, int region_num,
     pcibus_t size = memory_region_size(memory);
     uint8_t hdr_type;
 
-    assert(!pci_is_vf(pci_dev)); /* VFs must use pcie_sriov_vf_register_bar */
     assert(region_num >= 0);
     assert(region_num < PCI_NUM_REGIONS);
     assert(is_power_of_2(size));
@@ -1325,7 +1322,6 @@ void pci_register_bar(PCIDevice *pci_dev, int region_num,
     assert(hdr_type != PCI_HEADER_TYPE_BRIDGE || region_num < 2);
 
     r = &pci_dev->io_regions[region_num];
-    r->addr = PCI_BAR_UNMAPPED;
     r->size = size;
     r->type = type;
     r->memory = memory;
@@ -1333,22 +1329,35 @@ void pci_register_bar(PCIDevice *pci_dev, int region_num,
                         ? pci_get_bus(pci_dev)->address_space_io
                         : pci_get_bus(pci_dev)->address_space_mem;
 
-    wmask = ~(size - 1);
-    if (region_num == PCI_ROM_SLOT) {
-        /* ROM enable bit is writable */
-        wmask |= PCI_ROM_ADDRESS_ENABLE;
-    }
+    if (pci_is_vf(pci_dev)) {
+        PCIDevice *pf = pci_dev->exp.sriov_vf.pf;
+        assert(!pf || type == pf->exp.sriov_pf.vf_bar_type[region_num]);
 
-    addr = pci_bar(pci_dev, region_num);
-    pci_set_long(pci_dev->config + addr, type);
-
-    if (!(r->type & PCI_BASE_ADDRESS_SPACE_IO) &&
-        r->type & PCI_BASE_ADDRESS_MEM_TYPE_64) {
-        pci_set_quad(pci_dev->wmask + addr, wmask);
-        pci_set_quad(pci_dev->cmask + addr, ~0ULL);
+        r->addr = pci_bar_address(pci_dev, region_num, r->type, r->size);
+        if (r->addr != PCI_BAR_UNMAPPED) {
+            memory_region_add_subregion_overlap(r->address_space,
+                                                r->addr, r->memory, 1);
+        }
     } else {
-        pci_set_long(pci_dev->wmask + addr, wmask & 0xffffffff);
-        pci_set_long(pci_dev->cmask + addr, 0xffffffff);
+        r->addr = PCI_BAR_UNMAPPED;
+
+        wmask = ~(size - 1);
+        if (region_num == PCI_ROM_SLOT) {
+            /* ROM enable bit is writable */
+            wmask |= PCI_ROM_ADDRESS_ENABLE;
+        }
+
+        addr = pci_bar(pci_dev, region_num);
+        pci_set_long(pci_dev->config + addr, type);
+
+        if (!(r->type & PCI_BASE_ADDRESS_SPACE_IO) &&
+            r->type & PCI_BASE_ADDRESS_MEM_TYPE_64) {
+            pci_set_quad(pci_dev->wmask + addr, wmask);
+            pci_set_quad(pci_dev->cmask + addr, ~0ULL);
+        } else {
+            pci_set_long(pci_dev->wmask + addr, wmask & 0xffffffff);
+            pci_set_long(pci_dev->cmask + addr, 0xffffffff);
+        }
     }
 }
 
@@ -1437,7 +1446,11 @@ static pcibus_t pci_config_get_bar_addr(PCIDevice *d, int reg,
             pci_get_word(pf->config + sriov_cap + PCI_SRIOV_VF_OFFSET);
         uint16_t vf_stride =
             pci_get_word(pf->config + sriov_cap + PCI_SRIOV_VF_STRIDE);
-        uint32_t vf_num = (d->devfn - (pf->devfn + vf_offset)) / vf_stride;
+        uint32_t vf_num = d->devfn - (pf->devfn + vf_offset);
+
+        if (vf_num) {
+            vf_num /= vf_stride;
+        }
 
         if (type & PCI_BASE_ADDRESS_MEM_TYPE_64) {
             new_addr = pci_get_quad(pf->config + bar);
@@ -2105,6 +2118,11 @@ static void pci_qdev_realize(DeviceState *qdev, Error **errp)
         }
     }
 
+    if (!pcie_sriov_register_device(pci_dev, errp)) {
+        pci_qdev_unrealize(DEVICE(pci_dev));
+        return;
+    }
+
     /*
      * A PCIe Downstream Port that do not have ARI Forwarding enabled must
      * associate only Device 0 with the device attached to the bus

hw/pci/pcie_sriov.c

@@ -20,6 +20,8 @@
 #include "qapi/error.h"
 #include "trace.h"
 
+static GHashTable *pfs;
+
 static void unparent_vfs(PCIDevice *dev, uint16_t total_vfs)
 {
     for (uint16_t i = 0; i < total_vfs; i++) {
@@ -31,17 +33,62 @@ static void unparent_vfs(PCIDevice *dev, uint16_t total_vfs)
     dev->exp.sriov_pf.vf = NULL;
 }
 
-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,
-                        Error **errp)
+static void clear_ctrl_vfe(PCIDevice *dev)
+{
+    uint8_t *ctrl = dev->config + dev->exp.sriov_cap + PCI_SRIOV_CTRL;
+    pci_set_word(ctrl, pci_get_word(ctrl) & ~PCI_SRIOV_CTRL_VFE);
+}
+
+static void register_vfs(PCIDevice *dev)
+{
+    uint16_t num_vfs;
+    uint16_t i;
+    uint16_t sriov_cap = dev->exp.sriov_cap;
+
+    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;
+    }
+
+    trace_sriov_register_vfs(dev->name, PCI_SLOT(dev->devfn),
+                             PCI_FUNC(dev->devfn), num_vfs);
+    for (i = 0; i < num_vfs; i++) {
+        pci_set_enabled(dev->exp.sriov_pf.vf[i], true);
+    }
+}
+
+static void unregister_vfs(PCIDevice *dev)
+{
+    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));
+    for (i = 0; i < pci_get_word(cfg + PCI_SRIOV_TOTAL_VF); i++) {
+        pci_set_enabled(dev->exp.sriov_pf.vf[i], false);
+    }
+}
+
+static bool pcie_sriov_pf_init_common(PCIDevice *dev, uint16_t offset,
+                                      uint16_t vf_dev_id, uint16_t init_vfs,
+                                      uint16_t total_vfs, 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 (!pci_is_express(dev)) {
+        error_setg(errp, "PCI Express is required for SR-IOV PF");
+        return false;
+    }
+
+    if (pci_is_vf(dev)) {
+        error_setg(errp, "a device cannot be both an SR-IOV PF and a VF");
+        return false;
+    }
+
     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;
@@ -90,6 +137,28 @@ bool pcie_sriov_pf_init(PCIDevice *dev, uint16_t offset,
 
     qdev_prop_set_bit(&dev->qdev, "multifunction", true);
 
+    return true;
+}
+
+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,
+                        Error **errp)
+{
+    BusState *bus = qdev_get_parent_bus(&dev->qdev);
+    int32_t devfn = dev->devfn + vf_offset;
+
+    if (pfs && g_hash_table_contains(pfs, dev->qdev.id)) {
+        error_setg(errp, "attaching user-created SR-IOV VF unsupported");
+        return false;
+    }
+
+    if (!pcie_sriov_pf_init_common(dev, offset, vf_dev_id, init_vfs,
+                                   total_vfs, vf_offset, vf_stride, errp)) {
+        return false;
+    }
+
     dev->exp.sriov_pf.vf = g_new(PCIDevice *, total_vfs);
 
     for (uint16_t i = 0; i < total_vfs; i++) {
@@ -119,7 +188,24 @@ void pcie_sriov_pf_exit(PCIDevice *dev)
 {
     uint8_t *cfg = dev->config + dev->exp.sriov_cap;
 
-    unparent_vfs(dev, pci_get_word(cfg + PCI_SRIOV_TOTAL_VF));
+    if (dev->exp.sriov_pf.vf_user_created) {
+        uint16_t ven_id = pci_get_word(dev->config + PCI_VENDOR_ID);
+        uint16_t total_vfs = pci_get_word(dev->config + PCI_SRIOV_TOTAL_VF);
+        uint16_t vf_dev_id = pci_get_word(dev->config + PCI_SRIOV_VF_DID);
+
+        unregister_vfs(dev);
+
+        for (uint16_t i = 0; i < total_vfs; i++) {
+            PCIDevice *vf = dev->exp.sriov_pf.vf[i];
+
+            vf->exp.sriov_vf.pf = NULL;
+
+            pci_config_set_vendor_id(vf->config, ven_id);
+            pci_config_set_device_id(vf->config, vf_dev_id);
+        }
+    } else {
+        unparent_vfs(dev, pci_get_word(cfg + PCI_SRIOV_TOTAL_VF));
+    }
 }
 
 void pcie_sriov_pf_init_vf_bar(PCIDevice *dev, int region_num,
@@ -152,74 +238,172 @@ void pcie_sriov_pf_init_vf_bar(PCIDevice *dev, int region_num,
 void pcie_sriov_vf_register_bar(PCIDevice *dev, int region_num,
                                 MemoryRegion *memory)
 {
-    PCIIORegion *r;
-    PCIBus *bus = pci_get_bus(dev);
     uint8_t type;
-    pcibus_t size = memory_region_size(memory);
 
-    assert(pci_is_vf(dev)); /* PFs must use pci_register_bar */
-    assert(region_num >= 0);
-    assert(region_num < PCI_NUM_REGIONS);
+    assert(dev->exp.sriov_vf.pf);
     type = dev->exp.sriov_vf.pf->exp.sriov_pf.vf_bar_type[region_num];
 
-    if (!is_power_of_2(size)) {
-        error_report("%s: PCI region size must be a power"
-                     " of two - type=0x%x, size=0x%"FMT_PCIBUS,
-                     __func__, type, size);
-        exit(1);
-    }
-
-    r = &dev->io_regions[region_num];
-    r->memory = memory;
-    r->address_space =
-        type & PCI_BASE_ADDRESS_SPACE_IO
-        ? bus->address_space_io
-        : bus->address_space_mem;
-    r->size = size;
-    r->type = type;
-
-    r->addr = pci_bar_address(dev, region_num, r->type, r->size);
-    if (r->addr != PCI_BAR_UNMAPPED) {
-        memory_region_add_subregion_overlap(r->address_space,
-                                            r->addr, r->memory, 1);
-    }
+    return pci_register_bar(dev, region_num, type, memory);
 }
 
-static void clear_ctrl_vfe(PCIDevice *dev)
+static gint compare_vf_devfns(gconstpointer a, gconstpointer b)
 {
-    uint8_t *ctrl = dev->config + dev->exp.sriov_cap + PCI_SRIOV_CTRL;
-    pci_set_word(ctrl, pci_get_word(ctrl) & ~PCI_SRIOV_CTRL_VFE);
+    return (*(PCIDevice **)a)->devfn - (*(PCIDevice **)b)->devfn;
 }
 
-static void register_vfs(PCIDevice *dev)
+int16_t pcie_sriov_pf_init_from_user_created_vfs(PCIDevice *dev,
+                                                 uint16_t offset,
+                                                 Error **errp)
 {
-    uint16_t num_vfs;
+    GPtrArray *pf;
+    PCIDevice **vfs;
+    BusState *bus = qdev_get_parent_bus(DEVICE(dev));
+    uint16_t ven_id = pci_get_word(dev->config + PCI_VENDOR_ID);
+    uint16_t vf_dev_id;
+    uint16_t vf_offset;
+    uint16_t vf_stride;
     uint16_t i;
-    uint16_t sriov_cap = dev->exp.sriov_cap;
 
-    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;
+    if (!pfs || !dev->qdev.id) {
+        return 0;
     }
 
-    trace_sriov_register_vfs(dev->name, PCI_SLOT(dev->devfn),
-                             PCI_FUNC(dev->devfn), num_vfs);
-    for (i = 0; i < num_vfs; i++) {
-        pci_set_enabled(dev->exp.sriov_pf.vf[i], true);
+    pf = g_hash_table_lookup(pfs, dev->qdev.id);
+    if (!pf) {
+        return 0;
     }
+
+    if (pf->len > UINT16_MAX) {
+        error_setg(errp, "too many VFs");
+        return -1;
+    }
+
+    g_ptr_array_sort(pf, compare_vf_devfns);
+    vfs = (void *)pf->pdata;
+
+    if (vfs[0]->devfn <= dev->devfn) {
+        error_setg(errp, "a VF function number is less than the PF function number");
+        return -1;
+    }
+
+    vf_dev_id = pci_get_word(vfs[0]->config + PCI_DEVICE_ID);
+    vf_offset = vfs[0]->devfn - dev->devfn;
+    vf_stride = pf->len < 2 ? 0 : vfs[1]->devfn - vfs[0]->devfn;
+
+    for (i = 0; i < pf->len; i++) {
+        if (bus != qdev_get_parent_bus(&vfs[i]->qdev)) {
+            error_setg(errp, "SR-IOV VF parent bus mismatches with PF");
+            return -1;
+        }
+
+        if (ven_id != pci_get_word(vfs[i]->config + PCI_VENDOR_ID)) {
+            error_setg(errp, "SR-IOV VF vendor ID mismatches with PF");
+            return -1;
+        }
+
+        if (vf_dev_id != pci_get_word(vfs[i]->config + PCI_DEVICE_ID)) {
+            error_setg(errp, "inconsistent SR-IOV VF device IDs");
+            return -1;
+        }
+
+        for (size_t j = 0; j < PCI_NUM_REGIONS; j++) {
+            if (vfs[i]->io_regions[j].size != vfs[0]->io_regions[j].size ||
+                vfs[i]->io_regions[j].type != vfs[0]->io_regions[j].type) {
+                error_setg(errp, "inconsistent SR-IOV BARs");
+                return -1;
+            }
+        }
+
+        if (vfs[i]->devfn - vfs[0]->devfn != vf_stride * i) {
+            error_setg(errp, "inconsistent SR-IOV stride");
+            return -1;
+        }
+    }
+
+    if (!pcie_sriov_pf_init_common(dev, offset, vf_dev_id, pf->len,
+                                   pf->len, vf_offset, vf_stride, errp)) {
+        return -1;
+    }
+
+    for (i = 0; i < pf->len; i++) {
+        vfs[i]->exp.sriov_vf.pf = dev;
+        vfs[i]->exp.sriov_vf.vf_number = i;
+
+        /* set vid/did according to sr/iov spec - they are not used */
+        pci_config_set_vendor_id(vfs[i]->config, 0xffff);
+        pci_config_set_device_id(vfs[i]->config, 0xffff);
+    }
+
+    dev->exp.sriov_pf.vf = vfs;
+    dev->exp.sriov_pf.vf_user_created = true;
+
+    for (i = 0; i < PCI_NUM_REGIONS; i++) {
+        PCIIORegion *region = &vfs[0]->io_regions[i];
+
+        if (region->size) {
+            pcie_sriov_pf_init_vf_bar(dev, i, region->type, region->size);
+        }
+    }
+
+    return PCI_EXT_CAP_SRIOV_SIZEOF;
 }
 
-static void unregister_vfs(PCIDevice *dev)
+bool pcie_sriov_register_device(PCIDevice *dev, Error **errp)
 {
-    uint16_t i;
-    uint8_t *cfg = dev->config + dev->exp.sriov_cap;
+    if (!dev->exp.sriov_pf.vf && dev->qdev.id &&
+        pfs && g_hash_table_contains(pfs, dev->qdev.id)) {
+        error_setg(errp, "attaching user-created SR-IOV VF unsupported");
+        return false;
+    }
 
-    trace_sriov_unregister_vfs(dev->name, PCI_SLOT(dev->devfn),
-                               PCI_FUNC(dev->devfn));
-    for (i = 0; i < pci_get_word(cfg + PCI_SRIOV_TOTAL_VF); i++) {
-        pci_set_enabled(dev->exp.sriov_pf.vf[i], false);
+    if (dev->sriov_pf) {
+        PCIDevice *pci_pf;
+        GPtrArray *pf;
+
+        if (!PCI_DEVICE_GET_CLASS(dev)->sriov_vf_user_creatable) {
+            error_setg(errp, "user cannot create SR-IOV VF with this device type");
+            return false;
+        }
+
+        if (!pci_is_express(dev)) {
+            error_setg(errp, "PCI Express is required for SR-IOV VF");
+            return false;
+        }
+
+        if (!pci_qdev_find_device(dev->sriov_pf, &pci_pf)) {
+            error_setg(errp, "PCI device specified as SR-IOV PF already exists");
+            return false;
+        }
+
+        if (!pfs) {
+            pfs = g_hash_table_new_full(g_str_hash, g_str_equal, g_free, NULL);
+        }
+
+        pf = g_hash_table_lookup(pfs, dev->sriov_pf);
+        if (!pf) {
+            pf = g_ptr_array_new();
+            g_hash_table_insert(pfs, g_strdup(dev->sriov_pf), pf);
+        }
+
+        g_ptr_array_add(pf, dev);
+    }
+
+    return true;
+}
+
+void pcie_sriov_unregister_device(PCIDevice *dev)
+{
+    if (dev->sriov_pf && pfs) {
+        GPtrArray *pf = g_hash_table_lookup(pfs, dev->sriov_pf);
+
+        if (pf) {
+            g_ptr_array_remove_fast(pf, dev);
+
+            if (!pf->len) {
+                g_hash_table_remove(pfs, dev->sriov_pf);
+                g_ptr_array_free(pf, FALSE);
+            }
+        }
     }
 }
 
@@ -306,7 +490,7 @@ void pcie_sriov_pf_add_sup_pgsize(PCIDevice *dev, uint16_t opt_sup_pgsize)
 
 uint16_t pcie_sriov_vf_number(PCIDevice *dev)
 {
-    assert(pci_is_vf(dev));
+    assert(dev->exp.sriov_vf.pf);
     return dev->exp.sriov_vf.vf_number;
 }
 

hw/riscv/virt-acpi-build.c

@@ -141,12 +141,36 @@ static void acpi_dsdt_add_cpus(Aml *scope, RISCVVirtState *s)
     }
 }
 
+static void acpi_dsdt_add_plic_aplic(Aml *scope, uint8_t socket_count,
+                                     uint64_t mmio_base, uint64_t mmio_size,
+                                     const char *hid)
+{
+    uint64_t plic_aplic_addr;
+    uint32_t gsi_base;
+    uint8_t  socket;
+
+    for (socket = 0; socket < socket_count; socket++) {
+        plic_aplic_addr = mmio_base + mmio_size * socket;
+        gsi_base = VIRT_IRQCHIP_NUM_SOURCES * socket;
+        Aml *dev = aml_device("IC%.02X", socket);
+        aml_append(dev, aml_name_decl("_HID", aml_string("%s", hid)));
+        aml_append(dev, aml_name_decl("_UID", aml_int(socket)));
+        aml_append(dev, aml_name_decl("_GSB", aml_int(gsi_base)));
+
+        Aml *crs = aml_resource_template();
+        aml_append(crs, aml_memory32_fixed(plic_aplic_addr, mmio_size,
+                                           AML_READ_WRITE));
+        aml_append(dev, aml_name_decl("_CRS", crs));
+        aml_append(scope, dev);
+    }
+}
+
 static void
 acpi_dsdt_add_uart(Aml *scope, const MemMapEntry *uart_memmap,
                     uint32_t uart_irq)
 {
     Aml *dev = aml_device("COM0");
-    aml_append(dev, aml_name_decl("_HID", aml_string("PNP0501")));
+    aml_append(dev, aml_name_decl("_HID", aml_string("RSCV0003")));
     aml_append(dev, aml_name_decl("_UID", aml_int(0)));
 
     Aml *crs = aml_resource_template();
@@ -411,6 +435,14 @@ static void build_dsdt(GArray *table_data,
 
     socket_count = riscv_socket_count(ms);
 
+    if (s->aia_type == VIRT_AIA_TYPE_NONE) {
+        acpi_dsdt_add_plic_aplic(scope, socket_count, memmap[VIRT_PLIC].base,
+                                 memmap[VIRT_PLIC].size, "RSCV0001");
+    } else {
+        acpi_dsdt_add_plic_aplic(scope, socket_count, memmap[VIRT_APLIC_S].base,
+                                 memmap[VIRT_APLIC_S].size, "RSCV0002");
+    }
+
     acpi_dsdt_add_uart(scope, &memmap[VIRT_UART0], UART0_IRQ);
 
     if (socket_count == 1) {

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_IN_ORDER,
     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_IN_ORDER,
     VIRTIO_F_NOTIFICATION_DATA,
     VHOST_INVALID_FEATURE_BIT
 };

hw/smbios/smbios.c

@@ -1093,6 +1093,7 @@ static bool smbios_get_tables_ep(MachineState *ms,
                        Error **errp)
 {
     unsigned i, dimm_cnt, offset;
+    MachineClass *mc = MACHINE_GET_CLASS(ms);
     ERRP_GUARD();
 
     assert(ep_type == SMBIOS_ENTRY_POINT_TYPE_32 ||
@@ -1123,12 +1124,12 @@ static bool smbios_get_tables_ep(MachineState *ms,
     smbios_build_type_9_table(errp);
     smbios_build_type_11_table();
 
-#define MAX_DIMM_SZ (16 * GiB)
-#define GET_DIMM_SZ ((i < dimm_cnt - 1) ? MAX_DIMM_SZ \
-                                        : ((current_machine->ram_size - 1) % MAX_DIMM_SZ) + 1)
+#define GET_DIMM_SZ ((i < dimm_cnt - 1) ? mc->smbios_memory_device_size \
+    : ((current_machine->ram_size - 1) % mc->smbios_memory_device_size) + 1)
 
-    dimm_cnt = QEMU_ALIGN_UP(current_machine->ram_size, MAX_DIMM_SZ) /
-               MAX_DIMM_SZ;
+    dimm_cnt = QEMU_ALIGN_UP(current_machine->ram_size,
+                             mc->smbios_memory_device_size) /
+               mc->smbios_memory_device_size;
 
     /*
      * The offset determines if we need to keep additional space between

hw/vfio/common.c

@@ -599,7 +599,7 @@ static void vfio_listener_region_add(MemoryListener *listener,
         IOMMUMemoryRegion *iommu_mr = IOMMU_MEMORY_REGION(section->mr);
         int iommu_idx;
 
-        trace_vfio_listener_region_add_iommu(iova, end);
+        trace_vfio_listener_region_add_iommu(section->mr->name, iova, end);
         /*
          * FIXME: For VFIO iommu types which have KVM acceleration to
          * avoid bouncing all map/unmaps through qemu this way, this
@@ -725,6 +725,7 @@ static void vfio_listener_region_del(MemoryListener *listener,
     if (memory_region_is_iommu(section->mr)) {
         VFIOGuestIOMMU *giommu;
 
+        trace_vfio_listener_region_del_iommu(section->mr->name);
         QLIST_FOREACH(giommu, &bcontainer->giommu_list, giommu_next) {
             if (MEMORY_REGION(giommu->iommu_mr) == section->mr &&
                 giommu->n.start == section->offset_within_region) {

hw/vfio/trace-events

@@ -95,7 +95,8 @@ vfio_region_read(char *name, int index, uint64_t addr, unsigned size, uint64_t d
 vfio_iommu_map_notify(const char *op, uint64_t iova_start, uint64_t iova_end) "iommu %s @ 0x%"PRIx64" - 0x%"PRIx64
 vfio_listener_region_skip(const char *name, uint64_t start, uint64_t end) "SKIPPING %s 0x%"PRIx64" - 0x%"PRIx64
 vfio_spapr_group_attach(int groupfd, int tablefd) "Attached groupfd %d to liobn fd %d"
-vfio_listener_region_add_iommu(uint64_t start, uint64_t end) "region_add [iommu] 0x%"PRIx64" - 0x%"PRIx64
+vfio_listener_region_add_iommu(const char* name, uint64_t start, uint64_t end) "region_add [iommu] %s 0x%"PRIx64" - 0x%"PRIx64
+vfio_listener_region_del_iommu(const char *name) "region_del [iommu] %s"
 vfio_listener_region_add_ram(uint64_t iova_start, uint64_t iova_end, void *vaddr) "region_add [ram] 0x%"PRIx64" - 0x%"PRIx64" [%p]"
 vfio_known_safe_misalignment(const char *name, uint64_t iova, uint64_t offset_within_region, uintptr_t page_size) "Region \"%s\" iova=0x%"PRIx64" offset_within_region=0x%"PRIx64" qemu_real_host_page_size=0x%"PRIxPTR
 vfio_listener_region_add_no_dma_map(const char *name, uint64_t iova, uint64_t size, uint64_t page_size) "Region \"%s\" 0x%"PRIx64" size=0x%"PRIx64" is not aligned to 0x%"PRIx64" and cannot be mapped for DMA"

hw/virtio/trace-events

@@ -116,6 +116,7 @@ virtio_iommu_get_config(uint64_t page_size_mask, uint64_t start, uint64_t end, u
 virtio_iommu_set_config(uint8_t bypass) "bypass=0x%x"
 virtio_iommu_attach(uint32_t domain_id, uint32_t ep_id) "domain=%d endpoint=%d"
 virtio_iommu_detach(uint32_t domain_id, uint32_t ep_id) "domain=%d endpoint=%d"
+virtio_iommu_detach_endpoint_from_domain(uint32_t domain_id, uint32_t ep_id) "domain=%d endpoint=%d"
 virtio_iommu_map(uint32_t domain_id, uint64_t virt_start, uint64_t virt_end, uint64_t phys_start, uint32_t flags) "domain=%d virt_start=0x%"PRIx64" virt_end=0x%"PRIx64 " phys_start=0x%"PRIx64" flags=%d"
 virtio_iommu_unmap(uint32_t domain_id, uint64_t virt_start, uint64_t virt_end) "domain=%d virt_start=0x%"PRIx64" virt_end=0x%"PRIx64
 virtio_iommu_unmap_done(uint32_t domain_id, uint64_t virt_start, uint64_t virt_end) "domain=%d virt_start=0x%"PRIx64" virt_end=0x%"PRIx64

hw/virtio/vhost-user-fs.c

@@ -33,6 +33,7 @@ static const int user_feature_bits[] = {
     VIRTIO_F_RING_PACKED,
     VIRTIO_F_IOMMU_PLATFORM,
     VIRTIO_F_RING_RESET,
+    VIRTIO_F_IN_ORDER,
     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_IN_ORDER,
     VIRTIO_F_NOTIFICATION_DATA,
     VHOST_INVALID_FEATURE_BIT
 };

hw/virtio/virtio-crypto.c

@@ -205,6 +205,7 @@ virtio_crypto_create_asym_session(VirtIOCrypto *vcrypto,
     int queue_index;
     uint32_t algo, keytype, keylen;
 
+    sreq->info.op_code = opcode;
     algo = ldl_le_p(&sess_req->para.algo);
     keytype = ldl_le_p(&sess_req->para.keytype);
     keylen = ldl_le_p(&sess_req->para.keylen);
@@ -224,7 +225,6 @@ virtio_crypto_create_asym_session(VirtIOCrypto *vcrypto,
         iov_discard_front(&iov, &out_num, keylen);
     }
 
-    sreq->info.op_code = opcode;
     asym_info = &sreq->info.u.asym_sess_info;
     asym_info->algo = algo;
     asym_info->keytype = keytype;

hw/virtio/virtio-iommu.c

@@ -308,6 +308,7 @@ static void virtio_iommu_detach_endpoint_from_domain(VirtIOIOMMUEndpoint *ep)
     if (!ep->domain) {
         return;
     }
+    trace_virtio_iommu_detach_endpoint_from_domain(domain->id, ep->id);
     g_tree_foreach(domain->mappings, virtio_iommu_notify_unmap_cb,
                    ep->iommu_mr);
     QLIST_REMOVE(ep, next);
@@ -467,26 +468,6 @@ 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;
@@ -558,8 +539,6 @@ static int virtio_iommu_set_host_iova_ranges(VirtIOIOMMU *s, PCIBus *bus,
 {
     IOMMUPciBus *sbus = g_hash_table_lookup(s->as_by_busptr, bus);
     IOMMUDevice *sdev;
-    GList *current_ranges;
-    GList *l, *tmp, *new_ranges = NULL;
     int ret = -EINVAL;
 
     if (!sbus) {
@@ -573,35 +552,10 @@ static int virtio_iommu_set_host_iova_ranges(VirtIOIOMMU *s, PCIBus *bus,
         return ret;
     }
 
-    current_ranges = sdev->host_resv_ranges;
-
-    g_assert(!sdev->probe_done);
-
-    /* check that each new resv region is included in an existing one */
     if (sdev->host_resv_ranges) {
-        range_inverse_array(iova_ranges,
-                            &new_ranges,
-                            0, UINT64_MAX);
-
-        for (tmp = new_ranges; tmp; tmp = tmp->next) {
-            Range *newr = (Range *)tmp->data;
-            bool included = false;
-
-            for (l = current_ranges; l; l = l->next) {
-                Range * r = (Range *)l->data;
-
-                if (range_contains_range(r, newr)) {
-                    included = true;
-                    break;
-                }
-            }
-            if (!included) {
-                goto error;
-            }
-        }
-        /* all new reserved ranges are included in existing ones */
-        ret = 0;
-        goto out;
+        error_setg(errp, "%s virtio-iommu does not support aliased BDF",
+                   __func__);
+        return ret;
     }
 
     range_inverse_array(iova_ranges,
@@ -610,14 +564,31 @@ static int virtio_iommu_set_host_iova_ranges(VirtIOIOMMU *s, PCIBus *bus,
     rebuild_resv_regions(sdev);
 
     return 0;
-error:
-    error_setg(errp, "%s Conflicting host reserved ranges set!",
-               __func__);
-out:
-    g_list_free_full(new_ranges, g_free);
-    return ret;
 }
 
+static void virtio_iommu_unset_host_iova_ranges(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(g_steal_pointer(&sdev->host_resv_ranges), g_free);
+    g_list_free_full(sdev->resv_regions, g_free);
+    sdev->host_resv_ranges = NULL;
+    sdev->resv_regions = NULL;
+    add_prop_resv_regions(sdev);
+}
+
+
 static bool check_page_size_mask(VirtIOIOMMU *viommu, uint64_t new_mask,
                                  Error **errp)
 {
@@ -726,9 +697,10 @@ virtio_iommu_unset_iommu_device(PCIBus *bus, void *opaque, int devfn)
     if (!hiod) {
         return;
     }
+    virtio_iommu_unset_host_iova_ranges(viommu, hiod->aliased_bus,
+                                        hiod->aliased_devfn);
 
     g_hash_table_remove(viommu->host_iommu_devices, &key);
-    virtio_iommu_device_clear(viommu, bus, devfn);
 }
 
 static const PCIIOMMUOps virtio_iommu_ops = {
@@ -815,6 +787,7 @@ static int virtio_iommu_detach(VirtIOIOMMU *s,
     if (QLIST_EMPTY(&domain->endpoint_list)) {
         g_tree_remove(s->domains, GUINT_TO_POINTER(domain->id));
     }
+    g_tree_remove(s->endpoints, GUINT_TO_POINTER(ep_id));
     return VIRTIO_IOMMU_S_OK;
 }
 
@@ -977,7 +950,6 @@ static int virtio_iommu_probe(VirtIOIOMMU *s,
     }
     buf += count;
     free -= count;
-    sdev->probe_done = true;
 
     return VIRTIO_IOMMU_S_OK;
 }

hw/virtio/virtio-net-pci.c

@@ -75,6 +75,7 @@ static void virtio_net_pci_class_init(ObjectClass *klass, void *data)
     k->device_id = PCI_DEVICE_ID_VIRTIO_NET;
     k->revision = VIRTIO_PCI_ABI_VERSION;
     k->class_id = PCI_CLASS_NETWORK_ETHERNET;
+    k->sriov_vf_user_creatable = true;
     set_bit(DEVICE_CATEGORY_NETWORK, dc->categories);
     device_class_set_props(dc, virtio_net_properties);
     vpciklass->realize = virtio_net_pci_realize;

hw/virtio/virtio-pci.c

@@ -1955,6 +1955,7 @@ static void virtio_pci_device_plugged(DeviceState *d, Error **errp)
     uint8_t *config;
     uint32_t size;
     VirtIODevice *vdev = virtio_bus_get_device(bus);
+    int16_t res;
 
     /*
      * Virtio capabilities present without
@@ -2100,6 +2101,14 @@ static void virtio_pci_device_plugged(DeviceState *d, Error **errp)
         pci_register_bar(&proxy->pci_dev, proxy->legacy_io_bar_idx,
                          PCI_BASE_ADDRESS_SPACE_IO, &proxy->bar);
     }
+
+    res = pcie_sriov_pf_init_from_user_created_vfs(&proxy->pci_dev,
+                                                   proxy->last_pcie_cap_offset,
+                                                   errp);
+    if (res > 0) {
+        proxy->last_pcie_cap_offset += res;
+        virtio_add_feature(&vdev->host_features, VIRTIO_F_SR_IOV);
+    }
 }
 
 static void virtio_pci_device_unplugged(DeviceState *d)
@@ -2187,7 +2196,7 @@ static void virtio_pci_realize(PCIDevice *pci_dev, Error **errp)
 
     if (pcie_port && pci_is_express(pci_dev)) {
         int pos;
-        uint16_t last_pcie_cap_offset = PCI_CONFIG_SPACE_SIZE;
+        proxy->last_pcie_cap_offset = PCI_CONFIG_SPACE_SIZE;
 
         pos = pcie_endpoint_cap_init(pci_dev, 0);
         assert(pos > 0);
@@ -2207,9 +2216,9 @@ static void virtio_pci_realize(PCIDevice *pci_dev, Error **errp)
         pci_set_word(pci_dev->config + pos + PCI_PM_PMC, 0x3);
 
         if (proxy->flags & VIRTIO_PCI_FLAG_AER) {
-            pcie_aer_init(pci_dev, PCI_ERR_VER, last_pcie_cap_offset,
+            pcie_aer_init(pci_dev, PCI_ERR_VER, proxy->last_pcie_cap_offset,
                           PCI_ERR_SIZEOF, NULL);
-            last_pcie_cap_offset += PCI_ERR_SIZEOF;
+            proxy->last_pcie_cap_offset += PCI_ERR_SIZEOF;
         }
 
         if (proxy->flags & VIRTIO_PCI_FLAG_INIT_DEVERR) {
@@ -2234,9 +2243,9 @@ static void virtio_pci_realize(PCIDevice *pci_dev, Error **errp)
         }
 
         if (proxy->flags & VIRTIO_PCI_FLAG_ATS) {
-            pcie_ats_init(pci_dev, last_pcie_cap_offset,
+            pcie_ats_init(pci_dev, proxy->last_pcie_cap_offset,
                           proxy->flags & VIRTIO_PCI_FLAG_ATS_PAGE_ALIGNED);
-            last_pcie_cap_offset += PCI_EXT_CAP_ATS_SIZEOF;
+            proxy->last_pcie_cap_offset += PCI_EXT_CAP_ATS_SIZEOF;
         }
 
         if (proxy->flags & VIRTIO_PCI_FLAG_INIT_FLR) {
@@ -2263,6 +2272,7 @@ static void virtio_pci_exit(PCIDevice *pci_dev)
     bool pcie_port = pci_bus_is_express(pci_get_bus(pci_dev)) &&
                      !pci_bus_is_root(pci_get_bus(pci_dev));
 
+    pcie_sriov_pf_exit(&proxy->pci_dev);
     msix_uninit_exclusive_bar(pci_dev);
     if (proxy->flags & VIRTIO_PCI_FLAG_AER && pcie_port &&
         pci_is_express(pci_dev)) {

hw/virtio/virtio.c

@@ -872,6 +872,46 @@ static void virtqueue_packed_fill(VirtQueue *vq, const VirtQueueElement *elem,
     vq->used_elems[idx].ndescs = elem->ndescs;
 }
 
+static void virtqueue_ordered_fill(VirtQueue *vq, const VirtQueueElement *elem,
+                                   unsigned int len)
+{
+    unsigned int i, steps, max_steps;
+
+    i = vq->used_idx % vq->vring.num;
+    steps = 0;
+    /*
+     * We shouldn't need to increase 'i' by more than the distance
+     * between used_idx and last_avail_idx.
+     */
+    max_steps = (vq->last_avail_idx - vq->used_idx) % vq->vring.num;
+
+    /* Search for element in vq->used_elems */
+    while (steps <= max_steps) {
+        /* Found element, set length and mark as filled */
+        if (vq->used_elems[i].index == elem->index) {
+            vq->used_elems[i].len = len;
+            vq->used_elems[i].in_order_filled = true;
+            break;
+        }
+
+        i += vq->used_elems[i].ndescs;
+        steps += vq->used_elems[i].ndescs;
+
+        if (i >= vq->vring.num) {
+            i -= vq->vring.num;
+        }
+    }
+
+    /*
+     * We should be able to find a matching VirtQueueElement in
+     * used_elems. If we don't, this is an error.
+     */
+    if (steps >= max_steps) {
+        qemu_log_mask(LOG_GUEST_ERROR, "%s: %s cannot fill buffer id %u\n",
+                      __func__, vq->vdev->name, elem->index);
+    }
+}
+
 static void virtqueue_packed_fill_desc(VirtQueue *vq,
                                        const VirtQueueElement *elem,
                                        unsigned int idx,
@@ -922,7 +962,9 @@ void virtqueue_fill(VirtQueue *vq, const VirtQueueElement *elem,
         return;
     }
 
-    if (virtio_vdev_has_feature(vq->vdev, VIRTIO_F_RING_PACKED)) {
+    if (virtio_vdev_has_feature(vq->vdev, VIRTIO_F_IN_ORDER)) {
+        virtqueue_ordered_fill(vq, elem, len);
+    } else if (virtio_vdev_has_feature(vq->vdev, VIRTIO_F_RING_PACKED)) {
         virtqueue_packed_fill(vq, elem, len, idx);
     } else {
         virtqueue_split_fill(vq, elem, len, idx);
@@ -981,6 +1023,73 @@ static void virtqueue_packed_flush(VirtQueue *vq, unsigned int count)
     }
 }
 
+static void virtqueue_ordered_flush(VirtQueue *vq)
+{
+    unsigned int i = vq->used_idx % vq->vring.num;
+    unsigned int ndescs = 0;
+    uint16_t old = vq->used_idx;
+    uint16_t new;
+    bool packed;
+    VRingUsedElem uelem;
+
+    packed = virtio_vdev_has_feature(vq->vdev, VIRTIO_F_RING_PACKED);
+
+    if (packed) {
+        if (unlikely(!vq->vring.desc)) {
+            return;
+        }
+    } else if (unlikely(!vq->vring.used)) {
+        return;
+    }
+
+    /* First expected in-order element isn't ready, nothing to do */
+    if (!vq->used_elems[i].in_order_filled) {
+        return;
+    }
+
+    /* Search for filled elements in-order */
+    while (vq->used_elems[i].in_order_filled) {
+        /*
+         * First entry for packed VQs is written last so the guest
+         * doesn't see invalid descriptors.
+         */
+        if (packed && i != vq->used_idx) {
+            virtqueue_packed_fill_desc(vq, &vq->used_elems[i], ndescs, false);
+        } else if (!packed) {
+            uelem.id = vq->used_elems[i].index;
+            uelem.len = vq->used_elems[i].len;
+            vring_used_write(vq, &uelem, i);
+        }
+
+        vq->used_elems[i].in_order_filled = false;
+        ndescs += vq->used_elems[i].ndescs;
+        i += vq->used_elems[i].ndescs;
+        if (i >= vq->vring.num) {
+            i -= vq->vring.num;
+        }
+    }
+
+    if (packed) {
+        virtqueue_packed_fill_desc(vq, &vq->used_elems[vq->used_idx], 0, true);
+        vq->used_idx += ndescs;
+        if (vq->used_idx >= vq->vring.num) {
+            vq->used_idx -= vq->vring.num;
+            vq->used_wrap_counter ^= 1;
+            vq->signalled_used_valid = false;
+        }
+    } else {
+        /* Make sure buffer is written before we update index. */
+        smp_wmb();
+        new = old + ndescs;
+        vring_used_idx_set(vq, new);
+        if (unlikely((int16_t)(new - vq->signalled_used) <
+                     (uint16_t)(new - old))) {
+            vq->signalled_used_valid = false;
+        }
+    }
+    vq->inuse -= ndescs;
+}
+
 void virtqueue_flush(VirtQueue *vq, unsigned int count)
 {
     if (virtio_device_disabled(vq->vdev)) {
@@ -988,7 +1097,9 @@ void virtqueue_flush(VirtQueue *vq, unsigned int count)
         return;
     }
 
-    if (virtio_vdev_has_feature(vq->vdev, VIRTIO_F_RING_PACKED)) {
+    if (virtio_vdev_has_feature(vq->vdev, VIRTIO_F_IN_ORDER)) {
+        virtqueue_ordered_flush(vq);
+    } else if (virtio_vdev_has_feature(vq->vdev, VIRTIO_F_RING_PACKED)) {
         virtqueue_packed_flush(vq, count);
     } else {
         virtqueue_split_flush(vq, count);
@@ -1505,7 +1616,7 @@ static void *virtqueue_alloc_element(size_t sz, unsigned out_num, unsigned in_nu
 
 static void *virtqueue_split_pop(VirtQueue *vq, size_t sz)
 {
-    unsigned int i, head, max;
+    unsigned int i, head, max, idx;
     VRingMemoryRegionCaches *caches;
     MemoryRegionCache indirect_desc_cache;
     MemoryRegionCache *desc_cache;
@@ -1629,6 +1740,13 @@ static void *virtqueue_split_pop(VirtQueue *vq, size_t sz)
         elem->in_sg[i] = iov[out_num + i];
     }
 
+    if (virtio_vdev_has_feature(vdev, VIRTIO_F_IN_ORDER)) {
+        idx = (vq->last_avail_idx - 1) % vq->vring.num;
+        vq->used_elems[idx].index = elem->index;
+        vq->used_elems[idx].len = elem->len;
+        vq->used_elems[idx].ndescs = elem->ndescs;
+    }
+
     vq->inuse++;
 
     trace_virtqueue_pop(vq, elem, elem->in_num, elem->out_num);
@@ -1762,6 +1880,13 @@ static void *virtqueue_packed_pop(VirtQueue *vq, size_t sz)
 
     elem->index = id;
     elem->ndescs = (desc_cache == &indirect_desc_cache) ? 1 : elem_entries;
+
+    if (virtio_vdev_has_feature(vdev, VIRTIO_F_IN_ORDER)) {
+        vq->used_elems[vq->last_avail_idx].index = elem->index;
+        vq->used_elems[vq->last_avail_idx].len = elem->len;
+        vq->used_elems[vq->last_avail_idx].ndescs = elem->ndescs;
+    }
+
     vq->last_avail_idx += elem->ndescs;
     vq->inuse += elem->ndescs;
 

include/exec/cpu-common.h

@@ -129,6 +129,14 @@ size_t qemu_ram_pagesize_largest(void);
  */
 void cpu_address_space_init(CPUState *cpu, int asidx,
                             const char *prefix, MemoryRegion *mr);
+/**
+ * cpu_address_space_destroy:
+ * @cpu: CPU for which address space needs to be destroyed
+ * @asidx: integer index of this address space
+ *
+ * Note that with KVM only one address space is supported.
+ */
+void cpu_address_space_destroy(CPUState *cpu, int asidx);
 
 void cpu_physical_memory_rw(hwaddr addr, void *buf,
                             hwaddr len, bool is_write);

include/exec/gdbstub.h

@@ -40,6 +40,12 @@ void gdb_register_coprocessor(CPUState *cpu,
                               gdb_get_reg_cb get_reg, gdb_set_reg_cb set_reg,
                               const GDBFeature *feature, int g_pos);
 
+/**
+ * gdb_unregister_coprocessor_all() - unregisters supplemental set of registers
+ * @cpu - the CPU associated with registers
+ */
+void gdb_unregister_coprocessor_all(CPUState *cpu);
+
 /**
  * gdbserver_start: start the gdb server
  * @port_or_device: connection spec for gdb

include/hw/acpi/cpu.h

@@ -19,6 +19,8 @@
 #include "hw/boards.h"
 #include "hw/hotplug.h"
 
+#define ACPI_CPU_HOTPLUG_REG_LEN 12
+
 typedef struct AcpiCpuStatus {
     CPUState *cpu;
     uint64_t arch_id;
@@ -61,9 +63,10 @@ typedef void (*build_madt_cpu_fn)(int uid, const CPUArchIdList *apic_ids,
                                   GArray *entry, bool force_enabled);
 
 void build_cpus_aml(Aml *table, MachineState *machine, CPUHotplugFeatures opts,
-                    build_madt_cpu_fn build_madt_cpu, hwaddr io_base,
+                    build_madt_cpu_fn build_madt_cpu, hwaddr base_addr,
                     const char *res_root,
-                    const char *event_handler_method);
+                    const char *event_handler_method,
+                    AmlRegionSpace rs);
 
 void acpi_cpu_ospm_status(CPUHotplugState *cpu_st, ACPIOSTInfoList ***list);
 

include/hw/acpi/generic_event_device.h

@@ -62,6 +62,7 @@
 #include "hw/sysbus.h"
 #include "hw/acpi/memory_hotplug.h"
 #include "hw/acpi/ghes.h"
+#include "hw/acpi/cpu.h"
 #include "qom/object.h"
 
 #define ACPI_POWER_BUTTON_DEVICE "PWRB"
@@ -86,6 +87,7 @@ OBJECT_DECLARE_SIMPLE_TYPE(AcpiGedState, ACPI_GED)
 #define GED_DEVICE      "GED"
 #define AML_GED_EVT_REG "EREG"
 #define AML_GED_EVT_SEL "ESEL"
+#define AML_GED_EVT_CPU_SCAN_METHOD "\\_SB.GED.CSCN"
 
 /*
  * Platforms need to specify the GED event bitmap
@@ -95,6 +97,7 @@ OBJECT_DECLARE_SIMPLE_TYPE(AcpiGedState, ACPI_GED)
 #define ACPI_GED_MEM_HOTPLUG_EVT   0x1
 #define ACPI_GED_PWR_DOWN_EVT      0x2
 #define ACPI_GED_NVDIMM_HOTPLUG_EVT 0x4
+#define ACPI_GED_CPU_HOTPLUG_EVT    0x8
 
 typedef struct GEDState {
     MemoryRegion evt;
@@ -106,6 +109,8 @@ struct AcpiGedState {
     SysBusDevice parent_obj;
     MemHotplugState memhp_state;
     MemoryRegion container_memhp;
+    CPUHotplugState cpuhp_state;
+    MemoryRegion container_cpuhp;
     GEDState ged_state;
     uint32_t ged_event_bitmap;
     qemu_irq irq;

include/hw/boards.h

@@ -237,6 +237,9 @@ typedef struct {
  *    purposes only.
  *    Applies only to default memory backend, i.e., explicit memory backend
  *    wasn't used.
+ * @smbios_memory_device_size:
+ *    Default size of memory device,
+ *    SMBIOS 3.1.0 "7.18 Memory Device (Type 17)"
  */
 struct MachineClass {
     /*< private >*/
@@ -304,6 +307,7 @@ struct MachineClass {
     const CPUArchIdList *(*possible_cpu_arch_ids)(MachineState *machine);
     int64_t (*get_default_cpu_node_id)(const MachineState *ms, int idx);
     ram_addr_t (*fixup_ram_size)(ram_addr_t size);
+    uint64_t smbios_memory_device_size;
 };
 
 /**

include/hw/core/cpu.h

@@ -496,6 +496,7 @@ struct CPUState {
     QSIMPLEQ_HEAD(, qemu_work_item) work_list;
 
     struct CPUAddressSpace *cpu_ases;
+    int cpu_ases_count;
     int num_ases;
     AddressSpace *as;
     MemoryRegion *memory;

include/hw/cxl/cxl_device.h

@@ -181,6 +181,21 @@ typedef struct CXLCCI {
         uint64_t runtime;
         QEMUTimer *timer;
     } bg;
+
+    /* firmware update */
+    struct {
+        uint8_t active_slot;
+        uint8_t staged_slot;
+        bool slot[4];
+        uint8_t curr_action;
+        uint8_t curr_slot;
+        /* handle partial transfers */
+        bool transferring;
+        size_t prev_offset;
+        size_t prev_len;
+        time_t last_partxfer;
+    } fw;
+
     size_t payload_max;
     /* Pointer to device hosting the CCI */
     DeviceState *d;
@@ -397,9 +412,14 @@ static inline void __toggle_media(CXLDeviceState *cxl_dstate, int val)
 #define cxl_dev_enable_media(cxlds)                     \
         do { __toggle_media((cxlds), 0x1); } while (0)
 
-static inline bool sanitize_running(CXLCCI *cci)
+static inline bool cxl_dev_media_disabled(CXLDeviceState *cxl_dstate)
 {
-    return !!cci->bg.runtime && cci->bg.opcode == 0x4400;
+    uint64_t dev_status_reg = cxl_dstate->mbox_reg_state64[R_CXL_MEM_DEV_STS];
+    return FIELD_EX64(dev_status_reg, CXL_MEM_DEV_STS, MEDIA_STATUS) == 0x3;
+}
+static inline bool scan_media_running(CXLCCI *cci)
+{
+    return !!cci->bg.runtime && cci->bg.opcode == 0x4304;
 }
 
 typedef struct CXLError {
@@ -422,6 +442,47 @@ typedef struct CXLPoison {
 typedef QLIST_HEAD(, CXLPoison) CXLPoisonList;
 #define CXL_POISON_LIST_LIMIT 256
 
+/* CXL memory device patrol scrub control attributes */
+typedef struct CXLMemPatrolScrubReadAttrs {
+        uint8_t scrub_cycle_cap;
+        uint16_t scrub_cycle;
+        uint8_t scrub_flags;
+} QEMU_PACKED CXLMemPatrolScrubReadAttrs;
+
+typedef struct CXLMemPatrolScrubWriteAttrs {
+    uint8_t scrub_cycle_hr;
+    uint8_t scrub_flags;
+} QEMU_PACKED CXLMemPatrolScrubWriteAttrs;
+
+#define CXL_MEMDEV_PS_GET_FEATURE_VERSION    0x01
+#define CXL_MEMDEV_PS_SET_FEATURE_VERSION    0x01
+#define CXL_MEMDEV_PS_SCRUB_CYCLE_CHANGE_CAP_DEFAULT    BIT(0)
+#define CXL_MEMDEV_PS_SCRUB_REALTIME_REPORT_CAP_DEFAULT    BIT(1)
+#define CXL_MEMDEV_PS_CUR_SCRUB_CYCLE_DEFAULT    12
+#define CXL_MEMDEV_PS_MIN_SCRUB_CYCLE_DEFAULT    1
+#define CXL_MEMDEV_PS_ENABLE_DEFAULT    0
+
+/* CXL memory device DDR5 ECS control attributes */
+typedef struct CXLMemECSReadAttrs {
+        uint8_t ecs_log_cap;
+        uint8_t ecs_cap;
+        uint16_t ecs_config;
+        uint8_t ecs_flags;
+} QEMU_PACKED CXLMemECSReadAttrs;
+
+typedef struct CXLMemECSWriteAttrs {
+   uint8_t ecs_log_cap;
+    uint16_t ecs_config;
+} QEMU_PACKED CXLMemECSWriteAttrs;
+
+#define CXL_ECS_GET_FEATURE_VERSION    0x01
+#define CXL_ECS_SET_FEATURE_VERSION    0x01
+#define CXL_ECS_LOG_ENTRY_TYPE_DEFAULT    0x01
+#define CXL_ECS_REALTIME_REPORT_CAP_DEFAULT    1
+#define CXL_ECS_THRESHOLD_COUNT_DEFAULT    3 /* 3: 256, 4: 1024, 5: 4096 */
+#define CXL_ECS_MODE_DEFAULT    0
+#define CXL_ECS_NUM_MEDIA_FRUS   3 /* Default */
+
 #define DCD_MAX_NUM_REGION 8
 
 typedef struct CXLDCExtentRaw {
@@ -459,6 +520,14 @@ typedef struct CXLDCRegion {
     unsigned long *blk_bitmap;
 } CXLDCRegion;
 
+typedef struct CXLSetFeatureInfo {
+    QemuUUID uuid;
+    uint8_t data_transfer_flag;
+    bool data_saved_across_reset;
+    uint16_t data_offset;
+    size_t data_size;
+} CXLSetFeatureInfo;
+
 struct CXLType3Dev {
     /* Private */
     PCIDevice parent_obj;
@@ -491,6 +560,19 @@ struct CXLType3Dev {
     unsigned int poison_list_cnt;
     bool poison_list_overflowed;
     uint64_t poison_list_overflow_ts;
+    /* Poison Injection - backup */
+    CXLPoisonList poison_list_bkp;
+    CXLPoisonList scan_media_results;
+    bool scan_media_hasrun;
+
+    CXLSetFeatureInfo set_feat_info;
+
+    /* Patrol scrub control attributes */
+    CXLMemPatrolScrubReadAttrs patrol_scrub_attrs;
+    CXLMemPatrolScrubWriteAttrs patrol_scrub_wr_attrs;
+    /* ECS control attributes */
+    CXLMemECSReadAttrs ecs_attrs[CXL_ECS_NUM_MEDIA_FRUS];
+    CXLMemECSWriteAttrs ecs_wr_attrs[CXL_ECS_NUM_MEDIA_FRUS];
 
     struct dynamic_capacity {
         HostMemoryBackend *host_dc;
@@ -554,10 +636,12 @@ CXLRetCode cxl_event_get_records(CXLDeviceState *cxlds, CXLGetEventPayload *pl,
                                  size_t *len);
 CXLRetCode cxl_event_clear_records(CXLDeviceState *cxlds,
                                    CXLClearEventPayload *pl);
+void cxl_discard_all_event_records(CXLDeviceState *cxlds);
 
 void cxl_event_irq_assert(CXLType3Dev *ct3d);
 
 void cxl_set_poison_list_overflowed(CXLType3Dev *ct3d);
+void cxl_clear_poison_list_overflowed(CXLType3Dev *ct3d);
 
 CXLDCRegion *cxl_find_dc_region(CXLType3Dev *ct3d, uint64_t dpa, uint64_t len);
 

include/hw/cxl/cxl_mailbox.h

@@ -0,0 +1,18 @@
+/*
+ * QEMU CXL Mailbox
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2. See the
+ * COPYING file in the top-level directory.
+ */
+
+#ifndef CXL_MAILBOX_H
+#define CXL_MAILBOX_H
+
+#define CXL_MBOX_IMMEDIATE_CONFIG_CHANGE (1 << 1)
+#define CXL_MBOX_IMMEDIATE_DATA_CHANGE (1 << 2)
+#define CXL_MBOX_IMMEDIATE_POLICY_CHANGE (1 << 3)
+#define CXL_MBOX_IMMEDIATE_LOG_CHANGE (1 << 4)
+#define CXL_MBOX_SECURITY_STATE_CHANGE (1 << 5)
+#define CXL_MBOX_BACKGROUND_OPERATION (1 << 6)
+
+#endif

include/hw/pci/pci_device.h

@@ -3,6 +3,7 @@
 
 #include "hw/pci/pci.h"
 #include "hw/pci/pcie.h"
+#include "hw/pci/pcie_doe.h"
 
 #define TYPE_PCI_DEVICE "pci-device"
 typedef struct PCIDeviceClass PCIDeviceClass;
@@ -37,6 +38,8 @@ struct PCIDeviceClass {
     uint16_t subsystem_id;              /* only for header type = 0 */
 
     const char *romfile;                /* rom bar */
+
+    bool sriov_vf_user_creatable;
 };
 
 enum PCIReqIDType {
@@ -157,9 +160,17 @@ struct PCIDevice {
     MSIVectorReleaseNotifier msix_vector_release_notifier;
     MSIVectorPollNotifier msix_vector_poll_notifier;
 
+    /* SPDM */
+    uint16_t spdm_port;
+
+    /* DOE */
+    DOECap doe_spdm;
+
     /* ID of standby device in net_failover pair */
     char *failover_pair_id;
     uint32_t acpi_index;
+
+    char *sriov_pf;
 };
 
 static inline int pci_intx(PCIDevice *pci_dev)
@@ -192,7 +203,7 @@ static inline int pci_is_express_downstream_port(const PCIDevice *d)
 
 static inline int pci_is_vf(const PCIDevice *d)
 {
-    return d->exp.sriov_vf.pf != NULL;
+    return d->sriov_pf || d->exp.sriov_vf.pf != NULL;
 }
 
 static inline uint32_t pci_config_size(const PCIDevice *d)

include/hw/pci/pcie_doe.h

@@ -46,6 +46,8 @@ REG32(PCI_DOE_CAP_STATUS, 0)
 
 /* PCI-SIG defined Data Object Types - r6.0 Table 6-32 */
 #define PCI_SIG_DOE_DISCOVERY       0x00
+#define PCI_SIG_DOE_CMA             0x01
+#define PCI_SIG_DOE_SECURED_CMA     0x02
 
 #define PCI_DOE_DW_SIZE_MAX         (1 << 18)
 #define PCI_DOE_PROTOCOL_NUM_MAX    256
@@ -106,6 +108,9 @@ struct DOECap {
     /* Protocols and its callback response */
     DOEProtocol *protocols;
     uint16_t protocol_num;
+
+    /* Used for spdm-socket */
+    int spdm_socket;
 };
 
 void pcie_doe_init(PCIDevice *pdev, DOECap *doe_cap, uint16_t offset,

include/hw/pci/pcie_sriov.h

@@ -18,6 +18,7 @@
 typedef struct PCIESriovPF {
     uint8_t vf_bar_type[PCI_NUM_REGIONS];   /* Store type for each VF bar */
     PCIDevice **vf;     /* Pointer to an array of num_vfs VF devices */
+    bool vf_user_created; /* If VFs are created by user */
 } PCIESriovPF;
 
 typedef struct PCIESriovVF {
@@ -40,6 +41,23 @@ void pcie_sriov_pf_init_vf_bar(PCIDevice *dev, int region_num,
 void pcie_sriov_vf_register_bar(PCIDevice *dev, int region_num,
                                 MemoryRegion *memory);
 
+/**
+ * pcie_sriov_pf_init_from_user_created_vfs() - Initialize PF with user-created
+ *                                              VFs.
+ * @dev: A PCIe device being realized.
+ * @offset: The offset of the SR-IOV capability.
+ * @errp: pointer to Error*, to store an error if it happens.
+ *
+ * Return: The size of added capability. 0 if the user did not create VFs.
+ *         -1 if failed.
+ */
+int16_t pcie_sriov_pf_init_from_user_created_vfs(PCIDevice *dev,
+                                                 uint16_t offset,
+                                                 Error **errp);
+
+bool pcie_sriov_register_device(PCIDevice *dev, Error **errp);
+void pcie_sriov_unregister_device(PCIDevice *dev);
+
 /*
  * Default (minimal) page size support values
  * as required by the SR/IOV standard:

include/hw/virtio/virtio-iommu.h

@@ -43,7 +43,6 @@ typedef struct IOMMUDevice {
     MemoryRegion bypass_mr;     /* The alias of shared memory MR */
     GList *resv_regions;
     GList *host_resv_ranges;
-    bool probe_done;
 } IOMMUDevice;
 
 typedef struct IOMMUPciBus {

include/hw/virtio/virtio-pci.h

@@ -152,6 +152,7 @@ struct VirtIOPCIProxy {
     uint32_t modern_io_bar_idx;
     uint32_t modern_mem_bar_idx;
     int config_cap;
+    uint16_t last_pcie_cap_offset;
     uint32_t flags;
     bool disable_modern;
     bool ignore_backend_features;

include/hw/virtio/virtio.h

@@ -69,6 +69,8 @@ typedef struct VirtQueueElement
     unsigned int ndescs;
     unsigned int out_num;
     unsigned int in_num;
+    /* Element has been processed (VIRTIO_F_IN_ORDER) */
+    bool in_order_filled;
     hwaddr *in_addr;
     hwaddr *out_addr;
     struct iovec *in_sg;
@@ -371,7 +373,9 @@ typedef struct VirtIORNGConf VirtIORNGConf;
     DEFINE_PROP_BIT64("packed", _state, _field, \
                       VIRTIO_F_RING_PACKED, false), \
     DEFINE_PROP_BIT64("queue_reset", _state, _field, \
-                      VIRTIO_F_RING_RESET, true)
+                      VIRTIO_F_RING_RESET, true), \
+    DEFINE_PROP_BIT64("in_order", _state, _field, \
+                      VIRTIO_F_IN_ORDER, false)
 
 hwaddr virtio_queue_get_desc_addr(VirtIODevice *vdev, int n);
 bool virtio_queue_enabled_legacy(VirtIODevice *vdev, int n);

include/sysemu/kvm.h

@@ -313,6 +313,31 @@ int kvm_create_device(KVMState *s, uint64_t type, bool test);
  */
 bool kvm_device_supported(int vmfd, uint64_t type);
 
+/**
+ * kvm_create_vcpu - Gets a parked KVM vCPU or creates a KVM vCPU
+ * @cpu: QOM CPUState object for which KVM vCPU has to be fetched/created.
+ *
+ * @returns: 0 when success, errno (<0) when failed.
+ */
+int kvm_create_vcpu(CPUState *cpu);
+
+/**
+ * kvm_park_vcpu - Park QEMU KVM vCPU context
+ * @cpu: QOM CPUState object for which QEMU KVM vCPU context has to be parked.
+ *
+ * @returns: none
+ */
+void kvm_park_vcpu(CPUState *cpu);
+
+/**
+ * kvm_unpark_vcpu - unpark QEMU KVM vCPU context
+ * @s: KVM State
+ * @vcpu_id: Architecture vCPU ID of the parked vCPU
+ *
+ * @returns: KVM fd
+ */
+int kvm_unpark_vcpu(KVMState *s, unsigned long vcpu_id);
+
 /* Arch specific hooks */
 
 extern const KVMCapabilityInfo kvm_arch_required_capabilities[];

include/sysemu/spdm-socket.h

@@ -0,0 +1,74 @@
+/*
+ * QEMU SPDM socket support
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a copy
+ * of this software and associated documentation files (the "Software"), to deal
+ * in the Software without restriction, including without limitation the rights
+ * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+ * copies of the Software, and to permit persons to whom the Software is
+ * furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+ * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+ * THE SOFTWARE.
+ */
+
+#ifndef SPDM_REQUESTER_H
+#define SPDM_REQUESTER_H
+
+/**
+ * spdm_socket_connect: connect to an external SPDM socket
+ * @port: port to connect to
+ * @errp: error object handle
+ *
+ * This will connect to an external SPDM socket server. On error
+ * it will return -1 and errp will be set. On success this function
+ * will return the socket number.
+ */
+int spdm_socket_connect(uint16_t port, Error **errp);
+
+/**
+ * spdm_socket_rsp: send and receive a message to a SPDM server
+ * @socket: socket returned from spdm_socket_connect()
+ * @transport_type: SPDM_SOCKET_TRANSPORT_TYPE_* macro
+ * @req: request buffer
+ * @req_len: request buffer length
+ * @rsp: response buffer
+ * @rsp_len: response buffer length
+ *
+ * Send platform data to a SPDM server on socket and then receive
+ * a response.
+ */
+uint32_t spdm_socket_rsp(const int socket, uint32_t transport_type,
+                         void *req, uint32_t req_len,
+                         void *rsp, uint32_t rsp_len);
+
+/**
+ * spdm_socket_close: send a shutdown command to the server
+ * @socket: socket returned from spdm_socket_connect()
+ * @transport_type: SPDM_SOCKET_TRANSPORT_TYPE_* macro
+ *
+ * This will issue a shutdown command to the server.
+ */
+void spdm_socket_close(const int socket, uint32_t transport_type);
+
+#define SPDM_SOCKET_COMMAND_NORMAL                0x0001
+#define SPDM_SOCKET_COMMAND_OOB_ENCAP_KEY_UPDATE  0x8001
+#define SPDM_SOCKET_COMMAND_CONTINUE              0xFFFD
+#define SPDM_SOCKET_COMMAND_SHUTDOWN              0xFFFE
+#define SPDM_SOCKET_COMMAND_UNKOWN                0xFFFF
+#define SPDM_SOCKET_COMMAND_TEST                  0xDEAD
+
+#define SPDM_SOCKET_TRANSPORT_TYPE_MCTP           0x01
+#define SPDM_SOCKET_TRANSPORT_TYPE_PCI_DOE        0x02
+
+#define SPDM_SOCKET_MAX_MESSAGE_BUFFER_SIZE       0x1200
+
+#endif

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_IN_ORDER,
     VIRTIO_F_NOTIFICATION_DATA,
     VIRTIO_NET_F_CSUM,
     VIRTIO_NET_F_CTRL_GUEST_OFFLOADS,

system/physmem.c

@@ -763,6 +763,7 @@ void cpu_address_space_init(CPUState *cpu, int asidx,
 
     if (!cpu->cpu_ases) {
         cpu->cpu_ases = g_new0(CPUAddressSpace, cpu->num_ases);
+        cpu->cpu_ases_count = cpu->num_ases;
     }
 
     newas = &cpu->cpu_ases[asidx];
@@ -776,6 +777,34 @@ void cpu_address_space_init(CPUState *cpu, int asidx,
     }
 }
 
+void cpu_address_space_destroy(CPUState *cpu, int asidx)
+{
+    CPUAddressSpace *cpuas;
+
+    assert(cpu->cpu_ases);
+    assert(asidx >= 0 && asidx < cpu->num_ases);
+    /* KVM cannot currently support multiple address spaces. */
+    assert(asidx == 0 || !kvm_enabled());
+
+    cpuas = &cpu->cpu_ases[asidx];
+    if (tcg_enabled()) {
+        memory_listener_unregister(&cpuas->tcg_as_listener);
+    }
+
+    address_space_destroy(cpuas->as);
+    g_free_rcu(cpuas->as, rcu);
+
+    if (asidx == 0) {
+        /* reset the convenience alias for address space 0 */
+        cpu->as = NULL;
+    }
+
+    if (--cpu->cpu_ases_count == 0) {
+        g_free(cpu->cpu_ases);
+        cpu->cpu_ases = NULL;
+    }
+}
+
 AddressSpace *cpu_get_address_space(CPUState *cpu, int asidx)
 {
     /* Return the AddressSpace corresponding to the specified index */

tests/qtest/bios-tables-test.c

@@ -267,15 +267,6 @@ static void dump_aml_files(test_data *data, bool rebuild)
                                        data->arch, data->machine,
                                        sdt->aml, ext);
 
-            /*
-             * To keep test cases not failing before the DATA files are moved to
-             * ${arch}/${machine} folder, add this check as well.
-             */
-            if (!g_file_test(aml_file, G_FILE_TEST_EXISTS)) {
-                aml_file = g_strdup_printf("%s/%s/%.4s%s", data_dir,
-                                           data->machine, sdt->aml, ext);
-            }
-
             if (!g_file_test(aml_file, G_FILE_TEST_EXISTS) &&
                 sdt->aml_len == exp_sdt->aml_len &&
                 !memcmp(sdt->aml, exp_sdt->aml, sdt->aml_len)) {
@@ -412,11 +403,6 @@ static GArray *load_expected_aml(test_data *data)
 try_again:
         aml_file = g_strdup_printf("%s/%s/%s/%.4s%s", data_dir, data->arch,
                                    data->machine, sdt->aml, ext);
-        if (!g_file_test(aml_file, G_FILE_TEST_EXISTS)) {
-            aml_file = g_strdup_printf("%s/%s/%.4s%s", data_dir, data->machine,
-                                       sdt->aml, ext);
-        }
-
         if (verbosity_level >= 2) {
             fprintf(stderr, "Looking for expected file '%s'\n", aml_file);
         }
@@ -1977,6 +1963,28 @@ static void test_acpi_microvm_acpi_erst(void)
 }
 #endif /* CONFIG_POSIX */
 
+static void test_acpi_riscv64_virt_tcg(void)
+{
+    test_data data = {
+        .machine = "virt",
+        .arch = "riscv64",
+        .tcg_only = true,
+        .uefi_fl1 = "pc-bios/edk2-riscv-code.fd",
+        .uefi_fl2 = "pc-bios/edk2-riscv-vars.fd",
+        .cd = "tests/data/uefi-boot-images/bios-tables-test.riscv64.iso.qcow2",
+        .ram_start = 0x80000000ULL,
+        .scan_len = 128ULL * 1024 * 1024,
+    };
+
+    /*
+     * RHCT will have ISA string encoded. To reduce the effort
+     * of updating expected AML file for any new default ISA extension,
+     * use the profile rva22s64.
+     */
+    test_acpi_one("-cpu rva22s64 ", &data);
+    free_test_data(&data);
+}
+
 static void test_acpi_aarch64_virt_tcg(void)
 {
     test_data data = {
@@ -2455,6 +2463,10 @@ int main(int argc, char *argv[])
                 qtest_add_func("acpi/virt/viot", test_acpi_aarch64_virt_viot);
             }
         }
+    } else if (strcmp(arch, "riscv64") == 0) {
+        if (has_tcg && qtest_has_device("virtio-blk-pci")) {
+            qtest_add_func("acpi/virt", test_acpi_riscv64_virt_tcg);
+        }
     }
     ret = g_test_run();
     boot_sector_cleanup(disk);